0 files changed, 0 insertions, 0 deletions
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7b71dd74baeb..fbf0c3a65f59 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -8,6 +8,7 @@
 #ifndef _LINUX_ACPI_H
 #define _LINUX_ACPI_H
 
+#include <linux/cleanup.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>	/* for struct resource */
 #include <linux/resource_ext.h>
@@ -15,6 +16,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/property.h>
 #include <linux/uuid.h>
+#include <linux/node.h>
 
 struct irq_domain;
 struct irq_domain_ops;
@@ -23,6 +25,7 @@ struct irq_domain_ops;
 #define _LINUX
 #endif
 #include <acpi/acpi.h>
+#include <acpi/acpi_numa.h>
 
 #ifdef	CONFIG_ACPI
 
@@ -30,13 +33,23 @@ struct irq_domain_ops;
 #include <linux/dynamic_debug.h>
 #include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/fw_table.h>
 
 #include <acpi/acpi_bus.h>
 #include <acpi/acpi_drivers.h>
-#include <acpi/acpi_numa.h>
 #include <acpi/acpi_io.h>
 #include <asm/acpi.h>
 
+#ifdef CONFIG_ACPI_TABLE_LIB
+#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "ACPI")
+#define __init_or_acpilib
+#define __initdata_or_acpilib
+#else
+#define EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_acpilib __init
+#define __initdata_or_acpilib __initdata
+#endif
+
 static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
 {
 	return adev ? adev->handle : NULL;
@@ -70,19 +83,6 @@ static inline void acpi_free_fwnode_static(struct fwnode_handle *fwnode)
 	kfree(fwnode);
 }
 
-/**
- * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with
- * the PCI-defined class-code information
- *
- * @_cls : the class, subclass, prog-if triple for this device
- * @_msk : the class mask for this device
- *
- * This macro is used to create a struct acpi_device_id that matches a
- * specific PCI class. The .id and .driver_data fields will be left
- * initialized with the default value.
- */
-#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (_cls), .cls_msk = (_msk),
-
 static inline bool has_acpi_companion(struct device *dev)
 {
 	return is_acpi_device_node(dev->fwnode);
@@ -108,6 +108,7 @@ enum acpi_irq_model_id {
 	ACPI_IRQ_MODEL_PLATFORM,
 	ACPI_IRQ_MODEL_GIC,
 	ACPI_IRQ_MODEL_LPIC,
+	ACPI_IRQ_MODEL_RINTC,
 	ACPI_IRQ_MODEL_COUNT
 };
 
@@ -132,21 +133,8 @@ enum acpi_address_range_id {
 
 
 /* Table Handlers */
-union acpi_subtable_headers {
-	struct acpi_subtable_header common;
-	struct acpi_hmat_structure hmat;
-	struct acpi_prmt_module_header prmt;
-	struct acpi_cedt_header cedt;
-};
-
 typedef int (*acpi_tbl_table_handler)(struct acpi_table_header *table);
 
-typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header,
-				      const unsigned long end);
-
-typedef int (*acpi_tbl_entry_handler_arg)(union acpi_subtable_headers *header,
-					  void *arg, const unsigned long end);
-
 /* Debugger support */
 
 struct acpi_debugger_ops {
@@ -220,14 +208,6 @@ static inline int acpi_debugger_notify_command_complete(void)
 		(!entry) || (unsigned long)entry + sizeof(*entry) > end ||  \
 		((struct acpi_subtable_header *)entry)->length < sizeof(*entry))
 
-struct acpi_subtable_proc {
-	int id;
-	acpi_tbl_entry_handler handler;
-	acpi_tbl_entry_handler_arg handler_arg;
-	void *arg;
-	int count;
-};
-
 void __iomem *__acpi_map_table(unsigned long phys, unsigned long size);
 void __acpi_unmap_table(void __iomem *map, unsigned long size);
 int early_acpi_boot_init(void);
@@ -242,15 +222,16 @@ void acpi_reserve_initial_tables (void);
 void acpi_table_init_complete (void);
 int acpi_table_init (void);
 
-#ifdef CONFIG_ACPI_TABLE_LIB
-#define EXPORT_SYMBOL_ACPI_LIB(x) EXPORT_SYMBOL_NS_GPL(x, ACPI)
-#define __init_or_acpilib
-#define __initdata_or_acpilib
-#else
-#define EXPORT_SYMBOL_ACPI_LIB(x)
-#define __init_or_acpilib __init
-#define __initdata_or_acpilib __initdata
-#endif
+static inline struct acpi_table_header *acpi_get_table_pointer(char *signature, u32 instance)
+{
+	struct acpi_table_header *table;
+	int status = acpi_get_table(signature, instance, &table);
+
+	if (ACPI_FAILURE(status))
+		return ERR_PTR(-ENOENT);
+	return table;
+}
+DEFINE_FREE(acpi_put_table, struct acpi_table_header *, if (!IS_ERR_OR_NULL(_T)) acpi_put_table(_T))
 
 int acpi_table_parse(char *id, acpi_tbl_table_handler handler);
 int __init_or_acpilib acpi_table_parse_entries(char *id,
@@ -269,10 +250,7 @@ acpi_table_parse_cedt(enum acpi_cedt_type id,
 int acpi_parse_mcfg (struct acpi_table_header *header);
 void acpi_table_print_madt_entry (struct acpi_subtable_header *madt);
 
-/* the following numa functions are architecture-dependent */
-void acpi_numa_slit_init (struct acpi_table_slit *slit);
-
-#if defined(CONFIG_X86) || defined(CONFIG_IA64) || defined(CONFIG_LOONGARCH)
+#if defined(CONFIG_X86) || defined(CONFIG_LOONGARCH)
 void acpi_numa_processor_affinity_init (struct acpi_srat_cpu_affinity *pa);
 #else
 static inline void
@@ -294,7 +272,11 @@ static inline void
 acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) { }
 #endif
 
-int acpi_numa_memory_affinity_init (struct acpi_srat_mem_affinity *ma);
+#ifdef CONFIG_RISCV
+void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa);
+#else
+static inline void acpi_numa_rintc_affinity_init(struct acpi_srat_rintc_affinity *pa) { }
+#endif
 
 #ifndef PHYS_CPUID_INVALID
 typedef u32 phys_cpuid_t;
@@ -311,6 +293,9 @@ static inline bool invalid_phys_cpuid(phys_cpuid_t phys_id)
 	return phys_id == PHYS_CPUID_INVALID;
 }
 
+
+int __init acpi_get_madt_revision(void);
+
 /* Validate the processor object's proc_id */
 bool acpi_duplicate_processor_id(int proc_id);
 /* Processor _CTS control */
@@ -336,6 +321,8 @@ int acpi_map_cpu(acpi_handle handle, phys_cpuid_t physid, u32 acpi_id,
 int acpi_unmap_cpu(int cpu);
 #endif /* CONFIG_ACPI_HOTPLUG_CPU */
 
+acpi_handle acpi_get_processor_handle(int cpu);
+
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
 int acpi_get_ioapic_id(acpi_handle handle, u32 gsi_base, u64 *phys_addr);
 #endif
@@ -355,14 +342,16 @@ static inline bool acpi_sci_irq_valid(void)
 }
 
 extern int sbf_port;
-extern unsigned long acpi_realmode_flags;
 
 int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
 int acpi_isa_irq_to_gsi (unsigned isa_irq, u32 *gsi);
 
+typedef struct fwnode_handle *(*acpi_gsi_domain_disp_fn)(u32);
+
 void acpi_set_irq_model(enum acpi_irq_model_id model,
-			struct fwnode_handle *(*)(u32));
+			acpi_gsi_domain_disp_fn fn);
+acpi_gsi_domain_disp_fn acpi_get_gsi_dispatcher(void);
 void acpi_set_gsi_to_irq_fallback(u32 (*)(u32));
 
 struct irq_domain *acpi_irq_create_hierarchy(unsigned int flags,
@@ -388,6 +377,7 @@ void acpi_unregister_gsi (u32 gsi);
 
 struct pci_dev;
 
+struct acpi_prt_entry *acpi_pci_irq_lookup(struct pci_dev *dev, int pin);
 int acpi_pci_irq_enable (struct pci_dev *dev);
 void acpi_penalize_isa_irq(int irq, int active);
 bool acpi_isa_irq_available(int irq);
@@ -412,7 +402,9 @@ extern bool acpi_is_pnp_device(struct acpi_device *);
 
 #if defined(CONFIG_ACPI_WMI) || defined(CONFIG_ACPI_WMI_MODULE)
 
-typedef void (*wmi_notify_handler) (u32 value, void *context);
+typedef void (*wmi_notify_handler) (union acpi_object *data, void *context);
+
+int wmi_instance_count(const char *guid);
 
 extern acpi_status wmi_evaluate_method(const char *guid, u8 instance,
 					u32 method_id,
@@ -425,7 +417,6 @@ extern acpi_status wmi_set_block(const char *guid, u8 instance,
 extern acpi_status wmi_install_notify_handler(const char *guid,
 					wmi_notify_handler handler, void *data);
 extern acpi_status wmi_remove_notify_handler(const char *guid);
-extern acpi_status wmi_get_event_data(u32 event, struct acpi_buffer *out);
 extern bool wmi_has_guid(const char *guid);
 extern char *wmi_get_acpi_device_uid(const char *guid);
 
@@ -446,10 +437,27 @@ extern char *wmi_get_acpi_device_uid(const char *guid);
 
 extern char acpi_video_backlight_string[];
 extern long acpi_is_video_device(acpi_handle handle);
-extern int acpi_blacklisted(void);
+
 extern void acpi_osi_setup(char *str);
 extern bool acpi_osi_is_win8(void);
 
+#ifdef CONFIG_ACPI_THERMAL_LIB
+int thermal_acpi_active_trip_temp(struct acpi_device *adev, int id, int *ret_temp);
+int thermal_acpi_passive_trip_temp(struct acpi_device *adev, int *ret_temp);
+int thermal_acpi_hot_trip_temp(struct acpi_device *adev, int *ret_temp);
+int thermal_acpi_critical_trip_temp(struct acpi_device *adev, int *ret_temp);
+#endif
+
+#ifdef CONFIG_ACPI_HMAT
+int acpi_get_genport_coordinates(u32 uid, struct access_coordinate *coord);
+#else
+static inline int acpi_get_genport_coordinates(u32 uid,
+					       struct access_coordinate *coord)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 #ifdef CONFIG_ACPI_NUMA
 int acpi_map_pxm_to_node(int pxm);
 int acpi_get_node(acpi_handle handle);
@@ -488,8 +496,6 @@ static inline int acpi_get_node(acpi_handle handle)
 	return 0;
 }
 #endif
-extern int acpi_paddr_to_node(u64 start_addr, u64 size);
-
 extern int pnpacpi_disabled;
 
 #define PXM_INVAL	(-1)
@@ -583,10 +589,15 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
 #define OSC_SB_CPCV2_SUPPORT			0x00000040
 #define OSC_SB_PCLPI_SUPPORT			0x00000080
 #define OSC_SB_OSLPI_SUPPORT			0x00000100
+#define OSC_SB_FAST_THERMAL_SAMPLING_SUPPORT	0x00000200
+#define OSC_SB_OVER_16_PSTATES_SUPPORT		0x00000400
+#define OSC_SB_GED_SUPPORT			0x00000800
 #define OSC_SB_CPC_DIVERSE_HIGH_SUPPORT		0x00001000
-#define OSC_SB_GENERIC_INITIATOR_SUPPORT	0x00002000
+#define OSC_SB_IRQ_RESOURCE_SOURCE_SUPPORT	0x00002000
 #define OSC_SB_CPC_FLEXIBLE_ADR_SPACE		0x00004000
+#define OSC_SB_GENERIC_INITIATOR_SUPPORT	0x00020000
 #define OSC_SB_NATIVE_USB4_SUPPORT		0x00040000
+#define OSC_SB_BATTERY_CHARGE_LIMITING_SUPPORT	0x00080000
 #define OSC_SB_PRM_SUPPORT			0x00200000
 #define OSC_SB_FFH_OPR_SUPPORT			0x00400000
 
@@ -712,13 +723,15 @@ int acpi_match_platform_list(const struct acpi_platform_list *plat);
 
 extern void acpi_early_init(void);
 extern void acpi_subsystem_init(void);
-extern void arch_post_acpi_subsys_init(void);
 
 extern int acpi_nvs_register(__u64 start, __u64 size);
 
 extern int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 				    void *data);
 
+const struct acpi_device_id *acpi_match_acpi_device(const struct acpi_device_id *ids,
+						    const struct acpi_device *adev);
+
 const struct acpi_device_id *acpi_match_device(const struct acpi_device_id *ids,
 					       const struct device *dev);
 
@@ -754,25 +767,29 @@ int acpi_reconfig_notifier_unregister(struct notifier_block *nb);
 int acpi_gtdt_init(struct acpi_table_header *table, int *platform_timer_count);
 int acpi_gtdt_map_ppi(int type);
 bool acpi_gtdt_c3stop(int type);
-int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count);
 #endif
 
 #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER
-static inline void acpi_arch_set_root_pointer(u64 addr)
+static __always_inline void acpi_arch_set_root_pointer(u64 addr)
 {
 }
 #endif
 
 #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER
-static inline u64 acpi_arch_get_root_pointer(void)
+static __always_inline u64 acpi_arch_get_root_pointer(void)
 {
 	return 0;
 }
 #endif
 
+int acpi_get_local_u64_address(acpi_handle handle, u64 *addr);
 int acpi_get_local_address(acpi_handle handle, u32 *addr);
 const char *acpi_get_subsystem_id(acpi_handle handle);
 
+#ifdef CONFIG_ACPI_MRRM
+int acpi_mrrm_max_mem_region(void);
+#endif
+
 #else	/* !CONFIG_ACPI */
 
 #define acpi_disabled 1
@@ -781,9 +798,10 @@ const char *acpi_get_subsystem_id(acpi_handle handle);
 #define ACPI_COMPANION_SET(dev, adev)	do { } while (0)
 #define ACPI_HANDLE(dev)		(NULL)
 #define ACPI_HANDLE_FWNODE(fwnode)	(NULL)
-#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (0), .cls_msk = (0),
 
-#include <acpi/acpi_numa.h>
+/* Get rid of the -Wunused-variable for adev */
+#define acpi_dev_uid_match(adev, uid2)			(adev && false)
+#define acpi_dev_hid_uid_match(adev, hid2, uid2)	(adev && false)
 
 struct fwnode_handle;
 
@@ -799,12 +817,6 @@ static inline bool acpi_dev_present(const char *hid, const char *uid, s64 hrv)
 
 struct acpi_device;
 
-static inline bool
-acpi_dev_hid_uid_match(struct acpi_device *adev, const char *hid2, const char *uid2)
-{
-	return false;
-}
-
 static inline int acpi_dev_uid_to_integer(struct acpi_device *adev, u64 *integer)
 {
 	return -ENODEV;
@@ -859,6 +871,11 @@ static inline struct fwnode_handle *acpi_fwnode_handle(struct acpi_device *adev)
 	return NULL;
 }
 
+static inline acpi_handle acpi_device_handle(struct acpi_device *adev)
+{
+	return NULL;
+}
+
 static inline bool has_acpi_companion(struct device *dev)
 {
 	return false;
@@ -935,6 +952,12 @@ static inline int acpi_nvs_for_each_region(int (*func)(__u64, __u64, void *),
 
 struct acpi_device_id;
 
+static inline const struct acpi_device_id *acpi_match_acpi_device(
+	const struct acpi_device_id *ids, const struct acpi_device *adev)
+{
+	return NULL;
+}
+
 static inline const struct acpi_device_id *acpi_match_device(
 	const struct acpi_device_id *ids, const struct device *dev)
 {
@@ -1082,8 +1105,31 @@ static inline bool acpi_sleep_state_supported(u8 sleep_state)
 	return false;
 }
 
+static inline acpi_handle acpi_get_processor_handle(int cpu)
+{
+	return NULL;
+}
+
+static inline int acpi_mrrm_max_mem_region(void)
+{
+	return 1;
+}
+
 #endif	/* !CONFIG_ACPI */
 
+#ifdef CONFIG_ACPI_HMAT
+int hmat_get_extended_linear_cache_size(struct resource *backing_res, int nid,
+					resource_size_t *size);
+#else
+static inline int hmat_get_extended_linear_cache_size(struct resource *backing_res,
+						      int nid, resource_size_t *size)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+extern void arch_post_acpi_subsys_init(void);
+
 #ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
 int acpi_ioapic_add(acpi_handle root);
 #else
@@ -1102,24 +1148,25 @@ void acpi_os_set_prepare_extended_sleep(int (*func)(u8 sleep_state,
 
 acpi_status acpi_os_prepare_extended_sleep(u8 sleep_state,
 					   u32 val_a, u32 val_b);
-#ifdef CONFIG_X86
 struct acpi_s2idle_dev_ops {
 	struct list_head list_node;
 	void (*prepare)(void);
 	void (*check)(void);
 	void (*restore)(void);
 };
+#if defined(CONFIG_SUSPEND) && defined(CONFIG_X86)
 int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg);
 void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg);
-#endif /* CONFIG_X86 */
-#ifndef CONFIG_IA64
-void arch_reserve_mem_area(acpi_physical_address addr, size_t size);
-#else
-static inline void arch_reserve_mem_area(acpi_physical_address addr,
-					  size_t size)
+#else /* CONFIG_SUSPEND && CONFIG_X86 */
+static inline int acpi_register_lps0_dev(struct acpi_s2idle_dev_ops *arg)
+{
+	return -ENODEV;
+}
+static inline void acpi_unregister_lps0_dev(struct acpi_s2idle_dev_ops *arg)
 {
 }
-#endif /* CONFIG_X86 */
+#endif /* CONFIG_SUSPEND && CONFIG_X86 */
+void arch_reserve_mem_area(acpi_physical_address addr, size_t size);
 #else
 #define acpi_os_set_prepare_sleep(func, pm1a_ctrl, pm1b_ctrl) do { } while (0)
 #endif
@@ -1157,8 +1204,6 @@ int acpi_subsys_suspend_noirq(struct device *dev);
 int acpi_subsys_suspend(struct device *dev);
 int acpi_subsys_freeze(struct device *dev);
 int acpi_subsys_poweroff(struct device *dev);
-void acpi_ec_mark_gpe_for_wake(void);
-void acpi_ec_set_gpe_wake_mask(u8 action);
 int acpi_subsys_restore_early(struct device *dev);
 #else
 static inline int acpi_subsys_prepare(struct device *dev) { return 0; }
@@ -1169,11 +1214,18 @@ static inline int acpi_subsys_suspend(struct device *dev) { return 0; }
 static inline int acpi_subsys_freeze(struct device *dev) { return 0; }
 static inline int acpi_subsys_poweroff(struct device *dev) { return 0; }
 static inline int acpi_subsys_restore_early(struct device *dev) { return 0; }
+#endif
+
+#if defined(CONFIG_ACPI_EC) && defined(CONFIG_PM_SLEEP)
+void acpi_ec_mark_gpe_for_wake(void);
+void acpi_ec_set_gpe_wake_mask(u8 action);
+#else
 static inline void acpi_ec_mark_gpe_for_wake(void) {}
 static inline void acpi_ec_set_gpe_wake_mask(u8 action) {}
 #endif
 
 #ifdef CONFIG_ACPI
+char *acpi_handle_path(acpi_handle handle);
 __printf(3, 4)
 void acpi_handle_printk(const char *level, acpi_handle handle,
 			const char *fmt, ...);
@@ -1236,7 +1288,7 @@ bool acpi_gpio_get_irq_resource(struct acpi_resource *ares,
 				struct acpi_resource_gpio **agpio);
 bool acpi_gpio_get_io_resource(struct acpi_resource *ares,
 			       struct acpi_resource_gpio **agpio);
-int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name, int index,
+int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id, int index,
 				  bool *wake_capable);
 #else
 static inline bool acpi_gpio_get_irq_resource(struct acpi_resource *ares,
@@ -1249,7 +1301,7 @@ static inline bool acpi_gpio_get_io_resource(struct acpi_resource *ares,
 {
 	return false;
 }
-static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *name,
+static inline int acpi_dev_gpio_irq_wake_get_by(struct acpi_device *adev, const char *con_id,
 						int index, bool *wake_capable)
 {
 	return -ENXIO;
@@ -1262,10 +1314,10 @@ static inline int acpi_dev_gpio_irq_wake_get(struct acpi_device *adev, int index
 	return acpi_dev_gpio_irq_wake_get_by(adev, NULL, index, wake_capable);
 }
 
-static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *name,
+static inline int acpi_dev_gpio_irq_get_by(struct acpi_device *adev, const char *con_id,
 					   int index)
 {
-	return acpi_dev_gpio_irq_wake_get_by(adev, name, index, NULL);
+	return acpi_dev_gpio_irq_wake_get_by(adev, con_id, index, NULL);
 }
 
 static inline int acpi_dev_gpio_irq_get(struct acpi_device *adev, int index)
@@ -1303,9 +1355,6 @@ acpi_data_add_props(struct acpi_device_data *data, const guid_t *guid,
 int acpi_node_prop_get(const struct fwnode_handle *fwnode, const char *propname,
 		       void **valptr);
 
-struct fwnode_handle *acpi_get_next_subnode(const struct fwnode_handle *fwnode,
-					    struct fwnode_handle *child);
-
 struct acpi_probe_entry;
 typedef bool (*acpi_probe_entry_validate_subtbl)(struct acpi_subtable_header *,
 						 struct acpi_probe_entry *);
@@ -1336,6 +1385,8 @@ struct acpi_probe_entry {
 	kernel_ulong_t driver_data;
 };
 
+void arch_sort_irqchip_probe(struct acpi_probe_entry *ap_head, int nr);
+
 #define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable,	\
 				 valid, data, fn)			\
 	static const struct acpi_probe_entry __acpi_probe_##name	\
@@ -1403,13 +1454,6 @@ static inline int acpi_node_prop_get(const struct fwnode_handle *fwnode,
 }
 
 static inline struct fwnode_handle *
-acpi_get_next_subnode(const struct fwnode_handle *fwnode,
-		      struct fwnode_handle *child)
-{
-	return NULL;
-}
-
-static inline struct fwnode_handle *
 acpi_graph_get_next_endpoint(const struct fwnode_handle *fwnode,
 			     struct fwnode_handle *prev)
 {
@@ -1455,18 +1499,25 @@ int acpi_parse_spcr(bool enable_earlycon, bool enable_console);
 #else
 static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console)
 {
-	return 0;
+	return -ENODEV;
 }
 #endif
 
 #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI)
 int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res);
+const struct cpumask *acpi_irq_get_affinity(acpi_handle handle,
+					    unsigned int index);
 #else
 static inline
 int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res)
 {
 	return -EINVAL;
 }
+static inline const struct cpumask *acpi_irq_get_affinity(acpi_handle handle,
+							  unsigned int index)
+{
+	return NULL;
+}
 #endif
 
 #ifdef CONFIG_ACPI_LPIT
@@ -1478,12 +1529,24 @@ static inline int lpit_read_residency_count_address(u64 *address)
 }
 #endif
 
+#ifdef CONFIG_ACPI_PROCESSOR_IDLE
+#ifndef arch_get_idle_state_flags
+static inline unsigned int arch_get_idle_state_flags(u32 arch_flags)
+{
+	return 0;
+}
+#endif
+#endif /* CONFIG_ACPI_PROCESSOR_IDLE */
+
 #ifdef CONFIG_ACPI_PPTT
 int acpi_pptt_cpu_is_thread(unsigned int cpu);
 int find_acpi_cpu_topology(unsigned int cpu, int level);
 int find_acpi_cpu_topology_cluster(unsigned int cpu);
 int find_acpi_cpu_topology_package(unsigned int cpu);
 int find_acpi_cpu_topology_hetero_id(unsigned int cpu);
+void acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id, cpumask_t *cpus);
+int find_acpi_cache_level_from_id(u32 cache_id);
+int acpi_pptt_get_cpumask_from_cache_id(u32 cache_id, cpumask_t *cpus);
 #else
 static inline int acpi_pptt_cpu_is_thread(unsigned int cpu)
 {
@@ -1505,8 +1568,21 @@ static inline int find_acpi_cpu_topology_hetero_id(unsigned int cpu)
 {
 	return -EINVAL;
 }
+static inline void acpi_pptt_get_cpus_from_container(u32 acpi_cpu_id,
+						     cpumask_t *cpus) { }
+static inline int find_acpi_cache_level_from_id(u32 cache_id)
+{
+	return -ENOENT;
+}
+static inline int acpi_pptt_get_cpumask_from_cache_id(u32 cache_id,
+						      cpumask_t *cpus)
+{
+	return -ENOENT;
+}
 #endif
 
+void acpi_arch_init(void);
+
 #ifdef CONFIG_ACPI_PCC
 void acpi_init_pcc(void);
 #else
@@ -1531,4 +1607,18 @@ static inline void acpi_device_notify(struct device *dev) { }
 static inline void acpi_device_notify_remove(struct device *dev) { }
 #endif
 
+static inline void acpi_use_parent_companion(struct device *dev)
+{
+	ACPI_COMPANION_SET(dev, ACPI_COMPANION(dev->parent));
+}
+
+#ifdef CONFIG_ACPI_NUMA
+bool acpi_node_backed_by_real_pxm(int nid);
+#else
+static inline bool acpi_node_backed_by_real_pxm(int nid)
+{
+	return false;
+}
+#endif
+
 #endif	/*_LINUX_ACPI_H*/
diff --git a/include/linux/acpi_agdi.h b/include/linux/acpi_agdi.h
deleted file mode 100644
index f477f0b452fa..000000000000
--- a/include/linux/acpi_agdi.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-
-#ifndef __ACPI_AGDI_H__
-#define __ACPI_AGDI_H__
-
-#include <linux/acpi.h>
-
-#ifdef CONFIG_ACPI_AGDI
-void __init acpi_agdi_init(void);
-#else
-static inline void acpi_agdi_init(void) {}
-#endif
-#endif /* __ACPI_AGDI_H__ */
diff --git a/include/linux/acpi_amd_wbrf.h b/include/linux/acpi_amd_wbrf.h
new file mode 100644
index 000000000000..898f31d536d4
--- /dev/null
+++ b/include/linux/acpi_amd_wbrf.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Wifi Band Exclusion Interface (AMD ACPI Implementation)
+ * Copyright (C) 2023 Advanced Micro Devices
+ */
+
+#ifndef _ACPI_AMD_WBRF_H
+#define _ACPI_AMD_WBRF_H
+
+#include <linux/device.h>
+#include <linux/notifier.h>
+
+/* The maximum number of frequency band ranges */
+#define MAX_NUM_OF_WBRF_RANGES		11
+
+/* Record actions */
+#define WBRF_RECORD_ADD		0x0
+#define WBRF_RECORD_REMOVE	0x1
+
+/**
+ * struct freq_band_range - Wifi frequency band range definition
+ * @start: start frequency point (in Hz)
+ * @end: end frequency point (in Hz)
+ */
+struct freq_band_range {
+	u64		start;
+	u64		end;
+};
+
+/**
+ * struct wbrf_ranges_in_out - wbrf ranges info
+ * @num_of_ranges: total number of band ranges in this struct
+ * @band_list: array of Wifi band ranges
+ */
+struct wbrf_ranges_in_out {
+	u64			num_of_ranges;
+	struct freq_band_range	band_list[MAX_NUM_OF_WBRF_RANGES];
+};
+
+/**
+ * enum wbrf_notifier_actions - wbrf notifier actions index
+ * @WBRF_CHANGED: there was some frequency band updates. The consumers
+ *               should retrieve the latest active frequency bands.
+ */
+enum wbrf_notifier_actions {
+	WBRF_CHANGED,
+};
+
+#if IS_ENABLED(CONFIG_AMD_WBRF)
+bool acpi_amd_wbrf_supported_producer(struct device *dev);
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in);
+bool acpi_amd_wbrf_supported_consumer(struct device *dev);
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out);
+int amd_wbrf_register_notifier(struct notifier_block *nb);
+int amd_wbrf_unregister_notifier(struct notifier_block *nb);
+#else
+static inline
+bool acpi_amd_wbrf_supported_consumer(struct device *dev)
+{
+	return false;
+}
+
+static inline
+int acpi_amd_wbrf_add_remove(struct device *dev, uint8_t action, struct wbrf_ranges_in_out *in)
+{
+	return -ENODEV;
+}
+
+static inline
+bool acpi_amd_wbrf_supported_producer(struct device *dev)
+{
+	return false;
+}
+static inline
+int amd_wbrf_retrieve_freq_band(struct device *dev, struct wbrf_ranges_in_out *out)
+{
+	return -ENODEV;
+}
+static inline
+int amd_wbrf_register_notifier(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+static inline
+int amd_wbrf_unregister_notifier(struct notifier_block *nb)
+{
+	return -ENODEV;
+}
+#endif /* CONFIG_AMD_WBRF */
+
+#endif /* _ACPI_AMD_WBRF_H */
diff --git a/include/linux/acpi_apmt.h b/include/linux/acpi_apmt.h
deleted file mode 100644
index 40bd634d082f..000000000000
--- a/include/linux/acpi_apmt.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0
- *
- * ARM CoreSight PMU driver.
- * Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES.
- *
- */
-
-#ifndef __ACPI_APMT_H__
-#define __ACPI_APMT_H__
-
-#include <linux/acpi.h>
-
-#ifdef CONFIG_ACPI_APMT
-void acpi_apmt_init(void);
-#else
-static inline void acpi_apmt_init(void) { }
-#endif /* CONFIG_ACPI_APMT */
-
-#endif /* __ACPI_APMT_H__ */
diff --git a/include/linux/acpi_dma.h b/include/linux/acpi_dma.h
index 72cedb916a9c..e748b2877602 100644
--- a/include/linux/acpi_dma.h
+++ b/include/linux/acpi_dma.h
@@ -11,10 +11,11 @@
 #ifndef __LINUX_ACPI_DMA_H
 #define __LINUX_ACPI_DMA_H
 
-#include <linux/list.h>
-#include <linux/device.h>
 #include <linux/err.h>
 #include <linux/dmaengine.h>
+#include <linux/types.h>
+
+struct device;
 
 /**
  * struct acpi_dma_spec - slave device DMA resources
@@ -65,7 +66,6 @@ int devm_acpi_dma_controller_register(struct device *dev,
 		struct dma_chan *(*acpi_dma_xlate)
 		(struct acpi_dma_spec *, struct acpi_dma *),
 		void *data);
-void devm_acpi_dma_controller_free(struct device *dev);
 
 struct dma_chan *acpi_dma_request_slave_chan_by_index(struct device *dev,
 						      size_t index);
@@ -94,9 +94,6 @@ static inline int devm_acpi_dma_controller_register(struct device *dev,
 {
 	return -ENODEV;
 }
-static inline void devm_acpi_dma_controller_free(struct device *dev)
-{
-}
 
 static inline struct dma_chan *acpi_dma_request_slave_chan_by_index(
 		struct device *dev, size_t index)
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index b43be0987b19..d4ed5622cf2b 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -21,29 +21,29 @@
  */
 #define IORT_SMMU_V3_PMCG_GENERIC        0x00000000 /* Generic SMMUv3 PMCG */
 #define IORT_SMMU_V3_PMCG_HISI_HIP08     0x00000001 /* HiSilicon HIP08 PMCG */
+#define IORT_SMMU_V3_PMCG_HISI_HIP09     0x00000002 /* HiSilicon HIP09 PMCG */
 
 int iort_register_domain_token(int trans_id, phys_addr_t base,
 			       struct fwnode_handle *fw_node);
 void iort_deregister_domain_token(int trans_id);
 struct fwnode_handle *iort_find_domain_token(int trans_id);
+int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
+
 #ifdef CONFIG_ACPI_IORT
-void acpi_iort_init(void);
 u32 iort_msi_map_id(struct device *dev, u32 id);
 struct irq_domain *iort_get_device_domain(struct device *dev, u32 id,
 					  enum irq_domain_bus_token bus_token);
 void acpi_configure_pmsi_domain(struct device *dev);
-int iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id);
 void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode,
 		       struct list_head *head);
 void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode,
 		       struct list_head *head);
 /* IOMMU interface */
-int iort_dma_get_ranges(struct device *dev, u64 *size);
+int iort_dma_get_ranges(struct device *dev, u64 *limit);
 int iort_iommu_configure_id(struct device *dev, const u32 *id_in);
 void iort_iommu_get_resv_regions(struct device *dev, struct list_head *head);
 phys_addr_t acpi_iort_dma_get_max_cpu_address(void);
 #else
-static inline void acpi_iort_init(void) { }
 static inline u32 iort_msi_map_id(struct device *dev, u32 id)
 { return id; }
 static inline struct irq_domain *iort_get_device_domain(
@@ -55,7 +55,7 @@ void iort_get_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *hea
 static inline
 void iort_put_rmr_sids(struct fwnode_handle *iommu_fwnode, struct list_head *head) { }
 /* IOMMU interface */
-static inline int iort_dma_get_ranges(struct device *dev, u64 *size)
+static inline int iort_dma_get_ranges(struct device *dev, u64 *limit)
 { return -ENODEV; }
 static inline int iort_iommu_configure_id(struct device *dev, const u32 *id_in)
 { return -ENODEV; }
diff --git a/include/linux/acpi_pmtmr.h b/include/linux/acpi_pmtmr.h
index 50d88bf1498d..0ded9220d379 100644
--- a/include/linux/acpi_pmtmr.h
+++ b/include/linux/acpi_pmtmr.h
@@ -26,6 +26,19 @@ static inline u32 acpi_pm_read_early(void)
 	return acpi_pm_read_verified() & ACPI_PM_MASK;
 }
 
+/**
+ * Register callback for suspend and resume event
+ *
+ * @cb Callback triggered on suspend and resume
+ * @data Data passed with the callback
+ */
+void acpi_pmtmr_register_suspend_resume_callback(void (*cb)(void *data, bool suspend), void *data);
+
+/**
+ * Remove registered callback for suspend and resume event
+ */
+void acpi_pmtmr_unregister_suspend_resume_callback(void);
+
 #else
 
 static inline u32 acpi_pm_read_early(void)
diff --git a/include/linux/acpi_rimt.h b/include/linux/acpi_rimt.h
new file mode 100644
index 000000000000..fad3adc4d899
--- /dev/null
+++ b/include/linux/acpi_rimt.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  Copyright (C) 2024-2025, Ventana Micro Systems Inc.
+ *	Author: Sunil V L <sunilvl@ventanamicro.com>
+ */
+
+#ifndef _ACPI_RIMT_H
+#define _ACPI_RIMT_H
+
+#ifdef CONFIG_ACPI_RIMT
+int rimt_iommu_register(struct device *dev);
+#else
+static inline int rimt_iommu_register(struct device *dev)
+{
+	return -ENODEV;
+}
+#endif
+
+#if defined(CONFIG_IOMMU_API) && defined(CONFIG_ACPI_RIMT)
+int rimt_iommu_configure_id(struct device *dev, const u32 *id_in);
+#else
+static inline int rimt_iommu_configure_id(struct device *dev, const u32 *id_in)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /* _ACPI_RIMT_H */
diff --git a/include/linux/adi-axi-common.h b/include/linux/adi-axi-common.h
new file mode 100644
index 000000000000..37962ba530df
--- /dev/null
+++ b/include/linux/adi-axi-common.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Analog Devices AXI common registers & definitions
+ *
+ * Copyright 2019 Analog Devices Inc.
+ *
+ * https://wiki.analog.com/resources/fpga/docs/axi_ip
+ * https://wiki.analog.com/resources/fpga/docs/hdl/regmap
+ */
+
+#include <linux/types.h>
+
+#ifndef ADI_AXI_COMMON_H_
+#define ADI_AXI_COMMON_H_
+
+#define ADI_AXI_REG_VERSION			0x0000
+#define ADI_AXI_REG_FPGA_INFO			0x001C
+
+#define ADI_AXI_PCORE_VER(major, minor, patch)	\
+	(((major) << 16) | ((minor) << 8) | (patch))
+
+#define ADI_AXI_PCORE_VER_MAJOR(version)	(((version) >> 16) & 0xff)
+#define ADI_AXI_PCORE_VER_MINOR(version)	(((version) >> 8) & 0xff)
+#define ADI_AXI_PCORE_VER_PATCH(version)	((version) & 0xff)
+
+/**
+ * adi_axi_pcore_ver_gteq() - check if a version is satisfied
+ * @version: the full version read from the hardware
+ * @major: the major version to compare against
+ * @minor: the minor version to compare against
+ *
+ * ADI AXI IP Cores use semantic versioning, so this can be used to check for
+ * feature availability.
+ *
+ * Return: true if the version is greater than or equal to the specified
+ *         major and minor version, false otherwise.
+ */
+static inline bool adi_axi_pcore_ver_gteq(u32 version, u32 major, u32 minor)
+{
+	return ADI_AXI_PCORE_VER_MAJOR(version) > (major) ||
+	       (ADI_AXI_PCORE_VER_MAJOR(version) == (major) &&
+		ADI_AXI_PCORE_VER_MINOR(version) >= (minor));
+}
+
+#define ADI_AXI_INFO_FPGA_TECH(info)            (((info) >> 24) & 0xff)
+#define ADI_AXI_INFO_FPGA_FAMILY(info)          (((info) >> 16) & 0xff)
+#define ADI_AXI_INFO_FPGA_SPEED_GRADE(info)     (((info) >> 8) & 0xff)
+
+enum adi_axi_fpga_technology {
+	ADI_AXI_FPGA_TECH_UNKNOWN = 0,
+	ADI_AXI_FPGA_TECH_SERIES7,
+	ADI_AXI_FPGA_TECH_ULTRASCALE,
+	ADI_AXI_FPGA_TECH_ULTRASCALE_PLUS,
+};
+
+enum adi_axi_fpga_family {
+	ADI_AXI_FPGA_FAMILY_UNKNOWN = 0,
+	ADI_AXI_FPGA_FAMILY_ARTIX,
+	ADI_AXI_FPGA_FAMILY_KINTEX,
+	ADI_AXI_FPGA_FAMILY_VIRTEX,
+	ADI_AXI_FPGA_FAMILY_ZYNQ,
+};
+
+enum adi_axi_fpga_speed_grade {
+	ADI_AXI_FPGA_SPEED_UNKNOWN      = 0,
+	ADI_AXI_FPGA_SPEED_1    = 10,
+	ADI_AXI_FPGA_SPEED_1L   = 11,
+	ADI_AXI_FPGA_SPEED_1H   = 12,
+	ADI_AXI_FPGA_SPEED_1HV  = 13,
+	ADI_AXI_FPGA_SPEED_1LV  = 14,
+	ADI_AXI_FPGA_SPEED_2    = 20,
+	ADI_AXI_FPGA_SPEED_2L   = 21,
+	ADI_AXI_FPGA_SPEED_2LV  = 22,
+	ADI_AXI_FPGA_SPEED_3    = 30,
+};
+
+#endif /* ADI_AXI_COMMON_H_ */
diff --git a/include/linux/adreno-smmu-priv.h b/include/linux/adreno-smmu-priv.h
index c637e0997f6d..d83c9175828f 100644
--- a/include/linux/adreno-smmu-priv.h
+++ b/include/linux/adreno-smmu-priv.h
@@ -45,11 +45,16 @@ struct adreno_smmu_fault_info {
  *                 TTBR0 translation is enabled with the specified cfg
  * @get_fault_info: Called by the GPU fault handler to get information about
  *                  the fault
- * @set_stall:     Configure whether stall on fault (CFCFG) is enabled.  Call
- *                 before set_ttbr0_cfg().  If stalling on fault is enabled,
- *                 the GPU driver must call resume_translation()
+ * @set_stall:     Configure whether stall on fault (CFCFG) is enabled. If
+ *                 stalling on fault is enabled, the GPU driver must call
+ *                 resume_translation()
  * @resume_translation: Resume translation after a fault
  *
+ * @set_prr_bit:   [optional] Configure the GPU's Partially Resident
+ *                 Region (PRR) bit in the ACTLR register.
+ * @set_prr_addr:  [optional] Configure the PRR_CFG_*ADDR register with
+ *                 the physical address of PRR page passed from GPU
+ *                 driver.
  *
  * The GPU driver (drm/msm) and adreno-smmu work together for controlling
  * the GPU's SMMU instance.  This is by necessity, as the GPU is directly
@@ -67,6 +72,8 @@ struct adreno_smmu_priv {
     void (*get_fault_info)(const void *cookie, struct adreno_smmu_fault_info *info);
     void (*set_stall)(const void *cookie, bool enabled);
     void (*resume_translation)(const void *cookie, bool terminate);
+    void (*set_prr_bit)(const void *cookie, bool set);
+    void (*set_prr_addr)(const void *cookie, phys_addr_t page_addr);
 };
 
 #endif /* __ADRENO_SMMU_PRIV_H */
diff --git a/include/linux/aer.h b/include/linux/aer.h
index 97f64ba1b34a..02940be66324 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -16,13 +16,26 @@
 #define AER_CORRECTABLE			2
 #define DPC_FATAL			3
 
+/*
+ * AER and DPC capabilities TLP Logging register sizes (PCIe r6.2, sec 7.8.4
+ * & 7.9.14).
+ */
+#define PCIE_STD_NUM_TLP_HEADERLOG     4
+#define PCIE_STD_MAX_TLP_PREFIXLOG     4
+#define PCIE_STD_MAX_TLP_HEADERLOG	(PCIE_STD_NUM_TLP_HEADERLOG + 10)
+
 struct pci_dev;
 
-struct aer_header_log_regs {
-	unsigned int dw0;
-	unsigned int dw1;
-	unsigned int dw2;
-	unsigned int dw3;
+struct pcie_tlp_log {
+	union {
+		u32 dw[PCIE_STD_MAX_TLP_HEADERLOG];
+		struct {
+			u32 _do_not_use[PCIE_STD_NUM_TLP_HEADERLOG];
+			u32 prefix[PCIE_STD_MAX_TLP_PREFIXLOG];
+		};
+	};
+	u8 header_len;		/* Length of the Logged TLP Header in DWORDs */
+	bool flit;		/* TLP was logged when in Flit mode */
 };
 
 struct aer_capability_regs {
@@ -33,7 +46,7 @@ struct aer_capability_regs {
 	u32 cor_status;
 	u32 cor_mask;
 	u32 cap_control;
-	struct aer_header_log_regs header_log;
+	struct pcie_tlp_log header_log;
 	u32 root_command;
 	u32 root_status;
 	u16 cor_err_source;
@@ -41,30 +54,17 @@ struct aer_capability_regs {
 };
 
 #if defined(CONFIG_PCIEAER)
-/* PCIe port driver needs this function to enable AER */
-int pci_enable_pcie_error_reporting(struct pci_dev *dev);
-int pci_disable_pcie_error_reporting(struct pci_dev *dev);
 int pci_aer_clear_nonfatal_status(struct pci_dev *dev);
-void pci_save_aer_state(struct pci_dev *dev);
-void pci_restore_aer_state(struct pci_dev *dev);
+int pcie_aer_is_native(struct pci_dev *dev);
 #else
-static inline int pci_enable_pcie_error_reporting(struct pci_dev *dev)
-{
-	return -EINVAL;
-}
-static inline int pci_disable_pcie_error_reporting(struct pci_dev *dev)
-{
-	return -EINVAL;
-}
 static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev)
 {
 	return -EINVAL;
 }
-static inline void pci_save_aer_state(struct pci_dev *dev) {}
-static inline void pci_restore_aer_state(struct pci_dev *dev) {}
+static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; }
 #endif
 
-void cper_print_aer(struct pci_dev *dev, int aer_severity,
+void pci_print_aer(struct pci_dev *dev, int aer_severity,
 		    struct aer_capability_regs *aer);
 int cper_severity_to_aer(int cper_severity);
 void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
diff --git a/include/linux/alarmtimer.h b/include/linux/alarmtimer.h
index 05e758b8b894..3ffa5341dce2 100644
--- a/include/linux/alarmtimer.h
+++ b/include/linux/alarmtimer.h
@@ -20,12 +20,6 @@ enum alarmtimer_type {
 	ALARM_BOOTTIME_FREEZER,
 };
 
-enum alarmtimer_restart {
-	ALARMTIMER_NORESTART,
-	ALARMTIMER_RESTART,
-};
-
-
 #define ALARMTIMER_STATE_INACTIVE	0x00
 #define ALARMTIMER_STATE_ENQUEUED	0x01
 
@@ -42,14 +36,14 @@ enum alarmtimer_restart {
 struct alarm {
 	struct timerqueue_node	node;
 	struct hrtimer		timer;
-	enum alarmtimer_restart	(*function)(struct alarm *, ktime_t now);
+	void			(*function)(struct alarm *, ktime_t now);
 	enum alarmtimer_type	type;
 	int			state;
 	void			*data;
 };
 
 void alarm_init(struct alarm *alarm, enum alarmtimer_type type,
-		enum alarmtimer_restart (*function)(struct alarm *, ktime_t));
+		void (*function)(struct alarm *, ktime_t));
 void alarm_start(struct alarm *alarm, ktime_t start);
 void alarm_start_relative(struct alarm *alarm, ktime_t start);
 void alarm_restart(struct alarm *alarm);
diff --git a/include/linux/alcor_pci.h b/include/linux/alcor_pci.h
index c4a0b23846d8..dcb1d37dabc2 100644
--- a/include/linux/alcor_pci.h
+++ b/include/linux/alcor_pci.h
@@ -11,6 +11,7 @@
 #define ALCOR_SD_CARD 0
 #define ALCOR_MS_CARD 1
 
+#define DRV_NAME_ALCOR_PCI			"alcor_pci"
 #define DRV_NAME_ALCOR_PCI_SDMMC		"alcor_sdmmc"
 #define DRV_NAME_ALCOR_PCI_MS			"alcor_ms"
 
diff --git a/include/linux/align.h b/include/linux/align.h
index 2b4acec7b95a..55debf105a5d 100644
--- a/include/linux/align.h
+++ b/include/linux/align.h
@@ -2,14 +2,6 @@
 #ifndef _LINUX_ALIGN_H
 #define _LINUX_ALIGN_H
 
-#include <linux/const.h>
-
-/* @a is a power of 2 value */
-#define ALIGN(x, a)		__ALIGN_KERNEL((x), (a))
-#define ALIGN_DOWN(x, a)	__ALIGN_KERNEL((x) - ((a) - 1), (a))
-#define __ALIGN_MASK(x, mask)	__ALIGN_KERNEL_MASK((x), (mask))
-#define PTR_ALIGN(p, a)		((typeof(p))ALIGN((unsigned long)(p), (a)))
-#define PTR_ALIGN_DOWN(p, a)	((typeof(p))ALIGN_DOWN((unsigned long)(p), (a)))
-#define IS_ALIGNED(x, a)		(((x) & ((typeof(x))(a) - 1)) == 0)
+#include <vdso/align.h>
 
 #endif	/* _LINUX_ALIGN_H */
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
new file mode 100644
index 000000000000..d40ac39bfbe8
--- /dev/null
+++ b/include/linux/alloc_tag.h
@@ -0,0 +1,268 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * allocation tagging
+ */
+#ifndef _LINUX_ALLOC_TAG_H
+#define _LINUX_ALLOC_TAG_H
+
+#include <linux/bug.h>
+#include <linux/codetag.h>
+#include <linux/container_of.h>
+#include <linux/preempt.h>
+#include <asm/percpu.h>
+#include <linux/cpumask.h>
+#include <linux/smp.h>
+#include <linux/static_key.h>
+#include <linux/irqflags.h>
+
+struct alloc_tag_counters {
+	u64 bytes;
+	u64 calls;
+};
+
+/*
+ * An instance of this structure is created in a special ELF section at every
+ * allocation callsite. At runtime, the special section is treated as
+ * an array of these. Embedded codetag utilizes codetag framework.
+ */
+struct alloc_tag {
+	struct codetag			ct;
+	struct alloc_tag_counters __percpu	*counters;
+} __aligned(8);
+
+struct alloc_tag_kernel_section {
+	struct alloc_tag *first_tag;
+	unsigned long count;
+};
+
+struct alloc_tag_module_section {
+	union {
+		unsigned long start_addr;
+		struct alloc_tag *first_tag;
+	};
+	unsigned long end_addr;
+	/* used size */
+	unsigned long size;
+};
+
+#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
+
+#define CODETAG_EMPTY	((void *)1)
+
+static inline bool is_codetag_empty(union codetag_ref *ref)
+{
+	return ref->ct == CODETAG_EMPTY;
+}
+
+static inline void set_codetag_empty(union codetag_ref *ref)
+{
+	if (ref)
+		ref->ct = CODETAG_EMPTY;
+}
+
+#else /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
+
+static inline bool is_codetag_empty(union codetag_ref *ref) { return false; }
+
+static inline void set_codetag_empty(union codetag_ref *ref)
+{
+	if (ref)
+		ref->ct = NULL;
+}
+
+#endif /* CONFIG_MEM_ALLOC_PROFILING_DEBUG */
+
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+
+#define ALLOC_TAG_SECTION_NAME	"alloc_tags"
+
+struct codetag_bytes {
+	struct codetag *ct;
+	s64 bytes;
+};
+
+size_t alloc_tag_top_users(struct codetag_bytes *tags, size_t count, bool can_sleep);
+
+static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct)
+{
+	return container_of(ct, struct alloc_tag, ct);
+}
+
+#if defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE)
+/*
+ * When percpu variables are required to be defined as weak, static percpu
+ * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION).
+ * Instead we will account all module allocations to a single counter.
+ */
+DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
+
+#define DEFINE_ALLOC_TAG(_alloc_tag)						\
+	static struct alloc_tag _alloc_tag __used __aligned(8)			\
+	__section(ALLOC_TAG_SECTION_NAME) = {					\
+		.ct = CODE_TAG_INIT,						\
+		.counters = &_shared_alloc_tag };
+
+#else /* CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU && MODULE */
+
+#ifdef MODULE
+
+#define DEFINE_ALLOC_TAG(_alloc_tag)						\
+	static struct alloc_tag _alloc_tag __used __aligned(8)			\
+	__section(ALLOC_TAG_SECTION_NAME) = {					\
+		.ct = CODE_TAG_INIT,						\
+		.counters = NULL };
+
+#else  /* MODULE */
+
+#define DEFINE_ALLOC_TAG(_alloc_tag)						\
+	static DEFINE_PER_CPU(struct alloc_tag_counters, _alloc_tag_cntr);	\
+	static struct alloc_tag _alloc_tag __used __aligned(8)			\
+	__section(ALLOC_TAG_SECTION_NAME) = {					\
+		.ct = CODE_TAG_INIT,						\
+		.counters = &_alloc_tag_cntr };
+
+#endif /* MODULE */
+
+#endif /* CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU && MODULE */
+
+DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
+			mem_alloc_profiling_key);
+
+static inline bool mem_alloc_profiling_enabled(void)
+{
+	return static_branch_maybe(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
+				   &mem_alloc_profiling_key);
+}
+
+static inline struct alloc_tag_counters alloc_tag_read(struct alloc_tag *tag)
+{
+	struct alloc_tag_counters v = { 0, 0 };
+	struct alloc_tag_counters *counter;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		counter = per_cpu_ptr(tag->counters, cpu);
+		v.bytes += counter->bytes;
+		v.calls += counter->calls;
+	}
+
+	return v;
+}
+
+#ifdef CONFIG_MEM_ALLOC_PROFILING_DEBUG
+static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag)
+{
+	WARN_ONCE(ref && ref->ct && !is_codetag_empty(ref),
+		  "alloc_tag was not cleared (got tag for %s:%u)\n",
+		  ref->ct->filename, ref->ct->lineno);
+
+	WARN_ONCE(!tag, "current->alloc_tag not set\n");
+}
+
+static inline void alloc_tag_sub_check(union codetag_ref *ref)
+{
+	WARN_ONCE(ref && !ref->ct, "alloc_tag was not set\n");
+}
+#else
+static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag *tag) {}
+static inline void alloc_tag_sub_check(union codetag_ref *ref) {}
+#endif
+
+/* Caller should verify both ref and tag to be valid */
+static inline bool __alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+{
+	alloc_tag_add_check(ref, tag);
+	if (!ref || !tag)
+		return false;
+
+	ref->ct = &tag->ct;
+	return true;
+}
+
+static inline bool alloc_tag_ref_set(union codetag_ref *ref, struct alloc_tag *tag)
+{
+	if (unlikely(!__alloc_tag_ref_set(ref, tag)))
+		return false;
+
+	/*
+	 * We need in increment the call counter every time we have a new
+	 * allocation or when we split a large allocation into smaller ones.
+	 * Each new reference for every sub-allocation needs to increment call
+	 * counter because when we free each part the counter will be decremented.
+	 */
+	this_cpu_inc(tag->counters->calls);
+	return true;
+}
+
+static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag, size_t bytes)
+{
+	if (likely(alloc_tag_ref_set(ref, tag)))
+		this_cpu_add(tag->counters->bytes, bytes);
+}
+
+static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes)
+{
+	struct alloc_tag *tag;
+
+	alloc_tag_sub_check(ref);
+	if (!ref || !ref->ct)
+		return;
+
+	if (is_codetag_empty(ref)) {
+		ref->ct = NULL;
+		return;
+	}
+
+	tag = ct_to_alloc_tag(ref->ct);
+
+	this_cpu_sub(tag->counters->bytes, bytes);
+	this_cpu_dec(tag->counters->calls);
+
+	ref->ct = NULL;
+}
+
+static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag)
+{
+	tag->ct.flags |= CODETAG_FLAG_INACCURATE;
+}
+
+static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag)
+{
+	return !!(tag->ct.flags & CODETAG_FLAG_INACCURATE);
+}
+
+#define alloc_tag_record(p)	((p) = current->alloc_tag)
+
+#else /* CONFIG_MEM_ALLOC_PROFILING */
+
+#define DEFINE_ALLOC_TAG(_alloc_tag)
+static inline bool mem_alloc_profiling_enabled(void) { return false; }
+static inline void alloc_tag_add(union codetag_ref *ref, struct alloc_tag *tag,
+				 size_t bytes) {}
+static inline void alloc_tag_sub(union codetag_ref *ref, size_t bytes) {}
+static inline void alloc_tag_set_inaccurate(struct alloc_tag *tag) {}
+static inline bool alloc_tag_is_inaccurate(struct alloc_tag *tag) { return false; }
+#define alloc_tag_record(p)	do {} while (0)
+
+#endif /* CONFIG_MEM_ALLOC_PROFILING */
+
+#define alloc_hooks_tag(_tag, _do_alloc)				\
+({									\
+	typeof(_do_alloc) _res;						\
+	if (mem_alloc_profiling_enabled()) {				\
+		struct alloc_tag * __maybe_unused _old;			\
+		_old = alloc_tag_save(_tag);				\
+		_res = _do_alloc;					\
+		alloc_tag_restore(_tag, _old);				\
+	} else								\
+		_res = _do_alloc;					\
+	_res;								\
+})
+
+#define alloc_hooks(_do_alloc)						\
+({									\
+	DEFINE_ALLOC_TAG(_alloc_tag);					\
+	alloc_hooks_tag(&_alloc_tag, _do_alloc);			\
+})
+
+#endif /* _LINUX_ALLOC_TAG_H */
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 5001e14c5c06..9946276aff73 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -105,24 +105,36 @@ enum amba_vendor {
 	AMBA_VENDOR_LSI = 0xb6,
 };
 
-extern struct bus_type amba_bustype;
+extern const struct bus_type amba_bustype;
 
-#define to_amba_device(d)	container_of(d, struct amba_device, dev)
+#define to_amba_device(d)	container_of_const(d, struct amba_device, dev)
 
 #define amba_get_drvdata(d)	dev_get_drvdata(&d->dev)
 #define amba_set_drvdata(d,p)	dev_set_drvdata(&d->dev, p)
 
+/*
+ * use a macro to avoid include chaining to get THIS_MODULE
+ */
+#define amba_driver_register(drv) \
+	__amba_driver_register(drv, THIS_MODULE)
+
 #ifdef CONFIG_ARM_AMBA
-int amba_driver_register(struct amba_driver *);
+int __amba_driver_register(struct amba_driver *, struct module *);
 void amba_driver_unregister(struct amba_driver *);
+bool dev_is_amba(const struct device *dev);
 #else
-static inline int amba_driver_register(struct amba_driver *drv)
+static inline int __amba_driver_register(struct amba_driver *drv,
+					 struct module *owner)
 {
 	return -EINVAL;
 }
 static inline void amba_driver_unregister(struct amba_driver *drv)
 {
 }
+static inline bool dev_is_amba(const struct device *dev)
+{
+	return false;
+}
 #endif
 
 struct amba_device *amba_device_alloc(const char *, resource_size_t, size_t);
diff --git a/include/linux/amba/clcd-regs.h b/include/linux/amba/clcd-regs.h
deleted file mode 100644
index 421b0fa90d6a..000000000000
--- a/include/linux/amba/clcd-regs.h
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * David A Rusling
- *
- * Copyright (C) 2001 ARM Limited
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-
-#ifndef AMBA_CLCD_REGS_H
-#define AMBA_CLCD_REGS_H
-
-/*
- * CLCD Controller Internal Register addresses
- */
-#define CLCD_TIM0		0x00000000
-#define CLCD_TIM1 		0x00000004
-#define CLCD_TIM2 		0x00000008
-#define CLCD_TIM3 		0x0000000c
-#define CLCD_UBAS 		0x00000010
-#define CLCD_LBAS 		0x00000014
-
-#define CLCD_PL110_IENB		0x00000018
-#define CLCD_PL110_CNTL		0x0000001c
-#define CLCD_PL110_STAT		0x00000020
-#define CLCD_PL110_INTR 	0x00000024
-#define CLCD_PL110_UCUR		0x00000028
-#define CLCD_PL110_LCUR		0x0000002C
-
-#define CLCD_PL111_CNTL		0x00000018
-#define CLCD_PL111_IENB		0x0000001c
-#define CLCD_PL111_RIS		0x00000020
-#define CLCD_PL111_MIS		0x00000024
-#define CLCD_PL111_ICR		0x00000028
-#define CLCD_PL111_UCUR		0x0000002c
-#define CLCD_PL111_LCUR		0x00000030
-
-#define CLCD_PALL 		0x00000200
-#define CLCD_PALETTE		0x00000200
-
-#define TIM2_PCD_LO_MASK	GENMASK(4, 0)
-#define TIM2_PCD_LO_BITS	5
-#define TIM2_CLKSEL		(1 << 5)
-#define TIM2_ACB_MASK		GENMASK(10, 6)
-#define TIM2_IVS		(1 << 11)
-#define TIM2_IHS		(1 << 12)
-#define TIM2_IPC		(1 << 13)
-#define TIM2_IOE		(1 << 14)
-#define TIM2_BCD		(1 << 26)
-#define TIM2_PCD_HI_MASK	GENMASK(31, 27)
-#define TIM2_PCD_HI_BITS	5
-#define TIM2_PCD_HI_SHIFT	27
-
-#define CNTL_LCDEN		(1 << 0)
-#define CNTL_LCDBPP1		(0 << 1)
-#define CNTL_LCDBPP2		(1 << 1)
-#define CNTL_LCDBPP4		(2 << 1)
-#define CNTL_LCDBPP8		(3 << 1)
-#define CNTL_LCDBPP16		(4 << 1)
-#define CNTL_LCDBPP16_565	(6 << 1)
-#define CNTL_LCDBPP16_444	(7 << 1)
-#define CNTL_LCDBPP24		(5 << 1)
-#define CNTL_LCDBW		(1 << 4)
-#define CNTL_LCDTFT		(1 << 5)
-#define CNTL_LCDMONO8		(1 << 6)
-#define CNTL_LCDDUAL		(1 << 7)
-#define CNTL_BGR		(1 << 8)
-#define CNTL_BEBO		(1 << 9)
-#define CNTL_BEPO		(1 << 10)
-#define CNTL_LCDPWR		(1 << 11)
-#define CNTL_LCDVCOMP(x)	((x) << 12)
-#define CNTL_LDMAFIFOTIME	(1 << 15)
-#define CNTL_WATERMARK		(1 << 16)
-
-/* ST Microelectronics variant bits */
-#define CNTL_ST_1XBPP_444	0x0
-#define CNTL_ST_1XBPP_5551	(1 << 17)
-#define CNTL_ST_1XBPP_565	(1 << 18)
-#define CNTL_ST_CDWID_12	0x0
-#define CNTL_ST_CDWID_16	(1 << 19)
-#define CNTL_ST_CDWID_18	(1 << 20)
-#define CNTL_ST_CDWID_24	((1 << 19)|(1 << 20))
-#define CNTL_ST_CEAEN		(1 << 21)
-#define CNTL_ST_LCDBPP24_PACKED	(6 << 1)
-
-#endif /* AMBA_CLCD_REGS_H */
diff --git a/include/linux/amba/clcd.h b/include/linux/amba/clcd.h
deleted file mode 100644
index b6e0cbeaf533..000000000000
--- a/include/linux/amba/clcd.h
+++ /dev/null
@@ -1,290 +0,0 @@
-/*
- * linux/include/asm-arm/hardware/amba_clcd.h -- Integrator LCD panel.
- *
- * David A Rusling
- *
- * Copyright (C) 2001 ARM Limited
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file COPYING in the main directory of this archive
- * for more details.
- */
-#include <linux/fb.h>
-#include <linux/amba/clcd-regs.h>
-
-enum {
-	/* individual formats */
-	CLCD_CAP_RGB444		= (1 << 0),
-	CLCD_CAP_RGB5551	= (1 << 1),
-	CLCD_CAP_RGB565		= (1 << 2),
-	CLCD_CAP_RGB888		= (1 << 3),
-	CLCD_CAP_BGR444		= (1 << 4),
-	CLCD_CAP_BGR5551	= (1 << 5),
-	CLCD_CAP_BGR565		= (1 << 6),
-	CLCD_CAP_BGR888		= (1 << 7),
-
-	/* connection layouts */
-	CLCD_CAP_444		= CLCD_CAP_RGB444 | CLCD_CAP_BGR444,
-	CLCD_CAP_5551		= CLCD_CAP_RGB5551 | CLCD_CAP_BGR5551,
-	CLCD_CAP_565		= CLCD_CAP_RGB565 | CLCD_CAP_BGR565,
-	CLCD_CAP_888		= CLCD_CAP_RGB888 | CLCD_CAP_BGR888,
-
-	/* red/blue ordering */
-	CLCD_CAP_RGB		= CLCD_CAP_RGB444 | CLCD_CAP_RGB5551 |
-				  CLCD_CAP_RGB565 | CLCD_CAP_RGB888,
-	CLCD_CAP_BGR		= CLCD_CAP_BGR444 | CLCD_CAP_BGR5551 |
-				  CLCD_CAP_BGR565 | CLCD_CAP_BGR888,
-
-	CLCD_CAP_ALL		= CLCD_CAP_BGR | CLCD_CAP_RGB,
-};
-
-struct backlight_device;
-
-struct clcd_panel {
-	struct fb_videomode	mode;
-	signed short		width;	/* width in mm */
-	signed short		height;	/* height in mm */
-	u32			tim2;
-	u32			tim3;
-	u32			cntl;
-	u32			caps;
-	unsigned int		bpp:8,
-				fixedtimings:1,
-				grayscale:1;
-	unsigned int		connector;
-	struct backlight_device	*backlight;
-	/*
-	 * If the B/R lines are switched between the CLCD
-	 * and the panel we need to know this and not try to
-	 * compensate with the BGR bit in the control register.
-	 */
-	bool			bgr_connection;
-};
-
-struct clcd_regs {
-	u32			tim0;
-	u32			tim1;
-	u32			tim2;
-	u32			tim3;
-	u32			cntl;
-	unsigned long		pixclock;
-};
-
-struct clcd_fb;
-
-/*
- * the board-type specific routines
- */
-struct clcd_board {
-	const char *name;
-
-	/*
-	 * Optional.  Hardware capability flags.
-	 */
-	u32	caps;
-
-	/*
-	 * Optional.  Check whether the var structure is acceptable
-	 * for this display.
-	 */
-	int	(*check)(struct clcd_fb *fb, struct fb_var_screeninfo *var);
-
-	/*
-	 * Compulsory.  Decode fb->fb.var into regs->*.  In the case of
-	 * fixed timing, set regs->* to the register values required.
-	 */
-	void	(*decode)(struct clcd_fb *fb, struct clcd_regs *regs);
-
-	/*
-	 * Optional.  Disable any extra display hardware.
-	 */
-	void	(*disable)(struct clcd_fb *);
-
-	/*
-	 * Optional.  Enable any extra display hardware.
-	 */
-	void	(*enable)(struct clcd_fb *);
-
-	/*
-	 * Setup platform specific parts of CLCD driver
-	 */
-	int	(*setup)(struct clcd_fb *);
-
-	/*
-	 * mmap the framebuffer memory
-	 */
-	int	(*mmap)(struct clcd_fb *, struct vm_area_struct *);
-
-	/*
-	 * Remove platform specific parts of CLCD driver
-	 */
-	void	(*remove)(struct clcd_fb *);
-};
-
-struct amba_device;
-struct clk;
-
-/* this data structure describes each frame buffer device we find */
-struct clcd_fb {
-	struct fb_info		fb;
-	struct amba_device	*dev;
-	struct clk		*clk;
-	struct clcd_panel	*panel;
-	struct clcd_board	*board;
-	void			*board_data;
-	void __iomem		*regs;
-	u16			off_ienb;
-	u16			off_cntl;
-	u32			clcd_cntl;
-	u32			cmap[16];
-	bool			clk_enabled;
-};
-
-static inline void clcdfb_decode(struct clcd_fb *fb, struct clcd_regs *regs)
-{
-	struct fb_var_screeninfo *var = &fb->fb.var;
-	u32 val, cpl;
-
-	/*
-	 * Program the CLCD controller registers and start the CLCD
-	 */
-	val = ((var->xres / 16) - 1) << 2;
-	val |= (var->hsync_len - 1) << 8;
-	val |= (var->right_margin - 1) << 16;
-	val |= (var->left_margin - 1) << 24;
-	regs->tim0 = val;
-
-	val = var->yres;
-	if (fb->panel->cntl & CNTL_LCDDUAL)
-		val /= 2;
-	val -= 1;
-	val |= (var->vsync_len - 1) << 10;
-	val |= var->lower_margin << 16;
-	val |= var->upper_margin << 24;
-	regs->tim1 = val;
-
-	val = fb->panel->tim2;
-	val |= var->sync & FB_SYNC_HOR_HIGH_ACT  ? 0 : TIM2_IHS;
-	val |= var->sync & FB_SYNC_VERT_HIGH_ACT ? 0 : TIM2_IVS;
-
-	cpl = var->xres_virtual;
-	if (fb->panel->cntl & CNTL_LCDTFT)	  /* TFT */
-		/* / 1 */;
-	else if (!var->grayscale)		  /* STN color */
-		cpl = cpl * 8 / 3;
-	else if (fb->panel->cntl & CNTL_LCDMONO8) /* STN monochrome, 8bit */
-		cpl /= 8;
-	else					  /* STN monochrome, 4bit */
-		cpl /= 4;
-
-	regs->tim2 = val | ((cpl - 1) << 16);
-
-	regs->tim3 = fb->panel->tim3;
-
-	val = fb->panel->cntl;
-	if (var->grayscale)
-		val |= CNTL_LCDBW;
-
-	if (fb->panel->caps && fb->board->caps && var->bits_per_pixel >= 16) {
-		/*
-		 * if board and panel supply capabilities, we can support
-		 * changing BGR/RGB depending on supplied parameters. Here
-		 * we switch to what the framebuffer is providing if need
-		 * be, so if the framebuffer is BGR but the display connection
-		 * is RGB (first case) we switch it around. Vice versa mutatis
-		 * mutandis if the framebuffer is RGB but the display connection
-		 * is BGR, we flip it around.
-		 */
-		if (var->red.offset == 0)
-			val &= ~CNTL_BGR;
-		else
-			val |= CNTL_BGR;
-		if (fb->panel->bgr_connection)
-			val ^= CNTL_BGR;
-	}
-
-	switch (var->bits_per_pixel) {
-	case 1:
-		val |= CNTL_LCDBPP1;
-		break;
-	case 2:
-		val |= CNTL_LCDBPP2;
-		break;
-	case 4:
-		val |= CNTL_LCDBPP4;
-		break;
-	case 8:
-		val |= CNTL_LCDBPP8;
-		break;
-	case 16:
-		/*
-		 * PL110 cannot choose between 5551 and 565 modes in its
-		 * control register.  It is possible to use 565 with
-		 * custom external wiring.
-		 */
-		if (amba_part(fb->dev) == 0x110 ||
-		    var->green.length == 5)
-			val |= CNTL_LCDBPP16;
-		else if (var->green.length == 6)
-			val |= CNTL_LCDBPP16_565;
-		else
-			val |= CNTL_LCDBPP16_444;
-		break;
-	case 32:
-		val |= CNTL_LCDBPP24;
-		break;
-	}
-
-	regs->cntl = val;
-	regs->pixclock = var->pixclock;
-}
-
-static inline int clcdfb_check(struct clcd_fb *fb, struct fb_var_screeninfo *var)
-{
-	var->xres_virtual = var->xres = (var->xres + 15) & ~15;
-	var->yres_virtual = var->yres = (var->yres + 1) & ~1;
-
-#define CHECK(e,l,h) (var->e < l || var->e > h)
-	if (CHECK(right_margin, (5+1), 256) ||	/* back porch */
-	    CHECK(left_margin, (5+1), 256) ||	/* front porch */
-	    CHECK(hsync_len, (5+1), 256) ||
-	    var->xres > 4096 ||
-	    var->lower_margin > 255 ||		/* back porch */
-	    var->upper_margin > 255 ||		/* front porch */
-	    var->vsync_len > 32 ||
-	    var->yres > 1024)
-		return -EINVAL;
-#undef CHECK
-
-	/* single panel mode: PCD = max(PCD, 1) */
-	/* dual panel mode: PCD = max(PCD, 5) */
-
-	/*
-	 * You can't change the grayscale setting, and
-	 * we can only do non-interlaced video.
-	 */
-	if (var->grayscale != fb->fb.var.grayscale ||
-	    (var->vmode & FB_VMODE_MASK) != FB_VMODE_NONINTERLACED)
-		return -EINVAL;
-
-#define CHECK(e) (var->e != fb->fb.var.e)
-	if (fb->panel->fixedtimings &&
-	    (CHECK(xres)		||
-	     CHECK(yres)		||
-	     CHECK(bits_per_pixel)	||
-	     CHECK(pixclock)		||
-	     CHECK(left_margin)		||
-	     CHECK(right_margin)	||
-	     CHECK(upper_margin)	||
-	     CHECK(lower_margin)	||
-	     CHECK(hsync_len)		||
-	     CHECK(vsync_len)		||
-	     CHECK(sync)))
-		return -EINVAL;
-#undef CHECK
-
-	var->nonstd = 0;
-	var->accel_flags = 0;
-
-	return 0;
-}
diff --git a/include/linux/amba/pl022.h b/include/linux/amba/pl022.h
index 9bf58aac0df2..d7b07d0311e1 100644
--- a/include/linux/amba/pl022.h
+++ b/include/linux/amba/pl022.h
@@ -16,6 +16,7 @@
 #ifndef _SSP_PL022_H
 #define _SSP_PL022_H
 
+#include <linux/dmaengine.h>
 #include <linux/types.h>
 
 /**
@@ -224,6 +225,7 @@ struct dma_chan;
  * struct pl022_ssp_master - device.platform_data for SPI controller devices.
  * @bus_id: identifier for this bus
  * @enable_dma: if true enables DMA driven transfers.
+ * @dma_filter: callback filter for dma_request_channel.
  * @dma_rx_param: parameter to locate an RX DMA channel.
  * @dma_tx_param: parameter to locate a TX DMA channel.
  * @autosuspend_delay: delay in ms following transfer completion before the
@@ -235,7 +237,7 @@ struct dma_chan;
 struct pl022_ssp_controller {
 	u16 bus_id;
 	u8 enable_dma:1;
-	bool (*dma_filter)(struct dma_chan *chan, void *filter_param);
+	dma_filter_fn dma_filter;
 	void *dma_rx_param;
 	void *dma_tx_param;
 	int autosuspend_delay;
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index a1307b58cc2c..9120de05ead0 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -10,6 +10,11 @@
 #ifndef ASM_ARM_HARDWARE_SERIAL_AMBA_H
 #define ASM_ARM_HARDWARE_SERIAL_AMBA_H
 
+#ifndef __ASSEMBLY__
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#endif
+
 #include <linux/types.h>
 
 /* -------------------------------------------------------------------------------
@@ -70,141 +75,145 @@
 #define ZX_UART011_ICR		0x4c
 #define ZX_UART011_DMACR	0x50
 
-#define UART011_DR_OE		(1 << 11)
-#define UART011_DR_BE		(1 << 10)
-#define UART011_DR_PE		(1 << 9)
-#define UART011_DR_FE		(1 << 8)
-
-#define UART01x_RSR_OE 		0x08
-#define UART01x_RSR_BE 		0x04
-#define UART01x_RSR_PE 		0x02
-#define UART01x_RSR_FE 		0x01
-
-#define UART011_FR_RI		0x100
-#define UART011_FR_TXFE		0x080
-#define UART011_FR_RXFF		0x040
-#define UART01x_FR_TXFF		0x020
-#define UART01x_FR_RXFE		0x010
-#define UART01x_FR_BUSY		0x008
-#define UART01x_FR_DCD 		0x004
-#define UART01x_FR_DSR 		0x002
-#define UART01x_FR_CTS 		0x001
+#define UART011_DR_OE		BIT(11)
+#define UART011_DR_BE		BIT(10)
+#define UART011_DR_PE		BIT(9)
+#define UART011_DR_FE		BIT(8)
+
+#define UART01x_RSR_OE		BIT(3)
+#define UART01x_RSR_BE		BIT(2)
+#define UART01x_RSR_PE		BIT(1)
+#define UART01x_RSR_FE		BIT(0)
+
+#define UART011_FR_RI		BIT(8)
+#define UART011_FR_TXFE		BIT(7)
+#define UART011_FR_RXFF		BIT(6)
+#define UART01x_FR_TXFF		(1 << 5)	/* used in ASM */
+#define UART01x_FR_RXFE		BIT(4)
+#define UART01x_FR_BUSY		(1 << 3)	/* used in ASM */
+#define UART01x_FR_DCD		BIT(2)
+#define UART01x_FR_DSR		BIT(1)
+#define UART01x_FR_CTS		BIT(0)
 #define UART01x_FR_TMSK		(UART01x_FR_TXFF + UART01x_FR_BUSY)
 
 /*
  * Some bits of Flag Register on ZTE device have different position from
  * standard ones.
  */
-#define ZX_UART01x_FR_BUSY	0x100
-#define ZX_UART01x_FR_DSR	0x008
-#define ZX_UART01x_FR_CTS	0x002
-#define ZX_UART011_FR_RI	0x001
-
-#define UART011_CR_CTSEN	0x8000	/* CTS hardware flow control */
-#define UART011_CR_RTSEN	0x4000	/* RTS hardware flow control */
-#define UART011_CR_OUT2		0x2000	/* OUT2 */
-#define UART011_CR_OUT1		0x1000	/* OUT1 */
-#define UART011_CR_RTS		0x0800	/* RTS */
-#define UART011_CR_DTR		0x0400	/* DTR */
-#define UART011_CR_RXE		0x0200	/* receive enable */
-#define UART011_CR_TXE		0x0100	/* transmit enable */
-#define UART011_CR_LBE		0x0080	/* loopback enable */
-#define UART010_CR_RTIE		0x0040
-#define UART010_CR_TIE 		0x0020
-#define UART010_CR_RIE 		0x0010
-#define UART010_CR_MSIE		0x0008
-#define ST_UART011_CR_OVSFACT	0x0008	/* Oversampling factor */
-#define UART01x_CR_IIRLP	0x0004	/* SIR low power mode */
-#define UART01x_CR_SIREN	0x0002	/* SIR enable */
-#define UART01x_CR_UARTEN	0x0001	/* UART enable */
- 
-#define UART011_LCRH_SPS	0x80
+#define ZX_UART01x_FR_BUSY	BIT(8)
+#define ZX_UART01x_FR_DSR	BIT(3)
+#define ZX_UART01x_FR_CTS	BIT(1)
+#define ZX_UART011_FR_RI	BIT(0)
+
+#define UART011_CR_CTSEN	BIT(15)	/* CTS hardware flow control */
+#define UART011_CR_RTSEN	BIT(14)	/* RTS hardware flow control */
+#define UART011_CR_OUT2		BIT(13)	/* OUT2 */
+#define UART011_CR_OUT1		BIT(12)	/* OUT1 */
+#define UART011_CR_RTS		BIT(11)	/* RTS */
+#define UART011_CR_DTR		BIT(10)	/* DTR */
+#define UART011_CR_RXE		BIT(9)	/* receive enable */
+#define UART011_CR_TXE		BIT(8)	/* transmit enable */
+#define UART011_CR_LBE		BIT(7)	/* loopback enable */
+#define UART010_CR_RTIE		BIT(6)
+#define UART010_CR_TIE		BIT(5)
+#define UART010_CR_RIE		BIT(4)
+#define UART010_CR_MSIE		BIT(3)
+#define ST_UART011_CR_OVSFACT	BIT(3)	/* Oversampling factor */
+#define UART01x_CR_IIRLP	BIT(2)	/* SIR low power mode */
+#define UART01x_CR_SIREN	BIT(1)	/* SIR enable */
+#define UART01x_CR_UARTEN	BIT(0)	/* UART enable */
+
+#define UART011_LCRH_SPS	BIT(7)
 #define UART01x_LCRH_WLEN_8	0x60
 #define UART01x_LCRH_WLEN_7	0x40
 #define UART01x_LCRH_WLEN_6	0x20
 #define UART01x_LCRH_WLEN_5	0x00
-#define UART01x_LCRH_FEN	0x10
-#define UART01x_LCRH_STP2	0x08
-#define UART01x_LCRH_EPS	0x04
-#define UART01x_LCRH_PEN	0x02
-#define UART01x_LCRH_BRK	0x01
-
-#define ST_UART011_DMAWM_RX_1	(0 << 3)
-#define ST_UART011_DMAWM_RX_2	(1 << 3)
-#define ST_UART011_DMAWM_RX_4	(2 << 3)
-#define ST_UART011_DMAWM_RX_8	(3 << 3)
-#define ST_UART011_DMAWM_RX_16	(4 << 3)
-#define ST_UART011_DMAWM_RX_32	(5 << 3)
-#define ST_UART011_DMAWM_RX_48	(6 << 3)
-#define ST_UART011_DMAWM_TX_1	0
-#define ST_UART011_DMAWM_TX_2	1
-#define ST_UART011_DMAWM_TX_4	2
-#define ST_UART011_DMAWM_TX_8	3
-#define ST_UART011_DMAWM_TX_16	4
-#define ST_UART011_DMAWM_TX_32	5
-#define ST_UART011_DMAWM_TX_48	6
-
-#define UART010_IIR_RTIS	0x08
-#define UART010_IIR_TIS		0x04
-#define UART010_IIR_RIS		0x02
-#define UART010_IIR_MIS		0x01
-
-#define UART011_IFLS_RX1_8	(0 << 3)
-#define UART011_IFLS_RX2_8	(1 << 3)
-#define UART011_IFLS_RX4_8	(2 << 3)
-#define UART011_IFLS_RX6_8	(3 << 3)
-#define UART011_IFLS_RX7_8	(4 << 3)
-#define UART011_IFLS_TX1_8	(0 << 0)
-#define UART011_IFLS_TX2_8	(1 << 0)
-#define UART011_IFLS_TX4_8	(2 << 0)
-#define UART011_IFLS_TX6_8	(3 << 0)
-#define UART011_IFLS_TX7_8	(4 << 0)
+#define UART01x_LCRH_FEN	BIT(4)
+#define UART01x_LCRH_STP2	BIT(3)
+#define UART01x_LCRH_EPS	BIT(2)
+#define UART01x_LCRH_PEN	BIT(1)
+#define UART01x_LCRH_BRK	BIT(0)
+
+#define ST_UART011_DMAWM_RX	GENMASK(5, 3)
+#define ST_UART011_DMAWM_RX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 0)
+#define ST_UART011_DMAWM_RX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 1)
+#define ST_UART011_DMAWM_RX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 2)
+#define ST_UART011_DMAWM_RX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 3)
+#define ST_UART011_DMAWM_RX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 4)
+#define ST_UART011_DMAWM_RX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 5)
+#define ST_UART011_DMAWM_RX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_RX, 6)
+#define ST_UART011_DMAWM_TX	GENMASK(2, 0)
+#define ST_UART011_DMAWM_TX_1	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 0)
+#define ST_UART011_DMAWM_TX_2	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 1)
+#define ST_UART011_DMAWM_TX_4	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 2)
+#define ST_UART011_DMAWM_TX_8	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 3)
+#define ST_UART011_DMAWM_TX_16	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 4)
+#define ST_UART011_DMAWM_TX_32	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 5)
+#define ST_UART011_DMAWM_TX_48	FIELD_PREP_CONST(ST_UART011_DMAWM_TX, 6)
+
+#define UART010_IIR_RTIS	BIT(3)
+#define UART010_IIR_TIS		BIT(2)
+#define UART010_IIR_RIS		BIT(1)
+#define UART010_IIR_MIS		BIT(0)
+
+#define UART011_IFLS_RXIFLSEL	GENMASK(5, 3)
+#define UART011_IFLS_RX1_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 0)
+#define UART011_IFLS_RX2_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 1)
+#define UART011_IFLS_RX4_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 2)
+#define UART011_IFLS_RX6_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 3)
+#define UART011_IFLS_RX7_8	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 4)
+#define UART011_IFLS_TXIFLSEL	GENMASK(2, 0)
+#define UART011_IFLS_TX1_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 0)
+#define UART011_IFLS_TX2_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 1)
+#define UART011_IFLS_TX4_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 2)
+#define UART011_IFLS_TX6_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 3)
+#define UART011_IFLS_TX7_8	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 4)
 /* special values for ST vendor with deeper fifo */
-#define UART011_IFLS_RX_HALF	(5 << 3)
-#define UART011_IFLS_TX_HALF	(5 << 0)
-
-#define UART011_OEIM		(1 << 10)	/* overrun error interrupt mask */
-#define UART011_BEIM		(1 << 9)	/* break error interrupt mask */
-#define UART011_PEIM		(1 << 8)	/* parity error interrupt mask */
-#define UART011_FEIM		(1 << 7)	/* framing error interrupt mask */
-#define UART011_RTIM		(1 << 6)	/* receive timeout interrupt mask */
-#define UART011_TXIM		(1 << 5)	/* transmit interrupt mask */
-#define UART011_RXIM		(1 << 4)	/* receive interrupt mask */
-#define UART011_DSRMIM		(1 << 3)	/* DSR interrupt mask */
-#define UART011_DCDMIM		(1 << 2)	/* DCD interrupt mask */
-#define UART011_CTSMIM		(1 << 1)	/* CTS interrupt mask */
-#define UART011_RIMIM		(1 << 0)	/* RI interrupt mask */
-
-#define UART011_OEIS		(1 << 10)	/* overrun error interrupt status */
-#define UART011_BEIS		(1 << 9)	/* break error interrupt status */
-#define UART011_PEIS		(1 << 8)	/* parity error interrupt status */
-#define UART011_FEIS		(1 << 7)	/* framing error interrupt status */
-#define UART011_RTIS		(1 << 6)	/* receive timeout interrupt status */
-#define UART011_TXIS		(1 << 5)	/* transmit interrupt status */
-#define UART011_RXIS		(1 << 4)	/* receive interrupt status */
-#define UART011_DSRMIS		(1 << 3)	/* DSR interrupt status */
-#define UART011_DCDMIS		(1 << 2)	/* DCD interrupt status */
-#define UART011_CTSMIS		(1 << 1)	/* CTS interrupt status */
-#define UART011_RIMIS		(1 << 0)	/* RI interrupt status */
-
-#define UART011_OEIC		(1 << 10)	/* overrun error interrupt clear */
-#define UART011_BEIC		(1 << 9)	/* break error interrupt clear */
-#define UART011_PEIC		(1 << 8)	/* parity error interrupt clear */
-#define UART011_FEIC		(1 << 7)	/* framing error interrupt clear */
-#define UART011_RTIC		(1 << 6)	/* receive timeout interrupt clear */
-#define UART011_TXIC		(1 << 5)	/* transmit interrupt clear */
-#define UART011_RXIC		(1 << 4)	/* receive interrupt clear */
-#define UART011_DSRMIC		(1 << 3)	/* DSR interrupt clear */
-#define UART011_DCDMIC		(1 << 2)	/* DCD interrupt clear */
-#define UART011_CTSMIC		(1 << 1)	/* CTS interrupt clear */
-#define UART011_RIMIC		(1 << 0)	/* RI interrupt clear */
-
-#define UART011_DMAONERR	(1 << 2)	/* disable dma on error */
-#define UART011_TXDMAE		(1 << 1)	/* enable transmit dma */
-#define UART011_RXDMAE		(1 << 0)	/* enable receive dma */
-
-#define UART01x_RSR_ANY		(UART01x_RSR_OE|UART01x_RSR_BE|UART01x_RSR_PE|UART01x_RSR_FE)
-#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS)
+#define UART011_IFLS_RX_HALF	FIELD_PREP_CONST(UART011_IFLS_RXIFLSEL, 5)
+#define UART011_IFLS_TX_HALF	FIELD_PREP_CONST(UART011_IFLS_TXIFLSEL, 5)
+
+#define UART011_OEIM		BIT(10)	/* overrun error interrupt mask */
+#define UART011_BEIM		BIT(9)	/* break error interrupt mask */
+#define UART011_PEIM		BIT(8)	/* parity error interrupt mask */
+#define UART011_FEIM		BIT(7)	/* framing error interrupt mask */
+#define UART011_RTIM		BIT(6)	/* receive timeout interrupt mask */
+#define UART011_TXIM		BIT(5)	/* transmit interrupt mask */
+#define UART011_RXIM		BIT(4)	/* receive interrupt mask */
+#define UART011_DSRMIM		BIT(3)	/* DSR interrupt mask */
+#define UART011_DCDMIM		BIT(2)	/* DCD interrupt mask */
+#define UART011_CTSMIM		BIT(1)	/* CTS interrupt mask */
+#define UART011_RIMIM		BIT(0)	/* RI interrupt mask */
+
+#define UART011_OEIS		BIT(10)	/* overrun error interrupt status */
+#define UART011_BEIS		BIT(9)	/* break error interrupt status */
+#define UART011_PEIS		BIT(8)	/* parity error interrupt status */
+#define UART011_FEIS		BIT(7)	/* framing error interrupt status */
+#define UART011_RTIS		BIT(6)	/* receive timeout interrupt status */
+#define UART011_TXIS		BIT(5)	/* transmit interrupt status */
+#define UART011_RXIS		BIT(4)	/* receive interrupt status */
+#define UART011_DSRMIS		BIT(3)	/* DSR interrupt status */
+#define UART011_DCDMIS		BIT(2)	/* DCD interrupt status */
+#define UART011_CTSMIS		BIT(1)	/* CTS interrupt status */
+#define UART011_RIMIS		BIT(0)	/* RI interrupt status */
+
+#define UART011_OEIC		BIT(10)	/* overrun error interrupt clear */
+#define UART011_BEIC		BIT(9)	/* break error interrupt clear */
+#define UART011_PEIC		BIT(8)	/* parity error interrupt clear */
+#define UART011_FEIC		BIT(7)	/* framing error interrupt clear */
+#define UART011_RTIC		BIT(6)	/* receive timeout interrupt clear */
+#define UART011_TXIC		BIT(5)	/* transmit interrupt clear */
+#define UART011_RXIC		BIT(4)	/* receive interrupt clear */
+#define UART011_DSRMIC		BIT(3)	/* DSR interrupt clear */
+#define UART011_DCDMIC		BIT(2)	/* DCD interrupt clear */
+#define UART011_CTSMIC		BIT(1)	/* CTS interrupt clear */
+#define UART011_RIMIC		BIT(0)	/* RI interrupt clear */
+
+#define UART011_DMAONERR	BIT(2)	/* disable dma on error */
+#define UART011_TXDMAE		BIT(1)	/* enable transmit dma */
+#define UART011_RXDMAE		BIT(0)	/* enable receive dma */
+
+#define UART01x_RSR_ANY		(UART01x_RSR_OE | UART01x_RSR_BE | UART01x_RSR_PE | UART01x_RSR_FE)
+#define UART01x_FR_MODEM_ANY	(UART01x_FR_DCD | UART01x_FR_DSR | UART01x_FR_CTS)
 
 #ifndef __ASSEMBLY__
 struct amba_device; /* in uncompress this is included but amba/bus.h is not */
@@ -220,8 +229,8 @@ struct amba_pl011_data {
 	bool dma_rx_poll_enable;
 	unsigned int dma_rx_poll_rate;
 	unsigned int dma_rx_poll_timeout;
-        void (*init) (void);
-	void (*exit) (void);
+	void (*init)(void);
+	void (*exit)(void);
 };
 #endif
 
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 953e6f12fa1c..edcee9f5335a 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -12,151 +12,16 @@
 
 struct amd_iommu;
 
-/*
- * This is mainly used to communicate information back-and-forth
- * between SVM and IOMMU for setting up and tearing down posted
- * interrupt
- */
-struct amd_iommu_pi_data {
-	u32 ga_tag;
-	u32 prev_ga_tag;
-	u64 base;
-	bool is_guest_mode;
-	struct vcpu_data *vcpu_data;
-	void *ir_data;
-};
-
 #ifdef CONFIG_AMD_IOMMU
 
 struct task_struct;
 struct pci_dev;
 
-extern int amd_iommu_detect(void);
-extern int amd_iommu_init_hardware(void);
-
-/**
- * amd_iommu_init_device() - Init device for use with IOMMUv2 driver
- * @pdev: The PCI device to initialize
- * @pasids: Number of PASIDs to support for this device
- *
- * This function does all setup for the device pdev so that it can be
- * used with IOMMUv2.
- * Returns 0 on success or negative value on error.
- */
-extern int amd_iommu_init_device(struct pci_dev *pdev, int pasids);
+extern void amd_iommu_detect(void);
 
-/**
- * amd_iommu_free_device() - Free all IOMMUv2 related device resources
- *			     and disable IOMMUv2 usage for this device
- * @pdev: The PCI device to disable IOMMUv2 usage for'
- */
-extern void amd_iommu_free_device(struct pci_dev *pdev);
-
-/**
- * amd_iommu_bind_pasid() - Bind a given task to a PASID on a device
- * @pdev: The PCI device to bind the task to
- * @pasid: The PASID on the device the task should be bound to
- * @task: the task to bind
- *
- * The function returns 0 on success or a negative value on error.
- */
-extern int amd_iommu_bind_pasid(struct pci_dev *pdev, u32 pasid,
-				struct task_struct *task);
-
-/**
- * amd_iommu_unbind_pasid() - Unbind a PASID from its task on
- *			      a device
- * @pdev: The device of the PASID
- * @pasid: The PASID to unbind
- *
- * When this function returns the device is no longer using the PASID
- * and the PASID is no longer bound to its task.
- */
-extern void amd_iommu_unbind_pasid(struct pci_dev *pdev, u32 pasid);
-
-/**
- * amd_iommu_set_invalid_ppr_cb() - Register a call-back for failed
- *				    PRI requests
- * @pdev: The PCI device the call-back should be registered for
- * @cb: The call-back function
- *
- * The IOMMUv2 driver invokes this call-back when it is unable to
- * successfully handle a PRI request. The device driver can then decide
- * which PRI response the device should see. Possible return values for
- * the call-back are:
- *
- * - AMD_IOMMU_INV_PRI_RSP_SUCCESS - Send SUCCESS back to the device
- * - AMD_IOMMU_INV_PRI_RSP_INVALID - Send INVALID back to the device
- * - AMD_IOMMU_INV_PRI_RSP_FAIL    - Send Failure back to the device,
- *				     the device is required to disable
- *				     PRI when it receives this response
- *
- * The function returns 0 on success or negative value on error.
- */
-#define AMD_IOMMU_INV_PRI_RSP_SUCCESS	0
-#define AMD_IOMMU_INV_PRI_RSP_INVALID	1
-#define AMD_IOMMU_INV_PRI_RSP_FAIL	2
-
-typedef int (*amd_iommu_invalid_ppr_cb)(struct pci_dev *pdev,
-					u32 pasid,
-					unsigned long address,
-					u16);
-
-extern int amd_iommu_set_invalid_ppr_cb(struct pci_dev *pdev,
-					amd_iommu_invalid_ppr_cb cb);
-
-#define PPR_FAULT_EXEC	(1 << 1)
-#define PPR_FAULT_READ  (1 << 2)
-#define PPR_FAULT_WRITE (1 << 5)
-#define PPR_FAULT_USER  (1 << 6)
-#define PPR_FAULT_RSVD  (1 << 7)
-#define PPR_FAULT_GN    (1 << 8)
-
-/**
- * amd_iommu_device_info() - Get information about IOMMUv2 support of a
- *			     PCI device
- * @pdev: PCI device to query information from
- * @info: A pointer to an amd_iommu_device_info structure which will contain
- *	  the information about the PCI device
- *
- * Returns 0 on success, negative value on error
- */
-
-#define AMD_IOMMU_DEVICE_FLAG_ATS_SUP     0x1    /* ATS feature supported */
-#define AMD_IOMMU_DEVICE_FLAG_PRI_SUP     0x2    /* PRI feature supported */
-#define AMD_IOMMU_DEVICE_FLAG_PASID_SUP   0x4    /* PASID context supported */
-#define AMD_IOMMU_DEVICE_FLAG_EXEC_SUP    0x8    /* Device may request execution
-						    on memory pages */
-#define AMD_IOMMU_DEVICE_FLAG_PRIV_SUP   0x10    /* Device may request
-						    super-user privileges */
-
-struct amd_iommu_device_info {
-	int max_pasids;
-	u32 flags;
-};
-
-extern int amd_iommu_device_info(struct pci_dev *pdev,
-				 struct amd_iommu_device_info *info);
-
-/**
- * amd_iommu_set_invalidate_ctx_cb() - Register a call-back for invalidating
- *				       a pasid context. This call-back is
- *				       invoked when the IOMMUv2 driver needs to
- *				       invalidate a PASID context, for example
- *				       because the task that is bound to that
- *				       context is about to exit.
- *
- * @pdev: The PCI device the call-back should be registered for
- * @cb: The call-back function
- */
-
-typedef void (*amd_iommu_invalidate_ctx)(struct pci_dev *pdev, u32 pasid);
-
-extern int amd_iommu_set_invalidate_ctx_cb(struct pci_dev *pdev,
-					   amd_iommu_invalidate_ctx cb);
 #else /* CONFIG_AMD_IOMMU */
 
-static inline int amd_iommu_detect(void) { return -ENODEV; }
+static inline void amd_iommu_detect(void) { }
 
 #endif /* CONFIG_AMD_IOMMU */
 
@@ -165,10 +30,8 @@ static inline int amd_iommu_detect(void) { return -ENODEV; }
 /* IOMMU AVIC Function */
 extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
 
-extern int
-amd_iommu_update_ga(int cpu, bool is_run, void *data);
-
-extern int amd_iommu_activate_guest_mode(void *data);
+extern int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr);
+extern int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr);
 extern int amd_iommu_deactivate_guest_mode(void *data);
 
 #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
@@ -179,13 +42,12 @@ amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
 	return 0;
 }
 
-static inline int
-amd_iommu_update_ga(int cpu, bool is_run, void *data)
+static inline int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr)
 {
 	return 0;
 }
 
-static inline int amd_iommu_activate_guest_mode(void *data)
+static inline int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr)
 {
 	return 0;
 }
@@ -206,8 +68,12 @@ int amd_iommu_pc_get_reg(struct amd_iommu *iommu, u8 bank, u8 cntr, u8 fxn,
 		u64 *value);
 struct amd_iommu *get_amd_iommu(unsigned int idx);
 
-#ifdef CONFIG_AMD_MEM_ENCRYPT
-int amd_iommu_snp_enable(void);
+#ifdef CONFIG_KVM_AMD_SEV
+int amd_iommu_snp_disable(void);
+extern bool amd_iommu_sev_tio_supported(void);
+#else
+static inline int amd_iommu_snp_disable(void) { return 0; }
+static inline bool amd_iommu_sev_tio_supported(void) { return false; }
 #endif
 
 #endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/include/linux/amd-pmf-io.h b/include/linux/amd-pmf-io.h
new file mode 100644
index 000000000000..6fa510f419c0
--- /dev/null
+++ b/include/linux/amd-pmf-io.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * AMD Platform Management Framework Interface
+ *
+ * Copyright (c) 2023, Advanced Micro Devices, Inc.
+ * All Rights Reserved.
+ *
+ * Authors: Shyam Sundar S K <Shyam-sundar.S-k@amd.com>
+ *          Basavaraj Natikar <Basavaraj.Natikar@amd.com>
+ */
+
+#ifndef AMD_PMF_IO_H
+#define AMD_PMF_IO_H
+
+#include <linux/types.h>
+
+/**
+ * enum sfh_message_type - Query the SFH message type
+ * @MT_HPD: Message ID to know the Human presence info from MP2 FW
+ * @MT_ALS: Message ID to know the Ambient light info from MP2 FW
+ * @MT_SRA: Message ID to know the SRA data from MP2 FW
+ */
+enum sfh_message_type {
+	MT_HPD,
+	MT_ALS,
+	MT_SRA,
+};
+
+/**
+ * enum sfh_hpd_info - Query the Human presence information
+ * @SFH_NOT_DETECTED: Check the HPD connection information from MP2 FW
+ * @SFH_USER_PRESENT: Check if the user is present from HPD sensor
+ * @SFH_USER_AWAY: Check if the user is away from HPD sensor
+ */
+enum sfh_hpd_info {
+	SFH_NOT_DETECTED,
+	SFH_USER_PRESENT,
+	SFH_USER_AWAY,
+};
+
+/**
+ * struct amd_sfh_info - get HPD sensor info from MP2 FW
+ * @ambient_light: Populates the ambient light information
+ * @user_present: Populates the user presence information
+ * @platform_type: Operating modes (clamshell, flat, tent, etc.)
+ * @laptop_placement: Device states (ontable, onlap, outbag)
+ */
+struct amd_sfh_info {
+	u32 ambient_light;
+	u8 user_present;
+	u32 platform_type;
+	u32 laptop_placement;
+};
+
+enum laptop_placement {
+	LP_UNKNOWN = 0,
+	ON_TABLE,
+	ON_LAP_MOTION,
+	IN_BAG,
+	OUT_OF_BAG,
+	LP_UNDEFINED,
+};
+
+int amd_get_sfh_info(struct amd_sfh_info *sfh_info, enum sfh_message_type op);
+#endif
diff --git a/include/linux/amd-pstate.h b/include/linux/amd-pstate.h
deleted file mode 100644
index c10ebf8c42e6..000000000000
--- a/include/linux/amd-pstate.h
+++ /dev/null
@@ -1,111 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * linux/include/linux/amd-pstate.h
- *
- * Copyright (C) 2022 Advanced Micro Devices, Inc.
- *
- * Author: Meng Li <li.meng@amd.com>
- */
-
-#ifndef _LINUX_AMD_PSTATE_H
-#define _LINUX_AMD_PSTATE_H
-
-#include <linux/pm_qos.h>
-
-#define AMD_CPPC_EPP_PERFORMANCE		0x00
-#define AMD_CPPC_EPP_BALANCE_PERFORMANCE	0x80
-#define AMD_CPPC_EPP_BALANCE_POWERSAVE		0xBF
-#define AMD_CPPC_EPP_POWERSAVE			0xFF
-
-/*********************************************************************
- *                        AMD P-state INTERFACE                       *
- *********************************************************************/
-/**
- * struct  amd_aperf_mperf
- * @aperf: actual performance frequency clock count
- * @mperf: maximum performance frequency clock count
- * @tsc:   time stamp counter
- */
-struct amd_aperf_mperf {
-	u64 aperf;
-	u64 mperf;
-	u64 tsc;
-};
-
-/**
- * struct amd_cpudata - private CPU data for AMD P-State
- * @cpu: CPU number
- * @req: constraint request to apply
- * @cppc_req_cached: cached performance request hints
- * @highest_perf: the maximum performance an individual processor may reach,
- *		  assuming ideal conditions
- * @nominal_perf: the maximum sustained performance level of the processor,
- *		  assuming ideal operating conditions
- * @lowest_nonlinear_perf: the lowest performance level at which nonlinear power
- *			   savings are achieved
- * @lowest_perf: the absolute lowest performance level of the processor
- * @max_freq: the frequency that mapped to highest_perf
- * @min_freq: the frequency that mapped to lowest_perf
- * @nominal_freq: the frequency that mapped to nominal_perf
- * @lowest_nonlinear_freq: the frequency that mapped to lowest_nonlinear_perf
- * @cur: Difference of Aperf/Mperf/tsc count between last and current sample
- * @prev: Last Aperf/Mperf/tsc count value read from register
- * @freq: current cpu frequency value
- * @boost_supported: check whether the Processor or SBIOS supports boost mode
- * @epp_policy: Last saved policy used to set energy-performance preference
- * @epp_cached: Cached CPPC energy-performance preference value
- * @policy: Cpufreq policy value
- * @cppc_cap1_cached Cached MSR_AMD_CPPC_CAP1 register value
- *
- * The amd_cpudata is key private data for each CPU thread in AMD P-State, and
- * represents all the attributes and goals that AMD P-State requests at runtime.
- */
-struct amd_cpudata {
-	int	cpu;
-
-	struct	freq_qos_request req[2];
-	u64	cppc_req_cached;
-
-	u32	highest_perf;
-	u32	nominal_perf;
-	u32	lowest_nonlinear_perf;
-	u32	lowest_perf;
-
-	u32	max_freq;
-	u32	min_freq;
-	u32	nominal_freq;
-	u32	lowest_nonlinear_freq;
-
-	struct amd_aperf_mperf cur;
-	struct amd_aperf_mperf prev;
-
-	u64	freq;
-	bool	boost_supported;
-
-	/* EPP feature related attributes*/
-	s16	epp_policy;
-	s16	epp_cached;
-	u32	policy;
-	u64	cppc_cap1_cached;
-	bool	suspended;
-};
-
-/*
- * enum amd_pstate_mode - driver working mode of amd pstate
- */
-enum amd_pstate_mode {
-	AMD_PSTATE_DISABLE = 0,
-	AMD_PSTATE_PASSIVE,
-	AMD_PSTATE_ACTIVE,
-	AMD_PSTATE_GUIDED,
-	AMD_PSTATE_MAX,
-};
-
-static const char * const amd_pstate_mode_string[] = {
-	[AMD_PSTATE_DISABLE]     = "disable",
-	[AMD_PSTATE_PASSIVE]     = "passive",
-	[AMD_PSTATE_ACTIVE]      = "active",
-	[AMD_PSTATE_GUIDED]      = "guided",
-	NULL,
-};
-#endif /* _LINUX_AMD_PSTATE_H */
diff --git a/include/linux/annotate.h b/include/linux/annotate.h
new file mode 100644
index 000000000000..2f1599c9e573
--- /dev/null
+++ b/include/linux/annotate.h
@@ -0,0 +1,127 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ANNOTATE_H
+#define _LINUX_ANNOTATE_H
+
+#include <linux/objtool_types.h>
+
+#ifdef CONFIG_OBJTOOL
+
+#define __ASM_ANNOTATE(section, label, type)				\
+	.pushsection section, "M", @progbits, 8;			\
+	.long label - ., type;						\
+	.popsection
+
+#ifndef __ASSEMBLY__
+
+#define ASM_ANNOTATE_LABEL(label, type)					\
+	__stringify(__ASM_ANNOTATE(.discard.annotate_insn, label, type))
+
+#define ASM_ANNOTATE(type)						\
+	"911: "								\
+	__stringify(__ASM_ANNOTATE(.discard.annotate_insn, 911b, type))
+
+#define ASM_ANNOTATE_DATA(type)						\
+	"912: "								\
+	__stringify(__ASM_ANNOTATE(.discard.annotate_data, 912b, type))
+
+#else /* __ASSEMBLY__ */
+
+.macro ANNOTATE type
+.Lhere_\@:
+	__ASM_ANNOTATE(.discard.annotate_insn, .Lhere_\@, \type)
+.endm
+
+.macro ANNOTATE_DATA type
+.Lhere_\@:
+	__ASM_ANNOTATE(.discard.annotate_data, .Lhere_\@, \type)
+.endm
+
+#endif /* __ASSEMBLY__ */
+
+#else /* !CONFIG_OBJTOOL */
+#ifndef __ASSEMBLY__
+#define ASM_ANNOTATE_LABEL(label, type) ""
+#define ASM_ANNOTATE(type)
+#define ASM_ANNOTATE_DATA(type)
+#else /* __ASSEMBLY__ */
+.macro ANNOTATE type
+.endm
+.macro ANNOTATE_DATA type
+.endm
+#endif /* __ASSEMBLY__ */
+#endif /* !CONFIG_OBJTOOL */
+
+#ifndef __ASSEMBLY__
+
+/*
+ * Annotate away the various 'relocation to !ENDBR` complaints; knowing that
+ * these relocations will never be used for indirect calls.
+ */
+#define ANNOTATE_NOENDBR		ASM_ANNOTATE(ANNOTYPE_NOENDBR)
+#define ANNOTATE_NOENDBR_SYM(sym)	asm(ASM_ANNOTATE_LABEL(sym, ANNOTYPE_NOENDBR))
+
+/*
+ * This should be used immediately before an indirect jump/call. It tells
+ * objtool the subsequent indirect jump/call is vouched safe for retpoline
+ * builds.
+ */
+#define ANNOTATE_RETPOLINE_SAFE		ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE)
+/*
+ * See linux/instrumentation.h
+ */
+#define ANNOTATE_INSTR_BEGIN(label)	ASM_ANNOTATE_LABEL(label, ANNOTYPE_INSTR_BEGIN)
+#define ANNOTATE_INSTR_END(label)	ASM_ANNOTATE_LABEL(label, ANNOTYPE_INSTR_END)
+/*
+ * objtool annotation to ignore the alternatives and only consider the original
+ * instruction(s).
+ */
+#define ANNOTATE_IGNORE_ALTERNATIVE	ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS)
+/*
+ * This macro indicates that the following intra-function call is valid.
+ * Any non-annotated intra-function call will cause objtool to issue a warning.
+ */
+#define ANNOTATE_INTRA_FUNCTION_CALL	ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL)
+/*
+ * Use objtool to validate the entry requirement that all code paths do
+ * VALIDATE_UNRET_END before RET.
+ *
+ * NOTE: The macro must be used at the beginning of a global symbol, otherwise
+ * it will be ignored.
+ */
+#define ANNOTATE_UNRET_BEGIN		ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN)
+/*
+ * This should be used to refer to an instruction that is considered
+ * terminating, like a noreturn CALL or UD2 when we know they are not -- eg
+ * WARN using UD2.
+ */
+#define ANNOTATE_REACHABLE(label)	ASM_ANNOTATE_LABEL(label, ANNOTYPE_REACHABLE)
+/*
+ * This should not be used; it annotates away CFI violations. There are a few
+ * valid use cases like kexec handover to the next kernel image, and there is
+ * no security concern there.
+ *
+ * There are also a few real issues annotated away, like EFI because we can't
+ * control the EFI code.
+ */
+#define ANNOTATE_NOCFI_SYM(sym)		asm(ASM_ANNOTATE_LABEL(sym, ANNOTYPE_NOCFI))
+
+/*
+ * Annotate a special section entry.  This emables livepatch module generation
+ * to find and extract individual special section entries as needed.
+ */
+#define ANNOTATE_DATA_SPECIAL		ASM_ANNOTATE_DATA(ANNOTYPE_DATA_SPECIAL)
+
+#else /* __ASSEMBLY__ */
+#define ANNOTATE_NOENDBR		ANNOTATE type=ANNOTYPE_NOENDBR
+#define ANNOTATE_RETPOLINE_SAFE		ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE
+/*	ANNOTATE_INSTR_BEGIN		ANNOTATE type=ANNOTYPE_INSTR_BEGIN */
+/*	ANNOTATE_INSTR_END		ANNOTATE type=ANNOTYPE_INSTR_END */
+#define ANNOTATE_IGNORE_ALTERNATIVE	ANNOTATE type=ANNOTYPE_IGNORE_ALTS
+#define ANNOTATE_INTRA_FUNCTION_CALL	ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL
+#define ANNOTATE_UNRET_BEGIN		ANNOTATE type=ANNOTYPE_UNRET_BEGIN
+#define ANNOTATE_REACHABLE		ANNOTATE type=ANNOTYPE_REACHABLE
+#define ANNOTATE_NOCFI_SYM		ANNOTATE type=ANNOTYPE_NOCFI
+#define ANNOTATE_DATA_SPECIAL		ANNOTATE_DATA type=ANNOTYPE_DATA_SPECIAL
+#endif /* __ASSEMBLY__ */
+
+#endif /* _LINUX_ANNOTATE_H */
diff --git a/include/linux/anon_inodes.h b/include/linux/anon_inodes.h
index 5deaddbd7927..edef565c2a1a 100644
--- a/include/linux/anon_inodes.h
+++ b/include/linux/anon_inodes.h
@@ -9,19 +9,24 @@
 #ifndef _LINUX_ANON_INODES_H
 #define _LINUX_ANON_INODES_H
 
+#include <linux/types.h>
+
 struct file_operations;
 struct inode;
 
 struct file *anon_inode_getfile(const char *name,
 				const struct file_operations *fops,
 				void *priv, int flags);
-struct file *anon_inode_getfile_secure(const char *name,
+struct file *anon_inode_getfile_fmode(const char *name,
+				const struct file_operations *fops,
+				void *priv, int flags, fmode_t f_mode);
+struct file *anon_inode_create_getfile(const char *name,
 				       const struct file_operations *fops,
 				       void *priv, int flags,
 				       const struct inode *context_inode);
 int anon_inode_getfd(const char *name, const struct file_operations *fops,
 		     void *priv, int flags);
-int anon_inode_getfd_secure(const char *name,
+int anon_inode_create_getfd(const char *name,
 			    const struct file_operations *fops,
 			    void *priv, int flags,
 			    const struct inode *context_inode);
diff --git a/include/linux/aperture.h b/include/linux/aperture.h
index 442f15a57cad..1a9a88b11584 100644
--- a/include/linux/aperture.h
+++ b/include/linux/aperture.h
@@ -14,7 +14,9 @@ int devm_aperture_acquire_for_platform_device(struct platform_device *pdev,
 					      resource_size_t size);
 
 int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size,
-					bool primary, const char *name);
+					const char *name);
+
+int __aperture_remove_legacy_vga_devices(struct pci_dev *pdev);
 
 int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name);
 #else
@@ -26,7 +28,12 @@ static inline int devm_aperture_acquire_for_platform_device(struct platform_devi
 }
 
 static inline int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t size,
-						      bool primary, const char *name)
+						      const char *name)
+{
+	return 0;
+}
+
+static inline int __aperture_remove_legacy_vga_devices(struct pci_dev *pdev)
 {
 	return 0;
 }
@@ -39,7 +46,6 @@ static inline int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev,
 
 /**
  * aperture_remove_all_conflicting_devices - remove all existing framebuffers
- * @primary: also kick vga16fb if present; only relevant for VGA devices
  * @name: a descriptive name of the requesting driver
  *
  * This function removes all graphics device drivers. Use this function on systems
@@ -48,9 +54,9 @@ static inline int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev,
  * Returns:
  * 0 on success, or a negative errno code otherwise
  */
-static inline int aperture_remove_all_conflicting_devices(bool primary, const char *name)
+static inline int aperture_remove_all_conflicting_devices(const char *name)
 {
-	return aperture_remove_conflicting_devices(0, (resource_size_t)-1, primary, name);
+	return aperture_remove_conflicting_devices(0, (resource_size_t)-1, name);
 }
 
 #endif
diff --git a/include/linux/apple-mailbox.h b/include/linux/apple-mailbox.h
deleted file mode 100644
index 720fbb70294a..000000000000
--- a/include/linux/apple-mailbox.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
-/*
- * Apple mailbox message format
- *
- * Copyright (C) 2021 The Asahi Linux Contributors
- */
-
-#ifndef _LINUX_APPLE_MAILBOX_H_
-#define _LINUX_APPLE_MAILBOX_H_
-
-#include <linux/types.h>
-
-/* encodes a single 96bit message sent over the single channel */
-struct apple_mbox_msg {
-	u64 msg0;
-	u32 msg1;
-};
-
-#endif
diff --git a/include/linux/arch_topology.h b/include/linux/arch_topology.h
index a07b510e7dc5..ebd7f8935f96 100644
--- a/include/linux/arch_topology.h
+++ b/include/linux/arch_topology.h
@@ -11,22 +11,17 @@
 void topology_normalize_cpu_scale(void);
 int topology_update_cpu_topology(void);
 
-#ifdef CONFIG_ACPI_CPPC_LIB
-void topology_init_cpu_capacity_cppc(void);
-#endif
-
 struct device_node;
 bool topology_parse_cpu_capacity(struct device_node *cpu_node, int cpu);
 
-DECLARE_PER_CPU(unsigned long, cpu_scale);
 
-static inline unsigned long topology_get_cpu_scale(int cpu)
+DECLARE_PER_CPU(unsigned long, capacity_freq_ref);
+
+static inline unsigned long topology_get_freq_ref(int cpu)
 {
-	return per_cpu(cpu_scale, cpu);
+	return per_cpu(capacity_freq_ref, cpu);
 }
 
-void topology_set_cpu_scale(unsigned int cpu, unsigned long capacity);
-
 DECLARE_PER_CPU(unsigned long, arch_freq_scale);
 
 static inline unsigned long topology_get_freq_scale(int cpu)
@@ -42,6 +37,7 @@ enum scale_freq_source {
 	SCALE_FREQ_SOURCE_CPUFREQ = 0,
 	SCALE_FREQ_SOURCE_ARCH,
 	SCALE_FREQ_SOURCE_CPPC,
+	SCALE_FREQ_SOURCE_VIRT,
 };
 
 struct scale_freq_data {
@@ -53,14 +49,14 @@ void topology_scale_freq_tick(void);
 void topology_set_scale_freq_source(struct scale_freq_data *data, const struct cpumask *cpus);
 void topology_clear_scale_freq_source(enum scale_freq_source source, const struct cpumask *cpus);
 
-DECLARE_PER_CPU(unsigned long, thermal_pressure);
+DECLARE_PER_CPU(unsigned long, hw_pressure);
 
-static inline unsigned long topology_get_thermal_pressure(int cpu)
+static inline unsigned long topology_get_hw_pressure(int cpu)
 {
-	return per_cpu(thermal_pressure, cpu);
+	return per_cpu(hw_pressure, cpu);
 }
 
-void topology_update_thermal_pressure(const struct cpumask *cpus,
+void topology_update_hw_pressure(const struct cpumask *cpus,
 				      unsigned long capped_freq);
 
 struct cpu_topology {
@@ -84,6 +80,11 @@ extern struct cpu_topology cpu_topology[NR_CPUS];
 #define topology_sibling_cpumask(cpu)	(&cpu_topology[cpu].thread_sibling)
 #define topology_cluster_cpumask(cpu)	(&cpu_topology[cpu].cluster_sibling)
 #define topology_llc_cpumask(cpu)	(&cpu_topology[cpu].llc_sibling)
+
+#ifndef arch_cpu_is_threaded
+#define arch_cpu_is_threaded()	(0)
+#endif
+
 void init_cpu_topology(void);
 void store_cpu_topology(unsigned int cpuid);
 const struct cpumask *cpu_coregroup_mask(int cpu);
@@ -92,6 +93,22 @@ void update_siblings_masks(unsigned int cpu);
 void remove_cpu_topology(unsigned int cpuid);
 void reset_cpu_topology(void);
 int parse_acpi_topology(void);
-#endif
+void freq_inv_set_max_ratio(int cpu, u64 max_rate);
+
+/*
+ * Architectures like ARM64 don't have reliable architectural way to get SMT
+ * information and depend on the firmware (ACPI/OF) report. Non-SMT core won't
+ * initialize thread_id so we can use this to detect the SMT implementation.
+ */
+static inline bool topology_core_has_smt(int cpu)
+{
+	return cpu_topology[cpu].thread_id != -1;
+}
+
+#else
+
+static inline bool topology_core_has_smt(int cpu) { return false; }
+
+#endif /* CONFIG_GENERIC_ARCH_TOPOLOGY */
 
 #endif /* _LINUX_ARCH_TOPOLOGY_H_ */
diff --git a/include/linux/args.h b/include/linux/args.h
new file mode 100644
index 000000000000..2e8e65d975c7
--- /dev/null
+++ b/include/linux/args.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_ARGS_H
+#define _LINUX_ARGS_H
+
+/*
+ * How do these macros work?
+ *
+ * In __COUNT_ARGS() _0 to _12 are just placeholders from the start
+ * in order to make sure _n is positioned over the correct number
+ * from 12 to 0 (depending on X, which is a variadic argument list).
+ * They serve no purpose other than occupying a position. Since each
+ * macro parameter must have a distinct identifier, those identifiers
+ * are as good as any.
+ *
+ * In COUNT_ARGS() we use actual integers, so __COUNT_ARGS() returns
+ * that as _n.
+ */
+
+/* This counts to 15. Any more, it will return 16th argument. */
+#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _13, _14, _15, _n, X...) _n
+#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
+
+/* Concatenate two parameters, but allow them to be expanded beforehand. */
+#define __CONCAT(a, b) a ## b
+#define CONCATENATE(a, b) __CONCAT(a, b)
+
+#endif	/* _LINUX_ARGS_H */
diff --git a/include/linux/arm-cci.h b/include/linux/arm-cci.h
index d0e44201d855..7f7a576267bc 100644
--- a/include/linux/arm-cci.h
+++ b/include/linux/arm-cci.h
@@ -43,6 +43,8 @@ static inline int __cci_control_port_by_index(u32 port, bool enable)
 }
 #endif
 
+void cci_enable_port_for_self(void);
+
 #define cci_disable_port_by_device(dev) \
 	__cci_control_port_by_device(dev, false)
 #define cci_enable_port_by_device(dev) \
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index f196c19f8e55..50b47eba7d01 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -5,7 +5,13 @@
 #ifndef __LINUX_ARM_SMCCC_H
 #define __LINUX_ARM_SMCCC_H
 
+#include <linux/args.h>
 #include <linux/init.h>
+
+#ifndef __ASSEMBLY__
+#include <linux/uuid.h>
+#endif
+
 #include <uapi/linux/const.h>
 
 /*
@@ -66,6 +72,8 @@
 #define ARM_SMCCC_VERSION_1_3		0x10003
 
 #define ARM_SMCCC_1_3_SVE_HINT		0x10000
+#define ARM_SMCCC_CALL_HINTS		ARM_SMCCC_1_3_SVE_HINT
+
 
 #define ARM_SMCCC_VERSION_FUNC_ID					\
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
@@ -104,14 +112,81 @@
 			   ARM_SMCCC_FUNC_QUERY_CALL_UID)
 
 /* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0	0xb66fb428U
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1	0xe911c52eU
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2	0x564bcaa9U
-#define ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3	0x743a004dU
+#define ARM_SMCCC_VENDOR_HYP_UID_KVM UUID_INIT(\
+	0x28b46fb6, 0x2ec5, 0x11e9, \
+	0xa9, 0xca, 0x4b, 0x56, \
+	0x4d, 0x00, 0x3a, 0x74)
 
 /* KVM "vendor specific" services */
 #define ARM_SMCCC_KVM_FUNC_FEATURES		0
 #define ARM_SMCCC_KVM_FUNC_PTP			1
+/* Start of pKVM hypercall range */
+#define ARM_SMCCC_KVM_FUNC_HYP_MEMINFO		2
+#define ARM_SMCCC_KVM_FUNC_MEM_SHARE		3
+#define ARM_SMCCC_KVM_FUNC_MEM_UNSHARE		4
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_5		5
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_6		6
+#define ARM_SMCCC_KVM_FUNC_MMIO_GUARD		7
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_8		8
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_9		9
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_10		10
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_11		11
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_12		12
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_13		13
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_14		14
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_15		15
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_16		16
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_17		17
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_18		18
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_19		19
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_20		20
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_21		21
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_22		22
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_23		23
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_24		24
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_25		25
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_26		26
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_27		27
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_28		28
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_29		29
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_30		30
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_31		31
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_32		32
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_33		33
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_34		34
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_35		35
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_36		36
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_37		37
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_38		38
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_39		39
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_40		40
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_41		41
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_42		42
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_43		43
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_44		44
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_45		45
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_46		46
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_47		47
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_48		48
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_49		49
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_50		50
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_51		51
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_52		52
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_53		53
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_54		54
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_55		55
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_56		56
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_57		57
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_58		58
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_59		59
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_60		60
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_61		61
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_62		62
+#define ARM_SMCCC_KVM_FUNC_PKVM_RESV_63		63
+/* End of pKVM hypercall range */
+#define ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_VER	64
+#define ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_CPUS	65
+
 #define ARM_SMCCC_KVM_FUNC_FEATURES_2		127
 #define ARM_SMCCC_KVM_NUM_FUNCS			128
 
@@ -134,6 +209,42 @@
 			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
 			   ARM_SMCCC_KVM_FUNC_PTP)
 
+#define ARM_SMCCC_VENDOR_HYP_KVM_HYP_MEMINFO_FUNC_ID			\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   ARM_SMCCC_KVM_FUNC_HYP_MEMINFO)
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_MEM_SHARE_FUNC_ID			\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   ARM_SMCCC_KVM_FUNC_MEM_SHARE)
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_MEM_UNSHARE_FUNC_ID			\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   ARM_SMCCC_KVM_FUNC_MEM_UNSHARE)
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_MMIO_GUARD_FUNC_ID			\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   ARM_SMCCC_KVM_FUNC_MMIO_GUARD)
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_DISCOVER_IMPL_VER_FUNC_ID		\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_VER)
+
+#define ARM_SMCCC_VENDOR_HYP_KVM_DISCOVER_IMPL_CPUS_FUNC_ID		\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,				\
+			   ARM_SMCCC_SMC_64,				\
+			   ARM_SMCCC_OWNER_VENDOR_HYP,			\
+			   ARM_SMCCC_KVM_FUNC_DISCOVER_IMPL_CPUS)
+
 /* ptp_kvm counter type ID */
 #define KVM_PTP_VIRT_COUNTER			0
 #define KVM_PTP_PHYS_COUNTER			1
@@ -224,8 +335,6 @@ u32 arm_smccc_get_version(void);
 
 void __init arm_smccc_version_init(u32 version, enum arm_smccc_conduit conduit);
 
-extern u64 smccc_has_sve_hint;
-
 /**
  * arm_smccc_get_soc_id_version()
  *
@@ -244,6 +353,57 @@ s32 arm_smccc_get_soc_id_version(void);
  */
 s32 arm_smccc_get_soc_id_revision(void);
 
+#ifndef __ASSEMBLY__
+
+/*
+ * Returns whether a specific hypervisor UUID is advertised for the
+ * Vendor Specific Hypervisor Service range.
+ */
+bool arm_smccc_hypervisor_has_uuid(const uuid_t *uuid);
+
+static inline uuid_t smccc_res_to_uuid(u32 r0, u32 r1, u32 r2, u32 r3)
+{
+	uuid_t uuid = {
+		.b = {
+			[0]  = (r0 >> 0)  & 0xff,
+			[1]  = (r0 >> 8)  & 0xff,
+			[2]  = (r0 >> 16) & 0xff,
+			[3]  = (r0 >> 24) & 0xff,
+
+			[4]  = (r1 >> 0)  & 0xff,
+			[5]  = (r1 >> 8)  & 0xff,
+			[6]  = (r1 >> 16) & 0xff,
+			[7]  = (r1 >> 24) & 0xff,
+
+			[8]  = (r2 >> 0)  & 0xff,
+			[9]  = (r2 >> 8)  & 0xff,
+			[10] = (r2 >> 16) & 0xff,
+			[11] = (r2 >> 24) & 0xff,
+
+			[12] = (r3 >> 0)  & 0xff,
+			[13] = (r3 >> 8)  & 0xff,
+			[14] = (r3 >> 16) & 0xff,
+			[15] = (r3 >> 24) & 0xff,
+		},
+	};
+
+	return uuid;
+}
+
+static inline u32 smccc_uuid_to_reg(const uuid_t *uuid, int reg)
+{
+	u32 val = 0;
+
+	val |= (u32)(uuid->b[4 * reg + 0] << 0);
+	val |= (u32)(uuid->b[4 * reg + 1] << 8);
+	val |= (u32)(uuid->b[4 * reg + 2] << 16);
+	val |= (u32)(uuid->b[4 * reg + 3] << 24);
+
+	return val;
+}
+
+#endif /* !__ASSEMBLY__ */
+
 /**
  * struct arm_smccc_res - Result from SMC/HVC call
  * @a0-a3 result values from registers 0 to 3
@@ -324,15 +484,6 @@ struct arm_smccc_quirk {
 };
 
 /**
- * __arm_smccc_sve_check() - Set the SVE hint bit when doing SMC calls
- *
- * Sets the SMCCC hint bit to indicate if there is live state in the SVE
- * registers, this modifies x0 in place and should never be called from C
- * code.
- */
-asmlinkage unsigned long __arm_smccc_sve_check(unsigned long x0);
-
-/**
  * __arm_smccc_smc() - make SMC calls
  * @a0-a7: arguments passed in registers 0 to 7
  * @res: result values from registers 0 to 3
@@ -399,45 +550,26 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 
 #endif
 
-/* nVHE hypervisor doesn't have a current thread so needs separate checks */
-#if defined(CONFIG_ARM64_SVE) && !defined(__KVM_NVHE_HYPERVISOR__)
-
-#define SMCCC_SVE_CHECK ALTERNATIVE("nop \n",  "bl __arm_smccc_sve_check \n", \
-				    ARM64_SVE)
-#define smccc_sve_clobbers "x16", "x30", "cc",
-
-#else
-
-#define SMCCC_SVE_CHECK
-#define smccc_sve_clobbers
+#define __constraint_read_2	"r" (arg0)
+#define __constraint_read_3	__constraint_read_2, "r" (arg1)
+#define __constraint_read_4	__constraint_read_3, "r" (arg2)
+#define __constraint_read_5	__constraint_read_4, "r" (arg3)
+#define __constraint_read_6	__constraint_read_5, "r" (arg4)
+#define __constraint_read_7	__constraint_read_6, "r" (arg5)
+#define __constraint_read_8	__constraint_read_7, "r" (arg6)
+#define __constraint_read_9	__constraint_read_8, "r" (arg7)
 
-#endif
-
-#define ___count_args(_0, _1, _2, _3, _4, _5, _6, _7, _8, x, ...) x
-
-#define __count_args(...)						\
-	___count_args(__VA_ARGS__, 7, 6, 5, 4, 3, 2, 1, 0)
-
-#define __constraint_read_0	"r" (arg0)
-#define __constraint_read_1	__constraint_read_0, "r" (arg1)
-#define __constraint_read_2	__constraint_read_1, "r" (arg2)
-#define __constraint_read_3	__constraint_read_2, "r" (arg3)
-#define __constraint_read_4	__constraint_read_3, "r" (arg4)
-#define __constraint_read_5	__constraint_read_4, "r" (arg5)
-#define __constraint_read_6	__constraint_read_5, "r" (arg6)
-#define __constraint_read_7	__constraint_read_6, "r" (arg7)
-
-#define __declare_arg_0(a0, res)					\
+#define __declare_arg_2(a0, res)					\
 	struct arm_smccc_res   *___res = res;				\
 	register unsigned long arg0 asm("r0") = (u32)a0
 
-#define __declare_arg_1(a0, a1, res)					\
+#define __declare_arg_3(a0, a1, res)					\
 	typeof(a1) __a1 = a1;						\
 	struct arm_smccc_res   *___res = res;				\
 	register unsigned long arg0 asm("r0") = (u32)a0;			\
 	register typeof(a1) arg1 asm("r1") = __a1
 
-#define __declare_arg_2(a0, a1, a2, res)				\
+#define __declare_arg_4(a0, a1, a2, res)				\
 	typeof(a1) __a1 = a1;						\
 	typeof(a2) __a2 = a2;						\
 	struct arm_smccc_res   *___res = res;				\
@@ -445,7 +577,7 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 	register typeof(a1) arg1 asm("r1") = __a1;			\
 	register typeof(a2) arg2 asm("r2") = __a2
 
-#define __declare_arg_3(a0, a1, a2, a3, res)				\
+#define __declare_arg_5(a0, a1, a2, a3, res)				\
 	typeof(a1) __a1 = a1;						\
 	typeof(a2) __a2 = a2;						\
 	typeof(a3) __a3 = a3;						\
@@ -455,34 +587,26 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 	register typeof(a2) arg2 asm("r2") = __a2;			\
 	register typeof(a3) arg3 asm("r3") = __a3
 
-#define __declare_arg_4(a0, a1, a2, a3, a4, res)			\
+#define __declare_arg_6(a0, a1, a2, a3, a4, res)			\
 	typeof(a4) __a4 = a4;						\
-	__declare_arg_3(a0, a1, a2, a3, res);				\
+	__declare_arg_5(a0, a1, a2, a3, res);				\
 	register typeof(a4) arg4 asm("r4") = __a4
 
-#define __declare_arg_5(a0, a1, a2, a3, a4, a5, res)			\
+#define __declare_arg_7(a0, a1, a2, a3, a4, a5, res)			\
 	typeof(a5) __a5 = a5;						\
-	__declare_arg_4(a0, a1, a2, a3, a4, res);			\
+	__declare_arg_6(a0, a1, a2, a3, a4, res);			\
 	register typeof(a5) arg5 asm("r5") = __a5
 
-#define __declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res)		\
+#define __declare_arg_8(a0, a1, a2, a3, a4, a5, a6, res)		\
 	typeof(a6) __a6 = a6;						\
-	__declare_arg_5(a0, a1, a2, a3, a4, a5, res);			\
+	__declare_arg_7(a0, a1, a2, a3, a4, a5, res);			\
 	register typeof(a6) arg6 asm("r6") = __a6
 
-#define __declare_arg_7(a0, a1, a2, a3, a4, a5, a6, a7, res)		\
+#define __declare_arg_9(a0, a1, a2, a3, a4, a5, a6, a7, res)		\
 	typeof(a7) __a7 = a7;						\
-	__declare_arg_6(a0, a1, a2, a3, a4, a5, a6, res);		\
+	__declare_arg_8(a0, a1, a2, a3, a4, a5, a6, res);		\
 	register typeof(a7) arg7 asm("r7") = __a7
 
-#define ___declare_args(count, ...) __declare_arg_ ## count(__VA_ARGS__)
-#define __declare_args(count, ...)  ___declare_args(count, __VA_ARGS__)
-
-#define ___constraints(count)						\
-	: __constraint_read_ ## count					\
-	: smccc_sve_clobbers "memory"
-#define __constraints(count)	___constraints(count)
-
 /*
  * We have an output list that is not necessarily used, and GCC feels
  * entitled to optimise the whole sequence away. "volatile" is what
@@ -494,11 +618,13 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 		register unsigned long r1 asm("r1");			\
 		register unsigned long r2 asm("r2");			\
 		register unsigned long r3 asm("r3"); 			\
-		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm volatile(SMCCC_SVE_CHECK				\
-			     inst "\n" :				\
+		CONCATENATE(__declare_arg_,				\
+			    COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__);	\
+		asm volatile(inst "\n" :				\
 			     "=r" (r0), "=r" (r1), "=r" (r2), "=r" (r3)	\
-			     __constraints(__count_args(__VA_ARGS__)));	\
+			     : CONCATENATE(__constraint_read_,		\
+					   COUNT_ARGS(__VA_ARGS__))	\
+			     : "memory");				\
 		if (___res)						\
 			*___res = (typeof(*___res)){r0, r1, r2, r3};	\
 	} while (0)
@@ -542,8 +668,12 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
  */
 #define __fail_smccc_1_1(...)						\
 	do {								\
-		__declare_args(__count_args(__VA_ARGS__), __VA_ARGS__);	\
-		asm ("" : __constraints(__count_args(__VA_ARGS__)));	\
+		CONCATENATE(__declare_arg_,				\
+			    COUNT_ARGS(__VA_ARGS__))(__VA_ARGS__);	\
+		asm ("" :						\
+		     : CONCATENATE(__constraint_read_,			\
+				   COUNT_ARGS(__VA_ARGS__))		\
+		     : "memory");					\
 		if (___res)						\
 			___res->a0 = SMCCC_RET_NOT_SUPPORTED;		\
 	} while (0)
@@ -580,5 +710,45 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 		method;							\
 	})
 
+#ifdef CONFIG_ARM64
+
+#define __fail_smccc_1_2(___res)					\
+	do {								\
+		if (___res)						\
+			___res->a0 = SMCCC_RET_NOT_SUPPORTED;		\
+	} while (0)
+
+/*
+ * arm_smccc_1_2_invoke() - make an SMCCC v1.2 compliant call
+ *
+ * @args: SMC args are in the a0..a17 fields of the arm_smcc_1_2_regs structure
+ * @res: result values from registers 0 to 17
+ *
+ * This macro will make either an HVC call or an SMC call depending on the
+ * current SMCCC conduit. If no valid conduit is available then -1
+ * (SMCCC_RET_NOT_SUPPORTED) is returned in @res.a0 (if supplied).
+ *
+ * The return value also provides the conduit that was used.
+ */
+#define arm_smccc_1_2_invoke(args, res) ({				\
+		struct arm_smccc_1_2_regs *__args = args;		\
+		struct arm_smccc_1_2_regs *__res = res;			\
+		int method = arm_smccc_1_1_get_conduit();		\
+		switch (method) {					\
+		case SMCCC_CONDUIT_HVC:					\
+			arm_smccc_1_2_hvc(__args, __res);		\
+			break;						\
+		case SMCCC_CONDUIT_SMC:					\
+			arm_smccc_1_2_smc(__args, __res);		\
+			break;						\
+		default:						\
+			__fail_smccc_1_2(__res);			\
+			method = SMCCC_CONDUIT_NONE;			\
+			break;						\
+		}							\
+		method;							\
+	})
+#endif /*CONFIG_ARM64*/
+
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/
diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 583fe3b49a49..81e603839c4a 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -6,6 +6,7 @@
 #ifndef _LINUX_ARM_FFA_H
 #define _LINUX_ARM_FFA_H
 
+#include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/module.h>
 #include <linux/types.h>
@@ -20,6 +21,7 @@
 
 #define FFA_ERROR			FFA_SMC_32(0x60)
 #define FFA_SUCCESS			FFA_SMC_32(0x61)
+#define FFA_FN64_SUCCESS		FFA_SMC_64(0x61)
 #define FFA_INTERRUPT			FFA_SMC_32(0x62)
 #define FFA_VERSION			FFA_SMC_32(0x63)
 #define FFA_FEATURES			FFA_SMC_32(0x64)
@@ -54,6 +56,28 @@
 #define FFA_MEM_FRAG_RX			FFA_SMC_32(0x7A)
 #define FFA_MEM_FRAG_TX			FFA_SMC_32(0x7B)
 #define FFA_NORMAL_WORLD_RESUME		FFA_SMC_32(0x7C)
+#define FFA_NOTIFICATION_BITMAP_CREATE	FFA_SMC_32(0x7D)
+#define FFA_NOTIFICATION_BITMAP_DESTROY FFA_SMC_32(0x7E)
+#define FFA_NOTIFICATION_BIND		FFA_SMC_32(0x7F)
+#define FFA_NOTIFICATION_UNBIND		FFA_SMC_32(0x80)
+#define FFA_NOTIFICATION_SET		FFA_SMC_32(0x81)
+#define FFA_NOTIFICATION_GET		FFA_SMC_32(0x82)
+#define FFA_NOTIFICATION_INFO_GET	FFA_SMC_32(0x83)
+#define FFA_FN64_NOTIFICATION_INFO_GET	FFA_SMC_64(0x83)
+#define FFA_RX_ACQUIRE			FFA_SMC_32(0x84)
+#define FFA_SPM_ID_GET			FFA_SMC_32(0x85)
+#define FFA_MSG_SEND2			FFA_SMC_32(0x86)
+#define FFA_SECONDARY_EP_REGISTER	FFA_SMC_32(0x87)
+#define FFA_FN64_SECONDARY_EP_REGISTER	FFA_SMC_64(0x87)
+#define FFA_MEM_PERM_GET		FFA_SMC_32(0x88)
+#define FFA_FN64_MEM_PERM_GET		FFA_SMC_64(0x88)
+#define FFA_MEM_PERM_SET		FFA_SMC_32(0x89)
+#define FFA_FN64_MEM_PERM_SET		FFA_SMC_64(0x89)
+#define FFA_CONSOLE_LOG			FFA_SMC_32(0x8A)
+#define FFA_PARTITION_INFO_GET_REGS	FFA_SMC_64(0x8B)
+#define FFA_EL3_INTR_HANDLE		FFA_SMC_32(0x8C)
+#define FFA_MSG_SEND_DIRECT_REQ2	FFA_SMC_64(0x8D)
+#define FFA_MSG_SEND_DIRECT_RESP2	FFA_SMC_64(0x8E)
 
 /*
  * For some calls it is necessary to use SMC64 to pass or return 64-bit values.
@@ -76,6 +100,7 @@
 #define FFA_RET_DENIED             (-6)
 #define FFA_RET_RETRY              (-7)
 #define FFA_RET_ABORTED            (-8)
+#define FFA_RET_NO_DATA            (-9)
 
 /* FFA version encoding */
 #define FFA_MAJOR_VERSION_MASK	GENMASK(30, 16)
@@ -86,6 +111,8 @@
 	(FIELD_PREP(FFA_MAJOR_VERSION_MASK, (major)) |		\
 	 FIELD_PREP(FFA_MINOR_VERSION_MASK, (minor)))
 #define FFA_VERSION_1_0		FFA_PACK_VERSION_INFO(1, 0)
+#define FFA_VERSION_1_1		FFA_PACK_VERSION_INFO(1, 1)
+#define FFA_VERSION_1_2		FFA_PACK_VERSION_INFO(1, 2)
 
 /**
  * FF-A specification mentions explicitly about '4K pages'. This should
@@ -94,9 +121,19 @@
  */
 #define FFA_PAGE_SIZE		SZ_4K
 
+/*
+ * Minimum buffer size/alignment encodings returned by an FFA_FEATURES
+ * query for FFA_RXTX_MAP.
+ */
+#define FFA_FEAT_RXTX_MIN_SZ_4K		0
+#define FFA_FEAT_RXTX_MIN_SZ_64K	1
+#define FFA_FEAT_RXTX_MIN_SZ_16K	2
+#define FFA_FEAT_RXTX_MIN_SZ_MASK	GENMASK(1, 0)
+
 /* FFA Bus/Device/Driver related */
 struct ffa_device {
 	u32 id;
+	u32 properties;
 	int vm_id;
 	bool mode_32bit;
 	uuid_t uuid;
@@ -119,7 +156,7 @@ struct ffa_driver {
 	struct device_driver driver;
 };
 
-#define to_ffa_driver(d) container_of(d, struct ffa_driver, driver)
+#define to_ffa_driver(d) container_of_const(d, struct ffa_driver, driver)
 
 static inline void ffa_dev_set_drvdata(struct ffa_device *fdev, void *data)
 {
@@ -131,25 +168,31 @@ static inline void *ffa_dev_get_drvdata(struct ffa_device *fdev)
 	return dev_get_drvdata(&fdev->dev);
 }
 
+struct ffa_partition_info;
+
 #if IS_REACHABLE(CONFIG_ARM_FFA_TRANSPORT)
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
-				       const struct ffa_ops *ops);
+struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+		    const struct ffa_ops *ops);
 void ffa_device_unregister(struct ffa_device *ffa_dev);
 int ffa_driver_register(struct ffa_driver *driver, struct module *owner,
 			const char *mod_name);
 void ffa_driver_unregister(struct ffa_driver *driver);
+void ffa_devices_unregister(void);
 bool ffa_device_is_valid(struct ffa_device *ffa_dev);
 
 #else
-static inline
-struct ffa_device *ffa_device_register(const uuid_t *uuid, int vm_id,
-				       const struct ffa_ops *ops)
+static inline struct ffa_device *
+ffa_device_register(const struct ffa_partition_info *part_info,
+		    const struct ffa_ops *ops)
 {
 	return NULL;
 }
 
 static inline void ffa_device_unregister(struct ffa_device *dev) {}
 
+static inline void ffa_devices_unregister(void) {}
+
 static inline int
 ffa_driver_register(struct ffa_driver *driver, struct module *owner,
 		    const char *mod_name)
@@ -180,6 +223,11 @@ bool ffa_device_is_valid(struct ffa_device *ffa_dev) { return false; }
 #define module_ffa_driver(__ffa_driver)	\
 	module_driver(__ffa_driver, ffa_register, ffa_unregister)
 
+extern const struct bus_type ffa_bus_type;
+
+/* The FF-A 1.0 partition structure lacks the uuid[4] */
+#define FFA_1_0_PARTITON_INFO_SZ	(8)
+
 /* FFA transport related */
 struct ffa_partition_info {
 	u16 id;
@@ -190,12 +238,37 @@ struct ffa_partition_info {
 #define FFA_PARTITION_DIRECT_SEND	BIT(1)
 /* partition can send and receive indirect messages. */
 #define FFA_PARTITION_INDIRECT_MSG	BIT(2)
+/* partition can receive notifications */
+#define FFA_PARTITION_NOTIFICATION_RECV	BIT(3)
 /* partition runs in the AArch64 execution state. */
 #define FFA_PARTITION_AARCH64_EXEC	BIT(8)
+/* partition supports receipt of direct request2 */
+#define FFA_PARTITION_DIRECT_REQ2_RECV	BIT(9)
+/* partition can send direct request2. */
+#define FFA_PARTITION_DIRECT_REQ2_SEND	BIT(10)
 	u32 properties;
-	u32 uuid[4];
+	uuid_t uuid;
 };
 
+static inline
+bool ffa_partition_check_property(struct ffa_device *dev, u32 property)
+{
+	return dev->properties & property;
+}
+
+#define ffa_partition_supports_notify_recv(dev)	\
+	ffa_partition_check_property(dev, FFA_PARTITION_NOTIFICATION_RECV)
+
+#define ffa_partition_supports_indirect_msg(dev)	\
+	ffa_partition_check_property(dev, FFA_PARTITION_INDIRECT_MSG)
+
+#define ffa_partition_supports_direct_recv(dev)	\
+	ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_RECV)
+
+#define ffa_partition_supports_direct_req2_recv(dev)	\
+	(ffa_partition_check_property(dev, FFA_PARTITION_DIRECT_REQ2_RECV) && \
+	 !dev->mode_32bit)
+
 /* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP} which pass data via registers */
 struct ffa_send_direct_data {
 	unsigned long data0; /* w3/x3 */
@@ -205,6 +278,21 @@ struct ffa_send_direct_data {
 	unsigned long data4; /* w7/x7 */
 };
 
+struct ffa_indirect_msg_hdr {
+	u32 flags;
+	u32 res0;
+	u32 offset;
+	u32 send_recv_id;
+	u32 size;
+	u32 res1;
+	uuid_t uuid;
+};
+
+/* For use with FFA_MSG_SEND_DIRECT_{REQ,RESP}2 which pass data via registers */
+struct ffa_send_direct_data2 {
+	unsigned long data[14]; /* x4-x17 */
+};
+
 struct ffa_mem_region_addr_range {
 	/* The base IPA of the constituent memory region, aligned to 4 kiB */
 	u64 address;
@@ -250,6 +338,7 @@ struct ffa_mem_region_attributes {
 	 * an `struct ffa_mem_region_addr_range`.
 	 */
 	u32 composite_off;
+	u8 impdef_val[16];
 	u64 reserved;
 };
 
@@ -270,8 +359,8 @@ struct ffa_mem_region {
 #define FFA_MEM_NON_SHAREABLE	(0)
 #define FFA_MEM_OUTER_SHAREABLE	(2)
 #define FFA_MEM_INNER_SHAREABLE	(3)
-	u8 attributes;
-	u8 reserved_0;
+	/* Memory region attributes, upper byte MBZ pre v1.1 */
+	u16 attributes;
 /*
  * Clear memory region contents after unmapping it from the sender and
  * before mapping it for any receiver.
@@ -309,27 +398,57 @@ struct ffa_mem_region {
 	 * memory region.
 	 */
 	u64 tag;
-	u32 reserved_1;
+	/* Size of each endpoint memory access descriptor, MBZ pre v1.1 */
+	u32 ep_mem_size;
 	/*
 	 * The number of `ffa_mem_region_attributes` entries included in this
 	 * transaction.
 	 */
 	u32 ep_count;
 	/*
-	 * An array of endpoint memory access descriptors.
-	 * Each one specifies a memory region offset, an endpoint and the
-	 * attributes with which this memory region should be mapped in that
-	 * endpoint's page table.
+	 * 16-byte aligned offset from the base address of this descriptor
+	 * to the first element of the endpoint memory access descriptor array
+	 * Valid only from v1.1
 	 */
-	struct ffa_mem_region_attributes ep_mem_access[];
+	u32 ep_mem_offset;
+	/* MBZ, valid only from v1.1 */
+	u32 reserved[3];
 };
 
-#define	COMPOSITE_OFFSET(x)	\
-	(offsetof(struct ffa_mem_region, ep_mem_access[x]))
 #define CONSTITUENTS_OFFSET(x)	\
 	(offsetof(struct ffa_composite_mem_region, constituents[x]))
-#define COMPOSITE_CONSTITUENTS_OFFSET(x, y)	\
-	(COMPOSITE_OFFSET(x) + CONSTITUENTS_OFFSET(y))
+
+#define FFA_EMAD_HAS_IMPDEF_FIELD(version)	((version) >= FFA_VERSION_1_2)
+#define FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version) ((version) > FFA_VERSION_1_0)
+
+static inline u32 ffa_emad_size_get(u32 ffa_version)
+{
+	u32 sz;
+	struct ffa_mem_region_attributes *ep_mem_access;
+
+	if (FFA_EMAD_HAS_IMPDEF_FIELD(ffa_version))
+		sz = sizeof(*ep_mem_access);
+	else
+		sz = sizeof(*ep_mem_access) - sizeof(ep_mem_access->impdef_val);
+
+	return sz;
+}
+
+static inline u32
+ffa_mem_desc_offset(struct ffa_mem_region *buf, int count, u32 ffa_version)
+{
+	u32 offset = count * ffa_emad_size_get(ffa_version);
+	/*
+	 * Earlier to v1.1, the endpoint memory descriptor array started at
+	 * offset 32(i.e. offset of ep_mem_offset in the current structure)
+	 */
+	if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(ffa_version))
+		offset += offsetof(struct ffa_mem_region, ep_mem_offset);
+	else
+		offset += sizeof(struct ffa_mem_region);
+
+	return offset;
+}
 
 struct ffa_mem_ops_args {
 	bool use_txbuf;
@@ -351,6 +470,9 @@ struct ffa_msg_ops {
 	void (*mode_32bit_set)(struct ffa_device *dev);
 	int (*sync_send_receive)(struct ffa_device *dev,
 				 struct ffa_send_direct_data *data);
+	int (*indirect_send)(struct ffa_device *dev, void *buf, size_t sz);
+	int (*sync_send_receive2)(struct ffa_device *dev,
+				  struct ffa_send_direct_data2 *data);
 };
 
 struct ffa_mem_ops {
@@ -359,10 +481,35 @@ struct ffa_mem_ops {
 	int (*memory_lend)(struct ffa_mem_ops_args *args);
 };
 
+struct ffa_cpu_ops {
+	int (*run)(struct ffa_device *dev, u16 vcpu);
+};
+
+typedef void (*ffa_sched_recv_cb)(u16 vcpu, bool is_per_vcpu, void *cb_data);
+typedef void (*ffa_notifier_cb)(int notify_id, void *cb_data);
+typedef void (*ffa_fwk_notifier_cb)(int notify_id, void *cb_data, void *buf);
+
+struct ffa_notifier_ops {
+	int (*sched_recv_cb_register)(struct ffa_device *dev,
+				      ffa_sched_recv_cb cb, void *cb_data);
+	int (*sched_recv_cb_unregister)(struct ffa_device *dev);
+	int (*notify_request)(struct ffa_device *dev, bool per_vcpu,
+			      ffa_notifier_cb cb, void *cb_data, int notify_id);
+	int (*notify_relinquish)(struct ffa_device *dev, int notify_id);
+	int (*fwk_notify_request)(struct ffa_device *dev,
+				  ffa_fwk_notifier_cb cb, void *cb_data,
+				  int notify_id);
+	int (*fwk_notify_relinquish)(struct ffa_device *dev, int notify_id);
+	int (*notify_send)(struct ffa_device *dev, int notify_id, bool per_vcpu,
+			   u16 vcpu);
+};
+
 struct ffa_ops {
 	const struct ffa_info_ops *info_ops;
 	const struct ffa_msg_ops *msg_ops;
 	const struct ffa_mem_ops *mem_ops;
+	const struct ffa_cpu_ops *cpu_ops;
+	const struct ffa_notifier_ops *notifier_ops;
 };
 
 #endif /* _LINUX_ARM_FFA_H */
diff --git a/include/linux/arm_mpam.h b/include/linux/arm_mpam.h
new file mode 100644
index 000000000000..7f00c5285a32
--- /dev/null
+++ b/include/linux/arm_mpam.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2025 Arm Ltd. */
+
+#ifndef __LINUX_ARM_MPAM_H
+#define __LINUX_ARM_MPAM_H
+
+#include <linux/acpi.h>
+#include <linux/types.h>
+
+struct mpam_msc;
+
+enum mpam_msc_iface {
+	MPAM_IFACE_MMIO,	/* a real MPAM MSC */
+	MPAM_IFACE_PCC,		/* a fake MPAM MSC */
+};
+
+enum mpam_class_types {
+	MPAM_CLASS_CACHE,	/* Caches, e.g. L2, L3 */
+	MPAM_CLASS_MEMORY,	/* Main memory */
+	MPAM_CLASS_UNKNOWN,	/* Everything else, e.g. SMMU */
+};
+
+#define MPAM_CLASS_ID_DEFAULT	255
+
+#ifdef CONFIG_ACPI_MPAM
+int acpi_mpam_parse_resources(struct mpam_msc *msc,
+			      struct acpi_mpam_msc_node *tbl_msc);
+
+int acpi_mpam_count_msc(void);
+#else
+static inline int acpi_mpam_parse_resources(struct mpam_msc *msc,
+					    struct acpi_mpam_msc_node *tbl_msc)
+{
+	return -EINVAL;
+}
+
+static inline int acpi_mpam_count_msc(void) { return -EINVAL; }
+#endif
+
+#ifdef CONFIG_ARM64_MPAM_DRIVER
+int mpam_ris_create(struct mpam_msc *msc, u8 ris_idx,
+		    enum mpam_class_types type, u8 class_id, int component_id);
+#else
+static inline int mpam_ris_create(struct mpam_msc *msc, u8 ris_idx,
+				  enum mpam_class_types type, u8 class_id,
+				  int component_id)
+{
+	return -EINVAL;
+}
+#endif
+
+/**
+ * mpam_register_requestor() - Register a requestor with the MPAM driver
+ * @partid_max:		The maximum PARTID value the requestor can generate.
+ * @pmg_max:		The maximum PMG value the requestor can generate.
+ *
+ * Registers a requestor with the MPAM driver to ensure the chosen system-wide
+ * minimum PARTID and PMG values will allow the requestors features to be used.
+ *
+ * Returns an error if the registration is too late, and a larger PARTID/PMG
+ * value has been advertised to user-space. In this case the requestor should
+ * not use its MPAM features. Returns 0 on success.
+ */
+int mpam_register_requestor(u16 partid_max, u8 pmg_max);
+
+#endif /* __LINUX_ARM_MPAM_H */
diff --git a/include/linux/arm_sdei.h b/include/linux/arm_sdei.h
index 14dc461b0e82..f652a5028b59 100644
--- a/include/linux/arm_sdei.h
+++ b/include/linux/arm_sdei.h
@@ -46,11 +46,13 @@ int sdei_unregister_ghes(struct ghes *ghes);
 /* For use by arch code when CPU hotplug notifiers are not appropriate. */
 int sdei_mask_local_cpu(void);
 int sdei_unmask_local_cpu(void);
-void __init sdei_init(void);
+void __init acpi_sdei_init(void);
+void sdei_handler_abort(void);
 #else
 static inline int sdei_mask_local_cpu(void) { return 0; }
 static inline int sdei_unmask_local_cpu(void) { return 0; }
-static inline void sdei_init(void) { }
+static inline void acpi_sdei_init(void) { }
+static inline void sdei_handler_abort(void) { }
 #endif /* CONFIG_ARM_SDE_INTERFACE */
 
 
diff --git a/include/linux/array_size.h b/include/linux/array_size.h
new file mode 100644
index 000000000000..06d7d83196ca
--- /dev/null
+++ b/include/linux/array_size.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_ARRAY_SIZE_H
+#define _LINUX_ARRAY_SIZE_H
+
+#include <linux/compiler.h>
+
+/**
+ * ARRAY_SIZE - get the number of elements in array @arr
+ * @arr: array to be sized
+ */
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
+
+#endif  /* _LINUX_ARRAY_SIZE_H */
diff --git a/include/linux/asn1_decoder.h b/include/linux/asn1_decoder.h
index 83f9c6e1e5e9..b41bce82a191 100644
--- a/include/linux/asn1_decoder.h
+++ b/include/linux/asn1_decoder.h
@@ -9,6 +9,7 @@
 #define _LINUX_ASN1_DECODER_H
 
 #include <linux/asn1.h>
+#include <linux/types.h>
 
 struct asn1_decoder;
 
diff --git a/include/linux/asn1_encoder.h b/include/linux/asn1_encoder.h
index 08cd0c2ad34f..d17484dffb74 100644
--- a/include/linux/asn1_encoder.h
+++ b/include/linux/asn1_encoder.h
@@ -6,7 +6,6 @@
 #include <linux/types.h>
 #include <linux/asn1.h>
 #include <linux/asn1_ber_bytecode.h>
-#include <linux/bug.h>
 
 #define asn1_oid_len(oid) (sizeof(oid)/sizeof(u32))
 unsigned char *
diff --git a/include/linux/async.h b/include/linux/async.h
index cce4ad31e8fc..19b778d08600 100644
--- a/include/linux/async.h
+++ b/include/linux/async.h
@@ -90,6 +90,8 @@ async_schedule_dev(async_func_t func, struct device *dev)
 	return async_schedule_node(func, dev, dev_to_node(dev));
 }
 
+bool async_schedule_dev_nocall(async_func_t func, struct device *dev);
+
 /**
  * async_schedule_dev_domain - A device specific version of async_schedule_domain
  * @func: function to execute asynchronously
@@ -118,4 +120,5 @@ extern void async_synchronize_cookie(async_cookie_t cookie);
 extern void async_synchronize_cookie_domain(async_cookie_t cookie,
 					    struct async_domain *domain);
 extern bool current_is_async(void);
+extern void async_init(void);
 #endif
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 5cc73d7e5b52..1ca9f9e05f4f 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -168,11 +168,6 @@ async_xor_offs(struct page *dest, unsigned int offset,
 		int src_cnt, size_t len, struct async_submit_ctl *submit);
 
 struct dma_async_tx_descriptor *
-async_xor_val(struct page *dest, struct page **src_list, unsigned int offset,
-	      int src_cnt, size_t len, enum sum_check_flags *result,
-	      struct async_submit_ctl *submit);
-
-struct dma_async_tx_descriptor *
 async_xor_val_offs(struct page *dest, unsigned int offset,
 		struct page **src_list, unsigned int *src_offset,
 		int src_cnt, size_t len, enum sum_check_flags *result,
diff --git a/include/linux/ata.h b/include/linux/ata.h
index c224dbddb9b2..54b416e26995 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -29,6 +29,7 @@ enum {
 	ATA_MAX_SECTORS_128	= 128,
 	ATA_MAX_SECTORS		= 256,
 	ATA_MAX_SECTORS_1024    = 1024,
+	ATA_MAX_SECTORS_8191    = 8191,
 	ATA_MAX_SECTORS_LBA48	= 65535,/* avoid count to be 0000h */
 	ATA_MAX_SECTORS_TAPE	= 65535,
 	ATA_MAX_TRIM_RNUM	= 64,	/* 512-byte payload / (6-byte LBA + 2-byte range per entry) */
@@ -322,15 +323,21 @@ enum {
 	ATA_LOG_SATA_NCQ	= 0x10,
 	ATA_LOG_NCQ_NON_DATA	= 0x12,
 	ATA_LOG_NCQ_SEND_RECV	= 0x13,
+	ATA_LOG_CDL		= 0x18,
+	ATA_LOG_CDL_SIZE	= ATA_SECT_SIZE,
 	ATA_LOG_IDENTIFY_DEVICE	= 0x30,
+	ATA_LOG_SENSE_NCQ	= 0x0F,
+	ATA_LOG_SENSE_NCQ_SIZE	= ATA_SECT_SIZE * 2,
 	ATA_LOG_CONCURRENT_POSITIONING_RANGES = 0x47,
 
 	/* Identify device log pages: */
+	ATA_LOG_SUPPORTED_CAPABILITIES	= 0x03,
+	ATA_LOG_CURRENT_SETTINGS  = 0x04,
 	ATA_LOG_SECURITY	  = 0x06,
 	ATA_LOG_SATA_SETTINGS	  = 0x08,
 	ATA_LOG_ZONED_INFORMATION = 0x09,
 
-	/* Identify device SATA settings log:*/
+	/* Identify device SATA settings log: */
 	ATA_LOG_DEVSLP_OFFSET	  = 0x30,
 	ATA_LOG_DEVSLP_SIZE	  = 0x08,
 	ATA_LOG_DEVSLP_MDAT	  = 0x00,
@@ -415,6 +422,8 @@ enum {
 	SETFEATURES_SATA_ENABLE = 0x10, /* Enable use of SATA feature */
 	SETFEATURES_SATA_DISABLE = 0x90, /* Disable use of SATA feature */
 
+	SETFEATURES_CDL		= 0x0d, /* Enable/disable cmd duration limits */
+
 	/* SETFEATURE Sector counts for SATA features */
 	SATA_FPDMA_OFFSET	= 0x01,	/* FPDMA non-zero buffer offsets */
 	SATA_FPDMA_AA		= 0x02, /* FPDMA Setup FIS Auto-Activate */
@@ -425,6 +434,7 @@ enum {
 	SATA_DEVSLP		= 0x09,	/* Device Sleep */
 
 	SETFEATURE_SENSE_DATA	= 0xC3, /* Sense Data Reporting feature */
+	SETFEATURE_SENSE_DATA_SUCC_NCQ = 0xC4, /* Sense Data for successful NCQ commands */
 
 	/* feature values for SET_MAX */
 	ATA_SET_MAX_ADDR	= 0x00,
@@ -557,6 +567,7 @@ struct ata_bmdma_prd {
 #define ata_id_has_ncq(id)	((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8))
 #define ata_id_queue_depth(id)	(((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1)
 #define ata_id_removable(id)	((id)[ATA_ID_CONFIG] & (1 << 7))
+#define ata_id_is_locked(id)	(((id)[ATA_ID_DLF] & 0x7) == 0x7)
 #define ata_id_has_atapi_AN(id)	\
 	((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \
 	  ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \
diff --git a/include/linux/ath9k_platform.h b/include/linux/ath9k_platform.h
deleted file mode 100644
index 76860a461ed2..000000000000
--- a/include/linux/ath9k_platform.h
+++ /dev/null
@@ -1,51 +0,0 @@
-/*
- * Copyright (c) 2008 Atheros Communications Inc.
- * Copyright (c) 2009 Gabor Juhos <juhosg@openwrt.org>
- * Copyright (c) 2009 Imre Kaloz <kaloz@openwrt.org>
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
- * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
- * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
- * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#ifndef _LINUX_ATH9K_PLATFORM_H
-#define _LINUX_ATH9K_PLATFORM_H
-
-#define ATH9K_PLAT_EEP_MAX_WORDS	2048
-
-struct ath9k_platform_data {
-	const char *eeprom_name;
-
-	u16 eeprom_data[ATH9K_PLAT_EEP_MAX_WORDS];
-	u8 *macaddr;
-
-	int led_pin;
-	u32 gpio_mask;
-	u32 gpio_val;
-
-	u32 bt_active_pin;
-	u32 bt_priority_pin;
-	u32 wlan_active_pin;
-
-	bool endian_check;
-	bool is_clk_25mhz;
-	bool tx_gain_buffalo;
-	bool disable_2ghz;
-	bool disable_5ghz;
-	bool led_active_high;
-
-	int (*get_mac_revision)(void);
-	int (*external_reset)(void);
-
-	bool use_eeprom;
-};
-
-#endif /* _LINUX_ATH9K_PLATFORM_H */
diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 9b02961d65ee..70807c679f1a 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -185,6 +185,7 @@ struct atmdev_ops { /* only send is required */
 	int (*compat_ioctl)(struct atm_dev *dev,unsigned int cmd,
 			    void __user *arg);
 #endif
+	int (*pre_send)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send)(struct atm_vcc *vcc,struct sk_buff *skb);
 	int (*send_bh)(struct atm_vcc *vcc, struct sk_buff *skb);
 	int (*send_oam)(struct atm_vcc *vcc,void *cell,int flags);
@@ -249,6 +250,12 @@ static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
 }
 
+static inline void atm_return_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	WARN_ON_ONCE(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize,
+					   &sk_atm(vcc)->sk_wmem_alloc));
+}
+
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
 	atomic_add(truesize, &sk_atm(vcc)->sk_rmem_alloc);
diff --git a/include/linux/atmel-mci.h b/include/linux/atmel-mci.h
deleted file mode 100644
index 1491af38cc6e..000000000000
--- a/include/linux/atmel-mci.h
+++ /dev/null
@@ -1,46 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_ATMEL_MCI_H
-#define __LINUX_ATMEL_MCI_H
-
-#include <linux/types.h>
-#include <linux/dmaengine.h>
-
-#define ATMCI_MAX_NR_SLOTS	2
-
-/**
- * struct mci_slot_pdata - board-specific per-slot configuration
- * @bus_width: Number of data lines wired up the slot
- * @detect_pin: GPIO pin wired to the card detect switch
- * @wp_pin: GPIO pin wired to the write protect sensor
- * @detect_is_active_high: The state of the detect pin when it is active
- * @non_removable: The slot is not removable, only detect once
- *
- * If a given slot is not present on the board, @bus_width should be
- * set to 0. The other fields are ignored in this case.
- *
- * Any pins that aren't available should be set to a negative value.
- *
- * Note that support for multiple slots is experimental -- some cards
- * might get upset if we don't get the clock management exactly right.
- * But in most cases, it should work just fine.
- */
-struct mci_slot_pdata {
-	unsigned int		bus_width;
-	int			detect_pin;
-	int			wp_pin;
-	bool			detect_is_active_high;
-	bool			non_removable;
-};
-
-/**
- * struct mci_platform_data - board-specific MMC/SDcard configuration
- * @dma_slave: DMA slave interface to use in data transfers.
- * @slot: Per-slot configuration data.
- */
-struct mci_platform_data {
-	void			*dma_slave;
-	dma_filter_fn		dma_filter;
-	struct mci_slot_pdata	slot[ATMCI_MAX_NR_SLOTS];
-};
-
-#endif /* __LINUX_ATMEL_MCI_H */
diff --git a/include/linux/atomic/atomic-arch-fallback.h b/include/linux/atomic/atomic-arch-fallback.h
index a6e4437c5f36..2f9d36b72bd8 100644
--- a/include/linux/atomic/atomic-arch-fallback.h
+++ b/include/linux/atomic/atomic-arch-fallback.h
@@ -8,2664 +8,4686 @@
 
 #include <linux/compiler.h>
 
-#ifndef arch_xchg_relaxed
-#define arch_xchg_acquire arch_xchg
-#define arch_xchg_release arch_xchg
-#define arch_xchg_relaxed arch_xchg
-#else /* arch_xchg_relaxed */
-
-#ifndef arch_xchg_acquire
-#define arch_xchg_acquire(...) \
-	__atomic_op_acquire(arch_xchg, __VA_ARGS__)
+#if defined(arch_xchg)
+#define raw_xchg arch_xchg
+#elif defined(arch_xchg_relaxed)
+#define raw_xchg(...) \
+	__atomic_op_fence(arch_xchg, __VA_ARGS__)
+#else
+extern void raw_xchg_not_implemented(void);
+#define raw_xchg(...) raw_xchg_not_implemented()
 #endif
 
-#ifndef arch_xchg_release
-#define arch_xchg_release(...) \
-	__atomic_op_release(arch_xchg, __VA_ARGS__)
+#if defined(arch_xchg_acquire)
+#define raw_xchg_acquire arch_xchg_acquire
+#elif defined(arch_xchg_relaxed)
+#define raw_xchg_acquire(...) \
+	__atomic_op_acquire(arch_xchg, __VA_ARGS__)
+#elif defined(arch_xchg)
+#define raw_xchg_acquire arch_xchg
+#else
+extern void raw_xchg_acquire_not_implemented(void);
+#define raw_xchg_acquire(...) raw_xchg_acquire_not_implemented()
 #endif
 
-#ifndef arch_xchg
-#define arch_xchg(...) \
-	__atomic_op_fence(arch_xchg, __VA_ARGS__)
+#if defined(arch_xchg_release)
+#define raw_xchg_release arch_xchg_release
+#elif defined(arch_xchg_relaxed)
+#define raw_xchg_release(...) \
+	__atomic_op_release(arch_xchg, __VA_ARGS__)
+#elif defined(arch_xchg)
+#define raw_xchg_release arch_xchg
+#else
+extern void raw_xchg_release_not_implemented(void);
+#define raw_xchg_release(...) raw_xchg_release_not_implemented()
+#endif
+
+#if defined(arch_xchg_relaxed)
+#define raw_xchg_relaxed arch_xchg_relaxed
+#elif defined(arch_xchg)
+#define raw_xchg_relaxed arch_xchg
+#else
+extern void raw_xchg_relaxed_not_implemented(void);
+#define raw_xchg_relaxed(...) raw_xchg_relaxed_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg)
+#define raw_cmpxchg arch_cmpxchg
+#elif defined(arch_cmpxchg_relaxed)
+#define raw_cmpxchg(...) \
+	__atomic_op_fence(arch_cmpxchg, __VA_ARGS__)
+#else
+extern void raw_cmpxchg_not_implemented(void);
+#define raw_cmpxchg(...) raw_cmpxchg_not_implemented()
 #endif
 
-#endif /* arch_xchg_relaxed */
-
-#ifndef arch_cmpxchg_relaxed
-#define arch_cmpxchg_acquire arch_cmpxchg
-#define arch_cmpxchg_release arch_cmpxchg
-#define arch_cmpxchg_relaxed arch_cmpxchg
-#else /* arch_cmpxchg_relaxed */
-
-#ifndef arch_cmpxchg_acquire
-#define arch_cmpxchg_acquire(...) \
+#if defined(arch_cmpxchg_acquire)
+#define raw_cmpxchg_acquire arch_cmpxchg_acquire
+#elif defined(arch_cmpxchg_relaxed)
+#define raw_cmpxchg_acquire(...) \
 	__atomic_op_acquire(arch_cmpxchg, __VA_ARGS__)
+#elif defined(arch_cmpxchg)
+#define raw_cmpxchg_acquire arch_cmpxchg
+#else
+extern void raw_cmpxchg_acquire_not_implemented(void);
+#define raw_cmpxchg_acquire(...) raw_cmpxchg_acquire_not_implemented()
 #endif
 
-#ifndef arch_cmpxchg_release
-#define arch_cmpxchg_release(...) \
+#if defined(arch_cmpxchg_release)
+#define raw_cmpxchg_release arch_cmpxchg_release
+#elif defined(arch_cmpxchg_relaxed)
+#define raw_cmpxchg_release(...) \
 	__atomic_op_release(arch_cmpxchg, __VA_ARGS__)
+#elif defined(arch_cmpxchg)
+#define raw_cmpxchg_release arch_cmpxchg
+#else
+extern void raw_cmpxchg_release_not_implemented(void);
+#define raw_cmpxchg_release(...) raw_cmpxchg_release_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg_relaxed)
+#define raw_cmpxchg_relaxed arch_cmpxchg_relaxed
+#elif defined(arch_cmpxchg)
+#define raw_cmpxchg_relaxed arch_cmpxchg
+#else
+extern void raw_cmpxchg_relaxed_not_implemented(void);
+#define raw_cmpxchg_relaxed(...) raw_cmpxchg_relaxed_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg64)
+#define raw_cmpxchg64 arch_cmpxchg64
+#elif defined(arch_cmpxchg64_relaxed)
+#define raw_cmpxchg64(...) \
+	__atomic_op_fence(arch_cmpxchg64, __VA_ARGS__)
+#else
+extern void raw_cmpxchg64_not_implemented(void);
+#define raw_cmpxchg64(...) raw_cmpxchg64_not_implemented()
 #endif
 
-#ifndef arch_cmpxchg
-#define arch_cmpxchg(...) \
-	__atomic_op_fence(arch_cmpxchg, __VA_ARGS__)
-#endif
-
-#endif /* arch_cmpxchg_relaxed */
-
-#ifndef arch_cmpxchg64_relaxed
-#define arch_cmpxchg64_acquire arch_cmpxchg64
-#define arch_cmpxchg64_release arch_cmpxchg64
-#define arch_cmpxchg64_relaxed arch_cmpxchg64
-#else /* arch_cmpxchg64_relaxed */
-
-#ifndef arch_cmpxchg64_acquire
-#define arch_cmpxchg64_acquire(...) \
+#if defined(arch_cmpxchg64_acquire)
+#define raw_cmpxchg64_acquire arch_cmpxchg64_acquire
+#elif defined(arch_cmpxchg64_relaxed)
+#define raw_cmpxchg64_acquire(...) \
 	__atomic_op_acquire(arch_cmpxchg64, __VA_ARGS__)
+#elif defined(arch_cmpxchg64)
+#define raw_cmpxchg64_acquire arch_cmpxchg64
+#else
+extern void raw_cmpxchg64_acquire_not_implemented(void);
+#define raw_cmpxchg64_acquire(...) raw_cmpxchg64_acquire_not_implemented()
 #endif
 
-#ifndef arch_cmpxchg64_release
-#define arch_cmpxchg64_release(...) \
+#if defined(arch_cmpxchg64_release)
+#define raw_cmpxchg64_release arch_cmpxchg64_release
+#elif defined(arch_cmpxchg64_relaxed)
+#define raw_cmpxchg64_release(...) \
 	__atomic_op_release(arch_cmpxchg64, __VA_ARGS__)
+#elif defined(arch_cmpxchg64)
+#define raw_cmpxchg64_release arch_cmpxchg64
+#else
+extern void raw_cmpxchg64_release_not_implemented(void);
+#define raw_cmpxchg64_release(...) raw_cmpxchg64_release_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg64_relaxed)
+#define raw_cmpxchg64_relaxed arch_cmpxchg64_relaxed
+#elif defined(arch_cmpxchg64)
+#define raw_cmpxchg64_relaxed arch_cmpxchg64
+#else
+extern void raw_cmpxchg64_relaxed_not_implemented(void);
+#define raw_cmpxchg64_relaxed(...) raw_cmpxchg64_relaxed_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg128)
+#define raw_cmpxchg128 arch_cmpxchg128
+#elif defined(arch_cmpxchg128_relaxed)
+#define raw_cmpxchg128(...) \
+	__atomic_op_fence(arch_cmpxchg128, __VA_ARGS__)
+#else
+extern void raw_cmpxchg128_not_implemented(void);
+#define raw_cmpxchg128(...) raw_cmpxchg128_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg128_acquire)
+#define raw_cmpxchg128_acquire arch_cmpxchg128_acquire
+#elif defined(arch_cmpxchg128_relaxed)
+#define raw_cmpxchg128_acquire(...) \
+	__atomic_op_acquire(arch_cmpxchg128, __VA_ARGS__)
+#elif defined(arch_cmpxchg128)
+#define raw_cmpxchg128_acquire arch_cmpxchg128
+#else
+extern void raw_cmpxchg128_acquire_not_implemented(void);
+#define raw_cmpxchg128_acquire(...) raw_cmpxchg128_acquire_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg128_release)
+#define raw_cmpxchg128_release arch_cmpxchg128_release
+#elif defined(arch_cmpxchg128_relaxed)
+#define raw_cmpxchg128_release(...) \
+	__atomic_op_release(arch_cmpxchg128, __VA_ARGS__)
+#elif defined(arch_cmpxchg128)
+#define raw_cmpxchg128_release arch_cmpxchg128
+#else
+extern void raw_cmpxchg128_release_not_implemented(void);
+#define raw_cmpxchg128_release(...) raw_cmpxchg128_release_not_implemented()
+#endif
+
+#if defined(arch_cmpxchg128_relaxed)
+#define raw_cmpxchg128_relaxed arch_cmpxchg128_relaxed
+#elif defined(arch_cmpxchg128)
+#define raw_cmpxchg128_relaxed arch_cmpxchg128
+#else
+extern void raw_cmpxchg128_relaxed_not_implemented(void);
+#define raw_cmpxchg128_relaxed(...) raw_cmpxchg128_relaxed_not_implemented()
+#endif
+
+#if defined(arch_try_cmpxchg)
+#define raw_try_cmpxchg arch_try_cmpxchg
+#elif defined(arch_try_cmpxchg_relaxed)
+#define raw_try_cmpxchg(...) \
+	__atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__)
+#else
+#define raw_try_cmpxchg(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = raw_cmpxchg((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
 #endif
 
-#ifndef arch_cmpxchg64
-#define arch_cmpxchg64(...) \
-	__atomic_op_fence(arch_cmpxchg64, __VA_ARGS__)
+#if defined(arch_try_cmpxchg_acquire)
+#define raw_try_cmpxchg_acquire arch_try_cmpxchg_acquire
+#elif defined(arch_try_cmpxchg_relaxed)
+#define raw_try_cmpxchg_acquire(...) \
+	__atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__)
+#elif defined(arch_try_cmpxchg)
+#define raw_try_cmpxchg_acquire arch_try_cmpxchg
+#else
+#define raw_try_cmpxchg_acquire(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = raw_cmpxchg_acquire((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
 #endif
 
-#endif /* arch_cmpxchg64_relaxed */
-
-#ifndef arch_try_cmpxchg_relaxed
-#ifdef arch_try_cmpxchg
-#define arch_try_cmpxchg_acquire arch_try_cmpxchg
-#define arch_try_cmpxchg_release arch_try_cmpxchg
-#define arch_try_cmpxchg_relaxed arch_try_cmpxchg
-#endif /* arch_try_cmpxchg */
-
-#ifndef arch_try_cmpxchg
-#define arch_try_cmpxchg(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg_release)
+#define raw_try_cmpxchg_release arch_try_cmpxchg_release
+#elif defined(arch_try_cmpxchg_relaxed)
+#define raw_try_cmpxchg_release(...) \
+	__atomic_op_release(arch_try_cmpxchg, __VA_ARGS__)
+#elif defined(arch_try_cmpxchg)
+#define raw_try_cmpxchg_release arch_try_cmpxchg
+#else
+#define raw_try_cmpxchg_release(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg_release((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg */
+#endif
 
-#ifndef arch_try_cmpxchg_acquire
-#define arch_try_cmpxchg_acquire(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg_relaxed)
+#define raw_try_cmpxchg_relaxed arch_try_cmpxchg_relaxed
+#elif defined(arch_try_cmpxchg)
+#define raw_try_cmpxchg_relaxed arch_try_cmpxchg
+#else
+#define raw_try_cmpxchg_relaxed(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg_acquire((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg_relaxed((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg_acquire */
+#endif
 
-#ifndef arch_try_cmpxchg_release
-#define arch_try_cmpxchg_release(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg64)
+#define raw_try_cmpxchg64 arch_try_cmpxchg64
+#elif defined(arch_try_cmpxchg64_relaxed)
+#define raw_try_cmpxchg64(...) \
+	__atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__)
+#else
+#define raw_try_cmpxchg64(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg_release((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg64((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg_release */
+#endif
 
-#ifndef arch_try_cmpxchg_relaxed
-#define arch_try_cmpxchg_relaxed(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg64_acquire)
+#define raw_try_cmpxchg64_acquire arch_try_cmpxchg64_acquire
+#elif defined(arch_try_cmpxchg64_relaxed)
+#define raw_try_cmpxchg64_acquire(...) \
+	__atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__)
+#elif defined(arch_try_cmpxchg64)
+#define raw_try_cmpxchg64_acquire arch_try_cmpxchg64
+#else
+#define raw_try_cmpxchg64_acquire(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg_relaxed((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg64_acquire((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg_relaxed */
-
-#else /* arch_try_cmpxchg_relaxed */
-
-#ifndef arch_try_cmpxchg_acquire
-#define arch_try_cmpxchg_acquire(...) \
-	__atomic_op_acquire(arch_try_cmpxchg, __VA_ARGS__)
 #endif
 
-#ifndef arch_try_cmpxchg_release
-#define arch_try_cmpxchg_release(...) \
-	__atomic_op_release(arch_try_cmpxchg, __VA_ARGS__)
+#if defined(arch_try_cmpxchg64_release)
+#define raw_try_cmpxchg64_release arch_try_cmpxchg64_release
+#elif defined(arch_try_cmpxchg64_relaxed)
+#define raw_try_cmpxchg64_release(...) \
+	__atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__)
+#elif defined(arch_try_cmpxchg64)
+#define raw_try_cmpxchg64_release arch_try_cmpxchg64
+#else
+#define raw_try_cmpxchg64_release(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = raw_cmpxchg64_release((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
 #endif
 
-#ifndef arch_try_cmpxchg
-#define arch_try_cmpxchg(...) \
-	__atomic_op_fence(arch_try_cmpxchg, __VA_ARGS__)
+#if defined(arch_try_cmpxchg64_relaxed)
+#define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64_relaxed
+#elif defined(arch_try_cmpxchg64)
+#define raw_try_cmpxchg64_relaxed arch_try_cmpxchg64
+#else
+#define raw_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = raw_cmpxchg64_relaxed((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
 #endif
 
-#endif /* arch_try_cmpxchg_relaxed */
-
-#ifndef arch_try_cmpxchg64_relaxed
-#ifdef arch_try_cmpxchg64
-#define arch_try_cmpxchg64_acquire arch_try_cmpxchg64
-#define arch_try_cmpxchg64_release arch_try_cmpxchg64
-#define arch_try_cmpxchg64_relaxed arch_try_cmpxchg64
-#endif /* arch_try_cmpxchg64 */
-
-#ifndef arch_try_cmpxchg64
-#define arch_try_cmpxchg64(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg128)
+#define raw_try_cmpxchg128 arch_try_cmpxchg128
+#elif defined(arch_try_cmpxchg128_relaxed)
+#define raw_try_cmpxchg128(...) \
+	__atomic_op_fence(arch_try_cmpxchg128, __VA_ARGS__)
+#else
+#define raw_try_cmpxchg128(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg64((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg128((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg64 */
+#endif
 
-#ifndef arch_try_cmpxchg64_acquire
-#define arch_try_cmpxchg64_acquire(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg128_acquire)
+#define raw_try_cmpxchg128_acquire arch_try_cmpxchg128_acquire
+#elif defined(arch_try_cmpxchg128_relaxed)
+#define raw_try_cmpxchg128_acquire(...) \
+	__atomic_op_acquire(arch_try_cmpxchg128, __VA_ARGS__)
+#elif defined(arch_try_cmpxchg128)
+#define raw_try_cmpxchg128_acquire arch_try_cmpxchg128
+#else
+#define raw_try_cmpxchg128_acquire(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg64_acquire((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg128_acquire((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg64_acquire */
+#endif
 
-#ifndef arch_try_cmpxchg64_release
-#define arch_try_cmpxchg64_release(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg128_release)
+#define raw_try_cmpxchg128_release arch_try_cmpxchg128_release
+#elif defined(arch_try_cmpxchg128_relaxed)
+#define raw_try_cmpxchg128_release(...) \
+	__atomic_op_release(arch_try_cmpxchg128, __VA_ARGS__)
+#elif defined(arch_try_cmpxchg128)
+#define raw_try_cmpxchg128_release arch_try_cmpxchg128
+#else
+#define raw_try_cmpxchg128_release(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg64_release((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg128_release((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg64_release */
+#endif
 
-#ifndef arch_try_cmpxchg64_relaxed
-#define arch_try_cmpxchg64_relaxed(_ptr, _oldp, _new) \
+#if defined(arch_try_cmpxchg128_relaxed)
+#define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128_relaxed
+#elif defined(arch_try_cmpxchg128)
+#define raw_try_cmpxchg128_relaxed arch_try_cmpxchg128
+#else
+#define raw_try_cmpxchg128_relaxed(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg64_relaxed((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg128_relaxed((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg64_relaxed */
+#endif
 
-#else /* arch_try_cmpxchg64_relaxed */
+#define raw_cmpxchg_local arch_cmpxchg_local
 
-#ifndef arch_try_cmpxchg64_acquire
-#define arch_try_cmpxchg64_acquire(...) \
-	__atomic_op_acquire(arch_try_cmpxchg64, __VA_ARGS__)
+#ifdef arch_try_cmpxchg_local
+#define raw_try_cmpxchg_local arch_try_cmpxchg_local
+#else
+#define raw_try_cmpxchg_local(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = raw_cmpxchg_local((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
 #endif
 
-#ifndef arch_try_cmpxchg64_release
-#define arch_try_cmpxchg64_release(...) \
-	__atomic_op_release(arch_try_cmpxchg64, __VA_ARGS__)
-#endif
+#define raw_cmpxchg64_local arch_cmpxchg64_local
 
-#ifndef arch_try_cmpxchg64
-#define arch_try_cmpxchg64(...) \
-	__atomic_op_fence(arch_try_cmpxchg64, __VA_ARGS__)
+#ifdef arch_try_cmpxchg64_local
+#define raw_try_cmpxchg64_local arch_try_cmpxchg64_local
+#else
+#define raw_try_cmpxchg64_local(_ptr, _oldp, _new) \
+({ \
+	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
+	___r = raw_cmpxchg64_local((_ptr), ___o, (_new)); \
+	if (unlikely(___r != ___o)) \
+		*___op = ___r; \
+	likely(___r == ___o); \
+})
 #endif
 
-#endif /* arch_try_cmpxchg64_relaxed */
+#define raw_cmpxchg128_local arch_cmpxchg128_local
 
-#ifndef arch_try_cmpxchg_local
-#define arch_try_cmpxchg_local(_ptr, _oldp, _new) \
+#ifdef arch_try_cmpxchg128_local
+#define raw_try_cmpxchg128_local arch_try_cmpxchg128_local
+#else
+#define raw_try_cmpxchg128_local(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg_local((_ptr), ___o, (_new)); \
+	___r = raw_cmpxchg128_local((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg_local */
+#endif
 
-#ifndef arch_try_cmpxchg64_local
-#define arch_try_cmpxchg64_local(_ptr, _oldp, _new) \
+#define raw_sync_cmpxchg arch_sync_cmpxchg
+
+#ifdef arch_sync_try_cmpxchg
+#define raw_sync_try_cmpxchg arch_sync_try_cmpxchg
+#else
+#define raw_sync_try_cmpxchg(_ptr, _oldp, _new) \
 ({ \
 	typeof(*(_ptr)) *___op = (_oldp), ___o = *___op, ___r; \
-	___r = arch_cmpxchg64_local((_ptr), ___o, (_new)); \
+	___r = raw_sync_cmpxchg((_ptr), ___o, (_new)); \
 	if (unlikely(___r != ___o)) \
 		*___op = ___r; \
 	likely(___r == ___o); \
 })
-#endif /* arch_try_cmpxchg64_local */
+#endif
+
+/**
+ * raw_atomic_read() - atomic load with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically loads the value of @v with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_read() elsewhere.
+ *
+ * Return: The value loaded from @v.
+ */
+static __always_inline int
+raw_atomic_read(const atomic_t *v)
+{
+	return arch_atomic_read(v);
+}
 
-#ifndef arch_atomic_read_acquire
+/**
+ * raw_atomic_read_acquire() - atomic load with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically loads the value of @v with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_read_acquire() elsewhere.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline int
-arch_atomic_read_acquire(const atomic_t *v)
+raw_atomic_read_acquire(const atomic_t *v)
 {
+#if defined(arch_atomic_read_acquire)
+	return arch_atomic_read_acquire(v);
+#else
 	int ret;
 
 	if (__native_word(atomic_t)) {
 		ret = smp_load_acquire(&(v)->counter);
 	} else {
-		ret = arch_atomic_read(v);
+		ret = raw_atomic_read(v);
 		__atomic_acquire_fence();
 	}
 
 	return ret;
-}
-#define arch_atomic_read_acquire arch_atomic_read_acquire
 #endif
+}
 
-#ifndef arch_atomic_set_release
+/**
+ * raw_atomic_set() - atomic set with relaxed ordering
+ * @v: pointer to atomic_t
+ * @i: int value to assign
+ *
+ * Atomically sets @v to @i with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_set() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_set_release(atomic_t *v, int i)
+raw_atomic_set(atomic_t *v, int i)
 {
+	arch_atomic_set(v, i);
+}
+
+/**
+ * raw_atomic_set_release() - atomic set with release ordering
+ * @v: pointer to atomic_t
+ * @i: int value to assign
+ *
+ * Atomically sets @v to @i with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_set_release() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_set_release(atomic_t *v, int i)
+{
+#if defined(arch_atomic_set_release)
+	arch_atomic_set_release(v, i);
+#else
 	if (__native_word(atomic_t)) {
 		smp_store_release(&(v)->counter, i);
 	} else {
 		__atomic_release_fence();
-		arch_atomic_set(v, i);
+		raw_atomic_set(v, i);
 	}
-}
-#define arch_atomic_set_release arch_atomic_set_release
 #endif
-
-#ifndef arch_atomic_add_return_relaxed
-#define arch_atomic_add_return_acquire arch_atomic_add_return
-#define arch_atomic_add_return_release arch_atomic_add_return
-#define arch_atomic_add_return_relaxed arch_atomic_add_return
-#else /* arch_atomic_add_return_relaxed */
-
-#ifndef arch_atomic_add_return_acquire
-static __always_inline int
-arch_atomic_add_return_acquire(int i, atomic_t *v)
-{
-	int ret = arch_atomic_add_return_relaxed(i, v);
-	__atomic_acquire_fence();
-	return ret;
 }
-#define arch_atomic_add_return_acquire arch_atomic_add_return_acquire
-#endif
 
-#ifndef arch_atomic_add_return_release
-static __always_inline int
-arch_atomic_add_return_release(int i, atomic_t *v)
+/**
+ * raw_atomic_add() - atomic add with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_add(int i, atomic_t *v)
 {
-	__atomic_release_fence();
-	return arch_atomic_add_return_relaxed(i, v);
+	arch_atomic_add(i, v);
 }
-#define arch_atomic_add_return_release arch_atomic_add_return_release
-#endif
 
-#ifndef arch_atomic_add_return
+/**
+ * raw_atomic_add_return() - atomic add with full ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_add_return(int i, atomic_t *v)
+raw_atomic_add_return(int i, atomic_t *v)
 {
+#if defined(arch_atomic_add_return)
+	return arch_atomic_add_return(i, v);
+#elif defined(arch_atomic_add_return_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic_add_return_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_add_return arch_atomic_add_return
+#else
+#error "Unable to define raw_atomic_add_return"
 #endif
+}
 
-#endif /* arch_atomic_add_return_relaxed */
-
-#ifndef arch_atomic_fetch_add_relaxed
-#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add
-#define arch_atomic_fetch_add_release arch_atomic_fetch_add
-#define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add
-#else /* arch_atomic_fetch_add_relaxed */
-
-#ifndef arch_atomic_fetch_add_acquire
+/**
+ * raw_atomic_add_return_acquire() - atomic add with acquire ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_add_acquire(int i, atomic_t *v)
+raw_atomic_add_return_acquire(int i, atomic_t *v)
 {
-	int ret = arch_atomic_fetch_add_relaxed(i, v);
+#if defined(arch_atomic_add_return_acquire)
+	return arch_atomic_add_return_acquire(i, v);
+#elif defined(arch_atomic_add_return_relaxed)
+	int ret = arch_atomic_add_return_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire
+#elif defined(arch_atomic_add_return)
+	return arch_atomic_add_return(i, v);
+#else
+#error "Unable to define raw_atomic_add_return_acquire"
 #endif
+}
 
-#ifndef arch_atomic_fetch_add_release
+/**
+ * raw_atomic_add_return_release() - atomic add with release ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_add_release(int i, atomic_t *v)
+raw_atomic_add_return_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_add_return_release)
+	return arch_atomic_add_return_release(i, v);
+#elif defined(arch_atomic_add_return_relaxed)
 	__atomic_release_fence();
-	return arch_atomic_fetch_add_relaxed(i, v);
+	return arch_atomic_add_return_relaxed(i, v);
+#elif defined(arch_atomic_add_return)
+	return arch_atomic_add_return(i, v);
+#else
+#error "Unable to define raw_atomic_add_return_release"
+#endif
 }
-#define arch_atomic_fetch_add_release arch_atomic_fetch_add_release
+
+/**
+ * raw_atomic_add_return_relaxed() - atomic add with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
+static __always_inline int
+raw_atomic_add_return_relaxed(int i, atomic_t *v)
+{
+#if defined(arch_atomic_add_return_relaxed)
+	return arch_atomic_add_return_relaxed(i, v);
+#elif defined(arch_atomic_add_return)
+	return arch_atomic_add_return(i, v);
+#else
+#error "Unable to define raw_atomic_add_return_relaxed"
 #endif
+}
 
-#ifndef arch_atomic_fetch_add
+/**
+ * raw_atomic_fetch_add() - atomic add with full ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_add() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_add(int i, atomic_t *v)
+raw_atomic_fetch_add(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_add)
+	return arch_atomic_fetch_add(i, v);
+#elif defined(arch_atomic_fetch_add_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic_fetch_add_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_fetch_add arch_atomic_fetch_add
+#else
+#error "Unable to define raw_atomic_fetch_add"
 #endif
+}
 
-#endif /* arch_atomic_fetch_add_relaxed */
-
-#ifndef arch_atomic_sub_return_relaxed
-#define arch_atomic_sub_return_acquire arch_atomic_sub_return
-#define arch_atomic_sub_return_release arch_atomic_sub_return
-#define arch_atomic_sub_return_relaxed arch_atomic_sub_return
-#else /* arch_atomic_sub_return_relaxed */
-
-#ifndef arch_atomic_sub_return_acquire
+/**
+ * raw_atomic_fetch_add_acquire() - atomic add with acquire ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_add_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_sub_return_acquire(int i, atomic_t *v)
+raw_atomic_fetch_add_acquire(int i, atomic_t *v)
 {
-	int ret = arch_atomic_sub_return_relaxed(i, v);
+#if defined(arch_atomic_fetch_add_acquire)
+	return arch_atomic_fetch_add_acquire(i, v);
+#elif defined(arch_atomic_fetch_add_relaxed)
+	int ret = arch_atomic_fetch_add_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire
+#elif defined(arch_atomic_fetch_add)
+	return arch_atomic_fetch_add(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_add_acquire"
 #endif
+}
 
-#ifndef arch_atomic_sub_return_release
+/**
+ * raw_atomic_fetch_add_release() - atomic add with release ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_add_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_sub_return_release(int i, atomic_t *v)
+raw_atomic_fetch_add_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_add_release)
+	return arch_atomic_fetch_add_release(i, v);
+#elif defined(arch_atomic_fetch_add_relaxed)
 	__atomic_release_fence();
-	return arch_atomic_sub_return_relaxed(i, v);
+	return arch_atomic_fetch_add_relaxed(i, v);
+#elif defined(arch_atomic_fetch_add)
+	return arch_atomic_fetch_add(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_add_release"
+#endif
 }
-#define arch_atomic_sub_return_release arch_atomic_sub_return_release
+
+/**
+ * raw_atomic_fetch_add_relaxed() - atomic add with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_add_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline int
+raw_atomic_fetch_add_relaxed(int i, atomic_t *v)
+{
+#if defined(arch_atomic_fetch_add_relaxed)
+	return arch_atomic_fetch_add_relaxed(i, v);
+#elif defined(arch_atomic_fetch_add)
+	return arch_atomic_fetch_add(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_add_relaxed"
 #endif
+}
 
-#ifndef arch_atomic_sub_return
+/**
+ * raw_atomic_sub() - atomic subtract with relaxed ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_sub() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_sub(int i, atomic_t *v)
+{
+	arch_atomic_sub(i, v);
+}
+
+/**
+ * raw_atomic_sub_return() - atomic subtract with full ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_sub_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_sub_return(int i, atomic_t *v)
+raw_atomic_sub_return(int i, atomic_t *v)
 {
+#if defined(arch_atomic_sub_return)
+	return arch_atomic_sub_return(i, v);
+#elif defined(arch_atomic_sub_return_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic_sub_return_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_sub_return arch_atomic_sub_return
+#else
+#error "Unable to define raw_atomic_sub_return"
 #endif
+}
 
-#endif /* arch_atomic_sub_return_relaxed */
-
-#ifndef arch_atomic_fetch_sub_relaxed
-#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub
-#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub
-#define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub
-#else /* arch_atomic_fetch_sub_relaxed */
-
-#ifndef arch_atomic_fetch_sub_acquire
+/**
+ * raw_atomic_sub_return_acquire() - atomic subtract with acquire ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_sub_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_sub_acquire(int i, atomic_t *v)
+raw_atomic_sub_return_acquire(int i, atomic_t *v)
 {
-	int ret = arch_atomic_fetch_sub_relaxed(i, v);
+#if defined(arch_atomic_sub_return_acquire)
+	return arch_atomic_sub_return_acquire(i, v);
+#elif defined(arch_atomic_sub_return_relaxed)
+	int ret = arch_atomic_sub_return_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire
+#elif defined(arch_atomic_sub_return)
+	return arch_atomic_sub_return(i, v);
+#else
+#error "Unable to define raw_atomic_sub_return_acquire"
 #endif
+}
 
-#ifndef arch_atomic_fetch_sub_release
+/**
+ * raw_atomic_sub_return_release() - atomic subtract with release ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_sub_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_sub_release(int i, atomic_t *v)
+raw_atomic_sub_return_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_sub_return_release)
+	return arch_atomic_sub_return_release(i, v);
+#elif defined(arch_atomic_sub_return_relaxed)
 	__atomic_release_fence();
-	return arch_atomic_fetch_sub_relaxed(i, v);
+	return arch_atomic_sub_return_relaxed(i, v);
+#elif defined(arch_atomic_sub_return)
+	return arch_atomic_sub_return(i, v);
+#else
+#error "Unable to define raw_atomic_sub_return_release"
+#endif
 }
-#define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release
+
+/**
+ * raw_atomic_sub_return_relaxed() - atomic subtract with relaxed ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_sub_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
+static __always_inline int
+raw_atomic_sub_return_relaxed(int i, atomic_t *v)
+{
+#if defined(arch_atomic_sub_return_relaxed)
+	return arch_atomic_sub_return_relaxed(i, v);
+#elif defined(arch_atomic_sub_return)
+	return arch_atomic_sub_return(i, v);
+#else
+#error "Unable to define raw_atomic_sub_return_relaxed"
 #endif
+}
 
-#ifndef arch_atomic_fetch_sub
+/**
+ * raw_atomic_fetch_sub() - atomic subtract with full ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_sub() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_sub(int i, atomic_t *v)
+raw_atomic_fetch_sub(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_sub)
+	return arch_atomic_fetch_sub(i, v);
+#elif defined(arch_atomic_fetch_sub_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic_fetch_sub_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_fetch_sub arch_atomic_fetch_sub
+#else
+#error "Unable to define raw_atomic_fetch_sub"
 #endif
-
-#endif /* arch_atomic_fetch_sub_relaxed */
-
-#ifndef arch_atomic_inc
-static __always_inline void
-arch_atomic_inc(atomic_t *v)
-{
-	arch_atomic_add(1, v);
 }
-#define arch_atomic_inc arch_atomic_inc
-#endif
-
-#ifndef arch_atomic_inc_return_relaxed
-#ifdef arch_atomic_inc_return
-#define arch_atomic_inc_return_acquire arch_atomic_inc_return
-#define arch_atomic_inc_return_release arch_atomic_inc_return
-#define arch_atomic_inc_return_relaxed arch_atomic_inc_return
-#endif /* arch_atomic_inc_return */
 
-#ifndef arch_atomic_inc_return
+/**
+ * raw_atomic_fetch_sub_acquire() - atomic subtract with acquire ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_sub_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_inc_return(atomic_t *v)
+raw_atomic_fetch_sub_acquire(int i, atomic_t *v)
 {
-	return arch_atomic_add_return(1, v);
-}
-#define arch_atomic_inc_return arch_atomic_inc_return
+#if defined(arch_atomic_fetch_sub_acquire)
+	return arch_atomic_fetch_sub_acquire(i, v);
+#elif defined(arch_atomic_fetch_sub_relaxed)
+	int ret = arch_atomic_fetch_sub_relaxed(i, v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic_fetch_sub)
+	return arch_atomic_fetch_sub(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_sub_acquire"
 #endif
-
-#ifndef arch_atomic_inc_return_acquire
-static __always_inline int
-arch_atomic_inc_return_acquire(atomic_t *v)
-{
-	return arch_atomic_add_return_acquire(1, v);
 }
-#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire
-#endif
 
-#ifndef arch_atomic_inc_return_release
+/**
+ * raw_atomic_fetch_sub_release() - atomic subtract with release ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_sub_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_inc_return_release(atomic_t *v)
+raw_atomic_fetch_sub_release(int i, atomic_t *v)
 {
-	return arch_atomic_add_return_release(1, v);
-}
-#define arch_atomic_inc_return_release arch_atomic_inc_return_release
+#if defined(arch_atomic_fetch_sub_release)
+	return arch_atomic_fetch_sub_release(i, v);
+#elif defined(arch_atomic_fetch_sub_relaxed)
+	__atomic_release_fence();
+	return arch_atomic_fetch_sub_relaxed(i, v);
+#elif defined(arch_atomic_fetch_sub)
+	return arch_atomic_fetch_sub(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_sub_release"
 #endif
-
-#ifndef arch_atomic_inc_return_relaxed
-static __always_inline int
-arch_atomic_inc_return_relaxed(atomic_t *v)
-{
-	return arch_atomic_add_return_relaxed(1, v);
 }
-#define arch_atomic_inc_return_relaxed arch_atomic_inc_return_relaxed
-#endif
-
-#else /* arch_atomic_inc_return_relaxed */
 
-#ifndef arch_atomic_inc_return_acquire
+/**
+ * raw_atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_sub_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_inc_return_acquire(atomic_t *v)
+raw_atomic_fetch_sub_relaxed(int i, atomic_t *v)
 {
-	int ret = arch_atomic_inc_return_relaxed(v);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic_inc_return_acquire arch_atomic_inc_return_acquire
+#if defined(arch_atomic_fetch_sub_relaxed)
+	return arch_atomic_fetch_sub_relaxed(i, v);
+#elif defined(arch_atomic_fetch_sub)
+	return arch_atomic_fetch_sub(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_sub_relaxed"
 #endif
+}
 
-#ifndef arch_atomic_inc_return_release
-static __always_inline int
-arch_atomic_inc_return_release(atomic_t *v)
+/**
+ * raw_atomic_inc() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_inc() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_inc(atomic_t *v)
 {
-	__atomic_release_fence();
-	return arch_atomic_inc_return_relaxed(v);
-}
-#define arch_atomic_inc_return_release arch_atomic_inc_return_release
+#if defined(arch_atomic_inc)
+	arch_atomic_inc(v);
+#else
+	raw_atomic_add(1, v);
 #endif
+}
 
-#ifndef arch_atomic_inc_return
+/**
+ * raw_atomic_inc_return() - atomic increment with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_inc_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_inc_return(atomic_t *v)
+raw_atomic_inc_return(atomic_t *v)
 {
+#if defined(arch_atomic_inc_return)
+	return arch_atomic_inc_return(v);
+#elif defined(arch_atomic_inc_return_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic_inc_return_relaxed(v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_inc_return arch_atomic_inc_return
+#else
+	return raw_atomic_add_return(1, v);
 #endif
+}
 
-#endif /* arch_atomic_inc_return_relaxed */
-
-#ifndef arch_atomic_fetch_inc_relaxed
-#ifdef arch_atomic_fetch_inc
-#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc
-#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc
-#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc
-#endif /* arch_atomic_fetch_inc */
-
-#ifndef arch_atomic_fetch_inc
+/**
+ * raw_atomic_inc_return_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_inc_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc(atomic_t *v)
+raw_atomic_inc_return_acquire(atomic_t *v)
 {
-	return arch_atomic_fetch_add(1, v);
-}
-#define arch_atomic_fetch_inc arch_atomic_fetch_inc
+#if defined(arch_atomic_inc_return_acquire)
+	return arch_atomic_inc_return_acquire(v);
+#elif defined(arch_atomic_inc_return_relaxed)
+	int ret = arch_atomic_inc_return_relaxed(v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic_inc_return)
+	return arch_atomic_inc_return(v);
+#else
+	return raw_atomic_add_return_acquire(1, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_inc_acquire
+/**
+ * raw_atomic_inc_return_release() - atomic increment with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_inc_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc_acquire(atomic_t *v)
+raw_atomic_inc_return_release(atomic_t *v)
 {
-	return arch_atomic_fetch_add_acquire(1, v);
-}
-#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire
+#if defined(arch_atomic_inc_return_release)
+	return arch_atomic_inc_return_release(v);
+#elif defined(arch_atomic_inc_return_relaxed)
+	__atomic_release_fence();
+	return arch_atomic_inc_return_relaxed(v);
+#elif defined(arch_atomic_inc_return)
+	return arch_atomic_inc_return(v);
+#else
+	return raw_atomic_add_return_release(1, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_inc_release
+/**
+ * raw_atomic_inc_return_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_inc_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc_release(atomic_t *v)
+raw_atomic_inc_return_relaxed(atomic_t *v)
 {
-	return arch_atomic_fetch_add_release(1, v);
-}
-#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release
+#if defined(arch_atomic_inc_return_relaxed)
+	return arch_atomic_inc_return_relaxed(v);
+#elif defined(arch_atomic_inc_return)
+	return arch_atomic_inc_return(v);
+#else
+	return raw_atomic_add_return_relaxed(1, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_inc_relaxed
+/**
+ * raw_atomic_fetch_inc() - atomic increment with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_inc() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc_relaxed(atomic_t *v)
+raw_atomic_fetch_inc(atomic_t *v)
 {
-	return arch_atomic_fetch_add_relaxed(1, v);
-}
-#define arch_atomic_fetch_inc_relaxed arch_atomic_fetch_inc_relaxed
+#if defined(arch_atomic_fetch_inc)
+	return arch_atomic_fetch_inc(v);
+#elif defined(arch_atomic_fetch_inc_relaxed)
+	int ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic_fetch_inc_relaxed(v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic_fetch_add(1, v);
 #endif
+}
 
-#else /* arch_atomic_fetch_inc_relaxed */
-
-#ifndef arch_atomic_fetch_inc_acquire
+/**
+ * raw_atomic_fetch_inc_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_inc_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc_acquire(atomic_t *v)
+raw_atomic_fetch_inc_acquire(atomic_t *v)
 {
+#if defined(arch_atomic_fetch_inc_acquire)
+	return arch_atomic_fetch_inc_acquire(v);
+#elif defined(arch_atomic_fetch_inc_relaxed)
 	int ret = arch_atomic_fetch_inc_relaxed(v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_inc_acquire arch_atomic_fetch_inc_acquire
+#elif defined(arch_atomic_fetch_inc)
+	return arch_atomic_fetch_inc(v);
+#else
+	return raw_atomic_fetch_add_acquire(1, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_inc_release
+/**
+ * raw_atomic_fetch_inc_release() - atomic increment with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_inc_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc_release(atomic_t *v)
+raw_atomic_fetch_inc_release(atomic_t *v)
 {
+#if defined(arch_atomic_fetch_inc_release)
+	return arch_atomic_fetch_inc_release(v);
+#elif defined(arch_atomic_fetch_inc_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_fetch_inc_relaxed(v);
-}
-#define arch_atomic_fetch_inc_release arch_atomic_fetch_inc_release
+#elif defined(arch_atomic_fetch_inc)
+	return arch_atomic_fetch_inc(v);
+#else
+	return raw_atomic_fetch_add_release(1, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_inc
+/**
+ * raw_atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_inc_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_inc(atomic_t *v)
+raw_atomic_fetch_inc_relaxed(atomic_t *v)
 {
-	int ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic_fetch_inc_relaxed(v);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic_fetch_inc arch_atomic_fetch_inc
+#if defined(arch_atomic_fetch_inc_relaxed)
+	return arch_atomic_fetch_inc_relaxed(v);
+#elif defined(arch_atomic_fetch_inc)
+	return arch_atomic_fetch_inc(v);
+#else
+	return raw_atomic_fetch_add_relaxed(1, v);
 #endif
-
-#endif /* arch_atomic_fetch_inc_relaxed */
-
-#ifndef arch_atomic_dec
-static __always_inline void
-arch_atomic_dec(atomic_t *v)
-{
-	arch_atomic_sub(1, v);
 }
-#define arch_atomic_dec arch_atomic_dec
-#endif
 
-#ifndef arch_atomic_dec_return_relaxed
-#ifdef arch_atomic_dec_return
-#define arch_atomic_dec_return_acquire arch_atomic_dec_return
-#define arch_atomic_dec_return_release arch_atomic_dec_return
-#define arch_atomic_dec_return_relaxed arch_atomic_dec_return
-#endif /* arch_atomic_dec_return */
-
-#ifndef arch_atomic_dec_return
-static __always_inline int
-arch_atomic_dec_return(atomic_t *v)
+/**
+ * raw_atomic_dec() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_dec(atomic_t *v)
 {
-	return arch_atomic_sub_return(1, v);
-}
-#define arch_atomic_dec_return arch_atomic_dec_return
+#if defined(arch_atomic_dec)
+	arch_atomic_dec(v);
+#else
+	raw_atomic_sub(1, v);
 #endif
-
-#ifndef arch_atomic_dec_return_acquire
-static __always_inline int
-arch_atomic_dec_return_acquire(atomic_t *v)
-{
-	return arch_atomic_sub_return_acquire(1, v);
 }
-#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire
-#endif
 
-#ifndef arch_atomic_dec_return_release
+/**
+ * raw_atomic_dec_return() - atomic decrement with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_dec_return_release(atomic_t *v)
+raw_atomic_dec_return(atomic_t *v)
 {
-	return arch_atomic_sub_return_release(1, v);
-}
-#define arch_atomic_dec_return_release arch_atomic_dec_return_release
+#if defined(arch_atomic_dec_return)
+	return arch_atomic_dec_return(v);
+#elif defined(arch_atomic_dec_return_relaxed)
+	int ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic_dec_return_relaxed(v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic_sub_return(1, v);
 #endif
-
-#ifndef arch_atomic_dec_return_relaxed
-static __always_inline int
-arch_atomic_dec_return_relaxed(atomic_t *v)
-{
-	return arch_atomic_sub_return_relaxed(1, v);
 }
-#define arch_atomic_dec_return_relaxed arch_atomic_dec_return_relaxed
-#endif
-
-#else /* arch_atomic_dec_return_relaxed */
 
-#ifndef arch_atomic_dec_return_acquire
+/**
+ * raw_atomic_dec_return_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_dec_return_acquire(atomic_t *v)
+raw_atomic_dec_return_acquire(atomic_t *v)
 {
+#if defined(arch_atomic_dec_return_acquire)
+	return arch_atomic_dec_return_acquire(v);
+#elif defined(arch_atomic_dec_return_relaxed)
 	int ret = arch_atomic_dec_return_relaxed(v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_dec_return_acquire arch_atomic_dec_return_acquire
+#elif defined(arch_atomic_dec_return)
+	return arch_atomic_dec_return(v);
+#else
+	return raw_atomic_sub_return_acquire(1, v);
 #endif
+}
 
-#ifndef arch_atomic_dec_return_release
+/**
+ * raw_atomic_dec_return_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
-arch_atomic_dec_return_release(atomic_t *v)
+raw_atomic_dec_return_release(atomic_t *v)
 {
+#if defined(arch_atomic_dec_return_release)
+	return arch_atomic_dec_return_release(v);
+#elif defined(arch_atomic_dec_return_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_dec_return_relaxed(v);
+#elif defined(arch_atomic_dec_return)
+	return arch_atomic_dec_return(v);
+#else
+	return raw_atomic_sub_return_release(1, v);
+#endif
 }
-#define arch_atomic_dec_return_release arch_atomic_dec_return_release
+
+/**
+ * raw_atomic_dec_return_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
+static __always_inline int
+raw_atomic_dec_return_relaxed(atomic_t *v)
+{
+#if defined(arch_atomic_dec_return_relaxed)
+	return arch_atomic_dec_return_relaxed(v);
+#elif defined(arch_atomic_dec_return)
+	return arch_atomic_dec_return(v);
+#else
+	return raw_atomic_sub_return_relaxed(1, v);
 #endif
+}
 
-#ifndef arch_atomic_dec_return
+/**
+ * raw_atomic_fetch_dec() - atomic decrement with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_dec() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_dec_return(atomic_t *v)
+raw_atomic_fetch_dec(atomic_t *v)
 {
+#if defined(arch_atomic_fetch_dec)
+	return arch_atomic_fetch_dec(v);
+#elif defined(arch_atomic_fetch_dec_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic_dec_return_relaxed(v);
+	ret = arch_atomic_fetch_dec_relaxed(v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_dec_return arch_atomic_dec_return
+#else
+	return raw_atomic_fetch_sub(1, v);
 #endif
-
-#endif /* arch_atomic_dec_return_relaxed */
-
-#ifndef arch_atomic_fetch_dec_relaxed
-#ifdef arch_atomic_fetch_dec
-#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec
-#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec
-#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec
-#endif /* arch_atomic_fetch_dec */
-
-#ifndef arch_atomic_fetch_dec
-static __always_inline int
-arch_atomic_fetch_dec(atomic_t *v)
-{
-	return arch_atomic_fetch_sub(1, v);
 }
-#define arch_atomic_fetch_dec arch_atomic_fetch_dec
-#endif
 
-#ifndef arch_atomic_fetch_dec_acquire
+/**
+ * raw_atomic_fetch_dec_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_dec_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_dec_acquire(atomic_t *v)
+raw_atomic_fetch_dec_acquire(atomic_t *v)
 {
-	return arch_atomic_fetch_sub_acquire(1, v);
-}
-#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire
+#if defined(arch_atomic_fetch_dec_acquire)
+	return arch_atomic_fetch_dec_acquire(v);
+#elif defined(arch_atomic_fetch_dec_relaxed)
+	int ret = arch_atomic_fetch_dec_relaxed(v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic_fetch_dec)
+	return arch_atomic_fetch_dec(v);
+#else
+	return raw_atomic_fetch_sub_acquire(1, v);
 #endif
-
-#ifndef arch_atomic_fetch_dec_release
-static __always_inline int
-arch_atomic_fetch_dec_release(atomic_t *v)
-{
-	return arch_atomic_fetch_sub_release(1, v);
 }
-#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release
-#endif
 
-#ifndef arch_atomic_fetch_dec_relaxed
+/**
+ * raw_atomic_fetch_dec_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_dec_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_dec_relaxed(atomic_t *v)
+raw_atomic_fetch_dec_release(atomic_t *v)
 {
-	return arch_atomic_fetch_sub_relaxed(1, v);
-}
-#define arch_atomic_fetch_dec_relaxed arch_atomic_fetch_dec_relaxed
+#if defined(arch_atomic_fetch_dec_release)
+	return arch_atomic_fetch_dec_release(v);
+#elif defined(arch_atomic_fetch_dec_relaxed)
+	__atomic_release_fence();
+	return arch_atomic_fetch_dec_relaxed(v);
+#elif defined(arch_atomic_fetch_dec)
+	return arch_atomic_fetch_dec(v);
+#else
+	return raw_atomic_fetch_sub_release(1, v);
 #endif
+}
 
-#else /* arch_atomic_fetch_dec_relaxed */
-
-#ifndef arch_atomic_fetch_dec_acquire
+/**
+ * raw_atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_dec_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_dec_acquire(atomic_t *v)
+raw_atomic_fetch_dec_relaxed(atomic_t *v)
 {
-	int ret = arch_atomic_fetch_dec_relaxed(v);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic_fetch_dec_acquire arch_atomic_fetch_dec_acquire
+#if defined(arch_atomic_fetch_dec_relaxed)
+	return arch_atomic_fetch_dec_relaxed(v);
+#elif defined(arch_atomic_fetch_dec)
+	return arch_atomic_fetch_dec(v);
+#else
+	return raw_atomic_fetch_sub_relaxed(1, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_dec_release
-static __always_inline int
-arch_atomic_fetch_dec_release(atomic_t *v)
+/**
+ * raw_atomic_and() - atomic bitwise AND with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_and() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_and(int i, atomic_t *v)
 {
-	__atomic_release_fence();
-	return arch_atomic_fetch_dec_relaxed(v);
+	arch_atomic_and(i, v);
 }
-#define arch_atomic_fetch_dec_release arch_atomic_fetch_dec_release
-#endif
 
-#ifndef arch_atomic_fetch_dec
+/**
+ * raw_atomic_fetch_and() - atomic bitwise AND with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_and() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_dec(atomic_t *v)
+raw_atomic_fetch_and(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_and)
+	return arch_atomic_fetch_and(i, v);
+#elif defined(arch_atomic_fetch_and_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic_fetch_dec_relaxed(v);
+	ret = arch_atomic_fetch_and_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_fetch_dec arch_atomic_fetch_dec
+#else
+#error "Unable to define raw_atomic_fetch_and"
 #endif
+}
 
-#endif /* arch_atomic_fetch_dec_relaxed */
-
-#ifndef arch_atomic_fetch_and_relaxed
-#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and
-#define arch_atomic_fetch_and_release arch_atomic_fetch_and
-#define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and
-#else /* arch_atomic_fetch_and_relaxed */
-
-#ifndef arch_atomic_fetch_and_acquire
+/**
+ * raw_atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_and_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_and_acquire(int i, atomic_t *v)
+raw_atomic_fetch_and_acquire(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_and_acquire)
+	return arch_atomic_fetch_and_acquire(i, v);
+#elif defined(arch_atomic_fetch_and_relaxed)
 	int ret = arch_atomic_fetch_and_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire
+#elif defined(arch_atomic_fetch_and)
+	return arch_atomic_fetch_and(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_and_acquire"
 #endif
+}
 
-#ifndef arch_atomic_fetch_and_release
+/**
+ * raw_atomic_fetch_and_release() - atomic bitwise AND with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_and_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_and_release(int i, atomic_t *v)
+raw_atomic_fetch_and_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_and_release)
+	return arch_atomic_fetch_and_release(i, v);
+#elif defined(arch_atomic_fetch_and_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_fetch_and_relaxed(i, v);
-}
-#define arch_atomic_fetch_and_release arch_atomic_fetch_and_release
+#elif defined(arch_atomic_fetch_and)
+	return arch_atomic_fetch_and(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_and_release"
 #endif
+}
 
-#ifndef arch_atomic_fetch_and
+/**
+ * raw_atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_and_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_and(int i, atomic_t *v)
+raw_atomic_fetch_and_relaxed(int i, atomic_t *v)
 {
-	int ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic_fetch_and_relaxed(i, v);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic_fetch_and arch_atomic_fetch_and
+#if defined(arch_atomic_fetch_and_relaxed)
+	return arch_atomic_fetch_and_relaxed(i, v);
+#elif defined(arch_atomic_fetch_and)
+	return arch_atomic_fetch_and(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_and_relaxed"
 #endif
-
-#endif /* arch_atomic_fetch_and_relaxed */
-
-#ifndef arch_atomic_andnot
-static __always_inline void
-arch_atomic_andnot(int i, atomic_t *v)
-{
-	arch_atomic_and(~i, v);
 }
-#define arch_atomic_andnot arch_atomic_andnot
-#endif
-
-#ifndef arch_atomic_fetch_andnot_relaxed
-#ifdef arch_atomic_fetch_andnot
-#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot
-#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot
-#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot
-#endif /* arch_atomic_fetch_andnot */
 
-#ifndef arch_atomic_fetch_andnot
-static __always_inline int
-arch_atomic_fetch_andnot(int i, atomic_t *v)
+/**
+ * raw_atomic_andnot() - atomic bitwise AND NOT with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_andnot() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_andnot(int i, atomic_t *v)
 {
-	return arch_atomic_fetch_and(~i, v);
-}
-#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot
+#if defined(arch_atomic_andnot)
+	arch_atomic_andnot(i, v);
+#else
+	raw_atomic_and(~i, v);
 #endif
-
-#ifndef arch_atomic_fetch_andnot_acquire
-static __always_inline int
-arch_atomic_fetch_andnot_acquire(int i, atomic_t *v)
-{
-	return arch_atomic_fetch_and_acquire(~i, v);
 }
-#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire
-#endif
 
-#ifndef arch_atomic_fetch_andnot_release
+/**
+ * raw_atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_andnot() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_andnot_release(int i, atomic_t *v)
+raw_atomic_fetch_andnot(int i, atomic_t *v)
 {
-	return arch_atomic_fetch_and_release(~i, v);
-}
-#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release
+#if defined(arch_atomic_fetch_andnot)
+	return arch_atomic_fetch_andnot(i, v);
+#elif defined(arch_atomic_fetch_andnot_relaxed)
+	int ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic_fetch_andnot_relaxed(i, v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic_fetch_and(~i, v);
 #endif
-
-#ifndef arch_atomic_fetch_andnot_relaxed
-static __always_inline int
-arch_atomic_fetch_andnot_relaxed(int i, atomic_t *v)
-{
-	return arch_atomic_fetch_and_relaxed(~i, v);
 }
-#define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed
-#endif
 
-#else /* arch_atomic_fetch_andnot_relaxed */
-
-#ifndef arch_atomic_fetch_andnot_acquire
+/**
+ * raw_atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_andnot_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_andnot_acquire(int i, atomic_t *v)
+raw_atomic_fetch_andnot_acquire(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_andnot_acquire)
+	return arch_atomic_fetch_andnot_acquire(i, v);
+#elif defined(arch_atomic_fetch_andnot_relaxed)
 	int ret = arch_atomic_fetch_andnot_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire
+#elif defined(arch_atomic_fetch_andnot)
+	return arch_atomic_fetch_andnot(i, v);
+#else
+	return raw_atomic_fetch_and_acquire(~i, v);
 #endif
+}
 
-#ifndef arch_atomic_fetch_andnot_release
+/**
+ * raw_atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_andnot_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_andnot_release(int i, atomic_t *v)
+raw_atomic_fetch_andnot_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_andnot_release)
+	return arch_atomic_fetch_andnot_release(i, v);
+#elif defined(arch_atomic_fetch_andnot_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_fetch_andnot_relaxed(i, v);
+#elif defined(arch_atomic_fetch_andnot)
+	return arch_atomic_fetch_andnot(i, v);
+#else
+	return raw_atomic_fetch_and_release(~i, v);
+#endif
 }
-#define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release
+
+/**
+ * raw_atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_andnot_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline int
+raw_atomic_fetch_andnot_relaxed(int i, atomic_t *v)
+{
+#if defined(arch_atomic_fetch_andnot_relaxed)
+	return arch_atomic_fetch_andnot_relaxed(i, v);
+#elif defined(arch_atomic_fetch_andnot)
+	return arch_atomic_fetch_andnot(i, v);
+#else
+	return raw_atomic_fetch_and_relaxed(~i, v);
 #endif
+}
+
+/**
+ * raw_atomic_or() - atomic bitwise OR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_or() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_or(int i, atomic_t *v)
+{
+	arch_atomic_or(i, v);
+}
 
-#ifndef arch_atomic_fetch_andnot
+/**
+ * raw_atomic_fetch_or() - atomic bitwise OR with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_or() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_andnot(int i, atomic_t *v)
+raw_atomic_fetch_or(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_or)
+	return arch_atomic_fetch_or(i, v);
+#elif defined(arch_atomic_fetch_or_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic_fetch_andnot_relaxed(i, v);
+	ret = arch_atomic_fetch_or_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_fetch_andnot arch_atomic_fetch_andnot
+#else
+#error "Unable to define raw_atomic_fetch_or"
 #endif
+}
 
-#endif /* arch_atomic_fetch_andnot_relaxed */
-
-#ifndef arch_atomic_fetch_or_relaxed
-#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or
-#define arch_atomic_fetch_or_release arch_atomic_fetch_or
-#define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or
-#else /* arch_atomic_fetch_or_relaxed */
-
-#ifndef arch_atomic_fetch_or_acquire
+/**
+ * raw_atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_or_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_or_acquire(int i, atomic_t *v)
+raw_atomic_fetch_or_acquire(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_or_acquire)
+	return arch_atomic_fetch_or_acquire(i, v);
+#elif defined(arch_atomic_fetch_or_relaxed)
 	int ret = arch_atomic_fetch_or_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire
+#elif defined(arch_atomic_fetch_or)
+	return arch_atomic_fetch_or(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_or_acquire"
 #endif
+}
 
-#ifndef arch_atomic_fetch_or_release
+/**
+ * raw_atomic_fetch_or_release() - atomic bitwise OR with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_or_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_or_release(int i, atomic_t *v)
+raw_atomic_fetch_or_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_or_release)
+	return arch_atomic_fetch_or_release(i, v);
+#elif defined(arch_atomic_fetch_or_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_fetch_or_relaxed(i, v);
+#elif defined(arch_atomic_fetch_or)
+	return arch_atomic_fetch_or(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_or_release"
+#endif
 }
-#define arch_atomic_fetch_or_release arch_atomic_fetch_or_release
+
+/**
+ * raw_atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_or_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline int
+raw_atomic_fetch_or_relaxed(int i, atomic_t *v)
+{
+#if defined(arch_atomic_fetch_or_relaxed)
+	return arch_atomic_fetch_or_relaxed(i, v);
+#elif defined(arch_atomic_fetch_or)
+	return arch_atomic_fetch_or(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_or_relaxed"
 #endif
+}
 
-#ifndef arch_atomic_fetch_or
+/**
+ * raw_atomic_xor() - atomic bitwise XOR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_xor() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic_xor(int i, atomic_t *v)
+{
+	arch_atomic_xor(i, v);
+}
+
+/**
+ * raw_atomic_fetch_xor() - atomic bitwise XOR with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_xor() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_or(int i, atomic_t *v)
+raw_atomic_fetch_xor(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_xor)
+	return arch_atomic_fetch_xor(i, v);
+#elif defined(arch_atomic_fetch_xor_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic_fetch_or_relaxed(i, v);
+	ret = arch_atomic_fetch_xor_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_fetch_or arch_atomic_fetch_or
+#else
+#error "Unable to define raw_atomic_fetch_xor"
 #endif
+}
 
-#endif /* arch_atomic_fetch_or_relaxed */
-
-#ifndef arch_atomic_fetch_xor_relaxed
-#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor
-#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor
-#define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor
-#else /* arch_atomic_fetch_xor_relaxed */
-
-#ifndef arch_atomic_fetch_xor_acquire
+/**
+ * raw_atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_xor_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_xor_acquire(int i, atomic_t *v)
+raw_atomic_fetch_xor_acquire(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_xor_acquire)
+	return arch_atomic_fetch_xor_acquire(i, v);
+#elif defined(arch_atomic_fetch_xor_relaxed)
 	int ret = arch_atomic_fetch_xor_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire
+#elif defined(arch_atomic_fetch_xor)
+	return arch_atomic_fetch_xor(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_xor_acquire"
 #endif
+}
 
-#ifndef arch_atomic_fetch_xor_release
+/**
+ * raw_atomic_fetch_xor_release() - atomic bitwise XOR with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_xor_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_xor_release(int i, atomic_t *v)
+raw_atomic_fetch_xor_release(int i, atomic_t *v)
 {
+#if defined(arch_atomic_fetch_xor_release)
+	return arch_atomic_fetch_xor_release(i, v);
+#elif defined(arch_atomic_fetch_xor_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_fetch_xor_relaxed(i, v);
+#elif defined(arch_atomic_fetch_xor)
+	return arch_atomic_fetch_xor(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_xor_release"
+#endif
 }
-#define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release
+
+/**
+ * raw_atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_xor_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline int
+raw_atomic_fetch_xor_relaxed(int i, atomic_t *v)
+{
+#if defined(arch_atomic_fetch_xor_relaxed)
+	return arch_atomic_fetch_xor_relaxed(i, v);
+#elif defined(arch_atomic_fetch_xor)
+	return arch_atomic_fetch_xor(i, v);
+#else
+#error "Unable to define raw_atomic_fetch_xor_relaxed"
 #endif
+}
 
-#ifndef arch_atomic_fetch_xor
+/**
+ * raw_atomic_xchg() - atomic exchange with full ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_xchg() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_fetch_xor(int i, atomic_t *v)
+raw_atomic_xchg(atomic_t *v, int new)
 {
+#if defined(arch_atomic_xchg)
+	return arch_atomic_xchg(v, new);
+#elif defined(arch_atomic_xchg_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic_fetch_xor_relaxed(i, v);
+	ret = arch_atomic_xchg_relaxed(v, new);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_fetch_xor arch_atomic_fetch_xor
+#else
+	return raw_xchg(&v->counter, new);
 #endif
+}
 
-#endif /* arch_atomic_fetch_xor_relaxed */
-
-#ifndef arch_atomic_xchg_relaxed
-#define arch_atomic_xchg_acquire arch_atomic_xchg
-#define arch_atomic_xchg_release arch_atomic_xchg
-#define arch_atomic_xchg_relaxed arch_atomic_xchg
-#else /* arch_atomic_xchg_relaxed */
-
-#ifndef arch_atomic_xchg_acquire
+/**
+ * raw_atomic_xchg_acquire() - atomic exchange with acquire ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_xchg_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_xchg_acquire(atomic_t *v, int i)
+raw_atomic_xchg_acquire(atomic_t *v, int new)
 {
-	int ret = arch_atomic_xchg_relaxed(v, i);
+#if defined(arch_atomic_xchg_acquire)
+	return arch_atomic_xchg_acquire(v, new);
+#elif defined(arch_atomic_xchg_relaxed)
+	int ret = arch_atomic_xchg_relaxed(v, new);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_xchg_acquire arch_atomic_xchg_acquire
+#elif defined(arch_atomic_xchg)
+	return arch_atomic_xchg(v, new);
+#else
+	return raw_xchg_acquire(&v->counter, new);
 #endif
+}
 
-#ifndef arch_atomic_xchg_release
+/**
+ * raw_atomic_xchg_release() - atomic exchange with release ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_xchg_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_xchg_release(atomic_t *v, int i)
+raw_atomic_xchg_release(atomic_t *v, int new)
 {
+#if defined(arch_atomic_xchg_release)
+	return arch_atomic_xchg_release(v, new);
+#elif defined(arch_atomic_xchg_relaxed)
 	__atomic_release_fence();
-	return arch_atomic_xchg_relaxed(v, i);
+	return arch_atomic_xchg_relaxed(v, new);
+#elif defined(arch_atomic_xchg)
+	return arch_atomic_xchg(v, new);
+#else
+	return raw_xchg_release(&v->counter, new);
+#endif
 }
-#define arch_atomic_xchg_release arch_atomic_xchg_release
+
+/**
+ * raw_atomic_xchg_relaxed() - atomic exchange with relaxed ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_xchg_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline int
+raw_atomic_xchg_relaxed(atomic_t *v, int new)
+{
+#if defined(arch_atomic_xchg_relaxed)
+	return arch_atomic_xchg_relaxed(v, new);
+#elif defined(arch_atomic_xchg)
+	return arch_atomic_xchg(v, new);
+#else
+	return raw_xchg_relaxed(&v->counter, new);
 #endif
+}
 
-#ifndef arch_atomic_xchg
+/**
+ * raw_atomic_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_cmpxchg() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_xchg(atomic_t *v, int i)
+raw_atomic_cmpxchg(atomic_t *v, int old, int new)
 {
+#if defined(arch_atomic_cmpxchg)
+	return arch_atomic_cmpxchg(v, old, new);
+#elif defined(arch_atomic_cmpxchg_relaxed)
 	int ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic_xchg_relaxed(v, i);
+	ret = arch_atomic_cmpxchg_relaxed(v, old, new);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic_xchg arch_atomic_xchg
+#else
+	return raw_cmpxchg(&v->counter, old, new);
 #endif
+}
 
-#endif /* arch_atomic_xchg_relaxed */
-
-#ifndef arch_atomic_cmpxchg_relaxed
-#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg
-#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg
-#define arch_atomic_cmpxchg_relaxed arch_atomic_cmpxchg
-#else /* arch_atomic_cmpxchg_relaxed */
-
-#ifndef arch_atomic_cmpxchg_acquire
+/**
+ * raw_atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_cmpxchg_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
+raw_atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
 {
+#if defined(arch_atomic_cmpxchg_acquire)
+	return arch_atomic_cmpxchg_acquire(v, old, new);
+#elif defined(arch_atomic_cmpxchg_relaxed)
 	int ret = arch_atomic_cmpxchg_relaxed(v, old, new);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic_cmpxchg_acquire arch_atomic_cmpxchg_acquire
+#elif defined(arch_atomic_cmpxchg)
+	return arch_atomic_cmpxchg(v, old, new);
+#else
+	return raw_cmpxchg_acquire(&v->counter, old, new);
 #endif
+}
 
-#ifndef arch_atomic_cmpxchg_release
+/**
+ * raw_atomic_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_cmpxchg_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_cmpxchg_release(atomic_t *v, int old, int new)
+raw_atomic_cmpxchg_release(atomic_t *v, int old, int new)
 {
+#if defined(arch_atomic_cmpxchg_release)
+	return arch_atomic_cmpxchg_release(v, old, new);
+#elif defined(arch_atomic_cmpxchg_relaxed)
 	__atomic_release_fence();
 	return arch_atomic_cmpxchg_relaxed(v, old, new);
-}
-#define arch_atomic_cmpxchg_release arch_atomic_cmpxchg_release
+#elif defined(arch_atomic_cmpxchg)
+	return arch_atomic_cmpxchg(v, old, new);
+#else
+	return raw_cmpxchg_release(&v->counter, old, new);
 #endif
+}
 
-#ifndef arch_atomic_cmpxchg
+/**
+ * raw_atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_cmpxchg_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-arch_atomic_cmpxchg(atomic_t *v, int old, int new)
+raw_atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
 {
-	int ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic_cmpxchg_relaxed(v, old, new);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic_cmpxchg arch_atomic_cmpxchg
+#if defined(arch_atomic_cmpxchg_relaxed)
+	return arch_atomic_cmpxchg_relaxed(v, old, new);
+#elif defined(arch_atomic_cmpxchg)
+	return arch_atomic_cmpxchg(v, old, new);
+#else
+	return raw_cmpxchg_relaxed(&v->counter, old, new);
 #endif
+}
 
-#endif /* arch_atomic_cmpxchg_relaxed */
-
-#ifndef arch_atomic_try_cmpxchg_relaxed
-#ifdef arch_atomic_try_cmpxchg
-#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg
-#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg
-#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg
-#endif /* arch_atomic_try_cmpxchg */
-
-#ifndef arch_atomic_try_cmpxchg
+/**
+ * raw_atomic_try_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_try_cmpxchg() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
+raw_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
+#if defined(arch_atomic_try_cmpxchg)
+	return arch_atomic_try_cmpxchg(v, old, new);
+#elif defined(arch_atomic_try_cmpxchg_relaxed)
+	bool ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic_try_cmpxchg_relaxed(v, old, new);
+	__atomic_post_full_fence();
+	return ret;
+#else
 	int r, o = *old;
-	r = arch_atomic_cmpxchg(v, o, new);
+	r = raw_atomic_cmpxchg(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
 #endif
+}
 
-#ifndef arch_atomic_try_cmpxchg_acquire
+/**
+ * raw_atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_try_cmpxchg_acquire() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
+raw_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
 {
+#if defined(arch_atomic_try_cmpxchg_acquire)
+	return arch_atomic_try_cmpxchg_acquire(v, old, new);
+#elif defined(arch_atomic_try_cmpxchg_relaxed)
+	bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic_try_cmpxchg)
+	return arch_atomic_try_cmpxchg(v, old, new);
+#else
 	int r, o = *old;
-	r = arch_atomic_cmpxchg_acquire(v, o, new);
+	r = raw_atomic_cmpxchg_acquire(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire
 #endif
+}
 
-#ifndef arch_atomic_try_cmpxchg_release
+/**
+ * raw_atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_try_cmpxchg_release() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
+raw_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
 {
+#if defined(arch_atomic_try_cmpxchg_release)
+	return arch_atomic_try_cmpxchg_release(v, old, new);
+#elif defined(arch_atomic_try_cmpxchg_relaxed)
+	__atomic_release_fence();
+	return arch_atomic_try_cmpxchg_relaxed(v, old, new);
+#elif defined(arch_atomic_try_cmpxchg)
+	return arch_atomic_try_cmpxchg(v, old, new);
+#else
 	int r, o = *old;
-	r = arch_atomic_cmpxchg_release(v, o, new);
+	r = raw_atomic_cmpxchg_release(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release
 #endif
+}
 
-#ifndef arch_atomic_try_cmpxchg_relaxed
+/**
+ * raw_atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_try_cmpxchg_relaxed() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
+raw_atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
 {
+#if defined(arch_atomic_try_cmpxchg_relaxed)
+	return arch_atomic_try_cmpxchg_relaxed(v, old, new);
+#elif defined(arch_atomic_try_cmpxchg)
+	return arch_atomic_try_cmpxchg(v, old, new);
+#else
 	int r, o = *old;
-	r = arch_atomic_cmpxchg_relaxed(v, o, new);
+	r = raw_atomic_cmpxchg_relaxed(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic_try_cmpxchg_relaxed arch_atomic_try_cmpxchg_relaxed
-#endif
-
-#else /* arch_atomic_try_cmpxchg_relaxed */
-
-#ifndef arch_atomic_try_cmpxchg_acquire
-static __always_inline bool
-arch_atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
-{
-	bool ret = arch_atomic_try_cmpxchg_relaxed(v, old, new);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic_try_cmpxchg_acquire arch_atomic_try_cmpxchg_acquire
 #endif
-
-#ifndef arch_atomic_try_cmpxchg_release
-static __always_inline bool
-arch_atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
-{
-	__atomic_release_fence();
-	return arch_atomic_try_cmpxchg_relaxed(v, old, new);
 }
-#define arch_atomic_try_cmpxchg_release arch_atomic_try_cmpxchg_release
-#endif
 
-#ifndef arch_atomic_try_cmpxchg
-static __always_inline bool
-arch_atomic_try_cmpxchg(atomic_t *v, int *old, int new)
-{
-	bool ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic_try_cmpxchg_relaxed(v, old, new);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic_try_cmpxchg arch_atomic_try_cmpxchg
-#endif
-
-#endif /* arch_atomic_try_cmpxchg_relaxed */
-
-#ifndef arch_atomic_sub_and_test
 /**
- * arch_atomic_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic_t
+ * raw_atomic_sub_and_test() - atomic subtract and test if zero with full ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_sub_and_test() elsewhere.
  *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_sub_and_test(int i, atomic_t *v)
+raw_atomic_sub_and_test(int i, atomic_t *v)
 {
-	return arch_atomic_sub_return(i, v) == 0;
-}
-#define arch_atomic_sub_and_test arch_atomic_sub_and_test
+#if defined(arch_atomic_sub_and_test)
+	return arch_atomic_sub_and_test(i, v);
+#else
+	return raw_atomic_sub_return(i, v) == 0;
 #endif
+}
 
-#ifndef arch_atomic_dec_and_test
 /**
- * arch_atomic_dec_and_test - decrement and test
- * @v: pointer of type atomic_t
+ * raw_atomic_dec_and_test() - atomic decrement and test if zero with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_and_test() elsewhere.
  *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_dec_and_test(atomic_t *v)
+raw_atomic_dec_and_test(atomic_t *v)
 {
-	return arch_atomic_dec_return(v) == 0;
-}
-#define arch_atomic_dec_and_test arch_atomic_dec_and_test
+#if defined(arch_atomic_dec_and_test)
+	return arch_atomic_dec_and_test(v);
+#else
+	return raw_atomic_dec_return(v) == 0;
 #endif
+}
 
-#ifndef arch_atomic_inc_and_test
 /**
- * arch_atomic_inc_and_test - increment and test
- * @v: pointer of type atomic_t
+ * raw_atomic_inc_and_test() - atomic increment and test if zero with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
  *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
+ * Safe to use in noinstr code; prefer atomic_inc_and_test() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_inc_and_test(atomic_t *v)
+raw_atomic_inc_and_test(atomic_t *v)
 {
-	return arch_atomic_inc_return(v) == 0;
-}
-#define arch_atomic_inc_and_test arch_atomic_inc_and_test
+#if defined(arch_atomic_inc_and_test)
+	return arch_atomic_inc_and_test(v);
+#else
+	return raw_atomic_inc_return(v) == 0;
 #endif
+}
 
-#ifndef arch_atomic_add_negative_relaxed
-#ifdef arch_atomic_add_negative
-#define arch_atomic_add_negative_acquire arch_atomic_add_negative
-#define arch_atomic_add_negative_release arch_atomic_add_negative
-#define arch_atomic_add_negative_relaxed arch_atomic_add_negative
-#endif /* arch_atomic_add_negative */
-
-#ifndef arch_atomic_add_negative
 /**
- * arch_atomic_add_negative - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
+ * raw_atomic_add_negative() - atomic add and test if negative with full ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_negative() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_add_negative(int i, atomic_t *v)
+raw_atomic_add_negative(int i, atomic_t *v)
 {
-	return arch_atomic_add_return(i, v) < 0;
-}
-#define arch_atomic_add_negative arch_atomic_add_negative
+#if defined(arch_atomic_add_negative)
+	return arch_atomic_add_negative(i, v);
+#elif defined(arch_atomic_add_negative_relaxed)
+	bool ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic_add_negative_relaxed(i, v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic_add_return(i, v) < 0;
 #endif
+}
 
-#ifndef arch_atomic_add_negative_acquire
 /**
- * arch_atomic_add_negative_acquire - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
+ * raw_atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Safe to use in noinstr code; prefer atomic_add_negative_acquire() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_add_negative_acquire(int i, atomic_t *v)
+raw_atomic_add_negative_acquire(int i, atomic_t *v)
 {
-	return arch_atomic_add_return_acquire(i, v) < 0;
-}
-#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire
+#if defined(arch_atomic_add_negative_acquire)
+	return arch_atomic_add_negative_acquire(i, v);
+#elif defined(arch_atomic_add_negative_relaxed)
+	bool ret = arch_atomic_add_negative_relaxed(i, v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic_add_negative)
+	return arch_atomic_add_negative(i, v);
+#else
+	return raw_atomic_add_return_acquire(i, v) < 0;
 #endif
+}
 
-#ifndef arch_atomic_add_negative_release
 /**
- * arch_atomic_add_negative_release - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
+ * raw_atomic_add_negative_release() - atomic add and test if negative with release ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_negative_release() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_add_negative_release(int i, atomic_t *v)
+raw_atomic_add_negative_release(int i, atomic_t *v)
 {
-	return arch_atomic_add_return_release(i, v) < 0;
-}
-#define arch_atomic_add_negative_release arch_atomic_add_negative_release
+#if defined(arch_atomic_add_negative_release)
+	return arch_atomic_add_negative_release(i, v);
+#elif defined(arch_atomic_add_negative_relaxed)
+	__atomic_release_fence();
+	return arch_atomic_add_negative_relaxed(i, v);
+#elif defined(arch_atomic_add_negative)
+	return arch_atomic_add_negative(i, v);
+#else
+	return raw_atomic_add_return_release(i, v) < 0;
 #endif
+}
 
-#ifndef arch_atomic_add_negative_relaxed
 /**
- * arch_atomic_add_negative_relaxed - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic_t
+ * raw_atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Safe to use in noinstr code; prefer atomic_add_negative_relaxed() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_add_negative_relaxed(int i, atomic_t *v)
-{
-	return arch_atomic_add_return_relaxed(i, v) < 0;
-}
-#define arch_atomic_add_negative_relaxed arch_atomic_add_negative_relaxed
-#endif
-
-#else /* arch_atomic_add_negative_relaxed */
-
-#ifndef arch_atomic_add_negative_acquire
-static __always_inline bool
-arch_atomic_add_negative_acquire(int i, atomic_t *v)
+raw_atomic_add_negative_relaxed(int i, atomic_t *v)
 {
-	bool ret = arch_atomic_add_negative_relaxed(i, v);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic_add_negative_acquire arch_atomic_add_negative_acquire
-#endif
-
-#ifndef arch_atomic_add_negative_release
-static __always_inline bool
-arch_atomic_add_negative_release(int i, atomic_t *v)
-{
-	__atomic_release_fence();
+#if defined(arch_atomic_add_negative_relaxed)
 	return arch_atomic_add_negative_relaxed(i, v);
-}
-#define arch_atomic_add_negative_release arch_atomic_add_negative_release
+#elif defined(arch_atomic_add_negative)
+	return arch_atomic_add_negative(i, v);
+#else
+	return raw_atomic_add_return_relaxed(i, v) < 0;
 #endif
-
-#ifndef arch_atomic_add_negative
-static __always_inline bool
-arch_atomic_add_negative(int i, atomic_t *v)
-{
-	bool ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic_add_negative_relaxed(i, v);
-	__atomic_post_full_fence();
-	return ret;
 }
-#define arch_atomic_add_negative arch_atomic_add_negative
-#endif
-
-#endif /* arch_atomic_add_negative_relaxed */
 
-#ifndef arch_atomic_fetch_add_unless
 /**
- * arch_atomic_fetch_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
+ * raw_atomic_fetch_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_t
+ * @a: int value to add
+ * @u: int value to compare with
  *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns original value of @v
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_fetch_add_unless() elsewhere.
+ *
+ * Return: The original value of @v.
  */
 static __always_inline int
-arch_atomic_fetch_add_unless(atomic_t *v, int a, int u)
+raw_atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
-	int c = arch_atomic_read(v);
+#if defined(arch_atomic_fetch_add_unless)
+	return arch_atomic_fetch_add_unless(v, a, u);
+#else
+	int c = raw_atomic_read(v);
 
 	do {
 		if (unlikely(c == u))
 			break;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c + a));
+	} while (!raw_atomic_try_cmpxchg(v, &c, c + a));
 
 	return c;
-}
-#define arch_atomic_fetch_add_unless arch_atomic_fetch_add_unless
 #endif
+}
 
-#ifndef arch_atomic_add_unless
 /**
- * arch_atomic_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
+ * raw_atomic_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_t
+ * @a: int value to add
+ * @u: int value to compare with
  *
- * Atomically adds @a to @v, if @v was not already @u.
- * Returns true if the addition was done.
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_add_unless() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_add_unless(atomic_t *v, int a, int u)
+raw_atomic_add_unless(atomic_t *v, int a, int u)
 {
-	return arch_atomic_fetch_add_unless(v, a, u) != u;
-}
-#define arch_atomic_add_unless arch_atomic_add_unless
+#if defined(arch_atomic_add_unless)
+	return arch_atomic_add_unless(v, a, u);
+#else
+	return raw_atomic_fetch_add_unless(v, a, u) != u;
 #endif
+}
 
-#ifndef arch_atomic_inc_not_zero
 /**
- * arch_atomic_inc_not_zero - increment unless the number is zero
- * @v: pointer of type atomic_t
+ * raw_atomic_inc_not_zero() - atomic increment unless zero with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
  *
- * Atomically increments @v by 1, if @v is non-zero.
- * Returns true if the increment was done.
+ * Safe to use in noinstr code; prefer atomic_inc_not_zero() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
  */
 static __always_inline bool
-arch_atomic_inc_not_zero(atomic_t *v)
+raw_atomic_inc_not_zero(atomic_t *v)
 {
-	return arch_atomic_add_unless(v, 1, 0);
-}
-#define arch_atomic_inc_not_zero arch_atomic_inc_not_zero
+#if defined(arch_atomic_inc_not_zero)
+	return arch_atomic_inc_not_zero(v);
+#else
+	return raw_atomic_add_unless(v, 1, 0);
 #endif
+}
 
-#ifndef arch_atomic_inc_unless_negative
+/**
+ * raw_atomic_inc_unless_negative() - atomic increment unless negative with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_inc_unless_negative() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_inc_unless_negative(atomic_t *v)
+raw_atomic_inc_unless_negative(atomic_t *v)
 {
-	int c = arch_atomic_read(v);
+#if defined(arch_atomic_inc_unless_negative)
+	return arch_atomic_inc_unless_negative(v);
+#else
+	int c = raw_atomic_read(v);
 
 	do {
 		if (unlikely(c < 0))
 			return false;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c + 1));
+	} while (!raw_atomic_try_cmpxchg(v, &c, c + 1));
 
 	return true;
-}
-#define arch_atomic_inc_unless_negative arch_atomic_inc_unless_negative
 #endif
+}
 
-#ifndef arch_atomic_dec_unless_positive
+/**
+ * raw_atomic_dec_unless_positive() - atomic decrement unless positive with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_unless_positive() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_dec_unless_positive(atomic_t *v)
+raw_atomic_dec_unless_positive(atomic_t *v)
 {
-	int c = arch_atomic_read(v);
+#if defined(arch_atomic_dec_unless_positive)
+	return arch_atomic_dec_unless_positive(v);
+#else
+	int c = raw_atomic_read(v);
 
 	do {
 		if (unlikely(c > 0))
 			return false;
-	} while (!arch_atomic_try_cmpxchg(v, &c, c - 1));
+	} while (!raw_atomic_try_cmpxchg(v, &c, c - 1));
 
 	return true;
-}
-#define arch_atomic_dec_unless_positive arch_atomic_dec_unless_positive
 #endif
+}
 
-#ifndef arch_atomic_dec_if_positive
+/**
+ * raw_atomic_dec_if_positive() - atomic decrement if positive with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_dec_if_positive() elsewhere.
+ *
+ * Return: The old value of (@v - 1), regardless of whether @v was updated.
+ */
 static __always_inline int
-arch_atomic_dec_if_positive(atomic_t *v)
+raw_atomic_dec_if_positive(atomic_t *v)
 {
-	int dec, c = arch_atomic_read(v);
+#if defined(arch_atomic_dec_if_positive)
+	return arch_atomic_dec_if_positive(v);
+#else
+	int dec, c = raw_atomic_read(v);
 
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-	} while (!arch_atomic_try_cmpxchg(v, &c, dec));
+	} while (!raw_atomic_try_cmpxchg(v, &c, dec));
 
 	return dec;
-}
-#define arch_atomic_dec_if_positive arch_atomic_dec_if_positive
 #endif
+}
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #include <asm-generic/atomic64.h>
 #endif
 
-#ifndef arch_atomic64_read_acquire
+/**
+ * raw_atomic64_read() - atomic load with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically loads the value of @v with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_read() elsewhere.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline s64
-arch_atomic64_read_acquire(const atomic64_t *v)
+raw_atomic64_read(const atomic64_t *v)
 {
+	return arch_atomic64_read(v);
+}
+
+/**
+ * raw_atomic64_read_acquire() - atomic load with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically loads the value of @v with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_read_acquire() elsewhere.
+ *
+ * Return: The value loaded from @v.
+ */
+static __always_inline s64
+raw_atomic64_read_acquire(const atomic64_t *v)
+{
+#if defined(arch_atomic64_read_acquire)
+	return arch_atomic64_read_acquire(v);
+#else
 	s64 ret;
 
 	if (__native_word(atomic64_t)) {
 		ret = smp_load_acquire(&(v)->counter);
 	} else {
-		ret = arch_atomic64_read(v);
+		ret = raw_atomic64_read(v);
 		__atomic_acquire_fence();
 	}
 
 	return ret;
-}
-#define arch_atomic64_read_acquire arch_atomic64_read_acquire
 #endif
+}
 
-#ifndef arch_atomic64_set_release
+/**
+ * raw_atomic64_set() - atomic set with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @i: s64 value to assign
+ *
+ * Atomically sets @v to @i with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_set() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic64_set_release(atomic64_t *v, s64 i)
+raw_atomic64_set(atomic64_t *v, s64 i)
 {
+	arch_atomic64_set(v, i);
+}
+
+/**
+ * raw_atomic64_set_release() - atomic set with release ordering
+ * @v: pointer to atomic64_t
+ * @i: s64 value to assign
+ *
+ * Atomically sets @v to @i with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_set_release() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_set_release(atomic64_t *v, s64 i)
+{
+#if defined(arch_atomic64_set_release)
+	arch_atomic64_set_release(v, i);
+#else
 	if (__native_word(atomic64_t)) {
 		smp_store_release(&(v)->counter, i);
 	} else {
 		__atomic_release_fence();
-		arch_atomic64_set(v, i);
+		raw_atomic64_set(v, i);
 	}
-}
-#define arch_atomic64_set_release arch_atomic64_set_release
 #endif
-
-#ifndef arch_atomic64_add_return_relaxed
-#define arch_atomic64_add_return_acquire arch_atomic64_add_return
-#define arch_atomic64_add_return_release arch_atomic64_add_return
-#define arch_atomic64_add_return_relaxed arch_atomic64_add_return
-#else /* arch_atomic64_add_return_relaxed */
-
-#ifndef arch_atomic64_add_return_acquire
-static __always_inline s64
-arch_atomic64_add_return_acquire(s64 i, atomic64_t *v)
-{
-	s64 ret = arch_atomic64_add_return_relaxed(i, v);
-	__atomic_acquire_fence();
-	return ret;
 }
-#define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire
-#endif
 
-#ifndef arch_atomic64_add_return_release
-static __always_inline s64
-arch_atomic64_add_return_release(s64 i, atomic64_t *v)
+/**
+ * raw_atomic64_add() - atomic add with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_add(s64 i, atomic64_t *v)
 {
-	__atomic_release_fence();
-	return arch_atomic64_add_return_relaxed(i, v);
+	arch_atomic64_add(i, v);
 }
-#define arch_atomic64_add_return_release arch_atomic64_add_return_release
-#endif
 
-#ifndef arch_atomic64_add_return
+/**
+ * raw_atomic64_add_return() - atomic add with full ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_add_return(s64 i, atomic64_t *v)
+raw_atomic64_add_return(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_add_return)
+	return arch_atomic64_add_return(i, v);
+#elif defined(arch_atomic64_add_return_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic64_add_return_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_add_return arch_atomic64_add_return
+#else
+#error "Unable to define raw_atomic64_add_return"
 #endif
+}
 
-#endif /* arch_atomic64_add_return_relaxed */
-
-#ifndef arch_atomic64_fetch_add_relaxed
-#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add
-#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add
-#define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add
-#else /* arch_atomic64_fetch_add_relaxed */
-
-#ifndef arch_atomic64_fetch_add_acquire
+/**
+ * raw_atomic64_add_return_acquire() - atomic add with acquire ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
+raw_atomic64_add_return_acquire(s64 i, atomic64_t *v)
 {
-	s64 ret = arch_atomic64_fetch_add_relaxed(i, v);
+#if defined(arch_atomic64_add_return_acquire)
+	return arch_atomic64_add_return_acquire(i, v);
+#elif defined(arch_atomic64_add_return_relaxed)
+	s64 ret = arch_atomic64_add_return_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire
+#elif defined(arch_atomic64_add_return)
+	return arch_atomic64_add_return(i, v);
+#else
+#error "Unable to define raw_atomic64_add_return_acquire"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_add_release
+/**
+ * raw_atomic64_add_return_release() - atomic add with release ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_add_release(s64 i, atomic64_t *v)
+raw_atomic64_add_return_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_add_return_release)
+	return arch_atomic64_add_return_release(i, v);
+#elif defined(arch_atomic64_add_return_relaxed)
 	__atomic_release_fence();
-	return arch_atomic64_fetch_add_relaxed(i, v);
+	return arch_atomic64_add_return_relaxed(i, v);
+#elif defined(arch_atomic64_add_return)
+	return arch_atomic64_add_return(i, v);
+#else
+#error "Unable to define raw_atomic64_add_return_release"
+#endif
 }
-#define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release
+
+/**
+ * raw_atomic64_add_return_relaxed() - atomic add with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
+static __always_inline s64
+raw_atomic64_add_return_relaxed(s64 i, atomic64_t *v)
+{
+#if defined(arch_atomic64_add_return_relaxed)
+	return arch_atomic64_add_return_relaxed(i, v);
+#elif defined(arch_atomic64_add_return)
+	return arch_atomic64_add_return(i, v);
+#else
+#error "Unable to define raw_atomic64_add_return_relaxed"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_add
+/**
+ * raw_atomic64_fetch_add() - atomic add with full ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_add() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_add(s64 i, atomic64_t *v)
+raw_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_add)
+	return arch_atomic64_fetch_add(i, v);
+#elif defined(arch_atomic64_fetch_add_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic64_fetch_add_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_add arch_atomic64_fetch_add
+#else
+#error "Unable to define raw_atomic64_fetch_add"
 #endif
+}
 
-#endif /* arch_atomic64_fetch_add_relaxed */
-
-#ifndef arch_atomic64_sub_return_relaxed
-#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return
-#define arch_atomic64_sub_return_release arch_atomic64_sub_return
-#define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return
-#else /* arch_atomic64_sub_return_relaxed */
-
-#ifndef arch_atomic64_sub_return_acquire
+/**
+ * raw_atomic64_fetch_add_acquire() - atomic add with acquire ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_add_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_sub_return_acquire(s64 i, atomic64_t *v)
+raw_atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
 {
-	s64 ret = arch_atomic64_sub_return_relaxed(i, v);
+#if defined(arch_atomic64_fetch_add_acquire)
+	return arch_atomic64_fetch_add_acquire(i, v);
+#elif defined(arch_atomic64_fetch_add_relaxed)
+	s64 ret = arch_atomic64_fetch_add_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire
+#elif defined(arch_atomic64_fetch_add)
+	return arch_atomic64_fetch_add(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_add_acquire"
 #endif
+}
 
-#ifndef arch_atomic64_sub_return_release
+/**
+ * raw_atomic64_fetch_add_release() - atomic add with release ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_add_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_sub_return_release(s64 i, atomic64_t *v)
+raw_atomic64_fetch_add_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_add_release)
+	return arch_atomic64_fetch_add_release(i, v);
+#elif defined(arch_atomic64_fetch_add_relaxed)
 	__atomic_release_fence();
-	return arch_atomic64_sub_return_relaxed(i, v);
+	return arch_atomic64_fetch_add_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_add)
+	return arch_atomic64_fetch_add(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_add_release"
+#endif
 }
-#define arch_atomic64_sub_return_release arch_atomic64_sub_return_release
+
+/**
+ * raw_atomic64_fetch_add_relaxed() - atomic add with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_add_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline s64
+raw_atomic64_fetch_add_relaxed(s64 i, atomic64_t *v)
+{
+#if defined(arch_atomic64_fetch_add_relaxed)
+	return arch_atomic64_fetch_add_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_add)
+	return arch_atomic64_fetch_add(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_add_relaxed"
 #endif
+}
+
+/**
+ * raw_atomic64_sub() - atomic subtract with relaxed ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_sub() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_sub(s64 i, atomic64_t *v)
+{
+	arch_atomic64_sub(i, v);
+}
 
-#ifndef arch_atomic64_sub_return
+/**
+ * raw_atomic64_sub_return() - atomic subtract with full ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_sub_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_sub_return(s64 i, atomic64_t *v)
+raw_atomic64_sub_return(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_sub_return)
+	return arch_atomic64_sub_return(i, v);
+#elif defined(arch_atomic64_sub_return_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic64_sub_return_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_sub_return arch_atomic64_sub_return
+#else
+#error "Unable to define raw_atomic64_sub_return"
 #endif
+}
 
-#endif /* arch_atomic64_sub_return_relaxed */
-
-#ifndef arch_atomic64_fetch_sub_relaxed
-#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub
-#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub
-#define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub
-#else /* arch_atomic64_fetch_sub_relaxed */
-
-#ifndef arch_atomic64_fetch_sub_acquire
+/**
+ * raw_atomic64_sub_return_acquire() - atomic subtract with acquire ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_sub_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
+raw_atomic64_sub_return_acquire(s64 i, atomic64_t *v)
 {
-	s64 ret = arch_atomic64_fetch_sub_relaxed(i, v);
+#if defined(arch_atomic64_sub_return_acquire)
+	return arch_atomic64_sub_return_acquire(i, v);
+#elif defined(arch_atomic64_sub_return_relaxed)
+	s64 ret = arch_atomic64_sub_return_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire
+#elif defined(arch_atomic64_sub_return)
+	return arch_atomic64_sub_return(i, v);
+#else
+#error "Unable to define raw_atomic64_sub_return_acquire"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_sub_release
+/**
+ * raw_atomic64_sub_return_release() - atomic subtract with release ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_sub_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_sub_release(s64 i, atomic64_t *v)
+raw_atomic64_sub_return_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_sub_return_release)
+	return arch_atomic64_sub_return_release(i, v);
+#elif defined(arch_atomic64_sub_return_relaxed)
 	__atomic_release_fence();
-	return arch_atomic64_fetch_sub_relaxed(i, v);
+	return arch_atomic64_sub_return_relaxed(i, v);
+#elif defined(arch_atomic64_sub_return)
+	return arch_atomic64_sub_return(i, v);
+#else
+#error "Unable to define raw_atomic64_sub_return_release"
+#endif
 }
-#define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release
+
+/**
+ * raw_atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_sub_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
+static __always_inline s64
+raw_atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
+{
+#if defined(arch_atomic64_sub_return_relaxed)
+	return arch_atomic64_sub_return_relaxed(i, v);
+#elif defined(arch_atomic64_sub_return)
+	return arch_atomic64_sub_return(i, v);
+#else
+#error "Unable to define raw_atomic64_sub_return_relaxed"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_sub
+/**
+ * raw_atomic64_fetch_sub() - atomic subtract with full ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_sub() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
+raw_atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_sub)
+	return arch_atomic64_fetch_sub(i, v);
+#elif defined(arch_atomic64_fetch_sub_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic64_fetch_sub_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_sub arch_atomic64_fetch_sub
+#else
+#error "Unable to define raw_atomic64_fetch_sub"
 #endif
-
-#endif /* arch_atomic64_fetch_sub_relaxed */
-
-#ifndef arch_atomic64_inc
-static __always_inline void
-arch_atomic64_inc(atomic64_t *v)
-{
-	arch_atomic64_add(1, v);
 }
-#define arch_atomic64_inc arch_atomic64_inc
-#endif
 
-#ifndef arch_atomic64_inc_return_relaxed
-#ifdef arch_atomic64_inc_return
-#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return
-#define arch_atomic64_inc_return_release arch_atomic64_inc_return
-#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return
-#endif /* arch_atomic64_inc_return */
-
-#ifndef arch_atomic64_inc_return
+/**
+ * raw_atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_sub_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_inc_return(atomic64_t *v)
+raw_atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_add_return(1, v);
-}
-#define arch_atomic64_inc_return arch_atomic64_inc_return
+#if defined(arch_atomic64_fetch_sub_acquire)
+	return arch_atomic64_fetch_sub_acquire(i, v);
+#elif defined(arch_atomic64_fetch_sub_relaxed)
+	s64 ret = arch_atomic64_fetch_sub_relaxed(i, v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic64_fetch_sub)
+	return arch_atomic64_fetch_sub(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_sub_acquire"
 #endif
-
-#ifndef arch_atomic64_inc_return_acquire
-static __always_inline s64
-arch_atomic64_inc_return_acquire(atomic64_t *v)
-{
-	return arch_atomic64_add_return_acquire(1, v);
 }
-#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire
-#endif
 
-#ifndef arch_atomic64_inc_return_release
+/**
+ * raw_atomic64_fetch_sub_release() - atomic subtract with release ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_sub_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_inc_return_release(atomic64_t *v)
+raw_atomic64_fetch_sub_release(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_add_return_release(1, v);
-}
-#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release
+#if defined(arch_atomic64_fetch_sub_release)
+	return arch_atomic64_fetch_sub_release(i, v);
+#elif defined(arch_atomic64_fetch_sub_relaxed)
+	__atomic_release_fence();
+	return arch_atomic64_fetch_sub_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_sub)
+	return arch_atomic64_fetch_sub(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_sub_release"
 #endif
-
-#ifndef arch_atomic64_inc_return_relaxed
-static __always_inline s64
-arch_atomic64_inc_return_relaxed(atomic64_t *v)
-{
-	return arch_atomic64_add_return_relaxed(1, v);
 }
-#define arch_atomic64_inc_return_relaxed arch_atomic64_inc_return_relaxed
-#endif
-
-#else /* arch_atomic64_inc_return_relaxed */
 
-#ifndef arch_atomic64_inc_return_acquire
+/**
+ * raw_atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_sub_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_inc_return_acquire(atomic64_t *v)
+raw_atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v)
 {
-	s64 ret = arch_atomic64_inc_return_relaxed(v);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic64_inc_return_acquire arch_atomic64_inc_return_acquire
+#if defined(arch_atomic64_fetch_sub_relaxed)
+	return arch_atomic64_fetch_sub_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_sub)
+	return arch_atomic64_fetch_sub(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_sub_relaxed"
 #endif
+}
 
-#ifndef arch_atomic64_inc_return_release
-static __always_inline s64
-arch_atomic64_inc_return_release(atomic64_t *v)
+/**
+ * raw_atomic64_inc() - atomic increment with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_inc(atomic64_t *v)
 {
-	__atomic_release_fence();
-	return arch_atomic64_inc_return_relaxed(v);
-}
-#define arch_atomic64_inc_return_release arch_atomic64_inc_return_release
+#if defined(arch_atomic64_inc)
+	arch_atomic64_inc(v);
+#else
+	raw_atomic64_add(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_inc_return
+/**
+ * raw_atomic64_inc_return() - atomic increment with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_inc_return(atomic64_t *v)
+raw_atomic64_inc_return(atomic64_t *v)
 {
+#if defined(arch_atomic64_inc_return)
+	return arch_atomic64_inc_return(v);
+#elif defined(arch_atomic64_inc_return_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
 	ret = arch_atomic64_inc_return_relaxed(v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_inc_return arch_atomic64_inc_return
+#else
+	return raw_atomic64_add_return(1, v);
 #endif
+}
 
-#endif /* arch_atomic64_inc_return_relaxed */
-
-#ifndef arch_atomic64_fetch_inc_relaxed
-#ifdef arch_atomic64_fetch_inc
-#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc
-#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc
-#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc
-#endif /* arch_atomic64_fetch_inc */
-
-#ifndef arch_atomic64_fetch_inc
+/**
+ * raw_atomic64_inc_return_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc(atomic64_t *v)
+raw_atomic64_inc_return_acquire(atomic64_t *v)
 {
-	return arch_atomic64_fetch_add(1, v);
-}
-#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc
+#if defined(arch_atomic64_inc_return_acquire)
+	return arch_atomic64_inc_return_acquire(v);
+#elif defined(arch_atomic64_inc_return_relaxed)
+	s64 ret = arch_atomic64_inc_return_relaxed(v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic64_inc_return)
+	return arch_atomic64_inc_return(v);
+#else
+	return raw_atomic64_add_return_acquire(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_inc_acquire
+/**
+ * raw_atomic64_inc_return_release() - atomic increment with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc_acquire(atomic64_t *v)
+raw_atomic64_inc_return_release(atomic64_t *v)
 {
-	return arch_atomic64_fetch_add_acquire(1, v);
-}
-#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire
+#if defined(arch_atomic64_inc_return_release)
+	return arch_atomic64_inc_return_release(v);
+#elif defined(arch_atomic64_inc_return_relaxed)
+	__atomic_release_fence();
+	return arch_atomic64_inc_return_relaxed(v);
+#elif defined(arch_atomic64_inc_return)
+	return arch_atomic64_inc_return(v);
+#else
+	return raw_atomic64_add_return_release(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_inc_release
+/**
+ * raw_atomic64_inc_return_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc_release(atomic64_t *v)
+raw_atomic64_inc_return_relaxed(atomic64_t *v)
 {
-	return arch_atomic64_fetch_add_release(1, v);
-}
-#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release
+#if defined(arch_atomic64_inc_return_relaxed)
+	return arch_atomic64_inc_return_relaxed(v);
+#elif defined(arch_atomic64_inc_return)
+	return arch_atomic64_inc_return(v);
+#else
+	return raw_atomic64_add_return_relaxed(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_inc_relaxed
+/**
+ * raw_atomic64_fetch_inc() - atomic increment with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_inc() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc_relaxed(atomic64_t *v)
+raw_atomic64_fetch_inc(atomic64_t *v)
 {
-	return arch_atomic64_fetch_add_relaxed(1, v);
-}
-#define arch_atomic64_fetch_inc_relaxed arch_atomic64_fetch_inc_relaxed
+#if defined(arch_atomic64_fetch_inc)
+	return arch_atomic64_fetch_inc(v);
+#elif defined(arch_atomic64_fetch_inc_relaxed)
+	s64 ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic64_fetch_inc_relaxed(v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic64_fetch_add(1, v);
 #endif
+}
 
-#else /* arch_atomic64_fetch_inc_relaxed */
-
-#ifndef arch_atomic64_fetch_inc_acquire
+/**
+ * raw_atomic64_fetch_inc_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_inc_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc_acquire(atomic64_t *v)
+raw_atomic64_fetch_inc_acquire(atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_inc_acquire)
+	return arch_atomic64_fetch_inc_acquire(v);
+#elif defined(arch_atomic64_fetch_inc_relaxed)
 	s64 ret = arch_atomic64_fetch_inc_relaxed(v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_inc_acquire arch_atomic64_fetch_inc_acquire
+#elif defined(arch_atomic64_fetch_inc)
+	return arch_atomic64_fetch_inc(v);
+#else
+	return raw_atomic64_fetch_add_acquire(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_inc_release
+/**
+ * raw_atomic64_fetch_inc_release() - atomic increment with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_inc_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc_release(atomic64_t *v)
+raw_atomic64_fetch_inc_release(atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_inc_release)
+	return arch_atomic64_fetch_inc_release(v);
+#elif defined(arch_atomic64_fetch_inc_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_fetch_inc_relaxed(v);
-}
-#define arch_atomic64_fetch_inc_release arch_atomic64_fetch_inc_release
+#elif defined(arch_atomic64_fetch_inc)
+	return arch_atomic64_fetch_inc(v);
+#else
+	return raw_atomic64_fetch_add_release(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_inc
+/**
+ * raw_atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_inc_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_inc(atomic64_t *v)
+raw_atomic64_fetch_inc_relaxed(atomic64_t *v)
 {
-	s64 ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic64_fetch_inc_relaxed(v);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic64_fetch_inc arch_atomic64_fetch_inc
+#if defined(arch_atomic64_fetch_inc_relaxed)
+	return arch_atomic64_fetch_inc_relaxed(v);
+#elif defined(arch_atomic64_fetch_inc)
+	return arch_atomic64_fetch_inc(v);
+#else
+	return raw_atomic64_fetch_add_relaxed(1, v);
 #endif
-
-#endif /* arch_atomic64_fetch_inc_relaxed */
-
-#ifndef arch_atomic64_dec
-static __always_inline void
-arch_atomic64_dec(atomic64_t *v)
-{
-	arch_atomic64_sub(1, v);
 }
-#define arch_atomic64_dec arch_atomic64_dec
-#endif
-
-#ifndef arch_atomic64_dec_return_relaxed
-#ifdef arch_atomic64_dec_return
-#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return
-#define arch_atomic64_dec_return_release arch_atomic64_dec_return
-#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return
-#endif /* arch_atomic64_dec_return */
 
-#ifndef arch_atomic64_dec_return
-static __always_inline s64
-arch_atomic64_dec_return(atomic64_t *v)
+/**
+ * raw_atomic64_dec() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_dec(atomic64_t *v)
 {
-	return arch_atomic64_sub_return(1, v);
-}
-#define arch_atomic64_dec_return arch_atomic64_dec_return
+#if defined(arch_atomic64_dec)
+	arch_atomic64_dec(v);
+#else
+	raw_atomic64_sub(1, v);
 #endif
-
-#ifndef arch_atomic64_dec_return_acquire
-static __always_inline s64
-arch_atomic64_dec_return_acquire(atomic64_t *v)
-{
-	return arch_atomic64_sub_return_acquire(1, v);
 }
-#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire
-#endif
 
-#ifndef arch_atomic64_dec_return_release
+/**
+ * raw_atomic64_dec_return() - atomic decrement with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_dec_return_release(atomic64_t *v)
+raw_atomic64_dec_return(atomic64_t *v)
 {
-	return arch_atomic64_sub_return_release(1, v);
-}
-#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release
+#if defined(arch_atomic64_dec_return)
+	return arch_atomic64_dec_return(v);
+#elif defined(arch_atomic64_dec_return_relaxed)
+	s64 ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic64_dec_return_relaxed(v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic64_sub_return(1, v);
 #endif
-
-#ifndef arch_atomic64_dec_return_relaxed
-static __always_inline s64
-arch_atomic64_dec_return_relaxed(atomic64_t *v)
-{
-	return arch_atomic64_sub_return_relaxed(1, v);
 }
-#define arch_atomic64_dec_return_relaxed arch_atomic64_dec_return_relaxed
-#endif
 
-#else /* arch_atomic64_dec_return_relaxed */
-
-#ifndef arch_atomic64_dec_return_acquire
+/**
+ * raw_atomic64_dec_return_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_dec_return_acquire(atomic64_t *v)
+raw_atomic64_dec_return_acquire(atomic64_t *v)
 {
+#if defined(arch_atomic64_dec_return_acquire)
+	return arch_atomic64_dec_return_acquire(v);
+#elif defined(arch_atomic64_dec_return_relaxed)
 	s64 ret = arch_atomic64_dec_return_relaxed(v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_dec_return_acquire arch_atomic64_dec_return_acquire
+#elif defined(arch_atomic64_dec_return)
+	return arch_atomic64_dec_return(v);
+#else
+	return raw_atomic64_sub_return_acquire(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_dec_return_release
+/**
+ * raw_atomic64_dec_return_release() - atomic decrement with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
-arch_atomic64_dec_return_release(atomic64_t *v)
+raw_atomic64_dec_return_release(atomic64_t *v)
 {
+#if defined(arch_atomic64_dec_return_release)
+	return arch_atomic64_dec_return_release(v);
+#elif defined(arch_atomic64_dec_return_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_dec_return_relaxed(v);
+#elif defined(arch_atomic64_dec_return)
+	return arch_atomic64_dec_return(v);
+#else
+	return raw_atomic64_sub_return_release(1, v);
+#endif
 }
-#define arch_atomic64_dec_return_release arch_atomic64_dec_return_release
+
+/**
+ * raw_atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
+static __always_inline s64
+raw_atomic64_dec_return_relaxed(atomic64_t *v)
+{
+#if defined(arch_atomic64_dec_return_relaxed)
+	return arch_atomic64_dec_return_relaxed(v);
+#elif defined(arch_atomic64_dec_return)
+	return arch_atomic64_dec_return(v);
+#else
+	return raw_atomic64_sub_return_relaxed(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_dec_return
+/**
+ * raw_atomic64_fetch_dec() - atomic decrement with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_dec() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_dec_return(atomic64_t *v)
+raw_atomic64_fetch_dec(atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_dec)
+	return arch_atomic64_fetch_dec(v);
+#elif defined(arch_atomic64_fetch_dec_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic64_dec_return_relaxed(v);
+	ret = arch_atomic64_fetch_dec_relaxed(v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_dec_return arch_atomic64_dec_return
+#else
+	return raw_atomic64_fetch_sub(1, v);
 #endif
-
-#endif /* arch_atomic64_dec_return_relaxed */
-
-#ifndef arch_atomic64_fetch_dec_relaxed
-#ifdef arch_atomic64_fetch_dec
-#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec
-#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec
-#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec
-#endif /* arch_atomic64_fetch_dec */
-
-#ifndef arch_atomic64_fetch_dec
-static __always_inline s64
-arch_atomic64_fetch_dec(atomic64_t *v)
-{
-	return arch_atomic64_fetch_sub(1, v);
 }
-#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec
-#endif
 
-#ifndef arch_atomic64_fetch_dec_acquire
+/**
+ * raw_atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_dec_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_dec_acquire(atomic64_t *v)
+raw_atomic64_fetch_dec_acquire(atomic64_t *v)
 {
-	return arch_atomic64_fetch_sub_acquire(1, v);
-}
-#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire
+#if defined(arch_atomic64_fetch_dec_acquire)
+	return arch_atomic64_fetch_dec_acquire(v);
+#elif defined(arch_atomic64_fetch_dec_relaxed)
+	s64 ret = arch_atomic64_fetch_dec_relaxed(v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic64_fetch_dec)
+	return arch_atomic64_fetch_dec(v);
+#else
+	return raw_atomic64_fetch_sub_acquire(1, v);
 #endif
-
-#ifndef arch_atomic64_fetch_dec_release
-static __always_inline s64
-arch_atomic64_fetch_dec_release(atomic64_t *v)
-{
-	return arch_atomic64_fetch_sub_release(1, v);
 }
-#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release
-#endif
 
-#ifndef arch_atomic64_fetch_dec_relaxed
+/**
+ * raw_atomic64_fetch_dec_release() - atomic decrement with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_dec_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_dec_relaxed(atomic64_t *v)
+raw_atomic64_fetch_dec_release(atomic64_t *v)
 {
-	return arch_atomic64_fetch_sub_relaxed(1, v);
-}
-#define arch_atomic64_fetch_dec_relaxed arch_atomic64_fetch_dec_relaxed
+#if defined(arch_atomic64_fetch_dec_release)
+	return arch_atomic64_fetch_dec_release(v);
+#elif defined(arch_atomic64_fetch_dec_relaxed)
+	__atomic_release_fence();
+	return arch_atomic64_fetch_dec_relaxed(v);
+#elif defined(arch_atomic64_fetch_dec)
+	return arch_atomic64_fetch_dec(v);
+#else
+	return raw_atomic64_fetch_sub_release(1, v);
 #endif
+}
 
-#else /* arch_atomic64_fetch_dec_relaxed */
-
-#ifndef arch_atomic64_fetch_dec_acquire
+/**
+ * raw_atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_dec_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_dec_acquire(atomic64_t *v)
+raw_atomic64_fetch_dec_relaxed(atomic64_t *v)
 {
-	s64 ret = arch_atomic64_fetch_dec_relaxed(v);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic64_fetch_dec_acquire arch_atomic64_fetch_dec_acquire
+#if defined(arch_atomic64_fetch_dec_relaxed)
+	return arch_atomic64_fetch_dec_relaxed(v);
+#elif defined(arch_atomic64_fetch_dec)
+	return arch_atomic64_fetch_dec(v);
+#else
+	return raw_atomic64_fetch_sub_relaxed(1, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_dec_release
-static __always_inline s64
-arch_atomic64_fetch_dec_release(atomic64_t *v)
+/**
+ * raw_atomic64_and() - atomic bitwise AND with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_and() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_and(s64 i, atomic64_t *v)
 {
-	__atomic_release_fence();
-	return arch_atomic64_fetch_dec_relaxed(v);
+	arch_atomic64_and(i, v);
 }
-#define arch_atomic64_fetch_dec_release arch_atomic64_fetch_dec_release
-#endif
 
-#ifndef arch_atomic64_fetch_dec
+/**
+ * raw_atomic64_fetch_and() - atomic bitwise AND with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_and() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_dec(atomic64_t *v)
+raw_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_and)
+	return arch_atomic64_fetch_and(i, v);
+#elif defined(arch_atomic64_fetch_and_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic64_fetch_dec_relaxed(v);
+	ret = arch_atomic64_fetch_and_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_dec arch_atomic64_fetch_dec
+#else
+#error "Unable to define raw_atomic64_fetch_and"
 #endif
+}
 
-#endif /* arch_atomic64_fetch_dec_relaxed */
-
-#ifndef arch_atomic64_fetch_and_relaxed
-#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and
-#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and
-#define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and
-#else /* arch_atomic64_fetch_and_relaxed */
-
-#ifndef arch_atomic64_fetch_and_acquire
+/**
+ * raw_atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_and_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
+raw_atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_and_acquire)
+	return arch_atomic64_fetch_and_acquire(i, v);
+#elif defined(arch_atomic64_fetch_and_relaxed)
 	s64 ret = arch_atomic64_fetch_and_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire
+#elif defined(arch_atomic64_fetch_and)
+	return arch_atomic64_fetch_and(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_and_acquire"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_and_release
+/**
+ * raw_atomic64_fetch_and_release() - atomic bitwise AND with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_and_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_and_release(s64 i, atomic64_t *v)
+raw_atomic64_fetch_and_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_and_release)
+	return arch_atomic64_fetch_and_release(i, v);
+#elif defined(arch_atomic64_fetch_and_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_fetch_and_relaxed(i, v);
-}
-#define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release
+#elif defined(arch_atomic64_fetch_and)
+	return arch_atomic64_fetch_and(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_and_release"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_and
+/**
+ * raw_atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_and_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_and(s64 i, atomic64_t *v)
+raw_atomic64_fetch_and_relaxed(s64 i, atomic64_t *v)
 {
-	s64 ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic64_fetch_and_relaxed(i, v);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic64_fetch_and arch_atomic64_fetch_and
+#if defined(arch_atomic64_fetch_and_relaxed)
+	return arch_atomic64_fetch_and_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_and)
+	return arch_atomic64_fetch_and(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_and_relaxed"
 #endif
-
-#endif /* arch_atomic64_fetch_and_relaxed */
-
-#ifndef arch_atomic64_andnot
-static __always_inline void
-arch_atomic64_andnot(s64 i, atomic64_t *v)
-{
-	arch_atomic64_and(~i, v);
 }
-#define arch_atomic64_andnot arch_atomic64_andnot
-#endif
 
-#ifndef arch_atomic64_fetch_andnot_relaxed
-#ifdef arch_atomic64_fetch_andnot
-#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot
-#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot
-#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot
-#endif /* arch_atomic64_fetch_andnot */
-
-#ifndef arch_atomic64_fetch_andnot
-static __always_inline s64
-arch_atomic64_fetch_andnot(s64 i, atomic64_t *v)
+/**
+ * raw_atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_andnot() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_andnot(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_fetch_and(~i, v);
-}
-#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot
+#if defined(arch_atomic64_andnot)
+	arch_atomic64_andnot(i, v);
+#else
+	raw_atomic64_and(~i, v);
 #endif
-
-#ifndef arch_atomic64_fetch_andnot_acquire
-static __always_inline s64
-arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
-{
-	return arch_atomic64_fetch_and_acquire(~i, v);
 }
-#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire
-#endif
 
-#ifndef arch_atomic64_fetch_andnot_release
+/**
+ * raw_atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_andnot() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
+raw_atomic64_fetch_andnot(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_fetch_and_release(~i, v);
-}
-#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release
+#if defined(arch_atomic64_fetch_andnot)
+	return arch_atomic64_fetch_andnot(i, v);
+#elif defined(arch_atomic64_fetch_andnot_relaxed)
+	s64 ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic64_fetch_andnot_relaxed(i, v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic64_fetch_and(~i, v);
 #endif
-
-#ifndef arch_atomic64_fetch_andnot_relaxed
-static __always_inline s64
-arch_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
-{
-	return arch_atomic64_fetch_and_relaxed(~i, v);
 }
-#define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed
-#endif
-
-#else /* arch_atomic64_fetch_andnot_relaxed */
 
-#ifndef arch_atomic64_fetch_andnot_acquire
+/**
+ * raw_atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_andnot_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
+raw_atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_andnot_acquire)
+	return arch_atomic64_fetch_andnot_acquire(i, v);
+#elif defined(arch_atomic64_fetch_andnot_relaxed)
 	s64 ret = arch_atomic64_fetch_andnot_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire
+#elif defined(arch_atomic64_fetch_andnot)
+	return arch_atomic64_fetch_andnot(i, v);
+#else
+	return raw_atomic64_fetch_and_acquire(~i, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_andnot_release
+/**
+ * raw_atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_andnot_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
+raw_atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_andnot_release)
+	return arch_atomic64_fetch_andnot_release(i, v);
+#elif defined(arch_atomic64_fetch_andnot_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_fetch_andnot_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_andnot)
+	return arch_atomic64_fetch_andnot(i, v);
+#else
+	return raw_atomic64_fetch_and_release(~i, v);
+#endif
 }
-#define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release
+
+/**
+ * raw_atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_andnot_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline s64
+raw_atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
+{
+#if defined(arch_atomic64_fetch_andnot_relaxed)
+	return arch_atomic64_fetch_andnot_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_andnot)
+	return arch_atomic64_fetch_andnot(i, v);
+#else
+	return raw_atomic64_fetch_and_relaxed(~i, v);
 #endif
+}
 
-#ifndef arch_atomic64_fetch_andnot
+/**
+ * raw_atomic64_or() - atomic bitwise OR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_or() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_or(s64 i, atomic64_t *v)
+{
+	arch_atomic64_or(i, v);
+}
+
+/**
+ * raw_atomic64_fetch_or() - atomic bitwise OR with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_or() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_andnot(s64 i, atomic64_t *v)
+raw_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_or)
+	return arch_atomic64_fetch_or(i, v);
+#elif defined(arch_atomic64_fetch_or_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic64_fetch_andnot_relaxed(i, v);
+	ret = arch_atomic64_fetch_or_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot
+#else
+#error "Unable to define raw_atomic64_fetch_or"
 #endif
+}
 
-#endif /* arch_atomic64_fetch_andnot_relaxed */
-
-#ifndef arch_atomic64_fetch_or_relaxed
-#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or
-#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or
-#define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or
-#else /* arch_atomic64_fetch_or_relaxed */
-
-#ifndef arch_atomic64_fetch_or_acquire
+/**
+ * raw_atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_or_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
+raw_atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_or_acquire)
+	return arch_atomic64_fetch_or_acquire(i, v);
+#elif defined(arch_atomic64_fetch_or_relaxed)
 	s64 ret = arch_atomic64_fetch_or_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire
+#elif defined(arch_atomic64_fetch_or)
+	return arch_atomic64_fetch_or(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_or_acquire"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_or_release
+/**
+ * raw_atomic64_fetch_or_release() - atomic bitwise OR with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_or_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_or_release(s64 i, atomic64_t *v)
+raw_atomic64_fetch_or_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_or_release)
+	return arch_atomic64_fetch_or_release(i, v);
+#elif defined(arch_atomic64_fetch_or_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_fetch_or_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_or)
+	return arch_atomic64_fetch_or(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_or_release"
+#endif
 }
-#define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release
+
+/**
+ * raw_atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_or_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline s64
+raw_atomic64_fetch_or_relaxed(s64 i, atomic64_t *v)
+{
+#if defined(arch_atomic64_fetch_or_relaxed)
+	return arch_atomic64_fetch_or_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_or)
+	return arch_atomic64_fetch_or(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_or_relaxed"
 #endif
+}
+
+/**
+ * raw_atomic64_xor() - atomic bitwise XOR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_xor() elsewhere.
+ *
+ * Return: Nothing.
+ */
+static __always_inline void
+raw_atomic64_xor(s64 i, atomic64_t *v)
+{
+	arch_atomic64_xor(i, v);
+}
 
-#ifndef arch_atomic64_fetch_or
+/**
+ * raw_atomic64_fetch_xor() - atomic bitwise XOR with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_xor() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_or(s64 i, atomic64_t *v)
+raw_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_xor)
+	return arch_atomic64_fetch_xor(i, v);
+#elif defined(arch_atomic64_fetch_xor_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic64_fetch_or_relaxed(i, v);
+	ret = arch_atomic64_fetch_xor_relaxed(i, v);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_or arch_atomic64_fetch_or
+#else
+#error "Unable to define raw_atomic64_fetch_xor"
 #endif
+}
 
-#endif /* arch_atomic64_fetch_or_relaxed */
-
-#ifndef arch_atomic64_fetch_xor_relaxed
-#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor
-#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor
-#define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor
-#else /* arch_atomic64_fetch_xor_relaxed */
-
-#ifndef arch_atomic64_fetch_xor_acquire
+/**
+ * raw_atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_xor_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
+raw_atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_xor_acquire)
+	return arch_atomic64_fetch_xor_acquire(i, v);
+#elif defined(arch_atomic64_fetch_xor_relaxed)
 	s64 ret = arch_atomic64_fetch_xor_relaxed(i, v);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire
+#elif defined(arch_atomic64_fetch_xor)
+	return arch_atomic64_fetch_xor(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_xor_acquire"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_xor_release
+/**
+ * raw_atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_xor_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_xor_release(s64 i, atomic64_t *v)
+raw_atomic64_fetch_xor_release(s64 i, atomic64_t *v)
 {
+#if defined(arch_atomic64_fetch_xor_release)
+	return arch_atomic64_fetch_xor_release(i, v);
+#elif defined(arch_atomic64_fetch_xor_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_fetch_xor_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_xor)
+	return arch_atomic64_fetch_xor(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_xor_release"
+#endif
 }
-#define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release
+
+/**
+ * raw_atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_xor_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline s64
+raw_atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
+{
+#if defined(arch_atomic64_fetch_xor_relaxed)
+	return arch_atomic64_fetch_xor_relaxed(i, v);
+#elif defined(arch_atomic64_fetch_xor)
+	return arch_atomic64_fetch_xor(i, v);
+#else
+#error "Unable to define raw_atomic64_fetch_xor_relaxed"
 #endif
+}
 
-#ifndef arch_atomic64_fetch_xor
+/**
+ * raw_atomic64_xchg() - atomic exchange with full ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_xchg() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
+raw_atomic64_xchg(atomic64_t *v, s64 new)
 {
+#if defined(arch_atomic64_xchg)
+	return arch_atomic64_xchg(v, new);
+#elif defined(arch_atomic64_xchg_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic64_fetch_xor_relaxed(i, v);
+	ret = arch_atomic64_xchg_relaxed(v, new);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_fetch_xor arch_atomic64_fetch_xor
+#else
+	return raw_xchg(&v->counter, new);
 #endif
+}
 
-#endif /* arch_atomic64_fetch_xor_relaxed */
-
-#ifndef arch_atomic64_xchg_relaxed
-#define arch_atomic64_xchg_acquire arch_atomic64_xchg
-#define arch_atomic64_xchg_release arch_atomic64_xchg
-#define arch_atomic64_xchg_relaxed arch_atomic64_xchg
-#else /* arch_atomic64_xchg_relaxed */
-
-#ifndef arch_atomic64_xchg_acquire
+/**
+ * raw_atomic64_xchg_acquire() - atomic exchange with acquire ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_xchg_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_xchg_acquire(atomic64_t *v, s64 i)
+raw_atomic64_xchg_acquire(atomic64_t *v, s64 new)
 {
-	s64 ret = arch_atomic64_xchg_relaxed(v, i);
+#if defined(arch_atomic64_xchg_acquire)
+	return arch_atomic64_xchg_acquire(v, new);
+#elif defined(arch_atomic64_xchg_relaxed)
+	s64 ret = arch_atomic64_xchg_relaxed(v, new);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_xchg_acquire arch_atomic64_xchg_acquire
+#elif defined(arch_atomic64_xchg)
+	return arch_atomic64_xchg(v, new);
+#else
+	return raw_xchg_acquire(&v->counter, new);
 #endif
+}
 
-#ifndef arch_atomic64_xchg_release
+/**
+ * raw_atomic64_xchg_release() - atomic exchange with release ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_xchg_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_xchg_release(atomic64_t *v, s64 i)
+raw_atomic64_xchg_release(atomic64_t *v, s64 new)
 {
+#if defined(arch_atomic64_xchg_release)
+	return arch_atomic64_xchg_release(v, new);
+#elif defined(arch_atomic64_xchg_relaxed)
 	__atomic_release_fence();
-	return arch_atomic64_xchg_relaxed(v, i);
+	return arch_atomic64_xchg_relaxed(v, new);
+#elif defined(arch_atomic64_xchg)
+	return arch_atomic64_xchg(v, new);
+#else
+	return raw_xchg_release(&v->counter, new);
+#endif
 }
-#define arch_atomic64_xchg_release arch_atomic64_xchg_release
+
+/**
+ * raw_atomic64_xchg_relaxed() - atomic exchange with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_xchg_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
+static __always_inline s64
+raw_atomic64_xchg_relaxed(atomic64_t *v, s64 new)
+{
+#if defined(arch_atomic64_xchg_relaxed)
+	return arch_atomic64_xchg_relaxed(v, new);
+#elif defined(arch_atomic64_xchg)
+	return arch_atomic64_xchg(v, new);
+#else
+	return raw_xchg_relaxed(&v->counter, new);
 #endif
+}
 
-#ifndef arch_atomic64_xchg
+/**
+ * raw_atomic64_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_cmpxchg() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_xchg(atomic64_t *v, s64 i)
+raw_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
+#if defined(arch_atomic64_cmpxchg)
+	return arch_atomic64_cmpxchg(v, old, new);
+#elif defined(arch_atomic64_cmpxchg_relaxed)
 	s64 ret;
 	__atomic_pre_full_fence();
-	ret = arch_atomic64_xchg_relaxed(v, i);
+	ret = arch_atomic64_cmpxchg_relaxed(v, old, new);
 	__atomic_post_full_fence();
 	return ret;
-}
-#define arch_atomic64_xchg arch_atomic64_xchg
+#else
+	return raw_cmpxchg(&v->counter, old, new);
 #endif
+}
 
-#endif /* arch_atomic64_xchg_relaxed */
-
-#ifndef arch_atomic64_cmpxchg_relaxed
-#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg
-#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg
-#define arch_atomic64_cmpxchg_relaxed arch_atomic64_cmpxchg
-#else /* arch_atomic64_cmpxchg_relaxed */
-
-#ifndef arch_atomic64_cmpxchg_acquire
+/**
+ * raw_atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_cmpxchg_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
+raw_atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
 {
+#if defined(arch_atomic64_cmpxchg_acquire)
+	return arch_atomic64_cmpxchg_acquire(v, old, new);
+#elif defined(arch_atomic64_cmpxchg_relaxed)
 	s64 ret = arch_atomic64_cmpxchg_relaxed(v, old, new);
 	__atomic_acquire_fence();
 	return ret;
-}
-#define arch_atomic64_cmpxchg_acquire arch_atomic64_cmpxchg_acquire
+#elif defined(arch_atomic64_cmpxchg)
+	return arch_atomic64_cmpxchg(v, old, new);
+#else
+	return raw_cmpxchg_acquire(&v->counter, old, new);
 #endif
+}
 
-#ifndef arch_atomic64_cmpxchg_release
+/**
+ * raw_atomic64_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_cmpxchg_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
+raw_atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
 {
+#if defined(arch_atomic64_cmpxchg_release)
+	return arch_atomic64_cmpxchg_release(v, old, new);
+#elif defined(arch_atomic64_cmpxchg_relaxed)
 	__atomic_release_fence();
 	return arch_atomic64_cmpxchg_relaxed(v, old, new);
-}
-#define arch_atomic64_cmpxchg_release arch_atomic64_cmpxchg_release
+#elif defined(arch_atomic64_cmpxchg)
+	return arch_atomic64_cmpxchg(v, old, new);
+#else
+	return raw_cmpxchg_release(&v->counter, old, new);
 #endif
+}
 
-#ifndef arch_atomic64_cmpxchg
+/**
+ * raw_atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_cmpxchg_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
+raw_atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
 {
-	s64 ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic64_cmpxchg_relaxed(v, old, new);
-	__atomic_post_full_fence();
-	return ret;
-}
-#define arch_atomic64_cmpxchg arch_atomic64_cmpxchg
+#if defined(arch_atomic64_cmpxchg_relaxed)
+	return arch_atomic64_cmpxchg_relaxed(v, old, new);
+#elif defined(arch_atomic64_cmpxchg)
+	return arch_atomic64_cmpxchg(v, old, new);
+#else
+	return raw_cmpxchg_relaxed(&v->counter, old, new);
 #endif
+}
 
-#endif /* arch_atomic64_cmpxchg_relaxed */
-
-#ifndef arch_atomic64_try_cmpxchg_relaxed
-#ifdef arch_atomic64_try_cmpxchg
-#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg
-#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg
-#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg
-#endif /* arch_atomic64_try_cmpxchg */
-
-#ifndef arch_atomic64_try_cmpxchg
+/**
+ * raw_atomic64_try_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_try_cmpxchg() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
+raw_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
+#if defined(arch_atomic64_try_cmpxchg)
+	return arch_atomic64_try_cmpxchg(v, old, new);
+#elif defined(arch_atomic64_try_cmpxchg_relaxed)
+	bool ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new);
+	__atomic_post_full_fence();
+	return ret;
+#else
 	s64 r, o = *old;
-	r = arch_atomic64_cmpxchg(v, o, new);
+	r = raw_atomic64_cmpxchg(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
 #endif
+}
 
-#ifndef arch_atomic64_try_cmpxchg_acquire
+/**
+ * raw_atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_acquire() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
+raw_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
 {
+#if defined(arch_atomic64_try_cmpxchg_acquire)
+	return arch_atomic64_try_cmpxchg_acquire(v, old, new);
+#elif defined(arch_atomic64_try_cmpxchg_relaxed)
+	bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic64_try_cmpxchg)
+	return arch_atomic64_try_cmpxchg(v, old, new);
+#else
 	s64 r, o = *old;
-	r = arch_atomic64_cmpxchg_acquire(v, o, new);
+	r = raw_atomic64_cmpxchg_acquire(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire
 #endif
+}
 
-#ifndef arch_atomic64_try_cmpxchg_release
+/**
+ * raw_atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_release() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
+raw_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
 {
+#if defined(arch_atomic64_try_cmpxchg_release)
+	return arch_atomic64_try_cmpxchg_release(v, old, new);
+#elif defined(arch_atomic64_try_cmpxchg_relaxed)
+	__atomic_release_fence();
+	return arch_atomic64_try_cmpxchg_relaxed(v, old, new);
+#elif defined(arch_atomic64_try_cmpxchg)
+	return arch_atomic64_try_cmpxchg(v, old, new);
+#else
 	s64 r, o = *old;
-	r = arch_atomic64_cmpxchg_release(v, o, new);
+	r = raw_atomic64_cmpxchg_release(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release
 #endif
+}
 
-#ifndef arch_atomic64_try_cmpxchg_relaxed
+/**
+ * raw_atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_try_cmpxchg_relaxed() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
+raw_atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
 {
+#if defined(arch_atomic64_try_cmpxchg_relaxed)
+	return arch_atomic64_try_cmpxchg_relaxed(v, old, new);
+#elif defined(arch_atomic64_try_cmpxchg)
+	return arch_atomic64_try_cmpxchg(v, old, new);
+#else
 	s64 r, o = *old;
-	r = arch_atomic64_cmpxchg_relaxed(v, o, new);
+	r = raw_atomic64_cmpxchg_relaxed(v, o, new);
 	if (unlikely(r != o))
 		*old = r;
 	return likely(r == o);
-}
-#define arch_atomic64_try_cmpxchg_relaxed arch_atomic64_try_cmpxchg_relaxed
-#endif
-
-#else /* arch_atomic64_try_cmpxchg_relaxed */
-
-#ifndef arch_atomic64_try_cmpxchg_acquire
-static __always_inline bool
-arch_atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
-{
-	bool ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic64_try_cmpxchg_acquire arch_atomic64_try_cmpxchg_acquire
-#endif
-
-#ifndef arch_atomic64_try_cmpxchg_release
-static __always_inline bool
-arch_atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
-{
-	__atomic_release_fence();
-	return arch_atomic64_try_cmpxchg_relaxed(v, old, new);
-}
-#define arch_atomic64_try_cmpxchg_release arch_atomic64_try_cmpxchg_release
 #endif
-
-#ifndef arch_atomic64_try_cmpxchg
-static __always_inline bool
-arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
-{
-	bool ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic64_try_cmpxchg_relaxed(v, old, new);
-	__atomic_post_full_fence();
-	return ret;
 }
-#define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
-#endif
 
-#endif /* arch_atomic64_try_cmpxchg_relaxed */
-
-#ifndef arch_atomic64_sub_and_test
 /**
- * arch_atomic64_sub_and_test - subtract value from variable and test result
- * @i: integer value to subtract
- * @v: pointer of type atomic64_t
+ * raw_atomic64_sub_and_test() - atomic subtract and test if zero with full ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_sub_and_test() elsewhere.
  *
- * Atomically subtracts @i from @v and returns
- * true if the result is zero, or false for all
- * other cases.
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
+raw_atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_sub_return(i, v) == 0;
-}
-#define arch_atomic64_sub_and_test arch_atomic64_sub_and_test
+#if defined(arch_atomic64_sub_and_test)
+	return arch_atomic64_sub_and_test(i, v);
+#else
+	return raw_atomic64_sub_return(i, v) == 0;
 #endif
+}
 
-#ifndef arch_atomic64_dec_and_test
 /**
- * arch_atomic64_dec_and_test - decrement and test
- * @v: pointer of type atomic64_t
+ * raw_atomic64_dec_and_test() - atomic decrement and test if zero with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_and_test() elsewhere.
  *
- * Atomically decrements @v by 1 and
- * returns true if the result is 0, or false for all other
- * cases.
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_dec_and_test(atomic64_t *v)
+raw_atomic64_dec_and_test(atomic64_t *v)
 {
-	return arch_atomic64_dec_return(v) == 0;
-}
-#define arch_atomic64_dec_and_test arch_atomic64_dec_and_test
+#if defined(arch_atomic64_dec_and_test)
+	return arch_atomic64_dec_and_test(v);
+#else
+	return raw_atomic64_dec_return(v) == 0;
 #endif
+}
 
-#ifndef arch_atomic64_inc_and_test
 /**
- * arch_atomic64_inc_and_test - increment and test
- * @v: pointer of type atomic64_t
+ * raw_atomic64_inc_and_test() - atomic increment and test if zero with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
  *
- * Atomically increments @v by 1
- * and returns true if the result is zero, or false for all
- * other cases.
+ * Safe to use in noinstr code; prefer atomic64_inc_and_test() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_inc_and_test(atomic64_t *v)
+raw_atomic64_inc_and_test(atomic64_t *v)
 {
-	return arch_atomic64_inc_return(v) == 0;
-}
-#define arch_atomic64_inc_and_test arch_atomic64_inc_and_test
+#if defined(arch_atomic64_inc_and_test)
+	return arch_atomic64_inc_and_test(v);
+#else
+	return raw_atomic64_inc_return(v) == 0;
 #endif
+}
 
-#ifndef arch_atomic64_add_negative_relaxed
-#ifdef arch_atomic64_add_negative
-#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative
-#define arch_atomic64_add_negative_release arch_atomic64_add_negative
-#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative
-#endif /* arch_atomic64_add_negative */
-
-#ifndef arch_atomic64_add_negative
 /**
- * arch_atomic64_add_negative - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic64_t
+ * raw_atomic64_add_negative() - atomic add and test if negative with full ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_negative() elsewhere.
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_add_negative(s64 i, atomic64_t *v)
+raw_atomic64_add_negative(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_add_return(i, v) < 0;
-}
-#define arch_atomic64_add_negative arch_atomic64_add_negative
+#if defined(arch_atomic64_add_negative)
+	return arch_atomic64_add_negative(i, v);
+#elif defined(arch_atomic64_add_negative_relaxed)
+	bool ret;
+	__atomic_pre_full_fence();
+	ret = arch_atomic64_add_negative_relaxed(i, v);
+	__atomic_post_full_fence();
+	return ret;
+#else
+	return raw_atomic64_add_return(i, v) < 0;
 #endif
+}
 
-#ifndef arch_atomic64_add_negative_acquire
 /**
- * arch_atomic64_add_negative_acquire - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic64_t
+ * raw_atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_negative_acquire() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v)
+raw_atomic64_add_negative_acquire(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_add_return_acquire(i, v) < 0;
-}
-#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire
+#if defined(arch_atomic64_add_negative_acquire)
+	return arch_atomic64_add_negative_acquire(i, v);
+#elif defined(arch_atomic64_add_negative_relaxed)
+	bool ret = arch_atomic64_add_negative_relaxed(i, v);
+	__atomic_acquire_fence();
+	return ret;
+#elif defined(arch_atomic64_add_negative)
+	return arch_atomic64_add_negative(i, v);
+#else
+	return raw_atomic64_add_return_acquire(i, v) < 0;
 #endif
+}
 
-#ifndef arch_atomic64_add_negative_release
 /**
- * arch_atomic64_add_negative_release - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic64_t
+ * raw_atomic64_add_negative_release() - atomic add and test if negative with release ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_negative_release() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_add_negative_release(s64 i, atomic64_t *v)
+raw_atomic64_add_negative_release(s64 i, atomic64_t *v)
 {
-	return arch_atomic64_add_return_release(i, v) < 0;
-}
-#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release
+#if defined(arch_atomic64_add_negative_release)
+	return arch_atomic64_add_negative_release(i, v);
+#elif defined(arch_atomic64_add_negative_relaxed)
+	__atomic_release_fence();
+	return arch_atomic64_add_negative_relaxed(i, v);
+#elif defined(arch_atomic64_add_negative)
+	return arch_atomic64_add_negative(i, v);
+#else
+	return raw_atomic64_add_return_release(i, v) < 0;
 #endif
+}
 
-#ifndef arch_atomic64_add_negative_relaxed
 /**
- * arch_atomic64_add_negative_relaxed - Add and test if negative
- * @i: integer value to add
- * @v: pointer of type atomic64_t
+ * raw_atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
  *
- * Atomically adds @i to @v and returns true if the result is negative,
- * or false when the result is greater than or equal to zero.
+ * Safe to use in noinstr code; prefer atomic64_add_negative_relaxed() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
-{
-	return arch_atomic64_add_return_relaxed(i, v) < 0;
-}
-#define arch_atomic64_add_negative_relaxed arch_atomic64_add_negative_relaxed
-#endif
-
-#else /* arch_atomic64_add_negative_relaxed */
-
-#ifndef arch_atomic64_add_negative_acquire
-static __always_inline bool
-arch_atomic64_add_negative_acquire(s64 i, atomic64_t *v)
-{
-	bool ret = arch_atomic64_add_negative_relaxed(i, v);
-	__atomic_acquire_fence();
-	return ret;
-}
-#define arch_atomic64_add_negative_acquire arch_atomic64_add_negative_acquire
-#endif
-
-#ifndef arch_atomic64_add_negative_release
-static __always_inline bool
-arch_atomic64_add_negative_release(s64 i, atomic64_t *v)
+raw_atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
 {
-	__atomic_release_fence();
+#if defined(arch_atomic64_add_negative_relaxed)
 	return arch_atomic64_add_negative_relaxed(i, v);
-}
-#define arch_atomic64_add_negative_release arch_atomic64_add_negative_release
+#elif defined(arch_atomic64_add_negative)
+	return arch_atomic64_add_negative(i, v);
+#else
+	return raw_atomic64_add_return_relaxed(i, v) < 0;
 #endif
-
-#ifndef arch_atomic64_add_negative
-static __always_inline bool
-arch_atomic64_add_negative(s64 i, atomic64_t *v)
-{
-	bool ret;
-	__atomic_pre_full_fence();
-	ret = arch_atomic64_add_negative_relaxed(i, v);
-	__atomic_post_full_fence();
-	return ret;
 }
-#define arch_atomic64_add_negative arch_atomic64_add_negative
-#endif
-
-#endif /* arch_atomic64_add_negative_relaxed */
 
-#ifndef arch_atomic64_fetch_add_unless
 /**
- * arch_atomic64_fetch_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
+ * raw_atomic64_fetch_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic64_t
+ * @a: s64 value to add
+ * @u: s64 value to compare with
  *
- * Atomically adds @a to @v, so long as @v was not already @u.
- * Returns original value of @v
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_fetch_add_unless() elsewhere.
+ *
+ * Return: The original value of @v.
  */
 static __always_inline s64
-arch_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
+raw_atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	s64 c = arch_atomic64_read(v);
+#if defined(arch_atomic64_fetch_add_unless)
+	return arch_atomic64_fetch_add_unless(v, a, u);
+#else
+	s64 c = raw_atomic64_read(v);
 
 	do {
 		if (unlikely(c == u))
 			break;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c + a));
+	} while (!raw_atomic64_try_cmpxchg(v, &c, c + a));
 
 	return c;
-}
-#define arch_atomic64_fetch_add_unless arch_atomic64_fetch_add_unless
 #endif
+}
 
-#ifndef arch_atomic64_add_unless
 /**
- * arch_atomic64_add_unless - add unless the number is already a given value
- * @v: pointer of type atomic64_t
- * @a: the amount to add to v...
- * @u: ...unless v is equal to u.
+ * raw_atomic64_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic64_t
+ * @a: s64 value to add
+ * @u: s64 value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_add_unless() elsewhere.
  *
- * Atomically adds @a to @v, if @v was not already @u.
- * Returns true if the addition was done.
+ * Return: @true if @v was updated, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
+raw_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	return arch_atomic64_fetch_add_unless(v, a, u) != u;
-}
-#define arch_atomic64_add_unless arch_atomic64_add_unless
+#if defined(arch_atomic64_add_unless)
+	return arch_atomic64_add_unless(v, a, u);
+#else
+	return raw_atomic64_fetch_add_unless(v, a, u) != u;
 #endif
+}
 
-#ifndef arch_atomic64_inc_not_zero
 /**
- * arch_atomic64_inc_not_zero - increment unless the number is zero
- * @v: pointer of type atomic64_t
+ * raw_atomic64_inc_not_zero() - atomic increment unless zero with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc_not_zero() elsewhere.
  *
- * Atomically increments @v by 1, if @v is non-zero.
- * Returns true if the increment was done.
+ * Return: @true if @v was updated, @false otherwise.
  */
 static __always_inline bool
-arch_atomic64_inc_not_zero(atomic64_t *v)
+raw_atomic64_inc_not_zero(atomic64_t *v)
 {
-	return arch_atomic64_add_unless(v, 1, 0);
-}
-#define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
+#if defined(arch_atomic64_inc_not_zero)
+	return arch_atomic64_inc_not_zero(v);
+#else
+	return raw_atomic64_add_unless(v, 1, 0);
 #endif
+}
 
-#ifndef arch_atomic64_inc_unless_negative
+/**
+ * raw_atomic64_inc_unless_negative() - atomic increment unless negative with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_inc_unless_negative() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic64_inc_unless_negative(atomic64_t *v)
+raw_atomic64_inc_unless_negative(atomic64_t *v)
 {
-	s64 c = arch_atomic64_read(v);
+#if defined(arch_atomic64_inc_unless_negative)
+	return arch_atomic64_inc_unless_negative(v);
+#else
+	s64 c = raw_atomic64_read(v);
 
 	do {
 		if (unlikely(c < 0))
 			return false;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c + 1));
+	} while (!raw_atomic64_try_cmpxchg(v, &c, c + 1));
 
 	return true;
-}
-#define arch_atomic64_inc_unless_negative arch_atomic64_inc_unless_negative
 #endif
+}
 
-#ifndef arch_atomic64_dec_unless_positive
+/**
+ * raw_atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_unless_positive() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic64_dec_unless_positive(atomic64_t *v)
+raw_atomic64_dec_unless_positive(atomic64_t *v)
 {
-	s64 c = arch_atomic64_read(v);
+#if defined(arch_atomic64_dec_unless_positive)
+	return arch_atomic64_dec_unless_positive(v);
+#else
+	s64 c = raw_atomic64_read(v);
 
 	do {
 		if (unlikely(c > 0))
 			return false;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, c - 1));
+	} while (!raw_atomic64_try_cmpxchg(v, &c, c - 1));
 
 	return true;
-}
-#define arch_atomic64_dec_unless_positive arch_atomic64_dec_unless_positive
 #endif
+}
 
-#ifndef arch_atomic64_dec_if_positive
+/**
+ * raw_atomic64_dec_if_positive() - atomic decrement if positive with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic64_dec_if_positive() elsewhere.
+ *
+ * Return: The old value of (@v - 1), regardless of whether @v was updated.
+ */
 static __always_inline s64
-arch_atomic64_dec_if_positive(atomic64_t *v)
+raw_atomic64_dec_if_positive(atomic64_t *v)
 {
-	s64 dec, c = arch_atomic64_read(v);
+#if defined(arch_atomic64_dec_if_positive)
+	return arch_atomic64_dec_if_positive(v);
+#else
+	s64 dec, c = raw_atomic64_read(v);
 
 	do {
 		dec = c - 1;
 		if (unlikely(dec < 0))
 			break;
-	} while (!arch_atomic64_try_cmpxchg(v, &c, dec));
+	} while (!raw_atomic64_try_cmpxchg(v, &c, dec));
 
 	return dec;
-}
-#define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive
 #endif
+}
 
 #endif /* _LINUX_ATOMIC_FALLBACK_H */
-// ad2e2b4d168dbc60a73922616047a9bfa446af36
+// b565db590afeeff0d7c9485ccbca5bb6e155749f
diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h
index 03a232a1fa57..37ab6314a9f7 100644
--- a/include/linux/atomic/atomic-instrumented.h
+++ b/include/linux/atomic/atomic-instrumented.h
@@ -4,15 +4,10 @@
 // DO NOT MODIFY THIS FILE DIRECTLY
 
 /*
- * This file provides wrappers with KASAN instrumentation for atomic operations.
- * To use this functionality an arch's atomic.h file needs to define all
- * atomic operations with arch_ prefix (e.g. arch_atomic_read()) and include
- * this file at the end. This file provides atomic_read() that forwards to
- * arch_atomic_read() for actual atomic operation.
- * Note: if an arch atomic operation is implemented by means of other atomic
- * operations (e.g. atomic_read()/atomic_cmpxchg() loop), then it needs to use
- * arch_ variants (i.e. arch_atomic_read()/arch_atomic_cmpxchg()) to avoid
- * double instrumentation.
+ * This file provoides atomic operations with explicit instrumentation (e.g.
+ * KASAN, KCSAN), which should be used unless it is necessary to avoid
+ * instrumentation. Where it is necessary to aovid instrumenation, the
+ * raw_atomic*() operations should be used.
  */
 #ifndef _LINUX_ATOMIC_INSTRUMENTED_H
 #define _LINUX_ATOMIC_INSTRUMENTED_H
@@ -21,1927 +16,4738 @@
 #include <linux/compiler.h>
 #include <linux/instrumented.h>
 
+/**
+ * atomic_read() - atomic load with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically loads the value of @v with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_read() there.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline int
 atomic_read(const atomic_t *v)
 {
 	instrument_atomic_read(v, sizeof(*v));
-	return arch_atomic_read(v);
-}
-
+	return raw_atomic_read(v);
+}
+
+/**
+ * atomic_read_acquire() - atomic load with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically loads the value of @v with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_read_acquire() there.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline int
 atomic_read_acquire(const atomic_t *v)
 {
 	instrument_atomic_read(v, sizeof(*v));
-	return arch_atomic_read_acquire(v);
-}
-
+	return raw_atomic_read_acquire(v);
+}
+
+/**
+ * atomic_set() - atomic set with relaxed ordering
+ * @v: pointer to atomic_t
+ * @i: int value to assign
+ *
+ * Atomically sets @v to @i with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_set() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_set(atomic_t *v, int i)
 {
 	instrument_atomic_write(v, sizeof(*v));
-	arch_atomic_set(v, i);
-}
-
+	raw_atomic_set(v, i);
+}
+
+/**
+ * atomic_set_release() - atomic set with release ordering
+ * @v: pointer to atomic_t
+ * @i: int value to assign
+ *
+ * Atomically sets @v to @i with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_set_release() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_set_release(atomic_t *v, int i)
 {
 	kcsan_release();
 	instrument_atomic_write(v, sizeof(*v));
-	arch_atomic_set_release(v, i);
-}
-
+	raw_atomic_set_release(v, i);
+}
+
+/**
+ * atomic_add() - atomic add with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_add(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_add(i, v);
+	raw_atomic_add(i, v);
 }
 
+/**
+ * atomic_add_return() - atomic add with full ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_add_return(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_return(i, v);
+	return raw_atomic_add_return(i, v);
 }
 
+/**
+ * atomic_add_return_acquire() - atomic add with acquire ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_add_return_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_return_acquire(i, v);
+	return raw_atomic_add_return_acquire(i, v);
 }
 
+/**
+ * atomic_add_return_release() - atomic add with release ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_add_return_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_return_release(i, v);
+	return raw_atomic_add_return_release(i, v);
 }
 
+/**
+ * atomic_add_return_relaxed() - atomic add with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_add_return_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_return_relaxed(i, v);
+	return raw_atomic_add_return_relaxed(i, v);
 }
 
+/**
+ * atomic_fetch_add() - atomic add with full ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_add() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_add(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_add(i, v);
+	return raw_atomic_fetch_add(i, v);
 }
 
+/**
+ * atomic_fetch_add_acquire() - atomic add with acquire ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_add_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_add_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_add_acquire(i, v);
+	return raw_atomic_fetch_add_acquire(i, v);
 }
 
+/**
+ * atomic_fetch_add_release() - atomic add with release ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_add_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_add_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_add_release(i, v);
+	return raw_atomic_fetch_add_release(i, v);
 }
 
+/**
+ * atomic_fetch_add_relaxed() - atomic add with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_add_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_add_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_add_relaxed(i, v);
+	return raw_atomic_fetch_add_relaxed(i, v);
 }
 
+/**
+ * atomic_sub() - atomic subtract with relaxed ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_sub() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_sub(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_sub(i, v);
+	raw_atomic_sub(i, v);
 }
 
+/**
+ * atomic_sub_return() - atomic subtract with full ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_sub_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_sub_return(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_sub_return(i, v);
+	return raw_atomic_sub_return(i, v);
 }
 
+/**
+ * atomic_sub_return_acquire() - atomic subtract with acquire ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_sub_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_sub_return_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_sub_return_acquire(i, v);
+	return raw_atomic_sub_return_acquire(i, v);
 }
 
+/**
+ * atomic_sub_return_release() - atomic subtract with release ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_sub_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_sub_return_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_sub_return_release(i, v);
+	return raw_atomic_sub_return_release(i, v);
 }
 
+/**
+ * atomic_sub_return_relaxed() - atomic subtract with relaxed ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_sub_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_sub_return_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_sub_return_relaxed(i, v);
+	return raw_atomic_sub_return_relaxed(i, v);
 }
 
+/**
+ * atomic_fetch_sub() - atomic subtract with full ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_sub() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_sub(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_sub(i, v);
+	return raw_atomic_fetch_sub(i, v);
 }
 
+/**
+ * atomic_fetch_sub_acquire() - atomic subtract with acquire ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_sub_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_sub_acquire(i, v);
+	return raw_atomic_fetch_sub_acquire(i, v);
 }
 
+/**
+ * atomic_fetch_sub_release() - atomic subtract with release ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_sub_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_sub_release(i, v);
+	return raw_atomic_fetch_sub_release(i, v);
 }
 
+/**
+ * atomic_fetch_sub_relaxed() - atomic subtract with relaxed ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_sub_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_sub_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_sub_relaxed(i, v);
+	return raw_atomic_fetch_sub_relaxed(i, v);
 }
 
+/**
+ * atomic_inc() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_inc(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_inc(v);
+	raw_atomic_inc(v);
 }
 
+/**
+ * atomic_inc_return() - atomic increment with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_inc_return(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_return(v);
+	return raw_atomic_inc_return(v);
 }
 
+/**
+ * atomic_inc_return_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_inc_return_acquire(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_return_acquire(v);
+	return raw_atomic_inc_return_acquire(v);
 }
 
+/**
+ * atomic_inc_return_release() - atomic increment with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_inc_return_release(atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_return_release(v);
+	return raw_atomic_inc_return_release(v);
 }
 
+/**
+ * atomic_inc_return_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_inc_return_relaxed(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_return_relaxed(v);
+	return raw_atomic_inc_return_relaxed(v);
 }
 
+/**
+ * atomic_fetch_inc() - atomic increment with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_inc() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_inc(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_inc(v);
+	return raw_atomic_fetch_inc(v);
 }
 
+/**
+ * atomic_fetch_inc_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_inc_acquire(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_inc_acquire(v);
+	return raw_atomic_fetch_inc_acquire(v);
 }
 
+/**
+ * atomic_fetch_inc_release() - atomic increment with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_inc_release(atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_inc_release(v);
+	return raw_atomic_fetch_inc_release(v);
 }
 
+/**
+ * atomic_fetch_inc_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_inc_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_inc_relaxed(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_inc_relaxed(v);
+	return raw_atomic_fetch_inc_relaxed(v);
 }
 
+/**
+ * atomic_dec() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_dec(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_dec(v);
+	raw_atomic_dec(v);
 }
 
+/**
+ * atomic_dec_return() - atomic decrement with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_dec_return(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_return(v);
+	return raw_atomic_dec_return(v);
 }
 
+/**
+ * atomic_dec_return_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_dec_return_acquire(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_return_acquire(v);
+	return raw_atomic_dec_return_acquire(v);
 }
 
+/**
+ * atomic_dec_return_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_dec_return_release(atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_return_release(v);
+	return raw_atomic_dec_return_release(v);
 }
 
+/**
+ * atomic_dec_return_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline int
 atomic_dec_return_relaxed(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_return_relaxed(v);
+	return raw_atomic_dec_return_relaxed(v);
 }
 
+/**
+ * atomic_fetch_dec() - atomic decrement with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_dec() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_dec(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_dec(v);
+	return raw_atomic_fetch_dec(v);
 }
 
+/**
+ * atomic_fetch_dec_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_dec_acquire(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_dec_acquire(v);
+	return raw_atomic_fetch_dec_acquire(v);
 }
 
+/**
+ * atomic_fetch_dec_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_dec_release(atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_dec_release(v);
+	return raw_atomic_fetch_dec_release(v);
 }
 
+/**
+ * atomic_fetch_dec_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_dec_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_dec_relaxed(atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_dec_relaxed(v);
+	return raw_atomic_fetch_dec_relaxed(v);
 }
 
+/**
+ * atomic_and() - atomic bitwise AND with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_and() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_and(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_and(i, v);
+	raw_atomic_and(i, v);
 }
 
+/**
+ * atomic_fetch_and() - atomic bitwise AND with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_and() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_and(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_and(i, v);
+	return raw_atomic_fetch_and(i, v);
 }
 
+/**
+ * atomic_fetch_and_acquire() - atomic bitwise AND with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_and_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_and_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_and_acquire(i, v);
+	return raw_atomic_fetch_and_acquire(i, v);
 }
 
+/**
+ * atomic_fetch_and_release() - atomic bitwise AND with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_and_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_and_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_and_release(i, v);
+	return raw_atomic_fetch_and_release(i, v);
 }
 
+/**
+ * atomic_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_and_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_and_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_and_relaxed(i, v);
+	return raw_atomic_fetch_and_relaxed(i, v);
 }
 
+/**
+ * atomic_andnot() - atomic bitwise AND NOT with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_andnot() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_andnot(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_andnot(i, v);
+	raw_atomic_andnot(i, v);
 }
 
+/**
+ * atomic_fetch_andnot() - atomic bitwise AND NOT with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_andnot(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_andnot(i, v);
+	return raw_atomic_fetch_andnot(i, v);
 }
 
+/**
+ * atomic_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_andnot_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_andnot_acquire(i, v);
+	return raw_atomic_fetch_andnot_acquire(i, v);
 }
 
+/**
+ * atomic_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_andnot_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_andnot_release(i, v);
+	return raw_atomic_fetch_andnot_release(i, v);
 }
 
+/**
+ * atomic_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_andnot_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_andnot_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_andnot_relaxed(i, v);
+	return raw_atomic_fetch_andnot_relaxed(i, v);
 }
 
+/**
+ * atomic_or() - atomic bitwise OR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_or() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_or(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_or(i, v);
+	raw_atomic_or(i, v);
 }
 
+/**
+ * atomic_fetch_or() - atomic bitwise OR with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_or() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_or(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_or(i, v);
+	return raw_atomic_fetch_or(i, v);
 }
 
+/**
+ * atomic_fetch_or_acquire() - atomic bitwise OR with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_or_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_or_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_or_acquire(i, v);
+	return raw_atomic_fetch_or_acquire(i, v);
 }
 
+/**
+ * atomic_fetch_or_release() - atomic bitwise OR with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_or_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_or_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_or_release(i, v);
+	return raw_atomic_fetch_or_release(i, v);
 }
 
+/**
+ * atomic_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_or_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_or_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_or_relaxed(i, v);
+	return raw_atomic_fetch_or_relaxed(i, v);
 }
 
+/**
+ * atomic_xor() - atomic bitwise XOR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_xor() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_xor(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_xor(i, v);
+	raw_atomic_xor(i, v);
 }
 
+/**
+ * atomic_fetch_xor() - atomic bitwise XOR with full ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_xor() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_xor(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_xor(i, v);
+	return raw_atomic_fetch_xor(i, v);
 }
 
+/**
+ * atomic_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_xor_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_xor_acquire(i, v);
+	return raw_atomic_fetch_xor_acquire(i, v);
 }
 
+/**
+ * atomic_fetch_xor_release() - atomic bitwise XOR with release ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_xor_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_xor_release(i, v);
+	return raw_atomic_fetch_xor_release(i, v);
 }
 
+/**
+ * atomic_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
+ * @i: int value
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_xor_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_xor_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_xor_relaxed(i, v);
+	return raw_atomic_fetch_xor_relaxed(i, v);
 }
 
+/**
+ * atomic_xchg() - atomic exchange with full ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_xchg() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-atomic_xchg(atomic_t *v, int i)
+atomic_xchg(atomic_t *v, int new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_xchg(v, i);
+	return raw_atomic_xchg(v, new);
 }
 
+/**
+ * atomic_xchg_acquire() - atomic exchange with acquire ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_xchg_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-atomic_xchg_acquire(atomic_t *v, int i)
+atomic_xchg_acquire(atomic_t *v, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_xchg_acquire(v, i);
+	return raw_atomic_xchg_acquire(v, new);
 }
 
+/**
+ * atomic_xchg_release() - atomic exchange with release ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_xchg_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-atomic_xchg_release(atomic_t *v, int i)
+atomic_xchg_release(atomic_t *v, int new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_xchg_release(v, i);
+	return raw_atomic_xchg_release(v, new);
 }
 
+/**
+ * atomic_xchg_relaxed() - atomic exchange with relaxed ordering
+ * @v: pointer to atomic_t
+ * @new: int value to assign
+ *
+ * Atomically updates @v to @new with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_xchg_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
-atomic_xchg_relaxed(atomic_t *v, int i)
+atomic_xchg_relaxed(atomic_t *v, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_xchg_relaxed(v, i);
+	return raw_atomic_xchg_relaxed(v, new);
 }
 
+/**
+ * atomic_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_cmpxchg() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_cmpxchg(v, old, new);
-}
-
+	return raw_atomic_cmpxchg(v, old, new);
+}
+
+/**
+ * atomic_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_cmpxchg_acquire(v, old, new);
+	return raw_atomic_cmpxchg_acquire(v, old, new);
 }
 
+/**
+ * atomic_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_cmpxchg_release(atomic_t *v, int old, int new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_cmpxchg_release(v, old, new);
-}
-
+	return raw_atomic_cmpxchg_release(v, old, new);
+}
+
+/**
+ * atomic_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_t
+ * @old: int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_cmpxchg_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_cmpxchg_relaxed(v, old, new);
+	return raw_atomic_cmpxchg_relaxed(v, old, new);
 }
 
+/**
+ * atomic_try_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_try_cmpxchg(atomic_t *v, int *old, int new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_try_cmpxchg(v, old, new);
-}
-
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_try_cmpxchg(v, old, new);
+}
+
+/**
+ * atomic_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_acquire() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_try_cmpxchg_acquire(v, old, new);
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_try_cmpxchg_acquire(v, old, new);
 }
 
+/**
+ * atomic_try_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_release() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_try_cmpxchg_release(v, old, new);
-}
-
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_try_cmpxchg_release(v, old, new);
+}
+
+/**
+ * atomic_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_t
+ * @old: pointer to int value to compare with
+ * @new: int value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_try_cmpxchg_relaxed() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_try_cmpxchg_relaxed(v, old, new);
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_try_cmpxchg_relaxed(v, old, new);
 }
 
+/**
+ * atomic_sub_and_test() - atomic subtract and test if zero with full ordering
+ * @i: int value to subtract
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_sub_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic_sub_and_test(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_sub_and_test(i, v);
+	return raw_atomic_sub_and_test(i, v);
 }
 
+/**
+ * atomic_dec_and_test() - atomic decrement and test if zero with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic_dec_and_test(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_and_test(v);
+	return raw_atomic_dec_and_test(v);
 }
 
+/**
+ * atomic_inc_and_test() - atomic increment and test if zero with full ordering
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic_inc_and_test(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_and_test(v);
+	return raw_atomic_inc_and_test(v);
 }
 
+/**
+ * atomic_add_negative() - atomic add and test if negative with full ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_negative() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_add_negative(int i, atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_negative(i, v);
+	return raw_atomic_add_negative(i, v);
 }
 
+/**
+ * atomic_add_negative_acquire() - atomic add and test if negative with acquire ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_negative_acquire() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_add_negative_acquire(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_negative_acquire(i, v);
+	return raw_atomic_add_negative_acquire(i, v);
 }
 
+/**
+ * atomic_add_negative_release() - atomic add and test if negative with release ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_negative_release() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_add_negative_release(int i, atomic_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_negative_release(i, v);
+	return raw_atomic_add_negative_release(i, v);
 }
 
+/**
+ * atomic_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
+ * @i: int value to add
+ * @v: pointer to atomic_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_negative_relaxed() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_add_negative_relaxed(int i, atomic_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_negative_relaxed(i, v);
+	return raw_atomic_add_negative_relaxed(i, v);
 }
 
+/**
+ * atomic_fetch_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_t
+ * @a: int value to add
+ * @u: int value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_fetch_add_unless() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline int
 atomic_fetch_add_unless(atomic_t *v, int a, int u)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_fetch_add_unless(v, a, u);
-}
-
+	return raw_atomic_fetch_add_unless(v, a, u);
+}
+
+/**
+ * atomic_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_t
+ * @a: int value to add
+ * @u: int value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_add_unless() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_add_unless(atomic_t *v, int a, int u)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_add_unless(v, a, u);
+	return raw_atomic_add_unless(v, a, u);
 }
 
+/**
+ * atomic_inc_not_zero() - atomic increment unless zero with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_not_zero() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_inc_not_zero(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_not_zero(v);
+	return raw_atomic_inc_not_zero(v);
 }
 
+/**
+ * atomic_inc_unless_negative() - atomic increment unless negative with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_inc_unless_negative() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_inc_unless_negative(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_inc_unless_negative(v);
+	return raw_atomic_inc_unless_negative(v);
 }
 
+/**
+ * atomic_dec_unless_positive() - atomic decrement unless positive with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_unless_positive() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_dec_unless_positive(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_unless_positive(v);
+	return raw_atomic_dec_unless_positive(v);
 }
 
+/**
+ * atomic_dec_if_positive() - atomic decrement if positive with full ordering
+ * @v: pointer to atomic_t
+ *
+ * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_dec_if_positive() there.
+ *
+ * Return: The old value of (@v - 1), regardless of whether @v was updated.
+ */
 static __always_inline int
 atomic_dec_if_positive(atomic_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_dec_if_positive(v);
+	return raw_atomic_dec_if_positive(v);
 }
 
+/**
+ * atomic64_read() - atomic load with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically loads the value of @v with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_read() there.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline s64
 atomic64_read(const atomic64_t *v)
 {
 	instrument_atomic_read(v, sizeof(*v));
-	return arch_atomic64_read(v);
-}
-
+	return raw_atomic64_read(v);
+}
+
+/**
+ * atomic64_read_acquire() - atomic load with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically loads the value of @v with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_read_acquire() there.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline s64
 atomic64_read_acquire(const atomic64_t *v)
 {
 	instrument_atomic_read(v, sizeof(*v));
-	return arch_atomic64_read_acquire(v);
-}
-
+	return raw_atomic64_read_acquire(v);
+}
+
+/**
+ * atomic64_set() - atomic set with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @i: s64 value to assign
+ *
+ * Atomically sets @v to @i with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_set() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_set(atomic64_t *v, s64 i)
 {
 	instrument_atomic_write(v, sizeof(*v));
-	arch_atomic64_set(v, i);
-}
-
+	raw_atomic64_set(v, i);
+}
+
+/**
+ * atomic64_set_release() - atomic set with release ordering
+ * @v: pointer to atomic64_t
+ * @i: s64 value to assign
+ *
+ * Atomically sets @v to @i with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_set_release() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_set_release(atomic64_t *v, s64 i)
 {
 	kcsan_release();
 	instrument_atomic_write(v, sizeof(*v));
-	arch_atomic64_set_release(v, i);
-}
-
+	raw_atomic64_set_release(v, i);
+}
+
+/**
+ * atomic64_add() - atomic add with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_add(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_add(i, v);
+	raw_atomic64_add(i, v);
 }
 
+/**
+ * atomic64_add_return() - atomic add with full ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_add_return(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_return(i, v);
+	return raw_atomic64_add_return(i, v);
 }
 
+/**
+ * atomic64_add_return_acquire() - atomic add with acquire ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_add_return_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_return_acquire(i, v);
+	return raw_atomic64_add_return_acquire(i, v);
 }
 
+/**
+ * atomic64_add_return_release() - atomic add with release ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_add_return_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_return_release(i, v);
+	return raw_atomic64_add_return_release(i, v);
 }
 
+/**
+ * atomic64_add_return_relaxed() - atomic add with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_add_return_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_return_relaxed(i, v);
+	return raw_atomic64_add_return_relaxed(i, v);
 }
 
+/**
+ * atomic64_fetch_add() - atomic add with full ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_add() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_add(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_add(i, v);
+	return raw_atomic64_fetch_add(i, v);
 }
 
+/**
+ * atomic64_fetch_add_acquire() - atomic add with acquire ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_add_acquire(i, v);
+	return raw_atomic64_fetch_add_acquire(i, v);
 }
 
+/**
+ * atomic64_fetch_add_release() - atomic add with release ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_add_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_add_release(i, v);
+	return raw_atomic64_fetch_add_release(i, v);
 }
 
+/**
+ * atomic64_fetch_add_relaxed() - atomic add with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_add_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_add_relaxed(i, v);
+	return raw_atomic64_fetch_add_relaxed(i, v);
 }
 
+/**
+ * atomic64_sub() - atomic subtract with relaxed ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_sub() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_sub(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_sub(i, v);
+	raw_atomic64_sub(i, v);
 }
 
+/**
+ * atomic64_sub_return() - atomic subtract with full ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_sub_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_sub_return(i, v);
+	return raw_atomic64_sub_return(i, v);
 }
 
+/**
+ * atomic64_sub_return_acquire() - atomic subtract with acquire ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_sub_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_sub_return_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_sub_return_acquire(i, v);
+	return raw_atomic64_sub_return_acquire(i, v);
 }
 
+/**
+ * atomic64_sub_return_release() - atomic subtract with release ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_sub_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_sub_return_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_sub_return_release(i, v);
+	return raw_atomic64_sub_return_release(i, v);
 }
 
+/**
+ * atomic64_sub_return_relaxed() - atomic subtract with relaxed ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_sub_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_sub_return_relaxed(i, v);
+	return raw_atomic64_sub_return_relaxed(i, v);
 }
 
+/**
+ * atomic64_fetch_sub() - atomic subtract with full ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_sub(i, v);
+	return raw_atomic64_fetch_sub(i, v);
 }
 
+/**
+ * atomic64_fetch_sub_acquire() - atomic subtract with acquire ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_sub_acquire(i, v);
+	return raw_atomic64_fetch_sub_acquire(i, v);
 }
 
+/**
+ * atomic64_fetch_sub_release() - atomic subtract with release ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_sub_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_sub_release(i, v);
+	return raw_atomic64_fetch_sub_release(i, v);
 }
 
+/**
+ * atomic64_fetch_sub_relaxed() - atomic subtract with relaxed ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_sub_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_sub_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_sub_relaxed(i, v);
+	return raw_atomic64_fetch_sub_relaxed(i, v);
 }
 
+/**
+ * atomic64_inc() - atomic increment with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_inc(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_inc(v);
+	raw_atomic64_inc(v);
 }
 
+/**
+ * atomic64_inc_return() - atomic increment with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_inc_return(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_return(v);
+	return raw_atomic64_inc_return(v);
 }
 
+/**
+ * atomic64_inc_return_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_inc_return_acquire(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_return_acquire(v);
+	return raw_atomic64_inc_return_acquire(v);
 }
 
+/**
+ * atomic64_inc_return_release() - atomic increment with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_inc_return_release(atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_return_release(v);
+	return raw_atomic64_inc_return_release(v);
 }
 
+/**
+ * atomic64_inc_return_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_inc_return_relaxed(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_return_relaxed(v);
+	return raw_atomic64_inc_return_relaxed(v);
 }
 
+/**
+ * atomic64_fetch_inc() - atomic increment with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_inc(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_inc(v);
+	return raw_atomic64_fetch_inc(v);
 }
 
+/**
+ * atomic64_fetch_inc_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_inc_acquire(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_inc_acquire(v);
+	return raw_atomic64_fetch_inc_acquire(v);
 }
 
+/**
+ * atomic64_fetch_inc_release() - atomic increment with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_inc_release(atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_inc_release(v);
+	return raw_atomic64_fetch_inc_release(v);
 }
 
+/**
+ * atomic64_fetch_inc_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_inc_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_inc_relaxed(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_inc_relaxed(v);
+	return raw_atomic64_fetch_inc_relaxed(v);
 }
 
+/**
+ * atomic64_dec() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_dec(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_dec(v);
+	raw_atomic64_dec(v);
 }
 
+/**
+ * atomic64_dec_return() - atomic decrement with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_dec_return(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_return(v);
+	return raw_atomic64_dec_return(v);
 }
 
+/**
+ * atomic64_dec_return_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_dec_return_acquire(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_return_acquire(v);
+	return raw_atomic64_dec_return_acquire(v);
 }
 
+/**
+ * atomic64_dec_return_release() - atomic decrement with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_dec_return_release(atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_return_release(v);
+	return raw_atomic64_dec_return_release(v);
 }
 
+/**
+ * atomic64_dec_return_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline s64
 atomic64_dec_return_relaxed(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_return_relaxed(v);
+	return raw_atomic64_dec_return_relaxed(v);
 }
 
+/**
+ * atomic64_fetch_dec() - atomic decrement with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_dec(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_dec(v);
+	return raw_atomic64_fetch_dec(v);
 }
 
+/**
+ * atomic64_fetch_dec_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_dec_acquire(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_dec_acquire(v);
+	return raw_atomic64_fetch_dec_acquire(v);
 }
 
+/**
+ * atomic64_fetch_dec_release() - atomic decrement with release ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_dec_release(atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_dec_release(v);
+	return raw_atomic64_fetch_dec_release(v);
 }
 
+/**
+ * atomic64_fetch_dec_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_dec_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_dec_relaxed(atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_dec_relaxed(v);
+	return raw_atomic64_fetch_dec_relaxed(v);
 }
 
+/**
+ * atomic64_and() - atomic bitwise AND with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_and() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_and(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_and(i, v);
+	raw_atomic64_and(i, v);
 }
 
+/**
+ * atomic64_fetch_and() - atomic bitwise AND with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_and() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_and(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_and(i, v);
+	return raw_atomic64_fetch_and(i, v);
 }
 
+/**
+ * atomic64_fetch_and_acquire() - atomic bitwise AND with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_and_acquire(i, v);
+	return raw_atomic64_fetch_and_acquire(i, v);
 }
 
+/**
+ * atomic64_fetch_and_release() - atomic bitwise AND with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_and_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_and_release(i, v);
+	return raw_atomic64_fetch_and_release(i, v);
 }
 
+/**
+ * atomic64_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_and_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_and_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_and_relaxed(i, v);
+	return raw_atomic64_fetch_and_relaxed(i, v);
 }
 
+/**
+ * atomic64_andnot() - atomic bitwise AND NOT with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_andnot() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_andnot(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_andnot(i, v);
+	raw_atomic64_andnot(i, v);
 }
 
+/**
+ * atomic64_fetch_andnot() - atomic bitwise AND NOT with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_andnot(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_andnot(i, v);
+	return raw_atomic64_fetch_andnot(i, v);
 }
 
+/**
+ * atomic64_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_andnot_acquire(i, v);
+	return raw_atomic64_fetch_andnot_acquire(i, v);
 }
 
+/**
+ * atomic64_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_andnot_release(i, v);
+	return raw_atomic64_fetch_andnot_release(i, v);
 }
 
+/**
+ * atomic64_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_andnot_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_andnot_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_andnot_relaxed(i, v);
+	return raw_atomic64_fetch_andnot_relaxed(i, v);
 }
 
+/**
+ * atomic64_or() - atomic bitwise OR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_or() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_or(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_or(i, v);
+	raw_atomic64_or(i, v);
 }
 
+/**
+ * atomic64_fetch_or() - atomic bitwise OR with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_or() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_or(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_or(i, v);
+	return raw_atomic64_fetch_or(i, v);
 }
 
+/**
+ * atomic64_fetch_or_acquire() - atomic bitwise OR with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_or_acquire(i, v);
+	return raw_atomic64_fetch_or_acquire(i, v);
 }
 
+/**
+ * atomic64_fetch_or_release() - atomic bitwise OR with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_or_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_or_release(i, v);
+	return raw_atomic64_fetch_or_release(i, v);
 }
 
+/**
+ * atomic64_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_or_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_or_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_or_relaxed(i, v);
+	return raw_atomic64_fetch_or_relaxed(i, v);
 }
 
+/**
+ * atomic64_xor() - atomic bitwise XOR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_xor() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic64_xor(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic64_xor(i, v);
+	raw_atomic64_xor(i, v);
 }
 
+/**
+ * atomic64_fetch_xor() - atomic bitwise XOR with full ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_xor(i, v);
+	return raw_atomic64_fetch_xor(i, v);
 }
 
+/**
+ * atomic64_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_xor_acquire(i, v);
+	return raw_atomic64_fetch_xor_acquire(i, v);
 }
 
+/**
+ * atomic64_fetch_xor_release() - atomic bitwise XOR with release ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_xor_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_xor_release(i, v);
+	return raw_atomic64_fetch_xor_release(i, v);
 }
 
+/**
+ * atomic64_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
+ * @i: s64 value
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_xor_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_xor_relaxed(i, v);
+	return raw_atomic64_fetch_xor_relaxed(i, v);
 }
 
+/**
+ * atomic64_xchg() - atomic exchange with full ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_xchg() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-atomic64_xchg(atomic64_t *v, s64 i)
+atomic64_xchg(atomic64_t *v, s64 new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_xchg(v, i);
+	return raw_atomic64_xchg(v, new);
 }
 
+/**
+ * atomic64_xchg_acquire() - atomic exchange with acquire ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_xchg_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-atomic64_xchg_acquire(atomic64_t *v, s64 i)
+atomic64_xchg_acquire(atomic64_t *v, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_xchg_acquire(v, i);
+	return raw_atomic64_xchg_acquire(v, new);
 }
 
+/**
+ * atomic64_xchg_release() - atomic exchange with release ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_xchg_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-atomic64_xchg_release(atomic64_t *v, s64 i)
+atomic64_xchg_release(atomic64_t *v, s64 new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_xchg_release(v, i);
+	return raw_atomic64_xchg_release(v, new);
 }
 
+/**
+ * atomic64_xchg_relaxed() - atomic exchange with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @new: s64 value to assign
+ *
+ * Atomically updates @v to @new with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_xchg_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
-atomic64_xchg_relaxed(atomic64_t *v, s64 i)
+atomic64_xchg_relaxed(atomic64_t *v, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_xchg_relaxed(v, i);
+	return raw_atomic64_xchg_relaxed(v, new);
 }
 
+/**
+ * atomic64_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_cmpxchg(v, old, new);
-}
-
+	return raw_atomic64_cmpxchg(v, old, new);
+}
+
+/**
+ * atomic64_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_cmpxchg_acquire(v, old, new);
+	return raw_atomic64_cmpxchg_acquire(v, old, new);
 }
 
+/**
+ * atomic64_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_cmpxchg_release(v, old, new);
-}
-
+	return raw_atomic64_cmpxchg_release(v, old, new);
+}
+
+/**
+ * atomic64_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @old: s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_cmpxchg_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_cmpxchg_relaxed(v, old, new);
+	return raw_atomic64_cmpxchg_relaxed(v, old, new);
 }
 
+/**
+ * atomic64_try_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic64_try_cmpxchg(v, old, new);
-}
-
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic64_try_cmpxchg(v, old, new);
+}
+
+/**
+ * atomic64_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_acquire() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic64_try_cmpxchg_acquire(v, old, new);
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic64_try_cmpxchg_acquire(v, old, new);
 }
 
+/**
+ * atomic64_try_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_release() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic64_try_cmpxchg_release(v, old, new);
-}
-
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic64_try_cmpxchg_release(v, old, new);
+}
+
+/**
+ * atomic64_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic64_t
+ * @old: pointer to s64 value to compare with
+ * @new: s64 value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_try_cmpxchg_relaxed() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic64_try_cmpxchg_relaxed(v, old, new);
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic64_try_cmpxchg_relaxed(v, old, new);
 }
 
+/**
+ * atomic64_sub_and_test() - atomic subtract and test if zero with full ordering
+ * @i: s64 value to subtract
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_sub_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_sub_and_test(i, v);
+	return raw_atomic64_sub_and_test(i, v);
 }
 
+/**
+ * atomic64_dec_and_test() - atomic decrement and test if zero with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic64_dec_and_test(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_and_test(v);
+	return raw_atomic64_dec_and_test(v);
 }
 
+/**
+ * atomic64_inc_and_test() - atomic increment and test if zero with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic64_inc_and_test(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_and_test(v);
+	return raw_atomic64_inc_and_test(v);
 }
 
+/**
+ * atomic64_add_negative() - atomic add and test if negative with full ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_negative() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_negative(i, v);
+	return raw_atomic64_add_negative(i, v);
 }
 
+/**
+ * atomic64_add_negative_acquire() - atomic add and test if negative with acquire ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_negative_acquire() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic64_add_negative_acquire(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_negative_acquire(i, v);
+	return raw_atomic64_add_negative_acquire(i, v);
 }
 
+/**
+ * atomic64_add_negative_release() - atomic add and test if negative with release ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_negative_release() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic64_add_negative_release(s64 i, atomic64_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_negative_release(i, v);
+	return raw_atomic64_add_negative_release(i, v);
 }
 
+/**
+ * atomic64_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
+ * @i: s64 value to add
+ * @v: pointer to atomic64_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_negative_relaxed() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic64_add_negative_relaxed(s64 i, atomic64_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_negative_relaxed(i, v);
+	return raw_atomic64_add_negative_relaxed(i, v);
 }
 
+/**
+ * atomic64_fetch_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic64_t
+ * @a: s64 value to add
+ * @u: s64 value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_fetch_add_unless() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline s64
 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_fetch_add_unless(v, a, u);
-}
-
+	return raw_atomic64_fetch_add_unless(v, a, u);
+}
+
+/**
+ * atomic64_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic64_t
+ * @a: s64 value to add
+ * @u: s64 value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_add_unless() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_add_unless(v, a, u);
+	return raw_atomic64_add_unless(v, a, u);
 }
 
+/**
+ * atomic64_inc_not_zero() - atomic increment unless zero with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_not_zero() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic64_inc_not_zero(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_not_zero(v);
+	return raw_atomic64_inc_not_zero(v);
 }
 
+/**
+ * atomic64_inc_unless_negative() - atomic increment unless negative with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_inc_unless_negative() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic64_inc_unless_negative(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_inc_unless_negative(v);
+	return raw_atomic64_inc_unless_negative(v);
 }
 
+/**
+ * atomic64_dec_unless_positive() - atomic decrement unless positive with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_unless_positive() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic64_dec_unless_positive(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_unless_positive(v);
+	return raw_atomic64_dec_unless_positive(v);
 }
 
+/**
+ * atomic64_dec_if_positive() - atomic decrement if positive with full ordering
+ * @v: pointer to atomic64_t
+ *
+ * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic64_dec_if_positive() there.
+ *
+ * Return: The old value of (@v - 1), regardless of whether @v was updated.
+ */
 static __always_inline s64
 atomic64_dec_if_positive(atomic64_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic64_dec_if_positive(v);
+	return raw_atomic64_dec_if_positive(v);
 }
 
+/**
+ * atomic_long_read() - atomic load with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically loads the value of @v with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_read() there.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline long
 atomic_long_read(const atomic_long_t *v)
 {
 	instrument_atomic_read(v, sizeof(*v));
-	return arch_atomic_long_read(v);
-}
-
+	return raw_atomic_long_read(v);
+}
+
+/**
+ * atomic_long_read_acquire() - atomic load with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically loads the value of @v with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_read_acquire() there.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline long
 atomic_long_read_acquire(const atomic_long_t *v)
 {
 	instrument_atomic_read(v, sizeof(*v));
-	return arch_atomic_long_read_acquire(v);
-}
-
+	return raw_atomic_long_read_acquire(v);
+}
+
+/**
+ * atomic_long_set() - atomic set with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @i: long value to assign
+ *
+ * Atomically sets @v to @i with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_set() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_set(atomic_long_t *v, long i)
 {
 	instrument_atomic_write(v, sizeof(*v));
-	arch_atomic_long_set(v, i);
-}
-
+	raw_atomic_long_set(v, i);
+}
+
+/**
+ * atomic_long_set_release() - atomic set with release ordering
+ * @v: pointer to atomic_long_t
+ * @i: long value to assign
+ *
+ * Atomically sets @v to @i with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_set_release() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_set_release(atomic_long_t *v, long i)
 {
 	kcsan_release();
 	instrument_atomic_write(v, sizeof(*v));
-	arch_atomic_long_set_release(v, i);
-}
-
+	raw_atomic_long_set_release(v, i);
+}
+
+/**
+ * atomic_long_add() - atomic add with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_add(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_add(i, v);
+	raw_atomic_long_add(i, v);
 }
 
+/**
+ * atomic_long_add_return() - atomic add with full ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_add_return(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_return(i, v);
+	return raw_atomic_long_add_return(i, v);
 }
 
+/**
+ * atomic_long_add_return_acquire() - atomic add with acquire ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_add_return_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_return_acquire(i, v);
+	return raw_atomic_long_add_return_acquire(i, v);
 }
 
+/**
+ * atomic_long_add_return_release() - atomic add with release ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_add_return_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_return_release(i, v);
+	return raw_atomic_long_add_return_release(i, v);
 }
 
+/**
+ * atomic_long_add_return_relaxed() - atomic add with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_add_return_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_return_relaxed(i, v);
+	return raw_atomic_long_add_return_relaxed(i, v);
 }
 
+/**
+ * atomic_long_fetch_add() - atomic add with full ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_add(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_add(i, v);
+	return raw_atomic_long_fetch_add(i, v);
 }
 
+/**
+ * atomic_long_fetch_add_acquire() - atomic add with acquire ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_add_acquire(i, v);
+	return raw_atomic_long_fetch_add_acquire(i, v);
 }
 
+/**
+ * atomic_long_fetch_add_release() - atomic add with release ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_add_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_add_release(i, v);
+	return raw_atomic_long_fetch_add_release(i, v);
 }
 
+/**
+ * atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_add_relaxed(i, v);
+	return raw_atomic_long_fetch_add_relaxed(i, v);
 }
 
+/**
+ * atomic_long_sub() - atomic subtract with relaxed ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_sub() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_sub(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_sub(i, v);
+	raw_atomic_long_sub(i, v);
 }
 
+/**
+ * atomic_long_sub_return() - atomic subtract with full ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_sub_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_sub_return(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_sub_return(i, v);
+	return raw_atomic_long_sub_return(i, v);
 }
 
+/**
+ * atomic_long_sub_return_acquire() - atomic subtract with acquire ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_sub_return_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_sub_return_acquire(i, v);
+	return raw_atomic_long_sub_return_acquire(i, v);
 }
 
+/**
+ * atomic_long_sub_return_release() - atomic subtract with release ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_sub_return_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_sub_return_release(i, v);
+	return raw_atomic_long_sub_return_release(i, v);
 }
 
+/**
+ * atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_sub_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_sub_return_relaxed(i, v);
+	return raw_atomic_long_sub_return_relaxed(i, v);
 }
 
+/**
+ * atomic_long_fetch_sub() - atomic subtract with full ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_sub(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_sub(i, v);
+	return raw_atomic_long_fetch_sub(i, v);
 }
 
+/**
+ * atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_sub_acquire(i, v);
+	return raw_atomic_long_fetch_sub_acquire(i, v);
 }
 
+/**
+ * atomic_long_fetch_sub_release() - atomic subtract with release ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_sub_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_sub_release(i, v);
+	return raw_atomic_long_fetch_sub_release(i, v);
 }
 
+/**
+ * atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_sub_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_sub_relaxed(i, v);
+	return raw_atomic_long_fetch_sub_relaxed(i, v);
 }
 
+/**
+ * atomic_long_inc() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_inc(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_inc(v);
+	raw_atomic_long_inc(v);
 }
 
+/**
+ * atomic_long_inc_return() - atomic increment with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_inc_return(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_return(v);
+	return raw_atomic_long_inc_return(v);
 }
 
+/**
+ * atomic_long_inc_return_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_inc_return_acquire(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_return_acquire(v);
+	return raw_atomic_long_inc_return_acquire(v);
 }
 
+/**
+ * atomic_long_inc_return_release() - atomic increment with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_inc_return_release(atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_return_release(v);
+	return raw_atomic_long_inc_return_release(v);
 }
 
+/**
+ * atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_inc_return_relaxed(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_return_relaxed(v);
+	return raw_atomic_long_inc_return_relaxed(v);
 }
 
+/**
+ * atomic_long_fetch_inc() - atomic increment with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_inc(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_inc(v);
+	return raw_atomic_long_fetch_inc(v);
 }
 
+/**
+ * atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_inc_acquire(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_inc_acquire(v);
+	return raw_atomic_long_fetch_inc_acquire(v);
 }
 
+/**
+ * atomic_long_fetch_inc_release() - atomic increment with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_inc_release(atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_inc_release(v);
+	return raw_atomic_long_fetch_inc_release(v);
 }
 
+/**
+ * atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_inc_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_inc_relaxed(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_inc_relaxed(v);
+	return raw_atomic_long_fetch_inc_relaxed(v);
 }
 
+/**
+ * atomic_long_dec() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_dec(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_dec(v);
+	raw_atomic_long_dec(v);
 }
 
+/**
+ * atomic_long_dec_return() - atomic decrement with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_return() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_dec_return(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_return(v);
+	return raw_atomic_long_dec_return(v);
 }
 
+/**
+ * atomic_long_dec_return_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_acquire() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_dec_return_acquire(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_return_acquire(v);
+	return raw_atomic_long_dec_return_acquire(v);
 }
 
+/**
+ * atomic_long_dec_return_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_release() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_dec_return_release(atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_return_release(v);
+	return raw_atomic_long_dec_return_release(v);
 }
 
+/**
+ * atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_return_relaxed() there.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
 atomic_long_dec_return_relaxed(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_return_relaxed(v);
+	return raw_atomic_long_dec_return_relaxed(v);
 }
 
+/**
+ * atomic_long_fetch_dec() - atomic decrement with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_dec(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_dec(v);
+	return raw_atomic_long_fetch_dec(v);
 }
 
+/**
+ * atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_dec_acquire(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_dec_acquire(v);
+	return raw_atomic_long_fetch_dec_acquire(v);
 }
 
+/**
+ * atomic_long_fetch_dec_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_dec_release(atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_dec_release(v);
+	return raw_atomic_long_fetch_dec_release(v);
 }
 
+/**
+ * atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_dec_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_dec_relaxed(atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_dec_relaxed(v);
+	return raw_atomic_long_fetch_dec_relaxed(v);
 }
 
+/**
+ * atomic_long_and() - atomic bitwise AND with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_and() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_and(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_and(i, v);
+	raw_atomic_long_and(i, v);
 }
 
+/**
+ * atomic_long_fetch_and() - atomic bitwise AND with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_and(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_and(i, v);
+	return raw_atomic_long_fetch_and(i, v);
 }
 
+/**
+ * atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_and_acquire(i, v);
+	return raw_atomic_long_fetch_and_acquire(i, v);
 }
 
+/**
+ * atomic_long_fetch_and_release() - atomic bitwise AND with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_and_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_and_release(i, v);
+	return raw_atomic_long_fetch_and_release(i, v);
 }
 
+/**
+ * atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_and_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_and_relaxed(i, v);
+	return raw_atomic_long_fetch_and_relaxed(i, v);
 }
 
+/**
+ * atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_andnot() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_andnot(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_andnot(i, v);
+	raw_atomic_long_andnot(i, v);
 }
 
+/**
+ * atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_andnot(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_andnot(i, v);
+	return raw_atomic_long_fetch_andnot(i, v);
 }
 
+/**
+ * atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_andnot_acquire(i, v);
+	return raw_atomic_long_fetch_andnot_acquire(i, v);
 }
 
+/**
+ * atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_andnot_release(i, v);
+	return raw_atomic_long_fetch_andnot_release(i, v);
 }
 
+/**
+ * atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_andnot_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_andnot_relaxed(i, v);
+	return raw_atomic_long_fetch_andnot_relaxed(i, v);
 }
 
+/**
+ * atomic_long_or() - atomic bitwise OR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_or() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_or(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_or(i, v);
+	raw_atomic_long_or(i, v);
 }
 
+/**
+ * atomic_long_fetch_or() - atomic bitwise OR with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_or(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_or(i, v);
+	return raw_atomic_long_fetch_or(i, v);
 }
 
+/**
+ * atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_or_acquire(i, v);
+	return raw_atomic_long_fetch_or_acquire(i, v);
 }
 
+/**
+ * atomic_long_fetch_or_release() - atomic bitwise OR with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_or_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_or_release(i, v);
+	return raw_atomic_long_fetch_or_release(i, v);
 }
 
+/**
+ * atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_or_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_or_relaxed(i, v);
+	return raw_atomic_long_fetch_or_relaxed(i, v);
 }
 
+/**
+ * atomic_long_xor() - atomic bitwise XOR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_xor() there.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
 atomic_long_xor(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	arch_atomic_long_xor(i, v);
+	raw_atomic_long_xor(i, v);
 }
 
+/**
+ * atomic_long_fetch_xor() - atomic bitwise XOR with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_xor(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_xor(i, v);
+	return raw_atomic_long_fetch_xor(i, v);
 }
 
+/**
+ * atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_xor_acquire(i, v);
+	return raw_atomic_long_fetch_xor_acquire(i, v);
 }
 
+/**
+ * atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_xor_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_xor_release(i, v);
+	return raw_atomic_long_fetch_xor_release(i, v);
 }
 
+/**
+ * atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_xor_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_xor_relaxed(i, v);
+	return raw_atomic_long_fetch_xor_relaxed(i, v);
 }
 
+/**
+ * atomic_long_xchg() - atomic exchange with full ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_xchg() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-atomic_long_xchg(atomic_long_t *v, long i)
+atomic_long_xchg(atomic_long_t *v, long new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_xchg(v, i);
+	return raw_atomic_long_xchg(v, new);
 }
 
+/**
+ * atomic_long_xchg_acquire() - atomic exchange with acquire ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_xchg_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-atomic_long_xchg_acquire(atomic_long_t *v, long i)
+atomic_long_xchg_acquire(atomic_long_t *v, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_xchg_acquire(v, i);
+	return raw_atomic_long_xchg_acquire(v, new);
 }
 
+/**
+ * atomic_long_xchg_release() - atomic exchange with release ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_xchg_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-atomic_long_xchg_release(atomic_long_t *v, long i)
+atomic_long_xchg_release(atomic_long_t *v, long new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_xchg_release(v, i);
+	return raw_atomic_long_xchg_release(v, new);
 }
 
+/**
+ * atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_xchg_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-atomic_long_xchg_relaxed(atomic_long_t *v, long i)
+atomic_long_xchg_relaxed(atomic_long_t *v, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_xchg_relaxed(v, i);
+	return raw_atomic_long_xchg_relaxed(v, new);
 }
 
+/**
+ * atomic_long_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_cmpxchg(v, old, new);
-}
-
+	return raw_atomic_long_cmpxchg(v, old, new);
+}
+
+/**
+ * atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_acquire() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_cmpxchg_acquire(v, old, new);
+	return raw_atomic_long_cmpxchg_acquire(v, old, new);
 }
 
+/**
+ * atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_release() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_cmpxchg_release(v, old, new);
-}
-
+	return raw_atomic_long_cmpxchg_release(v, old, new);
+}
+
+/**
+ * atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_cmpxchg_relaxed() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_cmpxchg_relaxed(v, old, new);
+	return raw_atomic_long_cmpxchg_relaxed(v, old, new);
 }
 
+/**
+ * atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_long_try_cmpxchg(v, old, new);
-}
-
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_long_try_cmpxchg(v, old, new);
+}
+
+/**
+ * atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_acquire() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_long_try_cmpxchg_acquire(v, old, new);
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_long_try_cmpxchg_acquire(v, old, new);
 }
 
+/**
+ * atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_release() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_long_try_cmpxchg_release(v, old, new);
-}
-
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_long_try_cmpxchg_release(v, old, new);
+}
+
+/**
+ * atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_try_cmpxchg_relaxed() there.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	instrument_atomic_read_write(old, sizeof(*old));
-	return arch_atomic_long_try_cmpxchg_relaxed(v, old, new);
+	instrument_read_write(old, sizeof(*old));
+	return raw_atomic_long_try_cmpxchg_relaxed(v, old, new);
 }
 
+/**
+ * atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_sub_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_sub_and_test(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_sub_and_test(i, v);
+	return raw_atomic_long_sub_and_test(i, v);
 }
 
+/**
+ * atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_dec_and_test(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_and_test(v);
+	return raw_atomic_long_dec_and_test(v);
 }
 
+/**
+ * atomic_long_inc_and_test() - atomic increment and test if zero with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_and_test() there.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_inc_and_test(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_and_test(v);
+	return raw_atomic_long_inc_and_test(v);
 }
 
+/**
+ * atomic_long_add_negative() - atomic add and test if negative with full ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_negative() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_add_negative(long i, atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_negative(i, v);
+	return raw_atomic_long_add_negative(i, v);
 }
 
+/**
+ * atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_acquire() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_add_negative_acquire(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_negative_acquire(i, v);
+	return raw_atomic_long_add_negative_acquire(i, v);
 }
 
+/**
+ * atomic_long_add_negative_release() - atomic add and test if negative with release ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_release() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_add_negative_release(long i, atomic_long_t *v)
 {
 	kcsan_release();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_negative_release(i, v);
+	return raw_atomic_long_add_negative_release(i, v);
 }
 
+/**
+ * atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_negative_relaxed() there.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
 {
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_negative_relaxed(i, v);
+	return raw_atomic_long_add_negative_relaxed(i, v);
 }
 
+/**
+ * atomic_long_fetch_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_long_t
+ * @a: long value to add
+ * @u: long value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_fetch_add_unless() there.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
 atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_fetch_add_unless(v, a, u);
-}
-
+	return raw_atomic_long_fetch_add_unless(v, a, u);
+}
+
+/**
+ * atomic_long_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_long_t
+ * @a: long value to add
+ * @u: long value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_add_unless() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_add_unless(atomic_long_t *v, long a, long u)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_add_unless(v, a, u);
+	return raw_atomic_long_add_unless(v, a, u);
 }
 
+/**
+ * atomic_long_inc_not_zero() - atomic increment unless zero with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_not_zero() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_inc_not_zero(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_not_zero(v);
+	return raw_atomic_long_inc_not_zero(v);
 }
 
+/**
+ * atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_inc_unless_negative() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_inc_unless_negative(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_inc_unless_negative(v);
+	return raw_atomic_long_inc_unless_negative(v);
 }
 
+/**
+ * atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_unless_positive() there.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
 atomic_long_dec_unless_positive(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_unless_positive(v);
+	return raw_atomic_long_dec_unless_positive(v);
 }
 
+/**
+ * atomic_long_dec_if_positive() - atomic decrement if positive with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Unsafe to use in noinstr code; use raw_atomic_long_dec_if_positive() there.
+ *
+ * Return: The old value of (@v - 1), regardless of whether @v was updated.
+ */
 static __always_inline long
 atomic_long_dec_if_positive(atomic_long_t *v)
 {
 	kcsan_mb();
 	instrument_atomic_read_write(v, sizeof(*v));
-	return arch_atomic_long_dec_if_positive(v);
+	return raw_atomic_long_dec_if_positive(v);
 }
 
 #define xchg(ptr, ...) \
@@ -1949,14 +4755,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_xchg(__ai_ptr, __VA_ARGS__); \
+	raw_xchg(__ai_ptr, __VA_ARGS__); \
 })
 
 #define xchg_acquire(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_xchg_acquire(__ai_ptr, __VA_ARGS__); \
+	raw_xchg_acquire(__ai_ptr, __VA_ARGS__); \
 })
 
 #define xchg_release(ptr, ...) \
@@ -1964,14 +4770,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_release(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_xchg_release(__ai_ptr, __VA_ARGS__); \
+	raw_xchg_release(__ai_ptr, __VA_ARGS__); \
 })
 
 #define xchg_relaxed(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_xchg_relaxed(__ai_ptr, __VA_ARGS__); \
+	raw_xchg_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg(ptr, ...) \
@@ -1979,14 +4785,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg_acquire(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg_acquire(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg_release(ptr, ...) \
@@ -1994,14 +4800,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_release(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg_release(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg_relaxed(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64(ptr, ...) \
@@ -2009,14 +4815,14 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg64(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_acquire(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg64_acquire(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_release(ptr, ...) \
@@ -2024,14 +4830,44 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_release(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_relaxed(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg64_relaxed(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	kcsan_mb(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	raw_cmpxchg128(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_acquire(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	raw_cmpxchg128_acquire(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_release(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	kcsan_release(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	raw_cmpxchg128_release(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_relaxed(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	raw_cmpxchg128_relaxed(__ai_ptr, __VA_ARGS__); \
 })
 
 #define try_cmpxchg(ptr, oldp, ...) \
@@ -2041,7 +4877,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	kcsan_mb(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg_acquire(ptr, oldp, ...) \
@@ -2050,7 +4886,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(oldp) __ai_oldp = (oldp); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg_release(ptr, oldp, ...) \
@@ -2060,7 +4896,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	kcsan_release(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg_relaxed(ptr, oldp, ...) \
@@ -2069,7 +4905,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(oldp) __ai_oldp = (oldp); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg64(ptr, oldp, ...) \
@@ -2079,7 +4915,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	kcsan_mb(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg64(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg64_acquire(ptr, oldp, ...) \
@@ -2088,7 +4924,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(oldp) __ai_oldp = (oldp); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg64_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg64_release(ptr, oldp, ...) \
@@ -2098,7 +4934,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	kcsan_release(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg64_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg64_relaxed(ptr, oldp, ...) \
@@ -2107,21 +4943,66 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(oldp) __ai_oldp = (oldp); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg64_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	kcsan_mb(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	raw_try_cmpxchg128(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128_acquire(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	raw_try_cmpxchg128_acquire(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128_release(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	kcsan_release(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	raw_try_cmpxchg128_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+})
+
+#define try_cmpxchg128_relaxed(ptr, oldp, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	raw_try_cmpxchg128_relaxed(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define cmpxchg_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg_local(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg_local(__ai_ptr, __VA_ARGS__); \
 })
 
 #define cmpxchg64_local(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \
+	raw_cmpxchg64_local(__ai_ptr, __VA_ARGS__); \
+})
+
+#define cmpxchg128_local(ptr, ...) \
+({ \
+	typeof(ptr) __ai_ptr = (ptr); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	raw_cmpxchg128_local(__ai_ptr, __VA_ARGS__); \
 })
 
 #define sync_cmpxchg(ptr, ...) \
@@ -2129,7 +5010,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(ptr) __ai_ptr = (ptr); \
 	kcsan_mb(); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
-	arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \
+	raw_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 
 #define try_cmpxchg_local(ptr, oldp, ...) \
@@ -2138,7 +5019,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(oldp) __ai_oldp = (oldp); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
 #define try_cmpxchg64_local(ptr, oldp, ...) \
@@ -2147,24 +5028,26 @@ atomic_long_dec_if_positive(atomic_long_t *v)
 	typeof(oldp) __ai_oldp = (oldp); \
 	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
 	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
-	arch_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
+	raw_try_cmpxchg64_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
-#define cmpxchg_double(ptr, ...) \
+#define try_cmpxchg128_local(ptr, oldp, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	kcsan_mb(); \
-	instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
-	arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \
+	typeof(oldp) __ai_oldp = (oldp); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	instrument_read_write(__ai_oldp, sizeof(*__ai_oldp)); \
+	raw_try_cmpxchg128_local(__ai_ptr, __ai_oldp, __VA_ARGS__); \
 })
 
-
-#define cmpxchg_double_local(ptr, ...) \
+#define sync_try_cmpxchg(ptr, ...) \
 ({ \
 	typeof(ptr) __ai_ptr = (ptr); \
-	instrument_atomic_read_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
-	arch_cmpxchg_double_local(__ai_ptr, __VA_ARGS__); \
+	kcsan_mb(); \
+	instrument_atomic_read_write(__ai_ptr, sizeof(*__ai_ptr)); \
+	raw_sync_try_cmpxchg(__ai_ptr, __VA_ARGS__); \
 })
 
+
 #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 6b513a42e1a1b5962532a019b7fc91eaa044ad5e
+// f618ac667f868941a84ce0ab2242f1786e049ed4
diff --git a/include/linux/atomic/atomic-long.h b/include/linux/atomic/atomic-long.h
index 2fc51ba66beb..f86b29d90877 100644
--- a/include/linux/atomic/atomic-long.h
+++ b/include/linux/atomic/atomic-long.h
@@ -21,1030 +21,1792 @@ typedef atomic_t atomic_long_t;
 #define atomic_long_cond_read_relaxed	atomic_cond_read_relaxed
 #endif
 
-#ifdef CONFIG_64BIT
-
-static __always_inline long
-arch_atomic_long_read(const atomic_long_t *v)
-{
-	return arch_atomic64_read(v);
-}
-
-static __always_inline long
-arch_atomic_long_read_acquire(const atomic_long_t *v)
-{
-	return arch_atomic64_read_acquire(v);
-}
-
-static __always_inline void
-arch_atomic_long_set(atomic_long_t *v, long i)
-{
-	arch_atomic64_set(v, i);
-}
-
-static __always_inline void
-arch_atomic_long_set_release(atomic_long_t *v, long i)
-{
-	arch_atomic64_set_release(v, i);
-}
-
-static __always_inline void
-arch_atomic_long_add(long i, atomic_long_t *v)
-{
-	arch_atomic64_add(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_add_return(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_return(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_add_return_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_return_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_add_return_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_return_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_return_relaxed(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_add(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_add(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_add_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_add_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_add_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_add_relaxed(i, v);
-}
-
-static __always_inline void
-arch_atomic_long_sub(long i, atomic_long_t *v)
-{
-	arch_atomic64_sub(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_sub_return(long i, atomic_long_t *v)
-{
-	return arch_atomic64_sub_return(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_sub_return_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_sub_return_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_sub_return_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_sub_return_relaxed(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_sub(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_sub(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_sub_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_sub_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_sub_relaxed(i, v);
-}
-
-static __always_inline void
-arch_atomic_long_inc(atomic_long_t *v)
-{
-	arch_atomic64_inc(v);
-}
-
-static __always_inline long
-arch_atomic_long_inc_return(atomic_long_t *v)
-{
-	return arch_atomic64_inc_return(v);
-}
-
-static __always_inline long
-arch_atomic_long_inc_return_acquire(atomic_long_t *v)
-{
-	return arch_atomic64_inc_return_acquire(v);
-}
-
-static __always_inline long
-arch_atomic_long_inc_return_release(atomic_long_t *v)
-{
-	return arch_atomic64_inc_return_release(v);
-}
-
-static __always_inline long
-arch_atomic_long_inc_return_relaxed(atomic_long_t *v)
-{
-	return arch_atomic64_inc_return_relaxed(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_inc(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_inc(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_inc_acquire(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_inc_acquire(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_inc_release(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_inc_release(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_inc_relaxed(v);
-}
-
-static __always_inline void
-arch_atomic_long_dec(atomic_long_t *v)
-{
-	arch_atomic64_dec(v);
-}
-
-static __always_inline long
-arch_atomic_long_dec_return(atomic_long_t *v)
-{
-	return arch_atomic64_dec_return(v);
-}
-
-static __always_inline long
-arch_atomic_long_dec_return_acquire(atomic_long_t *v)
-{
-	return arch_atomic64_dec_return_acquire(v);
-}
-
-static __always_inline long
-arch_atomic_long_dec_return_release(atomic_long_t *v)
-{
-	return arch_atomic64_dec_return_release(v);
-}
-
-static __always_inline long
-arch_atomic_long_dec_return_relaxed(atomic_long_t *v)
-{
-	return arch_atomic64_dec_return_relaxed(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_dec(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_dec(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_dec_acquire(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_dec_acquire(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_dec_release(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_dec_release(v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v)
-{
-	return arch_atomic64_fetch_dec_relaxed(v);
-}
-
-static __always_inline void
-arch_atomic_long_and(long i, atomic_long_t *v)
-{
-	arch_atomic64_and(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_and(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_and(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_and_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_and_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_and_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_and_relaxed(i, v);
-}
-
-static __always_inline void
-arch_atomic_long_andnot(long i, atomic_long_t *v)
-{
-	arch_atomic64_andnot(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_andnot(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_andnot(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_andnot_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_andnot_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_andnot_relaxed(i, v);
-}
-
-static __always_inline void
-arch_atomic_long_or(long i, atomic_long_t *v)
-{
-	arch_atomic64_or(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_or(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_or(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_or_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_or_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_or_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_or_relaxed(i, v);
-}
-
-static __always_inline void
-arch_atomic_long_xor(long i, atomic_long_t *v)
-{
-	arch_atomic64_xor(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_xor(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_xor(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_xor_acquire(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_xor_release(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_fetch_xor_relaxed(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_xchg(atomic_long_t *v, long i)
-{
-	return arch_atomic64_xchg(v, i);
-}
-
-static __always_inline long
-arch_atomic_long_xchg_acquire(atomic_long_t *v, long i)
-{
-	return arch_atomic64_xchg_acquire(v, i);
-}
-
-static __always_inline long
-arch_atomic_long_xchg_release(atomic_long_t *v, long i)
-{
-	return arch_atomic64_xchg_release(v, i);
-}
-
-static __always_inline long
-arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i)
-{
-	return arch_atomic64_xchg_relaxed(v, i);
-}
-
-static __always_inline long
-arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
-{
-	return arch_atomic64_cmpxchg(v, old, new);
-}
-
-static __always_inline long
-arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
+/**
+ * raw_atomic_long_read() - atomic load with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically loads the value of @v with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_read() elsewhere.
+ *
+ * Return: The value loaded from @v.
+ */
+static __always_inline long
+raw_atomic_long_read(const atomic_long_t *v)
 {
-	return arch_atomic64_cmpxchg_acquire(v, old, new);
-}
-
-static __always_inline long
-arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
-{
-	return arch_atomic64_cmpxchg_release(v, old, new);
-}
-
-static __always_inline long
-arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
-{
-	return arch_atomic64_cmpxchg_relaxed(v, old, new);
-}
-
-static __always_inline bool
-arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
-{
-	return arch_atomic64_try_cmpxchg(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
-{
-	return arch_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
-{
-	return arch_atomic64_try_cmpxchg_release(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
-{
-	return arch_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new);
-}
-
-static __always_inline bool
-arch_atomic_long_sub_and_test(long i, atomic_long_t *v)
-{
-	return arch_atomic64_sub_and_test(i, v);
-}
-
-static __always_inline bool
-arch_atomic_long_dec_and_test(atomic_long_t *v)
-{
-	return arch_atomic64_dec_and_test(v);
-}
-
-static __always_inline bool
-arch_atomic_long_inc_and_test(atomic_long_t *v)
-{
-	return arch_atomic64_inc_and_test(v);
-}
-
-static __always_inline bool
-arch_atomic_long_add_negative(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_negative(i, v);
-}
-
-static __always_inline bool
-arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_negative_acquire(i, v);
-}
-
-static __always_inline bool
-arch_atomic_long_add_negative_release(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_negative_release(i, v);
-}
-
-static __always_inline bool
-arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
-{
-	return arch_atomic64_add_negative_relaxed(i, v);
-}
-
-static __always_inline long
-arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
-{
-	return arch_atomic64_fetch_add_unless(v, a, u);
-}
-
-static __always_inline bool
-arch_atomic_long_add_unless(atomic_long_t *v, long a, long u)
-{
-	return arch_atomic64_add_unless(v, a, u);
-}
-
-static __always_inline bool
-arch_atomic_long_inc_not_zero(atomic_long_t *v)
-{
-	return arch_atomic64_inc_not_zero(v);
-}
-
-static __always_inline bool
-arch_atomic_long_inc_unless_negative(atomic_long_t *v)
-{
-	return arch_atomic64_inc_unless_negative(v);
-}
-
-static __always_inline bool
-arch_atomic_long_dec_unless_positive(atomic_long_t *v)
-{
-	return arch_atomic64_dec_unless_positive(v);
-}
-
-static __always_inline long
-arch_atomic_long_dec_if_positive(atomic_long_t *v)
-{
-	return arch_atomic64_dec_if_positive(v);
-}
-
-#else /* CONFIG_64BIT */
-
-static __always_inline long
-arch_atomic_long_read(const atomic_long_t *v)
-{
-	return arch_atomic_read(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_read(v);
+#else
+	return raw_atomic_read(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_read_acquire() - atomic load with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically loads the value of @v with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_read_acquire() elsewhere.
+ *
+ * Return: The value loaded from @v.
+ */
 static __always_inline long
-arch_atomic_long_read_acquire(const atomic_long_t *v)
+raw_atomic_long_read_acquire(const atomic_long_t *v)
 {
-	return arch_atomic_read_acquire(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_read_acquire(v);
+#else
+	return raw_atomic_read_acquire(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_set() - atomic set with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @i: long value to assign
+ *
+ * Atomically sets @v to @i with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_set() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_set(atomic_long_t *v, long i)
+raw_atomic_long_set(atomic_long_t *v, long i)
 {
-	arch_atomic_set(v, i);
+#ifdef CONFIG_64BIT
+	raw_atomic64_set(v, i);
+#else
+	raw_atomic_set(v, i);
+#endif
 }
 
+/**
+ * raw_atomic_long_set_release() - atomic set with release ordering
+ * @v: pointer to atomic_long_t
+ * @i: long value to assign
+ *
+ * Atomically sets @v to @i with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_set_release() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_set_release(atomic_long_t *v, long i)
+raw_atomic_long_set_release(atomic_long_t *v, long i)
 {
-	arch_atomic_set_release(v, i);
+#ifdef CONFIG_64BIT
+	raw_atomic64_set_release(v, i);
+#else
+	raw_atomic_set_release(v, i);
+#endif
 }
 
+/**
+ * raw_atomic_long_add() - atomic add with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_add(long i, atomic_long_t *v)
+raw_atomic_long_add(long i, atomic_long_t *v)
 {
-	arch_atomic_add(i, v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_add(i, v);
+#else
+	raw_atomic_add(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_return() - atomic add with full ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_add_return(long i, atomic_long_t *v)
+raw_atomic_long_add_return(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_return(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_return(i, v);
+#else
+	return raw_atomic_add_return(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_return_acquire() - atomic add with acquire ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_add_return_acquire(long i, atomic_long_t *v)
+raw_atomic_long_add_return_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_return_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_return_acquire(i, v);
+#else
+	return raw_atomic_add_return_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_return_release() - atomic add with release ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_add_return_release(long i, atomic_long_t *v)
+raw_atomic_long_add_return_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_return_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_return_release(i, v);
+#else
+	return raw_atomic_add_return_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_return_relaxed() - atomic add with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_add_return_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_add_return_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_return_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_return_relaxed(i, v);
+#else
+	return raw_atomic_add_return_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_add() - atomic add with full ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_add() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_add(long i, atomic_long_t *v)
+raw_atomic_long_fetch_add(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_add(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_add(i, v);
+#else
+	return raw_atomic_fetch_add(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_add_acquire() - atomic add with acquire ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_add_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
+raw_atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_add_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_add_acquire(i, v);
+#else
+	return raw_atomic_fetch_add_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_add_release() - atomic add with release ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_add_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_add_release(long i, atomic_long_t *v)
+raw_atomic_long_fetch_add_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_add_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_add_release(i, v);
+#else
+	return raw_atomic_fetch_add_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_add_relaxed() - atomic add with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_add_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_fetch_add_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_add_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_add_relaxed(i, v);
+#else
+	return raw_atomic_fetch_add_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_sub() - atomic subtract with relaxed ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_sub() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_sub(long i, atomic_long_t *v)
+raw_atomic_long_sub(long i, atomic_long_t *v)
 {
-	arch_atomic_sub(i, v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_sub(i, v);
+#else
+	raw_atomic_sub(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_sub_return() - atomic subtract with full ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_sub_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_sub_return(long i, atomic_long_t *v)
+raw_atomic_long_sub_return(long i, atomic_long_t *v)
 {
-	return arch_atomic_sub_return(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_sub_return(i, v);
+#else
+	return raw_atomic_sub_return(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_sub_return_acquire() - atomic subtract with acquire ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_sub_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_sub_return_acquire(long i, atomic_long_t *v)
+raw_atomic_long_sub_return_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_sub_return_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_sub_return_acquire(i, v);
+#else
+	return raw_atomic_sub_return_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_sub_return_release() - atomic subtract with release ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_sub_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_sub_return_release(long i, atomic_long_t *v)
+raw_atomic_long_sub_return_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_sub_return_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_sub_return_release(i, v);
+#else
+	return raw_atomic_sub_return_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_sub_return_relaxed() - atomic subtract with relaxed ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_sub_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_sub_return_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_sub_return_relaxed(i, v);
+#else
+	return raw_atomic_sub_return_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_sub() - atomic subtract with full ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_sub() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_sub(long i, atomic_long_t *v)
+raw_atomic_long_fetch_sub(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_sub(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_sub(i, v);
+#else
+	return raw_atomic_fetch_sub(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_sub_acquire() - atomic subtract with acquire ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_sub_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
+raw_atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_sub_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_sub_acquire(i, v);
+#else
+	return raw_atomic_fetch_sub_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_sub_release() - atomic subtract with release ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_sub_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_sub_release(long i, atomic_long_t *v)
+raw_atomic_long_fetch_sub_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_sub_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_sub_release(i, v);
+#else
+	return raw_atomic_fetch_sub_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_sub_relaxed() - atomic subtract with relaxed ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_sub_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_fetch_sub_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_sub_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_sub_relaxed(i, v);
+#else
+	return raw_atomic_fetch_sub_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_inc(atomic_long_t *v)
+raw_atomic_long_inc(atomic_long_t *v)
 {
-	arch_atomic_inc(v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_inc(v);
+#else
+	raw_atomic_inc(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_return() - atomic increment with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_inc_return(atomic_long_t *v)
+raw_atomic_long_inc_return(atomic_long_t *v)
 {
-	return arch_atomic_inc_return(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_return(v);
+#else
+	return raw_atomic_inc_return(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_return_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_inc_return_acquire(atomic_long_t *v)
+raw_atomic_long_inc_return_acquire(atomic_long_t *v)
 {
-	return arch_atomic_inc_return_acquire(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_return_acquire(v);
+#else
+	return raw_atomic_inc_return_acquire(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_return_release() - atomic increment with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_inc_return_release(atomic_long_t *v)
+raw_atomic_long_inc_return_release(atomic_long_t *v)
 {
-	return arch_atomic_inc_return_release(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_return_release(v);
+#else
+	return raw_atomic_inc_return_release(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_return_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_inc_return_relaxed(atomic_long_t *v)
+raw_atomic_long_inc_return_relaxed(atomic_long_t *v)
 {
-	return arch_atomic_inc_return_relaxed(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_return_relaxed(v);
+#else
+	return raw_atomic_inc_return_relaxed(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_inc() - atomic increment with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_inc() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_inc(atomic_long_t *v)
+raw_atomic_long_fetch_inc(atomic_long_t *v)
 {
-	return arch_atomic_fetch_inc(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_inc(v);
+#else
+	return raw_atomic_fetch_inc(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_inc_acquire() - atomic increment with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_inc_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_inc_acquire(atomic_long_t *v)
+raw_atomic_long_fetch_inc_acquire(atomic_long_t *v)
 {
-	return arch_atomic_fetch_inc_acquire(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_inc_acquire(v);
+#else
+	return raw_atomic_fetch_inc_acquire(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_inc_release() - atomic increment with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_inc_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_inc_release(atomic_long_t *v)
+raw_atomic_long_fetch_inc_release(atomic_long_t *v)
 {
-	return arch_atomic_fetch_inc_release(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_inc_release(v);
+#else
+	return raw_atomic_fetch_inc_release(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_inc_relaxed() - atomic increment with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_inc_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_inc_relaxed(atomic_long_t *v)
+raw_atomic_long_fetch_inc_relaxed(atomic_long_t *v)
 {
-	return arch_atomic_fetch_inc_relaxed(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_inc_relaxed(v);
+#else
+	return raw_atomic_fetch_inc_relaxed(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_dec(atomic_long_t *v)
+raw_atomic_long_dec(atomic_long_t *v)
 {
-	arch_atomic_dec(v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_dec(v);
+#else
+	raw_atomic_dec(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_return() - atomic decrement with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_return() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_dec_return(atomic_long_t *v)
+raw_atomic_long_dec_return(atomic_long_t *v)
 {
-	return arch_atomic_dec_return(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_return(v);
+#else
+	return raw_atomic_dec_return(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_return_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_return_acquire() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_dec_return_acquire(atomic_long_t *v)
+raw_atomic_long_dec_return_acquire(atomic_long_t *v)
 {
-	return arch_atomic_dec_return_acquire(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_return_acquire(v);
+#else
+	return raw_atomic_dec_return_acquire(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_return_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_return_release() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_dec_return_release(atomic_long_t *v)
+raw_atomic_long_dec_return_release(atomic_long_t *v)
 {
-	return arch_atomic_dec_return_release(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_return_release(v);
+#else
+	return raw_atomic_dec_return_release(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_return_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_return_relaxed() elsewhere.
+ *
+ * Return: The updated value of @v.
+ */
 static __always_inline long
-arch_atomic_long_dec_return_relaxed(atomic_long_t *v)
+raw_atomic_long_dec_return_relaxed(atomic_long_t *v)
 {
-	return arch_atomic_dec_return_relaxed(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_return_relaxed(v);
+#else
+	return raw_atomic_dec_return_relaxed(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_dec() - atomic decrement with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_dec() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_dec(atomic_long_t *v)
+raw_atomic_long_fetch_dec(atomic_long_t *v)
 {
-	return arch_atomic_fetch_dec(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_dec(v);
+#else
+	return raw_atomic_fetch_dec(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_dec_acquire() - atomic decrement with acquire ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_dec_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_dec_acquire(atomic_long_t *v)
+raw_atomic_long_fetch_dec_acquire(atomic_long_t *v)
 {
-	return arch_atomic_fetch_dec_acquire(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_dec_acquire(v);
+#else
+	return raw_atomic_fetch_dec_acquire(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_dec_release() - atomic decrement with release ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_dec_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_dec_release(atomic_long_t *v)
+raw_atomic_long_fetch_dec_release(atomic_long_t *v)
 {
-	return arch_atomic_fetch_dec_release(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_dec_release(v);
+#else
+	return raw_atomic_fetch_dec_release(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_dec_relaxed() - atomic decrement with relaxed ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_dec_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_dec_relaxed(atomic_long_t *v)
+raw_atomic_long_fetch_dec_relaxed(atomic_long_t *v)
 {
-	return arch_atomic_fetch_dec_relaxed(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_dec_relaxed(v);
+#else
+	return raw_atomic_fetch_dec_relaxed(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_and() - atomic bitwise AND with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_and() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_and(long i, atomic_long_t *v)
+raw_atomic_long_and(long i, atomic_long_t *v)
 {
-	arch_atomic_and(i, v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_and(i, v);
+#else
+	raw_atomic_and(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_and() - atomic bitwise AND with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_and() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_and(long i, atomic_long_t *v)
+raw_atomic_long_fetch_and(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_and(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_and(i, v);
+#else
+	return raw_atomic_fetch_and(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_and_acquire() - atomic bitwise AND with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_and_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
+raw_atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_and_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_and_acquire(i, v);
+#else
+	return raw_atomic_fetch_and_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_and_release() - atomic bitwise AND with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_and_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_and_release(long i, atomic_long_t *v)
+raw_atomic_long_fetch_and_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_and_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_and_release(i, v);
+#else
+	return raw_atomic_fetch_and_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_and_relaxed() - atomic bitwise AND with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_and_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_fetch_and_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_and_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_and_relaxed(i, v);
+#else
+	return raw_atomic_fetch_and_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_andnot() - atomic bitwise AND NOT with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_andnot() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_andnot(long i, atomic_long_t *v)
+raw_atomic_long_andnot(long i, atomic_long_t *v)
 {
-	arch_atomic_andnot(i, v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_andnot(i, v);
+#else
+	raw_atomic_andnot(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_andnot() - atomic bitwise AND NOT with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_andnot() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_andnot(long i, atomic_long_t *v)
+raw_atomic_long_fetch_andnot(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_andnot(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_andnot(i, v);
+#else
+	return raw_atomic_fetch_andnot(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_andnot_acquire() - atomic bitwise AND NOT with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
+raw_atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_andnot_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_andnot_acquire(i, v);
+#else
+	return raw_atomic_fetch_andnot_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_andnot_release() - atomic bitwise AND NOT with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
+raw_atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_andnot_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_andnot_release(i, v);
+#else
+	return raw_atomic_fetch_andnot_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_andnot_relaxed() - atomic bitwise AND NOT with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v & ~@i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_andnot_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_fetch_andnot_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_andnot_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_andnot_relaxed(i, v);
+#else
+	return raw_atomic_fetch_andnot_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_or() - atomic bitwise OR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_or() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_or(long i, atomic_long_t *v)
+raw_atomic_long_or(long i, atomic_long_t *v)
 {
-	arch_atomic_or(i, v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_or(i, v);
+#else
+	raw_atomic_or(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_or() - atomic bitwise OR with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_or() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_or(long i, atomic_long_t *v)
+raw_atomic_long_fetch_or(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_or(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_or(i, v);
+#else
+	return raw_atomic_fetch_or(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_or_acquire() - atomic bitwise OR with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_or_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
+raw_atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_or_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_or_acquire(i, v);
+#else
+	return raw_atomic_fetch_or_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_or_release() - atomic bitwise OR with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_or_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_or_release(long i, atomic_long_t *v)
+raw_atomic_long_fetch_or_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_or_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_or_release(i, v);
+#else
+	return raw_atomic_fetch_or_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_or_relaxed() - atomic bitwise OR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v | @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_or_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_fetch_or_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_or_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_or_relaxed(i, v);
+#else
+	return raw_atomic_fetch_or_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_xor() - atomic bitwise XOR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_xor() elsewhere.
+ *
+ * Return: Nothing.
+ */
 static __always_inline void
-arch_atomic_long_xor(long i, atomic_long_t *v)
+raw_atomic_long_xor(long i, atomic_long_t *v)
 {
-	arch_atomic_xor(i, v);
+#ifdef CONFIG_64BIT
+	raw_atomic64_xor(i, v);
+#else
+	raw_atomic_xor(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_xor() - atomic bitwise XOR with full ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_xor() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_xor(long i, atomic_long_t *v)
+raw_atomic_long_fetch_xor(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_xor(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_xor(i, v);
+#else
+	return raw_atomic_fetch_xor(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_xor_acquire() - atomic bitwise XOR with acquire ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_xor_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
+raw_atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_xor_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_xor_acquire(i, v);
+#else
+	return raw_atomic_fetch_xor_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_xor_release() - atomic bitwise XOR with release ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_xor_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_xor_release(long i, atomic_long_t *v)
+raw_atomic_long_fetch_xor_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_xor_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_xor_release(i, v);
+#else
+	return raw_atomic_fetch_xor_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_xor_relaxed() - atomic bitwise XOR with relaxed ordering
+ * @i: long value
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v ^ @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_xor_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_fetch_xor_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_xor_relaxed(i, v);
+#else
+	return raw_atomic_fetch_xor_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_xchg() - atomic exchange with full ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_xchg() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_xchg(atomic_long_t *v, long i)
+raw_atomic_long_xchg(atomic_long_t *v, long new)
 {
-	return arch_atomic_xchg(v, i);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_xchg(v, new);
+#else
+	return raw_atomic_xchg(v, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_xchg_acquire() - atomic exchange with acquire ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_xchg_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_xchg_acquire(atomic_long_t *v, long i)
+raw_atomic_long_xchg_acquire(atomic_long_t *v, long new)
 {
-	return arch_atomic_xchg_acquire(v, i);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_xchg_acquire(v, new);
+#else
+	return raw_atomic_xchg_acquire(v, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_xchg_release() - atomic exchange with release ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_xchg_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_xchg_release(atomic_long_t *v, long i)
+raw_atomic_long_xchg_release(atomic_long_t *v, long new)
 {
-	return arch_atomic_xchg_release(v, i);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_xchg_release(v, new);
+#else
+	return raw_atomic_xchg_release(v, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_xchg_relaxed() - atomic exchange with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @new: long value to assign
+ *
+ * Atomically updates @v to @new with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_xchg_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_xchg_relaxed(atomic_long_t *v, long i)
+raw_atomic_long_xchg_relaxed(atomic_long_t *v, long new)
 {
-	return arch_atomic_xchg_relaxed(v, i);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_xchg_relaxed(v, new);
+#else
+	return raw_atomic_xchg_relaxed(v, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_cmpxchg() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
+raw_atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
 {
-	return arch_atomic_cmpxchg(v, old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_cmpxchg(v, old, new);
+#else
+	return raw_atomic_cmpxchg(v, old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_cmpxchg_acquire() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
+raw_atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
 {
-	return arch_atomic_cmpxchg_acquire(v, old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_cmpxchg_acquire(v, old, new);
+#else
+	return raw_atomic_cmpxchg_acquire(v, old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_cmpxchg_release() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
+raw_atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
 {
-	return arch_atomic_cmpxchg_release(v, old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_cmpxchg_release(v, old, new);
+#else
+	return raw_atomic_cmpxchg_release(v, old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @old: long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_cmpxchg_relaxed() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
+raw_atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
 {
-	return arch_atomic_cmpxchg_relaxed(v, old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_cmpxchg_relaxed(v, old, new);
+#else
+	return raw_atomic_cmpxchg_relaxed(v, old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_try_cmpxchg() - atomic compare and exchange with full ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with full ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
+raw_atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
 {
-	return arch_atomic_try_cmpxchg(v, (int *)old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_try_cmpxchg(v, (s64 *)old, new);
+#else
+	return raw_atomic_try_cmpxchg(v, (int *)old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_try_cmpxchg_acquire() - atomic compare and exchange with acquire ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with acquire ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_acquire() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
+raw_atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
 {
-	return arch_atomic_try_cmpxchg_acquire(v, (int *)old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_try_cmpxchg_acquire(v, (s64 *)old, new);
+#else
+	return raw_atomic_try_cmpxchg_acquire(v, (int *)old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_try_cmpxchg_release() - atomic compare and exchange with release ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with release ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_release() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
+raw_atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
 {
-	return arch_atomic_try_cmpxchg_release(v, (int *)old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_try_cmpxchg_release(v, (s64 *)old, new);
+#else
+	return raw_atomic_try_cmpxchg_release(v, (int *)old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_try_cmpxchg_relaxed() - atomic compare and exchange with relaxed ordering
+ * @v: pointer to atomic_long_t
+ * @old: pointer to long value to compare with
+ * @new: long value to assign
+ *
+ * If (@v == @old), atomically updates @v to @new with relaxed ordering.
+ * Otherwise, @v is not modified, @old is updated to the current value of @v,
+ * and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_try_cmpxchg_relaxed() elsewhere.
+ *
+ * Return: @true if the exchange occured, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
+raw_atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
 {
-	return arch_atomic_try_cmpxchg_relaxed(v, (int *)old, new);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_try_cmpxchg_relaxed(v, (s64 *)old, new);
+#else
+	return raw_atomic_try_cmpxchg_relaxed(v, (int *)old, new);
+#endif
 }
 
+/**
+ * raw_atomic_long_sub_and_test() - atomic subtract and test if zero with full ordering
+ * @i: long value to subtract
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_sub_and_test() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_sub_and_test(long i, atomic_long_t *v)
+raw_atomic_long_sub_and_test(long i, atomic_long_t *v)
 {
-	return arch_atomic_sub_and_test(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_sub_and_test(i, v);
+#else
+	return raw_atomic_sub_and_test(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_and_test() - atomic decrement and test if zero with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v - 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_and_test() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_dec_and_test(atomic_long_t *v)
+raw_atomic_long_dec_and_test(atomic_long_t *v)
 {
-	return arch_atomic_dec_and_test(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_and_test(v);
+#else
+	return raw_atomic_dec_and_test(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_and_test() - atomic increment and test if zero with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + 1) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_and_test() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is zero, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_inc_and_test(atomic_long_t *v)
+raw_atomic_long_inc_and_test(atomic_long_t *v)
 {
-	return arch_atomic_inc_and_test(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_and_test(v);
+#else
+	return raw_atomic_inc_and_test(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_negative() - atomic add and test if negative with full ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with full ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_negative() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_add_negative(long i, atomic_long_t *v)
+raw_atomic_long_add_negative(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_negative(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_negative(i, v);
+#else
+	return raw_atomic_add_negative(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_negative_acquire() - atomic add and test if negative with acquire ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with acquire ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_negative_acquire() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_add_negative_acquire(long i, atomic_long_t *v)
+raw_atomic_long_add_negative_acquire(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_negative_acquire(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_negative_acquire(i, v);
+#else
+	return raw_atomic_add_negative_acquire(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_negative_release() - atomic add and test if negative with release ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with release ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_negative_release() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_add_negative_release(long i, atomic_long_t *v)
+raw_atomic_long_add_negative_release(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_negative_release(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_negative_release(i, v);
+#else
+	return raw_atomic_add_negative_release(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_negative_relaxed() - atomic add and test if negative with relaxed ordering
+ * @i: long value to add
+ * @v: pointer to atomic_long_t
+ *
+ * Atomically updates @v to (@v + @i) with relaxed ordering.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_negative_relaxed() elsewhere.
+ *
+ * Return: @true if the resulting value of @v is negative, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
+raw_atomic_long_add_negative_relaxed(long i, atomic_long_t *v)
 {
-	return arch_atomic_add_negative_relaxed(i, v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_negative_relaxed(i, v);
+#else
+	return raw_atomic_add_negative_relaxed(i, v);
+#endif
 }
 
+/**
+ * raw_atomic_long_fetch_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_long_t
+ * @a: long value to add
+ * @u: long value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_fetch_add_unless() elsewhere.
+ *
+ * Return: The original value of @v.
+ */
 static __always_inline long
-arch_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
+raw_atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
 {
-	return arch_atomic_fetch_add_unless(v, a, u);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_fetch_add_unless(v, a, u);
+#else
+	return raw_atomic_fetch_add_unless(v, a, u);
+#endif
 }
 
+/**
+ * raw_atomic_long_add_unless() - atomic add unless value with full ordering
+ * @v: pointer to atomic_long_t
+ * @a: long value to add
+ * @u: long value to compare with
+ *
+ * If (@v != @u), atomically updates @v to (@v + @a) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_add_unless() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_add_unless(atomic_long_t *v, long a, long u)
+raw_atomic_long_add_unless(atomic_long_t *v, long a, long u)
 {
-	return arch_atomic_add_unless(v, a, u);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_add_unless(v, a, u);
+#else
+	return raw_atomic_add_unless(v, a, u);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_not_zero() - atomic increment unless zero with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v != 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_not_zero() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_inc_not_zero(atomic_long_t *v)
+raw_atomic_long_inc_not_zero(atomic_long_t *v)
 {
-	return arch_atomic_inc_not_zero(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_not_zero(v);
+#else
+	return raw_atomic_inc_not_zero(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_inc_unless_negative() - atomic increment unless negative with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v >= 0), atomically updates @v to (@v + 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_inc_unless_negative() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_inc_unless_negative(atomic_long_t *v)
+raw_atomic_long_inc_unless_negative(atomic_long_t *v)
 {
-	return arch_atomic_inc_unless_negative(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_inc_unless_negative(v);
+#else
+	return raw_atomic_inc_unless_negative(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_unless_positive() - atomic decrement unless positive with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v <= 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_unless_positive() elsewhere.
+ *
+ * Return: @true if @v was updated, @false otherwise.
+ */
 static __always_inline bool
-arch_atomic_long_dec_unless_positive(atomic_long_t *v)
+raw_atomic_long_dec_unless_positive(atomic_long_t *v)
 {
-	return arch_atomic_dec_unless_positive(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_unless_positive(v);
+#else
+	return raw_atomic_dec_unless_positive(v);
+#endif
 }
 
+/**
+ * raw_atomic_long_dec_if_positive() - atomic decrement if positive with full ordering
+ * @v: pointer to atomic_long_t
+ *
+ * If (@v > 0), atomically updates @v to (@v - 1) with full ordering.
+ * Otherwise, @v is not modified and relaxed ordering is provided.
+ *
+ * Safe to use in noinstr code; prefer atomic_long_dec_if_positive() elsewhere.
+ *
+ * Return: The old value of (@v - 1), regardless of whether @v was updated.
+ */
 static __always_inline long
-arch_atomic_long_dec_if_positive(atomic_long_t *v)
+raw_atomic_long_dec_if_positive(atomic_long_t *v)
 {
-	return arch_atomic_dec_if_positive(v);
+#ifdef CONFIG_64BIT
+	return raw_atomic64_dec_if_positive(v);
+#else
+	return raw_atomic_dec_if_positive(v);
+#endif
 }
 
-#endif /* CONFIG_64BIT */
 #endif /* _LINUX_ATOMIC_LONG_H */
-// a194c07d7d2f4b0e178d3c118c919775d5d65f50
+// eadf183c3600b8b92b91839dd3be6bcc560c752d
diff --git a/include/linux/attribute_container.h b/include/linux/attribute_container.h
index e4004d1e6725..b3643de9931d 100644
--- a/include/linux/attribute_container.h
+++ b/include/linux/attribute_container.h
@@ -61,14 +61,8 @@ int attribute_container_device_trigger_safe(struct device *dev,
 					    int (*undo)(struct attribute_container *,
 							struct device *,
 							struct device *));
-void attribute_container_trigger(struct device *dev, 
-				 int (*fn)(struct attribute_container *,
-					   struct device *));
 int attribute_container_add_attrs(struct device *classdev);
 int attribute_container_add_class_device(struct device *classdev);
-int attribute_container_add_class_device_adapter(struct attribute_container *cont,
-						 struct device *dev,
-						 struct device *classdev);
 void attribute_container_remove_attrs(struct device *classdev);
 void attribute_container_class_device_del(struct device *classdev);
 struct attribute_container *attribute_container_classdev_to_container(struct device *);
diff --git a/include/linux/audit.h b/include/linux/audit.h
index 31086a72e32a..536f8ee8da81 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -36,6 +36,9 @@ struct mqstat;
 struct audit_watch;
 struct audit_tree;
 struct sk_buff;
+struct kern_ipc_perm;
+struct lsm_id;
+struct lsm_prop;
 
 struct audit_krule {
 	u32			pflags;
@@ -117,6 +120,8 @@ enum audit_nfcfgop {
 	AUDIT_NFT_OP_OBJ_RESET,
 	AUDIT_NFT_OP_FLOWTABLE_REGISTER,
 	AUDIT_NFT_OP_FLOWTABLE_UNREGISTER,
+	AUDIT_NFT_OP_SETELEM_RESET,
+	AUDIT_NFT_OP_RULE_RESET,
 	AUDIT_NFT_OP_INVALID,
 };
 
@@ -130,8 +135,6 @@ extern unsigned compat_dir_class[];
 extern unsigned compat_chattr_class[];
 extern unsigned compat_signal_class[];
 
-extern int audit_classify_compat_syscall(int abi, unsigned syscall);
-
 /* audit_names->type values */
 #define	AUDIT_TYPE_UNKNOWN	0	/* we don't know yet */
 #define	AUDIT_TYPE_NORMAL	1	/* a "normal" audit record */
@@ -146,6 +149,10 @@ extern int audit_classify_compat_syscall(int abi, unsigned syscall);
 #define AUDIT_TTY_ENABLE	BIT(0)
 #define AUDIT_TTY_LOG_PASSWD	BIT(1)
 
+/* bit values for audit_cfg_lsm */
+#define AUDIT_CFG_LSM_SECCTX_SUBJECT	BIT(0)
+#define AUDIT_CFG_LSM_SECCTX_OBJECT	BIT(1)
+
 struct filename;
 
 #define AUDIT_OFF	0
@@ -184,6 +191,8 @@ extern void		    audit_log_path_denied(int type,
 						  const char *operation);
 extern void		    audit_log_lost(const char *message);
 
+extern int audit_log_subj_ctx(struct audit_buffer *ab, struct lsm_prop *prop);
+extern int audit_log_obj_ctx(struct audit_buffer *ab, struct lsm_prop *prop);
 extern int audit_log_task_context(struct audit_buffer *ab);
 extern void audit_log_task_info(struct audit_buffer *ab);
 
@@ -209,6 +218,8 @@ extern u32 audit_enabled;
 
 extern int audit_signal_info(int sig, struct task_struct *t);
 
+extern void audit_cfg_lsm(const struct lsm_id *lsmid, int flags);
+
 #else /* CONFIG_AUDIT */
 static inline __printf(4, 5)
 void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type,
@@ -244,6 +255,16 @@ static inline void audit_log_key(struct audit_buffer *ab, char *key)
 { }
 static inline void audit_log_path_denied(int type, const char *operation)
 { }
+static inline int audit_log_subj_ctx(struct audit_buffer *ab,
+				     struct lsm_prop *prop)
+{
+	return 0;
+}
+static inline int audit_log_obj_ctx(struct audit_buffer *ab,
+				    struct lsm_prop *prop)
+{
+	return 0;
+}
 static inline int audit_log_task_context(struct audit_buffer *ab)
 {
 	return 0;
@@ -268,6 +289,9 @@ static inline int audit_signal_info(int sig, struct task_struct *t)
 	return 0;
 }
 
+static inline void audit_cfg_lsm(const struct lsm_id *lsmid, int flags)
+{ }
+
 #endif /* CONFIG_AUDIT */
 
 #ifdef CONFIG_AUDIT_COMPAT_GENERIC
@@ -416,7 +440,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 extern void __audit_log_capset(const struct cred *new, const struct cred *old);
 extern void __audit_mmap_fd(int fd, int flags);
 extern void __audit_openat2_how(struct open_how *how);
-extern void __audit_log_kern_module(char *name);
+extern void __audit_log_kern_module(const char *name);
 extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar);
 extern void __audit_tk_injoffset(struct timespec64 offset);
 extern void __audit_ntp_log(const struct audit_ntp_data *ad);
@@ -518,7 +542,7 @@ static inline void audit_openat2_how(struct open_how *how)
 		__audit_openat2_how(how);
 }
 
-static inline void audit_log_kern_module(char *name)
+static inline void audit_log_kern_module(const char *name)
 {
 	if (!audit_dummy_context())
 		__audit_log_kern_module(name);
@@ -526,7 +550,7 @@ static inline void audit_log_kern_module(char *name)
 
 static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar)
 {
-	if (!audit_dummy_context())
+	if (audit_enabled)
 		__audit_fanotify(response, friar);
 }
 
@@ -676,9 +700,8 @@ static inline void audit_mmap_fd(int fd, int flags)
 static inline void audit_openat2_how(struct open_how *how)
 { }
 
-static inline void audit_log_kern_module(char *name)
-{
-}
+static inline void audit_log_kern_module(const char *name)
+{ }
 
 static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar)
 { }
diff --git a/include/linux/audit_arch.h b/include/linux/audit_arch.h
index 8fdb1afe251a..0e34d673ef17 100644
--- a/include/linux/audit_arch.h
+++ b/include/linux/audit_arch.h
@@ -21,4 +21,6 @@ enum auditsc_class_t {
 	AUDITSC_NVALS /* count */
 };
 
+extern int audit_classify_compat_syscall(int abi, unsigned syscall);
+
 #endif
diff --git a/include/linux/auxiliary_bus.h b/include/linux/auxiliary_bus.h
index de21d9d24a95..4086afd0cc6b 100644
--- a/include/linux/auxiliary_bus.h
+++ b/include/linux/auxiliary_bus.h
@@ -58,6 +58,10 @@
  *       in
  * @name: Match name found by the auxiliary device driver,
  * @id: unique identitier if multiple devices of the same name are exported,
+ * @sysfs: embedded struct which hold all sysfs related fields,
+ * @sysfs.irqs: irqs xarray contains irq indices which are used by the device,
+ * @sysfs.lock: Synchronize irq sysfs creation,
+ * @sysfs.irq_dir_exists: whether "irqs" directory exists,
  *
  * An auxiliary_device represents a part of its parent device's functionality.
  * It is given a name that, combined with the registering drivers
@@ -139,6 +143,11 @@ struct auxiliary_device {
 	struct device dev;
 	const char *name;
 	u32 id;
+	struct {
+		struct xarray irqs;
+		struct mutex lock; /* Synchronize irq sysfs creation */
+		bool irq_dir_exists;
+	} sysfs;
 };
 
 /**
@@ -203,7 +212,7 @@ static inline struct auxiliary_device *to_auxiliary_dev(struct device *dev)
 	return container_of(dev, struct auxiliary_device, dev);
 }
 
-static inline struct auxiliary_driver *to_auxiliary_drv(struct device_driver *drv)
+static inline const struct auxiliary_driver *to_auxiliary_drv(const struct device_driver *drv)
 {
 	return container_of(drv, struct auxiliary_driver, driver);
 }
@@ -212,8 +221,24 @@ int auxiliary_device_init(struct auxiliary_device *auxdev);
 int __auxiliary_device_add(struct auxiliary_device *auxdev, const char *modname);
 #define auxiliary_device_add(auxdev) __auxiliary_device_add(auxdev, KBUILD_MODNAME)
 
+#ifdef CONFIG_SYSFS
+int auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq);
+void auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev,
+				       int irq);
+#else /* CONFIG_SYSFS */
+static inline int
+auxiliary_device_sysfs_irq_add(struct auxiliary_device *auxdev, int irq)
+{
+	return 0;
+}
+
+static inline void
+auxiliary_device_sysfs_irq_remove(struct auxiliary_device *auxdev, int irq) {}
+#endif
+
 static inline void auxiliary_device_uninit(struct auxiliary_device *auxdev)
 {
+	mutex_destroy(&auxdev->sysfs.lock);
 	put_device(&auxdev->dev);
 }
 
@@ -229,6 +254,23 @@ int __auxiliary_driver_register(struct auxiliary_driver *auxdrv, struct module *
 
 void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv);
 
+struct auxiliary_device *auxiliary_device_create(struct device *dev,
+						 const char *modname,
+						 const char *devname,
+						 void *platform_data,
+						 int id);
+void auxiliary_device_destroy(void *auxdev);
+
+struct auxiliary_device *__devm_auxiliary_device_create(struct device *dev,
+							const char *modname,
+							const char *devname,
+							void *platform_data,
+							int id);
+
+#define devm_auxiliary_device_create(dev, devname, platform_data)     \
+	__devm_auxiliary_device_create(dev, KBUILD_MODNAME, devname,  \
+				       platform_data, 0)
+
 /**
  * module_auxiliary_driver() - Helper macro for registering an auxiliary driver
  * @__auxiliary_driver: auxiliary driver struct
@@ -244,8 +286,4 @@ void auxiliary_driver_unregister(struct auxiliary_driver *auxdrv);
 #define module_auxiliary_driver(__auxiliary_driver) \
 	module_driver(__auxiliary_driver, auxiliary_driver_register, auxiliary_driver_unregister)
 
-struct auxiliary_device *auxiliary_find_device(struct device *start,
-					       const void *data,
-					       int (*match)(struct device *dev, const void *data));
-
 #endif /* _AUXILIARY_BUS_H_ */
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index c15221dcb75e..11bdab5522fd 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -4,6 +4,11 @@
 #ifndef _VIRTCHNL_H_
 #define _VIRTCHNL_H_
 
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/overflow.h>
+#include <uapi/linux/if_ether.h>
+
 /* Description:
  * This header file describes the Virtual Function (VF) - Physical Function
  * (PF) communication protocol used by the drivers for all devices starting
@@ -84,6 +89,9 @@ enum virtchnl_rx_hsplit {
 	VIRTCHNL_RX_HSPLIT_SPLIT_SCTP    = 8,
 };
 
+enum virtchnl_bw_limit_type {
+	VIRTCHNL_BW_SHAPER = 0,
+};
 /* END GENERIC DEFINES */
 
 /* Opcodes for VF-PF communication. These are placed in the v_opcode field
@@ -114,6 +122,7 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_GET_STATS = 15,
 	VIRTCHNL_OP_RSVD = 16,
 	VIRTCHNL_OP_EVENT = 17, /* must ALWAYS be 17 */
+	VIRTCHNL_OP_CONFIG_RSS_HFUNC = 18,
 	/* opcode 19 is reserved */
 	VIRTCHNL_OP_IWARP = 20, /* advanced opcode */
 	VIRTCHNL_OP_RDMA = VIRTCHNL_OP_IWARP,
@@ -123,8 +132,8 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP = VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
 	VIRTCHNL_OP_CONFIG_RSS_KEY = 23,
 	VIRTCHNL_OP_CONFIG_RSS_LUT = 24,
-	VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25,
-	VIRTCHNL_OP_SET_RSS_HENA = 26,
+	VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS = 25,
+	VIRTCHNL_OP_SET_RSS_HASHCFG = 26,
 	VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27,
 	VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28,
 	VIRTCHNL_OP_REQUEST_QUEUES = 29,
@@ -145,6 +154,14 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2 = 55,
 	VIRTCHNL_OP_ENABLE_VLAN_INSERTION_V2 = 56,
 	VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2 = 57,
+	/* opcode 58 and 59 are reserved */
+	VIRTCHNL_OP_1588_PTP_GET_CAPS = 60,
+	VIRTCHNL_OP_1588_PTP_GET_TIME = 61,
+	/* opcode 62 - 65 are reserved */
+	VIRTCHNL_OP_GET_QOS_CAPS = 66,
+	/* opcode 68 through 111 are reserved */
+	VIRTCHNL_OP_CONFIG_QUEUE_BW = 112,
+	VIRTCHNL_OP_CONFIG_QUANTA = 113,
 	VIRTCHNL_OP_MAX,
 };
 
@@ -240,6 +257,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 #define VIRTCHNL_VF_OFFLOAD_REQ_QUEUES		BIT(6)
 /* used to negotiate communicating link speeds in Mbps */
 #define VIRTCHNL_VF_CAP_ADV_LINK_SPEED		BIT(7)
+#define  VIRTCHNL_VF_OFFLOAD_CRC		BIT(10)
+#define VIRTCHNL_VF_OFFLOAD_TC_U32		BIT(11)
 #define VIRTCHNL_VF_OFFLOAD_VLAN_V2		BIT(15)
 #define VIRTCHNL_VF_OFFLOAD_VLAN		BIT(16)
 #define VIRTCHNL_VF_OFFLOAD_RX_POLLING		BIT(17)
@@ -253,6 +272,8 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_vsi_resource);
 #define VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC	BIT(26)
 #define VIRTCHNL_VF_OFFLOAD_ADV_RSS_PF		BIT(27)
 #define VIRTCHNL_VF_OFFLOAD_FDIR_PF		BIT(28)
+#define VIRTCHNL_VF_OFFLOAD_QOS			BIT(29)
+#define VIRTCHNL_VF_CAP_PTP			BIT(31)
 
 #define VF_BASE_MODE_OFFLOADS (VIRTCHNL_VF_OFFLOAD_L2 | \
 			       VIRTCHNL_VF_OFFLOAD_VLAN | \
@@ -268,10 +289,11 @@ struct virtchnl_vf_resource {
 	u32 rss_key_size;
 	u32 rss_lut_size;
 
-	struct virtchnl_vsi_resource vsi_res[1];
+	struct virtchnl_vsi_resource vsi_res[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_vf_resource);
+VIRTCHNL_CHECK_STRUCT_LEN(20, virtchnl_vf_resource);
+#define virtchnl_vf_resource_LEGACY_SIZEOF	36
 
 /* VIRTCHNL_OP_CONFIG_TX_QUEUE
  * VF sends this message to set up parameters for one TX queue.
@@ -291,10 +313,70 @@ struct virtchnl_txq_info {
 
 VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_txq_info);
 
+/* RX descriptor IDs (range from 0 to 63) */
+enum virtchnl_rx_desc_ids {
+	VIRTCHNL_RXDID_0_16B_BASE		= 0,
+	VIRTCHNL_RXDID_1_32B_BASE		= 1,
+	VIRTCHNL_RXDID_2_FLEX_SQ_NIC		= 2,
+	VIRTCHNL_RXDID_3_FLEX_SQ_SW		= 3,
+	VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB	= 4,
+	VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL	= 5,
+	VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2		= 6,
+	VIRTCHNL_RXDID_7_HW_RSVD		= 7,
+	/* 8 through 15 are reserved */
+	VIRTCHNL_RXDID_16_COMMS_GENERIC		= 16,
+	VIRTCHNL_RXDID_17_COMMS_AUX_VLAN	= 17,
+	VIRTCHNL_RXDID_18_COMMS_AUX_IPV4	= 18,
+	VIRTCHNL_RXDID_19_COMMS_AUX_IPV6	= 19,
+	VIRTCHNL_RXDID_20_COMMS_AUX_FLOW	= 20,
+	VIRTCHNL_RXDID_21_COMMS_AUX_TCP		= 21,
+	/* 22 through 63 are reserved */
+};
+
+#define VIRTCHNL_RXDID_BIT(x)			BIT_ULL(VIRTCHNL_RXDID_##x)
+
+/* RX descriptor ID bitmasks */
+enum virtchnl_rx_desc_id_bitmasks {
+	VIRTCHNL_RXDID_0_16B_BASE_M		= VIRTCHNL_RXDID_BIT(0_16B_BASE),
+	VIRTCHNL_RXDID_1_32B_BASE_M		= VIRTCHNL_RXDID_BIT(1_32B_BASE),
+	VIRTCHNL_RXDID_2_FLEX_SQ_NIC_M		= VIRTCHNL_RXDID_BIT(2_FLEX_SQ_NIC),
+	VIRTCHNL_RXDID_3_FLEX_SQ_SW_M		= VIRTCHNL_RXDID_BIT(3_FLEX_SQ_SW),
+	VIRTCHNL_RXDID_4_FLEX_SQ_NIC_VEB_M	= VIRTCHNL_RXDID_BIT(4_FLEX_SQ_NIC_VEB),
+	VIRTCHNL_RXDID_5_FLEX_SQ_NIC_ACL_M	= VIRTCHNL_RXDID_BIT(5_FLEX_SQ_NIC_ACL),
+	VIRTCHNL_RXDID_6_FLEX_SQ_NIC_2_M	= VIRTCHNL_RXDID_BIT(6_FLEX_SQ_NIC_2),
+	VIRTCHNL_RXDID_7_HW_RSVD_M		= VIRTCHNL_RXDID_BIT(7_HW_RSVD),
+	/* 8 through 15 are reserved */
+	VIRTCHNL_RXDID_16_COMMS_GENERIC_M	= VIRTCHNL_RXDID_BIT(16_COMMS_GENERIC),
+	VIRTCHNL_RXDID_17_COMMS_AUX_VLAN_M	= VIRTCHNL_RXDID_BIT(17_COMMS_AUX_VLAN),
+	VIRTCHNL_RXDID_18_COMMS_AUX_IPV4_M	= VIRTCHNL_RXDID_BIT(18_COMMS_AUX_IPV4),
+	VIRTCHNL_RXDID_19_COMMS_AUX_IPV6_M	= VIRTCHNL_RXDID_BIT(19_COMMS_AUX_IPV6),
+	VIRTCHNL_RXDID_20_COMMS_AUX_FLOW_M	= VIRTCHNL_RXDID_BIT(20_COMMS_AUX_FLOW),
+	VIRTCHNL_RXDID_21_COMMS_AUX_TCP_M	= VIRTCHNL_RXDID_BIT(21_COMMS_AUX_TCP),
+	/* 22 through 63 are reserved */
+};
+
+/* virtchnl_rxq_info_flags - definition of bits in the flags field of the
+ *			     virtchnl_rxq_info structure.
+ *
+ * @VIRTCHNL_PTP_RX_TSTAMP: request to enable Rx timestamping
+ *
+ * Other flag bits are currently reserved and they may be extended in the
+ * future.
+ */
+enum virtchnl_rxq_info_flags {
+	VIRTCHNL_PTP_RX_TSTAMP = BIT(0),
+};
+
 /* VIRTCHNL_OP_CONFIG_RX_QUEUE
  * VF sends this message to set up parameters for one RX queue.
  * External data buffer contains one instance of virtchnl_rxq_info.
- * PF configures requested queue and returns a status code.
+ * PF configures requested queue and returns a status code. The
+ * crc_disable flag disables CRC stripping on the VF. Setting
+ * the crc_disable flag to 1 will disable CRC stripping for each
+ * queue in the VF where the flag is set. The VIRTCHNL_VF_OFFLOAD_CRC
+ * offload must have been set prior to sending this info or the PF
+ * will ignore the request. This flag should be set the same for
+ * all of the queues for a VF.
  */
 
 /* Rx queue config info */
@@ -306,9 +388,15 @@ struct virtchnl_rxq_info {
 	u16 splithdr_enabled; /* deprecated with AVF 1.0 */
 	u32 databuffer_size;
 	u32 max_pkt_size;
-	u8 pad0;
-	u8 rxdid;
-	u8 pad1[2];
+	u8 crc_disable;
+	/* see enum virtchnl_rx_desc_ids;
+	 * only used when VIRTCHNL_VF_OFFLOAD_RX_FLEX_DESC is supported. Note
+	 * that when the offload is not supported, the descriptor format aligns
+	 * with VIRTCHNL_RXDID_1_32B_BASE.
+	 */
+	enum virtchnl_rx_desc_ids rxdid:8;
+	enum virtchnl_rxq_info_flags flags:8; /* see virtchnl_rxq_info_flags */
+	u8 pad1;
 	u64 dma_ring_addr;
 
 	/* see enum virtchnl_rx_hsplit; deprecated with AVF 1.0 */
@@ -340,10 +428,11 @@ struct virtchnl_vsi_queue_config_info {
 	u16 vsi_id;
 	u16 num_queue_pairs;
 	u32 pad;
-	struct virtchnl_queue_pair_info qpair[1];
+	struct virtchnl_queue_pair_info qpair[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(72, virtchnl_vsi_queue_config_info);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vsi_queue_config_info);
+#define virtchnl_vsi_queue_config_info_LEGACY_SIZEOF	72
 
 /* VIRTCHNL_OP_REQUEST_QUEUES
  * VF sends this message to request the PF to allocate additional queues to
@@ -385,10 +474,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_vector_map);
 
 struct virtchnl_irq_map_info {
 	u16 num_vectors;
-	struct virtchnl_vector_map vecmap[1];
+	struct virtchnl_vector_map vecmap[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(14, virtchnl_irq_map_info);
+VIRTCHNL_CHECK_STRUCT_LEN(2, virtchnl_irq_map_info);
+#define virtchnl_irq_map_info_LEGACY_SIZEOF	14
 
 /* VIRTCHNL_OP_ENABLE_QUEUES
  * VIRTCHNL_OP_DISABLE_QUEUES
@@ -459,10 +549,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_ether_addr);
 struct virtchnl_ether_addr_list {
 	u16 vsi_id;
 	u16 num_elements;
-	struct virtchnl_ether_addr list[1];
+	struct virtchnl_ether_addr list[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_ether_addr_list);
+#define virtchnl_ether_addr_list_LEGACY_SIZEOF	12
 
 /* VIRTCHNL_OP_ADD_VLAN
  * VF sends this message to add one or more VLAN tag filters for receives.
@@ -481,10 +572,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_ether_addr_list);
 struct virtchnl_vlan_filter_list {
 	u16 vsi_id;
 	u16 num_elements;
-	u16 vlan_id[1];
+	u16 vlan_id[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_vlan_filter_list);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_vlan_filter_list);
+#define virtchnl_vlan_filter_list_LEGACY_SIZEOF	6
 
 /* This enum is used for all of the VIRTCHNL_VF_OFFLOAD_VLAN_V2_CAPS related
  * structures and opcodes.
@@ -711,10 +803,11 @@ struct virtchnl_vlan_filter_list_v2 {
 	u16 vport_id;
 	u16 num_elements;
 	u8 pad[4];
-	struct virtchnl_vlan_filter filters[1];
+	struct virtchnl_vlan_filter filters[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_vlan_filter_list_v2);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_vlan_filter_list_v2);
+#define virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF	40
 
 /* VIRTCHNL_OP_ENABLE_VLAN_STRIPPING_V2
  * VIRTCHNL_OP_DISABLE_VLAN_STRIPPING_V2
@@ -866,31 +959,57 @@ VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_promisc_info);
 struct virtchnl_rss_key {
 	u16 vsi_id;
 	u16 key_len;
-	u8 key[1];         /* RSS hash key, packed bytes */
+	u8 key[];          /* RSS hash key, packed bytes */
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_key);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_key);
+#define virtchnl_rss_key_LEGACY_SIZEOF	6
 
 struct virtchnl_rss_lut {
 	u16 vsi_id;
 	u16 lut_entries;
-	u8 lut[1];        /* RSS lookup table */
+	u8 lut[];         /* RSS lookup table */
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(6, virtchnl_rss_lut);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_lut);
+#define virtchnl_rss_lut_LEGACY_SIZEOF	6
 
-/* VIRTCHNL_OP_GET_RSS_HENA_CAPS
- * VIRTCHNL_OP_SET_RSS_HENA
- * VF sends these messages to get and set the hash filter enable bits for RSS.
+/* VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS
+ * VIRTCHNL_OP_SET_RSS_HASHCFG
+ * VF sends these messages to get and set the hash filter configuration for RSS.
  * By default, the PF sets these to all possible traffic types that the
  * hardware supports. The VF can query this value if it wants to change the
  * traffic types that are hashed by the hardware.
  */
-struct virtchnl_rss_hena {
-	u64 hena;
+struct virtchnl_rss_hashcfg {
+	/* Bits defined by enum libie_filter_pctype */
+	u64 hashcfg;
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hashcfg);
+
+/* Type of RSS algorithm */
+enum virtchnl_rss_algorithm {
+	VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC	= 0,
+	VIRTCHNL_RSS_ALG_R_ASYMMETRIC		= 1,
+	VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC	= 2,
+	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
+};
+
+/* VIRTCHNL_OP_CONFIG_RSS_HFUNC
+ * VF sends this message to configure the RSS hash function. Only supported
+ * if both PF and VF drivers set the VIRTCHNL_VF_OFFLOAD_RSS_PF bit during
+ * configuration negotiation.
+ * The hash function is initialized to VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC
+ * by the PF.
+ */
+struct virtchnl_rss_hfunc {
+	u16 vsi_id;
+	u16 rss_algorithm; /* enum virtchnl_rss_algorithm */
+	u32 reserved;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hfunc);
 
 /* VIRTCHNL_OP_ENABLE_CHANNELS
  * VIRTCHNL_OP_DISABLE_CHANNELS
@@ -911,10 +1030,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_channel_info);
 struct virtchnl_tc_info {
 	u32	num_tc;
 	u32	pad;
-	struct	virtchnl_channel_info list[1];
+	struct virtchnl_channel_info list[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(24, virtchnl_tc_info);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_tc_info);
+#define virtchnl_tc_info_LEGACY_SIZEOF	24
 
 /* VIRTCHNL_ADD_CLOUD_FILTER
  * VIRTCHNL_DEL_CLOUD_FILTER
@@ -977,10 +1097,6 @@ struct virtchnl_filter {
 
 VIRTCHNL_CHECK_STRUCT_LEN(272, virtchnl_filter);
 
-struct virtchnl_supported_rxdids {
-	u64 supported_rxdids;
-};
-
 /* VIRTCHNL_OP_EVENT
  * PF sends this message to inform the VF driver of events that may affect it.
  * No direct response is expected from the VF, though it may generate other
@@ -1052,10 +1168,11 @@ VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_rdma_qv_info);
 
 struct virtchnl_rdma_qvlist_info {
 	u32 num_vectors;
-	struct virtchnl_rdma_qv_info qv_info[1];
+	struct virtchnl_rdma_qv_info qv_info[];
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_rdma_qvlist_info);
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rdma_qvlist_info);
+#define virtchnl_rdma_qvlist_info_LEGACY_SIZEOF	16
 
 /* VF reset states - these are written into the RSTAT register:
  * VFGEN_RSTAT on the VF
@@ -1074,15 +1191,8 @@ enum virtchnl_vfr_states {
 	VIRTCHNL_VFR_VFACTIVE,
 };
 
-/* Type of RSS algorithm */
-enum virtchnl_rss_algorithm {
-	VIRTCHNL_RSS_ALG_TOEPLITZ_ASYMMETRIC	= 0,
-	VIRTCHNL_RSS_ALG_R_ASYMMETRIC		= 1,
-	VIRTCHNL_RSS_ALG_TOEPLITZ_SYMMETRIC	= 2,
-	VIRTCHNL_RSS_ALG_XOR_SYMMETRIC		= 3,
-};
-
 #define VIRTCHNL_MAX_NUM_PROTO_HDRS	32
+#define VIRTCHNL_MAX_SIZE_RAW_PACKET	1024
 #define PROTO_HDR_SHIFT			5
 #define PROTO_HDR_FIELD_START(proto_hdr_type) ((proto_hdr_type) << PROTO_HDR_SHIFT)
 #define PROTO_HDR_FIELD_MASK ((1UL << PROTO_HDR_SHIFT) - 1)
@@ -1143,6 +1253,17 @@ enum virtchnl_proto_hdr_type {
 	VIRTCHNL_PROTO_HDR_ESP,
 	VIRTCHNL_PROTO_HDR_AH,
 	VIRTCHNL_PROTO_HDR_PFCP,
+	VIRTCHNL_PROTO_HDR_GTPC,
+	VIRTCHNL_PROTO_HDR_ECPRI,
+	VIRTCHNL_PROTO_HDR_L2TPV2,
+	VIRTCHNL_PROTO_HDR_PPP,
+	/* IPv4 and IPv6 Fragment header types are only associated to
+	 * VIRTCHNL_PROTO_HDR_IPV4 and VIRTCHNL_PROTO_HDR_IPV6 respectively,
+	 * cannot be used independently.
+	 */
+	VIRTCHNL_PROTO_HDR_IPV4_FRAG,
+	VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG,
+	VIRTCHNL_PROTO_HDR_GRE,
 };
 
 /* Protocol header field within a protocol header. */
@@ -1165,6 +1286,7 @@ enum virtchnl_proto_hdr_field {
 	VIRTCHNL_PROTO_HDR_IPV4_DSCP,
 	VIRTCHNL_PROTO_HDR_IPV4_TTL,
 	VIRTCHNL_PROTO_HDR_IPV4_PROT,
+	VIRTCHNL_PROTO_HDR_IPV4_CHKSUM,
 	/* IPV6 */
 	VIRTCHNL_PROTO_HDR_IPV6_SRC =
 		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV6),
@@ -1172,18 +1294,34 @@ enum virtchnl_proto_hdr_field {
 	VIRTCHNL_PROTO_HDR_IPV6_TC,
 	VIRTCHNL_PROTO_HDR_IPV6_HOP_LIMIT,
 	VIRTCHNL_PROTO_HDR_IPV6_PROT,
+	/* IPV6 Prefix */
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX32_SRC,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX32_DST,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX40_SRC,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX40_DST,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX48_SRC,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX48_DST,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX56_SRC,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX56_DST,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_SRC,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX64_DST,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX96_SRC,
+	VIRTCHNL_PROTO_HDR_IPV6_PREFIX96_DST,
 	/* TCP */
 	VIRTCHNL_PROTO_HDR_TCP_SRC_PORT =
 		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_TCP),
 	VIRTCHNL_PROTO_HDR_TCP_DST_PORT,
+	VIRTCHNL_PROTO_HDR_TCP_CHKSUM,
 	/* UDP */
 	VIRTCHNL_PROTO_HDR_UDP_SRC_PORT =
 		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_UDP),
 	VIRTCHNL_PROTO_HDR_UDP_DST_PORT,
+	VIRTCHNL_PROTO_HDR_UDP_CHKSUM,
 	/* SCTP */
 	VIRTCHNL_PROTO_HDR_SCTP_SRC_PORT =
 		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_SCTP),
 	VIRTCHNL_PROTO_HDR_SCTP_DST_PORT,
+	VIRTCHNL_PROTO_HDR_SCTP_CHKSUM,
 	/* GTPU_IP */
 	VIRTCHNL_PROTO_HDR_GTPU_IP_TEID =
 		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_IP),
@@ -1207,6 +1345,28 @@ enum virtchnl_proto_hdr_field {
 	VIRTCHNL_PROTO_HDR_PFCP_S_FIELD =
 		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_PFCP),
 	VIRTCHNL_PROTO_HDR_PFCP_SEID,
+	/* GTPC */
+	VIRTCHNL_PROTO_HDR_GTPC_TEID =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPC),
+	/* ECPRI */
+	VIRTCHNL_PROTO_HDR_ECPRI_MSG_TYPE =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_ECPRI),
+	VIRTCHNL_PROTO_HDR_ECPRI_PC_RTC_ID,
+	/* IPv4 Dummy Fragment */
+	VIRTCHNL_PROTO_HDR_IPV4_FRAG_PKID =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV4_FRAG),
+	/* IPv6 Extension Fragment */
+	VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG_PKID =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_IPV6_EH_FRAG),
+	/* GTPU_DWN/UP */
+	VIRTCHNL_PROTO_HDR_GTPU_DWN_QFI =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_DWN),
+	VIRTCHNL_PROTO_HDR_GTPU_UP_QFI =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_GTPU_EH_PDU_UP),
+	/* L2TPv2 */
+	VIRTCHNL_PROTO_HDR_L2TPV2_SESS_ID =
+		PROTO_HDR_FIELD_START(VIRTCHNL_PROTO_HDR_L2TPV2),
+	VIRTCHNL_PROTO_HDR_L2TPV2_LEN_SESS_ID,
 };
 
 struct virtchnl_proto_hdr {
@@ -1228,13 +1388,22 @@ struct virtchnl_proto_hdrs {
 	u8 pad[3];
 	/**
 	 * specify where protocol header start from.
+	 * must be 0 when sending a raw packet request.
 	 * 0 - from the outer layer
 	 * 1 - from the first inner layer
 	 * 2 - from the second inner layer
 	 * ....
 	 **/
-	int count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */
-	struct virtchnl_proto_hdr proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS];
+	u32 count; /* the proto layers must < VIRTCHNL_MAX_NUM_PROTO_HDRS */
+	union {
+		struct virtchnl_proto_hdr
+			proto_hdr[VIRTCHNL_MAX_NUM_PROTO_HDRS];
+		struct {
+			u16 pkt_len;
+			u8 spec[VIRTCHNL_MAX_SIZE_RAW_PACKET];
+			u8 mask[VIRTCHNL_MAX_SIZE_RAW_PACKET];
+		} raw;
+	};
 };
 
 VIRTCHNL_CHECK_STRUCT_LEN(2312, virtchnl_proto_hdrs);
@@ -1277,7 +1446,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(36, virtchnl_filter_action);
 
 struct virtchnl_filter_action_set {
 	/* action number must be less then VIRTCHNL_MAX_NUM_ACTIONS */
-	int count;
+	u32 count;
 	struct virtchnl_filter_action actions[VIRTCHNL_MAX_NUM_ACTIONS];
 };
 
@@ -1367,6 +1536,168 @@ struct virtchnl_fdir_del {
 
 VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_fdir_del);
 
+#define VIRTCHNL_1588_PTP_CAP_RX_TSTAMP		BIT(1)
+#define VIRTCHNL_1588_PTP_CAP_READ_PHC		BIT(2)
+
+/**
+ * struct virtchnl_ptp_caps - Defines the PTP caps available to the VF.
+ * @caps: On send, VF sets what capabilities it requests. On reply, PF
+ *        indicates what has been enabled for this VF. The PF shall not set
+ *        bits which were not requested by the VF.
+ * @rsvd: Reserved bits for future extension.
+ *
+ * Structure that defines the PTP capabilities available to the VF. The VF
+ * sends VIRTCHNL_OP_1588_PTP_GET_CAPS, and must fill in the ptp_caps field
+ * indicating what capabilities it is requesting. The PF will respond with the
+ * same message with the virtchnl_ptp_caps structure indicating what is
+ * enabled for the VF.
+ *
+ * VIRTCHNL_1588_PTP_CAP_RX_TSTAMP indicates that the VF receive queues have
+ * receive timestamps enabled in the flexible descriptors. Note that this
+ * requires a VF to also negotiate to enable advanced flexible descriptors in
+ * the receive path instead of the default legacy descriptor format.
+ *
+ * VIRTCHNL_1588_PTP_CAP_READ_PHC indicates that the VF may read the PHC time
+ * via the VIRTCHNL_OP_1588_PTP_GET_TIME command.
+ *
+ * Note that in the future, additional capability flags may be added which
+ * indicate additional extended support. All fields marked as reserved by this
+ * header will be set to zero. VF implementations should verify this to ensure
+ * that future extensions do not break compatibility.
+ */
+struct virtchnl_ptp_caps {
+	u32 caps;
+	u8 rsvd[44];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(48, virtchnl_ptp_caps);
+
+/**
+ * struct virtchnl_phc_time - Contains the 64bits of PHC clock time in ns.
+ * @time: PHC time in nanoseconds
+ * @rsvd: Reserved for future extension
+ *
+ * Structure received with VIRTCHNL_OP_1588_PTP_GET_TIME. Contains the 64bits
+ * of PHC clock time in nanoseconds.
+ *
+ * VIRTCHNL_OP_1588_PTP_GET_TIME may be sent to request the current time of
+ * the PHC. This op is available in case direct access via the PHC registers
+ * is not available.
+ */
+struct virtchnl_phc_time {
+	u64 time;
+	u8 rsvd[8];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(16, virtchnl_phc_time);
+
+struct virtchnl_shaper_bw {
+	/* Unit is Kbps */
+	u32 committed;
+	u32 peak;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_shaper_bw);
+
+/* VIRTCHNL_OP_GET_QOS_CAPS
+ * VF sends this message to get its QoS Caps, such as
+ * TC number, Arbiter and Bandwidth.
+ */
+struct virtchnl_qos_cap_elem {
+	u8 tc_num;
+	u8 tc_prio;
+#define VIRTCHNL_ABITER_STRICT      0
+#define VIRTCHNL_ABITER_ETS         2
+	u8 arbiter;
+#define VIRTCHNL_STRICT_WEIGHT      1
+	u8 weight;
+	enum virtchnl_bw_limit_type type;
+	union {
+		struct virtchnl_shaper_bw shaper;
+		u8 pad2[32];
+	};
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(40, virtchnl_qos_cap_elem);
+
+struct virtchnl_qos_cap_list {
+	u16 vsi_id;
+	u16 num_elem;
+	struct virtchnl_qos_cap_elem cap[];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_qos_cap_list);
+#define virtchnl_qos_cap_list_LEGACY_SIZEOF	44
+
+/* VIRTCHNL_OP_CONFIG_QUEUE_BW */
+struct virtchnl_queue_bw {
+	u16 queue_id;
+	u8 tc;
+	u8 pad;
+	struct virtchnl_shaper_bw shaper;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_queue_bw);
+
+struct virtchnl_queues_bw_cfg {
+	u16 vsi_id;
+	u16 num_queues;
+	struct virtchnl_queue_bw cfg[];
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_queues_bw_cfg);
+#define virtchnl_queues_bw_cfg_LEGACY_SIZEOF	16
+
+enum virtchnl_queue_type {
+	VIRTCHNL_QUEUE_TYPE_TX			= 0,
+	VIRTCHNL_QUEUE_TYPE_RX			= 1,
+};
+
+/* structure to specify a chunk of contiguous queues */
+struct virtchnl_queue_chunk {
+	/* see enum virtchnl_queue_type */
+	s32 type;
+	u16 start_queue_id;
+	u16 num_queues;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_queue_chunk);
+
+struct virtchnl_quanta_cfg {
+	u16 quanta_size;
+	u16 pad;
+	struct virtchnl_queue_chunk queue_select;
+};
+
+VIRTCHNL_CHECK_STRUCT_LEN(12, virtchnl_quanta_cfg);
+
+#define __vss_byone(p, member, count, old)				      \
+	(struct_size(p, member, count) + (old - 1 - struct_size(p, member, 0)))
+
+#define __vss_byelem(p, member, count, old)				      \
+	(struct_size(p, member, count - 1) + (old - struct_size(p, member, 0)))
+
+#define __vss_full(p, member, count, old)				      \
+	(struct_size(p, member, count) + (old - struct_size(p, member, 0)))
+
+#define __vss(type, func, p, member, count)		\
+	struct type: func(p, member, count, type##_LEGACY_SIZEOF)
+
+#define virtchnl_struct_size(p, m, c)					      \
+	_Generic(*p,							      \
+		 __vss(virtchnl_vf_resource, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_vsi_queue_config_info, __vss_full, p, m, c),  \
+		 __vss(virtchnl_irq_map_info, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_ether_addr_list, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_vlan_filter_list, __vss_full, p, m, c),	      \
+		 __vss(virtchnl_vlan_filter_list_v2, __vss_byelem, p, m, c),  \
+		 __vss(virtchnl_tc_info, __vss_byelem, p, m, c),	      \
+		 __vss(virtchnl_rdma_qvlist_info, __vss_byelem, p, m, c),     \
+		 __vss(virtchnl_qos_cap_list, __vss_byelem, p, m, c),	      \
+		 __vss(virtchnl_queues_bw_cfg, __vss_byelem, p, m, c),	      \
+		 __vss(virtchnl_rss_key, __vss_byone, p, m, c),		      \
+		 __vss(virtchnl_rss_lut, __vss_byone, p, m, c))
+
 /**
  * virtchnl_vc_validate_vf_msg
  * @ver: Virtchnl version info
@@ -1401,24 +1732,23 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		valid_len = sizeof(struct virtchnl_rxq_info);
 		break;
 	case VIRTCHNL_OP_CONFIG_VSI_QUEUES:
-		valid_len = sizeof(struct virtchnl_vsi_queue_config_info);
+		valid_len = virtchnl_vsi_queue_config_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_vsi_queue_config_info *vqc =
 			    (struct virtchnl_vsi_queue_config_info *)msg;
-			valid_len += (vqc->num_queue_pairs *
-				      sizeof(struct
-					     virtchnl_queue_pair_info));
+			valid_len = virtchnl_struct_size(vqc, qpair,
+							 vqc->num_queue_pairs);
 			if (vqc->num_queue_pairs == 0)
 				err_msg_format = true;
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_IRQ_MAP:
-		valid_len = sizeof(struct virtchnl_irq_map_info);
+		valid_len = virtchnl_irq_map_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_irq_map_info *vimi =
 			    (struct virtchnl_irq_map_info *)msg;
-			valid_len += (vimi->num_vectors *
-				      sizeof(struct virtchnl_vector_map));
+			valid_len = virtchnl_struct_size(vimi, vecmap,
+							 vimi->num_vectors);
 			if (vimi->num_vectors == 0)
 				err_msg_format = true;
 		}
@@ -1429,23 +1759,24 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		break;
 	case VIRTCHNL_OP_ADD_ETH_ADDR:
 	case VIRTCHNL_OP_DEL_ETH_ADDR:
-		valid_len = sizeof(struct virtchnl_ether_addr_list);
+		valid_len = virtchnl_ether_addr_list_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_ether_addr_list *veal =
 			    (struct virtchnl_ether_addr_list *)msg;
-			valid_len += veal->num_elements *
-			    sizeof(struct virtchnl_ether_addr);
+			valid_len = virtchnl_struct_size(veal, list,
+							 veal->num_elements);
 			if (veal->num_elements == 0)
 				err_msg_format = true;
 		}
 		break;
 	case VIRTCHNL_OP_ADD_VLAN:
 	case VIRTCHNL_OP_DEL_VLAN:
-		valid_len = sizeof(struct virtchnl_vlan_filter_list);
+		valid_len = virtchnl_vlan_filter_list_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_vlan_filter_list *vfl =
 			    (struct virtchnl_vlan_filter_list *)msg;
-			valid_len += vfl->num_elements * sizeof(u16);
+			valid_len = virtchnl_struct_size(vfl, vlan_id,
+							 vfl->num_elements);
 			if (vfl->num_elements == 0)
 				err_msg_format = true;
 		}
@@ -1469,35 +1800,40 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 	case VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP:
 		break;
 	case VIRTCHNL_OP_CONFIG_RDMA_IRQ_MAP:
-		valid_len = sizeof(struct virtchnl_rdma_qvlist_info);
+		valid_len = virtchnl_rdma_qvlist_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_rdma_qvlist_info *qv =
 				(struct virtchnl_rdma_qvlist_info *)msg;
 
-			valid_len += ((qv->num_vectors - 1) *
-				sizeof(struct virtchnl_rdma_qv_info));
+			valid_len = virtchnl_struct_size(qv, qv_info,
+							 qv->num_vectors);
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_RSS_KEY:
-		valid_len = sizeof(struct virtchnl_rss_key);
+		valid_len = virtchnl_rss_key_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_rss_key *vrk =
 				(struct virtchnl_rss_key *)msg;
-			valid_len += vrk->key_len - 1;
+			valid_len = virtchnl_struct_size(vrk, key,
+							 vrk->key_len);
 		}
 		break;
 	case VIRTCHNL_OP_CONFIG_RSS_LUT:
-		valid_len = sizeof(struct virtchnl_rss_lut);
+		valid_len = virtchnl_rss_lut_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_rss_lut *vrl =
 				(struct virtchnl_rss_lut *)msg;
-			valid_len += vrl->lut_entries - 1;
+			valid_len = virtchnl_struct_size(vrl, lut,
+							 vrl->lut_entries);
 		}
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
+	case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
+		valid_len = sizeof(struct virtchnl_rss_hfunc);
+		break;
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS:
 		break;
-	case VIRTCHNL_OP_SET_RSS_HENA:
-		valid_len = sizeof(struct virtchnl_rss_hena);
+	case VIRTCHNL_OP_SET_RSS_HASHCFG:
+		valid_len = sizeof(struct virtchnl_rss_hashcfg);
 		break;
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 	case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
@@ -1506,12 +1842,12 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		valid_len = sizeof(struct virtchnl_vf_res_request);
 		break;
 	case VIRTCHNL_OP_ENABLE_CHANNELS:
-		valid_len = sizeof(struct virtchnl_tc_info);
+		valid_len = virtchnl_tc_info_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_tc_info *vti =
 				(struct virtchnl_tc_info *)msg;
-			valid_len += (vti->num_tc - 1) *
-				     sizeof(struct virtchnl_channel_info);
+			valid_len = virtchnl_struct_size(vti, list,
+							 vti->num_tc);
 			if (vti->num_tc == 0)
 				err_msg_format = true;
 		}
@@ -1538,13 +1874,13 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 		break;
 	case VIRTCHNL_OP_ADD_VLAN_V2:
 	case VIRTCHNL_OP_DEL_VLAN_V2:
-		valid_len = sizeof(struct virtchnl_vlan_filter_list_v2);
+		valid_len = virtchnl_vlan_filter_list_v2_LEGACY_SIZEOF;
 		if (msglen >= valid_len) {
 			struct virtchnl_vlan_filter_list_v2 *vfl =
 			    (struct virtchnl_vlan_filter_list_v2 *)msg;
 
-			valid_len += (vfl->num_elements - 1) *
-				sizeof(struct virtchnl_vlan_filter);
+			valid_len = virtchnl_struct_size(vfl, filters,
+							 vfl->num_elements);
 
 			if (vfl->num_elements == 0) {
 				err_msg_format = true;
@@ -1558,6 +1894,41 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 	case VIRTCHNL_OP_DISABLE_VLAN_INSERTION_V2:
 		valid_len = sizeof(struct virtchnl_vlan_setting);
 		break;
+	case VIRTCHNL_OP_GET_QOS_CAPS:
+		break;
+	case VIRTCHNL_OP_CONFIG_QUEUE_BW:
+		valid_len = virtchnl_queues_bw_cfg_LEGACY_SIZEOF;
+		if (msglen >= valid_len) {
+			struct virtchnl_queues_bw_cfg *q_bw =
+				(struct virtchnl_queues_bw_cfg *)msg;
+
+			valid_len = virtchnl_struct_size(q_bw, cfg,
+							 q_bw->num_queues);
+			if (q_bw->num_queues == 0) {
+				err_msg_format = true;
+				break;
+			}
+		}
+		break;
+	case VIRTCHNL_OP_CONFIG_QUANTA:
+		valid_len = sizeof(struct virtchnl_quanta_cfg);
+		if (msglen >= valid_len) {
+			struct virtchnl_quanta_cfg *q_quanta =
+				(struct virtchnl_quanta_cfg *)msg;
+
+			if (q_quanta->quanta_size == 0 ||
+			    q_quanta->queue_select.num_queues == 0) {
+				err_msg_format = true;
+				break;
+			}
+		}
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_CAPS:
+		valid_len = sizeof(struct virtchnl_ptp_caps);
+		break;
+	case VIRTCHNL_OP_1588_PTP_GET_TIME:
+		valid_len = sizeof(struct virtchnl_phc_time);
+		break;
 	/* These are always errors coming from the VF. */
 	case VIRTCHNL_OP_EVENT:
 	case VIRTCHNL_OP_UNKNOWN:
diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h
index ae12696ec492..0217c1073735 100644
--- a/include/linux/backing-dev-defs.h
+++ b/include/linux/backing-dev-defs.h
@@ -63,6 +63,8 @@ enum wb_reason {
 struct wb_completion {
 	atomic_t		cnt;
 	wait_queue_head_t	*waitq;
+	unsigned long progress_stamp;	/* The jiffies when slow progress is detected */
+	unsigned long wait_start;	/* The jiffies when waiting for the writeback work to finish */
 };
 
 #define __WB_COMPLETION_INIT(_waitq)	\
@@ -141,8 +143,6 @@ struct bdi_writeback {
 	struct delayed_work dwork;	/* work item used for writeback */
 	struct delayed_work bw_dwork;	/* work item used for bandwidth estimate */
 
-	unsigned long dirty_sleep;	/* last wait */
-
 	struct list_head bdi_node;	/* anchored at bdi->wb_list */
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -154,6 +154,10 @@ struct bdi_writeback {
 	struct list_head blkcg_node;	/* anchored at blkcg->cgwb_list */
 	struct list_head b_attached;	/* attached inodes, protected by list_lock */
 	struct list_head offline_node;	/* anchored at offline_cgwbs */
+	struct work_struct switch_work;	/* work used to perform inode switching
+					 * to this wb */
+	struct llist_head switch_wbs_ctxs;	/* queued contexts for
+						 * writeback switching */
 
 	union {
 		struct work_struct release_work;
@@ -166,7 +170,9 @@ struct backing_dev_info {
 	u64 id;
 	struct rb_node rb_node; /* keyed by ->id */
 	struct list_head bdi_list;
-	unsigned long ra_pages;	/* max readahead in PAGE_SIZE units */
+	/* max readahead in PAGE_SIZE units */
+	unsigned long __data_racy ra_pages;
+
 	unsigned long io_pages;	/* max allowed IO size */
 
 	struct kref refcnt;	/* Reference counter for the structure */
@@ -179,6 +185,11 @@ struct backing_dev_info {
 	 * any dirty wbs, which is depended upon by bdi_has_dirty().
 	 */
 	atomic_long_t tot_write_bandwidth;
+	/*
+	 * Jiffies when last process was dirty throttled on this bdi. Used by
+	 * blk-wbt.
+	 */
+	unsigned long last_bdp_sleep;
 
 	struct bdi_writeback wb;  /* the root writeback info for this bdi */
 	struct list_head wb_list; /* list of all wbs */
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index fbad4fcd408e..0c8342747cab 100644
--- a/include/linux/backing-dev.h
+++ b/include/linux/backing-dev.h
@@ -38,7 +38,6 @@ struct backing_dev_info *bdi_alloc(int node_id);
 
 void wb_start_background_writeback(struct bdi_writeback *wb);
 void wb_workfn(struct work_struct *work);
-void wb_wakeup_delayed(struct bdi_writeback *wb);
 
 void wb_wait_for_completion(struct wb_completion *done);
 
@@ -46,7 +45,6 @@ extern spinlock_t bdi_lock;
 extern struct list_head bdi_list;
 
 extern struct workqueue_struct *bdi_wq;
-extern struct workqueue_struct *bdi_async_bio_wq;
 
 static inline bool wb_has_dirty_io(struct bdi_writeback *wb)
 {
@@ -68,16 +66,6 @@ static inline void wb_stat_mod(struct bdi_writeback *wb,
 	percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH);
 }
 
-static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
-{
-	wb_stat_mod(wb, item, 1);
-}
-
-static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
-{
-	wb_stat_mod(wb, item, -1);
-}
-
 static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item)
 {
 	return percpu_counter_read_positive(&wb->stat[item]);
@@ -120,12 +108,10 @@ int bdi_set_strict_limit(struct backing_dev_info *bdi, unsigned int strict_limit
  *
  * BDI_CAP_WRITEBACK:		Supports dirty page writeback, and dirty pages
  *				should contribute to accounting
- * BDI_CAP_WRITEBACK_ACCT:	Automatically account writeback pages
  * BDI_CAP_STRICTLIMIT:		Keep number of dirty pages below bdi threshold
  */
 #define BDI_CAP_WRITEBACK		(1 << 0)
-#define BDI_CAP_WRITEBACK_ACCT		(1 << 1)
-#define BDI_CAP_STRICTLIMIT		(1 << 2)
+#define BDI_CAP_STRICTLIMIT		(1 << 1)
 
 extern struct backing_dev_info noop_backing_dev_info;
 
@@ -251,6 +237,7 @@ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode)
 {
 #ifdef CONFIG_LOCKDEP
 	WARN_ON_ONCE(debug_locks &&
+		     (inode->i_sb->s_iflags & SB_I_CGROUPWB) &&
 		     (!lockdep_is_held(&inode->i_lock) &&
 		      !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) &&
 		      !lockdep_is_held(&inode->i_wb->list_lock)));
@@ -290,10 +277,11 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie)
 	rcu_read_lock();
 
 	/*
-	 * Paired with store_release in inode_switch_wbs_work_fn() and
+	 * Paired with a release fence in inode_do_switch_wbs() and
 	 * ensures that we see the new wb if we see cleared I_WB_SWITCH.
 	 */
-	cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH;
+	cookie->locked = inode_state_read_once(inode) & I_WB_SWITCH;
+	smp_rmb();
 
 	if (unlikely(cookie->locked))
 		xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags);
diff --git a/include/linux/backing-file.h b/include/linux/backing-file.h
new file mode 100644
index 000000000000..1476a6ed1bfd
--- /dev/null
+++ b/include/linux/backing-file.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Common helpers for stackable filesystems and backing files.
+ *
+ * Copyright (C) 2023 CTERA Networks.
+ */
+
+#ifndef _LINUX_BACKING_FILE_H
+#define _LINUX_BACKING_FILE_H
+
+#include <linux/file.h>
+#include <linux/uio.h>
+#include <linux/fs.h>
+
+struct backing_file_ctx {
+	const struct cred *cred;
+	void (*accessed)(struct file *file);
+	void (*end_write)(struct kiocb *iocb, ssize_t);
+};
+
+struct file *backing_file_open(const struct path *user_path, int flags,
+			       const struct path *real_path,
+			       const struct cred *cred);
+struct file *backing_tmpfile_open(const struct path *user_path, int flags,
+				  const struct path *real_parentpath,
+				  umode_t mode, const struct cred *cred);
+ssize_t backing_file_read_iter(struct file *file, struct iov_iter *iter,
+			       struct kiocb *iocb, int flags,
+			       struct backing_file_ctx *ctx);
+ssize_t backing_file_write_iter(struct file *file, struct iov_iter *iter,
+				struct kiocb *iocb, int flags,
+				struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_read(struct file *in, struct kiocb *iocb,
+				 struct pipe_inode_info *pipe, size_t len,
+				 unsigned int flags,
+				 struct backing_file_ctx *ctx);
+ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+				  struct file *out, struct kiocb *iocb,
+				  size_t len, unsigned int flags,
+				  struct backing_file_ctx *ctx);
+int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
+		      struct backing_file_ctx *ctx);
+
+#endif /* _LINUX_BACKING_FILE_H */
diff --git a/include/linux/backlight.h b/include/linux/backlight.h
index 614653e07e3a..f29a9ef1052e 100644
--- a/include/linux/backlight.h
+++ b/include/linux/backlight.h
@@ -10,9 +10,8 @@
 #define _LINUX_BACKLIGHT_H
 
 #include <linux/device.h>
-#include <linux/fb.h>
 #include <linux/mutex.h>
-#include <linux/notifier.h>
+#include <linux/types.h>
 
 /**
  * enum backlight_update_reason - what method was used to update backlight
@@ -65,24 +64,6 @@ enum backlight_type {
 	BACKLIGHT_TYPE_MAX,
 };
 
-/**
- * enum backlight_notification - the type of notification
- *
- * The notifications that is used for notification sent to the receiver
- * that registered notifications using backlight_register_notifier().
- */
-enum backlight_notification {
-	/**
-	 * @BACKLIGHT_REGISTERED: The backlight device is registered.
-	 */
-	BACKLIGHT_REGISTERED,
-
-	/**
-	 * @BACKLIGHT_UNREGISTERED: The backlight revice is unregistered.
-	 */
-	BACKLIGHT_UNREGISTERED,
-};
-
 /** enum backlight_scale - the type of scale used for brightness values
  *
  * The type of scale used for brightness values.
@@ -110,7 +91,6 @@ enum backlight_scale {
 };
 
 struct backlight_device;
-struct fb_info;
 
 /**
  * struct backlight_ops - backlight operations
@@ -160,18 +140,18 @@ struct backlight_ops {
 	int (*get_brightness)(struct backlight_device *);
 
 	/**
-	 * @check_fb: Check the framebuffer device.
+	 * @controls_device: Check against the display device
 	 *
-	 * Check if given framebuffer device is the one bound to this backlight.
-	 * This operation is optional and if not implemented it is assumed that the
-	 * fbdev is always the one bound to the backlight.
+	 * Check if the backlight controls the given display device. This
+	 * operation is optional and if not implemented it is assumed that
+	 * the display is always the one controlled by the backlight.
 	 *
 	 * RETURNS:
 	 *
-	 * If info is NULL or the info matches the fbdev bound to the backlight return true.
-	 * If info does not match the fbdev bound to the backlight return false.
+	 * If display_dev is NULL or display_dev matches the device controlled by
+	 * the backlight, return true. Otherwise return false.
 	 */
-	int (*check_fb)(struct backlight_device *bd, struct fb_info *info);
+	bool (*controls_device)(struct backlight_device *bd, struct device *display_dev);
 };
 
 /**
@@ -209,33 +189,18 @@ struct backlight_properties {
 	 * attribute: /sys/class/backlight/<backlight>/bl_power
 	 * When the power property is updated update_status() is called.
 	 *
-	 * The possible values are: (0: full on, 1 to 3: power saving
-	 * modes; 4: full off), see FB_BLANK_XXX.
+	 * The possible values are: (0: full on, 4: full off), see
+	 * BACKLIGHT_POWER constants.
 	 *
-	 * When the backlight device is enabled @power is set
-	 * to FB_BLANK_UNBLANK. When the backlight device is disabled
-	 * @power is set to FB_BLANK_POWERDOWN.
+	 * When the backlight device is enabled, @power is set to
+	 * BACKLIGHT_POWER_ON. When the backlight device is disabled,
+	 * @power is set to BACKLIGHT_POWER_OFF.
 	 */
 	int power;
 
-	/**
-	 * @fb_blank: The power state from the FBIOBLANK ioctl.
-	 *
-	 * When the FBIOBLANK ioctl is called @fb_blank is set to the
-	 * blank parameter and the update_status() operation is called.
-	 *
-	 * When the backlight device is enabled @fb_blank is set
-	 * to FB_BLANK_UNBLANK. When the backlight device is disabled
-	 * @fb_blank is set to FB_BLANK_POWERDOWN.
-	 *
-	 * Backlight drivers should avoid using this property. It has been
-	 * replaced by state & BL_CORE_FBLANK (although most drivers should
-	 * use backlight_is_blank() as the preferred means to get the blank
-	 * state).
-	 *
-	 * fb_blank is deprecated and will be removed.
-	 */
-	int fb_blank;
+#define BACKLIGHT_POWER_ON		(0)
+#define BACKLIGHT_POWER_OFF		(4)
+#define BACKLIGHT_POWER_REDUCED		(1) // deprecated; don't use in new code
 
 	/**
 	 * @type: The type of backlight supported.
@@ -312,11 +277,6 @@ struct backlight_device {
 	const struct backlight_ops *ops;
 
 	/**
-	 * @fb_notif: The framebuffer notifier block
-	 */
-	struct notifier_block fb_notif;
-
-	/**
 	 * @entry: List entry of all registered backlight devices
 	 */
 	struct list_head entry;
@@ -327,15 +287,7 @@ struct backlight_device {
 	struct device dev;
 
 	/**
-	 * @fb_bl_on: The state of individual fbdev's.
-	 *
-	 * Multiple fbdev's may share one backlight device. The fb_bl_on
-	 * records the state of the individual fbdev.
-	 */
-	bool fb_bl_on[FB_MAX];
-
-	/**
-	 * @use_count: The number of uses of fb_bl_on.
+	 * @use_count: The number of unblanked displays.
 	 */
 	int use_count;
 };
@@ -365,8 +317,7 @@ static inline int backlight_enable(struct backlight_device *bd)
 	if (!bd)
 		return 0;
 
-	bd->props.power = FB_BLANK_UNBLANK;
-	bd->props.fb_blank = FB_BLANK_UNBLANK;
+	bd->props.power = BACKLIGHT_POWER_ON;
 	bd->props.state &= ~BL_CORE_FBBLANK;
 
 	return backlight_update_status(bd);
@@ -381,8 +332,7 @@ static inline int backlight_disable(struct backlight_device *bd)
 	if (!bd)
 		return 0;
 
-	bd->props.power = FB_BLANK_POWERDOWN;
-	bd->props.fb_blank = FB_BLANK_POWERDOWN;
+	bd->props.power = BACKLIGHT_POWER_OFF;
 	bd->props.state |= BL_CORE_FBBLANK;
 
 	return backlight_update_status(bd);
@@ -395,15 +345,13 @@ static inline int backlight_disable(struct backlight_device *bd)
  * Display is expected to be blank if any of these is true::
  *
  *   1) if power in not UNBLANK
- *   2) if fb_blank is not UNBLANK
- *   3) if state indicate BLANK or SUSPENDED
+ *   2) if state indicate BLANK or SUSPENDED
  *
  * Returns true if display is expected to be blank, false otherwise.
  */
 static inline bool backlight_is_blank(const struct backlight_device *bd)
 {
-	return bd->props.power != FB_BLANK_UNBLANK ||
-	       bd->props.fb_blank != FB_BLANK_UNBLANK ||
+	return bd->props.power != BACKLIGHT_POWER_ON ||
 	       bd->props.state & (BL_CORE_SUSPENDED | BL_CORE_FBBLANK);
 }
 
@@ -440,13 +388,27 @@ void devm_backlight_device_unregister(struct device *dev,
 				      struct backlight_device *bd);
 void backlight_force_update(struct backlight_device *bd,
 			    enum backlight_update_reason reason);
-int backlight_register_notifier(struct notifier_block *nb);
-int backlight_unregister_notifier(struct notifier_block *nb);
 struct backlight_device *backlight_device_get_by_name(const char *name);
 struct backlight_device *backlight_device_get_by_type(enum backlight_type type);
 int backlight_device_set_brightness(struct backlight_device *bd,
 				    unsigned long brightness);
 
+#if IS_REACHABLE(CONFIG_BACKLIGHT_CLASS_DEVICE)
+void backlight_notify_blank(struct backlight_device *bd,
+			    struct device *display_dev,
+			    bool fb_on, bool prev_fb_on);
+void backlight_notify_blank_all(struct device *display_dev,
+				bool fb_on, bool prev_fb_on);
+#else
+static inline void backlight_notify_blank(struct backlight_device *bd,
+					  struct device *display_dev,
+					  bool fb_on, bool prev_fb_on)
+{ }
+static inline void backlight_notify_blank_all(struct device *display_dev,
+					      bool fb_on, bool prev_fb_on)
+{ }
+#endif
+
 #define to_backlight_device(obj) container_of(obj, struct backlight_device, dev)
 
 /**
diff --git a/include/linux/badblocks.h b/include/linux/badblocks.h
index 2426276b9bd3..996493917f36 100644
--- a/include/linux/badblocks.h
+++ b/include/linux/badblocks.h
@@ -15,6 +15,7 @@
 #define BB_OFFSET(x)	(((x) & BB_OFFSET_MASK) >> 9)
 #define BB_LEN(x)	(((x) & BB_LEN_MASK) + 1)
 #define BB_ACK(x)	(!!((x) & BB_ACK_MASK))
+#define BB_END(x)	(BB_OFFSET(x) + BB_LEN(x))
 #define BB_MAKE(a, l, ack) (((a)<<9) | ((l)-1) | ((u64)(!!(ack)) << 63))
 
 /* Bad block numbers are stored sorted in a single page.
@@ -41,11 +42,17 @@ struct badblocks {
 	sector_t size;		/* in sectors */
 };
 
-int badblocks_check(struct badblocks *bb, sector_t s, int sectors,
-		   sector_t *first_bad, int *bad_sectors);
-int badblocks_set(struct badblocks *bb, sector_t s, int sectors,
-			int acknowledged);
-int badblocks_clear(struct badblocks *bb, sector_t s, int sectors);
+struct badblocks_context {
+	sector_t	start;
+	sector_t	len;
+	int		ack;
+};
+
+int badblocks_check(struct badblocks *bb, sector_t s, sector_t sectors,
+		    sector_t *first_bad, sector_t *bad_sectors);
+bool badblocks_set(struct badblocks *bb, sector_t s, sector_t sectors,
+		   int acknowledged);
+bool badblocks_clear(struct badblocks *bb, sector_t s, sector_t sectors);
 void ack_all_badblocks(struct badblocks *bb);
 ssize_t badblocks_show(struct badblocks *bb, char *page, int unack);
 ssize_t badblocks_store(struct badblocks *bb, const char *page, size_t len,
@@ -63,4 +70,27 @@ static inline void devm_exit_badblocks(struct device *dev, struct badblocks *bb)
 	}
 	badblocks_exit(bb);
 }
+
+static inline int badblocks_full(struct badblocks *bb)
+{
+	return (bb->count >= MAX_BADBLOCKS);
+}
+
+static inline int badblocks_empty(struct badblocks *bb)
+{
+	return (bb->count == 0);
+}
+
+static inline void set_changed(struct badblocks *bb)
+{
+	if (bb->changed != 1)
+		bb->changed = 1;
+}
+
+static inline void clear_changed(struct badblocks *bb)
+{
+	if (bb->changed != 0)
+		bb->changed = 0;
+}
+
 #endif
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 5ca2d5699620..7cfe48769239 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -4,12 +4,13 @@
  *
  * Common interface definitions for making balloon pages movable by compaction.
  *
- * Balloon page migration makes use of the general non-lru movable page
+ * Balloon page migration makes use of the general "movable_ops page migration"
  * feature.
  *
  * page->private is used to reference the responsible balloon device.
- * page->mapping is used in context of non-lru page migration to reference
- * the address space operations for page isolation/migration/compaction.
+ * That these pages have movable_ops, and which movable_ops apply,
+ * is derived from the page type (PageOffline()) combined with the
+ * PG_movable_ops flag (PageMovableOps()).
  *
  * As the page isolation scanning step a compaction thread does is a lockless
  * procedure (from a page standpoint), it might bring some racy situations while
@@ -17,12 +18,10 @@
  * and safely perform balloon's page compaction and migration we must, always,
  * ensure following these simple rules:
  *
- *   i. when updating a balloon's page ->mapping element, strictly do it under
- *      the following lock order, independently of the far superior
- *      locking scheme (lru_lock, balloon_lock):
+ *   i. Setting the PG_movable_ops flag and page->private with the following
+ *	lock order
  *	    +-page_lock(page);
  *	      +--spin_lock_irq(&b_dev_info->pages_lock);
- *	            ... page->mapping updates here ...
  *
  *  ii. isolation or dequeueing procedure must remove the page from balloon
  *      device page list under b_dev_info->pages_lock.
@@ -78,6 +77,15 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon)
 
 #ifdef CONFIG_BALLOON_COMPACTION
 extern const struct movable_operations balloon_mops;
+/*
+ * balloon_page_device - get the b_dev_info descriptor for the balloon device
+ *			 that enqueues the given page.
+ */
+static inline struct balloon_dev_info *balloon_page_device(struct page *page)
+{
+	return (struct balloon_dev_info *)page_private(page);
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
 
 /*
  * balloon_page_insert - insert a page into the balloon's page list and make
@@ -92,68 +100,34 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 				       struct page *page)
 {
 	__SetPageOffline(page);
-	__SetPageMovable(page, &balloon_mops);
-	set_page_private(page, (unsigned long)balloon);
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION)) {
+		SetPageMovableOps(page);
+		set_page_private(page, (unsigned long)balloon);
+	}
 	list_add(&page->lru, &balloon->pages);
 }
 
-/*
- * balloon_page_delete - delete a page from balloon's page list and clear
- *			 the page->private assignement accordingly.
- * @page    : page to be released from balloon's page list
- *
- * Caller must ensure the page is locked and the spin_lock protecting balloon
- * pages list is held before deleting a page from the balloon device.
- */
-static inline void balloon_page_delete(struct page *page)
+static inline gfp_t balloon_mapping_gfp_mask(void)
 {
-	__ClearPageOffline(page);
-	__ClearPageMovable(page);
-	set_page_private(page, 0);
-	/*
-	 * No touch page.lru field once @page has been isolated
-	 * because VM is using the field.
-	 */
-	if (!PageIsolated(page))
-		list_del(&page->lru);
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION))
+		return GFP_HIGHUSER_MOVABLE;
+	return GFP_HIGHUSER;
 }
 
 /*
- * balloon_page_device - get the b_dev_info descriptor for the balloon device
- *			 that enqueues the given page.
+ * balloon_page_finalize - prepare a balloon page that was removed from the
+ *			   balloon list for release to the page allocator
+ * @page: page to be released to the page allocator
+ *
+ * Caller must ensure that the page is locked.
  */
-static inline struct balloon_dev_info *balloon_page_device(struct page *page)
+static inline void balloon_page_finalize(struct page *page)
 {
-	return (struct balloon_dev_info *)page_private(page);
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION))
+		set_page_private(page, 0);
+	/* PageOffline is sticky until the page is freed to the buddy. */
 }
 
-static inline gfp_t balloon_mapping_gfp_mask(void)
-{
-	return GFP_HIGHUSER_MOVABLE;
-}
-
-#else /* !CONFIG_BALLOON_COMPACTION */
-
-static inline void balloon_page_insert(struct balloon_dev_info *balloon,
-				       struct page *page)
-{
-	__SetPageOffline(page);
-	list_add(&page->lru, &balloon->pages);
-}
-
-static inline void balloon_page_delete(struct page *page)
-{
-	__ClearPageOffline(page);
-	list_del(&page->lru);
-}
-
-static inline gfp_t balloon_mapping_gfp_mask(void)
-{
-	return GFP_HIGHUSER;
-}
-
-#endif /* CONFIG_BALLOON_COMPACTION */
-
 /*
  * balloon_page_push - insert a page into a page list.
  * @head : pointer to list
diff --git a/include/linux/base64.h b/include/linux/base64.h
index 660d4cb1ef31..a2c6c9222da3 100644
--- a/include/linux/base64.h
+++ b/include/linux/base64.h
@@ -8,9 +8,15 @@
 
 #include <linux/types.h>
 
+enum base64_variant {
+	BASE64_STD,       /* RFC 4648 (standard) */
+	BASE64_URLSAFE,   /* RFC 4648 (base64url) */
+	BASE64_IMAP,      /* RFC 3501 */
+};
+
 #define BASE64_CHARS(nbytes)   DIV_ROUND_UP((nbytes) * 4, 3)
 
-int base64_encode(const u8 *src, int len, char *dst);
-int base64_decode(const char *src, int len, u8 *dst);
+int base64_encode(const u8 *src, int len, char *dst, bool padding, enum base64_variant variant);
+int base64_decode(const char *src, int len, u8 *dst, bool padding, enum base64_variant variant);
 
 #endif /* _LINUX_BASE64_H */
diff --git a/include/linux/bcm47xx_nvram.h b/include/linux/bcm47xx_nvram.h
index 7615f8d7b1ed..e4b6ce953ddb 100644
--- a/include/linux/bcm47xx_nvram.h
+++ b/include/linux/bcm47xx_nvram.h
@@ -7,7 +7,6 @@
 
 #include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/vmalloc.h>
 
 #ifdef CONFIG_BCM47XX_NVRAM
diff --git a/include/linux/bcm47xx_sprom.h b/include/linux/bcm47xx_sprom.h
index f8254fd53e15..40a7da3ef50e 100644
--- a/include/linux/bcm47xx_sprom.h
+++ b/include/linux/bcm47xx_sprom.h
@@ -5,8 +5,8 @@
 #ifndef __BCM47XX_SPROM_H
 #define __BCM47XX_SPROM_H
 
+#include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/vmalloc.h>
 
 struct ssb_sprom;
diff --git a/include/linux/bcm963xx_nvram.h b/include/linux/bcm963xx_nvram.h
index c8c7f01159fe..48830bf18042 100644
--- a/include/linux/bcm963xx_nvram.h
+++ b/include/linux/bcm963xx_nvram.h
@@ -81,25 +81,21 @@ static int __maybe_unused bcm963xx_nvram_checksum(
 	const struct bcm963xx_nvram *nvram,
 	u32 *expected_out, u32 *actual_out)
 {
+	const u32 zero = 0;
 	u32 expected, actual;
 	size_t len;
 
 	if (nvram->version <= 4) {
 		expected = nvram->checksum_v4;
-		len = BCM963XX_NVRAM_V4_SIZE - sizeof(u32);
+		len = BCM963XX_NVRAM_V4_SIZE;
 	} else {
 		expected = nvram->checksum_v5;
-		len = BCM963XX_NVRAM_V5_SIZE - sizeof(u32);
+		len = BCM963XX_NVRAM_V5_SIZE;
 	}
 
-	/*
-	 * Calculate the CRC32 value for the nvram with a checksum value
-	 * of 0 without modifying or copying the nvram by combining:
-	 * - The CRC32 of the nvram without the checksum value
-	 * - The CRC32 of a zero checksum value (which is also 0)
-	 */
-	actual = crc32_le_combine(
-		crc32_le(~0, (u8 *)nvram, len), 0, sizeof(u32));
+	/* Calculate the CRC32 of the nvram with the checksum field set to 0. */
+	actual = crc32_le(~0, nvram, len - sizeof(u32));
+	actual = crc32_le(actual, &zero, sizeof(u32));
 
 	if (expected_out)
 		*expected_out = expected;
diff --git a/include/linux/bcma/bcma_driver_pci.h b/include/linux/bcma/bcma_driver_pci.h
index 68da8dba5162..dba41b65ae0d 100644
--- a/include/linux/bcma/bcma_driver_pci.h
+++ b/include/linux/bcma/bcma_driver_pci.h
@@ -203,7 +203,7 @@ struct pci_dev;
 #define BCMA_CORE_PCI_MDIO_RXCTRL0		0x840
 
 /* PCIE Root Capability Register bits (Host mode only) */
-#define BCMA_CORE_PCI_RC_CRS_VISIBILITY		0x0001
+#define BCMA_CORE_PCI_RC_RRS_VISIBILITY		0x0001
 
 struct bcma_drv_pci;
 struct bcma_bus;
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 8d51f69f9f5e..65abd5ab8836 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -19,13 +19,13 @@ struct linux_binprm {
 #ifdef CONFIG_MMU
 	struct vm_area_struct *vma;
 	unsigned long vma_pages;
+	unsigned long argmin; /* rlimit marker for copy_strings() */
 #else
 # define MAX_ARG_PAGES	32
 	struct page *page[MAX_ARG_PAGES];
 #endif
 	struct mm_struct *mm;
 	unsigned long p; /* current top of mem */
-	unsigned long argmin; /* rlimit marker for copy_strings() */
 	unsigned int
 		/* Should an execfd be passed to userspace? */
 		have_execfd:1,
@@ -42,7 +42,14 @@ struct linux_binprm {
 		 * Set when errors can no longer be returned to the
 		 * original userspace.
 		 */
-		point_of_no_return:1;
+		point_of_no_return:1,
+		/* Set when "comm" must come from the dentry. */
+		comm_from_dentry:1,
+		/*
+		 * Set by user space to check executability according to the
+		 * caller's environment.
+		 */
+		is_check:1;
 	struct file *executable; /* Executable to pass to the interpreter */
 	struct file *interpreter;
 	struct file *file;
@@ -57,7 +64,7 @@ struct linux_binprm {
 	const char *fdpath;	/* generated filename for execveat */
 	unsigned interp_flags;
 	int execfd;		/* File descriptor of the executable */
-	unsigned long loader, exec;
+	unsigned long exec;
 
 	struct rlimit rlim_stack; /* Saved RLIMIT_STACK used during exec. */
 
@@ -83,13 +90,22 @@ struct linux_binfmt {
 	struct list_head lh;
 	struct module *module;
 	int (*load_binary)(struct linux_binprm *);
-	int (*load_shlib)(struct file *);
 #ifdef CONFIG_COREDUMP
 	int (*core_dump)(struct coredump_params *cprm);
 	unsigned long min_coredump;	/* minimal dump size */
 #endif
 } __randomize_layout;
 
+#if IS_ENABLED(CONFIG_BINFMT_MISC)
+struct binfmt_misc {
+	struct list_head entries;
+	rwlock_t entries_lock;
+	bool enabled;
+} __randomize_layout;
+
+extern struct binfmt_misc init_binfmt_misc;
+#endif
+
 extern void __register_binfmt(struct linux_binfmt *fmt, int insert);
 
 /* Registration of default binfmt handlers */
diff --git a/include/linux/bio-integrity.h b/include/linux/bio-integrity.h
new file mode 100644
index 000000000000..21e4652dcfd2
--- /dev/null
+++ b/include/linux/bio-integrity.h
@@ -0,0 +1,148 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_BIO_INTEGRITY_H
+#define _LINUX_BIO_INTEGRITY_H
+
+#include <linux/bio.h>
+
+enum bip_flags {
+	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
+	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
+	BIP_DISK_NOCHECK	= 1 << 2, /* disable disk integrity checking */
+	BIP_IP_CHECKSUM		= 1 << 3, /* IP checksum */
+	BIP_COPY_USER		= 1 << 4, /* Kernel bounce buffer in use */
+	BIP_CHECK_GUARD		= 1 << 5, /* guard check */
+	BIP_CHECK_REFTAG	= 1 << 6, /* reftag check */
+	BIP_CHECK_APPTAG	= 1 << 7, /* apptag check */
+
+	BIP_MEMPOOL		= 1 << 15, /* buffer backed by mempool */
+};
+
+struct bio_integrity_payload {
+	struct bvec_iter	bip_iter;
+
+	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
+	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
+	unsigned short		bip_flags;	/* control flags */
+	u16			app_tag;	/* application tag value */
+
+	struct bio_vec		*bip_vec;
+};
+
+#define BIP_CLONE_FLAGS (BIP_MAPPED_INTEGRITY | BIP_IP_CHECKSUM | \
+			 BIP_CHECK_GUARD | BIP_CHECK_REFTAG | BIP_CHECK_APPTAG)
+
+#ifdef CONFIG_BLK_DEV_INTEGRITY
+
+#define bip_for_each_vec(bvl, bip, iter)				\
+	for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
+
+#define bio_for_each_integrity_vec(_bvl, _bio, _iter)			\
+	for_each_bio(_bio)						\
+		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
+
+static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
+{
+	if (bio->bi_opf & REQ_INTEGRITY)
+		return bio->bi_integrity;
+
+	return NULL;
+}
+
+static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+
+	if (bip)
+		return bip->bip_flags & flag;
+
+	return false;
+}
+
+static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
+{
+	return bip->bip_iter.bi_sector;
+}
+
+static inline void bip_set_seed(struct bio_integrity_payload *bip,
+				sector_t seed)
+{
+	bip->bip_iter.bi_sector = seed;
+}
+
+void bio_integrity_init(struct bio *bio, struct bio_integrity_payload *bip,
+		struct bio_vec *bvecs, unsigned int nr_vecs);
+struct bio_integrity_payload *bio_integrity_alloc(struct bio *bio, gfp_t gfp,
+		unsigned int nr);
+int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len,
+		unsigned int offset);
+int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter);
+int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta);
+void bio_integrity_unmap_user(struct bio *bio);
+bool bio_integrity_prep(struct bio *bio);
+void bio_integrity_advance(struct bio *bio, unsigned int bytes_done);
+void bio_integrity_trim(struct bio *bio);
+int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask);
+
+#else /* CONFIG_BLK_DEV_INTEGRITY */
+
+static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
+{
+	return NULL;
+}
+
+static inline int bio_integrity_map_user(struct bio *bio, struct iov_iter *iter)
+{
+	return -EINVAL;
+}
+
+static inline int bio_integrity_map_iter(struct bio *bio, struct uio_meta *meta)
+{
+	return -EINVAL;
+}
+
+static inline void bio_integrity_unmap_user(struct bio *bio)
+{
+}
+
+static inline bool bio_integrity_prep(struct bio *bio)
+{
+	return true;
+}
+
+static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
+		gfp_t gfp_mask)
+{
+	return 0;
+}
+
+static inline void bio_integrity_advance(struct bio *bio,
+		unsigned int bytes_done)
+{
+}
+
+static inline void bio_integrity_trim(struct bio *bio)
+{
+}
+
+static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
+{
+	return false;
+}
+
+static inline struct bio_integrity_payload *
+bio_integrity_alloc(struct bio *bio, gfp_t gfp, unsigned int nr)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
+					unsigned int len, unsigned int offset)
+{
+	return 0;
+}
+#endif /* CONFIG_BLK_DEV_INTEGRITY */
+
+void bio_integrity_alloc_buf(struct bio *bio, bool zero_buffer);
+void bio_integrity_free_buf(struct bio_integrity_payload *bip);
+
+#endif /* _LINUX_BIO_INTEGRITY_H */
diff --git a/include/linux/bio.h b/include/linux/bio.h
index b3e7529ff55e..ad2d57908c1c 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -11,6 +11,7 @@
 #include <linux/uio.h>
 
 #define BIO_MAX_VECS		256U
+#define BIO_MAX_INLINE_VECS	UIO_MAXIOV
 
 struct queue_limits;
 
@@ -19,9 +20,6 @@ static inline unsigned int bio_max_segs(unsigned int nr_segs)
 	return min(nr_segs, BIO_MAX_VECS);
 }
 
-#define bio_prio(bio)			(bio)->bi_ioprio
-#define bio_set_prio(bio, prio)		((bio)->bi_ioprio = prio)
-
 #define bio_iter_iovec(bio, iter)				\
 	bvec_iter_bvec((bio)->bi_io_vec, (iter))
 
@@ -229,7 +227,7 @@ static inline void bio_cnt_set(struct bio *bio, unsigned int count)
 
 static inline bool bio_flagged(struct bio *bio, unsigned int bit)
 {
-	return (bio->bi_flags & (1U << bit)) != 0;
+	return bio->bi_flags & (1U << bit);
 }
 
 static inline void bio_set_flag(struct bio *bio, unsigned int bit)
@@ -253,6 +251,11 @@ static inline struct page *bio_first_page_all(struct bio *bio)
 	return bio_first_bvec_all(bio)->bv_page;
 }
 
+static inline struct folio *bio_first_folio_all(struct bio *bio)
+{
+	return page_folio(bio_first_page_all(bio));
+}
+
 static inline struct bio_vec *bio_last_bvec_all(struct bio *bio)
 {
 	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
@@ -281,9 +284,14 @@ static inline void bio_first_folio(struct folio_iter *fi, struct bio *bio,
 {
 	struct bio_vec *bvec = bio_first_bvec_all(bio) + i;
 
+	if (unlikely(i >= bio->bi_vcnt)) {
+		fi->folio = NULL;
+		return;
+	}
+
 	fi->folio = page_folio(bvec->bv_page);
 	fi->offset = bvec->bv_offset +
-			PAGE_SIZE * (bvec->bv_page - &fi->folio->page);
+			PAGE_SIZE * folio_page_idx(fi->folio, bvec->bv_page);
 	fi->_seg_count = bvec->bv_len;
 	fi->length = min(folio_size(fi->folio) - fi->offset, fi->_seg_count);
 	fi->_next = folio_next(fi->folio);
@@ -298,10 +306,8 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 		fi->offset = 0;
 		fi->length = min(folio_size(fi->folio), fi->_seg_count);
 		fi->_next = folio_next(fi->folio);
-	} else if (fi->_i + 1 < bio->bi_vcnt) {
-		bio_first_folio(fi, bio, fi->_i + 1);
 	} else {
-		fi->folio = NULL;
+		bio_first_folio(fi, bio, fi->_i + 1);
 	}
 }
 
@@ -313,72 +319,13 @@ static inline void bio_next_folio(struct folio_iter *fi, struct bio *bio)
 #define bio_for_each_folio_all(fi, bio)				\
 	for (bio_first_folio(&fi, bio, 0); fi.folio; bio_next_folio(&fi, bio))
 
-enum bip_flags {
-	BIP_BLOCK_INTEGRITY	= 1 << 0, /* block layer owns integrity data */
-	BIP_MAPPED_INTEGRITY	= 1 << 1, /* ref tag has been remapped */
-	BIP_CTRL_NOCHECK	= 1 << 2, /* disable HBA integrity checking */
-	BIP_DISK_NOCHECK	= 1 << 3, /* disable disk integrity checking */
-	BIP_IP_CHECKSUM		= 1 << 4, /* IP checksum */
-};
-
-/*
- * bio integrity payload
- */
-struct bio_integrity_payload {
-	struct bio		*bip_bio;	/* parent bio */
-
-	struct bvec_iter	bip_iter;
-
-	unsigned short		bip_vcnt;	/* # of integrity bio_vecs */
-	unsigned short		bip_max_vcnt;	/* integrity bio_vec slots */
-	unsigned short		bip_flags;	/* control flags */
-
-	struct bvec_iter	bio_iter;	/* for rewinding parent bio */
-
-	struct work_struct	bip_work;	/* I/O completion */
-
-	struct bio_vec		*bip_vec;
-	struct bio_vec		bip_inline_vecs[];/* embedded bvec array */
-};
-
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-static inline struct bio_integrity_payload *bio_integrity(struct bio *bio)
-{
-	if (bio->bi_opf & REQ_INTEGRITY)
-		return bio->bi_integrity;
-
-	return NULL;
-}
-
-static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
-{
-	struct bio_integrity_payload *bip = bio_integrity(bio);
-
-	if (bip)
-		return bip->bip_flags & flag;
-
-	return false;
-}
-
-static inline sector_t bip_get_seed(struct bio_integrity_payload *bip)
-{
-	return bip->bip_iter.bi_sector;
-}
-
-static inline void bip_set_seed(struct bio_integrity_payload *bip,
-				sector_t seed)
-{
-	bip->bip_iter.bi_sector = seed;
-}
-
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-
 void bio_trim(struct bio *bio, sector_t offset, sector_t size);
 extern struct bio *bio_split(struct bio *bio, int sectors,
 			     gfp_t gfp, struct bio_set *bs);
-struct bio *bio_split_rw(struct bio *bio, const struct queue_limits *lim,
-		unsigned *segs, struct bio_set *bs, unsigned max_bytes);
+int bio_split_io_at(struct bio *bio, const struct queue_limits *lim,
+		unsigned *segs, unsigned max_bytes, unsigned len_align);
+u8 bio_seg_gap(struct request_queue *q, struct bio *prev, struct bio *next,
+		u8 gaps_bit);
 
 /**
  * bio_next_split - get next @sectors from a bio, splitting if necessary
@@ -458,23 +405,53 @@ static inline int bio_iov_vecs_to_alloc(struct iov_iter *iter, int max_segs)
 
 struct request_queue;
 
-extern int submit_bio_wait(struct bio *bio);
 void bio_init(struct bio *bio, struct block_device *bdev, struct bio_vec *table,
 	      unsigned short max_vecs, blk_opf_t opf);
+static inline void bio_init_inline(struct bio *bio, struct block_device *bdev,
+	      unsigned short max_vecs, blk_opf_t opf)
+{
+	bio_init(bio, bdev, bio_inline_vecs(bio), max_vecs, opf);
+}
 extern void bio_uninit(struct bio *);
 void bio_reset(struct bio *bio, struct block_device *bdev, blk_opf_t opf);
 void bio_chain(struct bio *, struct bio *);
 
-int bio_add_page(struct bio *, struct page *, unsigned len, unsigned off);
-bool bio_add_folio(struct bio *, struct folio *, size_t len, size_t off);
-extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *,
-			   unsigned int, unsigned int);
-int bio_add_zone_append_page(struct bio *bio, struct page *page,
-			     unsigned int len, unsigned int offset);
+int __must_check bio_add_page(struct bio *bio, struct page *page, unsigned len,
+			      unsigned off);
+bool __must_check bio_add_folio(struct bio *bio, struct folio *folio,
+				size_t len, size_t off);
 void __bio_add_page(struct bio *bio, struct page *page,
 		unsigned int len, unsigned int off);
-int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter);
-void bio_iov_bvec_set(struct bio *bio, struct iov_iter *iter);
+void bio_add_folio_nofail(struct bio *bio, struct folio *folio, size_t len,
+			  size_t off);
+void bio_add_virt_nofail(struct bio *bio, void *vaddr, unsigned len);
+
+/**
+ * bio_add_max_vecs - number of bio_vecs needed to add data to a bio
+ * @kaddr: kernel virtual address to add
+ * @len: length in bytes to add
+ *
+ * Calculate how many bio_vecs need to be allocated to add the kernel virtual
+ * address range in [@kaddr:@len] in the worse case.
+ */
+static inline unsigned int bio_add_max_vecs(void *kaddr, unsigned int len)
+{
+	if (is_vmalloc_addr(kaddr))
+		return DIV_ROUND_UP(offset_in_page(kaddr) + len, PAGE_SIZE);
+	return 1;
+}
+
+unsigned int bio_add_vmalloc_chunk(struct bio *bio, void *vaddr, unsigned len);
+bool bio_add_vmalloc(struct bio *bio, void *vaddr, unsigned int len);
+
+int submit_bio_wait(struct bio *bio);
+int bdev_rw_virt(struct block_device *bdev, sector_t sector, void *data,
+		size_t len, enum req_op op);
+
+int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter,
+		unsigned len_align_mask);
+
+void bio_iov_bvec_set(struct bio *bio, const struct iov_iter *iter);
 void __bio_release_pages(struct bio *bio, bool mark_dirty);
 extern void bio_set_pages_dirty(struct bio *bio);
 extern void bio_check_pages_dirty(struct bio *bio);
@@ -484,11 +461,16 @@ extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter,
 extern void bio_copy_data(struct bio *dst, struct bio *src);
 extern void bio_free_pages(struct bio *bio);
 void guard_bio_eod(struct bio *bio);
-void zero_fill_bio(struct bio *bio);
+void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter);
+
+static inline void zero_fill_bio(struct bio *bio)
+{
+	zero_fill_bio_iter(bio, bio->bi_iter);
+}
 
 static inline void bio_release_pages(struct bio *bio, bool mark_dirty)
 {
-	if (!bio_flagged(bio, BIO_NO_PAGE_REF))
+	if (bio_flagged(bio, BIO_PAGE_PINNED))
 		__bio_release_pages(bio, mark_dirty);
 }
 
@@ -596,6 +578,13 @@ static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
 	bl->tail = bl2->tail;
 }
 
+static inline void bio_list_merge_init(struct bio_list *bl,
+		struct bio_list *bl2)
+{
+	bio_list_merge(bl, bl2);
+	bio_list_init(bl2);
+}
+
 static inline void bio_list_merge_head(struct bio_list *bl,
 				       struct bio_list *bl2)
 {
@@ -669,10 +658,6 @@ struct bio_set {
 
 	mempool_t bio_pool;
 	mempool_t bvec_pool;
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-	mempool_t bio_integrity_pool;
-	mempool_t bvec_integrity_pool;
-#endif
 
 	unsigned int back_pad;
 	/*
@@ -695,88 +680,6 @@ static inline bool bioset_initialized(struct bio_set *bs)
 	return bs->bio_slab != NULL;
 }
 
-#if defined(CONFIG_BLK_DEV_INTEGRITY)
-
-#define bip_for_each_vec(bvl, bip, iter)				\
-	for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter)
-
-#define bio_for_each_integrity_vec(_bvl, _bio, _iter)			\
-	for_each_bio(_bio)						\
-		bip_for_each_vec(_bvl, _bio->bi_integrity, _iter)
-
-extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int);
-extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int);
-extern bool bio_integrity_prep(struct bio *);
-extern void bio_integrity_advance(struct bio *, unsigned int);
-extern void bio_integrity_trim(struct bio *);
-extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t);
-extern int bioset_integrity_create(struct bio_set *, int);
-extern void bioset_integrity_free(struct bio_set *);
-extern void bio_integrity_init(void);
-
-#else /* CONFIG_BLK_DEV_INTEGRITY */
-
-static inline void *bio_integrity(struct bio *bio)
-{
-	return NULL;
-}
-
-static inline int bioset_integrity_create(struct bio_set *bs, int pool_size)
-{
-	return 0;
-}
-
-static inline void bioset_integrity_free (struct bio_set *bs)
-{
-	return;
-}
-
-static inline bool bio_integrity_prep(struct bio *bio)
-{
-	return true;
-}
-
-static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src,
-				      gfp_t gfp_mask)
-{
-	return 0;
-}
-
-static inline void bio_integrity_advance(struct bio *bio,
-					 unsigned int bytes_done)
-{
-	return;
-}
-
-static inline void bio_integrity_trim(struct bio *bio)
-{
-	return;
-}
-
-static inline void bio_integrity_init(void)
-{
-	return;
-}
-
-static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag)
-{
-	return false;
-}
-
-static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp,
-								unsigned int nr)
-{
-	return ERR_PTR(-EINVAL);
-}
-
-static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
-					unsigned int len, unsigned int offset)
-{
-	return 0;
-}
-
-#endif /* CONFIG_BLK_DEV_INTEGRITY */
-
 /*
  * Mark a bio as polled. Note that for async polled IO, the caller must
  * expect -EWOULDBLOCK if we cannot allocate a request (or other resources).
@@ -787,7 +690,7 @@ static inline int bio_integrity_add_page(struct bio *bio, struct page *page,
 static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb)
 {
 	bio->bi_opf |= REQ_POLLED;
-	if (!is_sync_kiocb(kiocb))
+	if (kiocb->ki_flags & IOCB_NOWAIT)
 		bio->bi_opf |= REQ_NOWAIT;
 }
 
@@ -796,7 +699,28 @@ static inline void bio_clear_polled(struct bio *bio)
 	bio->bi_opf &= ~REQ_POLLED;
 }
 
+/**
+ * bio_is_zone_append - is this a zone append bio?
+ * @bio:	bio to check
+ *
+ * Check if @bio is a zone append operation.  Core block layer code and end_io
+ * handlers must use this instead of an open coded REQ_OP_ZONE_APPEND check
+ * because the block layer can rewrite REQ_OP_ZONE_APPEND to REQ_OP_WRITE if
+ * it is not natively supported.
+ */
+static inline bool bio_is_zone_append(struct bio *bio)
+{
+	if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED))
+		return false;
+	return bio_op(bio) == REQ_OP_ZONE_APPEND ||
+		bio_flagged(bio, BIO_EMULATES_ZONE_APPEND);
+}
+
 struct bio *blk_next_bio(struct bio *bio, struct block_device *bdev,
 		unsigned int nr_pages, blk_opf_t opf, gfp_t gfp);
+struct bio *bio_chain_and_submit(struct bio *prev, struct bio *new);
+
+struct bio *blk_alloc_discard_bio(struct block_device *bdev,
+		sector_t *sector, sector_t *nr_sects, gfp_t gfp_mask);
 
 #endif /* __LINUX_BIO_H */
diff --git a/include/linux/bit_spinlock.h b/include/linux/bit_spinlock.h
index bbc4730a6505..c0989b5b0407 100644
--- a/include/linux/bit_spinlock.h
+++ b/include/linux/bit_spinlock.h
@@ -13,7 +13,7 @@
  * Don't use this unless you really need to: spin_lock() and spin_unlock()
  * are significantly faster.
  */
-static inline void bit_spin_lock(int bitnum, unsigned long *addr)
+static __always_inline void bit_spin_lock(int bitnum, unsigned long *addr)
 {
 	/*
 	 * Assuming the lock is uncontended, this never enters
@@ -38,7 +38,7 @@ static inline void bit_spin_lock(int bitnum, unsigned long *addr)
 /*
  * Return true if it was acquired
  */
-static inline int bit_spin_trylock(int bitnum, unsigned long *addr)
+static __always_inline int bit_spin_trylock(int bitnum, unsigned long *addr)
 {
 	preempt_disable();
 #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK)
@@ -54,7 +54,7 @@ static inline int bit_spin_trylock(int bitnum, unsigned long *addr)
 /*
  *  bit-based spin_unlock()
  */
-static inline void bit_spin_unlock(int bitnum, unsigned long *addr)
+static __always_inline void bit_spin_unlock(int bitnum, unsigned long *addr)
 {
 #ifdef CONFIG_DEBUG_SPINLOCK
 	BUG_ON(!test_bit(bitnum, addr));
@@ -71,7 +71,7 @@ static inline void bit_spin_unlock(int bitnum, unsigned long *addr)
  *  non-atomic version, which can be used eg. if the bit lock itself is
  *  protecting the rest of the flags in the word.
  */
-static inline void __bit_spin_unlock(int bitnum, unsigned long *addr)
+static __always_inline void __bit_spin_unlock(int bitnum, unsigned long *addr)
 {
 #ifdef CONFIG_DEBUG_SPINLOCK
 	BUG_ON(!test_bit(bitnum, addr));
diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index ebfa12f69501..126dc5b380af 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -8,6 +8,7 @@
 #define _LINUX_BITFIELD_H
 
 #include <linux/build_bug.h>
+#include <linux/typecheck.h>
 #include <asm/byteorder.h>
 
 /*
@@ -16,6 +17,7 @@
  * FIELD_{GET,PREP} macros take as first parameter shifted mask
  * from which they extract the base mask and shift amount.
  * Mask must be a compilation time constant.
+ * field_{get,prep} are variants that take a non-const mask.
  *
  * Example:
  *
@@ -38,8 +40,7 @@
  *	  FIELD_PREP(REG_FIELD_D, 0x40);
  *
  * Modify:
- *  reg &= ~REG_FIELD_C;
- *  reg |= FIELD_PREP(REG_FIELD_C, c);
+ *  FIELD_MODIFY(REG_FIELD_C, &reg, c);
  */
 
 #define __bf_shf(x) (__builtin_ffsll(x) - 1)
@@ -60,21 +61,42 @@
 
 #define __bf_cast_unsigned(type, x)	((__unsigned_scalar_typeof(type))(x))
 
-#define __BF_FIELD_CHECK(_mask, _reg, _val, _pfx)			\
+#define __BF_FIELD_CHECK_MASK(_mask, _val, _pfx)			\
 	({								\
 		BUILD_BUG_ON_MSG(!__builtin_constant_p(_mask),		\
 				 _pfx "mask is not constant");		\
 		BUILD_BUG_ON_MSG((_mask) == 0, _pfx "mask is zero");	\
 		BUILD_BUG_ON_MSG(__builtin_constant_p(_val) ?		\
-				 ~((_mask) >> __bf_shf(_mask)) & (_val) : 0, \
+				 ~((_mask) >> __bf_shf(_mask)) &	\
+					(0 + (_val)) : 0,		\
 				 _pfx "value too large for the field"); \
-		BUILD_BUG_ON_MSG(__bf_cast_unsigned(_mask, _mask) >	\
-				 __bf_cast_unsigned(_reg, ~0ull),	\
-				 _pfx "type of reg too small for mask"); \
 		__BUILD_BUG_ON_NOT_POWER_OF_2((_mask) +			\
 					      (1ULL << __bf_shf(_mask))); \
 	})
 
+#define __BF_FIELD_CHECK_REG(mask, reg, pfx)				\
+	BUILD_BUG_ON_MSG(__bf_cast_unsigned(mask, mask) >		\
+			 __bf_cast_unsigned(reg, ~0ull),		\
+			 pfx "type of reg too small for mask")
+
+#define __BF_FIELD_CHECK(mask, reg, val, pfx)				\
+	({								\
+		__BF_FIELD_CHECK_MASK(mask, val, pfx);			\
+		__BF_FIELD_CHECK_REG(mask, reg, pfx);			\
+	})
+
+#define __FIELD_PREP(mask, val, pfx)					\
+	({								\
+		__BF_FIELD_CHECK_MASK(mask, val, pfx);			\
+		((typeof(mask))(val) << __bf_shf(mask)) & (mask);	\
+	})
+
+#define __FIELD_GET(mask, reg, pfx)					\
+	({								\
+		__BF_FIELD_CHECK_MASK(mask, 0U, pfx);			\
+		(typeof(mask))(((reg) & (mask)) >> __bf_shf(mask));	\
+	})
+
 /**
  * FIELD_MAX() - produce the maximum value representable by a field
  * @_mask: shifted mask defining the field's length and position
@@ -111,8 +133,8 @@
  */
 #define FIELD_PREP(_mask, _val)						\
 	({								\
-		__BF_FIELD_CHECK(_mask, 0ULL, _val, "FIELD_PREP: ");	\
-		((typeof(_mask))(_val) << __bf_shf(_mask)) & (_mask);	\
+		__BF_FIELD_CHECK_REG(_mask, 0ULL, "FIELD_PREP: ");	\
+		__FIELD_PREP(_mask, _val, "FIELD_PREP: ");		\
 	})
 
 #define __BF_CHECK_POW2(n)	BUILD_BUG_ON_ZERO(((n) & ((n) - 1)) != 0)
@@ -151,8 +173,25 @@
  */
 #define FIELD_GET(_mask, _reg)						\
 	({								\
-		__BF_FIELD_CHECK(_mask, _reg, 0U, "FIELD_GET: ");	\
-		(typeof(_mask))(((_reg) & (_mask)) >> __bf_shf(_mask));	\
+		__BF_FIELD_CHECK_REG(_mask, _reg, "FIELD_GET: ");	\
+		__FIELD_GET(_mask, _reg, "FIELD_GET: ");		\
+	})
+
+/**
+ * FIELD_MODIFY() - modify a bitfield element
+ * @_mask: shifted mask defining the field's length and position
+ * @_reg_p: pointer to the memory that should be updated
+ * @_val: value to store in the bitfield
+ *
+ * FIELD_MODIFY() modifies the set of bits in @_reg_p specified by @_mask,
+ * by replacing them with the bitfield value passed in as @_val.
+ */
+#define FIELD_MODIFY(_mask, _reg_p, _val)						\
+	({										\
+		typecheck_pointer(_reg_p);						\
+		__BF_FIELD_CHECK(_mask, *(_reg_p), _val, "FIELD_MODIFY: ");		\
+		*(_reg_p) &= ~(_mask);							\
+		*(_reg_p) |= (((typeof(_mask))(_val) << __bf_shf(_mask)) & (_mask));	\
 	})
 
 extern void __compiletime_error("value doesn't fit into mask")
@@ -171,14 +210,14 @@ static __always_inline u64 field_mask(u64 field)
 }
 #define field_max(field)	((typeof(field))field_mask(field))
 #define ____MAKE_OP(type,base,to,from)					\
-static __always_inline __##type type##_encode_bits(base v, base field)	\
+static __always_inline __##type __must_check type##_encode_bits(base v, base field)	\
 {									\
 	if (__builtin_constant_p(v) && (v & ~field_mask(field)))	\
 		__field_overflow();					\
 	return to((v & field_mask(field)) * field_multiplier(field));	\
 }									\
-static __always_inline __##type type##_replace_bits(__##type old,	\
-					base val, base field)		\
+static __always_inline __##type __must_check type##_replace_bits(__##type old,	\
+							base val, base field)	\
 {									\
 	return (old & ~to(field)) | type##_encode_bits(val, field);	\
 }									\
@@ -187,7 +226,7 @@ static __always_inline void type##p_replace_bits(__##type *p,		\
 {									\
 	*p = (*p & ~to(field)) | type##_encode_bits(val, field);	\
 }									\
-static __always_inline base type##_get_bits(__##type v, base field)	\
+static __always_inline base __must_check type##_get_bits(__##type v, base field)	\
 {									\
 	return (from(v) & field)/field_multiplier(field);		\
 }
@@ -202,4 +241,62 @@ __MAKE_OP(64)
 #undef __MAKE_OP
 #undef ____MAKE_OP
 
+#define __field_prep(mask, val)						\
+	({								\
+		__auto_type __mask = (mask);				\
+		typeof(__mask) __val = (val);				\
+		unsigned int __shift = BITS_PER_TYPE(__mask) <= 32 ?	\
+				       __ffs(__mask) : __ffs64(__mask);	\
+		(__val << __shift) & __mask;				\
+	})
+
+#define __field_get(mask, reg)						\
+	({								\
+		__auto_type __mask = (mask);				\
+		typeof(__mask) __reg =  (reg);				\
+		unsigned int __shift = BITS_PER_TYPE(__mask) <= 32 ?	\
+				       __ffs(__mask) : __ffs64(__mask);	\
+		(__reg & __mask) >> __shift;				\
+	})
+
+/**
+ * field_prep() - prepare a bitfield element
+ * @mask: shifted mask defining the field's length and position, must be
+ *        non-zero
+ * @val:  value to put in the field
+ *
+ * Return: field value masked and shifted to its final destination
+ *
+ * field_prep() masks and shifts up the value.  The result should be
+ * combined with other fields of the bitfield using logical OR.
+ * Unlike FIELD_PREP(), @mask is not limited to a compile-time constant.
+ * Typical usage patterns are a value stored in a table, or calculated by
+ * shifting a constant by a variable number of bits.
+ * If you want to ensure that @mask is a compile-time constant, please use
+ * FIELD_PREP() directly instead.
+ */
+#define field_prep(mask, val)						\
+	(__builtin_constant_p(mask) ? __FIELD_PREP(mask, val, "field_prep: ") \
+				    : __field_prep(mask, val))
+
+/**
+ * field_get() - extract a bitfield element
+ * @mask: shifted mask defining the field's length and position, must be
+ *        non-zero
+ * @reg:  value of entire bitfield
+ *
+ * Return: extracted field value
+ *
+ * field_get() extracts the field specified by @mask from the
+ * bitfield passed in as @reg by masking and shifting it down.
+ * Unlike FIELD_GET(), @mask is not limited to a compile-time constant.
+ * Typical usage patterns are a value stored in a table, or calculated by
+ * shifting a constant by a variable number of bits.
+ * If you want to ensure that @mask is a compile-time constant, please use
+ * FIELD_GET() directly instead.
+ */
+#define field_get(mask, reg)						\
+	(__builtin_constant_p(mask) ? __FIELD_GET(mask, reg, "field_get: ") \
+				    : __field_get(mask, reg))
+
 #endif
diff --git a/include/linux/bitmap-str.h b/include/linux/bitmap-str.h
new file mode 100644
index 000000000000..53d3e1b32d3d
--- /dev/null
+++ b/include/linux/bitmap-str.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BITMAP_STR_H
+#define __LINUX_BITMAP_STR_H
+
+#include <linux/types.h>
+
+int bitmap_parse_user(const char __user *ubuf, unsigned int ulen, unsigned long *dst, int nbits);
+int bitmap_print_to_pagebuf(bool list, char *buf, const unsigned long *maskp, int nmaskbits);
+int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp, int nmaskbits,
+				loff_t off, size_t count);
+int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, int nmaskbits,
+			     loff_t off, size_t count);
+int bitmap_parse(const char *buf, unsigned int buflen, unsigned long *dst, int nbits);
+int bitmap_parselist(const char *buf, unsigned long *maskp, int nmaskbits);
+int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
+					unsigned long *dst, int nbits);
+
+#endif /* __LINUX_BITMAP_STR_H */
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 7d6d73b78147..b0395e4ccf90 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -6,10 +6,13 @@
 
 #include <linux/align.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
+#include <linux/errno.h>
 #include <linux/find.h>
 #include <linux/limits.h>
 #include <linux/string.h>
 #include <linux/types.h>
+#include <linux/bitmap-str.h>
 
 struct device;
 
@@ -20,7 +23,7 @@ struct device;
  *
  * Function implementations generic to all architectures are in
  * lib/bitmap.c.  Functions implementations that are architecture
- * specific are in various include/asm-<arch>/bitops.h headers
+ * specific are in various arch/<arch>/include/asm/bitops.h headers
  * and other arch/<arch> specific files.
  *
  * See lib/bitmap.c for more details.
@@ -42,6 +45,7 @@ struct device;
  *  bitmap_copy(dst, src, nbits)                *dst = *src
  *  bitmap_and(dst, src1, src2, nbits)          *dst = *src1 & *src2
  *  bitmap_or(dst, src1, src2, nbits)           *dst = *src1 | *src2
+ *  bitmap_weighted_or(dst, src1, src2, nbits)	*dst = *src1 | *src2. Returns Hamming Weight of dst
  *  bitmap_xor(dst, src1, src2, nbits)          *dst = *src1 ^ *src2
  *  bitmap_andnot(dst, src1, src2, nbits)       *dst = *src1 & ~(*src2)
  *  bitmap_complement(dst, src, nbits)          *dst = ~(*src)
@@ -52,6 +56,7 @@ struct device;
  *  bitmap_full(src, nbits)                     Are all bits set in *src?
  *  bitmap_weight(src, nbits)                   Hamming Weight: number set bits
  *  bitmap_weight_and(src1, src2, nbits)        Hamming Weight of and'ed bitmap
+ *  bitmap_weight_andnot(src1, src2, nbits)     Hamming Weight of andnot'ed bitmap
  *  bitmap_set(dst, pos, nbits)                 Set specified bit area
  *  bitmap_clear(dst, pos, nbits)               Clear specified bit area
  *  bitmap_find_next_zero_area(buf, len, pos, n, mask)  Find bit free area
@@ -60,6 +65,8 @@ struct device;
  *  bitmap_shift_left(dst, src, n, nbits)       *dst = *src << n
  *  bitmap_cut(dst, src, first, n, nbits)       Cut n bits from first, copy rest
  *  bitmap_replace(dst, old, new, mask, nbits)  *dst = (*old & ~(*mask)) | (*new & *mask)
+ *  bitmap_scatter(dst, src, mask, nbits)	*dst = map(dense, sparse)(src)
+ *  bitmap_gather(dst, src, mask, nbits)	*dst = map(sparse, dense)(src)
  *  bitmap_remap(dst, src, old, new, nbits)     *dst = map(old, new)(src)
  *  bitmap_bitremap(oldbit, old, new, nbits)    newbit = map(old, new)(oldbit)
  *  bitmap_onto(dst, orig, relmap, nbits)       *dst = orig relative to relmap
@@ -77,6 +84,10 @@ struct device;
  *  bitmap_to_arr64(buf, src, nbits)            Copy nbits from buf to u64[] dst
  *  bitmap_get_value8(map, start)               Get 8bit value from map at start
  *  bitmap_set_value8(map, value, start)        Set 8bit value to map at start
+ *  bitmap_read(map, start, nbits)              Read an nbits-sized value from
+ *                                              map at start
+ *  bitmap_write(map, value, start, nbits)      Write an nbits-sized value to
+ *                                              map at start
  *
  * Note, bitmap_zero() and bitmap_fill() operate over the region of
  * unsigned longs, that is, bits behind bitmap till the unsigned long
@@ -125,6 +136,8 @@ unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node);
 unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node);
 void bitmap_free(const unsigned long *bitmap);
 
+DEFINE_FREE(bitmap, unsigned long *, if (_T) bitmap_free(_T))
+
 /* Managed variants of the above. */
 unsigned long *devm_bitmap_alloc(struct device *dev,
 				 unsigned int nbits, gfp_t flags);
@@ -153,6 +166,8 @@ bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
 		 const unsigned long *bitmap2, unsigned int nbits);
+unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitmap1,
+				  const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
 		  const unsigned long *bitmap2, unsigned int nbits);
 bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
@@ -167,6 +182,8 @@ bool __bitmap_subset(const unsigned long *bitmap1,
 unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits);
 unsigned int __bitmap_weight_and(const unsigned long *bitmap1,
 				 const unsigned long *bitmap2, unsigned int nbits);
+unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1,
+				    const unsigned long *bitmap2, unsigned int nbits);
 void __bitmap_set(unsigned long *map, unsigned int start, int len);
 void __bitmap_clear(unsigned long *map, unsigned int start, int len);
 
@@ -189,25 +206,17 @@ unsigned long bitmap_find_next_zero_area_off(unsigned long *map,
  * the bit offset of all zero areas this function finds is multiples of that
  * power of 2. A @align_mask of 0 means no alignment is required.
  */
-static inline unsigned long
-bitmap_find_next_zero_area(unsigned long *map,
-			   unsigned long size,
-			   unsigned long start,
-			   unsigned int nr,
-			   unsigned long align_mask)
+static __always_inline
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask)
 {
 	return bitmap_find_next_zero_area_off(map, size, start, nr,
 					      align_mask, 0);
 }
 
-int bitmap_parse(const char *buf, unsigned int buflen,
-			unsigned long *dst, int nbits);
-int bitmap_parse_user(const char __user *ubuf, unsigned int ulen,
-			unsigned long *dst, int nbits);
-int bitmap_parselist(const char *buf, unsigned long *maskp,
-			int nmaskbits);
-int bitmap_parselist_user(const char __user *ubuf, unsigned int ulen,
-			unsigned long *dst, int nbits);
 void bitmap_remap(unsigned long *dst, const unsigned long *src,
 		const unsigned long *old, const unsigned long *new, unsigned int nbits);
 int bitmap_bitremap(int oldbit,
@@ -216,30 +225,15 @@ void bitmap_onto(unsigned long *dst, const unsigned long *orig,
 		const unsigned long *relmap, unsigned int bits);
 void bitmap_fold(unsigned long *dst, const unsigned long *orig,
 		unsigned int sz, unsigned int nbits);
-int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order);
-void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order);
-int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order);
-
-#ifdef __BIG_ENDIAN
-void bitmap_copy_le(unsigned long *dst, const unsigned long *src, unsigned int nbits);
-#else
-#define bitmap_copy_le bitmap_copy
-#endif
-int bitmap_print_to_pagebuf(bool list, char *buf,
-				   const unsigned long *maskp, int nmaskbits);
-
-extern int bitmap_print_bitmask_to_buf(char *buf, const unsigned long *maskp,
-				      int nmaskbits, loff_t off, size_t count);
-
-extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp,
-				      int nmaskbits, loff_t off, size_t count);
 
 #define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) & (BITS_PER_LONG - 1)))
 #define BITMAP_LAST_WORD_MASK(nbits) (~0UL >> (-(nbits) & (BITS_PER_LONG - 1)))
 
-static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
+#define bitmap_size(nbits)	(ALIGN(nbits, BITS_PER_LONG) / BITS_PER_BYTE)
+
+static __always_inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = 0;
@@ -247,9 +241,9 @@ static inline void bitmap_zero(unsigned long *dst, unsigned int nbits)
 		memset(dst, 0, len);
 }
 
-static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
+static __always_inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = ~0UL;
@@ -257,10 +251,10 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits)
 		memset(dst, 0xff, len);
 }
 
-static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
-			unsigned int nbits)
+static __always_inline
+void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
-	unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+	unsigned int len = bitmap_size(nbits);
 
 	if (small_const_nbits(nbits))
 		*dst = *src;
@@ -271,14 +265,26 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
 /*
  * Copy bitmap and clear tail bits in last word.
  */
-static inline void bitmap_copy_clear_tail(unsigned long *dst,
-		const unsigned long *src, unsigned int nbits)
+static __always_inline
+void bitmap_copy_clear_tail(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	bitmap_copy(dst, src, nbits);
 	if (nbits % BITS_PER_LONG)
 		dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
 }
 
+static inline void bitmap_copy_and_extend(unsigned long *to,
+					  const unsigned long *from,
+					  unsigned int count, unsigned int size)
+{
+	unsigned int copy = BITS_TO_LONGS(count);
+
+	memcpy(to, from, copy * sizeof(long));
+	if (count % BITS_PER_LONG)
+		to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
+	memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
+}
+
 /*
  * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
  * machines the order of hi and lo parts of numbers match the bitmap structure.
@@ -302,12 +308,10 @@ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap,
 #endif
 
 /*
- * On 64-bit systems bitmaps are represented as u64 arrays internally. On LE32
- * machines the order of hi and lo parts of numbers match the bitmap structure.
- * In both cases conversion is not needed when copying data from/to arrays of
- * u64.
+ * On 64-bit systems bitmaps are represented as u64 arrays internally. So,
+ * the conversion is not needed when copying data from/to arrays of u64.
  */
-#if (BITS_PER_LONG == 32) && defined(__BIG_ENDIAN)
+#if BITS_PER_LONG == 32
 void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits);
 void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
 #else
@@ -317,16 +321,18 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits);
 	bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits))
 #endif
 
-static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_and(unsigned long *dst, const unsigned long *src1,
+		const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return (*dst = *src1 & *src2 & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_and(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+void bitmap_or(unsigned long *dst, const unsigned long *src1,
+	       const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 | *src2;
@@ -334,8 +340,21 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+unsigned int bitmap_weighted_or(unsigned long *dst, const unsigned long *src1,
+				const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits)) {
+		*dst = *src1 | *src2;
+		return hweight_long(*dst & BITMAP_LAST_WORD_MASK(nbits));
+	} else {
+		return __bitmap_weighted_or(dst, src1, src2, nbits);
+	}
+}
+
+static __always_inline
+void bitmap_xor(unsigned long *dst, const unsigned long *src1,
+		const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = *src1 ^ *src2;
@@ -343,16 +362,17 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
 		__bitmap_xor(dst, src1, src2, nbits);
 }
 
-static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
-			const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+		   const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return (*dst = *src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
 	return __bitmap_andnot(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
-			unsigned int nbits)
+static __always_inline
+void bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = ~(*src);
@@ -367,8 +387,8 @@ static inline void bitmap_complement(unsigned long *dst, const unsigned long *sr
 #endif
 #define BITMAP_MEM_MASK (BITMAP_MEM_ALIGNMENT - 1)
 
-static inline bool bitmap_equal(const unsigned long *src1,
-				const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_equal(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return !((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
@@ -387,10 +407,9 @@ static inline bool bitmap_equal(const unsigned long *src1,
  *
  * Returns: True if (*@src1 | *@src2) == *@src3, false otherwise
  */
-static inline bool bitmap_or_equal(const unsigned long *src1,
-				   const unsigned long *src2,
-				   const unsigned long *src3,
-				   unsigned int nbits)
+static __always_inline
+bool bitmap_or_equal(const unsigned long *src1, const unsigned long *src2,
+		     const unsigned long *src3, unsigned int nbits)
 {
 	if (!small_const_nbits(nbits))
 		return __bitmap_or_equal(src1, src2, src3, nbits);
@@ -398,9 +417,8 @@ static inline bool bitmap_or_equal(const unsigned long *src1,
 	return !(((*src1 | *src2) ^ *src3) & BITMAP_LAST_WORD_MASK(nbits));
 }
 
-static inline bool bitmap_intersects(const unsigned long *src1,
-				     const unsigned long *src2,
-				     unsigned int nbits)
+static __always_inline
+bool bitmap_intersects(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
@@ -408,8 +426,8 @@ static inline bool bitmap_intersects(const unsigned long *src1,
 		return __bitmap_intersects(src1, src2, nbits);
 }
 
-static inline bool bitmap_subset(const unsigned long *src1,
-				 const unsigned long *src2, unsigned int nbits)
+static __always_inline
+bool bitmap_subset(const unsigned long *src1, const unsigned long *src2, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
@@ -417,7 +435,8 @@ static inline bool bitmap_subset(const unsigned long *src1,
 		return __bitmap_subset(src1, src2, nbits);
 }
 
-static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
+static __always_inline
+bool bitmap_empty(const unsigned long *src, unsigned nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
@@ -425,7 +444,8 @@ static inline bool bitmap_empty(const unsigned long *src, unsigned nbits)
 	return find_first_bit(src, nbits) == nbits;
 }
 
-static inline bool bitmap_full(const unsigned long *src, unsigned int nbits)
+static __always_inline
+bool bitmap_full(const unsigned long *src, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
@@ -450,8 +470,17 @@ unsigned long bitmap_weight_and(const unsigned long *src1,
 	return __bitmap_weight_and(src1, src2, nbits);
 }
 
-static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
-		unsigned int nbits)
+static __always_inline
+unsigned long bitmap_weight_andnot(const unsigned long *src1,
+				   const unsigned long *src2, unsigned int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src1 & ~(*src2) & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight_andnot(src1, src2, nbits);
+}
+
+static __always_inline
+void bitmap_set(unsigned long *map, unsigned int start, unsigned int nbits)
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__set_bit(start, map);
@@ -466,8 +495,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start,
 		__bitmap_set(map, start, nbits);
 }
 
-static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
-		unsigned int nbits)
+static __always_inline
+void bitmap_clear(unsigned long *map, unsigned int start, unsigned int nbits)
 {
 	if (__builtin_constant_p(nbits) && nbits == 1)
 		__clear_bit(start, map);
@@ -482,8 +511,9 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start,
 		__bitmap_clear(map, start, nbits);
 }
 
-static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
-				unsigned int shift, unsigned int nbits)
+static __always_inline
+void bitmap_shift_right(unsigned long *dst, const unsigned long *src,
+			unsigned int shift, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*src & BITMAP_LAST_WORD_MASK(nbits)) >> shift;
@@ -491,8 +521,9 @@ static inline void bitmap_shift_right(unsigned long *dst, const unsigned long *s
 		__bitmap_shift_right(dst, src, shift, nbits);
 }
 
-static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
-				unsigned int shift, unsigned int nbits)
+static __always_inline
+void bitmap_shift_left(unsigned long *dst, const unsigned long *src,
+		       unsigned int shift, unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*src << shift) & BITMAP_LAST_WORD_MASK(nbits);
@@ -500,11 +531,12 @@ static inline void bitmap_shift_left(unsigned long *dst, const unsigned long *sr
 		__bitmap_shift_left(dst, src, shift, nbits);
 }
 
-static inline void bitmap_replace(unsigned long *dst,
-				  const unsigned long *old,
-				  const unsigned long *new,
-				  const unsigned long *mask,
-				  unsigned int nbits)
+static __always_inline
+void bitmap_replace(unsigned long *dst,
+		    const unsigned long *old,
+		    const unsigned long *new,
+		    const unsigned long *mask,
+		    unsigned int nbits)
 {
 	if (small_const_nbits(nbits))
 		*dst = (*old & ~(*mask)) | (*new & *mask);
@@ -512,15 +544,183 @@ static inline void bitmap_replace(unsigned long *dst,
 		__bitmap_replace(dst, old, new, mask, nbits);
 }
 
-static inline void bitmap_next_set_region(unsigned long *bitmap,
-					  unsigned int *rs, unsigned int *re,
-					  unsigned int end)
+/**
+ * bitmap_scatter - Scatter a bitmap according to the given mask
+ * @dst: scattered bitmap
+ * @src: gathered bitmap
+ * @mask: mask representing bits to assign to in the scattered bitmap
+ * @nbits: number of bits in each of these bitmaps
+ *
+ * Scatters bitmap with sequential bits according to the given @mask.
+ *
+ * Example:
+ * If @src bitmap = 0x005a, with @mask = 0x1313, @dst will be 0x0302.
+ *
+ * Or in binary form
+ * @src			@mask			@dst
+ * 0000000001011010	0001001100010011	0000001100000010
+ *
+ * (Bits 0, 1, 2, 3, 4, 5 are copied to the bits 0, 1, 4, 8, 9, 12)
+ *
+ * A more 'visual' description of the operation::
+ *
+ *	src:  0000000001011010
+ *	                ||||||
+ *	         +------+|||||
+ *	         |  +----+||||
+ *	         |  |+----+|||
+ *	         |  ||   +-+||
+ *	         |  ||   |  ||
+ *	mask: ...v..vv...v..vv
+ *	      ...0..11...0..10
+ *	dst:  0000001100000010
+ *
+ * A relationship exists between bitmap_scatter() and bitmap_gather(). See
+ * bitmap_gather() for the bitmap gather detailed operations. TL;DR:
+ * bitmap_gather() can be seen as the 'reverse' bitmap_scatter() operation.
+ */
+static __always_inline
+void bitmap_scatter(unsigned long *dst, const unsigned long *src,
+		    const unsigned long *mask, unsigned int nbits)
+{
+	unsigned int n = 0;
+	unsigned int bit;
+
+	bitmap_zero(dst, nbits);
+
+	for_each_set_bit(bit, mask, nbits)
+		__assign_bit(bit, dst, test_bit(n++, src));
+}
+
+/**
+ * bitmap_gather - Gather a bitmap according to given mask
+ * @dst: gathered bitmap
+ * @src: scattered bitmap
+ * @mask: mask representing bits to extract from in the scattered bitmap
+ * @nbits: number of bits in each of these bitmaps
+ *
+ * Gathers bitmap with sparse bits according to the given @mask.
+ *
+ * Example:
+ * If @src bitmap = 0x0302, with @mask = 0x1313, @dst will be 0x001a.
+ *
+ * Or in binary form
+ * @src			@mask			@dst
+ * 0000001100000010	0001001100010011	0000000000011010
+ *
+ * (Bits 0, 1, 4, 8, 9, 12 are copied to the bits 0, 1, 2, 3, 4, 5)
+ *
+ * A more 'visual' description of the operation::
+ *
+ *	mask: ...v..vv...v..vv
+ *	src:  0000001100000010
+ *	         ^  ^^   ^   0
+ *	         |  ||   |  10
+ *	         |  ||   > 010
+ *	         |  |+--> 1010
+ *	         |  +--> 11010
+ *	         +----> 011010
+ *	dst:  0000000000011010
+ *
+ * A relationship exists between bitmap_gather() and bitmap_scatter(). See
+ * bitmap_scatter() for the bitmap scatter detailed operations. TL;DR:
+ * bitmap_scatter() can be seen as the 'reverse' bitmap_gather() operation.
+ *
+ * Suppose scattered computed using bitmap_scatter(scattered, src, mask, n).
+ * The operation bitmap_gather(result, scattered, mask, n) leads to a result
+ * equal or equivalent to src.
+ *
+ * The result can be 'equivalent' because bitmap_scatter() and bitmap_gather()
+ * are not bijective.
+ * The result and src values are equivalent in that sense that a call to
+ * bitmap_scatter(res, src, mask, n) and a call to
+ * bitmap_scatter(res, result, mask, n) will lead to the same res value.
+ */
+static __always_inline
+void bitmap_gather(unsigned long *dst, const unsigned long *src,
+		   const unsigned long *mask, unsigned int nbits)
+{
+	unsigned int n = 0;
+	unsigned int bit;
+
+	bitmap_zero(dst, nbits);
+
+	for_each_set_bit(bit, mask, nbits)
+		__assign_bit(n++, dst, test_bit(bit, src));
+}
+
+static __always_inline
+void bitmap_next_set_region(unsigned long *bitmap, unsigned int *rs,
+			    unsigned int *re, unsigned int end)
 {
 	*rs = find_next_bit(bitmap, end, *rs);
 	*re = find_next_zero_bit(bitmap, end, *rs + 1);
 }
 
 /**
+ * bitmap_release_region - release allocated bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to release
+ *	@order: region size (log base 2 of number of bits) to release
+ *
+ * This is the complement to __bitmap_find_free_region() and releases
+ * the found region (by clearing it in the bitmap).
+ */
+static __always_inline
+void bitmap_release_region(unsigned long *bitmap, unsigned int pos, int order)
+{
+	bitmap_clear(bitmap, pos, BIT(order));
+}
+
+/**
+ * bitmap_allocate_region - allocate bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to allocate
+ *	@order: region size (log base 2 of number of bits) to allocate
+ *
+ * Allocate (set bits in) a specified region of a bitmap.
+ *
+ * Returns: 0 on success, or %-EBUSY if specified region wasn't
+ * free (not all bits were zero).
+ */
+static __always_inline
+int bitmap_allocate_region(unsigned long *bitmap, unsigned int pos, int order)
+{
+	unsigned int len = BIT(order);
+
+	if (find_next_bit(bitmap, pos + len, pos) < pos + len)
+		return -EBUSY;
+	bitmap_set(bitmap, pos, len);
+	return 0;
+}
+
+/**
+ * bitmap_find_free_region - find a contiguous aligned mem region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@bits: number of bits in the bitmap
+ *	@order: region size (log base 2 of number of bits) to find
+ *
+ * Find a region of free (zero) bits in a @bitmap of @bits bits and
+ * allocate them (set them to one).  Only consider regions of length
+ * a power (@order) of two, aligned to that power of two, which
+ * makes the search algorithm much faster.
+ *
+ * Returns: the bit offset in bitmap of the allocated region,
+ * or -errno on failure.
+ */
+static __always_inline
+int bitmap_find_free_region(unsigned long *bitmap, unsigned int bits, int order)
+{
+	unsigned int pos, end;		/* scans bitmap by regions of size order */
+
+	for (pos = 0; (end = pos + BIT(order)) <= bits; pos = end) {
+		if (!bitmap_allocate_region(bitmap, pos, order))
+			return pos;
+	}
+	return -ENOMEM;
+}
+
+/**
  * BITMAP_FROM_U64() - Represent u64 value in the format suitable for bitmap.
  * @n: u64 value
  *
@@ -563,44 +763,89 @@ static inline void bitmap_next_set_region(unsigned long *bitmap,
  * That is ``(u32 *)(&val)[0]`` gets the upper 32 bits,
  * but we expect the lower 32-bits of u64.
  */
-static inline void bitmap_from_u64(unsigned long *dst, u64 mask)
+static __always_inline void bitmap_from_u64(unsigned long *dst, u64 mask)
 {
 	bitmap_from_arr64(dst, &mask, 64);
 }
 
 /**
- * bitmap_get_value8 - get an 8-bit value within a memory region
+ * bitmap_read - read a value of n-bits from the memory region
  * @map: address to the bitmap memory region
- * @start: bit offset of the 8-bit value; must be a multiple of 8
+ * @start: bit offset of the n-bit value
+ * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG
  *
- * Returns the 8-bit value located at the @start bit offset within the @src
- * memory region.
+ * Returns: value of @nbits bits located at the @start bit offset within the
+ * @map memory region. For @nbits = 0 and @nbits > BITS_PER_LONG the return
+ * value is undefined.
  */
-static inline unsigned long bitmap_get_value8(const unsigned long *map,
-					      unsigned long start)
+static __always_inline
+unsigned long bitmap_read(const unsigned long *map, unsigned long start, unsigned long nbits)
 {
-	const size_t index = BIT_WORD(start);
-	const unsigned long offset = start % BITS_PER_LONG;
+	size_t index = BIT_WORD(start);
+	unsigned long offset = start % BITS_PER_LONG;
+	unsigned long space = BITS_PER_LONG - offset;
+	unsigned long value_low, value_high;
+
+	if (unlikely(!nbits || nbits > BITS_PER_LONG))
+		return 0;
+
+	if (space >= nbits)
+		return (map[index] >> offset) & BITMAP_LAST_WORD_MASK(nbits);
 
-	return (map[index] >> offset) & 0xFF;
+	value_low = map[index] & BITMAP_FIRST_WORD_MASK(start);
+	value_high = map[index + 1] & BITMAP_LAST_WORD_MASK(start + nbits);
+	return (value_low >> offset) | (value_high << space);
 }
 
 /**
- * bitmap_set_value8 - set an 8-bit value within a memory region
+ * bitmap_write - write n-bit value within a memory region
  * @map: address to the bitmap memory region
- * @value: the 8-bit value; values wider than 8 bits may clobber bitmap
- * @start: bit offset of the 8-bit value; must be a multiple of 8
+ * @value: value to write, clamped to nbits
+ * @start: bit offset of the n-bit value
+ * @nbits: size of value in bits, nonzero, up to BITS_PER_LONG.
+ *
+ * bitmap_write() behaves as-if implemented as @nbits calls of __assign_bit(),
+ * i.e. bits beyond @nbits are ignored:
+ *
+ *   for (bit = 0; bit < nbits; bit++)
+ *           __assign_bit(start + bit, bitmap, val & BIT(bit));
+ *
+ * For @nbits == 0 and @nbits > BITS_PER_LONG no writes are performed.
  */
-static inline void bitmap_set_value8(unsigned long *map, unsigned long value,
-				     unsigned long start)
+static __always_inline
+void bitmap_write(unsigned long *map, unsigned long value,
+		  unsigned long start, unsigned long nbits)
 {
-	const size_t index = BIT_WORD(start);
-	const unsigned long offset = start % BITS_PER_LONG;
-
-	map[index] &= ~(0xFFUL << offset);
+	size_t index;
+	unsigned long offset;
+	unsigned long space;
+	unsigned long mask;
+	bool fit;
+
+	if (unlikely(!nbits || nbits > BITS_PER_LONG))
+		return;
+
+	mask = BITMAP_LAST_WORD_MASK(nbits);
+	value &= mask;
+	offset = start % BITS_PER_LONG;
+	space = BITS_PER_LONG - offset;
+	fit = space >= nbits;
+	index = BIT_WORD(start);
+
+	map[index] &= (fit ? (~(mask << offset)) : ~BITMAP_FIRST_WORD_MASK(start));
 	map[index] |= value << offset;
+	if (fit)
+		return;
+
+	map[index + 1] &= BITMAP_FIRST_WORD_MASK(start + nbits);
+	map[index + 1] |= (value >> space);
 }
 
+#define bitmap_get_value8(map, start)			\
+	bitmap_read(map, start, BITS_PER_BYTE)
+#define bitmap_set_value8(map, value, start)		\
+	bitmap_write(map, value, start, BITS_PER_BYTE)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __LINUX_BITMAP_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 2ba557e067fe..ea7898cc5903 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -8,19 +8,13 @@
 
 #include <uapi/linux/kernel.h>
 
-/* Set bits in the first 'n' bytes when loaded from memory */
-#ifdef __LITTLE_ENDIAN
-#  define aligned_byte_mask(n) ((1UL << 8*(n))-1)
-#else
-#  define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
-#endif
-
-#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 #define BITS_TO_LONGS(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
 #define BITS_TO_U64(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u64))
 #define BITS_TO_U32(nr)		__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(u32))
 #define BITS_TO_BYTES(nr)	__KERNEL_DIV_ROUND_UP(nr, BITS_PER_TYPE(char))
 
+#define BYTES_TO_BITS(nb)	((nb) * BITS_PER_BYTE)
+
 extern unsigned int __sw_hweight8(unsigned int w);
 extern unsigned int __sw_hweight16(unsigned int w);
 extern unsigned int __sw_hweight32(unsigned int w);
@@ -52,12 +46,17 @@ extern unsigned long __sw_hweight64(__u64 w);
 	  __builtin_constant_p(*(const unsigned long *)(addr))) ?	\
 	 const##op(nr, addr) : op(nr, addr))
 
+/*
+ * The following macros are non-atomic versions of their non-underscored
+ * counterparts.
+ */
 #define __set_bit(nr, addr)		bitop(___set_bit, nr, addr)
 #define __clear_bit(nr, addr)		bitop(___clear_bit, nr, addr)
 #define __change_bit(nr, addr)		bitop(___change_bit, nr, addr)
 #define __test_and_set_bit(nr, addr)	bitop(___test_and_set_bit, nr, addr)
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
+
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
 #define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
@@ -80,6 +79,7 @@ __check_bitop_pr(__test_and_set_bit);
 __check_bitop_pr(__test_and_clear_bit);
 __check_bitop_pr(__test_and_change_bit);
 __check_bitop_pr(test_bit);
+__check_bitop_pr(test_bit_acquire);
 
 #undef __check_bitop_pr
 
@@ -200,7 +200,7 @@ static __always_inline __s64 sign_extend64(__u64 value, int index)
 	return (__s64)(value << shift) >> shift;
 }
 
-static inline unsigned fls_long(unsigned long l)
+static inline unsigned int fls_long(unsigned long l)
 {
 	if (sizeof(l) == 4)
 		return fls(l);
@@ -229,6 +229,37 @@ static inline int get_count_order_long(unsigned long l)
 }
 
 /**
+ * parity8 - get the parity of an u8 value
+ * @value: the value to be examined
+ *
+ * Determine the parity of the u8 argument.
+ *
+ * Returns:
+ * 0 for even parity, 1 for odd parity
+ *
+ * Note: This function informs you about the current parity. Example to bail
+ * out when parity is odd:
+ *
+ *	if (parity8(val) == 1)
+ *		return -EBADMSG;
+ *
+ * If you need to calculate a parity bit, you need to draw the conclusion from
+ * this result yourself. Example to enforce odd parity, parity bit is bit 7:
+ *
+ *	if (parity8(val) == 0)
+ *		val ^= BIT(7);
+ */
+static inline int parity8(u8 val)
+{
+	/*
+	 * One explanation of this algorithm:
+	 * https://funloop.org/codex/problem/parity/README.html
+	 */
+	val ^= val >> 4;
+	return (0x6996 >> (val & 0xf)) & 1;
+}
+
+/**
  * __ffs64 - find first set bit in a 64 bit word
  * @word: The 64 bit word
  *
@@ -236,7 +267,7 @@ static inline int get_count_order_long(unsigned long l)
  * The result is not defined if no bits are set, so check that @word
  * is non-zero before calling this.
  */
-static inline unsigned long __ffs64(u64 word)
+static inline __attribute_const__ unsigned int __ffs64(u64 word)
 {
 #if BITS_PER_LONG == 32
 	if (((u32)word) == 0UL)
@@ -252,18 +283,12 @@ static inline unsigned long __ffs64(u64 word)
  * @word: The word to search
  * @n: Bit to find
  */
-static inline unsigned long fns(unsigned long word, unsigned int n)
+static inline unsigned int fns(unsigned long word, unsigned int n)
 {
-	unsigned int bit;
+	while (word && n--)
+		word &= word - 1;
 
-	while (word) {
-		bit = __ffs(word);
-		if (n-- == 0)
-			return bit;
-		__clear_bit(bit, &word);
-	}
-
-	return BITS_PER_LONG;
+	return word ? __ffs(word) : BITS_PER_LONG;
 }
 
 /**
@@ -272,23 +297,11 @@ static inline unsigned long fns(unsigned long word, unsigned int n)
  * @addr: the address to start counting from
  * @value: the value to assign
  */
-static __always_inline void assign_bit(long nr, volatile unsigned long *addr,
-				       bool value)
-{
-	if (value)
-		set_bit(nr, addr);
-	else
-		clear_bit(nr, addr);
-}
+#define assign_bit(nr, addr, value)					\
+	((value) ? set_bit((nr), (addr)) : clear_bit((nr), (addr)))
 
-static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
-					 bool value)
-{
-	if (value)
-		__set_bit(nr, addr);
-	else
-		__clear_bit(nr, addr);
-}
+#define __assign_bit(nr, addr, value)					\
+	((value) ? __set_bit((nr), (addr)) : __clear_bit((nr), (addr)))
 
 /**
  * __ptr_set_bit - Set bit in a pointer's value
diff --git a/include/linux/bits.h b/include/linux/bits.h
index 7c0cf5031abe..a40cc861b3a7 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -2,15 +2,15 @@
 #ifndef __LINUX_BITS_H
 #define __LINUX_BITS_H
 
-#include <linux/const.h>
 #include <vdso/bits.h>
-#include <asm/bitsperlong.h>
+#include <uapi/linux/bits.h>
 
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
 #define BIT_ULL_MASK(nr)	(ULL(1) << ((nr) % BITS_PER_LONG_LONG))
 #define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
+#define BITS_PER_TYPE(type)	(sizeof(type) * BITS_PER_BYTE)
 
 /*
  * Create a contiguous bitmask starting at bit position @l and ending at
@@ -18,28 +18,72 @@
  * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
  */
 #if !defined(__ASSEMBLY__)
+
+/*
+ * Missing asm support
+ *
+ * GENMASK_U*() and BIT_U*() depend on BITS_PER_TYPE() which relies on sizeof(),
+ * something not available in asm. Nevertheless, fixed width integers is a C
+ * concept. Assembly code can rely on the long and long long versions instead.
+ */
+
 #include <linux/build_bug.h>
-#define GENMASK_INPUT_CHECK(h, l) \
-	(BUILD_BUG_ON_ZERO(__builtin_choose_expr( \
-		__is_constexpr((l) > (h)), (l) > (h), 0)))
-#else
+#include <linux/compiler.h>
+#include <linux/overflow.h>
+
+#define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
+
+/*
+ * Generate a mask for the specified type @t. Additional checks are made to
+ * guarantee the value returned fits in that type, relying on
+ * -Wshift-count-overflow compiler check to detect incompatible arguments.
+ * For example, all these create build errors or warnings:
+ *
+ * - GENMASK(15, 20): wrong argument order
+ * - GENMASK(72, 15): doesn't fit unsigned long
+ * - GENMASK_U32(33, 15): doesn't fit in a u32
+ */
+#define GENMASK_TYPE(t, h, l)					\
+	((t)(GENMASK_INPUT_CHECK(h, l) +			\
+	     (type_max(t) << (l) &				\
+	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
+
+#define GENMASK(h, l)		GENMASK_TYPE(unsigned long, h, l)
+#define GENMASK_ULL(h, l)	GENMASK_TYPE(unsigned long long, h, l)
+
+#define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
+#define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
+#define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
+#define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+#define GENMASK_U128(h, l)	GENMASK_TYPE(u128, h, l)
+
+/*
+ * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
+ * following examples generate compiler warnings due to -Wshift-count-overflow:
+ *
+ * - BIT_U8(8)
+ * - BIT_U32(-1)
+ * - BIT_U32(40)
+ */
+#define BIT_INPUT_CHECK(type, nr) \
+	BUILD_BUG_ON_ZERO(const_true((nr) >= BITS_PER_TYPE(type)))
+
+#define BIT_TYPE(type, nr) ((type)(BIT_INPUT_CHECK(type, nr) + BIT_ULL(nr)))
+
+#define BIT_U8(nr)	BIT_TYPE(u8, nr)
+#define BIT_U16(nr)	BIT_TYPE(u16, nr)
+#define BIT_U32(nr)	BIT_TYPE(u32, nr)
+#define BIT_U64(nr)	BIT_TYPE(u64, nr)
+
+#else /* defined(__ASSEMBLY__) */
+
 /*
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
-#define GENMASK_INPUT_CHECK(h, l) 0
-#endif
-
-#define __GENMASK(h, l) \
-	(((~UL(0)) - (UL(1) << (l)) + 1) & \
-	 (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
-#define GENMASK(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-
-#define __GENMASK_ULL(h, l) \
-	(((~ULL(0)) - (ULL(1) << (l)) + 1) & \
-	 (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
-#define GENMASK_ULL(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
+#define GENMASK(h, l)		__GENMASK(h, l)
+#define GENMASK_ULL(h, l)	__GENMASK_ULL(h, l)
+
+#endif /* !defined(__ASSEMBLY__) */
 
 #endif	/* __LINUX_BITS_H */
diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h
index e6802b69cdd6..4f39e9cd7576 100644
--- a/include/linux/blk-crypto-profile.h
+++ b/include/linux/blk-crypto-profile.h
@@ -57,6 +57,62 @@ struct blk_crypto_ll_ops {
 	int (*keyslot_evict)(struct blk_crypto_profile *profile,
 			     const struct blk_crypto_key *key,
 			     unsigned int slot);
+
+	/**
+	 * @derive_sw_secret: Derive the software secret from a hardware-wrapped
+	 *		      key in ephemerally-wrapped form.
+	 *
+	 * This only needs to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED
+	 * is supported.
+	 *
+	 * Must return 0 on success, -EBADMSG if the key is invalid, or another
+	 * -errno code on other errors.
+	 */
+	int (*derive_sw_secret)(struct blk_crypto_profile *profile,
+				const u8 *eph_key, size_t eph_key_size,
+				u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]);
+
+	/**
+	 * @import_key: Create a hardware-wrapped key by importing a raw key.
+	 *
+	 * This only needs to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED
+	 * is supported.
+	 *
+	 * On success, must write the new key in long-term wrapped form to
+	 * @lt_key and return its size in bytes.  On failure, must return a
+	 * -errno value.
+	 */
+	int (*import_key)(struct blk_crypto_profile *profile,
+			  const u8 *raw_key, size_t raw_key_size,
+			  u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]);
+
+	/**
+	 * @generate_key: Generate a hardware-wrapped key.
+	 *
+	 * This only needs to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED
+	 * is supported.
+	 *
+	 * On success, must write the new key in long-term wrapped form to
+	 * @lt_key and return its size in bytes.  On failure, must return a
+	 * -errno value.
+	 */
+	int (*generate_key)(struct blk_crypto_profile *profile,
+			    u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]);
+
+	/**
+	 * @prepare_key: Prepare a hardware-wrapped key to be used.
+	 *
+	 * Prepare a hardware-wrapped key to be used by converting it from
+	 * long-term wrapped form to ephemerally-wrapped form.  This only needs
+	 * to be implemented if BLK_CRYPTO_KEY_TYPE_HW_WRAPPED is supported.
+	 *
+	 * On success, must write the key in ephemerally-wrapped form to
+	 * @eph_key and return its size in bytes.  On failure, must return
+	 * -EBADMSG if the key is invalid, or another -errno on other error.
+	 */
+	int (*prepare_key)(struct blk_crypto_profile *profile,
+			   const u8 *lt_key, size_t lt_key_size,
+			   u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]);
 };
 
 /**
@@ -85,6 +141,12 @@ struct blk_crypto_profile {
 	unsigned int max_dun_bytes_supported;
 
 	/**
+	 * @key_types_supported: A bitmask of the supported key types:
+	 * BLK_CRYPTO_KEY_TYPE_RAW and/or BLK_CRYPTO_KEY_TYPE_HW_WRAPPED.
+	 */
+	unsigned int key_types_supported;
+
+	/**
 	 * @modes_supported: Array of bitmasks that specifies whether each
 	 * combination of crypto mode and data unit size is supported.
 	 * Specifically, the i'th bit of modes_supported[crypto_mode] is set if
@@ -111,6 +173,7 @@ struct blk_crypto_profile {
 	 * keyslots while ensuring that they can't be changed concurrently.
 	 */
 	struct rw_semaphore lock;
+	struct lock_class_key lockdep_key;
 
 	/* List of idle slots, with least recently used slot at front */
 	wait_queue_head_t idle_slots_wait_queue;
@@ -142,6 +205,17 @@ void blk_crypto_reprogram_all_keys(struct blk_crypto_profile *profile);
 
 void blk_crypto_profile_destroy(struct blk_crypto_profile *profile);
 
+int blk_crypto_import_key(struct blk_crypto_profile *profile,
+			  const u8 *raw_key, size_t raw_key_size,
+			  u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]);
+
+int blk_crypto_generate_key(struct blk_crypto_profile *profile,
+			    u8 lt_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]);
+
+int blk_crypto_prepare_key(struct blk_crypto_profile *profile,
+			   const u8 *lt_key, size_t lt_key_size,
+			   u8 eph_key[BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE]);
+
 void blk_crypto_intersect_capabilities(struct blk_crypto_profile *parent,
 				       const struct blk_crypto_profile *child);
 
diff --git a/include/linux/blk-crypto.h b/include/linux/blk-crypto.h
index 5e5822c18ee4..58b0c5254a67 100644
--- a/include/linux/blk-crypto.h
+++ b/include/linux/blk-crypto.h
@@ -6,7 +6,9 @@
 #ifndef __LINUX_BLK_CRYPTO_H
 #define __LINUX_BLK_CRYPTO_H
 
+#include <linux/minmax.h>
 #include <linux/types.h>
+#include <uapi/linux/blk-crypto.h>
 
 enum blk_crypto_mode_num {
 	BLK_ENCRYPTION_MODE_INVALID,
@@ -17,7 +19,55 @@ enum blk_crypto_mode_num {
 	BLK_ENCRYPTION_MODE_MAX,
 };
 
-#define BLK_CRYPTO_MAX_KEY_SIZE		64
+/*
+ * Supported types of keys.  Must be bitflags due to their use in
+ * blk_crypto_profile::key_types_supported.
+ */
+enum blk_crypto_key_type {
+	/*
+	 * Raw keys (i.e. "software keys").  These keys are simply kept in raw,
+	 * plaintext form in kernel memory.
+	 */
+	BLK_CRYPTO_KEY_TYPE_RAW = 0x1,
+
+	/*
+	 * Hardware-wrapped keys.  These keys are only present in kernel memory
+	 * in ephemerally-wrapped form, and they can only be unwrapped by
+	 * dedicated hardware.  For details, see the "Hardware-wrapped keys"
+	 * section of Documentation/block/inline-encryption.rst.
+	 */
+	BLK_CRYPTO_KEY_TYPE_HW_WRAPPED = 0x2,
+};
+
+/*
+ * Currently the maximum raw key size is 64 bytes, as that is the key size of
+ * BLK_ENCRYPTION_MODE_AES_256_XTS which takes the longest key.
+ *
+ * The maximum hardware-wrapped key size depends on the hardware's key wrapping
+ * algorithm, which is a hardware implementation detail, so it isn't precisely
+ * specified.  But currently 128 bytes is plenty in practice.  Implementations
+ * are recommended to wrap a 32-byte key for the hardware KDF with AES-256-GCM,
+ * which should result in a size closer to 64 bytes than 128.
+ *
+ * Both of these values can trivially be increased if ever needed.
+ */
+#define BLK_CRYPTO_MAX_RAW_KEY_SIZE		64
+#define BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE	128
+
+#define BLK_CRYPTO_MAX_ANY_KEY_SIZE \
+	MAX(BLK_CRYPTO_MAX_RAW_KEY_SIZE, BLK_CRYPTO_MAX_HW_WRAPPED_KEY_SIZE)
+
+/*
+ * Size of the "software secret" which can be derived from a hardware-wrapped
+ * key.  This is currently always 32 bytes.  Note, the choice of 32 bytes
+ * assumes that the software secret is only used directly for algorithms that
+ * don't require more than a 256-bit key to get the desired security strength.
+ * If it were to be used e.g. directly as an AES-256-XTS key, then this would
+ * need to be increased (which is possible if hardware supports it, but care
+ * would need to be taken to avoid breaking users who need exactly 32 bytes).
+ */
+#define BLK_CRYPTO_SW_SECRET_SIZE	32
+
 /**
  * struct blk_crypto_config - an inline encryption key's crypto configuration
  * @crypto_mode: encryption algorithm this key is for
@@ -26,20 +76,23 @@ enum blk_crypto_mode_num {
  *	ciphertext.  This is always a power of 2.  It might be e.g. the
  *	filesystem block size or the disk sector size.
  * @dun_bytes: the maximum number of bytes of DUN used when using this key
+ * @key_type: the type of this key -- either raw or hardware-wrapped
  */
 struct blk_crypto_config {
 	enum blk_crypto_mode_num crypto_mode;
 	unsigned int data_unit_size;
 	unsigned int dun_bytes;
+	enum blk_crypto_key_type key_type;
 };
 
 /**
  * struct blk_crypto_key - an inline encryption key
- * @crypto_cfg: the crypto configuration (like crypto_mode, key size) for this
- *		key
+ * @crypto_cfg: the crypto mode, data unit size, key type, and other
+ *		characteristics of this key and how it will be used
  * @data_unit_size_bits: log2 of data_unit_size
- * @size: size of this key in bytes (determined by @crypto_cfg.crypto_mode)
- * @raw: the raw bytes of this key.  Only the first @size bytes are used.
+ * @size: size of this key in bytes.  The size of a raw key is fixed for a given
+ *	  crypto mode, but the size of a hardware-wrapped key can vary.
+ * @bytes: the bytes of this key.  Only the first @size bytes are significant.
  *
  * A blk_crypto_key is immutable once created, and many bios can reference it at
  * the same time.  It must not be freed until all bios using it have completed
@@ -49,7 +102,7 @@ struct blk_crypto_key {
 	struct blk_crypto_config crypto_cfg;
 	unsigned int data_unit_size_bits;
 	unsigned int size;
-	u8 raw[BLK_CRYPTO_MAX_KEY_SIZE];
+	u8 bytes[BLK_CRYPTO_MAX_ANY_KEY_SIZE];
 };
 
 #define BLK_CRYPTO_MAX_IV_SIZE		32
@@ -87,7 +140,9 @@ bool bio_crypt_dun_is_contiguous(const struct bio_crypt_ctx *bc,
 				 unsigned int bytes,
 				 const u64 next_dun[BLK_CRYPTO_DUN_ARRAY_SIZE]);
 
-int blk_crypto_init_key(struct blk_crypto_key *blk_key, const u8 *raw_key,
+int blk_crypto_init_key(struct blk_crypto_key *blk_key,
+			const u8 *key_bytes, size_t key_size,
+			enum blk_crypto_key_type key_type,
 			enum blk_crypto_mode_num crypto_mode,
 			unsigned int dun_bytes,
 			unsigned int data_unit_size);
@@ -103,6 +158,10 @@ bool blk_crypto_config_supported_natively(struct block_device *bdev,
 bool blk_crypto_config_supported(struct block_device *bdev,
 				 const struct blk_crypto_config *cfg);
 
+int blk_crypto_derive_sw_secret(struct block_device *bdev,
+				const u8 *eph_key, size_t eph_key_size,
+				u8 sw_secret[BLK_CRYPTO_SW_SECRET_SIZE]);
+
 #else /* CONFIG_BLK_INLINE_ENCRYPTION */
 
 static inline bool bio_has_crypt_ctx(struct bio *bio)
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index 378b2459efe2..a6b84206eb94 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -3,54 +3,58 @@
 #define _LINUX_BLK_INTEGRITY_H
 
 #include <linux/blk-mq.h>
+#include <linux/bio-integrity.h>
+#include <linux/blk-mq-dma.h>
 
 struct request;
 
+/*
+ * Maximum contiguous integrity buffer allocation.
+ */
+#define BLK_INTEGRITY_MAX_SIZE		SZ_2M
+
 enum blk_integrity_flags {
-	BLK_INTEGRITY_VERIFY		= 1 << 0,
-	BLK_INTEGRITY_GENERATE		= 1 << 1,
+	BLK_INTEGRITY_NOVERIFY		= 1 << 0,
+	BLK_INTEGRITY_NOGENERATE	= 1 << 1,
 	BLK_INTEGRITY_DEVICE_CAPABLE	= 1 << 2,
-	BLK_INTEGRITY_IP_CHECKSUM	= 1 << 3,
+	BLK_INTEGRITY_REF_TAG		= 1 << 3,
+	BLK_INTEGRITY_STACKED		= 1 << 4,
 };
 
-struct blk_integrity_iter {
-	void			*prot_buf;
-	void			*data_buf;
-	sector_t		seed;
-	unsigned int		data_size;
-	unsigned short		interval;
-	unsigned char		tuple_size;
-	const char		*disk_name;
-};
-
-typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *);
-typedef void (integrity_prepare_fn) (struct request *);
-typedef void (integrity_complete_fn) (struct request *, unsigned int);
-
-struct blk_integrity_profile {
-	integrity_processing_fn		*generate_fn;
-	integrity_processing_fn		*verify_fn;
-	integrity_prepare_fn		*prepare_fn;
-	integrity_complete_fn		*complete_fn;
-	const char			*name;
-};
+const char *blk_integrity_profile_name(struct blk_integrity *bi);
+bool queue_limits_stack_integrity(struct queue_limits *t,
+		struct queue_limits *b);
+static inline bool queue_limits_stack_integrity_bdev(struct queue_limits *t,
+		struct block_device *bdev)
+{
+	return queue_limits_stack_integrity(t, &bdev->bd_disk->queue->limits);
+}
 
 #ifdef CONFIG_BLK_DEV_INTEGRITY
-void blk_integrity_register(struct gendisk *, struct blk_integrity *);
-void blk_integrity_unregister(struct gendisk *);
-int blk_integrity_compare(struct gendisk *, struct gendisk *);
-int blk_rq_map_integrity_sg(struct request_queue *, struct bio *,
-				   struct scatterlist *);
+int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
+
 int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
+int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
+			      ssize_t bytes);
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp);
+bool blk_rq_integrity_dma_map_iter_start(struct request *req,
+		struct device *dma_dev,  struct dma_iova_state *state,
+		struct blk_dma_iter *iter);
+bool blk_rq_integrity_dma_map_iter_next(struct request *req,
+		struct device *dma_dev, struct blk_dma_iter *iter);
 
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
 {
-	struct blk_integrity *bi = &disk->queue->integrity;
+	return q->limits.integrity.metadata_size;
+}
 
-	if (!bi->profile)
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+{
+	if (!blk_integrity_queue_supports_integrity(disk->queue))
 		return NULL;
-
-	return bi;
+	return &disk->queue->limits.integrity;
 }
 
 static inline struct blk_integrity *
@@ -59,18 +63,6 @@ bdev_get_integrity(struct block_device *bdev)
 	return blk_get_integrity(bdev->bd_disk);
 }
 
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
-{
-	return q->integrity.profile;
-}
-
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-						    unsigned int segs)
-{
-	q->limits.max_integrity_segments = segs;
-}
-
 static inline unsigned short
 queue_max_integrity_segments(const struct request_queue *q)
 {
@@ -96,7 +88,7 @@ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 					       unsigned int sectors)
 {
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+	return bio_integrity_intervals(bi, sectors) * bi->metadata_size;
 }
 
 static inline bool blk_integrity_rq(struct request *rq)
@@ -105,54 +97,59 @@ static inline bool blk_integrity_rq(struct request *rq)
 }
 
 /*
- * Return the first bvec that contains integrity data.  Only drivers that are
- * limited to a single integrity segment should use this helper.
+ * Return the current bvec that contains the integrity data. bip_iter may be
+ * advanced to iterate over the integrity data.
  */
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+static inline struct bio_vec rq_integrity_vec(struct request *rq)
 {
-	if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
-		return NULL;
-	return rq->bio->bi_integrity->bip_vec;
+	return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec,
+				 rq->bio->bi_integrity->bip_iter);
 }
 #else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+				   struct logical_block_metadata_cap __user *argp)
+{
+	return -ENOIOCTLCMD;
+}
 static inline int blk_rq_count_integrity_sg(struct request_queue *q,
 					    struct bio *b)
 {
 	return 0;
 }
-static inline int blk_rq_map_integrity_sg(struct request_queue *q,
-					  struct bio *b,
+static inline int blk_rq_map_integrity_sg(struct request *q,
 					  struct scatterlist *s)
 {
 	return 0;
 }
-static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
-{
-	return NULL;
-}
-static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
+static inline int blk_rq_integrity_map_user(struct request *rq,
+					    void __user *ubuf,
+					    ssize_t bytes)
 {
-	return NULL;
+	return -EINVAL;
 }
-static inline bool
-blk_integrity_queue_supports_integrity(struct request_queue *q)
+static inline bool blk_rq_integrity_dma_map_iter_start(struct request *req,
+		struct device *dma_dev,  struct dma_iova_state *state,
+		struct blk_dma_iter *iter)
 {
 	return false;
 }
-static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b)
+static inline bool blk_rq_integrity_dma_map_iter_next(struct request *req,
+		struct device *dma_dev, struct blk_dma_iter *iter)
 {
-	return 0;
+	return false;
 }
-static inline void blk_integrity_register(struct gendisk *d,
-					 struct blk_integrity *b)
+static inline struct blk_integrity *bdev_get_integrity(struct block_device *b)
 {
+	return NULL;
 }
-static inline void blk_integrity_unregister(struct gendisk *d)
+static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
 {
+	return NULL;
 }
-static inline void blk_queue_max_integrity_segments(struct request_queue *q,
-						    unsigned int segs)
+static inline bool
+blk_integrity_queue_supports_integrity(struct request_queue *q)
 {
+	return false;
 }
 static inline unsigned short
 queue_max_integrity_segments(const struct request_queue *q)
@@ -176,9 +173,11 @@ static inline int blk_integrity_rq(struct request *rq)
 	return 0;
 }
 
-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
+static inline struct bio_vec rq_integrity_vec(struct request *rq)
 {
-	return NULL;
+	/* the optimizer will remove all calls to this function */
+	return (struct bio_vec){ };
 }
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
+
 #endif /* _LINUX_BLK_INTEGRITY_H */
diff --git a/include/linux/blk-mq-dma.h b/include/linux/blk-mq-dma.h
new file mode 100644
index 000000000000..cb88fc791fbd
--- /dev/null
+++ b/include/linux/blk-mq-dma.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef BLK_MQ_DMA_H
+#define BLK_MQ_DMA_H
+
+#include <linux/blk-mq.h>
+#include <linux/pci-p2pdma.h>
+
+struct blk_map_iter {
+	struct bvec_iter		iter;
+	struct bio			*bio;
+	struct bio_vec			*bvecs;
+	bool				is_integrity;
+};
+
+struct blk_dma_iter {
+	/* Output address range for this iteration */
+	dma_addr_t			addr;
+	u32				len;
+	struct pci_p2pdma_map_state	p2pdma;
+
+	/* Status code. Only valid when blk_rq_dma_map_iter_* returned false */
+	blk_status_t			status;
+
+	/* Internal to blk_rq_dma_map_iter_* */
+	struct blk_map_iter		iter;
+};
+
+bool blk_rq_dma_map_iter_start(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter);
+bool blk_rq_dma_map_iter_next(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter);
+
+/**
+ * blk_rq_dma_map_coalesce - were all segments coalesced?
+ * @state: DMA state to check
+ *
+ * Returns true if blk_rq_dma_map_iter_start coalesced all segments into a
+ * single DMA range.
+ */
+static inline bool blk_rq_dma_map_coalesce(struct dma_iova_state *state)
+{
+	return dma_use_iova(state);
+}
+
+/**
+ * blk_rq_dma_unmap - try to DMA unmap a request
+ * @req:	request to unmap
+ * @dma_dev:	device to unmap from
+ * @state:	DMA IOVA state
+ * @mapped_len: number of bytes to unmap
+ * @map:	peer-to-peer mapping type
+ *
+ * Returns %false if the callers need to manually unmap every DMA segment
+ * mapped using @iter or %true if no work is left to be done.
+ */
+static inline bool blk_rq_dma_unmap(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, size_t mapped_len,
+		enum pci_p2pdma_map_type map)
+{
+	if (map == PCI_P2PDMA_MAP_BUS_ADDR)
+		return true;
+
+	if (dma_use_iova(state)) {
+		unsigned int attrs = 0;
+
+		if (map == PCI_P2PDMA_MAP_THRU_HOST_BRIDGE)
+			attrs |= DMA_ATTR_MMIO;
+
+		dma_iova_destroy(dma_dev, state, mapped_len, rq_dma_dir(req),
+				 attrs);
+		return true;
+	}
+
+	return !dma_need_unmap(dma_dev);
+}
+#endif /* BLK_MQ_DMA_H */
diff --git a/include/linux/blk-mq-pci.h b/include/linux/blk-mq-pci.h
deleted file mode 100644
index ca544e1d3508..000000000000
--- a/include/linux/blk-mq-pci.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BLK_MQ_PCI_H
-#define _LINUX_BLK_MQ_PCI_H
-
-struct blk_mq_queue_map;
-struct pci_dev;
-
-void blk_mq_pci_map_queues(struct blk_mq_queue_map *qmap, struct pci_dev *pdev,
-			   int offset);
-
-#endif /* _LINUX_BLK_MQ_PCI_H */
diff --git a/include/linux/blk-mq-virtio.h b/include/linux/blk-mq-virtio.h
deleted file mode 100644
index 13226e9b22dd..000000000000
--- a/include/linux/blk-mq-virtio.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BLK_MQ_VIRTIO_H
-#define _LINUX_BLK_MQ_VIRTIO_H
-
-struct blk_mq_queue_map;
-struct virtio_device;
-
-void blk_mq_virtio_map_queues(struct blk_mq_queue_map *qmap,
-		struct virtio_device *vdev, int first_vec);
-
-#endif /* _LINUX_BLK_MQ_VIRTIO_H */
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index 06caacd77ed6..cae9e857aea4 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -8,6 +8,8 @@
 #include <linux/scatterlist.h>
 #include <linux/prefetch.h>
 #include <linux/srcu.h>
+#include <linux/rw_hint.h>
+#include <linux/rwsem.h>
 
 struct blk_mq_tags;
 struct blk_flush_queue;
@@ -26,46 +28,65 @@ typedef enum rq_end_io_ret (rq_end_io_fn)(struct request *, blk_status_t);
  * request flags */
 typedef __u32 __bitwise req_flags_t;
 
-/* drive already may have started this one */
-#define RQF_STARTED		((__force req_flags_t)(1 << 1))
-/* may not be passed by ioscheduler */
-#define RQF_SOFTBARRIER		((__force req_flags_t)(1 << 3))
-/* request for flush sequence */
-#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << 4))
-/* merge of different types, fail separately */
-#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << 5))
-/* track inflight for MQ */
-#define RQF_MQ_INFLIGHT		((__force req_flags_t)(1 << 6))
-/* don't call prep for this one */
-#define RQF_DONTPREP		((__force req_flags_t)(1 << 7))
-/* vaguely specified driver internal error.  Ignored by the block layer */
-#define RQF_FAILED		((__force req_flags_t)(1 << 10))
-/* don't warn about errors */
-#define RQF_QUIET		((__force req_flags_t)(1 << 11))
-/* elevator private data attached */
-#define RQF_ELVPRIV		((__force req_flags_t)(1 << 12))
-/* account into disk and partition IO statistics */
-#define RQF_IO_STAT		((__force req_flags_t)(1 << 13))
-/* runtime pm request */
-#define RQF_PM			((__force req_flags_t)(1 << 15))
-/* on IO scheduler merge hash */
-#define RQF_HASHED		((__force req_flags_t)(1 << 16))
-/* track IO completion time */
-#define RQF_STATS		((__force req_flags_t)(1 << 17))
-/* Look at ->special_vec for the actual data payload instead of the
-   bio chain. */
-#define RQF_SPECIAL_PAYLOAD	((__force req_flags_t)(1 << 18))
-/* The per-zone write lock is held for this request */
-#define RQF_ZONE_WRITE_LOCKED	((__force req_flags_t)(1 << 19))
-/* ->timeout has been called, don't expire again */
-#define RQF_TIMED_OUT		((__force req_flags_t)(1 << 21))
-/* queue has elevator attached */
-#define RQF_ELV			((__force req_flags_t)(1 << 22))
-#define RQF_RESV			((__force req_flags_t)(1 << 23))
+/* Keep rqf_name[] in sync with the definitions below */
+enum rqf_flags {
+	/* drive already may have started this one */
+	__RQF_STARTED,
+	/* request for flush sequence */
+	__RQF_FLUSH_SEQ,
+	/* merge of different types, fail separately */
+	__RQF_MIXED_MERGE,
+	/* don't call prep for this one */
+	__RQF_DONTPREP,
+	/* use hctx->sched_tags */
+	__RQF_SCHED_TAGS,
+	/* use an I/O scheduler for this request */
+	__RQF_USE_SCHED,
+	/* vaguely specified driver internal error.  Ignored by block layer */
+	__RQF_FAILED,
+	/* don't warn about errors */
+	__RQF_QUIET,
+	/* account into disk and partition IO statistics */
+	__RQF_IO_STAT,
+	/* runtime pm request */
+	__RQF_PM,
+	/* on IO scheduler merge hash */
+	__RQF_HASHED,
+	/* track IO completion time */
+	__RQF_STATS,
+	/* Look at ->special_vec for the actual data payload instead of the
+	   bio chain. */
+	__RQF_SPECIAL_PAYLOAD,
+	/* request completion needs to be signaled to zone write plugging. */
+	__RQF_ZONE_WRITE_PLUGGING,
+	/* ->timeout has been called, don't expire again */
+	__RQF_TIMED_OUT,
+	__RQF_RESV,
+	__RQF_BITS
+};
+
+#define RQF_STARTED		((__force req_flags_t)(1 << __RQF_STARTED))
+#define RQF_FLUSH_SEQ		((__force req_flags_t)(1 << __RQF_FLUSH_SEQ))
+#define RQF_MIXED_MERGE		((__force req_flags_t)(1 << __RQF_MIXED_MERGE))
+#define RQF_DONTPREP		((__force req_flags_t)(1 << __RQF_DONTPREP))
+#define RQF_SCHED_TAGS		((__force req_flags_t)(1 << __RQF_SCHED_TAGS))
+#define RQF_USE_SCHED		((__force req_flags_t)(1 << __RQF_USE_SCHED))
+#define RQF_FAILED		((__force req_flags_t)(1 << __RQF_FAILED))
+#define RQF_QUIET		((__force req_flags_t)(1 << __RQF_QUIET))
+#define RQF_IO_STAT		((__force req_flags_t)(1 << __RQF_IO_STAT))
+#define RQF_PM			((__force req_flags_t)(1 << __RQF_PM))
+#define RQF_HASHED		((__force req_flags_t)(1 << __RQF_HASHED))
+#define RQF_STATS		((__force req_flags_t)(1 << __RQF_STATS))
+#define RQF_SPECIAL_PAYLOAD	\
+			((__force req_flags_t)(1 << __RQF_SPECIAL_PAYLOAD))
+#define RQF_ZONE_WRITE_PLUGGING	\
+			((__force req_flags_t)(1 << __RQF_ZONE_WRITE_PLUGGING))
+#define RQF_TIMED_OUT		((__force req_flags_t)(1 << __RQF_TIMED_OUT))
+#define RQF_RESV		((__force req_flags_t)(1 << __RQF_RESV))
 
 /* flags that prevent us from merging requests: */
 #define RQF_NOMERGE_FLAGS \
-	(RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
+	(RQF_STARTED | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD)
 
 enum mq_rq_state {
 	MQ_RQ_IDLE		= 0,
@@ -129,18 +150,21 @@ struct request {
 	 * physical address coalescing is performed.
 	 */
 	unsigned short nr_phys_segments;
-
-#ifdef CONFIG_BLK_DEV_INTEGRITY
 	unsigned short nr_integrity_segments;
-#endif
+
+	/*
+	 * The lowest set bit for address gaps between physical segments. This
+	 * provides information necessary for dma optimization opprotunities,
+	 * like for testing if the segments can be coalesced against the
+	 * device's iommu granule.
+	 */
+	unsigned char phys_gap_bit;
 
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct bio_crypt_ctx *crypt_ctx;
 	struct blk_crypto_keyslot *crypt_keyslot;
 #endif
 
-	unsigned short ioprio;
-
 	enum mq_rq_state state;
 	atomic_t ref;
 
@@ -160,39 +184,30 @@ struct request {
 
 	/*
 	 * The rb_node is only used inside the io scheduler, requests
-	 * are pruned when moved to the dispatch queue. So let the
-	 * completion_data share space with the rb_node.
+	 * are pruned when moved to the dispatch queue. special_vec must
+	 * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be
+	 * insert into an IO scheduler.
 	 */
 	union {
 		struct rb_node rb_node;	/* sort/lookup */
 		struct bio_vec special_vec;
-		void *completion_data;
 	};
 
-
 	/*
 	 * Three pointers are available for the IO schedulers, if they need
-	 * more they have to dynamically allocate it.  Flush requests are
-	 * never put on the IO scheduler. So let the flush fields share
-	 * space with the elevator data.
+	 * more they have to dynamically allocate it.
 	 */
-	union {
-		struct {
-			struct io_cq		*icq;
-			void			*priv[2];
-		} elv;
-
-		struct {
-			unsigned int		seq;
-			struct list_head	list;
-			rq_end_io_fn		*saved_end_io;
-		} flush;
-	};
+	struct {
+		struct io_cq		*icq;
+		void			*priv[2];
+	} elv;
 
-	union {
-		struct __call_single_data csd;
-		u64 fifo_time;
-	};
+	struct {
+		unsigned int		seq;
+		rq_end_io_fn		*saved_end_io;
+	} flush;
+
+	u64 fifo_time;
 
 	/*
 	 * completion callback.
@@ -201,6 +216,14 @@ struct request {
 	void *end_io_data;
 };
 
+/*
+ * Returns a mask with all bits starting at req->phys_gap_bit set to 1.
+ */
+static inline unsigned long req_phys_gap_mask(const struct request *req)
+{
+	return ~(((1 << req->phys_gap_bit) >> 1) - 1);
+}
+
 static inline enum req_op req_op(const struct request *req)
 {
 	return req->cmd_flags & REQ_OP_MASK;
@@ -208,12 +231,14 @@ static inline enum req_op req_op(const struct request *req)
 
 static inline bool blk_rq_is_passthrough(struct request *rq)
 {
-	return blk_op_is_passthrough(req_op(rq));
+	return blk_op_is_passthrough(rq->cmd_flags);
 }
 
 static inline unsigned short req_get_ioprio(struct request *req)
 {
-	return req->ioprio;
+	if (req->bio)
+		return req->bio->bi_ioprio;
+	return 0;
 }
 
 #define rq_data_dir(rq)		(op_is_write(req_op(rq)) ? WRITE : READ)
@@ -221,62 +246,61 @@ static inline unsigned short req_get_ioprio(struct request *req)
 #define rq_dma_dir(rq) \
 	(op_is_write(req_op(rq)) ? DMA_TO_DEVICE : DMA_FROM_DEVICE)
 
-#define rq_list_add(listptr, rq)	do {		\
-	(rq)->rq_next = *(listptr);			\
-	*(listptr) = rq;				\
-} while (0)
-
-#define rq_list_add_tail(lastpptr, rq)	do {		\
-	(rq)->rq_next = NULL;				\
-	**(lastpptr) = rq;				\
-	*(lastpptr) = &rq->rq_next;			\
-} while (0)
-
-#define rq_list_pop(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))	{		\
-		__req = *(listptr);			\
-		*(listptr) = __req->rq_next;		\
-	}						\
-	__req;						\
-})
+static inline int rq_list_empty(const struct rq_list *rl)
+{
+	return rl->head == NULL;
+}
 
-#define rq_list_peek(listptr)				\
-({							\
-	struct request *__req = NULL;			\
-	if ((listptr) && *(listptr))			\
-		__req = *(listptr);			\
-	__req;						\
-})
+static inline void rq_list_init(struct rq_list *rl)
+{
+	rl->head = NULL;
+	rl->tail = NULL;
+}
+
+static inline void rq_list_add_tail(struct rq_list *rl, struct request *rq)
+{
+	rq->rq_next = NULL;
+	if (rl->tail)
+		rl->tail->rq_next = rq;
+	else
+		rl->head = rq;
+	rl->tail = rq;
+}
 
-#define rq_list_for_each(listptr, pos)			\
-	for (pos = rq_list_peek((listptr)); pos; pos = rq_list_next(pos))
+static inline void rq_list_add_head(struct rq_list *rl, struct request *rq)
+{
+	rq->rq_next = rl->head;
+	rl->head = rq;
+	if (!rl->tail)
+		rl->tail = rq;
+}
 
-#define rq_list_for_each_safe(listptr, pos, nxt)			\
-	for (pos = rq_list_peek((listptr)), nxt = rq_list_next(pos);	\
-		pos; pos = nxt, nxt = pos ? rq_list_next(pos) : NULL)
+static inline struct request *rq_list_pop(struct rq_list *rl)
+{
+	struct request *rq = rl->head;
 
-#define rq_list_next(rq)	(rq)->rq_next
-#define rq_list_empty(list)	((list) == (struct request *) NULL)
+	if (rq) {
+		rl->head = rl->head->rq_next;
+		if (!rl->head)
+			rl->tail = NULL;
+		rq->rq_next = NULL;
+	}
 
-/**
- * rq_list_move() - move a struct request from one list to another
- * @src: The source list @rq is currently in
- * @dst: The destination list that @rq will be appended to
- * @rq: The request to move
- * @prev: The request preceding @rq in @src (NULL if @rq is the head)
- */
-static inline void rq_list_move(struct request **src, struct request **dst,
-				struct request *rq, struct request *prev)
+	return rq;
+}
+
+static inline struct request *rq_list_peek(struct rq_list *rl)
 {
-	if (prev)
-		prev->rq_next = rq->rq_next;
-	else
-		*src = rq->rq_next;
-	rq_list_add(dst, rq);
+	return rl->head;
 }
 
+#define rq_list_for_each(rl, pos)					\
+	for (pos = rq_list_peek((rl)); (pos); pos = pos->rq_next)
+
+#define rq_list_for_each_safe(rl, pos, nxt)				\
+	for (pos = rq_list_peek((rl)), nxt = pos->rq_next;		\
+		pos; pos = nxt, nxt = pos ? pos->rq_next : NULL)
+
 /**
  * enum blk_eh_timer_return - How the timeout handler should proceed
  * @BLK_EH_DONE: The block driver completed the command or will complete it at
@@ -289,9 +313,6 @@ enum blk_eh_timer_return {
 	BLK_EH_RESET_TIMER,
 };
 
-#define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */
-#define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */
-
 /**
  * struct blk_mq_hw_ctx - State for a hardware queue facing the hardware
  * block device
@@ -404,11 +425,6 @@ struct blk_mq_hw_ctx {
 	 */
 	struct blk_mq_tags	*sched_tags;
 
-	/** @queued: Number of queued requests. */
-	unsigned long		queued;
-	/** @run: Number of dispatched requests. */
-	unsigned long		run;
-
 	/** @numa_node: NUMA node the storage adapter has been connected to. */
 	unsigned int		numa_node;
 	/** @queue_num: Index of this hardware queue. */
@@ -507,6 +523,11 @@ enum hctx_type {
  *		   request_queue.tag_set_list.
  * @srcu:	   Use as lock when type of the request queue is blocking
  *		   (BLK_MQ_F_BLOCKING).
+ * @tags_srcu:	   SRCU used to defer freeing of tags page_list to prevent
+ *		   use-after-free when iterating tags.
+ * @update_nr_hwq_lock:
+ * 		   Synchronize updating nr_hw_queues with add/del disk &
+ * 		   switching elevator.
  */
 struct blk_mq_tag_set {
 	const struct blk_mq_ops	*ops;
@@ -528,6 +549,9 @@ struct blk_mq_tag_set {
 	struct mutex		tag_list_lock;
 	struct list_head	tag_list;
 	struct srcu_struct	*srcu;
+	struct srcu_struct	tags_srcu;
+
+	struct rw_semaphore	update_nr_hwq_lock;
 };
 
 /**
@@ -569,7 +593,7 @@ struct blk_mq_ops {
 	 * empty the @rqlist completely, then the rest will be queued
 	 * individually by the block layer upon return.
 	 */
-	void (*queue_rqs)(struct request **rqlist);
+	void (*queue_rqs)(struct rq_list *rqlist);
 
 	/**
 	 * @get_budget: Reserve budget before queue request, once .queue_rq is
@@ -660,8 +684,8 @@ struct blk_mq_ops {
 #endif
 };
 
+/* Keep hctx_flag_name[] in sync with the definitions below */
 enum {
-	BLK_MQ_F_SHOULD_MERGE	= 1 << 0,
 	BLK_MQ_F_TAG_QUEUE_SHARED = 1 << 1,
 	/*
 	 * Set when this device requires underlying blk-mq device for
@@ -669,48 +693,48 @@ enum {
 	 */
 	BLK_MQ_F_STACKING	= 1 << 2,
 	BLK_MQ_F_TAG_HCTX_SHARED = 1 << 3,
-	BLK_MQ_F_BLOCKING	= 1 << 5,
-	/* Do not allow an I/O scheduler to be configured. */
-	BLK_MQ_F_NO_SCHED	= 1 << 6,
+	BLK_MQ_F_BLOCKING	= 1 << 4,
+
+	/*
+	 * Alloc tags on a round-robin base instead of the first available one.
+	 */
+	BLK_MQ_F_TAG_RR		= 1 << 5,
+
 	/*
 	 * Select 'none' during queue registration in case of a single hwq
 	 * or shared hwqs instead of 'mq-deadline'.
 	 */
-	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 7,
-	BLK_MQ_F_ALLOC_POLICY_START_BIT = 8,
-	BLK_MQ_F_ALLOC_POLICY_BITS = 1,
-
-	BLK_MQ_S_STOPPED	= 0,
-	BLK_MQ_S_TAG_ACTIVE	= 1,
-	BLK_MQ_S_SCHED_RESTART	= 2,
-
-	/* hw queue is inactive after all its CPUs become offline */
-	BLK_MQ_S_INACTIVE	= 3,
-
-	BLK_MQ_MAX_DEPTH	= 10240,
+	BLK_MQ_F_NO_SCHED_BY_DEFAULT	= 1 << 6,
 
-	BLK_MQ_CPU_WORK_BATCH	= 8,
+	BLK_MQ_F_MAX = 1 << 7,
 };
-#define BLK_MQ_FLAG_TO_ALLOC_POLICY(flags) \
-	((flags >> BLK_MQ_F_ALLOC_POLICY_START_BIT) & \
-		((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1))
-#define BLK_ALLOC_POLICY_TO_MQ_FLAG(policy) \
-	((policy & ((1 << BLK_MQ_F_ALLOC_POLICY_BITS) - 1)) \
-		<< BLK_MQ_F_ALLOC_POLICY_START_BIT)
 
+#define BLK_MQ_MAX_DEPTH	(10240)
 #define BLK_MQ_NO_HCTX_IDX	(-1U)
 
-struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set, void *queuedata,
+enum {
+	/* Keep hctx_state_name[] in sync with the definitions below */
+	BLK_MQ_S_STOPPED,
+	BLK_MQ_S_TAG_ACTIVE,
+	BLK_MQ_S_SCHED_RESTART,
+	/* hw queue is inactive after all its CPUs become offline */
+	BLK_MQ_S_INACTIVE,
+	BLK_MQ_S_MAX
+};
+
+struct gendisk *__blk_mq_alloc_disk(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata,
 		struct lock_class_key *lkclass);
-#define blk_mq_alloc_disk(set, queuedata)				\
+#define blk_mq_alloc_disk(set, lim, queuedata)				\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_mq_alloc_disk(set, queuedata, &__key);			\
+	__blk_mq_alloc_disk(set, lim, queuedata, &__key);		\
 })
 struct gendisk *blk_mq_alloc_disk_for_queue(struct request_queue *q,
 		struct lock_class_key *lkclass);
-struct request_queue *blk_mq_init_queue(struct blk_mq_tag_set *);
+struct request_queue *blk_mq_alloc_queue(struct blk_mq_tag_set *set,
+		struct queue_limits *lim, void *queuedata);
 int blk_mq_init_allocated_queue(struct blk_mq_tag_set *set,
 		struct request_queue *q);
 void blk_mq_destroy_queue(struct request_queue *);
@@ -722,6 +746,8 @@ int blk_mq_alloc_sq_tag_set(struct blk_mq_tag_set *set,
 void blk_mq_free_tag_set(struct blk_mq_tag_set *set);
 
 void blk_mq_free_request(struct request *rq);
+int blk_rq_poll(struct request *rq, struct io_comp_batch *iob,
+		unsigned int poll_flags);
 
 bool blk_mq_queue_inflight(struct request_queue *q);
 
@@ -746,8 +772,7 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
 struct blk_mq_tags {
 	unsigned int nr_tags;
 	unsigned int nr_reserved_tags;
-
-	atomic_t active_queues;
+	unsigned int active_queues;
 
 	struct sbitmap_queue bitmap_tags;
 	struct sbitmap_queue breserved_tags;
@@ -761,6 +786,7 @@ struct blk_mq_tags {
 	 * request pool
 	 */
 	spinlock_t lock;
+	struct rcu_head rcu_head;
 };
 
 static inline struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags,
@@ -844,7 +870,7 @@ void blk_mq_end_request_batch(struct io_comp_batch *ib);
  */
 static inline bool blk_mq_need_time_stamp(struct request *rq)
 {
-	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_ELV));
+	return (rq->rq_flags & (RQF_IO_STAT | RQF_STATS | RQF_USE_SCHED));
 }
 
 static inline bool blk_mq_is_reserved_rq(struct request *rq)
@@ -852,24 +878,46 @@ static inline bool blk_mq_is_reserved_rq(struct request *rq)
 	return rq->rq_flags & RQF_RESV;
 }
 
-/*
+/**
+ * blk_mq_add_to_batch() - add a request to the completion batch
+ * @req: The request to add to batch
+ * @iob: The batch to add the request
+ * @is_error: Specify true if the request failed with an error
+ * @complete: The completaion handler for the request
+ *
  * Batched completions only work when there is no I/O error and no special
  * ->end_io handler.
+ *
+ * Return: true when the request was added to the batch, otherwise false
  */
 static inline bool blk_mq_add_to_batch(struct request *req,
-				       struct io_comp_batch *iob, int ioerror,
+				       struct io_comp_batch *iob, bool is_error,
 				       void (*complete)(struct io_comp_batch *))
 {
-	if (!iob || (req->rq_flags & RQF_ELV) || ioerror ||
-			(req->end_io && !blk_rq_is_passthrough(req)))
+	/*
+	 * Check various conditions that exclude batch processing:
+	 * 1) No batch container
+	 * 2) Has scheduler data attached
+	 * 3) Not a passthrough request and end_io set
+	 * 4) Not a passthrough request and failed with an error
+	 */
+	if (!iob)
 		return false;
+	if (req->rq_flags & RQF_SCHED_TAGS)
+		return false;
+	if (!blk_rq_is_passthrough(req)) {
+		if (req->end_io)
+			return false;
+		if (is_error)
+			return false;
+	}
 
 	if (!iob->complete)
 		iob->complete = complete;
 	else if (iob->complete != complete)
 		return false;
 	iob->need_ts |= blk_mq_need_time_stamp(req);
-	rq_list_add(&iob->req_list, req);
+	rq_list_add_tail(&iob->req_list, req);
 	return true;
 }
 
@@ -896,14 +944,34 @@ void blk_mq_delay_run_hw_queues(struct request_queue *q, unsigned long msecs);
 void blk_mq_tagset_busy_iter(struct blk_mq_tag_set *tagset,
 		busy_tag_iter_fn *fn, void *priv);
 void blk_mq_tagset_wait_completed_request(struct blk_mq_tag_set *tagset);
-void blk_mq_freeze_queue(struct request_queue *q);
-void blk_mq_unfreeze_queue(struct request_queue *q);
+void blk_mq_freeze_queue_nomemsave(struct request_queue *q);
+void blk_mq_unfreeze_queue_nomemrestore(struct request_queue *q);
+static inline unsigned int __must_check
+blk_mq_freeze_queue(struct request_queue *q)
+{
+	unsigned int memflags = memalloc_noio_save();
+
+	blk_mq_freeze_queue_nomemsave(q);
+	return memflags;
+}
+static inline void
+blk_mq_unfreeze_queue(struct request_queue *q, unsigned int memflags)
+{
+	blk_mq_unfreeze_queue_nomemrestore(q);
+	memalloc_noio_restore(memflags);
+}
 void blk_freeze_queue_start(struct request_queue *q);
 void blk_mq_freeze_queue_wait(struct request_queue *q);
 int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 				     unsigned long timeout);
+void blk_mq_unfreeze_queue_non_owner(struct request_queue *q);
+void blk_freeze_queue_start_non_owner(struct request_queue *q);
 
+unsigned int blk_mq_num_possible_queues(unsigned int max_queues);
+unsigned int blk_mq_num_online_queues(unsigned int max_queues);
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
+void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
+			  struct device *dev, unsigned int offset);
 void blk_mq_update_nr_hw_queues(struct blk_mq_tag_set *set, int nr_hw_queues);
 
 void blk_mq_quiesce_queue_nowait(struct request_queue *q);
@@ -947,8 +1015,20 @@ static inline void *blk_mq_rq_to_pdu(struct request *rq)
 	return rq + 1;
 }
 
+static inline struct blk_mq_hw_ctx *queue_hctx(struct request_queue *q, int id)
+{
+	struct blk_mq_hw_ctx *hctx;
+
+	rcu_read_lock();
+	hctx = rcu_dereference(q->queue_hw_ctx)[id];
+	rcu_read_unlock();
+
+	return hctx;
+}
+
 #define queue_for_each_hw_ctx(q, hctx, i)				\
-	xa_for_each(&(q)->hctx_table, (i), (hctx))
+	for ((i) = 0; (i) < (q)->nr_hw_queues &&			\
+	     ({ hctx = queue_hctx((q), i); 1; }); (i)++)
 
 #define hctx_for_each_ctx(hctx, ctx, i)					\
 	for ((i) = 0; (i) < (hctx)->nr_ctx &&				\
@@ -960,15 +1040,6 @@ static inline void blk_mq_cleanup_rq(struct request *rq)
 		rq->q->mq_ops->cleanup_rq(rq);
 }
 
-static inline void blk_rq_bio_prep(struct request *rq, struct bio *bio,
-		unsigned int nr_segs)
-{
-	rq->nr_phys_segments = nr_segs;
-	rq->__data_len = bio->bi_iter.bi_size;
-	rq->bio = rq->biotail = bio;
-	rq->ioprio = bio_prio(bio);
-}
-
 void blk_mq_hctx_set_fq_lock_class(struct blk_mq_hw_ctx *hctx,
 		struct lock_class_key *key);
 
@@ -1000,8 +1071,8 @@ int blk_rq_map_user_io(struct request *, struct rq_map_data *,
 int blk_rq_map_user_iov(struct request_queue *, struct request *,
 		struct rq_map_data *, const struct iov_iter *, gfp_t);
 int blk_rq_unmap_user(struct bio *);
-int blk_rq_map_kern(struct request_queue *, struct request *, void *,
-		unsigned int, gfp_t);
+int blk_rq_map_kern(struct request *rq, void *kbuf, unsigned int len,
+		gfp_t gfp);
 int blk_rq_append_bio(struct request *rq, struct bio *bio);
 void blk_execute_rq_nowait(struct request *rq, bool at_head);
 blk_status_t blk_execute_rq(struct request *rq, bool at_head);
@@ -1142,79 +1213,32 @@ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq)
 	return max_t(unsigned short, rq->nr_phys_segments, 1);
 }
 
-int __blk_rq_map_sg(struct request_queue *q, struct request *rq,
-		struct scatterlist *sglist, struct scatterlist **last_sg);
-static inline int blk_rq_map_sg(struct request_queue *q, struct request *rq,
-		struct scatterlist *sglist)
-{
-	struct scatterlist *last_sg = NULL;
-
-	return __blk_rq_map_sg(q, rq, sglist, &last_sg);
-}
-void blk_dump_rq_flags(struct request *, char *);
-
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int blk_rq_zone_no(struct request *rq)
-{
-	return disk_zone_no(rq->q->disk, blk_rq_pos(rq));
-}
-
-static inline unsigned int blk_rq_zone_is_seq(struct request *rq)
+/**
+ * blk_rq_nr_bvec - return number of bvecs in a request
+ * @rq: request to calculate bvecs for
+ *
+ * Returns the number of bvecs.
+ */
+static inline unsigned int blk_rq_nr_bvec(struct request *rq)
 {
-	return disk_zone_is_seq(rq->q->disk, blk_rq_pos(rq));
-}
+	struct req_iterator rq_iter;
+	struct bio_vec bv;
+	unsigned int nr_bvec = 0;
 
-bool blk_req_needs_zone_write_lock(struct request *rq);
-bool blk_req_zone_write_trylock(struct request *rq);
-void __blk_req_zone_write_lock(struct request *rq);
-void __blk_req_zone_write_unlock(struct request *rq);
+	rq_for_each_bvec(bv, rq, rq_iter)
+		nr_bvec++;
 
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-	if (blk_req_needs_zone_write_lock(rq))
-		__blk_req_zone_write_lock(rq);
+	return nr_bvec;
 }
 
-static inline void blk_req_zone_write_unlock(struct request *rq)
+int __blk_rq_map_sg(struct request *rq, struct scatterlist *sglist,
+		struct scatterlist **last_sg);
+static inline int blk_rq_map_sg(struct request *rq, struct scatterlist *sglist)
 {
-	if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED)
-		__blk_req_zone_write_unlock(rq);
-}
-
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
-	return rq->q->disk->seq_zones_wlock &&
-		test_bit(blk_rq_zone_no(rq), rq->q->disk->seq_zones_wlock);
-}
-
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
-	if (!blk_req_needs_zone_write_lock(rq))
-		return true;
-	return !blk_req_zone_is_write_locked(rq);
-}
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline bool blk_req_needs_zone_write_lock(struct request *rq)
-{
-	return false;
-}
-
-static inline void blk_req_zone_write_lock(struct request *rq)
-{
-}
-
-static inline void blk_req_zone_write_unlock(struct request *rq)
-{
-}
-static inline bool blk_req_zone_is_write_locked(struct request *rq)
-{
-	return false;
-}
+	struct scatterlist *last_sg = NULL;
 
-static inline bool blk_req_can_dispatch_to_zone(struct request *rq)
-{
-	return true;
+	return __blk_rq_map_sg(rq, sglist, &last_sg);
 }
-#endif /* CONFIG_BLK_DEV_ZONED */
+void blk_dump_rq_flags(struct request *, char *);
 
 #endif /* BLK_MQ_H */
diff --git a/include/linux/blk-pm.h b/include/linux/blk-pm.h
index 2580e05a8ab6..004b38a538ff 100644
--- a/include/linux/blk-pm.h
+++ b/include/linux/blk-pm.h
@@ -15,7 +15,6 @@ extern int blk_pre_runtime_suspend(struct request_queue *q);
 extern void blk_post_runtime_suspend(struct request_queue *q, int err);
 extern void blk_pre_runtime_resume(struct request_queue *q);
 extern void blk_post_runtime_resume(struct request_queue *q);
-extern void blk_set_runtime_active(struct request_queue *q);
 #else
 static inline void blk_pm_runtime_init(struct request_queue *q,
 				       struct device *dev) {}
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 740afe80f297..5dc061d318a4 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -10,6 +10,7 @@
 #include <linux/bvec.h>
 #include <linux/device.h>
 #include <linux/ktime.h>
+#include <linux/rw_hint.h>
 
 struct bio_set;
 struct bio;
@@ -44,29 +45,34 @@ struct block_device {
 	struct request_queue *	bd_queue;
 	struct disk_stats __percpu *bd_stats;
 	unsigned long		bd_stamp;
-	bool			bd_read_only;	/* read-only policy */
-	u8			bd_partno;
-	bool			bd_write_holder;
-	bool			bd_has_submit_bio;
+	atomic_t		__bd_flags;	// partition number + flags
+#define BD_PARTNO		255	// lower 8 bits; assign-once
+#define BD_READ_ONLY		(1u<<8) // read-only policy
+#define BD_WRITE_HOLDER		(1u<<9)
+#define BD_HAS_SUBMIT_BIO	(1u<<10)
+#define BD_RO_WARNED		(1u<<11)
+#ifdef CONFIG_FAIL_MAKE_REQUEST
+#define BD_MAKE_IT_FAIL		(1u<<12)
+#endif
 	dev_t			bd_dev;
+	struct address_space	*bd_mapping;	/* page cache */
+
 	atomic_t		bd_openers;
 	spinlock_t		bd_size_lock; /* for bd_inode->i_size updates */
-	struct inode *		bd_inode;	/* will die */
-	struct super_block *	bd_super;
 	void *			bd_claiming;
 	void *			bd_holder;
-	/* The counter of freeze processes */
-	int			bd_fsfreeze_count;
+	const struct blk_holder_ops *bd_holder_ops;
+	struct mutex		bd_holder_lock;
 	int			bd_holders;
 	struct kobject		*bd_holder_dir;
 
-	/* Mutex for freeze */
-	struct mutex		bd_fsfreeze_mutex;
-	struct super_block	*bd_fsfreeze_sb;
+	atomic_t		bd_fsfreeze_count; /* number of freeze requests */
+	struct mutex		bd_fsfreeze_mutex; /* serialize freeze/thaw */
 
 	struct partition_meta_info *bd_meta_info;
-#ifdef CONFIG_FAIL_MAKE_REQUEST
-	bool			bd_make_it_fail;
+	int			bd_writers;
+#ifdef CONFIG_SECURITY
+	void			*bd_security;
 #endif
 	/*
 	 * keep this out-of-line as it's both big and not needed in the fast
@@ -86,22 +92,16 @@ struct block_device {
 
 /*
  * Block error status values.  See block/blk-core:blk_errors for the details.
- * Alpha cannot write a byte atomically, so we need to use 32-bit value.
  */
-#if defined(CONFIG_ALPHA) && !defined(__alpha_bwx__)
-typedef u32 __bitwise blk_status_t;
-typedef u32 blk_short_t;
-#else
 typedef u8 __bitwise blk_status_t;
 typedef u16 blk_short_t;
-#endif
 #define	BLK_STS_OK 0
 #define BLK_STS_NOTSUPP		((__force blk_status_t)1)
 #define BLK_STS_TIMEOUT		((__force blk_status_t)2)
 #define BLK_STS_NOSPC		((__force blk_status_t)3)
 #define BLK_STS_TRANSPORT	((__force blk_status_t)4)
 #define BLK_STS_TARGET		((__force blk_status_t)5)
-#define BLK_STS_NEXUS		((__force blk_status_t)6)
+#define BLK_STS_RESV_CONFLICT	((__force blk_status_t)6)
 #define BLK_STS_MEDIUM		((__force blk_status_t)7)
 #define BLK_STS_PROTECTION	((__force blk_status_t)8)
 #define BLK_STS_RESOURCE	((__force blk_status_t)9)
@@ -135,25 +135,13 @@ typedef u16 blk_short_t;
 #define BLK_STS_DEV_RESOURCE	((__force blk_status_t)13)
 
 /*
- * BLK_STS_ZONE_RESOURCE is returned from the driver to the block layer if zone
- * related resources are unavailable, but the driver can guarantee the queue
- * will be rerun in the future once the resources become available again.
- *
- * This is different from BLK_STS_DEV_RESOURCE in that it explicitly references
- * a zone specific resource and IO to a different zone on the same device could
- * still be served. Examples of that are zones that are write-locked, but a read
- * to the same zone could be served.
- */
-#define BLK_STS_ZONE_RESOURCE	((__force blk_status_t)14)
-
-/*
  * BLK_STS_ZONE_OPEN_RESOURCE is returned from the driver in the completion
  * path if the device returns a status indicating that too many zone resources
  * are currently open. The same command should be successful if resubmitted
  * after the number of open zones decreases below the device's limits, which is
  * reported in the request_queue's max_open_zones.
  */
-#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)15)
+#define BLK_STS_ZONE_OPEN_RESOURCE	((__force blk_status_t)14)
 
 /*
  * BLK_STS_ZONE_ACTIVE_RESOURCE is returned from the driver in the completion
@@ -162,14 +150,25 @@ typedef u16 blk_short_t;
  * after the number of active zones decreases below the device's limits, which
  * is reported in the request_queue's max_active_zones.
  */
-#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)16)
+#define BLK_STS_ZONE_ACTIVE_RESOURCE	((__force blk_status_t)15)
 
 /*
  * BLK_STS_OFFLINE is returned from the driver when the target device is offline
  * or is being taken offline. This could help differentiate the case where a
  * device is intentionally being shut down from a real I/O error.
  */
-#define BLK_STS_OFFLINE		((__force blk_status_t)17)
+#define BLK_STS_OFFLINE		((__force blk_status_t)16)
+
+/*
+ * BLK_STS_DURATION_LIMIT is returned from the driver when the target device
+ * aborted the command because it exceeded one of its Command Duration Limits.
+ */
+#define BLK_STS_DURATION_LIMIT	((__force blk_status_t)17)
+
+/*
+ * Invalid size or alignment.
+ */
+#define BLK_STS_INVAL	((__force blk_status_t)19)
 
 /**
  * blk_path_error - returns true if error may be path related
@@ -189,7 +188,7 @@ static inline bool blk_path_error(blk_status_t error)
 	case BLK_STS_NOTSUPP:
 	case BLK_STS_NOSPC:
 	case BLK_STS_TARGET:
-	case BLK_STS_NEXUS:
+	case BLK_STS_RESV_CONFLICT:
 	case BLK_STS_MEDIUM:
 	case BLK_STS_PROTECTION:
 		return false;
@@ -199,52 +198,6 @@ static inline bool blk_path_error(blk_status_t error)
 	return true;
 }
 
-/*
- * From most significant bit:
- * 1 bit: reserved for other usage, see below
- * 12 bits: original size of bio
- * 51 bits: issue time of bio
- */
-#define BIO_ISSUE_RES_BITS      1
-#define BIO_ISSUE_SIZE_BITS     12
-#define BIO_ISSUE_RES_SHIFT     (64 - BIO_ISSUE_RES_BITS)
-#define BIO_ISSUE_SIZE_SHIFT    (BIO_ISSUE_RES_SHIFT - BIO_ISSUE_SIZE_BITS)
-#define BIO_ISSUE_TIME_MASK     ((1ULL << BIO_ISSUE_SIZE_SHIFT) - 1)
-#define BIO_ISSUE_SIZE_MASK     \
-	(((1ULL << BIO_ISSUE_SIZE_BITS) - 1) << BIO_ISSUE_SIZE_SHIFT)
-#define BIO_ISSUE_RES_MASK      (~((1ULL << BIO_ISSUE_RES_SHIFT) - 1))
-
-/* Reserved bit for blk-throtl */
-#define BIO_ISSUE_THROTL_SKIP_LATENCY (1ULL << 63)
-
-struct bio_issue {
-	u64 value;
-};
-
-static inline u64 __bio_issue_time(u64 time)
-{
-	return time & BIO_ISSUE_TIME_MASK;
-}
-
-static inline u64 bio_issue_time(struct bio_issue *issue)
-{
-	return __bio_issue_time(issue->value);
-}
-
-static inline sector_t bio_issue_size(struct bio_issue *issue)
-{
-	return ((issue->value & BIO_ISSUE_SIZE_MASK) >> BIO_ISSUE_SIZE_SHIFT);
-}
-
-static inline void bio_issue_init(struct bio_issue *issue,
-				       sector_t size)
-{
-	size &= (1ULL << BIO_ISSUE_SIZE_BITS) - 1;
-	issue->value = ((issue->value & BIO_ISSUE_RES_MASK) |
-			(ktime_get_ns() & BIO_ISSUE_TIME_MASK) |
-			((u64)size << BIO_ISSUE_SIZE_SHIFT));
-}
-
 typedef __u32 __bitwise blk_opf_t;
 
 typedef unsigned int blk_qc_t;
@@ -262,12 +215,31 @@ struct bio {
 						 */
 	unsigned short		bi_flags;	/* BIO_* below */
 	unsigned short		bi_ioprio;
+	enum rw_hint		bi_write_hint;
+	u8			bi_write_stream;
 	blk_status_t		bi_status;
+
+	/*
+	 * The bvec gap bit indicates the lowest set bit in any address offset
+	 * between all bi_io_vecs. This field is initialized only after the bio
+	 * is split to the hardware limits (see bio_split_io_at()). The value
+	 * may be used to consider DMA optimization when performing that
+	 * mapping. The value is compared to a power of two mask where the
+	 * result depends on any bit set within the mask, so saving the lowest
+	 * bit is sufficient to know if any segment gap collides with the mask.
+	 */
+	u8			bi_bvec_gap_bit;
+
 	atomic_t		__bi_remaining;
 
 	struct bvec_iter	bi_iter;
 
-	blk_qc_t		bi_cookie;
+	union {
+		/* for polled bios: */
+		blk_qc_t		bi_cookie;
+		/* for plugged zoned writes only: */
+		unsigned int		__bi_nr_segments;
+	};
 	bio_end_io_t		*bi_end_io;
 	void			*bi_private;
 #ifdef CONFIG_BLK_CGROUP
@@ -278,7 +250,8 @@ struct bio {
 	 * on release of the bio.
 	 */
 	struct blkcg_gq		*bi_blkg;
-	struct bio_issue	bi_issue;
+	/* Time that this bio was issued. */
+	u64			issue_time_ns;
 #ifdef CONFIG_BLK_CGROUP_IOCOST
 	u64			bi_iocost_cost;
 #endif
@@ -288,11 +261,9 @@ struct bio {
 	struct bio_crypt_ctx	*bi_crypt_context;
 #endif
 
-	union {
 #if defined(CONFIG_BLK_DEV_INTEGRITY)
-		struct bio_integrity_payload *bi_integrity; /* data integrity */
+	struct bio_integrity_payload *bi_integrity; /* data integrity */
 #endif
-	};
 
 	unsigned short		bi_vcnt;	/* how many bio_vec's */
 
@@ -307,25 +278,22 @@ struct bio {
 	struct bio_vec		*bi_io_vec;	/* the actual vec list */
 
 	struct bio_set		*bi_pool;
-
-	/*
-	 * We can inline a number of vecs at the end of the bio, to avoid
-	 * double allocations for a small number of bio_vecs. This member
-	 * MUST obviously be kept at the very end of the bio.
-	 */
-	struct bio_vec		bi_inline_vecs[];
 };
 
 #define BIO_RESET_BYTES		offsetof(struct bio, bi_max_vecs)
 #define BIO_MAX_SECTORS		(UINT_MAX >> SECTOR_SHIFT)
 
+static inline struct bio_vec *bio_inline_vecs(struct bio *bio)
+{
+	return (struct bio_vec *)(bio + 1);
+}
+
 /*
  * bio flags
  */
 enum {
-	BIO_NO_PAGE_REF,	/* don't put release vec pages */
+	BIO_PAGE_PINNED,	/* Unpin pages in bio_release_pages() */
 	BIO_CLONED,		/* doesn't own data */
-	BIO_BOUNCED,		/* bio is a bounce bio */
 	BIO_QUIET,		/* Make BIO Quiet */
 	BIO_CHAIN,		/* chained bio, ->bi_remaining in effect */
 	BIO_REFFED,		/* bio has elevated ->bi_cnt */
@@ -335,9 +303,18 @@ enum {
 				 * of this bio. */
 	BIO_CGROUP_ACCT,	/* has been accounted to a cgroup */
 	BIO_QOS_THROTTLED,	/* bio went through rq_qos throttle path */
+	/*
+	 * This bio has completed bps throttling at the single tg granularity,
+	 * which is different from BIO_BPS_THROTTLED. When the bio is enqueued
+	 * into the sq->queued of the upper tg, or is about to be dispatched,
+	 * this flag needs to be cleared. Since blk-throttle and rq_qos are not
+	 * on the same hierarchical level, reuse the value.
+	 */
+	BIO_TG_BPS_THROTTLED = BIO_QOS_THROTTLED,
 	BIO_QOS_MERGED,		/* but went through rq_qos merge path */
 	BIO_REMAPPED,
-	BIO_ZONE_WRITE_LOCKED,	/* Owns a zoned device zone write lock */
+	BIO_ZONE_WRITE_PLUGGING, /* bio handled through zone write plugging */
+	BIO_EMULATES_ZONE_APPEND, /* bio emulates a zone append operation */
 	BIO_FLAG_LAST
 };
 
@@ -371,20 +348,20 @@ enum req_op {
 	REQ_OP_DISCARD		= (__force blk_opf_t)3,
 	/* securely erase sectors */
 	REQ_OP_SECURE_ERASE	= (__force blk_opf_t)5,
+	/* write data at the current zone write pointer */
+	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)7,
 	/* write the zero filled sector many times */
 	REQ_OP_WRITE_ZEROES	= (__force blk_opf_t)9,
 	/* Open a zone */
-	REQ_OP_ZONE_OPEN	= (__force blk_opf_t)10,
+	REQ_OP_ZONE_OPEN	= (__force blk_opf_t)11,
 	/* Close a zone */
-	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)11,
+	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)13,
 	/* Transition a zone to full */
-	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)12,
-	/* write data at the current zone write pointer */
-	REQ_OP_ZONE_APPEND	= (__force blk_opf_t)13,
+	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)15,
 	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= (__force blk_opf_t)15,
+	REQ_OP_ZONE_RESET	= (__force blk_opf_t)17,
 	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
+	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)19,
 
 	/* Driver private requests */
 	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
@@ -393,6 +370,7 @@ enum req_op {
 	REQ_OP_LAST		= (__force blk_opf_t)36,
 };
 
+/* Keep cmd_flag_name[] in sync with the definitions below */
 enum req_flag_bits {
 	__REQ_FAILFAST_DEV =	/* no driver retries of device errors */
 		REQ_OP_BITS,
@@ -414,7 +392,7 @@ enum req_flag_bits {
 	__REQ_SWAP,		/* swap I/O */
 	__REQ_DRV,		/* for driver use */
 	__REQ_FS_PRIVATE,	/* for file system (submitter) use */
-
+	__REQ_ATOMIC,		/* for atomic write operations */
 	/*
 	 * Command specific flags, keep last:
 	 */
@@ -446,6 +424,7 @@ enum req_flag_bits {
 #define REQ_SWAP	(__force blk_opf_t)(1ULL << __REQ_SWAP)
 #define REQ_DRV		(__force blk_opf_t)(1ULL << __REQ_DRV)
 #define REQ_FS_PRIVATE	(__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE)
+#define REQ_ATOMIC	(__force blk_opf_t)(1ULL << __REQ_ATOMIC)
 
 #define REQ_NOUNMAP	(__force blk_opf_t)(1ULL << __REQ_NOUNMAP)
 
@@ -500,15 +479,13 @@ static inline bool op_is_discard(blk_opf_t op)
 }
 
 /*
- * Check if a bio or request operation is a zone management operation, with
- * the exception of REQ_OP_ZONE_RESET_ALL which is treated as a special case
- * due to its different handling in the block layer and device response in
- * case of command failure.
+ * Check if a bio or request operation is a zone management operation.
  */
 static inline bool op_is_zone_mgmt(enum req_op op)
 {
 	switch (op & REQ_OP_MASK) {
 	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
 	case REQ_OP_ZONE_OPEN:
 	case REQ_OP_ZONE_CLOSE:
 	case REQ_OP_ZONE_FINISH:
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index c0ffe203a602..72e34acd439c 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -24,6 +24,8 @@
 #include <linux/sbitmap.h>
 #include <linux/uuid.h>
 #include <linux/xarray.h>
+#include <linux/file.h>
+#include <linux/lockdep.h>
 
 struct module;
 struct request_queue;
@@ -36,13 +38,14 @@ struct blk_flush_queue;
 struct kiocb;
 struct pr_ops;
 struct rq_qos;
+struct blk_report_zones_args;
 struct blk_queue_stats;
 struct blk_stat_callback;
 struct blk_crypto_profile;
 
 extern const struct device_type disk_type;
-extern struct device_type part_type;
-extern struct class block_class;
+extern const struct device_type part_type;
+extern const struct class block_class;
 
 /*
  * Maximum number of blkcg policies allowed to be registered concurrently.
@@ -104,14 +107,40 @@ enum {
 struct disk_events;
 struct badblocks;
 
+enum blk_integrity_checksum {
+	BLK_INTEGRITY_CSUM_NONE		= 0,
+	BLK_INTEGRITY_CSUM_IP		= 1,
+	BLK_INTEGRITY_CSUM_CRC		= 2,
+	BLK_INTEGRITY_CSUM_CRC64	= 3,
+} __packed ;
+
 struct blk_integrity {
-	const struct blk_integrity_profile	*profile;
 	unsigned char				flags;
-	unsigned char				tuple_size;
+	enum blk_integrity_checksum		csum_type;
+	unsigned char				metadata_size;
+	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
+	unsigned char				pi_tuple_size;
 };
 
+typedef unsigned int __bitwise blk_mode_t;
+
+/* open for reading */
+#define BLK_OPEN_READ		((__force blk_mode_t)(1 << 0))
+/* open for writing */
+#define BLK_OPEN_WRITE		((__force blk_mode_t)(1 << 1))
+/* open exclusively (vs other exclusive openers */
+#define BLK_OPEN_EXCL		((__force blk_mode_t)(1 << 2))
+/* opened with O_NDELAY */
+#define BLK_OPEN_NDELAY		((__force blk_mode_t)(1 << 3))
+/* open for "writes" only for ioctls (specialy hack for floppy.c) */
+#define BLK_OPEN_WRITE_IOCTL	((__force blk_mode_t)(1 << 4))
+/* open is exclusive wrt all other BLK_OPEN_WRITE opens to the device */
+#define BLK_OPEN_RESTRICT_WRITES	((__force blk_mode_t)(1 << 5))
+/* return partition scanning errors */
+#define BLK_OPEN_STRICT_SCAN	((__force blk_mode_t)(1 << 6))
+
 struct gendisk {
 	/*
 	 * major/first_minor/minors should not be set by any new driver, the
@@ -144,6 +173,7 @@ struct gendisk {
 #define GD_ADDED			4
 #define GD_SUPPRESS_PART_SCAN		5
 #define GD_OWNS_QUEUE			6
+#define GD_ZONE_APPEND_USED		7
 
 	struct mutex open_mutex;	/* open/close mutex */
 	unsigned open_partitions;	/* number of open partitions */
@@ -155,29 +185,25 @@ struct gendisk {
 	struct list_head slave_bdevs;
 #endif
 	struct timer_rand_state *random;
-	atomic_t sync_io;		/* RAID */
 	struct disk_events *ev;
 
 #ifdef CONFIG_BLK_DEV_ZONED
 	/*
-	 * Zoned block device information for request dispatch control.
-	 * nr_zones is the total number of zones of the device. This is always
-	 * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones
-	 * bits which indicates if a zone is conventional (bit set) or
-	 * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones
-	 * bits which indicates if a zone is write locked, that is, if a write
-	 * request targeting the zone was dispatched.
-	 *
-	 * Reads of this information must be protected with blk_queue_enter() /
-	 * blk_queue_exit(). Modifying this information is only allowed while
-	 * no requests are being processed. See also blk_mq_freeze_queue() and
-	 * blk_mq_unfreeze_queue().
+	 * Zoned block device information. Reads of this information must be
+	 * protected with blk_queue_enter() / blk_queue_exit(). Modifying this
+	 * information is only allowed while no requests are being processed.
+	 * See also blk_mq_freeze_queue() and blk_mq_unfreeze_queue().
 	 */
 	unsigned int		nr_zones;
-	unsigned int		max_open_zones;
-	unsigned int		max_active_zones;
-	unsigned long		*conv_zones_bitmap;
-	unsigned long		*seq_zones_wlock;
+	unsigned int		zone_capacity;
+	unsigned int		last_zone_capacity;
+	u8 __rcu		*zones_cond;
+	unsigned int		zone_wplugs_hash_bits;
+	atomic_t		nr_zone_wplugs;
+	spinlock_t		zone_wplugs_lock;
+	struct mempool		*zone_wplugs_pool;
+	struct hlist_head	*zone_wplugs_hash;
+	struct workqueue_struct *zone_wplugs_wq;
 #endif /* CONFIG_BLK_DEV_ZONED */
 
 #if IS_ENABLED(CONFIG_CDROM)
@@ -187,18 +213,16 @@ struct gendisk {
 	struct badblocks *bb;
 	struct lockdep_map lockdep_map;
 	u64 diskseq;
+	blk_mode_t open_mode;
 
 	/*
 	 * Independent sector access ranges. This is always NULL for
 	 * devices that do not have multiple independent access ranges.
 	 */
 	struct blk_independent_access_ranges *ia_ranges;
-};
 
-static inline bool disk_live(struct gendisk *disk)
-{
-	return !inode_unhashed(disk->part0->bd_inode);
-}
+	struct mutex rqos_state_mutex;	/* rqos state change mutex */
+};
 
 /**
  * disk_openers - returns how many openers are there for a disk
@@ -215,6 +239,19 @@ static inline unsigned int disk_openers(struct gendisk *disk)
 	return atomic_read(&disk->part0->bd_openers);
 }
 
+/**
+ * disk_has_partscan - return %true if partition scanning is enabled on a disk
+ * @disk: disk to check
+ *
+ * Returns %true if partitions scanning is enabled for @disk, or %false if
+ * partition scanning is disabled either permanently or temporarily.
+ */
+static inline bool disk_has_partscan(struct gendisk *disk)
+{
+	return !(disk->flags & (GENHD_FL_NO_PART | GENHD_FL_HIDDEN)) &&
+		!test_bit(GD_SUPPRESS_PART_SCAN, &disk->state);
+}
+
 /*
  * The gendisk is refcounted by the part0 block_device, and the bd_device
  * therein is also used for device model presentation in sysfs.
@@ -235,9 +272,21 @@ static inline dev_t disk_devt(struct gendisk *disk)
 	return MKDEV(disk->major, disk->first_minor);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER)
+ * however we constrain this to what we can validate and test.
+ */
+#define BLK_MAX_BLOCK_SIZE      SZ_64K
+#else
+#define BLK_MAX_BLOCK_SIZE      PAGE_SIZE
+#endif
+
+
+/* blk_validate_limits() validates bsize, so drivers don't usually need to */
 static inline int blk_validate_block_size(unsigned long bsize)
 {
-	if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize))
+	if (bsize < 512 || bsize > BLK_MAX_BLOCK_SIZE || !is_power_of_2(bsize))
 		return -EINVAL;
 
 	return 0;
@@ -249,29 +298,79 @@ static inline bool blk_op_is_passthrough(blk_opf_t op)
 	return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT;
 }
 
-/*
- * Zoned block device models (zoned limit).
- *
- * Note: This needs to be ordered from the least to the most severe
- * restrictions for the inheritance in blk_stack_limits() to work.
- */
-enum blk_zoned_model {
-	BLK_ZONED_NONE = 0,	/* Regular block device */
-	BLK_ZONED_HA,		/* Host-aware zoned block device */
-	BLK_ZONED_HM,		/* Host-managed zoned block device */
-};
+/* flags set by the driver in queue_limits.features */
+typedef unsigned int __bitwise blk_features_t;
+
+/* supports a volatile write cache */
+#define BLK_FEAT_WRITE_CACHE		((__force blk_features_t)(1u << 0))
+
+/* supports passing on the FUA bit */
+#define BLK_FEAT_FUA			((__force blk_features_t)(1u << 1))
+
+/* rotational device (hard drive or floppy) */
+#define BLK_FEAT_ROTATIONAL		((__force blk_features_t)(1u << 2))
+
+/* contributes to the random number pool */
+#define BLK_FEAT_ADD_RANDOM		((__force blk_features_t)(1u << 3))
+
+/* do disk/partitions IO accounting */
+#define BLK_FEAT_IO_STAT		((__force blk_features_t)(1u << 4))
+
+/* don't modify data until writeback is done */
+#define BLK_FEAT_STABLE_WRITES		((__force blk_features_t)(1u << 5))
+
+/* always completes in submit context */
+#define BLK_FEAT_SYNCHRONOUS		((__force blk_features_t)(1u << 6))
+
+/* supports REQ_NOWAIT */
+#define BLK_FEAT_NOWAIT			((__force blk_features_t)(1u << 7))
+
+/* supports DAX */
+#define BLK_FEAT_DAX			((__force blk_features_t)(1u << 8))
+
+/* supports I/O polling */
+#define BLK_FEAT_POLL			((__force blk_features_t)(1u << 9))
+
+/* is a zoned device */
+#define BLK_FEAT_ZONED			((__force blk_features_t)(1u << 10))
+
+/* supports PCI(e) p2p requests */
+#define BLK_FEAT_PCI_P2PDMA		((__force blk_features_t)(1u << 12))
+
+/* skip this queue in blk_mq_(un)quiesce_tagset */
+#define BLK_FEAT_SKIP_TAGSET_QUIESCE	((__force blk_features_t)(1u << 13))
+
+/* undocumented magic for bcache */
+#define BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE \
+	((__force blk_features_t)(1u << 15))
+
+/* atomic writes enabled */
+#define BLK_FEAT_ATOMIC_WRITES \
+	((__force blk_features_t)(1u << 16))
 
 /*
- * BLK_BOUNCE_NONE:	never bounce (default)
- * BLK_BOUNCE_HIGH:	bounce all highmem pages
+ * Flags automatically inherited when stacking limits.
  */
-enum blk_bounce {
-	BLK_BOUNCE_NONE,
-	BLK_BOUNCE_HIGH,
-};
+#define BLK_FEAT_INHERIT_MASK \
+	(BLK_FEAT_WRITE_CACHE | BLK_FEAT_FUA | BLK_FEAT_ROTATIONAL | \
+	 BLK_FEAT_STABLE_WRITES | BLK_FEAT_ZONED | \
+	 BLK_FEAT_RAID_PARTIAL_STRIPES_EXPENSIVE)
+
+/* internal flags in queue_limits.flags */
+typedef unsigned int __bitwise blk_flags_t;
+
+/* do not send FLUSH/FUA commands despite advertising a write cache */
+#define BLK_FLAG_WRITE_CACHE_DISABLED	((__force blk_flags_t)(1u << 0))
+
+/* I/O topology is misaligned */
+#define BLK_FLAG_MISALIGNED		((__force blk_flags_t)(1u << 1))
+
+/* passthrough command IO accounting */
+#define BLK_FLAG_IOSTATS_PASSTHROUGH	((__force blk_flags_t)(1u << 2))
 
 struct queue_limits {
-	enum blk_bounce		bounce;
+	blk_features_t		features;
+	blk_flags_t		flags;
 	unsigned long		seg_boundary_mask;
 	unsigned long		virt_boundary_mask;
 
@@ -281,6 +380,7 @@ struct queue_limits {
 	unsigned int		max_sectors;
 	unsigned int		max_user_sectors;
 	unsigned int		max_segment_size;
+	unsigned int		max_fast_segment_size;
 	unsigned int		physical_block_size;
 	unsigned int		logical_block_size;
 	unsigned int		alignment_offset;
@@ -288,21 +388,37 @@ struct queue_limits {
 	unsigned int		io_opt;
 	unsigned int		max_discard_sectors;
 	unsigned int		max_hw_discard_sectors;
+	unsigned int		max_user_discard_sectors;
 	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
+	unsigned int		max_wzeroes_unmap_sectors;
+	unsigned int		max_hw_wzeroes_unmap_sectors;
+	unsigned int		max_user_wzeroes_unmap_sectors;
+	unsigned int		max_hw_zone_append_sectors;
 	unsigned int		max_zone_append_sectors;
 	unsigned int		discard_granularity;
 	unsigned int		discard_alignment;
 	unsigned int		zone_write_granularity;
 
+	/* atomic write limits */
+	unsigned int		atomic_write_hw_max;
+	unsigned int		atomic_write_max_sectors;
+	unsigned int		atomic_write_hw_boundary;
+	unsigned int		atomic_write_boundary_sectors;
+	unsigned int		atomic_write_hw_unit_min;
+	unsigned int		atomic_write_unit_min;
+	unsigned int		atomic_write_hw_unit_max;
+	unsigned int		atomic_write_unit_max;
+
 	unsigned short		max_segments;
 	unsigned short		max_integrity_segments;
 	unsigned short		max_discard_segments;
 
-	unsigned char		misaligned;
-	unsigned char		discard_misaligned;
-	unsigned char		raid_partial_stripes_expensive;
-	enum blk_zoned_model	zoned;
+	unsigned short		max_write_streams;
+	unsigned int		write_stream_granularity;
+
+	unsigned int		max_open_zones;
+	unsigned int		max_active_zones;
 
 	/*
 	 * Drivers that set dma_alignment to less than 511 must be prepared to
@@ -310,52 +426,28 @@ struct queue_limits {
 	 * due to possible offsets.
 	 */
 	unsigned int		dma_alignment;
+	unsigned int		dma_pad_mask;
+
+	struct blk_integrity	integrity;
 };
 
 typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx,
 			       void *data);
 
-void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model);
+int disk_report_zone(struct gendisk *disk, struct blk_zone *zone,
+		     unsigned int idx, struct blk_report_zones_args *args);
 
-#ifdef CONFIG_BLK_DEV_ZONED
+int blkdev_get_zone_info(struct block_device *bdev, sector_t sector,
+			 struct blk_zone *zone);
 
 #define BLK_ALL_ZONES  ((unsigned int)-1)
 int blkdev_report_zones(struct block_device *bdev, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data);
-unsigned int bdev_nr_zones(struct block_device *bdev);
-extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
-			    sector_t sectors, sector_t nr_sectors,
-			    gfp_t gfp_mask);
-int blk_revalidate_disk_zones(struct gendisk *disk,
-			      void (*update_driver_data)(struct gendisk *disk));
-
-extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode,
-				     unsigned int cmd, unsigned long arg);
-extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode,
-				  unsigned int cmd, unsigned long arg);
-
-#else /* CONFIG_BLK_DEV_ZONED */
-
-static inline unsigned int bdev_nr_zones(struct block_device *bdev)
-{
-	return 0;
-}
-
-static inline int blkdev_report_zones_ioctl(struct block_device *bdev,
-					    fmode_t mode, unsigned int cmd,
-					    unsigned long arg)
-{
-	return -ENOTTY;
-}
-
-static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev,
-					 fmode_t mode, unsigned int cmd,
-					 unsigned long arg)
-{
-	return -ENOTTY;
-}
-
-#endif /* CONFIG_BLK_DEV_ZONED */
+		unsigned int nr_zones, report_zones_cb cb, void *data);
+int blkdev_report_zones_cached(struct block_device *bdev, sector_t sector,
+		unsigned int nr_zones, report_zones_cb cb, void *data);
+int blkdev_zone_mgmt(struct block_device *bdev, enum req_op op,
+		sector_t sectors, sector_t nr_sectors);
+int blk_revalidate_disk_zones(struct gendisk *disk);
 
 /*
  * Independent access ranges: struct blk_independent_access_range describes
@@ -385,61 +477,55 @@ struct blk_independent_access_ranges {
 };
 
 struct request_queue {
-	struct request		*last_merge;
-	struct elevator_queue	*elevator;
-
-	struct percpu_ref	q_usage_counter;
+	/*
+	 * The queue owner gets to use this for whatever they like.
+	 * ll_rw_blk doesn't touch it.
+	 */
+	void			*queuedata;
 
-	struct blk_queue_stats	*stats;
-	struct rq_qos		*rq_qos;
+	struct elevator_queue	*elevator;
 
 	const struct blk_mq_ops	*mq_ops;
 
 	/* sw queues */
 	struct blk_mq_ctx __percpu	*queue_ctx;
 
+	/*
+	 * various queue flags, see QUEUE_* below
+	 */
+	unsigned long		queue_flags;
+
+	unsigned int __data_racy rq_timeout;
+
 	unsigned int		queue_depth;
 
+	refcount_t		refs;
+
 	/* hw dispatch queues */
-	struct xarray		hctx_table;
 	unsigned int		nr_hw_queues;
+	struct blk_mq_hw_ctx * __rcu *queue_hw_ctx;
 
-	/*
-	 * The queue owner gets to use this for whatever they like.
-	 * ll_rw_blk doesn't touch it.
-	 */
-	void			*queuedata;
+	struct percpu_ref	q_usage_counter;
+	struct lock_class_key	io_lock_cls_key;
+	struct lockdep_map	io_lockdep_map;
 
-	/*
-	 * various queue flags, see QUEUE_* below
-	 */
-	unsigned long		queue_flags;
-	/*
-	 * Number of contexts that have called blk_set_pm_only(). If this
-	 * counter is above zero then only RQF_PM requests are processed.
-	 */
-	atomic_t		pm_only;
+	struct lock_class_key	q_lock_cls_key;
+	struct lockdep_map	q_lockdep_map;
 
-	/*
-	 * ida allocated id for this queue.  Used to index queues from
-	 * ioctx.
-	 */
-	int			id;
+	struct request		*last_merge;
 
 	spinlock_t		queue_lock;
 
-	struct gendisk		*disk;
+	int			quiesce_depth;
 
-	refcount_t		refs;
+	struct gendisk		*disk;
 
 	/*
 	 * mq queue kobject
 	 */
 	struct kobject *mq_kobj;
 
-#ifdef  CONFIG_BLK_DEV_INTEGRITY
-	struct blk_integrity integrity;
-#endif	/* CONFIG_BLK_DEV_INTEGRITY */
+	struct queue_limits	limits;
 
 #ifdef CONFIG_PM
 	struct device		*dev;
@@ -447,19 +533,31 @@ struct request_queue {
 #endif
 
 	/*
+	 * Number of contexts that have called blk_set_pm_only(). If this
+	 * counter is above zero then only RQF_PM requests are processed.
+	 */
+	atomic_t		pm_only;
+
+	struct blk_queue_stats	*stats;
+	struct rq_qos		*rq_qos;
+	struct mutex		rq_qos_mutex;
+
+	/*
+	 * ida allocated id for this queue.  Used to index queues from
+	 * ioctx.
+	 */
+	int			id;
+
+	/*
 	 * queue settings
 	 */
 	unsigned long		nr_requests;	/* Max # of requests */
 
-	unsigned int		dma_pad_mask;
-
 #ifdef CONFIG_BLK_INLINE_ENCRYPTION
 	struct blk_crypto_profile *crypto_profile;
 	struct kobject *crypto_kobject;
 #endif
 
-	unsigned int		rq_timeout;
-
 	struct timer_list	timeout;
 	struct work_struct	timeout_work;
 
@@ -475,11 +573,12 @@ struct request_queue {
 	struct mutex		blkcg_mutex;
 #endif
 
-	struct queue_limits	limits;
+	int			node;
 
-	unsigned int		required_elevator_features;
+	spinlock_t		requeue_lock;
+	struct list_head	requeue_list;
+	struct delayed_work	requeue_work;
 
-	int			node;
 #ifdef CONFIG_BLK_DEV_IO_TRACE
 	struct blk_trace __rcu	*blk_trace;
 #endif
@@ -487,13 +586,25 @@ struct request_queue {
 	 * for flush operations
 	 */
 	struct blk_flush_queue	*fq;
+	struct list_head	flush_list;
 
-	struct list_head	requeue_list;
-	spinlock_t		requeue_lock;
-	struct delayed_work	requeue_work;
+	/*
+	 * Protects against I/O scheduler switching, particularly when updating
+	 * q->elevator. Since the elevator update code path may also modify q->
+	 * nr_requests and wbt latency, this lock also protects the sysfs attrs
+	 * nr_requests and wbt_lat_usec. Additionally the nr_hw_queues update
+	 * may modify hctx tags, reserved-tags and cpumask, so this lock also
+	 * helps protect the hctx sysfs/debugfs attrs. To ensure proper locking
+	 * order during an elevator or nr_hw_queue update, first freeze the
+	 * queue, then acquire ->elevator_lock.
+	 */
+	struct mutex		elevator_lock;
 
 	struct mutex		sysfs_lock;
-	struct mutex		sysfs_dir_lock;
+	/*
+	 * Protects queue limits and also sysfs attribute read_ahead_kb.
+	 */
+	struct mutex		limits_lock;
 
 	/*
 	 * for reusing dead hctx instance in case of updating
@@ -509,6 +620,16 @@ struct request_queue {
 	struct throtl_data *td;
 #endif
 	struct rcu_head		rcu_head;
+#ifdef CONFIG_LOCKDEP
+	struct task_struct	*mq_freeze_owner;
+	int			mq_freeze_owner_depth;
+	/*
+	 * Records disk & queue state in current context, used in unfreeze
+	 * queue
+	 */
+	bool			mq_freeze_disk_dead;
+	bool			mq_freeze_queue_dying;
+#endif
 	wait_queue_head_t	mq_freeze_wq;
 	/*
 	 * Protect concurrent access to q_usage_counter by
@@ -516,8 +637,6 @@ struct request_queue {
 	 */
 	struct mutex		mq_freeze_lock;
 
-	int			quiesce_depth;
-
 	struct blk_mq_tag_set	*tag_set;
 	struct list_head	tag_set_list;
 
@@ -528,64 +647,46 @@ struct request_queue {
 	 * Serializes all debugfs metadata operations using the above dentries.
 	 */
 	struct mutex		debugfs_mutex;
-
-	bool			mq_sysfs_init_done;
 };
 
 /* Keep blk_queue_flag_name[] in sync with the definitions below */
-#define QUEUE_FLAG_STOPPED	0	/* queue is stopped */
-#define QUEUE_FLAG_DYING	1	/* queue being torn down */
-#define QUEUE_FLAG_NOMERGES     3	/* disable merge attempts */
-#define QUEUE_FLAG_SAME_COMP	4	/* complete on same CPU-group */
-#define QUEUE_FLAG_FAIL_IO	5	/* fake timeout */
-#define QUEUE_FLAG_NONROT	6	/* non-rotational device (SSD) */
-#define QUEUE_FLAG_VIRT		QUEUE_FLAG_NONROT /* paravirt device */
-#define QUEUE_FLAG_IO_STAT	7	/* do disk/partitions IO accounting */
-#define QUEUE_FLAG_NOXMERGES	9	/* No extended merges */
-#define QUEUE_FLAG_ADD_RANDOM	10	/* Contributes to random pool */
-#define QUEUE_FLAG_SYNCHRONOUS	11	/* always completes in submit context */
-#define QUEUE_FLAG_SAME_FORCE	12	/* force complete on same CPU */
-#define QUEUE_FLAG_INIT_DONE	14	/* queue is initialized */
-#define QUEUE_FLAG_STABLE_WRITES 15	/* don't modify blks until WB is done */
-#define QUEUE_FLAG_POLL		16	/* IO polling enabled if set */
-#define QUEUE_FLAG_WC		17	/* Write back caching */
-#define QUEUE_FLAG_FUA		18	/* device supports FUA writes */
-#define QUEUE_FLAG_DAX		19	/* device supports DAX */
-#define QUEUE_FLAG_STATS	20	/* track IO start and completion times */
-#define QUEUE_FLAG_REGISTERED	22	/* queue has been registered to a disk */
-#define QUEUE_FLAG_QUIESCED	24	/* queue has been quiesced */
-#define QUEUE_FLAG_PCI_P2PDMA	25	/* device supports PCI p2p requests */
-#define QUEUE_FLAG_ZONE_RESETALL 26	/* supports Zone Reset All */
-#define QUEUE_FLAG_RQ_ALLOC_TIME 27	/* record rq->alloc_time_ns */
-#define QUEUE_FLAG_HCTX_ACTIVE	28	/* at least one blk-mq hctx is active */
-#define QUEUE_FLAG_NOWAIT       29	/* device supports NOWAIT */
-#define QUEUE_FLAG_SQ_SCHED     30	/* single queue style io dispatch */
-#define QUEUE_FLAG_SKIP_TAGSET_QUIESCE	31 /* quiesce_tagset skip the queue*/
-
-#define QUEUE_FLAG_MQ_DEFAULT	((1UL << QUEUE_FLAG_IO_STAT) |		\
-				 (1UL << QUEUE_FLAG_SAME_COMP) |	\
-				 (1UL << QUEUE_FLAG_NOWAIT))
+enum {
+	QUEUE_FLAG_DYING,		/* queue being torn down */
+	QUEUE_FLAG_NOMERGES,		/* disable merge attempts */
+	QUEUE_FLAG_SAME_COMP,		/* complete on same CPU-group */
+	QUEUE_FLAG_FAIL_IO,		/* fake timeout */
+	QUEUE_FLAG_NOXMERGES,		/* No extended merges */
+	QUEUE_FLAG_SAME_FORCE,		/* force complete on same CPU */
+	QUEUE_FLAG_INIT_DONE,		/* queue is initialized */
+	QUEUE_FLAG_STATS,		/* track IO start and completion times */
+	QUEUE_FLAG_REGISTERED,		/* queue has been registered to a disk */
+	QUEUE_FLAG_QUIESCED,		/* queue has been quiesced */
+	QUEUE_FLAG_RQ_ALLOC_TIME,	/* record rq->alloc_time_ns */
+	QUEUE_FLAG_HCTX_ACTIVE,		/* at least one blk-mq hctx is active */
+	QUEUE_FLAG_SQ_SCHED,		/* single queue style io dispatch */
+	QUEUE_FLAG_DISABLE_WBT_DEF,	/* for sched to disable/enable wbt */
+	QUEUE_FLAG_NO_ELV_SWITCH,	/* can't switch elevator any more */
+	QUEUE_FLAG_QOS_ENABLED,		/* qos is enabled */
+	QUEUE_FLAG_BIO_ISSUE_TIME,	/* record bio->issue_time_ns */
+	QUEUE_FLAG_MAX
+};
+
+#define QUEUE_FLAG_MQ_DEFAULT	(1UL << QUEUE_FLAG_SAME_COMP)
 
 void blk_queue_flag_set(unsigned int flag, struct request_queue *q);
 void blk_queue_flag_clear(unsigned int flag, struct request_queue *q);
-bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 
-#define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_dying(q)	test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags)
 #define blk_queue_init_done(q)	test_bit(QUEUE_FLAG_INIT_DONE, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_noxmerges(q)	\
 	test_bit(QUEUE_FLAG_NOXMERGES, &(q)->queue_flags)
-#define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
-#define blk_queue_stable_writes(q) \
-	test_bit(QUEUE_FLAG_STABLE_WRITES, &(q)->queue_flags)
-#define blk_queue_io_stat(q)	test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags)
-#define blk_queue_add_random(q)	test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags)
-#define blk_queue_zone_resetall(q)	\
-	test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags)
-#define blk_queue_dax(q)	test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags)
-#define blk_queue_pci_p2pdma(q)	\
-	test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags)
+#define blk_queue_nonrot(q)	(!((q)->limits.features & BLK_FEAT_ROTATIONAL))
+#define blk_queue_io_stat(q)	((q)->limits.features & BLK_FEAT_IO_STAT)
+#define blk_queue_passthrough_stat(q)	\
+	((q)->limits.flags & BLK_FLAG_IOSTATS_PASSTHROUGH)
+#define blk_queue_dax(q)	((q)->limits.features & BLK_FEAT_DAX)
+#define blk_queue_pci_p2pdma(q)	((q)->limits.features & BLK_FEAT_PCI_P2PDMA)
 #ifdef CONFIG_BLK_RQ_ALLOC_TIME
 #define blk_queue_rq_alloc_time(q)	\
 	test_bit(QUEUE_FLAG_RQ_ALLOC_TIME, &(q)->queue_flags)
@@ -601,7 +702,11 @@ bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q);
 #define blk_queue_registered(q)	test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags)
 #define blk_queue_sq_sched(q)	test_bit(QUEUE_FLAG_SQ_SCHED, &(q)->queue_flags)
 #define blk_queue_skip_tagset_quiesce(q) \
-	test_bit(QUEUE_FLAG_SKIP_TAGSET_QUIESCE, &(q)->queue_flags)
+	((q)->limits.features & BLK_FEAT_SKIP_TAGSET_QUIESCE)
+#define blk_queue_disable_wbt(q)	\
+	test_bit(QUEUE_FLAG_DISABLE_WBT_DEF, &(q)->queue_flags)
+#define blk_queue_no_elv_switch(q)	\
+	test_bit(QUEUE_FLAG_NO_ELV_SWITCH, &(q)->queue_flags)
 
 extern void blk_set_pm_only(struct request_queue *q);
 extern void blk_clear_pm_only(struct request_queue *q);
@@ -629,29 +734,10 @@ static inline enum rpm_status queue_rpm_status(struct request_queue *q)
 }
 #endif
 
-static inline enum blk_zoned_model
-blk_queue_zoned_model(struct request_queue *q)
-{
-	if (IS_ENABLED(CONFIG_BLK_DEV_ZONED))
-		return q->limits.zoned;
-	return BLK_ZONED_NONE;
-}
-
 static inline bool blk_queue_is_zoned(struct request_queue *q)
 {
-	switch (blk_queue_zoned_model(q)) {
-	case BLK_ZONED_HA:
-	case BLK_ZONED_HM:
-		return true;
-	default:
-		return false;
-	}
-}
-
-#ifdef CONFIG_BLK_DEV_ZONED
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return blk_queue_is_zoned(disk->queue) ? disk->nr_zones : 0;
+	return IS_ENABLED(CONFIG_BLK_DEV_ZONED) &&
+		(q->limits.features & BLK_FEAT_ZONED);
 }
 
 static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
@@ -661,60 +747,15 @@ static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
 	return sector >> ilog2(disk->queue->limits.chunk_sectors);
 }
 
-static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
-{
-	if (!blk_queue_is_zoned(disk->queue))
-		return false;
-	if (!disk->conv_zones_bitmap)
-		return true;
-	return !test_bit(disk_zone_no(disk, sector), disk->conv_zones_bitmap);
-}
-
-static inline void disk_set_max_open_zones(struct gendisk *disk,
-		unsigned int max_open_zones)
-{
-	disk->max_open_zones = max_open_zones;
-}
-
-static inline void disk_set_max_active_zones(struct gendisk *disk,
-		unsigned int max_active_zones)
-{
-	disk->max_active_zones = max_active_zones;
-}
-
-static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
-{
-	return bdev->bd_disk->max_open_zones;
-}
-
-static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
-{
-	return bdev->bd_disk->max_active_zones;
-}
-
-#else /* CONFIG_BLK_DEV_ZONED */
-static inline unsigned int disk_nr_zones(struct gendisk *disk)
-{
-	return 0;
-}
-static inline bool disk_zone_is_seq(struct gendisk *disk, sector_t sector)
-{
-	return false;
-}
-static inline unsigned int disk_zone_no(struct gendisk *disk, sector_t sector)
-{
-	return 0;
-}
 static inline unsigned int bdev_max_open_zones(struct block_device *bdev)
 {
-	return 0;
+	return bdev->bd_disk->queue->limits.max_open_zones;
 }
 
 static inline unsigned int bdev_max_active_zones(struct block_device *bdev)
 {
-	return 0;
+	return bdev->bd_disk->queue->limits.max_active_zones;
 }
-#endif /* CONFIG_BLK_DEV_ZONED */
 
 static inline unsigned int blk_queue_depth(struct request_queue *q)
 {
@@ -734,6 +775,9 @@ static inline unsigned int blk_queue_depth(struct request_queue *q)
 #define for_each_bio(_bio)		\
 	for (; _bio; _bio = _bio->bi_next)
 
+int __must_check add_disk_fwnode(struct device *parent, struct gendisk *disk,
+				 const struct attribute_group **groups,
+				 struct fwnode_handle *fwnode);
 int __must_check device_add_disk(struct device *parent, struct gendisk *disk,
 				 const struct attribute_group **groups);
 static inline int __must_check add_disk(struct gendisk *disk)
@@ -745,19 +789,40 @@ void invalidate_disk(struct gendisk *disk);
 void set_disk_ro(struct gendisk *disk, bool read_only);
 void disk_uevent(struct gendisk *disk, enum kobject_action action);
 
-static inline int get_disk_ro(struct gendisk *disk)
+static inline u8 bdev_partno(const struct block_device *bdev)
+{
+	return atomic_read(&bdev->__bd_flags) & BD_PARTNO;
+}
+
+static inline bool bdev_test_flag(const struct block_device *bdev, unsigned flag)
+{
+	return atomic_read(&bdev->__bd_flags) & flag;
+}
+
+static inline void bdev_set_flag(struct block_device *bdev, unsigned flag)
+{
+	atomic_or(flag, &bdev->__bd_flags);
+}
+
+static inline void bdev_clear_flag(struct block_device *bdev, unsigned flag)
+{
+	atomic_andnot(flag, &bdev->__bd_flags);
+}
+
+static inline bool get_disk_ro(struct gendisk *disk)
 {
-	return disk->part0->bd_read_only ||
+	return bdev_test_flag(disk->part0, BD_READ_ONLY) ||
 		test_bit(GD_READ_ONLY, &disk->state);
 }
 
-static inline int bdev_read_only(struct block_device *bdev)
+static inline bool bdev_read_only(struct block_device *bdev)
 {
-	return bdev->bd_read_only || get_disk_ro(bdev->bd_disk);
+	return bdev_test_flag(bdev, BD_READ_ONLY) || get_disk_ro(bdev->bd_disk);
 }
 
 bool set_capacity_and_notify(struct gendisk *disk, sector_t size);
-bool disk_force_media_change(struct gendisk *disk, unsigned int events);
+void disk_force_media_change(struct gendisk *disk);
+void bdev_mark_dead(struct block_device *bdev, bool surprise);
 
 void add_disk_randomness(struct gendisk *disk) __latent_entropy;
 void rand_initialize_disk(struct gendisk *disk);
@@ -788,25 +853,137 @@ static inline u64 sb_bdev_nr_blocks(struct super_block *sb)
 		(sb->s_blocksize_bits - SECTOR_SHIFT);
 }
 
+#ifdef CONFIG_BLK_DEV_ZONED
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return disk->nr_zones;
+}
+
+/**
+ * bio_needs_zone_write_plugging - Check if a BIO needs to be handled with zone
+ *				   write plugging
+ * @bio: The BIO being submitted
+ *
+ * Return true whenever @bio execution needs to be handled through zone
+ * write plugging (using blk_zone_plug_bio()). Return false otherwise.
+ */
+static inline bool bio_needs_zone_write_plugging(struct bio *bio)
+{
+	enum req_op op = bio_op(bio);
+
+	/*
+	 * Only zoned block devices have a zone write plug hash table. But not
+	 * all of them have one (e.g. DM devices may not need one).
+	 */
+	if (!bio->bi_bdev->bd_disk->zone_wplugs_hash)
+		return false;
+
+	/* Only write operations need zone write plugging. */
+	if (!op_is_write(op))
+		return false;
+
+	/* Ignore empty flush */
+	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+		return false;
+
+	/* Ignore BIOs that already have been handled by zone write plugging. */
+	if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
+		return false;
+
+	/*
+	 * All zone write operations must be handled through zone write plugging
+	 * using blk_zone_plug_bio().
+	 */
+	switch (op) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return true;
+	default:
+		return false;
+	}
+}
+
+bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
+
+/**
+ * disk_zone_capacity - returns the zone capacity of zone containing @sector
+ * @disk:	disk to work with
+ * @sector:	sector number within the querying zone
+ *
+ * Returns the zone capacity of a zone containing @sector. @sector can be any
+ * sector in the zone.
+ */
+static inline unsigned int disk_zone_capacity(struct gendisk *disk,
+					      sector_t sector)
+{
+	sector_t zone_sectors = disk->queue->limits.chunk_sectors;
+
+	if (sector + zone_sectors >= get_capacity(disk))
+		return disk->last_zone_capacity;
+	return disk->zone_capacity;
+}
+static inline unsigned int bdev_zone_capacity(struct block_device *bdev,
+					      sector_t pos)
+{
+	return disk_zone_capacity(bdev->bd_disk, pos);
+}
+
+bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector);
+
+#else /* CONFIG_BLK_DEV_ZONED */
+static inline unsigned int disk_nr_zones(struct gendisk *disk)
+{
+	return 0;
+}
+
+static inline bool bdev_zone_is_seq(struct block_device *bdev, sector_t sector)
+{
+	return false;
+}
+
+static inline bool bio_needs_zone_write_plugging(struct bio *bio)
+{
+	return false;
+}
+
+static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
+{
+	return false;
+}
+#endif /* CONFIG_BLK_DEV_ZONED */
+
+static inline unsigned int bdev_nr_zones(struct block_device *bdev)
+{
+	return disk_nr_zones(bdev->bd_disk);
+}
+
 int bdev_disk_changed(struct gendisk *disk, bool invalidate);
 
 void put_disk(struct gendisk *disk);
-struct gendisk *__blk_alloc_disk(int node, struct lock_class_key *lkclass);
+struct gendisk *__blk_alloc_disk(struct queue_limits *lim, int node,
+		struct lock_class_key *lkclass);
 
 /**
  * blk_alloc_disk - allocate a gendisk structure
+ * @lim: queue limits to be used for this disk.
  * @node_id: numa node to allocate on
  *
  * Allocate and pre-initialize a gendisk structure for use with BIO based
  * drivers.
  *
+ * Returns an ERR_PTR on error, else the allocated disk.
+ *
  * Context: can sleep
  */
-#define blk_alloc_disk(node_id)						\
+#define blk_alloc_disk(lim, node_id)					\
 ({									\
 	static struct lock_class_key __key;				\
 									\
-	__blk_alloc_disk(node_id, &__key);				\
+	__blk_alloc_disk(lim, node_id, &__key);				\
 })
 
 int __register_blkdev(unsigned int major, const char *name,
@@ -815,8 +992,7 @@ int __register_blkdev(unsigned int major, const char *name,
 	__register_blkdev(major, name, NULL)
 void unregister_blkdev(unsigned int major, const char *name);
 
-bool bdev_check_media_change(struct block_device *bdev);
-int __invalidate_device(struct block_device *bdev, bool kill_dirty);
+bool disk_check_media_change(struct gendisk *disk);
 void set_capacity(struct gendisk *disk, sector_t size);
 
 #ifdef CONFIG_BLOCK_HOLDER_DEPRECATED
@@ -836,13 +1012,14 @@ static inline void bd_unlink_disk_holder(struct block_device *bdev,
 
 dev_t part_devt(struct gendisk *disk, u8 partno);
 void inc_diskseq(struct gendisk *disk);
-dev_t blk_lookup_devt(const char *name, int partno);
 void blk_request_module(dev_t devt);
 
 extern int blk_register_queue(struct gendisk *disk);
 extern void blk_unregister_queue(struct gendisk *disk);
 void submit_bio_noacct(struct bio *bio);
 struct bio *bio_split_to_limits(struct bio *bio);
+struct bio *bio_submit_split_bioset(struct bio *bio, unsigned int split_sectors,
+				    struct bio_set *bs);
 
 extern int blk_lld_busy(struct request_queue *q);
 extern int blk_queue_enter(struct request_queue *q, blk_mq_req_flags_t flags);
@@ -854,6 +1031,7 @@ extern const char *blk_op_str(enum req_op op);
 
 int blk_status_to_errno(blk_status_t status);
 blk_status_t errno_to_blk_status(int errno);
+const char *blk_status_to_str(blk_status_t status);
 
 /* only poll the hardware once, don't continue until a completion was found */
 #define BLK_POLL_ONESHOT		(1 << 0)
@@ -874,86 +1052,111 @@ static inline unsigned int bio_zone_no(struct bio *bio)
 	return disk_zone_no(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
 }
 
-static inline unsigned int bio_zone_is_seq(struct bio *bio)
+static inline bool bio_straddles_zones(struct bio *bio)
 {
-	return disk_zone_is_seq(bio->bi_bdev->bd_disk, bio->bi_iter.bi_sector);
+	return bio_sectors(bio) &&
+		bio_zone_no(bio) !=
+		disk_zone_no(bio->bi_bdev->bd_disk, bio_end_sector(bio) - 1);
 }
 
 /*
- * Return how much of the chunk is left to be used for I/O at a given offset.
+ * Return how much within the boundary is left to be used for I/O at a given
+ * offset.
  */
-static inline unsigned int blk_chunk_sectors_left(sector_t offset,
-		unsigned int chunk_sectors)
+static inline unsigned int blk_boundary_sectors_left(sector_t offset,
+		unsigned int boundary_sectors)
 {
-	if (unlikely(!is_power_of_2(chunk_sectors)))
-		return chunk_sectors - sector_div(offset, chunk_sectors);
-	return chunk_sectors - (offset & (chunk_sectors - 1));
+	if (unlikely(!is_power_of_2(boundary_sectors)))
+		return boundary_sectors - sector_div(offset, boundary_sectors);
+	return boundary_sectors - (offset & (boundary_sectors - 1));
+}
+
+/**
+ * queue_limits_start_update - start an atomic update of queue limits
+ * @q:		queue to update
+ *
+ * This functions starts an atomic update of the queue limits.  It takes a lock
+ * to prevent other updates and returns a snapshot of the current limits that
+ * the caller can modify.  The caller must call queue_limits_commit_update()
+ * to finish the update.
+ *
+ * Context: process context.
+ */
+static inline struct queue_limits
+queue_limits_start_update(struct request_queue *q)
+{
+	mutex_lock(&q->limits_lock);
+	return q->limits;
+}
+int queue_limits_commit_update_frozen(struct request_queue *q,
+		struct queue_limits *lim);
+int queue_limits_commit_update(struct request_queue *q,
+		struct queue_limits *lim);
+int queue_limits_set(struct request_queue *q, struct queue_limits *lim);
+int blk_validate_limits(struct queue_limits *lim);
+
+/**
+ * queue_limits_cancel_update - cancel an atomic update of queue limits
+ * @q:		queue to update
+ *
+ * This functions cancels an atomic update of the queue limits started by
+ * queue_limits_start_update() and should be used when an error occurs after
+ * starting update.
+ */
+static inline void queue_limits_cancel_update(struct request_queue *q)
+{
+	mutex_unlock(&q->limits_lock);
+}
+
+/*
+ * These helpers are for drivers that have sloppy feature negotiation and might
+ * have to disable DISCARD, WRITE_ZEROES or SECURE_DISCARD from the I/O
+ * completion handler when the device returned an indicator that the respective
+ * feature is not actually supported.  They are racy and the driver needs to
+ * cope with that.  Try to avoid this scheme if you can.
+ */
+static inline void blk_queue_disable_discard(struct request_queue *q)
+{
+	q->limits.max_discard_sectors = 0;
+}
+
+static inline void blk_queue_disable_secure_erase(struct request_queue *q)
+{
+	q->limits.max_secure_erase_sectors = 0;
+}
+
+static inline void blk_queue_disable_write_zeroes(struct request_queue *q)
+{
+	q->limits.max_write_zeroes_sectors = 0;
+	q->limits.max_wzeroes_unmap_sectors = 0;
 }
 
 /*
  * Access functions for manipulating queue properties
  */
-void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce limit);
-extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
-extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int);
-extern void blk_queue_max_segments(struct request_queue *, unsigned short);
-extern void blk_queue_max_discard_segments(struct request_queue *,
-		unsigned short);
-void blk_queue_max_secure_erase_sectors(struct request_queue *q,
-		unsigned int max_sectors);
-extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
-extern void blk_queue_max_discard_sectors(struct request_queue *q,
-		unsigned int max_discard_sectors);
-extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
-		unsigned int max_write_same_sectors);
-extern void blk_queue_logical_block_size(struct request_queue *, unsigned int);
-extern void blk_queue_max_zone_append_sectors(struct request_queue *q,
-		unsigned int max_zone_append_sectors);
-extern void blk_queue_physical_block_size(struct request_queue *, unsigned int);
-void blk_queue_zone_write_granularity(struct request_queue *q,
-				      unsigned int size);
-extern void blk_queue_alignment_offset(struct request_queue *q,
-				       unsigned int alignment);
-void disk_update_readahead(struct gendisk *disk);
-extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
-extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
-extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt);
-extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth);
 extern void blk_set_stacking_limits(struct queue_limits *lim);
 extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 			    sector_t offset);
-extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
-			      sector_t offset);
-extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
-extern void blk_queue_segment_boundary(struct request_queue *, unsigned long);
-extern void blk_queue_virt_boundary(struct request_queue *, unsigned long);
-extern void blk_queue_dma_alignment(struct request_queue *, int);
-extern void blk_queue_update_dma_alignment(struct request_queue *, int);
+void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
+		sector_t offset, const char *pfx);
 extern void blk_queue_rq_timeout(struct request_queue *, unsigned int);
-extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua);
 
 struct blk_independent_access_ranges *
 disk_alloc_independent_access_ranges(struct gendisk *disk, int nr_ia_ranges);
 void disk_set_independent_access_ranges(struct gendisk *disk,
 				struct blk_independent_access_ranges *iars);
 
-/*
- * Elevator features for blk_queue_required_elevator_features:
- */
-/* Supports zoned block devices sequential write constraint */
-#define ELEVATOR_F_ZBD_SEQ_WRITE	(1U << 0)
-
-extern void blk_queue_required_elevator_features(struct request_queue *q,
-						 unsigned int features);
-extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
-					      struct device *dev);
-
 bool __must_check blk_get_queue(struct request_queue *);
 extern void blk_put_queue(struct request_queue *);
 
 void blk_mark_disk_dead(struct gendisk *disk);
 
+struct rq_list {
+	struct request *head;
+	struct request *tail;
+};
+
 #ifdef CONFIG_BLOCK
 /*
  * blk_plug permits building a queue of related requests by holding the I/O
@@ -967,17 +1170,17 @@ void blk_mark_disk_dead(struct gendisk *disk);
  * blk_flush_plug() is called.
  */
 struct blk_plug {
-	struct request *mq_list; /* blk-mq requests */
+	struct rq_list mq_list; /* blk-mq requests */
 
 	/* if ios_left is > 1, we can batch tag/rq allocations */
-	struct request *cached_rq;
+	struct rq_list cached_rqs;
+	u64 cur_ktime;
 	unsigned short nr_ios;
 
 	unsigned short rq_count;
 
 	bool multiple_queues;
 	bool has_elevator;
-	bool nowait;
 
 	struct list_head cb_list; /* md requires an unplug callback */
 };
@@ -1002,6 +1205,18 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 		__blk_flush_plug(plug, async);
 }
 
+/*
+ * tsk == current here
+ */
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+	struct blk_plug *plug = tsk->plug;
+
+	if (plug)
+		plug->cur_ktime = 0;
+	current->flags &= ~PF_BLOCK_TS;
+}
+
 int blkdev_issue_flush(struct block_device *bdev);
 long nr_blockdev_pages(void);
 #else /* CONFIG_BLOCK */
@@ -1025,6 +1240,10 @@ static inline void blk_flush_plug(struct blk_plug *plug, bool async)
 {
 }
 
+static inline void blk_plug_invalidate_ts(struct task_struct *tsk)
+{
+}
+
 static inline int blkdev_issue_flush(struct block_device *bdev)
 {
 	return 0;
@@ -1047,6 +1266,7 @@ int blkdev_issue_secure_erase(struct block_device *bdev, sector_t sector,
 
 #define BLKDEV_ZERO_NOUNMAP	(1 << 0)  /* do not free blocks */
 #define BLKDEV_ZERO_NOFALLBACK	(1 << 1)  /* don't write explicit zeroes */
+#define BLKDEV_ZERO_KILLABLE	(1 << 2)  /* interruptible by fatal signals */
 
 extern int __blkdev_issue_zeroout(struct block_device *bdev, sector_t sector,
 		sector_t nr_sects, gfp_t gfp_mask, struct bio **biop,
@@ -1077,7 +1297,7 @@ static inline int sb_issue_zeroout(struct super_block *sb, sector_t block,
 
 static inline bool bdev_is_partition(struct block_device *bdev)
 {
-	return bdev->bd_partno;
+	return bdev_partno(bdev) != 0;
 }
 
 enum blk_default_limits {
@@ -1087,7 +1307,10 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-#define BLK_DEF_MAX_SECTORS 2560u
+static inline struct queue_limits *bdev_limits(struct block_device *bdev)
+{
+	return &bdev_get_queue(bdev)->limits;
+}
 
 static inline unsigned long queue_segment_boundary(const struct request_queue *q)
 {
@@ -1129,18 +1352,20 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q)
 	return q->limits.max_segment_size;
 }
 
-static inline unsigned int queue_max_zone_append_sectors(const struct request_queue *q)
+static inline bool queue_emulates_zone_append(struct request_queue *q)
 {
+	return blk_queue_is_zoned(q) && !q->limits.max_hw_zone_append_sectors;
+}
 
-	const struct queue_limits *l = &q->limits;
-
-	return min(l->max_zone_append_sectors, l->max_sectors);
+static inline bool bdev_emulates_zone_append(struct block_device *bdev)
+{
+	return queue_emulates_zone_append(bdev_get_queue(bdev));
 }
 
 static inline unsigned int
 bdev_max_zone_append_sectors(struct block_device *bdev)
 {
-	return queue_max_zone_append_sectors(bdev_get_queue(bdev));
+	return bdev_limits(bdev)->max_zone_append_sectors;
 }
 
 static inline unsigned int bdev_max_segments(struct block_device *bdev)
@@ -1148,14 +1373,16 @@ static inline unsigned int bdev_max_segments(struct block_device *bdev)
 	return queue_max_segments(bdev_get_queue(bdev));
 }
 
-static inline unsigned queue_logical_block_size(const struct request_queue *q)
+static inline unsigned short bdev_max_write_streams(struct block_device *bdev)
 {
-	int retval = 512;
-
-	if (q && q->limits.logical_block_size)
-		retval = q->limits.logical_block_size;
+	if (bdev_is_partition(bdev))
+		return 0;
+	return bdev_limits(bdev)->max_write_streams;
+}
 
-	return retval;
+static inline unsigned queue_logical_block_size(const struct request_queue *q)
+{
+	return q->limits.logical_block_size;
 }
 
 static inline unsigned int bdev_logical_block_size(struct block_device *bdev)
@@ -1178,7 +1405,7 @@ static inline unsigned int queue_io_min(const struct request_queue *q)
 	return q->limits.io_min;
 }
 
-static inline int bdev_io_min(struct block_device *bdev)
+static inline unsigned int bdev_io_min(struct block_device *bdev)
 {
 	return queue_io_min(bdev_get_queue(bdev));
 }
@@ -1188,7 +1415,7 @@ static inline unsigned int queue_io_opt(const struct request_queue *q)
 	return q->limits.io_opt;
 }
 
-static inline int bdev_io_opt(struct block_device *bdev)
+static inline unsigned int bdev_io_opt(struct block_device *bdev)
 {
 	return queue_io_opt(bdev_get_queue(bdev));
 }
@@ -1210,28 +1437,29 @@ unsigned int bdev_discard_alignment(struct block_device *bdev);
 
 static inline unsigned int bdev_max_discard_sectors(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.max_discard_sectors;
+	return bdev_limits(bdev)->max_discard_sectors;
 }
 
 static inline unsigned int bdev_discard_granularity(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.discard_granularity;
+	return bdev_limits(bdev)->discard_granularity;
 }
 
 static inline unsigned int
 bdev_max_secure_erase_sectors(struct block_device *bdev)
 {
-	return bdev_get_queue(bdev)->limits.max_secure_erase_sectors;
+	return bdev_limits(bdev)->max_secure_erase_sectors;
 }
 
 static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 {
-	struct request_queue *q = bdev_get_queue(bdev);
-
-	if (q)
-		return q->limits.max_write_zeroes_sectors;
+	return bdev_limits(bdev)->max_write_zeroes_sectors;
+}
 
-	return 0;
+static inline unsigned int
+bdev_write_zeroes_unmap_sectors(struct block_device *bdev)
+{
+	return bdev_limits(bdev)->max_wzeroes_unmap_sectors;
 }
 
 static inline bool bdev_nonrot(struct block_device *bdev)
@@ -1241,34 +1469,38 @@ static inline bool bdev_nonrot(struct block_device *bdev)
 
 static inline bool bdev_synchronous(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_SYNCHRONOUS,
-			&bdev_get_queue(bdev)->queue_flags);
+	return bdev->bd_disk->queue->limits.features & BLK_FEAT_SYNCHRONOUS;
 }
 
 static inline bool bdev_stable_writes(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_STABLE_WRITES,
-			&bdev_get_queue(bdev)->queue_flags);
+	struct request_queue *q = bdev_get_queue(bdev);
+
+	if (IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY) &&
+	    q->limits.integrity.csum_type != BLK_INTEGRITY_CSUM_NONE)
+		return true;
+	return q->limits.features & BLK_FEAT_STABLE_WRITES;
 }
 
-static inline bool bdev_write_cache(struct block_device *bdev)
+static inline bool blk_queue_write_cache(struct request_queue *q)
 {
-	return test_bit(QUEUE_FLAG_WC, &bdev_get_queue(bdev)->queue_flags);
+	return (q->limits.features & BLK_FEAT_WRITE_CACHE) &&
+		!(q->limits.flags & BLK_FLAG_WRITE_CACHE_DISABLED);
 }
 
-static inline bool bdev_fua(struct block_device *bdev)
+static inline bool bdev_write_cache(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_FUA, &bdev_get_queue(bdev)->queue_flags);
+	return blk_queue_write_cache(bdev_get_queue(bdev));
 }
 
-static inline bool bdev_nowait(struct block_device *bdev)
+static inline bool bdev_fua(struct block_device *bdev)
 {
-	return test_bit(QUEUE_FLAG_NOWAIT, &bdev_get_queue(bdev)->queue_flags);
+	return bdev_limits(bdev)->features & BLK_FEAT_FUA;
 }
 
-static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev)
+static inline bool bdev_nowait(struct block_device *bdev)
 {
-	return blk_queue_zoned_model(bdev_get_queue(bdev));
+	return bdev->bd_disk->queue->limits.features & BLK_FEAT_NOWAIT;
 }
 
 static inline bool bdev_is_zoned(struct block_device *bdev)
@@ -1281,15 +1513,6 @@ static inline unsigned int bdev_zone_no(struct block_device *bdev, sector_t sec)
 	return disk_zone_no(bdev->bd_disk, sec);
 }
 
-static inline bool bdev_op_is_zoned_write(struct block_device *bdev,
-					  blk_opf_t op)
-{
-	if (!bdev_is_zoned(bdev))
-		return false;
-
-	return op == REQ_OP_WRITE || op == REQ_OP_WRITE_ZEROES;
-}
-
 static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 {
 	struct request_queue *q = bdev_get_queue(bdev);
@@ -1299,21 +1522,67 @@ static inline sector_t bdev_zone_sectors(struct block_device *bdev)
 	return q->limits.chunk_sectors;
 }
 
+static inline sector_t bdev_zone_start(struct block_device *bdev,
+				       sector_t sector)
+{
+	return sector & ~(bdev_zone_sectors(bdev) - 1);
+}
+
 static inline sector_t bdev_offset_from_zone_start(struct block_device *bdev,
 						   sector_t sector)
 {
 	return sector & (bdev_zone_sectors(bdev) - 1);
 }
 
+static inline sector_t bio_offset_from_zone_start(struct bio *bio)
+{
+	return bdev_offset_from_zone_start(bio->bi_bdev,
+					   bio->bi_iter.bi_sector);
+}
+
 static inline bool bdev_is_zone_start(struct block_device *bdev,
 				      sector_t sector)
 {
 	return bdev_offset_from_zone_start(bdev, sector) == 0;
 }
 
-static inline int queue_dma_alignment(const struct request_queue *q)
+/* Check whether @sector is a multiple of the zone size. */
+static inline bool bdev_is_zone_aligned(struct block_device *bdev,
+					sector_t sector)
+{
+	return bdev_is_zone_start(bdev, sector);
+}
+
+int blk_zone_issue_zeroout(struct block_device *bdev, sector_t sector,
+			   sector_t nr_sects, gfp_t gfp_mask);
+
+static inline unsigned int queue_dma_alignment(const struct request_queue *q)
+{
+	return q->limits.dma_alignment;
+}
+
+static inline unsigned int
+queue_atomic_write_unit_max_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_unit_max;
+}
+
+static inline unsigned int
+queue_atomic_write_unit_min_bytes(const struct request_queue *q)
 {
-	return q ? q->limits.dma_alignment : 511;
+	return q->limits.atomic_write_unit_min;
+}
+
+static inline unsigned int
+queue_atomic_write_boundary_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_boundary_sectors << SECTOR_SHIFT;
+}
+
+static inline unsigned int
+queue_atomic_write_max_bytes(const struct request_queue *q)
+{
+	return q->limits.atomic_write_max_sectors << SECTOR_SHIFT;
 }
 
 static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
@@ -1321,17 +1590,17 @@ static inline unsigned int bdev_dma_alignment(struct block_device *bdev)
 	return queue_dma_alignment(bdev_get_queue(bdev));
 }
 
-static inline bool bdev_iter_is_aligned(struct block_device *bdev,
-					struct iov_iter *iter)
+static inline unsigned int
+blk_lim_dma_alignment_and_pad(struct queue_limits *lim)
 {
-	return iov_iter_is_aligned(iter, bdev_dma_alignment(bdev),
-				   bdev_logical_block_size(bdev) - 1);
+	return lim->dma_alignment | lim->dma_pad_mask;
 }
 
-static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr,
+static inline bool blk_rq_aligned(struct request_queue *q, unsigned long addr,
 				 unsigned int len)
 {
-	unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask;
+	unsigned int alignment = blk_lim_dma_alignment_and_pad(&q->limits);
+
 	return !(addr & alignment) && !(len & alignment);
 }
 
@@ -1341,11 +1610,6 @@ static inline unsigned int blksize_bits(unsigned int size)
 	return order_base_2(size >> SECTOR_SHIFT) + SECTOR_SHIFT;
 }
 
-static inline unsigned int block_size(struct block_device *bdev)
-{
-	return 1 << bdev->bd_inode->i_blkbits;
-}
-
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_mod_delayed_work_on(int cpu, struct delayed_work *dwork, unsigned long delay);
 
@@ -1380,20 +1644,23 @@ struct block_device_operations {
 	void (*submit_bio)(struct bio *bio);
 	int (*poll_bio)(struct bio *bio, struct io_comp_batch *iob,
 			unsigned int flags);
-	int (*open) (struct block_device *, fmode_t);
-	void (*release) (struct gendisk *, fmode_t);
-	int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
-	int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long);
+	int (*open)(struct gendisk *disk, blk_mode_t mode);
+	void (*release)(struct gendisk *disk);
+	int (*ioctl)(struct block_device *bdev, blk_mode_t mode,
+			unsigned cmd, unsigned long arg);
+	int (*compat_ioctl)(struct block_device *bdev, blk_mode_t mode,
+			unsigned cmd, unsigned long arg);
 	unsigned int (*check_events) (struct gendisk *disk,
 				      unsigned int clearing);
 	void (*unlock_native_capacity) (struct gendisk *);
-	int (*getgeo)(struct block_device *, struct hd_geometry *);
+	int (*getgeo)(struct gendisk *, struct hd_geometry *);
 	int (*set_read_only)(struct block_device *bdev, bool ro);
 	void (*free_disk)(struct gendisk *disk);
 	/* this callback is with swap_lock and sometimes page table lock held */
 	void (*swap_slot_free_notify) (struct block_device *, unsigned long);
 	int (*report_zones)(struct gendisk *, sector_t sector,
-			unsigned int nr_zones, report_zones_cb cb, void *data);
+			    unsigned int nr_zones,
+			    struct blk_report_zones_args *args);
 	char *(*devnode)(struct gendisk *disk, umode_t *mode);
 	/* returns the length of the identifier or a negative errno: */
 	int (*get_unique_id)(struct gendisk *disk, u8 id[16],
@@ -1410,7 +1677,7 @@ struct block_device_operations {
 };
 
 #ifdef CONFIG_COMPAT
-extern int blkdev_compat_ptr_ioctl(struct block_device *, fmode_t,
+extern int blkdev_compat_ptr_ioctl(struct block_device *, blk_mode_t,
 				      unsigned int, unsigned long);
 #else
 #define blkdev_compat_ptr_ioctl NULL
@@ -1448,8 +1715,8 @@ static inline void bio_end_io_acct(struct bio *bio, unsigned long start_time)
 	return bio_end_io_acct_remapped(bio, start_time, bio->bi_bdev);
 }
 
-int bdev_read_only(struct block_device *bdev);
-int set_blocksize(struct block_device *bdev, int size);
+int bdev_validate_blocksize(struct block_device *bdev, int block_size);
+int set_blocksize(struct file *file, int size);
 
 int lookup_bdev(const char *pathname, dev_t *dev);
 
@@ -1463,22 +1730,52 @@ void blkdev_show(struct seq_file *seqf, off_t offset);
 #define BLKDEV_MAJOR_MAX	0
 #endif
 
-struct block_device *blkdev_get_by_path(const char *path, fmode_t mode,
-		void *holder);
-struct block_device *blkdev_get_by_dev(dev_t dev, fmode_t mode, void *holder);
-int bd_prepare_to_claim(struct block_device *bdev, void *holder);
-void bd_abort_claiming(struct block_device *bdev, void *holder);
-void blkdev_put(struct block_device *bdev, fmode_t mode);
+struct blk_holder_ops {
+	void (*mark_dead)(struct block_device *bdev, bool surprise);
+
+	/*
+	 * Sync the file system mounted on the block device.
+	 */
+	void (*sync)(struct block_device *bdev);
+
+	/*
+	 * Freeze the file system mounted on the block device.
+	 */
+	int (*freeze)(struct block_device *bdev);
 
-/* just for blk-cgroup, don't use elsewhere */
-struct block_device *blkdev_get_no_open(dev_t dev);
-void blkdev_put_no_open(struct block_device *bdev);
+	/*
+	 * Thaw the file system mounted on the block device.
+	 */
+	int (*thaw)(struct block_device *bdev);
+};
+
+/*
+ * For filesystems using @fs_holder_ops, the @holder argument passed to
+ * helpers used to open and claim block devices via
+ * bd_prepare_to_claim() must point to a superblock.
+ */
+extern const struct blk_holder_ops fs_holder_ops;
+
+/*
+ * Return the correct open flags for blkdev_get_by_* for super block flags
+ * as stored in sb->s_flags.
+ */
+#define sb_open_mode(flags) \
+	(BLK_OPEN_READ | BLK_OPEN_RESTRICT_WRITES | \
+	 (((flags) & SB_RDONLY) ? 0 : BLK_OPEN_WRITE))
+
+struct file *bdev_file_open_by_dev(dev_t dev, blk_mode_t mode, void *holder,
+		const struct blk_holder_ops *hops);
+struct file *bdev_file_open_by_path(const char *path, blk_mode_t mode,
+		void *holder, const struct blk_holder_ops *hops);
+int bd_prepare_to_claim(struct block_device *bdev, void *holder,
+		const struct blk_holder_ops *hops);
+void bd_abort_claiming(struct block_device *bdev, void *holder);
 
-struct block_device *bdev_alloc(struct gendisk *disk, u8 partno);
-void bdev_add(struct block_device *bdev, dev_t dev);
 struct block_device *I_BDEV(struct inode *inode);
-int truncate_bdev_range(struct block_device *bdev, fmode_t mode, loff_t lstart,
-		loff_t lend);
+struct block_device *file_bdev(struct file *bdev_file);
+bool disk_live(struct gendisk *disk);
+unsigned int block_size(struct block_device *bdev);
 
 #ifdef CONFIG_BLOCK
 void invalidate_bdev(struct block_device *bdev);
@@ -1486,8 +1783,9 @@ int sync_blockdev(struct block_device *bdev);
 int sync_blockdev_range(struct block_device *bdev, loff_t lstart, loff_t lend);
 int sync_blockdev_nowait(struct block_device *bdev);
 void sync_bdevs(bool wait);
-void bdev_statx_dioalign(struct inode *inode, struct kstat *stat);
+void bdev_statx(const struct path *path, struct kstat *stat, u32 request_mask);
 void printk_all_partitions(void);
+int __init early_lookup_bdev(const char *pathname, dev_t *dev);
 #else
 static inline void invalidate_bdev(struct block_device *bdev)
 {
@@ -1503,25 +1801,76 @@ static inline int sync_blockdev_nowait(struct block_device *bdev)
 static inline void sync_bdevs(bool wait)
 {
 }
-static inline void bdev_statx_dioalign(struct inode *inode, struct kstat *stat)
+static inline void bdev_statx(const struct path *path, struct kstat *stat,
+		u32 request_mask)
 {
 }
 static inline void printk_all_partitions(void)
 {
 }
+static inline int early_lookup_bdev(const char *pathname, dev_t *dev)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_BLOCK */
 
-int fsync_bdev(struct block_device *bdev);
-
-int freeze_bdev(struct block_device *bdev);
-int thaw_bdev(struct block_device *bdev);
+int bdev_freeze(struct block_device *bdev);
+int bdev_thaw(struct block_device *bdev);
+void bdev_fput(struct file *bdev_file);
 
 struct io_comp_batch {
-	struct request *req_list;
+	struct rq_list req_list;
 	bool need_ts;
 	void (*complete)(struct io_comp_batch *);
 };
 
+static inline bool blk_atomic_write_start_sect_aligned(sector_t sector,
+						struct queue_limits *limits)
+{
+	unsigned int alignment = max(limits->atomic_write_hw_unit_min,
+				limits->atomic_write_hw_boundary);
+
+	return IS_ALIGNED(sector, alignment >> SECTOR_SHIFT);
+}
+
+static inline bool bdev_can_atomic_write(struct block_device *bdev)
+{
+	struct request_queue *bd_queue = bdev->bd_queue;
+	struct queue_limits *limits = &bd_queue->limits;
+
+	if (!limits->atomic_write_unit_min)
+		return false;
+
+	if (bdev_is_partition(bdev))
+		return blk_atomic_write_start_sect_aligned(bdev->bd_start_sect,
+							limits);
+
+	return true;
+}
+
+static inline unsigned int
+bdev_atomic_write_unit_min_bytes(struct block_device *bdev)
+{
+	if (!bdev_can_atomic_write(bdev))
+		return 0;
+	return queue_atomic_write_unit_min_bytes(bdev_get_queue(bdev));
+}
+
+static inline unsigned int
+bdev_atomic_write_unit_max_bytes(struct block_device *bdev)
+{
+	if (!bdev_can_atomic_write(bdev))
+		return 0;
+	return queue_atomic_write_unit_max_bytes(bdev_get_queue(bdev));
+}
+
+static inline int bio_split_rw_at(struct bio *bio,
+		const struct queue_limits *lim,
+		unsigned *segs, unsigned max_bytes)
+{
+	return bio_split_io_at(bio, lim, segs, max_bytes, lim->dma_alignment);
+}
+
 #define DEFINE_IO_COMP_BATCH(name)	struct io_comp_batch name = { }
 
 #endif /* _LINUX_BLKDEV_H */
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index cfbda114348c..05c8754456aa 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -14,11 +14,12 @@
 #include <linux/sysfs.h>
 
 struct blk_trace {
+	int version;
 	int trace_state;
 	struct rchan *rchan;
 	unsigned long __percpu *sequence;
 	unsigned char __percpu *msg_data;
-	u16 act_mask;
+	u64 act_mask;
 	u64 start_lba;
 	u64 end_lba;
 	u32 pid;
@@ -85,10 +86,14 @@ extern int blk_trace_remove(struct request_queue *q);
 # define blk_add_driver_data(rq, data, len)		do {} while (0)
 # define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
 # define blk_trace_startstop(q, start)			(-ENOTTY)
-# define blk_trace_remove(q)				(-ENOTTY)
 # define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
 # define blk_add_cgroup_trace_msg(q, cg, fmt, ...)	do { } while (0)
 # define blk_trace_note_message_enabled(q)		(false)
+
+static inline int blk_trace_remove(struct request_queue *q)
+{
+	return -ENOTTY;
+}
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
 
 #ifdef CONFIG_COMPAT
diff --git a/include/linux/bnxt/hsi.h b/include/linux/bnxt/hsi.h
new file mode 100644
index 000000000000..47c34990cf23
--- /dev/null
+++ b/include/linux/bnxt/hsi.h
@@ -0,0 +1,11166 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2014-2018 Broadcom Limited
+ * Copyright (c) 2018-2025 Broadcom Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * DO NOT MODIFY!!! This file is automatically generated.
+ */
+
+#ifndef _BNXT_HSI_H_
+#define _BNXT_HSI_H_
+
+/* hwrm_cmd_hdr (size:128b/16B) */
+struct hwrm_cmd_hdr {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_resp_hdr (size:64b/8B) */
+struct hwrm_resp_hdr {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+};
+
+#define CMD_DISCR_TLV_ENCAP 0x8000UL
+#define CMD_DISCR_LAST     CMD_DISCR_TLV_ENCAP
+
+
+#define TLV_TYPE_HWRM_REQUEST                    0x1UL
+#define TLV_TYPE_HWRM_RESPONSE                   0x2UL
+#define TLV_TYPE_ROCE_SP_COMMAND                 0x3UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN1              0x4UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN1             0x5UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN2              0x6UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN2             0x7UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN1_EXT          0x8UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN1_EXT         0x9UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN2_EXT          0xaUL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN2_EXT         0xbUL
+#define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL
+#define TLV_TYPE_ENGINE_CKV_IV                   0x8003UL
+#define TLV_TYPE_ENGINE_CKV_AUTH_TAG             0x8004UL
+#define TLV_TYPE_ENGINE_CKV_CIPHERTEXT           0x8005UL
+#define TLV_TYPE_ENGINE_CKV_HOST_ALGORITHMS      0x8006UL
+#define TLV_TYPE_ENGINE_CKV_HOST_ECC_PUBLIC_KEY  0x8007UL
+#define TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE      0x8008UL
+#define TLV_TYPE_ENGINE_CKV_FW_ECC_PUBLIC_KEY    0x8009UL
+#define TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS        0x800aUL
+#define TLV_TYPE_LAST                           TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS
+
+
+/* tlv (size:64b/8B) */
+struct tlv {
+	__le16	cmd_discr;
+	u8	reserved_8b;
+	u8	flags;
+	#define TLV_FLAGS_MORE         0x1UL
+	#define TLV_FLAGS_MORE_LAST      0x0UL
+	#define TLV_FLAGS_MORE_NOT_LAST  0x1UL
+	#define TLV_FLAGS_REQUIRED     0x2UL
+	#define TLV_FLAGS_REQUIRED_NO    (0x0UL << 1)
+	#define TLV_FLAGS_REQUIRED_YES   (0x1UL << 1)
+	#define TLV_FLAGS_REQUIRED_LAST TLV_FLAGS_REQUIRED_YES
+	__le16	tlv_type;
+	__le16	length;
+};
+
+/* input (size:128b/16B) */
+struct input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* output (size:64b/8B) */
+struct output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+};
+
+/* hwrm_short_input (size:128b/16B) */
+struct hwrm_short_input {
+	__le16	req_type;
+	__le16	signature;
+	#define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL
+	#define SHORT_REQ_SIGNATURE_LAST     SHORT_REQ_SIGNATURE_SHORT_CMD
+	__le16	target_id;
+	#define SHORT_REQ_TARGET_ID_DEFAULT 0x0UL
+	#define SHORT_REQ_TARGET_ID_TOOLS   0xfffdUL
+	#define SHORT_REQ_TARGET_ID_LAST   SHORT_REQ_TARGET_ID_TOOLS
+	__le16	size;
+	__le64	req_addr;
+};
+
+/* cmd_nums (size:64b/8B) */
+struct cmd_nums {
+	__le16	req_type;
+	#define HWRM_VER_GET                              0x0UL
+	#define HWRM_FUNC_ECHO_RESPONSE                   0xbUL
+	#define HWRM_ERROR_RECOVERY_QCFG                  0xcUL
+	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
+	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
+	#define HWRM_FUNC_VF_CFG                          0xfUL
+	#define HWRM_RESERVED1                            0x10UL
+	#define HWRM_FUNC_RESET                           0x11UL
+	#define HWRM_FUNC_GETFID                          0x12UL
+	#define HWRM_FUNC_VF_ALLOC                        0x13UL
+	#define HWRM_FUNC_VF_FREE                         0x14UL
+	#define HWRM_FUNC_QCAPS                           0x15UL
+	#define HWRM_FUNC_QCFG                            0x16UL
+	#define HWRM_FUNC_CFG                             0x17UL
+	#define HWRM_FUNC_QSTATS                          0x18UL
+	#define HWRM_FUNC_CLR_STATS                       0x19UL
+	#define HWRM_FUNC_DRV_UNRGTR                      0x1aUL
+	#define HWRM_FUNC_VF_RESC_FREE                    0x1bUL
+	#define HWRM_FUNC_VF_VNIC_IDS_QUERY               0x1cUL
+	#define HWRM_FUNC_DRV_RGTR                        0x1dUL
+	#define HWRM_FUNC_DRV_QVER                        0x1eUL
+	#define HWRM_FUNC_BUF_RGTR                        0x1fUL
+	#define HWRM_PORT_PHY_CFG                         0x20UL
+	#define HWRM_PORT_MAC_CFG                         0x21UL
+	#define HWRM_PORT_TS_QUERY                        0x22UL
+	#define HWRM_PORT_QSTATS                          0x23UL
+	#define HWRM_PORT_LPBK_QSTATS                     0x24UL
+	#define HWRM_PORT_CLR_STATS                       0x25UL
+	#define HWRM_PORT_LPBK_CLR_STATS                  0x26UL
+	#define HWRM_PORT_PHY_QCFG                        0x27UL
+	#define HWRM_PORT_MAC_QCFG                        0x28UL
+	#define HWRM_PORT_MAC_PTP_QCFG                    0x29UL
+	#define HWRM_PORT_PHY_QCAPS                       0x2aUL
+	#define HWRM_PORT_PHY_I2C_WRITE                   0x2bUL
+	#define HWRM_PORT_PHY_I2C_READ                    0x2cUL
+	#define HWRM_PORT_LED_CFG                         0x2dUL
+	#define HWRM_PORT_LED_QCFG                        0x2eUL
+	#define HWRM_PORT_LED_QCAPS                       0x2fUL
+	#define HWRM_QUEUE_QPORTCFG                       0x30UL
+	#define HWRM_QUEUE_QCFG                           0x31UL
+	#define HWRM_QUEUE_CFG                            0x32UL
+	#define HWRM_FUNC_VLAN_CFG                        0x33UL
+	#define HWRM_FUNC_VLAN_QCFG                       0x34UL
+	#define HWRM_QUEUE_PFCENABLE_QCFG                 0x35UL
+	#define HWRM_QUEUE_PFCENABLE_CFG                  0x36UL
+	#define HWRM_QUEUE_PRI2COS_QCFG                   0x37UL
+	#define HWRM_QUEUE_PRI2COS_CFG                    0x38UL
+	#define HWRM_QUEUE_COS2BW_QCFG                    0x39UL
+	#define HWRM_QUEUE_COS2BW_CFG                     0x3aUL
+	#define HWRM_QUEUE_DSCP_QCAPS                     0x3bUL
+	#define HWRM_QUEUE_DSCP2PRI_QCFG                  0x3cUL
+	#define HWRM_QUEUE_DSCP2PRI_CFG                   0x3dUL
+	#define HWRM_VNIC_ALLOC                           0x40UL
+	#define HWRM_VNIC_FREE                            0x41UL
+	#define HWRM_VNIC_CFG                             0x42UL
+	#define HWRM_VNIC_QCFG                            0x43UL
+	#define HWRM_VNIC_TPA_CFG                         0x44UL
+	#define HWRM_VNIC_TPA_QCFG                        0x45UL
+	#define HWRM_VNIC_RSS_CFG                         0x46UL
+	#define HWRM_VNIC_RSS_QCFG                        0x47UL
+	#define HWRM_VNIC_PLCMODES_CFG                    0x48UL
+	#define HWRM_VNIC_PLCMODES_QCFG                   0x49UL
+	#define HWRM_VNIC_QCAPS                           0x4aUL
+	#define HWRM_VNIC_UPDATE                          0x4bUL
+	#define HWRM_RING_ALLOC                           0x50UL
+	#define HWRM_RING_FREE                            0x51UL
+	#define HWRM_RING_CMPL_RING_QAGGINT_PARAMS        0x52UL
+	#define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS     0x53UL
+	#define HWRM_RING_AGGINT_QCAPS                    0x54UL
+	#define HWRM_RING_SCHQ_ALLOC                      0x55UL
+	#define HWRM_RING_SCHQ_CFG                        0x56UL
+	#define HWRM_RING_SCHQ_FREE                       0x57UL
+	#define HWRM_RING_RESET                           0x5eUL
+	#define HWRM_RING_GRP_ALLOC                       0x60UL
+	#define HWRM_RING_GRP_FREE                        0x61UL
+	#define HWRM_RING_CFG                             0x62UL
+	#define HWRM_RING_QCFG                            0x63UL
+	#define HWRM_RESERVED5                            0x64UL
+	#define HWRM_RESERVED6                            0x65UL
+	#define HWRM_VNIC_RSS_COS_LB_CTX_ALLOC            0x70UL
+	#define HWRM_VNIC_RSS_COS_LB_CTX_FREE             0x71UL
+	#define HWRM_QUEUE_MPLS_QCAPS                     0x80UL
+	#define HWRM_QUEUE_MPLSTC2PRI_QCFG                0x81UL
+	#define HWRM_QUEUE_MPLSTC2PRI_CFG                 0x82UL
+	#define HWRM_QUEUE_VLANPRI_QCAPS                  0x83UL
+	#define HWRM_QUEUE_VLANPRI2PRI_QCFG               0x84UL
+	#define HWRM_QUEUE_VLANPRI2PRI_CFG                0x85UL
+	#define HWRM_QUEUE_GLOBAL_CFG                     0x86UL
+	#define HWRM_QUEUE_GLOBAL_QCFG                    0x87UL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_QCFG      0x88UL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_CFG       0x89UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_QCFG      0x8aUL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_CFG       0x8bUL
+	#define HWRM_QUEUE_QCAPS                          0x8cUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_QCFG       0x8dUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_CFG        0x8eUL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_QCFG       0x8fUL
+	#define HWRM_CFA_L2_FILTER_ALLOC                  0x90UL
+	#define HWRM_CFA_L2_FILTER_FREE                   0x91UL
+	#define HWRM_CFA_L2_FILTER_CFG                    0x92UL
+	#define HWRM_CFA_L2_SET_RX_MASK                   0x93UL
+	#define HWRM_CFA_VLAN_ANTISPOOF_CFG               0x94UL
+	#define HWRM_CFA_TUNNEL_FILTER_ALLOC              0x95UL
+	#define HWRM_CFA_TUNNEL_FILTER_FREE               0x96UL
+	#define HWRM_CFA_ENCAP_RECORD_ALLOC               0x97UL
+	#define HWRM_CFA_ENCAP_RECORD_FREE                0x98UL
+	#define HWRM_CFA_NTUPLE_FILTER_ALLOC              0x99UL
+	#define HWRM_CFA_NTUPLE_FILTER_FREE               0x9aUL
+	#define HWRM_CFA_NTUPLE_FILTER_CFG                0x9bUL
+	#define HWRM_CFA_EM_FLOW_ALLOC                    0x9cUL
+	#define HWRM_CFA_EM_FLOW_FREE                     0x9dUL
+	#define HWRM_CFA_EM_FLOW_CFG                      0x9eUL
+	#define HWRM_TUNNEL_DST_PORT_QUERY                0xa0UL
+	#define HWRM_TUNNEL_DST_PORT_ALLOC                0xa1UL
+	#define HWRM_TUNNEL_DST_PORT_FREE                 0xa2UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_CFG        0xa3UL
+	#define HWRM_STAT_CTX_ENG_QUERY                   0xafUL
+	#define HWRM_STAT_CTX_ALLOC                       0xb0UL
+	#define HWRM_STAT_CTX_FREE                        0xb1UL
+	#define HWRM_STAT_CTX_QUERY                       0xb2UL
+	#define HWRM_STAT_CTX_CLR_STATS                   0xb3UL
+	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
+	#define HWRM_PORT_PHY_MDIO_WRITE                  0xb5UL
+	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
+	#define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE            0xb7UL
+	#define HWRM_PORT_PHY_MDIO_BUS_RELEASE            0xb8UL
+	#define HWRM_PORT_QSTATS_EXT_PFC_WD               0xb9UL
+	#define HWRM_RESERVED7                            0xbaUL
+	#define HWRM_PORT_TX_FIR_CFG                      0xbbUL
+	#define HWRM_PORT_TX_FIR_QCFG                     0xbcUL
+	#define HWRM_PORT_ECN_QSTATS                      0xbdUL
+	#define HWRM_FW_LIVEPATCH_QUERY                   0xbeUL
+	#define HWRM_FW_LIVEPATCH                         0xbfUL
+	#define HWRM_FW_RESET                             0xc0UL
+	#define HWRM_FW_QSTATUS                           0xc1UL
+	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
+	#define HWRM_FW_SYNC                              0xc3UL
+	#define HWRM_FW_STATE_QCAPS                       0xc4UL
+	#define HWRM_FW_STATE_QUIESCE                     0xc5UL
+	#define HWRM_FW_STATE_BACKUP                      0xc6UL
+	#define HWRM_FW_STATE_RESTORE                     0xc7UL
+	#define HWRM_FW_SET_TIME                          0xc8UL
+	#define HWRM_FW_GET_TIME                          0xc9UL
+	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
+	#define HWRM_FW_GET_STRUCTURED_DATA               0xcbUL
+	#define HWRM_FW_IPC_MAILBOX                       0xccUL
+	#define HWRM_FW_ECN_CFG                           0xcdUL
+	#define HWRM_FW_ECN_QCFG                          0xceUL
+	#define HWRM_FW_SECURE_CFG                        0xcfUL
+	#define HWRM_EXEC_FWD_RESP                        0xd0UL
+	#define HWRM_REJECT_FWD_RESP                      0xd1UL
+	#define HWRM_FWD_RESP                             0xd2UL
+	#define HWRM_FWD_ASYNC_EVENT_CMPL                 0xd3UL
+	#define HWRM_OEM_CMD                              0xd4UL
+	#define HWRM_PORT_PRBS_TEST                       0xd5UL
+	#define HWRM_PORT_SFP_SIDEBAND_CFG                0xd6UL
+	#define HWRM_PORT_SFP_SIDEBAND_QCFG               0xd7UL
+	#define HWRM_FW_STATE_UNQUIESCE                   0xd8UL
+	#define HWRM_PORT_DSC_DUMP                        0xd9UL
+	#define HWRM_PORT_EP_TX_QCFG                      0xdaUL
+	#define HWRM_PORT_EP_TX_CFG                       0xdbUL
+	#define HWRM_PORT_CFG                             0xdcUL
+	#define HWRM_PORT_QCFG                            0xddUL
+	#define HWRM_PORT_MAC_QCAPS                       0xdfUL
+	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
+	#define HWRM_REG_POWER_QUERY                      0xe1UL
+	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
+	#define HWRM_REG_POWER_HISTOGRAM                  0xe3UL
+	#define HWRM_MONITOR_PAX_HISTOGRAM_START          0xe4UL
+	#define HWRM_MONITOR_PAX_HISTOGRAM_COLLECT        0xe5UL
+	#define HWRM_STAT_QUERY_ROCE_STATS                0xe6UL
+	#define HWRM_STAT_QUERY_ROCE_STATS_EXT            0xe7UL
+	#define HWRM_WOL_FILTER_ALLOC                     0xf0UL
+	#define HWRM_WOL_FILTER_FREE                      0xf1UL
+	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
+	#define HWRM_WOL_REASON_QCFG                      0xf3UL
+	#define HWRM_CFA_METER_QCAPS                      0xf4UL
+	#define HWRM_CFA_METER_PROFILE_ALLOC              0xf5UL
+	#define HWRM_CFA_METER_PROFILE_FREE               0xf6UL
+	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
+	#define HWRM_CFA_METER_INSTANCE_ALLOC             0xf8UL
+	#define HWRM_CFA_METER_INSTANCE_FREE              0xf9UL
+	#define HWRM_CFA_METER_INSTANCE_CFG               0xfaUL
+	#define HWRM_CFA_VFR_ALLOC                        0xfdUL
+	#define HWRM_CFA_VFR_FREE                         0xfeUL
+	#define HWRM_CFA_VF_PAIR_ALLOC                    0x100UL
+	#define HWRM_CFA_VF_PAIR_FREE                     0x101UL
+	#define HWRM_CFA_VF_PAIR_INFO                     0x102UL
+	#define HWRM_CFA_FLOW_ALLOC                       0x103UL
+	#define HWRM_CFA_FLOW_FREE                        0x104UL
+	#define HWRM_CFA_FLOW_FLUSH                       0x105UL
+	#define HWRM_CFA_FLOW_STATS                       0x106UL
+	#define HWRM_CFA_FLOW_INFO                        0x107UL
+	#define HWRM_CFA_DECAP_FILTER_ALLOC               0x108UL
+	#define HWRM_CFA_DECAP_FILTER_FREE                0x109UL
+	#define HWRM_CFA_VLAN_ANTISPOOF_QCFG              0x10aUL
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_ALLOC       0x10bUL
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_FREE        0x10cUL
+	#define HWRM_CFA_PAIR_ALLOC                       0x10dUL
+	#define HWRM_CFA_PAIR_FREE                        0x10eUL
+	#define HWRM_CFA_PAIR_INFO                        0x10fUL
+	#define HWRM_FW_IPC_MSG                           0x110UL
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_INFO        0x111UL
+	#define HWRM_CFA_REDIRECT_QUERY_TUNNEL_TYPE       0x112UL
+	#define HWRM_CFA_FLOW_AGING_TIMER_RESET           0x113UL
+	#define HWRM_CFA_FLOW_AGING_CFG                   0x114UL
+	#define HWRM_CFA_FLOW_AGING_QCFG                  0x115UL
+	#define HWRM_CFA_FLOW_AGING_QCAPS                 0x116UL
+	#define HWRM_CFA_CTX_MEM_RGTR                     0x117UL
+	#define HWRM_CFA_CTX_MEM_UNRGTR                   0x118UL
+	#define HWRM_CFA_CTX_MEM_QCTX                     0x119UL
+	#define HWRM_CFA_CTX_MEM_QCAPS                    0x11aUL
+	#define HWRM_CFA_COUNTER_QCAPS                    0x11bUL
+	#define HWRM_CFA_COUNTER_CFG                      0x11cUL
+	#define HWRM_CFA_COUNTER_QCFG                     0x11dUL
+	#define HWRM_CFA_COUNTER_QSTATS                   0x11eUL
+	#define HWRM_CFA_TCP_FLAG_PROCESS_QCFG            0x11fUL
+	#define HWRM_CFA_EEM_QCAPS                        0x120UL
+	#define HWRM_CFA_EEM_CFG                          0x121UL
+	#define HWRM_CFA_EEM_QCFG                         0x122UL
+	#define HWRM_CFA_EEM_OP                           0x123UL
+	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
+	#define HWRM_CFA_TFLIB                            0x125UL
+	#define HWRM_CFA_LAG_GROUP_MEMBER_RGTR            0x126UL
+	#define HWRM_CFA_LAG_GROUP_MEMBER_UNRGTR          0x127UL
+	#define HWRM_CFA_TLS_FILTER_ALLOC                 0x128UL
+	#define HWRM_CFA_TLS_FILTER_FREE                  0x129UL
+	#define HWRM_CFA_RELEASE_AFM_FUNC                 0x12aUL
+	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
+	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
+	#define HWRM_ENGINE_CKV_CKEK_DELETE               0x130UL
+	#define HWRM_ENGINE_CKV_KEY_ADD                   0x131UL
+	#define HWRM_ENGINE_CKV_KEY_DELETE                0x132UL
+	#define HWRM_ENGINE_CKV_FLUSH                     0x133UL
+	#define HWRM_ENGINE_CKV_RNG_GET                   0x134UL
+	#define HWRM_ENGINE_CKV_KEY_GEN                   0x135UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_CFG             0x136UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_QCFG            0x137UL
+	#define HWRM_ENGINE_QG_CONFIG_QUERY               0x13cUL
+	#define HWRM_ENGINE_QG_QUERY                      0x13dUL
+	#define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL
+	#define HWRM_ENGINE_QG_METER_PROFILE_QUERY        0x13fUL
+	#define HWRM_ENGINE_QG_METER_PROFILE_ALLOC        0x140UL
+	#define HWRM_ENGINE_QG_METER_PROFILE_FREE         0x141UL
+	#define HWRM_ENGINE_QG_METER_QUERY                0x142UL
+	#define HWRM_ENGINE_QG_METER_BIND                 0x143UL
+	#define HWRM_ENGINE_QG_METER_UNBIND               0x144UL
+	#define HWRM_ENGINE_QG_FUNC_BIND                  0x145UL
+	#define HWRM_ENGINE_SG_CONFIG_QUERY               0x146UL
+	#define HWRM_ENGINE_SG_QUERY                      0x147UL
+	#define HWRM_ENGINE_SG_METER_QUERY                0x148UL
+	#define HWRM_ENGINE_SG_METER_CONFIG               0x149UL
+	#define HWRM_ENGINE_SG_QG_BIND                    0x14aUL
+	#define HWRM_ENGINE_QG_SG_UNBIND                  0x14bUL
+	#define HWRM_ENGINE_CONFIG_QUERY                  0x154UL
+	#define HWRM_ENGINE_STATS_CONFIG                  0x155UL
+	#define HWRM_ENGINE_STATS_CLEAR                   0x156UL
+	#define HWRM_ENGINE_STATS_QUERY                   0x157UL
+	#define HWRM_ENGINE_STATS_QUERY_CONTINUOUS_ERROR  0x158UL
+	#define HWRM_ENGINE_RQ_ALLOC                      0x15eUL
+	#define HWRM_ENGINE_RQ_FREE                       0x15fUL
+	#define HWRM_ENGINE_CQ_ALLOC                      0x160UL
+	#define HWRM_ENGINE_CQ_FREE                       0x161UL
+	#define HWRM_ENGINE_NQ_ALLOC                      0x162UL
+	#define HWRM_ENGINE_NQ_FREE                       0x163UL
+	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
+	#define HWRM_ENGINE_FUNC_QCFG                     0x165UL
+	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
+	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
+	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
+	#define HWRM_FUNC_BACKING_STORE_CFG               0x193UL
+	#define HWRM_FUNC_BACKING_STORE_QCFG              0x194UL
+	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
+	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
+	#define HWRM_FUNC_HOST_PF_IDS_QUERY               0x197UL
+	#define HWRM_FUNC_QSTATS_EXT                      0x198UL
+	#define HWRM_STAT_EXT_CTX_QUERY                   0x199UL
+	#define HWRM_FUNC_SPD_CFG                         0x19aUL
+	#define HWRM_FUNC_SPD_QCFG                        0x19bUL
+	#define HWRM_FUNC_PTP_PIN_QCFG                    0x19cUL
+	#define HWRM_FUNC_PTP_PIN_CFG                     0x19dUL
+	#define HWRM_FUNC_PTP_CFG                         0x19eUL
+	#define HWRM_FUNC_PTP_TS_QUERY                    0x19fUL
+	#define HWRM_FUNC_PTP_EXT_CFG                     0x1a0UL
+	#define HWRM_FUNC_PTP_EXT_QCFG                    0x1a1UL
+	#define HWRM_FUNC_KEY_CTX_ALLOC                   0x1a2UL
+	#define HWRM_FUNC_BACKING_STORE_CFG_V2            0x1a3UL
+	#define HWRM_FUNC_BACKING_STORE_QCFG_V2           0x1a4UL
+	#define HWRM_FUNC_DBR_PACING_CFG                  0x1a5UL
+	#define HWRM_FUNC_DBR_PACING_QCFG                 0x1a6UL
+	#define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT      0x1a7UL
+	#define HWRM_FUNC_BACKING_STORE_QCAPS_V2          0x1a8UL
+	#define HWRM_FUNC_DBR_PACING_NQLIST_QUERY         0x1a9UL
+	#define HWRM_FUNC_DBR_RECOVERY_COMPLETED          0x1aaUL
+	#define HWRM_FUNC_SYNCE_CFG                       0x1abUL
+	#define HWRM_FUNC_SYNCE_QCFG                      0x1acUL
+	#define HWRM_FUNC_KEY_CTX_FREE                    0x1adUL
+	#define HWRM_FUNC_LAG_MODE_CFG                    0x1aeUL
+	#define HWRM_FUNC_LAG_MODE_QCFG                   0x1afUL
+	#define HWRM_FUNC_LAG_CREATE                      0x1b0UL
+	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
+	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
+	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
+	#define HWRM_FUNC_TTX_PACING_RATE_PROF_QUERY      0x1c3UL
+	#define HWRM_FUNC_TTX_PACING_RATE_QUERY           0x1c4UL
+	#define HWRM_SELFTEST_QLIST                       0x200UL
+	#define HWRM_SELFTEST_EXEC                        0x201UL
+	#define HWRM_SELFTEST_IRQ                         0x202UL
+	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA        0x203UL
+	#define HWRM_PCIE_QSTATS                          0x204UL
+	#define HWRM_MFG_FRU_WRITE_CONTROL                0x205UL
+	#define HWRM_MFG_TIMERS_QUERY                     0x206UL
+	#define HWRM_MFG_OTP_CFG                          0x207UL
+	#define HWRM_MFG_OTP_QCFG                         0x208UL
+	#define HWRM_MFG_HDMA_TEST                        0x209UL
+	#define HWRM_MFG_FRU_EEPROM_WRITE                 0x20aUL
+	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
+	#define HWRM_MFG_SOC_IMAGE                        0x20cUL
+	#define HWRM_MFG_SOC_QSTATUS                      0x20dUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_FINALIZE     0x20eUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_READ         0x20fUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_HEALTH       0x210UL
+	#define HWRM_MFG_PRVSN_EXPORT_CSR                 0x211UL
+	#define HWRM_MFG_PRVSN_IMPORT_CERT                0x212UL
+	#define HWRM_MFG_PRVSN_GET_STATE                  0x213UL
+	#define HWRM_MFG_GET_NVM_MEASUREMENT              0x214UL
+	#define HWRM_MFG_PSOC_QSTATUS                     0x215UL
+	#define HWRM_MFG_SELFTEST_QLIST                   0x216UL
+	#define HWRM_MFG_SELFTEST_EXEC                    0x217UL
+	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
+	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
+	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
+	#define HWRM_MFG_TESTS                            0x21bUL
+	#define HWRM_MFG_WRITE_CERT_NVM                   0x21cUL
+	#define HWRM_PORT_POE_CFG                         0x230UL
+	#define HWRM_PORT_POE_QCFG                        0x231UL
+	#define HWRM_PORT_PHY_FDRSTAT                     0x232UL
+	#define HWRM_UDCC_QCAPS                           0x258UL
+	#define HWRM_UDCC_CFG                             0x259UL
+	#define HWRM_UDCC_QCFG                            0x25aUL
+	#define HWRM_UDCC_SESSION_CFG                     0x25bUL
+	#define HWRM_UDCC_SESSION_QCFG                    0x25cUL
+	#define HWRM_UDCC_SESSION_QUERY                   0x25dUL
+	#define HWRM_UDCC_COMP_CFG                        0x25eUL
+	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
+	#define HWRM_UDCC_COMP_QUERY                      0x260UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS            0x261UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_CFG              0x262UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG             0x263UL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_QCFG              0x264UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_QCFG              0x265UL
+	#define HWRM_TF                                   0x2bcUL
+	#define HWRM_TF_VERSION_GET                       0x2bdUL
+	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
+	#define HWRM_TF_SESSION_REGISTER                  0x2c8UL
+	#define HWRM_TF_SESSION_UNREGISTER                0x2c9UL
+	#define HWRM_TF_SESSION_CLOSE                     0x2caUL
+	#define HWRM_TF_SESSION_QCFG                      0x2cbUL
+	#define HWRM_TF_SESSION_RESC_QCAPS                0x2ccUL
+	#define HWRM_TF_SESSION_RESC_ALLOC                0x2cdUL
+	#define HWRM_TF_SESSION_RESC_FREE                 0x2ceUL
+	#define HWRM_TF_SESSION_RESC_FLUSH                0x2cfUL
+	#define HWRM_TF_SESSION_RESC_INFO                 0x2d0UL
+	#define HWRM_TF_SESSION_HOTUP_STATE_SET           0x2d1UL
+	#define HWRM_TF_SESSION_HOTUP_STATE_GET           0x2d2UL
+	#define HWRM_TF_TBL_TYPE_GET                      0x2daUL
+	#define HWRM_TF_TBL_TYPE_SET                      0x2dbUL
+	#define HWRM_TF_TBL_TYPE_BULK_GET                 0x2dcUL
+	#define HWRM_TF_EM_INSERT                         0x2eaUL
+	#define HWRM_TF_EM_DELETE                         0x2ebUL
+	#define HWRM_TF_EM_HASH_INSERT                    0x2ecUL
+	#define HWRM_TF_EM_MOVE                           0x2edUL
+	#define HWRM_TF_TCAM_SET                          0x2f8UL
+	#define HWRM_TF_TCAM_GET                          0x2f9UL
+	#define HWRM_TF_TCAM_MOVE                         0x2faUL
+	#define HWRM_TF_TCAM_FREE                         0x2fbUL
+	#define HWRM_TF_GLOBAL_CFG_SET                    0x2fcUL
+	#define HWRM_TF_GLOBAL_CFG_GET                    0x2fdUL
+	#define HWRM_TF_IF_TBL_SET                        0x2feUL
+	#define HWRM_TF_IF_TBL_GET                        0x2ffUL
+	#define HWRM_TF_RESC_USAGE_SET                    0x300UL
+	#define HWRM_TF_RESC_USAGE_QUERY                  0x301UL
+	#define HWRM_TF_TBL_TYPE_ALLOC                    0x302UL
+	#define HWRM_TF_TBL_TYPE_FREE                     0x303UL
+	#define HWRM_TFC_TBL_SCOPE_QCAPS                  0x380UL
+	#define HWRM_TFC_TBL_SCOPE_ID_ALLOC               0x381UL
+	#define HWRM_TFC_TBL_SCOPE_CONFIG                 0x382UL
+	#define HWRM_TFC_TBL_SCOPE_DECONFIG               0x383UL
+	#define HWRM_TFC_TBL_SCOPE_FID_ADD                0x384UL
+	#define HWRM_TFC_TBL_SCOPE_FID_REM                0x385UL
+	#define HWRM_TFC_TBL_SCOPE_POOL_ALLOC             0x386UL
+	#define HWRM_TFC_TBL_SCOPE_POOL_FREE              0x387UL
+	#define HWRM_TFC_SESSION_ID_ALLOC                 0x388UL
+	#define HWRM_TFC_SESSION_FID_ADD                  0x389UL
+	#define HWRM_TFC_SESSION_FID_REM                  0x38aUL
+	#define HWRM_TFC_IDENT_ALLOC                      0x38bUL
+	#define HWRM_TFC_IDENT_FREE                       0x38cUL
+	#define HWRM_TFC_IDX_TBL_ALLOC                    0x38dUL
+	#define HWRM_TFC_IDX_TBL_ALLOC_SET                0x38eUL
+	#define HWRM_TFC_IDX_TBL_SET                      0x38fUL
+	#define HWRM_TFC_IDX_TBL_GET                      0x390UL
+	#define HWRM_TFC_IDX_TBL_FREE                     0x391UL
+	#define HWRM_TFC_GLOBAL_ID_ALLOC                  0x392UL
+	#define HWRM_TFC_TCAM_SET                         0x393UL
+	#define HWRM_TFC_TCAM_GET                         0x394UL
+	#define HWRM_TFC_TCAM_ALLOC                       0x395UL
+	#define HWRM_TFC_TCAM_ALLOC_SET                   0x396UL
+	#define HWRM_TFC_TCAM_FREE                        0x397UL
+	#define HWRM_TFC_IF_TBL_SET                       0x398UL
+	#define HWRM_TFC_IF_TBL_GET                       0x399UL
+	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
+	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
+	#define HWRM_TFC_GLOBAL_ID_FREE                   0x39cUL
+	#define HWRM_TFC_TCAM_PRI_UPDATE                  0x39dUL
+	#define HWRM_TFC_HOT_UPGRADE_PROCESS              0x3a0UL
+	#define HWRM_SV                                   0x400UL
+	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
+	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
+	#define HWRM_DBG_READ_DIRECT                      0xff10UL
+	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
+	#define HWRM_DBG_WRITE_DIRECT                     0xff12UL
+	#define HWRM_DBG_WRITE_INDIRECT                   0xff13UL
+	#define HWRM_DBG_DUMP                             0xff14UL
+	#define HWRM_DBG_ERASE_NVM                        0xff15UL
+	#define HWRM_DBG_CFG                              0xff16UL
+	#define HWRM_DBG_COREDUMP_LIST                    0xff17UL
+	#define HWRM_DBG_COREDUMP_INITIATE                0xff18UL
+	#define HWRM_DBG_COREDUMP_RETRIEVE                0xff19UL
+	#define HWRM_DBG_FW_CLI                           0xff1aUL
+	#define HWRM_DBG_I2C_CMD                          0xff1bUL
+	#define HWRM_DBG_RING_INFO_GET                    0xff1cUL
+	#define HWRM_DBG_CRASHDUMP_HEADER                 0xff1dUL
+	#define HWRM_DBG_CRASHDUMP_ERASE                  0xff1eUL
+	#define HWRM_DBG_DRV_TRACE                        0xff1fUL
+	#define HWRM_DBG_QCAPS                            0xff20UL
+	#define HWRM_DBG_QCFG                             0xff21UL
+	#define HWRM_DBG_CRASHDUMP_MEDIUM_CFG             0xff22UL
+	#define HWRM_DBG_USEQ_ALLOC                       0xff23UL
+	#define HWRM_DBG_USEQ_FREE                        0xff24UL
+	#define HWRM_DBG_USEQ_FLUSH                       0xff25UL
+	#define HWRM_DBG_USEQ_QCAPS                       0xff26UL
+	#define HWRM_DBG_USEQ_CW_CFG                      0xff27UL
+	#define HWRM_DBG_USEQ_SCHED_CFG                   0xff28UL
+	#define HWRM_DBG_USEQ_RUN                         0xff29UL
+	#define HWRM_DBG_USEQ_DELIVERY_REQ                0xff2aUL
+	#define HWRM_DBG_USEQ_RESP_HDR                    0xff2bUL
+	#define HWRM_DBG_COREDUMP_CAPTURE                 0xff2cUL
+	#define HWRM_DBG_PTRACE                           0xff2dUL
+	#define HWRM_DBG_SIM_CABLE_STATE                  0xff2eUL
+	#define HWRM_DBG_TOKEN_QUERY_AUTH_IDS             0xff2fUL
+	#define HWRM_DBG_TOKEN_CFG                        0xff30UL
+	#define HWRM_NVM_GET_VPD_FIELD_INFO               0xffeaUL
+	#define HWRM_NVM_SET_VPD_FIELD_INFO               0xffebUL
+	#define HWRM_NVM_DEFRAG                           0xffecUL
+	#define HWRM_NVM_REQ_ARBITRATION                  0xffedUL
+	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
+	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
+	#define HWRM_NVM_FLUSH                            0xfff0UL
+	#define HWRM_NVM_GET_VARIABLE                     0xfff1UL
+	#define HWRM_NVM_SET_VARIABLE                     0xfff2UL
+	#define HWRM_NVM_INSTALL_UPDATE                   0xfff3UL
+	#define HWRM_NVM_MODIFY                           0xfff4UL
+	#define HWRM_NVM_VERIFY_UPDATE                    0xfff5UL
+	#define HWRM_NVM_GET_DEV_INFO                     0xfff6UL
+	#define HWRM_NVM_ERASE_DIR_ENTRY                  0xfff7UL
+	#define HWRM_NVM_MOD_DIR_ENTRY                    0xfff8UL
+	#define HWRM_NVM_FIND_DIR_ENTRY                   0xfff9UL
+	#define HWRM_NVM_GET_DIR_ENTRIES                  0xfffaUL
+	#define HWRM_NVM_GET_DIR_INFO                     0xfffbUL
+	#define HWRM_NVM_RAW_DUMP                         0xfffcUL
+	#define HWRM_NVM_READ                             0xfffdUL
+	#define HWRM_NVM_WRITE                            0xfffeUL
+	#define HWRM_NVM_RAW_WRITE_BLK                    0xffffUL
+	#define HWRM_LAST                                HWRM_NVM_RAW_WRITE_BLK
+	__le16	unused_0[3];
+};
+
+/* ret_codes (size:64b/8B) */
+struct ret_codes {
+	__le16	error_code;
+	#define HWRM_ERR_CODE_SUCCESS                      0x0UL
+	#define HWRM_ERR_CODE_FAIL                         0x1UL
+	#define HWRM_ERR_CODE_INVALID_PARAMS               0x2UL
+	#define HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED       0x3UL
+	#define HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR         0x4UL
+	#define HWRM_ERR_CODE_INVALID_FLAGS                0x5UL
+	#define HWRM_ERR_CODE_INVALID_ENABLES              0x6UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_TLV              0x7UL
+	#define HWRM_ERR_CODE_NO_BUFFER                    0x8UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR       0x9UL
+	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS           0xaUL
+	#define HWRM_ERR_CODE_HOT_RESET_FAIL               0xbUL
+	#define HWRM_ERR_CODE_NO_FLOW_COUNTER_DURING_ALLOC 0xcUL
+	#define HWRM_ERR_CODE_KEY_HASH_COLLISION           0xdUL
+	#define HWRM_ERR_CODE_KEY_ALREADY_EXISTS           0xeUL
+	#define HWRM_ERR_CODE_HWRM_ERROR                   0xfUL
+	#define HWRM_ERR_CODE_BUSY                         0x10UL
+	#define HWRM_ERR_CODE_RESOURCE_LOCKED              0x11UL
+	#define HWRM_ERR_CODE_PF_UNAVAILABLE               0x12UL
+	#define HWRM_ERR_CODE_ENTITY_NOT_PRESENT           0x13UL
+	#define HWRM_ERR_CODE_SECURE_SOC_ERROR             0x14UL
+	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
+	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
+	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
+	#define HWRM_ERR_CODE_LAST                        HWRM_ERR_CODE_CMD_NOT_SUPPORTED
+	__le16	unused_0[3];
+};
+
+/* hwrm_err_output (size:128b/16B) */
+struct hwrm_err_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	opaque_0;
+	__le16	opaque_1;
+	u8	cmd_err;
+	u8	valid;
+};
+#define HWRM_NA_SIGNATURE ((__le32)(-1))
+#define HWRM_MAX_REQ_LEN 128
+#define HWRM_MAX_RESP_LEN 704
+#define HW_HASH_INDEX_SIZE 0x80
+#define HW_HASH_KEY_SIZE 40
+#define HWRM_RESP_VALID_KEY 1
+#define HWRM_TARGET_ID_BONO 0xFFF8
+#define HWRM_TARGET_ID_KONG 0xFFF9
+#define HWRM_TARGET_ID_APE 0xFFFA
+#define HWRM_TARGET_ID_TOOLS 0xFFFD
+#define HWRM_VERSION_MAJOR 1
+#define HWRM_VERSION_MINOR 10
+#define HWRM_VERSION_UPDATE 3
+#define HWRM_VERSION_RSVD 133
+#define HWRM_VERSION_STR "1.10.3.133"
+
+/* hwrm_ver_get_input (size:192b/24B) */
+struct hwrm_ver_get_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	hwrm_intf_maj;
+	u8	hwrm_intf_min;
+	u8	hwrm_intf_upd;
+	u8	unused_0[5];
+};
+
+/* hwrm_ver_get_output (size:1408b/176B) */
+struct hwrm_ver_get_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	hwrm_intf_maj_8b;
+	u8	hwrm_intf_min_8b;
+	u8	hwrm_intf_upd_8b;
+	u8	hwrm_intf_rsvd_8b;
+	u8	hwrm_fw_maj_8b;
+	u8	hwrm_fw_min_8b;
+	u8	hwrm_fw_bld_8b;
+	u8	hwrm_fw_rsvd_8b;
+	u8	mgmt_fw_maj_8b;
+	u8	mgmt_fw_min_8b;
+	u8	mgmt_fw_bld_8b;
+	u8	mgmt_fw_rsvd_8b;
+	u8	netctrl_fw_maj_8b;
+	u8	netctrl_fw_min_8b;
+	u8	netctrl_fw_bld_8b;
+	u8	netctrl_fw_rsvd_8b;
+	__le32	dev_caps_cfg;
+	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_FW_UPD_SUPPORTED                  0x1UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FW_DCBX_AGENT_SUPPORTED                  0x2UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED                      0x4UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED                       0x8UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED                   0x10UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED              0x20UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_L2_FILTER_TYPES_ROCE_OR_L2_SUPPORTED     0x40UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_VIRTIO_VSWITCH_OFFLOAD_SUPPORTED         0x80UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED                     0x100UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_AGING_SUPPORTED                     0x200UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED                      0x2000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED                    0x4000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE                      0x8000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE                       0x10000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_DEBUG_TOKEN_SUPPORTED                    0x20000UL
+	u8	roce_fw_maj_8b;
+	u8	roce_fw_min_8b;
+	u8	roce_fw_bld_8b;
+	u8	roce_fw_rsvd_8b;
+	char	hwrm_fw_name[16];
+	char	mgmt_fw_name[16];
+	char	netctrl_fw_name[16];
+	char	active_pkg_name[16];
+	char	roce_fw_name[16];
+	__le16	chip_num;
+	u8	chip_rev;
+	u8	chip_metal;
+	u8	chip_bond_id;
+	u8	chip_platform_type;
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_ASIC      0x0UL
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_FPGA      0x1UL
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM 0x2UL
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_LAST     VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM
+	__le16	max_req_win_len;
+	__le16	max_resp_len;
+	__le16	def_req_timeout;
+	u8	flags;
+	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY                   0x1UL
+	#define VER_GET_RESP_FLAGS_EXT_VER_AVAIL                 0x2UL
+	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY_BACKING_STORE     0x4UL
+	u8	unused_0[2];
+	u8	always_1;
+	__le16	hwrm_intf_major;
+	__le16	hwrm_intf_minor;
+	__le16	hwrm_intf_build;
+	__le16	hwrm_intf_patch;
+	__le16	hwrm_fw_major;
+	__le16	hwrm_fw_minor;
+	__le16	hwrm_fw_build;
+	__le16	hwrm_fw_patch;
+	__le16	mgmt_fw_major;
+	__le16	mgmt_fw_minor;
+	__le16	mgmt_fw_build;
+	__le16	mgmt_fw_patch;
+	__le16	netctrl_fw_major;
+	__le16	netctrl_fw_minor;
+	__le16	netctrl_fw_build;
+	__le16	netctrl_fw_patch;
+	__le16	roce_fw_major;
+	__le16	roce_fw_minor;
+	__le16	roce_fw_build;
+	__le16	roce_fw_patch;
+	__le16	max_ext_req_len;
+	__le16	max_req_timeout;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* eject_cmpl (size:128b/16B) */
+struct eject_cmpl {
+	__le16	type;
+	#define EJECT_CMPL_TYPE_MASK       0x3fUL
+	#define EJECT_CMPL_TYPE_SFT        0
+	#define EJECT_CMPL_TYPE_STAT_EJECT   0x1aUL
+	#define EJECT_CMPL_TYPE_LAST        EJECT_CMPL_TYPE_STAT_EJECT
+	#define EJECT_CMPL_FLAGS_MASK      0xffc0UL
+	#define EJECT_CMPL_FLAGS_SFT       6
+	#define EJECT_CMPL_FLAGS_ERROR      0x40UL
+	__le16	len;
+	__le32	opaque;
+	__le16	v;
+	#define EJECT_CMPL_V                              0x1UL
+	#define EJECT_CMPL_ERRORS_MASK                    0xfffeUL
+	#define EJECT_CMPL_ERRORS_SFT                     1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_MASK        0xeUL
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_SFT         1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER     (0x0UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT   (0x1UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT    (0x3UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH         (0x5UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_LAST         EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH
+	__le16	reserved16;
+	__le32	unused_2;
+};
+
+/* hwrm_cmpl (size:128b/16B) */
+struct hwrm_cmpl {
+	__le16	type;
+	#define CMPL_TYPE_MASK     0x3fUL
+	#define CMPL_TYPE_SFT      0
+	#define CMPL_TYPE_HWRM_DONE  0x20UL
+	#define CMPL_TYPE_LAST      CMPL_TYPE_HWRM_DONE
+	__le16	sequence_id;
+	__le32	unused_1;
+	__le32	v;
+	#define CMPL_V     0x1UL
+	__le32	unused_3;
+};
+
+/* hwrm_fwd_req_cmpl (size:128b/16B) */
+struct hwrm_fwd_req_cmpl {
+	__le16	req_len_type;
+	#define FWD_REQ_CMPL_TYPE_MASK        0x3fUL
+	#define FWD_REQ_CMPL_TYPE_SFT         0
+	#define FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ  0x22UL
+	#define FWD_REQ_CMPL_TYPE_LAST         FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ
+	#define FWD_REQ_CMPL_REQ_LEN_MASK     0xffc0UL
+	#define FWD_REQ_CMPL_REQ_LEN_SFT      6
+	__le16	source_id;
+	__le32	unused0;
+	__le32	req_buf_addr_v[2];
+	#define FWD_REQ_CMPL_V                0x1UL
+	#define FWD_REQ_CMPL_REQ_BUF_ADDR_MASK 0xfffffffeUL
+	#define FWD_REQ_CMPL_REQ_BUF_ADDR_SFT 1
+};
+
+/* hwrm_fwd_resp_cmpl (size:128b/16B) */
+struct hwrm_fwd_resp_cmpl {
+	__le16	type;
+	#define FWD_RESP_CMPL_TYPE_MASK         0x3fUL
+	#define FWD_RESP_CMPL_TYPE_SFT          0
+	#define FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP  0x24UL
+	#define FWD_RESP_CMPL_TYPE_LAST          FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP
+	__le16	source_id;
+	__le16	resp_len;
+	__le16	unused_1;
+	__le32	resp_buf_addr_v[2];
+	#define FWD_RESP_CMPL_V                 0x1UL
+	#define FWD_RESP_CMPL_RESP_BUF_ADDR_MASK 0xfffffffeUL
+	#define FWD_RESP_CMPL_RESP_BUF_ADDR_SFT 1
+};
+
+/* hwrm_async_event_cmpl (size:128b/16B) */
+struct hwrm_async_event_cmpl {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_TYPE_LAST             ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE              0x0UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_MTU_CHANGE                 0x1UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE               0x2UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE               0x3UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED           0x4UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_NOT_ALLOWED      0x5UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE           0x6UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE             0x7UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY                    0x8UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY                  0x9UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG                0xaUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD                0x10UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD                  0x11UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT             0x12UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD                  0x20UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_LOAD                    0x21UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_FLR                          0x30UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE              0x31UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE        0x32UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE                   0x33UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE                 0x34UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE             0x35UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_FLOW_AGED                    0x36UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION              0x37UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ             0x38UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE            0x39UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE          0x3aUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE                 0x3bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE                  0x3cUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_DEFAULT_VNIC_CHANGE       0x3dUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE        0x3eUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_QUIESCE_DONE                    0x3fUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE               0x40UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE         0x41UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST                    0x42UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE                      0x43UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP                   0x44UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT                    0x45UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD       0x46UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RSS_CHANGE                      0x47UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_NQ_UPDATE       0x48UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR                       0x4aUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER                0x4cUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE                0x4dUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE         0x4eUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE                  0x4fUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP                   0x50UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ADPTV_QOS                       0x51UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x52UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_V          0x1UL
+	#define ASYNC_EVENT_CMPL_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_link_status_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_link_status_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE 0x0UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LAST              ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE     0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_DOWN  0x0UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP    0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_LAST ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_MASK       0xeUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT        1
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK    0xffff0UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT     4
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK      0xff00000UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT       20
+};
+
+/* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */
+struct hwrm_async_event_cmpl_port_conn_not_allowed {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_LAST             ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED 0x4UL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK                 0xffffUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_SFT                  0
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_MASK      0xff0000UL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_SFT       16
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_NONE        (0x0UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_DISABLETX   (0x1UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_WARNINGMSG  (0x2UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN     (0x3UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_LAST       ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN
+};
+
+/* hwrm_async_event_cmpl_link_speed_cfg_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_link_speed_cfg_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE 0x6UL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_MASK                     0xffffUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_SFT                      0
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_SUPPORTED_LINK_SPEEDS_CHANGE     0x10000UL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_ILLEGAL_LINK_SPEED_CFG           0x20000UL
+};
+
+/* hwrm_async_event_cmpl_reset_notify (size:128b/16B) */
+struct hwrm_async_event_cmpl_reset_notify {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_LAST             ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY 0x8UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_LAST        ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_MASK                  0xffUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_SFT                   0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_STOP_TX_QUEUE    0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN           0x2UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_LAST                   ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK                    0xff00UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_SFT                     8
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MANAGEMENT_RESET_REQUEST  (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL        (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL    (0x3UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET                (0x4UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION             (0x5UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST                     ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK           0xffff0000UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
+};
+
+/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_recovery {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST          ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK                 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT                  0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC           0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
+};
+
+/* hwrm_async_event_cmpl_ring_monitor_msg (size:128b/16B) */
+struct hwrm_async_event_cmpl_ring_monitor_msg {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_LAST             ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG 0xaUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_LAST            ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_SFT 0
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_TX    0x0UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX    0x1UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL  0x2UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_LAST ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_vf_cfg_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE 0x33UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_LAST         ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MTU_CHANGE                0x1UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MRU_CHANGE                0x2UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_MAC_ADDR_CHANGE      0x4UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_VLAN_CHANGE          0x8UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE     0x10UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TF_OWNERSHIP_RELEASE      0x20UL
+};
+
+/* hwrm_async_event_cmpl_default_vnic_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_default_vnic_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_MASK         0xffc0UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_SFT          6
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION 0x35UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_LAST                   ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_MASK          0x3UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_SFT           0
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_ALLOC  0x1UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE   0x2UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_LAST           ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_MASK                   0x3fcUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_SFT                    2
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_MASK                   0x3fffc00UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_SFT                    10
+};
+
+/* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */
+struct hwrm_async_event_cmpl_hw_flow_aged {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_LAST             ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED 0x36UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_MASK       0x7fffffffUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_SFT        0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION     0x80000000UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_RX    (0x0UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX    (0x1UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_LAST ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_req (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_req {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_LAST               ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_done (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_done {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_LAST                ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
+};
+
+/* hwrm_async_event_cmpl_deferred_response (size:128b/16B) */
+struct hwrm_async_event_cmpl_deferred_response {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE 0x40UL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_echo_request (size:128b/16B) */
+struct hwrm_async_event_cmpl_echo_request {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_LAST             ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST 0x42UL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */
+struct hwrm_async_event_cmpl_phc_update {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST             ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST      ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK   0xffff0000UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT    16
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK          0xfUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT           0
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER      0x1UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY   0x2UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER    0x3UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE  0x4UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST           ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK   0xffff0UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT    4
+};
+
+/* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */
+struct hwrm_async_event_cmpl_pps_timestamp {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_LAST             ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP 0x44UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_LAST         ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE              0x1UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL       0x0UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL       0x1UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_LAST          ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_MASK         0xeUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_SFT          1
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_MASK 0xffff0UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_SFT 4
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_V          0x1UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_MASK 0xffffffffUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_SFT 0
+};
+
+/* hwrm_async_event_cmpl_error_report (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_SFT 0
+};
+
+/* hwrm_async_event_cmpl_dbg_buf_producer (size:128b/16B) */
+struct hwrm_async_event_cmpl_dbg_buf_producer {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_LAST             ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_LAST            ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_MASK 0xffffffffUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_MASK               0xffffUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SFT                0
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT_TRACE            0x0UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT2_TRACE           0x1UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT_TRACE            0x2UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT2_TRACE           0x3UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP0_TRACE          0x4UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_L2_HWRM_TRACE        0x5UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ROCE_HWRM_TRACE      0x6UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA0_TRACE            0x7UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA1_TRACE            0x8UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA2_TRACE            0x9UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP1_TRACE          0xaUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE  0xbUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ERR_QPC_TRACE        0xcUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_LAST                ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ERR_QPC_TRACE
+};
+
+/* hwrm_async_event_cmpl_hwrm_error (size:128b/16B) */
+struct hwrm_async_event_cmpl_hwrm_error {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_LAST             ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR 0xffUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_LAST      ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_MASK    0xffUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_SFT     0
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_WARNING   0x0UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_NONFATAL  0x1UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL     0x2UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_LAST     ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_V          0x1UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP     0x1UL
+};
+
+/* hwrm_async_event_cmpl_error_report_base (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_base {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT                         0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED                      0x0UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM                   0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL                0x2UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM                           0x3UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD       0x4UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD             0x5UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUP_UDCC_SES                  0x7UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DB_DROP                       0x8UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MD_TEMP                       0x9UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_VNIC_ERR                      0xaUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_VNIC_ERR
+};
+
+/* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_pause_storm {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_MASK       0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_SFT        0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM  0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM
+};
+
+/* hwrm_async_event_cmpl_error_report_invalid_signal (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_invalid_signal {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_SFT           0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL  0x2UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL
+};
+
+/* hwrm_async_event_cmpl_error_report_nvm (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_nvm {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_MASK 0xffffffffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_MASK     0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_SFT      0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR  0x3UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_LAST      ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK   0xff00UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_SFT    8
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_WRITE    (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE    (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST    ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE
+};
+
+/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK                   0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT                    0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD  0x4UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST                    ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_MASK                        0xffffff00UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_SFT                         8
+};
+
+/* hwrm_async_event_cmpl_error_report_thermal (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_thermal {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_MASK  0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_SFT   0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_MASK 0xff00UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_SFT 8
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_SFT           0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT   0x5UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_MASK      0x700UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SFT       8
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_WARN        (0x0UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_CRITICAL    (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_FATAL       (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN    (0x3UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR           0x800UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_DECREASING  (0x0UL << 11)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING  (0x1UL << 11)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING
+};
+
+/* hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_SFT                         0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
+};
+
+/* hwrm_func_reset_input (size:192b/24B) */
+struct hwrm_func_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_RESET_REQ_ENABLES_VF_ID_VALID     0x1UL
+	__le16	vf_id;
+	u8	func_reset_level;
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETALL      0x0UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETME       0x1UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETCHILDREN 0x2UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF       0x3UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_LAST         FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF
+	u8	unused_0;
+};
+
+/* hwrm_func_reset_output (size:128b/16B) */
+struct hwrm_func_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_getfid_input (size:192b/24B) */
+struct hwrm_func_getfid_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_GETFID_REQ_ENABLES_PCI_ID     0x1UL
+	__le16	pci_id;
+	u8	unused_0[2];
+};
+
+/* hwrm_func_getfid_output (size:128b/16B) */
+struct hwrm_func_getfid_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_func_vf_alloc_input (size:192b/24B) */
+struct hwrm_func_vf_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_VF_ALLOC_REQ_ENABLES_FIRST_VF_ID     0x1UL
+	__le16	first_vf_id;
+	__le16	num_vfs;
+};
+
+/* hwrm_func_vf_alloc_output (size:128b/16B) */
+struct hwrm_func_vf_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	first_vf_id;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_func_vf_free_input (size:192b/24B) */
+struct hwrm_func_vf_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_VF_FREE_REQ_ENABLES_FIRST_VF_ID     0x1UL
+	__le16	first_vf_id;
+	__le16	num_vfs;
+};
+
+/* hwrm_func_vf_free_output (size:128b/16B) */
+struct hwrm_func_vf_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_vf_cfg_input (size:576b/72B) */
+struct hwrm_func_vf_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_VF_CFG_REQ_ENABLES_MTU                      0x1UL
+	#define FUNC_VF_CFG_REQ_ENABLES_GUEST_VLAN               0x2UL
+	#define FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4UL
+	#define FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x8UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x10UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x20UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS             0x40UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS             0x80UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_L2_CTXS              0x100UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS                0x200UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x400UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x800UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_TX_KEY_CTXS     0x1000UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_RX_KEY_CTXS     0x2000UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_TX_KEY_CTXS     0x4000UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_RX_KEY_CTXS     0x8000UL
+	__le16	mtu;
+	__le16	guest_vlan;
+	__le16	async_event_cr;
+	u8	dflt_mac_addr[6];
+	__le32	flags;
+	#define FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST             0x1UL
+	#define FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST             0x2UL
+	#define FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST           0x4UL
+	#define FUNC_VF_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST     0x8UL
+	#define FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST       0x10UL
+	#define FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST       0x20UL
+	#define FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST           0x40UL
+	#define FUNC_VF_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST         0x80UL
+	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE       0x100UL
+	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE      0x200UL
+	__le16	num_rsscos_ctxs;
+	__le16	num_cmpl_rings;
+	__le16	num_tx_rings;
+	__le16	num_rx_rings;
+	__le16	num_l2_ctxs;
+	__le16	num_vnics;
+	__le16	num_stat_ctxs;
+	__le16	num_hw_ring_grps;
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
+	__le16	num_msix;
+	u8	unused[2];
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+};
+
+/* hwrm_func_vf_cfg_output (size:128b/16B) */
+struct hwrm_func_vf_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_qcaps_input (size:192b/24B) */
+struct hwrm_func_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_qcaps_output (size:1152b/144B) */
+struct hwrm_func_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	__le16	port_id;
+	__le32	flags;
+	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED                   0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING               0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                         0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED                     0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED                     0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED                0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED                     0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED                  0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED                   0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED               0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED                   0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED            0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED            0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED             0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED               0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED              0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED                  0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED                  0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED                    0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED           0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                         0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC                 0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE                     0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE                0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED                   0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD                    0x2000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_NOTIFY_VF_DEF_VNIC_CHNG_SUPPORTED     0x4000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED         0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_COREDUMP_CMD_SUPPORTED                0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_CRASHDUMP_CMD_SUPPORTED               0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PFC_WD_STATS_SUPPORTED                0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DBG_QCAPS_CMD_SUPPORTED               0x80000000UL
+	u8	mac_address[6];
+	__le16	max_rsscos_ctx;
+	__le16	max_cmpl_rings;
+	__le16	max_tx_rings;
+	__le16	max_rx_rings;
+	__le16	max_l2_ctxs;
+	__le16	max_vnics;
+	__le16	first_vf_id;
+	__le16	max_vfs;
+	__le16	max_stat_ctx;
+	__le32	max_encap_records;
+	__le32	max_decap_records;
+	__le32	max_tx_em_flows;
+	__le32	max_tx_wm_flows;
+	__le32	max_rx_em_flows;
+	__le32	max_rx_wm_flows;
+	__le32	max_mcast_filters;
+	__le32	max_flow_id;
+	__le32	max_hw_ring_grps;
+	__le16	max_sp_tx_rings;
+	__le16	max_msix_vfs;
+	__le32	flags_ext;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED                          0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED                         0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED                      0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT                        0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PROXY_MODE_SUPPORT                          0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_PROXY_SRC_INTF_OVERRIDE_SUPPORT          0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_SCHQ_SUPPORTED                              0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PPP_PUSH_MODE_SUPPORTED                     0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EVB_MODE_CFG_NOT_SUPPORTED                  0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_SOC_SPD_SUPPORTED                           0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED                      0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_FAST_RESET_CAPABLE                          0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_METADATA_CFG_CAPABLE                     0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_NVM_OPTION_ACTION_SUPPORTED                 0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_BD_METADATA_SUPPORTED                       0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECHO_REQUEST_SUPPORTED                      0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED                          0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PTM_SUPPORTED                           0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED                           0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_VF_CFG_ASYNC_FOR_PF_SUPPORTED               0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PARTITION_BW_SUPPORTED                      0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED                0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_KTLS_SUPPORTED                              0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL                             0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED                            0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP                            0x2000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED                             0x4000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED                              0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED                     0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED                        0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_HW_DBR_DROP_RECOV_SUPPORTED                 0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_DISABLE_CQ_OVERFLOW_DETECTION_SUPPORTED     0x80000000UL
+	u8	max_schqs;
+	u8	mpc_chnls_cap;
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE         0x1UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RCE         0x2UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA      0x4UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA      0x8UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
+	__le16	max_key_ctxs_alloc;
+	__le32	flags_ext2;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED      0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                        0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                       0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED              0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED        0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED               0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                     0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                       0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED               0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED              0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                      0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                 0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED                0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED           0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED           0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_CONCURRENT_KTLS_QUIC_SUPPORTED        0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_CROSS_TC_CAP_SUPPORTED           0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_CAP_SUPPORTED             0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_RESERVATION_SUPPORTED     0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DB_ERROR_STATS_SUPPORTED              0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED       0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDCC_SUPPORTED                        0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_SO_TXTIME_SUPPORTED          0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED      0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED         0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED                  0x2000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED          0x4000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED       0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED                   0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED             0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED            0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED               0x80000000UL
+	__le16	tunnel_disable_flag;
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NVGRE      0x4UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_L2GRE      0x8UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_GRE        0x10UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_IPINIP     0x20UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
+	__le16	xid_partition_cap;
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_TX_CK     0x1UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK     0x2UL
+	u8	device_serial_number[8];
+	__le16	ctxs_per_partition;
+	__le16	max_tso_segs;
+	__le32	roce_vf_max_av;
+	__le32	roce_vf_max_cq;
+	__le32	roce_vf_max_mrw;
+	__le32	roce_vf_max_qp;
+	__le32	roce_vf_max_srq;
+	__le32	roce_vf_max_gid;
+	__le32	flags_ext3;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP            0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER                 0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED            0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RX_RATE_PROFILE_SEL_SUPPORTED     0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_BIDI_OPT_SUPPORTED                0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED          0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_ROCE_VF_DYN_ALLOC_SUPPORT         0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_CHANGE_UDP_SRCPORT_SUPPORT        0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_PCIE_COMPLIANCE_SUPPORTED         0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MULTI_L2_DB_SUPPORTED             0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_PCIE_SECURE_ATS_SUPPORTED         0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MBUF_STATS_SUPPORTED              0x800UL
+	__le16	max_roce_vfs;
+	__le16	max_crypto_rx_flow_filters;
+	u8	unused_3[3];
+	u8	valid;
+};
+
+/* hwrm_func_qcfg_input (size:192b/24B) */
+struct hwrm_func_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_qcfg_output (size:1408b/176B) */
+struct hwrm_func_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	__le16	port_id;
+	__le16	vlan;
+	__le16	flags;
+	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_MAGICPKT_ENABLED     0x1UL
+	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED          0x2UL
+	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED        0x4UL
+	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED     0x8UL
+	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED        0x10UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST                   0x20UL
+	#define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF                   0x40UL
+	#define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED          0x80UL
+	#define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS      0x100UL
+	#define FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED            0x200UL
+	#define FUNC_QCFG_RESP_FLAGS_PPP_PUSH_MODE_ENABLED        0x400UL
+	#define FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED         0x800UL
+	#define FUNC_QCFG_RESP_FLAGS_FAST_RESET_ALLOWED           0x1000UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_ROOT                   0x2000UL
+	#define FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV            0x4000UL
+	#define FUNC_QCFG_RESP_FLAGS_ROCE_VNIC_ID_VALID           0x8000UL
+	u8	mac_address[6];
+	__le16	pci_id;
+	__le16	alloc_rsscos_ctx;
+	__le16	alloc_cmpl_rings;
+	__le16	alloc_tx_rings;
+	__le16	alloc_rx_rings;
+	__le16	alloc_l2_ctx;
+	__le16	alloc_vnics;
+	__le16	admin_mtu;
+	__le16	mru;
+	__le16	stat_ctx_id;
+	u8	port_partition_type;
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_SPF     0x0UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_MPFS    0x1UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0 0x2UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2 0x5UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_LAST   FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN
+	u8	port_pf_cnt;
+	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL
+	#define FUNC_QCFG_RESP_PORT_PF_CNT_LAST   FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL
+	__le16	dflt_vnic_id;
+	__le16	max_mtu_configured;
+	__le32	min_bw;
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	max_bw;
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	evb_mode;
+	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL
+	#define FUNC_QCFG_RESP_EVB_MODE_VEB    0x1UL
+	#define FUNC_QCFG_RESP_EVB_MODE_VEPA   0x2UL
+	#define FUNC_QCFG_RESP_EVB_MODE_LAST  FUNC_QCFG_RESP_EVB_MODE_VEPA
+	u8	options;
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST          FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT                    4
+	__le16	alloc_vfs;
+	__le32	alloc_mcast_filters;
+	__le32	alloc_hw_ring_grps;
+	__le16	alloc_sp_tx_rings;
+	__le16	alloc_stat_ctx;
+	__le16	alloc_msix;
+	__le16	registered_vfs;
+	__le16	l2_doorbell_bar_size_kb;
+	u8	active_endpoints;
+	u8	always_1;
+	__le32	reset_addr_poll;
+	__le16	legacy_l2_db_size_kb;
+	__le16	svif_info;
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_MASK      0x7fffUL
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_SFT       0
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_VALID     0x8000UL
+	u8	mpc_chnls;
+	#define FUNC_QCFG_RESP_MPC_CHNLS_TCE_ENABLED         0x1UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_RCE_ENABLED         0x2UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED      0x4UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED      0x8UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED     0x10UL
+	u8	db_page_size;
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4KB   0x0UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_8KB   0x1UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_16KB  0x2UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_32KB  0x3UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_64KB  0x4UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_128KB 0x5UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_256KB 0x6UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_512KB 0x7UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_1MB   0x8UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_2MB   0x9UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB   0xaUL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_LAST FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB
+	__le16	roce_vnic_id;
+	__le32	partition_min_bw;
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
+	__le32	partition_max_bw;
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
+	__le16	host_mtu;
+	__le16	flags2;
+	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
+	__le16	stag_vid;
+	u8	port_kdnet_mode;
+	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
+	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED  0x1UL
+	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_LAST    FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED
+	u8	kdnet_pcie_function;
+	__le16	port_kdnet_fid;
+	u8	unused_5;
+	u8	roce_bidi_opt_mode;
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DISABLED      0x1UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED     0x2UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_SHARED        0x4UL
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
+	u8	lag_id;
+	u8	parif;
+	u8	fw_lag_id;
+	u8	unused_6;
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
+	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
+	__le16	mirror_vnic_id;
+	u8	max_link_width;
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_UNKNOWN 0x0UL
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X1      0x1UL
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X2      0x2UL
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X4      0x4UL
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X8      0x8UL
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_X16     0x10UL
+	#define FUNC_QCFG_RESP_MAX_LINK_WIDTH_LAST   FUNC_QCFG_RESP_MAX_LINK_WIDTH_X16
+	u8	max_link_speed;
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_UNKNOWN 0x0UL
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_G1      0x1UL
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_G2      0x2UL
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_G3      0x3UL
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_G4      0x4UL
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_G5      0x5UL
+	#define FUNC_QCFG_RESP_MAX_LINK_SPEED_LAST   FUNC_QCFG_RESP_MAX_LINK_SPEED_G5
+	u8	negotiated_link_width;
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_UNKNOWN 0x0UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X1      0x1UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X2      0x2UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X4      0x4UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X8      0x8UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X16     0x10UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_LAST   FUNC_QCFG_RESP_NEGOTIATED_LINK_WIDTH_X16
+	u8	negotiated_link_speed;
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_UNKNOWN 0x0UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G1      0x1UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G2      0x2UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G3      0x3UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G4      0x4UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G5      0x5UL
+	#define FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_LAST   FUNC_QCFG_RESP_NEGOTIATED_LINK_SPEED_G5
+	u8	unused_7[2];
+	u8	pcie_compliance;
+	u8	unused_8;
+	__le16	l2_db_multi_page_size_kb;
+	u8	unused_9[5];
+	u8	valid;
+};
+
+/* hwrm_func_cfg_input (size:1280b/160B) */
+struct hwrm_func_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	__le16	num_msix;
+	__le32	flags;
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE     0x1UL
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE      0x2UL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_MASK                      0x1fcUL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_SFT                       2
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE        0x200UL
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE       0x400UL
+	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST               0x800UL
+	#define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC         0x1000UL
+	#define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST                 0x2000UL
+	#define FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST                 0x4000UL
+	#define FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST               0x8000UL
+	#define FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST         0x10000UL
+	#define FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST           0x20000UL
+	#define FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST           0x40000UL
+	#define FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST               0x80000UL
+	#define FUNC_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST             0x100000UL
+	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
+	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
+	#define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST                 0x800000UL
+	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE             0x1000000UL
+	#define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS        0x2000000UL
+	#define FUNC_CFG_REQ_FLAGS_HOT_RESET_IF_EN_DIS            0x4000000UL
+	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE           0x8000000UL
+	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE          0x10000000UL
+	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE             0x20000000UL
+	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE            0x40000000UL
+	__le32	enables;
+	#define FUNC_CFG_REQ_ENABLES_ADMIN_MTU                0x1UL
+	#define FUNC_CFG_REQ_ENABLES_MRU                      0x2UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x4UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x8UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS             0x10UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS             0x20UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS              0x40UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_VNICS                0x80UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x100UL
+	#define FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x200UL
+	#define FUNC_CFG_REQ_ENABLES_DFLT_VLAN                0x400UL
+	#define FUNC_CFG_REQ_ENABLES_DFLT_IP_ADDR             0x800UL
+	#define FUNC_CFG_REQ_ENABLES_MIN_BW                   0x1000UL
+	#define FUNC_CFG_REQ_ENABLES_MAX_BW                   0x2000UL
+	#define FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4000UL
+	#define FUNC_CFG_REQ_ENABLES_VLAN_ANTISPOOF_MODE      0x8000UL
+	#define FUNC_CFG_REQ_ENABLES_ALLOWED_VLAN_PRIS        0x10000UL
+	#define FUNC_CFG_REQ_ENABLES_EVB_MODE                 0x20000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS        0x40000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x80000UL
+	#define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE           0x100000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_MSIX                 0x200000UL
+	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE         0x400000UL
+	#define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT     0x800000UL
+	#define FUNC_CFG_REQ_ENABLES_SCHQ_ID                  0x1000000UL
+	#define FUNC_CFG_REQ_ENABLES_MPC_CHNLS                0x2000000UL
+	#define FUNC_CFG_REQ_ENABLES_PARTITION_MIN_BW         0x4000000UL
+	#define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW         0x8000000UL
+	#define FUNC_CFG_REQ_ENABLES_TPID                     0x10000000UL
+	#define FUNC_CFG_REQ_ENABLES_HOST_MTU                 0x20000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_TX_KEY_CTXS         0x40000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_RX_KEY_CTXS         0x80000000UL
+	__le16	admin_mtu;
+	__le16	mru;
+	__le16	num_rsscos_ctxs;
+	__le16	num_cmpl_rings;
+	__le16	num_tx_rings;
+	__le16	num_rx_rings;
+	__le16	num_l2_ctxs;
+	__le16	num_vnics;
+	__le16	num_stat_ctxs;
+	__le16	num_hw_ring_grps;
+	u8	dflt_mac_addr[6];
+	__le16	dflt_vlan;
+	__be32	dflt_ip_addr[4];
+	__le32	min_bw;
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_MIN_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	max_bw;
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_MAX_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
+	__le16	async_event_cr;
+	u8	vlan_antispoof_mode;
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_NOCHECK                 0x0UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_VALIDATE_VLAN           0x1UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_IF_VLANDNE       0x2UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN 0x3UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_LAST                   FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN
+	u8	allowed_vlan_pris;
+	u8	evb_mode;
+	#define FUNC_CFG_REQ_EVB_MODE_NO_EVB 0x0UL
+	#define FUNC_CFG_REQ_EVB_MODE_VEB    0x1UL
+	#define FUNC_CFG_REQ_EVB_MODE_VEPA   0x2UL
+	#define FUNC_CFG_REQ_EVB_MODE_LAST  FUNC_CFG_REQ_EVB_MODE_VEPA
+	u8	options;
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST          FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
+	__le16	num_mcast_filters;
+	__le16	schq_id;
+	__le16	mpc_chnls;
+	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_ENABLE          0x1UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_DISABLE         0x2UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_ENABLE          0x4UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_DISABLE         0x8UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_ENABLE       0x10UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_DISABLE      0x20UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_ENABLE       0x40UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_DISABLE      0x80UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_ENABLE      0x100UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_DISABLE     0x200UL
+	__le32	partition_min_bw;
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
+	__le32	partition_max_bw;
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
+	__be16	tpid;
+	__le16	host_mtu;
+	__le32	flags2;
+	#define FUNC_CFG_REQ_FLAGS2_KTLS_KEY_CTX_ASSETS_TEST     0x1UL
+	#define FUNC_CFG_REQ_FLAGS2_QUIC_KEY_CTX_ASSETS_TEST     0x2UL
+	__le32	enables2;
+	#define FUNC_CFG_REQ_ENABLES2_KDNET                    0x1UL
+	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE             0x2UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_TX_KEY_CTXS         0x4UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_RX_KEY_CTXS         0x8UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF       0x10UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_CQ_PER_VF       0x20UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_MRW_PER_VF      0x40UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_QP_PER_VF       0x80UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_SRQ_PER_VF      0x100UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF      0x200UL
+	#define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG        0x400UL
+	#define FUNC_CFG_REQ_ENABLES2_PHYSICAL_SLOT_NUMBER     0x800UL
+	#define FUNC_CFG_REQ_ENABLES2_PCIE_COMPLIANCE          0x1000UL
+	u8	port_kdnet_mode;
+	#define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL
+	#define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED  0x1UL
+	#define FUNC_CFG_REQ_PORT_KDNET_MODE_LAST    FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED
+	u8	db_page_size;
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4KB   0x0UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_8KB   0x1UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_16KB  0x2UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_32KB  0x3UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_64KB  0x4UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_128KB 0x5UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_256KB 0x6UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_512KB 0x7UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_1MB   0x8UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_2MB   0x9UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4MB   0xaUL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_LAST FUNC_CFG_REQ_DB_PAGE_SIZE_4MB
+	__le16	physical_slot_number;
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_TX_CK     0x1UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_RX_CK     0x2UL
+	u8	pcie_compliance;
+	u8	unused_2;
+};
+
+/* hwrm_func_cfg_output (size:128b/16B) */
+struct hwrm_func_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_cfg_cmd_err (size:64b/8B) */
+struct hwrm_func_cfg_cmd_err {
+	u8	code;
+	#define FUNC_CFG_CMD_ERR_CODE_UNKNOWN                      0x0UL
+	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_OUT_OF_RANGE    0x1UL
+	#define FUNC_CFG_CMD_ERR_CODE_NPAR_PARTITION_DOWN_FAILED   0x2UL
+	#define FUNC_CFG_CMD_ERR_CODE_TPID_SET_DFLT_VLAN_NOT_SET   0x3UL
+	#define FUNC_CFG_CMD_ERR_CODE_RES_ARRAY_ALLOC_FAILED       0x4UL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_RING_ASSET_TEST_FAILED    0x5UL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_RING_RES_UPDATE_FAILED    0x6UL
+	#define FUNC_CFG_CMD_ERR_CODE_APPLY_MAX_BW_FAILED          0x7UL
+	#define FUNC_CFG_CMD_ERR_CODE_ENABLE_EVB_FAILED            0x8UL
+	#define FUNC_CFG_CMD_ERR_CODE_RSS_CTXT_ASSET_TEST_FAILED   0x9UL
+	#define FUNC_CFG_CMD_ERR_CODE_RSS_CTXT_RES_UPDATE_FAILED   0xaUL
+	#define FUNC_CFG_CMD_ERR_CODE_CMPL_RING_ASSET_TEST_FAILED  0xbUL
+	#define FUNC_CFG_CMD_ERR_CODE_CMPL_RING_RES_UPDATE_FAILED  0xcUL
+	#define FUNC_CFG_CMD_ERR_CODE_NQ_ASSET_TEST_FAILED         0xdUL
+	#define FUNC_CFG_CMD_ERR_CODE_NQ_RES_UPDATE_FAILED         0xeUL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_RING_ASSET_TEST_FAILED    0xfUL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_RING_RES_UPDATE_FAILED    0x10UL
+	#define FUNC_CFG_CMD_ERR_CODE_VNIC_ASSET_TEST_FAILED       0x11UL
+	#define FUNC_CFG_CMD_ERR_CODE_VNIC_RES_UPDATE_FAILED       0x12UL
+	#define FUNC_CFG_CMD_ERR_CODE_FAILED_TO_START_STATS_THREAD 0x13UL
+	#define FUNC_CFG_CMD_ERR_CODE_RDMA_SRIOV_DISABLED          0x14UL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_KTLS_DISABLED             0x15UL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_KTLS_ASSET_TEST_FAILED    0x16UL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_KTLS_RES_UPDATE_FAILED    0x17UL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_KTLS_DISABLED             0x18UL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_KTLS_ASSET_TEST_FAILED    0x19UL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_KTLS_RES_UPDATE_FAILED    0x1aUL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_QUIC_DISABLED             0x1bUL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_QUIC_ASSET_TEST_FAILED    0x1cUL
+	#define FUNC_CFG_CMD_ERR_CODE_TX_QUIC_RES_UPDATE_FAILED    0x1dUL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_QUIC_DISABLED             0x1eUL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_QUIC_ASSET_TEST_FAILED    0x1fUL
+	#define FUNC_CFG_CMD_ERR_CODE_RX_QUIC_RES_UPDATE_FAILED    0x20UL
+	#define FUNC_CFG_CMD_ERR_CODE_INVALID_KDNET_MODE           0x21UL
+	#define FUNC_CFG_CMD_ERR_CODE_SCHQ_CFG_FAIL                0x22UL
+	#define FUNC_CFG_CMD_ERR_CODE_LAST                        FUNC_CFG_CMD_ERR_CODE_SCHQ_CFG_FAIL
+	u8	unused_0[7];
+};
+
+/* hwrm_func_qstats_input (size:192b/24B) */
+struct hwrm_func_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	flags;
+	#define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY        0x1UL
+	#define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x2UL
+	#define FUNC_QSTATS_REQ_FLAGS_L2_ONLY          0x4UL
+	u8	unused_0[5];
+};
+
+/* hwrm_func_qstats_output (size:1408b/176B) */
+struct hwrm_func_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_drop_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_drop_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	rx_agg_pkts;
+	__le64	rx_agg_bytes;
+	__le64	rx_agg_events;
+	__le64	rx_agg_aborts;
+	u8	clear_seq;
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_func_qstats_ext_input (size:256b/32B) */
+struct hwrm_func_qstats_ext_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	flags;
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY        0x1UL
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x2UL
+	u8	unused_0[1];
+	__le32	enables;
+	#define FUNC_QSTATS_EXT_REQ_ENABLES_SCHQ_ID     0x1UL
+	__le16	schq_id;
+	__le16	traffic_class;
+	u8	unused_1[4];
+};
+
+/* hwrm_func_qstats_ext_output (size:1536b/192B) */
+struct hwrm_func_qstats_ext_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_clr_stats_input (size:192b/24B) */
+struct hwrm_func_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_clr_stats_output (size:128b/16B) */
+struct hwrm_func_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_vf_resc_free_input (size:192b/24B) */
+struct hwrm_func_vf_resc_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vf_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_vf_resc_free_output (size:128b/16B) */
+struct hwrm_func_vf_resc_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_rgtr_input (size:896b/112B) */
+struct hwrm_func_drv_rgtr_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_ALL_MODE                     0x1UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE                    0x2UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE                   0x4UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE           0x8UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT                0x10UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT           0x20UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT                   0x40UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT               0x80UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT     0x100UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT                 0x200UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT           0x400UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE         0x800UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_EGRESS_NIC_FLOW_MODE          0x1000UL
+	__le32	enables;
+	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_TIMESTAMP           0x4UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD          0x8UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD     0x10UL
+	__le16	os_type;
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UNKNOWN   0x0UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_OTHER     0x1UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_MSDOS     0xeUL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WINDOWS   0x12UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_SOLARIS   0x1dUL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX     0x24UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_FREEBSD   0x2aUL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_ESXI      0x68UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN864    0x73UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN2012R2 0x74UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI      0x8000UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LAST     FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI
+	u8	ver_maj_8b;
+	u8	ver_min_8b;
+	u8	ver_upd_8b;
+	u8	unused_0[3];
+	__le32	timestamp;
+	u8	unused_1[4];
+	__le32	vf_req_fwd[8];
+	__le32	async_event_fwd[8];
+	__le16	ver_maj;
+	__le16	ver_min;
+	__le16	ver_upd;
+	__le16	ver_patch;
+};
+
+/* hwrm_func_drv_rgtr_output (size:128b/16B) */
+struct hwrm_func_drv_rgtr_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED     0x1UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_drv_unrgtr_input (size:192b/24B) */
+struct hwrm_func_drv_unrgtr_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_UNRGTR_REQ_FLAGS_PREPARE_FOR_SHUTDOWN     0x1UL
+	u8	unused_0[4];
+};
+
+/* hwrm_func_drv_unrgtr_output (size:128b/16B) */
+struct hwrm_func_drv_unrgtr_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_buf_rgtr_input (size:1024b/128B) */
+struct hwrm_func_buf_rgtr_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_BUF_RGTR_REQ_ENABLES_VF_ID            0x1UL
+	#define FUNC_BUF_RGTR_REQ_ENABLES_ERR_BUF_ADDR     0x2UL
+	__le16	vf_id;
+	__le16	req_buf_num_pages;
+	__le16	req_buf_page_size;
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_16B 0x4UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4K  0xcUL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_8K  0xdUL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_64K 0x10UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_2M  0x15UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4M  0x16UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G  0x1eUL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_LAST FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G
+	__le16	req_buf_len;
+	__le16	resp_buf_len;
+	u8	unused_0[2];
+	__le64	req_buf_page_addr0;
+	__le64	req_buf_page_addr1;
+	__le64	req_buf_page_addr2;
+	__le64	req_buf_page_addr3;
+	__le64	req_buf_page_addr4;
+	__le64	req_buf_page_addr5;
+	__le64	req_buf_page_addr6;
+	__le64	req_buf_page_addr7;
+	__le64	req_buf_page_addr8;
+	__le64	req_buf_page_addr9;
+	__le64	error_buf_addr;
+	__le64	resp_buf_addr;
+};
+
+/* hwrm_func_buf_rgtr_output (size:128b/16B) */
+struct hwrm_func_buf_rgtr_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_qver_input (size:192b/24B) */
+struct hwrm_func_drv_qver_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	reserved;
+	__le16	fid;
+	u8	driver_type;
+	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_L2   0x0UL
+	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE 0x1UL
+	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_LAST FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE
+	u8	unused_0;
+};
+
+/* hwrm_func_drv_qver_output (size:256b/32B) */
+struct hwrm_func_drv_qver_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	os_type;
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_UNKNOWN   0x0UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_OTHER     0x1UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_MSDOS     0xeUL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_WINDOWS   0x12UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_SOLARIS   0x1dUL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_LINUX     0x24UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_FREEBSD   0x2aUL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_ESXI      0x68UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN864    0x73UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN2012R2 0x74UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_UEFI      0x8000UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_LAST     FUNC_DRV_QVER_RESP_OS_TYPE_UEFI
+	u8	ver_maj_8b;
+	u8	ver_min_8b;
+	u8	ver_upd_8b;
+	u8	unused_0[3];
+	__le16	ver_maj;
+	__le16	ver_min;
+	__le16	ver_upd;
+	__le16	ver_patch;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* hwrm_func_resource_qcaps_input (size:192b/24B) */
+struct hwrm_func_resource_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_resource_qcaps_output (size:704b/88B) */
+struct hwrm_func_resource_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	max_vfs;
+	__le16	max_msix;
+	__le16	vf_reservation_strategy;
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MAXIMAL        0x0UL
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL        0x1UL
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC 0x2UL
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_LAST          FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC
+	__le16	min_rsscos_ctx;
+	__le16	max_rsscos_ctx;
+	__le16	min_cmpl_rings;
+	__le16	max_cmpl_rings;
+	__le16	min_tx_rings;
+	__le16	max_tx_rings;
+	__le16	min_rx_rings;
+	__le16	max_rx_rings;
+	__le16	min_l2_ctxs;
+	__le16	max_l2_ctxs;
+	__le16	min_vnics;
+	__le16	max_vnics;
+	__le16	min_stat_ctx;
+	__le16	max_stat_ctx;
+	__le16	min_hw_ring_grps;
+	__le16	max_hw_ring_grps;
+	__le16	max_tx_scheduler_inputs;
+	__le16	flags;
+	#define FUNC_RESOURCE_QCAPS_RESP_FLAGS_MIN_GUARANTEED     0x1UL
+	__le16	min_msix;
+	__le32	min_ktls_tx_key_ctxs;
+	__le32	max_ktls_tx_key_ctxs;
+	__le32	min_ktls_rx_key_ctxs;
+	__le32	max_ktls_rx_key_ctxs;
+	__le32	min_quic_tx_key_ctxs;
+	__le32	max_quic_tx_key_ctxs;
+	__le32	min_quic_rx_key_ctxs;
+	__le32	max_quic_rx_key_ctxs;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_vf_resource_cfg_input (size:704b/88B) */
+struct hwrm_func_vf_resource_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vf_id;
+	__le16	max_msix;
+	__le16	min_rsscos_ctx;
+	__le16	max_rsscos_ctx;
+	__le16	min_cmpl_rings;
+	__le16	max_cmpl_rings;
+	__le16	min_tx_rings;
+	__le16	max_tx_rings;
+	__le16	min_rx_rings;
+	__le16	max_rx_rings;
+	__le16	min_l2_ctxs;
+	__le16	max_l2_ctxs;
+	__le16	min_vnics;
+	__le16	max_vnics;
+	__le16	min_stat_ctx;
+	__le16	max_stat_ctx;
+	__le16	min_hw_ring_grps;
+	__le16	max_hw_ring_grps;
+	__le16	flags;
+	#define FUNC_VF_RESOURCE_CFG_REQ_FLAGS_MIN_GUARANTEED     0x1UL
+	__le16	min_msix;
+	__le32	min_ktls_tx_key_ctxs;
+	__le32	max_ktls_tx_key_ctxs;
+	__le32	min_ktls_rx_key_ctxs;
+	__le32	max_ktls_rx_key_ctxs;
+	__le32	min_quic_tx_key_ctxs;
+	__le32	max_quic_tx_key_ctxs;
+	__le32	min_quic_rx_key_ctxs;
+	__le32	max_quic_rx_key_ctxs;
+};
+
+/* hwrm_func_vf_resource_cfg_output (size:384b/48B) */
+struct hwrm_func_vf_resource_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	reserved_rsscos_ctx;
+	__le16	reserved_cmpl_rings;
+	__le16	reserved_tx_rings;
+	__le16	reserved_rx_rings;
+	__le16	reserved_l2_ctxs;
+	__le16	reserved_vnics;
+	__le16	reserved_stat_ctx;
+	__le16	reserved_hw_ring_grps;
+	__le32	reserved_ktls_tx_key_ctxs;
+	__le32	reserved_ktls_rx_key_ctxs;
+	__le32	reserved_quic_tx_key_ctxs;
+	__le32	reserved_quic_rx_key_ctxs;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */
+struct hwrm_func_backing_store_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_func_backing_store_qcaps_output (size:832b/104B) */
+struct hwrm_func_backing_store_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	qp_max_entries;
+	__le16	qp_min_qp1_entries;
+	__le16	qp_max_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_max_l2_entries;
+	__le32	srq_max_entries;
+	__le16	srq_entry_size;
+	__le16	cq_max_l2_entries;
+	__le32	cq_max_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_max_vnic_entries;
+	__le16	vnic_max_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le32	stat_max_entries;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le32	tqm_min_entries_per_ring;
+	__le32	tqm_max_entries_per_ring;
+	__le32	mrav_max_entries;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+	__le32	tim_max_entries;
+	__le16	mrav_num_entries_units;
+	u8	tqm_entries_multiple;
+	u8	ctx_kind_initializer;
+	__le16	ctx_init_mask;
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_QP       0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_SRQ      0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_CQ       0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_VNIC     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_STAT     0x10UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_MRAV     0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_TKC      0x40UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_RKC      0x80UL
+	u8	qp_init_offset;
+	u8	srq_init_offset;
+	u8	cq_init_offset;
+	u8	vnic_init_offset;
+	u8	tqm_fp_rings_count;
+	u8	stat_init_offset;
+	u8	mrav_init_offset;
+	u8	tqm_fp_rings_count_ext;
+	u8	tkc_init_offset;
+	u8	rkc_init_offset;
+	__le16	tkc_entry_size;
+	__le16	rkc_entry_size;
+	__le32	tkc_max_entries;
+	__le32	rkc_max_entries;
+	__le16	fast_qpmd_qp_num_entries;
+	u8	rsvd1[5];
+	u8	valid;
+};
+
+/* tqm_fp_ring_cfg (size:128b/16B) */
+struct tqm_fp_ring_cfg {
+	u8	tqm_ring_pg_size_tqm_ring_lvl;
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_MASK      0xfUL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_SFT       0
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_0       0x0UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_1       0x1UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2       0x2UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LAST       TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_SFT   4
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_LAST   TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G
+	u8	unused[3];
+	__le32	tqm_ring_num_entries;
+	__le64	tqm_ring_page_dir;
+};
+
+/* hwrm_func_backing_store_cfg_input (size:2688b/336B) */
+struct hwrm_func_backing_store_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE               0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT     0x2UL
+	__le32	enables;
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP               0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ              0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ               0x4UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC             0x8UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT             0x10UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP           0x20UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0        0x40UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1        0x80UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2        0x100UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3        0x200UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4        0x400UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5        0x800UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6        0x1000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7        0x2000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV             0x4000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM              0x8000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING8        0x10000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING9        0x20000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING10       0x40000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TKC              0x80000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_RKC              0x100000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD     0x200000UL
+	u8	qpc_pg_size_qpc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G
+	u8	srq_pg_size_srq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G
+	u8	cq_pg_size_cq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G
+	u8	vnic_pg_size_vnic_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G
+	u8	stat_pg_size_stat_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G
+	u8	tqm_sp_pg_size_tqm_sp_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G
+	u8	tqm_ring0_pg_size_tqm_ring0_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G
+	u8	tqm_ring1_pg_size_tqm_ring1_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G
+	u8	tqm_ring2_pg_size_tqm_ring2_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G
+	u8	tqm_ring3_pg_size_tqm_ring3_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G
+	u8	tqm_ring4_pg_size_tqm_ring4_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G
+	u8	tqm_ring5_pg_size_tqm_ring5_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G
+	u8	tqm_ring6_pg_size_tqm_ring6_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G
+	u8	tqm_ring7_pg_size_tqm_ring7_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G
+	u8	mrav_pg_size_mrav_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G
+	u8	tim_pg_size_tim_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G
+	__le64	qpc_page_dir;
+	__le64	srq_page_dir;
+	__le64	cq_page_dir;
+	__le64	vnic_page_dir;
+	__le64	stat_page_dir;
+	__le64	tqm_sp_page_dir;
+	__le64	tqm_ring0_page_dir;
+	__le64	tqm_ring1_page_dir;
+	__le64	tqm_ring2_page_dir;
+	__le64	tqm_ring3_page_dir;
+	__le64	tqm_ring4_page_dir;
+	__le64	tqm_ring5_page_dir;
+	__le64	tqm_ring6_page_dir;
+	__le64	tqm_ring7_page_dir;
+	__le64	mrav_page_dir;
+	__le64	tim_page_dir;
+	__le32	qp_num_entries;
+	__le32	srq_num_entries;
+	__le32	cq_num_entries;
+	__le32	stat_num_entries;
+	__le32	tqm_sp_num_entries;
+	__le32	tqm_ring0_num_entries;
+	__le32	tqm_ring1_num_entries;
+	__le32	tqm_ring2_num_entries;
+	__le32	tqm_ring3_num_entries;
+	__le32	tqm_ring4_num_entries;
+	__le32	tqm_ring5_num_entries;
+	__le32	tqm_ring6_num_entries;
+	__le32	tqm_ring7_num_entries;
+	__le32	mrav_num_entries;
+	__le32	tim_num_entries;
+	__le16	qp_num_qp1_entries;
+	__le16	qp_num_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_num_l2_entries;
+	__le16	srq_entry_size;
+	__le16	cq_num_l2_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_num_vnic_entries;
+	__le16	vnic_num_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+	u8	tqm_ring8_pg_size_tqm_ring_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G
+	u8	ring8_unused[3];
+	__le32	tqm_ring8_num_entries;
+	__le64	tqm_ring8_page_dir;
+	u8	tqm_ring9_pg_size_tqm_ring_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G
+	u8	ring9_unused[3];
+	__le32	tqm_ring9_num_entries;
+	__le64	tqm_ring9_page_dir;
+	u8	tqm_ring10_pg_size_tqm_ring_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G
+	u8	ring10_unused[3];
+	__le32	tqm_ring10_num_entries;
+	__le64	tqm_ring10_page_dir;
+	__le32	tkc_num_entries;
+	__le32	rkc_num_entries;
+	__le64	tkc_page_dir;
+	__le64	rkc_page_dir;
+	__le16	tkc_entry_size;
+	__le16	rkc_entry_size;
+	u8	tkc_pg_size_tkc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G
+	u8	rkc_pg_size_rkc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G
+	__le16	qp_num_fast_qpmd_entries;
+};
+
+/* hwrm_func_backing_store_cfg_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_error_recovery_qcfg_input (size:192b/24B) */
+struct hwrm_error_recovery_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */
+struct hwrm_error_recovery_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU     0x2UL
+	__le32	driver_polling_freq;
+	__le32	master_func_wait_period;
+	__le32	normal_func_wait_period;
+	__le32	master_func_wait_period_after_reset;
+	__le32	max_bailout_time_after_reset;
+	__le32	fw_health_status_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT           2
+	__le32	fw_heartbeat_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT           2
+	__le32	fw_reset_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg_mask;
+	u8	unused_0[3];
+	u8	reg_array_cnt;
+	__le32	reset_reg[16];
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
+	__le32	reset_reg_val[16];
+	u8	delay_after_reset[16];
+	__le32	err_recovery_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SFT           2
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_func_echo_response_input (size:192b/24B) */
+struct hwrm_func_echo_response_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	event_data1;
+	__le32	event_data2;
+};
+
+/* hwrm_func_echo_response_output (size:128b/16B) */
+struct hwrm_func_echo_response_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_pin_qcfg_input (size:192b/24B) */
+struct hwrm_func_ptp_pin_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_func_ptp_pin_qcfg_output (size:128b/16B) */
+struct hwrm_func_ptp_pin_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_pins;
+	u8	state;
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN0_ENABLED     0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN1_ENABLED     0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN2_ENABLED     0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN3_ENABLED     0x8UL
+	u8	pin0_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT
+	u8	pin1_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT
+	u8	pin2_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	pin3_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_func_ptp_pin_cfg_input (size:256b/32B) */
+struct hwrm_func_ptp_pin_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_STATE     0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_USAGE     0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_STATE     0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_USAGE     0x8UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_STATE     0x10UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_USAGE     0x20UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_STATE     0x40UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_USAGE     0x80UL
+	u8	pin0_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED
+	u8	pin0_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT
+	u8	pin1_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED
+	u8	pin1_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT
+	u8	pin2_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED
+	u8	pin2_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	pin3_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED
+	u8	pin3_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	unused_0[4];
+};
+
+/* hwrm_func_ptp_pin_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_pin_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_cfg_input (size:384b/48B) */
+struct hwrm_func_ptp_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	enables;
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_PPS_EVENT               0x1UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_SOURCE     0x2UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_PHASE      0x4UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD     0x8UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP         0x10UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE      0x20UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME                0x40UL
+	u8	ptp_pps_event;
+	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL     0x1UL
+	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL     0x2UL
+	u8	ptp_freq_adj_dll_source;
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_NONE    0x0UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_0  0x1UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_1  0x2UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_2  0x3UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_3  0x4UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_0  0x5UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_1  0x6UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_2  0x7UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_3  0x8UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID 0xffUL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_LAST   FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID
+	u8	ptp_freq_adj_dll_phase;
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_NONE 0x0UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K   0x1UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K   0x2UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M  0x3UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M  0x4UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M
+	u8	unused_0[3];
+	__le32	ptp_freq_adj_ext_period;
+	__le32	ptp_freq_adj_ext_up;
+	__le32	ptp_freq_adj_ext_phase_lower;
+	__le32	ptp_freq_adj_ext_phase_upper;
+	__le64	ptp_set_time;
+};
+
+/* hwrm_func_ptp_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_ts_query_input (size:192b/24B) */
+struct hwrm_func_ptp_ts_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PPS_TIME     0x1UL
+	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PTM_TIME     0x2UL
+	u8	unused_0[4];
+};
+
+/* hwrm_func_ptp_ts_query_output (size:320b/40B) */
+struct hwrm_func_ptp_ts_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	pps_event_ts;
+	__le64	ptm_local_ts;
+	__le64	ptm_system_ts;
+	__le32	ptm_link_delay;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */
+struct hwrm_func_ptp_ext_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	enables;
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID     0x1UL
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID        0x2UL
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE       0x4UL
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER     0x8UL
+	__le16	phc_master_fid;
+	__le16	phc_sec_fid;
+	u8	phc_sec_mode;
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH  0x0UL
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL     0x1UL
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST   FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY
+	u8	unused_0;
+	__le32	failover_timer;
+	u8	unused_1[4];
+};
+
+/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_ext_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */
+struct hwrm_func_ptp_ext_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */
+struct hwrm_func_ptp_ext_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	phc_master_fid;
+	__le16	phc_sec_fid;
+	__le16	phc_active_fid0;
+	__le16	phc_active_fid1;
+	__le32	last_failover_event;
+	__le16	from_fid;
+	__le16	to_fid;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_cfg_v2_input (size:512b/64B) */
+struct hwrm_func_backing_store_cfg_v2_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ERR_QPC_TRACE       0x2bUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
+	__le16	instance;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE        0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE     0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_EXTEND           0x4UL
+	__le64	page_dir;
+	__le32	num_entries;
+	__le16	entry_size;
+	u8	page_size_pbl_level;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK  0xfUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT   0
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0   0x0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1   0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2   0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G
+	u8	subtype_valid_cnt;
+	__le32	split_entry_0;
+	__le32	split_entry_1;
+	__le32	split_entry_2;
+	__le32	split_entry_3;
+	__le32	enables;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_ENABLES_NEXT_BS_OFFSET     0x1UL
+	__le32	next_bs_offset;
+};
+
+/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_v2_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	rsvd0[7];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */
+struct hwrm_func_backing_store_qcfg_v2_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION_TABLE 0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ERR_QPC_TRACE       0x2bUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
+	__le16	instance;
+	u8	rsvd[4];
+};
+
+/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */
+struct hwrm_func_backing_store_qcfg_v2_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ERR_QPC_TRACE       0x2aUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
+	__le16	instance;
+	__le32	flags;
+	__le64	page_dir;
+	__le32	num_entries;
+	u8	page_size_pbl_level;
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK  0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT   0
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0   0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1   0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2   0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G
+	u8	subtype_valid_cnt;
+	u8	rsvd[2];
+	__le32	split_entry_0;
+	__le32	split_entry_1;
+	__le32	split_entry_2;
+	__le32	split_entry_3;
+	u8	rsvd2[7];
+	u8	valid;
+};
+
+/* qpc_split_entries (size:128b/16B) */
+struct qpc_split_entries {
+	__le32	qp_num_l2_entries;
+	__le32	qp_num_qp1_entries;
+	__le32	qp_num_fast_qpmd_entries;
+	__le32	rsvd;
+};
+
+/* srq_split_entries (size:128b/16B) */
+struct srq_split_entries {
+	__le32	srq_num_l2_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* cq_split_entries (size:128b/16B) */
+struct cq_split_entries {
+	__le32	cq_num_l2_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* vnic_split_entries (size:128b/16B) */
+struct vnic_split_entries {
+	__le32	vnic_num_vnic_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* mrav_split_entries (size:128b/16B) */
+struct mrav_split_entries {
+	__le32	mrav_num_av_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* ts_split_entries (size:128b/16B) */
+struct ts_split_entries {
+	__le32	region_num_entries;
+	u8	tsid;
+	u8	lkup_static_bkt_cnt_exp[2];
+	u8	locked;
+	__le32	rsvd2[2];
+};
+
+/* ck_split_entries (size:128b/16B) */
+struct ck_split_entries {
+	__le32	num_quic_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
+struct hwrm_func_backing_store_qcaps_v2_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ERR_QPC_TRACE       0x2bUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
+	u8	rsvd[6];
+};
+
+/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */
+struct hwrm_func_backing_store_qcaps_v2_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ERR_QPC_TRACE       0x2bUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
+	__le16	entry_size;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT            0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID                      0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY           0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE                    0x10UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_BIN_DBG_TRACE                0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_NEXT_BS_OFFSET                  0x40UL
+	__le32	instance_bit_map;
+	u8	ctx_init_value;
+	u8	ctx_init_offset;
+	u8	entry_multiple;
+	u8	rsvd;
+	__le32	max_num_entries;
+	__le32	min_num_entries;
+	__le16	next_valid_type;
+	u8	subtype_valid_cnt;
+	u8	exact_cnt_bit_map;
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_0_EXACT     0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_1_EXACT     0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_2_EXACT     0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_3_EXACT     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_MASK             0xf0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_SFT              4
+	__le32	split_entry_0;
+	__le32	split_entry_1;
+	__le32	split_entry_2;
+	__le32	split_entry_3;
+	__le16	max_instance_count;
+	u8	rsvd3;
+	u8	valid;
+};
+
+/* hwrm_func_dbr_pacing_qcfg_input (size:128b/16B) */
+struct hwrm_func_dbr_pacing_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_func_dbr_pacing_qcfg_output (size:512b/64B) */
+struct hwrm_func_dbr_pacing_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
+	u8	unused_0[7];
+	__le32	dbr_stat_db_fifo_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
+	__le32	dbr_stat_db_fifo_reg_watermark_mask;
+	u8	dbr_stat_db_fifo_reg_watermark_shift;
+	u8	unused_1[3];
+	__le32	dbr_stat_db_fifo_reg_fifo_room_mask;
+	u8	dbr_stat_db_fifo_reg_fifo_room_shift;
+	u8	unused_2[3];
+	__le32	dbr_throttling_aeq_arm_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
+	u8	dbr_throttling_aeq_arm_reg_val;
+	u8	unused_3[3];
+	__le32	dbr_stat_db_max_fifo_depth;
+	__le32	primary_nq_id;
+	__le32	pacing_threshold;
+	u8	unused_4[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_if_change_input (size:192b/24B) */
+struct hwrm_func_drv_if_change_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP     0x1UL
+	__le32	unused;
+};
+
+/* hwrm_func_drv_if_change_output (size:128b/16B) */
+struct hwrm_func_drv_if_change_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE           0x4UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_port_phy_cfg_input (size:512b/64B) */
+struct hwrm_port_phy_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY                  0x1UL
+	#define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED                 0x2UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FORCE                      0x4UL
+	#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG            0x8UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE                 0x10UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE                0x20UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE          0x40UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE         0x80UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE         0x100UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE        0x200UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE        0x400UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE       0x800UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE        0x1000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE       0x2000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN             0x4000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE       0x8000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE      0x10000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_ENABLE      0x20000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_DISABLE     0x40000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_ENABLE       0x80000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE      0x100000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE      0x200000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE     0x400000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_LINK_TRAINING_ENABLE       0x800000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_LINK_TRAINING_DISABLE      0x1000000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_PRECODING_ENABLE           0x2000000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_PRECODING_DISABLE          0x4000000UL
+	__le32	enables;
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE                     0x1UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX                   0x2UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE                    0x4UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED               0x8UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK          0x10UL
+	#define PORT_PHY_CFG_REQ_ENABLES_WIRESPEED                     0x20UL
+	#define PORT_PHY_CFG_REQ_ENABLES_LPBK                          0x40UL
+	#define PORT_PHY_CFG_REQ_ENABLES_PREEMPHASIS                   0x80UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE                   0x100UL
+	#define PORT_PHY_CFG_REQ_ENABLES_EEE_LINK_SPEED_MASK           0x200UL
+	#define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER                  0x400UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED         0x800UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK     0x1000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2            0x2000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK        0x4000UL
+	__le16	port_id;
+	__le16	force_link_speed;
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB
+	u8	auto_mode;
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_NONE         0x0UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_ALL_SPEEDS   0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_SPEED    0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_OR_BELOW 0x3UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK   0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_LAST        PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK
+	u8	auto_duplex;
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_HALF 0x0UL
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_FULL 0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH 0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_LAST PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH
+	u8	auto_pause;
+	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_TX                0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_RX                0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
+	u8	mgmt_flag;
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_LINK_RELEASE     0x1UL
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_MGMT_VALID       0x80UL
+	__le16	auto_link_speed;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_LAST PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB
+	__le16	auto_link_speed_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MB       0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GB         0x8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2GB         0x10UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10GB        0x40UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_20GB        0x80UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_25GB        0x100UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_40GB        0x200UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_50GB        0x400UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100GB       0x800UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
+	u8	wirespeed;
+	#define PORT_PHY_CFG_REQ_WIRESPEED_OFF 0x0UL
+	#define PORT_PHY_CFG_REQ_WIRESPEED_ON  0x1UL
+	#define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON
+	u8	lpbk;
+	#define PORT_PHY_CFG_REQ_LPBK_NONE     0x0UL
+	#define PORT_PHY_CFG_REQ_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_CFG_REQ_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_CFG_REQ_LPBK_LAST    PORT_PHY_CFG_REQ_LPBK_EXTERNAL
+	u8	force_pause;
+	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX     0x1UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX     0x2UL
+	u8	unused_1;
+	__le32	preemphasis;
+	__le16	eee_link_speed_mask;
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_100MB     0x2UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_1GB       0x8UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_10GB      0x40UL
+	__le16	force_pam4_link_speed;
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB
+	__le32	tx_lpi_timer;
+	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_MASK 0xffffffUL
+	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_SFT 0
+	__le16	auto_link_pam4_speed_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G      0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G     0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G     0x4UL
+	__le16	force_link_speeds2;
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112
+	__le16	auto_link_speeds2_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB                0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB               0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_25GB               0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_40GB               0x8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB               0x10UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB              0x20UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_800GB_PAM4_112     0x2000UL
+	u8	unused_2[6];
+};
+
+/* hwrm_port_phy_cfg_output (size:128b/16B) */
+struct hwrm_port_phy_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_cfg_cmd_err (size:64b/8B) */
+struct hwrm_port_phy_cfg_cmd_err {
+	u8	code;
+	#define PORT_PHY_CFG_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define PORT_PHY_CFG_CMD_ERR_CODE_ILLEGAL_SPEED 0x1UL
+	#define PORT_PHY_CFG_CMD_ERR_CODE_RETRY         0x2UL
+	#define PORT_PHY_CFG_CMD_ERR_CODE_LAST         PORT_PHY_CFG_CMD_ERR_CODE_RETRY
+	u8	unused_0[7];
+};
+
+/* hwrm_port_phy_qcfg_input (size:192b/24B) */
+struct hwrm_port_phy_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_phy_qcfg_output (size:832b/104B) */
+struct hwrm_port_phy_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	link;
+	#define PORT_PHY_QCFG_RESP_LINK_NO_LINK 0x0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL  0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_LINK    0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_LAST   PORT_PHY_QCFG_RESP_LINK_LINK
+	u8	active_fec_signal_mode;
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK                0xfUL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112              0x2UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE    (0x1UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE    (0x2UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE   (0x3UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE  (0x4UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE   (0x5UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE  (0x6UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_LAST                  PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE
+	__le16	link_speed;
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_800GB 0x1f40UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB
+	u8	duplex_cfg;
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_HALF 0x0UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL 0x1UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_LAST PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL
+	u8	pause;
+	#define PORT_PHY_QCFG_RESP_PAUSE_TX     0x1UL
+	#define PORT_PHY_QCFG_RESP_PAUSE_RX     0x2UL
+	__le16	support_speeds;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MBHD     0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB       0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GBHD       0x4UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB         0x8UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2GB         0x10UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2_5GB       0x20UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10GB        0x40UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_20GB        0x80UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB        0x100UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB        0x200UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB        0x400UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB       0x800UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MBHD      0x1000UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MB        0x2000UL
+	__le16	force_link_speed;
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB
+	u8	auto_mode;
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_NONE         0x0UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ALL_SPEEDS   0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_SPEED    0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_OR_BELOW 0x3UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK   0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK
+	u8	auto_pause;
+	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_TX                0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_RX                0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
+	__le16	auto_link_speed;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB
+	__le16	auto_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MB       0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GB         0x8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2GB         0x10UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10GB        0x40UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_20GB        0x80UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_25GB        0x100UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_40GB        0x200UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_50GB        0x400UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100GB       0x800UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
+	u8	wirespeed;
+	#define PORT_PHY_QCFG_RESP_WIRESPEED_OFF 0x0UL
+	#define PORT_PHY_QCFG_RESP_WIRESPEED_ON  0x1UL
+	#define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON
+	u8	lpbk;
+	#define PORT_PHY_QCFG_RESP_LPBK_NONE     0x0UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LAST    PORT_PHY_QCFG_RESP_LPBK_EXTERNAL
+	u8	force_pause;
+	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX     0x1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX     0x2UL
+	u8	module_status;
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NONE          0x0UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_DISABLETX     0x1UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG    0x2UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN       0x3UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED   0x4UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT  0x5UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED    0x6UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST         PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE
+	__le32	preemphasis;
+	u8	phy_maj;
+	u8	phy_min;
+	u8	phy_bld;
+	u8	phy_type;
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_UNKNOWN          0x0UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASECR           0x1UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR4          0x2UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASELR           0x3UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASESR           0x4UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR2          0x5UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKX           0x6UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR           0x7UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASET            0x8UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE           0x9UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_SGMIIEXTPHY      0xaUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_L  0xbUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_S  0xcUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_N  0xdUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASESR       0xeUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR4     0xfUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR4     0x10UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR4     0x11UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER4     0x12UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR10    0x13UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASECR4      0x14UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASESR4      0x15UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4      0x16UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4      0x17UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE 0x18UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET         0x19UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX        0x1aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX        0x1bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR4     0x1cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4     0x1dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4     0x1eUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4     0x1fUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR       0x20UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR       0x21UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR       0x22UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER       0x23UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2     0x24UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2     0x25UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2     0x26UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2     0x27UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR      0x28UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR      0x29UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR      0x2aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER      0x2bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2     0x2cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2     0x2dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2     0x2eUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2     0x2fUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8     0x30UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8     0x31UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8     0x32UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8     0x33UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4     0x34UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4     0x35UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4     0x36UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4     0x37UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASECR8     0x38UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASESR8     0x39UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASELR8     0x3aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEER8     0x3bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEFR8     0x3cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8     0x3dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8
+	u8	media_type;
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN   0x0UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP        0x1UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC       0x2UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE     0x3UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE 0x4UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_LAST     PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE
+	u8	xcvr_pkg_type;
+	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_INTERNAL 0x1UL
+	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL 0x2UL
+	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_LAST         PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL
+	u8	eee_config_phy_addr;
+	#define PORT_PHY_QCFG_RESP_PHY_ADDR_MASK              0x1fUL
+	#define PORT_PHY_QCFG_RESP_PHY_ADDR_SFT               0
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_MASK            0xe0UL
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_SFT             5
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ENABLED      0x20UL
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ACTIVE       0x40UL
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_TX_LPI       0x80UL
+	u8	parallel_detect;
+	#define PORT_PHY_QCFG_RESP_PARALLEL_DETECT     0x1UL
+	__le16	link_partner_adv_speeds;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MBHD     0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MB       0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GBHD       0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GB         0x8UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2GB         0x10UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2_5GB       0x20UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10GB        0x40UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_20GB        0x80UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_25GB        0x100UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_40GB        0x200UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_50GB        0x400UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100GB       0x800UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MBHD      0x1000UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MB        0x2000UL
+	u8	link_partner_adv_auto_mode;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_NONE         0x0UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ALL_SPEEDS   0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_SPEED    0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_OR_BELOW 0x3UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK   0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK
+	u8	link_partner_adv_pause;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_TX     0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_RX     0x2UL
+	__le16	adv_eee_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
+	__le16	link_partner_adv_eee_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
+	__le32	xcvr_identifier_type_tx_lpi_timer;
+	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_MASK            0xffffffUL
+	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_SFT             0
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_MASK    0xff000000UL
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFT     24
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_UNKNOWN   (0x0UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFP       (0x3UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP      (0xcUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPPLUS  (0xdUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPDD    (0x18UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP112   (0x1eUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFPDD     (0x1fUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP      (0x20UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP
+	__le16	fec_cfg;
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED           0x1UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED        0x2UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED          0x4UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED       0x8UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED         0x10UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED       0x20UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED         0x40UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED      0x80UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED        0x100UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_SUPPORTED     0x200UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED       0x400UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED      0x800UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED        0x1000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED     0x2000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED       0x4000UL
+	u8	duplex_state;
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_LAST PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
+	u8	option_flags;
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT     0x1UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN     0x2UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED     0x4UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_LINK_TRAINING         0x8UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_PRECODING             0x10UL
+	char	phy_vendor_name[16];
+	char	phy_vendor_partnumber[16];
+	__le16	support_pam4_speeds;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G      0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G     0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G     0x4UL
+	__le16	force_pam4_link_speed;
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB
+	__le16	auto_pam4_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_50G      0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_100G     0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_200G     0x4UL
+	u8	link_partner_pam4_adv_speeds;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB      0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB     0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
+	u8	link_down_reason;
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF                      0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_OTP_SPEED_VIOLATION     0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_CABLE_REMOVED           0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_MODULE_FAULT            0x8UL
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_BMC_REQUEST             0x10UL
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_TX_LASER_DISABLED       0x20UL
+	__le16	support_speeds2;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112     0x2000UL
+	__le16	force_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112
+	__le16	auto_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_800GB_PAM4_112     0x2000UL
+	u8	active_lanes;
+	u8	valid;
+};
+
+/* hwrm_port_mac_cfg_input (size:448b/56B) */
+struct hwrm_port_mac_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_MAC_CFG_REQ_FLAGS_MATCH_LINK                    0x1UL
+	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_ENABLE           0x2UL
+	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_ENABLE         0x4UL
+	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_ENABLE            0x8UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_ENABLE      0x10UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE     0x20UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE      0x40UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE     0x80UL
+	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_ENABLE                0x100UL
+	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_DISABLE               0x200UL
+	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_DISABLE          0x400UL
+	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_DISABLE        0x800UL
+	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_DISABLE           0x1000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_ONE_STEP_TX_TS            0x2000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE      0x4000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE     0x8000UL
+	__le32	enables;
+	#define PORT_MAC_CFG_REQ_ENABLES_IPG                            0x1UL
+	#define PORT_MAC_CFG_REQ_ENABLES_LPBK                           0x2UL
+	#define PORT_MAC_CFG_REQ_ENABLES_VLAN_PRI2COS_MAP_PRI           0x4UL
+	#define PORT_MAC_CFG_REQ_ENABLES_TUNNEL_PRI2COS_MAP_PRI         0x10UL
+	#define PORT_MAC_CFG_REQ_ENABLES_DSCP2COS_MAP_PRI               0x20UL
+	#define PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE     0x40UL
+	#define PORT_MAC_CFG_REQ_ENABLES_TX_TS_CAPTURE_PTP_MSG_TYPE     0x80UL
+	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE                  0x400UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_LOAD_CONTROL               0x800UL
+	__le16	port_id;
+	u8	ipg;
+	u8	lpbk;
+	#define PORT_MAC_CFG_REQ_LPBK_NONE   0x0UL
+	#define PORT_MAC_CFG_REQ_LPBK_LOCAL  0x1UL
+	#define PORT_MAC_CFG_REQ_LPBK_REMOTE 0x2UL
+	#define PORT_MAC_CFG_REQ_LPBK_LAST  PORT_MAC_CFG_REQ_LPBK_REMOTE
+	u8	vlan_pri2cos_map_pri;
+	u8	reserved1;
+	u8	tunnel_pri2cos_map_pri;
+	u8	dscp2pri_map_pri;
+	__le16	rx_ts_capture_ptp_msg_type;
+	__le16	tx_ts_capture_ptp_msg_type;
+	u8	cos_field_cfg;
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_RSVD1                     0x1UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_MASK         0x6UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_SFT          1
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_INNERMOST      (0x0UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTER          (0x1UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTERMOST      (0x2UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED    (0x3UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_LAST          PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_MASK       0x18UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_SFT        3
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_INNERMOST    (0x0UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTER        (0x1UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTERMOST    (0x2UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED  (0x3UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_LAST        PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_MASK          0xe0UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
+	u8	unused_0[3];
+	__le32	ptp_freq_adj_ppb;
+	u8	unused_1[3];
+	u8	ptp_load_control;
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_NONE      0x0UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_IMMEDIATE 0x1UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT 0x2UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_LAST     PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT
+	__le64	ptp_adj_phase;
+};
+
+/* hwrm_port_mac_cfg_output (size:128b/16B) */
+struct hwrm_port_mac_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	mru;
+	__le16	mtu;
+	u8	ipg;
+	u8	lpbk;
+	#define PORT_MAC_CFG_RESP_LPBK_NONE   0x0UL
+	#define PORT_MAC_CFG_RESP_LPBK_LOCAL  0x1UL
+	#define PORT_MAC_CFG_RESP_LPBK_REMOTE 0x2UL
+	#define PORT_MAC_CFG_RESP_LPBK_LAST  PORT_MAC_CFG_RESP_LPBK_REMOTE
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_port_mac_ptp_qcfg_input (size:192b/24B) */
+struct hwrm_port_mac_ptp_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_mac_ptp_qcfg_output (size:704b/88B) */
+struct hwrm_port_mac_ptp_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS                       0x1UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS                      0x4UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS                         0x8UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK     0x10UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED                      0x20UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_64B_PHC_TIME                        0x40UL
+	u8	unused_0[3];
+	__le32	rx_ts_reg_off_lower;
+	__le32	rx_ts_reg_off_upper;
+	__le32	rx_ts_reg_off_seq_id;
+	__le32	rx_ts_reg_off_src_id_0;
+	__le32	rx_ts_reg_off_src_id_1;
+	__le32	rx_ts_reg_off_src_id_2;
+	__le32	rx_ts_reg_off_domain_id;
+	__le32	rx_ts_reg_off_fifo;
+	__le32	rx_ts_reg_off_fifo_adv;
+	__le32	rx_ts_reg_off_granularity;
+	__le32	tx_ts_reg_off_lower;
+	__le32	tx_ts_reg_off_upper;
+	__le32	tx_ts_reg_off_seq_id;
+	__le32	tx_ts_reg_off_fifo;
+	__le32	tx_ts_reg_off_granularity;
+	__le32	ts_ref_clock_reg_lower;
+	__le32	ts_ref_clock_reg_upper;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* tx_port_stats (size:3264b/408B) */
+struct tx_port_stats {
+	__le64	tx_64b_frames;
+	__le64	tx_65b_127b_frames;
+	__le64	tx_128b_255b_frames;
+	__le64	tx_256b_511b_frames;
+	__le64	tx_512b_1023b_frames;
+	__le64	tx_1024b_1518b_frames;
+	__le64	tx_good_vlan_frames;
+	__le64	tx_1519b_2047b_frames;
+	__le64	tx_2048b_4095b_frames;
+	__le64	tx_4096b_9216b_frames;
+	__le64	tx_9217b_16383b_frames;
+	__le64	tx_good_frames;
+	__le64	tx_total_frames;
+	__le64	tx_ucast_frames;
+	__le64	tx_mcast_frames;
+	__le64	tx_bcast_frames;
+	__le64	tx_pause_frames;
+	__le64	tx_pfc_frames;
+	__le64	tx_jabber_frames;
+	__le64	tx_fcs_err_frames;
+	__le64	tx_control_frames;
+	__le64	tx_oversz_frames;
+	__le64	tx_single_dfrl_frames;
+	__le64	tx_multi_dfrl_frames;
+	__le64	tx_single_coll_frames;
+	__le64	tx_multi_coll_frames;
+	__le64	tx_late_coll_frames;
+	__le64	tx_excessive_coll_frames;
+	__le64	tx_frag_frames;
+	__le64	tx_err;
+	__le64	tx_tagged_frames;
+	__le64	tx_dbl_tagged_frames;
+	__le64	tx_runt_frames;
+	__le64	tx_fifo_underruns;
+	__le64	tx_pfc_ena_frames_pri0;
+	__le64	tx_pfc_ena_frames_pri1;
+	__le64	tx_pfc_ena_frames_pri2;
+	__le64	tx_pfc_ena_frames_pri3;
+	__le64	tx_pfc_ena_frames_pri4;
+	__le64	tx_pfc_ena_frames_pri5;
+	__le64	tx_pfc_ena_frames_pri6;
+	__le64	tx_pfc_ena_frames_pri7;
+	__le64	tx_eee_lpi_events;
+	__le64	tx_eee_lpi_duration;
+	__le64	tx_llfc_logical_msgs;
+	__le64	tx_hcfc_msgs;
+	__le64	tx_total_collisions;
+	__le64	tx_bytes;
+	__le64	tx_xthol_frames;
+	__le64	tx_stat_discard;
+	__le64	tx_stat_error;
+};
+
+/* rx_port_stats (size:4224b/528B) */
+struct rx_port_stats {
+	__le64	rx_64b_frames;
+	__le64	rx_65b_127b_frames;
+	__le64	rx_128b_255b_frames;
+	__le64	rx_256b_511b_frames;
+	__le64	rx_512b_1023b_frames;
+	__le64	rx_1024b_1518b_frames;
+	__le64	rx_good_vlan_frames;
+	__le64	rx_1519b_2047b_frames;
+	__le64	rx_2048b_4095b_frames;
+	__le64	rx_4096b_9216b_frames;
+	__le64	rx_9217b_16383b_frames;
+	__le64	rx_total_frames;
+	__le64	rx_ucast_frames;
+	__le64	rx_mcast_frames;
+	__le64	rx_bcast_frames;
+	__le64	rx_fcs_err_frames;
+	__le64	rx_ctrl_frames;
+	__le64	rx_pause_frames;
+	__le64	rx_pfc_frames;
+	__le64	rx_unsupported_opcode_frames;
+	__le64	rx_unsupported_da_pausepfc_frames;
+	__le64	rx_wrong_sa_frames;
+	__le64	rx_align_err_frames;
+	__le64	rx_oor_len_frames;
+	__le64	rx_code_err_frames;
+	__le64	rx_false_carrier_frames;
+	__le64	rx_ovrsz_frames;
+	__le64	rx_jbr_frames;
+	__le64	rx_mtu_err_frames;
+	__le64	rx_match_crc_frames;
+	__le64	rx_promiscuous_frames;
+	__le64	rx_tagged_frames;
+	__le64	rx_double_tagged_frames;
+	__le64	rx_trunc_frames;
+	__le64	rx_good_frames;
+	__le64	rx_pfc_xon2xoff_frames_pri0;
+	__le64	rx_pfc_xon2xoff_frames_pri1;
+	__le64	rx_pfc_xon2xoff_frames_pri2;
+	__le64	rx_pfc_xon2xoff_frames_pri3;
+	__le64	rx_pfc_xon2xoff_frames_pri4;
+	__le64	rx_pfc_xon2xoff_frames_pri5;
+	__le64	rx_pfc_xon2xoff_frames_pri6;
+	__le64	rx_pfc_xon2xoff_frames_pri7;
+	__le64	rx_pfc_ena_frames_pri0;
+	__le64	rx_pfc_ena_frames_pri1;
+	__le64	rx_pfc_ena_frames_pri2;
+	__le64	rx_pfc_ena_frames_pri3;
+	__le64	rx_pfc_ena_frames_pri4;
+	__le64	rx_pfc_ena_frames_pri5;
+	__le64	rx_pfc_ena_frames_pri6;
+	__le64	rx_pfc_ena_frames_pri7;
+	__le64	rx_sch_crc_err_frames;
+	__le64	rx_undrsz_frames;
+	__le64	rx_frag_frames;
+	__le64	rx_eee_lpi_events;
+	__le64	rx_eee_lpi_duration;
+	__le64	rx_llfc_physical_msgs;
+	__le64	rx_llfc_logical_msgs;
+	__le64	rx_llfc_msgs_with_crc_err;
+	__le64	rx_hcfc_msgs;
+	__le64	rx_hcfc_msgs_with_crc_err;
+	__le64	rx_bytes;
+	__le64	rx_runt_bytes;
+	__le64	rx_runt_frames;
+	__le64	rx_stat_discard;
+	__le64	rx_stat_err;
+};
+
+/* hwrm_port_qstats_input (size:320b/40B) */
+struct hwrm_port_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	flags;
+	#define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[5];
+	__le64	tx_stat_host_addr;
+	__le64	rx_stat_host_addr;
+};
+
+/* hwrm_port_qstats_output (size:128b/16B) */
+struct hwrm_port_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tx_stat_size;
+	__le16	rx_stat_size;
+	u8	flags;
+	#define PORT_QSTATS_RESP_FLAGS_CLEARED     0x1UL
+	u8	unused_0[2];
+	u8	valid;
+};
+
+/* tx_port_stats_ext (size:2048b/256B) */
+struct tx_port_stats_ext {
+	__le64	tx_bytes_cos0;
+	__le64	tx_bytes_cos1;
+	__le64	tx_bytes_cos2;
+	__le64	tx_bytes_cos3;
+	__le64	tx_bytes_cos4;
+	__le64	tx_bytes_cos5;
+	__le64	tx_bytes_cos6;
+	__le64	tx_bytes_cos7;
+	__le64	tx_packets_cos0;
+	__le64	tx_packets_cos1;
+	__le64	tx_packets_cos2;
+	__le64	tx_packets_cos3;
+	__le64	tx_packets_cos4;
+	__le64	tx_packets_cos5;
+	__le64	tx_packets_cos6;
+	__le64	tx_packets_cos7;
+	__le64	pfc_pri0_tx_duration_us;
+	__le64	pfc_pri0_tx_transitions;
+	__le64	pfc_pri1_tx_duration_us;
+	__le64	pfc_pri1_tx_transitions;
+	__le64	pfc_pri2_tx_duration_us;
+	__le64	pfc_pri2_tx_transitions;
+	__le64	pfc_pri3_tx_duration_us;
+	__le64	pfc_pri3_tx_transitions;
+	__le64	pfc_pri4_tx_duration_us;
+	__le64	pfc_pri4_tx_transitions;
+	__le64	pfc_pri5_tx_duration_us;
+	__le64	pfc_pri5_tx_transitions;
+	__le64	pfc_pri6_tx_duration_us;
+	__le64	pfc_pri6_tx_transitions;
+	__le64	pfc_pri7_tx_duration_us;
+	__le64	pfc_pri7_tx_transitions;
+};
+
+/* rx_port_stats_ext (size:3904b/488B) */
+struct rx_port_stats_ext {
+	__le64	link_down_events;
+	__le64	continuous_pause_events;
+	__le64	resume_pause_events;
+	__le64	continuous_roce_pause_events;
+	__le64	resume_roce_pause_events;
+	__le64	rx_bytes_cos0;
+	__le64	rx_bytes_cos1;
+	__le64	rx_bytes_cos2;
+	__le64	rx_bytes_cos3;
+	__le64	rx_bytes_cos4;
+	__le64	rx_bytes_cos5;
+	__le64	rx_bytes_cos6;
+	__le64	rx_bytes_cos7;
+	__le64	rx_packets_cos0;
+	__le64	rx_packets_cos1;
+	__le64	rx_packets_cos2;
+	__le64	rx_packets_cos3;
+	__le64	rx_packets_cos4;
+	__le64	rx_packets_cos5;
+	__le64	rx_packets_cos6;
+	__le64	rx_packets_cos7;
+	__le64	pfc_pri0_rx_duration_us;
+	__le64	pfc_pri0_rx_transitions;
+	__le64	pfc_pri1_rx_duration_us;
+	__le64	pfc_pri1_rx_transitions;
+	__le64	pfc_pri2_rx_duration_us;
+	__le64	pfc_pri2_rx_transitions;
+	__le64	pfc_pri3_rx_duration_us;
+	__le64	pfc_pri3_rx_transitions;
+	__le64	pfc_pri4_rx_duration_us;
+	__le64	pfc_pri4_rx_transitions;
+	__le64	pfc_pri5_rx_duration_us;
+	__le64	pfc_pri5_rx_transitions;
+	__le64	pfc_pri6_rx_duration_us;
+	__le64	pfc_pri6_rx_transitions;
+	__le64	pfc_pri7_rx_duration_us;
+	__le64	pfc_pri7_rx_transitions;
+	__le64	rx_bits;
+	__le64	rx_buffer_passed_threshold;
+	__le64	rx_pcs_symbol_err;
+	__le64	rx_corrected_bits;
+	__le64	rx_discard_bytes_cos0;
+	__le64	rx_discard_bytes_cos1;
+	__le64	rx_discard_bytes_cos2;
+	__le64	rx_discard_bytes_cos3;
+	__le64	rx_discard_bytes_cos4;
+	__le64	rx_discard_bytes_cos5;
+	__le64	rx_discard_bytes_cos6;
+	__le64	rx_discard_bytes_cos7;
+	__le64	rx_discard_packets_cos0;
+	__le64	rx_discard_packets_cos1;
+	__le64	rx_discard_packets_cos2;
+	__le64	rx_discard_packets_cos3;
+	__le64	rx_discard_packets_cos4;
+	__le64	rx_discard_packets_cos5;
+	__le64	rx_discard_packets_cos6;
+	__le64	rx_discard_packets_cos7;
+	__le64	rx_fec_corrected_blocks;
+	__le64	rx_fec_uncorrectable_blocks;
+	__le64	rx_filter_miss;
+	__le64	rx_fec_symbol_err;
+};
+
+/* hwrm_port_qstats_ext_input (size:320b/40B) */
+struct hwrm_port_qstats_ext_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	tx_stat_size;
+	__le16	rx_stat_size;
+	u8	flags;
+	#define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0;
+	__le64	tx_stat_host_addr;
+	__le64	rx_stat_host_addr;
+};
+
+/* hwrm_port_qstats_ext_output (size:128b/16B) */
+struct hwrm_port_qstats_ext_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tx_stat_size;
+	__le16	rx_stat_size;
+	__le16	total_active_cos_queues;
+	u8	flags;
+	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED     0x1UL
+	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED                           0x2UL
+	u8	valid;
+};
+
+/* hwrm_port_lpbk_qstats_input (size:256b/32B) */
+struct hwrm_port_lpbk_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	lpbk_stat_size;
+	u8	flags;
+	#define PORT_LPBK_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[5];
+	__le64	lpbk_stat_host_addr;
+};
+
+/* hwrm_port_lpbk_qstats_output (size:128b/16B) */
+struct hwrm_port_lpbk_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	lpbk_stat_size;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* port_lpbk_stats (size:640b/80B) */
+struct port_lpbk_stats {
+	__le64	lpbk_ucast_frames;
+	__le64	lpbk_mcast_frames;
+	__le64	lpbk_bcast_frames;
+	__le64	lpbk_ucast_bytes;
+	__le64	lpbk_mcast_bytes;
+	__le64	lpbk_bcast_bytes;
+	__le64	lpbk_tx_discards;
+	__le64	lpbk_tx_errors;
+	__le64	lpbk_rx_discards;
+	__le64	lpbk_rx_errors;
+};
+
+/* hwrm_port_ecn_qstats_input (size:256b/32B) */
+struct hwrm_port_ecn_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	ecn_stat_buf_size;
+	u8	flags;
+	#define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[3];
+	__le64	ecn_stat_host_addr;
+};
+
+/* hwrm_port_ecn_qstats_output (size:128b/16B) */
+struct hwrm_port_ecn_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	ecn_stat_buf_size;
+	u8	mark_en;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* port_stats_ecn (size:512b/64B) */
+struct port_stats_ecn {
+	__le64	mark_cnt_cos0;
+	__le64	mark_cnt_cos1;
+	__le64	mark_cnt_cos2;
+	__le64	mark_cnt_cos3;
+	__le64	mark_cnt_cos4;
+	__le64	mark_cnt_cos5;
+	__le64	mark_cnt_cos6;
+	__le64	mark_cnt_cos7;
+};
+
+/* hwrm_port_clr_stats_input (size:192b/24B) */
+struct hwrm_port_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	flags;
+	#define PORT_CLR_STATS_REQ_FLAGS_ROCE_COUNTERS     0x1UL
+	u8	unused_0[5];
+};
+
+/* hwrm_port_clr_stats_output (size:128b/16B) */
+struct hwrm_port_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_lpbk_clr_stats_input (size:192b/24B) */
+struct hwrm_port_lpbk_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_lpbk_clr_stats_output (size:128b/16B) */
+struct hwrm_port_lpbk_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_ts_query_input (size:320b/40B) */
+struct hwrm_port_ts_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH             0x1UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_TX            0x0UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_RX            0x1UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_LAST         PORT_TS_QUERY_REQ_FLAGS_PATH_RX
+	#define PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME     0x2UL
+	__le16	port_id;
+	u8	unused_0[2];
+	__le16	enables;
+	#define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT     0x1UL
+	#define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID         0x2UL
+	#define PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET     0x4UL
+	__le16	ts_req_timeout;
+	__le32	ptp_seq_id;
+	__le16	ptp_hdr_offset;
+	u8	unused_1[6];
+};
+
+/* hwrm_port_ts_query_output (size:192b/24B) */
+struct hwrm_port_ts_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	ptp_msg_ts;
+	__le16	ptp_msg_seqid;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_port_phy_qcaps_input (size:192b/24B) */
+struct hwrm_port_phy_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_phy_qcaps_output (size:320b/40B) */
+struct hwrm_port_phy_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED                    0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED          0x2UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_AUTONEG_LPBK_SUPPORTED           0x4UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED         0x8UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET     0x10UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED         0x20UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_FW_MANAGED_LINK_DOWN             0x40UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_NO_FCS                           0x80UL
+	u8	port_cnt;
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_2       0x2UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_3       0x3UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_4       0x4UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_12      0xcUL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST   PORT_PHY_QCAPS_RESP_PORT_CNT_12
+	__le16	supported_speeds_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD     0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB       0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GBHD       0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GB         0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2GB         0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2_5GB       0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10GB        0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_20GB        0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_25GB        0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_40GB        0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_50GB        0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB       0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD      0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB        0x2000UL
+	__le16	supported_speeds_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD     0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB       0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GBHD       0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GB         0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2GB         0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2_5GB       0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10GB        0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_20GB        0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_25GB        0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_40GB        0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_50GB        0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB       0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD      0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB        0x2000UL
+	__le16	supported_speeds_eee_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1     0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB     0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD2     0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_1GB       0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD3     0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD4     0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_10GB      0x40UL
+	__le32	tx_lpi_timer_low;
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_MASK 0xffffffUL
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_SFT 0
+	#define PORT_PHY_QCAPS_RESP_RSVD2_MASK           0xff000000UL
+	#define PORT_PHY_QCAPS_RESP_RSVD2_SFT            24
+	__le32	valid_tx_lpi_timer_high;
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK 0xffffffUL
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_SFT 0
+	#define PORT_PHY_QCAPS_RESP_RSVD_MASK             0xff000000UL
+	#define PORT_PHY_QCAPS_RESP_RSVD_SFT              24
+	__le16	supported_pam4_speeds_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_50G      0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_100G     0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_200G     0x4UL
+	__le16	supported_pam4_speeds_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_50G      0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G     0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G     0x4UL
+	__le16	flags2;
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED           0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED             0x2UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED         0x4UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED           0x8UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_REMOTE_LPBK_UNSUPPORTED     0x10UL
+	u8	internal_port_cnt;
+	u8	unused_0;
+	__le16	supported_speeds2_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_800GB_PAM4_112     0x2000UL
+	__le16	supported_speeds2_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_800GB_PAM4_112     0x2000UL
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_port_phy_i2c_write_input (size:832b/104B) */
+struct hwrm_port_phy_i2c_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET     0x1UL
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER     0x2UL
+	__le16	port_id;
+	u8	i2c_slave_addr;
+	u8	bank_number;
+	__le16	page_number;
+	__le16	page_offset;
+	u8	data_length;
+	u8	unused_1[7];
+	__le32	data[16];
+};
+
+/* hwrm_port_phy_i2c_write_output (size:128b/16B) */
+struct hwrm_port_phy_i2c_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_i2c_read_input (size:320b/40B) */
+struct hwrm_port_phy_i2c_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET     0x1UL
+	#define PORT_PHY_I2C_READ_REQ_ENABLES_BANK_NUMBER     0x2UL
+	__le16	port_id;
+	u8	i2c_slave_addr;
+	u8	bank_number;
+	__le16	page_number;
+	__le16	page_offset;
+	u8	data_length;
+	u8	unused_1[7];
+};
+
+/* hwrm_port_phy_i2c_read_output (size:640b/80B) */
+struct hwrm_port_phy_i2c_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	data[16];
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_mdio_write_input (size:320b/40B) */
+struct hwrm_port_phy_mdio_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	__le16	reg_data;
+	u8	cl45_mdio;
+	u8	unused_1[7];
+};
+
+/* hwrm_port_phy_mdio_write_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_mdio_read_input (size:256b/32B) */
+struct hwrm_port_phy_mdio_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	u8	cl45_mdio;
+	u8	unused_1;
+};
+
+/* hwrm_port_phy_mdio_read_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	reg_data;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_port_led_cfg_input (size:512b/64B) */
+struct hwrm_port_led_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_ID            0x1UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_STATE         0x2UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_COLOR         0x4UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_ON      0x8UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_OFF     0x10UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_GROUP_ID      0x20UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_ID            0x40UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_STATE         0x80UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_COLOR         0x100UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_ON      0x200UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_OFF     0x400UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_GROUP_ID      0x800UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_ID            0x1000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_STATE         0x2000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_COLOR         0x4000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_ON      0x8000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_OFF     0x10000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_GROUP_ID      0x20000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_ID            0x40000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_STATE         0x80000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_COLOR         0x100000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_ON      0x200000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_OFF     0x400000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_GROUP_ID      0x800000UL
+	__le16	port_id;
+	u8	num_leds;
+	u8	rsvd;
+	u8	led0_id;
+	u8	led0_state;
+	#define PORT_LED_CFG_REQ_LED0_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_LAST    PORT_LED_CFG_REQ_LED0_STATE_BLINKALT
+	u8	led0_color;
+	#define PORT_LED_CFG_REQ_LED0_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_LAST      PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER
+	u8	unused_0;
+	__le16	led0_blink_on;
+	__le16	led0_blink_off;
+	u8	led0_group_id;
+	u8	rsvd0;
+	u8	led1_id;
+	u8	led1_state;
+	#define PORT_LED_CFG_REQ_LED1_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_LAST    PORT_LED_CFG_REQ_LED1_STATE_BLINKALT
+	u8	led1_color;
+	#define PORT_LED_CFG_REQ_LED1_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_LAST      PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER
+	u8	unused_1;
+	__le16	led1_blink_on;
+	__le16	led1_blink_off;
+	u8	led1_group_id;
+	u8	rsvd1;
+	u8	led2_id;
+	u8	led2_state;
+	#define PORT_LED_CFG_REQ_LED2_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_LAST    PORT_LED_CFG_REQ_LED2_STATE_BLINKALT
+	u8	led2_color;
+	#define PORT_LED_CFG_REQ_LED2_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_LAST      PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER
+	u8	unused_2;
+	__le16	led2_blink_on;
+	__le16	led2_blink_off;
+	u8	led2_group_id;
+	u8	rsvd2;
+	u8	led3_id;
+	u8	led3_state;
+	#define PORT_LED_CFG_REQ_LED3_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_LAST    PORT_LED_CFG_REQ_LED3_STATE_BLINKALT
+	u8	led3_color;
+	#define PORT_LED_CFG_REQ_LED3_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_LAST      PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER
+	u8	unused_3;
+	__le16	led3_blink_on;
+	__le16	led3_blink_off;
+	u8	led3_group_id;
+	u8	rsvd3;
+};
+
+/* hwrm_port_led_cfg_output (size:128b/16B) */
+struct hwrm_port_led_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_led_qcfg_input (size:192b/24B) */
+struct hwrm_port_led_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_led_qcfg_output (size:448b/56B) */
+struct hwrm_port_led_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_leds;
+	u8	led0_id;
+	u8	led0_type;
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_LAST    PORT_LED_QCFG_RESP_LED0_TYPE_INVALID
+	u8	led0_state;
+	#define PORT_LED_QCFG_RESP_LED0_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_LAST    PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT
+	u8	led0_color;
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_LAST      PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER
+	u8	unused_0;
+	__le16	led0_blink_on;
+	__le16	led0_blink_off;
+	u8	led0_group_id;
+	u8	led1_id;
+	u8	led1_type;
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_LAST    PORT_LED_QCFG_RESP_LED1_TYPE_INVALID
+	u8	led1_state;
+	#define PORT_LED_QCFG_RESP_LED1_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_LAST    PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT
+	u8	led1_color;
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_LAST      PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER
+	u8	unused_1;
+	__le16	led1_blink_on;
+	__le16	led1_blink_off;
+	u8	led1_group_id;
+	u8	led2_id;
+	u8	led2_type;
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_LAST    PORT_LED_QCFG_RESP_LED2_TYPE_INVALID
+	u8	led2_state;
+	#define PORT_LED_QCFG_RESP_LED2_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_LAST    PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT
+	u8	led2_color;
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_LAST      PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER
+	u8	unused_2;
+	__le16	led2_blink_on;
+	__le16	led2_blink_off;
+	u8	led2_group_id;
+	u8	led3_id;
+	u8	led3_type;
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_LAST    PORT_LED_QCFG_RESP_LED3_TYPE_INVALID
+	u8	led3_state;
+	#define PORT_LED_QCFG_RESP_LED3_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_LAST    PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT
+	u8	led3_color;
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_LAST      PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER
+	u8	unused_3;
+	__le16	led3_blink_on;
+	__le16	led3_blink_off;
+	u8	led3_group_id;
+	u8	unused_4[6];
+	u8	valid;
+};
+
+/* hwrm_port_led_qcaps_input (size:192b/24B) */
+struct hwrm_port_led_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_led_qcaps_output (size:384b/48B) */
+struct hwrm_port_led_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_leds;
+	u8	unused[3];
+	u8	led0_id;
+	u8	led0_type;
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_LAST    PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID
+	u8	led0_group_id;
+	u8	unused_0;
+	__le16	led0_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led0_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_RSVD                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_AMBER_SUPPORTED      0x2UL
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GREEN_SUPPORTED      0x4UL
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GRNAMB_SUPPORTED     0x8UL
+	u8	led1_id;
+	u8	led1_type;
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_LAST    PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID
+	u8	led1_group_id;
+	u8	unused_1;
+	__le16	led1_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led1_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_RSVD                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_AMBER_SUPPORTED      0x2UL
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GREEN_SUPPORTED      0x4UL
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GRNAMB_SUPPORTED     0x8UL
+	u8	led2_id;
+	u8	led2_type;
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_LAST    PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID
+	u8	led2_group_id;
+	u8	unused_2;
+	__le16	led2_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led2_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_RSVD                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_AMBER_SUPPORTED      0x2UL
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GREEN_SUPPORTED      0x4UL
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GRNAMB_SUPPORTED     0x8UL
+	u8	led3_id;
+	u8	led3_type;
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_LAST    PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID
+	u8	led3_group_id;
+	u8	unused_3;
+	__le16	led3_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led3_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_RSVD                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_AMBER_SUPPORTED      0x2UL
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GREEN_SUPPORTED      0x4UL
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GRNAMB_SUPPORTED     0x8UL
+	u8	unused_4[3];
+	u8	valid;
+};
+
+/* hwrm_port_mac_qcaps_input (size:192b/24B) */
+struct hwrm_port_mac_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_mac_qcaps_output (size:128b/16B) */
+struct hwrm_port_mac_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED     0x1UL
+	#define PORT_MAC_QCAPS_RESP_FLAGS_REMOTE_LPBK_SUPPORTED        0x2UL
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_queue_qportcfg_input (size:192b/24B) */
+struct hwrm_queue_qportcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH     0x1UL
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_TX    0x0UL
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX    0x1UL
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_LAST QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX
+	__le16	port_id;
+	u8	drv_qmap_cap;
+	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_DISABLED 0x0UL
+	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED  0x1UL
+	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_LAST    QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED
+	u8	unused_0;
+};
+
+/* hwrm_queue_qportcfg_output (size:1344b/168B) */
+struct hwrm_queue_qportcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	max_configurable_queues;
+	u8	max_configurable_lossless_queues;
+	u8	queue_cfg_allowed;
+	u8	queue_cfg_info;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG             0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_USE_PROFILE_TYPE     0x2UL
+	u8	queue_pfcenable_cfg_allowed;
+	u8	queue_pri2cos_cfg_allowed;
+	u8	queue_cos2bw_cfg_allowed;
+	u8	queue_id0;
+	u8	queue_id0_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id1;
+	u8	queue_id1_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id2;
+	u8	queue_id2_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id3;
+	u8	queue_id3_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id4;
+	u8	queue_id4_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id5;
+	u8	queue_id5_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id6;
+	u8	queue_id6_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id7;
+	u8	queue_id7_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id0_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	char	qid0_name[16];
+	char	qid1_name[16];
+	char	qid2_name[16];
+	char	qid3_name[16];
+	char	qid4_name[16];
+	char	qid5_name[16];
+	char	qid6_name[16];
+	char	qid7_name[16];
+	u8	queue_id1_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id2_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id3_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id4_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id5_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id6_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id7_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	valid;
+};
+
+/* hwrm_queue_qcfg_input (size:192b/24B) */
+struct hwrm_queue_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_QCFG_REQ_FLAGS_PATH     0x1UL
+	#define QUEUE_QCFG_REQ_FLAGS_PATH_TX    0x0UL
+	#define QUEUE_QCFG_REQ_FLAGS_PATH_RX    0x1UL
+	#define QUEUE_QCFG_REQ_FLAGS_PATH_LAST QUEUE_QCFG_REQ_FLAGS_PATH_RX
+	__le32	queue_id;
+};
+
+/* hwrm_queue_qcfg_output (size:128b/16B) */
+struct hwrm_queue_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	queue_len;
+	u8	service_profile;
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSY    0x0UL
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSLESS 0x1UL
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN  0xffUL
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LAST    QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN
+	u8	queue_cfg_info;
+	#define QUEUE_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_queue_cfg_input (size:320b/40B) */
+struct hwrm_queue_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_CFG_REQ_FLAGS_PATH_MASK 0x3UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_SFT  0
+	#define QUEUE_CFG_REQ_FLAGS_PATH_TX     0x0UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_RX     0x1UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_LAST  QUEUE_CFG_REQ_FLAGS_PATH_BIDIR
+	__le32	enables;
+	#define QUEUE_CFG_REQ_ENABLES_DFLT_LEN            0x1UL
+	#define QUEUE_CFG_REQ_ENABLES_SERVICE_PROFILE     0x2UL
+	__le32	queue_id;
+	__le32	dflt_len;
+	u8	service_profile;
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY    0x0UL
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS 0x1UL
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN  0xffUL
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LAST    QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN
+	u8	unused_0[7];
+};
+
+/* hwrm_queue_cfg_output (size:128b/16B) */
+struct hwrm_queue_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcenable_qcfg_input (size:192b/24B) */
+struct hwrm_queue_pfcenable_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_queue_pfcenable_qcfg_output (size:128b/16B) */
+struct hwrm_queue_pfcenable_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_ENABLED              0x1UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_ENABLED              0x2UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_ENABLED              0x4UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_ENABLED              0x8UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_ENABLED              0x10UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_ENABLED              0x20UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_ENABLED              0x40UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_ENABLED              0x80UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcenable_cfg_input (size:192b/24B) */
+struct hwrm_queue_pfcenable_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED              0x1UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED              0x2UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED              0x4UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED              0x8UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED              0x10UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED              0x20UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED              0x40UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED              0x80UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
+	__le16	port_id;
+	u8	unused_0[2];
+};
+
+/* hwrm_queue_pfcenable_cfg_output (size:128b/16B) */
+struct hwrm_queue_pfcenable_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_pri2cos_qcfg_input (size:192b/24B) */
+struct hwrm_queue_pri2cos_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH      0x1UL
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_TX     0x0UL
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX     0x1UL
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN     0x2UL
+	u8	port_id;
+	u8	unused_0[3];
+};
+
+/* hwrm_queue_pri2cos_qcfg_output (size:192b/24B) */
+struct hwrm_queue_pri2cos_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	pri0_cos_queue_id;
+	u8	pri1_cos_queue_id;
+	u8	pri2_cos_queue_id;
+	u8	pri3_cos_queue_id;
+	u8	pri4_cos_queue_id;
+	u8	pri5_cos_queue_id;
+	u8	pri6_cos_queue_id;
+	u8	pri7_cos_queue_id;
+	u8	queue_cfg_info;
+	#define QUEUE_PRI2COS_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_queue_pri2cos_cfg_input (size:320b/40B) */
+struct hwrm_queue_pri2cos_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_MASK 0x3UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_SFT  0
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_TX     0x0UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_RX     0x1UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN     0x4UL
+	__le32	enables;
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID     0x1UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI1_COS_QUEUE_ID     0x2UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI2_COS_QUEUE_ID     0x4UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI3_COS_QUEUE_ID     0x8UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI4_COS_QUEUE_ID     0x10UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI5_COS_QUEUE_ID     0x20UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI6_COS_QUEUE_ID     0x40UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI7_COS_QUEUE_ID     0x80UL
+	u8	port_id;
+	u8	pri0_cos_queue_id;
+	u8	pri1_cos_queue_id;
+	u8	pri2_cos_queue_id;
+	u8	pri3_cos_queue_id;
+	u8	pri4_cos_queue_id;
+	u8	pri5_cos_queue_id;
+	u8	pri6_cos_queue_id;
+	u8	pri7_cos_queue_id;
+	u8	unused_0[7];
+};
+
+/* hwrm_queue_pri2cos_cfg_output (size:128b/16B) */
+struct hwrm_queue_pri2cos_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_cos2bw_qcfg_input (size:192b/24B) */
+struct hwrm_queue_cos2bw_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_queue_cos2bw_qcfg_output (size:896b/112B) */
+struct hwrm_queue_cos2bw_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	queue_id0;
+	u8	unused_0;
+	__le16	unused_1;
+	__le32	queue_id0_min_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	queue_id0_max_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	queue_id0_tsa_assign;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
+	u8	queue_id0_pri_lvl;
+	u8	queue_id0_bw_weight;
+	struct {
+		u8	queue_id;
+		__le32	queue_id_min_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
+		__le32	queue_id_max_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
+		u8	queue_id_tsa_assign;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
+		u8	queue_id_pri_lvl;
+		u8	queue_id_bw_weight;
+	} __packed cfg[7];
+	u8	unused_2[4];
+	u8	valid;
+};
+
+/* hwrm_queue_cos2bw_cfg_input (size:1024b/128B) */
+struct hwrm_queue_cos2bw_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID     0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID1_VALID     0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID2_VALID     0x4UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID3_VALID     0x8UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID4_VALID     0x10UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID5_VALID     0x20UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID6_VALID     0x40UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID7_VALID     0x80UL
+	__le16	port_id;
+	u8	queue_id0;
+	u8	unused_0;
+	__le32	queue_id0_min_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	queue_id0_max_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	queue_id0_tsa_assign;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
+	u8	queue_id0_pri_lvl;
+	u8	queue_id0_bw_weight;
+	struct {
+		u8	queue_id;
+		__le32	queue_id_min_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
+		__le32	queue_id_max_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
+		u8	queue_id_tsa_assign;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
+		u8	queue_id_pri_lvl;
+		u8	queue_id_bw_weight;
+	} __packed cfg[7];
+	u8	unused_1[5];
+};
+
+/* hwrm_queue_cos2bw_cfg_output (size:128b/16B) */
+struct hwrm_queue_cos2bw_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_dscp_qcaps_input (size:192b/24B) */
+struct hwrm_queue_dscp_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	port_id;
+	u8	unused_0[7];
+};
+
+/* hwrm_queue_dscp_qcaps_output (size:128b/16B) */
+struct hwrm_queue_dscp_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_dscp_bits;
+	u8	unused_0;
+	__le16	max_entries;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_queue_dscp2pri_qcfg_input (size:256b/32B) */
+struct hwrm_queue_dscp2pri_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	dest_data_addr;
+	u8	port_id;
+	u8	unused_0;
+	__le16	dest_data_buffer_size;
+	u8	unused_1[4];
+};
+
+/* hwrm_queue_dscp2pri_qcfg_output (size:128b/16B) */
+struct hwrm_queue_dscp2pri_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	entry_cnt;
+	u8	default_pri;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_queue_dscp2pri_cfg_input (size:320b/40B) */
+struct hwrm_queue_dscp2pri_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	src_data_addr;
+	__le32	flags;
+	#define QUEUE_DSCP2PRI_CFG_REQ_FLAGS_USE_HW_DEFAULT_PRI     0x1UL
+	__le32	enables;
+	#define QUEUE_DSCP2PRI_CFG_REQ_ENABLES_DEFAULT_PRI     0x1UL
+	u8	port_id;
+	u8	default_pri;
+	__le16	entry_cnt;
+	u8	unused_0[4];
+};
+
+/* hwrm_queue_dscp2pri_cfg_output (size:128b/16B) */
+struct hwrm_queue_dscp2pri_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcwd_timeout_qcaps_input (size:128b/16B) */
+struct hwrm_queue_pfcwd_timeout_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_queue_pfcwd_timeout_qcaps_output (size:128b/16B) */
+struct hwrm_queue_pfcwd_timeout_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	max_pfcwd_timeout;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcwd_timeout_cfg_input (size:192b/24B) */
+struct hwrm_queue_pfcwd_timeout_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	pfcwd_timeout_value;
+	u8	unused_0[6];
+};
+
+/* hwrm_queue_pfcwd_timeout_cfg_output (size:128b/16B) */
+struct hwrm_queue_pfcwd_timeout_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcwd_timeout_qcfg_input (size:128b/16B) */
+struct hwrm_queue_pfcwd_timeout_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_queue_pfcwd_timeout_qcfg_output (size:128b/16B) */
+struct hwrm_queue_pfcwd_timeout_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	pfcwd_timeout_value;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_alloc_input (size:192b/24B) */
+struct hwrm_vnic_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_ALLOC_REQ_FLAGS_DEFAULT                  0x1UL
+	#define VNIC_ALLOC_REQ_FLAGS_VIRTIO_NET_FID_VALID     0x2UL
+	#define VNIC_ALLOC_REQ_FLAGS_VNIC_ID_VALID            0x4UL
+	__le16	virtio_net_fid;
+	__le16	vnic_id;
+};
+
+/* hwrm_vnic_alloc_output (size:128b/16B) */
+struct hwrm_vnic_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	vnic_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_vnic_update_input (size:256b/32B) */
+struct hwrm_vnic_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	__le32	enables;
+	#define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID               0x1UL
+	#define VNIC_UPDATE_REQ_ENABLES_MRU_VALID                      0x2UL
+	#define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID     0x4UL
+	u8	vnic_state;
+	#define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL
+	#define VNIC_UPDATE_REQ_VNIC_STATE_DROP   0x1UL
+	#define VNIC_UPDATE_REQ_VNIC_STATE_LAST  VNIC_UPDATE_REQ_VNIC_STATE_DROP
+	u8	metadata_format_type;
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4
+	__le16	mru;
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_update_output (size:128b/16B) */
+struct hwrm_vnic_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_free_input (size:192b/24B) */
+struct hwrm_vnic_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_free_output (size:128b/16B) */
+struct hwrm_vnic_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_cfg_input (size:384b/48B) */
+struct hwrm_vnic_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_CFG_REQ_FLAGS_DEFAULT                              0x1UL
+	#define VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE                      0x2UL
+	#define VNIC_CFG_REQ_FLAGS_BD_STALL_MODE                        0x4UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE                  0x8UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_ONLY_VNIC_MODE                  0x10UL
+	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE                     0x20UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE     0x40UL
+	#define VNIC_CFG_REQ_FLAGS_PORTCOS_MAPPING_MODE                 0x80UL
+	__le32	enables;
+	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP            0x1UL
+	#define VNIC_CFG_REQ_ENABLES_RSS_RULE                 0x2UL
+	#define VNIC_CFG_REQ_ENABLES_COS_RULE                 0x4UL
+	#define VNIC_CFG_REQ_ENABLES_LB_RULE                  0x8UL
+	#define VNIC_CFG_REQ_ENABLES_MRU                      0x10UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID       0x20UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID     0x40UL
+	#define VNIC_CFG_REQ_ENABLES_QUEUE_ID                 0x80UL
+	#define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE          0x100UL
+	#define VNIC_CFG_REQ_ENABLES_L2_CQE_MODE              0x200UL
+	#define VNIC_CFG_REQ_ENABLES_RAW_QP_ID                0x400UL
+	__le16	vnic_id;
+	__le16	dflt_ring_grp;
+	__le16	rss_rule;
+	__le16	cos_rule;
+	__le16	lb_rule;
+	__le16	mru;
+	__le16	default_rx_ring_id;
+	__le16	default_cmpl_ring_id;
+	__le16	queue_id;
+	u8	rx_csum_v2_mode;
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_DEFAULT 0x0UL
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_ALL_OK  0x1UL
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX     0x2UL
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_LAST   VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX
+	u8	l2_cqe_mode;
+	#define VNIC_CFG_REQ_L2_CQE_MODE_DEFAULT    0x0UL
+	#define VNIC_CFG_REQ_L2_CQE_MODE_COMPRESSED 0x1UL
+	#define VNIC_CFG_REQ_L2_CQE_MODE_MIXED      0x2UL
+	#define VNIC_CFG_REQ_L2_CQE_MODE_LAST      VNIC_CFG_REQ_L2_CQE_MODE_MIXED
+	__le32	raw_qp_id;
+};
+
+/* hwrm_vnic_cfg_output (size:128b/16B) */
+struct hwrm_vnic_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_qcaps_input (size:192b/24B) */
+struct hwrm_vnic_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_qcaps_output (size:192b/24B) */
+struct hwrm_vnic_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	mru;
+	u8	unused_0[2];
+	__le32	flags;
+	#define VNIC_QCAPS_RESP_FLAGS_UNUSED                                  0x1UL
+	#define VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP                          0x2UL
+	#define VNIC_QCAPS_RESP_FLAGS_BD_STALL_CAP                            0x4UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP                      0x8UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP                      0x10UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                         0x20UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP         0x40UL
+	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                       0x80UL
+	#define VNIC_QCAPS_RESP_FLAGS_COS_ASSIGNMENT_CAP                      0x100UL
+	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V2_CAP                          0x200UL
+	#define VNIC_QCAPS_RESP_FLAGS_VNIC_STATE_CAP                          0x400UL
+	#define VNIC_QCAPS_RESP_FLAGS_VIRTIO_NET_VNIC_ALLOC_CAP               0x800UL
+	#define VNIC_QCAPS_RESP_FLAGS_METADATA_FORMAT_CAP                     0x1000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_STRICT_HASH_TYPE_CAP                0x2000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP                 0x4000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CAP           0x8000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_XOR_CAP                0x10000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CHKSM_CAP     0x20000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP                 0x40000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V3_CAP                          0x80000UL
+	#define VNIC_QCAPS_RESP_FLAGS_L2_CQE_MODE_CAP                         0x100000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV4_CAP               0x200000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV4_CAP              0x400000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV6_CAP               0x800000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP              0x1000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_TRUSTED_VF_CAP            0x2000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_PORTCOS_MAPPING_MODE                    0x4000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED              0x8000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP                  0x10000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP                       0x20000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP                            0x40000000UL
+	__le16	max_aggs_supported;
+	u8	unused_1[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_tpa_cfg_input (size:384b/48B) */
+struct hwrm_vnic_tpa_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_TPA_CFG_REQ_FLAGS_TPA                       0x1UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_ENCAP_TPA                 0x2UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_RSC_WND_UPDATE            0x4UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_GRO                       0x8UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_ECN              0x10UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_IPID_CHECK            0x40UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_TTL_CHECK             0x80UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_PACK_AS_GRO           0x100UL
+	__le32	enables;
+	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS      0x1UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS          0x2UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_TIMER     0x4UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN       0x8UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN        0x10UL
+	__le16	vnic_id;
+	__le16	max_agg_segs;
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_1   0x0UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_2   0x1UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_4   0x2UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_8   0x3UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX 0x1fUL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_LAST VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX
+	__le16	max_aggs;
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_1   0x0UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_2   0x1UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_4   0x2UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_8   0x3UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_16  0x4UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_MAX 0x7UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_LAST VNIC_TPA_CFG_REQ_MAX_AGGS_MAX
+	u8	unused_0[2];
+	__le32	max_agg_timer;
+	__le32	min_agg_len;
+	__le32	tnl_tpa_en_bitmap;
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE             0x8UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4            0x10UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6            0x20UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_tpa_cfg_output (size:128b/16B) */
+struct hwrm_vnic_tpa_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_tpa_qcfg_input (size:192b/24B) */
+struct hwrm_vnic_tpa_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vnic_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_vnic_tpa_qcfg_output (size:256b/32B) */
+struct hwrm_vnic_tpa_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define VNIC_TPA_QCFG_RESP_FLAGS_TPA                       0x1UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_ENCAP_TPA                 0x2UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_RSC_WND_UPDATE            0x4UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO                       0x8UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_ECN              0x10UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_IPID_CHECK            0x40UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_TTL_CHECK             0x80UL
+	__le16	max_agg_segs;
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_1   0x0UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_2   0x1UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_4   0x2UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_8   0x3UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX 0x1fUL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX
+	__le16	max_aggs;
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_1   0x0UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_2   0x1UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_4   0x2UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_8   0x3UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_16  0x4UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX 0x7UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX
+	__le32	max_agg_timer;
+	__le32	min_agg_len;
+	__le32	tnl_tpa_en_bitmap;
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE             0x8UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV4            0x10UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV6            0x20UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_vnic_rss_cfg_input (size:384b/48B) */
+struct hwrm_vnic_rss_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	hash_type;
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4                0x1UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4            0x2UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4            0x4UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6                0x8UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6            0x10UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6            0x20UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4         0x80UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4        0x100UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6         0x200UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6        0x400UL
+	__le16	vnic_id;
+	u8	ring_table_pair_index;
+	u8	hash_mode_flags;
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT         0x1UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
+	__le64	ring_grp_tbl_addr;
+	__le64	hash_key_tbl_addr;
+	__le16	rss_ctx_idx;
+	u8	flags;
+	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE               0x1UL
+	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE               0x2UL
+	#define VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT     0x4UL
+	u8	ring_select_mode;
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ          0x0UL
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_XOR               0x1UL
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_LAST             VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_rss_cfg_output (size:128b/16B) */
+struct hwrm_vnic_rss_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_rss_cfg_cmd_err (size:64b/8B) */
+struct hwrm_vnic_rss_cfg_cmd_err {
+	u8	code;
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_UNKNOWN                      0x0UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY          0x1UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_UNABLE_TO_GET_RSS_CFG        0x2UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_TYPE_UNSUPPORTED        0x3UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_TYPE_ERR                0x4UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_MODE_FAIL               0x5UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_RING_GRP_TABLE_ALLOC_ERR     0x6UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_HASH_KEY_ALLOC_ERR           0x7UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_DMA_FAILED                   0x8UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_RX_RING_ALLOC_ERR            0x9UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_CMPL_RING_ALLOC_ERR          0xaUL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_HW_SET_RSS_FAILED            0xbUL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_CTX_INVALID                  0xcUL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_VNIC_INVALID                 0xdUL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_VNIC_RING_TABLE_PAIR_INVALID 0xeUL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_LAST                        VNIC_RSS_CFG_CMD_ERR_CODE_VNIC_RING_TABLE_PAIR_INVALID
+	u8	unused_0[7];
+};
+
+/* hwrm_vnic_rss_qcfg_input (size:192b/24B) */
+struct hwrm_vnic_rss_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	rss_ctx_idx;
+	__le16	vnic_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_rss_qcfg_output (size:512b/64B) */
+struct hwrm_vnic_rss_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	hash_type;
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV4                0x1UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV4            0x2UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV4            0x4UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6                0x8UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV6            0x10UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV6            0x20UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV4         0x80UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV4        0x100UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV6         0x200UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV6        0x400UL
+	u8	unused_0[4];
+	__le32	hash_key[10];
+	u8	hash_mode_flags;
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_DEFAULT         0x1UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
+	u8	ring_select_mode;
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ          0x0UL
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_XOR               0x1UL
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_LAST             VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
+	u8	unused_1[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_plcmodes_cfg_input (size:320b/40B) */
+struct hwrm_vnic_plcmodes_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_REGULAR_PLACEMENT     0x1UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT       0x2UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4              0x4UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6              0x8UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_FCOE              0x10UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_ROCE              0x20UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_VIRTIO_PLACEMENT      0x40UL
+	__le32	enables;
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID      0x1UL
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_OFFSET_VALID        0x2UL
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID     0x4UL
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_MAX_BDS_VALID           0x8UL
+	__le32	vnic_id;
+	__le16	jumbo_thresh;
+	__le16	hds_offset;
+	__le16	hds_threshold;
+	__le16	max_bds;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_plcmodes_cfg_output (size:128b/16B) */
+struct hwrm_vnic_plcmodes_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_plcmodes_cfg_cmd_err (size:64b/8B) */
+struct hwrm_vnic_plcmodes_cfg_cmd_err {
+	u8	code;
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_UNKNOWN               0x0UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD 0x1UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_LAST                 VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD
+	u8	unused_0[7];
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_alloc_input (size:128b/16B) */
+struct hwrm_vnic_rss_cos_lb_ctx_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_alloc_output (size:128b/16B) */
+struct hwrm_vnic_rss_cos_lb_ctx_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	rss_cos_lb_ctx_id;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_free_input (size:192b/24B) */
+struct hwrm_vnic_rss_cos_lb_ctx_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	rss_cos_lb_ctx_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_free_output (size:128b/16B) */
+struct hwrm_vnic_rss_cos_lb_ctx_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_alloc_input (size:768b/96B) */
+struct hwrm_ring_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG              0x2UL
+	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID         0x8UL
+	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID              0x20UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID          0x40UL
+	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID          0x80UL
+	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID         0x100UL
+	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                   0x200UL
+	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE            0x400UL
+	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID        0x800UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RATE_PROFILE_VALID     0x1000UL
+	#define RING_ALLOC_REQ_ENABLES_DPI_VALID                 0x2000UL
+	u8	ring_type;
+	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
+	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
+	#define RING_ALLOC_REQ_RING_TYPE_RX        0x2UL
+	#define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL
+	#define RING_ALLOC_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_ALLOC_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_NQ
+	u8	cmpl_coal_cnt;
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_OFF 0x0UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_4   0x1UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_8   0x2UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_12  0x3UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_16  0x4UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_24  0x5UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_32  0x6UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_48  0x7UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64  0x8UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_96  0x9UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_128 0xaUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_192 0xbUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_256 0xcUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_320 0xdUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_384 0xeUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX 0xfUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_LAST    RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX
+	__le16	flags;
+	#define RING_ALLOC_REQ_FLAGS_RX_SOP_PAD                        0x1UL
+	#define RING_ALLOC_REQ_FLAGS_DISABLE_CQ_OVERFLOW_DETECTION     0x2UL
+	#define RING_ALLOC_REQ_FLAGS_NQ_DBR_PACING                     0x4UL
+	#define RING_ALLOC_REQ_FLAGS_TX_PKT_TS_CMPL_ENABLE             0x8UL
+	__le64	page_tbl_addr;
+	__le32	fbo;
+	u8	page_size;
+	u8	page_tbl_depth;
+	__le16	schq_id;
+	__le32	length;
+	__le16	logical_id;
+	__le16	cmpl_ring_id;
+	__le16	queue_id;
+	__le16	rx_buf_size;
+	__le16	rx_ring_id;
+	__le16	nq_ring_id;
+	__le16	ring_arb_cfg;
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK      0xfUL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT       0
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SP          0x1UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ         0x2UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_LAST       RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ
+	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_MASK            0xf0UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_SFT             4
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_MASK 0xff00UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_SFT 8
+	__le16	steering_tag;
+	__le32	reserved3;
+	__le32	stat_ctx_id;
+	__le32	reserved4;
+	__le32	max_bw;
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_SFT              0
+	#define RING_ALLOC_REQ_MAX_BW_SCALE                     0x10000000UL
+	#define RING_ALLOC_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define RING_ALLOC_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define RING_ALLOC_REQ_MAX_BW_SCALE_LAST                 RING_ALLOC_REQ_MAX_BW_SCALE_BYTES
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_LAST         RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	int_mode;
+	#define RING_ALLOC_REQ_INT_MODE_LEGACY 0x0UL
+	#define RING_ALLOC_REQ_INT_MODE_RSVD   0x1UL
+	#define RING_ALLOC_REQ_INT_MODE_MSIX   0x2UL
+	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
+	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
+	u8	mpc_chnls_type;
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TCE     0x0UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RCE     0x1UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TE_CFA  0x2UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
+	u8	rx_rate_profile_sel;
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_DEFAULT   0x0UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE 0x1UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_LAST     RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE
+	u8	unused_4;
+	__le64	cq_handle;
+	__le16	dpi;
+	__le16	unused_5[3];
+};
+
+/* hwrm_ring_alloc_output (size:128b/16B) */
+struct hwrm_ring_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	ring_id;
+	__le16	logical_ring_id;
+	u8	push_buffer_index;
+	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
+	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
+	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_LAST       RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
+	u8	unused_0[2];
+	u8	valid;
+};
+
+/* hwrm_ring_free_input (size:256b/32B) */
+struct hwrm_ring_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define RING_FREE_REQ_RING_TYPE_L2_CMPL   0x0UL
+	#define RING_FREE_REQ_RING_TYPE_TX        0x1UL
+	#define RING_FREE_REQ_RING_TYPE_RX        0x2UL
+	#define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL
+	#define RING_FREE_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_FREE_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_NQ
+	u8	flags;
+	#define RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID 0x1UL
+	#define RING_FREE_REQ_FLAGS_LAST             RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID
+	__le16	ring_id;
+	__le32	prod_idx;
+	__le32	opaque;
+	__le32	unused_1;
+};
+
+/* hwrm_ring_free_output (size:128b/16B) */
+struct hwrm_ring_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_reset_input (size:192b/24B) */
+struct hwrm_ring_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define RING_RESET_REQ_RING_TYPE_L2_CMPL     0x0UL
+	#define RING_RESET_REQ_RING_TYPE_TX          0x1UL
+	#define RING_RESET_REQ_RING_TYPE_RX          0x2UL
+	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL   0x3UL
+	#define RING_RESET_REQ_RING_TYPE_RX_RING_GRP 0x6UL
+	#define RING_RESET_REQ_RING_TYPE_LAST       RING_RESET_REQ_RING_TYPE_RX_RING_GRP
+	u8	unused_0;
+	__le16	ring_id;
+	u8	unused_1[4];
+};
+
+/* hwrm_ring_reset_output (size:128b/16B) */
+struct hwrm_ring_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	push_buffer_index;
+	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
+	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
+	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_LAST       RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
+	u8	unused_0[3];
+	u8	consumer_idx[3];
+	u8	valid;
+};
+
+/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
+struct hwrm_ring_aggint_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */
+struct hwrm_ring_aggint_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	cmpl_params;
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN                  0x1UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX                  0x2UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET                      0x4UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE                        0x8UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR                0x10UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT     0x20UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR                0x40UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT     0x80UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT                0x100UL
+	__le32	nq_params;
+	#define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN     0x1UL
+	__le16	num_cmpl_dma_aggr_min;
+	__le16	num_cmpl_dma_aggr_max;
+	__le16	num_cmpl_dma_aggr_during_int_min;
+	__le16	num_cmpl_dma_aggr_during_int_max;
+	__le16	cmpl_aggr_dma_tmr_min;
+	__le16	cmpl_aggr_dma_tmr_max;
+	__le16	cmpl_aggr_dma_tmr_during_int_min;
+	__le16	cmpl_aggr_dma_tmr_during_int_max;
+	__le16	int_lat_tmr_min_min;
+	__le16	int_lat_tmr_min_max;
+	__le16	int_lat_tmr_max_min;
+	__le16	int_lat_tmr_max_max;
+	__le16	num_cmpl_aggr_int_min;
+	__le16	num_cmpl_aggr_int_max;
+	__le16	timer_units;
+	u8	unused_0[1];
+	u8	valid;
+};
+
+/* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */
+struct hwrm_ring_cmpl_ring_qaggint_params_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	ring_id;
+	__le16	flags;
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_MASK 0x3UL
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_SFT 0
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_IS_NQ        0x4UL
+	u8	unused_0[4];
+};
+
+/* hwrm_ring_cmpl_ring_qaggint_params_output (size:256b/32B) */
+struct hwrm_ring_cmpl_ring_qaggint_params_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	flags;
+	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_TIMER_RESET     0x1UL
+	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_RING_IDLE       0x2UL
+	__le16	num_cmpl_dma_aggr;
+	__le16	num_cmpl_dma_aggr_during_int;
+	__le16	cmpl_aggr_dma_tmr;
+	__le16	cmpl_aggr_dma_tmr_during_int;
+	__le16	int_lat_tmr_min;
+	__le16	int_lat_tmr_max;
+	__le16	num_cmpl_aggr_int;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_cmpl_ring_cfg_aggint_params_input (size:320b/40B) */
+struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	ring_id;
+	__le16	flags;
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET     0x1UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE       0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ           0x4UL
+	__le16	num_cmpl_dma_aggr;
+	__le16	num_cmpl_dma_aggr_during_int;
+	__le16	cmpl_aggr_dma_tmr;
+	__le16	cmpl_aggr_dma_tmr_during_int;
+	__le16	int_lat_tmr_min;
+	__le16	int_lat_tmr_max;
+	__le16	num_cmpl_aggr_int;
+	__le16	enables;
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR                0x1UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT     0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR                0x4UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN                  0x8UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX                  0x10UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT                0x20UL
+	u8	unused_0[4];
+};
+
+/* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */
+struct hwrm_ring_cmpl_ring_cfg_aggint_params_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_grp_alloc_input (size:192b/24B) */
+struct hwrm_ring_grp_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	cr;
+	__le16	rr;
+	__le16	ar;
+	__le16	sc;
+};
+
+/* hwrm_ring_grp_alloc_output (size:128b/16B) */
+struct hwrm_ring_grp_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	ring_group_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_ring_grp_free_input (size:192b/24B) */
+struct hwrm_ring_grp_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	ring_group_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_ring_grp_free_output (size:128b/16B) */
+struct hwrm_ring_grp_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+#define DEFAULT_FLOW_ID 0xFFFFFFFFUL
+#define ROCEV1_FLOW_ID 0xFFFFFFFEUL
+#define ROCEV2_FLOW_ID 0xFFFFFFFDUL
+#define ROCEV2_CNP_FLOW_ID 0xFFFFFFFCUL
+
+/* hwrm_cfa_l2_filter_alloc_input (size:768b/96B) */
+struct hwrm_cfa_l2_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH              0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_TX             0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX             0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_LAST          CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_LOOPBACK          0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_DROP              0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST         0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_MASK      0x30UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_SFT       4
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_NO_ROCE_L2  (0x0UL << 4)
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_L2          (0x1UL << 4)
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE        (0x2UL << 4)
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_LAST       CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_XDP_DISABLE       0x40UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_SOURCE_VALID      0x80UL
+	__le32	enables;
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR             0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK        0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN            0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN_MASK       0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN            0x10UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK       0x20UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR           0x40UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR_MASK      0x80UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN          0x100UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN_MASK     0x200UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN          0x400UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN_MASK     0x800UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_TYPE            0x1000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_ID              0x2000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE         0x4000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID              0x8000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID      0x10000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS           0x20000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_NUM_VLANS         0x40000UL
+	u8	l2_addr[6];
+	u8	num_vlans;
+	u8	t_num_vlans;
+	u8	l2_addr_mask[6];
+	__le16	l2_ovlan;
+	__le16	l2_ovlan_mask;
+	__le16	l2_ivlan;
+	__le16	l2_ivlan_mask;
+	u8	unused_1[2];
+	u8	t_l2_addr[6];
+	u8	unused_2[2];
+	u8	t_l2_addr_mask[6];
+	__le16	t_l2_ovlan;
+	__le16	t_l2_ovlan_mask;
+	__le16	t_l2_ivlan;
+	__le16	t_l2_ivlan_mask;
+	u8	src_type;
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_NPORT 0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_PF    0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VF    0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VNIC  0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_KONG  0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_APE   0x5UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_BONO  0x6UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG  0x7UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_LAST CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG
+	u8	unused_3;
+	__le32	src_id;
+	u8	tunnel_type;
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	unused_4;
+	__le16	dst_id;
+	__le16	mirror_vnic_id;
+	u8	pri_hint;
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER    0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_ABOVE_FILTER 0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_BELOW_FILTER 0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MAX          0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN          0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_LAST        CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN
+	u8	unused_5;
+	__le32	unused_6;
+	__le64	l2_filter_id_hint;
+};
+
+/* hwrm_cfa_l2_filter_alloc_output (size:192b/24B) */
+struct hwrm_cfa_l2_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	l2_filter_id;
+	__le32	flow_id;
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_l2_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	l2_filter_id;
+};
+
+/* hwrm_cfa_l2_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_l2_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_filter_cfg_input (size:384b/48B) */
+struct hwrm_cfa_l2_filter_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH                  0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX                 0x0UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX                 0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST              CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP                  0x2UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK          0xcUL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT           2
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2      (0x0UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2              (0x1UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE            (0x2UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST           CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK         0x30UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT          4
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE      (0x0UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP    (0x1UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP    (0x2UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP  (0x3UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST          CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP
+	__le32	enables;
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID                 0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID     0x2UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_PROF_FUNC              0x4UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_L2_CONTEXT_ID          0x8UL
+	__le64	l2_filter_id;
+	__le32	dst_id;
+	__le32	new_mirror_vnic_id;
+	__le32	prof_func;
+	__le32	l2_context_id;
+};
+
+/* hwrm_cfa_l2_filter_cfg_output (size:128b/16B) */
+struct hwrm_cfa_l2_filter_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_set_rx_mask_input (size:448b/56B) */
+struct hwrm_cfa_l2_set_rx_mask_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	__le32	mask;
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_MCAST               0x2UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST           0x4UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_BCAST               0x8UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS         0x10UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_OUTERMOST           0x20UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLANONLY            0x40UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLAN_NONVLAN        0x80UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_ANYVLAN_NONVLAN     0x100UL
+	__le64	mc_tbl_addr;
+	__le32	num_mc_entries;
+	u8	unused_0[4];
+	__le64	vlan_tag_tbl_addr;
+	__le32	num_vlan_tags;
+	u8	unused_1[4];
+};
+
+/* hwrm_cfa_l2_set_rx_mask_output (size:128b/16B) */
+struct hwrm_cfa_l2_set_rx_mask_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_set_rx_mask_cmd_err (size:64b/8B) */
+struct hwrm_cfa_l2_set_rx_mask_cmd_err {
+	u8	code;
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN                    0x0UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_MAX_VLAN_TAGS              0x2UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_INVALID_VNIC_ID            0x3UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_INVALID_ACTION             0x4UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_LAST                      CFA_L2_SET_RX_MASK_CMD_ERR_CODE_INVALID_ACTION
+	u8	unused_0[7];
+};
+
+/* hwrm_cfa_tunnel_filter_alloc_input (size:704b/88B) */
+struct hwrm_cfa_tunnel_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
+	__le32	enables;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID       0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_ADDR            0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN           0x4UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR            0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR_TYPE       0x10UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR_TYPE     0x20UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR          0x40UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x80UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_VNI                0x100UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID        0x200UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x400UL
+	__le64	l2_filter_id;
+	u8	l2_addr[6];
+	__le16	l2_ivlan;
+	__le32	l3_addr[4];
+	__le32	t_l3_addr[4];
+	u8	l3_addr_type;
+	u8	t_l3_addr_type;
+	u8	tunnel_type;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	tunnel_flags;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_OAM_CHECKSUM_EXPLHDR     0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_CRITICAL_OPT_S1          0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_EXTHDR_SEQNUM_S0         0x4UL
+	__le32	vni;
+	__le32	dst_vnic_id;
+	__le32	mirror_vnic_id;
+};
+
+/* hwrm_cfa_tunnel_filter_alloc_output (size:192b/24B) */
+struct hwrm_cfa_tunnel_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	tunnel_filter_id;
+	__le32	flow_id;
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_tunnel_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_tunnel_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	tunnel_filter_id;
+};
+
+/* hwrm_cfa_tunnel_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_tunnel_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vxlan_ipv4_hdr (size:128b/16B) */
+struct hwrm_vxlan_ipv4_hdr {
+	u8	ver_hlen;
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_MASK 0xfUL
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT 0
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_MASK      0xf0UL
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT       4
+	u8	tos;
+	__be16	ip_id;
+	__be16	flags_frag_offset;
+	u8	ttl;
+	u8	protocol;
+	__be32	src_ip_addr;
+	__be32	dest_ip_addr;
+};
+
+/* hwrm_vxlan_ipv6_hdr (size:320b/40B) */
+struct hwrm_vxlan_ipv6_hdr {
+	__be32	ver_tc_flow_label;
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_SFT         0x1cUL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_MASK        0xf0000000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_SFT          0x14UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_MASK         0xff00000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_SFT  0x0UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK 0xfffffUL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_LAST           VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK
+	__be16	payload_len;
+	u8	next_hdr;
+	u8	ttl;
+	__be32	src_ip_addr[4];
+	__be32	dest_ip_addr[4];
+};
+
+/* hwrm_cfa_encap_data_vxlan (size:640b/80B) */
+struct hwrm_cfa_encap_data_vxlan {
+	u8	src_mac_addr[6];
+	__le16	unused_0;
+	u8	dst_mac_addr[6];
+	u8	num_vlan_tags;
+	u8	unused_1;
+	__be16	ovlan_tpid;
+	__be16	ovlan_tci;
+	__be16	ivlan_tpid;
+	__be16	ivlan_tci;
+	__le32	l3[10];
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_MASK 0xfUL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV4 0x4UL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6 0x6UL
+	#define CFA_ENCAP_DATA_VXLAN_L3_LAST    CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6
+	__be16	src_port;
+	__be16	dst_port;
+	__be32	vni;
+	u8	hdr_rsvd0[3];
+	u8	hdr_rsvd1;
+	u8	hdr_flags;
+	u8	unused[3];
+};
+
+/* hwrm_cfa_encap_record_alloc_input (size:832b/104B) */
+struct hwrm_cfa_encap_record_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL     0x2UL
+	u8	encap_type;
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN        0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE        0x2UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE        0x3UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP         0x4UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE       0x5UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS         0x6UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN         0x7UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE        0x8UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4     0x9UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1     0xaUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE     0xbUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST        CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE
+	u8	unused_0[3];
+	__le32	encap_data[20];
+};
+
+/* hwrm_cfa_encap_record_alloc_output (size:128b/16B) */
+struct hwrm_cfa_encap_record_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	encap_record_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_encap_record_free_input (size:192b/24B) */
+struct hwrm_cfa_encap_record_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	encap_record_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_cfa_encap_record_free_output (size:128b/16B) */
+struct hwrm_cfa_encap_record_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_ntuple_filter_alloc_input (size:1024b/128B) */
+struct hwrm_cfa_ntuple_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK              0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP                  0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER                 0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID              0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_ARP_REPLY             0x10UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX     0x20UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_NO_L2_CONTEXT         0x40UL
+	__le32	enables;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID         0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE            0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE          0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR          0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE          0x10UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR           0x20UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK      0x40UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR           0x80UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR_MASK      0x100UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL          0x200UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT             0x400UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT_MASK        0x800UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT             0x1000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT_MASK        0x2000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_PRI_HINT             0x4000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_NTUPLE_FILTER_ID     0x8000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID               0x10000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID       0x20000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR          0x40000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_RFS_RING_TBL_IDX     0x80000UL
+	__le64	l2_filter_id;
+	u8	src_macaddr[6];
+	__be16	ethertype;
+	u8	ip_addr_type;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
+	u8	ip_protocol;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMP    0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMPV6  0x3aUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD    0xffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD
+	__le16	dst_id;
+	__le16	rfs_ring_tbl_idx;
+	u8	tunnel_type;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	pri_hint;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER 0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE     0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_BELOW     0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_HIGHEST   0x3UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST    0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LAST     CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST
+	__be32	src_ipaddr[4];
+	__be32	src_ipaddr_mask[4];
+	__be32	dst_ipaddr[4];
+	__be32	dst_ipaddr_mask[4];
+	__be16	src_port;
+	__be16	src_port_mask;
+	__be16	dst_port;
+	__be16	dst_port_mask;
+	__le64	ntuple_filter_id_hint;
+};
+
+/* hwrm_cfa_ntuple_filter_alloc_output (size:192b/24B) */
+struct hwrm_cfa_ntuple_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	ntuple_filter_id;
+	__le32	flow_id;
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_ntuple_filter_alloc_cmd_err (size:64b/8B) */
+struct hwrm_cfa_ntuple_filter_alloc_cmd_err {
+	u8	code;
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN            0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ZERO_MAC           0x65UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_BC_MC_MAC          0x66UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_VNIC       0x67UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_PF_FID     0x68UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_L2_CTXT_ID 0x69UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_NULL_L2_CTXT_CFG   0x6aUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_NULL_L2_DATA_FLD   0x6bUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_CFA_LAYOUT 0x6cUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L2_CTXT_ALLOC_FAIL 0x6dUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ROCE_FLOW_ERR      0x6eUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_OWNER_FID  0x6fUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ZERO_REF_CNT       0x70UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_FLOW_TYPE  0x71UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_IVLAN      0x72UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_MAX_VLAN_ID        0x73UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_TNL_REQ    0x74UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L2_ADDR            0x75UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L2_IVLAN           0x76UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L3_ADDR            0x77UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_L3_ADDR_TYPE       0x78UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_T_L3_ADDR_TYPE     0x79UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_DST_VNIC_ID        0x7aUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_VNI                0x7bUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_DST_ID     0x7cUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_FAIL_ROCE_L2_FLOW  0x7dUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_NPAR_VLAN  0x7eUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_ATSP_ADD           0x7fUL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_DFLT_VLAN_FAIL     0x80UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_INVALID_L3_TYPE    0x81UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_VAL_FAIL_TNL_FLOW  0x82UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_LAST              CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_VAL_FAIL_TNL_FLOW
+	u8	unused_0[7];
+};
+
+/* hwrm_cfa_ntuple_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_ntuple_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	ntuple_filter_id;
+};
+
+/* hwrm_cfa_ntuple_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_ntuple_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_ntuple_filter_cfg_input (size:384b/48B) */
+struct hwrm_cfa_ntuple_filter_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID                0x1UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID        0x2UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID     0x4UL
+	__le32	flags;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID              0x1UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_RFS_RING_IDX     0x2UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_NO_L2_CONTEXT         0x4UL
+	__le64	ntuple_filter_id;
+	__le32	new_dst_id;
+	__le32	new_mirror_vnic_id;
+	__le16	new_meter_instance_id;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID 0xffffUL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_LAST   CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID
+	u8	unused_1[6];
+};
+
+/* hwrm_cfa_ntuple_filter_cfg_output (size:128b/16B) */
+struct hwrm_cfa_ntuple_filter_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_decap_filter_alloc_input (size:832b/104B) */
+struct hwrm_cfa_decap_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL     0x1UL
+	__le32	enables;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID          0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR        0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR        0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_OVLAN_VID          0x10UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IVLAN_VID          0x20UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_OVLAN_VID        0x40UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID        0x80UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE          0x100UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR         0x200UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR         0x400UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE        0x800UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL        0x1000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_PORT           0x2000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT           0x4000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_ID             0x8000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x10000UL
+	__be32	tunnel_id;
+	u8	tunnel_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	unused_0;
+	__le16	unused_1;
+	u8	src_macaddr[6];
+	u8	unused_2[2];
+	u8	dst_macaddr[6];
+	__be16	ovlan_vid;
+	__be16	ivlan_vid;
+	__be16	t_ovlan_vid;
+	__be16	t_ivlan_vid;
+	__be16	ethertype;
+	u8	ip_addr_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
+	u8	ip_protocol;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP
+	__le16	unused_3;
+	__le32	unused_4;
+	__be32	src_ipaddr[4];
+	__be32	dst_ipaddr[4];
+	__be16	src_port;
+	__be16	dst_port;
+	__le16	dst_id;
+	__le16	l2_ctxt_ref_id;
+};
+
+/* hwrm_cfa_decap_filter_alloc_output (size:128b/16B) */
+struct hwrm_cfa_decap_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	decap_filter_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_decap_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_decap_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	decap_filter_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_cfa_decap_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_decap_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_alloc_input (size:1024b/128B) */
+struct hwrm_cfa_flow_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flags;
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL                 0x1UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK          0x6UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT           1
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE            (0x0UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE             (0x1UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO             (0x2UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK          0x38UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT           3
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2              (0x0UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4            (0x1UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6            (0x2UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_TX                0x40UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_RX                0x80UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_MATCH_VXLAN_IP_VNI     0x100UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_VHOST_ID_USE_VLAN      0x200UL
+	__le16	src_fid;
+	__le32	tunnel_handle;
+	__le16	action_flags;
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                       0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                   0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                      0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                     0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                   0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST                  0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS          0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE         0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT             0x200UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP                 0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED        0x800UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT                  0x1000UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NO_FLOW_COUNTER_ALLOC     0x2000UL
+	__le16	dst_fid;
+	__be16	l2_rewrite_vlan_tpid;
+	__be16	l2_rewrite_vlan_tci;
+	__le16	act_meter_id;
+	__le16	ref_flow_handle;
+	__be16	ethertype;
+	__be16	outer_vlan_tci;
+	__be16	dmac[3];
+	__be16	inner_vlan_tci;
+	__be16	smac[3];
+	u8	ip_dst_mask_len;
+	u8	ip_src_mask_len;
+	__be32	ip_dst[4];
+	__be32	ip_src[4];
+	__be16	l4_src_port;
+	__be16	l4_src_port_mask;
+	__be16	l4_dst_port;
+	__be16	l4_dst_port_mask;
+	__be32	nat_ip_address[4];
+	__be16	l2_rewrite_dmac[3];
+	__be16	nat_port;
+	__be16	l2_rewrite_smac[3];
+	u8	ip_proto;
+	u8	tunnel_type;
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+};
+
+/* hwrm_cfa_flow_alloc_output (size:256b/32B) */
+struct hwrm_cfa_flow_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	flow_handle;
+	u8	unused_0[2];
+	__le32	flow_id;
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX
+	__le64	ext_flow_handle;
+	__le32	flow_counter_id;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_alloc_cmd_err (size:64b/8B) */
+struct hwrm_cfa_flow_alloc_cmd_err {
+	u8	code;
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_UNKNOWN         0x0UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_L2_CONTEXT_TCAM 0x1UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_ACTION_RECORD   0x2UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_COUNTER    0x3UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_WILD_CARD_TCAM  0x4UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_HASH_COLLISION  0x5UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_KEY_EXISTS      0x6UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB    0x7UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_LAST           CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB
+	u8	unused_0[7];
+};
+
+/* hwrm_cfa_flow_free_input (size:256b/32B) */
+struct hwrm_cfa_flow_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flow_handle;
+	__le16	unused_0;
+	__le32	flow_counter_id;
+	__le64	ext_flow_handle;
+};
+
+/* hwrm_cfa_flow_free_output (size:256b/32B) */
+struct hwrm_cfa_flow_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	packet;
+	__le64	byte;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_info_input (size:256b/32B) */
+struct hwrm_cfa_flow_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flow_handle;
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK      0xfffUL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT       0x1000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT    0x2000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_TX        0x3000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT    0x4000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX        0x8000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT_RX    0x9000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT_RX 0xa000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_RX        0xb000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX 0xc000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_LAST         CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX
+	u8	unused_0[6];
+	__le64	ext_flow_handle;
+};
+
+/* hwrm_cfa_flow_info_output (size:5632b/704B) */
+struct hwrm_cfa_flow_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX     0x1UL
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX     0x2UL
+	u8	profile;
+	__le16	src_fid;
+	__le16	dst_fid;
+	__le16	l2_ctxt_id;
+	__le64	em_info;
+	__le64	tcam_info;
+	__le64	vfp_tcam_info;
+	__le16	ar_id;
+	__le16	flow_handle;
+	__le32	tunnel_handle;
+	__le16	flow_timer;
+	u8	unused_0[6];
+	__le32	flow_key_data[130];
+	__le32	flow_action_info[30];
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_stats_input (size:640b/80B) */
+struct hwrm_cfa_flow_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	num_flows;
+	__le16	flow_handle_0;
+	__le16	flow_handle_1;
+	__le16	flow_handle_2;
+	__le16	flow_handle_3;
+	__le16	flow_handle_4;
+	__le16	flow_handle_5;
+	__le16	flow_handle_6;
+	__le16	flow_handle_7;
+	__le16	flow_handle_8;
+	__le16	flow_handle_9;
+	u8	unused_0[2];
+	__le32	flow_id_0;
+	__le32	flow_id_1;
+	__le32	flow_id_2;
+	__le32	flow_id_3;
+	__le32	flow_id_4;
+	__le32	flow_id_5;
+	__le32	flow_id_6;
+	__le32	flow_id_7;
+	__le32	flow_id_8;
+	__le32	flow_id_9;
+};
+
+/* hwrm_cfa_flow_stats_output (size:1408b/176B) */
+struct hwrm_cfa_flow_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	packet_0;
+	__le64	packet_1;
+	__le64	packet_2;
+	__le64	packet_3;
+	__le64	packet_4;
+	__le64	packet_5;
+	__le64	packet_6;
+	__le64	packet_7;
+	__le64	packet_8;
+	__le64	packet_9;
+	__le64	byte_0;
+	__le64	byte_1;
+	__le64	byte_2;
+	__le64	byte_3;
+	__le64	byte_4;
+	__le64	byte_5;
+	__le64	byte_6;
+	__le64	byte_7;
+	__le64	byte_8;
+	__le64	byte_9;
+	__le16	flow_hits;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_cfa_vfr_alloc_input (size:448b/56B) */
+struct hwrm_cfa_vfr_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vf_id;
+	__le16	reserved;
+	u8	unused_0[4];
+	char	vfr_name[32];
+};
+
+/* hwrm_cfa_vfr_alloc_output (size:128b/16B) */
+struct hwrm_cfa_vfr_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	rx_cfa_code;
+	__le16	tx_cfa_action;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_vfr_free_input (size:448b/56B) */
+struct hwrm_cfa_vfr_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	char	vfr_name[32];
+	__le16	vf_id;
+	__le16	reserved;
+	u8	unused_0[4];
+};
+
+/* hwrm_cfa_vfr_free_output (size:128b/16B) */
+struct hwrm_cfa_vfr_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_qcaps_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcaps_output (size:320b/40B) */
+struct hwrm_cfa_eem_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX                                         0x1UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX                                         0x2UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_CENTRALIZED_MEMORY_MODEL_SUPPORTED              0x4UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_DETACHED_CENTRALIZED_MEMORY_MODEL_SUPPORTED     0x8UL
+	__le32	unused_0;
+	__le32	supported;
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE                       0x2UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE            0x4UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE     0x8UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_FID_TABLE                        0x10UL
+	__le32	max_entries_supported;
+	__le16	key_entry_size;
+	__le16	record_entry_size;
+	__le16	efc_entry_size;
+	__le16	fid_entry_size;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_cfg_input (size:384b/48B) */
+struct hwrm_cfa_eem_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	#define CFA_EEM_CFG_REQ_FLAGS_SECONDARY_PF          0x8UL
+	__le16	group_id;
+	__le16	unused_0;
+	__le32	num_entries;
+	__le32	unused_1;
+	__le16	key0_ctx_id;
+	__le16	key1_ctx_id;
+	__le16	record_ctx_id;
+	__le16	efc_ctx_id;
+	__le16	fid_ctx_id;
+	__le16	unused_2;
+	__le32	unused_3;
+};
+
+/* hwrm_cfa_eem_cfg_output (size:128b/16B) */
+struct hwrm_cfa_eem_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_qcfg_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_RX     0x2UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcfg_output (size:256b/32B) */
+struct hwrm_cfa_eem_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	num_entries;
+	__le16	key0_ctx_id;
+	__le16	key1_ctx_id;
+	__le16	record_ctx_id;
+	__le16	efc_ctx_id;
+	__le16	fid_ctx_id;
+	u8	unused_2[5];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_op_input (size:192b/24B) */
+struct hwrm_cfa_eem_op_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_RX     0x2UL
+	__le16	unused_0;
+	__le16	op;
+	#define CFA_EEM_OP_REQ_OP_RESERVED    0x0UL
+	#define CFA_EEM_OP_REQ_OP_EEM_DISABLE 0x1UL
+	#define CFA_EEM_OP_REQ_OP_EEM_ENABLE  0x2UL
+	#define CFA_EEM_OP_REQ_OP_EEM_CLEANUP 0x3UL
+	#define CFA_EEM_OP_REQ_OP_LAST       CFA_EEM_OP_REQ_OP_EEM_CLEANUP
+};
+
+/* hwrm_cfa_eem_op_output (size:128b/16B) */
+struct hwrm_cfa_eem_op_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_adv_flow_mgnt_qcaps_input (size:256b/32B) */
+struct hwrm_cfa_adv_flow_mgnt_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[4];
+};
+
+/* hwrm_cfa_adv_flow_mgnt_qcaps_output (size:128b/16B) */
+struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_16BIT_SUPPORTED                     0x1UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_64BIT_SUPPORTED                     0x2UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_BATCH_DELETE_SUPPORTED                  0x4UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_RESET_ALL_SUPPORTED                     0x8UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_DEST_FUNC_SUPPORTED              0x10UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TX_EEM_FLOW_SUPPORTED                        0x20UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RX_EEM_FLOW_SUPPORTED                        0x40UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_COUNTER_ALLOC_SUPPORTED                 0x80UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_SUPPORTED                   0x100UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_UNTAGGED_VLAN_SUPPORTED                      0x200UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_XDP_SUPPORTED                                0x400UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_HEADER_SOURCE_FIELDS_SUPPORTED            0x800UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ARP_SUPPORTED                 0x1000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V2_SUPPORTED                0x2000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ETHERTYPE_IP_SUPPORTED        0x4000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TRUFLOW_CAPABLE                              0x8000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_FILTER_TRAFFIC_TYPE_L2_ROCE_SUPPORTED     0x10000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED                                0x20000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED               0x40000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED                     0x80000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED        0x100000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V3_SUPPORTED                0x200000UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
+struct hwrm_tunnel_dst_port_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	tunnel_type;
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN              0x1UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE             0x5UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI              0xeUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6               0xfUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE                0x11UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
+	u8	tunnel_next_proto;
+	u8	unused_0[6];
+};
+
+/* hwrm_tunnel_dst_port_query_output (size:128b/16B) */
+struct hwrm_tunnel_dst_port_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tunnel_dst_port_id;
+	__be16	tunnel_dst_port_val;
+	u8	upar_in_use;
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR0     0x1UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR1     0x2UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR2     0x4UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR3     0x8UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR4     0x10UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5     0x20UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6     0x40UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7     0x80UL
+	u8	status;
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_CHIP_LEVEL     0x1UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_FUNC_LEVEL     0x2UL
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_tunnel_dst_port_alloc_input (size:192b/24B) */
+struct hwrm_tunnel_dst_port_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	tunnel_type;
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN              0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE             0x5UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI              0xeUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6               0xfUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE                0x11UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
+	u8	tunnel_next_proto;
+	__be16	tunnel_dst_port_val;
+	u8	unused_0[4];
+};
+
+/* hwrm_tunnel_dst_port_alloc_output (size:128b/16B) */
+struct hwrm_tunnel_dst_port_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tunnel_dst_port_id;
+	u8	error_info;
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS         0x0UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED   0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED     0x3UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED
+	u8	upar_in_use;
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0     0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1     0x2UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR2     0x4UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR3     0x8UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR4     0x10UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR5     0x20UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR6     0x40UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR7     0x80UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_tunnel_dst_port_free_input (size:192b/24B) */
+struct hwrm_tunnel_dst_port_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	tunnel_type;
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN              0x1UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE             0x5UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI              0xeUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6               0xfUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE                0x11UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
+	u8	tunnel_next_proto;
+	__le16	tunnel_dst_port_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_tunnel_dst_port_free_output (size:128b/16B) */
+struct hwrm_tunnel_dst_port_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	error_info;
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_SUCCESS           0x0UL
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_OWNER     0x1UL
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED 0x2UL
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_LAST             TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED
+	u8	unused_1[6];
+	u8	valid;
+};
+
+/* ctx_hw_stats (size:1280b/160B) */
+struct ctx_hw_stats {
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	tpa_pkts;
+	__le64	tpa_bytes;
+	__le64	tpa_events;
+	__le64	tpa_aborts;
+};
+
+/* ctx_hw_stats_ext (size:1408b/176B) */
+struct ctx_hw_stats_ext {
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
+};
+
+/* hwrm_stat_ctx_alloc_input (size:384b/48B) */
+struct hwrm_stat_ctx_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	stats_dma_addr;
+	__le32	update_period_ms;
+	u8	stat_ctx_flags;
+	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE             0x1UL
+	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF     0x2UL
+	u8	unused_0;
+	__le16	stats_dma_length;
+	__le16	flags;
+	#define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID     0x1UL
+	__le16	steering_tag;
+	__le32	stat_ctx_id;
+	__le16	alloc_seq_id;
+	u8	unused_1[6];
+};
+
+/* hwrm_stat_ctx_alloc_output (size:128b/16B) */
+struct hwrm_stat_ctx_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	stat_ctx_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_stat_ctx_free_input (size:192b/24B) */
+struct hwrm_stat_ctx_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_stat_ctx_free_output (size:128b/16B) */
+struct hwrm_stat_ctx_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	stat_ctx_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_stat_ctx_query_input (size:192b/24B) */
+struct hwrm_stat_ctx_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	flags;
+	#define STAT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[3];
+};
+
+/* hwrm_stat_ctx_query_output (size:1408b/176B) */
+struct hwrm_stat_ctx_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	rx_agg_pkts;
+	__le64	rx_agg_bytes;
+	__le64	rx_agg_events;
+	__le64	rx_agg_aborts;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_stat_ext_ctx_query_input (size:192b/24B) */
+struct hwrm_stat_ext_ctx_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	flags;
+	#define STAT_EXT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[3];
+};
+
+/* hwrm_stat_ext_ctx_query_output (size:1536b/192B) */
+struct hwrm_stat_ext_ctx_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_stat_ctx_clr_stats_input (size:192b/24B) */
+struct hwrm_stat_ctx_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_stat_ctx_clr_stats_output (size:128b/16B) */
+struct hwrm_stat_ctx_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_pcie_qstats_input (size:256b/32B) */
+struct hwrm_pcie_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	pcie_stat_size;
+	u8	unused_0[6];
+	__le64	pcie_stat_host_addr;
+};
+
+/* hwrm_pcie_qstats_output (size:128b/16B) */
+struct hwrm_pcie_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	pcie_stat_size;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* pcie_ctx_hw_stats (size:768b/96B) */
+struct pcie_ctx_hw_stats {
+	__le64	pcie_pl_signal_integrity;
+	__le64	pcie_dl_signal_integrity;
+	__le64	pcie_tl_signal_integrity;
+	__le64	pcie_link_integrity;
+	__le64	pcie_tx_traffic_rate;
+	__le64	pcie_rx_traffic_rate;
+	__le64	pcie_tx_dllp_statistics;
+	__le64	pcie_rx_dllp_statistics;
+	__le64	pcie_equalization_time;
+	__le32	pcie_ltssm_histogram[4];
+	__le64	pcie_recovery_histogram;
+};
+
+/* pcie_ctx_hw_stats_v2 (size:4544b/568B) */
+struct pcie_ctx_hw_stats_v2 {
+	__le64	pcie_pl_signal_integrity;
+	__le64	pcie_dl_signal_integrity;
+	__le64	pcie_tl_signal_integrity;
+	__le64	pcie_link_integrity;
+	__le64	pcie_tx_traffic_rate;
+	__le64	pcie_rx_traffic_rate;
+	__le64	pcie_tx_dllp_statistics;
+	__le64	pcie_rx_dllp_statistics;
+	__le64	pcie_equalization_time;
+	__le32	pcie_ltssm_histogram[4];
+	__le64	pcie_recovery_histogram;
+	__le32	pcie_tl_credit_nph_histogram[8];
+	__le32	pcie_tl_credit_ph_histogram[8];
+	__le32	pcie_tl_credit_pd_histogram[8];
+	__le32	pcie_cmpl_latest_times[4];
+	__le32	pcie_cmpl_longest_time;
+	__le32	pcie_cmpl_shortest_time;
+	__le32	unused_0[2];
+	__le32	pcie_cmpl_latest_headers[4][4];
+	__le32	pcie_cmpl_longest_headers[4][4];
+	__le32	pcie_cmpl_shortest_headers[4][4];
+	__le32	pcie_wr_latency_histogram[12];
+	__le32	pcie_wr_latency_all_normal_count;
+	__le32	unused_1;
+	__le64	pcie_posted_packet_count;
+	__le64	pcie_non_posted_packet_count;
+	__le64	pcie_other_packet_count;
+	__le64	pcie_blocked_packet_count;
+	__le64	pcie_cmpl_packet_count;
+	__le32	pcie_rd_latency_histogram[12];
+	__le32	pcie_rd_latency_all_normal_count;
+	__le32	unused_2;
+};
+
+/* hwrm_stat_generic_qstats_input (size:256b/32B) */
+struct hwrm_stat_generic_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	generic_stat_size;
+	u8	flags;
+	#define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[5];
+	__le64	generic_stat_host_addr;
+};
+
+/* hwrm_stat_generic_qstats_output (size:128b/16B) */
+struct hwrm_stat_generic_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	generic_stat_size;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* generic_sw_hw_stats (size:1472b/184B) */
+struct generic_sw_hw_stats {
+	__le64	pcie_statistics_tx_tlp;
+	__le64	pcie_statistics_rx_tlp;
+	__le64	pcie_credit_fc_hdr_posted;
+	__le64	pcie_credit_fc_hdr_nonposted;
+	__le64	pcie_credit_fc_hdr_cmpl;
+	__le64	pcie_credit_fc_data_posted;
+	__le64	pcie_credit_fc_data_nonposted;
+	__le64	pcie_credit_fc_data_cmpl;
+	__le64	pcie_credit_fc_tgt_nonposted;
+	__le64	pcie_credit_fc_tgt_data_posted;
+	__le64	pcie_credit_fc_tgt_hdr_posted;
+	__le64	pcie_credit_fc_cmpl_hdr_posted;
+	__le64	pcie_credit_fc_cmpl_data_posted;
+	__le64	pcie_cmpl_longest;
+	__le64	pcie_cmpl_shortest;
+	__le64	cache_miss_count_cfcq;
+	__le64	cache_miss_count_cfcs;
+	__le64	cache_miss_count_cfcc;
+	__le64	cache_miss_count_cfcm;
+	__le64	hw_db_recov_dbs_dropped;
+	__le64	hw_db_recov_drops_serviced;
+	__le64	hw_db_recov_dbs_recovered;
+	__le64	hw_db_recov_oo_drop_count;
+};
+
+/* hwrm_fw_reset_input (size:192b/24B) */
+struct hwrm_fw_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	embedded_proc_type;
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT                  0x0UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT                  0x1UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL               0x2UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE                  0x3UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST                  0x4UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP                    0x5UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP                  0x6UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT  0x7UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION 0x8UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_LAST                 FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION
+	u8	selfrst_status;
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE      0x0UL
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP      0x1UL
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
+	#define FW_RESET_REQ_SELFRST_STATUS_LAST            FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE
+	u8	host_idx;
+	u8	flags;
+	#define FW_RESET_REQ_FLAGS_RESET_GRACEFUL     0x1UL
+	#define FW_RESET_REQ_FLAGS_FW_ACTIVATION      0x2UL
+	u8	unused_0[4];
+};
+
+/* hwrm_fw_reset_output (size:128b/16B) */
+struct hwrm_fw_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	selfrst_status;
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTNONE      0x0UL
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTASAP      0x1UL
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
+	#define FW_RESET_RESP_SELFRST_STATUS_LAST            FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_fw_qstatus_input (size:192b/24B) */
+struct hwrm_fw_qstatus_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	embedded_proc_type;
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_BOOT    0x0UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_MGMT    0x1UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE    0x3UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST    0x4UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_AP      0x5UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP    0x6UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_LAST   FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_qstatus_output (size:128b/16B) */
+struct hwrm_fw_qstatus_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	selfrst_status;
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTNONE    0x0UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTASAP    0x1UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST 0x2UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER   0x3UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_LAST          FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER
+	u8	nvm_option_action_status;
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_NONE     0x0UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_HOTRESET 0x1UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_WARMBOOT 0x2UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT 0x3UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_LAST                  FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_fw_set_time_input (size:256b/32B) */
+struct hwrm_fw_set_time_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	year;
+	#define FW_SET_TIME_REQ_YEAR_UNKNOWN 0x0UL
+	#define FW_SET_TIME_REQ_YEAR_LAST   FW_SET_TIME_REQ_YEAR_UNKNOWN
+	u8	month;
+	u8	day;
+	u8	hour;
+	u8	minute;
+	u8	second;
+	u8	unused_0;
+	__le16	millisecond;
+	__le16	zone;
+	#define FW_SET_TIME_REQ_ZONE_UTC     0
+	#define FW_SET_TIME_REQ_ZONE_UNKNOWN 65535
+	#define FW_SET_TIME_REQ_ZONE_LAST   FW_SET_TIME_REQ_ZONE_UNKNOWN
+	u8	unused_1[4];
+};
+
+/* hwrm_fw_set_time_output (size:128b/16B) */
+struct hwrm_fw_set_time_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_struct_hdr (size:128b/16B) */
+struct hwrm_struct_hdr {
+	__le16	struct_id;
+	#define STRUCT_HDR_STRUCT_ID_LLDP_CFG              0x41bUL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_ETS              0x41dUL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_PFC              0x41fUL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_APP              0x421UL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE    0x422UL
+	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC          0x424UL
+	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE           0x426UL
+	#define STRUCT_HDR_STRUCT_ID_POWER_BKUP            0x427UL
+	#define STRUCT_HDR_STRUCT_ID_PEER_MMAP             0x429UL
+	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE            0x1UL
+	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION      0xaUL
+	#define STRUCT_HDR_STRUCT_ID_RSS_V2                0x64UL
+	#define STRUCT_HDR_STRUCT_ID_MSIX_PER_VF           0xc8UL
+	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_COUNT 0x12cUL
+	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND 0x12dUL
+	#define STRUCT_HDR_STRUCT_ID_DBG_TOKEN_CLAIMS      0x190UL
+	#define STRUCT_HDR_STRUCT_ID_LAST                 STRUCT_HDR_STRUCT_ID_DBG_TOKEN_CLAIMS
+	__le16	len;
+	u8	version;
+	#define STRUCT_HDR_VERSION_0 0x0UL
+	#define STRUCT_HDR_VERSION_1 0x1UL
+	#define STRUCT_HDR_VERSION_LAST STRUCT_HDR_VERSION_1
+	u8	count;
+	__le16	subtype;
+	__le16	next_offset;
+	#define STRUCT_HDR_NEXT_OFFSET_LAST 0x0UL
+	u8	unused_0[6];
+};
+
+/* hwrm_struct_data_dcbx_app (size:64b/8B) */
+struct hwrm_struct_data_dcbx_app {
+	__be16	protocol_id;
+	u8	protocol_selector;
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_ETHER_TYPE   0x1UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_PORT     0x2UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_UDP_PORT     0x3UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT 0x4UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_LAST        STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT
+	u8	priority;
+	u8	valid;
+	u8	unused_0[3];
+};
+
+/* hwrm_fw_set_structured_data_input (size:256b/32B) */
+struct hwrm_fw_set_structured_data_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	src_data_addr;
+	__le16	data_len;
+	u8	hdr_cnt;
+	u8	unused_0[5];
+};
+
+/* hwrm_fw_set_structured_data_output (size:128b/16B) */
+struct hwrm_fw_set_structured_data_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fw_set_structured_data_cmd_err (size:64b/8B) */
+struct hwrm_fw_set_structured_data_cmd_err {
+	u8	code;
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT   0x1UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT       0x2UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID        0x3UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_ALREADY_ADDED 0x4UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_INST_IN_PROG  0x5UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_LAST         FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_INST_IN_PROG
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_get_structured_data_input (size:256b/32B) */
+struct hwrm_fw_get_structured_data_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	dest_data_addr;
+	__le16	data_len;
+	__le16	structure_id;
+	__le16	subtype;
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_UNUSED                  0x0UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_ALL                     0xffffUL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_ADMIN       0x100UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_PEER        0x101UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_OPERATIONAL 0x102UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_ADMIN          0x200UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_PEER           0x201UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_OPERATIONAL    0x202UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL        0x300UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_CLAIMS_SUPPORTED        0x320UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_CLAIMS_ACTIVE           0x321UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_LAST                   FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_CLAIMS_ACTIVE
+	u8	count;
+	u8	unused_0;
+};
+
+/* hwrm_fw_get_structured_data_output (size:128b/16B) */
+struct hwrm_fw_get_structured_data_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	hdr_cnt;
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_fw_get_structured_data_cmd_err (size:64b/8B) */
+struct hwrm_fw_get_structured_data_cmd_err {
+	u8	code;
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID  0x3UL
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_LAST   FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_livepatch_query_input (size:192b/24B) */
+struct hwrm_fw_livepatch_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	fw_target;
+	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_COMMON_FW 0x1UL
+	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW 0x2UL
+	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_LAST     FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_livepatch_query_output (size:640b/80B) */
+struct hwrm_fw_livepatch_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	char	install_ver[32];
+	char	active_ver[32];
+	__le16	status_flags;
+	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL     0x1UL
+	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE      0x2UL
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_fw_livepatch_input (size:256b/32B) */
+struct hwrm_fw_livepatch_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	opcode;
+	#define FW_LIVEPATCH_REQ_OPCODE_ACTIVATE   0x1UL
+	#define FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE 0x2UL
+	#define FW_LIVEPATCH_REQ_OPCODE_LAST      FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE
+	u8	fw_target;
+	#define FW_LIVEPATCH_REQ_FW_TARGET_COMMON_FW 0x1UL
+	#define FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW 0x2UL
+	#define FW_LIVEPATCH_REQ_FW_TARGET_LAST     FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW
+	u8	loadtype;
+	#define FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL   0x1UL
+	#define FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT 0x2UL
+	#define FW_LIVEPATCH_REQ_LOADTYPE_LAST         FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT
+	u8	flags;
+	__le32	patch_len;
+	__le64	host_addr;
+};
+
+/* hwrm_fw_livepatch_output (size:128b/16B) */
+struct hwrm_fw_livepatch_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fw_livepatch_cmd_err (size:64b/8B) */
+struct hwrm_fw_livepatch_cmd_err {
+	u8	code;
+	#define FW_LIVEPATCH_CMD_ERR_CODE_UNKNOWN         0x0UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_OPCODE  0x1UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_TARGET  0x2UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_SUPPORTED   0x3UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_INSTALLED   0x4UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_PATCHED     0x5UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_AUTH_FAIL       0x6UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_HEADER  0x7UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_SIZE    0x8UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED 0x9UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_LAST           FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED
+	u8	unused_0[7];
+};
+
+/* hwrm_exec_fwd_resp_input (size:1024b/128B) */
+struct hwrm_exec_fwd_resp_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	encap_request[26];
+	__le16	encap_resp_target_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_exec_fwd_resp_output (size:128b/16B) */
+struct hwrm_exec_fwd_resp_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_reject_fwd_resp_input (size:1024b/128B) */
+struct hwrm_reject_fwd_resp_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	encap_request[26];
+	__le16	encap_resp_target_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_reject_fwd_resp_output (size:128b/16B) */
+struct hwrm_reject_fwd_resp_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fwd_resp_input (size:1024b/128B) */
+struct hwrm_fwd_resp_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	encap_resp_target_id;
+	__le16	encap_resp_cmpl_ring;
+	__le16	encap_resp_len;
+	u8	unused_0;
+	u8	unused_1;
+	__le64	encap_resp_addr;
+	__le32	encap_resp[24];
+};
+
+/* hwrm_fwd_resp_output (size:128b/16B) */
+struct hwrm_fwd_resp_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fwd_async_event_cmpl_input (size:320b/40B) */
+struct hwrm_fwd_async_event_cmpl_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	encap_async_event_target_id;
+	u8	unused_0[6];
+	__le32	encap_async_event_cmpl[4];
+};
+
+/* hwrm_fwd_async_event_cmpl_output (size:128b/16B) */
+struct hwrm_fwd_async_event_cmpl_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_temp_monitor_query_input (size:128b/16B) */
+struct hwrm_temp_monitor_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_temp_monitor_query_output (size:192b/24B) */
+struct hwrm_temp_monitor_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	temp;
+	u8	phy_temp;
+	u8	om_temp;
+	u8	flags;
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE             0x1UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE         0x2UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT                 0x4UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE          0x8UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_EXT_TEMP_FIELDS_AVAILABLE      0x10UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_THRESHOLD_VALUES_AVAILABLE     0x20UL
+	u8	temp2;
+	u8	phy_temp2;
+	u8	om_temp2;
+	u8	warn_threshold;
+	u8	critical_threshold;
+	u8	fatal_threshold;
+	u8	shutdown_threshold;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_wol_filter_alloc_input (size:512b/64B) */
+struct hwrm_wol_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS           0x1UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET        0x2UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE      0x4UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR      0x8UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR     0x10UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE     0x20UL
+	__le16	port_id;
+	u8	wol_type;
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT 0x0UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP      0x1UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID  0xffUL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_LAST    WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID
+	u8	unused_0[5];
+	u8	mac_address[6];
+	__le16	pattern_offset;
+	__le16	pattern_buf_size;
+	__le16	pattern_mask_size;
+	u8	unused_1[4];
+	__le64	pattern_buf_addr;
+	__le64	pattern_mask_addr;
+};
+
+/* hwrm_wol_filter_alloc_output (size:128b/16B) */
+struct hwrm_wol_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	wol_filter_id;
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_wol_filter_free_input (size:256b/32B) */
+struct hwrm_wol_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS     0x1UL
+	__le32	enables;
+	#define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID     0x1UL
+	__le16	port_id;
+	u8	wol_filter_id;
+	u8	unused_0[5];
+};
+
+/* hwrm_wol_filter_free_output (size:128b/16B) */
+struct hwrm_wol_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_wol_filter_qcfg_input (size:448b/56B) */
+struct hwrm_wol_filter_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	handle;
+	u8	unused_0[4];
+	__le64	pattern_buf_addr;
+	__le16	pattern_buf_size;
+	u8	unused_1[6];
+	__le64	pattern_mask_addr;
+	__le16	pattern_mask_size;
+	u8	unused_2[6];
+};
+
+/* hwrm_wol_filter_qcfg_output (size:256b/32B) */
+struct hwrm_wol_filter_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	next_handle;
+	u8	wol_filter_id;
+	u8	wol_type;
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT 0x0UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP      0x1UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID  0xffUL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_LAST    WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID
+	__le32	unused_0;
+	u8	mac_address[6];
+	__le16	pattern_offset;
+	__le16	pattern_size;
+	__le16	pattern_mask_size;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_wol_reason_qcfg_input (size:320b/40B) */
+struct hwrm_wol_reason_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+	__le64	wol_pkt_buf_addr;
+	__le16	wol_pkt_buf_size;
+	u8	unused_1[6];
+};
+
+/* hwrm_wol_reason_qcfg_output (size:128b/16B) */
+struct hwrm_wol_reason_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	wol_filter_id;
+	u8	wol_reason;
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT 0x0UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_BMP      0x1UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID  0xffUL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_LAST    WOL_REASON_QCFG_RESP_WOL_REASON_INVALID
+	u8	wol_pkt_len;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_dbg_read_direct_input (size:256b/32B) */
+struct hwrm_dbg_read_direct_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	read_addr;
+	__le32	read_len32;
+};
+
+/* hwrm_dbg_read_direct_output (size:128b/16B) */
+struct hwrm_dbg_read_direct_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	crc32;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_qcaps_input (size:192b/24B) */
+struct hwrm_dbg_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_dbg_qcaps_output (size:192b/24B) */
+struct hwrm_dbg_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[2];
+	__le32	coredump_component_disable_caps;
+	#define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM     0x1UL
+	__le32	flags;
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM             0x1UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR        0x2UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR         0x4UL
+	#define DBG_QCAPS_RESP_FLAGS_USEQ                      0x8UL
+	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR         0x10UL
+	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE     0x20UL
+	#define DBG_QCAPS_RESP_FLAGS_PTRACE                    0x40UL
+	#define DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED     0x80UL
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_qcfg_input (size:192b/24B) */
+struct hwrm_dbg_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	__le16	flags;
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_MASK         0x3UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_SFT          0
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_NVM       0x0UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR  0x1UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR   0x2UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_LAST          DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
+	__le32	coredump_component_disable_flags;
+	#define DBG_QCFG_REQ_COREDUMP_COMPONENT_DISABLE_FLAGS_NVRAM     0x1UL
+};
+
+/* hwrm_dbg_qcfg_output (size:256b/32B) */
+struct hwrm_dbg_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[2];
+	__le32	coredump_size;
+	__le32	flags;
+	#define DBG_QCFG_RESP_FLAGS_UART_LOG               0x1UL
+	#define DBG_QCFG_RESP_FLAGS_UART_LOG_SECONDARY     0x2UL
+	#define DBG_QCFG_RESP_FLAGS_FW_TRACE               0x4UL
+	#define DBG_QCFG_RESP_FLAGS_FW_TRACE_SECONDARY     0x8UL
+	#define DBG_QCFG_RESP_FLAGS_DEBUG_NOTIFY           0x10UL
+	#define DBG_QCFG_RESP_FLAGS_JTAG_DEBUG             0x20UL
+	__le16	async_cmpl_ring;
+	u8	unused_2[2];
+	__le32	crashdump_size;
+	u8	unused_3[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */
+struct hwrm_dbg_crashdump_medium_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	output_dest_flags;
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR     0x1UL
+	__le16	pg_size_lvl;
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK      0x3UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT       0
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0       0x0UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1       0x1UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2       0x2UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST       DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK  0x1cUL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT   2
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K   (0x0UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K   (0x1UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K  (0x2UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M   (0x3UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M   (0x4UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G   (0x5UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST   DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT  5
+	__le32	size;
+	__le32	coredump_component_disable_flags;
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM     0x1UL
+	__le32	unused_0;
+	__le64	pbl;
+};
+
+/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */
+struct hwrm_dbg_crashdump_medium_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* coredump_segment_record (size:128b/16B) */
+struct coredump_segment_record {
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	max_instances;
+	u8	version_hi;
+	u8	version_low;
+	u8	seg_flags;
+	u8	compress_flags;
+	#define SFLAG_COMPRESSED_ZLIB     0x1UL
+	u8	unused_0[2];
+	__le32	segment_len;
+};
+
+/* hwrm_dbg_coredump_list_input (size:256b/32B) */
+struct hwrm_dbg_coredump_list_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le16	seq_no;
+	u8	flags;
+	#define DBG_COREDUMP_LIST_REQ_FLAGS_CRASHDUMP     0x1UL
+	u8	unused_0[1];
+};
+
+/* hwrm_dbg_coredump_list_output (size:128b/16B) */
+struct hwrm_dbg_coredump_list_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_LIST_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	total_segments;
+	__le16	data_len;
+	u8	unused_1;
+	u8	valid;
+};
+
+/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */
+struct hwrm_dbg_coredump_initiate_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_0;
+	u8	seg_flags;
+	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_LIVE_DATA                0x1UL
+	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_CRASH_DATA               0x2UL
+	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE     0x4UL
+	u8	unused_1[7];
+};
+
+/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */
+struct hwrm_dbg_coredump_initiate_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* coredump_data_hdr (size:128b/16B) */
+struct coredump_data_hdr {
+	__le32	address;
+	__le32	flags_length;
+	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_MASK     0xffffffUL
+	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_SFT      0
+	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_INDIRECT_ACCESS     0x1000000UL
+	__le32	instance;
+	__le32	next_offset;
+};
+
+/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */
+struct hwrm_dbg_coredump_retrieve_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le32	unused_0;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_1;
+	u8	seg_flags;
+	u8	unused_2;
+	__le16	unused_3;
+	__le32	unused_4;
+	__le32	seq_no;
+	__le32	unused_5;
+};
+
+/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */
+struct hwrm_dbg_coredump_retrieve_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	data_len;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_ring_info_get_input (size:192b/24B) */
+struct hwrm_dbg_ring_info_get_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL 0x0UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_TX      0x1UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_RX      0x2UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_NQ      0x3UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_LAST   DBG_RING_INFO_GET_REQ_RING_TYPE_NQ
+	u8	unused_0[3];
+	__le32	fw_ring_id;
+};
+
+/* hwrm_dbg_ring_info_get_output (size:192b/24B) */
+struct hwrm_dbg_ring_info_get_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	producer_index;
+	__le32	consumer_index;
+	__le32	cag_vector_ctrl;
+	__le16	st_tag;
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_dbg_log_buffer_flush_input (size:192b/24B) */
+struct hwrm_dbg_log_buffer_flush_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT_TRACE           0x0UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT2_TRACE          0x1UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT_TRACE           0x2UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT2_TRACE          0x3UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP0_TRACE         0x4UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_L2_HWRM_TRACE       0x5UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ROCE_HWRM_TRACE     0x6UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA0_TRACE           0x7UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA1_TRACE           0x8UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE           0x9UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE         0xaUL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE 0xbUL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE       0xcUL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_LAST               DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ERR_QPC_TRACE
+	u8	unused_1[2];
+	__le32	flags;
+	#define DBG_LOG_BUFFER_FLUSH_REQ_FLAGS_FLUSH_ALL_BUFFERS     0x1UL
+};
+
+/* hwrm_dbg_log_buffer_flush_output (size:128b/16B) */
+struct hwrm_dbg_log_buffer_flush_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	current_buffer_offset;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_nvm_read_input (size:320b/40B) */
+struct hwrm_nvm_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le16	dir_idx;
+	u8	unused_0[2];
+	__le32	offset;
+	__le32	len;
+	u8	unused_1[4];
+};
+
+/* hwrm_nvm_read_output (size:128b/16B) */
+struct hwrm_nvm_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_dir_entries_input (size:192b/24B) */
+struct hwrm_nvm_get_dir_entries_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+};
+
+/* hwrm_nvm_get_dir_entries_output (size:128b/16B) */
+struct hwrm_nvm_get_dir_entries_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_dir_info_input (size:128b/16B) */
+struct hwrm_nvm_get_dir_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_nvm_get_dir_info_output (size:192b/24B) */
+struct hwrm_nvm_get_dir_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	entries;
+	__le32	entry_length;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_write_input (size:448b/56B) */
+struct hwrm_nvm_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_src_addr;
+	__le16	dir_type;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	__le16	dir_attr;
+	__le32	dir_data_length;
+	__le16	option;
+	__le16	flags;
+	#define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG     0x1UL
+	#define NVM_WRITE_REQ_FLAGS_BATCH_MODE               0x2UL
+	#define NVM_WRITE_REQ_FLAGS_BATCH_LAST               0x4UL
+	#define NVM_WRITE_REQ_FLAGS_SKIP_CRID_CHECK          0x8UL
+	__le32	dir_item_length;
+	__le32	offset;
+	__le32	len;
+	__le32	unused_0;
+};
+
+/* hwrm_nvm_write_output (size:128b/16B) */
+struct hwrm_nvm_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	dir_item_length;
+	__le16	dir_idx;
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_nvm_write_cmd_err (size:64b/8B) */
+struct hwrm_nvm_write_cmd_err {
+	u8	code;
+	#define NVM_WRITE_CMD_ERR_CODE_UNKNOWN              0x0UL
+	#define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR             0x1UL
+	#define NVM_WRITE_CMD_ERR_CODE_NO_SPACE             0x2UL
+	#define NVM_WRITE_CMD_ERR_CODE_WRITE_FAILED         0x3UL
+	#define NVM_WRITE_CMD_ERR_CODE_REQD_ERASE_FAILED    0x4UL
+	#define NVM_WRITE_CMD_ERR_CODE_VERIFY_FAILED        0x5UL
+	#define NVM_WRITE_CMD_ERR_CODE_INVALID_HEADER       0x6UL
+	#define NVM_WRITE_CMD_ERR_CODE_UPDATE_DIGEST_FAILED 0x7UL
+	#define NVM_WRITE_CMD_ERR_CODE_LAST                NVM_WRITE_CMD_ERR_CODE_UPDATE_DIGEST_FAILED
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_modify_input (size:320b/40B) */
+struct hwrm_nvm_modify_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_src_addr;
+	__le16	dir_idx;
+	__le16	flags;
+	#define NVM_MODIFY_REQ_FLAGS_BATCH_MODE     0x1UL
+	#define NVM_MODIFY_REQ_FLAGS_BATCH_LAST     0x2UL
+	__le32	offset;
+	__le32	len;
+	u8	unused_1[4];
+};
+
+/* hwrm_nvm_modify_output (size:128b/16B) */
+struct hwrm_nvm_modify_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_find_dir_entry_input (size:256b/32B) */
+struct hwrm_nvm_find_dir_entry_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define NVM_FIND_DIR_ENTRY_REQ_ENABLES_DIR_IDX_VALID     0x1UL
+	__le16	dir_idx;
+	__le16	dir_type;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	u8	opt_ordinal;
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_MASK 0x3UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_SFT 0
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ    0x0UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GE    0x1UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT    0x2UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_LAST NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT
+	u8	unused_0[3];
+};
+
+/* hwrm_nvm_find_dir_entry_output (size:256b/32B) */
+struct hwrm_nvm_find_dir_entry_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	dir_item_length;
+	__le32	dir_data_length;
+	__le32	fw_ver;
+	__le16	dir_ordinal;
+	__le16	dir_idx;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_erase_dir_entry_input (size:192b/24B) */
+struct hwrm_nvm_erase_dir_entry_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	dir_idx;
+	u8	unused_0[6];
+};
+
+/* hwrm_nvm_erase_dir_entry_output (size:128b/16B) */
+struct hwrm_nvm_erase_dir_entry_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_dev_info_input (size:192b/24B) */
+struct hwrm_nvm_get_dev_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	flags;
+	#define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM     0x1UL
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_get_dev_info_output (size:768b/96B) */
+struct hwrm_nvm_get_dev_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	manufacturer_id;
+	__le16	device_id;
+	__le32	sector_size;
+	__le32	nvram_size;
+	__le32	reserved_size;
+	__le32	available_size;
+	u8	nvm_cfg_ver_maj;
+	u8	nvm_cfg_ver_min;
+	u8	nvm_cfg_ver_upd;
+	u8	flags;
+	#define NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID     0x1UL
+	char	pkg_name[16];
+	__le16	hwrm_fw_major;
+	__le16	hwrm_fw_minor;
+	__le16	hwrm_fw_build;
+	__le16	hwrm_fw_patch;
+	__le16	mgmt_fw_major;
+	__le16	mgmt_fw_minor;
+	__le16	mgmt_fw_build;
+	__le16	mgmt_fw_patch;
+	__le16	roce_fw_major;
+	__le16	roce_fw_minor;
+	__le16	roce_fw_build;
+	__le16	roce_fw_patch;
+	__le16	netctrl_fw_major;
+	__le16	netctrl_fw_minor;
+	__le16	netctrl_fw_build;
+	__le16	netctrl_fw_patch;
+	__le16	srt2_fw_major;
+	__le16	srt2_fw_minor;
+	__le16	srt2_fw_build;
+	__le16	srt2_fw_patch;
+	u8	security_soc_fw_major;
+	u8	security_soc_fw_minor;
+	u8	security_soc_fw_build;
+	u8	security_soc_fw_patch;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_nvm_mod_dir_entry_input (size:256b/32B) */
+struct hwrm_nvm_mod_dir_entry_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define NVM_MOD_DIR_ENTRY_REQ_ENABLES_CHECKSUM     0x1UL
+	__le16	dir_idx;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	__le16	dir_attr;
+	__le32	checksum;
+};
+
+/* hwrm_nvm_mod_dir_entry_output (size:128b/16B) */
+struct hwrm_nvm_mod_dir_entry_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_verify_update_input (size:192b/24B) */
+struct hwrm_nvm_verify_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	dir_type;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	u8	unused_0[2];
+};
+
+/* hwrm_nvm_verify_update_output (size:128b/16B) */
+struct hwrm_nvm_verify_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_install_update_input (size:192b/24B) */
+struct hwrm_nvm_install_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	install_type;
+	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_NORMAL 0x0UL
+	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL    0xffffffffUL
+	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_LAST  NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL
+	__le16	flags;
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ERASE_UNUSED_SPACE     0x1UL
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_REMOVE_UNUSED_PKG      0x2UL
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG      0x4UL
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_VERIFY_ONLY            0x8UL
+	u8	unused_0[2];
+};
+
+/* hwrm_nvm_install_update_output (size:192b/24B) */
+struct hwrm_nvm_install_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	installed_items;
+	u8	result;
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS                      0x0UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE                      0xffUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE               0xfdUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER      0xfbUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER       0xf3UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE         0xf2UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER          0xecUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE            0xebUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM          0xeaUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH          0xe9UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST             0xe8UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER              0xe7UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM             0xe6UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM        0xe5UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH          0xe4UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE            0xe1UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV         0xceUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID        0xcdUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR    0xccUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID        0xcbUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM         0xc5UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM               0xc4UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM             0xc3UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR       0xb9UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR           0xb8UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND               0xb0UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED                  0xa7UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_LAST                        NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED
+	u8	problem_item;
+	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE    0x0UL
+	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL
+	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_LAST   NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE
+	u8	reset_required;
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_NONE  0x0UL
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_PCI   0x1UL
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER 0x2UL
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_LAST NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_nvm_install_update_cmd_err (size:64b/8B) */
+struct hwrm_nvm_install_update_cmd_err {
+	u8	code;
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN            0x0UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR           0x1UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE           0x2UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK      0x3UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT 0x4UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_DEFRAG_FAILED      0x5UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN_DIR_ERR    0x6UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST              NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN_DIR_ERR
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_get_variable_input (size:320b/40B) */
+struct hwrm_nvm_get_variable_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	dest_data_addr;
+	__le16	data_len;
+	__le16	option_num;
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
+	__le16	dimensions;
+	__le16	index_0;
+	__le16	index_1;
+	__le16	index_2;
+	__le16	index_3;
+	u8	flags;
+	#define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT           0x1UL
+	#define NVM_GET_VARIABLE_REQ_FLAGS_VALIDATE_OPT_VALUE     0x2UL
+	u8	unused_0;
+};
+
+/* hwrm_nvm_get_variable_output (size:128b/16B) */
+struct hwrm_nvm_get_variable_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	data_len;
+	__le16	option_num;
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0    0x0UL
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF 0xffffUL
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_LAST     NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF
+	u8	flags;
+	#define NVM_GET_VARIABLE_RESP_FLAGS_VALIDATE_OPT_VALUE     0x1UL
+	u8	unused_0[2];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_variable_cmd_err (size:64b/8B) */
+struct hwrm_nvm_get_variable_cmd_err {
+	u8	code;
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN          0x0UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST    0x1UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR      0x2UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT    0x3UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_INDEX_INVALID    0x4UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_ACCESS_DENIED    0x5UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CB_FAILED        0x6UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_INVALID_DATA_LEN 0x7UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_NO_MEM           0x8UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LAST            NVM_GET_VARIABLE_CMD_ERR_CODE_NO_MEM
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_set_variable_input (size:320b/40B) */
+struct hwrm_nvm_set_variable_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	src_data_addr;
+	__le16	data_len;
+	__le16	option_num;
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
+	__le16	dimensions;
+	__le16	index_0;
+	__le16	index_1;
+	__le16	index_2;
+	__le16	index_3;
+	u8	flags;
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH                0x1UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK          0xeUL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT           1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE            (0x0UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1       (0x1UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256          (0x2UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH  (0x3UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST           NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_MASK        0x70UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_SFT         4
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FACTORY_DEFAULT            0x80UL
+	u8	unused_0;
+};
+
+/* hwrm_nvm_set_variable_output (size:128b/16B) */
+struct hwrm_nvm_set_variable_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_set_variable_cmd_err (size:64b/8B) */
+struct hwrm_nvm_set_variable_cmd_err {
+	u8	code;
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN              0x0UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST        0x1UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR          0x2UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT        0x3UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_ACTION_NOT_SUPPORTED 0x4UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_INDEX_INVALID        0x5UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_ACCESS_DENIED        0x6UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CB_FAILED            0x7UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_INVALID_DATA_LEN     0x8UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_NO_MEM               0x9UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_LAST                NVM_SET_VARIABLE_CMD_ERR_CODE_NO_MEM
+	u8	unused_0[7];
+};
+
+/* hwrm_selftest_qlist_input (size:128b/16B) */
+struct hwrm_selftest_qlist_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_selftest_qlist_output (size:2240b/280B) */
+struct hwrm_selftest_qlist_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_tests;
+	u8	available_tests;
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST                 0x1UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST                0x2UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST            0x4UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST              0x8UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_SERDES_TEST     0x20UL
+	u8	offline_tests;
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST                 0x1UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST                0x2UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST            0x4UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST              0x8UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_SERDES_TEST     0x20UL
+	u8	unused_0;
+	__le16	test_timeout;
+	u8	unused_1[2];
+	char	test_name[8][32];
+	u8	eyescope_target_BER_support;
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED  0x0UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED  0x1UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E10_SUPPORTED 0x2UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E11_SUPPORTED 0x3UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED 0x4UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_LAST              SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED
+	u8	unused_2[6];
+	u8	valid;
+};
+
+/* hwrm_selftest_exec_input (size:192b/24B) */
+struct hwrm_selftest_exec_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	flags;
+	#define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST                 0x1UL
+	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST                0x2UL
+	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST            0x4UL
+	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST              0x8UL
+	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_SERDES_TEST     0x20UL
+	u8	unused_0[7];
+};
+
+/* hwrm_selftest_exec_output (size:128b/16B) */
+struct hwrm_selftest_exec_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	requested_tests;
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST                 0x1UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST                0x2UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST            0x4UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST              0x8UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_SERDES_TEST     0x20UL
+	u8	test_success;
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST                 0x1UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST                0x2UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST            0x4UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST              0x8UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_SERDES_TEST     0x20UL
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_selftest_irq_input (size:128b/16B) */
+struct hwrm_selftest_irq_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_selftest_irq_output (size:128b/16B) */
+struct hwrm_selftest_irq_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* dbc_dbc (size:64b/8B) */
+struct dbc_dbc {
+	__le32	index;
+	#define DBC_DBC_INDEX_MASK 0xffffffUL
+	#define DBC_DBC_INDEX_SFT  0
+	#define DBC_DBC_EPOCH      0x1000000UL
+	#define DBC_DBC_TOGGLE_MASK 0x6000000UL
+	#define DBC_DBC_TOGGLE_SFT 25
+	__le32	type_path_xid;
+	#define DBC_DBC_XID_MASK          0xfffffUL
+	#define DBC_DBC_XID_SFT           0
+	#define DBC_DBC_PATH_MASK         0x3000000UL
+	#define DBC_DBC_PATH_SFT          24
+	#define DBC_DBC_PATH_ROCE           (0x0UL << 24)
+	#define DBC_DBC_PATH_L2             (0x1UL << 24)
+	#define DBC_DBC_PATH_ENGINE         (0x2UL << 24)
+	#define DBC_DBC_PATH_LAST          DBC_DBC_PATH_ENGINE
+	#define DBC_DBC_VALID             0x4000000UL
+	#define DBC_DBC_DEBUG_TRACE       0x8000000UL
+	#define DBC_DBC_TYPE_MASK         0xf0000000UL
+	#define DBC_DBC_TYPE_SFT          28
+	#define DBC_DBC_TYPE_SQ             (0x0UL << 28)
+	#define DBC_DBC_TYPE_RQ             (0x1UL << 28)
+	#define DBC_DBC_TYPE_SRQ            (0x2UL << 28)
+	#define DBC_DBC_TYPE_SRQ_ARM        (0x3UL << 28)
+	#define DBC_DBC_TYPE_CQ             (0x4UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMSE       (0x5UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMALL      (0x6UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMENA      (0x7UL << 28)
+	#define DBC_DBC_TYPE_SRQ_ARMENA     (0x8UL << 28)
+	#define DBC_DBC_TYPE_CQ_CUTOFF_ACK  (0x9UL << 28)
+	#define DBC_DBC_TYPE_NQ             (0xaUL << 28)
+	#define DBC_DBC_TYPE_NQ_ARM         (0xbUL << 28)
+	#define DBC_DBC_TYPE_NQ_MASK        (0xeUL << 28)
+	#define DBC_DBC_TYPE_NULL           (0xfUL << 28)
+	#define DBC_DBC_TYPE_LAST          DBC_DBC_TYPE_NULL
+};
+
+/* db_push_start (size:64b/8B) */
+struct db_push_start {
+	u64	db;
+	#define DB_PUSH_START_DB_INDEX_MASK     0xffffffUL
+	#define DB_PUSH_START_DB_INDEX_SFT      0
+	#define DB_PUSH_START_DB_PI_LO_MASK     0xff000000UL
+	#define DB_PUSH_START_DB_PI_LO_SFT      24
+	#define DB_PUSH_START_DB_XID_MASK       0xfffff00000000ULL
+	#define DB_PUSH_START_DB_XID_SFT        32
+	#define DB_PUSH_START_DB_PI_HI_MASK     0xf0000000000000ULL
+	#define DB_PUSH_START_DB_PI_HI_SFT      52
+	#define DB_PUSH_START_DB_TYPE_MASK      0xf000000000000000ULL
+	#define DB_PUSH_START_DB_TYPE_SFT       60
+	#define DB_PUSH_START_DB_TYPE_PUSH_START  (0xcULL << 60)
+	#define DB_PUSH_START_DB_TYPE_PUSH_END    (0xdULL << 60)
+	#define DB_PUSH_START_DB_TYPE_LAST       DB_PUSH_START_DB_TYPE_PUSH_END
+};
+
+/* db_push_end (size:64b/8B) */
+struct db_push_end {
+	u64	db;
+	#define DB_PUSH_END_DB_INDEX_MASK      0xffffffUL
+	#define DB_PUSH_END_DB_INDEX_SFT       0
+	#define DB_PUSH_END_DB_PI_LO_MASK      0xff000000UL
+	#define DB_PUSH_END_DB_PI_LO_SFT       24
+	#define DB_PUSH_END_DB_XID_MASK        0xfffff00000000ULL
+	#define DB_PUSH_END_DB_XID_SFT         32
+	#define DB_PUSH_END_DB_PI_HI_MASK      0xf0000000000000ULL
+	#define DB_PUSH_END_DB_PI_HI_SFT       52
+	#define DB_PUSH_END_DB_PATH_MASK       0x300000000000000ULL
+	#define DB_PUSH_END_DB_PATH_SFT        56
+	#define DB_PUSH_END_DB_PATH_ROCE         (0x0ULL << 56)
+	#define DB_PUSH_END_DB_PATH_L2           (0x1ULL << 56)
+	#define DB_PUSH_END_DB_PATH_ENGINE       (0x2ULL << 56)
+	#define DB_PUSH_END_DB_PATH_LAST        DB_PUSH_END_DB_PATH_ENGINE
+	#define DB_PUSH_END_DB_DEBUG_TRACE     0x800000000000000ULL
+	#define DB_PUSH_END_DB_TYPE_MASK       0xf000000000000000ULL
+	#define DB_PUSH_END_DB_TYPE_SFT        60
+	#define DB_PUSH_END_DB_TYPE_PUSH_START   (0xcULL << 60)
+	#define DB_PUSH_END_DB_TYPE_PUSH_END     (0xdULL << 60)
+	#define DB_PUSH_END_DB_TYPE_LAST        DB_PUSH_END_DB_TYPE_PUSH_END
+};
+
+/* db_push_info (size:64b/8B) */
+struct db_push_info {
+	u32	push_size_push_index;
+	#define DB_PUSH_INFO_PUSH_INDEX_MASK 0xffffffUL
+	#define DB_PUSH_INFO_PUSH_INDEX_SFT 0
+	#define DB_PUSH_INFO_PUSH_SIZE_MASK 0x1f000000UL
+	#define DB_PUSH_INFO_PUSH_SIZE_SFT  24
+	u32	reserved32;
+};
+
+/* fw_status_reg (size:32b/4B) */
+struct fw_status_reg {
+	u32	fw_status;
+	#define FW_STATUS_REG_CODE_MASK              0xffffUL
+	#define FW_STATUS_REG_CODE_SFT               0
+	#define FW_STATUS_REG_CODE_READY               0x8000UL
+	#define FW_STATUS_REG_CODE_LAST               FW_STATUS_REG_CODE_READY
+	#define FW_STATUS_REG_IMAGE_DEGRADED         0x10000UL
+	#define FW_STATUS_REG_RECOVERABLE            0x20000UL
+	#define FW_STATUS_REG_CRASHDUMP_ONGOING      0x40000UL
+	#define FW_STATUS_REG_CRASHDUMP_COMPLETE     0x80000UL
+	#define FW_STATUS_REG_SHUTDOWN               0x100000UL
+	#define FW_STATUS_REG_CRASHED_NO_MASTER      0x200000UL
+	#define FW_STATUS_REG_RECOVERING             0x400000UL
+	#define FW_STATUS_REG_MANU_DEBUG_STATUS      0x800000UL
+};
+
+/* hcomm_status (size:64b/8B) */
+struct hcomm_status {
+	u32	sig_ver;
+	#define HCOMM_STATUS_VER_MASK      0xffUL
+	#define HCOMM_STATUS_VER_SFT       0
+	#define HCOMM_STATUS_VER_LATEST      0x1UL
+	#define HCOMM_STATUS_VER_LAST       HCOMM_STATUS_VER_LATEST
+	#define HCOMM_STATUS_SIGNATURE_MASK 0xffffff00UL
+	#define HCOMM_STATUS_SIGNATURE_SFT 8
+	#define HCOMM_STATUS_SIGNATURE_VAL   (0x484353UL << 8)
+	#define HCOMM_STATUS_SIGNATURE_LAST HCOMM_STATUS_SIGNATURE_VAL
+	u32	fw_status_loc;
+	#define HCOMM_STATUS_TRUE_ADDR_SPACE_MASK    0x3UL
+	#define HCOMM_STATUS_TRUE_ADDR_SPACE_SFT     0
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_GRC       0x1UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR0      0x2UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1      0x3UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_LAST     HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1
+	#define HCOMM_STATUS_TRUE_OFFSET_MASK        0xfffffffcUL
+	#define HCOMM_STATUS_TRUE_OFFSET_SFT         2
+};
+#define HCOMM_STATUS_STRUCT_LOC 0x31001F0UL
+
+#endif /* _BNXT_HSI_H_ */
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index ca73940e26df..25df9260d206 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -10,6 +10,7 @@
 #ifdef __KERNEL__
 #include <linux/kernel.h>
 #include <linux/types.h>
+bool __init cmdline_has_extra_options(void);
 #else /* !__KERNEL__ */
 /*
  * NOTE: This is only for tools/bootconfig, because tools/bootconfig will
@@ -287,7 +288,12 @@ int __init xbc_init(const char *buf, size_t size, const char **emsg, int *epos);
 int __init xbc_get_info(int *node_size, size_t *data_size);
 
 /* XBC cleanup data structures */
-void __init xbc_exit(void);
+void __init _xbc_exit(bool early);
+
+static __always_inline void xbc_exit(void)
+{
+	_xbc_exit(false);
+}
 
 /* XBC embedded bootconfig data in kernel */
 #ifdef CONFIG_BOOT_CONFIG_EMBED
diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
index cc35d010fa94..4c506e76a808 100644
--- a/include/linux/bootmem_info.h
+++ b/include/linux/bootmem_info.h
@@ -3,13 +3,13 @@
 #define __LINUX_BOOTMEM_INFO_H
 
 #include <linux/mm.h>
+#include <linux/kmemleak.h>
 
 /*
- * Types for free bootmem stored in page->lru.next. These have to be in
- * some random range in unsigned long space for debugging purposes.
+ * Types for free bootmem stored in the low bits of page->private.
  */
-enum {
-	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
+enum bootmem_type {
+	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 1,
 	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
 	MIX_SECTION_INFO,
 	NODE_INFO,
@@ -18,11 +18,23 @@ enum {
 
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
+void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
+				  unsigned long nr_pages);
 
 void get_page_bootmem(unsigned long info, struct page *page,
-		      unsigned long type);
+		enum bootmem_type type);
 void put_page_bootmem(struct page *page);
 
+static inline enum bootmem_type bootmem_type(const struct page *page)
+{
+	return (unsigned long)page->private & 0xf;
+}
+
+static inline unsigned long bootmem_info(const struct page *page)
+{
+	return (unsigned long)page->private >> 4;
+}
+
 /*
  * Any memory allocated via the memblock allocator and not via the
  * buddy will be marked reserved already in the memmap. For those
@@ -30,7 +42,7 @@ void put_page_bootmem(struct page *page);
  */
 static inline void free_bootmem_page(struct page *page)
 {
-	unsigned long magic = page->index;
+	enum bootmem_type type = bootmem_type(page);
 
 	/*
 	 * The reserve_bootmem_region sets the reserved flag on bootmem
@@ -38,7 +50,7 @@ static inline void free_bootmem_page(struct page *page)
 	 */
 	VM_BUG_ON_PAGE(page_ref_count(page) != 2, page);
 
-	if (magic == SECTION_INFO || magic == MIX_SECTION_INFO)
+	if (type == SECTION_INFO || type == MIX_SECTION_INFO)
 		put_page_bootmem(page);
 	else
 		VM_BUG_ON_PAGE(1, page);
@@ -48,17 +60,33 @@ static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
 
+static inline void register_page_bootmem_memmap(unsigned long section_nr,
+		struct page *map, unsigned long nr_pages)
+{
+}
+
 static inline void put_page_bootmem(struct page *page)
 {
 }
 
+static inline enum bootmem_type bootmem_type(const struct page *page)
+{
+	return SECTION_INFO;
+}
+
+static inline unsigned long bootmem_info(const struct page *page)
+{
+	return 0;
+}
+
 static inline void get_page_bootmem(unsigned long info, struct page *page,
-				    unsigned long type)
+				    enum bootmem_type type)
 {
 }
 
 static inline void free_bootmem_page(struct page *page)
 {
+	kmemleak_free_part_phys(PFN_PHYS(page_to_pfn(page)), PAGE_SIZE);
 	free_reserved_page(page);
 }
 #endif
diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
index 7b121bd780eb..c9e6b26abab6 100644
--- a/include/linux/bpf-cgroup-defs.h
+++ b/include/linux/bpf-cgroup-defs.h
@@ -28,19 +28,24 @@ enum cgroup_bpf_attach_type {
 	CGROUP_INET6_BIND,
 	CGROUP_INET4_CONNECT,
 	CGROUP_INET6_CONNECT,
+	CGROUP_UNIX_CONNECT,
 	CGROUP_INET4_POST_BIND,
 	CGROUP_INET6_POST_BIND,
 	CGROUP_UDP4_SENDMSG,
 	CGROUP_UDP6_SENDMSG,
+	CGROUP_UNIX_SENDMSG,
 	CGROUP_SYSCTL,
 	CGROUP_UDP4_RECVMSG,
 	CGROUP_UDP6_RECVMSG,
+	CGROUP_UNIX_RECVMSG,
 	CGROUP_GETSOCKOPT,
 	CGROUP_SETSOCKOPT,
 	CGROUP_INET4_GETPEERNAME,
 	CGROUP_INET6_GETPEERNAME,
+	CGROUP_UNIX_GETPEERNAME,
 	CGROUP_INET4_GETSOCKNAME,
 	CGROUP_INET6_GETSOCKNAME,
+	CGROUP_UNIX_GETSOCKNAME,
 	CGROUP_INET_SOCK_RELEASE,
 	CGROUP_LSM_START,
 	CGROUP_LSM_END = CGROUP_LSM_START + CGROUP_LSM_NUM - 1,
@@ -58,6 +63,7 @@ struct cgroup_bpf {
 	 */
 	struct hlist_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
 	u8 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
+	u64 revisions[MAX_CGROUP_BPF_ATTACH_TYPE];
 
 	/* list of cgroup shared storages */
 	struct list_head storages;
diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 57e9e109257e..d1eb5c7729cb 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -48,19 +48,24 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type)
 	CGROUP_ATYPE(CGROUP_INET6_BIND);
 	CGROUP_ATYPE(CGROUP_INET4_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET6_CONNECT);
+	CGROUP_ATYPE(CGROUP_UNIX_CONNECT);
 	CGROUP_ATYPE(CGROUP_INET4_POST_BIND);
 	CGROUP_ATYPE(CGROUP_INET6_POST_BIND);
 	CGROUP_ATYPE(CGROUP_UDP4_SENDMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_SENDMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_SENDMSG);
 	CGROUP_ATYPE(CGROUP_SYSCTL);
 	CGROUP_ATYPE(CGROUP_UDP4_RECVMSG);
 	CGROUP_ATYPE(CGROUP_UDP6_RECVMSG);
+	CGROUP_ATYPE(CGROUP_UNIX_RECVMSG);
 	CGROUP_ATYPE(CGROUP_GETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_SETSOCKOPT);
 	CGROUP_ATYPE(CGROUP_INET4_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETPEERNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETPEERNAME);
 	CGROUP_ATYPE(CGROUP_INET4_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET6_GETSOCKNAME);
+	CGROUP_ATYPE(CGROUP_UNIX_GETSOCKNAME);
 	CGROUP_ATYPE(CGROUP_INET_SOCK_RELEASE);
 	default:
 		return CGROUP_BPF_ATTACH_TYPE_INVALID;
@@ -72,9 +77,6 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type)
 extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE];
 #define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype])
 
-#define for_each_cgroup_storage_type(stype) \
-	for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++)
-
 struct bpf_cgroup_storage_map;
 
 struct bpf_storage_buffer {
@@ -98,7 +100,6 @@ struct bpf_cgroup_storage {
 struct bpf_cgroup_link {
 	struct bpf_link link;
 	struct cgroup *cgroup;
-	enum bpf_attach_type type;
 };
 
 struct bpf_prog_list {
@@ -106,10 +107,10 @@ struct bpf_prog_list {
 	struct bpf_prog *prog;
 	struct bpf_cgroup_link *link;
 	struct bpf_cgroup_storage *storage[MAX_BPF_CGROUP_STORAGE_TYPE];
+	u32 flags;
 };
 
-int cgroup_bpf_inherit(struct cgroup *cgrp);
-void cgroup_bpf_offline(struct cgroup *cgrp);
+void __init cgroup_bpf_lifetime_notifier_init(void);
 
 int __cgroup_bpf_run_filter_skb(struct sock *sk,
 				struct sk_buff *skb,
@@ -119,7 +120,8 @@ int __cgroup_bpf_run_filter_sk(struct sock *sk,
 			       enum cgroup_bpf_attach_type atype);
 
 int __cgroup_bpf_run_filter_sock_addr(struct sock *sk,
-				      struct sockaddr *uaddr,
+				      struct sockaddr_unsized *uaddr,
+				      int *uaddrlen,
 				      enum cgroup_bpf_attach_type atype,
 				      void *t_ctx,
 				      u32 *flags);
@@ -132,16 +134,17 @@ int __cgroup_bpf_check_dev_permission(short dev_type, u32 major, u32 minor,
 				      short access, enum cgroup_bpf_attach_type atype);
 
 int __cgroup_bpf_run_filter_sysctl(struct ctl_table_header *head,
-				   struct ctl_table *table, int write,
+				   const struct ctl_table *table, int write,
 				   char **buf, size_t *pcount, loff_t *ppos,
 				   enum cgroup_bpf_attach_type atype);
 
 int __cgroup_bpf_run_filter_setsockopt(struct sock *sock, int *level,
-				       int *optname, char __user *optval,
+				       int *optname, sockptr_t optval,
 				       int *optlen, char **kernel_optval);
+
 int __cgroup_bpf_run_filter_getsockopt(struct sock *sk, int level,
-				       int optname, char __user *optval,
-				       int __user *optlen, int max_optlen,
+				       int optname, sockptr_t optval,
+				       sockptr_t optlen, int max_optlen,
 				       int retval);
 
 int __cgroup_bpf_run_filter_getsockopt_kern(struct sock *sk, int level,
@@ -189,7 +192,8 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 ({									      \
 	int __ret = 0;							      \
 	if (cgroup_bpf_enabled(CGROUP_INET_INGRESS) &&			      \
-	    cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS))		      \
+	    cgroup_bpf_sock_enabled(sk, CGROUP_INET_INGRESS) && sk &&	      \
+	    sk_fullsock(sk))						      \
 		__ret = __cgroup_bpf_run_filter_skb(sk, skb,		      \
 						    CGROUP_INET_INGRESS); \
 									      \
@@ -199,9 +203,9 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk, skb)			       \
 ({									       \
 	int __ret = 0;							       \
-	if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk && sk == skb->sk) { \
+	if (cgroup_bpf_enabled(CGROUP_INET_EGRESS) && sk) {		       \
 		typeof(sk) __sk = sk_to_full_sk(sk);			       \
-		if (sk_fullsock(__sk) &&				       \
+		if (__sk && __sk == skb_to_full_sk(skb) &&	       \
 		    cgroup_bpf_sock_enabled(__sk, CGROUP_INET_EGRESS))	       \
 			__ret = __cgroup_bpf_run_filter_skb(__sk, skb,	       \
 						      CGROUP_INET_EGRESS); \
@@ -230,22 +234,24 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk)				       \
 	BPF_CGROUP_RUN_SK_PROG(sk, CGROUP_INET6_POST_BIND)
 
-#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype)				       \
+#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype)		       \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))					       \
-		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  NULL, NULL);	       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk,		       \
+				(struct sockaddr_unsized *)uaddr, uaddrlen,     \
+				atype, NULL, NULL);			       \
 	__ret;								       \
 })
 
-#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx)		       \
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx)	       \
 ({									       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))	{				       \
 		lock_sock(sk);						       \
-		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  t_ctx, NULL);	       \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk,		       \
+				(struct sockaddr_unsized *)uaddr, uaddrlen,     \
+				atype, t_ctx, NULL);			       \
 		release_sock(sk);					       \
 	}								       \
 	__ret;								       \
@@ -256,14 +262,15 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
  * (at bit position 0) is to indicate CAP_NET_BIND_SERVICE capability check
  * should be bypassed (BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE).
  */
-#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, bind_flags)	       \
+#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, bind_flags) \
 ({									       \
 	u32 __flags = 0;						       \
 	int __ret = 0;							       \
 	if (cgroup_bpf_enabled(atype))	{				       \
 		lock_sock(sk);						       \
-		__ret = __cgroup_bpf_run_filter_sock_addr(sk, uaddr, atype,     \
-							  NULL, &__flags);     \
+		__ret = __cgroup_bpf_run_filter_sock_addr(sk,		       \
+				(struct sockaddr_unsized *)uaddr, uaddrlen,     \
+				atype, NULL, &__flags);			       \
 		release_sock(sk);					       \
 		if (__flags & BPF_RET_BIND_NO_CAP_NET_BIND_SERVICE)	       \
 			*bind_flags |= BIND_NO_CAP_NET_BIND_SERVICE;	       \
@@ -276,29 +283,38 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 	  cgroup_bpf_enabled(CGROUP_INET6_CONNECT)) &&		       \
 	 (sk)->sk_prot->pre_connect)
 
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET4_CONNECT)
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen)			\
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen)			\
+	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT)
+
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET4_CONNECT, NULL)
+
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_INET6_CONNECT, NULL)
 
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr)			       \
-	BPF_CGROUP_RUN_SA_PROG(sk, uaddr, CGROUP_INET6_CONNECT)
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_CONNECT, NULL)
 
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET4_CONNECT, NULL)
+#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_SENDMSG, t_ctx)
 
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_INET6_CONNECT, NULL)
+#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_SENDMSG, t_ctx)
 
-#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_SENDMSG, t_ctx)
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx)	\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_SENDMSG, t_ctx)
 
-#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx)		       \
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_SENDMSG, t_ctx)
+#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP4_RECVMSG, NULL)
 
-#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr)			\
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP4_RECVMSG, NULL)
+#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UDP6_RECVMSG, NULL)
 
-#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr)			\
-	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, CGROUP_UDP6_RECVMSG, NULL)
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen)		\
+	BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, CGROUP_UNIX_RECVMSG, NULL)
 
 /* The SOCK_OPS"_SK" macro should be used when sock_ops->sk is not a
  * fullsock and its parent fullsock cannot be traced by
@@ -373,14 +389,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
 	__ret;								       \
 })
 
-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen)			       \
-({									       \
-	int __ret = 0;							       \
-	if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT))			       \
-		get_user(__ret, optlen);				       \
-	__ret;								       \
-})
-
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen,   \
 				       max_optlen, retval)		       \
 ({									       \
@@ -417,12 +425,12 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
 
 const struct bpf_func_proto *
 cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
-const struct bpf_func_proto *
-cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 #else
 
-static inline int cgroup_bpf_inherit(struct cgroup *cgrp) { return 0; }
-static inline void cgroup_bpf_offline(struct cgroup *cgrp) {}
+static inline void cgroup_bpf_lifetime_notifier_init(void)
+{
+	return;
+}
 
 static inline int cgroup_bpf_prog_attach(const union bpf_attr *attr,
 					 enum bpf_prog_type ptype,
@@ -455,12 +463,6 @@ cgroup_common_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	return NULL;
 }
 
-static inline const struct bpf_func_proto *
-cgroup_current_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
-{
-	return NULL;
-}
-
 static inline int bpf_cgroup_storage_assign(struct bpf_prog_aux *aux,
 					    struct bpf_map *map) { return 0; }
 static inline struct bpf_cgroup_storage *bpf_cgroup_storage_alloc(
@@ -477,28 +479,30 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 }
 
 #define cgroup_bpf_enabled(atype) (0)
-#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, atype, t_ctx) ({ 0; })
-#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, atype) ({ 0; })
+#define BPF_CGROUP_RUN_SA_PROG_LOCK(sk, uaddr, uaddrlen, atype, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_SA_PROG(sk, uaddr, uaddrlen, atype) ({ 0; })
 #define BPF_CGROUP_PRE_CONNECT_ENABLED(sk) (0)
 #define BPF_CGROUP_RUN_PROG_INET_INGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_EGRESS(sk,skb) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET_SOCK_RELEASE(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, atype, flags) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET_BIND_LOCK(sk, uaddr, uaddrlen, atype, flags) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, t_ctx) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr) ({ 0; })
-#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_INET6_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_CONNECT_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP6_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_SENDMSG_LOCK(sk, uaddr, uaddrlen, t_ctx) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UDP6_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
+#define BPF_CGROUP_RUN_PROG_UNIX_RECVMSG_LOCK(sk, uaddr, uaddrlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
 				       optlen, max_optlen, retval) ({ retval; })
 #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \
@@ -506,8 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
 				       kernel_optval) ({ 0; })
 
-#define for_each_cgroup_storage_type(stype) for (; false; )
-
 #endif /* CONFIG_CGROUP_BPF */
 
 #endif /* _BPF_CGROUP_H */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e53ceee1df37..6498be4c44f8 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -7,6 +7,7 @@
 #include <uapi/linux/bpf.h>
 #include <uapi/linux/filter.h>
 
+#include <crypto/sha2.h>
 #include <linux/workqueue.h>
 #include <linux/file.h>
 #include <linux/percpu.h>
@@ -29,6 +30,8 @@
 #include <linux/rcupdate_trace.h>
 #include <linux/static_call.h>
 #include <linux/memcontrol.h>
+#include <linux/cfi.h>
+#include <asm/rqspinlock.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -36,6 +39,7 @@ struct perf_event;
 struct bpf_prog;
 struct bpf_prog_aux;
 struct bpf_map;
+struct bpf_arena;
 struct sock;
 struct seq_file;
 struct btf;
@@ -51,11 +55,15 @@ struct module;
 struct bpf_func_state;
 struct ftrace_ops;
 struct cgroup;
+struct bpf_token;
+struct user_namespace;
+struct super_block;
+struct inode;
 
 extern struct idr btf_idr;
 extern spinlock_t btf_idr_lock;
 extern struct kobject *btf_kobj;
-extern struct bpf_mem_alloc bpf_global_ma;
+extern struct bpf_mem_alloc bpf_global_ma, bpf_global_percpu_ma;
 extern bool bpf_global_ma_set;
 
 typedef u64 (*bpf_callback_t)(u64, u64, u64, u64, u64);
@@ -102,11 +110,16 @@ struct bpf_map_ops {
 	long (*map_pop_elem)(struct bpf_map *map, void *value);
 	long (*map_peek_elem)(struct bpf_map *map, void *value);
 	void *(*map_lookup_percpu_elem)(struct bpf_map *map, void *key, u32 cpu);
+	int (*map_get_hash)(struct bpf_map *map, u32 hash_buf_size, void *hash_buf);
 
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
 				int fd);
-	void (*map_fd_put_ptr)(void *ptr);
+	/* If need_defer is true, the implementation should guarantee that
+	 * the to-be-put element is still alive before the bpf program, which
+	 * may manipulate it, exists.
+	 */
+	void (*map_fd_put_ptr)(struct bpf_map *map, void *ptr, bool need_defer);
 	int (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
 	u32 (*map_fd_sys_lookup_elem)(void *ptr);
 	void (*map_seq_show_elem)(struct bpf_map *map, void *key,
@@ -130,6 +143,9 @@ struct bpf_map_ops {
 	int (*map_mmap)(struct bpf_map *map, struct vm_area_struct *vma);
 	__poll_t (*map_poll)(struct bpf_map *map, struct file *filp,
 			     struct poll_table_struct *pts);
+	unsigned long (*map_get_unmapped_area)(struct file *filep, unsigned long addr,
+					       unsigned long len, unsigned long pgoff,
+					       unsigned long flags);
 
 	/* Functions called by bpf_local_storage maps */
 	int (*map_local_storage_charge)(struct bpf_local_storage_map *smap,
@@ -171,8 +187,8 @@ struct bpf_map_ops {
 };
 
 enum {
-	/* Support at most 10 fields in a BTF type */
-	BTF_FIELDS_MAX	   = 10,
+	/* Support at most 11 fields in a BTF type */
+	BTF_FIELDS_MAX	   = 11,
 };
 
 enum btf_field_type {
@@ -180,16 +196,35 @@ enum btf_field_type {
 	BPF_TIMER      = (1 << 1),
 	BPF_KPTR_UNREF = (1 << 2),
 	BPF_KPTR_REF   = (1 << 3),
-	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF,
-	BPF_LIST_HEAD  = (1 << 4),
-	BPF_LIST_NODE  = (1 << 5),
-	BPF_RB_ROOT    = (1 << 6),
-	BPF_RB_NODE    = (1 << 7),
-	BPF_GRAPH_NODE_OR_ROOT = BPF_LIST_NODE | BPF_LIST_HEAD |
-				 BPF_RB_NODE | BPF_RB_ROOT,
-	BPF_REFCOUNT   = (1 << 8),
+	BPF_KPTR_PERCPU = (1 << 4),
+	BPF_KPTR       = BPF_KPTR_UNREF | BPF_KPTR_REF | BPF_KPTR_PERCPU,
+	BPF_LIST_HEAD  = (1 << 5),
+	BPF_LIST_NODE  = (1 << 6),
+	BPF_RB_ROOT    = (1 << 7),
+	BPF_RB_NODE    = (1 << 8),
+	BPF_GRAPH_NODE = BPF_RB_NODE | BPF_LIST_NODE,
+	BPF_GRAPH_ROOT = BPF_RB_ROOT | BPF_LIST_HEAD,
+	BPF_REFCOUNT   = (1 << 9),
+	BPF_WORKQUEUE  = (1 << 10),
+	BPF_UPTR       = (1 << 11),
+	BPF_RES_SPIN_LOCK = (1 << 12),
+	BPF_TASK_WORK  = (1 << 13),
 };
 
+enum bpf_cgroup_storage_type {
+	BPF_CGROUP_STORAGE_SHARED,
+	BPF_CGROUP_STORAGE_PERCPU,
+	__BPF_CGROUP_STORAGE_MAX
+#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
+};
+
+#ifdef CONFIG_CGROUP_BPF
+# define for_each_cgroup_storage_type(stype) \
+	for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++)
+#else
+# define for_each_cgroup_storage_type(stype) for (; false; )
+#endif /* CONFIG_CGROUP_BPF */
+
 typedef void (*btf_dtor_kfunc_t)(void *);
 
 struct btf_field_kptr {
@@ -223,16 +258,43 @@ struct btf_record {
 	u32 cnt;
 	u32 field_mask;
 	int spin_lock_off;
+	int res_spin_lock_off;
 	int timer_off;
+	int wq_off;
 	int refcount_off;
+	int task_work_off;
 	struct btf_field fields[];
 };
 
+/* Non-opaque version of bpf_rb_node in uapi/linux/bpf.h */
+struct bpf_rb_node_kern {
+	struct rb_node rb_node;
+	void *owner;
+} __attribute__((aligned(8)));
+
+/* Non-opaque version of bpf_list_node in uapi/linux/bpf.h */
+struct bpf_list_node_kern {
+	struct list_head list_head;
+	void *owner;
+} __attribute__((aligned(8)));
+
+/* 'Ownership' of program-containing map is claimed by the first program
+ * that is going to use this map or by the first program which FD is
+ * stored in the map to make sure that all callers and callees have the
+ * same prog type, JITed flag and xdp_has_frags flag.
+ */
+struct bpf_map_owner {
+	enum bpf_prog_type type;
+	bool jited;
+	bool xdp_has_frags;
+	u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE];
+	const struct btf_type *attach_func_proto;
+	enum bpf_attach_type expected_attach_type;
+};
+
 struct bpf_map {
-	/* The first two cachelines with read-mostly members of which some
-	 * are also accessed in fast-path (e.g. ops, max_entries).
-	 */
-	const struct bpf_map_ops *ops ____cacheline_aligned;
+	u8 sha[SHA256_DIGEST_SIZE];
+	const struct bpf_map_ops *ops;
 	struct bpf_map *inner_map_meta;
 #ifdef CONFIG_SECURITY
 	void *security;
@@ -250,31 +312,29 @@ struct bpf_map {
 	u32 btf_value_type_id;
 	u32 btf_vmlinux_value_type_id;
 	struct btf *btf;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	struct obj_cgroup *objcg;
 #endif
 	char name[BPF_OBJ_NAME_LEN];
-	/* The 3rd and 4th cacheline with misc members to avoid false sharing
-	 * particularly with refcounting.
-	 */
-	atomic64_t refcnt ____cacheline_aligned;
-	atomic64_t usercnt;
-	struct work_struct work;
 	struct mutex freeze_mutex;
+	atomic64_t refcnt;
+	atomic64_t usercnt;
+	/* rcu is used before freeing and work is only used during freeing */
+	union {
+		struct work_struct work;
+		struct rcu_head rcu;
+	};
 	atomic64_t writecnt;
-	/* 'Ownership' of program-containing map is claimed by the first program
-	 * that is going to use this map or by the first program which FD is
-	 * stored in the map to make sure that all callers and callees have the
-	 * same prog type, JITed flag and xdp_has_frags flag.
-	 */
-	struct {
-		spinlock_t lock;
-		enum bpf_prog_type type;
-		bool jited;
-		bool xdp_has_frags;
-	} owner;
+	spinlock_t owner_lock;
+	struct bpf_map_owner *owner;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
+	bool free_after_mult_rcu_gp;
+	bool free_after_rcu_gp;
+	atomic64_t sleepable_refcnt;
+	s64 __percpu *elem_count;
+	u64 cookie; /* write-once */
+	char *excl_prog_sha;
 };
 
 static inline const char *btf_field_type_name(enum btf_field_type type)
@@ -282,11 +342,19 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 	switch (type) {
 	case BPF_SPIN_LOCK:
 		return "bpf_spin_lock";
+	case BPF_RES_SPIN_LOCK:
+		return "bpf_res_spin_lock";
 	case BPF_TIMER:
 		return "bpf_timer";
+	case BPF_WORKQUEUE:
+		return "bpf_wq";
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
 		return "kptr";
+	case BPF_KPTR_PERCPU:
+		return "percpu_kptr";
+	case BPF_UPTR:
+		return "uptr";
 	case BPF_LIST_HEAD:
 		return "bpf_list_head";
 	case BPF_LIST_NODE:
@@ -297,21 +365,35 @@ static inline const char *btf_field_type_name(enum btf_field_type type)
 		return "bpf_rb_node";
 	case BPF_REFCOUNT:
 		return "bpf_refcount";
+	case BPF_TASK_WORK:
+		return "bpf_task_work";
 	default:
 		WARN_ON_ONCE(1);
 		return "unknown";
 	}
 }
 
+#if IS_ENABLED(CONFIG_DEBUG_KERNEL)
+#define BPF_WARN_ONCE(cond, format...) WARN_ONCE(cond, format)
+#else
+#define BPF_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
+#endif
+
 static inline u32 btf_field_type_size(enum btf_field_type type)
 {
 	switch (type) {
 	case BPF_SPIN_LOCK:
 		return sizeof(struct bpf_spin_lock);
+	case BPF_RES_SPIN_LOCK:
+		return sizeof(struct bpf_res_spin_lock);
 	case BPF_TIMER:
 		return sizeof(struct bpf_timer);
+	case BPF_WORKQUEUE:
+		return sizeof(struct bpf_wq);
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
+	case BPF_UPTR:
 		return sizeof(u64);
 	case BPF_LIST_HEAD:
 		return sizeof(struct bpf_list_head);
@@ -323,6 +405,8 @@ static inline u32 btf_field_type_size(enum btf_field_type type)
 		return sizeof(struct bpf_rb_node);
 	case BPF_REFCOUNT:
 		return sizeof(struct bpf_refcount);
+	case BPF_TASK_WORK:
+		return sizeof(struct bpf_task_work);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -334,10 +418,16 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 	switch (type) {
 	case BPF_SPIN_LOCK:
 		return __alignof__(struct bpf_spin_lock);
+	case BPF_RES_SPIN_LOCK:
+		return __alignof__(struct bpf_res_spin_lock);
 	case BPF_TIMER:
 		return __alignof__(struct bpf_timer);
+	case BPF_WORKQUEUE:
+		return __alignof__(struct bpf_wq);
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
+	case BPF_UPTR:
 		return __alignof__(u64);
 	case BPF_LIST_HEAD:
 		return __alignof__(struct bpf_list_head);
@@ -349,6 +439,8 @@ static inline u32 btf_field_type_align(enum btf_field_type type)
 		return __alignof__(struct bpf_rb_node);
 	case BPF_REFCOUNT:
 		return __alignof__(struct bpf_refcount);
+	case BPF_TASK_WORK:
+		return __alignof__(struct bpf_task_work);
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
@@ -373,9 +465,14 @@ static inline void bpf_obj_init_field(const struct btf_field *field, void *addr)
 	case BPF_RB_ROOT:
 		/* RB_ROOT_CACHED 0-inits, no need to do anything after memset */
 	case BPF_SPIN_LOCK:
+	case BPF_RES_SPIN_LOCK:
 	case BPF_TIMER:
+	case BPF_WORKQUEUE:
 	case BPF_KPTR_UNREF:
 	case BPF_KPTR_REF:
+	case BPF_KPTR_PERCPU:
+	case BPF_UPTR:
+	case BPF_TASK_WORK:
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -425,7 +522,7 @@ static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
 
 	size /= sizeof(long);
 	while (size--)
-		*ldst++ = *lsrc++;
+		data_race(*ldst++ = *lsrc++);
 }
 
 /* copy everything but bpf_spin_lock, bpf_timer, and kptrs. There could be one of each. */
@@ -464,6 +561,25 @@ static inline void copy_map_value_long(struct bpf_map *map, void *dst, void *src
 	bpf_obj_memcpy(map->record, dst, src, map->value_size, true);
 }
 
+static inline void bpf_obj_swap_uptrs(const struct btf_record *rec, void *dst, void *src)
+{
+	unsigned long *src_uptr, *dst_uptr;
+	const struct btf_field *field;
+	int i;
+
+	if (!btf_record_has_field(rec, BPF_UPTR))
+		return;
+
+	for (i = 0, field = rec->fields; i < rec->cnt; i++, field++) {
+		if (field->type != BPF_UPTR)
+			continue;
+
+		src_uptr = src + field->offset;
+		dst_uptr = dst + field->offset;
+		swap(*src_uptr, *dst_uptr);
+	}
+}
+
 static inline void bpf_obj_memzero(struct btf_record *rec, void *dst, u32 size)
 {
 	u32 curr_off = 0;
@@ -492,12 +608,14 @@ static inline void zero_map_value(struct bpf_map *map, void *dst)
 void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
 			   bool lock_src);
 void bpf_timer_cancel_and_free(void *timer);
+void bpf_wq_cancel_and_free(void *timer);
+void bpf_task_work_cancel_and_free(void *timer);
 void bpf_list_head_free(const struct btf_field *field, void *list_head,
 			struct bpf_spin_lock *spin_lock);
 void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
 		      struct bpf_spin_lock *spin_lock);
-
-
+u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena);
+u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena);
 int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
 
 struct bpf_offload_dev;
@@ -545,6 +663,16 @@ int map_check_no_btf(const struct bpf_map *map,
 bool bpf_map_meta_equal(const struct bpf_map *meta0,
 			const struct bpf_map *meta1);
 
+static inline bool bpf_map_has_internal_structs(struct bpf_map *map)
+{
+	return btf_record_has_field(map->record, BPF_TIMER | BPF_WORKQUEUE | BPF_TASK_WORK);
+}
+
+void bpf_map_free_internal_structs(struct bpf_map *map, void *obj);
+
+int bpf_dynptr_from_file_sleepable(struct file *file, u32 flags,
+				   struct bpf_dynptr *ptr__uninit);
+
 extern const struct bpf_map_ops bpf_map_offload_ops;
 
 /* bpf_type_flag contains a set of flags that are applicable to the values of
@@ -591,6 +719,7 @@ enum bpf_type_flag {
 	 */
 	PTR_UNTRUSTED		= BIT(6 + BPF_BASE_TYPE_BITS),
 
+	/* MEM can be uninitialized. */
 	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
 
 	/* DYNPTR points to memory local to the bpf program. */
@@ -640,7 +769,8 @@ enum bpf_type_flag {
 	MEM_RCU			= BIT(13 + BPF_BASE_TYPE_BITS),
 
 	/* Used to tag PTR_TO_BTF_ID | MEM_ALLOC references which are non-owning.
-	 * Currently only valid for linked-list and rbtree nodes.
+	 * Currently only valid for linked-list and rbtree nodes. If the nodes
+	 * have a bpf_refcount_field, they must be tagged MEM_RCU as well.
 	 */
 	NON_OWN_REF		= BIT(14 + BPF_BASE_TYPE_BITS),
 
@@ -650,12 +780,30 @@ enum bpf_type_flag {
 	/* DYNPTR points to xdp_buff */
 	DYNPTR_TYPE_XDP		= BIT(16 + BPF_BASE_TYPE_BITS),
 
+	/* Memory must be aligned on some architectures, used in combination with
+	 * MEM_FIXED_SIZE.
+	 */
+	MEM_ALIGNED		= BIT(17 + BPF_BASE_TYPE_BITS),
+
+	/* MEM is being written to, often combined with MEM_UNINIT. Non-presence
+	 * of MEM_WRITE means that MEM is only being read. MEM_WRITE without the
+	 * MEM_UNINIT means that memory needs to be initialized since it is also
+	 * read.
+	 */
+	MEM_WRITE		= BIT(18 + BPF_BASE_TYPE_BITS),
+
+	/* DYNPTR points to skb_metadata_end()-skb_metadata_len() */
+	DYNPTR_TYPE_SKB_META	= BIT(19 + BPF_BASE_TYPE_BITS),
+
+	/* DYNPTR points to file */
+	DYNPTR_TYPE_FILE	= BIT(20 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
 
 #define DYNPTR_TYPE_FLAG_MASK	(DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF | DYNPTR_TYPE_SKB \
-				 | DYNPTR_TYPE_XDP)
+				 | DYNPTR_TYPE_XDP | DYNPTR_TYPE_SKB_META | DYNPTR_TYPE_FILE)
 
 /* Max number of base types. */
 #define BPF_BASE_TYPE_LIMIT	(1UL << BPF_BASE_TYPE_BITS)
@@ -678,6 +826,7 @@ enum bpf_arg_type {
 	 * on eBPF program stack
 	 */
 	ARG_PTR_TO_MEM,		/* pointer to valid memory (stack, packet, map value) */
+	ARG_PTR_TO_ARENA,
 
 	ARG_CONST_SIZE,		/* number of bytes accessed from memory */
 	ARG_CONST_SIZE_OR_ZERO,	/* number of bytes accessed from memory or 0 */
@@ -686,8 +835,6 @@ enum bpf_arg_type {
 	ARG_ANYTHING,		/* any (initialized) argument is ok */
 	ARG_PTR_TO_SPIN_LOCK,	/* pointer to bpf_spin_lock */
 	ARG_PTR_TO_SOCK_COMMON,	/* pointer to sock_common */
-	ARG_PTR_TO_INT,		/* pointer to int */
-	ARG_PTR_TO_LONG,	/* pointer to long */
 	ARG_PTR_TO_SOCKET,	/* pointer to bpf_sock (fullsock) */
 	ARG_PTR_TO_BTF_ID,	/* pointer to in-kernel struct */
 	ARG_PTR_TO_RINGBUF_MEM,	/* pointer to dynamically reserved ringbuf memory */
@@ -698,7 +845,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_STACK,	/* pointer to stack */
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
-	ARG_PTR_TO_KPTR,	/* pointer to referenced kptr */
+	ARG_KPTR_XCHG_DEST,	/* pointer to destination that kptrs are bpf_kptr_xchg'd into */
 	ARG_PTR_TO_DYNPTR,      /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
 	__BPF_ARG_TYPE_MAX,
 
@@ -709,10 +856,10 @@ enum bpf_arg_type {
 	ARG_PTR_TO_SOCKET_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_SOCKET,
 	ARG_PTR_TO_STACK_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_STACK,
 	ARG_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | ARG_PTR_TO_BTF_ID,
-	/* pointer to memory does not need to be initialized, helper function must fill
-	 * all bytes or clear them in error case.
+	/* Pointer to memory does not need to be initialized, since helper function
+	 * fills all bytes or clears them in error case.
 	 */
-	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | ARG_PTR_TO_MEM,
+	ARG_PTR_TO_UNINIT_MEM		= MEM_UNINIT | MEM_WRITE | ARG_PTR_TO_MEM,
 	/* Pointer to valid memory of size known at compile time. */
 	ARG_PTR_TO_FIXED_SIZE_MEM	= MEM_FIXED_SIZE | ARG_PTR_TO_MEM,
 
@@ -762,6 +909,12 @@ struct bpf_func_proto {
 	bool gpl_only;
 	bool pkt_access;
 	bool might_sleep;
+	/* set to true if helper follows contract for llvm
+	 * attribute bpf_fastcall:
+	 * - void functions do not scratch r0
+	 * - functions taking N arguments scratch only registers r1-rN
+	 */
+	bool allow_fastcall;
 	enum bpf_return_type ret_type;
 	union {
 		struct {
@@ -844,13 +997,11 @@ enum bpf_reg_type {
 	 * additional context, assume the value is non-null.
 	 */
 	PTR_TO_BTF_ID,
-	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
-	 * been checked for null. Used primarily to inform the verifier
-	 * an explicit null check is required for this struct.
-	 */
 	PTR_TO_MEM,		 /* reg points to valid memory region */
+	PTR_TO_ARENA,
 	PTR_TO_BUF,		 /* reg points to a read/write buffer */
 	PTR_TO_FUNC,		 /* reg points to a bpf program function */
+	PTR_TO_INSN,		 /* reg points to a bpf program instruction */
 	CONST_PTR_TO_DYNPTR,	 /* reg points to a const struct bpf_dynptr */
 	__BPF_REG_TYPE_MAX,
 
@@ -859,6 +1010,10 @@ enum bpf_reg_type {
 	PTR_TO_SOCKET_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_SOCKET,
 	PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | PTR_TO_SOCK_COMMON,
 	PTR_TO_TCP_SOCK_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_TCP_SOCK,
+	/* PTR_TO_BTF_ID_OR_NULL points to a kernel struct that has not
+	 * been checked for null. Used primarily to inform the verifier
+	 * an explicit null check is required for this struct.
+	 */
 	PTR_TO_BTF_ID_OR_NULL		= PTR_MAYBE_NULL | PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
@@ -873,14 +1028,17 @@ static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
  */
 struct bpf_insn_access_aux {
 	enum bpf_reg_type reg_type;
+	bool is_ldsx;
 	union {
 		int ctx_field_size;
 		struct {
 			struct btf *btf;
 			u32 btf_id;
+			u32 ref_obj_id;
 		};
 	};
 	struct bpf_verifier_log *log; /* for verbose logs */
+	bool is_retval; /* is accessing function return value ? */
 };
 
 static inline void
@@ -889,10 +1047,29 @@ bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
 	aux->ctx_field_size = size;
 }
 
+static bool bpf_is_ldimm64(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+}
+
 static inline bool bpf_pseudo_func(const struct bpf_insn *insn)
 {
-	return insn->code == (BPF_LD | BPF_IMM | BPF_DW) &&
-	       insn->src_reg == BPF_PSEUDO_FUNC;
+	return bpf_is_ldimm64(insn) && insn->src_reg == BPF_PSEUDO_FUNC;
+}
+
+/* Given a BPF_ATOMIC instruction @atomic_insn, return true if it is an
+ * atomic load or store, and false if it is a read-modify-write instruction.
+ */
+static inline bool
+bpf_atomic_is_load_store(const struct bpf_insn *atomic_insn)
+{
+	switch (atomic_insn->imm) {
+	case BPF_LOAD_ACQ:
+	case BPF_STORE_REL:
+		return true;
+	default:
+		return false;
+	}
 }
 
 struct bpf_prog_ops {
@@ -915,6 +1092,8 @@ struct bpf_verifier_ops {
 				struct bpf_insn_access_aux *info);
 	int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
 			    const struct bpf_prog *prog);
+	int (*gen_epilogue)(struct bpf_insn *insn, const struct bpf_prog *prog,
+			    s16 ctx_stack_off);
 	int (*gen_ld_abs)(const struct bpf_insn *orig,
 			  struct bpf_insn *insn_buf);
 	u32 (*convert_ctx_access)(enum bpf_access_type type,
@@ -953,14 +1132,6 @@ struct bpf_prog_offload {
 	u32			jited_len;
 };
 
-enum bpf_cgroup_storage_type {
-	BPF_CGROUP_STORAGE_SHARED,
-	BPF_CGROUP_STORAGE_PERCPU,
-	__BPF_CGROUP_STORAGE_MAX
-};
-
-#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
-
 /* The longest tracepoint has 12 args.
  * See include/trace/bpf_probe.h
  */
@@ -971,7 +1142,7 @@ enum bpf_cgroup_storage_type {
  */
 #define MAX_BPF_FUNC_REG_ARGS 5
 
-/* The argument is a structure. */
+/* The argument is a structure or a union. */
 #define BTF_FMODEL_STRUCT_ARG		BIT(0)
 
 /* The argument is signed. */
@@ -1015,6 +1186,22 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_SHARE_IPMODIFY	BIT(6)
 
+/* Indicate that current trampoline is in a tail call context. Then, it has to
+ * cache and restore tail_call_cnt to avoid infinite tail call loop.
+ */
+#define BPF_TRAMP_F_TAIL_CALL_CTX	BIT(7)
+
+/*
+ * Indicate the trampoline should be suitable to receive indirect calls;
+ * without this indirectly calling the generated code can result in #UD/#CP,
+ * depending on the CFI options.
+ *
+ * Used by bpf_struct_ops.
+ *
+ * Incompatible with FENTRY usage, overloads @func_addr argument.
+ */
+#define BPF_TRAMP_F_INDIRECT		BIT(8)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.
  */
@@ -1054,10 +1241,16 @@ struct bpf_tramp_run_ctx;
  *      fexit = a set of program to run after original function
  */
 struct bpf_tramp_image;
-int arch_prepare_bpf_trampoline(struct bpf_tramp_image *tr, void *image, void *image_end,
+int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *image_end,
 				const struct btf_func_model *m, u32 flags,
 				struct bpf_tramp_links *tlinks,
-				void *orig_call);
+				void *func_addr);
+void *arch_alloc_bpf_trampoline(unsigned int size);
+void arch_free_bpf_trampoline(void *image, unsigned int size);
+int __must_check arch_protect_bpf_trampoline(void *image, unsigned int size);
+int arch_bpf_trampoline_size(const struct btf_func_model *m, u32 flags,
+			     struct bpf_tramp_links *tlinks, void *func_addr);
+
 u64 notrace __bpf_prog_enter_sleepable_recur(struct bpf_prog *prog,
 					     struct bpf_tramp_run_ctx *run_ctx);
 void notrace __bpf_prog_exit_sleepable_recur(struct bpf_prog *prog, u64 start,
@@ -1071,6 +1264,18 @@ typedef void (*bpf_trampoline_exit_t)(struct bpf_prog *prog, u64 start,
 bpf_trampoline_enter_t bpf_trampoline_enter(const struct bpf_prog *prog);
 bpf_trampoline_exit_t bpf_trampoline_exit(const struct bpf_prog *prog);
 
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+	return flags & BPF_TRAMP_F_CALL_ORIG && !(flags & BPF_TRAMP_F_SKIP_FRAME);
+}
+#else
+static inline bool bpf_trampoline_use_jmp(u64 flags)
+{
+	return false;
+}
+#endif
+
 struct bpf_ksym {
 	unsigned long		 start;
 	unsigned long		 end;
@@ -1090,6 +1295,7 @@ enum bpf_tramp_prog_type {
 
 struct bpf_tramp_image {
 	void *image;
+	int size;
 	struct bpf_ksym ksym;
 	struct percpu_ref pcref;
 	void *ip_after_call;
@@ -1125,8 +1331,6 @@ struct bpf_trampoline {
 	int progs_cnt[BPF_TRAMP_MAX];
 	/* Executable image of trampoline */
 	struct bpf_tramp_image *cur_image;
-	u64 selector;
-	struct module *mod;
 };
 
 struct bpf_attach_target_info {
@@ -1160,7 +1364,11 @@ struct bpf_dispatcher {
 #endif
 };
 
-static __always_inline __nocfi unsigned int bpf_dispatcher_nop_func(
+#ifndef __bpfcall
+#define __bpfcall __nocfi
+#endif
+
+static __always_inline __bpfcall unsigned int bpf_dispatcher_nop_func(
 	const void *ctx,
 	const struct bpf_insn *insnsi,
 	bpf_func_t bpf_func)
@@ -1194,14 +1402,39 @@ enum bpf_dynptr_type {
 	BPF_DYNPTR_TYPE_SKB,
 	/* Underlying data is a xdp_buff */
 	BPF_DYNPTR_TYPE_XDP,
+	/* Points to skb_metadata_end()-skb_metadata_len() */
+	BPF_DYNPTR_TYPE_SKB_META,
+	/* Underlying data is a file */
+	BPF_DYNPTR_TYPE_FILE,
 };
 
-int bpf_dynptr_check_size(u32 size);
-u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_check_size(u64 size);
+u64 __bpf_dynptr_size(const struct bpf_dynptr_kern *ptr);
+const void *__bpf_dynptr_data(const struct bpf_dynptr_kern *ptr, u64 len);
+void *__bpf_dynptr_data_rw(const struct bpf_dynptr_kern *ptr, u64 len);
+bool __bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr);
+int __bpf_dynptr_write(const struct bpf_dynptr_kern *dst, u64 offset,
+		       void *src, u64 len, u64 flags);
+void *bpf_dynptr_slice_rdwr(const struct bpf_dynptr *p, u64 offset,
+			    void *buffer__opt, u64 buffer__szk);
+
+static inline int bpf_dynptr_check_off_len(const struct bpf_dynptr_kern *ptr, u64 offset, u64 len)
+{
+	u64 size = __bpf_dynptr_size(ptr);
+
+	if (len > size || offset > size - len)
+		return -E2BIG;
+
+	return 0;
+}
 
 #ifdef CONFIG_BPF_JIT
-int bpf_trampoline_link_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
-int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link, struct bpf_trampoline *tr);
+int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
+			     struct bpf_trampoline *tr,
+			     struct bpf_prog *tgt_prog);
+int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
+			       struct bpf_trampoline *tr,
+			       struct bpf_prog *tgt_prog);
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
@@ -1250,7 +1483,7 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 
 #define DEFINE_BPF_DISPATCHER(name)					\
 	__BPF_DISPATCHER_SC(name);					\
-	noinline __nocfi unsigned int bpf_dispatcher_##name##_func(	\
+	noinline __bpfcall unsigned int bpf_dispatcher_##name##_func(	\
 		const void *ctx,					\
 		const struct bpf_insn *insnsi,				\
 		bpf_func_t bpf_func)					\
@@ -1273,7 +1506,8 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 void bpf_dispatcher_change_prog(struct bpf_dispatcher *d, struct bpf_prog *from,
 				struct bpf_prog *to);
 /* Called only from JIT-enabled code, so there's no need for stubs. */
-void bpf_image_ksym_add(void *data, struct bpf_ksym *ksym);
+void bpf_image_ksym_init(void *data, unsigned int size, struct bpf_ksym *ksym);
+void bpf_image_ksym_add(struct bpf_ksym *ksym);
 void bpf_image_ksym_del(struct bpf_ksym *ksym);
 void bpf_ksym_add(struct bpf_ksym *ksym);
 void bpf_ksym_del(struct bpf_ksym *ksym);
@@ -1282,19 +1516,21 @@ void bpf_jit_uncharge_modmem(u32 size);
 bool bpf_prog_has_trampoline(const struct bpf_prog *prog);
 #else
 static inline int bpf_trampoline_link_prog(struct bpf_tramp_link *link,
-					   struct bpf_trampoline *tr)
+					   struct bpf_trampoline *tr,
+					   struct bpf_prog *tgt_prog)
 {
 	return -ENOTSUPP;
 }
 static inline int bpf_trampoline_unlink_prog(struct bpf_tramp_link *link,
-					     struct bpf_trampoline *tr)
+					     struct bpf_trampoline *tr,
+					     struct bpf_prog *tgt_prog)
 {
 	return -ENOTSUPP;
 }
 static inline struct bpf_trampoline *bpf_trampoline_get(u64 key,
 							struct bpf_attach_target_info *tgt_info)
 {
-	return ERR_PTR(-EOPNOTSUPP);
+	return NULL;
 }
 static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
 #define DEFINE_BPF_DISPATCHER(name)
@@ -1317,6 +1553,8 @@ static inline bool bpf_prog_has_trampoline(const struct bpf_prog *prog)
 struct bpf_func_info_aux {
 	u16 linkage;
 	bool unreliable;
+	bool called : 1;
+	bool verified : 1;
 };
 
 enum bpf_jit_poke_reason {
@@ -1345,7 +1583,10 @@ struct bpf_jit_poke_descriptor {
 struct bpf_ctx_arg_aux {
 	u32 offset;
 	enum bpf_reg_type reg_type;
+	struct btf *btf;
 	u32 btf_id;
+	u32 ref_obj_id;
+	bool refcounted;
 };
 
 struct btf_mod_pair {
@@ -1355,6 +1596,37 @@ struct btf_mod_pair {
 
 struct bpf_kfunc_desc_tab;
 
+enum bpf_stream_id {
+	BPF_STDOUT = 1,
+	BPF_STDERR = 2,
+};
+
+struct bpf_stream_elem {
+	struct llist_node node;
+	int total_len;
+	int consumed_len;
+	char str[];
+};
+
+enum {
+	/* 100k bytes */
+	BPF_STREAM_MAX_CAPACITY = 100000ULL,
+};
+
+struct bpf_stream {
+	atomic_t capacity;
+	struct llist_head log;	/* list of in-flight stream elements in LIFO order */
+
+	struct mutex lock;  /* lock protecting backlog_{head,tail} */
+	struct llist_node *backlog_head; /* list of in-flight stream elements in FIFO order */
+	struct llist_node *backlog_tail; /* tail of the list above */
+};
+
+struct bpf_stream_stage {
+	struct llist_head log;
+	int len;
+};
+
 struct bpf_prog_aux {
 	atomic64_t refcnt;
 	u32 used_map_cnt;
@@ -1365,13 +1637,17 @@ struct bpf_prog_aux {
 	u32 stack_depth;
 	u32 id;
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
+	u32 real_func_cnt; /* includes hidden progs, only used for JIT and freeing progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+	u32 attach_st_ops_member_off;
 	u32 ctx_arg_info_size;
 	u32 max_rdonly_access;
 	u32 max_rdwr_access;
+	u32 subprog_start;
 	struct btf *attach_btf;
-	const struct bpf_ctx_arg_aux *ctx_arg_info;
+	struct bpf_ctx_arg_aux *ctx_arg_info;
+	void __percpu *priv_stack_ptr;
 	struct mutex dst_mutex; /* protects dst_* pointers below, *after* prog becomes visible */
 	struct bpf_prog *dst_prog;
 	struct bpf_trampoline *dst_trampoline;
@@ -1381,22 +1657,39 @@ struct bpf_prog_aux {
 	bool dev_bound; /* Program is bound to the netdev. */
 	bool offload_requested; /* Program is bound and offloaded to the netdev. */
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool attach_tracing_prog; /* true if tracing another tracing program */
 	bool func_proto_unreliable;
-	bool sleepable;
 	bool tail_call_reachable;
 	bool xdp_has_frags;
+	bool exception_cb;
+	bool exception_boundary;
+	bool is_extended; /* true if extended by freplace program */
+	bool jits_use_priv_stack;
+	bool priv_stack_requested;
+	bool changes_pkt_data;
+	bool might_sleep;
+	bool kprobe_write_ctx;
+	u64 prog_array_member_cnt; /* counts how many times as member of prog_array */
+	struct mutex ext_mutex; /* mutex for is_extended and prog_array_member_cnt */
+	struct bpf_arena *arena;
+	void (*recursion_detected)(struct bpf_prog *prog); /* callback if recursion is detected */
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
 	const char *attach_func_name;
 	struct bpf_prog **func;
+	struct bpf_prog_aux *main_prog_aux;
 	void *jit_data; /* JIT specific data. arch dependent */
 	struct bpf_jit_poke_descriptor *poke_tab;
 	struct bpf_kfunc_desc_tab *kfunc_tab;
 	struct bpf_kfunc_btf_tab *kfunc_btf_tab;
 	u32 size_poke_tab;
+#ifdef CONFIG_FINEIBT
+	struct bpf_ksym ksym_prefix;
+#endif
 	struct bpf_ksym ksym;
 	const struct bpf_prog_ops *ops;
+	const struct bpf_struct_ops *st_ops;
 	struct bpf_map **used_maps;
 	struct mutex used_maps_mutex; /* mutex for used_maps and used_map_cnt */
 	struct btf_mod_pair *used_btfs;
@@ -1407,9 +1700,11 @@ struct bpf_prog_aux {
 	int cgroup_atype; /* enum cgroup_bpf_attach_type */
 	struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
 	char name[BPF_OBJ_NAME_LEN];
+	u64 (*bpf_exception_cb)(u64 cookie, u64 sp, u64 bp, u64, u64);
 #ifdef CONFIG_SECURITY
 	void *security;
 #endif
+	struct bpf_token *token;
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
@@ -1443,6 +1738,7 @@ struct bpf_prog_aux {
 		struct work_struct work;
 		struct rcu_head	rcu;
 	};
+	struct bpf_stream stream[2];
 };
 
 struct bpf_prog {
@@ -1460,12 +1756,16 @@ struct bpf_prog {
 				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
 				call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
 				call_get_func_ip:1, /* Do we call get_func_ip() */
-				tstamp_type_access:1; /* Accessed __sk_buff->tstamp_type */
+				tstamp_type_access:1, /* Accessed __sk_buff->tstamp_type */
+				sleepable:1;	/* BPF program is sleepable */
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	enum bpf_attach_type	expected_attach_type; /* For some prog types */
 	u32			len;		/* Number of filter blocks */
 	u32			jited_len;	/* Size of jited insns in bytes */
-	u8			tag[BPF_TAG_SIZE];
+	union {
+		u8 digest[SHA256_DIGEST_SIZE];
+		u8 tag[BPF_TAG_SIZE];
+	};
 	struct bpf_prog_stats __percpu *stats;
 	int __percpu		*active;
 	unsigned int		(*bpf_func)(const void *ctx,
@@ -1493,12 +1793,37 @@ struct bpf_link {
 	enum bpf_link_type type;
 	const struct bpf_link_ops *ops;
 	struct bpf_prog *prog;
-	struct work_struct work;
+
+	u32 flags;
+	enum bpf_attach_type attach_type;
+
+	/* rcu is used before freeing, work can be used to schedule that
+	 * RCU-based freeing before that, so they never overlap
+	 */
+	union {
+		struct rcu_head rcu;
+		struct work_struct work;
+	};
+	/* whether BPF link itself has "sleepable" semantics, which can differ
+	 * from underlying BPF program having a "sleepable" semantics, as BPF
+	 * link's semantics is determined by target attach hook
+	 */
+	bool sleepable;
 };
 
 struct bpf_link_ops {
 	void (*release)(struct bpf_link *link);
+	/* deallocate link resources callback, called without RCU grace period
+	 * waiting
+	 */
 	void (*dealloc)(struct bpf_link *link);
+	/* deallocate link resources callback, called after RCU grace period;
+	 * if either the underlying BPF program is sleepable or BPF link's
+	 * target hook is sleepable, we'll go through tasks trace RCU GP and
+	 * then "classic" RCU GP; this need for chaining tasks trace and
+	 * classic RCU GPs is designated by setting bpf_link->sleepable flag
+	 */
+	void (*dealloc_deferred)(struct bpf_link *link);
 	int (*detach)(struct bpf_link *link);
 	int (*update_prog)(struct bpf_link *link, struct bpf_prog *new_prog,
 			   struct bpf_prog *old_prog);
@@ -1507,6 +1832,7 @@ struct bpf_link_ops {
 			      struct bpf_link_info *info);
 	int (*update_map)(struct bpf_link *link, struct bpf_map *new_map,
 			  struct bpf_map *old_map);
+	__poll_t (*poll)(struct file *file, struct poll_table_struct *pts);
 };
 
 struct bpf_tramp_link {
@@ -1522,11 +1848,16 @@ struct bpf_shim_tramp_link {
 
 struct bpf_tracing_link {
 	struct bpf_tramp_link link;
-	enum bpf_attach_type attach_type;
 	struct bpf_trampoline *trampoline;
 	struct bpf_prog *tgt_prog;
 };
 
+struct bpf_raw_tp_link {
+	struct bpf_link link;
+	struct bpf_raw_event_map *btp;
+	u64 cookie;
+};
+
 struct bpf_link_primer {
 	struct bpf_link *link;
 	struct file *file;
@@ -1534,10 +1865,84 @@ struct bpf_link_primer {
 	u32 id;
 };
 
+struct bpf_mount_opts {
+	kuid_t uid;
+	kgid_t gid;
+	umode_t mode;
+
+	/* BPF token-related delegation options */
+	u64 delegate_cmds;
+	u64 delegate_maps;
+	u64 delegate_progs;
+	u64 delegate_attachs;
+};
+
+struct bpf_token {
+	struct work_struct work;
+	atomic64_t refcnt;
+	struct user_namespace *userns;
+	u64 allowed_cmds;
+	u64 allowed_maps;
+	u64 allowed_progs;
+	u64 allowed_attachs;
+#ifdef CONFIG_SECURITY
+	void *security;
+#endif
+};
+
 struct bpf_struct_ops_value;
 struct btf_member;
 
 #define BPF_STRUCT_OPS_MAX_NR_MEMBERS 64
+/**
+ * struct bpf_struct_ops - A structure of callbacks allowing a subsystem to
+ *			   define a BPF_MAP_TYPE_STRUCT_OPS map type composed
+ *			   of BPF_PROG_TYPE_STRUCT_OPS progs.
+ * @verifier_ops: A structure of callbacks that are invoked by the verifier
+ *		  when determining whether the struct_ops progs in the
+ *		  struct_ops map are valid.
+ * @init: A callback that is invoked a single time, and before any other
+ *	  callback, to initialize the structure. A nonzero return value means
+ *	  the subsystem could not be initialized.
+ * @check_member: When defined, a callback invoked by the verifier to allow
+ *		  the subsystem to determine if an entry in the struct_ops map
+ *		  is valid. A nonzero return value means that the map is
+ *		  invalid and should be rejected by the verifier.
+ * @init_member: A callback that is invoked for each member of the struct_ops
+ *		 map to allow the subsystem to initialize the member. A nonzero
+ *		 value means the member could not be initialized. This callback
+ *		 is exclusive with the @type, @type_id, @value_type, and
+ *		 @value_id fields.
+ * @reg: A callback that is invoked when the struct_ops map has been
+ *	 initialized and is being attached to. Zero means the struct_ops map
+ *	 has been successfully registered and is live. A nonzero return value
+ *	 means the struct_ops map could not be registered.
+ * @unreg: A callback that is invoked when the struct_ops map should be
+ *	   unregistered.
+ * @update: A callback that is invoked when the live struct_ops map is being
+ *	    updated to contain new values. This callback is only invoked when
+ *	    the struct_ops map is loaded with BPF_F_LINK. If not defined, the
+ *	    it is assumed that the struct_ops map cannot be updated.
+ * @validate: A callback that is invoked after all of the members have been
+ *	      initialized. This callback should perform static checks on the
+ *	      map, meaning that it should either fail or succeed
+ *	      deterministically. A struct_ops map that has been validated may
+ *	      not necessarily succeed in being registered if the call to @reg
+ *	      fails. For example, a valid struct_ops map may be loaded, but
+ *	      then fail to be registered due to there being another active
+ *	      struct_ops map on the system in the subsystem already. For this
+ *	      reason, if this callback is not defined, the check is skipped as
+ *	      the struct_ops map will have final verification performed in
+ *	      @reg.
+ * @cfi_stubs: Pointer to a structure of stub functions for CFI. These stubs
+ *	       provide the correct Control Flow Integrity hashes for the
+ *	       trampolines generated by BPF struct_ops.
+ * @owner: The module that owns this struct_ops. Used for module reference
+ *	   counting to ensure the module providing the struct_ops cannot be
+ *	   unloaded while in use.
+ * @name: The name of the struct bpf_struct_ops object.
+ * @func_models: Func models
+ */
 struct bpf_struct_ops {
 	const struct bpf_verifier_ops *verifier_ops;
 	int (*init)(struct btf *btf);
@@ -1547,30 +1952,80 @@ struct bpf_struct_ops {
 	int (*init_member)(const struct btf_type *t,
 			   const struct btf_member *member,
 			   void *kdata, const void *udata);
-	int (*reg)(void *kdata);
-	void (*unreg)(void *kdata);
-	int (*update)(void *kdata, void *old_kdata);
+	int (*reg)(void *kdata, struct bpf_link *link);
+	void (*unreg)(void *kdata, struct bpf_link *link);
+	int (*update)(void *kdata, void *old_kdata, struct bpf_link *link);
 	int (*validate)(void *kdata);
-	const struct btf_type *type;
-	const struct btf_type *value_type;
+	void *cfi_stubs;
+	struct module *owner;
 	const char *name;
 	struct btf_func_model func_models[BPF_STRUCT_OPS_MAX_NR_MEMBERS];
+};
+
+/* Every member of a struct_ops type has an instance even a member is not
+ * an operator (function pointer). The "info" field will be assigned to
+ * prog->aux->ctx_arg_info of BPF struct_ops programs to provide the
+ * argument information required by the verifier to verify the program.
+ *
+ * btf_ctx_access() will lookup prog->aux->ctx_arg_info to find the
+ * corresponding entry for an given argument.
+ */
+struct bpf_struct_ops_arg_info {
+	struct bpf_ctx_arg_aux *info;
+	u32 cnt;
+};
+
+struct bpf_struct_ops_desc {
+	struct bpf_struct_ops *st_ops;
+
+	const struct btf_type *type;
+	const struct btf_type *value_type;
 	u32 type_id;
 	u32 value_id;
+
+	/* Collection of argument information for each member */
+	struct bpf_struct_ops_arg_info *arg_info;
+};
+
+enum bpf_struct_ops_state {
+	BPF_STRUCT_OPS_STATE_INIT,
+	BPF_STRUCT_OPS_STATE_INUSE,
+	BPF_STRUCT_OPS_STATE_TOBEFREE,
+	BPF_STRUCT_OPS_STATE_READY,
+};
+
+struct bpf_struct_ops_common_value {
+	refcount_t refcnt;
+	enum bpf_struct_ops_state state;
 };
 
 #if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
+/* This macro helps developer to register a struct_ops type and generate
+ * type information correctly. Developers should use this macro to register
+ * a struct_ops type instead of calling __register_bpf_struct_ops() directly.
+ */
+#define register_bpf_struct_ops(st_ops, type)				\
+	({								\
+		struct bpf_struct_ops_##type {				\
+			struct bpf_struct_ops_common_value common;	\
+			struct type data ____cacheline_aligned_in_smp;	\
+		};							\
+		BTF_TYPE_EMIT(struct bpf_struct_ops_##type);		\
+		__register_bpf_struct_ops(st_ops);			\
+	})
 #define BPF_MODULE_OWNER ((void *)((0xeB9FUL << 2) + POISON_POINTER_DELTA))
-const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id);
-void bpf_struct_ops_init(struct btf *btf, struct bpf_verifier_log *log);
 bool bpf_struct_ops_get(const void *kdata);
 void bpf_struct_ops_put(const void *kdata);
+int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff);
 int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map, void *key,
 				       void *value);
 int bpf_struct_ops_prepare_trampoline(struct bpf_tramp_links *tlinks,
 				      struct bpf_tramp_link *link,
 				      const struct btf_func_model *model,
-				      void *image, void *image_end);
+				      void *stub_func,
+				      void **image, u32 *image_off,
+				      bool allow_alloc);
+void bpf_struct_ops_image_free(void *image);
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
 {
 	if (owner == BPF_MODULE_OWNER)
@@ -1586,6 +2041,7 @@ static inline void bpf_module_put(const void *data, struct module *owner)
 		module_put(owner);
 }
 int bpf_struct_ops_link_create(union bpf_attr *attr);
+u32 bpf_struct_ops_id(const void *kdata);
 
 #ifdef CONFIG_NET
 /* Define it here to avoid the use of forward declaration */
@@ -1603,15 +2059,13 @@ struct bpf_dummy_ops {
 int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 			    union bpf_attr __user *uattr);
 #endif
+int bpf_struct_ops_desc_init(struct bpf_struct_ops_desc *st_ops_desc,
+			     struct btf *btf,
+			     struct bpf_verifier_log *log);
+void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map);
+void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc);
 #else
-static inline const struct bpf_struct_ops *bpf_struct_ops_find(u32 type_id)
-{
-	return NULL;
-}
-static inline void bpf_struct_ops_init(struct btf *btf,
-				       struct bpf_verifier_log *log)
-{
-}
+#define register_bpf_struct_ops(st_ops, type) ({ (void *)(st_ops); 0; })
 static inline bool bpf_try_module_get(const void *data, struct module *owner)
 {
 	return try_module_get(owner);
@@ -1620,6 +2074,10 @@ static inline void bpf_module_put(const void *data, struct module *owner)
 {
 	module_put(owner);
 }
+static inline int bpf_struct_ops_supported(const struct bpf_struct_ops *st_ops, u32 moff)
+{
+	return -ENOTSUPP;
+}
 static inline int bpf_struct_ops_map_sys_lookup_elem(struct bpf_map *map,
 						     void *key,
 						     void *value)
@@ -1630,16 +2088,28 @@ static inline int bpf_struct_ops_link_create(union bpf_attr *attr)
 {
 	return -EOPNOTSUPP;
 }
+static inline void bpf_map_struct_ops_info_fill(struct bpf_map_info *info, struct bpf_map *map)
+{
+}
+
+static inline void bpf_struct_ops_desc_release(struct bpf_struct_ops_desc *st_ops_desc)
+{
+}
 
 #endif
 
+int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
+			       const struct bpf_ctx_arg_aux *info, u32 cnt);
+
 #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM)
 int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
-				    int cgroup_atype);
+				    int cgroup_atype,
+				    enum bpf_attach_type attach_type);
 void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog);
 #else
 static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
-						  int cgroup_atype)
+						  int cgroup_atype,
+						  enum bpf_attach_type attach_type)
 {
 	return -EOPNOTSUPP;
 }
@@ -1660,6 +2130,12 @@ struct bpf_array {
 	};
 };
 
+/*
+ * The bpf_array_get_next_key() function may be used for all array-like
+ * maps, i.e., maps with u32 keys with range [0 ,..., max_entries)
+ */
+int bpf_array_get_next_key(struct bpf_map *map, void *key, void *next_key);
+
 #define BPF_COMPLEXITY_LIMIT_INSNS      1000000 /* yes. 1M insns */
 #define MAX_TAIL_CALL_CNT 33
 
@@ -1668,6 +2144,7 @@ struct bpf_array {
  */
 enum {
 	BPF_MAX_LOOPS = 8 * 1024 * 1024,
+	BPF_MAX_TIMED_LOOPS = 0xffff,
 };
 
 #define BPF_F_ACCESS_MASK	(BPF_F_RDONLY |		\
@@ -1704,6 +2181,16 @@ static inline bool bpf_map_flags_access_ok(u32 access_flags)
 	       (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
 }
 
+static inline struct bpf_map_owner *bpf_map_owner_alloc(struct bpf_map *map)
+{
+	return kzalloc(sizeof(*map->owner), GFP_ATOMIC);
+}
+
+static inline void bpf_map_owner_free(struct bpf_map *map)
+{
+	kfree(map->owner);
+}
+
 struct bpf_event_entry {
 	struct perf_event *event;
 	struct file *perf_file;
@@ -1724,6 +2211,8 @@ int bpf_prog_calc_tag(struct bpf_prog *fp);
 const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
 const struct bpf_func_proto *bpf_get_trace_vprintk_proto(void);
 
+const struct bpf_func_proto *bpf_get_perf_event_read_value_proto(void);
+
 typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
 					unsigned long off, unsigned long len);
 typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type,
@@ -1807,6 +2296,7 @@ struct bpf_cg_run_ctx {
 struct bpf_trace_run_ctx {
 	struct bpf_run_ctx run_ctx;
 	u64 bpf_cookie;
+	bool is_uprobe;
 };
 
 struct bpf_tramp_run_ctx {
@@ -1855,6 +2345,8 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
 	if (unlikely(!array))
 		return ret;
 
+	run_ctx.is_uprobe = false;
+
 	migrate_disable();
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
@@ -1879,44 +2371,49 @@ bpf_prog_run_array(const struct bpf_prog_array *array,
  * rcu-protected dynamically sized maps.
  */
 static __always_inline u32
-bpf_prog_run_array_sleepable(const struct bpf_prog_array __rcu *array_rcu,
-			     const void *ctx, bpf_prog_run_fn run_prog)
+bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
+			  const void *ctx, bpf_prog_run_fn run_prog)
 {
 	const struct bpf_prog_array_item *item;
 	const struct bpf_prog *prog;
-	const struct bpf_prog_array *array;
 	struct bpf_run_ctx *old_run_ctx;
 	struct bpf_trace_run_ctx run_ctx;
 	u32 ret = 1;
 
 	might_fault();
+	RCU_LOCKDEP_WARN(!rcu_read_lock_trace_held(), "no rcu lock held");
+
+	if (unlikely(!array))
+		return ret;
 
-	rcu_read_lock_trace();
 	migrate_disable();
 
-	array = rcu_dereference_check(array_rcu, rcu_read_lock_trace_held());
-	if (unlikely(!array))
-		goto out;
+	run_ctx.is_uprobe = true;
+
 	old_run_ctx = bpf_set_run_ctx(&run_ctx.run_ctx);
 	item = &array->items[0];
 	while ((prog = READ_ONCE(item->prog))) {
-		if (!prog->aux->sleepable)
+		if (!prog->sleepable)
 			rcu_read_lock();
 
 		run_ctx.bpf_cookie = item->bpf_cookie;
 		ret &= run_prog(prog, ctx);
 		item++;
 
-		if (!prog->aux->sleepable)
+		if (!prog->sleepable)
 			rcu_read_unlock();
 	}
 	bpf_reset_run_ctx(old_run_ctx);
-out:
 	migrate_enable();
-	rcu_read_unlock_trace();
 	return ret;
 }
 
+bool bpf_jit_bypass_spec_v1(void);
+bool bpf_jit_bypass_spec_v4(void);
+
+#define bpf_rcu_lock_held() \
+	(rcu_read_lock_held() || rcu_read_lock_trace_held() || rcu_read_lock_bh_held())
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 extern struct mutex bpf_stats_enabled_mutex;
@@ -1939,9 +2436,11 @@ static inline void bpf_enable_instrumentation(void)
 	migrate_enable();
 }
 
+extern const struct super_operations bpf_super_ops;
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 extern const struct file_operations bpf_iter_fops;
+extern const struct file_operations bpf_token_fops;
 
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	extern const struct bpf_prog_ops _name ## _prog_ops; \
@@ -1977,11 +2476,40 @@ void bpf_map_free_record(struct bpf_map *map);
 struct btf_record *btf_record_dup(const struct btf_record *rec);
 bool btf_record_equal(const struct btf_record *rec_a, const struct btf_record *rec_b);
 void bpf_obj_free_timer(const struct btf_record *rec, void *obj);
+void bpf_obj_free_workqueue(const struct btf_record *rec, void *obj);
+void bpf_obj_free_task_work(const struct btf_record *rec, void *obj);
 void bpf_obj_free_fields(const struct btf_record *rec, void *obj);
+void __bpf_obj_drop_impl(void *p, const struct btf_record *rec, bool percpu);
 
 struct bpf_map *bpf_map_get(u32 ufd);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
-struct bpf_map *__bpf_map_get(struct fd f);
+
+/*
+ * The __bpf_map_get() and __btf_get_by_fd() functions parse a file
+ * descriptor and return a corresponding map or btf object.
+ * Their names are double underscored to emphasize the fact that they
+ * do not increase refcnt. To also increase refcnt use corresponding
+ * bpf_map_get() and btf_get_by_fd() functions.
+ */
+
+static inline struct bpf_map *__bpf_map_get(struct fd f)
+{
+	if (fd_empty(f))
+		return ERR_PTR(-EBADF);
+	if (unlikely(fd_file(f)->f_op != &bpf_map_fops))
+		return ERR_PTR(-EINVAL);
+	return fd_file(f)->private_data;
+}
+
+static inline struct btf *__btf_get_by_fd(struct fd f)
+{
+	if (fd_empty(f))
+		return ERR_PTR(-EBADF);
+	if (unlikely(fd_file(f)->f_op != &btf_fops))
+		return ERR_PTR(-EINVAL);
+	return fd_file(f)->private_data;
+}
+
 void bpf_map_inc(struct bpf_map *map);
 void bpf_map_inc_with_uref(struct bpf_map *map);
 struct bpf_map *__bpf_map_inc_not_zero(struct bpf_map *map, bool uref);
@@ -2005,81 +2533,130 @@ int  generic_map_delete_batch(struct bpf_map *map,
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
-#ifdef CONFIG_MEMCG_KMEM
+
+int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
+			unsigned long nr_pages, struct page **page_array);
+#ifdef CONFIG_MEMCG
 void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
 			   int node);
+void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags,
+			     int node);
 void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags);
 void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size,
 		       gfp_t flags);
 void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size,
 				    size_t align, gfp_t flags);
 #else
-static inline void *
-bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
-		     int node)
+/*
+ * These specialized allocators have to be macros for their allocations to be
+ * accounted separately (to have separate alloc_tag).
+ */
+#define bpf_map_kmalloc_node(_map, _size, _flags, _node)	\
+		kmalloc_node(_size, _flags, _node)
+#define bpf_map_kmalloc_nolock(_map, _size, _flags, _node)	\
+		kmalloc_nolock(_size, _flags, _node)
+#define bpf_map_kzalloc(_map, _size, _flags)			\
+		kzalloc(_size, _flags)
+#define bpf_map_kvcalloc(_map, _n, _size, _flags)		\
+		kvcalloc(_n, _size, _flags)
+#define bpf_map_alloc_percpu(_map, _size, _align, _flags)	\
+		__alloc_percpu_gfp(_size, _align, _flags)
+#endif
+
+static inline int
+bpf_map_init_elem_count(struct bpf_map *map)
 {
-	return kmalloc_node(size, flags, node);
+	size_t size = sizeof(*map->elem_count), align = size;
+	gfp_t flags = GFP_USER | __GFP_NOWARN;
+
+	map->elem_count = bpf_map_alloc_percpu(map, size, align, flags);
+	if (!map->elem_count)
+		return -ENOMEM;
+
+	return 0;
 }
 
-static inline void *
-bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags)
+static inline void
+bpf_map_free_elem_count(struct bpf_map *map)
 {
-	return kzalloc(size, flags);
+	free_percpu(map->elem_count);
 }
 
-static inline void *
-bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags)
+static inline void bpf_map_inc_elem_count(struct bpf_map *map)
 {
-	return kvcalloc(n, size, flags);
+	this_cpu_inc(*map->elem_count);
 }
 
-static inline void __percpu *
-bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, size_t align,
-		     gfp_t flags)
+static inline void bpf_map_dec_elem_count(struct bpf_map *map)
 {
-	return __alloc_percpu_gfp(size, align, flags);
+	this_cpu_dec(*map->elem_count);
 }
-#endif
 
 extern int sysctl_unprivileged_bpf_disabled;
 
-static inline bool bpf_allow_ptr_leaks(void)
+bool bpf_token_capable(const struct bpf_token *token, int cap);
+
+static inline bool bpf_allow_ptr_leaks(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_allow_uninit_stack(void)
+static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_bypass_spec_v1(void)
+static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_jit_bypass_spec_v1() ||
+		cpu_mitigations_off() ||
+		bpf_token_capable(token, CAP_PERFMON);
 }
 
-static inline bool bpf_bypass_spec_v4(void)
+static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
 {
-	return perfmon_capable();
+	return bpf_jit_bypass_spec_v4() ||
+		cpu_mitigations_off() ||
+		bpf_token_capable(token, CAP_PERFMON);
 }
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
-		   const struct bpf_link_ops *ops, struct bpf_prog *prog);
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog,
+		   enum bpf_attach_type attach_type);
+void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
+			     const struct bpf_link_ops *ops, struct bpf_prog *prog,
+			     enum bpf_attach_type attach_type, bool sleepable);
 int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
 int bpf_link_settle(struct bpf_link_primer *primer);
 void bpf_link_cleanup(struct bpf_link_primer *primer);
 void bpf_link_inc(struct bpf_link *link);
+struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link);
 void bpf_link_put(struct bpf_link *link);
 int bpf_link_new_fd(struct bpf_link *link);
-struct file *bpf_link_new_file(struct bpf_link *link, int *reserved_fd);
 struct bpf_link *bpf_link_get_from_fd(u32 ufd);
 struct bpf_link *bpf_link_get_curr_or_next(u32 *id);
 
-int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
-int bpf_obj_get_user(const char __user *pathname, int flags);
+void bpf_token_inc(struct bpf_token *token);
+void bpf_token_put(struct bpf_token *token);
+int bpf_token_create(union bpf_attr *attr);
+struct bpf_token *bpf_token_get_from_fd(u32 ufd);
+int bpf_token_get_info_by_fd(struct bpf_token *token,
+			     const union bpf_attr *attr,
+			     union bpf_attr __user *uattr);
+
+bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
+bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type);
+bool bpf_token_allow_prog_type(const struct bpf_token *token,
+			       enum bpf_prog_type prog_type,
+			       enum bpf_attach_type attach_type);
+
+int bpf_obj_pin_user(u32 ufd, int path_fd, const char __user *pathname);
+int bpf_obj_get_user(int path_fd, const char __user *pathname, int flags);
+struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir,
+			    umode_t mode);
 
 #define BPF_ITER_FUNC_PREFIX "bpf_iter_"
 #define DEFINE_BPF_ITER_FUNC(target, args...)			\
@@ -2167,7 +2744,7 @@ struct bpf_iter__bpf_map_elem {
 
 int bpf_iter_reg_target(const struct bpf_iter_reg *reg_info);
 void bpf_iter_unreg_target(const struct bpf_iter_reg *reg_info);
-bool bpf_iter_prog_supported(struct bpf_prog *prog);
+int bpf_iter_prog_supported(struct bpf_prog *prog);
 const struct bpf_func_proto *
 bpf_iter_get_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog);
 int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr, struct bpf_prog *prog);
@@ -2191,7 +2768,7 @@ int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
 int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
 			    u64 flags);
 
-int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
+int bpf_stackmap_extract(struct bpf_map *map, void *key, void *value, bool delete);
 
 int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
 				 void *key, void *value, u64 map_flags);
@@ -2219,7 +2796,7 @@ struct sk_buff;
 struct bpf_dtab_netdev;
 struct bpf_cpu_map_entry;
 
-void __dev_flush(void);
+void __dev_flush(struct list_head *flush_list);
 int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx);
 int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
@@ -2227,12 +2804,12 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf,
 int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx,
 			  struct bpf_map *map, bool exclude_ingress);
 int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
-			     struct bpf_prog *xdp_prog);
+			     const struct bpf_prog *xdp_prog);
 int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
-			   struct bpf_prog *xdp_prog, struct bpf_map *map,
-			   bool exclude_ingress);
+			   const struct bpf_prog *xdp_prog,
+			   struct bpf_map *map, bool exclude_ingress);
 
-void __cpu_map_flush(void);
+void __cpu_map_flush(struct list_head *flush_list);
 int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf,
 		    struct net_device *dev_rx);
 int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
@@ -2309,19 +2886,19 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
 			   struct btf_func_model *m);
 
 struct bpf_reg_state;
-int btf_check_subprog_arg_match(struct bpf_verifier_env *env, int subprog,
-				struct bpf_reg_state *regs);
-int btf_check_subprog_call(struct bpf_verifier_env *env, int subprog,
-			   struct bpf_reg_state *regs);
-int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog,
-			  struct bpf_reg_state *reg);
+int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog);
 int btf_check_type_match(struct bpf_verifier_log *log, const struct bpf_prog *prog,
 			 struct btf *btf, const struct btf_type *t);
+const char *btf_find_decl_tag_value(const struct btf *btf, const struct btf_type *pt,
+				    int comp_idx, const char *tag_key);
+int btf_find_next_decl_tag(const struct btf *btf, const struct btf_type *pt,
+			   int comp_idx, const char *tag_key, int last_id);
 
 struct bpf_prog *bpf_prog_by_id(u32 id);
 struct bpf_link *bpf_link_by_id(u32 id);
 
-const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id);
+const struct bpf_func_proto *bpf_base_func_proto(enum bpf_func_id func_id,
+						 const struct bpf_prog *prog);
 void bpf_task_storage_free(struct task_struct *task);
 void bpf_cgrp_storage_free(struct cgroup *cgroup);
 bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
@@ -2368,6 +2945,8 @@ void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
 		     enum bpf_dynptr_type type, u32 offset, u32 size);
 void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
 void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr);
+void bpf_prog_report_arena_violation(bool write, unsigned long addr, unsigned long fault_ip);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
@@ -2405,7 +2984,13 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog)
 
 static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 				 const struct bpf_link_ops *ops,
-				 struct bpf_prog *prog)
+				 struct bpf_prog *prog, enum bpf_attach_type attach_type)
+{
+}
+
+static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
+					   const struct bpf_link_ops *ops, struct bpf_prog *prog,
+					   enum bpf_attach_type attach_type, bool sleepable)
 {
 }
 
@@ -2428,6 +3013,11 @@ static inline void bpf_link_inc(struct bpf_link *link)
 {
 }
 
+static inline struct bpf_link *bpf_link_inc_not_zero(struct bpf_link *link)
+{
+	return NULL;
+}
+
 static inline void bpf_link_put(struct bpf_link *link)
 {
 }
@@ -2437,7 +3027,32 @@ static inline int bpf_obj_get_user(const char __user *pathname, int flags)
 	return -EOPNOTSUPP;
 }
 
-static inline void __dev_flush(void)
+static inline bool bpf_token_capable(const struct bpf_token *token, int cap)
+{
+	return capable(cap) || (cap != CAP_SYS_ADMIN && capable(CAP_SYS_ADMIN));
+}
+
+static inline void bpf_token_inc(struct bpf_token *token)
+{
+}
+
+static inline void bpf_token_put(struct bpf_token *token)
+{
+}
+
+static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline int bpf_token_get_info_by_fd(struct bpf_token *token,
+					   const union bpf_attr *attr,
+					   union bpf_attr __user *uattr)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void __dev_flush(struct list_head *flush_list)
 {
 }
 
@@ -2470,20 +3085,20 @@ struct sk_buff;
 
 static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
 					   struct sk_buff *skb,
-					   struct bpf_prog *xdp_prog)
+					   const struct bpf_prog *xdp_prog)
 {
 	return 0;
 }
 
 static inline
 int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
-			   struct bpf_prog *xdp_prog, struct bpf_map *map,
-			   bool exclude_ingress)
+			   const struct bpf_prog *xdp_prog,
+			   struct bpf_map *map, bool exclude_ingress)
 {
 	return 0;
 }
 
-static inline void __cpu_map_flush(void)
+static inline void __cpu_map_flush(struct list_head *flush_list)
 {
 }
 
@@ -2560,7 +3175,7 @@ static inline int btf_struct_access(struct bpf_verifier_log *log,
 }
 
 static inline const struct bpf_func_proto *
-bpf_base_func_proto(enum bpf_func_id func_id)
+bpf_base_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
 	return NULL;
 }
@@ -2618,10 +3233,26 @@ static inline void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
 static inline void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
 {
 }
+
+static inline void bpf_prog_report_arena_violation(bool write, unsigned long addr,
+						   unsigned long fault_ip)
+{
+}
 #endif /* CONFIG_BPF_SYSCALL */
 
-void __bpf_free_used_btfs(struct bpf_prog_aux *aux,
-			  struct btf_mod_pair *used_btfs, u32 len);
+static __always_inline int
+bpf_probe_read_kernel_common(void *dst, u32 size, const void *unsafe_ptr)
+{
+	int ret = -EFAULT;
+
+	if (IS_ENABLED(CONFIG_BPF_EVENTS))
+		ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
+	if (unlikely(ret < 0))
+		memset(dst, 0, size);
+	return ret;
+}
+
+void __bpf_free_used_btfs(struct btf_mod_pair *used_btfs, u32 len);
 
 static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
 						 enum bpf_prog_type type)
@@ -2699,6 +3330,7 @@ int sock_map_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype);
 int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, u64 flags);
 int sock_map_bpf_prog_query(const union bpf_attr *attr,
 			    union bpf_attr __user *uattr);
+int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog);
 
 void sock_map_unhash(struct sock *sk);
 void sock_map_destroy(struct sock *sk);
@@ -2797,9 +3429,30 @@ static inline int sock_map_bpf_prog_query(const union bpf_attr *attr,
 {
 	return -EINVAL;
 }
+
+static inline int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
 
+static __always_inline void
+bpf_prog_inc_misses_counters(const struct bpf_prog_array *array)
+{
+	const struct bpf_prog_array_item *item;
+	struct bpf_prog *prog;
+
+	if (unlikely(!array))
+		return;
+
+	item = &array->items[0];
+	while ((prog = READ_ONCE(item->prog))) {
+		bpf_prog_inc_misses_counter(prog);
+		item++;
+	}
+}
+
 #if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
 void bpf_sk_reuseport_detach(struct sock *sk);
 int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
@@ -2827,6 +3480,38 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
 #endif /* CONFIG_BPF_SYSCALL */
 #endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
 
+#if defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL)
+
+struct bpf_key *bpf_lookup_user_key(s32 serial, u64 flags);
+struct bpf_key *bpf_lookup_system_key(u64 id);
+void bpf_key_put(struct bpf_key *bkey);
+int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p,
+			       struct bpf_dynptr *sig_p,
+			       struct bpf_key *trusted_keyring);
+
+#else
+static inline struct bpf_key *bpf_lookup_user_key(u32 serial, u64 flags)
+{
+	return NULL;
+}
+
+static inline struct bpf_key *bpf_lookup_system_key(u64 id)
+{
+	return NULL;
+}
+
+static inline void bpf_key_put(struct bpf_key *bkey)
+{
+}
+
+static inline int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_p,
+					     struct bpf_dynptr *sig_p,
+					     struct bpf_key *trusted_keyring)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* defined(CONFIG_KEYS) && defined(CONFIG_BPF_SYSCALL) */
+
 /* verifier prototypes for helper functions called from eBPF programs */
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
@@ -2848,7 +3533,9 @@ extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
 extern const struct bpf_func_proto bpf_get_current_comm_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto;
 extern const struct bpf_func_proto bpf_get_stack_proto;
+extern const struct bpf_func_proto bpf_get_stack_sleepable_proto;
 extern const struct bpf_func_proto bpf_get_task_stack_proto;
+extern const struct bpf_func_proto bpf_get_task_stack_sleepable_proto;
 extern const struct bpf_func_proto bpf_get_stackid_proto_pe;
 extern const struct bpf_func_proto bpf_get_stack_proto_pe;
 extern const struct bpf_func_proto bpf_sock_map_update_proto;
@@ -2856,6 +3543,7 @@ extern const struct bpf_func_proto bpf_sock_hash_update_proto;
 extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
 extern const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto;
 extern const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto;
+extern const struct bpf_func_proto bpf_current_task_under_cgroup_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
 extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
 extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
@@ -2930,8 +3618,8 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 				struct bpf_insn *insn_buf,
 				struct bpf_prog *prog,
 				u32 *target_size);
-int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
-			       struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+			       struct bpf_dynptr *ptr);
 #else
 static inline bool bpf_sock_common_is_valid_access(int off, int size,
 						   enum bpf_access_type type,
@@ -2953,8 +3641,8 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 {
 	return 0;
 }
-static inline int bpf_dynptr_from_skb_rdonly(struct sk_buff *skb, u64 flags,
-					     struct bpf_dynptr_kern *ptr)
+static inline int bpf_dynptr_from_skb_rdonly(struct __sk_buff *skb, u64 flags,
+					     struct bpf_dynptr *ptr)
 {
 	return -EOPNOTSUPP;
 }
@@ -3022,12 +3710,17 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
 #endif /* CONFIG_INET */
 
 enum bpf_text_poke_type {
+	BPF_MOD_NOP,
 	BPF_MOD_CALL,
 	BPF_MOD_JUMP,
 };
 
-int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
-		       void *addr1, void *addr2);
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type old_t,
+		       enum bpf_text_poke_type new_t, void *old_addr,
+		       void *new_addr);
+
+void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
+			       struct bpf_prog *new, struct bpf_prog *old);
 
 void *bpf_arch_text_copy(void *dst, void *src, size_t len);
 int bpf_arch_text_invalidate(void *dst, size_t len);
@@ -3038,6 +3731,16 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 #define MAX_BPRINTF_VARARGS		12
 #define MAX_BPRINTF_BUF			1024
 
+/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
+ * arguments representation.
+ */
+#define MAX_BPRINTF_BIN_ARGS	512
+
+struct bpf_bprintf_buffers {
+	char bin_args[MAX_BPRINTF_BIN_ARGS];
+	char buf[MAX_BPRINTF_BUF];
+};
+
 struct bpf_bprintf_data {
 	u32 *bin_args;
 	char *buf;
@@ -3045,9 +3748,33 @@ struct bpf_bprintf_data {
 	bool get_buf;
 };
 
-int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 num_args, struct bpf_bprintf_data *data);
 void bpf_bprintf_cleanup(struct bpf_bprintf_data *data);
+int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs);
+void bpf_put_buffers(void);
+
+void bpf_prog_stream_init(struct bpf_prog *prog);
+void bpf_prog_stream_free(struct bpf_prog *prog);
+int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len);
+void bpf_stream_stage_init(struct bpf_stream_stage *ss);
+void bpf_stream_stage_free(struct bpf_stream_stage *ss);
+__printf(2, 3)
+int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...);
+int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog,
+			    enum bpf_stream_id stream_id);
+int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss);
+
+#define bpf_stream_printk(ss, ...) bpf_stream_stage_printk(&ss, __VA_ARGS__)
+#define bpf_stream_dump_stack(ss) bpf_stream_stage_dump_stack(&ss)
+
+#define bpf_stream_stage(ss, prog, stream_id, expr)            \
+	({                                                     \
+		bpf_stream_stage_init(&ss);                    \
+		(expr);                                        \
+		bpf_stream_stage_commit(&ss, prog, stream_id); \
+		bpf_stream_stage_free(&ss);                    \
+	})
 
 #ifdef CONFIG_BPF_LSM
 void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype);
@@ -3078,4 +3805,39 @@ static inline gfp_t bpf_memcg_flags(gfp_t flags)
 	return flags;
 }
 
+static inline bool bpf_is_subprog(const struct bpf_prog *prog)
+{
+	return prog->aux->func_idx != 0;
+}
+
+int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep,
+			   const char **linep, int *nump);
+struct bpf_prog *bpf_prog_find_from_stack(void);
+
+int bpf_insn_array_init(struct bpf_map *map, const struct bpf_prog *prog);
+int bpf_insn_array_ready(struct bpf_map *map);
+void bpf_insn_array_release(struct bpf_map *map);
+void bpf_insn_array_adjust(struct bpf_map *map, u32 off, u32 len);
+void bpf_insn_array_adjust_after_remove(struct bpf_map *map, u32 off, u32 len);
+
+#ifdef CONFIG_BPF_SYSCALL
+void bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image);
+#else
+static inline void
+bpf_prog_update_insn_ptrs(struct bpf_prog *prog, u32 *offsets, void *image)
+{
+}
+#endif
+
+static inline int bpf_map_check_op_flags(struct bpf_map *map, u64 flags, u64 allowed_flags)
+{
+	if (flags & ~allowed_flags)
+		return -EINVAL;
+
+	if ((flags & BPF_F_LOCK) && !btf_record_has_field(map->record, BPF_SPIN_LOCK))
+		return -EINVAL;
+
+	return 0;
+}
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_crypto.h b/include/linux/bpf_crypto.h
new file mode 100644
index 000000000000..a41e71d4e2d9
--- /dev/null
+++ b/include/linux/bpf_crypto.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
+#ifndef _BPF_CRYPTO_H
+#define _BPF_CRYPTO_H
+
+struct bpf_crypto_type {
+	void *(*alloc_tfm)(const char *algo);
+	void (*free_tfm)(void *tfm);
+	int (*has_algo)(const char *algo);
+	int (*setkey)(void *tfm, const u8 *key, unsigned int keylen);
+	int (*setauthsize)(void *tfm, unsigned int authsize);
+	int (*encrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv);
+	int (*decrypt)(void *tfm, const u8 *src, u8 *dst, unsigned int len, u8 *iv);
+	unsigned int (*ivsize)(void *tfm);
+	unsigned int (*statesize)(void *tfm);
+	u32 (*get_flags)(void *tfm);
+	struct module *owner;
+	char name[14];
+};
+
+int bpf_crypto_register_type(const struct bpf_crypto_type *type);
+int bpf_crypto_unregister_type(const struct bpf_crypto_type *type);
+
+#endif /* _BPF_CRYPTO_H */
diff --git a/include/linux/bpf_local_storage.h b/include/linux/bpf_local_storage.h
index 173ec7f43ed1..66432248cd81 100644
--- a/include/linux/bpf_local_storage.h
+++ b/include/linux/bpf_local_storage.h
@@ -18,9 +18,6 @@
 
 #define BPF_LOCAL_STORAGE_CACHE_SIZE	16
 
-#define bpf_rcu_lock_held()                                                    \
-	(rcu_read_lock_held() || rcu_read_lock_trace_held() ||                 \
-	 rcu_read_lock_bh_held())
 struct bpf_local_storage_map_bucket {
 	struct hlist_head list;
 	raw_spinlock_t lock;
@@ -56,9 +53,7 @@ struct bpf_local_storage_map {
 	u32 bucket_log;
 	u16 elem_size;
 	u16 cache_idx;
-	struct bpf_mem_alloc selem_ma;
-	struct bpf_mem_alloc storage_ma;
-	bool bpf_ma;
+	bool use_kmalloc_nolock;
 };
 
 struct bpf_local_storage_data {
@@ -77,7 +72,13 @@ struct bpf_local_storage_elem {
 	struct hlist_node map_node;	/* Linked to bpf_local_storage_map */
 	struct hlist_node snode;	/* Linked to bpf_local_storage */
 	struct bpf_local_storage __rcu *local_storage;
-	struct rcu_head rcu;
+	union {
+		struct rcu_head rcu;
+		struct hlist_node free_node;	/* used to postpone
+						 * bpf_selem_free
+						 * after raw_spin_unlock
+						 */
+	};
 	/* 8 bytes hole */
 	/* The data is stored in another cacheline to minimize
 	 * the number of cachelines access during a cache hit.
@@ -94,6 +95,7 @@ struct bpf_local_storage {
 				 */
 	struct rcu_head rcu;
 	raw_spinlock_t lock;	/* Protect adding/removing from the "list" */
+	bool use_kmalloc_nolock;
 };
 
 /* U16_MAX is much more than enough for sk local storage
@@ -127,12 +129,38 @@ int bpf_local_storage_map_alloc_check(union bpf_attr *attr);
 struct bpf_map *
 bpf_local_storage_map_alloc(union bpf_attr *attr,
 			    struct bpf_local_storage_cache *cache,
-			    bool bpf_ma);
+			    bool use_kmalloc_nolock);
 
-struct bpf_local_storage_data *
+void __bpf_local_storage_insert_cache(struct bpf_local_storage *local_storage,
+				      struct bpf_local_storage_map *smap,
+				      struct bpf_local_storage_elem *selem);
+/* If cacheit_lockit is false, this lookup function is lockless */
+static inline struct bpf_local_storage_data *
 bpf_local_storage_lookup(struct bpf_local_storage *local_storage,
 			 struct bpf_local_storage_map *smap,
-			 bool cacheit_lockit);
+			 bool cacheit_lockit)
+{
+	struct bpf_local_storage_data *sdata;
+	struct bpf_local_storage_elem *selem;
+
+	/* Fast path (cache hit) */
+	sdata = rcu_dereference_check(local_storage->cache[smap->cache_idx],
+				      bpf_rcu_lock_held());
+	if (sdata && rcu_access_pointer(sdata->smap) == smap)
+		return sdata;
+
+	/* Slow path (cache miss) */
+	hlist_for_each_entry_rcu(selem, &local_storage->list, snode,
+				  rcu_read_lock_trace_held())
+		if (rcu_access_pointer(SDATA(selem)->smap) == smap)
+			break;
+
+	if (!selem)
+		return NULL;
+	if (cacheit_lockit)
+		__bpf_local_storage_insert_cache(local_storage, smap, selem);
+	return SDATA(selem);
+}
 
 void bpf_local_storage_destroy(struct bpf_local_storage *local_storage);
 
@@ -155,10 +183,9 @@ void bpf_selem_link_map(struct bpf_local_storage_map *smap,
 
 struct bpf_local_storage_elem *
 bpf_selem_alloc(struct bpf_local_storage_map *smap, void *owner, void *value,
-		bool charge_mem, gfp_t gfp_flags);
+		bool swap_uptrs, gfp_t gfp_flags);
 
 void bpf_selem_free(struct bpf_local_storage_elem *selem,
-		    struct bpf_local_storage_map *smap,
 		    bool reuse_now);
 
 int
@@ -169,7 +196,7 @@ bpf_local_storage_alloc(void *owner,
 
 struct bpf_local_storage_data *
 bpf_local_storage_update(void *owner, struct bpf_local_storage_map *smap,
-			 void *value, u64 map_flags, gfp_t gfp_flags);
+			 void *value, u64 map_flags, bool swap_uptrs, gfp_t gfp_flags);
 
 u64 bpf_local_storage_map_mem_usage(const struct bpf_map *map);
 
diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
index 1de7ece5d36d..643809cc78c3 100644
--- a/include/linux/bpf_lsm.h
+++ b/include/linux/bpf_lsm.h
@@ -9,6 +9,7 @@
 
 #include <linux/sched.h>
 #include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
 #include <linux/lsm_hooks.h>
 
 #ifdef CONFIG_BPF_LSM
@@ -45,6 +46,13 @@ void bpf_inode_storage_free(struct inode *inode);
 
 void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func);
 
+int bpf_lsm_get_retval_range(const struct bpf_prog *prog,
+			     struct bpf_retval_range *range);
+int bpf_set_dentry_xattr_locked(struct dentry *dentry, const char *name__str,
+				const struct bpf_dynptr *value_p, int flags);
+int bpf_remove_dentry_xattr_locked(struct dentry *dentry, const char *name__str);
+bool bpf_lsm_has_d_inode_locked(const struct bpf_prog *prog);
+
 #else /* !CONFIG_BPF_LSM */
 
 static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
@@ -78,6 +86,24 @@ static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
 {
 }
 
+static inline int bpf_lsm_get_retval_range(const struct bpf_prog *prog,
+					   struct bpf_retval_range *range)
+{
+	return -EOPNOTSUPP;
+}
+static inline int bpf_set_dentry_xattr_locked(struct dentry *dentry, const char *name__str,
+					      const struct bpf_dynptr *value_p, int flags)
+{
+	return -EOPNOTSUPP;
+}
+static inline int bpf_remove_dentry_xattr_locked(struct dentry *dentry, const char *name__str)
+{
+	return -EOPNOTSUPP;
+}
+static inline bool bpf_lsm_has_d_inode_locked(const struct bpf_prog *prog)
+{
+	return false;
+}
 #endif /* CONFIG_BPF_LSM */
 
 #endif /* _LINUX_BPF_LSM_H */
diff --git a/include/linux/bpf_mem_alloc.h b/include/linux/bpf_mem_alloc.h
index 3929be5743f4..e45162ef59bb 100644
--- a/include/linux/bpf_mem_alloc.h
+++ b/include/linux/bpf_mem_alloc.h
@@ -11,6 +11,8 @@ struct bpf_mem_caches;
 struct bpf_mem_alloc {
 	struct bpf_mem_caches __percpu *caches;
 	struct bpf_mem_cache __percpu *cache;
+	struct obj_cgroup *objcg;
+	bool percpu;
 	struct work_struct work;
 };
 
@@ -20,17 +22,29 @@ struct bpf_mem_alloc {
  * 'size = 0' is for bpf_mem_alloc which manages many fixed-size objects.
  * Alloc and free are done with bpf_mem_{alloc,free}() and the size of
  * the returned object is given by the size argument of bpf_mem_alloc().
+ * If percpu equals true, error will be returned in order to avoid
+ * large memory consumption and the below bpf_mem_alloc_percpu_unit_init()
+ * should be used to do on-demand per-cpu allocation for each size.
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu);
+/* Initialize a non-fix-size percpu memory allocator */
+int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg);
+/* The percpu allocation with a specific unit size. */
+int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size);
 void bpf_mem_alloc_destroy(struct bpf_mem_alloc *ma);
 
+/* Check the allocation size for kmalloc equivalent allocator */
+int bpf_mem_alloc_check_size(bool percpu, size_t size);
+
 /* kmalloc/kfree equivalent: */
 void *bpf_mem_alloc(struct bpf_mem_alloc *ma, size_t size);
 void bpf_mem_free(struct bpf_mem_alloc *ma, void *ptr);
+void bpf_mem_free_rcu(struct bpf_mem_alloc *ma, void *ptr);
 
 /* kmem_cache_alloc/free equivalent: */
 void *bpf_mem_cache_alloc(struct bpf_mem_alloc *ma);
 void bpf_mem_cache_free(struct bpf_mem_alloc *ma, void *ptr);
+void bpf_mem_cache_free_rcu(struct bpf_mem_alloc *ma, void *ptr);
 void bpf_mem_cache_raw_free(void *ptr);
 void *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags);
 
diff --git a/include/linux/bpf_mprog.h b/include/linux/bpf_mprog.h
new file mode 100644
index 000000000000..929225f7b095
--- /dev/null
+++ b/include/linux/bpf_mprog.h
@@ -0,0 +1,343 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2023 Isovalent */
+#ifndef __BPF_MPROG_H
+#define __BPF_MPROG_H
+
+#include <linux/bpf.h>
+
+/* bpf_mprog framework:
+ *
+ * bpf_mprog is a generic layer for multi-program attachment. In-kernel users
+ * of the bpf_mprog don't need to care about the dependency resolution
+ * internals, they can just consume it with few API calls. Currently available
+ * dependency directives are BPF_F_{BEFORE,AFTER} which enable insertion of
+ * a BPF program or BPF link relative to an existing BPF program or BPF link
+ * inside the multi-program array as well as prepend and append behavior if
+ * no relative object was specified, see corresponding selftests for concrete
+ * examples (e.g. tc_links and tc_opts test cases of test_progs).
+ *
+ * Usage of bpf_mprog_{attach,detach,query}() core APIs with pseudo code:
+ *
+ *  Attach case:
+ *
+ *   struct bpf_mprog_entry *entry, *entry_new;
+ *   int ret;
+ *
+ *   // bpf_mprog user-side lock
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   ret = bpf_mprog_attach(entry, &entry_new, [...]);
+ *   if (!ret) {
+ *       if (entry != entry_new) {
+ *           // swap @entry to @entry_new at attach location
+ *           // ensure there are no inflight users of @entry:
+ *           synchronize_rcu();
+ *       }
+ *       bpf_mprog_commit(entry);
+ *   } else {
+ *       // error path, bail out, propagate @ret
+ *   }
+ *   // bpf_mprog user-side unlock
+ *
+ *  Detach case:
+ *
+ *   struct bpf_mprog_entry *entry, *entry_new;
+ *   int ret;
+ *
+ *   // bpf_mprog user-side lock
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   ret = bpf_mprog_detach(entry, &entry_new, [...]);
+ *   if (!ret) {
+ *       // all (*) marked is optional and depends on the use-case
+ *       // whether bpf_mprog_bundle should be freed or not
+ *       if (!bpf_mprog_total(entry_new))     (*)
+ *           entry_new = NULL                 (*)
+ *       // swap @entry to @entry_new at attach location
+ *       // ensure there are no inflight users of @entry:
+ *       synchronize_rcu();
+ *       bpf_mprog_commit(entry);
+ *       if (!entry_new)                      (*)
+ *           // free bpf_mprog_bundle         (*)
+ *   } else {
+ *       // error path, bail out, propagate @ret
+ *   }
+ *   // bpf_mprog user-side unlock
+ *
+ *  Query case:
+ *
+ *   struct bpf_mprog_entry *entry;
+ *   int ret;
+ *
+ *   // bpf_mprog user-side lock
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   ret = bpf_mprog_query(attr, uattr, entry);
+ *   // bpf_mprog user-side unlock
+ *
+ *  Data/fast path:
+ *
+ *   struct bpf_mprog_entry *entry;
+ *   struct bpf_mprog_fp *fp;
+ *   struct bpf_prog *prog;
+ *   int ret = [...];
+ *
+ *   rcu_read_lock();
+ *   // fetch active @entry from attach location
+ *   [...]
+ *   bpf_mprog_foreach_prog(entry, fp, prog) {
+ *       ret = bpf_prog_run(prog, [...]);
+ *       // process @ret from program
+ *   }
+ *   [...]
+ *   rcu_read_unlock();
+ *
+ * bpf_mprog locking considerations:
+ *
+ * bpf_mprog_{attach,detach,query}() must be protected by an external lock
+ * (like RTNL in case of tcx).
+ *
+ * bpf_mprog_entry pointer can be an __rcu annotated pointer (in case of tcx
+ * the netdevice has tcx_ingress and tcx_egress __rcu pointer) which gets
+ * updated via rcu_assign_pointer() pointing to the active bpf_mprog_entry of
+ * the bpf_mprog_bundle.
+ *
+ * Fast path accesses the active bpf_mprog_entry within RCU critical section
+ * (in case of tcx it runs in NAPI which provides RCU protection there,
+ * other users might need explicit rcu_read_lock()). The bpf_mprog_commit()
+ * assumes that for the old bpf_mprog_entry there are no inflight users
+ * anymore.
+ *
+ * The READ_ONCE()/WRITE_ONCE() pairing for bpf_mprog_fp's prog access is for
+ * the replacement case where we don't swap the bpf_mprog_entry.
+ */
+
+#define bpf_mprog_foreach_tuple(entry, fp, cp, t)			\
+	for (fp = &entry->fp_items[0], cp = &entry->parent->cp_items[0];\
+	     ({								\
+		t.prog = READ_ONCE(fp->prog);				\
+		t.link = cp->link;					\
+		t.prog;							\
+	      });							\
+	     fp++, cp++)
+
+#define bpf_mprog_foreach_prog(entry, fp, p)				\
+	for (fp = &entry->fp_items[0];					\
+	     (p = READ_ONCE(fp->prog));					\
+	     fp++)
+
+#define BPF_MPROG_MAX 64
+
+struct bpf_mprog_fp {
+	struct bpf_prog *prog;
+};
+
+struct bpf_mprog_cp {
+	struct bpf_link *link;
+};
+
+struct bpf_mprog_entry {
+	struct bpf_mprog_fp fp_items[BPF_MPROG_MAX];
+	struct bpf_mprog_bundle *parent;
+};
+
+struct bpf_mprog_bundle {
+	struct bpf_mprog_entry a;
+	struct bpf_mprog_entry b;
+	struct bpf_mprog_cp cp_items[BPF_MPROG_MAX];
+	struct bpf_prog *ref;
+	atomic64_t revision;
+	u32 count;
+};
+
+struct bpf_tuple {
+	struct bpf_prog *prog;
+	struct bpf_link *link;
+};
+
+static inline struct bpf_mprog_entry *
+bpf_mprog_peer(const struct bpf_mprog_entry *entry)
+{
+	if (entry == &entry->parent->a)
+		return &entry->parent->b;
+	else
+		return &entry->parent->a;
+}
+
+static inline void bpf_mprog_bundle_init(struct bpf_mprog_bundle *bundle)
+{
+	BUILD_BUG_ON(sizeof(bundle->a.fp_items[0]) > sizeof(u64));
+	BUILD_BUG_ON(ARRAY_SIZE(bundle->a.fp_items) !=
+		     ARRAY_SIZE(bundle->cp_items));
+
+	memset(bundle, 0, sizeof(*bundle));
+	atomic64_set(&bundle->revision, 1);
+	bundle->a.parent = bundle;
+	bundle->b.parent = bundle;
+}
+
+static inline void bpf_mprog_inc(struct bpf_mprog_entry *entry)
+{
+	entry->parent->count++;
+}
+
+static inline void bpf_mprog_dec(struct bpf_mprog_entry *entry)
+{
+	entry->parent->count--;
+}
+
+static inline int bpf_mprog_max(void)
+{
+	return ARRAY_SIZE(((struct bpf_mprog_entry *)NULL)->fp_items) - 1;
+}
+
+static inline int bpf_mprog_total(struct bpf_mprog_entry *entry)
+{
+	int total = entry->parent->count;
+
+	WARN_ON_ONCE(total > bpf_mprog_max());
+	return total;
+}
+
+static inline bool bpf_mprog_exists(struct bpf_mprog_entry *entry,
+				    struct bpf_prog *prog)
+{
+	const struct bpf_mprog_fp *fp;
+	const struct bpf_prog *tmp;
+
+	bpf_mprog_foreach_prog(entry, fp, tmp) {
+		if (tmp == prog)
+			return true;
+	}
+	return false;
+}
+
+static inline void bpf_mprog_mark_for_release(struct bpf_mprog_entry *entry,
+					      struct bpf_tuple *tuple)
+{
+	WARN_ON_ONCE(entry->parent->ref);
+	if (!tuple->link)
+		entry->parent->ref = tuple->prog;
+}
+
+static inline void bpf_mprog_complete_release(struct bpf_mprog_entry *entry)
+{
+	/* In the non-link case prog deletions can only drop the reference
+	 * to the prog after the bpf_mprog_entry got swapped and the
+	 * bpf_mprog ensured that there are no inflight users anymore.
+	 *
+	 * Paired with bpf_mprog_mark_for_release().
+	 */
+	if (entry->parent->ref) {
+		bpf_prog_put(entry->parent->ref);
+		entry->parent->ref = NULL;
+	}
+}
+
+static inline void bpf_mprog_revision_new(struct bpf_mprog_entry *entry)
+{
+	atomic64_inc(&entry->parent->revision);
+}
+
+static inline void bpf_mprog_commit(struct bpf_mprog_entry *entry)
+{
+	bpf_mprog_complete_release(entry);
+	bpf_mprog_revision_new(entry);
+}
+
+static inline u64 bpf_mprog_revision(struct bpf_mprog_entry *entry)
+{
+	return atomic64_read(&entry->parent->revision);
+}
+
+static inline void bpf_mprog_entry_copy(struct bpf_mprog_entry *dst,
+					struct bpf_mprog_entry *src)
+{
+	memcpy(dst->fp_items, src->fp_items, sizeof(src->fp_items));
+}
+
+static inline void bpf_mprog_entry_clear(struct bpf_mprog_entry *dst)
+{
+	memset(dst->fp_items, 0, sizeof(dst->fp_items));
+}
+
+static inline void bpf_mprog_clear_all(struct bpf_mprog_entry *entry,
+				       struct bpf_mprog_entry **entry_new)
+{
+	struct bpf_mprog_entry *peer;
+
+	peer = bpf_mprog_peer(entry);
+	bpf_mprog_entry_clear(peer);
+	peer->parent->count = 0;
+	*entry_new = peer;
+}
+
+static inline void bpf_mprog_entry_grow(struct bpf_mprog_entry *entry, int idx)
+{
+	int total = bpf_mprog_total(entry);
+
+	memmove(entry->fp_items + idx + 1,
+		entry->fp_items + idx,
+		(total - idx) * sizeof(struct bpf_mprog_fp));
+
+	memmove(entry->parent->cp_items + idx + 1,
+		entry->parent->cp_items + idx,
+		(total - idx) * sizeof(struct bpf_mprog_cp));
+}
+
+static inline void bpf_mprog_entry_shrink(struct bpf_mprog_entry *entry, int idx)
+{
+	/* Total array size is needed in this case to enure the NULL
+	 * entry is copied at the end.
+	 */
+	int total = ARRAY_SIZE(entry->fp_items);
+
+	memmove(entry->fp_items + idx,
+		entry->fp_items + idx + 1,
+		(total - idx - 1) * sizeof(struct bpf_mprog_fp));
+
+	memmove(entry->parent->cp_items + idx,
+		entry->parent->cp_items + idx + 1,
+		(total - idx - 1) * sizeof(struct bpf_mprog_cp));
+}
+
+static inline void bpf_mprog_read(struct bpf_mprog_entry *entry, u32 idx,
+				  struct bpf_mprog_fp **fp,
+				  struct bpf_mprog_cp **cp)
+{
+	*fp = &entry->fp_items[idx];
+	*cp = &entry->parent->cp_items[idx];
+}
+
+static inline void bpf_mprog_write(struct bpf_mprog_fp *fp,
+				   struct bpf_mprog_cp *cp,
+				   struct bpf_tuple *tuple)
+{
+	WRITE_ONCE(fp->prog, tuple->prog);
+	cp->link = tuple->link;
+}
+
+int bpf_mprog_attach(struct bpf_mprog_entry *entry,
+		     struct bpf_mprog_entry **entry_new,
+		     struct bpf_prog *prog_new, struct bpf_link *link,
+		     struct bpf_prog *prog_old,
+		     u32 flags, u32 id_or_fd, u64 revision);
+
+int bpf_mprog_detach(struct bpf_mprog_entry *entry,
+		     struct bpf_mprog_entry **entry_new,
+		     struct bpf_prog *prog, struct bpf_link *link,
+		     u32 flags, u32 id_or_fd, u64 revision);
+
+int bpf_mprog_query(const union bpf_attr *attr, union bpf_attr __user *uattr,
+		    struct bpf_mprog_entry *entry);
+
+static inline bool bpf_mprog_supported(enum bpf_prog_type type)
+{
+	switch (type) {
+	case BPF_PROG_TYPE_SCHED_CLS:
+		return true;
+	default:
+		return false;
+	}
+}
+#endif /* __BPF_MPROG_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index fc0d6f32c687..b13de31e163f 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -132,6 +132,8 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_ARENA, arena_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_INSN_ARRAY, insn_array_map_ops)
 
 BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)
@@ -142,9 +144,14 @@ BPF_LINK_TYPE(BPF_LINK_TYPE_ITER, iter)
 #ifdef CONFIG_NET
 BPF_LINK_TYPE(BPF_LINK_TYPE_NETNS, netns)
 BPF_LINK_TYPE(BPF_LINK_TYPE_XDP, xdp)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETFILTER, netfilter)
+BPF_LINK_TYPE(BPF_LINK_TYPE_TCX, tcx)
+BPF_LINK_TYPE(BPF_LINK_TYPE_NETKIT, netkit)
+BPF_LINK_TYPE(BPF_LINK_TYPE_SOCKMAP, sockmap)
 #endif
 #ifdef CONFIG_PERF_EVENTS
 BPF_LINK_TYPE(BPF_LINK_TYPE_PERF_EVENT, perf)
 #endif
 BPF_LINK_TYPE(BPF_LINK_TYPE_KPROBE_MULTI, kprobe_multi)
 BPF_LINK_TYPE(BPF_LINK_TYPE_STRUCT_OPS, struct_ops)
+BPF_LINK_TYPE(BPF_LINK_TYPE_UPROBE_MULTI, uprobe_multi)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3dd29a53b711..130bcbd66f60 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -18,46 +18,13 @@
  * that converting umax_value to int cannot overflow.
  */
 #define BPF_MAX_VAR_SIZ	(1 << 29)
-/* size of type_str_buf in bpf_verifier. */
-#define TYPE_STR_BUF_LEN 128
-
-/* Liveness marks, used for registers and spilled-regs (in stack slots).
- * Read marks propagate upwards until they find a write mark; they record that
- * "one of this state's descendants read this reg" (and therefore the reg is
- * relevant for states_equal() checks).
- * Write marks collect downwards and do not propagate; they record that "the
- * straight-line code that reached this state (from its parent) wrote this reg"
- * (and therefore that reads propagated from this state or its descendants
- * should not propagate to its parent).
- * A state with a write mark can receive read marks; it just won't propagate
- * them to its parent, since the write mark is a property, not of the state,
- * but of the link between it and its parent.  See mark_reg_read() and
- * mark_stack_slot_read() in kernel/bpf/verifier.c.
+/* size of tmp_str_buf in bpf_verifier.
+ * we need at least 306 bytes to fit full stack mask representation
+ * (in the "-8,-16,...,-512" form)
  */
-enum bpf_reg_liveness {
-	REG_LIVE_NONE = 0, /* reg hasn't been read or written this branch */
-	REG_LIVE_READ32 = 0x1, /* reg was read, so we're sensitive to initial value */
-	REG_LIVE_READ64 = 0x2, /* likewise, but full 64-bit content matters */
-	REG_LIVE_READ = REG_LIVE_READ32 | REG_LIVE_READ64,
-	REG_LIVE_WRITTEN = 0x4, /* reg was written first, screening off later reads */
-	REG_LIVE_DONE = 0x8, /* liveness won't be updating this register anymore */
-};
-
-/* For every reg representing a map value or allocated object pointer,
- * we consider the tuple of (ptr, id) for them to be unique in verifier
- * context and conside them to not alias each other for the purposes of
- * tracking lock state.
- */
-struct bpf_active_lock {
-	/* This can either be reg->map_ptr or reg->btf. If ptr is NULL,
-	 * there's no active lock held, and other fields have no
-	 * meaning. If non-NULL, it indicates that a lock is held and
-	 * id member has the reg->id of the register which can be >= 0.
-	 */
-	void *ptr;
-	/* This will be reg->id */
-	u32 id;
-};
+#define TMP_STR_BUF_LEN 320
+/* Patch buffer size */
+#define INSN_BUF_SIZE 32
 
 #define ITER_PREFIX "bpf_iter_"
 
@@ -70,7 +37,10 @@ enum bpf_iter_state {
 struct bpf_reg_state {
 	/* Ordering of fields matters.  See states_equal() */
 	enum bpf_reg_type type;
-	/* Fixed part of pointer offset, pointer types only */
+	/*
+	 * Fixed part of pointer offset, pointer types only.
+	 * Or constant delta between "linked" scalars with the same ID.
+	 */
 	s32 off;
 	union {
 		/* valid when type == PTR_TO_PACKET */
@@ -123,6 +93,14 @@ struct bpf_reg_state {
 			int depth:30;
 		} iter;
 
+		/* For irq stack slots */
+		struct {
+			enum {
+				IRQ_NATIVE_KFUNC,
+				IRQ_LOCK_KFUNC,
+			} kfunc_class;
+		} irq;
+
 		/* Max size from any of the above. */
 		struct {
 			unsigned long raw1;
@@ -164,6 +142,13 @@ struct bpf_reg_state {
 	 * Similarly to dynptrs, we use ID to track "belonging" of a reference
 	 * to a specific instance of bpf_iter.
 	 */
+	/*
+	 * Upper bit of ID is used to remember relationship between "linked"
+	 * registers. Example:
+	 * r1 = r2;    both will have r1->id == r2->id == N
+	 * r1 += 10;   r1->id == N | BPF_ADD_CONST and r1->off == 10
+	 */
+#define BPF_ADD_CONST (1U << 31)
 	u32 id;
 	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
 	 * from a pointer-cast helper, bpf_sk_fullsock() and
@@ -205,8 +190,6 @@ struct bpf_reg_state {
 	 * allowed and has the same effect as bpf_sk_release(sk).
 	 */
 	u32 ref_obj_id;
-	/* parentage chain for liveness checking */
-	struct bpf_reg_state *parent;
 	/* Inside the callee two registers can be both PTR_TO_STACK like
 	 * R1=fp-8 and R2=fp-8, but one of them points to this function stack
 	 * while another to the caller's stack. To differentiate them 'frameno'
@@ -219,7 +202,6 @@ struct bpf_reg_state {
 	 * patching which only happens after main verification finished.
 	 */
 	s32 subreg_def;
-	enum bpf_reg_liveness live;
 	/* if (!precise && SCALAR_VALUE) min/max/tnum don't affect safety */
 	bool precise;
 };
@@ -234,10 +216,15 @@ enum bpf_stack_slot_type {
 	 */
 	STACK_DYNPTR,
 	STACK_ITER,
+	STACK_IRQ_FLAG,
 };
 
 #define BPF_REG_SIZE 8	/* size of eBPF register in bytes */
 
+#define BPF_REGMASK_ARGS ((1 << BPF_REG_1) | (1 << BPF_REG_2) | \
+			  (1 << BPF_REG_3) | (1 << BPF_REG_4) | \
+			  (1 << BPF_REG_5))
+
 #define BPF_DYNPTR_SIZE		sizeof(struct bpf_dynptr_kern)
 #define BPF_DYNPTR_NR_SLOTS		(BPF_DYNPTR_SIZE / BPF_REG_SIZE)
 
@@ -247,6 +234,17 @@ struct bpf_stack_state {
 };
 
 struct bpf_reference_state {
+	/* Each reference object has a type. Ensure REF_TYPE_PTR is zero to
+	 * default to pointer reference on zero initialization of a state.
+	 */
+	enum ref_state_type {
+		REF_TYPE_PTR		= (1 << 1),
+		REF_TYPE_IRQ		= (1 << 2),
+		REF_TYPE_LOCK		= (1 << 3),
+		REF_TYPE_RES_LOCK 	= (1 << 4),
+		REF_TYPE_RES_LOCK_IRQ	= (1 << 5),
+		REF_TYPE_LOCK_MASK	= REF_TYPE_LOCK | REF_TYPE_RES_LOCK | REF_TYPE_RES_LOCK_IRQ,
+	} type;
 	/* Track each reference created with a unique id, even if the same
 	 * instruction creates the reference multiple times (eg, via CALL).
 	 */
@@ -255,17 +253,15 @@ struct bpf_reference_state {
 	 * is used purely to inform the user of a reference leak.
 	 */
 	int insn_idx;
-	/* There can be a case like:
-	 * main (frame 0)
-	 *  cb (frame 1)
-	 *   func (frame 3)
-	 *    cb (frame 4)
-	 * Hence for frame 4, if callback_ref just stored boolean, it would be
-	 * impossible to distinguish nested callback refs. Hence store the
-	 * frameno and compare that to callback_ref in check_reference_leak when
-	 * exiting a callback function.
-	 */
-	int callback_ref;
+	/* Use to keep track of the source object of a lock, to ensure
+	 * it matches on unlock.
+	 */
+	void *ptr;
+};
+
+struct bpf_retval_range {
+	s32 minval;
+	s32 maxval;
 };
 
 /* state of the program:
@@ -290,34 +286,81 @@ struct bpf_func_state {
 	 * void foo(void) { bpf_timer_set_callback(,foo); }
 	 */
 	u32 async_entry_cnt;
+	struct bpf_retval_range callback_ret_range;
 	bool in_callback_fn;
-	struct tnum callback_ret_range;
 	bool in_async_callback_fn;
+	bool in_exception_callback_fn;
+	/* For callback calling functions that limit number of possible
+	 * callback executions (e.g. bpf_loop) keeps track of current
+	 * simulated iteration number.
+	 * Value in frame N refers to number of times callback with frame
+	 * N+1 was simulated, e.g. for the following call:
+	 *
+	 *   bpf_loop(..., fn, ...); | suppose current frame is N
+	 *                           | fn would be simulated in frame N+1
+	 *                           | number of simulations is tracked in frame N
+	 */
+	u32 callback_depth;
 
 	/* The following fields should be last. See copy_func_state() */
-	int acquired_refs;
-	struct bpf_reference_state *refs;
-	int allocated_stack;
+	/* The state of the stack. Each element of the array describes BPF_REG_SIZE
+	 * (i.e. 8) bytes worth of stack memory.
+	 * stack[0] represents bytes [*(r10-8)..*(r10-1)]
+	 * stack[1] represents bytes [*(r10-16)..*(r10-9)]
+	 * ...
+	 * stack[allocated_stack/8 - 1] represents [*(r10-allocated_stack)..*(r10-allocated_stack+7)]
+	 */
 	struct bpf_stack_state *stack;
+	/* Size of the current stack, in bytes. The stack state is tracked below, in
+	 * `stack`. allocated_stack is always a multiple of BPF_REG_SIZE.
+	 */
+	int allocated_stack;
 };
 
-struct bpf_idx_pair {
-	u32 prev_idx;
-	u32 idx;
+#define MAX_CALL_FRAMES 8
+
+/* instruction history flags, used in bpf_jmp_history_entry.flags field */
+enum {
+	/* instruction references stack slot through PTR_TO_STACK register;
+	 * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8)
+	 * and accessed stack slot's index in next 6 bits (MAX_BPF_STACK is 512,
+	 * 8 bytes per slot, so slot index (spi) is [0, 63])
+	 */
+	INSN_F_FRAMENO_MASK = 0x7, /* 3 bits */
+
+	INSN_F_SPI_MASK = 0x3f, /* 6 bits */
+	INSN_F_SPI_SHIFT = 3, /* shifted 3 bits to the left */
+
+	INSN_F_STACK_ACCESS = BIT(9),
+
+	INSN_F_DST_REG_STACK = BIT(10), /* dst_reg is PTR_TO_STACK */
+	INSN_F_SRC_REG_STACK = BIT(11), /* src_reg is PTR_TO_STACK */
+	/* total 12 bits are used now. */
 };
 
-struct bpf_id_pair {
-	u32 old;
-	u32 cur;
+static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES);
+static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8);
+
+struct bpf_jmp_history_entry {
+	u32 idx;
+	/* insn idx can't be bigger than 1 million */
+	u32 prev_idx : 20;
+	/* special INSN_F_xxx flags */
+	u32 flags : 12;
+	/* additional registers that need precision tracking when this
+	 * jump is backtracked, vector of six 10-bit records
+	 */
+	u64 linked_regs;
 };
 
-#define MAX_CALL_FRAMES 8
 /* Maximum number of register states that can exist at once */
 #define BPF_ID_MAP_SIZE ((MAX_BPF_REG + MAX_BPF_STACK / BPF_REG_SIZE) * MAX_CALL_FRAMES)
 struct bpf_verifier_state {
 	/* call stack tracking */
 	struct bpf_func_state *frame[MAX_CALL_FRAMES];
 	struct bpf_verifier_state *parent;
+	/* Acquired reference states */
+	struct bpf_reference_state *refs;
 	/*
 	 * 'branches' field is the number of branches left to explore:
 	 * 0 - all possible paths from this state reached bpf_exit or
@@ -367,35 +410,49 @@ struct bpf_verifier_state {
 	u32 insn_idx;
 	u32 curframe;
 
-	struct bpf_active_lock active_lock;
+	u32 acquired_refs;
+	u32 active_locks;
+	u32 active_preempt_locks;
+	u32 active_irq_id;
+	u32 active_lock_id;
+	void *active_lock_ptr;
+	u32 active_rcu_locks;
+
 	bool speculative;
-	bool active_rcu_lock;
+	bool in_sleepable;
+	bool cleaned;
 
 	/* first and last insn idx of this verifier state */
 	u32 first_insn_idx;
 	u32 last_insn_idx;
+	/* if this state is a backedge state then equal_state
+	 * records cached state to which this state is equal.
+	 */
+	struct bpf_verifier_state *equal_state;
 	/* jmp history recorded from first to last.
 	 * backtracking is using it to go from last to first.
 	 * For most states jmp_history_cnt is [0-3].
 	 * For loops can go up to ~40.
 	 */
-	struct bpf_idx_pair *jmp_history;
+	struct bpf_jmp_history_entry *jmp_history;
 	u32 jmp_history_cnt;
+	u32 dfs_depth;
+	u32 callback_unroll_depth;
+	u32 may_goto_depth;
 };
 
-#define bpf_get_spilled_reg(slot, frame)				\
+#define bpf_get_spilled_reg(slot, frame, mask)				\
 	(((slot < frame->allocated_stack / BPF_REG_SIZE) &&		\
-	  (frame->stack[slot].slot_type[0] == STACK_SPILL))		\
+	  ((1 << frame->stack[slot].slot_type[BPF_REG_SIZE - 1]) & (mask))) \
 	 ? &frame->stack[slot].spilled_ptr : NULL)
 
 /* Iterate over 'frame', setting 'reg' to either NULL or a spilled register. */
-#define bpf_for_each_spilled_reg(iter, frame, reg)			\
-	for (iter = 0, reg = bpf_get_spilled_reg(iter, frame);		\
+#define bpf_for_each_spilled_reg(iter, frame, reg, mask)			\
+	for (iter = 0, reg = bpf_get_spilled_reg(iter, frame, mask);		\
 	     iter < frame->allocated_stack / BPF_REG_SIZE;		\
-	     iter++, reg = bpf_get_spilled_reg(iter, frame))
+	     iter++, reg = bpf_get_spilled_reg(iter, frame, mask))
 
-/* Invoke __expr over regsiters in __vst, setting __state and __reg */
-#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr)   \
+#define bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, __mask, __expr)   \
 	({                                                               \
 		struct bpf_verifier_state *___vstate = __vst;            \
 		int ___i, ___j;                                          \
@@ -407,7 +464,7 @@ struct bpf_verifier_state {
 				__reg = &___regs[___j];                  \
 				(void)(__expr);                          \
 			}                                                \
-			bpf_for_each_spilled_reg(___j, __state, __reg) { \
+			bpf_for_each_spilled_reg(___j, __state, __reg, __mask) { \
 				if (!__reg)                              \
 					continue;                        \
 				(void)(__expr);                          \
@@ -415,11 +472,17 @@ struct bpf_verifier_state {
 		}                                                        \
 	})
 
+/* Invoke __expr over regsiters in __vst, setting __state and __reg */
+#define bpf_for_each_reg_in_vstate(__vst, __state, __reg, __expr) \
+	bpf_for_each_reg_in_vstate_mask(__vst, __state, __reg, 1 << STACK_SPILL, __expr)
+
 /* linked list of verifier states used to prune search */
 struct bpf_verifier_state_list {
 	struct bpf_verifier_state state;
-	struct bpf_verifier_state_list *next;
-	int miss_cnt, hit_cnt;
+	struct list_head node;
+	u32 miss_cnt;
+	u32 hit_cnt:31;
+	u32 in_free_list:1;
 };
 
 struct bpf_loop_inline_state {
@@ -430,6 +493,13 @@ struct bpf_loop_inline_state {
 	u32 callback_subprogno; /* valid when fit_for_inline is true */
 };
 
+/* pointer and state for maps */
+struct bpf_map_ptr_state {
+	struct bpf_map *map_ptr;
+	bool poison;
+	bool unpriv;
+};
+
 /* Possible states for alu_state member. */
 #define BPF_ALU_SANITIZE_SRC		(1U << 0)
 #define BPF_ALU_SANITIZE_DST		(1U << 1)
@@ -439,10 +509,19 @@ struct bpf_loop_inline_state {
 #define BPF_ALU_SANITIZE		(BPF_ALU_SANITIZE_SRC | \
 					 BPF_ALU_SANITIZE_DST)
 
+/*
+ * An array of BPF instructions.
+ * Primary usage: return value of bpf_insn_successors.
+ */
+struct bpf_iarray {
+	int cnt;
+	u32 items[];
+};
+
 struct bpf_insn_aux_data {
 	union {
 		enum bpf_reg_type ptr_type;	/* pointer type for load/store insns */
-		unsigned long map_ptr_state;	/* pointer/poison value for maps */
+		struct bpf_map_ptr_state map_ptr_state;
 		s32 call_imm;			/* saved imm field of call insn */
 		u32 alu_limit;			/* limit for add/sub register with pointer */
 		struct {
@@ -470,15 +549,28 @@ struct bpf_insn_aux_data {
 		/* remember the offset of node field within type to rewrite */
 		u64 insert_off;
 	};
+	struct bpf_iarray *jt;	/* jump table for gotox or bpf_tailcall call instruction */
 	struct btf_struct_meta *kptr_struct_meta;
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
-	bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
+	bool nospec; /* do not execute this instruction speculatively */
+	bool nospec_result; /* result is unsafe under speculation, nospec must follow */
 	bool zext_dst; /* this insn zero extends dst reg */
-	bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
+	bool needs_zext; /* alu op needs to clear upper bits */
+	bool non_sleepable; /* helper/kfunc may be called from non-sleepable context */
 	bool is_iter_next; /* bpf_iter_<type>_next() kfunc call */
+	bool call_with_percpu_alloc_ptr; /* {this,per}_cpu_ptr() with prog percpu alloc */
 	u8 alu_state; /* used in combination with alu_limit */
+	/* true if STX or LDX instruction is a part of a spill/fill
+	 * pattern for a bpf_fastcall call.
+	 */
+	u8 fastcall_pattern:1;
+	/* for CALL instructions, a number of spill/fill pairs in the
+	 * bpf_fastcall pattern.
+	 */
+	u8 fastcall_spills_num:3;
+	u8 arg_prog:4;
 
 	/* below fields are initialized once */
 	unsigned int orig_idx; /* original instruction index */
@@ -488,6 +580,17 @@ struct bpf_insn_aux_data {
 	 * this instruction, regardless of any heuristics
 	 */
 	bool force_checkpoint;
+	/* true if instruction is a call to a helper function that
+	 * accepts callback function as a parameter.
+	 */
+	bool calls_callback;
+	/*
+	 * CFG strongly connected component this instruction belongs to,
+	 * zero if it is a singleton SCC.
+	 */
+	u32 scc;
+	/* registers alive before this instruction. */
+	u16 live_regs_before;
 };
 
 #define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
@@ -530,17 +633,107 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 
 #define BPF_MAX_SUBPROGS 256
 
+struct bpf_subprog_arg_info {
+	enum bpf_arg_type arg_type;
+	union {
+		u32 mem_size;
+		u32 btf_id;
+	};
+};
+
+enum priv_stack_mode {
+	PRIV_STACK_UNKNOWN,
+	NO_PRIV_STACK,
+	PRIV_STACK_ADAPTIVE,
+};
+
 struct bpf_subprog_info {
 	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
+	u32 postorder_start; /* The idx to the env->cfg.insn_postorder */
+	u32 exit_idx; /* Index of one of the BPF_EXIT instructions in this subprogram */
 	u16 stack_depth; /* max. stack depth used by this function */
-	bool has_tail_call;
-	bool tail_call_reachable;
-	bool has_ld_abs;
-	bool is_async_cb;
+	u16 stack_extra;
+	/* offsets in range [stack_depth .. fastcall_stack_off)
+	 * are used for bpf_fastcall spills and fills.
+	 */
+	s16 fastcall_stack_off;
+	bool has_tail_call: 1;
+	bool tail_call_reachable: 1;
+	bool has_ld_abs: 1;
+	bool is_cb: 1;
+	bool is_async_cb: 1;
+	bool is_exception_cb: 1;
+	bool args_cached: 1;
+	/* true if bpf_fastcall stack region is used by functions that can't be inlined */
+	bool keep_fastcall_stack: 1;
+	bool changes_pkt_data: 1;
+	bool might_sleep: 1;
+	u8 arg_cnt:3;
+
+	enum priv_stack_mode priv_stack_mode;
+	struct bpf_subprog_arg_info args[MAX_BPF_FUNC_REG_ARGS];
+};
+
+struct bpf_verifier_env;
+
+struct backtrack_state {
+	struct bpf_verifier_env *env;
+	u32 frame;
+	u32 reg_masks[MAX_CALL_FRAMES];
+	u64 stack_masks[MAX_CALL_FRAMES];
+};
+
+struct bpf_id_pair {
+	u32 old;
+	u32 cur;
+};
+
+struct bpf_idmap {
+	u32 tmp_id_gen;
+	struct bpf_id_pair map[BPF_ID_MAP_SIZE];
+};
+
+struct bpf_idset {
+	u32 count;
+	u32 ids[BPF_ID_MAP_SIZE];
 };
 
+/* see verifier.c:compute_scc_callchain() */
+struct bpf_scc_callchain {
+	/* call sites from bpf_verifier_state->frame[*]->callsite leading to this SCC */
+	u32 callsites[MAX_CALL_FRAMES - 1];
+	/* last frame in a chain is identified by SCC id */
+	u32 scc;
+};
+
+/* verifier state waiting for propagate_backedges() */
+struct bpf_scc_backedge {
+	struct bpf_scc_backedge *next;
+	struct bpf_verifier_state state;
+};
+
+struct bpf_scc_visit {
+	struct bpf_scc_callchain callchain;
+	/* first state in current verification path that entered SCC
+	 * identified by the callchain
+	 */
+	struct bpf_verifier_state *entry_state;
+	struct bpf_scc_backedge *backedges; /* list of backedges */
+	u32 num_backedges;
+};
+
+/* An array of bpf_scc_visit structs sharing tht same bpf_scc_callchain->scc
+ * but having different bpf_scc_callchain->callsites.
+ */
+struct bpf_scc_info {
+	u32 num_visits;
+	struct bpf_scc_visit visits[];
+};
+
+struct bpf_liveness;
+
 /* single container for all structs
  * one verifier_env per bpf_check() call
  */
@@ -549,35 +742,61 @@ struct bpf_verifier_env {
 	u32 prev_insn_idx;
 	struct bpf_prog *prog;		/* eBPF program being verified */
 	const struct bpf_verifier_ops *ops;
+	struct module *attach_btf_mod;	/* The owner module of prog->aux->attach_btf */
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
 	bool test_state_freq;		/* test verifier with different pruning frequency */
+	bool test_reg_invariants;	/* fail verification on register invariants violations */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
-	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
-	struct bpf_verifier_state_list *free_list;
+	/* Search pruning optimization, array of list_heads for
+	 * lists of struct bpf_verifier_state_list.
+	 */
+	struct list_head *explored_states;
+	struct list_head free_list;	/* list of struct bpf_verifier_state_list */
 	struct bpf_map *used_maps[MAX_USED_MAPS]; /* array of map's used by eBPF program */
 	struct btf_mod_pair used_btfs[MAX_USED_BTFS]; /* array of BTF's used by BPF program */
+	struct bpf_map *insn_array_maps[MAX_USED_MAPS]; /* array of INSN_ARRAY map's to be relocated */
 	u32 used_map_cnt;		/* number of used maps */
 	u32 used_btf_cnt;		/* number of used BTF objects */
+	u32 insn_array_map_cnt;		/* number of used maps of type BPF_MAP_TYPE_INSN_ARRAY */
 	u32 id_gen;			/* used to generate unique reg IDs */
+	u32 hidden_subprog_cnt;		/* number of hidden subprogs */
+	int exception_callback_subprog;
 	bool explore_alu_limits;
 	bool allow_ptr_leaks;
+	/* Allow access to uninitialized stack memory. Writes with fixed offset are
+	 * always allowed, so this refers to reads (with fixed or variable offset),
+	 * to writes with variable offset and to indirect (helper) accesses.
+	 */
 	bool allow_uninit_stack;
 	bool bpf_capable;
 	bool bypass_spec_v1;
 	bool bypass_spec_v4;
 	bool seen_direct_write;
+	bool seen_exception;
 	struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */
 	const struct bpf_line_info *prev_linfo;
 	struct bpf_verifier_log log;
-	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1];
-	struct bpf_id_pair idmap_scratch[BPF_ID_MAP_SIZE];
+	struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 2]; /* max + 2 for the fake and exception subprogs */
+	union {
+		struct bpf_idmap idmap_scratch;
+		struct bpf_idset idset_scratch;
+	};
 	struct {
 		int *insn_state;
 		int *insn_stack;
+		/*
+		 * vector of instruction indexes sorted in post-order, grouped by subprogram,
+		 * see bpf_subprog_info->postorder_start.
+		 */
+		int *insn_postorder;
 		int cur_stack;
+		/* current position in the insn_postorder vector */
+		int cur_postorder;
 	} cfg;
+	struct backtrack_state bt;
+	struct bpf_jmp_history_entry *cur_hist_ent;
 	u32 pass_cnt; /* number of times do_check() was called */
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
@@ -597,6 +816,9 @@ struct bpf_verifier_env {
 	u32 peak_states;
 	/* longest register parentage chain walked for liveness marking */
 	u32 longest_mark_read_walk;
+	u32 free_list_size;
+	u32 explored_states_size;
+	u32 num_backedges;
 	bpfptr_t fd_array;
 
 	/* bit mask to keep track of whether a register has been accessed
@@ -606,10 +828,33 @@ struct bpf_verifier_env {
 	/* Same as scratched_regs but for stack slots */
 	u64 scratched_stack_slots;
 	u64 prev_log_pos, prev_insn_print_pos;
-	/* buffer used in reg_type_str() to generate reg_type string */
-	char type_str_buf[TYPE_STR_BUF_LEN];
+	/* buffer used to temporary hold constants as scalar registers */
+	struct bpf_reg_state fake_reg[2];
+	/* buffer used to generate temporary string representations,
+	 * e.g., in reg_type_str() to generate reg_type string
+	 */
+	char tmp_str_buf[TMP_STR_BUF_LEN];
+	struct bpf_insn insn_buf[INSN_BUF_SIZE];
+	struct bpf_insn epilogue_buf[INSN_BUF_SIZE];
+	struct bpf_scc_callchain callchain_buf;
+	struct bpf_liveness *liveness;
+	/* array of pointers to bpf_scc_info indexed by SCC id */
+	struct bpf_scc_info **scc_info;
+	u32 scc_cnt;
+	struct bpf_iarray *succ;
+	struct bpf_iarray *gotox_tmp_buf;
 };
 
+static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->prog->aux->func_info_aux[subprog];
+}
+
+static inline struct bpf_subprog_info *subprog_info(struct bpf_verifier_env *env, int subprog)
+{
+	return &env->subprog_info[subprog];
+}
+
 __printf(2, 0) void bpf_verifier_vlog(struct bpf_verifier_log *log,
 				      const char *fmt, va_list args);
 __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
@@ -621,6 +866,23 @@ int bpf_vlog_init(struct bpf_verifier_log *log, u32 log_level,
 void bpf_vlog_reset(struct bpf_verifier_log *log, u64 new_pos);
 int bpf_vlog_finalize(struct bpf_verifier_log *log, u32 *log_size_actual);
 
+__printf(3, 4) void verbose_linfo(struct bpf_verifier_env *env,
+				  u32 insn_off,
+				  const char *prefix_fmt, ...);
+
+#define verifier_bug_if(cond, env, fmt, args...)						\
+	({											\
+		bool __cond = (cond);								\
+		if (unlikely(__cond))								\
+			verifier_bug(env, fmt " (" #cond ")", ##args);				\
+		(__cond);									\
+	})
+#define verifier_bug(env, fmt, args...)								\
+	({											\
+		BPF_WARN_ONCE(1, "verifier bug: " fmt "\n", ##args);				\
+		bpf_log(&env->log, "verifier bug: " fmt "\n", ##args);				\
+	})
+
 static inline struct bpf_func_state *cur_func(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state *cur = env->cur_state;
@@ -643,14 +905,6 @@ bpf_prog_offload_replace_insn(struct bpf_verifier_env *env, u32 off,
 void
 bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt);
 
-int check_ptr_off_reg(struct bpf_verifier_env *env,
-		      const struct bpf_reg_state *reg, int regno);
-int check_func_arg_reg_off(struct bpf_verifier_env *env,
-			   const struct bpf_reg_state *reg, int regno,
-			   enum bpf_arg_type arg_type);
-int check_mem_reg(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
-		   u32 regno, u32 mem_size);
-
 /* this lives here instead of in bpf.h because it needs to dereference tgt_prog */
 static inline u64 bpf_trampoline_compute_key(const struct bpf_prog *tgt_prog,
 					     struct btf *btf, u32 btf_id)
@@ -696,8 +950,8 @@ static inline u32 type_flag(u32 type)
 /* only use after check_attach_btf_id() */
 static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
 {
-	return prog->type == BPF_PROG_TYPE_EXT ?
-		prog->aux->dst_prog->type : prog->type;
+	return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ?
+		prog->aux->saved_dst_prog_type : prog->type;
 }
 
 static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
@@ -706,18 +960,131 @@ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
 	case BPF_PROG_TYPE_TRACING:
 		return prog->expected_attach_type != BPF_TRACE_ITER;
 	case BPF_PROG_TYPE_STRUCT_OPS:
+		return prog->aux->jits_use_priv_stack;
 	case BPF_PROG_TYPE_LSM:
+	case BPF_PROG_TYPE_SYSCALL:
 		return false;
 	default:
 		return true;
 	}
 }
 
-#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED)
+#define BPF_REG_TRUSTED_MODIFIERS (MEM_ALLOC | PTR_TRUSTED | NON_OWN_REF)
 
 static inline bool bpf_type_has_unsafe_modifiers(u32 type)
 {
 	return type_flag(type) & ~BPF_REG_TRUSTED_MODIFIERS;
 }
 
+static inline bool type_is_ptr_alloc_obj(u32 type)
+{
+	return base_type(type) == PTR_TO_BTF_ID && type_flag(type) & MEM_ALLOC;
+}
+
+static inline bool type_is_non_owning_ref(u32 type)
+{
+	return type_is_ptr_alloc_obj(type) && type_flag(type) & NON_OWN_REF;
+}
+
+static inline bool type_is_pkt_pointer(enum bpf_reg_type type)
+{
+	type = base_type(type);
+	return type == PTR_TO_PACKET ||
+	       type == PTR_TO_PACKET_META;
+}
+
+static inline bool type_is_sk_pointer(enum bpf_reg_type type)
+{
+	return type == PTR_TO_SOCKET ||
+		type == PTR_TO_SOCK_COMMON ||
+		type == PTR_TO_TCP_SOCK ||
+		type == PTR_TO_XDP_SOCK;
+}
+
+static inline bool type_may_be_null(u32 type)
+{
+	return type & PTR_MAYBE_NULL;
+}
+
+static inline void mark_reg_scratched(struct bpf_verifier_env *env, u32 regno)
+{
+	env->scratched_regs |= 1U << regno;
+}
+
+static inline void mark_stack_slot_scratched(struct bpf_verifier_env *env, u32 spi)
+{
+	env->scratched_stack_slots |= 1ULL << spi;
+}
+
+static inline bool reg_scratched(const struct bpf_verifier_env *env, u32 regno)
+{
+	return (env->scratched_regs >> regno) & 1;
+}
+
+static inline bool stack_slot_scratched(const struct bpf_verifier_env *env, u64 regno)
+{
+	return (env->scratched_stack_slots >> regno) & 1;
+}
+
+static inline bool verifier_state_scratched(const struct bpf_verifier_env *env)
+{
+	return env->scratched_regs || env->scratched_stack_slots;
+}
+
+static inline void mark_verifier_state_clean(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = 0U;
+	env->scratched_stack_slots = 0ULL;
+}
+
+/* Used for printing the entire verifier state. */
+static inline void mark_verifier_state_scratched(struct bpf_verifier_env *env)
+{
+	env->scratched_regs = ~0U;
+	env->scratched_stack_slots = ~0ULL;
+}
+
+static inline bool bpf_stack_narrow_access_ok(int off, int fill_size, int spill_size)
+{
+#ifdef __BIG_ENDIAN
+	off -= spill_size - fill_size;
+#endif
+
+	return !(off % BPF_REG_SIZE);
+}
+
+static inline bool insn_is_gotox(struct bpf_insn *insn)
+{
+	return BPF_CLASS(insn->code) == BPF_JMP &&
+	       BPF_OP(insn->code) == BPF_JA &&
+	       BPF_SRC(insn->code) == BPF_X;
+}
+
+const char *reg_type_str(struct bpf_verifier_env *env, enum bpf_reg_type type);
+const char *dynptr_type_str(enum bpf_dynptr_type type);
+const char *iter_type_str(const struct btf *btf, u32 btf_id);
+const char *iter_state_str(enum bpf_iter_state state);
+
+void print_verifier_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate,
+			  u32 frameno, bool print_all);
+void print_insn_state(struct bpf_verifier_env *env, const struct bpf_verifier_state *vstate,
+		      u32 frameno);
+
+struct bpf_subprog_info *bpf_find_containing_subprog(struct bpf_verifier_env *env, int off);
+int bpf_jmp_offset(struct bpf_insn *insn);
+struct bpf_iarray *bpf_insn_successors(struct bpf_verifier_env *env, u32 idx);
+void bpf_fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask);
+bool bpf_calls_callback(struct bpf_verifier_env *env, int insn_idx);
+
+int bpf_stack_liveness_init(struct bpf_verifier_env *env);
+void bpf_stack_liveness_free(struct bpf_verifier_env *env);
+int bpf_update_live_stack(struct bpf_verifier_env *env);
+int bpf_mark_stack_read(struct bpf_verifier_env *env, u32 frameno, u32 insn_idx, u64 mask);
+void bpf_mark_stack_write(struct bpf_verifier_env *env, u32 frameno, u64 mask);
+int bpf_reset_stack_write_marks(struct bpf_verifier_env *env, u32 insn_idx);
+int bpf_commit_stack_write_marks(struct bpf_verifier_env *env);
+int bpf_live_stack_query_init(struct bpf_verifier_env *env, struct bpf_verifier_state *st);
+bool bpf_stack_slot_alive(struct bpf_verifier_env *env, u32 frameno, u32 spi);
+void bpf_reset_live_stack_callchain(struct bpf_verifier_env *env);
+
 #endif /* _LINUX_BPF_VERIFIER_H */
diff --git a/include/linux/bpfilter.h b/include/linux/bpfilter.h
deleted file mode 100644
index 2ae3c8e1d83c..000000000000
--- a/include/linux/bpfilter.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_BPFILTER_H
-#define _LINUX_BPFILTER_H
-
-#include <uapi/linux/bpfilter.h>
-#include <linux/usermode_driver.h>
-#include <linux/sockptr.h>
-
-struct sock;
-int bpfilter_ip_set_sockopt(struct sock *sk, int optname, sockptr_t optval,
-			    unsigned int optlen);
-int bpfilter_ip_get_sockopt(struct sock *sk, int optname, char __user *optval,
-			    int __user *optlen);
-void bpfilter_umh_cleanup(struct umd_info *info);
-
-struct bpfilter_umh_ops {
-	struct umd_info info;
-	/* since ip_getsockopt() can run in parallel, serialize access to umh */
-	struct mutex lock;
-	int (*sockopt)(struct sock *sk, int optname, sockptr_t optval,
-		       unsigned int optlen, bool is_set);
-	int (*start)(void);
-};
-extern struct bpfilter_umh_ops bpfilter_ops;
-#endif
diff --git a/include/linux/bpfptr.h b/include/linux/bpfptr.h
index 79b2f78eec1a..f6e0795db484 100644
--- a/include/linux/bpfptr.h
+++ b/include/linux/bpfptr.h
@@ -65,9 +65,9 @@ static inline int copy_to_bpfptr_offset(bpfptr_t dst, size_t offset,
 	return copy_to_sockptr_offset((sockptr_t) dst, offset, src, size);
 }
 
-static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len)
+static inline void *kvmemdup_bpfptr_noprof(bpfptr_t src, size_t len)
 {
-	void *p = kvmalloc(len, GFP_USER | __GFP_NOWARN);
+	void *p = kvmalloc_node_align_noprof(len, 1, GFP_USER | __GFP_NOWARN, NUMA_NO_NODE);
 
 	if (!p)
 		return ERR_PTR(-ENOMEM);
@@ -77,6 +77,7 @@ static inline void *kvmemdup_bpfptr(bpfptr_t src, size_t len)
 	}
 	return p;
 }
+#define kvmemdup_bpfptr(...)	alloc_hooks(kvmemdup_bpfptr_noprof(__VA_ARGS__))
 
 static inline long strncpy_from_bpfptr(char *dst, bpfptr_t src, size_t count)
 {
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 9e77165f3ef6..115a964f3006 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -11,6 +11,7 @@
 
 #define PHY_ID_BCM50610			0x0143bd60
 #define PHY_ID_BCM50610M		0x0143bd70
+#define PHY_ID_BCM5221			0x004061e0
 #define PHY_ID_BCM5241			0x0143bc30
 #define PHY_ID_BCMAC131			0x0143bc70
 #define PHY_ID_BCM5481			0x0143bca0
@@ -44,6 +45,7 @@
 #define PHY_ID_BCM7366			0x600d8490
 #define PHY_ID_BCM7346			0x600d8650
 #define PHY_ID_BCM7362			0x600d84b0
+#define PHY_ID_BCM74165			0x359052c0
 #define PHY_ID_BCM7425			0x600d86b0
 #define PHY_ID_BCM7429			0x600d8730
 #define PHY_ID_BCM7435			0x600d8750
@@ -89,6 +91,7 @@
 #define MII_BCM54XX_EXP_SEL	0x17	/* Expansion register select */
 #define MII_BCM54XX_EXP_SEL_TOP	0x0d00	/* TOP_MISC expansion register select */
 #define MII_BCM54XX_EXP_SEL_SSD	0x0e00	/* Secondary SerDes select */
+#define MII_BCM54XX_EXP_SEL_WOL	0x0e00	/* Wake-on-LAN expansion select register */
 #define MII_BCM54XX_EXP_SEL_ER	0x0f00	/* Expansion register select */
 #define MII_BCM54XX_EXP_SEL_ETC	0x0d00	/* Expansion register spare + 2k mem */
 
@@ -134,6 +137,7 @@
 
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC			0x07
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN	0x0010
+#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RSVD		0x0060
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_EN	0x0080
 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN	0x0100
 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX		0x0200
@@ -160,6 +164,7 @@
 #define BCM_LED_SRC_OPENSHORT	0xb
 #define BCM_LED_SRC_OFF		0xe	/* Tied high */
 #define BCM_LED_SRC_ON		0xf	/* Tied low */
+#define BCM_LED_SRC_MASK	GENMASK(3, 0)
 
 /*
  * Broadcom Multicolor LED configurations (expansion register 4)
@@ -179,6 +184,12 @@
 #define BCM_LED_MULTICOLOR_PROGRAM	0xa
 
 /*
+ * Broadcom Synchronous Ethernet Controls (expansion register 0x0E)
+ */
+#define BCM_EXP_SYNC_ETHERNET		(MII_BCM54XX_EXP_SEL_ER + 0x0E)
+#define BCM_EXP_SYNC_ETHERNET_MII_LITE	BIT(11)
+
+/*
  * BCM5482: Shadow registers
  * Shadow values go into bits [14:10] of register 0x1c to select a shadow
  * register to access.
@@ -205,11 +216,13 @@
 #define  BCM_NO_ANEG_APD_EN		0x0060 /* bits 5 & 6 */
 #define  BCM_APD_SINGLELP_EN	0x0100 /* Bit 8 */
 
-#define BCM5482_SHD_LEDS1	0x0d	/* 01101: LED Selector 1 */
+#define BCM54XX_SHD_LEDS1	0x0d	/* 01101: LED Selector 1 */
 					/* LED3 / ~LINKSPD[2] selector */
-#define BCM5482_SHD_LEDS1_LED3(src)	((src & 0xf) << 4)
+#define BCM54XX_SHD_LEDS_SHIFT(led)	(4 * (led))
+#define BCM54XX_SHD_LEDS1_LED3(src)	((src & 0xf) << 4)
 					/* LED1 / ~LINKSPD[1] selector */
-#define BCM5482_SHD_LEDS1_LED1(src)	((src & 0xf) << 0)
+#define BCM54XX_SHD_LEDS1_LED1(src)	((src & 0xf) << 0)
+#define BCM54XX_SHD_LEDS2	0x0e	/* 01110: LED Selector 2 */
 #define BCM54XX_SHD_RGMII_MODE	0x0b	/* 01011: RGMII Mode Selector */
 #define BCM5482_SHD_SSD		0x14	/* 10100: Secondary SerDes control */
 #define BCM5482_SHD_SSD_LEDM	0x0008	/* SSD LED Mode enable */
@@ -253,6 +266,9 @@
 #define BCM54XX_TOP_MISC_IDDQ_SD		(1 << 2)
 #define BCM54XX_TOP_MISC_IDDQ_SR		(1 << 3)
 
+#define BCM54XX_TOP_MISC_LED_CTL		(MII_BCM54XX_EXP_SEL_TOP + 0x0C)
+#define  BCM54XX_LED4_SEL_INTR			BIT(1)
+
 /*
  * BCM5482: Secondary SerDes registers
  */
@@ -262,16 +278,164 @@
 #define BCM5482_SSD_SGMII_SLAVE_EN	0x0002	/* Slave mode enable */
 #define BCM5482_SSD_SGMII_SLAVE_AD	0x0001	/* Slave auto-detection */
 
+/* BroadR-Reach LRE Registers. */
+#define MII_BCM54XX_LRECR		0x00	/* LRE Control Register                    */
+#define MII_BCM54XX_LRESR		0x01	/* LRE Status Register                     */
+#define MII_BCM54XX_LREPHYSID1		0x02	/* LRE PHYS ID 1                           */
+#define MII_BCM54XX_LREPHYSID2		0x03	/* LRE PHYS ID 2                           */
+#define MII_BCM54XX_LREANAA		0x04	/* LDS Auto-Negotiation Advertised Ability */
+#define MII_BCM54XX_LREANAC		0x05	/* LDS Auto-Negotiation Advertised Control */
+#define MII_BCM54XX_LREANPT		0x06	/* LDS Ability Next Page Transmit          */
+#define MII_BCM54XX_LRELPA		0x07	/* LDS Link Partner Ability                */
+#define MII_BCM54XX_LRELPNPM		0x08	/* LDS Link Partner Next Page Message      */
+#define MII_BCM54XX_LRELPNPC		0x09	/* LDS Link Partner Next Page Control      */
+#define MII_BCM54XX_LRELDSE		0x0a	/* LDS Expansion Register                  */
+#define MII_BCM54XX_LREES		0x0f	/* LRE Extended Status                     */
+
+/* LRE control register. */
+#define LRECR_RESET			0x8000	/* Reset to default state      */
+#define LRECR_LOOPBACK			0x4000	/* Internal Loopback           */
+#define LRECR_LDSRES			0x2000	/* Restart LDS Process         */
+#define LRECR_LDSEN			0x1000	/* LDS Enable                  */
+#define LRECR_PDOWN			0x0800	/* Enable low power state      */
+#define LRECR_ISOLATE			0x0400	/* Isolate data paths from MII */
+#define LRECR_SPEED100			0x0200	/* Select 100 Mbps             */
+#define LRECR_SPEED10			0x0000	/* Select 10 Mbps              */
+#define LRECR_4PAIRS			0x0020	/* Select 4 Pairs              */
+#define LRECR_2PAIRS			0x0010	/* Select 2 Pairs              */
+#define LRECR_1PAIR			0x0000	/* Select 1 Pair               */
+#define LRECR_MASTER			0x0008	/* Force Master when LDS disabled */
+#define LRECR_SLAVE			0x0000	/* Force Slave when LDS disabled  */
+
+/* LRE status register. */
+#define LRESR_100_1PAIR			0x2000	/* Can do 100Mbps 1 Pair       */
+#define LRESR_100_4PAIR			0x1000	/* Can do 100Mbps 4 Pairs      */
+#define LRESR_100_2PAIR			0x0800	/* Can do 100Mbps 2 Pairs      */
+#define LRESR_10_2PAIR			0x0400	/* Can do 10Mbps 2 Pairs       */
+#define LRESR_10_1PAIR			0x0200	/* Can do 10Mbps 1 Pair        */
+#define LRESR_ESTATEN			0x0100	/* Extended Status in R15      */
+#define LRESR_RESV			0x0080	/* Unused...                   */
+#define LRESR_MFPS			0x0040	/* Can suppress Management Frames Preamble */
+#define LRESR_LDSCOMPLETE		0x0020	/* LDS Auto-negotiation complete */
+#define LRESR_8023			0x0010	/* Has IEEE 802.3 Support      */
+#define LRESR_LDSABILITY		0x0008	/* LDS auto-negotiation capable */
+#define LRESR_LSTATUS			0x0004	/* Link status                 */
+#define LRESR_JCD			0x0002	/* Jabber detected             */
+#define LRESR_ERCAP			0x0001	/* Ext-reg capability          */
+
+/* LDS Auto-Negotiation Advertised Ability. */
+#define LREANAA_PAUSE_ASYM		0x8000	/* Can pause asymmetrically    */
+#define LREANAA_PAUSE			0x4000	/* Can pause                   */
+#define LREANAA_100_1PAIR		0x0020	/* Can do 100Mbps 1 Pair       */
+#define LREANAA_100_4PAIR		0x0010	/* Can do 100Mbps 4 Pair       */
+#define LREANAA_100_2PAIR		0x0008	/* Can do 100Mbps 2 Pair       */
+#define LREANAA_10_2PAIR		0x0004	/* Can do 10Mbps 2 Pair        */
+#define LREANAA_10_1PAIR		0x0002	/* Can do 10Mbps 1 Pair        */
+
+#define LRE_ADVERTISE_FULL		(LREANAA_100_1PAIR | LREANAA_100_4PAIR | \
+					 LREANAA_100_2PAIR | LREANAA_10_2PAIR | \
+					 LREANAA_10_1PAIR)
+
+#define LRE_ADVERTISE_ALL		LRE_ADVERTISE_FULL
+
+/* LDS Link Partner Ability. */
+#define LRELPA_PAUSE_ASYM		0x8000	/* Supports asymmetric pause   */
+#define LRELPA_PAUSE			0x4000	/* Supports pause capability   */
+#define LRELPA_100_1PAIR		0x0020	/* 100Mbps 1 Pair capable      */
+#define LRELPA_100_4PAIR		0x0010	/* 100Mbps 4 Pair capable      */
+#define LRELPA_100_2PAIR		0x0008	/* 100Mbps 2 Pair capable      */
+#define LRELPA_10_2PAIR			0x0004	/* 10Mbps 2 Pair capable       */
+#define LRELPA_10_1PAIR			0x0002	/* 10Mbps 1 Pair capable       */
+
+/* LDS Expansion register. */
+#define LDSE_DOWNGRADE			0x8000	/* Can do LDS Speed Downgrade  */
+#define LDSE_MASTER			0x4000	/* Master / Slave              */
+#define LDSE_PAIRS_MASK			0x3000	/* Pair Count Mask             */
+#define LDSE_PAIRS_SHIFT		12
+#define LDSE_4PAIRS			(2 << LDSE_PAIRS_SHIFT)	/* 4 Pairs Connection */
+#define LDSE_2PAIRS			(1 << LDSE_PAIRS_SHIFT)	/* 2 Pairs Connection */
+#define LDSE_1PAIR			(0 << LDSE_PAIRS_SHIFT)	/* 1 Pair  Connection */
+#define LDSE_CABLEN_MASK		0x0FFF	/* Cable Length Mask           */
+
 /* BCM54810 Registers */
 #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL	(MII_BCM54XX_EXP_SEL_ER + 0x90)
 #define BCM54810_EXP_BROADREACH_LRE_MISC_CTL_EN	(1 << 0)
 #define BCM54810_SHD_CLK_CTL			0x3
 #define BCM54810_SHD_CLK_CTL_GTXCLK_EN		(1 << 9)
 
+/* BCM54811 Registers */
+#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL	(MII_BCM54XX_EXP_SEL_ER + 0x9A)
+/* Access Control Override Enable */
+#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_EN		BIT(15)
+/* Access Control Override Value */
+#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_OVERRIDE_VAL	BIT(14)
+/* Access Control Value */
+#define BCM54811_EXP_BROADREACH_LRE_OVERLAY_CTL_VAL		BIT(13)
+
 /* BCM54612E Registers */
 #define BCM54612E_EXP_SPARE0		(MII_BCM54XX_EXP_SEL_ETC + 0x34)
 #define BCM54612E_LED4_CLK125OUT_EN	(1 << 1)
 
+
+/* Wake-on-LAN registers */
+#define BCM54XX_WOL_MAIN_CTL		(MII_BCM54XX_EXP_SEL_WOL + 0x80)
+#define  BCM54XX_WOL_EN			BIT(0)
+#define  BCM54XX_WOL_MODE_SINGLE_MPD	0
+#define  BCM54XX_WOL_MODE_SINGLE_MPDSEC	1
+#define  BCM54XX_WOL_MODE_DUAL		2
+#define  BCM54XX_WOL_MODE_SHIFT		1
+#define  BCM54XX_WOL_MODE_MASK		0x3
+#define  BCM54XX_WOL_MP_MSB_FF_EN	BIT(3)
+#define  BCM54XX_WOL_SECKEY_OPT_4B	0
+#define  BCM54XX_WOL_SECKEY_OPT_6B	1
+#define  BCM54XX_WOL_SECKEY_OPT_8B	2
+#define  BCM54XX_WOL_SECKEY_OPT_SHIFT	4
+#define  BCM54XX_WOL_SECKEY_OPT_MASK	0x3
+#define  BCM54XX_WOL_L2_TYPE_CHK	BIT(6)
+#define  BCM54XX_WOL_L4IPV4UDP_CHK	BIT(7)
+#define  BCM54XX_WOL_L4IPV6UDP_CHK	BIT(8)
+#define  BCM54XX_WOL_UDPPORT_CHK	BIT(9)
+#define  BCM54XX_WOL_CRC_CHK		BIT(10)
+#define  BCM54XX_WOL_SECKEY_MODE	BIT(11)
+#define  BCM54XX_WOL_RST		BIT(12)
+#define  BCM54XX_WOL_DIR_PKT_EN		BIT(13)
+#define  BCM54XX_WOL_MASK_MODE_DA_FF	0
+#define  BCM54XX_WOL_MASK_MODE_DA_MPD	1
+#define  BCM54XX_WOL_MASK_MODE_DA_ONLY	2
+#define  BCM54XX_WOL_MASK_MODE_MPD	3
+#define  BCM54XX_WOL_MASK_MODE_SHIFT	14
+#define  BCM54XX_WOL_MASK_MODE_MASK	0x3
+
+#define BCM54XX_WOL_INNER_PROTO		(MII_BCM54XX_EXP_SEL_WOL + 0x81)
+#define BCM54XX_WOL_OUTER_PROTO		(MII_BCM54XX_EXP_SEL_WOL + 0x82)
+#define BCM54XX_WOL_OUTER_PROTO2	(MII_BCM54XX_EXP_SEL_WOL + 0x83)
+
+#define BCM54XX_WOL_MPD_DATA1(x)	(MII_BCM54XX_EXP_SEL_WOL + 0x84 + (x))
+#define BCM54XX_WOL_MPD_DATA2(x)	(MII_BCM54XX_EXP_SEL_WOL + 0x87 + (x))
+#define BCM54XX_WOL_SEC_KEY_8B		(MII_BCM54XX_EXP_SEL_WOL + 0x8A)
+#define BCM54XX_WOL_MASK(x)		(MII_BCM54XX_EXP_SEL_WOL + 0x8B + (x))
+#define BCM54XX_SEC_KEY_STORE(x)	(MII_BCM54XX_EXP_SEL_WOL + 0x8E)
+#define BCM54XX_WOL_SHARED_CNT		(MII_BCM54XX_EXP_SEL_WOL + 0x92)
+
+#define BCM54XX_WOL_INT_MASK		(MII_BCM54XX_EXP_SEL_WOL + 0x93)
+#define  BCM54XX_WOL_PKT1		BIT(0)
+#define  BCM54XX_WOL_PKT2		BIT(1)
+#define  BCM54XX_WOL_DIR		BIT(2)
+#define  BCM54XX_WOL_ALL_INTRS		(BCM54XX_WOL_PKT1 | \
+					 BCM54XX_WOL_PKT2 | \
+					 BCM54XX_WOL_DIR)
+
+#define BCM54XX_WOL_INT_STATUS		(MII_BCM54XX_EXP_SEL_WOL + 0x94)
+
+/* BCM5221 Registers */
+#define BCM5221_AEGSR			0x1C
+#define BCM5221_AEGSR_MDIX_STATUS	BIT(13)
+#define BCM5221_AEGSR_MDIX_MAN_SWAP	BIT(12)
+#define BCM5221_AEGSR_MDIX_DIS		BIT(11)
+
+#define BCM5221_SHDW_AM4_EN_CLK_LPM	BIT(2)
+#define BCM5221_SHDW_AM4_FORCE_LPM	BIT(1)
+
 /*****************************************************************************/
 /* Fast Ethernet Transceiver definitions. */
 /*****************************************************************************/
@@ -304,6 +468,8 @@
 #define LPI_FEATURE_EN			0x8000
 #define LPI_FEATURE_EN_DIG1000X		0x4000
 
+#define BRCM_CL45VEN_EEE_LPI_CNT	0x803f
+
 /* Core register definitions*/
 #define MII_BRCM_CORE_BASE12	0x12
 #define MII_BRCM_CORE_BASE13	0x13
diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h
index 9e97ced2896d..14fa93268630 100644
--- a/include/linux/bsg-lib.h
+++ b/include/linux/bsg-lib.h
@@ -65,7 +65,8 @@ struct bsg_job {
 void bsg_job_done(struct bsg_job *job, int result,
 		  unsigned int reply_payload_rcv_len);
 struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
-		bsg_job_fn *job_fn, bsg_timeout_fn *timeout, int dd_job_size);
+		struct queue_limits *lim, bsg_job_fn *job_fn,
+		bsg_timeout_fn *timeout, int dd_job_size);
 void bsg_remove_queue(struct request_queue *q);
 void bsg_job_put(struct bsg_job *job);
 int __must_check bsg_job_get(struct bsg_job *job);
diff --git a/include/linux/bsg.h b/include/linux/bsg.h
index 1ac81c809da9..ee2df73edf83 100644
--- a/include/linux/bsg.h
+++ b/include/linux/bsg.h
@@ -9,7 +9,7 @@ struct device;
 struct request_queue;
 
 typedef int (bsg_sg_io_fn)(struct request_queue *, struct sg_io_v4 *hdr,
-		fmode_t mode, unsigned int timeout);
+		bool open_for_write, unsigned int timeout);
 
 struct bsg_device *bsg_register_queue(struct request_queue *q,
 		struct device *parent, const char *name,
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 508199e38415..f06976ffb63f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -74,6 +74,11 @@
 #define KF_ITER_NEW     (1 << 8) /* kfunc implements BPF iter constructor */
 #define KF_ITER_NEXT    (1 << 9) /* kfunc implements BPF iter next method */
 #define KF_ITER_DESTROY (1 << 10) /* kfunc implements BPF iter destructor */
+#define KF_RCU_PROTECTED (1 << 11) /* kfunc should be protected by rcu cs when they are invoked */
+#define KF_FASTCALL     (1 << 12) /* kfunc supports bpf_fastcall protocol */
+#define KF_ARENA_RET    (1 << 13) /* kfunc returns an arena pointer */
+#define KF_ARENA_ARG1   (1 << 14) /* kfunc takes an arena pointer as its first argument */
+#define KF_ARENA_ARG2   (1 << 15) /* kfunc takes an arena pointer as its second argument */
 
 /*
  * Tag marking a kernel function as a kfunc. This is meant to minimize the
@@ -81,7 +86,18 @@
  * as to avoid issues such as the compiler inlining or eliding either a static
  * kfunc, or a global kfunc in an LTO build.
  */
-#define __bpf_kfunc __used noinline
+#define __bpf_kfunc __used __retain __noclone noinline
+
+#define __bpf_kfunc_start_defs()					       \
+	__diag_push();							       \
+	__diag_ignore_all("-Wmissing-declarations",			       \
+			  "Global kfuncs as their definitions will be in BTF");\
+	__diag_ignore_all("-Wmissing-prototypes",			       \
+			  "Global kfuncs as their definitions will be in BTF")
+
+#define __bpf_kfunc_end_defs() __diag_pop()
+#define __bpf_hook_start() __bpf_kfunc_start_defs()
+#define __bpf_hook_end() __bpf_kfunc_end_defs()
 
 /*
  * Return the name of the passed struct, if exists, or halt the build if for
@@ -98,10 +114,14 @@ struct btf_type;
 union bpf_attr;
 struct btf_show;
 struct btf_id_set;
+struct bpf_prog;
+
+typedef int (*btf_kfunc_filter_t)(const struct bpf_prog *prog, u32 kfunc_id);
 
 struct btf_kfunc_id_set {
 	struct module *owner;
 	struct btf_id_set8 *set;
+	btf_kfunc_filter_t filter;
 };
 
 struct btf_id_dtor_kfunc {
@@ -121,8 +141,10 @@ struct btf_struct_metas {
 
 extern const struct file_operations btf_fops;
 
+const char *btf_get_name(const struct btf *btf);
 void btf_get(struct btf *btf);
 void btf_put(struct btf *btf);
+const struct btf_header *btf_header(const struct btf *btf);
 int btf_new_fd(const union bpf_attr *attr, bpfptr_t uattr, u32 uattr_sz);
 struct btf *btf_get_by_fd(int fd);
 int btf_get_info_by_fd(const struct btf *btf,
@@ -195,18 +217,22 @@ int btf_get_fd_by_id(u32 id);
 u32 btf_obj_id(const struct btf *btf);
 bool btf_is_kernel(const struct btf *btf);
 bool btf_is_module(const struct btf *btf);
+bool btf_is_vmlinux(const struct btf *btf);
 struct module *btf_try_get_module(const struct btf *btf);
 u32 btf_nr_types(const struct btf *btf);
+struct btf *btf_base_btf(const struct btf *btf);
+bool btf_type_is_i32(const struct btf_type *t);
+bool btf_type_is_i64(const struct btf_type *t);
+bool btf_type_is_primitive(const struct btf_type *t);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
-int btf_find_spin_lock(const struct btf *btf, const struct btf_type *t);
-int btf_find_timer(const struct btf *btf, const struct btf_type *t);
 struct btf_record *btf_parse_fields(const struct btf *btf, const struct btf_type *t,
 				    u32 field_mask, u32 value_size);
 int btf_check_and_fixup_fields(const struct btf *btf, struct btf_record *rec);
 bool btf_type_is_void(const struct btf_type *t);
 s32 btf_find_by_name_kind(const struct btf *btf, const char *name, u8 kind);
+s32 bpf_find_btf_id(const char *name, u32 kind, struct btf **btf_p);
 const struct btf_type *btf_type_skip_modifiers(const struct btf *btf,
 					       u32 id, u32 *res_id);
 const struct btf_type *btf_type_resolve_ptr(const struct btf *btf,
@@ -323,11 +349,21 @@ static inline u8 btf_int_offset(const struct btf_type *t)
 	return BTF_INT_OFFSET(*(u32 *)(t + 1));
 }
 
+static inline __u8 btf_int_bits(const struct btf_type *t)
+{
+	return BTF_INT_BITS(*(__u32 *)(t + 1));
+}
+
 static inline bool btf_type_is_scalar(const struct btf_type *t)
 {
 	return btf_type_is_int(t) || btf_type_is_enum(t);
 }
 
+static inline bool btf_type_is_fwd(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_FWD;
+}
+
 static inline bool btf_type_is_typedef(const struct btf_type *t)
 {
 	return BTF_INFO_KIND(t->info) == BTF_KIND_TYPEDEF;
@@ -462,6 +498,11 @@ static inline struct btf_param *btf_params(const struct btf_type *t)
 	return (struct btf_param *)(t + 1);
 }
 
+static inline struct btf_decl_tag *btf_decl_tag(const struct btf_type *t)
+{
+	return (struct btf_decl_tag *)(t + 1);
+}
+
 static inline int btf_id_cmp_func(const void *a, const void *b)
 {
 	const int *pa = a, *pb = b;
@@ -479,18 +520,65 @@ static inline void *btf_id_set8_contains(const struct btf_id_set8 *set, u32 id)
 	return bsearch(&id, set->pairs, set->cnt, sizeof(set->pairs[0]), btf_id_cmp_func);
 }
 
-struct bpf_prog;
+bool btf_param_match_suffix(const struct btf *btf,
+			    const struct btf_param *arg,
+			    const char *suffix);
+int btf_ctx_arg_offset(const struct btf *btf, const struct btf_type *func_proto,
+		       u32 arg_no);
+u32 btf_ctx_arg_idx(struct btf *btf, const struct btf_type *func_proto, int off);
+
 struct bpf_verifier_log;
 
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_BPF_SYSCALL)
+struct bpf_struct_ops;
+int __register_bpf_struct_ops(struct bpf_struct_ops *st_ops);
+const struct bpf_struct_ops_desc *bpf_struct_ops_find_value(struct btf *btf, u32 value_id);
+const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id);
+#else
+static inline const struct bpf_struct_ops_desc *bpf_struct_ops_find(struct btf *btf, u32 type_id)
+{
+	return NULL;
+}
+#endif
+
+enum btf_field_iter_kind {
+	BTF_FIELD_ITER_IDS,
+	BTF_FIELD_ITER_STRS,
+};
+
+struct btf_field_desc {
+	/* once-per-type offsets */
+	int t_off_cnt, t_offs[2];
+	/* member struct size, or zero, if no members */
+	int m_sz;
+	/* repeated per-member offsets */
+	int m_off_cnt, m_offs[1];
+};
+
+struct btf_field_iter {
+	struct btf_field_desc desc;
+	void *p;
+	int m_idx;
+	int off_idx;
+	int vlen;
+};
+
 #ifdef CONFIG_BPF_SYSCALL
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
+void btf_set_base_btf(struct btf *btf, const struct btf *base_btf);
+int btf_relocate(struct btf *btf, const struct btf *base_btf, __u32 **map_ids);
+int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+			enum btf_field_iter_kind iter_kind);
+__u32 *btf_field_iter_next(struct btf_field_iter *it);
+
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
+const char *btf_str_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
 struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
-u32 *btf_kfunc_id_set_contains(const struct btf *btf,
-			       enum bpf_prog_type prog_type,
-			       u32 kfunc_btf_id);
-u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id);
+u32 *btf_kfunc_id_set_contains(const struct btf *btf, u32 kfunc_btf_id,
+			       const struct bpf_prog *prog);
+u32 *btf_kfunc_is_modify_return(const struct btf *btf, u32 kfunc_btf_id,
+				const struct bpf_prog *prog);
 int register_btf_kfunc_id_set(enum bpf_prog_type prog_type,
 			      const struct btf_kfunc_id_set *s);
 int register_btf_fmodret_id_set(const struct btf_kfunc_id_set *kset);
@@ -498,27 +586,61 @@ s32 btf_find_dtor_kfunc(struct btf *btf, u32 btf_id);
 int register_btf_id_dtor_kfuncs(const struct btf_id_dtor_kfunc *dtors, u32 add_cnt,
 				struct module *owner);
 struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf, u32 btf_id);
-const struct btf_member *
-btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, enum bpf_prog_type prog_type,
-		      int arg);
+bool btf_is_projection_of(const char *pname, const char *tname);
+bool btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+			   const struct btf_type *t, enum bpf_prog_type prog_type,
+			   int arg);
 int get_kern_ctx_btf_id(struct bpf_verifier_log *log, enum bpf_prog_type prog_type);
 bool btf_types_are_same(const struct btf *btf1, u32 id1,
 			const struct btf *btf2, u32 id2);
+int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx);
+
+static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t)
+{
+	if (!btf_type_is_ptr(t))
+		return false;
+
+	t = btf_type_skip_modifiers(btf, t->type, NULL);
+
+	return btf_type_is_struct(t);
+}
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
 {
 	return NULL;
 }
+
+static inline void btf_set_base_btf(struct btf *btf, const struct btf *base_btf)
+{
+}
+
+static inline int btf_relocate(void *log, struct btf *btf, const struct btf *base_btf,
+			       __u32 **map_ids)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int btf_field_iter_init(struct btf_field_iter *it, struct btf_type *t,
+				      enum btf_field_iter_kind iter_kind)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline __u32 *btf_field_iter_next(struct btf_field_iter *it)
+{
+	return NULL;
+}
+
 static inline const char *btf_name_by_offset(const struct btf *btf,
 					     u32 offset)
 {
 	return NULL;
 }
 static inline u32 *btf_kfunc_id_set_contains(const struct btf *btf,
-					     enum bpf_prog_type prog_type,
-					     u32 kfunc_btf_id)
+					     u32 kfunc_btf_id,
+					     struct bpf_prog *prog)
+
 {
 	return NULL;
 }
@@ -540,12 +662,12 @@ static inline struct btf_struct_meta *btf_find_struct_meta(const struct btf *btf
 {
 	return NULL;
 }
-static inline const struct btf_member *
-btf_get_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
-		      const struct btf_type *t, enum bpf_prog_type prog_type,
-		      int arg)
+static inline bool
+btf_is_prog_ctx_type(struct bpf_verifier_log *log, const struct btf *btf,
+		     const struct btf_type *t, enum bpf_prog_type prog_type,
+		     int arg)
 {
-	return NULL;
+	return false;
 }
 static inline int get_kern_ctx_btf_id(struct bpf_verifier_log *log,
 				      enum bpf_prog_type prog_type) {
@@ -556,16 +678,9 @@ static inline bool btf_types_are_same(const struct btf *btf1, u32 id1,
 {
 	return false;
 }
-#endif
-
-static inline bool btf_type_is_struct_ptr(struct btf *btf, const struct btf_type *t)
+static inline int btf_check_iter_arg(struct btf *btf, const struct btf_type *func, int arg_idx)
 {
-	if (!btf_type_is_ptr(t))
-		return false;
-
-	t = btf_type_skip_modifiers(btf, t->type, NULL);
-
-	return btf_type_is_struct(t);
+	return -EOPNOTSUPP;
 }
-
+#endif
 #endif
diff --git a/include/linux/btf_ids.h b/include/linux/btf_ids.h
index 00950cc03bff..139bdececdcf 100644
--- a/include/linux/btf_ids.h
+++ b/include/linux/btf_ids.h
@@ -3,11 +3,16 @@
 #ifndef _LINUX_BTF_IDS_H
 #define _LINUX_BTF_IDS_H
 
+#include <linux/types.h> /* for u32 */
+
 struct btf_id_set {
 	u32 cnt;
 	u32 ids[];
 };
 
+/* This flag implies BTF_SET8 holds kfunc(s) */
+#define BTF_SET8_KFUNCS		(1 << 0)
+
 struct btf_id_set8 {
 	u32 cnt;
 	u32 flags;
@@ -21,6 +26,7 @@ struct btf_id_set8 {
 
 #include <linux/compiler.h> /* for __PASTE */
 #include <linux/compiler_attributes.h> /* for __maybe_unused */
+#include <linux/stringify.h>
 
 /*
  * Following macros help to define lists of BTF IDs placed
@@ -49,7 +55,7 @@ word							\
 	____BTF_ID(symbol, word)
 
 #define __ID(prefix) \
-	__PASTE(prefix, __COUNTER__)
+	__PASTE(__PASTE(prefix, __COUNTER__), __LINE__)
 
 /*
  * The BTF_ID defines unique symbol for each ID pointing
@@ -183,17 +189,18 @@ extern struct btf_id_set name;
  * .word (1 << 3) | (1 << 1) | (1 << 2)
  *
  */
-#define __BTF_SET8_START(name, scope)			\
+#define __BTF_SET8_START(name, scope, flags)		\
+__BTF_ID_LIST(name, local)				\
 asm(							\
 ".pushsection " BTF_IDS_SECTION ",\"a\";       \n"	\
 "." #scope " __BTF_ID__set8__" #name ";        \n"	\
 "__BTF_ID__set8__" #name ":;                   \n"	\
-".zero 8                                       \n"	\
+".zero 4                                       \n"	\
+".long " __stringify(flags)                   "\n"	\
 ".popsection;                                  \n");
 
 #define BTF_SET8_START(name)				\
-__BTF_ID_LIST(name, local)				\
-__BTF_SET8_START(name, local)
+__BTF_SET8_START(name, local, 0)
 
 #define BTF_SET8_END(name)				\
 asm(							\
@@ -202,6 +209,12 @@ asm(							\
 ".popsection;                                 \n");	\
 extern struct btf_id_set8 name;
 
+#define BTF_KFUNCS_START(name)				\
+__BTF_SET8_START(name, local, BTF_SET8_KFUNCS)
+
+#define BTF_KFUNCS_END(name)				\
+BTF_SET8_END(name)
+
 #else
 
 #define BTF_ID_LIST(name) static u32 __maybe_unused name[64];
@@ -216,6 +229,8 @@ extern struct btf_id_set8 name;
 #define BTF_SET_END(name)
 #define BTF_SET8_START(name) static struct btf_id_set8 __maybe_unused name = { 0 };
 #define BTF_SET8_END(name)
+#define BTF_KFUNCS_START(name) static struct btf_id_set8 __maybe_unused name = { .flags = BTF_SET8_KFUNCS };
+#define BTF_KFUNCS_END(name)
 
 #endif /* CONFIG_DEBUG_INFO_BTF */
 
@@ -267,5 +282,7 @@ MAX_BTF_TRACING_TYPE,
 extern u32 btf_tracing_ids[];
 extern u32 bpf_cgroup_btf_id[];
 extern u32 bpf_local_storage_map_btf_id[];
+extern u32 btf_bpf_map_id[];
+extern u32 bpf_kmem_cache_btf_id[];
 
 #endif
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 1520793c72da..b16b88bfbc3e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -16,8 +16,6 @@
 #include <linux/wait.h>
 #include <linux/atomic.h>
 
-#ifdef CONFIG_BLOCK
-
 enum bh_state_bits {
 	BH_Uptodate,	/* Contains valid data */
 	BH_Dirty,	/* Is dirty */
@@ -36,6 +34,7 @@ enum bh_state_bits {
 	BH_Meta,	/* Buffer contains metadata */
 	BH_Prio,	/* Buffer should be submitted with REQ_PRIO */
 	BH_Defer_Completion, /* Defer AIO completion to workqueue */
+	BH_Migrate,     /* Buffer is being migrated (norefs) */
 
 	BH_PrivateStart,/* not a state bit, but the first bit available
 			 * for private allocation by other entities
@@ -55,7 +54,7 @@ typedef void (bh_end_io_t)(struct buffer_head *bh, int uptodate);
  * filesystem and block layers.  Nowadays the basic I/O unit
  * is the bio, and buffer_heads are used for extracting block
  * mappings (via a get_block_t call), for tracking state within
- * a page (via a page_mapping) and for wrapping bio submission
+ * a folio (via a folio_mapping) and for wrapping bio submission
  * for backward compatibility reasons (e.g. submit_bh).
  */
 struct buffer_head {
@@ -173,7 +172,10 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh)
 	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
-#define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
+static inline unsigned long bh_offset(const struct buffer_head *bh)
+{
+	return (unsigned long)(bh)->b_data & (page_size(bh->b_page) - 1);
+}
 
 /* If we *know* page->private refers to buffer_heads */
 #define page_buffers(page)					\
@@ -181,7 +183,6 @@ static __always_inline int buffer_uptodate(const struct buffer_head *bh)
 		BUG_ON(!PagePrivate(page));			\
 		((struct buffer_head *)page_private(page));	\
 	})
-#define page_has_buffers(page)	PagePrivate(page)
 #define folio_buffers(folio)		folio_get_private(folio)
 
 void buffer_check_dirty_writeback(struct folio *folio,
@@ -194,29 +195,22 @@ void buffer_check_dirty_writeback(struct folio *folio,
 void mark_buffer_dirty(struct buffer_head *bh);
 void mark_buffer_write_io_error(struct buffer_head *bh);
 void touch_buffer(struct buffer_head *bh);
-void set_bh_page(struct buffer_head *bh,
-		struct page *page, unsigned long offset);
 void folio_set_bh(struct buffer_head *bh, struct folio *folio,
 		  unsigned long offset);
-bool try_to_free_buffers(struct folio *);
 struct buffer_head *folio_alloc_buffers(struct folio *folio, unsigned long size,
-					bool retry);
-struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size,
-		bool retry);
-void create_empty_buffers(struct page *, unsigned long,
-			unsigned long b_state);
-void folio_create_empty_buffers(struct folio *folio, unsigned long blocksize,
-				unsigned long b_state);
+					gfp_t gfp);
+struct buffer_head *alloc_page_buffers(struct page *page, unsigned long size);
+struct buffer_head *create_empty_buffers(struct folio *folio,
+		unsigned long blocksize, unsigned long b_state);
 void end_buffer_read_sync(struct buffer_head *bh, int uptodate);
 void end_buffer_write_sync(struct buffer_head *bh, int uptodate);
-void end_buffer_async_write(struct buffer_head *bh, int uptodate);
 
 /* Things to do with buffers at mapping->private_list */
 void mark_buffer_dirty_inode(struct buffer_head *bh, struct inode *inode);
-int inode_has_buffers(struct inode *);
-void invalidate_inode_buffers(struct inode *);
-int remove_inode_buffers(struct inode *inode);
-int sync_mapping_buffers(struct address_space *mapping);
+int generic_buffers_fsync_noflush(struct file *file, loff_t start, loff_t end,
+				  bool datasync);
+int generic_buffers_fsync(struct file *file, loff_t start, loff_t end,
+			  bool datasync);
 void clean_bdev_aliases(struct block_device *bdev, sector_t block,
 			sector_t len);
 static inline void clean_bdev_bh_alias(struct buffer_head *bh)
@@ -229,16 +223,15 @@ void __wait_on_buffer(struct buffer_head *);
 wait_queue_head_t *bh_waitq_head(struct buffer_head *bh);
 struct buffer_head *__find_get_block(struct block_device *bdev, sector_t block,
 			unsigned size);
-struct buffer_head *__getblk_gfp(struct block_device *bdev, sector_t block,
-				  unsigned size, gfp_t gfp);
+struct buffer_head *__find_get_block_nonatomic(struct block_device *bdev,
+			sector_t block, unsigned size);
+struct buffer_head *bdev_getblk(struct block_device *bdev, sector_t block,
+		unsigned size, gfp_t gfp);
 void __brelse(struct buffer_head *);
 void __bforget(struct buffer_head *);
 void __breadahead(struct block_device *, sector_t block, unsigned int size);
 struct buffer_head *__bread_gfp(struct block_device *,
 				sector_t block, unsigned size, gfp_t gfp);
-void invalidate_bh_lrus(void);
-void invalidate_bh_lrus_cpu(void);
-bool has_bh_in_lru(int cpu, void *dummy);
 struct buffer_head *alloc_buffer_head(gfp_t gfp_flags);
 void free_buffer_head(struct buffer_head * bh);
 void unlock_buffer(struct buffer_head *bh);
@@ -254,51 +247,33 @@ int __bh_read(struct buffer_head *bh, blk_opf_t op_flags, bool wait);
 void __bh_read_batch(int nr, struct buffer_head *bhs[],
 		     blk_opf_t op_flags, bool force_lock);
 
-extern int buffer_heads_over_limit;
-
 /*
  * Generic address_space_operations implementations for buffer_head-backed
  * address_spaces.
  */
 void block_invalidate_folio(struct folio *folio, size_t offset, size_t length);
-int block_write_full_page(struct page *page, get_block_t *get_block,
-				struct writeback_control *wbc);
-int __block_write_full_page(struct inode *inode, struct page *page,
-			get_block_t *get_block, struct writeback_control *wbc,
-			bh_end_io_t *handler);
+int block_write_full_folio(struct folio *folio, struct writeback_control *wbc,
+		void *get_block);
+int __block_write_full_folio(struct inode *inode, struct folio *folio,
+		get_block_t *get_block, struct writeback_control *wbc);
 int block_read_full_folio(struct folio *, get_block_t *);
 bool block_is_partially_uptodate(struct folio *, size_t from, size_t count);
 int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
-		struct page **pagep, get_block_t *get_block);
-int __block_write_begin(struct page *page, loff_t pos, unsigned len,
+		struct folio **foliop, get_block_t *get_block);
+int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block);
-int block_write_end(struct file *, struct address_space *,
-				loff_t, unsigned, unsigned,
-				struct page *, void *);
-int generic_write_end(struct file *, struct address_space *,
-				loff_t, unsigned, unsigned,
-				struct page *, void *);
-void page_zero_new_buffers(struct page *page, unsigned from, unsigned to);
-void clean_page_buffers(struct page *page);
-int cont_write_begin(struct file *, struct address_space *, loff_t,
-			unsigned, struct page **, void **,
+int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *);
+int generic_write_end(const struct kiocb *, struct address_space *,
+				loff_t, unsigned len, unsigned copied,
+				struct folio *, void *);
+void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
+int cont_write_begin(const struct kiocb *, struct address_space *, loff_t,
+			unsigned, struct folio **, void **,
 			get_block_t *, loff_t *);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
-int block_commit_write(struct page *page, unsigned from, unsigned to);
+void block_commit_write(struct folio *folio, size_t from, size_t to);
 int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
 				get_block_t get_block);
-/* Convert errno to return value from ->page_mkwrite() call */
-static inline vm_fault_t block_page_mkwrite_return(int err)
-{
-	if (err == 0)
-		return VM_FAULT_LOCKED;
-	if (err == -EFAULT || err == -EAGAIN)
-		return VM_FAULT_NOPAGE;
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	/* -ENOSPC, -EDQUOT, -EIO ... */
-	return VM_FAULT_SIGBUS;
-}
 sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *);
 int block_truncate_page(struct address_space *, loff_t, get_block_t *);
 
@@ -312,8 +287,6 @@ extern int buffer_migrate_folio_norefs(struct address_space *,
 #define buffer_migrate_folio_norefs NULL
 #endif
 
-void buffer_init(void);
-
 /*
  * inline definitions
  */
@@ -329,12 +302,38 @@ static inline void put_bh(struct buffer_head *bh)
         atomic_dec(&bh->b_count);
 }
 
+/**
+ * brelse - Release a buffer.
+ * @bh: The buffer to release.
+ *
+ * Decrement a buffer_head's reference count.  If @bh is NULL, this
+ * function is a no-op.
+ *
+ * If all buffers on a folio have zero reference count, are clean
+ * and unlocked, and if the folio is unlocked and not under writeback
+ * then try_to_free_buffers() may strip the buffers from the folio in
+ * preparation for freeing it (sometimes, rarely, buffers are removed
+ * from a folio but it ends up not being freed, and buffers may later
+ * be reattached).
+ *
+ * Context: Any context.
+ */
 static inline void brelse(struct buffer_head *bh)
 {
 	if (bh)
 		__brelse(bh);
 }
 
+/**
+ * bforget - Discard any dirty data in a buffer.
+ * @bh: The buffer to forget.
+ *
+ * Call this function instead of brelse() if the data written to a buffer
+ * no longer needs to be written back.  It will clear the buffer's dirty
+ * flag so writeback of this buffer will be skipped.
+ *
+ * Context: Any context.
+ */
 static inline void bforget(struct buffer_head *bh)
 {
 	if (bh)
@@ -359,17 +358,38 @@ sb_breadahead(struct super_block *sb, sector_t block)
 	__breadahead(sb->s_bdev, block, sb->s_blocksize);
 }
 
-static inline struct buffer_head *
-sb_getblk(struct super_block *sb, sector_t block)
+static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
+		sector_t block, unsigned size)
 {
-	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, __GFP_MOVABLE);
+	gfp_t gfp;
+
+	gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);
+	gfp |= __GFP_NOFAIL;
+
+	return bdev_getblk(bdev, block, size, gfp);
 }
 
+static inline struct buffer_head *__getblk(struct block_device *bdev,
+		sector_t block, unsigned size)
+{
+	gfp_t gfp;
+
+	gfp = mapping_gfp_constraint(bdev->bd_mapping, ~__GFP_FS);
+	gfp |= __GFP_MOVABLE | __GFP_NOFAIL;
 
-static inline struct buffer_head *
-sb_getblk_gfp(struct super_block *sb, sector_t block, gfp_t gfp)
+	return bdev_getblk(bdev, block, size, gfp);
+}
+
+static inline struct buffer_head *sb_getblk(struct super_block *sb,
+		sector_t block)
 {
-	return __getblk_gfp(sb->s_bdev, block, sb->s_blocksize, gfp);
+	return __getblk(sb->s_bdev, block, sb->s_blocksize);
+}
+
+static inline struct buffer_head *sb_getblk_gfp(struct super_block *sb,
+		sector_t block, gfp_t gfp)
+{
+	return bdev_getblk(sb->s_bdev, block, sb->s_blocksize, gfp);
 }
 
 static inline struct buffer_head *
@@ -378,6 +398,12 @@ sb_find_get_block(struct super_block *sb, sector_t block)
 	return __find_get_block(sb->s_bdev, block, sb->s_blocksize);
 }
 
+static inline struct buffer_head *
+sb_find_get_block_nonatomic(struct super_block *sb, sector_t block)
+{
+	return __find_get_block_nonatomic(sb->s_bdev, block, sb->s_blocksize);
+}
+
 static inline void
 map_bh(struct buffer_head *bh, struct super_block *sb, sector_t block)
 {
@@ -406,20 +432,6 @@ static inline void lock_buffer(struct buffer_head *bh)
 		__lock_buffer(bh);
 }
 
-static inline struct buffer_head *getblk_unmovable(struct block_device *bdev,
-						   sector_t block,
-						   unsigned size)
-{
-	return __getblk_gfp(bdev, block, size, 0);
-}
-
-static inline struct buffer_head *__getblk(struct block_device *bdev,
-					   sector_t block,
-					   unsigned size)
-{
-	return __getblk_gfp(bdev, block, size, __GFP_MOVABLE);
-}
-
 static inline void bh_readahead(struct buffer_head *bh, blk_opf_t op_flags)
 {
 	if (!buffer_uptodate(bh) && trylock_buffer(bh)) {
@@ -456,24 +468,63 @@ static inline void bh_readahead_batch(int nr, struct buffer_head *bhs[],
 }
 
 /**
- *  __bread() - reads a specified block and returns the bh
- *  @bdev: the block_device to read from
- *  @block: number of block
- *  @size: size (in bytes) to read
+ * __bread() - Read a block.
+ * @bdev: The block device to read from.
+ * @block: Block number in units of block size.
+ * @size: The block size of this device in bytes.
  *
- *  Reads a specified block, and returns buffer head that contains it.
- *  The page cache is allocated from movable area so that it can be migrated.
- *  It returns NULL if the block was unreadable.
+ * Read a specified block, and return the buffer head that refers
+ * to it.  The memory is allocated from the movable area so that it can
+ * be migrated.  The returned buffer head has its refcount increased.
+ * The caller should call brelse() when it has finished with the buffer.
+ *
+ * Context: May sleep waiting for I/O.
+ * Return: NULL if the block was unreadable.
  */
-static inline struct buffer_head *
-__bread(struct block_device *bdev, sector_t block, unsigned size)
+static inline struct buffer_head *__bread(struct block_device *bdev,
+		sector_t block, unsigned size)
 {
 	return __bread_gfp(bdev, block, size, __GFP_MOVABLE);
 }
 
+/**
+ * get_nth_bh - Get a reference on the n'th buffer after this one.
+ * @bh: The buffer to start counting from.
+ * @count: How many buffers to skip.
+ *
+ * This is primarily useful for finding the nth buffer in a folio; in
+ * that case you pass the head buffer and the byte offset in the folio
+ * divided by the block size.  It can be used for other purposes, but
+ * it will wrap at the end of the folio rather than returning NULL or
+ * proceeding to the next folio for you.
+ *
+ * Return: The requested buffer with an elevated refcount.
+ */
+static inline __must_check
+struct buffer_head *get_nth_bh(struct buffer_head *bh, unsigned int count)
+{
+	while (count--)
+		bh = bh->b_this_page;
+	get_bh(bh);
+	return bh;
+}
+
 bool block_dirty_folio(struct address_space *mapping, struct folio *folio);
 
-#else /* CONFIG_BLOCK */
+#ifdef CONFIG_BUFFER_HEAD
+
+void buffer_init(void);
+bool try_to_free_buffers(struct folio *folio);
+int inode_has_buffers(struct inode *inode);
+void invalidate_inode_buffers(struct inode *inode);
+int remove_inode_buffers(struct inode *inode);
+int sync_mapping_buffers(struct address_space *mapping);
+void invalidate_bh_lrus(void);
+void invalidate_bh_lrus_cpu(void);
+bool has_bh_in_lru(int cpu, void *dummy);
+extern int buffer_heads_over_limit;
+
+#else /* CONFIG_BUFFER_HEAD */
 
 static inline void buffer_init(void) {}
 static inline bool try_to_free_buffers(struct folio *folio) { return true; }
@@ -481,9 +532,10 @@ static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
+static inline void invalidate_bh_lrus(void) {}
 static inline void invalidate_bh_lrus_cpu(void) {}
 static inline bool has_bh_in_lru(int cpu, void *dummy) { return false; }
 #define buffer_heads_over_limit 0
 
-#endif /* CONFIG_BLOCK */
+#endif /* CONFIG_BUFFER_HEAD */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/bug.h b/include/linux/bug.h
index 348acf2558f3..17a4933c611b 100644
--- a/include/linux/bug.h
+++ b/include/linux/bug.h
@@ -42,6 +42,7 @@ void bug_get_file_line(struct bug_entry *bug, const char **file,
 struct bug_entry *find_bug(unsigned long bugaddr);
 
 enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs);
+enum bug_trap_type report_bug_entry(struct bug_entry *bug, struct pt_regs *regs);
 
 /* These are defined by the architecture */
 int is_valid_bugaddr(unsigned long addr);
@@ -62,6 +63,13 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr,
 }
 
 struct bug_entry;
+
+static inline enum bug_trap_type
+report_bug_entry(struct bug_entry *bug, struct pt_regs *regs)
+{
+	return BUG_TRAP_TYPE_BUG;
+}
+
 static inline void bug_get_file_line(struct bug_entry *bug, const char **file,
 				     unsigned int *line)
 {
@@ -73,15 +81,23 @@ static inline void generic_bug_clear_once(void) {}
 
 #endif	/* CONFIG_GENERIC_BUG */
 
+#ifdef CONFIG_PRINTK
+void mem_dump_obj(void *object);
+#else
+static inline void mem_dump_obj(void *object) {}
+#endif
+
 /*
  * Since detected data corruption should stop operation on the affected
  * structures. Return value must be checked and sanely acted on by caller.
  */
 static inline __must_check bool check_data_corruption(bool v) { return v; }
-#define CHECK_DATA_CORRUPTION(condition, fmt, ...)			 \
+#define CHECK_DATA_CORRUPTION(condition, addr, fmt, ...)		 \
 	check_data_corruption(({					 \
 		bool corruption = unlikely(condition);			 \
 		if (corruption) {					 \
+			if (addr)					 \
+				mem_dump_obj(addr);			 \
 			if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION)) { \
 				pr_err(fmt, ##__VA_ARGS__);		 \
 				BUG();					 \
diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
index 3aa3640f8c18..2cfbb4c65c78 100644
--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
@@ -4,17 +4,17 @@
 
 #include <linux/compiler.h>
 
-#ifdef __CHECKER__
-#define BUILD_BUG_ON_ZERO(e) (0)
-#else /* __CHECKER__ */
 /*
  * Force a compilation error if condition is true, but also produce a
  * result (of value 0 and type int), so the expression can be used
  * e.g. in a structure initializer (or where-ever else comma expressions
  * aren't permitted).
+ *
+ * Take an error message as an optional second argument. If omitted,
+ * default to the stringification of the tested expression.
  */
-#define BUILD_BUG_ON_ZERO(e) ((int)(sizeof(struct { int:(-!!(e)); })))
-#endif /* __CHECKER__ */
+#define BUILD_BUG_ON_ZERO(e, ...) \
+	__BUILD_BUG_ON_ZERO_MSG(e, ##__VA_ARGS__, #e " is true")
 
 /* Force a compilation error if a constant expression is not a power of 2 */
 #define __BUILD_BUG_ON_NOT_POWER_OF_2(n)	\
diff --git a/include/linux/buildid.h b/include/linux/buildid.h
index 3b7a0ff4642f..831c1b4b626c 100644
--- a/include/linux/buildid.h
+++ b/include/linux/buildid.h
@@ -2,19 +2,45 @@
 #ifndef _LINUX_BUILDID_H
 #define _LINUX_BUILDID_H
 
-#include <linux/mm_types.h>
+#include <linux/types.h>
 
 #define BUILD_ID_SIZE_MAX 20
 
-int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id,
-		   __u32 *size);
+struct vm_area_struct;
+int build_id_parse(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size);
+int build_id_parse_nofault(struct vm_area_struct *vma, unsigned char *build_id, __u32 *size);
 int build_id_parse_buf(const void *buf, unsigned char *build_id, u32 buf_size);
 
-#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_CRASH_CORE)
+#if IS_ENABLED(CONFIG_STACKTRACE_BUILD_ID) || IS_ENABLED(CONFIG_VMCORE_INFO)
 extern unsigned char vmlinux_build_id[BUILD_ID_SIZE_MAX];
 void init_vmlinux_build_id(void);
 #else
 static inline void init_vmlinux_build_id(void) { }
 #endif
 
+struct freader {
+	void *buf;
+	u32 buf_sz;
+	int err;
+	union {
+		struct {
+			struct file *file;
+			struct folio *folio;
+			void *addr;
+			loff_t folio_off;
+			bool may_fault;
+		};
+		struct {
+			const char *data;
+			u64 data_sz;
+		};
+	};
+};
+
+void freader_init_from_file(struct freader *r, void *buf, u32 buf_sz,
+			    struct file *file, bool may_fault);
+void freader_init_from_mem(struct freader *r, const char *data, u64 data_sz);
+const void *freader_fetch(struct freader *r, loff_t file_off, size_t sz);
+void freader_cleanup(struct freader *r);
+
 #endif
diff --git a/include/linux/bus/stm32_firewall_device.h b/include/linux/bus/stm32_firewall_device.h
new file mode 100644
index 000000000000..eaa7a3f54450
--- /dev/null
+++ b/include/linux/bus/stm32_firewall_device.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023, STMicroelectronics - All Rights Reserved
+ */
+
+#ifndef STM32_FIREWALL_DEVICE_H
+#define STM32_FIREWALL_DEVICE_H
+
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#define STM32_FIREWALL_MAX_EXTRA_ARGS		5
+
+/* Opaque reference to stm32_firewall_controller */
+struct stm32_firewall_controller;
+
+/**
+ * struct stm32_firewall - Information on a device's firewall. Each device can have more than one
+ *			   firewall.
+ *
+ * @firewall_ctrl:		Pointer referencing a firewall controller of the device. It is
+ *				opaque so a device cannot manipulate the controller's ops or access
+ *				the controller's data
+ * @extra_args:			Extra arguments that are implementation dependent
+ * @entry:			Name of the firewall entry
+ * @extra_args_size:		Number of extra arguments
+ * @firewall_id:		Firewall ID associated the device for this firewall controller
+ */
+struct stm32_firewall {
+	struct stm32_firewall_controller *firewall_ctrl;
+	u32 extra_args[STM32_FIREWALL_MAX_EXTRA_ARGS];
+	const char *entry;
+	size_t extra_args_size;
+	u32 firewall_id;
+};
+
+#if IS_ENABLED(CONFIG_STM32_FIREWALL)
+/**
+ * stm32_firewall_get_firewall - Get the firewall(s) associated to given device.
+ *				 The firewall controller reference is always the first argument
+ *				 of each of the access-controller property entries.
+ *				 The firewall ID is always the second argument of each of the
+ *				 access-controller  property entries.
+ *				 If there's no argument linked to the phandle, then the firewall ID
+ *				 field is set to U32_MAX, which is an invalid ID.
+ *
+ * @np:				Device node to parse
+ * @firewall:			Array of firewall references
+ * @nb_firewall:		Number of firewall references to get. Must be at least 1.
+ *
+ * Returns 0 on success, -ENODEV if there's no match with a firewall controller or appropriate errno
+ * code if error occurred.
+ */
+int stm32_firewall_get_firewall(struct device_node *np, struct stm32_firewall *firewall,
+				unsigned int nb_firewall);
+
+/**
+ * stm32_firewall_grant_access - Request firewall access rights and grant access.
+ *
+ * @firewall:			Firewall reference containing the ID to check against its firewall
+ *				controller
+ *
+ * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or
+ * appropriate errno code if error occurred
+ */
+int stm32_firewall_grant_access(struct stm32_firewall *firewall);
+
+/**
+ * stm32_firewall_release_access - Release access granted from a call to
+ *				   stm32_firewall_grant_access().
+ *
+ * @firewall:			Firewall reference containing the ID to check against its firewall
+ *				controller
+ */
+void stm32_firewall_release_access(struct stm32_firewall *firewall);
+
+/**
+ * stm32_firewall_grant_access_by_id - Request firewall access rights of a given device
+ *				       based on a specific firewall ID
+ *
+ * Warnings:
+ * There is no way to ensure that the given ID will correspond to the firewall referenced in the
+ * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this
+ * function must be used with caution.
+ * This function should be used for subsystem resources that do not have the same firewall ID
+ * as their parent.
+ * U32_MAX is an invalid ID.
+ *
+ * @firewall:			Firewall reference containing the firewall controller
+ * @subsystem_id:		Firewall ID of the subsystem resource
+ *
+ * Returns 0 if access is granted, -EACCES if access is denied, -ENODEV if firewall is null or
+ * appropriate errno code if error occurred
+ */
+int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id);
+
+/**
+ * stm32_firewall_release_access_by_id - Release access granted from a call to
+ *					 stm32_firewall_grant_access_by_id().
+ *
+ * Warnings:
+ * There is no way to ensure that the given ID will correspond to the firewall referenced in the
+ * device node if the ID did not come from stm32_firewall_get_firewall(). In that case, this
+ * function must be used with caution.
+ * This function should be used for subsystem resources that do not have the same firewall ID
+ * as their parent.
+ * U32_MAX is an invalid ID.
+ *
+ * @firewall:			Firewall reference containing the firewall controller
+ * @subsystem_id:		Firewall ID of the subsystem resource
+ */
+void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall, u32 subsystem_id);
+
+#else /* CONFIG_STM32_FIREWALL */
+
+static inline int stm32_firewall_get_firewall(struct device_node *np,
+					      struct stm32_firewall *firewall,
+					      unsigned int nb_firewall)
+{
+	return -ENODEV;
+}
+
+static inline int stm32_firewall_grant_access(struct stm32_firewall *firewall)
+{
+	return -ENODEV;
+}
+
+static inline void stm32_firewall_release_access(struct stm32_firewall *firewall)
+{
+}
+
+static inline int stm32_firewall_grant_access_by_id(struct stm32_firewall *firewall,
+						    u32 subsystem_id)
+{
+	return -ENODEV;
+}
+
+static inline void stm32_firewall_release_access_by_id(struct stm32_firewall *firewall,
+						       u32 subsystem_id)
+{
+}
+
+#endif /* CONFIG_STM32_FIREWALL */
+#endif /* STM32_FIREWALL_DEVICE_H */
diff --git a/include/linux/bvec.h b/include/linux/bvec.h
index 555aae5448ae..3fc0efa0825b 100644
--- a/include/linux/bvec.h
+++ b/include/linux/bvec.h
@@ -22,11 +22,8 @@ struct page;
  * @bv_len:    Number of bytes in the address range.
  * @bv_offset: Start of the address range relative to the start of @bv_page.
  *
- * The following holds for a bvec if n * PAGE_SIZE < bv_offset + bv_len:
- *
- *   nth_page(@bv_page, n) == @bv_page + n
- *
- * This holds because page_is_mergeable() checks the above property.
+ * All pages within a bio_vec starting from @bv_page are contiguous and
+ * can simply be iterated (see bvec_advance()).
  */
 struct bio_vec {
 	struct page	*bv_page;
@@ -57,9 +54,12 @@ static inline void bvec_set_page(struct bio_vec *bv, struct page *page,
  * @offset:	offset into the folio
  */
 static inline void bvec_set_folio(struct bio_vec *bv, struct folio *folio,
-		unsigned int len, unsigned int offset)
+		size_t len, size_t offset)
 {
-	bvec_set_page(bv, &folio->page, len, offset);
+	unsigned long nr = offset / PAGE_SIZE;
+
+	WARN_ON_ONCE(len > UINT_MAX);
+	bvec_set_page(bv, folio_page(folio, nr), len, offset % PAGE_SIZE);
 }
 
 /**
@@ -83,7 +83,7 @@ struct bvec_iter {
 
 	unsigned int            bi_bvec_done;	/* number of bytes completed in
 						   current bvec */
-} __packed;
+} __packed __aligned(4);
 
 struct bvec_iter_all {
 	struct bio_vec	bv;
@@ -184,6 +184,12 @@ static inline void bvec_iter_advance_single(const struct bio_vec *bv,
 		((bvl = bvec_iter_bvec((bio_vec), (iter))), 1);	\
 	     bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len))
 
+#define for_each_mp_bvec(bvl, bio_vec, iter, start)			\
+	for (iter = (start);						\
+	     (iter).bi_size &&						\
+		((bvl = mp_bvec_iter_bvec((bio_vec), (iter))), 1);	\
+	     bvec_iter_advance_single((bio_vec), &(iter), (bvl).bv_len))
+
 /* for iterating one bio from start to end */
 #define BVEC_ITER_ALL_INIT (struct bvec_iter)				\
 {									\
@@ -280,4 +286,13 @@ static inline void *bvec_virt(struct bio_vec *bvec)
 	return page_address(bvec->bv_page) + bvec->bv_offset;
 }
 
+/**
+ * bvec_phys - return the physical address for a bvec
+ * @bvec: bvec to return the physical address for
+ */
+static inline phys_addr_t bvec_phys(const struct bio_vec *bvec)
+{
+	return page_to_phys(bvec->bv_page) + bvec->bv_offset;
+}
+
 #endif /* __LINUX_BVEC_H */
diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h
index c9a4c96c9943..55a44199de87 100644
--- a/include/linux/byteorder/generic.h
+++ b/include/linux/byteorder/generic.h
@@ -173,6 +173,38 @@ static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
 	}
 }
 
+static inline void le64_to_cpu_array(u64 *buf, unsigned int words)
+{
+	while (words--) {
+		__le64_to_cpus(buf);
+		buf++;
+	}
+}
+
+static inline void cpu_to_le64_array(u64 *buf, unsigned int words)
+{
+	while (words--) {
+		__cpu_to_le64s(buf);
+		buf++;
+	}
+}
+
+static inline void memcpy_from_le32(u32 *dst, const __le32 *src, size_t words)
+{
+	size_t i;
+
+	for (i = 0; i < words; i++)
+		dst[i] = le32_to_cpu(src[i]);
+}
+
+static inline void memcpy_to_le32(__le32 *dst, const u32 *src, size_t words)
+{
+	size_t i;
+
+	for (i = 0; i < words; i++)
+		dst[i] = cpu_to_le32(src[i]);
+}
+
 static inline void be16_add_cpu(__be16 *var, u16 val)
 {
 	*var = cpu_to_be16(be16_to_cpu(*var) + val);
diff --git a/include/linux/cache.h b/include/linux/cache.h
index 5da1bbd96154..e69768f50d53 100644
--- a/include/linux/cache.h
+++ b/include/linux/cache.h
@@ -3,14 +3,37 @@
 #define __LINUX_CACHE_H
 
 #include <uapi/linux/kernel.h>
+#include <vdso/cache.h>
 #include <asm/cache.h>
 
 #ifndef L1_CACHE_ALIGN
 #define L1_CACHE_ALIGN(x) __ALIGN_KERNEL(x, L1_CACHE_BYTES)
 #endif
 
-#ifndef SMP_CACHE_BYTES
-#define SMP_CACHE_BYTES L1_CACHE_BYTES
+/**
+ * SMP_CACHE_ALIGN - align a value to the L2 cacheline size
+ * @x: value to align
+ *
+ * On some architectures, L2 ("SMP") CL size is bigger than L1, and sometimes,
+ * this needs to be accounted.
+ *
+ * Return: aligned value.
+ */
+#ifndef SMP_CACHE_ALIGN
+#define SMP_CACHE_ALIGN(x)	ALIGN(x, SMP_CACHE_BYTES)
+#endif
+
+/*
+ * ``__aligned_largest`` aligns a field to the value most optimal for the
+ * target architecture to perform memory operations. Get the actual value
+ * to be able to use it anywhere else.
+ */
+#ifndef __LARGEST_ALIGN
+#define __LARGEST_ALIGN		sizeof(struct { long x; } __aligned_largest)
+#endif
+
+#ifndef LARGEST_ALIGN
+#define LARGEST_ALIGN(x)	ALIGN(x, __LARGEST_ALIGN)
 #endif
 
 /*
@@ -37,10 +60,6 @@
 #define __ro_after_init __section(".data..ro_after_init")
 #endif
 
-#ifndef ____cacheline_aligned
-#define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES)))
-#endif
-
 #ifndef ____cacheline_aligned_in_smp
 #ifdef CONFIG_SMP
 #define ____cacheline_aligned_in_smp ____cacheline_aligned
@@ -85,6 +104,64 @@
 #define cache_line_size()	L1_CACHE_BYTES
 #endif
 
+#ifndef __cacheline_group_begin
+#define __cacheline_group_begin(GROUP) \
+	__u8 __cacheline_group_begin__##GROUP[0]
+#endif
+
+#ifndef __cacheline_group_end
+#define __cacheline_group_end(GROUP) \
+	__u8 __cacheline_group_end__##GROUP[0]
+#endif
+
+/**
+ * __cacheline_group_begin_aligned - declare an aligned group start
+ * @GROUP: name of the group
+ * @...: optional group alignment
+ *
+ * The following block inside a struct:
+ *
+ *	__cacheline_group_begin_aligned(grp);
+ *	field a;
+ *	field b;
+ *	__cacheline_group_end_aligned(grp);
+ *
+ * will always be aligned to either the specified alignment or
+ * ``SMP_CACHE_BYTES``.
+ */
+#define __cacheline_group_begin_aligned(GROUP, ...)		\
+	__cacheline_group_begin(GROUP)				\
+	__aligned((__VA_ARGS__ + 0) ? : SMP_CACHE_BYTES)
+
+/**
+ * __cacheline_group_end_aligned - declare an aligned group end
+ * @GROUP: name of the group
+ * @...: optional alignment (same as was in __cacheline_group_begin_aligned())
+ *
+ * Note that the end marker is aligned to sizeof(long) to allow more precise
+ * size assertion. It also declares a padding at the end to avoid next field
+ * falling into this cacheline.
+ */
+#define __cacheline_group_end_aligned(GROUP, ...)		\
+	__cacheline_group_end(GROUP) __aligned(sizeof(long));	\
+	struct { } __cacheline_group_pad__##GROUP		\
+	__aligned((__VA_ARGS__ + 0) ? : SMP_CACHE_BYTES)
+
+#ifndef CACHELINE_ASSERT_GROUP_MEMBER
+#define CACHELINE_ASSERT_GROUP_MEMBER(TYPE, GROUP, MEMBER) \
+	BUILD_BUG_ON(!(offsetof(TYPE, MEMBER) >= \
+		       offsetofend(TYPE, __cacheline_group_begin__##GROUP) && \
+		       offsetofend(TYPE, MEMBER) <= \
+		       offsetof(TYPE, __cacheline_group_end__##GROUP)))
+#endif
+
+#ifndef CACHELINE_ASSERT_GROUP_SIZE
+#define CACHELINE_ASSERT_GROUP_SIZE(TYPE, GROUP, SIZE) \
+	BUILD_BUG_ON(offsetof(TYPE, __cacheline_group_end__##GROUP) - \
+		     offsetofend(TYPE, __cacheline_group_begin__##GROUP) > \
+		     SIZE)
+#endif
+
 /*
  * Helper to add padding within a struct to ensure data fall into separate
  * cachelines.
@@ -98,4 +175,10 @@ struct cacheline_padding {
 #define CACHELINE_PADDING(name)
 #endif
 
+#ifdef ARCH_DMA_MINALIGN
+#define ARCH_HAS_DMA_MINALIGN
+#else
+#define ARCH_DMA_MINALIGN __alignof__(unsigned long long)
+#endif
+
 #endif /* __LINUX_CACHE_H */
diff --git a/include/linux/cache_coherency.h b/include/linux/cache_coherency.h
new file mode 100644
index 000000000000..cc81c5733e31
--- /dev/null
+++ b/include/linux/cache_coherency.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Cache coherency maintenance operation device drivers
+ *
+ * Copyright Huawei 2025
+ */
+#ifndef _LINUX_CACHE_COHERENCY_H_
+#define _LINUX_CACHE_COHERENCY_H_
+
+#include <linux/list.h>
+#include <linux/kref.h>
+#include <linux/types.h>
+
+struct cc_inval_params {
+	phys_addr_t addr;
+	size_t size;
+};
+
+struct cache_coherency_ops_inst;
+
+struct cache_coherency_ops {
+	int (*wbinv)(struct cache_coherency_ops_inst *cci,
+		     struct cc_inval_params *invp);
+	int (*done)(struct cache_coherency_ops_inst *cci);
+};
+
+struct cache_coherency_ops_inst {
+	struct kref kref;
+	struct list_head node;
+	const struct cache_coherency_ops *ops;
+};
+
+int cache_coherency_ops_instance_register(struct cache_coherency_ops_inst *cci);
+void cache_coherency_ops_instance_unregister(struct cache_coherency_ops_inst *cci);
+
+struct cache_coherency_ops_inst *
+_cache_coherency_ops_instance_alloc(const struct cache_coherency_ops *ops,
+				    size_t size);
+/**
+ * cache_coherency_ops_instance_alloc - Allocate cache coherency ops instance
+ * @ops: Cache maintenance operations
+ * @drv_struct: structure that contains the struct cache_coherency_ops_inst
+ * @member: Name of the struct cache_coherency_ops_inst member in @drv_struct.
+ *
+ * This allocates a driver specific structure and initializes the
+ * cache_coherency_ops_inst embedded in the drv_struct. Upon success the
+ * pointer must be freed via cache_coherency_ops_instance_put().
+ *
+ * Returns a &drv_struct * on success, %NULL on error.
+ */
+#define cache_coherency_ops_instance_alloc(ops, drv_struct, member)	    \
+	({								    \
+		static_assert(__same_type(struct cache_coherency_ops_inst,  \
+					  ((drv_struct *)NULL)->member));   \
+		static_assert(offsetof(drv_struct, member) == 0);	    \
+		(drv_struct *)_cache_coherency_ops_instance_alloc(ops,	    \
+			sizeof(drv_struct));				    \
+	})
+void cache_coherency_ops_instance_put(struct cache_coherency_ops_inst *cci);
+
+#endif
diff --git a/include/linux/cacheflush.h b/include/linux/cacheflush.h
index a6189d21f2ba..55f297b2c23f 100644
--- a/include/linux/cacheflush.h
+++ b/include/linux/cacheflush.h
@@ -7,14 +7,23 @@
 struct folio;
 
 #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE
-#ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO
+#ifndef flush_dcache_folio
 void flush_dcache_folio(struct folio *folio);
 #endif
 #else
 static inline void flush_dcache_folio(struct folio *folio)
 {
 }
-#define ARCH_IMPLEMENTS_FLUSH_DCACHE_FOLIO 0
+#define flush_dcache_folio flush_dcache_folio
 #endif /* ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE */
 
+#ifndef flush_icache_pages
+static inline void flush_icache_pages(struct vm_area_struct *vma,
+				     struct page *page, unsigned int nr)
+{
+}
+#endif
+
+#define flush_icache_page(vma, page)	flush_icache_pages(vma, page, 1)
+
 #endif /* _LINUX_CACHEFLUSH_H */
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index a5cfd44fab45..c8f4f0a0b874 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -3,7 +3,8 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
-#include <linux/cpumask.h>
+#include <linux/cpuhplock.h>
+#include <linux/cpumask_types.h>
 #include <linux/smp.h>
 
 struct device_node;
@@ -73,6 +74,7 @@ struct cacheinfo {
 
 struct cpu_cacheinfo {
 	struct cacheinfo *info_list;
+	unsigned int per_cpu_data_slice_size;
 	unsigned int num_levels;
 	unsigned int num_leaves;
 	bool cpu_map_populated;
@@ -112,29 +114,55 @@ int acpi_get_cache_info(unsigned int cpu,
 const struct attribute_group *cache_get_priv_group(struct cacheinfo *this_leaf);
 
 /*
- * Get the id of the cache associated with @cpu at level @level.
+ * Get the cacheinfo structure for the cache associated with @cpu at
+ * level @level.
  * cpuhp lock must be held.
  */
-static inline int get_cpu_cacheinfo_id(int cpu, int level)
+static inline struct cacheinfo *get_cpu_cacheinfo_level(int cpu, int level)
 {
 	struct cpu_cacheinfo *ci = get_cpu_cacheinfo(cpu);
 	int i;
 
+	lockdep_assert_cpus_held();
+
 	for (i = 0; i < ci->num_leaves; i++) {
 		if (ci->info_list[i].level == level) {
 			if (ci->info_list[i].attributes & CACHE_ID)
-				return ci->info_list[i].id;
-			return -1;
+				return &ci->info_list[i];
+			return NULL;
 		}
 	}
 
-	return -1;
+	return NULL;
+}
+
+/*
+ * Get the id of the cache associated with @cpu at level @level.
+ * cpuhp lock must be held.
+ */
+static inline int get_cpu_cacheinfo_id(int cpu, int level)
+{
+	struct cacheinfo *ci = get_cpu_cacheinfo_level(cpu, level);
+
+	return ci ? ci->id : -1;
 }
 
-#ifdef CONFIG_ARM64
+#if defined(CONFIG_ARM64) || defined(CONFIG_ARM)
 #define use_arch_cache_info()	(true)
 #else
 #define use_arch_cache_info()	(false)
 #endif
 
+#ifndef CONFIG_ARCH_HAS_CPU_CACHE_ALIASING
+#define cpu_dcache_is_aliasing()	false
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
+#else
+#include <asm/cachetype.h>
+
+#ifndef cpu_icache_is_aliasing
+#define cpu_icache_is_aliasing()	cpu_dcache_is_aliasing()
+#endif
+
+#endif
+
 #endif /* _LINUX_CACHEINFO_H */
diff --git a/include/linux/call_once.h b/include/linux/call_once.h
new file mode 100644
index 000000000000..13cd6469e7e5
--- /dev/null
+++ b/include/linux/call_once.h
@@ -0,0 +1,66 @@
+#ifndef _LINUX_CALL_ONCE_H
+#define _LINUX_CALL_ONCE_H
+
+#include <linux/types.h>
+#include <linux/mutex.h>
+
+#define ONCE_NOT_STARTED 0
+#define ONCE_RUNNING     1
+#define ONCE_COMPLETED   2
+
+struct once {
+        atomic_t state;
+        struct mutex lock;
+};
+
+static inline void __once_init(struct once *once, const char *name,
+			       struct lock_class_key *key)
+{
+        atomic_set(&once->state, ONCE_NOT_STARTED);
+        __mutex_init(&once->lock, name, key);
+}
+
+#define once_init(once)							\
+do {									\
+	static struct lock_class_key __key;				\
+	__once_init((once), #once, &__key);				\
+} while (0)
+
+/*
+ * call_once - Ensure a function has been called exactly once
+ *
+ * @once: Tracking struct
+ * @cb: Function to be called
+ *
+ * If @once has never completed successfully before, call @cb and, if
+ * it returns a zero or positive value, mark @once as completed.  Return
+ * the value returned by @cb
+ *
+ * If @once has completed succesfully before, return 0.
+ *
+ * The call to @cb is implicitly surrounded by a mutex, though for
+ * efficiency the * function avoids taking it after the first call.
+ */
+static inline int call_once(struct once *once, int (*cb)(struct once *))
+{
+	int r, state;
+
+	/* Pairs with atomic_set_release() below.  */
+	if (atomic_read_acquire(&once->state) == ONCE_COMPLETED)
+		return 0;
+
+	guard(mutex)(&once->lock);
+	state = atomic_read(&once->state);
+	if (unlikely(state != ONCE_NOT_STARTED))
+		return WARN_ON_ONCE(state != ONCE_COMPLETED) ? -EINVAL : 0;
+
+	atomic_set(&once->state, ONCE_RUNNING);
+	r = cb(once);
+	if (r < 0)
+		atomic_set(&once->state, ONCE_NOT_STARTED);
+	else
+		atomic_set_release(&once->state, ONCE_COMPLETED);
+	return r;
+}
+
+#endif /* _LINUX_CALL_ONCE_H */
diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h
index 9b8a9c39614b..726d909e87ce 100644
--- a/include/linux/can/bittiming.h
+++ b/include/linux/can/bittiming.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0-only */
 /* Copyright (c) 2020 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
- * Copyright (c) 2021 Vincent Mailhol <mailhol.vincent@wanadoo.fr>
+ * Copyright (c) 2021-2025 Vincent Mailhol <mailhol@kernel.org>
  */
 
 #ifndef _CAN_BITTIMING_H
@@ -14,8 +14,14 @@
 #define CAN_BITRATE_UNSET 0
 #define CAN_BITRATE_UNKNOWN (-1U)
 
-#define CAN_CTRLMODE_TDC_MASK					\
+#define CAN_CTRLMODE_FD_TDC_MASK				\
 	(CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL)
+#define CAN_CTRLMODE_XL_TDC_MASK				\
+	(CAN_CTRLMODE_XL_TDC_AUTO | CAN_CTRLMODE_XL_TDC_MANUAL)
+#define CAN_CTRLMODE_TDC_AUTO_MASK				\
+	(CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_XL_TDC_AUTO)
+#define CAN_CTRLMODE_TDC_MANUAL_MASK				\
+	(CAN_CTRLMODE_TDC_MANUAL | CAN_CTRLMODE_XL_TDC_MANUAL)
 
 /*
  * struct can_tdc - CAN FD Transmission Delay Compensation parameters
@@ -81,6 +87,11 @@ struct can_tdc {
 	u32 tdcf;
 };
 
+/* The transceiver decoding margin corresponds to t_Decode in ISO 11898-2 */
+#define CAN_PWM_DECODE_NS 5
+/* Maximum PWM symbol duration. Corresponds to t_SymbolNom_MAX - t_Decode */
+#define CAN_PWM_NS_MAX (205 - CAN_PWM_DECODE_NS)
+
 /*
  * struct can_tdc_const - CAN hardware-dependent constant for
  *	Transmission Delay Compensation
@@ -114,27 +125,85 @@ struct can_tdc_const {
 	u32 tdcf_max;
 };
 
+/*
+ * struct can_pwm - CAN Pulse-Width Modulation (PWM) parameters
+ *
+ * @pwms: pulse width modulation short phase
+ * @pwml: pulse width modulation long phase
+ * @pwmo: pulse width modulation offset
+ */
+struct can_pwm {
+	u32 pwms;
+	u32 pwml;
+	u32 pwmo;
+};
+
+/*
+ * struct can_pwm - CAN hardware-dependent constants for Pulse-Width
+ *	Modulation (PWM)
+ *
+ * @pwms_min: PWM short phase minimum value. Must be at least 1.
+ * @pwms_max: PWM short phase maximum value
+ * @pwml_min: PWM long phase minimum value. Must be at least 1.
+ * @pwml_max: PWM long phase maximum value
+ * @pwmo_min: PWM offset phase minimum value
+ * @pwmo_max: PWM offset phase maximum value
+ */
+struct can_pwm_const {
+	u32 pwms_min;
+	u32 pwms_max;
+	u32 pwml_min;
+	u32 pwml_max;
+	u32 pwmo_min;
+	u32 pwmo_max;
+};
+
+struct data_bittiming_params {
+	const struct can_bittiming_const *data_bittiming_const;
+	struct can_bittiming data_bittiming;
+	const struct can_tdc_const *tdc_const;
+	const struct can_pwm_const *pwm_const;
+	union {
+		struct can_tdc tdc;
+		struct can_pwm pwm;
+	};
+	const u32 *data_bitrate_const;
+	unsigned int data_bitrate_const_cnt;
+	int (*do_set_data_bittiming)(struct net_device *dev);
+	int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv);
+};
+
 #ifdef CONFIG_CAN_CALC_BITTIMING
 int can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 		       const struct can_bittiming_const *btc, struct netlink_ext_ack *extack);
 
 void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const,
 		   const struct can_bittiming *dbt,
-		   u32 *ctrlmode, u32 ctrlmode_supported);
+		   u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported);
+
+int can_calc_pwm(struct net_device *dev, struct netlink_ext_ack *extack);
 #else /* !CONFIG_CAN_CALC_BITTIMING */
 static inline int
 can_calc_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 		   const struct can_bittiming_const *btc, struct netlink_ext_ack *extack)
 {
-	netdev_err(dev, "bit-timing calculation not available\n");
+	NL_SET_ERR_MSG(extack, "bit-timing calculation not available\n");
 	return -EINVAL;
 }
 
 static inline void
 can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const,
 	      const struct can_bittiming *dbt,
-	      u32 *ctrlmode, u32 ctrlmode_supported)
+	      u32 tdc_mask, u32 *ctrlmode, u32 ctrlmode_supported)
+{
+}
+
+static inline int
+can_calc_pwm(struct net_device *dev, struct netlink_ext_ack *extack)
 {
+	NL_SET_ERR_MSG(extack,
+		       "bit-timing calculation not available: manually provide PWML and PWMS\n");
+	return -EINVAL;
 }
 #endif /* CONFIG_CAN_CALC_BITTIMING */
 
@@ -149,6 +218,39 @@ int can_get_bittiming(const struct net_device *dev, struct can_bittiming *bt,
 		      const unsigned int bitrate_const_cnt,
 		      struct netlink_ext_ack *extack);
 
+int can_validate_pwm_bittiming(const struct net_device *dev,
+			       const struct can_pwm *pwm,
+			       struct netlink_ext_ack *extack);
+
+/*
+ * can_get_relative_tdco() - TDCO relative to the sample point
+ *
+ * struct can_tdc::tdco represents the absolute offset from TDCV. Some
+ * controllers use instead an offset relative to the Sample Point (SP)
+ * such that:
+ *
+ * SSP = TDCV + absolute TDCO
+ *     = TDCV + SP + relative TDCO
+ *
+ * -+----------- one bit ----------+-- TX pin
+ *  |<--- Sample Point --->|
+ *
+ *                         --+----------- one bit ----------+-- RX pin
+ *  |<-------- TDCV -------->|
+ *                           |<------------------------>| absolute TDCO
+ *                           |<--- Sample Point --->|
+ *                           |                      |<->| relative TDCO
+ *  |<------------- Secondary Sample Point ------------>|
+ */
+static inline s32 can_get_relative_tdco(const struct data_bittiming_params *dbt_params)
+{
+	const struct can_bittiming *dbt = &dbt_params->data_bittiming;
+	s32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg +
+				  dbt->phase_seg1) * dbt->brp;
+
+	return (s32)dbt_params->tdc.tdco - sample_point_in_tc;
+}
+
 /*
  * can_bit_time() - Duration of one bit
  *
@@ -162,4 +264,17 @@ static inline unsigned int can_bit_time(const struct can_bittiming *bt)
 	return CAN_SYNC_SEG + bt->prop_seg + bt->phase_seg1 + bt->phase_seg2;
 }
 
+/* Duration of one bit in minimum time quantum */
+static inline unsigned int can_bit_time_tqmin(const struct can_bittiming *bt)
+{
+	return can_bit_time(bt) * bt->brp;
+}
+
+/* Convert a duration from minimum a minimum time quantum to nano seconds */
+static inline u32 can_tqmin_to_ns(u32 tqmin, u32 clock_freq)
+{
+	return DIV_U64_ROUND_CLOSEST(mul_u32_u32(tqmin, NSEC_PER_SEC),
+				     clock_freq);
+}
+
 #endif /* !_CAN_BITTIMING_H */
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 982ba245eb41..f6416a56e95d 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -45,16 +45,11 @@ struct can_priv {
 	struct net_device *dev;
 	struct can_device_stats can_stats;
 
-	const struct can_bittiming_const *bittiming_const,
-		*data_bittiming_const;
-	struct can_bittiming bittiming, data_bittiming;
-	const struct can_tdc_const *tdc_const;
-	struct can_tdc tdc;
-
+	const struct can_bittiming_const *bittiming_const;
+	struct can_bittiming bittiming;
+	struct data_bittiming_params fd, xl;
 	unsigned int bitrate_const_cnt;
 	const u32 *bitrate_const;
-	const u32 *data_bitrate_const;
-	unsigned int data_bitrate_const_cnt;
 	u32 bitrate_max;
 	struct can_clock clock;
 
@@ -77,69 +72,22 @@ struct can_priv {
 	struct delayed_work restart_work;
 
 	int (*do_set_bittiming)(struct net_device *dev);
-	int (*do_set_data_bittiming)(struct net_device *dev);
 	int (*do_set_mode)(struct net_device *dev, enum can_mode mode);
 	int (*do_set_termination)(struct net_device *dev, u16 term);
 	int (*do_get_state)(const struct net_device *dev,
 			    enum can_state *state);
 	int (*do_get_berr_counter)(const struct net_device *dev,
 				   struct can_berr_counter *bec);
-	int (*do_get_auto_tdcv)(const struct net_device *dev, u32 *tdcv);
 };
 
-static inline bool can_tdc_is_enabled(const struct can_priv *priv)
+static inline bool can_fd_tdc_is_enabled(const struct can_priv *priv)
 {
-	return !!(priv->ctrlmode & CAN_CTRLMODE_TDC_MASK);
+	return !!(priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK);
 }
 
-/*
- * can_get_relative_tdco() - TDCO relative to the sample point
- *
- * struct can_tdc::tdco represents the absolute offset from TDCV. Some
- * controllers use instead an offset relative to the Sample Point (SP)
- * such that:
- *
- * SSP = TDCV + absolute TDCO
- *     = TDCV + SP + relative TDCO
- *
- * -+----------- one bit ----------+-- TX pin
- *  |<--- Sample Point --->|
- *
- *                         --+----------- one bit ----------+-- RX pin
- *  |<-------- TDCV -------->|
- *                           |<------------------------>| absolute TDCO
- *                           |<--- Sample Point --->|
- *                           |                      |<->| relative TDCO
- *  |<------------- Secondary Sample Point ------------>|
- */
-static inline s32 can_get_relative_tdco(const struct can_priv *priv)
+static inline bool can_xl_tdc_is_enabled(const struct can_priv *priv)
 {
-	const struct can_bittiming *dbt = &priv->data_bittiming;
-	s32 sample_point_in_tc = (CAN_SYNC_SEG + dbt->prop_seg +
-				  dbt->phase_seg1) * dbt->brp;
-
-	return (s32)priv->tdc.tdco - sample_point_in_tc;
-}
-
-/* helper to define static CAN controller features at device creation time */
-static inline int __must_check can_set_static_ctrlmode(struct net_device *dev,
-						       u32 static_mode)
-{
-	struct can_priv *priv = netdev_priv(dev);
-
-	/* alloc_candev() succeeded => netdev_priv() is valid at this point */
-	if (priv->ctrlmode_supported & static_mode) {
-		netdev_warn(dev,
-			    "Controller features can not be supported and static at the same time\n");
-		return -EINVAL;
-	}
-	priv->ctrlmode = static_mode;
-
-	/* override MTU which was set by default in can_setup()? */
-	if (static_mode & CAN_CTRLMODE_FD)
-		dev->mtu = CANFD_MTU;
-
-	return 0;
+	return !!(priv->ctrlmode & CAN_CTRLMODE_XL_TDC_MASK);
 }
 
 static inline u32 can_get_static_ctrlmode(struct can_priv *priv)
@@ -152,22 +100,6 @@ static inline bool can_is_canxl_dev_mtu(unsigned int mtu)
 	return (mtu >= CANXL_MIN_MTU && mtu <= CANXL_MAX_MTU);
 }
 
-/* drop skb if it does not contain a valid CAN frame for sending */
-static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb)
-{
-	struct can_priv *priv = netdev_priv(dev);
-
-	if (priv->ctrlmode & CAN_CTRLMODE_LISTENONLY) {
-		netdev_info_once(dev,
-				 "interface in listen only mode, dropping skb\n");
-		kfree_skb(skb);
-		dev->stats.tx_dropped++;
-		return true;
-	}
-
-	return can_dropped_invalid_skb(dev, skb);
-}
-
 void can_setup(struct net_device *dev);
 
 struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
@@ -179,14 +111,27 @@ struct net_device *alloc_candev_mqs(int sizeof_priv, unsigned int echo_skb_max,
 void free_candev(struct net_device *dev);
 
 /* a candev safe wrapper around netdev_priv */
+#if IS_ENABLED(CONFIG_CAN_NETLINK)
 struct can_priv *safe_candev_priv(struct net_device *dev);
+#else
+static inline struct can_priv *safe_candev_priv(struct net_device *dev)
+{
+	return NULL;
+}
+#endif
 
 int open_candev(struct net_device *dev);
 void close_candev(struct net_device *dev);
-int can_change_mtu(struct net_device *dev, int new_mtu);
-int can_eth_ioctl_hwts(struct net_device *netdev, struct ifreq *ifr, int cmd);
+void can_set_default_mtu(struct net_device *dev);
+int __must_check can_set_static_ctrlmode(struct net_device *dev,
+					 u32 static_mode);
+int can_hwtstamp_get(struct net_device *netdev,
+		     struct kernel_hwtstamp_config *cfg);
+int can_hwtstamp_set(struct net_device *netdev,
+		     struct kernel_hwtstamp_config *cfg,
+		     struct netlink_ext_ack *extack);
 int can_ethtool_op_get_ts_info_hwts(struct net_device *dev,
-				    struct ethtool_ts_info *info);
+				    struct kernel_ethtool_ts_info *info);
 
 int register_candev(struct net_device *dev);
 void unregister_candev(struct net_device *dev);
@@ -195,6 +140,57 @@ int can_restart_now(struct net_device *dev);
 void can_bus_off(struct net_device *dev);
 
 const char *can_get_state_str(const enum can_state state);
+const char *can_get_ctrlmode_str(u32 ctrlmode);
+
+static inline bool can_dev_in_xl_only_mode(struct can_priv *priv)
+{
+	const u32 mixed_mode = CAN_CTRLMODE_FD | CAN_CTRLMODE_XL;
+
+	/* When CAN XL is enabled but FD is disabled we are running in
+	 * the so-called 'CANXL-only mode' where the error signalling is
+	 * disabled. This helper function determines the required value
+	 * to disable error signalling in the CAN XL controller.
+	 * The so-called CC/FD/XL 'mixed mode' requires error signalling.
+	 */
+	return ((priv->ctrlmode & mixed_mode) == CAN_CTRLMODE_XL);
+}
+
+/* drop skb if it does not contain a valid CAN frame for sending */
+static inline bool can_dev_dropped_skb(struct net_device *dev, struct sk_buff *skb)
+{
+	struct can_priv *priv = netdev_priv(dev);
+	u32 silent_mode = priv->ctrlmode & (CAN_CTRLMODE_LISTENONLY |
+					    CAN_CTRLMODE_RESTRICTED);
+
+	if (silent_mode) {
+		netdev_info_once(dev, "interface in %s mode, dropping skb\n",
+				 can_get_ctrlmode_str(silent_mode));
+		goto invalid_skb;
+	}
+
+	if (!(priv->ctrlmode & CAN_CTRLMODE_FD) && can_is_canfd_skb(skb)) {
+		netdev_info_once(dev, "CAN FD is disabled, dropping skb\n");
+		goto invalid_skb;
+	}
+
+	if (can_dev_in_xl_only_mode(priv) && !can_is_canxl_skb(skb)) {
+		netdev_info_once(dev,
+				 "Error signaling is disabled, dropping skb\n");
+		goto invalid_skb;
+	}
+
+	return can_dropped_invalid_skb(dev, skb);
+
+invalid_skb:
+	kfree_skb(skb);
+	dev->stats.tx_dropped++;
+	return true;
+}
+
+void can_state_get_by_berr_counter(const struct net_device *dev,
+				   const struct can_berr_counter *bec,
+				   enum can_state *tx_state,
+				   enum can_state *rx_state);
 void can_change_state(struct net_device *dev, struct can_frame *cf,
 		      enum can_state tx_state, enum can_state rx_state);
 
diff --git a/include/linux/can/dev/peak_canfd.h b/include/linux/can/dev/peak_canfd.h
index f38772fd0c07..d3788a3d0942 100644
--- a/include/linux/can/dev/peak_canfd.h
+++ b/include/linux/can/dev/peak_canfd.h
@@ -2,8 +2,8 @@
 /*
  * CAN driver for PEAK System micro-CAN based adapters
  *
- * Copyright (C) 2003-2011 PEAK System-Technik GmbH
- * Copyright (C) 2011-2013 Stephane Grosjean <s.grosjean@peak-system.com>
+ * Copyright (C) 2003-2025 PEAK System-Technik GmbH
+ * Author: Stéphane Grosjean <stephane.grosjean@hms-networks.com>
  */
 #ifndef PUCAN_H
 #define PUCAN_H
diff --git a/include/linux/can/length.h b/include/linux/can/length.h
index 6995092b774e..abc978b38f79 100644
--- a/include/linux/can/length.h
+++ b/include/linux/can/length.h
@@ -1,126 +1,258 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Copyright (C) 2020 Oliver Hartkopp <socketcan@hartkopp.net>
  * Copyright (C) 2020 Marc Kleine-Budde <kernel@pengutronix.de>
+ * Copyright (C) 2020, 2023 Vincent Mailhol <mailhol.vincent@wanadoo.fr>
  */
 
 #ifndef _CAN_LENGTH_H
 #define _CAN_LENGTH_H
 
+#include <linux/bits.h>
+#include <linux/can.h>
+#include <linux/can/netlink.h>
+#include <linux/math.h>
+
 /*
- * Size of a Classical CAN Standard Frame
+ * Size of a Classical CAN Standard Frame header in bits
  *
- * Name of Field			Bits
+ * Name of Field				Bits
  * ---------------------------------------------------------
- * Start-of-frame			1
- * Identifier				11
- * Remote transmission request (RTR)	1
- * Identifier extension bit (IDE)	1
- * Reserved bit (r0)			1
- * Data length code (DLC)		4
- * Data field				0...64
- * CRC					15
- * CRC delimiter			1
- * ACK slot				1
- * ACK delimiter			1
- * End-of-frame (EOF)			7
- * Inter frame spacing			3
+ * Start Of Frame (SOF)				1
+ * Arbitration field:
+ *	base ID					11
+ *	Remote Transmission Request (RTR)	1
+ * Control field:
+ *	IDentifier Extension bit (IDE)		1
+ *	FD Format indicator (FDF)		1
+ *	Data Length Code (DLC)			4
+ *
+ * including all fields preceding the data field, ignoring bitstuffing
+ */
+#define CAN_FRAME_HEADER_SFF_BITS 19
+
+/*
+ * Size of a Classical CAN Extended Frame header in bits
+ *
+ * Name of Field				Bits
+ * ---------------------------------------------------------
+ * Start Of Frame (SOF)				1
+ * Arbitration field:
+ *	base ID					11
+ *	Substitute Remote Request (SRR)		1
+ *	IDentifier Extension bit (IDE)		1
+ *	ID extension				18
+ *	Remote Transmission Request (RTR)	1
+ * Control field:
+ *	FD Format indicator (FDF)		1
+ *	Reserved bit (r0)			1
+ *	Data length code (DLC)			4
+ *
+ * including all fields preceding the data field, ignoring bitstuffing
+ */
+#define CAN_FRAME_HEADER_EFF_BITS 39
+
+/*
+ * Size of a CAN-FD Standard Frame in bits
  *
- * rounded up and ignoring bitstuffing
+ * Name of Field				Bits
+ * ---------------------------------------------------------
+ * Start Of Frame (SOF)				1
+ * Arbitration field:
+ *	base ID					11
+ *	Remote Request Substitution (RRS)	1
+ * Control field:
+ *	IDentifier Extension bit (IDE)		1
+ *	FD Format indicator (FDF)		1
+ *	Reserved bit (res)			1
+ *	Bit Rate Switch (BRS)			1
+ *	Error Status Indicator (ESI)		1
+ *	Data length code (DLC)			4
+ *
+ * including all fields preceding the data field, ignoring bitstuffing
+ */
+#define CANFD_FRAME_HEADER_SFF_BITS 22
+
+/*
+ * Size of a CAN-FD Extended Frame in bits
+ *
+ * Name of Field				Bits
+ * ---------------------------------------------------------
+ * Start Of Frame (SOF)				1
+ * Arbitration field:
+ *	base ID					11
+ *	Substitute Remote Request (SRR)		1
+ *	IDentifier Extension bit (IDE)		1
+ *	ID extension				18
+ *	Remote Request Substitution (RRS)	1
+ * Control field:
+ *	FD Format indicator (FDF)		1
+ *	Reserved bit (res)			1
+ *	Bit Rate Switch (BRS)			1
+ *	Error Status Indicator (ESI)		1
+ *	Data length code (DLC)			4
+ *
+ * including all fields preceding the data field, ignoring bitstuffing
  */
-#define CAN_FRAME_OVERHEAD_SFF DIV_ROUND_UP(47, 8)
+#define CANFD_FRAME_HEADER_EFF_BITS 41
 
 /*
- * Size of a Classical CAN Extended Frame
+ * Size of a CAN CRC Field in bits
  *
  * Name of Field			Bits
  * ---------------------------------------------------------
- * Start-of-frame			1
- * Identifier A				11
- * Substitute remote request (SRR)	1
- * Identifier extension bit (IDE)	1
- * Identifier B				18
- * Remote transmission request (RTR)	1
- * Reserved bits (r1, r0)		2
- * Data length code (DLC)		4
- * Data field				0...64
- * CRC					15
- * CRC delimiter			1
- * ACK slot				1
- * ACK delimiter			1
- * End-of-frame (EOF)			7
- * Inter frame spacing			3
+ * CRC sequence (CRC15)			15
+ * CRC Delimiter			1
  *
- * rounded up and ignoring bitstuffing
+ * ignoring bitstuffing
  */
-#define CAN_FRAME_OVERHEAD_EFF DIV_ROUND_UP(67, 8)
+#define CAN_FRAME_CRC_FIELD_BITS 16
 
 /*
- * Size of a CAN-FD Standard Frame
+ * Size of a CAN-FD CRC17 Field in bits (length: 0..16)
  *
  * Name of Field			Bits
  * ---------------------------------------------------------
- * Start-of-frame			1
- * Identifier				11
- * Reserved bit (r1)			1
- * Identifier extension bit (IDE)	1
- * Flexible data rate format (FDF)	1
- * Reserved bit (r0)			1
- * Bit Rate Switch (BRS)		1
- * Error Status Indicator (ESI)		1
- * Data length code (DLC)		4
- * Data field				0...512
- * Stuff Bit Count (SBC)		0...16: 4 20...64:5
- * CRC					0...16: 17 20...64:21
- * CRC delimiter (CD)			1
- * ACK slot (AS)			1
- * ACK delimiter (AD)			1
- * End-of-frame (EOF)			7
- * Inter frame spacing			3
- *
- * assuming CRC21, rounded up and ignoring bitstuffing
- */
-#define CANFD_FRAME_OVERHEAD_SFF DIV_ROUND_UP(61, 8)
+ * Stuff Count				4
+ * CRC Sequence (CRC17)			17
+ * CRC Delimiter			1
+ * Fixed stuff bits			6
+ */
+#define CANFD_FRAME_CRC17_FIELD_BITS 28
 
 /*
- * Size of a CAN-FD Extended Frame
+ * Size of a CAN-FD CRC21 Field in bits (length: 20..64)
  *
  * Name of Field			Bits
  * ---------------------------------------------------------
- * Start-of-frame			1
- * Identifier A				11
- * Substitute remote request (SRR)	1
- * Identifier extension bit (IDE)	1
- * Identifier B				18
- * Reserved bit (r1)			1
- * Flexible data rate format (FDF)	1
- * Reserved bit (r0)			1
- * Bit Rate Switch (BRS)		1
- * Error Status Indicator (ESI)		1
- * Data length code (DLC)		4
- * Data field				0...512
- * Stuff Bit Count (SBC)		0...16: 4 20...64:5
- * CRC					0...16: 17 20...64:21
- * CRC delimiter (CD)			1
- * ACK slot (AS)			1
- * ACK delimiter (AD)			1
- * End-of-frame (EOF)			7
- * Inter frame spacing			3
- *
- * assuming CRC21, rounded up and ignoring bitstuffing
- */
-#define CANFD_FRAME_OVERHEAD_EFF DIV_ROUND_UP(80, 8)
+ * Stuff Count				4
+ * CRC sequence (CRC21)			21
+ * CRC Delimiter			1
+ * Fixed stuff bits			7
+ */
+#define CANFD_FRAME_CRC21_FIELD_BITS 33
+
+/*
+ * Size of a CAN(-FD) Frame footer in bits
+ *
+ * Name of Field			Bits
+ * ---------------------------------------------------------
+ * ACK slot				1
+ * ACK delimiter			1
+ * End Of Frame (EOF)			7
+ *
+ * including all fields following the CRC field
+ */
+#define CAN_FRAME_FOOTER_BITS 9
+
+/*
+ * First part of the Inter Frame Space
+ * (a.k.a. IMF - intermission field)
+ */
+#define CAN_INTERMISSION_BITS 3
+
+/**
+ * can_bitstuffing_len() - Calculate the maximum length with bitstuffing
+ * @destuffed_len: length of a destuffed bit stream
+ *
+ * The worst bit stuffing case is a sequence in which dominant and
+ * recessive bits alternate every four bits:
+ *
+ *   Destuffed: 1 1111  0000  1111  0000  1111
+ *   Stuffed:   1 1111o 0000i 1111o 0000i 1111o
+ *
+ * Nomenclature
+ *
+ *  - "0": dominant bit
+ *  - "o": dominant stuff bit
+ *  - "1": recessive bit
+ *  - "i": recessive stuff bit
+ *
+ * Aside from the first bit, one stuff bit is added every four bits.
+ *
+ * Return: length of the stuffed bit stream in the worst case scenario.
+ */
+#define can_bitstuffing_len(destuffed_len)			\
+	(destuffed_len + (destuffed_len - 1) / 4)
+
+#define __can_bitstuffing_len(bitstuffing, destuffed_len)	\
+	(bitstuffing ? can_bitstuffing_len(destuffed_len) :	\
+		       destuffed_len)
+
+#define __can_cc_frame_bits(is_eff, bitstuffing,		\
+			    intermission, data_len)		\
+(								\
+	__can_bitstuffing_len(bitstuffing,			\
+		(is_eff ? CAN_FRAME_HEADER_EFF_BITS :		\
+			  CAN_FRAME_HEADER_SFF_BITS) +		\
+		(data_len) * BITS_PER_BYTE +			\
+		CAN_FRAME_CRC_FIELD_BITS) +			\
+	CAN_FRAME_FOOTER_BITS +					\
+	(intermission ? CAN_INTERMISSION_BITS : 0)		\
+)
+
+#define __can_fd_frame_bits(is_eff, bitstuffing,		\
+			    intermission, data_len)		\
+(								\
+	__can_bitstuffing_len(bitstuffing,			\
+		(is_eff ? CANFD_FRAME_HEADER_EFF_BITS :		\
+			  CANFD_FRAME_HEADER_SFF_BITS) +	\
+		(data_len) * BITS_PER_BYTE) +			\
+	((data_len) <= 16 ?					\
+		CANFD_FRAME_CRC17_FIELD_BITS :			\
+		CANFD_FRAME_CRC21_FIELD_BITS) +			\
+	CAN_FRAME_FOOTER_BITS +					\
+	(intermission ? CAN_INTERMISSION_BITS : 0)		\
+)
+
+/**
+ * can_frame_bits() - Calculate the number of bits on the wire in a
+ *	CAN frame
+ * @is_fd: true: CAN-FD frame; false: Classical CAN frame.
+ * @is_eff: true: Extended frame; false: Standard frame.
+ * @bitstuffing: true: calculate the bitstuffing worst case; false:
+ *	calculate the bitstuffing best case (no dynamic
+ *	bitstuffing). CAN-FD's fixed stuff bits are always included.
+ * @intermission: if and only if true, include the inter frame space
+ *	assuming no bus idle (i.e. only the intermission). Strictly
+ *	speaking, the inter frame space is not part of the
+ *	frame. However, it is needed when calculating the delay
+ *	between the Start Of Frame of two consecutive frames.
+ * @data_len: length of the data field in bytes. Correspond to
+ *	can(fd)_frame->len. Should be zero for remote frames. No
+ *	sanitization is done on @data_len and it shall have no side
+ *	effects.
+ *
+ * Return: the numbers of bits on the wire of a CAN frame.
+ */
+#define can_frame_bits(is_fd, is_eff, bitstuffing,		\
+		       intermission, data_len)			\
+(								\
+	is_fd ? __can_fd_frame_bits(is_eff, bitstuffing,	\
+				    intermission, data_len) :	\
+		__can_cc_frame_bits(is_eff, bitstuffing,	\
+				    intermission, data_len)	\
+)
+
+/*
+ * Number of bytes in a CAN frame
+ * (rounded up, including intermission)
+ */
+#define can_frame_bytes(is_fd, is_eff, bitstuffing, data_len)	\
+	DIV_ROUND_UP(can_frame_bits(is_fd, is_eff, bitstuffing,	\
+				    true, data_len),		\
+		     BITS_PER_BYTE)
 
 /*
  * Maximum size of a Classical CAN frame
- * (rounded up and ignoring bitstuffing)
+ * (rounded up, ignoring bitstuffing but including intermission)
  */
-#define CAN_FRAME_LEN_MAX (CAN_FRAME_OVERHEAD_EFF + CAN_MAX_DLEN)
+#define CAN_FRAME_LEN_MAX can_frame_bytes(false, true, false, CAN_MAX_DLEN)
 
 /*
  * Maximum size of a CAN-FD frame
- * (rounded up and ignoring bitstuffing)
+ * (rounded up, ignoring dynamic bitstuffing but including intermission)
  */
-#define CANFD_FRAME_LEN_MAX (CANFD_FRAME_OVERHEAD_EFF + CANFD_MAX_DLEN)
+#define CANFD_FRAME_LEN_MAX can_frame_bytes(true, true, false, CANFD_MAX_DLEN)
 
 /*
  * can_cc_dlc2len(value) - convert a given data length code (dlc) of a
diff --git a/include/linux/can/rx-offload.h b/include/linux/can/rx-offload.h
index c205c51d79c9..d29bb4521947 100644
--- a/include/linux/can/rx-offload.h
+++ b/include/linux/can/rx-offload.h
@@ -3,7 +3,7 @@
  * linux/can/rx-offload.h
  *
  * Copyright (c) 2014 David Jander, Protonic Holland
- * Copyright (c) 2014-2017 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
+ * Copyright (c) 2014-2017, 2023 Pengutronix, Marc Kleine-Budde <kernel@pengutronix.de>
  */
 
 #ifndef _CAN_RX_OFFLOAD_H
@@ -44,11 +44,14 @@ int can_rx_offload_irq_offload_timestamp(struct can_rx_offload *offload,
 int can_rx_offload_irq_offload_fifo(struct can_rx_offload *offload);
 int can_rx_offload_queue_timestamp(struct can_rx_offload *offload,
 				   struct sk_buff *skb, u32 timestamp);
-unsigned int can_rx_offload_get_echo_skb(struct can_rx_offload *offload,
-					 unsigned int idx, u32 timestamp,
-					 unsigned int *frame_len_ptr);
+unsigned int can_rx_offload_get_echo_skb_queue_timestamp(struct can_rx_offload *offload,
+							 unsigned int idx, u32 timestamp,
+							 unsigned int *frame_len_ptr);
 int can_rx_offload_queue_tail(struct can_rx_offload *offload,
 			      struct sk_buff *skb);
+unsigned int can_rx_offload_get_echo_skb_queue_tail(struct can_rx_offload *offload,
+						    unsigned int idx,
+						    unsigned int *frame_len_ptr);
 void can_rx_offload_irq_finish(struct can_rx_offload *offload);
 void can_rx_offload_threaded_irq_finish(struct can_rx_offload *offload);
 void can_rx_offload_del(struct can_rx_offload *offload);
diff --git a/include/linux/capability.h b/include/linux/capability.h
index 0c356a517991..1fb08922552c 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -139,7 +139,6 @@ static inline kernel_cap_t cap_raise_nfsd_set(const kernel_cap_t a,
 }
 
 #ifdef CONFIG_MULTIUSER
-extern bool has_capability(struct task_struct *t, int cap);
 extern bool has_ns_capability(struct task_struct *t,
 			      struct user_namespace *ns, int cap);
 extern bool has_capability_noaudit(struct task_struct *t, int cap);
@@ -150,10 +149,6 @@ extern bool ns_capable(struct user_namespace *ns, int cap);
 extern bool ns_capable_noaudit(struct user_namespace *ns, int cap);
 extern bool ns_capable_setid(struct user_namespace *ns, int cap);
 #else
-static inline bool has_capability(struct task_struct *t, int cap)
-{
-	return true;
-}
 static inline bool has_ns_capability(struct task_struct *t,
 			      struct user_namespace *ns, int cap)
 {
diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h
index cb0d6cd1c12f..559353ad64ac 100644
--- a/include/linux/cc_platform.h
+++ b/include/linux/cc_platform.h
@@ -74,7 +74,7 @@ enum cc_attr {
 	CC_ATTR_GUEST_UNROLL_STRING_IO,
 
 	/**
-	 * @CC_ATTR_SEV_SNP: Guest SNP is active.
+	 * @CC_ATTR_GUEST_SEV_SNP: Guest SNP is active.
 	 *
 	 * The platform/OS is running as a guest/virtual machine and actively
 	 * using AMD SEV-SNP features.
@@ -82,14 +82,28 @@ enum cc_attr {
 	CC_ATTR_GUEST_SEV_SNP,
 
 	/**
-	 * @CC_ATTR_HOTPLUG_DISABLED: Hotplug is not supported or disabled.
+	 * @CC_ATTR_GUEST_SNP_SECURE_TSC: SNP Secure TSC is active.
 	 *
-	 * The platform/OS is running as a guest/virtual machine does not
-	 * support CPU hotplug feature.
+	 * The platform/OS is running as a guest/virtual machine and actively
+	 * using AMD SEV-SNP Secure TSC feature.
+	 */
+	CC_ATTR_GUEST_SNP_SECURE_TSC,
+
+	/**
+	 * @CC_ATTR_HOST_SEV_SNP: AMD SNP enabled on the host.
+	 *
+	 * The host kernel is running with the necessary features
+	 * enabled to run SEV-SNP guests.
+	 */
+	CC_ATTR_HOST_SEV_SNP,
+
+	/**
+	 * @CC_ATTR_SNP_SECURE_AVIC: Secure AVIC mode is active.
 	 *
-	 * Examples include TDX Guest.
+	 * The host kernel is running with the necessary features enabled
+	 * to run SEV-SNP guests with full Secure AVIC capabilities.
 	 */
-	CC_ATTR_HOTPLUG_DISABLED,
+	CC_ATTR_SNP_SECURE_AVIC,
 };
 
 #ifdef CONFIG_ARCH_HAS_CC_PLATFORM
@@ -107,10 +121,14 @@ enum cc_attr {
  * * FALSE - Specified Confidential Computing attribute is not active
  */
 bool cc_platform_has(enum cc_attr attr);
+void cc_platform_set(enum cc_attr attr);
+void cc_platform_clear(enum cc_attr attr);
 
 #else	/* !CONFIG_ARCH_HAS_CC_PLATFORM */
 
 static inline bool cc_platform_has(enum cc_attr attr) { return false; }
+static inline void cc_platform_set(enum cc_attr attr) { }
+static inline void cc_platform_clear(enum cc_attr attr) { }
 
 #endif	/* CONFIG_ARCH_HAS_CC_PLATFORM */
 
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index 67caa909e3e6..b907e6c2307d 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -13,6 +13,7 @@
 
 #include <linux/fs.h>		/* not really needed, later.. */
 #include <linux/list.h>
+#include <linux/blkdev.h>
 #include <scsi/scsi_common.h>
 #include <uapi/linux/cdrom.h>
 
@@ -61,9 +62,8 @@ struct cdrom_device_info {
 	__u8 last_sense;
 	__u8 media_written;		/* dirty flag, DVD+RW bookkeeping */
 	unsigned short mmc3_profile;	/* current MMC3 profile */
-	int for_data;
-	int (*exit)(struct cdrom_device_info *);
 	int mrw_mode_page;
+	bool opened_for_data;
 	__s64 last_media_change_ms;
 };
 
@@ -76,7 +76,7 @@ struct cdrom_device_ops {
 				      unsigned int clearing, int slot);
 	int (*tray_move) (struct cdrom_device_info *, int);
 	int (*lock_door) (struct cdrom_device_info *, int);
-	int (*select_speed) (struct cdrom_device_info *, int);
+	int (*select_speed) (struct cdrom_device_info *, unsigned long);
 	int (*get_last_session) (struct cdrom_device_info *,
 				 struct cdrom_multisession *);
 	int (*get_mcn) (struct cdrom_device_info *,
@@ -101,11 +101,10 @@ int cdrom_read_tocentry(struct cdrom_device_info *cdi,
 		struct cdrom_tocentry *entry);
 
 /* the general block_device operations structure: */
-extern int cdrom_open(struct cdrom_device_info *cdi, struct block_device *bdev,
-			fmode_t mode);
-extern void cdrom_release(struct cdrom_device_info *cdi, fmode_t mode);
-extern int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
-		       fmode_t mode, unsigned int cmd, unsigned long arg);
+int cdrom_open(struct cdrom_device_info *cdi, blk_mode_t mode);
+void cdrom_release(struct cdrom_device_info *cdi);
+int cdrom_ioctl(struct cdrom_device_info *cdi, struct block_device *bdev,
+		unsigned int cmd, unsigned long arg);
 extern unsigned int cdrom_check_events(struct cdrom_device_info *cdi,
 				       unsigned int clearing);
 
diff --git a/include/linux/cdx/bitfield.h b/include/linux/cdx/bitfield.h
new file mode 100644
index 000000000000..567f8ec47582
--- /dev/null
+++ b/include/linux/cdx/bitfield.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2005-2006 Fen Systems Ltd.
+ * Copyright 2006-2013 Solarflare Communications Inc.
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef CDX_BITFIELD_H
+#define CDX_BITFIELD_H
+
+#include <linux/bitfield.h>
+
+/* Lowest bit numbers and widths */
+#define CDX_DWORD_LBN 0
+#define CDX_DWORD_WIDTH 32
+
+/* Specified attribute (e.g. LBN) of the specified field */
+#define CDX_VAL(field, attribute) field ## _ ## attribute
+/* Low bit number of the specified field */
+#define CDX_LOW_BIT(field) CDX_VAL(field, LBN)
+/* Bit width of the specified field */
+#define CDX_WIDTH(field) CDX_VAL(field, WIDTH)
+/* High bit number of the specified field */
+#define CDX_HIGH_BIT(field) (CDX_LOW_BIT(field) + CDX_WIDTH(field) - 1)
+
+/* A doubleword (i.e. 4 byte) datatype - little-endian in HW */
+struct cdx_dword {
+	__le32 cdx_u32;
+};
+
+/* Value expanders for printk */
+#define CDX_DWORD_VAL(dword)				\
+	((unsigned int)le32_to_cpu((dword).cdx_u32))
+
+/*
+ * Extract bit field portion [low,high) from the 32-bit little-endian
+ * element which contains bits [min,max)
+ */
+#define CDX_DWORD_FIELD(dword, field)					\
+	(FIELD_GET(GENMASK(CDX_HIGH_BIT(field), CDX_LOW_BIT(field)),	\
+		   le32_to_cpu((dword).cdx_u32)))
+
+/*
+ * Creates the portion of the named bit field that lies within the
+ * range [min,max).
+ */
+#define CDX_INSERT_FIELD(field, value)				\
+	(FIELD_PREP(GENMASK(CDX_HIGH_BIT(field),		\
+			    CDX_LOW_BIT(field)), value))
+
+/*
+ * Creates the portion of the named bit fields that lie within the
+ * range [min,max).
+ */
+#define CDX_INSERT_FIELDS(field1, value1,		\
+			  field2, value2,		\
+			  field3, value3,		\
+			  field4, value4,		\
+			  field5, value5,		\
+			  field6, value6,		\
+			  field7, value7)		\
+	(CDX_INSERT_FIELD(field1, (value1)) |		\
+	 CDX_INSERT_FIELD(field2, (value2)) |		\
+	 CDX_INSERT_FIELD(field3, (value3)) |		\
+	 CDX_INSERT_FIELD(field4, (value4)) |		\
+	 CDX_INSERT_FIELD(field5, (value5)) |		\
+	 CDX_INSERT_FIELD(field6, (value6)) |		\
+	 CDX_INSERT_FIELD(field7, (value7)))
+
+#define CDX_POPULATE_DWORD(dword, ...)					\
+	(dword).cdx_u32 = cpu_to_le32(CDX_INSERT_FIELDS(__VA_ARGS__))
+
+/* Populate a dword field with various numbers of arguments */
+#define CDX_POPULATE_DWORD_7 CDX_POPULATE_DWORD
+#define CDX_POPULATE_DWORD_6(dword, ...) \
+	CDX_POPULATE_DWORD_7(dword, CDX_DWORD, 0, __VA_ARGS__)
+#define CDX_POPULATE_DWORD_5(dword, ...) \
+	CDX_POPULATE_DWORD_6(dword, CDX_DWORD, 0, __VA_ARGS__)
+#define CDX_POPULATE_DWORD_4(dword, ...) \
+	CDX_POPULATE_DWORD_5(dword, CDX_DWORD, 0, __VA_ARGS__)
+#define CDX_POPULATE_DWORD_3(dword, ...) \
+	CDX_POPULATE_DWORD_4(dword, CDX_DWORD, 0, __VA_ARGS__)
+#define CDX_POPULATE_DWORD_2(dword, ...) \
+	CDX_POPULATE_DWORD_3(dword, CDX_DWORD, 0, __VA_ARGS__)
+#define CDX_POPULATE_DWORD_1(dword, ...) \
+	CDX_POPULATE_DWORD_2(dword, CDX_DWORD, 0, __VA_ARGS__)
+#define CDX_SET_DWORD(dword) \
+	CDX_POPULATE_DWORD_1(dword, CDX_DWORD, 0xffffffff)
+
+#endif /* CDX_BITFIELD_H */
diff --git a/include/linux/cdx/cdx_bus.h b/include/linux/cdx/cdx_bus.h
index 35ef41d8a61a..b1ba97f6c9ad 100644
--- a/include/linux/cdx/cdx_bus.h
+++ b/include/linux/cdx/cdx_bus.h
@@ -12,9 +12,9 @@
 #include <linux/device.h>
 #include <linux/list.h>
 #include <linux/mod_devicetable.h>
+#include <linux/msi.h>
 
 #define MAX_CDX_DEV_RESOURCES	4
-#define CDX_ANY_ID (0xFFFF)
 #define CDX_CONTROLLER_ID_SHIFT 4
 #define CDX_BUS_NUM_MASK 0xF
 
@@ -22,13 +22,31 @@
 struct cdx_controller;
 
 enum {
+	CDX_DEV_MSI_CONF,
+	CDX_DEV_BUS_MASTER_CONF,
 	CDX_DEV_RESET_CONF,
+	CDX_DEV_MSI_ENABLE,
+};
+
+struct cdx_msi_config {
+	u64 addr;
+	u32 data;
+	u16 msi_index;
 };
 
 struct cdx_device_config {
 	u8 type;
+	union {
+		struct cdx_msi_config msi;
+		bool bus_master_enable;
+		bool msi_enable;
+	};
 };
 
+typedef int (*cdx_bus_enable_cb)(struct cdx_controller *cdx, u8 bus_num);
+
+typedef int (*cdx_bus_disable_cb)(struct cdx_controller *cdx, u8 bus_num);
+
 typedef int (*cdx_scan_cb)(struct cdx_controller *cdx);
 
 typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx,
@@ -36,6 +54,19 @@ typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx,
 				    struct cdx_device_config *dev_config);
 
 /**
+ * CDX_DEVICE - macro used to describe a specific CDX device
+ * @vend: the 16 bit CDX Vendor ID
+ * @dev: the 16 bit CDX Device ID
+ *
+ * This macro is used to create a struct cdx_device_id that matches a
+ * specific device. The subvendor and subdevice fields will be set to
+ * CDX_ANY_ID.
+ */
+#define CDX_DEVICE(vend, dev) \
+	.vendor = (vend), .device = (dev), \
+	.subvendor = CDX_ANY_ID, .subdevice = CDX_ANY_ID
+
+/**
  * CDX_DEVICE_DRIVER_OVERRIDE - macro used to describe a CDX device with
  *                              override_only flags.
  * @vend: the 16 bit CDX Vendor ID
@@ -43,18 +74,24 @@ typedef int (*cdx_dev_configure_cb)(struct cdx_controller *cdx,
  * @driver_override: the 32 bit CDX Device override_only
  *
  * This macro is used to create a struct cdx_device_id that matches only a
- * driver_override device.
+ * driver_override device. The subvendor and subdevice fields will be set to
+ * CDX_ANY_ID.
  */
 #define CDX_DEVICE_DRIVER_OVERRIDE(vend, dev, driver_override) \
-	.vendor = (vend), .device = (dev), .override_only = (driver_override)
+	.vendor = (vend), .device = (dev), .subvendor = CDX_ANY_ID,\
+	.subdevice = CDX_ANY_ID, .override_only = (driver_override)
 
 /**
  * struct cdx_ops - Callbacks supported by CDX controller.
+ * @bus_enable: enable bus on the controller
+ * @bus_disable: disable bus on the controller
  * @scan: scan the devices on the controller
  * @dev_configure: configuration like reset, master_enable,
  *		   msi_config etc for a CDX device
  */
 struct cdx_ops {
+	cdx_bus_enable_cb bus_enable;
+	cdx_bus_disable_cb bus_disable;
 	cdx_scan_cb scan;
 	cdx_dev_configure_cb dev_configure;
 };
@@ -63,13 +100,17 @@ struct cdx_ops {
  * struct cdx_controller: CDX controller object
  * @dev: Linux device associated with the CDX controller.
  * @priv: private data
+ * @msi_domain: MSI domain
  * @id: Controller ID
+ * @controller_registered: controller registered with bus
  * @ops: CDX controller ops
  */
 struct cdx_controller {
 	struct device *dev;
 	void *priv;
+	struct irq_domain *msi_domain;
 	u32 id;
+	bool controller_registered;
 	struct cdx_ops *ops;
 };
 
@@ -79,36 +120,68 @@ struct cdx_controller {
  * @cdx: CDX controller associated with the device
  * @vendor: Vendor ID for CDX device
  * @device: Device ID for CDX device
+ * @subsystem_vendor: Subsystem Vendor ID for CDX device
+ * @subsystem_device: Subsystem Device ID for CDX device
+ * @class: Class for the CDX device
+ * @revision: Revision of the CDX device
  * @bus_num: Bus number for this CDX device
  * @dev_num: Device number for this device
  * @res: array of MMIO region entries
  * @res_attr: resource binary attribute
+ * @debugfs_dir: debugfs directory for this device
  * @res_count: number of valid MMIO regions
  * @dma_mask: Default DMA mask
  * @flags: CDX device flags
  * @req_id: Requestor ID associated with CDX device
+ * @is_bus: Is this bus device
+ * @enabled: is this bus enabled
+ * @msi_dev_id: MSI Device ID associated with CDX device
+ * @num_msi: Number of MSI's supported by the device
  * @driver_override: driver name to force a match; do not set directly,
  *                   because core frees it; use driver_set_override() to
  *                   set or clear it.
+ * @irqchip_lock: lock to synchronize irq/msi configuration
+ * @msi_write_pending: MSI write pending for this device
  */
 struct cdx_device {
 	struct device dev;
 	struct cdx_controller *cdx;
 	u16 vendor;
 	u16 device;
+	u16 subsystem_vendor;
+	u16 subsystem_device;
+	u32 class;
+	u8 revision;
 	u8 bus_num;
 	u8 dev_num;
 	struct resource res[MAX_CDX_DEV_RESOURCES];
+	struct bin_attribute *res_attr[MAX_CDX_DEV_RESOURCES];
+	struct dentry *debugfs_dir;
 	u8 res_count;
 	u64 dma_mask;
 	u16 flags;
 	u32 req_id;
+	bool is_bus;
+	bool enabled;
+	u32 msi_dev_id;
+	u32 num_msi;
 	const char *driver_override;
+	struct mutex irqchip_lock;
+	bool msi_write_pending;
 };
 
 #define to_cdx_device(_dev) \
 	container_of(_dev, struct cdx_device, dev)
 
+#define cdx_resource_start(dev, num)	((dev)->res[(num)].start)
+#define cdx_resource_end(dev, num)	((dev)->res[(num)].end)
+#define cdx_resource_flags(dev, num)	((dev)->res[(num)].flags)
+#define cdx_resource_len(dev, num) \
+	((cdx_resource_start((dev), (num)) == 0 &&	\
+	  cdx_resource_end((dev), (num)) ==		\
+	  cdx_resource_start((dev), (num))) ? 0 :	\
+	 (cdx_resource_end((dev), (num)) -		\
+	  cdx_resource_start((dev), (num)) + 1))
 /**
  * struct cdx_driver - CDX device driver
  * @driver: Generic device driver
@@ -138,7 +211,7 @@ struct cdx_driver {
 };
 
 #define to_cdx_driver(_drv) \
-	container_of(_drv, struct cdx_driver, driver)
+	container_of_const(_drv, struct cdx_driver, driver)
 
 /* Macro to avoid include chaining to get THIS_MODULE */
 #define cdx_driver_register(drv) \
@@ -161,7 +234,7 @@ int __must_check __cdx_driver_register(struct cdx_driver *cdx_driver,
  */
 void cdx_driver_unregister(struct cdx_driver *cdx_driver);
 
-extern struct bus_type cdx_bus_type;
+extern const struct bus_type cdx_bus_type;
 
 /**
  * cdx_dev_reset - Reset CDX device
@@ -171,4 +244,48 @@ extern struct bus_type cdx_bus_type;
  */
 int cdx_dev_reset(struct device *dev);
 
+/**
+ * cdx_set_master - enables bus-mastering for CDX device
+ * @cdx_dev: the CDX device to enable
+ *
+ * Return: 0 for success, -errno on failure
+ */
+int cdx_set_master(struct cdx_device *cdx_dev);
+
+/**
+ * cdx_clear_master - disables bus-mastering for CDX device
+ * @cdx_dev: the CDX device to disable
+ *
+ * Return: 0 for success, -errno on failure
+ */
+int cdx_clear_master(struct cdx_device *cdx_dev);
+
+#ifdef CONFIG_GENERIC_MSI_IRQ
+/**
+ * cdx_enable_msi - Enable MSI for the CDX device.
+ * @cdx_dev: device pointer
+ *
+ * Return: 0 for success, -errno on failure
+ */
+int cdx_enable_msi(struct cdx_device *cdx_dev);
+
+/**
+ * cdx_disable_msi - Disable MSI for the CDX device.
+ * @cdx_dev: device pointer
+ */
+void cdx_disable_msi(struct cdx_device *cdx_dev);
+
+#else /* CONFIG_GENERIC_MSI_IRQ */
+
+static inline int cdx_enable_msi(struct cdx_device *cdx_dev)
+{
+	return -ENODEV;
+}
+
+static inline void cdx_disable_msi(struct cdx_device *cdx_dev)
+{
+}
+
+#endif /* CONFIG_GENERIC_MSI_IRQ */
+
 #endif /* _CDX_BUS_H_ */
diff --git a/include/linux/cdx/edac_cdx_pcol.h b/include/linux/cdx/edac_cdx_pcol.h
new file mode 100644
index 000000000000..749db33bb482
--- /dev/null
+++ b/include/linux/cdx/edac_cdx_pcol.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Driver for AMD network controllers and boards
+ *
+ * Copyright (C) 2021, Xilinx, Inc.
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef MC_CDX_PCOL_H
+#define MC_CDX_PCOL_H
+#include  <linux/cdx/mcdi.h>
+
+#define MC_CMD_EDAC_GET_DDR_CONFIG_OUT_WORD_LENGTH_LEN		4
+/* Number of registers for the DDR controller */
+#define MC_CMD_GET_DDR_CONFIG_OFST	4
+#define MC_CMD_GET_DDR_CONFIG_LEN	4
+
+/***********************************/
+/* MC_CMD_EDAC_GET_DDR_CONFIG
+ * Provides detailed configuration for the DDR controller of the given index.
+ */
+#define MC_CMD_EDAC_GET_DDR_CONFIG 0x3
+
+/* MC_CMD_EDAC_GET_DDR_CONFIG_IN msgrequest */
+#define MC_CMD_EDAC_GET_DDR_CONFIG_IN_CONTROLLER_INDEX_OFST		0
+#define MC_CMD_EDAC_GET_DDR_CONFIG_IN_CONTROLLER_INDEX_LEN		4
+
+#endif /* MC_CDX_PCOL_H */
diff --git a/include/linux/cdx/mcdi.h b/include/linux/cdx/mcdi.h
new file mode 100644
index 000000000000..74075305cba4
--- /dev/null
+++ b/include/linux/cdx/mcdi.h
@@ -0,0 +1,199 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2008-2013 Solarflare Communications Inc.
+ * Copyright (C) 2022-2023, Advanced Micro Devices, Inc.
+ */
+
+#ifndef CDX_MCDI_H
+#define CDX_MCDI_H
+
+#include <linux/mutex.h>
+#include <linux/kref.h>
+#include <linux/rpmsg.h>
+
+#include "linux/cdx/bitfield.h"
+
+/**
+ * enum cdx_mcdi_mode - MCDI transaction mode
+ * @MCDI_MODE_EVENTS: wait for an mcdi response callback.
+ * @MCDI_MODE_FAIL: we think MCDI is dead, so fail-fast all calls
+ */
+enum cdx_mcdi_mode {
+	MCDI_MODE_EVENTS,
+	MCDI_MODE_FAIL,
+};
+
+#define MCDI_RPC_TIMEOUT	(10 * HZ)
+#define MCDI_RPC_LONG_TIMEOU	(60 * HZ)
+#define MCDI_RPC_POST_RST_TIME	(10 * HZ)
+
+/**
+ * enum cdx_mcdi_cmd_state - State for an individual MCDI command
+ * @MCDI_STATE_QUEUED: Command not started and is waiting to run.
+ * @MCDI_STATE_RETRY: Command was submitted and MC rejected with no resources,
+ *	as MC have too many outstanding commands. Command will be retried once
+ *	another command returns.
+ * @MCDI_STATE_RUNNING: Command was accepted and is running.
+ * @MCDI_STATE_RUNNING_CANCELLED: Command is running but the issuer cancelled
+ *	the command.
+ * @MCDI_STATE_FINISHED: Processing of this command has completed.
+ */
+
+enum cdx_mcdi_cmd_state {
+	MCDI_STATE_QUEUED,
+	MCDI_STATE_RETRY,
+	MCDI_STATE_RUNNING,
+	MCDI_STATE_RUNNING_CANCELLED,
+	MCDI_STATE_FINISHED,
+};
+
+/**
+ * struct cdx_mcdi - CDX MCDI Firmware interface, to interact
+ *	with CDX controller.
+ * @mcdi: MCDI interface
+ * @mcdi_ops: MCDI operations
+ * @r5_rproc : R5 Remoteproc device handle
+ * @rpdev: RPMsg device
+ * @ept: RPMsg endpoint
+ * @work: Post probe work
+ */
+struct cdx_mcdi {
+	/* MCDI interface */
+	struct cdx_mcdi_data *mcdi;
+	const struct cdx_mcdi_ops *mcdi_ops;
+
+	struct rproc *r5_rproc;
+	struct rpmsg_device *rpdev;
+	struct rpmsg_endpoint *ept;
+	struct work_struct work;
+};
+
+struct cdx_mcdi_ops {
+	void (*mcdi_request)(struct cdx_mcdi *cdx,
+			     const struct cdx_dword *hdr, size_t hdr_len,
+			     const struct cdx_dword *sdu, size_t sdu_len);
+	unsigned int (*mcdi_rpc_timeout)(struct cdx_mcdi *cdx, unsigned int cmd);
+};
+
+typedef void cdx_mcdi_async_completer(struct cdx_mcdi *cdx,
+				      unsigned long cookie, int rc,
+				      struct cdx_dword *outbuf,
+				      size_t outlen_actual);
+
+/**
+ * struct cdx_mcdi_cmd - An outstanding MCDI command
+ * @ref: Reference count. There will be one reference if the command is
+ *	in the mcdi_iface cmd_list, another if it's on a cleanup list,
+ *	and a third if it's queued in the work queue.
+ * @list: The data for this entry in mcdi->cmd_list
+ * @cleanup_list: The data for this entry in a cleanup list
+ * @work: The work item for this command, queued in mcdi->workqueue
+ * @mcdi: The mcdi_iface for this command
+ * @state: The state of this command
+ * @inlen: inbuf length
+ * @inbuf: Input buffer
+ * @quiet: Whether to silence errors
+ * @reboot_seen: Whether a reboot has been seen during this command,
+ *	to prevent duplicates
+ * @seq: Sequence number
+ * @started: Jiffies this command was started at
+ * @cookie: Context for completion function
+ * @completer: Completion function
+ * @handle: Command handle
+ * @cmd: Command number
+ * @rc: Return code
+ * @outlen: Length of output buffer
+ * @outbuf: Output buffer
+ */
+struct cdx_mcdi_cmd {
+	struct kref ref;
+	struct list_head list;
+	struct list_head cleanup_list;
+	struct work_struct work;
+	struct cdx_mcdi_iface *mcdi;
+	enum cdx_mcdi_cmd_state state;
+	size_t inlen;
+	const struct cdx_dword *inbuf;
+	bool quiet;
+	bool reboot_seen;
+	u8 seq;
+	unsigned long started;
+	unsigned long cookie;
+	cdx_mcdi_async_completer *completer;
+	unsigned int handle;
+	unsigned int cmd;
+	int rc;
+	size_t outlen;
+	struct cdx_dword *outbuf;
+	/* followed by inbuf data if necessary */
+};
+
+/**
+ * struct cdx_mcdi_iface - MCDI protocol context
+ * @cdx: The associated NIC
+ * @iface_lock: Serialise access to this structure
+ * @outstanding_cleanups: Count of cleanups
+ * @cmd_list: List of outstanding and running commands
+ * @workqueue: Workqueue used for delayed processing
+ * @cmd_complete_wq: Waitqueue for command completion
+ * @db_held_by: Command the MC doorbell is in use by
+ * @seq_held_by: Command each sequence number is in use by
+ * @prev_handle: The last used command handle
+ * @mode: Poll for mcdi completion, or wait for an mcdi_event
+ * @prev_seq: The last used sequence number
+ * @new_epoch: Indicates start of day or start of MC reboot recovery
+ */
+struct cdx_mcdi_iface {
+	struct cdx_mcdi *cdx;
+	/* Serialise access */
+	struct mutex iface_lock;
+	unsigned int outstanding_cleanups;
+	struct list_head cmd_list;
+	struct workqueue_struct *workqueue;
+	wait_queue_head_t cmd_complete_wq;
+	struct cdx_mcdi_cmd *db_held_by;
+	struct cdx_mcdi_cmd *seq_held_by[16];
+	unsigned int prev_handle;
+	enum cdx_mcdi_mode mode;
+	u8 prev_seq;
+	bool new_epoch;
+};
+
+/**
+ * struct cdx_mcdi_data - extra state for NICs that implement MCDI
+ * @iface: Interface/protocol state
+ * @fn_flags: Flags for this function, as returned by %MC_CMD_DRV_ATTACH.
+ */
+struct cdx_mcdi_data {
+	struct cdx_mcdi_iface iface;
+	u32 fn_flags;
+};
+
+void cdx_mcdi_finish(struct cdx_mcdi *cdx);
+int cdx_mcdi_init(struct cdx_mcdi *cdx);
+void cdx_mcdi_process_cmd(struct cdx_mcdi *cdx, struct cdx_dword *outbuf, int len);
+int cdx_mcdi_rpc(struct cdx_mcdi *cdx, unsigned int cmd,
+		 const struct cdx_dword *inbuf, size_t inlen,
+		 struct cdx_dword *outbuf, size_t outlen, size_t *outlen_actual);
+
+/*
+ * We expect that 16- and 32-bit fields in MCDI requests and responses
+ * are appropriately aligned, but 64-bit fields are only
+ * 32-bit-aligned.
+ */
+#define MCDI_DECLARE_BUF(_name, _len) struct cdx_dword _name[DIV_ROUND_UP(_len, 4)] = {{0}}
+#define _MCDI_PTR(_buf, _offset)					\
+	((u8 *)(_buf) + (_offset))
+#define MCDI_PTR(_buf, _field)						\
+	_MCDI_PTR(_buf, MC_CMD_ ## _field ## _OFST)
+#define _MCDI_CHECK_ALIGN(_ofst, _align)				\
+	((void)BUILD_BUG_ON_ZERO((_ofst) & ((_align) - 1)),		\
+	 (_ofst))
+#define _MCDI_DWORD(_buf, _field)					\
+	((_buf) + (_MCDI_CHECK_ALIGN(MC_CMD_ ## _field ## _OFST, 4) >> 2))
+
+#define MCDI_SET_DWORD(_buf, _field, _value)				\
+	CDX_POPULATE_DWORD_1(*_MCDI_DWORD(_buf, _field), CDX_DWORD, _value)
+#define MCDI_DWORD(_buf, _field)					\
+	CDX_DWORD_FIELD(*_MCDI_DWORD(_buf, _field), CDX_DWORD)
+#endif /* CDX_MCDI_H */
diff --git a/include/linux/ceph/ceph_debug.h b/include/linux/ceph/ceph_debug.h
index d5a5da838caf..5f904591fa5f 100644
--- a/include/linux/ceph/ceph_debug.h
+++ b/include/linux/ceph/ceph_debug.h
@@ -19,12 +19,21 @@
 	pr_debug("%.*s %12.12s:%-4d : " fmt,				\
 		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
 		 kbasename(__FILE__), __LINE__, ##__VA_ARGS__)
+#  define doutc(client, fmt, ...)					\
+	pr_debug("%.*s %12.12s:%-4d : [%pU %llu] " fmt,			\
+		 8 - (int)sizeof(KBUILD_MODNAME), "    ",		\
+		 kbasename(__FILE__), __LINE__,				\
+		 &client->fsid, client->monc.auth->global_id,		\
+		 ##__VA_ARGS__)
 # else
 /* faux printk call just to see any compiler warnings. */
-#  define dout(fmt, ...)	do {				\
-		if (0)						\
-			printk(KERN_DEBUG fmt, ##__VA_ARGS__);	\
-	} while (0)
+#  define dout(fmt, ...)					\
+		no_printk(KERN_DEBUG fmt, ##__VA_ARGS__)
+#  define doutc(client, fmt, ...)				\
+		no_printk(KERN_DEBUG "[%pU %llu] " fmt,		\
+			  &client->fsid,			\
+			  client->monc.auth->global_id,		\
+			  ##__VA_ARGS__)
 # endif
 
 #else
@@ -33,7 +42,32 @@
  * or, just wrap pr_debug
  */
 # define dout(fmt, ...)	pr_debug(" " fmt, ##__VA_ARGS__)
+# define doutc(client, fmt, ...)					\
+	pr_debug(" [%pU %llu] %s: " fmt, &client->fsid,			\
+		 client->monc.auth->global_id, __func__, ##__VA_ARGS__)
 
 #endif
 
+#define pr_notice_client(client, fmt, ...)				\
+	pr_notice("[%pU %llu]: " fmt, &client->fsid,			\
+		  client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_info_client(client, fmt, ...)				\
+	pr_info("[%pU %llu]: " fmt, &client->fsid,			\
+		client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_client(client, fmt, ...)				\
+	pr_warn("[%pU %llu]: " fmt, &client->fsid,			\
+		client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_once_client(client, fmt, ...)				\
+	pr_warn_once("[%pU %llu]: " fmt, &client->fsid,			\
+		     client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_err_client(client, fmt, ...)					\
+	pr_err("[%pU %llu]: " fmt, &client->fsid,			\
+	       client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_warn_ratelimited_client(client, fmt, ...)			\
+	pr_warn_ratelimited("[%pU %llu]: " fmt, &client->fsid,		\
+			    client->monc.auth->global_id, ##__VA_ARGS__)
+#define pr_err_ratelimited_client(client, fmt, ...)			\
+	pr_err_ratelimited("[%pU %llu]: " fmt, &client->fsid,		\
+			   client->monc.auth->global_id, ##__VA_ARGS__)
+
 #endif
diff --git a/include/linux/ceph/ceph_fs.h b/include/linux/ceph/ceph_fs.h
index 49586ff26152..c7f2c63b3bc3 100644
--- a/include/linux/ceph/ceph_fs.h
+++ b/include/linux/ceph/ceph_fs.h
@@ -357,16 +357,26 @@ enum {
 	CEPH_MDS_OP_RENAMESNAP = 0x01403,
 };
 
-extern const char *ceph_mds_op_name(int op);
+#define IS_CEPH_MDS_OP_NEWINODE(op) (op == CEPH_MDS_OP_CREATE     || \
+				     op == CEPH_MDS_OP_MKNOD      || \
+				     op == CEPH_MDS_OP_MKDIR      || \
+				     op == CEPH_MDS_OP_SYMLINK)
 
+extern const char *ceph_mds_op_name(int op);
 
-#define CEPH_SETATTR_MODE   1
-#define CEPH_SETATTR_UID    2
-#define CEPH_SETATTR_GID    4
-#define CEPH_SETATTR_MTIME  8
-#define CEPH_SETATTR_ATIME 16
-#define CEPH_SETATTR_SIZE  32
-#define CEPH_SETATTR_CTIME 64
+#define CEPH_SETATTR_MODE              (1 << 0)
+#define CEPH_SETATTR_UID               (1 << 1)
+#define CEPH_SETATTR_GID               (1 << 2)
+#define CEPH_SETATTR_MTIME             (1 << 3)
+#define CEPH_SETATTR_ATIME             (1 << 4)
+#define CEPH_SETATTR_SIZE              (1 << 5)
+#define CEPH_SETATTR_CTIME             (1 << 6)
+#define CEPH_SETATTR_MTIME_NOW         (1 << 7)
+#define CEPH_SETATTR_ATIME_NOW         (1 << 8)
+#define CEPH_SETATTR_BTIME             (1 << 9)
+#define CEPH_SETATTR_KILL_SGUID        (1 << 10)
+#define CEPH_SETATTR_FSCRYPT_AUTH      (1 << 11)
+#define CEPH_SETATTR_FSCRYPT_FILE      (1 << 12)
 
 /*
  * Ceph setxattr request flags.
@@ -479,7 +489,7 @@ union ceph_mds_request_args_ext {
 #define CEPH_MDS_FLAG_WANT_DENTRY	2 /* want dentry in reply */
 #define CEPH_MDS_FLAG_ASYNC		4 /* request is asynchronous */
 
-struct ceph_mds_request_head_old {
+struct ceph_mds_request_head_legacy {
 	__le64 oldest_client_tid;
 	__le32 mdsmap_epoch;           /* on client */
 	__le32 flags;                  /* CEPH_MDS_FLAG_* */
@@ -492,20 +502,26 @@ struct ceph_mds_request_head_old {
 	union ceph_mds_request_args args;
 } __attribute__ ((packed));
 
-#define CEPH_MDS_REQUEST_HEAD_VERSION  1
+#define CEPH_MDS_REQUEST_HEAD_VERSION  3
 
 struct ceph_mds_request_head {
 	__le16 version;                /* struct version */
 	__le64 oldest_client_tid;
 	__le32 mdsmap_epoch;           /* on client */
 	__le32 flags;                  /* CEPH_MDS_FLAG_* */
-	__u8 num_retry, num_fwd;       /* count retry, fwd attempts */
+	__u8 num_retry, num_fwd;       /* legacy count retry and fwd attempts */
 	__le16 num_releases;           /* # include cap/lease release records */
 	__le32 op;                     /* mds op code */
 	__le32 caller_uid, caller_gid;
 	__le64 ino;                    /* use this ino for openc, mkdir, mknod,
 					  etc. (if replaying) */
 	union ceph_mds_request_args_ext args;
+
+	__le32 ext_num_retry;          /* new count retry attempts */
+	__le32 ext_num_fwd;            /* new count fwd attempts */
+
+	__le32 struct_len;             /* to store size of struct ceph_mds_request_head */
+	__le32 owner_uid, owner_gid;   /* used for OPs which create inodes */
 } __attribute__ ((packed));
 
 /* cap/lease release record */
@@ -778,7 +794,7 @@ struct ceph_mds_caps {
 
 struct ceph_mds_cap_peer {
 	__le64 cap_id;
-	__le32 seq;
+	__le32 issue_seq;
 	__le32 mseq;
 	__le32 mds;
 	__u8   flags;
@@ -792,7 +808,7 @@ struct ceph_mds_cap_release {
 struct ceph_mds_cap_item {
 	__le64 ino;
 	__le64 cap_id;
-	__le32 migrate_seq, seq;
+	__le32 migrate_seq, issue_seq;
 } __attribute__ ((packed));
 
 #define CEPH_MDS_LEASE_REVOKE           1  /*    mds  -> client */
diff --git a/include/linux/ceph/decode.h b/include/linux/ceph/decode.h
index 04f3ace5787b..8fc1aed64113 100644
--- a/include/linux/ceph/decode.h
+++ b/include/linux/ceph/decode.h
@@ -6,7 +6,7 @@
 #include <linux/bug.h>
 #include <linux/slab.h>
 #include <linux/time.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 #include <linux/ceph/types.h>
 
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 4497d0a6772c..63e0e2aa1ce9 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -4,7 +4,7 @@
 
 #include <linux/ceph/ceph_debug.h>
 
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <linux/backing-dev.h>
 #include <linux/completion.h>
 #include <linux/exportfs.h>
@@ -306,8 +306,7 @@ struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client);
 u64 ceph_client_gid(struct ceph_client *client);
 extern void ceph_destroy_client(struct ceph_client *client);
 extern void ceph_reset_client_addr(struct ceph_client *client);
-extern int __ceph_open_session(struct ceph_client *client,
-			       unsigned long started);
+extern int __ceph_open_session(struct ceph_client *client);
 extern int ceph_open_session(struct ceph_client *client);
 int ceph_wait_for_latest_osdmap(struct ceph_client *client,
 				unsigned long timeout);
@@ -317,12 +316,6 @@ extern void ceph_release_page_vector(struct page **pages, int num_pages);
 extern void ceph_put_page_vector(struct page **pages, int num_pages,
 				 bool dirty);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
-extern int ceph_copy_user_to_page_vector(struct page **pages,
-					 const void __user *data,
-					 loff_t off, size_t len);
-extern void ceph_copy_to_page_vector(struct page **pages,
-				    const void *data,
-				    loff_t off, size_t len);
 extern void ceph_copy_from_page_vector(struct page **pages,
 				    void *data,
 				    loff_t off, size_t len);
diff --git a/include/linux/ceph/mdsmap.h b/include/linux/ceph/mdsmap.h
deleted file mode 100644
index 4c3e0648dc27..000000000000
--- a/include/linux/ceph/mdsmap.h
+++ /dev/null
@@ -1,72 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _FS_CEPH_MDSMAP_H
-#define _FS_CEPH_MDSMAP_H
-
-#include <linux/bug.h>
-#include <linux/ceph/types.h>
-
-/*
- * mds map - describe servers in the mds cluster.
- *
- * we limit fields to those the client actually xcares about
- */
-struct ceph_mds_info {
-	u64 global_id;
-	struct ceph_entity_addr addr;
-	s32 state;
-	int num_export_targets;
-	bool laggy;
-	u32 *export_targets;
-};
-
-struct ceph_mdsmap {
-	u32 m_epoch, m_client_epoch, m_last_failure;
-	u32 m_root;
-	u32 m_session_timeout;          /* seconds */
-	u32 m_session_autoclose;        /* seconds */
-	u64 m_max_file_size;
-	u64 m_max_xattr_size;		/* maximum size for xattrs blob */
-	u32 m_max_mds;			/* expected up:active mds number */
-	u32 m_num_active_mds;		/* actual up:active mds number */
-	u32 possible_max_rank;		/* possible max rank index */
-	struct ceph_mds_info *m_info;
-
-	/* which object pools file data can be stored in */
-	int m_num_data_pg_pools;
-	u64 *m_data_pg_pools;
-	u64 m_cas_pg_pool;
-
-	bool m_enabled;
-	bool m_damaged;
-	int m_num_laggy;
-};
-
-static inline struct ceph_entity_addr *
-ceph_mdsmap_get_addr(struct ceph_mdsmap *m, int w)
-{
-	if (w >= m->possible_max_rank)
-		return NULL;
-	return &m->m_info[w].addr;
-}
-
-static inline int ceph_mdsmap_get_state(struct ceph_mdsmap *m, int w)
-{
-	BUG_ON(w < 0);
-	if (w >= m->possible_max_rank)
-		return CEPH_MDS_STATE_DNE;
-	return m->m_info[w].state;
-}
-
-static inline bool ceph_mdsmap_is_laggy(struct ceph_mdsmap *m, int w)
-{
-	if (w >= 0 && w < m->possible_max_rank)
-		return m->m_info[w].laggy;
-	return false;
-}
-
-extern int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m);
-struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end, bool msgr2);
-extern void ceph_mdsmap_destroy(struct ceph_mdsmap *m);
-extern bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m);
-
-#endif
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 99c1726be6ee..6aa4c6478c9f 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -2,6 +2,7 @@
 #ifndef __FS_CEPH_MESSENGER_H
 #define __FS_CEPH_MESSENGER_H
 
+#include <crypto/sha2.h>
 #include <linux/bvec.h>
 #include <linux/crypto.h>
 #include <linux/kref.h>
@@ -17,6 +18,7 @@
 
 struct ceph_msg;
 struct ceph_connection;
+struct ceph_msg_data_cursor;
 
 /*
  * Ceph defines these callbacks for handling connection events.
@@ -70,6 +72,30 @@ struct ceph_connection_operations {
 				      int used_proto, int result,
 				      const int *allowed_protos, int proto_cnt,
 				      const int *allowed_modes, int mode_cnt);
+
+	/**
+	 * sparse_read: read sparse data
+	 * @con: connection we're reading from
+	 * @cursor: data cursor for reading extents
+	 * @buf: optional buffer to read into
+	 *
+	 * This should be called more than once, each time setting up to
+	 * receive an extent into the current cursor position, and zeroing
+	 * the holes between them.
+	 *
+	 * Returns amount of data to be read (in bytes), 0 if reading is
+	 * complete, or -errno if there was an error.
+	 *
+	 * If @buf is set on a >0 return, then the data should be read into
+	 * the provided buffer. Otherwise, it should be read into the cursor.
+	 *
+	 * The sparse read operation is expected to initialize the cursor
+	 * with a length covering up to the end of the last extent.
+	 */
+	int (*sparse_read)(struct ceph_connection *con,
+			   struct ceph_msg_data_cursor *cursor,
+			   char **buf);
+
 };
 
 /* use format string %s%lld */
@@ -98,6 +124,7 @@ enum ceph_msg_data_type {
 	CEPH_MSG_DATA_BIO,	/* data source/destination is a bio list */
 #endif /* CONFIG_BLOCK */
 	CEPH_MSG_DATA_BVECS,	/* data source/destination is a bio_vec array */
+	CEPH_MSG_DATA_ITER,	/* data source/destination is an iov_iter */
 };
 
 #ifdef CONFIG_BLOCK
@@ -199,6 +226,7 @@ struct ceph_msg_data {
 			bool		own_pages;
 		};
 		struct ceph_pagelist	*pagelist;
+		struct iov_iter		iter;
 	};
 };
 
@@ -207,6 +235,7 @@ struct ceph_msg_data_cursor {
 
 	struct ceph_msg_data	*data;		/* current data item */
 	size_t			resid;		/* bytes not yet consumed */
+	int			sr_resid;	/* residual sparse_read len */
 	bool			need_crc;	/* crc update needed */
 	union {
 #ifdef CONFIG_BLOCK
@@ -222,6 +251,10 @@ struct ceph_msg_data_cursor {
 			struct page	*page;		/* page from list */
 			size_t		offset;		/* bytes from list */
 		};
+		struct {
+			struct iov_iter		iov_iter;
+			unsigned int		lastlen;
+		};
 	};
 };
 
@@ -251,6 +284,7 @@ struct ceph_msg {
 	struct kref kref;
 	bool more_to_follow;
 	bool needs_out_seq;
+	u64 sparse_read_total;
 	int front_alloc_len;
 
 	struct ceph_msgpool *pool;
@@ -309,6 +343,10 @@ struct ceph_connection_v1_info {
 
 	int in_base_pos;     /* bytes read */
 
+	/* sparse reads */
+	struct kvec in_sr_kvec; /* current location to receive into */
+	u64 in_sr_len;		/* amount of data in this extent */
+
 	/* message in temps */
 	u8 in_tag;           /* protocol control byte */
 	struct ceph_msg_header in_hdr;
@@ -375,7 +413,8 @@ struct ceph_connection_v2_info {
 	struct ceph_msg_data_cursor in_cursor;
 	struct ceph_msg_data_cursor out_cursor;
 
-	struct crypto_shash *hmac_tfm;  /* post-auth signature */
+	struct hmac_sha256_key hmac_key;  /* post-auth signature */
+	bool hmac_key_set;
 	struct crypto_aead *gcm_tfm;  /* on-wire encryption */
 	struct aead_request *gcm_req;
 	struct crypto_wait gcm_wait;
@@ -395,6 +434,7 @@ struct ceph_connection_v2_info {
 
 	void *conn_bufs[16];
 	int conn_buf_cnt;
+	int data_len_remain;
 
 	struct kvec in_sign_kvecs[8];
 	struct kvec out_sign_kvecs[8];
@@ -510,12 +550,12 @@ void ceph_addr_set_port(struct ceph_entity_addr *addr, int p);
 void ceph_con_process_message(struct ceph_connection *con);
 int ceph_con_in_msg_alloc(struct ceph_connection *con,
 			  struct ceph_msg_header *hdr, int *skip);
-void ceph_con_get_out_msg(struct ceph_connection *con);
+struct ceph_msg *ceph_con_get_out_msg(struct ceph_connection *con);
 
 /* messenger_v1.c */
 int ceph_con_v1_try_read(struct ceph_connection *con);
 int ceph_con_v1_try_write(struct ceph_connection *con);
-void ceph_con_v1_revoke(struct ceph_connection *con);
+void ceph_con_v1_revoke(struct ceph_connection *con, struct ceph_msg *msg);
 void ceph_con_v1_revoke_incoming(struct ceph_connection *con);
 bool ceph_con_v1_opened(struct ceph_connection *con);
 void ceph_con_v1_reset_session(struct ceph_connection *con);
@@ -524,7 +564,7 @@ void ceph_con_v1_reset_protocol(struct ceph_connection *con);
 /* messenger_v2.c */
 int ceph_con_v2_try_read(struct ceph_connection *con);
 int ceph_con_v2_try_write(struct ceph_connection *con);
-void ceph_con_v2_revoke(struct ceph_connection *con);
+void ceph_con_v2_revoke(struct ceph_connection *con, struct ceph_msg *msg);
 void ceph_con_v2_revoke_incoming(struct ceph_connection *con);
 bool ceph_con_v2_opened(struct ceph_connection *con);
 void ceph_con_v2_reset_session(struct ceph_connection *con);
@@ -573,6 +613,8 @@ void ceph_msg_data_add_bio(struct ceph_msg *msg, struct ceph_bio_iter *bio_pos,
 #endif /* CONFIG_BLOCK */
 void ceph_msg_data_add_bvecs(struct ceph_msg *msg,
 			     struct ceph_bvec_iter *bvec_pos);
+void ceph_msg_data_add_iter(struct ceph_msg *msg,
+			    struct iov_iter *iter);
 
 struct ceph_msg *ceph_msg_new2(int type, int front_len, int max_data_items,
 			       gfp_t flags, bool can_fail);
diff --git a/include/linux/ceph/mon_client.h b/include/linux/ceph/mon_client.h
index b658961156a0..7a9a40163c0f 100644
--- a/include/linux/ceph/mon_client.h
+++ b/include/linux/ceph/mon_client.h
@@ -19,7 +19,7 @@ struct ceph_monmap {
 	struct ceph_fsid fsid;
 	u32 epoch;
 	u32 num_mon;
-	struct ceph_entity_inst mon_inst[];
+	struct ceph_entity_inst mon_inst[] __counted_by(num_mon);
 };
 
 struct ceph_mon_client;
diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h
index fb6be72104df..50b14a5661c7 100644
--- a/include/linux/ceph/osd_client.h
+++ b/include/linux/ceph/osd_client.h
@@ -29,14 +29,63 @@ typedef void (*ceph_osdc_callback_t)(struct ceph_osd_request *);
 
 #define CEPH_HOMELESS_OSD	-1
 
-/* a given osd we're communicating with */
+/*
+ * A single extent in a SPARSE_READ reply.
+ *
+ * Note that these come from the OSD as little-endian values. On BE arches,
+ * we convert them in-place after receipt.
+ */
+struct ceph_sparse_extent {
+	u64	off;
+	u64	len;
+} __packed;
+
+/* Sparse read state machine state values */
+enum ceph_sparse_read_state {
+	CEPH_SPARSE_READ_HDR	= 0,
+	CEPH_SPARSE_READ_EXTENTS,
+	CEPH_SPARSE_READ_DATA_LEN,
+	CEPH_SPARSE_READ_DATA_PRE,
+	CEPH_SPARSE_READ_DATA,
+};
+
+/*
+ * A SPARSE_READ reply is a 32-bit count of extents, followed by an array of
+ * 64-bit offset/length pairs, and then all of the actual file data
+ * concatenated after it (sans holes).
+ *
+ * Unfortunately, we don't know how long the extent array is until we've
+ * started reading the data section of the reply. The caller should send down
+ * a destination buffer for the array, but we'll alloc one if it's too small
+ * or if the caller doesn't.
+ */
+struct ceph_sparse_read {
+	enum ceph_sparse_read_state	sr_state;    /* state machine state */
+	u64				sr_req_off;  /* orig request offset */
+	u64				sr_req_len;  /* orig request length */
+	u64				sr_pos;      /* current pos in buffer */
+	int				sr_index;    /* current extent index */
+	u32				sr_datalen;  /* length of actual data */
+	u32				sr_count;    /* extent count in reply */
+	int				sr_ext_len;  /* length of extent array */
+	struct ceph_sparse_extent	*sr_extent;  /* extent array */
+};
+
+/*
+ * A given osd we're communicating with.
+ *
+ * Note that the o_requests tree can be searched while holding the "lock" mutex
+ * or the "o_requests_lock" spinlock. Insertion or removal requires both!
+ */
 struct ceph_osd {
 	refcount_t o_ref;
+	int o_sparse_op_idx;
 	struct ceph_osd_client *o_osdc;
 	int o_osd;
 	int o_incarnation;
 	struct rb_node o_node;
 	struct ceph_connection o_con;
+	spinlock_t o_requests_lock;
 	struct rb_root o_requests;
 	struct rb_root o_linger_requests;
 	struct rb_root o_backoff_mappings;
@@ -46,6 +95,7 @@ struct ceph_osd {
 	unsigned long lru_ttl;
 	struct list_head o_keepalive_item;
 	struct mutex lock;
+	struct ceph_sparse_read	o_sparse_read;
 };
 
 #define CEPH_OSD_SLAB_OPS	2
@@ -59,6 +109,7 @@ enum ceph_osd_data_type {
 	CEPH_OSD_DATA_TYPE_BIO,
 #endif /* CONFIG_BLOCK */
 	CEPH_OSD_DATA_TYPE_BVECS,
+	CEPH_OSD_DATA_TYPE_ITER,
 };
 
 struct ceph_osd_data {
@@ -82,6 +133,7 @@ struct ceph_osd_data {
 			struct ceph_bvec_iter	bvec_pos;
 			u32			num_bvecs;
 		};
+		struct iov_iter		iter;
 	};
 };
 
@@ -98,6 +150,8 @@ struct ceph_osd_req_op {
 			u64 offset, length;
 			u64 truncate_size;
 			u32 truncate_seq;
+			int sparse_ext_cnt;
+			struct ceph_sparse_extent *sparse_ext;
 			struct ceph_osd_data osd_data;
 		} extent;
 		struct {
@@ -145,6 +199,9 @@ struct ceph_osd_req_op {
 			u32 src_fadvise_flags;
 			struct ceph_osd_data osd_data;
 		} copy_from;
+		struct {
+			u64 ver;
+		} assert_ver;
 	};
 };
 
@@ -199,6 +256,7 @@ struct ceph_osd_request {
 	struct ceph_osd_client *r_osdc;
 	struct kref       r_kref;
 	bool              r_mempool;
+	bool		  r_linger;           /* don't resend on failure */
 	struct completion r_completion;       /* private to osd_client.c */
 	ceph_osdc_callback_t r_callback;
 
@@ -211,9 +269,9 @@ struct ceph_osd_request {
 	struct ceph_snap_context *r_snapc;    /* for writes */
 	struct timespec64 r_mtime;            /* ditto */
 	u64 r_data_offset;                    /* ditto */
-	bool r_linger;                        /* don't resend on failure */
 
 	/* internal */
+	u64 r_version;			      /* data version sent in reply */
 	unsigned long r_stamp;                /* jiffies, send or check time */
 	unsigned long r_start_stamp;          /* jiffies */
 	ktime_t r_start_latency;              /* ktime_t */
@@ -221,7 +279,7 @@ struct ceph_osd_request {
 	int r_attempts;
 	u32 r_map_dne_bound;
 
-	struct ceph_osd_req_op r_ops[];
+	struct ceph_osd_req_op r_ops[] __counted_by(r_num_ops);
 };
 
 struct ceph_request_redirect {
@@ -391,8 +449,6 @@ extern int ceph_osdc_init(struct ceph_osd_client *osdc,
 extern void ceph_osdc_stop(struct ceph_osd_client *osdc);
 extern void ceph_osdc_reopen_osds(struct ceph_osd_client *osdc);
 
-extern void ceph_osdc_handle_reply(struct ceph_osd_client *osdc,
-				   struct ceph_msg *msg);
 extern void ceph_osdc_handle_map(struct ceph_osd_client *osdc,
 				 struct ceph_msg *msg);
 void ceph_osdc_update_epoch_barrier(struct ceph_osd_client *osdc, u32 eb);
@@ -434,9 +490,6 @@ extern void osd_req_op_extent_osd_data_pages(struct ceph_osd_request *,
 					struct page **pages, u64 length,
 					u32 alignment, bool pages_from_pool,
 					bool own_pages);
-extern void osd_req_op_extent_osd_data_pagelist(struct ceph_osd_request *,
-					unsigned int which,
-					struct ceph_pagelist *pagelist);
 #ifdef CONFIG_BLOCK
 void osd_req_op_extent_osd_data_bio(struct ceph_osd_request *osd_req,
 				    unsigned int which,
@@ -450,10 +503,9 @@ void osd_req_op_extent_osd_data_bvecs(struct ceph_osd_request *osd_req,
 void osd_req_op_extent_osd_data_bvec_pos(struct ceph_osd_request *osd_req,
 					 unsigned int which,
 					 struct ceph_bvec_iter *bvec_pos);
+void osd_req_op_extent_osd_iter(struct ceph_osd_request *osd_req,
+				unsigned int which, struct iov_iter *iter);
 
-extern void osd_req_op_cls_request_data_pagelist(struct ceph_osd_request *,
-					unsigned int which,
-					struct ceph_pagelist *pagelist);
 extern void osd_req_op_cls_request_data_pages(struct ceph_osd_request *,
 					unsigned int which,
 					struct page **pages, u64 length,
@@ -504,6 +556,23 @@ extern struct ceph_osd_request *ceph_osdc_new_request(struct ceph_osd_client *,
 				      u32 truncate_seq, u64 truncate_size,
 				      bool use_mempool);
 
+int __ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt);
+
+/*
+ * How big an extent array should we preallocate for a sparse read? This is
+ * just a starting value.  If we get more than this back from the OSD, the
+ * receiver will reallocate.
+ */
+#define CEPH_SPARSE_EXT_ARRAY_INITIAL  16
+
+static inline int ceph_alloc_sparse_ext_map(struct ceph_osd_req_op *op, int cnt)
+{
+	if (!cnt)
+		cnt = CEPH_SPARSE_EXT_ARRAY_INITIAL;
+
+	return __ceph_alloc_sparse_ext_map(op, cnt);
+}
+
 extern void ceph_osdc_get_request(struct ceph_osd_request *req);
 extern void ceph_osdc_put_request(struct ceph_osd_request *req);
 
@@ -551,12 +620,24 @@ int ceph_osdc_notify(struct ceph_osd_client *osdc,
 		     u32 timeout,
 		     struct page ***preply_pages,
 		     size_t *preply_len);
-int ceph_osdc_watch_check(struct ceph_osd_client *osdc,
-			  struct ceph_osd_linger_request *lreq);
 int ceph_osdc_list_watchers(struct ceph_osd_client *osdc,
 			    struct ceph_object_id *oid,
 			    struct ceph_object_locator *oloc,
 			    struct ceph_watch_item **watchers,
 			    u32 *num_watchers);
-#endif
 
+/* Find offset into the buffer of the end of the extent map */
+static inline u64 ceph_sparse_ext_map_end(struct ceph_osd_req_op *op)
+{
+	struct ceph_sparse_extent *ext;
+
+	/* No extents? No data */
+	if (op->extent.sparse_ext_cnt == 0)
+		return 0;
+
+	ext = &op->extent.sparse_ext[op->extent.sparse_ext_cnt - 1];
+
+	return ext->off + ext->len - op->extent.offset;
+}
+
+#endif
diff --git a/include/linux/ceph/pagelist.h b/include/linux/ceph/pagelist.h
index 5dead8486fd8..879bec0863aa 100644
--- a/include/linux/ceph/pagelist.h
+++ b/include/linux/ceph/pagelist.h
@@ -17,12 +17,6 @@ struct ceph_pagelist {
 	refcount_t refcnt;
 };
 
-struct ceph_pagelist_cursor {
-	struct ceph_pagelist *pl;   /* pagelist, for error checking */
-	struct list_head *page_lru; /* page in list */
-	size_t room;		    /* room remaining to reset to */
-};
-
 struct ceph_pagelist *ceph_pagelist_alloc(gfp_t gfp_flags);
 
 extern void ceph_pagelist_release(struct ceph_pagelist *pl);
@@ -33,12 +27,6 @@ extern int ceph_pagelist_reserve(struct ceph_pagelist *pl, size_t space);
 
 extern int ceph_pagelist_free_reserve(struct ceph_pagelist *pl);
 
-extern void ceph_pagelist_set_cursor(struct ceph_pagelist *pl,
-				     struct ceph_pagelist_cursor *c);
-
-extern int ceph_pagelist_truncate(struct ceph_pagelist *pl,
-				  struct ceph_pagelist_cursor *c);
-
 static inline int ceph_pagelist_encode_64(struct ceph_pagelist *pl, u64 v)
 {
 	__le64 ev = cpu_to_le64(v);
diff --git a/include/linux/ceph/rados.h b/include/linux/ceph/rados.h
index 43a7a1573b51..73c3efbec36c 100644
--- a/include/linux/ceph/rados.h
+++ b/include/linux/ceph/rados.h
@@ -524,6 +524,10 @@ struct ceph_osd_op {
 			__le64 cookie;
 		} __attribute__ ((packed)) notify;
 		struct {
+			__le64 unused;
+			__le64 ver;
+		} __attribute__ ((packed)) assert_ver;
+		struct {
 			__le64 offset, length;
 			__le64 src_offset;
 		} __attribute__ ((packed)) clonerange;
diff --git a/include/linux/cfag12864b.h b/include/linux/cfag12864b.h
index 6617d9c68d86..83e6613d12ae 100644
--- a/include/linux/cfag12864b.h
+++ b/include/linux/cfag12864b.h
@@ -28,13 +28,6 @@
 extern unsigned char * cfag12864b_buffer;
 
 /*
- * Get the refresh rate of the LCD
- *
- * Returns the refresh rate (hertz).
- */
-extern unsigned int cfag12864b_getrate(void);
-
-/*
  * Enable refreshing
  *
  * Returns 0 if successful (anyone was using it),
@@ -50,16 +43,6 @@ extern unsigned char cfag12864b_enable(void);
 extern void cfag12864b_disable(void);
 
 /*
- * Is enabled refreshing? (is anyone using the module?)
- *
- * Returns 0 if refreshing is not enabled (anyone is using it),
- * or != 0 if refreshing is enabled (someone is using it).
- *
- * Useful for buffer read-only modules.
- */
-extern unsigned char cfag12864b_isenabled(void);
-
-/*
  * Is the module inited?
  */
 extern unsigned char cfag12864b_isinited(void);
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index 5e134f4ce8b7..1fd22ea6eba4 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -9,8 +9,11 @@
 
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <asm/cfi.h>
+
+#ifdef CONFIG_CFI
+extern bool cfi_warn;
 
-#ifdef CONFIG_CFI_CLANG
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 				      unsigned long *target, u32 type);
 
@@ -20,10 +23,50 @@ static inline enum bug_trap_type report_cfi_failure_noaddr(struct pt_regs *regs,
 	return report_cfi_failure(regs, addr, NULL, 0);
 }
 
+#ifndef cfi_get_offset
+/*
+ * Returns the CFI prefix offset. By default, the compiler emits only
+ * a 4-byte CFI type hash before the function. If an architecture
+ * uses -fpatchable-function-entry=N,M where M>0 to change the prefix
+ * offset, they must override this function.
+ */
+static inline int cfi_get_offset(void)
+{
+	return 4;
+}
+#endif
+
+#ifndef cfi_get_func_hash
+static inline u32 cfi_get_func_hash(void *func)
+{
+	u32 hash;
+
+	if (get_kernel_nofault(hash, func - cfi_get_offset()))
+		return 0;
+
+	return hash;
+}
+#endif
+
+/* CFI type hashes for BPF function types */
+extern u32 cfi_bpf_hash;
+extern u32 cfi_bpf_subprog_hash;
+
+#else /* CONFIG_CFI */
+
+static inline int cfi_get_offset(void) { return 0; }
+static inline u32 cfi_get_func_hash(void *func) { return 0; }
+
+#define cfi_bpf_hash 0U
+#define cfi_bpf_subprog_hash 0U
+
+#endif /* CONFIG_CFI */
+
 #ifdef CONFIG_ARCH_USES_CFI_TRAPS
 bool is_cfi_trap(unsigned long addr);
+#else
+static inline bool is_cfi_trap(unsigned long addr) { return false; }
 #endif
-#endif /* CONFIG_CFI_CLANG */
 
 #ifdef CONFIG_MODULES
 #ifdef CONFIG_ARCH_USES_CFI_TRAPS
@@ -36,4 +79,8 @@ static inline void module_cfi_finalize(const Elf_Ehdr *hdr,
 #endif /* CONFIG_ARCH_USES_CFI_TRAPS */
 #endif /* CONFIG_MODULES */
 
+#ifndef CFI_NOSEAL
+#define CFI_NOSEAL(x)
+#endif
+
 #endif /* _LINUX_CFI_H */
diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h
index 6b8713675765..a86af9bc8bdc 100644
--- a/include/linux/cfi_types.h
+++ b/include/linux/cfi_types.h
@@ -8,7 +8,7 @@
 #ifdef __ASSEMBLY__
 #include <linux/linkage.h>
 
-#ifdef CONFIG_CFI_CLANG
+#ifdef CONFIG_CFI
 /*
  * Use the __kcfi_typeid_<function> type identifier symbol to
  * annotate indirectly called assembly functions. The compiler emits
@@ -29,17 +29,40 @@
 #define SYM_TYPED_START(name, linkage, align...)	\
 	SYM_TYPED_ENTRY(name, linkage, align)
 
-#else /* CONFIG_CFI_CLANG */
+#else /* CONFIG_CFI */
 
 #define SYM_TYPED_START(name, linkage, align...)	\
 	SYM_START(name, linkage, align)
 
-#endif /* CONFIG_CFI_CLANG */
+#endif /* CONFIG_CFI */
 
 #ifndef SYM_TYPED_FUNC_START
 #define SYM_TYPED_FUNC_START(name) 			\
 	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #endif
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_CFI
+#define DEFINE_CFI_TYPE(name, func)						\
+	/*									\
+	 * Force a reference to the function so the compiler generates		\
+	 * __kcfi_typeid_<func>.						\
+	 */									\
+	__ADDRESSABLE(func);							\
+	/* u32 name __ro_after_init = __kcfi_typeid_<func> */			\
+	extern u32 name;							\
+	asm (									\
+	"	.pushsection	.data..ro_after_init,\"aw\",\%progbits	\n"	\
+	"	.type	" #name ",\%object				\n"	\
+	"	.globl	" #name "					\n"	\
+	"	.p2align	2, 0x0					\n"	\
+	#name ":							\n"	\
+	"	.4byte	__kcfi_typeid_" #func "				\n"	\
+	"	.size	" #name ", 4					\n"	\
+	"	.popsection						\n"	\
+	);
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* _LINUX_CFI_TYPES_H */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 8a0d5466c7be..b760a3c470a5 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -71,9 +71,6 @@ enum {
 
 	/* Cgroup is frozen. */
 	CGRP_FROZEN,
-
-	/* Control group has to be killed. */
-	CGRP_KILL,
 };
 
 /* cgroup_root->flags */
@@ -94,6 +91,12 @@ enum {
 	 * cgroup_threadgroup_rwsem. This makes hot path operations such as
 	 * forks and exits into the slow path and more expensive.
 	 *
+	 * Alleviate the contention between fork, exec, exit operations and
+	 * writing to cgroup.procs by taking a per threadgroup rwsem instead of
+	 * the global cgroup_threadgroup_rwsem. Fork and other operations
+	 * from threads in different thread groups no longer contend with
+	 * writing to cgroup.procs.
+	 *
 	 * The static usage pattern of creating a cgroup, enabling controllers,
 	 * and then seeding it with CLONE_INTO_CGROUP doesn't require write
 	 * locking cgroup_threadgroup_rwsem and thus doesn't benefit from
@@ -115,6 +118,16 @@ enum {
 	 * Enable recursive subtree protection
 	 */
 	CGRP_ROOT_MEMORY_RECURSIVE_PROT = (1 << 18),
+
+	/*
+	 * Enable hugetlb accounting for the memory controller.
+	 */
+	CGRP_ROOT_MEMORY_HUGETLB_ACCOUNTING = (1 << 19),
+
+	/*
+	 * Enable legacy local pids.events.
+	 */
+	CGRP_ROOT_PIDS_LOCAL_EVENTS = (1 << 20),
 };
 
 /* cftype->flags */
@@ -133,6 +146,17 @@ enum {
 	__CFTYPE_ADDED		= (1 << 18),
 };
 
+enum cgroup_attach_lock_mode {
+	/* Default */
+	CGRP_ATTACH_LOCK_GLOBAL,
+
+	/* When pid=0 && threadgroup=false, see comments in cgroup_procs_write_start */
+	CGRP_ATTACH_LOCK_NONE,
+
+	/* When favordynmods is on, see comments above CGRP_ROOT_FAVOR_DYNMODS */
+	CGRP_ATTACH_LOCK_PER_THREADGROUP,
+};
+
 /*
  * cgroup_file is the handle for a file instance created in a cgroup which
  * is used, for example, to generate file changed notifications.  This can
@@ -162,13 +186,31 @@ struct cgroup_subsys_state {
 	/* reference count - access via css_[try]get() and css_put() */
 	struct percpu_ref refcnt;
 
-	/* siblings list anchored at the parent's ->children */
+	/*
+	 * Depending on the context, this field is initialized
+	 * via css_rstat_init() at different places:
+	 *
+	 * when css is associated with cgroup::self
+	 *   when css->cgroup is the root cgroup
+	 *     performed in cgroup_init()
+	 *   when css->cgroup is not the root cgroup
+	 *     performed in cgroup_create()
+	 * when css is associated with a subsystem
+	 *   when css->cgroup is the root cgroup
+	 *     performed in cgroup_init_subsys() in the non-early path
+	 *   when css->cgroup is not the root cgroup
+	 *     performed in css_create()
+	 */
+	struct css_rstat_cpu __percpu *rstat_cpu;
+
+	/*
+	 * siblings list anchored at the parent's ->children
+	 *
+	 * linkage is protected by cgroup_mutex or RCU
+	 */
 	struct list_head sibling;
 	struct list_head children;
 
-	/* flush target list anchored at cgrp->rstat_css_list */
-	struct list_head rstat_css_node;
-
 	/*
 	 * PI: Subsys-unique ID.  0 is unused and root is always 1.  The
 	 * matching css can be looked up using css_from_id().
@@ -200,6 +242,24 @@ struct cgroup_subsys_state {
 	 * fields of the containing structure.
 	 */
 	struct cgroup_subsys_state *parent;
+
+	/*
+	 * Keep track of total numbers of visible descendant CSSes.
+	 * The total number of dying CSSes is tracked in
+	 * css->cgroup->nr_dying_subsys[ssid].
+	 * Protected by cgroup_mutex.
+	 */
+	int nr_descendants;
+
+	/*
+	 * A singly-linked list of css structures to be rstat flushed.
+	 * This is a scratch field to be used exclusively by
+	 * css_rstat_flush().
+	 *
+	 * Protected by rstat_base_lock when css is cgroup::self.
+	 * Protected by css->ss->rstat_ss_lock otherwise.
+	 */
+	struct cgroup_subsys_state *rstat_flush_next;
 };
 
 /*
@@ -238,7 +298,7 @@ struct css_set {
 	 * Lists running through all tasks using this cgroup group.
 	 * mg_tasks lists tasks which belong to this cset but are in the
 	 * process of being migrated out or in.  Protected by
-	 * css_set_rwsem, but, during migration, once tasks are moved to
+	 * css_set_lock, but, during migration, once tasks are moved to
 	 * mg_tasks, it can be read safely while holding cgroup_mutex.
 	 */
 	struct list_head tasks;
@@ -305,14 +365,15 @@ struct cgroup_base_stat {
 #ifdef CONFIG_SCHED_CORE
 	u64 forceidle_sum;
 #endif
+	u64 ntime;
 };
 
 /*
  * rstat - cgroup scalable recursive statistics.  Accounting is done
- * per-cpu in cgroup_rstat_cpu which is then lazily propagated up the
+ * per-cpu in css_rstat_cpu which is then lazily propagated up the
  * hierarchy on reads.
  *
- * When a stat gets updated, the cgroup_rstat_cpu and its ancestors are
+ * When a stat gets updated, the css_rstat_cpu and its ancestors are
  * linked into the updated tree.  On the following read, propagation only
  * considers and consumes the updated tree.  This makes reading O(the
  * number of descendants which have been active since last read) instead of
@@ -324,10 +385,26 @@ struct cgroup_base_stat {
  * frequency decreases the cost of each read.
  *
  * This struct hosts both the fields which implement the above -
- * updated_children and updated_next - and the fields which track basic
- * resource statistics on top of it - bsync, bstat and last_bstat.
+ * updated_children and updated_next.
+ */
+struct css_rstat_cpu {
+	/*
+	 * Child cgroups with stat updates on this cpu since the last read
+	 * are linked on the parent's ->updated_children through
+	 * ->updated_next. updated_children is terminated by its container css.
+	 */
+	struct cgroup_subsys_state *updated_children;
+	struct cgroup_subsys_state *updated_next;	/* NULL if not on the list */
+
+	struct llist_node lnode;		/* lockless list for update */
+	struct cgroup_subsys_state *owner;	/* back pointer */
+};
+
+/*
+ * This struct hosts the fields which track basic resource statistics on
+ * top of it - bsync, bstat and last_bstat.
  */
-struct cgroup_rstat_cpu {
+struct cgroup_rstat_base_cpu {
 	/*
 	 * ->bsync protects ->bstat.  These are the only fields which get
 	 * updated in the hot path.
@@ -342,18 +419,18 @@ struct cgroup_rstat_cpu {
 	struct cgroup_base_stat last_bstat;
 
 	/*
-	 * Child cgroups with stat updates on this cpu since the last read
-	 * are linked on the parent's ->updated_children through
-	 * ->updated_next.
-	 *
-	 * In addition to being more compact, singly-linked list pointing
-	 * to the cgroup makes it unnecessary for each per-cpu struct to
-	 * point back to the associated cgroup.
-	 *
-	 * Protected by per-cpu cgroup_rstat_cpu_lock.
+	 * This field is used to record the cumulative per-cpu time of
+	 * the cgroup and its descendants. Currently it can be read via
+	 * eBPF/drgn etc, and we are still trying to determine how to
+	 * expose it in the cgroupfs interface.
 	 */
-	struct cgroup *updated_children;	/* terminated by self cgroup */
-	struct cgroup *updated_next;		/* NULL iff not on the list */
+	struct cgroup_base_stat subtree_bstat;
+
+	/*
+	 * Snapshots at the last reading. These are used to calculate the
+	 * deltas to propagate to the per-cpu subtree_bstat.
+	 */
+	struct cgroup_base_stat last_subtree_bstat;
 };
 
 struct cgroup_freezer_state {
@@ -361,7 +438,7 @@ struct cgroup_freezer_state {
 	bool freeze;
 
 	/* Should the cgroup actually be frozen? */
-	int e_freeze;
+	bool e_freeze;
 
 	/* Fields below are protected by css_set_lock */
 
@@ -373,6 +450,23 @@ struct cgroup_freezer_state {
 	 * frozen, SIGSTOPped, and PTRACEd.
 	 */
 	int nr_frozen_tasks;
+
+	/* Freeze time data consistency protection */
+	seqcount_spinlock_t freeze_seq;
+
+	/*
+	 * Most recent time the cgroup was requested to freeze.
+	 * Accesses guarded by freeze_seq counter. Writes serialized
+	 * by css_set_lock.
+	 */
+	u64 freeze_start_nsec;
+
+	/*
+	 * Total duration the cgroup has spent freezing.
+	 * Accesses guarded by freeze_seq counter. Writes serialized
+	 * by css_set_lock.
+	 */
+	u64 frozen_nsec;
 };
 
 struct cgroup {
@@ -424,6 +518,9 @@ struct cgroup {
 
 	int nr_threaded_children;	/* # of live threaded child cgroups */
 
+	/* sequence number for cgroup.kill, serialized by css_set_lock. */
+	unsigned int kill_seq;
+
 	struct kernfs_node *kn;		/* cgroup kernfs entry */
 	struct cgroup_file procs_file;	/* handle for "cgroup.procs" */
 	struct cgroup_file events_file;	/* handle for "cgroup.events" */
@@ -446,6 +543,12 @@ struct cgroup {
 	/* Private pointers for each registered subsystem */
 	struct cgroup_subsys_state __rcu *subsys[CGROUP_SUBSYS_COUNT];
 
+	/*
+	 * Keep track of total number of dying CSSes at and below this cgroup.
+	 * Protected by cgroup_mutex.
+	 */
+	int nr_dying_subsys[CGROUP_SUBSYS_COUNT];
+
 	struct cgroup_root *root;
 
 	/*
@@ -473,9 +576,23 @@ struct cgroup {
 	struct cgroup *dom_cgrp;
 	struct cgroup *old_dom_cgrp;		/* used while enabling threaded */
 
-	/* per-cpu recursive resource statistics */
-	struct cgroup_rstat_cpu __percpu *rstat_cpu;
-	struct list_head rstat_css_list;
+	/*
+	 * Depending on the context, this field is initialized via
+	 * css_rstat_init() at different places:
+	 *
+	 * when cgroup is the root cgroup
+	 *   performed in cgroup_setup_root()
+	 * otherwise
+	 *   performed in cgroup_create()
+	 */
+	struct cgroup_rstat_base_cpu __percpu *rstat_base_cpu;
+
+	/*
+	 * Add padding to keep the read mostly rstat per-cpu pointer on a
+	 * different cacheline than the following *bstat fields which can have
+	 * frequent updates.
+	 */
+	CACHELINE_PADDING(_pad_);
 
 	/* cgroup basic resource statistics */
 	struct cgroup_base_stat last_bstat;
@@ -501,9 +618,6 @@ struct cgroup {
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 
-	/* If there is block congestion on this cgroup. */
-	atomic_t congestion_count;
-
 	/* Used to store internal freezer state */
 	struct cgroup_freezer_state freezer;
 
@@ -529,6 +643,10 @@ struct cgroup_root {
 	/* Unique id for this hierarchy. */
 	int hierarchy_id;
 
+	/* A list running through the active hierarchies */
+	struct list_head root_list;
+	struct rcu_head rcu;	/* Must be near the top */
+
 	/*
 	 * The root cgroup. The containing cgroup_root will be destroyed on its
 	 * release. cgrp->ancestors[0] will be used overflowing into the
@@ -542,9 +660,6 @@ struct cgroup_root {
 	/* Number of cgroups in the hierarchy, used only for /proc/cgroups */
 	atomic_t nr_cgrps;
 
-	/* A list running through the active hierarchies */
-	struct list_head root_list;
-
 	/* Hierarchy-specific flags */
 	unsigned int flags;
 
@@ -564,9 +679,8 @@ struct cgroup_root {
  */
 struct cftype {
 	/*
-	 * By convention, the name should begin with the name of the
-	 * subsystem, followed by a period.  Zero length string indicates
-	 * end of cftype array.
+	 * Name of the subsystem is prepended in cgroup_file_name().
+	 * Zero length string indicates end of cftype array.
 	 */
 	char name[MAX_CFTYPE_NAME];
 	unsigned long private;
@@ -642,9 +756,7 @@ struct cftype {
 	__poll_t (*poll)(struct kernfs_open_file *of,
 			 struct poll_table_struct *pt);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lock_class_key	lockdep_key;
-#endif
 };
 
 /*
@@ -658,14 +770,16 @@ struct cgroup_subsys {
 	void (*css_released)(struct cgroup_subsys_state *css);
 	void (*css_free)(struct cgroup_subsys_state *css);
 	void (*css_reset)(struct cgroup_subsys_state *css);
+	void (*css_killed)(struct cgroup_subsys_state *css);
 	void (*css_rstat_flush)(struct cgroup_subsys_state *css, int cpu);
 	int (*css_extra_stat_show)(struct seq_file *seq,
 				   struct cgroup_subsys_state *css);
+	int (*css_local_stat_show)(struct seq_file *seq,
+				   struct cgroup_subsys_state *css);
 
 	int (*can_attach)(struct cgroup_taskset *tset);
 	void (*cancel_attach)(struct cgroup_taskset *tset);
 	void (*attach)(struct cgroup_taskset *tset);
-	void (*post_attach)(void);
 	int (*can_fork)(struct task_struct *task,
 			struct css_set *cset);
 	void (*cancel_fork)(struct task_struct *task, struct css_set *cset);
@@ -735,20 +849,32 @@ struct cgroup_subsys {
 	 * specifies the mask of subsystems that this one depends on.
 	 */
 	unsigned int depends_on;
+
+	spinlock_t rstat_ss_lock;
+	struct llist_head __percpu *lhead; /* lockless update list head */
 };
 
 extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
+extern bool cgroup_enable_per_threadgroup_rwsem;
+
+struct cgroup_of_peak {
+	unsigned long		value;
+	struct list_head	list;
+};
 
 /**
  * cgroup_threadgroup_change_begin - threadgroup exclusion for cgroups
  * @tsk: target task
  *
  * Allows cgroup operations to synchronize against threadgroup changes
- * using a percpu_rw_semaphore.
+ * using a global percpu_rw_semaphore and a per threadgroup rw_semaphore when
+ * favordynmods is on. See the comment above CGRP_ROOT_FAVOR_DYNMODS definition.
  */
 static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
 {
 	percpu_down_read(&cgroup_threadgroup_rwsem);
+	if (cgroup_enable_per_threadgroup_rwsem)
+		down_read(&tsk->signal->cgroup_threadgroup_rwsem);
 }
 
 /**
@@ -759,6 +885,8 @@ static inline void cgroup_threadgroup_change_begin(struct task_struct *tsk)
  */
 static inline void cgroup_threadgroup_change_end(struct task_struct *tsk)
 {
+	if (cgroup_enable_per_threadgroup_rwsem)
+		up_read(&tsk->signal->cgroup_threadgroup_rwsem);
 	percpu_up_read(&cgroup_threadgroup_rwsem);
 }
 
@@ -806,14 +934,12 @@ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 #endif
 }
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-#ifdef CONFIG_CGROUP_NET_CLASSID
 	return READ_ONCE(skcd->classid);
-#else
-	return 0;
-#endif
 }
+#endif
 
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
@@ -823,13 +949,13 @@ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 #endif
 }
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-#ifdef CONFIG_CGROUP_NET_CLASSID
 	WRITE_ONCE(skcd->classid, classid);
-#endif
 }
+#endif
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */
 
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 567c547cf371..bc892e3b37ee 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -10,8 +10,8 @@
  */
 
 #include <linux/sched.h>
-#include <linux/cpumask.h>
 #include <linux/nodemask.h>
+#include <linux/list.h>
 #include <linux/rculist.h>
 #include <linux/cgroupstats.h>
 #include <linux/fs.h>
@@ -19,6 +19,7 @@
 #include <linux/kernfs.h>
 #include <linux/jump_label.h>
 #include <linux/types.h>
+#include <linux/notifier.h>
 #include <linux/ns_common.h>
 #include <linux/nsproxy.h>
 #include <linux/user_namespace.h>
@@ -26,11 +27,10 @@
 #include <linux/kernel_stat.h>
 
 #include <linux/cgroup-defs.h>
+#include <linux/cgroup_namespace.h>
 
 struct kernel_clone_args;
 
-#ifdef CONFIG_CGROUPS
-
 /*
  * All weight knobs on the default hierarchy should use the following min,
  * default and max values.  The default value is the logarithmic center of
@@ -40,13 +40,13 @@ struct kernel_clone_args;
 #define CGROUP_WEIGHT_DFL		100
 #define CGROUP_WEIGHT_MAX		10000
 
-/* walk only threadgroup leaders */
-#define CSS_TASK_ITER_PROCS		(1U << 0)
-/* walk all threaded css_sets in the domain */
-#define CSS_TASK_ITER_THREADED		(1U << 1)
+#ifdef CONFIG_CGROUPS
 
-/* internal flags */
-#define CSS_TASK_ITER_SKIPPED		(1U << 16)
+enum css_task_iter_flags {
+	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
+	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
+	CSS_TASK_ITER_SKIPPED  = (1U << 16), /* internal flags */
+};
 
 /* a css_task_iter should be treated as an opaque object */
 struct css_task_iter {
@@ -68,9 +68,16 @@ struct css_task_iter {
 	struct list_head		iters_node;	/* css_set->task_iters */
 };
 
+enum cgroup_lifetime_events {
+	CGROUP_LIFETIME_ONLINE,
+	CGROUP_LIFETIME_OFFLINE,
+};
+
 extern struct file_system_type cgroup_fs_type;
 extern struct cgroup_root cgrp_dfl_root;
 extern struct css_set init_css_set;
+extern spinlock_t css_set_lock;
+extern struct blocking_notifier_head cgroup_lifetime_notifier;
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _cgrp_subsys;
 #include <linux/cgroup_subsys.h>
@@ -114,11 +121,11 @@ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from);
 
 int cgroup_add_dfl_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_add_legacy_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
+int cgroup_add_cftypes(struct cgroup_subsys *ss, struct cftype *cfts);
 int cgroup_rm_cftypes(struct cftype *cfts);
 void cgroup_file_notify(struct cgroup_file *cfile);
 void cgroup_file_show(struct cgroup_file *cfile, bool show);
 
-int task_cgroup_path(struct task_struct *task, char *buf, size_t buflen);
 int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry);
 int proc_cgroup_show(struct seq_file *m, struct pid_namespace *ns,
 		     struct pid *pid, struct task_struct *tsk);
@@ -130,9 +137,10 @@ extern void cgroup_cancel_fork(struct task_struct *p,
 			       struct kernel_clone_args *kargs);
 extern void cgroup_post_fork(struct task_struct *p,
 			     struct kernel_clone_args *kargs);
-void cgroup_exit(struct task_struct *p);
-void cgroup_release(struct task_struct *p);
-void cgroup_free(struct task_struct *p);
+void cgroup_task_exit(struct task_struct *p);
+void cgroup_task_dead(struct task_struct *p);
+void cgroup_task_release(struct task_struct *p);
+void cgroup_task_free(struct task_struct *p);
 
 int cgroup_init_early(void);
 int cgroup_init(void);
@@ -345,7 +353,23 @@ static inline u64 cgroup_id(const struct cgroup *cgrp)
  */
 static inline bool css_is_dying(struct cgroup_subsys_state *css)
 {
-	return !(css->flags & CSS_NO_REF) && percpu_ref_is_dying(&css->refcnt);
+	return css->flags & CSS_DYING;
+}
+
+static inline bool css_is_online(struct cgroup_subsys_state *css)
+{
+	return css->flags & CSS_ONLINE;
+}
+
+static inline bool css_is_self(struct cgroup_subsys_state *css)
+{
+	if (css == &css->cgroup->self) {
+		/* cgroup::self should not have subsystem association */
+		WARN_ON(css->ss != NULL);
+		return true;
+	}
+
+	return false;
 }
 
 static inline void cgroup_get(struct cgroup *cgrp)
@@ -389,7 +413,6 @@ static inline void cgroup_unlock(void)
  * as locks used during the cgroup_subsys::attach() methods.
  */
 #ifdef CONFIG_PROVE_RCU
-extern spinlock_t css_set_lock;
 #define task_css_set_check(task, __c)					\
 	rcu_dereference_check((task)->cgroups,				\
 		rcu_read_lock_sched_held() ||				\
@@ -634,6 +657,7 @@ static inline void cgroup_kthread_ready(void)
 }
 
 void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen);
+struct cgroup *__cgroup_get_from_id(u64 id);
 struct cgroup *cgroup_get_from_id(u64 id);
 #else /* !CONFIG_CGROUPS */
 
@@ -657,9 +681,10 @@ static inline void cgroup_cancel_fork(struct task_struct *p,
 				      struct kernel_clone_args *kargs) {}
 static inline void cgroup_post_fork(struct task_struct *p,
 				    struct kernel_clone_args *kargs) {}
-static inline void cgroup_exit(struct task_struct *p) {}
-static inline void cgroup_release(struct task_struct *p) {}
-static inline void cgroup_free(struct task_struct *p) {}
+static inline void cgroup_task_exit(struct task_struct *p) {}
+static inline void cgroup_task_dead(struct task_struct *p) {}
+static inline void cgroup_task_release(struct task_struct *p) {}
+static inline void cgroup_task_free(struct task_struct *p) {}
 
 static inline int cgroup_init_early(void) { return 0; }
 static inline int cgroup_init(void) { return 0; }
@@ -690,10 +715,8 @@ static inline void cgroup_path_from_kernfs_id(u64 id, char *buf, size_t buflen)
 /*
  * cgroup scalable recursive statistics.
  */
-void cgroup_rstat_updated(struct cgroup *cgrp, int cpu);
-void cgroup_rstat_flush(struct cgroup *cgrp);
-void cgroup_rstat_flush_hold(struct cgroup *cgrp);
-void cgroup_rstat_flush_release(void);
+void css_rstat_updated(struct cgroup_subsys_state *css, int cpu);
+void css_rstat_flush(struct cgroup_subsys_state *css);
 
 /*
  * Basic resource stats.
@@ -769,50 +792,6 @@ static inline void cgroup_sk_free(struct sock_cgroup_data *skcd) {}
 
 #endif	/* CONFIG_CGROUP_DATA */
 
-struct cgroup_namespace {
-	struct ns_common	ns;
-	struct user_namespace	*user_ns;
-	struct ucounts		*ucounts;
-	struct css_set          *root_cset;
-};
-
-extern struct cgroup_namespace init_cgroup_ns;
-
-#ifdef CONFIG_CGROUPS
-
-void free_cgroup_ns(struct cgroup_namespace *ns);
-
-struct cgroup_namespace *copy_cgroup_ns(unsigned long flags,
-					struct user_namespace *user_ns,
-					struct cgroup_namespace *old_ns);
-
-int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
-		   struct cgroup_namespace *ns);
-
-#else /* !CONFIG_CGROUPS */
-
-static inline void free_cgroup_ns(struct cgroup_namespace *ns) { }
-static inline struct cgroup_namespace *
-copy_cgroup_ns(unsigned long flags, struct user_namespace *user_ns,
-	       struct cgroup_namespace *old_ns)
-{
-	return old_ns;
-}
-
-#endif /* !CONFIG_CGROUPS */
-
-static inline void get_cgroup_ns(struct cgroup_namespace *ns)
-{
-	if (ns)
-		refcount_inc(&ns->ns.count);
-}
-
-static inline void put_cgroup_ns(struct cgroup_namespace *ns)
-{
-	if (ns && refcount_dec_and_test(&ns->ns.count))
-		free_cgroup_ns(ns);
-}
-
 #ifdef CONFIG_CGROUPS
 
 void cgroup_enter_frozen(void);
@@ -856,4 +835,8 @@ static inline void cgroup_bpf_put(struct cgroup *cgrp) {}
 
 #endif /* CONFIG_CGROUP_BPF */
 
+struct cgroup *task_get_cgroup1(struct task_struct *tsk, int hierarchy_id);
+
+struct cgroup_of_peak *of_peak(struct kernfs_open_file *of);
+
 #endif /* _LINUX_CGROUP_H */
diff --git a/include/linux/cgroup_dmem.h b/include/linux/cgroup_dmem.h
new file mode 100644
index 000000000000..dd4869f1d736
--- /dev/null
+++ b/include/linux/cgroup_dmem.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2023-2024 Intel Corporation
+ */
+
+#ifndef _CGROUP_DMEM_H
+#define _CGROUP_DMEM_H
+
+#include <linux/types.h>
+#include <linux/llist.h>
+
+struct dmem_cgroup_pool_state;
+
+/* Opaque definition of a cgroup region, used internally */
+struct dmem_cgroup_region;
+
+#if IS_ENABLED(CONFIG_CGROUP_DMEM)
+struct dmem_cgroup_region *dmem_cgroup_register_region(u64 size, const char *name_fmt, ...) __printf(2,3);
+void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region);
+int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
+			   struct dmem_cgroup_pool_state **ret_pool,
+			   struct dmem_cgroup_pool_state **ret_limit_pool);
+void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size);
+bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
+				      struct dmem_cgroup_pool_state *test_pool,
+				      bool ignore_low, bool *ret_hit_low);
+
+void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool);
+#else
+static inline __printf(2,3) struct dmem_cgroup_region *
+dmem_cgroup_register_region(u64 size, const char *name_fmt, ...)
+{
+	return NULL;
+}
+
+static inline void dmem_cgroup_unregister_region(struct dmem_cgroup_region *region)
+{ }
+
+static inline int dmem_cgroup_try_charge(struct dmem_cgroup_region *region, u64 size,
+					 struct dmem_cgroup_pool_state **ret_pool,
+					 struct dmem_cgroup_pool_state **ret_limit_pool)
+{
+	*ret_pool = NULL;
+
+	if (ret_limit_pool)
+		*ret_limit_pool = NULL;
+
+	return 0;
+}
+
+static inline void dmem_cgroup_uncharge(struct dmem_cgroup_pool_state *pool, u64 size)
+{ }
+
+static inline
+bool dmem_cgroup_state_evict_valuable(struct dmem_cgroup_pool_state *limit_pool,
+				      struct dmem_cgroup_pool_state *test_pool,
+				      bool ignore_low, bool *ret_hit_low)
+{
+	return true;
+}
+
+static inline void dmem_cgroup_pool_state_put(struct dmem_cgroup_pool_state *pool)
+{ }
+
+#endif
+#endif	/* _CGROUP_DMEM_H */
diff --git a/include/linux/cgroup_namespace.h b/include/linux/cgroup_namespace.h
new file mode 100644
index 000000000000..78a8418558a4
--- /dev/null
+++ b/include/linux/cgroup_namespace.h
@@ -0,0 +1,58 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CGROUP_NAMESPACE_H
+#define _LINUX_CGROUP_NAMESPACE_H
+
+#include <linux/ns_common.h>
+
+struct cgroup_namespace {
+	struct ns_common	ns;
+	struct user_namespace	*user_ns;
+	struct ucounts		*ucounts;
+	struct css_set          *root_cset;
+};
+
+extern struct cgroup_namespace init_cgroup_ns;
+
+#ifdef CONFIG_CGROUPS
+
+static inline struct cgroup_namespace *to_cg_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct cgroup_namespace, ns);
+}
+
+void free_cgroup_ns(struct cgroup_namespace *ns);
+
+struct cgroup_namespace *copy_cgroup_ns(u64 flags,
+					struct user_namespace *user_ns,
+					struct cgroup_namespace *old_ns);
+
+int cgroup_path_ns(struct cgroup *cgrp, char *buf, size_t buflen,
+		   struct cgroup_namespace *ns);
+
+static inline void get_cgroup_ns(struct cgroup_namespace *ns)
+{
+	ns_ref_inc(ns);
+}
+
+static inline void put_cgroup_ns(struct cgroup_namespace *ns)
+{
+	if (ns_ref_put(ns))
+		free_cgroup_ns(ns);
+}
+
+#else /* !CONFIG_CGROUPS */
+
+static inline void free_cgroup_ns(struct cgroup_namespace *ns) { }
+static inline struct cgroup_namespace *
+copy_cgroup_ns(u64 flags, struct user_namespace *user_ns,
+	       struct cgroup_namespace *old_ns)
+{
+	return old_ns;
+}
+
+static inline void get_cgroup_ns(struct cgroup_namespace *ns) { }
+static inline void put_cgroup_ns(struct cgroup_namespace *ns) { }
+
+#endif /* !CONFIG_CGROUPS */
+
+#endif /* _LINUX_CGROUP_NAMESPACE_H */
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index 445235487230..3fd0bcbf3080 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -65,6 +65,10 @@ SUBSYS(rdma)
 SUBSYS(misc)
 #endif
 
+#if IS_ENABLED(CONFIG_CGROUP_DMEM)
+SUBSYS(dmem)
+#endif
+
 /*
  * The following subsystems are not supported on the default hierarchy.
  */
diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
new file mode 100644
index 000000000000..8d41b917c77d
--- /dev/null
+++ b/include/linux/cleanup.h
@@ -0,0 +1,534 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CLEANUP_H
+#define _LINUX_CLEANUP_H
+
+#include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/args.h>
+
+/**
+ * DOC: scope-based cleanup helpers
+ *
+ * The "goto error" pattern is notorious for introducing subtle resource
+ * leaks. It is tedious and error prone to add new resource acquisition
+ * constraints into code paths that already have several unwind
+ * conditions. The "cleanup" helpers enable the compiler to help with
+ * this tedium and can aid in maintaining LIFO (last in first out)
+ * unwind ordering to avoid unintentional leaks.
+ *
+ * As drivers make up the majority of the kernel code base, here is an
+ * example of using these helpers to clean up PCI drivers. The target of
+ * the cleanups are occasions where a goto is used to unwind a device
+ * reference (pci_dev_put()), or unlock the device (pci_dev_unlock())
+ * before returning.
+ *
+ * The DEFINE_FREE() macro can arrange for PCI device references to be
+ * dropped when the associated variable goes out of scope::
+ *
+ *	DEFINE_FREE(pci_dev_put, struct pci_dev *, if (_T) pci_dev_put(_T))
+ *	...
+ *	struct pci_dev *dev __free(pci_dev_put) =
+ *		pci_get_slot(parent, PCI_DEVFN(0, 0));
+ *
+ * The above will automatically call pci_dev_put() if @dev is non-NULL
+ * when @dev goes out of scope (automatic variable scope). If a function
+ * wants to invoke pci_dev_put() on error, but return @dev (i.e. without
+ * freeing it) on success, it can do::
+ *
+ *	return no_free_ptr(dev);
+ *
+ * ...or::
+ *
+ *	return_ptr(dev);
+ *
+ * The DEFINE_GUARD() macro can arrange for the PCI device lock to be
+ * dropped when the scope where guard() is invoked ends::
+ *
+ *	DEFINE_GUARD(pci_dev, struct pci_dev *, pci_dev_lock(_T), pci_dev_unlock(_T))
+ *	...
+ *	guard(pci_dev)(dev);
+ *
+ * The lifetime of the lock obtained by the guard() helper follows the
+ * scope of automatic variable declaration. Take the following example::
+ *
+ *	func(...)
+ *	{
+ *		if (...) {
+ *			...
+ *			guard(pci_dev)(dev); // pci_dev_lock() invoked here
+ *			...
+ *		} // <- implied pci_dev_unlock() triggered here
+ *	}
+ *
+ * Observe the lock is held for the remainder of the "if ()" block not
+ * the remainder of "func()".
+ *
+ * The ACQUIRE() macro can be used in all places that guard() can be
+ * used and additionally support conditional locks::
+ *
+ *	DEFINE_GUARD_COND(pci_dev, _try, pci_dev_trylock(_T))
+ *	...
+ *	ACQUIRE(pci_dev_try, lock)(dev);
+ *	rc = ACQUIRE_ERR(pci_dev_try, &lock);
+ *	if (rc)
+ *		return rc;
+ *	// @lock is held
+ *
+ * Now, when a function uses both __free() and guard()/ACQUIRE(), or
+ * multiple instances of __free(), the LIFO order of variable definition
+ * order matters. GCC documentation says:
+ *
+ * "When multiple variables in the same scope have cleanup attributes,
+ * at exit from the scope their associated cleanup functions are run in
+ * reverse order of definition (last defined, first cleanup)."
+ *
+ * When the unwind order matters it requires that variables be defined
+ * mid-function scope rather than at the top of the file.  Take the
+ * following example and notice the bug highlighted by "!!"::
+ *
+ *	LIST_HEAD(list);
+ *	DEFINE_MUTEX(lock);
+ *
+ *	struct object {
+ *	        struct list_head node;
+ *	};
+ *
+ *	static struct object *alloc_add(void)
+ *	{
+ *	        struct object *obj;
+ *
+ *	        lockdep_assert_held(&lock);
+ *	        obj = kzalloc(sizeof(*obj), GFP_KERNEL);
+ *	        if (obj) {
+ *	                LIST_HEAD_INIT(&obj->node);
+ *	                list_add(obj->node, &list):
+ *	        }
+ *	        return obj;
+ *	}
+ *
+ *	static void remove_free(struct object *obj)
+ *	{
+ *	        lockdep_assert_held(&lock);
+ *	        list_del(&obj->node);
+ *	        kfree(obj);
+ *	}
+ *
+ *	DEFINE_FREE(remove_free, struct object *, if (_T) remove_free(_T))
+ *	static int init(void)
+ *	{
+ *	        struct object *obj __free(remove_free) = NULL;
+ *	        int err;
+ *
+ *	        guard(mutex)(&lock);
+ *	        obj = alloc_add();
+ *
+ *	        if (!obj)
+ *	                return -ENOMEM;
+ *
+ *	        err = other_init(obj);
+ *	        if (err)
+ *	                return err; // remove_free() called without the lock!!
+ *
+ *	        no_free_ptr(obj);
+ *	        return 0;
+ *	}
+ *
+ * That bug is fixed by changing init() to call guard() and define +
+ * initialize @obj in this order::
+ *
+ *	guard(mutex)(&lock);
+ *	struct object *obj __free(remove_free) = alloc_add();
+ *
+ * Given that the "__free(...) = NULL" pattern for variables defined at
+ * the top of the function poses this potential interdependency problem
+ * the recommendation is to always define and assign variables in one
+ * statement and not group variable definitions at the top of the
+ * function when __free() is used.
+ *
+ * Lastly, given that the benefit of cleanup helpers is removal of
+ * "goto", and that the "goto" statement can jump between scopes, the
+ * expectation is that usage of "goto" and cleanup helpers is never
+ * mixed in the same function. I.e. for a given routine, convert all
+ * resources that need a "goto" cleanup to scope-based cleanup, or
+ * convert none of them.
+ */
+
+/*
+ * DEFINE_FREE(name, type, free):
+ *	simple helper macro that defines the required wrapper for a __free()
+ *	based cleanup function. @free is an expression using '_T' to access the
+ *	variable. @free should typically include a NULL test before calling a
+ *	function, see the example below.
+ *
+ * __free(name):
+ *	variable attribute to add a scoped based cleanup to the variable.
+ *
+ * no_free_ptr(var):
+ *	like a non-atomic xchg(var, NULL), such that the cleanup function will
+ *	be inhibited -- provided it sanely deals with a NULL value.
+ *
+ *	NOTE: this has __must_check semantics so that it is harder to accidentally
+ *	leak the resource.
+ *
+ * return_ptr(p):
+ *	returns p while inhibiting the __free().
+ *
+ * Ex.
+ *
+ * DEFINE_FREE(kfree, void *, if (_T) kfree(_T))
+ *
+ * void *alloc_obj(...)
+ * {
+ *	struct obj *p __free(kfree) = kmalloc(...);
+ *	if (!p)
+ *		return NULL;
+ *
+ *	if (!init_obj(p))
+ *		return NULL;
+ *
+ *	return_ptr(p);
+ * }
+ *
+ * NOTE: the DEFINE_FREE()'s @free expression includes a NULL test even though
+ * kfree() is fine to be called with a NULL value. This is on purpose. This way
+ * the compiler sees the end of our alloc_obj() function as:
+ *
+ *	tmp = p;
+ *	p = NULL;
+ *	if (p)
+ *		kfree(p);
+ *	return tmp;
+ *
+ * And through the magic of value-propagation and dead-code-elimination, it
+ * eliminates the actual cleanup call and compiles into:
+ *
+ *	return p;
+ *
+ * Without the NULL test it turns into a mess and the compiler can't help us.
+ */
+
+#define DEFINE_FREE(_name, _type, _free) \
+	static __always_inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; }
+
+#define __free(_name)	__cleanup(__free_##_name)
+
+#define __get_and_null(p, nullvalue)	    \
+	({                                  \
+		auto __ptr = &(p);	    \
+		auto __val = *__ptr;	    \
+		*__ptr = nullvalue;         \
+		__val;                      \
+	})
+
+static __always_inline __must_check
+const volatile void * __must_check_fn(const volatile void *val)
+{ return val; }
+
+#define no_free_ptr(p) \
+	((typeof(p)) __must_check_fn((__force const volatile void *)__get_and_null(p, NULL)))
+
+#define return_ptr(p)	return no_free_ptr(p)
+
+/*
+ * Only for situations where an allocation is handed in to another function
+ * and consumed by that function on success.
+ *
+ *	struct foo *f __free(kfree) = kzalloc(sizeof(*f), GFP_KERNEL);
+ *
+ *	setup(f);
+ *	if (some_condition)
+ *		return -EINVAL;
+ *	....
+ *	ret = bar(f);
+ *	if (!ret)
+ *		retain_and_null_ptr(f);
+ *	return ret;
+ *
+ * After retain_and_null_ptr(f) the variable f is NULL and cannot be
+ * dereferenced anymore.
+ */
+#define retain_and_null_ptr(p)		((void)__get_and_null(p, NULL))
+
+/*
+ * DEFINE_CLASS(name, type, exit, init, init_args...):
+ *	helper to define the destructor and constructor for a type.
+ *	@exit is an expression using '_T' -- similar to FREE above.
+ *	@init is an expression in @init_args resulting in @type
+ *
+ * EXTEND_CLASS(name, ext, init, init_args...):
+ *	extends class @name to @name@ext with the new constructor
+ *
+ * CLASS(name, var)(args...):
+ *	declare the variable @var as an instance of the named class
+ *
+ * CLASS_INIT(name, var, init_expr):
+ *	declare the variable @var as an instance of the named class with
+ *	custom initialization expression.
+ *
+ * Ex.
+ *
+ * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd)
+ *
+ *	CLASS(fdget, f)(fd);
+ *	if (fd_empty(f))
+ *		return -EBADF;
+ *
+ *	// use 'f' without concern
+ */
+
+#define DEFINE_CLASS(_name, _type, _exit, _init, _init_args...)		\
+typedef _type class_##_name##_t;					\
+static __always_inline void class_##_name##_destructor(_type *p)	\
+{ _type _T = *p; _exit; }						\
+static __always_inline _type class_##_name##_constructor(_init_args)	\
+{ _type t = _init; return t; }
+
+#define EXTEND_CLASS(_name, ext, _init, _init_args...)			\
+typedef class_##_name##_t class_##_name##ext##_t;			\
+static __always_inline void class_##_name##ext##_destructor(class_##_name##_t *p) \
+{ class_##_name##_destructor(p); }					\
+static __always_inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
+{ class_##_name##_t t = _init; return t; }
+
+#define CLASS(_name, var)						\
+	class_##_name##_t var __cleanup(class_##_name##_destructor) =	\
+		class_##_name##_constructor
+
+#define CLASS_INIT(_name, _var, _init_expr)                             \
+        class_##_name##_t _var __cleanup(class_##_name##_destructor) = (_init_expr)
+
+#define __scoped_class(_name, var, _label, args...)        \
+	for (CLASS(_name, var)(args); ; ({ goto _label; })) \
+		if (0) {                                   \
+_label:                                                    \
+			break;                             \
+		} else
+
+#define scoped_class(_name, var, args...) \
+	__scoped_class(_name, var, __UNIQUE_ID(label), args)
+
+/*
+ * DEFINE_GUARD(name, type, lock, unlock):
+ *	trivial wrapper around DEFINE_CLASS() above specifically
+ *	for locks.
+ *
+ * DEFINE_GUARD_COND(name, ext, condlock)
+ *	wrapper around EXTEND_CLASS above to add conditional lock
+ *	variants to a base class, eg. mutex_trylock() or
+ *	mutex_lock_interruptible().
+ *
+ * guard(name):
+ *	an anonymous instance of the (guard) class, not recommended for
+ *	conditional locks.
+ *
+ * scoped_guard (name, args...) { }:
+ *	similar to CLASS(name, scope)(args), except the variable (with the
+ *	explicit name 'scope') is declard in a for-loop such that its scope is
+ *	bound to the next (compound) statement.
+ *
+ *	for conditional locks the loop body is skipped when the lock is not
+ *	acquired.
+ *
+ * scoped_cond_guard (name, fail, args...) { }:
+ *      similar to scoped_guard(), except it does fail when the lock
+ *      acquire fails.
+ *
+ *      Only for conditional locks.
+ *
+ * ACQUIRE(name, var):
+ *	a named instance of the (guard) class, suitable for conditional
+ *	locks when paired with ACQUIRE_ERR().
+ *
+ * ACQUIRE_ERR(name, &var):
+ *	a helper that is effectively a PTR_ERR() conversion of the guard
+ *	pointer. Returns 0 when the lock was acquired and a negative
+ *	error code otherwise.
+ */
+
+#define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond)	\
+static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
+
+#define DEFINE_CLASS_IS_UNCONDITIONAL(_name)		\
+	__DEFINE_CLASS_IS_CONDITIONAL(_name, false);	\
+	static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	{ return (void *)1; }
+
+#define __GUARD_IS_ERR(_ptr)                                       \
+	({                                                         \
+		unsigned long _rc = (__force unsigned long)(_ptr); \
+		unlikely((_rc - 1) >= -MAX_ERRNO - 1);             \
+	})
+
+#define __DEFINE_GUARD_LOCK_PTR(_name, _exp)                                \
+	static __always_inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	{                                                                   \
+		void *_ptr = (void *)(__force unsigned long)*(_exp);        \
+		if (IS_ERR(_ptr)) {                                         \
+			_ptr = NULL;                                        \
+		}                                                           \
+		return _ptr;                                                \
+	}                                                                   \
+	static __always_inline int class_##_name##_lock_err(class_##_name##_t *_T) \
+	{                                                                   \
+		long _rc = (__force unsigned long)*(_exp);                  \
+		if (!_rc) {                                                 \
+			_rc = -EBUSY;                                       \
+		}                                                           \
+		if (!IS_ERR_VALUE(_rc)) {                                   \
+			_rc = 0;                                            \
+		}                                                           \
+		return _rc;                                                 \
+	}
+
+#define DEFINE_CLASS_IS_GUARD(_name) \
+	__DEFINE_CLASS_IS_CONDITIONAL(_name, false); \
+	__DEFINE_GUARD_LOCK_PTR(_name, _T)
+
+#define DEFINE_CLASS_IS_COND_GUARD(_name) \
+	__DEFINE_CLASS_IS_CONDITIONAL(_name, true); \
+	__DEFINE_GUARD_LOCK_PTR(_name, _T)
+
+#define DEFINE_GUARD(_name, _type, _lock, _unlock) \
+	DEFINE_CLASS(_name, _type, if (!__GUARD_IS_ERR(_T)) { _unlock; }, ({ _lock; _T; }), _type _T); \
+	DEFINE_CLASS_IS_GUARD(_name)
+
+#define DEFINE_GUARD_COND_4(_name, _ext, _lock, _cond) \
+	__DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \
+	EXTEND_CLASS(_name, _ext, \
+		     ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \
+		     class_##_name##_t _T) \
+	static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_ptr(_T); } \
+	static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_err(_T); }
+
+/*
+ * Default binary condition; success on 'true'.
+ */
+#define DEFINE_GUARD_COND_3(_name, _ext, _lock) \
+	DEFINE_GUARD_COND_4(_name, _ext, _lock, _RET)
+
+#define DEFINE_GUARD_COND(X...) CONCATENATE(DEFINE_GUARD_COND_, COUNT_ARGS(X))(X)
+
+#define guard(_name) \
+	CLASS(_name, __UNIQUE_ID(guard))
+
+#define __guard_ptr(_name) class_##_name##_lock_ptr
+#define __guard_err(_name) class_##_name##_lock_err
+#define __is_cond_ptr(_name) class_##_name##_is_conditional
+
+#define ACQUIRE(_name, _var)     CLASS(_name, _var)
+#define ACQUIRE_ERR(_name, _var) __guard_err(_name)(_var)
+
+/*
+ * Helper macro for scoped_guard().
+ *
+ * Note that the "!__is_cond_ptr(_name)" part of the condition ensures that
+ * compiler would be sure that for the unconditional locks the body of the
+ * loop (caller-provided code glued to the else clause) could not be skipped.
+ * It is needed because the other part - "__guard_ptr(_name)(&scope)" - is too
+ * hard to deduce (even if could be proven true for unconditional locks).
+ */
+#define __scoped_guard(_name, _label, args...)				\
+	for (CLASS(_name, scope)(args);					\
+	     __guard_ptr(_name)(&scope) || !__is_cond_ptr(_name);	\
+	     ({ goto _label; }))					\
+		if (0) {						\
+_label:									\
+			break;						\
+		} else
+
+#define scoped_guard(_name, args...)	\
+	__scoped_guard(_name, __UNIQUE_ID(label), args)
+
+#define __scoped_cond_guard(_name, _fail, _label, args...)		\
+	for (CLASS(_name, scope)(args); true; ({ goto _label; }))	\
+		if (!__guard_ptr(_name)(&scope)) {			\
+			BUILD_BUG_ON(!__is_cond_ptr(_name));		\
+			_fail;						\
+_label:									\
+			break;						\
+		} else
+
+#define scoped_cond_guard(_name, _fail, args...)	\
+	__scoped_cond_guard(_name, _fail, __UNIQUE_ID(label), args)
+
+/*
+ * Additional helper macros for generating lock guards with types, either for
+ * locks that don't have a native type (eg. RCU, preempt) or those that need a
+ * 'fat' pointer (eg. spin_lock_irqsave).
+ *
+ * DEFINE_LOCK_GUARD_0(name, lock, unlock, ...)
+ * DEFINE_LOCK_GUARD_1(name, type, lock, unlock, ...)
+ * DEFINE_LOCK_GUARD_1_COND(name, ext, condlock)
+ *
+ * will result in the following type:
+ *
+ *   typedef struct {
+ *	type *lock;		// 'type := void' for the _0 variant
+ *	__VA_ARGS__;
+ *   } class_##name##_t;
+ *
+ * As above, both _lock and _unlock are statements, except this time '_T' will
+ * be a pointer to the above struct.
+ */
+
+#define __DEFINE_UNLOCK_GUARD(_name, _type, _unlock, ...)		\
+typedef struct {							\
+	_type *lock;							\
+	__VA_ARGS__;							\
+} class_##_name##_t;							\
+									\
+static __always_inline void class_##_name##_destructor(class_##_name##_t *_T) \
+{									\
+	if (!__GUARD_IS_ERR(_T->lock)) { _unlock; }			\
+}									\
+									\
+__DEFINE_GUARD_LOCK_PTR(_name, &_T->lock)
+
+#define __DEFINE_LOCK_GUARD_1(_name, _type, _lock)			\
+static __always_inline class_##_name##_t class_##_name##_constructor(_type *l) \
+{									\
+	class_##_name##_t _t = { .lock = l }, *_T = &_t;		\
+	_lock;								\
+	return _t;							\
+}
+
+#define __DEFINE_LOCK_GUARD_0(_name, _lock)				\
+static __always_inline class_##_name##_t class_##_name##_constructor(void) \
+{									\
+	class_##_name##_t _t = { .lock = (void*)1 },			\
+			 *_T __maybe_unused = &_t;			\
+	_lock;								\
+	return _t;							\
+}
+
+#define DEFINE_LOCK_GUARD_1(_name, _type, _lock, _unlock, ...)		\
+__DEFINE_CLASS_IS_CONDITIONAL(_name, false);				\
+__DEFINE_UNLOCK_GUARD(_name, _type, _unlock, __VA_ARGS__)		\
+__DEFINE_LOCK_GUARD_1(_name, _type, _lock)
+
+#define DEFINE_LOCK_GUARD_0(_name, _lock, _unlock, ...)			\
+__DEFINE_CLASS_IS_CONDITIONAL(_name, false);				\
+__DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__)		\
+__DEFINE_LOCK_GUARD_0(_name, _lock)
+
+#define DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _cond)		\
+	__DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true);		\
+	EXTEND_CLASS(_name, _ext,					\
+		     ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\
+		        int _RET = (_lock);                             \
+		        if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\
+			_t; }),						\
+		     typeof_member(class_##_name##_t, lock) l)		\
+	static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_ptr(_T); } \
+	static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_err(_T); }
+
+#define DEFINE_LOCK_GUARD_1_COND_3(_name, _ext, _lock) \
+	DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _RET)
+
+#define DEFINE_LOCK_GUARD_1_COND(X...) CONCATENATE(DEFINE_LOCK_GUARD_1_COND_, COUNT_ARGS(X))(X)
+
+#endif /* _LINUX_CLEANUP_H */
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 28ff6f1a6ada..630705a47129 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -74,7 +74,7 @@ void clk_hw_forward_rate_request(const struct clk_hw *core,
 				 unsigned long parent_rate);
 
 /**
- * struct clk_duty - Struture encoding the duty cycle ratio of a clock
+ * struct clk_duty - Structure encoding the duty cycle ratio of a clock
  *
  * @num:	Numerator of the duty cycle ratio
  * @den:	Denominator of the duty cycle ratio
@@ -129,7 +129,7 @@ struct clk_duty {
  * @restore_context: Restore the context of the clock after a restoration
  *		of power.
  *
- * @recalc_rate	Recalculate the rate of this clock, by querying hardware. The
+ * @recalc_rate: Recalculate the rate of this clock, by querying hardware. The
  *		parent rate is an input parameter.  It is up to the caller to
  *		ensure that the prepare_mutex is held across this call. If the
  *		driver cannot figure out a rate for this clock, it must return
@@ -394,6 +394,20 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
 	__clk_hw_register_fixed_rate((dev), NULL, (name), (parent_name), NULL, \
 				     NULL, (flags), (fixed_rate), 0, 0, true)
 /**
+ * devm_clk_hw_register_fixed_rate_parent_data - register fixed-rate clock with
+ * the clock framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_data: parent clk data
+ * @flags: framework-specific flags
+ * @fixed_rate: non-adjustable clock rate
+ */
+#define devm_clk_hw_register_fixed_rate_parent_data(dev, name, parent_data, flags, \
+						    fixed_rate)			   \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL,		   \
+				     (parent_data), (flags), (fixed_rate), 0,	   \
+				     0, true)
+/**
  * clk_hw_register_fixed_rate_parent_hw - register fixed-rate clock with
  * the clock framework
  * @dev: device that is registering this clock
@@ -415,7 +429,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
  * @flags: framework-specific flags
  * @fixed_rate: non-adjustable clock rate
  */
-#define clk_hw_register_fixed_rate_parent_data(dev, name, parent_hw, flags,   \
+#define clk_hw_register_fixed_rate_parent_data(dev, name, parent_data, flags, \
 					     fixed_rate)		      \
 	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, NULL,	      \
 				     (parent_data), (flags), (fixed_rate), 0, \
@@ -448,15 +462,15 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
  */
 #define clk_hw_register_fixed_rate_with_accuracy_parent_hw(dev, name,	      \
 		parent_hw, flags, fixed_rate, fixed_accuracy)		      \
-	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw)   \
-				     NULL, NULL, (flags), (fixed_rate),	      \
+	__clk_hw_register_fixed_rate((dev), NULL, (name), NULL, (parent_hw),  \
+				     NULL, (flags), (fixed_rate),	      \
 				     (fixed_accuracy), 0, false)
 /**
  * clk_hw_register_fixed_rate_with_accuracy_parent_data - register fixed-rate
  * clock with the clock framework
  * @dev: device that is registering this clock
  * @name: name of this clock
- * @parent_name: name of clock's parent
+ * @parent_data: name of clock's parent
  * @flags: framework-specific flags
  * @fixed_rate: non-adjustable clock rate
  * @fixed_accuracy: non-adjustable clock accuracy
@@ -471,7 +485,7 @@ struct clk *clk_register_fixed_rate(struct device *dev, const char *name,
  * the clock framework
  * @dev: device that is registering this clock
  * @name: name of this clock
- * @parent_name: name of clock's parent
+ * @parent_data: name of clock's parent
  * @flags: framework-specific flags
  * @fixed_rate: non-adjustable clock rate
  */
@@ -609,6 +623,24 @@ struct clk *clk_register_gate(struct device *dev, const char *name,
 			       NULL, (flags), (reg), (bit_idx),		      \
 			       (clk_gate_flags), (lock))
 /**
+ * devm_clk_hw_register_gate_parent_hw - register a gate clock with the clock
+ * framework
+ * @dev: device that is registering this clock
+ * @name: name of this clock
+ * @parent_hw: pointer to parent clk
+ * @flags: framework-specific flags for this clock
+ * @reg: register address to control gating of this clock
+ * @bit_idx: which bit in the register controls gating of this clock
+ * @clk_gate_flags: gate-specific flags for this clock
+ * @lock: shared register lock for this clock
+ */
+#define devm_clk_hw_register_gate_parent_hw(dev, name, parent_hw, flags,      \
+					    reg, bit_idx, clk_gate_flags,     \
+					    lock)			      \
+	__devm_clk_hw_register_gate((dev), NULL, (name), NULL, (parent_hw),   \
+				    NULL, (flags), (reg), (bit_idx),	      \
+				    (clk_gate_flags), (lock))
+/**
  * devm_clk_hw_register_gate_parent_data - register a gate clock with the
  * clock framework
  * @dev: device that is registering this clock
@@ -649,7 +681,7 @@ struct clk_div_table {
  * Clock with an adjustable divider affecting its output frequency.  Implements
  * .recalc_rate, .set_rate and .round_rate
  *
- * Flags:
+ * @flags:
  * CLK_DIVIDER_ONE_BASED - by default the divisor is the value read from the
  *	register plus one.  If CLK_DIVIDER_ONE_BASED is set then the divider is
  *	the raw value read from the register, with the value of zero considered
@@ -675,13 +707,15 @@ struct clk_div_table {
  * CLK_DIVIDER_BIG_ENDIAN - By default little endian register accesses are used
  *	for the divider register.  Setting this flag makes the register accesses
  *	big endian.
+ * CLK_DIVIDER_EVEN_INTEGERS - clock divisor is 2, 4, 6, 8, 10, etc.
+ *	Formula is 2 * (value read from hardware + 1).
  */
 struct clk_divider {
 	struct clk_hw	hw;
 	void __iomem	*reg;
 	u8		shift;
 	u8		width;
-	u8		flags;
+	u16		flags;
 	const struct clk_div_table	*table;
 	spinlock_t	*lock;
 };
@@ -697,6 +731,7 @@ struct clk_divider {
 #define CLK_DIVIDER_READ_ONLY		BIT(5)
 #define CLK_DIVIDER_MAX_AT_ZERO		BIT(6)
 #define CLK_DIVIDER_BIG_ENDIAN		BIT(7)
+#define CLK_DIVIDER_EVEN_INTEGERS	BIT(8)
 
 extern const struct clk_ops clk_divider_ops;
 extern const struct clk_ops clk_divider_ro_ops;
@@ -726,19 +761,21 @@ struct clk_hw *__clk_hw_register_divider(struct device *dev,
 		struct device_node *np, const char *name,
 		const char *parent_name, const struct clk_hw *parent_hw,
 		const struct clk_parent_data *parent_data, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		void __iomem *reg, u8 shift, u8 width,
+		unsigned long clk_divider_flags,
 		const struct clk_div_table *table, spinlock_t *lock);
 struct clk_hw *__devm_clk_hw_register_divider(struct device *dev,
 		struct device_node *np, const char *name,
 		const char *parent_name, const struct clk_hw *parent_hw,
 		const struct clk_parent_data *parent_data, unsigned long flags,
-		void __iomem *reg, u8 shift, u8 width, u8 clk_divider_flags,
+		void __iomem *reg, u8 shift, u8 width,
+		unsigned long clk_divider_flags,
 		const struct clk_div_table *table, spinlock_t *lock);
 struct clk *clk_register_divider_table(struct device *dev, const char *name,
 		const char *parent_name, unsigned long flags,
 		void __iomem *reg, u8 shift, u8 width,
-		u8 clk_divider_flags, const struct clk_div_table *table,
-		spinlock_t *lock);
+		unsigned long clk_divider_flags,
+		const struct clk_div_table *table, spinlock_t *lock);
 /**
  * clk_register_divider - register a divider clock with the clock framework
  * @dev: device registering this clock
@@ -1084,18 +1121,28 @@ void of_fixed_factor_clk_setup(struct device_node *node);
  * @hw:		handle between common and hardware-specific interfaces
  * @mult:	multiplier
  * @div:	divider
+ * @acc:	fixed accuracy in ppb
+ * @flags:	behavior modifying flags
  *
  * Clock with a fixed multiplier and divider. The output frequency is the
  * parent clock rate divided by div and multiplied by mult.
- * Implements .recalc_rate, .set_rate and .round_rate
+ * Implements .recalc_rate, .set_rate, .round_rate and .recalc_accuracy
+ *
+ * Flags:
+ * * CLK_FIXED_FACTOR_FIXED_ACCURACY - Use the value in @acc instead of the
+ *                                     parent clk accuracy.
  */
 
 struct clk_fixed_factor {
 	struct clk_hw	hw;
 	unsigned int	mult;
 	unsigned int	div;
+	unsigned long	acc;
+	unsigned int	flags;
 };
 
+#define CLK_FIXED_FACTOR_FIXED_ACCURACY	BIT(0)
+
 #define to_clk_fixed_factor(_hw) container_of(_hw, struct clk_fixed_factor, hw)
 
 extern const struct clk_ops clk_fixed_factor_ops;
@@ -1106,10 +1153,27 @@ void clk_unregister_fixed_factor(struct clk *clk);
 struct clk_hw *clk_hw_register_fixed_factor(struct device *dev,
 		const char *name, const char *parent_name, unsigned long flags,
 		unsigned int mult, unsigned int div);
+struct clk_hw *clk_hw_register_fixed_factor_fwname(struct device *dev,
+		struct device_node *np, const char *name, const char *fw_name,
+		unsigned long flags, unsigned int mult, unsigned int div);
+struct clk_hw *clk_hw_register_fixed_factor_with_accuracy_fwname(struct device *dev,
+		struct device_node *np, const char *name, const char *fw_name,
+		unsigned long flags, unsigned int mult, unsigned int div,
+		unsigned long acc);
+struct clk_hw *clk_hw_register_fixed_factor_index(struct device *dev,
+		const char *name, unsigned int index, unsigned long flags,
+		unsigned int mult, unsigned int div);
 void clk_hw_unregister_fixed_factor(struct clk_hw *hw);
 struct clk_hw *devm_clk_hw_register_fixed_factor(struct device *dev,
 		const char *name, const char *parent_name, unsigned long flags,
 		unsigned int mult, unsigned int div);
+struct clk_hw *devm_clk_hw_register_fixed_factor_fwname(struct device *dev,
+		struct device_node *np, const char *name, const char *fw_name,
+		unsigned long flags, unsigned int mult, unsigned int div);
+struct clk_hw *devm_clk_hw_register_fixed_factor_with_accuracy_fwname(struct device *dev,
+		struct device_node *np, const char *name, const char *fw_name,
+		unsigned long flags, unsigned int mult, unsigned int div,
+		unsigned long acc);
 struct clk_hw *devm_clk_hw_register_fixed_factor_index(struct device *dev,
 		const char *name, unsigned int index, unsigned long flags,
 		unsigned int mult, unsigned int div);
@@ -1130,11 +1194,12 @@ struct clk_hw *clk_hw_register_fixed_factor_parent_hw(struct device *dev,
  * @mwidth:	width of the numerator bit field
  * @nshift:	shift to the denominator bit field
  * @nwidth:	width of the denominator bit field
+ * @approximation: clk driver's callback for calculating the divider clock
  * @lock:	register lock
  *
  * Clock with adjustable fractional divider affecting its output frequency.
  *
- * Flags:
+ * @flags:
  * CLK_FRAC_DIVIDER_ZERO_BASED - by default the numerator and denominator
  *	is the value read from the register. If CLK_FRAC_DIVIDER_ZERO_BASED
  *	is set then the numerator and denominator are both the value read
@@ -1191,7 +1256,7 @@ void clk_hw_unregister_fractional_divider(struct clk_hw *hw);
  * Clock with an adjustable multiplier affecting its output frequency.
  * Implements .recalc_rate, .set_rate and .round_rate
  *
- * Flags:
+ * @flags:
  * CLK_MULTIPLIER_ZERO_BYPASS - By default, the multiplier is the value read
  *	from the register, with 0 being a valid value effectively
  *	zeroing the output clock rate. If CLK_MULTIPLIER_ZERO_BYPASS is
@@ -1295,6 +1360,32 @@ void clk_hw_unregister(struct clk_hw *hw);
 /* helper functions */
 const char *__clk_get_name(const struct clk *clk);
 const char *clk_hw_get_name(const struct clk_hw *hw);
+
+/**
+ * clk_hw_get_dev() - get device from an hardware clock.
+ * @hw: the clk_hw pointer to get the struct device from
+ *
+ * This is a helper to get the struct device associated with a hardware
+ * clock. Some clock controllers, such as the one registered with
+ * CLK_OF_DECLARE(), may have not provided a device pointer while
+ * registering the clock.
+ *
+ * Return: the struct device associated with the clock, or NULL if there
+ * is none.
+ */
+struct device *clk_hw_get_dev(const struct clk_hw *hw);
+
+/**
+ * clk_hw_get_of_node() - get device_node from a hardware clock.
+ * @hw: the clk_hw pointer to get the struct device_node from
+ *
+ * This is a helper to get the struct device_node associated with a
+ * hardware clock.
+ *
+ * Return: the struct device_node associated with the clock, or NULL
+ * if there is none.
+ */
+struct device_node *clk_hw_get_of_node(const struct clk_hw *hw);
 #ifdef CONFIG_COMMON_CLK
 struct clk_hw *__clk_get_hw(struct clk *clk);
 #else
@@ -1321,7 +1412,6 @@ unsigned long clk_hw_get_flags(const struct clk_hw *hw);
 	(clk_hw_get_flags((hw)) & CLK_SET_RATE_PARENT)
 
 bool clk_hw_is_prepared(const struct clk_hw *hw);
-bool clk_hw_rate_is_protected(const struct clk_hw *hw);
 bool clk_hw_is_enabled(const struct clk_hw *hw);
 bool __clk_is_enabled(struct clk *clk);
 struct clk *__clk_lookup(const char *name);
@@ -1333,6 +1423,8 @@ int __clk_mux_determine_rate_closest(struct clk_hw *hw,
 int clk_mux_determine_rate_flags(struct clk_hw *hw,
 				 struct clk_rate_request *req,
 				 unsigned long flags);
+int clk_hw_determine_rate_no_reparent(struct clk_hw *hw,
+				      struct clk_rate_request *req);
 void clk_hw_reparent(struct clk_hw *hw, struct clk_hw *new_parent);
 void clk_hw_get_rate_range(struct clk_hw *hw, unsigned long *min_rate,
 			   unsigned long *max_rate);
@@ -1377,7 +1469,7 @@ struct clk_onecell_data {
 
 struct clk_hw_onecell_data {
 	unsigned int num;
-	struct clk_hw *hws[];
+	struct clk_hw *hws[] __counted_by(num);
 };
 
 #define CLK_OF_DECLARE(name, compat, fn) \
diff --git a/include/linux/clk.h b/include/linux/clk.h
index 1ef013324237..b607482ca77e 100644
--- a/include/linux/clk.h
+++ b/include/linux/clk.h
@@ -183,6 +183,51 @@ int clk_get_scaled_duty_cycle(struct clk *clk, unsigned int scale);
  */
 bool clk_is_match(const struct clk *p, const struct clk *q);
 
+/**
+ * clk_rate_exclusive_get - get exclusivity over the rate control of a
+ *                          producer
+ * @clk: clock source
+ *
+ * This function allows drivers to get exclusive control over the rate of a
+ * provider. It prevents any other consumer to execute, even indirectly,
+ * opereation which could alter the rate of the provider or cause glitches
+ *
+ * If exlusivity is claimed more than once on clock, even by the same driver,
+ * the rate effectively gets locked as exclusivity can't be preempted.
+ *
+ * Must not be called from within atomic context.
+ *
+ * Returns success (0) or negative errno.
+ */
+int clk_rate_exclusive_get(struct clk *clk);
+
+/**
+ * devm_clk_rate_exclusive_get - devm variant of clk_rate_exclusive_get
+ * @dev: device the exclusivity is bound to
+ * @clk: clock source
+ *
+ * Calls clk_rate_exclusive_get() on @clk and registers a devm cleanup handler
+ * on @dev to call clk_rate_exclusive_put().
+ *
+ * Must not be called from within atomic context.
+ */
+int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk);
+
+/**
+ * clk_rate_exclusive_put - release exclusivity over the rate control of a
+ *                          producer
+ * @clk: clock source
+ *
+ * This function allows drivers to release the exclusivity it previously got
+ * from clk_rate_exclusive_get()
+ *
+ * The caller must balance the number of clk_rate_exclusive_get() and
+ * clk_rate_exclusive_put() calls.
+ *
+ * Must not be called from within atomic context.
+ */
+void clk_rate_exclusive_put(struct clk *clk);
+
 #else
 
 static inline int clk_notifier_register(struct clk *clk,
@@ -236,6 +281,18 @@ static inline bool clk_is_match(const struct clk *p, const struct clk *q)
 	return p == q;
 }
 
+static inline int clk_rate_exclusive_get(struct clk *clk)
+{
+	return 0;
+}
+
+static inline int devm_clk_rate_exclusive_get(struct device *dev, struct clk *clk)
+{
+	return 0;
+}
+
+static inline void clk_rate_exclusive_put(struct clk *clk) {}
+
 #endif
 
 #ifdef CONFIG_HAVE_CLK_PREPARE
@@ -439,6 +496,24 @@ int __must_check devm_clk_bulk_get_all(struct device *dev,
 				       struct clk_bulk_data **clks);
 
 /**
+ * devm_clk_bulk_get_all_enabled - Get and enable all clocks of the consumer (managed)
+ * @dev: device for clock "consumer"
+ * @clks: pointer to the clk_bulk_data table of consumer
+ *
+ * Returns a positive value for the number of clocks obtained while the
+ * clock references are stored in the clk_bulk_data table in @clks field.
+ * Returns 0 if there're none and a negative value if something failed.
+ *
+ * This helper function allows drivers to get all clocks of the
+ * consumer and enables them in one operation with management.
+ * The clks will automatically be disabled and freed when the device
+ * is unbound.
+ */
+
+int __must_check devm_clk_bulk_get_all_enabled(struct device *dev,
+					       struct clk_bulk_data **clks);
+
+/**
  * devm_clk_get - lookup and obtain a managed reference to a clock producer.
  * @dev: device for clock "consumer"
  * @id: clock consumer ID
@@ -568,6 +643,32 @@ struct clk *devm_clk_get_optional_prepared(struct device *dev, const char *id);
 struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id);
 
 /**
+ * devm_clk_get_optional_enabled_with_rate - devm_clk_get_optional() +
+ *                                           clk_set_rate() +
+ *                                           clk_prepare_enable()
+ * @dev: device for clock "consumer"
+ * @id: clock consumer ID
+ * @rate: new clock rate
+ *
+ * Context: May sleep.
+ *
+ * Return: a struct clk corresponding to the clock producer, or
+ * valid IS_ERR() condition containing errno.  The implementation
+ * uses @dev and @id to determine the clock consumer, and thereby
+ * the clock producer.  If no such clk is found, it returns NULL
+ * which serves as a dummy clk.  That's the only difference compared
+ * to devm_clk_get_enabled().
+ *
+ * The returned clk (if valid) is prepared and enabled and rate was set.
+ *
+ * The clock will automatically be disabled, unprepared and freed
+ * when the device is unbound from the bus.
+ */
+struct clk *devm_clk_get_optional_enabled_with_rate(struct device *dev,
+						    const char *id,
+						    unsigned long rate);
+
+/**
  * devm_get_clk_from_child - lookup and obtain a managed reference to a
  *			     clock producer from child node.
  * @dev: device for clock "consumer"
@@ -583,38 +684,6 @@ struct clk *devm_clk_get_optional_enabled(struct device *dev, const char *id);
  */
 struct clk *devm_get_clk_from_child(struct device *dev,
 				    struct device_node *np, const char *con_id);
-/**
- * clk_rate_exclusive_get - get exclusivity over the rate control of a
- *                          producer
- * @clk: clock source
- *
- * This function allows drivers to get exclusive control over the rate of a
- * provider. It prevents any other consumer to execute, even indirectly,
- * opereation which could alter the rate of the provider or cause glitches
- *
- * If exlusivity is claimed more than once on clock, even by the same driver,
- * the rate effectively gets locked as exclusivity can't be preempted.
- *
- * Must not be called from within atomic context.
- *
- * Returns success (0) or negative errno.
- */
-int clk_rate_exclusive_get(struct clk *clk);
-
-/**
- * clk_rate_exclusive_put - release exclusivity over the rate control of a
- *                          producer
- * @clk: clock source
- *
- * This function allows drivers to release the exclusivity it previously got
- * from clk_rate_exclusive_get()
- *
- * The caller must balance the number of clk_rate_exclusive_get() and
- * clk_rate_exclusive_put() calls.
- *
- * Must not be called from within atomic context.
- */
-void clk_rate_exclusive_put(struct clk *clk);
 
 /**
  * clk_enable - inform the system when the clock source should be running.
@@ -941,6 +1010,13 @@ static inline struct clk *devm_clk_get_optional_enabled(struct device *dev,
 	return NULL;
 }
 
+static inline struct clk *
+devm_clk_get_optional_enabled_with_rate(struct device *dev, const char *id,
+					unsigned long rate)
+{
+	return NULL;
+}
+
 static inline int __must_check devm_clk_bulk_get(struct device *dev, int num_clks,
 						 struct clk_bulk_data *clks)
 {
@@ -960,6 +1036,12 @@ static inline int __must_check devm_clk_bulk_get_all(struct device *dev,
 	return 0;
 }
 
+static inline int __must_check devm_clk_bulk_get_all_enabled(struct device *dev,
+						struct clk_bulk_data **clks)
+{
+	return 0;
+}
+
 static inline struct clk *devm_get_clk_from_child(struct device *dev,
 				struct device_node *np, const char *con_id)
 {
@@ -974,14 +1056,6 @@ static inline void clk_bulk_put_all(int num_clks, struct clk_bulk_data *clks) {}
 
 static inline void devm_clk_put(struct device *dev, struct clk *clk) {}
 
-
-static inline int clk_rate_exclusive_get(struct clk *clk)
-{
-	return 0;
-}
-
-static inline void clk_rate_exclusive_put(struct clk *clk) {}
-
 static inline int clk_enable(struct clk *clk)
 {
 	return 0;
diff --git a/include/linux/clk/at91_pmc.h b/include/linux/clk/at91_pmc.h
index 7af499bdbecb..d60ce9708ea2 100644
--- a/include/linux/clk/at91_pmc.h
+++ b/include/linux/clk/at91_pmc.h
@@ -47,8 +47,6 @@
 #define	AT91_PMC_PCSR		0x18			/* Peripheral Clock Status Register */
 
 #define AT91_PMC_PLL_ACR	0x18			/* PLL Analog Control Register [for SAM9X60] */
-#define		AT91_PMC_PLL_ACR_DEFAULT_UPLL	UL(0x12020010)	/* Default PLL ACR value for UPLL */
-#define		AT91_PMC_PLL_ACR_DEFAULT_PLLA	UL(0x00020010)	/* Default PLL ACR value for PLLA */
 #define		AT91_PMC_PLL_ACR_UTMIVR		(1 << 12)	/* UPLL Voltage regulator Control */
 #define		AT91_PMC_PLL_ACR_UTMIBG		(1 << 13)	/* UPLL Bandgap Control */
 
diff --git a/include/linux/clk/davinci.h b/include/linux/clk/davinci.h
index e1d37451e03f..787a81116b00 100644
--- a/include/linux/clk/davinci.h
+++ b/include/linux/clk/davinci.h
@@ -12,12 +12,6 @@
 #include <linux/regmap.h>
 
 /* function for registering clocks in early boot */
-
-#ifdef CONFIG_ARCH_DAVINCI_DA830
-int da830_pll_init(struct device *dev, void __iomem *base, struct regmap *cfgchip);
-#endif
-#ifdef CONFIG_ARCH_DAVINCI_DA850
 int da850_pll0_init(struct device *dev, void __iomem *base, struct regmap *cfgchip);
-#endif
 
 #endif /* __LINUX_CLK_DAVINCI_PLL_H___ */
diff --git a/include/linux/clk/mmp.h b/include/linux/clk/mmp.h
deleted file mode 100644
index 445130460380..000000000000
--- a/include/linux/clk/mmp.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __CLK_MMP_H
-#define __CLK_MMP_H
-
-#include <linux/types.h>
-
-extern void pxa168_clk_init(phys_addr_t mpmu_phys,
-			    phys_addr_t apmu_phys,
-			    phys_addr_t apbc_phys);
-extern void pxa910_clk_init(phys_addr_t mpmu_phys,
-			    phys_addr_t apmu_phys,
-			    phys_addr_t apbc_phys,
-			    phys_addr_t apbcp_phys);
-extern void mmp2_clk_init(phys_addr_t mpmu_phys,
-			  phys_addr_t apmu_phys,
-			  phys_addr_t apbc_phys);
-
-#endif
diff --git a/include/linux/clk/renesas.h b/include/linux/clk/renesas.h
index 0ebbe2f0b45e..69d8159deee3 100644
--- a/include/linux/clk/renesas.h
+++ b/include/linux/clk/renesas.h
@@ -10,7 +10,9 @@
 #ifndef __LINUX_CLK_RENESAS_H_
 #define __LINUX_CLK_RENESAS_H_
 
+#include <linux/clk-provider.h>
 #include <linux/types.h>
+#include <linux/units.h>
 
 struct device;
 struct device_node;
@@ -32,4 +34,147 @@ void cpg_mssr_detach_dev(struct generic_pm_domain *unused, struct device *dev);
 #define cpg_mssr_attach_dev	NULL
 #define cpg_mssr_detach_dev	NULL
 #endif
+
+/**
+ * struct rzv2h_pll_limits - PLL parameter constraints
+ *
+ * This structure defines the minimum and maximum allowed values for
+ * various parameters used to configure a PLL. These limits ensure
+ * the PLL operates within valid and stable ranges.
+ *
+ * @fout: Output frequency range (in MHz)
+ * @fout.min: Minimum allowed output frequency
+ * @fout.max: Maximum allowed output frequency
+ *
+ * @fvco: PLL oscillation frequency range (in MHz)
+ * @fvco.min: Minimum allowed VCO frequency
+ * @fvco.max: Maximum allowed VCO frequency
+ *
+ * @m: Main-divider range
+ * @m.min: Minimum main-divider value
+ * @m.max: Maximum main-divider value
+ *
+ * @p: Pre-divider range
+ * @p.min: Minimum pre-divider value
+ * @p.max: Maximum pre-divider value
+ *
+ * @s: Divider range
+ * @s.min: Minimum divider value
+ * @s.max: Maximum divider value
+ *
+ * @k: Delta-sigma modulator range (signed)
+ * @k.min: Minimum delta-sigma value
+ * @k.max: Maximum delta-sigma value
+ */
+struct rzv2h_pll_limits {
+	struct {
+		u32 min;
+		u32 max;
+	} fout;
+
+	struct {
+		u32 min;
+		u32 max;
+	} fvco;
+
+	struct {
+		u16 min;
+		u16 max;
+	} m;
+
+	struct {
+		u8 min;
+		u8 max;
+	} p;
+
+	struct {
+		u8 min;
+		u8 max;
+	} s;
+
+	struct {
+		s16 min;
+		s16 max;
+	} k;
+};
+
+/**
+ * struct rzv2h_pll_pars - PLL configuration parameters
+ *
+ * This structure contains the configuration parameters for the
+ * Phase-Locked Loop (PLL), used to achieve a specific output frequency.
+ *
+ * @m: Main divider value
+ * @p: Pre-divider value
+ * @s: Output divider value
+ * @k: Delta-sigma modulation value
+ * @freq_millihz: Calculated PLL output frequency in millihertz
+ * @error_millihz: Frequency error from target in millihertz (signed)
+ */
+struct rzv2h_pll_pars {
+	u16 m;
+	u8 p;
+	u8 s;
+	s16 k;
+	u64 freq_millihz;
+	s64 error_millihz;
+};
+
+/**
+ * struct rzv2h_pll_div_pars - PLL parameters with post-divider
+ *
+ * This structure is used for PLLs that include an additional post-divider
+ * stage after the main PLL block. It contains both the PLL configuration
+ * parameters and the resulting frequency/error values after the divider.
+ *
+ * @pll: Main PLL configuration parameters (see struct rzv2h_pll_pars)
+ *
+ * @div: Post-divider configuration and result
+ * @div.divider_value: Divider applied to the PLL output
+ * @div.freq_millihz: Output frequency after divider in millihertz
+ * @div.error_millihz: Frequency error from target in millihertz (signed)
+ */
+struct rzv2h_pll_div_pars {
+	struct rzv2h_pll_pars pll;
+	struct {
+		u8 divider_value;
+		u64 freq_millihz;
+		s64 error_millihz;
+	} div;
+};
+
+#define RZV2H_CPG_PLL_DSI_LIMITS(name)					\
+	static const struct rzv2h_pll_limits (name) = {			\
+		.fout = { .min = 25 * MEGA, .max = 375 * MEGA },	\
+		.fvco = { .min = 1600 * MEGA, .max = 3200 * MEGA },	\
+		.m = { .min = 64, .max = 533 },				\
+		.p = { .min = 1, .max = 4 },				\
+		.s = { .min = 0, .max = 6 },				\
+		.k = { .min = -32768, .max = 32767 },			\
+	}								\
+
+#ifdef CONFIG_CLK_RZV2H
+bool rzv2h_get_pll_pars(const struct rzv2h_pll_limits *limits,
+			struct rzv2h_pll_pars *pars, u64 freq_millihz);
+
+bool rzv2h_get_pll_divs_pars(const struct rzv2h_pll_limits *limits,
+			     struct rzv2h_pll_div_pars *pars,
+			     const u8 *table, u8 table_size, u64 freq_millihz);
+#else
+static inline bool rzv2h_get_pll_pars(const struct rzv2h_pll_limits *limits,
+				      struct rzv2h_pll_pars *pars,
+				      u64 freq_millihz)
+{
+	return false;
+}
+
+static inline bool rzv2h_get_pll_divs_pars(const struct rzv2h_pll_limits *limits,
+					   struct rzv2h_pll_div_pars *pars,
+					   const u8 *table, u8 table_size,
+					   u64 freq_millihz)
+{
+	return false;
+}
+#endif
+
 #endif
diff --git a/include/linux/clk/ti.h b/include/linux/clk/ti.h
index cbfcbf186ce3..54a3fa370004 100644
--- a/include/linux/clk/ti.h
+++ b/include/linux/clk/ti.h
@@ -13,11 +13,14 @@
 /**
  * struct clk_omap_reg - OMAP register declaration
  * @offset: offset from the master IP module base address
+ * @bit: register bit offset
  * @index: index of the master IP module
+ * @flags: flags
  */
 struct clk_omap_reg {
 	void __iomem *ptr;
 	u16 offset;
+	u8 bit;
 	u8 index;
 	u8 flags;
 };
@@ -31,14 +34,14 @@ struct clk_omap_reg {
  * @clk_ref: struct clk_hw pointer to the clock's reference clock input
  * @control_reg: register containing the DPLL mode bitfield
  * @enable_mask: mask of the DPLL mode bitfield in @control_reg
- * @last_rounded_rate: cache of the last rate result of omap2_dpll_round_rate()
- * @last_rounded_m: cache of the last M result of omap2_dpll_round_rate()
+ * @last_rounded_rate: cache of the last rate result of omap2_dpll_determine_rate()
+ * @last_rounded_m: cache of the last M result of omap2_dpll_determine_rate()
  * @last_rounded_m4xen: cache of the last M4X result of
- *			omap4_dpll_regm4xen_round_rate()
+ *			omap4_dpll_regm4xen_determine_rate()
  * @last_rounded_lpmode: cache of the last lpmode result of
  *			 omap4_dpll_lpmode_recalc()
  * @max_multiplier: maximum valid non-bypass multiplier value (actual)
- * @last_rounded_n: cache of the last N result of omap2_dpll_round_rate()
+ * @last_rounded_n: cache of the last N result of omap2_dpll_determine_rate()
  * @min_divider: minimum valid non-bypass divider value (actual)
  * @max_divider: maximum valid non-bypass divider value (actual)
  * @max_rate: maximum clock rate for the DPLL
diff --git a/include/linux/clockchips.h b/include/linux/clockchips.h
index 9aac31d856f3..b0df28ddd394 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -12,7 +12,7 @@
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
 
 # include <linux/clocksource.h>
-# include <linux/cpumask.h>
+# include <linux/cpumask_types.h>
 # include <linux/ktime.h>
 # include <linux/notifier.h>
 
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 1d42d4b17327..65b7c41471c3 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -21,6 +21,7 @@
 #include <asm/div64.h>
 #include <asm/io.h>
 
+struct clocksource_base;
 struct clocksource;
 struct module;
 
@@ -48,8 +49,10 @@ struct module;
  * @archdata:		Optional arch-specific data
  * @max_cycles:		Maximum safe cycle value which won't overflow on
  *			multiplication
+ * @max_raw_delta:	Maximum safe delta value for negative motion detection
  * @name:		Pointer to clocksource name
  * @list:		List head for registration (internal)
+ * @freq_khz:		Clocksource frequency in khz.
  * @rating:		Rating value for selection (higher is better)
  *			To avoid rating inflation the following
  *			list should give you a guide as to how
@@ -70,6 +73,8 @@ struct module;
  *			validate the clocksource from which the snapshot was
  *			taken.
  * @flags:		Flags describing special properties
+ * @base:		Hardware abstraction for clock on which a clocksource
+ *			is based
  * @enable:		Optional function to enable the clocksource
  * @disable:		Optional function to disable the clocksource
  * @suspend:		Optional suspend function for the clocksource
@@ -105,12 +110,15 @@ struct clocksource {
 	struct arch_clocksource_data archdata;
 #endif
 	u64			max_cycles;
+	u64			max_raw_delta;
 	const char		*name;
 	struct list_head	list;
+	u32			freq_khz;
 	int			rating;
 	enum clocksource_ids	id;
 	enum vdso_clock_mode	vdso_clock_mode;
 	unsigned long		flags;
+	struct clocksource_base *base;
 
 	int			(*enable)(struct clocksource *cs);
 	void			(*disable)(struct clocksource *cs);
@@ -209,7 +217,6 @@ static inline s64 clocksource_cyc2ns(u64 cycles, u32 mult, u32 shift)
 
 extern int clocksource_unregister(struct clocksource*);
 extern void clocksource_touch_watchdog(void);
-extern void clocksource_change_rating(struct clocksource *cs, int rating);
 extern void clocksource_suspend(void);
 extern void clocksource_resume(void);
 extern struct clocksource * __init clocksource_default_clock(void);
@@ -291,7 +298,40 @@ static inline void timer_probe(void) {}
 #define TIMER_ACPI_DECLARE(name, table_id, fn)		\
 	ACPI_DECLARE_PROBE_ENTRY(timer, name, table_id, 0, NULL, 0, fn)
 
-extern ulong max_cswd_read_retries;
+static inline unsigned int clocksource_get_max_watchdog_retry(void)
+{
+	/*
+	 * When system is in the boot phase or under heavy workload, there
+	 * can be random big latencies during the clocksource/watchdog
+	 * read, so allow retries to filter the noise latency. As the
+	 * latency's frequency and maximum value goes up with the number of
+	 * CPUs, scale the number of retries with the number of online
+	 * CPUs.
+	 */
+	return (ilog2(num_online_cpus()) / 2) + 1;
+}
+
 void clocksource_verify_percpu(struct clocksource *cs);
 
+/**
+ * struct clocksource_base - hardware abstraction for clock on which a clocksource
+ *			is based
+ * @id:			Defaults to CSID_GENERIC. The id value is used for conversion
+ *			functions which require that the current clocksource is based
+ *			on a clocksource_base with a particular ID in certain snapshot
+ *			functions to allow callers to validate the clocksource from
+ *			which the snapshot was taken.
+ * @freq_khz:		Nominal frequency of the base clock in kHz
+ * @offset:		Offset between the base clock and the clocksource
+ * @numerator:		Numerator of the clock ratio between base clock and the clocksource
+ * @denominator:	Denominator of the clock ratio between base clock and the clocksource
+ */
+struct clocksource_base {
+	enum clocksource_ids	id;
+	u32			freq_khz;
+	u64			offset;
+	u32			numerator;
+	u32			denominator;
+};
+
 #endif /* _LINUX_CLOCKSOURCE_H */
diff --git a/include/linux/clocksource_ids.h b/include/linux/clocksource_ids.h
index 16775d7d8f8d..c4ef4ae2eded 100644
--- a/include/linux/clocksource_ids.h
+++ b/include/linux/clocksource_ids.h
@@ -6,6 +6,11 @@
 enum clocksource_ids {
 	CSID_GENERIC		= 0,
 	CSID_ARM_ARCH_COUNTER,
+	CSID_S390_TOD,
+	CSID_X86_TSC_EARLY,
+	CSID_X86_TSC,
+	CSID_X86_KVM_CLK,
+	CSID_X86_ART,
 	CSID_MAX,
 };
 
diff --git a/include/linux/closure.h b/include/linux/closure.h
new file mode 100644
index 000000000000..880fe85e35e9
--- /dev/null
+++ b/include/linux/closure.h
@@ -0,0 +1,492 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CLOSURE_H
+#define _LINUX_CLOSURE_H
+
+#include <linux/llist.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/workqueue.h>
+
+/*
+ * Closure is perhaps the most overused and abused term in computer science, but
+ * since I've been unable to come up with anything better you're stuck with it
+ * again.
+ *
+ * What are closures?
+ *
+ * They embed a refcount. The basic idea is they count "things that are in
+ * progress" - in flight bios, some other thread that's doing something else -
+ * anything you might want to wait on.
+ *
+ * The refcount may be manipulated with closure_get() and closure_put().
+ * closure_put() is where many of the interesting things happen, when it causes
+ * the refcount to go to 0.
+ *
+ * Closures can be used to wait on things both synchronously and asynchronously,
+ * and synchronous and asynchronous use can be mixed without restriction. To
+ * wait synchronously, use closure_sync() - you will sleep until your closure's
+ * refcount hits 1.
+ *
+ * To wait asynchronously, use
+ *   continue_at(cl, next_function, workqueue);
+ *
+ * passing it, as you might expect, the function to run when nothing is pending
+ * and the workqueue to run that function out of.
+ *
+ * continue_at() also, critically, requires a 'return' immediately following the
+ * location where this macro is referenced, to return to the calling function.
+ * There's good reason for this.
+ *
+ * To use safely closures asynchronously, they must always have a refcount while
+ * they are running owned by the thread that is running them. Otherwise, suppose
+ * you submit some bios and wish to have a function run when they all complete:
+ *
+ * foo_endio(struct bio *bio)
+ * {
+ *	closure_put(cl);
+ * }
+ *
+ * closure_init(cl);
+ *
+ * do_stuff();
+ * closure_get(cl);
+ * bio1->bi_endio = foo_endio;
+ * bio_submit(bio1);
+ *
+ * do_more_stuff();
+ * closure_get(cl);
+ * bio2->bi_endio = foo_endio;
+ * bio_submit(bio2);
+ *
+ * continue_at(cl, complete_some_read, system_wq);
+ *
+ * If closure's refcount started at 0, complete_some_read() could run before the
+ * second bio was submitted - which is almost always not what you want! More
+ * importantly, it wouldn't be possible to say whether the original thread or
+ * complete_some_read()'s thread owned the closure - and whatever state it was
+ * associated with!
+ *
+ * So, closure_init() initializes a closure's refcount to 1 - and when a
+ * closure_fn is run, the refcount will be reset to 1 first.
+ *
+ * Then, the rule is - if you got the refcount with closure_get(), release it
+ * with closure_put() (i.e, in a bio->bi_endio function). If you have a refcount
+ * on a closure because you called closure_init() or you were run out of a
+ * closure - _always_ use continue_at(). Doing so consistently will help
+ * eliminate an entire class of particularly pernicious races.
+ *
+ * Lastly, you might have a wait list dedicated to a specific event, and have no
+ * need for specifying the condition - you just want to wait until someone runs
+ * closure_wake_up() on the appropriate wait list. In that case, just use
+ * closure_wait(). It will return either true or false, depending on whether the
+ * closure was already on a wait list or not - a closure can only be on one wait
+ * list at a time.
+ *
+ * Parents:
+ *
+ * closure_init() takes two arguments - it takes the closure to initialize, and
+ * a (possibly null) parent.
+ *
+ * If parent is non null, the new closure will have a refcount for its lifetime;
+ * a closure is considered to be "finished" when its refcount hits 0 and the
+ * function to run is null. Hence
+ *
+ * continue_at(cl, NULL, NULL);
+ *
+ * returns up the (spaghetti) stack of closures, precisely like normal return
+ * returns up the C stack. continue_at() with non null fn is better thought of
+ * as doing a tail call.
+ *
+ * All this implies that a closure should typically be embedded in a particular
+ * struct (which its refcount will normally control the lifetime of), and that
+ * struct can very much be thought of as a stack frame.
+ */
+
+struct closure;
+struct closure_syncer;
+typedef void (closure_fn) (struct work_struct *);
+extern struct dentry *bcache_debug;
+
+struct closure_waitlist {
+	struct llist_head	list;
+};
+
+enum closure_state {
+	/*
+	 * CLOSURE_WAITING: Set iff the closure is on a waitlist. Must be set by
+	 * the thread that owns the closure, and cleared by the thread that's
+	 * waking up the closure.
+	 *
+	 * The rest are for debugging and don't affect behaviour:
+	 *
+	 * CLOSURE_RUNNING: Set when a closure is running (i.e. by
+	 * closure_init() and when closure_put() runs then next function), and
+	 * must be cleared before remaining hits 0. Primarily to help guard
+	 * against incorrect usage and accidentally transferring references.
+	 * continue_at() and closure_return() clear it for you, if you're doing
+	 * something unusual you can use closure_set_dead() which also helps
+	 * annotate where references are being transferred.
+	 */
+
+	CLOSURE_BITS_START	= (1U << 26),
+	CLOSURE_DESTRUCTOR	= (1U << 26),
+	CLOSURE_WAITING		= (1U << 28),
+	CLOSURE_RUNNING		= (1U << 30),
+};
+
+#define CLOSURE_GUARD_MASK					\
+	((CLOSURE_DESTRUCTOR|CLOSURE_WAITING|CLOSURE_RUNNING) << 1)
+
+#define CLOSURE_REMAINING_MASK		(CLOSURE_BITS_START - 1)
+#define CLOSURE_REMAINING_INITIALIZER	(1|CLOSURE_RUNNING)
+
+struct closure {
+	union {
+		struct {
+			struct workqueue_struct *wq;
+			struct closure_syncer	*s;
+			struct llist_node	list;
+			closure_fn		*fn;
+		};
+		struct work_struct	work;
+	};
+
+	struct closure		*parent;
+
+	atomic_t		remaining;
+	bool			closure_get_happened;
+
+#ifdef CONFIG_DEBUG_CLOSURES
+#define CLOSURE_MAGIC_DEAD	0xc054dead
+#define CLOSURE_MAGIC_ALIVE	0xc054a11e
+#define CLOSURE_MAGIC_STACK	0xc05451cc
+
+	unsigned int		magic;
+	struct list_head	all;
+	unsigned long		ip;
+	unsigned long		waiting_on;
+#endif
+};
+
+void closure_sub(struct closure *cl, int v);
+void closure_put(struct closure *cl);
+void __closure_wake_up(struct closure_waitlist *list);
+bool closure_wait(struct closure_waitlist *list, struct closure *cl);
+void __closure_sync(struct closure *cl);
+
+static inline unsigned closure_nr_remaining(struct closure *cl)
+{
+	return atomic_read(&cl->remaining) & CLOSURE_REMAINING_MASK;
+}
+
+/**
+ * closure_sync - sleep until a closure a closure has nothing left to wait on
+ *
+ * Sleeps until the refcount hits 1 - the thread that's running the closure owns
+ * the last refcount.
+ */
+static inline void closure_sync(struct closure *cl)
+{
+#ifdef CONFIG_DEBUG_CLOSURES
+	BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened);
+#endif
+
+	if (cl->closure_get_happened)
+		__closure_sync(cl);
+}
+
+int __closure_sync_timeout(struct closure *cl, unsigned long timeout);
+
+static inline int closure_sync_timeout(struct closure *cl, unsigned long timeout)
+{
+#ifdef CONFIG_DEBUG_CLOSURES
+	BUG_ON(closure_nr_remaining(cl) != 1 && !cl->closure_get_happened);
+#endif
+	return cl->closure_get_happened
+		? __closure_sync_timeout(cl, timeout)
+		: 0;
+}
+
+#ifdef CONFIG_DEBUG_CLOSURES
+
+void closure_debug_create(struct closure *cl);
+void closure_debug_destroy(struct closure *cl);
+
+#else
+
+static inline void closure_debug_create(struct closure *cl) {}
+static inline void closure_debug_destroy(struct closure *cl) {}
+
+#endif
+
+static inline void closure_set_ip(struct closure *cl)
+{
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->ip = _THIS_IP_;
+#endif
+}
+
+static inline void closure_set_ret_ip(struct closure *cl)
+{
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->ip = _RET_IP_;
+#endif
+}
+
+static inline void closure_set_waiting(struct closure *cl, unsigned long f)
+{
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->waiting_on = f;
+#endif
+}
+
+static inline void closure_set_stopped(struct closure *cl)
+{
+	atomic_sub(CLOSURE_RUNNING, &cl->remaining);
+}
+
+static inline void set_closure_fn(struct closure *cl, closure_fn *fn,
+				  struct workqueue_struct *wq)
+{
+	closure_set_ip(cl);
+	cl->fn = fn;
+	cl->wq = wq;
+}
+
+static inline void closure_queue(struct closure *cl)
+{
+	struct workqueue_struct *wq = cl->wq;
+	/**
+	 * Changes made to closure, work_struct, or a couple of other structs
+	 * may cause work.func not pointing to the right location.
+	 */
+	BUILD_BUG_ON(offsetof(struct closure, fn)
+		     != offsetof(struct work_struct, func));
+
+	if (wq) {
+		INIT_WORK(&cl->work, cl->work.func);
+		BUG_ON(!queue_work(wq, &cl->work));
+	} else
+		cl->fn(&cl->work);
+}
+
+/**
+ * closure_get - increment a closure's refcount
+ */
+static inline void closure_get(struct closure *cl)
+{
+	cl->closure_get_happened = true;
+
+#ifdef CONFIG_DEBUG_CLOSURES
+	BUG_ON((atomic_inc_return(&cl->remaining) &
+		CLOSURE_REMAINING_MASK) <= 1);
+#else
+	atomic_inc(&cl->remaining);
+#endif
+}
+
+/**
+ * closure_get_not_zero
+ */
+static inline bool closure_get_not_zero(struct closure *cl)
+{
+	unsigned old = atomic_read(&cl->remaining);
+	do {
+		if (!(old & CLOSURE_REMAINING_MASK))
+			return false;
+
+	} while (!atomic_try_cmpxchg_acquire(&cl->remaining, &old, old + 1));
+
+	return true;
+}
+
+/**
+ * closure_init - Initialize a closure, setting the refcount to 1
+ * @cl:		closure to initialize
+ * @parent:	parent of the new closure. cl will take a refcount on it for its
+ *		lifetime; may be NULL.
+ */
+static inline void closure_init(struct closure *cl, struct closure *parent)
+{
+	cl->fn = NULL;
+	cl->parent = parent;
+	if (parent)
+		closure_get(parent);
+
+	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
+	cl->closure_get_happened = false;
+
+	closure_debug_create(cl);
+	closure_set_ip(cl);
+}
+
+static inline void closure_init_stack(struct closure *cl)
+{
+	memset(cl, 0, sizeof(struct closure));
+	atomic_set(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->magic = CLOSURE_MAGIC_STACK;
+#endif
+}
+
+static inline void closure_init_stack_release(struct closure *cl)
+{
+	memset(cl, 0, sizeof(struct closure));
+	atomic_set_release(&cl->remaining, CLOSURE_REMAINING_INITIALIZER);
+#ifdef CONFIG_DEBUG_CLOSURES
+	cl->magic = CLOSURE_MAGIC_STACK;
+#endif
+}
+
+/**
+ * closure_wake_up - wake up all closures on a wait list,
+ *		     with memory barrier
+ */
+static inline void closure_wake_up(struct closure_waitlist *list)
+{
+	/* Memory barrier for the wait list */
+	smp_mb();
+	__closure_wake_up(list);
+}
+
+#define CLOSURE_CALLBACK(name)	void name(struct work_struct *ws)
+#define closure_type(name, type, member)				\
+	struct closure *cl = container_of(ws, struct closure, work);	\
+	type *name = container_of(cl, type, member)
+
+/**
+ * continue_at - jump to another function with barrier
+ *
+ * After @cl is no longer waiting on anything (i.e. all outstanding refs have
+ * been dropped with closure_put()), it will resume execution at @fn running out
+ * of @wq (or, if @wq is NULL, @fn will be called by closure_put() directly).
+ *
+ * This is because after calling continue_at() you no longer have a ref on @cl,
+ * and whatever @cl owns may be freed out from under you - a running closure fn
+ * has a ref on its own closure which continue_at() drops.
+ *
+ * Note you are expected to immediately return after using this macro.
+ */
+#define continue_at(_cl, _fn, _wq)					\
+do {									\
+	set_closure_fn(_cl, _fn, _wq);					\
+	closure_sub(_cl, CLOSURE_RUNNING + 1);				\
+} while (0)
+
+/**
+ * closure_return - finish execution of a closure
+ *
+ * This is used to indicate that @cl is finished: when all outstanding refs on
+ * @cl have been dropped @cl's ref on its parent closure (as passed to
+ * closure_init()) will be dropped, if one was specified - thus this can be
+ * thought of as returning to the parent closure.
+ */
+#define closure_return(_cl)	continue_at((_cl), NULL, NULL)
+
+void closure_return_sync(struct closure *cl);
+
+/**
+ * continue_at_nobarrier - jump to another function without barrier
+ *
+ * Causes @fn to be executed out of @cl, in @wq context (or called directly if
+ * @wq is NULL).
+ *
+ * The ref the caller of continue_at_nobarrier() had on @cl is now owned by @fn,
+ * thus it's not safe to touch anything protected by @cl after a
+ * continue_at_nobarrier().
+ */
+#define continue_at_nobarrier(_cl, _fn, _wq)				\
+do {									\
+	set_closure_fn(_cl, _fn, _wq);					\
+	closure_queue(_cl);						\
+} while (0)
+
+/**
+ * closure_return_with_destructor - finish execution of a closure,
+ *				    with destructor
+ *
+ * Works like closure_return(), except @destructor will be called when all
+ * outstanding refs on @cl have been dropped; @destructor may be used to safely
+ * free the memory occupied by @cl, and it is called with the ref on the parent
+ * closure still held - so @destructor could safely return an item to a
+ * freelist protected by @cl's parent.
+ */
+#define closure_return_with_destructor(_cl, _destructor)		\
+do {									\
+	set_closure_fn(_cl, _destructor, NULL);				\
+	closure_sub(_cl, CLOSURE_RUNNING - CLOSURE_DESTRUCTOR + 1);	\
+} while (0)
+
+/**
+ * closure_call - execute @fn out of a new, uninitialized closure
+ *
+ * Typically used when running out of one closure, and we want to run @fn
+ * asynchronously out of a new closure - @parent will then wait for @cl to
+ * finish.
+ */
+static inline void closure_call(struct closure *cl, closure_fn fn,
+				struct workqueue_struct *wq,
+				struct closure *parent)
+{
+	closure_init(cl, parent);
+	continue_at_nobarrier(cl, fn, wq);
+}
+
+#define __closure_wait_event(waitlist, _cond)				\
+do {									\
+	struct closure cl;						\
+									\
+	closure_init_stack(&cl);					\
+									\
+	while (1) {							\
+		closure_wait(waitlist, &cl);				\
+		if (_cond)						\
+			break;						\
+		closure_sync(&cl);					\
+	}								\
+	closure_wake_up(waitlist);					\
+	closure_sync(&cl);						\
+} while (0)
+
+#define closure_wait_event(waitlist, _cond)				\
+do {									\
+	if (!(_cond))							\
+		__closure_wait_event(waitlist, _cond);			\
+} while (0)
+
+#define __closure_wait_event_timeout(waitlist, _cond, _until)		\
+({									\
+	struct closure cl;						\
+	long _t;							\
+									\
+	closure_init_stack(&cl);					\
+									\
+	while (1) {							\
+		closure_wait(waitlist, &cl);				\
+		if (_cond) {						\
+			_t = max_t(long, 1L, _until - jiffies);		\
+			break;						\
+		}							\
+		_t = max_t(long, 0L, _until - jiffies);			\
+		if (!_t)						\
+			break;						\
+		closure_sync_timeout(&cl, _t);				\
+	}								\
+	closure_wake_up(waitlist);					\
+	closure_sync(&cl);						\
+	_t;								\
+})
+
+/*
+ * Returns 0 if timeout expired, remaining time in jiffies (at least 1) if
+ * condition became true
+ */
+#define closure_wait_event_timeout(waitlist, _cond, _timeout)		\
+({									\
+	unsigned long _until = jiffies + _timeout;			\
+	(_cond)								\
+		? max_t(long, 1L, _until - jiffies)			\
+		: __closure_wait_event_timeout(waitlist, _cond, _until);\
+})
+
+#endif /* _LINUX_CLOSURE_H */
diff --git a/include/linux/cma.h b/include/linux/cma.h
index 63873b93deaa..62d9c1cf6326 100644
--- a/include/linux/cma.h
+++ b/include/linux/cma.h
@@ -6,12 +6,8 @@
 #include <linux/types.h>
 #include <linux/numa.h>
 
-/*
- * There is always at least global CMA area and a few optional
- * areas configured in kernel .config.
- */
 #ifdef CONFIG_CMA_AREAS
-#define MAX_CMA_AREAS	(1 + CONFIG_CMA_AREAS)
+#define MAX_CMA_AREAS	CONFIG_CMA_AREAS
 #endif
 
 #define CMA_MAX_NAME 64
@@ -44,6 +40,9 @@ static inline int __init cma_declare_contiguous(phys_addr_t base,
 	return cma_declare_contiguous_nid(base, size, limit, alignment,
 			order_per_bit, fixed, name, res_cma, NUMA_NO_NODE);
 }
+extern int __init cma_declare_contiguous_multi(phys_addr_t size,
+			phys_addr_t align, unsigned int order_per_bit,
+			const char *name, struct cma **res_cma, int nid);
 extern int cma_init_reserved_mem(phys_addr_t base, phys_addr_t size,
 					unsigned int order_per_bit,
 					const char *name,
@@ -54,6 +53,28 @@ extern bool cma_pages_valid(struct cma *cma, const struct page *pages, unsigned
 extern bool cma_release(struct cma *cma, const struct page *pages, unsigned long count);
 
 extern int cma_for_each_area(int (*it)(struct cma *cma, void *data), void *data);
+extern bool cma_intersects(struct cma *cma, unsigned long start, unsigned long end);
 
 extern void cma_reserve_pages_on_error(struct cma *cma);
+
+#ifdef CONFIG_CMA
+struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp);
+bool cma_free_folio(struct cma *cma, const struct folio *folio);
+bool cma_validate_zones(struct cma *cma);
+#else
+static inline struct folio *cma_alloc_folio(struct cma *cma, int order, gfp_t gfp)
+{
+	return NULL;
+}
+
+static inline bool cma_free_folio(struct cma *cma, const struct folio *folio)
+{
+	return false;
+}
+static inline bool cma_validate_zones(struct cma *cma)
+{
+	return false;
+}
+#endif
+
 #endif
diff --git a/include/linux/cmpxchg-emu.h b/include/linux/cmpxchg-emu.h
new file mode 100644
index 000000000000..998deec67740
--- /dev/null
+++ b/include/linux/cmpxchg-emu.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Emulated 1-byte and 2-byte cmpxchg operations for architectures
+ * lacking direct support for these sizes.  These are implemented in terms
+ * of 4-byte cmpxchg operations.
+ *
+ * Copyright (C) 2024 Paul E. McKenney.
+ */
+
+#ifndef __LINUX_CMPXCHG_EMU_H
+#define __LINUX_CMPXCHG_EMU_H
+
+uintptr_t cmpxchg_emu_u8(volatile u8 *p, uintptr_t old, uintptr_t new);
+
+#endif /* __LINUX_CMPXCHG_EMU_H */
diff --git a/include/linux/codetag.h b/include/linux/codetag.h
new file mode 100644
index 000000000000..8ea2a5f7c98a
--- /dev/null
+++ b/include/linux/codetag.h
@@ -0,0 +1,115 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * code tagging framework
+ */
+#ifndef _LINUX_CODETAG_H
+#define _LINUX_CODETAG_H
+
+#include <linux/types.h>
+
+struct codetag_iterator;
+struct codetag_type;
+struct codetag_module;
+struct seq_buf;
+struct module;
+
+#define CODETAG_SECTION_START_PREFIX	"__start_"
+#define CODETAG_SECTION_STOP_PREFIX	"__stop_"
+
+/* codetag flags */
+#define CODETAG_FLAG_INACCURATE	(1 << 0)
+
+/*
+ * An instance of this structure is created in a special ELF section at every
+ * code location being tagged.  At runtime, the special section is treated as
+ * an array of these.
+ */
+struct codetag {
+	unsigned int flags;
+	unsigned int lineno;
+	const char *modname;
+	const char *function;
+	const char *filename;
+} __aligned(8);
+
+union codetag_ref {
+	struct codetag *ct;
+};
+
+struct codetag_type_desc {
+	const char *section;
+	size_t tag_size;
+	int (*module_load)(struct module *mod,
+			   struct codetag *start, struct codetag *end);
+	void (*module_unload)(struct module *mod,
+			      struct codetag *start, struct codetag *end);
+#ifdef CONFIG_MODULES
+	void (*module_replaced)(struct module *mod, struct module *new_mod);
+	bool (*needs_section_mem)(struct module *mod, unsigned long size);
+	void *(*alloc_section_mem)(struct module *mod, unsigned long size,
+				   unsigned int prepend, unsigned long align);
+	void (*free_section_mem)(struct module *mod, bool used);
+#endif
+};
+
+struct codetag_iterator {
+	struct codetag_type *cttype;
+	struct codetag_module *cmod;
+	unsigned long mod_id;
+	struct codetag *ct;
+	unsigned long mod_seq;
+};
+
+#ifdef MODULE
+#define CT_MODULE_NAME KBUILD_MODNAME
+#else
+#define CT_MODULE_NAME NULL
+#endif
+
+#define CODE_TAG_INIT {					\
+	.modname	= CT_MODULE_NAME,		\
+	.function	= __func__,			\
+	.filename	= __FILE__,			\
+	.lineno		= __LINE__,			\
+	.flags		= 0,				\
+}
+
+void codetag_lock_module_list(struct codetag_type *cttype, bool lock);
+bool codetag_trylock_module_list(struct codetag_type *cttype);
+struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype);
+struct codetag *codetag_next_ct(struct codetag_iterator *iter);
+
+void codetag_to_text(struct seq_buf *out, struct codetag *ct);
+
+struct codetag_type *
+codetag_register_type(const struct codetag_type_desc *desc);
+
+#if defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES)
+
+bool codetag_needs_module_section(struct module *mod, const char *name,
+				  unsigned long size);
+void *codetag_alloc_module_section(struct module *mod, const char *name,
+				   unsigned long size, unsigned int prepend,
+				   unsigned long align);
+void codetag_free_module_sections(struct module *mod);
+void codetag_module_replaced(struct module *mod, struct module *new_mod);
+int codetag_load_module(struct module *mod);
+void codetag_unload_module(struct module *mod);
+
+#else /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */
+
+static inline bool
+codetag_needs_module_section(struct module *mod, const char *name,
+			     unsigned long size) { return false; }
+static inline void *
+codetag_alloc_module_section(struct module *mod, const char *name,
+			     unsigned long size, unsigned int prepend,
+			     unsigned long align) { return NULL; }
+static inline void codetag_free_module_sections(struct module *mod) {}
+static inline void codetag_module_replaced(struct module *mod, struct module *new_mod) {}
+static inline int codetag_load_module(struct module *mod) { return 0; }
+static inline void codetag_unload_module(struct module *mod) {}
+
+#endif /* defined(CONFIG_CODE_TAGGING) && defined(CONFIG_MODULES) */
+
+#endif /* _LINUX_CODETAG_H */
diff --git a/include/linux/comedi/comedi_8254.h b/include/linux/comedi/comedi_8254.h
index d8264417e53c..d527f04400df 100644
--- a/include/linux/comedi/comedi_8254.h
+++ b/include/linux/comedi/comedi_8254.h
@@ -12,6 +12,8 @@
 #define _COMEDI_8254_H
 
 #include <linux/types.h>
+#include <linux/errno.h>
+#include <linux/err.h>
 
 struct comedi_device;
 struct comedi_insn;
@@ -57,10 +59,24 @@ struct comedi_subdevice;
 /* counter maps zero to 0x10000 */
 #define I8254_MAX_COUNT			0x10000
 
+struct comedi_8254;
+
+/**
+ * typedef comedi_8254_iocb_fn - call-back function type for 8254 register access
+ * @i8254:		pointer to struct comedi_8254
+ * @dir:		direction (0 = read, 1 = write)
+ * @reg:		register number
+ * @val:		value to write
+ *
+ * Return: Register value when reading, 0 when writing.
+ */
+typedef unsigned int comedi_8254_iocb_fn(struct comedi_8254 *i8254, int dir,
+					 unsigned int reg, unsigned int val);
+
 /**
  * struct comedi_8254 - private data used by this module
- * @iobase:		PIO base address of the registers (in/out)
- * @mmio:		MMIO base address of the registers (read/write)
+ * @iocb:		I/O call-back function for register access
+ * @context:		context for register access (e.g. a base address)
  * @iosize:		I/O size used to access the registers (b/w/l)
  * @regshift:		register gap shift
  * @osc_base:		cascaded oscillator speed in ns
@@ -76,8 +92,8 @@ struct comedi_subdevice;
  * @insn_config:	driver specific (*insn_config) callback
  */
 struct comedi_8254 {
-	unsigned long iobase;
-	void __iomem *mmio;
+	comedi_8254_iocb_fn *iocb;
+	unsigned long context;
 	unsigned int iosize;
 	unsigned int regshift;
 	unsigned int osc_base;
@@ -122,13 +138,24 @@ void comedi_8254_set_busy(struct comedi_8254 *i8254,
 void comedi_8254_subdevice_init(struct comedi_subdevice *s,
 				struct comedi_8254 *i8254);
 
-struct comedi_8254 *comedi_8254_init(unsigned long iobase,
-				     unsigned int osc_base,
-				     unsigned int iosize,
-				     unsigned int regshift);
-struct comedi_8254 *comedi_8254_mm_init(void __iomem *mmio,
-					unsigned int osc_base,
-					unsigned int iosize,
-					unsigned int regshift);
+#ifdef CONFIG_HAS_IOPORT
+struct comedi_8254 *comedi_8254_io_alloc(unsigned long iobase,
+					 unsigned int osc_base,
+					 unsigned int iosize,
+					 unsigned int regshift);
+#else
+static inline struct comedi_8254 *comedi_8254_io_alloc(unsigned long iobase,
+						       unsigned int osc_base,
+						       unsigned int iosize,
+						       unsigned int regshift)
+{
+	return ERR_PTR(-ENXIO);
+}
+#endif
+
+struct comedi_8254 *comedi_8254_mm_alloc(void __iomem *mmio,
+					 unsigned int osc_base,
+					 unsigned int iosize,
+					 unsigned int regshift);
 
 #endif	/* _COMEDI_8254_H */
diff --git a/include/linux/comedi/comedi_8255.h b/include/linux/comedi/comedi_8255.h
index b2a5bc6b3a49..d24a69da389b 100644
--- a/include/linux/comedi/comedi_8255.h
+++ b/include/linux/comedi/comedi_8255.h
@@ -10,6 +10,8 @@
 #ifndef _COMEDI_8255_H
 #define _COMEDI_8255_H
 
+#include <linux/errno.h>
+
 #define I8255_SIZE		0x04
 
 #define I8255_DATA_A_REG	0x00
@@ -27,16 +29,26 @@
 struct comedi_device;
 struct comedi_subdevice;
 
-int subdev_8255_init(struct comedi_device *dev, struct comedi_subdevice *s,
-		     int (*io)(struct comedi_device *dev, int dir, int port,
-			       int data, unsigned long regbase),
-		     unsigned long regbase);
+#ifdef CONFIG_HAS_IOPORT
+int subdev_8255_io_init(struct comedi_device *dev, struct comedi_subdevice *s,
+			unsigned long regbase);
+#else
+static inline int subdev_8255_io_init(struct comedi_device *dev,
+				      struct comedi_subdevice *s,
+				      unsigned long regbase)
+{
+	return -ENXIO;
+}
+#endif
 
 int subdev_8255_mm_init(struct comedi_device *dev, struct comedi_subdevice *s,
-			int (*io)(struct comedi_device *dev, int dir, int port,
-				  int data, unsigned long regbase),
 			unsigned long regbase);
 
+int subdev_8255_cb_init(struct comedi_device *dev, struct comedi_subdevice *s,
+			int (*io)(struct comedi_device *dev, int dir, int port,
+				  int data, unsigned long context),
+			unsigned long context);
+
 unsigned long subdev_8255_regbase(struct comedi_subdevice *s);
 
 #endif
diff --git a/include/linux/comedi/comedidev.h b/include/linux/comedi/comedidev.h
index 0a1150900ef3..35fdc41845ce 100644
--- a/include/linux/comedi/comedidev.h
+++ b/include/linux/comedi/comedidev.h
@@ -15,6 +15,7 @@
 #include <linux/spinlock_types.h>
 #include <linux/rwsem.h>
 #include <linux/kref.h>
+#include <linux/completion.h>
 #include <linux/comedi.h>
 
 #define COMEDI_VERSION(a, b, c) (((a) << 16) + ((b) << 8) + (c))
@@ -234,16 +235,12 @@ struct comedi_buf_page {
  *
  * A COMEDI data buffer is allocated as individual pages, either in
  * conventional memory or DMA coherent memory, depending on the attached,
- * low-level hardware device.  (The buffer pages also get mapped into the
- * kernel's contiguous virtual address space pointed to by the 'prealloc_buf'
- * member of &struct comedi_async.)
+ * low-level hardware device.
  *
  * The buffer is normally freed when the COMEDI device is detached from the
  * low-level driver (which may happen due to device removal), but if it happens
  * to be mmapped at the time, the pages cannot be freed until the buffer has
- * been munmapped.  That is what the reference counter is for.  (The virtual
- * address space pointed by 'prealloc_buf' is freed when the COMEDI device is
- * detached.)
+ * been munmapped.  That is what the reference counter is for.
  */
 struct comedi_buf_map {
 	struct device *dma_hw_dev;
@@ -255,7 +252,6 @@ struct comedi_buf_map {
 
 /**
  * struct comedi_async - Control data for asynchronous COMEDI commands
- * @prealloc_buf: Kernel virtual address of allocated acquisition buffer.
  * @prealloc_bufsz: Buffer size (in bytes).
  * @buf_map: Map of buffer pages.
  * @max_bufsize: Maximum allowed buffer size (in bytes).
@@ -277,6 +273,8 @@ struct comedi_buf_map {
  * @events: Bit-vector of events that have occurred.
  * @cmd: Details of comedi command in progress.
  * @wait_head: Task wait queue for file reader or writer.
+ * @run_complete: "run complete" completion event.
+ * @run_active: "run active" reference counter.
  * @cb_mask: Bit-vector of events that should wake waiting tasks.
  * @inttrig: Software trigger function for command, or NULL.
  *
@@ -344,7 +342,6 @@ struct comedi_buf_map {
  * less than or equal to UINT_MAX).
  */
 struct comedi_async {
-	void *prealloc_buf;
 	unsigned int prealloc_bufsz;
 	struct comedi_buf_map *buf_map;
 	unsigned int max_bufsize;
@@ -363,6 +360,8 @@ struct comedi_async {
 	unsigned int events;
 	struct comedi_cmd cmd;
 	wait_queue_head_t wait_head;
+	struct completion run_complete;
+	refcount_t run_active;
 	unsigned int cb_mask;
 	int (*inttrig)(struct comedi_device *dev, struct comedi_subdevice *s,
 		       unsigned int x);
@@ -590,6 +589,8 @@ struct comedi_device *comedi_dev_get_from_minor(unsigned int minor);
 int comedi_dev_put(struct comedi_device *dev);
 
 bool comedi_is_subdevice_running(struct comedi_subdevice *s);
+bool comedi_get_is_subdevice_running(struct comedi_subdevice *s);
+void comedi_put_is_subdevice_running(struct comedi_subdevice *s);
 
 void *comedi_alloc_spriv(struct comedi_subdevice *s, size_t size);
 void comedi_set_spriv_auto_free(struct comedi_subdevice *s);
@@ -633,7 +634,7 @@ extern const struct comedi_lrange range_unknown;
  */
 struct comedi_lrange {
 	int length;
-	struct comedi_krange range[];
+	struct comedi_krange range[] __counted_by(length);
 };
 
 /**
diff --git a/include/linux/comedi/comedilib.h b/include/linux/comedi/comedilib.h
index 0223c9cd9215..1f2b22b383cc 100644
--- a/include/linux/comedi/comedilib.h
+++ b/include/linux/comedi/comedilib.h
@@ -10,8 +10,38 @@
 #ifndef _LINUX_COMEDILIB_H
 #define _LINUX_COMEDILIB_H
 
-struct comedi_device *comedi_open(const char *path);
-int comedi_close(struct comedi_device *dev);
+struct comedi_device *comedi_open_from(const char *path, int from);
+
+/**
+ * comedi_open() - Open a COMEDI device from the kernel
+ * @filename: Fake pathname of the form "/dev/comediN".
+ *
+ * Converts @filename to a COMEDI device number and "opens" it if it exists
+ * and is attached to a low-level COMEDI driver.
+ *
+ * Return: A pointer to the COMEDI device on success.
+ * Return %NULL on failure.
+ */
+static inline struct comedi_device *comedi_open(const char *path)
+{
+	return comedi_open_from(path, -1);
+}
+
+int comedi_close_from(struct comedi_device *dev, int from);
+
+/**
+ * comedi_close() - Close a COMEDI device from the kernel
+ * @dev: COMEDI device.
+ *
+ * Closes a COMEDI device previously opened by comedi_open().
+ *
+ * Returns: 0
+ */
+static inline int comedi_close(struct comedi_device *dev)
+{
+	return comedi_close_from(dev, -1);
+}
+
 int comedi_dio_get_config(struct comedi_device *dev, unsigned int subdev,
 			  unsigned int chan, unsigned int *io);
 int comedi_dio_config(struct comedi_device *dev, unsigned int subdev,
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index 57b16e69c19a..173d9c07a895 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -80,6 +80,11 @@ static inline unsigned long compact_gap(unsigned int order)
 	return 2UL << order;
 }
 
+static inline int current_is_kcompactd(void)
+{
+	return current->flags & PF_KCOMPACTD;
+}
+
 #ifdef CONFIG_COMPACTION
 
 extern unsigned int extfrag_for_order(struct zone *zone, unsigned int order);
@@ -90,7 +95,7 @@ extern enum compact_result try_to_compact_pages(gfp_t gfp_mask,
 		struct page **page);
 extern void reset_isolation_suitable(pg_data_t *pgdat);
 extern bool compaction_suitable(struct zone *zone, int order,
-					       int highest_zoneidx);
+				unsigned long watermark, int highest_zoneidx);
 
 extern void compaction_defer_reset(struct zone *zone, int order,
 				bool alloc_success);
@@ -98,8 +103,8 @@ extern void compaction_defer_reset(struct zone *zone, int order,
 bool compaction_zonelist_suitable(struct alloc_context *ac, int order,
 					int alloc_flags);
 
-extern void kcompactd_run(int nid);
-extern void kcompactd_stop(int nid);
+extern void __meminit kcompactd_run(int nid);
+extern void __meminit kcompactd_stop(int nid);
 extern void wakeup_kcompactd(pg_data_t *pgdat, int order, int highest_zoneidx);
 
 #else
@@ -108,7 +113,8 @@ static inline void reset_isolation_suitable(pg_data_t *pgdat)
 }
 
 static inline bool compaction_suitable(struct zone *zone, int order,
-						      int highest_zoneidx)
+				       unsigned long watermark,
+				       int highest_zoneidx)
 {
 	return false;
 }
diff --git a/include/linux/compat.h b/include/linux/compat.h
index 44b1736c95b5..56cebaff0c91 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -581,11 +581,6 @@ asmlinkage long compat_sys_io_pgetevents_time64(compat_aio_context_t ctx_id,
 					struct io_event __user *events,
 					struct __kernel_timespec __user *timeout,
 					const struct __compat_aio_sigset __user *usig);
-
-/* fs/cookies.c */
-asmlinkage long compat_sys_lookup_dcookie(u32, u32, char __user *, compat_size_t);
-
-/* fs/eventpoll.c */
 asmlinkage long compat_sys_epoll_pwait(int epfd,
 			struct epoll_event __user *events,
 			int maxevents, int timeout,
@@ -597,18 +592,12 @@ asmlinkage long compat_sys_epoll_pwait2(int epfd,
 			const struct __kernel_timespec __user *timeout,
 			const compat_sigset_t __user *sigmask,
 			compat_size_t sigsetsize);
-
-/* fs/fcntl.c */
 asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd,
 				 compat_ulong_t arg);
 asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd,
 				   compat_ulong_t arg);
-
-/* fs/ioctl.c */
 asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd,
 				 compat_ulong_t arg);
-
-/* fs/open.c */
 asmlinkage long compat_sys_statfs(const char __user *pathname,
 				  struct compat_statfs __user *buf);
 asmlinkage long compat_sys_statfs64(const char __user *pathname,
@@ -619,17 +608,13 @@ asmlinkage long compat_sys_fstatfs(unsigned int fd,
 asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz,
 				     struct compat_statfs64 __user *buf);
 asmlinkage long compat_sys_truncate(const char __user *, compat_off_t);
-asmlinkage long compat_sys_ftruncate(unsigned int, compat_ulong_t);
+asmlinkage long compat_sys_ftruncate(unsigned int, compat_off_t);
 /* No generic prototype for truncate64, ftruncate64, fallocate */
 asmlinkage long compat_sys_openat(int dfd, const char __user *filename,
 				  int flags, umode_t mode);
-
-/* fs/readdir.c */
 asmlinkage long compat_sys_getdents(unsigned int fd,
 				    struct compat_linux_dirent __user *dirent,
 				    unsigned int count);
-
-/* fs/read_write.c */
 asmlinkage long compat_sys_lseek(unsigned int, compat_off_t, unsigned int);
 /* No generic prototype for pread64 and pwrite64 */
 asmlinkage ssize_t compat_sys_preadv(compat_ulong_t fd,
@@ -649,14 +634,10 @@ asmlinkage long compat_sys_pwritev64(unsigned long fd,
 		const struct iovec __user *vec,
 		unsigned long vlen, loff_t pos);
 #endif
-
-/* fs/sendfile.c */
 asmlinkage long compat_sys_sendfile(int out_fd, int in_fd,
 				    compat_off_t __user *offset, compat_size_t count);
 asmlinkage long compat_sys_sendfile64(int out_fd, int in_fd,
 				    compat_loff_t __user *offset, compat_size_t count);
-
-/* fs/select.c */
 asmlinkage long compat_sys_pselect6_time32(int n, compat_ulong_t __user *inp,
 				    compat_ulong_t __user *outp,
 				    compat_ulong_t __user *exp,
@@ -677,68 +658,45 @@ asmlinkage long compat_sys_ppoll_time64(struct pollfd __user *ufds,
 				 struct __kernel_timespec __user *tsp,
 				 const compat_sigset_t __user *sigmask,
 				 compat_size_t sigsetsize);
-
-/* fs/signalfd.c */
 asmlinkage long compat_sys_signalfd4(int ufd,
 				     const compat_sigset_t __user *sigmask,
 				     compat_size_t sigsetsize, int flags);
-
-/* fs/stat.c */
 asmlinkage long compat_sys_newfstatat(unsigned int dfd,
 				      const char __user *filename,
 				      struct compat_stat __user *statbuf,
 				      int flag);
 asmlinkage long compat_sys_newfstat(unsigned int fd,
 				    struct compat_stat __user *statbuf);
-
-/* fs/sync.c: No generic prototype for sync_file_range and sync_file_range2 */
-
-/* kernel/exit.c */
+/* No generic prototype for sync_file_range and sync_file_range2 */
 asmlinkage long compat_sys_waitid(int, compat_pid_t,
 		struct compat_siginfo __user *, int,
 		struct compat_rusage __user *);
-
-
-
-/* kernel/futex.c */
 asmlinkage long
 compat_sys_set_robust_list(struct compat_robust_list_head __user *head,
 			   compat_size_t len);
 asmlinkage long
 compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr,
 			   compat_size_t __user *len_ptr);
-
-/* kernel/itimer.c */
 asmlinkage long compat_sys_getitimer(int which,
 				     struct old_itimerval32 __user *it);
 asmlinkage long compat_sys_setitimer(int which,
 				     struct old_itimerval32 __user *in,
 				     struct old_itimerval32 __user *out);
-
-/* kernel/kexec.c */
 asmlinkage long compat_sys_kexec_load(compat_ulong_t entry,
 				      compat_ulong_t nr_segments,
 				      struct compat_kexec_segment __user *,
 				      compat_ulong_t flags);
-
-/* kernel/posix-timers.c */
 asmlinkage long compat_sys_timer_create(clockid_t which_clock,
 			struct compat_sigevent __user *timer_event_spec,
 			timer_t __user *created_timer_id);
-
-/* kernel/ptrace.c */
 asmlinkage long compat_sys_ptrace(compat_long_t request, compat_long_t pid,
 				  compat_long_t addr, compat_long_t data);
-
-/* kernel/sched/core.c */
 asmlinkage long compat_sys_sched_setaffinity(compat_pid_t pid,
 				     unsigned int len,
 				     compat_ulong_t __user *user_mask_ptr);
 asmlinkage long compat_sys_sched_getaffinity(compat_pid_t pid,
 				     unsigned int len,
 				     compat_ulong_t __user *user_mask_ptr);
-
-/* kernel/signal.c */
 asmlinkage long compat_sys_sigaltstack(const compat_stack_t __user *uss_ptr,
 				       compat_stack_t __user *uoss_ptr);
 asmlinkage long compat_sys_rt_sigsuspend(compat_sigset_t __user *unewset,
@@ -763,25 +721,17 @@ asmlinkage long compat_sys_rt_sigtimedwait_time64(compat_sigset_t __user *uthese
 asmlinkage long compat_sys_rt_sigqueueinfo(compat_pid_t pid, int sig,
 				struct compat_siginfo __user *uinfo);
 /* No generic prototype for rt_sigreturn */
-
-/* kernel/sys.c */
 asmlinkage long compat_sys_times(struct compat_tms __user *tbuf);
 asmlinkage long compat_sys_getrlimit(unsigned int resource,
 				     struct compat_rlimit __user *rlim);
 asmlinkage long compat_sys_setrlimit(unsigned int resource,
 				     struct compat_rlimit __user *rlim);
 asmlinkage long compat_sys_getrusage(int who, struct compat_rusage __user *ru);
-
-/* kernel/time.c */
 asmlinkage long compat_sys_gettimeofday(struct old_timeval32 __user *tv,
 		struct timezone __user *tz);
 asmlinkage long compat_sys_settimeofday(struct old_timeval32 __user *tv,
 		struct timezone __user *tz);
-
-/* kernel/timer.c */
 asmlinkage long compat_sys_sysinfo(struct compat_sysinfo __user *info);
-
-/* ipc/mqueue.c */
 asmlinkage long compat_sys_mq_open(const char __user *u_name,
 			int oflag, compat_mode_t mode,
 			struct compat_mq_attr __user *u_attr);
@@ -790,22 +740,14 @@ asmlinkage long compat_sys_mq_notify(mqd_t mqdes,
 asmlinkage long compat_sys_mq_getsetattr(mqd_t mqdes,
 			const struct compat_mq_attr __user *u_mqstat,
 			struct compat_mq_attr __user *u_omqstat);
-
-/* ipc/msg.c */
 asmlinkage long compat_sys_msgctl(int first, int second, void __user *uptr);
 asmlinkage long compat_sys_msgrcv(int msqid, compat_uptr_t msgp,
 		compat_ssize_t msgsz, compat_long_t msgtyp, int msgflg);
 asmlinkage long compat_sys_msgsnd(int msqid, compat_uptr_t msgp,
 		compat_ssize_t msgsz, int msgflg);
-
-/* ipc/sem.c */
 asmlinkage long compat_sys_semctl(int semid, int semnum, int cmd, int arg);
-
-/* ipc/shm.c */
 asmlinkage long compat_sys_shmctl(int first, int second, void __user *uptr);
 asmlinkage long compat_sys_shmat(int shmid, compat_uptr_t shmaddr, int shmflg);
-
-/* net/socket.c */
 asmlinkage long compat_sys_recvfrom(int fd, void __user *buf, compat_size_t len,
 			    unsigned flags, struct sockaddr __user *addr,
 			    int __user *addrlen);
@@ -813,20 +755,13 @@ asmlinkage long compat_sys_sendmsg(int fd, struct compat_msghdr __user *msg,
 				   unsigned flags);
 asmlinkage long compat_sys_recvmsg(int fd, struct compat_msghdr __user *msg,
 				   unsigned int flags);
-
-/* mm/filemap.c: No generic prototype for readahead */
-
-/* security/keys/keyctl.c */
+/* No generic prototype for readahead */
 asmlinkage long compat_sys_keyctl(u32 option,
 			      u32 arg2, u32 arg3, u32 arg4, u32 arg5);
-
-/* arch/example/kernel/sys_example.c */
 asmlinkage long compat_sys_execve(const char __user *filename, const compat_uptr_t __user *argv,
 		     const compat_uptr_t __user *envp);
-
-/* mm/fadvise.c: No generic prototype for fadvise64_64 */
-
-/* mm/, CONFIG_MMU only */
+/* No generic prototype for fadvise64_64 */
+/* CONFIG_MMU only */
 asmlinkage long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid,
 					compat_pid_t pid, int sig,
 					struct compat_siginfo __user *uinfo);
@@ -896,18 +831,18 @@ asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u32);
 asmlinkage long compat_sys_recv(int fd, void __user *buf, compat_size_t len,
 				unsigned flags);
 
-/* obsolete: fs/readdir.c */
+/* obsolete */
 asmlinkage long compat_sys_old_readdir(unsigned int fd,
 				       struct compat_old_linux_dirent __user *,
 				       unsigned int count);
 
-/* obsolete: fs/select.c */
+/* obsolete */
 asmlinkage long compat_sys_old_select(struct compat_sel_arg_struct __user *arg);
 
-/* obsolete: ipc */
+/* obsolete */
 asmlinkage long compat_sys_ipc(u32, int, int, u32, compat_uptr_t, u32);
 
-/* obsolete: kernel/signal.c */
+/* obsolete */
 #ifdef __ARCH_WANT_SYS_SIGPENDING
 asmlinkage long compat_sys_sigpending(compat_old_sigset_t __user *set);
 #endif
@@ -922,7 +857,7 @@ asmlinkage long compat_sys_sigaction(int sig,
                                    struct compat_old_sigaction __user *oact);
 #endif
 
-/* obsolete: net/socket.c */
+/* obsolete */
 asmlinkage long compat_sys_socketcall(int call, u32 __user *args);
 
 #ifdef __ARCH_WANT_COMPAT_TRUNCATE64
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 6cfd6902bd5b..107ce05bd16e 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -1,36 +1,59 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_COMPILER_TYPES_H
-#error "Please don't include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
+#error "Please do not include <linux/compiler-clang.h> directly, include <linux/compiler.h> instead."
 #endif
 
 /* Compiler specific definitions for Clang compiler */
 
-/* same as gcc, this was present in clang-2.6 so we can assume it works
- * with any version that can compile the kernel
+/*
+ * Clang prior to 17 is being silly and considers many __cleanup() variables
+ * as unused (because they are, their sole purpose is to go out of scope).
+ *
+ * https://github.com/llvm/llvm-project/commit/877210faa447f4cc7db87812f8ed80e398fedd61
  */
-#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
+#undef __cleanup
+#define __cleanup(func) __maybe_unused __attribute__((__cleanup__(func)))
 
 /* all clang versions usable with the kernel support KASAN ABI version 5 */
 #define KASAN_ABI_VERSION 5
 
 /*
+ * Clang 22 added preprocessor macros to match GCC, in hopes of eventually
+ * dropping __has_feature support for sanitizers:
+ * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae4fdc8a9c
+ * Create these macros for older versions of clang so that it is easy to clean
+ * up once the minimum supported version of LLVM for building the kernel always
+ * creates these macros.
+ *
  * Note: Checking __has_feature(*_sanitizer) is only true if the feature is
  * enabled. Therefore it is not required to additionally check defined(CONFIG_*)
  * to avoid adding redundant attributes in other configurations.
  */
+#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__)
+#define __SANITIZE_ADDRESS__
+#endif
+#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__)
+#define __SANITIZE_HWADDRESS__
+#endif
+#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__)
+#define __SANITIZE_THREAD__
+#endif
 
-#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer)
-/* Emulate GCC's __SANITIZE_ADDRESS__ flag */
+/*
+ * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel.
+ */
+#ifdef __SANITIZE_HWADDRESS__
 #define __SANITIZE_ADDRESS__
+#endif
+
+#ifdef __SANITIZE_ADDRESS__
 #define __no_sanitize_address \
 		__attribute__((no_sanitize("address", "hwaddress")))
 #else
 #define __no_sanitize_address
 #endif
 
-#if __has_feature(thread_sanitizer)
-/* emulate gcc's __SANITIZE_THREAD__ flag */
-#define __SANITIZE_THREAD__
+#ifdef __SANITIZE_THREAD__
 #define __no_sanitize_thread \
 		__attribute__((no_sanitize("thread")))
 #else
@@ -85,15 +108,13 @@
 #define __no_sanitize_coverage
 #endif
 
+/* Only Clang needs to disable the coverage sanitizer for kstack_erase. */
+#define __no_kstack_erase	__no_sanitize_coverage
+
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
-#if __has_feature(kcfi)
-/* Disable CFI checking inside a function. */
-#define __nocfi		__attribute__((__no_sanitize__("kcfi")))
-#endif
-
 /*
  * Turn individual warnings and errors on and off locally, depending
  * on version.
@@ -110,11 +131,25 @@
 #define __diag_str(s)		__diag_str1(s)
 #define __diag(s)		_Pragma(__diag_str(clang diagnostic s))
 
-#if CONFIG_CLANG_VERSION >= 110000
-#define __diag_clang_11(s)	__diag(s)
-#else
-#define __diag_clang_11(s)
-#endif
+#define __diag_clang_13(s)	__diag(s)
 
 #define __diag_ignore_all(option, comment) \
-	__diag_clang(11, ignore, option)
+	__diag_clang(13, ignore, option)
+
+/*
+ * clang has horrible behavior with "g" or "rm" constraints for asm
+ * inputs, turning them into something worse than "m". Avoid using
+ * constraints with multiple possible uses (but "ir" seems to be ok):
+ *
+ *	https://github.com/llvm/llvm-project/issues/20571
+ */
+#define ASM_INPUT_G "ir"
+#define ASM_INPUT_RM "r"
+
+/*
+ * Declare compiler support for __typeof_unqual__() operator.
+ *
+ * Bindgen uses LLVM even if our C compiler is GCC, so we cannot
+ * rely on the auto-detected CONFIG_CC_HAS_TYPEOF_UNQUAL.
+ */
+#define CC_HAS_TYPEOF_UNQUAL (__clang_major__ >= 19)
diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index 7af9e34ec261..5de824a0b3d7 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef __LINUX_COMPILER_TYPES_H
-#error "Please don't include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
+#error "Please do not include <linux/compiler-gcc.h> directly, include <linux/compiler.h> instead."
 #endif
 
 /*
@@ -35,12 +35,6 @@
 	(typeof(ptr)) (__ptr + (off));					\
 })
 
-#ifdef CONFIG_RETPOLINE
-#define __noretpoline __attribute__((__indirect_branch__("keep")))
-#endif
-
-#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__)
-
 #if defined(LATENT_ENTROPY_PLUGIN) && !defined(__CHECKER__)
 #define __latent_entropy __attribute__((latent_entropy))
 #endif
@@ -54,18 +48,6 @@
  */
 #define barrier_before_unreachable() asm volatile("")
 
-/*
- * Mark a position in code as unreachable.  This can be used to
- * suppress control flow warnings after asm blocks that transfer
- * control elsewhere.
- */
-#define unreachable() \
-	do {					\
-		annotate_unreachable();		\
-		barrier_before_unreachable();	\
-		__builtin_unreachable();	\
-	} while (0)
-
 #if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP)
 #define __HAVE_BUILTIN_BSWAP32__
 #define __HAVE_BUILTIN_BSWAP64__
@@ -82,7 +64,11 @@
 #define __noscs __attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
 
+#ifdef __SANITIZE_HWADDRESS__
+#define __no_sanitize_address __attribute__((__no_sanitize__("hwaddress")))
+#else
 #define __no_sanitize_address __attribute__((__no_sanitize_address__))
+#endif
 
 #if defined(__SANITIZE_THREAD__)
 #define __no_sanitize_thread __attribute__((__no_sanitize_thread__))
@@ -137,8 +123,10 @@
 #define __diag_GCC_8(s)
 #endif
 
+#define __diag_GCC_all(s)	__diag(s)
+
 #define __diag_ignore_all(option, comment) \
-	__diag_GCC(8, ignore, option)
+	__diag(__diag_GCC_ignore option)
 
 /*
  * Prior to 9.1, -Wno-alloc-size-larger-than (and therefore the "alloc_size"
@@ -147,3 +135,11 @@
 #if GCC_VERSION < 90100
 #undef __alloc_size__
 #endif
+
+/*
+ * Declare compiler support for __typeof_unqual__() operator.
+ *
+ * Bindgen uses LLVM even if our C compiler is GCC, so we cannot
+ * rely on the auto-detected CONFIG_CC_HAS_TYPEOF_UNQUAL.
+ */
+#define CC_HAS_TYPEOF_UNQUAL (__GNUC__ >= 14)
diff --git a/include/linux/compiler-version.h b/include/linux/compiler-version.h
index 573fa85b6c0c..ac1665a98a15 100644
--- a/include/linux/compiler-version.h
+++ b/include/linux/compiler-version.h
@@ -12,3 +12,33 @@
  * and add dependency on include/config/CC_VERSION_TEXT, which is touched
  * by Kconfig when the version string from the compiler changes.
  */
+
+/* Additional tree-wide dependencies start here. */
+
+/*
+ * If any of the GCC plugins change, we need to rebuild everything that
+ * was built with them, as they may have changed their behavior and those
+ * behaviors may need to be synchronized across all translation units.
+ */
+#ifdef GCC_PLUGINS
+#include <generated/gcc-plugins.h>
+#endif
+
+/*
+ * If the randstruct seed itself changes (whether for GCC plugins or
+ * Clang), the entire tree needs to be rebuilt since the randomization of
+ * structures may change between compilation units if not.
+ */
+#ifdef RANDSTRUCT
+#include <generated/randstruct_hash.h>
+#endif
+
+/*
+ * If any external changes affect Clang's integer wrapping sanitizer
+ * behavior, a full rebuild is needed as the coverage for wrapping types
+ * may have changed, which may impact the expected behaviors that should
+ * not differ between compilation units.
+ */
+#ifdef INTEGER_WRAP
+#include <generated/integer-wrap.h>
+#endif
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index d7779a18b24f..04487c9bd751 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -109,35 +109,21 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 
 /* Unreachable code */
 #ifdef CONFIG_OBJTOOL
-/*
- * These macros help objtool understand GCC code flow for unreachable code.
- * The __COUNTER__ based labels are a hack to make each instance of the macros
- * unique, to convince GCC not to merge duplicate inline asm statements.
- */
-#define __stringify_label(n) #n
-
-#define __annotate_unreachable(c) ({					\
-	asm volatile(__stringify_label(c) ":\n\t"			\
-		     ".pushsection .discard.unreachable\n\t"		\
-		     ".long " __stringify_label(c) "b - .\n\t"		\
-		     ".popsection\n\t" : : "i" (c));			\
-})
-#define annotate_unreachable() __annotate_unreachable(__COUNTER__)
-
 /* Annotate a C jump table to allow objtool to follow the code flow */
-#define __annotate_jump_table __section(".rodata..c_jump_table")
-
+#define __annotate_jump_table __section(".data.rel.ro.c_jump_table")
 #else /* !CONFIG_OBJTOOL */
-#define annotate_unreachable()
 #define __annotate_jump_table
 #endif /* CONFIG_OBJTOOL */
 
-#ifndef unreachable
-# define unreachable() do {		\
-	annotate_unreachable();		\
+/*
+ * Mark a position in code as unreachable.  This can be used to
+ * suppress control flow warnings after asm blocks that transfer
+ * control elsewhere.
+ */
+#define unreachable() do {		\
+	barrier_before_unreachable();	\
 	__builtin_unreachable();	\
 } while (0)
-#endif
 
 /*
  * KENTRY - kernel entry point
@@ -177,10 +163,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	__asm__ ("" : "=r" (var) : "0" (var))
 #endif
 
-/* Not-quite-unique ID. */
-#ifndef __UNIQUE_ID
-# define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
-#endif
+/* Format: __UNIQUE_ID_<name>_<__COUNTER__> */
+#define __UNIQUE_ID(name)					\
+	__PASTE(__UNIQUE_ID_,					\
+	__PASTE(name,						\
+	__PASTE(_, __COUNTER__)))
 
 /**
  * data_race - mark an expression as containing intentional data races
@@ -188,33 +175,92 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  * This data_race() macro is useful for situations in which data races
  * should be forgiven.  One example is diagnostic code that accesses
  * shared variables but is not a part of the core synchronization design.
+ * For example, if accesses to a given variable are protected by a lock,
+ * except for diagnostic code, then the accesses under the lock should
+ * be plain C-language accesses and those in the diagnostic code should
+ * use data_race().  This way, KCSAN will complain if buggy lockless
+ * accesses to that variable are introduced, even if the buggy accesses
+ * are protected by READ_ONCE() or WRITE_ONCE().
  *
  * This macro *does not* affect normal code generation, but is a hint
- * to tooling that data races here are to be ignored.
+ * to tooling that data races here are to be ignored.  If the access must
+ * be atomic *and* KCSAN should ignore the access, use both data_race()
+ * and READ_ONCE(), for example, data_race(READ_ONCE(x)).
  */
 #define data_race(expr)							\
 ({									\
-	__unqual_scalar_typeof(({ expr; })) __v = ({			\
-		__kcsan_disable_current();				\
-		expr;							\
-	});								\
+	__kcsan_disable_current();					\
+	auto __v = (expr);						\
 	__kcsan_enable_current();					\
 	__v;								\
 })
 
+#ifdef __CHECKER__
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) (0)
+#else /* __CHECKER__ */
+#define __BUILD_BUG_ON_ZERO_MSG(e, msg, ...) ((int)sizeof(struct {_Static_assert(!(e), msg);}))
+#endif /* __CHECKER__ */
+
+/* &a[0] degrades to a pointer: a different type from an array */
+#define __is_array(a)		(!__same_type((a), &(a)[0]))
+#define __must_be_array(a)	__BUILD_BUG_ON_ZERO_MSG(!__is_array(a), \
+							"must be array")
+
+#define __is_byte_array(a)	(__is_array(a) && sizeof((a)[0]) == 1)
+#define __must_be_byte_array(a)	__BUILD_BUG_ON_ZERO_MSG(!__is_byte_array(a), \
+							"must be byte array")
+
+/*
+ * If the "nonstring" attribute isn't available, we have to return true
+ * so the __must_*() checks pass when "nonstring" isn't supported.
+ */
+#if __has_attribute(__nonstring__) && defined(__annotated)
+#define __is_cstr(a)		(!__annotated(a, nonstring))
+#define __is_noncstr(a)		(__annotated(a, nonstring))
+#else
+#define __is_cstr(a)		(true)
+#define __is_noncstr(a)		(true)
+#endif
+
+/* Require C Strings (i.e. NUL-terminated) lack the "nonstring" attribute. */
+#define __must_be_cstr(p) \
+	__BUILD_BUG_ON_ZERO_MSG(!__is_cstr(p), \
+				"must be C-string (NUL-terminated)")
+#define __must_be_noncstr(p) \
+	__BUILD_BUG_ON_ZERO_MSG(!__is_noncstr(p), \
+				"must be non-C-string (not NUL-terminated)")
+
+/*
+ * Use __typeof_unqual__() when available.
+ *
+ * XXX: Remove test for __CHECKER__ once
+ * sparse learns about __typeof_unqual__().
+ */
+#if CC_HAS_TYPEOF_UNQUAL && !defined(__CHECKER__)
+# define USE_TYPEOF_UNQUAL 1
+#endif
+
+/*
+ * Define TYPEOF_UNQUAL() to use __typeof_unqual__() as typeof
+ * operator when available, to return an unqualified type of the exp.
+ */
+#if defined(USE_TYPEOF_UNQUAL)
+# define TYPEOF_UNQUAL(exp) __typeof_unqual__(exp)
+#else
+# define TYPEOF_UNQUAL(exp) __typeof__(exp)
+#endif
+
 #endif /* __KERNEL__ */
 
+#if defined(CONFIG_CFI) && !defined(__DISABLE_EXPORTS) && !defined(BUILD_VDSO)
 /*
- * Force the compiler to emit 'sym' as a symbol, so that we can reference
- * it from inline assembler. Necessary in case 'sym' could be inlined
- * otherwise, or eliminated entirely due to lack of references that are
- * visible to the compiler.
+ * Force a reference to the external symbol so the compiler generates
+ * __kcfi_typid.
  */
-#define ___ADDRESSABLE(sym, __attrs) \
-	static void * __used __attrs \
-		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
-#define __ADDRESSABLE(sym) \
-	___ADDRESSABLE(sym, __section(".discard.addressable"))
+#define KCFI_REFERENCE(sym) __ADDRESSABLE(sym)
+#else
+#define KCFI_REFERENCE(sym)
+#endif
 
 /**
  * offset_to_ptr - convert a relative memory offset to an absolute pointer
@@ -227,8 +273,65 @@ static inline void *offset_to_ptr(const int *off)
 
 #endif /* __ASSEMBLY__ */
 
-/* &a[0] degrades to a pointer: a different type from an array */
-#define __must_be_array(a)	BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))
+/*
+ * Force the compiler to emit 'sym' as a symbol, so that we can reference
+ * it from inline assembler. Necessary in case 'sym' could be inlined
+ * otherwise, or eliminated entirely due to lack of references that are
+ * visible to the compiler.
+ */
+#define ___ADDRESSABLE(sym, __attrs)						\
+	static void * __used __attrs						\
+	__UNIQUE_ID(__PASTE(addressable_, sym)) = (void *)(uintptr_t)&sym;
+
+#define __ADDRESSABLE(sym) \
+	___ADDRESSABLE(sym, __section(".discard.addressable"))
+
+/*
+ * This returns a constant expression while determining if an argument is
+ * a constant expression, most importantly without evaluating the argument.
+ * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
+ *
+ * Details:
+ * - sizeof() return an integer constant expression, and does not evaluate
+ *   the value of its operand; it only examines the type of its operand.
+ * - The results of comparing two integer constant expressions is also
+ *   an integer constant expression.
+ * - The first literal "8" isn't important. It could be any literal value.
+ * - The second literal "8" is to avoid warnings about unaligned pointers;
+ *   this could otherwise just be "1".
+ * - (long)(x) is used to avoid warnings about 64-bit types on 32-bit
+ *   architectures.
+ * - The C Standard defines "null pointer constant", "(void *)0", as
+ *   distinct from other void pointers.
+ * - If (x) is an integer constant expression, then the "* 0l" resolves
+ *   it into an integer constant expression of value 0. Since it is cast to
+ *   "void *", this makes the second operand a null pointer constant.
+ * - If (x) is not an integer constant expression, then the second operand
+ *   resolves to a void pointer (but not a null pointer constant: the value
+ *   is not an integer constant 0).
+ * - The conditional operator's third operand, "(int *)8", is an object
+ *   pointer (to type "int").
+ * - The behavior (including the return type) of the conditional operator
+ *   ("operand1 ? operand2 : operand3") depends on the kind of expressions
+ *   given for the second and third operands. This is the central mechanism
+ *   of the macro:
+ *   - When one operand is a null pointer constant (i.e. when x is an integer
+ *     constant expression) and the other is an object pointer (i.e. our
+ *     third operand), the conditional operator returns the type of the
+ *     object pointer operand (i.e. "int *"). Here, within the sizeof(), we
+ *     would then get:
+ *       sizeof(*((int *)(...))  == sizeof(int)  == 4
+ *   - When one operand is a void pointer (i.e. when x is not an integer
+ *     constant expression) and the other is an object pointer (i.e. our
+ *     third operand), the conditional operator returns a "void *" type.
+ *     Here, within the sizeof(), we would then get:
+ *       sizeof(*((void *)(...)) == sizeof(void) == 1
+ * - The equality comparison to "sizeof(int)" therefore depends on (x):
+ *     sizeof(int) == sizeof(int)     (x) was a constant expression
+ *     sizeof(int) != sizeof(void)    (x) was not a constant expression
+ */
+#define __is_constexpr(x) \
+	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
 
 /*
  * Whether 'type' is a signed type or an unsigned type. Supports scalar types,
@@ -238,6 +341,37 @@ static inline void *offset_to_ptr(const int *off)
 #define is_unsigned_type(type) (!is_signed_type(type))
 
 /*
+ * Useful shorthand for "is this condition known at compile-time?"
+ *
+ * Note that the condition may involve non-constant values,
+ * but the compiler may know enough about the details of the
+ * values to determine that the condition is statically true.
+ */
+#define statically_true(x) (__builtin_constant_p(x) && (x))
+
+/*
+ * Similar to statically_true() but produces a constant expression
+ *
+ * To be used in conjunction with macros, such as BUILD_BUG_ON_ZERO(),
+ * which require their input to be a constant expression and for which
+ * statically_true() would otherwise fail.
+ *
+ * This is a trade-off: const_true() requires all its operands to be
+ * compile time constants. Else, it would always returns false even on
+ * the most trivial cases like:
+ *
+ *   true || non_const_var
+ *
+ * On the opposite, statically_true() is able to fold more complex
+ * tautologies and will return true on expressions such as:
+ *
+ *   !(non_const_var * 8 % 4)
+ *
+ * For the general case, statically_true() is better.
+ */
+#define const_true(x) __builtin_choose_expr(__is_constexpr(x), x, false)
+
+/*
  * This is needed in functions which generate the stack canary, see
  * arch/x86/kernel/smpboot.c::start_secondary() for an example.
  */
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index e659cb6fded3..c16d4199bf92 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -70,6 +70,12 @@
 #define __assume_aligned(a, ...)        __attribute__((__assume_aligned__(a, ## __VA_ARGS__)))
 
 /*
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-cleanup-variable-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#cleanup
+ */
+#define __cleanup(func)			__attribute__((__cleanup__(func)))
+
+/*
  * Note the long name.
  *
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-const-function-attribute
@@ -256,6 +262,18 @@
 #define __noreturn                      __attribute__((__noreturn__))
 
 /*
+ * Optional: only supported since GCC >= 11.1, clang >= 7.0.
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-no_005fstack_005fprotector-function-attribute
+ *   clang: https://clang.llvm.org/docs/AttributeReference.html#no-stack-protector-safebuffers
+ */
+#if __has_attribute(__no_stack_protector__)
+# define __no_stack_protector		__attribute__((__no_stack_protector__))
+#else
+# define __no_stack_protector
+#endif
+
+/*
  * Optional: not supported by gcc.
  *
  * clang: https://clang.llvm.org/docs/AttributeReference.html#overloadable
@@ -303,6 +321,18 @@
 #define __section(section)              __attribute__((__section__(section)))
 
 /*
+ * Optional: only supported since gcc >= 12
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-uninitialized-variable-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#uninitialized
+ */
+#if __has_attribute(__uninitialized__)
+# define __uninitialized		__attribute__((__uninitialized__))
+#else
+# define __uninitialized
+#endif
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-unused-function-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Type-Attributes.html#index-unused-type-attribute
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-unused-variable-attribute
@@ -319,6 +349,19 @@
 #define __used                          __attribute__((__used__))
 
 /*
+ * The __used attribute guarantees that the attributed variable will be
+ * always emitted by a compiler. It doesn't prevent the compiler from
+ * throwing 'unused' warnings when it can't detect how the variable is
+ * actually used. It's a compiler implementation details either emit
+ * the warning in that case or not.
+ *
+ * The combination of both 'used' and 'unused' attributes ensures that
+ * the variable would be emitted, and will not trigger 'unused' warnings.
+ * The attribute is applicable for functions, static and global variables.
+ */
+#define __always_used			__used __maybe_unused
+
+/*
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-warn_005funused_005fresult-function-attribute
  * clang: https://clang.llvm.org/docs/AttributeReference.html#nodiscard-warn-unused-result
  */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 547ea1ff806e..1280693766b9 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -2,9 +2,35 @@
 #ifndef __LINUX_COMPILER_TYPES_H
 #define __LINUX_COMPILER_TYPES_H
 
+/*
+ * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21.
+ * In the meantime, to support gcc < 10, we implement __has_builtin
+ * by hand.
+ */
+#ifndef __has_builtin
+#define __has_builtin(x) (0)
+#endif
+
+/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
+#define ___PASTE(a, b) a##b
+#define __PASTE(a, b) ___PASTE(a, b)
+
 #ifndef __ASSEMBLY__
 
 /*
+ * C23 introduces "auto" as a standard way to define type-inferred
+ * variables, but "auto" has been a (useless) keyword even since K&R C,
+ * so it has always been "namespace reserved."
+ *
+ * Until at some future time we require C23 support, we need the gcc
+ * extension __auto_type, but there is no reason to put that elsewhere
+ * in the source code.
+ */
+#if __STDC_VERSION__ < 202311L
+# define auto __auto_type
+#endif
+
+/*
  * Skipped when running bindgen due to a libclang issue;
  * see https://github.com/rust-lang/rust-bindgen/issues/2244.
  */
@@ -48,7 +74,7 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 #  define __user	BTF_TYPE_TAG(user)
 # endif
 # define __iomem
-# define __percpu	BTF_TYPE_TAG(percpu)
+# define __percpu	__percpu_qual BTF_TYPE_TAG(percpu)
 # define __rcu		BTF_TYPE_TAG(rcu)
 
 # define __chk_user_ptr(x)	(void)0
@@ -70,10 +96,6 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
 # define __builtin_warning(x, y...) (1)
 #endif /* __CHECKER__ */
 
-/* Indirect macros required for expanded argument pasting, eg. __LINE__. */
-#define ___PASTE(a,b) a##b
-#define __PASTE(a,b) ___PASTE(a,b)
-
 #ifdef __KERNEL__
 
 /* Attributes */
@@ -90,31 +112,71 @@ static inline void __chk_io_ptr(const volatile void __iomem *ptr) { }
  *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Label-Attributes.html#index-cold-label-attribute
  *
  * When -falign-functions=N is in use, we must avoid the cold attribute as
- * contemporary versions of GCC drop the alignment for cold functions. Worse,
- * GCC can implicitly mark callees of cold functions as cold themselves, so
- * it's not sufficient to add __function_aligned here as that will not ensure
- * that callees are correctly aligned.
+ * GCC drops the alignment for cold functions. Worse, GCC can implicitly mark
+ * callees of cold functions as cold themselves, so it's not sufficient to add
+ * __function_aligned here as that will not ensure that callees are correctly
+ * aligned.
  *
  * See:
  *
  *   https://lore.kernel.org/lkml/Y77%2FqVgvaJidFpYt@FVFF77S0Q05N
  *   https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c9
  */
-#if !defined(CONFIG_CC_IS_GCC) || (CONFIG_FUNCTION_ALIGNMENT == 0)
+#if defined(CONFIG_CC_HAS_SANE_FUNCTION_ALIGNMENT) || (CONFIG_FUNCTION_ALIGNMENT == 0)
 #define __cold				__attribute__((__cold__))
 #else
 #define __cold
 #endif
 
-/* Builtins */
+/*
+ * On x86-64 and arm64 targets, __preserve_most changes the calling convention
+ * of a function to make the code in the caller as unintrusive as possible. This
+ * convention behaves identically to the C calling convention on how arguments
+ * and return values are passed, but uses a different set of caller- and callee-
+ * saved registers.
+ *
+ * The purpose is to alleviates the burden of saving and recovering a large
+ * register set before and after the call in the caller.  This is beneficial for
+ * rarely taken slow paths, such as error-reporting functions that may be called
+ * from hot paths.
+ *
+ * Note: This may conflict with instrumentation inserted on function entry which
+ * does not use __preserve_most or equivalent convention (if in assembly). Since
+ * function tracing assumes the normal C calling convention, where the attribute
+ * is supported, __preserve_most implies notrace.  It is recommended to restrict
+ * use of the attribute to functions that should or already disable tracing.
+ *
+ * Optional: not supported by gcc.
+ *
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#preserve-most
+ */
+#if __has_attribute(__preserve_most__) && (defined(CONFIG_X86_64) || defined(CONFIG_ARM64))
+# define __preserve_most notrace __attribute__((__preserve_most__))
+#else
+# define __preserve_most
+#endif
 
 /*
- * __has_builtin is supported on gcc >= 10, clang >= 3 and icc >= 21.
- * In the meantime, to support gcc < 10, we implement __has_builtin
- * by hand.
+ * Annotating a function/variable with __retain tells the compiler to place
+ * the object in its own section and set the flag SHF_GNU_RETAIN. This flag
+ * instructs the linker to retain the object during garbage-cleanup or LTO
+ * phases.
+ *
+ * Note that the __used macro is also used to prevent functions or data
+ * being optimized out, but operates at the compiler/IR-level and may still
+ * allow unintended removal of objects during linking.
+ *
+ * Optional: only supported since gcc >= 11, clang >= 13
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-retain-function-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#retain
  */
-#ifndef __has_builtin
-#define __has_builtin(x) (0)
+#if __has_attribute(__retain__) && \
+	(defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || \
+	 defined(CONFIG_LTO_CLANG))
+# define __retain			__attribute__((__retain__))
+#else
+# define __retain
 #endif
 
 /* Compiler specific macros. */
@@ -201,10 +263,9 @@ struct ftrace_likely_data {
 /*
  * GCC does not warn about unused static inline functions for -Wunused-function.
  * Suppress the warning in clang as well by using __maybe_unused, but enable it
- * for W=1 build. This will allow clang to find unused functions. Remove the
- * __inline_maybe_unused entirely after fixing most of -Wunused-function warnings.
+ * for W=2 build. This will allow clang to find unused functions.
  */
-#ifdef KBUILD_EXTRA_WARN1
+#ifdef KBUILD_EXTRA_WARN2
 #define __inline_maybe_unused
 #else
 #define __inline_maybe_unused __maybe_unused
@@ -217,6 +278,12 @@ struct ftrace_likely_data {
 #define noinline_for_stack noinline
 
 /*
+ * Use noinline_for_tracing for functions that should not be inlined.
+ * For tracing reasons.
+ */
+#define noinline_for_tracing noinline
+
+/*
  * Sanitizer helper attributes: Because using __always_inline and
  * __no_sanitize_* conflict, provide helper attributes that will either expand
  * to __no_sanitize_* in compilation units where instrumentation is enabled
@@ -247,20 +314,125 @@ struct ftrace_likely_data {
  * disable all instrumentation. See Kconfig.kcsan where this is mandatory.
  */
 # define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation
+/*
+ * Type qualifier to mark variables where all data-racy accesses should be
+ * ignored by KCSAN. Note, the implementation simply marks these variables as
+ * volatile, since KCSAN will treat such accesses as "marked".
+ */
+# define __data_racy volatile
 # define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused
 #else
 # define __no_kcsan
+# define __data_racy
+#endif
+
+#ifdef __SANITIZE_MEMORY__
+/*
+ * Similarly to KASAN and KCSAN, KMSAN loses function attributes of inlined
+ * functions, therefore disabling KMSAN checks also requires disabling inlining.
+ *
+ * __no_sanitize_or_inline effectively prevents KMSAN from reporting errors
+ * within the function and marks all its outputs as initialized.
+ */
+# define __no_sanitize_or_inline __no_kmsan_checks notrace __maybe_unused
 #endif
 
 #ifndef __no_sanitize_or_inline
 #define __no_sanitize_or_inline __always_inline
 #endif
 
+/*
+ * The assume attribute is used to indicate that a certain condition is
+ * assumed to be true. If this condition is violated at runtime, the behavior
+ * is undefined. Compilers may or may not use this indication to generate
+ * optimized code.
+ *
+ * Note that the clang documentation states that optimizers may react
+ * differently to this attribute, and this may even have a negative
+ * performance impact. Therefore this attribute should be used with care.
+ *
+ * Optional: only supported since gcc >= 13
+ * Optional: only supported since clang >= 19
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Statement-Attributes.html#index-assume-statement-attribute
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#id13
+ *
+ */
+#ifdef CONFIG_CC_HAS_ASSUME
+# define __assume(expr)			__attribute__((__assume__(expr)))
+#else
+# define __assume(expr)
+#endif
+
+/*
+ * Optional: only supported since gcc >= 15
+ * Optional: only supported since clang >= 18
+ *
+ *   gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108896
+ * clang: https://github.com/llvm/llvm-project/pull/76348
+ *
+ * __bdos on clang < 19.1.2 can erroneously return 0:
+ * https://github.com/llvm/llvm-project/pull/110497
+ *
+ * __bdos on clang < 19.1.3 can be off by 4:
+ * https://github.com/llvm/llvm-project/pull/112636
+ */
+#ifdef CONFIG_CC_HAS_COUNTED_BY
+# define __counted_by(member)		__attribute__((__counted_by__(member)))
+#else
+# define __counted_by(member)
+#endif
+
+/*
+ * Optional: only supported since gcc >= 15
+ * Optional: not supported by Clang
+ *
+ * gcc: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=117178
+ */
+#ifdef CONFIG_CC_HAS_MULTIDIMENSIONAL_NONSTRING
+# define __nonstring_array		__attribute__((__nonstring__))
+#else
+# define __nonstring_array
+#endif
+
+/*
+ * Apply __counted_by() when the Endianness matches to increase test coverage.
+ */
+#ifdef __LITTLE_ENDIAN
+#define __counted_by_le(member)	__counted_by(member)
+#define __counted_by_be(member)
+#else
+#define __counted_by_le(member)
+#define __counted_by_be(member)	__counted_by(member)
+#endif
+
+/*
+ * This designates the minimum number of elements a passed array parameter must
+ * have. For example:
+ *
+ *     void some_function(u8 param[at_least 7]);
+ *
+ * If a caller passes an array with fewer than 7 elements, the compiler will
+ * emit a warning.
+ */
+#ifndef __CHECKER__
+#define at_least static
+#else
+#define at_least
+#endif
+
+/* Do not trap wrapping arithmetic within an annotated function. */
+#ifdef CONFIG_UBSAN_INTEGER_WRAP
+# define __signed_wrap __attribute__((no_sanitize("signed-integer-overflow")))
+#else
+# define __signed_wrap
+#endif
+
 /* Section for code which can't be instrumented at all */
 #define __noinstr_section(section)					\
 	noinline notrace __attribute((__section__(section)))		\
 	__no_kcsan __no_sanitize_address __no_profile __no_sanitize_coverage \
-	__no_sanitize_memory
+	__no_sanitize_memory __signed_wrap
 
 #define noinstr __noinstr_section(".noinstr.text")
 
@@ -302,14 +474,26 @@ struct ftrace_likely_data {
 # define randomized_struct_fields_end
 #endif
 
+#ifndef __no_kstack_erase
+# define __no_kstack_erase
+#endif
+
 #ifndef __noscs
 # define __noscs
 #endif
 
-#ifndef __nocfi
+#if defined(CONFIG_CFI)
+# define __nocfi		__attribute__((__no_sanitize__("kcfi")))
+#else
 # define __nocfi
 #endif
 
+#if defined(CONFIG_ARCH_USES_CFI_GENERIC_LLVM_PASS)
+# define __nocfi_generic	__nocfi
+#else
+# define __nocfi_generic
+#endif
+
 /*
  * Any place that could be marked with the "alloc_size" attribute is also
  * a place to be marked with the "malloc" attribute, except those that may
@@ -324,8 +508,51 @@ struct ftrace_likely_data {
 # define __realloc_size(x, ...)
 #endif
 
-#ifndef asm_volatile_goto
-#define asm_volatile_goto(x...) asm goto(x)
+/*
+ * When the size of an allocated object is needed, use the best available
+ * mechanism to find it. (For cases where sizeof() cannot be used.)
+ *
+ * Optional: only supported since gcc >= 12
+ *
+ *   gcc: https://gcc.gnu.org/onlinedocs/gcc/Object-Size-Checking.html
+ * clang: https://clang.llvm.org/docs/LanguageExtensions.html#evaluating-object-size
+ */
+#if __has_builtin(__builtin_dynamic_object_size)
+#define __struct_size(p)	__builtin_dynamic_object_size(p, 0)
+#define __member_size(p)	__builtin_dynamic_object_size(p, 1)
+#else
+#define __struct_size(p)	__builtin_object_size(p, 0)
+#define __member_size(p)	__builtin_object_size(p, 1)
+#endif
+
+/*
+ * Determine if an attribute has been applied to a variable.
+ * Using __annotated needs to check for __annotated being available,
+ * or negative tests may fail when annotation cannot be checked. For
+ * example, see the definition of __is_cstr().
+ */
+#if __has_builtin(__builtin_has_attribute)
+#define __annotated(var, attr)	__builtin_has_attribute(var, attr)
+#endif
+
+/*
+ * Some versions of gcc do not mark 'asm goto' volatile:
+ *
+ *  https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103979
+ *
+ * We do it here by hand, because it doesn't hurt.
+ */
+#ifndef asm_goto_output
+#define asm_goto_output(x...) asm volatile goto(x)
+#endif
+
+/*
+ * Clang has trouble with constraints with multiple
+ * alternative behaviors (mainly "g" and "rm").
+ */
+#ifndef ASM_INPUT_G
+  #define ASM_INPUT_G "g"
+  #define ASM_INPUT_RM "rm"
 #endif
 
 #ifdef CONFIG_CC_HAS_ASM_INLINE
@@ -365,6 +592,12 @@ struct ftrace_likely_data {
 	 sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 
 #ifdef __OPTIMIZE__
+/*
+ * #ifdef __OPTIMIZE__ is only a good approximation; for instance "make
+ * CFLAGS_foo.o=-Og" defines __OPTIMIZE__, does not elide the conditional code
+ * and can break compilation with wrong error message(s). Combine with
+ * -U__OPTIMIZE__ when needed.
+ */
 # define __compiletime_assert(condition, msg, prefix, suffix)		\
 	do {								\
 		/*							\
@@ -378,7 +611,7 @@ struct ftrace_likely_data {
 			prefix ## suffix();				\
 	} while (0)
 #else
-# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
+# define __compiletime_assert(condition, msg, prefix, suffix) ((void)(condition))
 #endif
 
 #define _compiletime_assert(condition, msg, prefix, suffix) \
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 62b32b19e0a8..fb2915676574 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -116,6 +116,7 @@ extern bool try_wait_for_completion(struct completion *x);
 extern bool completion_done(struct completion *x);
 
 extern void complete(struct completion *);
+extern void complete_on_current_cpu(struct completion *x);
 extern void complete_all(struct completion *);
 
 #endif
diff --git a/include/linux/component.h b/include/linux/component.h
index df4aa75c9e7c..9d6c66401280 100644
--- a/include/linux/component.h
+++ b/include/linux/component.h
@@ -3,7 +3,7 @@
 #define COMPONENT_H
 
 #include <linux/stddef.h>
-
+#include <linux/types.h>
 
 struct device;
 
@@ -90,6 +90,8 @@ int component_compare_dev_name(struct device *dev, void *data);
 
 void component_master_del(struct device *,
 	const struct component_master_ops *);
+bool component_master_is_bound(struct device *parent,
+	const struct component_master_ops *ops);
 
 struct component_match;
 
diff --git a/include/linux/configfs.h b/include/linux/configfs.h
index 2606711adb18..ef65c75beeaa 100644
--- a/include/linux/configfs.h
+++ b/include/linux/configfs.h
@@ -64,8 +64,8 @@ extern void config_item_put(struct config_item *);
 
 struct config_item_type {
 	struct module				*ct_owner;
-	struct configfs_item_operations		*ct_item_ops;
-	struct configfs_group_operations	*ct_group_ops;
+	const struct configfs_item_operations	*ct_item_ops;
+	const struct configfs_group_operations	*ct_group_ops;
 	struct configfs_attribute		**ct_attrs;
 	struct configfs_bin_attribute		**ct_bin_attrs;
 };
@@ -120,15 +120,19 @@ struct configfs_attribute {
 	ssize_t (*store)(struct config_item *, const char *, size_t);
 };
 
-#define CONFIGFS_ATTR(_pfx, _name)			\
+#define CONFIGFS_ATTR_PERM(_pfx, _name, _perm)		\
 static struct configfs_attribute _pfx##attr_##_name = {	\
 	.ca_name	= __stringify(_name),		\
-	.ca_mode	= S_IRUGO | S_IWUSR,		\
+	.ca_mode	= _perm,			\
 	.ca_owner	= THIS_MODULE,			\
 	.show		= _pfx##_name##_show,		\
 	.store		= _pfx##_name##_store,		\
 }
 
+#define CONFIGFS_ATTR(_pfx, _name) CONFIGFS_ATTR_PERM(	\
+		_pfx, _name, S_IRUGO | S_IWUSR		\
+)
+
 #define CONFIGFS_ATTR_RO(_pfx, _name)			\
 static struct configfs_attribute _pfx##attr_##_name = {	\
 	.ca_name	= __stringify(_name),		\
@@ -216,6 +220,9 @@ struct configfs_group_operations {
 	struct config_group *(*make_group)(struct config_group *group, const char *name);
 	void (*disconnect_notify)(struct config_group *group, struct config_item *item);
 	void (*drop_item)(struct config_group *group, struct config_item *item);
+	bool (*is_visible)(struct config_item *item, struct configfs_attribute *attr, int n);
+	bool (*is_bin_visible)(struct config_item *item, struct configfs_bin_attribute *attr,
+			       int n);
 };
 
 struct configfs_subsystem {
diff --git a/include/linux/connector.h b/include/linux/connector.h
index 487350bb19c3..70bc1160f3d8 100644
--- a/include/linux/connector.h
+++ b/include/linux/connector.h
@@ -90,13 +90,18 @@ void cn_del_callback(const struct cb_id *id);
  *		If @group is not zero, then message will be delivered
  *		to the specified group.
  * @gfp_mask:	GFP mask.
+ * @filter:     Filter function to be used at netlink layer.
+ * @filter_data:Filter data to be supplied to the filter function
  *
  * It can be safely called from softirq context, but may silently
  * fail under strong memory pressure.
  *
  * If there are no listeners for given group %-ESRCH can be returned.
  */
-int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid, u32 group, gfp_t gfp_mask);
+int cn_netlink_send_mult(struct cn_msg *msg, u16 len, u32 portid,
+			 u32 group, gfp_t gfp_mask,
+			 netlink_filter_fn filter,
+			 void *filter_data);
 
 /**
  * cn_netlink_send - Sends message to the specified groups.
diff --git a/include/linux/console.h b/include/linux/console.h
index d3195664baa5..fc9f5c5c1b04 100644
--- a/include/linux/console.h
+++ b/include/linux/console.h
@@ -16,8 +16,12 @@
 
 #include <linux/atomic.h>
 #include <linux/bits.h>
+#include <linux/irq_work.h>
 #include <linux/rculist.h>
+#include <linux/rcuwait.h>
+#include <linux/smp.h>
 #include <linux/types.h>
+#include <linux/vesa.h>
 
 struct vc_data;
 struct console_font_op;
@@ -36,63 +40,91 @@ enum vc_intensity;
 /**
  * struct consw - callbacks for consoles
  *
+ * @owner:      the module to get references of when this console is used
+ * @con_startup: set up the console and return its name (like VGA, EGA, ...)
+ * @con_init:   initialize the console on @vc. @init is true for the very first
+ *		call on this @vc.
+ * @con_deinit: deinitialize the console from @vc.
+ * @con_clear:  erase @count characters at [@x, @y] on @vc. @count >= 1.
+ * @con_putc:   emit one character with attributes @ca to [@x, @y] on @vc.
+ *		(optional -- @con_putcs would be called instead)
+ * @con_putcs:  emit @count characters with attributes @s to [@x, @y] on @vc.
+ * @con_cursor: enable/disable cursor depending on @enable
  * @con_scroll: move lines from @top to @bottom in direction @dir by @lines.
  *		Return true if no generic handling should be done.
  *		Invoked by csi_M and printing to the console.
- * @con_set_palette: sets the palette of the console to @table (optional)
+ * @con_switch: notifier about the console switch; it is supposed to return
+ *		true if a redraw is needed.
+ * @con_blank:  blank/unblank the console. The target mode is passed in @blank.
+ *		@mode_switch is set if changing from/to text/graphics. The hook
+ *		is supposed to return true if a redraw is needed.
+ * @con_font_set: set console @vc font to @font with height @vpitch. @flags can
+ *		be %KD_FONT_FLAG_DONT_RECALC. (optional)
+ * @con_font_get: fetch the current font on @vc of height @vpitch into @font.
+ *		(optional)
+ * @con_font_default: set default font on @vc. @name can be %NULL or font name
+ *		to search for. @font can be filled back. (optional)
+ * @con_resize:	resize the @vc console to @width x @height. @from_user is true
+ *		when this change comes from the user space.
+ * @con_set_palette: sets the palette of the console @vc to @table (optional)
  * @con_scrolldelta: the contents of the console should be scrolled by @lines.
  *		     Invoked by user. (optional)
+ * @con_set_origin: set origin (see &vc_data::vc_origin) of the @vc. If not
+ *		provided or returns false, the origin is set to
+ *		@vc->vc_screenbuf. (optional)
+ * @con_save_screen: save screen content into @vc->vc_screenbuf. Called e.g.
+ *		upon entering graphics. (optional)
+ * @con_build_attr: build attributes based on @color, @intensity and other
+ *		parameters. The result is used for both normal and erase
+ *		characters. (optional)
+ * @con_invert_region: invert a region of length @count on @vc starting at @p.
+ *		(optional)
+ * @con_debug_enter: prepare the console for the debugger. This includes, but
+ *		is not limited to, unblanking the console, loading an
+ *		appropriate palette, and allowing debugger generated output.
+ *		(optional)
+ * @con_debug_leave: restore the console to its pre-debug state as closely as
+ *		possible. (optional)
  */
 struct consw {
 	struct module *owner;
 	const char *(*con_startup)(void);
-	void	(*con_init)(struct vc_data *vc, int init);
+	void	(*con_init)(struct vc_data *vc, bool init);
 	void	(*con_deinit)(struct vc_data *vc);
-	void	(*con_clear)(struct vc_data *vc, int sy, int sx, int height,
-			int width);
-	void	(*con_putc)(struct vc_data *vc, int c, int ypos, int xpos);
-	void	(*con_putcs)(struct vc_data *vc, const unsigned short *s,
-			int count, int ypos, int xpos);
-	void	(*con_cursor)(struct vc_data *vc, int mode);
+	void	(*con_clear)(struct vc_data *vc, unsigned int y,
+			     unsigned int x, unsigned int count);
+	void	(*con_putc)(struct vc_data *vc, u16 ca, unsigned int y,
+			    unsigned int x);
+	void	(*con_putcs)(struct vc_data *vc, const u16 *s,
+			     unsigned int count, unsigned int ypos,
+			     unsigned int xpos);
+	void	(*con_cursor)(struct vc_data *vc, bool enable);
 	bool	(*con_scroll)(struct vc_data *vc, unsigned int top,
 			unsigned int bottom, enum con_scroll dir,
 			unsigned int lines);
-	int	(*con_switch)(struct vc_data *vc);
-	int	(*con_blank)(struct vc_data *vc, int blank, int mode_switch);
-	int	(*con_font_set)(struct vc_data *vc, struct console_font *font,
-			unsigned int vpitch, unsigned int flags);
+	bool	(*con_switch)(struct vc_data *vc);
+	bool	(*con_blank)(struct vc_data *vc, enum vesa_blank_mode blank,
+			     bool mode_switch);
+	int	(*con_font_set)(struct vc_data *vc,
+				const struct console_font *font,
+				unsigned int vpitch, unsigned int flags);
 	int	(*con_font_get)(struct vc_data *vc, struct console_font *font,
 			unsigned int vpitch);
 	int	(*con_font_default)(struct vc_data *vc,
-			struct console_font *font, char *name);
+			struct console_font *font, const char *name);
 	int     (*con_resize)(struct vc_data *vc, unsigned int width,
-			unsigned int height, unsigned int user);
+			      unsigned int height, bool from_user);
 	void	(*con_set_palette)(struct vc_data *vc,
 			const unsigned char *table);
 	void	(*con_scrolldelta)(struct vc_data *vc, int lines);
-	int	(*con_set_origin)(struct vc_data *vc);
+	bool	(*con_set_origin)(struct vc_data *vc);
 	void	(*con_save_screen)(struct vc_data *vc);
 	u8	(*con_build_attr)(struct vc_data *vc, u8 color,
 			enum vc_intensity intensity,
 			bool blink, bool underline, bool reverse, bool italic);
 	void	(*con_invert_region)(struct vc_data *vc, u16 *p, int count);
-	u16    *(*con_screen_pos)(const struct vc_data *vc, int offset);
-	unsigned long (*con_getxy)(struct vc_data *vc, unsigned long position,
-			int *px, int *py);
-	/*
-	 * Flush the video console driver's scrollback buffer
-	 */
-	void	(*con_flush_scrollback)(struct vc_data *vc);
-	/*
-	 * Prepare the console for the debugger.  This includes, but is not
-	 * limited to, unblanking the console, loading an appropriate
-	 * palette, and allowing debugger generated output.
-	 */
-	int	(*con_debug_enter)(struct vc_data *vc);
-	/*
-	 * Restore the console to its pre-debug state as closely as possible.
-	 */
-	int	(*con_debug_leave)(struct vc_data *vc);
+	void	(*con_debug_enter)(struct vc_data *vc);
+	void	(*con_debug_leave)(struct vc_data *vc);
 };
 
 extern const struct consw *conswitchp;
@@ -101,36 +133,32 @@ extern const struct consw dummy_con;	/* dummy console buffer */
 extern const struct consw vga_con;	/* VGA text console */
 extern const struct consw newport_con;	/* SGI Newport console  */
 
+struct screen_info;
+#ifdef CONFIG_VGA_CONSOLE
+void vgacon_register_screen(struct screen_info *si);
+#else
+static inline void vgacon_register_screen(struct screen_info *si) { }
+#endif
+
 int con_is_bound(const struct consw *csw);
 int do_unregister_con_driver(const struct consw *csw);
 int do_take_over_console(const struct consw *sw, int first, int last, int deflt);
 void give_up_console(const struct consw *sw);
-#ifdef CONFIG_HW_CONSOLE
-int con_debug_enter(struct vc_data *vc);
-int con_debug_leave(void);
+#ifdef CONFIG_VT
+void con_debug_enter(struct vc_data *vc);
+void con_debug_leave(void);
 #else
-static inline int con_debug_enter(struct vc_data *vc)
-{
-	return 0;
-}
-static inline int con_debug_leave(void)
-{
-	return 0;
-}
+static inline void con_debug_enter(struct vc_data *vc) { }
+static inline void con_debug_leave(void) { }
 #endif
 
-/* cursor */
-#define CM_DRAW     (1)
-#define CM_ERASE    (2)
-#define CM_MOVE     (3)
-
 /*
  * The interface for a console, or any other device that wants to capture
  * console messages (printer driver?)
  */
 
 /**
- * cons_flags - General console flags
+ * enum cons_flags - General console flags
  * @CON_PRINTBUFFER:	Used by newly registered consoles to avoid duplicate
  *			output of messages that were already shown by boot
  *			consoles or read by userspace via syslog() syscall.
@@ -154,6 +182,12 @@ static inline int con_debug_leave(void)
  *			receiving the printk spam for obvious reasons.
  * @CON_EXTENDED:	The console supports the extended output format of
  *			/dev/kmesg which requires a larger output buffer.
+ * @CON_SUSPENDED:	Indicates if a console is suspended. If true, the
+ *			printing callbacks must not be called.
+ * @CON_NBCON:		Console can operate outside of the legacy style console_lock
+ *			constraints.
+ * @CON_NBCON_ATOMIC_UNSAFE: The write_atomic() callback is not safe and is
+ *			therefore only used by nbcon_atomic_flush_unsafe().
  */
 enum cons_flags {
 	CON_PRINTBUFFER		= BIT(0),
@@ -163,12 +197,119 @@ enum cons_flags {
 	CON_ANYTIME		= BIT(4),
 	CON_BRL			= BIT(5),
 	CON_EXTENDED		= BIT(6),
+	CON_SUSPENDED		= BIT(7),
+	CON_NBCON		= BIT(8),
+	CON_NBCON_ATOMIC_UNSAFE	= BIT(9),
+};
+
+/**
+ * struct nbcon_state - console state for nbcon consoles
+ * @atom:	Compound of the state fields for atomic operations
+ *
+ * @req_prio:		The priority of a handover request
+ * @prio:		The priority of the current owner
+ * @unsafe:		Console is busy in a non takeover region
+ * @unsafe_takeover:	A hostile takeover in an unsafe state happened in the
+ *			past. The console cannot be safe until re-initialized.
+ * @cpu:		The CPU on which the owner runs
+ *
+ * To be used for reading and preparing of the value stored in the nbcon
+ * state variable @console::nbcon_state.
+ *
+ * The @prio and @req_prio fields are particularly important to allow
+ * spin-waiting to timeout and give up without the risk of a waiter being
+ * assigned the lock after giving up.
+ */
+struct nbcon_state {
+	union {
+		unsigned int	atom;
+		struct {
+			unsigned int prio		:  2;
+			unsigned int req_prio		:  2;
+			unsigned int unsafe		:  1;
+			unsigned int unsafe_takeover	:  1;
+			unsigned int cpu		: 24;
+		};
+	};
+};
+
+/*
+ * The nbcon_state struct is used to easily create and interpret values that
+ * are stored in the @console::nbcon_state variable. Ensure this struct stays
+ * within the size boundaries of the atomic variable's underlying type in
+ * order to avoid any accidental truncation.
+ */
+static_assert(sizeof(struct nbcon_state) <= sizeof(int));
+
+/**
+ * enum nbcon_prio - console owner priority for nbcon consoles
+ * @NBCON_PRIO_NONE:		Unused
+ * @NBCON_PRIO_NORMAL:		Normal (non-emergency) usage
+ * @NBCON_PRIO_EMERGENCY:	Emergency output (WARN/OOPS...)
+ * @NBCON_PRIO_PANIC:		Panic output
+ * @NBCON_PRIO_MAX:		The number of priority levels
+ *
+ * A higher priority context can takeover the console when it is
+ * in the safe state. The final attempt to flush consoles in panic()
+ * can be allowed to do so even in an unsafe state (Hope and pray).
+ */
+enum nbcon_prio {
+	NBCON_PRIO_NONE = 0,
+	NBCON_PRIO_NORMAL,
+	NBCON_PRIO_EMERGENCY,
+	NBCON_PRIO_PANIC,
+	NBCON_PRIO_MAX,
+};
+
+struct console;
+struct printk_buffers;
+
+/**
+ * struct nbcon_context - Context for console acquire/release
+ * @console:			The associated console
+ * @spinwait_max_us:		Limit for spin-wait acquire
+ * @prio:			Priority of the context
+ * @allow_unsafe_takeover:	Allow performing takeover even if unsafe. Can
+ *				be used only with NBCON_PRIO_PANIC @prio. It
+ *				might cause a system freeze when the console
+ *				is used later.
+ * @backlog:			Ringbuffer has pending records
+ * @pbufs:			Pointer to the text buffer for this context
+ * @seq:			The sequence number to print for this context
+ */
+struct nbcon_context {
+	/* members set by caller */
+	struct console		*console;
+	unsigned int		spinwait_max_us;
+	enum nbcon_prio		prio;
+	unsigned int		allow_unsafe_takeover	: 1;
+
+	/* members set by emit */
+	unsigned int		backlog			: 1;
+
+	/* members set by acquire */
+	struct printk_buffers	*pbufs;
+	u64			seq;
+};
+
+/**
+ * struct nbcon_write_context - Context handed to the nbcon write callbacks
+ * @ctxt:		The core console context
+ * @outbuf:		Pointer to the text buffer for output
+ * @len:		Length to write
+ * @unsafe_takeover:	If a hostile takeover in an unsafe state has occurred
+ */
+struct nbcon_write_context {
+	struct nbcon_context	__private ctxt;
+	char			*outbuf;
+	unsigned int		len;
+	bool			unsafe_takeover;
 };
 
 /**
  * struct console - The console descriptor structure
  * @name:		The name of the console driver
- * @write:		Write callback to output messages (Optional)
+ * @write:		Legacy write callback to output messages (Optional)
  * @read:		Read callback for console input (Optional)
  * @device:		The underlying TTY device driver (Optional)
  * @unblank:		Callback to unblank the console (Optional)
@@ -184,6 +325,15 @@ enum cons_flags {
  * @dropped:		Number of unreported dropped ringbuffer records
  * @data:		Driver private data
  * @node:		hlist node for the console list
+ *
+ * @nbcon_state:	State for nbcon consoles
+ * @nbcon_seq:		Sequence number of the next record for nbcon to print
+ * @nbcon_device_ctxt:	Context available for non-printing operations
+ * @nbcon_prev_seq:	Seq num the previous nbcon owner was assigned to print
+ * @pbufs:		Pointer to nbcon private buffer
+ * @kthread:		Printer kthread for this console
+ * @rcuwait:		RCU-safe wait object for @kthread waking
+ * @irq_work:		Defer @kthread waking to IRQ work context
  */
 struct console {
 	char			name[16];
@@ -203,6 +353,123 @@ struct console {
 	unsigned long		dropped;
 	void			*data;
 	struct hlist_node	node;
+
+	/* nbcon console specific members */
+
+	/**
+	 * @write_atomic:
+	 *
+	 * NBCON callback to write out text in any context. (Optional)
+	 *
+	 * This callback is called with the console already acquired. However,
+	 * a higher priority context is allowed to take it over by default.
+	 *
+	 * The callback must call nbcon_enter_unsafe() and nbcon_exit_unsafe()
+	 * around any code where the takeover is not safe, for example, when
+	 * manipulating the serial port registers.
+	 *
+	 * nbcon_enter_unsafe() will fail if the context has lost the console
+	 * ownership in the meantime. In this case, the callback is no longer
+	 * allowed to go forward. It must back out immediately and carefully.
+	 * The buffer content is also no longer trusted since it no longer
+	 * belongs to the context.
+	 *
+	 * The callback should allow the takeover whenever it is safe. It
+	 * increases the chance to see messages when the system is in trouble.
+	 * If the driver must reacquire ownership in order to finalize or
+	 * revert hardware changes, nbcon_reacquire_nobuf() can be used.
+	 * However, on reacquire the buffer content is no longer available. A
+	 * reacquire cannot be used to resume printing.
+	 *
+	 * The callback can be called from any context (including NMI).
+	 * Therefore it must avoid usage of any locking and instead rely
+	 * on the console ownership for synchronization.
+	 */
+	void (*write_atomic)(struct console *con, struct nbcon_write_context *wctxt);
+
+	/**
+	 * @write_thread:
+	 *
+	 * NBCON callback to write out text in task context.
+	 *
+	 * This callback must be called only in task context with both
+	 * device_lock() and the nbcon console acquired with
+	 * NBCON_PRIO_NORMAL.
+	 *
+	 * The same rules for console ownership verification and unsafe
+	 * sections handling applies as with write_atomic().
+	 *
+	 * The console ownership handling is necessary for synchronization
+	 * against write_atomic() which is synchronized only via the context.
+	 *
+	 * The device_lock() provides the primary serialization for operations
+	 * on the device. It might be as relaxed (mutex)[*] or as tight
+	 * (disabled preemption and interrupts) as needed. It allows
+	 * the kthread to operate in the least restrictive mode[**].
+	 *
+	 * [*] Standalone nbcon_context_try_acquire() is not safe with
+	 *     the preemption enabled, see nbcon_owner_matches(). But it
+	 *     can be safe when always called in the preemptive context
+	 *     under the device_lock().
+	 *
+	 * [**] The device_lock() makes sure that nbcon_context_try_acquire()
+	 *      would never need to spin which is important especially with
+	 *      PREEMPT_RT.
+	 */
+	void (*write_thread)(struct console *con, struct nbcon_write_context *wctxt);
+
+	/**
+	 * @device_lock:
+	 *
+	 * NBCON callback to begin synchronization with driver code.
+	 *
+	 * Console drivers typically must deal with access to the hardware
+	 * via user input/output (such as an interactive login shell) and
+	 * output of kernel messages via printk() calls. This callback is
+	 * called by the printk-subsystem whenever it needs to synchronize
+	 * with hardware access by the driver. It should be implemented to
+	 * use whatever synchronization mechanism the driver is using for
+	 * itself (for example, the port lock for uart serial consoles).
+	 *
+	 * The callback is always called from task context. It may use any
+	 * synchronization method required by the driver.
+	 *
+	 * IMPORTANT: The callback MUST disable migration. The console driver
+	 *	may be using a synchronization mechanism that already takes
+	 *	care of this (such as spinlocks). Otherwise this function must
+	 *	explicitly call migrate_disable().
+	 *
+	 * The flags argument is provided as a convenience to the driver. It
+	 * will be passed again to device_unlock(). It can be ignored if the
+	 * driver does not need it.
+	 */
+	void (*device_lock)(struct console *con, unsigned long *flags);
+
+	/**
+	 * @device_unlock:
+	 *
+	 * NBCON callback to finish synchronization with driver code.
+	 *
+	 * It is the counterpart to device_lock().
+	 *
+	 * This callback is always called from task context. It must
+	 * appropriately re-enable migration (depending on how device_lock()
+	 * disabled migration).
+	 *
+	 * The flags argument is the value of the same variable that was
+	 * passed to device_lock().
+	 */
+	void (*device_unlock)(struct console *con, unsigned long flags);
+
+	atomic_t		__private nbcon_state;
+	atomic_long_t		__private nbcon_seq;
+	struct nbcon_context	__private nbcon_device_ctxt;
+	atomic_long_t           __private nbcon_prev_seq;
+
+	struct printk_buffers	*pbufs;
+	struct task_struct	*kthread;
+	struct rcuwait		rcuwait;
+	struct irq_work		irq_work;
 };
 
 #ifdef CONFIG_LOCKDEP
@@ -231,28 +498,34 @@ extern void console_list_unlock(void) __releases(console_mutex);
 extern struct hlist_head console_list;
 
 /**
- * console_srcu_read_flags - Locklessly read the console flags
+ * console_srcu_read_flags - Locklessly read flags of a possibly registered
+ *				console
  * @con:	struct console pointer of console to read flags from
  *
- * This function provides the necessary READ_ONCE() and data_race()
- * notation for locklessly reading the console flags. The READ_ONCE()
- * in this function matches the WRITE_ONCE() when @flags are modified
- * for registered consoles with console_srcu_write_flags().
+ * Locklessly reading @con->flags provides a consistent read value because
+ * there is at most one CPU modifying @con->flags and that CPU is using only
+ * read-modify-write operations to do so.
+ *
+ * Requires console_srcu_read_lock to be held, which implies that @con might
+ * be a registered console. The purpose of holding console_srcu_read_lock is
+ * to guarantee that the console state is valid (CON_SUSPENDED/CON_ENABLED)
+ * and that no exit/cleanup routines will run if the console is currently
+ * undergoing unregistration.
  *
- * Only use this function to read console flags when locklessly
- * iterating the console list via srcu.
+ * If the caller is holding the console_list_lock or it is _certain_ that
+ * @con is not and will not become registered, the caller may read
+ * @con->flags directly instead.
  *
  * Context: Any context.
+ * Return: The current value of the @con->flags field.
  */
 static inline short console_srcu_read_flags(const struct console *con)
 {
 	WARN_ON_ONCE(!console_srcu_read_lock_is_held());
 
 	/*
-	 * Locklessly reading console->flags provides a consistent
-	 * read value because there is at most one CPU modifying
-	 * console->flags and that CPU is using only read-modify-write
-	 * operations to do so.
+	 * The READ_ONCE() matches the WRITE_ONCE() when @flags are modified
+	 * for registered consoles with console_srcu_write_flags().
 	 */
 	return data_race(READ_ONCE(con->flags));
 }
@@ -321,7 +594,7 @@ static inline bool console_is_registered(const struct console *con)
  * for_each_console() - Iterator over registered consoles
  * @con:	struct console pointer used as loop cursor
  *
- * The console list and the console->flags are immutable while iterating.
+ * The console list and the &console.flags are immutable while iterating.
  *
  * Requires console_list_lock to be held.
  */
@@ -329,6 +602,86 @@ static inline bool console_is_registered(const struct console *con)
 	lockdep_assert_console_list_lock_held();			\
 	hlist_for_each_entry(con, &console_list, node)
 
+#ifdef CONFIG_PRINTK
+extern void nbcon_cpu_emergency_enter(void);
+extern void nbcon_cpu_emergency_exit(void);
+extern bool nbcon_can_proceed(struct nbcon_write_context *wctxt);
+extern void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
+					char *buf, unsigned int len);
+extern bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt);
+extern bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt);
+extern void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt);
+extern bool nbcon_allow_unsafe_takeover(void);
+extern bool nbcon_kdb_try_acquire(struct console *con,
+				  struct nbcon_write_context *wctxt);
+extern void nbcon_kdb_release(struct nbcon_write_context *wctxt);
+
+/*
+ * Check if the given console is currently capable and allowed to print
+ * records. Note that this function does not consider the current context,
+ * which can also play a role in deciding if @con can be used to print
+ * records.
+ */
+static inline bool console_is_usable(struct console *con, short flags, bool use_atomic)
+{
+	if (!(flags & CON_ENABLED))
+		return false;
+
+	if ((flags & CON_SUSPENDED))
+		return false;
+
+	if (flags & CON_NBCON) {
+		if (use_atomic) {
+			/* The write_atomic() callback is optional. */
+			if (!con->write_atomic)
+				return false;
+
+			/*
+			 * An unsafe write_atomic() callback is only usable
+			 * when unsafe takeovers are allowed.
+			 */
+			if ((flags & CON_NBCON_ATOMIC_UNSAFE) && !nbcon_allow_unsafe_takeover())
+				return false;
+		}
+
+		/*
+		 * For the !use_atomic case, @printk_kthreads_running is not
+		 * checked because the write_thread() callback is also used
+		 * via the legacy loop when the printer threads are not
+		 * available.
+		 */
+	} else {
+		if (!con->write)
+			return false;
+	}
+
+	/*
+	 * Console drivers may assume that per-cpu resources have been
+	 * allocated. So unless they're explicitly marked as being able to
+	 * cope (CON_ANYTIME) don't call them until this CPU is officially up.
+	 */
+	if (!cpu_online(raw_smp_processor_id()) && !(flags & CON_ANYTIME))
+		return false;
+
+	return true;
+}
+
+#else
+static inline void nbcon_cpu_emergency_enter(void) { }
+static inline void nbcon_cpu_emergency_exit(void) { }
+static inline bool nbcon_can_proceed(struct nbcon_write_context *wctxt) { return false; }
+static inline void nbcon_write_context_set_buf(struct nbcon_write_context *wctxt,
+					       char *buf, unsigned int len) { }
+static inline bool nbcon_enter_unsafe(struct nbcon_write_context *wctxt) { return false; }
+static inline bool nbcon_exit_unsafe(struct nbcon_write_context *wctxt) { return false; }
+static inline void nbcon_reacquire_nobuf(struct nbcon_write_context *wctxt) { }
+static inline bool nbcon_kdb_try_acquire(struct console *con,
+					 struct nbcon_write_context *wctxt) { return false; }
+static inline void nbcon_kdb_release(struct nbcon_write_context *wctxt) { }
+static inline bool console_is_usable(struct console *con, short flags,
+				     bool use_atomic) { return false; }
+#endif
+
 extern int console_set_on_cmdline;
 extern struct console *early_console;
 
@@ -337,7 +690,7 @@ enum con_flush_mode {
 	CONSOLE_REPLAY_ALL,
 };
 
-extern int add_preferred_console(char *name, int idx, char *options);
+extern int add_preferred_console(const char *name, const short idx, char *options);
 extern void console_force_preferred_locked(struct console *con);
 extern void register_console(struct console *);
 extern int unregister_console(struct console *);
@@ -348,8 +701,8 @@ extern void console_conditional_schedule(void);
 extern void console_unblank(void);
 extern void console_flush_on_panic(enum con_flush_mode mode);
 extern struct tty_driver *console_device(int *);
-extern void console_stop(struct console *);
-extern void console_start(struct console *);
+extern void console_suspend(struct console *);
+extern void console_resume(struct console *);
 extern int is_console_locked(void);
 extern int braille_register_console(struct console *, int index,
 		char *console_options, char *braille_options);
@@ -363,8 +716,8 @@ static inline void console_sysfs_notify(void)
 extern bool console_suspend_enabled;
 
 /* Suspend and resume console messages over PM events */
-extern void suspend_console(void);
-extern void resume_console(void);
+extern void console_suspend_all(void);
+extern void console_resume_all(void);
 
 int mda_console_init(void);
 
@@ -381,11 +734,7 @@ void vcs_remove_sysfs(int index);
  */
 extern atomic_t ignore_console_lock_warning;
 
-/* VESA Blanking Levels */
-#define VESA_NO_BLANKING        0
-#define VESA_VSYNC_SUSPEND      1
-#define VESA_HSYNC_SUSPEND      2
-#define VESA_POWERDOWN          3
+DEFINE_LOCK_GUARD_0(console_lock, console_lock(), console_unlock());
 
 extern void console_init(void);
 
diff --git a/include/linux/console_struct.h b/include/linux/console_struct.h
index 539f1cd45309..13b35637bd5a 100644
--- a/include/linux/console_struct.h
+++ b/include/linux/console_struct.h
@@ -145,13 +145,13 @@ struct vc_data {
 	unsigned int	vc_need_wrap	: 1;
 	unsigned int	vc_can_do_color	: 1;
 	unsigned int	vc_report_mouse : 2;
+	unsigned int	vc_bracketed_paste : 1;
 	unsigned char	vc_utf		: 1;	/* Unicode UTF-8 encoding */
 	unsigned char	vc_utf_count;
 		 int	vc_utf_char;
 	DECLARE_BITMAP(vc_tab_stop, VC_TABSTOPS_COUNT);	/* Tab stops. 256 columns. */
 	unsigned char   vc_palette[16*3];       /* Colour palette for VGA+ */
 	unsigned short * vc_translate;
-	unsigned int    vc_resize_user;         /* resize request from user */
 	unsigned int	vc_bell_pitch;		/* Console bell pitch */
 	unsigned int	vc_bell_duration;	/* Console bell duration */
 	unsigned short	vc_cur_blink_ms;	/* Cursor blink duration */
@@ -159,6 +159,9 @@ struct vc_data {
 	struct uni_pagedict *uni_pagedict;
 	struct uni_pagedict **uni_pagedict_loc; /* [!] Location of uni_pagedict variable for this console */
 	u32 **vc_uni_lines;			/* unicode screen content */
+	u16		*vc_saved_screen;
+	unsigned int	vc_saved_cols;
+	unsigned int	vc_saved_rows;
 	/* additional information is in vt_kern.h */
 };
 
diff --git a/include/linux/consolemap.h b/include/linux/consolemap.h
index c35db4896c37..6180b803795c 100644
--- a/include/linux/consolemap.h
+++ b/include/linux/consolemap.h
@@ -28,6 +28,10 @@ int conv_uni_to_pc(struct vc_data *conp, long ucs);
 u32 conv_8bit_to_uni(unsigned char c);
 int conv_uni_to_8bit(u32 uni);
 void console_map_init(void);
+bool ucs_is_double_width(uint32_t cp);
+bool ucs_is_zero_width(uint32_t cp);
+u32 ucs_recompose(u32 base, u32 mark);
+u32 ucs_get_fallback(u32 cp);
 #else
 static inline u16 inverse_translate(const struct vc_data *conp, u16 glyph,
 		bool use_unicode)
@@ -57,6 +61,26 @@ static inline int conv_uni_to_8bit(u32 uni)
 }
 
 static inline void console_map_init(void) { }
+
+static inline bool ucs_is_double_width(uint32_t cp)
+{
+	return false;
+}
+
+static inline bool ucs_is_zero_width(uint32_t cp)
+{
+	return false;
+}
+
+static inline u32 ucs_recompose(u32 base, u32 mark)
+{
+	return 0;
+}
+
+static inline u32 ucs_get_fallback(u32 cp)
+{
+	return 0;
+}
 #endif /* CONFIG_CONSOLE_TRANSLATIONS */
 
 #endif /* __LINUX_CONSOLEMAP_H__ */
diff --git a/include/linux/const.h b/include/linux/const.h
index 435ddd72d2c4..81b8aae5a855 100644
--- a/include/linux/const.h
+++ b/include/linux/const.h
@@ -3,12 +3,4 @@
 
 #include <vdso/const.h>
 
-/*
- * This returns a constant expression while determining if an argument is
- * a constant expression, most importantly without evaluating the argument.
- * Glory to Martin Uecker <Martin.Uecker@med.uni-goettingen.de>
- */
-#define __is_constexpr(x) \
-	(sizeof(int) == sizeof(*(8 ? ((void *)((long)(x) * 0l)) : (int *)8)))
-
 #endif /* _LINUX_CONST_H */
diff --git a/include/linux/container.h b/include/linux/container.h
index 2566a1baa736..dd00cc918a92 100644
--- a/include/linux/container.h
+++ b/include/linux/container.h
@@ -12,7 +12,7 @@
 #include <linux/device.h>
 
 /* drivers/base/power/container.c */
-extern struct bus_type container_subsys;
+extern const struct bus_type container_subsys;
 
 struct container_dev {
 	struct device dev;
diff --git a/include/linux/container_of.h b/include/linux/container_of.h
index 713890c867be..1f6ebf27d962 100644
--- a/include/linux/container_of.h
+++ b/include/linux/container_of.h
@@ -14,6 +14,7 @@
  * @member:	the name of the member within the struct.
  *
  * WARNING: any const qualifier of @ptr is lost.
+ * Do not use container_of() in new code.
  */
 #define container_of(ptr, type, member) ({				\
 	void *__mptr = (void *)(ptr);					\
@@ -28,6 +29,8 @@
  * @ptr:		the pointer to the member
  * @type:		the type of the container struct this is embedded in.
  * @member:		the name of the member within the struct.
+ *
+ * Always prefer container_of_const() instead of container_of() in new code.
  */
 #define container_of_const(ptr, type, member)				\
 	_Generic(ptr,							\
diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index d3cbb6c16bab..af9fe87a0922 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -26,26 +26,26 @@ extern void user_exit_callable(void);
 static inline void user_enter(void)
 {
 	if (context_tracking_enabled())
-		ct_user_enter(CONTEXT_USER);
+		ct_user_enter(CT_STATE_USER);
 
 }
 static inline void user_exit(void)
 {
 	if (context_tracking_enabled())
-		ct_user_exit(CONTEXT_USER);
+		ct_user_exit(CT_STATE_USER);
 }
 
 /* Called with interrupts disabled.  */
 static __always_inline void user_enter_irqoff(void)
 {
 	if (context_tracking_enabled())
-		__ct_user_enter(CONTEXT_USER);
+		__ct_user_enter(CT_STATE_USER);
 
 }
 static __always_inline void user_exit_irqoff(void)
 {
 	if (context_tracking_enabled())
-		__ct_user_exit(CONTEXT_USER);
+		__ct_user_exit(CT_STATE_USER);
 }
 
 static inline enum ctx_state exception_enter(void)
@@ -57,7 +57,7 @@ static inline enum ctx_state exception_enter(void)
 		return 0;
 
 	prev_ctx = __ct_state();
-	if (prev_ctx != CONTEXT_KERNEL)
+	if (prev_ctx != CT_STATE_KERNEL)
 		ct_user_exit(prev_ctx);
 
 	return prev_ctx;
@@ -67,7 +67,7 @@ static inline void exception_exit(enum ctx_state prev_ctx)
 {
 	if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) &&
 	    context_tracking_enabled()) {
-		if (prev_ctx != CONTEXT_KERNEL)
+		if (prev_ctx != CT_STATE_KERNEL)
 			ct_user_enter(prev_ctx);
 	}
 }
@@ -75,15 +75,17 @@ static inline void exception_exit(enum ctx_state prev_ctx)
 static __always_inline bool context_tracking_guest_enter(void)
 {
 	if (context_tracking_enabled())
-		__ct_user_enter(CONTEXT_GUEST);
+		__ct_user_enter(CT_STATE_GUEST);
 
 	return context_tracking_enabled_this_cpu();
 }
 
-static __always_inline void context_tracking_guest_exit(void)
+static __always_inline bool context_tracking_guest_exit(void)
 {
 	if (context_tracking_enabled())
-		__ct_user_exit(CONTEXT_GUEST);
+		__ct_user_exit(CT_STATE_GUEST);
+
+	return context_tracking_enabled_this_cpu();
 }
 
 #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond))
@@ -98,7 +100,7 @@ static inline void exception_exit(enum ctx_state prev_ctx) { }
 static inline int ct_state(void) { return -1; }
 static inline int __ct_state(void) { return -1; }
 static __always_inline bool context_tracking_guest_enter(void) { return false; }
-static __always_inline void context_tracking_guest_exit(void) { }
+static __always_inline bool context_tracking_guest_exit(void) { return false; }
 #define CT_WARN_ON(cond) do { } while (0)
 #endif /* !CONFIG_CONTEXT_TRACKING_USER */
 
@@ -113,13 +115,17 @@ extern void ct_idle_enter(void);
 extern void ct_idle_exit(void);
 
 /*
- * Is the current CPU in an extended quiescent state?
+ * Is RCU watching the current CPU (IOW, it is not in an extended quiescent state)?
+ *
+ * Note that this returns the actual boolean data (watching / not watching),
+ * whereas ct_rcu_watching() returns the RCU_WATCHING subvariable of
+ * context_tracking.state.
  *
  * No ordering, as we are sampling CPU-local information.
  */
-static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
+static __always_inline bool rcu_is_watching_curr_cpu(void)
 {
-	return !(arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & RCU_DYNTICKS_IDX);
+	return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING;
 }
 
 /*
@@ -128,7 +134,7 @@ static __always_inline bool rcu_dynticks_curr_cpu_in_eqs(void)
  */
 static __always_inline unsigned long ct_state_inc(int incby)
 {
-	return arch_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state));
+	return raw_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state));
 }
 
 static __always_inline bool warn_rcu_enter(void)
@@ -140,9 +146,9 @@ static __always_inline bool warn_rcu_enter(void)
 	 * lots of the actual reporting also relies on RCU.
 	 */
 	preempt_disable_notrace();
-	if (rcu_dynticks_curr_cpu_in_eqs()) {
+	if (!rcu_is_watching_curr_cpu()) {
 		ret = true;
-		ct_state_inc(RCU_DYNTICKS_IDX);
+		ct_state_inc(CT_RCU_WATCHING);
 	}
 
 	return ret;
@@ -151,7 +157,7 @@ static __always_inline bool warn_rcu_enter(void)
 static __always_inline void warn_rcu_exit(bool rcu)
 {
 	if (rcu)
-		ct_state_inc(RCU_DYNTICKS_IDX);
+		ct_state_inc(CT_RCU_WATCHING);
 	preempt_enable_notrace();
 }
 
diff --git a/include/linux/context_tracking_irq.h b/include/linux/context_tracking_irq.h
index c50b5670c4a5..197916ee91a4 100644
--- a/include/linux/context_tracking_irq.h
+++ b/include/linux/context_tracking_irq.h
@@ -10,12 +10,12 @@ void ct_irq_exit_irqson(void);
 void ct_nmi_enter(void);
 void ct_nmi_exit(void);
 #else
-static inline void ct_irq_enter(void) { }
-static inline void ct_irq_exit(void) { }
+static __always_inline void ct_irq_enter(void) { }
+static __always_inline void ct_irq_exit(void) { }
 static inline void ct_irq_enter_irqson(void) { }
 static inline void ct_irq_exit_irqson(void) { }
-static inline void ct_nmi_enter(void) { }
-static inline void ct_nmi_exit(void) { }
+static __always_inline void ct_nmi_enter(void) { }
+static __always_inline void ct_nmi_exit(void) { }
 #endif
 
 #endif
diff --git a/include/linux/context_tracking_state.h b/include/linux/context_tracking_state.h
index fdd537ea513f..0b81248aa03e 100644
--- a/include/linux/context_tracking_state.h
+++ b/include/linux/context_tracking_state.h
@@ -7,23 +7,17 @@
 #include <linux/context_tracking_irq.h>
 
 /* Offset to allow distinguishing irq vs. task-based idle entry/exit. */
-#define DYNTICK_IRQ_NONIDLE	((LONG_MAX / 2) + 1)
+#define CT_NESTING_IRQ_NONIDLE	((LONG_MAX / 2) + 1)
 
 enum ctx_state {
-	CONTEXT_DISABLED	= -1,	/* returned by ct_state() if unknown */
-	CONTEXT_KERNEL		= 0,
-	CONTEXT_IDLE		= 1,
-	CONTEXT_USER		= 2,
-	CONTEXT_GUEST		= 3,
-	CONTEXT_MAX		= 4,
+	CT_STATE_DISABLED	= -1,	/* returned by ct_state() if unknown */
+	CT_STATE_KERNEL		= 0,
+	CT_STATE_IDLE		= 1,
+	CT_STATE_USER		= 2,
+	CT_STATE_GUEST		= 3,
+	CT_STATE_MAX		= 4,
 };
 
-/* Even value for idle, else odd. */
-#define RCU_DYNTICKS_IDX CONTEXT_MAX
-
-#define CT_STATE_MASK (CONTEXT_MAX - 1)
-#define CT_DYNTICKS_MASK (~CT_STATE_MASK)
-
 struct context_tracking {
 #ifdef CONFIG_CONTEXT_TRACKING_USER
 	/*
@@ -39,64 +33,100 @@ struct context_tracking {
 	atomic_t state;
 #endif
 #ifdef CONFIG_CONTEXT_TRACKING_IDLE
-	long dynticks_nesting;		/* Track process nesting level. */
-	long dynticks_nmi_nesting;	/* Track irq/NMI nesting level. */
+	long nesting;		/* Track process nesting level. */
+	long nmi_nesting;	/* Track irq/NMI nesting level. */
 #endif
 };
 
+/*
+ * We cram two different things within the same atomic variable:
+ *
+ *                     CT_RCU_WATCHING_START  CT_STATE_START
+ *                                |                |
+ *                                v                v
+ *     MSB [ RCU watching counter ][ context_state ] LSB
+ *         ^                       ^
+ *         |                       |
+ * CT_RCU_WATCHING_END        CT_STATE_END
+ *
+ * Bits are used from the LSB upwards, so unused bits (if any) will always be in
+ * upper bits of the variable.
+ */
 #ifdef CONFIG_CONTEXT_TRACKING
+#define CT_SIZE (sizeof(((struct context_tracking *)0)->state) * BITS_PER_BYTE)
+
+#define CT_STATE_WIDTH bits_per(CT_STATE_MAX - 1)
+#define CT_STATE_START 0
+#define CT_STATE_END   (CT_STATE_START + CT_STATE_WIDTH - 1)
+
+#define CT_RCU_WATCHING_MAX_WIDTH (CT_SIZE - CT_STATE_WIDTH)
+#define CT_RCU_WATCHING_WIDTH     (IS_ENABLED(CONFIG_RCU_DYNTICKS_TORTURE) ? 2 : CT_RCU_WATCHING_MAX_WIDTH)
+#define CT_RCU_WATCHING_START     (CT_STATE_END + 1)
+#define CT_RCU_WATCHING_END       (CT_RCU_WATCHING_START + CT_RCU_WATCHING_WIDTH - 1)
+#define CT_RCU_WATCHING           BIT(CT_RCU_WATCHING_START)
+
+#define CT_STATE_MASK        GENMASK(CT_STATE_END,        CT_STATE_START)
+#define CT_RCU_WATCHING_MASK GENMASK(CT_RCU_WATCHING_END, CT_RCU_WATCHING_START)
+
+#define CT_UNUSED_WIDTH (CT_RCU_WATCHING_MAX_WIDTH - CT_RCU_WATCHING_WIDTH)
+
+static_assert(CT_STATE_WIDTH        +
+	      CT_RCU_WATCHING_WIDTH +
+	      CT_UNUSED_WIDTH       ==
+	      CT_SIZE);
+
 DECLARE_PER_CPU(struct context_tracking, context_tracking);
-#endif
+#endif	/* CONFIG_CONTEXT_TRACKING */
 
 #ifdef CONFIG_CONTEXT_TRACKING_USER
 static __always_inline int __ct_state(void)
 {
-	return arch_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK;
+	return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_STATE_MASK;
 }
 #endif
 
 #ifdef CONFIG_CONTEXT_TRACKING_IDLE
-static __always_inline int ct_dynticks(void)
+static __always_inline int ct_rcu_watching(void)
 {
-	return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_DYNTICKS_MASK;
+	return atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING_MASK;
 }
 
-static __always_inline int ct_dynticks_cpu(int cpu)
+static __always_inline int ct_rcu_watching_cpu(int cpu)
 {
 	struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
 
-	return atomic_read(&ct->state) & CT_DYNTICKS_MASK;
+	return atomic_read(&ct->state) & CT_RCU_WATCHING_MASK;
 }
 
-static __always_inline int ct_dynticks_cpu_acquire(int cpu)
+static __always_inline int ct_rcu_watching_cpu_acquire(int cpu)
 {
 	struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
 
-	return atomic_read_acquire(&ct->state) & CT_DYNTICKS_MASK;
+	return atomic_read_acquire(&ct->state) & CT_RCU_WATCHING_MASK;
 }
 
-static __always_inline long ct_dynticks_nesting(void)
+static __always_inline long ct_nesting(void)
 {
-	return __this_cpu_read(context_tracking.dynticks_nesting);
+	return __this_cpu_read(context_tracking.nesting);
 }
 
-static __always_inline long ct_dynticks_nesting_cpu(int cpu)
+static __always_inline long ct_nesting_cpu(int cpu)
 {
 	struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
 
-	return ct->dynticks_nesting;
+	return ct->nesting;
 }
 
-static __always_inline long ct_dynticks_nmi_nesting(void)
+static __always_inline long ct_nmi_nesting(void)
 {
-	return __this_cpu_read(context_tracking.dynticks_nmi_nesting);
+	return __this_cpu_read(context_tracking.nmi_nesting);
 }
 
-static __always_inline long ct_dynticks_nmi_nesting_cpu(int cpu)
+static __always_inline long ct_nmi_nesting_cpu(int cpu)
 {
 	struct context_tracking *ct = per_cpu_ptr(&context_tracking, cpu);
 
-	return ct->dynticks_nmi_nesting;
+	return ct->nmi_nesting;
 }
 #endif /* #ifdef CONFIG_CONTEXT_TRACKING_IDLE */
 
@@ -113,7 +143,7 @@ static __always_inline bool context_tracking_enabled_cpu(int cpu)
 	return context_tracking_enabled() && per_cpu(context_tracking.active, cpu);
 }
 
-static inline bool context_tracking_enabled_this_cpu(void)
+static __always_inline bool context_tracking_enabled_this_cpu(void)
 {
 	return context_tracking_enabled() && __this_cpu_read(context_tracking.active);
 }
@@ -123,14 +153,14 @@ static inline bool context_tracking_enabled_this_cpu(void)
  *
  * Returns the current cpu's context tracking state if context tracking
  * is enabled.  If context tracking is disabled, returns
- * CONTEXT_DISABLED.  This should be used primarily for debugging.
+ * CT_STATE_DISABLED.  This should be used primarily for debugging.
  */
 static __always_inline int ct_state(void)
 {
 	int ret;
 
 	if (!context_tracking_enabled())
-		return CONTEXT_DISABLED;
+		return CT_STATE_DISABLED;
 
 	preempt_disable();
 	ret = __ct_state();
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index d3eba4360150..68861da4cf7c 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -10,7 +10,7 @@
 #ifdef CONFIG_COREDUMP
 struct core_vma_metadata {
 	unsigned long start, end;
-	unsigned long flags;
+	vm_flags_t flags;
 	unsigned long dump_size;
 	unsigned long pgoff;
 	struct file   *file;
@@ -28,8 +28,11 @@ struct coredump_params {
 	int vma_count;
 	size_t vma_data_size;
 	struct core_vma_metadata *vma_meta;
+	struct pid *pid;
 };
 
+extern unsigned int core_file_note_size_limit;
+
 /*
  * These are the only things you should do on a core-file: use only these
  * functions to write out all the necessary info.
@@ -40,9 +43,31 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len);
-extern void do_coredump(const kernel_siginfo_t *siginfo);
+extern void vfs_coredump(const kernel_siginfo_t *siginfo);
+
+/*
+ * Logging for the coredump code, ratelimited.
+ * The TGID and comm fields are added to the message.
+ */
+
+#define __COREDUMP_PRINTK(Level, Format, ...) \
+	do {	\
+		char comm[TASK_COMM_LEN];	\
+		/* This will always be NUL terminated. */ \
+		memcpy(comm, current->comm, sizeof(comm)); \
+		printk_ratelimited(Level "coredump: %d(%*pE): " Format "\n",	\
+			task_tgid_vnr(current), (int)strlen(comm), comm, ##__VA_ARGS__);	\
+	} while (0)	\
+
+#define coredump_report(fmt, ...) __COREDUMP_PRINTK(KERN_INFO, fmt, ##__VA_ARGS__)
+#define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__)
+
 #else
-static inline void do_coredump(const kernel_siginfo_t *siginfo) {}
+static inline void vfs_coredump(const kernel_siginfo_t *siginfo) {}
+
+#define coredump_report(...)
+#define coredump_report_failure(...)
+
 #endif
 
 #if defined(CONFIG_COREDUMP) && defined(CONFIG_SYSCTL)
diff --git a/include/linux/coresight-pmu.h b/include/linux/coresight-pmu.h
index 51ac441a37c3..89b0ac0014b0 100644
--- a/include/linux/coresight-pmu.h
+++ b/include/linux/coresight-pmu.h
@@ -49,12 +49,21 @@
  * Interpretation of the PERF_RECORD_AUX_OUTPUT_HW_ID payload.
  * Used to associate a CPU with the CoreSight Trace ID.
  * [07:00] - Trace ID - uses 8 bits to make value easy to read in file.
- * [59:08] - Unused (SBZ)
- * [63:60] - Version
+ * [39:08] - Sink ID - as reported in /sys/bus/event_source/devices/cs_etm/sinks/
+ *	      Added in minor version 1.
+ * [55:40] - Unused (SBZ)
+ * [59:56] - Minor Version - previously existing fields are compatible with
+ *	      all minor versions.
+ * [63:60] - Major Version - previously existing fields mean different things
+ *	      in new major versions.
  */
 #define CS_AUX_HW_ID_TRACE_ID_MASK	GENMASK_ULL(7, 0)
-#define CS_AUX_HW_ID_VERSION_MASK	GENMASK_ULL(63, 60)
+#define CS_AUX_HW_ID_SINK_ID_MASK	GENMASK_ULL(39, 8)
 
-#define CS_AUX_HW_ID_CURR_VERSION 0
+#define CS_AUX_HW_ID_MINOR_VERSION_MASK	GENMASK_ULL(59, 56)
+#define CS_AUX_HW_ID_MAJOR_VERSION_MASK	GENMASK_ULL(63, 60)
+
+#define CS_AUX_HW_ID_MAJOR_VERSION 0
+#define CS_AUX_HW_ID_MINOR_VERSION 1
 
 #endif
diff --git a/include/linux/coresight.h b/include/linux/coresight.h
index f19a47b9bb5a..2b48be97fcd0 100644
--- a/include/linux/coresight.h
+++ b/include/linux/coresight.h
@@ -6,10 +6,13 @@
 #ifndef _LINUX_CORESIGHT_H
 #define _LINUX_CORESIGHT_H
 
+#include <linux/amba/bus.h>
+#include <linux/clk.h>
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/perf_event.h>
 #include <linux/sched.h>
+#include <linux/platform_device.h>
 
 /* Peripheral id registers (0xFD0-0xFEC) */
 #define CORESIGHT_PERIPHIDR4	0xfd0
@@ -33,7 +36,7 @@
 
 #define CORESIGHT_UNLOCK	0xc5acce55
 
-extern struct bus_type coresight_bustype;
+extern const struct bus_type coresight_bustype;
 
 enum coresight_dev_type {
 	CORESIGHT_DEV_TYPE_SINK,
@@ -41,10 +44,11 @@ enum coresight_dev_type {
 	CORESIGHT_DEV_TYPE_LINKSINK,
 	CORESIGHT_DEV_TYPE_SOURCE,
 	CORESIGHT_DEV_TYPE_HELPER,
-	CORESIGHT_DEV_TYPE_ECT,
+	CORESIGHT_DEV_TYPE_MAX
 };
 
 enum coresight_dev_subtype_sink {
+	CORESIGHT_DEV_SUBTYPE_SINK_DUMMY,
 	CORESIGHT_DEV_SUBTYPE_SINK_PORT,
 	CORESIGHT_DEV_SUBTYPE_SINK_BUFFER,
 	CORESIGHT_DEV_SUBTYPE_SINK_SYSMEM,
@@ -61,17 +65,14 @@ enum coresight_dev_subtype_source {
 	CORESIGHT_DEV_SUBTYPE_SOURCE_PROC,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_BUS,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_SOFTWARE,
+	CORESIGHT_DEV_SUBTYPE_SOURCE_TPDM,
 	CORESIGHT_DEV_SUBTYPE_SOURCE_OTHERS,
 };
 
 enum coresight_dev_subtype_helper {
 	CORESIGHT_DEV_SUBTYPE_HELPER_CATU,
-};
-
-/* Embedded Cross Trigger (ECT) sub-types */
-enum coresight_dev_subtype_ect {
-	CORESIGHT_DEV_SUBTYPE_ECT_NONE,
-	CORESIGHT_DEV_SUBTYPE_ECT_CTI,
+	CORESIGHT_DEV_SUBTYPE_HELPER_ECT_CTI,
+	CORESIGHT_DEV_SUBTYPE_HELPER_CTCU,
 };
 
 /**
@@ -84,8 +85,6 @@ enum coresight_dev_subtype_ect {
  *			by @coresight_dev_subtype_source.
  * @helper_subtype:	type of helper this component is, as defined
  *			by @coresight_dev_subtype_helper.
- * @ect_subtype:        type of cross trigger this component is, as
- *			defined by @coresight_dev_subtype_ect
  */
 union coresight_dev_subtype {
 	/* We have some devices which acts as LINK and SINK */
@@ -95,21 +94,25 @@ union coresight_dev_subtype {
 	};
 	enum coresight_dev_subtype_source source_subtype;
 	enum coresight_dev_subtype_helper helper_subtype;
-	enum coresight_dev_subtype_ect ect_subtype;
 };
 
 /**
  * struct coresight_platform_data - data harvested from the firmware
  * specification.
  *
- * @nr_inport:	Number of elements for the input connections.
- * @nr_outport:	Number of elements for the output connections.
- * @conns:	Sparse array of nr_outport connections from this component.
+ * @nr_inconns: Number of elements for the input connections.
+ * @nr_outconns: Number of elements for the output connections.
+ * @out_conns: Array of nr_outconns pointers to connections from this
+ *	       component.
+ * @in_conns: Sparse array of pointers to input connections. Sparse
+ *            because the source device owns the connection so when it's
+ *            unloaded the connection leaves an empty slot.
  */
 struct coresight_platform_data {
-	int nr_inport;
-	int nr_outport;
-	struct coresight_connection *conns;
+	int nr_inconns;
+	int nr_outconns;
+	struct coresight_connection **out_conns;
+	struct coresight_connection **in_conns;
 };
 
 /**
@@ -164,19 +167,47 @@ struct coresight_desc {
 
 /**
  * struct coresight_connection - representation of a single connection
- * @outport:	a connection's output port number.
- * @child_port:	remote component's port number @output is connected to.
- * @chid_fwnode: remote component's fwnode handle.
- * @child_dev:	a @coresight_device representation of the component
-		connected to @outport.
+ * @src_port:	a connection's output port number.
+ * @dest_port:	destination's input port number @src_port is connected to.
+ * @dest_fwnode: destination component's fwnode handle.
+ * @dest_dev:	a @coresight_device representation of the component
+		connected to @src_port. NULL until the device is created
  * @link: Representation of the connection as a sysfs link.
+ * @filter_src_fwnode: filter source component's fwnode handle.
+ * @filter_src_dev: a @coresight_device representation of the component that
+		needs to be filtered.
+ *
+ * The full connection structure looks like this, where in_conns store
+ * references to same connection as the source device's out_conns.
+ *
+ * +-----------------------------+   +-----------------------------+
+ * |coresight_device             |   |coresight_connection         |
+ * |-----------------------------|   |-----------------------------|
+ * |                             |   |                             |
+ * |                             |   |                    dest_dev*|<--
+ * |pdata->out_conns[nr_outconns]|<->|src_dev*                     |   |
+ * |                             |   |                             |   |
+ * +-----------------------------+   +-----------------------------+   |
+ *                                                                     |
+ *                                   +-----------------------------+   |
+ *                                   |coresight_device             |   |
+ *                                   |------------------------------   |
+ *                                   |                             |   |
+ *                                   |  pdata->in_conns[nr_inconns]|<--
+ *                                   |                             |
+ *                                   +-----------------------------+
  */
 struct coresight_connection {
-	int outport;
-	int child_port;
-	struct fwnode_handle *child_fwnode;
-	struct coresight_device *child_dev;
+	int src_port;
+	int dest_port;
+	struct fwnode_handle *dest_fwnode;
+	struct coresight_device *dest_dev;
 	struct coresight_sysfs_link *link;
+	struct coresight_device *src_dev;
+	struct fwnode_handle *filter_src_fwnode;
+	struct coresight_device *filter_src_dev;
+	int src_refcnt;
+	int dest_refcnt;
 };
 
 /**
@@ -193,6 +224,24 @@ struct coresight_sysfs_link {
 	const char *target_name;
 };
 
+/* architecturally we have 128 IDs some of which are reserved */
+#define CORESIGHT_TRACE_IDS_MAX 128
+
+/**
+ * Trace ID map.
+ *
+ * @used_ids:	Bitmap to register available (bit = 0) and in use (bit = 1) IDs.
+ *		Initialised so that the reserved IDs are permanently marked as
+ *		in use.
+ * @perf_cs_etm_session_active: Number of Perf sessions using this ID map.
+ */
+struct coresight_trace_id_map {
+	DECLARE_BITMAP(used_ids, CORESIGHT_TRACE_IDS_MAX);
+	atomic_t __percpu *cpu_map;
+	atomic_t perf_cs_etm_session_active;
+	raw_spinlock_t lock;
+};
+
 /**
  * struct coresight_device - representation of a device as used by the framework
  * @pdata:	Platform data with device connections associated to this device.
@@ -202,17 +251,24 @@ struct coresight_sysfs_link {
  *		by @coresight_ops.
  * @access:	Device i/o access abstraction for this device.
  * @dev:	The device entity associated to this component.
- * @refcnt:	keep track of what is in use.
+ * @mode:	The device mode, i.e sysFS, Perf or disabled. This is actually
+ *		an 'enum cs_mode' but stored in an atomic type. Access is always
+ *		through atomic APIs, ensuring SMP-safe synchronisation between
+ *		racing from sysFS and Perf mode. A compare-and-exchange
+ *		operation is done to atomically claim one mode or the other.
+ * @refcnt:	keep track of what is in use. Only access this outside of the
+ *		device's spinlock when the coresight_mutex held and mode ==
+ *		CS_MODE_SYSFS. Otherwise it must be accessed from inside the
+ *		spinlock.
  * @orphan:	true if the component has connections that haven't been linked.
- * @enable:	'true' if component is currently part of an active path.
- * @activated:	'true' only if a _sink_ has been activated.  A sink can be
- *		activated but not yet enabled.  Enabling for a _sink_
- *		happens when a source has been selected and a path is enabled
- *		from source to that sink.
+ * @sysfs_sink_activated: 'true' when a sink has been selected for use via sysfs
+ *		by writing a 1 to the 'enable_sink' file.  A sink can be
+ *		activated but not yet enabled.  Enabling for a _sink_ happens
+ *		when a source has been selected and a path is enabled from
+ *		source to that sink. A sink can also become enabled but not
+ *		activated if it's used via Perf.
  * @ea:		Device attribute for sink representation under PMU directory.
  * @def_sink:	cached reference to default sink found for this device.
- * @ect_dev:	Associated cross trigger device. Not part of the trace data
- *		path or connections.
  * @nr_links:   number of sysfs links created to other components from this
  *		device. These will appear in the "connections" group.
  * @has_conns_grp: Have added a "connections" group for sysfs links.
@@ -228,23 +284,21 @@ struct coresight_device {
 	const struct coresight_ops *ops;
 	struct csdev_access access;
 	struct device dev;
-	atomic_t *refcnt;
+	atomic_t mode;
+	int refcnt;
 	bool orphan;
-	bool enable;	/* true only if configured as part of a path */
 	/* sink specific fields */
-	bool activated;	/* true only if a sink is part of a path */
+	bool sysfs_sink_activated;
 	struct dev_ext_attribute *ea;
 	struct coresight_device *def_sink;
-	/* cross trigger handling */
-	struct coresight_device *ect_dev;
+	struct coresight_trace_id_map perf_sink_id_map;
 	/* sysfs links between components */
 	int nr_links;
 	bool has_conns_grp;
-	bool ect_enabled; /* true only if associated ect device is enabled */
 	/* system configuration and feature lists */
 	struct list_head feature_csdev_list;
 	struct list_head config_csdev_list;
-	spinlock_t cscfg_csdev_lock;
+	raw_spinlock_t cscfg_csdev_lock;
 	void *active_cscfg_ctxt;
 };
 
@@ -272,11 +326,31 @@ static struct coresight_dev_list (var) = {				\
 
 #define to_coresight_device(d) container_of(d, struct coresight_device, dev)
 
+/**
+ * struct coresight_path - data needed by enable/disable path
+ * @path_list:		path from source to sink.
+ * @trace_id:		trace_id of the whole path.
+ * @handle:		handle of the aux_event.
+ */
+struct coresight_path {
+	struct list_head		path_list;
+	u8				trace_id;
+	struct perf_output_handle	*handle;
+};
+
+enum cs_mode {
+	CS_MODE_DISABLED,
+	CS_MODE_SYSFS,
+	CS_MODE_PERF,
+};
+
+#define coresight_ops(csdev)	csdev->ops
 #define source_ops(csdev)	csdev->ops->source_ops
 #define sink_ops(csdev)		csdev->ops->sink_ops
 #define link_ops(csdev)		csdev->ops->link_ops
 #define helper_ops(csdev)	csdev->ops->helper_ops
 #define ect_ops(csdev)		csdev->ops->ect_ops
+#define panic_ops(csdev)	csdev->ops->panic_ops
 
 /**
  * struct coresight_ops_sink - basic operations for a sink
@@ -288,7 +362,8 @@ static struct coresight_dev_list (var) = {				\
  * @update_buffer:	update buffer pointers after a trace session.
  */
 struct coresight_ops_sink {
-	int (*enable)(struct coresight_device *csdev, u32 mode, void *data);
+	int (*enable)(struct coresight_device *csdev, enum cs_mode mode,
+		      struct coresight_path *path);
 	int (*disable)(struct coresight_device *csdev);
 	void *(*alloc_buffer)(struct coresight_device *csdev,
 			      struct perf_event *event, void **pages,
@@ -306,8 +381,12 @@ struct coresight_ops_sink {
  * @disable:	disables flow between iport and oport.
  */
 struct coresight_ops_link {
-	int (*enable)(struct coresight_device *csdev, int iport, int oport);
-	void (*disable)(struct coresight_device *csdev, int iport, int oport);
+	int (*enable)(struct coresight_device *csdev,
+		      struct coresight_connection *in,
+		      struct coresight_connection *out);
+	void (*disable)(struct coresight_device *csdev,
+			struct coresight_connection *in,
+			struct coresight_connection *out);
 };
 
 /**
@@ -317,13 +396,17 @@ struct coresight_ops_link {
  *		is associated to.
  * @enable:	enables tracing for a source.
  * @disable:	disables tracing for a source.
+ * @resume_perf: resumes tracing for a source in perf session.
+ * @pause_perf:	pauses tracing for a source in perf session.
  */
 struct coresight_ops_source {
 	int (*cpu_id)(struct coresight_device *csdev);
-	int (*enable)(struct coresight_device *csdev,
-		      struct perf_event *event,  u32 mode);
+	int (*enable)(struct coresight_device *csdev, struct perf_event *event,
+		      enum cs_mode mode, struct coresight_path *path);
 	void (*disable)(struct coresight_device *csdev,
 			struct perf_event *event);
+	int (*resume_perf)(struct coresight_device *csdev);
+	void (*pause_perf)(struct coresight_device *csdev);
 };
 
 /**
@@ -336,31 +419,32 @@ struct coresight_ops_source {
  * @disable	: Disable the device
  */
 struct coresight_ops_helper {
-	int (*enable)(struct coresight_device *csdev, void *data);
-	int (*disable)(struct coresight_device *csdev, void *data);
+	int (*enable)(struct coresight_device *csdev, enum cs_mode mode,
+		      struct coresight_path *path);
+	int (*disable)(struct coresight_device *csdev,
+		       struct coresight_path *path);
 };
 
+
 /**
- * struct coresight_ops_ect - Ops for an embedded cross trigger device
+ * struct coresight_ops_panic - Generic device ops for panic handing
  *
- * @enable	: Enable the device
- * @disable	: Disable the device
+ * @sync	: Sync the device register state/trace data
  */
-struct coresight_ops_ect {
-	int (*enable)(struct coresight_device *csdev);
-	int (*disable)(struct coresight_device *csdev);
+struct coresight_ops_panic {
+	int (*sync)(struct coresight_device *csdev);
 };
 
 struct coresight_ops {
+	int (*trace_id)(struct coresight_device *csdev, enum cs_mode mode,
+			struct coresight_device *sink);
 	const struct coresight_ops_sink *sink_ops;
 	const struct coresight_ops_link *link_ops;
 	const struct coresight_ops_source *source_ops;
 	const struct coresight_ops_helper *helper_ops;
-	const struct coresight_ops_ect *ect_ops;
+	const struct coresight_ops_panic *panic_ops;
 };
 
-#if IS_ENABLED(CONFIG_CORESIGHT)
-
 static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa,
 					      u32 offset)
 {
@@ -370,6 +454,37 @@ static inline u32 csdev_access_relaxed_read32(struct csdev_access *csa,
 	return csa->read(offset, true, false);
 }
 
+#define CORESIGHT_CIDRn(i)	(0xFF0 + ((i) * 4))
+
+static inline u32 coresight_get_cid(void __iomem *base)
+{
+	u32 i, cid = 0;
+
+	for (i = 0; i < 4; i++)
+		cid |= readl(base + CORESIGHT_CIDRn(i)) << (i * 8);
+
+	return cid;
+}
+
+static inline bool is_coresight_device(void __iomem *base)
+{
+	u32 cid = coresight_get_cid(base);
+
+	return cid == CORESIGHT_CID;
+}
+
+#define CORESIGHT_PIDRn(i)	(0xFE0 + ((i) * 4))
+
+static inline u32 coresight_get_pid(struct csdev_access *csa)
+{
+	u32 i, pid = 0;
+
+	for (i = 0; i < 4; i++)
+		pid |= csdev_access_relaxed_read32(csa, CORESIGHT_PIDRn(i)) << (i * 8);
+
+	return pid;
+}
+
 static inline u64 csdev_access_relaxed_read_pair(struct csdev_access *csa,
 						 u32 lo_offset, u32 hi_offset)
 {
@@ -481,9 +596,14 @@ static inline void csdev_access_write64(struct csdev_access *csa, u64 val, u32 o
 }
 #endif	/* CONFIG_64BIT */
 
+static inline bool coresight_is_device_source(struct coresight_device *csdev)
+{
+	return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE);
+}
+
 static inline bool coresight_is_percpu_source(struct coresight_device *csdev)
 {
-	return csdev && (csdev->type == CORESIGHT_DEV_TYPE_SOURCE) &&
+	return csdev && coresight_is_device_source(csdev) &&
 	       (csdev->subtype.source_subtype == CORESIGHT_DEV_SUBTYPE_SOURCE_PROC);
 }
 
@@ -493,23 +613,60 @@ static inline bool coresight_is_percpu_sink(struct coresight_device *csdev)
 	       (csdev->subtype.sink_subtype == CORESIGHT_DEV_SUBTYPE_SINK_PERCPU_SYSMEM);
 }
 
-extern struct coresight_device *
-coresight_register(struct coresight_desc *desc);
-extern void coresight_unregister(struct coresight_device *csdev);
-extern int coresight_enable(struct coresight_device *csdev);
-extern void coresight_disable(struct coresight_device *csdev);
-extern int coresight_timeout(struct csdev_access *csa, u32 offset,
-			     int position, int value);
+/*
+ * Atomically try to take the device and set a new mode. Returns true on
+ * success, false if the device is already taken by someone else.
+ */
+static inline bool coresight_take_mode(struct coresight_device *csdev,
+				       enum cs_mode new_mode)
+{
+	int curr = CS_MODE_DISABLED;
+
+	return atomic_try_cmpxchg_acquire(&csdev->mode, &curr, new_mode);
+}
 
-extern int coresight_claim_device(struct coresight_device *csdev);
-extern int coresight_claim_device_unlocked(struct coresight_device *csdev);
+static inline enum cs_mode coresight_get_mode(struct coresight_device *csdev)
+{
+	return atomic_read_acquire(&csdev->mode);
+}
 
-extern void coresight_disclaim_device(struct coresight_device *csdev);
-extern void coresight_disclaim_device_unlocked(struct coresight_device *csdev);
-extern char *coresight_alloc_device_name(struct coresight_dev_list *devs,
+static inline void coresight_set_mode(struct coresight_device *csdev,
+				      enum cs_mode new_mode)
+{
+	enum cs_mode current_mode = coresight_get_mode(csdev);
+
+	/*
+	 * Changing to a new mode must be done from an already disabled state
+	 * unless it's synchronized with coresight_take_mode(). Otherwise the
+	 * device is already in use and signifies a locking issue.
+	 */
+	WARN(new_mode != CS_MODE_DISABLED && current_mode != CS_MODE_DISABLED &&
+	     current_mode != new_mode, "Device already in use\n");
+
+	atomic_set_release(&csdev->mode, new_mode);
+}
+
+struct coresight_device *coresight_register(struct coresight_desc *desc);
+void coresight_unregister(struct coresight_device *csdev);
+int coresight_enable_sysfs(struct coresight_device *csdev);
+void coresight_disable_sysfs(struct coresight_device *csdev);
+int coresight_timeout(struct csdev_access *csa, u32 offset, int position, int value);
+typedef void (*coresight_timeout_cb_t) (struct csdev_access *, u32, int, int);
+int coresight_timeout_action(struct csdev_access *csa, u32 offset, int position, int value,
+			     coresight_timeout_cb_t cb);
+int coresight_claim_device(struct coresight_device *csdev);
+int coresight_claim_device_unlocked(struct coresight_device *csdev);
+
+int coresight_claim_device(struct coresight_device *csdev);
+int coresight_claim_device_unlocked(struct coresight_device *csdev);
+void coresight_clear_self_claim_tag(struct csdev_access *csa);
+void coresight_clear_self_claim_tag_unlocked(struct csdev_access *csa);
+void coresight_disclaim_device(struct coresight_device *csdev);
+void coresight_disclaim_device_unlocked(struct coresight_device *csdev);
+char *coresight_alloc_device_name(struct coresight_dev_list *devs,
 					 struct device *dev);
 
-extern bool coresight_loses_context_with_cpu(struct device *dev);
+bool coresight_loses_context_with_cpu(struct device *dev);
 
 u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset);
 u32 coresight_read32(struct coresight_device *csdev, u32 offset);
@@ -522,85 +679,31 @@ void coresight_relaxed_write64(struct coresight_device *csdev,
 			       u64 val, u32 offset);
 void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset);
 
-#else
-static inline struct coresight_device *
-coresight_register(struct coresight_desc *desc) { return NULL; }
-static inline void coresight_unregister(struct coresight_device *csdev) {}
-static inline int
-coresight_enable(struct coresight_device *csdev) { return -ENOSYS; }
-static inline void coresight_disable(struct coresight_device *csdev) {}
-
-static inline int coresight_timeout(struct csdev_access *csa, u32 offset,
-				    int position, int value)
-{
-	return 1;
-}
-
-static inline int coresight_claim_device_unlocked(struct coresight_device *csdev)
-{
-	return -EINVAL;
-}
-
-static inline int coresight_claim_device(struct coresight_device *csdev)
-{
-	return -EINVAL;
-}
-
-static inline void coresight_disclaim_device(struct coresight_device *csdev) {}
-static inline void coresight_disclaim_device_unlocked(struct coresight_device *csdev) {}
-
-static inline bool coresight_loses_context_with_cpu(struct device *dev)
-{
-	return false;
-}
-
-static inline u32 coresight_relaxed_read32(struct coresight_device *csdev, u32 offset)
-{
-	WARN_ON_ONCE(1);
-	return 0;
-}
-
-static inline u32 coresight_read32(struct coresight_device *csdev, u32 offset)
-{
-	WARN_ON_ONCE(1);
-	return 0;
-}
-
-static inline void coresight_write32(struct coresight_device *csdev, u32 val, u32 offset)
-{
-}
-
-static inline void coresight_relaxed_write32(struct coresight_device *csdev,
-					     u32 val, u32 offset)
-{
-}
-
-static inline u64 coresight_relaxed_read64(struct coresight_device *csdev,
-					   u32 offset)
-{
-	WARN_ON_ONCE(1);
-	return 0;
-}
-
-static inline u64 coresight_read64(struct coresight_device *csdev, u32 offset)
-{
-	WARN_ON_ONCE(1);
-	return 0;
-}
-
-static inline void coresight_relaxed_write64(struct coresight_device *csdev,
-					     u64 val, u32 offset)
-{
-}
-
-static inline void coresight_write64(struct coresight_device *csdev, u64 val, u32 offset)
-{
-}
-
-#endif		/* IS_ENABLED(CONFIG_CORESIGHT) */
-
-extern int coresight_get_cpu(struct device *dev);
+int coresight_get_cpu(struct device *dev);
+int coresight_get_static_trace_id(struct device *dev, u32 *id);
 
 struct coresight_platform_data *coresight_get_platform_data(struct device *dev);
-
+struct coresight_connection *
+coresight_add_out_conn(struct device *dev,
+		       struct coresight_platform_data *pdata,
+		       const struct coresight_connection *new_conn);
+int coresight_add_in_conn(struct coresight_connection *conn);
+struct coresight_device *
+coresight_find_input_type(struct coresight_platform_data *pdata,
+			  enum coresight_dev_type type,
+			  union coresight_dev_subtype subtype);
+struct coresight_device *
+coresight_find_output_type(struct coresight_platform_data *pdata,
+			   enum coresight_dev_type type,
+			   union coresight_dev_subtype subtype);
+
+int coresight_init_driver(const char *drv, struct amba_driver *amba_drv,
+			  struct platform_driver *pdev_drv, struct module *owner);
+
+void coresight_remove_driver(struct amba_driver *amba_drv,
+			     struct platform_driver *pdev_drv);
+int coresight_etm_get_trace_id(struct coresight_device *csdev, enum cs_mode mode,
+			       struct coresight_device *sink);
+int coresight_get_enable_clocks(struct device *dev, struct clk **pclk,
+				struct clk **atclk);
 #endif		/* _LINUX_COREISGHT_H */
diff --git a/include/linux/counter.h b/include/linux/counter.h
index b63746637de2..f208e867dd0f 100644
--- a/include/linux/counter.h
+++ b/include/linux/counter.h
@@ -6,14 +6,15 @@
 #ifndef _COUNTER_H_
 #define _COUNTER_H_
 
+#include <linux/array_size.h>
 #include <linux/cdev.h>
 #include <linux/device.h>
-#include <linux/kernel.h>
 #include <linux/kfifo.h>
 #include <linux/mutex.h>
 #include <linux/spinlock_types.h>
 #include <linux/types.h>
 #include <linux/wait.h>
+
 #include <uapi/linux/counter.h>
 
 struct counter_device;
@@ -359,7 +360,6 @@ struct counter_ops {
  * @num_counts:		number of Counts specified in @counts
  * @ext:		optional array of Counter device extensions
  * @num_ext:		number of Counter device extensions specified in @ext
- * @priv:		optional private data supplied by driver
  * @dev:		internal device structure
  * @chrdev:		internal character device structure
  * @events_list:	list of current watching Counter events
@@ -399,7 +399,7 @@ struct counter_device {
 	struct mutex ops_exist_lock;
 };
 
-void *counter_priv(const struct counter_device *const counter);
+void *counter_priv(const struct counter_device *const counter) __attribute_const__;
 
 struct counter_device *counter_alloc(size_t sizeof_priv);
 void counter_put(struct counter_device *const counter);
@@ -580,6 +580,9 @@ struct counter_array {
 #define COUNTER_COMP_CEILING(_read, _write) \
 	COUNTER_COMP_COUNT_U64("ceiling", _read, _write)
 
+#define COUNTER_COMP_COMPARE(_read, _write) \
+	COUNTER_COMP_COUNT_U64("compare", _read, _write)
+
 #define COUNTER_COMP_COUNT_MODE(_read, _write, _available) \
 { \
 	.type = COUNTER_COMP_COUNT_MODE, \
@@ -602,6 +605,9 @@ struct counter_array {
 #define COUNTER_COMP_FLOOR(_read, _write) \
 	COUNTER_COMP_COUNT_U64("floor", _read, _write)
 
+#define COUNTER_COMP_FREQUENCY(_read) \
+	COUNTER_COMP_SIGNAL_U64("frequency", _read, NULL)
+
 #define COUNTER_COMP_POLARITY(_read, _write, _available) \
 { \
 	.type = COUNTER_COMP_SIGNAL_POLARITY, \
diff --git a/include/linux/cper.h b/include/linux/cper.h
index eacb7dd7b3af..5b1236d8c65b 100644
--- a/include/linux/cper.h
+++ b/include/linux/cper.h
@@ -89,6 +89,33 @@ enum {
 #define CPER_NOTIFY_DMAR						\
 	GUID_INIT(0x667DD791, 0xC6B3, 0x4c27, 0x8A, 0x6B, 0x0F, 0x8E,	\
 		  0x72, 0x2D, 0xEB, 0x41)
+/* CXL Protocol Error Section */
+#define CPER_SEC_CXL_PROT_ERR						\
+	GUID_INIT(0x80B9EFB4, 0x52B5, 0x4DE3, 0xA7, 0x77, 0x68, 0x78,	\
+		  0x4B, 0x77, 0x10, 0x48)
+
+/* CXL Event record UUIDs are formatted as GUIDs and reported in section type */
+/*
+ * General Media Event Record
+ * CXL rev 3.0 Section 8.2.9.2.1.1; Table 8-43
+ */
+#define CPER_SEC_CXL_GEN_MEDIA_GUID					\
+	GUID_INIT(0xfbcd0a77, 0xc260, 0x417f,				\
+		  0x85, 0xa9, 0x08, 0x8b, 0x16, 0x21, 0xeb, 0xa6)
+/*
+ * DRAM Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.2; Table 8-44
+ */
+#define CPER_SEC_CXL_DRAM_GUID						\
+	GUID_INIT(0x601dcbb3, 0x9c06, 0x4eab,				\
+		  0xb8, 0xaf, 0x4e, 0x9b, 0xfb, 0x5c, 0x96, 0x24)
+/*
+ * Memory Module Event Record
+ * CXL rev 3.0 section 8.2.9.2.1.3; Table 8-45
+ */
+#define CPER_SEC_CXL_MEM_MODULE_GUID					\
+	GUID_INIT(0xfe927475, 0xdd59, 0x4339,				\
+		  0xa5, 0x86, 0x79, 0xba, 0xb1, 0x13, 0xb7, 0x74)
 
 /*
  * Flags bits definitions for flags in struct cper_record_header
@@ -270,11 +297,11 @@ enum {
 #define CPER_ARM_INFO_FLAGS_PROPAGATED		BIT(2)
 #define CPER_ARM_INFO_FLAGS_OVERFLOW		BIT(3)
 
-#define CPER_ARM_CACHE_ERROR			0
-#define CPER_ARM_TLB_ERROR			1
-#define CPER_ARM_BUS_ERROR			2
-#define CPER_ARM_VENDOR_ERROR			3
-#define CPER_ARM_MAX_TYPE			CPER_ARM_VENDOR_ERROR
+#define CPER_ARM_ERR_TYPE_MASK			GENMASK(4,1)
+#define CPER_ARM_CACHE_ERROR			BIT(1)
+#define CPER_ARM_TLB_ERROR			BIT(2)
+#define CPER_ARM_BUS_ERROR			BIT(3)
+#define CPER_ARM_VENDOR_ERROR			BIT(4)
 
 #define CPER_ARM_ERR_VALID_TRANSACTION_TYPE	BIT(0)
 #define CPER_ARM_ERR_VALID_OPERATION_TYPE	BIT(1)
@@ -561,6 +588,8 @@ const char *cper_mem_err_type_str(unsigned int);
 const char *cper_mem_err_status_str(u64 status);
 void cper_print_bits(const char *prefix, unsigned int bits,
 		     const char * const strs[], unsigned int strs_size);
+int cper_bits_to_str(char *buf, int buf_size, unsigned long bits,
+		     const char * const strs[], unsigned int strs_size);
 void cper_mem_err_pack(const struct cper_sec_mem_err *,
 		       struct cper_mem_err_compact *);
 const char *cper_mem_err_unpack(struct trace_seq *,
@@ -572,4 +601,14 @@ void cper_print_proc_ia(const char *pfx,
 int cper_mem_err_location(struct cper_mem_err_compact *mem, char *msg);
 int cper_dimm_err_location(struct cper_mem_err_compact *mem, char *msg);
 
+struct acpi_hest_generic_status;
+void cper_estatus_print(const char *pfx,
+			const struct acpi_hest_generic_status *estatus);
+int cper_estatus_check_header(const struct acpi_hest_generic_status *estatus);
+int cper_estatus_check(const struct acpi_hest_generic_status *estatus);
+
+struct cxl_cper_sec_prot_err;
+void cxl_cper_print_prot_err(const char *pfx,
+			     const struct cxl_cper_sec_prot_err *prot_err);
+
 #endif
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 8582a7142623..487b3bf2e1ea 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -16,8 +16,9 @@
 
 #include <linux/node.h>
 #include <linux/compiler.h>
-#include <linux/cpumask.h>
 #include <linux/cpuhotplug.h>
+#include <linux/cpuhplock.h>
+#include <linux/cpu_smt.h>
 
 struct device;
 struct device_node;
@@ -70,17 +71,37 @@ extern ssize_t cpu_show_mmio_stale_data(struct device *dev,
 					char *buf);
 extern ssize_t cpu_show_retbleed(struct device *dev,
 				 struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_spec_rstack_overflow(struct device *dev,
+					     struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_gds(struct device *dev,
+			    struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_reg_file_data_sampling(struct device *dev,
+					       struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_ghostwrite(struct device *dev, struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_old_microcode(struct device *dev,
+				      struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
+						  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_vmscape(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
 				 const struct attribute_group **groups,
 				 const char *fmt, ...);
+extern bool arch_cpu_is_hotpluggable(int cpu);
+extern int arch_register_cpu(int cpu);
+extern void arch_unregister_cpu(int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
 extern void unregister_cpu(struct cpu *cpu);
 extern ssize_t arch_cpu_probe(const char *, size_t);
 extern ssize_t arch_cpu_release(const char *, size_t);
 #endif
 
+#ifdef CONFIG_GENERIC_CPU_DEVICES
+DECLARE_PER_CPU(struct cpu, cpu_devices);
+#endif
+
 /*
  * These states are not related to the core CPU hotplug mechanism. They are
  * used by various (sub)architectures to track internal state
@@ -100,7 +121,8 @@ void notify_cpu_starting(unsigned int cpu);
 extern void cpu_maps_update_begin(void);
 extern void cpu_maps_update_done(void);
 int bringup_hibernate_cpu(unsigned int sleep_cpu);
-void bringup_nonboot_cpus(unsigned int setup_max_cpus);
+void bringup_nonboot_cpus(unsigned int max_cpus);
+int arch_cpu_rescan_dead_smt_siblings(void);
 
 #else	/* CONFIG_SMP */
 #define cpuhp_tasks_frozen	0
@@ -115,38 +137,10 @@ static inline void cpu_maps_update_done(void)
 
 static inline int add_cpu(unsigned int cpu) { return 0;}
 
-#endif /* CONFIG_SMP */
-extern struct bus_type cpu_subsys;
-
-extern int lockdep_is_cpus_held(void);
+static inline int arch_cpu_rescan_dead_smt_siblings(void) { return 0; }
 
-#ifdef CONFIG_HOTPLUG_CPU
-extern void cpus_write_lock(void);
-extern void cpus_write_unlock(void);
-extern void cpus_read_lock(void);
-extern void cpus_read_unlock(void);
-extern int  cpus_read_trylock(void);
-extern void lockdep_assert_cpus_held(void);
-extern void cpu_hotplug_disable(void);
-extern void cpu_hotplug_enable(void);
-void clear_tasks_mm_cpumask(int cpu);
-int remove_cpu(unsigned int cpu);
-int cpu_device_down(struct device *dev);
-extern void smp_shutdown_nonboot_cpus(unsigned int primary_cpu);
-
-#else /* CONFIG_HOTPLUG_CPU */
-
-static inline void cpus_write_lock(void) { }
-static inline void cpus_write_unlock(void) { }
-static inline void cpus_read_lock(void) { }
-static inline void cpus_read_unlock(void) { }
-static inline int  cpus_read_trylock(void) { return true; }
-static inline void lockdep_assert_cpus_held(void) { }
-static inline void cpu_hotplug_disable(void) { }
-static inline void cpu_hotplug_enable(void) { }
-static inline int remove_cpu(unsigned int cpu) { return -EPERM; }
-static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { }
-#endif	/* !CONFIG_HOTPLUG_CPU */
+#endif /* CONFIG_SMP */
+extern const struct bus_type cpu_subsys;
 
 #ifdef CONFIG_PM_SLEEP_SMP
 extern int freeze_secondary_cpus(int primary);
@@ -163,7 +157,7 @@ static inline int suspend_disable_secondary_cpus(void)
 }
 static inline void suspend_enable_secondary_cpus(void)
 {
-	return thaw_secondary_cpus();
+	thaw_secondary_cpus();
 }
 
 #else /* !CONFIG_PM_SLEEP_SMP */
@@ -182,51 +176,57 @@ void arch_cpu_idle(void);
 void arch_cpu_idle_prepare(void);
 void arch_cpu_idle_enter(void);
 void arch_cpu_idle_exit(void);
+void arch_tick_broadcast_enter(void);
+void arch_tick_broadcast_exit(void);
 void __noreturn arch_cpu_idle_dead(void);
 
-int cpu_report_state(int cpu);
-int cpu_check_up_prepare(int cpu);
-void cpu_set_state_online(int cpu);
-void play_idle_precise(u64 duration_ns, u64 latency_ns);
+#ifdef CONFIG_ARCH_HAS_CPU_FINALIZE_INIT
+void arch_cpu_finalize_init(void);
+#else
+static inline void arch_cpu_finalize_init(void) { }
+#endif
 
-static inline void play_idle(unsigned long duration_us)
-{
-	play_idle_precise(duration_us * NSEC_PER_USEC, U64_MAX);
-}
+void play_idle_precise(u64 duration_ns, u64 latency_ns);
 
 #ifdef CONFIG_HOTPLUG_CPU
-bool cpu_wait_death(unsigned int cpu, int seconds);
-bool cpu_report_death(void);
 void cpuhp_report_idle_dead(void);
 #else
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
-enum cpuhp_smt_control {
-	CPU_SMT_ENABLED,
-	CPU_SMT_DISABLED,
-	CPU_SMT_FORCE_DISABLED,
-	CPU_SMT_NOT_SUPPORTED,
-	CPU_SMT_NOT_IMPLEMENTED,
+enum cpu_attack_vectors {
+	CPU_MITIGATE_USER_KERNEL,
+	CPU_MITIGATE_USER_USER,
+	CPU_MITIGATE_GUEST_HOST,
+	CPU_MITIGATE_GUEST_GUEST,
+	NR_CPU_ATTACK_VECTORS,
 };
 
-#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
-extern enum cpuhp_smt_control cpu_smt_control;
-extern void cpu_smt_disable(bool force);
-extern void cpu_smt_check_topology(void);
-extern bool cpu_smt_possible(void);
-extern int cpuhp_smt_enable(void);
-extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval);
-#else
-# define cpu_smt_control		(CPU_SMT_NOT_IMPLEMENTED)
-static inline void cpu_smt_disable(bool force) { }
-static inline void cpu_smt_check_topology(void) { }
-static inline bool cpu_smt_possible(void) { return false; }
-static inline int cpuhp_smt_enable(void) { return 0; }
-static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; }
-#endif
+enum smt_mitigations {
+	SMT_MITIGATIONS_OFF,
+	SMT_MITIGATIONS_AUTO,
+	SMT_MITIGATIONS_ON,
+};
 
+#ifdef CONFIG_CPU_MITIGATIONS
 extern bool cpu_mitigations_off(void);
 extern bool cpu_mitigations_auto_nosmt(void);
+extern bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v);
+extern enum smt_mitigations smt_mitigations;
+#else
+static inline bool cpu_mitigations_off(void)
+{
+	return true;
+}
+static inline bool cpu_mitigations_auto_nosmt(void)
+{
+	return false;
+}
+static inline bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v)
+{
+	return false;
+}
+#define smt_mitigations SMT_MITIGATIONS_OFF
+#endif
 
 #endif /* _LINUX_CPU_H_ */
diff --git a/include/linux/cpu_cooling.h b/include/linux/cpu_cooling.h
index a3bdc8a98f2c..2c774fb3c091 100644
--- a/include/linux/cpu_cooling.h
+++ b/include/linux/cpu_cooling.h
@@ -15,7 +15,6 @@
 
 #include <linux/of.h>
 #include <linux/thermal.h>
-#include <linux/cpumask.h>
 
 struct cpufreq_policy;
 
diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h
index cae324d10965..2fd7ba75362a 100644
--- a/include/linux/cpu_rmap.h
+++ b/include/linux/cpu_rmap.h
@@ -7,7 +7,7 @@
  * Copyright 2011 Solarflare Communications Inc.
  */
 
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/gfp.h>
 #include <linux/slab.h>
 #include <linux/kref.h>
@@ -32,6 +32,7 @@ struct cpu_rmap {
 #define CPU_RMAP_DIST_INF 0xffff
 
 extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags);
+extern void cpu_rmap_get(struct cpu_rmap *rmap);
 extern int cpu_rmap_put(struct cpu_rmap *rmap);
 
 extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj);
diff --git a/include/linux/cpu_smt.h b/include/linux/cpu_smt.h
new file mode 100644
index 000000000000..0c1664294b57
--- /dev/null
+++ b/include/linux/cpu_smt.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_CPU_SMT_H_
+#define _LINUX_CPU_SMT_H_
+
+enum cpuhp_smt_control {
+	CPU_SMT_ENABLED,
+	CPU_SMT_DISABLED,
+	CPU_SMT_FORCE_DISABLED,
+	CPU_SMT_NOT_SUPPORTED,
+	CPU_SMT_NOT_IMPLEMENTED,
+};
+
+#if defined(CONFIG_SMP) && defined(CONFIG_HOTPLUG_SMT)
+extern enum cpuhp_smt_control cpu_smt_control;
+extern unsigned int cpu_smt_num_threads;
+extern void cpu_smt_disable(bool force);
+extern void cpu_smt_set_num_threads(unsigned int num_threads,
+				    unsigned int max_threads);
+extern bool cpu_smt_possible(void);
+extern int cpuhp_smt_enable(void);
+extern int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval);
+#else
+# define cpu_smt_control               (CPU_SMT_NOT_IMPLEMENTED)
+# define cpu_smt_num_threads 1
+static inline void cpu_smt_disable(bool force) { }
+static inline void cpu_smt_set_num_threads(unsigned int num_threads,
+					   unsigned int max_threads) { }
+static inline bool cpu_smt_possible(void) { return false; }
+static inline int cpuhp_smt_enable(void) { return 0; }
+static inline int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { return 0; }
+#endif
+
+#endif /* _LINUX_CPU_SMT_H_ */
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 26e2eb399484..0465d1e6f72a 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -19,18 +19,17 @@
 #include <linux/pm_qos.h>
 #include <linux/spinlock.h>
 #include <linux/sysfs.h>
+#include <linux/minmax.h>
 
 /*********************************************************************
  *                        CPUFREQ INTERFACE                          *
  *********************************************************************/
 /*
  * Frequency values here are CPU kHz
- *
- * Maximum transition latency is in nanoseconds - if it's unknown,
- * CPUFREQ_ETERNAL shall be used.
  */
 
-#define CPUFREQ_ETERNAL			(-1)
+#define CPUFREQ_DEFAULT_TRANSITION_LATENCY_NS	NSEC_PER_MSEC
+
 #define CPUFREQ_NAME_LEN		16
 /* Print length for names. Extra 1 space for accommodating '\n' in prints */
 #define CPUFREQ_NAME_PLEN		(CPUFREQ_NAME_LEN + 1)
@@ -140,6 +139,12 @@ struct cpufreq_policy {
 	 */
 	bool			dvfs_possible_from_any_cpu;
 
+	/* Per policy boost enabled flag. */
+	bool			boost_enabled;
+
+	/* Per policy boost supported flag. */
+	bool			boost_supported;
+
 	 /* Cached frequency lookup from cpufreq_driver_resolve_freq. */
 	unsigned int cached_target_freq;
 	unsigned int cached_resolved_idx;
@@ -163,6 +168,12 @@ struct cpufreq_policy {
 	struct notifier_block nb_max;
 };
 
+DEFINE_GUARD(cpufreq_policy_write, struct cpufreq_policy *,
+	     down_write(&_T->rwsem), up_write(&_T->rwsem))
+
+DEFINE_GUARD(cpufreq_policy_read, struct cpufreq_policy *,
+	     down_read(&_T->rwsem), up_read(&_T->rwsem))
+
 /*
  * Used for passing new cpufreq policy data to the cpufreq driver's ->verify()
  * callback for sanitization.  That callback is only expected to modify the min
@@ -206,6 +217,9 @@ static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 static inline void cpufreq_cpu_put(struct cpufreq_policy *policy) { }
 #endif
 
+/* Scope based cleanup macro for cpufreq_policy kobject reference counting */
+DEFINE_FREE(put_cpufreq_policy, struct cpufreq_policy *, if (_T) cpufreq_cpu_put(_T))
+
 static inline bool policy_is_inactive(struct cpufreq_policy *policy)
 {
 	return cpumask_empty(policy->cpus);
@@ -225,9 +239,6 @@ void disable_cpufreq(void);
 
 u64 get_cpu_idle_time(unsigned int cpu, u64 *wall, int io_busy);
 
-struct cpufreq_policy *cpufreq_cpu_acquire(unsigned int cpu);
-void cpufreq_cpu_release(struct cpufreq_policy *policy);
-int cpufreq_get_policy(struct cpufreq_policy *policy, unsigned int cpu);
 void refresh_frequency_limits(struct cpufreq_policy *policy);
 void cpufreq_update_policy(unsigned int cpu);
 void cpufreq_update_limits(unsigned int cpu);
@@ -237,6 +248,12 @@ struct kobject *get_governor_parent_kobj(struct cpufreq_policy *policy);
 void cpufreq_enable_fast_switch(struct cpufreq_policy *policy);
 void cpufreq_disable_fast_switch(struct cpufreq_policy *policy);
 bool has_target_index(void);
+
+DECLARE_PER_CPU(unsigned long, cpufreq_pressure);
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+	return READ_ONCE(per_cpu(cpufreq_pressure, cpu));
+}
 #else
 static inline unsigned int cpufreq_get(unsigned int cpu)
 {
@@ -259,6 +276,11 @@ static inline bool cpufreq_supports_freq_invariance(void)
 	return false;
 }
 static inline void disable_cpufreq(void) { }
+static inline void cpufreq_update_limits(unsigned int cpu) { }
+static inline unsigned long cpufreq_get_pressure(int cpu)
+{
+	return 0;
+}
 #endif
 
 #ifdef CONFIG_CPU_FREQ_STAT
@@ -340,7 +362,10 @@ struct cpufreq_driver {
 	/*
 	 * ->fast_switch() replacement for drivers that use an internal
 	 * representation of performance levels and can pass hints other than
-	 * the target performance level to the hardware.
+	 * the target performance level to the hardware. This can only be set
+	 * if ->fast_switch is set too, because in those cases (under specific
+	 * conditions) scale invariance can be disabled, which causes the
+	 * schedutil governor to fall back to the latter.
 	 */
 	void		(*adjust_perf)(unsigned int cpu,
 				       unsigned long min_perf,
@@ -367,18 +392,18 @@ struct cpufreq_driver {
 	int		(*target_intermediate)(struct cpufreq_policy *policy,
 					       unsigned int index);
 
-	/* should be defined, if possible */
+	/* should be defined, if possible, return 0 on error */
 	unsigned int	(*get)(unsigned int cpu);
 
 	/* Called to update policy limits on firmware notifications. */
-	void		(*update_limits)(unsigned int cpu);
+	void		(*update_limits)(struct cpufreq_policy *policy);
 
 	/* optional */
 	int		(*bios_limit)(int cpu, unsigned int *limit);
 
 	int		(*online)(struct cpufreq_policy *policy);
 	int		(*offline)(struct cpufreq_policy *policy);
-	int		(*exit)(struct cpufreq_policy *policy);
+	void		(*exit)(struct cpufreq_policy *policy);
 	int		(*suspend)(struct cpufreq_policy *policy);
 	int		(*resume)(struct cpufreq_policy *policy);
 
@@ -464,17 +489,8 @@ static inline void cpufreq_verify_within_limits(struct cpufreq_policy_data *poli
 						unsigned int min,
 						unsigned int max)
 {
-	if (policy->min < min)
-		policy->min = min;
-	if (policy->max < min)
-		policy->max = min;
-	if (policy->min > max)
-		policy->min = max;
-	if (policy->max > max)
-		policy->max = max;
-	if (policy->min > policy->max)
-		policy->min = policy->max;
-	return;
+	policy->max = clamp(policy->max, min, max);
+	policy->min = clamp(policy->min, min, policy->max);
 }
 
 static inline void
@@ -568,14 +584,6 @@ static inline unsigned long cpufreq_scale(unsigned long old, u_int div,
 #define CPUFREQ_POLICY_POWERSAVE	(1)
 #define CPUFREQ_POLICY_PERFORMANCE	(2)
 
-/*
- * The polling frequency depends on the capability of the processor. Default
- * polling frequency is 1000 times the transition latency of the processor. The
- * ondemand governor will work on any processor with transition latency <= 10ms,
- * using appropriate sampling rate.
- */
-#define LATENCY_MULTIPLIER		(1000)
-
 struct cpufreq_governor {
 	char	name[CPUFREQ_NAME_LEN];
 	int	(*init)(struct cpufreq_policy *policy);
@@ -640,6 +648,15 @@ module_exit(__governor##_exit)
 struct cpufreq_governor *cpufreq_default_governor(void);
 struct cpufreq_governor *cpufreq_fallback_governor(void);
 
+#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
+bool sugov_is_governor(struct cpufreq_policy *policy);
+#else
+static inline bool sugov_is_governor(struct cpufreq_policy *policy)
+{
+	return false;
+}
+#endif
+
 static inline void cpufreq_policy_apply_limits(struct cpufreq_policy *policy)
 {
 	if (policy->max < policy->cur)
@@ -696,26 +713,6 @@ struct cpufreq_frequency_table {
 				    * order */
 };
 
-#if defined(CONFIG_CPU_FREQ) && defined(CONFIG_PM_OPP)
-int dev_pm_opp_init_cpufreq_table(struct device *dev,
-				  struct cpufreq_frequency_table **table);
-void dev_pm_opp_free_cpufreq_table(struct device *dev,
-				   struct cpufreq_frequency_table **table);
-#else
-static inline int dev_pm_opp_init_cpufreq_table(struct device *dev,
-						struct cpufreq_frequency_table
-						**table)
-{
-	return -EINVAL;
-}
-
-static inline void dev_pm_opp_free_cpufreq_table(struct device *dev,
-						 struct cpufreq_frequency_table
-						 **table)
-{
-}
-#endif
-
 /*
  * cpufreq_for_each_entry -	iterate over a cpufreq_frequency_table
  * @pos:	the cpufreq_frequency_table * to use as a loop cursor.
@@ -781,26 +778,23 @@ static inline void dev_pm_opp_free_cpufreq_table(struct device *dev,
 		else
 
 
-int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
-				    struct cpufreq_frequency_table *table);
+int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy);
+
+int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy);
 
-int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy,
-				   struct cpufreq_frequency_table *table);
 int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy);
 
 int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
-				 unsigned int target_freq,
-				 unsigned int relation);
+				 unsigned int target_freq, unsigned int min,
+				 unsigned int max, unsigned int relation);
 int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
 		unsigned int freq);
 
 ssize_t cpufreq_show_cpus(const struct cpumask *mask, char *buf);
 
 #ifdef CONFIG_CPU_FREQ
-int cpufreq_boost_trigger_state(int state);
-int cpufreq_boost_enabled(void);
-int cpufreq_enable_boost_support(void);
-bool policy_has_boost_freq(struct cpufreq_policy *policy);
+bool cpufreq_boost_enabled(void);
+int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state);
 
 /* Find lowest freq at or above target in a table in ascending order */
 static inline int cpufreq_table_find_index_al(struct cpufreq_policy *policy,
@@ -855,12 +849,12 @@ static inline int cpufreq_table_find_index_dl(struct cpufreq_policy *policy,
 	return best;
 }
 
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
-					     unsigned int target_freq,
-					     bool efficiencies)
+static inline int find_index_l(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int min, unsigned int max,
+			       bool efficiencies)
 {
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
 		return cpufreq_table_find_index_al(policy, target_freq,
@@ -870,6 +864,14 @@ static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_l(struct cpufreq_policy *policy,
+					     unsigned int target_freq,
+					     bool efficiencies)
+{
+	return find_index_l(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
 /* Find highest freq at or below target in a table in ascending order */
 static inline int cpufreq_table_find_index_ah(struct cpufreq_policy *policy,
 					      unsigned int target_freq,
@@ -923,12 +925,12 @@ static inline int cpufreq_table_find_index_dh(struct cpufreq_policy *policy,
 	return best;
 }
 
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
-					     unsigned int target_freq,
-					     bool efficiencies)
+static inline int find_index_h(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int min, unsigned int max,
+			       bool efficiencies)
 {
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
 		return cpufreq_table_find_index_ah(policy, target_freq,
@@ -938,6 +940,14 @@ static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_h(struct cpufreq_policy *policy,
+					     unsigned int target_freq,
+					     bool efficiencies)
+{
+	return find_index_h(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
 /* Find closest freq to target in a table in ascending order */
 static inline int cpufreq_table_find_index_ac(struct cpufreq_policy *policy,
 					      unsigned int target_freq,
@@ -1008,12 +1018,12 @@ static inline int cpufreq_table_find_index_dc(struct cpufreq_policy *policy,
 	return best;
 }
 
-/* Works only on sorted freq-tables */
-static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
-					     unsigned int target_freq,
-					     bool efficiencies)
+static inline int find_index_c(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int min, unsigned int max,
+			       bool efficiencies)
 {
-	target_freq = clamp_val(target_freq, policy->min, policy->max);
+	target_freq = clamp_val(target_freq, min, max);
 
 	if (policy->freq_table_sorted == CPUFREQ_TABLE_SORTED_ASCENDING)
 		return cpufreq_table_find_index_ac(policy, target_freq,
@@ -1023,8 +1033,32 @@ static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
 						   efficiencies);
 }
 
+/* Works only on sorted freq-tables */
+static inline int cpufreq_table_find_index_c(struct cpufreq_policy *policy,
+					     unsigned int target_freq,
+					     bool efficiencies)
+{
+	return find_index_c(policy, target_freq, policy->min, policy->max, efficiencies);
+}
+
+static inline bool cpufreq_is_in_limits(struct cpufreq_policy *policy,
+					unsigned int min, unsigned int max,
+					int idx)
+{
+	unsigned int freq;
+
+	if (idx < 0)
+		return false;
+
+	freq = policy->freq_table[idx].frequency;
+
+	return freq == clamp_val(freq, min, max);
+}
+
 static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 						 unsigned int target_freq,
+						 unsigned int min,
+						 unsigned int max,
 						 unsigned int relation)
 {
 	bool efficiencies = policy->efficiencies_available &&
@@ -1035,28 +1069,26 @@ static inline int cpufreq_frequency_table_target(struct cpufreq_policy *policy,
 	relation &= ~CPUFREQ_RELATION_E;
 
 	if (unlikely(policy->freq_table_sorted == CPUFREQ_TABLE_UNSORTED))
-		return cpufreq_table_index_unsorted(policy, target_freq,
-						    relation);
+		return cpufreq_table_index_unsorted(policy, target_freq, min,
+						    max, relation);
 retry:
 	switch (relation) {
 	case CPUFREQ_RELATION_L:
-		idx = cpufreq_table_find_index_l(policy, target_freq,
-						 efficiencies);
+		idx = find_index_l(policy, target_freq, min, max, efficiencies);
 		break;
 	case CPUFREQ_RELATION_H:
-		idx = cpufreq_table_find_index_h(policy, target_freq,
-						 efficiencies);
+		idx = find_index_h(policy, target_freq, min, max, efficiencies);
 		break;
 	case CPUFREQ_RELATION_C:
-		idx = cpufreq_table_find_index_c(policy, target_freq,
-						 efficiencies);
+		idx = find_index_c(policy, target_freq, min, max, efficiencies);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		return 0;
 	}
 
-	if (idx < 0 && efficiencies) {
+	/* Limit frequency index to honor min and max */
+	if (!cpufreq_is_in_limits(policy, min, max, idx) && efficiencies) {
 		efficiencies = false;
 		goto retry;
 	}
@@ -1113,10 +1145,9 @@ static inline int parse_perf_domain(int cpu, const char *list_name,
 				    const char *cell_name,
 				    struct of_phandle_args *args)
 {
-	struct device_node *cpu_np;
 	int ret;
 
-	cpu_np = of_cpu_device_node_get(cpu);
+	struct device_node *cpu_np __free(device_node) = of_cpu_device_node_get(cpu);
 	if (!cpu_np)
 		return -ENODEV;
 
@@ -1124,9 +1155,6 @@ static inline int parse_perf_domain(int cpu, const char *list_name,
 					 args);
 	if (ret < 0)
 		return ret;
-
-	of_node_put(cpu_np);
-
 	return 0;
 }
 
@@ -1151,8 +1179,7 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_
 		if (ret < 0)
 			continue;
 
-		if (pargs->np == args.np && pargs->args_count == args.args_count &&
-		    !memcmp(pargs->args, args.args, sizeof(args.args[0]) * args.args_count))
+		if (of_phandle_args_equal(pargs, &args))
 			cpumask_set_cpu(cpu, cpumask);
 
 		of_node_put(args.np);
@@ -1161,23 +1188,14 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_
 	return 0;
 }
 #else
-static inline int cpufreq_boost_trigger_state(int state)
-{
-	return 0;
-}
-static inline int cpufreq_boost_enabled(void)
+static inline bool cpufreq_boost_enabled(void)
 {
-	return 0;
-}
-
-static inline int cpufreq_enable_boost_support(void)
-{
-	return -EINVAL;
+	return false;
 }
 
-static inline bool policy_has_boost_freq(struct cpufreq_policy *policy)
+static inline int cpufreq_boost_set_sw(struct cpufreq_policy *policy, int state)
 {
-	return false;
+	return -EOPNOTSUPP;
 }
 
 static inline int
@@ -1195,15 +1213,7 @@ static inline int of_perf_domain_get_sharing_cpumask(int pcpu, const char *list_
 }
 #endif
 
-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
-			struct cpufreq_governor *old_gov);
-#else
-static inline void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
-			struct cpufreq_governor *old_gov) { }
-#endif
-
-extern unsigned int arch_freq_get_on_cpu(int cpu);
+extern int arch_freq_get_on_cpu(int cpu);
 
 #ifndef arch_set_freq_scale
 static __always_inline
@@ -1213,10 +1223,10 @@ void arch_set_freq_scale(const struct cpumask *cpus,
 {
 }
 #endif
+
 /* the following are really really optional */
 extern struct freq_attr cpufreq_freq_attr_scaling_available_freqs;
 extern struct freq_attr cpufreq_freq_attr_scaling_boost_freqs;
-extern struct freq_attr *cpufreq_generic_attr[];
 int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy);
 
 unsigned int cpufreq_generic_get(unsigned int cpu);
@@ -1224,6 +1234,8 @@ void cpufreq_generic_init(struct cpufreq_policy *policy,
 		struct cpufreq_frequency_table *table,
 		unsigned int transition_latency);
 
+bool cpufreq_ready_for_eas(const struct cpumask *cpu_mask);
+
 static inline void cpufreq_register_em_with_opp(struct cpufreq_policy *policy)
 {
 	dev_pm_opp_of_register_em(get_cpu_device(policy->cpu),
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 0f1001dca0e0..62cd7b35a29c 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -27,7 +27,7 @@
  * startup callbacks sequentially from CPUHP_OFFLINE + 1 to CPUHP_ONLINE
  * during a CPU online operation. During a CPU offline operation the
  * installed teardown callbacks are invoked in the reverse order from
- * CPU_ONLINE - 1 down to CPUHP_OFFLINE.
+ * CPUHP_ONLINE - 1 down to CPUHP_OFFLINE.
  *
  * The state space has three sections: PREPARE, STARTING and ONLINE.
  *
@@ -48,7 +48,7 @@
  *    same section.
  *
  * If neither #1 nor #2 apply, please use the dynamic state space when
- * setting up a state by using CPUHP_PREPARE_DYN or CPUHP_PREPARE_ONLINE
+ * setting up a state by using CPUHP_BP_PREPARE_DYN or CPUHP_AP_ONLINE_DYN
  * for the @state argument of the setup function.
  *
  * See Documentation/core-api/cpu_hotplug.rst for further information and
@@ -60,21 +60,17 @@ enum cpuhp_state {
 	/* PREPARE section invoked on a control CPU */
 	CPUHP_OFFLINE = 0,
 	CPUHP_CREATE_THREADS,
-	CPUHP_PERF_PREPARE,
 	CPUHP_PERF_X86_PREPARE,
 	CPUHP_PERF_X86_AMD_UNCORE_PREP,
 	CPUHP_PERF_POWER,
 	CPUHP_PERF_SUPERH,
 	CPUHP_X86_HPET_DEAD,
-	CPUHP_X86_APB_DEAD,
 	CPUHP_X86_MCE_DEAD,
 	CPUHP_VIRT_NET_DEAD,
 	CPUHP_IBMVNIC_DEAD,
 	CPUHP_SLUB_DEAD,
 	CPUHP_DEBUG_OBJ_DEAD,
 	CPUHP_MM_WRITEBACK_DEAD,
-	/* Must be after CPUHP_MM_VMSTAT_DEAD */
-	CPUHP_MM_DEMOTION_DEAD,
 	CPUHP_MM_VMSTAT_DEAD,
 	CPUHP_SOFTIRQ_DEAD,
 	CPUHP_NET_MVNETA_DEAD,
@@ -90,14 +86,11 @@ enum cpuhp_state {
 	CPUHP_FS_BUFF_DEAD,
 	CPUHP_PRINTK_DEAD,
 	CPUHP_MM_MEMCQ_DEAD,
-	CPUHP_XFS_DEAD,
 	CPUHP_PERCPU_CNT_DEAD,
 	CPUHP_RADIX_DEAD,
 	CPUHP_PAGE_ALLOC,
 	CPUHP_NET_DEV_DEAD,
-	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_IOVA_DEAD,
-	CPUHP_LUSTRE_CFS_DEAD,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
 	CPUHP_PADATA_DEAD,
 	CPUHP_AP_DTPM_CPU_DEAD,
@@ -105,11 +98,9 @@ enum cpuhp_state {
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
-	CPUHP_PROFILE_PREPARE,
 	CPUHP_X2APIC_PREPARE,
 	CPUHP_SMPCFD_PREPARE,
 	CPUHP_RELAY_PREPARE,
-	CPUHP_SLAB_PREPARE,
 	CPUHP_MD_RAID5_PREPARE,
 	CPUHP_RCUTREE_PREP,
 	CPUHP_CPUIDLE_COUPLED_PREPARE,
@@ -119,20 +110,19 @@ enum cpuhp_state {
 	CPUHP_XEN_EVTCHN_PREPARE,
 	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
 	CPUHP_SH_SH3X_PREPARE,
-	CPUHP_NET_FLOW_PREPARE,
 	CPUHP_TOPOLOGY_PREPARE,
 	CPUHP_NET_IUCV_PREPARE,
 	CPUHP_ARM_BL_PREPARE,
 	CPUHP_TRACE_RB_PREPARE,
-	CPUHP_MM_ZS_PREPARE,
-	CPUHP_MM_ZSWP_MEM_PREPARE,
 	CPUHP_MM_ZSWP_POOL_PREPARE,
 	CPUHP_KVM_PPC_BOOK3S_PREPARE,
 	CPUHP_ZCOMP_PREPARE,
 	CPUHP_TIMERS_PREPARE,
+	CPUHP_TMIGR_PREPARE,
 	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BP_PREPARE_DYN,
 	CPUHP_BP_PREPARE_DYN_END		= CPUHP_BP_PREPARE_DYN + 20,
+	CPUHP_BP_KICK_AP,
 	CPUHP_BRINGUP_CPU,
 
 	/*
@@ -151,18 +141,17 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_ARMADA_XP_STARTING,
 	CPUHP_AP_IRQ_BCM2836_STARTING,
 	CPUHP_AP_IRQ_MIPS_GIC_STARTING,
-	CPUHP_AP_IRQ_RISCV_STARTING,
-	CPUHP_AP_IRQ_LOONGARCH_STARTING,
+	CPUHP_AP_IRQ_EIOINTC_STARTING,
+	CPUHP_AP_IRQ_AVECINTC_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
+	CPUHP_AP_IRQ_ACLINT_SSWI_STARTING,
+	CPUHP_AP_IRQ_RISCV_IMSIC_STARTING,
+	CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
-	CPUHP_AP_MICROCODE_LOADER,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-	CPUHP_AP_PERF_X86_CQM_STARTING,
-	CPUHP_AP_PERF_X86_CSTATE_STARTING,
 	CPUHP_AP_PERF_XTENSA_STARTING,
-	CPUHP_AP_MIPS_OP_LOONGSON3_STARTING,
 	CPUHP_AP_ARM_VFP_STARTING,
 	CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
 	CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
@@ -172,15 +161,17 @@ enum cpuhp_state {
 	CPUHP_AP_ARM_L2X0_STARTING,
 	CPUHP_AP_EXYNOS4_MCT_TIMER_STARTING,
 	CPUHP_AP_ARM_ARCH_TIMER_STARTING,
+	CPUHP_AP_ARM_ARCH_TIMER_EVTSTRM_STARTING,
 	CPUHP_AP_ARM_GLOBAL_TIMER_STARTING,
 	CPUHP_AP_JCORE_TIMER_STARTING,
 	CPUHP_AP_ARM_TWD_STARTING,
 	CPUHP_AP_QCOM_TIMER_STARTING,
 	CPUHP_AP_TEGRA_TIMER_STARTING,
 	CPUHP_AP_ARMADA_TIMER_STARTING,
-	CPUHP_AP_MARCO_TIMER_STARTING,
+	CPUHP_AP_LOONGARCH_ARCH_TIMER_STARTING,
 	CPUHP_AP_MIPS_GIC_TIMER_STARTING,
 	CPUHP_AP_ARC_TIMER_STARTING,
+	CPUHP_AP_REALTEK_TIMER_STARTING,
 	CPUHP_AP_RISCV_TIMER_STARTING,
 	CPUHP_AP_CLINT_TIMER_STARTING,
 	CPUHP_AP_CSKY_TIMER_STARTING,
@@ -189,10 +180,13 @@ enum cpuhp_state {
 	/* Must be the last timer callback */
 	CPUHP_AP_DUMMY_TIMER_STARTING,
 	CPUHP_AP_ARM_XEN_STARTING,
+	CPUHP_AP_ARM_XEN_RUNSTATE_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_STARTING,
 	CPUHP_AP_ARM_CORESIGHT_CTI_STARTING,
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
+	CPUHP_AP_HRTIMERS_DYING,
+	CPUHP_AP_TICK_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DYING,
 	CPUHP_AP_ONLINE,
@@ -200,10 +194,10 @@ enum cpuhp_state {
 
 	/* Online section invoked on the hotplugged CPU from the hotplug thread */
 	CPUHP_AP_ONLINE_IDLE,
+	CPUHP_AP_HYPERV_ONLINE,
 	CPUHP_AP_KVM_ONLINE,
 	CPUHP_AP_SCHED_WAIT_EMPTY,
 	CPUHP_AP_SMPBOOT_THREADS,
-	CPUHP_AP_X86_VDSO_VMA_ONLINE,
 	CPUHP_AP_IRQ_AFFINITY_ONLINE,
 	CPUHP_AP_BLK_MQ_ONLINE,
 	CPUHP_AP_ARM_MVEBU_SYNC_CLOCKS,
@@ -213,10 +207,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-	CPUHP_AP_PERF_X86_RAPL_ONLINE,
-	CPUHP_AP_PERF_X86_CQM_ONLINE,
-	CPUHP_AP_PERF_X86_CSTATE_ONLINE,
-	CPUHP_AP_PERF_X86_IDXD_ONLINE,
 	CPUHP_AP_PERF_S390_CF_ONLINE,
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
@@ -235,6 +225,7 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_ARM_APM_XGENE_ONLINE,
 	CPUHP_AP_PERF_ARM_CAVIUM_TX2_UNCORE_ONLINE,
 	CPUHP_AP_PERF_ARM_MARVELL_CN10K_DDR_ONLINE,
+	CPUHP_AP_PERF_ARM_MRVL_PEM_ONLINE,
 	CPUHP_AP_PERF_POWERPC_NEST_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_CORE_IMC_ONLINE,
 	CPUHP_AP_PERF_POWERPC_THREAD_IMC_ONLINE,
@@ -242,15 +233,15 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_POWERPC_HV_24x7_ONLINE,
 	CPUHP_AP_PERF_POWERPC_HV_GPCI_ONLINE,
 	CPUHP_AP_PERF_CSKY_ONLINE,
+	CPUHP_AP_TMIGR_ONLINE,
 	CPUHP_AP_WATCHDOG_ONLINE,
 	CPUHP_AP_WORKQUEUE_ONLINE,
 	CPUHP_AP_RANDOM_ONLINE,
 	CPUHP_AP_RCUTREE_ONLINE,
+	CPUHP_AP_KTHREADS_ONLINE,
 	CPUHP_AP_BASE_CACHEINFO_ONLINE,
 	CPUHP_AP_ONLINE_DYN,
-	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 30,
-	/* Must be after CPUHP_AP_ONLINE_DYN for node_states[N_CPU] update */
-	CPUHP_AP_MM_DEMOTION_ONLINE,
+	CPUHP_AP_ONLINE_DYN_END		= CPUHP_AP_ONLINE_DYN + 40,
 	CPUHP_AP_X86_HPET_ONLINE,
 	CPUHP_AP_X86_KVM_CLK_ONLINE,
 	CPUHP_AP_ACTIVE,
@@ -517,4 +508,20 @@ void cpuhp_online_idle(enum cpuhp_state state);
 static inline void cpuhp_online_idle(enum cpuhp_state state) { }
 #endif
 
+struct task_struct;
+
+void cpuhp_ap_sync_alive(void);
+void arch_cpuhp_sync_state_poll(void);
+void arch_cpuhp_cleanup_kick_cpu(unsigned int cpu);
+int arch_cpuhp_kick_ap_alive(unsigned int cpu, struct task_struct *tidle);
+bool arch_cpuhp_init_parallel_bringup(void);
+
+#ifdef CONFIG_HOTPLUG_CORE_SYNC_DEAD
+void cpuhp_ap_report_dead(void);
+void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu);
+#else
+static inline void cpuhp_ap_report_dead(void) { }
+static inline void arch_cpuhp_cleanup_dead_cpu(unsigned int cpu) { }
+#endif
+
 #endif
diff --git a/include/linux/cpuhplock.h b/include/linux/cpuhplock.h
new file mode 100644
index 000000000000..f7aa20f62b87
--- /dev/null
+++ b/include/linux/cpuhplock.h
@@ -0,0 +1,49 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * include/linux/cpuhplock.h - CPU hotplug locking
+ *
+ * Locking functions for CPU hotplug.
+ */
+#ifndef _LINUX_CPUHPLOCK_H_
+#define _LINUX_CPUHPLOCK_H_
+
+#include <linux/cleanup.h>
+#include <linux/errno.h>
+
+struct device;
+
+extern int lockdep_is_cpus_held(void);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void cpus_write_lock(void);
+void cpus_write_unlock(void);
+void cpus_read_lock(void);
+void cpus_read_unlock(void);
+int  cpus_read_trylock(void);
+void lockdep_assert_cpus_held(void);
+void cpu_hotplug_disable_offlining(void);
+void cpu_hotplug_disable(void);
+void cpu_hotplug_enable(void);
+void clear_tasks_mm_cpumask(int cpu);
+int remove_cpu(unsigned int cpu);
+int cpu_device_down(struct device *dev);
+void smp_shutdown_nonboot_cpus(unsigned int primary_cpu);
+
+#else /* CONFIG_HOTPLUG_CPU */
+
+static inline void cpus_write_lock(void) { }
+static inline void cpus_write_unlock(void) { }
+static inline void cpus_read_lock(void) { }
+static inline void cpus_read_unlock(void) { }
+static inline int  cpus_read_trylock(void) { return true; }
+static inline void lockdep_assert_cpus_held(void) { }
+static inline void cpu_hotplug_disable_offlining(void) { }
+static inline void cpu_hotplug_disable(void) { }
+static inline void cpu_hotplug_enable(void) { }
+static inline int remove_cpu(unsigned int cpu) { return -EPERM; }
+static inline void smp_shutdown_nonboot_cpus(unsigned int primary_cpu) { }
+#endif	/* !CONFIG_HOTPLUG_CPU */
+
+DEFINE_LOCK_GUARD_0(cpus_read_lock, cpus_read_lock(), cpus_read_unlock())
+
+#endif /* _LINUX_CPUHPLOCK_H_ */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 3183aeb7f5b4..4073690504a7 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -61,7 +61,7 @@ struct cpuidle_state {
 			struct cpuidle_driver *drv,
 			int index);
 
-	int (*enter_dead) (struct cpuidle_device *dev, int index);
+	void (*enter_dead) (struct cpuidle_device *dev, int index);
 
 	/*
 	 * CPUs execute ->enter_s2idle with the local tick or entire timekeeping
@@ -248,7 +248,8 @@ extern int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 				      struct cpuidle_device *dev,
 				      u64 latency_limit_ns);
 extern int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
-				struct cpuidle_device *dev);
+				struct cpuidle_device *dev,
+				u64 latency_limit_ns);
 extern void cpuidle_use_deepest_state(u64 latency_limit_ns);
 #else
 static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
@@ -256,7 +257,8 @@ static inline int cpuidle_find_deepest_state(struct cpuidle_driver *drv,
 					     u64 latency_limit_ns)
 {return -ENODEV; }
 static inline int cpuidle_enter_s2idle(struct cpuidle_driver *drv,
-				       struct cpuidle_device *dev)
+				       struct cpuidle_device *dev,
+				       u64 latency_limit_ns)
 {return -ENODEV; }
 static inline void cpuidle_use_deepest_state(u64 latency_limit_ns)
 {
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index ca736b05ec7b..80211900f373 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -4,28 +4,19 @@
 
 /*
  * Cpumasks provide a bitmap suitable for representing the
- * set of CPU's in a system, one bit position per CPU number.  In general,
+ * set of CPUs in a system, one bit position per CPU number.  In general,
  * only nr_cpu_ids (<= NR_CPUS) bits are valid.
  */
-#include <linux/kernel.h>
-#include <linux/threads.h>
-#include <linux/bitmap.h>
 #include <linux/atomic.h>
-#include <linux/bug.h>
+#include <linux/bitmap.h>
+#include <linux/cleanup.h>
+#include <linux/cpumask_types.h>
 #include <linux/gfp_types.h>
 #include <linux/numa.h>
+#include <linux/threads.h>
+#include <linux/types.h>
 
-/* Don't assign or return these: may not be this big! */
-typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
-
-/**
- * cpumask_bits - get the bits in a cpumask
- * @maskp: the struct cpumask *
- *
- * You should only assume nr_cpu_ids bits of this mask are valid.  This is
- * a macro so it's const-correct.
- */
-#define cpumask_bits(maskp) ((maskp)->bits)
+#include <asm/bug.h>
 
 /**
  * cpumask_pr_args - printf args to output a cpumask
@@ -41,7 +32,7 @@ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
 extern unsigned int nr_cpu_ids;
 #endif
 
-static inline void set_nr_cpu_ids(unsigned int nr)
+static __always_inline void set_nr_cpu_ids(unsigned int nr)
 {
 #if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
 	WARN_ON(nr != nr_cpu_ids);
@@ -92,12 +83,13 @@ static inline void set_nr_cpu_ids(unsigned int nr)
  *
  *     cpu_possible_mask- has bit 'cpu' set iff cpu is populatable
  *     cpu_present_mask - has bit 'cpu' set iff cpu is populated
+ *     cpu_enabled_mask - has bit 'cpu' set iff cpu can be brought online
  *     cpu_online_mask  - has bit 'cpu' set iff cpu available to scheduler
  *     cpu_active_mask  - has bit 'cpu' set iff cpu available to migration
  *
  *  If !CONFIG_HOTPLUG_CPU, present == possible, and active == online.
  *
- *  The cpu_possible_mask is fixed at boot time, as the set of CPU id's
+ *  The cpu_possible_mask is fixed at boot time, as the set of CPU IDs
  *  that it is possible might ever be plugged in at anytime during the
  *  life of that system boot.  The cpu_present_mask is dynamic(*),
  *  representing which CPUs are currently plugged in.  And
@@ -112,7 +104,7 @@ static inline void set_nr_cpu_ids(unsigned int nr)
  *      hotplug, it's a copy of cpu_possible_mask, hence fixed at boot.
  *
  * Subtleties:
- * 1) UP arch's (NR_CPUS == 1, CONFIG_SMP not defined) hardcode
+ * 1) UP ARCHes (NR_CPUS == 1, CONFIG_SMP not defined) hardcode
  *    assumption that their single CPU is online.  The UP
  *    cpu_{online,possible,present}_masks are placebos.  Changing them
  *    will have no useful affect on the following num_*_cpus()
@@ -124,16 +116,19 @@ static inline void set_nr_cpu_ids(unsigned int nr)
 
 extern struct cpumask __cpu_possible_mask;
 extern struct cpumask __cpu_online_mask;
+extern struct cpumask __cpu_enabled_mask;
 extern struct cpumask __cpu_present_mask;
 extern struct cpumask __cpu_active_mask;
 extern struct cpumask __cpu_dying_mask;
 #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask)
 #define cpu_online_mask   ((const struct cpumask *)&__cpu_online_mask)
+#define cpu_enabled_mask   ((const struct cpumask *)&__cpu_enabled_mask)
 #define cpu_present_mask  ((const struct cpumask *)&__cpu_present_mask)
 #define cpu_active_mask   ((const struct cpumask *)&__cpu_active_mask)
 #define cpu_dying_mask    ((const struct cpumask *)&__cpu_dying_mask)
 
 extern atomic_t __num_online_cpus;
+extern unsigned int __num_possible_cpus;
 
 extern cpumask_t cpus_booted_once_mask;
 
@@ -155,9 +150,9 @@ static __always_inline unsigned int cpumask_check(unsigned int cpu)
  * cpumask_first - get the first cpu in a cpumask
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline unsigned int cpumask_first(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first(const struct cpumask *srcp)
 {
 	return find_first_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -166,45 +161,75 @@ static inline unsigned int cpumask_first(const struct cpumask *srcp)
  * cpumask_first_zero - get the first unset cpu in a cpumask
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if all cpus are set.
+ * Return: >= nr_cpu_ids if all cpus are set.
  */
-static inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_first_zero(const struct cpumask *srcp)
 {
 	return find_first_zero_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
 
 /**
  * cpumask_first_and - return the first cpu from *srcp1 & *srcp2
- * @src1p: the first input
- * @src2p: the second input
+ * @srcp1: the first input
+ * @srcp2: the second input
  *
- * Returns >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
+ * Return: >= nr_cpu_ids if no cpus set in both.  See also cpumask_next_and().
  */
-static inline
+static __always_inline
 unsigned int cpumask_first_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return find_first_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
 /**
+ * cpumask_first_andnot - return the first cpu from *srcp1 & ~*srcp2
+ * @srcp1: the first input
+ * @srcp2: the second input
+ *
+ * Return: >= nr_cpu_ids if no such cpu found.
+ */
+static __always_inline
+unsigned int cpumask_first_andnot(const struct cpumask *srcp1, const struct cpumask *srcp2)
+{
+	return find_first_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
+}
+
+/**
+ * cpumask_first_and_and - return the first cpu from *srcp1 & *srcp2 & *srcp3
+ * @srcp1: the first input
+ * @srcp2: the second input
+ * @srcp3: the third input
+ *
+ * Return: >= nr_cpu_ids if no cpus set in all.
+ */
+static __always_inline
+unsigned int cpumask_first_and_and(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2,
+				   const struct cpumask *srcp3)
+{
+	return find_first_and_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
+				      cpumask_bits(srcp3), small_cpumask_bits);
+}
+
+/**
  * cpumask_last - get the last CPU in a cpumask
  * @srcp:	- the cpumask pointer
  *
- * Returns	>= nr_cpumask_bits if no CPUs set.
+ * Return:	>= nr_cpumask_bits if no CPUs set.
  */
-static inline unsigned int cpumask_last(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_last(const struct cpumask *srcp)
 {
 	return find_last_bit(cpumask_bits(srcp), small_cpumask_bits);
 }
 
 /**
  * cpumask_next - get the next cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if no further cpus set.
+ * Return: >= nr_cpu_ids if no further cpus set.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
@@ -215,12 +240,13 @@ unsigned int cpumask_next(int n, const struct cpumask *srcp)
 
 /**
  * cpumask_next_zero - get the next unset cpu in a cpumask
- * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
  * @srcp: the cpumask pointer
  *
- * Returns >= nr_cpu_ids if no further cpus unset.
+ * Return: >= nr_cpu_ids if no further cpus unset.
  */
-static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -230,18 +256,21 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp)
 
 #if NR_CPUS == 1
 /* Uniprocessor: there is only one valid CPU */
-static inline unsigned int cpumask_local_spread(unsigned int i, int node)
+static __always_inline
+unsigned int cpumask_local_spread(unsigned int i, int node)
 {
 	return 0;
 }
 
-static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
-						      const struct cpumask *src2p)
+static __always_inline
+unsigned int cpumask_any_and_distribute(const struct cpumask *src1p,
+					const struct cpumask *src2p)
 {
 	return cpumask_first_and(src1p, src2p);
 }
 
-static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_any_distribute(const struct cpumask *srcp)
 {
 	return cpumask_first(srcp);
 }
@@ -254,15 +283,15 @@ unsigned int cpumask_any_distribute(const struct cpumask *srcp);
 
 /**
  * cpumask_next_and - get the next cpu in *src1p & *src2p
- * @n: the cpu prior to the place to search (ie. return will be > @n)
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
  * @src1p: the first cpumask pointer
  * @src2p: the second cpumask pointer
  *
- * Returns >= nr_cpu_ids if no further cpus set in both.
+ * Return: >= nr_cpu_ids if no further cpus set in both.
  */
-static inline
+static __always_inline
 unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
-		     const struct cpumask *src2p)
+			      const struct cpumask *src2p)
 {
 	/* -1 is a legal arg here. */
 	if (n != -1)
@@ -272,35 +301,83 @@ unsigned int cpumask_next_and(int n, const struct cpumask *src1p,
 }
 
 /**
- * for_each_cpu - iterate over every cpu in a mask
- * @cpu: the (optionally unsigned) integer iterator
- * @mask: the cpumask pointer
+ * cpumask_next_andnot - get the next cpu in *src1p & ~*src2p
+ * @n: the cpu prior to the place to search (i.e. return will be > @n)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
  *
- * After the loop, cpu is >= nr_cpu_ids.
+ * Return: >= nr_cpu_ids if no further cpus set in both.
  */
-#define for_each_cpu(cpu, mask)				\
-	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
+static __always_inline
+unsigned int cpumask_next_andnot(int n, const struct cpumask *src1p,
+				 const struct cpumask *src2p)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_andnot_bit(cpumask_bits(src1p), cpumask_bits(src2p),
+		small_cpumask_bits, n + 1);
+}
 
-#if NR_CPUS == 1
-static inline
-unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap)
+/**
+ * cpumask_next_and_wrap - get the next cpu in *src1p & *src2p, starting from
+ *			   @n+1. If nothing found, wrap around and start from
+ *			   the beginning
+ * @n: the cpu prior to the place to search (i.e. search starts from @n+1)
+ * @src1p: the first cpumask pointer
+ * @src2p: the second cpumask pointer
+ *
+ * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src1p & @src2p is empty.
+ */
+static __always_inline
+unsigned int cpumask_next_and_wrap(int n, const struct cpumask *src1p,
+			      const struct cpumask *src2p)
 {
-	cpumask_check(start);
+	/* -1 is a legal arg here. */
 	if (n != -1)
 		cpumask_check(n);
+	return find_next_and_bit_wrap(cpumask_bits(src1p), cpumask_bits(src2p),
+		small_cpumask_bits, n + 1);
+}
 
-	/*
-	 * Return the first available CPU when wrapping, or when starting before cpu0,
-	 * since there is only one valid option.
-	 */
-	if (wrap && n >= 0)
-		return nr_cpumask_bits;
+/**
+ * cpumask_next_wrap - get the next cpu in *src, starting from @n+1. If nothing
+ *		       found, wrap around and start from the beginning
+ * @n: the cpu prior to the place to search (i.e. search starts from @n+1)
+ * @src: cpumask pointer
+ *
+ * Return: next set bit, wrapped if needed, or >= nr_cpu_ids if @src is empty.
+ */
+static __always_inline
+unsigned int cpumask_next_wrap(int n, const struct cpumask *src)
+{
+	/* -1 is a legal arg here. */
+	if (n != -1)
+		cpumask_check(n);
+	return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1);
+}
 
-	return cpumask_first(mask);
+/**
+ * cpumask_random - get random cpu in *src.
+ * @src: cpumask pointer
+ *
+ * Return: random set bit, or >= nr_cpu_ids if @src is empty.
+ */
+static __always_inline
+unsigned int cpumask_random(const struct cpumask *src)
+{
+	return find_random_bit(cpumask_bits(src), nr_cpu_ids);
 }
-#else
-unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap);
-#endif
+
+/**
+ * for_each_cpu - iterate over every cpu in a mask
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask pointer
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu(cpu, mask)				\
+	for_each_set_bit(cpu, cpumask_bits(mask), small_cpumask_bits)
 
 /**
  * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location
@@ -368,19 +445,33 @@ unsigned int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int sta
 	for_each_or_bit(cpu, cpumask_bits(mask1), cpumask_bits(mask2), small_cpumask_bits)
 
 /**
- * cpumask_any_but - return a "random" in a cpumask, but not this one.
+ * for_each_cpu_from - iterate over CPUs present in @mask, from @cpu to the end of @mask.
+ * @cpu: the (optionally unsigned) integer iterator
+ * @mask: the cpumask pointer
+ *
+ * After the loop, cpu is >= nr_cpu_ids.
+ */
+#define for_each_cpu_from(cpu, mask)				\
+	for_each_set_bit_from(cpu, cpumask_bits(mask), small_cpumask_bits)
+
+/**
+ * cpumask_any_but - return an arbitrary cpu in a cpumask, but not this one.
  * @mask: the cpumask to search
  * @cpu: the cpu to ignore.
  *
  * Often used to find any cpu but smp_processor_id() in a mask.
- * Returns >= nr_cpu_ids if no cpus set.
+ * If @cpu == -1, the function is equivalent to cpumask_any().
+ * Return: >= nr_cpu_ids if no cpus set.
  */
-static inline
-unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
+static __always_inline
+unsigned int cpumask_any_but(const struct cpumask *mask, int cpu)
 {
 	unsigned int i;
 
-	cpumask_check(cpu);
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
 	for_each_cpu(i, mask)
 		if (i != cpu)
 			break;
@@ -388,46 +479,85 @@ unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 }
 
 /**
- * cpumask_nth - get the first cpu in a cpumask
- * @srcp: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * cpumask_any_and_but - pick an arbitrary cpu from *mask1 & *mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * If @cpu == -1, the function is equivalent to cpumask_any_and().
+ * Returns >= nr_cpu_ids if no cpus set.
  */
-static inline unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
+static __always_inline
+unsigned int cpumask_any_and_but(const struct cpumask *mask1,
+				 const struct cpumask *mask2,
+				 int cpu)
 {
-	return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
+	unsigned int i;
+
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
+	i = cpumask_first_and(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_and(cpu, mask1, mask2);
 }
 
 /**
- * cpumask_nth_and - get the first cpu in 2 cpumasks
- * @srcp1: the cpumask pointer
- * @srcp2: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * cpumask_any_andnot_but - pick an arbitrary cpu from *mask1 & ~*mask2, but not this one.
+ * @mask1: the first input cpumask
+ * @mask2: the second input cpumask
+ * @cpu: the cpu to ignore
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * If @cpu == -1, the function returns the first matching cpu.
+ * Returns >= nr_cpu_ids if no cpus set.
  */
-static inline
-unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
-							const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_any_andnot_but(const struct cpumask *mask1,
+				    const struct cpumask *mask2,
+				    int cpu)
 {
-	return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
-				small_cpumask_bits, cpumask_check(cpu));
+	unsigned int i;
+
+	/* -1 is a legal arg here. */
+	if (cpu != -1)
+		cpumask_check(cpu);
+
+	i = cpumask_first_andnot(mask1, mask2);
+	if (i != cpu)
+		return i;
+
+	return cpumask_next_andnot(cpu, mask1, mask2);
 }
 
 /**
- * cpumask_nth_andnot - get the first cpu set in 1st cpumask, and clear in 2nd.
+ * cpumask_nth - get the Nth cpu in a cpumask
+ * @srcp: the cpumask pointer
+ * @cpu: the Nth cpu to find, starting from 0
+ *
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
+ */
+static __always_inline
+unsigned int cpumask_nth(unsigned int cpu, const struct cpumask *srcp)
+{
+	return find_nth_bit(cpumask_bits(srcp), small_cpumask_bits, cpumask_check(cpu));
+}
+
+/**
+ * cpumask_nth_and - get the Nth cpu in 2 cpumasks
  * @srcp1: the cpumask pointer
  * @srcp2: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * @cpu: the Nth cpu to find, starting from 0
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
-static inline
-unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
+static __always_inline
+unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 							const struct cpumask *srcp2)
 {
-	return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
+	return find_nth_and_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
 				small_cpumask_bits, cpumask_check(cpu));
 }
 
@@ -436,9 +566,9 @@ unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
  * @srcp1: the cpumask pointer
  * @srcp2: the cpumask pointer
  * @srcp3: the cpumask pointer
- * @cpu: the N'th cpu to find, starting from 0
+ * @cpu: the Nth cpu to find, starting from 0
  *
- * Returns >= nr_cpu_ids if such cpu doesn't exist.
+ * Return: >= nr_cpu_ids if such cpu doesn't exist.
  */
 static __always_inline
 unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp1,
@@ -466,16 +596,30 @@ unsigned int cpumask_nth_and_andnot(unsigned int cpu, const struct cpumask *srcp
  * @cpu: cpu number (< nr_cpu_ids)
  * @dstp: the cpumask pointer
  */
-static __always_inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
-static __always_inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
+static __always_inline
+void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 {
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+/**
+ * cpumask_clear_cpus - clear cpus in a cpumask
+ * @dstp:  the cpumask pointer
+ * @cpu:   cpu number (< nr_cpu_ids)
+ * @ncpus: number of cpus to clear (< nr_cpu_ids)
+ */
+static __always_inline void cpumask_clear_cpus(struct cpumask *dstp,
+						unsigned int cpu, unsigned int ncpus)
+{
+	cpumask_check(cpu + ncpus - 1);
+	bitmap_clear(cpumask_bits(dstp), cpumask_check(cpu), ncpus);
+}
 
 /**
  * cpumask_clear_cpu - clear a cpu in a cpumask
@@ -497,9 +641,10 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp)
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns true if @cpu is set in @cpumask, else returns false
+ * Return: true if @cpu is set in @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask)
 {
 	return test_bit(cpumask_check(cpu), cpumask_bits((cpumask)));
 }
@@ -509,11 +654,12 @@ static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpum
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
- *
  * test_and_set_bit wrapper for cpumasks.
+ *
+ * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -523,11 +669,12 @@ static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cp
  * @cpu: cpu number (< nr_cpu_ids)
  * @cpumask: the cpumask pointer
  *
- * Returns true if @cpu is set in old bitmap of @cpumask, else returns false
- *
  * test_and_clear_bit wrapper for cpumasks.
+ *
+ * Return: true if @cpu is set in old bitmap of @cpumask, else returns false
  */
-static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
+static __always_inline
+bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask)
 {
 	return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask));
 }
@@ -536,7 +683,7 @@ static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *
  * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_setall(struct cpumask *dstp)
+static __always_inline void cpumask_setall(struct cpumask *dstp)
 {
 	if (small_const_nbits(small_cpumask_bits)) {
 		cpumask_bits(dstp)[0] = BITMAP_LAST_WORD_MASK(nr_cpumask_bits);
@@ -549,7 +696,7 @@ static inline void cpumask_setall(struct cpumask *dstp)
  * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask
  * @dstp: the cpumask pointer
  */
-static inline void cpumask_clear(struct cpumask *dstp)
+static __always_inline void cpumask_clear(struct cpumask *dstp)
 {
 	bitmap_zero(cpumask_bits(dstp), large_cpumask_bits);
 }
@@ -560,11 +707,11 @@ static inline void cpumask_clear(struct cpumask *dstp)
  * @src1p: the first input
  * @src2p: the second input
  *
- * If *@dstp is empty, returns false, else returns true
+ * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_and(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -576,22 +723,39 @@ static inline bool cpumask_and(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
-			      const struct cpumask *src2p)
+static __always_inline
+void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p,
+		const struct cpumask *src2p)
 {
 	bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p),
 				      cpumask_bits(src2p), small_cpumask_bits);
 }
 
 /**
+ * cpumask_weighted_or - *dstp = *src1p | *src2p and return the weight of the result
+ * @dstp: the cpumask result
+ * @src1p: the first input
+ * @src2p: the second input
+ *
+ * Return: The number of bits set in the resulting cpumask @dstp
+ */
+static __always_inline
+unsigned int cpumask_weighted_or(struct cpumask *dstp, const struct cpumask *src1p,
+				 const struct cpumask *src2p)
+{
+	return bitmap_weighted_or(cpumask_bits(dstp), cpumask_bits(src1p),
+				  cpumask_bits(src2p), small_cpumask_bits);
+}
+
+/**
  * cpumask_xor - *dstp = *src1p ^ *src2p
  * @dstp: the cpumask result
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_xor(struct cpumask *dstp,
-			       const struct cpumask *src1p,
-			       const struct cpumask *src2p)
+static __always_inline
+void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p,
+		 const struct cpumask *src2p)
 {
 	bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p),
 				       cpumask_bits(src2p), small_cpumask_bits);
@@ -603,11 +767,11 @@ static inline void cpumask_xor(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  *
- * If *@dstp is empty, returns false, else returns true
+ * Return: false if *@dstp is empty, else returns true
  */
-static inline bool cpumask_andnot(struct cpumask *dstp,
-				  const struct cpumask *src1p,
-				  const struct cpumask *src2p)
+static __always_inline
+bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p,
+		    const struct cpumask *src2p)
 {
 	return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
 					  cpumask_bits(src2p), small_cpumask_bits);
@@ -617,9 +781,11 @@ static inline bool cpumask_andnot(struct cpumask *dstp,
  * cpumask_equal - *src1p == *src2p
  * @src1p: the first input
  * @src2p: the second input
+ *
+ * Return: true if the cpumasks are equal, false if not
  */
-static inline bool cpumask_equal(const struct cpumask *src1p,
-				const struct cpumask *src2p)
+static __always_inline
+bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 						 small_cpumask_bits);
@@ -630,10 +796,13 @@ static inline bool cpumask_equal(const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  * @src3p: the third input
+ *
+ * Return: true if first cpumask ORed with second cpumask == third cpumask,
+ *	   otherwise false
  */
-static inline bool cpumask_or_equal(const struct cpumask *src1p,
-				    const struct cpumask *src2p,
-				    const struct cpumask *src3p)
+static __always_inline
+bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p,
+		      const struct cpumask *src3p)
 {
 	return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p),
 			       cpumask_bits(src3p), small_cpumask_bits);
@@ -643,9 +812,12 @@ static inline bool cpumask_or_equal(const struct cpumask *src1p,
  * cpumask_intersects - (*src1p & *src2p) != 0
  * @src1p: the first input
  * @src2p: the second input
+ *
+ * Return: true if first cpumask ANDed with second cpumask is non-empty,
+ *	   otherwise false
  */
-static inline bool cpumask_intersects(const struct cpumask *src1p,
-				     const struct cpumask *src2p)
+static __always_inline
+bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p),
 						      small_cpumask_bits);
@@ -656,10 +828,10 @@ static inline bool cpumask_intersects(const struct cpumask *src1p,
  * @src1p: the first input
  * @src2p: the second input
  *
- * Returns true if *@src1p is a subset of *@src2p, else returns false
+ * Return: true if *@src1p is a subset of *@src2p, else returns false
  */
-static inline bool cpumask_subset(const struct cpumask *src1p,
-				 const struct cpumask *src2p)
+static __always_inline
+bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p)
 {
 	return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p),
 						  small_cpumask_bits);
@@ -668,8 +840,10 @@ static inline bool cpumask_subset(const struct cpumask *src1p,
 /**
  * cpumask_empty - *srcp == 0
  * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear.
+ *
+ * Return: true if srcp is empty (has no bits set), else false
  */
-static inline bool cpumask_empty(const struct cpumask *srcp)
+static __always_inline bool cpumask_empty(const struct cpumask *srcp)
 {
 	return bitmap_empty(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -677,8 +851,10 @@ static inline bool cpumask_empty(const struct cpumask *srcp)
 /**
  * cpumask_full - *srcp == 0xFFFFFFFF...
  * @srcp: the cpumask to that all cpus < nr_cpu_ids are set.
+ *
+ * Return: true if srcp is full (has all bits set), else false
  */
-static inline bool cpumask_full(const struct cpumask *srcp)
+static __always_inline bool cpumask_full(const struct cpumask *srcp)
 {
 	return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits);
 }
@@ -686,8 +862,10 @@ static inline bool cpumask_full(const struct cpumask *srcp)
 /**
  * cpumask_weight - Count of bits in *srcp
  * @srcp: the cpumask to count bits (< nr_cpu_ids) in.
+ *
+ * Return: count of bits set in *srcp
  */
-static inline unsigned int cpumask_weight(const struct cpumask *srcp)
+static __always_inline unsigned int cpumask_weight(const struct cpumask *srcp)
 {
 	return bitmap_weight(cpumask_bits(srcp), small_cpumask_bits);
 }
@@ -696,21 +874,37 @@ static inline unsigned int cpumask_weight(const struct cpumask *srcp)
  * cpumask_weight_and - Count of bits in (*srcp1 & *srcp2)
  * @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
  * @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
+ *
+ * Return: count of bits set in both *srcp1 and *srcp2
  */
-static inline unsigned int cpumask_weight_and(const struct cpumask *srcp1,
-						const struct cpumask *srcp2)
+static __always_inline
+unsigned int cpumask_weight_and(const struct cpumask *srcp1, const struct cpumask *srcp2)
 {
 	return bitmap_weight_and(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
 }
 
 /**
+ * cpumask_weight_andnot - Count of bits in (*srcp1 & ~*srcp2)
+ * @srcp1: the cpumask to count bits (< nr_cpu_ids) in.
+ * @srcp2: the cpumask to count bits (< nr_cpu_ids) in.
+ *
+ * Return: count of bits set in both *srcp1 and *srcp2
+ */
+static __always_inline
+unsigned int cpumask_weight_andnot(const struct cpumask *srcp1,
+				   const struct cpumask *srcp2)
+{
+	return bitmap_weight_andnot(cpumask_bits(srcp1), cpumask_bits(srcp2), small_cpumask_bits);
+}
+
+/**
  * cpumask_shift_right - *dstp = *srcp >> n
  * @dstp: the cpumask result
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_right(struct cpumask *dstp,
-				       const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					       small_cpumask_bits);
@@ -722,8 +916,8 @@ static inline void cpumask_shift_right(struct cpumask *dstp,
  * @srcp: the input to shift
  * @n: the number of bits to shift by
  */
-static inline void cpumask_shift_left(struct cpumask *dstp,
-				      const struct cpumask *srcp, int n)
+static __always_inline
+void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n)
 {
 	bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n,
 					      nr_cpumask_bits);
@@ -734,26 +928,26 @@ static inline void cpumask_shift_left(struct cpumask *dstp,
  * @dstp: the result
  * @srcp: the input cpumask
  */
-static inline void cpumask_copy(struct cpumask *dstp,
-				const struct cpumask *srcp)
+static __always_inline
+void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp)
 {
 	bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), large_cpumask_bits);
 }
 
 /**
- * cpumask_any - pick a "random" cpu from *srcp
+ * cpumask_any - pick an arbitrary cpu from *srcp
  * @srcp: the input cpumask
  *
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
 #define cpumask_any(srcp) cpumask_first(srcp)
 
 /**
- * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2
+ * cpumask_any_and - pick an arbitrary cpu from *mask1 & *mask2
  * @mask1: the first input cpumask
  * @mask2: the second input cpumask
  *
- * Returns >= nr_cpu_ids if no cpus set.
+ * Return: >= nr_cpu_ids if no cpus set.
  */
 #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2))
 
@@ -769,10 +963,10 @@ static inline void cpumask_copy(struct cpumask *dstp,
  * @len: the length of the buffer
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -783,10 +977,10 @@ static inline int cpumask_parse_user(const char __user *buf, int len,
  * @len: the length of the buffer
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parselist_user(const char __user *buf, int len,
-				     struct cpumask *dstp)
+static __always_inline
+int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp)
 {
 	return bitmap_parselist_user(buf, len, cpumask_bits(dstp),
 				     nr_cpumask_bits);
@@ -797,9 +991,9 @@ static inline int cpumask_parselist_user(const char __user *buf, int len,
  * @buf: the buffer to extract from
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
-static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpumask_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parse(buf, UINT_MAX, cpumask_bits(dstp), nr_cpumask_bits);
 }
@@ -809,70 +1003,32 @@ static inline int cpumask_parse(const char *buf, struct cpumask *dstp)
  * @buf: the buffer to extract from
  * @dstp: the cpumask to set.
  *
- * Returns -errno, or 0 for success.
+ * Return: -errno, or 0 for success.
  */
-static inline int cpulist_parse(const char *buf, struct cpumask *dstp)
+static __always_inline int cpulist_parse(const char *buf, struct cpumask *dstp)
 {
 	return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits);
 }
 
 /**
- * cpumask_size - size to allocate for a 'struct cpumask' in bytes
+ * cpumask_size - calculate size to allocate for a 'struct cpumask' in bytes
+ *
+ * Return: size to allocate for a &struct cpumask in bytes
  */
-static inline unsigned int cpumask_size(void)
+static __always_inline unsigned int cpumask_size(void)
 {
-	return BITS_TO_LONGS(large_cpumask_bits) * sizeof(long);
+	return bitmap_size(large_cpumask_bits);
 }
 
-/*
- * cpumask_var_t: struct cpumask for stack usage.
- *
- * Oh, the wicked games we play!  In order to make kernel coding a
- * little more difficult, we typedef cpumask_var_t to an array or a
- * pointer: doing &mask on an array is a noop, so it still works.
- *
- * ie.
- *	cpumask_var_t tmpmask;
- *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
- *		return -ENOMEM;
- *
- *	  ... use 'tmpmask' like a normal struct cpumask * ...
- *
- *	free_cpumask_var(tmpmask);
- *
- *
- * However, one notable exception is there. alloc_cpumask_var() allocates
- * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has
- * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t.
- *
- *	cpumask_var_t tmpmask;
- *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
- *		return -ENOMEM;
- *
- *	var = *tmpmask;
- *
- * This code makes NR_CPUS length memcopy and brings to a memory corruption.
- * cpumask_copy() provide safe copy functionality.
- *
- * Note that there is another evil here: If you define a cpumask_var_t
- * as a percpu variable then the way to obtain the address of the cpumask
- * structure differently influences what this_cpu_* operation needs to be
- * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
- * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
- * other type of cpumask_var_t implementation is configured.
- *
- * Please also note that __cpumask_var_read_mostly can be used to declare
- * a cpumask_var_t variable itself (not its content) as read mostly.
- */
 #ifdef CONFIG_CPUMASK_OFFSTACK
-typedef struct cpumask *cpumask_var_t;
 
 #define this_cpu_cpumask_var_ptr(x)	this_cpu_read(x)
 #define __cpumask_var_read_mostly	__read_mostly
+#define CPUMASK_VAR_NULL		NULL
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
 	return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
@@ -887,14 +1043,16 @@ bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
  * a nop returning a constant 1 (in <linux/cpumask.h>).
  *
  * See alloc_cpumask_var_node.
+ *
+ * Return: %true if allocation succeeded, %false if not
  */
-static inline
+static __always_inline
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
 }
 
-static inline
+static __always_inline
 bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return alloc_cpumask_var(mask, flags | __GFP_ZERO);
@@ -904,59 +1062,61 @@ void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpumask_available(cpumask_var_t mask)
 {
 	return mask != NULL;
 }
 
 #else
-typedef struct cpumask cpumask_var_t[1];
 
 #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x)
 #define __cpumask_var_read_mostly
+#define CPUMASK_VAR_NULL {}
 
-static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	return true;
 }
 
-static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+static __always_inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 					  int node)
 {
 	return true;
 }
 
-static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+static __always_inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
 	cpumask_clear(*mask);
 	return true;
 }
 
-static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+static __always_inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
 					  int node)
 {
 	cpumask_clear(*mask);
 	return true;
 }
 
-static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
+static __always_inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 }
 
-static inline void free_cpumask_var(cpumask_var_t mask)
+static __always_inline void free_cpumask_var(cpumask_var_t mask)
 {
 }
 
-static inline void free_bootmem_cpumask_var(cpumask_var_t mask)
+static __always_inline void free_bootmem_cpumask_var(cpumask_var_t mask)
 {
 }
 
-static inline bool cpumask_available(cpumask_var_t mask)
+static __always_inline bool cpumask_available(cpumask_var_t mask)
 {
 	return true;
 }
 #endif /* CONFIG_CPUMASK_OFFSTACK */
 
+DEFINE_FREE(free_cpumask_var, struct cpumask *, if (_T) free_cpumask_var(_T));
+
 /* It's common to want to use cpu_all_mask in struct member initializers,
  * so it has to refer to an address rather than a pointer. */
 extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
@@ -970,62 +1130,43 @@ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS);
 #define for_each_possible_cpu(cpu)	for ((cpu) = 0; (cpu) < 1; (cpu)++)
 #define for_each_online_cpu(cpu)	for ((cpu) = 0; (cpu) < 1; (cpu)++)
 #define for_each_present_cpu(cpu)	for ((cpu) = 0; (cpu) < 1; (cpu)++)
+
+#define for_each_possible_cpu_wrap(cpu, start)	\
+	for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++)
+#define for_each_online_cpu_wrap(cpu, start)	\
+	for ((void)(start), (cpu) = 0; (cpu) < 1; (cpu)++)
 #else
 #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask)
 #define for_each_online_cpu(cpu)   for_each_cpu((cpu), cpu_online_mask)
+#define for_each_enabled_cpu(cpu)   for_each_cpu((cpu), cpu_enabled_mask)
 #define for_each_present_cpu(cpu)  for_each_cpu((cpu), cpu_present_mask)
+
+#define for_each_possible_cpu_wrap(cpu, start)	\
+	for_each_cpu_wrap((cpu), cpu_possible_mask, (start))
+#define for_each_online_cpu_wrap(cpu, start)	\
+	for_each_cpu_wrap((cpu), cpu_online_mask, (start))
 #endif
 
 /* Wrappers for arch boot code to manipulate normally-constant masks */
 void init_cpu_present(const struct cpumask *src);
 void init_cpu_possible(const struct cpumask *src);
-void init_cpu_online(const struct cpumask *src);
 
-static inline void reset_cpu_possible_mask(void)
-{
-	bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS);
-}
+#define assign_cpu(cpu, mask, val)	\
+	assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
-static inline void
-set_cpu_possible(unsigned int cpu, bool possible)
-{
-	if (possible)
-		cpumask_set_cpu(cpu, &__cpu_possible_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_possible_mask);
-}
+#define __assign_cpu(cpu, mask, val)	\
+	__assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val))
 
-static inline void
-set_cpu_present(unsigned int cpu, bool present)
-{
-	if (present)
-		cpumask_set_cpu(cpu, &__cpu_present_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_present_mask);
-}
+#define set_cpu_enabled(cpu, enabled)	assign_cpu((cpu), &__cpu_enabled_mask, (enabled))
+#define set_cpu_present(cpu, present)	assign_cpu((cpu), &__cpu_present_mask, (present))
+#define set_cpu_active(cpu, active)	assign_cpu((cpu), &__cpu_active_mask, (active))
+#define set_cpu_dying(cpu, dying)	assign_cpu((cpu), &__cpu_dying_mask, (dying))
 
 void set_cpu_online(unsigned int cpu, bool online);
-
-static inline void
-set_cpu_active(unsigned int cpu, bool active)
-{
-	if (active)
-		cpumask_set_cpu(cpu, &__cpu_active_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_active_mask);
-}
-
-static inline void
-set_cpu_dying(unsigned int cpu, bool dying)
-{
-	if (dying)
-		cpumask_set_cpu(cpu, &__cpu_dying_mask);
-	else
-		cpumask_clear_cpu(cpu, &__cpu_dying_mask);
-}
+void set_cpu_possible(unsigned int cpu, bool possible);
 
 /**
- * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask *
+ * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask *
  * @bitmap: the bitmap
  *
  * There are a few places where cpumask_var_t isn't appropriate and
@@ -1038,7 +1179,7 @@ set_cpu_dying(unsigned int cpu, bool dying)
 	((struct cpumask *)(1 ? (bitmap)				\
 			    : (void *)sizeof(__check_is_bitmap(bitmap))))
 
-static inline int __check_is_bitmap(const unsigned long *bitmap)
+static __always_inline int __check_is_bitmap(const unsigned long *bitmap)
 {
 	return 1;
 }
@@ -1053,7 +1194,7 @@ static inline int __check_is_bitmap(const unsigned long *bitmap)
 extern const unsigned long
 	cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)];
 
-static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
+static __always_inline const struct cpumask *get_cpu_mask(unsigned int cpu)
 {
 	const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG];
 	p -= cpu / BITS_PER_LONG;
@@ -1068,36 +1209,49 @@ static inline const struct cpumask *get_cpu_mask(unsigned int cpu)
  * interface gives only a momentary snapshot and is not protected against
  * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held
  * region.
+ *
+ * Return: momentary snapshot of the number of online CPUs
  */
 static __always_inline unsigned int num_online_cpus(void)
 {
-	return arch_atomic_read(&__num_online_cpus);
+	return raw_atomic_read(&__num_online_cpus);
 }
-#define num_possible_cpus()	cpumask_weight(cpu_possible_mask)
+
+static __always_inline unsigned int num_possible_cpus(void)
+{
+	return __num_possible_cpus;
+}
+
+#define num_enabled_cpus()	cpumask_weight(cpu_enabled_mask)
 #define num_present_cpus()	cpumask_weight(cpu_present_mask)
 #define num_active_cpus()	cpumask_weight(cpu_active_mask)
 
-static inline bool cpu_online(unsigned int cpu)
+static __always_inline bool cpu_online(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_online_mask);
 }
 
-static inline bool cpu_possible(unsigned int cpu)
+static __always_inline bool cpu_enabled(unsigned int cpu)
+{
+	return cpumask_test_cpu(cpu, cpu_enabled_mask);
+}
+
+static __always_inline bool cpu_possible(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_possible_mask);
 }
 
-static inline bool cpu_present(unsigned int cpu)
+static __always_inline bool cpu_present(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_present_mask);
 }
 
-static inline bool cpu_active(unsigned int cpu)
+static __always_inline bool cpu_active(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_active_mask);
 }
 
-static inline bool cpu_dying(unsigned int cpu)
+static __always_inline bool cpu_dying(unsigned int cpu)
 {
 	return cpumask_test_cpu(cpu, cpu_dying_mask);
 }
@@ -1106,30 +1260,36 @@ static inline bool cpu_dying(unsigned int cpu)
 
 #define num_online_cpus()	1U
 #define num_possible_cpus()	1U
+#define num_enabled_cpus()	1U
 #define num_present_cpus()	1U
 #define num_active_cpus()	1U
 
-static inline bool cpu_online(unsigned int cpu)
+static __always_inline bool cpu_online(unsigned int cpu)
+{
+	return cpu == 0;
+}
+
+static __always_inline bool cpu_possible(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_possible(unsigned int cpu)
+static __always_inline bool cpu_enabled(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_present(unsigned int cpu)
+static __always_inline bool cpu_present(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_active(unsigned int cpu)
+static __always_inline bool cpu_active(unsigned int cpu)
 {
 	return cpu == 0;
 }
 
-static inline bool cpu_dying(unsigned int cpu)
+static __always_inline bool cpu_dying(unsigned int cpu)
 {
 	return false;
 }
@@ -1160,10 +1320,10 @@ static inline bool cpu_dying(unsigned int cpu)
  * @mask: the cpumask to copy
  * @buf: the buffer to copy into
  *
- * Returns the length of the (null-terminated) @buf string, zero if
+ * Return: the length of the (null-terminated) @buf string, zero if
  * nothing is copied.
  */
-static inline ssize_t
+static __always_inline ssize_t
 cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
 {
 	return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask),
@@ -1183,12 +1343,12 @@ cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask)
  * cpumask; Typically used by bin_attribute to export cpumask bitmask
  * ABI.
  *
- * Returns the length of how many bytes have been copied, excluding
+ * Return: the length of how many bytes have been copied, excluding
  * terminating '\0'.
  */
-static inline ssize_t
-cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
-		loff_t off, size_t count)
+static __always_inline
+ssize_t cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
+				    loff_t off, size_t count)
 {
 	return bitmap_print_bitmask_to_buf(buf, cpumask_bits(mask),
 				   nr_cpu_ids, off, count) - 1;
@@ -1197,13 +1357,20 @@ cpumap_print_bitmask_to_buf(char *buf, const struct cpumask *mask,
 /**
  * cpumap_print_list_to_buf  - copies the cpumask into the buffer as
  *	comma-separated list of cpus
+ * @buf: the buffer to copy into
+ * @mask: the cpumask to copy
+ * @off: in the string from which we are copying, we copy to @buf
+ * @count: the maximum number of bytes to print
  *
  * Everything is same with the above cpumap_print_bitmask_to_buf()
  * except the print format.
+ *
+ * Return: the length of how many bytes have been copied, excluding
+ * terminating '\0'.
  */
-static inline ssize_t
-cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
-		loff_t off, size_t count)
+static __always_inline
+ssize_t cpumap_print_list_to_buf(char *buf, const struct cpumask *mask,
+				 loff_t off, size_t count)
 {
 	return bitmap_print_list_to_buf(buf, cpumask_bits(mask),
 				   nr_cpu_ids, off, count) - 1;
diff --git a/include/linux/cpumask_types.h b/include/linux/cpumask_types.h
new file mode 100644
index 000000000000..461ed1b6bcdb
--- /dev/null
+++ b/include/linux/cpumask_types.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_CPUMASK_TYPES_H
+#define __LINUX_CPUMASK_TYPES_H
+
+#include <linux/bitops.h>
+#include <linux/threads.h>
+
+/* Don't assign or return these: may not be this big! */
+typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t;
+
+/**
+ * cpumask_bits - get the bits in a cpumask
+ * @maskp: the struct cpumask *
+ *
+ * You should only assume nr_cpu_ids bits of this mask are valid.  This is
+ * a macro so it's const-correct.
+ */
+#define cpumask_bits(maskp) ((maskp)->bits)
+
+/*
+ * cpumask_var_t: struct cpumask for stack usage.
+ *
+ * Oh, the wicked games we play!  In order to make kernel coding a
+ * little more difficult, we typedef cpumask_var_t to an array or a
+ * pointer: doing &mask on an array is a noop, so it still works.
+ *
+ * i.e.
+ *	cpumask_var_t tmpmask;
+ *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ *		return -ENOMEM;
+ *
+ *	  ... use 'tmpmask' like a normal struct cpumask * ...
+ *
+ *	free_cpumask_var(tmpmask);
+ *
+ *
+ * However, one notable exception is there. alloc_cpumask_var() allocates
+ * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has
+ * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t.
+ *
+ *	cpumask_var_t tmpmask;
+ *	if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL))
+ *		return -ENOMEM;
+ *
+ *	var = *tmpmask;
+ *
+ * This code makes NR_CPUS length memcopy and brings to a memory corruption.
+ * cpumask_copy() provide safe copy functionality.
+ *
+ * Note that there is another evil here: If you define a cpumask_var_t
+ * as a percpu variable then the way to obtain the address of the cpumask
+ * structure differently influences what this_cpu_* operation needs to be
+ * used. Please use this_cpu_cpumask_var_t in those cases. The direct use
+ * of this_cpu_ptr() or this_cpu_read() will lead to failures when the
+ * other type of cpumask_var_t implementation is configured.
+ *
+ * Please also note that __cpumask_var_read_mostly can be used to declare
+ * a cpumask_var_t variable itself (not its content) as read mostly.
+ */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+typedef struct cpumask *cpumask_var_t;
+#else
+typedef struct cpumask cpumask_var_t[1];
+#endif /* CONFIG_CPUMASK_OFFSTACK */
+
+#endif /* __LINUX_CPUMASK_TYPES_H */
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 980b76a1237e..a98d3330385c 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -70,21 +70,24 @@ extern int cpuset_init(void);
 extern void cpuset_init_smp(void);
 extern void cpuset_force_rebuild(void);
 extern void cpuset_update_active_cpus(void);
-extern void cpuset_wait_for_hotplug(void);
-extern void cpuset_read_lock(void);
-extern void cpuset_read_unlock(void);
+extern void inc_dl_tasks_cs(struct task_struct *task);
+extern void dec_dl_tasks_cs(struct task_struct *task);
+extern void cpuset_lock(void);
+extern void cpuset_unlock(void);
+extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
+extern bool cpuset_cpu_is_isolated(int cpu);
 extern nodemask_t cpuset_mems_allowed(struct task_struct *p);
 #define cpuset_current_mems_allowed (current->mems_allowed)
 void cpuset_init_current_mems_allowed(void);
 int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
-extern bool cpuset_node_allowed(int node, gfp_t gfp_mask);
+extern bool cpuset_current_node_allowed(int node, gfp_t gfp_mask);
 
 static inline bool __cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 {
-	return cpuset_node_allowed(zone_to_nid(z), gfp_mask);
+	return cpuset_current_node_allowed(zone_to_nid(z), gfp_mask);
 }
 
 static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
@@ -97,6 +100,7 @@ static inline bool cpuset_zone_allowed(struct zone *z, gfp_t gfp_mask)
 extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 					  const struct task_struct *tsk2);
 
+#ifdef CONFIG_CPUSETS_V1
 #define cpuset_memory_pressure_bump() 				\
 	do {							\
 		if (cpuset_memory_pressure_enabled)		\
@@ -104,6 +108,9 @@ extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
 	} while (0)
 extern int cpuset_memory_pressure_enabled;
 extern void __cpuset_memory_pressure_bump(void);
+#else
+static inline void cpuset_memory_pressure_bump(void) { }
+#endif
 
 extern void cpuset_task_status_allowed(struct seq_file *m,
 					struct task_struct *task);
@@ -111,23 +118,19 @@ extern int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
 			    struct pid *pid, struct task_struct *tsk);
 
 extern int cpuset_mem_spread_node(void);
-extern int cpuset_slab_spread_node(void);
 
 static inline int cpuset_do_page_mem_spread(void)
 {
 	return task_spread_page(current);
 }
 
-static inline int cpuset_do_slab_mem_spread(void)
-{
-	return task_spread_slab(current);
-}
-
 extern bool current_cpuset_is_being_rebound(void);
 
+extern void dl_rebuild_rd_accounting(void);
 extern void rebuild_sched_domains(void);
 
 extern void cpuset_print_current_mems_allowed(void);
+extern void cpuset_reset_sched_domains(void);
 
 /*
  * read_mems_allowed_begin is required when making decisions involving
@@ -171,6 +174,7 @@ static inline void set_mems_allowed(nodemask_t nodemask)
 	task_unlock(current);
 }
 
+extern bool cpuset_node_allowed(struct cgroup *cgroup, int nid);
 #else /* !CONFIG_CPUSETS */
 
 static inline bool cpusets_enabled(void) { return false; }
@@ -187,15 +191,21 @@ static inline void cpuset_update_active_cpus(void)
 	partition_sched_domains(1, NULL, NULL);
 }
 
-static inline void cpuset_wait_for_hotplug(void) { }
+static inline void inc_dl_tasks_cs(struct task_struct *task) { }
+static inline void dec_dl_tasks_cs(struct task_struct *task) { }
+static inline void cpuset_lock(void) { }
+static inline void cpuset_unlock(void) { }
 
-static inline void cpuset_read_lock(void) { }
-static inline void cpuset_read_unlock(void) { }
+static inline void cpuset_cpus_allowed_locked(struct task_struct *p,
+					struct cpumask *mask)
+{
+	cpumask_copy(mask, task_cpu_possible_mask(p));
+}
 
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
-	cpumask_copy(mask, task_cpu_possible_mask(p));
+	cpuset_cpus_allowed_locked(p, mask);
 }
 
 static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
@@ -203,6 +213,11 @@ static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)
 	return false;
 }
 
+static inline bool cpuset_cpu_is_isolated(int cpu)
+{
+	return false;
+}
+
 static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)
 {
 	return node_possible_map;
@@ -244,27 +259,26 @@ static inline int cpuset_mem_spread_node(void)
 	return 0;
 }
 
-static inline int cpuset_slab_spread_node(void)
+static inline int cpuset_do_page_mem_spread(void)
 {
 	return 0;
 }
 
-static inline int cpuset_do_page_mem_spread(void)
+static inline bool current_cpuset_is_being_rebound(void)
 {
-	return 0;
+	return false;
 }
 
-static inline int cpuset_do_slab_mem_spread(void)
+static inline void dl_rebuild_rd_accounting(void)
 {
-	return 0;
 }
 
-static inline bool current_cpuset_is_being_rebound(void)
+static inline void rebuild_sched_domains(void)
 {
-	return false;
+	partition_sched_domains(1, NULL, NULL);
 }
 
-static inline void rebuild_sched_domains(void)
+static inline void cpuset_reset_sched_domains(void)
 {
 	partition_sched_domains(1, NULL, NULL);
 }
@@ -287,6 +301,10 @@ static inline bool read_mems_allowed_retry(unsigned int seq)
 	return false;
 }
 
+static inline bool cpuset_node_allowed(struct cgroup *cgroup, int nid)
+{
+	return true;
+}
 #endif /* !CONFIG_CPUSETS */
 
 #endif /* _LINUX_CPUSET_H */
diff --git a/include/linux/crash_core.h b/include/linux/crash_core.h
index de62a722431e..d35726d6a415 100644
--- a/include/linux/crash_core.h
+++ b/include/linux/crash_core.h
@@ -6,82 +6,94 @@
 #include <linux/elfcore.h>
 #include <linux/elf.h>
 
-#define CRASH_CORE_NOTE_NAME	   "CORE"
-#define CRASH_CORE_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4)
-#define CRASH_CORE_NOTE_NAME_BYTES ALIGN(sizeof(CRASH_CORE_NOTE_NAME), 4)
-#define CRASH_CORE_NOTE_DESC_BYTES ALIGN(sizeof(struct elf_prstatus), 4)
+struct kimage;
 
+struct crash_mem {
+	unsigned int max_nr_ranges;
+	unsigned int nr_ranges;
+	struct range ranges[] __counted_by(max_nr_ranges);
+};
+
+#ifdef CONFIG_CRASH_DUMP
+
+int crash_shrink_memory(unsigned long new_size);
+ssize_t crash_get_memory_size(void);
+
+#ifndef arch_kexec_protect_crashkres
 /*
- * The per-cpu notes area is a list of notes terminated by a "NULL"
- * note header.  For kdump, the code in vmcore.c runs in the context
- * of the second kernel to combine them into one note.
+ * Protection mechanism for crashkernel reserved memory after
+ * the kdump kernel is loaded.
+ *
+ * Provide an empty default implementation here -- architecture
+ * code may override this
  */
-#define CRASH_CORE_NOTE_BYTES	   ((CRASH_CORE_NOTE_HEAD_BYTES * 2) +	\
-				     CRASH_CORE_NOTE_NAME_BYTES +	\
-				     CRASH_CORE_NOTE_DESC_BYTES)
-
-#define VMCOREINFO_BYTES	   PAGE_SIZE
-#define VMCOREINFO_NOTE_NAME	   "VMCOREINFO"
-#define VMCOREINFO_NOTE_NAME_BYTES ALIGN(sizeof(VMCOREINFO_NOTE_NAME), 4)
-#define VMCOREINFO_NOTE_SIZE	   ((CRASH_CORE_NOTE_HEAD_BYTES * 2) +	\
-				     VMCOREINFO_NOTE_NAME_BYTES +	\
-				     VMCOREINFO_BYTES)
-
-typedef u32 note_buf_t[CRASH_CORE_NOTE_BYTES/4];
-
-void crash_update_vmcoreinfo_safecopy(void *ptr);
-void crash_save_vmcoreinfo(void);
-void arch_crash_save_vmcoreinfo(void);
-__printf(1, 2)
-void vmcoreinfo_append_str(const char *fmt, ...);
-phys_addr_t paddr_vmcoreinfo_note(void);
-
-#define VMCOREINFO_OSRELEASE(value) \
-	vmcoreinfo_append_str("OSRELEASE=%s\n", value)
-#define VMCOREINFO_BUILD_ID()						\
-	({								\
-		static_assert(sizeof(vmlinux_build_id) == 20);		\
-		vmcoreinfo_append_str("BUILD-ID=%20phN\n", vmlinux_build_id); \
-	})
-
-#define VMCOREINFO_PAGESIZE(value) \
-	vmcoreinfo_append_str("PAGESIZE=%ld\n", value)
-#define VMCOREINFO_SYMBOL(name) \
-	vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)&name)
-#define VMCOREINFO_SYMBOL_ARRAY(name) \
-	vmcoreinfo_append_str("SYMBOL(%s)=%lx\n", #name, (unsigned long)name)
-#define VMCOREINFO_SIZE(name) \
-	vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
-			      (unsigned long)sizeof(name))
-#define VMCOREINFO_STRUCT_SIZE(name) \
-	vmcoreinfo_append_str("SIZE(%s)=%lu\n", #name, \
-			      (unsigned long)sizeof(struct name))
-#define VMCOREINFO_OFFSET(name, field) \
-	vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
-			      (unsigned long)offsetof(struct name, field))
-#define VMCOREINFO_TYPE_OFFSET(name, field) \
-	vmcoreinfo_append_str("OFFSET(%s.%s)=%lu\n", #name, #field, \
-			      (unsigned long)offsetof(name, field))
-#define VMCOREINFO_LENGTH(name, value) \
-	vmcoreinfo_append_str("LENGTH(%s)=%lu\n", #name, (unsigned long)value)
-#define VMCOREINFO_NUMBER(name) \
-	vmcoreinfo_append_str("NUMBER(%s)=%ld\n", #name, (long)name)
-#define VMCOREINFO_CONFIG(name) \
-	vmcoreinfo_append_str("CONFIG_%s=y\n", #name)
-
-extern unsigned char *vmcoreinfo_data;
-extern size_t vmcoreinfo_size;
-extern u32 *vmcoreinfo_note;
-
-Elf_Word *append_elf_note(Elf_Word *buf, char *name, unsigned int type,
-			  void *data, size_t data_len);
-void final_note(Elf_Word *buf);
-
-int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
-		unsigned long long *crash_size, unsigned long long *crash_base);
-int parse_crashkernel_high(char *cmdline, unsigned long long system_ram,
-		unsigned long long *crash_size, unsigned long long *crash_base);
-int parse_crashkernel_low(char *cmdline, unsigned long long system_ram,
-		unsigned long long *crash_size, unsigned long long *crash_base);
+static inline void arch_kexec_protect_crashkres(void) { }
+#endif
+
+#ifndef arch_kexec_unprotect_crashkres
+static inline void arch_kexec_unprotect_crashkres(void) { }
+#endif
+
+#ifdef CONFIG_CRASH_DM_CRYPT
+int crash_load_dm_crypt_keys(struct kimage *image);
+ssize_t dm_crypt_keys_read(char *buf, size_t count, u64 *ppos);
+#else
+static inline int crash_load_dm_crypt_keys(struct kimage *image) {return 0; }
+#endif
+
+#ifndef arch_crash_handle_hotplug_event
+static inline void arch_crash_handle_hotplug_event(struct kimage *image, void *arg) { }
+#endif
+
+int crash_check_hotplug_support(void);
+
+#ifndef arch_crash_hotplug_support
+static inline int arch_crash_hotplug_support(struct kimage *image, unsigned long kexec_flags)
+{
+	return 0;
+}
+#endif
+
+#ifndef crash_get_elfcorehdr_size
+static inline unsigned int crash_get_elfcorehdr_size(void) { return 0; }
+#endif
+
+/* Alignment required for elf header segment */
+#define ELF_CORE_HEADER_ALIGN   4096
+
+extern int crash_exclude_mem_range(struct crash_mem *mem,
+				   unsigned long long mstart,
+				   unsigned long long mend);
+extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
+				       void **addr, unsigned long *sz);
+
+struct kimage;
+struct kexec_segment;
+
+#define KEXEC_CRASH_HP_NONE			0
+#define KEXEC_CRASH_HP_ADD_CPU			1
+#define KEXEC_CRASH_HP_REMOVE_CPU		2
+#define KEXEC_CRASH_HP_ADD_MEMORY		3
+#define KEXEC_CRASH_HP_REMOVE_MEMORY		4
+#define KEXEC_CRASH_HP_INVALID_CPU		-1U
+
+extern void __crash_kexec(struct pt_regs *regs);
+extern void crash_kexec(struct pt_regs *regs);
+int kexec_should_crash(struct task_struct *p);
+int kexec_crash_loaded(void);
+void crash_save_cpu(struct pt_regs *regs, int cpu);
+extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
+
+#else /* !CONFIG_CRASH_DUMP*/
+struct pt_regs;
+struct task_struct;
+struct kimage;
+static inline void __crash_kexec(struct pt_regs *regs) { }
+static inline void crash_kexec(struct pt_regs *regs) { }
+static inline int kexec_should_crash(struct task_struct *p) { return 0; }
+static inline int kexec_crash_loaded(void) { return 0; }
+static inline void crash_save_cpu(struct pt_regs *regs, int cpu) {};
+static inline int kimage_crash_copy_vmcoreinfo(struct kimage *image) { return 0; };
+#endif /* CONFIG_CRASH_DUMP*/
 
 #endif /* LINUX_CRASH_CORE_H */
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index 0f3a656293b0..dd6fc3b2133b 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -15,11 +15,15 @@
 extern unsigned long long elfcorehdr_addr;
 extern unsigned long long elfcorehdr_size;
 
+extern unsigned long long dm_crypt_keys_addr;
+
 #ifdef CONFIG_CRASH_DUMP
 extern int elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size);
 extern void elfcorehdr_free(unsigned long long addr);
 extern ssize_t elfcorehdr_read(char *buf, size_t count, u64 *ppos);
 extern ssize_t elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+void elfcorehdr_fill_device_ram_ptload_elf64(Elf64_Phdr *phdr,
+		unsigned long long paddr, unsigned long long size);
 extern int remap_oldmem_pfn_range(struct vm_area_struct *vma,
 				  unsigned long from, unsigned long pfn,
 				  unsigned long size, pgprot_t prot);
@@ -50,6 +54,7 @@ void vmcore_cleanup(void);
 #define vmcore_elf64_check_arch(x) (elf_check_arch(x) || vmcore_elf_check_arch_cross(x))
 #endif
 
+#ifndef is_kdump_kernel
 /*
  * is_kdump_kernel() checks whether this kernel is booting after a panic of
  * previous kernel or not. This is determined by checking if previous kernel
@@ -64,6 +69,7 @@ static inline bool is_kdump_kernel(void)
 {
 	return elfcorehdr_addr != ELFCORE_ADDR_MAX;
 }
+#endif
 
 /* is_vmcore_usable() checks if the kernel is booting after a panic and
  * the vmcore region is usable.
@@ -75,7 +81,8 @@ static inline bool is_kdump_kernel(void)
 
 static inline int is_vmcore_usable(void)
 {
-	return is_kdump_kernel() && elfcorehdr_addr != ELFCORE_ADDR_ERR ? 1 : 0;
+	return elfcorehdr_addr != ELFCORE_ADDR_ERR &&
+		elfcorehdr_addr != ELFCORE_ADDR_MAX ? 1 : 0;
 }
 
 /* vmcore_unusable() marks the vmcore as unusable,
@@ -84,8 +91,7 @@ static inline int is_vmcore_usable(void)
 
 static inline void vmcore_unusable(void)
 {
-	if (is_kdump_kernel())
-		elfcorehdr_addr = ELFCORE_ADDR_ERR;
+	elfcorehdr_addr = ELFCORE_ADDR_ERR;
 }
 
 /**
@@ -97,6 +103,12 @@ static inline void vmcore_unusable(void)
  *              indicated in the vmcore instead. For example, a ballooned page
  *              contains no data and reading from such a page will cause high
  *              load in the hypervisor.
+ * @get_device_ram: query RAM ranges that can only be detected by device
+ *   drivers, such as the virtio-mem driver, so they can be included in
+ *   the crash dump on architectures that allocate the elfcore hdr in the dump
+ *   ("2nd") kernel. Indicated RAM ranges may contain holes to reduce the
+ *   total number of ranges; such holes can be detected using the pfn_is_ram
+ *   callback just like for other RAM.
  * @next: List head to manage registered callbacks internally; initialized by
  *        register_vmcore_cb().
  *
@@ -107,11 +119,44 @@ static inline void vmcore_unusable(void)
  */
 struct vmcore_cb {
 	bool (*pfn_is_ram)(struct vmcore_cb *cb, unsigned long pfn);
+	int (*get_device_ram)(struct vmcore_cb *cb, struct list_head *list);
 	struct list_head next;
 };
 extern void register_vmcore_cb(struct vmcore_cb *cb);
 extern void unregister_vmcore_cb(struct vmcore_cb *cb);
 
+struct vmcore_range {
+	struct list_head list;
+	unsigned long long paddr;
+	unsigned long long size;
+	loff_t offset;
+};
+
+/* Allocate a vmcore range and add it to the list. */
+static inline int vmcore_alloc_add_range(struct list_head *list,
+		unsigned long long paddr, unsigned long long size)
+{
+	struct vmcore_range *m = kzalloc(sizeof(*m), GFP_KERNEL);
+
+	if (!m)
+		return -ENOMEM;
+	m->paddr = paddr;
+	m->size = size;
+	list_add_tail(&m->list, list);
+	return 0;
+}
+
+/* Free a list of vmcore ranges. */
+static inline void vmcore_free_ranges(struct list_head *list)
+{
+	struct vmcore_range *m, *tmp;
+
+	list_for_each_entry_safe(m, tmp, list, list) {
+		list_del(&m->list);
+		kfree(m);
+	}
+}
+
 #else /* !CONFIG_CRASH_DUMP */
 static inline bool is_kdump_kernel(void) { return false; }
 #endif /* CONFIG_CRASH_DUMP */
diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h
new file mode 100644
index 000000000000..f0dc03d94ca2
--- /dev/null
+++ b/include/linux/crash_reserve.h
@@ -0,0 +1,66 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_CRASH_RESERVE_H
+#define LINUX_CRASH_RESERVE_H
+
+#include <linux/linkage.h>
+#include <linux/elfcore.h>
+#include <linux/elf.h>
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+#include <asm/crash_reserve.h>
+#endif
+
+/* Location of a reserved region to hold the crash kernel.
+ */
+extern struct resource crashk_res;
+extern struct resource crashk_low_res;
+extern struct range crashk_cma_ranges[];
+#if defined(CONFIG_CMA) && defined(CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION)
+#define CRASHKERNEL_CMA
+#define CRASHKERNEL_CMA_RANGES_MAX 4
+extern int crashk_cma_cnt;
+#else
+#define crashk_cma_cnt 0
+#define CRASHKERNEL_CMA_RANGES_MAX 0
+#endif
+
+
+int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
+		unsigned long long *crash_size, unsigned long long *crash_base,
+		unsigned long long *low_size, unsigned long long *cma_size,
+		bool *high);
+
+void __init reserve_crashkernel_cma(unsigned long long cma_size);
+
+#ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
+#ifndef arch_add_crash_res_to_iomem
+static inline bool arch_add_crash_res_to_iomem(void)
+{
+	return true;
+}
+#endif
+#ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE
+#define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)
+#endif
+#ifndef CRASH_ALIGN
+#define CRASH_ALIGN			SZ_2M
+#endif
+#ifndef CRASH_ADDR_LOW_MAX
+#define CRASH_ADDR_LOW_MAX		SZ_4G
+#endif
+#ifndef CRASH_ADDR_HIGH_MAX
+#define CRASH_ADDR_HIGH_MAX		memblock_end_of_DRAM()
+#endif
+
+void __init reserve_crashkernel_generic(unsigned long long crash_size,
+					unsigned long long crash_base,
+					unsigned long long crash_low_size,
+					bool high);
+#else
+static inline void __init reserve_crashkernel_generic(
+		unsigned long long crash_size,
+		unsigned long long crash_base,
+		unsigned long long crash_low_size,
+		bool high)
+{}
+#endif
+#endif /* LINUX_CRASH_RESERVE_H */
diff --git a/include/linux/crc-ccitt.h b/include/linux/crc-ccitt.h
index 72c92c396bb8..cd4f420231ba 100644
--- a/include/linux/crc-ccitt.h
+++ b/include/linux/crc-ccitt.h
@@ -5,19 +5,12 @@
 #include <linux/types.h>
 
 extern u16 const crc_ccitt_table[256];
-extern u16 const crc_ccitt_false_table[256];
 
 extern u16 crc_ccitt(u16 crc, const u8 *buffer, size_t len);
-extern u16 crc_ccitt_false(u16 crc, const u8 *buffer, size_t len);
 
 static inline u16 crc_ccitt_byte(u16 crc, const u8 c)
 {
 	return (crc >> 8) ^ crc_ccitt_table[(crc ^ c) & 0xff];
 }
 
-static inline u16 crc_ccitt_false_byte(u16 crc, const u8 c)
-{
-    return (crc << 8) ^ crc_ccitt_false_table[(crc >> 8) ^ c];
-}
-
 #endif /* _LINUX_CRC_CCITT_H */
diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h
index 6bb0c0bf357b..ecc8bc2dd7f4 100644
--- a/include/linux/crc-t10dif.h
+++ b/include/linux/crc-t10dif.h
@@ -4,13 +4,11 @@
 
 #include <linux/types.h>
 
-#define CRC_T10DIF_DIGEST_SIZE 2
-#define CRC_T10DIF_BLOCK_SIZE 1
-#define CRC_T10DIF_STRING "crct10dif"
+u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len);
 
-extern __u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer,
-				size_t len);
-extern __u16 crc_t10dif(unsigned char const *, size_t);
-extern __u16 crc_t10dif_update(__u16 crc, unsigned char const *, size_t);
+static inline u16 crc_t10dif(const u8 *p, size_t len)
+{
+	return crc_t10dif_update(0, p, len);
+}
 
 #endif
diff --git a/include/linux/crc16.h b/include/linux/crc16.h
index 9fa74529b317..b861d969b161 100644
--- a/include/linux/crc16.h
+++ b/include/linux/crc16.h
@@ -15,14 +15,7 @@
 
 #include <linux/types.h>
 
-extern u16 const crc16_table[256];
-
-extern u16 crc16(u16 crc, const u8 *buffer, size_t len);
-
-static inline u16 crc16_byte(u16 crc, const u8 data)
-{
-	return (crc >> 8) ^ crc16_table[(crc ^ data) & 0xff];
-}
+u16 crc16(u16 crc, const u8 *p, size_t len);
 
 #endif /* __CRC16_H */
 
diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 9e8a032c1788..da78b215ff2e 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -1,69 +1,100 @@
-/*
- * crc32.h
- * See linux/lib/crc32.c for license and changes
- */
+/* SPDX-License-Identifier: GPL-2.0-only */
 #ifndef _LINUX_CRC32_H
 #define _LINUX_CRC32_H
 
 #include <linux/types.h>
 #include <linux/bitrev.h>
 
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len);
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len);
-
 /**
- * crc32_le_combine - Combine two crc32 check values into one. For two
- * 		      sequences of bytes, seq1 and seq2 with lengths len1
- * 		      and len2, crc32_le() check values were calculated
- * 		      for each, crc1 and crc2.
+ * crc32_le() - Compute least-significant-bit-first IEEE CRC-32
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * This implements the CRC variant that is often known as the IEEE CRC-32, or
+ * simply CRC-32, and is widely used in Ethernet and other applications:
+ *
+ * - Polynomial: x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 +
+ *		 x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+ * - Bit order: Least-significant-bit-first
+ * - Polynomial in integer form: 0xedb88320
  *
- * @crc1: crc32 of the first block
- * @crc2: crc32 of the second block
- * @len2: length of the second block
+ * This does *not* invert the CRC at the beginning or end.  The caller is
+ * expected to do that if it needs to.  Inverting at both ends is recommended.
  *
- * Return: The crc32_le() check value of seq1 and seq2 concatenated,
- * 	   requiring only crc1, crc2, and len2. Note: If seq_full denotes
- * 	   the concatenated memory area of seq1 with seq2, and crc_full
- * 	   the crc32_le() value of seq_full, then crc_full ==
- * 	   crc32_le_combine(crc1, crc2, len2) when crc_full was seeded
- * 	   with the same initializer as crc1, and crc2 seed was 0. See
- * 	   also crc32_combine_test().
+ * For new applications, prefer to use CRC-32C instead.  See crc32c().
+ *
+ * Context: Any context
+ * Return: The new CRC value
  */
-u32 __attribute_const__ crc32_le_shift(u32 crc, size_t len);
+u32 crc32_le(u32 crc, const void *p, size_t len);
 
-static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2)
+/* This is just an alias for crc32_le(). */
+static inline u32 crc32(u32 crc, const void *p, size_t len)
 {
-	return crc32_le_shift(crc1, len2) ^ crc2;
+	return crc32_le(crc, p, len);
 }
 
-u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len);
-
 /**
- * __crc32c_le_combine - Combine two crc32c check values into one. For two
- * 			 sequences of bytes, seq1 and seq2 with lengths len1
- * 			 and len2, __crc32c_le() check values were calculated
- * 			 for each, crc1 and crc2.
+ * crc32_be() - Compute most-significant-bit-first IEEE CRC-32
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
  *
- * @crc1: crc32c of the first block
- * @crc2: crc32c of the second block
- * @len2: length of the second block
+ * crc32_be() is the same as crc32_le() except that crc32_be() computes the
+ * *most-significant-bit-first* variant of the CRC.  I.e., within each byte, the
+ * most significant bit is processed first (treated as highest order polynomial
+ * coefficient).  The same bit order is also used for the CRC value itself:
  *
- * Return: The __crc32c_le() check value of seq1 and seq2 concatenated,
- * 	   requiring only crc1, crc2, and len2. Note: If seq_full denotes
- * 	   the concatenated memory area of seq1 with seq2, and crc_full
- * 	   the __crc32c_le() value of seq_full, then crc_full ==
- * 	   __crc32c_le_combine(crc1, crc2, len2) when crc_full was
- * 	   seeded with the same initializer as crc1, and crc2 seed
- * 	   was 0. See also crc32c_combine_test().
+ * - Polynomial: x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 +
+ *		 x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+ * - Bit order: Most-significant-bit-first
+ * - Polynomial in integer form: 0x04c11db7
+ *
+ * Context: Any context
+ * Return: The new CRC value
  */
-u32 __attribute_const__ __crc32c_le_shift(u32 crc, size_t len);
+u32 crc32_be(u32 crc, const void *p, size_t len);
 
-static inline u32 __crc32c_le_combine(u32 crc1, u32 crc2, size_t len2)
-{
-	return __crc32c_le_shift(crc1, len2) ^ crc2;
-}
+/**
+ * crc32c() - Compute CRC-32C
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * This implements CRC-32C, i.e. the Castagnoli CRC.  This is the recommended
+ * CRC variant to use in new applications that want a 32-bit CRC.
+ *
+ * - Polynomial: x^32 + x^28 + x^27 + x^26 + x^25 + x^23 + x^22 + x^20 + x^19 +
+ *		 x^18 + x^14 + x^13 + x^11 + x^10 + x^9 + x^8 + x^6 + x^0
+ * - Bit order: Least-significant-bit-first
+ * - Polynomial in integer form: 0x82f63b78
+ *
+ * This does *not* invert the CRC at the beginning or end.  The caller is
+ * expected to do that if it needs to.  Inverting at both ends is recommended.
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
+u32 crc32c(u32 crc, const void *p, size_t len);
 
-#define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
+/*
+ * crc32_optimizations() returns flags that indicate which CRC32 library
+ * functions are using architecture-specific optimizations.  Unlike
+ * IS_ENABLED(CONFIG_CRC32_ARCH) it takes into account the different CRC32
+ * variants and also whether any needed CPU features are available at runtime.
+ */
+#define CRC32_LE_OPTIMIZATION	BIT(0) /* crc32_le() is optimized */
+#define CRC32_BE_OPTIMIZATION	BIT(1) /* crc32_be() is optimized */
+#define CRC32C_OPTIMIZATION	BIT(2) /* crc32c() is optimized */
+#if IS_ENABLED(CONFIG_CRC32_ARCH)
+u32 crc32_optimizations(void);
+#else
+static inline u32 crc32_optimizations(void) { return 0; }
+#endif
 
 /*
  * Helpers for hash table generation of ethernet nics:
diff --git a/include/linux/crc32c.h b/include/linux/crc32c.h
index 357ae4611a45..b8cff2f4309a 100644
--- a/include/linux/crc32c.h
+++ b/include/linux/crc32c.h
@@ -2,11 +2,6 @@
 #ifndef _LINUX_CRC32C_H
 #define _LINUX_CRC32C_H
 
-#include <linux/types.h>
-
-extern u32 crc32c(u32 crc, const void *address, unsigned int length);
-
-/* This macro exists for backwards-compatibility. */
-#define crc32c_le crc32c
+#include <linux/crc32.h>
 
 #endif	/* _LINUX_CRC32C_H */
diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h
index 62c4b7790a28..ccab711295fa 100644
--- a/include/linux/crc32poly.h
+++ b/include/linux/crc32poly.h
@@ -2,19 +2,13 @@
 #ifndef _LINUX_CRC32_POLY_H
 #define _LINUX_CRC32_POLY_H
 
-/*
- * There are multiple 16-bit CRC polynomials in common use, but this is
- * *the* standard CRC-32 polynomial, first popularized by Ethernet.
- * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
- */
+/* The polynomial used by crc32_le(), in integer form.  See crc32_le(). */
 #define CRC32_POLY_LE 0xedb88320
+
+/* The polynomial used by crc32_be(), in integer form.  See crc32_be(). */
 #define CRC32_POLY_BE 0x04c11db7
 
-/*
- * This is the CRC32c polynomial, as outlined by Castagnoli.
- * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
- * x^8+x^6+x^0
- */
-#define CRC32C_POLY_LE 0x82F63B78
+/* The polynomial used by crc32c(), in integer form.  See crc32c(). */
+#define CRC32C_POLY_LE 0x82f63b78
 
 #endif /* _LINUX_CRC32_POLY_H */
diff --git a/include/linux/crc64.h b/include/linux/crc64.h
index e044c60d1e61..fc0c06ab1993 100644
--- a/include/linux/crc64.h
+++ b/include/linux/crc64.h
@@ -1,18 +1,28 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * See lib/crc64.c for the related specification and polynomial arithmetic.
- */
 #ifndef _LINUX_CRC64_H
 #define _LINUX_CRC64_H
 
 #include <linux/types.h>
 
-#define CRC64_ROCKSOFT_STRING "crc64-rocksoft"
-
-u64 __pure crc64_be(u64 crc, const void *p, size_t len);
-u64 __pure crc64_rocksoft_generic(u64 crc, const void *p, size_t len);
+/**
+ * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64
+ * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation,
+ *       or the previous crc64 value if computing incrementally.
+ * @p: pointer to buffer over which CRC64 is run
+ * @len: length of buffer @p
+ */
+u64 crc64_be(u64 crc, const void *p, size_t len);
 
-u64 crc64_rocksoft(const unsigned char *buffer, size_t len);
-u64 crc64_rocksoft_update(u64 crc, const unsigned char *buffer, size_t len);
+/**
+ * crc64_nvme - Calculate CRC64-NVME
+ * @crc: seed value for computation. 0 for a new CRC calculation, or the
+ *	 previous crc64 value if computing incrementally.
+ * @p: pointer to buffer over which CRC64 is run
+ * @len: length of buffer @p
+ *
+ * This computes the CRC64 defined in the NVME NVM Command Set Specification,
+ * *including the bitwise inversion at the beginning and end*.
+ */
+u64 crc64_nvme(u64 crc, const void *p, size_t len);
 
 #endif /* _LINUX_CRC64_H */
diff --git a/include/linux/crc7.h b/include/linux/crc7.h
index b462842f3c32..61d34749e437 100644
--- a/include/linux/crc7.h
+++ b/include/linux/crc7.h
@@ -3,13 +3,6 @@
 #define _LINUX_CRC7_H
 #include <linux/types.h>
 
-extern const u8 crc7_be_syndrome_table[256];
-
-static inline u8 crc7_be_byte(u8 crc, u8 data)
-{
-	return crc7_be_syndrome_table[crc ^ data];
-}
-
 extern u8 crc7_be(u8 crc, const u8 *buffer, size_t len);
 
 #endif
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 9ed9232af934..343a140a6ba2 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -12,6 +12,7 @@
 #include <linux/init.h>
 #include <linux/key.h>
 #include <linux/atomic.h>
+#include <linux/refcount.h>
 #include <linux/uidgid.h>
 #include <linux/sched.h>
 #include <linux/sched/user.h>
@@ -19,11 +20,13 @@
 struct cred;
 struct inode;
 
+extern struct task_struct init_task;
+
 /*
  * COW Supplementary groups list
  */
 struct group_info {
-	atomic_t	usage;
+	refcount_t	usage;
 	int		ngroups;
 	kgid_t		gid[];
 } __randomize_layout;
@@ -39,7 +42,7 @@ struct group_info {
  */
 static inline struct group_info *get_group_info(struct group_info *gi)
 {
-	atomic_inc(&gi->usage);
+	refcount_inc(&gi->usage);
 	return gi;
 }
 
@@ -49,7 +52,7 @@ static inline struct group_info *get_group_info(struct group_info *gi)
  */
 #define put_group_info(group_info)			\
 do {							\
-	if (atomic_dec_and_test(&(group_info)->usage))	\
+	if (refcount_dec_and_test(&(group_info)->usage))	\
 		groups_free(group_info);		\
 } while (0)
 
@@ -108,14 +111,7 @@ static inline int groups_search(const struct group_info *group_info, kgid_t grp)
  * same context as task->real_cred.
  */
 struct cred {
-	atomic_t	usage;
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	atomic_t	subscribers;	/* number of processes subscribed */
-	void		*put_addr;
-	unsigned	magic;
-#define CRED_MAGIC	0x43736564
-#define CRED_MAGIC_DEAD	0x44656144
-#endif
+	atomic_long_t	usage;
 	kuid_t		uid;		/* real UID of the task */
 	kgid_t		gid;		/* real GID of the task */
 	kuid_t		suid;		/* saved UID of the task */
@@ -154,17 +150,19 @@ struct cred {
 
 extern void __put_cred(struct cred *);
 extern void exit_creds(struct task_struct *);
-extern int copy_creds(struct task_struct *, unsigned long);
+extern int copy_creds(struct task_struct *, u64);
 extern const struct cred *get_task_cred(struct task_struct *);
 extern struct cred *cred_alloc_blank(void);
 extern struct cred *prepare_creds(void);
 extern struct cred *prepare_exec_creds(void);
 extern int commit_creds(struct cred *);
 extern void abort_creds(struct cred *);
-extern const struct cred *override_creds(const struct cred *);
-extern void revert_creds(const struct cred *);
 extern struct cred *prepare_kernel_cred(struct task_struct *);
-extern int change_create_files_as(struct cred *, struct inode *);
+static inline const struct cred *kernel_cred(void)
+{
+	/* shut up sparse */
+	return rcu_dereference_raw(init_task.cred);
+}
 extern int set_security_override(struct cred *, u32);
 extern int set_security_override_from_ctx(struct cred *, const char *);
 extern int set_create_files_as(struct cred *, struct inode *);
@@ -172,46 +170,6 @@ extern int cred_fscmp(const struct cred *, const struct cred *);
 extern void __init cred_init(void);
 extern int set_cred_ucounts(struct cred *);
 
-/*
- * check for validity of credentials
- */
-#ifdef CONFIG_DEBUG_CREDENTIALS
-extern void __noreturn __invalid_creds(const struct cred *, const char *, unsigned);
-extern void __validate_process_creds(struct task_struct *,
-				     const char *, unsigned);
-
-extern bool creds_are_invalid(const struct cred *cred);
-
-static inline void __validate_creds(const struct cred *cred,
-				    const char *file, unsigned line)
-{
-	if (unlikely(creds_are_invalid(cred)))
-		__invalid_creds(cred, file, line);
-}
-
-#define validate_creds(cred)				\
-do {							\
-	__validate_creds((cred), __FILE__, __LINE__);	\
-} while(0)
-
-#define validate_process_creds()				\
-do {								\
-	__validate_process_creds(current, __FILE__, __LINE__);	\
-} while(0)
-
-extern void validate_creds_for_do_exit(struct task_struct *);
-#else
-static inline void validate_creds(const struct cred *cred)
-{
-}
-static inline void validate_creds_for_do_exit(struct task_struct *tsk)
-{
-}
-static inline void validate_process_creds(void)
-{
-}
-#endif
-
 static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 {
 	return cap_issubset(cred->cap_ambient,
@@ -219,25 +177,33 @@ static inline bool cap_ambient_invariant_ok(const struct cred *cred)
 					  cred->cap_inheritable));
 }
 
-/**
- * get_new_cred - Get a reference on a new set of credentials
- * @cred: The new credentials to reference
- *
- * Get a reference on the specified set of new credentials.  The caller must
- * release the reference.
- */
-static inline struct cred *get_new_cred(struct cred *cred)
+static inline const struct cred *override_creds(const struct cred *override_cred)
 {
-	atomic_inc(&cred->usage);
-	return cred;
+	return rcu_replace_pointer(current->cred, override_cred, 1);
+}
+
+static inline const struct cred *revert_creds(const struct cred *revert_cred)
+{
+	return rcu_replace_pointer(current->cred, revert_cred, 1);
 }
 
+DEFINE_CLASS(override_creds,
+	     const struct cred *,
+	     revert_creds(_T),
+	     override_creds(override_cred), const struct cred *override_cred)
+
+#define scoped_with_creds(cred) \
+	scoped_class(override_creds, __UNIQUE_ID(label), cred)
+
+#define scoped_with_kernel_creds() scoped_with_creds(kernel_cred())
+
 /**
- * get_cred - Get a reference on a set of credentials
+ * get_cred_many - Get references on a set of credentials
  * @cred: The credentials to reference
+ * @nr: Number of references to acquire
  *
- * Get a reference on the specified set of credentials.  The caller must
- * release the reference.  If %NULL is passed, it is returned with no action.
+ * Get references on the specified set of credentials.  The caller must release
+ * all acquired reference.  If %NULL is passed, it is returned with no action.
  *
  * This is used to deal with a committed set of credentials.  Although the
  * pointer is const, this will temporarily discard the const and increment the
@@ -245,14 +211,28 @@ static inline struct cred *get_new_cred(struct cred *cred)
  * accidental alteration of a set of credentials that should be considered
  * immutable.
  */
-static inline const struct cred *get_cred(const struct cred *cred)
+static inline const struct cred *get_cred_many(const struct cred *cred, int nr)
 {
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return cred;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
-	return get_new_cred(nonconst_cred);
+	atomic_long_add(nr, &nonconst_cred->usage);
+	return cred;
+}
+
+/*
+ * get_cred - Get a reference on a set of credentials
+ * @cred: The credentials to reference
+ *
+ * Get a reference on the specified set of credentials.  The caller must
+ * release the reference.  If %NULL is passed, it is returned with no action.
+ *
+ * This is used to deal with a committed set of credentials.
+ */
+static inline const struct cred *get_cred(const struct cred *cred)
+{
+	return get_cred_many(cred, 1);
 }
 
 static inline const struct cred *get_cred_rcu(const struct cred *cred)
@@ -260,9 +240,8 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 	struct cred *nonconst_cred = (struct cred *) cred;
 	if (!cred)
 		return NULL;
-	if (!atomic_inc_not_zero(&nonconst_cred->usage))
+	if (!atomic_long_inc_not_zero(&nonconst_cred->usage))
 		return NULL;
-	validate_creds(cred);
 	nonconst_cred->non_rcu = 0;
 	return cred;
 }
@@ -270,6 +249,7 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
 /**
  * put_cred - Release a reference to a set of credentials
  * @cred: The credentials to release
+ * @nr: Number of references to release
  *
  * Release a reference to a set of credentials, deleting them when the last ref
  * is released.  If %NULL is passed, nothing is done.
@@ -278,17 +258,35 @@ static inline const struct cred *get_cred_rcu(const struct cred *cred)
  * on task_struct are attached by const pointers to prevent accidental
  * alteration of otherwise immutable credential sets.
  */
-static inline void put_cred(const struct cred *_cred)
+static inline void put_cred_many(const struct cred *_cred, int nr)
 {
 	struct cred *cred = (struct cred *) _cred;
 
 	if (cred) {
-		validate_creds(cred);
-		if (atomic_dec_and_test(&(cred)->usage))
+		if (atomic_long_sub_and_test(nr, &cred->usage))
 			__put_cred(cred);
 	}
 }
 
+/*
+ * put_cred - Release a reference to a set of credentials
+ * @cred: The credentials to release
+ *
+ * Release a reference to a set of credentials, deleting them when the last ref
+ * is released.  If %NULL is passed, nothing is done.
+ */
+static inline void put_cred(const struct cred *cred)
+{
+	put_cred_many(cred, 1);
+}
+
+DEFINE_CLASS(prepare_creds,
+	      struct cred *,
+	      if (_T) put_cred(_T),
+	      prepare_creds(), void)
+
+DEFINE_FREE(put_cred, struct cred *, if (!IS_ERR_OR_NULL(_T)) put_cred(_T))
+
 /**
  * current_cred - Access the current task's subjective credentials
  *
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index fa310ac1db59..a2137e19be7d 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -13,7 +13,8 @@
 #define _LINUX_CRYPTO_H
 
 #include <linux/completion.h>
-#include <linux/refcount.h>
+#include <linux/errno.h>
+#include <linux/refcount_types.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 
@@ -22,20 +23,19 @@
  */
 #define CRYPTO_ALG_TYPE_MASK		0x0000000f
 #define CRYPTO_ALG_TYPE_CIPHER		0x00000001
-#define CRYPTO_ALG_TYPE_COMPRESS	0x00000002
 #define CRYPTO_ALG_TYPE_AEAD		0x00000003
+#define CRYPTO_ALG_TYPE_LSKCIPHER	0x00000004
 #define CRYPTO_ALG_TYPE_SKCIPHER	0x00000005
+#define CRYPTO_ALG_TYPE_AKCIPHER	0x00000006
+#define CRYPTO_ALG_TYPE_SIG		0x00000007
 #define CRYPTO_ALG_TYPE_KPP		0x00000008
 #define CRYPTO_ALG_TYPE_ACOMPRESS	0x0000000a
 #define CRYPTO_ALG_TYPE_SCOMPRESS	0x0000000b
 #define CRYPTO_ALG_TYPE_RNG		0x0000000c
-#define CRYPTO_ALG_TYPE_AKCIPHER	0x0000000d
 #define CRYPTO_ALG_TYPE_HASH		0x0000000e
 #define CRYPTO_ALG_TYPE_SHASH		0x0000000e
 #define CRYPTO_ALG_TYPE_AHASH		0x0000000f
 
-#define CRYPTO_ALG_TYPE_HASH_MASK	0x0000000e
-#define CRYPTO_ALG_TYPE_AHASH_MASK	0x0000000e
 #define CRYPTO_ALG_TYPE_ACOMPRESS_MASK	0x0000000e
 
 #define CRYPTO_ALG_LARVAL		0x00000010
@@ -50,6 +50,15 @@
 #define CRYPTO_ALG_NEED_FALLBACK	0x00000100
 
 /*
+ * Set if the algorithm data structure should be duplicated into
+ * kmalloc memory before registration.  This is useful for hardware
+ * that can be disconnected at will.  Do not use this if the data
+ * structure is embedded into a bigger one.  Duplicate the overall
+ * data structure in the driver in that case.
+ */
+#define CRYPTO_ALG_DUP_FIRST		0x00000200
+
+/*
  * Set if the algorithm has passed automated run-time testing.  Note that
  * if there is no run-time testing for a given algorithm it is considered
  * to have passed.
@@ -110,7 +119,6 @@
  *	  crypto_aead_walksize() (with the remainder going at the end), no chunk
  *	  can cross a page boundary or a scatterlist element boundary.
  *    ahash:
- *	- The result buffer must be aligned to the algorithm's alignmask.
  *	- crypto_ahash_finup() must not be used unless the algorithm implements
  *	  ->finup() natively.
  */
@@ -125,6 +133,14 @@
  */
 #define CRYPTO_ALG_FIPS_INTERNAL	0x00020000
 
+/* Set if the algorithm supports virtual addresses. */
+#define CRYPTO_ALG_REQ_VIRT		0x00040000
+
+/* Set if the algorithm cannot have a fallback (e.g., phmac). */
+#define CRYPTO_ALG_NO_FALLBACK		0x00080000
+
+/* The high bits 0xff000000 are reserved for type-specific flags. */
+
 /*
  * Transform masks and values (for crt_flags).
  */
@@ -134,6 +150,7 @@
 #define CRYPTO_TFM_REQ_FORBID_WEAK_KEYS	0x00000100
 #define CRYPTO_TFM_REQ_MAY_SLEEP	0x00000200
 #define CRYPTO_TFM_REQ_MAY_BACKLOG	0x00000400
+#define CRYPTO_TFM_REQ_ON_STACK		0x00000800
 
 /*
  * Miscellaneous stuff.
@@ -240,26 +257,7 @@ struct cipher_alg {
 	void (*cia_decrypt)(struct crypto_tfm *tfm, u8 *dst, const u8 *src);
 };
 
-/**
- * struct compress_alg - compression/decompression algorithm
- * @coa_compress: Compress a buffer of specified length, storing the resulting
- *		  data in the specified buffer. Return the length of the
- *		  compressed data in dlen.
- * @coa_decompress: Decompress the source buffer, storing the uncompressed
- *		    data in the specified buffer. The length of the data is
- *		    returned in dlen.
- *
- * All fields are mandatory.
- */
-struct compress_alg {
-	int (*coa_compress)(struct crypto_tfm *tfm, const u8 *src,
-			    unsigned int slen, u8 *dst, unsigned int *dlen);
-	int (*coa_decompress)(struct crypto_tfm *tfm, const u8 *src,
-			      unsigned int slen, u8 *dst, unsigned int *dlen);
-};
-
 #define cra_cipher	cra_u.cipher
-#define cra_compress	cra_u.compress
 
 /**
  * struct crypto_alg - definition of a cryptograpic cipher algorithm
@@ -278,18 +276,21 @@ struct compress_alg {
  * @cra_ctxsize: Size of the operational context of the transformation. This
  *		 value informs the kernel crypto API about the memory size
  *		 needed to be allocated for the transformation context.
- * @cra_alignmask: Alignment mask for the input and output data buffer. The data
- *		   buffer containing the input data for the algorithm must be
- *		   aligned to this alignment mask. The data buffer for the
- *		   output data must be aligned to this alignment mask. Note that
- *		   the Crypto API will do the re-alignment in software, but
- *		   only under special conditions and there is a performance hit.
- *		   The re-alignment happens at these occasions for different
- *		   @cra_u types: cipher -- For both input data and output data
- *		   buffer; ahash -- For output hash destination buf; shash --
- *		   For output hash destination buf.
- *		   This is needed on hardware which is flawed by design and
- *		   cannot pick data from arbitrary addresses.
+ * @cra_alignmask: For cipher, skcipher, lskcipher, and aead algorithms this is
+ *		   1 less than the alignment, in bytes, that the algorithm
+ *		   implementation requires for input and output buffers.  When
+ *		   the crypto API is invoked with buffers that are not aligned
+ *		   to this alignment, the crypto API automatically utilizes
+ *		   appropriately aligned temporary buffers to comply with what
+ *		   the algorithm needs.  (For scatterlists this happens only if
+ *		   the algorithm uses the skcipher_walk helper functions.)  This
+ *		   misalignment handling carries a performance penalty, so it is
+ *		   preferred that algorithms do not set a nonzero alignmask.
+ *		   Also, crypto API users may wish to allocate buffers aligned
+ *		   to the alignmask of the algorithm being used, in order to
+ *		   avoid the API having to realign them.  Note: the alignmask is
+ *		   not supported for hash algorithms and is always 0 for them.
+ * @cra_reqsize: Size of the request context for this algorithm.
  * @cra_priority: Priority of this transformation implementation. In case
  *		  multiple transformations with same @cra_name are available to
  *		  the Crypto API, the kernel will use the one with highest
@@ -308,27 +309,16 @@ struct compress_alg {
  *	      transformation types. There are multiple options, such as
  *	      &crypto_skcipher_type, &crypto_ahash_type, &crypto_rng_type.
  *	      This field might be empty. In that case, there are no common
- *	      callbacks. This is the case for: cipher, compress, shash.
+ *	      callbacks. This is the case for: cipher.
  * @cra_u: Callbacks implementing the transformation. This is a union of
  *	   multiple structures. Depending on the type of transformation selected
  *	   by @cra_type and @cra_flags above, the associated structure must be
  *	   filled with callbacks. This field might be empty. This is the case
  *	   for ahash, shash.
- * @cra_init: Initialize the cryptographic transformation object. This function
- *	      is used to initialize the cryptographic transformation object.
- *	      This function is called only once at the instantiation time, right
- *	      after the transformation context was allocated. In case the
- *	      cryptographic hardware has some special requirements which need to
- *	      be handled by software, this function shall check for the precise
- *	      requirement of the transformation and put any software fallbacks
- *	      in place.
- * @cra_exit: Deinitialize the cryptographic transformation object. This is a
- *	      counterpart to @cra_init, used to remove various changes set in
- *	      @cra_init.
+ * @cra_init: Deprecated, do not use.
+ * @cra_exit: Deprecated, do not use.
  * @cra_u.cipher: Union member which contains a single-block symmetric cipher
  *		  definition. See @struct @cipher_alg.
- * @cra_u.compress: Union member which contains a (de)compression algorithm.
- *		    See @struct @compress_alg.
  * @cra_module: Owner of this transformation implementation. Set to THIS_MODULE
  * @cra_list: internally used
  * @cra_users: internally used
@@ -347,6 +337,7 @@ struct crypto_alg {
 	unsigned int cra_blocksize;
 	unsigned int cra_ctxsize;
 	unsigned int cra_alignmask;
+	unsigned int cra_reqsize;
 
 	int cra_priority;
 	refcount_t cra_refcnt;
@@ -358,7 +349,6 @@ struct crypto_alg {
 
 	union {
 		struct cipher_alg cipher;
-		struct compress_alg compress;
 	} cra_u;
 
 	int (*cra_init)(struct crypto_tfm *tfm);
@@ -424,18 +414,16 @@ struct crypto_tfm {
 	u32 crt_flags;
 
 	int node;
-	
+
+	struct crypto_tfm *fb;
+
 	void (*exit)(struct crypto_tfm *tfm);
-	
+
 	struct crypto_alg *__crt_alg;
 
 	void *__crt_ctx[] CRYPTO_MINALIGN_ATTR;
 };
 
-struct crypto_comp {
-	struct crypto_tfm base;
-};
-
 /* 
  * Transform user interface.
  */
@@ -471,6 +459,11 @@ static inline unsigned int crypto_tfm_alg_alignmask(struct crypto_tfm *tfm)
 	return tfm->__crt_alg->cra_alignmask;
 }
 
+static inline unsigned int crypto_tfm_alg_reqsize(struct crypto_tfm *tfm)
+{
+	return tfm->__crt_alg->cra_reqsize;
+}
+
 static inline u32 crypto_tfm_get_flags(struct crypto_tfm *tfm)
 {
 	return tfm->crt_flags;
@@ -492,52 +485,45 @@ static inline unsigned int crypto_tfm_ctx_alignment(void)
 	return __alignof__(tfm->__crt_ctx);
 }
 
-static inline struct crypto_comp *__crypto_comp_cast(struct crypto_tfm *tfm)
+static inline bool crypto_tfm_is_async(struct crypto_tfm *tfm)
 {
-	return (struct crypto_comp *)tfm;
+	return tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC;
 }
 
-static inline struct crypto_comp *crypto_alloc_comp(const char *alg_name,
-						    u32 type, u32 mask)
+static inline bool crypto_req_on_stack(struct crypto_async_request *req)
 {
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_COMPRESS;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return __crypto_comp_cast(crypto_alloc_base(alg_name, type, mask));
+	return req->flags & CRYPTO_TFM_REQ_ON_STACK;
 }
 
-static inline struct crypto_tfm *crypto_comp_tfm(struct crypto_comp *tfm)
+static inline void crypto_request_set_callback(
+	struct crypto_async_request *req, u32 flags,
+	crypto_completion_t compl, void *data)
 {
-	return &tfm->base;
-}
+	u32 keep = CRYPTO_TFM_REQ_ON_STACK;
 
-static inline void crypto_free_comp(struct crypto_comp *tfm)
-{
-	crypto_free_tfm(crypto_comp_tfm(tfm));
+	req->complete = compl;
+	req->data = data;
+	req->flags &= keep;
+	req->flags |= flags & ~keep;
 }
 
-static inline int crypto_has_comp(const char *alg_name, u32 type, u32 mask)
+static inline void crypto_request_set_tfm(struct crypto_async_request *req,
+					  struct crypto_tfm *tfm)
 {
-	type &= ~CRYPTO_ALG_TYPE_MASK;
-	type |= CRYPTO_ALG_TYPE_COMPRESS;
-	mask |= CRYPTO_ALG_TYPE_MASK;
-
-	return crypto_has_alg(alg_name, type, mask);
+	req->tfm = tfm;
+	req->flags &= ~CRYPTO_TFM_REQ_ON_STACK;
 }
 
-static inline const char *crypto_comp_name(struct crypto_comp *tfm)
+struct crypto_async_request *crypto_request_clone(
+	struct crypto_async_request *req, size_t total, gfp_t gfp);
+
+static inline void crypto_stack_request_init(struct crypto_async_request *req,
+					     struct crypto_tfm *tfm)
 {
-	return crypto_tfm_alg_name(crypto_comp_tfm(tfm));
+	req->flags = 0;
+	crypto_request_set_tfm(req, tfm);
+	req->flags |= CRYPTO_TFM_REQ_ON_STACK;
 }
 
-int crypto_comp_compress(struct crypto_comp *tfm,
-			 const u8 *src, unsigned int slen,
-			 u8 *dst, unsigned int *dlen);
-
-int crypto_comp_decompress(struct crypto_comp *tfm,
-			   const u8 *src, unsigned int slen,
-			   u8 *dst, unsigned int *dlen);
-
 #endif	/* _LINUX_CRYPTO_H */
 
diff --git a/include/linux/damon.h b/include/linux/damon.h
index d5d4d19928e0..3813373a9200 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -2,7 +2,7 @@
 /*
  * DAMON api
  *
- * Author: SeongJae Park <sjpark@amazon.de>
+ * Author: SeongJae Park <sj@kernel.org>
  */
 
 #ifndef _DAMON_H_
@@ -36,13 +36,38 @@ struct damon_addr_range {
 };
 
 /**
+ * struct damon_size_range - Represents size for filter to operate on [@min, @max].
+ * @min:	Min size (inclusive).
+ * @max:	Max size (inclusive).
+ */
+struct damon_size_range {
+	unsigned long min;
+	unsigned long max;
+};
+
+/**
  * struct damon_region - Represents a monitoring target region.
  * @ar:			The address range of the region.
  * @sampling_addr:	Address of the sample for the next access check.
  * @nr_accesses:	Access frequency of this region.
+ * @nr_accesses_bp:	@nr_accesses in basis point (0.01%) that updated for
+ *			each sampling interval.
  * @list:		List head for siblings.
  * @age:		Age of this region.
  *
+ * @nr_accesses is reset to zero for every &damon_attrs->aggr_interval and be
+ * increased for every &damon_attrs->sample_interval if an access to the region
+ * during the last sampling interval is found.  The update of this field should
+ * not be done with direct access but with the helper function,
+ * damon_update_region_access_rate().
+ *
+ * @nr_accesses_bp is another representation of @nr_accesses in basis point
+ * (1 in 10,000) that updated for every &damon_attrs->sample_interval in a
+ * manner similar to moving sum.  By the algorithm, this value becomes
+ * @nr_accesses * 10000 for every &struct damon_attrs->aggr_interval.  This can
+ * be used when the aggregation interval is too huge and therefore cannot wait
+ * for it before getting the access monitoring results.
+ *
  * @age is initially zero, increased for each aggregation interval, and reset
  * to zero again if the access frequency is significantly changed.  If two
  * regions are merged into a new region, both @nr_accesses and @age of the new
@@ -52,6 +77,7 @@ struct damon_region {
 	struct damon_addr_range ar;
 	unsigned long sampling_addr;
 	unsigned int nr_accesses;
+	unsigned int nr_accesses_bp;
 	struct list_head list;
 
 	unsigned int age;
@@ -65,17 +91,23 @@ struct damon_region {
  * @nr_regions:		Number of monitoring target regions of this target.
  * @regions_list:	Head of the monitoring target regions of this target.
  * @list:		List head for siblings.
+ * @obsolete:		Whether the commit destination target is obsolete.
  *
  * Each monitoring context could have multiple targets.  For example, a context
  * for virtual memory address spaces could have multiple target processes.  The
  * @pid should be set for appropriate &struct damon_operations including the
  * virtual address spaces monitoring operations.
+ *
+ * @obsolete is used only for damon_commit_targets() source targets, to specify
+ * the matching destination targets are obsolete.  Read damon_commit_targets()
+ * to see how it is handled.
  */
 struct damon_target {
 	struct pid *pid;
 	unsigned int nr_regions;
 	struct list_head regions_list;
 	struct list_head list;
+	bool obsolete;
 };
 
 /**
@@ -84,19 +116,21 @@ struct damon_target {
  *
  * @DAMOS_WILLNEED:	Call ``madvise()`` for the region with MADV_WILLNEED.
  * @DAMOS_COLD:		Call ``madvise()`` for the region with MADV_COLD.
- * @DAMOS_PAGEOUT:	Call ``madvise()`` for the region with MADV_PAGEOUT.
+ * @DAMOS_PAGEOUT:	Reclaim the region.
  * @DAMOS_HUGEPAGE:	Call ``madvise()`` for the region with MADV_HUGEPAGE.
  * @DAMOS_NOHUGEPAGE:	Call ``madvise()`` for the region with MADV_NOHUGEPAGE.
  * @DAMOS_LRU_PRIO:	Prioritize the region on its LRU lists.
  * @DAMOS_LRU_DEPRIO:	Deprioritize the region on its LRU lists.
+ * @DAMOS_MIGRATE_HOT:  Migrate the regions prioritizing warmer regions.
+ * @DAMOS_MIGRATE_COLD:	Migrate the regions prioritizing colder regions.
  * @DAMOS_STAT:		Do nothing but count the stat.
  * @NR_DAMOS_ACTIONS:	Total number of DAMOS actions
  *
  * The support of each action is up to running &struct damon_operations.
- * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR supports all actions except
- * &enum DAMOS_LRU_PRIO and &enum DAMOS_LRU_DEPRIO.  &enum DAMON_OPS_PADDR
- * supports only &enum DAMOS_PAGEOUT, &enum DAMOS_LRU_PRIO, &enum
- * DAMOS_LRU_DEPRIO, and &DAMOS_STAT.
+ * Refer to 'Operation Action' section of Documentation/mm/damon/design.rst for
+ * status of the supports.
+ *
+ * Note that DAMOS_PAGEOUT doesn't trigger demotions.
  */
 enum damos_action {
 	DAMOS_WILLNEED,
@@ -106,15 +140,82 @@ enum damos_action {
 	DAMOS_NOHUGEPAGE,
 	DAMOS_LRU_PRIO,
 	DAMOS_LRU_DEPRIO,
+	DAMOS_MIGRATE_HOT,
+	DAMOS_MIGRATE_COLD,
 	DAMOS_STAT,		/* Do nothing but only record the stat */
 	NR_DAMOS_ACTIONS,
 };
 
 /**
+ * enum damos_quota_goal_metric - Represents the metric to be used as the goal
+ *
+ * @DAMOS_QUOTA_USER_INPUT:	User-input value.
+ * @DAMOS_QUOTA_SOME_MEM_PSI_US:	System level some memory PSI in us.
+ * @DAMOS_QUOTA_NODE_MEM_USED_BP:	MemUsed ratio of a node.
+ * @DAMOS_QUOTA_NODE_MEM_FREE_BP:	MemFree ratio of a node.
+ * @DAMOS_QUOTA_NODE_MEMCG_USED_BP:	MemUsed ratio of a node for a cgroup.
+ * @DAMOS_QUOTA_NODE_MEMCG_FREE_BP:	MemFree ratio of a node for a cgroup.
+ * @NR_DAMOS_QUOTA_GOAL_METRICS:	Number of DAMOS quota goal metrics.
+ *
+ * Metrics equal to larger than @NR_DAMOS_QUOTA_GOAL_METRICS are unsupported.
+ */
+enum damos_quota_goal_metric {
+	DAMOS_QUOTA_USER_INPUT,
+	DAMOS_QUOTA_SOME_MEM_PSI_US,
+	DAMOS_QUOTA_NODE_MEM_USED_BP,
+	DAMOS_QUOTA_NODE_MEM_FREE_BP,
+	DAMOS_QUOTA_NODE_MEMCG_USED_BP,
+	DAMOS_QUOTA_NODE_MEMCG_FREE_BP,
+	NR_DAMOS_QUOTA_GOAL_METRICS,
+};
+
+/**
+ * struct damos_quota_goal - DAMOS scheme quota auto-tuning goal.
+ * @metric:		Metric to be used for representing the goal.
+ * @target_value:	Target value of @metric to achieve with the tuning.
+ * @current_value:	Current value of @metric.
+ * @last_psi_total:	Last measured total PSI
+ * @nid:		Node id.
+ * @memcg_id:		Memcg id.
+ * @list:		List head for siblings.
+ *
+ * Data structure for getting the current score of the quota tuning goal.  The
+ * score is calculated by how close @current_value and @target_value are.  Then
+ * the score is entered to DAMON's internal feedback loop mechanism to get the
+ * auto-tuned quota.
+ *
+ * If @metric is DAMOS_QUOTA_USER_INPUT, @current_value should be manually
+ * entered by the user, probably inside the kdamond callbacks.  Otherwise,
+ * DAMON sets @current_value with self-measured value of @metric.
+ *
+ * If @metric is DAMOS_QUOTA_NODE_MEM_{USED,FREE}_BP, @nid represents the node
+ * id of the target node to account the used/free memory.
+ *
+ * If @metric is DAMOS_QUOTA_NODE_MEMCG_{USED,FREE}_BP, @nid and @memcg_id
+ * represents the node id and the cgroup to account the used memory for.
+ */
+struct damos_quota_goal {
+	enum damos_quota_goal_metric metric;
+	unsigned long target_value;
+	unsigned long current_value;
+	/* metric-dependent fields */
+	union {
+		u64 last_psi_total;
+		struct {
+			int nid;
+			unsigned short memcg_id;
+		};
+	};
+	struct list_head list;
+};
+
+/**
  * struct damos_quota - Controls the aggressiveness of the given scheme.
+ * @reset_interval:	Charge reset interval in milliseconds.
  * @ms:			Maximum milliseconds that the scheme can use.
  * @sz:			Maximum bytes of memory that the action can be applied.
- * @reset_interval:	Charge reset interval in milliseconds.
+ * @goals:		Head of quota tuning goals (&damos_quota_goal) list.
+ * @esz:		Effective size quota in bytes.
  *
  * @weight_sz:		Weight of the region's size for prioritization.
  * @weight_nr_accesses:	Weight of the region's nr_accesses for prioritization.
@@ -128,9 +229,21 @@ enum damos_action {
  * size quota is set, DAMON tries to apply the action only up to &sz bytes
  * within &reset_interval.
  *
- * Internally, the time quota is transformed to a size quota using estimated
- * throughput of the scheme's action.  DAMON then compares it against &sz and
- * uses smaller one as the effective quota.
+ * To convince the different types of quotas and goals, DAMON internally
+ * converts those into one single size quota called "effective quota".  DAMON
+ * internally uses it as the only one real quota.  The conversion is made as
+ * follows.
+ *
+ * The time quota is transformed to a size quota using estimated throughput of
+ * the scheme's action.  DAMON then compares it against &sz and uses smaller
+ * one as the effective quota.
+ *
+ * If @goals is not empty, DAMON calculates yet another size quota based on the
+ * goals using its internal feedback loop algorithm, for every @reset_interval.
+ * Then, if the new size quota is smaller than the effective quota, it uses the
+ * new size quota as the effective quota.
+ *
+ * The resulting effective size quota in bytes is set to @esz.
  *
  * For selecting regions within the quota, DAMON prioritizes current scheme's
  * target memory regions using the &struct damon_operations->get_scheme_score.
@@ -139,9 +252,11 @@ enum damos_action {
  * encouraged to respect those.
  */
 struct damos_quota {
+	unsigned long reset_interval;
 	unsigned long ms;
 	unsigned long sz;
-	unsigned long reset_interval;
+	struct list_head goals;
+	unsigned long esz;
 
 	unsigned int weight_sz;
 	unsigned int weight_nr_accesses;
@@ -152,8 +267,6 @@ struct damos_quota {
 	unsigned long total_charged_sz;
 	unsigned long total_charged_ns;
 
-	unsigned long esz;	/* Effective size quota in bytes */
-
 	/* For charging the quota */
 	unsigned long charged_sz;
 	unsigned long charged_from;
@@ -161,8 +274,10 @@ struct damos_quota {
 	unsigned long charge_addr_from;
 
 	/* For prioritization */
-	unsigned long histogram[DAMOS_MAX_SCORE + 1];
 	unsigned int min_score;
+
+	/* For feedback loop */
+	unsigned long esz_bp;
 };
 
 /**
@@ -212,54 +327,128 @@ struct damos_watermarks {
  * @sz_tried:	Total size of regions that the scheme is tried to be applied.
  * @nr_applied:	Total number of regions that the scheme is applied.
  * @sz_applied:	Total size of regions that the scheme is applied.
+ * @sz_ops_filter_passed:
+ *		Total bytes that passed ops layer-handled DAMOS filters.
  * @qt_exceeds: Total number of times the quota of the scheme has exceeded.
+ *
+ * "Tried an action to a region" in this context means the DAMOS core logic
+ * determined the region as eligible to apply the action.  The access pattern
+ * (&struct damos_access_pattern), quotas (&struct damos_quota), watermarks
+ * (&struct damos_watermarks) and filters (&struct damos_filter) that handled
+ * on core logic can affect this.  The core logic asks the operation set
+ * (&struct damon_operations) to apply the action to the region.
+ *
+ * "Applied an action to a region" in this context means the operation set
+ * (&struct damon_operations) successfully applied the action to the region, at
+ * least to a part of the region.  The filters (&struct damos_filter) that
+ * handled on operation set layer and type of the action and pages of the
+ * region can affect this.  For example, if a filter is set to exclude
+ * anonymous pages and the region has only anonymous pages, the region will be
+ * failed at applying the action.  If the action is &DAMOS_PAGEOUT and all
+ * pages of the region are already paged out, the region will be failed at
+ * applying the action.
  */
 struct damos_stat {
 	unsigned long nr_tried;
 	unsigned long sz_tried;
 	unsigned long nr_applied;
 	unsigned long sz_applied;
+	unsigned long sz_ops_filter_passed;
 	unsigned long qt_exceeds;
 };
 
 /**
  * enum damos_filter_type - Type of memory for &struct damos_filter
  * @DAMOS_FILTER_TYPE_ANON:	Anonymous pages.
+ * @DAMOS_FILTER_TYPE_ACTIVE:	Active pages.
  * @DAMOS_FILTER_TYPE_MEMCG:	Specific memcg's pages.
+ * @DAMOS_FILTER_TYPE_YOUNG:	Recently accessed pages.
+ * @DAMOS_FILTER_TYPE_HUGEPAGE_SIZE:	Page is part of a hugepage.
+ * @DAMOS_FILTER_TYPE_UNMAPPED:	Unmapped pages.
+ * @DAMOS_FILTER_TYPE_ADDR:	Address range.
+ * @DAMOS_FILTER_TYPE_TARGET:	Data Access Monitoring target.
  * @NR_DAMOS_FILTER_TYPES:	Number of filter types.
  *
- * The support of each filter type is up to running &struct damon_operations.
- * &enum DAMON_OPS_PADDR is supporting all filter types, while
- * &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR are not supporting any
- * filter types.
+ * The anon pages type and memcg type filters are handled by underlying
+ * &struct damon_operations as a part of scheme action trying, and therefore
+ * accounted as 'tried'.  In contrast, other types are handled by core layer
+ * before trying of the action and therefore not accounted as 'tried'.
+ *
+ * The support of the filters that handled by &struct damon_operations depend
+ * on the running &struct damon_operations.
+ * &enum DAMON_OPS_PADDR supports both anon pages type and memcg type filters,
+ * while &enum DAMON_OPS_VADDR and &enum DAMON_OPS_FVADDR don't support any of
+ * the two types.
  */
 enum damos_filter_type {
 	DAMOS_FILTER_TYPE_ANON,
+	DAMOS_FILTER_TYPE_ACTIVE,
 	DAMOS_FILTER_TYPE_MEMCG,
+	DAMOS_FILTER_TYPE_YOUNG,
+	DAMOS_FILTER_TYPE_HUGEPAGE_SIZE,
+	DAMOS_FILTER_TYPE_UNMAPPED,
+	DAMOS_FILTER_TYPE_ADDR,
+	DAMOS_FILTER_TYPE_TARGET,
 	NR_DAMOS_FILTER_TYPES,
 };
 
 /**
  * struct damos_filter - DAMOS action target memory filter.
- * @type:	Type of the page.
- * @matching:	If the matching page should filtered out or in.
+ * @type:	Type of the target memory.
+ * @matching:	Whether this is for @type-matching memory.
+ * @allow:	Whether to include or exclude the @matching memory.
  * @memcg_id:	Memcg id of the question if @type is DAMOS_FILTER_MEMCG.
+ * @addr_range:	Address range if @type is DAMOS_FILTER_TYPE_ADDR.
+ * @target_idx:	Index of the &struct damon_target of
+ *		&damon_ctx->adaptive_targets if @type is
+ *		DAMOS_FILTER_TYPE_TARGET.
+ * @sz_range:	Size range if @type is DAMOS_FILTER_TYPE_HUGEPAGE_SIZE.
  * @list:	List head for siblings.
  *
  * Before applying the &damos->action to a memory region, DAMOS checks if each
- * page of the region matches to this and avoid applying the action if so.
- * Note that the check support is up to &struct damon_operations
- * implementation.
+ * byte of the region matches to this given condition and avoid applying the
+ * action if so.  Support of each filter type depends on the running &struct
+ * damon_operations and the type.  Refer to &enum damos_filter_type for more
+ * details.
  */
 struct damos_filter {
 	enum damos_filter_type type;
 	bool matching;
+	bool allow;
 	union {
 		unsigned short memcg_id;
+		struct damon_addr_range addr_range;
+		int target_idx;
+		struct damon_size_range sz_range;
 	};
 	struct list_head list;
 };
 
+struct damon_ctx;
+struct damos;
+
+/**
+ * struct damos_walk_control - Control damos_walk().
+ *
+ * @walk_fn:	Function to be called back for each region.
+ * @data:	Data that will be passed to walk functions.
+ *
+ * Control damos_walk(), which requests specific kdamond to invoke the given
+ * function to each region that eligible to apply actions of the kdamond's
+ * schemes.  Refer to damos_walk() for more details.
+ */
+struct damos_walk_control {
+	void (*walk_fn)(void *data, struct damon_ctx *ctx,
+			struct damon_target *t, struct damon_region *r,
+			struct damos *s, unsigned long sz_filter_passed);
+	void *data;
+/* private: internal use only */
+	/* informs if the kdamond finished handling of the walk request */
+	struct completion completion;
+	/* informs if the walk is canceled. */
+	bool canceled;
+};
+
 /**
  * struct damos_access_pattern - Target access pattern of the given scheme.
  * @min_sz_region:	Minimum size of target regions.
@@ -279,30 +468,66 @@ struct damos_access_pattern {
 };
 
 /**
+ * struct damos_migrate_dests - Migration destination nodes and their weights.
+ * @node_id_arr:	Array of migration destination node ids.
+ * @weight_arr:		Array of migration weights for @node_id_arr.
+ * @nr_dests:		Length of the @node_id_arr and @weight_arr arrays.
+ *
+ * @node_id_arr is an array of the ids of migration destination nodes.
+ * @weight_arr is an array of the weights for those.  The weights in
+ * @weight_arr are for nodes in @node_id_arr of same array index.
+ */
+struct damos_migrate_dests {
+	unsigned int *node_id_arr;
+	unsigned int *weight_arr;
+	size_t nr_dests;
+};
+
+/**
  * struct damos - Represents a Data Access Monitoring-based Operation Scheme.
  * @pattern:		Access pattern of target regions.
- * @action:		&damo_action to be applied to the target regions.
+ * @action:		&damos_action to be applied to the target regions.
+ * @apply_interval_us:	The time between applying the @action.
  * @quota:		Control the aggressiveness of this scheme.
  * @wmarks:		Watermarks for automated (in)activation of this scheme.
- * @filters:		Additional set of &struct damos_filter for &action.
+ * @migrate_dests:	Destination nodes if @action is "migrate_{hot,cold}".
+ * @target_nid:		Destination node if @action is "migrate_{hot,cold}".
+ * @core_filters:	Additional set of &struct damos_filter for &action.
+ * @ops_filters:	ops layer handling &struct damos_filter objects list.
+ * @last_applied:	Last @action applied ops-managing entity.
  * @stat:		Statistics of this scheme.
  * @list:		List head for siblings.
  *
- * For each aggregation interval, DAMON finds regions which fit in the
+ * For each @apply_interval_us, DAMON finds regions which fit in the
  * &pattern and applies &action to those. To avoid consuming too much
  * CPU time or IO resources for the &action, &quota is used.
  *
+ * If @apply_interval_us is zero, &damon_attrs->aggr_interval is used instead.
+ *
  * To do the work only when needed, schemes can be activated for specific
  * system situations using &wmarks.  If all schemes that registered to the
  * monitoring context are inactive, DAMON stops monitoring either, and just
  * repeatedly checks the watermarks.
  *
- * If all schemes that registered to a &struct damon_ctx are inactive, DAMON
- * stops monitoring and just repeatedly checks the watermarks.
+ * @migrate_dests specifies multiple migration target nodes with different
+ * weights for migrate_hot or migrate_cold actions.  @target_nid is ignored if
+ * this is set.
+ *
+ * @target_nid is used to set the migration target node for migrate_hot or
+ * migrate_cold actions, and @migrate_dests is unset.
  *
  * Before applying the &action to a memory region, &struct damon_operations
  * implementation could check pages of the region and skip &action to respect
- * &filters
+ * &core_filters
+ *
+ * The minimum entity that @action can be applied depends on the underlying
+ * &struct damon_operations.  Since it may not be aligned with the core layer
+ * abstract, namely &struct damon_region, &struct damon_operations could apply
+ * @action to same entity multiple times.  Large folios that underlying on
+ * multiple &struct damon region objects could be such examples.  The &struct
+ * damon_operations can use @last_applied to avoid that.  DAMOS core logic
+ * unsets @last_applied when each regions walking for applying the scheme is
+ * finished.
  *
  * After applying the &action to each region, &stat_count and &stat_sz is
  * updated to reflect the number of regions and total size of regions that the
@@ -311,9 +536,35 @@ struct damos_access_pattern {
 struct damos {
 	struct damos_access_pattern pattern;
 	enum damos_action action;
+	unsigned long apply_interval_us;
+/* private: internal use only */
+	/*
+	 * number of sample intervals that should be passed before applying
+	 * @action
+	 */
+	unsigned long next_apply_sis;
+	/* informs if ongoing DAMOS walk for this scheme is finished */
+	bool walk_completed;
+	/*
+	 * If the current region in the filtering stage is allowed by core
+	 * layer-handled filters.  If true, operations layer allows it, too.
+	 */
+	bool core_filters_allowed;
+	/* whether to reject core/ops filters umatched regions */
+	bool core_filters_default_reject;
+	bool ops_filters_default_reject;
+/* public: */
 	struct damos_quota quota;
 	struct damos_watermarks wmarks;
-	struct list_head filters;
+	union {
+		struct {
+			int target_nid;
+			struct damos_migrate_dests migrate_dests;
+		};
+	};
+	struct list_head core_filters;
+	struct list_head ops_filters;
+	void *last_applied;
 	struct damos_stat stat;
 	struct list_head list;
 };
@@ -334,8 +585,6 @@ enum damon_ops_id {
 	NR_DAMON_OPS,
 };
 
-struct damon_ctx;
-
 /**
  * struct damon_operations - Monitoring operations for given use cases.
  *
@@ -344,10 +593,10 @@ struct damon_ctx;
  * @update:			Update operations-related data structures.
  * @prepare_access_checks:	Prepare next access check of target regions.
  * @check_accesses:		Check the accesses to target regions.
- * @reset_aggregated:		Reset aggregated accesses monitoring results.
  * @get_scheme_score:		Get the score of a region for a scheme.
  * @apply_scheme:		Apply a DAMON-based operation scheme.
  * @target_valid:		Determine if the target is valid.
+ * @cleanup_target:		Clean up each target before deallocation.
  * @cleanup:			Clean up the context.
  *
  * DAMON can be extended for various address spaces and usages.  For this,
@@ -356,8 +605,7 @@ struct damon_ctx;
  * (&damon_ctx.kdamond) calls @init and @prepare_access_checks before starting
  * the monitoring, @update after each &damon_attrs.ops_update_interval, and
  * @check_accesses, @target_valid and @prepare_access_checks after each
- * &damon_attrs.sample_interval.  Finally, @reset_aggregated is called after
- * each &damon_attrs.aggr_interval.
+ * &damon_attrs.sample_interval.
  *
  * Each &struct damon_operations instance having valid @id can be registered
  * via damon_register_ops() and selected by damon_select_ops() later.
@@ -372,16 +620,16 @@ struct damon_ctx;
  * last preparation and update the number of observed accesses of each region.
  * It should also return max number of observed accesses that made as a result
  * of its update.  The value will be used for regions adjustment threshold.
- * @reset_aggregated should reset the access monitoring results that aggregated
- * by @check_accesses.
  * @get_scheme_score should return the priority score of a region for a scheme
  * as an integer in [0, &DAMOS_MAX_SCORE].
  * @apply_scheme is called from @kdamond when a region for user provided
  * DAMON-based operation scheme is found.  It should apply the scheme's action
  * to the region and return bytes of the region that the action is successfully
- * applied.
+ * applied.  It should also report how many bytes of the region has passed
+ * filters (&struct damos_filter) that handled by itself.
  * @target_valid should check whether the target is still valid for the
  * monitoring.
+ * @cleanup_target is called before the target will be deallocated.
  * @cleanup is called from @kdamond just before its termination.
  */
 struct damon_operations {
@@ -390,58 +638,67 @@ struct damon_operations {
 	void (*update)(struct damon_ctx *context);
 	void (*prepare_access_checks)(struct damon_ctx *context);
 	unsigned int (*check_accesses)(struct damon_ctx *context);
-	void (*reset_aggregated)(struct damon_ctx *context);
 	int (*get_scheme_score)(struct damon_ctx *context,
 			struct damon_target *t, struct damon_region *r,
 			struct damos *scheme);
 	unsigned long (*apply_scheme)(struct damon_ctx *context,
 			struct damon_target *t, struct damon_region *r,
-			struct damos *scheme);
+			struct damos *scheme, unsigned long *sz_filter_passed);
 	bool (*target_valid)(struct damon_target *t);
+	void (*cleanup_target)(struct damon_target *t);
 	void (*cleanup)(struct damon_ctx *context);
 };
 
+/*
+ * struct damon_call_control - Control damon_call().
+ *
+ * @fn:			Function to be called back.
+ * @data:		Data that will be passed to @fn.
+ * @repeat:		Repeat invocations.
+ * @return_code:	Return code from @fn invocation.
+ * @dealloc_on_cancel:	De-allocate when canceled.
+ *
+ * Control damon_call(), which requests specific kdamond to invoke a given
+ * function.  Refer to damon_call() for more details.
+ */
+struct damon_call_control {
+	int (*fn)(void *data);
+	void *data;
+	bool repeat;
+	int return_code;
+	bool dealloc_on_cancel;
+/* private: internal use only */
+	/* informs if the kdamond finished handling of the request */
+	struct completion completion;
+	/* informs if the kdamond canceled @fn infocation */
+	bool canceled;
+	/* List head for siblings. */
+	struct list_head list;
+};
+
 /**
- * struct damon_callback - Monitoring events notification callbacks.
- *
- * @before_start:	Called before starting the monitoring.
- * @after_wmarks_check:	Called after each schemes' watermarks check.
- * @after_sampling:	Called after each sampling.
- * @after_aggregation:	Called after each aggregation.
- * @before_damos_apply:	Called before applying DAMOS action.
- * @before_terminate:	Called before terminating the monitoring.
- * @private:		User private data.
- *
- * The monitoring thread (&damon_ctx.kdamond) calls @before_start and
- * @before_terminate just before starting and finishing the monitoring,
- * respectively.  Therefore, those are good places for installing and cleaning
- * @private.
- *
- * The monitoring thread calls @after_wmarks_check after each DAMON-based
- * operation schemes' watermarks check.  If users need to make changes to the
- * attributes of the monitoring context while it's deactivated due to the
- * watermarks, this is the good place to do.
- *
- * The monitoring thread calls @after_sampling and @after_aggregation for each
- * of the sampling intervals and aggregation intervals, respectively.
- * Therefore, users can safely access the monitoring results without additional
- * protection.  For the reason, users are recommended to use these callback for
- * the accesses to the results.
- *
- * If any callback returns non-zero, monitoring stops.
+ * struct damon_intervals_goal - Monitoring intervals auto-tuning goal.
+ *
+ * @access_bp:		Access events observation ratio to achieve in bp.
+ * @aggrs:		Number of aggregations to achieve @access_bp within.
+ * @min_sample_us:	Minimum resulting sampling interval in microseconds.
+ * @max_sample_us:	Maximum resulting sampling interval in microseconds.
+ *
+ * DAMON automatically tunes &damon_attrs->sample_interval and
+ * &damon_attrs->aggr_interval aiming the ratio in bp (1/10,000) of
+ * DAMON-observed access events to theoretical maximum amount within @aggrs
+ * aggregations be same to @access_bp.  The logic increases
+ * &damon_attrs->aggr_interval and &damon_attrs->sampling_interval in same
+ * ratio if the current access events observation ratio is lower than the
+ * target for each @aggrs aggregations, and vice versa.
+ *
+ * If @aggrs is zero, the tuning is disabled and hence this struct is ignored.
  */
-struct damon_callback {
-	void *private;
-
-	int (*before_start)(struct damon_ctx *context);
-	int (*after_wmarks_check)(struct damon_ctx *context);
-	int (*after_sampling)(struct damon_ctx *context);
-	int (*after_aggregation)(struct damon_ctx *context);
-	int (*before_damos_apply)(struct damon_ctx *context,
-			struct damon_target *target,
-			struct damon_region *region,
-			struct damos *scheme);
-	void (*before_terminate)(struct damon_ctx *context);
+struct damon_intervals_goal {
+	unsigned long access_bp;
+	unsigned long aggrs;
+	unsigned long min_sample_us;
+	unsigned long max_sample_us;
 };
 
 /**
@@ -450,26 +707,40 @@ struct damon_callback {
  * @sample_interval:		The time between access samplings.
  * @aggr_interval:		The time between monitor results aggregations.
  * @ops_update_interval:	The time between monitoring operations updates.
+ * @intervals_goal:		Intervals auto-tuning goal.
  * @min_nr_regions:		The minimum number of adaptive monitoring
  *				regions.
  * @max_nr_regions:		The maximum number of adaptive monitoring
  *				regions.
  *
  * For each @sample_interval, DAMON checks whether each region is accessed or
- * not.  It aggregates and keeps the access information (number of accesses to
- * each region) for @aggr_interval time.  DAMON also checks whether the target
- * memory regions need update (e.g., by ``mmap()`` calls from the application,
- * in case of virtual memory monitoring) and applies the changes for each
- * @ops_update_interval.  All time intervals are in micro-seconds.
- * Please refer to &struct damon_operations and &struct damon_callback for more
- * detail.
+ * not during the last @sample_interval.  If such access is found, DAMON
+ * aggregates the information by increasing &damon_region->nr_accesses for
+ * @aggr_interval time.  For each @aggr_interval, the count is reset.  DAMON
+ * also checks whether the target memory regions need update (e.g., by
+ * ``mmap()`` calls from the application, in case of virtual memory monitoring)
+ * and applies the changes for each @ops_update_interval.  All time intervals
+ * are in micro-seconds.  Please refer to &struct damon_operations and &struct
+ * damon_call_control for more detail.
  */
 struct damon_attrs {
 	unsigned long sample_interval;
 	unsigned long aggr_interval;
 	unsigned long ops_update_interval;
+	struct damon_intervals_goal intervals_goal;
 	unsigned long min_nr_regions;
 	unsigned long max_nr_regions;
+/* private: internal use only */
+	/*
+	 * @aggr_interval to @sample_interval ratio.
+	 * Core-external components call damon_set_attrs() with &damon_attrs
+	 * that this field is unset.  In the case, damon_set_attrs() sets this
+	 * field of resulting &damon_attrs.  Core-internal components such as
+	 * kdamond_tune_intervals() calls damon_set_attrs() with &damon_attrs
+	 * that this field is set.  In the case, damon_set_attrs() just keep
+	 * it.
+	 */
+	unsigned long aggr_samples;
 };
 
 /**
@@ -497,8 +768,8 @@ struct damon_attrs {
  * Accesses to other fields must be protected by themselves.
  *
  * @ops:	Set of monitoring operations for given use cases.
- * @callback:	Set of callbacks for monitoring events notifications.
- *
+ * @addr_unit:	Scale factor for core to ops address conversion.
+ * @min_sz_region:		Minimum region size.
  * @adaptive_targets:	Head of monitoring targets (&damon_target) list.
  * @schemes:		Head of schemes (&damos) list.
  */
@@ -506,15 +777,42 @@ struct damon_ctx {
 	struct damon_attrs attrs;
 
 /* private: internal use only */
-	struct timespec64 last_aggregation;
-	struct timespec64 last_ops_update;
+	/* number of sample intervals that passed since this context started */
+	unsigned long passed_sample_intervals;
+	/*
+	 * number of sample intervals that should be passed before next
+	 * aggregation
+	 */
+	unsigned long next_aggregation_sis;
+	/*
+	 * number of sample intervals that should be passed before next ops
+	 * update
+	 */
+	unsigned long next_ops_update_sis;
+	/*
+	 * number of sample intervals that should be passed before next
+	 * intervals tuning
+	 */
+	unsigned long next_intervals_tune_sis;
+	/* for waiting until the execution of the kdamond_fn is started */
+	struct completion kdamond_started;
+	/* for scheme quotas prioritization */
+	unsigned long *regions_score_histogram;
+
+	/* lists of &struct damon_call_control */
+	struct list_head call_controls;
+	struct mutex call_controls_lock;
+
+	struct damos_walk_control *walk_control;
+	struct mutex walk_control_lock;
 
 /* public: */
 	struct task_struct *kdamond;
 	struct mutex kdamond_lock;
 
 	struct damon_operations ops;
-	struct damon_callback callback;
+	unsigned long addr_unit;
+	unsigned long min_sz_region;
 
 	struct list_head adaptive_targets;
 	struct list_head schemes;
@@ -567,11 +865,23 @@ static inline unsigned long damon_sz_region(struct damon_region *r)
 #define damon_for_each_scheme_safe(s, next, ctx) \
 	list_for_each_entry_safe(s, next, &(ctx)->schemes, list)
 
-#define damos_for_each_filter(f, scheme) \
-	list_for_each_entry(f, &(scheme)->filters, list)
+#define damos_for_each_quota_goal(goal, quota) \
+	list_for_each_entry(goal, &quota->goals, list)
+
+#define damos_for_each_quota_goal_safe(goal, next, quota) \
+	list_for_each_entry_safe(goal, next, &(quota)->goals, list)
+
+#define damos_for_each_core_filter(f, scheme) \
+	list_for_each_entry(f, &(scheme)->core_filters, list)
+
+#define damos_for_each_core_filter_safe(f, next, scheme) \
+	list_for_each_entry_safe(f, next, &(scheme)->core_filters, list)
+
+#define damos_for_each_ops_filter(f, scheme) \
+	list_for_each_entry(f, &(scheme)->ops_filters, list)
 
-#define damos_for_each_filter_safe(f, next, scheme) \
-	list_for_each_entry_safe(f, next, &(scheme)->filters, list)
+#define damos_for_each_ops_filter_safe(f, next, scheme) \
+	list_for_each_entry_safe(f, next, &(scheme)->ops_filters, list)
 
 #ifdef CONFIG_DAMON
 
@@ -591,24 +901,37 @@ static inline void damon_insert_region(struct damon_region *r,
 void damon_add_region(struct damon_region *r, struct damon_target *t);
 void damon_destroy_region(struct damon_region *r, struct damon_target *t);
 int damon_set_regions(struct damon_target *t, struct damon_addr_range *ranges,
-		unsigned int nr_ranges);
+		unsigned int nr_ranges, unsigned long min_sz_region);
+void damon_update_region_access_rate(struct damon_region *r, bool accessed,
+		struct damon_attrs *attrs);
 
 struct damos_filter *damos_new_filter(enum damos_filter_type type,
-		bool matching);
+		bool matching, bool allow);
 void damos_add_filter(struct damos *s, struct damos_filter *f);
+bool damos_filter_for_ops(enum damos_filter_type type);
 void damos_destroy_filter(struct damos_filter *f);
 
+struct damos_quota_goal *damos_new_quota_goal(
+		enum damos_quota_goal_metric metric,
+		unsigned long target_value);
+void damos_add_quota_goal(struct damos_quota *q, struct damos_quota_goal *g);
+void damos_destroy_quota_goal(struct damos_quota_goal *goal);
+
 struct damos *damon_new_scheme(struct damos_access_pattern *pattern,
-			enum damos_action action, struct damos_quota *quota,
-			struct damos_watermarks *wmarks);
+			enum damos_action action,
+			unsigned long apply_interval_us,
+			struct damos_quota *quota,
+			struct damos_watermarks *wmarks,
+			int target_nid);
 void damon_add_scheme(struct damon_ctx *ctx, struct damos *s);
 void damon_destroy_scheme(struct damos *s);
+int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src);
 
 struct damon_target *damon_new_target(void);
 void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);
 bool damon_targets_empty(struct damon_ctx *ctx);
 void damon_free_target(struct damon_target *t);
-void damon_destroy_target(struct damon_target *t);
+void damon_destroy_target(struct damon_target *t, struct damon_ctx *ctx);
 unsigned int damon_nr_regions(struct damon_target *t);
 
 struct damon_ctx *damon_new_ctx(void);
@@ -616,6 +939,7 @@ void damon_destroy_ctx(struct damon_ctx *ctx);
 int damon_set_attrs(struct damon_ctx *ctx, struct damon_attrs *attrs);
 void damon_set_schemes(struct damon_ctx *ctx,
 			struct damos **schemes, ssize_t nr_schemes);
+int damon_commit_ctx(struct damon_ctx *old_ctx, struct damon_ctx *new_ctx);
 int damon_nr_running_ctxs(void);
 bool damon_is_registered_ops(enum damon_ops_id id);
 int damon_register_ops(struct damon_operations *ops);
@@ -626,12 +950,25 @@ static inline bool damon_target_has_pid(const struct damon_ctx *ctx)
 	return ctx->ops.id == DAMON_OPS_VADDR || ctx->ops.id == DAMON_OPS_FVADDR;
 }
 
+static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs)
+{
+	/* {aggr,sample}_interval are unsigned long, hence could overflow */
+	return min(attrs->aggr_interval / attrs->sample_interval,
+			(unsigned long)UINT_MAX);
+}
 
+
+bool damon_initialized(void);
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+bool damon_is_running(struct damon_ctx *ctx);
+
+int damon_call(struct damon_ctx *ctx, struct damon_call_control *control);
+int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control);
 
 int damon_set_region_biggest_system_ram_default(struct damon_target *t,
-				unsigned long *start, unsigned long *end);
+				unsigned long *start, unsigned long *end,
+				unsigned long min_sz_region);
 
 #endif	/* CONFIG_DAMON */
 
diff --git a/include/linux/dax.h b/include/linux/dax.h
index bf6258472e49..9d624f4d9df6 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -26,13 +26,7 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			enum dax_access_mode, void **, pfn_t *);
-	/*
-	 * Validate whether this device is usable as an fsdax backing
-	 * device.
-	 */
-	bool (*dax_supported)(struct dax_device *, struct block_device *, int,
-			sector_t, sector_t);
+			enum dax_access_mode, void **, unsigned long *);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 	/*
@@ -63,18 +57,21 @@ void kill_dax(struct dax_device *dax_dev);
 void dax_write_cache(struct dax_device *dax_dev, bool wc);
 bool dax_write_cache_enabled(struct dax_device *dax_dev);
 bool dax_synchronous(struct dax_device *dax_dev);
+void set_dax_nocache(struct dax_device *dax_dev);
+void set_dax_nomc(struct dax_device *dax_dev);
 void set_dax_synchronous(struct dax_device *dax_dev);
 size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
 		void *addr, size_t bytes, struct iov_iter *i);
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
-static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
-					     struct dax_device *dax_dev)
+static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
+					    const struct inode *inode,
+					    struct dax_device *dax_dev)
 {
-	if (!(vma->vm_flags & VM_SYNC))
+	if (!(vm_flags & VM_SYNC))
 		return true;
-	if (!IS_DAX(file_inode(vma->vm_file)))
+	if (!IS_DAX(inode))
 		return false;
 	return dax_synchronous(dax_dev);
 }
@@ -86,11 +83,7 @@ static inline void *dax_holder(struct dax_device *dax_dev)
 static inline struct dax_device *alloc_dax(void *private,
 		const struct dax_operations *ops)
 {
-	/*
-	 * Callers should check IS_ENABLED(CONFIG_DAX) to know if this
-	 * NULL is an error or expected.
-	 */
-	return NULL;
+	return ERR_PTR(-EOPNOTSUPP);
 }
 static inline void put_dax(struct dax_device *dax_dev)
 {
@@ -109,13 +102,20 @@ static inline bool dax_synchronous(struct dax_device *dax_dev)
 {
 	return true;
 }
+static inline void set_dax_nocache(struct dax_device *dax_dev)
+{
+}
+static inline void set_dax_nomc(struct dax_device *dax_dev)
+{
+}
 static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 }
-static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
-				struct dax_device *dax_dev)
+static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
+					    const struct inode *inode,
+					    struct dax_device *dax_dev)
 {
-	return !(vma->vm_flags & VM_SYNC);
+	return !(vm_flags & VM_SYNC);
 }
 static inline size_t dax_recovery_write(struct dax_device *dax_dev,
 		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
@@ -124,9 +124,6 @@ static inline size_t dax_recovery_write(struct dax_device *dax_dev,
 }
 #endif
 
-void set_dax_nocache(struct dax_device *dax_dev);
-void set_dax_nomc(struct dax_device *dax_dev);
-
 struct writeback_control;
 #if defined(CONFIG_BLOCK) && defined(CONFIG_FS_DAX)
 int dax_add_host(struct dax_device *dax_dev, struct gendisk *disk);
@@ -159,8 +156,8 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 
 struct page *dax_layout_busy_page(struct address_space *mapping);
 struct page *dax_layout_busy_page_range(struct address_space *mapping, loff_t start, loff_t end);
-dax_entry_t dax_lock_page(struct page *page);
-void dax_unlock_page(struct page *page, dax_entry_t cookie);
+dax_entry_t dax_lock_folio(struct folio *folio);
+void dax_unlock_folio(struct folio *folio, dax_entry_t cookie);
 dax_entry_t dax_lock_mapping_entry(struct address_space *mapping,
 		unsigned long index, struct page **page);
 void dax_unlock_mapping_entry(struct address_space *mapping,
@@ -182,14 +179,14 @@ static inline int dax_writeback_mapping_range(struct address_space *mapping,
 	return -EOPNOTSUPP;
 }
 
-static inline dax_entry_t dax_lock_page(struct page *page)
+static inline dax_entry_t dax_lock_folio(struct folio *folio)
 {
-	if (IS_DAX(page->mapping->host))
+	if (IS_DAX(folio->mapping->host))
 		return ~0UL;
 	return 0;
 }
 
-static inline void dax_unlock_page(struct page *page, dax_entry_t cookie)
+static inline void dax_unlock_folio(struct folio *folio, dax_entry_t cookie)
 {
 }
 
@@ -212,6 +209,11 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		const struct iomap_ops *ops);
 
+static inline bool dax_page_is_idle(struct page *page)
+{
+	return page && page_ref_count(page) == 0;
+}
+
 #if IS_ENABLED(CONFIG_DAX)
 int dax_read_lock(void);
 void dax_read_unlock(int id);
@@ -225,10 +227,23 @@ static inline void dax_read_unlock(int id)
 {
 }
 #endif /* CONFIG_DAX */
+
+#if !IS_ENABLED(CONFIG_FS_DAX)
+static inline int __must_check dax_break_layout(struct inode *inode,
+			    loff_t start, loff_t end, void (cb)(struct inode *))
+{
+	return 0;
+}
+
+static inline void dax_break_layout_final(struct inode *inode)
+{
+}
+#endif
+
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
+		enum dax_access_mode mode, void **kaddr, unsigned long *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
@@ -241,13 +256,24 @@ void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
-vm_fault_t dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
-		    pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
+vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
+			unsigned long *pfnp, int *errp,
+			const struct iomap_ops *ops);
 vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
-		enum page_entry_size pe_size, pfn_t pfn);
+		unsigned int order, unsigned long pfn);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
+void dax_delete_mapping_range(struct address_space *mapping,
+				loff_t start, loff_t end);
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 				      pgoff_t index);
+int __must_check dax_break_layout(struct inode *inode, loff_t start,
+				loff_t end, void (cb)(struct inode *));
+static inline int __must_check dax_break_layout_inode(struct inode *inode,
+						void (cb)(struct inode *))
+{
+	return dax_break_layout(inode, 0, LLONG_MAX, cb);
+}
+void dax_break_layout_final(struct inode *inode);
 int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 				  struct inode *dest, loff_t destoff,
 				  loff_t len, bool *is_same,
@@ -261,6 +287,19 @@ static inline bool dax_mapping(struct address_space *mapping)
 	return mapping->host && IS_DAX(mapping->host);
 }
 
+/*
+ * Due to dax's memory and block duo personalities, hwpoison reporting
+ * takes into consideration which personality is presently visible.
+ * When dax acts like a block device, such as in block IO, an encounter of
+ * dax hwpoison is reported as -EIO.
+ * When dax acts like memory, such as in page fault, a detection of hwpoison
+ * is reported as -EHWPOISON which leads to VM_FAULT_HWPOISON.
+ */
+static inline int dax_mem2blk_err(int err)
+{
+	return (err == -EHWPOISON) ? -EIO : err;
+}
+
 #ifdef CONFIG_DEV_DAX_HMEM_DEVICES
 void hmem_register_resource(int target_nid, struct resource *r);
 #else
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 6b351e009f59..898c60d21c92 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -57,6 +57,8 @@ struct qstr {
 };
 
 #define QSTR_INIT(n,l) { { { .len = l } }, .name = n }
+#define QSTR_LEN(n,l) (struct qstr)QSTR_INIT(n,l)
+#define QSTR(n) QSTR_LEN(n, strlen(n))
 
 extern const struct qstr empty_name;
 extern const struct qstr slash_name;
@@ -68,16 +70,24 @@ extern const struct qstr dotdot_name;
  * large memory footprint increase).
  */
 #ifdef CONFIG_64BIT
-# define DNAME_INLINE_LEN 32 /* 192 bytes */
+# define DNAME_INLINE_WORDS 5 /* 192 bytes */
 #else
 # ifdef CONFIG_SMP
-#  define DNAME_INLINE_LEN 36 /* 128 bytes */
+#  define DNAME_INLINE_WORDS 9 /* 128 bytes */
 # else
-#  define DNAME_INLINE_LEN 40 /* 128 bytes */
+#  define DNAME_INLINE_WORDS 11 /* 128 bytes */
 # endif
 #endif
 
+#define DNAME_INLINE_LEN (DNAME_INLINE_WORDS*sizeof(unsigned long))
+
+union shortname_store {
+	unsigned char string[DNAME_INLINE_LEN];
+	unsigned long words[DNAME_INLINE_WORDS];
+};
+
 #define d_lock	d_lockref.lock
+#define d_iname d_shortname.string
 
 struct dentry {
 	/* RCU lookup touched fields */
@@ -85,24 +95,32 @@ struct dentry {
 	seqcount_spinlock_t d_seq;	/* per dentry seqlock */
 	struct hlist_bl_node d_hash;	/* lookup hash list */
 	struct dentry *d_parent;	/* parent directory */
-	struct qstr d_name;
+	union {
+	struct qstr __d_name;		/* for use ONLY in fs/dcache.c */
+	const struct qstr d_name;
+	};
 	struct inode *d_inode;		/* Where the name belongs to - NULL is
 					 * negative */
-	unsigned char d_iname[DNAME_INLINE_LEN];	/* small names */
+	union shortname_store d_shortname;
+	/* --- cacheline 1 boundary (64 bytes) was 32 bytes ago --- */
 
 	/* Ref lookup also touches following */
-	struct lockref d_lockref;	/* per-dentry lock and refcount */
 	const struct dentry_operations *d_op;
 	struct super_block *d_sb;	/* The root of the dentry tree */
 	unsigned long d_time;		/* used by d_revalidate */
 	void *d_fsdata;			/* fs-specific data */
+	/* --- cacheline 2 boundary (128 bytes) --- */
+	struct lockref d_lockref;	/* per-dentry lock and refcount
+					 * keep separate from RCU lookup area if
+					 * possible!
+					 */
 
 	union {
 		struct list_head d_lru;		/* LRU list */
 		wait_queue_head_t *d_wait;	/* in-lookup ones only */
 	};
-	struct list_head d_child;	/* child of parent list */
-	struct list_head d_subdirs;	/* our children */
+	struct hlist_node d_sib;	/* child of parent list */
+	struct hlist_head d_children;	/* our children */
 	/*
 	 * d_alias and d_rcu can share memory
 	 */
@@ -111,7 +129,7 @@ struct dentry {
 		struct hlist_bl_node d_in_lookup_hash;	/* only for in-lookup ones */
 	 	struct rcu_head d_rcu;
 	} d_u;
-} __randomize_layout;
+};
 
 /*
  * dentry->d_lock spinlock nesting subclasses:
@@ -125,8 +143,14 @@ enum dentry_d_lock_class
 	DENTRY_D_LOCK_NESTED
 };
 
+enum d_real_type {
+	D_REAL_DATA,
+	D_REAL_METADATA,
+};
+
 struct dentry_operations {
-	int (*d_revalidate)(struct dentry *, unsigned int);
+	int (*d_revalidate)(struct inode *, const struct qstr *,
+			    struct dentry *, unsigned int);
 	int (*d_weak_revalidate)(struct dentry *, unsigned int);
 	int (*d_hash)(const struct dentry *, struct qstr *);
 	int (*d_compare)(const struct dentry *,
@@ -139,7 +163,9 @@ struct dentry_operations {
 	char *(*d_dname)(struct dentry *, char *, int);
 	struct vfsmount *(*d_automount)(struct path *);
 	int (*d_manage)(const struct path *, bool);
-	struct dentry *(*d_real)(struct dentry *, const struct inode *);
+	struct dentry *(*d_real)(struct dentry *, enum d_real_type type);
+	bool (*d_unalias_trylock)(const struct dentry *);
+	void (*d_unalias_unlock)(const struct dentry *);
 } ____cacheline_aligned;
 
 /*
@@ -151,68 +177,59 @@ struct dentry_operations {
  */
 
 /* d_flags entries */
-#define DCACHE_OP_HASH			0x00000001
-#define DCACHE_OP_COMPARE		0x00000002
-#define DCACHE_OP_REVALIDATE		0x00000004
-#define DCACHE_OP_DELETE		0x00000008
-#define DCACHE_OP_PRUNE			0x00000010
-
-#define	DCACHE_DISCONNECTED		0x00000020
-     /* This dentry is possibly not currently connected to the dcache tree, in
-      * which case its parent will either be itself, or will have this flag as
-      * well.  nfsd will not use a dentry with this bit set, but will first
-      * endeavour to clear the bit either by discovering that it is connected,
-      * or by performing lookup operations.   Any filesystem which supports
-      * nfsd_operations MUST have a lookup function which, if it finds a
-      * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that
-      * dentry into place and return that dentry rather than the passed one,
-      * typically using d_splice_alias. */
-
-#define DCACHE_REFERENCED		0x00000040 /* Recently used, don't discard. */
-
-#define DCACHE_DONTCACHE		0x00000080 /* Purge from memory on final dput() */
-
-#define DCACHE_CANT_MOUNT		0x00000100
-#define DCACHE_GENOCIDE			0x00000200
-#define DCACHE_SHRINK_LIST		0x00000400
-
-#define DCACHE_OP_WEAK_REVALIDATE	0x00000800
-
-#define DCACHE_NFSFS_RENAMED		0x00001000
-     /* this dentry has been "silly renamed" and has to be deleted on the last
-      * dput() */
-#define DCACHE_COOKIE			0x00002000 /* For use by dcookie subsystem */
-#define DCACHE_FSNOTIFY_PARENT_WATCHED	0x00004000
-     /* Parent inode is watched by some fsnotify listener */
-
-#define DCACHE_DENTRY_KILLED		0x00008000
-
-#define DCACHE_MOUNTED			0x00010000 /* is a mountpoint */
-#define DCACHE_NEED_AUTOMOUNT		0x00020000 /* handle automount on this dir */
-#define DCACHE_MANAGE_TRANSIT		0x00040000 /* manage transit from this dirent */
+enum dentry_flags {
+	DCACHE_OP_HASH			= BIT(0),
+	DCACHE_OP_COMPARE		= BIT(1),
+	DCACHE_OP_REVALIDATE		= BIT(2),
+	DCACHE_OP_DELETE		= BIT(3),
+	DCACHE_OP_PRUNE			= BIT(4),
+	/*
+	 * This dentry is possibly not currently connected to the dcache tree,
+	 * in which case its parent will either be itself, or will have this
+	 * flag as well.  nfsd will not use a dentry with this bit set, but will
+	 * first endeavour to clear the bit either by discovering that it is
+	 * connected, or by performing lookup operations.  Any filesystem which
+	 * supports nfsd_operations MUST have a lookup function which, if it
+	 * finds a directory inode with a DCACHE_DISCONNECTED dentry, will
+	 * d_move that dentry into place and return that dentry rather than the
+	 * passed one, typically using d_splice_alias.
+	 */
+	DCACHE_DISCONNECTED		= BIT(5),
+	DCACHE_REFERENCED		= BIT(6),	/* Recently used, don't discard. */
+	DCACHE_DONTCACHE		= BIT(7),	/* Purge from memory on final dput() */
+	DCACHE_CANT_MOUNT		= BIT(8),
+	DCACHE_SHRINK_LIST		= BIT(10),
+	DCACHE_OP_WEAK_REVALIDATE	= BIT(11),
+	/*
+	 * this dentry has been "silly renamed" and has to be deleted on the
+	 * last dput()
+	 */
+	DCACHE_NFSFS_RENAMED		= BIT(12),
+	DCACHE_FSNOTIFY_PARENT_WATCHED	= BIT(13),	/* Parent inode is watched by some fsnotify listener */
+	DCACHE_DENTRY_KILLED		= BIT(14),
+	DCACHE_MOUNTED			= BIT(15),	/* is a mountpoint */
+	DCACHE_NEED_AUTOMOUNT		= BIT(16),	/* handle automount on this dir */
+	DCACHE_MANAGE_TRANSIT		= BIT(17),	/* manage transit from this dirent */
+	DCACHE_LRU_LIST			= BIT(18),
+	DCACHE_ENTRY_TYPE		= (7 << 19),	/* bits 19..21 are for storing type: */
+	DCACHE_MISS_TYPE		= (0 << 19),	/* Negative dentry */
+	DCACHE_WHITEOUT_TYPE		= (1 << 19),	/* Whiteout dentry (stop pathwalk) */
+	DCACHE_DIRECTORY_TYPE		= (2 << 19),	/* Normal directory */
+	DCACHE_AUTODIR_TYPE		= (3 << 19),	/* Lookupless directory (presumed automount) */
+	DCACHE_REGULAR_TYPE		= (4 << 19),	/* Regular file type */
+	DCACHE_SPECIAL_TYPE		= (5 << 19),	/* Other file type */
+	DCACHE_SYMLINK_TYPE		= (6 << 19),	/* Symlink */
+	DCACHE_NOKEY_NAME		= BIT(22),	/* Encrypted name encoded without key */
+	DCACHE_OP_REAL			= BIT(23),
+	DCACHE_PAR_LOOKUP		= BIT(24),	/* being looked up (with parent locked shared) */
+	DCACHE_DENTRY_CURSOR		= BIT(25),
+	DCACHE_NORCU			= BIT(26),	/* No RCU delay for freeing */
+	DCACHE_PERSISTENT		= BIT(27)
+};
+
 #define DCACHE_MANAGED_DENTRY \
 	(DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT)
 
-#define DCACHE_LRU_LIST			0x00080000
-
-#define DCACHE_ENTRY_TYPE		0x00700000
-#define DCACHE_MISS_TYPE		0x00000000 /* Negative dentry (maybe fallthru to nowhere) */
-#define DCACHE_WHITEOUT_TYPE		0x00100000 /* Whiteout dentry (stop pathwalk) */
-#define DCACHE_DIRECTORY_TYPE		0x00200000 /* Normal directory */
-#define DCACHE_AUTODIR_TYPE		0x00300000 /* Lookupless directory (presumed automount) */
-#define DCACHE_REGULAR_TYPE		0x00400000 /* Regular file type (or fallthru to such) */
-#define DCACHE_SPECIAL_TYPE		0x00500000 /* Other file type (or fallthru to such) */
-#define DCACHE_SYMLINK_TYPE		0x00600000 /* Symlink (or fallthru to such) */
-
-#define DCACHE_MAY_FREE			0x00800000
-#define DCACHE_FALLTHRU			0x01000000 /* Fall through to lower layer */
-#define DCACHE_NOKEY_NAME		0x02000000 /* Encrypted name encoded without key */
-#define DCACHE_OP_REAL			0x04000000
-
-#define DCACHE_PAR_LOOKUP		0x10000000 /* being looked up (with parent locked shared) */
-#define DCACHE_DENTRY_CURSOR		0x20000000
-#define DCACHE_NORCU			0x40000000 /* No RCU delay for freeing */
-
 extern seqlock_t rename_lock;
 
 /*
@@ -220,12 +237,9 @@ extern seqlock_t rename_lock;
  */
 extern void d_instantiate(struct dentry *, struct inode *);
 extern void d_instantiate_new(struct dentry *, struct inode *);
-extern struct dentry * d_instantiate_unique(struct dentry *, struct inode *);
-extern struct dentry * d_instantiate_anon(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
-extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op);
 
 /* allocate/de-allocate */
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
@@ -233,28 +247,29 @@ extern struct dentry * d_alloc_anon(struct super_block *);
 extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
 					wait_queue_head_t *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
+/* weird procfs mess; *NOT* exported */
+extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *,
+					  const struct dentry_operations *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
 			const struct qstr *name);
-extern struct dentry * d_exact_alias(struct dentry *, struct inode *);
 extern struct dentry *d_find_any_alias(struct inode *inode);
 extern struct dentry * d_obtain_alias(struct inode *);
 extern struct dentry * d_obtain_root(struct inode *);
 extern void shrink_dcache_sb(struct super_block *);
 extern void shrink_dcache_parent(struct dentry *);
-extern void shrink_dcache_for_umount(struct super_block *);
 extern void d_invalidate(struct dentry *);
 
 /* only used at mount-time */
 extern struct dentry * d_make_root(struct inode *);
 
-/* <clickety>-<click> the ramfs-type tree */
-extern void d_genocide(struct dentry *);
-
+extern void d_mark_tmpfile(struct file *, struct inode *);
 extern void d_tmpfile(struct file *, struct inode *);
 
 extern struct dentry *d_find_alias(struct inode *);
 extern void d_prune_aliases(struct inode *);
+extern void d_dispose_if_unused(struct dentry *, struct list_head *);
+extern void shrink_dentry_list(struct list_head *);
 
 extern struct dentry *d_find_alias_rcu(struct inode *);
 
@@ -273,18 +288,15 @@ extern void d_move(struct dentry *, struct dentry *);
 extern void d_exchange(struct dentry *, struct dentry *);
 extern struct dentry *d_ancestor(struct dentry *, struct dentry *);
 
-/* appendix may either be NULL or be used for transname suffixes */
 extern struct dentry *d_lookup(const struct dentry *, const struct qstr *);
-extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *);
-extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *);
-extern struct dentry *__d_lookup_rcu(const struct dentry *parent,
-				const struct qstr *name, unsigned *seq);
 
 static inline unsigned d_count(const struct dentry *dentry)
 {
 	return dentry->d_lockref.count;
 }
 
+ino_t d_parent_ino(struct dentry *dentry);
+
 /*
  * helper function for dentry_operations.d_dname() members
  */
@@ -300,20 +312,40 @@ extern char *dentry_path(const struct dentry *, char *, int);
 /* Allocation counts.. */
 
 /**
- *	dget, dget_dlock -	get a reference to a dentry
- *	@dentry: dentry to get a reference to
+ * dget_dlock -	get a reference to a dentry
+ * @dentry: dentry to get a reference to
  *
- *	Given a dentry or %NULL pointer increment the reference count
- *	if appropriate and return the dentry. A dentry will not be 
- *	destroyed when it has references.
+ * Given a live dentry, increment the reference count and return the dentry.
+ * Caller must hold @dentry->d_lock.  Making sure that dentry is alive is
+ * caller's resonsibility.  There are many conditions sufficient to guarantee
+ * that; e.g. anything with non-negative refcount is alive, so's anything
+ * hashed, anything positive, anyone's parent, etc.
  */
 static inline struct dentry *dget_dlock(struct dentry *dentry)
 {
-	if (dentry)
-		dentry->d_lockref.count++;
+	dentry->d_lockref.count++;
 	return dentry;
 }
 
+
+/**
+ * dget - get a reference to a dentry
+ * @dentry: dentry to get a reference to
+ *
+ * Given a dentry or %NULL pointer increment the reference count
+ * if appropriate and return the dentry.  A dentry will not be
+ * destroyed when it has references.  Conversely, a dentry with
+ * no references can disappear for any number of reasons, starting
+ * with memory pressure.  In other words, that primitive is
+ * used to clone an existing reference; using it on something with
+ * zero refcount is a bug.
+ *
+ * NOTE: it will spin if @dentry->d_lock is held.  From the deadlock
+ * avoidance point of view it is equivalent to spin_lock()/increment
+ * refcount/spin_unlock(), so calling it under @dentry->d_lock is
+ * always a bug; so's calling it under ->d_lock on any of its descendents.
+ *
+ */
 static inline struct dentry *dget(struct dentry *dentry)
 {
 	if (dentry)
@@ -324,12 +356,11 @@ static inline struct dentry *dget(struct dentry *dentry)
 extern struct dentry *dget_parent(struct dentry *dentry);
 
 /**
- *	d_unhashed -	is dentry hashed
- *	@dentry: entry to check
+ * d_unhashed - is dentry hashed
+ * @dentry: entry to check
  *
- *	Returns true if the dentry passed is not currently hashed.
+ * Returns true if the dentry passed is not currently hashed.
  */
- 
 static inline int d_unhashed(const struct dentry *dentry)
 {
 	return hlist_bl_unhashed(&dentry->d_hash);
@@ -489,20 +520,7 @@ static inline int simple_positive(const struct dentry *dentry)
 	return d_really_is_positive(dentry) && !d_unhashed(dentry);
 }
 
-extern void d_set_fallthru(struct dentry *dentry);
-
-static inline bool d_is_fallthru(const struct dentry *dentry)
-{
-	return dentry->d_flags & DCACHE_FALLTHRU;
-}
-
-
-extern int sysctl_vfs_cache_pressure;
-
-static inline unsigned long vfs_pressure_ratio(unsigned long val)
-{
-	return mult_frac(val, sysctl_vfs_cache_pressure, 100);
-}
+unsigned long vfs_pressure_ratio(unsigned long val);
 
 /**
  * d_inode - Get the actual inode of this dentry
@@ -546,41 +564,25 @@ static inline struct inode *d_backing_inode(const struct dentry *upper)
 }
 
 /**
- * d_backing_dentry - Get upper or lower dentry we should be using
- * @upper: The upper layer
- *
- * This is the helper that should be used to get the dentry of the inode that
- * will be used if this dentry were opened as a file.  It may be the upper
- * dentry or it may be a lower dentry pinned by the upper.
- *
- * Normal filesystems should not use this to access their own dentries.
- */
-static inline struct dentry *d_backing_dentry(struct dentry *upper)
-{
-	return upper;
-}
-
-/**
  * d_real - Return the real dentry
  * @dentry: the dentry to query
- * @inode: inode to select the dentry from multiple layers (can be NULL)
+ * @type: the type of real dentry (data or metadata)
  *
  * If dentry is on a union/overlay, then return the underlying, real dentry.
  * Otherwise return the dentry itself.
  *
  * See also: Documentation/filesystems/vfs.rst
  */
-static inline struct dentry *d_real(struct dentry *dentry,
-				    const struct inode *inode)
+static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type)
 {
 	if (unlikely(dentry->d_flags & DCACHE_OP_REAL))
-		return dentry->d_op->d_real(dentry, inode);
+		return dentry->d_op->d_real(dentry, type);
 	else
 		return dentry;
 }
 
 /**
- * d_real_inode - Return the real inode
+ * d_real_inode - Return the real inode hosting the data
  * @dentry: The dentry to query
  *
  * If dentry is on a union/overlay, then return the underlying, real inode.
@@ -589,14 +591,28 @@ static inline struct dentry *d_real(struct dentry *dentry,
 static inline struct inode *d_real_inode(const struct dentry *dentry)
 {
 	/* This usage of d_real() results in const dentry */
-	return d_backing_inode(d_real((struct dentry *) dentry, NULL));
+	return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA));
 }
 
 struct name_snapshot {
 	struct qstr name;
-	unsigned char inline_name[DNAME_INLINE_LEN];
+	union shortname_store inline_name;
 };
 void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *);
 void release_dentry_name_snapshot(struct name_snapshot *);
 
+static inline struct dentry *d_first_child(const struct dentry *dentry)
+{
+	return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib);
+}
+
+static inline struct dentry *d_next_sibling(const struct dentry *dentry)
+{
+	return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib);
+}
+
+void set_default_d_op(struct super_block *, const struct dentry_operations *);
+struct dentry *d_make_persistent(struct dentry *, struct inode *);
+void d_make_discardable(struct dentry *dentry);
+
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/dccp.h b/include/linux/dccp.h
index 325af611909f..0b61b8b996d4 100644
--- a/include/linux/dccp.h
+++ b/include/linux/dccp.h
@@ -2,79 +2,8 @@
 #ifndef _LINUX_DCCP_H
 #define _LINUX_DCCP_H
 
-
-#include <linux/in.h>
-#include <linux/interrupt.h>
-#include <linux/ktime.h>
-#include <linux/list.h>
-#include <linux/uio.h>
-#include <linux/workqueue.h>
-
-#include <net/inet_connection_sock.h>
-#include <net/inet_sock.h>
-#include <net/inet_timewait_sock.h>
-#include <net/tcp_states.h>
 #include <uapi/linux/dccp.h>
 
-enum dccp_state {
-	DCCP_OPEN	     = TCP_ESTABLISHED,
-	DCCP_REQUESTING	     = TCP_SYN_SENT,
-	DCCP_LISTEN	     = TCP_LISTEN,
-	DCCP_RESPOND	     = TCP_SYN_RECV,
-	/*
-	 * States involved in closing a DCCP connection:
-	 * 1) ACTIVE_CLOSEREQ is entered by a server sending a CloseReq.
-	 *
-	 * 2) CLOSING can have three different meanings (RFC 4340, 8.3):
-	 *  a. Client has performed active-close, has sent a Close to the server
-	 *     from state OPEN or PARTOPEN, and is waiting for the final Reset
-	 *     (in this case, SOCK_DONE == 1).
-	 *  b. Client is asked to perform passive-close, by receiving a CloseReq
-	 *     in (PART)OPEN state. It sends a Close and waits for final Reset
-	 *     (in this case, SOCK_DONE == 0).
-	 *  c. Server performs an active-close as in (a), keeps TIMEWAIT state.
-	 *
-	 * 3) The following intermediate states are employed to give passively
-	 *    closing nodes a chance to process their unread data:
-	 *    - PASSIVE_CLOSE    (from OPEN => CLOSED) and
-	 *    - PASSIVE_CLOSEREQ (from (PART)OPEN to CLOSING; case (b) above).
-	 */
-	DCCP_ACTIVE_CLOSEREQ = TCP_FIN_WAIT1,
-	DCCP_PASSIVE_CLOSE   = TCP_CLOSE_WAIT,	/* any node receiving a Close */
-	DCCP_CLOSING	     = TCP_CLOSING,
-	DCCP_TIME_WAIT	     = TCP_TIME_WAIT,
-	DCCP_CLOSED	     = TCP_CLOSE,
-	DCCP_NEW_SYN_RECV    = TCP_NEW_SYN_RECV,
-	DCCP_PARTOPEN	     = TCP_MAX_STATES,
-	DCCP_PASSIVE_CLOSEREQ,			/* clients receiving CloseReq */
-	DCCP_MAX_STATES
-};
-
-enum {
-	DCCPF_OPEN	      = TCPF_ESTABLISHED,
-	DCCPF_REQUESTING      = TCPF_SYN_SENT,
-	DCCPF_LISTEN	      = TCPF_LISTEN,
-	DCCPF_RESPOND	      = TCPF_SYN_RECV,
-	DCCPF_ACTIVE_CLOSEREQ = TCPF_FIN_WAIT1,
-	DCCPF_CLOSING	      = TCPF_CLOSING,
-	DCCPF_TIME_WAIT	      = TCPF_TIME_WAIT,
-	DCCPF_CLOSED	      = TCPF_CLOSE,
-	DCCPF_NEW_SYN_RECV    = TCPF_NEW_SYN_RECV,
-	DCCPF_PARTOPEN	      = (1 << DCCP_PARTOPEN),
-};
-
-static inline struct dccp_hdr *dccp_hdr(const struct sk_buff *skb)
-{
-	return (struct dccp_hdr *)skb_transport_header(skb);
-}
-
-static inline struct dccp_hdr *dccp_zeroed_hdr(struct sk_buff *skb, int headlen)
-{
-	skb_push(skb, headlen);
-	skb_reset_transport_header(skb);
-	return memset(skb_transport_header(skb), 0, headlen);
-}
-
 static inline struct dccp_hdr_ext *dccp_hdrx(const struct dccp_hdr *dh)
 {
 	return (struct dccp_hdr_ext *)((unsigned char *)dh + sizeof(*dh));
@@ -85,12 +14,6 @@ static inline unsigned int __dccp_basic_hdr_len(const struct dccp_hdr *dh)
 	return sizeof(*dh) + (dh->dccph_x ? sizeof(struct dccp_hdr_ext) : 0);
 }
 
-static inline unsigned int dccp_basic_hdr_len(const struct sk_buff *skb)
-{
-	const struct dccp_hdr *dh = dccp_hdr(skb);
-	return __dccp_basic_hdr_len(dh);
-}
-
 static inline __u64 dccp_hdr_seq(const struct dccp_hdr *dh)
 {
 	__u64 seq_nr =  ntohs(dh->dccph_seq);
@@ -103,222 +26,10 @@ static inline __u64 dccp_hdr_seq(const struct dccp_hdr *dh)
 	return seq_nr;
 }
 
-static inline struct dccp_hdr_request *dccp_hdr_request(struct sk_buff *skb)
-{
-	return (struct dccp_hdr_request *)(skb_transport_header(skb) +
-					   dccp_basic_hdr_len(skb));
-}
-
-static inline struct dccp_hdr_ack_bits *dccp_hdr_ack_bits(const struct sk_buff *skb)
-{
-	return (struct dccp_hdr_ack_bits *)(skb_transport_header(skb) +
-					    dccp_basic_hdr_len(skb));
-}
-
-static inline u64 dccp_hdr_ack_seq(const struct sk_buff *skb)
-{
-	const struct dccp_hdr_ack_bits *dhack = dccp_hdr_ack_bits(skb);
-	return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) + ntohl(dhack->dccph_ack_nr_low);
-}
-
-static inline struct dccp_hdr_response *dccp_hdr_response(struct sk_buff *skb)
-{
-	return (struct dccp_hdr_response *)(skb_transport_header(skb) +
-					    dccp_basic_hdr_len(skb));
-}
-
-static inline struct dccp_hdr_reset *dccp_hdr_reset(struct sk_buff *skb)
-{
-	return (struct dccp_hdr_reset *)(skb_transport_header(skb) +
-					 dccp_basic_hdr_len(skb));
-}
-
 static inline unsigned int __dccp_hdr_len(const struct dccp_hdr *dh)
 {
 	return __dccp_basic_hdr_len(dh) +
 	       dccp_packet_hdr_len(dh->dccph_type);
 }
 
-static inline unsigned int dccp_hdr_len(const struct sk_buff *skb)
-{
-	return __dccp_hdr_len(dccp_hdr(skb));
-}
-
-/**
- * struct dccp_request_sock  -  represent DCCP-specific connection request
- * @dreq_inet_rsk: structure inherited from
- * @dreq_iss: initial sequence number, sent on the first Response (RFC 4340, 7.1)
- * @dreq_gss: greatest sequence number sent (for retransmitted Responses)
- * @dreq_isr: initial sequence number received in the first Request
- * @dreq_gsr: greatest sequence number received (for retransmitted Request(s))
- * @dreq_service: service code present on the Request (there is just one)
- * @dreq_featneg: feature negotiation options for this connection
- * The following two fields are analogous to the ones in dccp_sock:
- * @dreq_timestamp_echo: last received timestamp to echo (13.1)
- * @dreq_timestamp_echo: the time of receiving the last @dreq_timestamp_echo
- */
-struct dccp_request_sock {
-	struct inet_request_sock dreq_inet_rsk;
-	__u64			 dreq_iss;
-	__u64			 dreq_gss;
-	__u64			 dreq_isr;
-	__u64			 dreq_gsr;
-	__be32			 dreq_service;
-	spinlock_t		 dreq_lock;
-	struct list_head	 dreq_featneg;
-	__u32			 dreq_timestamp_echo;
-	__u32			 dreq_timestamp_time;
-};
-
-static inline struct dccp_request_sock *dccp_rsk(const struct request_sock *req)
-{
-	return (struct dccp_request_sock *)req;
-}
-
-extern struct inet_timewait_death_row dccp_death_row;
-
-extern int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
-			      struct sk_buff *skb);
-
-struct dccp_options_received {
-	u64	dccpor_ndp:48;
-	u32	dccpor_timestamp;
-	u32	dccpor_timestamp_echo;
-	u32	dccpor_elapsed_time;
-};
-
-struct ccid;
-
-enum dccp_role {
-	DCCP_ROLE_UNDEFINED,
-	DCCP_ROLE_LISTEN,
-	DCCP_ROLE_CLIENT,
-	DCCP_ROLE_SERVER,
-};
-
-struct dccp_service_list {
-	__u32	dccpsl_nr;
-	__be32	dccpsl_list[];
-};
-
-#define DCCP_SERVICE_INVALID_VALUE htonl((__u32)-1)
-#define DCCP_SERVICE_CODE_IS_ABSENT		0
-
-static inline bool dccp_list_has_service(const struct dccp_service_list *sl,
-					const __be32 service)
-{
-	if (likely(sl != NULL)) {
-		u32 i = sl->dccpsl_nr;
-		while (i--)
-			if (sl->dccpsl_list[i] == service)
-				return true;
-	}
-	return false;
-}
-
-struct dccp_ackvec;
-
-/**
- * struct dccp_sock - DCCP socket state
- *
- * @dccps_swl - sequence number window low
- * @dccps_swh - sequence number window high
- * @dccps_awl - acknowledgement number window low
- * @dccps_awh - acknowledgement number window high
- * @dccps_iss - initial sequence number sent
- * @dccps_isr - initial sequence number received
- * @dccps_osr - first OPEN sequence number received
- * @dccps_gss - greatest sequence number sent
- * @dccps_gsr - greatest valid sequence number received
- * @dccps_gar - greatest valid ack number received on a non-Sync; initialized to %dccps_iss
- * @dccps_service - first (passive sock) or unique (active sock) service code
- * @dccps_service_list - second .. last service code on passive socket
- * @dccps_timestamp_echo - latest timestamp received on a TIMESTAMP option
- * @dccps_timestamp_time - time of receiving latest @dccps_timestamp_echo
- * @dccps_l_ack_ratio - feature-local Ack Ratio
- * @dccps_r_ack_ratio - feature-remote Ack Ratio
- * @dccps_l_seq_win - local Sequence Window (influences ack number validity)
- * @dccps_r_seq_win - remote Sequence Window (influences seq number validity)
- * @dccps_pcslen - sender   partial checksum coverage (via sockopt)
- * @dccps_pcrlen - receiver partial checksum coverage (via sockopt)
- * @dccps_send_ndp_count - local Send NDP Count feature (7.7.2)
- * @dccps_ndp_count - number of Non Data Packets since last data packet
- * @dccps_mss_cache - current value of MSS (path MTU minus header sizes)
- * @dccps_rate_last - timestamp for rate-limiting DCCP-Sync (RFC 4340, 7.5.4)
- * @dccps_featneg - tracks feature-negotiation state (mostly during handshake)
- * @dccps_hc_rx_ackvec - rx half connection ack vector
- * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection)
- * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection)
- * @dccps_options_received - parsed set of retrieved options
- * @dccps_qpolicy - TX dequeueing policy, one of %dccp_packet_dequeueing_policy
- * @dccps_tx_qlen - maximum length of the TX queue
- * @dccps_role - role of this sock, one of %dccp_role
- * @dccps_hc_rx_insert_options - receiver wants to add options when acking
- * @dccps_hc_tx_insert_options - sender wants to add options when sending
- * @dccps_server_timewait - server holds timewait state on close (RFC 4340, 8.3)
- * @dccps_sync_scheduled - flag which signals "send out-of-band message soon"
- * @dccps_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets
- * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing)
- * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs)
- */
-struct dccp_sock {
-	/* inet_connection_sock has to be the first member of dccp_sock */
-	struct inet_connection_sock	dccps_inet_connection;
-#define dccps_syn_rtt			dccps_inet_connection.icsk_ack.lrcvtime
-	__u64				dccps_swl;
-	__u64				dccps_swh;
-	__u64				dccps_awl;
-	__u64				dccps_awh;
-	__u64				dccps_iss;
-	__u64				dccps_isr;
-	__u64				dccps_osr;
-	__u64				dccps_gss;
-	__u64				dccps_gsr;
-	__u64				dccps_gar;
-	__be32				dccps_service;
-	__u32				dccps_mss_cache;
-	struct dccp_service_list	*dccps_service_list;
-	__u32				dccps_timestamp_echo;
-	__u32				dccps_timestamp_time;
-	__u16				dccps_l_ack_ratio;
-	__u16				dccps_r_ack_ratio;
-	__u64				dccps_l_seq_win:48;
-	__u64				dccps_r_seq_win:48;
-	__u8				dccps_pcslen:4;
-	__u8				dccps_pcrlen:4;
-	__u8				dccps_send_ndp_count:1;
-	__u64				dccps_ndp_count:48;
-	unsigned long			dccps_rate_last;
-	struct list_head		dccps_featneg;
-	struct dccp_ackvec		*dccps_hc_rx_ackvec;
-	struct ccid			*dccps_hc_rx_ccid;
-	struct ccid			*dccps_hc_tx_ccid;
-	struct dccp_options_received	dccps_options_received;
-	__u8				dccps_qpolicy;
-	__u32				dccps_tx_qlen;
-	enum dccp_role			dccps_role:2;
-	__u8				dccps_hc_rx_insert_options:1;
-	__u8				dccps_hc_tx_insert_options:1;
-	__u8				dccps_server_timewait:1;
-	__u8				dccps_sync_scheduled:1;
-	struct tasklet_struct		dccps_xmitlet;
-	struct timer_list		dccps_xmit_timer;
-};
-
-#define dccp_sk(ptr)	container_of_const(ptr, struct dccp_sock, \
-					   dccps_inet_connection.icsk_inet.sk)
-
-static inline const char *dccp_role(const struct sock *sk)
-{
-	switch (dccp_sk(sk)->dccps_role) {
-	case DCCP_ROLE_UNDEFINED: return "undefined";
-	case DCCP_ROLE_LISTEN:	  return "listen";
-	case DCCP_ROLE_SERVER:	  return "server";
-	case DCCP_ROLE_CLIENT:	  return "client";
-	}
-	return NULL;
-}
-
-extern void dccp_syn_ack_timeout(const struct request_sock *req);
-
 #endif /* _LINUX_DCCP_H */
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index ea2d919fd9c7..7cecda29447e 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -57,7 +57,6 @@ static const struct file_operations __fops = {				\
 	.release = simple_attr_release,					\
 	.read	 = debugfs_attr_read,					\
 	.write	 = (__is_signed) ? debugfs_attr_write_signed : debugfs_attr_write,	\
-	.llseek  = no_llseek,						\
 }
 
 #define DEFINE_DEBUGFS_ATTRIBUTE(__fops, __get, __set, __fmt)		\
@@ -68,13 +67,77 @@ static const struct file_operations __fops = {				\
 
 typedef struct vfsmount *(*debugfs_automount_t)(struct dentry *, void *);
 
+struct debugfs_short_fops {
+	ssize_t (*read)(struct file *, char __user *, size_t, loff_t *);
+	ssize_t (*write)(struct file *, const char __user *, size_t, loff_t *);
+	loff_t (*llseek) (struct file *, loff_t, int);
+};
+
 #if defined(CONFIG_DEBUG_FS)
 
 struct dentry *debugfs_lookup(const char *name, struct dentry *parent);
 
-struct dentry *debugfs_create_file(const char *name, umode_t mode,
-				   struct dentry *parent, void *data,
-				   const struct file_operations *fops);
+struct dentry *debugfs_create_file_full(const char *name, umode_t mode,
+					struct dentry *parent, void *data,
+					const void *aux,
+					const struct file_operations *fops);
+struct dentry *debugfs_create_file_short(const char *name, umode_t mode,
+					 struct dentry *parent, void *data,
+					 const void *aux,
+					 const struct debugfs_short_fops *fops);
+
+/**
+ * debugfs_create_file - create a file in the debugfs filesystem
+ * @name: a pointer to a string containing the name of the file to create.
+ * @mode: the permission that the file should have.
+ * @parent: a pointer to the parent dentry for this file.  This should be a
+ *          directory dentry if set.  If this parameter is NULL, then the
+ *          file will be created in the root of the debugfs filesystem.
+ * @data: a pointer to something that the caller will want to get to later
+ *        on.  The inode.i_private pointer will point to this value on
+ *        the open() call.
+ * @fops: a pointer to a struct file_operations or struct debugfs_short_fops that
+ *        should be used for this file.
+ *
+ * This is the basic "create a file" function for debugfs.  It allows for a
+ * wide range of flexibility in creating a file, or a directory (if you want
+ * to create a directory, the debugfs_create_dir() function is
+ * recommended to be used instead.)
+ *
+ * This function will return a pointer to a dentry if it succeeds.  This
+ * pointer must be passed to the debugfs_remove() function when the file is
+ * to be removed (no automatic cleanup happens if your module is unloaded,
+ * you are responsible here.)  If an error occurs, ERR_PTR(-ERROR) will be
+ * returned.
+ *
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ *
+ * If fops points to a struct debugfs_short_fops, then simple_open() will be
+ * used for the open, and only read/write/llseek are supported and are proxied,
+ * so no module reference or release are needed.
+ *
+ * NOTE: it's expected that most callers should _ignore_ the errors returned
+ * by this function. Other debugfs functions handle the fact that the "dentry"
+ * passed to them could be an error and they don't crash in that case.
+ * Drivers should generally work fine even if debugfs fails to init anyway.
+ */
+#define debugfs_create_file(name, mode, parent, data, fops)			\
+	_Generic(fops,								\
+		 const struct file_operations *: debugfs_create_file_full,	\
+		 const struct debugfs_short_fops *: debugfs_create_file_short,	\
+		 struct file_operations *: debugfs_create_file_full,		\
+		 struct debugfs_short_fops *: debugfs_create_file_short)	\
+		(name, mode, parent, data, NULL, fops)
+
+#define debugfs_create_file_aux(name, mode, parent, data, aux, fops)		\
+	_Generic(fops,								\
+		 const struct file_operations *: debugfs_create_file_full,	\
+		 const struct debugfs_short_fops *: debugfs_create_file_short,	\
+		 struct file_operations *: debugfs_create_file_full,		\
+		 struct debugfs_short_fops *: debugfs_create_file_short)	\
+		(name, mode, parent, data, aux, fops)
+
 struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode,
 				   struct dentry *parent, void *data,
 				   const struct file_operations *fops);
@@ -99,7 +162,7 @@ void debugfs_remove(struct dentry *dentry);
 
 void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
 
-const struct file_operations *debugfs_real_fops(const struct file *filp);
+void *debugfs_get_aux(const struct file *file);
 
 int debugfs_file_get(struct dentry *dentry);
 void debugfs_file_put(struct dentry *dentry);
@@ -111,8 +174,7 @@ ssize_t debugfs_attr_write(struct file *file, const char __user *buf,
 ssize_t debugfs_attr_write_signed(struct file *file, const char __user *buf,
 			size_t len, loff_t *ppos);
 
-struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
-                struct dentry *new_dir, const char *new_name);
+int debugfs_change_name(struct dentry *dentry, const char *fmt, ...) __printf(2, 3);
 
 void debugfs_create_u8(const char *name, umode_t mode, struct dentry *parent,
 		       u8 *value);
@@ -171,6 +233,25 @@ ssize_t debugfs_write_file_bool(struct file *file, const char __user *user_buf,
 ssize_t debugfs_read_file_str(struct file *file, char __user *user_buf,
 			      size_t count, loff_t *ppos);
 
+/**
+ * struct debugfs_cancellation - cancellation data
+ * @list: internal, for keeping track
+ * @cancel: callback to call
+ * @cancel_data: extra data for the callback to call
+ */
+struct debugfs_cancellation {
+	struct list_head list;
+	void (*cancel)(struct dentry *, void *);
+	void *cancel_data;
+};
+
+void __acquires(cancellation)
+debugfs_enter_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+void __releases(cancellation)
+debugfs_leave_cancellation(struct file *file,
+			   struct debugfs_cancellation *cancellation);
+
 #else
 
 #include <linux/err.h>
@@ -187,9 +268,17 @@ static inline struct dentry *debugfs_lookup(const char *name,
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct dentry *debugfs_create_file_aux(const char *name,
+					umode_t mode, struct dentry *parent,
+					void *data, void *aux,
+					const void *fops)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline struct dentry *debugfs_create_file(const char *name, umode_t mode,
 					struct dentry *parent, void *data,
-					const struct file_operations *fops)
+					const void *fops)
 {
 	return ERR_PTR(-ENODEV);
 }
@@ -239,7 +328,7 @@ static inline void debugfs_lookup_and_remove(const char *name,
 					     struct dentry *parent)
 { }
 
-const struct file_operations *debugfs_real_fops(const struct file *filp);
+void *debugfs_get_aux(const struct file *file);
 
 static inline int debugfs_file_get(struct dentry *dentry)
 {
@@ -269,10 +358,10 @@ static inline ssize_t debugfs_attr_write_signed(struct file *file,
 	return -ENODEV;
 }
 
-static inline struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
-                struct dentry *new_dir, char *new_name)
+static inline int __printf(2, 3) debugfs_change_name(struct dentry *dentry,
+					const char *fmt, ...)
 {
-	return ERR_PTR(-ENODEV);
+	return -ENODEV;
 }
 
 static inline void debugfs_create_u8(const char *name, umode_t mode,
@@ -380,6 +469,11 @@ static inline ssize_t debugfs_read_file_str(struct file *file,
 
 #endif
 
+#define debugfs_create_file_aux_num(name, mode, parent, data, n, fops) \
+	debugfs_create_file_aux(name, mode, parent, data, \
+				(void *)(unsigned long)n, fops)
+#define debugfs_get_aux_num(f) (unsigned long)debugfs_get_aux(f)
+
 /**
  * debugfs_create_xul - create a debugfs file that is used to read and write an
  * unsigned long value, formatted in hexadecimal
diff --git a/include/linux/debugobjects.h b/include/linux/debugobjects.h
index 32444686b6ff..8b95545e7924 100644
--- a/include/linux/debugobjects.h
+++ b/include/linux/debugobjects.h
@@ -23,13 +23,17 @@ struct debug_obj_descr;
  * @state:	tracked object state
  * @astate:	current active state
  * @object:	pointer to the real object
+ * @batch_last:	pointer to the last hlist node in a batch
  * @descr:	pointer to an object type specific debug description structure
  */
 struct debug_obj {
-	struct hlist_node	node;
-	enum debug_obj_state	state;
-	unsigned int		astate;
-	void			*object;
+	struct hlist_node		node;
+	enum debug_obj_state		state;
+	unsigned int			astate;
+	union {
+		void			*object;
+		struct hlist_node	*batch_last;
+	};
 	const struct debug_obj_descr *descr;
 };
 
diff --git a/include/linux/decompress/mm.h b/include/linux/decompress/mm.h
index 9192986b1a73..ac862422df15 100644
--- a/include/linux/decompress/mm.h
+++ b/include/linux/decompress/mm.h
@@ -48,7 +48,7 @@ MALLOC_VISIBLE void *malloc(int size)
 	if (!malloc_ptr)
 		malloc_ptr = free_mem_ptr;
 
-	malloc_ptr = (malloc_ptr + 3) & ~3;     /* Align */
+	malloc_ptr = (malloc_ptr + 7) & ~7;     /* Align */
 
 	p = (void *)malloc_ptr;
 	malloc_ptr += size;
diff --git a/include/linux/decompress/unxz.h b/include/linux/decompress/unxz.h
index f764e2a7201e..3dd2658a9dab 100644
--- a/include/linux/decompress/unxz.h
+++ b/include/linux/decompress/unxz.h
@@ -1,10 +1,9 @@
+/* SPDX-License-Identifier: 0BSD */
+
 /*
  * Wrapper for decompressing XZ-compressed kernel, initramfs, and initrd
  *
  * Author: Lasse Collin <lasse.collin@tukaani.org>
- *
- * This file has been put into the public domain.
- * You can do whatever you want with this file.
  */
 
 #ifndef DECOMPRESS_UNXZ_H
diff --git a/include/linux/delay.h b/include/linux/delay.h
index 039e7e0c7378..46412c00033a 100644
--- a/include/linux/delay.h
+++ b/include/linux/delay.h
@@ -6,21 +6,12 @@
  * Copyright (C) 1993 Linus Torvalds
  *
  * Delay routines, using a pre-computed "loops_per_jiffy" value.
- *
- * Please note that ndelay(), udelay() and mdelay() may return early for
- * several reasons:
- *  1. computed loops_per_jiffy too low (due to the time taken to
- *     execute the timer interrupt.)
- *  2. cache behaviour affecting the time it takes to execute the
- *     loop function.
- *  3. CPU clock rate changes.
- *
- * Please see this thread:
- *   https://lists.openwall.net/linux-kernel/2011/01/09/56
+ * Sleep routines using timer list timers or hrtimers.
  */
 
 #include <linux/math.h>
 #include <linux/sched.h>
+#include <linux/jiffies.h>
 
 extern unsigned long loops_per_jiffy;
 
@@ -35,12 +26,21 @@ extern unsigned long loops_per_jiffy;
  * The 2nd mdelay() definition ensures GCC will optimize away the 
  * while loop for the common cases where n <= MAX_UDELAY_MS  --  Paul G.
  */
-
 #ifndef MAX_UDELAY_MS
 #define MAX_UDELAY_MS	5
 #endif
 
 #ifndef mdelay
+/**
+ * mdelay - Inserting a delay based on milliseconds with busy waiting
+ * @n:	requested delay in milliseconds
+ *
+ * See udelay() for basic information about mdelay() and it's variants.
+ *
+ * Please double check, whether mdelay() is the right way to go or whether a
+ * refactoring of the code is the better variant to be able to use msleep()
+ * instead.
+ */
 #define mdelay(n) (\
 	(__builtin_constant_p(n) && (n)<=MAX_UDELAY_MS) ? udelay((n)*1000) : \
 	({unsigned long __ms=(n); while (__ms--) udelay(1000);}))
@@ -56,36 +56,82 @@ static inline void ndelay(unsigned long x)
 
 extern unsigned long lpj_fine;
 void calibrate_delay(void);
+unsigned long calibrate_delay_is_known(void);
 void __attribute__((weak)) calibration_delay_done(void);
 void msleep(unsigned int msecs);
 unsigned long msleep_interruptible(unsigned int msecs);
 void usleep_range_state(unsigned long min, unsigned long max,
 			unsigned int state);
 
+/**
+ * usleep_range - Sleep for an approximate time
+ * @min:	Minimum time in microseconds to sleep
+ * @max:	Maximum time in microseconds to sleep
+ *
+ * For basic information please refer to usleep_range_state().
+ *
+ * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep.
+ */
 static inline void usleep_range(unsigned long min, unsigned long max)
 {
 	usleep_range_state(min, max, TASK_UNINTERRUPTIBLE);
 }
 
-static inline void usleep_idle_range(unsigned long min, unsigned long max)
+/**
+ * usleep_range_idle - Sleep for an approximate time with idle time accounting
+ * @min:	Minimum time in microseconds to sleep
+ * @max:	Maximum time in microseconds to sleep
+ *
+ * For basic information please refer to usleep_range_state().
+ *
+ * The sleeping task has the state TASK_IDLE during the sleep to prevent
+ * contribution to the load average.
+ */
+static inline void usleep_range_idle(unsigned long min, unsigned long max)
 {
 	usleep_range_state(min, max, TASK_IDLE);
 }
 
+/**
+ * ssleep - wrapper for seconds around msleep
+ * @seconds:	Requested sleep duration in seconds
+ *
+ * Please refer to msleep() for detailed information.
+ */
 static inline void ssleep(unsigned int seconds)
 {
 	msleep(seconds * 1000);
 }
 
-/* see Documentation/timers/timers-howto.rst for the thresholds */
+static const unsigned int max_slack_shift = 2;
+#define USLEEP_RANGE_UPPER_BOUND	((TICK_NSEC << max_slack_shift) / NSEC_PER_USEC)
+
+/**
+ * fsleep - flexible sleep which autoselects the best mechanism
+ * @usecs:	requested sleep duration in microseconds
+ *
+ * flseep() selects the best mechanism that will provide maximum 25% slack
+ * to the requested sleep duration. Therefore it uses:
+ *
+ * * udelay() loop for sleep durations <= 10 microseconds to avoid hrtimer
+ *   overhead for really short sleep durations.
+ * * usleep_range() for sleep durations which would lead with the usage of
+ *   msleep() to a slack larger than 25%. This depends on the granularity of
+ *   jiffies.
+ * * msleep() for all other sleep durations.
+ *
+ * Note: When %CONFIG_HIGH_RES_TIMERS is not set, all sleeps are processed with
+ * the granularity of jiffies and the slack might exceed 25% especially for
+ * short sleep durations.
+ */
 static inline void fsleep(unsigned long usecs)
 {
 	if (usecs <= 10)
 		udelay(usecs);
-	else if (usecs <= 20000)
-		usleep_range(usecs, 2 * usecs);
+	else if (usecs < USLEEP_RANGE_UPPER_BOUND)
+		usleep_range(usecs, usecs + (usecs >> max_slack_shift));
 	else
-		msleep(DIV_ROUND_UP(usecs, 1000));
+		msleep(DIV_ROUND_UP(usecs, USEC_PER_MSEC));
 }
 
 #endif /* defined(_LINUX_DELAY_H) */
diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h
index 6639f48dac36..800dcc360db2 100644
--- a/include/linux/delayacct.h
+++ b/include/linux/delayacct.h
@@ -29,25 +29,39 @@ struct task_delay_info {
 	 * XXX_delay contains the accumulated delay time in nanoseconds.
 	 */
 	u64 blkio_start;
+	u64 blkio_delay_max;
+	u64 blkio_delay_min;
 	u64 blkio_delay;	/* wait for sync block io completion */
 	u64 swapin_start;
+	u64 swapin_delay_max;
+	u64 swapin_delay_min;
 	u64 swapin_delay;	/* wait for swapin */
 	u32 blkio_count;	/* total count of the number of sync block */
 				/* io operations performed */
 	u32 swapin_count;	/* total count of swapin */
 
 	u64 freepages_start;
+	u64 freepages_delay_max;
+	u64 freepages_delay_min;
 	u64 freepages_delay;	/* wait for memory reclaim */
 
 	u64 thrashing_start;
+	u64 thrashing_delay_max;
+	u64 thrashing_delay_min;
 	u64 thrashing_delay;	/* wait for thrashing page */
 
 	u64 compact_start;
+	u64 compact_delay_max;
+	u64 compact_delay_min;
 	u64 compact_delay;	/* wait for memory compact */
 
 	u64 wpcopy_start;
+	u64 wpcopy_delay_max;
+	u64 wpcopy_delay_min;
 	u64 wpcopy_delay;	/* wait for write-protect copy */
 
+	u64 irq_delay_max;
+	u64 irq_delay_min;
 	u64 irq_delay;	/* wait for IRQ/SOFTIRQ */
 
 	u32 freepages_count;	/* total count of memory reclaim */
diff --git a/include/linux/dev_printk.h b/include/linux/dev_printk.h
index 8904063d4c9f..eb2094e43050 100644
--- a/include/linux/dev_printk.h
+++ b/include/linux/dev_printk.h
@@ -130,6 +130,16 @@ void _dev_info(const struct device *dev, const char *fmt, ...)
 	})
 
 /*
+ * Dummy dev_printk for disabled debugging statements to use whilst maintaining
+ * gcc's format checking.
+ */
+#define dev_no_printk(level, dev, fmt, ...)				\
+	({								\
+		if (0)							\
+			_dev_printk(level, dev, fmt, ##__VA_ARGS__);	\
+	})
+
+/*
  * #defines for all the dev_<level> macros to prefix with whatever
  * possible use of #define dev_fmt(fmt) ...
  */
@@ -158,10 +168,7 @@ void _dev_info(const struct device *dev, const char *fmt, ...)
 	dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #else
 #define dev_dbg(dev, fmt, ...)						\
-({									\
-	if (0)								\
-		dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \
-})
+	dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #endif
 
 #ifdef CONFIG_PRINTK
@@ -247,20 +254,14 @@ do {									\
 } while (0)
 #else
 #define dev_dbg_ratelimited(dev, fmt, ...)				\
-do {									\
-	if (0)								\
-		dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \
-} while (0)
+	dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #endif
 
 #ifdef VERBOSE_DEBUG
 #define dev_vdbg	dev_dbg
 #else
 #define dev_vdbg(dev, fmt, ...)						\
-({									\
-	if (0)								\
-		dev_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__); \
-})
+	dev_no_printk(KERN_DEBUG, dev, dev_fmt(fmt), ##__VA_ARGS__)
 #endif
 
 /*
@@ -274,4 +275,15 @@ do {									\
 	WARN_ONCE(condition, "%s %s: " format, \
 			dev_driver_string(dev), dev_name(dev), ## arg)
 
+__printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+__printf(3, 4) int dev_warn_probe(const struct device *dev, int err, const char *fmt, ...);
+
+/* Simple helper for dev_err_probe() when ERR_PTR() is to be returned. */
+#define dev_err_ptr_probe(dev, ___err, fmt, ...) \
+	ERR_PTR(dev_err_probe(dev, ___err, fmt, ##__VA_ARGS__))
+
+/* Simple helper for dev_err_probe() when ERR_CAST() is to be returned. */
+#define dev_err_cast_probe(dev, ___err_ptr, fmt, ...) \
+	ERR_PTR(dev_err_probe(dev, PTR_ERR(___err_ptr), fmt, ##__VA_ARGS__))
+
 #endif /* _DEVICE_PRINTK_H_ */
diff --git a/include/linux/devcoredump.h b/include/linux/devcoredump.h
index c008169ed2c6..377892604ff4 100644
--- a/include/linux/devcoredump.h
+++ b/include/linux/devcoredump.h
@@ -12,6 +12,9 @@
 #include <linux/scatterlist.h>
 #include <linux/slab.h>
 
+/* if data isn't read by userspace after 5 minutes then delete it */
+#define DEVCD_TIMEOUT	(HZ * 60 * 5)
+
 /*
  * _devcd_free_sgtable - free all the memory of the given scatterlist table
  * (i.e. both pages and scatterlist instances)
@@ -50,19 +53,22 @@ static inline void _devcd_free_sgtable(struct scatterlist *table)
 	kfree(delete_iter);
 }
 
-
 #ifdef CONFIG_DEV_COREDUMP
 void dev_coredumpv(struct device *dev, void *data, size_t datalen,
 		   gfp_t gfp);
 
-void dev_coredumpm(struct device *dev, struct module *owner,
-		   void *data, size_t datalen, gfp_t gfp,
-		   ssize_t (*read)(char *buffer, loff_t offset, size_t count,
-				   void *data, size_t datalen),
-		   void (*free)(void *data));
+void dev_coredumpm_timeout(struct device *dev, struct module *owner,
+			   void *data, size_t datalen, gfp_t gfp,
+			   ssize_t (*read)(char *buffer, loff_t offset,
+					   size_t count, void *data,
+					   size_t datalen),
+			   void (*free)(void *data),
+			   unsigned long timeout);
 
 void dev_coredumpsg(struct device *dev, struct scatterlist *table,
 		    size_t datalen, gfp_t gfp);
+
+void dev_coredump_put(struct device *dev);
 #else
 static inline void dev_coredumpv(struct device *dev, void *data,
 				 size_t datalen, gfp_t gfp)
@@ -71,11 +77,13 @@ static inline void dev_coredumpv(struct device *dev, void *data,
 }
 
 static inline void
-dev_coredumpm(struct device *dev, struct module *owner,
-	      void *data, size_t datalen, gfp_t gfp,
-	      ssize_t (*read)(char *buffer, loff_t offset, size_t count,
-			      void *data, size_t datalen),
-	      void (*free)(void *data))
+dev_coredumpm_timeout(struct device *dev, struct module *owner,
+		      void *data, size_t datalen, gfp_t gfp,
+		      ssize_t (*read)(char *buffer, loff_t offset,
+				      size_t count, void *data,
+				      size_t datalen),
+		      void (*free)(void *data),
+		      unsigned long timeout)
 {
 	free(data);
 }
@@ -85,6 +93,34 @@ static inline void dev_coredumpsg(struct device *dev, struct scatterlist *table,
 {
 	_devcd_free_sgtable(table);
 }
+static inline void dev_coredump_put(struct device *dev)
+{
+}
 #endif /* CONFIG_DEV_COREDUMP */
 
+/**
+ * dev_coredumpm - create device coredump with read/free methods
+ * @dev: the struct device for the crashed device
+ * @owner: the module that contains the read/free functions, use %THIS_MODULE
+ * @data: data cookie for the @read/@free functions
+ * @datalen: length of the data
+ * @gfp: allocation flags
+ * @read: function to read from the given buffer
+ * @free: function to free the given buffer
+ *
+ * Creates a new device coredump for the given device. If a previous one hasn't
+ * been read yet, the new coredump is discarded. The data lifetime is determined
+ * by the device coredump framework and when it is no longer needed the @free
+ * function will be called to free the data.
+ */
+static inline void dev_coredumpm(struct device *dev, struct module *owner,
+				 void *data, size_t datalen, gfp_t gfp,
+				 ssize_t (*read)(char *buffer, loff_t offset, size_t count,
+						 void *data, size_t datalen),
+				void (*free)(void *data))
+{
+	dev_coredumpm_timeout(dev, owner, data, datalen, gfp, read, free,
+			      DEVCD_TIMEOUT);
+}
+
 #endif /* __DEVCOREDUMP_H */
diff --git a/include/linux/devfreq-governor.h b/include/linux/devfreq-governor.h
new file mode 100644
index 000000000000..dfdd0160a29f
--- /dev/null
+++ b/include/linux/devfreq-governor.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * governor.h - internal header for devfreq governors.
+ *
+ * Copyright (C) 2011 Samsung Electronics
+ *	MyungJoo Ham <myungjoo.ham@samsung.com>
+ *
+ * This header is for devfreq governors
+ */
+
+#ifndef __LINUX_DEVFREQ_DEVFREQ_H__
+#define __LINUX_DEVFREQ_DEVFREQ_H__
+
+#include <linux/devfreq.h>
+
+#define DEVFREQ_NAME_LEN			16
+
+#define to_devfreq(DEV)	container_of((DEV), struct devfreq, dev)
+
+/* Devfreq events */
+#define DEVFREQ_GOV_START			0x1
+#define DEVFREQ_GOV_STOP			0x2
+#define DEVFREQ_GOV_UPDATE_INTERVAL		0x3
+#define DEVFREQ_GOV_SUSPEND			0x4
+#define DEVFREQ_GOV_RESUME			0x5
+
+#define DEVFREQ_MIN_FREQ			0
+#define DEVFREQ_MAX_FREQ			ULONG_MAX
+
+/*
+ * Definition of the governor feature flags
+ * - DEVFREQ_GOV_FLAG_IMMUTABLE
+ *   : This governor is never changeable to other governors.
+ * - DEVFREQ_GOV_FLAG_IRQ_DRIVEN
+ *   : The devfreq won't schedule the work for this governor.
+ */
+#define DEVFREQ_GOV_FLAG_IMMUTABLE			BIT(0)
+#define DEVFREQ_GOV_FLAG_IRQ_DRIVEN			BIT(1)
+
+/*
+ * Definition of governor attribute flags except for common sysfs attributes
+ * - DEVFREQ_GOV_ATTR_POLLING_INTERVAL
+ *   : Indicate polling_interval sysfs attribute
+ * - DEVFREQ_GOV_ATTR_TIMER
+ *   : Indicate timer sysfs attribute
+ */
+#define DEVFREQ_GOV_ATTR_POLLING_INTERVAL		BIT(0)
+#define DEVFREQ_GOV_ATTR_TIMER				BIT(1)
+
+/**
+ * struct devfreq_governor - Devfreq policy governor
+ * @node:		list node - contains registered devfreq governors
+ * @name:		Governor's name
+ * @attrs:		Governor's sysfs attribute flags
+ * @flags:		Governor's feature flags
+ * @get_target_freq:	Returns desired operating frequency for the device.
+ *			Basically, get_target_freq will run
+ *			devfreq_dev_profile.get_dev_status() to get the
+ *			status of the device (load = busy_time / total_time).
+ * @event_handler:      Callback for devfreq core framework to notify events
+ *                      to governors. Events include per device governor
+ *                      init and exit, opp changes out of devfreq, suspend
+ *                      and resume of per device devfreq during device idle.
+ *
+ * Note that the callbacks are called with devfreq->lock locked by devfreq.
+ */
+struct devfreq_governor {
+	struct list_head node;
+
+	const char name[DEVFREQ_NAME_LEN];
+	const u64 attrs;
+	const u64 flags;
+	int (*get_target_freq)(struct devfreq *this, unsigned long *freq);
+	int (*event_handler)(struct devfreq *devfreq,
+				unsigned int event, void *data);
+};
+
+void devfreq_monitor_start(struct devfreq *devfreq);
+void devfreq_monitor_stop(struct devfreq *devfreq);
+void devfreq_monitor_suspend(struct devfreq *devfreq);
+void devfreq_monitor_resume(struct devfreq *devfreq);
+void devfreq_update_interval(struct devfreq *devfreq, unsigned int *delay);
+
+int devfreq_add_governor(struct devfreq_governor *governor);
+int devfreq_remove_governor(struct devfreq_governor *governor);
+
+int devm_devfreq_add_governor(struct device *dev,
+			      struct devfreq_governor *governor);
+
+int devfreq_update_status(struct devfreq *devfreq, unsigned long freq);
+int devfreq_update_target(struct devfreq *devfreq, unsigned long freq);
+void devfreq_get_freq_range(struct devfreq *devfreq, unsigned long *min_freq,
+			    unsigned long *max_freq);
+
+static inline int devfreq_update_stats(struct devfreq *df)
+{
+	if (!df->profile->get_dev_status)
+		return -EINVAL;
+
+	return df->profile->get_dev_status(df->dev.parent, &df->last_status);
+}
+#endif /* __LINUX_DEVFREQ_DEVFREQ_H__ */
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index 7fd704bb8f3d..dc1075dc3446 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -103,12 +103,13 @@ struct devfreq_dev_status {
  *
  * @is_cooling_device: A self-explanatory boolean giving the device a
  *                     cooling effect property.
+ * @dev_groups:		Optional device-specific sysfs attribute groups that to
+ *			be attached to the devfreq device.
  */
 struct devfreq_dev_profile {
 	unsigned long initial_freq;
 	unsigned int polling_ms;
 	enum devfreq_timer timer;
-	bool is_cooling_device;
 
 	int (*target)(struct device *dev, unsigned long *freq, u32 flags);
 	int (*get_dev_status)(struct device *dev,
@@ -118,6 +119,10 @@ struct devfreq_dev_profile {
 
 	unsigned long *freq_table;
 	unsigned int max_state;
+
+	bool is_cooling_device;
+
+	const struct attribute_group **dev_groups;
 };
 
 /**
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index a52d2b9a6846..38f625af6ab4 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -93,7 +93,14 @@ typedef void (*dm_status_fn) (struct dm_target *ti, status_type_t status_type,
 typedef int (*dm_message_fn) (struct dm_target *ti, unsigned int argc, char **argv,
 			      char *result, unsigned int maxlen);
 
-typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev);
+/*
+ * Called with *forward == true. If it remains true, the ioctl should be
+ * forwarded to bdev. If it is reset to false, the target already fully handled
+ * the ioctl and the return value is the return value for the whole ioctl.
+ */
+typedef int (*dm_prepare_ioctl_fn) (struct dm_target *ti, struct block_device **bdev,
+				    unsigned int cmd, unsigned long arg,
+				    bool *forward);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 typedef int (*dm_report_zones_fn) (struct dm_target *ti,
@@ -149,7 +156,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode node, void **kaddr,
-		pfn_t *pfn);
+		unsigned long *pfn);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
@@ -165,22 +172,26 @@ void dm_error(const char *message);
 
 struct dm_dev {
 	struct block_device *bdev;
+	struct file *bdev_file;
 	struct dax_device *dax_dev;
-	fmode_t mode;
+	blk_mode_t mode;
 	char name[16];
 };
 
-dev_t dm_get_dev_t(const char *path);
-
 /*
  * Constructors should call these functions to ensure destination devices
  * are opened/closed correctly.
  */
-int dm_get_device(struct dm_target *ti, const char *path, fmode_t mode,
+int dm_get_device(struct dm_target *ti, const char *path, blk_mode_t mode,
 		  struct dm_dev **result);
 void dm_put_device(struct dm_target *ti, struct dm_dev *d);
 
 /*
+ * Helper function for getting devices
+ */
+int dm_devt_from_path(const char *path, dev_t *dev_p);
+
+/*
  * Information about a target type
  */
 
@@ -295,6 +306,9 @@ struct target_type {
 #define dm_target_supports_mixed_zoned_model(type) (false)
 #endif
 
+#define DM_TARGET_ATOMIC_WRITES		0x00000400
+#define dm_target_supports_atomic_writes(type) ((type)->features & DM_TARGET_ATOMIC_WRITES)
+
 struct dm_target {
 	struct dm_table *table;
 	struct target_type *type;
@@ -359,22 +373,17 @@ struct dm_target {
 	bool discards_supported:1;
 
 	/*
-	 * Set if this target requires that discards be split on
-	 * 'max_discard_sectors' boundaries.
-	 */
-	bool max_discard_granularity:1;
-
-	/*
-	 * Set if this target requires that secure_erases be split on
-	 * 'max_secure_erase_sectors' boundaries.
+	 * Automatically set by dm-core if this target supports
+	 * REQ_OP_ZONE_RESET_ALL. Otherwise, this operation will be emulated
+	 * using REQ_OP_ZONE_RESET. Target drivers must not set this manually.
 	 */
-	bool max_secure_erase_granularity:1;
+	bool zone_reset_all_supported:1;
 
 	/*
-	 * Set if this target requires that write_zeroes be split on
-	 * 'max_write_zeroes_sectors' boundaries.
+	 * Set if this target requires that discards be split on
+	 * 'max_discard_sectors' boundaries.
 	 */
-	bool max_write_zeroes_granularity:1;
+	bool max_discard_granularity:1;
 
 	/*
 	 * Set if we need to limit the number of in-flight bios when swapping.
@@ -398,6 +407,27 @@ struct dm_target {
 	 * bio_set_dev(). NOTE: ideally a target should _not_ need this.
 	 */
 	bool needs_bio_set_dev:1;
+
+	/*
+	 * Set if the target supports flush optimization. If all the targets in
+	 * a table have flush_bypasses_map set, the dm core will not send
+	 * flushes to the targets via a ->map method. It will iterate over
+	 * dm_table->devices and send flushes to the devices directly. This
+	 * optimization reduces the number of flushes being sent when multiple
+	 * targets in a table use the same underlying device.
+	 *
+	 * This optimization may be enabled on targets that just pass the
+	 * flushes to the underlying devices without performing any other
+	 * actions on the flush request. Currently, dm-linear and dm-stripe
+	 * support it.
+	 */
+	bool flush_bypasses_map:1;
+
+	/*
+	 * Set if the target calls bio_integrity_alloc on bios received
+	 * in the map method.
+	 */
+	bool mempool_needs_integrity:1;
 };
 
 void *dm_per_bio_data(struct bio *bio, size_t data_size);
@@ -504,17 +534,22 @@ int dm_post_suspending(struct dm_target *ti);
 int dm_noflush_suspending(struct dm_target *ti);
 void dm_accept_partial_bio(struct bio *bio, unsigned int n_sectors);
 void dm_submit_bio_remap(struct bio *clone, struct bio *tgt_clone);
-union map_info *dm_get_rq_mapinfo(struct request *rq);
 
 #ifdef CONFIG_BLK_DEV_ZONED
 struct dm_report_zones_args {
 	struct dm_target *tgt;
+	struct gendisk *disk;
 	sector_t next_sector;
 
-	void *orig_data;
-	report_zones_cb orig_cb;
 	unsigned int zone_idx;
 
+	/* for block layer ->report_zones */
+	struct blk_report_zones_args *rep_args;
+
+	/* for internal users */
+	report_zones_cb cb;
+	void *data;
+
 	/* must be filled by ->report_zones before calling dm_report_zones_cb */
 	sector_t start;
 };
@@ -545,7 +580,7 @@ int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo);
 /*
  * First create an empty table.
  */
-int dm_table_create(struct dm_table **result, fmode_t mode,
+int dm_table_create(struct dm_table **result, blk_mode_t mode,
 		    unsigned int num_targets, struct mapped_device *md);
 
 /*
@@ -588,7 +623,7 @@ void dm_sync_table(struct mapped_device *md);
  * Queries
  */
 sector_t dm_table_get_size(struct dm_table *t);
-fmode_t dm_table_get_mode(struct dm_table *t);
+blk_mode_t dm_table_get_mode(struct dm_table *t);
 struct mapped_device *dm_table_get_md(struct dm_table *t);
 const char *dm_table_device_name(struct dm_table *t);
 
diff --git a/include/linux/device.h b/include/linux/device.h
index 472dd24d4823..0be95294b6e6 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -26,10 +26,11 @@
 #include <linux/atomic.h>
 #include <linux/uidgid.h>
 #include <linux/gfp.h>
-#include <linux/overflow.h>
 #include <linux/device/bus.h>
 #include <linux/device/class.h>
+#include <linux/device/devres.h>
 #include <linux/device/driver.h>
+#include <linux/cleanup.h>
 #include <asm/device.h>
 
 struct device;
@@ -41,7 +42,6 @@ struct class;
 struct subsys_private;
 struct device_node;
 struct fwnode_handle;
-struct iommu_ops;
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;
@@ -62,7 +62,7 @@ struct msi_device_data;
  */
 struct subsys_interface {
 	const char *name;
-	struct bus_type *subsys;
+	const struct bus_type *subsys;
 	struct list_head node;
 	int (*add_dev)(struct device *dev, struct subsys_interface *sif);
 	void (*remove_dev)(struct device *dev, struct subsys_interface *sif);
@@ -71,9 +71,9 @@ struct subsys_interface {
 int subsys_interface_register(struct subsys_interface *sif);
 void subsys_interface_unregister(struct subsys_interface *sif);
 
-int subsys_system_register(struct bus_type *subsys,
+int subsys_system_register(const struct bus_type *subsys,
 			   const struct attribute_group **groups);
-int subsys_virtual_register(struct bus_type *subsys,
+int subsys_virtual_register(const struct bus_type *subsys,
 			    const struct attribute_group **groups);
 
 /*
@@ -96,7 +96,12 @@ struct device_type {
 	const struct dev_pm_ops *pm;
 };
 
-/* interface for exporting device attributes */
+/**
+ * struct device_attribute - Interface for exporting device attributes.
+ * @attr: sysfs attribute definition.
+ * @show: Show handler.
+ * @store: Store handler.
+ */
 struct device_attribute {
 	struct attribute	attr;
 	ssize_t (*show)(struct device *dev, struct device_attribute *attr,
@@ -105,6 +110,11 @@ struct device_attribute {
 			 const char *buf, size_t count);
 };
 
+/**
+ * struct dev_ext_attribute - Exported device attribute with extra context.
+ * @attr: Exported device attribute.
+ * @var: Pointer to context.
+ */
 struct dev_ext_attribute {
 	struct device_attribute attr;
 	void *var;
@@ -122,31 +132,140 @@ ssize_t device_show_bool(struct device *dev, struct device_attribute *attr,
 			char *buf);
 ssize_t device_store_bool(struct device *dev, struct device_attribute *attr,
 			 const char *buf, size_t count);
+ssize_t device_show_string(struct device *dev, struct device_attribute *attr,
+			   char *buf);
 
+/**
+ * DEVICE_ATTR - Define a device attribute.
+ * @_name: Attribute name.
+ * @_mode: File mode.
+ * @_show: Show handler. Optional, but mandatory if attribute is readable.
+ * @_store: Store handler. Optional, but mandatory if attribute is writable.
+ *
+ * Convenience macro for defining a struct device_attribute.
+ *
+ * For example, ``DEVICE_ATTR(foo, 0644, foo_show, foo_store);`` expands to:
+ *
+ * .. code-block:: c
+ *
+ *	struct device_attribute dev_attr_foo = {
+ *		.attr	= { .name = "foo", .mode = 0644 },
+ *		.show	= foo_show,
+ *		.store	= foo_store,
+ *	};
+ */
 #define DEVICE_ATTR(_name, _mode, _show, _store) \
 	struct device_attribute dev_attr_##_name = __ATTR(_name, _mode, _show, _store)
+
+/**
+ * DEVICE_ATTR_PREALLOC - Define a preallocated device attribute.
+ * @_name: Attribute name.
+ * @_mode: File mode.
+ * @_show: Show handler. Optional, but mandatory if attribute is readable.
+ * @_store: Store handler. Optional, but mandatory if attribute is writable.
+ *
+ * Like DEVICE_ATTR(), but ``SYSFS_PREALLOC`` is set on @_mode.
+ */
 #define DEVICE_ATTR_PREALLOC(_name, _mode, _show, _store) \
 	struct device_attribute dev_attr_##_name = \
 		__ATTR_PREALLOC(_name, _mode, _show, _store)
+
+/**
+ * DEVICE_ATTR_RW - Define a read-write device attribute.
+ * @_name: Attribute name.
+ *
+ * Like DEVICE_ATTR(), but @_mode is 0644, @_show is <_name>_show,
+ * and @_store is <_name>_store.
+ */
 #define DEVICE_ATTR_RW(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RW(_name)
+
+/**
+ * DEVICE_ATTR_ADMIN_RW - Define an admin-only read-write device attribute.
+ * @_name: Attribute name.
+ *
+ * Like DEVICE_ATTR_RW(), but @_mode is 0600.
+ */
 #define DEVICE_ATTR_ADMIN_RW(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RW_MODE(_name, 0600)
+
+/**
+ * DEVICE_ATTR_RO - Define a readable device attribute.
+ * @_name: Attribute name.
+ *
+ * Like DEVICE_ATTR(), but @_mode is 0444 and @_show is <_name>_show.
+ */
 #define DEVICE_ATTR_RO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RO(_name)
+
+/**
+ * DEVICE_ATTR_ADMIN_RO - Define an admin-only readable device attribute.
+ * @_name: Attribute name.
+ *
+ * Like DEVICE_ATTR_RO(), but @_mode is 0400.
+ */
 #define DEVICE_ATTR_ADMIN_RO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_RO_MODE(_name, 0400)
+
+/**
+ * DEVICE_ATTR_WO - Define an admin-only writable device attribute.
+ * @_name: Attribute name.
+ *
+ * Like DEVICE_ATTR(), but @_mode is 0200 and @_store is <_name>_store.
+ */
 #define DEVICE_ATTR_WO(_name) \
 	struct device_attribute dev_attr_##_name = __ATTR_WO(_name)
+
+/**
+ * DEVICE_ULONG_ATTR - Define a device attribute backed by an unsigned long.
+ * @_name: Attribute name.
+ * @_mode: File mode.
+ * @_var: Identifier of unsigned long.
+ *
+ * Like DEVICE_ATTR(), but @_show and @_store are automatically provided
+ * such that reads and writes to the attribute from userspace affect @_var.
+ */
 #define DEVICE_ULONG_ATTR(_name, _mode, _var) \
 	struct dev_ext_attribute dev_attr_##_name = \
 		{ __ATTR(_name, _mode, device_show_ulong, device_store_ulong), &(_var) }
+
+/**
+ * DEVICE_INT_ATTR - Define a device attribute backed by an int.
+ * @_name: Attribute name.
+ * @_mode: File mode.
+ * @_var: Identifier of int.
+ *
+ * Like DEVICE_ULONG_ATTR(), but @_var is an int.
+ */
 #define DEVICE_INT_ATTR(_name, _mode, _var) \
 	struct dev_ext_attribute dev_attr_##_name = \
 		{ __ATTR(_name, _mode, device_show_int, device_store_int), &(_var) }
+
+/**
+ * DEVICE_BOOL_ATTR - Define a device attribute backed by a bool.
+ * @_name: Attribute name.
+ * @_mode: File mode.
+ * @_var: Identifier of bool.
+ *
+ * Like DEVICE_ULONG_ATTR(), but @_var is a bool.
+ */
 #define DEVICE_BOOL_ATTR(_name, _mode, _var) \
 	struct dev_ext_attribute dev_attr_##_name = \
 		{ __ATTR(_name, _mode, device_show_bool, device_store_bool), &(_var) }
+
+/**
+ * DEVICE_STRING_ATTR_RO - Define a device attribute backed by a r/o string.
+ * @_name: Attribute name.
+ * @_mode: File mode.
+ * @_var: Identifier of string.
+ *
+ * Like DEVICE_ULONG_ATTR(), but @_var is a string. Because the length of the
+ * string allocation is unknown, the attribute must be read-only.
+ */
+#define DEVICE_STRING_ATTR_RO(_name, _mode, _var) \
+	struct dev_ext_attribute dev_attr_##_name = \
+		{ __ATTR(_name, (_mode) & ~0222, device_show_string, NULL), (_var) }
+
 #define DEVICE_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \
 	struct device_attribute dev_attr_##_name =		\
 		__ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store)
@@ -162,127 +281,6 @@ int __must_check device_create_bin_file(struct device *dev,
 void device_remove_bin_file(struct device *dev,
 			    const struct bin_attribute *attr);
 
-/* device resource management */
-typedef void (*dr_release_t)(struct device *dev, void *res);
-typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data);
-
-void *__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp,
-			  int nid, const char *name) __malloc;
-#define devres_alloc(release, size, gfp) \
-	__devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release)
-#define devres_alloc_node(release, size, gfp, nid) \
-	__devres_alloc_node(release, size, gfp, nid, #release)
-
-void devres_for_each_res(struct device *dev, dr_release_t release,
-			 dr_match_t match, void *match_data,
-			 void (*fn)(struct device *, void *, void *),
-			 void *data);
-void devres_free(void *res);
-void devres_add(struct device *dev, void *res);
-void *devres_find(struct device *dev, dr_release_t release,
-		  dr_match_t match, void *match_data);
-void *devres_get(struct device *dev, void *new_res,
-		 dr_match_t match, void *match_data);
-void *devres_remove(struct device *dev, dr_release_t release,
-		    dr_match_t match, void *match_data);
-int devres_destroy(struct device *dev, dr_release_t release,
-		   dr_match_t match, void *match_data);
-int devres_release(struct device *dev, dr_release_t release,
-		   dr_match_t match, void *match_data);
-
-/* devres group */
-void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp);
-void devres_close_group(struct device *dev, void *id);
-void devres_remove_group(struct device *dev, void *id);
-int devres_release_group(struct device *dev, void *id);
-
-/* managed devm_k.alloc/kfree for device drivers */
-void *devm_kmalloc(struct device *dev, size_t size, gfp_t gfp) __alloc_size(2);
-void *devm_krealloc(struct device *dev, void *ptr, size_t size,
-		    gfp_t gfp) __must_check __realloc_size(3);
-__printf(3, 0) char *devm_kvasprintf(struct device *dev, gfp_t gfp,
-				     const char *fmt, va_list ap) __malloc;
-__printf(3, 4) char *devm_kasprintf(struct device *dev, gfp_t gfp,
-				    const char *fmt, ...) __malloc;
-static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
-{
-	return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
-}
-static inline void *devm_kmalloc_array(struct device *dev,
-				       size_t n, size_t size, gfp_t flags)
-{
-	size_t bytes;
-
-	if (unlikely(check_mul_overflow(n, size, &bytes)))
-		return NULL;
-
-	return devm_kmalloc(dev, bytes, flags);
-}
-static inline void *devm_kcalloc(struct device *dev,
-				 size_t n, size_t size, gfp_t flags)
-{
-	return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
-}
-void devm_kfree(struct device *dev, const void *p);
-char *devm_kstrdup(struct device *dev, const char *s, gfp_t gfp) __malloc;
-const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp);
-void *devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp)
-	__realloc_size(3);
-
-unsigned long devm_get_free_pages(struct device *dev,
-				  gfp_t gfp_mask, unsigned int order);
-void devm_free_pages(struct device *dev, unsigned long addr);
-
-void __iomem *devm_ioremap_resource(struct device *dev,
-				    const struct resource *res);
-void __iomem *devm_ioremap_resource_wc(struct device *dev,
-				       const struct resource *res);
-
-void __iomem *devm_of_iomap(struct device *dev,
-			    struct device_node *node, int index,
-			    resource_size_t *size);
-
-/* allows to add/remove a custom action to devres stack */
-void devm_remove_action(struct device *dev, void (*action)(void *), void *data);
-void devm_release_action(struct device *dev, void (*action)(void *), void *data);
-
-int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name);
-#define devm_add_action(release, action, data) \
-	__devm_add_action(release, action, data, #action)
-
-static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *),
-					     void *data, const char *name)
-{
-	int ret;
-
-	ret = __devm_add_action(dev, action, data, name);
-	if (ret)
-		action(data);
-
-	return ret;
-}
-#define devm_add_action_or_reset(release, action, data) \
-	__devm_add_action_or_reset(release, action, data, #action)
-
-/**
- * devm_alloc_percpu - Resource-managed alloc_percpu
- * @dev: Device to allocate per-cpu memory for
- * @type: Type to allocate per-cpu memory for
- *
- * Managed alloc_percpu. Per-cpu memory allocated with this function is
- * automatically freed on driver detach.
- *
- * RETURNS:
- * Pointer to allocated memory on success, NULL on failure.
- */
-#define devm_alloc_percpu(dev, type)      \
-	((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), \
-						      __alignof__(type)))
-
-void __percpu *__devm_alloc_percpu(struct device *dev, size_t size,
-				   size_t align);
-void devm_free_percpu(struct device *dev, void __percpu *pdata);
-
 struct device_dma_parameters {
 	/*
 	 * a low level driver may set these to teach IOMMU code about
@@ -509,7 +507,10 @@ struct device_physical_location {
  * @dma_pools:	Dma pools (if dma'ble device).
  * @dma_mem:	Internal for coherent mem override.
  * @cma_area:	Contiguous memory area for dma allocations
- * @dma_io_tlb_mem: Pointer to the swiotlb pool used.  Not for driver use.
+ * @dma_io_tlb_mem: Software IO TLB allocator.  Not for driver use.
+ * @dma_io_tlb_pools:	List of transient swiotlb memory pools.
+ * @dma_io_tlb_lock:	Protects changes to the list of active pools.
+ * @dma_uses_io_tlb: %true if device has used the software IO TLB.
  * @archdata:	For arch-specific additions.
  * @of_node:	Associated device tree node.
  * @fwnode:	Associated device node supplied by platform firmware.
@@ -517,7 +518,6 @@ struct device_physical_location {
  * @id:		device instance
  * @devres_lock: Spinlock to protect the resource of the device.
  * @devres_head: The resources list of the device.
- * @knode_class: The node used to add the device to the class list.
  * @class:	The class of the device.
  * @groups:	Optional attribute groups.
  * @release:	Callback to free the device after all references have
@@ -548,6 +548,9 @@ struct device_physical_location {
  *		and optionall (if the coherent mask is large enough) also
  *		for dma allocations.  This flag is managed by the dma ops
  *		instance from ->dma_supported.
+ * @dma_skip_sync: DMA sync operations can be skipped for coherent buffers.
+ * @dma_iommu: Device is using default IOMMU implementation for DMA and
+ *		doesn't rely on dma_ops structure.
  *
  * At the lowest level, every device in a Linux system is represented by an
  * instance of struct device. The device structure contains the information
@@ -589,7 +592,7 @@ struct device {
 	struct dev_pin_info	*pins;
 #endif
 	struct dev_msi_info	msi;
-#ifdef CONFIG_DMA_OPS
+#ifdef CONFIG_ARCH_HAS_DMA_OPS
 	const struct dma_map_ops *dma_ops;
 #endif
 	u64		*dma_mask;	/* dma mask (if dma'able device) */
@@ -616,6 +619,11 @@ struct device {
 #ifdef CONFIG_SWIOTLB
 	struct io_tlb_mem *dma_io_tlb_mem;
 #endif
+#ifdef CONFIG_SWIOTLB_DYNAMIC
+	struct list_head dma_io_tlb_pools;
+	spinlock_t dma_io_tlb_lock;
+	bool dma_uses_io_tlb;
+#endif
 	/* arch specific additions */
 	struct dev_archdata	archdata;
 
@@ -655,6 +663,12 @@ struct device {
 #ifdef CONFIG_DMA_OPS_BYPASS
 	bool			dma_ops_bypass : 1;
 #endif
+#ifdef CONFIG_DMA_NEED_SYNC
+	bool			dma_skip_sync:1;
+#endif
+#ifdef CONFIG_IOMMU_DMA
+	bool			dma_iommu:1;
+#endif
 };
 
 /**
@@ -700,6 +714,11 @@ static inline bool device_iommu_mapped(struct device *dev)
 /* Get the wakeup routines, which depend on struct device */
 #include <linux/pm_wakeup.h>
 
+/**
+ * dev_name - Return a device's name.
+ * @dev: Device with name to get.
+ * Return: The kobject name of the device, or its initial name if unavailable.
+ */
 static inline const char *dev_name(const struct device *dev)
 {
 	/* Use the init name until the kobject becomes available */
@@ -813,6 +832,9 @@ static inline bool device_pm_not_required(struct device *dev)
 static inline void device_set_pm_not_required(struct device *dev)
 {
 	dev->power.no_pm = true;
+#ifdef CONFIG_PM
+	dev->power.no_callbacks = true;
+#endif
 }
 
 static inline void dev_pm_syscore_device(struct device *dev, bool val)
@@ -832,6 +854,42 @@ static inline bool dev_pm_test_driver_flags(struct device *dev, u32 flags)
 	return !!(dev->power.driver_flags & flags);
 }
 
+static inline bool dev_pm_smart_suspend(struct device *dev)
+{
+#ifdef CONFIG_PM_SLEEP
+	return dev->power.smart_suspend;
+#else
+	return false;
+#endif
+}
+
+/*
+ * dev_pm_set_strict_midlayer - Update the device's power.strict_midlayer flag
+ * @dev: Target device.
+ * @val: New flag value.
+ *
+ * When set, power.strict_midlayer means that the middle layer power management
+ * code (typically, a bus type or a PM domain) does not expect its runtime PM
+ * suspend callback to be invoked at all during system-wide PM transitions and
+ * it does not expect its runtime PM resume callback to be invoked at any point
+ * when runtime PM is disabled for the device during system-wide PM transitions.
+ */
+static inline void dev_pm_set_strict_midlayer(struct device *dev, bool val)
+{
+#ifdef CONFIG_PM_SLEEP
+	dev->power.strict_midlayer = val;
+#endif
+}
+
+static inline bool dev_pm_strict_midlayer_is_set(struct device *dev)
+{
+#ifdef CONFIG_PM_SLEEP
+	return dev->power.strict_midlayer;
+#else
+	return false;
+#endif
+}
+
 static inline void device_lock(struct device *dev)
 {
 	mutex_lock(&dev->mutex);
@@ -852,18 +910,13 @@ static inline void device_unlock(struct device *dev)
 	mutex_unlock(&dev->mutex);
 }
 
+DEFINE_GUARD(device, struct device *, device_lock(_T), device_unlock(_T))
+
 static inline void device_lock_assert(struct device *dev)
 {
 	lockdep_assert_held(&dev->mutex);
 }
 
-static inline struct device_node *dev_of_node(struct device *dev)
-{
-	if (!IS_ENABLED(CONFIG_OF) || !dev)
-		return NULL;
-	return dev->of_node;
-}
-
 static inline bool dev_has_sync_state(struct device *dev)
 {
 	if (!dev)
@@ -875,6 +928,18 @@ static inline bool dev_has_sync_state(struct device *dev)
 	return false;
 }
 
+static inline int dev_set_drv_sync_state(struct device *dev,
+					 void (*fn)(struct device *dev))
+{
+	if (!dev || !dev->driver)
+		return 0;
+	if (dev->driver->sync_state && dev->driver->sync_state != fn)
+		return -EBUSY;
+	if (!dev->driver->sync_state)
+		dev->driver->sync_state = fn;
+	return 0;
+}
+
 static inline void dev_set_removable(struct device *dev,
 				     enum device_removable removable)
 {
@@ -899,21 +964,52 @@ void device_unregister(struct device *dev);
 void device_initialize(struct device *dev);
 int __must_check device_add(struct device *dev);
 void device_del(struct device *dev);
-int device_for_each_child(struct device *dev, void *data,
-			  int (*fn)(struct device *dev, void *data));
-int device_for_each_child_reverse(struct device *dev, void *data,
-				  int (*fn)(struct device *dev, void *data));
-struct device *device_find_child(struct device *dev, void *data,
-				 int (*match)(struct device *dev, void *data));
-struct device *device_find_child_by_name(struct device *parent,
-					 const char *name);
-struct device *device_find_any_child(struct device *parent);
+
+DEFINE_FREE(device_del, struct device *, if (_T) device_del(_T))
+
+int device_for_each_child(struct device *parent, void *data,
+			  device_iter_t fn);
+int device_for_each_child_reverse(struct device *parent, void *data,
+				  device_iter_t fn);
+int device_for_each_child_reverse_from(struct device *parent,
+				       struct device *from, void *data,
+				       device_iter_t fn);
+struct device *device_find_child(struct device *parent, const void *data,
+				 device_match_t match);
+/**
+ * device_find_child_by_name - device iterator for locating a child device.
+ * @parent: parent struct device
+ * @name: name of the child device
+ *
+ * This is similar to the device_find_child() function above, but it
+ * returns a reference to a device that has the name @name.
+ *
+ * NOTE: you will need to drop the reference with put_device() after use.
+ */
+static inline struct device *device_find_child_by_name(struct device *parent,
+						       const char *name)
+{
+	return device_find_child(parent, name, device_match_name);
+}
+
+/**
+ * device_find_any_child - device iterator for locating a child device, if any.
+ * @parent: parent struct device
+ *
+ * This is similar to the device_find_child() function above, but it
+ * returns a reference to a child device, if any.
+ *
+ * NOTE: you will need to drop the reference with put_device() after use.
+ */
+static inline struct device *device_find_any_child(struct device *parent)
+{
+	return device_find_child(parent, NULL, device_match_any);
+}
 
 int device_rename(struct device *dev, const char *new_name);
 int device_move(struct device *dev, struct device *new_parent,
 		enum dpm_order dpm_order);
 int device_change_owner(struct device *dev, kuid_t kuid, kgid_t kgid);
-int device_is_dependent(struct device *dev, void *target);
 
 static inline bool device_supports_offline(struct device *dev)
 {
@@ -968,10 +1064,21 @@ void unlock_device_hotplug(void);
 int lock_device_hotplug_sysfs(void);
 int device_offline(struct device *dev);
 int device_online(struct device *dev);
+
 void set_primary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
 void set_secondary_fwnode(struct device *dev, struct fwnode_handle *fwnode);
-void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
 void device_set_node(struct device *dev, struct fwnode_handle *fwnode);
+int device_add_of_node(struct device *dev, struct device_node *of_node);
+void device_remove_of_node(struct device *dev);
+void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
+struct device *get_dev_from_fwnode(struct fwnode_handle *fwnode);
+
+static inline struct device_node *dev_of_node(struct device *dev)
+{
+	if (!IS_ENABLED(CONFIG_OF) || !dev)
+		return NULL;
+	return dev->of_node;
+}
 
 static inline int dev_num_vf(struct device *dev)
 {
@@ -1000,12 +1107,12 @@ static inline void *dev_get_platdata(const struct device *dev)
  * Manual binding of a device to driver. See drivers/base/bus.c
  * for information on use.
  */
-int __must_check device_driver_attach(struct device_driver *drv,
+int __must_check device_driver_attach(const struct device_driver *drv,
 				      struct device *dev);
 int __must_check device_bind_driver(struct device *dev);
 void device_release_driver(struct device *dev);
 int  __must_check device_attach(struct device *dev);
-int __must_check driver_attach(struct device_driver *drv);
+int __must_check driver_attach(const struct device_driver *drv);
 void device_initial_probe(struct device *dev);
 int __must_check device_reprobe(struct device *dev);
 
@@ -1041,31 +1148,21 @@ static inline void device_remove_group(struct device *dev,
 {
 	const struct attribute_group *groups[] = { grp, NULL };
 
-	return device_remove_groups(dev, groups);
+	device_remove_groups(dev, groups);
 }
 
-int __must_check devm_device_add_groups(struct device *dev,
-					const struct attribute_group **groups);
 int __must_check devm_device_add_group(struct device *dev,
 				       const struct attribute_group *grp);
 
 /*
- * Platform "fixup" functions - allow the platform to have their say
- * about devices and actions that the general device layer doesn't
- * know about.
- */
-/* Notify platform of device discovery */
-extern int (*platform_notify)(struct device *dev);
-
-extern int (*platform_notify_remove)(struct device *dev);
-
-
-/*
  * get_device - atomically increment the reference count for the device.
  *
  */
 struct device *get_device(struct device *dev);
 void put_device(struct device *dev);
+
+DEFINE_FREE(put_device, struct device *, if (_T) put_device(_T))
+
 bool kill_device(struct device *dev);
 
 #ifdef CONFIG_DEVTMPFS
@@ -1087,8 +1184,12 @@ void device_link_del(struct device_link *link);
 void device_link_remove(void *consumer, struct device *supplier);
 void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
+void device_link_wait_removal(void);
 
-__printf(3, 4) int dev_err_probe(const struct device *dev, int err, const char *fmt, ...);
+static inline bool device_link_test(const struct device_link *link, u32 flags)
+{
+	return !!(link->flags & flags);
+}
 
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
diff --git a/include/linux/device/bus.h b/include/linux/device/bus.h
index ae10c4322754..99b1002b3e31 100644
--- a/include/linux/device/bus.h
+++ b/include/linux/device/bus.h
@@ -48,6 +48,7 @@ struct fwnode_handle;
  *		will never get called until they do.
  * @remove:	Called when a device removed from this bus.
  * @shutdown:	Called at shut-down time to quiesce the device.
+ * @irq_get_affinity:	Get IRQ affinity mask for the device on this bus.
  *
  * @online:	Called to put the device back online (after offlining it).
  * @offline:	Called to put the device offline for hot-removal. May fail.
@@ -62,9 +63,6 @@ struct fwnode_handle;
  *			this bus.
  * @pm:		Power management operations of this bus, callback the specific
  *		device driver's pm-ops.
- * @iommu_ops:  IOMMU specific operations for this bus, used to attach IOMMU
- *              driver implementations to a bus and allow the driver to do
- *              bus-specific setup
  * @need_parent_lock:	When probing or removing a device on this bus, the
  *			device core should lock the device's parent.
  *
@@ -84,12 +82,14 @@ struct bus_type {
 	const struct attribute_group **dev_groups;
 	const struct attribute_group **drv_groups;
 
-	int (*match)(struct device *dev, struct device_driver *drv);
+	int (*match)(struct device *dev, const struct device_driver *drv);
 	int (*uevent)(const struct device *dev, struct kobj_uevent_env *env);
 	int (*probe)(struct device *dev);
 	void (*sync_state)(struct device *dev);
 	void (*remove)(struct device *dev);
 	void (*shutdown)(struct device *dev);
+	const struct cpumask *(*irq_get_affinity)(struct device *dev,
+			unsigned int irq_vec);
 
 	int (*online)(struct device *dev);
 	int (*offline)(struct device *dev);
@@ -104,8 +104,6 @@ struct bus_type {
 
 	const struct dev_pm_ops *pm;
 
-	const struct iommu_ops *iommu_ops;
-
 	bool need_parent_lock;
 };
 
@@ -131,8 +129,12 @@ struct bus_attribute {
 int __must_check bus_create_file(const struct bus_type *bus, struct bus_attribute *attr);
 void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr);
 
+/* Matching function type for drivers/base APIs to find a specific device */
+typedef int (*device_match_t)(struct device *dev, const void *data);
+
 /* Generic device matching functions that all busses can use to match with */
 int device_match_name(struct device *dev, const void *name);
+int device_match_type(struct device *dev, const void *type);
 int device_match_of_node(struct device *dev, const void *np);
 int device_match_fwnode(struct device *dev, const void *fwnode);
 int device_match_devt(struct device *dev, const void *pdevt);
@@ -140,12 +142,17 @@ int device_match_acpi_dev(struct device *dev, const void *adev);
 int device_match_acpi_handle(struct device *dev, const void *handle);
 int device_match_any(struct device *dev, const void *unused);
 
+/* Device iterating function type for various driver core for_each APIs */
+typedef int (*device_iter_t)(struct device *dev, void *data);
+
 /* iterator helpers for buses */
-int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data,
-		     int (*fn)(struct device *dev, void *data));
+int bus_for_each_dev(const struct bus_type *bus, struct device *start,
+		     void *data, device_iter_t fn);
 struct device *bus_find_device(const struct bus_type *bus, struct device *start,
-			       const void *data,
-			       int (*match)(struct device *dev, const void *data));
+			       const void *data, device_match_t match);
+struct device *bus_find_device_reverse(const struct bus_type *bus,
+				       struct device *start, const void *data,
+				       device_match_t match);
 /**
  * bus_find_device_by_name - device iterator for locating a particular device
  * of a specific name.
@@ -232,7 +239,7 @@ bus_find_device_by_acpi_dev(const struct bus_type *bus, const void *adev)
 
 int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start,
 		     void *data, int (*fn)(struct device_driver *, void *));
-void bus_sort_breadthfirst(struct bus_type *bus,
+void bus_sort_breadthfirst(const struct bus_type *bus,
 			   int (*compare)(const struct device *a,
 					  const struct device *b));
 /*
diff --git a/include/linux/device/class.h b/include/linux/device/class.h
index abf3d3bfb6fe..65880e60c720 100644
--- a/include/linux/device/class.h
+++ b/include/linux/device/class.h
@@ -40,8 +40,6 @@ struct fwnode_handle;
  *		for the devices belonging to the class. Usually tied to
  *		device's namespace.
  * @pm:		The default device power management operations of this class.
- * @p:		The private data of the driver core, no one other than the
- *		driver core can touch this.
  *
  * A class is a higher-level view of a device that abstracts out low-level
  * implementation details. Drivers may see a SCSI disk or an ATA disk, but,
@@ -84,20 +82,18 @@ bool class_is_registered(const struct class *class);
 struct class_compat;
 struct class_compat *class_compat_register(const char *name);
 void class_compat_unregister(struct class_compat *cls);
-int class_compat_create_link(struct class_compat *cls, struct device *dev,
-			     struct device *device_link);
-void class_compat_remove_link(struct class_compat *cls, struct device *dev,
-			      struct device *device_link);
+int class_compat_create_link(struct class_compat *cls, struct device *dev);
+void class_compat_remove_link(struct class_compat *cls, struct device *dev);
 
 void class_dev_iter_init(struct class_dev_iter *iter, const struct class *class,
 			 const struct device *start, const struct device_type *type);
 struct device *class_dev_iter_next(struct class_dev_iter *iter);
 void class_dev_iter_exit(struct class_dev_iter *iter);
 
-int class_for_each_device(const struct class *class, const struct device *start, void *data,
-			  int (*fn)(struct device *dev, void *data));
+int class_for_each_device(const struct class *class, const struct device *start,
+			  void *data, device_iter_t fn);
 struct device *class_find_device(const struct class *class, const struct device *start,
-				 const void *data, int (*match)(struct device *, const void *));
+				 const void *data, device_match_t match);
 
 /**
  * class_find_device_by_name - device iterator for locating a particular device
@@ -197,7 +193,7 @@ static inline int __must_check class_create_file(const struct class *class,
 static inline void class_remove_file(const struct class *class,
 				     const struct class_attribute *attr)
 {
-	return class_remove_file_ns(class, attr, NULL);
+	class_remove_file_ns(class, attr, NULL);
 }
 
 /* Simple class attribute that is just a static string */
diff --git a/include/linux/device/devres.h b/include/linux/device/devres.h
new file mode 100644
index 000000000000..9c1e3d643d69
--- /dev/null
+++ b/include/linux/device/devres.h
@@ -0,0 +1,189 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _DEVICE_DEVRES_H_
+#define _DEVICE_DEVRES_H_
+
+#include <linux/err.h>
+#include <linux/gfp_types.h>
+#include <linux/numa.h>
+#include <linux/overflow.h>
+#include <linux/stdarg.h>
+#include <linux/types.h>
+#include <asm/bug.h>
+#include <asm/percpu.h>
+
+struct device;
+struct device_node;
+struct resource;
+
+/* device resource management */
+typedef void (*dr_release_t)(struct device *dev, void *res);
+typedef int (*dr_match_t)(struct device *dev, void *res, void *match_data);
+
+void * __malloc
+__devres_alloc_node(dr_release_t release, size_t size, gfp_t gfp, int nid, const char *name);
+#define devres_alloc(release, size, gfp) \
+	__devres_alloc_node(release, size, gfp, NUMA_NO_NODE, #release)
+#define devres_alloc_node(release, size, gfp, nid) \
+	__devres_alloc_node(release, size, gfp, nid, #release)
+
+void devres_for_each_res(struct device *dev, dr_release_t release,
+			 dr_match_t match, void *match_data,
+			 void (*fn)(struct device *, void *, void *),
+			 void *data);
+void devres_free(void *res);
+void devres_add(struct device *dev, void *res);
+void *devres_find(struct device *dev, dr_release_t release, dr_match_t match, void *match_data);
+void *devres_get(struct device *dev, void *new_res, dr_match_t match, void *match_data);
+void *devres_remove(struct device *dev, dr_release_t release, dr_match_t match, void *match_data);
+int devres_destroy(struct device *dev, dr_release_t release, dr_match_t match, void *match_data);
+int devres_release(struct device *dev, dr_release_t release, dr_match_t match, void *match_data);
+
+/* devres group */
+void * __must_check devres_open_group(struct device *dev, void *id, gfp_t gfp);
+void devres_close_group(struct device *dev, void *id);
+void devres_remove_group(struct device *dev, void *id);
+int devres_release_group(struct device *dev, void *id);
+
+/* managed devm_k.alloc/kfree for device drivers */
+void * __alloc_size(2)
+devm_kmalloc(struct device *dev, size_t size, gfp_t gfp);
+void * __must_check __realloc_size(3)
+devm_krealloc(struct device *dev, void *ptr, size_t size, gfp_t gfp);
+static inline void *devm_kzalloc(struct device *dev, size_t size, gfp_t gfp)
+{
+	return devm_kmalloc(dev, size, gfp | __GFP_ZERO);
+}
+static inline void *devm_kmalloc_array(struct device *dev, size_t n, size_t size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(n, size, &bytes)))
+		return NULL;
+
+	return devm_kmalloc(dev, bytes, flags);
+}
+static inline void *devm_kcalloc(struct device *dev, size_t n, size_t size, gfp_t flags)
+{
+	return devm_kmalloc_array(dev, n, size, flags | __GFP_ZERO);
+}
+static inline __realloc_size(3, 4) void * __must_check
+devm_krealloc_array(struct device *dev, void *p, size_t new_n, size_t new_size, gfp_t flags)
+{
+	size_t bytes;
+
+	if (unlikely(check_mul_overflow(new_n, new_size, &bytes)))
+		return NULL;
+
+	return devm_krealloc(dev, p, bytes, flags);
+}
+
+void devm_kfree(struct device *dev, const void *p);
+
+void * __realloc_size(3)
+devm_kmemdup(struct device *dev, const void *src, size_t len, gfp_t gfp);
+const void *
+devm_kmemdup_const(struct device *dev, const void *src, size_t len, gfp_t gfp);
+static inline void *devm_kmemdup_array(struct device *dev, const void *src,
+				       size_t n, size_t size, gfp_t flags)
+{
+	return devm_kmemdup(dev, src, size_mul(size, n), flags);
+}
+
+char * __malloc
+devm_kstrdup(struct device *dev, const char *s, gfp_t gfp);
+const char *devm_kstrdup_const(struct device *dev, const char *s, gfp_t gfp);
+char * __printf(3, 0) __malloc
+devm_kvasprintf(struct device *dev, gfp_t gfp, const char *fmt, va_list ap);
+char * __printf(3, 4) __malloc
+devm_kasprintf(struct device *dev, gfp_t gfp, const char *fmt, ...);
+
+/**
+ * devm_alloc_percpu - Resource-managed alloc_percpu
+ * @dev: Device to allocate per-cpu memory for
+ * @type: Type to allocate per-cpu memory for
+ *
+ * Managed alloc_percpu. Per-cpu memory allocated with this function is
+ * automatically freed on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+#define devm_alloc_percpu(dev, type)      \
+	((typeof(type) __percpu *)__devm_alloc_percpu((dev), sizeof(type), __alignof__(type)))
+
+void __percpu *__devm_alloc_percpu(struct device *dev, size_t size, size_t align);
+
+unsigned long devm_get_free_pages(struct device *dev, gfp_t gfp_mask, unsigned int order);
+void devm_free_pages(struct device *dev, unsigned long addr);
+
+#ifdef CONFIG_HAS_IOMEM
+
+void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res);
+void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res);
+
+void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index,
+			    resource_size_t *size);
+#else
+
+static inline
+void __iomem *devm_ioremap_resource(struct device *dev, const struct resource *res)
+{
+	return IOMEM_ERR_PTR(-EINVAL);
+}
+
+static inline
+void __iomem *devm_ioremap_resource_wc(struct device *dev, const struct resource *res)
+{
+	return IOMEM_ERR_PTR(-EINVAL);
+}
+
+static inline
+void __iomem *devm_of_iomap(struct device *dev, struct device_node *node, int index,
+			    resource_size_t *size)
+{
+	return IOMEM_ERR_PTR(-EINVAL);
+}
+
+#endif
+
+/* allows to add/remove a custom action to devres stack */
+int devm_remove_action_nowarn(struct device *dev, void (*action)(void *), void *data);
+
+/**
+ * devm_remove_action() - removes previously added custom action
+ * @dev: Device that owns the action
+ * @action: Function implementing the action
+ * @data: Pointer to data passed to @action implementation
+ *
+ * Removes instance of @action previously added by devm_add_action().
+ * Both action and data should match one of the existing entries.
+ */
+static inline
+void devm_remove_action(struct device *dev, void (*action)(void *), void *data)
+{
+	WARN_ON(devm_remove_action_nowarn(dev, action, data));
+}
+
+void devm_release_action(struct device *dev, void (*action)(void *), void *data);
+
+int __devm_add_action(struct device *dev, void (*action)(void *), void *data, const char *name);
+#define devm_add_action(dev, action, data) \
+	__devm_add_action(dev, action, data, #action)
+
+static inline int __devm_add_action_or_reset(struct device *dev, void (*action)(void *),
+					     void *data, const char *name)
+{
+	int ret;
+
+	ret = __devm_add_action(dev, action, data, name);
+	if (ret)
+		action(data);
+
+	return ret;
+}
+#define devm_add_action_or_reset(dev, action, data) \
+	__devm_add_action_or_reset(dev, action, data, #action)
+
+bool devm_is_action_added(struct device *dev, void (*action)(void *), void *data);
+
+#endif /* _DEVICE_DEVRES_H_ */
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index c244267a6744..cd8e0f0a634b 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -126,7 +126,7 @@ int __must_check driver_register(struct device_driver *drv);
 void driver_unregister(struct device_driver *drv);
 
 struct device_driver *driver_find(const char *name, const struct bus_type *bus);
-int driver_probe_done(void);
+bool __init driver_probe_done(void);
 void wait_for_device_probe(void);
 void __init wait_for_init_devices_probe(void);
 
@@ -146,18 +146,18 @@ struct driver_attribute {
 #define DRIVER_ATTR_WO(_name) \
 	struct driver_attribute driver_attr_##_name = __ATTR_WO(_name)
 
-int __must_check driver_create_file(struct device_driver *driver,
+int __must_check driver_create_file(const struct device_driver *driver,
 				    const struct driver_attribute *attr);
-void driver_remove_file(struct device_driver *driver,
+void driver_remove_file(const struct device_driver *driver,
 			const struct driver_attribute *attr);
 
 int driver_set_override(struct device *dev, const char **override,
 			const char *s, size_t len);
 int __must_check driver_for_each_device(struct device_driver *drv, struct device *start,
-					void *data, int (*fn)(struct device *dev, void *));
-struct device *driver_find_device(struct device_driver *drv,
+					void *data, device_iter_t fn);
+struct device *driver_find_device(const struct device_driver *drv,
 				  struct device *start, const void *data,
-				  int (*match)(struct device *dev, const void *data));
+				  device_match_t match);
 
 /**
  * driver_find_device_by_name - device iterator for locating a particular device
@@ -165,7 +165,7 @@ struct device *driver_find_device(struct device_driver *drv,
  * @drv: the driver we're iterating
  * @name: name of the device to match
  */
-static inline struct device *driver_find_device_by_name(struct device_driver *drv,
+static inline struct device *driver_find_device_by_name(const struct device_driver *drv,
 							const char *name)
 {
 	return driver_find_device(drv, NULL, name, device_match_name);
@@ -178,7 +178,7 @@ static inline struct device *driver_find_device_by_name(struct device_driver *dr
  * @np: of_node pointer to match.
  */
 static inline struct device *
-driver_find_device_by_of_node(struct device_driver *drv,
+driver_find_device_by_of_node(const struct device_driver *drv,
 			      const struct device_node *np)
 {
 	return driver_find_device(drv, NULL, np, device_match_of_node);
@@ -203,13 +203,13 @@ driver_find_device_by_fwnode(struct device_driver *drv,
  * @drv: the driver we're iterating
  * @devt: devt pointer to match.
  */
-static inline struct device *driver_find_device_by_devt(struct device_driver *drv,
+static inline struct device *driver_find_device_by_devt(const struct device_driver *drv,
 							dev_t devt)
 {
 	return driver_find_device(drv, NULL, &devt, device_match_devt);
 }
 
-static inline struct device *driver_find_next_device(struct device_driver *drv,
+static inline struct device *driver_find_next_device(const struct device_driver *drv,
 						     struct device *start)
 {
 	return driver_find_device(drv, start, NULL, device_match_any);
@@ -223,14 +223,14 @@ static inline struct device *driver_find_next_device(struct device_driver *drv,
  * @adev: ACPI_COMPANION device to match.
  */
 static inline struct device *
-driver_find_device_by_acpi_dev(struct device_driver *drv,
+driver_find_device_by_acpi_dev(const struct device_driver *drv,
 			       const struct acpi_device *adev)
 {
 	return driver_find_device(drv, NULL, adev, device_match_acpi_dev);
 }
 #else
 static inline struct device *
-driver_find_device_by_acpi_dev(struct device_driver *drv, const void *adev)
+driver_find_device_by_acpi_dev(const struct device_driver *drv, const void *adev)
 {
 	return NULL;
 }
diff --git a/include/linux/device/faux.h b/include/linux/device/faux.h
new file mode 100644
index 000000000000..9f43c0e46aa4
--- /dev/null
+++ b/include/linux/device/faux.h
@@ -0,0 +1,69 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2025 Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+ * Copyright (c) 2025 The Linux Foundation
+ *
+ * A "simple" faux bus that allows devices to be created and added
+ * automatically to it.  This is to be used whenever you need to create a
+ * device that is not associated with any "real" system resources, and do
+ * not want to have to deal with a bus/driver binding logic.  It is
+ * intended to be very simple, with only a create and a destroy function
+ * available.
+ */
+#ifndef _FAUX_DEVICE_H_
+#define _FAUX_DEVICE_H_
+
+#include <linux/container_of.h>
+#include <linux/device.h>
+
+/**
+ * struct faux_device - a "faux" device
+ * @dev:	internal struct device of the object
+ *
+ * A simple faux device that can be created/destroyed.  To be used when a
+ * driver only needs to have a device to "hang" something off.  This can be
+ * used for downloading firmware or other basic tasks.  Use this instead of
+ * a struct platform_device if the device has no resources assigned to
+ * it at all.
+ */
+struct faux_device {
+	struct device dev;
+};
+#define to_faux_device(x) container_of_const((x), struct faux_device, dev)
+
+/**
+ * struct faux_device_ops - a set of callbacks for a struct faux_device
+ * @probe:	called when a faux device is probed by the driver core
+ *		before the device is fully bound to the internal faux bus
+ *		code.  If probe succeeds, return 0, otherwise return a
+ *		negative error number to stop the probe sequence from
+ *		succeeding.
+ * @remove:	called when a faux device is removed from the system
+ *
+ * Both @probe and @remove are optional, if not needed, set to NULL.
+ */
+struct faux_device_ops {
+	int (*probe)(struct faux_device *faux_dev);
+	void (*remove)(struct faux_device *faux_dev);
+};
+
+struct faux_device *faux_device_create(const char *name,
+				       struct device *parent,
+				       const struct faux_device_ops *faux_ops);
+struct faux_device *faux_device_create_with_groups(const char *name,
+						   struct device *parent,
+						   const struct faux_device_ops *faux_ops,
+						   const struct attribute_group **groups);
+void faux_device_destroy(struct faux_device *faux_dev);
+
+static inline void *faux_device_get_drvdata(const struct faux_device *faux_dev)
+{
+	return dev_get_drvdata(&faux_dev->dev);
+}
+
+static inline void faux_device_set_drvdata(struct faux_device *faux_dev, void *data)
+{
+	dev_set_drvdata(&faux_dev->dev, data);
+}
+
+#endif /* _FAUX_DEVICE_H_ */
diff --git a/include/linux/device_cgroup.h b/include/linux/device_cgroup.h
index d02f32b7514e..0864773a57e8 100644
--- a/include/linux/device_cgroup.h
+++ b/include/linux/device_cgroup.h
@@ -18,15 +18,16 @@ static inline int devcgroup_inode_permission(struct inode *inode, int mask)
 {
 	short type, access = 0;
 
+	if (likely(!S_ISBLK(inode->i_mode) && !S_ISCHR(inode->i_mode)))
+		return 0;
+
 	if (likely(!inode->i_rdev))
 		return 0;
 
 	if (S_ISBLK(inode->i_mode))
 		type = DEVCG_DEV_BLOCK;
-	else if (S_ISCHR(inode->i_mode))
+	else /* S_ISCHR by the test above */
 		type = DEVCG_DEV_CHAR;
-	else
-		return 0;
 
 	if (mask & MAY_WRITE)
 		access |= DEVCG_ACC_WRITE;
diff --git a/include/linux/devm-helpers.h b/include/linux/devm-helpers.h
index 74891802200d..708ca9131402 100644
--- a/include/linux/devm-helpers.h
+++ b/include/linux/devm-helpers.h
@@ -41,7 +41,7 @@ static inline void devm_delayed_work_drop(void *res)
  * detached. A few drivers need delayed work which must be cancelled before
  * driver is detached to avoid accessing removed resources.
  * devm_delayed_work_autocancel() can be used to omit the explicit
- * cancelleation when driver is detached.
+ * cancellation when driver is detached.
  */
 static inline int devm_delayed_work_autocancel(struct device *dev,
 					       struct delayed_work *w,
@@ -66,7 +66,7 @@ static inline void devm_work_drop(void *res)
  * A few drivers need to queue work which must be cancelled before driver
  * is detached to avoid accessing removed resources.
  * devm_work_autocancel() can be used to omit the explicit
- * cancelleation when driver is detached.
+ * cancellation when driver is detached.
  */
 static inline int devm_work_autocancel(struct device *dev,
 				       struct work_struct *w,
diff --git a/include/linux/dfl.h b/include/linux/dfl.h
index 0a7a00a0ee7f..1f02db0c1897 100644
--- a/include/linux/dfl.h
+++ b/include/linux/dfl.h
@@ -71,7 +71,7 @@ struct dfl_driver {
 };
 
 #define to_dfl_dev(d) container_of(d, struct dfl_device, dev)
-#define to_dfl_drv(d) container_of(d, struct dfl_driver, drv)
+#define to_dfl_drv(d) container_of_const(d, struct dfl_driver, drv)
 
 /*
  * use a macro to avoid include chaining to get THIS_MODULE.
diff --git a/include/linux/dibs.h b/include/linux/dibs.h
new file mode 100644
index 000000000000..c75607f8a5cf
--- /dev/null
+++ b/include/linux/dibs.h
@@ -0,0 +1,464 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Direct Internal Buffer Sharing
+ *
+ *  Definitions for the DIBS module
+ *
+ *  Copyright IBM Corp. 2025
+ */
+#ifndef _DIBS_H
+#define _DIBS_H
+
+#include <linux/device.h>
+#include <linux/uuid.h>
+
+/* DIBS - Direct Internal Buffer Sharing - concept
+ * -----------------------------------------------
+ * In the case of multiple system sharing the same hardware, dibs fabrics can
+ * provide dibs devices to these systems. The systems use dibs devices of the
+ * same fabric to communicate via dmbs (Direct Memory Buffers). Each dmb has
+ * exactly one owning local dibs device and one remote using dibs device, that
+ * is authorized to write into this dmb. This access control is provided by the
+ * dibs fabric.
+ *
+ * Because the access to the dmb is based on access to physical memory, it is
+ * lossless and synchronous. The remote devices can directly access any offset
+ * of the dmb.
+ *
+ * Dibs fabrics, dibs devices and dmbs are identified by tokens and ids.
+ * Dibs fabric id is unique within the same hardware (with the exception of the
+ * dibs loopback fabric), dmb token is unique within the same fabric, dibs
+ * device gids are guaranteed to be unique within the same fabric and
+ * statistically likely to be globally unique. The exchange of these tokens and
+ * ids between the systems is not part of the dibs concept.
+ *
+ * The dibs layer provides an abstraction between dibs device drivers and dibs
+ * clients.
+ */
+
+/* DMB - Direct Memory Buffer
+ * --------------------------
+ * A dibs client provides a dmb as input buffer for a local receiving
+ * dibs device for exactly one (remote) sending dibs device. Only this
+ * sending device can send data into this dmb using move_data(). Sender
+ * and receiver can be the same device. A dmb belongs to exactly one client.
+ */
+struct dibs_dmb {
+	/* tok - Token for this dmb
+	 * Used by remote and local devices and clients to address this dmb.
+	 * Provided by dibs fabric. Unique per dibs fabric.
+	 */
+	u64 dmb_tok;
+	/* rgid - GID of designated remote sending device */
+	uuid_t rgid;
+	/* cpu_addr - buffer address */
+	void *cpu_addr;
+	/* len - buffer length */
+	u32 dmb_len;
+	/* idx - Index of this DMB on this receiving device */
+	u32 idx;
+	/* VLAN support (deprecated)
+	 * In order to write into a vlan-tagged dmb, the remote device needs
+	 * to belong to the this vlan
+	 */
+	u32 vlan_valid;
+	u32 vlan_id;
+	/* optional, used by device driver */
+	dma_addr_t dma_addr;
+};
+
+/* DIBS events
+ * -----------
+ * Dibs devices can optionally notify dibs clients about events that happened
+ * in the fabric or at the remote device or remote dmb.
+ */
+enum dibs_event_type {
+	/* Buffer event, e.g. a remote dmb was unregistered */
+	DIBS_BUF_EVENT,
+	/* Device event, e.g. a remote dibs device was disabled */
+	DIBS_DEV_EVENT,
+	/* Software event, a dibs client can send an event signal to a
+	 * remote dibs device.
+	 */
+	DIBS_SW_EVENT,
+	DIBS_OTHER_TYPE };
+
+enum dibs_event_subtype {
+	DIBS_BUF_UNREGISTERED,
+	DIBS_DEV_DISABLED,
+	DIBS_DEV_ERR_STATE,
+	DIBS_OTHER_SUBTYPE
+};
+
+struct dibs_event {
+	u32 type;
+	u32 subtype;
+	/* uuid_null if invalid */
+	uuid_t gid;
+	/* zero if invalid */
+	u64 buffer_tok;
+	u64 time;
+	/* additional data or zero */
+	u64 data;
+};
+
+struct dibs_dev;
+
+/* DIBS client
+ * -----------
+ */
+#define MAX_DIBS_CLIENTS	8
+#define NO_DIBS_CLIENT		0xff
+/* All dibs clients have access to all dibs devices.
+ * A dibs client provides the following functions to be called by dibs layer or
+ * dibs device drivers:
+ */
+struct dibs_client_ops {
+	/**
+	 *  add_dev() - add a dibs device
+	 *  @dev: device that was added
+	 *
+	 * Will be called during dibs_register_client() for all existing
+	 * dibs devices and whenever a new dibs device is registered.
+	 * dev is usable until dibs_client.remove() is called.
+	 * *dev is protected by device refcounting.
+	 */
+	void (*add_dev)(struct dibs_dev *dev);
+	/**
+	 * del_dev() - remove a dibs device
+	 * @dev: device to be removed
+	 *
+	 * Will be called whenever a dibs device is removed.
+	 * Will be called during dibs_unregister_client() for all existing
+	 * dibs devices and whenever a dibs device is unregistered.
+	 * The device has already stopped initiative for this client:
+	 * No new handlers will be started.
+	 * The device is no longer usable by this client after this call.
+	 */
+	void (*del_dev)(struct dibs_dev *dev);
+	/**
+	 * handle_irq() - Handle signaling for a DMB
+	 * @dev: device that owns the dmb
+	 * @idx: Index of the dmb that got signalled
+	 * @dmbemask: signaling mask of the dmb
+	 *
+	 * Handle signaling for a dmb that was registered by this client
+	 * for this device.
+	 * The dibs device can coalesce multiple signaling triggers into a
+	 * single call of handle_irq(). dmbemask can be used to indicate
+	 * different kinds of triggers.
+	 *
+	 * Context: Called in IRQ context by dibs device driver
+	 */
+	void (*handle_irq)(struct dibs_dev *dev, unsigned int idx,
+			   u16 dmbemask);
+	/**
+	 * handle_event() - Handle control information sent by device
+	 * @dev: device reporting the event
+	 * @event: ism event structure
+	 *
+	 * * Context: Called in IRQ context by dibs device driver
+	 */
+	void (*handle_event)(struct dibs_dev *dev,
+			     const struct dibs_event *event);
+};
+
+struct dibs_client {
+	/* client name for logging and debugging purposes */
+	const char *name;
+	const struct dibs_client_ops *ops;
+	/* client index - provided and used by dibs layer */
+	u8 id;
+};
+
+/* Functions to be called by dibs clients:
+ */
+/**
+ * dibs_register_client() - register a client with dibs layer
+ * @client: this client
+ *
+ * Will call client->ops->add_dev() for all existing dibs devices.
+ * Return: zero on success.
+ */
+int dibs_register_client(struct dibs_client *client);
+/**
+ * dibs_unregister_client() - unregister a client with dibs layer
+ * @client: this client
+ *
+ * Will call client->ops->del_dev() for all existing dibs devices.
+ * Return: zero on success.
+ */
+int dibs_unregister_client(struct dibs_client *client);
+
+/* dibs clients can call dibs device ops. */
+
+/* DIBS devices
+ * ------------
+ */
+
+/* Defined fabric id / CHID for all loopback devices:
+ * All dibs loopback devices report this fabric id. In this case devices with
+ * the same fabric id can NOT communicate via dibs. Only loopback devices with
+ * the same dibs device gid can communicate (=same device with itself).
+ */
+#define DIBS_LOOPBACK_FABRIC	0xFFFF
+
+/* A dibs device provides the following functions to be called by dibs clients.
+ * They are mandatory, unless marked 'optional'.
+ */
+struct dibs_dev_ops {
+	/**
+	 * get_fabric_id()
+	 * @dev: local dibs device
+	 *
+	 * Only devices on the same dibs fabric can communicate. Fabric_id is
+	 * unique inside the same HW system. Use fabric_id for fast negative
+	 * checks, but only query_remote_gid() can give a reliable positive
+	 * answer:
+	 * Different fabric_id: dibs is not possible
+	 * Same fabric_id: dibs may be possible or not
+	 *		   (e.g. different HW systems)
+	 * EXCEPTION: DIBS_LOOPBACK_FABRIC denotes an ism_loopback device
+	 *	      that can only communicate with itself. Use dibs_dev.gid
+	 *	      or query_remote_gid()to determine whether sender and
+	 *	      receiver use the same ism_loopback device.
+	 * Return: 2 byte dibs fabric id
+	 */
+	u16 (*get_fabric_id)(struct dibs_dev *dev);
+	/**
+	 * query_remote_gid()
+	 * @dev: local dibs device
+	 * @rgid: gid of remote dibs device
+	 * @vid_valid: if zero, vid will be ignored;
+	 *	       deprecated, ignored if device does not support vlan
+	 * @vid: VLAN id; deprecated, ignored if device does not support vlan
+	 *
+	 * Query whether a remote dibs device is reachable via this local device
+	 * and this vlan id.
+	 * Return: 0 if remote gid is reachable.
+	 */
+	int (*query_remote_gid)(struct dibs_dev *dev, const uuid_t *rgid,
+				u32 vid_valid, u32 vid);
+	/**
+	 * max_dmbs()
+	 * Return: Max number of DMBs that can be registered for this kind of
+	 *	   dibs_dev
+	 */
+	int (*max_dmbs)(void);
+	/**
+	 * register_dmb() - allocate and register a dmb
+	 * @dev: dibs device
+	 * @dmb: dmb struct to be registered
+	 * @client: dibs client
+	 * @vid: VLAN id; deprecated, ignored if device does not support vlan
+	 *
+	 * The following fields of dmb must provide valid input:
+	 *	@rgid: gid of remote user device
+	 *	@dmb_len: buffer length
+	 *	@idx: Optionally:requested idx (if non-zero)
+	 *	@vlan_valid: if zero, vlan_id will be ignored;
+	 *		     deprecated, ignored if device does not support vlan
+	 *	@vlan_id: deprecated, ignored if device does not support vlan
+	 * Upon return in addition the following fields will be valid:
+	 *	@dmb_tok: for usage by remote and local devices and clients
+	 *	@cpu_addr: allocated buffer
+	 *	@idx: dmb index, unique per dibs device
+	 *	@dma_addr: to be used by device driver,if applicable
+	 *
+	 * Allocate a dmb buffer and register it with this device and for this
+	 * client.
+	 * Return: zero on success
+	 */
+	int (*register_dmb)(struct dibs_dev *dev, struct dibs_dmb *dmb,
+			    struct dibs_client *client);
+	/**
+	 * unregister_dmb() - unregister and free a dmb
+	 * @dev: dibs device
+	 * @dmb: dmb struct to be unregistered
+	 * The following fields of dmb must provide valid input:
+	 *	@dmb_tok
+	 *	@cpu_addr
+	 *	@idx
+	 *
+	 * Free dmb.cpu_addr and unregister the dmb from this device.
+	 * Return: zero on success
+	 */
+	int (*unregister_dmb)(struct dibs_dev *dev, struct dibs_dmb *dmb);
+	/**
+	 * move_data() - write into a remote dmb
+	 * @dev: Local sending dibs device
+	 * @dmb_tok: Token of the remote dmb
+	 * @idx: signaling index in dmbemask
+	 * @sf: signaling flag;
+	 *      if true, idx will be turned on at target dmbemask mask
+	 *      and target device will be signaled.
+	 * @offset: offset within target dmb
+	 * @data: pointer to data to be sent
+	 * @size: length of data to be sent, can be zero.
+	 *
+	 * Use dev to write data of size at offset into a remote dmb
+	 * identified by dmb_tok. Data is moved synchronously, *data can
+	 * be freed when this function returns.
+	 *
+	 * If signaling flag (sf) is true, bit number idx bit will be turned
+	 * on in the dmbemask mask when handle_irq() is called at the remote
+	 * dibs client that owns the target dmb. The target device may chose
+	 * to coalesce the signaling triggers of multiple move_data() calls
+	 * to the same target dmb into a single handle_irq() call.
+	 * Return: zero on success
+	 */
+	int (*move_data)(struct dibs_dev *dev, u64 dmb_tok, unsigned int idx,
+			 bool sf, unsigned int offset, void *data,
+			 unsigned int size);
+	/**
+	 * add_vlan_id() - add dibs device to vlan (optional, deprecated)
+	 * @dev: dibs device
+	 * @vlan_id: vlan id
+	 *
+	 * In order to write into a vlan-tagged dmb, the remote device needs
+	 * to belong to the this vlan. A device can belong to more than 1 vlan.
+	 * Any device can access an untagged dmb.
+	 * Deprecated, only supported for backwards compatibility.
+	 * Return: zero on success
+	 */
+	int (*add_vlan_id)(struct dibs_dev *dev, u64 vlan_id);
+	/**
+	 * del_vlan_id() - remove dibs device from vlan (optional, deprecated)
+	 * @dev: dibs device
+	 * @vlan_id: vlan id
+	 * Return: zero on success
+	 */
+	int (*del_vlan_id)(struct dibs_dev *dev, u64 vlan_id);
+	/**
+	 * signal_event() - trigger an event at a remote dibs device (optional)
+	 * @dev: local dibs device
+	 * @rgid: gid of remote dibs device
+	 * trigger_irq: zero: notification may be coalesced with other events
+	 *		non-zero: notify immediately
+	 * @subtype: 4 byte event code, meaning is defined by dibs client
+	 * @data: 8 bytes of additional information,
+	 *	  meaning is defined by dibs client
+	 *
+	 * dibs devices can offer support for sending a control event of type
+	 * EVENT_SWR to a remote dibs device.
+	 * NOTE: handle_event() will be called for all registered dibs clients
+	 * at the remote device.
+	 * Return: zero on success
+	 */
+	int (*signal_event)(struct dibs_dev *dev, const uuid_t *rgid,
+			    u32 trigger_irq, u32 event_code, u64 info);
+	/**
+	 * support_mmapped_rdmb() - can this device provide memory mapped
+	 *			    remote dmbs? (optional)
+	 * @dev: dibs device
+	 *
+	 * A dibs device can provide a kernel address + length, that represent
+	 * a remote target dmb (like MMIO). Alternatively to calling
+	 * move_data(), a dibs client can write into such a ghost-send-buffer
+	 * (= to this kernel address) and the data will automatically
+	 * immediately appear in the target dmb, even without calling
+	 * move_data().
+	 *
+	 * Either all 3 function pointers for support_dmb_nocopy(),
+	 * attach_dmb() and detach_dmb() are defined, or all of them must
+	 * be NULL.
+	 *
+	 * Return: non-zero, if memory mapped remote dmbs are supported.
+	 */
+	int (*support_mmapped_rdmb)(struct dibs_dev *dev);
+	/**
+	 * attach_dmb() - attach local memory to a remote dmb
+	 * @dev: Local sending ism device
+	 * @dmb: all other parameters are passed in the form of a
+	 *	 dmb struct
+	 *	 TODO: (THIS IS CONFUSING, should be changed)
+	 *  dmb_tok: (in) Token of the remote dmb, we want to attach to
+	 *  cpu_addr: (out) MMIO address
+	 *  dma_addr: (out) MMIO address (if applicable, invalid otherwise)
+	 *  dmb_len: (out) length of local MMIO region,
+	 *           equal to length of remote DMB.
+	 *  sba_idx: (out) index of remote dmb (NOT HELPFUL, should be removed)
+	 *
+	 * Provides a memory address to the sender that can be used to
+	 * directly write into the remote dmb.
+	 * Memory is available until detach_dmb is called
+	 *
+	 * Return: Zero upon success, Error code otherwise
+	 */
+	int (*attach_dmb)(struct dibs_dev *dev, struct dibs_dmb *dmb);
+	/**
+	 * detach_dmb() - Detach the ghost buffer from a remote dmb
+	 * @dev: ism device
+	 * @token: dmb token of the remote dmb
+	 *
+	 * No need to free cpu_addr.
+	 *
+	 * Return: Zero upon success, Error code otherwise
+	 */
+	int (*detach_dmb)(struct dibs_dev *dev, u64 token);
+};
+
+struct dibs_dev {
+	struct list_head list;
+	struct device dev;
+	/* To be filled by device driver, before calling dibs_dev_add(): */
+	const struct dibs_dev_ops *ops;
+	uuid_t gid;
+	/* priv pointer for device driver */
+	void *drv_priv;
+
+	/* priv pointer per client; for client usage only */
+	void *priv[MAX_DIBS_CLIENTS];
+
+	/* get this lock before accessing any of the fields below */
+	spinlock_t lock;
+	/* array of client ids indexed by dmb idx;
+	 * can be used as indices into priv and subs arrays
+	 */
+	u8 *dmb_clientid_arr;
+	/* Sparse array of all ISM clients */
+	struct dibs_client *subs[MAX_DIBS_CLIENTS];
+};
+
+static inline void dibs_set_priv(struct dibs_dev *dev,
+				 struct dibs_client *client, void *priv)
+{
+	dev->priv[client->id] = priv;
+}
+
+static inline void *dibs_get_priv(struct dibs_dev *dev,
+				  struct dibs_client *client)
+{
+	return dev->priv[client->id];
+}
+
+/* ------- End of client-only functions ----------- */
+
+/* Functions to be called by dibs device drivers:
+ */
+/**
+ * dibs_dev_alloc() - allocate and reference device structure
+ *
+ * The following fields will be valid upon successful return: dev
+ * NOTE: Use put_device(dibs_get_dev(@dibs)) to give up your reference instead
+ * of freeing @dibs @dev directly once you have successfully called this
+ * function.
+ * Return: Pointer to dibs device structure
+ */
+struct dibs_dev *dibs_dev_alloc(void);
+/**
+ * dibs_dev_add() - register with dibs layer and all clients
+ * @dibs: dibs device
+ *
+ * The following fields must be valid upon entry: dev, ops, drv_priv
+ * All fields will be valid upon successful return.
+ * Return: zero on success
+ */
+int dibs_dev_add(struct dibs_dev *dibs);
+/**
+ * dibs_dev_del() - unregister from dibs layer and all clients
+ * @dibs: dibs device
+ */
+void dibs_dev_del(struct dibs_dev *dibs);
+
+#endif	/* _DIBS_H */
diff --git a/include/linux/dim.h b/include/linux/dim.h
index f343bc9aa2ec..06543fd40fcc 100644
--- a/include/linux/dim.h
+++ b/include/linux/dim.h
@@ -10,6 +10,15 @@
 #include <linux/types.h>
 #include <linux/workqueue.h>
 
+struct net_device;
+
+/* Number of DIM profiles and period mode. */
+#define NET_DIM_PARAMS_NUM_PROFILES 5
+#define NET_DIM_DEFAULT_RX_CQ_PKTS_FROM_EQE 256
+#define NET_DIM_DEFAULT_TX_CQ_PKTS_FROM_EQE 128
+#define NET_DIM_DEF_PROFILE_CQE 1
+#define NET_DIM_DEF_PROFILE_EQE 1
+
 /*
  * Number of events between DIM iterations.
  * Causes a moderation of the algorithm run.
@@ -38,12 +47,45 @@
  * @pkts: CQ packet counter suggestion (by DIM)
  * @comps: Completion counter
  * @cq_period_mode: CQ period count mode (from CQE/EQE)
+ * @rcu: for asynchronous kfree_rcu
  */
 struct dim_cq_moder {
 	u16 usec;
 	u16 pkts;
 	u16 comps;
 	u8 cq_period_mode;
+	struct rcu_head rcu;
+};
+
+#define DIM_PROFILE_RX		BIT(0)	/* support rx profile modification */
+#define DIM_PROFILE_TX		BIT(1)	/* support tx profile modification */
+
+#define DIM_COALESCE_USEC	BIT(0)	/* support usec field modification */
+#define DIM_COALESCE_PKTS	BIT(1)	/* support pkts field modification */
+#define DIM_COALESCE_COMPS	BIT(2)	/* support comps field modification */
+
+/**
+ * struct dim_irq_moder - Structure for irq moderation information.
+ * Used to collect irq moderation related information.
+ *
+ * @profile_flags: DIM_PROFILE_*
+ * @coal_flags: DIM_COALESCE_* for Rx and Tx
+ * @dim_rx_mode: Rx DIM period count mode: CQE or EQE
+ * @dim_tx_mode: Tx DIM period count mode: CQE or EQE
+ * @rx_profile: DIM profile list for Rx
+ * @tx_profile: DIM profile list for Tx
+ * @rx_dim_work: Rx DIM worker scheduled by net_dim()
+ * @tx_dim_work: Tx DIM worker scheduled by net_dim()
+ */
+struct dim_irq_moder {
+	u8 profile_flags;
+	u8 coal_flags;
+	u8 dim_rx_mode;
+	u8 dim_tx_mode;
+	struct dim_cq_moder __rcu *rx_profile;
+	struct dim_cq_moder __rcu *tx_profile;
+	void (*rx_dim_work)(struct work_struct *work);
+	void (*tx_dim_work)(struct work_struct *work);
 };
 
 /**
@@ -192,6 +234,77 @@ enum dim_step_result {
 };
 
 /**
+ * net_dim_init_irq_moder - collect information to initialize irq moderation
+ * @dev: target network device
+ * @profile_flags: Rx or Tx profile modification capability
+ * @coal_flags: irq moderation params flags
+ * @rx_mode: CQ period mode for Rx
+ * @tx_mode: CQ period mode for Tx
+ * @rx_dim_work: Rx worker called after dim decision
+ * @tx_dim_work: Tx worker called after dim decision
+ *
+ * Return: 0 on success or a negative error code.
+ */
+int net_dim_init_irq_moder(struct net_device *dev, u8 profile_flags,
+			   u8 coal_flags, u8 rx_mode, u8 tx_mode,
+			   void (*rx_dim_work)(struct work_struct *work),
+			   void (*tx_dim_work)(struct work_struct *work));
+
+/**
+ * net_dim_free_irq_moder - free fields for irq moderation
+ * @dev: target network device
+ */
+void net_dim_free_irq_moder(struct net_device *dev);
+
+/**
+ * net_dim_setting - initialize DIM's cq mode and schedule worker
+ * @dev: target network device
+ * @dim: DIM context
+ * @is_tx: true indicates the tx direction, false indicates the rx direction
+ */
+void net_dim_setting(struct net_device *dev, struct dim *dim, bool is_tx);
+
+/**
+ * net_dim_work_cancel - synchronously cancel dim's worker
+ * @dim: DIM context
+ */
+void net_dim_work_cancel(struct dim *dim);
+
+/**
+ * net_dim_get_rx_irq_moder - get DIM rx results based on profile_ix
+ * @dev: target network device
+ * @dim: DIM context
+ *
+ * Return: DIM irq moderation
+ */
+struct dim_cq_moder
+net_dim_get_rx_irq_moder(struct net_device *dev, struct dim *dim);
+
+/**
+ * net_dim_get_tx_irq_moder - get DIM tx results based on profile_ix
+ * @dev: target network device
+ * @dim: DIM context
+ *
+ * Return: DIM irq moderation
+ */
+struct dim_cq_moder
+net_dim_get_tx_irq_moder(struct net_device *dev, struct dim *dim);
+
+/**
+ * net_dim_set_rx_mode - set DIM rx cq mode
+ * @dev: target network device
+ * @rx_mode: target rx cq mode
+ */
+void net_dim_set_rx_mode(struct net_device *dev, u8 rx_mode);
+
+/**
+ * net_dim_set_tx_mode - set DIM tx cq mode
+ * @dev: target network device
+ * @tx_mode: target tx cq mode
+ */
+void net_dim_set_tx_mode(struct net_device *dev, u8 tx_mode);
+
+/**
  *	dim_on_top - check if current state is a good place to stop (top location)
  *	@dim: DIM context
  *
@@ -238,7 +351,8 @@ void dim_park_tired(struct dim *dim);
  * Takes into consideration counter wrap-around.
  * Returned boolean indicates whether curr_stats are reliable.
  */
-bool dim_calc_stats(struct dim_sample *start, struct dim_sample *end,
+bool dim_calc_stats(const struct dim_sample *start,
+		    const struct dim_sample *end,
 		    struct dim_stats *curr_stats);
 
 /**
@@ -311,7 +425,7 @@ struct dim_cq_moder net_dim_get_def_tx_moderation(u8 cq_period_mode);
  * This is the main logic of the algorithm, where data is processed in order
  * to decide on next required action.
  */
-void net_dim(struct dim *dim, struct dim_sample end_sample);
+void net_dim(struct dim *dim, const struct dim_sample *end_sample);
 
 /* RDMA DIM */
 
diff --git a/include/linux/dio.h b/include/linux/dio.h
index 5abd07361eb5..464331c4c4a7 100644
--- a/include/linux/dio.h
+++ b/include/linux/dio.h
@@ -68,7 +68,7 @@ struct dio_bus {
 };
 
 extern struct dio_bus dio_bus;      /* Single DIO bus */
-extern struct bus_type dio_bus_type;
+extern const struct bus_type dio_bus_type;
 
     /*
      *  DIO device IDs
@@ -93,7 +93,7 @@ struct dio_driver {
 	struct device_driver driver;
 };
 
-#define to_dio_driver(drv)    container_of(drv, struct dio_driver, driver)
+#define to_dio_driver(drv)    container_of_const(drv, struct dio_driver, driver)
 
 /* DIO/DIO-II boards all have the following 8bit registers.
  * These are offsets from the base of the device.
diff --git a/include/linux/dlm.h b/include/linux/dlm.h
index c58c4f790c04..7e7b45b0d097 100644
--- a/include/linux/dlm.h
+++ b/include/linux/dlm.h
@@ -35,6 +35,9 @@ struct dlm_lockspace_ops {
 			      int num_slots, int our_slot, uint32_t generation);
 };
 
+/* only relevant for kernel lockspaces, will be removed in future */
+#define DLM_LSFL_SOFTIRQ __DLM_LSFL_RESERVED0
+
 /*
  * dlm_new_lockspace
  *
@@ -55,6 +58,11 @@ struct dlm_lockspace_ops {
  *   used to select the directory node.  Must be the same on all nodes.
  * DLM_LSFL_NEWEXCL
  *   dlm_new_lockspace() should return -EEXIST if the lockspace exists.
+ * DLM_LSFL_SOFTIRQ
+ *   dlm request callbacks (ast, bast) are softirq safe. Flag should be
+ *   preferred by users. Will be default in some future. If set the
+ *   strongest context for ast, bast callback is softirq as it avoids
+ *   an additional context switch.
  *
  * lvblen: length of lvb in bytes.  Must be multiple of 8.
  *   dlm_new_lockspace() returns an error if this does not match
@@ -80,12 +88,43 @@ int dlm_new_lockspace(const char *name, const char *cluster,
 		      int *ops_result, dlm_lockspace_t **lockspace);
 
 /*
+ * dlm_release_lockspace() release_option values:
+ *
+ * DLM_RELEASE_NO_LOCKS returns -EBUSY if any locks (lkb's)
+ *   exist in the local lockspace.
+ *
+ * DLM_RELEASE_UNUSED previous value that is no longer used.
+ *
+ * DLM_RELEASE_NORMAL releases the lockspace regardless of any
+ *   locks managed in the local lockspace.
+ *
+ * DLM_RELEASE_NO_EVENT release the lockspace regardless of any
+ *   locks managed in the local lockspace, and does not submit
+ *   a leave event to the cluster manager, so other nodes will
+ *   not be notified that the node should be removed from the
+ *   list of lockspace members.
+ *
+ * DLM_RELEASE_RECOVER like DLM_RELEASE_NORMAL, but the remaining
+ *   nodes will handle the removal of the node as if the node
+ *   had failed, e.g. the recover_slot() callback would be used.
+ */
+#define DLM_RELEASE_NO_LOCKS		0
+#define DLM_RELEASE_UNUSED		1
+#define DLM_RELEASE_NORMAL		2
+#define DLM_RELEASE_NO_EVENT		3
+#define DLM_RELEASE_RECOVER		4
+#define __DLM_RELEASE_MAX		DLM_RELEASE_RECOVER
+
+/*
  * dlm_release_lockspace
  *
  * Stop a lockspace.
+ *
+ * release_option: see DLM_RELEASE values above.
  */
 
-int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force);
+int dlm_release_lockspace(dlm_lockspace_t *lockspace,
+			  unsigned int release_option);
 
 /*
  * dlm_lock
@@ -121,7 +160,14 @@ int dlm_release_lockspace(dlm_lockspace_t *lockspace, int force);
  * call.
  *
  * AST routines should not block (at least not for long), but may make
- * any locking calls they please.
+ * any locking calls they please. If DLM_LSFL_SOFTIRQ for kernel
+ * users of dlm_new_lockspace() is passed the ast and bast callbacks
+ * can be processed in softirq context. Also some of the callback
+ * contexts are in the same context as the DLM lock request API, users
+ * must not hold locks while calling dlm lock request API and trying
+ * to acquire this lock in the callback again, this will end in a
+ * lock recursion. For newer implementation the DLM_LSFL_SOFTIRQ
+ * should be used.
  */
 
 int dlm_lock(dlm_lockspace_t *lockspace,
diff --git a/include/linux/dlm_plock.h b/include/linux/dlm_plock.h
index e6d76e8715a6..15fc856d198c 100644
--- a/include/linux/dlm_plock.h
+++ b/include/linux/dlm_plock.h
@@ -11,6 +11,8 @@ int dlm_posix_lock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		int cmd, struct file_lock *fl);
 int dlm_posix_unlock(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		struct file_lock *fl);
+int dlm_posix_cancel(dlm_lockspace_t *lockspace, u64 number, struct file *file,
+		     struct file_lock *fl);
 int dlm_posix_get(dlm_lockspace_t *lockspace, u64 number, struct file *file,
 		struct file_lock *fl);
 #endif
diff --git a/include/linux/dm-bufio.h b/include/linux/dm-bufio.h
index 681656a1c03d..d1503b815a78 100644
--- a/include/linux/dm-bufio.h
+++ b/include/linux/dm-bufio.h
@@ -38,6 +38,8 @@ dm_bufio_client_create(struct block_device *bdev, unsigned int block_size,
  */
 void dm_bufio_client_destroy(struct dm_bufio_client *c);
 
+void dm_bufio_client_reset(struct dm_bufio_client *c);
+
 /*
  * Set the sector range.
  * When this function is called, there must be no I/O in progress on the bufio
@@ -62,6 +64,9 @@ void dm_bufio_set_sector_offset(struct dm_bufio_client *c, sector_t start);
 void *dm_bufio_read(struct dm_bufio_client *c, sector_t block,
 		    struct dm_buffer **bp);
 
+void *dm_bufio_read_with_ioprio(struct dm_bufio_client *c, sector_t block,
+				struct dm_buffer **bp, unsigned short ioprio);
+
 /*
  * Like dm_bufio_read, but return buffer from cache, don't read
  * it. If the buffer is not in the cache, return NULL.
@@ -84,6 +89,10 @@ void *dm_bufio_new(struct dm_bufio_client *c, sector_t block,
 void dm_bufio_prefetch(struct dm_bufio_client *c,
 		       sector_t block, unsigned int n_blocks);
 
+void dm_bufio_prefetch_with_ioprio(struct dm_bufio_client *c,
+				sector_t block, unsigned int n_blocks,
+				unsigned short ioprio);
+
 /*
  * Release a reference obtained with dm_bufio_{read,get,new}. The data
  * pointer and dm_buffer pointer is no longer valid after this call.
diff --git a/include/linux/dm-io.h b/include/linux/dm-io.h
index 7595142f3fc5..7b2968612b7e 100644
--- a/include/linux/dm-io.h
+++ b/include/linux/dm-io.h
@@ -80,7 +80,8 @@ void dm_io_client_destroy(struct dm_io_client *client);
  * error occurred doing io to the corresponding region.
  */
 int dm_io(struct dm_io_request *io_req, unsigned int num_regions,
-	  struct dm_io_region *region, unsigned int long *sync_error_bits);
+	  struct dm_io_region *region, unsigned int long *sync_error_bits,
+	  unsigned short ioprio);
 
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_DM_IO_H */
diff --git a/include/linux/dm-verity-loadpin.h b/include/linux/dm-verity-loadpin.h
index 552b817ab102..3ac6dbaeaa37 100644
--- a/include/linux/dm-verity-loadpin.h
+++ b/include/linux/dm-verity-loadpin.h
@@ -12,7 +12,7 @@ extern struct list_head dm_verity_loadpin_trusted_root_digests;
 struct dm_verity_loadpin_trusted_root_digest {
 	struct list_head node;
 	unsigned int len;
-	u8 data[];
+	u8 data[] __counted_by(len);
 };
 
 #if IS_ENABLED(CONFIG_SECURITY_LOADPIN_VERITY)
diff --git a/include/linux/dma-buf-mapping.h b/include/linux/dma-buf-mapping.h
new file mode 100644
index 000000000000..a3c0ce2d3a42
--- /dev/null
+++ b/include/linux/dma-buf-mapping.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * DMA BUF Mapping Helpers
+ *
+ */
+#ifndef __DMA_BUF_MAPPING_H__
+#define __DMA_BUF_MAPPING_H__
+#include <linux/dma-buf.h>
+
+struct sg_table *dma_buf_phys_vec_to_sgt(struct dma_buf_attachment *attach,
+					 struct p2pdma_provider *provider,
+					 struct dma_buf_phys_vec *phys_vec,
+					 size_t nr_ranges, size_t size,
+					 enum dma_data_direction dir);
+void dma_buf_free_sgt(struct dma_buf_attachment *attach, struct sg_table *sgt,
+		      enum dma_data_direction dir);
+#endif
diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h
index 3f31baa3293f..0bc492090237 100644
--- a/include/linux/dma-buf.h
+++ b/include/linux/dma-buf.h
@@ -22,6 +22,7 @@
 #include <linux/fs.h>
 #include <linux/dma-fence.h>
 #include <linux/wait.h>
+#include <linux/pci-p2pdma.h>
 
 struct device;
 struct dma_buf;
@@ -35,15 +36,6 @@ struct dma_buf_attachment;
  */
 struct dma_buf_ops {
 	/**
-	  * @cache_sgt_mapping:
-	  *
-	  * If true the framework will cache the first mapping made for each
-	  * attachment. This avoids creating mappings for attachments multiple
-	  * times.
-	  */
-	bool cache_sgt_mapping;
-
-	/**
 	 * @attach:
 	 *
 	 * This is called from dma_buf_attach() to make sure that a given
@@ -343,16 +335,19 @@ struct dma_buf {
 	/**
 	 * @exp_name:
 	 *
-	 * Name of the exporter; useful for debugging. See the
-	 * DMA_BUF_SET_NAME IOCTL.
+	 * Name of the exporter; useful for debugging. Must not be NULL
 	 */
 	const char *exp_name;
 
 	/**
 	 * @name:
 	 *
-	 * Userspace-provided name; useful for accounting and debugging,
-	 * protected by dma_resv_lock() on @resv and @name_lock for read access.
+	 * Userspace-provided name. Default value is NULL. If not NULL,
+	 * length cannot be longer than DMA_BUF_NAME_LEN, including NIL
+	 * char. Useful for accounting and debugging. Read/Write accesses
+	 * are protected by @name_lock
+	 *
+	 * See the IOCTLs DMA_BUF_SET_NAME or DMA_BUF_SET_NAME_A/B
 	 */
 	const char *name;
 
@@ -488,8 +483,6 @@ struct dma_buf_attach_ops {
  * @dmabuf: buffer for this attachment.
  * @dev: device attached to the buffer.
  * @node: list of dma_buf_attachment, protected by dma_resv lock of the dmabuf.
- * @sgt: cached mapping.
- * @dir: direction of cached mapping.
  * @peer2peer: true if the importer can handle peer resources without pages.
  * @priv: exporter specific attachment data.
  * @importer_ops: importer operations for this attachment, if provided
@@ -509,8 +502,6 @@ struct dma_buf_attachment {
 	struct dma_buf *dmabuf;
 	struct device *dev;
 	struct list_head node;
-	struct sg_table *sgt;
-	enum dma_data_direction dir;
 	bool peer2peer;
 	const struct dma_buf_attach_ops *importer_ops;
 	void *importer_priv;
@@ -541,6 +532,16 @@ struct dma_buf_export_info {
 };
 
 /**
+ * struct dma_buf_phys_vec - describe continuous chunk of memory
+ * @paddr:   physical address of that chunk
+ * @len:     Length of this chunk
+ */
+struct dma_buf_phys_vec {
+	phys_addr_t paddr;
+	size_t len;
+};
+
+/**
  * DEFINE_DMA_BUF_EXPORT_INFO - helper macro for exporters
  * @name: export-info name
  *
@@ -578,20 +579,6 @@ static inline bool dma_buf_is_dynamic(struct dma_buf *dmabuf)
 	return !!dmabuf->ops->pin;
 }
 
-/**
- * dma_buf_attachment_is_dynamic - check if a DMA-buf attachment uses dynamic
- * mappings
- * @attach: the DMA-buf attachment to check
- *
- * Returns true if a DMA-buf importer wants to call the map/unmap functions with
- * the dma_resv lock held.
- */
-static inline bool
-dma_buf_attachment_is_dynamic(struct dma_buf_attachment *attach)
-{
-	return !!attach->importer_ops;
-}
-
 struct dma_buf_attachment *dma_buf_attach(struct dma_buf *dmabuf,
 					  struct device *dev);
 struct dma_buf_attachment *
@@ -631,4 +618,6 @@ int dma_buf_vmap(struct dma_buf *dmabuf, struct iosys_map *map);
 void dma_buf_vunmap(struct dma_buf *dmabuf, struct iosys_map *map);
 int dma_buf_vmap_unlocked(struct dma_buf *dmabuf, struct iosys_map *map);
 void dma_buf_vunmap_unlocked(struct dma_buf *dmabuf, struct iosys_map *map);
+struct dma_buf *dma_buf_iter_begin(void);
+struct dma_buf *dma_buf_iter_next(struct dma_buf *dmbuf);
 #endif /* __DMA_BUF_H__ */
diff --git a/include/linux/dma-buf/heaps/cma.h b/include/linux/dma-buf/heaps/cma.h
new file mode 100644
index 000000000000..e751479e21e7
--- /dev/null
+++ b/include/linux/dma-buf/heaps/cma.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef DMA_BUF_HEAP_CMA_H_
+#define DMA_BUF_HEAP_CMA_H_
+
+struct cma;
+
+#ifdef CONFIG_DMABUF_HEAPS_CMA
+int dma_heap_cma_register_heap(struct cma *cma);
+#else
+static inline int dma_heap_cma_register_heap(struct cma *cma)
+{
+	return 0;
+}
+#endif // CONFIG_DMABUF_HEAPS_CMA
+
+#endif // DMA_BUF_HEAP_CMA_H_
diff --git a/include/linux/dma-direct.h b/include/linux/dma-direct.h
index 18aade195884..c249912456f9 100644
--- a/include/linux/dma-direct.h
+++ b/include/linux/dma-direct.h
@@ -12,7 +12,7 @@
 #include <linux/mem_encrypt.h>
 #include <linux/swiotlb.h>
 
-extern unsigned int zone_dma_bits;
+extern u64 zone_dma_limit;
 
 /*
  * Record the mapping of CPU physical to DMA addresses for a given region.
@@ -21,7 +21,6 @@ struct bus_dma_region {
 	phys_addr_t	cpu_start;
 	dma_addr_t	dma_start;
 	u64		size;
-	u64		offset;
 };
 
 static inline dma_addr_t translate_phys_to_dma(struct device *dev,
@@ -29,9 +28,12 @@ static inline dma_addr_t translate_phys_to_dma(struct device *dev,
 {
 	const struct bus_dma_region *m;
 
-	for (m = dev->dma_range_map; m->size; m++)
-		if (paddr >= m->cpu_start && paddr - m->cpu_start < m->size)
-			return (dma_addr_t)paddr - m->offset;
+	for (m = dev->dma_range_map; m->size; m++) {
+		u64 offset = paddr - m->cpu_start;
+
+		if (paddr >= m->cpu_start && offset < m->size)
+			return m->dma_start + offset;
+	}
 
 	/* make sure dma_capable fails when no translation is available */
 	return DMA_MAPPING_ERROR;
@@ -42,27 +44,52 @@ static inline phys_addr_t translate_dma_to_phys(struct device *dev,
 {
 	const struct bus_dma_region *m;
 
-	for (m = dev->dma_range_map; m->size; m++)
-		if (dma_addr >= m->dma_start && dma_addr - m->dma_start < m->size)
-			return (phys_addr_t)dma_addr + m->offset;
+	for (m = dev->dma_range_map; m->size; m++) {
+		u64 offset = dma_addr - m->dma_start;
+
+		if (dma_addr >= m->dma_start && offset < m->size)
+			return m->cpu_start + offset;
+	}
 
 	return (phys_addr_t)-1;
 }
 
+static inline dma_addr_t dma_range_map_min(const struct bus_dma_region *map)
+{
+	dma_addr_t ret = (dma_addr_t)U64_MAX;
+
+	for (; map->size; map++)
+		ret = min(ret, map->dma_start);
+	return ret;
+}
+
+static inline dma_addr_t dma_range_map_max(const struct bus_dma_region *map)
+{
+	dma_addr_t ret = 0;
+
+	for (; map->size; map++)
+		ret = max(ret, map->dma_start + map->size - 1);
+	return ret;
+}
+
 #ifdef CONFIG_ARCH_HAS_PHYS_TO_DMA
 #include <asm/dma-direct.h>
 #ifndef phys_to_dma_unencrypted
 #define phys_to_dma_unencrypted		phys_to_dma
 #endif
 #else
-static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
-		phys_addr_t paddr)
+static inline dma_addr_t __phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
 	if (dev->dma_range_map)
 		return translate_phys_to_dma(dev, paddr);
 	return paddr;
 }
 
+static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
+						phys_addr_t paddr)
+{
+	return dma_addr_unencrypted(__phys_to_dma(dev, paddr));
+}
 /*
  * If memory encryption is supported, phys_to_dma will set the memory encryption
  * bit in the DMA address, and dma_to_phys will clear it.
@@ -71,19 +98,20 @@ static inline dma_addr_t phys_to_dma_unencrypted(struct device *dev,
  */
 static inline dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr)
 {
-	return __sme_set(phys_to_dma_unencrypted(dev, paddr));
+	return dma_addr_encrypted(__phys_to_dma(dev, paddr));
 }
 
 static inline phys_addr_t dma_to_phys(struct device *dev, dma_addr_t dma_addr)
 {
 	phys_addr_t paddr;
 
+	dma_addr = dma_addr_canonical(dma_addr);
 	if (dev->dma_range_map)
 		paddr = translate_dma_to_phys(dev, dma_addr);
 	else
 		paddr = dma_addr;
 
-	return __sme_clr(paddr);
+	return paddr;
 }
 #endif /* !CONFIG_ARCH_HAS_PHYS_TO_DMA */
 
@@ -121,7 +149,5 @@ void dma_direct_free_pages(struct device *dev, size_t size,
 		struct page *page, dma_addr_t dma_addr,
 		enum dma_data_direction dir);
 int dma_direct_supported(struct device *dev, u64 mask);
-dma_addr_t dma_direct_map_resource(struct device *dev, phys_addr_t paddr,
-		size_t size, enum dma_data_direction dir, unsigned long attrs);
 
 #endif /* _LINUX_DMA_DIRECT_H */
diff --git a/include/linux/dma-fence-array.h b/include/linux/dma-fence-array.h
index ec7f25def392..079b3dec0a16 100644
--- a/include/linux/dma-fence-array.h
+++ b/include/linux/dma-fence-array.h
@@ -33,6 +33,7 @@ struct dma_fence_array_cb {
  * @num_pending: fences in the array still pending
  * @fences: array of the fences
  * @work: internal irq_work function
+ * @callbacks: array of callback helpers
  */
 struct dma_fence_array {
 	struct dma_fence base;
@@ -43,6 +44,8 @@ struct dma_fence_array {
 	struct dma_fence **fences;
 
 	struct irq_work work;
+
+	struct dma_fence_array_cb callbacks[] __counted_by(num_fences);
 };
 
 /**
@@ -76,6 +79,12 @@ to_dma_fence_array(struct dma_fence *fence)
 	for (index = 0, fence = dma_fence_array_first(head); fence;	\
 	     ++(index), fence = dma_fence_array_next(head, index))
 
+struct dma_fence_array *dma_fence_array_alloc(int num_fences);
+void dma_fence_array_init(struct dma_fence_array *array,
+			  int num_fences, struct dma_fence **fences,
+			  u64 context, unsigned seqno,
+			  bool signal_on_any);
+
 struct dma_fence_array *dma_fence_array_create(int num_fences,
 					       struct dma_fence **fences,
 					       u64 context, unsigned seqno,
diff --git a/include/linux/dma-fence-chain.h b/include/linux/dma-fence-chain.h
index 4bdf0b96da28..68c3c1e41014 100644
--- a/include/linux/dma-fence-chain.h
+++ b/include/linux/dma-fence-chain.h
@@ -85,11 +85,13 @@ dma_fence_chain_contained(struct dma_fence *fence)
  * dma_fence_chain_alloc
  *
  * Returns a new struct dma_fence_chain object or NULL on failure.
+ *
+ * This specialized allocator has to be a macro for its allocations to be
+ * accounted separately (to have a separate alloc_tag). The typecast is
+ * intentional to enforce typesafety.
  */
-static inline struct dma_fence_chain *dma_fence_chain_alloc(void)
-{
-	return kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL);
-};
+#define dma_fence_chain_alloc()	\
+		((struct dma_fence_chain *)kmalloc(sizeof(struct dma_fence_chain), GFP_KERNEL))
 
 /**
  * dma_fence_chain_free
diff --git a/include/linux/dma-fence-unwrap.h b/include/linux/dma-fence-unwrap.h
index 66b1e56fbb81..62df222fe0f1 100644
--- a/include/linux/dma-fence-unwrap.h
+++ b/include/linux/dma-fence-unwrap.h
@@ -52,6 +52,8 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences,
 					   struct dma_fence **fences,
 					   struct dma_fence_unwrap *cursors);
 
+int dma_fence_dedup_array(struct dma_fence **array, int num_fences);
+
 /**
  * dma_fence_unwrap_merge - unwrap and merge fences
  *
diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h
index d54b595a0fe0..64639e104110 100644
--- a/include/linux/dma-fence.h
+++ b/include/linux/dma-fence.h
@@ -21,10 +21,12 @@
 #include <linux/sched.h>
 #include <linux/printk.h>
 #include <linux/rcupdate.h>
+#include <linux/timekeeping.h>
 
 struct dma_fence;
 struct dma_fence_ops;
 struct dma_fence_cb;
+struct seq_file;
 
 /**
  * struct dma_fence - software synchronization primitive
@@ -96,6 +98,7 @@ struct dma_fence {
 };
 
 enum dma_fence_flag_bits {
+	DMA_FENCE_FLAG_SEQNO64_BIT,
 	DMA_FENCE_FLAG_SIGNALED_BIT,
 	DMA_FENCE_FLAG_TIMESTAMP_BIT,
 	DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
@@ -124,14 +127,6 @@ struct dma_fence_cb {
  */
 struct dma_fence_ops {
 	/**
-	 * @use_64bit_seqno:
-	 *
-	 * True if this dma_fence implementation uses 64bit seqno, false
-	 * otherwise.
-	 */
-	bool use_64bit_seqno;
-
-	/**
 	 * @get_driver_name:
 	 *
 	 * Returns the driver name. This is a callback to allow drivers to
@@ -168,8 +163,8 @@ struct dma_fence_ops {
 	 * implementation know that there is another driver waiting on the
 	 * signal (ie. hw->sw case).
 	 *
-	 * This function can be called from atomic context, but not
-	 * from irq context, so normal spinlocks can be used.
+	 * This is called with irq's disabled, so only spinlocks which disable
+	 * IRQ's can be used in the code outside of this callback.
 	 *
 	 * A return value of false indicates the fence already passed,
 	 * or some failure occurred that made it impossible to enable
@@ -238,27 +233,6 @@ struct dma_fence_ops {
 	void (*release)(struct dma_fence *fence);
 
 	/**
-	 * @fence_value_str:
-	 *
-	 * Callback to fill in free-form debug info specific to this fence, like
-	 * the sequence number.
-	 *
-	 * This callback is optional.
-	 */
-	void (*fence_value_str)(struct dma_fence *fence, char *str, int size);
-
-	/**
-	 * @timeline_value_str:
-	 *
-	 * Fills in the current value of the timeline as a string, like the
-	 * sequence number. Note that the specific fence passed to this function
-	 * should not matter, drivers should only use it to look up the
-	 * corresponding timeline structures.
-	 */
-	void (*timeline_value_str)(struct dma_fence *fence,
-				   char *str, int size);
-
-	/**
 	 * @set_deadline:
 	 *
 	 * Callback to allow a fence waiter to inform the fence signaler of
@@ -282,6 +256,9 @@ struct dma_fence_ops {
 void dma_fence_init(struct dma_fence *fence, const struct dma_fence_ops *ops,
 		    spinlock_t *lock, u64 context, u64 seqno);
 
+void dma_fence_init64(struct dma_fence *fence, const struct dma_fence_ops *ops,
+		      spinlock_t *lock, u64 context, u64 seqno);
+
 void dma_fence_release(struct kref *kref);
 void dma_fence_free(struct dma_fence *fence);
 void dma_fence_describe(struct dma_fence *fence, struct seq_file *seq);
@@ -402,6 +379,29 @@ bool dma_fence_remove_callback(struct dma_fence *fence,
 void dma_fence_enable_sw_signaling(struct dma_fence *fence);
 
 /**
+ * DOC: Safe external access to driver provided object members
+ *
+ * All data not stored directly in the dma-fence object, such as the
+ * &dma_fence.lock and memory potentially accessed by functions in the
+ * &dma_fence.ops table, MUST NOT be accessed after the fence has been signalled
+ * because after that point drivers are allowed to free it.
+ *
+ * All code accessing that data via the dma-fence API (or directly, which is
+ * discouraged), MUST make sure to contain the complete access within a
+ * &rcu_read_lock and &rcu_read_unlock pair.
+ *
+ * Some dma-fence API handles this automatically, while other, as for example
+ * &dma_fence_driver_name and &dma_fence_timeline_name, leave that
+ * responsibility to the caller.
+ *
+ * To enable this scheme to work drivers MUST ensure a RCU grace period elapses
+ * between signalling the fence and freeing the said data.
+ *
+ */
+const char __rcu *dma_fence_driver_name(struct dma_fence *fence);
+const char __rcu *dma_fence_timeline_name(struct dma_fence *fence);
+
+/**
  * dma_fence_is_signaled_locked - Return an indication if the fence
  *                                is signaled yet.
  * @fence: the fence to check
@@ -461,21 +461,20 @@ dma_fence_is_signaled(struct dma_fence *fence)
 
 /**
  * __dma_fence_is_later - return if f1 is chronologically later than f2
+ * @fence: fence in whose context to do the comparison
  * @f1: the first fence's seqno
  * @f2: the second fence's seqno from the same context
- * @ops: dma_fence_ops associated with the seqno
  *
  * Returns true if f1 is chronologically later than f2. Both fences must be
  * from the same context, since a seqno is not common across contexts.
  */
-static inline bool __dma_fence_is_later(u64 f1, u64 f2,
-					const struct dma_fence_ops *ops)
+static inline bool __dma_fence_is_later(struct dma_fence *fence, u64 f1, u64 f2)
 {
 	/* This is for backward compatibility with drivers which can only handle
 	 * 32bit sequence numbers. Use a 64bit compare when the driver says to
 	 * do so.
 	 */
-	if (ops->use_64bit_seqno)
+	if (test_bit(DMA_FENCE_FLAG_SEQNO64_BIT, &fence->flags))
 		return f1 > f2;
 
 	return (int)(lower_32_bits(f1) - lower_32_bits(f2)) > 0;
@@ -495,7 +494,22 @@ static inline bool dma_fence_is_later(struct dma_fence *f1,
 	if (WARN_ON(f1->context != f2->context))
 		return false;
 
-	return __dma_fence_is_later(f1->seqno, f2->seqno, f1->ops);
+	return __dma_fence_is_later(f1, f1->seqno, f2->seqno);
+}
+
+/**
+ * dma_fence_is_later_or_same - return true if f1 is later or same as f2
+ * @f1: the first fence from the same context
+ * @f2: the second fence from the same context
+ *
+ * Returns true if f1 is chronologically later than f2 or the same fence. Both
+ * fences must be from the same context, since a seqno is not re-used across
+ * contexts.
+ */
+static inline bool dma_fence_is_later_or_same(struct dma_fence *f1,
+					      struct dma_fence *f2)
+{
+	return f1 == f2 || dma_fence_is_later(f1, f2);
 }
 
 /**
@@ -558,6 +572,12 @@ int dma_fence_get_status(struct dma_fence *fence);
  * rather than success. This must be set before signaling (so that the value
  * is visible before any waiters on the signal callback are woken). This
  * helper exists to help catching erroneous setting of #dma_fence.error.
+ *
+ * Examples of error codes which drivers should use:
+ *
+ * * %-ENODATA	 This operation produced no data, no other operation affected.
+ * * %-ECANCELED All operations from the same context have been canceled.
+ * * %-ETIME	 Operation caused a timeout and potentially device reset.
  */
 static inline void dma_fence_set_error(struct dma_fence *fence,
 				       int error)
@@ -568,6 +588,25 @@ static inline void dma_fence_set_error(struct dma_fence *fence,
 	fence->error = error;
 }
 
+/**
+ * dma_fence_timestamp - helper to get the completion timestamp of a fence
+ * @fence: fence to get the timestamp from.
+ *
+ * After a fence is signaled the timestamp is updated with the signaling time,
+ * but setting the timestamp can race with tasks waiting for the signaling. This
+ * helper busy waits for the correct timestamp to appear.
+ */
+static inline ktime_t dma_fence_timestamp(struct dma_fence *fence)
+{
+	if (WARN_ON(!test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags)))
+		return ktime_get();
+
+	while (!test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, &fence->flags))
+		cpu_relax();
+
+	return fence->timestamp;
+}
+
 signed long dma_fence_wait_timeout(struct dma_fence *,
 				   bool intr, signed long timeout);
 signed long dma_fence_wait_any_timeout(struct dma_fence **fences,
@@ -606,7 +645,7 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr)
 void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline);
 
 struct dma_fence *dma_fence_get_stub(void);
-struct dma_fence *dma_fence_allocate_private_stub(void);
+struct dma_fence *dma_fence_allocate_private_stub(ktime_t timestamp);
 u64 dma_fence_context_alloc(unsigned num);
 
 extern const struct dma_fence_ops dma_fence_array_ops;
diff --git a/include/linux/dma-heap.h b/include/linux/dma-heap.h
index 0c05561cad6e..27d15f60950a 100644
--- a/include/linux/dma-heap.h
+++ b/include/linux/dma-heap.h
@@ -9,22 +9,21 @@
 #ifndef _DMA_HEAPS_H
 #define _DMA_HEAPS_H
 
-#include <linux/cdev.h>
 #include <linux/types.h>
 
 struct dma_heap;
 
 /**
  * struct dma_heap_ops - ops to operate on a given heap
- * @allocate:		allocate dmabuf and return struct dma_buf ptr
+ * @allocate:	allocate dmabuf and return struct dma_buf ptr
  *
  * allocate returns dmabuf on success, ERR_PTR(-errno) on error.
  */
 struct dma_heap_ops {
 	struct dma_buf *(*allocate)(struct dma_heap *heap,
 				    unsigned long len,
-				    unsigned long fd_flags,
-				    unsigned long heap_flags);
+				    u32 fd_flags,
+				    u64 heap_flags);
 };
 
 /**
@@ -41,28 +40,10 @@ struct dma_heap_export_info {
 	void *priv;
 };
 
-/**
- * dma_heap_get_drvdata() - get per-heap driver data
- * @heap: DMA-Heap to retrieve private data for
- *
- * Returns:
- * The per-heap data for the heap.
- */
 void *dma_heap_get_drvdata(struct dma_heap *heap);
 
-/**
- * dma_heap_get_name() - get heap name
- * @heap: DMA-Heap to retrieve private data for
- *
- * Returns:
- * The char* for the heap name.
- */
 const char *dma_heap_get_name(struct dma_heap *heap);
 
-/**
- * dma_heap_add - adds a heap to dmabuf heaps
- * @exp_info:		information needed to register this heap
- */
 struct dma_heap *dma_heap_add(const struct dma_heap_export_info *exp_info);
 
 #endif /* _DMA_HEAPS_H */
diff --git a/include/linux/dma-map-ops.h b/include/linux/dma-map-ops.h
index 31f114f486c4..4809204c674c 100644
--- a/include/linux/dma-map-ops.h
+++ b/include/linux/dma-map-ops.h
@@ -8,35 +8,22 @@
 
 #include <linux/dma-mapping.h>
 #include <linux/pgtable.h>
+#include <linux/slab.h>
 
 struct cma;
-
-/*
- * Values for struct dma_map_ops.flags:
- *
- * DMA_F_PCI_P2PDMA_SUPPORTED: Indicates the dma_map_ops implementation can
- * handle PCI P2PDMA pages in the map_sg/unmap_sg operation.
- */
-#define DMA_F_PCI_P2PDMA_SUPPORTED     (1 << 0)
+struct iommu_ops;
 
 struct dma_map_ops {
-	unsigned int flags;
-
 	void *(*alloc)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, gfp_t gfp,
 			unsigned long attrs);
 	void (*free)(struct device *dev, size_t size, void *vaddr,
 			dma_addr_t dma_handle, unsigned long attrs);
-	struct page *(*alloc_pages)(struct device *dev, size_t size,
+	struct page *(*alloc_pages_op)(struct device *dev, size_t size,
 			dma_addr_t *dma_handle, enum dma_data_direction dir,
 			gfp_t gfp);
 	void (*free_pages)(struct device *dev, size_t size, struct page *vaddr,
 			dma_addr_t dma_handle, enum dma_data_direction dir);
-	struct sg_table *(*alloc_noncontiguous)(struct device *dev, size_t size,
-			enum dma_data_direction dir, gfp_t gfp,
-			unsigned long attrs);
-	void (*free_noncontiguous)(struct device *dev, size_t size,
-			struct sg_table *sgt, enum dma_data_direction dir);
 	int (*mmap)(struct device *, struct vm_area_struct *,
 			void *, dma_addr_t, size_t, unsigned long attrs);
 
@@ -44,10 +31,10 @@ struct dma_map_ops {
 			void *cpu_addr, dma_addr_t dma_addr, size_t size,
 			unsigned long attrs);
 
-	dma_addr_t (*map_page)(struct device *dev, struct page *page,
-			unsigned long offset, size_t size,
-			enum dma_data_direction dir, unsigned long attrs);
-	void (*unmap_page)(struct device *dev, dma_addr_t dma_handle,
+	dma_addr_t (*map_phys)(struct device *dev, phys_addr_t phys,
+			size_t size, enum dma_data_direction dir,
+			unsigned long attrs);
+	void (*unmap_phys)(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir,
 			unsigned long attrs);
 	/*
@@ -59,12 +46,6 @@ struct dma_map_ops {
 			enum dma_data_direction dir, unsigned long attrs);
 	void (*unmap_sg)(struct device *dev, struct scatterlist *sg, int nents,
 			enum dma_data_direction dir, unsigned long attrs);
-	dma_addr_t (*map_resource)(struct device *dev, phys_addr_t phys_addr,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs);
-	void (*unmap_resource)(struct device *dev, dma_addr_t dma_handle,
-			size_t size, enum dma_data_direction dir,
-			unsigned long attrs);
 	void (*sync_single_for_cpu)(struct device *dev, dma_addr_t dma_handle,
 			size_t size, enum dma_data_direction dir);
 	void (*sync_single_for_device)(struct device *dev,
@@ -83,7 +64,7 @@ struct dma_map_ops {
 	unsigned long (*get_merge_boundary)(struct device *dev);
 };
 
-#ifdef CONFIG_DMA_OPS
+#ifdef CONFIG_ARCH_HAS_DMA_OPS
 #include <asm/dma-mapping.h>
 
 static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
@@ -98,7 +79,7 @@ static inline void set_dma_ops(struct device *dev,
 {
 	dev->dma_ops = dma_ops;
 }
-#else /* CONFIG_DMA_OPS */
+#else /* CONFIG_ARCH_HAS_DMA_OPS */
 static inline const struct dma_map_ops *get_dma_ops(struct device *dev)
 {
 	return NULL;
@@ -107,7 +88,7 @@ static inline void set_dma_ops(struct device *dev,
 			       const struct dma_map_ops *dma_ops)
 {
 }
-#endif /* CONFIG_DMA_OPS */
+#endif /* CONFIG_ARCH_HAS_DMA_OPS */
 
 #ifdef CONFIG_DMA_CMA
 extern struct cma *dma_contiguous_default_area;
@@ -166,14 +147,11 @@ static inline void dma_free_contiguous(struct device *dev, struct page *page,
 {
 	__free_pages(page, get_order(size));
 }
+static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size)
+{
+}
 #endif /* CONFIG_DMA_CMA*/
 
-#ifdef CONFIG_DMA_PERNUMA_CMA
-void dma_pernuma_cma_reserve(void);
-#else
-static inline void dma_pernuma_cma_reserve(void) { }
-#endif /* CONFIG_DMA_PERNUMA_CMA */
-
 #ifdef CONFIG_DMA_DECLARE_COHERENT
 int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
 		dma_addr_t device_addr, size_t size);
@@ -220,20 +198,6 @@ static inline int dma_mmap_from_global_coherent(struct vm_area_struct *vma,
 }
 #endif /* CONFIG_DMA_GLOBAL_POOL */
 
-/*
- * This is the actual return value from the ->alloc_noncontiguous method.
- * The users of the DMA API should only care about the sg_table, but to make
- * the DMA-API internal vmaping and freeing easier we stash away the page
- * array as well (except for the fallback case).  This can go away any time,
- * e.g. when a vmap-variant that takes a scatterlist comes along.
- */
-struct dma_sgt_handle {
-	struct sg_table sgt;
-	struct page **pages;
-};
-#define sgt_handle(sgt) \
-	container_of((sgt), struct dma_sgt_handle, sgt)
-
 int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
 		void *cpu_addr, dma_addr_t dma_addr, size_t size,
 		unsigned long attrs);
@@ -275,13 +239,88 @@ static inline bool dev_is_dma_coherent(struct device *dev)
 {
 	return true;
 }
-#endif /* CONFIG_ARCH_HAS_DMA_COHERENCE_H */
+#endif
+
+static inline void dma_reset_need_sync(struct device *dev)
+{
+#ifdef CONFIG_DMA_NEED_SYNC
+	/* Reset it only once so that the function can be called on hotpath */
+	if (unlikely(dev->dma_skip_sync))
+		dev->dma_skip_sync = false;
+#endif
+}
+
+/*
+ * Check whether potential kmalloc() buffers are safe for non-coherent DMA.
+ */
+static inline bool dma_kmalloc_safe(struct device *dev,
+				    enum dma_data_direction dir)
+{
+	/*
+	 * If DMA bouncing of kmalloc() buffers is disabled, the kmalloc()
+	 * caches have already been aligned to a DMA-safe size.
+	 */
+	if (!IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC))
+		return true;
+
+	/*
+	 * kmalloc() buffers are DMA-safe irrespective of size if the device
+	 * is coherent or the direction is DMA_TO_DEVICE (non-desctructive
+	 * cache maintenance and benign cache line evictions).
+	 */
+	if (dev_is_dma_coherent(dev) || dir == DMA_TO_DEVICE)
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether the given size, assuming it is for a kmalloc()'ed buffer, is
+ * sufficiently aligned for non-coherent DMA.
+ */
+static inline bool dma_kmalloc_size_aligned(size_t size)
+{
+	/*
+	 * Larger kmalloc() sizes are guaranteed to be aligned to
+	 * ARCH_DMA_MINALIGN.
+	 */
+	if (size >= 2 * ARCH_DMA_MINALIGN ||
+	    IS_ALIGNED(kmalloc_size_roundup(size), dma_get_cache_alignment()))
+		return true;
+
+	return false;
+}
+
+/*
+ * Check whether the given object size may have originated from a kmalloc()
+ * buffer with a slab alignment below the DMA-safe alignment and needs
+ * bouncing for non-coherent DMA. The pointer alignment is not considered and
+ * in-structure DMA-safe offsets are the responsibility of the caller. Such
+ * code should use the static ARCH_DMA_MINALIGN for compiler annotations.
+ *
+ * The heuristics can have false positives, bouncing unnecessarily, though the
+ * buffers would be small. False negatives are theoretically possible if, for
+ * example, multiple small kmalloc() buffers are coalesced into a larger
+ * buffer that passes the alignment check. There are no such known constructs
+ * in the kernel.
+ */
+static inline bool dma_kmalloc_needs_bounce(struct device *dev, size_t size,
+					    enum dma_data_direction dir)
+{
+	return !dma_kmalloc_safe(dev, dir) && !dma_kmalloc_size_aligned(size);
+}
 
 void *arch_dma_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t gfp, unsigned long attrs);
 void arch_dma_free(struct device *dev, size_t size, void *cpu_addr,
 		dma_addr_t dma_addr, unsigned long attrs);
 
+#ifdef CONFIG_ARCH_HAS_DMA_SET_MASK
+void arch_dma_set_mask(struct device *dev, u64 mask);
+#else
+#define arch_dma_set_mask(dev, mask)	do { } while (0)
+#endif
+
 #ifdef CONFIG_MMU
 /*
  * Page protection so that devices that can't snoop CPU caches can use the
@@ -350,25 +389,23 @@ void *arch_dma_set_uncached(void *addr, size_t size);
 void arch_dma_clear_uncached(void *addr, size_t size);
 
 #ifdef CONFIG_ARCH_HAS_DMA_MAP_DIRECT
-bool arch_dma_map_page_direct(struct device *dev, phys_addr_t addr);
-bool arch_dma_unmap_page_direct(struct device *dev, dma_addr_t dma_handle);
+bool arch_dma_map_phys_direct(struct device *dev, phys_addr_t addr);
+bool arch_dma_unmap_phys_direct(struct device *dev, dma_addr_t dma_handle);
 bool arch_dma_map_sg_direct(struct device *dev, struct scatterlist *sg,
 		int nents);
 bool arch_dma_unmap_sg_direct(struct device *dev, struct scatterlist *sg,
 		int nents);
 #else
-#define arch_dma_map_page_direct(d, a)		(false)
-#define arch_dma_unmap_page_direct(d, a)	(false)
+#define arch_dma_map_phys_direct(d, a)		(false)
+#define arch_dma_unmap_phys_direct(d, a)	(false)
 #define arch_dma_map_sg_direct(d, s, n)		(false)
 #define arch_dma_unmap_sg_direct(d, s, n)	(false)
 #endif
 
 #ifdef CONFIG_ARCH_HAS_SETUP_DMA_OPS
-void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
-		const struct iommu_ops *iommu, bool coherent);
+void arch_setup_dma_ops(struct device *dev, bool coherent);
 #else
-static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base,
-		u64 size, const struct iommu_ops *iommu, bool coherent)
+static inline void arch_setup_dma_ops(struct device *dev, bool coherent)
 {
 }
 #endif /* CONFIG_ARCH_HAS_SETUP_DMA_OPS */
@@ -382,10 +419,10 @@ static inline void arch_teardown_dma_ops(struct device *dev)
 #endif /* CONFIG_ARCH_HAS_TEARDOWN_DMA_OPS */
 
 #ifdef CONFIG_DMA_API_DEBUG
-void dma_debug_add_bus(struct bus_type *bus);
+void dma_debug_add_bus(const struct bus_type *bus);
 void debug_dma_dump_mappings(struct device *dev);
 #else
-static inline void dma_debug_add_bus(struct bus_type *bus)
+static inline void dma_debug_add_bus(const struct bus_type *bus)
 {
 }
 static inline void debug_dma_dump_mappings(struct device *dev)
@@ -394,58 +431,4 @@ static inline void debug_dma_dump_mappings(struct device *dev)
 #endif /* CONFIG_DMA_API_DEBUG */
 
 extern const struct dma_map_ops dma_dummy_ops;
-
-enum pci_p2pdma_map_type {
-	/*
-	 * PCI_P2PDMA_MAP_UNKNOWN: Used internally for indicating the mapping
-	 * type hasn't been calculated yet. Functions that return this enum
-	 * never return this value.
-	 */
-	PCI_P2PDMA_MAP_UNKNOWN = 0,
-
-	/*
-	 * PCI_P2PDMA_MAP_NOT_SUPPORTED: Indicates the transaction will
-	 * traverse the host bridge and the host bridge is not in the
-	 * allowlist. DMA Mapping routines should return an error when
-	 * this is returned.
-	 */
-	PCI_P2PDMA_MAP_NOT_SUPPORTED,
-
-	/*
-	 * PCI_P2PDMA_BUS_ADDR: Indicates that two devices can talk to
-	 * each other directly through a PCI switch and the transaction will
-	 * not traverse the host bridge. Such a mapping should program
-	 * the DMA engine with PCI bus addresses.
-	 */
-	PCI_P2PDMA_MAP_BUS_ADDR,
-
-	/*
-	 * PCI_P2PDMA_MAP_THRU_HOST_BRIDGE: Indicates two devices can talk
-	 * to each other, but the transaction traverses a host bridge on the
-	 * allowlist. In this case, a normal mapping either with CPU physical
-	 * addresses (in the case of dma-direct) or IOVA addresses (in the
-	 * case of IOMMUs) should be used to program the DMA engine.
-	 */
-	PCI_P2PDMA_MAP_THRU_HOST_BRIDGE,
-};
-
-struct pci_p2pdma_map_state {
-	struct dev_pagemap *pgmap;
-	int map;
-	u64 bus_off;
-};
-
-#ifdef CONFIG_PCI_P2PDMA
-enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg);
-#else /* CONFIG_PCI_P2PDMA */
-static inline enum pci_p2pdma_map_type
-pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev,
-		       struct scatterlist *sg)
-{
-	return PCI_P2PDMA_MAP_NOT_SUPPORTED;
-}
-#endif /* CONFIG_PCI_P2PDMA */
-
 #endif /* _LINUX_DMA_MAP_OPS_H */
diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h
index 0ee20b764000..2ceda49c609f 100644
--- a/include/linux/dma-mapping.h
+++ b/include/linux/dma-mapping.h
@@ -2,14 +2,11 @@
 #ifndef _LINUX_DMA_MAPPING_H
 #define _LINUX_DMA_MAPPING_H
 
-#include <linux/sizes.h>
-#include <linux/string.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/dma-direction.h>
 #include <linux/scatterlist.h>
 #include <linux/bug.h>
-#include <linux/mem_encrypt.h>
 
 /**
  * List of possible attributes associated with a DMA mapping. The semantics
@@ -62,6 +59,26 @@
 #define DMA_ATTR_PRIVILEGED		(1UL << 9)
 
 /*
+ * DMA_ATTR_MMIO - Indicates memory-mapped I/O (MMIO) region for DMA mapping
+ *
+ * This attribute indicates the physical address is not normal system
+ * memory. It may not be used with kmap*()/phys_to_virt()/phys_to_page()
+ * functions, it may not be cacheable, and access using CPU load/store
+ * instructions may not be allowed.
+ *
+ * Usually this will be used to describe MMIO addresses, or other non-cacheable
+ * register addresses. When DMA mapping this sort of address we call
+ * the operation Peer to Peer as a one device is DMA'ing to another device.
+ * For PCI devices the p2pdma APIs must be used to determine if DMA_ATTR_MMIO
+ * is appropriate.
+ *
+ * For architectures that require cache flushing for DMA coherence
+ * DMA_ATTR_MMIO will not perform any cache flushing. The address
+ * provided must never be mapped cacheable into the CPU.
+ */
+#define DMA_ATTR_MMIO		(1UL << 10)
+
+/*
  * A dma_addr_t can hold any valid DMA or bus address for the platform.  It can
  * be given to a device to use as a DMA source or target.  It is specific to a
  * given device and there may be a translation between the CPU physical address
@@ -73,7 +90,23 @@
  */
 #define DMA_MAPPING_ERROR		(~(dma_addr_t)0)
 
-#define DMA_BIT_MASK(n)	(((n) == 64) ? ~0ULL : ((1ULL<<(n))-1))
+#define DMA_BIT_MASK(n)	GENMASK_ULL(n - 1, 0)
+
+struct dma_iova_state {
+	dma_addr_t addr;
+	u64 __size;
+};
+
+/*
+ * Use the high bit to mark if we used swiotlb for one or more ranges.
+ */
+#define DMA_IOVA_USE_SWIOTLB		(1ULL << 63)
+
+static inline size_t dma_iova_size(struct dma_iova_state *state)
+{
+	/* Casting is needed for 32-bits systems */
+	return (size_t)(state->__size & ~DMA_IOVA_USE_SWIOTLB);
+}
 
 #ifdef CONFIG_DMA_API_DEBUG
 void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr);
@@ -105,6 +138,10 @@ dma_addr_t dma_map_page_attrs(struct device *dev, struct page *page,
 		unsigned long attrs);
 void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs);
+dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_unmap_phys(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
 unsigned int dma_map_sg_attrs(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs);
 void dma_unmap_sg_attrs(struct device *dev, struct scatterlist *sg,
@@ -116,14 +153,6 @@ dma_addr_t dma_map_resource(struct device *dev, phys_addr_t phys_addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs);
 void dma_unmap_resource(struct device *dev, dma_addr_t addr, size_t size,
 		enum dma_data_direction dir, unsigned long attrs);
-void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
-		enum dma_data_direction dir);
-void dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir);
-void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-		    int nelems, enum dma_data_direction dir);
-void dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
-		       int nelems, enum dma_data_direction dir);
 void *dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
 		gfp_t flag, unsigned long attrs);
 void dma_free_attrs(struct device *dev, size_t size, void *cpu_addr,
@@ -143,9 +172,9 @@ bool dma_pci_p2pdma_supported(struct device *dev);
 int dma_set_mask(struct device *dev, u64 mask);
 int dma_set_coherent_mask(struct device *dev, u64 mask);
 u64 dma_get_required_mask(struct device *dev);
+bool dma_addressing_limited(struct device *dev);
 size_t dma_max_mapping_size(struct device *dev);
 size_t dma_opt_mapping_size(struct device *dev);
-bool dma_need_sync(struct device *dev, dma_addr_t dma_addr);
 unsigned long dma_get_merge_boundary(struct device *dev);
 struct sg_table *dma_alloc_noncontiguous(struct device *dev, size_t size,
 		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
@@ -167,6 +196,15 @@ static inline void dma_unmap_page_attrs(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 }
+static inline dma_addr_t dma_map_phys(struct device *dev, phys_addr_t phys,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return DMA_MAPPING_ERROR;
+}
+static inline void dma_unmap_phys(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+}
 static inline unsigned int dma_map_sg_attrs(struct device *dev,
 		struct scatterlist *sg, int nents, enum dma_data_direction dir,
 		unsigned long attrs)
@@ -193,22 +231,6 @@ static inline void dma_unmap_resource(struct device *dev, dma_addr_t addr,
 		size_t size, enum dma_data_direction dir, unsigned long attrs)
 {
 }
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
-		size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_sync_single_for_device(struct device *dev,
-		dma_addr_t addr, size_t size, enum dma_data_direction dir)
-{
-}
-static inline void dma_sync_sg_for_cpu(struct device *dev,
-		struct scatterlist *sg, int nelems, enum dma_data_direction dir)
-{
-}
-static inline void dma_sync_sg_for_device(struct device *dev,
-		struct scatterlist *sg, int nelems, enum dma_data_direction dir)
-{
-}
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
 	return -ENOMEM;
@@ -263,6 +285,10 @@ static inline u64 dma_get_required_mask(struct device *dev)
 {
 	return 0;
 }
+static inline bool dma_addressing_limited(struct device *dev)
+{
+	return false;
+}
 static inline size_t dma_max_mapping_size(struct device *dev)
 {
 	return 0;
@@ -271,10 +297,6 @@ static inline size_t dma_opt_mapping_size(struct device *dev)
 {
 	return 0;
 }
-static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
-{
-	return false;
-}
 static inline unsigned long dma_get_merge_boundary(struct device *dev)
 {
 	return 0;
@@ -304,6 +326,151 @@ static inline int dma_mmap_noncontiguous(struct device *dev,
 }
 #endif /* CONFIG_HAS_DMA */
 
+#ifdef CONFIG_IOMMU_DMA
+/**
+ * dma_use_iova - check if the IOVA API is used for this state
+ * @state: IOVA state
+ *
+ * Return %true if the DMA transfers uses the dma_iova_*() calls or %false if
+ * they can't be used.
+ */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return state->__size != 0;
+}
+
+bool dma_iova_try_alloc(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t size);
+void dma_iova_free(struct device *dev, struct dma_iova_state *state);
+void dma_iova_destroy(struct device *dev, struct dma_iova_state *state,
+		size_t mapped_len, enum dma_data_direction dir,
+		unsigned long attrs);
+int dma_iova_sync(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size);
+int dma_iova_link(struct device *dev, struct dma_iova_state *state,
+		phys_addr_t phys, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void dma_iova_unlink(struct device *dev, struct dma_iova_state *state,
+		size_t offset, size_t size, enum dma_data_direction dir,
+		unsigned long attrs);
+#else /* CONFIG_IOMMU_DMA */
+static inline bool dma_use_iova(struct dma_iova_state *state)
+{
+	return false;
+}
+static inline bool dma_iova_try_alloc(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t size)
+{
+	return false;
+}
+static inline void dma_iova_free(struct device *dev,
+		struct dma_iova_state *state)
+{
+}
+static inline void dma_iova_destroy(struct device *dev,
+		struct dma_iova_state *state, size_t mapped_len,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+}
+static inline int dma_iova_sync(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size)
+{
+	return -EOPNOTSUPP;
+}
+static inline int dma_iova_link(struct device *dev,
+		struct dma_iova_state *state, phys_addr_t phys, size_t offset,
+		size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+	return -EOPNOTSUPP;
+}
+static inline void dma_iova_unlink(struct device *dev,
+		struct dma_iova_state *state, size_t offset, size_t size,
+		enum dma_data_direction dir, unsigned long attrs)
+{
+}
+#endif /* CONFIG_IOMMU_DMA */
+
+#if defined(CONFIG_HAS_DMA) && defined(CONFIG_DMA_NEED_SYNC)
+void __dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr, size_t size,
+		enum dma_data_direction dir);
+void __dma_sync_single_for_device(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir);
+void __dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+		int nelems, enum dma_data_direction dir);
+void __dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+		int nelems, enum dma_data_direction dir);
+bool __dma_need_sync(struct device *dev, dma_addr_t dma_addr);
+
+static inline bool dma_dev_need_sync(const struct device *dev)
+{
+	/* Always call DMA sync operations when debugging is enabled */
+	return !dev->dma_skip_sync || IS_ENABLED(CONFIG_DMA_API_DEBUG);
+}
+
+static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
+{
+	if (dma_dev_need_sync(dev))
+		__dma_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static inline void dma_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+	if (dma_dev_need_sync(dev))
+		__dma_sync_single_for_device(dev, addr, size, dir);
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sg, int nelems, enum dma_data_direction dir)
+{
+	if (dma_dev_need_sync(dev))
+		__dma_sync_sg_for_cpu(dev, sg, nelems, dir);
+}
+
+static inline void dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg, int nelems, enum dma_data_direction dir)
+{
+	if (dma_dev_need_sync(dev))
+		__dma_sync_sg_for_device(dev, sg, nelems, dir);
+}
+
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return dma_dev_need_sync(dev) ? __dma_need_sync(dev, dma_addr) : false;
+}
+bool dma_need_unmap(struct device *dev);
+#else /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
+static inline bool dma_dev_need_sync(const struct device *dev)
+{
+	return false;
+}
+static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
+		size_t size, enum dma_data_direction dir)
+{
+}
+static inline void dma_sync_single_for_device(struct device *dev,
+		dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+}
+static inline void dma_sync_sg_for_cpu(struct device *dev,
+		struct scatterlist *sg, int nelems, enum dma_data_direction dir)
+{
+}
+static inline void dma_sync_sg_for_device(struct device *dev,
+		struct scatterlist *sg, int nelems, enum dma_data_direction dir)
+{
+}
+static inline bool dma_need_sync(struct device *dev, dma_addr_t dma_addr)
+{
+	return false;
+}
+static inline bool dma_need_unmap(struct device *dev)
+{
+	return false;
+}
+#endif /* !CONFIG_HAS_DMA || !CONFIG_DMA_NEED_SYNC */
+
 struct page *dma_alloc_pages(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, enum dma_data_direction dir, gfp_t gfp);
 void dma_free_pages(struct device *dev, size_t size, struct page *page,
@@ -417,6 +584,8 @@ static inline void dma_sync_sgtable_for_device(struct device *dev,
 #define dma_get_sgtable(d, t, v, h, s) dma_get_sgtable_attrs(d, t, v, h, s, 0)
 #define dma_mmap_coherent(d, v, c, h, s) dma_mmap_attrs(d, v, c, h, s, 0)
 
+bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size);
+
 static inline void *dma_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
 {
@@ -462,20 +631,6 @@ static inline int dma_coerce_mask_and_coherent(struct device *dev, u64 mask)
 	return dma_set_mask_and_coherent(dev, mask);
 }
 
-/**
- * dma_addressing_limited - return if the device is addressing limited
- * @dev:	device to check
- *
- * Return %true if the devices DMA mask is too small to address all memory in
- * the system, else %false.  Lack of addressing bits is the prime reason for
- * bounce buffering, but might not be the only one.
- */
-static inline bool dma_addressing_limited(struct device *dev)
-{
-	return min_not_zero(dma_get_mask(dev), dev->bus_dma_limit) <
-			    dma_get_required_mask(dev);
-}
-
 static inline unsigned int dma_get_max_seg_size(struct device *dev)
 {
 	if (dev->dma_parms && dev->dma_parms->max_segment_size)
@@ -483,13 +638,11 @@ static inline unsigned int dma_get_max_seg_size(struct device *dev)
 	return SZ_64K;
 }
 
-static inline int dma_set_max_seg_size(struct device *dev, unsigned int size)
+static inline void dma_set_max_seg_size(struct device *dev, unsigned int size)
 {
-	if (dev->dma_parms) {
-		dev->dma_parms->max_segment_size = size;
-		return 0;
-	}
-	return -EIO;
+	if (WARN_ON_ONCE(!dev->dma_parms))
+		return;
+	dev->dma_parms->max_segment_size = size;
 }
 
 static inline unsigned long dma_get_seg_boundary(struct device *dev)
@@ -518,13 +671,11 @@ static inline unsigned long dma_get_seg_boundary_nr_pages(struct device *dev,
 	return (dma_get_seg_boundary(dev) >> page_shift) + 1;
 }
 
-static inline int dma_set_seg_boundary(struct device *dev, unsigned long mask)
+static inline void dma_set_seg_boundary(struct device *dev, unsigned long mask)
 {
-	if (dev->dma_parms) {
-		dev->dma_parms->segment_boundary_mask = mask;
-		return 0;
-	}
-	return -EIO;
+	if (WARN_ON_ONCE(!dev->dma_parms))
+		return;
+	dev->dma_parms->segment_boundary_mask = mask;
 }
 
 static inline unsigned int dma_get_min_align_mask(struct device *dev)
@@ -534,22 +685,23 @@ static inline unsigned int dma_get_min_align_mask(struct device *dev)
 	return 0;
 }
 
-static inline int dma_set_min_align_mask(struct device *dev,
+static inline void dma_set_min_align_mask(struct device *dev,
 		unsigned int min_align_mask)
 {
 	if (WARN_ON_ONCE(!dev->dma_parms))
-		return -EIO;
+		return;
 	dev->dma_parms->min_align_mask = min_align_mask;
-	return 0;
 }
 
+#ifndef dma_get_cache_alignment
 static inline int dma_get_cache_alignment(void)
 {
-#ifdef ARCH_DMA_MINALIGN
+#ifdef ARCH_HAS_DMA_MINALIGN
 	return ARCH_DMA_MINALIGN;
 #endif
 	return 1;
 }
+#endif
 
 static inline void *dmam_alloc_coherent(struct device *dev, size_t size,
 		dma_addr_t *dma_handle, gfp_t gfp)
@@ -595,10 +747,14 @@ static inline int dma_mmap_wc(struct device *dev,
 #else
 #define DEFINE_DMA_UNMAP_ADDR(ADDR_NAME)
 #define DEFINE_DMA_UNMAP_LEN(LEN_NAME)
-#define dma_unmap_addr(PTR, ADDR_NAME)           (0)
-#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL)  do { } while (0)
-#define dma_unmap_len(PTR, LEN_NAME)             (0)
-#define dma_unmap_len_set(PTR, LEN_NAME, VAL)    do { } while (0)
+#define dma_unmap_addr(PTR, ADDR_NAME)           \
+	({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_addr_set(PTR, ADDR_NAME, VAL)  \
+	do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
+#define dma_unmap_len(PTR, LEN_NAME)             \
+	({ typeof(PTR) __p __maybe_unused = PTR; 0; })
+#define dma_unmap_len_set(PTR, LEN_NAME, VAL)    \
+	do { typeof(PTR) __p __maybe_unused = PTR; } while (0)
 #endif
 
 #endif /* _LINUX_DMA_MAPPING_H */
diff --git a/include/linux/dma-resv.h b/include/linux/dma-resv.h
index 8d0e34dad446..c5ab6fd9ebe8 100644
--- a/include/linux/dma-resv.h
+++ b/include/linux/dma-resv.h
@@ -105,10 +105,10 @@ enum dma_resv_usage {
 	 * This should be used by submissions which don't want to participate in
 	 * any implicit synchronization.
 	 *
-	 * The most common case are preemption fences, page table updates, TLB
-	 * flushes as well as explicit synced user submissions.
+	 * The most common cases are preemption fences, page table updates, TLB
+	 * flushes as well as explicitly synced user submissions.
 	 *
-	 * Explicit synced user user submissions can be promoted to
+	 * Explicitly synced user submissions can be promoted to
 	 * DMA_RESV_USAGE_READ or DMA_RESV_USAGE_WRITE as needed using
 	 * dma_buf_import_sync_file() when implicit synchronization should
 	 * become necessary after initial adding of the fence.
diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h
index d2638d9259dc..3080747689f6 100644
--- a/include/linux/dma/edma.h
+++ b/include/linux/dma/edma.h
@@ -40,7 +40,7 @@ struct dw_edma_region {
  *			iATU windows. That will be done by the controller
  *			automatically.
  */
-struct dw_edma_core_ops {
+struct dw_edma_plat_ops {
 	int (*irq_vector)(struct device *dev, unsigned int nr);
 	u64 (*pci_address)(struct device *dev, phys_addr_t cpu_addr);
 };
@@ -48,7 +48,8 @@ struct dw_edma_core_ops {
 enum dw_edma_map_format {
 	EDMA_MF_EDMA_LEGACY = 0x0,
 	EDMA_MF_EDMA_UNROLL = 0x1,
-	EDMA_MF_HDMA_COMPAT = 0x5
+	EDMA_MF_HDMA_COMPAT = 0x5,
+	EDMA_MF_HDMA_NATIVE = 0x7,
 };
 
 /**
@@ -80,7 +81,7 @@ enum dw_edma_chip_flags {
 struct dw_edma_chip {
 	struct device		*dev;
 	int			nr_irqs;
-	const struct dw_edma_core_ops   *ops;
+	const struct dw_edma_plat_ops	*ops;
 	u32			flags;
 
 	void __iomem		*reg_base;
diff --git a/include/linux/dma/imx-dma.h b/include/linux/dma/imx-dma.h
index cfec5f946e23..76a8de9ae151 100644
--- a/include/linux/dma/imx-dma.h
+++ b/include/linux/dma/imx-dma.h
@@ -41,6 +41,7 @@ enum sdma_peripheral_type {
 	IMX_DMATYPE_SAI,	/* SAI */
 	IMX_DMATYPE_MULTI_SAI,	/* MULTI FIFOs For Audio */
 	IMX_DMATYPE_HDMI,       /* HDMI Audio */
+	IMX_DMATYPE_I2C,	/* I2C */
 };
 
 enum imx_dma_prio {
diff --git a/include/linux/dma/ipu-dma.h b/include/linux/dma/ipu-dma.h
deleted file mode 100644
index 6969391580d2..000000000000
--- a/include/linux/dma/ipu-dma.h
+++ /dev/null
@@ -1,174 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2008
- * Guennadi Liakhovetski, DENX Software Engineering, <lg@denx.de>
- *
- * Copyright (C) 2005-2007 Freescale Semiconductor, Inc.
- */
-
-#ifndef __LINUX_DMA_IPU_DMA_H
-#define __LINUX_DMA_IPU_DMA_H
-
-#include <linux/types.h>
-#include <linux/dmaengine.h>
-
-/* IPU DMA Controller channel definitions. */
-enum ipu_channel {
-	IDMAC_IC_0 = 0,		/* IC (encoding task) to memory */
-	IDMAC_IC_1 = 1,		/* IC (viewfinder task) to memory */
-	IDMAC_ADC_0 = 1,
-	IDMAC_IC_2 = 2,
-	IDMAC_ADC_1 = 2,
-	IDMAC_IC_3 = 3,
-	IDMAC_IC_4 = 4,
-	IDMAC_IC_5 = 5,
-	IDMAC_IC_6 = 6,
-	IDMAC_IC_7 = 7,		/* IC (sensor data) to memory */
-	IDMAC_IC_8 = 8,
-	IDMAC_IC_9 = 9,
-	IDMAC_IC_10 = 10,
-	IDMAC_IC_11 = 11,
-	IDMAC_IC_12 = 12,
-	IDMAC_IC_13 = 13,
-	IDMAC_SDC_0 = 14,	/* Background synchronous display data */
-	IDMAC_SDC_1 = 15,	/* Foreground data (overlay) */
-	IDMAC_SDC_2 = 16,
-	IDMAC_SDC_3 = 17,
-	IDMAC_ADC_2 = 18,
-	IDMAC_ADC_3 = 19,
-	IDMAC_ADC_4 = 20,
-	IDMAC_ADC_5 = 21,
-	IDMAC_ADC_6 = 22,
-	IDMAC_ADC_7 = 23,
-	IDMAC_PF_0 = 24,
-	IDMAC_PF_1 = 25,
-	IDMAC_PF_2 = 26,
-	IDMAC_PF_3 = 27,
-	IDMAC_PF_4 = 28,
-	IDMAC_PF_5 = 29,
-	IDMAC_PF_6 = 30,
-	IDMAC_PF_7 = 31,
-};
-
-/* Order significant! */
-enum ipu_channel_status {
-	IPU_CHANNEL_FREE,
-	IPU_CHANNEL_INITIALIZED,
-	IPU_CHANNEL_READY,
-	IPU_CHANNEL_ENABLED,
-};
-
-#define IPU_CHANNELS_NUM 32
-
-enum pixel_fmt {
-	/* 1 byte */
-	IPU_PIX_FMT_GENERIC,
-	IPU_PIX_FMT_RGB332,
-	IPU_PIX_FMT_YUV420P,
-	IPU_PIX_FMT_YUV422P,
-	IPU_PIX_FMT_YUV420P2,
-	IPU_PIX_FMT_YVU422P,
-	/* 2 bytes */
-	IPU_PIX_FMT_RGB565,
-	IPU_PIX_FMT_RGB666,
-	IPU_PIX_FMT_BGR666,
-	IPU_PIX_FMT_YUYV,
-	IPU_PIX_FMT_UYVY,
-	/* 3 bytes */
-	IPU_PIX_FMT_RGB24,
-	IPU_PIX_FMT_BGR24,
-	/* 4 bytes */
-	IPU_PIX_FMT_GENERIC_32,
-	IPU_PIX_FMT_RGB32,
-	IPU_PIX_FMT_BGR32,
-	IPU_PIX_FMT_ABGR32,
-	IPU_PIX_FMT_BGRA32,
-	IPU_PIX_FMT_RGBA32,
-};
-
-enum ipu_color_space {
-	IPU_COLORSPACE_RGB,
-	IPU_COLORSPACE_YCBCR,
-	IPU_COLORSPACE_YUV
-};
-
-/*
- * Enumeration of IPU rotation modes
- */
-enum ipu_rotate_mode {
-	/* Note the enum values correspond to BAM value */
-	IPU_ROTATE_NONE = 0,
-	IPU_ROTATE_VERT_FLIP = 1,
-	IPU_ROTATE_HORIZ_FLIP = 2,
-	IPU_ROTATE_180 = 3,
-	IPU_ROTATE_90_RIGHT = 4,
-	IPU_ROTATE_90_RIGHT_VFLIP = 5,
-	IPU_ROTATE_90_RIGHT_HFLIP = 6,
-	IPU_ROTATE_90_LEFT = 7,
-};
-
-/*
- * Enumeration of DI ports for ADC.
- */
-enum display_port {
-	DISP0,
-	DISP1,
-	DISP2,
-	DISP3
-};
-
-struct idmac_video_param {
-	unsigned short		in_width;
-	unsigned short		in_height;
-	uint32_t		in_pixel_fmt;
-	unsigned short		out_width;
-	unsigned short		out_height;
-	uint32_t		out_pixel_fmt;
-	unsigned short		out_stride;
-	bool			graphics_combine_en;
-	bool			global_alpha_en;
-	bool			key_color_en;
-	enum display_port	disp;
-	unsigned short		out_left;
-	unsigned short		out_top;
-};
-
-/*
- * Union of initialization parameters for a logical channel. So far only video
- * parameters are used.
- */
-union ipu_channel_param {
-	struct idmac_video_param video;
-};
-
-struct idmac_tx_desc {
-	struct dma_async_tx_descriptor	txd;
-	struct scatterlist		*sg;	/* scatterlist for this */
-	unsigned int			sg_len;	/* tx-descriptor. */
-	struct list_head		list;
-};
-
-struct idmac_channel {
-	struct dma_chan		dma_chan;
-	dma_cookie_t		completed;	/* last completed cookie	   */
-	union ipu_channel_param	params;
-	enum ipu_channel	link;	/* input channel, linked to the output	   */
-	enum ipu_channel_status	status;
-	void			*client;	/* Only one client per channel	   */
-	unsigned int		n_tx_desc;
-	struct idmac_tx_desc	*desc;		/* allocated tx-descriptors	   */
-	struct scatterlist	*sg[2];	/* scatterlist elements in buffer-0 and -1 */
-	struct list_head	free_list;	/* free tx-descriptors		   */
-	struct list_head	queue;		/* queued tx-descriptors	   */
-	spinlock_t		lock;		/* protects sg[0,1], queue	   */
-	struct mutex		chan_mutex; /* protects status, cookie, free_list  */
-	bool			sec_chan_en;
-	int			active_buffer;
-	unsigned int		eof_irq;
-	char			eof_name[16];	/* EOF IRQ name for request_irq()  */
-};
-
-#define to_tx_desc(tx) container_of(tx, struct idmac_tx_desc, txd)
-#define to_idmac_chan(c) container_of(c, struct idmac_channel, dma_chan)
-
-#endif /* __LINUX_DMA_IPU_DMA_H */
diff --git a/include/linux/dma/k3-udma-glue.h b/include/linux/dma/k3-udma-glue.h
index e443be4d3b4b..5d43881e6fb7 100644
--- a/include/linux/dma/k3-udma-glue.h
+++ b/include/linux/dma/k3-udma-glue.h
@@ -26,6 +26,11 @@ struct k3_udma_glue_tx_channel;
 struct k3_udma_glue_tx_channel *k3_udma_glue_request_tx_chn(struct device *dev,
 		const char *name, struct k3_udma_glue_tx_channel_cfg *cfg);
 
+struct k3_udma_glue_tx_channel *
+k3_udma_glue_request_tx_chn_for_thread_id(struct device *dev,
+					  struct k3_udma_glue_tx_channel_cfg *cfg,
+					  struct device_node *udmax_np, u32 thread_id);
+
 void k3_udma_glue_release_tx_chn(struct k3_udma_glue_tx_channel *tx_chn);
 int k3_udma_glue_push_tx_chn(struct k3_udma_glue_tx_channel *tx_chn,
 			     struct cppi5_host_desc_t *desc_tx,
@@ -109,6 +114,11 @@ struct k3_udma_glue_rx_channel *k3_udma_glue_request_rx_chn(
 		const char *name,
 		struct k3_udma_glue_rx_channel_cfg *cfg);
 
+struct k3_udma_glue_rx_channel *
+k3_udma_glue_request_remote_rx_chn_for_thread_id(struct device *dev,
+						 struct k3_udma_glue_rx_channel_cfg *cfg,
+						 struct device_node *udmax_np, u32 thread_id);
+
 void k3_udma_glue_release_rx_chn(struct k3_udma_glue_rx_channel *rx_chn);
 int k3_udma_glue_enable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn);
 void k3_udma_glue_disable_rx_chn(struct k3_udma_glue_rx_channel *rx_chn);
@@ -126,12 +136,9 @@ u32 k3_udma_glue_rx_flow_get_fdq_id(struct k3_udma_glue_rx_channel *rx_chn,
 u32 k3_udma_glue_rx_get_flow_id_base(struct k3_udma_glue_rx_channel *rx_chn);
 int k3_udma_glue_rx_get_irq(struct k3_udma_glue_rx_channel *rx_chn,
 			    u32 flow_num);
-void k3_udma_glue_rx_put_irq(struct k3_udma_glue_rx_channel *rx_chn,
-			     u32 flow_num);
 void k3_udma_glue_reset_rx_chn(struct k3_udma_glue_rx_channel *rx_chn,
 		u32 flow_num, void *data,
-		void (*cleanup)(void *data, dma_addr_t desc_dma),
-		bool skip_fdq);
+		void (*cleanup)(void *data, dma_addr_t desc_dma));
 int k3_udma_glue_rx_flow_enable(struct k3_udma_glue_rx_channel *rx_chn,
 				u32 flow_idx);
 int k3_udma_glue_rx_flow_disable(struct k3_udma_glue_rx_channel *rx_chn,
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index c3656e590213..99efe2b9b4ea 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -84,7 +84,7 @@ enum dma_transfer_direction {
 	DMA_TRANS_NONE,
 };
 
-/**
+/*
  * Interleaved Transfer Request
  * ----------------------------
  * A chunk is collection of contiguous bytes to be transferred.
@@ -161,6 +161,16 @@ struct dma_interleaved_template {
 };
 
 /**
+ * struct dma_vec - DMA vector
+ * @addr: Bus address of the start of the vector
+ * @len: Length in bytes of the DMA vector
+ */
+struct dma_vec {
+	dma_addr_t addr;
+	size_t len;
+};
+
+/**
  * enum dma_ctrl_flags - DMA flags to augment operation preparation,
  *  control completion, and communicate status.
  * @DMA_PREP_INTERRUPT - trigger an interrupt (callback) upon completion of
@@ -213,7 +223,7 @@ enum sum_check_bits {
 };
 
 /**
- * enum pq_check_flags - result of async_{xor,pq}_zero_sum operations
+ * enum sum_check_flags - result of async_{xor,pq}_zero_sum operations
  * @SUM_CHECK_P_RESULT - 1 if xor zero sum error, 0 otherwise
  * @SUM_CHECK_Q_RESULT - 1 if reed-solomon zero sum error, 0 otherwise
  */
@@ -276,7 +286,7 @@ typedef struct { DECLARE_BITMAP(bits, DMA_TX_TYPE_END); } dma_cap_mask_t;
  *	pointer to the engine's metadata area
  *   4. Read out the metadata from the pointer
  *
- * Note: the two mode is not compatible and clients must use one mode for a
+ * Warning: the two modes are not compatible and clients must use one mode for a
  * descriptor.
  */
 enum dma_desc_metadata_mode {
@@ -517,8 +527,6 @@ static inline const char *dma_chan_name(struct dma_chan *chan)
 	return dev_name(&chan->dev->device);
 }
 
-void dma_chan_cleanup(struct kref *kref);
-
 /**
  * typedef dma_filter_fn - callback filter for dma_request_channel
  * @chan: channel to be reviewed
@@ -586,9 +594,13 @@ struct dma_descriptor_metadata_ops {
  * @phys: physical address of the descriptor
  * @chan: target channel for this operation
  * @tx_submit: accept the descriptor, assign ordered cookie and mark the
- * descriptor pending. To be pushed on .issue_pending() call
+ *	descriptor pending. To be pushed on .issue_pending() call
+ * @desc_free: driver's callback function to free a resusable descriptor
+ *	after completion
  * @callback: routine to call after this operation is complete
+ * @callback_result: error result from a DMA transaction
  * @callback_param: general parameter to pass to the callback routine
+ * @unmap: hook for generic DMA unmap data
  * @desc_metadata_mode: core managed metadata mode to protect mixed use of
  *	DESC_METADATA_CLIENT or DESC_METADATA_ENGINE. Otherwise
  *	DESC_METADATA_NONE
@@ -819,12 +831,14 @@ struct dma_filter {
  * @device_prep_dma_memset: prepares a memset operation
  * @device_prep_dma_memset_sg: prepares a memset operation over a scatter list
  * @device_prep_dma_interrupt: prepares an end of chain interrupt operation
+ * @device_prep_peripheral_dma_vec: prepares a scatter-gather DMA transfer,
+ *	where the address and size of each segment is located in one entry of
+ *	the dma_vec array.
  * @device_prep_slave_sg: prepares a slave dma operation
  * @device_prep_dma_cyclic: prepare a cyclic dma operation suitable for audio.
  *	The function takes a buffer of size buf_len. The callback function will
  *	be called after period_len bytes have been transferred.
  * @device_prep_interleaved_dma: Transfer expression in a generic way.
- * @device_prep_dma_imm_data: DMA's 8 byte immediate data to the dst address
  * @device_caps: May be used to override the generic DMA slave capabilities
  *	with per-channel specific ones
  * @device_config: Pushes a new configuration to a channel, return 0 or an error
@@ -912,6 +926,10 @@ struct dma_device {
 	struct dma_async_tx_descriptor *(*device_prep_dma_interrupt)(
 		struct dma_chan *chan, unsigned long flags);
 
+	struct dma_async_tx_descriptor *(*device_prep_peripheral_dma_vec)(
+		struct dma_chan *chan, const struct dma_vec *vecs,
+		size_t nents, enum dma_transfer_direction direction,
+		unsigned long flags);
 	struct dma_async_tx_descriptor *(*device_prep_slave_sg)(
 		struct dma_chan *chan, struct scatterlist *sgl,
 		unsigned int sg_len, enum dma_transfer_direction direction,
@@ -923,9 +941,6 @@ struct dma_device {
 	struct dma_async_tx_descriptor *(*device_prep_interleaved_dma)(
 		struct dma_chan *chan, struct dma_interleaved_template *xt,
 		unsigned long flags);
-	struct dma_async_tx_descriptor *(*device_prep_dma_imm_data)(
-		struct dma_chan *chan, dma_addr_t dst, u64 data,
-		unsigned long flags);
 
 	void (*device_caps)(struct dma_chan *chan, struct dma_slave_caps *caps);
 	int (*device_config)(struct dma_chan *chan, struct dma_slave_config *config);
@@ -955,7 +970,8 @@ static inline int dmaengine_slave_config(struct dma_chan *chan,
 
 static inline bool is_slave_direction(enum dma_transfer_direction direction)
 {
-	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM);
+	return (direction == DMA_MEM_TO_DEV) || (direction == DMA_DEV_TO_MEM) ||
+	       (direction == DMA_DEV_TO_DEV);
 }
 
 static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
@@ -974,6 +990,25 @@ static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_single(
 						  dir, flags, NULL);
 }
 
+/**
+ * dmaengine_prep_peripheral_dma_vec() - Prepare a DMA scatter-gather descriptor
+ * @chan: The channel to be used for this descriptor
+ * @vecs: The array of DMA vectors that should be transferred
+ * @nents: The number of DMA vectors in the array
+ * @dir: Specifies the direction of the data transfer
+ * @flags: DMA engine flags
+ */
+static inline struct dma_async_tx_descriptor *dmaengine_prep_peripheral_dma_vec(
+	struct dma_chan *chan, const struct dma_vec *vecs, size_t nents,
+	enum dma_transfer_direction dir, unsigned long flags)
+{
+	if (!chan || !chan->device || !chan->device->device_prep_peripheral_dma_vec)
+		return NULL;
+
+	return chan->device->device_prep_peripheral_dma_vec(chan, vecs, nents,
+							    dir, flags);
+}
+
 static inline struct dma_async_tx_descriptor *dmaengine_prep_slave_sg(
 	struct dma_chan *chan, struct scatterlist *sgl,	unsigned int sg_len,
 	enum dma_transfer_direction dir, unsigned long flags)
@@ -1489,6 +1524,7 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 
 struct dma_chan *dma_request_chan(struct device *dev, const char *name);
 struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask);
+struct dma_chan *devm_dma_request_chan(struct device *dev, const char *name);
 
 void dma_release_channel(struct dma_chan *chan);
 int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps);
@@ -1525,6 +1561,12 @@ static inline struct dma_chan *dma_request_chan_by_mask(
 {
 	return ERR_PTR(-ENODEV);
 }
+
+static inline struct dma_chan *devm_dma_request_chan(struct device *dev, const char *name)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline void dma_release_channel(struct dma_chan *chan)
 {
 }
@@ -1576,7 +1618,8 @@ int dma_async_device_register(struct dma_device *device);
 int dmaenginem_async_device_register(struct dma_device *device);
 void dma_async_device_unregister(struct dma_device *device);
 int dma_async_device_channel_register(struct dma_device *device,
-				      struct dma_chan *chan);
+				      struct dma_chan *chan,
+				      const char *name);
 void dma_async_device_channel_unregister(struct dma_device *device,
 					 struct dma_chan *chan);
 void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
@@ -1599,14 +1642,14 @@ static inline struct dma_chan
 {
 	struct dma_chan *chan;
 
-	chan = dma_request_slave_channel(dev, name);
-	if (chan)
+	chan = dma_request_chan(dev, name);
+	if (!IS_ERR(chan))
 		return chan;
 
 	if (!fn || !fn_param)
 		return NULL;
 
-	return __dma_request_channel(&mask, fn, fn_param, NULL);
+	return dma_request_channel(mask, fn, fn_param);
 }
 
 static inline char *
diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h
index f632ecfb4238..7d40b51933d1 100644
--- a/include/linux/dmapool.h
+++ b/include/linux/dmapool.h
@@ -11,6 +11,7 @@
 #ifndef LINUX_DMAPOOL_H
 #define	LINUX_DMAPOOL_H
 
+#include <linux/nodemask_types.h>
 #include <linux/scatterlist.h>
 #include <asm/io.h>
 
@@ -18,8 +19,8 @@ struct device;
 
 #ifdef CONFIG_HAS_DMA
 
-struct dma_pool *dma_pool_create(const char *name, struct device *dev, 
-			size_t size, size_t align, size_t allocation);
+struct dma_pool *dma_pool_create_node(const char *name, struct device *dev,
+		size_t size, size_t align, size_t boundary, int node);
 
 void dma_pool_destroy(struct dma_pool *pool);
 
@@ -35,9 +36,12 @@ struct dma_pool *dmam_pool_create(const char *name, struct device *dev,
 void dmam_pool_destroy(struct dma_pool *pool);
 
 #else /* !CONFIG_HAS_DMA */
-static inline struct dma_pool *dma_pool_create(const char *name,
-	struct device *dev, size_t size, size_t align, size_t allocation)
-{ return NULL; }
+static inline struct dma_pool *dma_pool_create_node(const char *name,
+		struct device *dev, size_t size, size_t align, size_t boundary,
+		int node)
+{
+	return NULL;
+}
 static inline void dma_pool_destroy(struct dma_pool *pool) { }
 static inline void *dma_pool_alloc(struct dma_pool *pool, gfp_t mem_flags,
 				   dma_addr_t *handle) { return NULL; }
@@ -49,6 +53,21 @@ static inline struct dma_pool *dmam_pool_create(const char *name,
 static inline void dmam_pool_destroy(struct dma_pool *pool) { }
 #endif /* !CONFIG_HAS_DMA */
 
+static inline struct dma_pool *dma_pool_create(const char *name,
+		struct device *dev, size_t size, size_t align, size_t boundary)
+{
+	return dma_pool_create_node(name, dev, size, align, boundary,
+				    NUMA_NO_NODE);
+}
+
+/**
+ * dma_pool_zalloc - Get a zero-initialized block of DMA coherent memory.
+ * @pool: dma pool that will produce the block
+ * @mem_flags: GFP_* bitmask
+ * @handle: pointer to dma address of block
+ *
+ * Same as dma_pool_alloc(), but the returned memory is zeroed.
+ */
 static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
 				    dma_addr_t *handle)
 {
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index 725d5e6acec0..692b2b445761 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -106,8 +106,6 @@ static inline bool dmar_rcu_check(void)
 extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 extern void dmar_register_bus_notifier(void);
-extern int dmar_parse_dev_scope(void *start, void *end, int *cnt,
-				struct dmar_dev_scope **devices, u16 segment);
 extern void *dmar_alloc_dev_scope(void *start, void *end, int *cnt);
 extern void dmar_free_dev_scope(struct dmar_dev_scope **devices, int *cnt);
 extern int dmar_insert_dev_scope(struct dmar_pci_notify_info *info,
@@ -119,7 +117,7 @@ extern int dmar_remove_dev_scope(struct dmar_pci_notify_info *info,
 				 int count);
 /* Intel IOMMU detection */
 void detect_intel_iommu(void);
-extern int enable_drhd_fault_handling(void);
+extern int enable_drhd_fault_handling(unsigned int cpu);
 extern int dmar_device_add(acpi_handle handle);
 extern int dmar_device_remove(acpi_handle handle);
 
@@ -202,67 +200,74 @@ static inline void detect_intel_iommu(void)
 
 struct irte {
 	union {
-		/* Shared between remapped and posted mode*/
 		struct {
-			__u64	present		: 1,  /*  0      */
-				fpd		: 1,  /*  1      */
-				__res0		: 6,  /*  2 -  6 */
-				avail		: 4,  /*  8 - 11 */
-				__res1		: 3,  /* 12 - 14 */
-				pst		: 1,  /* 15      */
-				vector		: 8,  /* 16 - 23 */
-				__res2		: 40; /* 24 - 63 */
+			union {
+				/* Shared between remapped and posted mode*/
+				struct {
+					__u64	present		: 1,  /*  0      */
+						fpd		: 1,  /*  1      */
+						__res0		: 6,  /*  2 -  6 */
+						avail		: 4,  /*  8 - 11 */
+						__res1		: 3,  /* 12 - 14 */
+						pst		: 1,  /* 15      */
+						vector		: 8,  /* 16 - 23 */
+						__res2		: 40; /* 24 - 63 */
+				};
+
+				/* Remapped mode */
+				struct {
+					__u64	r_present	: 1,  /*  0      */
+						r_fpd		: 1,  /*  1      */
+						dst_mode	: 1,  /*  2      */
+						redir_hint	: 1,  /*  3      */
+						trigger_mode	: 1,  /*  4      */
+						dlvry_mode	: 3,  /*  5 -  7 */
+						r_avail		: 4,  /*  8 - 11 */
+						r_res0		: 4,  /* 12 - 15 */
+						r_vector	: 8,  /* 16 - 23 */
+						r_res1		: 8,  /* 24 - 31 */
+						dest_id		: 32; /* 32 - 63 */
+				};
+
+				/* Posted mode */
+				struct {
+					__u64	p_present	: 1,  /*  0      */
+						p_fpd		: 1,  /*  1      */
+						p_res0		: 6,  /*  2 -  7 */
+						p_avail		: 4,  /*  8 - 11 */
+						p_res1		: 2,  /* 12 - 13 */
+						p_urgent	: 1,  /* 14      */
+						p_pst		: 1,  /* 15      */
+						p_vector	: 8,  /* 16 - 23 */
+						p_res2		: 14, /* 24 - 37 */
+						pda_l		: 26; /* 38 - 63 */
+				};
+				__u64 low;
+			};
+
+			union {
+				/* Shared between remapped and posted mode*/
+				struct {
+					__u64	sid		: 16,  /* 64 - 79  */
+						sq		: 2,   /* 80 - 81  */
+						svt		: 2,   /* 82 - 83  */
+						__res3		: 44;  /* 84 - 127 */
+				};
+
+				/* Posted mode*/
+				struct {
+					__u64	p_sid		: 16,  /* 64 - 79  */
+						p_sq		: 2,   /* 80 - 81  */
+						p_svt		: 2,   /* 82 - 83  */
+						p_res3		: 12,  /* 84 - 95  */
+						pda_h		: 32;  /* 96 - 127 */
+				};
+				__u64 high;
+			};
 		};
-
-		/* Remapped mode */
-		struct {
-			__u64	r_present	: 1,  /*  0      */
-				r_fpd		: 1,  /*  1      */
-				dst_mode	: 1,  /*  2      */
-				redir_hint	: 1,  /*  3      */
-				trigger_mode	: 1,  /*  4      */
-				dlvry_mode	: 3,  /*  5 -  7 */
-				r_avail		: 4,  /*  8 - 11 */
-				r_res0		: 4,  /* 12 - 15 */
-				r_vector	: 8,  /* 16 - 23 */
-				r_res1		: 8,  /* 24 - 31 */
-				dest_id		: 32; /* 32 - 63 */
-		};
-
-		/* Posted mode */
-		struct {
-			__u64	p_present	: 1,  /*  0      */
-				p_fpd		: 1,  /*  1      */
-				p_res0		: 6,  /*  2 -  7 */
-				p_avail		: 4,  /*  8 - 11 */
-				p_res1		: 2,  /* 12 - 13 */
-				p_urgent	: 1,  /* 14      */
-				p_pst		: 1,  /* 15      */
-				p_vector	: 8,  /* 16 - 23 */
-				p_res2		: 14, /* 24 - 37 */
-				pda_l		: 26; /* 38 - 63 */
-		};
-		__u64 low;
-	};
-
-	union {
-		/* Shared between remapped and posted mode*/
-		struct {
-			__u64	sid		: 16,  /* 64 - 79  */
-				sq		: 2,   /* 80 - 81  */
-				svt		: 2,   /* 82 - 83  */
-				__res3		: 44;  /* 84 - 127 */
-		};
-
-		/* Posted mode*/
-		struct {
-			__u64	p_sid		: 16,  /* 64 - 79  */
-				p_sq		: 2,   /* 80 - 81  */
-				p_svt		: 2,   /* 82 - 83  */
-				p_res3		: 12,  /* 84 - 95  */
-				pda_h		: 32;  /* 96 - 127 */
-		};
-		__u64 high;
+#ifdef CONFIG_IRQ_REMAP
+		__u128 irte;
+#endif
 	};
 };
 
@@ -287,7 +292,6 @@ static inline void dmar_copy_shared_irte(struct irte *dst, struct irte *src)
 struct irq_data;
 extern void dmar_msi_unmask(struct irq_data *data);
 extern void dmar_msi_mask(struct irq_data *data);
-extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);
 extern irqreturn_t dmar_fault(int irq, void *dev_id);
diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h
index b1d26f9f1c9f..9f183a679277 100644
--- a/include/linux/dnotify.h
+++ b/include/linux/dnotify.h
@@ -30,7 +30,7 @@ struct dnotify_struct {
 			    FS_MOVED_FROM | FS_MOVED_TO)
 
 extern void dnotify_flush(struct file *, fl_owner_t);
-extern int fcntl_dirnotify(int, struct file *, unsigned long);
+extern int fcntl_dirnotify(int, struct file *, unsigned int);
 
 #else
 
@@ -38,7 +38,7 @@ static inline void dnotify_flush(struct file *filp, fl_owner_t id)
 {
 }
 
-static inline int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
+static inline int fcntl_dirnotify(int fd, struct file *filp, unsigned int arg)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
new file mode 100644
index 000000000000..562f520b23c2
--- /dev/null
+++ b/include/linux/dpll.h
@@ -0,0 +1,229 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *  Copyright (c) 2023 Meta Platforms, Inc. and affiliates
+ *  Copyright (c) 2023 Intel and affiliates
+ */
+
+#ifndef __DPLL_H__
+#define __DPLL_H__
+
+#include <uapi/linux/dpll.h>
+#include <linux/device.h>
+#include <linux/netlink.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+
+struct dpll_device;
+struct dpll_pin;
+struct dpll_pin_esync;
+
+struct dpll_device_ops {
+	int (*mode_get)(const struct dpll_device *dpll, void *dpll_priv,
+			enum dpll_mode *mode, struct netlink_ext_ack *extack);
+	int (*lock_status_get)(const struct dpll_device *dpll, void *dpll_priv,
+			       enum dpll_lock_status *status,
+			       enum dpll_lock_status_error *status_error,
+			       struct netlink_ext_ack *extack);
+	int (*temp_get)(const struct dpll_device *dpll, void *dpll_priv,
+			s32 *temp, struct netlink_ext_ack *extack);
+	int (*clock_quality_level_get)(const struct dpll_device *dpll,
+				       void *dpll_priv,
+				       unsigned long *qls,
+				       struct netlink_ext_ack *extack);
+	int (*phase_offset_monitor_set)(const struct dpll_device *dpll,
+					void *dpll_priv,
+					enum dpll_feature_state state,
+					struct netlink_ext_ack *extack);
+	int (*phase_offset_monitor_get)(const struct dpll_device *dpll,
+					void *dpll_priv,
+					enum dpll_feature_state *state,
+					struct netlink_ext_ack *extack);
+	int (*phase_offset_avg_factor_set)(const struct dpll_device *dpll,
+					   void *dpll_priv, u32 factor,
+					   struct netlink_ext_ack *extack);
+	int (*phase_offset_avg_factor_get)(const struct dpll_device *dpll,
+					   void *dpll_priv, u32 *factor,
+					   struct netlink_ext_ack *extack);
+};
+
+struct dpll_pin_ops {
+	int (*frequency_set)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     const u64 frequency,
+			     struct netlink_ext_ack *extack);
+	int (*frequency_get)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     u64 *frequency, struct netlink_ext_ack *extack);
+	int (*direction_set)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     const enum dpll_pin_direction direction,
+			     struct netlink_ext_ack *extack);
+	int (*direction_get)(const struct dpll_pin *pin, void *pin_priv,
+			     const struct dpll_device *dpll, void *dpll_priv,
+			     enum dpll_pin_direction *direction,
+			     struct netlink_ext_ack *extack);
+	int (*state_on_pin_get)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_pin *parent_pin,
+				void *parent_pin_priv,
+				enum dpll_pin_state *state,
+				struct netlink_ext_ack *extack);
+	int (*state_on_dpll_get)(const struct dpll_pin *pin, void *pin_priv,
+				 const struct dpll_device *dpll,
+				 void *dpll_priv, enum dpll_pin_state *state,
+				 struct netlink_ext_ack *extack);
+	int (*state_on_pin_set)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_pin *parent_pin,
+				void *parent_pin_priv,
+				const enum dpll_pin_state state,
+				struct netlink_ext_ack *extack);
+	int (*state_on_dpll_set)(const struct dpll_pin *pin, void *pin_priv,
+				 const struct dpll_device *dpll,
+				 void *dpll_priv,
+				 const enum dpll_pin_state state,
+				 struct netlink_ext_ack *extack);
+	int (*prio_get)(const struct dpll_pin *pin,  void *pin_priv,
+			const struct dpll_device *dpll,  void *dpll_priv,
+			u32 *prio, struct netlink_ext_ack *extack);
+	int (*prio_set)(const struct dpll_pin *pin, void *pin_priv,
+			const struct dpll_device *dpll, void *dpll_priv,
+			const u32 prio, struct netlink_ext_ack *extack);
+	int (*phase_offset_get)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_device *dpll, void *dpll_priv,
+				s64 *phase_offset,
+				struct netlink_ext_ack *extack);
+	int (*phase_adjust_get)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_device *dpll, void *dpll_priv,
+				s32 *phase_adjust,
+				struct netlink_ext_ack *extack);
+	int (*phase_adjust_set)(const struct dpll_pin *pin, void *pin_priv,
+				const struct dpll_device *dpll, void *dpll_priv,
+				const s32 phase_adjust,
+				struct netlink_ext_ack *extack);
+	int (*ffo_get)(const struct dpll_pin *pin, void *pin_priv,
+		       const struct dpll_device *dpll, void *dpll_priv,
+		       s64 *ffo, struct netlink_ext_ack *extack);
+	int (*esync_set)(const struct dpll_pin *pin, void *pin_priv,
+			 const struct dpll_device *dpll, void *dpll_priv,
+			 u64 freq, struct netlink_ext_ack *extack);
+	int (*esync_get)(const struct dpll_pin *pin, void *pin_priv,
+			 const struct dpll_device *dpll, void *dpll_priv,
+			 struct dpll_pin_esync *esync,
+			 struct netlink_ext_ack *extack);
+	int (*ref_sync_set)(const struct dpll_pin *pin, void *pin_priv,
+			    const struct dpll_pin *ref_sync_pin,
+			    void *ref_sync_pin_priv,
+			    const enum dpll_pin_state state,
+			    struct netlink_ext_ack *extack);
+	int (*ref_sync_get)(const struct dpll_pin *pin, void *pin_priv,
+			    const struct dpll_pin *ref_sync_pin,
+			    void *ref_sync_pin_priv,
+			    enum dpll_pin_state *state,
+			    struct netlink_ext_ack *extack);
+};
+
+struct dpll_pin_frequency {
+	u64 min;
+	u64 max;
+};
+
+#define DPLL_PIN_FREQUENCY_RANGE(_min, _max)	\
+	{					\
+		.min = _min,			\
+		.max = _max,			\
+	}
+
+#define DPLL_PIN_FREQUENCY(_val) DPLL_PIN_FREQUENCY_RANGE(_val, _val)
+#define DPLL_PIN_FREQUENCY_1PPS \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_1_HZ)
+#define DPLL_PIN_FREQUENCY_10MHZ \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_MHZ)
+#define DPLL_PIN_FREQUENCY_IRIG_B \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_10_KHZ)
+#define DPLL_PIN_FREQUENCY_DCF77 \
+	DPLL_PIN_FREQUENCY(DPLL_PIN_FREQUENCY_77_5_KHZ)
+
+struct dpll_pin_phase_adjust_range {
+	s32 min;
+	s32 max;
+};
+
+struct dpll_pin_esync {
+	u64 freq;
+	const struct dpll_pin_frequency *range;
+	u8 range_num;
+	u8 pulse;
+};
+
+struct dpll_pin_properties {
+	const char *board_label;
+	const char *panel_label;
+	const char *package_label;
+	enum dpll_pin_type type;
+	unsigned long capabilities;
+	u32 freq_supported_num;
+	struct dpll_pin_frequency *freq_supported;
+	struct dpll_pin_phase_adjust_range phase_range;
+	u32 phase_gran;
+};
+
+#if IS_ENABLED(CONFIG_DPLL)
+void dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin);
+void dpll_netdev_pin_clear(struct net_device *dev);
+
+size_t dpll_netdev_pin_handle_size(const struct net_device *dev);
+int dpll_netdev_add_pin_handle(struct sk_buff *msg,
+			       const struct net_device *dev);
+#else
+static inline void
+dpll_netdev_pin_set(struct net_device *dev, struct dpll_pin *dpll_pin) { }
+static inline void dpll_netdev_pin_clear(struct net_device *dev) { }
+
+static inline size_t dpll_netdev_pin_handle_size(const struct net_device *dev)
+{
+	return 0;
+}
+
+static inline int
+dpll_netdev_add_pin_handle(struct sk_buff *msg, const struct net_device *dev)
+{
+	return 0;
+}
+#endif
+
+struct dpll_device *
+dpll_device_get(u64 clock_id, u32 dev_driver_id, struct module *module);
+
+void dpll_device_put(struct dpll_device *dpll);
+
+int dpll_device_register(struct dpll_device *dpll, enum dpll_type type,
+			 const struct dpll_device_ops *ops, void *priv);
+
+void dpll_device_unregister(struct dpll_device *dpll,
+			    const struct dpll_device_ops *ops, void *priv);
+
+struct dpll_pin *
+dpll_pin_get(u64 clock_id, u32 dev_driver_id, struct module *module,
+	     const struct dpll_pin_properties *prop);
+
+int dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
+		      const struct dpll_pin_ops *ops, void *priv);
+
+void dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin,
+			 const struct dpll_pin_ops *ops, void *priv);
+
+void dpll_pin_put(struct dpll_pin *pin);
+
+int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
+			     const struct dpll_pin_ops *ops, void *priv);
+
+void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin,
+				const struct dpll_pin_ops *ops, void *priv);
+
+int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin,
+			       struct dpll_pin *ref_sync_pin);
+
+int dpll_device_change_ntf(struct dpll_device *dpll);
+
+int dpll_pin_change_ntf(struct dpll_pin *pin);
+
+#endif
diff --git a/include/linux/dsa/8021q.h b/include/linux/dsa/8021q.h
index f3664ee12170..d13aabdeb4b2 100644
--- a/include/linux/dsa/8021q.h
+++ b/include/linux/dsa/8021q.h
@@ -8,12 +8,18 @@
 #include <net/dsa.h>
 #include <linux/types.h>
 
+/* VBID is limited to three bits only and zero is reserved.
+ * Only 7 bridges can be enumerated.
+ */
+#define DSA_TAG_8021Q_MAX_NUM_BRIDGES	7
+
 int dsa_tag_8021q_register(struct dsa_switch *ds, __be16 proto);
 
 void dsa_tag_8021q_unregister(struct dsa_switch *ds);
 
 int dsa_tag_8021q_bridge_join(struct dsa_switch *ds, int port,
-			      struct dsa_bridge bridge);
+			      struct dsa_bridge bridge, bool *tx_fwd_offload,
+			      struct netlink_ext_ack *extack);
 
 void dsa_tag_8021q_bridge_leave(struct dsa_switch *ds, int port,
 				struct dsa_bridge bridge);
diff --git a/include/linux/dsa/lan9303.h b/include/linux/dsa/lan9303.h
index b4f22112ba75..3ce7cbcc37a3 100644
--- a/include/linux/dsa/lan9303.h
+++ b/include/linux/dsa/lan9303.h
@@ -5,8 +5,8 @@ struct lan9303;
 
 struct lan9303_phy_ops {
 	/* PHY 1 and 2 access*/
-	int	(*phy_read)(struct lan9303 *chip, int port, int regnum);
-	int	(*phy_write)(struct lan9303 *chip, int port,
+	int	(*phy_read)(struct lan9303 *chip, int addr, int regnum);
+	int	(*phy_write)(struct lan9303 *chip, int addr,
 			     int regnum, u16 val);
 };
 
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index dca2969015d8..620a3260fc08 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -5,6 +5,8 @@
 #ifndef _NET_DSA_TAG_OCELOT_H
 #define _NET_DSA_TAG_OCELOT_H
 
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/kthread.h>
 #include <linux/packing.h>
 #include <linux/skbuff.h>
@@ -13,6 +15,7 @@
 struct ocelot_skb_cb {
 	struct sk_buff *clone;
 	unsigned int ptp_class; /* valid only for clones */
+	unsigned long ptp_tx_time; /* valid only for clones */
 	u32 tstamp_lo;
 	u8 ptp_cmd;
 	u8 ts_id;
@@ -273,4 +276,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
 	return rew_op;
 }
 
+/**
+ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
+ * @skb: Pointer to socket buffer
+ * @br: Pointer to bridge device that the port is under, if any
+ * @vlan_tci:
+ * @tag_type:
+ *
+ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
+ * payload and move it into the DSA tag, which will make the switch classify
+ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
+ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
+ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
+ * and source address learning is not performed for packets injected from the
+ * CPU anyway, so it doesn't matter that the VID is "wrong".
+ */
+static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
+					     struct net_device *br,
+					     u64 *vlan_tci, u64 *tag_type)
+{
+	struct vlan_ethhdr *hdr;
+	u16 proto, tci;
+
+	if (!br || !br_vlan_enabled(br)) {
+		*vlan_tci = 0;
+		*tag_type = IFH_TAG_TYPE_C;
+		return;
+	}
+
+	hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
+	br_vlan_get_proto(br, &proto);
+
+	if (ntohs(hdr->h_vlan_proto) == proto) {
+		vlan_remove_tag(skb, &tci);
+		*vlan_tci = tci;
+	} else {
+		rcu_read_lock();
+		br_vlan_get_pvid_rcu(br, &tci);
+		rcu_read_unlock();
+		*vlan_tci = tci;
+	}
+
+	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+}
+
 #endif
diff --git a/include/linux/dsa/sja1105.h b/include/linux/dsa/sja1105.h
index 159e43171ccc..b9dd35d4b8f5 100644
--- a/include/linux/dsa/sja1105.h
+++ b/include/linux/dsa/sja1105.h
@@ -28,7 +28,7 @@
 /* Source and Destination MAC of follow-up meta frames.
  * Whereas the choice of SMAC only affects the unique identification of the
  * switch as sender of meta frames, the DMAC must be an address that is present
- * in the DSA master port's multicast MAC filter.
+ * in the DSA conduit port's multicast MAC filter.
  * 01-80-C2-00-00-0E is a good choice for this, as all profiles of IEEE 1588
  * over L2 use this address for some purpose already.
  */
@@ -48,13 +48,9 @@ struct sja1105_deferred_xmit_work {
 
 /* Global tagger data */
 struct sja1105_tagger_data {
-	/* Tagger to switch */
 	void (*xmit_work_fn)(struct kthread_work *work);
 	void (*meta_tstamp_handler)(struct dsa_switch *ds, int port, u8 ts_id,
 				    enum sja1110_meta_tstamp dir, u64 tstamp);
-	/* Switch to tagger */
-	bool (*rxtstamp_get_state)(struct dsa_switch *ds);
-	void (*rxtstamp_set_state)(struct dsa_switch *ds, bool on);
 };
 
 struct sja1105_skb_cb {
diff --git a/include/linux/dw_apb_timer.h b/include/linux/dw_apb_timer.h
index 82ebf9223948..f8811c46b89e 100644
--- a/include/linux/dw_apb_timer.h
+++ b/include/linux/dw_apb_timer.h
@@ -34,9 +34,6 @@ struct dw_apb_clocksource {
 };
 
 void dw_apb_clockevent_register(struct dw_apb_clock_event_device *dw_ced);
-void dw_apb_clockevent_pause(struct dw_apb_clock_event_device *dw_ced);
-void dw_apb_clockevent_resume(struct dw_apb_clock_event_device *dw_ced);
-void dw_apb_clockevent_stop(struct dw_apb_clock_event_device *dw_ced);
 
 struct dw_apb_clock_event_device *
 dw_apb_clockevent_init(int cpu, const char *name, unsigned rating,
diff --git a/include/linux/dynamic_debug.h b/include/linux/dynamic_debug.h
index 061dd84d09f3..05743900a116 100644
--- a/include/linux/dynamic_debug.h
+++ b/include/linux/dynamic_debug.h
@@ -37,10 +37,13 @@ struct _ddebug {
 #define _DPRINTK_FLAGS_INCL_FUNCNAME	(1<<2)
 #define _DPRINTK_FLAGS_INCL_LINENO	(1<<3)
 #define _DPRINTK_FLAGS_INCL_TID		(1<<4)
+#define _DPRINTK_FLAGS_INCL_SOURCENAME	(1<<5)
+#define _DPRINTK_FLAGS_INCL_STACK	(1<<6)
 
 #define _DPRINTK_FLAGS_INCL_ANY		\
 	(_DPRINTK_FLAGS_INCL_MODNAME | _DPRINTK_FLAGS_INCL_FUNCNAME |\
-	 _DPRINTK_FLAGS_INCL_LINENO  | _DPRINTK_FLAGS_INCL_TID)
+	 _DPRINTK_FLAGS_INCL_LINENO  | _DPRINTK_FLAGS_INCL_TID |\
+	 _DPRINTK_FLAGS_INCL_SOURCENAME | _DPRINTK_FLAGS_INCL_STACK)
 
 #if defined DEBUG
 #define _DPRINTK_FLAGS_DEFAULT _DPRINTK_FLAGS_PRINT
@@ -158,6 +161,12 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 			 const struct ib_device *ibdev,
 			 const char *fmt, ...);
 
+#define __dynamic_dump_stack(desc)				\
+{								\
+	if (desc.flags & _DPRINTK_FLAGS_INCL_STACK)		\
+		dump_stack();					\
+}
+
 #define DEFINE_DYNAMIC_DEBUG_METADATA_CLS(name, cls, fmt)	\
 	static struct _ddebug  __aligned(8)			\
 	__section("__dyndbg") name = {				\
@@ -218,8 +227,10 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
  */
 #define __dynamic_func_call_cls(id, cls, fmt, func, ...) do {	\
 	DEFINE_DYNAMIC_DEBUG_METADATA_CLS(id, cls, fmt);	\
-	if (DYNAMIC_DEBUG_BRANCH(id))				\
+	if (DYNAMIC_DEBUG_BRANCH(id)) {				\
 		func(&id, ##__VA_ARGS__);			\
+		__dynamic_dump_stack(id);			\
+	}							\
 } while (0)
 #define __dynamic_func_call(id, fmt, func, ...)				\
 	__dynamic_func_call_cls(id, _DPRINTK_CLASS_DFLT, fmt,		\
@@ -227,8 +238,10 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 
 #define __dynamic_func_call_cls_no_desc(id, cls, fmt, func, ...) do {	\
 	DEFINE_DYNAMIC_DEBUG_METADATA_CLS(id, cls, fmt);		\
-	if (DYNAMIC_DEBUG_BRANCH(id))					\
+	if (DYNAMIC_DEBUG_BRANCH(id)) {					\
 		func(__VA_ARGS__);					\
+		__dynamic_dump_stack(id);				\
+	}								\
 } while (0)
 #define __dynamic_func_call_no_desc(id, fmt, func, ...)			\
 	__dynamic_func_call_cls_no_desc(id, _DPRINTK_CLASS_DFLT,	\
@@ -303,9 +316,9 @@ void __dynamic_ibdev_dbg(struct _ddebug *descriptor,
 #define DYNAMIC_DEBUG_BRANCH(descriptor) false
 
 #define dynamic_pr_debug(fmt, ...)					\
-	do { if (0) printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); } while (0)
+	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #define dynamic_dev_dbg(dev, fmt, ...)					\
-	do { if (0) dev_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__); } while (0)
+	dev_no_printk(KERN_DEBUG, dev, fmt, ##__VA_ARGS__)
 #define dynamic_hex_dump(prefix_str, prefix_type, rowsize,		\
 			 groupsize, buf, len, ascii)			\
 	do { if (0)							\
diff --git a/include/linux/dynamic_queue_limits.h b/include/linux/dynamic_queue_limits.h
index 407c2f281b64..808b1a5102e7 100644
--- a/include/linux/dynamic_queue_limits.h
+++ b/include/linux/dynamic_queue_limits.h
@@ -38,14 +38,25 @@
 
 #ifdef __KERNEL__
 
+#include <linux/bitops.h>
 #include <asm/bug.h>
 
+#define DQL_HIST_LEN		4
+#define DQL_HIST_ENT(dql, idx)	((dql)->history[(idx) % DQL_HIST_LEN])
+
 struct dql {
 	/* Fields accessed in enqueue path (dql_queued) */
 	unsigned int	num_queued;		/* Total ever queued */
 	unsigned int	adj_limit;		/* limit + num_completed */
 	unsigned int	last_obj_cnt;		/* Count at last queuing */
 
+	/* Stall threshold (in jiffies), defined by user */
+	unsigned short	stall_thrs;
+
+	unsigned long	history_head;		/* top 58 bits of jiffies */
+	/* stall entries, a bit per entry */
+	unsigned long	history[DQL_HIST_LEN];
+
 	/* Fields accessed only by completion path (dql_completed) */
 
 	unsigned int	limit ____cacheline_aligned_in_smp; /* Current limit */
@@ -62,21 +73,61 @@ struct dql {
 	unsigned int	max_limit;		/* Max limit */
 	unsigned int	min_limit;		/* Minimum limit */
 	unsigned int	slack_hold_time;	/* Time to measure slack */
+
+	/* Longest stall detected, reported to user */
+	unsigned short	stall_max;
+	unsigned long	last_reap;		/* Last reap (in jiffies) */
+	unsigned long	stall_cnt;		/* Number of stalls */
 };
 
 /* Set some static maximums */
 #define DQL_MAX_OBJECT (UINT_MAX / 16)
 #define DQL_MAX_LIMIT ((UINT_MAX / 2) - DQL_MAX_OBJECT)
 
+/* Populate the bitmap to be processed later in dql_check_stall() */
+static inline void dql_queue_stall(struct dql *dql)
+{
+	unsigned long map, now, now_hi, i;
+
+	now = jiffies;
+	now_hi = now / BITS_PER_LONG;
+
+	/* The following code set a bit in the ring buffer, where each
+	 * bit trackes time the packet was queued. The dql->history buffer
+	 * tracks DQL_HIST_LEN * BITS_PER_LONG time (jiffies) slot
+	 */
+	if (unlikely(now_hi != dql->history_head)) {
+		/* About to reuse slots, clear them */
+		for (i = 0; i < DQL_HIST_LEN; i++) {
+			/* Multiplication masks high bits */
+			if (now_hi * BITS_PER_LONG ==
+			    (dql->history_head + i) * BITS_PER_LONG)
+				break;
+			DQL_HIST_ENT(dql, dql->history_head + i + 1) = 0;
+		}
+		/* pairs with smp_rmb() in dql_check_stall() */
+		smp_wmb();
+		WRITE_ONCE(dql->history_head, now_hi);
+	}
+
+	/* __set_bit() does not guarantee WRITE_ONCE() semantics */
+	map = DQL_HIST_ENT(dql, now_hi);
+
+	/* Populate the history with an entry (bit) per queued */
+	if (!(map & BIT_MASK(now)))
+		WRITE_ONCE(DQL_HIST_ENT(dql, now_hi), map | BIT_MASK(now));
+}
+
 /*
  * Record number of objects queued. Assumes that caller has already checked
  * availability in the queue with dql_avail.
  */
 static inline void dql_queued(struct dql *dql, unsigned int count)
 {
-	BUG_ON(count > DQL_MAX_OBJECT);
+	if (WARN_ON_ONCE(count > DQL_MAX_OBJECT))
+		return;
 
-	dql->last_obj_cnt = count;
+	WRITE_ONCE(dql->last_obj_cnt, count);
 
 	/* We want to force a write first, so that cpu do not attempt
 	 * to get cache line containing last_obj_cnt, num_queued, adj_limit
@@ -86,6 +137,10 @@ static inline void dql_queued(struct dql *dql, unsigned int count)
 	barrier();
 
 	dql->num_queued += count;
+
+	/* Only populate stall information if the threshold is set */
+	if (READ_ONCE(dql->stall_thrs))
+		dql_queue_stall(dql);
 }
 
 /* Returns how many objects can be queued, < 0 indicates over limit. */
diff --git a/include/linux/edac.h b/include/linux/edac.h
index fa4bda2a70f6..fa32f2aca22f 100644
--- a/include/linux/edac.h
+++ b/include/linux/edac.h
@@ -30,7 +30,7 @@ struct device;
 
 extern int edac_op_state;
 
-struct bus_type *edac_get_sysfs_subsys(void);
+const struct bus_type *edac_get_sysfs_subsys(void);
 
 static inline void opstate_init(void)
 {
@@ -187,6 +187,7 @@ static inline char *mc_event_error_type(const unsigned int err_type)
  * @MEM_NVDIMM:		Non-volatile RAM
  * @MEM_WIO2:		Wide I/O 2.
  * @MEM_HBM2:		High bandwidth Memory Gen 2.
+ * @MEM_HBM3:		High bandwidth Memory Gen 3.
  */
 enum mem_type {
 	MEM_EMPTY = 0,
@@ -218,6 +219,7 @@ enum mem_type {
 	MEM_NVDIMM,
 	MEM_WIO2,
 	MEM_HBM2,
+	MEM_HBM3,
 };
 
 #define MEM_FLAG_EMPTY		BIT(MEM_EMPTY)
@@ -248,6 +250,7 @@ enum mem_type {
 #define MEM_FLAG_NVDIMM		BIT(MEM_NVDIMM)
 #define MEM_FLAG_WIO2		BIT(MEM_WIO2)
 #define MEM_FLAG_HBM2		BIT(MEM_HBM2)
+#define MEM_FLAG_HBM3		BIT(MEM_HBM3)
 
 /**
  * enum edac_type - Error Detection and Correction capabilities and mode
@@ -492,7 +495,7 @@ struct edac_raw_error_desc {
  */
 struct mem_ctl_info {
 	struct device			dev;
-	struct bus_type			*bus;
+	const struct bus_type		*bus;
 
 	struct list_head link;	/* for global list of mem_ctl_info structs */
 
@@ -658,4 +661,226 @@ static inline struct dimm_info *edac_get_dimm(struct mem_ctl_info *mci,
 
 	return mci->dimms[index];
 }
+
+#define EDAC_FEAT_NAME_LEN	128
+
+/* RAS feature type */
+enum edac_dev_feat {
+	RAS_FEAT_SCRUB,
+	RAS_FEAT_ECS,
+	RAS_FEAT_MEM_REPAIR,
+	RAS_FEAT_MAX
+};
+
+/**
+ * struct edac_scrub_ops - scrub device operations (all elements optional)
+ * @read_addr: read base address of scrubbing range.
+ * @read_size: read offset of scrubbing range.
+ * @write_addr: set base address of the scrubbing range.
+ * @write_size: set offset of the scrubbing range.
+ * @get_enabled_bg: check if currently performing background scrub.
+ * @set_enabled_bg: start or stop a bg-scrub.
+ * @get_min_cycle: get minimum supported scrub cycle duration in seconds.
+ * @get_max_cycle: get maximum supported scrub cycle duration in seconds.
+ * @get_cycle_duration: get current scrub cycle duration in seconds.
+ * @set_cycle_duration: set current scrub cycle duration in seconds.
+ */
+struct edac_scrub_ops {
+	int (*read_addr)(struct device *dev, void *drv_data, u64 *base);
+	int (*read_size)(struct device *dev, void *drv_data, u64 *size);
+	int (*write_addr)(struct device *dev, void *drv_data, u64 base);
+	int (*write_size)(struct device *dev, void *drv_data, u64 size);
+	int (*get_enabled_bg)(struct device *dev, void *drv_data, bool *enable);
+	int (*set_enabled_bg)(struct device *dev, void *drv_data, bool enable);
+	int (*get_min_cycle)(struct device *dev, void *drv_data,  u32 *min);
+	int (*get_max_cycle)(struct device *dev, void *drv_data,  u32 *max);
+	int (*get_cycle_duration)(struct device *dev, void *drv_data, u32 *cycle);
+	int (*set_cycle_duration)(struct device *dev, void *drv_data, u32 cycle);
+};
+
+#if IS_ENABLED(CONFIG_EDAC_SCRUB)
+int edac_scrub_get_desc(struct device *scrub_dev,
+			const struct attribute_group **attr_groups,
+			u8 instance);
+#else
+static inline int edac_scrub_get_desc(struct device *scrub_dev,
+				      const struct attribute_group **attr_groups,
+				      u8 instance)
+{ return -EOPNOTSUPP; }
+#endif /* CONFIG_EDAC_SCRUB */
+
+/**
+ * struct edac_ecs_ops - ECS device operations (all elements optional)
+ * @get_log_entry_type: read the log entry type value.
+ * @set_log_entry_type: set the log entry type value.
+ * @get_mode: read the mode value.
+ * @set_mode: set the mode value.
+ * @reset: reset the ECS counter.
+ * @get_threshold: read the threshold count per gigabits of memory cells.
+ * @set_threshold: set the threshold count per gigabits of memory cells.
+ */
+struct edac_ecs_ops {
+	int (*get_log_entry_type)(struct device *dev, void *drv_data, int fru_id, u32 *val);
+	int (*set_log_entry_type)(struct device *dev, void *drv_data, int fru_id, u32 val);
+	int (*get_mode)(struct device *dev, void *drv_data, int fru_id, u32 *val);
+	int (*set_mode)(struct device *dev, void *drv_data, int fru_id, u32 val);
+	int (*reset)(struct device *dev, void *drv_data, int fru_id, u32 val);
+	int (*get_threshold)(struct device *dev, void *drv_data, int fru_id, u32 *threshold);
+	int (*set_threshold)(struct device *dev, void *drv_data, int fru_id, u32 threshold);
+};
+
+struct edac_ecs_ex_info {
+	u16 num_media_frus;
+};
+
+#if IS_ENABLED(CONFIG_EDAC_ECS)
+int edac_ecs_get_desc(struct device *ecs_dev,
+		      const struct attribute_group **attr_groups,
+		      u16 num_media_frus);
+#else
+static inline int edac_ecs_get_desc(struct device *ecs_dev,
+				    const struct attribute_group **attr_groups,
+				    u16 num_media_frus)
+{ return -EOPNOTSUPP; }
+#endif /* CONFIG_EDAC_ECS */
+
+enum edac_mem_repair_type {
+	EDAC_REPAIR_PPR,
+	EDAC_REPAIR_CACHELINE_SPARING,
+	EDAC_REPAIR_ROW_SPARING,
+	EDAC_REPAIR_BANK_SPARING,
+	EDAC_REPAIR_RANK_SPARING,
+	EDAC_REPAIR_MAX
+};
+
+extern const char * const edac_repair_type[];
+
+enum edac_mem_repair_cmd {
+	EDAC_DO_MEM_REPAIR = 1,
+};
+
+/**
+ * struct edac_mem_repair_ops - memory repair operations
+ * (all elements are optional except do_repair, set_hpa/set_dpa)
+ * @get_repair_type: get the memory repair type, listed in
+ *			 enum edac_mem_repair_function.
+ * @get_persist_mode: get the current persist mode.
+ *		      false - Soft repair type (temporary repair).
+ *		      true - Hard memory repair type (permanent repair).
+ * @set_persist_mode: set the persist mode of the memory repair instance.
+ * @get_repair_safe_when_in_use: get whether memory media is accessible and
+ *				 data is retained during repair operation.
+ * @get_hpa: get current host physical address (HPA) of memory to repair.
+ * @set_hpa: set host physical address (HPA) of memory to repair.
+ * @get_min_hpa: get the minimum supported host physical address (HPA).
+ * @get_max_hpa: get the maximum supported host physical address (HPA).
+ * @get_dpa: get current device physical address (DPA) of memory to repair.
+ * @set_dpa: set device physical address (DPA) of memory to repair.
+ *	     In some states of system configuration (e.g. before address decoders
+ *	     have been configured), memory devices (e.g. CXL) may not have an active
+ *	     mapping in the host physical address map. As such, the memory
+ *	     to repair must be identified by a device specific physical addressing
+ *	     scheme using a device physical address(DPA). The DPA and other control
+ *	     attributes to use for the repair operations will be presented in related
+ *	     error records.
+ * @get_min_dpa: get the minimum supported device physical address (DPA).
+ * @get_max_dpa: get the maximum supported device physical address (DPA).
+ * @get_nibble_mask: get current nibble mask of memory to repair.
+ * @set_nibble_mask: set nibble mask of memory to repair.
+ * @get_bank_group: get current bank group of memory to repair.
+ * @set_bank_group: set bank group of memory to repair.
+ * @get_bank: get current bank of memory to repair.
+ * @set_bank: set bank of memory to repair.
+ * @get_rank: get current rank of memory to repair.
+ * @set_rank: set rank of memory to repair.
+ * @get_row: get current row of memory to repair.
+ * @set_row: set row of memory to repair.
+ * @get_column: get current column of memory to repair.
+ * @set_column: set column of memory to repair.
+ * @get_channel: get current channel of memory to repair.
+ * @set_channel: set channel of memory to repair.
+ * @get_sub_channel: get current subchannel of memory to repair.
+ * @set_sub_channel: set subchannel of memory to repair.
+ * @do_repair: Issue memory repair operation for the HPA/DPA and
+ *	       other control attributes set for the memory to repair.
+ *
+ * All elements are optional except do_repair and at least one of set_hpa/set_dpa.
+ */
+struct edac_mem_repair_ops {
+	int (*get_repair_type)(struct device *dev, void *drv_data, const char **type);
+	int (*get_persist_mode)(struct device *dev, void *drv_data, bool *persist);
+	int (*set_persist_mode)(struct device *dev, void *drv_data, bool persist);
+	int (*get_repair_safe_when_in_use)(struct device *dev, void *drv_data, bool *safe);
+	int (*get_hpa)(struct device *dev, void *drv_data, u64 *hpa);
+	int (*set_hpa)(struct device *dev, void *drv_data, u64 hpa);
+	int (*get_min_hpa)(struct device *dev, void *drv_data, u64 *hpa);
+	int (*get_max_hpa)(struct device *dev, void *drv_data, u64 *hpa);
+	int (*get_dpa)(struct device *dev, void *drv_data, u64 *dpa);
+	int (*set_dpa)(struct device *dev, void *drv_data, u64 dpa);
+	int (*get_min_dpa)(struct device *dev, void *drv_data, u64 *dpa);
+	int (*get_max_dpa)(struct device *dev, void *drv_data, u64 *dpa);
+	int (*get_nibble_mask)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_nibble_mask)(struct device *dev, void *drv_data, u32 val);
+	int (*get_bank_group)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_bank_group)(struct device *dev, void *drv_data, u32 val);
+	int (*get_bank)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_bank)(struct device *dev, void *drv_data, u32 val);
+	int (*get_rank)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_rank)(struct device *dev, void *drv_data, u32 val);
+	int (*get_row)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_row)(struct device *dev, void *drv_data, u32 val);
+	int (*get_column)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_column)(struct device *dev, void *drv_data, u32 val);
+	int (*get_channel)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_channel)(struct device *dev, void *drv_data, u32 val);
+	int (*get_sub_channel)(struct device *dev, void *drv_data, u32 *val);
+	int (*set_sub_channel)(struct device *dev, void *drv_data, u32 val);
+	int (*do_repair)(struct device *dev, void *drv_data, u32 val);
+};
+
+#if IS_ENABLED(CONFIG_EDAC_MEM_REPAIR)
+int edac_mem_repair_get_desc(struct device *dev,
+			     const struct attribute_group **attr_groups,
+			     u8 instance);
+#else
+static inline int edac_mem_repair_get_desc(struct device *dev,
+					   const struct attribute_group **attr_groups,
+					   u8 instance)
+{ return -EOPNOTSUPP; }
+#endif /* CONFIG_EDAC_MEM_REPAIR */
+
+/* EDAC device feature information structure */
+struct edac_dev_data {
+	union {
+		const struct edac_scrub_ops *scrub_ops;
+		const struct edac_ecs_ops *ecs_ops;
+		const struct edac_mem_repair_ops *mem_repair_ops;
+	};
+	u8 instance;
+	void *private;
+};
+
+struct edac_dev_feat_ctx {
+	struct device dev;
+	void *private;
+	struct edac_dev_data *scrub;
+	struct edac_dev_data ecs;
+	struct edac_dev_data *mem_repair;
+};
+
+struct edac_dev_feature {
+	enum edac_dev_feat ft_type;
+	u8 instance;
+	union {
+		const struct edac_scrub_ops *scrub_ops;
+		const struct edac_ecs_ops *ecs_ops;
+		const struct edac_mem_repair_ops *mem_repair_ops;
+	};
+	void *ctx;
+	struct edac_ecs_ex_info ecs_info;
+};
+
+int edac_dev_register(struct device *parent, char *dev_name,
+		      void *parent_pvt_data, int num_features,
+		      const struct edac_dev_feature *ras_features);
 #endif /* _LINUX_EDAC_H_ */
diff --git a/include/linux/eeprom_93cx6.h b/include/linux/eeprom_93cx6.h
index c860c72a921d..3a485cc0e0fa 100644
--- a/include/linux/eeprom_93cx6.h
+++ b/include/linux/eeprom_93cx6.h
@@ -11,6 +11,8 @@
 	Supported chipsets: 93c46, 93c56 and 93c66.
  */
 
+#include <linux/bits.h>
+
 /*
  * EEPROM operation defines.
  */
@@ -34,6 +36,7 @@
  * @register_write(struct eeprom_93cx6 *eeprom): handler to
  * write to the eeprom register by using all reg_* fields.
  * @width: eeprom width, should be one of the PCI_EEPROM_WIDTH_* defines
+ * @quirks: eeprom or controller quirks
  * @drive_data: Set if we're driving the data line.
  * @reg_data_in: register field to indicate data input
  * @reg_data_out: register field to indicate data output
@@ -50,6 +53,9 @@ struct eeprom_93cx6 {
 	void (*register_write)(struct eeprom_93cx6 *eeprom);
 
 	int width;
+	unsigned int quirks;
+/* Some EEPROMs require an extra clock cycle before reading */
+#define PCI_EEPROM_QUIRK_EXTRA_READ_CYCLE	BIT(0)
 
 	char drive_data;
 	char reg_data_in;
@@ -71,3 +77,8 @@ extern void eeprom_93cx6_wren(struct eeprom_93cx6 *eeprom, bool enable);
 
 extern void eeprom_93cx6_write(struct eeprom_93cx6 *eeprom,
 			       u8 addr, u16 data);
+
+static inline bool has_quirk_extra_read_cycle(struct eeprom_93cx6 *eeprom)
+{
+	return eeprom->quirks & PCI_EEPROM_QUIRK_EXTRA_READ_CYCLE;
+}
diff --git a/include/linux/eeprom_93xx46.h b/include/linux/eeprom_93xx46.h
deleted file mode 100644
index 34c2175e6a1e..000000000000
--- a/include/linux/eeprom_93xx46.h
+++ /dev/null
@@ -1,32 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Module: eeprom_93xx46
- * platform description for 93xx46 EEPROMs.
- */
-#include <linux/gpio/consumer.h>
-
-struct eeprom_93xx46_platform_data {
-	unsigned char	flags;
-#define EE_ADDR8	0x01		/*  8 bit addr. cfg */
-#define EE_ADDR16	0x02		/* 16 bit addr. cfg */
-#define EE_READONLY	0x08		/* forbid writing */
-#define EE_SIZE1K	0x10		/* 1 kb of data, that is a 93xx46 */
-#define EE_SIZE2K	0x20		/* 2 kb of data, that is a 93xx56 */
-#define EE_SIZE4K	0x40		/* 4 kb of data, that is a 93xx66 */
-
-	unsigned int	quirks;
-/* Single word read transfers only; no sequential read. */
-#define EEPROM_93XX46_QUIRK_SINGLE_WORD_READ		(1 << 0)
-/* Instructions such as EWEN are (addrlen + 2) in length. */
-#define EEPROM_93XX46_QUIRK_INSTRUCTION_LENGTH		(1 << 1)
-/* Add extra cycle after address during a read */
-#define EEPROM_93XX46_QUIRK_EXTRA_READ_CYCLE		BIT(2)
-
-	/*
-	 * optional hooks to control additional logic
-	 * before and after spi transfer.
-	 */
-	void (*prepare)(void *);
-	void (*finish)(void *);
-	struct gpio_desc *select;
-};
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7aa62c92185f..2a43094e23f7 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -24,10 +24,11 @@
 #include <linux/range.h>
 #include <linux/reboot.h>
 #include <linux/uuid.h>
-#include <linux/screen_info.h>
 
 #include <asm/page.h>
 
+struct screen_info;
+
 #define EFI_SUCCESS		0
 #define EFI_LOAD_ERROR		( 1 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_INVALID_PARAMETER	( 2 | (1UL << (BITS_PER_LONG-1)))
@@ -39,6 +40,7 @@
 #define EFI_WRITE_PROTECTED	( 8 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_OUT_OF_RESOURCES	( 9 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_NOT_FOUND		(14 | (1UL << (BITS_PER_LONG-1)))
+#define EFI_ACCESS_DENIED	(15 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_TIMEOUT		(18 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_ABORTED		(21 | (1UL << (BITS_PER_LONG-1)))
 #define EFI_SECURITY_VIOLATION	(26 | (1UL << (BITS_PER_LONG-1)))
@@ -72,10 +74,10 @@ typedef void *efi_handle_t;
  */
 typedef guid_t efi_guid_t __aligned(__alignof__(u32));
 
-#define EFI_GUID(a, b, c, d...) (efi_guid_t){ {					\
+#define EFI_GUID(a, b, c, d...) ((efi_guid_t){ {				\
 	(a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff,	\
 	(b) & 0xff, ((b) >> 8) & 0xff,						\
-	(c) & 0xff, ((c) >> 8) & 0xff, d } }
+	(c) & 0xff, ((c) >> 8) & 0xff, d } })
 
 /*
  * Generic EFI table header
@@ -108,24 +110,26 @@ typedef	struct {
 #define EFI_MEMORY_MAPPED_IO_PORT_SPACE	12
 #define EFI_PAL_CODE			13
 #define EFI_PERSISTENT_MEMORY		14
-#define EFI_MAX_MEMORY_TYPE		15
+#define EFI_UNACCEPTED_MEMORY		15
+#define EFI_MAX_MEMORY_TYPE		16
 
 /* Attribute values: */
-#define EFI_MEMORY_UC		((u64)0x0000000000000001ULL)	/* uncached */
-#define EFI_MEMORY_WC		((u64)0x0000000000000002ULL)	/* write-coalescing */
-#define EFI_MEMORY_WT		((u64)0x0000000000000004ULL)	/* write-through */
-#define EFI_MEMORY_WB		((u64)0x0000000000000008ULL)	/* write-back */
-#define EFI_MEMORY_UCE		((u64)0x0000000000000010ULL)	/* uncached, exported */
-#define EFI_MEMORY_WP		((u64)0x0000000000001000ULL)	/* write-protect */
-#define EFI_MEMORY_RP		((u64)0x0000000000002000ULL)	/* read-protect */
-#define EFI_MEMORY_XP		((u64)0x0000000000004000ULL)	/* execute-protect */
-#define EFI_MEMORY_NV		((u64)0x0000000000008000ULL)	/* non-volatile */
-#define EFI_MEMORY_MORE_RELIABLE \
-				((u64)0x0000000000010000ULL)	/* higher reliability */
-#define EFI_MEMORY_RO		((u64)0x0000000000020000ULL)	/* read-only */
-#define EFI_MEMORY_SP		((u64)0x0000000000040000ULL)	/* soft reserved */
-#define EFI_MEMORY_CPU_CRYPTO	((u64)0x0000000000080000ULL)	/* supports encryption */
-#define EFI_MEMORY_RUNTIME	((u64)0x8000000000000000ULL)	/* range requires runtime mapping */
+#define EFI_MEMORY_UC			BIT_ULL(0)	/* uncached */
+#define EFI_MEMORY_WC			BIT_ULL(1)	/* write-coalescing */
+#define EFI_MEMORY_WT			BIT_ULL(2)	/* write-through */
+#define EFI_MEMORY_WB			BIT_ULL(3)	/* write-back */
+#define EFI_MEMORY_UCE			BIT_ULL(4)	/* uncached, exported */
+#define EFI_MEMORY_WP			BIT_ULL(12)	/* write-protect */
+#define EFI_MEMORY_RP			BIT_ULL(13)	/* read-protect */
+#define EFI_MEMORY_XP			BIT_ULL(14)	/* execute-protect */
+#define EFI_MEMORY_NV			BIT_ULL(15)	/* non-volatile */
+#define EFI_MEMORY_MORE_RELIABLE	BIT_ULL(16)	/* higher reliability */
+#define EFI_MEMORY_RO			BIT_ULL(17)	/* read-only */
+#define EFI_MEMORY_SP			BIT_ULL(18)	/* soft reserved */
+#define EFI_MEMORY_CPU_CRYPTO		BIT_ULL(19)	/* supports encryption */
+#define EFI_MEMORY_HOT_PLUGGABLE	BIT_ULL(20)	/* supports unplugging at runtime */
+#define EFI_MEMORY_RUNTIME		BIT_ULL(63)	/* range requires runtime mapping */
+
 #define EFI_MEMORY_DESCRIPTOR_VERSION	1
 
 #define EFI_PAGE_SHIFT		12
@@ -286,7 +290,7 @@ typedef efi_status_t efi_get_variable_t (efi_char16_t *name, efi_guid_t *vendor,
 					 unsigned long *data_size, void *data);
 typedef efi_status_t efi_get_next_variable_t (unsigned long *name_size, efi_char16_t *name,
 					      efi_guid_t *vendor);
-typedef efi_status_t efi_set_variable_t (efi_char16_t *name, efi_guid_t *vendor, 
+typedef efi_status_t efi_set_variable_t (efi_char16_t *name, efi_guid_t *vendor,
 					 u32 attr, unsigned long data_size,
 					 void *data);
 typedef efi_status_t efi_get_next_high_mono_count_t (u32 *count);
@@ -356,14 +360,10 @@ void efi_native_runtime_setup(void);
  * where the UEFI SPEC breaks the line.
  */
 #define NULL_GUID				EFI_GUID(0x00000000, 0x0000, 0x0000,  0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00)
-#define MPS_TABLE_GUID				EFI_GUID(0xeb9d2d2f, 0x2d88, 0x11d3,  0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 #define ACPI_TABLE_GUID				EFI_GUID(0xeb9d2d30, 0x2d88, 0x11d3,  0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 #define ACPI_20_TABLE_GUID			EFI_GUID(0x8868e871, 0xe4f1, 0x11d3,  0xbc, 0x22, 0x00, 0x80, 0xc7, 0x3c, 0x88, 0x81)
 #define SMBIOS_TABLE_GUID			EFI_GUID(0xeb9d2d31, 0x2d88, 0x11d3,  0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 #define SMBIOS3_TABLE_GUID			EFI_GUID(0xf2fd1544, 0x9794, 0x4a2c,  0x99, 0x2e, 0xe5, 0xbb, 0xcf, 0x20, 0xe3, 0x94)
-#define SAL_SYSTEM_TABLE_GUID			EFI_GUID(0xeb9d2d32, 0x2d88, 0x11d3,  0x9a, 0x16, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
-#define HCDP_TABLE_GUID				EFI_GUID(0xf951938d, 0x620b, 0x42ef,  0x82, 0x79, 0xa8, 0x4b, 0x79, 0x61, 0x78, 0x98)
-#define UGA_IO_PROTOCOL_GUID			EFI_GUID(0x61a4d49e, 0x6f68, 0x4f1b,  0xb9, 0x22, 0xa8, 0x6e, 0xed, 0x0b, 0x07, 0xa2)
 #define EFI_GLOBAL_VARIABLE_GUID		EFI_GUID(0x8be4df61, 0x93ca, 0x11d2,  0xaa, 0x0d, 0x00, 0xe0, 0x98, 0x03, 0x2b, 0x8c)
 #define UV_SYSTEM_TABLE_GUID			EFI_GUID(0x3b13a7d4, 0x633e, 0x11dd,  0x93, 0xec, 0xda, 0x25, 0x56, 0xd8, 0x95, 0x93)
 #define LINUX_EFI_CRASH_GUID			EFI_GUID(0xcfc8fc79, 0xbe2e, 0x4ddc,  0x97, 0xf0, 0x9f, 0x98, 0xbf, 0xe2, 0x98, 0xa0)
@@ -373,19 +373,21 @@ void efi_native_runtime_setup(void);
 #define EFI_DEVICE_PATH_TO_TEXT_PROTOCOL_GUID	EFI_GUID(0x8b843e20, 0x8132, 0x4852,  0x90, 0xcc, 0x55, 0x1a, 0x4e, 0x4a, 0x7f, 0x1c)
 #define EFI_DEVICE_PATH_FROM_TEXT_PROTOCOL_GUID	EFI_GUID(0x05c99a21, 0xc70f, 0x4ad2,  0x8a, 0x5f, 0x35, 0xdf, 0x33, 0x43, 0xf5, 0x1e)
 #define EFI_GRAPHICS_OUTPUT_PROTOCOL_GUID	EFI_GUID(0x9042a9de, 0x23dc, 0x4a38,  0x96, 0xfb, 0x7a, 0xde, 0xd0, 0x80, 0x51, 0x6a)
-#define EFI_UGA_PROTOCOL_GUID			EFI_GUID(0x982c298b, 0xf4fa, 0x41cb,  0xb8, 0x38, 0x77, 0xaa, 0x68, 0x8f, 0xb8, 0x39)
+#define EFI_EDID_DISCOVERED_PROTOCOL_GUID	EFI_GUID(0x1c0c34f6, 0xd380, 0x41fa,  0xa0, 0x49, 0x8a, 0xd0, 0x6c, 0x1a, 0x66, 0xaa)
+#define EFI_EDID_ACTIVE_PROTOCOL_GUID		EFI_GUID(0xbd8c1056, 0x9f36, 0x44ec,  0x92, 0xa8, 0xa6, 0x33, 0x7f, 0x81, 0x79, 0x86)
 #define EFI_PCI_IO_PROTOCOL_GUID		EFI_GUID(0x4cf5b200, 0x68b8, 0x4ca5,  0x9e, 0xec, 0xb2, 0x3e, 0x3f, 0x50, 0x02, 0x9a)
 #define EFI_FILE_INFO_ID			EFI_GUID(0x09576e92, 0x6d3f, 0x11d2,  0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 #define EFI_SYSTEM_RESOURCE_TABLE_GUID		EFI_GUID(0xb122a263, 0x3661, 0x4f68,  0x99, 0x29, 0x78, 0xf8, 0xb0, 0xd6, 0x21, 0x80)
 #define EFI_FILE_SYSTEM_GUID			EFI_GUID(0x964e5b22, 0x6459, 0x11d2,  0x8e, 0x39, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 #define DEVICE_TREE_GUID			EFI_GUID(0xb1b621d5, 0xf19c, 0x41a5,  0x83, 0x0b, 0xd9, 0x15, 0x2c, 0x69, 0xaa, 0xe0)
-#define EFI_PROPERTIES_TABLE_GUID		EFI_GUID(0x880aaca3, 0x4adc, 0x4a04,  0x90, 0x79, 0xb7, 0x47, 0x34, 0x08, 0x25, 0xe5)
 #define EFI_RNG_PROTOCOL_GUID			EFI_GUID(0x3152bca5, 0xeade, 0x433d,  0x86, 0x2e, 0xc0, 0x1c, 0xdc, 0x29, 0x1f, 0x44)
 #define EFI_RNG_ALGORITHM_RAW			EFI_GUID(0xe43176d7, 0xb6e8, 0x4827,  0xb7, 0x84, 0x7f, 0xfd, 0xc4, 0xb6, 0x85, 0x61)
 #define EFI_MEMORY_ATTRIBUTES_TABLE_GUID	EFI_GUID(0xdcfa911d, 0x26eb, 0x469f,  0xa2, 0x20, 0x38, 0xb7, 0xdc, 0x46, 0x12, 0x20)
 #define EFI_CONSOLE_OUT_DEVICE_GUID		EFI_GUID(0xd3b36f2c, 0xd551, 0x11d4,  0x9a, 0x46, 0x00, 0x90, 0x27, 0x3f, 0xc1, 0x4d)
 #define APPLE_PROPERTIES_PROTOCOL_GUID		EFI_GUID(0x91bd12fe, 0xf6c3, 0x44fb,  0xa5, 0xb7, 0x51, 0x22, 0xab, 0x30, 0x3a, 0xe0)
+#define APPLE_SET_OS_PROTOCOL_GUID		EFI_GUID(0xc5c5da95, 0x7d5c, 0x45e6,  0xb2, 0xf1, 0x3f, 0xd5, 0x2b, 0xb1, 0x00, 0x77)
 #define EFI_TCG2_PROTOCOL_GUID			EFI_GUID(0x607f766c, 0x7455, 0x42be,  0x93, 0x0b, 0xe4, 0xd7, 0x6d, 0xb2, 0x72, 0x0f)
+#define EFI_TCG2_FINAL_EVENTS_TABLE_GUID	EFI_GUID(0x1e2ed096, 0x30e2, 0x4254,  0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25)
 #define EFI_LOAD_FILE_PROTOCOL_GUID		EFI_GUID(0x56ec3091, 0x954c, 0x11d2,  0x8e, 0x3f, 0x00, 0xa0, 0xc9, 0x69, 0x72, 0x3b)
 #define EFI_LOAD_FILE2_PROTOCOL_GUID		EFI_GUID(0x4006c0c1, 0xfcb3, 0x403e,  0x99, 0x6d, 0x4a, 0x6c, 0x87, 0x24, 0xe0, 0x6d)
 #define EFI_RT_PROPERTIES_TABLE_GUID		EFI_GUID(0xeb66918a, 0x7eef, 0x402a,  0x84, 0x2e, 0x93, 0x1d, 0x21, 0xc3, 0x8a, 0xe9)
@@ -400,6 +402,8 @@ void efi_native_runtime_setup(void);
 #define EFI_CERT_X509_GUID			EFI_GUID(0xa5c059a1, 0x94e4, 0x4aa7, 0x87, 0xb5, 0xab, 0x15, 0x5c, 0x2b, 0xf0, 0x72)
 #define EFI_CERT_X509_SHA256_GUID		EFI_GUID(0x3bd2a492, 0x96c0, 0x4079, 0xb4, 0x20, 0xfc, 0xf9, 0x8e, 0xf1, 0x03, 0xed)
 #define EFI_CC_BLOB_GUID			EFI_GUID(0x067b1f5f, 0xcf26, 0x44c5, 0x85, 0x54, 0x93, 0xd7, 0x77, 0x91, 0x2d, 0x42)
+#define EFI_CC_MEASUREMENT_PROTOCOL_GUID	EFI_GUID(0x96751a3d, 0x72f4, 0x41a6, 0xa7, 0x94, 0xed, 0x5d, 0x0e, 0x67, 0xae, 0x6b)
+#define EFI_CC_FINAL_EVENTS_TABLE_GUID		EFI_GUID(0xdd4a4648, 0x2de7, 0x4665, 0x96, 0x4d, 0x21, 0xd9, 0xef, 0x5f, 0xb4, 0x46)
 
 /*
  * This GUID is used to pass to the kernel proper the struct screen_info
@@ -411,12 +415,12 @@ void efi_native_runtime_setup(void);
 #define LINUX_EFI_LOADER_ENTRY_GUID		EFI_GUID(0x4a67b082, 0x0a4c, 0x41cf,  0xb6, 0xc7, 0x44, 0x0b, 0x29, 0xbb, 0x8c, 0x4f)
 #define LINUX_EFI_RANDOM_SEED_TABLE_GUID	EFI_GUID(0x1ce1e5bc, 0x7ceb, 0x42f2,  0x81, 0xe5, 0x8a, 0xad, 0xf1, 0x80, 0xf5, 0x7b)
 #define LINUX_EFI_TPM_EVENT_LOG_GUID		EFI_GUID(0xb7799cb0, 0xeca2, 0x4943,  0x96, 0x67, 0x1f, 0xae, 0x07, 0xb7, 0x47, 0xfa)
-#define LINUX_EFI_TPM_FINAL_LOG_GUID		EFI_GUID(0x1e2ed096, 0x30e2, 0x4254,  0xbd, 0x89, 0x86, 0x3b, 0xbe, 0xf8, 0x23, 0x25)
 #define LINUX_EFI_MEMRESERVE_TABLE_GUID		EFI_GUID(0x888eb0c6, 0x8ede, 0x4ff5,  0xa8, 0xf0, 0x9a, 0xee, 0x5c, 0xb9, 0x77, 0xc2)
 #define LINUX_EFI_INITRD_MEDIA_GUID		EFI_GUID(0x5568e427, 0x68fc, 0x4f3d,  0xac, 0x74, 0xca, 0x55, 0x52, 0x31, 0xcc, 0x68)
 #define LINUX_EFI_MOK_VARIABLE_TABLE_GUID	EFI_GUID(0xc451ed2b, 0x9694, 0x45d3,  0xba, 0xba, 0xed, 0x9f, 0x89, 0x88, 0xa3, 0x89)
 #define LINUX_EFI_COCO_SECRET_AREA_GUID		EFI_GUID(0xadf956ad, 0xe98c, 0x484c,  0xae, 0x11, 0xb5, 0x1c, 0x7d, 0x33, 0x64, 0x47)
 #define LINUX_EFI_BOOT_MEMMAP_GUID		EFI_GUID(0x800f683f, 0xd08b, 0x423a,  0xa2, 0x93, 0x96, 0x5c, 0x3c, 0x6f, 0xe2, 0xb4)
+#define LINUX_EFI_UNACCEPTED_MEM_TABLE_GUID	EFI_GUID(0xd5d1de3c, 0x105c, 0x44f9,  0x9e, 0xa9, 0xbc, 0xef, 0x98, 0x12, 0x00, 0x31)
 
 #define RISCV_EFI_BOOT_PROTOCOL_GUID		EFI_GUID(0xccd15fec, 0x6f73, 0x4eec,  0x83, 0x95, 0x3e, 0x69, 0xe4, 0xb9, 0x40, 0xbf)
 
@@ -435,6 +439,10 @@ void efi_native_runtime_setup(void);
 #define DELLEMC_EFI_RCI2_TABLE_GUID		EFI_GUID(0x2d9f28a2, 0xa886, 0x456a,  0x97, 0xa8, 0xf1, 0x1e, 0xf2, 0x4f, 0xf4, 0x55)
 #define AMD_SEV_MEM_ENCRYPT_GUID		EFI_GUID(0x0cf29b71, 0x9e51, 0x433a,  0xa3, 0xb7, 0x81, 0xf3, 0xab, 0x16, 0xb8, 0x75)
 
+/* OVMF protocol GUIDs */
+#define OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID	EFI_GUID(0xc5a010fe, 0x38a7, 0x4531,  0x8a, 0x4a, 0x05, 0x00, 0xd2, 0xfd, 0x16, 0x49)
+#define OVMF_MEMORY_LOG_TABLE_GUID		EFI_GUID(0x95305139, 0xb20f, 0x4723,  0x84, 0x25, 0x62, 0x7c, 0x88, 0x8f, 0xf1, 0x21)
+
 typedef struct {
 	efi_guid_t guid;
 	u64 table;
@@ -534,6 +542,14 @@ struct efi_boot_memmap {
 	efi_memory_desc_t	map[];
 };
 
+struct efi_unaccepted_memory {
+	u32 version;
+	u32 unit_size;
+	u64 phys_base;
+	u64 size;
+	unsigned long bitmap[];
+};
+
 /*
  * Architecture independent structure for describing a memory map for the
  * benefit of efi_memmap_init_early(), and for passing context between
@@ -566,15 +582,6 @@ struct efi_mem_range {
 };
 
 typedef struct {
-	u32 version;
-	u32 length;
-	u64 memory_protection_attribute;
-} efi_properties_table_t;
-
-#define EFI_PROPERTIES_TABLE_VERSION	0x00010000
-#define EFI_PROPERTIES_RUNTIME_MEMORY_PROTECTION_NON_EXECUTABLE_PE_DATA	0x1
-
-typedef struct {
 	u16 version;
 	u16 length;
 	u32 runtime_services_supported;
@@ -593,7 +600,11 @@ typedef struct {
 	u32 num_entries;
 	u32 desc_size;
 	u32 flags;
-	efi_memory_desc_t entry[0];
+	/*
+	 * There are @num_entries following, each of size @desc_size bytes,
+	 * including an efi_memory_desc_t header. See efi_memdesc_ptr().
+	 */
+	efi_memory_desc_t entry[];
 } efi_memory_attributes_table_t;
 
 typedef struct {
@@ -634,8 +645,10 @@ extern struct efi {
 	unsigned long			esrt;			/* ESRT table */
 	unsigned long			tpm_log;		/* TPM2 Event Log table */
 	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
+	unsigned long                   ovmf_debug_log;
 	unsigned long			mokvar_table;		/* MOK variable config table */
 	unsigned long			coco_secret;		/* Confidential computing secret table */
+	unsigned long			unaccepted;		/* Unaccepted memory table */
 
 	efi_get_time_t			*get_time;
 	efi_set_time_t			*set_time;
@@ -679,6 +692,11 @@ extern struct efi {
 
 extern struct mm_struct efi_mm;
 
+static inline bool mm_is_efi(struct mm_struct *mm)
+{
+	return IS_ENABLED(CONFIG_EFI) && mm == &efi_mm;
+}
+
 static inline int
 efi_guidcmp (efi_guid_t left, efi_guid_t right)
 {
@@ -712,7 +730,6 @@ static inline efi_status_t efi_query_variable_store(u32 attributes,
 	return EFI_SUCCESS;
 }
 #endif
-extern void __iomem *efi_lookup_mapped_addr(u64 phys_addr);
 
 extern int __init __efi_memmap_init(struct efi_memory_map_data *data);
 extern int __init efi_memmap_init_early(struct efi_memory_map_data *data);
@@ -740,8 +757,6 @@ extern int efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md);
 extern int __efi_mem_desc_lookup(u64 phys_addr, efi_memory_desc_t *out_md);
 extern void efi_mem_reserve(phys_addr_t addr, u64 size);
 extern int efi_mem_reserve_persistent(phys_addr_t addr, u64 size);
-extern void efi_initialize_iomem_resources(struct resource *code_resource,
-		struct resource *data_resource, struct resource *bss_resource);
 extern u64 efi_get_fdt_params(struct efi_memory_map_data *data);
 extern struct kobject *efi_kobj;
 
@@ -759,12 +774,12 @@ extern unsigned long efi_mem_attr_table;
  */
 typedef int (*efi_memattr_perm_setter)(struct mm_struct *, efi_memory_desc_t *, bool);
 
-extern int efi_memattr_init(void);
+extern void efi_memattr_init(void);
 extern int efi_memattr_apply_permissions(struct mm_struct *mm,
 					 efi_memattr_perm_setter fn);
 
 /*
- * efi_early_memdesc_ptr - get the n-th EFI memmap descriptor
+ * efi_memdesc_ptr - get the n-th EFI memmap descriptor
  * @map: the start of efi memmap
  * @desc_size: the size of space for each EFI memmap descriptor
  * @n: the index of efi memmap descriptor
@@ -782,7 +797,7 @@ extern int efi_memattr_apply_permissions(struct mm_struct *mm,
  * during bootup since for_each_efi_memory_desc_xxx() is available after the
  * kernel initializes the EFI subsystem to set up struct efi_memory_map.
  */
-#define efi_early_memdesc_ptr(map, desc_size, n)			\
+#define efi_memdesc_ptr(map, desc_size, n)			\
 	(efi_memory_desc_t *)((void *)(map) + ((n) * (desc_size)))
 
 /* Iterate through an efi_memory_map */
@@ -837,10 +852,6 @@ static inline int efi_range_is_wc(unsigned long start, unsigned long len)
 	return 1;
 }
 
-#ifdef CONFIG_EFI_PCDP
-extern int __init efi_setup_pcdp_console(char *);
-#endif
-
 /*
  * We play games with efi_enabled so that the compiler will, if
  * possible, remove EFI-related code altogether.
@@ -853,10 +864,9 @@ extern int __init efi_setup_pcdp_console(char *);
 #define EFI_PARAVIRT		6	/* Access is via a paravirt interface */
 #define EFI_ARCH_1		7	/* First arch-specific bit */
 #define EFI_DBG			8	/* Print additional debug info at runtime */
-#define EFI_NX_PE_DATA		9	/* Can runtime data regions be mapped non-executable? */
-#define EFI_MEM_ATTR		10	/* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
-#define EFI_MEM_NO_SOFT_RESERVE	11	/* Is the kernel configured to ignore soft reservations? */
-#define EFI_PRESERVE_BS_REGIONS	12	/* Are EFI boot-services memory segments available? */
+#define EFI_MEM_ATTR		9	/* Did firmware publish an EFI_MEMORY_ATTRIBUTES table? */
+#define EFI_MEM_NO_SOFT_RESERVE	10	/* Is the kernel configured to ignore soft reservations? */
+#define EFI_PRESERVE_BS_REGIONS	11	/* Are EFI boot-services memory segments available? */
 
 #ifdef CONFIG_EFI
 /*
@@ -1042,6 +1052,7 @@ struct efivar_operations {
 	efi_set_variable_t *set_variable;
 	efi_set_variable_t *set_variable_nonblocking;
 	efi_query_variable_store_t *query_variable_store;
+	efi_query_variable_info_t *query_variable_info;
 };
 
 struct efivars {
@@ -1049,13 +1060,18 @@ struct efivars {
 	const struct efivar_operations *ops;
 };
 
+#ifdef CONFIG_X86
+u64 __attribute_const__ efivar_reserved_space(void);
+#else
+static inline u64 efivar_reserved_space(void) { return 0; }
+#endif
+
 /*
- * The maximum size of VariableName + Data = 1024
- * Therefore, it's reasonable to save that much
- * space in each part of the structure,
- * and we use a page for reading/writing.
+ * There is no actual upper limit specified for the variable name size.
+ *
+ * This limit exists only for practical purposes, since name conversions
+ * are bounds-checked and name data is occasionally stored in-line.
  */
-
 #define EFI_VAR_NAME_LEN	1024
 
 int efivars_register(struct efivars *efivars,
@@ -1087,6 +1103,10 @@ efi_status_t efivar_set_variable_locked(efi_char16_t *name, efi_guid_t *vendor,
 efi_status_t efivar_set_variable(efi_char16_t *name, efi_guid_t *vendor,
 				 u32 attr, unsigned long data_size, void *data);
 
+efi_status_t efivar_query_variable_info(u32 attr, u64 *storage_space,
+					u64 *remaining_space,
+					u64 *max_variable_size);
+
 #if IS_ENABLED(CONFIG_EFI_CAPSULE_LOADER)
 extern bool efi_capsule_pending(int *reset_type);
 
@@ -1105,9 +1125,11 @@ extern bool efi_runtime_disabled(void);
 static inline bool efi_runtime_disabled(void) { return true; }
 #endif
 
-extern void efi_call_virt_check_flags(unsigned long flags, const char *call);
+extern void efi_call_virt_check_flags(unsigned long flags, const void *caller);
 extern unsigned long efi_call_virt_save_flags(void);
 
+void efi_runtime_assert_lock_held(void);
+
 enum efi_secureboot_mode {
 	efi_secureboot_mode_unset,
 	efi_secureboot_mode_unknown,
@@ -1146,8 +1168,7 @@ static inline void efi_check_for_embedded_firmwares(void) { }
 #define arch_efi_call_virt(p, f, args...)	((p)->f(args))
 
 /*
- * Arch code can implement the following three template macros, avoiding
- * reptition for the void/non-void return cases of {__,}efi_call_virt():
+ * Arch code must implement the following three routines:
  *
  *  * arch_efi_call_virt_setup()
  *
@@ -1156,9 +1177,8 @@ static inline void efi_check_for_embedded_firmwares(void) { }
  *
  *  * arch_efi_call_virt()
  *
- *    Performs the call. The last expression in the macro must be the call
- *    itself, allowing the logic to be shared by the void and non-void
- *    cases.
+ *    Performs the call. This routine takes a variable number of arguments so
+ *    it must be implemented as a variadic preprocessor macro.
  *
  *  * arch_efi_call_virt_teardown()
  *
@@ -1167,33 +1187,20 @@ static inline void efi_check_for_embedded_firmwares(void) { }
 
 #define efi_call_virt_pointer(p, f, args...)				\
 ({									\
-	efi_status_t __s;						\
+	typeof((p)->f(args)) __s;					\
 	unsigned long __flags;						\
 									\
 	arch_efi_call_virt_setup();					\
 									\
 	__flags = efi_call_virt_save_flags();				\
 	__s = arch_efi_call_virt(p, f, args);				\
-	efi_call_virt_check_flags(__flags, __stringify(f));		\
+	efi_call_virt_check_flags(__flags, NULL);			\
 									\
 	arch_efi_call_virt_teardown();					\
 									\
 	__s;								\
 })
 
-#define __efi_call_virt_pointer(p, f, args...)				\
-({									\
-	unsigned long __flags;						\
-									\
-	arch_efi_call_virt_setup();					\
-									\
-	__flags = efi_call_virt_save_flags();				\
-	arch_efi_call_virt(p, f, args);					\
-	efi_call_virt_check_flags(__flags, __stringify(f));		\
-									\
-	arch_efi_call_virt_teardown();					\
-})
-
 #define EFI_RANDOM_SEED_SIZE		32U // BLAKE2S_HASH_SIZE
 
 struct linux_efi_random_seed {
@@ -1219,6 +1226,10 @@ extern int efi_tpm_final_log_size;
 
 extern unsigned long rci2_table_phys;
 
+efi_status_t
+efi_call_acpi_prm_handler(efi_status_t (__efiapi *handler_addr)(u64, void *),
+			  u64 param_buffer_addr, void *context);
+
 /*
  * efi_runtime_service() function identifiers.
  * "NONE" is used by efi_recover_from_page_fault() to check if the page
@@ -1238,25 +1249,26 @@ enum efi_rts_ids {
 	EFI_RESET_SYSTEM,
 	EFI_UPDATE_CAPSULE,
 	EFI_QUERY_CAPSULE_CAPS,
+	EFI_ACPI_PRM_HANDLER,
 };
 
+union efi_rts_args;
+
 /*
  * efi_runtime_work:	Details of EFI Runtime Service work
- * @arg<1-5>:		EFI Runtime Service function arguments
+ * @args:		Pointer to union describing the arguments
  * @status:		Status of executing EFI Runtime Service
  * @efi_rts_id:		EFI Runtime Service function identifier
  * @efi_rts_comp:	Struct used for handling completions
+ * @caller:		The caller of the runtime service
  */
 struct efi_runtime_work {
-	void *arg1;
-	void *arg2;
-	void *arg3;
-	void *arg4;
-	void *arg5;
-	efi_status_t status;
-	struct work_struct work;
-	enum efi_rts_ids efi_rts_id;
-	struct completion efi_rts_comp;
+	union efi_rts_args	*args;
+	efi_status_t		status;
+	struct work_struct	work;
+	enum efi_rts_ids	efi_rts_id;
+	struct completion	efi_rts_comp;
+	const void		*caller;
 };
 
 extern struct efi_runtime_work efi_rts_work;
@@ -1279,8 +1291,6 @@ struct linux_efi_memreserve {
 
 void __init efi_arch_mem_reserve(phys_addr_t addr, u64 size);
 
-char *efi_systab_show_arch(char *str);
-
 /*
  * The LINUX_EFI_MOK_VARIABLE_TABLE_GUID config table can be provided
  * to the kernel by an EFI boot loader. The table contains a packed
@@ -1330,7 +1340,7 @@ struct linux_efi_initrd {
 
 bool xen_efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table);
 
-static inline
+static __always_inline
 bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 {
 	if (!IS_ENABLED(CONFIG_XEN_EFI))
@@ -1338,4 +1348,19 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 	return xen_efi_config_table_is_usable(guid, table);
 }
 
+umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n);
+
+int ovmf_log_probe(unsigned long ovmf_debug_log_table);
+
+/*
+ * efivar ops event type
+ */
+#define EFIVAR_OPS_RDONLY 0
+#define EFIVAR_OPS_RDWR 1
+
+extern struct blocking_notifier_head efivar_ops_nh;
+
+void efivars_generic_ops_register(void);
+void efivars_generic_ops_unregister(void);
+
 #endif /* _LINUX_EFI_H */
diff --git a/include/linux/ehl_pse_io_aux.h b/include/linux/ehl_pse_io_aux.h
new file mode 100644
index 000000000000..afb8587ee5fb
--- /dev/null
+++ b/include/linux/ehl_pse_io_aux.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel Elkhart Lake PSE I/O Auxiliary Device
+ *
+ * Copyright (c) 2025 Intel Corporation.
+ *
+ * Author: Raag Jadav <raag.jadav@intel.com>
+ */
+
+#ifndef _EHL_PSE_IO_AUX_H_
+#define _EHL_PSE_IO_AUX_H_
+
+#include <linux/ioport.h>
+
+#define EHL_PSE_IO_NAME		"ehl_pse_io"
+#define EHL_PSE_GPIO_NAME	"gpio"
+#define EHL_PSE_TIO_NAME	"pps_tio"
+
+struct ehl_pse_io_data {
+	struct resource mem;
+	int irq;
+};
+
+#endif /* _EHL_PSE_IO_AUX_H_ */
diff --git a/include/linux/eisa.h b/include/linux/eisa.h
index b012e30afebd..cf55630b595b 100644
--- a/include/linux/eisa.h
+++ b/include/linux/eisa.h
@@ -28,6 +28,9 @@
 #define EISA_CONFIG_ENABLED         1
 #define EISA_CONFIG_FORCED          2
 
+/* Chosen to hold the longest string in eisa.ids. */
+#define EISA_DEVICE_INFO_NAME_SIZE 74
+
 /* There is not much we can say about an EISA device, apart from
  * signature, slot number, and base address. dma_mask is set by
  * default to parent device mask..*/
@@ -41,7 +44,7 @@ struct eisa_device {
 	u64                   dma_mask;
 	struct device         dev; /* generic device */
 #ifdef CONFIG_EISA_NAMES
-	char		      pretty_name[50];
+	char		      pretty_name[EISA_DEVICE_INFO_NAME_SIZE];
 #endif
 };
 
@@ -60,12 +63,12 @@ struct eisa_driver {
 	struct device_driver         driver;
 };
 
-#define to_eisa_driver(drv) container_of(drv,struct eisa_driver, driver)
+#define to_eisa_driver(drv) container_of_const(drv,struct eisa_driver, driver)
 
 /* These external functions are only available when EISA support is enabled. */
 #ifdef CONFIG_EISA
 
-extern struct bus_type eisa_bus_type;
+extern const struct bus_type eisa_bus_type;
 int eisa_driver_register (struct eisa_driver *edrv);
 void eisa_driver_unregister (struct eisa_driver *edrv);
 
diff --git a/include/linux/elf-fdpic.h b/include/linux/elf-fdpic.h
index 3bea95a1af53..e533f4513194 100644
--- a/include/linux/elf-fdpic.h
+++ b/include/linux/elf-fdpic.h
@@ -10,13 +10,25 @@
 
 #include <uapi/linux/elf-fdpic.h>
 
+#if ELF_CLASS == ELFCLASS32
+#define Elf_Sword			Elf32_Sword
+#define elf_fdpic_loadseg		elf32_fdpic_loadseg
+#define elf_fdpic_loadmap		elf32_fdpic_loadmap
+#define ELF_FDPIC_LOADMAP_VERSION	ELF32_FDPIC_LOADMAP_VERSION
+#else
+#define Elf_Sword			Elf64_Sxword
+#define elf_fdpic_loadmap		elf64_fdpic_loadmap
+#define elf_fdpic_loadseg		elf64_fdpic_loadseg
+#define ELF_FDPIC_LOADMAP_VERSION	ELF64_FDPIC_LOADMAP_VERSION
+#endif
+
 /*
  * binfmt binary parameters structure
  */
 struct elf_fdpic_params {
 	struct elfhdr			hdr;		/* ref copy of ELF header */
 	struct elf_phdr			*phdrs;		/* ref copy of PT_PHDR table */
-	struct elf32_fdpic_loadmap	*loadmap;	/* loadmap to be passed to userspace */
+	struct elf_fdpic_loadmap	*loadmap;	/* loadmap to be passed to userspace */
 	unsigned long			elfhdr_addr;	/* mapped ELF header user address */
 	unsigned long			ph_addr;	/* mapped PT_PHDR user address */
 	unsigned long			map_addr;	/* mapped loadmap user address */
diff --git a/include/linux/elf.h b/include/linux/elf.h
index c9a46c4e183b..5c402788da19 100644
--- a/include/linux/elf.h
+++ b/include/linux/elf.h
@@ -65,7 +65,7 @@ extern Elf64_Dyn _DYNAMIC [];
 struct file;
 struct coredump_params;
 
-#ifndef ARCH_HAVE_EXTRA_ELF_NOTES
+#ifndef CONFIG_ARCH_HAVE_EXTRA_ELF_NOTES
 static inline int elf_coredump_extra_notes_size(void) { return 0; }
 static inline int elf_coredump_extra_notes_write(struct coredump_params *cprm) { return 0; }
 #else
diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h
index 69b136e4dd2b..bb3dcded055f 100644
--- a/include/linux/elfnote.h
+++ b/include/linux/elfnote.h
@@ -60,23 +60,21 @@
 
 #else	/* !__ASSEMBLER__ */
 #include <uapi/linux/elf.h>
+#include <linux/compiler.h>
 /*
  * Use an anonymous structure which matches the shape of
  * Elf{32,64}_Nhdr, but includes the name and desc data.  The size and
  * type of name and desc depend on the macro arguments.  "name" must
- * be a literal string, and "desc" must be passed by value.  You may
- * only define one note per line, since __LINE__ is used to generate
- * unique symbols.
+ * be a literal string, and "desc" must be passed by value.
  */
-#define _ELFNOTE_PASTE(a,b)	a##b
-#define _ELFNOTE(size, name, unique, type, desc)			\
+#define ELFNOTE(size, name, type, desc)					\
 	static const struct {						\
 		struct elf##size##_note _nhdr;				\
 		unsigned char _name[sizeof(name)]			\
 		__attribute__((aligned(sizeof(Elf##size##_Word))));	\
 		typeof(desc) _desc					\
 			     __attribute__((aligned(sizeof(Elf##size##_Word)))); \
-	} _ELFNOTE_PASTE(_note_, unique)				\
+	} __UNIQUE_ID(note)						\
 		__used							\
 		__attribute__((section(".note." name),			\
 			       aligned(sizeof(Elf##size##_Word)),	\
@@ -89,11 +87,10 @@
 		name,							\
 		desc							\
 	}
-#define ELFNOTE(size, name, type, desc)		\
-	_ELFNOTE(size, name, __LINE__, type, desc)
 
 #define ELFNOTE32(name, type, desc) ELFNOTE(32, name, type, desc)
 #define ELFNOTE64(name, type, desc) ELFNOTE(64, name, type, desc)
+
 #endif	/* __ASSEMBLER__ */
 
 #endif /* _LINUX_ELFNOTE_H */
diff --git a/include/linux/energy_model.h b/include/linux/energy_model.h
index b9caa01dfac4..43aa6153dc57 100644
--- a/include/linux/energy_model.h
+++ b/include/linux/energy_model.h
@@ -5,6 +5,7 @@
 #include <linux/device.h>
 #include <linux/jump_label.h>
 #include <linux/kobject.h>
+#include <linux/kref.h>
 #include <linux/rcupdate.h>
 #include <linux/sched/cpufreq.h>
 #include <linux/sched/topology.h>
@@ -12,6 +13,7 @@
 
 /**
  * struct em_perf_state - Performance state of a performance domain
+ * @performance:	CPU performance (capacity) at a given frequency
  * @frequency:	The frequency in KHz, for consistency with CPUFreq
  * @power:	The power consumed at this level (by 1 CPU or by a registered
  *		device). It can be a total power: static and dynamic.
@@ -20,6 +22,7 @@
  * @flags:	see "em_perf_state flags" description below.
  */
 struct em_perf_state {
+	unsigned long performance;
 	unsigned long frequency;
 	unsigned long power;
 	unsigned long cost;
@@ -37,9 +40,25 @@ struct em_perf_state {
 #define EM_PERF_STATE_INEFFICIENT BIT(0)
 
 /**
+ * struct em_perf_table - Performance states table
+ * @rcu:	RCU used for safe access and destruction
+ * @kref:	Reference counter to track the users
+ * @state:	List of performance states, in ascending order
+ */
+struct em_perf_table {
+	struct rcu_head rcu;
+	struct kref kref;
+	struct em_perf_state state[];
+};
+
+/**
  * struct em_perf_domain - Performance domain
- * @table:		List of performance states, in ascending order
+ * @em_table:		Pointer to the runtime modifiable em_perf_table
+ * @node:		node in	em_pd_list (in energy_model.c)
+ * @id:			A unique ID number for each performance domain
  * @nr_perf_states:	Number of performance states
+ * @min_perf_state:	Minimum allowed Performance State index
+ * @max_perf_state:	Maximum allowed Performance State index
  * @flags:		See "em_perf_domain flags"
  * @cpus:		Cpumask covering the CPUs of the domain. It's here
  *			for performance reasons to avoid potential cache
@@ -53,8 +72,12 @@ struct em_perf_state {
  * field is unused.
  */
 struct em_perf_domain {
-	struct em_perf_state *table;
+	struct em_perf_table __rcu *em_table;
+	struct list_head node;
+	int id;
 	int nr_perf_states;
+	int min_perf_state;
+	int max_perf_state;
 	unsigned long flags;
 	unsigned long cpus[];
 };
@@ -98,27 +121,6 @@ struct em_perf_domain {
 #define EM_MAX_NUM_CPUS 16
 #endif
 
-/*
- * To avoid an overflow on 32bit machines while calculating the energy
- * use a different order in the operation. First divide by the 'cpu_scale'
- * which would reduce big value stored in the 'cost' field, then multiply by
- * the 'sum_util'. This would allow to handle existing platforms, which have
- * e.g. power ~1.3 Watt at max freq, so the 'cost' value > 1mln micro-Watts.
- * In such scenario, where there are 4 CPUs in the Perf. Domain the 'sum_util'
- * could be 4096, then multiplication: 'cost' * 'sum_util'  would overflow.
- * This reordering of operations has some limitations, we lose small
- * precision in the estimation (comparing to 64bit platform w/o reordering).
- *
- * We are safe on 64bit machine.
- */
-#ifdef CONFIG_64BIT
-#define em_estimate_energy(cost, sum_util, scale_cpu) \
-	(((cost) * (sum_util)) / (scale_cpu))
-#else
-#define em_estimate_energy(cost, sum_util, scale_cpu) \
-	(((cost) / (scale_cpu)) * (sum_util))
-#endif
-
 struct em_data_callback {
 	/**
 	 * active_power() - Provide power at the next performance state of
@@ -168,40 +170,58 @@ struct em_data_callback {
 
 struct em_perf_domain *em_cpu_get(int cpu);
 struct em_perf_domain *em_pd_get(struct device *dev);
+int em_dev_update_perf_domain(struct device *dev,
+			      struct em_perf_table *new_table);
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *span,
-				bool microwatts);
+				const struct em_data_callback *cb,
+				const cpumask_t *cpus, bool microwatts);
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+				 const struct em_data_callback *cb,
+				 const cpumask_t *cpus, bool microwatts);
 void em_dev_unregister_perf_domain(struct device *dev);
+struct em_perf_table *em_table_alloc(struct em_perf_domain *pd);
+void em_table_free(struct em_perf_table *table);
+int em_dev_compute_costs(struct device *dev, struct em_perf_state *table,
+			 int nr_states);
+int em_dev_update_chip_binning(struct device *dev);
+int em_update_performance_limits(struct em_perf_domain *pd,
+		unsigned long freq_min_khz, unsigned long freq_max_khz);
+void em_adjust_cpu_capacity(unsigned int cpu);
+void em_rebuild_sched_domains(void);
 
 /**
  * em_pd_get_efficient_state() - Get an efficient performance state from the EM
- * @pd   : Performance domain for which we want an efficient frequency
- * @freq : Frequency to map with the EM
+ * @table:		List of performance states, in ascending order
+ * @pd:			performance domain for which this must be done
+ * @max_util:		Max utilization to map with the EM
  *
  * It is called from the scheduler code quite frequently and as a consequence
  * doesn't implement any check.
  *
- * Return: An efficient performance state, high enough to meet @freq
+ * Return: An efficient performance state id, high enough to meet @max_util
  * requirement.
  */
-static inline
-struct em_perf_state *em_pd_get_efficient_state(struct em_perf_domain *pd,
-						unsigned long freq)
+static inline int
+em_pd_get_efficient_state(struct em_perf_state *table,
+			  struct em_perf_domain *pd, unsigned long max_util)
 {
+	unsigned long pd_flags = pd->flags;
+	int min_ps = pd->min_perf_state;
+	int max_ps = pd->max_perf_state;
 	struct em_perf_state *ps;
 	int i;
 
-	for (i = 0; i < pd->nr_perf_states; i++) {
-		ps = &pd->table[i];
-		if (ps->frequency >= freq) {
-			if (pd->flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES &&
+	for (i = min_ps; i <= max_ps; i++) {
+		ps = &table[i];
+		if (ps->performance >= max_util) {
+			if (pd_flags & EM_PERF_DOMAIN_SKIP_INEFFICIENCIES &&
 			    ps->flags & EM_PERF_STATE_INEFFICIENT)
 				continue;
-			break;
+			return i;
 		}
 	}
 
-	return ps;
+	return max_ps;
 }
 
 /**
@@ -224,9 +244,11 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 				unsigned long max_util, unsigned long sum_util,
 				unsigned long allowed_cpu_cap)
 {
-	unsigned long freq, scale_cpu;
+	struct em_perf_table *em_table;
 	struct em_perf_state *ps;
-	int cpu;
+	int i;
+
+	WARN_ONCE(!rcu_read_lock_held(), "EM: rcu read lock needed\n");
 
 	if (!sum_util)
 		return 0;
@@ -234,32 +256,28 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	/*
 	 * In order to predict the performance state, map the utilization of
 	 * the most utilized CPU of the performance domain to a requested
-	 * frequency, like schedutil. Take also into account that the real
-	 * frequency might be set lower (due to thermal capping). Thus, clamp
+	 * performance, like schedutil. Take also into account that the real
+	 * performance might be set lower (due to thermal capping). Thus, clamp
 	 * max utilization to the allowed CPU capacity before calculating
-	 * effective frequency.
+	 * effective performance.
 	 */
-	cpu = cpumask_first(to_cpumask(pd->cpus));
-	scale_cpu = arch_scale_cpu_capacity(cpu);
-	ps = &pd->table[pd->nr_perf_states - 1];
-
-	max_util = map_util_perf(max_util);
 	max_util = min(max_util, allowed_cpu_cap);
-	freq = map_util_freq(max_util, ps->frequency, scale_cpu);
 
 	/*
 	 * Find the lowest performance state of the Energy Model above the
-	 * requested frequency.
+	 * requested performance.
 	 */
-	ps = em_pd_get_efficient_state(pd, freq);
+	em_table = rcu_dereference(pd->em_table);
+	i = em_pd_get_efficient_state(em_table->state, pd, max_util);
+	ps = &em_table->state[i];
 
 	/*
-	 * The capacity of a CPU in the domain at the performance state (ps)
-	 * can be computed as:
+	 * The performance (capacity) of a CPU in the domain at the performance
+	 * state (ps) can be computed as:
 	 *
-	 *             ps->freq * scale_cpu
-	 *   ps->cap = --------------------                          (1)
-	 *                 cpu_max_freq
+	 *                     ps->freq * scale_cpu
+	 *   ps->performance = --------------------                  (1)
+	 *                         cpu_max_freq
 	 *
 	 * So, ignoring the costs of idle states (which are not available in
 	 * the EM), the energy consumed by this CPU at that performance state
@@ -267,9 +285,10 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 *
 	 *             ps->power * cpu_util
 	 *   cpu_nrg = --------------------                          (2)
-	 *                   ps->cap
+	 *               ps->performance
 	 *
-	 * since 'cpu_util / ps->cap' represents its percentage of busy time.
+	 * since 'cpu_util / ps->performance' represents its percentage of busy
+	 * time.
 	 *
 	 *   NOTE: Although the result of this computation actually is in
 	 *         units of power, it can be manipulated as an energy value
@@ -279,9 +298,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 * By injecting (1) in (2), 'cpu_nrg' can be re-expressed as a product
 	 * of two terms:
 	 *
-	 *             ps->power * cpu_max_freq   cpu_util
-	 *   cpu_nrg = ------------------------ * ---------          (3)
-	 *                    ps->freq            scale_cpu
+	 *             ps->power * cpu_max_freq
+	 *   cpu_nrg = ------------------------ * cpu_util           (3)
+	 *               ps->freq * scale_cpu
 	 *
 	 * The first term is static, and is stored in the em_perf_state struct
 	 * as 'ps->cost'.
@@ -291,11 +310,9 @@ static inline unsigned long em_cpu_energy(struct em_perf_domain *pd,
 	 * total energy of the domain (which is the simple sum of the energy of
 	 * all of its CPUs) can be factorized as:
 	 *
-	 *            ps->cost * \Sum cpu_util
-	 *   pd_nrg = ------------------------                       (4)
-	 *                  scale_cpu
+	 *   pd_nrg = ps->cost * \Sum cpu_util                       (4)
 	 */
-	return em_estimate_energy(ps->cost, sum_util, scale_cpu);
+	return ps->cost * sum_util;
 }
 
 /**
@@ -310,6 +327,23 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
 	return pd->nr_perf_states;
 }
 
+/**
+ * em_perf_state_from_pd() - Get the performance states table of perf.
+ *				domain
+ * @pd		: performance domain for which this must be done
+ *
+ * To use this function the rcu_read_lock() should be hold. After the usage
+ * of the performance states table is finished, the rcu_read_unlock() should
+ * be called.
+ *
+ * Return: the pointer to performance states table of the performance domain
+ */
+static inline
+struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd)
+{
+	return rcu_dereference(pd->em_table)->state;
+}
+
 #else
 struct em_data_callback {};
 #define EM_ADV_DATA_CB(_active_power_cb, _cost_cb) { }
@@ -318,8 +352,15 @@ struct em_data_callback {};
 
 static inline
 int em_dev_register_perf_domain(struct device *dev, unsigned int nr_states,
-				struct em_data_callback *cb, cpumask_t *span,
-				bool microwatts)
+				const struct em_data_callback *cb,
+				const cpumask_t *cpus, bool microwatts)
+{
+	return -EINVAL;
+}
+static inline
+int em_dev_register_pd_no_update(struct device *dev, unsigned int nr_states,
+				 const struct em_data_callback *cb,
+				 const cpumask_t *cpus, bool microwatts)
 {
 	return -EINVAL;
 }
@@ -344,6 +385,41 @@ static inline int em_pd_nr_perf_states(struct em_perf_domain *pd)
 {
 	return 0;
 }
+static inline
+struct em_perf_table *em_table_alloc(struct em_perf_domain *pd)
+{
+	return NULL;
+}
+static inline void em_table_free(struct em_perf_table *table) {}
+static inline
+int em_dev_update_perf_domain(struct device *dev,
+			      struct em_perf_table *new_table)
+{
+	return -EINVAL;
+}
+static inline
+struct em_perf_state *em_perf_state_from_pd(struct em_perf_domain *pd)
+{
+	return NULL;
+}
+static inline
+int em_dev_compute_costs(struct device *dev, struct em_perf_state *table,
+			 int nr_states)
+{
+	return -EINVAL;
+}
+static inline int em_dev_update_chip_binning(struct device *dev)
+{
+	return -EINVAL;
+}
+static inline
+int em_update_performance_limits(struct em_perf_domain *pd,
+		unsigned long freq_min_khz, unsigned long freq_max_khz)
+{
+	return -EINVAL;
+}
+static inline void em_adjust_cpu_capacity(unsigned int cpu) {}
+static inline void em_rebuild_sched_domains(void) {}
 #endif
 
 #endif
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index d95ab85f96ba..87efb38b7081 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -2,21 +2,15 @@
 #ifndef __LINUX_ENTRYCOMMON_H
 #define __LINUX_ENTRYCOMMON_H
 
-#include <linux/static_call_types.h>
+#include <linux/irq-entry-common.h>
+#include <linux/livepatch.h>
 #include <linux/ptrace.h>
-#include <linux/syscalls.h>
+#include <linux/resume_user_mode.h>
 #include <linux/seccomp.h>
 #include <linux/sched.h>
 
 #include <asm/entry-common.h>
-
-/*
- * Define dummy _TIF work flags if not defined by the architecture or for
- * disabled functionality.
- */
-#ifndef _TIF_PATCH_PENDING
-# define _TIF_PATCH_PENDING		(0)
-#endif
+#include <asm/syscall.h>
 
 #ifndef _TIF_UPROBE
 # define _TIF_UPROBE			(0)
@@ -43,6 +37,7 @@
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
 				 SYSCALL_WORK_SYSCALL_USER_DISPATCH |	\
 				 ARCH_SYSCALL_WORK_ENTER)
+
 #define SYSCALL_WORK_EXIT	(SYSCALL_WORK_SYSCALL_TRACEPOINT |	\
 				 SYSCALL_WORK_SYSCALL_TRACE |		\
 				 SYSCALL_WORK_SYSCALL_AUDIT |		\
@@ -50,72 +45,7 @@
 				 SYSCALL_WORK_SYSCALL_EXIT_TRAP	|	\
 				 ARCH_SYSCALL_WORK_EXIT)
 
-/*
- * TIF flags handled in exit_to_user_mode_loop()
- */
-#ifndef ARCH_EXIT_TO_USER_MODE_WORK
-# define ARCH_EXIT_TO_USER_MODE_WORK		(0)
-#endif
-
-#define EXIT_TO_USER_MODE_WORK						\
-	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |	\
-	 ARCH_EXIT_TO_USER_MODE_WORK)
-
-/**
- * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
- * @regs:	Pointer to currents pt_regs
- *
- * Defaults to an empty implementation. Can be replaced by architecture
- * specific code.
- *
- * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
- * section. Use __always_inline so the compiler cannot push it out of line
- * and make it instrumentable.
- */
-static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
-
-#ifndef arch_enter_from_user_mode
-static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
-#endif
-
-/**
- * enter_from_user_mode - Establish state when coming from user mode
- *
- * Syscall/interrupt entry disables interrupts, but user mode is traced as
- * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
- *
- * 1) Tell lockdep that interrupts are disabled
- * 2) Invoke context tracking if enabled to reactivate RCU
- * 3) Trace interrupts off state
- *
- * Invoked from architecture specific syscall entry code with interrupts
- * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct and interrupts are still
- * disabled. The subsequent functions can be instrumented.
- *
- * This is invoked when there is architecture specific functionality to be
- * done between establishing state and enabling interrupts. The caller must
- * enable interrupts before invoking syscall_enter_from_user_mode_work().
- */
-void enter_from_user_mode(struct pt_regs *regs);
-
-/**
- * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
- * @regs:	Pointer to currents pt_regs
- *
- * Invoked from architecture specific syscall entry code with interrupts
- * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct, interrupts are enabled and the
- * subsequent functions can be instrumented.
- *
- * This handles lockdep, RCU (context tracking) and tracing state, i.e.
- * the functionality provided by enter_from_user_mode().
- *
- * This is invoked when there is extra architecture specific functionality
- * to be done between establishing state and handling user mode entry work.
- */
-void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
+long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work);
 
 /**
  * syscall_enter_from_user_mode_work - Check and handle work before invoking
@@ -124,8 +54,8 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
  * @syscall:	The syscall number
  *
  * Invoked from architecture specific syscall entry code with interrupts
- * enabled after invoking syscall_enter_from_user_mode_prepare() and extra
- * architecture specific work.
+ * enabled after invoking enter_from_user_mode(), enabling interrupts and
+ * extra architecture specific work.
  *
  * Returns: The original or a modified syscall number
  *
@@ -140,7 +70,15 @@ void syscall_enter_from_user_mode_prepare(struct pt_regs *regs);
  *     ptrace_report_syscall_entry(), __secure_computing(), trace_sys_enter()
  *  2) Invocation of audit_syscall_entry()
  */
-long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
+static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+
+	if (work & SYSCALL_WORK_ENTER)
+		syscall = syscall_trace_enter(regs, syscall, work);
+
+	return syscall;
+}
 
 /**
  * syscall_enter_from_user_mode - Establish state and check and handle work
@@ -153,130 +91,35 @@ long syscall_enter_from_user_mode_work(struct pt_regs *regs, long syscall);
  * function returns all state is correct, interrupts are enabled and the
  * subsequent functions can be instrumented.
  *
- * This is combination of syscall_enter_from_user_mode_prepare() and
- * syscall_enter_from_user_mode_work().
+ * This is the combination of enter_from_user_mode() and
+ * syscall_enter_from_user_mode_work() to be used when there is no
+ * architecture specific work to be done between the two.
  *
  * Returns: The original or a modified syscall number. See
  * syscall_enter_from_user_mode_work() for further explanation.
  */
-long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall);
-
-/**
- * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
- * @ti_work:	Cached TIF flags gathered with interrupts disabled
- *
- * Defaults to local_irq_enable(). Can be supplied by architecture specific
- * code.
- */
-static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
-
-#ifndef local_irq_enable_exit_to_user
-static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
+static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, long syscall)
 {
-	local_irq_enable();
-}
-#endif
+	long ret;
 
-/**
- * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
- *
- * Defaults to local_irq_disable(). Can be supplied by architecture specific
- * code.
- */
-static inline void local_irq_disable_exit_to_user(void);
+	enter_from_user_mode(regs);
 
-#ifndef local_irq_disable_exit_to_user
-static inline void local_irq_disable_exit_to_user(void)
-{
-	local_irq_disable();
-}
-#endif
-
-/**
- * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
- *				 to user mode.
- * @regs:	Pointer to currents pt_regs
- * @ti_work:	Cached TIF flags gathered with interrupts disabled
- *
- * Invoked from exit_to_user_mode_loop() with interrupt enabled
- *
- * Defaults to NOOP. Can be supplied by architecture specific code.
- */
-static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
-					       unsigned long ti_work);
-
-#ifndef arch_exit_to_user_mode_work
-static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
-					       unsigned long ti_work)
-{
-}
-#endif
-
-/**
- * arch_exit_to_user_mode_prepare - Architecture specific preparation for
- *				    exit to user mode.
- * @regs:	Pointer to currents pt_regs
- * @ti_work:	Cached TIF flags gathered with interrupts disabled
- *
- * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
- * function before return. Defaults to NOOP.
- */
-static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
-						  unsigned long ti_work);
+	instrumentation_begin();
+	local_irq_enable();
+	ret = syscall_enter_from_user_mode_work(regs, syscall);
+	instrumentation_end();
 
-#ifndef arch_exit_to_user_mode_prepare
-static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
-						  unsigned long ti_work)
-{
+	return ret;
 }
-#endif
-
-/**
- * arch_exit_to_user_mode - Architecture specific final work before
- *			    exit to user mode.
- *
- * Invoked from exit_to_user_mode() with interrupt disabled as the last
- * function before return. Defaults to NOOP.
- *
- * This needs to be __always_inline because it is non-instrumentable code
- * invoked after context tracking switched to user mode.
- *
- * An architecture implementation must not do anything complex, no locking
- * etc. The main purpose is for speculation mitigations.
- */
-static __always_inline void arch_exit_to_user_mode(void);
-
-#ifndef arch_exit_to_user_mode
-static __always_inline void arch_exit_to_user_mode(void) { }
-#endif
 
 /**
- * arch_do_signal_or_restart -  Architecture specific signal delivery function
- * @regs:	Pointer to currents pt_regs
+ * syscall_exit_work - Handle work before returning to user mode
+ * @regs:	Pointer to current pt_regs
+ * @work:	Current thread syscall work
  *
- * Invoked from exit_to_user_mode_loop().
+ * Do one-time syscall specific work.
  */
-void arch_do_signal_or_restart(struct pt_regs *regs);
-
-/**
- * exit_to_user_mode - Fixup state when exiting to user mode
- *
- * Syscall/interrupt exit enables interrupts, but the kernel state is
- * interrupts disabled when this is invoked. Also tell RCU about it.
- *
- * 1) Trace interrupts on state
- * 2) Invoke context tracking if enabled to adjust RCU state
- * 3) Invoke architecture specific last minute exit code, e.g. speculation
- *    mitigations, etc.: arch_exit_to_user_mode()
- * 4) Tell lockdep that interrupts are enabled
- *
- * Invoked from architecture specific code when syscall_exit_to_user_mode()
- * is not suitable as the last step before returning to userspace. Must be
- * invoked with interrupts disabled and the caller must be
- * non-instrumentable.
- * The caller has to invoke syscall_exit_to_user_mode_work() before this.
- */
-void exit_to_user_mode(void);
+void syscall_exit_work(struct pt_regs *regs, unsigned long work);
 
 /**
  * syscall_exit_to_user_mode_work - Handle work before returning to user mode
@@ -291,7 +134,30 @@ void exit_to_user_mode(void);
  * make the final state transitions. Interrupts must stay disabled between
  * return from this function and the invocation of exit_to_user_mode().
  */
-void syscall_exit_to_user_mode_work(struct pt_regs *regs);
+static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs)
+{
+	unsigned long work = READ_ONCE(current_thread_info()->syscall_work);
+	unsigned long nr = syscall_get_nr(current, regs);
+
+	CT_WARN_ON(ct_state() != CT_STATE_KERNEL);
+
+	if (IS_ENABLED(CONFIG_PROVE_LOCKING)) {
+		if (WARN(irqs_disabled(), "syscall %lu left IRQs disabled", nr))
+			local_irq_enable();
+	}
+
+	rseq_debug_syscall_return(regs);
+
+	/*
+	 * Do one-time syscall specific work. If these work items are
+	 * enabled, we want to run them exactly once per syscall exit with
+	 * interrupts enabled.
+	 */
+	if (unlikely(work & SYSCALL_WORK_EXIT))
+		syscall_exit_work(regs, work);
+	local_irq_disable_exit_to_user();
+	syscall_exit_to_user_mode_prepare(regs);
+}
 
 /**
  * syscall_exit_to_user_mode - Handle work before returning to user mode
@@ -322,147 +188,12 @@ void syscall_exit_to_user_mode_work(struct pt_regs *regs);
  * exit_to_user_mode(). This function is preferred unless there is a
  * compelling architectural reason to use the separate functions.
  */
-void syscall_exit_to_user_mode(struct pt_regs *regs);
-
-/**
- * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
- * @regs:	Pointer to currents pt_regs
- *
- * Invoked from architecture specific entry code with interrupts disabled.
- * Can only be called when the interrupt entry came from user mode. The
- * calling code must be non-instrumentable.  When the function returns all
- * state is correct and the subsequent functions can be instrumented.
- *
- * The function establishes state (lockdep, RCU (context tracking), tracing)
- */
-void irqentry_enter_from_user_mode(struct pt_regs *regs);
-
-/**
- * irqentry_exit_to_user_mode - Interrupt exit work
- * @regs:	Pointer to current's pt_regs
- *
- * Invoked with interrupts disabled and fully valid regs. Returns with all
- * work handled, interrupts disabled such that the caller can immediately
- * switch to user mode. Called from architecture specific interrupt
- * handling code.
- *
- * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
- * Interrupt exit is not invoking #1 which is the syscall specific one time
- * work.
- */
-void irqentry_exit_to_user_mode(struct pt_regs *regs);
-
-#ifndef irqentry_state
-/**
- * struct irqentry_state - Opaque object for exception state storage
- * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
- *            exit path has to invoke ct_irq_exit().
- * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
- *           lockdep state is restored correctly on exit from nmi.
- *
- * This opaque object is filled in by the irqentry_*_enter() functions and
- * must be passed back into the corresponding irqentry_*_exit() functions
- * when the exception is complete.
- *
- * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
- * and all members private.  Descriptions of the members are provided to aid in
- * the maintenance of the irqentry_*() functions.
- */
-typedef struct irqentry_state {
-	union {
-		bool	exit_rcu;
-		bool	lockdep;
-	};
-} irqentry_state_t;
-#endif
-
-/**
- * irqentry_enter - Handle state tracking on ordinary interrupt entries
- * @regs:	Pointer to pt_regs of interrupted context
- *
- * Invokes:
- *  - lockdep irqflag state tracking as low level ASM entry disabled
- *    interrupts.
- *
- *  - Context tracking if the exception hit user mode.
- *
- *  - The hardirq tracer to keep the state consistent as low level ASM
- *    entry disabled interrupts.
- *
- * As a precondition, this requires that the entry came from user mode,
- * idle, or a kernel context in which RCU is watching.
- *
- * For kernel mode entries RCU handling is done conditional. If RCU is
- * watching then the only RCU requirement is to check whether the tick has
- * to be restarted. If RCU is not watching then ct_irq_enter() has to be
- * invoked on entry and ct_irq_exit() on exit.
- *
- * Avoiding the ct_irq_enter/exit() calls is an optimization but also
- * solves the problem of kernel mode pagefaults which can schedule, which
- * is not possible after invoking ct_irq_enter() without undoing it.
- *
- * For user mode entries irqentry_enter_from_user_mode() is invoked to
- * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
- * would not be possible.
- *
- * Returns: An opaque object that must be passed to idtentry_exit()
- */
-irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
-
-/**
- * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
- *
- * Conditional reschedule with additional sanity checks.
- */
-void raw_irqentry_exit_cond_resched(void);
-#ifdef CONFIG_PREEMPT_DYNAMIC
-#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
-#define irqentry_exit_cond_resched_dynamic_disabled	NULL
-DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
-#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
-#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-void dynamic_irqentry_exit_cond_resched(void);
-#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
-#endif
-#else /* CONFIG_PREEMPT_DYNAMIC */
-#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
-#endif /* CONFIG_PREEMPT_DYNAMIC */
-
-/**
- * irqentry_exit - Handle return from exception that used irqentry_enter()
- * @regs:	Pointer to pt_regs (exception entry regs)
- * @state:	Return value from matching call to irqentry_enter()
- *
- * Depending on the return target (kernel/user) this runs the necessary
- * preemption and work checks if possible and required and returns to
- * the caller with interrupts disabled and no further work pending.
- *
- * This is the last action before returning to the low level ASM code which
- * just needs to return to the appropriate context.
- *
- * Counterpart to irqentry_enter().
- */
-void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
-
-/**
- * irqentry_nmi_enter - Handle NMI entry
- * @regs:	Pointer to currents pt_regs
- *
- * Similar to irqentry_enter() but taking care of the NMI constraints.
- */
-irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
-
-/**
- * irqentry_nmi_exit - Handle return from NMI handling
- * @regs:	Pointer to pt_regs (NMI entry regs)
- * @irq_state:	Return value from matching call to irqentry_nmi_enter()
- *
- * Last action before returning to the low level assembly code.
- *
- * Counterpart to irqentry_nmi_enter().
- */
-void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
+static __always_inline void syscall_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	syscall_exit_to_user_mode_work(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
 
 #endif
diff --git a/include/linux/entry-kvm.h b/include/linux/entry-virt.h
index 6813171afccb..bfa767702d9a 100644
--- a/include/linux/entry-kvm.h
+++ b/include/linux/entry-virt.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_ENTRYKVM_H
-#define __LINUX_ENTRYKVM_H
+#ifndef __LINUX_ENTRYVIRT_H
+#define __LINUX_ENTRYVIRT_H
 
 #include <linux/static_call_types.h>
 #include <linux/resume_user_mode.h>
@@ -10,17 +10,16 @@
 #include <linux/tick.h>
 
 /* Transfer to guest mode work */
-#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
+#ifdef CONFIG_VIRT_XFER_TO_GUEST_WORK
 
 #ifndef ARCH_XFER_TO_GUEST_MODE_WORK
 # define ARCH_XFER_TO_GUEST_MODE_WORK	(0)
 #endif
 
 #define XFER_TO_GUEST_MODE_WORK						\
-	(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL |	\
-	 _TIF_NOTIFY_RESUME | ARCH_XFER_TO_GUEST_MODE_WORK)
-
-struct kvm_vcpu;
+	(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | _TIF_SIGPENDING | \
+	 _TIF_NOTIFY_SIGNAL | _TIF_NOTIFY_RESUME |			\
+	 ARCH_XFER_TO_GUEST_MODE_WORK)
 
 /**
  * arch_xfer_to_guest_mode_handle_work - Architecture specific xfer to guest
@@ -31,12 +30,10 @@ struct kvm_vcpu;
  * Invoked from xfer_to_guest_mode_handle_work(). Defaults to NOOP. Can be
  * replaced by architecture specific code.
  */
-static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
-						      unsigned long ti_work);
+static inline int arch_xfer_to_guest_mode_handle_work(unsigned long ti_work);
 
-#ifndef arch_xfer_to_guest_mode_work
-static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
-						      unsigned long ti_work)
+#ifndef arch_xfer_to_guest_mode_handle_work
+static inline int arch_xfer_to_guest_mode_handle_work(unsigned long ti_work)
 {
 	return 0;
 }
@@ -45,11 +42,10 @@ static inline int arch_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu,
 /**
  * xfer_to_guest_mode_handle_work - Check and handle pending work which needs
  *				    to be handled before going to guest mode
- * @vcpu:	Pointer to current's VCPU data
  *
  * Returns: 0 or an error code
  */
-int xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu);
+int xfer_to_guest_mode_handle_work(void);
 
 /**
  * xfer_to_guest_mode_prepare - Perform last minute preparation work that
@@ -94,6 +90,6 @@ static inline bool xfer_to_guest_mode_work_pending(void)
 	lockdep_assert_irqs_disabled();
 	return __xfer_to_guest_mode_work_pending();
 }
-#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
+#endif /* CONFIG_VIRT_XFER_TO_GUEST_WORK */
 
 #endif
diff --git a/include/linux/err.h b/include/linux/err.h
index a139c64aef2a..8c37be0620ab 100644
--- a/include/linux/err.h
+++ b/include/linux/err.h
@@ -19,23 +19,74 @@
 
 #ifndef __ASSEMBLY__
 
+/**
+ * IS_ERR_VALUE - Detect an error pointer.
+ * @x: The pointer to check.
+ *
+ * Like IS_ERR(), but does not generate a compiler warning if result is unused.
+ */
 #define IS_ERR_VALUE(x) unlikely((unsigned long)(void *)(x) >= (unsigned long)-MAX_ERRNO)
 
+/**
+ * ERR_PTR - Create an error pointer.
+ * @error: A negative error code.
+ *
+ * Encodes @error into a pointer value. Users should consider the result
+ * opaque and not assume anything about how the error is encoded.
+ *
+ * Return: A pointer with @error encoded within its value.
+ */
 static inline void * __must_check ERR_PTR(long error)
 {
 	return (void *) error;
 }
 
+/**
+ * INIT_ERR_PTR - Init a const error pointer.
+ * @error: A negative error code.
+ *
+ * Like ERR_PTR(), but usable to initialize static variables.
+ */
+#define INIT_ERR_PTR(error) ((void *)(error))
+
+/* Return the pointer in the percpu address space. */
+#define ERR_PTR_PCPU(error) ((void __percpu *)(unsigned long)ERR_PTR(error))
+
+/* Cast an error pointer to __iomem. */
+#define IOMEM_ERR_PTR(error) (__force void __iomem *)ERR_PTR(error)
+
+/**
+ * PTR_ERR - Extract the error code from an error pointer.
+ * @ptr: An error pointer.
+ * Return: The error code within @ptr.
+ */
 static inline long __must_check PTR_ERR(__force const void *ptr)
 {
 	return (long) ptr;
 }
 
+/* Read an error pointer from the percpu address space. */
+#define PTR_ERR_PCPU(ptr) (PTR_ERR((const void *)(__force const unsigned long)(ptr)))
+
+/**
+ * IS_ERR - Detect an error pointer.
+ * @ptr: The pointer to check.
+ * Return: true if @ptr is an error pointer, false otherwise.
+ */
 static inline bool __must_check IS_ERR(__force const void *ptr)
 {
 	return IS_ERR_VALUE((unsigned long)ptr);
 }
 
+/* Read an error pointer from the percpu address space. */
+#define IS_ERR_PCPU(ptr) (IS_ERR((const void *)(__force const unsigned long)(ptr)))
+
+/**
+ * IS_ERR_OR_NULL - Detect an error pointer or a null pointer.
+ * @ptr: The pointer to check.
+ *
+ * Like IS_ERR(), but also returns true for a null pointer.
+ */
 static inline bool __must_check IS_ERR_OR_NULL(__force const void *ptr)
 {
 	return unlikely(!ptr) || IS_ERR_VALUE((unsigned long)ptr);
@@ -54,6 +105,23 @@ static inline void * __must_check ERR_CAST(__force const void *ptr)
 	return (void *) ptr;
 }
 
+/**
+ * PTR_ERR_OR_ZERO - Extract the error code from a pointer if it has one.
+ * @ptr: A potential error pointer.
+ *
+ * Convenience function that can be used inside a function that returns
+ * an error code to propagate errors received as error pointers.
+ * For example, ``return PTR_ERR_OR_ZERO(ptr);`` replaces:
+ *
+ * .. code-block:: c
+ *
+ *	if (IS_ERR(ptr))
+ *		return PTR_ERR(ptr);
+ *	else
+ *		return 0;
+ *
+ * Return: The error code within @ptr if it is an error pointer; 0 otherwise.
+ */
 static inline int __must_check PTR_ERR_OR_ZERO(__force const void *ptr)
 {
 	if (IS_ERR(ptr))
diff --git a/include/linux/etherdevice.h b/include/linux/etherdevice.h
index 224645f17c33..9a1eacf35d37 100644
--- a/include/linux/etherdevice.h
+++ b/include/linux/etherdevice.h
@@ -21,7 +21,7 @@
 #include <linux/netdevice.h>
 #include <linux/random.h>
 #include <linux/crc32.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 #include <asm/bitsperlong.h>
 
 #ifdef __KERNEL__
@@ -71,11 +71,17 @@ static const u8 eth_reserved_addr_base[ETH_ALEN] __aligned(2) =
 { 0x01, 0x80, 0xc2, 0x00, 0x00, 0x00 };
 #define eth_stp_addr eth_reserved_addr_base
 
+static const u8 eth_ipv4_mcast_addr_base[ETH_ALEN] __aligned(2) =
+{ 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 };
+
+static const u8 eth_ipv6_mcast_addr_base[ETH_ALEN] __aligned(2) =
+{ 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 };
+
 /**
  * is_link_local_ether_addr - Determine if given Ethernet address is link-local
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return true if address is link local reserved addr (01:80:c2:00:00:0X) per
+ * Return: true if address is link local reserved addr (01:80:c2:00:00:0X) per
  * IEEE 802.1Q 8.6.3 Frame filtering.
  *
  * Please note: addr must be aligned to u16.
@@ -98,7 +104,7 @@ static inline bool is_link_local_ether_addr(const u8 *addr)
  * is_zero_ether_addr - Determine if give Ethernet address is all zeros.
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return true if the address is all zeroes.
+ * Return: true if the address is all zeroes.
  *
  * Please note: addr must be aligned to u16.
  */
@@ -117,7 +123,7 @@ static inline bool is_zero_ether_addr(const u8 *addr)
  * is_multicast_ether_addr - Determine if the Ethernet address is a multicast.
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return true if the address is a multicast address.
+ * Return: true if the address is a multicast address.
  * By definition the broadcast address is also a multicast address.
  */
 static inline bool is_multicast_ether_addr(const u8 *addr)
@@ -151,7 +157,7 @@ static inline bool is_multicast_ether_addr_64bits(const u8 *addr)
  * is_local_ether_addr - Determine if the Ethernet address is locally-assigned one (IEEE 802).
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return true if the address is a local address.
+ * Return: true if the address is a local address.
  */
 static inline bool is_local_ether_addr(const u8 *addr)
 {
@@ -162,7 +168,7 @@ static inline bool is_local_ether_addr(const u8 *addr)
  * is_broadcast_ether_addr - Determine if the Ethernet address is broadcast
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return true if the address is the broadcast address.
+ * Return: true if the address is the broadcast address.
  *
  * Please note: addr must be aligned to u16.
  */
@@ -177,7 +183,7 @@ static inline bool is_broadcast_ether_addr(const u8 *addr)
  * is_unicast_ether_addr - Determine if the Ethernet address is unicast
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return true if the address is a unicast address.
+ * Return: true if the address is a unicast address.
  */
 static inline bool is_unicast_ether_addr(const u8 *addr)
 {
@@ -191,7 +197,7 @@ static inline bool is_unicast_ether_addr(const u8 *addr)
  * Check that the Ethernet address (MAC) is not 00:00:00:00:00:00, is not
  * a multicast address, and is not FF:FF:FF:FF:FF:FF.
  *
- * Return true if the address is valid.
+ * Return: true if the address is valid.
  *
  * Please note: addr must be aligned to u16.
  */
@@ -208,7 +214,7 @@ static inline bool is_valid_ether_addr(const u8 *addr)
  *
  * Check that the value from the Ethertype/length field is a valid Ethertype.
  *
- * Return true if the valid is an 802.3 supported Ethertype.
+ * Return: true if the valid is an 802.3 supported Ethertype.
  */
 static inline bool eth_proto_is_802_3(__be16 proto)
 {
@@ -430,18 +436,16 @@ static inline bool ether_addr_equal_masked(const u8 *addr1, const u8 *addr2,
 
 static inline bool ether_addr_is_ipv4_mcast(const u8 *addr)
 {
-	u8 base[ETH_ALEN] = { 0x01, 0x00, 0x5e, 0x00, 0x00, 0x00 };
 	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0xff, 0x80, 0x00, 0x00 };
 
-	return ether_addr_equal_masked(addr, base, mask);
+	return ether_addr_equal_masked(addr, eth_ipv4_mcast_addr_base, mask);
 }
 
 static inline bool ether_addr_is_ipv6_mcast(const u8 *addr)
 {
-	u8 base[ETH_ALEN] = { 0x33, 0x33, 0x00, 0x00, 0x00, 0x00 };
 	u8 mask[ETH_ALEN] = { 0xff, 0xff, 0x00, 0x00, 0x00, 0x00 };
 
-	return ether_addr_equal_masked(addr, base, mask);
+	return ether_addr_equal_masked(addr, eth_ipv6_mcast_addr_base, mask);
 }
 
 static inline bool ether_addr_is_ip_mcast(const u8 *addr)
@@ -454,7 +458,7 @@ static inline bool ether_addr_is_ip_mcast(const u8 *addr)
  * ether_addr_to_u64 - Convert an Ethernet address into a u64 value.
  * @addr: Pointer to a six-byte array containing the Ethernet address
  *
- * Return a u64 value of the address
+ * Return: a u64 value of the address
  */
 static inline u64 ether_addr_to_u64(const u8 *addr)
 {
@@ -608,7 +612,40 @@ static inline void eth_hw_addr_gen(struct net_device *dev, const u8 *base_addr,
 }
 
 /**
- * eth_skb_pad - Pad buffer to mininum number of octets for Ethernet frame
+ * eth_skb_pkt_type - Assign packet type if destination address does not match
+ * @skb: Assigned a packet type if address does not match @dev address
+ * @dev: Network device used to compare packet address against
+ *
+ * If the destination MAC address of the packet does not match the network
+ * device address, assign an appropriate packet type.
+ */
+static inline void eth_skb_pkt_type(struct sk_buff *skb,
+				    const struct net_device *dev)
+{
+	const struct ethhdr *eth = eth_hdr(skb);
+
+	if (unlikely(!ether_addr_equal_64bits(eth->h_dest, dev->dev_addr))) {
+		if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) {
+			if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast))
+				skb->pkt_type = PACKET_BROADCAST;
+			else
+				skb->pkt_type = PACKET_MULTICAST;
+		} else {
+			skb->pkt_type = PACKET_OTHERHOST;
+		}
+	}
+}
+
+static inline struct ethhdr *eth_skb_pull_mac(struct sk_buff *skb)
+{
+	struct ethhdr *eth = (struct ethhdr *)skb->data;
+
+	skb_pull_inline(skb, ETH_HLEN);
+	return eth;
+}
+
+/**
+ * eth_skb_pad - Pad buffer to minimum number of octets for Ethernet frame
  * @skb: Buffer to pad
  *
  * An Ethernet frame should have a minimum size of 60 bytes.  This function
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 62b61527bcc4..5c9162193d26 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -17,7 +17,13 @@
 #include <linux/compat.h>
 #include <linux/if_ether.h>
 #include <linux/netlink.h>
+#include <linux/timer_types.h>
 #include <uapi/linux/ethtool.h>
+#include <uapi/linux/ethtool_netlink_generated.h>
+#include <uapi/linux/net_tstamp.h>
+
+#define ETHTOOL_MM_MAX_VERIFY_TIME_MS		128
+#define ETHTOOL_MM_MAX_VERIFY_RETRIES		3
 
 struct compat_ethtool_rx_flow_spec {
 	u32		flow_type;
@@ -77,6 +83,9 @@ enum {
  * @cqe_size: Size of TX/RX completion queue event
  * @tx_push_buf_len: Size of TX push buffer
  * @tx_push_buf_max_len: Maximum allowed size of TX push buffer
+ * @hds_thresh: Packet size threshold for header data split (HDS)
+ * @hds_thresh_max: Maximum supported setting for @hds_threshold
+ *
  */
 struct kernel_ethtool_ringparam {
 	u32	rx_buf_len;
@@ -86,6 +95,8 @@ struct kernel_ethtool_ringparam {
 	u32	cqe_size;
 	u32	tx_push_buf_len;
 	u32	tx_push_buf_max_len;
+	u32	hds_thresh;
+	u32	hds_thresh_max;
 };
 
 /**
@@ -95,6 +106,8 @@ struct kernel_ethtool_ringparam {
  * @ETHTOOL_RING_USE_TX_PUSH: capture for setting tx_push
  * @ETHTOOL_RING_USE_RX_PUSH: capture for setting rx_push
  * @ETHTOOL_RING_USE_TX_PUSH_BUF_LEN: capture for setting tx_push_buf_len
+ * @ETHTOOL_RING_USE_TCP_DATA_SPLIT: capture for setting tcp_data_split
+ * @ETHTOOL_RING_USE_HDS_THRS: capture for setting header-data-split-thresh
  */
 enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_RX_BUF_LEN		= BIT(0),
@@ -102,6 +115,8 @@ enum ethtool_supported_ring_param {
 	ETHTOOL_RING_USE_TX_PUSH		= BIT(2),
 	ETHTOOL_RING_USE_RX_PUSH		= BIT(3),
 	ETHTOOL_RING_USE_TX_PUSH_BUF_LEN	= BIT(4),
+	ETHTOOL_RING_USE_TCP_DATA_SPLIT		= BIT(5),
+	ETHTOOL_RING_USE_HDS_THRS		= BIT(6),
 };
 
 #define __ETH_RSS_HASH_BIT(bit)	((u32)1 << (bit))
@@ -157,6 +172,57 @@ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings)
 	return index % n_rx_rings;
 }
 
+/**
+ * struct ethtool_rxfh_context - a custom RSS context configuration
+ * @indir_size: Number of u32 entries in indirection table
+ * @key_size: Size of hash key, in bytes
+ * @priv_size: Size of driver private data, in bytes
+ * @hfunc: RSS hash function identifier.  One of the %ETH_RSS_HASH_*
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
+ * @indir_configured: indir has been specified (at create time or subsequently)
+ * @key_configured: hkey has been specified (at create time or subsequently)
+ */
+struct ethtool_rxfh_context {
+	u32 indir_size;
+	u32 key_size;
+	u16 priv_size;
+	u8 hfunc;
+	u8 input_xfrm;
+	u8 indir_configured:1;
+	u8 key_configured:1;
+	/* private: driver private data, indirection table, and hash key are
+	 * stored sequentially in @data area.  Use below helpers to access.
+	 */
+	u32 key_off;
+	u8 data[] __aligned(sizeof(void *));
+};
+
+static inline void *ethtool_rxfh_context_priv(struct ethtool_rxfh_context *ctx)
+{
+	return ctx->data;
+}
+
+static inline u32 *ethtool_rxfh_context_indir(struct ethtool_rxfh_context *ctx)
+{
+	return (u32 *)(ctx->data + ALIGN(ctx->priv_size, sizeof(u32)));
+}
+
+static inline u8 *ethtool_rxfh_context_key(struct ethtool_rxfh_context *ctx)
+{
+	return &ctx->data[ctx->key_off];
+}
+
+void ethtool_rxfh_context_lost(struct net_device *dev, u32 context_id);
+
+struct link_mode_info {
+	int                             speed;
+	u8                              lanes;
+	u8                              duplex;
+};
+
+extern const struct link_mode_info link_mode_params[];
+
 /* declare a link mode bitmap */
 #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name)		\
 	DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS)
@@ -211,7 +277,7 @@ struct ethtool_link_ksettings {
  *   @mode : one of the ETHTOOL_LINK_MODE_*_BIT
  * (not atomic, no bound checking)
  *
- * Returns true/false.
+ * Returns: true/false.
  */
 #define ethtool_link_ksettings_test_link_mode(ptr, name, mode)		\
 	test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name)
@@ -220,6 +286,16 @@ extern int
 __ethtool_get_link_ksettings(struct net_device *dev,
 			     struct ethtool_link_ksettings *link_ksettings);
 
+struct ethtool_keee {
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(supported);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(advertised);
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertised);
+	u32	tx_lpi_timer;
+	bool	tx_lpi_enabled;
+	bool	eee_active;
+	bool	eee_enabled;
+};
+
 struct kernel_ethtool_coalesce {
 	u8 use_cqe_mode_tx;
 	u8 use_cqe_mode_rx;
@@ -272,7 +348,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32,
 #define ETHTOOL_COALESCE_TX_AGGR_MAX_BYTES	BIT(24)
 #define ETHTOOL_COALESCE_TX_AGGR_MAX_FRAMES	BIT(25)
 #define ETHTOOL_COALESCE_TX_AGGR_TIME_USECS	BIT(26)
-#define ETHTOOL_COALESCE_ALL_PARAMS		GENMASK(26, 0)
+#define ETHTOOL_COALESCE_RX_PROFILE		BIT(27)
+#define ETHTOOL_COALESCE_TX_PROFILE		BIT(28)
+#define ETHTOOL_COALESCE_ALL_PARAMS		GENMASK(28, 0)
 
 #define ETHTOOL_COALESCE_USECS						\
 	(ETHTOOL_COALESCE_RX_USECS | ETHTOOL_COALESCE_TX_USECS)
@@ -354,6 +432,29 @@ struct ethtool_eth_phy_stats {
 	);
 };
 
+/**
+ * struct ethtool_phy_stats - PHY-level statistics counters
+ * @rx_packets: Total successfully received frames
+ * @rx_bytes: Total successfully received bytes
+ * @rx_errors: Total received frames with errors (e.g., CRC errors)
+ * @tx_packets: Total successfully transmitted frames
+ * @tx_bytes: Total successfully transmitted bytes
+ * @tx_errors: Total transmitted frames with errors
+ *
+ * This structure provides a standardized interface for reporting
+ * PHY-level statistics counters. It is designed to expose statistics
+ * commonly provided by PHYs but not explicitly defined in the IEEE
+ * 802.3 standard.
+ */
+struct ethtool_phy_stats {
+	u64 rx_packets;
+	u64 rx_bytes;
+	u64 rx_errors;
+	u64 tx_packets;
+	u64 tx_bytes;
+	u64 tx_errors;
+};
+
 /* Basic IEEE 802.3 MAC Ctrl statistics (30.3.3.*), not otherwise exposed
  * via a more targeted API.
  */
@@ -391,7 +492,29 @@ struct ethtool_pause_stats {
 };
 
 #define ETHTOOL_MAX_LANES	8
+/*
+ * IEEE 802.3ck/df defines 16 bins for FEC histogram plus one more for
+ * the end-of-list marker, total 17 items
+ */
+#define ETHTOOL_FEC_HIST_MAX	17
+/**
+ * struct ethtool_fec_hist_range - error bits range for FEC histogram
+ * statistics
+ * @low: low bound of the bin (inclusive)
+ * @high: high bound of the bin (inclusive)
+ */
+struct ethtool_fec_hist_range {
+	u16 low;
+	u16 high;
+};
 
+struct ethtool_fec_hist {
+	struct ethtool_fec_hist_value {
+		u64 sum;
+		u64 per_lane[ETHTOOL_MAX_LANES];
+	} values[ETHTOOL_FEC_HIST_MAX];
+	const struct ethtool_fec_hist_range *ranges;
+};
 /**
  * struct ethtool_fec_stats - statistics for IEEE 802.3 FEC
  * @corrected_blocks: number of received blocks corrected by FEC
@@ -409,8 +532,10 @@ struct ethtool_pause_stats {
  *	not entire FEC data blocks. This is a non-standard statistic.
  *	Reported to user space as %ETHTOOL_A_FEC_STAT_CORR_BITS.
  *
- * @lane: per-lane/PCS-instance counts as defined by the standard
- * @total: error counts for the entire port, for drivers incapable of reporting
+ * For each of the above fields, the two substructure members are:
+ *
+ * - @lanes: per-lane/PCS-instance counts as defined by the standard
+ * - @total: error counts for the entire port, for drivers incapable of reporting
  *	per-lane stats
  *
  * Drivers should fill in either only total or per-lane statistics, core
@@ -433,7 +558,7 @@ struct ethtool_rmon_hist_range {
 	u16 high;
 };
 
-#define ETHTOOL_RMON_HIST_MAX	10
+#define ETHTOOL_RMON_HIST_MAX	11
 
 /**
  * struct ethtool_rmon_stats - selected RMON (RFC 2819) statistics
@@ -466,21 +591,47 @@ struct ethtool_rmon_stats {
 	);
 };
 
+/**
+ * struct ethtool_ts_stats - HW timestamping statistics
+ * @pkts: Number of packets successfully timestamped by the hardware.
+ * @onestep_pkts_unconfirmed: Number of PTP packets with one-step TX
+ *			      timestamping that were sent, but for which the
+ *			      device offers no confirmation whether they made
+ *			      it onto the wire and the timestamp was inserted
+ *			      in the originTimestamp or correctionField, or
+ *			      not.
+ * @lost: Number of hardware timestamping requests where the timestamping
+ *	information from the hardware never arrived for submission with
+ *	the skb.
+ * @err: Number of arbitrary timestamp generation error events that the
+ *	hardware encountered, exclusive of @lost statistics. Cases such
+ *	as resource exhaustion, unavailability, firmware errors, and
+ *	detected illogical timestamp values not submitted with the skb
+ *	are inclusive to this counter.
+ */
+struct ethtool_ts_stats {
+	struct_group(tx_stats,
+		u64 pkts;
+		u64 onestep_pkts_unconfirmed;
+		u64 lost;
+		u64 err;
+	);
+};
+
 #define ETH_MODULE_EEPROM_PAGE_LEN	128
 #define ETH_MODULE_MAX_I2C_ADDRESS	0x7f
 
 /**
- * struct ethtool_module_eeprom - EEPROM dump from specified page
- * @offset: Offset within the specified EEPROM page to begin read, in bytes.
- * @length: Number of bytes to read.
- * @page: Page number to read from.
- * @bank: Page bank number to read from, if applicable by EEPROM spec.
+ * struct ethtool_module_eeprom - plug-in module EEPROM read / write parameters
+ * @offset: When @offset is 0-127, it is used as an address to the Lower Memory
+ *	(@page must be 0). Otherwise, it is used as an address to the
+ *	Upper Memory.
+ * @length: Number of bytes to read / write.
+ * @page: Page number.
+ * @bank: Bank number, if supported by EEPROM spec.
  * @i2c_address: I2C address of a page. Value less than 0x7f expected. Most
  *	EEPROMs use 0x50 or 0x51.
  * @data: Pointer to buffer with EEPROM data of @length size.
- *
- * This can be used to manage pages during EEPROM dump in ethtool and pass
- * required information to the driver.
  */
 struct ethtool_module_eeprom {
 	u32	offset;
@@ -594,12 +745,169 @@ struct ethtool_mm_stats {
 	u64 MACMergeHoldCount;
 };
 
+enum ethtool_mmsv_event {
+	ETHTOOL_MMSV_LP_SENT_VERIFY_MPACKET,
+	ETHTOOL_MMSV_LD_SENT_VERIFY_MPACKET,
+	ETHTOOL_MMSV_LP_SENT_RESPONSE_MPACKET,
+};
+
+/* MAC Merge verification mPacket type */
+enum ethtool_mpacket {
+	ETHTOOL_MPACKET_VERIFY,
+	ETHTOOL_MPACKET_RESPONSE,
+};
+
+struct ethtool_mmsv;
+
+/**
+ * struct ethtool_mmsv_ops - Operations for MAC Merge Software Verification
+ * @configure_tx: Driver callback for the event where the preemptible TX
+ *		  becomes active or inactive. Preemptible traffic
+ *		  classes must be committed to hardware only while
+ *		  preemptible TX is active.
+ * @configure_pmac: Driver callback for the event where the pMAC state
+ *		    changes as result of an administrative setting
+ *		    (ethtool) or a call to ethtool_mmsv_link_state_handle().
+ * @send_mpacket: Driver-provided method for sending a Verify or a Response
+ *		  mPacket.
+ */
+struct ethtool_mmsv_ops {
+	void (*configure_tx)(struct ethtool_mmsv *mmsv, bool tx_active);
+	void (*configure_pmac)(struct ethtool_mmsv *mmsv, bool pmac_enabled);
+	void (*send_mpacket)(struct ethtool_mmsv *mmsv, enum ethtool_mpacket mpacket);
+};
+
+/**
+ * struct ethtool_mmsv - MAC Merge Software Verification
+ * @ops: operations for MAC Merge Software Verification
+ * @dev: pointer to net_device structure
+ * @lock: serialize access to MAC Merge state between
+ *	  ethtool requests and link state updates.
+ * @status: current verification FSM state
+ * @verify_timer: timer for verification in local TX direction
+ * @verify_enabled: indicates if verification is enabled
+ * @verify_retries: number of retries for verification
+ * @pmac_enabled: indicates if the preemptible MAC is enabled
+ * @verify_time: time for verification in milliseconds
+ * @tx_enabled: indicates if transmission is enabled
+ */
+struct ethtool_mmsv {
+	const struct ethtool_mmsv_ops *ops;
+	struct net_device *dev;
+	spinlock_t lock;
+	enum ethtool_mm_verify_status status;
+	struct timer_list verify_timer;
+	bool verify_enabled;
+	int verify_retries;
+	bool pmac_enabled;
+	u32 verify_time;
+	bool tx_enabled;
+};
+
+void ethtool_mmsv_stop(struct ethtool_mmsv *mmsv);
+void ethtool_mmsv_link_state_handle(struct ethtool_mmsv *mmsv, bool up);
+void ethtool_mmsv_event_handle(struct ethtool_mmsv *mmsv,
+			       enum ethtool_mmsv_event event);
+void ethtool_mmsv_get_mm(struct ethtool_mmsv *mmsv,
+			 struct ethtool_mm_state *state);
+void ethtool_mmsv_set_mm(struct ethtool_mmsv *mmsv, struct ethtool_mm_cfg *cfg);
+void ethtool_mmsv_init(struct ethtool_mmsv *mmsv, struct net_device *dev,
+		       const struct ethtool_mmsv_ops *ops);
+
+/**
+ * struct ethtool_rxfh_param - RXFH (RSS) parameters
+ * @hfunc: Defines the current RSS hash function used by HW (or to be set to).
+ *	Valid values are one of the %ETH_RSS_HASH_*.
+ * @indir_size: On SET, the array size of the user buffer for the
+ *	indirection table, which may be zero, or
+ *	%ETH_RXFH_INDIR_NO_CHANGE.  On GET (read from the driver),
+ *	the array size of the hardware indirection table.
+ * @indir: The indirection table of size @indir_size entries.
+ * @key_size: On SET, the array size of the user buffer for the hash key,
+ *	which may be zero.  On GET (read from the driver), the size of the
+ *	hardware hash key.
+ * @key: The hash key of size @key_size bytes.
+ * @rss_context: RSS context identifier.  Context 0 is the default for normal
+ *	traffic; other contexts can be referenced as the destination for RX flow
+ *	classification rules.  On SET, %ETH_RXFH_CONTEXT_ALLOC is used
+ *	to allocate a new RSS context; on return this field will
+ *	contain the ID of the newly allocated context.
+ * @rss_delete: Set to non-ZERO to remove the @rss_context context.
+ * @input_xfrm: Defines how the input data is transformed. Valid values are one
+ *	of %RXH_XFRM_*.
+ */
+struct ethtool_rxfh_param {
+	u8	hfunc;
+	u32	indir_size;
+	u32	*indir;
+	u32	key_size;
+	u8	*key;
+	u32	rss_context;
+	u8	rss_delete;
+	u8	input_xfrm;
+};
+
+/**
+ * struct ethtool_rxfh_fields - Rx Flow Hashing (RXFH) header field config
+ * @data: which header fields are used for hashing, bitmask of RXH_* defines
+ * @flow_type: L2-L4 network traffic flow type
+ * @rss_context: RSS context, will only be used if rxfh_per_ctx_fields is
+ *	set in struct ethtool_ops
+ */
+struct ethtool_rxfh_fields {
+	u32 data;
+	u32 flow_type;
+	u32 rss_context;
+};
+
+/**
+ * struct kernel_ethtool_ts_info - kernel copy of struct ethtool_ts_info
+ * @cmd: command number = %ETHTOOL_GET_TS_INFO
+ * @so_timestamping: bit mask of the sum of the supported SO_TIMESTAMPING flags
+ * @phc_index: device index of the associated PHC, or -1 if there is none
+ * @phc_qualifier: qualifier of the associated PHC
+ * @phc_source: source device of the associated PHC
+ * @phc_phyindex: index of PHY device source of the associated PHC
+ * @tx_types: bit mask of the supported hwtstamp_tx_types enumeration values
+ * @rx_filters: bit mask of the supported hwtstamp_rx_filters enumeration values
+ */
+struct kernel_ethtool_ts_info {
+	u32 cmd;
+	u32 so_timestamping;
+	int phc_index;
+	enum hwtstamp_provider_qualifier phc_qualifier;
+	enum hwtstamp_source phc_source;
+	int phc_phyindex;
+	u32 tx_types;
+	u32 rx_filters;
+};
+
 /**
  * struct ethtool_ops - optional netdev operations
+ * @supported_input_xfrm: supported types of input xfrm from %RXH_XFRM_*.
  * @cap_link_lanes_supported: indicates if the driver supports lanes
  *	parameter.
+ * @rxfh_per_ctx_fields: device supports selecting different header fields
+ *	for Rx hash calculation and RSS for each additional context.
+ * @rxfh_per_ctx_key: device supports setting different RSS key for each
+ *	additional context. Netlink API should report hfunc, key, and input_xfrm
+ *	for every context, not just context 0.
+ * @cap_rss_rxnfc_adds: device supports nonzero ring_cookie in filters with
+ *	%FLOW_RSS flag; the queue ID from the filter is added to the value from
+ *	the indirection table to determine the delivery queue.
+ * @rxfh_indir_space: max size of RSS indirection tables, if indirection table
+ *	size as returned by @get_rxfh_indir_size may change during lifetime
+ *	of the device. Leave as 0 if the table size is constant.
+ * @rxfh_key_space: same as @rxfh_indir_space, but for the key.
+ * @rxfh_priv_size: size of the driver private data area the core should
+ *	allocate for an RSS context (in &struct ethtool_rxfh_context).
+ * @rxfh_max_num_contexts: maximum (exclusive) supported RSS context ID.
+ *	If this is zero then the core may choose any (nonzero) ID, otherwise
+ *	the core will only use IDs strictly less than this value, as the
+ *	@rss_context argument to @create_rxfh_context and friends.
  * @supported_coalesce_params: supported types of interrupt coalescing.
  * @supported_ring_params: supported ring params.
+ * @supported_hwtstamp_qualifiers: bitfield of supported hwtstamp qualifier.
  * @get_drvinfo: Report driver/device information. Modern drivers no
  *	longer have to implement this callback. Most fields are
  *	correctly filled in by the core using system information, or
@@ -682,6 +990,7 @@ struct ethtool_mm_stats {
  * @reset: Reset (part of) the device, as specified by a bitmask of
  *	flags from &enum ethtool_reset_flags.  Returns a negative
  *	error code or zero.
+ * @get_rx_ring_count: Return the number of RX rings
  * @get_rxfh_key_size: Get the size of the RX flow hash key.
  *	Returns zero if not supported for this specific device.
  * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table.
@@ -694,15 +1003,34 @@ struct ethtool_mm_stats {
  *	will remain unchanged.
  *	Returns a negative error code or zero. An error code must be returned
  *	if at least one unsupported change was requested.
- * @get_rxfh_context: Get the contents of the RX flow hash indirection table,
- *	hash key, and/or hash function assiciated to the given rss context.
+ * @get_rxfh_fields: Get header fields used for flow hashing.
+ * @set_rxfh_fields: Set header fields used for flow hashing.
+ * @create_rxfh_context: Create a new RSS context with the specified RX flow
+ *	hash indirection table, hash key, and hash function.
+ *	The &struct ethtool_rxfh_context for this context is passed in @ctx;
+ *	note that the indir table, hkey and hfunc are not yet populated as
+ *	of this call.  The driver does not need to update these; the core
+ *	will do so if this op succeeds.
+ *	However, if @rxfh.indir is set to %NULL, the driver must update the
+ *	indir table in @ctx with the (default or inherited) table actually in
+ *	use; similarly, if @rxfh.key is %NULL, @rxfh.hfunc is
+ *	%ETH_RSS_HASH_NO_CHANGE, or @rxfh.input_xfrm is %RXH_XFRM_NO_CHANGE,
+ *	the driver should update the corresponding information in @ctx.
+ *	If the driver provides this method, it must also provide
+ *	@modify_rxfh_context and @remove_rxfh_context.
  *	Returns a negative error code or zero.
- * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting
+ * @modify_rxfh_context: Reconfigure the specified RSS context.  Allows setting
  *	the contents of the RX flow hash indirection table, hash key, and/or
- *	hash function associated to the given context. Arguments which are set
- *	to %NULL or zero will remain unchanged.
+ *	hash function associated with the given context.
+ *	Parameters which are set to %NULL or zero will remain unchanged.
+ *	The &struct ethtool_rxfh_context for this context is passed in @ctx;
+ *	note that it will still contain the *old* settings.  The driver does
+ *	not need to update these; the core will do so if this op succeeds.
  *	Returns a negative error code or zero. An error code must be returned
  *	if at least one unsupported change was requested.
+ * @remove_rxfh_context: Remove the specified RSS context.
+ *	The &struct ethtool_rxfh_context for this context is passed in @ctx.
+ *	Returns a negative error code or zero.
  * @get_channels: Get number of channels.
  * @set_channels: Set number of channels.  Returns a negative error code or
  *	zero.
@@ -714,6 +1042,10 @@ struct ethtool_mm_stats {
  *	It may be called with RCU, or rtnl or reference on the device.
  *	Drivers supporting transmit time stamps in software should set this to
  *	ethtool_op_get_ts_info().
+ * @get_ts_stats: Query the device hardware timestamping statistics. Drivers
+ *	must not zero statistics which they don't report. The stats structure
+ *	is initialized to ETHTOOL_STAT_NOT_SET indicating driver does not
+ *	report statistics.
  * @get_module_info: Get the size and type of the eeprom contained within
  *	a plug-in module.
  * @get_module_eeprom: Get the eeprom information from the plug-in module
@@ -757,6 +1089,8 @@ struct ethtool_mm_stats {
  * @get_module_eeprom_by_page: Get a region of plug-in module EEPROM data from
  *	specified page. Returns a negative error code or the amount of bytes
  *	read.
+ * @set_module_eeprom_by_page: Write to a region of plug-in module EEPROM,
+ *	from kernel space only. Returns a negative error code or zero.
  * @get_eth_phy_stats: Query some of the IEEE 802.3 PHY statistics.
  * @get_eth_mac_stats: Query some of the IEEE 802.3 MAC statistics.
  * @get_eth_ctrl_stats: Query some of the IEEE 802.3 MAC Ctrl statistics.
@@ -784,9 +1118,18 @@ struct ethtool_mm_stats {
  * of the generic netdev features interface.
  */
 struct ethtool_ops {
+	u32     supported_input_xfrm:8;
 	u32     cap_link_lanes_supported:1;
+	u32	rxfh_per_ctx_fields:1;
+	u32	rxfh_per_ctx_key:1;
+	u32	cap_rss_rxnfc_adds:1;
+	u32	rxfh_indir_space;
+	u16	rxfh_key_space;
+	u16	rxfh_priv_size;
+	u32	rxfh_max_num_contexts;
 	u32	supported_coalesce_params;
 	u32	supported_ring_params;
+	u32	supported_hwtstamp_qualifiers;
 	void	(*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *);
 	int	(*get_regs_len)(struct net_device *);
 	void	(*get_regs)(struct net_device *, struct ethtool_regs *, void *);
@@ -842,30 +1185,44 @@ struct ethtool_ops {
 	int	(*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *);
 	int	(*flash_device)(struct net_device *, struct ethtool_flash *);
 	int	(*reset)(struct net_device *, u32 *);
+	u32	(*get_rx_ring_count)(struct net_device *dev);
 	u32	(*get_rxfh_key_size)(struct net_device *);
 	u32	(*get_rxfh_indir_size)(struct net_device *);
-	int	(*get_rxfh)(struct net_device *, u32 *indir, u8 *key,
-			    u8 *hfunc);
-	int	(*set_rxfh)(struct net_device *, const u32 *indir,
-			    const u8 *key, const u8 hfunc);
-	int	(*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key,
-				    u8 *hfunc, u32 rss_context);
-	int	(*set_rxfh_context)(struct net_device *, const u32 *indir,
-				    const u8 *key, const u8 hfunc,
-				    u32 *rss_context, bool delete);
+	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
+	int	(*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
+			    struct netlink_ext_ack *extack);
+	int	(*get_rxfh_fields)(struct net_device *,
+				   struct ethtool_rxfh_fields *);
+	int	(*set_rxfh_fields)(struct net_device *,
+				   const struct ethtool_rxfh_fields *,
+				   struct netlink_ext_ack *extack);
+	int	(*create_rxfh_context)(struct net_device *,
+				       struct ethtool_rxfh_context *ctx,
+				       const struct ethtool_rxfh_param *rxfh,
+				       struct netlink_ext_ack *extack);
+	int	(*modify_rxfh_context)(struct net_device *,
+				       struct ethtool_rxfh_context *ctx,
+				       const struct ethtool_rxfh_param *rxfh,
+				       struct netlink_ext_ack *extack);
+	int	(*remove_rxfh_context)(struct net_device *,
+				       struct ethtool_rxfh_context *ctx,
+				       u32 rss_context,
+				       struct netlink_ext_ack *extack);
 	void	(*get_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*set_channels)(struct net_device *, struct ethtool_channels *);
 	int	(*get_dump_flag)(struct net_device *, struct ethtool_dump *);
 	int	(*get_dump_data)(struct net_device *,
 				 struct ethtool_dump *, void *);
 	int	(*set_dump)(struct net_device *, struct ethtool_dump *);
-	int	(*get_ts_info)(struct net_device *, struct ethtool_ts_info *);
+	int	(*get_ts_info)(struct net_device *, struct kernel_ethtool_ts_info *);
+	void	(*get_ts_stats)(struct net_device *dev,
+				struct ethtool_ts_stats *ts_stats);
 	int     (*get_module_info)(struct net_device *,
 				   struct ethtool_modinfo *);
 	int     (*get_module_eeprom)(struct net_device *,
 				     struct ethtool_eeprom *, u8 *);
-	int	(*get_eee)(struct net_device *, struct ethtool_eee *);
-	int	(*set_eee)(struct net_device *, struct ethtool_eee *);
+	int	(*get_eee)(struct net_device *dev, struct ethtool_keee *eee);
+	int	(*set_eee)(struct net_device *dev, struct ethtool_keee *eee);
 	int	(*get_tunable)(struct net_device *,
 			       const struct ethtool_tunable *, void *);
 	int	(*set_tunable)(struct net_device *,
@@ -879,7 +1236,8 @@ struct ethtool_ops {
 	int	(*set_link_ksettings)(struct net_device *,
 				      const struct ethtool_link_ksettings *);
 	void	(*get_fec_stats)(struct net_device *dev,
-				 struct ethtool_fec_stats *fec_stats);
+				 struct ethtool_fec_stats *fec_stats,
+				 struct ethtool_fec_hist *hist);
 	int	(*get_fecparam)(struct net_device *,
 				      struct ethtool_fecparam *);
 	int	(*set_fecparam)(struct net_device *,
@@ -893,6 +1251,9 @@ struct ethtool_ops {
 	int	(*get_module_eeprom_by_page)(struct net_device *dev,
 					     const struct ethtool_module_eeprom *page,
 					     struct netlink_ext_ack *extack);
+	int	(*set_module_eeprom_by_page)(struct net_device *dev,
+					     const struct ethtool_module_eeprom *page,
+					     struct netlink_ext_ack *extack);
 	void	(*get_eth_phy_stats)(struct net_device *dev,
 				     struct ethtool_eth_phy_stats *phy_stats);
 	void	(*get_eth_mac_stats)(struct net_device *dev,
@@ -935,6 +1296,21 @@ int ethtool_virtdev_set_link_ksettings(struct net_device *dev,
 				       const struct ethtool_link_ksettings *cmd,
 				       u32 *dev_speed, u8 *dev_duplex);
 
+/**
+ * struct ethtool_netdev_state - per-netdevice state for ethtool features
+ * @rss_ctx:		XArray of custom RSS contexts
+ * @rss_lock:		Protects entries in @rss_ctx.  May be taken from
+ *			within RTNL.
+ * @wol_enabled:	Wake-on-LAN is enabled
+ * @module_fw_flash_in_progress: Module firmware flashing is in progress.
+ */
+struct ethtool_netdev_state {
+	struct xarray		rss_ctx;
+	struct mutex		rss_lock;
+	unsigned		wol_enabled:1;
+	unsigned		module_fw_flash_in_progress:1;
+};
+
 struct phy_device;
 struct phy_tdr_config;
 struct phy_plca_cfg;
@@ -994,13 +1370,14 @@ ethtool_params_from_link_mode(struct ethtool_link_ksettings *link_ksettings,
  * @dev: pointer to net_device structure
  * @vclock_index: pointer to pointer of vclock index
  *
- * Return number of phc vclocks
+ * Return: number of phc vclocks
  */
 int ethtool_get_phc_vclocks(struct net_device *dev, int **vclock_index);
 
 /* Some generic methods drivers may use in their ethtool_ops */
 u32 ethtool_op_get_link(struct net_device *dev);
-int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti);
+int ethtool_op_get_ts_info(struct net_device *dev,
+			   struct kernel_ethtool_ts_info *eti);
 
 /**
  * ethtool_mm_frag_size_add_to_min - Translate (standard) additional fragment
@@ -1044,12 +1421,64 @@ static inline int ethtool_mm_frag_size_min_to_add(u32 val_min, u32 *val_add,
 }
 
 /**
+ * ethtool_get_ts_info_by_layer - Obtains time stamping capabilities from the MAC or PHY layer.
+ * @dev: pointer to net_device structure
+ * @info: buffer to hold the result
+ * Returns: zero on success, non-zero otherwise.
+ */
+int ethtool_get_ts_info_by_layer(struct net_device *dev,
+				 struct kernel_ethtool_ts_info *info);
+
+/**
  * ethtool_sprintf - Write formatted string to ethtool string data
- * @data: Pointer to start of string to update
+ * @data: Pointer to a pointer to the start of string to update
  * @fmt: Format of string to write
  *
- * Write formatted string to data. Update data to point at start of
+ * Write formatted string to *data. Update *data to point at start of
  * next string.
  */
 extern __printf(2, 3) void ethtool_sprintf(u8 **data, const char *fmt, ...);
+
+/**
+ * ethtool_puts - Write string to ethtool string data
+ * @data: Pointer to a pointer to the start of string to update
+ * @str: String to write
+ *
+ * Write string to *data without a trailing newline. Update *data
+ * to point at start of next string.
+ *
+ * Prefer this function to ethtool_sprintf() when given only
+ * two arguments or if @fmt is just "%s".
+ */
+extern void ethtool_puts(u8 **data, const char *str);
+
+/**
+ * ethtool_cpy - Write possibly-not-NUL-terminated string to ethtool string data
+ * @data: Pointer to a pointer to the start of string to write into
+ * @str: NUL-byte padded char array of size ETH_GSTRING_LEN to copy from
+ */
+#define ethtool_cpy(data, str)	do {				\
+	BUILD_BUG_ON(sizeof(str) != ETH_GSTRING_LEN);		\
+	memcpy(*(data), str, ETH_GSTRING_LEN);			\
+	*(data) += ETH_GSTRING_LEN;				\
+} while (0)
+
+/* Link mode to forced speed capabilities maps */
+struct ethtool_forced_speed_map {
+	u32		speed;
+	__ETHTOOL_DECLARE_LINK_MODE_MASK(caps);
+
+	const u32	*cap_arr;
+	u32		arr_size;
+};
+
+#define ETHTOOL_FORCED_SPEED_MAP(prefix, value)				\
+{									\
+	.speed		= SPEED_##value,				\
+	.cap_arr	= prefix##_##value,				\
+	.arr_size	= ARRAY_SIZE(prefix##_##value),			\
+}
+
+void
+ethtool_forced_speed_maps_init(struct ethtool_forced_speed_map *maps, u32 size);
 #endif /* _LINUX_ETHTOOL_H */
diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h
index fae0dfb9a9c8..39254b2726c0 100644
--- a/include/linux/ethtool_netlink.h
+++ b/include/linux/ethtool_netlink.h
@@ -23,8 +23,10 @@ struct phy_device;
 int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd);
 void ethnl_cable_test_free(struct phy_device *phydev);
 void ethnl_cable_test_finished(struct phy_device *phydev);
-int ethnl_cable_test_result(struct phy_device *phydev, u8 pair, u8 result);
-int ethnl_cable_test_fault_length(struct phy_device *phydev, u8 pair, u32 cm);
+int ethnl_cable_test_result_with_src(struct phy_device *phydev, u8 pair,
+				     u8 result, u32 src);
+int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev, u8 pair,
+					   u32 cm, u32 src);
 int ethnl_cable_test_amplitude(struct phy_device *phydev, u8 pair, s16 mV);
 int ethnl_cable_test_pulse(struct phy_device *phydev, u16 mV);
 int ethnl_cable_test_step(struct phy_device *phydev, u32 first, u32 last,
@@ -41,6 +43,8 @@ void ethtool_aggregate_rmon_stats(struct net_device *dev,
 				  struct ethtool_rmon_stats *rmon_stats);
 bool ethtool_dev_mm_supported(struct net_device *dev);
 
+void ethnl_pse_send_ntf(struct net_device *netdev, unsigned long notif);
+
 #else
 static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd)
 {
@@ -54,14 +58,14 @@ static inline void ethnl_cable_test_free(struct phy_device *phydev)
 static inline void ethnl_cable_test_finished(struct phy_device *phydev)
 {
 }
-static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair,
-					  u8 result)
+static inline int ethnl_cable_test_result_with_src(struct phy_device *phydev,
+						   u8 pair, u8 result, u32 src)
 {
 	return -EOPNOTSUPP;
 }
 
-static inline int ethnl_cable_test_fault_length(struct phy_device *phydev,
-						u8 pair, u32 cm)
+static inline int ethnl_cable_test_fault_length_with_src(struct phy_device *phydev,
+							 u8 pair, u32 cm, u32 src)
 {
 	return -EOPNOTSUPP;
 }
@@ -118,5 +122,25 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev)
 	return false;
 }
 
+static inline void ethnl_pse_send_ntf(struct net_device *netdev,
+				      unsigned long notif)
+{
+}
+
 #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */
+
+static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair,
+					  u8 result)
+{
+	return ethnl_cable_test_result_with_src(phydev, pair, result,
+						ETHTOOL_A_CABLE_INF_SRC_TDR);
+}
+
+static inline int ethnl_cable_test_fault_length(struct phy_device *phydev,
+						u8 pair, u32 cm)
+{
+	return ethnl_cable_test_fault_length_with_src(phydev, pair, cm,
+						      ETHTOOL_A_CABLE_INF_SRC_TDR);
+}
+
 #endif /* _LINUX_ETHTOOL_NETLINK_H_ */
diff --git a/include/linux/eventfd.h b/include/linux/eventfd.h
index 36a486505b08..e32bee4345fb 100644
--- a/include/linux/eventfd.h
+++ b/include/linux/eventfd.h
@@ -9,12 +9,12 @@
 #ifndef _LINUX_EVENTFD_H
 #define _LINUX_EVENTFD_H
 
-#include <linux/fcntl.h>
 #include <linux/wait.h>
 #include <linux/err.h>
 #include <linux/percpu-defs.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <uapi/linux/eventfd.h>
 
 /*
  * CAREFUL: Check include/uapi/asm-generic/fcntl.h when defining
@@ -23,10 +23,6 @@
  * from eventfd, in order to leave a free define-space for
  * shared O_* flags.
  */
-#define EFD_SEMAPHORE (1 << 0)
-#define EFD_CLOEXEC O_CLOEXEC
-#define EFD_NONBLOCK O_NONBLOCK
-
 #define EFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
 #define EFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS | EFD_SEMAPHORE)
 
@@ -39,8 +35,7 @@ void eventfd_ctx_put(struct eventfd_ctx *ctx);
 struct file *eventfd_fget(int fd);
 struct eventfd_ctx *eventfd_ctx_fdget(int fd);
 struct eventfd_ctx *eventfd_ctx_fileget(struct file *file);
-__u64 eventfd_signal(struct eventfd_ctx *ctx, __u64 n);
-__u64 eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n, unsigned mask);
+void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask);
 int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt);
 void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt);
@@ -62,15 +57,8 @@ static inline struct eventfd_ctx *eventfd_ctx_fdget(int fd)
 	return ERR_PTR(-ENOSYS);
 }
 
-static inline int eventfd_signal(struct eventfd_ctx *ctx, __u64 n)
+static inline void eventfd_signal_mask(struct eventfd_ctx *ctx, __poll_t mask)
 {
-	return -ENOSYS;
-}
-
-static inline int eventfd_signal_mask(struct eventfd_ctx *ctx, __u64 n,
-				      unsigned mask)
-{
-	return -ENOSYS;
 }
 
 static inline void eventfd_ctx_put(struct eventfd_ctx *ctx)
@@ -96,5 +84,10 @@ static inline void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
 
 #endif
 
+static inline void eventfd_signal(struct eventfd_ctx *ctx)
+{
+	eventfd_signal_mask(ctx, 0);
+}
+
 #endif /* _LINUX_EVENTFD_H */
 
diff --git a/include/linux/eventpoll.h b/include/linux/eventpoll.h
index 3337745d81bd..ccb478eb174b 100644
--- a/include/linux/eventpoll.h
+++ b/include/linux/eventpoll.h
@@ -25,6 +25,10 @@ struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long t
 /* Used to release the epoll bits inside the "struct file" */
 void eventpoll_release_file(struct file *file);
 
+/* Copy ready events to userspace */
+int epoll_sendevents(struct file *file, struct epoll_event __user *events,
+		     int maxevents);
+
 /*
  * This is called from inside fs/file_table.c:__fput() to unlink files
  * from the eventpoll interface. We need to have this facility to cleanup
@@ -42,7 +46,7 @@ static inline void eventpoll_release(struct file *file)
 	 * because the file in on the way to be removed and nobody ( but
 	 * eventpoll ) has still a reference to this file.
 	 */
-	if (likely(!file->f_ep))
+	if (likely(!READ_ONCE(file->f_ep)))
 		return;
 
 	/*
diff --git a/include/linux/evm.h b/include/linux/evm.h
index 7dc1ee74169f..ddece4a6b25d 100644
--- a/include/linux/evm.h
+++ b/include/linux/evm.h
@@ -12,58 +12,22 @@
 #include <linux/integrity.h>
 #include <linux/xattr.h>
 
-struct integrity_iint_cache;
-
 #ifdef CONFIG_EVM
 extern int evm_set_key(void *key, size_t keylen);
 extern enum integrity_status evm_verifyxattr(struct dentry *dentry,
 					     const char *xattr_name,
 					     void *xattr_value,
-					     size_t xattr_value_len,
-					     struct integrity_iint_cache *iint);
-extern int evm_inode_setattr(struct mnt_idmap *idmap,
-			     struct dentry *dentry, struct iattr *attr);
-extern void evm_inode_post_setattr(struct dentry *dentry, int ia_valid);
-extern int evm_inode_setxattr(struct mnt_idmap *idmap,
-			      struct dentry *dentry, const char *name,
-			      const void *value, size_t size);
-extern void evm_inode_post_setxattr(struct dentry *dentry,
-				    const char *xattr_name,
-				    const void *xattr_value,
-				    size_t xattr_value_len);
-extern int evm_inode_removexattr(struct mnt_idmap *idmap,
-				 struct dentry *dentry, const char *xattr_name);
-extern void evm_inode_post_removexattr(struct dentry *dentry,
-				       const char *xattr_name);
-static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap,
-					     struct dentry *dentry,
-					     const char *acl_name)
-{
-	evm_inode_post_removexattr(dentry, acl_name);
-}
-extern int evm_inode_set_acl(struct mnt_idmap *idmap,
-			     struct dentry *dentry, const char *acl_name,
-			     struct posix_acl *kacl);
-static inline int evm_inode_remove_acl(struct mnt_idmap *idmap,
-				       struct dentry *dentry,
-				       const char *acl_name)
-{
-	return evm_inode_set_acl(idmap, dentry, acl_name, NULL);
-}
-static inline void evm_inode_post_set_acl(struct dentry *dentry,
-					  const char *acl_name,
-					  struct posix_acl *kacl)
-{
-	return evm_inode_post_setxattr(dentry, acl_name, NULL, 0);
-}
-extern int evm_inode_init_security(struct inode *inode,
-				   const struct xattr *xattr_array,
-				   struct xattr *evm);
+					     size_t xattr_value_len);
+int evm_inode_init_security(struct inode *inode, struct inode *dir,
+			    const struct qstr *qstr, struct xattr *xattrs,
+			    int *xattr_count);
 extern bool evm_revalidate_status(const char *xattr_name);
 extern int evm_protected_xattr_if_enabled(const char *req_xattr_name);
 extern int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer,
 				     int buffer_size, char type,
 				     bool canonical_fmt);
+extern bool evm_metadata_changed(struct inode *inode,
+				 struct inode *metadata_inode);
 #ifdef CONFIG_FS_POSIX_ACL
 extern int posix_xattr_acl(const char *xattrname);
 #else
@@ -83,83 +47,16 @@ static inline int evm_set_key(void *key, size_t keylen)
 static inline enum integrity_status evm_verifyxattr(struct dentry *dentry,
 						    const char *xattr_name,
 						    void *xattr_value,
-						    size_t xattr_value_len,
-					struct integrity_iint_cache *iint)
+						    size_t xattr_value_len)
 {
 	return INTEGRITY_UNKNOWN;
 }
 #endif
 
-static inline int evm_inode_setattr(struct mnt_idmap *idmap,
-				    struct dentry *dentry, struct iattr *attr)
-{
-	return 0;
-}
-
-static inline void evm_inode_post_setattr(struct dentry *dentry, int ia_valid)
-{
-	return;
-}
-
-static inline int evm_inode_setxattr(struct mnt_idmap *idmap,
-				     struct dentry *dentry, const char *name,
-				     const void *value, size_t size)
-{
-	return 0;
-}
-
-static inline void evm_inode_post_setxattr(struct dentry *dentry,
-					   const char *xattr_name,
-					   const void *xattr_value,
-					   size_t xattr_value_len)
-{
-	return;
-}
-
-static inline int evm_inode_removexattr(struct mnt_idmap *idmap,
-					struct dentry *dentry,
-					const char *xattr_name)
-{
-	return 0;
-}
-
-static inline void evm_inode_post_removexattr(struct dentry *dentry,
-					      const char *xattr_name)
-{
-	return;
-}
-
-static inline void evm_inode_post_remove_acl(struct mnt_idmap *idmap,
-					     struct dentry *dentry,
-					     const char *acl_name)
-{
-	return;
-}
-
-static inline int evm_inode_set_acl(struct mnt_idmap *idmap,
-				    struct dentry *dentry, const char *acl_name,
-				    struct posix_acl *kacl)
-{
-	return 0;
-}
-
-static inline int evm_inode_remove_acl(struct mnt_idmap *idmap,
-				       struct dentry *dentry,
-				       const char *acl_name)
-{
-	return 0;
-}
-
-static inline void evm_inode_post_set_acl(struct dentry *dentry,
-					  const char *acl_name,
-					  struct posix_acl *kacl)
-{
-	return;
-}
-
-static inline int evm_inode_init_security(struct inode *inode,
-					  const struct xattr *xattr_array,
-					  struct xattr *evm)
+static inline int evm_inode_init_security(struct inode *inode, struct inode *dir,
+					  const struct qstr *qstr,
+					  struct xattr *xattrs,
+					  int *xattr_count)
 {
 	return 0;
 }
@@ -181,5 +78,11 @@ static inline int evm_read_protected_xattrs(struct dentry *dentry, u8 *buffer,
 	return -EOPNOTSUPP;
 }
 
+static inline bool evm_metadata_changed(struct inode *inode,
+					struct inode *metadata_inode)
+{
+	return false;
+}
+
 #endif /* CONFIG_EVM */
 #endif /* LINUX_EVM_H */
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
new file mode 100644
index 000000000000..7de229134e30
--- /dev/null
+++ b/include/linux/execmem.h
@@ -0,0 +1,207 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_EXECMEM_ALLOC_H
+#define _LINUX_EXECMEM_ALLOC_H
+
+#include <linux/types.h>
+#include <linux/moduleloader.h>
+#include <linux/cleanup.h>
+
+#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
+		!defined(CONFIG_KASAN_VMALLOC)
+#include <linux/kasan.h>
+#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
+#else
+#define MODULE_ALIGN PAGE_SIZE
+#endif
+
+/**
+ * enum execmem_type - types of executable memory ranges
+ *
+ * There are several subsystems that allocate executable memory.
+ * Architectures define different restrictions on placement,
+ * permissions, alignment and other parameters for memory that can be used
+ * by these subsystems.
+ * Types in this enum identify subsystems that allocate executable memory
+ * and let architectures define parameters for ranges suitable for
+ * allocations by each subsystem.
+ *
+ * @EXECMEM_DEFAULT: default parameters that would be used for types that
+ * are not explicitly defined.
+ * @EXECMEM_MODULE_TEXT: parameters for module text sections
+ * @EXECMEM_KPROBES: parameters for kprobes
+ * @EXECMEM_FTRACE: parameters for ftrace
+ * @EXECMEM_BPF: parameters for BPF
+ * @EXECMEM_MODULE_DATA: parameters for module data sections
+ * @EXECMEM_TYPE_MAX:
+ */
+enum execmem_type {
+	EXECMEM_DEFAULT,
+	EXECMEM_MODULE_TEXT = EXECMEM_DEFAULT,
+	EXECMEM_KPROBES,
+	EXECMEM_FTRACE,
+	EXECMEM_BPF,
+	EXECMEM_MODULE_DATA,
+	EXECMEM_TYPE_MAX,
+};
+
+/**
+ * enum execmem_range_flags - options for executable memory allocations
+ * @EXECMEM_KASAN_SHADOW:	allocate kasan shadow
+ * @EXECMEM_ROX_CACHE:		allocations should use ROX cache of huge pages
+ */
+enum execmem_range_flags {
+	EXECMEM_KASAN_SHADOW	= (1 << 0),
+	EXECMEM_ROX_CACHE	= (1 << 1),
+};
+
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
+/**
+ * execmem_fill_trapping_insns - set memory to contain instructions that
+ *				 will trap
+ * @ptr:	pointer to memory to fill
+ * @size:	size of the range to fill
+ *
+ * A hook for architecures to fill execmem ranges with invalid instructions.
+ * Architectures that use EXECMEM_ROX_CACHE must implement this.
+ */
+void execmem_fill_trapping_insns(void *ptr, size_t size);
+
+/**
+ * execmem_restore_rox - restore read-only-execute permissions
+ * @ptr:	address of the region to remap
+ * @size:	size of the region to remap
+ *
+ * Restores read-only-execute permissions on a range [@ptr, @ptr + @size)
+ * after it was temporarily remapped as writable. Relies on architecture
+ * implementation of set_memory_rox() to restore mapping using large pages.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int execmem_restore_rox(void *ptr, size_t size);
+#else
+static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
+#endif
+
+/**
+ * struct execmem_range - definition of an address space suitable for code and
+ *			  related data allocations
+ * @start:	address space start
+ * @end:	address space end (inclusive)
+ * @fallback_start: start of the secondary address space range for fallback
+ *                  allocations on architectures that require it
+ * @fallback_end:   start of the secondary address space (inclusive)
+ * @pgprot:	permissions for memory in this address space
+ * @alignment:	alignment required for text allocations
+ * @flags:	options for memory allocations for this range
+ */
+struct execmem_range {
+	unsigned long   start;
+	unsigned long   end;
+	unsigned long   fallback_start;
+	unsigned long   fallback_end;
+	pgprot_t        pgprot;
+	unsigned int	alignment;
+	enum execmem_range_flags flags;
+};
+
+/**
+ * struct execmem_info - architecture parameters for code allocations
+ * @ranges: array of parameter sets defining architecture specific
+ * parameters for executable memory allocations. The ranges that are not
+ * explicitly initialized by an architecture use parameters defined for
+ * @EXECMEM_DEFAULT.
+ */
+struct execmem_info {
+	struct execmem_range	ranges[EXECMEM_TYPE_MAX];
+};
+
+/**
+ * execmem_arch_setup - define parameters for allocations of executable memory
+ *
+ * A hook for architectures to define parameters for allocations of
+ * executable memory. These parameters should be filled into the
+ * @execmem_info structure.
+ *
+ * For architectures that do not implement this method a default set of
+ * parameters will be used
+ *
+ * Return: a structure defining architecture parameters and restrictions
+ * for allocations of executable memory
+ */
+struct execmem_info *execmem_arch_setup(void);
+
+/**
+ * execmem_alloc - allocate executable memory
+ * @type: type of the allocation
+ * @size: how many bytes of memory are required
+ *
+ * Allocates memory that will contain executable code, either generated or
+ * loaded from kernel modules.
+ *
+ * Allocates memory that will contain data coupled with executable code,
+ * like data sections in kernel modules.
+ *
+ * The memory will have protections defined by architecture for executable
+ * region of the @type.
+ *
+ * Return: a pointer to the allocated memory or %NULL
+ */
+void *execmem_alloc(enum execmem_type type, size_t size);
+
+/**
+ * execmem_alloc_rw - allocate writable executable memory
+ * @type: type of the allocation
+ * @size: how many bytes of memory are required
+ *
+ * Allocates memory that will contain executable code, either generated or
+ * loaded from kernel modules.
+ *
+ * Allocates memory that will contain data coupled with executable code,
+ * like data sections in kernel modules.
+ *
+ * Forces writable permissions on the allocated memory and the caller is
+ * responsible to manage the permissions afterwards.
+ *
+ * For architectures that use ROX cache the permissions will be set to R+W.
+ * For architectures that don't use ROX cache the default permissions for @type
+ * will be used as they must be writable.
+ *
+ * Return: a pointer to the allocated memory or %NULL
+ */
+void *execmem_alloc_rw(enum execmem_type type, size_t size);
+
+/**
+ * execmem_free - free executable memory
+ * @ptr: pointer to the memory that should be freed
+ */
+void execmem_free(void *ptr);
+
+DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T));
+
+#ifdef CONFIG_MMU
+/**
+ * execmem_vmap - create virtual mapping for EXECMEM_MODULE_DATA memory
+ * @size: size of the virtual mapping in bytes
+ *
+ * Maps virtually contiguous area in the range suitable for EXECMEM_MODULE_DATA.
+ *
+ * Return: the area descriptor on success or %NULL on failure.
+ */
+struct vm_struct *execmem_vmap(size_t size);
+#endif
+
+/**
+ * execmem_is_rox - check if execmem is read-only
+ * @type - the execmem type to check
+ *
+ * Return: %true if the @type is read-only, %false if it's writable
+ */
+bool execmem_is_rox(enum execmem_type type);
+
+#if defined(CONFIG_EXECMEM) && !defined(CONFIG_ARCH_WANTS_EXECMEM_LATE)
+void execmem_init(void);
+#else
+static inline void execmem_init(void) {}
+#endif
+
+#endif /* _LINUX_EXECMEM_ALLOC_H */
diff --git a/include/linux/export-internal.h b/include/linux/export-internal.h
index fe7e6ba918f1..d445705ac13c 100644
--- a/include/linux/export-internal.h
+++ b/include/linux/export-internal.h
@@ -10,8 +10,61 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 
+#if defined(CONFIG_HAVE_ARCH_PREL32_RELOCATIONS)
+/*
+ * relative reference: this reduces the size by half on 64-bit architectures,
+ * and eliminates the need for absolute relocations that require runtime
+ * processing on relocatable kernels.
+ */
+#define __KSYM_ALIGN		".balign 4"
+#define __KSYM_REF(sym)		".long " #sym "- ."
+#elif defined(CONFIG_64BIT)
+#define __KSYM_ALIGN		".balign 8"
+#define __KSYM_REF(sym)		".quad " #sym
+#else
+#define __KSYM_ALIGN		".balign 4"
+#define __KSYM_REF(sym)		".long " #sym
+#endif
+
+/*
+ * For every exported symbol, do the following:
+ *
+ * - Put the name of the symbol and namespace (empty string "" for none) in
+ *   __ksymtab_strings.
+ * - Place a struct kernel_symbol entry in the __ksymtab section.
+ *
+ * Note on .section use: we specify progbits since usage of the "M" (SHF_MERGE)
+ * section flag requires it. Use '%progbits' instead of '@progbits' since the
+ * former apparently works on all arches according to the binutils source.
+ */
+#define __KSYMTAB(name, sym, sec, ns)						\
+	asm("	.section \"__ksymtab_strings\",\"aMS\",%progbits,1"	"\n"	\
+	    "__kstrtab_" #name ":"					"\n"	\
+	    "	.asciz \"" #name "\""					"\n"	\
+	    "__kstrtabns_" #name ":"					"\n"	\
+	    "	.asciz \"" ns "\""					"\n"	\
+	    "	.previous"						"\n"	\
+	    "	.section \"___ksymtab" sec "+" #name "\", \"a\""	"\n"	\
+		__KSYM_ALIGN						"\n"	\
+	    "__ksymtab_" #name ":"					"\n"	\
+		__KSYM_REF(sym)						"\n"	\
+		__KSYM_REF(__kstrtab_ ##name)				"\n"	\
+		__KSYM_REF(__kstrtabns_ ##name)				"\n"	\
+	    "	.previous"						"\n"	\
+	)
+
+#if defined(CONFIG_PARISC) && defined(CONFIG_64BIT)
+#define KSYM_FUNC(name)		P%name
+#else
+#define KSYM_FUNC(name)		name
+#endif
+
+#define KSYMTAB_FUNC(name, sec, ns)	__KSYMTAB(name, KSYM_FUNC(name), sec, ns)
+#define KSYMTAB_DATA(name, sec, ns)	__KSYMTAB(name, name, sec, ns)
+
 #define SYMBOL_CRC(sym, crc, sec)   \
 	asm(".section \"___kcrctab" sec "+" #sym "\",\"a\""	"\n" \
+	    ".balign 4"						"\n" \
 	    "__crc_" #sym ":"					"\n" \
 	    ".long " #crc					"\n" \
 	    ".previous"						"\n")
diff --git a/include/linux/export.h b/include/linux/export.h
index 3f31ced0d977..a686fd0ba406 100644
--- a/include/linux/export.h
+++ b/include/linux/export.h
@@ -2,18 +2,11 @@
 #ifndef _LINUX_EXPORT_H
 #define _LINUX_EXPORT_H
 
+#include <linux/compiler.h>
+#include <linux/linkage.h>
 #include <linux/stringify.h>
 
 /*
- * Export symbols from the kernel to modules.  Forked from module.h
- * to reduce the amount of pointless cruft we feed to gcc when only
- * exporting a simple symbol or two.
- *
- * Try not to add #includes here.  It slows compilation and makes kernel
- * hackers place grumpy comments in header files.
- */
-
-/*
  * This comment block is used by fixdep. Please do not remove.
  *
  * When CONFIG_MODVERSIONS is changed from n to y, all source files having
@@ -21,137 +14,83 @@
  * side effect of the *.o build rule.
  */
 
-#ifndef __ASSEMBLY__
-#ifdef MODULE
-extern struct module __this_module;
-#define THIS_MODULE (&__this_module)
+#ifdef CONFIG_64BIT
+#define __EXPORT_SYMBOL_REF(sym)			\
+	.balign 8				ASM_NL	\
+	.quad sym
 #else
-#define THIS_MODULE ((struct module *)0)
+#define __EXPORT_SYMBOL_REF(sym)			\
+	.balign 4				ASM_NL	\
+	.long sym
 #endif
 
-#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
-#include <linux/compiler.h>
 /*
- * Emit the ksymtab entry as a pair of relative references: this reduces
- * the size by half on 64-bit architectures, and eliminates the need for
- * absolute relocations that require runtime processing on relocatable
- * kernels.
- */
-#define __KSYMTAB_ENTRY(sym, sec)					\
-	__ADDRESSABLE(sym)						\
-	asm("	.section \"___ksymtab" sec "+" #sym "\", \"a\"	\n"	\
-	    "	.balign	4					\n"	\
-	    "__ksymtab_" #sym ":				\n"	\
-	    "	.long	" #sym "- .				\n"	\
-	    "	.long	__kstrtab_" #sym "- .			\n"	\
-	    "	.long	__kstrtabns_" #sym "- .			\n"	\
-	    "	.previous					\n")
-
-struct kernel_symbol {
-	int value_offset;
-	int name_offset;
-	int namespace_offset;
-};
-#else
-#define __KSYMTAB_ENTRY(sym, sec)					\
-	static const struct kernel_symbol __ksymtab_##sym		\
-	__attribute__((section("___ksymtab" sec "+" #sym), used))	\
-	__aligned(sizeof(void *))					\
-	= { (unsigned long)&sym, __kstrtab_##sym, __kstrtabns_##sym }
-
-struct kernel_symbol {
-	unsigned long value;
-	const char *name;
-	const char *namespace;
-};
-#endif
-
-#ifdef __GENKSYMS__
-
-#define ___EXPORT_SYMBOL(sym, sec, ns)	__GENKSYMS_EXPORT_SYMBOL(sym)
-
-#else
-
-/*
- * For every exported symbol, do the following:
- *
- * - Put the name of the symbol and namespace (empty string "" for none) in
- *   __ksymtab_strings.
- * - Place a struct kernel_symbol entry in the __ksymtab section.
+ * LLVM integrated assembler cam merge adjacent string literals (like
+ * C and GNU-as) passed to '.ascii', but not to '.asciz' and chokes on:
  *
- * note on .section use: we specify progbits since usage of the "M" (SHF_MERGE)
- * section flag requires it. Use '%progbits' instead of '@progbits' since the
- * former apparently works on all arches according to the binutils source.
+ *   .asciz "MODULE_" "kvm" ;
  */
-#define ___EXPORT_SYMBOL(sym, sec, ns)						\
-	extern typeof(sym) sym;							\
-	extern const char __kstrtab_##sym[];					\
-	extern const char __kstrtabns_##sym[];					\
-	asm("	.section \"__ksymtab_strings\",\"aMS\",%progbits,1	\n"	\
-	    "__kstrtab_" #sym ":					\n"	\
-	    "	.asciz 	\"" #sym "\"					\n"	\
-	    "__kstrtabns_" #sym ":					\n"	\
-	    "	.asciz 	\"" ns "\"					\n"	\
-	    "	.previous						\n");	\
-	__KSYMTAB_ENTRY(sym, sec)
+#define ___EXPORT_SYMBOL(sym, license, ns...)		\
+	.section ".export_symbol","a"		ASM_NL	\
+	__export_symbol_##sym:			ASM_NL	\
+		.asciz license			ASM_NL	\
+		.ascii ns "\0"			ASM_NL	\
+		__EXPORT_SYMBOL_REF(sym)	ASM_NL	\
+	.previous
 
-#endif
-
-#if !defined(CONFIG_MODULES) || defined(__DISABLE_EXPORTS)
+#if defined(__DISABLE_EXPORTS)
 
 /*
  * Allow symbol exports to be disabled completely so that C code may
  * be reused in other execution contexts such as the UEFI stub or the
  * decompressor.
  */
-#define __EXPORT_SYMBOL(sym, sec, ns)
+#define __EXPORT_SYMBOL(sym, license, ns)
+
+#elif defined(__GENKSYMS__)
 
-#elif defined(CONFIG_TRIM_UNUSED_KSYMS)
+#define __EXPORT_SYMBOL(sym, license, ns)	__GENKSYMS_EXPORT_SYMBOL(sym)
 
-#include <generated/autoksyms.h>
+#elif defined(__ASSEMBLY__)
 
+#define __EXPORT_SYMBOL(sym, license, ns) \
+	___EXPORT_SYMBOL(sym, license, ns)
+
+#else
+
+#ifdef CONFIG_GENDWARFKSYMS
 /*
- * For fine grained build dependencies, we want to tell the build system
- * about each possible exported symbol even if they're not actually exported.
- * We use a symbol pattern __ksym_marker_<symbol> that the build system filters
- * from the $(NM) output (see scripts/gen_ksymdeps.sh). These symbols are
- * discarded in the final link stage.
+ * With CONFIG_GENDWARFKSYMS, ensure the compiler emits debugging
+ * information for all exported symbols, including those defined in
+ * different TUs, by adding a __gendwarfksyms_ptr_<symbol> pointer
+ * that's discarded during the final link.
  */
-#define __ksym_marker(sym)	\
-	static int __ksym_marker_##sym[0] __section(".discard.ksym") __used
-
-#define __EXPORT_SYMBOL(sym, sec, ns)					\
-	__ksym_marker(sym);						\
-	__cond_export_sym(sym, sec, ns, __is_defined(__KSYM_##sym))
-#define __cond_export_sym(sym, sec, ns, conf)				\
-	___cond_export_sym(sym, sec, ns, conf)
-#define ___cond_export_sym(sym, sec, ns, enabled)			\
-	__cond_export_sym_##enabled(sym, sec, ns)
-#define __cond_export_sym_1(sym, sec, ns) ___EXPORT_SYMBOL(sym, sec, ns)
-
-#ifdef __GENKSYMS__
-#define __cond_export_sym_0(sym, sec, ns) __GENKSYMS_EXPORT_SYMBOL(sym)
+#define __GENDWARFKSYMS_EXPORT(sym)				\
+	static typeof(sym) *__gendwarfksyms_ptr_##sym __used	\
+		__section(".discard.gendwarfksyms") = &sym;
 #else
-#define __cond_export_sym_0(sym, sec, ns) /* nothing */
+#define __GENDWARFKSYMS_EXPORT(sym)
 #endif
 
-#else
-
-#define __EXPORT_SYMBOL(sym, sec, ns)	___EXPORT_SYMBOL(sym, sec, ns)
+#define __EXPORT_SYMBOL(sym, license, ns)			\
+	extern typeof(sym) sym;					\
+	__ADDRESSABLE(sym)					\
+	__GENDWARFKSYMS_EXPORT(sym)				\
+	asm(__stringify(___EXPORT_SYMBOL(sym, license, ns)))
 
-#endif /* CONFIG_MODULES */
+#endif
 
 #ifdef DEFAULT_SYMBOL_NAMESPACE
-#define _EXPORT_SYMBOL(sym, sec)	__EXPORT_SYMBOL(sym, sec, __stringify(DEFAULT_SYMBOL_NAMESPACE))
+#define _EXPORT_SYMBOL(sym, license)	__EXPORT_SYMBOL(sym, license, DEFAULT_SYMBOL_NAMESPACE)
 #else
-#define _EXPORT_SYMBOL(sym, sec)	__EXPORT_SYMBOL(sym, sec, "")
+#define _EXPORT_SYMBOL(sym, license)	__EXPORT_SYMBOL(sym, license, "")
 #endif
 
 #define EXPORT_SYMBOL(sym)		_EXPORT_SYMBOL(sym, "")
-#define EXPORT_SYMBOL_GPL(sym)		_EXPORT_SYMBOL(sym, "_gpl")
-#define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", __stringify(ns))
-#define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "_gpl", __stringify(ns))
+#define EXPORT_SYMBOL_GPL(sym)		_EXPORT_SYMBOL(sym, "GPL")
+#define EXPORT_SYMBOL_NS(sym, ns)	__EXPORT_SYMBOL(sym, "", ns)
+#define EXPORT_SYMBOL_NS_GPL(sym, ns)	__EXPORT_SYMBOL(sym, "GPL", ns)
 
-#endif /* !__ASSEMBLY__ */
+#define EXPORT_SYMBOL_FOR_MODULES(sym, mods) __EXPORT_SYMBOL(sym, "GPL", "module:" mods)
 
 #endif /* _LINUX_EXPORT_H */
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 9edb29101ec8..f0cf2714ec52 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -3,6 +3,7 @@
 #define LINUX_EXPORTFS_H 1
 
 #include <linux/types.h>
+#include <linux/path.h>
 
 struct dentry;
 struct iattr;
@@ -99,12 +100,35 @@ enum fid_type {
 	FILEID_FAT_WITH_PARENT = 0x72,
 
 	/*
+	 * 64 bit inode number, 32 bit generation number.
+	 */
+	FILEID_INO64_GEN = 0x81,
+
+	/*
+	 * 64 bit inode number, 32 bit generation number,
+	 * 64 bit parent inode number, 32 bit parent generation.
+	 */
+	FILEID_INO64_GEN_PARENT = 0x82,
+
+	/*
 	 * 128 bit child FID (struct lu_fid)
 	 * 128 bit parent FID (struct lu_fid)
 	 */
 	FILEID_LUSTRE = 0x97,
 
 	/*
+	 * 64 bit inode number, 32 bit subvolume, 32 bit generation number:
+	 */
+	FILEID_BCACHEFS_WITHOUT_PARENT = 0xb1,
+	FILEID_BCACHEFS_WITH_PARENT = 0xb2,
+
+	/*
+	 *
+	 * 64 bit namespace identifier, 32 bit namespace type, 32 bit inode number.
+	 */
+	FILEID_NSFS = 0xf1,
+
+	/*
 	 * 64 bit unique kernfs id
 	 */
 	FILEID_KERNFS = 0xfe,
@@ -123,7 +147,11 @@ struct fid {
 			u32 parent_ino;
 			u32 parent_gen;
 		} i32;
- 		struct {
+		struct {
+			u64 ino;
+			u32 gen;
+		} __packed i64;
+		struct {
  			u32 block;
  			u16 partref;
  			u16 parent_partref;
@@ -135,6 +163,34 @@ struct fid {
 	};
 };
 
+enum handle_to_path_flags {
+	HANDLE_CHECK_PERMS   = (1 << 0),
+	HANDLE_CHECK_SUBTREE = (1 << 1),
+};
+
+struct handle_to_path_ctx {
+	struct path root;
+	enum handle_to_path_flags flags;
+	unsigned int fh_flags;
+};
+
+#define EXPORT_FH_CONNECTABLE	0x1 /* Encode file handle with parent */
+#define EXPORT_FH_FID		0x2 /* File handle may be non-decodeable */
+#define EXPORT_FH_DIR_ONLY	0x4 /* Only decode file handle for a directory */
+
+/*
+ * Filesystems use only lower 8 bits of file_handle type for fid_type.
+ * name_to_handle_at() uses upper 16 bits of type as user flags to be
+ * interpreted by open_by_handle_at().
+ */
+#define FILEID_USER_FLAGS_MASK	0xffff0000
+#define FILEID_USER_FLAGS(type) ((type) & FILEID_USER_FLAGS_MASK)
+
+/* Flags supported in encoded handle_type that is exported to user */
+#define FILEID_IS_CONNECTABLE	0x10000
+#define FILEID_IS_DIR		0x20000
+#define FILEID_VALID_USER_FLAGS	(FILEID_IS_CONNECTABLE | FILEID_IS_DIR)
+
 /**
  * struct export_operations - for nfsd to communicate with file systems
  * @encode_fh:      encode a file handle fragment from a dentry
@@ -150,7 +206,7 @@ struct fid {
  * encode_fh:
  *    @encode_fh should store in the file handle fragment @fh (using at most
  *    @max_len bytes) information that can be used by @decode_fh to recover the
- *    file referred to by the &struct dentry @de.  If the @connectable flag is
+ *    file referred to by the &struct dentry @de.  If @flag has CONNECTABLE bit
  *    set, the encode_fh() should store sufficient information so that a good
  *    attempt can be made to find not only the file but also it's place in the
  *    filesystem.   This typically means storing a reference to de->d_parent in
@@ -180,18 +236,24 @@ struct fid {
  *    directory.  The name should be stored in the @name (with the
  *    understanding that it is already pointing to a %NAME_MAX+1 sized
  *    buffer.   get_name() should return %0 on success, a negative error code
- *    or error.  @get_name will be called without @parent->i_mutex held.
+ *    or error.  @get_name will be called without @parent->i_rwsem held.
  *
  * get_parent:
  *    @get_parent should find the parent directory for the given @child which
  *    is also a directory.  In the event that it cannot be found, or storage
  *    space cannot be allocated, a %ERR_PTR should be returned.
  *
+ * permission:
+ *    Allow filesystems to specify a custom permission function.
+ *
+ * open:
+ *    Allow filesystems to specify a custom open function.
+ *
  * commit_metadata:
  *    @commit_metadata should commit metadata changes to stable storage.
  *
  * Locking rules:
- *    get_parent is called with child->d_inode->i_mutex down
+ *    get_parent is called with child->d_inode->i_rwsem down
  *    get_name is not (which is possibly inconsistent)
  */
 
@@ -213,6 +275,8 @@ struct export_operations {
 			  bool write, u32 *device_generation);
 	int (*commit_blocks)(struct inode *inode, struct iomap *iomaps,
 			     int nr_iomaps, struct iattr *iattr);
+	int (*permission)(struct handle_to_path_ctx *ctx, unsigned int oflags);
+	struct file * (*open)(const struct path *path, unsigned int oflags);
 #define	EXPORT_OP_NOWCC			(0x1) /* don't collect v3 wcc data */
 #define	EXPORT_OP_NOSUBTREECHK		(0x2) /* no subtree checking */
 #define	EXPORT_OP_CLOSE_BEFORE_UNLINK	(0x4) /* close files before unlink */
@@ -221,16 +285,77 @@ struct export_operations {
 						  atomic attribute updates
 						*/
 #define EXPORT_OP_FLUSH_ON_CLOSE	(0x20) /* fs flushes file data on close */
+#define EXPORT_OP_NOLOCKS		(0x40) /* no file locking support */
 	unsigned long	flags;
 };
 
+/**
+ * exportfs_cannot_lock() - check if export implements file locking
+ * @export_ops:	the nfs export operations to check
+ *
+ * Returns true if the export does not support file locking.
+ */
+static inline bool
+exportfs_cannot_lock(const struct export_operations *export_ops)
+{
+	return export_ops->flags & EXPORT_OP_NOLOCKS;
+}
+
 extern int exportfs_encode_inode_fh(struct inode *inode, struct fid *fid,
-				    int *max_len, struct inode *parent);
+				    int *max_len, struct inode *parent,
+				    int flags);
 extern int exportfs_encode_fh(struct dentry *dentry, struct fid *fid,
-	int *max_len, int connectable);
+			      int *max_len, int flags);
+
+static inline bool exportfs_can_encode_fid(const struct export_operations *nop)
+{
+	return !nop || nop->encode_fh;
+}
+
+static inline bool exportfs_can_decode_fh(const struct export_operations *nop)
+{
+	return nop && nop->fh_to_dentry;
+}
+
+static inline bool exportfs_can_encode_fh(const struct export_operations *nop,
+					  int fh_flags)
+{
+	/*
+	 * If a non-decodeable file handle was requested, we only need to make
+	 * sure that filesystem did not opt-out of encoding fid.
+	 */
+	if (fh_flags & EXPORT_FH_FID)
+		return exportfs_can_encode_fid(nop);
+
+	/* Normal file handles cannot be created without export ops */
+	if (!nop)
+		return false;
+
+	/*
+	 * If a connectable file handle was requested, we need to make sure that
+	 * filesystem can also decode connected file handles.
+	 */
+	if ((fh_flags & EXPORT_FH_CONNECTABLE) && !nop->fh_to_parent)
+		return false;
+
+	/*
+	 * If a decodeable file handle was requested, we need to make sure that
+	 * filesystem can also decode file handles.
+	 */
+	return exportfs_can_decode_fh(nop);
+}
+
+static inline int exportfs_encode_fid(struct inode *inode, struct fid *fid,
+				      int *max_len)
+{
+	return exportfs_encode_inode_fh(inode, fid, max_len, NULL,
+					EXPORT_FH_FID);
+}
+
 extern struct dentry *exportfs_decode_fh_raw(struct vfsmount *mnt,
 					     struct fid *fid, int fh_len,
 					     int fileid_type,
+					     unsigned int flags,
 					     int (*acceptable)(void *, struct dentry *),
 					     void *context);
 extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
@@ -240,10 +365,12 @@ extern struct dentry *exportfs_decode_fh(struct vfsmount *mnt, struct fid *fid,
 /*
  * Generic helpers for filesystems.
  */
-extern struct dentry *generic_fh_to_dentry(struct super_block *sb,
+int generic_encode_ino32_fh(struct inode *inode, __u32 *fh, int *max_len,
+			    struct inode *parent);
+struct dentry *generic_fh_to_dentry(struct super_block *sb,
 	struct fid *fid, int fh_len, int fh_type,
 	struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen));
-extern struct dentry *generic_fh_to_parent(struct super_block *sb,
+struct dentry *generic_fh_to_parent(struct super_block *sb,
 	struct fid *fid, int fh_len, int fh_type,
 	struct inode *(*get_inode) (struct super_block *sb, u64 ino, u32 gen));
 
diff --git a/include/linux/extcon.h b/include/linux/extcon.h
index 3c45c3846fe9..e596a0abcb27 100644
--- a/include/linux/extcon.h
+++ b/include/linux/extcon.h
@@ -328,16 +328,4 @@ struct extcon_specific_cable_nb {
        struct extcon_dev *edev;
        unsigned long previous_value;
 };
-
-static inline int extcon_register_interest(struct extcon_specific_cable_nb *obj,
-				const char *extcon_name, const char *cable_name,
-				struct notifier_block *nb)
-{
-	return -EINVAL;
-}
-
-static inline int extcon_unregister_interest(struct extcon_specific_cable_nb *obj)
-{
-	return -EINVAL;
-}
 #endif /* __LINUX_EXTCON_H__ */
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 1d6402529d10..a7880787cad3 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -13,20 +13,23 @@
 
 #define F2FS_SUPER_OFFSET		1024	/* byte-size offset */
 #define F2FS_MIN_LOG_SECTOR_SIZE	9	/* 9 bits for 512 bytes */
-#define F2FS_MAX_LOG_SECTOR_SIZE	12	/* 12 bits for 4096 bytes */
-#define F2FS_LOG_SECTORS_PER_BLOCK	3	/* log number for sector/blk */
-#define F2FS_BLKSIZE			4096	/* support only 4KB block */
-#define F2FS_BLKSIZE_BITS		12	/* bits for F2FS_BLKSIZE */
+#define F2FS_MAX_LOG_SECTOR_SIZE	PAGE_SHIFT	/* Max is Block Size */
+#define F2FS_LOG_SECTORS_PER_BLOCK	(PAGE_SHIFT - 9) /* log number for sector/blk */
+#define F2FS_BLKSIZE			PAGE_SIZE /* support only block == page */
+#define F2FS_BLKSIZE_BITS		PAGE_SHIFT /* bits for F2FS_BLKSIZE */
+#define F2FS_SUM_BLKSIZE		4096	/* only support 4096 byte sum block */
 #define F2FS_MAX_EXTENSION		64	/* # of extension entries */
 #define F2FS_EXTENSION_LEN		8	/* max size of extension */
-#define F2FS_BLK_ALIGN(x)	(((x) + F2FS_BLKSIZE - 1) >> F2FS_BLKSIZE_BITS)
 
 #define NULL_ADDR		((block_t)0)	/* used as block_t addresses */
 #define NEW_ADDR		((block_t)-1)	/* used as block_t addresses */
 #define COMPRESS_ADDR		((block_t)-2)	/* used as compressed data flag */
 
-#define F2FS_BYTES_TO_BLK(bytes)	((bytes) >> F2FS_BLKSIZE_BITS)
-#define F2FS_BLK_TO_BYTES(blk)		((blk) << F2FS_BLKSIZE_BITS)
+#define F2FS_BLKSIZE_MASK		(F2FS_BLKSIZE - 1)
+#define F2FS_BYTES_TO_BLK(bytes)	((unsigned long long)(bytes) >> F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_TO_BYTES(blk)		((unsigned long long)(blk) << F2FS_BLKSIZE_BITS)
+#define F2FS_BLK_END_BYTES(blk)		(F2FS_BLK_TO_BYTES(blk + 1) - 1)
+#define F2FS_BLK_ALIGN(x)		(F2FS_BYTES_TO_BLK((x) + F2FS_BLKSIZE - 1))
 
 /* 0, 1(node nid), 2(meta nid) are reserved node id */
 #define F2FS_RESERVED_NODE_NUM		3
@@ -40,12 +43,6 @@
 
 #define F2FS_ENC_UTF8_12_1	1
 
-#define F2FS_IO_SIZE(sbi)	BIT(F2FS_OPTION(sbi).write_io_size_bits) /* Blocks */
-#define F2FS_IO_SIZE_KB(sbi)	BIT(F2FS_OPTION(sbi).write_io_size_bits + 2) /* KB */
-#define F2FS_IO_SIZE_BITS(sbi)	(F2FS_OPTION(sbi).write_io_size_bits) /* power of 2 */
-#define F2FS_IO_SIZE_MASK(sbi)	(F2FS_IO_SIZE(sbi) - 1)
-#define F2FS_IO_ALIGNED(sbi)	(F2FS_IO_SIZE(sbi) > 1)
-
 /* This flag is used by node and meta inodes, and by recovery */
 #define GFP_F2FS_ZERO		(GFP_NOFS | __GFP_ZERO)
 
@@ -81,6 +78,9 @@ enum stop_cp_reason {
 	STOP_CP_REASON_CORRUPTED_SUMMARY,
 	STOP_CP_REASON_UPDATE_INODE,
 	STOP_CP_REASON_FLUSH_FAIL,
+	STOP_CP_REASON_NO_SEGMENT,
+	STOP_CP_REASON_CORRUPTED_FREE_BITMAP,
+	STOP_CP_REASON_CORRUPTED_NID,
 	STOP_CP_REASON_MAX,
 };
 
@@ -103,6 +103,8 @@ enum f2fs_error {
 	ERROR_INCONSISTENT_SIT,
 	ERROR_CORRUPTED_VERITY_XATTR,
 	ERROR_CORRUPTED_XATTR,
+	ERROR_INVALID_NODE_REFERENCE,
+	ERROR_INCONSISTENT_NAT,
 	ERROR_MAX,
 };
 
@@ -209,14 +211,14 @@ struct f2fs_checkpoint {
 	unsigned char sit_nat_version_bitmap[];
 } __packed;
 
-#define CP_CHKSUM_OFFSET	4092	/* default chksum offset in checkpoint */
+#define CP_CHKSUM_OFFSET	(F2FS_BLKSIZE - sizeof(__le32))	/* default chksum offset in checkpoint */
 #define CP_MIN_CHKSUM_OFFSET						\
 	(offsetof(struct f2fs_checkpoint, sit_nat_version_bitmap))
 
 /*
  * For orphan inode management
  */
-#define F2FS_ORPHANS_PER_BLOCK	1020
+#define F2FS_ORPHANS_PER_BLOCK	((F2FS_BLKSIZE - 4 * sizeof(__le32)) / sizeof(__le32))
 
 #define GET_ORPHAN_BLOCKS(n)	(((n) + F2FS_ORPHANS_PER_BLOCK - 1) / \
 					F2FS_ORPHANS_PER_BLOCK)
@@ -242,17 +244,33 @@ struct f2fs_extent {
 #define F2FS_NAME_LEN		255
 /* 200 bytes for inline xattrs by default */
 #define DEFAULT_INLINE_XATTR_ADDRS	50
-#define DEF_ADDRS_PER_INODE	923	/* Address Pointers in an Inode */
+
+#define OFFSET_OF_END_OF_I_EXT		360
+#define SIZE_OF_I_NID			20
+
+struct node_footer {
+	__le32 nid;		/* node id */
+	__le32 ino;		/* inode number */
+	__le32 flag;		/* include cold/fsync/dentry marks and offset */
+	__le64 cp_ver;		/* checkpoint version */
+	__le32 next_blkaddr;	/* next node page block address */
+} __packed;
+
+/* Address Pointers in an Inode */
+#define DEF_ADDRS_PER_INODE	((F2FS_BLKSIZE - OFFSET_OF_END_OF_I_EXT	\
+					- SIZE_OF_I_NID	\
+					- sizeof(struct node_footer)) / sizeof(__le32))
 #define CUR_ADDRS_PER_INODE(inode)	(DEF_ADDRS_PER_INODE - \
 					get_extra_isize(inode))
 #define DEF_NIDS_PER_INODE	5	/* Node IDs in an Inode */
-#define ADDRS_PER_INODE(inode)	addrs_per_inode(inode)
-#define DEF_ADDRS_PER_BLOCK	1018	/* Address Pointers in a Direct Block */
-#define ADDRS_PER_BLOCK(inode)	addrs_per_block(inode)
-#define NIDS_PER_BLOCK		1018	/* Node IDs in an Indirect Block */
+#define ADDRS_PER_INODE(inode)	addrs_per_page(inode, true)
+/* Address Pointers in a Direct Block */
+#define DEF_ADDRS_PER_BLOCK	((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32))
+#define ADDRS_PER_BLOCK(inode)	addrs_per_page(inode, false)
+/* Node IDs in an Indirect Block */
+#define NIDS_PER_BLOCK		((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32))
 
-#define ADDRS_PER_PAGE(page, inode)	\
-	(IS_INODE(page) ? ADDRS_PER_INODE(inode) : ADDRS_PER_BLOCK(inode))
+#define ADDRS_PER_PAGE(folio, inode)	(addrs_per_page(inode, IS_INODE(folio)))
 
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
@@ -264,7 +282,7 @@ struct f2fs_extent {
 #define F2FS_INLINE_DATA	0x02	/* file inline data flag */
 #define F2FS_INLINE_DENTRY	0x04	/* file inline dentry flag */
 #define F2FS_DATA_EXIST		0x08	/* file inline data exist flag */
-#define F2FS_INLINE_DOTS	0x10	/* file having implicit dot dentries */
+#define F2FS_INLINE_DOTS	0x10	/* file having implicit dot dentries (obsolete) */
 #define F2FS_EXTRA_ATTR		0x20	/* file having extra attribute */
 #define F2FS_PIN_FILE		0x40	/* file should not be gced */
 #define F2FS_COMPRESS_RELEASED	0x80	/* file released compressed blocks */
@@ -341,14 +359,6 @@ enum {
 
 #define OFFSET_BIT_MASK		GENMASK(OFFSET_BIT_SHIFT - 1, 0)
 
-struct node_footer {
-	__le32 nid;		/* node id */
-	__le32 ino;		/* inode number */
-	__le32 flag;		/* include cold/fsync/dentry marks and offset */
-	__le64 cp_ver;		/* checkpoint version */
-	__le32 next_blkaddr;	/* next node page block address */
-} __packed;
-
 struct f2fs_node {
 	/* can be one of three types: inode, direct, and indirect types */
 	union {
@@ -362,7 +372,7 @@ struct f2fs_node {
 /*
  * For NAT entries
  */
-#define NAT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_nat_entry))
+#define NAT_ENTRY_PER_BLOCK (F2FS_BLKSIZE / sizeof(struct f2fs_nat_entry))
 
 struct f2fs_nat_entry {
 	__u8 version;		/* latest version of cached nat entry */
@@ -377,16 +387,18 @@ struct f2fs_nat_block {
 /*
  * For SIT entries
  *
- * Each segment is 2MB in size by default so that a bitmap for validity of
- * there-in blocks should occupy 64 bytes, 512 bits.
+ * A validity bitmap of 64 bytes covers 512 blocks of area. For a 4K page size,
+ * this results in a segment size of 2MB. For 16k pages, the default segment size
+ * is 8MB.
  * Not allow to change this.
  */
 #define SIT_VBLOCK_MAP_SIZE 64
-#define SIT_ENTRY_PER_BLOCK (PAGE_SIZE / sizeof(struct f2fs_sit_entry))
+#define SIT_ENTRY_PER_BLOCK (F2FS_BLKSIZE / sizeof(struct f2fs_sit_entry))
 
 /*
  * F2FS uses 4 bytes to represent block address. As a result, supported size of
- * disk is 16 TB and it equals to 16 * 1024 * 1024 / 2 segments.
+ * disk is 16 TB for a 4K page size and 64 TB for a 16K page size and it equals
+ * to 16 * 1024 * 1024 / 2 segments.
  */
 #define F2FS_MAX_SEGMENT       ((16 * 1024 * 1024) / 2)
 
@@ -416,8 +428,10 @@ struct f2fs_sit_block {
 /*
  * For segment summary
  *
- * One summary block contains exactly 512 summary entries, which represents
- * exactly 2MB segment by default. Not allow to change the basic units.
+ * One summary block with 4KB size contains exactly 512 summary entries, which
+ * represents exactly one segment with 2MB size.
+ * Similarly, in the case of block with 16KB size, it represents one segment with 8MB size.
+ * Not allow to change the basic units.
  *
  * NOTE: For initializing fields, you must use set_summary
  *
@@ -428,12 +442,12 @@ struct f2fs_sit_block {
  * from node's page's beginning to get a data block address.
  * ex) data_blkaddr = (block_t)(nodepage_start_address + ofs_in_node)
  */
-#define ENTRIES_IN_SUM		512
-#define	SUMMARY_SIZE		(7)	/* sizeof(struct summary) */
+#define ENTRIES_IN_SUM		(F2FS_SUM_BLKSIZE / 8)
+#define	SUMMARY_SIZE		(7)	/* sizeof(struct f2fs_summary) */
 #define	SUM_FOOTER_SIZE		(5)	/* sizeof(struct summary_footer) */
 #define SUM_ENTRY_SIZE		(SUMMARY_SIZE * ENTRIES_IN_SUM)
 
-/* a summary entry for a 4KB-sized block in a segment */
+/* a summary entry for a block in a segment */
 struct f2fs_summary {
 	__le32 nid;		/* parent node id */
 	union {
@@ -454,7 +468,7 @@ struct summary_footer {
 	__le32 check_sum;		/* summary checksum */
 } __packed;
 
-#define SUM_JOURNAL_SIZE	(F2FS_BLKSIZE - SUM_FOOTER_SIZE -\
+#define SUM_JOURNAL_SIZE	(F2FS_SUM_BLKSIZE - SUM_FOOTER_SIZE -\
 				SUM_ENTRY_SIZE)
 #define NAT_JOURNAL_ENTRIES	((SUM_JOURNAL_SIZE - 2) /\
 				sizeof(struct nat_journal_entry))
@@ -517,7 +531,7 @@ struct f2fs_journal {
 	};
 } __packed;
 
-/* 4KB-sized summary block structure */
+/* Block-sized summary block structure */
 struct f2fs_summary_block {
 	struct f2fs_summary entries[ENTRIES_IN_SUM];
 	struct f2fs_journal journal;
@@ -548,6 +562,7 @@ typedef __le32	f2fs_hash_t;
 
 /*
  * space utilization of regular dentry and inline dentry (w/o extra reservation)
+ * when block size is 4KB.
  *		regular dentry		inline dentry (def)	inline dentry (min)
  * bitmap	1 * 27 = 27		1 * 23 = 23		1 * 1 = 1
  * reserved	1 * 3 = 3		1 * 7 = 7		1 * 1 = 1
@@ -558,11 +573,14 @@ typedef __le32	f2fs_hash_t;
  * Note: there are more reserved space in inline dentry than in regular
  * dentry, when converting inline dentry we should handle this carefully.
  */
-#define NR_DENTRY_IN_BLOCK	214	/* the number of dentry in a block */
+
+/* the number of dentry in a block */
+#define NR_DENTRY_IN_BLOCK	((BITS_PER_BYTE * F2FS_BLKSIZE) / \
+					((SIZE_OF_DIR_ENTRY + F2FS_SLOT_LEN) * BITS_PER_BYTE + 1))
 #define SIZE_OF_DIR_ENTRY	11	/* by byte */
 #define SIZE_OF_DENTRY_BITMAP	((NR_DENTRY_IN_BLOCK + BITS_PER_BYTE - 1) / \
 					BITS_PER_BYTE)
-#define SIZE_OF_RESERVED	(PAGE_SIZE - ((SIZE_OF_DIR_ENTRY + \
+#define SIZE_OF_RESERVED	(F2FS_BLKSIZE - ((SIZE_OF_DIR_ENTRY + \
 				F2FS_SLOT_LEN) * \
 				NR_DENTRY_IN_BLOCK + SIZE_OF_DENTRY_BITMAP))
 #define MIN_INLINE_DENTRY_SIZE		40	/* just include '.' and '..' entries */
@@ -575,7 +593,7 @@ struct f2fs_dir_entry {
 	__u8 file_type;		/* file type */
 } __packed;
 
-/* 4KB-sized directory entry block */
+/* Block-sized directory entry block */
 struct f2fs_dentry_block {
 	/* validity bitmap for directory entries in each block */
 	__u8 dentry_bitmap[SIZE_OF_DENTRY_BITMAP];
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
index f3f0b97b1675..7c38c6b76b60 100644
--- a/include/linux/falloc.h
+++ b/include/linux/falloc.h
@@ -25,12 +25,19 @@ struct space_resv {
 #define FS_IOC_UNRESVSP64	_IOW('X', 43, struct space_resv)
 #define FS_IOC_ZERO_RANGE	_IOW('X', 57, struct space_resv)
 
-#define	FALLOC_FL_SUPPORTED_MASK	(FALLOC_FL_KEEP_SIZE |		\
-					 FALLOC_FL_PUNCH_HOLE |		\
-					 FALLOC_FL_COLLAPSE_RANGE |	\
-					 FALLOC_FL_ZERO_RANGE |		\
-					 FALLOC_FL_INSERT_RANGE |	\
-					 FALLOC_FL_UNSHARE_RANGE)
+/*
+ * Mask of all supported fallocate modes.  Only one can be set at a time.
+ *
+ * In addition to the mode bit, the mode argument can also encode flags.
+ * FALLOC_FL_KEEP_SIZE is the only supported flag so far.
+ */
+#define FALLOC_FL_MODE_MASK	(FALLOC_FL_ALLOCATE_RANGE |	\
+				 FALLOC_FL_PUNCH_HOLE |		\
+				 FALLOC_FL_COLLAPSE_RANGE |	\
+				 FALLOC_FL_ZERO_RANGE |		\
+				 FALLOC_FL_INSERT_RANGE |	\
+				 FALLOC_FL_UNSHARE_RANGE |	\
+				 FALLOC_FL_WRITE_ZEROES)
 
 /* on ia32 l_start is on a 32-bit boundary */
 #if defined(CONFIG_X86_64)
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 4f1c4f603118..879cff5eccd4 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -25,7 +25,7 @@
 
 #define FANOTIFY_FID_BITS	(FAN_REPORT_DFID_NAME_TARGET)
 
-#define FANOTIFY_INFO_MODES	(FANOTIFY_FID_BITS | FAN_REPORT_PIDFD)
+#define FANOTIFY_INFO_MODES	(FANOTIFY_FID_BITS | FAN_REPORT_PIDFD | FAN_REPORT_MNT)
 
 /*
  * fanotify_init() flags that require CAP_SYS_ADMIN.
@@ -36,6 +36,7 @@
 #define FANOTIFY_ADMIN_INIT_FLAGS	(FANOTIFY_PERM_CLASSES | \
 					 FAN_REPORT_TID | \
 					 FAN_REPORT_PIDFD | \
+					 FAN_REPORT_FD_ERROR | \
 					 FAN_UNLIMITED_QUEUE | \
 					 FAN_UNLIMITED_MARKS)
 
@@ -46,7 +47,7 @@
  * so one of the flags for reporting file handles is required.
  */
 #define FANOTIFY_USER_INIT_FLAGS	(FAN_CLASS_NOTIF | \
-					 FANOTIFY_FID_BITS | \
+					 FANOTIFY_FID_BITS | FAN_REPORT_MNT | \
 					 FAN_CLOEXEC | FAN_NONBLOCK)
 
 #define FANOTIFY_INIT_FLAGS	(FANOTIFY_ADMIN_INIT_FLAGS | \
@@ -57,7 +58,7 @@
 #define FANOTIFY_INTERNAL_GROUP_FLAGS	(FANOTIFY_UNPRIV)
 
 #define FANOTIFY_MARK_TYPE_BITS	(FAN_MARK_INODE | FAN_MARK_MOUNT | \
-				 FAN_MARK_FILESYSTEM)
+				 FAN_MARK_FILESYSTEM | FAN_MARK_MNTNS)
 
 #define FANOTIFY_MARK_CMD_BITS	(FAN_MARK_ADD | FAN_MARK_REMOVE | \
 				 FAN_MARK_FLUSH)
@@ -88,6 +89,16 @@
 #define FANOTIFY_DIRENT_EVENTS	(FAN_MOVE | FAN_CREATE | FAN_DELETE | \
 				 FAN_RENAME)
 
+/* Content events can be used to inspect file content */
+#define FANOTIFY_CONTENT_PERM_EVENTS (FAN_OPEN_PERM | FAN_OPEN_EXEC_PERM | \
+				      FAN_ACCESS_PERM)
+/* Pre-content events can be used to fill file content */
+#define FANOTIFY_PRE_CONTENT_EVENTS  (FAN_PRE_ACCESS)
+
+/* Events that require a permission response from user */
+#define FANOTIFY_PERM_EVENTS	(FANOTIFY_CONTENT_PERM_EVENTS | \
+				 FANOTIFY_PRE_CONTENT_EVENTS)
+
 /* Events that can be reported with event->fd */
 #define FANOTIFY_FD_EVENTS (FANOTIFY_PATH_EVENTS | FANOTIFY_PERM_EVENTS)
 
@@ -98,14 +109,13 @@
 /* Events that can only be reported with data type FSNOTIFY_EVENT_ERROR */
 #define FANOTIFY_ERROR_EVENTS	(FAN_FS_ERROR)
 
+#define FANOTIFY_MOUNT_EVENTS	(FAN_MNT_ATTACH | FAN_MNT_DETACH)
+
 /* Events that user can request to be notified on */
 #define FANOTIFY_EVENTS		(FANOTIFY_PATH_EVENTS | \
 				 FANOTIFY_INODE_EVENTS | \
-				 FANOTIFY_ERROR_EVENTS)
-
-/* Events that require a permission response from user */
-#define FANOTIFY_PERM_EVENTS	(FAN_OPEN_PERM | FAN_ACCESS_PERM | \
-				 FAN_OPEN_EXEC_PERM)
+				 FANOTIFY_ERROR_EVENTS | \
+				 FANOTIFY_MOUNT_EVENTS)
 
 /* Extra flags that may be reported with event or control handling of events */
 #define FANOTIFY_EVENT_FLAGS	(FAN_EVENT_ON_CHILD | FAN_ONDIR)
@@ -125,7 +135,9 @@
 /* These masks check for invalid bits in permission responses. */
 #define FANOTIFY_RESPONSE_ACCESS (FAN_ALLOW | FAN_DENY)
 #define FANOTIFY_RESPONSE_FLAGS (FAN_AUDIT | FAN_INFO)
-#define FANOTIFY_RESPONSE_VALID_MASK (FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS)
+#define FANOTIFY_RESPONSE_VALID_MASK \
+	(FANOTIFY_RESPONSE_ACCESS | FANOTIFY_RESPONSE_FLAGS | \
+	 (FAN_ERRNO_MASK << FAN_ERRNO_SHIFT))
 
 /* Do not use these old uapi constants internally */
 #undef FAN_ALL_CLASS_BITS
diff --git a/include/linux/fault-inject.h b/include/linux/fault-inject.h
index 6d5edef09d45..58fd14c82270 100644
--- a/include/linux/fault-inject.h
+++ b/include/linux/fault-inject.h
@@ -2,13 +2,21 @@
 #ifndef _LINUX_FAULT_INJECT_H
 #define _LINUX_FAULT_INJECT_H
 
+#include <linux/err.h>
+#include <linux/types.h>
+
+struct dentry;
+struct kmem_cache;
+
+enum fault_flags {
+	FAULT_NOWARN =	1 << 0,
+};
+
 #ifdef CONFIG_FAULT_INJECTION
 
-#include <linux/types.h>
-#include <linux/debugfs.h>
+#include <linux/atomic.h>
 #include <linux/configfs.h>
 #include <linux/ratelimit.h>
-#include <linux/atomic.h>
 
 /*
  * For explanation of the elements of this struct, see
@@ -32,10 +40,6 @@ struct fault_attr {
 	struct dentry *dname;
 };
 
-enum fault_flags {
-	FAULT_NOWARN =	1 << 0,
-};
-
 #define FAULT_ATTR_INITIALIZER {					\
 		.interval = 1,						\
 		.times = ATOMIC_INIT(1),				\
@@ -51,6 +55,28 @@ int setup_fault_attr(struct fault_attr *attr, char *str);
 bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags);
 bool should_fail(struct fault_attr *attr, ssize_t size);
 
+#else /* CONFIG_FAULT_INJECTION */
+
+struct fault_attr {
+};
+
+#define DECLARE_FAULT_ATTR(name) struct fault_attr name = {}
+
+static inline int setup_fault_attr(struct fault_attr *attr, char *str)
+{
+	return 0; /* Note: 0 means error for __setup() handlers! */
+}
+static inline bool should_fail_ex(struct fault_attr *attr, ssize_t size, int flags)
+{
+	return false;
+}
+static inline bool should_fail(struct fault_attr *attr, ssize_t size)
+{
+	return false;
+}
+
+#endif /* CONFIG_FAULT_INJECTION */
+
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 
 struct dentry *fault_create_debugfs_attr(const char *name,
@@ -87,26 +113,19 @@ static inline void fault_config_init(struct fault_config *config,
 
 #endif /* CONFIG_FAULT_INJECTION_CONFIGFS */
 
-#endif /* CONFIG_FAULT_INJECTION */
-
-struct kmem_cache;
-
-bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order);
-
 #ifdef CONFIG_FAIL_PAGE_ALLOC
-bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order);
+bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order);
 #else
-static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
+static inline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order)
 {
 	return false;
 }
 #endif /* CONFIG_FAIL_PAGE_ALLOC */
 
-int should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #ifdef CONFIG_FAILSLAB
-extern bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags);
+int should_failslab(struct kmem_cache *s, gfp_t gfpflags);
 #else
-static inline bool __should_failslab(struct kmem_cache *s, gfp_t gfpflags)
+static inline int should_failslab(struct kmem_cache *s, gfp_t gfpflags)
 {
 	return false;
 }
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 08cb47da71f8..05cc251035da 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -2,27 +2,31 @@
 #ifndef _LINUX_FB_H
 #define _LINUX_FB_H
 
-#include <linux/refcount.h>
-#include <linux/kgdb.h>
 #include <uapi/linux/fb.h>
 
 #define FBIO_CURSOR            _IOWR('F', 0x08, struct fb_cursor_user)
 
-#include <linux/fs.h>
-#include <linux/init.h>
+#include <linux/mutex.h>
+#include <linux/printk.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
 #include <linux/workqueue.h>
-#include <linux/notifier.h>
-#include <linux/list.h>
-#include <linux/backlight.h>
-#include <linux/slab.h>
-#include <asm/io.h>
 
-struct vm_area_struct;
-struct fb_info;
+#include <asm/video.h>
+
+struct backlight_device;
 struct device;
+struct device_node;
+struct fb_info;
 struct file;
+struct i2c_adapter;
+struct inode;
+struct lcd_device;
+struct module;
+struct notifier_block;
+struct page;
 struct videomode;
-struct device_node;
+struct vm_area_struct;
 
 /* Definitions below are used in the parsed monitor specs */
 #define FB_DPMS_ACTIVE_OFF	1
@@ -125,26 +129,24 @@ struct fb_cursor_user {
  * Register/unregister for framebuffer events
  */
 
-/*	The resolution of the passed in fb_info about to change */
-#define FB_EVENT_MODE_CHANGE		0x01
-
 #ifdef CONFIG_GUMSTIX_AM200EPD
 /* only used by mach-pxa/am200epd.c */
 #define FB_EVENT_FB_REGISTERED          0x05
 #define FB_EVENT_FB_UNREGISTERED        0x06
 #endif
 
-/*      A display blank is requested       */
-#define FB_EVENT_BLANK                  0x09
-
 struct fb_event {
 	struct fb_info *info;
 	void *data;
 };
 
+/*	Enough for the VT console needs, see its max_font_width/height */
+#define FB_MAX_BLIT_WIDTH	64
+#define FB_MAX_BLIT_HEIGHT	128
+
 struct fb_blit_caps {
-	u32 x;
-	u32 y;
+	DECLARE_BITMAP(x, FB_MAX_BLIT_WIDTH);
+	DECLARE_BITMAP(y, FB_MAX_BLIT_HEIGHT);
 	u32 len;
 	u32 flags;
 };
@@ -191,10 +193,12 @@ struct fb_pixmap {
 	u32 scan_align;		/* alignment per scanline		*/
 	u32 access_align;	/* alignment per read/write (bits)	*/
 	u32 flags;		/* see FB_PIXMAP_*			*/
-	u32 blit_x;             /* supported bit block dimensions (1-32)*/
-	u32 blit_y;             /* Format: blit_x = 1 << (width - 1)    */
-	                        /*         blit_y = 1 << (height - 1)   */
-	                        /* if 0, will be set to 0xffffffff (all)*/
+				/* supported bit block dimensions	*/
+				/* Format: test_bit(width - 1, blit_x)	*/
+				/*	   test_bit(height - 1, blit_y)	*/
+				/* if zero, will be set to full (all)	*/
+	DECLARE_BITMAP(blit_x, FB_MAX_BLIT_WIDTH);
+	DECLARE_BITMAP(blit_y, FB_MAX_BLIT_HEIGHT);
 	/* access methods */
 	void (*writeio)(struct fb_info *info, void __iomem *dst, void *src, unsigned int size);
 	void (*readio) (struct fb_info *info, void *dst, void __iomem *src, unsigned int size);
@@ -215,7 +219,9 @@ struct fb_deferred_io {
 	int open_count; /* number of opened files; protected by fb_info lock */
 	struct mutex lock; /* mutex that protects the pageref list */
 	struct list_head pagereflist; /* list of pagerefs for touched pages */
+	struct address_space *mapping; /* page cache object for fb device */
 	/* callback */
+	struct page *(*get_page)(struct fb_info *info, unsigned long offset);
 	void (*deferred_io)(struct fb_info *info, struct list_head *pagelist);
 };
 #endif
@@ -382,7 +388,6 @@ struct fb_tile_ops {
 #endif /* CONFIG_FB_TILEBLITTING */
 
 /* FBINFO_* = fb_info.flags bit flags */
-#define FBINFO_DEFAULT		0
 #define FBINFO_HWACCEL_DISABLED	0x0002
 	/* When FBINFO_HWACCEL_DISABLED is set:
 	 *  Hardware acceleration is turned off.  Software implementations
@@ -461,6 +466,8 @@ struct fb_info {
 	struct list_head modelist;      /* mode list */
 	struct fb_videomode *mode;	/* current mode */
 
+	int blank; /* current blanking; see FB_BLANK_ constants */
+
 #if IS_ENABLED(CONFIG_FB_BACKLIGHT)
 	/* assigned backlight device */
 	/* set before framebuffer registration,
@@ -471,6 +478,13 @@ struct fb_info {
 	struct mutex bl_curve_mutex;
 	u8 bl_curve[FB_BACKLIGHT_LEVELS];
 #endif
+
+	/*
+	 * Assigned LCD device; set before framebuffer
+	 * registration, remove after unregister
+	 */
+	struct lcd_device *lcd_dev;
+
 #ifdef CONFIG_FB_DEFERRED_IO
 	struct delayed_work deferred_work;
 	unsigned long npagerefs;
@@ -480,7 +494,9 @@ struct fb_info {
 
 	const struct fb_ops *fbops;
 	struct device *device;		/* This is the parent */
+#if defined(CONFIG_FB_DEVICE)
 	struct device *dev;		/* This is this fb device */
+#endif
 	int class_flag;                    /* private sysfs flags */
 #ifdef CONFIG_FB_TILEBLITTING
 	struct fb_tile_ops *tileops;    /* Tile Blitting */
@@ -499,10 +515,9 @@ struct fb_info {
 	void *par;
 
 	bool skip_vt_switch; /* no VT switch on suspend/resume required */
+	bool skip_panic; /* Do not write to the fb after a panic */
 };
 
-#define FBINFO_FLAG_DEFAULT	FBINFO_DEFAULT
-
 /* This will go away
  * fbset currently hacks in FB_ACCELF_TEXT into var.accel_flags
  * when it wants to turn the acceleration engine on.  This is
@@ -511,58 +526,6 @@ struct fb_info {
  */
 #define STUPID_ACCELF_TEXT_SHIT
 
-// This will go away
-#if defined(__sparc__)
-
-/* We map all of our framebuffers such that big-endian accesses
- * are what we want, so the following is sufficient.
- */
-
-// This will go away
-#define fb_readb sbus_readb
-#define fb_readw sbus_readw
-#define fb_readl sbus_readl
-#define fb_readq sbus_readq
-#define fb_writeb sbus_writeb
-#define fb_writew sbus_writew
-#define fb_writel sbus_writel
-#define fb_writeq sbus_writeq
-#define fb_memset sbus_memset_io
-#define fb_memcpy_fromfb sbus_memcpy_fromio
-#define fb_memcpy_tofb sbus_memcpy_toio
-
-#elif defined(__i386__) || defined(__alpha__) || defined(__x86_64__) ||	\
-	defined(__hppa__) || defined(__sh__) || defined(__powerpc__) ||	\
-	defined(__arm__) || defined(__aarch64__) || defined(__mips__)
-
-#define fb_readb __raw_readb
-#define fb_readw __raw_readw
-#define fb_readl __raw_readl
-#define fb_readq __raw_readq
-#define fb_writeb __raw_writeb
-#define fb_writew __raw_writew
-#define fb_writel __raw_writel
-#define fb_writeq __raw_writeq
-#define fb_memset memset_io
-#define fb_memcpy_fromfb memcpy_fromio
-#define fb_memcpy_tofb memcpy_toio
-
-#else
-
-#define fb_readb(addr) (*(volatile u8 *) (addr))
-#define fb_readw(addr) (*(volatile u16 *) (addr))
-#define fb_readl(addr) (*(volatile u32 *) (addr))
-#define fb_readq(addr) (*(volatile u64 *) (addr))
-#define fb_writeb(b,addr) (*(volatile u8 *) (addr) = (b))
-#define fb_writew(b,addr) (*(volatile u16 *) (addr) = (b))
-#define fb_writel(b,addr) (*(volatile u32 *) (addr) = (b))
-#define fb_writeq(b,addr) (*(volatile u64 *) (addr) = (b))
-#define fb_memset memset
-#define fb_memcpy_fromfb memcpy
-#define fb_memcpy_tofb memcpy
-
-#endif
-
 #define FB_LEFT_POS(p, bpp)          (fb_be_math(p) ? (32 - (bpp)) : 0)
 #define FB_SHIFT_HIGH(p, val, bits)  (fb_be_math(p) ? (val) >> (bits) : \
 						      (val) << (bits))
@@ -576,12 +539,41 @@ struct fb_info {
 extern int fb_set_var(struct fb_info *info, struct fb_var_screeninfo *var);
 extern int fb_pan_display(struct fb_info *info, struct fb_var_screeninfo *var);
 extern int fb_blank(struct fb_info *info, int blank);
+
+/*
+ * Helpers for framebuffers in I/O memory
+ */
+
 extern void cfb_fillrect(struct fb_info *info, const struct fb_fillrect *rect);
 extern void cfb_copyarea(struct fb_info *info, const struct fb_copyarea *area);
 extern void cfb_imageblit(struct fb_info *info, const struct fb_image *image);
+extern ssize_t fb_io_read(struct fb_info *info, char __user *buf,
+			  size_t count, loff_t *ppos);
+extern ssize_t fb_io_write(struct fb_info *info, const char __user *buf,
+			   size_t count, loff_t *ppos);
+int fb_io_mmap(struct fb_info *info, struct vm_area_struct *vma);
+
+#define __FB_DEFAULT_IOMEM_OPS_RDWR \
+	.fb_read	= fb_io_read, \
+	.fb_write	= fb_io_write
+
+#define __FB_DEFAULT_IOMEM_OPS_DRAW \
+	.fb_fillrect	= cfb_fillrect, \
+	.fb_copyarea	= cfb_copyarea, \
+	.fb_imageblit	= cfb_imageblit
+
+#define __FB_DEFAULT_IOMEM_OPS_MMAP \
+	.fb_mmap	= fb_io_mmap
+
+#define FB_DEFAULT_IOMEM_OPS \
+	__FB_DEFAULT_IOMEM_OPS_RDWR, \
+	__FB_DEFAULT_IOMEM_OPS_DRAW, \
+	__FB_DEFAULT_IOMEM_OPS_MMAP
+
 /*
- * Drawing operations where framebuffer is in system RAM
+ * Helpers for framebuffers in system memory
  */
+
 extern void sys_fillrect(struct fb_info *info, const struct fb_fillrect *rect);
 extern void sys_copyarea(struct fb_info *info, const struct fb_copyarea *area);
 extern void sys_imageblit(struct fb_info *info, const struct fb_image *image);
@@ -590,11 +582,32 @@ extern ssize_t fb_sys_read(struct fb_info *info, char __user *buf,
 extern ssize_t fb_sys_write(struct fb_info *info, const char __user *buf,
 			    size_t count, loff_t *ppos);
 
-/* drivers/video/fbmem.c */
+#define __FB_DEFAULT_SYSMEM_OPS_RDWR \
+	.fb_read	= fb_sys_read, \
+	.fb_write	= fb_sys_write
+
+#define __FB_DEFAULT_SYSMEM_OPS_DRAW \
+	.fb_fillrect	= sys_fillrect, \
+	.fb_copyarea	= sys_copyarea, \
+	.fb_imageblit	= sys_imageblit
+
+/*
+ * Helpers for framebuffers in DMA-able memory
+ */
+
+#define __FB_DEFAULT_DMAMEM_OPS_RDWR \
+	.fb_read	= fb_sys_read, \
+	.fb_write	= fb_sys_write
+
+#define __FB_DEFAULT_DMAMEM_OPS_DRAW \
+	.fb_fillrect	= sys_fillrect, \
+	.fb_copyarea	= sys_copyarea, \
+	.fb_imageblit	= sys_imageblit
+
+/* fbmem.c */
 extern int register_framebuffer(struct fb_info *fb_info);
 extern void unregister_framebuffer(struct fb_info *fb_info);
-extern int fb_prepare_logo(struct fb_info *fb_info, int rotate);
-extern int fb_show_logo(struct fb_info *fb_info, int rotate);
+extern int devm_register_framebuffer(struct device *dev, struct fb_info *fb_info);
 extern char* fb_get_buffer_offset(struct fb_info *info, struct fb_pixmap *buf, u32 size);
 extern void fb_pad_unaligned_buffer(u8 *dst, u32 d_pitch, u8 *src, u32 idx,
 				u32 height, u32 shift_high, u32 shift_low, u32 mod);
@@ -605,10 +618,6 @@ extern int fb_get_color_depth(struct fb_var_screeninfo *var,
 extern int fb_get_options(const char *name, char **option);
 extern int fb_new_modelist(struct fb_info *info);
 
-extern bool fb_center_logo;
-extern int fb_logo_count;
-extern struct class *fb_class;
-
 static inline void lock_fb_info(struct fb_info *info)
 {
 	mutex_lock(&info->lock);
@@ -634,7 +643,7 @@ static inline void __fb_pad_aligned_buffer(u8 *dst, u32 d_pitch,
 	}
 }
 
-/* drivers/video/fb_defio.c */
+/* fb_defio.c */
 int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma);
 extern int  fb_deferred_io_init(struct fb_info *info);
 extern void fb_deferred_io_open(struct fb_info *info,
@@ -645,6 +654,79 @@ extern void fb_deferred_io_cleanup(struct fb_info *info);
 extern int fb_deferred_io_fsync(struct file *file, loff_t start,
 				loff_t end, int datasync);
 
+/*
+ * Generate callbacks for deferred I/O
+ */
+
+#define __FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, __mode) \
+	static ssize_t __prefix ## _defio_read(struct fb_info *info, char __user *buf, \
+					       size_t count, loff_t *ppos) \
+	{ \
+		return fb_ ## __mode ## _read(info, buf, count, ppos); \
+	} \
+	static ssize_t __prefix ## _defio_write(struct fb_info *info, const char __user *buf, \
+						size_t count, loff_t *ppos) \
+	{ \
+		unsigned long offset = *ppos; \
+		ssize_t ret = fb_ ## __mode ## _write(info, buf, count, ppos); \
+		if (ret > 0) \
+			__damage_range(info, offset, ret); \
+		return ret; \
+	}
+
+#define __FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, __mode) \
+	static void __prefix ## _defio_fillrect(struct fb_info *info, \
+						const struct fb_fillrect *rect) \
+	{ \
+		__mode ## _fillrect(info, rect); \
+		__damage_area(info, rect->dx, rect->dy, rect->width, rect->height); \
+	} \
+	static void __prefix ## _defio_copyarea(struct fb_info *info, \
+						const struct fb_copyarea *area) \
+	{ \
+		__mode ## _copyarea(info, area); \
+		__damage_area(info, area->dx, area->dy, area->width, area->height); \
+	} \
+	static void __prefix ## _defio_imageblit(struct fb_info *info, \
+						 const struct fb_image *image) \
+	{ \
+		__mode ## _imageblit(info, image); \
+		__damage_area(info, image->dx, image->dy, image->width, image->height); \
+	}
+
+#define FB_GEN_DEFAULT_DEFERRED_IOMEM_OPS(__prefix, __damage_range, __damage_area) \
+	__FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, io) \
+	__FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, cfb)
+
+#define FB_GEN_DEFAULT_DEFERRED_SYSMEM_OPS(__prefix, __damage_range, __damage_area) \
+	__FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \
+	__FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys)
+
+#define FB_GEN_DEFAULT_DEFERRED_DMAMEM_OPS(__prefix, __damage_range, __damage_area) \
+	__FB_GEN_DEFAULT_DEFERRED_OPS_RDWR(__prefix, __damage_range, sys) \
+	__FB_GEN_DEFAULT_DEFERRED_OPS_DRAW(__prefix, __damage_area, sys)
+
+/*
+ * Initializes struct fb_ops for deferred I/O.
+ */
+
+#define __FB_DEFAULT_DEFERRED_OPS_RDWR(__prefix) \
+	.fb_read	= __prefix ## _defio_read, \
+	.fb_write	= __prefix ## _defio_write
+
+#define __FB_DEFAULT_DEFERRED_OPS_DRAW(__prefix) \
+	.fb_fillrect	= __prefix ## _defio_fillrect, \
+	.fb_copyarea	= __prefix ## _defio_copyarea, \
+	.fb_imageblit	= __prefix ## _defio_imageblit
+
+#define __FB_DEFAULT_DEFERRED_OPS_MMAP(__prefix) \
+	.fb_mmap	= fb_deferred_io_mmap
+
+#define FB_DEFAULT_DEFERRED_OPS(__prefix) \
+	__FB_DEFAULT_DEFERRED_OPS_RDWR(__prefix), \
+	__FB_DEFAULT_DEFERRED_OPS_DRAW(__prefix), \
+	__FB_DEFAULT_DEFERRED_OPS_MMAP(__prefix)
+
 static inline bool fb_be_math(struct fb_info *info)
 {
 #ifdef CONFIG_FB_FOREIGN_ENDIAN
@@ -664,14 +746,29 @@ static inline bool fb_be_math(struct fb_info *info)
 #endif /* CONFIG_FB_FOREIGN_ENDIAN */
 }
 
-/* drivers/video/fbsysfs.c */
 extern struct fb_info *framebuffer_alloc(size_t size, struct device *dev);
 extern void framebuffer_release(struct fb_info *info);
-extern int fb_init_device(struct fb_info *fb_info);
-extern void fb_cleanup_device(struct fb_info *head);
 extern void fb_bl_default_curve(struct fb_info *fb_info, u8 off, u8 min, u8 max);
 
-/* drivers/video/fbmon.c */
+#if IS_ENABLED(CONFIG_FB_BACKLIGHT)
+struct backlight_device *fb_bl_device(struct fb_info *info);
+void fb_bl_notify_blank(struct fb_info *info, int old_blank);
+#else
+static inline struct backlight_device *fb_bl_device(struct fb_info *info)
+{
+	return NULL;
+}
+
+static inline void fb_bl_notify_blank(struct fb_info *info, int old_blank)
+{ }
+#endif
+
+static inline struct lcd_device *fb_lcd_device(struct fb_info *info)
+{
+	return info->lcd_dev;
+}
+
+/* fbmon.c */
 #define FB_MAXTIMINGS		0
 #define FB_VSYNCTIMINGS		1
 #define FB_HSYNCTIMINGS		2
@@ -705,7 +802,7 @@ extern int of_get_fb_videomode(struct device_node *np,
 extern int fb_videomode_from_videomode(const struct videomode *vm,
 				       struct fb_videomode *fbmode);
 
-/* drivers/video/modedb.c */
+/* modedb.c */
 #define VESA_MODEDB_SIZE 43
 #define DMT_SIZE 0x50
 
@@ -731,7 +828,7 @@ extern void fb_videomode_to_modelist(const struct fb_videomode *modedb, int num,
 extern const struct fb_videomode *fb_find_best_display(const struct fb_monspecs *specs,
 						       struct list_head *head);
 
-/* drivers/video/fbcmap.c */
+/* fbcmap.c */
 extern int fb_alloc_cmap(struct fb_cmap *cmap, int len, int transp);
 extern int fb_alloc_cmap_gfp(struct fb_cmap *cmap, int len, int transp, gfp_t flags);
 extern void fb_dealloc_cmap(struct fb_cmap *cmap);
@@ -781,16 +878,12 @@ extern int fb_find_mode(struct fb_var_screeninfo *var,
 			const struct fb_videomode *default_mode,
 			unsigned int default_bpp);
 
-#if defined(CONFIG_VIDEO_NOMODESET)
 bool fb_modesetting_disabled(const char *drvname);
-#else
-static inline bool fb_modesetting_disabled(const char *drvname)
-{
-	return false;
-}
-#endif
 
-/* Convenience logging macros */
+/*
+ * Convenience logging macros
+ */
+
 #define fb_err(fb_info, fmt, ...)					\
 	pr_err("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
 #define fb_notice(info, fmt, ...)					\
@@ -802,4 +895,12 @@ static inline bool fb_modesetting_disabled(const char *drvname)
 #define fb_dbg(fb_info, fmt, ...)					\
 	pr_debug("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
 
+#define fb_warn_once(fb_info, fmt, ...)					\
+	pr_warn_once("fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+
+#define fb_WARN_ONCE(fb_info, condition, fmt, ...) \
+	WARN_ONCE(condition, "fb%d: " fmt, (fb_info)->node, ##__VA_ARGS__)
+#define fb_WARN_ON_ONCE(fb_info, x) \
+	fb_WARN_ONCE(fb_info, (x), "%s", "fb_WARN_ON_ONCE(" __stringify(x) ")")
+
 #endif /* _LINUX_FB_H */
diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h
index 2382dec6d6ab..f206370060e1 100644
--- a/include/linux/fbcon.h
+++ b/include/linux/fbcon.h
@@ -1,6 +1,13 @@
 #ifndef _LINUX_FBCON_H
 #define _LINUX_FBCON_H
 
+#include <linux/compiler_types.h>
+
+struct fb_blit_caps;
+struct fb_info;
+struct fb_var_screeninfo;
+struct fb_videomode;
+
 #ifdef CONFIG_FRAMEBUFFER_CONSOLE
 void __init fb_console_init(void);
 void __exit fb_console_exit(void);
@@ -11,6 +18,7 @@ void fbcon_suspended(struct fb_info *info);
 void fbcon_resumed(struct fb_info *info);
 int fbcon_mode_deleted(struct fb_info *info,
 		       struct fb_videomode *mode);
+void fbcon_delete_modelist(struct list_head *head);
 void fbcon_new_modelist(struct fb_info *info);
 void fbcon_get_requirement(struct fb_info *info,
 			   struct fb_blit_caps *caps);
@@ -31,6 +39,7 @@ static inline void fbcon_suspended(struct fb_info *info) {}
 static inline void fbcon_resumed(struct fb_info *info) {}
 static inline int fbcon_mode_deleted(struct fb_info *info,
 				     struct fb_videomode *mode) { return 0; }
+static inline void fbcon_delete_modelist(struct list_head *head) {}
 static inline void fbcon_new_modelist(struct fb_info *info) {}
 static inline void fbcon_get_requirement(struct fb_info *info,
 					 struct fb_blit_caps *caps) {}
diff --git a/include/linux/fdtable.h b/include/linux/fdtable.h
index e066816f3519..c45306a9f007 100644
--- a/include/linux/fdtable.h
+++ b/include/linux/fdtable.h
@@ -22,7 +22,6 @@
  * as this is the granularity returned by copy_fdset().
  */
 #define NR_OPEN_DEFAULT BITS_PER_LONG
-#define NR_OPEN_MAX ~0U
 
 struct fdtable {
 	unsigned int max_fds;
@@ -33,16 +32,6 @@ struct fdtable {
 	struct rcu_head rcu;
 };
 
-static inline bool close_on_exec(unsigned int fd, const struct fdtable *fdt)
-{
-	return test_bit(fd, fdt->close_on_exec);
-}
-
-static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt)
-{
-	return test_bit(fd, fdt->open_fds);
-}
-
 /*
  * Open file table structure
  */
@@ -83,12 +72,17 @@ struct dentry;
 static inline struct file *files_lookup_fd_raw(struct files_struct *files, unsigned int fd)
 {
 	struct fdtable *fdt = rcu_dereference_raw(files->fdt);
-
-	if (fd < fdt->max_fds) {
-		fd = array_index_nospec(fd, fdt->max_fds);
-		return rcu_dereference_raw(fdt->fd[fd]);
-	}
-	return NULL;
+	unsigned long mask = array_index_mask_nospec(fd, fdt->max_fds);
+	struct file *needs_masking;
+
+	/*
+	 * 'mask' is zero for an out-of-bounds fd, all ones for ok.
+	 * 'fd&mask' is 'fd' for ok, or 0 for out of bounds.
+	 *
+	 * Accessing fdt->fd[0] is ok, but needs masking of the result.
+	 */
+	needs_masking = rcu_dereference_raw(fdt->fd[fd&mask]);
+	return (struct file *)(mask & (unsigned long)needs_masking);
 }
 
 static inline struct file *files_lookup_fd_locked(struct files_struct *files, unsigned int fd)
@@ -98,36 +92,26 @@ static inline struct file *files_lookup_fd_locked(struct files_struct *files, un
 	return files_lookup_fd_raw(files, fd);
 }
 
-static inline struct file *files_lookup_fd_rcu(struct files_struct *files, unsigned int fd)
+static inline bool close_on_exec(unsigned int fd, const struct files_struct *files)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
-			   "suspicious rcu_dereference_check() usage");
-	return files_lookup_fd_raw(files, fd);
+	return test_bit(fd, files_fdtable(files)->close_on_exec);
 }
 
-static inline struct file *lookup_fd_rcu(unsigned int fd)
-{
-	return files_lookup_fd_rcu(current->files, fd);
-}
-
-struct file *task_lookup_fd_rcu(struct task_struct *task, unsigned int fd);
-struct file *task_lookup_next_fd_rcu(struct task_struct *task, unsigned int *fd);
-
 struct task_struct;
 
 void put_files_struct(struct files_struct *fs);
 int unshare_files(void);
-struct files_struct *dup_fd(struct files_struct *, unsigned, int *) __latent_entropy;
+struct fd_range {
+	unsigned int from, to;
+};
+struct files_struct *dup_fd(struct files_struct *, struct fd_range *) __latent_entropy;
 void do_close_on_exec(struct files_struct *);
 int iterate_fd(struct files_struct *, unsigned,
 		int (*)(const void *, struct file *, unsigned),
 		const void *);
 
 extern int close_fd(unsigned int fd);
-extern int __close_range(unsigned int fd, unsigned int max_fd, unsigned int flags);
-extern struct file *close_fd_get_file(unsigned int fd);
-extern int unshare_fd(unsigned long unshare_flags, unsigned int max_fds,
-		      struct files_struct **new_fdp);
+extern struct file *file_close_fd(unsigned int fd);
 
 extern struct kmem_cache *files_cachep;
 
diff --git a/include/linux/fiemap.h b/include/linux/fiemap.h
index c50882f19235..966092ffa89a 100644
--- a/include/linux/fiemap.h
+++ b/include/linux/fiemap.h
@@ -5,12 +5,18 @@
 #include <uapi/linux/fiemap.h>
 #include <linux/fs.h>
 
+/**
+ * struct fiemap_extent_info - fiemap request to a filesystem
+ * @fi_flags:		Flags as passed from user
+ * @fi_extents_mapped:	Number of mapped extents
+ * @fi_extents_max:	Size of fiemap_extent array
+ * @fi_extents_start:	Start of fiemap_extent array
+ */
 struct fiemap_extent_info {
-	unsigned int fi_flags;		/* Flags as passed from user */
-	unsigned int fi_extents_mapped;	/* Number of mapped extents */
-	unsigned int fi_extents_max;	/* Size of fiemap_extent array */
-	struct fiemap_extent __user *fi_extents_start; /* Start of
-							fiemap_extent array */
+	unsigned int fi_flags;
+	unsigned int fi_extents_mapped;
+	unsigned int fi_extents_max;
+	struct fiemap_extent __user *fi_extents_start;
 };
 
 int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo,
diff --git a/include/linux/file.h b/include/linux/file.h
index 39704eae83e2..cf389fde9bc2 100644
--- a/include/linux/file.h
+++ b/include/linux/file.h
@@ -10,6 +10,8 @@
 #include <linux/types.h>
 #include <linux/posix_types.h>
 #include <linux/errno.h>
+#include <linux/cleanup.h>
+#include <linux/err.h>
 
 struct file;
 
@@ -23,63 +25,65 @@ struct inode;
 struct path;
 extern struct file *alloc_file_pseudo(struct inode *, struct vfsmount *,
 	const char *, int flags, const struct file_operations *);
+extern struct file *alloc_file_pseudo_noaccount(struct inode *, struct vfsmount *,
+	const char *, int flags, const struct file_operations *);
 extern struct file *alloc_file_clone(struct file *, int flags,
 	const struct file_operations *);
 
-static inline void fput_light(struct file *file, int fput_needed)
-{
-	if (fput_needed)
-		fput(file);
-}
-
+/* either a reference to struct file + flags
+ * (cloned vs. borrowed, pos locked), with
+ * flags stored in lower bits of value,
+ * or empty (represented by 0).
+ */
 struct fd {
-	struct file *file;
-	unsigned int flags;
+	unsigned long word;
 };
 #define FDPUT_FPUT       1
 #define FDPUT_POS_UNLOCK 2
 
-static inline void fdput(struct fd fd)
+#define fd_file(f) ((struct file *)((f).word & ~(FDPUT_FPUT|FDPUT_POS_UNLOCK)))
+static inline bool fd_empty(struct fd f)
 {
-	if (fd.flags & FDPUT_FPUT)
-		fput(fd.file);
+	return unlikely(!f.word);
 }
 
-extern struct file *fget(unsigned int fd);
-extern struct file *fget_raw(unsigned int fd);
-extern struct file *fget_task(struct task_struct *task, unsigned int fd);
-extern unsigned long __fdget(unsigned int fd);
-extern unsigned long __fdget_raw(unsigned int fd);
-extern unsigned long __fdget_pos(unsigned int fd);
-extern void __f_unlock_pos(struct file *);
-
-static inline struct fd __to_fd(unsigned long v)
+#define EMPTY_FD (struct fd){0}
+static inline struct fd BORROWED_FD(struct file *f)
 {
-	return (struct fd){(struct file *)(v & ~3),v & 3};
+	return (struct fd){(unsigned long)f};
 }
-
-static inline struct fd fdget(unsigned int fd)
+static inline struct fd CLONED_FD(struct file *f)
 {
-	return __to_fd(__fdget(fd));
+	return (struct fd){(unsigned long)f | FDPUT_FPUT};
 }
 
-static inline struct fd fdget_raw(unsigned int fd)
+static inline void fdput(struct fd fd)
 {
-	return __to_fd(__fdget_raw(fd));
+	if (unlikely(fd.word & FDPUT_FPUT))
+		fput(fd_file(fd));
 }
 
-static inline struct fd fdget_pos(int fd)
-{
-	return __to_fd(__fdget_pos(fd));
-}
+extern struct file *fget(unsigned int fd);
+extern struct file *fget_raw(unsigned int fd);
+extern struct file *fget_task(struct task_struct *task, unsigned int fd);
+extern struct file *fget_task_next(struct task_struct *task, unsigned int *fd);
+extern void __f_unlock_pos(struct file *);
+
+struct fd fdget(unsigned int fd);
+struct fd fdget_raw(unsigned int fd);
+struct fd fdget_pos(unsigned int fd);
 
 static inline void fdput_pos(struct fd f)
 {
-	if (f.flags & FDPUT_POS_UNLOCK)
-		__f_unlock_pos(f.file);
+	if (f.word & FDPUT_POS_UNLOCK)
+		__f_unlock_pos(fd_file(f));
 	fdput(f);
 }
 
+DEFINE_CLASS(fd, struct fd, fdput(_T), fdget(fd), int fd)
+DEFINE_CLASS(fd_raw, struct fd, fdput(_T), fdget_raw(fd), int fd)
+DEFINE_CLASS(fd_pos, struct fd, fdput_pos(_T), fdget_pos(fd), int fd)
+
 extern int f_dupfd(unsigned int from, struct file *file, unsigned flags);
 extern int replace_fd(unsigned fd, struct file *file, unsigned flags);
 extern void set_close_on_exec(unsigned int fd, int flag);
@@ -88,20 +92,34 @@ extern int __get_unused_fd_flags(unsigned flags, unsigned long nofile);
 extern int get_unused_fd_flags(unsigned flags);
 extern void put_unused_fd(unsigned int fd);
 
-extern void fd_install(unsigned int fd, struct file *file);
+DEFINE_CLASS(get_unused_fd, int, if (_T >= 0) put_unused_fd(_T),
+	     get_unused_fd_flags(flags), unsigned flags)
+DEFINE_FREE(fput, struct file *, if (!IS_ERR_OR_NULL(_T)) fput(_T))
 
-extern int __receive_fd(struct file *file, int __user *ufd,
-			unsigned int o_flags);
+/*
+ * take_fd() will take care to set @fd to -EBADF ensuring that
+ * CLASS(get_unused_fd) won't call put_unused_fd(). This makes it
+ * easier to rely on CLASS(get_unused_fd):
+ *
+ * struct file *f;
+ *
+ * CLASS(get_unused_fd, fd)(O_CLOEXEC);
+ * if (fd < 0)
+ *         return fd;
+ *
+ * f = dentry_open(&path, O_RDONLY, current_cred());
+ * if (IS_ERR(f))
+ *         return PTR_ERR(f);
+ *
+ * fd_install(fd, f);
+ * return take_fd(fd);
+ */
+#define take_fd(fd) __get_and_null(fd, -EBADF)
 
-extern int receive_fd(struct file *file, unsigned int o_flags);
+extern void fd_install(unsigned int fd, struct file *file);
+
+int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags);
 
-static inline int receive_fd_user(struct file *file, int __user *ufd,
-				  unsigned int o_flags)
-{
-	if (ufd == NULL)
-		return -EFAULT;
-	return __receive_fd(file, ufd, o_flags);
-}
 int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags);
 
 extern void flush_delayed_fput(void);
@@ -109,4 +127,130 @@ extern void __fput_sync(struct file *);
 
 extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max;
 
+/*
+ * fd_prepare: Combined fd + file allocation cleanup class.
+ * @err: Error code to indicate if allocation succeeded.
+ * @__fd: Allocated fd (may not be accessed directly)
+ * @__file: Allocated struct file pointer (may not be accessed directly)
+ *
+ * Allocates an fd and a file together. On error paths, automatically cleans
+ * up whichever resource was successfully allocated. Allows flexible file
+ * allocation with different functions per usage.
+ *
+ * Do not use directly.
+ */
+struct fd_prepare {
+	s32 err;
+	s32 __fd; /* do not access directly */
+	struct file *__file; /* do not access directly */
+};
+
+/* Typedef for fd_prepare cleanup guards. */
+typedef struct fd_prepare class_fd_prepare_t;
+
+/*
+ * Accessors for fd_prepare class members.
+ * _Generic() is used for zero-cost type safety.
+ */
+#define fd_prepare_fd(_fdf) \
+	(_Generic((_fdf), struct fd_prepare: (_fdf).__fd))
+
+#define fd_prepare_file(_fdf) \
+	(_Generic((_fdf), struct fd_prepare: (_fdf).__file))
+
+/* Do not use directly. */
+static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf)
+{
+	if (unlikely(fdf->err)) {
+		if (likely(fdf->__fd >= 0))
+			put_unused_fd(fdf->__fd);
+		if (unlikely(!IS_ERR_OR_NULL(fdf->__file)))
+			fput(fdf->__file);
+	}
+}
+
+/* Do not use directly. */
+static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf)
+{
+	if (unlikely(fdf->err))
+		return fdf->err;
+	if (unlikely(fdf->__fd < 0))
+		return fdf->__fd;
+	if (unlikely(IS_ERR(fdf->__file)))
+		return PTR_ERR(fdf->__file);
+	if (unlikely(!fdf->__file))
+		return -ENOMEM;
+	return 0;
+}
+
+/*
+ * __FD_PREPARE_INIT - Helper to initialize fd_prepare class.
+ * @_fd_flags: flags for get_unused_fd_flags()
+ * @_file_owned: expression that returns struct file *
+ *
+ * Returns a struct fd_prepare with fd, file, and err set.
+ * If fd allocation fails, fd will be negative and err will be set. If
+ * fd succeeds but file_init_expr fails, file will be ERR_PTR and err
+ * will be set. The err field is the single source of truth for error
+ * checking.
+ */
+#define __FD_PREPARE_INIT(_fd_flags, _file_owned)                 \
+	({                                                        \
+		struct fd_prepare fdf = {                         \
+			.__fd = get_unused_fd_flags((_fd_flags)), \
+		};                                                \
+		if (likely(fdf.__fd >= 0))                        \
+			fdf.__file = (_file_owned);               \
+		fdf.err = ACQUIRE_ERR(fd_prepare, &fdf);          \
+		fdf;                                              \
+	})
+
+/*
+ * FD_PREPARE - Macro to declare and initialize an fd_prepare variable.
+ *
+ * Declares and initializes an fd_prepare variable with automatic
+ * cleanup. No separate scope required - cleanup happens when variable
+ * goes out of scope.
+ *
+ * @_fdf: name of struct fd_prepare variable to define
+ * @_fd_flags: flags for get_unused_fd_flags()
+ * @_file_owned: struct file to take ownership of (can be expression)
+ */
+#define FD_PREPARE(_fdf, _fd_flags, _file_owned) \
+	CLASS_INIT(fd_prepare, _fdf, __FD_PREPARE_INIT(_fd_flags, _file_owned))
+
+/*
+ * fd_publish - Publish prepared fd and file to the fd table.
+ * @_fdf: struct fd_prepare variable
+ */
+#define fd_publish(_fdf)                                       \
+	({                                                     \
+		struct fd_prepare *fdp = &(_fdf);              \
+		VFS_WARN_ON_ONCE(fdp->err);                    \
+		VFS_WARN_ON_ONCE(fdp->__fd < 0);               \
+		VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \
+		fd_install(fdp->__fd, fdp->__file);            \
+		fdp->__fd;                                     \
+	})
+
+/* Do not use directly. */
+#define __FD_ADD(_fdf, _fd_flags, _file_owned)            \
+	({                                                \
+		FD_PREPARE(_fdf, _fd_flags, _file_owned); \
+		s32 ret = _fdf.err;                       \
+		if (likely(!ret))                         \
+			ret = fd_publish(_fdf);           \
+		ret;                                      \
+	})
+
+/*
+ * FD_ADD - Allocate and install an fd and file in one step.
+ * @_fd_flags: flags for get_unused_fd_flags()
+ * @_file_owned: struct file to take ownership of
+ *
+ * Returns the allocated fd number, or negative error code on failure.
+ */
+#define FD_ADD(_fd_flags, _file_owned) \
+	__FD_ADD(__UNIQUE_ID(fd_prepare), _fd_flags, _file_owned)
+
 #endif /* __LINUX_FILE_H */
diff --git a/include/linux/file_ref.h b/include/linux/file_ref.h
new file mode 100644
index 000000000000..31551e4cb8f3
--- /dev/null
+++ b/include/linux/file_ref.h
@@ -0,0 +1,218 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LINUX_FILE_REF_H
+#define _LINUX_FILE_REF_H
+
+#include <linux/atomic.h>
+#include <linux/preempt.h>
+#include <linux/types.h>
+
+/*
+ * file_ref is a reference count implementation specifically for use by
+ * files. It takes inspiration from rcuref but differs in key aspects
+ * such as support for SLAB_TYPESAFE_BY_RCU type caches.
+ *
+ * FILE_REF_ONEREF                FILE_REF_MAXREF
+ * 0x0000000000000000UL      0x7FFFFFFFFFFFFFFFUL
+ * <-------------------valid ------------------->
+ *
+ *                       FILE_REF_SATURATED
+ * 0x8000000000000000UL 0xA000000000000000UL 0xBFFFFFFFFFFFFFFFUL
+ * <-----------------------saturation zone---------------------->
+ *
+ * FILE_REF_RELEASED                   FILE_REF_DEAD
+ * 0xC000000000000000UL         0xE000000000000000UL
+ * <-------------------dead zone------------------->
+ *
+ * FILE_REF_NOREF
+ * 0xFFFFFFFFFFFFFFFFUL
+ */
+
+#ifdef CONFIG_64BIT
+#define FILE_REF_ONEREF		0x0000000000000000UL
+#define FILE_REF_MAXREF		0x7FFFFFFFFFFFFFFFUL
+#define FILE_REF_SATURATED	0xA000000000000000UL
+#define FILE_REF_RELEASED	0xC000000000000000UL
+#define FILE_REF_DEAD		0xE000000000000000UL
+#define FILE_REF_NOREF		0xFFFFFFFFFFFFFFFFUL
+#else
+#define FILE_REF_ONEREF		0x00000000U
+#define FILE_REF_MAXREF		0x7FFFFFFFU
+#define FILE_REF_SATURATED	0xA0000000U
+#define FILE_REF_RELEASED	0xC0000000U
+#define FILE_REF_DEAD		0xE0000000U
+#define FILE_REF_NOREF		0xFFFFFFFFU
+#endif
+
+typedef struct {
+#ifdef CONFIG_64BIT
+	atomic64_t refcnt;
+#else
+	atomic_t refcnt;
+#endif
+} file_ref_t;
+
+/**
+ * file_ref_init - Initialize a file reference count
+ * @ref: Pointer to the reference count
+ * @cnt: The initial reference count typically '1'
+ */
+static inline void file_ref_init(file_ref_t *ref, unsigned long cnt)
+{
+	atomic_long_set(&ref->refcnt, cnt - 1);
+}
+
+bool __file_ref_put(file_ref_t *ref, unsigned long cnt);
+
+/**
+ * file_ref_get - Acquire one reference on a file
+ * @ref: Pointer to the reference count
+ *
+ * Similar to atomic_inc_not_zero() but saturates at FILE_REF_MAXREF.
+ *
+ * Provides full memory ordering.
+ *
+ * Return: False if the attempt to acquire a reference failed. This happens
+ *         when the last reference has been put already. True if a reference
+ *         was successfully acquired
+ */
+static __always_inline __must_check bool file_ref_get(file_ref_t *ref)
+{
+	/*
+	 * Unconditionally increase the reference count with full
+	 * ordering. The saturation and dead zones provide enough
+	 * tolerance for this.
+	 *
+	 * If this indicates negative the file in question the fail can
+	 * be freed and immediately reused due to SLAB_TYPSAFE_BY_RCU.
+	 * Hence, unconditionally altering the file reference count to
+	 * e.g., reset the file reference count back to the middle of
+	 * the deadzone risk end up marking someone else's file as dead
+	 * behind their back.
+	 *
+	 * It would be possible to do a careful:
+	 *
+	 * cnt = atomic_long_inc_return();
+	 * if (likely(cnt >= 0))
+	 *	return true;
+	 *
+	 * and then something like:
+	 *
+	 * if (cnt >= FILE_REF_RELEASE)
+	 *	atomic_long_try_cmpxchg(&ref->refcnt, &cnt, FILE_REF_DEAD),
+	 *
+	 * to set the value back to the middle of the deadzone. But it's
+	 * practically impossible to go from FILE_REF_DEAD to
+	 * FILE_REF_ONEREF. It would need 2305843009213693952/2^61
+	 * file_ref_get()s to resurrect such a dead file.
+	 */
+	return !atomic_long_add_negative(1, &ref->refcnt);
+}
+
+/**
+ * file_ref_inc - Acquire one reference on a file
+ * @ref: Pointer to the reference count
+ *
+ * Acquire an additional reference on a file. Warns if the caller didn't
+ * already hold a reference.
+ */
+static __always_inline void file_ref_inc(file_ref_t *ref)
+{
+	long prior = atomic_long_fetch_inc_relaxed(&ref->refcnt);
+	WARN_ONCE(prior < 0, "file_ref_inc() on a released file reference");
+}
+
+/**
+ * file_ref_put -- Release a file reference
+ * @ref:	Pointer to the reference count
+ *
+ * Provides release memory ordering, such that prior loads and stores
+ * are done before, and provides an acquire ordering on success such
+ * that free() must come after.
+ *
+ * Return: True if this was the last reference with no future references
+ *         possible. This signals the caller that it can safely release
+ *         the object which is protected by the reference counter.
+ *         False if there are still active references or the put() raced
+ *         with a concurrent get()/put() pair. Caller is not allowed to
+ *         release the protected object.
+ */
+static __always_inline __must_check bool file_ref_put(file_ref_t *ref)
+{
+	long cnt;
+
+	/*
+	 * While files are SLAB_TYPESAFE_BY_RCU and thus file_ref_put()
+	 * calls don't risk UAFs when a file is recyclyed, it is still
+	 * vulnerable to UAFs caused by freeing the whole slab page once
+	 * it becomes unused. Prevent file_ref_put() from being
+	 * preempted protects against this.
+	 */
+	guard(preempt)();
+	/*
+	 * Unconditionally decrease the reference count. The saturation
+	 * and dead zones provide enough tolerance for this. If this
+	 * fails then we need to handle the last reference drop and
+	 * cases inside the saturation and dead zones.
+	 */
+	cnt = atomic_long_dec_return(&ref->refcnt);
+	if (cnt >= 0)
+		return false;
+	return __file_ref_put(ref, cnt);
+}
+
+/**
+ * file_ref_put_close - drop a reference expecting it would transition to FILE_REF_NOREF
+ * @ref:	Pointer to the reference count
+ *
+ * Semantically it is equivalent to calling file_ref_put(), but it trades lower
+ * performance in face of other CPUs also modifying the refcount for higher
+ * performance when this happens to be the last reference.
+ *
+ * For the last reference file_ref_put() issues 2 atomics. One to drop the
+ * reference and another to transition it to FILE_REF_DEAD. This routine does
+ * the work in one step, but in order to do it has to pre-read the variable which
+ * decreases scalability.
+ *
+ * Use with close() et al, stick to file_ref_put() by default.
+ */
+static __always_inline __must_check bool file_ref_put_close(file_ref_t *ref)
+{
+	long old;
+
+	old = atomic_long_read(&ref->refcnt);
+	if (likely(old == FILE_REF_ONEREF)) {
+		if (likely(atomic_long_try_cmpxchg(&ref->refcnt, &old, FILE_REF_DEAD)))
+			return true;
+	}
+	return file_ref_put(ref);
+}
+
+/**
+ * file_ref_read - Read the number of file references
+ * @ref: Pointer to the reference count
+ *
+ * Return: The number of held references (0 ... N)
+ */
+static inline unsigned long file_ref_read(file_ref_t *ref)
+{
+	unsigned long c = atomic_long_read(&ref->refcnt);
+
+	/* Return 0 if within the DEAD zone. */
+	return c >= FILE_REF_RELEASED ? 0 : c + 1;
+}
+
+/*
+ * __file_ref_read_raw - Return the value stored in ref->refcnt
+ * @ref: Pointer to the reference count
+ *
+ * Return: The raw value found in the counter
+ *
+ * A hack for file_needs_f_pos_lock(), you probably want to use
+ * file_ref_read() instead.
+ */
+static inline unsigned long __file_ref_read_raw(file_ref_t *ref)
+{
+	return atomic_long_read(&ref->refcnt);
+}
+
+#endif
diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h
index 47c05a9851d0..f89dcfad3f8f 100644
--- a/include/linux/fileattr.h
+++ b/include/linux/fileattr.h
@@ -14,13 +14,33 @@
 	 FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \
 	 FS_XFLAG_PROJINHERIT)
 
+/* Read-only inode flags */
+#define FS_XFLAG_RDONLY_MASK \
+	(FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR)
+
+/* Flags to indicate valid value of fsx_ fields */
+#define FS_XFLAG_VALUES_MASK \
+	(FS_XFLAG_EXTSIZE | FS_XFLAG_COWEXTSIZE)
+
+/* Flags for directories */
+#define FS_XFLAG_DIRONLY_MASK \
+	(FS_XFLAG_RTINHERIT | FS_XFLAG_NOSYMLINKS | FS_XFLAG_EXTSZINHERIT)
+
+/* Misc settable flags */
+#define FS_XFLAG_MISC_MASK \
+	(FS_XFLAG_REALTIME | FS_XFLAG_NODEFRAG | FS_XFLAG_FILESTREAM)
+
+#define FS_XFLAGS_MASK \
+	(FS_XFLAG_COMMON | FS_XFLAG_RDONLY_MASK | FS_XFLAG_VALUES_MASK | \
+	 FS_XFLAG_DIRONLY_MASK | FS_XFLAG_MISC_MASK)
+
 /*
  * Merged interface for miscellaneous file attributes.  'flags' originates from
  * ext* and 'fsx_flags' from xfs.  There's some overlap between the two, which
  * is handled by the VFS helpers, so filesystems are free to implement just one
  * or both of these sub-interfaces.
  */
-struct fileattr {
+struct file_kattr {
 	u32	flags;		/* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */
 	/* struct fsxattr: */
 	u32	fsx_xflags;	/* xflags field value (get/set) */
@@ -33,10 +53,10 @@ struct fileattr {
 	bool	fsx_valid:1;
 };
 
-int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa);
+int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa);
 
-void fileattr_fill_xflags(struct fileattr *fa, u32 xflags);
-void fileattr_fill_flags(struct fileattr *fa, u32 flags);
+void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags);
+void fileattr_fill_flags(struct file_kattr *fa, u32 flags);
 
 /**
  * fileattr_has_fsx - check for extended flags/attributes
@@ -45,15 +65,19 @@ void fileattr_fill_flags(struct fileattr *fa, u32 flags);
  * Return: true if any attributes are present that are not represented in
  * ->flags.
  */
-static inline bool fileattr_has_fsx(const struct fileattr *fa)
+static inline bool fileattr_has_fsx(const struct file_kattr *fa)
 {
 	return fa->fsx_valid &&
 		((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 ||
 		 fa->fsx_projid != 0 ||	fa->fsx_cowextsize != 0);
 }
 
-int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
-		     struct fileattr *fa);
+		     struct file_kattr *fa);
+int ioctl_getflags(struct file *file, unsigned int __user *argp);
+int ioctl_setflags(struct file *file, unsigned int __user *argp);
+int ioctl_fsgetxattr(struct file *file, void __user *argp);
+int ioctl_fssetxattr(struct file *file, void __user *argp);
 
 #endif /* _LINUX_FILEATTR_H */
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index efcdd1631d9b..54b824c05299 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -27,6 +27,7 @@
 #define FILE_LOCK_DEFERRED 1
 
 struct file_lock;
+struct file_lease;
 
 struct file_lock_operations {
 	void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
@@ -39,14 +40,17 @@ struct lock_manager_operations {
 	void (*lm_put_owner)(fl_owner_t);
 	void (*lm_notify)(struct file_lock *);	/* unblock callback */
 	int (*lm_grant)(struct file_lock *, int);
-	bool (*lm_break)(struct file_lock *);
-	int (*lm_change)(struct file_lock *, int, struct list_head *);
-	void (*lm_setup)(struct file_lock *, void **);
-	bool (*lm_breaker_owns_lease)(struct file_lock *);
 	bool (*lm_lock_expirable)(struct file_lock *cfl);
 	void (*lm_expire_lock)(void);
 };
 
+struct lease_manager_operations {
+	bool (*lm_break)(struct file_lease *);
+	int (*lm_change)(struct file_lease *, int, struct list_head *);
+	void (*lm_setup)(struct file_lease *, void **);
+	bool (*lm_breaker_owns_lease)(struct file_lease *);
+};
+
 struct lock_manager {
 	struct list_head list;
 	/*
@@ -85,31 +89,31 @@ bool opens_in_grace(struct net *);
  *
  * Obviously, the last two criteria only matter for POSIX locks.
  */
-struct file_lock {
-	struct file_lock *fl_blocker;	/* The lock, that is blocking us */
-	struct list_head fl_list;	/* link into file_lock_context */
-	struct hlist_node fl_link;	/* node in global lists */
-	struct list_head fl_blocked_requests;	/* list of requests with
+
+struct file_lock_core {
+	struct file_lock_core *flc_blocker;	/* The lock that is blocking us */
+	struct list_head flc_list;	/* link into file_lock_context */
+	struct hlist_node flc_link;	/* node in global lists */
+	struct list_head flc_blocked_requests;	/* list of requests with
 						 * ->fl_blocker pointing here
 						 */
-	struct list_head fl_blocked_member;	/* node in
+	struct list_head flc_blocked_member;	/* node in
 						 * ->fl_blocker->fl_blocked_requests
 						 */
-	fl_owner_t fl_owner;
-	unsigned int fl_flags;
-	unsigned char fl_type;
-	unsigned int fl_pid;
-	int fl_link_cpu;		/* what cpu's list is this on? */
-	wait_queue_head_t fl_wait;
-	struct file *fl_file;
+	fl_owner_t flc_owner;
+	unsigned int flc_flags;
+	unsigned char flc_type;
+	pid_t flc_pid;
+	int flc_link_cpu;		/* what cpu's list is this on? */
+	wait_queue_head_t flc_wait;
+	struct file *flc_file;
+};
+
+struct file_lock {
+	struct file_lock_core c;
 	loff_t fl_start;
 	loff_t fl_end;
 
-	struct fasync_struct *	fl_fasync; /* for lease break notifications */
-	/* for lease breaks: */
-	unsigned long fl_break_time;
-	unsigned long fl_downgrade_time;
-
 	const struct file_lock_operations *fl_ops;	/* Callbacks for filesystems */
 	const struct lock_manager_operations *fl_lmops;	/* Callbacks for lockmanagers */
 	union {
@@ -126,6 +130,15 @@ struct file_lock {
 	} fl_u;
 } __randomize_layout;
 
+struct file_lease {
+	struct file_lock_core c;
+	struct fasync_struct *	fl_fasync; /* for lease break notifications */
+	/* for lease breaks: */
+	unsigned long fl_break_time;
+	unsigned long fl_downgrade_time;
+	const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */
+} __randomize_layout;
+
 struct file_lock_context {
 	spinlock_t		flc_lock;
 	struct list_head	flc_flock;
@@ -144,14 +157,46 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int,
 			struct flock64 *);
 #endif
 
-int fcntl_setlease(unsigned int fd, struct file *filp, long arg);
+int fcntl_setlease(unsigned int fd, struct file *filp, int arg);
 int fcntl_getlease(struct file *filp);
+int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg);
+int fcntl_getdeleg(struct file *filp, struct delegation *deleg);
+
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_UNLCK;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_RDLCK;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+	return fl->c.flc_type == F_WRLCK;
+}
+
+static inline void locks_wake_up_waiter(struct file_lock_core *flc)
+{
+	wake_up(&flc->flc_wait);
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+	locks_wake_up_waiter(&fl->c);
+}
+
+static inline bool locks_can_async_lock(const struct file_operations *fops)
+{
+	return !fops->lock || fops->fop_flags & FOP_ASYNC_LOCK;
+}
 
 /* fs/locks.c */
 void locks_free_lock_context(struct inode *inode);
 void locks_free_lock(struct file_lock *fl);
 void locks_init_lock(struct file_lock *);
-struct file_lock * locks_alloc_lock(void);
+struct file_lock *locks_alloc_lock(void);
 void locks_copy_lock(struct file_lock *, struct file_lock *);
 void locks_copy_conflock(struct file_lock *, struct file_lock *);
 void locks_remove_posix(struct file *, fl_owner_t);
@@ -165,11 +210,23 @@ int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_l
 int vfs_cancel_lock(struct file *filp, struct file_lock *fl);
 bool vfs_inode_has_locks(struct inode *inode);
 int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl);
-int __break_lease(struct inode *inode, unsigned int flags, unsigned int type);
+
+void locks_init_lease(struct file_lease *);
+void locks_free_lease(struct file_lease *fl);
+struct file_lease *locks_alloc_lease(void);
+
+#define LEASE_BREAK_LEASE		BIT(0)	// break leases and delegations
+#define LEASE_BREAK_DELEG		BIT(1)	// break delegations only
+#define LEASE_BREAK_LAYOUT		BIT(2)	// break layouts only
+#define LEASE_BREAK_NONBLOCK		BIT(3)	// non-blocking break
+#define LEASE_BREAK_OPEN_RDONLY		BIT(4)	// readonly open event
+
+int __break_lease(struct inode *inode, unsigned int flags);
 void lease_get_mtime(struct inode *, struct timespec64 *time);
-int generic_setlease(struct file *, long, struct file_lock **, void **priv);
-int vfs_setlease(struct file *, long, struct file_lock **, void **);
-int lease_modify(struct file_lock *, int, struct list_head *);
+int generic_setlease(struct file *, int, struct file_lease **, void **priv);
+int kernel_setlease(struct file *, int, struct file_lease **, void **);
+int vfs_setlease(struct file *, int, struct file_lease **, void **);
+int lease_modify(struct file_lease *, int, struct list_head *);
 
 struct notifier_block;
 int lease_register_notifier(struct notifier_block *);
@@ -213,7 +270,7 @@ static inline int fcntl_setlk64(unsigned int fd, struct file *file,
 	return -EACCES;
 }
 #endif
-static inline int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
+static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg)
 {
 	return -EINVAL;
 }
@@ -223,6 +280,35 @@ static inline int fcntl_getlease(struct file *filp)
 	return F_UNLCK;
 }
 
+static inline int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg)
+{
+	return -EINVAL;
+}
+
+static inline int fcntl_getdeleg(struct file *filp, struct delegation *deleg)
+{
+	return -EINVAL;
+}
+
+static inline bool lock_is_unlock(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline bool lock_is_read(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline bool lock_is_write(struct file_lock *fl)
+{
+	return false;
+}
+
+static inline void locks_wake_up(struct file_lock *fl)
+{
+}
+
 static inline void
 locks_free_lock_context(struct inode *inode)
 {
@@ -233,6 +319,11 @@ static inline void locks_init_lock(struct file_lock *fl)
 	return;
 }
 
+static inline void locks_init_lease(struct file_lease *fl)
+{
+	return;
+}
+
 static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl)
 {
 	return;
@@ -295,7 +386,7 @@ static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *f
 	return -ENOLCK;
 }
 
-static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type)
+static inline int __break_lease(struct inode *inode, unsigned int flags)
 {
 	return 0;
 }
@@ -306,19 +397,25 @@ static inline void lease_get_mtime(struct inode *inode,
 	return;
 }
 
-static inline int generic_setlease(struct file *filp, long arg,
-				    struct file_lock **flp, void **priv)
+static inline int generic_setlease(struct file *filp, int arg,
+				    struct file_lease **flp, void **priv)
+{
+	return -EINVAL;
+}
+
+static inline int kernel_setlease(struct file *filp, int arg,
+			       struct file_lease **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int vfs_setlease(struct file *filp, long arg,
-			       struct file_lock **lease, void **priv)
+static inline int vfs_setlease(struct file *filp, int arg,
+			       struct file_lease **lease, void **priv)
 {
 	return -EINVAL;
 }
 
-static inline int lease_modify(struct file_lock *fl, int arg,
+static inline int lease_modify(struct file_lease *fl, int arg,
 			       struct list_head *dispose)
 {
 	return -EINVAL;
@@ -341,89 +438,137 @@ locks_inode_context(const struct inode *inode)
 
 #endif /* !CONFIG_FILE_LOCKING */
 
+/* for walking lists of file_locks linked by fl_list */
+#define for_each_file_lock(_fl, _head)	list_for_each_entry(_fl, _head, c.flc_list)
+
 static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl)
 {
 	return locks_lock_inode_wait(file_inode(filp), fl);
 }
 
 #ifdef CONFIG_FILE_LOCKING
+static inline unsigned int openmode_to_lease_flags(unsigned int mode)
+{
+	unsigned int flags = 0;
+
+	if ((mode & O_ACCMODE) == O_RDONLY)
+		flags |= LEASE_BREAK_OPEN_RDONLY;
+	if (mode & O_NONBLOCK)
+		flags |= LEASE_BREAK_NONBLOCK;
+	return flags;
+}
+
 static inline int break_lease(struct inode *inode, unsigned int mode)
 {
+	struct file_lock_context *flctx;
+
 	/*
 	 * Since this check is lockless, we must ensure that any refcounts
 	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
 	 * could end up racing with tasks trying to set a new lease on this
 	 * file.
 	 */
+	flctx = READ_ONCE(inode->i_flctx);
+	if (!flctx)
+		return 0;
 	smp_mb();
-	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
-		return __break_lease(inode, mode, FL_LEASE);
+	if (!list_empty_careful(&flctx->flc_lease))
+		return __break_lease(inode, LEASE_BREAK_LEASE | openmode_to_lease_flags(mode));
 	return 0;
 }
 
-static inline int break_deleg(struct inode *inode, unsigned int mode)
+static inline int break_deleg(struct inode *inode, unsigned int flags)
 {
+	struct file_lock_context *flctx;
+
 	/*
 	 * Since this check is lockless, we must ensure that any refcounts
 	 * taken are done before checking i_flctx->flc_lease. Otherwise, we
 	 * could end up racing with tasks trying to set a new lease on this
 	 * file.
 	 */
+	flctx = READ_ONCE(inode->i_flctx);
+	if (!flctx)
+		return 0;
 	smp_mb();
-	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
-		return __break_lease(inode, mode, FL_DELEG);
+	if (!list_empty_careful(&flctx->flc_lease)) {
+		flags |= LEASE_BREAK_DELEG;
+		return __break_lease(inode, flags);
+	}
 	return 0;
 }
 
-static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+struct delegated_inode {
+	struct inode *di_inode;
+};
+
+static inline bool is_delegated(struct delegated_inode *di)
+{
+	return di->di_inode;
+}
+
+static inline int try_break_deleg(struct inode *inode,
+				  struct delegated_inode *di)
 {
 	int ret;
 
-	ret = break_deleg(inode, O_WRONLY|O_NONBLOCK);
-	if (ret == -EWOULDBLOCK && delegated_inode) {
-		*delegated_inode = inode;
+	ret = break_deleg(inode, LEASE_BREAK_NONBLOCK);
+	if (ret == -EWOULDBLOCK && di) {
+		di->di_inode = inode;
 		ihold(inode);
 	}
 	return ret;
 }
 
-static inline int break_deleg_wait(struct inode **delegated_inode)
+static inline int break_deleg_wait(struct delegated_inode *di)
 {
 	int ret;
 
-	ret = break_deleg(*delegated_inode, O_WRONLY);
-	iput(*delegated_inode);
-	*delegated_inode = NULL;
+	ret = break_deleg(di->di_inode, 0);
+	iput(di->di_inode);
+	di->di_inode = NULL;
 	return ret;
 }
 
 static inline int break_layout(struct inode *inode, bool wait)
 {
 	smp_mb();
-	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease))
-		return __break_lease(inode,
-				wait ? O_WRONLY : O_WRONLY | O_NONBLOCK,
-				FL_LAYOUT);
+	if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) {
+		unsigned int flags = LEASE_BREAK_LAYOUT;
+
+		if (!wait)
+			flags |= LEASE_BREAK_NONBLOCK;
+
+		return __break_lease(inode, flags);
+	}
 	return 0;
 }
 
 #else /* !CONFIG_FILE_LOCKING */
-static inline int break_lease(struct inode *inode, unsigned int mode)
+struct delegated_inode { };
+
+static inline bool is_delegated(struct delegated_inode *di)
+{
+	return false;
+}
+
+static inline int break_lease(struct inode *inode, bool wait)
 {
 	return 0;
 }
 
-static inline int break_deleg(struct inode *inode, unsigned int mode)
+static inline int break_deleg(struct inode *inode, unsigned int flags)
 {
 	return 0;
 }
 
-static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode)
+static inline int try_break_deleg(struct inode *inode,
+				  struct delegated_inode *delegated_inode)
 {
 	return 0;
 }
 
-static inline int break_deleg_wait(struct inode **delegated_inode)
+static inline int break_deleg_wait(struct delegated_inode *delegated_inode)
 {
 	BUG();
 	return 0;
diff --git a/include/linux/filter.h b/include/linux/filter.h
index bbce89937fde..fd54fed8f95f 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -69,11 +69,23 @@ struct ctl_table_header;
 /* unused opcode to mark special load instruction. Same as BPF_ABS */
 #define BPF_PROBE_MEM	0x20
 
+/* unused opcode to mark special ldsx instruction. Same as BPF_IND */
+#define BPF_PROBE_MEMSX	0x40
+
+/* unused opcode to mark special load instruction. Same as BPF_MSH */
+#define BPF_PROBE_MEM32	0xa0
+
+/* unused opcode to mark special atomic instruction */
+#define BPF_PROBE_ATOMIC 0xe0
+
+/* unused opcode to mark special ldsx instruction. Same as BPF_NOSPEC */
+#define BPF_PROBE_MEM32SX 0xc0
+
 /* unused opcode to mark call to interpreter with arguments */
 #define BPF_CALL_ARGS	0xe0
 
 /* unused opcode to mark speculation barrier for mitigating
- * Speculative Store Bypass
+ * Spectre v1 and v4
  */
 #define BPF_NOSPEC	0xc0
 
@@ -90,39 +102,49 @@ struct ctl_table_header;
 
 /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
 
-#define BPF_ALU64_REG(OP, DST, SRC)				\
+#define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_X,	\
 		.dst_reg = DST,					\
 		.src_reg = SRC,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = 0 })
 
-#define BPF_ALU32_REG(OP, DST, SRC)				\
+#define BPF_ALU64_REG(OP, DST, SRC)				\
+	BPF_ALU64_REG_OFF(OP, DST, SRC, 0)
+
+#define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU | BPF_OP(OP) | BPF_X,		\
 		.dst_reg = DST,					\
 		.src_reg = SRC,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = 0 })
 
+#define BPF_ALU32_REG(OP, DST, SRC)				\
+	BPF_ALU32_REG_OFF(OP, DST, SRC, 0)
+
 /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
 
-#define BPF_ALU64_IMM(OP, DST, IMM)				\
+#define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU64 | BPF_OP(OP) | BPF_K,	\
 		.dst_reg = DST,					\
 		.src_reg = 0,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = IMM })
+#define BPF_ALU64_IMM(OP, DST, IMM)				\
+	BPF_ALU64_IMM_OFF(OP, DST, IMM, 0)
 
-#define BPF_ALU32_IMM(OP, DST, IMM)				\
+#define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF)			\
 	((struct bpf_insn) {					\
 		.code  = BPF_ALU | BPF_OP(OP) | BPF_K,		\
 		.dst_reg = DST,					\
 		.src_reg = 0,					\
-		.off   = 0,					\
+		.off   = OFF,					\
 		.imm   = IMM })
+#define BPF_ALU32_IMM(OP, DST, IMM)				\
+	BPF_ALU32_IMM_OFF(OP, DST, IMM, 0)
 
 /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
 
@@ -134,6 +156,16 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = LEN })
 
+/* Byte Swap, bswap16/32/64 */
+
+#define BPF_BSWAP(DST, LEN)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE),	\
+		.dst_reg = DST,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = LEN })
+
 /* Short form of mov, dst_reg = src_reg */
 
 #define BPF_MOV64_REG(DST, SRC)					\
@@ -152,6 +184,25 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = 0 })
 
+/* Special (internal-only) form of mov, used to resolve per-CPU addrs:
+ * dst_reg = src_reg + <percpu_base_off>
+ * BPF_ADDR_PERCPU is used as a special insn->off value.
+ */
+#define BPF_ADDR_PERCPU	(-1)
+
+#define BPF_MOV64_PERCPU_REG(DST, SRC)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = BPF_ADDR_PERCPU,			\
+		.imm   = 0 })
+
+static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU;
+}
+
 /* Short form of mov, dst_reg = imm32 */
 
 #define BPF_MOV64_IMM(DST, IMM)					\
@@ -170,6 +221,24 @@ struct ctl_table_header;
 		.off   = 0,					\
 		.imm   = IMM })
 
+/* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */
+
+#define BPF_MOVSX64_REG(DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU64 | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
+#define BPF_MOVSX32_REG(DST, SRC, OFF)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_ALU | BPF_MOV | BPF_X,		\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Special form of mov32, used for doing explicit zero extension on dst. */
 #define BPF_ZEXT_REG(DST)					\
 	((struct bpf_insn) {					\
@@ -184,6 +253,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 	return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1;
 }
 
+/* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers
+ * to pointers in user vma.
+ */
+static inline bool insn_is_cast_user(const struct bpf_insn *insn)
+{
+	return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) &&
+			      insn->off == BPF_ADDR_SPACE_CAST &&
+			      insn->imm == 1U << 16;
+}
+
 /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
 #define BPF_LD_IMM64(DST, IMM)					\
 	BPF_LD_IMM64_RAW(DST, 0, IMM)
@@ -254,6 +333,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Memory load, dst_reg = *(signed size *) (src_reg + off16) */
+
+#define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF)			\
+	((struct bpf_insn) {					\
+		.code  = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX,	\
+		.dst_reg = DST,					\
+		.src_reg = SRC,					\
+		.off   = OFF,					\
+		.imm   = 0 })
+
 /* Memory store, *(uint *) (dst_reg + off16) = src_reg */
 
 #define BPF_STX_MEM(SIZE, DST, SRC, OFF)			\
@@ -278,6 +367,8 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
  *   BPF_XOR | BPF_FETCH      src_reg = atomic_fetch_xor(dst_reg + off16, src_reg);
  *   BPF_XCHG                 src_reg = atomic_xchg(dst_reg + off16, src_reg)
  *   BPF_CMPXCHG              r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg)
+ *   BPF_LOAD_ACQ             dst_reg = smp_load_acquire(src_reg + off16)
+ *   BPF_STORE_REL            smp_store_release(dst_reg + off16, src_reg)
  */
 
 #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF)			\
@@ -351,6 +442,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = OFF,					\
 		.imm   = 0 })
 
+/* Unconditional jumps, gotol pc + imm32 */
+
+#define BPF_JMP32_A(IMM)					\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP32 | BPF_JA,			\
+		.dst_reg = 0,					\
+		.src_reg = 0,					\
+		.off   = 0,					\
+		.imm   = IMM })
+
 /* Relative call */
 
 #define BPF_CALL_REL(TGT)					\
@@ -373,6 +474,16 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 		.off   = 0,					\
 		.imm   = BPF_CALL_IMM(FUNC) })
 
+/* Kfunc call */
+
+#define BPF_CALL_KFUNC(OFF, IMM)				\
+	((struct bpf_insn) {					\
+		.code  = BPF_JMP | BPF_CALL,			\
+		.dst_reg = 0,					\
+		.src_reg = BPF_PSEUDO_KFUNC_CALL,		\
+		.off   = OFF,					\
+		.imm   = IMM })
+
 /* Raw code statement block */
 
 #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM)			\
@@ -496,24 +607,27 @@ static inline bool insn_is_zext(const struct bpf_insn *insn)
 	__BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2,       \
 		  u64, __ur_3, u64, __ur_4, u64, __ur_5)
 
-#define BPF_CALL_x(x, name, ...)					       \
+#define BPF_CALL_x(x, attr, name, ...)					       \
 	static __always_inline						       \
 	u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__));   \
 	typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \
-	u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__));	       \
-	u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__))	       \
+	attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__));    \
+	attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__))     \
 	{								       \
 		return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\
 	}								       \
 	static __always_inline						       \
 	u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__))
 
-#define BPF_CALL_0(name, ...)	BPF_CALL_x(0, name, __VA_ARGS__)
-#define BPF_CALL_1(name, ...)	BPF_CALL_x(1, name, __VA_ARGS__)
-#define BPF_CALL_2(name, ...)	BPF_CALL_x(2, name, __VA_ARGS__)
-#define BPF_CALL_3(name, ...)	BPF_CALL_x(3, name, __VA_ARGS__)
-#define BPF_CALL_4(name, ...)	BPF_CALL_x(4, name, __VA_ARGS__)
-#define BPF_CALL_5(name, ...)	BPF_CALL_x(5, name, __VA_ARGS__)
+#define __NOATTR
+#define BPF_CALL_0(name, ...)	BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__)
+#define BPF_CALL_1(name, ...)	BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__)
+#define BPF_CALL_2(name, ...)	BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__)
+#define BPF_CALL_3(name, ...)	BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__)
+#define BPF_CALL_4(name, ...)	BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__)
+#define BPF_CALL_5(name, ...)	BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__)
+
+#define NOTRACE_BPF_CALL_1(name, ...)	BPF_CALL_x(1, notrace, name, __VA_ARGS__)
 
 #define bpf_ctx_range(TYPE, MEMBER)						\
 	offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1
@@ -560,6 +674,11 @@ struct bpf_prog_stats {
 	struct u64_stats_sync syncp;
 } __aligned(2 * sizeof(u64));
 
+struct bpf_timed_may_goto {
+	u64 count;
+	u64 timestamp;
+};
+
 struct sk_filter {
 	refcount_t	refcnt;
 	struct rcu_head	rcu;
@@ -587,15 +706,19 @@ static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog,
 	cant_migrate();
 	if (static_branch_unlikely(&bpf_stats_enabled_key)) {
 		struct bpf_prog_stats *stats;
-		u64 start = sched_clock();
+		u64 duration, start = sched_clock();
 		unsigned long flags;
 
 		ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
-		stats = this_cpu_ptr(prog->stats);
-		flags = u64_stats_update_begin_irqsave(&stats->syncp);
-		u64_stats_inc(&stats->cnt);
-		u64_stats_add(&stats->nsecs, sched_clock() - start);
-		u64_stats_update_end_irqrestore(&stats->syncp, flags);
+
+		duration = sched_clock() - start;
+		if (likely(prog->stats)) {
+			stats = this_cpu_ptr(prog->stats);
+			flags = u64_stats_update_begin_irqsave(&stats->syncp);
+			u64_stats_inc(&stats->cnt);
+			u64_stats_add(&stats->nsecs, duration);
+			u64_stats_update_end_irqrestore(&stats->syncp, flags);
+		}
 	} else {
 		ret = dfunc(ctx, prog->insnsi, prog->bpf_func);
 	}
@@ -642,21 +765,128 @@ struct bpf_nh_params {
 	};
 };
 
+/* flags for bpf_redirect_info kern_flags */
+#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
+#define BPF_RI_F_RI_INIT	BIT(1)
+#define BPF_RI_F_CPU_MAP_INIT	BIT(2)
+#define BPF_RI_F_DEV_MAP_INIT	BIT(3)
+#define BPF_RI_F_XSK_MAP_INIT	BIT(4)
+
 struct bpf_redirect_info {
 	u64 tgt_index;
 	void *tgt_value;
 	struct bpf_map *map;
 	u32 flags;
-	u32 kern_flags;
 	u32 map_id;
 	enum bpf_map_type map_type;
 	struct bpf_nh_params nh;
+	u32 kern_flags;
 };
 
-DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
+struct bpf_net_context {
+	struct bpf_redirect_info ri;
+	struct list_head cpu_map_flush_list;
+	struct list_head dev_map_flush_list;
+	struct list_head xskmap_map_flush_list;
+};
 
-/* flags for bpf_redirect_info kern_flags */
-#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
+static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx)
+{
+	struct task_struct *tsk = current;
+
+	if (tsk->bpf_net_context != NULL)
+		return NULL;
+	bpf_net_ctx->ri.kern_flags = 0;
+
+	tsk->bpf_net_context = bpf_net_ctx;
+	return bpf_net_ctx;
+}
+
+static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx)
+{
+	if (bpf_net_ctx)
+		current->bpf_net_context = NULL;
+}
+
+static inline struct bpf_net_context *bpf_net_ctx_get(void)
+{
+	return current->bpf_net_context;
+}
+
+static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) {
+		memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh));
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT;
+	}
+
+	return &bpf_net_ctx->ri;
+}
+
+static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) {
+		INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list);
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT;
+	}
+
+	return &bpf_net_ctx->cpu_map_flush_list;
+}
+
+static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) {
+		INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list);
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT;
+	}
+
+	return &bpf_net_ctx->dev_map_flush_list;
+}
+
+static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) {
+		INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list);
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT;
+	}
+
+	return &bpf_net_ctx->xskmap_map_flush_list;
+}
+
+static inline void bpf_net_ctx_get_all_used_flush_lists(struct list_head **lh_map,
+							struct list_head **lh_dev,
+							struct list_head **lh_xsk)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+	u32 kern_flags = bpf_net_ctx->ri.kern_flags;
+	struct list_head *lh;
+
+	*lh_map = *lh_dev = *lh_xsk = NULL;
+
+	if (!IS_ENABLED(CONFIG_BPF_SYSCALL))
+		return;
+
+	lh = &bpf_net_ctx->dev_map_flush_list;
+	if (kern_flags & BPF_RI_F_DEV_MAP_INIT && !list_empty(lh))
+		*lh_dev = lh;
+
+	lh = &bpf_net_ctx->cpu_map_flush_list;
+	if (kern_flags & BPF_RI_F_CPU_MAP_INIT && !list_empty(lh))
+		*lh_map = lh;
+
+	lh = &bpf_net_ctx->xskmap_map_flush_list;
+	if (IS_ENABLED(CONFIG_XDP_SOCKETS) &&
+	    kern_flags & BPF_RI_F_XSK_MAP_INIT && !list_empty(lh))
+		*lh_xsk = lh;
+}
 
 /* Compute the linear packet data range [data, data_end) which
  * will be accessed by various program types (cls_bpf, act_bpf,
@@ -673,6 +903,26 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb)
 	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
+static inline int bpf_prog_run_data_pointers(
+	const struct bpf_prog *prog,
+	struct sk_buff *skb)
+{
+	struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;
+	void *save_data_meta, *save_data_end;
+	int res;
+
+	save_data_meta = cb->data_meta;
+	save_data_end = cb->data_end;
+
+	bpf_compute_data_pointers(skb);
+	res = bpf_prog_run(prog, skb);
+
+	cb->data_meta = save_data_meta;
+	cb->data_end = save_data_end;
+
+	return res;
+}
+
 /* Similar to bpf_compute_data_pointers(), except that save orginal
  * data in cb->data and cb->meta_data for restore.
  */
@@ -685,7 +935,7 @@ static inline void bpf_compute_and_save_data_end(
 	cb->data_end  = skb->data + skb_headlen(skb);
 }
 
-/* Restore data saved by bpf_compute_data_pointers(). */
+/* Restore data saved by bpf_compute_and_save_data_end(). */
 static inline void bpf_restore_data_end(
 	struct sk_buff *skb, void *saved_data_end)
 {
@@ -765,23 +1015,6 @@ DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
 
 u32 xdp_master_redirect(struct xdp_buff *xdp);
 
-static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
-					    struct xdp_buff *xdp)
-{
-	/* Driver XDP hooks are invoked within a single NAPI poll cycle and thus
-	 * under local_bh_disable(), which provides the needed RCU protection
-	 * for accessing map entries.
-	 */
-	u32 act = __bpf_prog_run(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
-
-	if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
-		if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
-			act = xdp_master_redirect(xdp);
-	}
-
-	return act;
-}
-
 void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog);
 
 static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog)
@@ -789,12 +1022,6 @@ static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog)
 	return prog->len * sizeof(struct bpf_insn);
 }
 
-static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog)
-{
-	return round_up(bpf_prog_insn_size(prog) +
-			sizeof(__be64) + 1, SHA1_BLOCK_SIZE);
-}
-
 static inline unsigned int bpf_prog_size(unsigned int proglen)
 {
 	return max(sizeof(struct bpf_prog),
@@ -847,26 +1074,38 @@ bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default)
 
 #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
 
-static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
+static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp)
 {
 #ifndef CONFIG_BPF_JIT_ALWAYS_ON
 	if (!fp->jited) {
 		set_vm_flush_reset_perms(fp);
-		set_memory_ro((unsigned long)fp, fp->pages);
+		return set_memory_ro((unsigned long)fp, fp->pages);
 	}
 #endif
+	return 0;
 }
 
-static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
+static inline int __must_check
+bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
 	set_vm_flush_reset_perms(hdr);
-	set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT);
+	return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT);
 }
 
-int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap,
+		       enum skb_drop_reason *reason);
+
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
-	return sk_filter_trim_cap(sk, skb, 1);
+	enum skb_drop_reason ignore_reason;
+
+	return sk_filter_trim_cap(sk, skb, 1, &ignore_reason);
+}
+
+static inline int sk_filter_reason(struct sock *sk, struct sk_buff *skb,
+				   enum skb_drop_reason *reason)
+{
+	return sk_filter_trim_cap(sk, skb, 1, reason);
 }
 
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
@@ -874,7 +1113,6 @@ void bpf_prog_free(struct bpf_prog *fp);
 
 bool bpf_opcode_in_insntable(u8 code);
 
-void bpf_prog_free_linfo(struct bpf_prog *prog);
 void bpf_prog_fill_jited_linfo(struct bpf_prog *prog,
 			       const u32 *insn_to_jit_off);
 int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog);
@@ -918,10 +1156,22 @@ u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog);
 void bpf_jit_compile(struct bpf_prog *prog);
 bool bpf_jit_needs_zext(void);
+bool bpf_jit_inlines_helper_call(s32 imm);
 bool bpf_jit_supports_subprog_tailcalls(void);
+bool bpf_jit_supports_percpu_insn(void);
 bool bpf_jit_supports_kfunc_call(void);
 bool bpf_jit_supports_far_kfunc_call(void);
-bool bpf_helper_changes_pkt_data(void *func);
+bool bpf_jit_supports_exceptions(void);
+bool bpf_jit_supports_ptr_xchg(void);
+bool bpf_jit_supports_arena(void);
+bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena);
+bool bpf_jit_supports_private_stack(void);
+bool bpf_jit_supports_timed_may_goto(void);
+u64 bpf_arch_uaddress_limit(void);
+void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie);
+u64 arch_bpf_timed_may_goto(void);
+u64 bpf_check_timed_may_goto(struct bpf_timed_may_goto *);
+bool bpf_helper_changes_pkt_data(enum bpf_func_id func_id);
 
 static inline bool bpf_dump_raw_ok(const struct cred *cred)
 {
@@ -935,25 +1185,23 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt);
 
-void bpf_clear_redirect_map(struct bpf_map *map);
-
 static inline bool xdp_return_frame_no_direct(void)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;
 }
 
 static inline void xdp_set_return_frame_no_direct(void)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;
 }
 
 static inline void xdp_clear_return_frame_no_direct(void)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;
 }
@@ -980,23 +1228,18 @@ static inline int xdp_ok_fwd_dev(const struct net_device *fwd,
  * This does not appear to be a real limitation for existing software.
  */
 int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
-			    struct xdp_buff *xdp, struct bpf_prog *prog);
+			    struct xdp_buff *xdp, const struct bpf_prog *prog);
 int xdp_do_redirect(struct net_device *dev,
 		    struct xdp_buff *xdp,
-		    struct bpf_prog *prog);
+		    const struct bpf_prog *prog);
 int xdp_do_redirect_frame(struct net_device *dev,
 			  struct xdp_buff *xdp,
 			  struct xdp_frame *xdpf,
-			  struct bpf_prog *prog);
+			  const struct bpf_prog *prog);
 void xdp_do_flush(void);
 
-/* The xdp_do_flush_map() helper has been renamed to drop the _map suffix, as
- * it is no longer only flushing maps. Keep this define for compatibility
- * until all drivers are updated - do not use xdp_do_flush_map() in new code!
- */
-#define xdp_do_flush_map xdp_do_flush
-
-void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act);
+void bpf_warn_invalid_xdp_action(const struct net_device *dev,
+				 const struct bpf_prog *prog, u32 act);
 
 #ifdef CONFIG_INET
 struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk,
@@ -1038,7 +1281,7 @@ struct bpf_binary_header *
 bpf_jit_binary_pack_hdr(const struct bpf_prog *fp);
 
 void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns);
-void bpf_prog_pack_free(struct bpf_binary_header *hdr);
+void bpf_prog_pack_free(void *ptr, u32 size);
 
 static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp)
 {
@@ -1052,8 +1295,7 @@ bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image,
 			  struct bpf_binary_header **rw_hdr,
 			  u8 **rw_image,
 			  bpf_jit_fill_hole_t bpf_fill_ill_insns);
-int bpf_jit_binary_pack_finalize(struct bpf_prog *prog,
-				 struct bpf_binary_header *ro_header,
+int bpf_jit_binary_pack_finalize(struct bpf_binary_header *ro_header,
 				 struct bpf_binary_header *rw_header);
 void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header,
 			      struct bpf_binary_header *rw_header);
@@ -1065,13 +1307,15 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
 			  const struct bpf_insn *insn, bool extra_pass,
 			  u64 *func_addr, bool *func_addr_fixed);
 
+const char *bpf_jit_get_prog_name(struct bpf_prog *prog);
+
 struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
 void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
 
 static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
 				u32 pass, void *image)
 {
-	pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen,
+	pr_err("flen=%u proglen=%u pass=%u image=%p from=%s pid=%d\n", flen,
 	       proglen, pass, image, current->comm, task_pid_nr(current));
 
 	if (image)
@@ -1110,7 +1354,7 @@ static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog)
 		return false;
 	if (!bpf_jit_harden)
 		return false;
-	if (bpf_jit_harden == 1 && bpf_capable())
+	if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF))
 		return false;
 
 	return true;
@@ -1131,17 +1375,18 @@ static inline bool bpf_jit_kallsyms_enabled(void)
 	return false;
 }
 
-const char *__bpf_address_lookup(unsigned long addr, unsigned long *size,
+int __bpf_address_lookup(unsigned long addr, unsigned long *size,
 				 unsigned long *off, char *sym);
 bool is_bpf_text_address(unsigned long addr);
 int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 		    char *sym);
+struct bpf_prog *bpf_prog_ksym_find(unsigned long addr);
 
-static inline const char *
+static inline int
 bpf_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym)
 {
-	const char *ret = __bpf_address_lookup(addr, size, off, sym);
+	int ret = __bpf_address_lookup(addr, size, off, sym);
 
 	if (ret && modname)
 		*modname = NULL;
@@ -1185,11 +1430,11 @@ static inline bool bpf_jit_kallsyms_enabled(void)
 	return false;
 }
 
-static inline const char *
+static inline int
 __bpf_address_lookup(unsigned long addr, unsigned long *size,
 		     unsigned long *off, char *sym)
 {
-	return NULL;
+	return 0;
 }
 
 static inline bool is_bpf_text_address(unsigned long addr)
@@ -1203,11 +1448,16 @@ static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value,
 	return -ERANGE;
 }
 
-static inline const char *
+static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr)
+{
+	return NULL;
+}
+
+static inline int
 bpf_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym)
 {
-	return NULL;
+	return 0;
 }
 
 static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp)
@@ -1287,13 +1537,14 @@ static inline int bpf_tell_extensions(void)
 
 struct bpf_sock_addr_kern {
 	struct sock *sk;
-	struct sockaddr *uaddr;
+	struct sockaddr_unsized *uaddr;
 	/* Temporary "register" to make indirect stores to nested structures
 	 * defined above. We need three registers to make such a store, but
 	 * only two (src and dst) are available at convert_ctx_access time
 	 */
 	u64 tmp_reg;
 	void *t_ctx;	/* Attach type specific context. */
+	u32 uaddrlen;
 };
 
 struct bpf_sock_ops_kern {
@@ -1308,6 +1559,7 @@ struct bpf_sock_ops_kern {
 	void	*skb_data_end;
 	u8	op;
 	u8	is_fullsock;
+	u8	is_locked_tcp_sock;
 	u8	remaining_opt_len;
 	u64	temp;			/* temp and everything after is not
 					 * initialized to 0 before calling
@@ -1322,7 +1574,7 @@ struct bpf_sock_ops_kern {
 
 struct bpf_sysctl_kern {
 	struct ctl_table_header *head;
-	struct ctl_table *table;
+	const struct ctl_table *table;
 	void *cur_val;
 	size_t cur_len;
 	void *new_val;
@@ -1428,7 +1680,7 @@ extern struct static_key_false bpf_sk_lookup_enabled;
 		_all_pass || _selected_sk ? SK_PASS : SK_DROP;		\
 	 })
 
-static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
+static inline bool bpf_sk_lookup_run_v4(const struct net *net, int protocol,
 					const __be32 saddr, const __be16 sport,
 					const __be32 daddr, const u16 dport,
 					const int ifindex, struct sock **psk)
@@ -1465,7 +1717,7 @@ static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol,
 }
 
 #if IS_ENABLED(CONFIG_IPV6)
-static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol,
+static inline bool bpf_sk_lookup_run_v6(const struct net *net, int protocol,
 					const struct in6_addr *saddr,
 					const __be16 sport,
 					const struct in6_addr *daddr,
@@ -1508,7 +1760,7 @@ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 inde
 						   u64 flags, const u64 flag_mask,
 						   void *lookup_elem(struct bpf_map *map, u32 key))
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX;
 
 	/* Lower bits of the flags are used as return code on lookup failure */
@@ -1551,6 +1803,9 @@ int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len);
 void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len);
 void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off,
 		      void *buf, unsigned long len, bool flush);
+int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset,
+			       const void *from, u32 len, u64 flags);
+void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset);
 #else /* CONFIG_NET */
 static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset,
 				       void *to, u32 len)
@@ -1581,10 +1836,21 @@ static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len)
 	return NULL;
 }
 
-static inline void *bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf,
-				     unsigned long len, bool flush)
+static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf,
+				    unsigned long len, bool flush)
 {
-	return NULL;
+}
+
+static inline int __bpf_skb_meta_store_bytes(struct sk_buff *skb, u32 offset,
+					     const void *from, u32 len,
+					     u64 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void *bpf_skb_meta_pointer(struct sk_buff *skb, u32 offset)
+{
+	return ERR_PTR(-EOPNOTSUPP);
 }
 #endif /* CONFIG_NET */
 
diff --git a/include/linux/find.h b/include/linux/find.h
index 5e4f39ef2e72..9d720ad92bc1 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -29,6 +29,10 @@ unsigned long __find_nth_and_andnot_bit(const unsigned long *addr1, const unsign
 					unsigned long n);
 extern unsigned long _find_first_and_bit(const unsigned long *addr1,
 					 const unsigned long *addr2, unsigned long size);
+unsigned long _find_first_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
+				 unsigned long size);
+unsigned long _find_first_and_and_bit(const unsigned long *addr1, const unsigned long *addr2,
+				      const unsigned long *addr3, unsigned long size);
 extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size);
 extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size);
 
@@ -40,6 +44,8 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
 				long size, unsigned long offset);
 #endif
 
+unsigned long find_random_bit(const unsigned long *addr, unsigned long size);
+
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
@@ -50,7 +56,7 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
 			    unsigned long offset)
 {
@@ -79,7 +85,7 @@ unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_and_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -110,7 +116,7 @@ unsigned long find_next_and_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_andnot_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -140,7 +146,7 @@ unsigned long find_next_andnot_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_or_bit(const unsigned long *addr1,
 		const unsigned long *addr2, unsigned long size,
 		unsigned long offset)
@@ -169,7 +175,7 @@ unsigned long find_next_or_bit(const unsigned long *addr1,
  * Returns the bit number of the next zero bit
  * If no bits are zero, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
 				 unsigned long offset)
 {
@@ -196,7 +202,7 @@ unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
  * Returns the bit number of the first set bit.
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -220,9 +226,9 @@ unsigned long find_first_bit(const unsigned long *addr, unsigned long size)
  *	 idx = find_first_bit(addr, size);
  *
  * Returns the bit number of the N'th set bit.
- * If no such, returns @size.
+ * If no such, returns >= @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsigned long n)
 {
 	if (n >= size)
@@ -247,7 +253,7 @@ unsigned long find_nth_bit(const unsigned long *addr, unsigned long size, unsign
  * Returns the bit number of the N'th set bit.
  * If no such, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *addr2,
 				unsigned long size, unsigned long n)
 {
@@ -264,33 +270,6 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *
 }
 
 /**
- * find_nth_andnot_bit - find N'th set bit in 2 memory regions,
- *			 flipping bits in 2nd region
- * @addr1: The 1st address to start the search at
- * @addr2: The 2nd address to start the search at
- * @size: The maximum number of bits to search
- * @n: The number of set bit, which position is needed, counting from 0
- *
- * Returns the bit number of the N'th set bit.
- * If no such, returns @size.
- */
-static inline
-unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
-				unsigned long size, unsigned long n)
-{
-	if (n >= size)
-		return size;
-
-	if (small_const_nbits(size)) {
-		unsigned long val =  *addr1 & (~*addr2) & GENMASK(size - 1, 0);
-
-		return val ? fns(val, n) : size;
-	}
-
-	return __find_nth_andnot_bit(addr1, addr2, size, n);
-}
-
-/**
  * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions,
  *			     excluding those set in 3rd region
  * @addr1: The 1st address to start the search at
@@ -330,7 +309,7 @@ unsigned long find_nth_and_andnot_bit(const unsigned long *addr1,
  * Returns the bit number for the next set bit
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_and_bit(const unsigned long *addr1,
 				 const unsigned long *addr2,
 				 unsigned long size)
@@ -345,6 +324,54 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
 }
 #endif
 
+/**
+ * find_first_andnot_bit - find the first bit set in 1st memory region and unset in 2nd
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the first set bit
+ * If no bits are set, returns >= @size.
+ */
+static __always_inline
+unsigned long find_first_andnot_bit(const unsigned long *addr1,
+				 const unsigned long *addr2,
+				 unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr1 & (~*addr2) & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_andnot_bit(addr1, addr2, size);
+}
+
+/**
+ * find_first_and_and_bit - find the first set bit in 3 memory regions
+ * @addr1: The first address to base the search on
+ * @addr2: The second address to base the search on
+ * @addr3: The third address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns the bit number for the first set bit
+ * If no bits are set, returns @size.
+ */
+static __always_inline
+unsigned long find_first_and_and_bit(const unsigned long *addr1,
+				     const unsigned long *addr2,
+				     const unsigned long *addr3,
+				     unsigned long size)
+{
+	if (small_const_nbits(size)) {
+		unsigned long val = *addr1 & *addr2 & *addr3 & GENMASK(size - 1, 0);
+
+		return val ? __ffs(val) : size;
+	}
+
+	return _find_first_and_and_bit(addr1, addr2, addr3, size);
+}
+
 #ifndef find_first_zero_bit
 /**
  * find_first_zero_bit - find the first cleared bit in a memory region
@@ -354,7 +381,7 @@ unsigned long find_first_and_bit(const unsigned long *addr1,
  * Returns the bit number of the first cleared bit.
  * If no bits are zero, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -375,7 +402,7 @@ unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size)
  *
  * Returns the bit number of the last set bit, or size.
  */
-static inline
+static __always_inline
 unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -398,14 +425,14 @@ unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
  * Returns the bit number for the next set bit, or first set bit up to @offset
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
 					const unsigned long *addr2,
 					unsigned long size, unsigned long offset)
 {
 	unsigned long bit = find_next_and_bit(addr1, addr2, size, offset);
 
-	if (bit < size)
+	if (bit < size || offset == 0)
 		return bit;
 
 	bit = find_first_and_bit(addr1, addr2, offset);
@@ -413,21 +440,21 @@ unsigned long find_next_and_bit_wrap(const unsigned long *addr1,
 }
 
 /**
- * find_next_bit_wrap - find the next set bit in both memory regions
- * @addr: The first address to base the search on
+ * find_next_bit_wrap - find the next set bit in a memory region
+ * @addr: The address to base the search on
  * @size: The bitmap size in bits
  * @offset: The bitnumber to start searching at
  *
  * Returns the bit number for the next set bit, or first set bit up to @offset
  * If no bits are set, returns @size.
  */
-static inline
+static __always_inline
 unsigned long find_next_bit_wrap(const unsigned long *addr,
 					unsigned long size, unsigned long offset)
 {
 	unsigned long bit = find_next_bit(addr, size, offset);
 
-	if (bit < size)
+	if (bit < size || offset == 0)
 		return bit;
 
 	bit = find_first_bit(addr, offset);
@@ -438,7 +465,7 @@ unsigned long find_next_bit_wrap(const unsigned long *addr,
  * Helper for for_each_set_bit_wrap(). Make sure you're doing right thing
  * before using it alone.
  */
-static inline
+static __always_inline
 unsigned long __for_each_wrap(const unsigned long *bitmap, unsigned long size,
 				 unsigned long start, unsigned long n)
 {
@@ -479,20 +506,20 @@ extern unsigned long find_next_clump8(unsigned long *clump,
 
 #if defined(__LITTLE_ENDIAN)
 
-static inline unsigned long find_next_zero_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
+static __always_inline
+unsigned long find_next_zero_bit_le(const void *addr, unsigned long size, unsigned long offset)
 {
 	return find_next_zero_bit(addr, size, offset);
 }
 
-static inline unsigned long find_next_bit_le(const void *addr,
-		unsigned long size, unsigned long offset)
+static __always_inline
+unsigned long find_next_bit_le(const void *addr, unsigned long size, unsigned long offset)
 {
 	return find_next_bit(addr, size, offset);
 }
 
-static inline unsigned long find_first_zero_bit_le(const void *addr,
-		unsigned long size)
+static __always_inline
+unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 {
 	return find_first_zero_bit(addr, size);
 }
@@ -500,7 +527,7 @@ static inline unsigned long find_first_zero_bit_le(const void *addr,
 #elif defined(__BIG_ENDIAN)
 
 #ifndef find_next_zero_bit_le
-static inline
+static __always_inline
 unsigned long find_next_zero_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
@@ -519,7 +546,7 @@ unsigned long find_next_zero_bit_le(const void *addr, unsigned
 #endif
 
 #ifndef find_first_zero_bit_le
-static inline
+static __always_inline
 unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 {
 	if (small_const_nbits(size)) {
@@ -533,7 +560,7 @@ unsigned long find_first_zero_bit_le(const void *addr, unsigned long size)
 #endif
 
 #ifndef find_next_bit_le
-static inline
+static __always_inline
 unsigned long find_next_bit_le(const void *addr, unsigned
 		long size, unsigned long offset)
 {
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index 1716c01c4e54..6143b7d28eac 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -75,7 +75,7 @@ void fw_csr_iterator_init(struct fw_csr_iterator *ci, const u32 *p);
 int fw_csr_iterator_next(struct fw_csr_iterator *ci, int *key, int *value);
 int fw_csr_string(const u32 *directory, int key, char *buf, size_t size);
 
-extern struct bus_type fw_bus_type;
+extern const struct bus_type fw_bus_type;
 
 struct fw_card_driver;
 struct fw_node;
@@ -88,23 +88,30 @@ struct fw_card {
 
 	int node_id;
 	int generation;
-	int current_tlabel;
-	u64 tlabel_mask;
-	struct list_head transaction_list;
 	u64 reset_jiffies;
 
-	u32 split_timeout_hi;
-	u32 split_timeout_lo;
-	unsigned int split_timeout_cycles;
-	unsigned int split_timeout_jiffies;
+	struct {
+		int current_tlabel;
+		u64 tlabel_mask;
+		struct list_head list;
+		spinlock_t lock;
+	} transactions;
+
+	struct {
+		u32 hi;
+		u32 lo;
+		unsigned int cycles;
+		unsigned int jiffies;
+		spinlock_t lock;
+	} split_timeout;
 
 	unsigned long long guid;
 	unsigned max_receive;
 	int link_speed;
 	int config_rom_generation;
 
-	spinlock_t lock; /* Take this lock when handling the lists in
-			  * this struct. */
+	spinlock_t lock;
+
 	struct fw_node *local_node;
 	struct fw_node *root_node;
 	struct fw_node *irm_node;
@@ -115,8 +122,6 @@ struct fw_card {
 	int index;
 	struct list_head link;
 
-	struct list_head phy_receiver_list;
-
 	struct delayed_work br_work; /* bus reset job */
 	bool br_short;
 
@@ -131,9 +136,16 @@ struct fw_card {
 
 	bool broadcast_channel_allocated;
 	u32 broadcast_channel;
-	__be32 topology_map[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4];
+
+	struct {
+		__be32 buffer[(CSR_TOPOLOGY_MAP_END - CSR_TOPOLOGY_MAP) / 4];
+		spinlock_t lock;
+	} topology_map;
 
 	__be32 maint_utility_register;
+
+	struct workqueue_struct *isoc_wq;
+	struct workqueue_struct *async_wq;
 };
 
 static inline struct fw_card *fw_card_get(struct fw_card *card)
@@ -158,6 +170,20 @@ struct fw_attribute_group {
 	struct attribute *attrs[13];
 };
 
+enum fw_device_quirk {
+	// See afa1282a35d3 ("firewire: core: check for 1394a compliant IRM, fix inaccessibility of Sony camcorder").
+	FW_DEVICE_QUIRK_IRM_IS_1394_1995_ONLY = BIT(0),
+
+	// See a509e43ff338 ("firewire: core: fix unstable I/O with Canon camcorder").
+	FW_DEVICE_QUIRK_IRM_IGNORES_BUS_MANAGER = BIT(1),
+
+	// MOTU Audio Express transfers acknowledge packet with 0x10 for pending state.
+	FW_DEVICE_QUIRK_ACK_PACKET_WITH_INVALID_PENDING_CODE = BIT(2),
+
+	// TASCAM FW-1082/FW-1804/FW-1884 often freezes when receiving S400 packets.
+	FW_DEVICE_QUIRK_UNSTABLE_AT_S400 = BIT(3),
+};
+
 enum fw_device_state {
 	FW_DEVICE_INITIALIZING,
 	FW_DEVICE_RUNNING,
@@ -191,6 +217,9 @@ struct fw_device {
 	struct fw_card *card;
 	struct device device;
 
+	// A set of enum fw_device_quirk.
+	int quirks;
+
 	struct mutex client_list_mutex;
 	struct list_head client_list;
 
@@ -261,6 +290,15 @@ typedef void (*fw_packet_callback_t)(struct fw_packet *packet,
 typedef void (*fw_transaction_callback_t)(struct fw_card *card, int rcode,
 					  void *data, size_t length,
 					  void *callback_data);
+typedef void (*fw_transaction_callback_with_tstamp_t)(struct fw_card *card, int rcode,
+					u32 request_tstamp, u32 response_tstamp, void *data,
+					size_t length, void *callback_data);
+
+union fw_transaction_callback {
+	fw_transaction_callback_t without_tstamp;
+	fw_transaction_callback_with_tstamp_t with_tstamp;
+};
+
 /*
  * This callback handles an inbound request subaction.  It is called in
  * RCU read-side context, therefore must not sleep.
@@ -296,8 +334,7 @@ struct fw_packet {
 	 * For successful transmission, the status code is the ack received
 	 * from the destination.  Otherwise it is one of the juju-specific
 	 * rcodes:  RCODE_SEND_ERROR, _CANCELLED, _BUSY, _GENERATION, _NO_ACK.
-	 * The callback can be called from tasklet context and thus
-	 * must never block.
+	 * The callback can be called from workqueue and thus must never block.
 	 */
 	fw_packet_callback_t callback;
 	int ack;
@@ -312,6 +349,7 @@ struct fw_transaction {
 	struct fw_card *card;
 	bool is_split_transaction;
 	struct timer_list split_timeout_timer;
+	u32 split_timeout_cycle;
 
 	struct fw_packet packet;
 
@@ -319,7 +357,8 @@ struct fw_transaction {
 	 * The data passed to the callback is valid only during the
 	 * callback.
 	 */
-	fw_transaction_callback_t callback;
+	union fw_transaction_callback callback;
+	bool with_tstamp;
 	void *callback_data;
 };
 
@@ -328,7 +367,11 @@ struct fw_address_handler {
 	u64 length;
 	fw_address_callback_t address_callback;
 	void *callback_data;
+
+	// Only for core functions.
 	struct list_head link;
+	struct kref kref;
+	struct completion done;
 };
 
 struct fw_address_region {
@@ -345,10 +388,79 @@ void fw_send_response(struct fw_card *card,
 		      struct fw_request *request, int rcode);
 int fw_get_request_speed(struct fw_request *request);
 u32 fw_request_get_timestamp(const struct fw_request *request);
-void fw_send_request(struct fw_card *card, struct fw_transaction *t,
-		     int tcode, int destination_id, int generation, int speed,
-		     unsigned long long offset, void *payload, size_t length,
-		     fw_transaction_callback_t callback, void *callback_data);
+
+void __fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode,
+		int destination_id, int generation, int speed, unsigned long long offset,
+		void *payload, size_t length, union fw_transaction_callback callback,
+		bool with_tstamp, void *callback_data);
+
+/**
+ * fw_send_request() - submit a request packet for transmission to generate callback for response
+ *		       subaction without time stamp.
+ * @card:		interface to send the request at
+ * @t:			transaction instance to which the request belongs
+ * @tcode:		transaction code
+ * @destination_id:	destination node ID, consisting of bus_ID and phy_ID
+ * @generation:		bus generation in which request and response are valid
+ * @speed:		transmission speed
+ * @offset:		48bit wide offset into destination's address space
+ * @payload:		data payload for the request subaction
+ * @length:		length of the payload, in bytes
+ * @callback:		function to be called when the transaction is completed
+ * @callback_data:	data to be passed to the transaction completion callback
+ *
+ * A variation of __fw_send_request() to generate callback for response subaction without time
+ * stamp.
+ *
+ * The callback is invoked in the workqueue context in most cases. However, if an error is detected
+ * before queueing or the destination address refers to the local node, it is invoked in the
+ * current context instead.
+ */
+static inline void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode,
+				   int destination_id, int generation, int speed,
+				   unsigned long long offset, void *payload, size_t length,
+				   fw_transaction_callback_t callback, void *callback_data)
+{
+	union fw_transaction_callback cb = {
+		.without_tstamp = callback,
+	};
+	__fw_send_request(card, t, tcode, destination_id, generation, speed, offset, payload,
+			  length, cb, false, callback_data);
+}
+
+/**
+ * fw_send_request_with_tstamp() - submit a request packet for transmission to generate callback for
+ *				   response with time stamp.
+ * @card:		interface to send the request at
+ * @t:			transaction instance to which the request belongs
+ * @tcode:		transaction code
+ * @destination_id:	destination node ID, consisting of bus_ID and phy_ID
+ * @generation:		bus generation in which request and response are valid
+ * @speed:		transmission speed
+ * @offset:		48bit wide offset into destination's address space
+ * @payload:		data payload for the request subaction
+ * @length:		length of the payload, in bytes
+ * @callback:		function to be called when the transaction is completed
+ * @callback_data:	data to be passed to the transaction completion callback
+ *
+ * A variation of __fw_send_request() to generate callback for response subaction with time stamp.
+ *
+ * The callback is invoked in the workqueue context in most cases. However, if an error is detected
+ * before queueing or the destination address refers to the local node, it is invoked in the current
+ * context instead.
+ */
+static inline void fw_send_request_with_tstamp(struct fw_card *card, struct fw_transaction *t,
+	int tcode, int destination_id, int generation, int speed, unsigned long long offset,
+	void *payload, size_t length, fw_transaction_callback_with_tstamp_t callback,
+	void *callback_data)
+{
+	union fw_transaction_callback cb = {
+		.with_tstamp = callback,
+	};
+	__fw_send_request(card, t, tcode, destination_id, generation, speed, offset, payload,
+			  length, cb, true, callback_data);
+}
+
 int fw_cancel_transaction(struct fw_card *card,
 			  struct fw_transaction *transaction);
 int fw_run_transaction(struct fw_card *card, int tcode, int destination_id,
@@ -390,8 +502,8 @@ struct fw_iso_packet {
 				/* rx: Sync bit, wait for matching sy	*/
 	u32 tag:2;		/* tx: Tag in packet header		*/
 	u32 sy:4;		/* tx: Sy in packet header		*/
-	u32 header_length:8;	/* Length of immediate header		*/
-	u32 header[0];		/* tx: Top of 1394 isoch. data_block	*/
+	u32 header_length:8;	/* Size of immediate header		*/
+	u32 header[];		/* tx: Top of 1394 isoch. data_block	*/
 };
 
 #define FW_ISO_CONTEXT_TRANSMIT			0
@@ -437,6 +549,7 @@ union fw_iso_callback {
 
 struct fw_iso_context {
 	struct fw_card *card;
+	struct work_struct work;
 	int type;
 	int channel;
 	int speed;
@@ -456,6 +569,25 @@ int fw_iso_context_queue(struct fw_iso_context *ctx,
 			 unsigned long payload);
 void fw_iso_context_queue_flush(struct fw_iso_context *ctx);
 int fw_iso_context_flush_completions(struct fw_iso_context *ctx);
+
+/**
+ * fw_iso_context_schedule_flush_completions() - schedule work item to process isochronous context.
+ * @ctx: the isochronous context
+ *
+ * Schedule a work item on workqueue to process the isochronous context. The registered callback
+ * function is called by the worker when a queued packet buffer with the interrupt flag is
+ * completed, either after transmission in the IT context or after being filled in the IR context.
+ * The callback function is also called when the header buffer in the context becomes full, If it
+ * is required to process the context in the current context, fw_iso_context_flush_completions() is
+ * available instead.
+ *
+ * Context: Any context.
+ */
+static inline void fw_iso_context_schedule_flush_completions(struct fw_iso_context *ctx)
+{
+	queue_work(ctx->card->isoc_wq, &ctx->work);
+}
+
 int fw_iso_context_start(struct fw_iso_context *ctx,
 			 int cycle, int sync, int tags);
 int fw_iso_context_stop(struct fw_iso_context *ctx);
diff --git a/include/linux/firmware.h b/include/linux/firmware.h
index de7fea3bca51..aae1b85ffc10 100644
--- a/include/linux/firmware.h
+++ b/include/linux/firmware.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/cleanup.h>
 #include <linux/gfp.h>
 
 #define FW_ACTION_NOUEVENT 0
@@ -27,6 +28,7 @@ struct firmware {
  * @FW_UPLOAD_ERR_INVALID_SIZE: invalid firmware image size
  * @FW_UPLOAD_ERR_RW_ERROR: read or write to HW failed, see kernel log
  * @FW_UPLOAD_ERR_WEAROUT: FLASH device is approaching wear-out, wait & retry
+ * @FW_UPLOAD_ERR_FW_INVALID: invalid firmware file
  * @FW_UPLOAD_ERR_MAX: Maximum error code marker
  */
 enum fw_upload_err {
@@ -38,6 +40,7 @@ enum fw_upload_err {
 	FW_UPLOAD_ERR_INVALID_SIZE,
 	FW_UPLOAD_ERR_RW_ERROR,
 	FW_UPLOAD_ERR_WEAROUT,
+	FW_UPLOAD_ERR_FW_INVALID,
 	FW_UPLOAD_ERR_MAX
 };
 
@@ -95,6 +98,10 @@ static inline bool firmware_request_builtin(struct firmware *fw,
 #if IS_REACHABLE(CONFIG_FW_LOADER)
 int request_firmware(const struct firmware **fw, const char *name,
 		     struct device *device);
+int firmware_request_nowait_nowarn(
+	struct module *module, const char *name,
+	struct device *device, gfp_t gfp, void *context,
+	void (*cont)(const struct firmware *fw, void *context));
 int firmware_request_nowarn(const struct firmware **fw, const char *name,
 			    struct device *device);
 int firmware_request_platform(const struct firmware **fw, const char *name,
@@ -120,6 +127,14 @@ static inline int request_firmware(const struct firmware **fw,
 	return -EINVAL;
 }
 
+static inline int firmware_request_nowait_nowarn(
+	struct module *module, const char *name,
+	struct device *device, gfp_t gfp, void *context,
+	void (*cont)(const struct firmware *fw, void *context))
+{
+	return -EINVAL;
+}
+
 static inline int firmware_request_nowarn(const struct firmware **fw,
 					  const char *name,
 					  struct device *device)
@@ -196,4 +211,6 @@ static inline void firmware_upload_unregister(struct fw_upload *fw_upload)
 
 int firmware_request_cache(struct device *device, const char *name);
 
+DEFINE_FREE(firmware, struct firmware *, release_firmware(_T))
+
 #endif
diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h
index 29cd11d5a3cf..0ec1cdc5585d 100644
--- a/include/linux/firmware/cirrus/cs_dsp.h
+++ b/include/linux/firmware/cirrus/cs_dsp.h
@@ -42,6 +42,16 @@
 #define CS_DSP_ACKED_CTL_MIN_VALUE           0
 #define CS_DSP_ACKED_CTL_MAX_VALUE           0xFFFFFF
 
+/*
+ * Write sequence operation codes
+ */
+#define CS_DSP_WSEQ_FULL	0x00
+#define CS_DSP_WSEQ_ADDR8	0x02
+#define CS_DSP_WSEQ_L16		0x04
+#define CS_DSP_WSEQ_H16		0x05
+#define CS_DSP_WSEQ_UNLOCK	0xFD
+#define CS_DSP_WSEQ_END		0xFF
+
 /**
  * struct cs_dsp_region - Describes a logical memory region in DSP address space
  * @type:	Memory region type
@@ -54,14 +64,12 @@ struct cs_dsp_region {
 
 /**
  * struct cs_dsp_alg_region - Describes a logical algorithm region in DSP address space
- * @list:	List node for internal use
  * @alg:	Algorithm id
  * @ver:	Expected algorithm version
  * @type:	Memory region type
  * @base:	Address of region
  */
 struct cs_dsp_alg_region {
-	struct list_head list;
 	unsigned int alg;
 	unsigned int ver;
 	int type;
@@ -94,7 +102,7 @@ struct cs_dsp_coeff_ctl {
 	const char *subname;
 	unsigned int subname_len;
 	unsigned int offset;
-	size_t len;
+	unsigned int len;
 	unsigned int type;
 	unsigned int flags;
 	unsigned int set:1;
@@ -123,7 +131,6 @@ struct cs_dsp_client_ops;
  * @sysclk_mask:	Mask of frequency bits within sysclk register (ADSP1 only)
  * @sysclk_shift:	Shift of frequency bits within sysclk register (ADSP1 only)
  * @alg_regions:	List of currently loaded algorithm regions
- * @fw_file_name:	Filename of the current firmware
  * @fw_name:		Name of the current firmware
  * @fw_id:		ID of the current firmware, obtained from the wmfw
  * @fw_id_version:	Version of the firmware, obtained from the wmfw
@@ -168,7 +175,7 @@ struct cs_dsp {
 	const struct cs_dsp_region *mem;
 	int num_mems;
 
-	int fw_ver;
+	int wmfw_ver;
 
 	bool booted;
 	bool running;
@@ -181,8 +188,8 @@ struct cs_dsp {
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_root;
-	char *wmfw_file_name;
-	char *bin_file_name;
+	const char *wmfw_file_name;
+	const char *bin_file_name;
 #endif
 };
 
@@ -214,13 +221,13 @@ int cs_dsp_adsp2_init(struct cs_dsp *dsp);
 int cs_dsp_halo_init(struct cs_dsp *dsp);
 
 int cs_dsp_adsp1_power_up(struct cs_dsp *dsp,
-			  const struct firmware *wmfw_firmware, char *wmfw_filename,
-			  const struct firmware *coeff_firmware, char *coeff_filename,
+			  const struct firmware *wmfw_firmware, const char *wmfw_filename,
+			  const struct firmware *coeff_firmware, const char *coeff_filename,
 			  const char *fw_name);
 void cs_dsp_adsp1_power_down(struct cs_dsp *dsp);
 int cs_dsp_power_up(struct cs_dsp *dsp,
-		    const struct firmware *wmfw_firmware, char *wmfw_filename,
-		    const struct firmware *coeff_firmware, char *coeff_filename,
+		    const struct firmware *wmfw_firmware, const char *wmfw_filename,
+		    const struct firmware *coeff_firmware, const char *coeff_filename,
 		    const char *fw_name);
 void cs_dsp_power_down(struct cs_dsp *dsp);
 int cs_dsp_run(struct cs_dsp *dsp);
@@ -239,8 +246,12 @@ void cs_dsp_cleanup_debugfs(struct cs_dsp *dsp);
 int cs_dsp_coeff_write_acked_control(struct cs_dsp_coeff_ctl *ctl, unsigned int event_id);
 int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off,
 			    const void *buf, size_t len);
+int cs_dsp_coeff_lock_and_write_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off,
+				     const void *buf, size_t len);
 int cs_dsp_coeff_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off,
 			   void *buf, size_t len);
+int cs_dsp_coeff_lock_and_read_ctrl(struct cs_dsp_coeff_ctl *ctl, unsigned int off,
+				    void *buf, size_t len);
 struct cs_dsp_coeff_ctl *cs_dsp_get_ctl(struct cs_dsp *dsp, const char *name, int type,
 					unsigned int alg);
 
@@ -256,6 +267,23 @@ struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp,
 const char *cs_dsp_mem_region_name(unsigned int type);
 
 /**
+ * struct cs_dsp_wseq - Describes a write sequence
+ * @ctl:	Write sequence cs_dsp control
+ * @ops:	Operations contained within
+ */
+struct cs_dsp_wseq {
+	struct cs_dsp_coeff_ctl *ctl;
+	struct list_head ops;
+};
+
+int cs_dsp_wseq_init(struct cs_dsp *dsp, struct cs_dsp_wseq *wseqs, unsigned int num_wseqs);
+int cs_dsp_wseq_write(struct cs_dsp *dsp, struct cs_dsp_wseq *wseq, u32 addr, u32 data,
+		      u8 op_code, bool update);
+int cs_dsp_wseq_multi_write(struct cs_dsp *dsp, struct cs_dsp_wseq *wseq,
+			    const struct reg_sequence *reg_seq, int num_regs,
+			    u8 op_code, bool update);
+
+/**
  * struct cs_dsp_chunk - Describes a buffer holding data formatted for the DSP
  * @data:	Pointer to underlying buffer memory
  * @max:	Pointer to end of the buffer memory
diff --git a/include/linux/firmware/cirrus/cs_dsp_test_utils.h b/include/linux/firmware/cirrus/cs_dsp_test_utils.h
new file mode 100644
index 000000000000..1f97764fdfd7
--- /dev/null
+++ b/include/linux/firmware/cirrus/cs_dsp_test_utils.h
@@ -0,0 +1,159 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Support utilities for cs_dsp testing.
+ *
+ * Copyright (C) 2024 Cirrus Logic, Inc. and
+ *                    Cirrus Logic International Semiconductor Ltd.
+ */
+
+#include <linux/regmap.h>
+#include <linux/firmware/cirrus/wmfw.h>
+
+struct kunit;
+struct cs_dsp_test;
+struct cs_dsp_test_local;
+
+/**
+ * struct cs_dsp_test - base class for test utilities
+ *
+ * @test:	Pointer to struct kunit instance.
+ * @dsp:	Pointer to struct cs_dsp instance.
+ * @local:	Private data for each test suite.
+ */
+struct cs_dsp_test {
+	struct kunit *test;
+	struct cs_dsp *dsp;
+
+	struct cs_dsp_test_local *local;
+
+	/* private: Following members are private */
+	bool saw_bus_write;
+};
+
+/**
+ * struct cs_dsp_mock_alg_def - Info for creating a mock algorithm entry.
+ *
+ * @id:		   Algorithm ID.
+ * @ver:	   Algorithm version.
+ * @xm_base_words: XM base address in DSP words.
+ * @xm_size_words: XM size in DSP words.
+ * @ym_base_words: YM base address in DSP words.
+ * @ym_size_words: YM size in DSP words.
+ * @zm_base_words: ZM base address in DSP words.
+ * @zm_size_words: ZM size in DSP words.
+ */
+struct cs_dsp_mock_alg_def {
+	unsigned int id;
+	unsigned int ver;
+	unsigned int xm_base_words;
+	unsigned int xm_size_words;
+	unsigned int ym_base_words;
+	unsigned int ym_size_words;
+	unsigned int zm_base_words;
+	unsigned int zm_size_words;
+};
+
+struct cs_dsp_mock_coeff_def {
+	const char *shortname;
+	const char *fullname;
+	const char *description;
+	u16 type;
+	u16 flags;
+	u16 mem_type;
+	unsigned int offset_dsp_words;
+	unsigned int length_bytes;
+};
+
+/**
+ * struct cs_dsp_mock_xm_header - XM header builder
+ *
+ * @test_priv:	     Pointer to the struct cs_dsp_test.
+ * @blob_data:	     Pointer to the created blob data.
+ * @blob_size_bytes: Size of the data at blob_data.
+ */
+struct cs_dsp_mock_xm_header {
+	struct cs_dsp_test *test_priv;
+	void *blob_data;
+	size_t blob_size_bytes;
+};
+
+struct cs_dsp_mock_wmfw_builder;
+struct cs_dsp_mock_bin_builder;
+
+extern const unsigned int cs_dsp_mock_adsp2_32bit_sysbase;
+extern const unsigned int cs_dsp_mock_adsp2_16bit_sysbase;
+extern const unsigned int cs_dsp_mock_halo_core_base;
+extern const unsigned int cs_dsp_mock_halo_sysinfo_base;
+
+extern const struct cs_dsp_region cs_dsp_mock_halo_dsp1_regions[];
+extern const unsigned int cs_dsp_mock_halo_dsp1_region_sizes[];
+extern const struct cs_dsp_region cs_dsp_mock_adsp2_32bit_dsp1_regions[];
+extern const unsigned int cs_dsp_mock_adsp2_32bit_dsp1_region_sizes[];
+extern const struct cs_dsp_region cs_dsp_mock_adsp2_16bit_dsp1_regions[];
+extern const unsigned int cs_dsp_mock_adsp2_16bit_dsp1_region_sizes[];
+int cs_dsp_mock_count_regions(const unsigned int *region_sizes);
+unsigned int cs_dsp_mock_size_of_region(const struct cs_dsp *dsp, int mem_type);
+unsigned int cs_dsp_mock_base_addr_for_mem(struct cs_dsp_test *priv, int mem_type);
+unsigned int cs_dsp_mock_reg_addr_inc_per_unpacked_word(struct cs_dsp_test *priv);
+unsigned int cs_dsp_mock_reg_block_length_bytes(struct cs_dsp_test *priv, int mem_type);
+unsigned int cs_dsp_mock_reg_block_length_registers(struct cs_dsp_test *priv, int mem_type);
+unsigned int cs_dsp_mock_reg_block_length_dsp_words(struct cs_dsp_test *priv, int mem_type);
+bool cs_dsp_mock_has_zm(struct cs_dsp_test *priv);
+int cs_dsp_mock_packed_to_unpacked_mem_type(int packed_mem_type);
+unsigned int cs_dsp_mock_num_dsp_words_to_num_packed_regs(unsigned int num_dsp_words);
+unsigned int cs_dsp_mock_xm_header_get_alg_base_in_words(struct cs_dsp_test *priv,
+							 unsigned int alg_id,
+							 int mem_type);
+unsigned int cs_dsp_mock_xm_header_get_fw_version(struct cs_dsp_mock_xm_header *header);
+void cs_dsp_mock_xm_header_drop_from_regmap_cache(struct cs_dsp_test *priv);
+int cs_dsp_mock_xm_header_write_to_regmap(struct cs_dsp_mock_xm_header *header);
+struct cs_dsp_mock_xm_header *cs_dsp_create_mock_xm_header(struct cs_dsp_test *priv,
+							   const struct cs_dsp_mock_alg_def *algs,
+							   size_t num_algs);
+
+int cs_dsp_mock_regmap_init(struct cs_dsp_test *priv);
+void cs_dsp_mock_regmap_drop_range(struct cs_dsp_test *priv,
+				   unsigned int first_reg, unsigned int last_reg);
+void cs_dsp_mock_regmap_drop_regs(struct cs_dsp_test *priv,
+				  unsigned int first_reg, size_t num_regs);
+void cs_dsp_mock_regmap_drop_bytes(struct cs_dsp_test *priv,
+				   unsigned int first_reg, size_t num_bytes);
+void cs_dsp_mock_regmap_drop_system_regs(struct cs_dsp_test *priv);
+bool cs_dsp_mock_regmap_is_dirty(struct cs_dsp_test *priv, bool drop_system_regs);
+
+struct cs_dsp_mock_bin_builder *cs_dsp_mock_bin_init(struct cs_dsp_test *priv,
+						     int format_version,
+						     unsigned int fw_version);
+void cs_dsp_mock_bin_add_raw_block(struct cs_dsp_mock_bin_builder *builder,
+				   unsigned int alg_id, unsigned int alg_ver,
+				   int type, unsigned int offset,
+				   const void *payload_data, size_t payload_len_bytes);
+void cs_dsp_mock_bin_add_info(struct cs_dsp_mock_bin_builder *builder,
+			      const char *info);
+void cs_dsp_mock_bin_add_name(struct cs_dsp_mock_bin_builder *builder,
+			      const char *name);
+void cs_dsp_mock_bin_add_patch(struct cs_dsp_mock_bin_builder *builder,
+			       unsigned int alg_id, unsigned int alg_ver,
+			       int mem_region, unsigned int reg_addr_offset,
+			       const void *payload_data, size_t payload_len_bytes);
+struct firmware *cs_dsp_mock_bin_get_firmware(struct cs_dsp_mock_bin_builder *builder);
+
+struct cs_dsp_mock_wmfw_builder *cs_dsp_mock_wmfw_init(struct cs_dsp_test *priv,
+						       int format_version);
+void cs_dsp_mock_wmfw_add_raw_block(struct cs_dsp_mock_wmfw_builder *builder,
+				    int mem_region, unsigned int mem_offset_dsp_words,
+				    const void *payload_data, size_t payload_len_bytes);
+void cs_dsp_mock_wmfw_add_info(struct cs_dsp_mock_wmfw_builder *builder,
+			       const char *info);
+void cs_dsp_mock_wmfw_add_data_block(struct cs_dsp_mock_wmfw_builder *builder,
+				     int mem_region, unsigned int mem_offset_dsp_words,
+				     const void *payload_data, size_t payload_len_bytes);
+void cs_dsp_mock_wmfw_start_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder,
+					   unsigned int alg_id,
+					   const char *name,
+					   const char *description);
+void cs_dsp_mock_wmfw_add_coeff_desc(struct cs_dsp_mock_wmfw_builder *builder,
+				     const struct cs_dsp_mock_coeff_def *def);
+void cs_dsp_mock_wmfw_end_alg_info_block(struct cs_dsp_mock_wmfw_builder *builder);
+struct firmware *cs_dsp_mock_wmfw_get_firmware(struct cs_dsp_mock_wmfw_builder *builder);
+int cs_dsp_mock_wmfw_format_version(struct cs_dsp_mock_wmfw_builder *builder);
diff --git a/include/linux/firmware/imx/dsp.h b/include/linux/firmware/imx/dsp.h
index 4f7895a3b73c..1f176a2683fe 100644
--- a/include/linux/firmware/imx/dsp.h
+++ b/include/linux/firmware/imx/dsp.h
@@ -37,17 +37,11 @@ struct imx_dsp_ipc {
 
 static inline void imx_dsp_set_data(struct imx_dsp_ipc *ipc, void *data)
 {
-	if (!ipc)
-		return;
-
 	ipc->private_data = data;
 }
 
 static inline void *imx_dsp_get_data(struct imx_dsp_ipc *ipc)
 {
-	if (!ipc)
-		return NULL;
-
 	return ipc->private_data;
 }
 
diff --git a/include/linux/firmware/imx/sci.h b/include/linux/firmware/imx/sci.h
index 5cc63fe7e84d..df17196df5ff 100644
--- a/include/linux/firmware/imx/sci.h
+++ b/include/linux/firmware/imx/sci.h
@@ -21,31 +21,37 @@ int imx_scu_enable_general_irq_channel(struct device *dev);
 int imx_scu_irq_register_notifier(struct notifier_block *nb);
 int imx_scu_irq_unregister_notifier(struct notifier_block *nb);
 int imx_scu_irq_group_enable(u8 group, u32 mask, u8 enable);
+int imx_scu_irq_get_status(u8 group, u32 *irq_status);
 int imx_scu_soc_init(struct device *dev);
 #else
 static inline int imx_scu_soc_init(struct device *dev)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int imx_scu_enable_general_irq_channel(struct device *dev)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int imx_scu_irq_register_notifier(struct notifier_block *nb)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int imx_scu_irq_unregister_notifier(struct notifier_block *nb)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
 }
 
 static inline int imx_scu_irq_group_enable(u8 group, u32 mask, u8 enable)
 {
-	return -ENOTSUPP;
+	return -EOPNOTSUPP;
+}
+
+static inline int imx_scu_irq_get_status(u8 group, u32 *irq_status)
+{
+	return -EOPNOTSUPP;
 }
 #endif
 #endif /* _SC_SCI_H */
diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h
new file mode 100644
index 000000000000..a33b45027356
--- /dev/null
+++ b/include/linux/firmware/imx/sm.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2024 NXP
+ */
+
+#ifndef _SCMI_IMX_H
+#define _SCMI_IMX_H
+
+#include <linux/bitfield.h>
+#include <linux/errno.h>
+#include <linux/scmi_imx_protocol.h>
+#include <linux/types.h>
+
+#define SCMI_IMX95_CTRL_PDM_CLK_SEL	0	/* AON PDM clock sel */
+#define SCMI_IMX95_CTRL_MQS1_SETTINGS	1	/* AON MQS settings */
+#define SCMI_IMX95_CTRL_SAI1_MCLK	2	/* AON SAI1 MCLK */
+#define SCMI_IMX95_CTRL_SAI3_MCLK	3	/* WAKE SAI3 MCLK */
+#define SCMI_IMX95_CTRL_SAI4_MCLK	4	/* WAKE SAI4 MCLK */
+#define SCMI_IMX95_CTRL_SAI5_MCLK	5	/* WAKE SAI5 MCLK */
+
+#define SCMI_IMX94_CTRL_PDM_CLK_SEL	0U	/*!< AON PDM clock sel */
+#define SCMI_IMX94_CTRL_MQS1_SETTINGS	1U	/*!< AON MQS settings */
+#define SCMI_IMX94_CTRL_MQS2_SETTINGS	2U	/*!< WAKE MQS settings */
+#define SCMI_IMX94_CTRL_SAI1_MCLK	3U	/*!< AON SAI1 MCLK */
+#define SCMI_IMX94_CTRL_SAI2_MCLK	4U	/*!< WAKE SAI2 MCLK */
+#define SCMI_IMX94_CTRL_SAI3_MCLK	5U	/*!< WAKE SAI3 MCLK */
+#define SCMI_IMX94_CTRL_SAI4_MCLK	6U	/*!< WAKE SAI4 MCLK */
+
+#if IS_ENABLED(CONFIG_IMX_SCMI_MISC_DRV)
+int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val);
+int scmi_imx_misc_ctrl_set(u32 id, u32 val);
+#else
+static inline int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int scmi_imx_misc_ctrl_set(u32 id, u32 val)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IMX_SCMI_CPU_DRV)
+int scmi_imx_cpu_start(u32 cpuid, bool start);
+int scmi_imx_cpu_started(u32 cpuid, bool *started);
+int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start, bool boot,
+				  bool resume);
+#else
+static inline int scmi_imx_cpu_start(u32 cpuid, bool start)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int scmi_imx_cpu_started(u32 cpuid, bool *started)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int scmi_imx_cpu_reset_vector_set(u32 cpuid, u64 vector, bool start,
+						bool boot, bool resume)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+enum scmi_imx_lmm_op {
+	SCMI_IMX_LMM_BOOT,
+	SCMI_IMX_LMM_POWER_ON,
+	SCMI_IMX_LMM_SHUTDOWN,
+};
+
+/* For shutdown pperation */
+#define SCMI_IMX_LMM_OP_FORCEFUL	0
+#define SCMI_IMX_LMM_OP_GRACEFUL	BIT(0)
+
+#if IS_ENABLED(CONFIG_IMX_SCMI_LMM_DRV)
+int scmi_imx_lmm_operation(u32 lmid, enum scmi_imx_lmm_op op, u32 flags);
+int scmi_imx_lmm_info(u32 lmid, struct scmi_imx_lmm_info *info);
+int scmi_imx_lmm_reset_vector_set(u32 lmid, u32 cpuid, u32 flags, u64 vector);
+#else
+static inline int scmi_imx_lmm_operation(u32 lmid, enum scmi_imx_lmm_op op, u32 flags)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int scmi_imx_lmm_info(u32 lmid, struct scmi_imx_lmm_info *info)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int scmi_imx_lmm_reset_vector_set(u32 lmid, u32 cpuid, u32 flags, u64 vector)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+#endif
diff --git a/include/linux/firmware/intel/stratix10-smc.h b/include/linux/firmware/intel/stratix10-smc.h
index a718f853d457..935dba3633b5 100644
--- a/include/linux/firmware/intel/stratix10-smc.h
+++ b/include/linux/firmware/intel/stratix10-smc.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017-2018, Intel Corporation
+ * Copyright (C) 2025, Altera Corporation
  */
 
 #ifndef __STRATIX10_SMC_H
@@ -47,6 +48,10 @@
 	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, ARM_SMCCC_SMC_64, \
 	ARM_SMCCC_OWNER_SIP, (func_num))
 
+#define INTEL_SIP_SMC_ASYNC_VAL(func_name)	\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL, ARM_SMCCC_SMC_64, \
+	ARM_SMCCC_OWNER_SIP, (func_name))
+
 /**
  * Return values in INTEL_SIP_SMC_* call
  *
@@ -467,6 +472,31 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
         INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FIRMWARE_VERSION)
 
 /**
+ * SMC call protocol for Mailbox, starting FUNCID from 60
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_MBOX_SEND_CMD
+ * a1 mailbox command code
+ * a2 physical address that contain mailbox command data (not include header)
+ * a3 mailbox command data size in word
+ * a4 set to 0 for CASUAL, set to 1 for URGENT
+ * a5 physical address for secure firmware to put response data
+ *    (not include header)
+ * a6 maximum size in word of physical address to store response data
+ * a7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK, INTEL_SIP_SMC_STATUS_REJECTED or
+ *    INTEL_SIP_SMC_STATUS_ERROR
+ * a1 mailbox error code
+ * a2 response data length in word
+ * a3 not used
+ */
+#define INTEL_SIP_SMC_FUNCID_MBOX_SEND_CMD 60
+	#define INTEL_SIP_SMC_MBOX_SEND_CMD \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_MBOX_SEND_CMD)
+
+/**
  * Request INTEL_SIP_SMC_SVC_VERSION
  *
  * Sync call used to query the SIP SMC API Version
@@ -595,4 +625,110 @@ INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FPGA_CONFIG_COMPLETED_WRITE)
 #define INTEL_SIP_SMC_FCS_GET_PROVISION_DATA \
 	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_FCS_GET_PROVISION_DATA)
 
+/**
+ * Request INTEL_SIP_SMC_HWMON_READTEMP
+ * Sync call to request temperature
+ *
+ * Call register usage:
+ * a0 Temperature Channel
+ * a1-a7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ * a1 Temperature Value
+ * a2-a3 not used
+ */
+#define INTEL_SIP_SMC_FUNCID_HWMON_READTEMP 32
+#define INTEL_SIP_SMC_HWMON_READTEMP \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_HWMON_READTEMP)
+
+/**
+ * Request INTEL_SIP_SMC_HWMON_READVOLT
+ * Sync call to request voltage
+ *
+ * Call register usage:
+ * a0 Voltage Channel
+ * a1-a7 not used
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ * a1 Voltage Value
+ * a2-a3 not used
+ */
+#define INTEL_SIP_SMC_FUNCID_HWMON_READVOLT 33
+#define INTEL_SIP_SMC_HWMON_READVOLT \
+	INTEL_SIP_SMC_FAST_CALL_VAL(INTEL_SIP_SMC_FUNCID_HWMON_READVOLT)
+
+/**
+ * Request INTEL_SIP_SMC_ASYNC_POLL
+ * Async call used by service driver at EL1 to query mailbox response from SDM.
+ *
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_ASYNC_POLL
+ * a1 transaction job id
+ * a2-17 will be used to return the response data
+ *
+ * Return status
+ * a0 INTEL_SIP_SMC_STATUS_OK
+ * a1-17 will contain the response values from mailbox for the previous send
+ * transaction
+ * Or
+ * a0 INTEL_SIP_SMC_STATUS_NO_RESPONSE
+ * a1-17 not used
+ */
+#define INTEL_SIP_SMC_ASYNC_FUNC_ID_POLL (0xC8)
+#define INTEL_SIP_SMC_ASYNC_POLL \
+	INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_POLL)
+
+/**
+ * Request INTEL_SIP_SMC_ASYNC_RSU_GET_SPT
+ * Async call to get RSU SPT from SDM.
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_ASYNC_RSU_GET_SPT
+ * a1 transaction job id
+ * a2-a17 not used
+ *
+ * Return status:
+ * a0 INTEL_SIP_SMC_STATUS_OK ,INTEL_SIP_SMC_STATUS_REJECTED
+ * or INTEL_SIP_SMC_STATUS_BUSY
+ * a1-a17 not used
+ */
+#define INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_GET_SPT (0xEA)
+#define INTEL_SIP_SMC_ASYNC_RSU_GET_SPT \
+	INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_GET_SPT)
+
+/**
+ * Request INTEL_SIP_SMC_ASYNC_RSU_GET_ERROR_STATUS
+ * Async call to get RSU error status from SDM.
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_ASYNC_RSU_GET_ERROR_STATUS
+ * a1 transaction job id
+ * a2-a17 not used
+ *
+ * Return status:
+ * a0 INTEL_SIP_SMC_STATUS_OK ,INTEL_SIP_SMC_STATUS_REJECTED
+ * or INTEL_SIP_SMC_STATUS_BUSY
+ * a1-a17 not used
+ */
+#define INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_GET_ERROR_STATUS (0xEB)
+#define INTEL_SIP_SMC_ASYNC_RSU_GET_ERROR_STATUS \
+	INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_GET_ERROR_STATUS)
+
+/**
+ * Request INTEL_SIP_SMC_ASYNC_RSU_NOTIFY
+ * Async call to send NOTIFY value to SDM.
+ * Call register usage:
+ * a0 INTEL_SIP_SMC_ASYNC_RSU_NOTIFY
+ * a1 transaction job id
+ * a2 notify value
+ * a3-a17 not used
+ *
+ * Return status:
+ * a0 INTEL_SIP_SMC_STATUS_OK ,INTEL_SIP_SMC_STATUS_REJECTED
+ * or INTEL_SIP_SMC_STATUS_BUSY
+ * a1-a17 not used
+ */
+#define INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_NOTIFY (0xEC)
+#define INTEL_SIP_SMC_ASYNC_RSU_NOTIFY \
+	INTEL_SIP_SMC_ASYNC_VAL(INTEL_SIP_SMC_ASYNC_FUNC_ID_RSU_NOTIFY)
 #endif
diff --git a/include/linux/firmware/intel/stratix10-svc-client.h b/include/linux/firmware/intel/stratix10-svc-client.h
index 0c16037fd08d..d290060f4c73 100644
--- a/include/linux/firmware/intel/stratix10-svc-client.h
+++ b/include/linux/firmware/intel/stratix10-svc-client.h
@@ -1,6 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
  * Copyright (C) 2017-2018, Intel Corporation
+ * Copyright (C) 2025, Altera Corporation
  */
 
 #ifndef __STRATIX10_SVC_CLIENT_H
@@ -11,10 +12,12 @@
  *
  * fpga: for FPGA configuration
  * rsu: for remote status update
+ * hwmon: for hardware monitoring (voltage and temperature)
  */
 #define SVC_CLIENT_FPGA			"fpga"
 #define SVC_CLIENT_RSU			"rsu"
 #define SVC_CLIENT_FCS			"fcs"
+#define SVC_CLIENT_HWMON		"hwmon"
 
 /*
  * Status of the sent command, in bit number
@@ -70,6 +73,7 @@
 #define SVC_RSU_REQUEST_TIMEOUT_MS              300
 #define SVC_FCS_REQUEST_TIMEOUT_MS		2000
 #define SVC_COMPLETED_TIMEOUT_MS		30000
+#define SVC_HWMON_REQUEST_TIMEOUT_MS		300
 
 struct stratix10_svc_chan;
 
@@ -118,9 +122,15 @@ struct stratix10_svc_chan;
  * @COMMAND_SMC_SVC_VERSION: Non-mailbox SMC SVC API Version,
  * return status is SVC_STATUS_OK
  *
+ * @COMMAND_MBOX_SEND_CMD: send generic mailbox command, return status is
+ * SVC_STATUS_OK or SVC_STATUS_ERROR
+ *
  * @COMMAND_RSU_DCMF_STATUS: query firmware for the DCMF status
  * return status is SVC_STATUS_OK or SVC_STATUS_ERROR
  *
+ * @COMMAND_RSU_GET_SPT_TABLE: query firmware for SPT table
+ * return status is SVC_STATUS_OK or SVC_STATUS_ERROR
+ *
  * @COMMAND_FCS_REQUEST_SERVICE: request validation of image from firmware,
  * return status is SVC_STATUS_OK, SVC_STATUS_INVALID_PARAM
  *
@@ -138,6 +148,12 @@ struct stratix10_svc_chan;
  *
  * @COMMAND_FCS_RANDOM_NUMBER_GEN: generate a random number, return status
  * is SVC_STATUS_OK, SVC_STATUS_ERROR
+ *
+ * @COMMAND_HWMON_READTEMP: query the temperature from the hardware monitor,
+ * return status is SVC_STATUS_OK or SVC_STATUS_ERROR
+ *
+ * @COMMAND_HWMON_READVOLT: query the voltage from the hardware monitor,
+ * return status is SVC_STATUS_OK or SVC_STATUS_ERROR
  */
 enum stratix10_svc_command_code {
 	/* for FPGA */
@@ -155,6 +171,7 @@ enum stratix10_svc_command_code {
 	COMMAND_RSU_DCMF_VERSION,
 	COMMAND_RSU_DCMF_STATUS,
 	COMMAND_FIRMWARE_VERSION,
+	COMMAND_RSU_GET_SPT_TABLE,
 	/* for FCS */
 	COMMAND_FCS_REQUEST_SERVICE = 20,
 	COMMAND_FCS_SEND_CERTIFICATE,
@@ -164,8 +181,13 @@ enum stratix10_svc_command_code {
 	COMMAND_FCS_RANDOM_NUMBER_GEN,
 	/* for general status poll */
 	COMMAND_POLL_SERVICE_STATUS = 40,
+	/* for generic mailbox send command */
+	COMMAND_MBOX_SEND_CMD = 100,
 	/* Non-mailbox SMC Call */
 	COMMAND_SMC_SVC_VERSION = 200,
+	/* for HWMON */
+	COMMAND_HWMON_READTEMP,
+	COMMAND_HWMON_READVOLT
 };
 
 /**
@@ -279,5 +301,92 @@ int stratix10_svc_send(struct stratix10_svc_chan *chan, void *msg);
  * request process.
  */
 void stratix10_svc_done(struct stratix10_svc_chan *chan);
+
+/**
+ * typedef async_callback_t - A type definition for an asynchronous callback function.
+ *
+ * This type defines a function pointer for an asynchronous callback.
+ * The callback function takes a single argument, which is a pointer to
+ * user-defined data.
+ *
+ * @cb_arg: Argument to be passed to the callback function.
+ */
+typedef void (*async_callback_t)(void *cb_arg);
+
+/**
+ * stratix10_svc_add_async_client - Add an asynchronous client to a Stratix 10
+ *                                  service channel.
+ * @chan: Pointer to the Stratix 10 service channel structure.
+ * @use_unique_clientid: Boolean flag indicating whether to use a unique client ID.
+ *
+ * This function registers an asynchronous client with the specified Stratix 10
+ * service channel. If the use_unique_clientid flag is set to true, a unique client
+ * ID will be assigned to the client.
+ *
+ * Return: 0 on success, or a negative error code on failure:
+ *         -EINVAL if the channel is NULL or the async controller is not initialized.
+ *         -EALREADY if the async channel is already allocated.
+ *         -ENOMEM if memory allocation fails.
+ *         Other negative values if ID allocation fails
+ */
+int stratix10_svc_add_async_client(struct stratix10_svc_chan *chan, bool use_unique_clientid);
+
+/**
+ * stratix10_svc_remove_async_client - Remove an asynchronous client from the Stratix 10
+ *                                     service channel.
+ * @chan: Pointer to the Stratix 10 service channel structure.
+ *
+ * This function removes an asynchronous client from the specified Stratix 10 service channel.
+ * It is typically used to clean up and release resources associated with the client.
+ *
+ * Return: 0 on success, -EINVAL if the channel or asynchronous channel is invalid.
+ */
+int stratix10_svc_remove_async_client(struct stratix10_svc_chan *chan);
+
+/**
+ * stratix10_svc_async_send - Send an asynchronous message to the SDM mailbox
+ *                            in EL3 secure firmware.
+ * @chan: Pointer to the service channel structure.
+ * @msg: Pointer to the message to be sent.
+ * @handler: Pointer to the handler object used by caller to track the transaction.
+ * @cb: Callback function to be called upon completion.
+ * @cb_arg: Argument to be passed to the callback function.
+ *
+ * This function sends a message asynchronously to the SDM mailbox in EL3 secure firmware.
+ * and registers a callback function to be invoked when the operation completes.
+ *
+ * Return: 0 on success,and negative error codes on failure.
+ */
+int stratix10_svc_async_send(struct stratix10_svc_chan *chan, void *msg, void **handler,
+			     async_callback_t cb, void *cb_arg);
+
+/**
+ * stratix10_svc_async_poll - Polls the status of an asynchronous service request.
+ * @chan: Pointer to the service channel structure.
+ * @tx_handle: Handle to the transaction being polled.
+ * @data: Pointer to the callback data structure to be filled with the result.
+ *
+ * This function checks the status of an asynchronous service request
+ * and fills the provided callback data structure with the result.
+ *
+ * Return: 0 on success, -EINVAL if any input parameter is invalid or if the
+ *         async controller is not initialized, -EAGAIN if the transaction is
+ *         still in progress, or other negative error codes on failure.
+ */
+int stratix10_svc_async_poll(struct stratix10_svc_chan *chan, void *tx_handle,
+			     struct stratix10_svc_cb_data *data);
+
+/**
+ * stratix10_svc_async_done - Complete an asynchronous transaction
+ * @chan: Pointer to the service channel structure
+ * @tx_handle: Pointer to the transaction handle
+ *
+ * This function completes an asynchronous transaction by removing the
+ * transaction from the hash table and deallocating the associated resources.
+ *
+ * Return: 0 on success, -EINVAL on invalid input or errors.
+ */
+int stratix10_svc_async_done(struct stratix10_svc_chan *chan, void *tx_handle);
+
 #endif
 
diff --git a/include/linux/firmware/mediatek/mtk-adsp-ipc.h b/include/linux/firmware/mediatek/mtk-adsp-ipc.h
index 28fd313340b8..6e86799a7dc4 100644
--- a/include/linux/firmware/mediatek/mtk-adsp-ipc.h
+++ b/include/linux/firmware/mediatek/mtk-adsp-ipc.h
@@ -40,23 +40,17 @@ struct mtk_adsp_chan {
 struct mtk_adsp_ipc {
 	struct mtk_adsp_chan chans[MTK_ADSP_MBOX_NUM];
 	struct device *dev;
-	struct mtk_adsp_ipc_ops *ops;
+	const struct mtk_adsp_ipc_ops *ops;
 	void *private_data;
 };
 
 static inline void mtk_adsp_ipc_set_data(struct mtk_adsp_ipc *ipc, void *data)
 {
-	if (!ipc)
-		return;
-
 	ipc->private_data = data;
 }
 
 static inline void *mtk_adsp_ipc_get_data(struct mtk_adsp_ipc *ipc)
 {
-	if (!ipc)
-		return NULL;
-
 	return ipc->private_data;
 }
 
diff --git a/include/linux/firmware/meson/meson_sm.h b/include/linux/firmware/meson/meson_sm.h
index 95b0da2326a9..8eaf8922ab02 100644
--- a/include/linux/firmware/meson/meson_sm.h
+++ b/include/linux/firmware/meson/meson_sm.h
@@ -19,7 +19,7 @@ enum {
 struct meson_sm_firmware;
 
 int meson_sm_call(struct meson_sm_firmware *fw, unsigned int cmd_index,
-		  u32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4);
+		  s32 *ret, u32 arg0, u32 arg1, u32 arg2, u32 arg3, u32 arg4);
 int meson_sm_call_write(struct meson_sm_firmware *fw, void *buffer,
 			unsigned int b_size, unsigned int cmd_index, u32 arg0,
 			u32 arg1, u32 arg2, u32 arg3, u32 arg4);
diff --git a/include/linux/firmware/qcom/qcom_qseecom.h b/include/linux/firmware/qcom/qcom_qseecom.h
new file mode 100644
index 000000000000..3387897bf368
--- /dev/null
+++ b/include/linux/firmware/qcom/qcom_qseecom.h
@@ -0,0 +1,54 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Driver for Qualcomm Secure Execution Environment (SEE) interface (QSEECOM).
+ * Responsible for setting up and managing QSEECOM client devices.
+ *
+ * Copyright (C) 2023 Maximilian Luz <luzmaximilian@gmail.com>
+ */
+
+#ifndef __QCOM_QSEECOM_H
+#define __QCOM_QSEECOM_H
+
+#include <linux/auxiliary_bus.h>
+#include <linux/dma-mapping.h>
+#include <linux/types.h>
+
+#include <linux/firmware/qcom/qcom_scm.h>
+
+/**
+ * struct qseecom_client - QSEECOM client device.
+ * @aux_dev: Underlying auxiliary device.
+ * @app_id: ID of the loaded application.
+ */
+struct qseecom_client {
+	struct auxiliary_device aux_dev;
+	u32 app_id;
+};
+
+/**
+ * qcom_qseecom_app_send() - Send to and receive data from a given QSEE app.
+ * @client:   The QSEECOM client associated with the target app.
+ * @req:      Request buffer sent to the app (must be TZ memory).
+ * @req_size: Size of the request buffer.
+ * @rsp:      Response buffer, written to by the app (must be TZ memory).
+ * @rsp_size: Size of the response buffer.
+ *
+ * Sends a request to the QSEE app associated with the given client and read
+ * back its response. The caller must provide two DMA memory regions, one for
+ * the request and one for the response, and fill out the @req region with the
+ * respective (app-specific) request data. The QSEE app reads this and returns
+ * its response in the @rsp region.
+ *
+ * Note: This is a convenience wrapper around qcom_scm_qseecom_app_send().
+ * Clients should prefer to use this wrapper.
+ *
+ * Return: Zero on success, nonzero on failure.
+ */
+static inline int qcom_qseecom_app_send(struct qseecom_client *client,
+					void *req, size_t req_size,
+					void *rsp, size_t rsp_size)
+{
+	return qcom_scm_qseecom_app_send(client->app_id, req, req_size, rsp, rsp_size);
+}
+
+#endif /* __QCOM_QSEECOM_H */
diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h
index 250ea4efb7cb..a55ca771286b 100644
--- a/include/linux/firmware/qcom/qcom_scm.h
+++ b/include/linux/firmware/qcom/qcom_scm.h
@@ -59,12 +59,12 @@ enum qcom_scm_ice_cipher {
 #define QCOM_SCM_PERM_RW (QCOM_SCM_PERM_READ | QCOM_SCM_PERM_WRITE)
 #define QCOM_SCM_PERM_RWX (QCOM_SCM_PERM_RW | QCOM_SCM_PERM_EXEC)
 
-extern bool qcom_scm_is_available(void);
+bool qcom_scm_is_available(void);
 
-extern int qcom_scm_set_cold_boot_addr(void *entry);
-extern int qcom_scm_set_warm_boot_addr(void *entry);
-extern void qcom_scm_cpu_power_down(u32 flags);
-extern int qcom_scm_set_remote_state(u32 state, u32 id);
+int qcom_scm_set_cold_boot_addr(void *entry);
+int qcom_scm_set_warm_boot_addr(void *entry);
+void qcom_scm_cpu_power_down(u32 flags);
+int qcom_scm_set_remote_state(u32 state, u32 id);
 
 struct qcom_scm_pas_metadata {
 	void *ptr;
@@ -72,54 +72,113 @@ struct qcom_scm_pas_metadata {
 	ssize_t size;
 };
 
-extern int qcom_scm_pas_init_image(u32 peripheral, const void *metadata,
-				   size_t size,
-				   struct qcom_scm_pas_metadata *ctx);
+int qcom_scm_pas_init_image(u32 peripheral, const void *metadata, size_t size,
+			    struct qcom_scm_pas_metadata *ctx);
 void qcom_scm_pas_metadata_release(struct qcom_scm_pas_metadata *ctx);
-extern int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr,
-				  phys_addr_t size);
-extern int qcom_scm_pas_auth_and_reset(u32 peripheral);
-extern int qcom_scm_pas_shutdown(u32 peripheral);
-extern bool qcom_scm_pas_supported(u32 peripheral);
-
-extern int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val);
-extern int qcom_scm_io_writel(phys_addr_t addr, unsigned int val);
-
-extern bool qcom_scm_restore_sec_cfg_available(void);
-extern int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
-extern int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
-extern int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
-extern int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size);
-extern int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
-					  u32 cp_nonpixel_start,
-					  u32 cp_nonpixel_size);
-extern int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz,
-			       u64 *src,
-			       const struct qcom_scm_vmperm *newvm,
-			       unsigned int dest_cnt);
-
-extern bool qcom_scm_ocmem_lock_available(void);
-extern int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset,
-			       u32 size, u32 mode);
-extern int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset,
-				 u32 size);
-
-extern bool qcom_scm_ice_available(void);
-extern int qcom_scm_ice_invalidate_key(u32 index);
-extern int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size,
-				enum qcom_scm_ice_cipher cipher,
-				u32 data_unit_size);
-
-extern bool qcom_scm_hdcp_available(void);
-extern int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt,
-			     u32 *resp);
-
-extern int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt);
-extern int qcom_scm_qsmmu500_wait_safe_toggle(bool en);
-
-extern int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
-			      u64 limit_node, u32 node_id, u64 version);
-extern int qcom_scm_lmh_profile_change(u32 profile_id);
-extern bool qcom_scm_lmh_dcvsh_available(void);
+int qcom_scm_pas_mem_setup(u32 peripheral, phys_addr_t addr, phys_addr_t size);
+int qcom_scm_pas_auth_and_reset(u32 peripheral);
+int qcom_scm_pas_shutdown(u32 peripheral);
+bool qcom_scm_pas_supported(u32 peripheral);
+
+int qcom_scm_io_readl(phys_addr_t addr, unsigned int *val);
+int qcom_scm_io_writel(phys_addr_t addr, unsigned int val);
+
+bool qcom_scm_restore_sec_cfg_available(void);
+int qcom_scm_restore_sec_cfg(u32 device_id, u32 spare);
+int qcom_scm_set_gpu_smmu_aperture(unsigned int context_bank);
+bool qcom_scm_set_gpu_smmu_aperture_is_available(void);
+int qcom_scm_iommu_secure_ptbl_size(u32 spare, size_t *size);
+int qcom_scm_iommu_secure_ptbl_init(u64 addr, u32 size, u32 spare);
+int qcom_scm_iommu_set_cp_pool_size(u32 spare, u32 size);
+int qcom_scm_mem_protect_video_var(u32 cp_start, u32 cp_size,
+				   u32 cp_nonpixel_start, u32 cp_nonpixel_size);
+int qcom_scm_assign_mem(phys_addr_t mem_addr, size_t mem_sz, u64 *src,
+			const struct qcom_scm_vmperm *newvm,
+			unsigned int dest_cnt);
+
+bool qcom_scm_ocmem_lock_available(void);
+int qcom_scm_ocmem_lock(enum qcom_scm_ocmem_client id, u32 offset, u32 size,
+			u32 mode);
+int qcom_scm_ocmem_unlock(enum qcom_scm_ocmem_client id, u32 offset, u32 size);
+
+bool qcom_scm_ice_available(void);
+int qcom_scm_ice_invalidate_key(u32 index);
+int qcom_scm_ice_set_key(u32 index, const u8 *key, u32 key_size,
+			 enum qcom_scm_ice_cipher cipher, u32 data_unit_size);
+bool qcom_scm_has_wrapped_key_support(void);
+int qcom_scm_derive_sw_secret(const u8 *eph_key, size_t eph_key_size,
+			      u8 *sw_secret, size_t sw_secret_size);
+int qcom_scm_generate_ice_key(u8 *lt_key, size_t lt_key_size);
+int qcom_scm_prepare_ice_key(const u8 *lt_key, size_t lt_key_size,
+			     u8 *eph_key, size_t eph_key_size);
+int qcom_scm_import_ice_key(const u8 *raw_key, size_t raw_key_size,
+			    u8 *lt_key, size_t lt_key_size);
+
+bool qcom_scm_hdcp_available(void);
+int qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp);
+
+int qcom_scm_iommu_set_pt_format(u32 sec_id, u32 ctx_num, u32 pt_fmt);
+int qcom_scm_qsmmu500_wait_safe_toggle(bool en);
+
+int qcom_scm_lmh_dcvsh(u32 payload_fn, u32 payload_reg, u32 payload_val,
+		       u64 limit_node, u32 node_id, u64 version);
+int qcom_scm_lmh_profile_change(u32 profile_id);
+bool qcom_scm_lmh_dcvsh_available(void);
+
+/*
+ * Request TZ to program set of access controlled registers necessary
+ * irrespective of any features
+ */
+#define QCOM_SCM_GPU_ALWAYS_EN_REQ BIT(0)
+/*
+ * Request TZ to program BCL id to access controlled register when BCL is
+ * enabled
+ */
+#define QCOM_SCM_GPU_BCL_EN_REQ BIT(1)
+/*
+ * Request TZ to program set of access controlled register for CLX feature
+ * when enabled
+ */
+#define QCOM_SCM_GPU_CLX_EN_REQ BIT(2)
+/*
+ * Request TZ to program tsense ids to access controlled registers for reading
+ * gpu temperature sensors
+ */
+#define QCOM_SCM_GPU_TSENSE_EN_REQ BIT(3)
+
+int qcom_scm_gpu_init_regs(u32 gpu_req);
+
+int qcom_scm_shm_bridge_create(u64 pfn_and_ns_perm_flags,
+			       u64 ipfn_and_s_perm_flags, u64 size_and_flags,
+			       u64 ns_vmids, u64 *handle);
+int qcom_scm_shm_bridge_delete(u64 handle);
+
+#ifdef CONFIG_QCOM_QSEECOM
+
+int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id);
+int qcom_scm_qseecom_app_send(u32 app_id, void *req, size_t req_size,
+			      void *rsp, size_t rsp_size);
+
+#else /* CONFIG_QCOM_QSEECOM */
+
+static inline int qcom_scm_qseecom_app_get_id(const char *app_name, u32 *app_id)
+{
+	return -EINVAL;
+}
+
+static inline int qcom_scm_qseecom_app_send(u32 app_id,
+					    void *req, size_t req_size,
+					    void *rsp, size_t rsp_size)
+{
+	return -EINVAL;
+}
+
+#endif /* CONFIG_QCOM_QSEECOM */
+
+int qcom_scm_qtee_invoke_smc(phys_addr_t inbuf, size_t inbuf_size,
+			     phys_addr_t outbuf, size_t outbuf_size,
+			     u64 *result, u64 *response_type);
+int qcom_scm_qtee_callback_response(phys_addr_t buf, size_t buf_size,
+				    u64 *result, u64 *response_type);
 
 #endif
diff --git a/include/linux/firmware/qcom/qcom_tzmem.h b/include/linux/firmware/qcom/qcom_tzmem.h
new file mode 100644
index 000000000000..23173e0c3ddd
--- /dev/null
+++ b/include/linux/firmware/qcom/qcom_tzmem.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2023-2024 Linaro Ltd.
+ */
+
+#ifndef __QCOM_TZMEM_H
+#define __QCOM_TZMEM_H
+
+#include <linux/cleanup.h>
+#include <linux/gfp.h>
+#include <linux/types.h>
+
+struct device;
+struct qcom_tzmem_pool;
+
+/**
+ * enum qcom_tzmem_policy - Policy for pool growth.
+ */
+enum qcom_tzmem_policy {
+	/**
+	 * @QCOM_TZMEM_POLICY_STATIC: Static pool,
+	 * never grow above initial size.
+	 */
+	QCOM_TZMEM_POLICY_STATIC = 1,
+	/**
+	 * @QCOM_TZMEM_POLICY_MULTIPLIER: When out of memory,
+	 * add increment * current size of memory.
+	 */
+	QCOM_TZMEM_POLICY_MULTIPLIER,
+	/**
+	 * @QCOM_TZMEM_POLICY_ON_DEMAND: When out of memory
+	 * add as much as is needed until max_size.
+	 */
+	QCOM_TZMEM_POLICY_ON_DEMAND,
+};
+
+/**
+ * struct qcom_tzmem_pool_config - TZ memory pool configuration.
+ * @initial_size: Number of bytes to allocate for the pool during its creation.
+ * @policy: Pool size growth policy.
+ * @increment: Used with policies that allow pool growth.
+ * @max_size: Size above which the pool will never grow.
+ */
+struct qcom_tzmem_pool_config {
+	size_t initial_size;
+	enum qcom_tzmem_policy policy;
+	size_t increment;
+	size_t max_size;
+};
+
+struct qcom_tzmem_pool *
+qcom_tzmem_pool_new(const struct qcom_tzmem_pool_config *config);
+void qcom_tzmem_pool_free(struct qcom_tzmem_pool *pool);
+struct qcom_tzmem_pool *
+devm_qcom_tzmem_pool_new(struct device *dev,
+			 const struct qcom_tzmem_pool_config *config);
+
+void *qcom_tzmem_alloc(struct qcom_tzmem_pool *pool, size_t size, gfp_t gfp);
+void qcom_tzmem_free(void *ptr);
+
+DEFINE_FREE(qcom_tzmem, void *, if (_T) qcom_tzmem_free(_T))
+
+phys_addr_t qcom_tzmem_to_phys(void *ptr);
+
+#if IS_ENABLED(CONFIG_QCOM_TZMEM_MODE_SHMBRIDGE)
+int qcom_tzmem_shm_bridge_create(phys_addr_t paddr, size_t size, u64 *handle);
+void qcom_tzmem_shm_bridge_delete(u64 handle);
+#else
+static inline int qcom_tzmem_shm_bridge_create(phys_addr_t paddr,
+					       size_t size, u64 *handle)
+{
+	return 0;
+}
+
+static inline void qcom_tzmem_shm_bridge_delete(u64 handle)
+{
+}
+#endif
+
+#endif /* __QCOM_TZMEM */
diff --git a/include/linux/firmware/samsung/exynos-acpm-protocol.h b/include/linux/firmware/samsung/exynos-acpm-protocol.h
new file mode 100644
index 000000000000..2091da965a5a
--- /dev/null
+++ b/include/linux/firmware/samsung/exynos-acpm-protocol.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2020 Samsung Electronics Co., Ltd.
+ * Copyright 2020 Google LLC.
+ * Copyright 2024 Linaro Ltd.
+ */
+
+#ifndef __EXYNOS_ACPM_PROTOCOL_H
+#define __EXYNOS_ACPM_PROTOCOL_H
+
+#include <linux/types.h>
+
+struct acpm_handle;
+struct device_node;
+
+struct acpm_dvfs_ops {
+	int (*set_rate)(const struct acpm_handle *handle,
+			unsigned int acpm_chan_id, unsigned int clk_id,
+			unsigned long rate);
+	unsigned long (*get_rate)(const struct acpm_handle *handle,
+				  unsigned int acpm_chan_id,
+				  unsigned int clk_id);
+};
+
+struct acpm_pmic_ops {
+	int (*read_reg)(const struct acpm_handle *handle,
+			unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan,
+			u8 *buf);
+	int (*bulk_read)(const struct acpm_handle *handle,
+			 unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan,
+			 u8 count, u8 *buf);
+	int (*write_reg)(const struct acpm_handle *handle,
+			 unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan,
+			 u8 value);
+	int (*bulk_write)(const struct acpm_handle *handle,
+			  unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan,
+			  u8 count, const u8 *buf);
+	int (*update_reg)(const struct acpm_handle *handle,
+			  unsigned int acpm_chan_id, u8 type, u8 reg, u8 chan,
+			  u8 value, u8 mask);
+};
+
+struct acpm_ops {
+	struct acpm_dvfs_ops dvfs_ops;
+	struct acpm_pmic_ops pmic_ops;
+};
+
+/**
+ * struct acpm_handle - Reference to an initialized protocol instance
+ * @ops:
+ */
+struct acpm_handle {
+	struct acpm_ops ops;
+};
+
+struct device;
+
+#if IS_ENABLED(CONFIG_EXYNOS_ACPM_PROTOCOL)
+const struct acpm_handle *devm_acpm_get_by_node(struct device *dev,
+						struct device_node *np);
+#else
+
+static inline const struct acpm_handle *devm_acpm_get_by_node(struct device *dev,
+							      struct device_node *np)
+{
+	return NULL;
+}
+#endif
+
+#endif /* __EXYNOS_ACPM_PROTOCOL_H */
diff --git a/include/linux/firmware/thead/thead,th1520-aon.h b/include/linux/firmware/thead/thead,th1520-aon.h
new file mode 100644
index 000000000000..dae132b66873
--- /dev/null
+++ b/include/linux/firmware/thead/thead,th1520-aon.h
@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2021 Alibaba Group Holding Limited.
+ */
+
+#ifndef _THEAD_AON_H
+#define _THEAD_AON_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+#define AON_RPC_MSG_MAGIC (0xef)
+#define TH1520_AON_RPC_VERSION 2
+#define TH1520_AON_RPC_MSG_NUM 7
+
+struct th1520_aon_chan;
+
+enum th1520_aon_rpc_svc {
+	TH1520_AON_RPC_SVC_UNKNOWN = 0,
+	TH1520_AON_RPC_SVC_PM = 1,
+	TH1520_AON_RPC_SVC_MISC = 2,
+	TH1520_AON_RPC_SVC_AVFS = 3,
+	TH1520_AON_RPC_SVC_SYS = 4,
+	TH1520_AON_RPC_SVC_WDG = 5,
+	TH1520_AON_RPC_SVC_LPM = 6,
+	TH1520_AON_RPC_SVC_MAX = 0x3F,
+};
+
+enum th1520_aon_misc_func {
+	TH1520_AON_MISC_FUNC_UNKNOWN = 0,
+	TH1520_AON_MISC_FUNC_SET_CONTROL = 1,
+	TH1520_AON_MISC_FUNC_GET_CONTROL = 2,
+	TH1520_AON_MISC_FUNC_REGDUMP_CFG = 3,
+};
+
+enum th1520_aon_wdg_func {
+	TH1520_AON_WDG_FUNC_UNKNOWN = 0,
+	TH1520_AON_WDG_FUNC_START = 1,
+	TH1520_AON_WDG_FUNC_STOP = 2,
+	TH1520_AON_WDG_FUNC_PING = 3,
+	TH1520_AON_WDG_FUNC_TIMEOUTSET = 4,
+	TH1520_AON_WDG_FUNC_RESTART = 5,
+	TH1520_AON_WDG_FUNC_GET_STATE = 6,
+	TH1520_AON_WDG_FUNC_POWER_OFF = 7,
+	TH1520_AON_WDG_FUNC_AON_WDT_ON = 8,
+	TH1520_AON_WDG_FUNC_AON_WDT_OFF = 9,
+};
+
+enum th1520_aon_sys_func {
+	TH1520_AON_SYS_FUNC_UNKNOWN = 0,
+	TH1520_AON_SYS_FUNC_AON_RESERVE_MEM = 1,
+};
+
+enum th1520_aon_lpm_func {
+	TH1520_AON_LPM_FUNC_UNKNOWN = 0,
+	TH1520_AON_LPM_FUNC_REQUIRE_STR = 1,
+	TH1520_AON_LPM_FUNC_RESUME_STR = 2,
+	TH1520_AON_LPM_FUNC_REQUIRE_STD = 3,
+	TH1520_AON_LPM_FUNC_CPUHP = 4,
+	TH1520_AON_LPM_FUNC_REGDUMP_CFG = 5,
+};
+
+enum th1520_aon_pm_func {
+	TH1520_AON_PM_FUNC_UNKNOWN = 0,
+	TH1520_AON_PM_FUNC_SET_RESOURCE_REGULATOR = 1,
+	TH1520_AON_PM_FUNC_GET_RESOURCE_REGULATOR = 2,
+	TH1520_AON_PM_FUNC_SET_RESOURCE_POWER_MODE = 3,
+	TH1520_AON_PM_FUNC_PWR_SET = 4,
+	TH1520_AON_PM_FUNC_PWR_GET = 5,
+	TH1520_AON_PM_FUNC_CHECK_FAULT = 6,
+	TH1520_AON_PM_FUNC_GET_TEMPERATURE = 7,
+};
+
+struct th1520_aon_rpc_msg_hdr {
+	u8 ver; /* version of msg hdr */
+	u8 size; /*  msg size ,uinit in bytes,the size includes rpc msg header self */
+	u8 svc; /* rpc main service id */
+	u8 func; /* rpc sub func id of specific service, sent by caller */
+} __packed __aligned(1);
+
+struct th1520_aon_rpc_ack_common {
+	struct th1520_aon_rpc_msg_hdr hdr;
+	u8 err_code;
+} __packed __aligned(1);
+
+#define RPC_SVC_MSG_TYPE_DATA 0
+#define RPC_SVC_MSG_TYPE_ACK 1
+#define RPC_SVC_MSG_NEED_ACK 0
+#define RPC_SVC_MSG_NO_NEED_ACK 1
+
+#define RPC_GET_VER(MESG) ((MESG)->ver)
+#define RPC_SET_VER(MESG, VER) ((MESG)->ver = (VER))
+#define RPC_GET_SVC_ID(MESG) ((MESG)->svc & 0x3F)
+#define RPC_SET_SVC_ID(MESG, ID) ((MESG)->svc |= 0x3F & (ID))
+#define RPC_GET_SVC_FLAG_MSG_TYPE(MESG) (((MESG)->svc & 0x80) >> 7)
+#define RPC_SET_SVC_FLAG_MSG_TYPE(MESG, TYPE) ((MESG)->svc |= (TYPE) << 7)
+#define RPC_GET_SVC_FLAG_ACK_TYPE(MESG) (((MESG)->svc & 0x40) >> 6)
+#define RPC_SET_SVC_FLAG_ACK_TYPE(MESG, ACK) ((MESG)->svc |= (ACK) << 6)
+
+#define RPC_SET_BE64(MESG, OFFSET, SET_DATA)                                \
+	do {                                                                \
+		u8 *data = (u8 *)(MESG);                                    \
+		u64 _offset = (OFFSET);                                     \
+		u64 _set_data = (SET_DATA);                                 \
+		data[_offset + 7] = _set_data & 0xFF;                       \
+		data[_offset + 6] = (_set_data & 0xFF00) >> 8;              \
+		data[_offset + 5] = (_set_data & 0xFF0000) >> 16;           \
+		data[_offset + 4] = (_set_data & 0xFF000000) >> 24;         \
+		data[_offset + 3] = (_set_data & 0xFF00000000) >> 32;       \
+		data[_offset + 2] = (_set_data & 0xFF0000000000) >> 40;     \
+		data[_offset + 1] = (_set_data & 0xFF000000000000) >> 48;   \
+		data[_offset + 0] = (_set_data & 0xFF00000000000000) >> 56; \
+	} while (0)
+
+#define RPC_SET_BE32(MESG, OFFSET, SET_DATA)			    \
+	do {							    \
+		u8 *data = (u8 *)(MESG);			    \
+		u64 _offset = (OFFSET);				    \
+		u64 _set_data = (SET_DATA);			    \
+		data[_offset + 3] = (_set_data) & 0xFF;		    \
+		data[_offset + 2] = (_set_data & 0xFF00) >> 8;	    \
+		data[_offset + 1] = (_set_data & 0xFF0000) >> 16;   \
+		data[_offset + 0] = (_set_data & 0xFF000000) >> 24; \
+	} while (0)
+
+#define RPC_SET_BE16(MESG, OFFSET, SET_DATA)		       \
+	do {						       \
+		u8 *data = (u8 *)(MESG);		       \
+		u64 _offset = (OFFSET);			       \
+		u64 _set_data = (SET_DATA);		       \
+		data[_offset + 1] = (_set_data) & 0xFF;	       \
+		data[_offset + 0] = (_set_data & 0xFF00) >> 8; \
+	} while (0)
+
+#define RPC_SET_U8(MESG, OFFSET, SET_DATA)	  \
+	do {					  \
+		u8 *data = (u8 *)(MESG);	  \
+		data[OFFSET] = (SET_DATA) & 0xFF; \
+	} while (0)
+
+#define RPC_GET_BE64(MESG, OFFSET, PTR)                                      \
+	do {                                                                 \
+		u8 *data = (u8 *)(MESG);                                     \
+		u64 _offset = (OFFSET);                                      \
+		*(u32 *)(PTR) =                                              \
+			(data[_offset + 7] | data[_offset + 6] << 8 |        \
+			 data[_offset + 5] << 16 | data[_offset + 4] << 24 | \
+			 data[_offset + 3] << 32 | data[_offset + 2] << 40 | \
+			 data[_offset + 1] << 48 | data[_offset + 0] << 56); \
+	} while (0)
+
+#define RPC_GET_BE32(MESG, OFFSET, PTR)                                      \
+	do {                                                                 \
+		u8 *data = (u8 *)(MESG);                                     \
+		u64 _offset = (OFFSET);                                      \
+		*(u32 *)(PTR) =                                              \
+			(data[_offset + 3] | data[_offset + 2] << 8 |        \
+			 data[_offset + 1] << 16 | data[_offset + 0] << 24); \
+	} while (0)
+
+#define RPC_GET_BE16(MESG, OFFSET, PTR)                                       \
+	do {                                                                  \
+		u8 *data = (u8 *)(MESG);                                      \
+		u64 _offset = (OFFSET);                                       \
+		*(u16 *)(PTR) = (data[_offset + 1] | data[_offset + 0] << 8); \
+	} while (0)
+
+#define RPC_GET_U8(MESG, OFFSET, PTR)          \
+	do {                                   \
+		u8 *data = (u8 *)(MESG);       \
+		*(u8 *)(PTR) = (data[OFFSET]); \
+	} while (0)
+
+/*
+ * Defines for SC PM Power Mode
+ */
+#define TH1520_AON_PM_PW_MODE_OFF 0 /* Power off */
+#define TH1520_AON_PM_PW_MODE_STBY 1 /* Power in standby */
+#define TH1520_AON_PM_PW_MODE_LP 2 /* Power in low-power */
+#define TH1520_AON_PM_PW_MODE_ON 3 /* Power on */
+
+/*
+ * Defines for AON power islands
+ */
+#define TH1520_AON_AUDIO_PD 0
+#define TH1520_AON_VDEC_PD 1
+#define TH1520_AON_NPU_PD 2
+#define TH1520_AON_VENC_PD 3
+#define TH1520_AON_GPU_PD 4
+#define TH1520_AON_DSP0_PD 5
+#define TH1520_AON_DSP1_PD 6
+
+struct th1520_aon_chan *th1520_aon_init(struct device *dev);
+void th1520_aon_deinit(struct th1520_aon_chan *aon_chan);
+
+int th1520_aon_call_rpc(struct th1520_aon_chan *aon_chan, void *msg);
+int th1520_aon_power_update(struct th1520_aon_chan *aon_chan, u16 rsrc,
+			    bool power_on);
+
+#endif /* _THEAD_AON_H */
diff --git a/include/linux/firmware/xlnx-event-manager.h b/include/linux/firmware/xlnx-event-manager.h
index 82e8254b0f80..645dd34155e6 100644
--- a/include/linux/firmware/xlnx-event-manager.h
+++ b/include/linux/firmware/xlnx-event-manager.h
@@ -1,4 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Xilinx Event Management Driver
+ *
+ * Copyright (C) 2024, Advanced Micro Devices, Inc.
+ */
 
 #ifndef _FIRMWARE_XLNX_EVENT_MANAGER_H_
 #define _FIRMWARE_XLNX_EVENT_MANAGER_H_
@@ -7,6 +12,11 @@
 
 #define CB_MAX_PAYLOAD_SIZE	(4U) /*In payload maximum 32bytes */
 
+#define EVENT_SUBSYSTEM_RESTART		(4U)
+
+#define PM_DEV_ACPU_0_0			(0x1810c0afU)
+#define PM_DEV_ACPU_0			(0x1810c003U)
+
 /************************** Exported Function *****************************/
 
 typedef void (*event_cb_func_t)(const u32 *payload, void *data);
diff --git a/include/linux/firmware/xlnx-zynqmp-ufs.h b/include/linux/firmware/xlnx-zynqmp-ufs.h
new file mode 100644
index 000000000000..d3538dd5822a
--- /dev/null
+++ b/include/linux/firmware/xlnx-zynqmp-ufs.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Firmware layer for UFS APIs.
+ *
+ * Copyright (c) 2025 Advanced Micro Devices, Inc.
+ */
+
+#ifndef __FIRMWARE_XLNX_ZYNQMP_UFS_H__
+#define __FIRMWARE_XLNX_ZYNQMP_UFS_H__
+
+#if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
+int zynqmp_pm_is_mphy_tx_rx_config_ready(bool *is_ready);
+int zynqmp_pm_is_sram_init_done(bool *is_done);
+int zynqmp_pm_set_sram_bypass(void);
+int zynqmp_pm_get_ufs_calibration_values(u32 *val);
+#else
+static inline int zynqmp_pm_is_mphy_tx_rx_config_ready(bool *is_ready)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_is_sram_init_done(bool *is_done)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_set_sram_bypass(void)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_get_ufs_calibration_values(u32 *val)
+{
+	return -ENODEV;
+}
+#endif
+
+#endif /* __FIRMWARE_XLNX_ZYNQMP_UFS_H__ */
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index f5da51677069..15fdbd089bbf 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -3,8 +3,9 @@
  * Xilinx Zynq MPSoC Firmware layer
  *
  *  Copyright (C) 2014-2021 Xilinx
+ *  Copyright (C) 2022 - 2025 Advanced Micro Devices, Inc.
  *
- *  Michal Simek <michal.simek@xilinx.com>
+ *  Michal Simek <michal.simek@amd.com>
  *  Davorin Mista <davorin.mista@aggios.com>
  *  Jolly Shah <jollys@xilinx.com>
  *  Rajan Vaja <rajanv@xilinx.com>
@@ -15,6 +16,7 @@
 #include <linux/types.h>
 
 #include <linux/err.h>
+#include <linux/firmware/xlnx-zynqmp-ufs.h>
 
 #define ZYNQMP_PM_VERSION_MAJOR	1
 #define ZYNQMP_PM_VERSION_MINOR	0
@@ -31,9 +33,37 @@
 /* SMC SIP service Call Function Identifier Prefix */
 #define PM_SIP_SVC			0xC2000000
 
+/* SMC function ID to get SiP SVC version */
+#define GET_SIP_SVC_VERSION	(0x8200ff03U)
+
+/* SiP Service Calls version numbers */
+#define SIP_SVC_VERSION_MAJOR		(0U)
+#define SIP_SVC_VERSION_MINOR		(2U)
+
+#define SIP_SVC_PASSTHROUGH_VERSION	((SIP_SVC_VERSION_MAJOR << 16) | \
+					 SIP_SVC_VERSION_MINOR)
+
+/* Fixed ID for FW specific APIs */
+#define PASS_THROUGH_FW_CMD_ID	GENMASK(11, 0)
+
 /* PM API versions */
+#define PM_API_VERSION_1	1
 #define PM_API_VERSION_2	2
 
+#define PM_PINCTRL_PARAM_SET_VERSION	2
+
+/* Family codes */
+#define PM_ZYNQMP_FAMILY_CODE 0x1 /* ZynqMP family code */
+#define PM_VERSAL_FAMILY_CODE 0x2 /* Versal family code */
+#define PM_VERSAL_NET_FAMILY_CODE 0x3 /* Versal NET family code */
+
+#define API_ID_MASK		GENMASK(7, 0)
+#define MODULE_ID_MASK		GENMASK(11, 8)
+#define PLM_MODULE_ID_MASK	GENMASK(15, 8)
+
+/* Firmware feature check version mask */
+#define FIRMWARE_VERSION_MASK		0xFFFFU
+
 /* ATF only commands */
 #define TF_A_PM_REGISTER_SGI		0xa04
 #define PM_GET_TRUSTZONE_VERSION	0xa03
@@ -41,7 +71,13 @@
 #define GET_CALLBACK_DATA		0xa01
 
 /* Number of 32bits values in payload */
-#define PAYLOAD_ARG_CNT	4U
+#define PAYLOAD_ARG_CNT	7U
+
+/* Number of 64bits arguments for SMC call */
+#define SMC_ARG_CNT_64	8U
+
+/* Number of 32bits arguments for SMC call */
+#define SMC_ARG_CNT_32	13U
 
 /* Number of arguments for a callback */
 #define CB_ARG_CNT     4
@@ -78,15 +114,42 @@
 /*
  * Node IDs for the Error Events.
  */
-#define EVENT_ERROR_PMC_ERR1	(0x28100000U)
-#define EVENT_ERROR_PMC_ERR2	(0x28104000U)
-#define EVENT_ERROR_PSM_ERR1	(0x28108000U)
-#define EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR1	(0x28108000U)
+#define VERSAL_EVENT_ERROR_PSM_ERR2	(0x2810C000U)
+
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR1	(0x28100000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR2	(0x28104000U)
+#define VERSAL_NET_EVENT_ERROR_PMC_ERR3	(0x28108000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR1	(0x2810C000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR2	(0x28110000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR3	(0x28114000U)
+#define VERSAL_NET_EVENT_ERROR_PSM_ERR4	(0x28118000U)
 
 /* ZynqMP SD tap delay tuning */
 #define SD_ITAPDLY	0xFF180314
 #define SD_OTAPDLYSEL	0xFF180318
 
+/**
+ * XPM_EVENT_ERROR_MASK_DDRMC_CR: Error event mask for DDRMC MC Correctable ECC Error.
+ */
+#define XPM_EVENT_ERROR_MASK_DDRMC_CR		BIT(18)
+
+/**
+ * XPM_EVENT_ERROR_MASK_DDRMC_NCR: Error event mask for DDRMC MC Non-Correctable ECC Error.
+ */
+#define XPM_EVENT_ERROR_MASK_DDRMC_NCR		BIT(19)
+#define XPM_EVENT_ERROR_MASK_NOC_NCR		BIT(13)
+#define XPM_EVENT_ERROR_MASK_NOC_CR		BIT(12)
+
+enum pm_module_id {
+	PM_MODULE_ID = 0x0,
+	XPM_MODULE_ID = 0x2,
+	XSEM_MODULE_ID = 0x3,
+	TF_A_MODULE_ID = 0xa,
+};
+
 enum pm_api_cb_id {
 	PM_INIT_SUSPEND_CB = 30,
 	PM_ACKNOWLEDGE_CB = 31,
@@ -94,7 +157,9 @@ enum pm_api_cb_id {
 };
 
 enum pm_api_id {
+	PM_API_FEATURES = 0,
 	PM_GET_API_VERSION = 1,
+	PM_GET_NODE_STATUS = 3,
 	PM_REGISTER_NOTIFIER = 5,
 	PM_FORCE_POWERDOWN = 8,
 	PM_REQUEST_WAKEUP = 10,
@@ -113,7 +178,6 @@ enum pm_api_id {
 	PM_SECURE_SHA = 26,
 	PM_PINCTRL_REQUEST = 28,
 	PM_PINCTRL_RELEASE = 29,
-	PM_PINCTRL_GET_FUNCTION = 30,
 	PM_PINCTRL_SET_FUNCTION = 31,
 	PM_PINCTRL_CONFIG_PARAM_GET = 32,
 	PM_PINCTRL_CONFIG_PARAM_SET = 33,
@@ -124,19 +188,20 @@ enum pm_api_id {
 	PM_CLOCK_GETSTATE = 38,
 	PM_CLOCK_SETDIVIDER = 39,
 	PM_CLOCK_GETDIVIDER = 40,
-	PM_CLOCK_SETRATE = 41,
-	PM_CLOCK_GETRATE = 42,
 	PM_CLOCK_SETPARENT = 43,
 	PM_CLOCK_GETPARENT = 44,
 	PM_FPGA_READ = 46,
 	PM_SECURE_AES = 47,
+	PM_EFUSE_ACCESS = 53,
 	PM_FEATURE_CHECK = 63,
 };
 
 /* PMU-FW return status codes */
 enum pm_ret_status {
 	XST_PM_SUCCESS = 0,
+	XST_PM_INVALID_VERSION = 4,
 	XST_PM_NO_FEATURE = 19,
+	XST_PM_INVALID_CRC = 301,
 	XST_PM_INTERNAL = 2000,
 	XST_PM_CONFLICT = 2001,
 	XST_PM_NO_ACCESS = 2002,
@@ -170,9 +235,14 @@ enum pm_ioctl_id {
 	/* Runtime feature configuration */
 	IOCTL_SET_FEATURE_CONFIG = 26,
 	IOCTL_GET_FEATURE_CONFIG = 27,
+	/* IOCTL for Secure Read/Write Interface */
+	IOCTL_READ_REG = 28,
+	IOCTL_MASK_WRITE_REG = 29,
 	/* Dynamic SD/GEM configuration */
 	IOCTL_SET_SD_CONFIG = 30,
 	IOCTL_SET_GEM_CONFIG = 31,
+	/* IOCTL to get default/current QoS */
+	IOCTL_GET_QOS = 34,
 };
 
 enum pm_query_id {
@@ -190,6 +260,7 @@ enum pm_query_id {
 	PM_QID_PINCTRL_GET_PIN_GROUPS = 11,
 	PM_QID_CLOCK_GET_NUM_CLOCKS = 12,
 	PM_QID_CLOCK_GET_MAX_DIVISOR = 13,
+	PM_QID_PINCTRL_GET_ATTRIBUTES = 15,
 };
 
 enum rpu_oper_mode {
@@ -484,20 +555,19 @@ struct zynqmp_pm_query_data {
 	u32 arg3;
 };
 
-int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 arg0, u32 arg1,
-			u32 arg2, u32 arg3, u32 *ret_payload);
+int zynqmp_pm_invoke_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
+int zynqmp_pm_invoke_fw_fn(u32 pm_api_id, u32 *ret_payload, u32 num_args, ...);
 
 #if IS_REACHABLE(CONFIG_ZYNQMP_FIRMWARE)
 int zynqmp_pm_get_api_version(u32 *version);
 int zynqmp_pm_get_chipid(u32 *idcode, u32 *version);
+int zynqmp_pm_get_family_info(u32 *family);
 int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata, u32 *out);
 int zynqmp_pm_clock_enable(u32 clock_id);
 int zynqmp_pm_clock_disable(u32 clock_id);
 int zynqmp_pm_clock_getstate(u32 clock_id, u32 *state);
 int zynqmp_pm_clock_setdivider(u32 clock_id, u32 divider);
 int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider);
-int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate);
-int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate);
 int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id);
 int zynqmp_pm_clock_getparent(u32 clock_id, u32 *parent_id);
 int zynqmp_pm_set_pll_frac_mode(u32 clk_id, u32 mode);
@@ -507,12 +577,11 @@ int zynqmp_pm_get_pll_frac_data(u32 clk_id, u32 *data);
 int zynqmp_pm_set_sd_tapdelay(u32 node_id, u32 type, u32 value);
 int zynqmp_pm_sd_dll_reset(u32 node_id, u32 type);
 int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select);
-int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
+int zynqmp_pm_reset_assert(const u32 reset,
 			   const enum zynqmp_pm_reset_action assert_flag);
-int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset, u32 *status);
+int zynqmp_pm_reset_get_status(const u32 reset, u32 *status);
 unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode);
 int zynqmp_pm_bootmode_write(u32 ps_mode);
-int zynqmp_pm_init_finalize(void);
 int zynqmp_pm_set_suspend_mode(u32 mode);
 int zynqmp_pm_request_node(const u32 node, const u32 capabilities,
 			   const u32 qos, const enum zynqmp_pm_request_ack ack);
@@ -521,6 +590,7 @@ int zynqmp_pm_set_requirement(const u32 node, const u32 capabilities,
 			      const u32 qos,
 			      const enum zynqmp_pm_request_ack ack);
 int zynqmp_pm_aes_engine(const u64 address, u32 *out);
+int zynqmp_pm_efuse_access(const u64 address, u32 *out);
 int zynqmp_pm_sha_hash(const u64 address, const u32 size, const u32 flags);
 int zynqmp_pm_fpga_load(const u64 address, const u32 size, const u32 flags);
 int zynqmp_pm_fpga_get_status(u32 *value);
@@ -534,7 +604,6 @@ int zynqmp_pm_system_shutdown(const u32 type, const u32 subtype);
 int zynqmp_pm_set_boot_health_status(u32 value);
 int zynqmp_pm_pinctrl_request(const u32 pin);
 int zynqmp_pm_pinctrl_release(const u32 pin);
-int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id);
 int zynqmp_pm_pinctrl_set_function(const u32 pin, const u32 id);
 int zynqmp_pm_pinctrl_get_config(const u32 pin, const u32 param,
 				 u32 *value);
@@ -547,6 +616,9 @@ int zynqmp_pm_feature(const u32 api_id);
 int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id);
 int zynqmp_pm_set_feature_config(enum pm_feature_config_id id, u32 value);
 int zynqmp_pm_get_feature_config(enum pm_feature_config_id id, u32 *payload);
+int zynqmp_pm_sec_read_reg(u32 node_id, u32 offset, u32 *ret_value);
+int zynqmp_pm_sec_mask_write_reg(const u32 node_id, const u32 offset,
+				 u32 mask, u32 value);
 int zynqmp_pm_register_sgi(u32 sgi_num, u32 reset);
 int zynqmp_pm_force_pwrdwn(const u32 target,
 			   const enum zynqmp_pm_request_ack ack);
@@ -557,6 +629,8 @@ int zynqmp_pm_request_wake(const u32 node,
 int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode);
 int zynqmp_pm_set_rpu_mode(u32 node_id, enum rpu_oper_mode rpu_mode);
 int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mode);
+int zynqmp_pm_get_node_status(const u32 node, u32 *const status,
+			      u32 *const requirements, u32 *const usage);
 int zynqmp_pm_set_sd_config(u32 node, enum pm_sd_config_type config, u32 value);
 int zynqmp_pm_set_gem_config(u32 node, enum pm_gem_config_type config,
 			     u32 value);
@@ -571,6 +645,11 @@ static inline int zynqmp_pm_get_chipid(u32 *idcode, u32 *version)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_get_family_info(u32 *family)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_query_data(struct zynqmp_pm_query_data qdata,
 				       u32 *out)
 {
@@ -602,16 +681,6 @@ static inline int zynqmp_pm_clock_getdivider(u32 clock_id, u32 *divider)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_clock_setrate(u32 clock_id, u64 rate)
-{
-	return -ENODEV;
-}
-
-static inline int zynqmp_pm_clock_getrate(u32 clock_id, u64 *rate)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_clock_setparent(u32 clock_id, u32 parent_id)
 {
 	return -ENODEV;
@@ -657,14 +726,13 @@ static inline int zynqmp_pm_ospi_mux_select(u32 dev_id, u32 select)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_reset_assert(const enum zynqmp_pm_reset reset,
+static inline int zynqmp_pm_reset_assert(const u32 reset,
 					 const enum zynqmp_pm_reset_action assert_flag)
 {
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_reset_get_status(const enum zynqmp_pm_reset reset,
-					     u32 *status)
+static inline int zynqmp_pm_reset_get_status(const u32 reset, u32 *status)
 {
 	return -ENODEV;
 }
@@ -679,11 +747,6 @@ static inline int zynqmp_pm_bootmode_write(u32 ps_mode)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_init_finalize(void)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_set_suspend_mode(u32 mode)
 {
 	return -ENODEV;
@@ -714,6 +777,11 @@ static inline int zynqmp_pm_aes_engine(const u64 address, u32 *out)
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_efuse_access(const u64 address, u32 *out)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_sha_hash(const u64 address, const u32 size,
 				     const u32 flags)
 {
@@ -781,11 +849,6 @@ static inline int zynqmp_pm_pinctrl_release(const u32 pin)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_pinctrl_get_function(const u32 pin, u32 *id)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_is_function_supported(const u32 api_id, const u32 id)
 {
 	return -ENODEV;
@@ -855,6 +918,17 @@ static inline int zynqmp_pm_request_wake(const u32 node,
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_sec_read_reg(u32 node_id, u32 offset, u32 *ret_value)
+{
+	return -ENODEV;
+}
+
+static inline int zynqmp_pm_sec_mask_write_reg(const u32 node_id, const u32 offset,
+					       u32 mask, u32 value)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_get_rpu_mode(u32 node_id, enum rpu_oper_mode *rpu_mode)
 {
 	return -ENODEV;
@@ -870,6 +944,13 @@ static inline int zynqmp_pm_set_tcm_config(u32 node_id, enum rpu_tcm_comb tcm_mo
 	return -ENODEV;
 }
 
+static inline int zynqmp_pm_get_node_status(const u32 node, u32 *const status,
+					    u32 *const requirements,
+					    u32 *const usage)
+{
+	return -ENODEV;
+}
+
 static inline int zynqmp_pm_set_sd_config(u32 node,
 					  enum pm_sd_config_type config,
 					  u32 value)
diff --git a/include/linux/flex_proportions.h b/include/linux/flex_proportions.h
index 3e378b1fb0bc..e9a72fd0bfe7 100644
--- a/include/linux/flex_proportions.h
+++ b/include/linux/flex_proportions.h
@@ -39,38 +39,6 @@ void fprop_global_destroy(struct fprop_global *p);
 bool fprop_new_period(struct fprop_global *p, int periods);
 
 /*
- *  ---- SINGLE ----
- */
-struct fprop_local_single {
-	/* the local events counter */
-	unsigned long events;
-	/* Period in which we last updated events */
-	unsigned int period;
-	raw_spinlock_t lock;	/* Protect period and numerator */
-};
-
-#define INIT_FPROP_LOCAL_SINGLE(name)			\
-{	.lock = __RAW_SPIN_LOCK_UNLOCKED(name.lock),	\
-}
-
-int fprop_local_init_single(struct fprop_local_single *pl);
-void fprop_local_destroy_single(struct fprop_local_single *pl);
-void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl);
-void fprop_fraction_single(struct fprop_global *p,
-	struct fprop_local_single *pl, unsigned long *numerator,
-	unsigned long *denominator);
-
-static inline
-void fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__fprop_inc_single(p, pl);
-	local_irq_restore(flags);
-}
-
-/*
  * ---- PERCPU ----
  */
 struct fprop_local_percpu {
diff --git a/include/linux/folio_queue.h b/include/linux/folio_queue.h
new file mode 100644
index 000000000000..adab609c972e
--- /dev/null
+++ b/include/linux/folio_queue.h
@@ -0,0 +1,282 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Queue of folios definitions
+ *
+ * Copyright (C) 2024 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * See:
+ *
+ *	Documentation/core-api/folio_queue.rst
+ *
+ * for a description of the API.
+ */
+
+#ifndef _LINUX_FOLIO_QUEUE_H
+#define _LINUX_FOLIO_QUEUE_H
+
+#include <linux/pagevec.h>
+#include <linux/mm.h>
+
+/*
+ * Segment in a queue of running buffers.  Each segment can hold a number of
+ * folios and a portion of the queue can be referenced with the ITER_FOLIOQ
+ * iterator.  The possibility exists of inserting non-folio elements into the
+ * queue (such as gaps).
+ *
+ * Explicit prev and next pointers are used instead of a list_head to make it
+ * easier to add segments to tail and remove them from the head without the
+ * need for a lock.
+ */
+struct folio_queue {
+	struct folio_batch	vec;		/* Folios in the queue segment */
+	u8			orders[PAGEVEC_SIZE]; /* Order of each folio */
+	struct folio_queue	*next;		/* Next queue segment or NULL */
+	struct folio_queue	*prev;		/* Previous queue segment of NULL */
+	unsigned long		marks;		/* 1-bit mark per folio */
+	unsigned long		marks2;		/* Second 1-bit mark per folio */
+#if PAGEVEC_SIZE > BITS_PER_LONG
+#error marks is not big enough
+#endif
+	unsigned int		rreq_id;
+	unsigned int		debug_id;
+};
+
+/**
+ * folioq_init - Initialise a folio queue segment
+ * @folioq: The segment to initialise
+ * @rreq_id: The request identifier to use in tracelines.
+ *
+ * Initialise a folio queue segment and set an identifier to be used in traces.
+ *
+ * Note that the folio pointers are left uninitialised.
+ */
+static inline void folioq_init(struct folio_queue *folioq, unsigned int rreq_id)
+{
+	folio_batch_init(&folioq->vec);
+	folioq->next = NULL;
+	folioq->prev = NULL;
+	folioq->marks = 0;
+	folioq->marks2 = 0;
+	folioq->rreq_id = rreq_id;
+	folioq->debug_id = 0;
+}
+
+/**
+ * folioq_nr_slots: Query the capacity of a folio queue segment
+ * @folioq: The segment to query
+ *
+ * Query the number of folios that a particular folio queue segment might hold.
+ * [!] NOTE: This must not be assumed to be the same for every segment!
+ */
+static inline unsigned int folioq_nr_slots(const struct folio_queue *folioq)
+{
+	return PAGEVEC_SIZE;
+}
+
+/**
+ * folioq_count: Query the occupancy of a folio queue segment
+ * @folioq: The segment to query
+ *
+ * Query the number of folios that have been added to a folio queue segment.
+ * Note that this is not decreased as folios are removed from a segment.
+ */
+static inline unsigned int folioq_count(struct folio_queue *folioq)
+{
+	return folio_batch_count(&folioq->vec);
+}
+
+/**
+ * folioq_full: Query if a folio queue segment is full
+ * @folioq: The segment to query
+ *
+ * Query if a folio queue segment is fully occupied.  Note that this does not
+ * change if folios are removed from a segment.
+ */
+static inline bool folioq_full(struct folio_queue *folioq)
+{
+	//return !folio_batch_space(&folioq->vec);
+	return folioq_count(folioq) >= folioq_nr_slots(folioq);
+}
+
+/**
+ * folioq_is_marked: Check first folio mark in a folio queue segment
+ * @folioq: The segment to query
+ * @slot: The slot number of the folio to query
+ *
+ * Determine if the first mark is set for the folio in the specified slot in a
+ * folio queue segment.
+ */
+static inline bool folioq_is_marked(const struct folio_queue *folioq, unsigned int slot)
+{
+	return test_bit(slot, &folioq->marks);
+}
+
+/**
+ * folioq_mark: Set the first mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Set the first mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
+static inline void folioq_mark(struct folio_queue *folioq, unsigned int slot)
+{
+	set_bit(slot, &folioq->marks);
+}
+
+/**
+ * folioq_unmark: Clear the first mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Clear the first mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
+static inline void folioq_unmark(struct folio_queue *folioq, unsigned int slot)
+{
+	clear_bit(slot, &folioq->marks);
+}
+
+/**
+ * folioq_is_marked2: Check second folio mark in a folio queue segment
+ * @folioq: The segment to query
+ * @slot: The slot number of the folio to query
+ *
+ * Determine if the second mark is set for the folio in the specified slot in a
+ * folio queue segment.
+ */
+static inline bool folioq_is_marked2(const struct folio_queue *folioq, unsigned int slot)
+{
+	return test_bit(slot, &folioq->marks2);
+}
+
+/**
+ * folioq_mark2: Set the second mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Set the second mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
+static inline void folioq_mark2(struct folio_queue *folioq, unsigned int slot)
+{
+	set_bit(slot, &folioq->marks2);
+}
+
+/**
+ * folioq_unmark2: Clear the second mark on a folio in a folio queue segment
+ * @folioq: The segment to modify
+ * @slot: The slot number of the folio to modify
+ *
+ * Clear the second mark for the folio in the specified slot in a folio queue
+ * segment.
+ */
+static inline void folioq_unmark2(struct folio_queue *folioq, unsigned int slot)
+{
+	clear_bit(slot, &folioq->marks2);
+}
+
+/**
+ * folioq_append: Add a folio to a folio queue segment
+ * @folioq: The segment to add to
+ * @folio: The folio to add
+ *
+ * Add a folio to the tail of the sequence in a folio queue segment, increasing
+ * the occupancy count and returning the slot number for the folio just added.
+ * The folio size is extracted and stored in the queue and the marks are left
+ * unmodified.
+ *
+ * Note that it's left up to the caller to check that the segment capacity will
+ * not be exceeded and to extend the queue.
+ */
+static inline unsigned int folioq_append(struct folio_queue *folioq, struct folio *folio)
+{
+	unsigned int slot = folioq->vec.nr++;
+
+	folioq->vec.folios[slot] = folio;
+	folioq->orders[slot] = folio_order(folio);
+	return slot;
+}
+
+/**
+ * folioq_append_mark: Add a folio to a folio queue segment
+ * @folioq: The segment to add to
+ * @folio: The folio to add
+ *
+ * Add a folio to the tail of the sequence in a folio queue segment, increasing
+ * the occupancy count and returning the slot number for the folio just added.
+ * The folio size is extracted and stored in the queue, the first mark is set
+ * and and the second and third marks are left unmodified.
+ *
+ * Note that it's left up to the caller to check that the segment capacity will
+ * not be exceeded and to extend the queue.
+ */
+static inline unsigned int folioq_append_mark(struct folio_queue *folioq, struct folio *folio)
+{
+	unsigned int slot = folioq->vec.nr++;
+
+	folioq->vec.folios[slot] = folio;
+	folioq->orders[slot] = folio_order(folio);
+	folioq_mark(folioq, slot);
+	return slot;
+}
+
+/**
+ * folioq_folio: Get a folio from a folio queue segment
+ * @folioq: The segment to access
+ * @slot: The folio slot to access
+ *
+ * Retrieve the folio in the specified slot from a folio queue segment.  Note
+ * that no bounds check is made and if the slot hasn't been added into yet, the
+ * pointer will be undefined.  If the slot has been cleared, NULL will be
+ * returned.
+ */
+static inline struct folio *folioq_folio(const struct folio_queue *folioq, unsigned int slot)
+{
+	return folioq->vec.folios[slot];
+}
+
+/**
+ * folioq_folio_order: Get the order of a folio from a folio queue segment
+ * @folioq: The segment to access
+ * @slot: The folio slot to access
+ *
+ * Retrieve the order of the folio in the specified slot from a folio queue
+ * segment.  Note that no bounds check is made and if the slot hasn't been
+ * added into yet, the order returned will be 0.
+ */
+static inline unsigned int folioq_folio_order(const struct folio_queue *folioq, unsigned int slot)
+{
+	return folioq->orders[slot];
+}
+
+/**
+ * folioq_folio_size: Get the size of a folio from a folio queue segment
+ * @folioq: The segment to access
+ * @slot: The folio slot to access
+ *
+ * Retrieve the size of the folio in the specified slot from a folio queue
+ * segment.  Note that no bounds check is made and if the slot hasn't been
+ * added into yet, the size returned will be PAGE_SIZE.
+ */
+static inline size_t folioq_folio_size(const struct folio_queue *folioq, unsigned int slot)
+{
+	return PAGE_SIZE << folioq_folio_order(folioq, slot);
+}
+
+/**
+ * folioq_clear: Clear a folio from a folio queue segment
+ * @folioq: The segment to clear
+ * @slot: The folio slot to clear
+ *
+ * Clear a folio from a sequence in a folio queue segment and clear its marks.
+ * The occupancy count is left unchanged.
+ */
+static inline void folioq_clear(struct folio_queue *folioq, unsigned int slot)
+{
+	folioq->vec.folios[slot] = NULL;
+	folioq_unmark(folioq, slot);
+	folioq_unmark2(folioq, slot);
+}
+
+#endif /* _LINUX_FOLIO_QUEUE_H */
diff --git a/include/linux/font.h b/include/linux/font.h
index abf1442ce719..fd8625cd76b2 100644
--- a/include/linux/font.h
+++ b/include/linux/font.h
@@ -35,6 +35,7 @@ struct font_desc {
 #define FONT6x10_IDX	10
 #define TER16x32_IDX	11
 #define FONT6x8_IDX	12
+#define TER10x18_IDX	13
 
 extern const struct font_desc	font_vga_8x8,
 			font_vga_8x16,
@@ -48,7 +49,8 @@ extern const struct font_desc	font_vga_8x8,
 			font_mini_4x6,
 			font_6x10,
 			font_ter_16x32,
-			font_6x8;
+			font_6x8,
+			font_ter_10x18;
 
 /* Find a font with a specific name */
 
@@ -57,7 +59,8 @@ extern const struct font_desc *find_font(const char *name);
 /* Get the default font for a specific screen size */
 
 extern const struct font_desc *get_default_font(int xres, int yres,
-						u32 font_w, u32 font_h);
+						unsigned long *font_w,
+						unsigned long *font_h);
 
 /* Max. length for the name of a predefined font */
 #define MAX_FONT_NAME	32
diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index c9de1f59ee80..b3b53f8c1b28 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_FORTIFY_STRING_H_
 #define _LINUX_FORTIFY_STRING_H_
 
+#include <linux/bitfield.h>
 #include <linux/bug.h>
 #include <linux/const.h>
 #include <linux/limits.h>
@@ -9,7 +10,50 @@
 #define __FORTIFY_INLINE extern __always_inline __gnu_inline __overloadable
 #define __RENAME(x) __asm__(#x)
 
-void fortify_panic(const char *name) __noreturn __cold;
+#define FORTIFY_REASON_DIR(r)		FIELD_GET(BIT(0), r)
+#define FORTIFY_REASON_FUNC(r)		FIELD_GET(GENMASK(7, 1), r)
+#define FORTIFY_REASON(func, write)	(FIELD_PREP(BIT(0), write) | \
+					 FIELD_PREP(GENMASK(7, 1), func))
+
+/* Overridden by KUnit tests. */
+#ifndef fortify_panic
+# define fortify_panic(func, write, avail, size, retfail)	\
+	 __fortify_panic(FORTIFY_REASON(func, write), avail, size)
+#endif
+#ifndef fortify_warn_once
+# define fortify_warn_once(x...)	WARN_ONCE(x)
+#endif
+
+#define FORTIFY_READ		 0
+#define FORTIFY_WRITE		 1
+
+#define EACH_FORTIFY_FUNC(macro)	\
+	macro(strncpy),			\
+	macro(strnlen),			\
+	macro(strlen),			\
+	macro(strscpy),			\
+	macro(strlcat),			\
+	macro(strcat),			\
+	macro(strncat),			\
+	macro(memset),			\
+	macro(memcpy),			\
+	macro(memmove),			\
+	macro(memscan),			\
+	macro(memcmp),			\
+	macro(memchr),			\
+	macro(memchr_inv),		\
+	macro(kmemdup),			\
+	macro(strcpy),			\
+	macro(UNKNOWN),
+
+#define MAKE_FORTIFY_FUNC(func)	FORTIFY_FUNC_##func
+
+enum fortify_func {
+	EACH_FORTIFY_FUNC(MAKE_FORTIFY_FUNC)
+};
+
+void __fortify_report(const u8 reason, const size_t avail, const size_t size);
+void __fortify_panic(const u8 reason, const size_t avail, const size_t size) __cold __noreturn;
 void __read_overflow(void) __compiletime_error("detected read beyond size of object (1st parameter)");
 void __read_overflow2(void) __compiletime_error("detected read beyond size of object (2nd parameter)");
 void __read_overflow2_field(size_t avail, size_t wanted) __compiletime_warning("detected read beyond size of field (2nd parameter); maybe use struct_group()?");
@@ -20,7 +64,7 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("
 ({								\
 	char *__p = (char *)(p);				\
 	size_t __ret = SIZE_MAX;				\
-	size_t __p_size = __member_size(p);			\
+	const size_t __p_size = __member_size(p);		\
 	if (__p_size != SIZE_MAX &&				\
 	    __builtin_constant_p(*__p)) {			\
 		size_t __p_len = __p_size - 1;			\
@@ -31,17 +75,30 @@ void __write_overflow_field(size_t avail, size_t wanted) __compiletime_warning("
 	__ret;							\
 })
 
-#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
+#if defined(__SANITIZE_ADDRESS__)
+
+#if !defined(CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX) && !defined(CONFIG_GENERIC_ENTRY)
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
+#elif defined(CONFIG_KASAN_GENERIC)
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__asan_memset);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memmove);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__asan_memcpy);
+#else /* CONFIG_KASAN_SW_TAGS */
+extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(__hwasan_memset);
+extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memmove);
+extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(__hwasan_memcpy);
+#endif
+
 extern void *__underlying_memchr(const void *p, int c, __kernel_size_t size) __RENAME(memchr);
 extern int __underlying_memcmp(const void *p, const void *q, __kernel_size_t size) __RENAME(memcmp);
-extern void *__underlying_memcpy(void *p, const void *q, __kernel_size_t size) __RENAME(memcpy);
-extern void *__underlying_memmove(void *p, const void *q, __kernel_size_t size) __RENAME(memmove);
-extern void *__underlying_memset(void *p, int c, __kernel_size_t size) __RENAME(memset);
 extern char *__underlying_strcat(char *p, const char *q) __RENAME(strcat);
 extern char *__underlying_strcpy(char *p, const char *q) __RENAME(strcpy);
 extern __kernel_size_t __underlying_strlen(const char *p) __RENAME(strlen);
 extern char *__underlying_strncat(char *p, const char *q, __kernel_size_t count) __RENAME(strncat);
 extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) __RENAME(strncpy);
+
 #else
 
 #if defined(__SANITIZE_MEMORY__)
@@ -66,6 +123,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 #define __underlying_strlen	__builtin_strlen
 #define __underlying_strncat	__builtin_strncat
 #define __underlying_strncpy	__builtin_strncpy
+
 #endif
 
 /**
@@ -93,13 +151,9 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 #if __has_builtin(__builtin_dynamic_object_size)
 #define POS			__pass_dynamic_object_size(1)
 #define POS0			__pass_dynamic_object_size(0)
-#define __struct_size(p)	__builtin_dynamic_object_size(p, 0)
-#define __member_size(p)	__builtin_dynamic_object_size(p, 1)
 #else
 #define POS			__pass_object_size(1)
 #define POS0			__pass_object_size(0)
-#define __struct_size(p)	__builtin_object_size(p, 0)
-#define __member_size(p)	__builtin_object_size(p, 1)
 #endif
 
 #define __compiletime_lessthan(bounds, length)	(	\
@@ -142,42 +196,15 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size)
 __FORTIFY_INLINE __diagnose_as(__builtin_strncpy, 1, 2, 3)
 char *strncpy(char * const POS p, const char *q, __kernel_size_t size)
 {
-	size_t p_size = __member_size(p);
+	const size_t p_size = __member_size(p);
 
 	if (__compiletime_lessthan(p_size, size))
 		__write_overflow();
 	if (p_size < size)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_strncpy, FORTIFY_WRITE, p_size, size, p);
 	return __underlying_strncpy(p, q, size);
 }
 
-/**
- * strcat - Append a string to an existing string
- *
- * @p: pointer to NUL-terminated string to append to
- * @q: pointer to NUL-terminated source string to append from
- *
- * Do not use this function. While FORTIFY_SOURCE tries to avoid
- * read and write overflows, this is only possible when the
- * destination buffer size is known to the compiler. Prefer
- * building the string with formatting, via scnprintf() or similar.
- * At the very least, use strncat().
- *
- * Returns @p.
- *
- */
-__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2)
-char *strcat(char * const POS p, const char *q)
-{
-	size_t p_size = __member_size(p);
-
-	if (p_size == SIZE_MAX)
-		return __underlying_strcat(p, q);
-	if (strlcat(p, q, p_size) >= p_size)
-		fortify_panic(__func__);
-	return p;
-}
-
 extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen);
 /**
  * strnlen - Return bounded count of characters in a NUL-terminated string
@@ -191,8 +218,8 @@ extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(st
  */
 __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size_t maxlen)
 {
-	size_t p_size = __member_size(p);
-	size_t p_len = __compiletime_strlen(p);
+	const size_t p_size = __member_size(p);
+	const size_t p_len = __compiletime_strlen(p);
 	size_t ret;
 
 	/* We can take compile-time actions when maxlen is const. */
@@ -205,7 +232,7 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size
 	/* Do not check characters beyond the end of p. */
 	ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size);
 	if (p_size <= ret && maxlen != ret)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_strnlen, FORTIFY_READ, p_size, ret + 1, ret);
 	return ret;
 }
 
@@ -233,95 +260,26 @@ __FORTIFY_INLINE __kernel_size_t strnlen(const char * const POS p, __kernel_size
 __FORTIFY_INLINE __diagnose_as(__builtin_strlen, 1)
 __kernel_size_t __fortify_strlen(const char * const POS p)
 {
+	const size_t p_size = __member_size(p);
 	__kernel_size_t ret;
-	size_t p_size = __member_size(p);
 
 	/* Give up if we don't know how large p is. */
 	if (p_size == SIZE_MAX)
 		return __underlying_strlen(p);
 	ret = strnlen(p, p_size);
 	if (p_size <= ret)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_strlen, FORTIFY_READ, p_size, ret + 1, ret);
 	return ret;
 }
 
-/* Defined after fortified strlen() to reuse it. */
-extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy);
-/**
- * strlcpy - Copy a string into another string buffer
- *
- * @p: pointer to destination of copy
- * @q: pointer to NUL-terminated source string to copy
- * @size: maximum number of bytes to write at @p
- *
- * If strlen(@q) >= @size, the copy of @q will be truncated at
- * @size - 1 bytes. @p will always be NUL-terminated.
- *
- * Do not use this function. While FORTIFY_SOURCE tries to avoid
- * over-reads when calculating strlen(@q), it is still possible.
- * Prefer strscpy(), though note its different return values for
- * detecting truncation.
- *
- * Returns total number of bytes written to @p, including terminating NUL.
- *
- */
-__FORTIFY_INLINE size_t strlcpy(char * const POS p, const char * const POS q, size_t size)
-{
-	size_t p_size = __member_size(p);
-	size_t q_size = __member_size(q);
-	size_t q_len;	/* Full count of source string length. */
-	size_t len;	/* Count of characters going into destination. */
-
-	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
-		return __real_strlcpy(p, q, size);
-	q_len = strlen(q);
-	len = (q_len >= size) ? size - 1 : q_len;
-	if (__builtin_constant_p(size) && __builtin_constant_p(q_len) && size) {
-		/* Write size is always larger than destination. */
-		if (len >= p_size)
-			__write_overflow();
-	}
-	if (size) {
-		if (len >= p_size)
-			fortify_panic(__func__);
-		__underlying_memcpy(p, q, len);
-		p[len] = '\0';
-	}
-	return q_len;
-}
-
 /* Defined after fortified strnlen() to reuse it. */
-extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(strscpy);
-/**
- * strscpy - Copy a C-string into a sized buffer
- *
- * @p: Where to copy the string to
- * @q: Where to copy the string from
- * @size: Size of destination buffer
- *
- * Copy the source string @p, or as much of it as fits, into the destination
- * @q buffer. The behavior is undefined if the string buffers overlap. The
- * destination @p buffer is always NUL terminated, unless it's zero-sized.
- *
- * Preferred to strlcpy() since the API doesn't require reading memory
- * from the source @q string beyond the specified @size bytes, and since
- * the return value is easier to error-check than strlcpy()'s.
- * In addition, the implementation is robust to the string changing out
- * from underneath it, unlike the current strlcpy() implementation.
- *
- * Preferred to strncpy() since it always returns a valid string, and
- * doesn't unnecessarily force the tail of the destination buffer to be
- * zero padded. If padding is desired please use strscpy_pad().
- *
- * Returns the number of characters copied in @p (not including the
- * trailing %NUL) or -E2BIG if @size is 0 or the copy of @q was truncated.
- */
-__FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, size_t size)
+extern ssize_t __real_strscpy(char *, const char *, size_t) __RENAME(sized_strscpy);
+__FORTIFY_INLINE ssize_t sized_strscpy(char * const POS p, const char * const POS q, size_t size)
 {
-	size_t len;
 	/* Use string size rather than possible enclosing struct size. */
-	size_t p_size = __member_size(p);
-	size_t q_size = __member_size(q);
+	const size_t p_size = __member_size(p);
+	const size_t q_size = __member_size(q);
+	size_t len;
 
 	/* If we cannot get size of p and q default to call strscpy. */
 	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
@@ -360,8 +318,8 @@ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, s
 	 * Generate a runtime write overflow error if len is greater than
 	 * p_size.
 	 */
-	if (len > p_size)
-		fortify_panic(__func__);
+	if (p_size < len)
+		fortify_panic(FORTIFY_FUNC_strscpy, FORTIFY_WRITE, p_size, len, -E2BIG);
 
 	/*
 	 * We can now safely call vanilla strscpy because we are protected from:
@@ -371,6 +329,97 @@ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, s
 	return __real_strscpy(p, q, len);
 }
 
+/* Defined after fortified strlen() to reuse it. */
+extern size_t __real_strlcat(char *p, const char *q, size_t avail) __RENAME(strlcat);
+/**
+ * strlcat - Append a string to an existing string
+ *
+ * @p: pointer to %NUL-terminated string to append to
+ * @q: pointer to %NUL-terminated string to append from
+ * @avail: Maximum bytes available in @p
+ *
+ * Appends %NUL-terminated string @q after the %NUL-terminated
+ * string at @p, but will not write beyond @avail bytes total,
+ * potentially truncating the copy from @q. @p will stay
+ * %NUL-terminated only if a %NUL already existed within
+ * the @avail bytes of @p. If so, the resulting number of
+ * bytes copied from @q will be at most "@avail - strlen(@p) - 1".
+ *
+ * Do not use this function. While FORTIFY_SOURCE tries to avoid
+ * read and write overflows, this is only possible when the sizes
+ * of @p and @q are known to the compiler. Prefer building the
+ * string with formatting, via scnprintf(), seq_buf, or similar.
+ *
+ * Returns total bytes that _would_ have been contained by @p
+ * regardless of truncation, similar to snprintf(). If return
+ * value is >= @avail, the string has been truncated.
+ *
+ */
+__FORTIFY_INLINE
+size_t strlcat(char * const POS p, const char * const POS q, size_t avail)
+{
+	const size_t p_size = __member_size(p);
+	const size_t q_size = __member_size(q);
+	size_t p_len, copy_len;
+	size_t actual, wanted;
+
+	/* Give up immediately if both buffer sizes are unknown. */
+	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
+		return __real_strlcat(p, q, avail);
+
+	p_len = strnlen(p, avail);
+	copy_len = strlen(q);
+	wanted = actual = p_len + copy_len;
+
+	/* Cannot append any more: report truncation. */
+	if (avail <= p_len)
+		return wanted;
+
+	/* Give up if string is already overflowed. */
+	if (p_size <= p_len)
+		fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_READ, p_size, p_len + 1, wanted);
+
+	if (actual >= avail) {
+		copy_len = avail - p_len - 1;
+		actual = p_len + copy_len;
+	}
+
+	/* Give up if copy will overflow. */
+	if (p_size <= actual)
+		fortify_panic(FORTIFY_FUNC_strlcat, FORTIFY_WRITE, p_size, actual + 1, wanted);
+	__underlying_memcpy(p + p_len, q, copy_len);
+	p[actual] = '\0';
+
+	return wanted;
+}
+
+/* Defined after fortified strlcat() to reuse it. */
+/**
+ * strcat - Append a string to an existing string
+ *
+ * @p: pointer to NUL-terminated string to append to
+ * @q: pointer to NUL-terminated source string to append from
+ *
+ * Do not use this function. While FORTIFY_SOURCE tries to avoid
+ * read and write overflows, this is only possible when the
+ * destination buffer size is known to the compiler. Prefer
+ * building the string with formatting, via scnprintf() or similar.
+ * At the very least, use strncat().
+ *
+ * Returns @p.
+ *
+ */
+__FORTIFY_INLINE __diagnose_as(__builtin_strcat, 1, 2)
+char *strcat(char * const POS p, const char *q)
+{
+	const size_t p_size = __member_size(p);
+	const size_t wanted = strlcat(p, q, p_size);
+
+	if (p_size <= wanted)
+		fortify_panic(FORTIFY_FUNC_strcat, FORTIFY_WRITE, p_size, wanted + 1, p);
+	return p;
+}
+
 /**
  * strncat - Append a string to an existing string
  *
@@ -394,22 +443,23 @@ __FORTIFY_INLINE ssize_t strscpy(char * const POS p, const char * const POS q, s
 __FORTIFY_INLINE __diagnose_as(__builtin_strncat, 1, 2, 3)
 char *strncat(char * const POS p, const char * const POS q, __kernel_size_t count)
 {
-	size_t p_len, copy_len;
-	size_t p_size = __member_size(p);
-	size_t q_size = __member_size(q);
+	const size_t p_size = __member_size(p);
+	const size_t q_size = __member_size(q);
+	size_t p_len, copy_len, total;
 
 	if (p_size == SIZE_MAX && q_size == SIZE_MAX)
 		return __underlying_strncat(p, q, count);
 	p_len = strlen(p);
 	copy_len = strnlen(q, count);
-	if (p_size < p_len + copy_len + 1)
-		fortify_panic(__func__);
+	total = p_len + copy_len + 1;
+	if (p_size < total)
+		fortify_panic(FORTIFY_FUNC_strncat, FORTIFY_WRITE, p_size, total, p);
 	__underlying_memcpy(p + p_len, q, copy_len);
 	p[p_len + copy_len] = '\0';
 	return p;
 }
 
-__FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size,
+__FORTIFY_INLINE bool fortify_memset_chk(__kernel_size_t size,
 					 const size_t p_size,
 					 const size_t p_size_field)
 {
@@ -444,7 +494,8 @@ __FORTIFY_INLINE void fortify_memset_chk(__kernel_size_t size,
 	 * lengths are unknown.)
 	 */
 	if (p_size != SIZE_MAX && p_size < size)
-		fortify_panic("memset");
+		fortify_panic(FORTIFY_FUNC_memset, FORTIFY_WRITE, p_size, size, true);
+	return false;
 }
 
 #define __fortify_memset_chk(p, c, size, p_size, p_size_field) ({	\
@@ -498,7 +549,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 					 const size_t q_size,
 					 const size_t p_size_field,
 					 const size_t q_size_field,
-					 const char *func)
+					 const u8 func)
 {
 	if (__builtin_constant_p(size)) {
 		/*
@@ -542,18 +593,15 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 	 * (The SIZE_MAX test is to optimize away checks where the buffer
 	 * lengths are unknown.)
 	 */
-	if ((p_size != SIZE_MAX && p_size < size) ||
-	    (q_size != SIZE_MAX && q_size < size))
-		fortify_panic(func);
+	if (p_size != SIZE_MAX && p_size < size)
+		fortify_panic(func, FORTIFY_WRITE, p_size, size, true);
+	else if (q_size != SIZE_MAX && q_size < size)
+		fortify_panic(func, FORTIFY_READ, q_size, size, true);
 
 	/*
 	 * Warn when writing beyond destination field size.
 	 *
-	 * We must ignore p_size_field == 0 for existing 0-element
-	 * fake flexible arrays, until they are all converted to
-	 * proper flexible arrays.
-	 *
-	 * The implementation of __builtin_*object_size() behaves
+	 * Note the implementation of __builtin_*object_size() behaves
 	 * like sizeof() when not directly referencing a flexible
 	 * array member, which means there will be many bounds checks
 	 * that will appear at run-time, without a way for them to be
@@ -561,13 +609,19 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 	 * is specifically the flexible array member).
 	 * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101832
 	 */
-	if (p_size_field != 0 && p_size_field != SIZE_MAX &&
+	if (p_size_field != SIZE_MAX &&
 	    p_size != p_size_field && p_size_field < size)
 		return true;
 
 	return false;
 }
 
+/*
+ * To work around what seems to be an optimizer bug, the macro arguments
+ * need to have const copies or the values end up changed by the time they
+ * reach fortify_warn_once(). See commit 6f7630b1b5bc ("fortify: Capture
+ * __bos() results in const temp vars") for more details.
+ */
 #define __fortify_memcpy_chk(p, q, size, p_size, q_size,		\
 			     p_size_field, q_size_field, op) ({		\
 	const size_t __fortify_size = (size_t)(size);			\
@@ -575,14 +629,20 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 	const size_t __q_size = (q_size);				\
 	const size_t __p_size_field = (p_size_field);			\
 	const size_t __q_size_field = (q_size_field);			\
-	WARN_ONCE(fortify_memcpy_chk(__fortify_size, __p_size,		\
+	/* Keep a mutable version of the size for the final copy. */	\
+	size_t __copy_size = __fortify_size;				\
+	fortify_warn_once(fortify_memcpy_chk(__fortify_size, __p_size,	\
 				     __q_size, __p_size_field,		\
-				     __q_size_field, #op),		\
+				     __q_size_field, FORTIFY_FUNC_ ##op), \
 		  #op ": detected field-spanning write (size %zu) of single %s (size %zu)\n", \
 		  __fortify_size,					\
-		  "field \"" #p "\" at " __FILE__ ":" __stringify(__LINE__), \
+		  "field \"" #p "\" at " FILE_LINE,			\
 		  __p_size_field);					\
-	__underlying_##op(p, q, __fortify_size);			\
+	/* Hide only the run-time size from value range tracking to */	\
+	/* silence compile-time false positive bounds warnings. */	\
+	if (!__builtin_constant_p(__copy_size))				\
+		OPTIMIZER_HIDE_VAR(__copy_size);			\
+	__underlying_##op(p, q, __copy_size);				\
 })
 
 /*
@@ -639,20 +699,20 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 extern void *__real_memscan(void *, int, __kernel_size_t) __RENAME(memscan);
 __FORTIFY_INLINE void *memscan(void * const POS0 p, int c, __kernel_size_t size)
 {
-	size_t p_size = __struct_size(p);
+	const size_t p_size = __struct_size(p);
 
 	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_memscan, FORTIFY_READ, p_size, size, NULL);
 	return __real_memscan(p, c, size);
 }
 
 __FORTIFY_INLINE __diagnose_as(__builtin_memcmp, 1, 2, 3)
 int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t size)
 {
-	size_t p_size = __struct_size(p);
-	size_t q_size = __struct_size(q);
+	const size_t p_size = __struct_size(p);
+	const size_t q_size = __struct_size(q);
 
 	if (__builtin_constant_p(size)) {
 		if (__compiletime_lessthan(p_size, size))
@@ -660,47 +720,51 @@ int memcmp(const void * const POS0 p, const void * const POS0 q, __kernel_size_t
 		if (__compiletime_lessthan(q_size, size))
 			__read_overflow2();
 	}
-	if (p_size < size || q_size < size)
-		fortify_panic(__func__);
+	if (p_size < size)
+		fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, p_size, size, INT_MIN);
+	else if (q_size < size)
+		fortify_panic(FORTIFY_FUNC_memcmp, FORTIFY_READ, q_size, size, INT_MIN);
 	return __underlying_memcmp(p, q, size);
 }
 
 __FORTIFY_INLINE __diagnose_as(__builtin_memchr, 1, 2, 3)
 void *memchr(const void * const POS0 p, int c, __kernel_size_t size)
 {
-	size_t p_size = __struct_size(p);
+	const size_t p_size = __struct_size(p);
 
 	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_memchr, FORTIFY_READ, p_size, size, NULL);
 	return __underlying_memchr(p, c, size);
 }
 
 void *__real_memchr_inv(const void *s, int c, size_t n) __RENAME(memchr_inv);
 __FORTIFY_INLINE void *memchr_inv(const void * const POS0 p, int c, size_t size)
 {
-	size_t p_size = __struct_size(p);
+	const size_t p_size = __struct_size(p);
 
 	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_memchr_inv, FORTIFY_READ, p_size, size, NULL);
 	return __real_memchr_inv(p, c, size);
 }
 
-extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup)
+extern void *__real_kmemdup(const void *src, size_t len, gfp_t gfp) __RENAME(kmemdup_noprof)
 								    __realloc_size(2);
-__FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp)
+__FORTIFY_INLINE void *kmemdup_noprof(const void * const POS0 p, size_t size, gfp_t gfp)
 {
-	size_t p_size = __struct_size(p);
+	const size_t p_size = __struct_size(p);
 
 	if (__compiletime_lessthan(p_size, size))
 		__read_overflow();
 	if (p_size < size)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_kmemdup, FORTIFY_READ, p_size, size,
+			      __real_kmemdup(p, 0, gfp));
 	return __real_kmemdup(p, size, gfp);
 }
+#define kmemdup(...)	alloc_hooks(kmemdup_noprof(__VA_ARGS__))
 
 /**
  * strcpy - Copy a string into another string buffer
@@ -720,8 +784,8 @@ __FORTIFY_INLINE void *kmemdup(const void * const POS0 p, size_t size, gfp_t gfp
 __FORTIFY_INLINE __diagnose_as(__builtin_strcpy, 1, 2)
 char *strcpy(char * const POS p, const char * const POS q)
 {
-	size_t p_size = __member_size(p);
-	size_t q_size = __member_size(q);
+	const size_t p_size = __member_size(p);
+	const size_t q_size = __member_size(q);
 	size_t size;
 
 	/* If neither buffer size is known, immediately give up. */
@@ -735,7 +799,7 @@ char *strcpy(char * const POS p, const char * const POS q)
 		__write_overflow();
 	/* Run-time check for dynamic size overflow. */
 	if (p_size < size)
-		fortify_panic(__func__);
+		fortify_panic(FORTIFY_FUNC_strcpy, FORTIFY_WRITE, p_size, size, p);
 	__underlying_memcpy(p, q, size);
 	return p;
 }
diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h
deleted file mode 100644
index 141ac3f251e6..000000000000
--- a/include/linux/fpga/adi-axi-common.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Analog Devices AXI common registers & definitions
- *
- * Copyright 2019 Analog Devices Inc.
- *
- * https://wiki.analog.com/resources/fpga/docs/axi_ip
- * https://wiki.analog.com/resources/fpga/docs/hdl/regmap
- */
-
-#ifndef ADI_AXI_COMMON_H_
-#define ADI_AXI_COMMON_H_
-
-#define ADI_AXI_REG_VERSION			0x0000
-
-#define ADI_AXI_PCORE_VER(major, minor, patch)	\
-	(((major) << 16) | ((minor) << 8) | (patch))
-
-#define ADI_AXI_PCORE_VER_MAJOR(version)	(((version) >> 16) & 0xff)
-#define ADI_AXI_PCORE_VER_MINOR(version)	(((version) >> 8) & 0xff)
-#define ADI_AXI_PCORE_VER_PATCH(version)	((version) & 0xff)
-
-#endif /* ADI_AXI_COMMON_H_ */
diff --git a/include/linux/fpga/fpga-bridge.h b/include/linux/fpga/fpga-bridge.h
index 223da48a6d18..94c4edd047e5 100644
--- a/include/linux/fpga/fpga-bridge.h
+++ b/include/linux/fpga/fpga-bridge.h
@@ -45,6 +45,7 @@ struct fpga_bridge_info {
  * @dev: FPGA bridge device
  * @mutex: enforces exclusive reference to bridge
  * @br_ops: pointer to struct of FPGA bridge ops
+ * @br_ops_owner: module containing the br_ops
  * @info: fpga image specific information
  * @node: FPGA bridge list node
  * @priv: low level driver private date
@@ -54,6 +55,7 @@ struct fpga_bridge {
 	struct device dev;
 	struct mutex mutex; /* for exclusive reference to bridge */
 	const struct fpga_bridge_ops *br_ops;
+	struct module *br_ops_owner;
 	struct fpga_image_info *info;
 	struct list_head node;
 	void *priv;
@@ -79,10 +81,12 @@ int of_fpga_bridge_get_to_list(struct device_node *np,
 			       struct fpga_image_info *info,
 			       struct list_head *bridge_list);
 
+#define fpga_bridge_register(parent, name, br_ops, priv) \
+	__fpga_bridge_register(parent, name, br_ops, priv, THIS_MODULE)
 struct fpga_bridge *
-fpga_bridge_register(struct device *parent, const char *name,
-		     const struct fpga_bridge_ops *br_ops,
-		     void *priv);
+__fpga_bridge_register(struct device *parent, const char *name,
+		       const struct fpga_bridge_ops *br_ops, void *priv,
+		       struct module *owner);
 void fpga_bridge_unregister(struct fpga_bridge *br);
 
 #endif /* _LINUX_FPGA_BRIDGE_H */
diff --git a/include/linux/fpga/fpga-mgr.h b/include/linux/fpga/fpga-mgr.h
index 54f63459efd6..0d4fe068f3d8 100644
--- a/include/linux/fpga/fpga-mgr.h
+++ b/include/linux/fpga/fpga-mgr.h
@@ -201,6 +201,7 @@ struct fpga_manager_ops {
  * @state: state of fpga manager
  * @compat_id: FPGA manager id for compatibility check.
  * @mops: pointer to struct of fpga manager ops
+ * @mops_owner: module containing the mops
  * @priv: low level driver private date
  */
 struct fpga_manager {
@@ -210,6 +211,7 @@ struct fpga_manager {
 	enum fpga_mgr_states state;
 	struct fpga_compat_id *compat_id;
 	const struct fpga_manager_ops *mops;
+	struct module *mops_owner;
 	void *priv;
 };
 
@@ -230,18 +232,30 @@ struct fpga_manager *fpga_mgr_get(struct device *dev);
 
 void fpga_mgr_put(struct fpga_manager *mgr);
 
+#define fpga_mgr_register_full(parent, info) \
+	__fpga_mgr_register_full(parent, info, THIS_MODULE)
 struct fpga_manager *
-fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info);
+__fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info,
+			 struct module *owner);
 
+#define fpga_mgr_register(parent, name, mops, priv) \
+	__fpga_mgr_register(parent, name, mops, priv, THIS_MODULE)
 struct fpga_manager *
-fpga_mgr_register(struct device *parent, const char *name,
-		  const struct fpga_manager_ops *mops, void *priv);
+__fpga_mgr_register(struct device *parent, const char *name,
+		    const struct fpga_manager_ops *mops, void *priv, struct module *owner);
+
 void fpga_mgr_unregister(struct fpga_manager *mgr);
 
+#define devm_fpga_mgr_register_full(parent, info) \
+	__devm_fpga_mgr_register_full(parent, info, THIS_MODULE)
 struct fpga_manager *
-devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info);
+__devm_fpga_mgr_register_full(struct device *parent, const struct fpga_manager_info *info,
+			      struct module *owner);
+#define devm_fpga_mgr_register(parent, name, mops, priv) \
+	__devm_fpga_mgr_register(parent, name, mops, priv, THIS_MODULE)
 struct fpga_manager *
-devm_fpga_mgr_register(struct device *parent, const char *name,
-		       const struct fpga_manager_ops *mops, void *priv);
+__devm_fpga_mgr_register(struct device *parent, const char *name,
+			 const struct fpga_manager_ops *mops, void *priv,
+			 struct module *owner);
 
 #endif /*_LINUX_FPGA_MGR_H */
diff --git a/include/linux/fpga/fpga-region.h b/include/linux/fpga/fpga-region.h
index 9d4d32909340..5fbc05fe70a6 100644
--- a/include/linux/fpga/fpga-region.h
+++ b/include/linux/fpga/fpga-region.h
@@ -36,6 +36,7 @@ struct fpga_region_info {
  * @mgr: FPGA manager
  * @info: FPGA image info
  * @compat_id: FPGA region id for compatibility check.
+ * @ops_owner: module containing the get_bridges function
  * @priv: private data
  * @get_bridges: optional function to get bridges to a list
  */
@@ -46,6 +47,7 @@ struct fpga_region {
 	struct fpga_manager *mgr;
 	struct fpga_image_info *info;
 	struct fpga_compat_id *compat_id;
+	struct module *ops_owner;
 	void *priv;
 	int (*get_bridges)(struct fpga_region *region);
 };
@@ -58,12 +60,17 @@ fpga_region_class_find(struct device *start, const void *data,
 
 int fpga_region_program_fpga(struct fpga_region *region);
 
+#define fpga_region_register_full(parent, info) \
+	__fpga_region_register_full(parent, info, THIS_MODULE)
 struct fpga_region *
-fpga_region_register_full(struct device *parent, const struct fpga_region_info *info);
+__fpga_region_register_full(struct device *parent, const struct fpga_region_info *info,
+			    struct module *owner);
 
+#define fpga_region_register(parent, mgr, get_bridges) \
+	__fpga_region_register(parent, mgr, get_bridges, THIS_MODULE)
 struct fpga_region *
-fpga_region_register(struct device *parent, struct fpga_manager *mgr,
-		     int (*get_bridges)(struct fpga_region *));
+__fpga_region_register(struct device *parent, struct fpga_manager *mgr,
+		       int (*get_bridges)(struct fpga_region *), struct module *owner);
 void fpga_region_unregister(struct fpga_region *region);
 
 #endif /* _FPGA_REGION_H */
diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index 47fefc7f363b..0a3bcd1718f3 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h
@@ -5,39 +5,69 @@
 
 #include <linux/compiler.h>
 #include <linux/ftrace.h>
-#include <linux/rethook.h>
+#include <linux/rcupdate.h>
+#include <linux/refcount.h>
+#include <linux/rhashtable.h>
+#include <linux/slab.h>
+
+struct fprobe;
+typedef int (*fprobe_entry_cb)(struct fprobe *fp, unsigned long entry_ip,
+			       unsigned long ret_ip, struct ftrace_regs *regs,
+			       void *entry_data);
+
+typedef void (*fprobe_exit_cb)(struct fprobe *fp, unsigned long entry_ip,
+			       unsigned long ret_ip, struct ftrace_regs *regs,
+			       void *entry_data);
+
+/**
+ * struct fprobe_hlist_node - address based hash list node for fprobe.
+ *
+ * @hlist: The hlist node for address search hash table.
+ * @addr: One of the probing address of @fp.
+ * @fp: The fprobe which owns this.
+ */
+struct fprobe_hlist_node {
+	struct rhlist_head	hlist;
+	unsigned long		addr;
+	struct fprobe		*fp;
+};
+
+/**
+ * struct fprobe_hlist - hash list nodes for fprobe.
+ *
+ * @hlist: The hlist node for existence checking hash table.
+ * @rcu: rcu_head for RCU deferred release.
+ * @fp: The fprobe which owns this fprobe_hlist.
+ * @size: The size of @array.
+ * @array: The fprobe_hlist_node for each address to probe.
+ */
+struct fprobe_hlist {
+	struct hlist_node		hlist;
+	struct rcu_head			rcu;
+	struct fprobe			*fp;
+	int				size;
+	struct fprobe_hlist_node	array[] __counted_by(size);
+};
 
 /**
  * struct fprobe - ftrace based probe.
- * @ops: The ftrace_ops.
+ *
  * @nmissed: The counter for missing events.
  * @flags: The status flag.
- * @rethook: The rethook data structure. (internal data)
  * @entry_data_size: The private data storage size.
- * @nr_maxactive: The max number of active functions.
  * @entry_handler: The callback function for function entry.
  * @exit_handler: The callback function for function exit.
+ * @hlist_array: The fprobe_hlist for fprobe search from IP hash table.
  */
 struct fprobe {
-#ifdef CONFIG_FUNCTION_TRACER
-	/*
-	 * If CONFIG_FUNCTION_TRACER is not set, CONFIG_FPROBE is disabled too.
-	 * But user of fprobe may keep embedding the struct fprobe on their own
-	 * code. To avoid build error, this will keep the fprobe data structure
-	 * defined here, but remove ftrace_ops data structure.
-	 */
-	struct ftrace_ops	ops;
-#endif
 	unsigned long		nmissed;
 	unsigned int		flags;
-	struct rethook		*rethook;
 	size_t			entry_data_size;
-	int			nr_maxactive;
 
-	int (*entry_handler)(struct fprobe *fp, unsigned long entry_ip,
-			     struct pt_regs *regs, void *entry_data);
-	void (*exit_handler)(struct fprobe *fp, unsigned long entry_ip,
-			     struct pt_regs *regs, void *entry_data);
+	fprobe_entry_cb entry_handler;
+	fprobe_exit_cb  exit_handler;
+
+	struct fprobe_hlist	*hlist_array;
 };
 
 /* This fprobe is soft-disabled. */
@@ -64,6 +94,8 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter
 int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num);
 int register_fprobe_syms(struct fprobe *fp, const char **syms, int num);
 int unregister_fprobe(struct fprobe *fp);
+bool fprobe_is_registered(struct fprobe *fp);
+int fprobe_count_ips_from_filter(const char *filter, const char *notfilter);
 #else
 static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
 {
@@ -81,6 +113,14 @@ static inline int unregister_fprobe(struct fprobe *fp)
 {
 	return -EOPNOTSUPP;
 }
+static inline bool fprobe_is_registered(struct fprobe *fp)
+{
+	return false;
+}
+static inline int fprobe_count_ips_from_filter(const char *filter, const char *notfilter)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 /**
@@ -108,4 +148,9 @@ static inline void enable_fprobe(struct fprobe *fp)
 		fp->flags &= ~FPROBE_FL_DISABLED;
 }
 
+/* The entry data size is 4 bits (=16) * sizeof(long) in maximum */
+#define FPROBE_DATA_SIZE_BITS		4
+#define MAX_FPROBE_DATA_SIZE_WORD	((1L << FPROBE_DATA_SIZE_BITS) - 1)
+#define MAX_FPROBE_DATA_SIZE		(MAX_FPROBE_DATA_SIZE_WORD * sizeof(long))
+
 #endif
diff --git a/include/linux/fpu.h b/include/linux/fpu.h
new file mode 100644
index 000000000000..2fb63e22913b
--- /dev/null
+++ b/include/linux/fpu.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_FPU_H
+#define _LINUX_FPU_H
+
+#ifdef _LINUX_FPU_COMPILATION_UNIT
+#error FP code must be compiled separately. See Documentation/core-api/floating-point.rst.
+#endif
+
+#include <asm/fpu.h>
+
+#endif
diff --git a/include/linux/framer/framer-provider.h b/include/linux/framer/framer-provider.h
new file mode 100644
index 000000000000..9724d4b44b9c
--- /dev/null
+++ b/include/linux/framer/framer-provider.h
@@ -0,0 +1,193 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer profider header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_PROVIDER_FRAMER_H
+#define __DRIVERS_PROVIDER_FRAMER_H
+
+#include <linux/export.h>
+#include <linux/framer/framer.h>
+#include <linux/types.h>
+
+#define FRAMER_FLAG_POLL_STATUS  BIT(0)
+
+/**
+ * struct framer_ops - set of function pointers for performing framer operations
+ * @init: operation to be performed for initializing the framer
+ * @exit: operation to be performed while exiting
+ * @power_on: powering on the framer
+ * @power_off: powering off the framer
+ * @flags: OR-ed flags (FRAMER_FLAG_*) to ask for core functionality
+ *          - @FRAMER_FLAG_POLL_STATUS:
+ *            Ask the core to perform a polling to get the framer status and
+ *            notify consumers on change.
+ *            The framer should call @framer_notify_status_change() when it
+ *            detects a status change. This is usually done using interrupts.
+ *            If the framer cannot detect this change, it can ask the core for
+ *            a status polling. The core will call @get_status() periodically
+ *            and, on change detected, it will notify the consumer.
+ *            the @get_status()
+ * @owner: the module owner containing the ops
+ */
+struct framer_ops {
+	int	(*init)(struct framer *framer);
+	void	(*exit)(struct framer *framer);
+	int	(*power_on)(struct framer *framer);
+	int	(*power_off)(struct framer *framer);
+
+	/**
+	 * @get_status:
+	 *
+	 * Optional.
+	 *
+	 * Used to get the framer status. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*get_status)(struct framer *framer, struct framer_status *status);
+
+	/**
+	 * @set_config:
+	 *
+	 * Optional.
+	 *
+	 * Used to set the framer configuration. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*set_config)(struct framer *framer, const struct framer_config *config);
+
+	/**
+	 * @get_config:
+	 *
+	 * Optional.
+	 *
+	 * Used to get the framer configuration. framer_init() must have
+	 * been called on the framer.
+	 *
+	 * Returns: 0 if successful, an negative error code otherwise
+	 */
+	int	(*get_config)(struct framer *framer, struct framer_config *config);
+
+	u32 flags;
+	struct module *owner;
+};
+
+/**
+ * struct framer_provider - represents the framer provider
+ * @dev: framer provider device
+ * @owner: the module owner having of_xlate
+ * @list: to maintain a linked list of framer providers
+ * @of_xlate: function pointer to obtain framer instance from framer pointer
+ */
+struct framer_provider {
+	struct device		*dev;
+	struct module		*owner;
+	struct list_head	list;
+	struct framer * (*of_xlate)(struct device *dev,
+				    const struct of_phandle_args *args);
+};
+
+static inline void framer_set_drvdata(struct framer *framer, void *data)
+{
+	dev_set_drvdata(&framer->dev, data);
+}
+
+static inline void *framer_get_drvdata(struct framer *framer)
+{
+	return dev_get_drvdata(&framer->dev);
+}
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+
+/* Create and destroy a framer */
+struct framer *framer_create(struct device *dev, struct device_node *node,
+			     const struct framer_ops *ops);
+void framer_destroy(struct framer *framer);
+
+/* devm version */
+struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+				  const struct framer_ops *ops);
+
+struct framer *framer_provider_simple_of_xlate(struct device *dev,
+					       const struct of_phandle_args *args);
+
+struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 const struct of_phandle_args *args));
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider);
+
+struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      const struct of_phandle_args *args));
+
+void framer_notify_status_change(struct framer *framer);
+
+#else /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+static inline struct framer *framer_create(struct device *dev, struct device_node *node,
+					   const struct framer_ops *ops)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void framer_destroy(struct framer *framer)
+{
+}
+
+/* devm version */
+static inline struct framer *devm_framer_create(struct device *dev, struct device_node *node,
+						const struct framer_ops *ops)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *framer_provider_simple_of_xlate(struct device *dev,
+							     const struct of_phandle_args *args)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer_provider *
+__framer_provider_of_register(struct device *dev, struct module *owner,
+			      struct framer *(*of_xlate)(struct device *dev,
+							 const struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_provider_of_unregister(struct framer_provider *framer_provider)
+{
+}
+
+static inline struct framer_provider *
+__devm_framer_provider_of_register(struct device *dev, struct module *owner,
+				   struct framer *(*of_xlate)(struct device *dev,
+							      const struct of_phandle_args *args))
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+void framer_notify_status_change(struct framer *framer)
+{
+}
+
+#endif /* IS_ENABLED(CONFIG_GENERIC_FRAMER) */
+
+#define framer_provider_of_register(dev, xlate)		\
+	__framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#define devm_framer_provider_of_register(dev, xlate)	\
+	__devm_framer_provider_of_register((dev), THIS_MODULE, (xlate))
+
+#endif /* __DRIVERS_PROVIDER_FRAMER_H */
diff --git a/include/linux/framer/framer.h b/include/linux/framer/framer.h
new file mode 100644
index 000000000000..2b85fe9e7f9a
--- /dev/null
+++ b/include/linux/framer/framer.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Generic framer header file
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+
+#ifndef __DRIVERS_FRAMER_H
+#define __DRIVERS_FRAMER_H
+
+#include <linux/err.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/device.h>
+#include <linux/workqueue.h>
+
+/**
+ * enum framer_iface - Framer interface
+ * @FRAMER_IFACE_E1: E1 interface
+ * @FRAMER_IFACE_T1: T1 interface
+ */
+enum framer_iface {
+	FRAMER_IFACE_E1,
+	FRAMER_IFACE_T1,
+};
+
+/**
+ * enum framer_clock_type - Framer clock type
+ * @FRAMER_CLOCK_EXT: External clock
+ * @FRAMER_CLOCK_INT: Internal clock
+ */
+enum framer_clock_type {
+	FRAMER_CLOCK_EXT,
+	FRAMER_CLOCK_INT,
+};
+
+/**
+ * struct framer_config - Framer configuration
+ * @iface: Framer line interface
+ * @clock_type: Framer clock type
+ * @line_clock_rate: Framer line clock rate
+ */
+struct framer_config {
+	enum framer_iface iface;
+	enum framer_clock_type clock_type;
+	unsigned long line_clock_rate;
+};
+
+/**
+ * struct framer_status - Framer status
+ * @link_is_on: Framer link state. true, the link is on, false, the link is off.
+ */
+struct framer_status {
+	bool link_is_on;
+};
+
+/**
+ * enum framer_event - Event available for notification
+ * @FRAMER_EVENT_STATUS: Event notified on framer_status changes
+ */
+enum framer_event {
+	FRAMER_EVENT_STATUS,
+};
+
+/**
+ * struct framer - represents the framer device
+ * @dev: framer device
+ * @id: id of the framer device
+ * @ops: function pointers for performing framer operations
+ * @mutex: mutex to protect framer_ops
+ * @init_count: used to protect when the framer is used by multiple consumers
+ * @power_count: used to protect when the framer is used by multiple consumers
+ * @pwr: power regulator associated with the framer
+ * @notify_status_work: work structure used for status notifications
+ * @notifier_list: notifier list used for notifications
+ * @polling_work: delayed work structure used for the polling task
+ * @prev_status: previous read status used by the polling task to detect changes
+ */
+struct framer {
+	struct device			dev;
+	int				id;
+	const struct framer_ops		*ops;
+	struct mutex			mutex;	/* Protect framer */
+	int				init_count;
+	int				power_count;
+	struct regulator		*pwr;
+	struct work_struct		notify_status_work;
+	struct blocking_notifier_head	notifier_list;
+	struct delayed_work		polling_work;
+	struct framer_status		prev_status;
+};
+
+#if IS_ENABLED(CONFIG_GENERIC_FRAMER)
+int framer_pm_runtime_get(struct framer *framer);
+int framer_pm_runtime_get_sync(struct framer *framer);
+int framer_pm_runtime_put(struct framer *framer);
+int framer_pm_runtime_put_sync(struct framer *framer);
+int framer_init(struct framer *framer);
+int framer_exit(struct framer *framer);
+int framer_power_on(struct framer *framer);
+int framer_power_off(struct framer *framer);
+int framer_get_status(struct framer *framer, struct framer_status *status);
+int framer_get_config(struct framer *framer, struct framer_config *config);
+int framer_set_config(struct framer *framer, const struct framer_config *config);
+int framer_notifier_register(struct framer *framer, struct notifier_block *nb);
+int framer_notifier_unregister(struct framer *framer, struct notifier_block *nb);
+
+struct framer *framer_get(struct device *dev, const char *con_id);
+void framer_put(struct device *dev, struct framer *framer);
+
+struct framer *devm_framer_get(struct device *dev, const char *con_id);
+struct framer *devm_framer_optional_get(struct device *dev, const char *con_id);
+#else
+static inline int framer_pm_runtime_get(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_get_sync(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_pm_runtime_put_sync(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_init(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_exit(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_power_on(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_power_off(struct framer *framer)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_get_status(struct framer *framer, struct framer_status *status)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_get_config(struct framer *framer, struct framer_config *config)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_set_config(struct framer *framer, const struct framer_config *config)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_notifier_register(struct framer *framer,
+					   struct notifier_block *nb)
+{
+	return -ENOSYS;
+}
+
+static inline int framer_notifier_unregister(struct framer *framer,
+					     struct notifier_block *nb)
+{
+	return -ENOSYS;
+}
+
+static inline struct framer *framer_get(struct device *dev, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline void framer_put(struct device *dev, struct framer *framer)
+{
+}
+
+static inline struct framer *devm_framer_get(struct device *dev, const char *con_id)
+{
+	return ERR_PTR(-ENOSYS);
+}
+
+static inline struct framer *devm_framer_optional_get(struct device *dev, const char *con_id)
+{
+	return NULL;
+}
+
+#endif
+
+#endif /* __DRIVERS_FRAMER_H */
diff --git a/include/linux/framer/pef2256.h b/include/linux/framer/pef2256.h
new file mode 100644
index 000000000000..71d80af58c40
--- /dev/null
+++ b/include/linux/framer/pef2256.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * PEF2256 consumer API
+ *
+ * Copyright 2023 CS GROUP France
+ *
+ * Author: Herve Codina <herve.codina@bootlin.com>
+ */
+#ifndef __PEF2256_H__
+#define __PEF2256_H__
+
+#include <linux/types.h>
+
+struct pef2256;
+struct regmap;
+
+/* Retrieve the PEF2256 regmap */
+struct regmap *pef2256_get_regmap(struct pef2256 *pef2256);
+
+/* PEF2256 hardware versions */
+enum pef2256_version {
+	PEF2256_VERSION_UNKNOWN,
+	PEF2256_VERSION_1_2,
+	PEF2256_VERSION_2_1,
+	PEF2256_VERSION_2_2,
+};
+
+/* Get the PEF2256 hardware version */
+enum pef2256_version pef2256_get_version(struct pef2256 *pef2256);
+
+#endif /* __PEF2256_H__ */
diff --git a/include/linux/freelist.h b/include/linux/freelist.h
deleted file mode 100644
index fc1842b96469..000000000000
--- a/include/linux/freelist.h
+++ /dev/null
@@ -1,129 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause */
-#ifndef FREELIST_H
-#define FREELIST_H
-
-#include <linux/atomic.h>
-
-/*
- * Copyright: cameron@moodycamel.com
- *
- * A simple CAS-based lock-free free list. Not the fastest thing in the world
- * under heavy contention, but simple and correct (assuming nodes are never
- * freed until after the free list is destroyed), and fairly speedy under low
- * contention.
- *
- * Adapted from: https://moodycamel.com/blog/2014/solving-the-aba-problem-for-lock-free-free-lists
- */
-
-struct freelist_node {
-	atomic_t		refs;
-	struct freelist_node	*next;
-};
-
-struct freelist_head {
-	struct freelist_node	*head;
-};
-
-#define REFS_ON_FREELIST 0x80000000
-#define REFS_MASK	 0x7FFFFFFF
-
-static inline void __freelist_add(struct freelist_node *node, struct freelist_head *list)
-{
-	/*
-	 * Since the refcount is zero, and nobody can increase it once it's
-	 * zero (except us, and we run only one copy of this method per node at
-	 * a time, i.e. the single thread case), then we know we can safely
-	 * change the next pointer of the node; however, once the refcount is
-	 * back above zero, then other threads could increase it (happens under
-	 * heavy contention, when the refcount goes to zero in between a load
-	 * and a refcount increment of a node in try_get, then back up to
-	 * something non-zero, then the refcount increment is done by the other
-	 * thread) -- so if the CAS to add the node to the actual list fails,
-	 * decrese the refcount and leave the add operation to the next thread
-	 * who puts the refcount back to zero (which could be us, hence the
-	 * loop).
-	 */
-	struct freelist_node *head = READ_ONCE(list->head);
-
-	for (;;) {
-		WRITE_ONCE(node->next, head);
-		atomic_set_release(&node->refs, 1);
-
-		if (!try_cmpxchg_release(&list->head, &head, node)) {
-			/*
-			 * Hmm, the add failed, but we can only try again when
-			 * the refcount goes back to zero.
-			 */
-			if (atomic_fetch_add_release(REFS_ON_FREELIST - 1, &node->refs) == 1)
-				continue;
-		}
-		return;
-	}
-}
-
-static inline void freelist_add(struct freelist_node *node, struct freelist_head *list)
-{
-	/*
-	 * We know that the should-be-on-freelist bit is 0 at this point, so
-	 * it's safe to set it using a fetch_add.
-	 */
-	if (!atomic_fetch_add_release(REFS_ON_FREELIST, &node->refs)) {
-		/*
-		 * Oh look! We were the last ones referencing this node, and we
-		 * know we want to add it to the free list, so let's do it!
-		 */
-		__freelist_add(node, list);
-	}
-}
-
-static inline struct freelist_node *freelist_try_get(struct freelist_head *list)
-{
-	struct freelist_node *prev, *next, *head = smp_load_acquire(&list->head);
-	unsigned int refs;
-
-	while (head) {
-		prev = head;
-		refs = atomic_read(&head->refs);
-		if ((refs & REFS_MASK) == 0 ||
-		    !atomic_try_cmpxchg_acquire(&head->refs, &refs, refs+1)) {
-			head = smp_load_acquire(&list->head);
-			continue;
-		}
-
-		/*
-		 * Good, reference count has been incremented (it wasn't at
-		 * zero), which means we can read the next and not worry about
-		 * it changing between now and the time we do the CAS.
-		 */
-		next = READ_ONCE(head->next);
-		if (try_cmpxchg_acquire(&list->head, &head, next)) {
-			/*
-			 * Yay, got the node. This means it was on the list,
-			 * which means should-be-on-freelist must be false no
-			 * matter the refcount (because nobody else knows it's
-			 * been taken off yet, it can't have been put back on).
-			 */
-			WARN_ON_ONCE(atomic_read(&head->refs) & REFS_ON_FREELIST);
-
-			/*
-			 * Decrease refcount twice, once for our ref, and once
-			 * for the list's ref.
-			 */
-			atomic_fetch_add(-2, &head->refs);
-
-			return head;
-		}
-
-		/*
-		 * OK, the head must have changed on us, but we still need to decrement
-		 * the refcount we increased.
-		 */
-		refs = atomic_fetch_add(-1, &prev->refs);
-		if (refs == REFS_ON_FREELIST + 1)
-			__freelist_add(prev, list);
-	}
-
-	return NULL;
-}
-
-#endif /* FREELIST_H */
diff --git a/include/linux/freezer.h b/include/linux/freezer.h
index b303472255be..0a8c6c4d1a82 100644
--- a/include/linux/freezer.h
+++ b/include/linux/freezer.h
@@ -22,14 +22,18 @@ extern bool pm_nosig_freezing;		/* PM nosig freezing in effect */
 extern unsigned int freeze_timeout_msecs;
 
 /*
- * Check if a process has been frozen
+ * Check if a process has been frozen for PM or cgroup1 freezer. Note that
+ * cgroup2 freezer uses the job control mechanism and does not interact with
+ * the PM freezer.
  */
 extern bool frozen(struct task_struct *p);
 
 extern bool freezing_slow_path(struct task_struct *p);
 
 /*
- * Check if there is a request to freeze a process
+ * Check if there is a request to freeze a task from PM or cgroup1 freezer.
+ * Note that cgroup2 freezer uses the job control mechanism and does not
+ * interact with the PM freezer.
  */
 static inline bool freezing(struct task_struct *p)
 {
@@ -47,6 +51,7 @@ extern int freeze_processes(void);
 extern int freeze_kernel_threads(void);
 extern void thaw_processes(void);
 extern void thaw_kernel_threads(void);
+extern void thaw_process(struct task_struct *p);
 
 static inline bool try_to_freeze(void)
 {
@@ -62,9 +67,9 @@ extern bool freeze_task(struct task_struct *p);
 extern bool set_freezable(void);
 
 #ifdef CONFIG_CGROUP_FREEZER
-extern bool cgroup_freezing(struct task_struct *task);
+extern bool cgroup1_freezing(struct task_struct *task);
 #else /* !CONFIG_CGROUP_FREEZER */
-static inline bool cgroup_freezing(struct task_struct *task)
+static inline bool cgroup1_freezing(struct task_struct *task)
 {
 	return false;
 }
@@ -80,6 +85,7 @@ static inline int freeze_processes(void) { return -ENOSYS; }
 static inline int freeze_kernel_threads(void) { return -ENOSYS; }
 static inline void thaw_processes(void) {}
 static inline void thaw_kernel_threads(void) {}
+static inline void thaw_process(struct task_struct *p) {}
 
 static inline bool try_to_freeze(void) { return false; }
 
diff --git a/include/linux/frontswap.h b/include/linux/frontswap.h
deleted file mode 100644
index a631bac12220..000000000000
--- a/include/linux/frontswap.h
+++ /dev/null
@@ -1,91 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FRONTSWAP_H
-#define _LINUX_FRONTSWAP_H
-
-#include <linux/swap.h>
-#include <linux/mm.h>
-#include <linux/bitops.h>
-#include <linux/jump_label.h>
-
-struct frontswap_ops {
-	void (*init)(unsigned); /* this swap type was just swapon'ed */
-	int (*store)(unsigned, pgoff_t, struct page *); /* store a page */
-	int (*load)(unsigned, pgoff_t, struct page *); /* load a page */
-	void (*invalidate_page)(unsigned, pgoff_t); /* page no longer needed */
-	void (*invalidate_area)(unsigned); /* swap type just swapoff'ed */
-};
-
-int frontswap_register_ops(const struct frontswap_ops *ops);
-
-extern void frontswap_init(unsigned type, unsigned long *map);
-extern int __frontswap_store(struct page *page);
-extern int __frontswap_load(struct page *page);
-extern void __frontswap_invalidate_page(unsigned, pgoff_t);
-extern void __frontswap_invalidate_area(unsigned);
-
-#ifdef CONFIG_FRONTSWAP
-extern struct static_key_false frontswap_enabled_key;
-
-static inline bool frontswap_enabled(void)
-{
-	return static_branch_unlikely(&frontswap_enabled_key);
-}
-
-static inline void frontswap_map_set(struct swap_info_struct *p,
-				     unsigned long *map)
-{
-	p->frontswap_map = map;
-}
-
-static inline unsigned long *frontswap_map_get(struct swap_info_struct *p)
-{
-	return p->frontswap_map;
-}
-#else
-/* all inline routines become no-ops and all externs are ignored */
-
-static inline bool frontswap_enabled(void)
-{
-	return false;
-}
-
-static inline void frontswap_map_set(struct swap_info_struct *p,
-				     unsigned long *map)
-{
-}
-
-static inline unsigned long *frontswap_map_get(struct swap_info_struct *p)
-{
-	return NULL;
-}
-#endif
-
-static inline int frontswap_store(struct page *page)
-{
-	if (frontswap_enabled())
-		return __frontswap_store(page);
-
-	return -1;
-}
-
-static inline int frontswap_load(struct page *page)
-{
-	if (frontswap_enabled())
-		return __frontswap_load(page);
-
-	return -1;
-}
-
-static inline void frontswap_invalidate_page(unsigned type, pgoff_t offset)
-{
-	if (frontswap_enabled())
-		__frontswap_invalidate_page(type, offset);
-}
-
-static inline void frontswap_invalidate_area(unsigned type)
-{
-	if (frontswap_enabled())
-		__frontswap_invalidate_area(type);
-}
-
-#endif /* _LINUX_FRONTSWAP_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c363f8687c7e..04ceeca12a0d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_FS_H
 #define _LINUX_FS_H
 
+#include <linux/fs/super.h>
+#include <linux/vfsdebug.h>
 #include <linux/linkage.h>
 #include <linux/wait_bit.h>
 #include <linux/kdev_t.h>
@@ -10,7 +12,6 @@
 #include <linux/stat.h>
 #include <linux/cache.h>
 #include <linux/list.h>
-#include <linux/list_lru.h>
 #include <linux/llist.h>
 #include <linux/radix-tree.h>
 #include <linux/xarray.h>
@@ -36,22 +37,23 @@
 #include <linux/uuid.h>
 #include <linux/errseq.h>
 #include <linux/ioprio.h>
-#include <linux/fs_types.h>
 #include <linux/build_bug.h>
 #include <linux/stddef.h>
 #include <linux/mount.h>
 #include <linux/cred.h>
 #include <linux/mnt_idmapping.h>
 #include <linux/slab.h>
+#include <linux/maple_tree.h>
+#include <linux/rw_hint.h>
+#include <linux/file_ref.h>
+#include <linux/unicode.h>
 
 #include <asm/byteorder.h>
 #include <uapi/linux/fs.h>
 
-struct backing_dev_info;
 struct bdi_writeback;
 struct bio;
 struct io_comp_batch;
-struct export_operations;
 struct fiemap_extent_info;
 struct hd_geometry;
 struct iovec;
@@ -65,16 +67,13 @@ struct vfsmount;
 struct cred;
 struct swap_info_struct;
 struct seq_file;
-struct workqueue_struct;
 struct iov_iter;
-struct fscrypt_info;
-struct fscrypt_operations;
-struct fsverity_info;
-struct fsverity_operations;
+struct fsnotify_mark_connector;
 struct fs_context;
 struct fs_parameter_spec;
-struct fileattr;
+struct file_kattr;
 struct iomap_ops;
+struct delegated_inode;
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
@@ -108,28 +107,28 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
  */
 
 /* file is open for reading */
-#define FMODE_READ		((__force fmode_t)0x1)
+#define FMODE_READ		((__force fmode_t)(1 << 0))
 /* file is open for writing */
-#define FMODE_WRITE		((__force fmode_t)0x2)
+#define FMODE_WRITE		((__force fmode_t)(1 << 1))
 /* file is seekable */
-#define FMODE_LSEEK		((__force fmode_t)0x4)
+#define FMODE_LSEEK		((__force fmode_t)(1 << 2))
 /* file can be accessed using pread */
-#define FMODE_PREAD		((__force fmode_t)0x8)
+#define FMODE_PREAD		((__force fmode_t)(1 << 3))
 /* file can be accessed using pwrite */
-#define FMODE_PWRITE		((__force fmode_t)0x10)
+#define FMODE_PWRITE		((__force fmode_t)(1 << 4))
 /* File is opened for execution with sys_execve / sys_uselib */
-#define FMODE_EXEC		((__force fmode_t)0x20)
-/* File is opened with O_NDELAY (only set for block devices) */
-#define FMODE_NDELAY		((__force fmode_t)0x40)
-/* File is opened with O_EXCL (only set for block devices) */
-#define FMODE_EXCL		((__force fmode_t)0x80)
-/* File is opened using open(.., 3, ..) and is writeable only for ioctls
-   (specialy hack for floppy.c) */
-#define FMODE_WRITE_IOCTL	((__force fmode_t)0x100)
+#define FMODE_EXEC		((__force fmode_t)(1 << 5))
+/* File writes are restricted (block device specific) */
+#define FMODE_WRITE_RESTRICTED	((__force fmode_t)(1 << 6))
+/* File supports atomic writes */
+#define FMODE_CAN_ATOMIC_WRITE	((__force fmode_t)(1 << 7))
+
+/* FMODE_* bit 8 */
+
 /* 32bit hashes as llseek() offset (for directories) */
-#define FMODE_32BITHASH         ((__force fmode_t)0x200)
+#define FMODE_32BITHASH         ((__force fmode_t)(1 << 9))
 /* 64bit hashes as llseek() offset (for directories) */
-#define FMODE_64BITHASH         ((__force fmode_t)0x400)
+#define FMODE_64BITHASH         ((__force fmode_t)(1 << 10))
 
 /*
  * Don't update ctime and mtime.
@@ -137,57 +136,85 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
  * Currently a special hack for the XFS open_by_handle ioctl, but we'll
  * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
  */
-#define FMODE_NOCMTIME		((__force fmode_t)0x800)
+#define FMODE_NOCMTIME		((__force fmode_t)(1 << 11))
 
 /* Expect random access pattern */
-#define FMODE_RANDOM		((__force fmode_t)0x1000)
+#define FMODE_RANDOM		((__force fmode_t)(1 << 12))
 
-/* File is huge (eg. /dev/mem): treat loff_t as unsigned */
-#define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)
+/* Supports IOCB_HAS_METADATA */
+#define FMODE_HAS_METADATA	((__force fmode_t)(1 << 13))
 
 /* File is opened with O_PATH; almost nothing can be done with it */
-#define FMODE_PATH		((__force fmode_t)0x4000)
+#define FMODE_PATH		((__force fmode_t)(1 << 14))
 
 /* File needs atomic accesses to f_pos */
-#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
+#define FMODE_ATOMIC_POS	((__force fmode_t)(1 << 15))
 /* Write access to underlying fs */
-#define FMODE_WRITER		((__force fmode_t)0x10000)
+#define FMODE_WRITER		((__force fmode_t)(1 << 16))
 /* Has read method(s) */
-#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
+#define FMODE_CAN_READ          ((__force fmode_t)(1 << 17))
 /* Has write method(s) */
-#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)
+#define FMODE_CAN_WRITE         ((__force fmode_t)(1 << 18))
 
-#define FMODE_OPENED		((__force fmode_t)0x80000)
-#define FMODE_CREATED		((__force fmode_t)0x100000)
+#define FMODE_OPENED		((__force fmode_t)(1 << 19))
+#define FMODE_CREATED		((__force fmode_t)(1 << 20))
 
 /* File is stream-like */
-#define FMODE_STREAM		((__force fmode_t)0x200000)
+#define FMODE_STREAM		((__force fmode_t)(1 << 21))
 
 /* File supports DIRECT IO */
-#define	FMODE_CAN_ODIRECT	((__force fmode_t)0x400000)
+#define	FMODE_CAN_ODIRECT	((__force fmode_t)(1 << 22))
 
-#define	FMODE_NOREUSE		((__force fmode_t)0x800000)
+#define	FMODE_NOREUSE		((__force fmode_t)(1 << 23))
 
-/* File supports non-exclusive O_DIRECT writes from multiple threads */
-#define FMODE_DIO_PARALLEL_WRITE	((__force fmode_t)0x1000000)
+/* File is embedded in backing_file object */
+#define FMODE_BACKING		((__force fmode_t)(1 << 24))
+
+/*
+ * Together with FMODE_NONOTIFY_PERM defines which fsnotify events shouldn't be
+ * generated (see below)
+ */
+#define FMODE_NONOTIFY		((__force fmode_t)(1 << 25))
 
-/* File was opened by fanotify and shouldn't generate fanotify events */
-#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)
+/*
+ * Together with FMODE_NONOTIFY defines which fsnotify events shouldn't be
+ * generated (see below)
+ */
+#define FMODE_NONOTIFY_PERM	((__force fmode_t)(1 << 26))
 
 /* File is capable of returning -EAGAIN if I/O will block */
-#define FMODE_NOWAIT		((__force fmode_t)0x8000000)
+#define FMODE_NOWAIT		((__force fmode_t)(1 << 27))
 
 /* File represents mount that needs unmounting */
-#define FMODE_NEED_UNMOUNT	((__force fmode_t)0x10000000)
+#define FMODE_NEED_UNMOUNT	((__force fmode_t)(1 << 28))
 
 /* File does not contribute to nr_files count */
-#define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)
+#define FMODE_NOACCOUNT		((__force fmode_t)(1 << 29))
 
-/* File supports async buffered reads */
-#define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)
-
-/* File supports async nowait buffered writes */
-#define FMODE_BUF_WASYNC	((__force fmode_t)0x80000000)
+/*
+ * The two FMODE_NONOTIFY* define which fsnotify events should not be generated
+ * for an open file. These are the possible values of
+ * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning:
+ *
+ * FMODE_NONOTIFY - suppress all (incl. non-permission) events.
+ * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events.
+ * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM.
+ */
+#define FMODE_FSNOTIFY_MASK \
+	(FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)
+
+#define FMODE_FSNOTIFY_NONE(mode) \
+	((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY)
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+#define FMODE_FSNOTIFY_HSM(mode) \
+	((mode & FMODE_FSNOTIFY_MASK) == 0 || \
+	 (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM))
+#define FMODE_FSNOTIFY_ACCESS_PERM(mode) \
+	((mode & FMODE_FSNOTIFY_MASK) == 0)
+#else
+#define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0
+#define FMODE_FSNOTIFY_HSM(mode)	0
+#endif
 
 /*
  * Attribute flags.  These should be or-ed together to figure out what
@@ -203,6 +230,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define ATTR_ATIME_SET	(1 << 7)
 #define ATTR_MTIME_SET	(1 << 8)
 #define ATTR_FORCE	(1 << 9) /* Not a change, but a change it */
+#define ATTR_CTIME_SET	(1 << 10)
 #define ATTR_KILL_SUID	(1 << 11)
 #define ATTR_KILL_SGID	(1 << 12)
 #define ATTR_FILE	(1 << 13)
@@ -210,6 +238,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
 #define ATTR_TIMES_SET	(1 << 16)
 #define ATTR_TOUCH	(1 << 17)
+#define ATTR_DELEG	(1 << 18) /* Delegated attrs. Don't break write delegations */
 
 /*
  * Whiteout is represented by a char device.  The following constants define the
@@ -264,11 +293,6 @@ struct iattr {
 };
 
 /*
- * Includes for diskquotas.
- */
-#include <linux/quota.h>
-
-/*
  * Maximum number of layers of fs stack.  Needs to be limited to
  * prevent kernel stack overflow
  */
@@ -313,25 +337,15 @@ struct address_space;
 struct writeback_control;
 struct readahead_control;
 
-/*
- * Write life time hint values.
- * Stored in struct inode as u8.
- */
-enum rw_hint {
-	WRITE_LIFE_NOT_SET	= 0,
-	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
-	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
-	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
-	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
-	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
-};
-
 /* Match RWF_* bits to IOCB bits */
 #define IOCB_HIPRI		(__force int) RWF_HIPRI
 #define IOCB_DSYNC		(__force int) RWF_DSYNC
 #define IOCB_SYNC		(__force int) RWF_SYNC
 #define IOCB_NOWAIT		(__force int) RWF_NOWAIT
 #define IOCB_APPEND		(__force int) RWF_APPEND
+#define IOCB_ATOMIC		(__force int) RWF_ATOMIC
+#define IOCB_DONTCACHE		(__force int) RWF_DONTCACHE
+#define IOCB_NOSIGNAL		(__force int) RWF_NOSIGNAL
 
 /* non-RWF related bits - start at 16 */
 #define IOCB_EVENTFD		(1 << 16)
@@ -342,6 +356,9 @@ enum rw_hint {
 #define IOCB_NOIO		(1 << 20)
 /* can use bio alloc cache */
 #define IOCB_ALLOC_CACHE	(1 << 21)
+/* kiocb is a read or write operation submitted by fs/aio.c. */
+#define IOCB_AIO_RW		(1 << 22)
+#define IOCB_HAS_METADATA	(1 << 23)
 
 /* for use in trace events */
 #define TRACE_IOCB_STRINGS \
@@ -350,12 +367,16 @@ enum rw_hint {
 	{ IOCB_SYNC,		"SYNC" }, \
 	{ IOCB_NOWAIT,		"NOWAIT" }, \
 	{ IOCB_APPEND,		"APPEND" }, \
+	{ IOCB_ATOMIC,		"ATOMIC" }, \
+	{ IOCB_DONTCACHE,	"DONTCACHE" }, \
 	{ IOCB_EVENTFD,		"EVENTFD"}, \
 	{ IOCB_DIRECT,		"DIRECT" }, \
 	{ IOCB_WRITE,		"WRITE" }, \
 	{ IOCB_WAITQ,		"WAITQ" }, \
 	{ IOCB_NOIO,		"NOIO" }, \
-	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }
+	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }, \
+	{ IOCB_AIO_RW,		"AIO_RW" }, \
+	{ IOCB_HAS_METADATA,	"AIO_HAS_METADATA" }
 
 struct kiocb {
 	struct file		*ki_filp;
@@ -364,7 +385,14 @@ struct kiocb {
 	void			*private;
 	int			ki_flags;
 	u16			ki_ioprio; /* See linux/ioprio.h */
-	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
+	u8			ki_write_stream;
+
+	/*
+	 * Only used for async buffered reads, where it denotes the page
+	 * waitqueue associated with completing the read.
+	 * Valid IFF IOCB_WAITQ is set.
+	 */
+	struct wait_page_queue	*ki_waitq;
 };
 
 static inline bool is_sync_kiocb(struct kiocb *kiocb)
@@ -373,7 +401,6 @@ static inline bool is_sync_kiocb(struct kiocb *kiocb)
 }
 
 struct address_space_operations {
-	int (*writepage)(struct page *page, struct writeback_control *wbc);
 	int (*read_folio)(struct file *, struct folio *);
 
 	/* Write back some dirty pages from this mapping. */
@@ -384,12 +411,12 @@ struct address_space_operations {
 
 	void (*readahead)(struct readahead_control *);
 
-	int (*write_begin)(struct file *, struct address_space *mapping,
+	int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata);
-	int (*write_end)(struct file *, struct address_space *mapping,
+				struct folio **foliop, void **fsdata);
+	int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata);
+				struct folio *folio, void *fsdata);
 
 	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
 	sector_t (*bmap)(struct address_space *, sector_t);
@@ -407,7 +434,7 @@ struct address_space_operations {
 	bool (*is_partially_uptodate) (struct folio *, size_t from,
 			size_t count);
 	void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
-	int (*error_remove_page)(struct address_space *, struct page *);
+	int (*error_remove_folio)(struct address_space *, struct folio *);
 
 	/* swapfile support */
 	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
@@ -427,7 +454,7 @@ extern const struct address_space_operations empty_aops;
  *   It is also used to block modification of page cache contents through
  *   memory mappings.
  * @gfp_mask: Memory allocation flags to use for allocating pages.
- * @i_mmap_writable: Number of VM_SHARED mappings.
+ * @i_mmap_writable: Number of VM_SHARED, VM_MAYWRITE mappings.
  * @nr_thps: Number of THPs in the pagecache (non-shmem only).
  * @i_mmap: Tree of private and shared mappings.
  * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
@@ -436,9 +463,9 @@ extern const struct address_space_operations empty_aops;
  * @a_ops: Methods.
  * @flags: Error bits and flags (AS_*).
  * @wb_err: The most recent error which has occurred.
- * @private_lock: For use by the owner of the address_space.
- * @private_list: For use by the owner of the address_space.
- * @private_data: For use by the owner of the address_space.
+ * @i_private_lock: For use by the owner of the address_space.
+ * @i_private_list: For use by the owner of the address_space.
+ * @i_private_data: For use by the owner of the address_space.
  */
 struct address_space {
 	struct inode		*host;
@@ -451,20 +478,20 @@ struct address_space {
 	atomic_t		nr_thps;
 #endif
 	struct rb_root_cached	i_mmap;
-	struct rw_semaphore	i_mmap_rwsem;
 	unsigned long		nrpages;
 	pgoff_t			writeback_index;
 	const struct address_space_operations *a_ops;
 	unsigned long		flags;
 	errseq_t		wb_err;
-	spinlock_t		private_lock;
-	struct list_head	private_list;
-	void			*private_data;
+	spinlock_t		i_private_lock;
+	struct list_head	i_private_list;
+	struct rw_semaphore	i_mmap_rwsem;
+	void *			i_private_data;
 } __attribute__((aligned(sizeof(long)))) __randomize_layout;
 	/*
 	 * On most architectures that alignment is already the case; but
 	 * must be enforced here for CRIS, to let the least significant bit
-	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
+	 * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON.
 	 */
 
 /* XArray tags, for tagging dirty and writeback pages in the pagecache. */
@@ -475,7 +502,7 @@ struct address_space {
 /*
  * Returns true if any of the pages in the mapping are marked with the tag.
  */
-static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
+static inline bool mapping_tagged(const struct address_space *mapping, xa_mark_t tag)
 {
 	return xa_marked(&mapping->i_pages, tag);
 }
@@ -523,21 +550,21 @@ static inline void i_mmap_assert_write_locked(struct address_space *mapping)
 /*
  * Might pages of this file be mapped into userspace?
  */
-static inline int mapping_mapped(struct address_space *mapping)
+static inline int mapping_mapped(const struct address_space *mapping)
 {
 	return	!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
 }
 
 /*
  * Might pages of this file have been modified in userspace?
- * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap
+ * Note that i_mmap_writable counts all VM_SHARED, VM_MAYWRITE vmas: do_mmap
  * marks vma as VM_SHARED if it is shared, and the file was opened for
  * writing i.e. vma may be mprotected writable even if now readonly.
  *
  * If i_mmap_writable is negative, no new writable mappings are allowed. You
  * can only deny writable mappings, if none exists right now.
  */
-static inline int mapping_writably_mapped(struct address_space *mapping)
+static inline int mapping_writably_mapped(const struct address_space *mapping)
 {
 	return atomic_read(&mapping->i_mmap_writable) > 0;
 }
@@ -596,13 +623,139 @@ is_uncached_acl(struct posix_acl *acl)
 	return (long)acl & 1;
 }
 
-#define IOP_FASTPERM	0x0001
-#define IOP_LOOKUP	0x0002
-#define IOP_NOFOLLOW	0x0004
-#define IOP_XATTR	0x0008
+#define IOP_FASTPERM		0x0001
+#define IOP_LOOKUP		0x0002
+#define IOP_NOFOLLOW		0x0004
+#define IOP_XATTR		0x0008
 #define IOP_DEFAULT_READLINK	0x0010
+#define IOP_MGTIME		0x0020
+#define IOP_CACHED_LINK		0x0040
+#define IOP_FASTPERM_MAY_EXEC	0x0080
 
-struct fsnotify_mark_connector;
+/*
+ * Inode state bits.  Protected by inode->i_lock
+ *
+ * Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
+ * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
+ *
+ * Four bits define the lifetime of an inode.  Initially, inodes are I_NEW,
+ * until that flag is cleared.  I_WILL_FREE, I_FREEING and I_CLEAR are set at
+ * various stages of removing an inode.
+ *
+ * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
+ *
+ * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
+ *			fdatasync() (unless I_DIRTY_DATASYNC is also set).
+ *			Timestamp updates are the usual cause.
+ * I_DIRTY_DATASYNC	Data-related inode changes pending.  We keep track of
+ *			these changes separately from I_DIRTY_SYNC so that we
+ *			don't have to write inode on fdatasync() when only
+ *			e.g. the timestamps have changed.
+ * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
+ * I_DIRTY_TIME		The inode itself has dirty timestamps, and the
+ *			lazytime mount option is enabled.  We keep track of this
+ *			separately from I_DIRTY_SYNC in order to implement
+ *			lazytime.  This gets cleared if I_DIRTY_INODE
+ *			(I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
+ *			I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
+ *			in place because writeback might already be in progress
+ *			and we don't want to lose the time update
+ * I_NEW		Serves as both a mutex and completion notification.
+ *			New inodes set I_NEW.  If two processes both create
+ *			the same inode, one of them will release its inode and
+ *			wait for I_NEW to be released before returning.
+ *			Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
+ *			also cause waiting on I_NEW, without I_NEW actually
+ *			being set.  find_inode() uses this to prevent returning
+ *			nearly-dead inodes.
+ * I_WILL_FREE		Must be set when calling write_inode_now() if i_count
+ *			is zero.  I_FREEING must be set when I_WILL_FREE is
+ *			cleared.
+ * I_FREEING		Set when inode is about to be freed but still has dirty
+ *			pages or buffers attached or the inode itself is still
+ *			dirty.
+ * I_CLEAR		Added by clear_inode().  In this state the inode is
+ *			clean and can be destroyed.  Inode keeps I_FREEING.
+ *
+ *			Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
+ *			prohibited for many purposes.  iget() must wait for
+ *			the inode to be completely released, then create it
+ *			anew.  Other functions will just ignore such inodes,
+ *			if appropriate.  I_NEW is used for waiting.
+ *
+ * I_SYNC		Writeback of inode is running. The bit is set during
+ *			data writeback, and cleared with a wakeup on the bit
+ *			address once it is done. The bit is also used to pin
+ *			the inode in memory for flusher thread.
+ *
+ * I_REFERENCED		Marks the inode as recently references on the LRU list.
+ *
+ * I_WB_SWITCH		Cgroup bdi_writeback switching in progress.  Used to
+ *			synchronize competing switching instances and to tell
+ *			wb stat updates to grab the i_pages lock.  See
+ *			inode_switch_wbs_work_fn() for details.
+ *
+ * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
+ *			and work dirs among overlayfs mounts.
+ *
+ * I_CREATING		New object's inode in the middle of setting up.
+ *
+ * I_DONTCACHE		Evict inode as soon as it is not used anymore.
+ *
+ * I_SYNC_QUEUED	Inode is queued in b_io or b_more_io writeback lists.
+ *			Used to detect that mark_inode_dirty() should not move
+ *			inode between dirty lists.
+ *
+ * I_PINNING_FSCACHE_WB	Inode is pinning an fscache object for writeback.
+ *
+ * I_LRU_ISOLATING	Inode is pinned being isolated from LRU without holding
+ *			i_count.
+ *
+ * Q: What is the difference between I_WILL_FREE and I_FREEING?
+ *
+ * __I_{SYNC,NEW,LRU_ISOLATING} are used to derive unique addresses to wait
+ * upon. There's one free address left.
+ */
+
+enum inode_state_bits {
+	__I_NEW			= 0U,
+	__I_SYNC		= 1U,
+	__I_LRU_ISOLATING	= 2U
+	/* reserved wait address bit 3 */
+};
+
+enum inode_state_flags_enum {
+	I_NEW			= (1U << __I_NEW),
+	I_SYNC			= (1U << __I_SYNC),
+	I_LRU_ISOLATING         = (1U << __I_LRU_ISOLATING),
+	/* reserved flag bit 3 */
+	I_DIRTY_SYNC		= (1U << 4),
+	I_DIRTY_DATASYNC	= (1U << 5),
+	I_DIRTY_PAGES		= (1U << 6),
+	I_WILL_FREE		= (1U << 7),
+	I_FREEING		= (1U << 8),
+	I_CLEAR			= (1U << 9),
+	I_REFERENCED		= (1U << 10),
+	I_LINKABLE		= (1U << 11),
+	I_DIRTY_TIME		= (1U << 12),
+	I_WB_SWITCH		= (1U << 13),
+	I_OVL_INUSE		= (1U << 14),
+	I_CREATING		= (1U << 15),
+	I_DONTCACHE		= (1U << 16),
+	I_SYNC_QUEUED		= (1U << 17),
+	I_PINNING_NETFS_WB	= (1U << 18)
+};
+
+#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
+#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
+#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
+
+/*
+ * Use inode_state_read() & friends to access.
+ */
+struct inode_state_flags {
+	enum inode_state_flags_enum __state;
+};
 
 /*
  * Keep mostly read-only and often accessed (especially for
@@ -612,14 +765,13 @@ struct fsnotify_mark_connector;
 struct inode {
 	umode_t			i_mode;
 	unsigned short		i_opflags;
-	kuid_t			i_uid;
-	kgid_t			i_gid;
 	unsigned int		i_flags;
-
 #ifdef CONFIG_FS_POSIX_ACL
 	struct posix_acl	*i_acl;
 	struct posix_acl	*i_default_acl;
 #endif
+	kuid_t			i_uid;
+	kgid_t			i_gid;
 
 	const struct inode_operations	*i_op;
 	struct super_block	*i_sb;
@@ -644,13 +796,17 @@ struct inode {
 	};
 	dev_t			i_rdev;
 	loff_t			i_size;
-	struct timespec64	i_atime;
-	struct timespec64	i_mtime;
-	struct timespec64	i_ctime;
+	time64_t		i_atime_sec;
+	time64_t		i_mtime_sec;
+	time64_t		i_ctime_sec;
+	u32			i_atime_nsec;
+	u32			i_mtime_nsec;
+	u32			i_ctime_nsec;
+	u32			i_generation;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
 	unsigned short          i_bytes;
 	u8			i_blkbits;
-	u8			i_write_hint;
+	enum rw_hint		i_write_hint;
 	blkcnt_t		i_blocks;
 
 #ifdef __NEED_I_SIZE_ORDERED
@@ -658,7 +814,8 @@ struct inode {
 #endif
 
 	/* Misc */
-	unsigned long		i_state;
+	struct inode_state_flags i_state;
+	/* 32-bit hole */
 	struct rw_semaphore	i_rwsem;
 
 	unsigned long		dirtied_when;	/* jiffies of first dirtying */
@@ -695,7 +852,10 @@ struct inode {
 	};
 	struct file_lock_context	*i_flctx;
 	struct address_space	i_data;
-	struct list_head	i_devices;
+	union {
+		struct list_head	i_devices;
+		int			i_linklen;
+	};
 	union {
 		struct pipe_inode_info	*i_pipe;
 		struct cdev		*i_cdev;
@@ -703,24 +863,114 @@ struct inode {
 		unsigned		i_dir_seq;
 	};
 
-	__u32			i_generation;
 
 #ifdef CONFIG_FSNOTIFY
 	__u32			i_fsnotify_mask; /* all events this inode cares about */
+	/* 32-bit hole reserved for expanding i_fsnotify_mask */
 	struct fsnotify_mark_connector __rcu	*i_fsnotify_marks;
 #endif
 
-#ifdef CONFIG_FS_ENCRYPTION
-	struct fscrypt_info	*i_crypt_info;
-#endif
-
-#ifdef CONFIG_FS_VERITY
-	struct fsverity_info	*i_verity_info;
-#endif
-
 	void			*i_private; /* fs or device private pointer */
 } __randomize_layout;
 
+/*
+ * i_state handling
+ *
+ * We hide all of it behind helpers so that we can validate consumers.
+ */
+static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode)
+{
+	return READ_ONCE(inode->i_state.__state);
+}
+
+static inline enum inode_state_flags_enum inode_state_read(struct inode *inode)
+{
+	lockdep_assert_held(&inode->i_lock);
+	return inode->i_state.__state;
+}
+
+static inline void inode_state_set_raw(struct inode *inode,
+				       enum inode_state_flags_enum flags)
+{
+	WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags);
+}
+
+static inline void inode_state_set(struct inode *inode,
+				   enum inode_state_flags_enum flags)
+{
+	lockdep_assert_held(&inode->i_lock);
+	inode_state_set_raw(inode, flags);
+}
+
+static inline void inode_state_clear_raw(struct inode *inode,
+					 enum inode_state_flags_enum flags)
+{
+	WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags);
+}
+
+static inline void inode_state_clear(struct inode *inode,
+				     enum inode_state_flags_enum flags)
+{
+	lockdep_assert_held(&inode->i_lock);
+	inode_state_clear_raw(inode, flags);
+}
+
+static inline void inode_state_assign_raw(struct inode *inode,
+					  enum inode_state_flags_enum flags)
+{
+	WRITE_ONCE(inode->i_state.__state, flags);
+}
+
+static inline void inode_state_assign(struct inode *inode,
+				      enum inode_state_flags_enum flags)
+{
+	lockdep_assert_held(&inode->i_lock);
+	inode_state_assign_raw(inode, flags);
+}
+
+static inline void inode_state_replace_raw(struct inode *inode,
+					   enum inode_state_flags_enum clearflags,
+					   enum inode_state_flags_enum setflags)
+{
+	enum inode_state_flags_enum flags;
+	flags = inode->i_state.__state;
+	flags &= ~clearflags;
+	flags |= setflags;
+	inode_state_assign_raw(inode, flags);
+}
+
+static inline void inode_state_replace(struct inode *inode,
+				       enum inode_state_flags_enum clearflags,
+				       enum inode_state_flags_enum setflags)
+{
+	lockdep_assert_held(&inode->i_lock);
+	inode_state_replace_raw(inode, clearflags, setflags);
+}
+
+static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen)
+{
+	VFS_WARN_ON_INODE(strlen(link) != linklen, inode);
+	VFS_WARN_ON_INODE(inode->i_opflags & IOP_CACHED_LINK, inode);
+	inode->i_link = link;
+	inode->i_linklen = linklen;
+	inode->i_opflags |= IOP_CACHED_LINK;
+}
+
+/*
+ * Get bit address from inode->i_state to use with wait_var_event()
+ * infrastructre.
+ */
+#define inode_state_wait_address(inode, bit) ((char *)&(inode)->i_state + (bit))
+
+struct wait_queue_head *inode_bit_waitqueue(struct wait_bit_queue_entry *wqe,
+					    struct inode *inode, u32 bit);
+
+static inline void inode_wake_up_bit(struct inode *inode, u32 bit)
+{
+	/* Caller is responsible for correct memory barriers. */
+	wake_up_var(inode_state_wait_address(inode, bit));
+}
+
 struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode);
 
 static inline unsigned int i_blocksize(const struct inode *node)
@@ -744,8 +994,10 @@ static inline void inode_fake_hash(struct inode *inode)
 	hlist_add_fake(&inode->i_hash);
 }
 
+void wait_on_new_inode(struct inode *inode);
+
 /*
- * inode->i_mutex nesting subclasses for the lock validator:
+ * inode->i_rwsem nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
  * 1: parent
@@ -775,6 +1027,11 @@ static inline void inode_lock(struct inode *inode)
 	down_write(&inode->i_rwsem);
 }
 
+static inline __must_check int inode_lock_killable(struct inode *inode)
+{
+	return down_write_killable(&inode->i_rwsem);
+}
+
 static inline void inode_unlock(struct inode *inode)
 {
 	up_write(&inode->i_rwsem);
@@ -785,6 +1042,11 @@ static inline void inode_lock_shared(struct inode *inode)
 	down_read(&inode->i_rwsem);
 }
 
+static inline __must_check int inode_lock_shared_killable(struct inode *inode)
+{
+	return down_read_killable(&inode->i_rwsem);
+}
+
 static inline void inode_unlock_shared(struct inode *inode)
 {
 	up_read(&inode->i_rwsem);
@@ -880,13 +1142,14 @@ static inline loff_t i_size_read(const struct inode *inode)
 	preempt_enable();
 	return i_size;
 #else
-	return inode->i_size;
+	/* Pairs with smp_store_release() in i_size_write() */
+	return smp_load_acquire(&inode->i_size);
 #endif
 }
 
 /*
  * NOTE: unlike i_size_read(), i_size_write() does need locking around it
- * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
+ * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount
  * can be lost, resulting in subsequent i_size_read() calls spinning forever.
  */
 static inline void i_size_write(struct inode *inode, loff_t i_size)
@@ -902,7 +1165,12 @@ static inline void i_size_write(struct inode *inode, loff_t i_size)
 	inode->i_size = i_size;
 	preempt_enable();
 #else
-	inode->i_size = i_size;
+	/*
+	 * Pairs with smp_load_acquire() in i_size_read() to ensure
+	 * changes related to inode size (such as page contents) are
+	 * visible before we see the changed inode size.
+	 */
+	smp_store_release(&inode->i_size, i_size);
 #endif
 }
 
@@ -917,6 +1185,7 @@ static inline unsigned imajor(const struct inode *inode)
 }
 
 struct fown_struct {
+	struct file *file;	/* backpointer for security modules */
 	rwlock_t lock;          /* protects pid, uid, euid fields */
 	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
 	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
@@ -932,6 +1201,7 @@ struct fown_struct {
  *      and so were/are genuinely "ahead".  Start next readahead when
  *      the first of these pages is accessed.
  * @ra_pages: Maximum size of a readahead request, copied from the bdi.
+ * @order: Preferred folio order used for most recent readahead.
  * @mmap_miss: How many mmap accesses missed in the page cache.
  * @prev_pos: The last byte in the most recent read request.
  *
@@ -943,7 +1213,8 @@ struct file_ra_state {
 	unsigned int size;
 	unsigned int async_size;
 	unsigned int ra_pages;
-	unsigned int mmap_miss;
+	unsigned short order;
+	unsigned short mmap_miss;
 	loff_t prev_pos;
 };
 
@@ -956,44 +1227,74 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 		index <  ra->start + ra->size);
 }
 
+/**
+ * struct file - Represents a file
+ * @f_lock: Protects f_ep, f_flags. Must not be taken from IRQ context.
+ * @f_mode: FMODE_* flags often used in hotpaths
+ * @f_op: file operations
+ * @f_mapping: Contents of a cacheable, mappable object.
+ * @private_data: filesystem or driver specific data
+ * @f_inode: cached inode
+ * @f_flags: file flags
+ * @f_iocb_flags: iocb flags
+ * @f_cred: stashed credentials of creator/opener
+ * @f_owner: file owner
+ * @f_path: path of the file
+ * @__f_path: writable alias for @f_path; *ONLY* for core VFS and only before
+ *   the file gets open
+ * @f_pos_lock: lock protecting file position
+ * @f_pipe: specific to pipes
+ * @f_pos: file position
+ * @f_security: LSM security context of this file
+ * @f_wb_err: writeback error
+ * @f_sb_err: per sb writeback errors
+ * @f_ep: link of all epoll hooks for this file
+ * @f_task_work: task work entry point
+ * @f_llist: work queue entrypoint
+ * @f_ra: file's readahead state
+ * @f_freeptr: Pointer used by SLAB_TYPESAFE_BY_RCU file cache (don't touch.)
+ * @f_ref: reference count
+ */
 struct file {
+	spinlock_t			f_lock;
+	fmode_t				f_mode;
+	const struct file_operations	*f_op;
+	struct address_space		*f_mapping;
+	void				*private_data;
+	struct inode			*f_inode;
+	unsigned int			f_flags;
+	unsigned int			f_iocb_flags;
+	const struct cred		*f_cred;
+	struct fown_struct		*f_owner;
+	/* --- cacheline 1 boundary (64 bytes) --- */
 	union {
-		struct llist_node	f_llist;
-		struct rcu_head 	f_rcuhead;
-		unsigned int 		f_iocb_flags;
+		const struct path	f_path;
+		struct path		__f_path;
 	};
-	struct path		f_path;
-	struct inode		*f_inode;	/* cached value */
-	const struct file_operations	*f_op;
-
-	/*
-	 * Protects f_ep, f_flags.
-	 * Must not be taken from IRQ context.
-	 */
-	spinlock_t		f_lock;
-	atomic_long_t		f_count;
-	unsigned int 		f_flags;
-	fmode_t			f_mode;
-	struct mutex		f_pos_lock;
-	loff_t			f_pos;
-	struct fown_struct	f_owner;
-	const struct cred	*f_cred;
-	struct file_ra_state	f_ra;
-
-	u64			f_version;
+	union {
+		/* regular files (with FMODE_ATOMIC_POS) and directories */
+		struct mutex		f_pos_lock;
+		/* pipes */
+		u64			f_pipe;
+	};
+	loff_t				f_pos;
 #ifdef CONFIG_SECURITY
-	void			*f_security;
+	void				*f_security;
 #endif
-	/* needed for tty driver, and maybe others */
-	void			*private_data;
-
+	/* --- cacheline 2 boundary (128 bytes) --- */
+	errseq_t			f_wb_err;
+	errseq_t			f_sb_err;
 #ifdef CONFIG_EPOLL
-	/* Used by fs/eventpoll.c to link all the hooks to this file */
-	struct hlist_head	*f_ep;
-#endif /* #ifdef CONFIG_EPOLL */
-	struct address_space	*f_mapping;
-	errseq_t		f_wb_err;
-	errseq_t		f_sb_err; /* for syncfs */
+	struct hlist_head		*f_ep;
+#endif
+	union {
+		struct callback_head	f_task_work;
+		struct llist_node	f_llist;
+		struct file_ra_state	f_ra;
+		freeptr_t		f_freeptr;
+	};
+	file_ref_t			f_ref;
+	/* --- cacheline 3 boundary (192 bytes) --- */
 } __randomize_layout
   __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */
 
@@ -1001,16 +1302,19 @@ struct file_handle {
 	__u32 handle_bytes;
 	int handle_type;
 	/* file identifier */
-	unsigned char f_handle[];
+	unsigned char f_handle[] __counted_by(handle_bytes);
 };
 
 static inline struct file *get_file(struct file *f)
 {
-	atomic_long_inc(&f->f_count);
+	file_ref_inc(&f->f_ref);
 	return f;
 }
-#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
-#define file_count(x)	atomic_long_read(&(x)->f_count)
+
+struct file *get_file_rcu(struct file __rcu **f);
+struct file *get_file_active(struct file **f);
+
+#define file_count(f)	file_ref_read(&(f)->f_ref)
 
 #define	MAX_NON_LFS	((1UL<<31) - 1)
 
@@ -1026,6 +1330,7 @@ static inline struct file *get_file(struct file *f)
 typedef void *fl_owner_t;
 
 struct file_lock;
+struct file_lease;
 
 /* The following constant reflects the upper bound of the file/locking space */
 #ifndef OFFSET_MAX
@@ -1033,6 +1338,12 @@ struct file_lock;
 #define OFFT_OFFSET_MAX	type_max(off_t)
 #endif
 
+int file_f_owner_allocate(struct file *file);
+static inline struct fown_struct *file_f_owner(const struct file *file)
+{
+	return READ_ONCE(file->f_owner);
+}
+
 extern void send_sigio(struct fown_struct *fown, int fd, int band);
 
 static inline struct inode *file_inode(const struct file *f)
@@ -1040,9 +1351,20 @@ static inline struct inode *file_inode(const struct file *f)
 	return f->f_inode;
 }
 
+/*
+ * file_dentry() is a relic from the days that overlayfs was using files with a
+ * "fake" path, meaning, f_path on overlayfs and f_inode on underlying fs.
+ * In those days, file_dentry() was needed to get the underlying fs dentry that
+ * matches f_inode.
+ * Files with "fake" path should not exist nowadays, so use an assertion to make
+ * sure that file_dentry() was not papering over filesystem bugs.
+ */
 static inline struct dentry *file_dentry(const struct file *file)
 {
-	return d_real(file->f_path.dentry, file_inode(file));
+	struct dentry *dentry = file->f_path.dentry;
+
+	WARN_ON_ONCE(d_inode(dentry) != file_inode(file));
+	return dentry;
 }
 
 struct fasync_struct {
@@ -1067,44 +1389,10 @@ extern void fasync_free(struct fasync_struct *);
 extern void kill_fasync(struct fasync_struct **, int, int);
 
 extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
-extern int f_setown(struct file *filp, unsigned long arg, int force);
+extern int f_setown(struct file *filp, int who, int force);
 extern void f_delown(struct file *filp);
 extern pid_t f_getown(struct file *filp);
-extern int send_sigurg(struct fown_struct *fown);
-
-/*
- * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
- * represented in both.
- */
-#define SB_RDONLY       BIT(0)	/* Mount read-only */
-#define SB_NOSUID       BIT(1)	/* Ignore suid and sgid bits */
-#define SB_NODEV        BIT(2)	/* Disallow access to device special files */
-#define SB_NOEXEC       BIT(3)	/* Disallow program execution */
-#define SB_SYNCHRONOUS  BIT(4)	/* Writes are synced at once */
-#define SB_MANDLOCK     BIT(6)	/* Allow mandatory locks on an FS */
-#define SB_DIRSYNC      BIT(7)	/* Directory modifications are synchronous */
-#define SB_NOATIME      BIT(10)	/* Do not update access times. */
-#define SB_NODIRATIME   BIT(11)	/* Do not update directory access times */
-#define SB_SILENT       BIT(15)
-#define SB_POSIXACL     BIT(16)	/* VFS does not apply the umask */
-#define SB_INLINECRYPT  BIT(17)	/* Use blk-crypto for encrypted files */
-#define SB_KERNMOUNT    BIT(22)	/* this is a kern_mount call */
-#define SB_I_VERSION    BIT(23)	/* Update inode I_version field */
-#define SB_LAZYTIME     BIT(25)	/* Update the on-disk [acm]times lazily */
-
-/* These sb flags are internal to the kernel */
-#define SB_SUBMOUNT     BIT(26)
-#define SB_FORCE        BIT(27)
-#define SB_NOSEC        BIT(28)
-#define SB_BORN         BIT(29)
-#define SB_ACTIVE       BIT(30)
-#define SB_NOUSER       BIT(31)
-
-/* These flags relate to encoding and casefolding */
-#define SB_ENC_STRICT_MODE_FL	(1 << 0)
-
-#define sb_has_strict_encoding(sb) \
-	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+extern int send_sigurg(struct file *file);
 
 /*
  *	Umount options
@@ -1116,174 +1404,6 @@ extern int send_sigurg(struct fown_struct *fown);
 #define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
 #define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */
 
-/* sb->s_iflags */
-#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
-#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
-#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
-#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
-
-/* sb->s_iflags to limit user namespace mounts */
-#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
-#define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
-#define SB_I_UNTRUSTED_MOUNTER		0x00000040
-
-#define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
-#define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
-#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
-#define SB_I_RETIRED	0x00000800	/* superblock shouldn't be reused */
-
-/* Possible states of 'frozen' field */
-enum {
-	SB_UNFROZEN = 0,		/* FS is unfrozen */
-	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
-	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
-	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
-					 * internal threads if needed) */
-	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
-};
-
-#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
-
-struct sb_writers {
-	int				frozen;		/* Is sb frozen? */
-	wait_queue_head_t		wait_unfrozen;	/* wait for thaw */
-	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
-};
-
-struct super_block {
-	struct list_head	s_list;		/* Keep this first */
-	dev_t			s_dev;		/* search index; _not_ kdev_t */
-	unsigned char		s_blocksize_bits;
-	unsigned long		s_blocksize;
-	loff_t			s_maxbytes;	/* Max file size */
-	struct file_system_type	*s_type;
-	const struct super_operations	*s_op;
-	const struct dquot_operations	*dq_op;
-	const struct quotactl_ops	*s_qcop;
-	const struct export_operations *s_export_op;
-	unsigned long		s_flags;
-	unsigned long		s_iflags;	/* internal SB_I_* flags */
-	unsigned long		s_magic;
-	struct dentry		*s_root;
-	struct rw_semaphore	s_umount;
-	int			s_count;
-	atomic_t		s_active;
-#ifdef CONFIG_SECURITY
-	void                    *s_security;
-#endif
-	const struct xattr_handler **s_xattr;
-#ifdef CONFIG_FS_ENCRYPTION
-	const struct fscrypt_operations	*s_cop;
-	struct fscrypt_keyring	*s_master_keys; /* master crypto keys in use */
-#endif
-#ifdef CONFIG_FS_VERITY
-	const struct fsverity_operations *s_vop;
-#endif
-#if IS_ENABLED(CONFIG_UNICODE)
-	struct unicode_map *s_encoding;
-	__u16 s_encoding_flags;
-#endif
-	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
-	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
-	struct block_device	*s_bdev;
-	struct backing_dev_info *s_bdi;
-	struct mtd_info		*s_mtd;
-	struct hlist_node	s_instances;
-	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
-	struct quota_info	s_dquot;	/* Diskquota specific options */
-
-	struct sb_writers	s_writers;
-
-	/*
-	 * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
-	 * s_fsnotify_marks together for cache efficiency. They are frequently
-	 * accessed and rarely modified.
-	 */
-	void			*s_fs_info;	/* Filesystem private info */
-
-	/* Granularity of c/m/atime in ns (cannot be worse than a second) */
-	u32			s_time_gran;
-	/* Time limits for c/m/atime in seconds */
-	time64_t		   s_time_min;
-	time64_t		   s_time_max;
-#ifdef CONFIG_FSNOTIFY
-	__u32			s_fsnotify_mask;
-	struct fsnotify_mark_connector __rcu	*s_fsnotify_marks;
-#endif
-
-	char			s_id[32];	/* Informational name */
-	uuid_t			s_uuid;		/* UUID */
-
-	unsigned int		s_max_links;
-	fmode_t			s_mode;
-
-	/*
-	 * The next field is for VFS *only*. No filesystems have any business
-	 * even looking at it. You had been warned.
-	 */
-	struct mutex s_vfs_rename_mutex;	/* Kludge */
-
-	/*
-	 * Filesystem subtype.  If non-empty the filesystem type field
-	 * in /proc/mounts will be "type.subtype"
-	 */
-	const char *s_subtype;
-
-	const struct dentry_operations *s_d_op; /* default d_op for dentries */
-
-	struct shrinker s_shrink;	/* per-sb shrinker handle */
-
-	/* Number of inodes with nlink == 0 but still referenced */
-	atomic_long_t s_remove_count;
-
-	/*
-	 * Number of inode/mount/sb objects that are being watched, note that
-	 * inodes objects are currently double-accounted.
-	 */
-	atomic_long_t s_fsnotify_connectors;
-
-	/* Being remounted read-only */
-	int s_readonly_remount;
-
-	/* per-sb errseq_t for reporting writeback errors via syncfs */
-	errseq_t s_wb_err;
-
-	/* AIO completions deferred from interrupt context */
-	struct workqueue_struct *s_dio_done_wq;
-	struct hlist_head s_pins;
-
-	/*
-	 * Owning user namespace and default context in which to
-	 * interpret filesystem uids, gids, quotas, device nodes,
-	 * xattrs and security labels.
-	 */
-	struct user_namespace *s_user_ns;
-
-	/*
-	 * The list_lru structure is essentially just a pointer to a table
-	 * of per-node lru lists, each of which has its own spinlock.
-	 * There is no need to put them into separate cachelines.
-	 */
-	struct list_lru		s_dentry_lru;
-	struct list_lru		s_inode_lru;
-	struct rcu_head		rcu;
-	struct work_struct	destroy_work;
-
-	struct mutex		s_sync_lock;	/* sync serialisation lock */
-
-	/*
-	 * Indicates how deep in a filesystem stack this SB is
-	 */
-	int s_stack_depth;
-
-	/* s_inode_list_lock protects s_inodes */
-	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
-	struct list_head	s_inodes;	/* all inodes */
-
-	spinlock_t		s_inode_wblist_lock;
-	struct list_head	s_inodes_wb;	/* writeback inodes */
-} __randomize_layout;
-
 static inline struct user_namespace *i_user_ns(const struct inode *inode)
 {
 	return inode->i_sb->s_user_ns;
@@ -1474,151 +1594,161 @@ static inline bool fsuidgid_has_mapping(struct super_block *sb,
 	       kgid_has_mapping(fs_userns, kgid);
 }
 
-extern struct timespec64 current_time(struct inode *inode);
+struct timespec64 current_time(struct inode *inode);
+struct timespec64 inode_set_ctime_current(struct inode *inode);
+struct timespec64 inode_set_ctime_deleg(struct inode *inode,
+					struct timespec64 update);
 
-/*
- * Snapshotting support.
- */
+static inline time64_t inode_get_atime_sec(const struct inode *inode)
+{
+	return inode->i_atime_sec;
+}
 
-/*
- * These are internal functions, please use sb_start_{write,pagefault,intwrite}
- * instead.
- */
-static inline void __sb_end_write(struct super_block *sb, int level)
+static inline long inode_get_atime_nsec(const struct inode *inode)
 {
-	percpu_up_read(sb->s_writers.rw_sem + level-1);
+	return inode->i_atime_nsec;
 }
 
-static inline void __sb_start_write(struct super_block *sb, int level)
+static inline struct timespec64 inode_get_atime(const struct inode *inode)
 {
-	percpu_down_read(sb->s_writers.rw_sem + level - 1);
+	struct timespec64 ts = { .tv_sec  = inode_get_atime_sec(inode),
+				 .tv_nsec = inode_get_atime_nsec(inode) };
+
+	return ts;
 }
 
-static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+static inline struct timespec64 inode_set_atime_to_ts(struct inode *inode,
+						      struct timespec64 ts)
 {
-	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+	inode->i_atime_sec = ts.tv_sec;
+	inode->i_atime_nsec = ts.tv_nsec;
+	return ts;
 }
 
-#define __sb_writers_acquired(sb, lev)	\
-	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
-#define __sb_writers_release(sb, lev)	\
-	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
+static inline struct timespec64 inode_set_atime(struct inode *inode,
+						time64_t sec, long nsec)
+{
+	struct timespec64 ts = { .tv_sec  = sec,
+				 .tv_nsec = nsec };
+
+	return inode_set_atime_to_ts(inode, ts);
+}
 
-static inline bool sb_write_started(const struct super_block *sb)
+static inline time64_t inode_get_mtime_sec(const struct inode *inode)
 {
-	return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
+	return inode->i_mtime_sec;
 }
 
-/**
- * sb_end_write - drop write access to a superblock
- * @sb: the super we wrote to
- *
- * Decrement number of writers to the filesystem. Wake up possible waiters
- * wanting to freeze the filesystem.
- */
-static inline void sb_end_write(struct super_block *sb)
+static inline long inode_get_mtime_nsec(const struct inode *inode)
 {
-	__sb_end_write(sb, SB_FREEZE_WRITE);
+	return inode->i_mtime_nsec;
 }
 
-/**
- * sb_end_pagefault - drop write access to a superblock from a page fault
- * @sb: the super we wrote to
- *
- * Decrement number of processes handling write page fault to the filesystem.
- * Wake up possible waiters wanting to freeze the filesystem.
- */
-static inline void sb_end_pagefault(struct super_block *sb)
+static inline struct timespec64 inode_get_mtime(const struct inode *inode)
 {
-	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
+	struct timespec64 ts = { .tv_sec  = inode_get_mtime_sec(inode),
+				 .tv_nsec = inode_get_mtime_nsec(inode) };
+	return ts;
 }
 
-/**
- * sb_end_intwrite - drop write access to a superblock for internal fs purposes
- * @sb: the super we wrote to
- *
- * Decrement fs-internal number of writers to the filesystem.  Wake up possible
- * waiters wanting to freeze the filesystem.
- */
-static inline void sb_end_intwrite(struct super_block *sb)
+static inline struct timespec64 inode_set_mtime_to_ts(struct inode *inode,
+						      struct timespec64 ts)
 {
-	__sb_end_write(sb, SB_FREEZE_FS);
+	inode->i_mtime_sec = ts.tv_sec;
+	inode->i_mtime_nsec = ts.tv_nsec;
+	return ts;
 }
 
-/**
- * sb_start_write - get write access to a superblock
- * @sb: the super we write to
- *
- * When a process wants to write data or metadata to a file system (i.e. dirty
- * a page or an inode), it should embed the operation in a sb_start_write() -
- * sb_end_write() pair to get exclusion against file system freezing. This
- * function increments number of writers preventing freezing. If the file
- * system is already frozen, the function waits until the file system is
- * thawed.
- *
- * Since freeze protection behaves as a lock, users have to preserve
- * ordering of freeze protection and other filesystem locks. Generally,
- * freeze protection should be the outermost lock. In particular, we have:
+static inline struct timespec64 inode_set_mtime(struct inode *inode,
+						time64_t sec, long nsec)
+{
+	struct timespec64 ts = { .tv_sec  = sec,
+				 .tv_nsec = nsec };
+	return inode_set_mtime_to_ts(inode, ts);
+}
+
+/*
+ * Multigrain timestamps
  *
- * sb_start_write
- *   -> i_mutex			(write path, truncate, directory ops, ...)
- *   -> s_umount		(freeze_super, thaw_super)
+ * Conditionally use fine-grained ctime and mtime timestamps when there
+ * are users actively observing them via getattr. The primary use-case
+ * for this is NFS clients that use the ctime to distinguish between
+ * different states of the file, and that are often fooled by multiple
+ * operations that occur in the same coarse-grained timer tick.
  */
-static inline void sb_start_write(struct super_block *sb)
+#define I_CTIME_QUERIED		((u32)BIT(31))
+
+static inline time64_t inode_get_ctime_sec(const struct inode *inode)
 {
-	__sb_start_write(sb, SB_FREEZE_WRITE);
+	return inode->i_ctime_sec;
 }
 
-static inline bool sb_start_write_trylock(struct super_block *sb)
+static inline long inode_get_ctime_nsec(const struct inode *inode)
 {
-	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
+	return inode->i_ctime_nsec & ~I_CTIME_QUERIED;
 }
 
+static inline struct timespec64 inode_get_ctime(const struct inode *inode)
+{
+	struct timespec64 ts = { .tv_sec  = inode_get_ctime_sec(inode),
+				 .tv_nsec = inode_get_ctime_nsec(inode) };
+
+	return ts;
+}
+
+struct timespec64 inode_set_ctime_to_ts(struct inode *inode, struct timespec64 ts);
+
 /**
- * sb_start_pagefault - get write access to a superblock from a page fault
- * @sb: the super we write to
+ * inode_set_ctime - set the ctime in the inode
+ * @inode: inode in which to set the ctime
+ * @sec: tv_sec value to set
+ * @nsec: tv_nsec value to set
  *
- * When a process starts handling write page fault, it should embed the
- * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
- * exclusion against file system freezing. This is needed since the page fault
- * is going to dirty a page. This function increments number of running page
- * faults preventing freezing. If the file system is already frozen, the
- * function waits until the file system is thawed.
- *
- * Since page fault freeze protection behaves as a lock, users have to preserve
- * ordering of freeze protection and other filesystem locks. It is advised to
- * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
- * handling code implies lock dependency:
- *
- * mmap_lock
- *   -> sb_start_pagefault
+ * Set the ctime in @inode to { @sec, @nsec }
  */
-static inline void sb_start_pagefault(struct super_block *sb)
+static inline struct timespec64 inode_set_ctime(struct inode *inode,
+						time64_t sec, long nsec)
 {
-	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
+	struct timespec64 ts = { .tv_sec  = sec,
+				 .tv_nsec = nsec };
+
+	return inode_set_ctime_to_ts(inode, ts);
 }
 
+struct timespec64 simple_inode_init_ts(struct inode *inode);
+
+/*
+ * Snapshotting support.
+ */
+
 /**
- * sb_start_intwrite - get write access to a superblock for internal fs purposes
- * @sb: the super we write to
- *
- * This is the third level of protection against filesystem freezing. It is
- * free for use by a filesystem. The only requirement is that it must rank
- * below sb_start_pagefault.
+ * file_write_started - check if SB_FREEZE_WRITE is held
+ * @file: the file we write to
  *
- * For example filesystem can call sb_start_intwrite() when starting a
- * transaction which somewhat eases handling of freezing for internal sources
- * of filesystem changes (internal fs threads, discarding preallocation on file
- * close, etc.).
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
  */
-static inline void sb_start_intwrite(struct super_block *sb)
+static inline bool file_write_started(const struct file *file)
 {
-	__sb_start_write(sb, SB_FREEZE_FS);
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return true;
+	return sb_write_started(file_inode(file)->i_sb);
 }
 
-static inline bool sb_start_intwrite_trylock(struct super_block *sb)
+/**
+ * file_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @file: the file we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ * May be false positive with !S_ISREG, because file_start_write() has
+ * no effect on !S_ISREG.
+ */
+static inline bool file_write_not_started(const struct file *file)
 {
-	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return true;
+	return sb_write_not_started(file_inode(file)->i_sb);
 }
 
 bool inode_owner_or_capable(struct mnt_idmap *idmap,
@@ -1627,39 +1757,38 @@ bool inode_owner_or_capable(struct mnt_idmap *idmap,
 /*
  * VFS helper functions..
  */
-int vfs_create(struct mnt_idmap *, struct inode *,
-	       struct dentry *, umode_t, bool);
-int vfs_mkdir(struct mnt_idmap *, struct inode *,
-	      struct dentry *, umode_t);
+int vfs_create(struct mnt_idmap *, struct dentry *, umode_t,
+	       struct delegated_inode *);
+struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *,
+			 struct dentry *, umode_t, struct delegated_inode *);
 int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
-              umode_t, dev_t);
+	      umode_t, dev_t, struct delegated_inode *);
 int vfs_symlink(struct mnt_idmap *, struct inode *,
-		struct dentry *, const char *);
+		struct dentry *, const char *, struct delegated_inode *);
 int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *,
-	     struct dentry *, struct inode **);
-int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *);
+	     struct dentry *, struct delegated_inode *);
+int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *,
+	      struct delegated_inode *);
 int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *,
-	       struct inode **);
+	       struct delegated_inode *);
 
 /**
  * struct renamedata - contains all information required for renaming
- * @old_mnt_idmap:     idmap of the old mount the inode was found from
- * @old_dir:           parent of source
+ * @mnt_idmap:     idmap of the mount in which the rename is happening.
+ * @old_parent:        parent of source
  * @old_dentry:                source
- * @new_mnt_idmap:     idmap of the new mount the inode was found from
- * @new_dir:           parent of destination
+ * @new_parent:        parent of destination
  * @new_dentry:                destination
  * @delegated_inode:   returns an inode needing a delegation break
  * @flags:             rename flags
  */
 struct renamedata {
-	struct mnt_idmap *old_mnt_idmap;
-	struct inode *old_dir;
+	struct mnt_idmap *mnt_idmap;
+	struct dentry *old_parent;
 	struct dentry *old_dentry;
-	struct mnt_idmap *new_mnt_idmap;
-	struct inode *new_dir;
+	struct dentry *new_parent;
 	struct dentry *new_dentry;
-	struct inode **delegated_inode;
+	struct delegated_inode *delegated_inode;
 	unsigned int flags;
 } __randomize_layout;
 
@@ -1669,12 +1798,15 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap,
 			       struct inode *dir, struct dentry *dentry)
 {
 	return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE,
-			 WHITEOUT_DEV);
+			 WHITEOUT_DEV, NULL);
 }
 
-struct file *vfs_tmpfile_open(struct mnt_idmap *idmap,
-			const struct path *parentpath,
-			umode_t mode, int open_flag, const struct cred *cred);
+struct file *kernel_tmpfile_open(struct mnt_idmap *idmap,
+				 const struct path *parentpath,
+				 umode_t mode, int open_flag,
+				 const struct cred *cred);
+struct file *kernel_file_open(const struct path *path, int flags,
+			      const struct cred *cred);
 
 int vfs_mkobj(struct dentry *, umode_t,
 		int (*f)(struct dentry *, umode_t, void *),
@@ -1684,8 +1816,6 @@ int vfs_fchown(struct file *file, uid_t user, gid_t group);
 int vfs_fchmod(struct file *file, umode_t mode);
 int vfs_utimes(const struct path *path, struct timespec64 *times);
 
-extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
-
 #ifdef CONFIG_COMPAT
 extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
 					unsigned long arg);
@@ -1701,6 +1831,8 @@ void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode,
 extern bool may_open_dev(const struct path *path);
 umode_t mode_strip_sgid(struct mnt_idmap *idmap,
 			const struct inode *dir, umode_t mode);
+bool in_group_or_capable(struct mnt_idmap *idmap,
+			 const struct inode *inode, vfsgid_t vfsgid);
 
 /*
  * This is the "filldir" function type, used by readdir() to let
@@ -1716,8 +1848,18 @@ typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
 struct dir_context {
 	filldir_t actor;
 	loff_t pos;
+	/*
+	 * Filesystems MUST NOT MODIFY count, but may use as a hint:
+	 * 0	    unknown
+	 * > 0      space in buffer (assume at least one entry)
+	 * INT_MAX  unlimited
+	 */
+	int count;
 };
 
+/* If OR-ed with d_type, pending signals are not checked */
+#define FILLDIR_FLAG_NOINTR	0x1000
+
 /*
  * These flags let !MMU mmap() govern direct device mapping vs immediate
  * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
@@ -1767,9 +1909,13 @@ struct dir_context {
 
 struct iov_iter;
 struct io_uring_cmd;
+struct offset_ctx;
+
+typedef unsigned int __bitwise fop_flags_t;
 
 struct file_operations {
 	struct module *owner;
+	fop_flags_t fop_flags;
 	loff_t (*llseek) (struct file *, loff_t, int);
 	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
 	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
@@ -1777,26 +1923,24 @@ struct file_operations {
 	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
 	int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
 			unsigned int flags);
-	int (*iterate) (struct file *, struct dir_context *);
 	int (*iterate_shared) (struct file *, struct dir_context *);
 	__poll_t (*poll) (struct file *, struct poll_table_struct *);
 	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
 	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
 	int (*mmap) (struct file *, struct vm_area_struct *);
-	unsigned long mmap_supported_flags;
 	int (*open) (struct inode *, struct file *);
 	int (*flush) (struct file *, fl_owner_t id);
 	int (*release) (struct inode *, struct file *);
 	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
 	int (*fasync) (int, struct file *, int);
 	int (*lock) (struct file *, int, struct file_lock *);
-	ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int);
 	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
 	int (*check_flags)(int);
 	int (*flock) (struct file *, int, struct file_lock *);
 	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
 	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
-	int (*setlease)(struct file *, long, struct file_lock **, void **);
+	void (*splice_eof)(struct file *file);
+	int (*setlease)(struct file *, int, struct file_lease **, void **);
 	long (*fallocate)(struct file *file, int mode, loff_t offset,
 			  loff_t len);
 	void (*show_fdinfo)(struct seq_file *m, struct file *f);
@@ -1812,8 +1956,33 @@ struct file_operations {
 	int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
 	int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *,
 				unsigned int poll_flags);
+	int (*mmap_prepare)(struct vm_area_desc *);
 } __randomize_layout;
 
+/* Supports async buffered reads */
+#define FOP_BUFFER_RASYNC	((__force fop_flags_t)(1 << 0))
+/* Supports async buffered writes */
+#define FOP_BUFFER_WASYNC	((__force fop_flags_t)(1 << 1))
+/* Supports synchronous page faults for mappings */
+#define FOP_MMAP_SYNC		((__force fop_flags_t)(1 << 2))
+/* Supports non-exclusive O_DIRECT writes from multiple threads */
+#define FOP_DIO_PARALLEL_WRITE	((__force fop_flags_t)(1 << 3))
+/* Contains huge pages */
+#define FOP_HUGE_PAGES		((__force fop_flags_t)(1 << 4))
+/* Treat loff_t as unsigned (e.g., /dev/mem) */
+#define FOP_UNSIGNED_OFFSET	((__force fop_flags_t)(1 << 5))
+/* Supports asynchronous lock callbacks */
+#define FOP_ASYNC_LOCK		((__force fop_flags_t)(1 << 6))
+/* File system supports uncached read/write buffered IO */
+#define FOP_DONTCACHE		((__force fop_flags_t)(1 << 7))
+
+/* Wrap a directory iterator that needs exclusive inode access */
+int wrap_directory_iterator(struct file *, struct dir_context *,
+			    int (*) (struct file *, struct dir_context *));
+#define WRAP_DIR_ITER(x) \
+	static int shared_##x(struct file *file , struct dir_context *ctx) \
+	{ return wrap_directory_iterator(file, ctx, x); }
+
 struct inode_operations {
 	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
 	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
@@ -1828,8 +1997,8 @@ struct inode_operations {
 	int (*unlink) (struct inode *,struct dentry *);
 	int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,
 			const char *);
-	int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,
-		      umode_t);
+	struct dentry *(*mkdir) (struct mnt_idmap *, struct inode *,
+				 struct dentry *, umode_t);
 	int (*rmdir) (struct inode *,struct dentry *);
 	int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,
 		      umode_t,dev_t);
@@ -1841,7 +2010,7 @@ struct inode_operations {
 	ssize_t (*listxattr) (struct dentry *, char *, size_t);
 	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
 		      u64 len);
-	int (*update_time)(struct inode *, struct timespec64 *, int);
+	int (*update_time)(struct inode *, int);
 	int (*atomic_open)(struct inode *, struct dentry *,
 			   struct file *, unsigned open_flag,
 			   umode_t create_mode);
@@ -1852,34 +2021,48 @@ struct inode_operations {
 	int (*set_acl)(struct mnt_idmap *, struct dentry *,
 		       struct posix_acl *, int);
 	int (*fileattr_set)(struct mnt_idmap *idmap,
-			    struct dentry *dentry, struct fileattr *fa);
-	int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
+			    struct dentry *dentry, struct file_kattr *fa);
+	int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);
+	struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 } ____cacheline_aligned;
 
-static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
-				     struct iov_iter *iter)
+/* Did the driver provide valid mmap hook configuration? */
+static inline bool can_mmap_file(struct file *file)
 {
-	return file->f_op->read_iter(kio, iter);
+	bool has_mmap = file->f_op->mmap;
+	bool has_mmap_prepare = file->f_op->mmap_prepare;
+
+	/* Hooks are mutually exclusive. */
+	if (WARN_ON_ONCE(has_mmap && has_mmap_prepare))
+		return false;
+	if (!has_mmap && !has_mmap_prepare)
+		return false;
+
+	return true;
 }
 
-static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
-				      struct iov_iter *iter)
+int __compat_vma_mmap(const struct file_operations *f_op,
+		struct file *file, struct vm_area_struct *vma);
+int compat_vma_mmap(struct file *file, struct vm_area_struct *vma);
+
+static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	return file->f_op->write_iter(kio, iter);
+	if (file->f_op->mmap_prepare)
+		return compat_vma_mmap(file, vma);
+
+	return file->f_op->mmap(file, vma);
 }
 
-static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
+static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
 {
-	return file->f_op->mmap(file, vma);
+	return file->f_op->mmap_prepare(desc);
 }
 
 extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
 extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
 extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
 				   loff_t, size_t, unsigned int);
-extern ssize_t generic_copy_file_range(struct file *file_in, loff_t pos_in,
-				       struct file *file_out, loff_t pos_out,
-				       size_t len, unsigned int flags);
+int remap_verify_area(struct file *file, loff_t pos, loff_t len, bool write);
 int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				    struct file *file_out, loff_t pos_out,
 				    loff_t *len, unsigned int remap_flags,
@@ -1887,9 +2070,6 @@ int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
 				  struct file *file_out, loff_t pos_out,
 				  loff_t *count, unsigned int remap_flags);
-extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
-				  struct file *file_out, loff_t pos_out,
-				  loff_t len, unsigned int remap_flags);
 extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
 				   struct file *file_out, loff_t pos_out,
 				   loff_t len, unsigned int remap_flags);
@@ -1899,41 +2079,6 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
 					struct file *dst_file, loff_t dst_pos,
 					loff_t len, unsigned int remap_flags);
 
-
-struct super_operations {
-   	struct inode *(*alloc_inode)(struct super_block *sb);
-	void (*destroy_inode)(struct inode *);
-	void (*free_inode)(struct inode *);
-
-   	void (*dirty_inode) (struct inode *, int flags);
-	int (*write_inode) (struct inode *, struct writeback_control *wbc);
-	int (*drop_inode) (struct inode *);
-	void (*evict_inode) (struct inode *);
-	void (*put_super) (struct super_block *);
-	int (*sync_fs)(struct super_block *sb, int wait);
-	int (*freeze_super) (struct super_block *);
-	int (*freeze_fs) (struct super_block *);
-	int (*thaw_super) (struct super_block *);
-	int (*unfreeze_fs) (struct super_block *);
-	int (*statfs) (struct dentry *, struct kstatfs *);
-	int (*remount_fs) (struct super_block *, int *, char *);
-	void (*umount_begin) (struct super_block *);
-
-	int (*show_options)(struct seq_file *, struct dentry *);
-	int (*show_devname)(struct seq_file *, struct dentry *);
-	int (*show_path)(struct seq_file *, struct dentry *);
-	int (*show_stats)(struct seq_file *, struct dentry *);
-#ifdef CONFIG_QUOTA
-	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
-	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
-	struct dquot **(*get_dquots)(struct inode *);
-#endif
-	long (*nr_cached_objects)(struct super_block *,
-				  struct shrink_control *);
-	long (*free_cached_objects)(struct super_block *,
-				    struct shrink_control *);
-};
-
 /*
  * Inode flags - they have no relation to superblock flags now
  */
@@ -1959,6 +2104,7 @@ struct super_operations {
 #define S_CASEFOLD	(1 << 15) /* Casefolded file */
 #define S_VERITY	(1 << 16) /* Verity file (using fs/verity/) */
 #define S_KERNEL_FILE	(1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */
+#define S_ANON_INODE	(1 << 19) /* Inode is an anonymous inode */
 
 /*
  * Note that nosuid etc flags are inode-specific: setting some file-system
@@ -1975,7 +2121,6 @@ struct super_operations {
  */
 #define __IS_FLG(inode, flg)	((inode)->i_sb->s_flags & (flg))
 
-static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; }
 #define IS_RDONLY(inode)	sb_rdonly((inode)->i_sb)
 #define IS_SYNC(inode)		(__IS_FLG(inode, SB_SYNCHRONOUS) || \
 					((inode)->i_flags & S_SYNC))
@@ -1988,11 +2133,22 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags
 #define IS_NOQUOTA(inode)	((inode)->i_flags & S_NOQUOTA)
 #define IS_APPEND(inode)	((inode)->i_flags & S_APPEND)
 #define IS_IMMUTABLE(inode)	((inode)->i_flags & S_IMMUTABLE)
+
+#ifdef CONFIG_FS_POSIX_ACL
 #define IS_POSIXACL(inode)	__IS_FLG(inode, SB_POSIXACL)
+#else
+#define IS_POSIXACL(inode)	0
+#endif
 
 #define IS_DEADDIR(inode)	((inode)->i_flags & S_DEAD)
 #define IS_NOCMTIME(inode)	((inode)->i_flags & S_NOCMTIME)
+
+#ifdef CONFIG_SWAP
 #define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
+#else
+#define IS_SWAPFILE(inode)	((void)(inode), 0U)
+#endif
+
 #define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
 #define IS_IMA(inode)		((inode)->i_flags & S_IMA)
 #define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
@@ -2004,6 +2160,7 @@ static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags
 
 #define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
 				 (inode)->i_rdev == WHITEOUT_DEV)
+#define IS_ANON_FILE(inode)	((inode)->i_flags & S_ANON_INODE)
 
 static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap,
 				   struct inode *inode)
@@ -2032,112 +2189,6 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
 	};
 }
 
-/*
- * Inode state bits.  Protected by inode->i_lock
- *
- * Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
- * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
- *
- * Four bits define the lifetime of an inode.  Initially, inodes are I_NEW,
- * until that flag is cleared.  I_WILL_FREE, I_FREEING and I_CLEAR are set at
- * various stages of removing an inode.
- *
- * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
- *
- * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
- *			fdatasync() (unless I_DIRTY_DATASYNC is also set).
- *			Timestamp updates are the usual cause.
- * I_DIRTY_DATASYNC	Data-related inode changes pending.  We keep track of
- *			these changes separately from I_DIRTY_SYNC so that we
- *			don't have to write inode on fdatasync() when only
- *			e.g. the timestamps have changed.
- * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
- * I_DIRTY_TIME		The inode itself has dirty timestamps, and the
- *			lazytime mount option is enabled.  We keep track of this
- *			separately from I_DIRTY_SYNC in order to implement
- *			lazytime.  This gets cleared if I_DIRTY_INODE
- *			(I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
- *			I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
- *			in place because writeback might already be in progress
- *			and we don't want to lose the time update
- * I_NEW		Serves as both a mutex and completion notification.
- *			New inodes set I_NEW.  If two processes both create
- *			the same inode, one of them will release its inode and
- *			wait for I_NEW to be released before returning.
- *			Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
- *			also cause waiting on I_NEW, without I_NEW actually
- *			being set.  find_inode() uses this to prevent returning
- *			nearly-dead inodes.
- * I_WILL_FREE		Must be set when calling write_inode_now() if i_count
- *			is zero.  I_FREEING must be set when I_WILL_FREE is
- *			cleared.
- * I_FREEING		Set when inode is about to be freed but still has dirty
- *			pages or buffers attached or the inode itself is still
- *			dirty.
- * I_CLEAR		Added by clear_inode().  In this state the inode is
- *			clean and can be destroyed.  Inode keeps I_FREEING.
- *
- *			Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
- *			prohibited for many purposes.  iget() must wait for
- *			the inode to be completely released, then create it
- *			anew.  Other functions will just ignore such inodes,
- *			if appropriate.  I_NEW is used for waiting.
- *
- * I_SYNC		Writeback of inode is running. The bit is set during
- *			data writeback, and cleared with a wakeup on the bit
- *			address once it is done. The bit is also used to pin
- *			the inode in memory for flusher thread.
- *
- * I_REFERENCED		Marks the inode as recently references on the LRU list.
- *
- * I_DIO_WAKEUP		Never set.  Only used as a key for wait_on_bit().
- *
- * I_WB_SWITCH		Cgroup bdi_writeback switching in progress.  Used to
- *			synchronize competing switching instances and to tell
- *			wb stat updates to grab the i_pages lock.  See
- *			inode_switch_wbs_work_fn() for details.
- *
- * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
- *			and work dirs among overlayfs mounts.
- *
- * I_CREATING		New object's inode in the middle of setting up.
- *
- * I_DONTCACHE		Evict inode as soon as it is not used anymore.
- *
- * I_SYNC_QUEUED	Inode is queued in b_io or b_more_io writeback lists.
- *			Used to detect that mark_inode_dirty() should not move
- * 			inode between dirty lists.
- *
- * I_PINNING_FSCACHE_WB	Inode is pinning an fscache object for writeback.
- *
- * Q: What is the difference between I_WILL_FREE and I_FREEING?
- */
-#define I_DIRTY_SYNC		(1 << 0)
-#define I_DIRTY_DATASYNC	(1 << 1)
-#define I_DIRTY_PAGES		(1 << 2)
-#define __I_NEW			3
-#define I_NEW			(1 << __I_NEW)
-#define I_WILL_FREE		(1 << 4)
-#define I_FREEING		(1 << 5)
-#define I_CLEAR			(1 << 6)
-#define __I_SYNC		7
-#define I_SYNC			(1 << __I_SYNC)
-#define I_REFERENCED		(1 << 8)
-#define __I_DIO_WAKEUP		9
-#define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
-#define I_LINKABLE		(1 << 10)
-#define I_DIRTY_TIME		(1 << 11)
-#define I_WB_SWITCH		(1 << 13)
-#define I_OVL_INUSE		(1 << 14)
-#define I_CREATING		(1 << 15)
-#define I_DONTCACHE		(1 << 16)
-#define I_SYNC_QUEUED		(1 << 17)
-#define I_PINNING_FSCACHE_WB	(1 << 18)
-
-#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
-#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
-#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)
-
 extern void __mark_inode_dirty(struct inode *, int);
 static inline void mark_inode_dirty(struct inode *inode)
 {
@@ -2149,6 +2200,11 @@ static inline void mark_inode_dirty_sync(struct inode *inode)
 	__mark_inode_dirty(inode, I_DIRTY_SYNC);
 }
 
+static inline int icount_read(const struct inode *inode)
+{
+	return atomic_read(&inode->i_count);
+}
+
 /*
  * Returns true if the given inode itself only has dirty timestamps (its pages
  * may still be dirty) and isn't currently being allocated or freed.
@@ -2160,8 +2216,8 @@ static inline void mark_inode_dirty_sync(struct inode *inode)
  */
 static inline bool inode_is_dirtytime_only(struct inode *inode)
 {
-	return (inode->i_state & (I_DIRTY_TIME | I_NEW |
-				  I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
+	return (inode_state_read_once(inode) &
+	       (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
 }
 
 extern void inc_nlink(struct inode *inode);
@@ -2190,7 +2246,7 @@ enum file_time_flags {
 
 extern bool atime_needs_update(const struct path *, struct inode *);
 extern void touch_atime(const struct path *);
-int inode_update_time(struct inode *inode, struct timespec64 *time, int flags);
+int inode_update_time(struct inode *inode, int flags);
 
 static inline void file_accessed(struct file *file)
 {
@@ -2212,6 +2268,9 @@ struct file_system_type {
 #define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
 #define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
 #define FS_ALLOW_IDMAP         32      /* FS has been updated to handle vfs idmappings. */
+#define FS_MGTIME		64	/* FS uses multigrain timestamps */
+#define FS_LBS			128	/* FS supports LBS */
+#define FS_POWER_FREEZE		256	/* Always freeze on suspend/hibernate */
 #define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
 	int (*init_fs_context)(struct fs_context *);
 	const struct fs_parameter_spec *parameters;
@@ -2235,21 +2294,22 @@ struct file_system_type {
 
 #define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)
 
-extern struct dentry *mount_bdev(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *data,
-	int (*fill_super)(struct super_block *, void *, int));
-extern struct dentry *mount_single(struct file_system_type *fs_type,
-	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int));
-extern struct dentry *mount_nodev(struct file_system_type *fs_type,
-	int flags, void *data,
-	int (*fill_super)(struct super_block *, void *, int));
+/**
+ * is_mgtime: is this inode using multigrain timestamps
+ * @inode: inode to test for multigrain timestamps
+ *
+ * Return true if the inode uses multigrain timestamps, false otherwise.
+ */
+static inline bool is_mgtime(const struct inode *inode)
+{
+	return inode->i_opflags & IOP_MGTIME;
+}
+
 extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
 void retire_super(struct super_block *sb);
 void generic_shutdown_super(struct super_block *sb);
 void kill_block_super(struct super_block *sb);
 void kill_anon_super(struct super_block *sb);
-void kill_litter_super(struct super_block *sb);
 void deactivate_super(struct super_block *sb);
 void deactivate_locked_super(struct super_block *sb);
 int set_anon_super(struct super_block *s, void *data);
@@ -2263,12 +2323,20 @@ struct super_block *sget(struct file_system_type *type,
 			int (*test)(struct super_block *,void *),
 			int (*set)(struct super_block *,void *),
 			int flags, void *data);
+struct super_block *sget_dev(struct fs_context *fc, dev_t dev);
 
 /* Alas, no aliases. Too much hassle with bringing module.h everywhere */
-#define fops_get(fops) \
-	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
-#define fops_put(fops) \
-	do { if (fops) module_put((fops)->owner); } while(0)
+#define fops_get(fops) ({						\
+	const struct file_operations *_fops = (fops);			\
+	(((_fops) && try_module_get((_fops)->owner) ? (_fops) : NULL));	\
+})
+
+#define fops_put(fops) ({						\
+	const struct file_operations *_fops = (fops);			\
+	if (_fops)							\
+		module_put((_fops)->owner);				\
+})
+
 /*
  * This one is to be used *ONLY* from ->open() instances.
  * fops must be non-NULL, pinned down *and* module dependencies
@@ -2286,17 +2354,53 @@ extern int unregister_filesystem(struct file_system_type *);
 extern int vfs_statfs(const struct path *, struct kstatfs *);
 extern int user_statfs(const char __user *, struct kstatfs *);
 extern int fd_statfs(int, struct kstatfs *);
-extern int freeze_super(struct super_block *super);
-extern int thaw_super(struct super_block *super);
 extern __printf(2, 3)
 int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
 extern int super_setup_bdi(struct super_block *sb);
 
-extern int current_umask(void);
+static inline void super_set_uuid(struct super_block *sb, const u8 *uuid, unsigned len)
+{
+	if (WARN_ON(len > sizeof(sb->s_uuid)))
+		len = sizeof(sb->s_uuid);
+	sb->s_uuid_len = len;
+	memcpy(&sb->s_uuid, uuid, len);
+}
+
+/* set sb sysfs name based on sb->s_bdev */
+static inline void super_set_sysfs_name_bdev(struct super_block *sb)
+{
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pg", sb->s_bdev);
+}
+
+/* set sb sysfs name based on sb->s_uuid */
+static inline void super_set_sysfs_name_uuid(struct super_block *sb)
+{
+	WARN_ON(sb->s_uuid_len != sizeof(sb->s_uuid));
+	snprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), "%pU", sb->s_uuid.b);
+}
+
+/* set sb sysfs name based on sb->s_id */
+static inline void super_set_sysfs_name_id(struct super_block *sb)
+{
+	strscpy(sb->s_sysfs_name, sb->s_id, sizeof(sb->s_sysfs_name));
+}
+
+/* try to use something standard before you use this */
+__printf(2, 3)
+static inline void super_set_sysfs_name_generic(struct super_block *sb, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(sb->s_sysfs_name, sizeof(sb->s_sysfs_name), fmt, args);
+	va_end(args);
+}
 
 extern void ihold(struct inode * inode);
 extern void iput(struct inode *);
-extern int generic_update_time(struct inode *, struct timespec64 *, int);
+void iput_not_last(struct inode *);
+int inode_update_timestamps(struct inode *inode, int flags);
+int generic_update_time(struct inode *, int);
 
 /* /sys/fs */
 extern struct kobject *fs_kobj;
@@ -2308,13 +2412,13 @@ struct audit_names;
 struct filename {
 	const char		*name;	/* pointer to actual string */
 	const __user char	*uptr;	/* original userland pointer */
-	int			refcnt;
+	atomic_t		refcnt;
 	struct audit_names	*aname;
 	const char		iname[];
 };
 static_assert(offsetof(struct filename, iname) % sizeof(long) == 0);
 
-static inline struct mnt_idmap *file_mnt_idmap(struct file *file)
+static inline struct mnt_idmap *file_mnt_idmap(const struct file *file)
 {
 	return mnt_idmap(file->f_path.mnt);
 }
@@ -2332,13 +2436,13 @@ static inline bool is_idmapped_mnt(const struct vfsmount *mnt)
 	return mnt_idmap(mnt) != &nop_mnt_idmap;
 }
 
-extern long vfs_truncate(const struct path *, loff_t);
+int vfs_truncate(const struct path *, loff_t);
 int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start,
 		unsigned int time_attrs, struct file *filp);
 extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
 			loff_t len);
-extern long do_sys_open(int dfd, const char __user *filename, int flags,
-			umode_t mode);
+int do_sys_open(int dfd, const char __user *filename, int flags,
+		umode_t mode);
 extern struct file *file_open_name(struct filename *, int, umode_t);
 extern struct file *filp_open(const char *, int, umode_t);
 extern struct file *file_open_root(const struct path *,
@@ -2349,22 +2453,69 @@ static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
 	return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root},
 			      name, flags, mode);
 }
-extern struct file * dentry_open(const struct path *, int, const struct cred *);
-extern struct file *dentry_create(const struct path *path, int flags,
-				  umode_t mode, const struct cred *cred);
-extern struct file * open_with_fake_path(const struct path *, int,
-					 struct inode*, const struct cred *);
+struct file *dentry_open(const struct path *path, int flags,
+			 const struct cred *creds);
+struct file *dentry_open_nonotify(const struct path *path, int flags,
+				  const struct cred *cred);
+struct file *dentry_create(const struct path *path, int flags, umode_t mode,
+			   const struct cred *cred);
+const struct path *backing_file_user_path(const struct file *f);
+
+/*
+ * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
+ * stored in ->vm_file is a backing file whose f_inode is on the underlying
+ * filesystem.  When the mapped file path and inode number are displayed to
+ * user (e.g. via /proc/<pid>/maps), these helpers should be used to get the
+ * path and inode number to display to the user, which is the path of the fd
+ * that user has requested to map and the inode number that would be returned
+ * by fstat() on that same fd.
+ */
+/* Get the path to display in /proc/<pid>/maps */
+static inline const struct path *file_user_path(const struct file *f)
+{
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		return backing_file_user_path(f);
+	return &f->f_path;
+}
+/* Get the inode whose inode number to display in /proc/<pid>/maps */
+static inline const struct inode *file_user_inode(const struct file *f)
+{
+	if (unlikely(f->f_mode & FMODE_BACKING))
+		return d_inode(backing_file_user_path(f)->dentry);
+	return file_inode(f);
+}
+
 static inline struct file *file_clone_open(struct file *file)
 {
 	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
 }
 extern int filp_close(struct file *, fl_owner_t id);
 
-extern struct filename *getname_flags(const char __user *, int, int *);
+extern struct filename *getname_flags(const char __user *, int);
 extern struct filename *getname_uflags(const char __user *, int);
-extern struct filename *getname(const char __user *);
+static inline struct filename *getname(const char __user *name)
+{
+	return getname_flags(name, 0);
+}
 extern struct filename *getname_kernel(const char *);
+extern struct filename *__getname_maybe_null(const char __user *);
+static inline struct filename *getname_maybe_null(const char __user *name, int flags)
+{
+	if (!(flags & AT_EMPTY_PATH))
+		return getname(name);
+
+	if (!name)
+		return NULL;
+	return __getname_maybe_null(name);
+}
 extern void putname(struct filename *name);
+DEFINE_FREE(putname, struct filename *, if (!IS_ERR_OR_NULL(_T)) putname(_T))
+
+static inline struct filename *refname(struct filename *name)
+{
+	atomic_inc(&name->refcnt);
+	return name;
+}
 
 extern int finish_open(struct file *file, struct dentry *dentry,
 			int (*open)(struct inode *, struct file *));
@@ -2388,12 +2539,6 @@ extern struct kmem_cache *names_cachep;
 #define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
 #define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))
 
-extern struct super_block *blockdev_superblock;
-static inline bool sb_is_blkdev_sb(struct super_block *sb)
-{
-	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
-}
-
 void emergency_thaw_all(void);
 extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
@@ -2439,6 +2584,8 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
 extern int __must_check file_check_and_advance_wb_err(struct file *file);
 extern int __must_check file_write_and_wait_range(struct file *file,
 						loff_t start, loff_t end);
+int filemap_flush_range(struct address_space *mapping, loff_t start,
+		loff_t end);
 
 static inline int file_write_and_wait(struct file *file)
 {
@@ -2471,6 +2618,11 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
 				(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
 		if (ret)
 			return ret;
+	} else if (iocb->ki_flags & IOCB_DONTCACHE) {
+		struct address_space *mapping = iocb->ki_filp->f_mapping;
+
+		filemap_flush_range(mapping, iocb->ki_pos - count,
+				iocb->ki_pos - 1);
 	}
 
 	return count;
@@ -2489,7 +2641,7 @@ static inline int bmap(struct inode *inode,  sector_t *block)
 #endif
 
 int notify_change(struct mnt_idmap *, struct dentry *,
-		  struct iattr *, struct inode **);
+		  struct iattr *, struct delegated_inode *);
 int inode_permission(struct mnt_idmap *, struct inode *, int);
 int generic_permission(struct mnt_idmap *, struct inode *, int);
 static inline int file_permission(struct file *file, int mask)
@@ -2515,6 +2667,13 @@ static inline bool inode_wrong_type(const struct inode *inode, umode_t mode)
 	return (inode->i_mode ^ mode) & S_IFMT;
 }
 
+/**
+ * file_start_write - get write access to a superblock for regular file io
+ * @file: the file we want to write to
+ *
+ * This is a variant of sb_start_write() which is a noop on non-regular file.
+ * Should be matched with a call to file_end_write().
+ */
 static inline void file_start_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
@@ -2529,11 +2688,53 @@ static inline bool file_start_write_trylock(struct file *file)
 	return sb_start_write_trylock(file_inode(file)->i_sb);
 }
 
+/**
+ * file_end_write - drop write access to a superblock of a regular file
+ * @file: the file we wrote to
+ *
+ * Should be matched with a call to file_start_write().
+ */
 static inline void file_end_write(struct file *file)
 {
 	if (!S_ISREG(file_inode(file)->i_mode))
 		return;
-	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
+	sb_end_write(file_inode(file)->i_sb);
+}
+
+/**
+ * kiocb_start_write - get write access to a superblock for async file io
+ * @iocb: the io context we want to submit the write with
+ *
+ * This is a variant of sb_start_write() for async io submission.
+ * Should be matched with a call to kiocb_end_write().
+ */
+static inline void kiocb_start_write(struct kiocb *iocb)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	sb_start_write(inode->i_sb);
+	/*
+	 * Fool lockdep by telling it the lock got released so that it
+	 * doesn't complain about the held lock when we return to userspace.
+	 */
+	__sb_writers_release(inode->i_sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * kiocb_end_write - drop write access to a superblock after async file io
+ * @iocb: the io context we sumbitted the write with
+ *
+ * Should be matched with a call to kiocb_start_write().
+ */
+static inline void kiocb_end_write(struct kiocb *iocb)
+{
+	struct inode *inode = file_inode(iocb->ki_filp);
+
+	/*
+	 * Tell lockdep we inherited freeze protection from submission thread.
+	 */
+	__sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE);
+	sb_end_write(inode->i_sb);
 }
 
 /*
@@ -2566,12 +2767,6 @@ static inline int deny_write_access(struct file *file)
 	struct inode *inode = file_inode(file);
 	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
 }
-static inline int exclusive_deny_write_access(struct file *file)
-{
-	int old = 0;
-	struct inode *inode = file_inode(file);
-	return atomic_try_cmpxchg(&inode->i_writecount, &old, -1) ? 0 : -ETXTBSY;
-}
 static inline void put_write_access(struct inode * inode)
 {
 	atomic_dec(&inode->i_writecount);
@@ -2581,6 +2776,34 @@ static inline void allow_write_access(struct file *file)
 	if (file)
 		atomic_inc(&file_inode(file)->i_writecount);
 }
+
+/*
+ * Do not prevent write to executable file when watched by pre-content events.
+ *
+ * Note that FMODE_FSNOTIFY_HSM mode is set depending on pre-content watches at
+ * the time of file open and remains constant for entire lifetime of the file,
+ * so if pre-content watches are added post execution or removed before the end
+ * of the execution, it will not cause i_writecount reference leak.
+ */
+static inline int exe_file_deny_write_access(struct file *exe_file)
+{
+	if (unlikely(FMODE_FSNOTIFY_HSM(exe_file->f_mode)))
+		return 0;
+	return deny_write_access(exe_file);
+}
+static inline void exe_file_allow_write_access(struct file *exe_file)
+{
+	if (unlikely(!exe_file || FMODE_FSNOTIFY_HSM(exe_file->f_mode)))
+		return;
+	allow_write_access(exe_file);
+}
+
+static inline void file_set_fsnotify_mode(struct file *file, fmode_t mode)
+{
+	file->f_mode &= ~FMODE_FSNOTIFY_MASK;
+	file->f_mode |= mode;
+}
+
 static inline bool inode_is_open_for_write(const struct inode *inode)
 {
 	return atomic_read(&inode->i_writecount) > 0;
@@ -2589,8 +2812,7 @@ static inline bool inode_is_open_for_write(const struct inode *inode)
 #if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
 static inline void i_readcount_dec(struct inode *inode)
 {
-	BUG_ON(!atomic_read(&inode->i_readcount));
-	atomic_dec(&inode->i_readcount);
+	BUG_ON(atomic_dec_return(&inode->i_readcount) < 0);
 }
 static inline void i_readcount_inc(struct inode *inode)
 {
@@ -2617,9 +2839,37 @@ extern struct file * open_exec(const char *);
 /* fs/dcache.c -- generic fs support functions */
 extern bool is_subdir(struct dentry *, struct dentry *);
 extern bool path_is_under(const struct path *, const struct path *);
+u64 vfsmount_to_propagation_flags(struct vfsmount *mnt);
 
 extern char *file_path(struct file *, char *, int);
 
+/**
+ * is_dot_dotdot - returns true only if @name is "." or ".."
+ * @name: file name to check
+ * @len: length of file name, in bytes
+ */
+static inline bool is_dot_dotdot(const char *name, size_t len)
+{
+	return len && unlikely(name[0] == '.') &&
+		(len == 1 || (len == 2 && name[1] == '.'));
+}
+
+/**
+ * name_contains_dotdot - check if a file name contains ".." path components
+ * @name: File path string to check
+ * Search for ".." surrounded by either '/' or start/end of string.
+ */
+static inline bool name_contains_dotdot(const char *name)
+{
+	size_t name_len;
+
+	name_len = strlen(name);
+	return strcmp(name, "..") == 0 ||
+	       strncmp(name, "../", 3) == 0 ||
+	       strstr(name, "/../") != NULL ||
+	       (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0);
+}
+
 #include <linux/err.h>
 
 /* needed for stackable file system support */
@@ -2627,14 +2877,19 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int whence);
 
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);
 
-extern int inode_init_always(struct super_block *, struct inode *);
+extern int inode_init_always_gfp(struct super_block *, struct inode *, gfp_t);
+static inline int inode_init_always(struct super_block *sb, struct inode *inode)
+{
+	return inode_init_always_gfp(sb, inode, GFP_NOFS);
+}
+
 extern void inode_init_once(struct inode *);
 extern void address_space_init_once(struct address_space *mapping);
 extern struct inode * igrab(struct inode *);
 extern ino_t iunique(struct super_block *, ino_t);
 extern int inode_needs_sync(struct inode *inode);
-extern int generic_delete_inode(struct inode *inode);
-static inline int generic_drop_inode(struct inode *inode)
+extern int inode_just_drop(struct inode *inode);
+static inline int inode_generic_drop(struct inode *inode)
 {
 	return !inode->i_nlink || inode_unhashed(inode);
 }
@@ -2642,7 +2897,7 @@ extern void d_mark_dontcache(struct inode *inode);
 
 extern struct inode *ilookup5_nowait(struct super_block *sb,
 		unsigned long hashval, int (*test)(struct inode *, void *),
-		void *data);
+		void *data, bool *isnew);
 extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
 		int (*test)(struct inode *, void *), void *data);
 extern struct inode *ilookup(struct super_block *sb, unsigned long ino);
@@ -2651,7 +2906,12 @@ extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
 		int (*test)(struct inode *, void *),
 		int (*set)(struct inode *, void *),
 		void *data);
-extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
+struct inode *iget5_locked(struct super_block *, unsigned long,
+			   int (*test)(struct inode *, void *),
+			   int (*set)(struct inode *, void *), void *);
+struct inode *iget5_locked_rcu(struct super_block *, unsigned long,
+			       int (*test)(struct inode *, void *),
+			       int (*set)(struct inode *, void *), void *);
 extern struct inode * iget_locked(struct super_block *, unsigned long);
 extern struct inode *find_inode_nowait(struct super_block *,
 				       unsigned long,
@@ -2675,7 +2935,7 @@ extern void evict_inodes(struct super_block *sb);
 void dump_mapping(const struct address_space *);
 
 /*
- * Userspace may rely on the the inode number being non-zero. For example, glibc
+ * Userspace may rely on the inode number being non-zero. For example, glibc
  * simply ignores files with zero i_ino in unlink() and other places.
  *
  * As an additional complication, if userspace was compiled with
@@ -2689,11 +2949,20 @@ static inline bool is_zero_ino(ino_t ino)
 	return (u32)ino == 0;
 }
 
-extern void __iget(struct inode * inode);
+static inline void __iget(struct inode *inode)
+{
+	lockdep_assert_held(&inode->i_lock);
+	atomic_inc(&inode->i_count);
+}
+
 extern void iget_failed(struct inode *);
 extern void clear_inode(struct inode *);
 extern void __destroy_inode(struct inode *);
-extern struct inode *new_inode_pseudo(struct super_block *sb);
+struct inode *alloc_inode(struct super_block *sb);
+static inline struct inode *new_inode_pseudo(struct super_block *sb)
+{
+	return alloc_inode(sb);
+}
 extern struct inode *new_inode(struct super_block *sb);
 extern void free_inode_nonrcu(struct inode *inode);
 extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *);
@@ -2705,11 +2974,7 @@ int setattr_should_drop_sgid(struct mnt_idmap *idmap,
  * This must be used for allocating filesystems specific inodes to set
  * up the inode reclaim context correctly.
  */
-static inline void *
-alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp)
-{
-	return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp);
-}
+#define alloc_inode_sb(_sb, _cache, _gfp) kmem_cache_alloc_lru(_cache, &_sb->s_inode_lru, _gfp)
 
 extern void __insert_inode_hash(struct inode *, unsigned long hashval);
 static inline void insert_inode_hash(struct inode *inode)
@@ -2725,13 +2990,12 @@ static inline void remove_inode_hash(struct inode *inode)
 }
 
 extern void inode_sb_list_add(struct inode *inode);
-extern void inode_add_lru(struct inode *inode);
-
-extern int sb_set_blocksize(struct super_block *, int);
-extern int sb_min_blocksize(struct super_block *, int);
+extern void inode_lru_list_add(struct inode *inode);
 
-extern int generic_file_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
+int generic_file_mmap(struct file *, struct vm_area_struct *);
+int generic_file_mmap_prepare(struct vm_area_desc *desc);
+int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
+int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 int generic_write_checks_count(struct kiocb *iocb, loff_t *count);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
@@ -2760,27 +3024,22 @@ ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
 ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
 			    struct pipe_inode_info *pipe,
 			    size_t len, unsigned int flags);
-ssize_t direct_splice_read(struct file *in, loff_t *ppos,
-			   struct pipe_inode_info *pipe,
-			   size_t len, unsigned int flags);
-extern ssize_t generic_file_splice_read(struct file *, loff_t *,
-		struct pipe_inode_info *, size_t, unsigned int);
+ssize_t copy_splice_read(struct file *in, loff_t *ppos,
+			 struct pipe_inode_info *pipe,
+			 size_t len, unsigned int flags);
 extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
 		struct file *, loff_t *, size_t, unsigned int);
-extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
-		struct file *out, loff_t *, size_t len, unsigned int flags);
-extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
-		loff_t *opos, size_t len, unsigned int flags);
 
 
 extern void
 file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
 extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
-#define no_llseek NULL
 extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
 extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
 extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
 		int whence, loff_t maxsize, loff_t eof);
+loff_t generic_llseek_cookie(struct file *file, loff_t offset, int whence,
+			     u64 *cookie);
 extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
 		int whence, loff_t size);
 extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
@@ -2818,7 +3077,9 @@ static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
 }
 #endif
 
+bool inode_dio_finished(const struct inode *inode);
 void inode_dio_wait(struct inode *inode);
+void inode_dio_wait_interruptible(struct inode *inode);
 
 /**
  * inode_dio_begin - signal start of a direct I/O requests
@@ -2842,7 +3103,7 @@ static inline void inode_dio_begin(struct inode *inode)
 static inline void inode_dio_end(struct inode *inode)
 {
 	if (atomic_dec_and_test(&inode->i_dio_count))
-		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
+		wake_up_var(&inode->i_dio_count);
 }
 
 extern void inode_set_flags(struct inode *inode, unsigned int flags,
@@ -2852,16 +3113,23 @@ extern const struct file_operations generic_ro_fops;
 
 #define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))
 
-extern int readlink_copy(char __user *, int, const char *);
+extern int readlink_copy(char __user *, int, const char *, int);
 extern int page_readlink(struct dentry *, char __user *, int);
+extern const char *page_get_link_raw(struct dentry *, struct inode *,
+				     struct delayed_call *);
 extern const char *page_get_link(struct dentry *, struct inode *,
 				 struct delayed_call *);
 extern void page_put_link(void *);
 extern int page_symlink(struct inode *inode, const char *symname, int len);
 extern const struct inode_operations page_symlink_inode_operations;
 extern void kfree_link(void *);
-void generic_fillattr(struct mnt_idmap *, struct inode *, struct kstat *);
+void fill_mg_cmtime(struct kstat *stat, u32 request_mask, struct inode *inode);
+void generic_fillattr(struct mnt_idmap *, u32, struct inode *, struct kstat *);
 void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
+void generic_fill_statx_atomic_writes(struct kstat *stat,
+				      unsigned int unit_min,
+				      unsigned int unit_max,
+				      unsigned int unit_max_opt);
 extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
 extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 void __inode_add_bytes(struct inode *inode, loff_t bytes);
@@ -2899,13 +3167,15 @@ extern int vfs_readlink(struct dentry *, char __user *, int);
 extern struct file_system_type *get_filesystem(struct file_system_type *fs);
 extern void put_filesystem(struct file_system_type *fs);
 extern struct file_system_type *get_fs_type(const char *name);
-extern struct super_block *get_super(struct block_device *);
-extern struct super_block *get_active_super(struct block_device *bdev);
 extern void drop_super(struct super_block *sb);
 extern void drop_super_exclusive(struct super_block *sb);
-extern void iterate_supers(void (*)(struct super_block *, void *), void *);
+extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg);
 extern void iterate_supers_type(struct file_system_type *,
 			        void (*)(struct super_block *, void *), void *);
+void filesystems_freeze(bool freeze_all);
+void filesystems_thaw(void);
+
+void end_dirop(struct dentry *de);
 
 extern int dcache_dir_open(struct inode *, struct file *);
 extern int dcache_dir_close(struct inode *, struct file *);
@@ -2920,6 +3190,10 @@ extern int simple_open(struct inode *inode, struct file *file);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
+extern void __simple_unlink(struct inode *, struct dentry *);
+extern void __simple_rmdir(struct inode *, struct dentry *);
+void simple_rename_timestamp(struct inode *old_dir, struct dentry *old_dentry,
+			     struct inode *new_dir, struct dentry *new_dentry);
 extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
 				  struct inode *new_dir, struct dentry *new_dentry);
 extern int simple_rename(struct mnt_idmap *, struct inode *,
@@ -2927,17 +3201,23 @@ extern int simple_rename(struct mnt_idmap *, struct inode *,
 			 unsigned int);
 extern void simple_recursive_removal(struct dentry *,
                               void (*callback)(struct dentry *));
+extern void simple_remove_by_name(struct dentry *, const char *,
+                              void (*callback)(struct dentry *));
+extern void locked_recursive_removal(struct dentry *,
+                              void (*callback)(struct dentry *));
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
-extern int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct page **pagep, void **fsdata);
+extern int simple_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len,
+			      struct folio **foliop, void **fsdata);
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
-extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
-extern const struct dentry_operations simple_dentry_operations;
+struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name,
+					   const struct inode *context_inode);
+extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
@@ -2951,18 +3231,92 @@ extern int simple_fill_super(struct super_block *, unsigned long,
 			     const struct tree_descr *);
 extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
 extern void simple_release_fs(struct vfsmount **mount, int *count);
+struct dentry *simple_start_creating(struct dentry *, const char *);
+void simple_done_creating(struct dentry *);
 
 extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
 			loff_t *ppos, const void *from, size_t available);
 extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
 		const void __user *from, size_t count);
 
+struct offset_ctx {
+	struct maple_tree	mt;
+	unsigned long		next_offset;
+};
+
+void simple_offset_init(struct offset_ctx *octx);
+int simple_offset_add(struct offset_ctx *octx, struct dentry *dentry);
+void simple_offset_remove(struct offset_ctx *octx, struct dentry *dentry);
+int simple_offset_rename(struct inode *old_dir, struct dentry *old_dentry,
+			 struct inode *new_dir, struct dentry *new_dentry);
+int simple_offset_rename_exchange(struct inode *old_dir,
+				  struct dentry *old_dentry,
+				  struct inode *new_dir,
+				  struct dentry *new_dentry);
+void simple_offset_destroy(struct offset_ctx *octx);
+
+extern const struct file_operations simple_offset_dir_operations;
+
 extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
 extern int generic_file_fsync(struct file *, loff_t, loff_t, int);
 
 extern int generic_check_addressable(unsigned, u64);
 
-extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);
+extern void generic_set_sb_d_ops(struct super_block *sb);
+extern int generic_ci_match(const struct inode *parent,
+			    const struct qstr *name,
+			    const struct qstr *folded_name,
+			    const u8 *de_name, u32 de_name_len);
+
+#if IS_ENABLED(CONFIG_UNICODE)
+int generic_ci_d_hash(const struct dentry *dentry, struct qstr *str);
+int generic_ci_d_compare(const struct dentry *dentry, unsigned int len,
+			 const char *str, const struct qstr *name);
+
+/**
+ * generic_ci_validate_strict_name - Check if a given name is suitable
+ * for a directory
+ *
+ * This functions checks if the proposed filename is valid for the
+ * parent directory. That means that only valid UTF-8 filenames will be
+ * accepted for casefold directories from filesystems created with the
+ * strict encoding flag.  That also means that any name will be
+ * accepted for directories that doesn't have casefold enabled, or
+ * aren't being strict with the encoding.
+ *
+ * @dir: inode of the directory where the new file will be created
+ * @name: name of the new file
+ *
+ * Return:
+ * * True: if the filename is suitable for this directory. It can be
+ *   true if a given name is not suitable for a strict encoding
+ *   directory, but the directory being used isn't strict
+ * * False if the filename isn't suitable for this directory. This only
+ *   happens when a directory is casefolded and the filesystem is strict
+ *   about its encoding.
+ */
+static inline bool generic_ci_validate_strict_name(struct inode *dir,
+						   const struct qstr *name)
+{
+	if (!IS_CASEFOLDED(dir) || !sb_has_strict_encoding(dir->i_sb))
+		return true;
+
+	/*
+	 * A casefold dir must have a encoding set, unless the filesystem
+	 * is corrupted
+	 */
+	if (WARN_ON_ONCE(!dir->i_sb->s_encoding))
+		return true;
+
+	return !utf8_validate(dir->i_sb->s_encoding, name);
+}
+#else
+static inline bool generic_ci_validate_strict_name(struct inode *dir,
+						   const struct qstr *name)
+{
+	return true;
+}
+#endif
 
 int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
 		unsigned int ia_valid);
@@ -2973,9 +3327,14 @@ void setattr_copy(struct mnt_idmap *, struct inode *inode,
 
 extern int file_update_time(struct file *file);
 
+static inline bool file_is_dax(const struct file *file)
+{
+	return file && IS_DAX(file->f_mapping->host);
+}
+
 static inline bool vma_is_dax(const struct vm_area_struct *vma)
 {
-	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+	return file_is_dax(vma->vm_file);
 }
 
 static inline bool vma_is_fsdax(struct vm_area_struct *vma)
@@ -3006,7 +3365,8 @@ static inline int iocb_flags(struct file *file)
 	return res;
 }
 
-static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
+static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags,
+				     int rw_type)
 {
 	int kiocb_flags = 0;
 
@@ -3017,34 +3377,41 @@ static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
 		return 0;
 	if (unlikely(flags & ~RWF_SUPPORTED))
 		return -EOPNOTSUPP;
+	if (unlikely((flags & RWF_APPEND) && (flags & RWF_NOAPPEND)))
+		return -EINVAL;
 
 	if (flags & RWF_NOWAIT) {
 		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
 			return -EOPNOTSUPP;
-		kiocb_flags |= IOCB_NOIO;
+	}
+	if (flags & RWF_ATOMIC) {
+		if (rw_type != WRITE)
+			return -EOPNOTSUPP;
+		if (!(ki->ki_filp->f_mode & FMODE_CAN_ATOMIC_WRITE))
+			return -EOPNOTSUPP;
+	}
+	if (flags & RWF_DONTCACHE) {
+		/* file system must support it */
+		if (!(ki->ki_filp->f_op->fop_flags & FOP_DONTCACHE))
+			return -EOPNOTSUPP;
+		/* DAX mappings not supported */
+		if (IS_DAX(ki->ki_filp->f_mapping->host))
+			return -EOPNOTSUPP;
 	}
 	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
 	if (flags & RWF_SYNC)
 		kiocb_flags |= IOCB_DSYNC;
 
+	if ((flags & RWF_NOAPPEND) && (ki->ki_flags & IOCB_APPEND)) {
+		if (IS_APPEND(file_inode(ki->ki_filp)))
+			return -EPERM;
+		ki->ki_flags &= ~IOCB_APPEND;
+	}
+
 	ki->ki_flags |= kiocb_flags;
 	return 0;
 }
 
-static inline ino_t parent_ino(struct dentry *dentry)
-{
-	ino_t res;
-
-	/*
-	 * Don't strictly need d_lock here? If the parent ino could change
-	 * then surely we'd have a deeper race in the caller?
-	 */
-	spin_lock(&dentry->d_lock);
-	res = dentry->d_parent->d_inode->i_ino;
-	spin_unlock(&dentry->d_lock);
-	return res;
-}
-
 /* Transaction based IO helpers */
 
 /*
@@ -3124,11 +3491,9 @@ struct ctl_table;
 int __init list_bdev_fs_names(char *buf, size_t size);
 
 #define __FMODE_EXEC		((__force int) FMODE_EXEC)
-#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)
 
 #define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
-#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
-					    (flag & __FMODE_NONOTIFY)))
+#define OPEN_FMODE(flag) ((__force fmode_t)((flag + 1) & O_ACCMODE))
 
 static inline bool is_sxid(umode_t mode)
 {
@@ -3169,7 +3534,7 @@ static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
 static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
 {
 	return ctx->actor(ctx, "..", 2, ctx->pos,
-			  parent_ino(file->f_path.dentry), DT_DIR);
+			  d_parent_ino(file->f_path.dentry), DT_DIR);
 }
 static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
 {
@@ -3208,4 +3573,37 @@ extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
 extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
 			   int advice);
 
+static inline bool vfs_empty_path(int dfd, const char __user *path)
+{
+	char c;
+
+	if (dfd < 0)
+		return false;
+
+	/* We now allow NULL to be used for empty path. */
+	if (!path)
+		return true;
+
+	if (unlikely(get_user(c, path)))
+		return false;
+
+	return !c;
+}
+
+int generic_atomic_write_valid(struct kiocb *iocb, struct iov_iter *iter);
+
+static inline bool extensible_ioctl_valid(unsigned int cmd_a,
+					  unsigned int cmd_b, size_t min_size)
+{
+	if (_IOC_DIR(cmd_a) != _IOC_DIR(cmd_b))
+		return false;
+	if (_IOC_TYPE(cmd_a) != _IOC_TYPE(cmd_b))
+		return false;
+	if (_IOC_NR(cmd_a) != _IOC_NR(cmd_b))
+		return false;
+	if (_IOC_SIZE(cmd_a) < min_size)
+		return false;
+	return true;
+}
+
 #endif /* _LINUX_FS_H */
diff --git a/include/linux/fs/super.h b/include/linux/fs/super.h
new file mode 100644
index 000000000000..f21ffbb6dea5
--- /dev/null
+++ b/include/linux/fs/super.h
@@ -0,0 +1,238 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FS_SUPER_H
+#define _LINUX_FS_SUPER_H
+
+#include <linux/fs/super_types.h>
+#include <linux/unicode.h>
+
+/*
+ * These are internal functions, please use sb_start_{write,pagefault,intwrite}
+ * instead.
+ */
+static inline void __sb_end_write(struct super_block *sb, int level)
+{
+	percpu_up_read(sb->s_writers.rw_sem + level - 1);
+}
+
+static inline void __sb_start_write(struct super_block *sb, int level)
+{
+	percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true);
+}
+
+static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
+{
+	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
+}
+
+#define __sb_writers_acquired(sb, lev) \
+	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev) - 1], 1, _THIS_IP_)
+#define __sb_writers_release(sb, lev) \
+	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev) - 1], _THIS_IP_)
+
+/**
+ * __sb_write_started - check if sb freeze level is held
+ * @sb: the super we write to
+ * @level: the freeze level
+ *
+ * * > 0 - sb freeze level is held
+ * *   0 - sb freeze level is not held
+ * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN
+ */
+static inline int __sb_write_started(const struct super_block *sb, int level)
+{
+	return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1);
+}
+
+/**
+ * sb_write_started - check if SB_FREEZE_WRITE is held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_started(const struct super_block *sb)
+{
+	return __sb_write_started(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_write_not_started - check if SB_FREEZE_WRITE is not held
+ * @sb: the super we write to
+ *
+ * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN.
+ */
+static inline bool sb_write_not_started(const struct super_block *sb)
+{
+	return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0;
+}
+
+/**
+ * sb_end_write - drop write access to a superblock
+ * @sb: the super we wrote to
+ *
+ * Decrement number of writers to the filesystem. Wake up possible waiters
+ * wanting to freeze the filesystem.
+ */
+static inline void sb_end_write(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_end_pagefault - drop write access to a superblock from a page fault
+ * @sb: the super we wrote to
+ *
+ * Decrement number of processes handling write page fault to the filesystem.
+ * Wake up possible waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_pagefault(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
+}
+
+/**
+ * sb_end_intwrite - drop write access to a superblock for internal fs purposes
+ * @sb: the super we wrote to
+ *
+ * Decrement fs-internal number of writers to the filesystem.  Wake up possible
+ * waiters wanting to freeze the filesystem.
+ */
+static inline void sb_end_intwrite(struct super_block *sb)
+{
+	__sb_end_write(sb, SB_FREEZE_FS);
+}
+
+/**
+ * sb_start_write - get write access to a superblock
+ * @sb: the super we write to
+ *
+ * When a process wants to write data or metadata to a file system (i.e. dirty
+ * a page or an inode), it should embed the operation in a sb_start_write() -
+ * sb_end_write() pair to get exclusion against file system freezing. This
+ * function increments number of writers preventing freezing. If the file
+ * system is already frozen, the function waits until the file system is
+ * thawed.
+ *
+ * Since freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. Generally,
+ * freeze protection should be the outermost lock. In particular, we have:
+ *
+ * sb_start_write
+ *   -> i_rwsem			(write path, truncate, directory ops, ...)
+ *   -> s_umount		(freeze_super, thaw_super)
+ */
+static inline void sb_start_write(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_WRITE);
+}
+
+DEFINE_GUARD(super_write,
+	     struct super_block *,
+	     sb_start_write(_T),
+	     sb_end_write(_T))
+
+static inline bool sb_start_write_trylock(struct super_block *sb)
+{
+	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
+}
+
+/**
+ * sb_start_pagefault - get write access to a superblock from a page fault
+ * @sb: the super we write to
+ *
+ * When a process starts handling write page fault, it should embed the
+ * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
+ * exclusion against file system freezing. This is needed since the page fault
+ * is going to dirty a page. This function increments number of running page
+ * faults preventing freezing. If the file system is already frozen, the
+ * function waits until the file system is thawed.
+ *
+ * Since page fault freeze protection behaves as a lock, users have to preserve
+ * ordering of freeze protection and other filesystem locks. It is advised to
+ * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
+ * handling code implies lock dependency:
+ *
+ * mmap_lock
+ *   -> sb_start_pagefault
+ */
+static inline void sb_start_pagefault(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
+}
+
+/**
+ * sb_start_intwrite - get write access to a superblock for internal fs purposes
+ * @sb: the super we write to
+ *
+ * This is the third level of protection against filesystem freezing. It is
+ * free for use by a filesystem. The only requirement is that it must rank
+ * below sb_start_pagefault.
+ *
+ * For example filesystem can call sb_start_intwrite() when starting a
+ * transaction which somewhat eases handling of freezing for internal sources
+ * of filesystem changes (internal fs threads, discarding preallocation on file
+ * close, etc.).
+ */
+static inline void sb_start_intwrite(struct super_block *sb)
+{
+	__sb_start_write(sb, SB_FREEZE_FS);
+}
+
+static inline bool sb_start_intwrite_trylock(struct super_block *sb)
+{
+	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
+}
+
+static inline bool sb_rdonly(const struct super_block *sb)
+{
+	return sb->s_flags & SB_RDONLY;
+}
+
+static inline bool sb_is_blkdev_sb(struct super_block *sb)
+{
+	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
+}
+
+#if IS_ENABLED(CONFIG_UNICODE)
+static inline struct unicode_map *sb_encoding(const struct super_block *sb)
+{
+	return sb->s_encoding;
+}
+
+/* Compare if two super blocks have the same encoding and flags */
+static inline bool sb_same_encoding(const struct super_block *sb1,
+				    const struct super_block *sb2)
+{
+	if (sb1->s_encoding == sb2->s_encoding)
+		return true;
+
+	return (sb1->s_encoding && sb2->s_encoding &&
+		(sb1->s_encoding->version == sb2->s_encoding->version) &&
+		(sb1->s_encoding_flags == sb2->s_encoding_flags));
+}
+#else
+static inline struct unicode_map *sb_encoding(const struct super_block *sb)
+{
+	return NULL;
+}
+
+static inline bool sb_same_encoding(const struct super_block *sb1,
+				    const struct super_block *sb2)
+{
+	return true;
+}
+#endif
+
+static inline bool sb_has_encoding(const struct super_block *sb)
+{
+	return !!sb_encoding(sb);
+}
+
+int sb_set_blocksize(struct super_block *sb, int size);
+int __must_check sb_min_blocksize(struct super_block *sb, int size);
+
+int freeze_super(struct super_block *super, enum freeze_holder who,
+		 const void *freeze_owner);
+int thaw_super(struct super_block *super, enum freeze_holder who,
+	       const void *freeze_owner);
+
+#endif /* _LINUX_FS_SUPER_H */
diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h
new file mode 100644
index 000000000000..6bd3009e09b3
--- /dev/null
+++ b/include/linux/fs/super_types.h
@@ -0,0 +1,336 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FS_SUPER_TYPES_H
+#define _LINUX_FS_SUPER_TYPES_H
+
+#include <linux/fs_dirent.h>
+#include <linux/errseq.h>
+#include <linux/list_lru.h>
+#include <linux/list.h>
+#include <linux/list_bl.h>
+#include <linux/llist.h>
+#include <linux/uidgid.h>
+#include <linux/uuid.h>
+#include <linux/percpu-rwsem.h>
+#include <linux/workqueue_types.h>
+#include <linux/quota.h>
+
+struct backing_dev_info;
+struct block_device;
+struct dentry;
+struct dentry_operations;
+struct dquot_operations;
+struct export_operations;
+struct file;
+struct file_system_type;
+struct fscrypt_operations;
+struct fsnotify_sb_info;
+struct fsverity_operations;
+struct kstatfs;
+struct mount;
+struct mtd_info;
+struct quotactl_ops;
+struct shrinker;
+struct unicode_map;
+struct user_namespace;
+struct workqueue_struct;
+struct writeback_control;
+struct xattr_handler;
+
+extern struct super_block *blockdev_superblock;
+
+/* Possible states of 'frozen' field */
+enum {
+	SB_UNFROZEN		= 0,	/* FS is unfrozen */
+	SB_FREEZE_WRITE		= 1,	/* Writes, dir ops, ioctls frozen */
+	SB_FREEZE_PAGEFAULT	= 2,	/* Page faults stopped as well */
+	SB_FREEZE_FS		= 3,	/* For internal FS use (e.g. to stop internal threads if needed) */
+	SB_FREEZE_COMPLETE	= 4,	/* ->freeze_fs finished successfully */
+};
+
+#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)
+
+struct sb_writers {
+	unsigned short			frozen;		/* Is sb frozen? */
+	int				freeze_kcount;	/* How many kernel freeze requests? */
+	int				freeze_ucount;	/* How many userspace freeze requests? */
+	const void			*freeze_owner;	/* Owner of the freeze */
+	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
+};
+
+/**
+ * enum freeze_holder - holder of the freeze
+ * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem
+ * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem
+ * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed
+ * @FREEZE_EXCL: a freeze that can only be undone by the owner
+ *
+ * Indicate who the owner of the freeze or thaw request is and whether
+ * the freeze needs to be exclusive or can nest.
+ * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the
+ * same holder aren't allowed. It is however allowed to hold a single
+ * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at
+ * the same time. This is relied upon by some filesystems during online
+ * repair or similar.
+ */
+enum freeze_holder {
+	FREEZE_HOLDER_KERNEL	= (1U << 0),
+	FREEZE_HOLDER_USERSPACE	= (1U << 1),
+	FREEZE_MAY_NEST		= (1U << 2),
+	FREEZE_EXCL		= (1U << 3),
+};
+
+struct super_operations {
+	struct inode *(*alloc_inode)(struct super_block *sb);
+	void (*destroy_inode)(struct inode *inode);
+	void (*free_inode)(struct inode *inode);
+	void (*dirty_inode)(struct inode *inode, int flags);
+	int (*write_inode)(struct inode *inode, struct writeback_control *wbc);
+	int (*drop_inode)(struct inode *inode);
+	void (*evict_inode)(struct inode *inode);
+	void (*put_super)(struct super_block *sb);
+	int (*sync_fs)(struct super_block *sb, int wait);
+	int (*freeze_super)(struct super_block *sb, enum freeze_holder who,
+			    const void *owner);
+	int (*freeze_fs)(struct super_block *sb);
+	int (*thaw_super)(struct super_block *sb, enum freeze_holder who,
+			  const void *owner);
+	int (*unfreeze_fs)(struct super_block *sb);
+	int (*statfs)(struct dentry *dentry, struct kstatfs *kstatfs);
+	int (*remount_fs) (struct super_block *, int *, char *);
+	void (*umount_begin)(struct super_block *sb);
+
+	int (*show_options)(struct seq_file *seq, struct dentry *dentry);
+	int (*show_devname)(struct seq_file *seq, struct dentry *dentry);
+	int (*show_path)(struct seq_file *seq, struct dentry *dentry);
+	int (*show_stats)(struct seq_file *seq, struct dentry *dentry);
+#ifdef CONFIG_QUOTA
+	ssize_t (*quota_read)(struct super_block *sb, int type, char *data,
+			      size_t len, loff_t off);
+	ssize_t (*quota_write)(struct super_block *sb, int type,
+			       const char *data, size_t len, loff_t off);
+	struct dquot __rcu **(*get_dquots)(struct inode *inode);
+#endif
+	long (*nr_cached_objects)(struct super_block *sb,
+				  struct shrink_control *sc);
+	long (*free_cached_objects)(struct super_block *sb,
+				    struct shrink_control *sc);
+	/*
+	 * If a filesystem can support graceful removal of a device and
+	 * continue read-write operations, implement this callback.
+	 *
+	 * Return 0 if the filesystem can continue read-write.
+	 * Non-zero return value or no such callback means the fs will be shutdown
+	 * as usual.
+	 */
+	int (*remove_bdev)(struct super_block *sb, struct block_device *bdev);
+	void (*shutdown)(struct super_block *sb);
+};
+
+struct super_block {
+	struct list_head			s_list;		/* Keep this first */
+	dev_t					s_dev;		/* search index; _not_ kdev_t */
+	unsigned char				s_blocksize_bits;
+	unsigned long				s_blocksize;
+	loff_t					s_maxbytes;	/* Max file size */
+	struct file_system_type			*s_type;
+	const struct super_operations		*s_op;
+	const struct dquot_operations		*dq_op;
+	const struct quotactl_ops		*s_qcop;
+	const struct export_operations		*s_export_op;
+	unsigned long				s_flags;
+	unsigned long				s_iflags;	/* internal SB_I_* flags */
+	unsigned long				s_magic;
+	struct dentry				*s_root;
+	struct rw_semaphore			s_umount;
+	int					s_count;
+	atomic_t				s_active;
+#ifdef CONFIG_SECURITY
+	void					*s_security;
+#endif
+	const struct xattr_handler		*const *s_xattr;
+#ifdef CONFIG_FS_ENCRYPTION
+	const struct fscrypt_operations		*s_cop;
+	struct fscrypt_keyring			*s_master_keys; /* master crypto keys in use */
+#endif
+#ifdef CONFIG_FS_VERITY
+	const struct fsverity_operations	*s_vop;
+#endif
+#if IS_ENABLED(CONFIG_UNICODE)
+	struct unicode_map			*s_encoding;
+	__u16					s_encoding_flags;
+#endif
+	struct hlist_bl_head			s_roots;	/* alternate root dentries for NFS */
+	struct mount				*s_mounts;	/* list of mounts; _not_ for fs use */
+	struct block_device			*s_bdev;	/* can go away once we use an accessor for @s_bdev_file */
+	struct file				*s_bdev_file;
+	struct backing_dev_info 		*s_bdi;
+	struct mtd_info				*s_mtd;
+	struct hlist_node			s_instances;
+	unsigned int				s_quota_types;	/* Bitmask of supported quota types */
+	struct quota_info			s_dquot;	/* Diskquota specific options */
+
+	struct sb_writers			s_writers;
+
+	/*
+	 * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
+	 * s_fsnotify_info together for cache efficiency. They are frequently
+	 * accessed and rarely modified.
+	 */
+	void					*s_fs_info;	/* Filesystem private info */
+
+	/* Granularity of c/m/atime in ns (cannot be worse than a second) */
+	u32					s_time_gran;
+	/* Time limits for c/m/atime in seconds */
+	time64_t				s_time_min;
+	time64_t		   		s_time_max;
+#ifdef CONFIG_FSNOTIFY
+	u32					s_fsnotify_mask;
+	struct fsnotify_sb_info			*s_fsnotify_info;
+#endif
+
+	/*
+	 * q: why are s_id and s_sysfs_name not the same? both are human
+	 * readable strings that identify the filesystem
+	 * a: s_id is allowed to change at runtime; it's used in log messages,
+	 * and we want to when a device starts out as single device (s_id is dev
+	 * name) but then a device is hot added and we have to switch to
+	 * identifying it by UUID
+	 * but s_sysfs_name is a handle for programmatic access, and can't
+	 * change at runtime
+	 */
+	char					s_id[32];	/* Informational name */
+	uuid_t					s_uuid;		/* UUID */
+	u8					s_uuid_len;	/* Default 16, possibly smaller for weird filesystems */
+
+	/* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */
+	char					s_sysfs_name[UUID_STRING_LEN + 1];
+
+	unsigned int				s_max_links;
+	unsigned int				s_d_flags;	/* default d_flags for dentries */
+
+	/*
+	 * The next field is for VFS *only*. No filesystems have any business
+	 * even looking at it. You had been warned.
+	 */
+	struct mutex				s_vfs_rename_mutex;	/* Kludge */
+
+	/*
+	 * Filesystem subtype.  If non-empty the filesystem type field
+	 * in /proc/mounts will be "type.subtype"
+	 */
+	const char				*s_subtype;
+
+	const struct dentry_operations		*__s_d_op; /* default d_op for dentries */
+
+	struct shrinker				*s_shrink;	/* per-sb shrinker handle */
+
+	/* Number of inodes with nlink == 0 but still referenced */
+	atomic_long_t				s_remove_count;
+
+	/* Read-only state of the superblock is being changed */
+	int					s_readonly_remount;
+
+	/* per-sb errseq_t for reporting writeback errors via syncfs */
+	errseq_t s_wb_err;
+
+	/* AIO completions deferred from interrupt context */
+	struct workqueue_struct			*s_dio_done_wq;
+	struct hlist_head			s_pins;
+
+	/*
+	 * Owning user namespace and default context in which to
+	 * interpret filesystem uids, gids, quotas, device nodes,
+	 * xattrs and security labels.
+	 */
+	struct user_namespace			*s_user_ns;
+
+	/*
+	 * The list_lru structure is essentially just a pointer to a table
+	 * of per-node lru lists, each of which has its own spinlock.
+	 * There is no need to put them into separate cachelines.
+	 */
+	struct list_lru				s_dentry_lru;
+	struct list_lru				s_inode_lru;
+	struct rcu_head				rcu;
+	struct work_struct			destroy_work;
+
+	struct mutex				s_sync_lock;	/* sync serialisation lock */
+
+	/*
+	 * Indicates how deep in a filesystem stack this SB is
+	 */
+	int s_stack_depth;
+
+	/* s_inode_list_lock protects s_inodes */
+	spinlock_t				s_inode_list_lock ____cacheline_aligned_in_smp;
+	struct list_head			s_inodes;	/* all inodes */
+
+	spinlock_t				s_inode_wblist_lock;
+	struct list_head			s_inodes_wb;	/* writeback inodes */
+	long					s_min_writeback_pages;
+} __randomize_layout;
+
+/*
+ * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
+ * represented in both.
+ */
+#define SB_RDONLY       BIT(0)	/* Mount read-only */
+#define SB_NOSUID       BIT(1)	/* Ignore suid and sgid bits */
+#define SB_NODEV        BIT(2)	/* Disallow access to device special files */
+#define SB_NOEXEC       BIT(3)	/* Disallow program execution */
+#define SB_SYNCHRONOUS  BIT(4)	/* Writes are synced at once */
+#define SB_MANDLOCK     BIT(6)	/* Allow mandatory locks on an FS */
+#define SB_DIRSYNC      BIT(7)	/* Directory modifications are synchronous */
+#define SB_NOATIME      BIT(10)	/* Do not update access times. */
+#define SB_NODIRATIME   BIT(11)	/* Do not update directory access times */
+#define SB_SILENT       BIT(15)
+#define SB_POSIXACL     BIT(16)	/* Supports POSIX ACLs */
+#define SB_INLINECRYPT  BIT(17)	/* Use blk-crypto for encrypted files */
+#define SB_KERNMOUNT    BIT(22)	/* this is a kern_mount call */
+#define SB_I_VERSION    BIT(23)	/* Update inode I_version field */
+#define SB_LAZYTIME     BIT(25)	/* Update the on-disk [acm]times lazily */
+
+/* These sb flags are internal to the kernel */
+#define SB_DEAD         BIT(21)
+#define SB_DYING        BIT(24)
+#define SB_FORCE        BIT(27)
+#define SB_NOSEC        BIT(28)
+#define SB_BORN         BIT(29)
+#define SB_ACTIVE       BIT(30)
+#define SB_NOUSER       BIT(31)
+
+/* These flags relate to encoding and casefolding */
+#define SB_ENC_STRICT_MODE_FL		(1 << 0)
+#define SB_ENC_NO_COMPAT_FALLBACK_FL	(1 << 1)
+
+#define sb_has_strict_encoding(sb) \
+	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)
+
+#if IS_ENABLED(CONFIG_UNICODE)
+#define sb_no_casefold_compat_fallback(sb) \
+	(sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL)
+#else
+#define sb_no_casefold_compat_fallback(sb) (1)
+#endif
+
+/* sb->s_iflags */
+#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
+#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
+#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
+#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */
+
+/* sb->s_iflags to limit user namespace mounts */
+#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
+#define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
+#define SB_I_UNTRUSTED_MOUNTER		0x00000040
+#define SB_I_EVM_HMAC_UNSUPPORTED	0x00000080
+
+#define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
+#define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
+#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
+#define SB_I_RETIRED	0x00000800	/* superblock shouldn't be reused */
+#define SB_I_NOUMASK	0x00001000	/* VFS does not apply umask */
+#define SB_I_NOIDMAP	0x00002000	/* No idmapped mounts on this superblock */
+#define SB_I_ALLOW_HSM	0x00004000	/* Allow HSM events on this superblock */
+
+#endif /* _LINUX_FS_SUPER_TYPES_H */
diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index ff6341e09925..0d6c8a6d7be2 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -109,6 +109,7 @@ struct fs_context {
 	bool			need_free:1;	/* Need to call ops->free() */
 	bool			global:1;	/* Goes into &init_user_ns */
 	bool			oldapi:1;	/* Coming from mount(2) */
+	bool			exclusive:1;    /* create new superblock, reject existing one */
 };
 
 struct fs_context_operations {
@@ -133,16 +134,21 @@ extern struct fs_context *fs_context_for_submount(struct file_system_type *fs_ty
 
 extern struct fs_context *vfs_dup_fs_context(struct fs_context *fc);
 extern int vfs_parse_fs_param(struct fs_context *fc, struct fs_parameter *param);
-extern int vfs_parse_fs_string(struct fs_context *fc, const char *key,
-			       const char *value, size_t v_size);
+extern int vfs_parse_fs_qstr(struct fs_context *fc, const char *key,
+				const struct qstr *value);
+static inline int vfs_parse_fs_string(struct fs_context *fc, const char *key,
+			       const char *value)
+{
+	return vfs_parse_fs_qstr(fc, key, value ? &QSTR(value) : NULL);
+}
+int vfs_parse_monolithic_sep(struct fs_context *fc, void *data,
+			     char *(*sep)(char **));
 extern int generic_parse_monolithic(struct fs_context *fc, void *data);
 extern int vfs_get_tree(struct fs_context *fc);
 extern void put_fs_context(struct fs_context *fc);
 extern int vfs_parse_fs_param_source(struct fs_context *fc,
 				     struct fs_parameter *param);
 extern void fc_drop_locked(struct fs_context *fc);
-int reconfigure_single(struct super_block *s,
-		       int flags, void *data);
 
 extern int get_tree_nodev(struct fs_context *fc,
 			 int (*fill_super)(struct super_block *sb,
@@ -150,14 +156,19 @@ extern int get_tree_nodev(struct fs_context *fc,
 extern int get_tree_single(struct fs_context *fc,
 			 int (*fill_super)(struct super_block *sb,
 					   struct fs_context *fc));
-extern int get_tree_single_reconf(struct fs_context *fc,
-			 int (*fill_super)(struct super_block *sb,
-					   struct fs_context *fc));
 extern int get_tree_keyed(struct fs_context *fc,
 			 int (*fill_super)(struct super_block *sb,
 					   struct fs_context *fc),
 			 void *key);
 
+int setup_bdev_super(struct super_block *sb, int sb_flags,
+		struct fs_context *fc);
+
+#define GET_TREE_BDEV_QUIET_LOOKUP		0x0001
+int get_tree_bdev_flags(struct fs_context *fc,
+		int (*fill_super)(struct super_block *sb,
+				  struct fs_context *fc), unsigned int flags);
+
 extern int get_tree_bdev(struct fs_context *fc,
 			       int (*fill_super)(struct super_block *sb,
 						 struct fs_context *fc));
@@ -180,10 +191,12 @@ struct fc_log {
 extern __attribute__((format(printf, 4, 5)))
 void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt, ...);
 
-#define __logfc(fc, l, fmt, ...) logfc((fc)->log.log, NULL, \
-					l, fmt, ## __VA_ARGS__)
-#define __plog(p, l, fmt, ...) logfc((p)->log, (p)->prefix, \
-					l, fmt, ## __VA_ARGS__)
+#define __logfc(fc, l, fmt, ...) \
+	logfc((fc)->log.log, NULL, (l), (fmt), ## __VA_ARGS__)
+#define __plogp(p, prefix, l, fmt, ...) \
+	logfc((p)->log, (prefix), (l), (fmt), ## __VA_ARGS__)
+#define __plog(p, l, fmt, ...) __plogp(p, (p)->prefix, l, fmt, ## __VA_ARGS__)
+
 /**
  * infof - Store supplementary informational message
  * @fc: The context in which to log the informational message
@@ -194,7 +207,9 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
  */
 #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__)
 #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__)
-#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
+#define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
+#define infofcp(fc, prefix, fmt, ...) \
+	__plogp((&(fc)->log), prefix, 'i', fmt, ## __VA_ARGS__)
 
 /**
  * warnf - Store supplementary warning message
@@ -207,6 +222,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
 #define warnf(fc, fmt, ...) __logfc(fc, 'w', fmt, ## __VA_ARGS__)
 #define warn_plog(p, fmt, ...) __plog(p, 'w', fmt, ## __VA_ARGS__)
 #define warnfc(fc, fmt, ...) __plog((&(fc)->log), 'w', fmt, ## __VA_ARGS__)
+#define warnfcp(fc, prefix, fmt, ...) \
+	__plogp((&(fc)->log), prefix, 'w', fmt, ## __VA_ARGS__)
 
 /**
  * errorf - Store supplementary error message
@@ -219,6 +236,8 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
 #define errorf(fc, fmt, ...) __logfc(fc, 'e', fmt, ## __VA_ARGS__)
 #define error_plog(p, fmt, ...) __plog(p, 'e', fmt, ## __VA_ARGS__)
 #define errorfc(fc, fmt, ...) __plog((&(fc)->log), 'e', fmt, ## __VA_ARGS__)
+#define errorfcp(fc, prefix, fmt, ...) \
+	__plogp((&(fc)->log), prefix, 'e', fmt, ## __VA_ARGS__)
 
 /**
  * invalf - Store supplementary invalid argument error message
@@ -231,5 +250,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
 #define invalf(fc, fmt, ...) (errorf(fc, fmt, ## __VA_ARGS__), -EINVAL)
 #define inval_plog(p, fmt, ...) (error_plog(p, fmt, ## __VA_ARGS__), -EINVAL)
 #define invalfc(fc, fmt, ...) (errorfc(fc, fmt, ## __VA_ARGS__), -EINVAL)
+#define invalfcp(fc, prefix, fmt, ...) \
+	(errorfcp(fc, prefix, fmt, ## __VA_ARGS__), -EINVAL)
 
 #endif /* _LINUX_FS_CONTEXT_H */
diff --git a/include/linux/fs_types.h b/include/linux/fs_dirent.h
index 54816791196f..92f75c5bac19 100644
--- a/include/linux/fs_types.h
+++ b/include/linux/fs_dirent.h
@@ -1,6 +1,9 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_FS_TYPES_H
-#define _LINUX_FS_TYPES_H
+#ifndef _LINUX_FS_DIRENT_H
+#define _LINUX_FS_DIRENT_H
+
+#include <linux/stat.h>
+#include <linux/types.h>
 
 /*
  * This is a header for the common implementation of dirent
@@ -66,10 +69,10 @@
 
 /*
  * declarations for helper functions, accompanying implementation
- * is in fs/fs_types.c
+ * is in fs/fs_dirent.c
  */
 extern unsigned char fs_ftype_to_dtype(unsigned int filetype);
 extern unsigned char fs_umode_to_ftype(umode_t mode);
 extern unsigned char fs_umode_to_dtype(umode_t mode);
 
-#endif
+#endif /* _LINUX_FS_DIRENT_H */
diff --git a/include/linux/fs_enet_pd.h b/include/linux/fs_enet_pd.h
deleted file mode 100644
index 77d783f71527..000000000000
--- a/include/linux/fs_enet_pd.h
+++ /dev/null
@@ -1,165 +0,0 @@
-/*
- * Platform information definitions for the
- * universal Freescale Ethernet driver.
- *
- * Copyright (c) 2003 Intracom S.A. 
- *  by Pantelis Antoniou <panto@intracom.gr>
- *
- * 2005 (c) MontaVista Software, Inc. 
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License 
- * version 2. This program is licensed "as is" without any warranty of any 
- * kind, whether express or implied.
- */
-
-#ifndef FS_ENET_PD_H
-#define FS_ENET_PD_H
-
-#include <linux/clk.h>
-#include <linux/string.h>
-#include <linux/of_mdio.h>
-#include <linux/if_ether.h>
-#include <asm/types.h>
-
-#define FS_ENET_NAME	"fs_enet"
-
-enum fs_id {
-	fsid_fec1,
-	fsid_fec2,
-	fsid_fcc1,
-	fsid_fcc2,
-	fsid_fcc3,
-	fsid_scc1,
-	fsid_scc2,
-	fsid_scc3,
-	fsid_scc4,
-};
-
-#define FS_MAX_INDEX	9
-
-static inline int fs_get_fec_index(enum fs_id id)
-{
-	if (id >= fsid_fec1 && id <= fsid_fec2)
-		return id - fsid_fec1;
-	return -1;
-}
-
-static inline int fs_get_fcc_index(enum fs_id id)
-{
-	if (id >= fsid_fcc1 && id <= fsid_fcc3)
-		return id - fsid_fcc1;
-	return -1;
-}
-
-static inline int fs_get_scc_index(enum fs_id id)
-{
-	if (id >= fsid_scc1 && id <= fsid_scc4)
-		return id - fsid_scc1;
-	return -1;
-}
-
-static inline int fs_fec_index2id(int index)
-{
-	int id = fsid_fec1 + index - 1;
-	if (id >= fsid_fec1 && id <= fsid_fec2)
-		return id;
-	return FS_MAX_INDEX;
-		}
-
-static inline int fs_fcc_index2id(int index)
-{
-	int id = fsid_fcc1 + index - 1;
-	if (id >= fsid_fcc1 && id <= fsid_fcc3)
-		return id;
-	return FS_MAX_INDEX;
-}
-
-static inline int fs_scc_index2id(int index)
-{
-	int id = fsid_scc1 + index - 1;
-	if (id >= fsid_scc1 && id <= fsid_scc4)
-		return id;
-	return FS_MAX_INDEX;
-}
-
-enum fs_mii_method {
-	fsmii_fixed,
-	fsmii_fec,
-	fsmii_bitbang,
-};
-
-enum fs_ioport {
-	fsiop_porta,
-	fsiop_portb,
-	fsiop_portc,
-	fsiop_portd,
-	fsiop_porte,
-};
-
-struct fs_mii_bit {
-	u32 offset;
-	u8 bit;
-	u8 polarity;
-};
-struct fs_mii_bb_platform_info {
-	struct fs_mii_bit 	mdio_dir;
-	struct fs_mii_bit 	mdio_dat;
-	struct fs_mii_bit	mdc_dat;
-	int delay;	/* delay in us         */
-	int irq[32]; 	/* irqs per phy's */
-};
-
-struct fs_platform_info {
-
-	void(*init_ioports)(struct fs_platform_info *);
-	/* device specific information */
-	int fs_no;		/* controller index            */
-	char fs_type[4];	/* controller type             */
-
-	u32 cp_page;		/* CPM page */
-	u32 cp_block;		/* CPM sblock */
-	u32 cp_command;		/* CPM page/sblock/mcn */
-
-	u32 clk_trx;		/* some stuff for pins & mux configuration*/
-	u32 clk_rx;
-	u32 clk_tx;
-	u32 clk_route;
-	u32 clk_mask;
-
-	u32 mem_offset;
-	u32 dpram_offset;
-	u32 fcc_regs_c;
-	
-	u32 device_flags;
-
-	struct device_node *phy_node;
-	const struct fs_mii_bus_info *bus_info;
-
-	int rx_ring, tx_ring;	/* number of buffers on rx     */
-	__u8 macaddr[ETH_ALEN];	/* mac address                 */
-	int rx_copybreak;	/* limit we copy small frames  */
-	int napi_weight;	/* NAPI weight                 */
-
-	int use_rmii;		/* use RMII mode 	       */
-	int has_phy;            /* if the network is phy container as well...*/
-
-	struct clk *clk_per;	/* 'per' clock for register access */
-};
-struct fs_mii_fec_platform_info {
-	u32 irq[32];
-	u32 mii_speed;
-};
-
-static inline int fs_get_id(struct fs_platform_info *fpi)
-{
-	if(strstr(fpi->fs_type, "SCC"))
-		return fs_scc_index2id(fpi->fs_no);
-	if(strstr(fpi->fs_type, "FCC"))
-		return fs_fcc_index2id(fpi->fs_no);
-	if(strstr(fpi->fs_type, "FEC"))
-		return fs_fec_index2id(fpi->fs_no);
-	return fpi->fs_no;
-}
-
-#endif
diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h
index 01542c4b87a2..5e8a3b546033 100644
--- a/include/linux/fs_parser.h
+++ b/include/linux/fs_parser.h
@@ -28,7 +28,8 @@ typedef int fs_param_type(struct p_log *,
  */
 fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64,
 	fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev,
-	fs_param_is_path, fs_param_is_fd;
+	fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid,
+	fs_param_is_file_or_string;
 
 /*
  * Specification of the type of value a parameter wants.
@@ -57,6 +58,8 @@ struct fs_parse_result {
 		int		int_32;		/* For spec_s32/spec_enum */
 		unsigned int	uint_32;	/* For spec_u32{,_octal,_hex}/spec_enum */
 		u64		uint_64;	/* For spec_u64 */
+		kuid_t		uid;
+		kgid_t		gid;
 	};
 };
 
@@ -81,15 +84,12 @@ extern int fs_lookup_param(struct fs_context *fc,
 
 extern int lookup_constant(const struct constant_table tbl[], const char *name, int not_found);
 
+extern const struct constant_table bool_names[];
+
 #ifdef CONFIG_VALIDATE_FS_PARSER
-extern bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size,
-				    int low, int high, int special);
 extern bool fs_validate_description(const char *name,
 				    const struct fs_parameter_spec *desc);
 #else
-static inline bool validate_constant_table(const struct constant_table *tbl, size_t tbl_size,
-					   int low, int high, int special)
-{ return true; }
 static inline bool fs_validate_description(const char *name,
 					   const struct fs_parameter_spec *desc)
 { return true; }
@@ -121,7 +121,7 @@ static inline bool fs_validate_description(const char *name,
 #define fsparam_u32oct(NAME, OPT) \
 			__fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)8)
 #define fsparam_u32hex(NAME, OPT) \
-			__fsparam(fs_param_is_u32_hex, NAME, OPT, 0, (void *)16)
+			__fsparam(fs_param_is_u32, NAME, OPT, 0, (void *)16)
 #define fsparam_s32(NAME, OPT)	__fsparam(fs_param_is_s32, NAME, OPT, 0, NULL)
 #define fsparam_u64(NAME, OPT)	__fsparam(fs_param_is_u64, NAME, OPT, 0, NULL)
 #define fsparam_enum(NAME, OPT, array)	__fsparam(fs_param_is_enum, NAME, OPT, 0, array)
@@ -131,5 +131,13 @@ static inline bool fs_validate_description(const char *name,
 #define fsparam_bdev(NAME, OPT)	__fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL)
 #define fsparam_path(NAME, OPT)	__fsparam(fs_param_is_path, NAME, OPT, 0, NULL)
 #define fsparam_fd(NAME, OPT)	__fsparam(fs_param_is_fd, NAME, OPT, 0, NULL)
+#define fsparam_file_or_string(NAME, OPT) \
+				__fsparam(fs_param_is_file_or_string, NAME, OPT, 0, NULL)
+#define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL)
+#define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL)
+
+/* String parameter that allows empty argument */
+#define fsparam_string_empty(NAME, OPT) \
+	__fsparam(fs_param_is_string, NAME, OPT, fs_param_can_be_empty, NULL)
 
 #endif /* _LINUX_FS_PARSER_H */
diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h
index 54210a42c30d..0cc2fa283305 100644
--- a/include/linux/fs_stack.h
+++ b/include/linux/fs_stack.h
@@ -3,7 +3,7 @@
 #define _LINUX_FS_STACK_H
 
 /* This file defines generic functions used primarily by stackable
- * filesystems; none of these functions require i_mutex to be held.
+ * filesystems; none of these functions require i_rwsem to be held.
  */
 
 #include <linux/fs.h>
@@ -16,15 +16,15 @@ extern void fsstack_copy_inode_size(struct inode *dst, struct inode *src);
 static inline void fsstack_copy_attr_atime(struct inode *dest,
 					   const struct inode *src)
 {
-	dest->i_atime = src->i_atime;
+	inode_set_atime_to_ts(dest, inode_get_atime(src));
 }
 
 static inline void fsstack_copy_attr_times(struct inode *dest,
 					   const struct inode *src)
 {
-	dest->i_atime = src->i_atime;
-	dest->i_mtime = src->i_mtime;
-	dest->i_ctime = src->i_ctime;
+	inode_set_atime_to_ts(dest, inode_get_atime(src));
+	inode_set_mtime_to_ts(dest, inode_get_mtime(src));
+	inode_set_ctime_to_ts(dest, inode_get_ctime(src));
 }
 
 #endif /* _LINUX_FS_STACK_H */
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 783b48dedb72..0070764b790a 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -2,14 +2,14 @@
 #ifndef _LINUX_FS_STRUCT_H
 #define _LINUX_FS_STRUCT_H
 
+#include <linux/sched.h>
 #include <linux/path.h>
 #include <linux/spinlock.h>
 #include <linux/seqlock.h>
 
 struct fs_struct {
 	int users;
-	spinlock_t lock;
-	seqcount_spinlock_t seq;
+	seqlock_t seq;
 	int umask;
 	int in_exec;
 	struct path root, pwd;
@@ -26,20 +26,25 @@ extern int unshare_fs_struct(void);
 
 static inline void get_fs_root(struct fs_struct *fs, struct path *root)
 {
-	spin_lock(&fs->lock);
+	read_seqlock_excl(&fs->seq);
 	*root = fs->root;
 	path_get(root);
-	spin_unlock(&fs->lock);
+	read_sequnlock_excl(&fs->seq);
 }
 
 static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd)
 {
-	spin_lock(&fs->lock);
+	read_seqlock_excl(&fs->seq);
 	*pwd = fs->pwd;
 	path_get(pwd);
-	spin_unlock(&fs->lock);
+	read_sequnlock_excl(&fs->seq);
 }
 
 extern bool current_chrooted(void);
 
+static inline int current_umask(void)
+{
+	return current->fs->umask;
+}
+
 #endif /* _LINUX_FS_STRUCT_H */
diff --git a/include/linux/fs_uart_pd.h b/include/linux/fs_uart_pd.h
deleted file mode 100644
index 36b61ff39277..000000000000
--- a/include/linux/fs_uart_pd.h
+++ /dev/null
@@ -1,71 +0,0 @@
-/*
- * Platform information definitions for the CPM Uart driver.
- *
- * 2006 (c) MontaVista Software, Inc.
- * Vitaly Bordug <vbordug@ru.mvista.com>
- *
- * This file is licensed under the terms of the GNU General Public License
- * version 2. This program is licensed "as is" without any warranty of any
- * kind, whether express or implied.
- */
-
-#ifndef FS_UART_PD_H
-#define FS_UART_PD_H
-
-#include <asm/types.h>
-
-enum fs_uart_id {
-	fsid_smc1_uart,
-	fsid_smc2_uart,
-	fsid_scc1_uart,
-	fsid_scc2_uart,
-	fsid_scc3_uart,
-	fsid_scc4_uart,
-	fs_uart_nr,
-};
-
-static inline int fs_uart_id_scc2fsid(int id)
-{
-    return fsid_scc1_uart + id - 1;
-}
-
-static inline int fs_uart_id_fsid2scc(int id)
-{
-    return id - fsid_scc1_uart + 1;
-}
-
-static inline int fs_uart_id_smc2fsid(int id)
-{
-    return fsid_smc1_uart + id - 1;
-}
-
-static inline int fs_uart_id_fsid2smc(int id)
-{
-    return id - fsid_smc1_uart + 1;
-}
-
-struct fs_uart_platform_info {
-        void(*init_ioports)(struct fs_uart_platform_info *);
-	/* device specific information */
-	int fs_no;		/* controller index */
-	char fs_type[4];        /* controller type  */
-	u32 uart_clk;
-	u8 tx_num_fifo;
-	u8 tx_buf_size;
-	u8 rx_num_fifo;
-	u8 rx_buf_size;
-	u8 brg;
-	u8 clk_rx;
-	u8 clk_tx;
-};
-
-static inline int fs_uart_get_id(struct fs_uart_platform_info *fpi)
-{
-        if(strstr(fpi->fs_type, "SMC"))
-                return fs_uart_id_smc2fsid(fpi->fs_no);
-        if(strstr(fpi->fs_type, "SCC"))
-                return fs_uart_id_scc2fsid(fpi->fs_no);
-        return fpi->fs_no;
-}
-
-#endif
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
index a174cedf4d90..4c91a019972b 100644
--- a/include/linux/fscache-cache.h
+++ b/include/linux/fscache-cache.h
@@ -19,6 +19,7 @@
 enum fscache_cache_trace;
 enum fscache_cookie_trace;
 enum fscache_access_trace;
+enum fscache_volume_trace;
 
 enum fscache_cache_state {
 	FSCACHE_CACHE_IS_NOT_PRESENT,	/* No cache is present for this name */
@@ -97,6 +98,11 @@ extern void fscache_withdraw_cookie(struct fscache_cookie *cookie);
 
 extern void fscache_io_error(struct fscache_cache *cache);
 
+extern struct fscache_volume *
+fscache_try_get_volume(struct fscache_volume *volume,
+		       enum fscache_volume_trace where);
+extern void fscache_put_volume(struct fscache_volume *volume,
+			       enum fscache_volume_trace where);
 extern void fscache_end_volume_access(struct fscache_volume *volume,
 				      struct fscache_cookie *cookie,
 				      enum fscache_access_trace why);
@@ -189,17 +195,20 @@ extern atomic_t fscache_n_write;
 extern atomic_t fscache_n_no_write_space;
 extern atomic_t fscache_n_no_create_space;
 extern atomic_t fscache_n_culled;
+extern atomic_t fscache_n_dio_misfit;
 #define fscache_count_read() atomic_inc(&fscache_n_read)
 #define fscache_count_write() atomic_inc(&fscache_n_write)
 #define fscache_count_no_write_space() atomic_inc(&fscache_n_no_write_space)
 #define fscache_count_no_create_space() atomic_inc(&fscache_n_no_create_space)
 #define fscache_count_culled() atomic_inc(&fscache_n_culled)
+#define fscache_count_dio_misfit() atomic_inc(&fscache_n_dio_misfit)
 #else
 #define fscache_count_read() do {} while(0)
 #define fscache_count_write() do {} while(0)
 #define fscache_count_no_write_space() do {} while(0)
 #define fscache_count_no_create_space() do {} while(0)
 #define fscache_count_culled() do {} while(0)
+#define fscache_count_dio_misfit() do {} while(0)
 #endif
 
 #endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
index 8e312c8323a8..58fdb9605425 100644
--- a/include/linux/fscache.h
+++ b/include/linux/fscache.h
@@ -172,9 +172,12 @@ extern void __fscache_invalidate(struct fscache_cookie *, const void *, loff_t,
 extern int __fscache_begin_read_operation(struct netfs_cache_resources *, struct fscache_cookie *);
 extern int __fscache_begin_write_operation(struct netfs_cache_resources *, struct fscache_cookie *);
 
-extern void __fscache_write_to_cache(struct fscache_cookie *, struct address_space *,
-				     loff_t, size_t, loff_t, netfs_io_terminated_t, void *,
-				     bool);
+void __fscache_write_to_cache(struct fscache_cookie *cookie,
+			      struct address_space *mapping,
+			      loff_t start, size_t len, loff_t i_size,
+			      netfs_io_terminated_t term_func,
+			      void *term_func_priv,
+			      bool using_pgpriv2, bool cond);
 extern void __fscache_clear_page_bits(struct address_space *, loff_t, size_t);
 
 /**
@@ -437,9 +440,6 @@ const struct netfs_cache_ops *fscache_operation_valid(const struct netfs_cache_r
  * indicates the cache resources to which the operation state should be
  * attached; @cookie indicates the cache object that will be accessed.
  *
- * This is intended to be called from the ->begin_cache_operation() netfs lib
- * operation as implemented by the network filesystem.
- *
  * @cres->inval_counter is set from @cookie->inval_counter for comparison at
  * the end of the operation.  This allows invalidation during the operation to
  * be detected by the caller.
@@ -498,9 +498,6 @@ static inline void fscache_end_operation(struct netfs_cache_resources *cres)
  *
  *	NETFS_READ_HOLE_IGNORE - Just try to read (may return a short read).
  *
- *	NETFS_READ_HOLE_CLEAR - Seek for data, clearing the part of the buffer
- *				skipped over, then do as for IGNORE.
- *
  *	NETFS_READ_HOLE_FAIL - Give ENODATA if we encounter a hole.
  */
 static inline
@@ -600,7 +597,8 @@ static inline void fscache_clear_page_bits(struct address_space *mapping,
  * @i_size: The new size of the inode
  * @term_func: The function to call upon completion
  * @term_func_priv: The private data for @term_func
- * @caching: If PG_fscache has been set
+ * @using_pgpriv2: If we're using PG_private_2 to mark in-progress write
+ * @caching: If we actually want to do the caching
  *
  * Helper function for a netfs to write dirty data from an inode into the cache
  * object that's backing it.
@@ -611,64 +609,24 @@ static inline void fscache_clear_page_bits(struct address_space *mapping,
  * marked with PG_fscache.
  *
  * If given, @term_func will be called upon completion and supplied with
- * @term_func_priv.  Note that the PG_fscache flags will have been cleared by
- * this point, so the netfs must retain its own pin on the mapping.
+ * @term_func_priv.  Note that if @using_pgpriv2 is set, the PG_private_2 flags
+ * will have been cleared by this point, so the netfs must retain its own pin
+ * on the mapping.
  */
 static inline void fscache_write_to_cache(struct fscache_cookie *cookie,
 					  struct address_space *mapping,
 					  loff_t start, size_t len, loff_t i_size,
 					  netfs_io_terminated_t term_func,
 					  void *term_func_priv,
-					  bool caching)
+					  bool using_pgpriv2, bool caching)
 {
 	if (caching)
 		__fscache_write_to_cache(cookie, mapping, start, len, i_size,
-					 term_func, term_func_priv, caching);
+					 term_func, term_func_priv,
+					 using_pgpriv2, caching);
 	else if (term_func)
-		term_func(term_func_priv, -ENOBUFS, false);
-
-}
-
-#if __fscache_available
-bool fscache_dirty_folio(struct address_space *mapping, struct folio *folio,
-		struct fscache_cookie *cookie);
-#else
-#define fscache_dirty_folio(MAPPING, FOLIO, COOKIE) \
-		filemap_dirty_folio(MAPPING, FOLIO)
-#endif
-
-/**
- * fscache_unpin_writeback - Unpin writeback resources
- * @wbc: The writeback control
- * @cookie: The cookie referring to the cache object
- *
- * Unpin the writeback resources pinned by fscache_dirty_folio().  This is
- * intended to be called by the netfs's ->write_inode() method.
- */
-static inline void fscache_unpin_writeback(struct writeback_control *wbc,
-					   struct fscache_cookie *cookie)
-{
-	if (wbc->unpinned_fscache_wb)
-		fscache_unuse_cookie(cookie, NULL, NULL);
-}
+		term_func(term_func_priv, -ENOBUFS);
 
-/**
- * fscache_clear_inode_writeback - Clear writeback resources pinned by an inode
- * @cookie: The cookie referring to the cache object
- * @inode: The inode to clean up
- * @aux: Auxiliary data to apply to the inode
- *
- * Clear any writeback resources held by an inode when the inode is evicted.
- * This must be called before clear_inode() is called.
- */
-static inline void fscache_clear_inode_writeback(struct fscache_cookie *cookie,
-						 struct inode *inode,
-						 const void *aux)
-{
-	if (inode->i_state & I_PINNING_FSCACHE_WB) {
-		loff_t i_size = i_size_read(inode);
-		fscache_unuse_cookie(cookie, aux, &i_size);
-	}
 }
 
 /**
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index c895b12737a1..516aba5b858b 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -31,7 +31,7 @@
 #define FSCRYPT_CONTENTS_ALIGNMENT 16
 
 union fscrypt_policy;
-struct fscrypt_info;
+struct fscrypt_inode_info;
 struct fs_parameter;
 struct seq_file;
 
@@ -59,26 +59,61 @@ struct fscrypt_name {
 
 #ifdef CONFIG_FS_ENCRYPTION
 
-/*
- * If set, the fscrypt bounce page pool won't be allocated (unless another
- * filesystem needs it).  Set this if the filesystem always uses its own bounce
- * pages for writes and therefore won't need the fscrypt bounce page pool.
- */
-#define FS_CFLG_OWN_PAGES (1U << 1)
-
 /* Crypto operations for filesystems */
 struct fscrypt_operations {
+	/*
+	 * The offset of the pointer to struct fscrypt_inode_info in the
+	 * filesystem-specific part of the inode, relative to the beginning of
+	 * the common part of the inode (the 'struct inode').
+	 */
+	ptrdiff_t inode_info_offs;
+
+	/*
+	 * If set, then fs/crypto/ will allocate a global bounce page pool the
+	 * first time an encryption key is set up for a file.  The bounce page
+	 * pool is required by the following functions:
+	 *
+	 * - fscrypt_encrypt_pagecache_blocks()
+	 * - fscrypt_zeroout_range() for files not using inline crypto
+	 *
+	 * If the filesystem doesn't use those, it doesn't need to set this.
+	 */
+	unsigned int needs_bounce_pages : 1;
+
+	/*
+	 * If set, then fs/crypto/ will allow the use of encryption settings
+	 * that assume inode numbers fit in 32 bits (i.e.
+	 * FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64}), provided that the other
+	 * prerequisites for these settings are also met.  This is only useful
+	 * if the filesystem wants to support inline encryption hardware that is
+	 * limited to 32-bit or 64-bit data unit numbers and where programming
+	 * keyslots is very slow.
+	 */
+	unsigned int has_32bit_inodes : 1;
 
-	/* Set of optional flags; see above for allowed flags */
-	unsigned int flags;
+	/*
+	 * If set, then fs/crypto/ will allow users to select a crypto data unit
+	 * size that is less than the filesystem block size.  This is done via
+	 * the log2_data_unit_size field of the fscrypt policy.  This flag is
+	 * not compatible with filesystems that encrypt variable-length blocks
+	 * (i.e. blocks that aren't all equal to filesystem's block size), for
+	 * example as a result of compression.  It's also not compatible with
+	 * the fscrypt_encrypt_block_inplace() and
+	 * fscrypt_decrypt_block_inplace() functions.
+	 */
+	unsigned int supports_subblock_data_units : 1;
 
 	/*
-	 * If set, this is a filesystem-specific key description prefix that
-	 * will be accepted for "logon" keys for v1 fscrypt policies, in
-	 * addition to the generic prefix "fscrypt:".  This functionality is
-	 * deprecated, so new filesystems shouldn't set this field.
+	 * This field exists only for backwards compatibility reasons and should
+	 * only be set by the filesystems that are setting it already.  It
+	 * contains the filesystem-specific key description prefix that is
+	 * accepted for "logon" keys for v1 fscrypt policies.  This
+	 * functionality is deprecated in favor of the generic prefix
+	 * "fscrypt:", which itself is deprecated in favor of the filesystem
+	 * keyring ioctls such as FS_IOC_ADD_ENCRYPTION_KEY.  Filesystems that
+	 * are newly adding fscrypt support should not set this field.
 	 */
-	const char *key_prefix;
+	const char *legacy_key_prefix;
 
 	/*
 	 * Get the fscrypt context of the given inode.
@@ -146,21 +181,6 @@ struct fscrypt_operations {
 	bool (*has_stable_inodes)(struct super_block *sb);
 
 	/*
-	 * Get the number of bits that the filesystem uses to represent inode
-	 * numbers and file logical block numbers.
-	 *
-	 * By default, both of these are assumed to be 64-bit.  This function
-	 * can be implemented to declare that either or both of these numbers is
-	 * shorter, which may allow the use of the
-	 * FSCRYPT_POLICY_FLAG_IV_INO_LBLK_{32,64} flags and/or the use of
-	 * inline crypto hardware whose maximum DUN length is less than 64 bits
-	 * (e.g., eMMC v5.2 spec compliant hardware).  This function only needs
-	 * to be implemented if support for one of these features is needed.
-	 */
-	void (*get_ino_and_lblk_bits)(struct super_block *sb,
-				      int *ino_bits_ret, int *lblk_bits_ret);
-
-	/*
 	 * Return an array of pointers to the block devices to which the
 	 * filesystem may write encrypted file contents, NULL if the filesystem
 	 * only has a single such block device, or an ERR_PTR() on error.
@@ -178,15 +198,47 @@ struct fscrypt_operations {
 					     unsigned int *num_devs);
 };
 
-static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode)
+int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
+			 struct dentry *dentry, unsigned int flags);
+
+/*
+ * Returns the address of the fscrypt info pointer within the
+ * filesystem-specific part of the inode.  (To save memory on filesystems that
+ * don't support fscrypt, a field in 'struct inode' itself is no longer used.)
+ */
+static inline struct fscrypt_inode_info **
+fscrypt_inode_info_addr(const struct inode *inode)
+{
+	VFS_WARN_ON_ONCE(inode->i_sb->s_cop->inode_info_offs == 0);
+	return (void *)inode + inode->i_sb->s_cop->inode_info_offs;
+}
+
+/*
+ * Load the inode's fscrypt info pointer, using a raw dereference.  Since this
+ * uses a raw dereference with no memory barrier, it is appropriate to use only
+ * when the caller knows the inode's key setup already happened, resulting in
+ * non-NULL fscrypt info.  E.g., the file contents en/decryption functions use
+ * this, since fscrypt_file_open() set up the key.
+ */
+static inline struct fscrypt_inode_info *
+fscrypt_get_inode_info_raw(const struct inode *inode)
+{
+	struct fscrypt_inode_info *ci = *fscrypt_inode_info_addr(inode);
+
+	VFS_WARN_ON_ONCE(ci == NULL);
+	return ci;
+}
+
+static inline struct fscrypt_inode_info *
+fscrypt_get_inode_info(const struct inode *inode)
 {
 	/*
 	 * Pairs with the cmpxchg_release() in fscrypt_setup_encryption_info().
-	 * I.e., another task may publish ->i_crypt_info concurrently, executing
-	 * a RELEASE barrier.  We need to use smp_load_acquire() here to safely
+	 * I.e., another task may publish the fscrypt info concurrently,
+	 * executing a RELEASE barrier.  Use smp_load_acquire() here to safely
 	 * ACQUIRE the memory the other task published.
 	 */
-	return smp_load_acquire(&inode->i_crypt_info);
+	return smp_load_acquire(fscrypt_inode_info_addr(inode));
 }
 
 /**
@@ -206,15 +258,29 @@ static inline bool fscrypt_needs_contents_encryption(const struct inode *inode)
 }
 
 /*
- * When d_splice_alias() moves a directory's no-key alias to its plaintext alias
- * as a result of the encryption key being added, DCACHE_NOKEY_NAME must be
- * cleared.  Note that we don't have to support arbitrary moves of this flag
- * because fscrypt doesn't allow no-key names to be the source or target of a
- * rename().
+ * When d_splice_alias() moves a directory's no-key alias to its
+ * plaintext alias as a result of the encryption key being added,
+ * DCACHE_NOKEY_NAME must be cleared and there might be an opportunity
+ * to disable d_revalidate.  Note that we don't have to support the
+ * inverse operation because fscrypt doesn't allow no-key names to be
+ * the source or target of a rename().
  */
 static inline void fscrypt_handle_d_move(struct dentry *dentry)
 {
-	dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+	/*
+	 * VFS calls fscrypt_handle_d_move even for non-fscrypt
+	 * filesystems.
+	 */
+	if (dentry->d_flags & DCACHE_NOKEY_NAME) {
+		dentry->d_flags &= ~DCACHE_NOKEY_NAME;
+
+		/*
+		 * Other filesystem features might be handling dentry
+		 * revalidation, in which case it cannot be disabled.
+		 */
+		if (dentry->d_op->d_revalidate == fscrypt_d_revalidate)
+			dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+	}
 }
 
 /**
@@ -246,16 +312,43 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
 	return dentry->d_flags & DCACHE_NOKEY_NAME;
 }
 
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+					  bool is_nokey_name)
+{
+	/*
+	 * This code tries to only take ->d_lock when necessary to write
+	 * to ->d_flags.  We shouldn't be peeking on d_flags for
+	 * DCACHE_OP_REVALIDATE unlocked, but in the unlikely case
+	 * there is a race, the worst it can happen is that we fail to
+	 * unset DCACHE_OP_REVALIDATE and pay the cost of an extra
+	 * d_revalidate.
+	 */
+	if (is_nokey_name) {
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags |= DCACHE_NOKEY_NAME;
+		spin_unlock(&dentry->d_lock);
+	} else if (dentry->d_flags & DCACHE_OP_REVALIDATE &&
+		   dentry->d_op->d_revalidate == fscrypt_d_revalidate) {
+		/*
+		 * Unencrypted dentries and encrypted dentries where the
+		 * key is available are always valid from fscrypt
+		 * perspective. Avoid the cost of calling
+		 * fscrypt_d_revalidate unnecessarily.
+		 */
+		spin_lock(&dentry->d_lock);
+		dentry->d_flags &= ~DCACHE_OP_REVALIDATE;
+		spin_unlock(&dentry->d_lock);
+	}
+}
+
 /* crypto.c */
 void fscrypt_enqueue_decrypt_work(struct work_struct *);
 
-struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
-					      unsigned int len,
-					      unsigned int offs,
-					      gfp_t gfp_flags);
+struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio,
+		size_t len, size_t offs, gfp_t gfp_flags);
 int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page,
 				  unsigned int len, unsigned int offs,
-				  u64 lblk_num, gfp_t gfp_flags);
+				  u64 lblk_num);
 
 int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len,
 				     size_t offs);
@@ -273,12 +366,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return (struct page *)page_private(bounce_page);
 }
 
-static inline bool fscrypt_is_bounce_folio(struct folio *folio)
+static inline bool fscrypt_is_bounce_folio(const struct folio *folio)
 {
 	return folio->mapping == NULL;
 }
 
-static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
+static inline
+struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio)
 {
 	return bounce_folio->private;
 }
@@ -353,7 +447,6 @@ int fscrypt_fname_disk_to_usr(const struct inode *inode,
 bool fscrypt_match_name(const struct fscrypt_name *fname,
 			const u8 *de_name, u32 de_name_len);
 u64 fscrypt_fname_siphash(const struct inode *dir, const struct qstr *name);
-int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags);
 
 /* bio.c */
 bool fscrypt_decrypt_bio(struct bio *bio);
@@ -390,7 +483,8 @@ static inline void fscrypt_set_ops(struct super_block *sb,
 }
 #else  /* !CONFIG_FS_ENCRYPTION */
 
-static inline struct fscrypt_info *fscrypt_get_info(const struct inode *inode)
+static inline struct fscrypt_inode_info *
+fscrypt_get_inode_info(const struct inode *inode)
 {
 	return NULL;
 }
@@ -409,15 +503,18 @@ static inline bool fscrypt_is_nokey_name(const struct dentry *dentry)
 	return false;
 }
 
+static inline void fscrypt_prepare_dentry(struct dentry *dentry,
+					  bool is_nokey_name)
+{
+}
+
 /* crypto.c */
 static inline void fscrypt_enqueue_decrypt_work(struct work_struct *work)
 {
 }
 
-static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
-							    unsigned int len,
-							    unsigned int offs,
-							    gfp_t gfp_flags)
+static inline struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio,
+		size_t len, size_t offs, gfp_t gfp_flags)
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
@@ -425,8 +522,7 @@ static inline struct page *fscrypt_encrypt_pagecache_blocks(struct page *page,
 static inline int fscrypt_encrypt_block_inplace(const struct inode *inode,
 						struct page *page,
 						unsigned int len,
-						unsigned int offs, u64 lblk_num,
-						gfp_t gfp_flags)
+						unsigned int offs, u64 lblk_num)
 {
 	return -EOPNOTSUPP;
 }
@@ -456,12 +552,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return ERR_PTR(-EINVAL);
 }
 
-static inline bool fscrypt_is_bounce_folio(struct folio *folio)
+static inline bool fscrypt_is_bounce_folio(const struct folio *folio)
 {
 	return false;
 }
 
-static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
+static inline
+struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio)
 {
 	WARN_ON_ONCE(1);
 	return ERR_PTR(-EINVAL);
@@ -646,8 +743,8 @@ static inline u64 fscrypt_fname_siphash(const struct inode *dir,
 	return 0;
 }
 
-static inline int fscrypt_d_revalidate(struct dentry *dentry,
-				       unsigned int flags)
+static inline int fscrypt_d_revalidate(struct inode *dir, const struct qstr *name,
+				       struct dentry *dentry, unsigned int flags)
 {
 	return 1;
 }
@@ -868,7 +965,7 @@ static inline bool fscrypt_inode_uses_fs_layer_crypto(const struct inode *inode)
  */
 static inline bool fscrypt_has_encryption_key(const struct inode *inode)
 {
-	return fscrypt_get_info(inode) != NULL;
+	return fscrypt_get_inode_info(inode) != NULL;
 }
 
 /**
@@ -966,6 +1063,9 @@ static inline int fscrypt_prepare_lookup(struct inode *dir,
 	fname->usr_fname = &dentry->d_name;
 	fname->disk_name.name = (unsigned char *)dentry->d_name.name;
 	fname->disk_name.len = dentry->d_name.len;
+
+	fscrypt_prepare_dentry(dentry, false);
+
 	return 0;
 }
 
diff --git a/include/linux/fsi.h b/include/linux/fsi.h
index 3df8c54868df..adea1b432f2d 100644
--- a/include/linux/fsi.h
+++ b/include/linux/fsi.h
@@ -44,7 +44,7 @@ struct fsi_driver {
 };
 
 #define to_fsi_dev(devp) container_of(devp, struct fsi_device, dev)
-#define to_fsi_drv(drvp) container_of(drvp, struct fsi_driver, drv)
+#define to_fsi_drv(drvp) container_of_const(drvp, struct fsi_driver, drv)
 
 extern int fsi_driver_register(struct fsi_driver *fsi_drv);
 extern void fsi_driver_unregister(struct fsi_driver *fsi_drv);
@@ -68,7 +68,7 @@ extern int fsi_slave_read(struct fsi_slave *slave, uint32_t addr,
 extern int fsi_slave_write(struct fsi_slave *slave, uint32_t addr,
 		const void *val, size_t size);
 
-extern struct bus_type fsi_bus_type;
+extern const struct bus_type fsi_bus_type;
 extern const struct device_type fsi_cdev_type;
 
 enum fsi_dev_type {
diff --git a/include/linux/fsl/enetc_mdio.h b/include/linux/fsl/enetc_mdio.h
index df25fffdc0ae..623ccfcbf39c 100644
--- a/include/linux/fsl/enetc_mdio.h
+++ b/include/linux/fsl/enetc_mdio.h
@@ -59,7 +59,8 @@ static inline int enetc_mdio_read_c45(struct mii_bus *bus, int phy_id,
 static inline int enetc_mdio_write_c45(struct mii_bus *bus, int phy_id,
 				       int devad, int regnum, u16 value)
 { return -EINVAL; }
-struct enetc_hw *enetc_hw_alloc(struct device *dev, void __iomem *port_regs)
+static inline struct enetc_hw *enetc_hw_alloc(struct device *dev,
+					      void __iomem *port_regs)
 { return ERR_PTR(-EINVAL); }
 
 #endif
diff --git a/include/linux/fsl/mc.h b/include/linux/fsl/mc.h
index a86115bc799c..897d6211c163 100644
--- a/include/linux/fsl/mc.h
+++ b/include/linux/fsl/mc.h
@@ -48,7 +48,7 @@ struct fsl_mc_driver {
 	struct device_driver driver;
 	const struct fsl_mc_device_id *match_id_table;
 	int (*probe)(struct fsl_mc_device *dev);
-	int (*remove)(struct fsl_mc_device *dev);
+	void (*remove)(struct fsl_mc_device *dev);
 	void (*shutdown)(struct fsl_mc_device *dev);
 	int (*suspend)(struct fsl_mc_device *dev, pm_message_t state);
 	int (*resume)(struct fsl_mc_device *dev);
@@ -56,7 +56,7 @@ struct fsl_mc_driver {
 };
 
 #define to_fsl_mc_driver(_drv) \
-	container_of(_drv, struct fsl_mc_driver, driver)
+	container_of_const(_drv, struct fsl_mc_driver, driver)
 
 /**
  * enum fsl_mc_pool_type - Types of allocatable MC bus resources
@@ -417,8 +417,6 @@ int __must_check fsl_mc_portal_allocate(struct fsl_mc_device *mc_dev,
 
 void fsl_mc_portal_free(struct fsl_mc_io *mc_io);
 
-int fsl_mc_portal_reset(struct fsl_mc_io *mc_io);
-
 int __must_check fsl_mc_object_allocate(struct fsl_mc_device *mc_dev,
 					enum fsl_mc_pool_type pool_type,
 					struct fsl_mc_device **new_mc_adev);
@@ -436,23 +434,23 @@ void fsl_mc_free_irqs(struct fsl_mc_device *mc_dev);
 struct fsl_mc_device *fsl_mc_get_endpoint(struct fsl_mc_device *mc_dev,
 					  u16 if_id);
 
-extern struct bus_type fsl_mc_bus_type;
-
-extern struct device_type fsl_mc_bus_dprc_type;
-extern struct device_type fsl_mc_bus_dpni_type;
-extern struct device_type fsl_mc_bus_dpio_type;
-extern struct device_type fsl_mc_bus_dpsw_type;
-extern struct device_type fsl_mc_bus_dpbp_type;
-extern struct device_type fsl_mc_bus_dpcon_type;
-extern struct device_type fsl_mc_bus_dpmcp_type;
-extern struct device_type fsl_mc_bus_dpmac_type;
-extern struct device_type fsl_mc_bus_dprtc_type;
-extern struct device_type fsl_mc_bus_dpseci_type;
-extern struct device_type fsl_mc_bus_dpdmux_type;
-extern struct device_type fsl_mc_bus_dpdcei_type;
-extern struct device_type fsl_mc_bus_dpaiop_type;
-extern struct device_type fsl_mc_bus_dpci_type;
-extern struct device_type fsl_mc_bus_dpdmai_type;
+extern const struct bus_type fsl_mc_bus_type;
+
+extern const struct device_type fsl_mc_bus_dprc_type;
+extern const struct device_type fsl_mc_bus_dpni_type;
+extern const struct device_type fsl_mc_bus_dpio_type;
+extern const struct device_type fsl_mc_bus_dpsw_type;
+extern const struct device_type fsl_mc_bus_dpbp_type;
+extern const struct device_type fsl_mc_bus_dpcon_type;
+extern const struct device_type fsl_mc_bus_dpmcp_type;
+extern const struct device_type fsl_mc_bus_dpmac_type;
+extern const struct device_type fsl_mc_bus_dprtc_type;
+extern const struct device_type fsl_mc_bus_dpseci_type;
+extern const struct device_type fsl_mc_bus_dpdmux_type;
+extern const struct device_type fsl_mc_bus_dpdcei_type;
+extern const struct device_type fsl_mc_bus_dpaiop_type;
+extern const struct device_type fsl_mc_bus_dpci_type;
+extern const struct device_type fsl_mc_bus_dpdmai_type;
 
 static inline bool is_fsl_mc_bus_dprc(const struct fsl_mc_device *mc_dev)
 {
diff --git a/include/linux/fsl/netc_global.h b/include/linux/fsl/netc_global.h
new file mode 100644
index 000000000000..fdecca8c90f0
--- /dev/null
+++ b/include/linux/fsl/netc_global.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2024 NXP
+ */
+#ifndef __NETC_GLOBAL_H
+#define __NETC_GLOBAL_H
+
+#include <linux/io.h>
+
+static inline u32 netc_read(void __iomem *reg)
+{
+	return ioread32(reg);
+}
+
+static inline void netc_write(void __iomem *reg, u32 val)
+{
+	iowrite32(val, reg);
+}
+
+#endif
diff --git a/include/linux/fsl/ntmp.h b/include/linux/fsl/ntmp.h
new file mode 100644
index 000000000000..916dc4fe7de3
--- /dev/null
+++ b/include/linux/fsl/ntmp.h
@@ -0,0 +1,121 @@
+/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */
+/* Copyright 2025 NXP */
+#ifndef __NETC_NTMP_H
+#define __NETC_NTMP_H
+
+#include <linux/bitops.h>
+#include <linux/if_ether.h>
+
+struct maft_keye_data {
+	u8 mac_addr[ETH_ALEN];
+	__le16 resv;
+};
+
+struct maft_cfge_data {
+	__le16 si_bitmap;
+	__le16 resv;
+};
+
+struct netc_cbdr_regs {
+	void __iomem *pir;
+	void __iomem *cir;
+	void __iomem *mr;
+
+	void __iomem *bar0;
+	void __iomem *bar1;
+	void __iomem *lenr;
+};
+
+struct netc_tbl_vers {
+	u8 maft_ver;
+	u8 rsst_ver;
+};
+
+struct netc_cbdr {
+	struct device *dev;
+	struct netc_cbdr_regs regs;
+
+	int bd_num;
+	int next_to_use;
+	int next_to_clean;
+
+	int dma_size;
+	void *addr_base;
+	void *addr_base_align;
+	dma_addr_t dma_base;
+	dma_addr_t dma_base_align;
+
+	/* Serialize the order of command BD ring */
+	spinlock_t ring_lock;
+};
+
+struct ntmp_user {
+	int cbdr_num;	/* number of control BD ring */
+	struct device *dev;
+	struct netc_cbdr *ring;
+	struct netc_tbl_vers tbl;
+};
+
+struct maft_entry_data {
+	struct maft_keye_data keye;
+	struct maft_cfge_data cfge;
+};
+
+#if IS_ENABLED(CONFIG_NXP_NETC_LIB)
+int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+		   const struct netc_cbdr_regs *regs);
+void ntmp_free_cbdr(struct netc_cbdr *cbdr);
+
+/* NTMP APIs */
+int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+			struct maft_entry_data *maft);
+int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+			  struct maft_entry_data *maft);
+int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id);
+int ntmp_rsst_update_entry(struct ntmp_user *user, const u32 *table,
+			   int count);
+int ntmp_rsst_query_entry(struct ntmp_user *user,
+			  u32 *table, int count);
+#else
+static inline int ntmp_init_cbdr(struct netc_cbdr *cbdr, struct device *dev,
+				 const struct netc_cbdr_regs *regs)
+{
+	return 0;
+}
+
+static inline void ntmp_free_cbdr(struct netc_cbdr *cbdr)
+{
+}
+
+static inline int ntmp_maft_add_entry(struct ntmp_user *user, u32 entry_id,
+				      struct maft_entry_data *maft)
+{
+	return 0;
+}
+
+static inline int ntmp_maft_query_entry(struct ntmp_user *user, u32 entry_id,
+					struct maft_entry_data *maft)
+{
+	return 0;
+}
+
+static inline int ntmp_maft_delete_entry(struct ntmp_user *user, u32 entry_id)
+{
+	return 0;
+}
+
+static inline int ntmp_rsst_update_entry(struct ntmp_user *user,
+					 const u32 *table, int count)
+{
+	return 0;
+}
+
+static inline int ntmp_rsst_query_entry(struct ntmp_user *user,
+					u32 *table, int count)
+{
+	return 0;
+}
+
+#endif
+
+#endif
diff --git a/include/linux/fsl/ptp_qoriq.h b/include/linux/fsl/ptp_qoriq.h
index b301bf7199d3..3601e25779ba 100644
--- a/include/linux/fsl/ptp_qoriq.h
+++ b/include/linux/fsl/ptp_qoriq.h
@@ -145,7 +145,6 @@ struct ptp_qoriq {
 	struct ptp_clock *clock;
 	struct ptp_clock_info caps;
 	struct resource *rsrc;
-	struct dentry *debugfs_root;
 	struct device *dev;
 	bool extts_fifo_support;
 	bool fiper3_support;
@@ -195,14 +194,5 @@ int ptp_qoriq_settime(struct ptp_clock_info *ptp,
 int ptp_qoriq_enable(struct ptp_clock_info *ptp,
 		     struct ptp_clock_request *rq, int on);
 int extts_clean_up(struct ptp_qoriq *ptp_qoriq, int index, bool update_event);
-#ifdef CONFIG_DEBUG_FS
-void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq);
-void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq);
-#else
-static inline void ptp_qoriq_create_debugfs(struct ptp_qoriq *ptp_qoriq)
-{ }
-static inline void ptp_qoriq_remove_debugfs(struct ptp_qoriq *ptp_qoriq)
-{ }
-#endif
 
 #endif
diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h
index 5d231ce8709b..49f20c2f99bf 100644
--- a/include/linux/fsl_devices.h
+++ b/include/linux/fsl_devices.h
@@ -118,7 +118,6 @@ struct fsl_usb2_platform_data {
 #define FSL_USB2_PORT0_ENABLED	0x00000001
 #define FSL_USB2_PORT1_ENABLED	0x00000002
 
-#define FLS_USB2_WORKAROUND_ENGCM09152	(1 << 0)
 
 struct spi_device;
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index bb8467cd11ae..28a9cb13fbfa 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -17,6 +17,25 @@
 #include <linux/slab.h>
 #include <linux/bug.h>
 
+/* Are there any inode/mount/sb objects watched with priority prio or above? */
+static inline bool fsnotify_sb_has_priority_watchers(struct super_block *sb,
+						     int prio)
+{
+	struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb);
+
+	/* Were any marks ever added to any object on this sb? */
+	if (!sbinfo)
+		return false;
+
+	return atomic_long_read(&sbinfo->watched_objects[prio]);
+}
+
+/* Are there any inode/mount/sb objects that are being watched at all? */
+static inline bool fsnotify_sb_has_watchers(struct super_block *sb)
+{
+	return fsnotify_sb_has_priority_watchers(sb, 0);
+}
+
 /*
  * Notify this @dir inode about a change in a child directory entry.
  * The directory entry may have turned positive or negative or its inode may
@@ -30,7 +49,7 @@ static inline int fsnotify_name(__u32 mask, const void *data, int data_type,
 				struct inode *dir, const struct qstr *name,
 				u32 cookie)
 {
-	if (atomic_long_read(&dir->i_sb->s_fsnotify_connectors) == 0)
+	if (!fsnotify_sb_has_watchers(dir->i_sb))
 		return 0;
 
 	return fsnotify(mask, data, data_type, dir, name, NULL, cookie);
@@ -44,7 +63,7 @@ static inline void fsnotify_dirent(struct inode *dir, struct dentry *dentry,
 
 static inline void fsnotify_inode(struct inode *inode, __u32 mask)
 {
-	if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0)
+	if (!fsnotify_sb_has_watchers(inode->i_sb))
 		return;
 
 	if (S_ISDIR(inode->i_mode))
@@ -59,7 +78,7 @@ static inline int fsnotify_parent(struct dentry *dentry, __u32 mask,
 {
 	struct inode *inode = d_inode(dentry);
 
-	if (atomic_long_read(&inode->i_sb->s_fsnotify_connectors) == 0)
+	if (!fsnotify_sb_has_watchers(inode->i_sb))
 		return 0;
 
 	if (S_ISDIR(inode->i_mode)) {
@@ -89,40 +108,132 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask)
 	fsnotify_parent(dentry, mask, dentry, FSNOTIFY_EVENT_DENTRY);
 }
 
+static inline int fsnotify_path(const struct path *path, __u32 mask)
+{
+	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
+}
+
 static inline int fsnotify_file(struct file *file, __u32 mask)
 {
-	const struct path *path = &file->f_path;
+	/*
+	 * FMODE_NONOTIFY are fds generated by fanotify itself which should not
+	 * generate new events. We also don't want to generate events for
+	 * FMODE_PATH fds (involves open & close events) as they are just
+	 * handle creation / destruction events and not "real" file events.
+	 */
+	if (FMODE_FSNOTIFY_NONE(file->f_mode))
+		return 0;
+
+	return fsnotify_path(&file->f_path, mask);
+}
+
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+
+int fsnotify_open_perm_and_set_mode(struct file *file);
 
-	if (file->f_mode & FMODE_NONOTIFY)
+/*
+ * fsnotify_file_area_perm - permission hook before access to file range
+ */
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	/*
+	 * filesystem may be modified in the context of permission events
+	 * (e.g. by HSM filling a file on access), so sb freeze protection
+	 * must not be held.
+	 */
+	lockdep_assert_once(file_write_not_started(file));
+
+	if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS)))
 		return 0;
 
-	return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH);
+	/*
+	 * read()/write() and other types of access generate pre-content events.
+	 */
+	if (unlikely(FMODE_FSNOTIFY_HSM(file->f_mode))) {
+		int ret = fsnotify_pre_content(&file->f_path, ppos, count);
+
+		if (ret)
+			return ret;
+	}
+
+	if (!(perm_mask & MAY_READ) ||
+	    likely(!FMODE_FSNOTIFY_ACCESS_PERM(file->f_mode)))
+		return 0;
+
+	/*
+	 * read() also generates the legacy FS_ACCESS_PERM event, so content
+	 * scanners can inspect the content filled by pre-content event.
+	 */
+	return fsnotify_path(&file->f_path, FS_ACCESS_PERM);
 }
 
-/* Simple call site for access decisions */
-static inline int fsnotify_perm(struct file *file, int mask)
+/*
+ * fsnotify_mmap_perm - permission hook before mmap of file range
+ */
+static inline int fsnotify_mmap_perm(struct file *file, int prot,
+				     const loff_t off, size_t len)
 {
-	int ret;
-	__u32 fsnotify_mask = 0;
+	/*
+	 * mmap() generates only pre-content events.
+	 */
+	if (!file || likely(!FMODE_FSNOTIFY_HSM(file->f_mode)))
+		return 0;
 
-	if (!(mask & (MAY_READ | MAY_OPEN)))
+	return fsnotify_pre_content(&file->f_path, &off, len);
+}
+
+/*
+ * fsnotify_truncate_perm - permission hook before file truncate
+ */
+static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
+{
+	struct inode *inode = d_inode(path->dentry);
+
+	if (!(inode->i_sb->s_iflags & SB_I_ALLOW_HSM) ||
+	    !fsnotify_sb_has_priority_watchers(inode->i_sb,
+					       FSNOTIFY_PRIO_PRE_CONTENT))
 		return 0;
 
-	if (mask & MAY_OPEN) {
-		fsnotify_mask = FS_OPEN_PERM;
+	return fsnotify_pre_content(path, &length, 0);
+}
 
-		if (file->f_flags & __FMODE_EXEC) {
-			ret = fsnotify_file(file, FS_OPEN_EXEC_PERM);
+/*
+ * fsnotify_file_perm - permission hook before file access (unknown range)
+ */
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return fsnotify_file_area_perm(file, perm_mask, NULL, 0);
+}
 
-			if (ret)
-				return ret;
-		}
-	} else if (mask & MAY_READ) {
-		fsnotify_mask = FS_ACCESS_PERM;
-	}
+#else
+static inline int fsnotify_open_perm_and_set_mode(struct file *file)
+{
+	return 0;
+}
+
+static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
+					  const loff_t *ppos, size_t count)
+{
+	return 0;
+}
+
+static inline int fsnotify_mmap_perm(struct file *file, int prot,
+				     const loff_t off, size_t len)
+{
+	return 0;
+}
 
-	return fsnotify_file(file, fsnotify_mask);
+static inline int fsnotify_truncate_perm(const struct path *path, loff_t length)
+{
+	return 0;
+}
+
+static inline int fsnotify_file_perm(struct file *file, int perm_mask)
+{
+	return 0;
 }
+#endif
 
 /*
  * fsnotify_link_count - inode's link count changed
@@ -184,6 +295,11 @@ static inline void fsnotify_vfsmount_delete(struct vfsmount *mnt)
 	__fsnotify_vfsmount_delete(mnt);
 }
 
+static inline void fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{
+	__fsnotify_mntns_delete(mntns);
+}
+
 /*
  * fsnotify_inoderemove - an inode is going away
  */
@@ -392,4 +508,19 @@ static inline int fsnotify_sb_error(struct super_block *sb, struct inode *inode,
 			NULL, NULL, NULL, 0);
 }
 
+static inline void fsnotify_mnt_attach(struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	fsnotify_mnt(FS_MNT_ATTACH, ns, mnt);
+}
+
+static inline void fsnotify_mnt_detach(struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	fsnotify_mnt(FS_MNT_DETACH, ns, mnt);
+}
+
+static inline void fsnotify_mnt_move(struct mnt_namespace *ns, struct vfsmount *mnt)
+{
+	fsnotify_mnt(FS_MNT_MOVE, ns, mnt);
+}
+
 #endif	/* _LINUX_FS_NOTIFY_H */
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index d7d96c806bff..0d954ea7b179 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -31,8 +31,8 @@
 #define FS_ACCESS		0x00000001	/* File was accessed */
 #define FS_MODIFY		0x00000002	/* File was modified */
 #define FS_ATTRIB		0x00000004	/* Metadata changed */
-#define FS_CLOSE_WRITE		0x00000008	/* Writtable file was closed */
-#define FS_CLOSE_NOWRITE	0x00000010	/* Unwrittable file closed */
+#define FS_CLOSE_WRITE		0x00000008	/* Writable file was closed */
+#define FS_CLOSE_NOWRITE	0x00000010	/* Unwritable file closed */
 #define FS_OPEN			0x00000020	/* File was opened */
 #define FS_MOVED_FROM		0x00000040	/* File was moved from X */
 #define FS_MOVED_TO		0x00000080	/* File was moved to Y */
@@ -55,6 +55,13 @@
 #define FS_OPEN_PERM		0x00010000	/* open event in an permission hook */
 #define FS_ACCESS_PERM		0x00020000	/* access event in a permissions hook */
 #define FS_OPEN_EXEC_PERM	0x00040000	/* open/exec event in a permission hook */
+/* #define FS_DIR_MODIFY	0x00080000 */	/* Deprecated (reserved) */
+
+#define FS_PRE_ACCESS		0x00100000	/* Pre-content access hook */
+
+#define FS_MNT_ATTACH		0x01000000	/* Mount was attached */
+#define FS_MNT_DETACH		0x02000000	/* Mount was detached */
+#define FS_MNT_MOVE		(FS_MNT_ATTACH | FS_MNT_DETACH)
 
 /*
  * Set on inode mark that cares about things that happen to its children.
@@ -77,8 +84,17 @@
  */
 #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME)
 
-#define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \
-				  FS_OPEN_EXEC_PERM)
+/* Mount namespace events */
+#define FSNOTIFY_MNT_EVENTS (FS_MNT_ATTACH | FS_MNT_DETACH)
+
+/* Content events can be used to inspect file content */
+#define FSNOTIFY_CONTENT_PERM_EVENTS (FS_OPEN_PERM | FS_OPEN_EXEC_PERM | \
+				      FS_ACCESS_PERM)
+/* Pre-content events can be used to fill file content */
+#define FSNOTIFY_PRE_CONTENT_EVENTS  (FS_PRE_ACCESS)
+
+#define ALL_FSNOTIFY_PERM_EVENTS (FSNOTIFY_CONTENT_PERM_EVENTS | \
+				  FSNOTIFY_PRE_CONTENT_EVENTS)
 
 /*
  * This is a list of all events that may get sent to a parent that is watching
@@ -99,6 +115,7 @@
 
 /* Events that can be reported to backends */
 #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \
+			     FSNOTIFY_MNT_EVENTS | \
 			     FS_EVENTS_POSS_ON_CHILD | \
 			     FS_DELETE_SELF | FS_MOVE_SELF | \
 			     FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \
@@ -177,6 +194,17 @@ struct fsnotify_event {
 };
 
 /*
+ * fsnotify group priorities.
+ * Events are sent in order from highest priority to lowest priority.
+ */
+enum fsnotify_group_prio {
+	FSNOTIFY_PRIO_NORMAL = 0,	/* normal notifiers, no permissions */
+	FSNOTIFY_PRIO_CONTENT,		/* fanotify permission events */
+	FSNOTIFY_PRIO_PRE_CONTENT,	/* fanotify pre-content events */
+	__FSNOTIFY_PRIO_NUM
+};
+
+/*
  * A group is a "thing" that wants to receive notification about filesystem
  * events.  The mask holds the subset of event types this group cares about.
  * refcnt on a group is up to the implementor and at any moment if it goes 0
@@ -201,19 +229,11 @@ struct fsnotify_group {
 	wait_queue_head_t notification_waitq;	/* read() on the notification file blocks on this waitq */
 	unsigned int q_len;			/* events on the queue */
 	unsigned int max_events;		/* maximum events allowed on the list */
-	/*
-	 * Valid fsnotify group priorities.  Events are send in order from highest
-	 * priority to lowest priority.  We default to the lowest priority.
-	 */
-	#define FS_PRIO_0	0 /* normal notifiers, no permissions */
-	#define FS_PRIO_1	1 /* fanotify content based access control */
-	#define FS_PRIO_2	2 /* fanotify pre-content access */
-	unsigned int priority;
+	enum fsnotify_group_prio priority;	/* priority for sending events */
 	bool shutdown;		/* group is being shut down, don't queue more events */
 
 #define FSNOTIFY_GROUP_USER	0x01 /* user allocated group */
 #define FSNOTIFY_GROUP_DUPS	0x02 /* allow multiple marks per object */
-#define FSNOTIFY_GROUP_NOFS	0x04 /* group lock is not direct reclaim safe */
 	int flags;
 	unsigned int owner_flags;	/* stored flags of mark_mutex owner */
 
@@ -230,6 +250,7 @@ struct fsnotify_group {
 						 * full */
 
 	struct mem_cgroup *memcg;	/* memcg to charge allocations */
+	struct user_namespace *user_ns;	/* user ns where group was created */
 
 	/* groups can define private fields here or use the void *private */
 	union {
@@ -252,6 +273,8 @@ struct fsnotify_group {
 			int f_flags; /* event_f_flags from fanotify_init() */
 			struct ucounts *ucounts;
 			mempool_t error_events_pool;
+			/* chained on perm_group_list */
+			struct list_head perm_grp_list;
 		} fanotify_data;
 #endif /* CONFIG_FANOTIFY */
 	};
@@ -264,30 +287,29 @@ struct fsnotify_group {
 static inline void fsnotify_group_lock(struct fsnotify_group *group)
 {
 	mutex_lock(&group->mark_mutex);
-	if (group->flags & FSNOTIFY_GROUP_NOFS)
-		group->owner_flags = memalloc_nofs_save();
+	group->owner_flags = memalloc_nofs_save();
 }
 
 static inline void fsnotify_group_unlock(struct fsnotify_group *group)
 {
-	if (group->flags & FSNOTIFY_GROUP_NOFS)
-		memalloc_nofs_restore(group->owner_flags);
+	memalloc_nofs_restore(group->owner_flags);
 	mutex_unlock(&group->mark_mutex);
 }
 
 static inline void fsnotify_group_assert_locked(struct fsnotify_group *group)
 {
 	WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
-	if (group->flags & FSNOTIFY_GROUP_NOFS)
-		WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
+	WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS));
 }
 
 /* When calling fsnotify tell it if the data is a path or inode */
 enum fsnotify_data_type {
 	FSNOTIFY_EVENT_NONE,
+	FSNOTIFY_EVENT_FILE_RANGE,
 	FSNOTIFY_EVENT_PATH,
 	FSNOTIFY_EVENT_INODE,
 	FSNOTIFY_EVENT_DENTRY,
+	FSNOTIFY_EVENT_MNT,
 	FSNOTIFY_EVENT_ERROR,
 };
 
@@ -297,6 +319,22 @@ struct fs_error_report {
 	struct super_block *sb;
 };
 
+struct file_range {
+	const struct path *path;
+	loff_t pos;
+	size_t count;
+};
+
+static inline const struct path *file_range_path(const struct file_range *range)
+{
+	return range->path;
+}
+
+struct fsnotify_mnt {
+	const struct mnt_namespace *ns;
+	u64 mnt_id;
+};
+
 static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 {
 	switch (data_type) {
@@ -306,6 +344,8 @@ static inline struct inode *fsnotify_data_inode(const void *data, int data_type)
 		return d_inode(data);
 	case FSNOTIFY_EVENT_PATH:
 		return d_inode(((const struct path *)data)->dentry);
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return d_inode(file_range_path(data)->dentry);
 	case FSNOTIFY_EVENT_ERROR:
 		return ((struct fs_error_report *)data)->inode;
 	default:
@@ -321,6 +361,8 @@ static inline struct dentry *fsnotify_data_dentry(const void *data, int data_typ
 		return (struct dentry *)data;
 	case FSNOTIFY_EVENT_PATH:
 		return ((const struct path *)data)->dentry;
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return file_range_path(data)->dentry;
 	default:
 		return NULL;
 	}
@@ -332,6 +374,8 @@ static inline const struct path *fsnotify_data_path(const void *data,
 	switch (data_type) {
 	case FSNOTIFY_EVENT_PATH:
 		return data;
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return file_range_path(data);
 	default:
 		return NULL;
 	}
@@ -347,6 +391,8 @@ static inline struct super_block *fsnotify_data_sb(const void *data,
 		return ((struct dentry *)data)->d_sb;
 	case FSNOTIFY_EVENT_PATH:
 		return ((const struct path *)data)->dentry->d_sb;
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return file_range_path(data)->dentry->d_sb;
 	case FSNOTIFY_EVENT_ERROR:
 		return ((struct fs_error_report *) data)->sb;
 	default:
@@ -354,6 +400,24 @@ static inline struct super_block *fsnotify_data_sb(const void *data,
 	}
 }
 
+static inline const struct fsnotify_mnt *fsnotify_data_mnt(const void *data,
+							   int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_MNT:
+		return data;
+	default:
+		return NULL;
+	}
+}
+
+static inline u64 fsnotify_data_mnt_id(const void *data, int data_type)
+{
+	const struct fsnotify_mnt *mnt_data = fsnotify_data_mnt(data, data_type);
+
+	return mnt_data ? mnt_data->mnt_id : 0;
+}
+
 static inline struct fs_error_report *fsnotify_data_error_report(
 							const void *data,
 							int data_type)
@@ -366,6 +430,18 @@ static inline struct fs_error_report *fsnotify_data_error_report(
 	}
 }
 
+static inline const struct file_range *fsnotify_data_file_range(
+							const void *data,
+							int data_type)
+{
+	switch (data_type) {
+	case FSNOTIFY_EVENT_FILE_RANGE:
+		return (struct file_range *)data;
+	default:
+		return NULL;
+	}
+}
+
 /*
  * Index to merged marks iterator array that correlates to a type of watch.
  * The type of watched object can be deduced from the iterator type, but not
@@ -379,6 +455,7 @@ enum fsnotify_iter_type {
 	FSNOTIFY_ITER_TYPE_SB,
 	FSNOTIFY_ITER_TYPE_PARENT,
 	FSNOTIFY_ITER_TYPE_INODE2,
+	FSNOTIFY_ITER_TYPE_MNTNS,
 	FSNOTIFY_ITER_TYPE_COUNT
 };
 
@@ -388,6 +465,7 @@ enum fsnotify_obj_type {
 	FSNOTIFY_OBJ_TYPE_INODE,
 	FSNOTIFY_OBJ_TYPE_VFSMOUNT,
 	FSNOTIFY_OBJ_TYPE_SB,
+	FSNOTIFY_OBJ_TYPE_MNTNS,
 	FSNOTIFY_OBJ_TYPE_COUNT,
 	FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT
 };
@@ -457,13 +535,6 @@ FSNOTIFY_ITER_FUNCS(sb, SB)
 	     type++)
 
 /*
- * fsnotify_connp_t is what we embed in objects which connector can be attached
- * to. fsnotify_connp_t * is how we refer from connector back to object.
- */
-struct fsnotify_mark_connector;
-typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
-
-/*
  * Inode/vfsmount/sb point to this structure which tracks all marks attached to
  * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this
  * structure. We destroy this structure when there are no more marks attached
@@ -471,14 +542,14 @@ typedef struct fsnotify_mark_connector __rcu *fsnotify_connp_t;
  */
 struct fsnotify_mark_connector {
 	spinlock_t lock;
-	unsigned short type;	/* Type of object [lock] */
-#define FSNOTIFY_CONN_FLAG_HAS_FSID	0x01
+	unsigned char type;	/* Type of object [lock] */
+	unsigned char prio;	/* Highest priority group */
+#define FSNOTIFY_CONN_FLAG_IS_WATCHED	0x01
 #define FSNOTIFY_CONN_FLAG_HAS_IREF	0x02
 	unsigned short flags;	/* flags [lock] */
-	__kernel_fsid_t fsid;	/* fsid of filesystem containing object */
 	union {
 		/* Object pointer [lock] */
-		fsnotify_connp_t *obj;
+		void *obj;
 		/* Used listing heads to free after srcu period expires */
 		struct fsnotify_mark_connector *destroy_next;
 	};
@@ -486,6 +557,37 @@ struct fsnotify_mark_connector {
 };
 
 /*
+ * Container for per-sb fsnotify state (sb marks and more).
+ * Attached lazily on first marked object on the sb and freed when killing sb.
+ */
+struct fsnotify_sb_info {
+	struct fsnotify_mark_connector __rcu *sb_marks;
+	/*
+	 * Number of inode/mount/sb objects that are being watched in this sb.
+	 * Note that inodes objects are currently double-accounted.
+	 *
+	 * The value in watched_objects[prio] is the number of objects that are
+	 * watched by groups of priority >= prio, so watched_objects[0] is the
+	 * total number of watched objects in this sb.
+	 */
+	atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM];
+};
+
+static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb)
+{
+#ifdef CONFIG_FSNOTIFY
+	return READ_ONCE(sb->s_fsnotify_info);
+#else
+	return NULL;
+#endif
+}
+
+static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb)
+{
+	return &fsnotify_sb_info(sb)->watched_objects[0];
+}
+
+/*
  * A mark is simply an object attached to an in core inode which allows an
  * fsnotify listener to indicate they are either no longer interested in events
  * of a type matching mask or only interested in those events.
@@ -530,6 +632,8 @@ struct fsnotify_mark {
 #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY	0x0100
 #define FSNOTIFY_MARK_FLAG_NO_IREF		0x0200
 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS	0x0400
+#define FSNOTIFY_MARK_FLAG_HAS_FSID		0x0800
+#define FSNOTIFY_MARK_FLAG_WEAK_FSID		0x1000
 	unsigned int flags;		/* flags [mark->lock] */
 };
 
@@ -546,7 +650,10 @@ extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data
 extern void __fsnotify_inode_delete(struct inode *inode);
 extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt);
 extern void fsnotify_sb_delete(struct super_block *sb);
+extern void __fsnotify_mntns_delete(struct mnt_namespace *mntns);
+extern void fsnotify_sb_free(struct super_block *sb);
 extern u32 fsnotify_get_cookie(void);
+extern void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt);
 
 static inline __u32 fsnotify_parent_needed_mask(__u32 mask)
 {
@@ -563,12 +670,14 @@ static inline __u32 fsnotify_parent_needed_mask(__u32 mask)
 
 static inline int fsnotify_inode_watches_children(struct inode *inode)
 {
+	__u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask);
+
 	/* FS_EVENT_ON_CHILD is set if the inode may care */
-	if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD))
+	if (!(parent_mask & FS_EVENT_ON_CHILD))
 		return 0;
 	/* this inode might care about child events, does it care about the
 	 * specific set of events that can happen on a child? */
-	return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD;
+	return parent_mask & FS_EVENTS_POSS_ON_CHILD;
 }
 
 /*
@@ -582,7 +691,7 @@ static inline void fsnotify_update_flags(struct dentry *dentry)
 	/*
 	 * Serialisation of setting PARENT_WATCHED on the dentries is provided
 	 * by d_lock. If inotify_inode_watched changes after we have taken
-	 * d_lock, the following __fsnotify_update_child_dentry_flags call will
+	 * d_lock, the following fsnotify_set_children_dentry_flags call will
 	 * find our entry, so it will spin until we complete here, and update
 	 * us with the new state.
 	 */
@@ -758,35 +867,35 @@ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn);
 extern void fsnotify_init_mark(struct fsnotify_mark *mark,
 			       struct fsnotify_group *group);
 /* Find mark belonging to given group in the list of marks */
-extern struct fsnotify_mark *fsnotify_find_mark(fsnotify_connp_t *connp,
-						struct fsnotify_group *group);
-/* Get cached fsid of filesystem containing object */
-extern int fsnotify_get_conn_fsid(const struct fsnotify_mark_connector *conn,
-				  __kernel_fsid_t *fsid);
+struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type,
+					 struct fsnotify_group *group);
 /* attach the mark to the object */
-extern int fsnotify_add_mark(struct fsnotify_mark *mark,
-			     fsnotify_connp_t *connp, unsigned int obj_type,
-			     int add_flags, __kernel_fsid_t *fsid);
-extern int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
-				    fsnotify_connp_t *connp,
-				    unsigned int obj_type, int add_flags,
-				    __kernel_fsid_t *fsid);
+int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj,
+		      unsigned int obj_type, int add_flags);
+int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj,
+			     unsigned int obj_type, int add_flags);
 
 /* attach the mark to the inode */
 static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
 					  struct inode *inode,
 					  int add_flags)
 {
-	return fsnotify_add_mark(mark, &inode->i_fsnotify_marks,
-				 FSNOTIFY_OBJ_TYPE_INODE, add_flags, NULL);
+	return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE,
+				 add_flags);
 }
 static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark,
 						 struct inode *inode,
 						 int add_flags)
 {
-	return fsnotify_add_mark_locked(mark, &inode->i_fsnotify_marks,
-					FSNOTIFY_OBJ_TYPE_INODE, add_flags,
-					NULL);
+	return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE,
+					add_flags);
+}
+
+static inline struct fsnotify_mark *fsnotify_find_inode_mark(
+						struct inode *inode,
+						struct fsnotify_group *group)
+{
+	return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group);
 }
 
 /* given a group and a mark, flag mark to be freed when all references are dropped */
@@ -801,21 +910,6 @@ extern void fsnotify_wait_marks_destroyed(void);
 /* Clear all of the marks of a group attached to a given object type */
 extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
 					  unsigned int obj_type);
-/* run all the marks in a group, and clear all of the vfsmount marks */
-static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT);
-}
-/* run all the marks in a group, and clear all of the inode marks */
-static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE);
-}
-/* run all the marks in a group, and clear all of the sn marks */
-static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB);
-}
 extern void fsnotify_get_mark(struct fsnotify_mark *mark);
 extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
@@ -825,9 +919,17 @@ static inline void fsnotify_init_event(struct fsnotify_event *event)
 {
 	INIT_LIST_HEAD(&event->list);
 }
+int fsnotify_pre_content(const struct path *path, const loff_t *ppos,
+			 size_t count);
 
 #else
 
+static inline int fsnotify_pre_content(const struct path *path,
+				       const loff_t *ppos, size_t count)
+{
+	return 0;
+}
+
 static inline int fsnotify(__u32 mask, const void *data, int data_type,
 			   struct inode *dir, const struct qstr *name,
 			   struct inode *inode, u32 cookie)
@@ -850,6 +952,12 @@ static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
 static inline void fsnotify_sb_delete(struct super_block *sb)
 {}
 
+static inline void __fsnotify_mntns_delete(struct mnt_namespace *mntns)
+{}
+
+static inline void fsnotify_sb_free(struct super_block *sb)
+{}
+
 static inline void fsnotify_update_flags(struct dentry *dentry)
 {}
 
@@ -861,6 +969,9 @@ static inline u32 fsnotify_get_cookie(void)
 static inline void fsnotify_unmount_inodes(struct super_block *sb)
 {}
 
+static inline void fsnotify_mnt(__u32 mask, struct mnt_namespace *ns, struct vfsmount *mnt)
+{}
+
 #endif	/* CONFIG_FSNOTIFY */
 
 #endif	/* __KERNEL __ */
diff --git a/include/linux/fsverity.h b/include/linux/fsverity.h
index e76605d5b36e..5bc7280425a7 100644
--- a/include/linux/fsverity.h
+++ b/include/linux/fsverity.h
@@ -26,8 +26,16 @@
 /* Arbitrary limit to bound the kmalloc() size.  Can be changed. */
 #define FS_VERITY_MAX_DESCRIPTOR_SIZE	16384
 
+struct fsverity_info;
+
 /* Verity operations for filesystems */
 struct fsverity_operations {
+	/**
+	 * The offset of the pointer to struct fsverity_info in the
+	 * filesystem-specific part of the inode, relative to the beginning of
+	 * the common part of the inode (the 'struct inode').
+	 */
+	ptrdiff_t inode_info_offs;
 
 	/**
 	 * Begin enabling verity on the given file.
@@ -124,15 +132,37 @@ struct fsverity_operations {
 
 #ifdef CONFIG_FS_VERITY
 
+/*
+ * Returns the address of the verity info pointer within the filesystem-specific
+ * part of the inode.  (To save memory on filesystems that don't support
+ * fsverity, a field in 'struct inode' itself is no longer used.)
+ */
+static inline struct fsverity_info **
+fsverity_info_addr(const struct inode *inode)
+{
+	VFS_WARN_ON_ONCE(inode->i_sb->s_vop->inode_info_offs == 0);
+	return (void *)inode + inode->i_sb->s_vop->inode_info_offs;
+}
+
 static inline struct fsverity_info *fsverity_get_info(const struct inode *inode)
 {
 	/*
-	 * Pairs with the cmpxchg_release() in fsverity_set_info().
-	 * I.e., another task may publish ->i_verity_info concurrently,
-	 * executing a RELEASE barrier.  We need to use smp_load_acquire() here
-	 * to safely ACQUIRE the memory the other task published.
+	 * Since this function can be called on inodes belonging to filesystems
+	 * that don't support fsverity at all, and fsverity_info_addr() doesn't
+	 * work on such filesystems, we have to start with an IS_VERITY() check.
+	 * Checking IS_VERITY() here is also useful to minimize the overhead of
+	 * fsverity_active() on non-verity files.
+	 */
+	if (!IS_VERITY(inode))
+		return NULL;
+
+	/*
+	 * Pairs with the cmpxchg_release() in fsverity_set_info().  I.e.,
+	 * another task may publish the inode's verity info concurrently,
+	 * executing a RELEASE barrier.  Use smp_load_acquire() here to safely
+	 * ACQUIRE the memory the other task published.
 	 */
-	return smp_load_acquire(&inode->i_verity_info);
+	return smp_load_acquire(fsverity_info_addr(inode));
 }
 
 /* enable.c */
@@ -143,8 +173,8 @@ int fsverity_ioctl_enable(struct file *filp, const void __user *arg);
 
 int fsverity_ioctl_measure(struct file *filp, void __user *arg);
 int fsverity_get_digest(struct inode *inode,
-			u8 digest[FS_VERITY_MAX_DIGEST_SIZE],
-			enum hash_algo *alg);
+			u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE],
+			u8 *alg, enum hash_algo *halg);
 
 /* open.c */
 
@@ -156,12 +186,19 @@ void __fsverity_cleanup_inode(struct inode *inode);
  * fsverity_cleanup_inode() - free the inode's verity info, if present
  * @inode: an inode being evicted
  *
- * Filesystems must call this on inode eviction to free ->i_verity_info.
+ * Filesystems must call this on inode eviction to free the inode's verity info.
  */
 static inline void fsverity_cleanup_inode(struct inode *inode)
 {
-	if (inode->i_verity_info)
+	/*
+	 * Only IS_VERITY() inodes can have verity info, so start by checking
+	 * for IS_VERITY() (which is faster than retrieving the pointer to the
+	 * verity info).  This minimizes overhead for non-verity inodes.
+	 */
+	if (IS_VERITY(inode))
 		__fsverity_cleanup_inode(inode);
+	else
+		VFS_WARN_ON_ONCE(*fsverity_info_addr(inode) != NULL);
 }
 
 /* read_metadata.c */
@@ -197,10 +234,14 @@ static inline int fsverity_ioctl_measure(struct file *filp, void __user *arg)
 }
 
 static inline int fsverity_get_digest(struct inode *inode,
-				      u8 digest[FS_VERITY_MAX_DIGEST_SIZE],
-				      enum hash_algo *alg)
+				      u8 raw_digest[FS_VERITY_MAX_DIGEST_SIZE],
+				      u8 *alg, enum hash_algo *halg)
 {
-	return -EOPNOTSUPP;
+	/*
+	 * fsverity is not enabled in the kernel configuration, so always report
+	 * that the file doesn't have fsverity enabled (digest size 0).
+	 */
+	return 0;
 }
 
 /* open.c */
@@ -263,12 +304,12 @@ static inline bool fsverity_verify_page(struct page *page)
  * fsverity_active() - do reads from the inode need to go through fs-verity?
  * @inode: inode to check
  *
- * This checks whether ->i_verity_info has been set.
+ * This checks whether the inode's verity info has been set.
  *
  * Filesystems call this from ->readahead() to check whether the pages need to
  * be verified or not.  Don't use IS_VERITY() for this purpose; it's subject to
  * a race condition where the file is being read concurrently with
- * FS_IOC_ENABLE_VERITY completing.  (S_VERITY is set before ->i_verity_info.)
+ * FS_IOC_ENABLE_VERITY completing.  (S_VERITY is set before the verity info.)
  *
  * Return: true if reads need to go through fs-verity, otherwise false
  */
@@ -283,7 +324,7 @@ static inline bool fsverity_active(const struct inode *inode)
  * @filp: the struct file being set up
  *
  * When opening a verity file, deny the open if it is for writing.  Otherwise,
- * set up the inode's ->i_verity_info if not already done.
+ * set up the inode's verity info if not already done.
  *
  * When combined with fscrypt, this must be called after fscrypt_file_open().
  * Otherwise, we won't have the key set up to decrypt the verity metadata.
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b23bdd414394..770f0dc993cc 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -41,6 +41,14 @@ struct ftrace_ops;
 struct ftrace_regs;
 struct dyn_ftrace;
 
+char *arch_ftrace_match_adjust(char *str, const char *search);
+
+#ifdef CONFIG_HAVE_FUNCTION_GRAPH_FREGS
+unsigned long ftrace_return_to_handler(struct ftrace_regs *fregs);
+#else
+unsigned long ftrace_return_to_handler(unsigned long frame_pointer);
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 /*
  * If the arch's mcount caller does not support all of ftrace's
@@ -74,19 +82,18 @@ static inline void early_trace_init(void) { }
 
 struct module;
 struct ftrace_hash;
-struct ftrace_direct_func;
 
 #if defined(CONFIG_FUNCTION_TRACER) && defined(CONFIG_MODULES) && \
 	defined(CONFIG_DYNAMIC_FTRACE)
-const char *
+int
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym);
 #else
-static inline const char *
+static inline int
 ftrace_mod_address_lookup(unsigned long addr, unsigned long *size,
 		   unsigned long *off, char **modname, char *sym)
 {
-	return NULL;
+	return 0;
 }
 #endif
 
@@ -105,14 +112,61 @@ static inline int ftrace_mod_get_kallsym(unsigned int symnum, unsigned long *val
 
 #ifdef CONFIG_FUNCTION_TRACER
 
-extern int ftrace_enabled;
+#include <linux/ftrace_regs.h>
 
-#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+extern int ftrace_enabled;
 
+/**
+ * ftrace_regs - ftrace partial/optimal register set
+ *
+ * ftrace_regs represents a group of registers which is used at the
+ * function entry and exit. There are three types of registers.
+ *
+ * - Registers for passing the parameters to callee, including the stack
+ *   pointer. (e.g. rcx, rdx, rdi, rsi, r8, r9 and rsp on x86_64)
+ * - Registers for passing the return values to caller.
+ *   (e.g. rax and rdx on x86_64)
+ * - Registers for hooking the function call and return including the
+ *   frame pointer (the frame pointer is architecture/config dependent)
+ *   (e.g. rip, rbp and rsp for x86_64)
+ *
+ * Also, architecture dependent fields can be used for internal process.
+ * (e.g. orig_ax on x86_64)
+ *
+ * Basically, ftrace_regs stores the registers related to the context.
+ * On function entry, registers for function parameters and hooking the
+ * function call are stored, and on function exit, registers for function
+ * return value and frame pointers are stored.
+ *
+ * And also, it dpends on the context that which registers are restored
+ * from the ftrace_regs.
+ * On the function entry, those registers will be restored except for
+ * the stack pointer, so that user can change the function parameters
+ * and instruction pointer (e.g. live patching.)
+ * On the function exit, only registers which is used for return values
+ * are restored.
+ *
+ * NOTE: user *must not* access regs directly, only do it via APIs, because
+ * the member can be changed according to the architecture.
+ * This is why the structure is empty here, so that nothing accesses
+ * the ftrace_regs directly.
+ */
 struct ftrace_regs {
-	struct pt_regs		regs;
+	/* Nothing to see here, use the accessor functions! */
 };
-#define arch_ftrace_get_regs(fregs) (&(fregs)->regs)
+
+#define ftrace_regs_size()	sizeof(struct __arch_ftrace_regs)
+
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+/*
+ * Architectures that define HAVE_DYNAMIC_FTRACE_WITH_ARGS must define their own
+ * arch_ftrace_get_regs() where it only returns pt_regs *if* it is fully
+ * populated. It should return NULL otherwise.
+ */
+static inline struct pt_regs *arch_ftrace_get_regs(struct ftrace_regs *fregs)
+{
+	return &arch_ftrace_regs(fregs)->regs;
+}
 
 /*
  * ftrace_regs_set_instruction_pointer() is to be defined by the architecture
@@ -122,6 +176,12 @@ struct ftrace_regs {
 #define ftrace_regs_set_instruction_pointer(fregs, ip) do { } while (0)
 #endif /* CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
 
+#ifdef CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS
+
+static_assert(sizeof(struct pt_regs) == ftrace_regs_size());
+
+#endif /* CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */
+
 static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs)
 {
 	if (!fregs)
@@ -130,6 +190,62 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs
 	return arch_ftrace_get_regs(fregs);
 }
 
+#if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \
+	defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS)
+
+#ifndef arch_ftrace_partial_regs
+#define arch_ftrace_partial_regs(regs) do {} while (0)
+#endif
+
+static __always_inline struct pt_regs *
+ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	/*
+	 * If CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS=y, ftrace_regs memory
+	 * layout is including pt_regs. So always returns that address.
+	 * Since arch_ftrace_get_regs() will check some members and may return
+	 * NULL, we can not use it.
+	 */
+	regs = &arch_ftrace_regs(fregs)->regs;
+
+	/* Allow arch specific updates to regs. */
+	arch_ftrace_partial_regs(regs);
+	return regs;
+}
+
+#endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */
+
+#ifdef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+
+/*
+ * Please define arch dependent pt_regs which compatible to the
+ * perf_arch_fetch_caller_regs() but based on ftrace_regs.
+ * This requires
+ *   - user_mode(_regs) returns false (always kernel mode).
+ *   - able to use the _regs for stack trace.
+ */
+#ifndef arch_ftrace_fill_perf_regs
+/* As same as perf_arch_fetch_caller_regs(), do nothing by default */
+#define arch_ftrace_fill_perf_regs(fregs, _regs) do {} while (0)
+#endif
+
+static __always_inline struct pt_regs *
+ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	arch_ftrace_fill_perf_regs(fregs, regs);
+	return regs;
+}
+
+#else /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS */
+
+static __always_inline struct pt_regs *
+ftrace_fill_perf_regs(struct ftrace_regs *fregs, struct pt_regs *regs)
+{
+	return &arch_ftrace_regs(fregs)->regs;
+}
+
+#endif
+
 /*
  * When true, the ftrace_regs_{get,set}_*() functions may be used on fregs.
  * Note: this can be true even when ftrace_get_regs() cannot provide a pt_regs.
@@ -142,22 +258,22 @@ static __always_inline bool ftrace_regs_has_args(struct ftrace_regs *fregs)
 	return ftrace_get_regs(fregs) != NULL;
 }
 
-#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
-#define ftrace_regs_get_instruction_pointer(fregs) \
-	instruction_pointer(ftrace_get_regs(fregs))
-#define ftrace_regs_get_argument(fregs, n) \
-	regs_get_kernel_argument(ftrace_get_regs(fregs), n)
-#define ftrace_regs_get_stack_pointer(fregs) \
-	kernel_stack_pointer(ftrace_get_regs(fregs))
-#define ftrace_regs_return_value(fregs) \
-	regs_return_value(ftrace_get_regs(fregs))
-#define ftrace_regs_set_return_value(fregs, ret) \
-	regs_set_return_value(ftrace_get_regs(fregs), ret)
-#define ftrace_override_function_with_return(fregs) \
-	override_function_with_return(ftrace_get_regs(fregs))
-#define ftrace_regs_query_register_offset(name) \
-	regs_query_register_offset(name)
-#endif
+#ifdef CONFIG_HAVE_REGS_AND_STACK_ACCESS_API
+static __always_inline unsigned long
+ftrace_regs_get_kernel_stack_nth(struct ftrace_regs *fregs, unsigned int nth)
+{
+	unsigned long *stackp;
+
+	stackp = (unsigned long *)ftrace_regs_get_stack_pointer(fregs);
+	if (((unsigned long)(stackp + nth) & ~(THREAD_SIZE - 1)) ==
+	    ((unsigned long)stackp & ~(THREAD_SIZE - 1)))
+		return *(stackp + nth);
+
+	return 0;
+}
+#else /* !CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */
+#define ftrace_regs_get_kernel_stack_nth(fregs, nth)	(0L)
+#endif /* CONFIG_HAVE_REGS_AND_STACK_ACCESS_API */
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip,
 			      struct ftrace_ops *op, struct ftrace_regs *fregs);
@@ -219,6 +335,8 @@ ftrace_func_t ftrace_ops_get_func(struct ftrace_ops *ops);
  *             ftrace_enabled.
  * DIRECT - Used by the direct ftrace_ops helper for direct functions
  *            (internal ftrace only, should not be used by others)
+ * SUBOP  - Is controlled by another op in field managed.
+ * GRAPH  - Is a component of the fgraph_ops structure
  */
 enum {
 	FTRACE_OPS_FL_ENABLED			= BIT(0),
@@ -239,6 +357,9 @@ enum {
 	FTRACE_OPS_FL_TRACE_ARRAY		= BIT(15),
 	FTRACE_OPS_FL_PERMANENT                 = BIT(16),
 	FTRACE_OPS_FL_DIRECT			= BIT(17),
+	FTRACE_OPS_FL_SUBOP			= BIT(18),
+	FTRACE_OPS_FL_GRAPH			= BIT(19),
+	FTRACE_OPS_FL_JMP			= BIT(20),
 };
 
 #ifndef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
@@ -326,7 +447,9 @@ struct ftrace_ops {
 	unsigned long			trampoline;
 	unsigned long			trampoline_size;
 	struct list_head		list;
+	struct list_head		subop_list;
 	ftrace_ops_func_t		ops_func;
+	struct ftrace_ops		*managed;
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	unsigned long			direct_call;
 #endif
@@ -405,7 +528,6 @@ struct ftrace_func_entry {
 };
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
-extern int ftrace_direct_func_count;
 unsigned long ftrace_find_rec_direct(unsigned long ip);
 int register_ftrace_direct(struct ftrace_ops *ops, unsigned long addr);
 int unregister_ftrace_direct(struct ftrace_ops *ops, unsigned long addr,
@@ -417,7 +539,6 @@ void ftrace_stub_direct_tramp(void);
 
 #else
 struct ftrace_ops;
-# define ftrace_direct_func_count 0
 static inline unsigned long ftrace_find_rec_direct(unsigned long ip)
 {
 	return 0;
@@ -457,11 +578,41 @@ static inline void arch_ftrace_set_direct_caller(struct ftrace_regs *fregs,
 						 unsigned long addr) { }
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS */
 
-#ifdef CONFIG_STACK_TRACER
+#ifdef CONFIG_DYNAMIC_FTRACE_WITH_JMP
+static inline bool ftrace_is_jmp(unsigned long addr)
+{
+	return addr & 1;
+}
 
-extern int stack_tracer_enabled;
+static inline unsigned long ftrace_jmp_set(unsigned long addr)
+{
+	return addr | 1UL;
+}
 
-int stack_trace_sysctl(struct ctl_table *table, int write, void *buffer,
+static inline unsigned long ftrace_jmp_get(unsigned long addr)
+{
+	return addr & ~1UL;
+}
+#else
+static inline bool ftrace_is_jmp(unsigned long addr)
+{
+	return false;
+}
+
+static inline unsigned long ftrace_jmp_set(unsigned long addr)
+{
+	return addr;
+}
+
+static inline unsigned long ftrace_jmp_get(unsigned long addr)
+{
+	return addr;
+}
+#endif /* CONFIG_DYNAMIC_FTRACE_WITH_JMP */
+
+#ifdef CONFIG_STACK_TRACER
+
+int stack_trace_sysctl(const struct ctl_table *table, int write, void *buffer,
 		       size_t *lenp, loff_t *ppos);
 
 /* DO NOT MODIFY THIS VARIABLE DIRECTLY! */
@@ -503,6 +654,30 @@ static inline void stack_tracer_disable(void) { }
 static inline void stack_tracer_enable(void) { }
 #endif
 
+enum {
+	FTRACE_UPDATE_CALLS		= (1 << 0),
+	FTRACE_DISABLE_CALLS		= (1 << 1),
+	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
+	FTRACE_START_FUNC_RET		= (1 << 3),
+	FTRACE_STOP_FUNC_RET		= (1 << 4),
+	FTRACE_MAY_SLEEP		= (1 << 5),
+};
+
+/* Arches can override ftrace_get_symaddr() to convert fentry_ip to symaddr. */
+#ifndef ftrace_get_symaddr
+/**
+ * ftrace_get_symaddr - return the symbol address from fentry_ip
+ * @fentry_ip: the address of ftrace location
+ *
+ * Get the symbol address from @fentry_ip (fast path). If there is no fast
+ * search path, this returns 0.
+ * User may need to use kallsyms API to find the symbol address.
+ */
+#define ftrace_get_symaddr(fentry_ip) (0)
+#endif
+
+void ftrace_sync_ipi(void *data);
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 void ftrace_arch_code_modify_prepare(void);
@@ -597,15 +772,6 @@ void ftrace_set_global_notrace(unsigned char *buf, int len, int reset);
 void ftrace_free_filter(struct ftrace_ops *ops);
 void ftrace_ops_set_global_filter(struct ftrace_ops *ops);
 
-enum {
-	FTRACE_UPDATE_CALLS		= (1 << 0),
-	FTRACE_DISABLE_CALLS		= (1 << 1),
-	FTRACE_UPDATE_TRACE_FUNC	= (1 << 2),
-	FTRACE_START_FUNC_RET		= (1 << 3),
-	FTRACE_STOP_FUNC_RET		= (1 << 4),
-	FTRACE_MAY_SLEEP		= (1 << 5),
-};
-
 /*
  * The FTRACE_UPDATE_* enum is used to pass information back
  * from the ftrace_update_record() and ftrace_test_record()
@@ -633,6 +799,7 @@ enum {
 	FTRACE_ITER_MOD		= (1 << 5),
 	FTRACE_ITER_ENABLED	= (1 << 6),
 	FTRACE_ITER_TOUCHED	= (1 << 7),
+	FTRACE_ITER_ADDRS	= (1 << 8),
 };
 
 void arch_ftrace_update_code(int command);
@@ -674,7 +841,6 @@ void __init
 ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable);
 
 /* defined in arch */
-extern int ftrace_ip_converted(unsigned long ip);
 extern int ftrace_dyn_arch_init(void);
 extern void ftrace_replace_code(int enable);
 extern int ftrace_update_ftrace_func(ftrace_func_t func);
@@ -813,7 +979,8 @@ static inline int ftrace_init_nop(struct module *mod, struct dyn_ftrace *rec)
 extern int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr);
 
 #if defined(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || \
-	defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS)
+	defined(CONFIG_DYNAMIC_FTRACE_WITH_CALL_OPS) || \
+	defined(CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS)
 /**
  * ftrace_modify_call - convert from one addr to another (no nop)
  * @rec: the call site record (e.g. mcount/fentry)
@@ -849,20 +1016,12 @@ static inline int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_a
 }
 #endif
 
-/* May be defined in arch */
-extern int ftrace_arch_read_dyn_info(char *buf, int size);
-
 extern int skip_trace(unsigned long ip);
 extern void ftrace_module_init(struct module *mod);
 extern void ftrace_module_enable(struct module *mod);
 extern void ftrace_release_mod(struct module *mod);
-
-extern void ftrace_disable_daemon(void);
-extern void ftrace_enable_daemon(void);
 #else /* CONFIG_DYNAMIC_FTRACE */
 static inline int skip_trace(unsigned long ip) { return 0; }
-static inline void ftrace_disable_daemon(void) { }
-static inline void ftrace_enable_daemon(void) { }
 static inline void ftrace_module_init(struct module *mod) { }
 static inline void ftrace_module_enable(struct module *mod) { }
 static inline void ftrace_release_mod(struct module *mod) { }
@@ -990,7 +1149,7 @@ static __always_inline unsigned long get_lock_parent_ip(void)
 # define trace_preempt_off(a0, a1) do { } while (0)
 #endif
 
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_init(void);
 #ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
 #define FTRACE_CALLSITE_SECTION	"__patchable_function_entries"
@@ -1008,7 +1167,15 @@ static inline void ftrace_init(void) { }
  */
 struct ftrace_graph_ent {
 	unsigned long func; /* Current function */
-	int depth;
+	unsigned long depth;
+} __packed;
+
+/*
+ * Structure that defines an entry function trace with retaddr.
+ */
+struct fgraph_retaddr_ent {
+	struct ftrace_graph_ent ent;
+	unsigned long retaddr;  /* Return address */
 } __packed;
 
 /*
@@ -1018,26 +1185,44 @@ struct ftrace_graph_ent {
  */
 struct ftrace_graph_ret {
 	unsigned long func; /* Current function */
+#ifdef CONFIG_FUNCTION_GRAPH_RETVAL
+	unsigned long retval;
+#endif
 	int depth;
 	/* Number of functions that overran the depth limit for current task */
 	unsigned int overrun;
-	unsigned long long calltime;
-	unsigned long long rettime;
 } __packed;
 
-/* Type of the callback handlers for tracing function graph*/
-typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *); /* return */
-typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *); /* entry */
+struct fgraph_ops;
 
-extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace);
+/* Type of the callback handlers for tracing function graph*/
+typedef void (*trace_func_graph_ret_t)(struct ftrace_graph_ret *,
+				       struct fgraph_ops *,
+				       struct ftrace_regs *); /* return */
+typedef int (*trace_func_graph_ent_t)(struct ftrace_graph_ent *,
+				      struct fgraph_ops *,
+				      struct ftrace_regs *); /* entry */
+
+extern int ftrace_graph_entry_stub(struct ftrace_graph_ent *trace,
+				   struct fgraph_ops *gops,
+				   struct ftrace_regs *fregs);
+bool ftrace_pids_enabled(struct ftrace_ops *ops);
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 
 struct fgraph_ops {
 	trace_func_graph_ent_t		entryfunc;
 	trace_func_graph_ret_t		retfunc;
+	struct ftrace_ops		ops; /* for the hash lists */
+	void				*private;
+	trace_func_graph_ent_t		saved_func;
+	int				idx;
 };
 
+void *fgraph_reserve_data(int idx, int size_bytes);
+void *fgraph_retrieve_data(int idx, int *size_bytes);
+void *fgraph_retrieve_parent_data(int idx, int *size_bytes, int depth);
+
 /*
  * Stack of return addresses for functions
  * of a thread.
@@ -1046,16 +1231,10 @@ struct fgraph_ops {
 struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
-	unsigned long long calltime;
-#ifdef CONFIG_FUNCTION_PROFILER
-	unsigned long long subtime;
-#endif
 #ifdef HAVE_FUNCTION_GRAPH_FP_TEST
 	unsigned long fp;
 #endif
-#ifdef HAVE_FUNCTION_GRAPH_RET_ADDR_PTR
 	unsigned long *retp;
-#endif
 };
 
 /*
@@ -1066,14 +1245,23 @@ struct ftrace_ret_stack {
 extern void return_to_handler(void);
 
 extern int
-function_graph_enter(unsigned long ret, unsigned long func,
-		     unsigned long frame_pointer, unsigned long *retp);
+function_graph_enter_regs(unsigned long ret, unsigned long func,
+			  unsigned long frame_pointer, unsigned long *retp,
+			  struct ftrace_regs *fregs);
+
+static inline int function_graph_enter(unsigned long ret, unsigned long func,
+				       unsigned long fp, unsigned long *retp)
+{
+	return function_graph_enter_regs(ret, func, fp, retp, NULL);
+}
 
 struct ftrace_ret_stack *
-ftrace_graph_get_ret_stack(struct task_struct *task, int idx);
+ftrace_graph_get_ret_stack(struct task_struct *task, int skip);
+unsigned long ftrace_graph_top_ret_addr(struct task_struct *task);
 
 unsigned long ftrace_graph_ret_addr(struct task_struct *task, int *idx,
 				    unsigned long ret, unsigned long *retp);
+unsigned long *fgraph_get_task_var(struct fgraph_ops *gops);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -1112,6 +1300,9 @@ extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
 extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 
+/* Used by assembly, but to quiet sparse warnings */
+extern struct ftrace_ops *function_trace_op;
+
 static inline void pause_graph_tracing(void)
 {
 	atomic_inc(&current->tracing_graph_pause);
@@ -1147,14 +1338,9 @@ static inline void unpause_graph_tracing(void) { }
 #ifdef CONFIG_TRACING
 enum ftrace_dump_mode;
 
-extern enum ftrace_dump_mode ftrace_dump_on_oops;
-extern int tracepoint_printk;
+extern int ftrace_dump_on_oops_enabled(void);
 
 extern void disable_trace_on_warning(void);
-extern int __disable_trace_on_warning;
-
-int tracepoint_printk_sysctl(struct ctl_table *table, int write,
-			     void *buffer, size_t *lenp, loff_t *ppos);
 
 #else /* CONFIG_TRACING */
 static inline void  disable_trace_on_warning(void) { }
diff --git a/include/linux/ftrace_regs.h b/include/linux/ftrace_regs.h
new file mode 100644
index 000000000000..15627ceea9bc
--- /dev/null
+++ b/include/linux/ftrace_regs.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_FTRACE_REGS_H
+#define _LINUX_FTRACE_REGS_H
+
+/*
+ * For archs that just copy pt_regs in ftrace regs, it can use this default.
+ * If an architecture does not use pt_regs, it must define all the below
+ * accessor functions.
+ */
+#ifndef HAVE_ARCH_FTRACE_REGS
+struct __arch_ftrace_regs {
+	struct pt_regs		regs;
+};
+
+#define arch_ftrace_regs(fregs) ((struct __arch_ftrace_regs *)(fregs))
+
+struct ftrace_regs;
+
+#define ftrace_regs_get_instruction_pointer(fregs) \
+	instruction_pointer(&arch_ftrace_regs(fregs)->regs)
+#define ftrace_regs_get_argument(fregs, n) \
+	regs_get_kernel_argument(&arch_ftrace_regs(fregs)->regs, n)
+#define ftrace_regs_get_stack_pointer(fregs) \
+	kernel_stack_pointer(&arch_ftrace_regs(fregs)->regs)
+#define ftrace_regs_get_return_value(fregs) \
+	regs_return_value(&arch_ftrace_regs(fregs)->regs)
+#define ftrace_regs_set_return_value(fregs, ret) \
+	regs_set_return_value(&arch_ftrace_regs(fregs)->regs, ret)
+#define ftrace_override_function_with_return(fregs) \
+	override_function_with_return(&arch_ftrace_regs(fregs)->regs)
+#define ftrace_regs_query_register_offset(name) \
+	regs_query_register_offset(name)
+#define ftrace_regs_get_frame_pointer(fregs) \
+	frame_pointer(&arch_ftrace_regs(fregs)->regs)
+
+#endif /* HAVE_ARCH_FTRACE_REGS */
+
+/* This can be overridden by the architectures */
+#ifndef FTRACE_REGS_MAX_ARGS
+# define FTRACE_REGS_MAX_ARGS	6
+#endif
+
+#endif /* _LINUX_FTRACE_REGS_H */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index b70df27d7e85..9e9750f04980 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -4,11 +4,11 @@
 
 #include <linux/sched.h>
 #include <linux/ktime.h>
+#include <linux/mm_types.h>
 
 #include <uapi/linux/futex.h>
 
 struct inode;
-struct mm_struct;
 struct task_struct;
 
 /*
@@ -34,6 +34,7 @@ union futex_key {
 		u64 i_seq;
 		unsigned long pgoff;
 		unsigned int offset;
+		/* unsigned int node; */
 	} shared;
 	struct {
 		union {
@@ -42,11 +43,13 @@ union futex_key {
 		};
 		unsigned long address;
 		unsigned int offset;
+		/* unsigned int node; */
 	} private;
 	struct {
 		u64 ptr;
 		unsigned long word;
 		unsigned int offset;
+		unsigned int node;	/* NOT hashed! */
 	} both;
 };
 
@@ -77,7 +80,20 @@ void futex_exec_release(struct task_struct *tsk);
 
 long do_futex(u32 __user *uaddr, int op, u32 val, ktime_t *timeout,
 	      u32 __user *uaddr2, u32 val2, u32 val3);
-#else
+int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4);
+
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+int futex_hash_allocate_default(void);
+void futex_hash_free(struct mm_struct *mm);
+int futex_mm_init(struct mm_struct *mm);
+
+#else /* !CONFIG_FUTEX_PRIVATE_HASH */
+static inline int futex_hash_allocate_default(void) { return 0; }
+static inline int futex_hash_free(struct mm_struct *mm) { return 0; }
+static inline int futex_mm_init(struct mm_struct *mm) { return 0; }
+#endif /* CONFIG_FUTEX_PRIVATE_HASH */
+
+#else /* !CONFIG_FUTEX */
 static inline void futex_init_task(struct task_struct *tsk) { }
 static inline void futex_exit_recursive(struct task_struct *tsk) { }
 static inline void futex_exit_release(struct task_struct *tsk) { }
@@ -88,6 +104,17 @@ static inline long do_futex(u32 __user *uaddr, int op, u32 val,
 {
 	return -EINVAL;
 }
+static inline int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4)
+{
+	return -EINVAL;
+}
+static inline int futex_hash_allocate_default(void)
+{
+	return 0;
+}
+static inline int futex_hash_free(struct mm_struct *mm) { return 0; }
+static inline int futex_mm_init(struct mm_struct *mm) { return 0; }
+
 #endif
 
 #endif
diff --git a/include/linux/fw_table.h b/include/linux/fw_table.h
new file mode 100644
index 000000000000..9bd605b87c4c
--- /dev/null
+++ b/include/linux/fw_table.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  fw_tables.h - Parsing support for ACPI and ACPI-like tables provided by
+ *                platform or device firmware
+ *
+ *  Copyright (C) 2001 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
+ *  Copyright (C) 2023 Intel Corp.
+ */
+#ifndef _FW_TABLE_H_
+#define _FW_TABLE_H_
+
+union acpi_subtable_headers;
+
+typedef int (*acpi_tbl_entry_handler)(union acpi_subtable_headers *header,
+				      const unsigned long end);
+
+typedef int (*acpi_tbl_entry_handler_arg)(union acpi_subtable_headers *header,
+					  void *arg, const unsigned long end);
+
+struct acpi_subtable_proc {
+	int id;
+	acpi_tbl_entry_handler handler;
+	acpi_tbl_entry_handler_arg handler_arg;
+	void *arg;
+	int count;
+};
+
+union fw_table_header {
+	struct acpi_table_header acpi;
+	struct acpi_table_cdat cdat;
+};
+
+union acpi_subtable_headers {
+	struct acpi_subtable_header common;
+	struct acpi_hmat_structure hmat;
+	struct acpi_prmt_module_header prmt;
+	struct acpi_cedt_header cedt;
+	struct acpi_cdat_header cdat;
+};
+
+int acpi_parse_entries_array(char *id, unsigned long table_size,
+			     union fw_table_header *table_header,
+			     unsigned long max_length,
+			     struct acpi_subtable_proc *proc,
+			     int proc_num, unsigned int max_entries);
+
+int cdat_table_parse(enum acpi_cdat_type type,
+		     acpi_tbl_entry_handler_arg handler_arg, void *arg,
+		     struct acpi_table_cdat *table_header,
+		     unsigned long length);
+
+/* CXL is the only non-ACPI consumer of the FIRMWARE_TABLE library */
+#if IS_ENABLED(CONFIG_ACPI) && !IS_ENABLED(CONFIG_CXL_BUS)
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_ACPI_LIB(x)
+#define __init_or_fwtbl_lib __init_or_acpilib
+#else
+#define EXPORT_SYMBOL_FWTBL_LIB(x) EXPORT_SYMBOL_NS_GPL(x, "CXL")
+#define __init_or_fwtbl_lib
+#endif
+
+#endif
diff --git a/include/linux/fwctl.h b/include/linux/fwctl.h
new file mode 100644
index 000000000000..5d61fc8a6871
--- /dev/null
+++ b/include/linux/fwctl.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ */
+#ifndef __LINUX_FWCTL_H
+#define __LINUX_FWCTL_H
+#include <linux/device.h>
+#include <linux/cdev.h>
+#include <linux/cleanup.h>
+#include <uapi/fwctl/fwctl.h>
+
+struct fwctl_device;
+struct fwctl_uctx;
+
+/**
+ * struct fwctl_ops - Driver provided operations
+ *
+ * fwctl_unregister() will wait until all excuting ops are completed before it
+ * returns. Drivers should be mindful to not let their ops run for too long as
+ * it will block device hot unplug and module unloading.
+ */
+struct fwctl_ops {
+	/**
+	 * @device_type: The drivers assigned device_type number. This is uABI.
+	 */
+	enum fwctl_device_type device_type;
+	/**
+	 * @uctx_size: The size of the fwctl_uctx struct to allocate. The first
+	 * bytes of this memory will be a fwctl_uctx. The driver can use the
+	 * remaining bytes as its private memory.
+	 */
+	size_t uctx_size;
+	/**
+	 * @open_uctx: Called when a file descriptor is opened before the uctx
+	 * is ever used.
+	 */
+	int (*open_uctx)(struct fwctl_uctx *uctx);
+	/**
+	 * @close_uctx: Called when the uctx is destroyed, usually when the FD
+	 * is closed.
+	 */
+	void (*close_uctx)(struct fwctl_uctx *uctx);
+	/**
+	 * @info: Implement FWCTL_INFO. Return a kmalloc() memory that is copied
+	 * to out_device_data. On input length indicates the size of the user
+	 * buffer on output it indicates the size of the memory. The driver can
+	 * ignore length on input, the core code will handle everything.
+	 */
+	void *(*info)(struct fwctl_uctx *uctx, size_t *length);
+	/**
+	 * @fw_rpc: Implement FWCTL_RPC. Deliver rpc_in/in_len to the FW and
+	 * return the response and set out_len. rpc_in can be returned as the
+	 * response pointer. Otherwise the returned pointer is freed with
+	 * kvfree().
+	 */
+	void *(*fw_rpc)(struct fwctl_uctx *uctx, enum fwctl_rpc_scope scope,
+			void *rpc_in, size_t in_len, size_t *out_len);
+};
+
+/**
+ * struct fwctl_device - Per-driver registration struct
+ * @dev: The sysfs (class/fwctl/fwctlXX) device
+ *
+ * Each driver instance will have one of these structs with the driver private
+ * data following immediately after. This struct is refcounted, it is freed by
+ * calling fwctl_put().
+ */
+struct fwctl_device {
+	struct device dev;
+	/* private: */
+	struct cdev cdev;
+
+	/* Protect uctx_list */
+	struct mutex uctx_list_lock;
+	struct list_head uctx_list;
+	/*
+	 * Protect ops, held for write when ops becomes NULL during unregister,
+	 * held for read whenever ops is loaded or an ops function is running.
+	 */
+	struct rw_semaphore registration_lock;
+	const struct fwctl_ops *ops;
+};
+
+struct fwctl_device *_fwctl_alloc_device(struct device *parent,
+					 const struct fwctl_ops *ops,
+					 size_t size);
+/**
+ * fwctl_alloc_device - Allocate a fwctl
+ * @parent: Physical device that provides the FW interface
+ * @ops: Driver ops to register
+ * @drv_struct: 'struct driver_fwctl' that holds the struct fwctl_device
+ * @member: Name of the struct fwctl_device in @drv_struct
+ *
+ * This allocates and initializes the fwctl_device embedded in the drv_struct.
+ * Upon success the pointer must be freed via fwctl_put(). Returns a 'drv_struct
+ * \*' on success, NULL on error.
+ */
+#define fwctl_alloc_device(parent, ops, drv_struct, member)               \
+	({                                                                \
+		static_assert(__same_type(struct fwctl_device,            \
+					  ((drv_struct *)NULL)->member)); \
+		static_assert(offsetof(drv_struct, member) == 0);         \
+		(drv_struct *)_fwctl_alloc_device(parent, ops,            \
+						  sizeof(drv_struct));    \
+	})
+
+static inline struct fwctl_device *fwctl_get(struct fwctl_device *fwctl)
+{
+	get_device(&fwctl->dev);
+	return fwctl;
+}
+static inline void fwctl_put(struct fwctl_device *fwctl)
+{
+	put_device(&fwctl->dev);
+}
+DEFINE_FREE(fwctl, struct fwctl_device *, if (_T) fwctl_put(_T));
+
+int fwctl_register(struct fwctl_device *fwctl);
+void fwctl_unregister(struct fwctl_device *fwctl);
+
+/**
+ * struct fwctl_uctx - Per user FD context
+ * @fwctl: fwctl instance that owns the context
+ *
+ * Every FD opened by userspace will get a unique context allocation. Any driver
+ * private data will follow immediately after.
+ */
+struct fwctl_uctx {
+	struct fwctl_device *fwctl;
+	/* private: */
+	/* Head at fwctl_device::uctx_list */
+	struct list_head uctx_list_entry;
+};
+
+#endif
diff --git a/include/linux/fwnode.h b/include/linux/fwnode.h
index 5700451b300f..097be89487bf 100644
--- a/include/linux/fwnode.h
+++ b/include/linux/fwnode.h
@@ -2,6 +2,11 @@
 /*
  * fwnode.h - Firmware device node object handle type definition.
  *
+ * This header file provides low-level data types and definitions for firmware
+ * and device property providers. The respective API header files supplied by
+ * them should contain all of the requisite data types and definitions for end
+ * users, so including it directly should not be necessary.
+ *
  * Copyright (C) 2015, Intel Corporation
  * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  */
@@ -9,10 +14,16 @@
 #ifndef _LINUX_FWNODE_H_
 #define _LINUX_FWNODE_H_
 
-#include <linux/types.h>
-#include <linux/list.h>
 #include <linux/bits.h>
 #include <linux/err.h>
+#include <linux/list.h>
+#include <linux/types.h>
+
+enum dev_dma_attr {
+	DEV_DMA_NOT_SUPPORTED,
+	DEV_DMA_NON_COHERENT,
+	DEV_DMA_COHERENT,
+};
 
 struct fwnode_operations;
 struct device;
@@ -41,6 +52,8 @@ struct device;
 struct fwnode_handle {
 	struct fwnode_handle *secondary;
 	const struct fwnode_operations *ops;
+
+	/* The below is used solely by device links, don't use otherwise */
 	struct device *dev;
 	struct list_head suppliers;
 	struct list_head consumers;
@@ -51,8 +64,10 @@ struct fwnode_handle {
  * fwnode link flags
  *
  * CYCLE:	The fwnode link is part of a cycle. Don't defer probe.
+ * IGNORE:	Completely ignore this link, even during cycle detection.
  */
 #define FWLINK_FLAG_CYCLE			BIT(0)
+#define FWLINK_FLAG_IGNORE			BIT(1)
 
 struct fwnode_link {
 	struct fwnode_handle *supplier;
@@ -81,7 +96,7 @@ struct fwnode_endpoint {
 #define SWNODE_GRAPH_PORT_NAME_FMT		"port@%u"
 #define SWNODE_GRAPH_ENDPOINT_NAME_FMT		"endpoint@%u"
 
-#define NR_FWNODE_REFERENCE_ARGS	8
+#define NR_FWNODE_REFERENCE_ARGS	16
 
 /**
  * struct fwnode_reference_args - Fwnode reference with additional arguments
@@ -102,6 +117,7 @@ struct fwnode_reference_args {
  * @device_is_available: Return true if the device is available.
  * @device_get_match_data: Return the device driver match data.
  * @property_present: Return true if a property is present.
+ * @property_read_bool: Return a boolean property value.
  * @property_read_int_array: Read an array of integer properties. Return zero on
  *			     success, a negative error code otherwise.
  * @property_read_string_array: Read an array of string properties. Return zero
@@ -131,6 +147,8 @@ struct fwnode_operations {
 	(*device_get_dma_attr)(const struct fwnode_handle *fwnode);
 	bool (*property_present)(const struct fwnode_handle *fwnode,
 				 const char *propname);
+	bool (*property_read_bool)(const struct fwnode_handle *fwnode,
+				   const char *propname);
 	int (*property_read_int_array)(const struct fwnode_handle *fwnode,
 				       const char *propname,
 				       unsigned int elem_size, void *val,
@@ -185,7 +203,6 @@ struct fwnode_operations {
 		if (fwnode_has_op(fwnode, op))				\
 			(fwnode)->ops->op(fwnode, ## __VA_ARGS__);	\
 	} while (false)
-#define get_dev_from_fwnode(fwnode)	get_device((fwnode)->dev)
 
 static inline void fwnode_init(struct fwnode_handle *fwnode,
 			       const struct fwnode_operations *ops)
@@ -207,9 +224,10 @@ static inline void fwnode_dev_initialized(struct fwnode_handle *fwnode,
 		fwnode->flags &= ~FWNODE_FLAG_INITIALIZED;
 }
 
-extern bool fw_devlink_is_strict(void);
-int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup);
+int fwnode_link_add(struct fwnode_handle *con, struct fwnode_handle *sup,
+		    u8 flags);
 void fwnode_links_purge(struct fwnode_handle *fwnode);
 void fw_devlink_purge_absent_suppliers(struct fwnode_handle *fwnode);
+bool fw_devlink_is_strict(void);
 
 #endif
diff --git a/include/linux/gameport.h b/include/linux/gameport.h
index 8c2f00018e89..86d62fdafd7a 100644
--- a/include/linux/gameport.h
+++ b/include/linux/gameport.h
@@ -5,7 +5,6 @@
 #ifndef _GAMEPORT_H
 #define _GAMEPORT_H
 
-#include <asm/io.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -59,12 +58,12 @@ struct gameport_driver {
 
 	bool ignore;
 };
-#define to_gameport_driver(d)	container_of(d, struct gameport_driver, driver)
+#define to_gameport_driver(d)	container_of_const(d, struct gameport_driver, driver)
 
 int gameport_open(struct gameport *gameport, struct gameport_driver *drv, int mode);
 void gameport_close(struct gameport *gameport);
 
-#if defined(CONFIG_GAMEPORT) || (defined(MODULE) && defined(CONFIG_GAMEPORT_MODULE))
+#if IS_REACHABLE(CONFIG_GAMEPORT)
 
 void __gameport_register_port(struct gameport *gameport, struct module *owner);
 /* use a define to avoid include chaining to get THIS_MODULE */
@@ -165,18 +164,12 @@ void gameport_unregister_driver(struct gameport_driver *drv);
 
 static inline void gameport_trigger(struct gameport *gameport)
 {
-	if (gameport->trigger)
-		gameport->trigger(gameport);
-	else
-		outb(0xff, gameport->io);
+	gameport->trigger(gameport);
 }
 
 static inline unsigned char gameport_read(struct gameport *gameport)
 {
-	if (gameport->read)
-		return gameport->read(gameport);
-	else
-		return inb(gameport->io);
+	return gameport->read(gameport);
 }
 
 static inline int gameport_cooked_read(struct gameport *gameport, int *axes, int *buttons)
diff --git a/include/linux/gcd.h b/include/linux/gcd.h
index cb572677fd7f..616e81a7f7e3 100644
--- a/include/linux/gcd.h
+++ b/include/linux/gcd.h
@@ -3,6 +3,9 @@
 #define _GCD_H
 
 #include <linux/compiler.h>
+#include <linux/jump_label.h>
+
+DECLARE_STATIC_KEY_TRUE(efficient_ffs_key);
 
 unsigned long gcd(unsigned long a, unsigned long b) __attribute_const__;
 
diff --git a/include/linux/generic-radix-tree.h b/include/linux/generic-radix-tree.h
index 107613f7d792..5b51c3d582d6 100644
--- a/include/linux/generic-radix-tree.h
+++ b/include/linux/generic-radix-tree.h
@@ -5,7 +5,7 @@
  * DOC: Generic radix trees/sparse arrays
  *
  * Very simple and minimalistic, supporting arbitrary size entries up to
- * PAGE_SIZE.
+ * GENRADIX_NODE_SIZE.
  *
  * A genradix is defined with the type it will store, like so:
  *
@@ -38,18 +38,76 @@
 
 #include <asm/page.h>
 #include <linux/bug.h>
+#include <linux/limits.h>
 #include <linux/log2.h>
 #include <linux/math.h>
+#include <linux/slab.h>
 #include <linux/types.h>
 
 struct genradix_root;
 
+#define GENRADIX_NODE_SHIFT	9
+#define GENRADIX_NODE_SIZE	(1U << GENRADIX_NODE_SHIFT)
+
+#define GENRADIX_ARY		(GENRADIX_NODE_SIZE / sizeof(struct genradix_node *))
+#define GENRADIX_ARY_SHIFT	ilog2(GENRADIX_ARY)
+
+/* depth that's needed for a genradix that can address up to ULONG_MAX: */
+#define GENRADIX_MAX_DEPTH	\
+	DIV_ROUND_UP(BITS_PER_LONG - GENRADIX_NODE_SHIFT, GENRADIX_ARY_SHIFT)
+
+#define GENRADIX_DEPTH_MASK				\
+	((unsigned long) (roundup_pow_of_two(GENRADIX_MAX_DEPTH + 1) - 1))
+
+static inline int genradix_depth_shift(unsigned depth)
+{
+	return GENRADIX_NODE_SHIFT + GENRADIX_ARY_SHIFT * depth;
+}
+
+/*
+ * Returns size (of data, in bytes) that a tree of a given depth holds:
+ */
+static inline size_t genradix_depth_size(unsigned depth)
+{
+	return 1UL << genradix_depth_shift(depth);
+}
+
+static inline unsigned genradix_root_to_depth(struct genradix_root *r)
+{
+	return (unsigned long) r & GENRADIX_DEPTH_MASK;
+}
+
+static inline struct genradix_node *genradix_root_to_node(struct genradix_root *r)
+{
+	return (void *) ((unsigned long) r & ~GENRADIX_DEPTH_MASK);
+}
+
 struct __genradix {
 	struct genradix_root		*root;
 };
 
+struct genradix_node {
+	union {
+		/* Interior node: */
+		struct genradix_node	*children[GENRADIX_ARY];
+
+		/* Leaf: */
+		u8			data[GENRADIX_NODE_SIZE];
+	};
+};
+
+static inline struct genradix_node *genradix_alloc_node(gfp_t gfp_mask)
+{
+	return kzalloc(GENRADIX_NODE_SIZE, gfp_mask);
+}
+
+static inline void genradix_free_node(struct genradix_node *node)
+{
+	kfree(node);
+}
+
 /*
- * NOTE: currently, sizeof(_type) must not be larger than PAGE_SIZE:
+ * NOTE: currently, sizeof(_type) must not be larger than GENRADIX_NODE_SIZE:
  */
 
 #define __GENRADIX_INITIALIZER					\
@@ -100,14 +158,14 @@ void __genradix_free(struct __genradix *);
 static inline size_t __idx_to_offset(size_t idx, size_t obj_size)
 {
 	if (__builtin_constant_p(obj_size))
-		BUILD_BUG_ON(obj_size > PAGE_SIZE);
+		BUILD_BUG_ON(obj_size > GENRADIX_NODE_SIZE);
 	else
-		BUG_ON(obj_size > PAGE_SIZE);
+		BUG_ON(obj_size > GENRADIX_NODE_SIZE);
 
 	if (!is_power_of_2(obj_size)) {
-		size_t objs_per_page = PAGE_SIZE / obj_size;
+		size_t objs_per_page = GENRADIX_NODE_SIZE / obj_size;
 
-		return (idx / objs_per_page) * PAGE_SIZE +
+		return (idx / objs_per_page) * GENRADIX_NODE_SIZE +
 			(idx % objs_per_page) * obj_size;
 	} else {
 		return idx * obj_size;
@@ -116,9 +174,38 @@ static inline size_t __idx_to_offset(size_t idx, size_t obj_size)
 
 #define __genradix_cast(_radix)		(typeof((_radix)->type[0]) *)
 #define __genradix_obj_size(_radix)	sizeof((_radix)->type[0])
+#define __genradix_objs_per_page(_radix)			\
+	(GENRADIX_NODE_SIZE / sizeof((_radix)->type[0]))
+#define __genradix_page_remainder(_radix)			\
+	(GENRADIX_NODE_SIZE % sizeof((_radix)->type[0]))
+
 #define __genradix_idx_to_offset(_radix, _idx)			\
 	__idx_to_offset(_idx, __genradix_obj_size(_radix))
 
+static inline void *__genradix_ptr_inlined(struct __genradix *radix, size_t offset)
+{
+	struct genradix_root *r = READ_ONCE(radix->root);
+	struct genradix_node *n = genradix_root_to_node(r);
+	unsigned level		= genradix_root_to_depth(r);
+	unsigned shift		= genradix_depth_shift(level);
+
+	if (unlikely(ilog2(offset) >= genradix_depth_shift(level)))
+		return NULL;
+
+	while (n && shift > GENRADIX_NODE_SHIFT) {
+		shift -= GENRADIX_ARY_SHIFT;
+		n = n->children[offset >> shift];
+		offset &= (1UL << shift) - 1;
+	}
+
+	return n ? &n->data[offset] : NULL;
+}
+
+#define genradix_ptr_inlined(_radix, _idx)			\
+	(__genradix_cast(_radix)				\
+	 __genradix_ptr_inlined(&(_radix)->tree,		\
+			__genradix_idx_to_offset(_radix, _idx)))
+
 void *__genradix_ptr(struct __genradix *, size_t);
 
 /**
@@ -133,7 +220,24 @@ void *__genradix_ptr(struct __genradix *, size_t);
 	 __genradix_ptr(&(_radix)->tree,			\
 			__genradix_idx_to_offset(_radix, _idx)))
 
-void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t);
+void *__genradix_ptr_alloc(struct __genradix *, size_t,
+			   struct genradix_node **, gfp_t);
+
+#define genradix_ptr_alloc_inlined(_radix, _idx, _gfp)			\
+	(__genradix_cast(_radix)					\
+	 (__genradix_ptr_inlined(&(_radix)->tree,			\
+			__genradix_idx_to_offset(_radix, _idx)) ?:	\
+	  __genradix_ptr_alloc(&(_radix)->tree,				\
+			__genradix_idx_to_offset(_radix, _idx),		\
+			NULL, _gfp)))
+
+#define genradix_ptr_alloc_preallocated_inlined(_radix, _idx, _new_node, _gfp)\
+	(__genradix_cast(_radix)					\
+	 (__genradix_ptr_inlined(&(_radix)->tree,			\
+			__genradix_idx_to_offset(_radix, _idx)) ?:	\
+	  __genradix_ptr_alloc(&(_radix)->tree,				\
+			__genradix_idx_to_offset(_radix, _idx),		\
+			_new_node, _gfp)))
 
 /**
  * genradix_ptr_alloc - get a pointer to a genradix entry, allocating it
@@ -148,7 +252,13 @@ void *__genradix_ptr_alloc(struct __genradix *, size_t, gfp_t);
 	(__genradix_cast(_radix)				\
 	 __genradix_ptr_alloc(&(_radix)->tree,			\
 			__genradix_idx_to_offset(_radix, _idx),	\
-			_gfp))
+			NULL, _gfp))
+
+#define genradix_ptr_alloc_preallocated(_radix, _idx, _new_node, _gfp)\
+	(__genradix_cast(_radix)				\
+	 __genradix_ptr_alloc(&(_radix)->tree,			\
+			__genradix_idx_to_offset(_radix, _idx),	\
+			_new_node, _gfp))
 
 struct genradix_iter {
 	size_t			offset;
@@ -179,16 +289,40 @@ void *__genradix_iter_peek(struct genradix_iter *, struct __genradix *, size_t);
 #define genradix_iter_peek(_iter, _radix)			\
 	(__genradix_cast(_radix)				\
 	 __genradix_iter_peek(_iter, &(_radix)->tree,		\
-			      PAGE_SIZE / __genradix_obj_size(_radix)))
+			__genradix_objs_per_page(_radix)))
+
+void *__genradix_iter_peek_prev(struct genradix_iter *, struct __genradix *,
+				size_t, size_t);
+
+/**
+ * genradix_iter_peek_prev - get first entry at or below iterator's current
+ *			     position
+ * @_iter:	a genradix_iter
+ * @_radix:	genradix being iterated over
+ *
+ * If no more entries exist at or below @_iter's current position, returns NULL
+ */
+#define genradix_iter_peek_prev(_iter, _radix)			\
+	(__genradix_cast(_radix)				\
+	 __genradix_iter_peek_prev(_iter, &(_radix)->tree,	\
+			__genradix_objs_per_page(_radix),	\
+			__genradix_obj_size(_radix) +		\
+			__genradix_page_remainder(_radix)))
 
 static inline void __genradix_iter_advance(struct genradix_iter *iter,
 					   size_t obj_size)
 {
+	if (iter->offset + obj_size < iter->offset) {
+		iter->offset	= SIZE_MAX;
+		iter->pos	= SIZE_MAX;
+		return;
+	}
+
 	iter->offset += obj_size;
 
 	if (!is_power_of_2(obj_size) &&
-	    (iter->offset & (PAGE_SIZE - 1)) + obj_size > PAGE_SIZE)
-		iter->offset = round_up(iter->offset, PAGE_SIZE);
+	    (iter->offset & (GENRADIX_NODE_SIZE - 1)) + obj_size > GENRADIX_NODE_SIZE)
+		iter->offset = round_up(iter->offset, GENRADIX_NODE_SIZE);
 
 	iter->pos++;
 }
@@ -196,6 +330,25 @@ static inline void __genradix_iter_advance(struct genradix_iter *iter,
 #define genradix_iter_advance(_iter, _radix)			\
 	__genradix_iter_advance(_iter, __genradix_obj_size(_radix))
 
+static inline void __genradix_iter_rewind(struct genradix_iter *iter,
+					  size_t obj_size)
+{
+	if (iter->offset == 0 ||
+	    iter->offset == SIZE_MAX) {
+		iter->offset = SIZE_MAX;
+		return;
+	}
+
+	if ((iter->offset & (GENRADIX_NODE_SIZE - 1)) == 0)
+		iter->offset -= GENRADIX_NODE_SIZE % obj_size;
+
+	iter->offset -= obj_size;
+	iter->pos--;
+}
+
+#define genradix_iter_rewind(_iter, _radix)			\
+	__genradix_iter_rewind(_iter, __genradix_obj_size(_radix))
+
 #define genradix_for_each_from(_radix, _iter, _p, _start)	\
 	for (_iter = genradix_iter_init(_radix, _start);	\
 	     (_p = genradix_iter_peek(&_iter, _radix)) != NULL;	\
@@ -213,6 +366,23 @@ static inline void __genradix_iter_advance(struct genradix_iter *iter,
 #define genradix_for_each(_radix, _iter, _p)			\
 	genradix_for_each_from(_radix, _iter, _p, 0)
 
+#define genradix_last_pos(_radix)				\
+	(SIZE_MAX / GENRADIX_NODE_SIZE * __genradix_objs_per_page(_radix) - 1)
+
+/**
+ * genradix_for_each_reverse - iterate over entry in a genradix, reverse order
+ * @_radix:	genradix to iterate over
+ * @_iter:	a genradix_iter to track current position
+ * @_p:		pointer to genradix entry type
+ *
+ * On every iteration, @_p will point to the current entry, and @_iter.pos
+ * will be the current entry's index.
+ */
+#define genradix_for_each_reverse(_radix, _iter, _p)		\
+	for (_iter = genradix_iter_init(_radix,	genradix_last_pos(_radix));\
+	     (_p = genradix_iter_peek_prev(&_iter, _radix)) != NULL;\
+	     genradix_iter_rewind(&_iter, _radix))
+
 int __genradix_prealloc(struct __genradix *, size_t, gfp_t);
 
 /**
diff --git a/include/linux/generic_pt/common.h b/include/linux/generic_pt/common.h
new file mode 100644
index 000000000000..6a9a1acb5aad
--- /dev/null
+++ b/include/linux/generic_pt/common.h
@@ -0,0 +1,191 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ */
+#ifndef __GENERIC_PT_COMMON_H
+#define __GENERIC_PT_COMMON_H
+
+#include <linux/types.h>
+#include <linux/build_bug.h>
+#include <linux/bits.h>
+
+/**
+ * DOC: Generic Radix Page Table
+ *
+ * Generic Radix Page Table is a set of functions and helpers to efficiently
+ * parse radix style page tables typically seen in HW implementations. The
+ * interface is built to deliver similar code generation as the mm's pte/pmd/etc
+ * system by fully inlining the exact code required to handle each table level.
+ *
+ * Like the mm subsystem each format contributes its parsing implementation
+ * under common names and the common code implements the required algorithms.
+ *
+ * The system is divided into three logical levels:
+ *
+ *  - The page table format and its manipulation functions
+ *  - Generic helpers to give a consistent API regardless of underlying format
+ *  - An algorithm implementation (e.g. IOMMU/DRM/KVM/MM)
+ *
+ * Multiple implementations are supported. The intention is to have the generic
+ * format code be re-usable for whatever specialized implementation is required.
+ * The generic code is solely about the format of the radix tree; it does not
+ * include memory allocation or higher level decisions that are left for the
+ * implementation.
+ *
+ * The generic framework supports a superset of functions across many HW
+ * implementations:
+ *
+ *  - Entries comprised of contiguous blocks of IO PTEs for larger page sizes
+ *  - Multi-level tables, up to 6 levels. Runtime selected top level
+ *  - Runtime variable table level size (ARM's concatenated tables)
+ *  - Expandable top level allowing dynamic sizing of table levels
+ *  - Optional leaf entries at any level
+ *  - 32-bit/64-bit virtual and output addresses, using every address bit
+ *  - Dirty tracking
+ *  - Sign extended addressing
+ */
+
+/**
+ * struct pt_common - struct for all page table implementations
+ */
+struct pt_common {
+	/**
+	 * @top_of_table: Encodes the table top pointer and the top level in a
+	 * single value. Must use READ_ONCE/WRITE_ONCE to access it. The lower
+	 * bits of the aligned table pointer are used for the level.
+	 */
+	uintptr_t top_of_table;
+	/**
+	 * @max_oasz_lg2: Maximum number of bits the OA can contain. Upper bits
+	 * must be zero. This may be less than what the page table format
+	 * supports, but must not be more.
+	 */
+	u8 max_oasz_lg2;
+	/**
+	 * @max_vasz_lg2: Maximum number of bits the VA can contain. Upper bits
+	 * are 0 or 1 depending on pt_full_va_prefix(). This may be less than
+	 * what the page table format supports, but must not be more. When
+	 * PT_FEAT_DYNAMIC_TOP is set this reflects the maximum VA capability.
+	 */
+	u8 max_vasz_lg2;
+	/**
+	 * @features: Bitmap of `enum pt_features`
+	 */
+	unsigned int features;
+};
+
+/* Encoding parameters for top_of_table */
+enum {
+	PT_TOP_LEVEL_BITS = 3,
+	PT_TOP_LEVEL_MASK = GENMASK(PT_TOP_LEVEL_BITS - 1, 0),
+};
+
+/**
+ * enum pt_features - Features turned on in the table. Each symbol is a bit
+ * position.
+ */
+enum pt_features {
+	/**
+	 * @PT_FEAT_DMA_INCOHERENT: Cache flush page table memory before
+	 * assuming the HW can read it. Otherwise a SMP release is sufficient
+	 * for HW to read it.
+	 */
+	PT_FEAT_DMA_INCOHERENT,
+	/**
+	 * @PT_FEAT_FULL_VA: The table can span the full VA range from 0 to
+	 * PT_VADDR_MAX.
+	 */
+	PT_FEAT_FULL_VA,
+	/**
+	 * @PT_FEAT_DYNAMIC_TOP: The table's top level can be increased
+	 * dynamically during map. This requires HW support for atomically
+	 * setting both the table top pointer and the starting table level.
+	 */
+	PT_FEAT_DYNAMIC_TOP,
+	/**
+	 * @PT_FEAT_SIGN_EXTEND: The top most bit of the valid VA range sign
+	 * extends up to the full pt_vaddr_t. This divides the page table into
+	 * three VA ranges::
+	 *
+	 *   0         -> 2^N - 1             Lower
+	 *   2^N       -> (MAX - 2^N - 1)     Non-Canonical
+	 *   MAX - 2^N -> MAX                 Upper
+	 *
+	 * In this mode pt_common::max_vasz_lg2 includes the sign bit and the
+	 * upper bits that don't fall within the translation are just validated.
+	 *
+	 * If not set there is no sign extension and valid VA goes from 0 to 2^N
+	 * - 1.
+	 */
+	PT_FEAT_SIGN_EXTEND,
+	/**
+	 * @PT_FEAT_FLUSH_RANGE: IOTLB maintenance is done by flushing IOVA
+	 * ranges which will clean out any walk cache or any IOPTE fully
+	 * contained by the range. The optimization objective is to minimize the
+	 * number of flushes even if ranges include IOVA gaps that do not need
+	 * to be flushed.
+	 */
+	PT_FEAT_FLUSH_RANGE,
+	/**
+	 * @PT_FEAT_FLUSH_RANGE_NO_GAPS: Like PT_FEAT_FLUSH_RANGE except that
+	 * the optimization objective is to only flush IOVA that has been
+	 * changed. This mode is suitable for cases like hypervisor shadowing
+	 * where flushing unchanged ranges may cause the hypervisor to reparse
+	 * significant amount of page table.
+	 */
+	PT_FEAT_FLUSH_RANGE_NO_GAPS,
+	/* private: */
+	PT_FEAT_FMT_START,
+};
+
+struct pt_amdv1 {
+	struct pt_common common;
+};
+
+enum {
+	/*
+	 * The memory backing the tables is encrypted. Use __sme_set() to adjust
+	 * the page table pointers in the tree. This only works with
+	 * CONFIG_AMD_MEM_ENCRYPT.
+	 */
+	PT_FEAT_AMDV1_ENCRYPT_TABLES = PT_FEAT_FMT_START,
+	/*
+	 * The PTEs are set to prevent cache incoherent traffic, such as PCI no
+	 * snoop. This is set either at creation time or before the first map
+	 * operation.
+	 */
+	PT_FEAT_AMDV1_FORCE_COHERENCE,
+};
+
+struct pt_vtdss {
+	struct pt_common common;
+};
+
+enum {
+	/*
+	 * The PTEs are set to prevent cache incoherent traffic, such as PCI no
+	 * snoop. This is set either at creation time or before the first map
+	 * operation.
+	 */
+	PT_FEAT_VTDSS_FORCE_COHERENCE = PT_FEAT_FMT_START,
+	/*
+	 * Prevent creating read-only PTEs. Used to work around HW errata
+	 * ERRATA_772415_SPR17.
+	 */
+	PT_FEAT_VTDSS_FORCE_WRITEABLE,
+};
+
+struct pt_x86_64 {
+	struct pt_common common;
+};
+
+enum {
+	/*
+	 * The memory backing the tables is encrypted. Use __sme_set() to adjust
+	 * the page table pointers in the tree. This only works with
+	 * CONFIG_AMD_MEM_ENCRYPT.
+	 */
+	PT_FEAT_X86_64_AMD_ENCRYPT_TABLES = PT_FEAT_FMT_START,
+};
+
+#endif
diff --git a/include/linux/generic_pt/iommu.h b/include/linux/generic_pt/iommu.h
new file mode 100644
index 000000000000..9eefbb74efd0
--- /dev/null
+++ b/include/linux/generic_pt/iommu.h
@@ -0,0 +1,293 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2024-2025, NVIDIA CORPORATION & AFFILIATES
+ */
+#ifndef __GENERIC_PT_IOMMU_H
+#define __GENERIC_PT_IOMMU_H
+
+#include <linux/generic_pt/common.h>
+#include <linux/iommu.h>
+#include <linux/mm_types.h>
+
+struct iommu_iotlb_gather;
+struct pt_iommu_ops;
+struct pt_iommu_driver_ops;
+struct iommu_dirty_bitmap;
+
+/**
+ * DOC: IOMMU Radix Page Table
+ *
+ * The IOMMU implementation of the Generic Page Table provides an ops struct
+ * that is useful to go with an iommu_domain to serve the DMA API, IOMMUFD and
+ * the generic map/unmap interface.
+ *
+ * This interface uses a caller provided locking approach. The caller must have
+ * a VA range lock concept that prevents concurrent threads from calling ops on
+ * the same VA. Generally the range lock must be at least as large as a single
+ * map call.
+ */
+
+/**
+ * struct pt_iommu - Base structure for IOMMU page tables
+ *
+ * The format-specific struct will include this as the first member.
+ */
+struct pt_iommu {
+	/**
+	 * @domain: The core IOMMU domain. The driver should use a union to
+	 * overlay this memory with its previously existing domain struct to
+	 * create an alias.
+	 */
+	struct iommu_domain domain;
+
+	/**
+	 * @ops: Function pointers to access the API
+	 */
+	const struct pt_iommu_ops *ops;
+
+	/**
+	 * @driver_ops: Function pointers provided by the HW driver to help
+	 * manage HW details like caches.
+	 */
+	const struct pt_iommu_driver_ops *driver_ops;
+
+	/**
+	 * @nid: Node ID to use for table memory allocations. The IOMMU driver
+	 * may want to set the NID to the device's NID, if there are multiple
+	 * table walkers.
+	 */
+	int nid;
+
+	/**
+	 * @iommu_device: Device pointer used for any DMA cache flushing when
+	 * PT_FEAT_DMA_INCOHERENT. This is the iommu device that created the
+	 * page table which must have dma ops that perform cache flushing.
+	 */
+	struct device *iommu_device;
+};
+
+/**
+ * struct pt_iommu_info - Details about the IOMMU page table
+ *
+ * Returned from pt_iommu_ops->get_info()
+ */
+struct pt_iommu_info {
+	/**
+	 * @pgsize_bitmap: A bitmask where each set bit indicates
+	 * a page size that can be natively stored in the page table.
+	 */
+	u64 pgsize_bitmap;
+};
+
+struct pt_iommu_ops {
+	/**
+	 * @set_dirty: Make the iova write dirty
+	 * @iommu_table: Table to manipulate
+	 * @iova: IO virtual address to start
+	 *
+	 * This is only used by iommufd testing. It makes the iova dirty so that
+	 * read_and_clear_dirty() will see it as dirty. Unlike all the other ops
+	 * this one is safe to call without holding any locking. It may return
+	 * -EAGAIN if there is a race.
+	 */
+	int (*set_dirty)(struct pt_iommu *iommu_table, dma_addr_t iova);
+
+	/**
+	 * @get_info: Return the pt_iommu_info structure
+	 * @iommu_table: Table to query
+	 *
+	 * Return some basic static information about the page table.
+	 */
+	void (*get_info)(struct pt_iommu *iommu_table,
+			 struct pt_iommu_info *info);
+
+	/**
+	 * @deinit: Undo a format specific init operation
+	 * @iommu_table: Table to destroy
+	 *
+	 * Release all of the memory. The caller must have already removed the
+	 * table from all HW access and all caches.
+	 */
+	void (*deinit)(struct pt_iommu *iommu_table);
+};
+
+/**
+ * struct pt_iommu_driver_ops - HW IOTLB cache flushing operations
+ *
+ * The IOMMU driver should implement these using container_of(iommu_table) to
+ * get to it's iommu_domain derived structure. All ops can be called in atomic
+ * contexts as they are buried under DMA API calls.
+ */
+struct pt_iommu_driver_ops {
+	/**
+	 * @change_top: Update the top of table pointer
+	 * @iommu_table: Table to operate on
+	 * @top_paddr: New CPU physical address of the top pointer
+	 * @top_level: IOMMU PT level of the new top
+	 *
+	 * Called under the get_top_lock() spinlock. The driver must update all
+	 * HW references to this domain with a new top address and
+	 * configuration. On return mappings placed in the new top must be
+	 * reachable by the HW.
+	 *
+	 * top_level encodes the level in IOMMU PT format, level 0 is the
+	 * smallest page size increasing from there. This has to be translated
+	 * to any HW specific format. During this call the new top will not be
+	 * visible to any other API.
+	 *
+	 * This op is only used by PT_FEAT_DYNAMIC_TOP, and is required if
+	 * enabled.
+	 */
+	void (*change_top)(struct pt_iommu *iommu_table, phys_addr_t top_paddr,
+			   unsigned int top_level);
+
+	/**
+	 * @get_top_lock: lock to hold when changing the table top
+	 * @iommu_table: Table to operate on
+	 *
+	 * Return a lock to hold when changing the table top page table from
+	 * being stored in HW. The lock will be held prior to calling
+	 * change_top() and released once the top is fully visible.
+	 *
+	 * Typically this would be a lock that protects the iommu_domain's
+	 * attachment list.
+	 *
+	 * This op is only used by PT_FEAT_DYNAMIC_TOP, and is required if
+	 * enabled.
+	 */
+	spinlock_t *(*get_top_lock)(struct pt_iommu *iommu_table);
+};
+
+static inline void pt_iommu_deinit(struct pt_iommu *iommu_table)
+{
+	/*
+	 * It is safe to call pt_iommu_deinit() before an init, or if init
+	 * fails. The ops pointer will only become non-NULL if deinit needs to be
+	 * run.
+	 */
+	if (iommu_table->ops)
+		iommu_table->ops->deinit(iommu_table);
+}
+
+/**
+ * struct pt_iommu_cfg - Common configuration values for all formats
+ */
+struct pt_iommu_cfg {
+	/**
+	 * @features: Features required. Only these features will be turned on.
+	 * The feature list should reflect what the IOMMU HW is capable of.
+	 */
+	unsigned int features;
+	/**
+	 * @hw_max_vasz_lg2: Maximum VA the IOMMU HW can support. This will
+	 * imply the top level of the table.
+	 */
+	u8 hw_max_vasz_lg2;
+	/**
+	 * @hw_max_oasz_lg2: Maximum OA the IOMMU HW can support. The format
+	 * might select a lower maximum OA.
+	 */
+	u8 hw_max_oasz_lg2;
+};
+
+/* Generate the exported function signatures from iommu_pt.h */
+#define IOMMU_PROTOTYPES(fmt)                                                  \
+	phys_addr_t pt_iommu_##fmt##_iova_to_phys(struct iommu_domain *domain, \
+						  dma_addr_t iova);            \
+	int pt_iommu_##fmt##_map_pages(struct iommu_domain *domain,            \
+				       unsigned long iova, phys_addr_t paddr,  \
+				       size_t pgsize, size_t pgcount,          \
+				       int prot, gfp_t gfp, size_t *mapped);   \
+	size_t pt_iommu_##fmt##_unmap_pages(                                   \
+		struct iommu_domain *domain, unsigned long iova,               \
+		size_t pgsize, size_t pgcount,                                 \
+		struct iommu_iotlb_gather *iotlb_gather);                      \
+	int pt_iommu_##fmt##_read_and_clear_dirty(                             \
+		struct iommu_domain *domain, unsigned long iova, size_t size,  \
+		unsigned long flags, struct iommu_dirty_bitmap *dirty);        \
+	int pt_iommu_##fmt##_init(struct pt_iommu_##fmt *table,                \
+				  const struct pt_iommu_##fmt##_cfg *cfg,      \
+				  gfp_t gfp);                                  \
+	void pt_iommu_##fmt##_hw_info(struct pt_iommu_##fmt *table,            \
+				      struct pt_iommu_##fmt##_hw_info *info)
+#define IOMMU_FORMAT(fmt, member)       \
+	struct pt_iommu_##fmt {         \
+		struct pt_iommu iommu;  \
+		struct pt_##fmt member; \
+	};                              \
+	IOMMU_PROTOTYPES(fmt)
+
+/*
+ * A driver uses IOMMU_PT_DOMAIN_OPS to populate the iommu_domain_ops for the
+ * iommu_pt
+ */
+#define IOMMU_PT_DOMAIN_OPS(fmt)                        \
+	.iova_to_phys = &pt_iommu_##fmt##_iova_to_phys, \
+	.map_pages = &pt_iommu_##fmt##_map_pages,       \
+	.unmap_pages = &pt_iommu_##fmt##_unmap_pages
+#define IOMMU_PT_DIRTY_OPS(fmt) \
+	.read_and_clear_dirty = &pt_iommu_##fmt##_read_and_clear_dirty
+
+/*
+ * The driver should setup its domain struct like
+ *	union {
+ *		struct iommu_domain domain;
+ *		struct pt_iommu_xxx xx;
+ *	};
+ * PT_IOMMU_CHECK_DOMAIN(struct mock_iommu_domain, xx.iommu, domain);
+ *
+ * Which creates an alias between driver_domain.domain and
+ * driver_domain.xx.iommu.domain. This is to avoid a mass rename of existing
+ * driver_domain.domain users.
+ */
+#define PT_IOMMU_CHECK_DOMAIN(s, pt_iommu_memb, domain_memb) \
+	static_assert(offsetof(s, pt_iommu_memb.domain) ==   \
+		      offsetof(s, domain_memb))
+
+struct pt_iommu_amdv1_cfg {
+	struct pt_iommu_cfg common;
+	unsigned int starting_level;
+};
+
+struct pt_iommu_amdv1_hw_info {
+	u64 host_pt_root;
+	u8 mode;
+};
+
+IOMMU_FORMAT(amdv1, amdpt);
+
+/* amdv1_mock is used by the iommufd selftest */
+#define pt_iommu_amdv1_mock pt_iommu_amdv1
+#define pt_iommu_amdv1_mock_cfg pt_iommu_amdv1_cfg
+struct pt_iommu_amdv1_mock_hw_info;
+IOMMU_PROTOTYPES(amdv1_mock);
+
+struct pt_iommu_vtdss_cfg {
+	struct pt_iommu_cfg common;
+	/* 4 is a 57 bit 5 level table */
+	unsigned int top_level;
+};
+
+struct pt_iommu_vtdss_hw_info {
+	u64 ssptptr;
+	u8 aw;
+};
+
+IOMMU_FORMAT(vtdss, vtdss_pt);
+
+struct pt_iommu_x86_64_cfg {
+	struct pt_iommu_cfg common;
+	/* 4 is a 57 bit 5 level table */
+	unsigned int top_level;
+};
+
+struct pt_iommu_x86_64_hw_info {
+	u64 gcr3_pt;
+	u8 levels;
+};
+
+IOMMU_FORMAT(x86_64, x86_64_pt);
+
+#undef IOMMU_PROTOTYPES
+#undef IOMMU_FORMAT
+#endif
diff --git a/include/linux/genetlink.h b/include/linux/genetlink.h
deleted file mode 100644
index c285968e437a..000000000000
--- a/include/linux/genetlink.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_GENERIC_NETLINK_H
-#define __LINUX_GENERIC_NETLINK_H
-
-#include <uapi/linux/genetlink.h>
-
-
-/* All generic netlink requests are serialized by a global lock.  */
-extern void genl_lock(void);
-extern void genl_unlock(void);
-
-/* for synchronisation between af_netlink and genetlink */
-extern atomic_t genl_sk_destructing_cnt;
-extern wait_queue_head_t genl_sk_destructing_waitq;
-
-#define MODULE_ALIAS_GENL_FAMILY(family)\
- MODULE_ALIAS_NET_PF_PROTO_NAME(PF_NETLINK, NETLINK_GENERIC, "-family-" family)
-
-#endif	/* __LINUX_GENERIC_NETLINK_H */
diff --git a/include/linux/genl_magic_func.h b/include/linux/genl_magic_func.h
index 2984b0cb24b1..d4da060b7532 100644
--- a/include/linux/genl_magic_func.h
+++ b/include/linux/genl_magic_func.h
@@ -2,6 +2,7 @@
 #ifndef GENL_MAGIC_FUNC_H
 #define GENL_MAGIC_FUNC_H
 
+#include <linux/args.h>
 #include <linux/build_bug.h>
 #include <linux/genl_magic_struct.h>
 
@@ -23,7 +24,7 @@
 #define GENL_struct(tag_name, tag_number, s_name, s_fields)		\
 	[tag_name] = { .type = NLA_NESTED },
 
-static struct nla_policy CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy)[] = {
+static struct nla_policy CONCATENATE(GENL_MAGIC_FAMILY, _tla_nl_policy)[] = {
 #include GENL_MAGIC_INCLUDE_FILE
 };
 
@@ -209,7 +210,7 @@ static int s_name ## _from_attrs_for_change(struct s_name *s,		\
  * Magic: define op number to op name mapping				{{{1
  *									{{{2
  */
-static const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd)
+static const char *CONCATENATE(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd)
 {
 	switch (cmd) {
 #undef GENL_op
@@ -235,7 +236,7 @@ static const char *CONCAT_(GENL_MAGIC_FAMILY, _genl_cmd_to_str)(__u8 cmd)
 	.cmd = op_name,						\
 },
 
-#define ZZZ_genl_ops		CONCAT_(GENL_MAGIC_FAMILY, _genl_ops)
+#define ZZZ_genl_ops		CONCATENATE(GENL_MAGIC_FAMILY, _genl_ops)
 static struct genl_ops ZZZ_genl_ops[] __read_mostly = {
 #include GENL_MAGIC_INCLUDE_FILE
 };
@@ -248,32 +249,32 @@ static struct genl_ops ZZZ_genl_ops[] __read_mostly = {
  * and provide register/unregister functions.
  *									{{{2
  */
-#define ZZZ_genl_family		CONCAT_(GENL_MAGIC_FAMILY, _genl_family)
+#define ZZZ_genl_family		CONCATENATE(GENL_MAGIC_FAMILY, _genl_family)
 static struct genl_family ZZZ_genl_family;
 /*
  * Magic: define multicast groups
  * Magic: define multicast group registration helper
  */
-#define ZZZ_genl_mcgrps		CONCAT_(GENL_MAGIC_FAMILY, _genl_mcgrps)
+#define ZZZ_genl_mcgrps		CONCATENATE(GENL_MAGIC_FAMILY, _genl_mcgrps)
 static const struct genl_multicast_group ZZZ_genl_mcgrps[] = {
 #undef GENL_mc_group
 #define GENL_mc_group(group) { .name = #group, },
 #include GENL_MAGIC_INCLUDE_FILE
 };
 
-enum CONCAT_(GENL_MAGIC_FAMILY, group_ids) {
+enum CONCATENATE(GENL_MAGIC_FAMILY, group_ids) {
 #undef GENL_mc_group
-#define GENL_mc_group(group) CONCAT_(GENL_MAGIC_FAMILY, _group_ ## group),
+#define GENL_mc_group(group) CONCATENATE(GENL_MAGIC_FAMILY, _group_ ## group),
 #include GENL_MAGIC_INCLUDE_FILE
 };
 
 #undef GENL_mc_group
 #define GENL_mc_group(group)						\
-static int CONCAT_(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)(	\
+static int CONCATENATE(GENL_MAGIC_FAMILY, _genl_multicast_ ## group)(	\
 	struct sk_buff *skb, gfp_t flags)				\
 {									\
 	unsigned int group_id =						\
-		CONCAT_(GENL_MAGIC_FAMILY, _group_ ## group);		\
+		CONCATENATE(GENL_MAGIC_FAMILY, _group_ ## group);		\
 	return genlmsg_multicast(&ZZZ_genl_family, skb, 0,		\
 				 group_id, flags);			\
 }
@@ -289,8 +290,8 @@ static struct genl_family ZZZ_genl_family __ro_after_init = {
 #ifdef GENL_MAGIC_FAMILY_HDRSZ
 	.hdrsize = NLA_ALIGN(GENL_MAGIC_FAMILY_HDRSZ),
 #endif
-	.maxattr = ARRAY_SIZE(CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy))-1,
-	.policy	= CONCAT_(GENL_MAGIC_FAMILY, _tla_nl_policy),
+	.maxattr = ARRAY_SIZE(CONCATENATE(GENL_MAGIC_FAMILY, _tla_nl_policy))-1,
+	.policy	= CONCATENATE(GENL_MAGIC_FAMILY, _tla_nl_policy),
 	.ops = ZZZ_genl_ops,
 	.n_ops = ARRAY_SIZE(ZZZ_genl_ops),
 	.mcgrps = ZZZ_genl_mcgrps,
@@ -299,12 +300,12 @@ static struct genl_family ZZZ_genl_family __ro_after_init = {
 	.module = THIS_MODULE,
 };
 
-int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void)
+int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void)
 {
 	return genl_register_family(&ZZZ_genl_family);
 }
 
-void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void)
+void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void)
 {
 	genl_unregister_family(&ZZZ_genl_family);
 }
diff --git a/include/linux/genl_magic_struct.h b/include/linux/genl_magic_struct.h
index f81d48987528..621b87a87d74 100644
--- a/include/linux/genl_magic_struct.h
+++ b/include/linux/genl_magic_struct.h
@@ -14,14 +14,12 @@
 # error "you need to define GENL_MAGIC_INCLUDE_FILE before inclusion"
 #endif
 
-#include <linux/genetlink.h>
+#include <linux/args.h>
 #include <linux/types.h>
+#include <net/genetlink.h>
 
-#define CONCAT__(a,b)	a ## b
-#define CONCAT_(a,b)	CONCAT__(a,b)
-
-extern int CONCAT_(GENL_MAGIC_FAMILY, _genl_register)(void);
-extern void CONCAT_(GENL_MAGIC_FAMILY, _genl_unregister)(void);
+extern int CONCATENATE(GENL_MAGIC_FAMILY, _genl_register)(void);
+extern void CONCATENATE(GENL_MAGIC_FAMILY, _genl_unregister)(void);
 
 /*
  * Extension of genl attribute validation policies			{{{2
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 665f06675c83..b155929af5b1 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -6,8 +6,12 @@
 
 #include <linux/mmzone.h>
 #include <linux/topology.h>
+#include <linux/alloc_tag.h>
+#include <linux/cleanup.h>
+#include <linux/sched.h>
 
 struct vm_area_struct;
+struct mempolicy;
 
 /* Convert GFP flags to their corresponding migrate type */
 #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE)
@@ -36,6 +40,25 @@ static inline bool gfpflags_allow_blocking(const gfp_t gfp_flags)
 	return !!(gfp_flags & __GFP_DIRECT_RECLAIM);
 }
 
+static inline bool gfpflags_allow_spinning(const gfp_t gfp_flags)
+{
+	/*
+	 * !__GFP_DIRECT_RECLAIM -> direct claim is not allowed.
+	 * !__GFP_KSWAPD_RECLAIM -> it's not safe to wake up kswapd.
+	 * All GFP_* flags including GFP_NOWAIT use one or both flags.
+	 * alloc_pages_nolock() is the only API that doesn't specify either flag.
+	 *
+	 * This is stronger than GFP_NOWAIT or GFP_ATOMIC because
+	 * those are guaranteed to never block on a sleeping lock.
+	 * Here we are enforcing that the allocation doesn't ever spin
+	 * on any locks (i.e. only trylocks). There is no high level
+	 * GFP_$FOO flag for this use in alloc_pages_nolock() as the
+	 * regular page allocator doesn't fully support this
+	 * allocation mode.
+	 */
+	return !!(gfp_flags & __GFP_RECLAIM);
+}
+
 #ifdef CONFIG_HIGHMEM
 #define OPT_ZONE_HIGHMEM ZONE_HIGHMEM
 #else
@@ -154,6 +177,31 @@ static inline int gfp_zonelist(gfp_t flags)
 }
 
 /*
+ * gfp flag masking for nested internal allocations.
+ *
+ * For code that needs to do allocations inside the public allocation API (e.g.
+ * memory allocation tracking code) the allocations need to obey the caller
+ * allocation context constrains to prevent allocation context mismatches (e.g.
+ * GFP_KERNEL allocations in GFP_NOFS contexts) from potential deadlock
+ * situations.
+ *
+ * It is also assumed that these nested allocations are for internal kernel
+ * object storage purposes only and are not going to be used for DMA, etc. Hence
+ * we strip out all the zone information and leave just the context information
+ * intact.
+ *
+ * Further, internal allocations must fail before the higher level allocation
+ * can fail, so we must make them fail faster and fail silently. We also don't
+ * want them to deplete emergency reserves.  Hence nested allocations must be
+ * prepared for these allocations to fail.
+ */
+static inline gfp_t gfp_nested_mask(gfp_t flags)
+{
+	return ((flags & (GFP_KERNEL | GFP_ATOMIC | __GFP_NOLOCKDEP)) |
+		(__GFP_NORETRY | __GFP_NOMEMALLOC | __GFP_NOWARN));
+}
+
+/*
  * We get the zone list from the current node and the gfp_mask.
  * This zone list contains a maximum of MAX_NUMNODES*MAX_NR_ZONES zones.
  * There are two zonelists per node, one for all zones with memory and
@@ -174,42 +222,42 @@ static inline void arch_free_page(struct page *page, int order) { }
 static inline void arch_alloc_page(struct page *page, int order) { }
 #endif
 
-struct page *__alloc_pages(gfp_t gfp, unsigned int order, int preferred_nid,
+struct page *__alloc_pages_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask);
-struct folio *__folio_alloc(gfp_t gfp, unsigned int order, int preferred_nid,
+#define __alloc_pages(...)			alloc_hooks(__alloc_pages_noprof(__VA_ARGS__))
+
+struct folio *__folio_alloc_noprof(gfp_t gfp, unsigned int order, int preferred_nid,
 		nodemask_t *nodemask);
+#define __folio_alloc(...)			alloc_hooks(__folio_alloc_noprof(__VA_ARGS__))
 
-unsigned long __alloc_pages_bulk(gfp_t gfp, int preferred_nid,
+unsigned long alloc_pages_bulk_noprof(gfp_t gfp, int preferred_nid,
 				nodemask_t *nodemask, int nr_pages,
-				struct list_head *page_list,
 				struct page **page_array);
+#define __alloc_pages_bulk(...)			alloc_hooks(alloc_pages_bulk_noprof(__VA_ARGS__))
 
-unsigned long alloc_pages_bulk_array_mempolicy(gfp_t gfp,
+unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp,
 				unsigned long nr_pages,
 				struct page **page_array);
+#define  alloc_pages_bulk_mempolicy(...)				\
+	alloc_hooks(alloc_pages_bulk_mempolicy_noprof(__VA_ARGS__))
 
 /* Bulk allocate order-0 pages */
-static inline unsigned long
-alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
-{
-	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL);
-}
+#define alloc_pages_bulk(_gfp, _nr_pages, _page_array)		\
+	__alloc_pages_bulk(_gfp, numa_mem_id(), NULL, _nr_pages, _page_array)
 
 static inline unsigned long
-alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array)
-{
-	return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, NULL, page_array);
-}
-
-static inline unsigned long
-alloc_pages_bulk_array_node(gfp_t gfp, int nid, unsigned long nr_pages, struct page **page_array)
+alloc_pages_bulk_node_noprof(gfp_t gfp, int nid, unsigned long nr_pages,
+				   struct page **page_array)
 {
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 
-	return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, NULL, page_array);
+	return alloc_pages_bulk_noprof(gfp, nid, NULL, nr_pages, page_array);
 }
 
+#define alloc_pages_bulk_node(...)				\
+	alloc_hooks(alloc_pages_bulk_node_noprof(__VA_ARGS__))
+
 static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
 {
 	gfp_t warn_gfp = gfp_mask & (__GFP_THISNODE|__GFP_NOWARN);
@@ -229,102 +277,123 @@ static inline void warn_if_node_offline(int this_node, gfp_t gfp_mask)
  * online. For more general interface, see alloc_pages_node().
  */
 static inline struct page *
-__alloc_pages_node(int nid, gfp_t gfp_mask, unsigned int order)
+__alloc_pages_node_noprof(int nid, gfp_t gfp_mask, unsigned int order)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
 	warn_if_node_offline(nid, gfp_mask);
 
-	return __alloc_pages(gfp_mask, order, nid, NULL);
+	return __alloc_pages_noprof(gfp_mask, order, nid, NULL);
 }
 
+#define  __alloc_pages_node(...)		alloc_hooks(__alloc_pages_node_noprof(__VA_ARGS__))
+
 static inline
-struct folio *__folio_alloc_node(gfp_t gfp, unsigned int order, int nid)
+struct folio *__folio_alloc_node_noprof(gfp_t gfp, unsigned int order, int nid)
 {
 	VM_BUG_ON(nid < 0 || nid >= MAX_NUMNODES);
 	warn_if_node_offline(nid, gfp);
 
-	return __folio_alloc(gfp, order, nid, NULL);
+	return __folio_alloc_noprof(gfp, order, nid, NULL);
 }
 
+#define  __folio_alloc_node(...)		alloc_hooks(__folio_alloc_node_noprof(__VA_ARGS__))
+
 /*
  * Allocate pages, preferring the node given as nid. When nid == NUMA_NO_NODE,
  * prefer the current CPU's closest node. Otherwise node must be valid and
  * online.
  */
-static inline struct page *alloc_pages_node(int nid, gfp_t gfp_mask,
-						unsigned int order)
+static inline struct page *alloc_pages_node_noprof(int nid, gfp_t gfp_mask,
+						   unsigned int order)
 {
 	if (nid == NUMA_NO_NODE)
 		nid = numa_mem_id();
 
-	return __alloc_pages_node(nid, gfp_mask, order);
+	return __alloc_pages_node_noprof(nid, gfp_mask, order);
 }
 
+#define  alloc_pages_node(...)			alloc_hooks(alloc_pages_node_noprof(__VA_ARGS__))
+
 #ifdef CONFIG_NUMA
-struct page *alloc_pages(gfp_t gfp, unsigned int order);
-struct folio *folio_alloc(gfp_t gfp, unsigned order);
-struct folio *vma_alloc_folio(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, bool hugepage);
+struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order);
+struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order);
+struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *mpol, pgoff_t ilx, int nid);
+struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma,
+		unsigned long addr);
 #else
-static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order)
+static inline struct page *alloc_pages_noprof(gfp_t gfp_mask, unsigned int order)
+{
+	return alloc_pages_node_noprof(numa_node_id(), gfp_mask, order);
+}
+static inline struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order)
 {
-	return alloc_pages_node(numa_node_id(), gfp_mask, order);
+	return __folio_alloc_node_noprof(gfp, order, numa_node_id());
 }
-static inline struct folio *folio_alloc(gfp_t gfp, unsigned int order)
+static inline struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *mpol, pgoff_t ilx, int nid)
 {
-	return __folio_alloc_node(gfp, order, numa_node_id());
+	return folio_alloc_noprof(gfp, order);
 }
-#define vma_alloc_folio(gfp, order, vma, addr, hugepage)		\
-	folio_alloc(gfp, order)
+#define vma_alloc_folio_noprof(gfp, order, vma, addr)		\
+	folio_alloc_noprof(gfp, order)
 #endif
+
+#define alloc_pages(...)			alloc_hooks(alloc_pages_noprof(__VA_ARGS__))
+#define folio_alloc(...)			alloc_hooks(folio_alloc_noprof(__VA_ARGS__))
+#define folio_alloc_mpol(...)			alloc_hooks(folio_alloc_mpol_noprof(__VA_ARGS__))
+#define vma_alloc_folio(...)			alloc_hooks(vma_alloc_folio_noprof(__VA_ARGS__))
+
 #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0)
-static inline struct page *alloc_page_vma(gfp_t gfp,
+
+static inline struct page *alloc_page_vma_noprof(gfp_t gfp,
 		struct vm_area_struct *vma, unsigned long addr)
 {
-	struct folio *folio = vma_alloc_folio(gfp, 0, vma, addr, false);
+	struct folio *folio = vma_alloc_folio_noprof(gfp, 0, vma, addr);
 
 	return &folio->page;
 }
+#define alloc_page_vma(...)			alloc_hooks(alloc_page_vma_noprof(__VA_ARGS__))
 
-extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order);
-extern unsigned long get_zeroed_page(gfp_t gfp_mask);
+struct page *alloc_pages_nolock_noprof(gfp_t gfp_flags, int nid, unsigned int order);
+#define alloc_pages_nolock(...)			alloc_hooks(alloc_pages_nolock_noprof(__VA_ARGS__))
 
-void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __alloc_size(1);
-void free_pages_exact(void *virt, size_t size);
-__meminit void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);
+extern unsigned long get_free_pages_noprof(gfp_t gfp_mask, unsigned int order);
+#define __get_free_pages(...)			alloc_hooks(get_free_pages_noprof(__VA_ARGS__))
 
-#define __get_free_page(gfp_mask) \
-		__get_free_pages((gfp_mask), 0)
+extern unsigned long get_zeroed_page_noprof(gfp_t gfp_mask);
+#define get_zeroed_page(...)			alloc_hooks(get_zeroed_page_noprof(__VA_ARGS__))
 
-#define __get_dma_pages(gfp_mask, order) \
-		__get_free_pages((gfp_mask) | GFP_DMA, (order))
+void *alloc_pages_exact_noprof(size_t size, gfp_t gfp_mask) __alloc_size(1);
+#define alloc_pages_exact(...)			alloc_hooks(alloc_pages_exact_noprof(__VA_ARGS__))
 
-extern void __free_pages(struct page *page, unsigned int order);
-extern void free_pages(unsigned long addr, unsigned int order);
+void free_pages_exact(void *virt, size_t size);
 
-struct page_frag_cache;
-extern void __page_frag_cache_drain(struct page *page, unsigned int count);
-extern void *page_frag_alloc_align(struct page_frag_cache *nc,
-				   unsigned int fragsz, gfp_t gfp_mask,
-				   unsigned int align_mask);
+__meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mask) __alloc_size(2);
+#define alloc_pages_exact_nid(...)					\
+	alloc_hooks(alloc_pages_exact_nid_noprof(__VA_ARGS__))
 
-static inline void *page_frag_alloc(struct page_frag_cache *nc,
-			     unsigned int fragsz, gfp_t gfp_mask)
-{
-	return page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
-}
+#define __get_free_page(gfp_mask)					\
+	__get_free_pages((gfp_mask), 0)
+
+#define __get_dma_pages(gfp_mask, order)				\
+	__get_free_pages((gfp_mask) | GFP_DMA, (order))
 
-extern void page_frag_free(void *addr);
+extern void __free_pages(struct page *page, unsigned int order);
+extern void free_pages_nolock(struct page *page, unsigned int order);
+extern void free_pages(unsigned long addr, unsigned int order);
 
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 
 void page_alloc_init_cpuhp(void);
+bool decay_pcp_high(struct zone *zone, struct per_cpu_pages *pcp);
 void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp);
 void drain_all_pages(struct zone *zone);
 void drain_local_pages(struct zone *zone);
 
 void page_alloc_init_late(void);
+void setup_pcp_cacheinfo(unsigned int cpu);
 
 /*
  * gfp_allowed_mask is set to GFP_BOOT_MASK during early boot to restrict what
@@ -343,15 +412,58 @@ static inline bool gfp_has_io_fs(gfp_t gfp)
 	return (gfp & (__GFP_IO | __GFP_FS)) == (__GFP_IO | __GFP_FS);
 }
 
+/*
+ * Check if the gfp flags allow compaction - GFP_NOIO is a really
+ * tricky context because the migration might require IO.
+ */
+static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
+{
+	return IS_ENABLED(CONFIG_COMPACTION) && (gfp_mask & __GFP_IO);
+}
+
 extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
 
 #ifdef CONFIG_CONTIG_ALLOC
+
+typedef unsigned int __bitwise acr_flags_t;
+#define ACR_FLAGS_NONE ((__force acr_flags_t)0) // ordinary allocation request
+#define ACR_FLAGS_CMA ((__force acr_flags_t)BIT(0)) // allocate for CMA
+
 /* The below functions must be run on a range from a single zone. */
-extern int alloc_contig_range(unsigned long start, unsigned long end,
-			      unsigned migratetype, gfp_t gfp_mask);
-extern struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask,
-				       int nid, nodemask_t *nodemask);
+extern int alloc_contig_range_noprof(unsigned long start, unsigned long end,
+				     acr_flags_t alloc_flags, gfp_t gfp_mask);
+#define alloc_contig_range(...)			alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__))
+
+extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask,
+					      int nid, nodemask_t *nodemask);
+#define alloc_contig_pages(...)			alloc_hooks(alloc_contig_pages_noprof(__VA_ARGS__))
+
 #endif
 void free_contig_range(unsigned long pfn, unsigned long nr_pages);
 
+#ifdef CONFIG_CONTIG_ALLOC
+static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp,
+							int nid, nodemask_t *node)
+{
+	struct page *page;
+
+	if (WARN_ON(!order || !(gfp & __GFP_COMP)))
+		return NULL;
+
+	page = alloc_contig_pages_noprof(1 << order, gfp, nid, node);
+
+	return page ? page_folio(page) : NULL;
+}
+#else
+static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp,
+							int nid, nodemask_t *node)
+{
+	return NULL;
+}
+#endif
+/* This should be paired with folio_put() rather than free_contig_range(). */
+#define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__))
+
+DEFINE_FREE(free_page, void *, free_page((unsigned long)_T))
+
 #endif /* __LINUX_GFP_H */
diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h
index 6583a58670c5..3de43b12209e 100644
--- a/include/linux/gfp_types.h
+++ b/include/linux/gfp_types.h
@@ -2,6 +2,8 @@
 #ifndef __LINUX_GFP_TYPES_H
 #define __LINUX_GFP_TYPES_H
 
+#include <linux/bits.h>
+
 /* The typedef is in types.h but we want the documentation here */
 #if 0
 /**
@@ -21,44 +23,80 @@ typedef unsigned int __bitwise gfp_t;
  * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c
  */
 
+enum {
+	___GFP_DMA_BIT,
+	___GFP_HIGHMEM_BIT,
+	___GFP_DMA32_BIT,
+	___GFP_MOVABLE_BIT,
+	___GFP_RECLAIMABLE_BIT,
+	___GFP_HIGH_BIT,
+	___GFP_IO_BIT,
+	___GFP_FS_BIT,
+	___GFP_ZERO_BIT,
+	___GFP_UNUSED_BIT,	/* 0x200u unused */
+	___GFP_DIRECT_RECLAIM_BIT,
+	___GFP_KSWAPD_RECLAIM_BIT,
+	___GFP_WRITE_BIT,
+	___GFP_NOWARN_BIT,
+	___GFP_RETRY_MAYFAIL_BIT,
+	___GFP_NOFAIL_BIT,
+	___GFP_NORETRY_BIT,
+	___GFP_MEMALLOC_BIT,
+	___GFP_COMP_BIT,
+	___GFP_NOMEMALLOC_BIT,
+	___GFP_HARDWALL_BIT,
+	___GFP_THISNODE_BIT,
+	___GFP_ACCOUNT_BIT,
+	___GFP_ZEROTAGS_BIT,
+#ifdef CONFIG_KASAN_HW_TAGS
+	___GFP_SKIP_ZERO_BIT,
+	___GFP_SKIP_KASAN_BIT,
+#endif
+#ifdef CONFIG_LOCKDEP
+	___GFP_NOLOCKDEP_BIT,
+#endif
+	___GFP_NO_OBJ_EXT_BIT,
+	___GFP_LAST_BIT
+};
+
 /* Plain integer GFP bitmasks. Do not use this directly. */
-#define ___GFP_DMA		0x01u
-#define ___GFP_HIGHMEM		0x02u
-#define ___GFP_DMA32		0x04u
-#define ___GFP_MOVABLE		0x08u
-#define ___GFP_RECLAIMABLE	0x10u
-#define ___GFP_HIGH		0x20u
-#define ___GFP_IO		0x40u
-#define ___GFP_FS		0x80u
-#define ___GFP_ZERO		0x100u
+#define ___GFP_DMA		BIT(___GFP_DMA_BIT)
+#define ___GFP_HIGHMEM		BIT(___GFP_HIGHMEM_BIT)
+#define ___GFP_DMA32		BIT(___GFP_DMA32_BIT)
+#define ___GFP_MOVABLE		BIT(___GFP_MOVABLE_BIT)
+#define ___GFP_RECLAIMABLE	BIT(___GFP_RECLAIMABLE_BIT)
+#define ___GFP_HIGH		BIT(___GFP_HIGH_BIT)
+#define ___GFP_IO		BIT(___GFP_IO_BIT)
+#define ___GFP_FS		BIT(___GFP_FS_BIT)
+#define ___GFP_ZERO		BIT(___GFP_ZERO_BIT)
 /* 0x200u unused */
-#define ___GFP_DIRECT_RECLAIM	0x400u
-#define ___GFP_KSWAPD_RECLAIM	0x800u
-#define ___GFP_WRITE		0x1000u
-#define ___GFP_NOWARN		0x2000u
-#define ___GFP_RETRY_MAYFAIL	0x4000u
-#define ___GFP_NOFAIL		0x8000u
-#define ___GFP_NORETRY		0x10000u
-#define ___GFP_MEMALLOC		0x20000u
-#define ___GFP_COMP		0x40000u
-#define ___GFP_NOMEMALLOC	0x80000u
-#define ___GFP_HARDWALL		0x100000u
-#define ___GFP_THISNODE		0x200000u
-#define ___GFP_ACCOUNT		0x400000u
-#define ___GFP_ZEROTAGS		0x800000u
+#define ___GFP_DIRECT_RECLAIM	BIT(___GFP_DIRECT_RECLAIM_BIT)
+#define ___GFP_KSWAPD_RECLAIM	BIT(___GFP_KSWAPD_RECLAIM_BIT)
+#define ___GFP_WRITE		BIT(___GFP_WRITE_BIT)
+#define ___GFP_NOWARN		BIT(___GFP_NOWARN_BIT)
+#define ___GFP_RETRY_MAYFAIL	BIT(___GFP_RETRY_MAYFAIL_BIT)
+#define ___GFP_NOFAIL		BIT(___GFP_NOFAIL_BIT)
+#define ___GFP_NORETRY		BIT(___GFP_NORETRY_BIT)
+#define ___GFP_MEMALLOC		BIT(___GFP_MEMALLOC_BIT)
+#define ___GFP_COMP		BIT(___GFP_COMP_BIT)
+#define ___GFP_NOMEMALLOC	BIT(___GFP_NOMEMALLOC_BIT)
+#define ___GFP_HARDWALL		BIT(___GFP_HARDWALL_BIT)
+#define ___GFP_THISNODE		BIT(___GFP_THISNODE_BIT)
+#define ___GFP_ACCOUNT		BIT(___GFP_ACCOUNT_BIT)
+#define ___GFP_ZEROTAGS		BIT(___GFP_ZEROTAGS_BIT)
 #ifdef CONFIG_KASAN_HW_TAGS
-#define ___GFP_SKIP_ZERO	0x1000000u
-#define ___GFP_SKIP_KASAN	0x2000000u
+#define ___GFP_SKIP_ZERO	BIT(___GFP_SKIP_ZERO_BIT)
+#define ___GFP_SKIP_KASAN	BIT(___GFP_SKIP_KASAN_BIT)
 #else
 #define ___GFP_SKIP_ZERO	0
 #define ___GFP_SKIP_KASAN	0
 #endif
 #ifdef CONFIG_LOCKDEP
-#define ___GFP_NOLOCKDEP	0x4000000u
+#define ___GFP_NOLOCKDEP	BIT(___GFP_NOLOCKDEP_BIT)
 #else
 #define ___GFP_NOLOCKDEP	0
 #endif
-/* If the above are modified, __GFP_BITS_SHIFT may need updating */
+#define ___GFP_NO_OBJ_EXT       BIT(___GFP_NO_OBJ_EXT_BIT)
 
 /*
  * Physical address zone modifiers (see linux/mmzone.h - low four bits)
@@ -99,12 +137,15 @@ typedef unsigned int __bitwise gfp_t;
  * node with no fallbacks or placement policy enforcements.
  *
  * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg.
+ *
+ * %__GFP_NO_OBJ_EXT causes slab allocation to have no object extension.
  */
 #define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE)
 #define __GFP_WRITE	((__force gfp_t)___GFP_WRITE)
 #define __GFP_HARDWALL   ((__force gfp_t)___GFP_HARDWALL)
 #define __GFP_THISNODE	((__force gfp_t)___GFP_THISNODE)
 #define __GFP_ACCOUNT	((__force gfp_t)___GFP_ACCOUNT)
+#define __GFP_NO_OBJ_EXT   ((__force gfp_t)___GFP_NO_OBJ_EXT)
 
 /**
  * DOC: Watermark modifiers
@@ -162,25 +203,26 @@ typedef unsigned int __bitwise gfp_t;
  * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim.
  *
  * The default allocator behavior depends on the request size. We have a concept
- * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
+ * of so-called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER).
  * !costly allocations are too essential to fail so they are implicitly
  * non-failing by default (with some exceptions like OOM victims might fail so
  * the caller still has to check for failures) while costly requests try to be
  * not disruptive and back off even without invoking the OOM killer.
  * The following three modifiers might be used to override some of these
- * implicit rules
+ * implicit rules. Please note that all of them must be used along with
+ * %__GFP_DIRECT_RECLAIM flag.
  *
  * %__GFP_NORETRY: The VM implementation will try only very lightweight
  * memory direct reclaim to get some memory under memory pressure (thus
  * it can sleep). It will avoid disruptive actions like OOM killer. The
  * caller must handle the failure which is quite likely to happen under
  * heavy memory pressure. The flag is suitable when failure can easily be
- * handled at small cost, such as reduced throughput
+ * handled at small cost, such as reduced throughput.
  *
  * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim
  * procedures that have previously failed if there is some indication
- * that progress has been made else where.  It can wait for other
- * tasks to attempt high level approaches to freeing memory such as
+ * that progress has been made elsewhere.  It can wait for other
+ * tasks to attempt high-level approaches to freeing memory such as
  * compaction (which removes fragmentation) and page-out.
  * There is still a definite limit to the number of retries, but it is
  * a larger limit than with %__GFP_NORETRY.
@@ -199,11 +241,14 @@ typedef unsigned int __bitwise gfp_t;
  * cannot handle allocation failures. The allocation could block
  * indefinitely but will never return with failure. Testing for
  * failure is pointless.
+ * It _must_ be blockable and used together with __GFP_DIRECT_RECLAIM.
+ * It should _never_ be used in non-sleepable contexts.
  * New users should be evaluated carefully (and the flag should be
  * used only when there is no reasonable failure policy) but it is
  * definitely preferable to use the flag rather than opencode endless
  * loop around allocator.
- * Using this flag for costly allocations is _highly_ discouraged.
+ * Allocating pages from the buddy with __GFP_NOFAIL and order > 1 is
+ * not supported. Please consider using kvmalloc() instead.
  */
 #define __GFP_IO	((__force gfp_t)___GFP_IO)
 #define __GFP_FS	((__force gfp_t)___GFP_FS)
@@ -230,7 +275,7 @@ typedef unsigned int __bitwise gfp_t;
  * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that
  * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting
  * memory tags at the same time as zeroing memory has minimal additional
- * performace impact.
+ * performance impact.
  *
  * %__GFP_SKIP_KASAN makes KASAN skip unpoisoning on page allocation.
  * Used for userspace and vmalloc pages; the latter are unpoisoned by
@@ -249,7 +294,7 @@ typedef unsigned int __bitwise gfp_t;
 #define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP)
 
 /* Room for N __GFP_FOO bits */
-#define __GFP_BITS_SHIFT (26 + IS_ENABLED(CONFIG_LOCKDEP))
+#define __GFP_BITS_SHIFT ___GFP_LAST_BIT
 #define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
 
 /**
@@ -274,7 +319,8 @@ typedef unsigned int __bitwise gfp_t;
  * accounted to kmemcg.
  *
  * %GFP_NOWAIT is for kernel allocations that should not stall for direct
- * reclaim, start physical IO or use any filesystem callback.
+ * reclaim, start physical IO or use any filesystem callback.  It is very
+ * likely to fail to allocate memory, even for very small allocations.
  *
  * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages
  * that do not require the starting of any physical IO.
@@ -325,7 +371,7 @@ typedef unsigned int __bitwise gfp_t;
 #define GFP_ATOMIC	(__GFP_HIGH|__GFP_KSWAPD_RECLAIM)
 #define GFP_KERNEL	(__GFP_RECLAIM | __GFP_IO | __GFP_FS)
 #define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT)
-#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM)
+#define GFP_NOWAIT	(__GFP_KSWAPD_RECLAIM | __GFP_NOWARN)
 #define GFP_NOIO	(__GFP_RECLAIM)
 #define GFP_NOFS	(__GFP_RECLAIM | __GFP_IO)
 #define GFP_USER	(__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL)
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 8528353e073b..8f85ddb26429 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * <linux/gpio.h>
+ * NOTE: This header *must not* be included.
  *
  * This is the LEGACY GPIO bulk include file, including legacy APIs. It is
  * used for GPIO drivers still referencing the global GPIO numberspace,
@@ -13,52 +13,20 @@
 #define __LINUX_GPIO_H
 
 #include <linux/types.h>
+#ifdef CONFIG_GPIOLIB
+#include <linux/gpio/consumer.h>
+#endif
 
-struct device;
+#ifdef CONFIG_GPIOLIB_LEGACY
 
-/* see Documentation/driver-api/gpio/legacy.rst */
+struct device;
 
 /* make these flag values available regardless of GPIO kconfig options */
-#define GPIOF_DIR_OUT	(0 << 0)
-#define GPIOF_DIR_IN	(1 << 0)
-
-#define GPIOF_INIT_LOW	(0 << 1)
-#define GPIOF_INIT_HIGH	(1 << 1)
-
-#define GPIOF_IN		(GPIOF_DIR_IN)
-#define GPIOF_OUT_INIT_LOW	(GPIOF_DIR_OUT | GPIOF_INIT_LOW)
-#define GPIOF_OUT_INIT_HIGH	(GPIOF_DIR_OUT | GPIOF_INIT_HIGH)
-
-/* Gpio pin is active-low */
-#define GPIOF_ACTIVE_LOW        (1 << 2)
-
-/* Gpio pin is open drain */
-#define GPIOF_OPEN_DRAIN	(1 << 3)
-
-/* Gpio pin is open source */
-#define GPIOF_OPEN_SOURCE	(1 << 4)
-
-#define GPIOF_EXPORT		(1 << 5)
-#define GPIOF_EXPORT_CHANGEABLE	(1 << 6)
-#define GPIOF_EXPORT_DIR_FIXED	(GPIOF_EXPORT)
-#define GPIOF_EXPORT_DIR_CHANGEABLE (GPIOF_EXPORT | GPIOF_EXPORT_CHANGEABLE)
-
-/**
- * struct gpio - a structure describing a GPIO with configuration
- * @gpio:	the GPIO number
- * @flags:	GPIO configuration as specified by GPIOF_*
- * @label:	a literal description string of this GPIO
- */
-struct gpio {
-	unsigned	gpio;
-	unsigned long	flags;
-	const char	*label;
-};
+#define GPIOF_IN		((1 << 0))
+#define GPIOF_OUT_INIT_LOW	((0 << 0) | (0 << 1))
+#define GPIOF_OUT_INIT_HIGH	((0 << 0) | (1 << 1))
 
 #ifdef CONFIG_GPIOLIB
-
-#include <linux/gpio/consumer.h>
-
 /*
  * "valid" GPIO numbers are nonnegative and may be passed to
  * setup routines like gpio_request().  Only some valid numbers
@@ -79,13 +47,6 @@ static inline bool gpio_is_valid(int number)
  * extra memory (for code and for per-GPIO table entries).
  */
 
-/*
- * At the end we want all GPIOs to be dynamically allocated from 0.
- * However, some legacy drivers still perform fixed allocation.
- * Until they are all fixed, leave 0-512 space for them.
- */
-#define GPIO_DYNAMIC_BASE	512
-
 /* Always use the library code for GPIO management calls,
  * or when sleeping may be involved.
  */
@@ -107,7 +68,7 @@ static inline int gpio_get_value_cansleep(unsigned gpio)
 }
 static inline void gpio_set_value_cansleep(unsigned gpio, int value)
 {
-	return gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value);
+	gpiod_set_raw_value_cansleep(gpio_to_desc(gpio), value);
 }
 
 static inline int gpio_get_value(unsigned gpio)
@@ -116,12 +77,7 @@ static inline int gpio_get_value(unsigned gpio)
 }
 static inline void gpio_set_value(unsigned gpio, int value)
 {
-	return gpiod_set_raw_value(gpio_to_desc(gpio), value);
-}
-
-static inline int gpio_cansleep(unsigned gpio)
-{
-	return gpiod_cansleep(gpio_to_desc(gpio));
+	gpiod_set_raw_value(gpio_to_desc(gpio), value);
 }
 
 static inline int gpio_to_irq(unsigned gpio)
@@ -130,12 +86,7 @@ static inline int gpio_to_irq(unsigned gpio)
 }
 
 int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
-int gpio_request_array(const struct gpio *array, size_t num);
-void gpio_free_array(const struct gpio *array, size_t num);
 
-/* CONFIG_GPIOLIB: bindings for managed devices that want to request gpios */
-
-int devm_gpio_request(struct device *dev, unsigned gpio, const char *label);
 int devm_gpio_request_one(struct device *dev, unsigned gpio,
 			  unsigned long flags, const char *label);
 
@@ -162,11 +113,6 @@ static inline int gpio_request_one(unsigned gpio,
 	return -ENOSYS;
 }
 
-static inline int gpio_request_array(const struct gpio *array, size_t num)
-{
-	return -ENOSYS;
-}
-
 static inline void gpio_free(unsigned gpio)
 {
 	might_sleep();
@@ -175,14 +121,6 @@ static inline void gpio_free(unsigned gpio)
 	WARN_ON(1);
 }
 
-static inline void gpio_free_array(const struct gpio *array, size_t num)
-{
-	might_sleep();
-
-	/* GPIO can never have been requested */
-	WARN_ON(1);
-}
-
 static inline int gpio_direction_input(unsigned gpio)
 {
 	return -ENOSYS;
@@ -206,13 +144,6 @@ static inline void gpio_set_value(unsigned gpio, int value)
 	WARN_ON(1);
 }
 
-static inline int gpio_cansleep(unsigned gpio)
-{
-	/* GPIO can never have been requested or set as {in,out}put */
-	WARN_ON(1);
-	return 0;
-}
-
 static inline int gpio_get_value_cansleep(unsigned gpio)
 {
 	/* GPIO can never have been requested or set as {in,out}put */
@@ -233,13 +164,6 @@ static inline int gpio_to_irq(unsigned gpio)
 	return -EINVAL;
 }
 
-static inline int devm_gpio_request(struct device *dev, unsigned gpio,
-				    const char *label)
-{
-	WARN_ON(1);
-	return -EINVAL;
-}
-
 static inline int devm_gpio_request_one(struct device *dev, unsigned gpio,
 					unsigned long flags, const char *label)
 {
@@ -248,5 +172,5 @@ static inline int devm_gpio_request_one(struct device *dev, unsigned gpio,
 }
 
 #endif /* ! CONFIG_GPIOLIB */
-
+#endif /* CONFIG_GPIOLIB_LEGACY */
 #endif /* __LINUX_GPIO_H */
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index 1c4385a00f88..cafeb7a40ad1 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -3,6 +3,7 @@
 #define __LINUX_GPIO_CONSUMER_H
 
 #include <linux/bits.h>
+#include <linux/err.h>
 #include <linux/types.h>
 
 struct acpi_device;
@@ -30,6 +31,7 @@ struct gpio_descs {
 #define GPIOD_FLAGS_BIT_DIR_OUT		BIT(1)
 #define GPIOD_FLAGS_BIT_DIR_VAL		BIT(2)
 #define GPIOD_FLAGS_BIT_OPEN_DRAIN	BIT(3)
+/* GPIOD_FLAGS_BIT_NONEXCLUSIVE is DEPRECATED, don't use in new code. */
 #define GPIOD_FLAGS_BIT_NONEXCLUSIVE	BIT(4)
 
 /**
@@ -110,8 +112,6 @@ int gpiod_get_direction(struct gpio_desc *desc);
 int gpiod_direction_input(struct gpio_desc *desc);
 int gpiod_direction_output(struct gpio_desc *desc, int value);
 int gpiod_direction_output_raw(struct gpio_desc *desc, int value);
-int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags);
-int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags);
 
 /* Value get/set from non-sleeping context */
 int gpiod_get_value(const struct gpio_desc *desc);
@@ -119,7 +119,7 @@ int gpiod_get_array_value(unsigned int array_size,
 			  struct gpio_desc **desc_array,
 			  struct gpio_array *array_info,
 			  unsigned long *value_bitmap);
-void gpiod_set_value(struct gpio_desc *desc, int value);
+int gpiod_set_value(struct gpio_desc *desc, int value);
 int gpiod_set_array_value(unsigned int array_size,
 			  struct gpio_desc **desc_array,
 			  struct gpio_array *array_info,
@@ -129,7 +129,7 @@ int gpiod_get_raw_array_value(unsigned int array_size,
 			      struct gpio_desc **desc_array,
 			      struct gpio_array *array_info,
 			      unsigned long *value_bitmap);
-void gpiod_set_raw_value(struct gpio_desc *desc, int value);
+int gpiod_set_raw_value(struct gpio_desc *desc, int value);
 int gpiod_set_raw_array_value(unsigned int array_size,
 			      struct gpio_desc **desc_array,
 			      struct gpio_array *array_info,
@@ -141,7 +141,7 @@ int gpiod_get_array_value_cansleep(unsigned int array_size,
 				   struct gpio_desc **desc_array,
 				   struct gpio_array *array_info,
 				   unsigned long *value_bitmap);
-void gpiod_set_value_cansleep(struct gpio_desc *desc, int value);
+int gpiod_set_value_cansleep(struct gpio_desc *desc, int value);
 int gpiod_set_array_value_cansleep(unsigned int array_size,
 				   struct gpio_desc **desc_array,
 				   struct gpio_array *array_info,
@@ -151,7 +151,7 @@ int gpiod_get_raw_array_value_cansleep(unsigned int array_size,
 				       struct gpio_desc **desc_array,
 				       struct gpio_array *array_info,
 				       unsigned long *value_bitmap);
-void gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value);
+int gpiod_set_raw_value_cansleep(struct gpio_desc *desc, int value);
 int gpiod_set_raw_array_value_cansleep(unsigned int array_size,
 				       struct gpio_desc **desc_array,
 				       struct gpio_array *array_info,
@@ -159,7 +159,6 @@ int gpiod_set_raw_array_value_cansleep(unsigned int array_size,
 
 int gpiod_set_config(struct gpio_desc *desc, unsigned long config);
 int gpiod_set_debounce(struct gpio_desc *desc, unsigned int debounce);
-int gpiod_set_transitory(struct gpio_desc *desc, bool transitory);
 void gpiod_toggle_active_low(struct gpio_desc *desc);
 
 int gpiod_is_active_low(const struct gpio_desc *desc);
@@ -168,10 +167,14 @@ int gpiod_cansleep(const struct gpio_desc *desc);
 int gpiod_to_irq(const struct gpio_desc *desc);
 int gpiod_set_consumer_name(struct gpio_desc *desc, const char *name);
 
+bool gpiod_is_shared(const struct gpio_desc *desc);
+
 /* Convert between the old gpio_ and new gpiod_ interfaces */
 struct gpio_desc *gpio_to_desc(unsigned gpio);
 int desc_to_gpio(const struct gpio_desc *desc);
 
+int gpiod_hwgpio(const struct gpio_desc *desc);
+
 struct gpio_desc *fwnode_gpiod_get_index(struct fwnode_handle *fwnode,
 					 const char *con_id, int index,
 					 enum gpiod_flags flags,
@@ -182,13 +185,14 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev,
 					      enum gpiod_flags flags,
 					      const char *label);
 
+bool gpiod_is_equal(const struct gpio_desc *desc,
+		    const struct gpio_desc *other);
+
 #else /* CONFIG_GPIOLIB */
 
-#include <linux/err.h>
+#include <linux/bug.h>
 #include <linux/kernel.h>
 
-#include <asm/bug.h>
-
 static inline int gpiod_count(struct device *dev, const char *con_id)
 {
 	return 0;
@@ -349,18 +353,6 @@ static inline int gpiod_direction_output_raw(struct gpio_desc *desc, int value)
 	WARN_ON(desc);
 	return -ENOSYS;
 }
-static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc,
-					       unsigned long flags)
-{
-	WARN_ON(desc);
-	return -ENOSYS;
-}
-static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc,
-						unsigned long flags)
-{
-	WARN_ON(desc);
-	return -ENOSYS;
-}
 static inline int gpiod_get_value(const struct gpio_desc *desc)
 {
 	/* GPIO can never have been requested */
@@ -376,10 +368,11 @@ static inline int gpiod_get_array_value(unsigned int array_size,
 	WARN_ON(desc_array);
 	return 0;
 }
-static inline void gpiod_set_value(struct gpio_desc *desc, int value)
+static inline int gpiod_set_value(struct gpio_desc *desc, int value)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(desc);
+	return 0;
 }
 static inline int gpiod_set_array_value(unsigned int array_size,
 					struct gpio_desc **desc_array,
@@ -405,10 +398,11 @@ static inline int gpiod_get_raw_array_value(unsigned int array_size,
 	WARN_ON(desc_array);
 	return 0;
 }
-static inline void gpiod_set_raw_value(struct gpio_desc *desc, int value)
+static inline int gpiod_set_raw_value(struct gpio_desc *desc, int value)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(desc);
+	return 0;
 }
 static inline int gpiod_set_raw_array_value(unsigned int array_size,
 					    struct gpio_desc **desc_array,
@@ -435,10 +429,11 @@ static inline int gpiod_get_array_value_cansleep(unsigned int array_size,
 	WARN_ON(desc_array);
 	return 0;
 }
-static inline void gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
+static inline int gpiod_set_value_cansleep(struct gpio_desc *desc, int value)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(desc);
+	return 0;
 }
 static inline int gpiod_set_array_value_cansleep(unsigned int array_size,
 					    struct gpio_desc **desc_array,
@@ -464,11 +459,12 @@ static inline int gpiod_get_raw_array_value_cansleep(unsigned int array_size,
 	WARN_ON(desc_array);
 	return 0;
 }
-static inline void gpiod_set_raw_value_cansleep(struct gpio_desc *desc,
-						int value)
+static inline int gpiod_set_raw_value_cansleep(struct gpio_desc *desc,
+					       int value)
 {
 	/* GPIO can never have been requested */
 	WARN_ON(desc);
+	return 0;
 }
 static inline int gpiod_set_raw_array_value_cansleep(unsigned int array_size,
 						struct gpio_desc **desc_array,
@@ -494,13 +490,6 @@ static inline int gpiod_set_debounce(struct gpio_desc *desc, unsigned int deboun
 	return -ENOSYS;
 }
 
-static inline int gpiod_set_transitory(struct gpio_desc *desc, bool transitory)
-{
-	/* GPIO can never have been requested */
-	WARN_ON(desc);
-	return -ENOSYS;
-}
-
 static inline void gpiod_toggle_active_low(struct gpio_desc *desc)
 {
 	/* GPIO can never have been requested */
@@ -535,6 +524,13 @@ static inline int gpiod_set_consumer_name(struct gpio_desc *desc,
 	return -EINVAL;
 }
 
+static inline bool gpiod_is_shared(const struct gpio_desc *desc)
+{
+	/* GPIO can never have been requested */
+	WARN_ON(desc);
+	return false;
+}
+
 static inline struct gpio_desc *gpio_to_desc(unsigned gpio)
 {
 	return NULL;
@@ -566,8 +562,40 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev,
 	return ERR_PTR(-ENOSYS);
 }
 
+static inline bool
+gpiod_is_equal(const struct gpio_desc *desc, const struct gpio_desc *other)
+{
+	WARN_ON(desc || other);
+	return false;
+}
+
 #endif /* CONFIG_GPIOLIB */
 
+#if IS_ENABLED(CONFIG_GPIOLIB) && IS_ENABLED(CONFIG_HTE)
+int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags);
+int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc, unsigned long flags);
+#else
+
+#include <linux/bug.h>
+
+static inline int gpiod_enable_hw_timestamp_ns(struct gpio_desc *desc,
+					       unsigned long flags)
+{
+	if (!IS_ENABLED(CONFIG_GPIOLIB))
+		WARN_ON(desc);
+
+	return -ENOSYS;
+}
+static inline int gpiod_disable_hw_timestamp_ns(struct gpio_desc *desc,
+						unsigned long flags)
+{
+	if (!IS_ENABLED(CONFIG_GPIOLIB))
+		WARN_ON(desc);
+
+	return -ENOSYS;
+}
+#endif /* CONFIG_GPIOLIB && CONFIG_HTE */
+
 static inline
 struct gpio_desc *devm_fwnode_gpiod_get(struct device *dev,
 					struct fwnode_handle *fwnode,
@@ -581,7 +609,7 @@ struct gpio_desc *devm_fwnode_gpiod_get(struct device *dev,
 
 struct acpi_gpio_params {
 	unsigned int crs_entry_index;
-	unsigned int line_index;
+	unsigned short line_index;
 	bool active_low;
 };
 
@@ -614,12 +642,8 @@ void acpi_dev_remove_driver_gpios(struct acpi_device *adev);
 int devm_acpi_dev_add_driver_gpios(struct device *dev,
 				   const struct acpi_gpio_mapping *gpios);
 
-struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin, char *label);
-
 #else  /* CONFIG_GPIOLIB && CONFIG_ACPI */
 
-#include <linux/err.h>
-
 static inline int acpi_dev_add_driver_gpios(struct acpi_device *adev,
 			      const struct acpi_gpio_mapping *gpios)
 {
@@ -633,12 +657,6 @@ static inline int devm_acpi_dev_add_driver_gpios(struct device *dev,
 	return -ENXIO;
 }
 
-static inline struct gpio_desc *acpi_get_and_request_gpiod(char *path, unsigned int pin,
-							   char *label)
-{
-	return ERR_PTR(-ENOSYS);
-}
-
 #endif /* CONFIG_GPIOLIB && CONFIG_ACPI */
 
 
@@ -651,8 +669,6 @@ void gpiod_unexport(struct gpio_desc *desc);
 
 #else  /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */
 
-#include <asm/errno.h>
-
 static inline int gpiod_export(struct gpio_desc *desc,
 			       bool direction_may_change)
 {
@@ -671,4 +687,14 @@ static inline void gpiod_unexport(struct gpio_desc *desc)
 
 #endif /* CONFIG_GPIOLIB && CONFIG_GPIO_SYSFS */
 
+static inline int gpiod_multi_set_value_cansleep(struct gpio_descs *descs,
+						 unsigned long *value_bitmap)
+{
+	if (IS_ERR_OR_NULL(descs))
+		return PTR_ERR_OR_ZERO(descs);
+
+	return gpiod_set_array_value_cansleep(descs->ndescs, descs->desc,
+					      descs->info, value_bitmap);
+}
+
 #endif
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 5c6db5533be6..fabe2baf7b50 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -3,6 +3,8 @@
 #define __LINUX_GPIO_DRIVER_H
 
 #include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/err.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/irqhandler.h>
@@ -12,6 +14,7 @@
 #include <linux/property.h>
 #include <linux/spinlock_types.h>
 #include <linux/types.h>
+#include <linux/util_macros.h>
 
 #ifdef CONFIG_GENERIC_MSI_IRQ
 #include <asm/msi.h>
@@ -61,13 +64,6 @@ struct gpio_irq_chip {
 	 */
 	struct irq_domain *domain;
 
-	/**
-	 * @domain_ops:
-	 *
-	 * Table of interrupt domain operations for this IRQ chip.
-	 */
-	const struct irq_domain_ops *domain_ops;
-
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 	/**
 	 * @fwnode:
@@ -252,6 +248,14 @@ struct gpio_irq_chip {
 	bool initialized;
 
 	/**
+	 * @domain_is_allocated_externally:
+	 *
+	 * True it the irq_domain was allocated outside of gpiolib, in which
+	 * case gpiolib won't free the irq_domain itself.
+	 */
+	bool domain_is_allocated_externally;
+
+	/**
 	 * @init_hw: optional routine to initialize hardware before
 	 * an IRQ chip will be added. This is quite useful when
 	 * a particular driver wants to clear IRQ related registers
@@ -283,8 +287,9 @@ struct gpio_irq_chip {
 	/**
 	 * @first:
 	 *
-	 * Required for static IRQ allocation. If set, irq_domain_add_simple()
-	 * will allocate and map all IRQs during initialization.
+	 * Required for static IRQ allocation. If set,
+	 * irq_domain_create_simple() will allocate and map all IRQs
+	 * during initialization.
 	 */
 	unsigned int first;
 
@@ -325,24 +330,30 @@ struct gpio_irq_chip {
  * @fwnode: optional fwnode providing this controller's properties
  * @owner: helps prevent removal of modules exporting active GPIOs
  * @request: optional hook for chip-specific activation, such as
- *	enabling module power and clock; may sleep
+ *	enabling module power and clock; may sleep; must return 0 on success
+ *	or negative error number on failure
  * @free: optional hook for chip-specific deactivation, such as
  *	disabling module power and clock; may sleep
  * @get_direction: returns direction for signal "offset", 0=out, 1=in,
  *	(same as GPIO_LINE_DIRECTION_OUT / GPIO_LINE_DIRECTION_IN),
  *	or negative error. It is recommended to always implement this
  *	function, even on input-only or output-only gpio chips.
- * @direction_input: configures signal "offset" as input, or returns error
- *	This can be omitted on input-only or output-only gpio chips.
- * @direction_output: configures signal "offset" as output, or returns error
- *	This can be omitted on input-only or output-only gpio chips.
+ * @direction_input: configures signal "offset" as input, returns 0 on success
+ *	or a negative error number. This can be omitted on input-only or
+ *	output-only gpio chips.
+ * @direction_output: configures signal "offset" as output, returns 0 on
+ *	success or a negative error number. This can be omitted on input-only
+ *	or output-only gpio chips.
  * @get: returns value for signal "offset", 0=low, 1=high, or negative error
  * @get_multiple: reads values for multiple signals defined by "mask" and
  *	stores them in "bits", returns 0 on success or negative error
- * @set: assigns output value for signal "offset"
- * @set_multiple: assigns output values for multiple signals defined by "mask"
+ * @set: assigns output value for signal "offset", returns 0 on success or
+ *       negative error value
+ * @set_multiple: assigns output values for multiple signals defined by
+ *                "mask", returns 0 on success or negative error value
  * @set_config: optional hook for all kinds of settings. Uses the same
- *	packed config format as generic pinconf.
+ *	packed config format as generic pinconf. Must return 0 on success and
+ *	a negative error number on failure.
  * @to_irq: optional hook supporting non-static gpiod_to_irq() mappings;
  *	implementation may not sleep
  * @dbg_show: optional routine to show contents in debugfs; default code
@@ -371,35 +382,12 @@ struct gpio_irq_chip {
  * @names: if set, must be an array of strings to use as alternative
  *      names for the GPIOs in this chip. Any entry in the array
  *      may be NULL if there is no alias for the GPIO, however the
- *      array must be @ngpio entries long.  A name can include a single printk
- *      format specifier for an unsigned int.  It is substituted by the actual
- *      number of the gpio.
+ *      array must be @ngpio entries long.
  * @can_sleep: flag must be set iff get()/set() methods sleep, as they
  *	must while accessing GPIO expander chips over I2C or SPI. This
  *	implies that if the chip supports IRQs, these IRQs need to be threaded
  *	as the chip access may sleep when e.g. reading out the IRQ status
  *	registers.
- * @read_reg: reader function for generic GPIO
- * @write_reg: writer function for generic GPIO
- * @be_bits: if the generic GPIO has big endian bit order (bit 31 is representing
- *	line 0, bit 30 is line 1 ... bit 0 is line 31) this is set to true by the
- *	generic GPIO core. It is for internal housekeeping only.
- * @reg_dat: data (in) register for generic GPIO
- * @reg_set: output set register (out=high) for generic GPIO
- * @reg_clr: output clear register (out=low) for generic GPIO
- * @reg_dir_out: direction out setting register for generic GPIO
- * @reg_dir_in: direction in setting register for generic GPIO
- * @bgpio_dir_unreadable: indicates that the direction register(s) cannot
- *	be read and we need to rely on out internal state tracking.
- * @bgpio_bits: number of register bits used for a generic GPIO i.e.
- *	<register width> * 8
- * @bgpio_lock: used to lock chip->bgpio_data. Also, this is needed to keep
- *	shadowed and real data registers writes together.
- * @bgpio_data:	shadowed data register for generic GPIO to clear/set bits
- *	safely.
- * @bgpio_dir: shadowed direction register for generic GPIO to clear/set
- *	direction safely. A "1" in this word means the line is set as
- *	output.
  *
  * A gpio_chip can help platforms abstract various sources of GPIOs so
  * they can all be accessed through a common programming interface.
@@ -433,9 +421,9 @@ struct gpio_chip {
 	int			(*get_multiple)(struct gpio_chip *gc,
 						unsigned long *mask,
 						unsigned long *bits);
-	void			(*set)(struct gpio_chip *gc,
-						unsigned int offset, int value);
-	void			(*set_multiple)(struct gpio_chip *gc,
+	int			(*set)(struct gpio_chip *gc,
+				       unsigned int offset, int value);
+	int			(*set_multiple)(struct gpio_chip *gc,
 						unsigned long *mask,
 						unsigned long *bits);
 	int			(*set_config)(struct gpio_chip *gc,
@@ -465,22 +453,6 @@ struct gpio_chip {
 	const char		*const *names;
 	bool			can_sleep;
 
-#if IS_ENABLED(CONFIG_GPIO_GENERIC)
-	unsigned long (*read_reg)(void __iomem *reg);
-	void (*write_reg)(void __iomem *reg, unsigned long data);
-	bool be_bits;
-	void __iomem *reg_dat;
-	void __iomem *reg_set;
-	void __iomem *reg_clr;
-	void __iomem *reg_dir_out;
-	void __iomem *reg_dir_in;
-	bool bgpio_dir_unreadable;
-	int bgpio_bits;
-	raw_spinlock_t bgpio_lock;
-	unsigned long bgpio_data;
-	unsigned long bgpio_dir;
-#endif /* CONFIG_GPIO_GENERIC */
-
 #ifdef CONFIG_GPIOLIB_IRQCHIP
 	/*
 	 * With CONFIG_GPIOLIB_IRQCHIP we get an irqchip inside the gpiolib
@@ -496,14 +468,6 @@ struct gpio_chip {
 	struct gpio_irq_chip irq;
 #endif /* CONFIG_GPIOLIB_IRQCHIP */
 
-	/**
-	 * @valid_mask:
-	 *
-	 * If not %NULL, holds bitmask of GPIOs which are valid to be used
-	 * from the chip.
-	 */
-	unsigned long *valid_mask;
-
 #if defined(CONFIG_OF_GPIO)
 	/*
 	 * If CONFIG_OF_GPIO is enabled, then all GPIO controllers described in
@@ -513,11 +477,33 @@ struct gpio_chip {
 	/**
 	 * @of_gpio_n_cells:
 	 *
-	 * Number of cells used to form the GPIO specifier.
+	 * Number of cells used to form the GPIO specifier. The standard is 2
+	 * cells:
+	 *
+	 * gpios = <&gpio offset flags>;
+	 *
+	 * some complex GPIO controllers instantiate more than one chip per
+	 * device tree node and have 3 cells:
+	 *
+	 * gpios = <&gpio instance offset flags>;
+	 *
+	 * Legacy GPIO controllers may even have 1 cell:
+	 *
+	 * gpios = <&gpio offset>;
 	 */
 	unsigned int of_gpio_n_cells;
 
 	/**
+	 * @of_node_instance_match:
+	 *
+	 * Determine if a chip is the right instance. Must be implemented by
+	 * any driver using more than one gpio_chip per device tree node.
+	 * Returns true if gc is the instance indicated by i (which is the
+	 * first cell in the phandles for GPIO lines and gpio-ranges).
+	 */
+	bool (*of_node_instance_match)(struct gpio_chip *gc, unsigned int i);
+
+	/**
 	 * @of_xlate:
 	 *
 	 * Callback to translate a device tree GPIO specifier into a chip-
@@ -528,29 +514,69 @@ struct gpio_chip {
 #endif /* CONFIG_OF_GPIO */
 };
 
-extern const char *gpiochip_is_requested(struct gpio_chip *gc,
-			unsigned int offset);
+char *gpiochip_dup_line_label(struct gpio_chip *gc, unsigned int offset);
+
+
+struct _gpiochip_for_each_data {
+	const char **label;
+	unsigned int *i;
+};
+
+DEFINE_CLASS(_gpiochip_for_each_data,
+	     struct _gpiochip_for_each_data,
+	     if (*_T.label) kfree(*_T.label),
+	     ({
+		struct _gpiochip_for_each_data _data = { label, i };
+		*_data.i = 0;
+		_data;
+	     }),
+	     const char **label, int *i)
+
+/**
+ * for_each_hwgpio_in_range - Iterates over all GPIOs in a given range
+ * @_chip: Chip to iterate over.
+ * @_i: Loop counter.
+ * @_base: First GPIO in the ranger.
+ * @_size: Amount of GPIOs to check starting from @base.
+ * @_label: Place to store the address of the label if the GPIO is requested.
+ *          Set to NULL for unused GPIOs.
+ */
+#define for_each_hwgpio_in_range(_chip, _i, _base, _size, _label)			\
+	for (CLASS(_gpiochip_for_each_data, _data)(&_label, &_i);			\
+	     _i < _size;								\
+	     _i++, kfree(_label), _label = NULL)					\
+		for_each_if(!IS_ERR(_label = gpiochip_dup_line_label(_chip, _base + _i)))
+
+/**
+ * for_each_hwgpio - Iterates over all GPIOs for given chip.
+ * @_chip: Chip to iterate over.
+ * @_i: Loop counter.
+ * @_label: Place to store the address of the label if the GPIO is requested.
+ *          Set to NULL for unused GPIOs.
+ */
+#define for_each_hwgpio(_chip, _i, _label)						\
+	for_each_hwgpio_in_range(_chip, _i, 0, _chip->ngpio, _label)
 
 /**
  * for_each_requested_gpio_in_range - iterates over requested GPIOs in a given range
- * @chip:	the chip to query
- * @i:		loop variable
- * @base:	first GPIO in the range
- * @size:	amount of GPIOs to check starting from @base
- * @label:	label of current GPIO
+ * @_chip:	the chip to query
+ * @_i:		loop variable
+ * @_base:	first GPIO in the range
+ * @_size:	amount of GPIOs to check starting from @base
+ * @_label:	label of current GPIO
  */
-#define for_each_requested_gpio_in_range(chip, i, base, size, label)			\
-	for (i = 0; i < size; i++)							\
-		if ((label = gpiochip_is_requested(chip, base + i)) == NULL) {} else
+#define for_each_requested_gpio_in_range(_chip, _i, _base, _size, _label)		\
+	for_each_hwgpio_in_range(_chip, _i, _base, _size, _label)			\
+		for_each_if(_label)
 
 /* Iterates over all requested GPIO of the given @chip */
 #define for_each_requested_gpio(chip, i, label)						\
 	for_each_requested_gpio_in_range(chip, i, 0, chip->ngpio, label)
 
 /* add/remove chips */
-extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
-				      struct lock_class_key *lock_key,
-				      struct lock_class_key *request_key);
+int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
+			       struct lock_class_key *lock_key,
+			       struct lock_class_key *request_key);
 
 /**
  * gpiochip_add_data() - register a gpio_chip
@@ -594,17 +620,22 @@ extern int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 	devm_gpiochip_add_data_with_key(dev, gc, data, NULL, NULL)
 #endif /* CONFIG_LOCKDEP */
 
-static inline int gpiochip_add(struct gpio_chip *gc)
-{
-	return gpiochip_add_data(gc, NULL);
-}
-extern void gpiochip_remove(struct gpio_chip *gc);
-extern int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc, void *data,
-					   struct lock_class_key *lock_key,
-					   struct lock_class_key *request_key);
+void gpiochip_remove(struct gpio_chip *gc);
+int devm_gpiochip_add_data_with_key(struct device *dev, struct gpio_chip *gc,
+				    void *data, struct lock_class_key *lock_key,
+				    struct lock_class_key *request_key);
+
+struct gpio_device *gpio_device_find(const void *data,
+				int (*match)(struct gpio_chip *gc,
+					     const void *data));
+
+struct gpio_device *gpio_device_get(struct gpio_device *gdev);
+void gpio_device_put(struct gpio_device *gdev);
 
-extern struct gpio_chip *gpiochip_find(void *data,
-			      int (*match)(struct gpio_chip *gc, void *data));
+DEFINE_FREE(gpio_device_put, struct gpio_device *,
+	    if (!IS_ERR_OR_NULL(_T)) gpio_device_put(_T))
+
+struct device *gpio_device_to_device(struct gpio_device *gdev);
 
 bool gpiochip_line_is_irq(struct gpio_chip *gc, unsigned int offset);
 int gpiochip_reqres_irq(struct gpio_chip *gc, unsigned int offset);
@@ -635,16 +666,11 @@ bool gpiochip_line_is_open_source(struct gpio_chip *gc, unsigned int offset);
 /* Sleep persistence inquiry for drivers */
 bool gpiochip_line_is_persistent(struct gpio_chip *gc, unsigned int offset);
 bool gpiochip_line_is_valid(const struct gpio_chip *gc, unsigned int offset);
+const unsigned long *gpiochip_query_valid_mask(const struct gpio_chip *gc);
 
 /* get driver data */
 void *gpiochip_get_data(struct gpio_chip *gc);
 
-struct bgpio_pdata {
-	const char *label;
-	int base;
-	int ngpio;
-};
-
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 
 int gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *gc,
@@ -658,38 +684,12 @@ int gpiochip_populate_parent_fwspec_fourcell(struct gpio_chip *gc,
 
 #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
-int bgpio_init(struct gpio_chip *gc, struct device *dev,
-	       unsigned long sz, void __iomem *dat, void __iomem *set,
-	       void __iomem *clr, void __iomem *dirout, void __iomem *dirin,
-	       unsigned long flags);
-
-#define BGPIOF_BIG_ENDIAN		BIT(0)
-#define BGPIOF_UNREADABLE_REG_SET	BIT(1) /* reg_set is unreadable */
-#define BGPIOF_UNREADABLE_REG_DIR	BIT(2) /* reg_dir is unreadable */
-#define BGPIOF_BIG_ENDIAN_BYTE_ORDER	BIT(3)
-#define BGPIOF_READ_OUTPUT_REG_SET	BIT(4) /* reg_set stores output value */
-#define BGPIOF_NO_OUTPUT		BIT(5) /* only input */
-#define BGPIOF_NO_SET_ON_INPUT		BIT(6)
-
-int gpiochip_irq_map(struct irq_domain *d, unsigned int irq,
-		     irq_hw_number_t hwirq);
-void gpiochip_irq_unmap(struct irq_domain *d, unsigned int irq);
-
-int gpiochip_irq_domain_activate(struct irq_domain *domain,
-				 struct irq_data *data, bool reserve);
-void gpiochip_irq_domain_deactivate(struct irq_domain *domain,
-				    struct irq_data *data);
-
-bool gpiochip_irqchip_irq_valid(const struct gpio_chip *gc,
-				unsigned int offset);
-
 #ifdef CONFIG_GPIOLIB_IRQCHIP
 int gpiochip_irqchip_add_domain(struct gpio_chip *gc,
 				struct irq_domain *domain);
 #else
 
 #include <asm/bug.h>
-#include <asm/errno.h>
 
 static inline int gpiochip_irqchip_add_domain(struct gpio_chip *gc,
 					      struct irq_domain *domain)
@@ -718,23 +718,68 @@ struct gpio_pin_range {
 
 #ifdef CONFIG_PINCTRL
 
-int gpiochip_add_pin_range(struct gpio_chip *gc, const char *pinctl_name,
-			   unsigned int gpio_offset, unsigned int pin_offset,
-			   unsigned int npins);
+int gpiochip_add_pin_range_with_pins(struct gpio_chip *gc,
+				     const char *pinctl_name,
+				     unsigned int gpio_offset,
+				     unsigned int pin_offset,
+				     unsigned int const *pins,
+				     unsigned int npins);
 int gpiochip_add_pingroup_range(struct gpio_chip *gc,
 			struct pinctrl_dev *pctldev,
 			unsigned int gpio_offset, const char *pin_group);
 void gpiochip_remove_pin_ranges(struct gpio_chip *gc);
 
+static inline int
+gpiochip_add_pin_range(struct gpio_chip *gc,
+		       const char *pinctl_name,
+		       unsigned int gpio_offset,
+		       unsigned int pin_offset,
+		       unsigned int npins)
+{
+	return gpiochip_add_pin_range_with_pins(gc, pinctl_name, gpio_offset,
+						pin_offset, NULL, npins);
+}
+
+static inline int
+gpiochip_add_sparse_pin_range(struct gpio_chip *gc,
+			      const char *pinctl_name,
+			      unsigned int gpio_offset,
+			      unsigned int const *pins,
+			      unsigned int npins)
+{
+	return gpiochip_add_pin_range_with_pins(gc, pinctl_name, gpio_offset, 0,
+						pins, npins);
+}
 #else /* ! CONFIG_PINCTRL */
 
 static inline int
+gpiochip_add_pin_range_with_pins(struct gpio_chip *gc,
+				 const char *pinctl_name,
+				 unsigned int gpio_offset,
+				 unsigned int pin_offset,
+				 unsigned int npins)
+{
+	return 0;
+}
+
+static inline int
 gpiochip_add_pin_range(struct gpio_chip *gc, const char *pinctl_name,
 		       unsigned int gpio_offset, unsigned int pin_offset,
 		       unsigned int npins)
 {
 	return 0;
 }
+
+static inline int
+gpiochip_add_sparse_pin_range(struct gpio_chip *gc,
+			      const char *pinctl_name,
+			      unsigned int gpio_offset,
+			      unsigned int const *pins,
+			      unsigned int npins)
+{
+	return 0;
+}
+
 static inline int
 gpiochip_add_pingroup_range(struct gpio_chip *gc,
 			struct pinctrl_dev *pctldev,
@@ -757,18 +802,28 @@ struct gpio_desc *gpiochip_request_own_desc(struct gpio_chip *gc,
 					    enum gpiod_flags dflags);
 void gpiochip_free_own_desc(struct gpio_desc *desc);
 
+struct gpio_desc *
+gpio_device_get_desc(struct gpio_device *gdev, unsigned int hwnum);
+
+struct gpio_chip *gpio_device_get_chip(struct gpio_device *gdev);
+
 #ifdef CONFIG_GPIOLIB
 
 /* lock/unlock as IRQ */
 int gpiochip_lock_as_irq(struct gpio_chip *gc, unsigned int offset);
 void gpiochip_unlock_as_irq(struct gpio_chip *gc, unsigned int offset);
 
-
 struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc);
+struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc);
 
-#else /* CONFIG_GPIOLIB */
+/* struct gpio_device getters */
+int gpio_device_get_base(struct gpio_device *gdev);
+const char *gpio_device_get_label(struct gpio_device *gdev);
 
-#include <linux/err.h>
+struct gpio_device *gpio_device_find_by_label(const char *label);
+struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode);
+
+#else /* CONFIG_GPIOLIB */
 
 #include <asm/bug.h>
 
@@ -779,6 +834,36 @@ static inline struct gpio_chip *gpiod_to_chip(const struct gpio_desc *desc)
 	return ERR_PTR(-ENODEV);
 }
 
+static inline struct gpio_device *gpiod_to_gpio_device(struct gpio_desc *desc)
+{
+	WARN_ON(1);
+	return ERR_PTR(-ENODEV);
+}
+
+static inline int gpio_device_get_base(struct gpio_device *gdev)
+{
+	WARN_ON(1);
+	return -ENODEV;
+}
+
+static inline const char *gpio_device_get_label(struct gpio_device *gdev)
+{
+	WARN_ON(1);
+	return NULL;
+}
+
+static inline struct gpio_device *gpio_device_find_by_label(const char *label)
+{
+	WARN_ON(1);
+	return NULL;
+}
+
+static inline struct gpio_device *gpio_device_find_by_fwnode(const struct fwnode_handle *fwnode)
+{
+	WARN_ON(1);
+	return NULL;
+}
+
 static inline int gpiochip_lock_as_irq(struct gpio_chip *gc,
 				       unsigned int offset)
 {
@@ -795,7 +880,7 @@ static inline void gpiochip_unlock_as_irq(struct gpio_chip *gc,
 
 #define for_each_gpiochip_node(dev, child)					\
 	device_for_each_child_node(dev, child)					\
-		if (!fwnode_property_present(child, "gpio-controller")) {} else
+		for_each_if(fwnode_property_present(child, "gpio-controller"))
 
 static inline unsigned int gpiochip_node_count(struct device *dev)
 {
diff --git a/include/linux/gpio/forwarder.h b/include/linux/gpio/forwarder.h
new file mode 100644
index 000000000000..ee5d8355f735
--- /dev/null
+++ b/include/linux/gpio/forwarder.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_GPIO_FORWARDER_H
+#define __LINUX_GPIO_FORWARDER_H
+
+struct gpio_desc;
+struct gpio_chip;
+struct gpiochip_fwd;
+
+struct gpiochip_fwd *devm_gpiochip_fwd_alloc(struct device *dev,
+					     unsigned int ngpios);
+int gpiochip_fwd_desc_add(struct gpiochip_fwd *fwd,
+			  struct gpio_desc *desc, unsigned int offset);
+void gpiochip_fwd_desc_free(struct gpiochip_fwd *fwd, unsigned int offset);
+int gpiochip_fwd_register(struct gpiochip_fwd *fwd, void *data);
+
+struct gpio_chip *gpiochip_fwd_get_gpiochip(struct gpiochip_fwd *fwd);
+
+void *gpiochip_fwd_get_data(struct gpiochip_fwd *fwd);
+
+int gpiochip_fwd_gpio_request(struct gpiochip_fwd *fwd, unsigned int offset);
+int gpiochip_fwd_gpio_get_direction(struct gpiochip_fwd *fwd,
+				    unsigned int offset);
+int gpiochip_fwd_gpio_direction_input(struct gpiochip_fwd *fwd,
+				      unsigned int offset);
+int gpiochip_fwd_gpio_direction_output(struct gpiochip_fwd *fwd,
+				       unsigned int offset,
+				       int value);
+int gpiochip_fwd_gpio_get(struct gpiochip_fwd *fwd, unsigned int offset);
+int gpiochip_fwd_gpio_get_multiple(struct gpiochip_fwd *fwd,
+				   unsigned long *mask,
+				   unsigned long *bits);
+int gpiochip_fwd_gpio_set(struct gpiochip_fwd *fwd, unsigned int offset,
+			  int value);
+int gpiochip_fwd_gpio_set_multiple(struct gpiochip_fwd *fwd,
+				   unsigned long *mask,
+				   unsigned long *bits);
+int gpiochip_fwd_gpio_set_config(struct gpiochip_fwd *fwd, unsigned int offset,
+				 unsigned long config);
+int gpiochip_fwd_gpio_to_irq(struct gpiochip_fwd *fwd, unsigned int offset);
+
+#endif
diff --git a/include/linux/gpio/generic.h b/include/linux/gpio/generic.h
new file mode 100644
index 000000000000..ff566dc9c3cb
--- /dev/null
+++ b/include/linux/gpio/generic.h
@@ -0,0 +1,190 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LINUX_GPIO_GENERIC_H
+#define __LINUX_GPIO_GENERIC_H
+
+#include <linux/cleanup.h>
+#include <linux/gpio/driver.h>
+#include <linux/spinlock.h>
+
+struct device;
+
+#define GPIO_GENERIC_BIG_ENDIAN			BIT(0)
+#define GPIO_GENERIC_UNREADABLE_REG_SET		BIT(1) /* reg_set is unreadable */
+#define GPIO_GENERIC_UNREADABLE_REG_DIR		BIT(2) /* reg_dir is unreadable */
+#define GPIO_GENERIC_BIG_ENDIAN_BYTE_ORDER	BIT(3)
+#define GPIO_GENERIC_READ_OUTPUT_REG_SET	BIT(4) /* reg_set stores output value */
+#define GPIO_GENERIC_NO_OUTPUT			BIT(5) /* only input */
+#define GPIO_GENERIC_NO_SET_ON_INPUT		BIT(6)
+#define GPIO_GENERIC_PINCTRL_BACKEND		BIT(7) /* Call pinctrl direction setters */
+#define GPIO_GENERIC_NO_INPUT			BIT(8) /* only output */
+
+/**
+ * struct gpio_generic_chip_config - Generic GPIO chip configuration data
+ * @dev: Parent device of the new GPIO chip (compulsory).
+ * @sz: Size (width) of the MMIO registers in bytes, typically 1, 2 or 4.
+ * @dat: MMIO address for the register to READ the value of the GPIO lines, it
+ *       is expected that a 1 in the corresponding bit in this register means
+ *       the line is asserted.
+ * @set: MMIO address for the register to SET the value of the GPIO lines, it
+ *       is expected that we write the line with 1 in this register to drive
+ *       the GPIO line high.
+ * @clr: MMIO address for the register to CLEAR the value of the GPIO lines,
+ *       it is expected that we write the line with 1 in this register to
+ *       drive the GPIO line low. It is allowed to leave this address as NULL,
+ *       in that case the SET register will be assumed to also clear the GPIO
+ *       lines, by actively writing the line with 0.
+ * @dirout: MMIO address for the register to set the line as OUTPUT. It is
+ *          assumed that setting a line to 1 in this register will turn that
+ *          line into an output line. Conversely, setting the line to 0 will
+ *          turn that line into an input.
+ * @dirin: MMIO address for the register to set this line as INPUT. It is
+ *         assumed that setting a line to 1 in this register will turn that
+ *         line into an input line. Conversely, setting the line to 0 will
+ *         turn that line into an output.
+ * @flags: Different flags that will affect the behaviour of the device, such
+ *         as endianness etc.
+ */
+struct gpio_generic_chip_config {
+	struct device *dev;
+	unsigned long sz;
+	void __iomem *dat;
+	void __iomem *set;
+	void __iomem *clr;
+	void __iomem *dirout;
+	void __iomem *dirin;
+	unsigned long flags;
+};
+
+/**
+ * struct gpio_generic_chip - Generic GPIO chip implementation.
+ * @gc: The underlying struct gpio_chip object, implementing low-level GPIO
+ *      chip routines.
+ * @read_reg: reader function for generic GPIO
+ * @write_reg: writer function for generic GPIO
+ * @be_bits: if the generic GPIO has big endian bit order (bit 31 is
+ *           representing line 0, bit 30 is line 1 ... bit 0 is line 31) this
+ *           is set to true by the generic GPIO core. It is for internal
+ *           housekeeping only.
+ * @reg_dat: data (in) register for generic GPIO
+ * @reg_set: output set register (out=high) for generic GPIO
+ * @reg_clr: output clear register (out=low) for generic GPIO
+ * @reg_dir_out: direction out setting register for generic GPIO
+ * @reg_dir_in: direction in setting register for generic GPIO
+ * @dir_unreadable: indicates that the direction register(s) cannot be read and
+ *                  we need to rely on out internal state tracking.
+ * @pinctrl: the generic GPIO uses a pin control backend.
+ * @bits: number of register bits used for a generic GPIO
+ *        i.e. <register width> * 8
+ * @lock: used to lock chip->sdata. Also, this is needed to keep
+ *        shadowed and real data registers writes together.
+ * @sdata: shadowed data register for generic GPIO to clear/set bits safely.
+ * @sdir: shadowed direction register for generic GPIO to clear/set direction
+ *        safely. A "1" in this word means the line is set as output.
+ */
+struct gpio_generic_chip {
+	struct gpio_chip gc;
+	unsigned long (*read_reg)(void __iomem *reg);
+	void (*write_reg)(void __iomem *reg, unsigned long data);
+	bool be_bits;
+	void __iomem *reg_dat;
+	void __iomem *reg_set;
+	void __iomem *reg_clr;
+	void __iomem *reg_dir_out;
+	void __iomem *reg_dir_in;
+	bool dir_unreadable;
+	bool pinctrl;
+	int bits;
+	raw_spinlock_t lock;
+	unsigned long sdata;
+	unsigned long sdir;
+};
+
+static inline struct gpio_generic_chip *
+to_gpio_generic_chip(struct gpio_chip *gc)
+{
+	return container_of(gc, struct gpio_generic_chip, gc);
+}
+
+int gpio_generic_chip_init(struct gpio_generic_chip *chip,
+			   const struct gpio_generic_chip_config *cfg);
+
+/**
+ * gpio_generic_chip_set() - Set the GPIO line value of the generic GPIO chip.
+ * @chip: Generic GPIO chip to use.
+ * @offset: Hardware offset of the line to set.
+ * @value: New GPIO line value.
+ *
+ * Some modules using the generic GPIO chip, need to set line values in their
+ * direction setters but they don't have access to the gpio-mmio symbols so
+ * they use the function pointer in struct gpio_chip directly. This is not
+ * optimal and can lead to crashes at run-time in some instances. This wrapper
+ * provides a safe interface for users.
+ *
+ * Returns: 0 on success, negative error number of failure.
+ */
+static inline int
+gpio_generic_chip_set(struct gpio_generic_chip *chip, unsigned int offset,
+		      int value)
+{
+	if (WARN_ON(!chip->gc.set))
+		return -EOPNOTSUPP;
+
+	return chip->gc.set(&chip->gc, offset, value);
+}
+
+/**
+ * gpio_generic_read_reg() - Read a register using the underlying callback.
+ * @chip: Generic GPIO chip to use.
+ * @reg: Register to read.
+ *
+ * Returns: value read from register.
+ */
+static inline unsigned long
+gpio_generic_read_reg(struct gpio_generic_chip *chip, void __iomem *reg)
+{
+	if (WARN_ON(!chip->read_reg))
+		return 0;
+
+	return chip->read_reg(reg);
+}
+
+/**
+ * gpio_generic_write_reg() - Write a register using the underlying callback.
+ * @chip: Generic GPIO chip to use.
+ * @reg: Register to write to.
+ * @val: New value to write.
+ */
+static inline void gpio_generic_write_reg(struct gpio_generic_chip *chip,
+					  void __iomem *reg, unsigned long val)
+{
+	if (WARN_ON(!chip->write_reg))
+		return;
+
+	chip->write_reg(reg, val);
+}
+
+#define gpio_generic_chip_lock(gen_gc) \
+	raw_spin_lock(&(gen_gc)->lock)
+
+#define gpio_generic_chip_unlock(gen_gc) \
+	raw_spin_unlock(&(gen_gc)->lock)
+
+#define gpio_generic_chip_lock_irqsave(gen_gc, flags) \
+	raw_spin_lock_irqsave(&(gen_gc)->lock, flags)
+
+#define gpio_generic_chip_unlock_irqrestore(gen_gc, flags) \
+	raw_spin_unlock_irqrestore(&(gen_gc)->lock, flags)
+
+DEFINE_LOCK_GUARD_1(gpio_generic_lock,
+		    struct gpio_generic_chip,
+		    gpio_generic_chip_lock(_T->lock),
+		    gpio_generic_chip_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(gpio_generic_lock_irqsave,
+		    struct gpio_generic_chip,
+		    gpio_generic_chip_lock_irqsave(_T->lock, _T->flags),
+		    gpio_generic_chip_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+#endif /* __LINUX_GPIO_GENERIC_H */
diff --git a/include/linux/gpio/gpio-nomadik.h b/include/linux/gpio/gpio-nomadik.h
new file mode 100644
index 000000000000..592a774a53cd
--- /dev/null
+++ b/include/linux/gpio/gpio-nomadik.h
@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_GPIO_NOMADIK_H
+#define __LINUX_GPIO_NOMADIK_H
+
+struct fwnode_handle;
+
+/* Package definitions */
+#define PINCTRL_NMK_STN8815	0
+#define PINCTRL_NMK_DB8500	1
+
+#define GPIO_BLOCK_SHIFT 5
+#define NMK_GPIO_PER_CHIP BIT(GPIO_BLOCK_SHIFT)
+#define NMK_MAX_BANKS DIV_ROUND_UP(512, NMK_GPIO_PER_CHIP)
+
+/* Register in the logic block */
+#define NMK_GPIO_DAT	0x00
+#define NMK_GPIO_DATS	0x04
+#define NMK_GPIO_DATC	0x08
+#define NMK_GPIO_PDIS	0x0c
+#define NMK_GPIO_DIR	0x10
+#define NMK_GPIO_DIRS	0x14
+#define NMK_GPIO_DIRC	0x18
+#define NMK_GPIO_SLPC	0x1c
+#define NMK_GPIO_AFSLA	0x20
+#define NMK_GPIO_AFSLB	0x24
+#define NMK_GPIO_LOWEMI	0x28
+
+#define NMK_GPIO_RIMSC	0x40
+#define NMK_GPIO_FIMSC	0x44
+#define NMK_GPIO_IS	0x48
+#define NMK_GPIO_IC	0x4c
+#define NMK_GPIO_RWIMSC	0x50
+#define NMK_GPIO_FWIMSC	0x54
+#define NMK_GPIO_WKS	0x58
+/* These appear in DB8540 and later ASICs */
+#define NMK_GPIO_EDGELEVEL 0x5C
+#define NMK_GPIO_LEVEL	0x60
+
+/* Pull up/down values */
+enum nmk_gpio_pull {
+	NMK_GPIO_PULL_NONE,
+	NMK_GPIO_PULL_UP,
+	NMK_GPIO_PULL_DOWN,
+};
+
+/* Sleep mode */
+enum nmk_gpio_slpm {
+	NMK_GPIO_SLPM_INPUT,
+	NMK_GPIO_SLPM_WAKEUP_ENABLE = NMK_GPIO_SLPM_INPUT,
+	NMK_GPIO_SLPM_NOCHANGE,
+	NMK_GPIO_SLPM_WAKEUP_DISABLE = NMK_GPIO_SLPM_NOCHANGE,
+};
+
+struct nmk_gpio_chip {
+	struct gpio_chip chip;
+	void __iomem *addr;
+	struct clk *clk;
+	unsigned int bank;
+	void (*set_ioforce)(bool enable);
+	spinlock_t lock;
+	bool sleepmode;
+	bool is_mobileye_soc;
+	/* Keep track of configured edges */
+	u32 edge_rising;
+	u32 edge_falling;
+	u32 real_wake;
+	u32 rwimsc;
+	u32 fwimsc;
+	u32 rimsc;
+	u32 fimsc;
+	u32 pull_up;
+	u32 lowemi;
+};
+
+/* Alternate functions: function C is set in hw by setting both A and B */
+#define NMK_GPIO_ALT_GPIO	0
+#define NMK_GPIO_ALT_A	1
+#define NMK_GPIO_ALT_B	2
+#define NMK_GPIO_ALT_C	(NMK_GPIO_ALT_A | NMK_GPIO_ALT_B)
+
+#define NMK_GPIO_ALT_CX_SHIFT 2
+#define NMK_GPIO_ALT_C1	((1<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+#define NMK_GPIO_ALT_C2	((2<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+#define NMK_GPIO_ALT_C3	((3<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+#define NMK_GPIO_ALT_C4	((4<<NMK_GPIO_ALT_CX_SHIFT) | NMK_GPIO_ALT_C)
+
+#define PRCM_GPIOCR_ALTCX(pin_num,\
+	altc1_used, altc1_ri, altc1_cb,\
+	altc2_used, altc2_ri, altc2_cb,\
+	altc3_used, altc3_ri, altc3_cb,\
+	altc4_used, altc4_ri, altc4_cb)\
+{\
+	.pin = pin_num,\
+	.altcx[PRCM_IDX_GPIOCR_ALTC1] = {\
+		.used = altc1_used,\
+		.reg_index = altc1_ri,\
+		.control_bit = altc1_cb\
+	},\
+	.altcx[PRCM_IDX_GPIOCR_ALTC2] = {\
+		.used = altc2_used,\
+		.reg_index = altc2_ri,\
+		.control_bit = altc2_cb\
+	},\
+	.altcx[PRCM_IDX_GPIOCR_ALTC3] = {\
+		.used = altc3_used,\
+		.reg_index = altc3_ri,\
+		.control_bit = altc3_cb\
+	},\
+	.altcx[PRCM_IDX_GPIOCR_ALTC4] = {\
+		.used = altc4_used,\
+		.reg_index = altc4_ri,\
+		.control_bit = altc4_cb\
+	},\
+}
+
+/**
+ * enum prcm_gpiocr_reg_index
+ * Used to reference an PRCM GPIOCR register address.
+ */
+enum prcm_gpiocr_reg_index {
+	PRCM_IDX_GPIOCR1,
+	PRCM_IDX_GPIOCR2,
+	PRCM_IDX_GPIOCR3
+};
+/**
+ * enum prcm_gpiocr_altcx_index
+ * Used to reference an Other alternate-C function.
+ */
+enum prcm_gpiocr_altcx_index {
+	PRCM_IDX_GPIOCR_ALTC1,
+	PRCM_IDX_GPIOCR_ALTC2,
+	PRCM_IDX_GPIOCR_ALTC3,
+	PRCM_IDX_GPIOCR_ALTC4,
+	PRCM_IDX_GPIOCR_ALTC_MAX,
+};
+
+/**
+ * struct prcm_gpio_altcx - Other alternate-C function
+ * @used: other alternate-C function availability
+ * @reg_index: PRCM GPIOCR register index used to control the function
+ * @control_bit: PRCM GPIOCR bit used to control the function
+ */
+struct prcm_gpiocr_altcx {
+	bool used:1;
+	u8 reg_index:2;
+	u8 control_bit:5;
+} __packed;
+
+/**
+ * struct prcm_gpio_altcx_pin_desc - Other alternate-C pin
+ * @pin: The pin number
+ * @altcx: array of other alternate-C[1-4] functions
+ */
+struct prcm_gpiocr_altcx_pin_desc {
+	unsigned short pin;
+	struct prcm_gpiocr_altcx altcx[PRCM_IDX_GPIOCR_ALTC_MAX];
+};
+
+/**
+ * struct nmk_function - Nomadik pinctrl mux function
+ * @name: The name of the function, exported to pinctrl core.
+ * @groups: An array of pin groups that may select this function.
+ * @ngroups: The number of entries in @groups.
+ */
+struct nmk_function {
+	const char *name;
+	const char * const *groups;
+	unsigned int ngroups;
+};
+
+/**
+ * struct nmk_pingroup - describes a Nomadik pin group
+ * @grp: Generic data of the pin group (name and pins)
+ * @altsetting: the altsetting to apply to all pins in this group to
+ *	configure them to be used by a function
+ */
+struct nmk_pingroup {
+	struct pingroup grp;
+	int altsetting;
+};
+
+#define NMK_PIN_GROUP(a, b)							\
+	{									\
+		.grp = PINCTRL_PINGROUP(#a, a##_pins, ARRAY_SIZE(a##_pins)),	\
+		.altsetting = b,						\
+	}
+
+/**
+ * struct nmk_pinctrl_soc_data - Nomadik pin controller per-SoC configuration
+ * @pins:	An array describing all pins the pin controller affects.
+ *		All pins which are also GPIOs must be listed first within the
+ *		array, and be numbered identically to the GPIO controller's
+ *		numbering.
+ * @npins:	The number of entries in @pins.
+ * @functions:	The functions supported on this SoC.
+ * @nfunction:	The number of entries in @functions.
+ * @groups:	An array describing all pin groups the pin SoC supports.
+ * @ngroups:	The number of entries in @groups.
+ * @altcx_pins:	The pins that support Other alternate-C function on this SoC
+ * @npins_altcx: The number of Other alternate-C pins
+ * @prcm_gpiocr_registers: The array of PRCM GPIOCR registers on this SoC
+ */
+struct nmk_pinctrl_soc_data {
+	const struct pinctrl_pin_desc *pins;
+	unsigned int npins;
+	const struct nmk_function *functions;
+	unsigned int nfunctions;
+	const struct nmk_pingroup *groups;
+	unsigned int ngroups;
+	const struct prcm_gpiocr_altcx_pin_desc *altcx_pins;
+	unsigned int npins_altcx;
+	const u16 *prcm_gpiocr_registers;
+};
+
+#ifdef CONFIG_PINCTRL_STN8815
+
+void nmk_pinctrl_stn8815_init(const struct nmk_pinctrl_soc_data **soc);
+
+#else
+
+static inline void
+nmk_pinctrl_stn8815_init(const struct nmk_pinctrl_soc_data **soc)
+{
+}
+
+#endif
+
+#ifdef CONFIG_PINCTRL_DB8500
+
+void nmk_pinctrl_db8500_init(const struct nmk_pinctrl_soc_data **soc);
+
+#else
+
+static inline void
+nmk_pinctrl_db8500_init(const struct nmk_pinctrl_soc_data **soc)
+{
+}
+
+#endif
+
+#ifdef CONFIG_PINCTRL_DB8540
+
+void nmk_pinctrl_db8540_init(const struct nmk_pinctrl_soc_data **soc);
+
+#else
+
+static inline void
+nmk_pinctrl_db8540_init(const struct nmk_pinctrl_soc_data **soc)
+{
+}
+
+#endif
+
+struct platform_device;
+
+#ifdef CONFIG_DEBUG_FS
+
+/*
+ * Symbols declared in gpio-nomadik used by pinctrl-nomadik. If pinctrl-nomadik
+ * is enabled, then gpio-nomadik is enabled as well; the reverse if not always
+ * true.
+ */
+void nmk_gpio_dbg_show_one(struct seq_file *s, struct pinctrl_dev *pctldev,
+			   struct gpio_chip *chip, unsigned int offset);
+
+#else
+
+static inline void nmk_gpio_dbg_show_one(struct seq_file *s,
+					 struct pinctrl_dev *pctldev,
+					 struct gpio_chip *chip,
+					 unsigned int offset)
+{
+}
+
+#endif
+
+void __nmk_gpio_make_output(struct nmk_gpio_chip *nmk_chip,
+			    unsigned int offset, int val);
+void __nmk_gpio_set_slpm(struct nmk_gpio_chip *nmk_chip, unsigned int offset,
+			 enum nmk_gpio_slpm mode);
+struct nmk_gpio_chip *nmk_gpio_populate_chip(struct fwnode_handle *fwnode,
+					     struct platform_device *pdev);
+
+/* Symbols declared in pinctrl-nomadik used by gpio-nomadik. */
+#ifdef CONFIG_PINCTRL_NOMADIK
+extern struct nmk_gpio_chip *nmk_gpio_chips[NMK_MAX_BANKS];
+extern spinlock_t nmk_gpio_slpm_lock;
+int __maybe_unused nmk_prcm_gpiocr_get_mode(struct pinctrl_dev *pctldev,
+					    int gpio);
+#endif
+
+#endif /* __LINUX_GPIO_NOMADIK_H */
diff --git a/include/linux/gpio/legacy-of-mm-gpiochip.h b/include/linux/gpio/legacy-of-mm-gpiochip.h
deleted file mode 100644
index 2e2bd3b19cc3..000000000000
--- a/include/linux/gpio/legacy-of-mm-gpiochip.h
+++ /dev/null
@@ -1,36 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-/*
- * OF helpers for the old of_mm_gpio_chip, used on ppc32 and nios2,
- * do not use in new code.
- *
- * Copyright (c) 2007-2008  MontaVista Software, Inc.
- *
- * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
- */
-
-#ifndef __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H
-#define __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H
-
-#include <linux/gpio/driver.h>
-#include <linux/of.h>
-
-/*
- * OF GPIO chip for memory mapped banks
- */
-struct of_mm_gpio_chip {
-	struct gpio_chip gc;
-	void (*save_regs)(struct of_mm_gpio_chip *mm_gc);
-	void __iomem *regs;
-};
-
-static inline struct of_mm_gpio_chip *to_of_mm_gpio_chip(struct gpio_chip *gc)
-{
-	return container_of(gc, struct of_mm_gpio_chip, gc);
-}
-
-extern int of_mm_gpiochip_add_data(struct device_node *np,
-				   struct of_mm_gpio_chip *mm_gc,
-				   void *data);
-extern void of_mm_gpiochip_remove(struct of_mm_gpio_chip *mm_gc);
-
-#endif /* __LINUX_GPIO_LEGACY_OF_MM_GPIO_CHIP_H */
diff --git a/include/linux/gpio/property.h b/include/linux/gpio/property.h
index 6c75c8bd44a0..0d2209308002 100644
--- a/include/linux/gpio/property.h
+++ b/include/linux/gpio/property.h
@@ -2,10 +2,13 @@
 #ifndef __LINUX_GPIO_PROPERTY_H
 #define __LINUX_GPIO_PROPERTY_H
 
-#include <dt-bindings/gpio/gpio.h> /* for GPIO_* flags */
 #include <linux/property.h>
 
+struct software_node;
+
 #define PROPERTY_ENTRY_GPIO(_name_, _chip_node_, _idx_, _flags_) \
 	PROPERTY_ENTRY_REF(_name_, _chip_node_, _idx_, _flags_)
 
+extern const struct software_node swnode_gpio_undefined;
+
 #endif /* __LINUX_GPIO_PROPERTY_H */
diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h
index a9f7b7faf57b..12d154732ca9 100644
--- a/include/linux/gpio/regmap.h
+++ b/include/linux/gpio/regmap.h
@@ -6,6 +6,7 @@
 struct device;
 struct fwnode_handle;
 struct gpio_regmap;
+struct gpio_chip;
 struct irq_domain;
 struct regmap;
 
@@ -21,7 +22,7 @@ struct regmap;
  *			If not given, the fwnode of the parent is used.
  * @label:		(Optional) Descriptive name for GPIO controller.
  *			If not given, the name of the device is used.
- * @ngpio:		Number of GPIOs
+ * @ngpio:		(Optional) Number of GPIOs
  * @names:		(Optional) Array of names for gpios
  * @reg_dat_base:	(Optional) (in) register base address
  * @reg_set_base:	(Optional) set register base address
@@ -30,16 +31,27 @@ struct regmap;
  * @reg_dir_out_base:	(Optional) out setting register base address
  * @reg_stride:		(Optional) May be set if the registers (of the
  *			same type, dat, set, etc) are not consecutive.
- * @ngpio_per_reg:	Number of GPIOs per register
+ * @ngpio_per_reg:	(Optional) Number of GPIOs per register
  * @irq_domain:		(Optional) IRQ domain if the controller is
  *			interrupt-capable
  * @reg_mask_xlate:     (Optional) Translates base address and GPIO
  *			offset to a register/bitmask pair. If not
  *			given the default gpio_regmap_simple_xlate()
  *			is used.
+ * @fixed_direction_output:
+ *			(Optional) Bitmap representing the fixed direction of
+ *			the GPIO lines. Useful when there are GPIO lines with a
+ *			fixed direction mixed together in the same register.
  * @drvdata:		(Optional) Pointer to driver specific data which is
  *			not used by gpio-remap but is provided "as is" to the
  *			driver callback(s).
+ * @init_valid_mask:	(Optional) Routine to initialize @valid_mask, to be used
+ *			if not all GPIOs are valid.
+ * @regmap_irq_chip:	(Optional) Pointer on an regmap_irq_chip structure. If
+ *			set, a regmap-irq device will be created and the IRQ
+ *			domain will be set accordingly.
+ * @regmap_irq_line:	(Optional) The IRQ the device uses to signal interrupts.
+ * @regmap_irq_flags:	(Optional) The IRQF_ flags to use for the interrupt.
  *
  * The ->reg_mask_xlate translates a given base address and GPIO offset to
  * register and mask pair. The base address is one of the given register
@@ -77,11 +89,22 @@ struct gpio_regmap_config {
 	int reg_stride;
 	int ngpio_per_reg;
 	struct irq_domain *irq_domain;
+	unsigned long *fixed_direction_output;
+
+#ifdef CONFIG_REGMAP_IRQ
+	struct regmap_irq_chip *regmap_irq_chip;
+	int regmap_irq_line;
+	unsigned long regmap_irq_flags;
+#endif
 
 	int (*reg_mask_xlate)(struct gpio_regmap *gpio, unsigned int base,
 			      unsigned int offset, unsigned int *reg,
 			      unsigned int *mask);
 
+	int (*init_valid_mask)(struct gpio_chip *gc,
+			       unsigned long *valid_mask,
+			       unsigned int ngpios);
+
 	void *drvdata;
 };
 
diff --git a/include/linux/gpio_keys.h b/include/linux/gpio_keys.h
index 3f84aeb81e48..80fa930b04c6 100644
--- a/include/linux/gpio_keys.h
+++ b/include/linux/gpio_keys.h
@@ -21,6 +21,7 @@ struct device;
  *			disable button via sysfs
  * @value:		axis value for %EV_ABS
  * @irq:		Irq number in case of interrupt keys
+ * @wakeirq:		Optional dedicated wake-up interrupt
  */
 struct gpio_keys_button {
 	unsigned int code;
@@ -34,6 +35,7 @@ struct gpio_keys_button {
 	bool can_disable;
 	int value;
 	unsigned int irq;
+	unsigned int wakeirq;
 };
 
 /**
diff --git a/include/linux/greybus.h b/include/linux/greybus.h
index 18c0fb958b74..4d58e27ceaf6 100644
--- a/include/linux/greybus.h
+++ b/include/linux/greybus.h
@@ -64,7 +64,7 @@ struct greybus_driver {
 
 	struct device_driver driver;
 };
-#define to_greybus_driver(d) container_of(d, struct greybus_driver, driver)
+#define to_greybus_driver(d) container_of_const(d, struct greybus_driver, driver)
 
 static inline void greybus_set_drvdata(struct gb_bundle *bundle, void *data)
 {
@@ -104,44 +104,14 @@ void gb_debugfs_init(void);
 void gb_debugfs_cleanup(void);
 struct dentry *gb_debugfs_get(void);
 
-extern struct bus_type greybus_bus_type;
+extern const struct bus_type greybus_bus_type;
 
-extern struct device_type greybus_hd_type;
-extern struct device_type greybus_module_type;
-extern struct device_type greybus_interface_type;
-extern struct device_type greybus_control_type;
-extern struct device_type greybus_bundle_type;
-extern struct device_type greybus_svc_type;
-
-static inline int is_gb_host_device(const struct device *dev)
-{
-	return dev->type == &greybus_hd_type;
-}
-
-static inline int is_gb_module(const struct device *dev)
-{
-	return dev->type == &greybus_module_type;
-}
-
-static inline int is_gb_interface(const struct device *dev)
-{
-	return dev->type == &greybus_interface_type;
-}
-
-static inline int is_gb_control(const struct device *dev)
-{
-	return dev->type == &greybus_control_type;
-}
-
-static inline int is_gb_bundle(const struct device *dev)
-{
-	return dev->type == &greybus_bundle_type;
-}
-
-static inline int is_gb_svc(const struct device *dev)
-{
-	return dev->type == &greybus_svc_type;
-}
+extern const struct device_type greybus_hd_type;
+extern const struct device_type greybus_module_type;
+extern const struct device_type greybus_interface_type;
+extern const struct device_type greybus_control_type;
+extern const struct device_type greybus_bundle_type;
+extern const struct device_type greybus_svc_type;
 
 static inline bool cport_id_valid(struct gb_host_device *hd, u16 cport_id)
 {
diff --git a/include/linux/greybus/greybus_protocols.h b/include/linux/greybus/greybus_protocols.h
index aeb8f9243545..820134b0105c 100644
--- a/include/linux/greybus/greybus_protocols.h
+++ b/include/linux/greybus/greybus_protocols.h
@@ -232,9 +232,7 @@ struct gb_fw_download_fetch_firmware_request {
 	__le32			size;
 } __packed;
 
-struct gb_fw_download_fetch_firmware_response {
-	__u8			data[0];
-} __packed;
+/* gb_fw_download_fetch_firmware_response contains no other data */
 
 /* firmware download release firmware request */
 struct gb_fw_download_release_firmware_request {
@@ -414,9 +412,7 @@ struct gb_bootrom_get_firmware_request {
 	__le32			size;
 } __packed;
 
-struct gb_bootrom_get_firmware_response {
-	__u8			data[0];
-} __packed;
+/* gb_bootrom_get_firmware_response contains no other data */
 
 /* Bootrom protocol Ready to boot request */
 struct gb_bootrom_ready_to_boot_request {
diff --git a/include/linux/greybus/svc.h b/include/linux/greybus/svc.h
index 5afaf5f06856..da547fb9071b 100644
--- a/include/linux/greybus/svc.h
+++ b/include/linux/greybus/svc.h
@@ -100,7 +100,4 @@ bool gb_svc_watchdog_enabled(struct gb_svc *svc);
 int gb_svc_watchdog_enable(struct gb_svc *svc);
 int gb_svc_watchdog_disable(struct gb_svc *svc);
 
-int gb_svc_protocol_init(void);
-void gb_svc_protocol_exit(void);
-
 #endif /* __SVC_H */
diff --git a/include/linux/group_cpus.h b/include/linux/group_cpus.h
index e42807ec61f6..9d4e5ab6c314 100644
--- a/include/linux/group_cpus.h
+++ b/include/linux/group_cpus.h
@@ -9,6 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/cpu.h>
 
-struct cpumask *group_cpus_evenly(unsigned int numgrps);
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks);
 
 #endif
diff --git a/include/linux/habanalabs/cpucp_if.h b/include/linux/habanalabs/cpucp_if.h
new file mode 100644
index 000000000000..45f181bcf890
--- /dev/null
+++ b/include/linux/habanalabs/cpucp_if.h
@@ -0,0 +1,1437 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2020-2023 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+#ifndef CPUCP_IF_H
+#define CPUCP_IF_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#include "hl_boot_if.h"
+
+#define NUM_HBM_PSEUDO_CH				2
+#define NUM_HBM_CH_PER_DEV				8
+#define CPUCP_PKT_HBM_ECC_INFO_WR_PAR_SHIFT		0
+#define CPUCP_PKT_HBM_ECC_INFO_WR_PAR_MASK		0x00000001
+#define CPUCP_PKT_HBM_ECC_INFO_RD_PAR_SHIFT		1
+#define CPUCP_PKT_HBM_ECC_INFO_RD_PAR_MASK		0x00000002
+#define CPUCP_PKT_HBM_ECC_INFO_CA_PAR_SHIFT		2
+#define CPUCP_PKT_HBM_ECC_INFO_CA_PAR_MASK		0x00000004
+#define CPUCP_PKT_HBM_ECC_INFO_DERR_SHIFT		3
+#define CPUCP_PKT_HBM_ECC_INFO_DERR_MASK		0x00000008
+#define CPUCP_PKT_HBM_ECC_INFO_SERR_SHIFT		4
+#define CPUCP_PKT_HBM_ECC_INFO_SERR_MASK		0x00000010
+#define CPUCP_PKT_HBM_ECC_INFO_TYPE_SHIFT		5
+#define CPUCP_PKT_HBM_ECC_INFO_TYPE_MASK		0x00000020
+#define CPUCP_PKT_HBM_ECC_INFO_HBM_CH_SHIFT		6
+#define CPUCP_PKT_HBM_ECC_INFO_HBM_CH_MASK		0x000007C0
+
+#define PLL_MAP_MAX_BITS	128
+#define PLL_MAP_LEN		(PLL_MAP_MAX_BITS / 8)
+
+enum eq_event_id {
+	EQ_EVENT_NIC_STS_REQUEST = 0,
+	EQ_EVENT_PWR_MODE_0,
+	EQ_EVENT_PWR_MODE_1,
+	EQ_EVENT_PWR_MODE_2,
+	EQ_EVENT_PWR_MODE_3,
+	EQ_EVENT_PWR_BRK_ENTRY,
+	EQ_EVENT_PWR_BRK_EXIT,
+	EQ_EVENT_HEARTBEAT,
+	EQ_EVENT_CPLD_RESET_REASON,
+	EQ_EVENT_CPLD_SHUTDOWN,
+	EQ_EVENT_POWER_EVT_START,
+	EQ_EVENT_POWER_EVT_END,
+	EQ_EVENT_THERMAL_EVT_START,
+	EQ_EVENT_THERMAL_EVT_END,
+};
+
+/*
+ * info of the pkt queue pointers in the first async occurrence
+ */
+struct cpucp_pkt_sync_err {
+	__le32 pi;
+	__le32 ci;
+};
+
+struct hl_eq_hbm_ecc_data {
+	/* SERR counter */
+	__le32 sec_cnt;
+	/* DERR counter */
+	__le32 dec_cnt;
+	/* Supplemental Information according to the mask bits */
+	__le32 hbm_ecc_info;
+	/* Address in hbm where the ecc happened */
+	__le32 first_addr;
+	/* SERR continuous address counter */
+	__le32 sec_cont_cnt;
+	__le32 pad;
+};
+
+/*
+ * EVENT QUEUE
+ */
+
+struct hl_eq_header {
+	__le32 reserved;
+	__le32 ctl;
+};
+
+struct hl_eq_ecc_data {
+	__le64 ecc_address;
+	__le64 ecc_syndrom;
+	__u8 memory_wrapper_idx;
+	__u8 is_critical;
+	__le16 block_id;
+	__u8 pad[4];
+};
+
+enum hl_sm_sei_cause {
+	SM_SEI_SO_OVERFLOW,
+	SM_SEI_LBW_4B_UNALIGNED,
+	SM_SEI_AXI_RESPONSE_ERR
+};
+
+struct hl_eq_sm_sei_data {
+	__le32 sei_log;
+	/* enum hl_sm_sei_cause */
+	__u8 sei_cause;
+	__u8 pad[3];
+};
+
+enum hl_fw_alive_severity {
+	FW_ALIVE_SEVERITY_MINOR,
+	FW_ALIVE_SEVERITY_CRITICAL
+};
+
+struct hl_eq_fw_alive {
+	__le64 uptime_seconds;
+	__le32 process_id;
+	__le32 thread_id;
+	/* enum hl_fw_alive_severity */
+	__u8 severity;
+	__u8 pad[7];
+};
+
+struct hl_eq_intr_cause {
+	__le64 intr_cause_data;
+};
+
+struct hl_eq_pcie_drain_ind_data {
+	struct hl_eq_intr_cause intr_cause;
+	__le64 drain_wr_addr_lbw;
+	__le64 drain_rd_addr_lbw;
+	__le64 drain_wr_addr_hbw;
+	__le64 drain_rd_addr_hbw;
+};
+
+struct hl_eq_razwi_lbw_info_regs {
+	__le32 rr_aw_razwi_reg;
+	__le32 rr_aw_razwi_id_reg;
+	__le32 rr_ar_razwi_reg;
+	__le32 rr_ar_razwi_id_reg;
+};
+
+struct hl_eq_razwi_hbw_info_regs {
+	__le32 rr_aw_razwi_hi_reg;
+	__le32 rr_aw_razwi_lo_reg;
+	__le32 rr_aw_razwi_id_reg;
+	__le32 rr_ar_razwi_hi_reg;
+	__le32 rr_ar_razwi_lo_reg;
+	__le32 rr_ar_razwi_id_reg;
+};
+
+/* razwi_happened masks */
+#define RAZWI_HAPPENED_HBW	0x1
+#define RAZWI_HAPPENED_LBW	0x2
+#define RAZWI_HAPPENED_AW	0x4
+#define RAZWI_HAPPENED_AR	0x8
+
+struct hl_eq_razwi_info {
+	__le32 razwi_happened_mask;
+	union {
+		struct hl_eq_razwi_lbw_info_regs lbw;
+		struct hl_eq_razwi_hbw_info_regs hbw;
+	};
+	__le32 pad;
+};
+
+struct hl_eq_razwi_with_intr_cause {
+	struct hl_eq_razwi_info razwi_info;
+	struct hl_eq_intr_cause intr_cause;
+};
+
+#define HBM_CA_ERR_CMD_LIFO_LEN		8
+#define HBM_RD_ERR_DATA_LIFO_LEN	8
+#define HBM_WR_PAR_CMD_LIFO_LEN		11
+
+enum hl_hbm_sei_cause {
+	/* Command/address parity error event is split into 2 events due to
+	 * size limitation: ODD suffix for odd HBM CK_t cycles and EVEN  suffix
+	 * for even HBM CK_t cycles
+	 */
+	HBM_SEI_CMD_PARITY_EVEN,
+	HBM_SEI_CMD_PARITY_ODD,
+	/* Read errors can be reflected as a combination of SERR/DERR/parity
+	 * errors. Therefore, we define one event for all read error types.
+	 * LKD will perform further proccessing.
+	 */
+	HBM_SEI_READ_ERR,
+	HBM_SEI_WRITE_DATA_PARITY_ERR,
+	HBM_SEI_CATTRIP,
+	HBM_SEI_MEM_BIST_FAIL,
+	HBM_SEI_DFI,
+	HBM_SEI_INV_TEMP_READ_OUT,
+	HBM_SEI_BIST_FAIL,
+};
+
+/* Masks for parsing hl_hbm_sei_headr fields */
+#define HBM_ECC_SERR_CNTR_MASK		0xFF
+#define HBM_ECC_DERR_CNTR_MASK		0xFF00
+#define HBM_RD_PARITY_CNTR_MASK		0xFF0000
+
+/* HBM index and MC index are known by the event_id */
+struct hl_hbm_sei_header {
+	union {
+		/* relevant only in case of HBM read error */
+		struct {
+			__u8 ecc_serr_cnt;
+			__u8 ecc_derr_cnt;
+			__u8 read_par_cnt;
+			__u8 reserved;
+		};
+		/* All other cases */
+		__le32 cnt;
+	};
+	__u8 sei_cause;		/* enum hl_hbm_sei_cause */
+	__u8 mc_channel;		/* range: 0-3 */
+	__u8 mc_pseudo_channel;	/* range: 0-7 */
+	__u8 is_critical;
+};
+
+#define HBM_RD_ADDR_SID_SHIFT		0
+#define HBM_RD_ADDR_SID_MASK		0x1
+#define HBM_RD_ADDR_BG_SHIFT		1
+#define HBM_RD_ADDR_BG_MASK		0x6
+#define HBM_RD_ADDR_BA_SHIFT		3
+#define HBM_RD_ADDR_BA_MASK		0x18
+#define HBM_RD_ADDR_COL_SHIFT		5
+#define HBM_RD_ADDR_COL_MASK		0x7E0
+#define HBM_RD_ADDR_ROW_SHIFT		11
+#define HBM_RD_ADDR_ROW_MASK		0x3FFF800
+
+struct hbm_rd_addr {
+	union {
+		/* bit fields are only for FW use */
+		struct {
+			u32 dbg_rd_err_addr_sid:1;
+			u32 dbg_rd_err_addr_bg:2;
+			u32 dbg_rd_err_addr_ba:2;
+			u32 dbg_rd_err_addr_col:6;
+			u32 dbg_rd_err_addr_row:15;
+			u32 reserved:6;
+		};
+		__le32 rd_addr_val;
+	};
+};
+
+#define HBM_RD_ERR_BEAT_SHIFT		2
+/* dbg_rd_err_misc fields: */
+/* Read parity is calculated per DW on every beat */
+#define HBM_RD_ERR_PAR_ERR_BEAT0_SHIFT	0
+#define HBM_RD_ERR_PAR_ERR_BEAT0_MASK	0x3
+#define HBM_RD_ERR_PAR_DATA_BEAT0_SHIFT	8
+#define HBM_RD_ERR_PAR_DATA_BEAT0_MASK	0x300
+/* ECC is calculated per PC on every beat */
+#define HBM_RD_ERR_SERR_BEAT0_SHIFT	16
+#define HBM_RD_ERR_SERR_BEAT0_MASK	0x10000
+#define HBM_RD_ERR_DERR_BEAT0_SHIFT	24
+#define HBM_RD_ERR_DERR_BEAT0_MASK	0x100000
+
+struct hl_eq_hbm_sei_read_err_intr_info {
+	/* DFI_RD_ERR_REP_ADDR */
+	struct hbm_rd_addr dbg_rd_err_addr;
+	/* DFI_RD_ERR_REP_ERR */
+	union {
+		struct {
+			/* bit fields are only for FW use */
+			u32 dbg_rd_err_par:8;
+			u32 dbg_rd_err_par_data:8;
+			u32 dbg_rd_err_serr:4;
+			u32 dbg_rd_err_derr:4;
+			u32 reserved:8;
+		};
+		__le32 dbg_rd_err_misc;
+	};
+	/* DFI_RD_ERR_REP_DM */
+	__le32 dbg_rd_err_dm;
+	/* DFI_RD_ERR_REP_SYNDROME */
+	__le32 dbg_rd_err_syndrome;
+	/* DFI_RD_ERR_REP_DATA */
+	__le32 dbg_rd_err_data[HBM_RD_ERR_DATA_LIFO_LEN];
+};
+
+struct hl_eq_hbm_sei_ca_par_intr_info {
+	/* 14 LSBs */
+	__le16 dbg_row[HBM_CA_ERR_CMD_LIFO_LEN];
+	/* 18 LSBs */
+	__le32 dbg_col[HBM_CA_ERR_CMD_LIFO_LEN];
+};
+
+#define WR_PAR_LAST_CMD_COL_SHIFT	0
+#define WR_PAR_LAST_CMD_COL_MASK	0x3F
+#define WR_PAR_LAST_CMD_BG_SHIFT	6
+#define WR_PAR_LAST_CMD_BG_MASK		0xC0
+#define WR_PAR_LAST_CMD_BA_SHIFT	8
+#define WR_PAR_LAST_CMD_BA_MASK		0x300
+#define WR_PAR_LAST_CMD_SID_SHIFT	10
+#define WR_PAR_LAST_CMD_SID_MASK	0x400
+
+/* Row address isn't latched */
+struct hbm_sei_wr_cmd_address {
+	/* DFI_DERR_LAST_CMD */
+	union {
+		struct {
+			/* bit fields are only for FW use */
+			u32 col:6;
+			u32 bg:2;
+			u32 ba:2;
+			u32 sid:1;
+			u32 reserved:21;
+		};
+		__le32 dbg_wr_cmd_addr;
+	};
+};
+
+struct hl_eq_hbm_sei_wr_par_intr_info {
+	/* entry 0: WR command address from the 1st cycle prior to the error
+	 * entry 1: WR command address from the 2nd cycle prior to the error
+	 * and so on...
+	 */
+	struct hbm_sei_wr_cmd_address dbg_last_wr_cmds[HBM_WR_PAR_CMD_LIFO_LEN];
+	/* derr[0:1] - 1st HBM cycle DERR output
+	 * derr[2:3] - 2nd HBM cycle DERR output
+	 */
+	__u8 dbg_derr;
+	/* extend to reach 8B */
+	__u8 pad[3];
+};
+
+/*
+ * this struct represents the following sei causes:
+ * command parity, ECC double error, ECC single error, dfi error, cattrip,
+ * temperature read-out, read parity error and write parity error.
+ * some only use the header while some have extra data.
+ */
+struct hl_eq_hbm_sei_data {
+	struct hl_hbm_sei_header hdr;
+	union {
+		struct hl_eq_hbm_sei_ca_par_intr_info ca_parity_even_info;
+		struct hl_eq_hbm_sei_ca_par_intr_info ca_parity_odd_info;
+		struct hl_eq_hbm_sei_read_err_intr_info read_err_info;
+		struct hl_eq_hbm_sei_wr_par_intr_info wr_parity_info;
+	};
+};
+
+/* Engine/farm arc interrupt type */
+enum hl_engine_arc_interrupt_type {
+	/* Qman/farm ARC DCCM QUEUE FULL interrupt type */
+	ENGINE_ARC_DCCM_QUEUE_FULL_IRQ = 1
+};
+
+/* Data structure specifies details of payload of DCCM QUEUE FULL interrupt */
+struct hl_engine_arc_dccm_queue_full_irq {
+	/* Queue index value which caused DCCM QUEUE FULL */
+	__le32 queue_index;
+	__le32 pad;
+};
+
+/* Data structure specifies details of QM/FARM ARC interrupt */
+struct hl_eq_engine_arc_intr_data {
+	/* ARC engine id e.g.  DCORE0_TPC0_QM_ARC, DCORE0_TCP1_QM_ARC */
+	__le32 engine_id;
+	__le32 intr_type; /* enum hl_engine_arc_interrupt_type */
+	/* More info related to the interrupt e.g. queue index
+	 * incase of DCCM_QUEUE_FULL interrupt.
+	 */
+	__le64 payload;
+	__le64 pad[5];
+};
+
+#define ADDR_DEC_ADDRESS_COUNT_MAX 4
+
+/* Data structure specifies details of ADDR_DEC interrupt */
+struct hl_eq_addr_dec_intr_data {
+	struct hl_eq_intr_cause intr_cause;
+	__le64 addr[ADDR_DEC_ADDRESS_COUNT_MAX];
+	__u8 addr_cnt;
+	__u8 pad[7];
+};
+
+struct hl_eq_entry {
+	struct hl_eq_header hdr;
+	union {
+		__le64 data_placeholder;
+		struct hl_eq_ecc_data ecc_data;
+		struct hl_eq_hbm_ecc_data hbm_ecc_data;	/* Obsolete */
+		struct hl_eq_sm_sei_data sm_sei_data;
+		struct cpucp_pkt_sync_err pkt_sync_err;
+		struct hl_eq_fw_alive fw_alive;
+		struct hl_eq_intr_cause intr_cause;
+		struct hl_eq_pcie_drain_ind_data pcie_drain_ind_data;
+		struct hl_eq_razwi_info razwi_info;
+		struct hl_eq_razwi_with_intr_cause razwi_with_intr_cause;
+		struct hl_eq_hbm_sei_data sei_data;	/* Gaudi2 HBM */
+		struct hl_eq_engine_arc_intr_data arc_data;
+		struct hl_eq_addr_dec_intr_data addr_dec;
+		__le64 data[7];
+	};
+};
+
+#define HL_EQ_ENTRY_SIZE		sizeof(struct hl_eq_entry)
+
+#define EQ_CTL_READY_SHIFT		31
+#define EQ_CTL_READY_MASK		0x80000000
+
+#define EQ_CTL_EVENT_MODE_SHIFT		28
+#define EQ_CTL_EVENT_MODE_MASK		0x70000000
+
+#define EQ_CTL_EVENT_TYPE_SHIFT		16
+#define EQ_CTL_EVENT_TYPE_MASK		0x0FFF0000
+
+#define EQ_CTL_INDEX_SHIFT		0
+#define EQ_CTL_INDEX_MASK		0x0000FFFF
+
+enum pq_init_status {
+	PQ_INIT_STATUS_NA = 0,
+	PQ_INIT_STATUS_READY_FOR_CP,
+	PQ_INIT_STATUS_READY_FOR_HOST,
+	PQ_INIT_STATUS_READY_FOR_CP_SINGLE_MSI,
+	PQ_INIT_STATUS_LEN_NOT_POWER_OF_TWO_ERR,
+	PQ_INIT_STATUS_ILLEGAL_Q_ADDR_ERR
+};
+
+/*
+ * CpuCP Primary Queue Packets
+ *
+ * During normal operation, the host's kernel driver needs to send various
+ * messages to CpuCP, usually either to SET some value into a H/W periphery or
+ * to GET the current value of some H/W periphery. For example, SET the
+ * frequency of MME/TPC and GET the value of the thermal sensor.
+ *
+ * These messages can be initiated either by the User application or by the
+ * host's driver itself, e.g. power management code. In either case, the
+ * communication from the host's driver to CpuCP will *always* be in
+ * synchronous mode, meaning that the host will send a single message and poll
+ * until the message was acknowledged and the results are ready (if results are
+ * needed).
+ *
+ * This means that only a single message can be sent at a time and the host's
+ * driver must wait for its result before sending the next message. Having said
+ * that, because these are control messages which are sent in a relatively low
+ * frequency, this limitation seems acceptable. It's important to note that
+ * in case of multiple devices, messages to different devices *can* be sent
+ * at the same time.
+ *
+ * The message, inputs/outputs (if relevant) and fence object will be located
+ * on the device DDR at an address that will be determined by the host's driver.
+ * During device initialization phase, the host will pass to CpuCP that address.
+ * Most of the message types will contain inputs/outputs inside the message
+ * itself. The common part of each message will contain the opcode of the
+ * message (its type) and a field representing a fence object.
+ *
+ * When the host's driver wishes to send a message to CPU CP, it will write the
+ * message contents to the device DDR, clear the fence object and then write to
+ * the PSOC_ARC1_AUX_SW_INTR, to issue interrupt 121 to ARC Management CPU.
+ *
+ * Upon receiving the interrupt (#121), CpuCP will read the message from the
+ * DDR. In case the message is a SET operation, CpuCP will first perform the
+ * operation and then write to the fence object on the device DDR. In case the
+ * message is a GET operation, CpuCP will first fill the results section on the
+ * device DDR and then write to the fence object. If an error occurred, CpuCP
+ * will fill the rc field with the right error code.
+ *
+ * In the meantime, the host's driver will poll on the fence object. Once the
+ * host sees that the fence object is signaled, it will read the results from
+ * the device DDR (if relevant) and resume the code execution in the host's
+ * driver.
+ *
+ * To use QMAN packets, the opcode must be the QMAN opcode, shifted by 8
+ * so the value being put by the host's driver matches the value read by CpuCP
+ *
+ * Non-QMAN packets should be limited to values 1 through (2^8 - 1)
+ *
+ * Detailed description:
+ *
+ * CPUCP_PACKET_DISABLE_PCI_ACCESS -
+ *       After receiving this packet the embedded CPU must NOT issue PCI
+ *       transactions (read/write) towards the Host CPU. This also include
+ *       sending MSI-X interrupts.
+ *       This packet is usually sent before the device is moved to D3Hot state.
+ *
+ * CPUCP_PACKET_ENABLE_PCI_ACCESS -
+ *       After receiving this packet the embedded CPU is allowed to issue PCI
+ *       transactions towards the Host CPU, including sending MSI-X interrupts.
+ *       This packet is usually send after the device is moved to D0 state.
+ *
+ * CPUCP_PACKET_TEMPERATURE_GET -
+ *       Fetch the current temperature / Max / Max Hyst / Critical /
+ *       Critical Hyst of a specified thermal sensor. The packet's
+ *       arguments specify the desired sensor and the field to get.
+ *
+ * CPUCP_PACKET_VOLTAGE_GET -
+ *       Fetch the voltage / Max / Min of a specified sensor. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_CURRENT_GET -
+ *       Fetch the current / Max / Min of a specified sensor. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_FAN_SPEED_GET -
+ *       Fetch the speed / Max / Min of a specified fan. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_PWM_GET -
+ *       Fetch the pwm value / mode of a specified pwm. The packet's
+ *       arguments specify the sensor and type.
+ *
+ * CPUCP_PACKET_PWM_SET -
+ *       Set the pwm value / mode of a specified pwm. The packet's
+ *       arguments specify the sensor, type and value.
+ *
+ * CPUCP_PACKET_FREQUENCY_SET -
+ *       Set the frequency of a specified PLL. The packet's arguments specify
+ *       the PLL and the desired frequency. The actual frequency in the device
+ *       might differ from the requested frequency.
+ *
+ * CPUCP_PACKET_FREQUENCY_GET -
+ *       Fetch the frequency of a specified PLL. The packet's arguments specify
+ *       the PLL.
+ *
+ * CPUCP_PACKET_LED_SET -
+ *       Set the state of a specified led. The packet's arguments
+ *       specify the led and the desired state.
+ *
+ * CPUCP_PACKET_I2C_WR -
+ *       Write 32-bit value to I2C device. The packet's arguments specify the
+ *       I2C bus, address and value.
+ *
+ * CPUCP_PACKET_I2C_RD -
+ *       Read 32-bit value from I2C device. The packet's arguments specify the
+ *       I2C bus and address.
+ *
+ * CPUCP_PACKET_INFO_GET -
+ *       Fetch information from the device as specified in the packet's
+ *       structure. The host's driver passes the max size it allows the CpuCP to
+ *       write to the structure, to prevent data corruption in case of
+ *       mismatched driver/FW versions.
+ *
+ * CPUCP_PACKET_FLASH_PROGRAM_REMOVED - this packet was removed
+ *
+ * CPUCP_PACKET_UNMASK_RAZWI_IRQ -
+ *       Unmask the given IRQ. The IRQ number is specified in the value field.
+ *       The packet is sent after receiving an interrupt and printing its
+ *       relevant information.
+ *
+ * CPUCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY -
+ *       Unmask the given IRQs. The IRQs numbers are specified in an array right
+ *       after the cpucp_packet structure, where its first element is the array
+ *       length. The packet is sent after a soft reset was done in order to
+ *       handle any interrupts that were sent during the reset process.
+ *
+ * CPUCP_PACKET_TEST -
+ *       Test packet for CpuCP connectivity. The CPU will put the fence value
+ *       in the result field.
+ *
+ * CPUCP_PACKET_FREQUENCY_CURR_GET -
+ *       Fetch the current frequency of a specified PLL. The packet's arguments
+ *       specify the PLL.
+ *
+ * CPUCP_PACKET_MAX_POWER_GET -
+ *       Fetch the maximal power of the device.
+ *
+ * CPUCP_PACKET_MAX_POWER_SET -
+ *       Set the maximal power of the device. The packet's arguments specify
+ *       the power.
+ *
+ * CPUCP_PACKET_EEPROM_DATA_GET -
+ *       Get EEPROM data from the CpuCP kernel. The buffer is specified in the
+ *       addr field. The CPU will put the returned data size in the result
+ *       field. In addition, the host's driver passes the max size it allows the
+ *       CpuCP to write to the structure, to prevent data corruption in case of
+ *       mismatched driver/FW versions.
+ *
+ * CPUCP_PACKET_NIC_INFO_GET -
+ *       Fetch information from the device regarding the NIC. the host's driver
+ *       passes the max size it allows the CpuCP to write to the structure, to
+ *       prevent data corruption in case of mismatched driver/FW versions.
+ *
+ * CPUCP_PACKET_TEMPERATURE_SET -
+ *       Set the value of the offset property of a specified thermal sensor.
+ *       The packet's arguments specify the desired sensor and the field to
+ *       set.
+ *
+ * CPUCP_PACKET_VOLTAGE_SET -
+ *       Trigger the reset_history property of a specified voltage sensor.
+ *       The packet's arguments specify the desired sensor and the field to
+ *       set.
+ *
+ * CPUCP_PACKET_CURRENT_SET -
+ *       Trigger the reset_history property of a specified current sensor.
+ *       The packet's arguments specify the desired sensor and the field to
+ *       set.
+ *
+ * CPUCP_PACKET_PCIE_THROUGHPUT_GET -
+ *       Get throughput of PCIe.
+ *       The packet's arguments specify the transaction direction (TX/RX).
+ *       The window measurement is 10[msec], and the return value is in KB/sec.
+ *
+ * CPUCP_PACKET_PCIE_REPLAY_CNT_GET
+ *       Replay count measures number of "replay" events, which is basicly
+ *       number of retries done by PCIe.
+ *
+ * CPUCP_PACKET_TOTAL_ENERGY_GET -
+ *       Total Energy is measurement of energy from the time FW Linux
+ *       is loaded. It is calculated by multiplying the average power
+ *       by time (passed from armcp start). The units are in MilliJouls.
+ *
+ * CPUCP_PACKET_PLL_INFO_GET -
+ *       Fetch frequencies of PLL from the required PLL IP.
+ *       The packet's arguments specify the device PLL type
+ *       Pll type is the PLL from device pll_index enum.
+ *       The result is composed of 4 outputs, each is 16-bit
+ *       frequency in MHz.
+ *
+ * CPUCP_PACKET_POWER_GET -
+ *       Fetch the present power consumption of the device (Current * Voltage).
+ *
+ * CPUCP_PACKET_NIC_PFC_SET -
+ *       Enable/Disable the NIC PFC feature. The packet's arguments specify the
+ *       NIC port, relevant lanes to configure and one bit indication for
+ *       enable/disable.
+ *
+ * CPUCP_PACKET_NIC_FAULT_GET -
+ *       Fetch the current indication for local/remote faults from the NIC MAC.
+ *       The result is 32-bit value of the relevant register.
+ *
+ * CPUCP_PACKET_NIC_LPBK_SET -
+ *       Enable/Disable the MAC loopback feature. The packet's arguments specify
+ *       the NIC port, relevant lanes to configure and one bit indication for
+ *       enable/disable.
+ *
+ * CPUCP_PACKET_NIC_MAC_INIT -
+ *       Configure the NIC MAC channels. The packet's arguments specify the
+ *       NIC port and the speed.
+ *
+ * CPUCP_PACKET_MSI_INFO_SET -
+ *       set the index number for each supported msi type going from
+ *       host to device
+ *
+ * CPUCP_PACKET_NIC_XPCS91_REGS_GET -
+ *       Fetch the un/correctable counters values from the NIC MAC.
+ *
+ * CPUCP_PACKET_NIC_STAT_REGS_GET -
+ *       Fetch various NIC MAC counters from the NIC STAT.
+ *
+ * CPUCP_PACKET_NIC_STAT_REGS_CLR -
+ *       Clear the various NIC MAC counters in the NIC STAT.
+ *
+ * CPUCP_PACKET_NIC_STAT_REGS_ALL_GET -
+ *       Fetch all NIC MAC counters from the NIC STAT.
+ *
+ * CPUCP_PACKET_IS_IDLE_CHECK -
+ *       Check if the device is IDLE in regard to the DMA/compute engines
+ *       and QMANs. The f/w will return a bitmask where each bit represents
+ *       a different engine or QMAN according to enum cpucp_idle_mask.
+ *       The bit will be 1 if the engine is NOT idle.
+ *
+ * CPUCP_PACKET_HBM_REPLACED_ROWS_INFO_GET -
+ *       Fetch all HBM replaced-rows and prending to be replaced rows data.
+ *
+ * CPUCP_PACKET_HBM_PENDING_ROWS_STATUS -
+ *       Fetch status of HBM rows pending replacement and need a reboot to
+ *       be replaced.
+ *
+ * CPUCP_PACKET_POWER_SET -
+ *       Resets power history of device to 0
+ *
+ * CPUCP_PACKET_ENGINE_CORE_ASID_SET -
+ *       Packet to perform engine core ASID configuration
+ *
+ * CPUCP_PACKET_SEC_ATTEST_GET -
+ *       Get the attestaion data that is collected during various stages of the
+ *       boot sequence. the attestation data is also hashed with some unique
+ *       number (nonce) provided by the host to prevent replay attacks.
+ *       public key and certificate also provided as part of the FW response.
+ *
+ * CPUCP_PACKET_INFO_SIGNED_GET -
+ *       Get the device information signed by the Trusted Platform device.
+ *       device info data is also hashed with some unique number (nonce) provided
+ *       by the host to prevent replay attacks. public key and certificate also
+ *       provided as part of the FW response.
+ *
+ * CPUCP_PACKET_MONITOR_DUMP_GET -
+ *       Get monitors registers dump from the CpuCP kernel.
+ *       The CPU will put the registers dump in the a buffer allocated by the driver
+ *       which address is passed via the CpuCp packet. In addition, the host's driver
+ *       passes the max size it allows the CpuCP to write to the structure, to prevent
+ *       data corruption in case of mismatched driver/FW versions.
+ *       Obsolete.
+ *
+ * CPUCP_PACKET_GENERIC_PASSTHROUGH -
+ *       Generic opcode for all firmware info that is only passed to host
+ *       through the LKD, without getting parsed there.
+ *
+ * CPUCP_PACKET_ACTIVE_STATUS_SET -
+ *       LKD sends FW indication whether device is free or in use, this indication is reported
+ *       also to the BMC.
+ *
+ * CPUCP_PACKET_SOFT_RESET -
+ *       Packet to perform soft-reset.
+ *
+ * CPUCP_PACKET_INTS_REGISTER -
+ *       Packet to inform FW that queues have been established and LKD is ready to receive
+ *       EQ events.
+ */
+
+enum cpucp_packet_id {
+	CPUCP_PACKET_DISABLE_PCI_ACCESS = 1,	/* internal */
+	CPUCP_PACKET_ENABLE_PCI_ACCESS,		/* internal */
+	CPUCP_PACKET_TEMPERATURE_GET,		/* sysfs */
+	CPUCP_PACKET_VOLTAGE_GET,		/* sysfs */
+	CPUCP_PACKET_CURRENT_GET,		/* sysfs */
+	CPUCP_PACKET_FAN_SPEED_GET,		/* sysfs */
+	CPUCP_PACKET_PWM_GET,			/* sysfs */
+	CPUCP_PACKET_PWM_SET,			/* sysfs */
+	CPUCP_PACKET_FREQUENCY_SET,		/* sysfs */
+	CPUCP_PACKET_FREQUENCY_GET,		/* sysfs */
+	CPUCP_PACKET_LED_SET,			/* debugfs */
+	CPUCP_PACKET_I2C_WR,			/* debugfs */
+	CPUCP_PACKET_I2C_RD,			/* debugfs */
+	CPUCP_PACKET_INFO_GET,			/* IOCTL */
+	CPUCP_PACKET_FLASH_PROGRAM_REMOVED,
+	CPUCP_PACKET_UNMASK_RAZWI_IRQ,		/* internal */
+	CPUCP_PACKET_UNMASK_RAZWI_IRQ_ARRAY,	/* internal */
+	CPUCP_PACKET_TEST,			/* internal */
+	CPUCP_PACKET_FREQUENCY_CURR_GET,	/* sysfs */
+	CPUCP_PACKET_MAX_POWER_GET,		/* sysfs */
+	CPUCP_PACKET_MAX_POWER_SET,		/* sysfs */
+	CPUCP_PACKET_EEPROM_DATA_GET,		/* sysfs */
+	CPUCP_PACKET_NIC_INFO_GET,		/* internal */
+	CPUCP_PACKET_TEMPERATURE_SET,		/* sysfs */
+	CPUCP_PACKET_VOLTAGE_SET,		/* sysfs */
+	CPUCP_PACKET_CURRENT_SET,		/* sysfs */
+	CPUCP_PACKET_PCIE_THROUGHPUT_GET,	/* internal */
+	CPUCP_PACKET_PCIE_REPLAY_CNT_GET,	/* internal */
+	CPUCP_PACKET_TOTAL_ENERGY_GET,		/* internal */
+	CPUCP_PACKET_PLL_INFO_GET,		/* internal */
+	CPUCP_PACKET_NIC_STATUS,		/* internal */
+	CPUCP_PACKET_POWER_GET,			/* internal */
+	CPUCP_PACKET_NIC_PFC_SET,		/* internal */
+	CPUCP_PACKET_NIC_FAULT_GET,		/* internal */
+	CPUCP_PACKET_NIC_LPBK_SET,		/* internal */
+	CPUCP_PACKET_NIC_MAC_CFG,		/* internal */
+	CPUCP_PACKET_MSI_INFO_SET,		/* internal */
+	CPUCP_PACKET_NIC_XPCS91_REGS_GET,	/* internal */
+	CPUCP_PACKET_NIC_STAT_REGS_GET,		/* internal */
+	CPUCP_PACKET_NIC_STAT_REGS_CLR,		/* internal */
+	CPUCP_PACKET_NIC_STAT_REGS_ALL_GET,	/* internal */
+	CPUCP_PACKET_IS_IDLE_CHECK,		/* internal */
+	CPUCP_PACKET_HBM_REPLACED_ROWS_INFO_GET,/* internal */
+	CPUCP_PACKET_HBM_PENDING_ROWS_STATUS,	/* internal */
+	CPUCP_PACKET_POWER_SET,			/* internal */
+	CPUCP_PACKET_RESERVED,			/* not used */
+	CPUCP_PACKET_ENGINE_CORE_ASID_SET,	/* internal */
+	CPUCP_PACKET_RESERVED2,			/* not used */
+	CPUCP_PACKET_SEC_ATTEST_GET,		/* internal */
+	CPUCP_PACKET_INFO_SIGNED_GET,		/* internal */
+	CPUCP_PACKET_RESERVED4,			/* not used */
+	CPUCP_PACKET_MONITOR_DUMP_GET,		/* debugfs */
+	CPUCP_PACKET_RESERVED5,			/* not used */
+	CPUCP_PACKET_RESERVED6,			/* not used */
+	CPUCP_PACKET_RESERVED7,			/* not used */
+	CPUCP_PACKET_GENERIC_PASSTHROUGH,	/* IOCTL */
+	CPUCP_PACKET_RESERVED8,			/* not used */
+	CPUCP_PACKET_ACTIVE_STATUS_SET,		/* internal */
+	CPUCP_PACKET_RESERVED9,			/* not used */
+	CPUCP_PACKET_RESERVED10,		/* not used */
+	CPUCP_PACKET_RESERVED11,		/* not used */
+	CPUCP_PACKET_RESERVED12,		/* internal */
+	CPUCP_PACKET_RESERVED13,                /* internal */
+	CPUCP_PACKET_SOFT_RESET,		/* internal */
+	CPUCP_PACKET_INTS_REGISTER,		/* internal */
+	CPUCP_PACKET_ID_MAX			/* must be last */
+};
+
+#define CPUCP_PACKET_FENCE_VAL	0xFE8CE7A5
+
+#define CPUCP_PKT_CTL_RC_SHIFT		12
+#define CPUCP_PKT_CTL_RC_MASK		0x0000F000
+
+#define CPUCP_PKT_CTL_OPCODE_SHIFT	16
+#define CPUCP_PKT_CTL_OPCODE_MASK	0x1FFF0000
+
+#define CPUCP_PKT_RES_PLL_OUT0_SHIFT	0
+#define CPUCP_PKT_RES_PLL_OUT0_MASK	0x000000000000FFFFull
+#define CPUCP_PKT_RES_PLL_OUT1_SHIFT	16
+#define CPUCP_PKT_RES_PLL_OUT1_MASK	0x00000000FFFF0000ull
+#define CPUCP_PKT_RES_PLL_OUT2_SHIFT	32
+#define CPUCP_PKT_RES_PLL_OUT2_MASK	0x0000FFFF00000000ull
+#define CPUCP_PKT_RES_PLL_OUT3_SHIFT	48
+#define CPUCP_PKT_RES_PLL_OUT3_MASK	0xFFFF000000000000ull
+
+#define CPUCP_PKT_RES_EEPROM_OUT0_SHIFT	0
+#define CPUCP_PKT_RES_EEPROM_OUT0_MASK	0x000000000000FFFFull
+#define CPUCP_PKT_RES_EEPROM_OUT1_SHIFT	16
+#define CPUCP_PKT_RES_EEPROM_OUT1_MASK	0x0000000000FF0000ull
+
+#define CPUCP_PKT_VAL_PFC_IN1_SHIFT	0
+#define CPUCP_PKT_VAL_PFC_IN1_MASK	0x0000000000000001ull
+#define CPUCP_PKT_VAL_PFC_IN2_SHIFT	1
+#define CPUCP_PKT_VAL_PFC_IN2_MASK	0x000000000000001Eull
+
+#define CPUCP_PKT_VAL_LPBK_IN1_SHIFT	0
+#define CPUCP_PKT_VAL_LPBK_IN1_MASK	0x0000000000000001ull
+#define CPUCP_PKT_VAL_LPBK_IN2_SHIFT	1
+#define CPUCP_PKT_VAL_LPBK_IN2_MASK	0x000000000000001Eull
+
+#define CPUCP_PKT_VAL_MAC_CNT_IN1_SHIFT	0
+#define CPUCP_PKT_VAL_MAC_CNT_IN1_MASK	0x0000000000000001ull
+#define CPUCP_PKT_VAL_MAC_CNT_IN2_SHIFT	1
+#define CPUCP_PKT_VAL_MAC_CNT_IN2_MASK	0x00000000FFFFFFFEull
+
+/* heartbeat status bits */
+#define CPUCP_PKT_HB_STATUS_EQ_FAULT_SHIFT		0
+#define CPUCP_PKT_HB_STATUS_EQ_FAULT_MASK		0x00000001
+
+struct cpucp_packet {
+	union {
+		__le64 value;	/* For SET packets */
+		__le64 result;	/* For GET packets */
+		__le64 addr;	/* For PQ */
+	};
+
+	__le32 ctl;
+
+	__le32 fence;		/* Signal to host that message is completed */
+
+	union {
+		struct {/* For temperature/current/voltage/fan/pwm get/set */
+			__le16 sensor_index;
+			__le16 type;
+		};
+
+		struct {	/* For I2C read/write */
+			__u8 i2c_bus;
+			__u8 i2c_addr;
+			__u8 i2c_reg;
+			/*
+			 * In legacy implemetations, i2c_len was not present,
+			 * was unused and just added as pad.
+			 * So if i2c_len is 0, it is treated as legacy
+			 * and r/w 1 Byte, else if i2c_len is specified,
+			 * its treated as new multibyte r/w support.
+			 */
+			__u8 i2c_len;
+		};
+
+		struct {/* For PLL info fetch */
+			__le16 pll_type;
+			/* TODO pll_reg is kept temporary before removal */
+			__le16 pll_reg;
+		};
+
+		/* For any general request */
+		__le32 index;
+
+		/* For frequency get/set */
+		__le32 pll_index;
+
+		/* For led set */
+		__le32 led_index;
+
+		/* For get CpuCP info/EEPROM data/NIC info */
+		__le32 data_max_size;
+
+		/*
+		 * For any general status bitmask. Shall be used whenever the
+		 * result cannot be used to hold general purpose data.
+		 */
+		__le32 status_mask;
+	};
+
+	union {
+		/* For NIC requests */
+		__le32 port_index;
+
+		/* For Generic packet sub index */
+		__le32 pkt_subidx;
+
+		/* random, used once number, for security packets */
+		__le32 nonce;
+	};
+};
+
+struct cpucp_unmask_irq_arr_packet {
+	struct cpucp_packet cpucp_pkt;
+	__le32 length;
+	__le32 irqs[];
+};
+
+struct cpucp_nic_status_packet {
+	struct cpucp_packet cpucp_pkt;
+	__le32 length;
+	__le32 data[];
+};
+
+struct cpucp_array_data_packet {
+	struct cpucp_packet cpucp_pkt;
+	__le32 length;
+	__le32 data[];
+};
+
+enum cpucp_led_index {
+	CPUCP_LED0_INDEX = 0,
+	CPUCP_LED1_INDEX,
+	CPUCP_LED2_INDEX,
+	CPUCP_LED_MAX_INDEX = CPUCP_LED2_INDEX
+};
+
+/*
+ * enum cpucp_packet_rc - Error return code
+ * @cpucp_packet_success	-> in case of success.
+ * @cpucp_packet_invalid	-> this is to support first generation platforms.
+ * @cpucp_packet_fault		-> in case of processing error like failing to
+ *                                 get device binding or semaphore etc.
+ * @cpucp_packet_invalid_pkt	-> when cpucp packet is un-supported.
+ * @cpucp_packet_invalid_params	-> when checking parameter like length of buffer
+ *				   or attribute value etc.
+ * @cpucp_packet_rc_max		-> It indicates size of enum so should be at last.
+ */
+enum cpucp_packet_rc {
+	cpucp_packet_success,
+	cpucp_packet_invalid,
+	cpucp_packet_fault,
+	cpucp_packet_invalid_pkt,
+	cpucp_packet_invalid_params,
+	cpucp_packet_rc_max
+};
+
+/*
+ * cpucp_temp_type should adhere to hwmon_temp_attributes
+ * defined in Linux kernel hwmon.h file
+ */
+enum cpucp_temp_type {
+	cpucp_temp_input,
+	cpucp_temp_min = 4,
+	cpucp_temp_min_hyst,
+	cpucp_temp_max = 6,
+	cpucp_temp_max_hyst,
+	cpucp_temp_crit,
+	cpucp_temp_crit_hyst,
+	cpucp_temp_offset = 19,
+	cpucp_temp_lowest = 21,
+	cpucp_temp_highest = 22,
+	cpucp_temp_reset_history = 23,
+	cpucp_temp_warn = 24,
+	cpucp_temp_max_crit = 25,
+	cpucp_temp_max_warn = 26,
+};
+
+enum cpucp_in_attributes {
+	cpucp_in_input,
+	cpucp_in_min,
+	cpucp_in_max,
+	cpucp_in_lowest = 6,
+	cpucp_in_highest = 7,
+	cpucp_in_reset_history,
+	cpucp_in_intr_alarm_a,
+	cpucp_in_intr_alarm_b,
+};
+
+enum cpucp_curr_attributes {
+	cpucp_curr_input,
+	cpucp_curr_min,
+	cpucp_curr_max,
+	cpucp_curr_lowest = 6,
+	cpucp_curr_highest = 7,
+	cpucp_curr_reset_history
+};
+
+enum cpucp_fan_attributes {
+	cpucp_fan_input,
+	cpucp_fan_min = 2,
+	cpucp_fan_max
+};
+
+enum cpucp_pwm_attributes {
+	cpucp_pwm_input,
+	cpucp_pwm_enable
+};
+
+enum cpucp_pcie_throughput_attributes {
+	cpucp_pcie_throughput_tx,
+	cpucp_pcie_throughput_rx
+};
+
+/* TODO temporary kept before removal */
+enum cpucp_pll_reg_attributes {
+	cpucp_pll_nr_reg,
+	cpucp_pll_nf_reg,
+	cpucp_pll_od_reg,
+	cpucp_pll_div_factor_reg,
+	cpucp_pll_div_sel_reg
+};
+
+/* TODO temporary kept before removal */
+enum cpucp_pll_type_attributes {
+	cpucp_pll_cpu,
+	cpucp_pll_pci,
+};
+
+/*
+ * cpucp_power_type aligns with hwmon_power_attributes
+ * defined in Linux kernel hwmon.h file
+ */
+enum cpucp_power_type {
+	CPUCP_POWER_INPUT = 8,
+	CPUCP_POWER_INPUT_HIGHEST = 9,
+	CPUCP_POWER_RESET_INPUT_HISTORY = 11
+};
+
+/*
+ * MSI type enumeration table for all ASICs and future SW versions.
+ * For future ASIC-LKD compatibility, we can only add new enumerations.
+ * at the end of the table (before CPUCP_NUM_OF_MSI_TYPES).
+ * Changing the order of entries or removing entries is not allowed.
+ */
+enum cpucp_msi_type {
+	CPUCP_EVENT_QUEUE_MSI_TYPE,
+	CPUCP_NIC_PORT1_MSI_TYPE,
+	CPUCP_NIC_PORT3_MSI_TYPE,
+	CPUCP_NIC_PORT5_MSI_TYPE,
+	CPUCP_NIC_PORT7_MSI_TYPE,
+	CPUCP_NIC_PORT9_MSI_TYPE,
+	CPUCP_EVENT_QUEUE_ERR_MSI_TYPE,
+	CPUCP_NUM_OF_MSI_TYPES
+};
+
+/*
+ * PLL enumeration table used for all ASICs and future SW versions.
+ * For future ASIC-LKD compatibility, we can only add new enumerations.
+ * at the end of the table.
+ * Changing the order of entries or removing entries is not allowed.
+ */
+enum pll_index {
+	CPU_PLL = 0,
+	PCI_PLL = 1,
+	NIC_PLL = 2,
+	DMA_PLL = 3,
+	MESH_PLL = 4,
+	MME_PLL = 5,
+	TPC_PLL = 6,
+	IF_PLL = 7,
+	SRAM_PLL = 8,
+	NS_PLL = 9,
+	HBM_PLL = 10,
+	MSS_PLL = 11,
+	DDR_PLL = 12,
+	VID_PLL = 13,
+	BANK_PLL = 14,
+	MMU_PLL = 15,
+	IC_PLL = 16,
+	MC_PLL = 17,
+	EMMC_PLL = 18,
+	D2D_PLL = 19,
+	CS_PLL = 20,
+	C2C_PLL = 21,
+	NCH_PLL = 22,
+	C2M_PLL = 23,
+	PLL_MAX
+};
+
+enum rl_index {
+	TPC_RL = 0,
+	MME_RL,
+	EDMA_RL,
+};
+
+enum pvt_index {
+	PVT_SW,
+	PVT_SE,
+	PVT_NW,
+	PVT_NE
+};
+
+/* Event Queue Packets */
+
+struct eq_generic_event {
+	__le64 data[7];
+};
+
+/*
+ * CpuCP info
+ */
+
+#define CARD_NAME_MAX_LEN		16
+#define CPUCP_MAX_SENSORS		128
+#define CPUCP_MAX_NICS			128
+#define CPUCP_LANES_PER_NIC		4
+#define CPUCP_NIC_QSFP_EEPROM_MAX_LEN	1024
+#define CPUCP_MAX_NIC_LANES		(CPUCP_MAX_NICS * CPUCP_LANES_PER_NIC)
+#define CPUCP_NIC_MASK_ARR_LEN		((CPUCP_MAX_NICS + 63) / 64)
+#define CPUCP_NIC_POLARITY_ARR_LEN	((CPUCP_MAX_NIC_LANES + 63) / 64)
+#define CPUCP_HBM_ROW_REPLACE_MAX	32
+
+struct cpucp_sensor {
+	__le32 type;
+	__le32 flags;
+};
+
+/**
+ * struct cpucp_card_types - ASIC card type.
+ * @cpucp_card_type_pci: PCI card.
+ * @cpucp_card_type_pmc: PCI Mezzanine Card.
+ */
+enum cpucp_card_types {
+	cpucp_card_type_pci,
+	cpucp_card_type_pmc
+};
+
+#define CPUCP_SEC_CONF_ENABLED_SHIFT	0
+#define CPUCP_SEC_CONF_ENABLED_MASK	0x00000001
+
+#define CPUCP_SEC_CONF_FLASH_WP_SHIFT	1
+#define CPUCP_SEC_CONF_FLASH_WP_MASK	0x00000002
+
+#define CPUCP_SEC_CONF_EEPROM_WP_SHIFT	2
+#define CPUCP_SEC_CONF_EEPROM_WP_MASK	0x00000004
+
+/**
+ * struct cpucp_security_info - Security information.
+ * @config: configuration bit field
+ * @keys_num: number of stored keys
+ * @revoked_keys: revoked keys bit field
+ * @min_svn: minimal security version
+ */
+struct cpucp_security_info {
+	__u8 config;
+	__u8 keys_num;
+	__u8 revoked_keys;
+	__u8 min_svn;
+};
+
+/**
+ * struct cpucp_info - Info from CpuCP that is necessary to the host's driver
+ * @sensors: available sensors description.
+ * @kernel_version: CpuCP linux kernel version.
+ * @reserved: reserved field.
+ * @card_type: card configuration type.
+ * @card_location: in a server, each card has different connections topology
+ *                 depending on its location (relevant for PMC card type)
+ * @cpld_version: CPLD programmed F/W version.
+ * @infineon_version: Infineon main DC-DC version.
+ * @fuse_version: silicon production FUSE information.
+ * @thermal_version: thermald S/W version.
+ * @cpucp_version: CpuCP S/W version.
+ * @infineon_second_stage_version: Infineon 2nd stage DC-DC version.
+ * @dram_size: available DRAM size.
+ * @card_name: card name that will be displayed in HWMON subsystem on the host
+ * @tpc_binning_mask: TPC binning mask, 1 bit per TPC instance
+ *                    (0 = functional, 1 = binned)
+ * @decoder_binning_mask: Decoder binning mask, 1 bit per decoder instance
+ *                        (0 = functional, 1 = binned), maximum 1 per dcore
+ * @sram_binning: Categorize SRAM functionality
+ *                (0 = fully functional, 1 = lower-half is not functional,
+ *                 2 = upper-half is not functional)
+ * @sec_info: security information
+ * @cpld_timestamp: CPLD programmed F/W timestamp.
+ * @pll_map: Bit map of supported PLLs for current ASIC version.
+ * @mme_binning_mask: MME binning mask,
+ *                    bits [0:6]   <==> dcore0 mme fma
+ *                    bits [7:13]  <==> dcore1 mme fma
+ *                    bits [14:20] <==> dcore0 mme ima
+ *                    bits [21:27] <==> dcore1 mme ima
+ *                    For each group, if the 6th bit is set then first 5 bits
+ *                    represent the col's idx [0-31], otherwise these bits are
+ *                    ignored, and col idx 32 is binned. 7th bit is don't care.
+ * @dram_binning_mask: DRAM binning mask, 1 bit per dram instance
+ *                     (0 = functional 1 = binned)
+ * @memory_repair_flag: eFuse flag indicating memory repair
+ * @edma_binning_mask: EDMA binning mask, 1 bit per EDMA instance
+ *                     (0 = functional 1 = binned)
+ * @xbar_binning_mask: Xbar binning mask, 1 bit per Xbar instance
+ *                     (0 = functional 1 = binned)
+ * @interposer_version: Interposer version programmed in eFuse
+ * @substrate_version: Substrate version programmed in eFuse
+ * @eq_health_check_supported: eq health check feature supported in FW.
+ * @fw_hbm_region_size: Size in bytes of FW reserved region in HBM.
+ * @fw_os_version: Firmware OS Version
+ */
+struct cpucp_info {
+	struct cpucp_sensor sensors[CPUCP_MAX_SENSORS];
+	__u8 kernel_version[VERSION_MAX_LEN];
+	__le32 reserved1;
+	__le32 card_type;
+	__le32 card_location;
+	__le32 cpld_version;
+	__le32 infineon_version;
+	__u8 fuse_version[VERSION_MAX_LEN];
+	__u8 thermal_version[VERSION_MAX_LEN];
+	__u8 cpucp_version[VERSION_MAX_LEN];
+	__le32 infineon_second_stage_version;
+	__le64 dram_size;
+	char card_name[CARD_NAME_MAX_LEN];
+	__le64 tpc_binning_mask;
+	__le64 decoder_binning_mask;
+	__u8 sram_binning;
+	__u8 dram_binning_mask;
+	__u8 memory_repair_flag;
+	__u8 edma_binning_mask;
+	__u8 xbar_binning_mask;
+	__u8 interposer_version;
+	__u8 substrate_version;
+	__u8 eq_health_check_supported;
+	struct cpucp_security_info sec_info;
+	__le32 cpld_timestamp;
+	__u8 pll_map[PLL_MAP_LEN];
+	__le64 mme_binning_mask;
+	__u8 fw_os_version[VERSION_MAX_LEN];
+};
+
+struct cpucp_mac_addr {
+	__u8 mac_addr[ETH_ALEN];
+};
+
+enum cpucp_serdes_type {
+	TYPE_1_SERDES_TYPE,
+	TYPE_2_SERDES_TYPE,
+	HLS1_SERDES_TYPE,
+	HLS1H_SERDES_TYPE,
+	HLS2_SERDES_TYPE,
+	HLS2_TYPE_1_SERDES_TYPE,
+	MAX_NUM_SERDES_TYPE,		/* number of types */
+	UNKNOWN_SERDES_TYPE = 0xFFFF	/* serdes_type is u16 */
+};
+
+struct cpucp_nic_info {
+	struct cpucp_mac_addr mac_addrs[CPUCP_MAX_NICS];
+	__le64 link_mask[CPUCP_NIC_MASK_ARR_LEN];
+	__le64 pol_tx_mask[CPUCP_NIC_POLARITY_ARR_LEN];
+	__le64 pol_rx_mask[CPUCP_NIC_POLARITY_ARR_LEN];
+	__le64 link_ext_mask[CPUCP_NIC_MASK_ARR_LEN];
+	__u8 qsfp_eeprom[CPUCP_NIC_QSFP_EEPROM_MAX_LEN];
+	__le64 auto_neg_mask[CPUCP_NIC_MASK_ARR_LEN];
+	__le16 serdes_type; /* enum cpucp_serdes_type */
+	__le16 tx_swap_map[CPUCP_MAX_NICS];
+	__u8 reserved[6];
+};
+
+#define PAGE_DISCARD_MAX	64
+
+struct page_discard_info {
+	__u8 num_entries;
+	__u8 reserved[7];
+	__le32 mmu_page_idx[PAGE_DISCARD_MAX];
+};
+
+/*
+ * struct frac_val - fracture value represented by "integer.frac".
+ * @integer: the integer part of the fracture value;
+ * @frac: the fracture part of the fracture value.
+ */
+struct frac_val {
+	union {
+		struct {
+			__le16 integer;
+			__le16 frac;
+		};
+		__le32 val;
+	};
+};
+
+/*
+ * struct ser_val - the SER (symbol error rate) value is represented by "integer * 10 ^ -exp".
+ * @integer: the integer part of the SER value;
+ * @exp: the exponent part of the SER value.
+ */
+struct ser_val {
+	__le16 integer;
+	__le16 exp;
+};
+
+/*
+ * struct cpucp_nic_status - describes the status of a NIC port.
+ * @port: NIC port index.
+ * @bad_format_cnt: e.g. CRC.
+ * @responder_out_of_sequence_psn_cnt: e.g NAK.
+ * @high_ber_reinit_cnt: link reinit due to high BER.
+ * @correctable_err_cnt: e.g. bit-flip.
+ * @uncorrectable_err_cnt: e.g. MAC errors.
+ * @retraining_cnt: re-training counter.
+ * @up: is port up.
+ * @pcs_link: has PCS link.
+ * @phy_ready: is PHY ready.
+ * @auto_neg: is Autoneg enabled.
+ * @timeout_retransmission_cnt: timeout retransmission events.
+ * @high_ber_cnt: high ber events.
+ * @pre_fec_ser: pre FEC SER value.
+ * @post_fec_ser: post FEC SER value.
+ * @throughput: measured throughput.
+ * @latency: measured latency.
+ */
+struct cpucp_nic_status {
+	__le32 port;
+	__le32 bad_format_cnt;
+	__le32 responder_out_of_sequence_psn_cnt;
+	__le32 high_ber_reinit;
+	__le32 correctable_err_cnt;
+	__le32 uncorrectable_err_cnt;
+	__le32 retraining_cnt;
+	__u8 up;
+	__u8 pcs_link;
+	__u8 phy_ready;
+	__u8 auto_neg;
+	__le32 timeout_retransmission_cnt;
+	__le32 high_ber_cnt;
+	struct ser_val pre_fec_ser;
+	struct ser_val post_fec_ser;
+	struct frac_val bandwidth;
+	struct frac_val lat;
+};
+
+enum cpucp_hbm_row_replace_cause {
+	REPLACE_CAUSE_DOUBLE_ECC_ERR,
+	REPLACE_CAUSE_MULTI_SINGLE_ECC_ERR,
+};
+
+struct cpucp_hbm_row_info {
+	__u8 hbm_idx;
+	__u8 pc;
+	__u8 sid;
+	__u8 bank_idx;
+	__le16 row_addr;
+	__u8 replaced_row_cause; /* enum cpucp_hbm_row_replace_cause */
+	__u8 pad;
+};
+
+struct cpucp_hbm_row_replaced_rows_info {
+	__le16 num_replaced_rows;
+	__u8 pad[6];
+	struct cpucp_hbm_row_info replaced_rows[CPUCP_HBM_ROW_REPLACE_MAX];
+};
+
+enum cpu_reset_status {
+	CPU_RST_STATUS_NA = 0,
+	CPU_RST_STATUS_SOFT_RST_DONE = 1,
+};
+
+#define SEC_PCR_DATA_BUF_SZ	256
+#define SEC_PCR_QUOTE_BUF_SZ	510	/* (512 - 2) 2 bytes used for size */
+#define SEC_SIGNATURE_BUF_SZ	255	/* (256 - 1) 1 byte used for size */
+#define SEC_PUB_DATA_BUF_SZ	510	/* (512 - 2) 2 bytes used for size */
+#define SEC_CERTIFICATE_BUF_SZ	2046	/* (2048 - 2) 2 bytes used for size */
+
+/*
+ * struct cpucp_sec_attest_info - attestation report of the boot
+ * @pcr_data: raw values of the PCR registers
+ * @pcr_num_reg: number of PCR registers in the pcr_data array
+ * @pcr_reg_len: length of each PCR register in the pcr_data array (bytes)
+ * @nonce: number only used once. random number provided by host. this also
+ *	    passed to the quote command as a qualifying data.
+ * @pcr_quote_len: length of the attestation quote data (bytes)
+ * @pcr_quote: attestation report data structure
+ * @quote_sig_len: length of the attestation report signature (bytes)
+ * @quote_sig: signature structure of the attestation report
+ * @pub_data_len: length of the public data (bytes)
+ * @public_data: public key for the signed attestation
+ *		 (outPublic + name + qualifiedName)
+ * @certificate_len: length of the certificate (bytes)
+ * @certificate: certificate for the attestation signing key
+ */
+struct cpucp_sec_attest_info {
+	__u8 pcr_data[SEC_PCR_DATA_BUF_SZ];
+	__u8 pcr_num_reg;
+	__u8 pcr_reg_len;
+	__le16 pad0;
+	__le32 nonce;
+	__le16 pcr_quote_len;
+	__u8 pcr_quote[SEC_PCR_QUOTE_BUF_SZ];
+	__u8 quote_sig_len;
+	__u8 quote_sig[SEC_SIGNATURE_BUF_SZ];
+	__le16 pub_data_len;
+	__u8 public_data[SEC_PUB_DATA_BUF_SZ];
+	__le16 certificate_len;
+	__u8 certificate[SEC_CERTIFICATE_BUF_SZ];
+};
+
+/*
+ * struct cpucp_dev_info_signed - device information signed by a secured device
+ * @info: device information structure as defined above
+ * @nonce: number only used once. random number provided by host. this number is
+ *	   hashed and signed along with the device information.
+ * @info_sig_len: length of the attestation signature (bytes)
+ * @info_sig: signature of the info + nonce data.
+ * @pub_data_len: length of the public data (bytes)
+ * @public_data: public key info signed info data
+ *		 (outPublic + name + qualifiedName)
+ * @certificate_len: length of the certificate (bytes)
+ * @certificate: certificate for the signing key
+ */
+struct cpucp_dev_info_signed {
+	struct cpucp_info info;	/* assumed to be 64bit aligned */
+	__le32 nonce;
+	__le32 pad0;
+	__u8 info_sig_len;
+	__u8 info_sig[SEC_SIGNATURE_BUF_SZ];
+	__le16 pub_data_len;
+	__u8 public_data[SEC_PUB_DATA_BUF_SZ];
+	__le16 certificate_len;
+	__u8 certificate[SEC_CERTIFICATE_BUF_SZ];
+};
+
+#define DCORE_MON_REGS_SZ	512
+/*
+ * struct dcore_monitor_regs_data - DCORE monitor regs data.
+ * the structure follows sync manager block layout. Obsolete.
+ * @mon_pay_addrl: array of payload address low bits.
+ * @mon_pay_addrh: array of payload address high bits.
+ * @mon_pay_data: array of payload data.
+ * @mon_arm: array of monitor arm.
+ * @mon_status: array of monitor status.
+ */
+struct dcore_monitor_regs_data {
+	__le32 mon_pay_addrl[DCORE_MON_REGS_SZ];
+	__le32 mon_pay_addrh[DCORE_MON_REGS_SZ];
+	__le32 mon_pay_data[DCORE_MON_REGS_SZ];
+	__le32 mon_arm[DCORE_MON_REGS_SZ];
+	__le32 mon_status[DCORE_MON_REGS_SZ];
+};
+
+/* contains SM data for each SYNC_MNGR (Obsolete) */
+struct cpucp_monitor_dump {
+	struct dcore_monitor_regs_data sync_mngr_w_s;
+	struct dcore_monitor_regs_data sync_mngr_e_s;
+	struct dcore_monitor_regs_data sync_mngr_w_n;
+	struct dcore_monitor_regs_data sync_mngr_e_n;
+};
+
+/*
+ * The Type of the generic request (and other input arguments) will be fetched from user by reading
+ * from "pkt_subidx" field in struct cpucp_packet.
+ *
+ * HL_PASSTHROUGHT_VERSIONS	- Fetch all firmware versions.
+ * HL_GET_ERR_COUNTERS_CMD	- Command to get error counters
+ * HL_GET_P_STATE		- get performance state
+ */
+enum hl_passthrough_type {
+	HL_PASSTHROUGH_VERSIONS,
+	HL_GET_ERR_COUNTERS_CMD,
+	HL_GET_P_STATE,
+};
+
+#endif /* CPUCP_IF_H */
diff --git a/include/linux/habanalabs/hl_boot_if.h b/include/linux/habanalabs/hl_boot_if.h
new file mode 100644
index 000000000000..af5fb4ad77eb
--- /dev/null
+++ b/include/linux/habanalabs/hl_boot_if.h
@@ -0,0 +1,807 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Copyright 2018-2023 HabanaLabs, Ltd.
+ * All Rights Reserved.
+ *
+ */
+
+#ifndef HL_BOOT_IF_H
+#define HL_BOOT_IF_H
+
+#define LKD_HARD_RESET_MAGIC		0xED7BD694 /* deprecated - do not use */
+#define HL_POWER9_HOST_MAGIC		0x1DA30009
+
+#define BOOT_FIT_SRAM_OFFSET		0x200000
+
+#define VERSION_MAX_LEN			128
+
+enum cpu_boot_err {
+	CPU_BOOT_ERR_DRAM_INIT_FAIL = 0,
+	CPU_BOOT_ERR_FIT_CORRUPTED = 1,
+	CPU_BOOT_ERR_TS_INIT_FAIL = 2,
+	CPU_BOOT_ERR_DRAM_SKIPPED = 3,
+	CPU_BOOT_ERR_BMC_WAIT_SKIPPED = 4,
+	CPU_BOOT_ERR_NIC_DATA_NOT_RDY = 5,
+	CPU_BOOT_ERR_NIC_FW_FAIL = 6,
+	CPU_BOOT_ERR_SECURITY_NOT_RDY = 7,
+	CPU_BOOT_ERR_SECURITY_FAIL = 8,
+	CPU_BOOT_ERR_EFUSE_FAIL = 9,
+	CPU_BOOT_ERR_PRI_IMG_VER_FAIL = 10,
+	CPU_BOOT_ERR_SEC_IMG_VER_FAIL = 11,
+	CPU_BOOT_ERR_PLL_FAIL = 12,
+	CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL = 13,
+	CPU_BOOT_ERR_BOOT_FW_CRIT_ERR = 18,
+	CPU_BOOT_ERR_BINNING_FAIL = 19,
+	CPU_BOOT_ERR_TPM_FAIL = 20,
+	CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL = 21,
+	CPU_BOOT_ERR_EEPROM_FAIL = 22,
+	CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL = 23,
+	CPU_BOOT_ERR_ENABLED = 31,
+	CPU_BOOT_ERR_SCND_EN = 63,
+	CPU_BOOT_ERR_LAST = 64 /* we have 2 registers of 32 bits */
+};
+
+/*
+ * Mask for fatal failures
+ * This mask contains all possible fatal failures, and a dynamic code
+ * will clear the non-relevant ones.
+ */
+#define CPU_BOOT_ERR_FATAL_MASK					\
+		((1 << CPU_BOOT_ERR_DRAM_INIT_FAIL) |		\
+		 (1 << CPU_BOOT_ERR_PLL_FAIL) |			\
+		 (1 << CPU_BOOT_ERR_BINNING_FAIL) |		\
+		 (1 << CPU_BOOT_ERR_DRAM_SKIPPED) |		\
+		 (1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL) |	\
+		 (1 << CPU_BOOT_ERR_EEPROM_FAIL))
+
+/*
+ * CPU error bits in BOOT_ERROR registers
+ *
+ * CPU_BOOT_ERR0_DRAM_INIT_FAIL		DRAM initialization failed.
+ *					DRAM is not reliable to use.
+ *
+ * CPU_BOOT_ERR0_FIT_CORRUPTED		FIT data integrity verification of the
+ *					image provided by the host has failed.
+ *
+ * CPU_BOOT_ERR0_TS_INIT_FAIL		Thermal Sensor initialization failed.
+ *					Boot continues as usual, but keep in
+ *					mind this is a warning.
+ *
+ * CPU_BOOT_ERR0_DRAM_SKIPPED		DRAM initialization has been skipped.
+ *					Skipping DRAM initialization has been
+ *					requested (e.g. strap, command, etc.)
+ *					and FW skipped the DRAM initialization.
+ *					Host can initialize the DRAM.
+ *
+ * CPU_BOOT_ERR0_BMC_WAIT_SKIPPED	Waiting for BMC data will be skipped.
+ *					Meaning the BMC data might not be
+ *					available until reset.
+ *
+ * CPU_BOOT_ERR0_NIC_DATA_NOT_RDY	NIC data from BMC is not ready.
+ *					BMC has not provided the NIC data yet.
+ *					Once provided this bit will be cleared.
+ *
+ * CPU_BOOT_ERR0_NIC_FW_FAIL		NIC FW loading failed.
+ *					The NIC FW loading and initialization
+ *					failed. This means NICs are not usable.
+ *
+ * CPU_BOOT_ERR0_SECURITY_NOT_RDY	Chip security initialization has been
+ *					started, but is not ready yet - chip
+ *					cannot be accessed.
+ *
+ * CPU_BOOT_ERR0_SECURITY_FAIL		Security related tasks have failed.
+ *					The tasks are security init (root of
+ *					trust), boot authentication (chain of
+ *					trust), data packets authentication.
+ *
+ * CPU_BOOT_ERR0_EFUSE_FAIL		Reading from eFuse failed.
+ *					The PCI device ID might be wrong.
+ *
+ * CPU_BOOT_ERR0_PRI_IMG_VER_FAIL	Verification of primary image failed.
+ *					It mean that ppboot checksum
+ *					verification for the preboot primary
+ *					image has failed to match expected
+ *					checksum. Trying to program image again
+ *					might solve this.
+ *
+ * CPU_BOOT_ERR0_SEC_IMG_VER_FAIL	Verification of secondary image failed.
+ *					It mean that ppboot checksum
+ *					verification for the preboot secondary
+ *					image has failed to match expected
+ *					checksum. Trying to program image again
+ *					might solve this.
+ *
+ * CPU_BOOT_ERR0_PLL_FAIL		PLL settings failed, meaning that one
+ *					of the PLLs remains in REF_CLK
+ *
+ * CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL	Device is unusable and customer support
+ *					should be contacted.
+ *
+ * CPU_BOOT_ERR0_BOOT_FW_CRIT_ERR	Critical error was detected during
+ *					the execution of ppboot or preboot.
+ *					for example: stack overflow.
+ *
+ * CPU_BOOT_ERR0_BINNING_FAIL		Binning settings failed, meaning
+ *					malfunctioning components might still be
+ *					in use.
+ *
+ * CPU_BOOT_ERR0_TPM_FAIL		TPM verification flow failed.
+ *
+ * CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL	Failed to set threshold for tmperature
+ *					sensor.
+ *
+ * CPU_BOOT_ERR_EEPROM_FAIL		Failed reading EEPROM data. Defaults
+ *					are used.
+ *
+ * CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL	Failed scrubbing the Engines/ARCFarm
+ *					memories. Boot disabled until reset.
+ *
+ * CPU_BOOT_ERR0_ENABLED		Error registers enabled.
+ *					This is a main indication that the
+ *					running FW populates the error
+ *					registers. Meaning the error bits are
+ *					not garbage, but actual error statuses.
+ */
+#define CPU_BOOT_ERR0_DRAM_INIT_FAIL		(1 << CPU_BOOT_ERR_DRAM_INIT_FAIL)
+#define CPU_BOOT_ERR0_FIT_CORRUPTED		(1 << CPU_BOOT_ERR_FIT_CORRUPTED)
+#define CPU_BOOT_ERR0_TS_INIT_FAIL		(1 << CPU_BOOT_ERR_TS_INIT_FAIL)
+#define CPU_BOOT_ERR0_DRAM_SKIPPED		(1 << CPU_BOOT_ERR_DRAM_SKIPPED)
+#define CPU_BOOT_ERR0_BMC_WAIT_SKIPPED		(1 << CPU_BOOT_ERR_BMC_WAIT_SKIPPED)
+#define CPU_BOOT_ERR0_NIC_DATA_NOT_RDY		(1 << CPU_BOOT_ERR_NIC_DATA_NOT_RDY)
+#define CPU_BOOT_ERR0_NIC_FW_FAIL		(1 << CPU_BOOT_ERR_NIC_FW_FAIL)
+#define CPU_BOOT_ERR0_SECURITY_NOT_RDY		(1 << CPU_BOOT_ERR_SECURITY_NOT_RDY)
+#define CPU_BOOT_ERR0_SECURITY_FAIL		(1 << CPU_BOOT_ERR_SECURITY_FAIL)
+#define CPU_BOOT_ERR0_EFUSE_FAIL		(1 << CPU_BOOT_ERR_EFUSE_FAIL)
+#define CPU_BOOT_ERR0_PRI_IMG_VER_FAIL		(1 << CPU_BOOT_ERR_PRI_IMG_VER_FAIL)
+#define CPU_BOOT_ERR0_SEC_IMG_VER_FAIL		(1 << CPU_BOOT_ERR_SEC_IMG_VER_FAIL)
+#define CPU_BOOT_ERR0_PLL_FAIL			(1 << CPU_BOOT_ERR_PLL_FAIL)
+#define CPU_BOOT_ERR0_DEVICE_UNUSABLE_FAIL	(1 << CPU_BOOT_ERR_DEVICE_UNUSABLE_FAIL)
+#define CPU_BOOT_ERR0_BOOT_FW_CRIT_ERR		(1 << CPU_BOOT_ERR_BOOT_FW_CRIT_ERR)
+#define CPU_BOOT_ERR0_BINNING_FAIL		(1 << CPU_BOOT_ERR_BINNING_FAIL)
+#define CPU_BOOT_ERR0_TPM_FAIL			(1 << CPU_BOOT_ERR_TPM_FAIL)
+#define CPU_BOOT_ERR0_TMP_THRESH_INIT_FAIL	(1 << CPU_BOOT_ERR_TMP_THRESH_INIT_FAIL)
+#define CPU_BOOT_ERR0_EEPROM_FAIL		(1 << CPU_BOOT_ERR_EEPROM_FAIL)
+#define CPU_BOOT_ERR0_ENG_ARC_MEM_SCRUB_FAIL	(1 << CPU_BOOT_ERR_ENG_ARC_MEM_SCRUB_FAIL)
+#define CPU_BOOT_ERR0_ENABLED			(1 << CPU_BOOT_ERR_ENABLED)
+#define CPU_BOOT_ERR1_ENABLED			(1 << CPU_BOOT_ERR_ENABLED)
+
+enum cpu_boot_dev_sts {
+	CPU_BOOT_DEV_STS_SECURITY_EN = 0,
+	CPU_BOOT_DEV_STS_DEBUG_EN = 1,
+	CPU_BOOT_DEV_STS_WATCHDOG_EN = 2,
+	CPU_BOOT_DEV_STS_DRAM_INIT_EN = 3,
+	CPU_BOOT_DEV_STS_BMC_WAIT_EN = 4,
+	CPU_BOOT_DEV_STS_E2E_CRED_EN = 5,
+	CPU_BOOT_DEV_STS_HBM_CRED_EN = 6,
+	CPU_BOOT_DEV_STS_RL_EN = 7,
+	CPU_BOOT_DEV_STS_SRAM_SCR_EN = 8,
+	CPU_BOOT_DEV_STS_DRAM_SCR_EN = 9,
+	CPU_BOOT_DEV_STS_FW_HARD_RST_EN = 10,
+	CPU_BOOT_DEV_STS_PLL_INFO_EN = 11,
+	CPU_BOOT_DEV_STS_SP_SRAM_EN = 12,
+	CPU_BOOT_DEV_STS_CLK_GATE_EN = 13,
+	CPU_BOOT_DEV_STS_HBM_ECC_EN = 14,
+	CPU_BOOT_DEV_STS_PKT_PI_ACK_EN = 15,
+	CPU_BOOT_DEV_STS_FW_LD_COM_EN = 16,
+	CPU_BOOT_DEV_STS_FW_IATU_CONF_EN = 17,
+	CPU_BOOT_DEV_STS_FW_NIC_MAC_EN = 18,
+	CPU_BOOT_DEV_STS_DYN_PLL_EN = 19,
+	CPU_BOOT_DEV_STS_GIC_PRIVILEGED_EN = 20,
+	CPU_BOOT_DEV_STS_EQ_INDEX_EN = 21,
+	CPU_BOOT_DEV_STS_MULTI_IRQ_POLL_EN = 22,
+	CPU_BOOT_DEV_STS_FW_NIC_STAT_XPCS91_EN = 23,
+	CPU_BOOT_DEV_STS_FW_NIC_STAT_EXT_EN = 24,
+	CPU_BOOT_DEV_STS_IS_IDLE_CHECK_EN = 25,
+	CPU_BOOT_DEV_STS_MAP_HWMON_EN = 26,
+	CPU_BOOT_DEV_STS_NIC_MEM_CLEAR_EN = 27,
+	CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN = 28,
+	CPU_BOOT_DEV_STS_ENABLED = 31,
+	CPU_BOOT_DEV_STS_SCND_EN = 63,
+	CPU_BOOT_DEV_STS_LAST = 64 /* we have 2 registers of 32 bits */
+};
+
+/*
+ * BOOT DEVICE STATUS bits in BOOT_DEVICE_STS registers
+ *
+ * CPU_BOOT_DEV_STS0_SECURITY_EN	Security is Enabled.
+ *					This is an indication for security
+ *					enabled in FW, which means that
+ *					all conditions for security are met:
+ *					device is indicated as security enabled,
+ *					registers are protected, and device
+ *					uses keys for image verification.
+ *					Initialized in: preboot
+ *
+ * CPU_BOOT_DEV_STS0_DEBUG_EN		Debug is enabled.
+ *					Enabled when JTAG or DEBUG is enabled
+ *					in FW.
+ *					Initialized in: preboot
+ *
+ * CPU_BOOT_DEV_STS0_WATCHDOG_EN	Watchdog is enabled.
+ *					Watchdog is enabled in FW.
+ *					Initialized in: preboot
+ *
+ * CPU_BOOT_DEV_STS0_DRAM_INIT_EN	DRAM initialization is enabled.
+ *					DRAM initialization has been done in FW.
+ *					Initialized in: u-boot
+ *
+ * CPU_BOOT_DEV_STS0_BMC_WAIT_EN	Waiting for BMC data enabled.
+ *					If set, it means that during boot,
+ *					FW waited for BMC data.
+ *					Initialized in: u-boot
+ *
+ * CPU_BOOT_DEV_STS0_E2E_CRED_EN	E2E credits initialized.
+ *					FW initialized E2E credits.
+ *					Initialized in: u-boot
+ *
+ * CPU_BOOT_DEV_STS0_HBM_CRED_EN	HBM credits initialized.
+ *					FW initialized HBM credits.
+ *					Initialized in: u-boot
+ *
+ * CPU_BOOT_DEV_STS0_RL_EN		Rate limiter initialized.
+ *					FW initialized rate limiter.
+ *					Initialized in: u-boot
+ *
+ * CPU_BOOT_DEV_STS0_SRAM_SCR_EN	SRAM scrambler enabled.
+ *					FW initialized SRAM scrambler.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_DRAM_SCR_EN	DRAM scrambler enabled.
+ *					FW initialized DRAM scrambler.
+ *					Initialized in: u-boot
+ *
+ * CPU_BOOT_DEV_STS0_FW_HARD_RST_EN	FW hard reset procedure is enabled.
+ *					FW has the hard reset procedure
+ *					implemented. This means that FW will
+ *					perform hard reset procedure on
+ *					receiving the halt-machine event.
+ *					Initialized in: preboot, u-boot, linux
+ *
+ * CPU_BOOT_DEV_STS0_PLL_INFO_EN	FW retrieval of PLL info is enabled.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_SP_SRAM_EN		SP SRAM is initialized and available
+ *					for use.
+ *					Initialized in: preboot
+ *
+ * CPU_BOOT_DEV_STS0_CLK_GATE_EN	Clock Gating enabled.
+ *					FW initialized Clock Gating.
+ *					Initialized in: preboot
+ *
+ * CPU_BOOT_DEV_STS0_HBM_ECC_EN		HBM ECC handling Enabled.
+ *					FW handles HBM ECC indications.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN	Packets ack value used in the armcpd
+ *					is set to the PI counter.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_FW_LD_COM_EN	Flexible FW loading communication
+ *					protocol is enabled.
+ *					Initialized in: preboot
+ *
+ * CPU_BOOT_DEV_STS0_FW_IATU_CONF_EN	FW iATU configuration is enabled.
+ *					This bit if set, means the iATU has been
+ *					configured and is ready for use.
+ *					Initialized in: ppboot
+ *
+ * CPU_BOOT_DEV_STS0_FW_NIC_MAC_EN	NIC MAC channels init is done by FW and
+ *					any access to them is done via the FW.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_DYN_PLL_EN		Dynamic PLL configuration is enabled.
+ *					FW sends to host a bitmap of supported
+ *					PLLs.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_GIC_PRIVILEGED_EN	GIC access permission only from
+ *					privileged entity. FW sets this status
+ *					bit for host. If this bit is set then
+ *					GIC can not be accessed from host.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_EQ_INDEX_EN	Event Queue (EQ) index is a running
+ *					index for each new event sent to host.
+ *					This is used as a method in host to
+ *					identify that the waiting event in
+ *					queue is actually a new event which
+ *					was not served before.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_MULTI_IRQ_POLL_EN	Use multiple scratchpad interfaces to
+ *					prevent IRQs overriding each other.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_FW_NIC_STAT_XPCS91_EN
+ *					NIC STAT and XPCS91 access is restricted
+ *					and is done via FW only.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_FW_NIC_STAT_EXT_EN
+ *					NIC STAT get all is supported.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_IS_IDLE_CHECK_EN
+ *					F/W checks if the device is idle by reading defined set
+ *					of registers. It returns a bitmask of all the engines,
+ *					where a bit is set if the engine is not idle.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_MAP_HWMON_EN
+ *					If set, means f/w supports proprietary
+ *					HWMON enum mapping to cpucp enums.
+ *					Initialized in: linux
+ *
+ * CPU_BOOT_DEV_STS0_NIC_MEM_CLEAR_EN
+ *					If set, means f/w supports nic hbm memory clear and
+ *					tmr,txs hbm memory init.
+ *					Initialized in: zephyr-mgmt
+ *
+ * CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN
+ *					MMU page tables are located in DRAM.
+ *					F/W initializes security settings for MMU
+ *					page tables to reside in DRAM.
+ *					Initialized in: zephyr-mgmt
+ *
+ * CPU_BOOT_DEV_STS0_ENABLED		Device status register enabled.
+ *					This is a main indication that the
+ *					running FW populates the device status
+ *					register. Meaning the device status
+ *					bits are not garbage, but actual
+ *					statuses.
+ *					Initialized in: preboot
+ *
+ */
+#define CPU_BOOT_DEV_STS0_SECURITY_EN		(1 << CPU_BOOT_DEV_STS_SECURITY_EN)
+#define CPU_BOOT_DEV_STS0_DEBUG_EN		(1 << CPU_BOOT_DEV_STS_DEBUG_EN)
+#define CPU_BOOT_DEV_STS0_WATCHDOG_EN		(1 << CPU_BOOT_DEV_STS_WATCHDOG_EN)
+#define CPU_BOOT_DEV_STS0_DRAM_INIT_EN		(1 << CPU_BOOT_DEV_STS_DRAM_INIT_EN)
+#define CPU_BOOT_DEV_STS0_BMC_WAIT_EN		(1 << CPU_BOOT_DEV_STS_BMC_WAIT_EN)
+#define CPU_BOOT_DEV_STS0_E2E_CRED_EN		(1 << CPU_BOOT_DEV_STS_E2E_CRED_EN)
+#define CPU_BOOT_DEV_STS0_HBM_CRED_EN		(1 << CPU_BOOT_DEV_STS_HBM_CRED_EN)
+#define CPU_BOOT_DEV_STS0_RL_EN			(1 << CPU_BOOT_DEV_STS_RL_EN)
+#define CPU_BOOT_DEV_STS0_SRAM_SCR_EN		(1 << CPU_BOOT_DEV_STS_SRAM_SCR_EN)
+#define CPU_BOOT_DEV_STS0_DRAM_SCR_EN		(1 << CPU_BOOT_DEV_STS_DRAM_SCR_EN)
+#define CPU_BOOT_DEV_STS0_FW_HARD_RST_EN	(1 << CPU_BOOT_DEV_STS_FW_HARD_RST_EN)
+#define CPU_BOOT_DEV_STS0_PLL_INFO_EN		(1 << CPU_BOOT_DEV_STS_PLL_INFO_EN)
+#define CPU_BOOT_DEV_STS0_SP_SRAM_EN		(1 << CPU_BOOT_DEV_STS_SP_SRAM_EN)
+#define CPU_BOOT_DEV_STS0_CLK_GATE_EN		(1 << CPU_BOOT_DEV_STS_CLK_GATE_EN)
+#define CPU_BOOT_DEV_STS0_HBM_ECC_EN		(1 << CPU_BOOT_DEV_STS_HBM_ECC_EN)
+#define CPU_BOOT_DEV_STS0_PKT_PI_ACK_EN		(1 << CPU_BOOT_DEV_STS_PKT_PI_ACK_EN)
+#define CPU_BOOT_DEV_STS0_FW_LD_COM_EN		(1 << CPU_BOOT_DEV_STS_FW_LD_COM_EN)
+#define CPU_BOOT_DEV_STS0_FW_IATU_CONF_EN	(1 << CPU_BOOT_DEV_STS_FW_IATU_CONF_EN)
+#define CPU_BOOT_DEV_STS0_FW_NIC_MAC_EN		(1 << CPU_BOOT_DEV_STS_FW_NIC_MAC_EN)
+#define CPU_BOOT_DEV_STS0_DYN_PLL_EN		(1 << CPU_BOOT_DEV_STS_DYN_PLL_EN)
+#define CPU_BOOT_DEV_STS0_GIC_PRIVILEGED_EN	(1 << CPU_BOOT_DEV_STS_GIC_PRIVILEGED_EN)
+#define CPU_BOOT_DEV_STS0_EQ_INDEX_EN		(1 << CPU_BOOT_DEV_STS_EQ_INDEX_EN)
+#define CPU_BOOT_DEV_STS0_MULTI_IRQ_POLL_EN	(1 << CPU_BOOT_DEV_STS_MULTI_IRQ_POLL_EN)
+#define CPU_BOOT_DEV_STS0_FW_NIC_STAT_XPCS91_EN	(1 << CPU_BOOT_DEV_STS_FW_NIC_STAT_XPCS91_EN)
+#define CPU_BOOT_DEV_STS0_FW_NIC_STAT_EXT_EN	(1 << CPU_BOOT_DEV_STS_FW_NIC_STAT_EXT_EN)
+#define CPU_BOOT_DEV_STS0_IS_IDLE_CHECK_EN	(1 << CPU_BOOT_DEV_STS_IS_IDLE_CHECK_EN)
+#define CPU_BOOT_DEV_STS0_MAP_HWMON_EN		(1 << CPU_BOOT_DEV_STS_MAP_HWMON_EN)
+#define CPU_BOOT_DEV_STS0_NIC_MEM_CLEAR_EN	(1 << CPU_BOOT_DEV_STS_NIC_MEM_CLEAR_EN)
+#define CPU_BOOT_DEV_STS0_MMU_PGTBL_DRAM_EN	(1 << CPU_BOOT_DEV_STS_MMU_PGTBL_DRAM_EN)
+#define CPU_BOOT_DEV_STS0_ENABLED		(1 << CPU_BOOT_DEV_STS_ENABLED)
+#define CPU_BOOT_DEV_STS1_ENABLED		(1 << CPU_BOOT_DEV_STS_ENABLED)
+
+enum cpu_boot_status {
+	CPU_BOOT_STATUS_NA = 0,		/* Default value after reset of chip */
+	CPU_BOOT_STATUS_IN_WFE = 1,
+	CPU_BOOT_STATUS_DRAM_RDY = 2,
+	CPU_BOOT_STATUS_SRAM_AVAIL = 3,
+	CPU_BOOT_STATUS_IN_BTL = 4,	/* BTL is H/W FSM */
+	CPU_BOOT_STATUS_IN_PREBOOT = 5,
+	CPU_BOOT_STATUS_IN_SPL,		/* deprecated - not reported */
+	CPU_BOOT_STATUS_IN_UBOOT = 7,
+	CPU_BOOT_STATUS_DRAM_INIT_FAIL,	/* deprecated - will be removed */
+	CPU_BOOT_STATUS_FIT_CORRUPTED,	/* deprecated - will be removed */
+	/* U-Boot console prompt activated, commands are not processed */
+	CPU_BOOT_STATUS_UBOOT_NOT_READY = 10,
+	/* Finished NICs init, reported after DRAM and NICs */
+	CPU_BOOT_STATUS_NIC_FW_RDY = 11,
+	CPU_BOOT_STATUS_TS_INIT_FAIL,	/* deprecated - will be removed */
+	CPU_BOOT_STATUS_DRAM_SKIPPED,	/* deprecated - will be removed */
+	CPU_BOOT_STATUS_BMC_WAITING_SKIPPED, /* deprecated - will be removed */
+	/* Last boot loader progress status, ready to receive commands */
+	CPU_BOOT_STATUS_READY_TO_BOOT = 15,
+	/* Internal Boot finished, ready for boot-fit */
+	CPU_BOOT_STATUS_WAITING_FOR_BOOT_FIT = 16,
+	/* Internal Security has been initialized, device can be accessed */
+	CPU_BOOT_STATUS_SECURITY_READY = 17,
+	/* FW component is preparing to shutdown and communication with host is not available */
+	CPU_BOOT_STATUS_FW_SHUTDOWN_PREP = 18,
+};
+
+enum kmd_msg {
+	KMD_MSG_NA = 0,
+	KMD_MSG_GOTO_WFE,
+	KMD_MSG_FIT_RDY,
+	KMD_MSG_SKIP_BMC,
+	RESERVED,
+	KMD_MSG_RST_DEV,
+	KMD_MSG_LAST
+};
+
+enum cpu_msg_status {
+	CPU_MSG_CLR = 0,
+	CPU_MSG_OK,
+	CPU_MSG_ERR,
+};
+
+/* communication registers mapping - consider ABI when changing */
+struct cpu_dyn_regs {
+	__le32 cpu_pq_base_addr_low;
+	__le32 cpu_pq_base_addr_high;
+	__le32 cpu_pq_length;
+	__le32 cpu_pq_init_status;
+	__le32 cpu_eq_base_addr_low;
+	__le32 cpu_eq_base_addr_high;
+	__le32 cpu_eq_length;
+	__le32 cpu_eq_ci;
+	__le32 cpu_cq_base_addr_low;
+	__le32 cpu_cq_base_addr_high;
+	__le32 cpu_cq_length;
+	__le32 cpu_pf_pq_pi;
+	__le32 cpu_boot_dev_sts0;
+	__le32 cpu_boot_dev_sts1;
+	__le32 cpu_boot_err0;
+	__le32 cpu_boot_err1;
+	__le32 cpu_boot_status;
+	__le32 fw_upd_sts;
+	__le32 fw_upd_cmd;
+	__le32 fw_upd_pending_sts;
+	__le32 fuse_ver_offset;
+	__le32 preboot_ver_offset;
+	__le32 uboot_ver_offset;
+	__le32 hw_state;
+	__le32 kmd_msg_to_cpu;
+	__le32 cpu_cmd_status_to_host;
+	__le32 gic_host_pi_upd_irq;
+	__le32 gic_tpc_qm_irq_ctrl;
+	__le32 gic_mme_qm_irq_ctrl;
+	__le32 gic_dma_qm_irq_ctrl;
+	__le32 gic_nic_qm_irq_ctrl;
+	__le32 gic_dma_core_irq_ctrl;
+	__le32 gic_host_halt_irq;
+	__le32 gic_host_ints_irq;
+	__le32 reserved0;
+	__le32 gic_rot_qm_irq_ctrl;
+	__le32 reserved1;
+	__le32 eng_arc_irq_ctrl;
+	__le32 reserved2[20];		/* reserve for future use */
+};
+
+/* TODO: remove the desc magic after the code is updated to use message */
+/* HCDM - Habana Communications Descriptor Magic */
+#define HL_COMMS_DESC_MAGIC	0x4843444D
+#define HL_COMMS_DESC_VER	3
+
+/* HCMv - Habana Communications Message + header version */
+#define HL_COMMS_MSG_MAGIC_VALUE	0x48434D00
+#define HL_COMMS_MSG_MAGIC_MASK		0xFFFFFF00
+#define HL_COMMS_MSG_MAGIC_VER_MASK	0xFF
+
+#define HL_COMMS_MSG_MAGIC_VER(ver)	(HL_COMMS_MSG_MAGIC_VALUE |	\
+					((ver) & HL_COMMS_MSG_MAGIC_VER_MASK))
+#define HL_COMMS_MSG_MAGIC_V0		HL_COMMS_DESC_MAGIC
+#define HL_COMMS_MSG_MAGIC_V1		HL_COMMS_MSG_MAGIC_VER(1)
+#define HL_COMMS_MSG_MAGIC_V2		HL_COMMS_MSG_MAGIC_VER(2)
+#define HL_COMMS_MSG_MAGIC_V3		HL_COMMS_MSG_MAGIC_VER(3)
+
+#define HL_COMMS_MSG_MAGIC		HL_COMMS_MSG_MAGIC_V3
+
+#define HL_COMMS_MSG_MAGIC_VALIDATE_MAGIC(magic)			\
+		(((magic) & HL_COMMS_MSG_MAGIC_MASK) ==			\
+		HL_COMMS_MSG_MAGIC_VALUE)
+
+#define HL_COMMS_MSG_MAGIC_VALIDATE_VERSION(magic, ver)			\
+		(((magic) & HL_COMMS_MSG_MAGIC_VER_MASK) >=		\
+		((ver) & HL_COMMS_MSG_MAGIC_VER_MASK))
+
+#define HL_COMMS_MSG_MAGIC_VALIDATE(magic, ver)				\
+		(HL_COMMS_MSG_MAGIC_VALIDATE_MAGIC((magic)) &&		\
+		HL_COMMS_MSG_MAGIC_VALIDATE_VERSION((magic), (ver)))
+
+enum comms_msg_type {
+	HL_COMMS_DESC_TYPE = 0,
+	HL_COMMS_RESET_CAUSE_TYPE = 1,
+	HL_COMMS_FW_CFG_SKIP_TYPE = 2,
+	HL_COMMS_BINNING_CONF_TYPE = 3,
+};
+
+/*
+ * Binning information shared between LKD and FW
+ * @tpc_mask_l - TPC binning information lower 64 bit
+ * @dec_mask - Decoder binning information
+ * @dram_mask - DRAM binning information
+ * @edma_mask - EDMA binning information
+ * @mme_mask_l - MME binning information lower 32
+ * @mme_mask_h - MME binning information upper 32
+ * @rot_mask - Rotator binning information
+ * @xbar_mask - xBAR binning information
+ * @reserved - reserved field for future binning info w/o ABI change
+ * @tpc_mask_h - TPC binning information upper 64 bit
+ * @nic_mask - NIC binning information
+ */
+struct lkd_fw_binning_info {
+	__le64 tpc_mask_l;
+	__le32 dec_mask;
+	__le32 dram_mask;
+	__le32 edma_mask;
+	__le32 mme_mask_l;
+	__le32 mme_mask_h;
+	__le32 rot_mask;
+	__le32 xbar_mask;
+	__le32 reserved0;
+	__le64 tpc_mask_h;
+	__le64 nic_mask;
+	__le32 reserved1[8];
+};
+
+/* TODO: remove this struct after the code is updated to use message */
+/* this is the comms descriptor header - meta data */
+struct comms_desc_header {
+	__le32 magic;		/* magic for validation */
+	__le32 crc32;		/* CRC32 of the descriptor w/o header */
+	__le16 size;		/* size of the descriptor w/o header */
+	__u8 version;	/* descriptor version */
+	__u8 reserved[5];	/* pad to 64 bit */
+};
+
+/* this is the comms message header - meta data */
+struct comms_msg_header {
+	__le32 magic;		/* magic for validation */
+	__le32 crc32;		/* CRC32 of the message w/o header */
+	__le16 size;		/* size of the message w/o header */
+	__u8 version;	/* message payload version */
+	__u8 type;		/* message type */
+	__u8 reserved[4];	/* pad to 64 bit */
+};
+
+enum lkd_fw_ascii_msg_lvls {
+	LKD_FW_ASCII_MSG_ERR = 0,
+	LKD_FW_ASCII_MSG_WRN = 1,
+	LKD_FW_ASCII_MSG_INF = 2,
+	LKD_FW_ASCII_MSG_DBG = 3,
+};
+
+#define LKD_FW_ASCII_MSG_MAX_LEN		128
+#define LKD_FW_ASCII_MSG_MAX			4	/* consider ABI when changing */
+#define LKD_FW_ASCII_MSG_MIN_DESC_VERSION	3
+
+struct lkd_fw_ascii_msg {
+	__u8 valid;
+	__u8 msg_lvl;
+	__u8 reserved[6];
+	char msg[LKD_FW_ASCII_MSG_MAX_LEN];
+};
+
+/* this is the main FW descriptor - consider ABI when changing */
+struct lkd_fw_comms_desc {
+	struct comms_desc_header header;
+	struct cpu_dyn_regs cpu_dyn_regs;
+	char fuse_ver[VERSION_MAX_LEN];
+	char cur_fw_ver[VERSION_MAX_LEN];
+	/* can be used for 1 more version w/o ABI change */
+	char reserved0[VERSION_MAX_LEN];
+	__le64 img_addr;	/* address for next FW component load */
+	struct lkd_fw_binning_info binning_info;
+	struct lkd_fw_ascii_msg ascii_msg[LKD_FW_ASCII_MSG_MAX];
+	__le32 rsvd_mem_size_mb; /* reserved memory size [MB] for FW/SVE */
+	char reserved1[4];
+};
+
+enum comms_reset_cause {
+	HL_RESET_CAUSE_UNKNOWN = 0,
+	HL_RESET_CAUSE_HEARTBEAT = 1,
+	HL_RESET_CAUSE_TDR = 2,
+};
+
+/* TODO: remove define after struct name is aligned on all projects */
+#define lkd_msg_comms lkd_fw_comms_msg
+
+/* this is the comms message descriptor */
+struct lkd_fw_comms_msg {
+	struct comms_msg_header header;
+	/* union for future expantions of new messages */
+	union {
+		struct {
+			struct cpu_dyn_regs cpu_dyn_regs;
+			char fuse_ver[VERSION_MAX_LEN];
+			char cur_fw_ver[VERSION_MAX_LEN];
+			/* can be used for 1 more version w/o ABI change */
+			char reserved0[VERSION_MAX_LEN];
+			/* address for next FW component load */
+			__le64 img_addr;
+			struct lkd_fw_binning_info binning_info;
+			struct lkd_fw_ascii_msg ascii_msg[LKD_FW_ASCII_MSG_MAX];
+			/* reserved memory size [MB] for FW/SVE */
+			__le32 rsvd_mem_size_mb;
+			char reserved1[4];
+		};
+		struct {
+			__u8 reset_cause;
+		};
+		struct {
+			__u8 fw_cfg_skip; /* 1 - skip, 0 - don't skip */
+		};
+		struct lkd_fw_binning_info binning_conf;
+	};
+};
+
+/*
+ * LKD commands:
+ *
+ * COMMS_NOOP			Used to clear the command register and no actual
+ *				command is send.
+ *
+ * COMMS_CLR_STS		Clear status command - FW should clear the
+ *				status register. Used for synchronization
+ *				between the commands as part of the race free
+ *				protocol.
+ *
+ * COMMS_RST_STATE		Reset the current communication state which is
+ *				kept by FW for proper responses.
+ *				Should be used in the beginning of the
+ *				communication cycle to clean any leftovers from
+ *				previous communication attempts.
+ *
+ * COMMS_PREP_DESC		Prepare descriptor for setting up the
+ *				communication and other dynamic data:
+ *				struct lkd_fw_comms_desc.
+ *				This command has a parameter stating the next FW
+ *				component size, so the FW can actually prepare a
+ *				space for it and in the status response provide
+ *				the descriptor offset. The Offset of the next FW
+ *				data component is a part of the descriptor
+ *				structure.
+ *
+ * COMMS_DATA_RDY		The FW data has been uploaded and is ready for
+ *				validation.
+ *
+ * COMMS_EXEC			Execute the next FW component.
+ *
+ * COMMS_RST_DEV		Reset the device.
+ *
+ * COMMS_GOTO_WFE		Execute WFE command. Allowed only on non-secure
+ *				devices.
+ *
+ * COMMS_SKIP_BMC		Perform actions required for BMC-less servers.
+ *				Do not wait for BMC response.
+ *
+ * COMMS_PREP_DESC_ELBI		Same as COMMS_PREP_DESC only that the memory
+ *				space is allocated in a ELBI access only
+ *				address range.
+ *
+ */
+enum comms_cmd {
+	COMMS_NOOP = 0,
+	COMMS_CLR_STS = 1,
+	COMMS_RST_STATE = 2,
+	COMMS_PREP_DESC = 3,
+	COMMS_DATA_RDY = 4,
+	COMMS_EXEC = 5,
+	COMMS_RST_DEV = 6,
+	COMMS_GOTO_WFE = 7,
+	COMMS_SKIP_BMC = 8,
+	COMMS_PREP_DESC_ELBI = 10,
+	COMMS_INVLD_LAST
+};
+
+#define COMMS_COMMAND_SIZE_SHIFT	0
+#define COMMS_COMMAND_SIZE_MASK		0x1FFFFFF
+#define COMMS_COMMAND_CMD_SHIFT		27
+#define COMMS_COMMAND_CMD_MASK		0xF8000000
+
+/*
+ * LKD command to FW register structure
+ * @size	- FW component size
+ * @cmd		- command from enum comms_cmd
+ */
+struct comms_command {
+	union {		/* bit fields are only for FW use */
+		struct {
+			u32 size :25;		/* 32MB max. */
+			u32 reserved :2;
+			enum comms_cmd cmd :5;		/* 32 commands */
+		};
+		__le32 val;
+	};
+};
+
+/*
+ * FW status
+ *
+ * COMMS_STS_NOOP		Used to clear the status register and no actual
+ *				status is provided.
+ *
+ * COMMS_STS_ACK		Command has been received and recognized.
+ *
+ * COMMS_STS_OK			Command execution has finished successfully.
+ *
+ * COMMS_STS_ERR		Command execution was unsuccessful and resulted
+ *				in error.
+ *
+ * COMMS_STS_VALID_ERR		FW validation has failed.
+ *
+ * COMMS_STS_TIMEOUT_ERR	Command execution has timed out.
+ */
+enum comms_sts {
+	COMMS_STS_NOOP = 0,
+	COMMS_STS_ACK = 1,
+	COMMS_STS_OK = 2,
+	COMMS_STS_ERR = 3,
+	COMMS_STS_VALID_ERR = 4,
+	COMMS_STS_TIMEOUT_ERR = 5,
+	COMMS_STS_INVLD_LAST
+};
+
+/* RAM types for FW components loading - defines the base address */
+enum comms_ram_types {
+	COMMS_SRAM = 0,
+	COMMS_DRAM = 1,
+};
+
+#define COMMS_STATUS_OFFSET_SHIFT	0
+#define COMMS_STATUS_OFFSET_MASK	0x03FFFFFF
+#define COMMS_STATUS_OFFSET_ALIGN_SHIFT	2
+#define COMMS_STATUS_RAM_TYPE_SHIFT	26
+#define COMMS_STATUS_RAM_TYPE_MASK	0x0C000000
+#define COMMS_STATUS_STATUS_SHIFT	28
+#define COMMS_STATUS_STATUS_MASK	0xF0000000
+
+/*
+ * FW status to LKD register structure
+ * @offset	- an offset from the base of the ram_type shifted right by
+ *		  2 bits (always aligned to 32 bits).
+ *		  Allows a maximum addressable offset of 256MB from RAM base.
+ *		  Example: for real offset in RAM of 0x800000 (8MB), the value
+ *		  in offset field is (0x800000 >> 2) = 0x200000.
+ * @ram_type	- the RAM type that should be used for offset from
+ *		  enum comms_ram_types
+ * @status	- status from enum comms_sts
+ */
+struct comms_status {
+	union {		/* bit fields are only for FW use */
+		struct {
+			u32 offset :26;
+			enum comms_ram_types ram_type :2;
+			enum comms_sts status :4;	/* 16 statuses */
+		};
+		__le32 val;
+	};
+};
+
+#define NAME_MAX_LEN	32 /* bytes */
+struct hl_module_data {
+	__u8 name[NAME_MAX_LEN];
+	__u8 version[VERSION_MAX_LEN];
+};
+
+/**
+ * struct hl_component_versions - versions associated with hl component.
+ * @struct_size: size of all the struct (including dynamic size of modules).
+ * @modules_offset: offset of the modules field in this struct.
+ * @component: version of the component itself.
+ * @fw_os: Firmware OS Version.
+ * @comp_name: Name of the component.
+ * @modules_counter: number of set bits in modules_mask.
+ * @reserved: reserved for future use.
+ * @modules: versions of the component's modules. Elborated explanation in
+ *              struct cpucp_versions.
+ */
+struct hl_component_versions {
+	__le16 struct_size;
+	__le16 modules_offset;
+	__u8 component[VERSION_MAX_LEN];
+	__u8 fw_os[VERSION_MAX_LEN];
+	__u8 comp_name[NAME_MAX_LEN];
+	__u8 modules_counter;
+	__u8 reserved[3];
+	struct hl_module_data modules[];
+};
+
+/* Max size of fit size */
+#define HL_FW_VERSIONS_FIT_SIZE	4096
+
+#endif /* HL_BOOT_IF_H */
diff --git a/include/linux/hdmi.h b/include/linux/hdmi.h
index 2f4dcc8d060e..96bda41d9148 100644
--- a/include/linux/hdmi.h
+++ b/include/linux/hdmi.h
@@ -59,6 +59,15 @@ enum hdmi_infoframe_type {
 #define HDMI_DRM_INFOFRAME_SIZE    26
 #define HDMI_VENDOR_INFOFRAME_SIZE  4
 
+/*
+ * HDMI 1.3a table 5-14 states that the largest InfoFrame_length is 27,
+ * not including the packet header or checksum byte. We include the
+ * checksum byte in HDMI_INFOFRAME_HEADER_SIZE, so this should allow
+ * HDMI_INFOFRAME_SIZE(MAX) to be the largest buffer we could ever need
+ * for any HDMI infoframe.
+ */
+#define HDMI_MAX_INFOFRAME_SIZE    27
+
 #define HDMI_INFOFRAME_SIZE(type)	\
 	(HDMI_INFOFRAME_HEADER_SIZE + HDMI_ ## type ## _INFOFRAME_SIZE)
 
@@ -170,19 +179,19 @@ struct hdmi_avi_infoframe {
 	enum hdmi_infoframe_type type;
 	unsigned char version;
 	unsigned char length;
+	bool itc;
+	unsigned char pixel_repeat;
 	enum hdmi_colorspace colorspace;
 	enum hdmi_scan_mode scan_mode;
 	enum hdmi_colorimetry colorimetry;
 	enum hdmi_picture_aspect picture_aspect;
 	enum hdmi_active_aspect active_aspect;
-	bool itc;
 	enum hdmi_extended_colorimetry extended_colorimetry;
 	enum hdmi_quantization_range quantization_range;
 	enum hdmi_nups nups;
 	unsigned char video_code;
 	enum hdmi_ycc_quantization_range ycc_quantization_range;
 	enum hdmi_content_type content_type;
-	unsigned char pixel_repeat;
 	unsigned short top_bar;
 	unsigned short bottom_bar;
 	unsigned short left_bar;
@@ -436,7 +445,6 @@ ssize_t hdmi_infoframe_pack(union hdmi_infoframe *frame, void *buffer,
 			    size_t size);
 ssize_t hdmi_infoframe_pack_only(const union hdmi_infoframe *frame,
 				 void *buffer, size_t size);
-int hdmi_infoframe_check(union hdmi_infoframe *frame);
 int hdmi_infoframe_unpack(union hdmi_infoframe *frame,
 			  const void *buffer, size_t size);
 void hdmi_infoframe_log(const char *level, struct device *dev,
diff --git a/include/linux/hfs_common.h b/include/linux/hfs_common.h
new file mode 100644
index 000000000000..dadb5e0aa8a3
--- /dev/null
+++ b/include/linux/hfs_common.h
@@ -0,0 +1,653 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * HFS/HFS+ common definitions, inline functions,
+ * and shared functionality.
+ */
+
+#ifndef _HFS_COMMON_H_
+#define _HFS_COMMON_H_
+
+#ifdef pr_fmt
+#undef pr_fmt
+#endif
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define hfs_dbg(fmt, ...)							\
+	pr_debug("pid %d:%s:%d %s(): " fmt,					\
+		 current->pid, __FILE__, __LINE__, __func__, ##__VA_ARGS__)	\
+
+/*
+ * Format of structures on disk
+ * Information taken from Apple Technote #1150 (HFS Plus Volume Format)
+ */
+
+/* offsets to various blocks */
+#define HFS_DD_BLK			0	/* Driver Descriptor block */
+#define HFS_PMAP_BLK			1	/* First block of partition map */
+#define HFS_MDB_BLK			2	/* Block (w/i partition) of MDB */
+
+/* magic numbers for various disk blocks */
+#define HFS_DRVR_DESC_MAGIC		0x4552	/* "ER": driver descriptor map */
+#define HFS_OLD_PMAP_MAGIC		0x5453	/* "TS": old-type partition map */
+#define HFS_NEW_PMAP_MAGIC		0x504D	/* "PM": new-type partition map */
+#define HFS_SUPER_MAGIC			0x4244	/* "BD": HFS MDB (super block) */
+#define HFS_MFS_SUPER_MAGIC		0xD2D7	/* MFS MDB (super block) */
+
+#define HFSPLUS_VOLHEAD_SIG		0x482b
+#define HFSPLUS_VOLHEAD_SIGX		0x4858
+#define HFSPLUS_SUPER_MAGIC		0x482b
+
+#define HFSP_WRAP_MAGIC			0x4244
+#define HFSP_WRAP_ATTRIB_SLOCK		0x8000
+#define HFSP_WRAP_ATTRIB_SPARED		0x0200
+
+#define HFSP_WRAPOFF_SIG		0x00
+#define HFSP_WRAPOFF_ATTRIB		0x0A
+#define HFSP_WRAPOFF_ABLKSIZE		0x14
+#define HFSP_WRAPOFF_ABLKSTART		0x1C
+#define HFSP_WRAPOFF_EMBEDSIG		0x7C
+#define HFSP_WRAPOFF_EMBEDEXT		0x7E
+
+#define HFSP_HARDLINK_TYPE		0x686c6e6b	/* 'hlnk' */
+#define HFSP_HFSPLUS_CREATOR		0x6866732b	/* 'hfs+' */
+
+#define HFSP_SYMLINK_TYPE		0x736c6e6b	/* 'slnk' */
+#define HFSP_SYMLINK_CREATOR		0x72686170	/* 'rhap' */
+
+#define HFSP_MOUNT_VERSION		0x482b4c78	/* 'H+Lx' */
+
+#define HFSP_HIDDENDIR_NAME \
+	"\xe2\x90\x80\xe2\x90\x80\xe2\x90\x80\xe2\x90\x80HFS+ Private Data"
+
+/* various FIXED size parameters */
+#define HFS_SECTOR_SIZE			512	/* size of an HFS sector */
+#define HFS_SECTOR_SIZE_BITS		9	/* log_2(HFS_SECTOR_SIZE) */
+#define HFS_MAX_VALENCE			32767U
+
+#define HFSPLUS_SECTOR_SIZE		HFS_SECTOR_SIZE
+#define HFSPLUS_SECTOR_SHIFT		HFS_SECTOR_SIZE_BITS
+#define HFSPLUS_VOLHEAD_SECTOR		2
+#define HFSPLUS_MIN_VERSION		4
+#define HFSPLUS_CURRENT_VERSION		5
+
+#define HFS_NAMELEN			31	/* maximum length of an HFS filename */
+#define HFS_MAX_NAMELEN			128
+
+#define HFSPLUS_MAX_STRLEN		255
+#define HFSPLUS_ATTR_MAX_STRLEN		127
+
+/* Meanings of the drAtrb field of the MDB,
+ * Reference: _Inside Macintosh: Files_ p. 2-61
+ */
+#define HFS_SB_ATTRIB_HLOCK	(1 << 7)
+#define HFS_SB_ATTRIB_UNMNT	(1 << 8)
+#define HFS_SB_ATTRIB_SPARED	(1 << 9)
+#define HFS_SB_ATTRIB_INCNSTNT	(1 << 11)
+#define HFS_SB_ATTRIB_SLOCK	(1 << 15)
+
+/* values for hfs_cat_rec.cdrType */
+#define HFS_CDR_DIR		0x01	/* folder (directory) */
+#define HFS_CDR_FIL		0x02	/* file */
+#define HFS_CDR_THD		0x03	/* folder (directory) thread */
+#define HFS_CDR_FTH		0x04	/* file thread */
+
+/* legal values for hfs_ext_key.FkType and hfs_file.fork */
+#define HFS_FK_DATA		0x00
+#define HFS_FK_RSRC		0xFF
+
+/* bits in hfs_fil_entry.Flags */
+#define HFS_FIL_LOCK		0x01	/* locked */
+#define HFS_FIL_THD		0x02	/* file thread */
+#define HFS_FIL_DOPEN		0x04	/* data fork open */
+#define HFS_FIL_ROPEN		0x08	/* resource fork open */
+#define HFS_FIL_DIR		0x10	/* directory (always clear) */
+#define HFS_FIL_NOCOPY		0x40	/* copy-protected file */
+#define HFS_FIL_USED		0x80	/* open */
+
+/* bits in hfs_dir_entry.Flags. dirflags is 16 bits. */
+#define HFS_DIR_LOCK		0x01	/* locked */
+#define HFS_DIR_THD		0x02	/* directory thread */
+#define HFS_DIR_INEXPFOLDER	0x04	/* in a shared area */
+#define HFS_DIR_MOUNTED		0x08	/* mounted */
+#define HFS_DIR_DIR		0x10	/* directory (always set) */
+#define HFS_DIR_EXPFOLDER	0x20	/* share point */
+
+/* bits hfs_finfo.fdFlags */
+#define HFS_FLG_INITED		0x0100
+#define HFS_FLG_LOCKED		0x1000
+#define HFS_FLG_INVISIBLE	0x4000
+
+/* Some special File ID numbers */
+#define HFS_POR_CNID		1	/* Parent Of the Root */
+#define HFSPLUS_POR_CNID	HFS_POR_CNID
+#define HFS_ROOT_CNID		2	/* ROOT directory */
+#define HFSPLUS_ROOT_CNID	HFS_ROOT_CNID
+#define HFS_EXT_CNID		3	/* EXTents B-tree */
+#define HFSPLUS_EXT_CNID	HFS_EXT_CNID
+#define HFS_CAT_CNID		4	/* CATalog B-tree */
+#define HFSPLUS_CAT_CNID	HFS_CAT_CNID
+#define HFS_BAD_CNID		5	/* BAD blocks file */
+#define HFSPLUS_BAD_CNID	HFS_BAD_CNID
+#define HFS_ALLOC_CNID		6	/* ALLOCation file (HFS+) */
+#define HFSPLUS_ALLOC_CNID	HFS_ALLOC_CNID
+#define HFS_START_CNID		7	/* STARTup file (HFS+) */
+#define HFSPLUS_START_CNID	HFS_START_CNID
+#define HFS_ATTR_CNID		8	/* ATTRibutes file (HFS+) */
+#define HFSPLUS_ATTR_CNID	HFS_ATTR_CNID
+#define HFS_EXCH_CNID		15	/* ExchangeFiles temp id */
+#define HFSPLUS_EXCH_CNID	HFS_EXCH_CNID
+#define HFS_FIRSTUSER_CNID	16	/* first available user id */
+#define HFSPLUS_FIRSTUSER_CNID	HFS_FIRSTUSER_CNID
+
+/*======== HFS/HFS+ structures as they appear on the disk ========*/
+
+typedef __be32 hfsplus_cnid;
+typedef __be16 hfsplus_unichr;
+
+/* Pascal-style string of up to 31 characters */
+struct hfs_name {
+	u8 len;
+	u8 name[HFS_NAMELEN];
+} __packed;
+
+/* A "string" as used in filenames, etc. */
+struct hfsplus_unistr {
+	__be16 length;
+	hfsplus_unichr unicode[HFSPLUS_MAX_STRLEN];
+} __packed;
+
+/*
+ * A "string" is used in attributes file
+ * for name of extended attribute
+ */
+struct hfsplus_attr_unistr {
+	__be16 length;
+	hfsplus_unichr unicode[HFSPLUS_ATTR_MAX_STRLEN];
+} __packed;
+
+struct hfs_extent {
+	__be16 block;
+	__be16 count;
+};
+typedef struct hfs_extent hfs_extent_rec[3];
+
+/* A single contiguous area of a file */
+struct hfsplus_extent {
+	__be32 start_block;
+	__be32 block_count;
+} __packed;
+typedef struct hfsplus_extent hfsplus_extent_rec[8];
+
+/* Information for a "Fork" in a file */
+struct hfsplus_fork_raw {
+	__be64 total_size;
+	__be32 clump_size;
+	__be32 total_blocks;
+	hfsplus_extent_rec extents;
+} __packed;
+
+struct hfs_mdb {
+	__be16 drSigWord;		/* Signature word indicating fs type */
+	__be32 drCrDate;		/* fs creation date/time */
+	__be32 drLsMod;			/* fs modification date/time */
+	__be16 drAtrb;			/* fs attributes */
+	__be16 drNmFls;			/* number of files in root directory */
+	__be16 drVBMSt;			/* location (in 512-byte blocks)
+					   of the volume bitmap */
+	__be16 drAllocPtr;		/* location (in allocation blocks)
+					   to begin next allocation search */
+	__be16 drNmAlBlks;		/* number of allocation blocks */
+	__be32 drAlBlkSiz;		/* bytes in an allocation block */
+	__be32 drClpSiz;		/* clumpsize, the number of bytes to
+					   allocate when extending a file */
+	__be16 drAlBlSt;		/* location (in 512-byte blocks)
+					   of the first allocation block */
+	__be32 drNxtCNID;		/* CNID to assign to the next
+					   file or directory created */
+	__be16 drFreeBks;		/* number of free allocation blocks */
+	u8 drVN[28];			/* the volume label */
+	__be32 drVolBkUp;		/* fs backup date/time */
+	__be16 drVSeqNum;		/* backup sequence number */
+	__be32 drWrCnt;			/* fs write count */
+	__be32 drXTClpSiz;		/* clumpsize for the extents B-tree */
+	__be32 drCTClpSiz;		/* clumpsize for the catalog B-tree */
+	__be16 drNmRtDirs;		/* number of directories in
+					   the root directory */
+	__be32 drFilCnt;		/* number of files in the fs */
+	__be32 drDirCnt;		/* number of directories in the fs */
+	u8 drFndrInfo[32];		/* data used by the Finder */
+	__be16 drEmbedSigWord;		/* embedded volume signature */
+	__be32 drEmbedExtent;		/* starting block number (xdrStABN)
+					   and number of allocation blocks
+					   (xdrNumABlks) occupied by embedded
+					   volume */
+	__be32 drXTFlSize;		/* bytes in the extents B-tree */
+	hfs_extent_rec drXTExtRec;	/* extents B-tree's first 3 extents */
+	__be32 drCTFlSize;		/* bytes in the catalog B-tree */
+	hfs_extent_rec drCTExtRec;	/* catalog B-tree's first 3 extents */
+} __packed;
+
+/* HFS+ Volume Header */
+struct hfsplus_vh {
+	__be16 signature;
+	__be16 version;
+	__be32 attributes;
+	__be32 last_mount_vers;
+	u32 reserved;
+
+	__be32 create_date;
+	__be32 modify_date;
+	__be32 backup_date;
+	__be32 checked_date;
+
+	__be32 file_count;
+	__be32 folder_count;
+
+	__be32 blocksize;
+	__be32 total_blocks;
+	__be32 free_blocks;
+
+	__be32 next_alloc;
+	__be32 rsrc_clump_sz;
+	__be32 data_clump_sz;
+	hfsplus_cnid next_cnid;
+
+	__be32 write_count;
+	__be64 encodings_bmp;
+
+	u32 finder_info[8];
+
+	struct hfsplus_fork_raw alloc_file;
+	struct hfsplus_fork_raw ext_file;
+	struct hfsplus_fork_raw cat_file;
+	struct hfsplus_fork_raw attr_file;
+	struct hfsplus_fork_raw start_file;
+} __packed;
+
+/* HFS+ volume attributes */
+#define HFSPLUS_VOL_UNMNT		(1 << 8)
+#define HFSPLUS_VOL_SPARE_BLK		(1 << 9)
+#define HFSPLUS_VOL_NOCACHE		(1 << 10)
+#define HFSPLUS_VOL_INCNSTNT		(1 << 11)
+#define HFSPLUS_VOL_NODEID_REUSED	(1 << 12)
+#define HFSPLUS_VOL_JOURNALED		(1 << 13)
+#define HFSPLUS_VOL_SOFTLOCK		(1 << 15)
+#define HFSPLUS_VOL_UNUSED_NODE_FIX	(1 << 31)
+
+struct hfs_point {
+	__be16 v;
+	__be16 h;
+} __packed;
+
+typedef struct hfs_point hfsp_point;
+
+struct hfs_rect {
+	__be16 top;
+	__be16 left;
+	__be16 bottom;
+	__be16 right;
+} __packed;
+
+typedef struct hfs_rect hfsp_rect;
+
+struct hfs_finfo {
+	__be32 fdType;
+	__be32 fdCreator;
+	__be16 fdFlags;
+	struct hfs_point fdLocation;
+	__be16 fdFldr;
+} __packed;
+
+typedef struct hfs_finfo FInfo;
+
+struct hfs_fxinfo {
+	__be16 fdIconID;
+	u8 fdUnused[8];
+	__be16 fdComment;
+	__be32 fdPutAway;
+} __packed;
+
+typedef struct hfs_fxinfo FXInfo;
+
+struct hfs_dinfo {
+	struct hfs_rect frRect;
+	__be16 frFlags;
+	struct hfs_point frLocation;
+	__be16 frView;
+} __packed;
+
+typedef struct hfs_dinfo DInfo;
+
+struct hfs_dxinfo {
+	struct hfs_point frScroll;
+	__be32 frOpenChain;
+	__be16 frUnused;
+	__be16 frComment;
+	__be32 frPutAway;
+} __packed;
+
+typedef struct hfs_dxinfo DXInfo;
+
+union hfs_finder_info {
+	struct {
+		struct hfs_finfo finfo;
+		struct hfs_fxinfo fxinfo;
+	} file;
+	struct {
+		struct hfs_dinfo dinfo;
+		struct hfs_dxinfo dxinfo;
+	} dir;
+} __packed;
+
+/* The key used in the catalog b-tree: */
+struct hfs_cat_key {
+	u8 key_len;		/* number of bytes in the key */
+	u8 reserved;		/* padding */
+	__be32 ParID;		/* CNID of the parent dir */
+	struct hfs_name	CName;	/* The filename of the entry */
+} __packed;
+
+/* HFS+ catalog entry key */
+struct hfsplus_cat_key {
+	__be16 key_len;
+	hfsplus_cnid parent;
+	struct hfsplus_unistr name;
+} __packed;
+
+#define HFSPLUS_CAT_KEYLEN	(sizeof(struct hfsplus_cat_key))
+
+/* The key used in the extents b-tree: */
+struct hfs_ext_key {
+	u8 key_len;		/* number of bytes in the key */
+	u8 FkType;		/* HFS_FK_{DATA,RSRC} */
+	__be32 FNum;		/* The File ID of the file */
+	__be16 FABN;		/* allocation blocks number*/
+} __packed;
+
+/* HFS+ extents tree key */
+struct hfsplus_ext_key {
+	__be16 key_len;
+	u8 fork_type;
+	u8 pad;
+	hfsplus_cnid cnid;
+	__be32 start_block;
+} __packed;
+
+#define HFSPLUS_EXT_KEYLEN	sizeof(struct hfsplus_ext_key)
+
+typedef union hfs_btree_key {
+	u8 key_len;			/* number of bytes in the key */
+	struct hfs_cat_key cat;
+	struct hfs_ext_key ext;
+} hfs_btree_key;
+
+#define HFS_MAX_CAT_KEYLEN	(sizeof(struct hfs_cat_key) - sizeof(u8))
+#define HFS_MAX_EXT_KEYLEN	(sizeof(struct hfs_ext_key) - sizeof(u8))
+
+typedef union hfs_btree_key btree_key;
+
+/* The catalog record for a file */
+struct hfs_cat_file {
+	s8 type;			/* The type of entry */
+	u8 reserved;
+	u8 Flags;			/* Flags such as read-only */
+	s8 Typ;				/* file version number = 0 */
+	struct hfs_finfo UsrWds;	/* data used by the Finder */
+	__be32 FlNum;			/* The CNID */
+	__be16 StBlk;			/* obsolete */
+	__be32 LgLen;			/* The logical EOF of the data fork*/
+	__be32 PyLen;			/* The physical EOF of the data fork */
+	__be16 RStBlk;			/* obsolete */
+	__be32 RLgLen;			/* The logical EOF of the rsrc fork */
+	__be32 RPyLen;			/* The physical EOF of the rsrc fork */
+	__be32 CrDat;			/* The creation date */
+	__be32 MdDat;			/* The modified date */
+	__be32 BkDat;			/* The last backup date */
+	struct hfs_fxinfo FndrInfo;	/* more data for the Finder */
+	__be16 ClpSize;			/* number of bytes to allocate
+					   when extending files */
+	hfs_extent_rec ExtRec;		/* first extent record
+					   for the data fork */
+	hfs_extent_rec RExtRec;		/* first extent record
+					   for the resource fork */
+	u32 Resrv;			/* reserved by Apple */
+} __packed;
+
+/* the catalog record for a directory */
+struct hfs_cat_dir {
+	s8 type;			/* The type of entry */
+	u8 reserved;
+	__be16 Flags;			/* flags */
+	__be16 Val;			/* Valence: number of files and
+					   dirs in the directory */
+	__be32 DirID;			/* The CNID */
+	__be32 CrDat;			/* The creation date */
+	__be32 MdDat;			/* The modification date */
+	__be32 BkDat;			/* The last backup date */
+	struct hfs_dinfo UsrInfo;	/* data used by the Finder */
+	struct hfs_dxinfo FndrInfo;	/* more data used by Finder */
+	u8 Resrv[16];			/* reserved by Apple */
+} __packed;
+
+/* the catalog record for a thread */
+struct hfs_cat_thread {
+	s8 type;			/* The type of entry */
+	u8 reserved[9];			/* reserved by Apple */
+	__be32 ParID;			/* CNID of parent directory */
+	struct hfs_name CName;		/* The name of this entry */
+}  __packed;
+
+/* A catalog tree record */
+typedef union hfs_cat_rec {
+	s8 type;			/* The type of entry */
+	struct hfs_cat_file file;
+	struct hfs_cat_dir dir;
+	struct hfs_cat_thread thread;
+} hfs_cat_rec;
+
+/* POSIX permissions */
+struct hfsplus_perm {
+	__be32 owner;
+	__be32 group;
+	u8  rootflags;
+	u8  userflags;
+	__be16 mode;
+	__be32 dev;
+} __packed;
+
+#define HFSPLUS_FLG_NODUMP	0x01
+#define HFSPLUS_FLG_IMMUTABLE	0x02
+#define HFSPLUS_FLG_APPEND	0x04
+
+/* HFS/HFS+ BTree node descriptor */
+struct hfs_bnode_desc {
+	__be32 next;		/* (V) Number of the next node at this level */
+	__be32 prev;		/* (V) Number of the prev node at this level */
+	u8 type;		/* (F) The type of node */
+	u8 height;		/* (F) The level of this node (leaves=1) */
+	__be16 num_recs;	/* (V) The number of records in this node */
+	u16 reserved;
+} __packed;
+
+/* HFS/HFS+ BTree node types */
+#define HFS_NODE_INDEX	0x00	/* An internal (index) node */
+#define HFS_NODE_HEADER	0x01	/* The tree header node (node 0) */
+#define HFS_NODE_MAP	0x02	/* Holds part of the bitmap of used nodes */
+#define HFS_NODE_LEAF	0xFF	/* A leaf (ndNHeight==1) node */
+
+/* HFS/HFS+ BTree header */
+struct hfs_btree_header_rec {
+	__be16 depth;		/* (V) The number of levels in this B-tree */
+	__be32 root;		/* (V) The node number of the root node */
+	__be32 leaf_count;	/* (V) The number of leaf records */
+	__be32 leaf_head;	/* (V) The number of the first leaf node */
+	__be32 leaf_tail;	/* (V) The number of the last leaf node */
+	__be16 node_size;	/* (F) The number of bytes in a node (=512) */
+	__be16 max_key_len;	/* (F) The length of a key in an index node */
+	__be32 node_count;	/* (V) The total number of nodes */
+	__be32 free_nodes;	/* (V) The number of unused nodes */
+	u16 reserved1;
+	__be32 clump_size;	/* (F) clump size. not usually used. */
+	u8 btree_type;		/* (F) BTree type */
+	u8 key_type;
+	__be32 attributes;	/* (F) attributes */
+	u32 reserved3[16];
+} __packed;
+
+/* BTree attributes */
+#define BTREE_ATTR_BADCLOSE	0x00000001	/* b-tree not closed properly. not
+						   used by hfsplus. */
+#define HFS_TREE_BIGKEYS	0x00000002	/* key length is u16 instead of u8.
+						   used by hfsplus. */
+#define HFS_TREE_VARIDXKEYS	0x00000004	/* variable key length instead of
+						   max key length. use din catalog
+						   b-tree but not in extents
+						   b-tree (hfsplus). */
+
+/* HFS+ BTree misc info */
+#define HFSPLUS_TREE_HEAD			0
+#define HFSPLUS_NODE_MXSZ			32768
+#define HFSPLUS_ATTR_TREE_NODE_SIZE		8192
+#define HFSPLUS_BTREE_HDR_NODE_RECS_COUNT	3
+#define HFSPLUS_BTREE_HDR_USER_BYTES		128
+
+/* btree key type */
+#define HFSPLUS_KEY_CASEFOLDING		0xCF	/* case-insensitive */
+#define HFSPLUS_KEY_BINARY		0xBC	/* case-sensitive */
+
+/* HFS+ folder data (part of an hfsplus_cat_entry) */
+struct hfsplus_cat_folder {
+	__be16 type;
+	__be16 flags;
+	__be32 valence;
+	hfsplus_cnid id;
+	__be32 create_date;
+	__be32 content_mod_date;
+	__be32 attribute_mod_date;
+	__be32 access_date;
+	__be32 backup_date;
+	struct hfsplus_perm permissions;
+	struct_group_attr(info, __packed,
+		DInfo user_info;
+		DXInfo finder_info;
+	);
+	__be32 text_encoding;
+	__be32 subfolders;	/* Subfolder count in HFSX. Reserved in HFS+. */
+} __packed;
+
+/* HFS+ file data (part of a cat_entry) */
+struct hfsplus_cat_file {
+	__be16 type;
+	__be16 flags;
+	u32 reserved1;
+	hfsplus_cnid id;
+	__be32 create_date;
+	__be32 content_mod_date;
+	__be32 attribute_mod_date;
+	__be32 access_date;
+	__be32 backup_date;
+	struct hfsplus_perm permissions;
+	struct_group_attr(info, __packed,
+		FInfo user_info;
+		FXInfo finder_info;
+	);
+	__be32 text_encoding;
+	u32 reserved2;
+
+	struct hfsplus_fork_raw data_fork;
+	struct hfsplus_fork_raw rsrc_fork;
+} __packed;
+
+/* File and folder flag bits */
+#define HFSPLUS_FILE_LOCKED		0x0001
+#define HFSPLUS_FILE_THREAD_EXISTS	0x0002
+#define HFSPLUS_XATTR_EXISTS		0x0004
+#define HFSPLUS_ACL_EXISTS		0x0008
+#define HFSPLUS_HAS_FOLDER_COUNT	0x0010	/* Folder has subfolder count
+						 * (HFSX only) */
+
+/* HFS+ catalog thread (part of a cat_entry) */
+struct hfsplus_cat_thread {
+	__be16 type;
+	s16 reserved;
+	hfsplus_cnid parentID;
+	struct hfsplus_unistr nodeName;
+} __packed;
+
+#define HFSPLUS_MIN_THREAD_SZ		10
+
+/* A data record in the catalog tree */
+typedef union {
+	__be16 type;
+	struct hfsplus_cat_folder folder;
+	struct hfsplus_cat_file file;
+	struct hfsplus_cat_thread thread;
+} __packed hfsplus_cat_entry;
+
+/* HFS+ catalog entry type */
+#define HFSPLUS_FOLDER		0x0001
+#define HFSPLUS_FILE		0x0002
+#define HFSPLUS_FOLDER_THREAD	0x0003
+#define HFSPLUS_FILE_THREAD	0x0004
+
+#define HFSPLUS_XATTR_FINDER_INFO_NAME	"com.apple.FinderInfo"
+#define HFSPLUS_XATTR_ACL_NAME		"com.apple.system.Security"
+
+#define HFSPLUS_ATTR_INLINE_DATA	0x10
+#define HFSPLUS_ATTR_FORK_DATA		0x20
+#define HFSPLUS_ATTR_EXTENTS		0x30
+
+/* HFS+ attributes tree key */
+struct hfsplus_attr_key {
+	__be16 key_len;
+	__be16 pad;
+	hfsplus_cnid cnid;
+	__be32 start_block;
+	struct hfsplus_attr_unistr key_name;
+} __packed;
+
+#define HFSPLUS_ATTR_KEYLEN	sizeof(struct hfsplus_attr_key)
+
+/* HFS+ fork data attribute */
+struct hfsplus_attr_fork_data {
+	__be32 record_type;
+	__be32 reserved;
+	struct hfsplus_fork_raw the_fork;
+} __packed;
+
+/* HFS+ extension attribute */
+struct hfsplus_attr_extents {
+	__be32 record_type;
+	__be32 reserved;
+	struct hfsplus_extent extents;
+} __packed;
+
+#define HFSPLUS_MAX_INLINE_DATA_SIZE	3802
+
+/* HFS+ attribute inline data */
+struct hfsplus_attr_inline_data {
+	__be32 record_type;
+	__be32 reserved1;
+	u8 reserved2[6];
+	__be16 length;
+	u8 raw_bytes[HFSPLUS_MAX_INLINE_DATA_SIZE];
+} __packed;
+
+/* A data record in the attributes tree */
+typedef union {
+	__be32 record_type;
+	struct hfsplus_attr_fork_data fork_data;
+	struct hfsplus_attr_extents extents;
+	struct hfsplus_attr_inline_data inline_data;
+} __packed hfsplus_attr_entry;
+
+/* HFS+ generic BTree key */
+typedef union {
+	__be16 key_len;
+	struct hfsplus_cat_key cat;
+	struct hfsplus_ext_key ext;
+	struct hfsplus_attr_key attr;
+} __packed hfsplus_btree_key;
+
+#endif /* _HFS_COMMON_H_ */
diff --git a/include/linux/hid-over-i2c.h b/include/linux/hid-over-i2c.h
new file mode 100644
index 000000000000..3b1a0208a6b8
--- /dev/null
+++ b/include/linux/hid-over-i2c.h
@@ -0,0 +1,117 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright 2024 Intel Corporation */
+
+#include <linux/bits.h>
+
+#ifndef _HID_OVER_I2C_H_
+#define _HID_OVER_I2C_H_
+
+#define HIDI2C_REG_LEN		sizeof(__le16)
+
+/* Input report type definition in HIDI2C protocol */
+enum hidi2c_report_type {
+	HIDI2C_RESERVED = 0,
+	HIDI2C_INPUT,
+	HIDI2C_OUTPUT,
+	HIDI2C_FEATURE,
+};
+
+/* Power state type definition in HIDI2C protocol */
+enum hidi2c_power_state {
+	HIDI2C_ON,
+	HIDI2C_SLEEP,
+};
+
+/* Opcode type definition in HIDI2C protocol */
+enum hidi2c_opcode {
+	HIDI2C_RESET = 1,
+	HIDI2C_GET_REPORT,
+	HIDI2C_SET_REPORT,
+	HIDI2C_GET_IDLE,
+	HIDI2C_SET_IDLE,
+	HIDI2C_GET_PROTOCOL,
+	HIDI2C_SET_PROTOCOL,
+	HIDI2C_SET_POWER,
+};
+
+/**
+ * struct hidi2c_report_packet - Report packet definition in HIDI2C protocol
+ * @len: data field length
+ * @data: HIDI2C report packet data
+ */
+struct hidi2c_report_packet {
+	__le16 len;
+	u8 data[];
+} __packed;
+
+#define HIDI2C_LENGTH_LEN	sizeof(__le16)
+
+#define HIDI2C_PACKET_LEN(data_len)	((data_len) + HIDI2C_LENGTH_LEN)
+#define HIDI2C_DATA_LEN(pkt_len)	((pkt_len) - HIDI2C_LENGTH_LEN)
+
+#define HIDI2C_CMD_MAX_RI	0x0F
+
+/**
+ * HIDI2C command data packet - Command packet definition in HIDI2C protocol
+ * @report_id:		[0:3] report id (<15) for features or output reports
+ * @report_type:	[4:5] indicate report type, reference to hidi2c_report_type
+ * @reserved0:		[6:7] reserved bits
+ * @opcode:		[8:11] command operation code, reference to hidi2c_opcode
+ * @reserved1:		[12:15] reserved bits
+ * @report_id_optional: [23:16] appended 3rd byte.
+ *                      If the report_id in the low byte is set to the
+ *                      sentinel value (HIDI2C_CMD_MAX_RI), then this
+ *                      optional third byte represents the report id (>=15)
+ *                      Otherwise, not this 3rd byte.
+ */
+
+#define HIDI2C_CMD_LEN			sizeof(__le16)
+#define HIDI2C_CMD_LEN_OPT		(sizeof(__le16) + 1)
+#define HIDI2C_CMD_REPORT_ID		GENMASK(3, 0)
+#define HIDI2C_CMD_REPORT_TYPE		GENMASK(5, 4)
+#define HIDI2C_CMD_OPCODE		GENMASK(11, 8)
+#define HIDI2C_CMD_OPCODE		GENMASK(11, 8)
+#define HIDI2C_CMD_3RD_BYTE		GENMASK(23, 16)
+
+#define HIDI2C_HID_DESC_BCDVERSION	0x100
+
+/**
+ * struct hidi2c_dev_descriptor - HIDI2C device descriptor definition
+ * @dev_desc_len: The length of the complete device descriptor, fixed to 0x1E (30).
+ * @bcd_ver: The version number of the HIDI2C protocol supported.
+ *           In binary coded decimal (BCD) format.
+ * @report_desc_len: The length of the report descriptor
+ * @report_desc_reg: The register address to retrieve report descriptor
+ * @input_reg: the register address to retrieve input report
+ * @max_input_len: The length of the largest possible HID input (or feature) report
+ * @output_reg: the register address to send output report
+ * @max_output_len: The length of the largest output (or feature) report
+ * @cmd_reg: the register address to send command
+ * @data_reg: the register address to send command data
+ * @vendor_id: Device manufacturers vendor ID
+ * @product_id: Device unique model/product ID
+ * @version_id: Device’s unique version
+ * @reserved0: Reserved and should be 0
+ * @reserved1: Reserved and should be 0
+ */
+struct hidi2c_dev_descriptor {
+	__le16 dev_desc_len;
+	__le16 bcd_ver;
+	__le16 report_desc_len;
+	__le16 report_desc_reg;
+	__le16 input_reg;
+	__le16 max_input_len;
+	__le16 output_reg;
+	__le16 max_output_len;
+	__le16 cmd_reg;
+	__le16 data_reg;
+	__le16 vendor_id;
+	__le16 product_id;
+	__le16 version_id;
+	__le16 reserved0;
+	__le16 reserved1;
+} __packed;
+
+#define HIDI2C_DEV_DESC_LEN		sizeof(struct hidi2c_dev_descriptor)
+
+#endif /* _HID_OVER_I2C_H_ */
diff --git a/include/linux/hid-over-spi.h b/include/linux/hid-over-spi.h
new file mode 100644
index 000000000000..da5a14b5e89b
--- /dev/null
+++ b/include/linux/hid-over-spi.h
@@ -0,0 +1,155 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright 2024 Intel Corporation */
+
+#ifndef _HID_OVER_SPI_H_
+#define _HID_OVER_SPI_H_
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+/* Input report type definition in HIDSPI protocol */
+enum input_report_type {
+	INVALID_INPUT_REPORT_TYPE_0	= 0,
+	DATA				= 1,
+	INVALID_TYPE_2			= 2,
+	RESET_RESPONSE			= 3,
+	COMMAND_RESPONSE		= 4,
+	GET_FEATURE_RESPONSE		= 5,
+	INVALID_TYPE_6			= 6,
+	DEVICE_DESCRIPTOR_RESPONSE	= 7,
+	REPORT_DESCRIPTOR_RESPONSE	= 8,
+	SET_FEATURE_RESPONSE		= 9,
+	OUTPUT_REPORT_RESPONSE		= 10,
+	GET_INPUT_REPORT_RESPONSE	= 11,
+	INVALID_INPUT_REPORT_TYPE	= 0xF,
+};
+
+/* Output report type definition in HIDSPI protocol */
+enum output_report_type {
+	INVALID_OUTPUT_REPORT_TYPE_0	= 0,
+	DEVICE_DESCRIPTOR		= 1,
+	REPORT_DESCRIPTOR		= 2,
+	SET_FEATURE			= 3,
+	GET_FEATURE			= 4,
+	OUTPUT_REPORT			= 5,
+	GET_INPUT_REPORT		= 6,
+	COMMAND_CONTENT			= 7,
+};
+
+/* Set power command ID for output report */
+#define HIDSPI_SET_POWER_CMD_ID  1
+
+/* Power state definition in HIDSPI protocol */
+enum hidspi_power_state {
+	HIDSPI_ON	= 1,
+	HIDSPI_SLEEP	= 2,
+	HIDSPI_OFF	= 3,
+};
+
+/**
+ * Input report header definition in HIDSPI protocol
+ * Report header size is 32bits, it includes:
+ * protocol_ver:     [0:3] Current supported HIDSPI protocol version, must be 0x3
+ * reserved0:        [4:7] Reserved bits
+ * input_report_len: [8:21] Input report length in number bytes divided by 4
+ * last_frag_flag:   [22]Indicate if this packet is last fragment.
+ *                       1 - indicates last fragment
+ *                       0 - indicates additional fragments
+ * reserved1:        [23] Reserved bits
+ * @sync_const:      [24:31] Used to validate input report header, must be 0x5A
+ */
+#define HIDSPI_INPUT_HEADER_SIZE		sizeof(u32)
+#define HIDSPI_INPUT_HEADER_VER			GENMASK(3, 0)
+#define HIDSPI_INPUT_HEADER_REPORT_LEN		GENMASK(21, 8)
+#define HIDSPI_INPUT_HEADER_LAST_FLAG		BIT(22)
+#define HIDSPI_INPUT_HEADER_SYNC		GENMASK(31, 24)
+
+/**
+ * struct input_report_body_header - Input report body header definition in HIDSPI protocol
+ * @input_report_type: indicate input report type, reference to enum input_report_type
+ * @content_len: this input report body packet length
+ * @content_id: indicate this input report's report id
+ */
+struct input_report_body_header {
+	u8 input_report_type;
+	__le16 content_len;
+	u8 content_id;
+} __packed;
+
+#define HIDSPI_INPUT_BODY_HEADER_SIZE	sizeof(struct input_report_body_header)
+
+/**
+ * struct input_report_body - Input report body definition in HIDSPI protocol
+ * @body_hdr: input report body header
+ * @content: input report body content
+ */
+struct input_report_body {
+	struct input_report_body_header body_hdr;
+	u8 content[];
+} __packed;
+
+#define HIDSPI_INPUT_BODY_SIZE(content_len)	((content_len) + HIDSPI_INPUT_BODY_HEADER_SIZE)
+
+/**
+ * struct output_report_header - Output report header definition in HIDSPI protocol
+ * @report_type: output report type, reference to enum output_report_type
+ * @content_len: length of content
+ * @content_id: 0x00 - descriptors
+ *              report id - Set/Feature feature or Input/Output Reports
+ *              command opcode - for commands
+ */
+struct output_report_header {
+	u8 report_type;
+	__le16 content_len;
+	u8 content_id;
+} __packed;
+
+#define HIDSPI_OUTPUT_REPORT_HEADER_SIZE	sizeof(struct output_report_header)
+
+/**
+ * struct output_report - Output report definition in HIDSPI protocol
+ * @output_hdr: output report header
+ * @content: output report content
+ */
+struct output_report {
+	struct output_report_header output_hdr;
+	u8 content[];
+} __packed;
+
+#define HIDSPI_OUTPUT_REPORT_SIZE(content_len)	((content_len) + HIDSPI_OUTPUT_REPORT_HEADER_SIZE)
+
+/**
+ * struct hidspi_dev_descriptor - HIDSPI device descriptor definition
+ * @dev_desc_len: The length of the complete device descriptor, fixed to 0x18 (24).
+ * @bcd_ver: The version number of the HIDSPI protocol supported.
+ *           In binary coded decimal (BCD) format. Must be fixed to 0x0300.
+ * @rep_desc_len: The length of the report descriptor
+ * @max_input_len: The length of the largest possible HID input (or feature) report
+ * @max_output_len: The length of the largest output (or feature) report
+ * @max_frag_len: The length of the largest fragment, where a fragment represents
+ *                the body of an input report.
+ * @vendor_id: Device manufacturers vendor ID
+ * @product_id: Device unique model/product ID
+ * @version_id: Device’s unique version
+ * @flags: Specify flags for the device’s operation
+ * @reserved: Reserved and should be 0
+ */
+struct hidspi_dev_descriptor {
+	__le16 dev_desc_len;
+	__le16 bcd_ver;
+	__le16 rep_desc_len;
+	__le16 max_input_len;
+	__le16 max_output_len;
+	__le16 max_frag_len;
+	__le16 vendor_id;
+	__le16 product_id;
+	__le16 version_id;
+	__le16 flags;
+	__le32 reserved;
+};
+
+#define HIDSPI_DEVICE_DESCRIPTOR_SIZE		sizeof(struct hidspi_dev_descriptor)
+#define HIDSPI_INPUT_DEVICE_DESCRIPTOR_SIZE	\
+	(HIDSPI_INPUT_BODY_HEADER_SIZE + HIDSPI_DEVICE_DESCRIPTOR_SIZE)
+
+#endif /* _HID_OVER_SPI_H_ */
diff --git a/include/linux/hid-roccat.h b/include/linux/hid-roccat.h
index 3214fb0815fc..753654fff07f 100644
--- a/include/linux/hid-roccat.h
+++ b/include/linux/hid-roccat.h
@@ -16,7 +16,7 @@
 
 #ifdef __KERNEL__
 
-int roccat_connect(struct class *klass, struct hid_device *hid,
+int roccat_connect(const struct class *klass, struct hid_device *hid,
 		int report_size);
 void roccat_disconnect(int minor);
 int roccat_report_event(int minor, u8 const *data);
diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h
index c27329e2a5ad..e71056553108 100644
--- a/include/linux/hid-sensor-hub.h
+++ b/include/linux/hid-sensor-hub.h
@@ -17,7 +17,7 @@
  * @attrib_id:		Attribute id for this attribute.
  * @report_id:		Report id in which this information resides.
  * @index:		Field index in the report.
- * @units:		Measurment unit for this attribute.
+ * @units:		Measurement unit for this attribute.
  * @unit_expo:		Exponent used in the data.
  * @size:		Size in bytes for data size.
  * @logical_minimum:	Logical minimum value for this attribute.
@@ -39,8 +39,8 @@ struct hid_sensor_hub_attribute_info {
  * struct sensor_hub_pending - Synchronous read pending information
  * @status:		Pending status true/false.
  * @ready:		Completion synchronization data.
- * @usage_id:		Usage id for physical device, E.g. Gyro usage id.
- * @attr_usage_id:	Usage Id of a field, E.g. X-AXIS for a gyro.
+ * @usage_id:		Usage id for physical device, e.g. gyro usage id.
+ * @attr_usage_id:	Usage Id of a field, e.g. X-axis for a gyro.
  * @raw_size:		Response size for a read request.
  * @raw_data:		Place holder for received response.
  */
@@ -104,10 +104,10 @@ struct hid_sensor_hub_callbacks {
 int sensor_hub_device_open(struct hid_sensor_hub_device *hsdev);
 
 /**
-* sensor_hub_device_clode() - Close hub device
+* sensor_hub_device_close() - Close hub device
 * @hsdev:	Hub device instance.
 *
-* Used to clode hid device for sensor hub.
+* Used to close hid device for sensor hub.
 */
 void sensor_hub_device_close(struct hid_sensor_hub_device *hsdev);
 
@@ -128,12 +128,13 @@ int sensor_hub_register_callback(struct hid_sensor_hub_device *hsdev,
 			struct hid_sensor_hub_callbacks *usage_callback);
 
 /**
-* sensor_hub_remove_callback() - Remove client callbacks
+* sensor_hub_remove_callback() - Remove client callback
 * @hsdev:	Hub device instance.
-* @usage_id:	Usage id of the client (E.g. 0x200076 for Gyro).
+* @usage_id:	Usage id of the client (e.g. 0x200076 for gyro).
 *
-* If there is a callback registred, this call will remove that
-* callbacks, so that it will stop data and event notifications.
+* Removes a previously registered callback for the given usage_id
+* and hsdev. Once removed, the client will no longer receive data or
+* event notifications.
 */
 int sensor_hub_remove_callback(struct hid_sensor_hub_device *hsdev,
 			u32 usage_id);
diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h
index 13b1e65fbdcc..8a03d9696b1c 100644
--- a/include/linux/hid-sensor-ids.h
+++ b/include/linux/hid-sensor-ids.h
@@ -21,11 +21,17 @@
 #define HID_USAGE_SENSOR_ALS					0x200041
 #define HID_USAGE_SENSOR_DATA_LIGHT				0x2004d0
 #define HID_USAGE_SENSOR_LIGHT_ILLUM				0x2004d1
+#define HID_USAGE_SENSOR_LIGHT_COLOR_TEMPERATURE		0x2004d2
+#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY			0x2004d3
+#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_X			0x2004d4
+#define HID_USAGE_SENSOR_LIGHT_CHROMATICITY_Y			0x2004d5
 
 /* PROX (200011) */
 #define HID_USAGE_SENSOR_PROX                                   0x200011
 #define HID_USAGE_SENSOR_DATA_PRESENCE                          0x2004b0
 #define HID_USAGE_SENSOR_HUMAN_PRESENCE                         0x2004b1
+#define HID_USAGE_SENSOR_HUMAN_PROXIMITY                        0x2004b2
+#define HID_USAGE_SENSOR_HUMAN_ATTENTION                        0x2004bd
 
 /* Pressure (200031) */
 #define HID_USAGE_SENSOR_PRESSURE                               0x200031
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 4e4c4fe36911..dce862cafbbd 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -46,7 +46,7 @@ struct hid_item {
 	    __s16  s16;
 	    __u32  u32;
 	    __s32  s32;
-	    __u8  *longdata;
+	    const __u8  *longdata;
 	} data;
 };
 
@@ -81,6 +81,8 @@ struct hid_item {
 #define HID_MAIN_ITEM_TAG_FEATURE		11
 #define HID_MAIN_ITEM_TAG_BEGIN_COLLECTION	10
 #define HID_MAIN_ITEM_TAG_END_COLLECTION	12
+#define HID_MAIN_ITEM_TAG_RESERVED_MIN		13
+#define HID_MAIN_ITEM_TAG_RESERVED_MAX		15
 
 /*
  * HID report descriptor main item contents
@@ -154,6 +156,7 @@ struct hid_item {
 #define HID_UP_TELEPHONY	0x000b0000
 #define HID_UP_CONSUMER		0x000c0000
 #define HID_UP_DIGITIZER	0x000d0000
+#define HID_UP_HAPTIC		0x000e0000
 #define HID_UP_PID		0x000f0000
 #define HID_UP_BATTERY		0x00850000
 #define HID_UP_CAMERA		0x00900000
@@ -218,6 +221,7 @@ struct hid_item {
 #define HID_GD_DOWN		0x00010091
 #define HID_GD_RIGHT		0x00010092
 #define HID_GD_LEFT		0x00010093
+#define HID_GD_DO_NOT_DISTURB	0x0001009b
 /* Microsoft Win8 Wireless Radio Controls CA usage codes */
 #define HID_GD_RFKILL_BTN	0x000100c6
 #define HID_GD_RFKILL_LED	0x000100c7
@@ -313,6 +317,28 @@ struct hid_item {
 #define HID_DG_TOOLSERIALNUMBER	0x000d005b
 #define HID_DG_LATENCYMODE	0x000d0060
 
+#define HID_HP_SIMPLECONTROLLER	0x000e0001
+#define HID_HP_WAVEFORMLIST	0x000e0010
+#define HID_HP_DURATIONLIST	0x000e0011
+#define HID_HP_AUTOTRIGGER	0x000e0020
+#define HID_HP_MANUALTRIGGER	0x000e0021
+#define HID_HP_AUTOTRIGGERASSOCIATEDCONTROL 0x000e0022
+#define HID_HP_INTENSITY	0x000e0023
+#define HID_HP_REPEATCOUNT	0x000e0024
+#define HID_HP_RETRIGGERPERIOD	0x000e0025
+#define HID_HP_WAVEFORMVENDORPAGE	0x000e0026
+#define HID_HP_WAVEFORMVENDORID	0x000e0027
+#define HID_HP_WAVEFORMCUTOFFTIME	0x000e0028
+#define HID_HP_WAVEFORMNONE	0x000e1001
+#define HID_HP_WAVEFORMSTOP	0x000e1002
+#define HID_HP_WAVEFORMCLICK	0x000e1003
+#define HID_HP_WAVEFORMBUZZCONTINUOUS	0x000e1004
+#define HID_HP_WAVEFORMRUMBLECONTINUOUS	0x000e1005
+#define HID_HP_WAVEFORMPRESS	0x000e1006
+#define HID_HP_WAVEFORMRELEASE	0x000e1007
+#define HID_HP_VENDORWAVEFORMMIN	0x000e2001
+#define HID_HP_VENDORWAVEFORMMAX	0x000e2fff
+
 #define HID_BAT_ABSOLUTESTATEOFCHARGE	0x00850065
 #define HID_BAT_CHARGING		0x00850044
 
@@ -341,6 +367,32 @@ struct hid_item {
  */
 #define MAX_USBHID_BOOT_QUIRKS 4
 
+/**
+ * DOC: HID quirks
+ * | @HID_QUIRK_NOTOUCH:
+ * | @HID_QUIRK_IGNORE: ignore this device
+ * | @HID_QUIRK_NOGET:
+ * | @HID_QUIRK_HIDDEV_FORCE:
+ * | @HID_QUIRK_BADPAD:
+ * | @HID_QUIRK_MULTI_INPUT:
+ * | @HID_QUIRK_HIDINPUT_FORCE:
+ * | @HID_QUIRK_ALWAYS_POLL:
+ * | @HID_QUIRK_INPUT_PER_APP:
+ * | @HID_QUIRK_X_INVERT:
+ * | @HID_QUIRK_Y_INVERT:
+ * | @HID_QUIRK_IGNORE_MOUSE:
+ * | @HID_QUIRK_SKIP_OUTPUT_REPORTS:
+ * | @HID_QUIRK_SKIP_OUTPUT_REPORT_ID:
+ * | @HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP:
+ * | @HID_QUIRK_HAVE_SPECIAL_DRIVER:
+ * | @HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE:
+ * | @HID_QUIRK_IGNORE_SPECIAL_DRIVER
+ * | @HID_QUIRK_POWER_ON_AFTER_BACKLIGHT
+ * | @HID_QUIRK_FULLSPEED_INTERVAL:
+ * | @HID_QUIRK_NO_INIT_REPORTS:
+ * | @HID_QUIRK_NO_IGNORE:
+ * | @HID_QUIRK_NO_INPUT_SYNC:
+ */
 /* BIT(0) reserved for backward compatibility, was HID_QUIRK_INVERT */
 #define HID_QUIRK_NOTOUCH			BIT(1)
 #define HID_QUIRK_IGNORE			BIT(2)
@@ -355,11 +407,15 @@ struct hid_item {
 #define HID_QUIRK_INPUT_PER_APP			BIT(11)
 #define HID_QUIRK_X_INVERT			BIT(12)
 #define HID_QUIRK_Y_INVERT			BIT(13)
+#define HID_QUIRK_IGNORE_MOUSE			BIT(14)
 #define HID_QUIRK_SKIP_OUTPUT_REPORTS		BIT(16)
 #define HID_QUIRK_SKIP_OUTPUT_REPORT_ID		BIT(17)
 #define HID_QUIRK_NO_OUTPUT_REPORTS_ON_INTR_EP	BIT(18)
 #define HID_QUIRK_HAVE_SPECIAL_DRIVER		BIT(19)
 #define HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE	BIT(20)
+#define HID_QUIRK_NOINVERT			BIT(21)
+#define HID_QUIRK_IGNORE_SPECIAL_DRIVER		BIT(22)
+#define HID_QUIRK_POWER_ON_AFTER_BACKLIGHT	BIT(23)
 #define HID_QUIRK_FULLSPEED_INTERVAL		BIT(28)
 #define HID_QUIRK_NO_INIT_REPORTS		BIT(29)
 #define HID_QUIRK_NO_IGNORE			BIT(30)
@@ -393,6 +449,12 @@ struct hid_item {
 #define HID_BOOT_PROTOCOL	0
 
 /*
+ * HID units
+ */
+#define HID_UNIT_GRAM		0x0101
+#define HID_UNIT_NEWTON		0xe111
+
+/*
  * This is the global environment of the parser. This information is
  * persistent for main-items. The global environment can be saved and
  * restored with PUSH/POP statements.
@@ -450,9 +512,9 @@ struct hid_usage {
 	__s8	  wheel_factor;		/* 120/resolution_multiplier */
 	__u16     code;			/* input driver code */
 	__u8      type;			/* input driver type */
-	__s8	  hat_min;		/* hat switch fun */
-	__s8	  hat_max;		/* ditto */
-	__s8	  hat_dir;		/* ditto */
+	__s16	  hat_min;		/* hat switch fun */
+	__s16	  hat_max;		/* ditto */
+	__s16	  hat_dir;		/* ditto */
 	__s16	  wheel_accumulated;	/* hi-res wheel */
 };
 
@@ -555,9 +617,9 @@ struct hid_input {
 	struct hid_report *report;
 	struct input_dev *input;
 	const char *name;
-	bool registered;
 	struct list_head reports;	/* the list of reports */
 	unsigned int application;	/* application usage for this input */
+	bool registered;
 };
 
 enum hid_type {
@@ -575,15 +637,17 @@ enum hid_battery_status {
 struct hid_driver;
 struct hid_ll_driver;
 
-struct hid_device {							/* device report descriptor */
-	__u8 *dev_rdesc;
-	unsigned dev_rsize;
-	__u8 *rdesc;
-	unsigned rsize;
+struct hid_device {
+	const __u8 *dev_rdesc;						/* device report descriptor */
+	const __u8 *bpf_rdesc;						/* bpf modified report descriptor, if any */
+	const __u8 *rdesc;						/* currently used report descriptor */
+	unsigned int dev_rsize;
+	unsigned int bpf_rsize;
+	unsigned int rsize;
+	unsigned int collection_size;					/* Number of allocated hid_collections */
 	struct hid_collection *collection;				/* List of HID collections */
-	unsigned collection_size;					/* Number of allocated hid_collections */
-	unsigned maxcollection;						/* Number of parsed collections */
-	unsigned maxapplication;					/* Number of applications */
+	unsigned int maxcollection;						/* Number of parsed collections */
+	unsigned int maxapplication;					/* Number of applications */
 	__u16 bus;							/* BUS ID */
 	__u16 group;							/* Report group */
 	__u32 vendor;							/* Vendor ID */
@@ -597,6 +661,7 @@ struct hid_device {							/* device report descriptor */
 	struct semaphore driver_input_lock;				/* protects the current driver */
 	struct device dev;						/* device */
 	struct hid_driver *driver;
+	void *devres_group_id;						/* ID of probe devres group	*/
 
 	const struct hid_ll_driver *ll_driver;
 	struct mutex ll_open_lock;
@@ -654,14 +719,17 @@ struct hid_device {							/* device report descriptor */
 	struct list_head debug_list;
 	spinlock_t  debug_list_lock;
 	wait_queue_head_t debug_wait;
+	struct kref			ref;
 
 	unsigned int id;						/* system unique id */
 
-#ifdef CONFIG_BPF
+#ifdef CONFIG_HID_BPF
 	struct hid_bpf bpf;						/* hid-bpf data */
-#endif /* CONFIG_BPF */
+#endif /* CONFIG_HID_BPF */
 };
 
+void hiddev_free(struct kref *ref);
+
 #define to_hid_device(pdev) \
 	container_of(pdev, struct hid_device, dev)
 
@@ -705,8 +773,9 @@ struct hid_descriptor {
 	__le16 bcdHID;
 	__u8  bCountryCode;
 	__u8  bNumDescriptors;
+	struct hid_class_descriptor rpt_desc;
 
-	struct hid_class_descriptor desc[1];
+	struct hid_class_descriptor opt_descs[];
 } __attribute__ ((packed));
 
 #define HID_DEVICE(b, g, ven, prod)					\
@@ -757,6 +826,8 @@ struct hid_usage_id {
  * @suspend: invoked on suspend (NULL means nop)
  * @resume: invoked on resume if device was not reset (NULL means nop)
  * @reset_resume: invoked on resume if device was reset (NULL means nop)
+ * @on_hid_hw_open: invoked when hid core opens first instance (NULL means nop)
+ * @on_hid_hw_close: invoked when hid core closes last instance (NULL means nop)
  *
  * probe should return -errno on error, or 0 on success. During probe,
  * input will not be passed to raw_event unless hid_device_io_start is
@@ -776,7 +847,7 @@ struct hid_usage_id {
  * zero from them.
  */
 struct hid_driver {
-	char *name;
+	const char *name;
 	const struct hid_device_id *id_table;
 
 	struct list_head dyn_list;
@@ -794,7 +865,7 @@ struct hid_driver {
 			struct hid_usage *usage, __s32 value);
 	void (*report)(struct hid_device *hdev, struct hid_report *report);
 
-	__u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf,
+	const __u8 *(*report_fixup)(struct hid_device *hdev, __u8 *buf,
 			unsigned int *size);
 
 	int (*input_mapping)(struct hid_device *hdev,
@@ -808,11 +879,13 @@ struct hid_driver {
 	void (*feature_mapping)(struct hid_device *hdev,
 			struct hid_field *field,
 			struct hid_usage *usage);
-#ifdef CONFIG_PM
+
 	int (*suspend)(struct hid_device *hdev, pm_message_t message);
 	int (*resume)(struct hid_device *hdev);
 	int (*reset_resume)(struct hid_device *hdev);
-#endif
+	void (*on_hid_hw_open)(struct hid_device *hdev);
+	void (*on_hid_hw_close)(struct hid_device *hdev);
+
 /* private: */
 	struct device_driver driver;
 };
@@ -884,7 +957,7 @@ extern bool hid_ignore(struct hid_device *);
 extern int hid_add_device(struct hid_device *);
 extern void hid_destroy_device(struct hid_device *);
 
-extern struct bus_type hid_bus_type;
+extern const struct bus_type hid_bus_type;
 
 extern int __must_check __hid_register_driver(struct hid_driver *,
 		struct module *, const char *mod_name);
@@ -911,7 +984,10 @@ extern void hidinput_hid_event(struct hid_device *, struct hid_field *, struct h
 extern void hidinput_report_event(struct hid_device *hid, struct hid_report *report);
 extern int hidinput_connect(struct hid_device *hid, unsigned int force);
 extern void hidinput_disconnect(struct hid_device *);
+void hidinput_reset_resume(struct hid_device *hid);
 
+struct hid_field *hid_find_field(struct hid_device *hdev, unsigned int report_type,
+				 unsigned int application, unsigned int usage);
 int hid_set_field(struct hid_field *, unsigned, __s32);
 int hid_input_report(struct hid_device *hid, enum hid_report_type type, u8 *data, u32 size,
 		     int interrupt);
@@ -925,7 +1001,7 @@ struct hid_device *hid_allocate_device(void);
 struct hid_report *hid_register_report(struct hid_device *device,
 				       enum hid_report_type type, unsigned int id,
 				       unsigned int application);
-int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size);
+int hid_parse_report(struct hid_device *hid, const __u8 *start, unsigned size);
 struct hid_report *hid_validate_values(struct hid_device *hid,
 				       enum hid_report_type type, unsigned int id,
 				       unsigned int field_index,
@@ -944,7 +1020,6 @@ const struct hid_device_id *hid_match_device(struct hid_device *hdev,
 					     struct hid_driver *hdrv);
 bool hid_compare_device_paths(struct hid_device *hdev_a,
 			      struct hid_device *hdev_b, char separator);
-s32 hid_snto32(__u32 value, unsigned n);
 __u32 hid_field_extract(const struct hid_device *hid, __u8 *report,
 		     unsigned offset, unsigned n);
 
@@ -1097,6 +1172,13 @@ int __must_check hid_hw_open(struct hid_device *hdev);
 void hid_hw_close(struct hid_device *hdev);
 void hid_hw_request(struct hid_device *hdev,
 		    struct hid_report *report, enum hid_class_request reqtype);
+int __hid_hw_raw_request(struct hid_device *hdev,
+			 unsigned char reportnum, __u8 *buf,
+			 size_t len, enum hid_report_type rtype,
+			 enum hid_class_request reqtype,
+			 __u64 source, bool from_bpf);
+int __hid_hw_output_report(struct hid_device *hdev, __u8 *buf, size_t len, __u64 source,
+			   bool from_bpf);
 int hid_hw_raw_request(struct hid_device *hdev,
 		       unsigned char reportnum, __u8 *buf,
 		       size_t len, enum hid_report_type rtype,
@@ -1166,7 +1248,11 @@ static inline void hid_hw_wait(struct hid_device *hdev)
 /**
  * hid_report_len - calculate the report length
  *
- * @report: the report we want to know the length
+ * @report: the report whose length we want to know
+ *
+ * The length counts the report ID byte, but only if the ID is nonzero
+ * and therefore is included in the report.  Reports whose ID is zero
+ * never include an ID byte.
  */
 static inline u32 hid_report_len(struct hid_report *report)
 {
@@ -1181,12 +1267,6 @@ unsigned long hid_lookup_quirk(const struct hid_device *hdev);
 int hid_quirks_init(char **quirks_param, __u16 bus, int count);
 void hid_quirks_exit(__u16 bus);
 
-#ifdef CONFIG_HID_PID
-int hid_pidff_init(struct hid_device *hid);
-#else
-#define hid_pidff_init NULL
-#endif
-
 #define dbg_hid(fmt, ...) pr_debug("%s: " fmt, __FILE__, ##__VA_ARGS__)
 
 #define hid_err(hid, fmt, ...)				\
@@ -1195,6 +1275,8 @@ int hid_pidff_init(struct hid_device *hid);
 	dev_notice(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_warn(hid, fmt, ...)				\
 	dev_warn(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_warn_ratelimited(hid, fmt, ...)				\
+	dev_warn_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_info(hid, fmt, ...)				\
 	dev_info(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_dbg(hid, fmt, ...)				\
@@ -1211,4 +1293,15 @@ int hid_pidff_init(struct hid_device *hid);
 #define hid_dbg_once(hid, fmt, ...)			\
 	dev_dbg_once(&(hid)->dev, fmt, ##__VA_ARGS__)
 
+#define hid_err_ratelimited(hid, fmt, ...)			\
+	dev_err_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_notice_ratelimited(hid, fmt, ...)			\
+	dev_notice_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_warn_ratelimited(hid, fmt, ...)			\
+	dev_warn_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_info_ratelimited(hid, fmt, ...)			\
+	dev_info_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_dbg_ratelimited(hid, fmt, ...)			\
+	dev_dbg_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
+
 #endif
diff --git a/include/linux/hid_bpf.h b/include/linux/hid_bpf.h
index e9afb61e6ee0..a2e47dbcf82c 100644
--- a/include/linux/hid_bpf.h
+++ b/include/linux/hid_bpf.h
@@ -4,7 +4,8 @@
 #define __HID_BPF_H
 
 #include <linux/bpf.h>
-#include <linux/spinlock.h>
+#include <linux/mutex.h>
+#include <linux/srcu.h>
 #include <uapi/linux/hid.h>
 
 struct hid_device;
@@ -20,15 +21,9 @@ struct hid_device;
  * struct hid_bpf_ctx - User accessible data for all HID programs
  *
  * ``data`` is not directly accessible from the context. We need to issue
- * a call to ``hid_bpf_get_data()`` in order to get a pointer to that field.
+ * a call to hid_bpf_get_data() in order to get a pointer to that field.
  *
- * All of these fields are currently read-only.
- *
- * @index: program index in the jump table. No special meaning (a smaller index
- *         doesn't mean the program will be executed before another program with
- *         a bigger index).
- * @hid: the ``struct hid_device`` representing the device itself
- * @report_type: used for ``hid_bpf_device_event()``
+ * @hid: the &struct hid_device representing the device itself
  * @allocated_size: Allocated size of data.
  *
  *                  This is how much memory is available and can be requested
@@ -45,84 +40,147 @@ struct hid_device;
  *        ``size`` must always be less or equal than ``allocated_size`` (it is enforced
  *        once all BPF programs have been run).
  * @retval: Return value of the previous program.
+ *
+ * ``hid`` and ``allocated_size`` are read-only, ``size`` and ``retval`` are read-write.
  */
 struct hid_bpf_ctx {
-	__u32 index;
-	const struct hid_device *hid;
+	struct hid_device *hid;
 	__u32 allocated_size;
-	enum hid_report_type report_type;
 	union {
 		__s32 retval;
 		__s32 size;
 	};
 };
 
-/**
- * enum hid_bpf_attach_flags - flags used when attaching a HIF-BPF program
- *
- * @HID_BPF_FLAG_NONE: no specific flag is used, the kernel choses where to
- *                     insert the program
- * @HID_BPF_FLAG_INSERT_HEAD: insert the given program before any other program
- *                            currently attached to the device. This doesn't
- *                            guarantee that this program will always be first
- * @HID_BPF_FLAG_MAX: sentinel value, not to be used by the callers
- */
-enum hid_bpf_attach_flags {
-	HID_BPF_FLAG_NONE = 0,
-	HID_BPF_FLAG_INSERT_HEAD = _BITUL(0),
-	HID_BPF_FLAG_MAX,
-};
-
-/* Following functions are tracepoints that BPF programs can attach to */
-int hid_bpf_device_event(struct hid_bpf_ctx *ctx);
-int hid_bpf_rdesc_fixup(struct hid_bpf_ctx *ctx);
-
-/* Following functions are kfunc that we export to BPF programs */
-/* available everywhere in HID-BPF */
-__u8 *hid_bpf_get_data(struct hid_bpf_ctx *ctx, unsigned int offset, const size_t __sz);
-
-/* only available in syscall */
-int hid_bpf_attach_prog(unsigned int hid_id, int prog_fd, __u32 flags);
-int hid_bpf_hw_request(struct hid_bpf_ctx *ctx, __u8 *buf, size_t buf__sz,
-		       enum hid_report_type rtype, enum hid_class_request reqtype);
-struct hid_bpf_ctx *hid_bpf_allocate_context(unsigned int hid_id);
-void hid_bpf_release_context(struct hid_bpf_ctx *ctx);
-
 /*
  * Below is HID internal
  */
 
-/* internal function to call eBPF programs, not to be used by anybody */
-int __hid_bpf_tail_call(struct hid_bpf_ctx *ctx);
-
 #define HID_BPF_MAX_PROGS_PER_DEV 64
 #define HID_BPF_FLAG_MASK (((HID_BPF_FLAG_MAX - 1) << 1) - 1)
 
-/* types of HID programs to attach to */
-enum hid_bpf_prog_type {
-	HID_BPF_PROG_TYPE_UNDEF = -1,
-	HID_BPF_PROG_TYPE_DEVICE_EVENT,			/* an event is emitted from the device */
-	HID_BPF_PROG_TYPE_RDESC_FIXUP,
-	HID_BPF_PROG_TYPE_MAX,
-};
 
 struct hid_report_enum;
 
-struct hid_bpf_ops {
+struct hid_ops {
 	struct hid_report *(*hid_get_report)(struct hid_report_enum *report_enum, const u8 *data);
 	int (*hid_hw_raw_request)(struct hid_device *hdev,
 				  unsigned char reportnum, __u8 *buf,
 				  size_t len, enum hid_report_type rtype,
-				  enum hid_class_request reqtype);
+				  enum hid_class_request reqtype,
+				  u64 source, bool from_bpf);
+	int (*hid_hw_output_report)(struct hid_device *hdev, __u8 *buf, size_t len,
+				    u64 source, bool from_bpf);
+	int (*hid_input_report)(struct hid_device *hid, enum hid_report_type type,
+				u8 *data, u32 size, int interrupt, u64 source, bool from_bpf,
+				bool lock_already_taken);
 	struct module *owner;
-	struct bus_type *bus_type;
+	const struct bus_type *bus_type;
 };
 
-extern struct hid_bpf_ops *hid_bpf_ops;
+extern const struct hid_ops *hid_ops;
 
-struct hid_bpf_prog_list {
-	u16 prog_idx[HID_BPF_MAX_PROGS_PER_DEV];
-	u8 prog_cnt;
+/**
+ * struct hid_bpf_ops - A BPF struct_ops of callbacks allowing to attach HID-BPF
+ *			programs to a HID device
+ * @hid_id: the HID uniq ID to attach to. This is writeable before ``load()``, and
+ *	    cannot be changed after
+ * @flags: flags used while attaching the struct_ops to the device. Currently only
+ *	   available value is %0 or ``BPF_F_BEFORE``.
+ *	   Writeable only before ``load()``
+ */
+struct hid_bpf_ops {
+	/* hid_id needs to stay first so we can easily change it
+	 * from userspace.
+	 */
+	int			hid_id;
+	u32			flags;
+
+	/* private: do not show up in the docs */
+	struct list_head	list;
+
+	/* public: rest should show up in the docs */
+
+	/**
+	 * @hid_device_event: called whenever an event is coming in from the device
+	 *
+	 * It has the following arguments:
+	 *
+	 * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx
+	 *
+	 * Return: %0 on success and keep processing; a positive
+	 * value to change the incoming size buffer; a negative
+	 * error code to interrupt the processing of this event
+	 *
+	 * Context: Interrupt context.
+	 */
+	int (*hid_device_event)(struct hid_bpf_ctx *ctx, enum hid_report_type report_type,
+				u64 source);
+
+	/**
+	 * @hid_rdesc_fixup: called when the probe function parses the report descriptor
+	 * of the HID device
+	 *
+	 * It has the following arguments:
+	 *
+	 * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx
+	 *
+	 * Return: %0 on success and keep processing; a positive
+	 * value to change the incoming size buffer; a negative
+	 * error code to interrupt the processing of this device
+	 */
+	int (*hid_rdesc_fixup)(struct hid_bpf_ctx *ctx);
+
+	/**
+	 * @hid_hw_request: called whenever a hid_hw_raw_request() call is emitted
+	 * on the HID device
+	 *
+	 * It has the following arguments:
+	 *
+	 * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx
+	 *
+	 * ``reportnum``: the report number, as in hid_hw_raw_request()
+	 *
+	 * ``rtype``: the report type (``HID_INPUT_REPORT``, ``HID_FEATURE_REPORT``,
+	 * ``HID_OUTPUT_REPORT``)
+	 *
+	 * ``reqtype``: the request
+	 *
+	 * ``source``: a u64 referring to a uniq but identifiable source. If %0, the
+	 * kernel itself emitted that call. For hidraw, ``source`` is set
+	 * to the associated ``struct file *``.
+	 *
+	 * Return: %0 to keep processing the request by hid-core; any other value
+	 * stops hid-core from processing that event. A positive value should be
+	 * returned with the number of bytes returned in the incoming buffer; a
+	 * negative error code interrupts the processing of this call.
+	 */
+	int (*hid_hw_request)(struct hid_bpf_ctx *ctx, unsigned char reportnum,
+			       enum hid_report_type rtype, enum hid_class_request reqtype,
+			       u64 source);
+
+	/**
+	 * @hid_hw_output_report: called whenever a hid_hw_output_report() call is emitted
+	 * on the HID device
+	 *
+	 * It has the following arguments:
+	 *
+	 * ``ctx``: The HID-BPF context as &struct hid_bpf_ctx
+	 *
+	 * ``source``: a u64 referring to a uniq but identifiable source. If %0, the
+	 * kernel itself emitted that call. For hidraw, ``source`` is set
+	 * to the associated ``struct file *``.
+	 *
+	 * Return: %0 to keep processing the request by hid-core; any other value
+	 * stops hid-core from processing that event. A positive value should be
+	 * returned with the number of bytes written to the device; a negative error
+	 * code interrupts the processing of this call.
+	 */
+	int (*hid_hw_output_report)(struct hid_bpf_ctx *ctx, u64 source);
+
+
+	/* private: do not show up in the docs */
+	struct hid_device *hdev;
 };
 
 /* stored in each device */
@@ -132,38 +190,46 @@ struct hid_bpf {
 					 * to this HID device
 					 */
 	u32 allocated_data;
-
-	struct hid_bpf_prog_list __rcu *progs[HID_BPF_PROG_TYPE_MAX];	/* attached BPF progs */
 	bool destroyed;			/* prevents the assignment of any progs */
 
-	spinlock_t progs_lock;		/* protects RCU update of progs */
-};
-
-/* specific HID-BPF link when a program is attached to a device */
-struct hid_bpf_link {
-	struct bpf_link link;
-	int hid_table_index;
+	struct hid_bpf_ops *rdesc_ops;
+	struct list_head prog_list;
+	struct mutex prog_list_lock;	/* protects prog_list update */
+	struct srcu_struct srcu;	/* protects prog_list read-only access */
 };
 
 #ifdef CONFIG_HID_BPF
 u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type, u8 *data,
-				  u32 *size, int interrupt);
+				  u32 *size, int interrupt, u64 source, bool from_bpf);
+int dispatch_hid_bpf_raw_requests(struct hid_device *hdev,
+				  unsigned char reportnum, __u8 *buf,
+				  u32 size, enum hid_report_type rtype,
+				  enum hid_class_request reqtype,
+				  u64 source, bool from_bpf);
+int dispatch_hid_bpf_output_report(struct hid_device *hdev, __u8 *buf, u32 size,
+				   u64 source, bool from_bpf);
 int hid_bpf_connect_device(struct hid_device *hdev);
 void hid_bpf_disconnect_device(struct hid_device *hdev);
 void hid_bpf_destroy_device(struct hid_device *hid);
-void hid_bpf_device_init(struct hid_device *hid);
-u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size);
+int hid_bpf_device_init(struct hid_device *hid);
+const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc, unsigned int *size);
 #else /* CONFIG_HID_BPF */
 static inline u8 *dispatch_hid_bpf_device_event(struct hid_device *hid, enum hid_report_type type,
-						u8 *data, u32 *size, int interrupt) { return data; }
+						u8 *data, u32 *size, int interrupt,
+						u64 source, bool from_bpf) { return data; }
+static inline int dispatch_hid_bpf_raw_requests(struct hid_device *hdev,
+						unsigned char reportnum, u8 *buf,
+						u32 size, enum hid_report_type rtype,
+						enum hid_class_request reqtype,
+						u64 source, bool from_bpf) { return 0; }
+static inline int dispatch_hid_bpf_output_report(struct hid_device *hdev, __u8 *buf, u32 size,
+						 u64 source, bool from_bpf) { return 0; }
 static inline int hid_bpf_connect_device(struct hid_device *hdev) { return 0; }
 static inline void hid_bpf_disconnect_device(struct hid_device *hdev) {}
 static inline void hid_bpf_destroy_device(struct hid_device *hid) {}
-static inline void hid_bpf_device_init(struct hid_device *hid) {}
-static inline u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, u8 *rdesc, unsigned int *size)
-{
-	return kmemdup(rdesc, *size, GFP_KERNEL);
-}
+static inline int hid_bpf_device_init(struct hid_device *hid) { return 0; }
+static inline const u8 *call_hid_bpf_rdesc_fixup(struct hid_device *hdev, const u8 *rdesc,
+						 unsigned int *size) { return rdesc; }
 
 #endif /* CONFIG_HID_BPF */
 
diff --git a/include/linux/hidraw.h b/include/linux/hidraw.h
index cd67f4ca5599..18fd30a288de 100644
--- a/include/linux/hidraw.h
+++ b/include/linux/hidraw.h
@@ -32,6 +32,7 @@ struct hidraw_list {
 	struct hidraw *hidraw;
 	struct list_head node;
 	struct mutex read_mutex;
+	bool revoked;
 };
 
 #ifdef CONFIG_HIDRAW
diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index a3028e400a9c..0574c21ca45d 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -7,7 +7,7 @@
  */
 #ifdef CONFIG_KMAP_LOCAL
 void *__kmap_local_pfn_prot(unsigned long pfn, pgprot_t prot);
-void *__kmap_local_page_prot(struct page *page, pgprot_t prot);
+void *__kmap_local_page_prot(const struct page *page, pgprot_t prot);
 void kunmap_local_indexed(const void *vaddr);
 void kmap_local_fork(struct task_struct *tsk);
 void __kmap_local_sched_out(void);
@@ -33,7 +33,7 @@ static inline void kmap_flush_tlb(unsigned long addr) { }
 #endif
 
 void *kmap_high(struct page *page);
-void kunmap_high(struct page *page);
+void kunmap_high(const struct page *page);
 void __kmap_flush_unused(void);
 struct page *__kmap_to_page(void *addr);
 
@@ -50,7 +50,7 @@ static inline void *kmap(struct page *page)
 	return addr;
 }
 
-static inline void kunmap(struct page *page)
+static inline void kunmap(const struct page *page)
 {
 	might_sleep();
 	if (!PageHighMem(page))
@@ -68,18 +68,26 @@ static inline void kmap_flush_unused(void)
 	__kmap_flush_unused();
 }
 
-static inline void *kmap_local_page(struct page *page)
+static inline void *kmap_local_page(const struct page *page)
 {
 	return __kmap_local_page_prot(page, kmap_prot);
 }
 
-static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+static inline void *kmap_local_page_try_from_panic(const struct page *page)
 {
-	struct page *page = folio_page(folio, offset / PAGE_SIZE);
+	if (!PageHighMem(page))
+		return page_address(page);
+	/* If the page is in HighMem, it's not safe to kmap it.*/
+	return NULL;
+}
+
+static inline void *kmap_local_folio(const struct folio *folio, size_t offset)
+{
+	const struct page *page = folio_page(folio, offset / PAGE_SIZE);
 	return __kmap_local_page_prot(page, kmap_prot) + offset % PAGE_SIZE;
 }
 
-static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot)
 {
 	return __kmap_local_page_prot(page, prot);
 }
@@ -94,7 +102,7 @@ static inline void __kunmap_local(const void *vaddr)
 	kunmap_local_indexed(vaddr);
 }
 
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot)
 {
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		migrate_disable();
@@ -105,7 +113,7 @@ static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
 	return __kmap_local_page_prot(page, prot);
 }
 
-static inline void *kmap_atomic(struct page *page)
+static inline void *kmap_atomic(const struct page *page)
 {
 	return kmap_atomic_prot(page, kmap_prot);
 }
@@ -131,22 +139,17 @@ static inline void __kunmap_atomic(const void *addr)
 		preempt_enable();
 }
 
-unsigned int __nr_free_highpages(void);
-extern atomic_long_t _totalhigh_pages;
+unsigned long __nr_free_highpages(void);
+unsigned long __totalhigh_pages(void);
 
-static inline unsigned int nr_free_highpages(void)
+static inline unsigned long nr_free_highpages(void)
 {
 	return __nr_free_highpages();
 }
 
 static inline unsigned long totalhigh_pages(void)
 {
-	return (unsigned long)atomic_long_read(&_totalhigh_pages);
-}
-
-static inline void totalhigh_pages_add(long count)
-{
-	atomic_long_add(count, &_totalhigh_pages);
+	return __totalhigh_pages();
 }
 
 static inline bool is_kmap_addr(const void *x)
@@ -170,27 +173,32 @@ static inline void *kmap(struct page *page)
 	return page_address(page);
 }
 
-static inline void kunmap_high(struct page *page) { }
+static inline void kunmap_high(const struct page *page) { }
 static inline void kmap_flush_unused(void) { }
 
-static inline void kunmap(struct page *page)
+static inline void kunmap(const struct page *page)
 {
 #ifdef ARCH_HAS_FLUSH_ON_KUNMAP
 	kunmap_flush_on_unmap(page_address(page));
 #endif
 }
 
-static inline void *kmap_local_page(struct page *page)
+static inline void *kmap_local_page(const struct page *page)
+{
+	return page_address(page);
+}
+
+static inline void *kmap_local_page_try_from_panic(const struct page *page)
 {
 	return page_address(page);
 }
 
-static inline void *kmap_local_folio(struct folio *folio, size_t offset)
+static inline void *kmap_local_folio(const struct folio *folio, size_t offset)
 {
-	return page_address(&folio->page) + offset;
+	return folio_address(folio) + offset;
 }
 
-static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_local_page_prot(const struct page *page, pgprot_t prot)
 {
 	return kmap_local_page(page);
 }
@@ -207,7 +215,7 @@ static inline void __kunmap_local(const void *addr)
 #endif
 }
 
-static inline void *kmap_atomic(struct page *page)
+static inline void *kmap_atomic(const struct page *page)
 {
 	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		migrate_disable();
@@ -217,7 +225,7 @@ static inline void *kmap_atomic(struct page *page)
 	return page_address(page);
 }
 
-static inline void *kmap_atomic_prot(struct page *page, pgprot_t prot)
+static inline void *kmap_atomic_prot(const struct page *page, pgprot_t prot)
 {
 	return kmap_atomic(page);
 }
@@ -239,8 +247,8 @@ static inline void __kunmap_atomic(const void *addr)
 		preempt_enable();
 }
 
-static inline unsigned int nr_free_highpages(void) { return 0; }
-static inline unsigned long totalhigh_pages(void) { return 0UL; }
+static inline unsigned long nr_free_highpages(void) { return 0; }
+static inline unsigned long totalhigh_pages(void) { return 0; }
 
 static inline bool is_kmap_addr(const void *x)
 {
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 4de1dbcd3ef6..abc20f9810fd 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -43,7 +43,7 @@ static inline void *kmap(struct page *page);
  * Counterpart to kmap(). A NOOP for CONFIG_HIGHMEM=n and for mappings of
  * pages in the low memory area.
  */
-static inline void kunmap(struct page *page);
+static inline void kunmap(const struct page *page);
 
 /**
  * kmap_to_page - Get the page for a kmap'ed address
@@ -93,7 +93,7 @@ static inline void kmap_flush_unused(void);
  * disabling migration in order to keep the virtual address stable across
  * preemption. No caller of kmap_local_page() can rely on this side effect.
  */
-static inline void *kmap_local_page(struct page *page);
+static inline void *kmap_local_page(const struct page *page);
 
 /**
  * kmap_local_folio - Map a page in this folio for temporary usage
@@ -129,7 +129,7 @@ static inline void *kmap_local_page(struct page *page);
  * Context: Can be invoked from any context.
  * Return: The virtual address of @offset.
  */
-static inline void *kmap_local_folio(struct folio *folio, size_t offset);
+static inline void *kmap_local_folio(const struct folio *folio, size_t offset);
 
 /**
  * kmap_atomic - Atomically map a page for temporary usage - Deprecated!
@@ -176,10 +176,10 @@ static inline void *kmap_local_folio(struct folio *folio, size_t offset);
  * kunmap_atomic(vaddr2);
  * kunmap_atomic(vaddr1);
  */
-static inline void *kmap_atomic(struct page *page);
+static inline void *kmap_atomic(const struct page *page);
 
 /* Highmem related interfaces for management code */
-static inline unsigned int nr_free_highpages(void);
+static inline unsigned long nr_free_highpages(void);
 static inline unsigned long totalhigh_pages(void);
 
 #ifndef ARCH_HAS_FLUSH_ANON_PAGE
@@ -226,8 +226,8 @@ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
 {
 	struct folio *folio;
 
-	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr, false);
-	if (folio)
+	folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
+	if (folio && user_alloc_needs_zeroing())
 		clear_user_highpage(&folio->page, vaddr);
 
 	return folio;
@@ -249,10 +249,12 @@ static inline void clear_highpage_kasan_tagged(struct page *page)
 	kunmap_local(kaddr);
 }
 
-#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE
+#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES
 
-static inline void tag_clear_highpage(struct page *page)
+/* Return false to let people know we did not initialize the pages */
+static inline bool tag_clear_highpages(struct page *page, int numpages)
 {
+	return false;
 }
 
 #endif
@@ -292,12 +294,6 @@ static inline void zero_user_segment(struct page *page,
 	zero_user_segments(page, start, end, 0, 0);
 }
 
-static inline void zero_user(struct page *page,
-	unsigned start, unsigned size)
-{
-	zero_user_segments(page, start, start + size, 0, 0);
-}
-
 #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE
 
 static inline void copy_user_highpage(struct page *to, struct page *from,
@@ -352,6 +348,9 @@ static inline int copy_mc_user_highpage(struct page *to, struct page *from,
 	kunmap_local(vto);
 	kunmap_local(vfrom);
 
+	if (ret)
+		memory_failure_queue(page_to_pfn(from), 0);
+
 	return ret;
 }
 
@@ -368,6 +367,9 @@ static inline int copy_mc_highpage(struct page *to, struct page *from)
 	kunmap_local(vto);
 	kunmap_local(vfrom);
 
+	if (ret)
+		memory_failure_queue(page_to_pfn(from), 0);
+
 	return ret;
 }
 #else
@@ -398,6 +400,33 @@ static inline void memcpy_page(struct page *dst_page, size_t dst_off,
 	kunmap_local(dst);
 }
 
+static inline void memcpy_folio(struct folio *dst_folio, size_t dst_off,
+		struct folio *src_folio, size_t src_off, size_t len)
+{
+	VM_BUG_ON(dst_off + len > folio_size(dst_folio));
+	VM_BUG_ON(src_off + len > folio_size(src_folio));
+
+	do {
+		char *dst = kmap_local_folio(dst_folio, dst_off);
+		const char *src = kmap_local_folio(src_folio, src_off);
+		size_t chunk = len;
+
+		if (folio_test_highmem(dst_folio) &&
+		    chunk > PAGE_SIZE - offset_in_page(dst_off))
+			chunk = PAGE_SIZE - offset_in_page(dst_off);
+		if (folio_test_highmem(src_folio) &&
+		    chunk > PAGE_SIZE - offset_in_page(src_off))
+			chunk = PAGE_SIZE - offset_in_page(src_off);
+		memcpy(dst, src, chunk);
+		kunmap_local(src);
+		kunmap_local(dst);
+
+		dst_off += chunk;
+		src_off += chunk;
+		len -= chunk;
+	} while (len > 0);
+}
+
 static inline void memset_page(struct page *page, size_t offset, int val,
 			       size_t len)
 {
@@ -440,6 +469,140 @@ static inline void memzero_page(struct page *page, size_t offset, size_t len)
 }
 
 /**
+ * memcpy_from_folio - Copy a range of bytes from a folio.
+ * @to: The memory to copy to.
+ * @folio: The folio to read from.
+ * @offset: The first byte in the folio to read.
+ * @len: The number of bytes to copy.
+ */
+static inline void memcpy_from_folio(char *to, struct folio *folio,
+		size_t offset, size_t len)
+{
+	VM_BUG_ON(offset + len > folio_size(folio));
+
+	do {
+		const char *from = kmap_local_folio(folio, offset);
+		size_t chunk = len;
+
+		if (folio_test_partial_kmap(folio) &&
+		    chunk > PAGE_SIZE - offset_in_page(offset))
+			chunk = PAGE_SIZE - offset_in_page(offset);
+		memcpy(to, from, chunk);
+		kunmap_local(from);
+
+		to += chunk;
+		offset += chunk;
+		len -= chunk;
+	} while (len > 0);
+}
+
+/**
+ * memcpy_to_folio - Copy a range of bytes to a folio.
+ * @folio: The folio to write to.
+ * @offset: The first byte in the folio to store to.
+ * @from: The memory to copy from.
+ * @len: The number of bytes to copy.
+ */
+static inline void memcpy_to_folio(struct folio *folio, size_t offset,
+		const char *from, size_t len)
+{
+	VM_BUG_ON(offset + len > folio_size(folio));
+
+	do {
+		char *to = kmap_local_folio(folio, offset);
+		size_t chunk = len;
+
+		if (folio_test_partial_kmap(folio) &&
+		    chunk > PAGE_SIZE - offset_in_page(offset))
+			chunk = PAGE_SIZE - offset_in_page(offset);
+		memcpy(to, from, chunk);
+		kunmap_local(to);
+
+		from += chunk;
+		offset += chunk;
+		len -= chunk;
+	} while (len > 0);
+
+	flush_dcache_folio(folio);
+}
+
+/**
+ * folio_zero_tail - Zero the tail of a folio.
+ * @folio: The folio to zero.
+ * @offset: The byte offset in the folio to start zeroing at.
+ * @kaddr: The address the folio is currently mapped to.
+ *
+ * If you have already used kmap_local_folio() to map a folio, written
+ * some data to it and now need to zero the end of the folio (and flush
+ * the dcache), you can use this function.  If you do not have the
+ * folio kmapped (eg the folio has been partially populated by DMA),
+ * use folio_zero_range() or folio_zero_segment() instead.
+ *
+ * Return: An address which can be passed to kunmap_local().
+ */
+static inline __must_check void *folio_zero_tail(struct folio *folio,
+		size_t offset, void *kaddr)
+{
+	size_t len = folio_size(folio) - offset;
+
+	if (folio_test_partial_kmap(folio)) {
+		size_t max = PAGE_SIZE - offset_in_page(offset);
+
+		while (len > max) {
+			memset(kaddr, 0, max);
+			kunmap_local(kaddr);
+			len -= max;
+			offset += max;
+			max = PAGE_SIZE;
+			kaddr = kmap_local_folio(folio, offset);
+		}
+	}
+
+	memset(kaddr, 0, len);
+	flush_dcache_folio(folio);
+
+	return kaddr;
+}
+
+/**
+ * folio_fill_tail - Copy some data to a folio and pad with zeroes.
+ * @folio: The destination folio.
+ * @offset: The offset into @folio at which to start copying.
+ * @from: The data to copy.
+ * @len: How many bytes of data to copy.
+ *
+ * This function is most useful for filesystems which support inline data.
+ * When they want to copy data from the inode into the page cache, this
+ * function does everything for them.  It supports large folios even on
+ * HIGHMEM configurations.
+ */
+static inline void folio_fill_tail(struct folio *folio, size_t offset,
+		const char *from, size_t len)
+{
+	char *to = kmap_local_folio(folio, offset);
+
+	VM_BUG_ON(offset + len > folio_size(folio));
+
+	if (folio_test_partial_kmap(folio)) {
+		size_t max = PAGE_SIZE - offset_in_page(offset);
+
+		while (len > max) {
+			memcpy(to, from, max);
+			kunmap_local(to);
+			len -= max;
+			from += max;
+			offset += max;
+			max = PAGE_SIZE;
+			to = kmap_local_folio(folio, offset);
+		}
+	}
+
+	memcpy(to, from, len);
+	to = folio_zero_tail(folio, offset + len, to + len);
+	kunmap_local(to);
+}
+
+/**
  * memcpy_from_file_folio - Copy some bytes from a file folio.
  * @to: The destination buffer.
  * @folio: The folio to copy from.
@@ -457,7 +620,7 @@ static inline size_t memcpy_from_file_folio(char *to, struct folio *folio,
 	size_t offset = offset_in_folio(folio, pos);
 	char *from = kmap_local_folio(folio, offset);
 
-	if (folio_test_highmem(folio)) {
+	if (folio_test_partial_kmap(folio)) {
 		offset = offset_in_page(offset);
 		len = min_t(size_t, len, PAGE_SIZE - offset);
 	} else
@@ -507,10 +670,18 @@ static inline void folio_zero_range(struct folio *folio,
 	zero_user_segments(&folio->page, start, start + length, 0, 0);
 }
 
-static inline void put_and_unmap_page(struct page *page, void *addr)
+/**
+ * folio_release_kmap - Unmap a folio and drop a refcount.
+ * @folio: The folio to release.
+ * @addr: The address previously returned by a call to kmap_local_folio().
+ *
+ * It is common, eg in directory handling to kmap a folio.  This function
+ * unmaps the folio and drops the refcount that was being held to keep the
+ * folio alive while we accessed it.
+ */
+static inline void folio_release_kmap(struct folio *folio, void *addr)
 {
 	kunmap_local(addr);
-	put_page(page);
+	folio_put(folio);
 }
-
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index a7d54d4d41fd..ca1ec437a3ca 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -43,6 +43,7 @@
 #define QM_MB_CMD_CQC_BT                0x5
 #define QM_MB_CMD_SQC_VFT_V2            0x6
 #define QM_MB_CMD_STOP_QP               0x8
+#define QM_MB_CMD_FLUSH_QM		0x9
 #define QM_MB_CMD_SRC                   0xc
 #define QM_MB_CMD_DST                   0xd
 
@@ -96,35 +97,40 @@
 /* page number for queue file region */
 #define QM_DOORBELL_PAGE_NR		1
 
+#define QM_DEV_ALG_MAX_LEN		256
+
+#define QM_MIG_REGION_SEL		0x100198
+#define QM_MIG_REGION_EN		BIT(0)
+
 /* uacce mode of the driver */
 #define UACCE_MODE_NOUACCE		0 /* don't use uacce */
 #define UACCE_MODE_SVA			1 /* use uacce sva mode */
 #define UACCE_MODE_DESC	"0(default) means only register to crypto, 1 means both register to crypto and uacce"
 
+#define QM_ECC_MBIT			BIT(2)
+
 enum qm_stop_reason {
 	QM_NORMAL,
 	QM_SOFT_RESET,
-	QM_FLR,
+	QM_DOWN,
 };
 
 enum qm_state {
-	QM_INIT = 0,
-	QM_START,
-	QM_CLOSE,
+	QM_WORK = 0,
 	QM_STOP,
 };
 
 enum qp_state {
-	QP_INIT = 1,
-	QP_START,
+	QP_START = 1,
 	QP_STOP,
-	QP_CLOSE,
 };
 
 enum qm_hw_ver {
 	QM_HW_V1 = 0x20,
 	QM_HW_V2 = 0x21,
 	QM_HW_V3 = 0x30,
+	QM_HW_V4 = 0x50,
+	QM_HW_V5 = 0x51,
 };
 
 enum qm_fun_type {
@@ -144,13 +150,32 @@ enum qm_vf_state {
 	QM_NOT_READY,
 };
 
+enum qm_misc_ctl_bits {
+	QM_DRIVER_REMOVING = 0x0,
+	QM_RST_SCHED,
+	QM_RESETTING,
+	QM_MODULE_PARAM,
+};
+
 enum qm_cap_bits {
 	QM_SUPPORT_DB_ISOLATION = 0x0,
 	QM_SUPPORT_FUNC_QOS,
 	QM_SUPPORT_STOP_QP,
+	QM_SUPPORT_STOP_FUNC,
 	QM_SUPPORT_MB_COMMAND,
 	QM_SUPPORT_SVA_PREFETCH,
 	QM_SUPPORT_RPM,
+	QM_SUPPORT_DAE,
+};
+
+struct qm_dev_alg {
+	u64 alg_msk;
+	const char *alg;
+};
+
+struct qm_dev_dfx {
+	u32 dev_state;
+	u32 dev_timeout;
 };
 
 struct dfx_diff_registers {
@@ -181,6 +206,7 @@ struct qm_debug {
 	struct dentry *debug_root;
 	struct dentry *qm_d;
 	struct debugfs_file files[DEBUG_FILE_NUM];
+	struct qm_dev_dfx dev_dfx;
 	unsigned int *qm_last_words;
 	/* ACC engines recoreding last regs */
 	unsigned int *last_words;
@@ -213,19 +239,28 @@ struct hisi_qm_status {
 
 struct hisi_qm;
 
-struct hisi_qm_err_info {
-	char *acpi_rst;
-	u32 msi_wr_port;
+enum acc_err_result {
+	ACC_ERR_NONE,
+	ACC_ERR_NEED_RESET,
+	ACC_ERR_RECOVERED,
+};
+
+struct hisi_qm_err_mask {
 	u32 ecc_2bits_mask;
-	u32 qm_shutdown_mask;
-	u32 dev_shutdown_mask;
-	u32 qm_reset_mask;
-	u32 dev_reset_mask;
+	u32 shutdown_mask;
+	u32 reset_mask;
 	u32 ce;
 	u32 nfe;
 	u32 fe;
 };
 
+struct hisi_qm_err_info {
+	char *acpi_rst;
+	u32 msi_wr_port;
+	struct hisi_qm_err_mask qm_err;
+	struct hisi_qm_err_mask dev_err;
+};
+
 struct hisi_qm_err_status {
 	u32 is_qm_ecc_mbit;
 	u32 is_dev_ecc_mbit;
@@ -241,9 +276,13 @@ struct hisi_qm_err_ini {
 	void (*close_axi_master_ooo)(struct hisi_qm *qm);
 	void (*open_sva_prefetch)(struct hisi_qm *qm);
 	void (*close_sva_prefetch)(struct hisi_qm *qm);
-	void (*log_dev_hw_err)(struct hisi_qm *qm, u32 err_sts);
 	void (*show_last_dfx_regs)(struct hisi_qm *qm);
 	void (*err_info_init)(struct hisi_qm *qm);
+	enum acc_err_result (*get_err_result)(struct hisi_qm *qm);
+	bool (*dev_is_abnormal)(struct hisi_qm *qm);
+	int (*set_priv_status)(struct hisi_qm *qm);
+	void (*disable_axi_error)(struct hisi_qm *qm);
+	void (*enable_axi_error)(struct hisi_qm *qm);
 };
 
 struct hisi_qm_cap_info {
@@ -258,6 +297,28 @@ struct hisi_qm_cap_info {
 	u32 v3_val;
 };
 
+struct hisi_qm_cap_query_info {
+	u32 type;
+	const char *name;
+	u32 offset;
+	u32 v1_val;
+	u32 v2_val;
+	u32 v3_val;
+};
+
+struct hisi_qm_cap_record {
+	u32 type;
+	const char *name;
+	u32 cap_val;
+};
+
+struct hisi_qm_cap_tables {
+	u32 qm_cap_size;
+	struct hisi_qm_cap_record *qm_cap_table;
+	u32 dev_cap_size;
+	struct hisi_qm_cap_record *dev_cap_table;
+};
+
 struct hisi_qm_list {
 	struct mutex lock;
 	struct list_head list;
@@ -269,6 +330,7 @@ struct hisi_qm_poll_data {
 	struct hisi_qm *qm;
 	struct work_struct work;
 	u16 *qp_finish_id;
+	u16 eqe_num;
 };
 
 /**
@@ -285,6 +347,18 @@ struct qm_err_isolate {
 	struct list_head qm_hw_errs;
 };
 
+struct qm_rsv_buf {
+	struct qm_sqc *sqc;
+	struct qm_cqc *cqc;
+	struct qm_eqc *eqc;
+	struct qm_aeqc *aeqc;
+	dma_addr_t sqc_dma;
+	dma_addr_t cqc_dma;
+	dma_addr_t eqc_dma;
+	dma_addr_t aeqc_dma;
+	struct qm_dma qcdma;
+};
+
 struct hisi_qm {
 	enum qm_hw_ver ver;
 	enum qm_fun_type fun_type;
@@ -317,6 +391,7 @@ struct hisi_qm {
 	dma_addr_t cqc_dma;
 	dma_addr_t eqe_dma;
 	dma_addr_t aeqe_dma;
+	struct qm_rsv_buf xqc_buf;
 
 	struct hisi_qm_status status;
 	const struct hisi_qm_err_ini *err_ini;
@@ -334,6 +409,8 @@ struct hisi_qm {
 
 	struct mutex mailbox_lock;
 
+	struct mutex ifc_lock;
+
 	const struct hisi_qm_hw_ops *ops;
 
 	struct qm_debug debug;
@@ -344,7 +421,6 @@ struct hisi_qm {
 	struct work_struct rst_work;
 	struct work_struct cmd_process;
 
-	const char *algs;
 	bool use_sva;
 
 	resource_size_t phys_base;
@@ -355,6 +431,8 @@ struct hisi_qm {
 	u32 mb_qos;
 	u32 type_rate;
 	struct qm_err_isolate isolate_data;
+
+	struct hisi_qm_cap_tables cap_tables;
 };
 
 struct hisi_qp_status {
@@ -395,37 +473,6 @@ struct hisi_qp {
 	struct uacce_queue *uacce_q;
 };
 
-static inline int q_num_set(const char *val, const struct kernel_param *kp,
-			    unsigned int device)
-{
-	struct pci_dev *pdev;
-	u32 n, q_num;
-	int ret;
-
-	if (!val)
-		return -EINVAL;
-
-	pdev = pci_get_device(PCI_VENDOR_ID_HUAWEI, device, NULL);
-	if (!pdev) {
-		q_num = min_t(u32, QM_QNUM_V1, QM_QNUM_V2);
-		pr_info("No device found currently, suppose queue number is %u\n",
-			q_num);
-	} else {
-		if (pdev->revision == QM_HW_V1)
-			q_num = QM_QNUM_V1;
-		else
-			q_num = QM_QNUM_V2;
-
-		pci_dev_put(pdev);
-	}
-
-	ret = kstrtou32(val, 10, &n);
-	if (ret || n < QM_MIN_QNUM || n > q_num)
-		return -EINVAL;
-
-	return param_set_int(val, kp);
-}
-
 static inline int vfs_num_set(const char *val, const struct kernel_param *kp)
 {
 	u32 n;
@@ -471,12 +518,28 @@ static inline void hisi_qm_init_list(struct hisi_qm_list *qm_list)
 	mutex_init(&qm_list->lock);
 }
 
+static inline void hisi_qm_add_list(struct hisi_qm *qm, struct hisi_qm_list *qm_list)
+{
+	mutex_lock(&qm_list->lock);
+	list_add_tail(&qm->list, &qm_list->list);
+	mutex_unlock(&qm_list->lock);
+}
+
+static inline void hisi_qm_del_list(struct hisi_qm *qm, struct hisi_qm_list *qm_list)
+{
+	mutex_lock(&qm_list->lock);
+	list_del(&qm->list);
+	mutex_unlock(&qm_list->lock);
+}
+
+int hisi_qm_q_num_set(const char *val, const struct kernel_param *kp,
+		      unsigned int device);
 int hisi_qm_init(struct hisi_qm *qm);
 void hisi_qm_uninit(struct hisi_qm *qm);
 int hisi_qm_start(struct hisi_qm *qm);
 int hisi_qm_stop(struct hisi_qm *qm, enum qm_stop_reason r);
 int hisi_qm_start_qp(struct hisi_qp *qp, unsigned long arg);
-int hisi_qm_stop_qp(struct hisi_qp *qp);
+void hisi_qm_stop_qp(struct hisi_qp *qp);
 int hisi_qp_send(struct hisi_qp *qp, const void *msg);
 void hisi_qm_debug_init(struct hisi_qm *qm);
 void hisi_qm_debug_regs_clear(struct hisi_qm *qm);
@@ -504,9 +567,9 @@ int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue,
 struct hisi_acc_sgl_pool;
 struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 	struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool,
-	u32 index, dma_addr_t *hw_sgl_dma);
+	u32 index, dma_addr_t *hw_sgl_dma, enum dma_data_direction dir);
 void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl,
-			   struct hisi_acc_hw_sgl *hw_sgl);
+			   struct hisi_acc_hw_sgl *hw_sgl, enum dma_data_direction dir);
 struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 						   u32 count, u32 sge_nr);
 void hisi_acc_free_sgl_pool(struct device *dev,
@@ -516,8 +579,8 @@ int hisi_qm_alloc_qps_node(struct hisi_qm_list *qm_list, int qp_num,
 void hisi_qm_free_qps(struct hisi_qp **qps, int qp_num);
 void hisi_qm_dev_shutdown(struct pci_dev *pdev);
 void hisi_qm_wait_task_finish(struct hisi_qm *qm, struct hisi_qm_list *qm_list);
-int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list);
-void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list);
+int hisi_qm_alg_register(struct hisi_qm *qm, struct hisi_qm_list *qm_list, int guard);
+void hisi_qm_alg_unregister(struct hisi_qm *qm, struct hisi_qm_list *qm_list, int guard);
 int hisi_qm_resume(struct device *dev);
 int hisi_qm_suspend(struct device *dev);
 void hisi_qm_pm_uninit(struct hisi_qm *qm);
@@ -528,6 +591,11 @@ void hisi_qm_regs_dump(struct seq_file *s, struct debugfs_regset32 *regset);
 u32 hisi_qm_get_hw_info(struct hisi_qm *qm,
 			const struct hisi_qm_cap_info *info_table,
 			u32 index, bool is_read);
+u32 hisi_qm_get_cap_value(struct hisi_qm *qm,
+			const struct hisi_qm_cap_query_info *info_table,
+			u32 index, bool is_read);
+int hisi_qm_set_algs(struct hisi_qm *qm, u64 alg_msk, const struct qm_dev_alg *dev_algs,
+		     u32 dev_algs_size);
 
 /* Used by VFIO ACC live migration driver */
 struct pci_driver *hisi_sec_get_pf_driver(void);
diff --git a/include/linux/hmm-dma.h b/include/linux/hmm-dma.h
new file mode 100644
index 000000000000..f58b9fc71999
--- /dev/null
+++ b/include/linux/hmm-dma.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (c) 2024 NVIDIA Corporation & Affiliates */
+#ifndef LINUX_HMM_DMA_H
+#define LINUX_HMM_DMA_H
+
+#include <linux/dma-mapping.h>
+
+struct dma_iova_state;
+struct pci_p2pdma_map_state;
+
+/*
+ * struct hmm_dma_map - array of PFNs and DMA addresses
+ *
+ * @state: DMA IOVA state
+ * @pfns: array of PFNs
+ * @dma_list: array of DMA addresses
+ * @dma_entry_size: size of each DMA entry in the array
+ */
+struct hmm_dma_map {
+	struct dma_iova_state state;
+	unsigned long *pfn_list;
+	dma_addr_t *dma_list;
+	size_t dma_entry_size;
+};
+
+int hmm_dma_map_alloc(struct device *dev, struct hmm_dma_map *map,
+		      size_t nr_entries, size_t dma_entry_size);
+void hmm_dma_map_free(struct device *dev, struct hmm_dma_map *map);
+dma_addr_t hmm_dma_map_pfn(struct device *dev, struct hmm_dma_map *map,
+			   size_t idx,
+			   struct pci_p2pdma_map_state *p2pdma_state);
+bool hmm_dma_unmap_pfn(struct device *dev, struct hmm_dma_map *map, size_t idx);
+#endif /* LINUX_HMM_DMA_H */
diff --git a/include/linux/hmm.h b/include/linux/hmm.h
index 126a36571667..db75ffc949a7 100644
--- a/include/linux/hmm.h
+++ b/include/linux/hmm.h
@@ -23,6 +23,10 @@ struct mmu_interval_notifier;
  * HMM_PFN_WRITE - if the page memory can be written to (requires HMM_PFN_VALID)
  * HMM_PFN_ERROR - accessing the pfn is impossible and the device should
  *                 fail. ie poisoned memory, special pages, no vma, etc
+ * HMM_PFN_P2PDMA - P2P page
+ * HMM_PFN_P2PDMA_BUS - Bus mapped P2P transfer
+ * HMM_PFN_DMA_MAPPED - Flag preserved on input-to-output transformation
+ *                      to mark that page is already DMA mapped
  *
  * On input:
  * 0                 - Return the current state of the page, do not fault it.
@@ -36,13 +40,21 @@ enum hmm_pfn_flags {
 	HMM_PFN_VALID = 1UL << (BITS_PER_LONG - 1),
 	HMM_PFN_WRITE = 1UL << (BITS_PER_LONG - 2),
 	HMM_PFN_ERROR = 1UL << (BITS_PER_LONG - 3),
-	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 8),
+	/*
+	 * Sticky flags, carried from input to output,
+	 * don't forget to update HMM_PFN_INOUT_FLAGS
+	 */
+	HMM_PFN_DMA_MAPPED = 1UL << (BITS_PER_LONG - 4),
+	HMM_PFN_P2PDMA     = 1UL << (BITS_PER_LONG - 5),
+	HMM_PFN_P2PDMA_BUS = 1UL << (BITS_PER_LONG - 6),
+
+	HMM_PFN_ORDER_SHIFT = (BITS_PER_LONG - 11),
 
 	/* Input flags */
 	HMM_PFN_REQ_FAULT = HMM_PFN_VALID,
 	HMM_PFN_REQ_WRITE = HMM_PFN_WRITE,
 
-	HMM_PFN_FLAGS = 0xFFUL << HMM_PFN_ORDER_SHIFT,
+	HMM_PFN_FLAGS = ~((1UL << HMM_PFN_ORDER_SHIFT) - 1),
 };
 
 /*
@@ -58,6 +70,14 @@ static inline struct page *hmm_pfn_to_page(unsigned long hmm_pfn)
 }
 
 /*
+ * hmm_pfn_to_phys() - return physical address pointed to by a device entry
+ */
+static inline phys_addr_t hmm_pfn_to_phys(unsigned long hmm_pfn)
+{
+	return __pfn_to_phys(hmm_pfn & ~HMM_PFN_FLAGS);
+}
+
+/*
  * hmm_pfn_to_map_order() - return the CPU mapping size order
  *
  * This is optionally useful to optimize processing of the pfn result
diff --git a/include/linux/host1x.h b/include/linux/host1x.h
index 9c8119ed13a4..9fa9c30a34e6 100644
--- a/include/linux/host1x.h
+++ b/include/linux/host1x.h
@@ -14,12 +14,17 @@
 
 enum host1x_class {
 	HOST1X_CLASS_HOST1X = 0x1,
+	HOST1X_CLASS_NVJPG1 = 0x7,
+	HOST1X_CLASS_NVENC = 0x21,
+	HOST1X_CLASS_NVENC1 = 0x22,
 	HOST1X_CLASS_GR2D = 0x51,
 	HOST1X_CLASS_GR2D_SB = 0x52,
 	HOST1X_CLASS_VIC = 0x5D,
 	HOST1X_CLASS_GR3D = 0x60,
+	HOST1X_CLASS_NVJPG = 0xC0,
 	HOST1X_CLASS_NVDEC = 0xF0,
 	HOST1X_CLASS_NVDEC1 = 0xF5,
+	HOST1X_CLASS_OFA = 0xF8,
 };
 
 struct host1x;
@@ -466,6 +471,7 @@ struct host1x_memory_context {
 	refcount_t ref;
 	struct pid *owner;
 
+	struct device_dma_parameters dma_parms;
 	struct device dev;
 	u64 dma_mask;
 	u32 stream_id;
diff --git a/include/linux/host1x_context_bus.h b/include/linux/host1x_context_bus.h
index 72462737a6db..c928cb432680 100644
--- a/include/linux/host1x_context_bus.h
+++ b/include/linux/host1x_context_bus.h
@@ -9,7 +9,7 @@
 #include <linux/device.h>
 
 #ifdef CONFIG_TEGRA_HOST1X_CONTEXT_BUS
-extern struct bus_type host1x_context_device_bus_type;
+extern const struct bus_type host1x_context_device_bus_type;
 #endif
 
 #endif
diff --git a/include/linux/hrtimer.h b/include/linux/hrtimer.h
index 0ee140176f10..2cf1bf65b225 100644
--- a/include/linux/hrtimer.h
+++ b/include/linux/hrtimer.h
@@ -13,16 +13,12 @@
 #define _LINUX_HRTIMER_H
 
 #include <linux/hrtimer_defs.h>
-#include <linux/rbtree.h>
+#include <linux/hrtimer_types.h>
 #include <linux/init.h>
 #include <linux/list.h>
-#include <linux/percpu.h>
-#include <linux/seqlock.h>
+#include <linux/percpu-defs.h>
+#include <linux/rbtree.h>
 #include <linux/timer.h>
-#include <linux/timerqueue.h>
-
-struct hrtimer_clock_base;
-struct hrtimer_cpu_base;
 
 /*
  * Mode arguments of xxx_hrtimer functions:
@@ -60,14 +56,6 @@ enum hrtimer_mode {
 };
 
 /*
- * Return values for the callback function
- */
-enum hrtimer_restart {
-	HRTIMER_NORESTART,	/* Timer is not restarted */
-	HRTIMER_RESTART,	/* Timer must be restarted */
-};
-
-/*
  * Values to track state of the timer
  *
  * Possible states:
@@ -95,38 +83,6 @@ enum hrtimer_restart {
 #define HRTIMER_STATE_ENQUEUED	0x01
 
 /**
- * struct hrtimer - the basic hrtimer structure
- * @node:	timerqueue node, which also manages node.expires,
- *		the absolute expiry time in the hrtimers internal
- *		representation. The time is related to the clock on
- *		which the timer is based. Is setup by adding
- *		slack to the _softexpires value. For non range timers
- *		identical to _softexpires.
- * @_softexpires: the absolute earliest expiry time of the hrtimer.
- *		The time which was given as expiry time when the timer
- *		was armed.
- * @function:	timer expiry callback function
- * @base:	pointer to the timer base (per cpu and per clock)
- * @state:	state information (See bit values above)
- * @is_rel:	Set if the timer was armed relative
- * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
- * @is_hard:	Set if hrtimer will be expired in hard interrupt context
- *		even on RT.
- *
- * The hrtimer structure must be initialized by hrtimer_init()
- */
-struct hrtimer {
-	struct timerqueue_node		node;
-	ktime_t				_softexpires;
-	enum hrtimer_restart		(*function)(struct hrtimer *);
-	struct hrtimer_clock_base	*base;
-	u8				state;
-	u8				is_rel;
-	u8				is_soft;
-	u8				is_hard;
-};
-
-/**
  * struct hrtimer_sleeper - simple sleeper structure
  * @timer:	embedded timer structure
  * @task:	task to wake up
@@ -138,105 +94,6 @@ struct hrtimer_sleeper {
 	struct task_struct *task;
 };
 
-#ifdef CONFIG_64BIT
-# define __hrtimer_clock_base_align	____cacheline_aligned
-#else
-# define __hrtimer_clock_base_align
-#endif
-
-/**
- * struct hrtimer_clock_base - the timer base for a specific clock
- * @cpu_base:		per cpu clock base
- * @index:		clock type index for per_cpu support when moving a
- *			timer to a base on another cpu.
- * @clockid:		clock id for per_cpu support
- * @seq:		seqcount around __run_hrtimer
- * @running:		pointer to the currently running hrtimer
- * @active:		red black tree root node for the active timers
- * @get_time:		function to retrieve the current time of the clock
- * @offset:		offset of this clock to the monotonic base
- */
-struct hrtimer_clock_base {
-	struct hrtimer_cpu_base	*cpu_base;
-	unsigned int		index;
-	clockid_t		clockid;
-	seqcount_raw_spinlock_t	seq;
-	struct hrtimer		*running;
-	struct timerqueue_head	active;
-	ktime_t			(*get_time)(void);
-	ktime_t			offset;
-} __hrtimer_clock_base_align;
-
-enum  hrtimer_base_type {
-	HRTIMER_BASE_MONOTONIC,
-	HRTIMER_BASE_REALTIME,
-	HRTIMER_BASE_BOOTTIME,
-	HRTIMER_BASE_TAI,
-	HRTIMER_BASE_MONOTONIC_SOFT,
-	HRTIMER_BASE_REALTIME_SOFT,
-	HRTIMER_BASE_BOOTTIME_SOFT,
-	HRTIMER_BASE_TAI_SOFT,
-	HRTIMER_MAX_CLOCK_BASES,
-};
-
-/**
- * struct hrtimer_cpu_base - the per cpu clock bases
- * @lock:		lock protecting the base and associated clock bases
- *			and timers
- * @cpu:		cpu number
- * @active_bases:	Bitfield to mark bases with active timers
- * @clock_was_set_seq:	Sequence counter of clock was set events
- * @hres_active:	State of high resolution mode
- * @in_hrtirq:		hrtimer_interrupt() is currently executing
- * @hang_detected:	The last hrtimer interrupt detected a hang
- * @softirq_activated:	displays, if the softirq is raised - update of softirq
- *			related settings is not required then.
- * @nr_events:		Total number of hrtimer interrupt events
- * @nr_retries:		Total number of hrtimer interrupt retries
- * @nr_hangs:		Total number of hrtimer interrupt hangs
- * @max_hang_time:	Maximum time spent in hrtimer_interrupt
- * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
- *			 expired
- * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
- *			callback to finish.
- * @expires_next:	absolute time of the next event, is required for remote
- *			hrtimer enqueue; it is the total first expiry time (hard
- *			and soft hrtimer are taken into account)
- * @next_timer:		Pointer to the first expiring timer
- * @softirq_expires_next: Time to check, if soft queues needs also to be expired
- * @softirq_next_timer: Pointer to the first expiring softirq based timer
- * @clock_base:		array of clock bases for this cpu
- *
- * Note: next_timer is just an optimization for __remove_hrtimer().
- *	 Do not dereference the pointer because it is not reliable on
- *	 cross cpu removals.
- */
-struct hrtimer_cpu_base {
-	raw_spinlock_t			lock;
-	unsigned int			cpu;
-	unsigned int			active_bases;
-	unsigned int			clock_was_set_seq;
-	unsigned int			hres_active		: 1,
-					in_hrtirq		: 1,
-					hang_detected		: 1,
-					softirq_activated       : 1;
-#ifdef CONFIG_HIGH_RES_TIMERS
-	unsigned int			nr_events;
-	unsigned short			nr_retries;
-	unsigned short			nr_hangs;
-	unsigned int			max_hang_time;
-#endif
-#ifdef CONFIG_PREEMPT_RT
-	spinlock_t			softirq_expiry_lock;
-	atomic_t			timer_waiters;
-#endif
-	ktime_t				expires_next;
-	struct hrtimer			*next_timer;
-	ktime_t				softirq_expires_next;
-	struct hrtimer			*softirq_next_timer;
-	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
-} ____cacheline_aligned;
-
 static inline void hrtimer_set_expires(struct hrtimer *timer, ktime_t time)
 {
 	timer->node.expires = time;
@@ -297,14 +154,11 @@ static inline s64 hrtimer_get_expires_ns(const struct hrtimer *timer)
 	return ktime_to_ns(timer->node.expires);
 }
 
-static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
-{
-	return ktime_sub(timer->node.expires, timer->base->get_time());
-}
+ktime_t hrtimer_cb_get_time(const struct hrtimer *timer);
 
-static inline ktime_t hrtimer_cb_get_time(struct hrtimer *timer)
+static inline ktime_t hrtimer_expires_remaining(const struct hrtimer *timer)
 {
-	return timer->base->get_time();
+	return ktime_sub(timer->node.expires, hrtimer_cb_get_time(timer));
 }
 
 static inline int hrtimer_is_hres_active(struct hrtimer *timer)
@@ -343,8 +197,7 @@ __hrtimer_expires_remaining_adjusted(const struct hrtimer *timer, ktime_t now)
 static inline ktime_t
 hrtimer_expires_remaining_adjusted(const struct hrtimer *timer)
 {
-	return __hrtimer_expires_remaining_adjusted(timer,
-						    timer->base->get_time());
+	return __hrtimer_expires_remaining_adjusted(timer, hrtimer_cb_get_time(timer));
 }
 
 #ifdef CONFIG_TIMERFD
@@ -366,37 +219,25 @@ static inline void hrtimer_cancel_wait_running(struct hrtimer *timer)
 }
 #endif
 
+static inline enum hrtimer_restart hrtimer_dummy_timeout(struct hrtimer *unused)
+{
+	return HRTIMER_NORESTART;
+}
+
 /* Exported timer functions: */
 
 /* Initialize timers: */
-extern void hrtimer_init(struct hrtimer *timer, clockid_t which_clock,
-			 enum hrtimer_mode mode);
-extern void hrtimer_init_sleeper(struct hrtimer_sleeper *sl, clockid_t clock_id,
-				 enum hrtimer_mode mode);
+extern void hrtimer_setup(struct hrtimer *timer, enum hrtimer_restart (*function)(struct hrtimer *),
+			  clockid_t clock_id, enum hrtimer_mode mode);
+extern void hrtimer_setup_on_stack(struct hrtimer *timer,
+				   enum hrtimer_restart (*function)(struct hrtimer *),
+				   clockid_t clock_id, enum hrtimer_mode mode);
+extern void hrtimer_setup_sleeper_on_stack(struct hrtimer_sleeper *sl, clockid_t clock_id,
+					   enum hrtimer_mode mode);
 
 #ifdef CONFIG_DEBUG_OBJECTS_TIMERS
-extern void hrtimer_init_on_stack(struct hrtimer *timer, clockid_t which_clock,
-				  enum hrtimer_mode mode);
-extern void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
-					  clockid_t clock_id,
-					  enum hrtimer_mode mode);
-
 extern void destroy_hrtimer_on_stack(struct hrtimer *timer);
 #else
-static inline void hrtimer_init_on_stack(struct hrtimer *timer,
-					 clockid_t which_clock,
-					 enum hrtimer_mode mode)
-{
-	hrtimer_init(timer, which_clock, mode);
-}
-
-static inline void hrtimer_init_sleeper_on_stack(struct hrtimer_sleeper *sl,
-						 clockid_t clock_id,
-						 enum hrtimer_mode mode)
-{
-	hrtimer_init_sleeper(sl, clock_id, mode);
-}
-
 static inline void destroy_hrtimer_on_stack(struct hrtimer *timer) { }
 #endif
 
@@ -480,30 +321,45 @@ static inline int hrtimer_callback_running(struct hrtimer *timer)
 	return timer->base->running == timer;
 }
 
+/**
+ * hrtimer_update_function - Update the timer's callback function
+ * @timer:	Timer to update
+ * @function:	New callback function
+ *
+ * Only safe to call if the timer is not enqueued. Can be called in the callback function if the
+ * timer is not enqueued at the same time (see the comments above HRTIMER_STATE_ENQUEUED).
+ */
+static inline void hrtimer_update_function(struct hrtimer *timer,
+					   enum hrtimer_restart (*function)(struct hrtimer *))
+{
+#ifdef CONFIG_PROVE_LOCKING
+	guard(raw_spinlock_irqsave)(&timer->base->cpu_base->lock);
+
+	if (WARN_ON_ONCE(hrtimer_is_queued(timer)))
+		return;
+
+	if (WARN_ON_ONCE(!function))
+		return;
+#endif
+	ACCESS_PRIVATE(timer, function) = function;
+}
+
 /* Forward a hrtimer so it expires after now: */
 extern u64
 hrtimer_forward(struct hrtimer *timer, ktime_t now, ktime_t interval);
 
 /**
- * hrtimer_forward_now - forward the timer expiry so it expires after now
+ * hrtimer_forward_now() - forward the timer expiry so it expires after now
  * @timer:	hrtimer to forward
  * @interval:	the interval to forward
  *
- * Forward the timer expiry so it will expire after the current time
- * of the hrtimer clock base. Returns the number of overruns.
- *
- * Can be safely called from the callback function of @timer. If
- * called from other contexts @timer must neither be enqueued nor
- * running the callback and the caller needs to take care of
- * serialization.
- *
- * Note: This only updates the timer expiry value and does not requeue
- * the timer.
+ * It is a variant of hrtimer_forward(). The timer will expire after the current
+ * time of the hrtimer clock base. See hrtimer_forward() for details.
  */
 static inline u64 hrtimer_forward_now(struct hrtimer *timer,
 				      ktime_t interval)
 {
-	return hrtimer_forward(timer, timer->base->get_time(), interval);
+	return hrtimer_forward(timer, hrtimer_cb_get_time(timer), interval);
 }
 
 /* Precise sleep: */
@@ -530,10 +386,11 @@ extern void __init hrtimers_init(void);
 extern void sysrq_timer_list_show(void);
 
 int hrtimers_prepare_cpu(unsigned int cpu);
+int hrtimers_cpu_starting(unsigned int cpu);
 #ifdef CONFIG_HOTPLUG_CPU
-int hrtimers_dead_cpu(unsigned int cpu);
+int hrtimers_cpu_dying(unsigned int cpu);
 #else
-#define hrtimers_dead_cpu	NULL
+#define hrtimers_cpu_dying	NULL
 #endif
 
 #endif
diff --git a/include/linux/hrtimer_defs.h b/include/linux/hrtimer_defs.h
index 2d3e3c5fb946..aa49ffa130e5 100644
--- a/include/linux/hrtimer_defs.h
+++ b/include/linux/hrtimer_defs.h
@@ -3,6 +3,8 @@
 #define _LINUX_HRTIMER_DEFS_H
 
 #include <linux/ktime.h>
+#include <linux/timerqueue.h>
+#include <linux/seqlock.h>
 
 #ifdef CONFIG_HIGH_RES_TIMERS
 
@@ -24,4 +26,105 @@
 
 #endif
 
+#ifdef CONFIG_64BIT
+# define __hrtimer_clock_base_align	____cacheline_aligned
+#else
+# define __hrtimer_clock_base_align
+#endif
+
+/**
+ * struct hrtimer_clock_base - the timer base for a specific clock
+ * @cpu_base:		per cpu clock base
+ * @index:		clock type index for per_cpu support when moving a
+ *			timer to a base on another cpu.
+ * @clockid:		clock id for per_cpu support
+ * @seq:		seqcount around __run_hrtimer
+ * @running:		pointer to the currently running hrtimer
+ * @active:		red black tree root node for the active timers
+ * @offset:		offset of this clock to the monotonic base
+ */
+struct hrtimer_clock_base {
+	struct hrtimer_cpu_base	*cpu_base;
+	unsigned int		index;
+	clockid_t		clockid;
+	seqcount_raw_spinlock_t	seq;
+	struct hrtimer		*running;
+	struct timerqueue_head	active;
+	ktime_t			offset;
+} __hrtimer_clock_base_align;
+
+enum  hrtimer_base_type {
+	HRTIMER_BASE_MONOTONIC,
+	HRTIMER_BASE_REALTIME,
+	HRTIMER_BASE_BOOTTIME,
+	HRTIMER_BASE_TAI,
+	HRTIMER_BASE_MONOTONIC_SOFT,
+	HRTIMER_BASE_REALTIME_SOFT,
+	HRTIMER_BASE_BOOTTIME_SOFT,
+	HRTIMER_BASE_TAI_SOFT,
+	HRTIMER_MAX_CLOCK_BASES,
+};
+
+/**
+ * struct hrtimer_cpu_base - the per cpu clock bases
+ * @lock:		lock protecting the base and associated clock bases
+ *			and timers
+ * @cpu:		cpu number
+ * @active_bases:	Bitfield to mark bases with active timers
+ * @clock_was_set_seq:	Sequence counter of clock was set events
+ * @hres_active:	State of high resolution mode
+ * @in_hrtirq:		hrtimer_interrupt() is currently executing
+ * @hang_detected:	The last hrtimer interrupt detected a hang
+ * @softirq_activated:	displays, if the softirq is raised - update of softirq
+ *			related settings is not required then.
+ * @nr_events:		Total number of hrtimer interrupt events
+ * @nr_retries:		Total number of hrtimer interrupt retries
+ * @nr_hangs:		Total number of hrtimer interrupt hangs
+ * @max_hang_time:	Maximum time spent in hrtimer_interrupt
+ * @softirq_expiry_lock: Lock which is taken while softirq based hrtimer are
+ *			 expired
+ * @online:		CPU is online from an hrtimers point of view
+ * @timer_waiters:	A hrtimer_cancel() invocation waits for the timer
+ *			callback to finish.
+ * @expires_next:	absolute time of the next event, is required for remote
+ *			hrtimer enqueue; it is the total first expiry time (hard
+ *			and soft hrtimer are taken into account)
+ * @next_timer:		Pointer to the first expiring timer
+ * @softirq_expires_next: Time to check, if soft queues needs also to be expired
+ * @softirq_next_timer: Pointer to the first expiring softirq based timer
+ * @clock_base:		array of clock bases for this cpu
+ *
+ * Note: next_timer is just an optimization for __remove_hrtimer().
+ *	 Do not dereference the pointer because it is not reliable on
+ *	 cross cpu removals.
+ */
+struct hrtimer_cpu_base {
+	raw_spinlock_t			lock;
+	unsigned int			cpu;
+	unsigned int			active_bases;
+	unsigned int			clock_was_set_seq;
+	unsigned int			hres_active		: 1,
+					in_hrtirq		: 1,
+					hang_detected		: 1,
+					softirq_activated       : 1,
+					online			: 1;
+#ifdef CONFIG_HIGH_RES_TIMERS
+	unsigned int			nr_events;
+	unsigned short			nr_retries;
+	unsigned short			nr_hangs;
+	unsigned int			max_hang_time;
+#endif
+#ifdef CONFIG_PREEMPT_RT
+	spinlock_t			softirq_expiry_lock;
+	atomic_t			timer_waiters;
+#endif
+	ktime_t				expires_next;
+	struct hrtimer			*next_timer;
+	ktime_t				softirq_expires_next;
+	struct hrtimer			*softirq_next_timer;
+	struct hrtimer_clock_base	clock_base[HRTIMER_MAX_CLOCK_BASES];
+	call_single_data_t		csd;
+} ____cacheline_aligned;
+
+
 #endif
diff --git a/include/linux/hrtimer_types.h b/include/linux/hrtimer_types.h
new file mode 100644
index 000000000000..8fbbb6bdf7a1
--- /dev/null
+++ b/include/linux/hrtimer_types.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_HRTIMER_TYPES_H
+#define _LINUX_HRTIMER_TYPES_H
+
+#include <linux/types.h>
+#include <linux/timerqueue_types.h>
+
+struct hrtimer_clock_base;
+
+/*
+ * Return values for the callback function
+ */
+enum hrtimer_restart {
+	HRTIMER_NORESTART,	/* Timer is not restarted */
+	HRTIMER_RESTART,	/* Timer must be restarted */
+};
+
+/**
+ * struct hrtimer - the basic hrtimer structure
+ * @node:	timerqueue node, which also manages node.expires,
+ *		the absolute expiry time in the hrtimers internal
+ *		representation. The time is related to the clock on
+ *		which the timer is based. Is setup by adding
+ *		slack to the _softexpires value. For non range timers
+ *		identical to _softexpires.
+ * @_softexpires: the absolute earliest expiry time of the hrtimer.
+ *		The time which was given as expiry time when the timer
+ *		was armed.
+ * @function:	timer expiry callback function
+ * @base:	pointer to the timer base (per cpu and per clock)
+ * @state:	state information (See bit values above)
+ * @is_rel:	Set if the timer was armed relative
+ * @is_soft:	Set if hrtimer will be expired in soft interrupt context.
+ * @is_hard:	Set if hrtimer will be expired in hard interrupt context
+ *		even on RT.
+ *
+ * The hrtimer structure must be initialized by hrtimer_setup()
+ */
+struct hrtimer {
+	struct timerqueue_node		node;
+	ktime_t				_softexpires;
+	enum hrtimer_restart		(*__private function)(struct hrtimer *);
+	struct hrtimer_clock_base	*base;
+	u8				state;
+	u8				is_rel;
+	u8				is_soft;
+	u8				is_hard;
+};
+
+#endif /* _LINUX_HRTIMER_TYPES_H */
diff --git a/include/linux/hsi/ssi_protocol.h b/include/linux/hsi/ssi_protocol.h
index 2d6f3cfa7dea..972434daa000 100644
--- a/include/linux/hsi/ssi_protocol.h
+++ b/include/linux/hsi/ssi_protocol.h
@@ -24,6 +24,7 @@ int ssip_slave_stop_tx(struct hsi_client *master);
 void ssip_reset_event(struct hsi_client *master);
 
 int ssip_slave_running(struct hsi_client *master);
+void ssi_waketest(struct hsi_client *cl, unsigned int enable);
 
 #endif /* __LINUX_SSIP_SLAVE_H__ */
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 20284387b841..ae7f21aad0ac 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -2,16 +2,16 @@
 #ifndef _LINUX_HUGE_MM_H
 #define _LINUX_HUGE_MM_H
 
-#include <linux/sched/coredump.h>
 #include <linux/mm_types.h>
 
 #include <linux/fs.h> /* only for vma_is_dax() */
+#include <linux/kobject.h>
 
 vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf);
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-void huge_pmd_set_accessed(struct vm_fault *vmf);
+bool huge_pmd_set_accessed(struct vm_fault *vmf);
 int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pud_t *dst_pud, pud_t *src_pud, unsigned long addr,
 		  struct vm_area_struct *vma);
@@ -25,9 +25,6 @@ static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud)
 #endif
 
 vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf);
-struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
-				   unsigned long addr, pmd_t *pmd,
-				   unsigned int flags);
 bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			   pmd_t *pmd, unsigned long addr, unsigned long next);
 int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd,
@@ -40,8 +37,14 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
 		    unsigned long cp_flags);
 
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn,
+			      bool write);
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn,
+			      bool write);
+vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
+				bool write);
+vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
+				bool write);
 
 enum transparent_hugepage_flag {
 	TRANSPARENT_HUGEPAGE_UNSUPPORTED,
@@ -66,149 +69,440 @@ ssize_t single_hugepage_flag_show(struct kobject *kobj,
 				  struct kobj_attribute *attr, char *buf,
 				  enum transparent_hugepage_flag flag);
 extern struct kobj_attribute shmem_enabled_attr;
+extern struct kobj_attribute thpsize_shmem_enabled_attr;
 
-#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
-#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
+/*
+ * Mask of all large folio orders supported for anonymous THP; all orders up to
+ * and including PMD_ORDER, except order-0 (which is not "huge") and order-1
+ * (which is a limitation of the THP implementation).
+ */
+#define THP_ORDERS_ALL_ANON	((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/*
+ * Mask of all large folio orders supported for file THP. Folios in a DAX
+ * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to
+ * it.  Same to PFNMAPs where there's neither page* nor pagecache.
+ */
+#define THP_ORDERS_ALL_SPECIAL		\
+	(BIT(PMD_ORDER) | BIT(PUD_ORDER))
+#define THP_ORDERS_ALL_FILE_DEFAULT	\
+	((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0))
+
+/*
+ * Mask of all large folio orders supported for THP.
+ */
+#define THP_ORDERS_ALL	\
+	(THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_SPECIAL | THP_ORDERS_ALL_FILE_DEFAULT)
+
+enum tva_type {
+	TVA_SMAPS,		/* Exposing "THPeligible:" in smaps. */
+	TVA_PAGEFAULT,		/* Serving a page fault. */
+	TVA_KHUGEPAGED,		/* Khugepaged collapse. */
+	TVA_FORCED_COLLAPSE,	/* Forced collapse (e.g. MADV_COLLAPSE). */
+};
+
+#define thp_vma_allowable_order(vma, vm_flags, type, order) \
+	(!!thp_vma_allowable_orders(vma, vm_flags, type, BIT(order)))
+
+#define split_folio(f) split_folio_to_list(f, NULL)
+
+#ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES
 #define HPAGE_PMD_SHIFT PMD_SHIFT
-#define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
+#define HPAGE_PUD_SHIFT PUD_SHIFT
+#else
+#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
+#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; })
+#endif
+
+#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
 #define HPAGE_PMD_MASK	(~(HPAGE_PMD_SIZE - 1))
+#define HPAGE_PMD_SIZE	((1UL) << HPAGE_PMD_SHIFT)
 
-#define HPAGE_PUD_SHIFT PUD_SHIFT
-#define HPAGE_PUD_SIZE	((1UL) << HPAGE_PUD_SHIFT)
+#define HPAGE_PUD_ORDER (HPAGE_PUD_SHIFT-PAGE_SHIFT)
+#define HPAGE_PUD_NR (1<<HPAGE_PUD_ORDER)
 #define HPAGE_PUD_MASK	(~(HPAGE_PUD_SIZE - 1))
+#define HPAGE_PUD_SIZE	((1UL) << HPAGE_PUD_SHIFT)
+
+enum mthp_stat_item {
+	MTHP_STAT_ANON_FAULT_ALLOC,
+	MTHP_STAT_ANON_FAULT_FALLBACK,
+	MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE,
+	MTHP_STAT_ZSWPOUT,
+	MTHP_STAT_SWPIN,
+	MTHP_STAT_SWPIN_FALLBACK,
+	MTHP_STAT_SWPIN_FALLBACK_CHARGE,
+	MTHP_STAT_SWPOUT,
+	MTHP_STAT_SWPOUT_FALLBACK,
+	MTHP_STAT_SHMEM_ALLOC,
+	MTHP_STAT_SHMEM_FALLBACK,
+	MTHP_STAT_SHMEM_FALLBACK_CHARGE,
+	MTHP_STAT_SPLIT,
+	MTHP_STAT_SPLIT_FAILED,
+	MTHP_STAT_SPLIT_DEFERRED,
+	MTHP_STAT_NR_ANON,
+	MTHP_STAT_NR_ANON_PARTIALLY_MAPPED,
+	__MTHP_STAT_COUNT
+};
+
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && defined(CONFIG_SYSFS)
+struct mthp_stat {
+	unsigned long stats[ilog2(MAX_PTRS_PER_PTE) + 1][__MTHP_STAT_COUNT];
+};
+
+DECLARE_PER_CPU(struct mthp_stat, mthp_stats);
+
+static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta)
+{
+	if (order <= 0 || order > PMD_ORDER)
+		return;
+
+	this_cpu_add(mthp_stats.stats[order][item], delta);
+}
+
+static inline void count_mthp_stat(int order, enum mthp_stat_item item)
+{
+	mod_mthp_stat(order, item, 1);
+}
+
+#else
+static inline void mod_mthp_stat(int order, enum mthp_stat_item item, int delta)
+{
+}
+
+static inline void count_mthp_stat(int order, enum mthp_stat_item item)
+{
+}
+#endif
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 
 extern unsigned long transparent_hugepage_flags;
+extern unsigned long huge_anon_orders_always;
+extern unsigned long huge_anon_orders_madvise;
+extern unsigned long huge_anon_orders_inherit;
+
+static inline bool hugepage_global_enabled(void)
+{
+	return transparent_hugepage_flags &
+			((1<<TRANSPARENT_HUGEPAGE_FLAG) |
+			(1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG));
+}
 
-#define hugepage_flags_enabled()					       \
-	(transparent_hugepage_flags &				       \
-	 ((1<<TRANSPARENT_HUGEPAGE_FLAG) |		       \
-	  (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)))
-#define hugepage_flags_always()				\
-	(transparent_hugepage_flags &			\
-	 (1<<TRANSPARENT_HUGEPAGE_FLAG))
+static inline bool hugepage_global_always(void)
+{
+	return transparent_hugepage_flags &
+			(1<<TRANSPARENT_HUGEPAGE_FLAG);
+}
+
+static inline int highest_order(unsigned long orders)
+{
+	return fls_long(orders) - 1;
+}
+
+static inline int next_order(unsigned long *orders, int prev)
+{
+	*orders &= ~BIT(prev);
+	return highest_order(*orders);
+}
 
 /*
  * Do the below checks:
  *   - For file vma, check if the linear page offset of vma is
- *     HPAGE_PMD_NR aligned within the file.  The hugepage is
- *     guaranteed to be hugepage-aligned within the file, but we must
- *     check that the PMD-aligned addresses in the VMA map to
- *     PMD-aligned offsets within the file, else the hugepage will
- *     not be PMD-mappable.
- *   - For all vmas, check if the haddr is in an aligned HPAGE_PMD_SIZE
+ *     order-aligned within the file.  The hugepage is
+ *     guaranteed to be order-aligned within the file, but we must
+ *     check that the order-aligned addresses in the VMA map to
+ *     order-aligned offsets within the file, else the hugepage will
+ *     not be mappable.
+ *   - For all vmas, check if the haddr is in an aligned hugepage
  *     area.
  */
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+		unsigned long addr, int order)
 {
+	unsigned long hpage_size = PAGE_SIZE << order;
 	unsigned long haddr;
 
 	/* Don't have to check pgoff for anonymous vma */
 	if (!vma_is_anonymous(vma)) {
 		if (!IS_ALIGNED((vma->vm_start >> PAGE_SHIFT) - vma->vm_pgoff,
-				HPAGE_PMD_NR))
+				hpage_size >> PAGE_SHIFT))
 			return false;
 	}
 
-	haddr = addr & HPAGE_PMD_MASK;
+	haddr = ALIGN_DOWN(addr, hpage_size);
 
-	if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end)
+	if (haddr < vma->vm_start || haddr + hpage_size > vma->vm_end)
 		return false;
 	return true;
 }
 
-static inline bool file_thp_enabled(struct vm_area_struct *vma)
+/*
+ * Filter the bitfield of input orders to the ones suitable for use in the vma.
+ * See thp_vma_suitable_order().
+ * All orders that pass the checks are returned as a bitfield.
+ */
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long orders)
 {
-	struct inode *inode;
+	int order;
 
-	if (!vma->vm_file)
-		return false;
+	/*
+	 * Iterate over orders, highest to lowest, removing orders that don't
+	 * meet alignment requirements from the set. Exit loop at first order
+	 * that meets requirements, since all lower orders must also meet
+	 * requirements.
+	 */
 
-	inode = vma->vm_file->f_inode;
+	order = highest_order(orders);
 
-	return (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS)) &&
-	       (vma->vm_flags & VM_EXEC) &&
-	       !inode_is_open_for_write(inode) && S_ISREG(inode->i_mode);
+	while (orders) {
+		if (thp_vma_suitable_order(vma, addr, order))
+			break;
+		order = next_order(&orders, order);
+	}
+
+	return orders;
+}
+
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+					 vm_flags_t vm_flags,
+					 enum tva_type type,
+					 unsigned long orders);
+
+/**
+ * thp_vma_allowable_orders - determine hugepage orders that are allowed for vma
+ * @vma:  the vm area to check
+ * @vm_flags: use these vm_flags instead of vma->vm_flags
+ * @type: TVA type
+ * @orders: bitfield of all orders to consider
+ *
+ * Calculates the intersection of the requested hugepage orders and the allowed
+ * hugepage orders for the provided vma. Permitted orders are encoded as a set
+ * bit at the corresponding bit position (bit-2 corresponds to order-2, bit-3
+ * corresponds to order-3, etc). Order-0 is never considered a hugepage order.
+ *
+ * Return: bitfield of orders allowed for hugepage in the vma. 0 if no hugepage
+ * orders are allowed.
+ */
+static inline
+unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+				       vm_flags_t vm_flags,
+				       enum tva_type type,
+				       unsigned long orders)
+{
+	/*
+	 * Optimization to check if required orders are enabled early. Only
+	 * forced collapse ignores sysfs configs.
+	 */
+	if (type != TVA_FORCED_COLLAPSE && vma_is_anonymous(vma)) {
+		unsigned long mask = READ_ONCE(huge_anon_orders_always);
+
+		if (vm_flags & VM_HUGEPAGE)
+			mask |= READ_ONCE(huge_anon_orders_madvise);
+		if (hugepage_global_always() ||
+		    ((vm_flags & VM_HUGEPAGE) && hugepage_global_enabled()))
+			mask |= READ_ONCE(huge_anon_orders_inherit);
+
+		orders &= mask;
+		if (!orders)
+			return 0;
+	}
+
+	return __thp_vma_allowable_orders(vma, vm_flags, type, orders);
 }
 
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
-			bool smaps, bool in_pf, bool enforce_sysfs);
+struct thpsize {
+	struct kobject kobj;
+	struct list_head node;
+	int order;
+};
+
+#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj)
 
 #define transparent_hugepage_use_zero_page()				\
 	(transparent_hugepage_flags &					\
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
 
+/*
+ * Check whether THPs are explicitly disabled for this VMA, for example,
+ * through madvise or prctl.
+ */
+static inline bool vma_thp_disabled(struct vm_area_struct *vma,
+		vm_flags_t vm_flags, bool forced_collapse)
+{
+	/* Are THPs disabled for this VMA? */
+	if (vm_flags & VM_NOHUGEPAGE)
+		return true;
+	/* Are THPs disabled for all VMAs in the whole process? */
+	if (mm_flags_test(MMF_DISABLE_THP_COMPLETELY, vma->vm_mm))
+		return true;
+	/*
+	 * Are THPs disabled only for VMAs where we didn't get an explicit
+	 * advise to use them?
+	 */
+	if (vm_flags & VM_HUGEPAGE)
+		return false;
+	/*
+	 * Forcing a collapse (e.g., madv_collapse), is a clear advice to
+	 * use THPs.
+	 */
+	if (forced_collapse)
+		return false;
+	return mm_flags_test(MMF_DISABLE_THP_EXCEPT_ADVISED, vma->vm_mm);
+}
+
+static inline bool thp_disabled_by_hw(void)
+{
+	/* If the hardware/firmware marked hugepage support disabled. */
+	return transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED);
+}
+
 unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr,
 		unsigned long len, unsigned long pgoff, unsigned long flags);
+unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
+		unsigned long len, unsigned long pgoff, unsigned long flags,
+		vm_flags_t vm_flags);
+
+enum split_type {
+	SPLIT_TYPE_UNIFORM,
+	SPLIT_TYPE_NON_UNIFORM,
+};
 
-void prep_transhuge_page(struct page *page);
-void free_transhuge_page(struct page *page);
+bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins);
+int __split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+		unsigned int new_order);
+int folio_split_unmapped(struct folio *folio, unsigned int new_order);
+int min_order_for_split(struct folio *folio);
+int split_folio_to_list(struct folio *folio, struct list_head *list);
+bool folio_split_supported(struct folio *folio, unsigned int new_order,
+		enum split_type split_type, bool warns);
+int folio_split(struct folio *folio, unsigned int new_order, struct page *page,
+		struct list_head *list);
 
-bool can_split_folio(struct folio *folio, int *pextra_pins);
-int split_huge_page_to_list(struct page *page, struct list_head *list);
+static inline int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+		unsigned int new_order)
+{
+	return __split_huge_page_to_list_to_order(page, list, new_order);
+}
+static inline int split_huge_page_to_order(struct page *page, unsigned int new_order)
+{
+	return split_huge_page_to_list_to_order(page, NULL, new_order);
+}
+
+/**
+ * try_folio_split_to_order() - try to split a @folio at @page to @new_order
+ * using non uniform split.
+ * @folio: folio to be split
+ * @page: split to @new_order at the given page
+ * @new_order: the target split order
+ *
+ * Try to split a @folio at @page using non uniform split to @new_order, if
+ * non uniform split is not supported, fall back to uniform split. After-split
+ * folios are put back to LRU list. Use min_order_for_split() to get the lower
+ * bound of @new_order.
+ *
+ * Return: 0 - split is successful, otherwise split failed.
+ */
+static inline int try_folio_split_to_order(struct folio *folio,
+		struct page *page, unsigned int new_order)
+{
+	if (!folio_split_supported(folio, new_order, SPLIT_TYPE_NON_UNIFORM, /* warns= */ false))
+		return split_huge_page_to_order(&folio->page, new_order);
+	return folio_split(folio, new_order, page, NULL);
+}
 static inline int split_huge_page(struct page *page)
 {
-	return split_huge_page_to_list(page, NULL);
+	return split_huge_page_to_list_to_order(page, NULL, 0);
 }
-void deferred_split_folio(struct folio *folio);
+void deferred_split_folio(struct folio *folio, bool partially_mapped);
+#ifdef CONFIG_MEMCG
+void reparent_deferred_split_queue(struct mem_cgroup *memcg);
+#endif
 
 void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long address, bool freeze, struct folio *folio);
+		unsigned long address, bool freeze);
+
+/**
+ * pmd_is_huge() - Is this PMD either a huge PMD entry or a software leaf entry?
+ * @pmd: The PMD to check.
+ *
+ * A huge PMD entry is a non-empty entry which is present and marked huge or a
+ * software leaf entry. This check be performed without the appropriate locks
+ * held, in which case the condition should be rechecked after they are
+ * acquired.
+ *
+ * Returns: true if this PMD is huge, false otherwise.
+ */
+static inline bool pmd_is_huge(pmd_t pmd)
+{
+	if (pmd_present(pmd)) {
+		return pmd_trans_huge(pmd);
+	} else if (!pmd_none(pmd)) {
+		/*
+		 * Non-present PMDs must be valid huge non-present entries. We
+		 * cannot assert that here due to header dependency issues.
+		 */
+		return true;
+	}
+
+	return false;
+}
 
 #define split_huge_pmd(__vma, __pmd, __address)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd)	\
-					|| pmd_devmap(*____pmd))	\
+		if (pmd_is_huge(*____pmd))				\
 			__split_huge_pmd(__vma, __pmd, __address,	\
-						false, NULL);		\
+					 false);			\
 	}  while (0)
 
-
 void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address,
-		bool freeze, struct folio *folio);
+		bool freeze);
 
 void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
 		unsigned long address);
 
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		    pud_t *pudp, unsigned long addr, pgprot_t newprot,
+		    unsigned long cp_flags);
+#else
+static inline int
+change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+		pud_t *pudp, unsigned long addr, pgprot_t newprot,
+		unsigned long cp_flags) { return 0; }
+#endif
+
 #define split_huge_pud(__vma, __pud, __address)				\
 	do {								\
 		pud_t *____pud = (__pud);				\
-		if (pud_trans_huge(*____pud)				\
-					|| pud_devmap(*____pud))	\
+		if (pud_trans_huge(*____pud))				\
 			__split_huge_pud(__vma, __pud, __address);	\
 	}  while (0)
 
-int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags,
+int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags,
 		     int advice);
-int madvise_collapse(struct vm_area_struct *vma,
-		     struct vm_area_struct **prev,
-		     unsigned long start, unsigned long end);
+int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end, bool *lock_dropped);
 void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start,
-			   unsigned long end, long adjust_next);
+			   unsigned long end, struct vm_area_struct *next);
 spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma);
 spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma);
 
-static inline int is_swap_pmd(pmd_t pmd)
-{
-	return !pmd_none(pmd) && !pmd_present(pmd);
-}
-
 /* mmap_lock must be held on entry */
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
 {
-	if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
+	if (pmd_is_huge(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma);
-	else
-		return NULL;
+
+	return NULL;
 }
 static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 		struct vm_area_struct *vma)
 {
-	if (pud_trans_huge(*pud) || pud_devmap(*pud))
+	if (pud_trans_huge(*pud))
 		return __pud_trans_huge_lock(pud, vma);
 	else
 		return NULL;
@@ -217,115 +511,177 @@ static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 /**
  * folio_test_pmd_mappable - Can we map this folio with a PMD?
  * @folio: The folio to test
+ *
+ * Return: true - @folio can be mapped, false - @folio cannot be mapped.
  */
 static inline bool folio_test_pmd_mappable(struct folio *folio)
 {
 	return folio_order(folio) >= HPAGE_PMD_ORDER;
 }
 
-struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
-struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
-		pud_t *pud, int flags, struct dev_pagemap **pgmap);
-
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf);
 
-extern struct page *huge_zero_page;
+vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf);
+
+extern struct folio *huge_zero_folio;
 extern unsigned long huge_zero_pfn;
 
-static inline bool is_huge_zero_page(struct page *page)
+static inline bool is_huge_zero_folio(const struct folio *folio)
+{
+	VM_WARN_ON_ONCE(!folio);
+
+	return READ_ONCE(huge_zero_folio) == folio;
+}
+
+static inline bool is_huge_zero_pfn(unsigned long pfn)
 {
-	return READ_ONCE(huge_zero_page) == page;
+	return READ_ONCE(huge_zero_pfn) == (pfn & ~(HPAGE_PMD_NR - 1));
 }
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-	return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
+	return pmd_present(pmd) && is_huge_zero_pfn(pmd_pfn(pmd));
 }
 
-static inline bool is_huge_zero_pud(pud_t pud)
+struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
+void mm_put_huge_zero_folio(struct mm_struct *mm);
+
+static inline struct folio *get_persistent_huge_zero_folio(void)
 {
-	return false;
-}
+	if (!IS_ENABLED(CONFIG_PERSISTENT_HUGE_ZERO_FOLIO))
+		return NULL;
 
-struct page *mm_get_huge_zero_page(struct mm_struct *mm);
-void mm_put_huge_zero_page(struct mm_struct *mm);
+	if (unlikely(!huge_zero_folio))
+		return NULL;
 
-#define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot))
+	return huge_zero_folio;
+}
 
 static inline bool thp_migration_supported(void)
 {
 	return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION);
 }
 
-#else /* CONFIG_TRANSPARENT_HUGEPAGE */
-#define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; })
-#define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; })
-#define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; })
+void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
+			   pmd_t *pmd, bool freeze);
+bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
+			   pmd_t *pmdp, struct folio *folio);
+void map_anon_folio_pmd_nopf(struct folio *folio, pmd_t *pmd,
+		struct vm_area_struct *vma, unsigned long haddr);
 
-#define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; })
-#define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; })
-#define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; })
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 static inline bool folio_test_pmd_mappable(struct folio *folio)
 {
 	return false;
 }
 
-static inline bool transhuge_vma_suitable(struct vm_area_struct *vma,
-		unsigned long addr)
+static inline bool thp_vma_suitable_order(struct vm_area_struct *vma,
+		unsigned long addr, int order)
 {
 	return false;
 }
 
-static inline bool hugepage_vma_check(struct vm_area_struct *vma,
-				      unsigned long vm_flags, bool smaps,
-				      bool in_pf, bool enforce_sysfs)
+static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
+		unsigned long addr, unsigned long orders)
 {
-	return false;
+	return 0;
 }
 
-static inline void prep_transhuge_page(struct page *page) {}
+static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
+					vm_flags_t vm_flags,
+					enum tva_type type,
+					unsigned long orders)
+{
+	return 0;
+}
 
 #define transparent_hugepage_flags 0UL
 
 #define thp_get_unmapped_area	NULL
 
+static inline unsigned long
+thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr,
+			      unsigned long len, unsigned long pgoff,
+			      unsigned long flags, vm_flags_t vm_flags)
+{
+	return 0;
+}
+
 static inline bool
-can_split_folio(struct folio *folio, int *pextra_pins)
+can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
 {
 	return false;
 }
 static inline int
-split_huge_page_to_list(struct page *page, struct list_head *list)
+split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
+		unsigned int new_order)
 {
-	return 0;
+	VM_WARN_ON_ONCE_PAGE(1, page);
+	return -EINVAL;
+}
+static inline int split_huge_page_to_order(struct page *page, unsigned int new_order)
+{
+	VM_WARN_ON_ONCE_PAGE(1, page);
+	return -EINVAL;
 }
 static inline int split_huge_page(struct page *page)
 {
-	return 0;
+	VM_WARN_ON_ONCE_PAGE(1, page);
+	return -EINVAL;
+}
+
+static inline int min_order_for_split(struct folio *folio)
+{
+	VM_WARN_ON_ONCE_FOLIO(1, folio);
+	return -EINVAL;
 }
-static inline void deferred_split_folio(struct folio *folio) {}
+
+static inline int split_folio_to_list(struct folio *folio, struct list_head *list)
+{
+	VM_WARN_ON_ONCE_FOLIO(1, folio);
+	return -EINVAL;
+}
+
+static inline int try_folio_split_to_order(struct folio *folio,
+		struct page *page, unsigned int new_order)
+{
+	VM_WARN_ON_ONCE_FOLIO(1, folio);
+	return -EINVAL;
+}
+
+static inline void deferred_split_folio(struct folio *folio, bool partially_mapped) {}
+static inline void reparent_deferred_split_queue(struct mem_cgroup *memcg) {}
 #define split_huge_pmd(__vma, __pmd, __address)	\
 	do { } while (0)
 
 static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
-		unsigned long address, bool freeze, struct folio *folio) {}
+		unsigned long address, bool freeze) {}
 static inline void split_huge_pmd_address(struct vm_area_struct *vma,
-		unsigned long address, bool freeze, struct folio *folio) {}
+		unsigned long address, bool freeze) {}
+static inline void split_huge_pmd_locked(struct vm_area_struct *vma,
+					 unsigned long address, pmd_t *pmd,
+					 bool freeze) {}
+
+static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma,
+					 unsigned long addr, pmd_t *pmdp,
+					 struct folio *folio)
+{
+	return false;
+}
 
 #define split_huge_pud(__vma, __pmd, __address)	\
 	do { } while (0)
 
 static inline int hugepage_madvise(struct vm_area_struct *vma,
-				   unsigned long *vm_flags, int advice)
+				   vm_flags_t *vm_flags, int advice)
 {
 	return -EINVAL;
 }
 
 static inline int madvise_collapse(struct vm_area_struct *vma,
-				   struct vm_area_struct **prev,
-				   unsigned long start, unsigned long end)
+				   unsigned long start,
+				   unsigned long end, bool *lock_dropped)
 {
 	return -EINVAL;
 }
@@ -333,12 +689,8 @@ static inline int madvise_collapse(struct vm_area_struct *vma,
 static inline void vma_adjust_trans_huge(struct vm_area_struct *vma,
 					 unsigned long start,
 					 unsigned long end,
-					 long adjust_next)
-{
-}
-static inline int is_swap_pmd(pmd_t pmd)
+					 struct vm_area_struct *next)
 {
-	return 0;
 }
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
@@ -356,65 +708,101 @@ static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
 	return 0;
 }
 
-static inline bool is_huge_zero_page(struct page *page)
+static inline vm_fault_t do_huge_pmd_device_private(struct vm_fault *vmf)
+{
+	return 0;
+}
+
+static inline bool is_huge_zero_folio(const struct folio *folio)
 {
 	return false;
 }
 
-static inline bool is_huge_zero_pmd(pmd_t pmd)
+static inline bool is_huge_zero_pfn(unsigned long pfn)
 {
 	return false;
 }
 
-static inline bool is_huge_zero_pud(pud_t pud)
+static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
 	return false;
 }
 
-static inline void mm_put_huge_zero_page(struct mm_struct *mm)
+static inline void mm_put_huge_zero_folio(struct mm_struct *mm)
 {
 	return;
 }
 
-static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
-	unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
+static inline bool thp_migration_supported(void)
+{
+	return false;
+}
+
+static inline int highest_order(unsigned long orders)
+{
+	return 0;
+}
+
+static inline int next_order(unsigned long *orders, int prev)
+{
+	return 0;
+}
+
+static inline void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+				    unsigned long address)
 {
-	return NULL;
 }
 
-static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
-	unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap)
+static inline int change_huge_pud(struct mmu_gather *tlb,
+				  struct vm_area_struct *vma, pud_t *pudp,
+				  unsigned long addr, pgprot_t newprot,
+				  unsigned long cp_flags)
+{
+	return 0;
+}
+
+static inline struct folio *get_persistent_huge_zero_folio(void)
 {
 	return NULL;
 }
 
-static inline bool thp_migration_supported(void)
+static inline bool pmd_is_huge(pmd_t pmd)
 {
 	return false;
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline int split_folio_to_list(struct folio *folio,
-		struct list_head *list)
+static inline int split_folio_to_list_to_order(struct folio *folio,
+		struct list_head *list, int new_order)
 {
-	return split_huge_page_to_list(&folio->page, list);
+	return split_huge_page_to_list_to_order(&folio->page, list, new_order);
 }
 
-static inline int split_folio(struct folio *folio)
+static inline int split_folio_to_order(struct folio *folio, int new_order)
 {
-	return split_folio_to_list(folio, NULL);
+	return split_folio_to_list_to_order(folio, NULL, new_order);
 }
 
-/*
- * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to
- * limitations in the implementation like arm64 MTE can override this to
- * false
+/**
+ * largest_zero_folio - Get the largest zero size folio available
+ *
+ * This function shall be used when mm_get_huge_zero_folio() cannot be
+ * used as there is no appropriate mm lifetime to tie the huge zero folio
+ * from the caller.
+ *
+ * Deduce the size of the folio with folio_size instead of assuming the
+ * folio size.
+ *
+ * Return: pointer to PMD sized zero folio if CONFIG_PERSISTENT_HUGE_ZERO_FOLIO
+ * is enabled or a single page sized zero folio
  */
-#ifndef arch_thp_swp_supported
-static inline bool arch_thp_swp_supported(void)
+static inline struct folio *largest_zero_folio(void)
 {
-	return true;
-}
-#endif
+	struct folio *folio = get_persistent_huge_zero_folio();
+
+	if (folio)
+		return folio;
 
+	return page_folio(ZERO_PAGE(0));
+}
 #endif /* _LINUX_HUGE_MM_H */
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 21f942025fec..019a1c5281e4 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -14,21 +14,18 @@
 #include <linux/pgtable.h>
 #include <linux/gfp.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/nodemask.h>
 
 struct ctl_table;
 struct user_struct;
 struct mmu_gather;
 struct node;
 
-#ifndef CONFIG_ARCH_HAS_HUGEPD
-typedef struct { unsigned long pd; } hugepd_t;
-#define is_hugepd(hugepd) (0)
-#define __hugepd(x) ((hugepd_t) { (x) })
-#endif
+void free_huge_folio(struct folio *folio);
 
 #ifdef CONFIG_HUGETLB_PAGE
 
-#include <linux/mempolicy.h>
+#include <linux/pagemap.h>
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
@@ -58,6 +55,7 @@ struct resv_map {
 	long adds_in_progress;
 	struct list_head region_cache;
 	long region_cache_count;
+	struct rw_semaphore rw_sema;
 #ifdef CONFIG_CGROUP_HUGETLB
 	/*
 	 * On private mappings, the counter to uncharge reservations is stored
@@ -130,18 +128,13 @@ int move_hugetlb_page_tables(struct vm_area_struct *vma,
 			     unsigned long len);
 int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *,
 			    struct vm_area_struct *, struct vm_area_struct *);
-struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
-				unsigned long address, unsigned int flags);
-long follow_hugetlb_page(struct mm_struct *, struct vm_area_struct *,
-			 struct page **, unsigned long *, unsigned long *,
-			 long, unsigned int, int *);
 void unmap_hugepage_range(struct vm_area_struct *,
-			  unsigned long, unsigned long, struct page *,
-			  zap_flags_t);
-void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+			  unsigned long start, unsigned long end,
+			  struct folio *, zap_flags_t);
+void __unmap_hugepage_range(struct mmu_gather *tlb,
 			  struct vm_area_struct *vma,
 			  unsigned long start, unsigned long end,
-			  struct page *ref_page, zap_flags_t zap_flags);
+			  struct folio *, zap_flags_t zap_flags);
 void hugetlb_report_meminfo(struct seq_file *);
 int hugetlb_report_node_meminfo(char *buf, int len, int nid);
 void hugetlb_show_meminfo_node(int nid);
@@ -156,29 +149,35 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 			     uffd_flags_t flags,
 			     struct folio **foliop);
 #endif /* CONFIG_USERFAULTFD */
-bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
-						struct vm_area_struct *vma,
-						vm_flags_t vm_flags);
+long hugetlb_reserve_pages(struct inode *inode, long from, long to,
+			   struct vm_area_desc *desc, vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
-bool isolate_hugetlb(struct folio *folio, struct list_head *list);
+bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list);
 int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison);
 int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 				bool *migratable_cleared);
-void folio_putback_active_hugetlb(struct folio *folio);
+void folio_putback_hugetlb(struct folio *folio);
 void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason);
-void free_huge_page(struct page *page);
 void hugetlb_fix_reserve_counts(struct inode *inode);
 extern struct mutex *hugetlb_fault_mutex_table;
 u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx);
 
 pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma,
 		      unsigned long addr, pud_t *pud);
+bool hugetlbfs_pagecache_present(struct hstate *h,
+				 struct vm_area_struct *vma,
+				 unsigned long address);
 
-struct address_space *hugetlb_page_mapping_lock_write(struct page *hpage);
+struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio);
 
-extern int sysctl_hugetlb_shm_group;
-extern struct list_head huge_boot_pages;
+extern int sysctl_hugetlb_shm_group __read_mostly;
+extern struct list_head huge_boot_pages[MAX_NUMNODES];
+
+void hugetlb_bootmem_alloc(void);
+bool hugetlb_bootmem_allocated(void);
+extern nodemask_t hugetlb_bootmem_nodes;
+void hugetlb_bootmem_set_nodes(void);
 
 /* arch callbacks */
 
@@ -246,6 +245,25 @@ int huge_pmd_unshare(struct mm_struct *mm, struct vm_area_struct *vma,
 void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma,
 				unsigned long *start, unsigned long *end);
 
+extern void __hugetlb_zap_begin(struct vm_area_struct *vma,
+				unsigned long *begin, unsigned long *end);
+extern void __hugetlb_zap_end(struct vm_area_struct *vma,
+			      struct zap_details *details);
+
+static inline void hugetlb_zap_begin(struct vm_area_struct *vma,
+				     unsigned long *start, unsigned long *end)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_begin(vma, start, end);
+}
+
+static inline void hugetlb_zap_end(struct vm_area_struct *vma,
+				   struct zap_details *details)
+{
+	if (is_vm_hugetlb_page(vma))
+		__hugetlb_zap_end(vma, details);
+}
+
 void hugetlb_vma_lock_read(struct vm_area_struct *vma);
 void hugetlb_vma_unlock_read(struct vm_area_struct *vma);
 void hugetlb_vma_lock_write(struct vm_area_struct *vma);
@@ -253,15 +271,13 @@ void hugetlb_vma_unlock_write(struct vm_area_struct *vma);
 int hugetlb_vma_trylock_write(struct vm_area_struct *vma);
 void hugetlb_vma_assert_locked(struct vm_area_struct *vma);
 void hugetlb_vma_lock_release(struct kref *kref);
-
-int pmd_huge(pmd_t pmd);
-int pud_huge(pud_t pud);
 long hugetlb_change_protection(struct vm_area_struct *vma,
 		unsigned long address, unsigned long end, pgprot_t newprot,
 		unsigned long cp_flags);
-
-bool is_hugetlb_entry_migration(pte_t pte);
 void hugetlb_unshare_all_pmds(struct vm_area_struct *vma);
+void fixup_hugetlb_reservations(struct vm_area_struct *vma);
+void hugetlb_split(struct vm_area_struct *vma, unsigned long addr);
+int hugetlb_vma_lock_alloc(struct vm_area_struct *vma);
 
 #else /* !CONFIG_HUGETLB_PAGE */
 
@@ -278,8 +294,8 @@ static inline unsigned long hugetlb_total_pages(void)
 	return 0;
 }
 
-static inline struct address_space *hugetlb_page_mapping_lock_write(
-							struct page *hpage)
+static inline struct address_space *hugetlb_folio_mapping_lock_write(
+							struct folio *folio)
 {
 	return NULL;
 }
@@ -297,19 +313,16 @@ static inline void adjust_range_if_pmd_sharing_possible(
 {
 }
 
-static inline struct page *hugetlb_follow_page_mask(struct vm_area_struct *vma,
-				unsigned long address, unsigned int flags)
+static inline void hugetlb_zap_begin(
+				struct vm_area_struct *vma,
+				unsigned long *start, unsigned long *end)
 {
-	BUILD_BUG(); /* should never be compiled in if !CONFIG_HUGETLB_PAGE*/
 }
 
-static inline long follow_hugetlb_page(struct mm_struct *mm,
-			struct vm_area_struct *vma, struct page **pages,
-			unsigned long *position, unsigned long *nr_pages,
-			long i, unsigned int flags, int *nonblocking)
+static inline void hugetlb_zap_end(
+				struct vm_area_struct *vma,
+				struct zap_details *details)
 {
-	BUG();
-	return 0;
 }
 
 static inline int copy_hugetlb_page_range(struct mm_struct *dst,
@@ -344,12 +357,6 @@ static inline void hugetlb_show_meminfo_node(int nid)
 {
 }
 
-static inline int prepare_hugepage_range(struct file *file,
-				unsigned long addr, unsigned long len)
-{
-	return -EINVAL;
-}
-
 static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 {
 }
@@ -375,29 +382,12 @@ static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma)
 {
 }
 
-static inline int pmd_huge(pmd_t pmd)
-{
-	return 0;
-}
-
-static inline int pud_huge(pud_t pud)
-{
-	return 0;
-}
-
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					unsigned long addr, unsigned long len)
 {
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-				unsigned long addr, unsigned long end,
-				unsigned long floor, unsigned long ceiling)
-{
-	BUG();
-}
-
 #ifdef CONFIG_USERFAULTFD
 static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 					   struct vm_area_struct *dst_vma,
@@ -417,7 +407,7 @@ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
 	return NULL;
 }
 
-static inline bool isolate_hugetlb(struct folio *folio, struct list_head *list)
+static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list)
 {
 	return false;
 }
@@ -433,7 +423,7 @@ static inline int get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 	return 0;
 }
 
-static inline void folio_putback_active_hugetlb(struct folio *folio)
+static inline void folio_putback_hugetlb(struct folio *folio)
 {
 }
 
@@ -450,9 +440,9 @@ static inline long hugetlb_change_protection(
 	return 0;
 }
 
-static inline void __unmap_hugepage_range_final(struct mmu_gather *tlb,
+static inline void __unmap_hugepage_range(struct mmu_gather *tlb,
 			struct vm_area_struct *vma, unsigned long start,
-			unsigned long end, struct page *ref_page,
+			unsigned long end, struct folio *folio,
 			zap_flags_t zap_flags)
 {
 	BUG();
@@ -468,17 +458,18 @@ static inline vm_fault_t hugetlb_fault(struct mm_struct *mm,
 
 static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { }
 
+static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma)
+{
+}
+
+static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {}
+
+static inline int hugetlb_vma_lock_alloc(struct vm_area_struct *vma)
+{
+	return 0;
+}
+
 #endif /* !CONFIG_HUGETLB_PAGE */
-/*
- * hugepages at page global directory. If arch support
- * hugepages at pgd level, they need to define this.
- */
-#ifndef pgd_huge
-#define pgd_huge(x)	0
-#endif
-#ifndef p4d_huge
-#define p4d_huge(x)	0
-#endif
 
 #ifndef pgd_write
 static inline int pgd_write(pgd_t pgd)
@@ -521,7 +512,6 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 }
 
 struct hugetlbfs_inode_info {
-	struct shared_policy policy;
 	struct inode vfs_inode;
 	unsigned int seals;
 };
@@ -531,17 +521,13 @@ static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode)
 	return container_of(inode, struct hugetlbfs_inode_info, vfs_inode);
 }
 
-extern const struct file_operations hugetlbfs_file_operations;
 extern const struct vm_operations_struct hugetlb_vm_ops;
 struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acct,
 				int creat_flags, int page_size_log);
 
-static inline bool is_file_hugepages(struct file *file)
+static inline bool is_file_hugepages(const struct file *file)
 {
-	if (file->f_op == &hugetlbfs_file_operations)
-		return true;
-
-	return is_file_shm_hugepages(file);
+	return file->f_op->fop_flags & FOP_HUGE_PAGES;
 }
 
 static inline struct hstate *hstate_inode(struct inode *i)
@@ -564,16 +550,10 @@ static inline struct hstate *hstate_inode(struct inode *i)
 }
 #endif /* !CONFIG_HUGETLBFS */
 
-#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
-unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-					unsigned long len, unsigned long pgoff,
-					unsigned long flags);
-#endif /* HAVE_ARCH_HUGETLB_UNMAPPED_AREA */
-
 unsigned long
-generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
-				  unsigned long len, unsigned long pgoff,
-				  unsigned long flags);
+hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
+				    unsigned long len, unsigned long pgoff,
+				    unsigned long flags);
 
 /*
  * huegtlb page specific state flags.  These flags are located in page.private
@@ -612,6 +592,7 @@ enum hugetlb_page_flags {
 	HPG_freed,
 	HPG_vmemmap_optimized,
 	HPG_raw_hwp_unreliable,
+	HPG_cma,
 	__NR_HPAGEFLAGS,
 };
 
@@ -625,47 +606,35 @@ static __always_inline						\
 bool folio_test_hugetlb_##flname(struct folio *folio)		\
 	{	void *private = &folio->private;		\
 		return test_bit(HPG_##flname, private);		\
-	}							\
-static inline int HPage##uname(struct page *page)		\
-	{ return test_bit(HPG_##flname, &(page->private)); }
+	}
 
 #define SETHPAGEFLAG(uname, flname)				\
 static __always_inline						\
 void folio_set_hugetlb_##flname(struct folio *folio)		\
 	{	void *private = &folio->private;		\
 		set_bit(HPG_##flname, private);			\
-	}							\
-static inline void SetHPage##uname(struct page *page)		\
-	{ set_bit(HPG_##flname, &(page->private)); }
+	}
 
 #define CLEARHPAGEFLAG(uname, flname)				\
 static __always_inline						\
 void folio_clear_hugetlb_##flname(struct folio *folio)		\
 	{	void *private = &folio->private;		\
 		clear_bit(HPG_##flname, private);		\
-	}							\
-static inline void ClearHPage##uname(struct page *page)		\
-	{ clear_bit(HPG_##flname, &(page->private)); }
+	}
 #else
 #define TESTHPAGEFLAG(uname, flname)				\
 static inline bool						\
 folio_test_hugetlb_##flname(struct folio *folio)		\
-	{ return 0; }						\
-static inline int HPage##uname(struct page *page)		\
 	{ return 0; }
 
 #define SETHPAGEFLAG(uname, flname)				\
 static inline void						\
 folio_set_hugetlb_##flname(struct folio *folio) 		\
-	{ }							\
-static inline void SetHPage##uname(struct page *page)		\
 	{ }
 
 #define CLEARHPAGEFLAG(uname, flname)				\
 static inline void						\
 folio_clear_hugetlb_##flname(struct folio *folio)		\
-	{ }							\
-static inline void ClearHPage##uname(struct page *page)		\
 	{ }
 #endif
 
@@ -683,6 +652,7 @@ HPAGEFLAG(Temporary, temporary)
 HPAGEFLAG(Freed, freed)
 HPAGEFLAG(VmemmapOptimized, vmemmap_optimized)
 HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable)
+HPAGEFLAG(Cma, cma)
 
 #ifdef CONFIG_HUGETLB_PAGE
 
@@ -690,6 +660,7 @@ HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable)
 /* Defines one hugetlb page size */
 struct hstate {
 	struct mutex resize_lock;
+	struct lock_class_key resize_key;
 	int next_nid_to_alloc;
 	int next_nid_to_free;
 	unsigned int order;
@@ -707,26 +678,35 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
-#ifdef CONFIG_CGROUP_HUGETLB
-	/* cgroup control files */
-	struct cftype cgroup_files_dfl[8];
-	struct cftype cgroup_files_legacy[10];
-#endif
 	char name[HSTATE_NAME_LEN];
 };
 
+struct cma;
+
 struct huge_bootmem_page {
 	struct list_head list;
 	struct hstate *hstate;
+	unsigned long flags;
+	struct cma *cma;
 };
 
-int isolate_or_dissolve_huge_page(struct page *page, struct list_head *list);
+#define HUGE_BOOTMEM_HVO		0x0001
+#define HUGE_BOOTMEM_ZONES_VALID	0x0002
+#define HUGE_BOOTMEM_CMA		0x0004
+
+bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m);
+
+int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list);
+int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn);
+void wait_for_freed_hugetlb_folios(void);
 struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
-				unsigned long addr, int avoid_reserve);
+				unsigned long addr, bool cow_from_owner);
 struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
-				nodemask_t *nmask, gfp_t gfp_mask);
-struct folio *alloc_hugetlb_folio_vma(struct hstate *h, struct vm_area_struct *vma,
-				unsigned long address);
+				nodemask_t *nmask, gfp_t gfp_mask,
+				bool allow_alloc_fallback);
+struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+					  nodemask_t *nmask, gfp_t gfp_mask);
+
 int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping,
 			pgoff_t idx);
 void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
@@ -750,6 +730,11 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
+static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
+{
+	return HUGETLBFS_SB(inode->i_sb)->spool;
+}
+
 static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
 {
 	return folio->_hugetlb_subpool;
@@ -761,12 +746,6 @@ static inline void hugetlb_set_folio_subpool(struct folio *folio,
 	folio->_hugetlb_subpool = subpool;
 }
 
-static inline void hugetlb_set_page_subpool(struct page *hpage,
-					struct hugepage_subpool *subpool)
-{
-	hugetlb_set_folio_subpool(page_folio(hpage), subpool);
-}
-
 static inline struct hstate *hstate_file(struct file *f)
 {
 	return hstate_inode(file_inode(f));
@@ -812,9 +791,14 @@ static inline unsigned huge_page_shift(struct hstate *h)
 	return h->order + PAGE_SHIFT;
 }
 
+static inline bool order_is_gigantic(unsigned int order)
+{
+	return order > MAX_PAGE_ORDER;
+}
+
 static inline bool hstate_is_gigantic(struct hstate *h)
 {
-	return huge_page_order(h) > MAX_ORDER;
+	return order_is_gigantic(huge_page_order(h));
 }
 
 static inline unsigned int pages_per_huge_page(const struct hstate *h)
@@ -827,6 +811,12 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h)
 	return huge_page_size(h) / 512;
 }
 
+static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h,
+				struct address_space *mapping, pgoff_t idx)
+{
+	return filemap_lock_folio(mapping, idx << huge_page_order(h));
+}
+
 #include <asm/hugetlb.h>
 
 #ifndef is_hugepage_only_range
@@ -838,9 +828,9 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 #define is_hugepage_only_range is_hugepage_only_range
 #endif
 
-#ifndef arch_clear_hugepage_flags
-static inline void arch_clear_hugepage_flags(struct page *page) { }
-#define arch_clear_hugepage_flags arch_clear_hugepage_flags
+#ifndef arch_clear_hugetlb_flags
+static inline void arch_clear_hugetlb_flags(struct folio *folio) { }
+#define arch_clear_hugetlb_flags arch_clear_hugetlb_flags
 #endif
 
 #ifndef arch_make_huge_pte
@@ -851,15 +841,21 @@ static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift,
 }
 #endif
 
-static inline struct hstate *folio_hstate(struct folio *folio)
+#ifndef arch_has_huge_bootmem_alloc
+/*
+ * Some architectures do their own bootmem allocation, so they can't use
+ * early CMA allocation.
+ */
+static inline bool arch_has_huge_bootmem_alloc(void)
 {
-	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
-	return size_to_hstate(folio_size(folio));
+	return false;
 }
+#endif
 
-static inline struct hstate *page_hstate(struct page *page)
+static inline struct hstate *folio_hstate(struct folio *folio)
 {
-	return folio_hstate(page_folio(page));
+	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
+	return size_to_hstate(folio_size(folio));
 }
 
 static inline unsigned hstate_index_to_shift(unsigned index)
@@ -872,8 +868,8 @@ static inline int hstate_index(struct hstate *h)
 	return h - hstates;
 }
 
-extern int dissolve_free_huge_page(struct page *page);
-extern int dissolve_free_huge_pages(unsigned long start_pfn,
+int dissolve_free_hugetlb_folio(struct folio *folio);
+int dissolve_free_hugetlb_folios(unsigned long start_pfn,
 				    unsigned long end_pfn);
 
 #ifdef CONFIG_MEMORY_FAILURE
@@ -936,10 +932,11 @@ static inline bool hugepage_movable_supported(struct hstate *h)
 /* Movability of hugepages depends on migration support. */
 static inline gfp_t htlb_alloc_mask(struct hstate *h)
 {
-	if (hugepage_movable_supported(h))
-		return GFP_HIGHUSER_MOVABLE;
-	else
-		return GFP_HIGHUSER;
+	gfp_t gfp = __GFP_COMP | __GFP_NOWARN;
+
+	gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER;
+
+	return gfp;
 }
 
 static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
@@ -954,13 +951,64 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
 	return modified_mask;
 }
 
+static inline bool htlb_allow_alloc_fallback(int reason)
+{
+	bool allowed_fallback = false;
+
+	/*
+	 * Note: the memory offline, memory failure and migration syscalls will
+	 * be allowed to fallback to other nodes due to lack of a better chioce,
+	 * that might break the per-node hugetlb pool. While other cases will
+	 * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool.
+	 */
+	switch (reason) {
+	case MR_MEMORY_HOTPLUG:
+	case MR_MEMORY_FAILURE:
+	case MR_SYSCALL:
+	case MR_MEMPOLICY_MBIND:
+		allowed_fallback = true;
+		break;
+	default:
+		break;
+	}
+
+	return allowed_fallback;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
-	if (huge_page_size(h) == PMD_SIZE)
+	const unsigned long size = huge_page_size(h);
+
+	VM_WARN_ON(size == PAGE_SIZE);
+
+	/*
+	 * hugetlb must use the exact same PT locks as core-mm page table
+	 * walkers would. When modifying a PTE table, hugetlb must take the
+	 * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD
+	 * PT lock etc.
+	 *
+	 * The expectation is that any hugetlb folio smaller than a PMD is
+	 * always mapped into a single PTE table and that any hugetlb folio
+	 * smaller than a PUD (but at least as big as a PMD) is always mapped
+	 * into a single PMD table.
+	 *
+	 * If that does not hold for an architecture, then that architecture
+	 * must disable split PT locks such that all *_lockptr() functions
+	 * will give us the same result: the per-MM PT lock.
+	 *
+	 * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where
+	 * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr()
+	 * and core-mm would use pmd_lockptr(). However, in such configurations
+	 * split PMD locks are disabled -- they don't make sense on a single
+	 * PGDIR page table -- and the end result is the same.
+	 */
+	if (size >= PUD_SIZE)
+		return pud_lockptr(mm, (pud_t *) pte);
+	else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE))
 		return pmd_lockptr(mm, (pmd_t *) pte);
-	VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
-	return &mm->page_table_lock;
+	/* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */
+	return ptep_lockptr(mm, pte);
 }
 
 #ifndef hugepages_supported
@@ -994,7 +1042,9 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep)
 {
-	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize);
 }
 #endif
 
@@ -1004,7 +1054,9 @@ static inline void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
 						unsigned long addr, pte_t *ptep,
 						pte_t old_pte, pte_t pte)
 {
-	set_huge_pte_at(vma->vm_mm, addr, ptep, pte);
+	unsigned long psize = huge_page_size(hstate_vma(vma));
+
+	set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize);
 }
 #endif
 
@@ -1013,37 +1065,69 @@ void hugetlb_register_node(struct node *node);
 void hugetlb_unregister_node(struct node *node);
 #endif
 
+/*
+ * Check if a given raw @page in a hugepage is HWPOISON.
+ */
+bool is_raw_hwpoison_page_in_hugepage(struct page *page);
+
+static inline unsigned long huge_page_mask_align(struct file *file)
+{
+	return PAGE_MASK & ~huge_page_mask(hstate_file(file));
+}
+
 #else	/* CONFIG_HUGETLB_PAGE */
 struct hstate {};
 
+static inline unsigned long huge_page_mask_align(struct file *file)
+{
+	return 0;
+}
+
 static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
 {
 	return NULL;
 }
 
-static inline int isolate_or_dissolve_huge_page(struct page *page,
+static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h,
+				struct address_space *mapping, pgoff_t idx)
+{
+	return NULL;
+}
+
+static inline int isolate_or_dissolve_huge_folio(struct folio *folio,
 						struct list_head *list)
 {
 	return -ENOMEM;
 }
 
+static inline int replace_free_hugepage_folios(unsigned long start_pfn,
+		unsigned long end_pfn)
+{
+	return 0;
+}
+
+static inline void wait_for_freed_hugetlb_folios(void)
+{
+}
+
 static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma,
 					   unsigned long addr,
-					   int avoid_reserve)
+					   bool cow_from_owner)
 {
 	return NULL;
 }
 
 static inline struct folio *
-alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
-			nodemask_t *nmask, gfp_t gfp_mask)
+alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid,
+			    nodemask_t *nmask, gfp_t gfp_mask)
 {
 	return NULL;
 }
 
-static inline struct folio *alloc_hugetlb_folio_vma(struct hstate *h,
-					       struct vm_area_struct *vma,
-					       unsigned long address)
+static inline struct folio *
+alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
+			nodemask_t *nmask, gfp_t gfp_mask,
+			bool allow_alloc_fallback)
 {
 	return NULL;
 }
@@ -1073,11 +1157,6 @@ static inline struct hstate *folio_hstate(struct folio *folio)
 	return NULL;
 }
 
-static inline struct hstate *page_hstate(struct page *page)
-{
-	return NULL;
-}
-
 static inline struct hstate *size_to_hstate(unsigned long size)
 {
 	return NULL;
@@ -1133,12 +1212,12 @@ static inline int hstate_index(struct hstate *h)
 	return 0;
 }
 
-static inline int dissolve_free_huge_page(struct page *page)
+static inline int dissolve_free_hugetlb_folio(struct folio *folio)
 {
 	return 0;
 }
 
-static inline int dissolve_free_huge_pages(unsigned long start_pfn,
+static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn,
 					   unsigned long end_pfn)
 {
 	return 0;
@@ -1164,6 +1243,11 @@ static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask)
 	return 0;
 }
 
+static inline bool htlb_allow_alloc_fallback(int reason)
+{
+	return false;
+}
+
 static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
 					   struct mm_struct *mm, pte_t *pte)
 {
@@ -1185,11 +1269,15 @@ static inline void hugetlb_count_sub(long l, struct mm_struct *mm)
 static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma,
 					  unsigned long addr, pte_t *ptep)
 {
+#ifdef CONFIG_MMU
+	return ptep_get(ptep);
+#else
 	return *ptep;
+#endif
 }
 
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
+				   pte_t *ptep, pte_t pte, unsigned long sz)
 {
 }
 
@@ -1200,6 +1288,21 @@ static inline void hugetlb_register_node(struct node *node)
 static inline void hugetlb_unregister_node(struct node *node)
 {
 }
+
+static inline bool hugetlbfs_pagecache_present(
+    struct hstate *h, struct vm_area_struct *vma, unsigned long address)
+{
+	return false;
+}
+
+static inline void hugetlb_bootmem_alloc(void)
+{
+}
+
+static inline bool hugetlb_bootmem_allocated(void)
+{
+	return false;
+}
 #endif	/* CONFIG_HUGETLB_PAGE */
 
 static inline spinlock_t *huge_pte_lock(struct hstate *h,
@@ -1220,7 +1323,7 @@ static inline __init void hugetlb_cma_reserve(int order)
 }
 #endif
 
-#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
 static inline bool hugetlb_pmd_shared(pte_t *pte)
 {
 	return page_count(virt_to_page(pte)) > 1;
@@ -1247,6 +1350,8 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 	return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data;
 }
 
+bool __vma_private_lock(struct vm_area_struct *vma);
+
 /*
  * Safe version of huge_pte_offset() to check the locks.  See comments
  * above huge_pte_offset().
@@ -1254,8 +1359,7 @@ static inline bool __vma_shareable_lock(struct vm_area_struct *vma)
 static inline pte_t *
 hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz)
 {
-#if defined(CONFIG_HUGETLB_PAGE) && \
-	defined(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && defined(CONFIG_LOCKDEP)
+#if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP)
 	struct hugetlb_vma_lock *vma_lock = vma->vm_private_data;
 
 	/*
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 3d82d91f49ac..e5d64b8b59c2 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -22,13 +22,6 @@ struct resv_map;
 struct file_region;
 
 #ifdef CONFIG_CGROUP_HUGETLB
-/*
- * Minimum page order trackable by hugetlb cgroup.
- * At least 3 pages are necessary for all the tracking information.
- * The second tail page contains all of the hugetlb-specific fields.
- */
-#define HUGETLB_CGROUP_MIN_ORDER order_base_2(__NR_USED_SUBPAGE)
-
 enum hugetlb_memory_event {
 	HUGETLB_MAX,
 	HUGETLB_NR_MEMORY_EVENTS,
@@ -68,8 +61,6 @@ static inline struct hugetlb_cgroup *
 __hugetlb_cgroup_from_folio(struct folio *folio, bool rsvd)
 {
 	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
-	if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER)
-		return NULL;
 	if (rsvd)
 		return folio->_hugetlb_cgroup_rsvd;
 	else
@@ -91,8 +82,6 @@ static inline void __set_hugetlb_cgroup(struct folio *folio,
 				       struct hugetlb_cgroup *h_cg, bool rsvd)
 {
 	VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio);
-	if (folio_order(folio) < HUGETLB_CGROUP_MIN_ORDER)
-		return;
 	if (rsvd)
 		folio->_hugetlb_cgroup_rsvd = h_cg;
 	else
diff --git a/include/linux/hugetlb_inline.h b/include/linux/hugetlb_inline.h
index 0660a03d37d9..a27aa0162918 100644
--- a/include/linux/hugetlb_inline.h
+++ b/include/linux/hugetlb_inline.h
@@ -2,22 +2,27 @@
 #ifndef _LINUX_HUGETLB_INLINE_H
 #define _LINUX_HUGETLB_INLINE_H
 
-#ifdef CONFIG_HUGETLB_PAGE
-
 #include <linux/mm.h>
 
-static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
+#ifdef CONFIG_HUGETLB_PAGE
+
+static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags)
 {
-	return !!(vma->vm_flags & VM_HUGETLB);
+	return !!(vm_flags & VM_HUGETLB);
 }
 
 #else
 
-static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
+static inline bool is_vm_hugetlb_flags(vm_flags_t vm_flags)
 {
 	return false;
 }
 
 #endif
 
+static inline bool is_vm_hugetlb_page(struct vm_area_struct *vma)
+{
+	return is_vm_hugetlb_flags(vma->vm_flags);
+}
+
 #endif
diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h
new file mode 100644
index 000000000000..c4403eeb7144
--- /dev/null
+++ b/include/linux/hung_task.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Detect Hung Task: detecting tasks stuck in D state
+ *
+ * Copyright (C) 2025 Tongcheng Travel (www.ly.com)
+ * Author: Lance Yang <mingzhe.yang@ly.com>
+ */
+#ifndef __LINUX_HUNG_TASK_H
+#define __LINUX_HUNG_TASK_H
+
+#include <linux/bug.h>
+#include <linux/sched.h>
+#include <linux/compiler.h>
+
+/*
+ * @blocker: Combines lock address and blocking type.
+ *
+ * Since lock pointers are at least 4-byte aligned(32-bit) or 8-byte
+ * aligned(64-bit). This leaves the 2 least bits (LSBs) of the pointer
+ * always zero. So we can use these bits to encode the specific blocking
+ * type.
+ *
+ * Note that on architectures where this is not guaranteed, or for any
+ * unaligned lock, this tracking mechanism is silently skipped for that
+ * lock.
+ *
+ * Type encoding:
+ * 00 - Blocked on mutex			(BLOCKER_TYPE_MUTEX)
+ * 01 - Blocked on semaphore			(BLOCKER_TYPE_SEM)
+ * 10 - Blocked on rw-semaphore as READER	(BLOCKER_TYPE_RWSEM_READER)
+ * 11 - Blocked on rw-semaphore as WRITER	(BLOCKER_TYPE_RWSEM_WRITER)
+ */
+#define BLOCKER_TYPE_MUTEX		0x00UL
+#define BLOCKER_TYPE_SEM		0x01UL
+#define BLOCKER_TYPE_RWSEM_READER	0x02UL
+#define BLOCKER_TYPE_RWSEM_WRITER	0x03UL
+
+#define BLOCKER_TYPE_MASK		0x03UL
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+static inline void hung_task_set_blocker(void *lock, unsigned long type)
+{
+	unsigned long lock_ptr = (unsigned long)lock;
+
+	WARN_ON_ONCE(!lock_ptr);
+	WARN_ON_ONCE(READ_ONCE(current->blocker));
+
+	/*
+	 * If the lock pointer matches the BLOCKER_TYPE_MASK, return
+	 * without writing anything.
+	 */
+	if (lock_ptr & BLOCKER_TYPE_MASK)
+		return;
+
+	WRITE_ONCE(current->blocker, lock_ptr | type);
+}
+
+static inline void hung_task_clear_blocker(void)
+{
+	WRITE_ONCE(current->blocker, 0UL);
+}
+
+/*
+ * hung_task_get_blocker_type - Extracts blocker type from encoded blocker
+ * address.
+ *
+ * @blocker: Blocker pointer with encoded type (via LSB bits)
+ *
+ * Returns: BLOCKER_TYPE_MUTEX, BLOCKER_TYPE_SEM, etc.
+ */
+static inline unsigned long hung_task_get_blocker_type(unsigned long blocker)
+{
+	WARN_ON_ONCE(!blocker);
+
+	return blocker & BLOCKER_TYPE_MASK;
+}
+
+static inline void *hung_task_blocker_to_lock(unsigned long blocker)
+{
+	WARN_ON_ONCE(!blocker);
+
+	return (void *)(blocker & ~BLOCKER_TYPE_MASK);
+}
+#else
+static inline void hung_task_set_blocker(void *lock, unsigned long type)
+{
+}
+static inline void hung_task_clear_blocker(void)
+{
+}
+static inline unsigned long hung_task_get_blocker_type(unsigned long blocker)
+{
+	return 0UL;
+}
+static inline void *hung_task_blocker_to_lock(unsigned long blocker)
+{
+	return NULL;
+}
+#endif
+
+#endif /* __LINUX_HUNG_TASK_H */
diff --git a/include/linux/hw_bitfield.h b/include/linux/hw_bitfield.h
new file mode 100644
index 000000000000..df202e167ce4
--- /dev/null
+++ b/include/linux/hw_bitfield.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2025, Collabora Ltd.
+ */
+
+#ifndef _LINUX_HW_BITFIELD_H
+#define _LINUX_HW_BITFIELD_H
+
+#include <linux/bitfield.h>
+#include <linux/build_bug.h>
+#include <linux/limits.h>
+
+/**
+ * FIELD_PREP_WM16() - prepare a bitfield element with a mask in the upper half
+ * @_mask: shifted mask defining the field's length and position
+ * @_val:  value to put in the field
+ *
+ * FIELD_PREP_WM16() masks and shifts up the value, as well as bitwise ORs the
+ * result with the mask shifted up by 16.
+ *
+ * This is useful for a common design of hardware registers where the upper
+ * 16-bit half of a 32-bit register is used as a write-enable mask. In such a
+ * register, a bit in the lower half is only updated if the corresponding bit
+ * in the upper half is high.
+ */
+#define FIELD_PREP_WM16(_mask, _val)					     \
+	({								     \
+		typeof(_val) __val = _val;				     \
+		typeof(_mask) __mask = _mask;				     \
+		__BF_FIELD_CHECK(__mask, ((u16)0U), __val,		     \
+				 "HWORD_UPDATE: ");			     \
+		(((typeof(__mask))(__val) << __bf_shf(__mask)) & (__mask)) | \
+		((__mask) << 16);					     \
+	})
+
+/**
+ * FIELD_PREP_WM16_CONST() - prepare a constant bitfield element with a mask in
+ *                           the upper half
+ * @_mask: shifted mask defining the field's length and position
+ * @_val:  value to put in the field
+ *
+ * FIELD_PREP_WM16_CONST() masks and shifts up the value, as well as bitwise ORs
+ * the result with the mask shifted up by 16.
+ *
+ * This is useful for a common design of hardware registers where the upper
+ * 16-bit half of a 32-bit register is used as a write-enable mask. In such a
+ * register, a bit in the lower half is only updated if the corresponding bit
+ * in the upper half is high.
+ *
+ * Unlike FIELD_PREP_WM16(), this is a constant expression and can therefore
+ * be used in initializers. Error checking is less comfortable for this
+ * version.
+ */
+#define FIELD_PREP_WM16_CONST(_mask, _val)				 \
+	(								 \
+		FIELD_PREP_CONST(_mask, _val) |				 \
+		(BUILD_BUG_ON_ZERO(const_true((u64)(_mask) > U16_MAX)) + \
+		 ((_mask) << 16))					 \
+	)
+
+
+#endif /* _LINUX_HW_BITFIELD_H */
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 7fbb45911273..db199d653dd1 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -90,9 +90,6 @@ extern int dbg_reserve_bp_slot(struct perf_event *bp);
 extern int dbg_release_bp_slot(struct perf_event *bp);
 extern int reserve_bp_slot(struct perf_event *bp);
 extern void release_bp_slot(struct perf_event *bp);
-int arch_reserve_bp_slot(struct perf_event *bp);
-void arch_release_bp_slot(struct perf_event *bp);
-void arch_unregister_hw_breakpoint(struct perf_event *bp);
 
 extern void flush_ptrace_hw_breakpoint(struct task_struct *tsk);
 
diff --git a/include/linux/hw_random.h b/include/linux/hw_random.h
index 8a3115516a1b..b424555753b1 100644
--- a/include/linux/hw_random.h
+++ b/include/linux/hw_random.h
@@ -13,9 +13,8 @@
 #define LINUX_HWRANDOM_H_
 
 #include <linux/completion.h>
-#include <linux/types.h>
-#include <linux/list.h>
 #include <linux/kref.h>
+#include <linux/types.h>
 
 /**
  * struct hwrng - Hardware Random Number Generator driver
@@ -63,5 +62,6 @@ extern void hwrng_unregister(struct hwrng *rng);
 extern void devm_hwrng_unregister(struct device *dve, struct hwrng *rng);
 
 extern long hwrng_msleep(struct hwrng *rng, unsigned int msecs);
+extern long hwrng_yield(struct hwrng *rng);
 
 #endif /* LINUX_HWRANDOM_H_ */
diff --git a/include/linux/hwmon.h b/include/linux/hwmon.h
index 492dd27a5dd8..301a83afbd66 100644
--- a/include/linux/hwmon.h
+++ b/include/linux/hwmon.h
@@ -24,6 +24,7 @@ enum hwmon_sensor_types {
 	hwmon_curr,
 	hwmon_power,
 	hwmon_energy,
+	hwmon_energy64,
 	hwmon_humidity,
 	hwmon_fan,
 	hwmon_pwm,
@@ -44,6 +45,8 @@ enum hwmon_chip_attributes {
 	hwmon_chip_in_samples,
 	hwmon_chip_power_samples,
 	hwmon_chip_temp_samples,
+	hwmon_chip_beep_enable,
+	hwmon_chip_pec,
 };
 
 #define HWMON_C_TEMP_RESET_HISTORY	BIT(hwmon_chip_temp_reset_history)
@@ -58,6 +61,8 @@ enum hwmon_chip_attributes {
 #define HWMON_C_IN_SAMPLES		BIT(hwmon_chip_in_samples)
 #define HWMON_C_POWER_SAMPLES		BIT(hwmon_chip_power_samples)
 #define HWMON_C_TEMP_SAMPLES		BIT(hwmon_chip_temp_samples)
+#define HWMON_C_BEEP_ENABLE		BIT(hwmon_chip_beep_enable)
+#define HWMON_C_PEC			BIT(hwmon_chip_pec)
 
 enum hwmon_temp_attributes {
 	hwmon_temp_enable,
@@ -87,6 +92,7 @@ enum hwmon_temp_attributes {
 	hwmon_temp_reset_history,
 	hwmon_temp_rated_min,
 	hwmon_temp_rated_max,
+	hwmon_temp_beep,
 };
 
 #define HWMON_T_ENABLE		BIT(hwmon_temp_enable)
@@ -116,6 +122,7 @@ enum hwmon_temp_attributes {
 #define HWMON_T_RESET_HISTORY	BIT(hwmon_temp_reset_history)
 #define HWMON_T_RATED_MIN	BIT(hwmon_temp_rated_min)
 #define HWMON_T_RATED_MAX	BIT(hwmon_temp_rated_max)
+#define HWMON_T_BEEP		BIT(hwmon_temp_beep)
 
 enum hwmon_in_attributes {
 	hwmon_in_enable,
@@ -136,6 +143,8 @@ enum hwmon_in_attributes {
 	hwmon_in_crit_alarm,
 	hwmon_in_rated_min,
 	hwmon_in_rated_max,
+	hwmon_in_beep,
+	hwmon_in_fault,
 };
 
 #define HWMON_I_ENABLE		BIT(hwmon_in_enable)
@@ -156,6 +165,8 @@ enum hwmon_in_attributes {
 #define HWMON_I_CRIT_ALARM	BIT(hwmon_in_crit_alarm)
 #define HWMON_I_RATED_MIN	BIT(hwmon_in_rated_min)
 #define HWMON_I_RATED_MAX	BIT(hwmon_in_rated_max)
+#define HWMON_I_BEEP		BIT(hwmon_in_beep)
+#define HWMON_I_FAULT		BIT(hwmon_in_fault)
 
 enum hwmon_curr_attributes {
 	hwmon_curr_enable,
@@ -176,6 +187,7 @@ enum hwmon_curr_attributes {
 	hwmon_curr_crit_alarm,
 	hwmon_curr_rated_min,
 	hwmon_curr_rated_max,
+	hwmon_curr_beep,
 };
 
 #define HWMON_C_ENABLE		BIT(hwmon_curr_enable)
@@ -196,6 +208,7 @@ enum hwmon_curr_attributes {
 #define HWMON_C_CRIT_ALARM	BIT(hwmon_curr_crit_alarm)
 #define HWMON_C_RATED_MIN	BIT(hwmon_curr_rated_min)
 #define HWMON_C_RATED_MAX	BIT(hwmon_curr_rated_max)
+#define HWMON_C_BEEP		BIT(hwmon_curr_beep)
 
 enum hwmon_power_attributes {
 	hwmon_power_enable,
@@ -285,6 +298,8 @@ enum hwmon_humidity_attributes {
 	hwmon_humidity_fault,
 	hwmon_humidity_rated_min,
 	hwmon_humidity_rated_max,
+	hwmon_humidity_min_alarm,
+	hwmon_humidity_max_alarm,
 };
 
 #define HWMON_H_ENABLE			BIT(hwmon_humidity_enable)
@@ -298,6 +313,8 @@ enum hwmon_humidity_attributes {
 #define HWMON_H_FAULT			BIT(hwmon_humidity_fault)
 #define HWMON_H_RATED_MIN		BIT(hwmon_humidity_rated_min)
 #define HWMON_H_RATED_MAX		BIT(hwmon_humidity_rated_max)
+#define HWMON_H_MIN_ALARM		BIT(hwmon_humidity_min_alarm)
+#define HWMON_H_MAX_ALARM		BIT(hwmon_humidity_max_alarm)
 
 enum hwmon_fan_attributes {
 	hwmon_fan_enable,
@@ -312,6 +329,7 @@ enum hwmon_fan_attributes {
 	hwmon_fan_min_alarm,
 	hwmon_fan_max_alarm,
 	hwmon_fan_fault,
+	hwmon_fan_beep,
 };
 
 #define HWMON_F_ENABLE			BIT(hwmon_fan_enable)
@@ -326,6 +344,7 @@ enum hwmon_fan_attributes {
 #define HWMON_F_MIN_ALARM		BIT(hwmon_fan_min_alarm)
 #define HWMON_F_MAX_ALARM		BIT(hwmon_fan_max_alarm)
 #define HWMON_F_FAULT			BIT(hwmon_fan_fault)
+#define HWMON_F_BEEP			BIT(hwmon_fan_beep)
 
 enum hwmon_pwm_attributes {
 	hwmon_pwm_input,
@@ -350,7 +369,9 @@ enum hwmon_intrusion_attributes {
 
 /**
  * struct hwmon_ops - hwmon device operations
- * @is_visible: Callback to return attribute visibility. Mandatory.
+ * @visible:	Static visibility. If non-zero, 'is_visible' is ignored.
+ * @is_visible: Callback to return attribute visibility. Mandatory unless
+ *		'visible' is non-zero.
  *		Parameters are:
  *		@const void *drvdata:
  *			Pointer to driver-private data structure passed
@@ -394,6 +415,7 @@ enum hwmon_intrusion_attributes {
  *		The function returns 0 on success or a negative error number.
  */
 struct hwmon_ops {
+	umode_t visible;
 	umode_t (*is_visible)(const void *drvdata, enum hwmon_sensor_types type,
 			      u32 attr, int channel);
 	int (*read)(struct device *dev, enum hwmon_sensor_types type,
@@ -415,12 +437,12 @@ struct hwmon_channel_info {
 	const u32 *config;
 };
 
-#define HWMON_CHANNEL_INFO(stype, ...)	\
-	(&(struct hwmon_channel_info) {	\
-		.type = hwmon_##stype,	\
-		.config = (u32 []) {	\
-			__VA_ARGS__, 0	\
-		}			\
+#define HWMON_CHANNEL_INFO(stype, ...)		\
+	(&(const struct hwmon_channel_info) {	\
+		.type = hwmon_##stype,		\
+		.config = (const u32 []) {	\
+			__VA_ARGS__, 0		\
+		}				\
 	})
 
 /**
@@ -463,7 +485,6 @@ devm_hwmon_device_register_with_info(struct device *dev,
 				const struct attribute_group **extra_groups);
 
 void hwmon_device_unregister(struct device *dev);
-void devm_hwmon_device_unregister(struct device *dev);
 
 int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type,
 		       u32 attr, int channel);
@@ -471,6 +492,9 @@ int hwmon_notify_event(struct device *dev, enum hwmon_sensor_types type,
 char *hwmon_sanitize_name(const char *name);
 char *devm_hwmon_sanitize_name(struct device *dev, const char *name);
 
+void hwmon_lock(struct device *dev);
+void hwmon_unlock(struct device *dev);
+
 /**
  * hwmon_is_bad_char - Is the char invalid in a hwmon name
  * @ch: the char to be considered
diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h
index bfe7c1f1ac6d..f35b42e8c5de 100644
--- a/include/linux/hwspinlock.h
+++ b/include/linux/hwspinlock.h
@@ -58,18 +58,16 @@ struct hwspinlock_pdata {
 int hwspin_lock_register(struct hwspinlock_device *bank, struct device *dev,
 		const struct hwspinlock_ops *ops, int base_id, int num_locks);
 int hwspin_lock_unregister(struct hwspinlock_device *bank);
-struct hwspinlock *hwspin_lock_request(void);
 struct hwspinlock *hwspin_lock_request_specific(unsigned int id);
 int hwspin_lock_free(struct hwspinlock *hwlock);
 int of_hwspin_lock_get_id(struct device_node *np, int index);
-int hwspin_lock_get_id(struct hwspinlock *hwlock);
 int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int,
 							unsigned long *);
 int __hwspin_trylock(struct hwspinlock *, int, unsigned long *);
 void __hwspin_unlock(struct hwspinlock *, int, unsigned long *);
 int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name);
+int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id);
 int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock);
-struct hwspinlock *devm_hwspin_lock_request(struct device *dev);
 struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev,
 						     unsigned int id);
 int devm_hwspin_lock_unregister(struct device *dev,
@@ -94,11 +92,6 @@ int devm_hwspin_lock_register(struct device *dev,
  * Note: ERR_PTR(-ENODEV) will still be considered a success for NULL-checking
  * users. Others, which care, can still check this with IS_ERR.
  */
-static inline struct hwspinlock *hwspin_lock_request(void)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline struct hwspinlock *hwspin_lock_request_specific(unsigned int id)
 {
 	return ERR_PTR(-ENODEV);
@@ -127,12 +120,12 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
 {
 }
 
-static inline int of_hwspin_lock_get_id(struct device_node *np, int index)
+static inline int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id)
 {
 	return 0;
 }
 
-static inline int hwspin_lock_get_id(struct hwspinlock *hwlock)
+static inline int of_hwspin_lock_get_id(struct device_node *np, int index)
 {
 	return 0;
 }
@@ -149,11 +142,6 @@ int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock)
 	return 0;
 }
 
-static inline struct hwspinlock *devm_hwspin_lock_request(struct device *dev)
-{
-	return ERR_PTR(-ENODEV);
-}
-
 static inline
 struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev,
 						     unsigned int id)
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index bfbc37ce223b..dfc516c1c719 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -24,7 +24,7 @@
 #include <linux/mod_devicetable.h>
 #include <linux/interrupt.h>
 #include <linux/reciprocal_div.h>
-#include <asm/hyperv-tlfs.h>
+#include <hyperv/hvhdk.h>
 
 #define MAX_PAGE_BUFFER_COUNT				32
 #define MAX_MULTIPAGE_BUFFER_COUNT			32 /* 128K */
@@ -164,8 +164,28 @@ struct hv_ring_buffer {
 	u8 buffer[];
 } __packed;
 
+
+/*
+ * If the requested ring buffer size is at least 8 times the size of the
+ * header, steal space from the ring buffer for the header. Otherwise, add
+ * space for the header so that is doesn't take too much of the ring buffer
+ * space.
+ *
+ * The factor of 8 is somewhat arbitrary. The goal is to prevent adding a
+ * relatively small header (4 Kbytes on x86) to a large-ish power-of-2 ring
+ * buffer size (such as 128 Kbytes) and so end up making a nearly twice as
+ * large allocation that will be almost half wasted. As a contrasting example,
+ * on ARM64 with 64 Kbyte page size, we don't want to take 64 Kbytes for the
+ * header from a 128 Kbyte allocation, leaving only 64 Kbytes for the ring.
+ * In this latter case, we must add 64 Kbytes for the header and not worry
+ * about what's wasted.
+ */
+#define VMBUS_HEADER_ADJ(payload_sz) \
+	((payload_sz) >=  8 * sizeof(struct hv_ring_buffer) ? \
+	0 : sizeof(struct hv_ring_buffer))
+
 /* Calculate the proper size of a ringbuffer, it must be page-aligned */
-#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(sizeof(struct hv_ring_buffer) + \
+#define VMBUS_RING_SIZE(payload_sz) PAGE_ALIGN(VMBUS_HEADER_ADJ(payload_sz) + \
 					       (payload_sz))
 
 struct hv_ring_buffer_info {
@@ -245,16 +265,18 @@ static inline u32 hv_get_avail_to_write_percent(
  * Linux kernel.
  */
 
-#define VERSION_WS2008  ((0 << 16) | (13))
-#define VERSION_WIN7    ((1 << 16) | (1))
-#define VERSION_WIN8    ((2 << 16) | (4))
-#define VERSION_WIN8_1    ((3 << 16) | (0))
-#define VERSION_WIN10 ((4 << 16) | (0))
-#define VERSION_WIN10_V4_1 ((4 << 16) | (1))
-#define VERSION_WIN10_V5 ((5 << 16) | (0))
-#define VERSION_WIN10_V5_1 ((5 << 16) | (1))
-#define VERSION_WIN10_V5_2 ((5 << 16) | (2))
-#define VERSION_WIN10_V5_3 ((5 << 16) | (3))
+#define VMBUS_MAKE_VERSION(MAJ, MIN)	((((u32)MAJ) << 16) | (MIN))
+#define VERSION_WS2008					VMBUS_MAKE_VERSION(0, 13)
+#define VERSION_WIN7					VMBUS_MAKE_VERSION(1, 1)
+#define VERSION_WIN8					VMBUS_MAKE_VERSION(2, 4)
+#define VERSION_WIN8_1					VMBUS_MAKE_VERSION(3, 0)
+#define VERSION_WIN10					VMBUS_MAKE_VERSION(4, 0)
+#define VERSION_WIN10_V4_1				VMBUS_MAKE_VERSION(4, 1)
+#define VERSION_WIN10_V5				VMBUS_MAKE_VERSION(5, 0)
+#define VERSION_WIN10_V5_1				VMBUS_MAKE_VERSION(5, 1)
+#define VERSION_WIN10_V5_2				VMBUS_MAKE_VERSION(5, 2)
+#define VERSION_WIN10_V5_3				VMBUS_MAKE_VERSION(5, 3)
+#define VERSION_WIN10_V6_0				VMBUS_MAKE_VERSION(6, 0)
 
 /* Make maximum size of pipe payload of 16K */
 #define MAX_PIPE_DATA_PAYLOAD		(sizeof(u8) * 16384)
@@ -315,14 +337,22 @@ struct vmbus_channel_offer {
 } __packed;
 
 /* Server Flags */
-#define VMBUS_CHANNEL_ENUMERATE_DEVICE_INTERFACE	1
-#define VMBUS_CHANNEL_SERVER_SUPPORTS_TRANSFER_PAGES	2
-#define VMBUS_CHANNEL_SERVER_SUPPORTS_GPADLS		4
-#define VMBUS_CHANNEL_NAMED_PIPE_MODE			0x10
-#define VMBUS_CHANNEL_LOOPBACK_OFFER			0x100
-#define VMBUS_CHANNEL_PARENT_OFFER			0x200
-#define VMBUS_CHANNEL_REQUEST_MONITORED_NOTIFICATION	0x400
-#define VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER		0x2000
+#define VMBUS_CHANNEL_ENUMERATE_DEVICE_INTERFACE		0x0001
+/*
+ * This flag indicates that the channel is offered by the paravisor, and must
+ * use encrypted memory for the channel ring buffer.
+ */
+#define VMBUS_CHANNEL_CONFIDENTIAL_RING_BUFFER			0x0002
+/*
+ * This flag indicates that the channel is offered by the paravisor, and must
+ * use encrypted memory for GPA direct packets and additional GPADLs.
+ */
+#define VMBUS_CHANNEL_CONFIDENTIAL_EXTERNAL_MEMORY		0x0004
+#define VMBUS_CHANNEL_NAMED_PIPE_MODE					0x0010
+#define VMBUS_CHANNEL_LOOPBACK_OFFER					0x0100
+#define VMBUS_CHANNEL_PARENT_OFFER						0x0200
+#define VMBUS_CHANNEL_REQUEST_MONITORED_NOTIFICATION	0x0400
+#define VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER				0x2000
 
 struct vmpacket_descriptor {
 	u16 type;
@@ -348,20 +378,7 @@ struct vmtransfer_page_packet_header {
 	u8  sender_owns_set;
 	u8 reserved;
 	u32 range_cnt;
-	struct vmtransfer_page_range ranges[1];
-} __packed;
-
-struct vmgpadl_packet_header {
-	struct vmpacket_descriptor d;
-	u32 gpadl;
-	u32 reserved;
-} __packed;
-
-struct vmadd_remove_transfer_page_set {
-	struct vmpacket_descriptor d;
-	u32 gpadl;
-	u16 xfer_pageset_id;
-	u16 reserved;
+	struct vmtransfer_page_range ranges[];
 } __packed;
 
 /*
@@ -375,30 +392,6 @@ struct gpa_range {
 };
 
 /*
- * This is the format for an Establish Gpadl packet, which contains a handle by
- * which this GPADL will be known and a set of GPA ranges associated with it.
- * This can be converted to a MDL by the guest OS.  If there are multiple GPA
- * ranges, then the resulting MDL will be "chained," representing multiple VA
- * ranges.
- */
-struct vmestablish_gpadl {
-	struct vmpacket_descriptor d;
-	u32 gpadl;
-	u32 range_cnt;
-	struct gpa_range range[1];
-} __packed;
-
-/*
- * This is the format for a Teardown Gpadl packet, which indicates that the
- * GPADL handle in the Establish Gpadl packet will never be referenced again.
- */
-struct vmteardown_gpadl {
-	struct vmpacket_descriptor d;
-	u32 gpadl;
-	u32 reserved;	/* for alignment to a 8-byte boundary */
-} __packed;
-
-/*
  * This is the format for a GPA-Direct packet, which contains a set of GPA
  * ranges, in addition to commands and/or data.
  */
@@ -409,25 +402,6 @@ struct vmdata_gpa_direct {
 	struct gpa_range range[1];
 } __packed;
 
-/* This is the format for a Additional Data Packet. */
-struct vmadditional_data {
-	struct vmpacket_descriptor d;
-	u64 total_bytes;
-	u32 offset;
-	u32 byte_cnt;
-	unsigned char data[1];
-} __packed;
-
-union vmpacket_largest_possible_header {
-	struct vmpacket_descriptor simple_hdr;
-	struct vmtransfer_page_packet_header xfer_page_hdr;
-	struct vmgpadl_packet_header gpadl_hdr;
-	struct vmadd_remove_transfer_page_set add_rm_xfer_page_hdr;
-	struct vmestablish_gpadl establish_gpadl_hdr;
-	struct vmteardown_gpadl teardown_gpadl_hdr;
-	struct vmdata_gpa_direct data_gpa_direct_hdr;
-};
-
 #define VMPACKET_DATA_START_ADDRESS(__packet)	\
 	(void *)(((unsigned char *)__packet) +	\
 	 ((struct vmpacket_descriptor)__packet)->offset8 * 8)
@@ -657,6 +631,12 @@ struct vmbus_channel_relid_released {
 	u32 child_relid;
 } __packed;
 
+/*
+ * Used by the paravisor only, means that the encrypted ring buffers and
+ * the encrypted external memory are supported
+ */
+#define VMBUS_FEATURE_FLAG_CONFIDENTIAL_CHANNELS	0x10
+
 struct vmbus_channel_initiate_contact {
 	struct vmbus_channel_message_header header;
 	u32 vmbus_version_requested;
@@ -665,8 +645,9 @@ struct vmbus_channel_initiate_contact {
 		u64 interrupt_page;
 		struct {
 			u8	msg_sint;
-			u8	padding1[3];
-			u32	padding2;
+			u8	msg_vtl;
+			u8	reserved[2];
+			u32 feature_flags; /* VMBus version 6.0 */
 		};
 	};
 	u64 monitor_page1;
@@ -743,20 +724,6 @@ struct vmbus_channel_msginfo {
 	unsigned char msg[];
 };
 
-struct vmbus_close_msg {
-	struct vmbus_channel_msginfo info;
-	struct vmbus_channel_close_channel msg;
-};
-
-/* Define connection identifier type. */
-union hv_connection_id {
-	u32 asu32;
-	struct {
-		u32 id:24;
-		u32 reserved:8;
-	} u;
-};
-
 enum vmbus_device_type {
 	HV_IDE = 0,
 	HV_SCSI,
@@ -800,6 +767,8 @@ struct vmbus_requestor {
 #define VMBUS_RQST_RESET (U64_MAX - 3)
 
 struct vmbus_device {
+	/* preferred ring buffer size in KB, 0 means no preferred size for this device */
+	size_t pref_ring_size;
 	u16  dev_type;
 	guid_t guid;
 	bool perf_device;
@@ -812,6 +781,7 @@ struct vmbus_gpadl {
 	u32 gpadl_handle;
 	u32 size;
 	void *buffer;
+	bool decrypted;
 };
 
 struct vmbus_channel {
@@ -842,7 +812,7 @@ struct vmbus_channel {
 	struct hv_ring_buffer_info outbound;	/* send to parent */
 	struct hv_ring_buffer_info inbound;	/* receive from parent */
 
-	struct vmbus_close_msg close_msg;
+	struct vmbus_channel_close_channel close_msg;
 
 	/* Statistics */
 	u64	interrupts;	/* Host to Guest interrupts */
@@ -1044,6 +1014,16 @@ struct vmbus_channel {
 
 	/* The max size of a packet on this channel */
 	u32 max_pkt_size;
+
+	/* function to mmap ring buffer memory to the channel's sysfs ring attribute */
+	int (*mmap_ring_buffer)(struct vmbus_channel *channel, struct vm_area_struct *vma);
+
+	/* boolean to control visibility of sysfs for ring buffer */
+	bool ring_sysfs_visible;
+	/* The ring buffer is encrypted */
+	bool co_ring_buffer;
+	/* The external memory is encrypted */
+	bool co_external_memory;
 };
 
 #define lock_requestor(channel, flags)					\
@@ -1068,6 +1048,16 @@ u64 vmbus_request_addr_match(struct vmbus_channel *channel, u64 trans_id,
 			     u64 rqst_addr);
 u64 vmbus_request_addr(struct vmbus_channel *channel, u64 trans_id);
 
+static inline bool is_co_ring_buffer(const struct vmbus_channel_offer_channel *o)
+{
+	return !!(o->offer.chn_flags & VMBUS_CHANNEL_CONFIDENTIAL_RING_BUFFER);
+}
+
+static inline bool is_co_external_memory(const struct vmbus_channel_offer_channel *o)
+{
+	return !!(o->offer.chn_flags & VMBUS_CHANNEL_CONFIDENTIAL_EXTERNAL_MEMORY);
+}
+
 static inline bool is_hvsock_offer(const struct vmbus_channel_offer_channel *o)
 {
 	return !!(o->offer.chn_flags & VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER);
@@ -1203,13 +1193,6 @@ extern int vmbus_sendpacket(struct vmbus_channel *channel,
 				  enum vmbus_packet_type type,
 				  u32 flags);
 
-extern int vmbus_sendpacket_pagebuffer(struct vmbus_channel *channel,
-					    struct hv_page_buffer pagebuffers[],
-					    u32 pagecount,
-					    void *buffer,
-					    u32 bufferlen,
-					    u64 requestid);
-
 extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 				     struct vmbus_packet_mpb_array *mpb,
 				     u32 desc_size,
@@ -1239,9 +1222,6 @@ extern int vmbus_recvpacket_raw(struct vmbus_channel *channel,
 				     u32 *buffer_actual_len,
 				     u64 *requestid);
 
-
-extern void vmbus_ontimer(unsigned long data);
-
 /* Base driver object */
 struct hv_driver {
 	const char *name;
@@ -1310,11 +1290,7 @@ struct hv_device {
 
 
 #define device_to_hv_device(d)	container_of_const(d, struct hv_device, device)
-
-static inline struct hv_driver *drv_to_hv_drv(struct device_driver *d)
-{
-	return container_of(d, struct hv_driver, driver);
-}
+#define drv_to_hv_drv(d)	container_of_const(d, struct hv_driver, driver)
 
 static inline void hv_set_drvdata(struct hv_device *dev, void *data)
 {
@@ -1326,6 +1302,8 @@ static inline void *hv_get_drvdata(struct hv_device *dev)
 	return dev_get_drvdata(&dev->device);
 }
 
+struct device *hv_get_vmbus_root_device(void);
+
 struct hv_ring_buffer_debug_info {
 	u32 current_interrupt_mask;
 	u32 current_read_index;
@@ -1543,6 +1521,7 @@ struct hv_util_service {
 	void *channel;
 	void (*util_cb)(void *);
 	int (*util_init)(struct hv_util_service *);
+	int (*util_init_transport)(void);
 	void (*util_deinit)(void);
 	int (*util_pre_suspend)(void);
 	int (*util_pre_resume)(void);
@@ -1653,6 +1632,7 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 				  const guid_t *shv_host_servie_id);
 int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp);
 void vmbus_set_event(struct vmbus_channel *channel);
+int vmbus_channel_set_cpu(struct vmbus_channel *channel, u32 target_cpu);
 
 /* Get the start of the ring buffer. */
 static inline void *
diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h
index 9efbc54e35e5..be5417303ecf 100644
--- a/include/linux/hypervisor.h
+++ b/include/linux/hypervisor.h
@@ -37,6 +37,9 @@ static inline bool hypervisor_isolated_pci_functions(void)
 	if (IS_ENABLED(CONFIG_S390))
 		return true;
 
+	if (IS_ENABLED(CONFIG_LOONGARCH))
+		return true;
+
 	return jailhouse_paravirt();
 }
 
diff --git a/include/linux/i2c-algo-pca.h b/include/linux/i2c-algo-pca.h
index 7c522fdd9ea7..e305bf32e40a 100644
--- a/include/linux/i2c-algo-pca.h
+++ b/include/linux/i2c-algo-pca.h
@@ -71,7 +71,7 @@ struct i2c_algo_pca_data {
 	void 				*data;	/* private low level data */
 	void (*write_byte)		(void *data, int reg, int val);
 	int  (*read_byte)		(void *data, int reg);
-	int  (*wait_for_completion)	(void *data);
+	int  (*wait_for_completion_cb)	(void *data);
 	void (*reset_chip)		(void *data);
 	/* For PCA9564, use one of the predefined frequencies:
 	 * 330000, 288000, 217000, 146000, 88000, 59000, 44000, 36000
diff --git a/include/linux/i2c-atr.h b/include/linux/i2c-atr.h
new file mode 100644
index 000000000000..2bb54dc87c8e
--- /dev/null
+++ b/include/linux/i2c-atr.h
@@ -0,0 +1,149 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * I2C Address Translator
+ *
+ * Copyright (c) 2019,2022 Luca Ceresoli <luca@lucaceresoli.net>
+ * Copyright (c) 2022,2023 Tomi Valkeinen <tomi.valkeinen@ideasonboard.com>
+ *
+ * Based on i2c-mux.h
+ */
+
+#ifndef _LINUX_I2C_ATR_H
+#define _LINUX_I2C_ATR_H
+
+#include <linux/i2c.h>
+#include <linux/types.h>
+
+struct device;
+struct fwnode_handle;
+struct i2c_atr;
+
+/**
+ * enum i2c_atr_flags - Flags for an I2C ATR driver
+ *
+ * @I2C_ATR_F_STATIC: ATR does not support dynamic mapping, use static mapping.
+ *                    Mappings will only be added or removed as a result of
+ *                    devices being added or removed from a child bus.
+ *                    The ATR pool will have to be big enough to accomodate all
+ *                    devices expected to be added to the child buses.
+ * @I2C_ATR_F_PASSTHROUGH: Allow unmapped incoming addresses to pass through
+ */
+enum i2c_atr_flags {
+	I2C_ATR_F_STATIC = BIT(0),
+	I2C_ATR_F_PASSTHROUGH = BIT(1),
+};
+
+/**
+ * struct i2c_atr_ops - Callbacks from ATR to the device driver.
+ * @attach_addr: Notify the driver of a new device connected on a child
+ *               bus, with the alias assigned to it. The driver must
+ *               configure the hardware to use the alias.
+ * @detach_addr: Notify the driver of a device getting disconnected. The
+ *               driver must configure the hardware to stop using the
+ *               alias.
+ *
+ * All these functions return 0 on success, a negative error code otherwise.
+ */
+struct i2c_atr_ops {
+	int (*attach_addr)(struct i2c_atr *atr, u32 chan_id,
+			   u16 addr, u16 alias);
+	void (*detach_addr)(struct i2c_atr *atr, u32 chan_id,
+			    u16 addr);
+};
+
+/**
+ * struct i2c_atr_adap_desc - An ATR downstream bus descriptor
+ * @chan_id:        Index of the new adapter (0 .. max_adapters-1).  This value is
+ *                  passed to the callbacks in `struct i2c_atr_ops`.
+ * @parent:         The device used as the parent of the new i2c adapter, or NULL
+ *                  to use the i2c-atr device as the parent.
+ * @bus_handle:     The fwnode handle that points to the adapter's i2c
+ *                  peripherals, or NULL.
+ * @num_aliases:    The number of aliases in this adapter's private alias pool. Set
+ *                  to zero if this adapter uses the ATR's global alias pool.
+ * @aliases:        An optional array of private aliases used by the adapter
+ *                  instead of the ATR's global pool of aliases. Must contain
+ *                  exactly num_aliases entries if num_aliases > 0, is ignored
+ *                  otherwise.
+ */
+struct i2c_atr_adap_desc {
+	u32 chan_id;
+	struct device *parent;
+	struct fwnode_handle *bus_handle;
+	size_t num_aliases;
+	u16 *aliases;
+};
+
+/**
+ * i2c_atr_new() - Allocate and initialize an I2C ATR helper.
+ * @parent:       The parent (upstream) adapter
+ * @dev:          The device acting as an ATR
+ * @ops:          Driver-specific callbacks
+ * @max_adapters: Maximum number of child adapters
+ * @flags:        Flags for ATR
+ *
+ * The new ATR helper is connected to the parent adapter but has no child
+ * adapters. Call i2c_atr_add_adapter() to add some.
+ *
+ * Call i2c_atr_delete() to remove.
+ *
+ * Return: pointer to the new ATR helper object, or ERR_PTR
+ */
+struct i2c_atr *i2c_atr_new(struct i2c_adapter *parent, struct device *dev,
+			    const struct i2c_atr_ops *ops, int max_adapters,
+			    u32 flags);
+
+/**
+ * i2c_atr_delete - Delete an I2C ATR helper.
+ * @atr: I2C ATR helper to be deleted.
+ *
+ * Precondition: all the adapters added with i2c_atr_add_adapter() must be
+ * removed by calling i2c_atr_del_adapter().
+ */
+void i2c_atr_delete(struct i2c_atr *atr);
+
+/**
+ * i2c_atr_add_adapter - Create a child ("downstream") I2C bus.
+ * @atr:        The I2C ATR
+ * @desc:       An ATR adapter descriptor
+ *
+ * After calling this function a new i2c bus will appear. Adding and removing
+ * devices on the downstream bus will result in calls to the
+ * &i2c_atr_ops->attach_client and &i2c_atr_ops->detach_client callbacks for the
+ * driver to assign an alias to the device.
+ *
+ * The adapter's fwnode is set to @bus_handle, or if @bus_handle is NULL the
+ * function looks for a child node whose 'reg' property matches the chan_id
+ * under the i2c-atr device's 'i2c-atr' node.
+ *
+ * Call i2c_atr_del_adapter() to remove the adapter.
+ *
+ * Return: 0 on success, a negative error code otherwise.
+ */
+int i2c_atr_add_adapter(struct i2c_atr *atr, struct i2c_atr_adap_desc *desc);
+
+/**
+ * i2c_atr_del_adapter - Remove a child ("downstream") I2C bus added by
+ *                       i2c_atr_add_adapter(). If no I2C bus has been added
+ *                       this function is a no-op.
+ * @atr:     The I2C ATR
+ * @chan_id: Index of the adapter to be removed (0 .. max_adapters-1)
+ */
+void i2c_atr_del_adapter(struct i2c_atr *atr, u32 chan_id);
+
+/**
+ * i2c_atr_set_driver_data - Set private driver data to the i2c-atr instance.
+ * @atr:  The I2C ATR
+ * @data: Pointer to the data to store
+ */
+void i2c_atr_set_driver_data(struct i2c_atr *atr, void *data);
+
+/**
+ * i2c_atr_get_driver_data - Get the stored drive data.
+ * @atr:     The I2C ATR
+ *
+ * Return: Pointer to the stored data
+ */
+void *i2c_atr_get_driver_data(struct i2c_atr *atr);
+
+#endif /* _LINUX_I2C_ATR_H */
diff --git a/include/linux/i2c-mux.h b/include/linux/i2c-mux.h
index 98ef73b7c8fd..1784ac7afb11 100644
--- a/include/linux/i2c-mux.h
+++ b/include/linux/i2c-mux.h
@@ -56,8 +56,7 @@ struct i2c_adapter *i2c_root_adapter(struct device *dev);
  * callback functions to perform hardware-specific mux control.
  */
 int i2c_mux_add_adapter(struct i2c_mux_core *muxc,
-			u32 force_nr, u32 chan_id,
-			unsigned int class);
+			u32 force_nr, u32 chan_id);
 
 void i2c_mux_del_adapters(struct i2c_mux_core *muxc);
 
diff --git a/include/linux/i2c-of-prober.h b/include/linux/i2c-of-prober.h
new file mode 100644
index 000000000000..bb6d47f50ee5
--- /dev/null
+++ b/include/linux/i2c-of-prober.h
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Definitions for the Linux I2C OF component prober
+ *
+ * Copyright (C) 2024 Google LLC
+ */
+
+#ifndef _LINUX_I2C_OF_PROBER_H
+#define _LINUX_I2C_OF_PROBER_H
+
+#include <linux/kconfig.h>
+#include <linux/types.h>
+
+struct device;
+struct device_node;
+
+/**
+ * struct i2c_of_probe_ops - I2C OF component prober callbacks
+ *
+ * A set of callbacks to be used by i2c_of_probe_component().
+ *
+ * All callbacks are optional. Callbacks are called only once per run, and are
+ * used in the order they are defined in this structure.
+ *
+ * All callbacks that have return values shall return %0 on success,
+ * or a negative error number on failure.
+ *
+ * The @dev parameter passed to the callbacks is the same as @dev passed to
+ * i2c_of_probe_component(). It should only be used for dev_printk() calls
+ * and nothing else, especially not managed device resource (devres) APIs.
+ */
+struct i2c_of_probe_ops {
+	/**
+	 * @enable: Retrieve and enable resources so that the components respond to probes.
+	 *
+	 * It is OK for this callback to return -EPROBE_DEFER since the intended use includes
+	 * retrieving resources and enables them. Resources should be reverted to their initial
+	 * state and released before returning if this fails.
+	 */
+	int (*enable)(struct device *dev, struct device_node *bus_node, void *data);
+
+	/**
+	 * @cleanup_early: Release exclusive resources prior to calling probe() on a
+	 *		   detected component.
+	 *
+	 * Only called if a matching component is actually found. If none are found,
+	 * resources that would have been released in this callback should be released in
+	 * @free_resourcs_late instead.
+	 */
+	void (*cleanup_early)(struct device *dev, void *data);
+
+	/**
+	 * @cleanup: Opposite of @enable to balance refcounts and free resources after probing.
+	 *
+	 * Should check if resources were already freed by @cleanup_early.
+	 */
+	void (*cleanup)(struct device *dev, void *data);
+};
+
+/**
+ * struct i2c_of_probe_cfg - I2C OF component prober configuration
+ * @ops: Callbacks for the prober to use.
+ * @type: A string to match the device node name prefix to probe for.
+ */
+struct i2c_of_probe_cfg {
+	const struct i2c_of_probe_ops *ops;
+	const char *type;
+};
+
+#if IS_ENABLED(CONFIG_OF_DYNAMIC)
+
+int i2c_of_probe_component(struct device *dev, const struct i2c_of_probe_cfg *cfg, void *ctx);
+
+/**
+ * DOC: I2C OF component prober simple helpers
+ *
+ * Components such as trackpads are commonly connected to a devices baseboard
+ * with a 6-pin ribbon cable. That gives at most one voltage supply and one
+ * GPIO (commonly a "enable" or "reset" line) besides the I2C bus, interrupt
+ * pin, and common ground. Touchscreens, while integrated into the display
+ * panel's connection, typically have the same set of connections.
+ *
+ * A simple set of helpers are provided here for use with the I2C OF component
+ * prober. This implementation targets such components, allowing for at most
+ * one regulator supply.
+ *
+ * The following helpers are provided:
+ * * i2c_of_probe_simple_enable()
+ * * i2c_of_probe_simple_cleanup_early()
+ * * i2c_of_probe_simple_cleanup()
+ */
+
+/**
+ * struct i2c_of_probe_simple_opts - Options for simple I2C component prober callbacks
+ * @res_node_compatible: Compatible string of device node to retrieve resources from.
+ * @supply_name: Name of regulator supply.
+ * @gpio_name: Name of GPIO. NULL if no GPIO line is used. Empty string ("") if GPIO
+ *	       line is unnamed.
+ * @post_power_on_delay_ms: Delay after regulators are powered on. Passed to msleep().
+ * @post_gpio_config_delay_ms: Delay after GPIO is configured. Passed to msleep().
+ * @gpio_assert_to_enable: %true if GPIO should be asserted, i.e. set to logical high,
+ *			   to enable the component.
+ *
+ * This describes power sequences common for the class of components supported by the
+ * simple component prober:
+ * * @gpio_name is configured to the non-active setting according to @gpio_assert_to_enable.
+ * * @supply_name regulator supply is enabled.
+ * * Wait for @post_power_on_delay_ms to pass.
+ * * @gpio_name is configured to the active setting according to @gpio_assert_to_enable.
+ * * Wait for @post_gpio_config_delay_ms to pass.
+ */
+struct i2c_of_probe_simple_opts {
+	const char *res_node_compatible;
+	const char *supply_name;
+	const char *gpio_name;
+	unsigned int post_power_on_delay_ms;
+	unsigned int post_gpio_config_delay_ms;
+	bool gpio_assert_to_enable;
+};
+
+struct gpio_desc;
+struct regulator;
+
+struct i2c_of_probe_simple_ctx {
+	/* public: provided by user before helpers are used. */
+	const struct i2c_of_probe_simple_opts *opts;
+	/* private: internal fields for helpers. */
+	struct regulator *supply;
+	struct gpio_desc *gpiod;
+};
+
+int i2c_of_probe_simple_enable(struct device *dev, struct device_node *bus_node, void *data);
+void i2c_of_probe_simple_cleanup_early(struct device *dev, void *data);
+void i2c_of_probe_simple_cleanup(struct device *dev, void *data);
+
+extern struct i2c_of_probe_ops i2c_of_probe_simple_ops;
+
+#endif /* IS_ENABLED(CONFIG_OF_DYNAMIC) */
+
+#endif /* _LINUX_I2C_OF_PROBER_H */
diff --git a/include/linux/i2c-smbus.h b/include/linux/i2c-smbus.h
index ced1c6ead52a..dc1bd2ab4c13 100644
--- a/include/linux/i2c-smbus.h
+++ b/include/linux/i2c-smbus.h
@@ -44,9 +44,11 @@ static inline void i2c_free_slave_host_notify_device(struct i2c_client *client)
 #endif
 
 #if IS_ENABLED(CONFIG_I2C_SMBUS) && IS_ENABLED(CONFIG_DMI)
-void i2c_register_spd(struct i2c_adapter *adap);
+void i2c_register_spd_write_disable(struct i2c_adapter *adap);
+void i2c_register_spd_write_enable(struct i2c_adapter *adap);
 #else
-static inline void i2c_register_spd(struct i2c_adapter *adap) { }
+static inline void i2c_register_spd_write_disable(struct i2c_adapter *adap) { }
+static inline void i2c_register_spd_write_enable(struct i2c_adapter *adap) { }
 #endif
 
 #endif /* _LINUX_I2C_SMBUS_H */
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 13a1ce38cb0c..20fd41b51d5c 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -23,14 +23,13 @@
 #include <linux/swab.h>		/* for swab16 */
 #include <uapi/linux/i2c.h>
 
-extern struct bus_type i2c_bus_type;
-extern struct device_type i2c_adapter_type;
-extern struct device_type i2c_client_type;
+extern const struct bus_type i2c_bus_type;
+extern const struct device_type i2c_adapter_type;
+extern const struct device_type i2c_client_type;
 
 /* --- General options ------------------------------------------------	*/
 
 struct i2c_msg;
-struct i2c_algorithm;
 struct i2c_adapter;
 struct i2c_client;
 struct i2c_driver;
@@ -237,7 +236,6 @@ enum i2c_driver_flags {
  * struct i2c_driver - represent an I2C device driver
  * @class: What kind of i2c device we instantiate (for detect)
  * @probe: Callback for device binding
- * @probe_new: Transitional callback for device binding - do not use
  * @remove: Callback for device unbinding
  * @shutdown: Callback for device shutdown
  * @alert: Alert callback, for example for the SMBus alert protocol
@@ -272,16 +270,8 @@ enum i2c_driver_flags {
 struct i2c_driver {
 	unsigned int class;
 
-	union {
 	/* Standard driver model interfaces */
-		int (*probe)(struct i2c_client *client);
-		/*
-		 * Legacy callback that was part of a conversion of .probe().
-		 * Today it has the same semantic as .probe(). Don't use for new
-		 * code.
-		 */
-		int (*probe_new)(struct i2c_client *client);
-	};
+	int (*probe)(struct i2c_client *client);
 	void (*remove)(struct i2c_client *client);
 
 
@@ -313,7 +303,7 @@ struct i2c_driver {
 
 	u32 flags;
 };
-#define to_i2c_driver(d) container_of(d, struct i2c_driver, driver)
+#define to_i2c_driver(d) container_of_const(d, struct i2c_driver, driver)
 
 /**
  * struct i2c_client - represent an I2C slave device
@@ -331,6 +321,8 @@ struct i2c_driver {
  *	calls it to pass on slave events to the slave driver.
  * @devres_group_id: id of the devres group that will be created for resources
  *	acquired when probing this device.
+ * @debugfs: pointer to the debugfs subdirectory which the I2C core created
+ *	for this client.
  *
  * An i2c_client identifies a single device (i.e. chip) connected to an
  * i2c bus. The behaviour exposed to Linux is defined by the driver
@@ -360,6 +352,7 @@ struct i2c_client {
 	i2c_slave_cb_t slave_cb;	/* callback for slave mode	*/
 #endif
 	void *devres_group_id;		/* ID of probe devres group	*/
+	struct dentry *debugfs;		/* per-client debugfs dir	*/
 };
 #define to_i2c_client(d) container_of(d, struct i2c_client, dev)
 
@@ -367,6 +360,8 @@ struct i2c_adapter *i2c_verify_adapter(struct device *dev);
 const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id,
 					 const struct i2c_client *client);
 
+const void *i2c_get_match_data(const struct i2c_client *client);
+
 static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj)
 {
 	struct device * const dev = kobj_to_dev(kobj);
@@ -410,7 +405,6 @@ static inline bool i2c_detect_slave_mode(struct device *dev) { return false; }
  * @addr: stored in i2c_client.addr
  * @dev_name: Overrides the default <busnr>-<addr> dev_name if set
  * @platform_data: stored in i2c_client.dev.platform_data
- * @of_node: pointer to OpenFirmware device node
  * @fwnode: device node supplied by the platform firmware
  * @swnode: software node for the device
  * @resources: resources associated with the device
@@ -434,7 +428,6 @@ struct i2c_board_info {
 	unsigned short	addr;
 	const char	*dev_name;
 	void		*platform_data;
-	struct device_node *of_node;
 	struct fwnode_handle *fwnode;
 	const struct software_node *swnode;
 	const struct resource *resources;
@@ -519,46 +512,54 @@ i2c_register_board_info(int busnum, struct i2c_board_info const *info,
 #endif /* I2C_BOARDINFO */
 
 /**
- * struct i2c_algorithm - represent I2C transfer method
- * @master_xfer: Issue a set of i2c transactions to the given I2C adapter
- *   defined by the msgs array, with num messages available to transfer via
- *   the adapter specified by adap.
- * @master_xfer_atomic: same as @master_xfer. Yet, only using atomic context
- *   so e.g. PMICs can be accessed very late before shutdown. Optional.
- * @smbus_xfer: Issue smbus transactions to the given I2C adapter. If this
+ * struct i2c_algorithm - represent I2C transfer methods
+ * @xfer: Transfer a given number of messages defined by the msgs array via
+ *   the specified adapter.
+ * @xfer_atomic: Same as @xfer. Yet, only using atomic context so e.g. PMICs
+ *   can be accessed very late before shutdown. Optional.
+ * @smbus_xfer: Issue SMBus transactions to the given I2C adapter. If this
  *   is not present, then the bus layer will try and convert the SMBus calls
  *   into I2C transfers instead.
- * @smbus_xfer_atomic: same as @smbus_xfer. Yet, only using atomic context
+ * @smbus_xfer_atomic: Same as @smbus_xfer. Yet, only using atomic context
  *   so e.g. PMICs can be accessed very late before shutdown. Optional.
  * @functionality: Return the flags that this algorithm/adapter pair supports
  *   from the ``I2C_FUNC_*`` flags.
- * @reg_slave: Register given client to I2C slave mode of this adapter
- * @unreg_slave: Unregister given client from I2C slave mode of this adapter
+ * @reg_target: Register given client to local target mode of this adapter
+ * @unreg_target: Unregister given client from local target mode of this adapter
+ *
+ * @master_xfer: deprecated, use @xfer
+ * @master_xfer_atomic: deprecated, use @xfer_atomic
+ * @reg_slave: deprecated, use @reg_target
+ * @unreg_slave: deprecated, use @unreg_target
  *
- * The following structs are for those who like to implement new bus drivers:
  * i2c_algorithm is the interface to a class of hardware solutions which can
  * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584
  * to name two of the most common.
  *
- * The return codes from the ``master_xfer{_atomic}`` fields should indicate the
+ * The return codes from the ``xfer{_atomic}`` fields should indicate the
  * type of error code that occurred during the transfer, as documented in the
  * Kernel Documentation file Documentation/i2c/fault-codes.rst. Otherwise, the
  * number of messages executed should be returned.
  */
 struct i2c_algorithm {
 	/*
-	 * If an adapter algorithm can't do I2C-level access, set master_xfer
+	 * If an adapter algorithm can't do I2C-level access, set xfer
 	 * to NULL. If an adapter algorithm can do SMBus access, set
 	 * smbus_xfer. If set to NULL, the SMBus protocol is simulated
 	 * using common I2C messages.
-	 *
-	 * master_xfer should return the number of messages successfully
-	 * processed, or a negative value on error
 	 */
-	int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs,
-			   int num);
-	int (*master_xfer_atomic)(struct i2c_adapter *adap,
+	union {
+		int (*xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs,
+			    int num);
+		int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs,
+				   int num);
+	};
+	union {
+		int (*xfer_atomic)(struct i2c_adapter *adap,
 				   struct i2c_msg *msgs, int num);
+		int (*master_xfer_atomic)(struct i2c_adapter *adap,
+					   struct i2c_msg *msgs, int num);
+	};
 	int (*smbus_xfer)(struct i2c_adapter *adap, u16 addr,
 			  unsigned short flags, char read_write,
 			  u8 command, int size, union i2c_smbus_data *data);
@@ -570,8 +571,14 @@ struct i2c_algorithm {
 	u32 (*functionality)(struct i2c_adapter *adap);
 
 #if IS_ENABLED(CONFIG_I2C_SLAVE)
-	int (*reg_slave)(struct i2c_client *client);
-	int (*unreg_slave)(struct i2c_client *client);
+	union {
+		int (*reg_target)(struct i2c_client *client);
+		int (*reg_slave)(struct i2c_client *client);
+	};
+	union {
+		int (*unreg_target)(struct i2c_client *client);
+		int (*unreg_slave)(struct i2c_client *client);
+	};
 #endif
 };
 
@@ -753,6 +760,11 @@ struct i2c_adapter {
 
 	struct irq_domain *host_notify_domain;
 	struct regulator *bus_regulator;
+
+	struct dentry *debugfs;
+
+	/* 7bit address space */
+	DECLARE_BITMAP(addrs_in_instantiation, 1 << 7);
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 
@@ -857,8 +869,6 @@ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap)
 
 /* i2c adapter classes (bitmask) */
 #define I2C_CLASS_HWMON		(1<<0)	/* lm_sensors, ... */
-#define I2C_CLASS_DDC		(1<<3)	/* DDC bus on graphics adapters */
-#define I2C_CLASS_SPD		(1<<7)	/* Memory modules */
 /* Warn users that the adapter doesn't support classes anymore */
 #define I2C_CLASS_DEPRECATED	(1<<8)
 
@@ -937,7 +947,22 @@ static inline int i2c_adapter_id(struct i2c_adapter *adap)
 
 static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg)
 {
-	return (msg->addr << 1) | (msg->flags & I2C_M_RD ? 1 : 0);
+	return (msg->addr << 1) | (msg->flags & I2C_M_RD);
+}
+
+/*
+ * 10-bit address
+ *   addr_1: 5'b11110 | addr[9:8] | (R/nW)
+ *   addr_2: addr[7:0]
+ */
+static inline u8 i2c_10bit_addr_hi_from_msg(const struct i2c_msg *msg)
+{
+	return 0xf0 | ((msg->addr & GENMASK(9, 8)) >> 7) | (msg->flags & I2C_M_RD);
+}
+
+static inline u8 i2c_10bit_addr_lo_from_msg(const struct i2c_msg *msg)
+{
+	return msg->addr & GENMASK(7, 0);
 }
 
 u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold);
@@ -967,8 +992,6 @@ int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr);
 #define builtin_i2c_driver(__i2c_driver) \
 	builtin_driver(__i2c_driver, i2c_add_driver)
 
-#endif /* I2C */
-
 /* must call put_device() when done with returned i2c_client device */
 struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode);
 
@@ -978,6 +1001,28 @@ struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode);
 /* must call i2c_put_adapter() when done with returned i2c_adapter device */
 struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode);
 
+#else /* I2C */
+
+static inline struct i2c_client *
+i2c_find_device_by_fwnode(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
+static inline struct i2c_adapter *
+i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
+static inline struct i2c_adapter *
+i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode)
+{
+	return NULL;
+}
+
+#endif /* !I2C */
+
 #if IS_ENABLED(CONFIG_OF)
 /* must call put_device() when done with returned i2c_client device */
 static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
@@ -997,10 +1042,6 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node
 	return i2c_get_adapter_by_fwnode(of_fwnode_handle(node));
 }
 
-const struct of_device_id
-*i2c_of_match_device(const struct of_device_id *matches,
-		     struct i2c_client *client);
-
 int of_i2c_get_board_info(struct device *dev, struct device_node *node,
 			  struct i2c_board_info *info);
 
@@ -1021,13 +1062,6 @@ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node
 	return NULL;
 }
 
-static inline const struct of_device_id
-*i2c_of_match_device(const struct of_device_id *matches,
-		     struct i2c_client *client)
-{
-	return NULL;
-}
-
 static inline int of_i2c_get_board_info(struct device *dev,
 					struct device_node *node,
 					struct i2c_board_info *info)
@@ -1040,7 +1074,7 @@ static inline int of_i2c_get_board_info(struct device *dev,
 struct acpi_resource;
 struct acpi_resource_i2c_serialbus;
 
-#if IS_ENABLED(CONFIG_ACPI)
+#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C)
 bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares,
 			       struct acpi_resource_i2c_serialbus **i2c);
 int i2c_acpi_client_count(struct acpi_device *adev);
diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h
index 90fa83464f00..9fcb6410a584 100644
--- a/include/linux/i3c/device.h
+++ b/include/linux/i3c/device.h
@@ -27,7 +27,7 @@
  * These are the standard error codes as defined by the I3C specification.
  * When -EIO is returned by the i3c_device_do_priv_xfers() or
  * i3c_device_send_hdr_cmds() one can check the error code in
- * &struct_i3c_priv_xfer.err or &struct i3c_hdr_cmd.err to get a better idea of
+ * &struct_i3c_xfer.err or &struct i3c_hdr_cmd.err to get a better idea of
  * what went wrong.
  *
  */
@@ -39,29 +39,39 @@ enum i3c_error_code {
 };
 
 /**
- * enum i3c_hdr_mode - HDR mode ids
+ * enum i3c_xfer_mode - I3C xfer mode ids
  * @I3C_HDR_DDR: DDR mode
  * @I3C_HDR_TSP: TSP mode
  * @I3C_HDR_TSL: TSL mode
+ * @I3C_SDR: SDR mode (NOT HDR mode)
  */
-enum i3c_hdr_mode {
-	I3C_HDR_DDR,
-	I3C_HDR_TSP,
-	I3C_HDR_TSL,
+enum i3c_xfer_mode {
+	/* The below 3 value (I3C_HDR*) must match GETCAP1 Byte bit position */
+	I3C_HDR_DDR = 0,
+	I3C_HDR_TSP = 1,
+	I3C_HDR_TSL = 2,
+	/* Use for default SDR transfer mode */
+	I3C_SDR = 31,
 };
 
 /**
- * struct i3c_priv_xfer - I3C SDR private transfer
+ * struct i3c_xfer - I3C data transfer
  * @rnw: encodes the transfer direction. true for a read, false for a write
+ * @cmd: Read/Write command in HDR mode, read: 0x80 - 0xff, write: 0x00 - 0x7f
  * @len: transfer length in bytes of the transfer
+ * @actual_len: actual length in bytes are transferred by the controller
  * @data: input/output buffer
  * @data.in: input buffer. Must point to a DMA-able buffer
  * @data.out: output buffer. Must point to a DMA-able buffer
  * @err: I3C error code
  */
-struct i3c_priv_xfer {
-	u8 rnw;
+struct i3c_xfer {
+	union {
+		u8 rnw;
+		u8 cmd;
+	};
 	u16 len;
+	u16 actual_len;
 	union {
 		void *in;
 		const void *out;
@@ -69,6 +79,9 @@ struct i3c_priv_xfer {
 	enum i3c_error_code err;
 };
 
+/* keep back compatible */
+#define i3c_priv_xfer i3c_xfer
+
 /**
  * enum i3c_dcr - I3C DCR values
  * @I3C_DCR_GENERIC_DEVICE: generic I3C device
@@ -96,7 +109,7 @@ enum i3c_dcr {
 
 /**
  * struct i3c_device_info - I3C device information
- * @pid: Provisional ID
+ * @pid: Provisioned ID
  * @bcr: Bus Characteristic Register
  * @dcr: Device Characteristic Register
  * @static_addr: static/I2C address
@@ -181,10 +194,7 @@ struct i3c_driver {
 	const struct i3c_device_id *id_table;
 };
 
-static inline struct i3c_driver *drv_to_i3cdrv(struct device_driver *drv)
-{
-	return container_of(drv, struct i3c_driver, driver);
-}
+#define drv_to_i3cdrv(__drv)	container_of_const(__drv, struct i3c_driver, driver)
 
 struct device *i3cdev_to_dev(struct i3c_device *i3cdev);
 
@@ -246,7 +256,7 @@ void i3c_driver_unregister(struct i3c_driver *drv);
  *
  * Return: 0 if both registrations succeeds, a negative error code otherwise.
  */
-static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv,
+static __always_inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv,
 					  struct i2c_driver *i2cdrv)
 {
 	int ret;
@@ -271,7 +281,7 @@ static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv,
  * Note that when CONFIG_I3C is not enabled, this function only unregisters the
  * @i2cdrv.
  */
-static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv,
+static __always_inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv,
 					     struct i2c_driver *i2cdrv)
 {
 	if (IS_ENABLED(CONFIG_I3C))
@@ -284,7 +294,7 @@ static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv,
  * module_i3c_i2c_driver() - Register a module providing an I3C and an I2C
  *			     driver
  * @__i3cdrv: the I3C driver to register
- * @__i2cdrv: the I3C driver to register
+ * @__i2cdrv: the I2C driver to register
  *
  * Provide generic init/exit functions that simply register/unregister an I3C
  * and an I2C driver.
@@ -298,9 +308,15 @@ static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv,
 		      i3c_i2c_driver_unregister,	\
 		      __i2cdrv)
 
-int i3c_device_do_priv_xfers(struct i3c_device *dev,
-			     struct i3c_priv_xfer *xfers,
-			     int nxfers);
+int i3c_device_do_xfers(struct i3c_device *dev, struct i3c_xfer *xfers,
+			int nxfers, enum i3c_xfer_mode mode);
+
+static inline int i3c_device_do_priv_xfers(struct i3c_device *dev,
+					   struct i3c_xfer *xfers,
+					   int nxfers)
+{
+	return i3c_device_do_xfers(dev, xfers, nxfers, I3C_SDR);
+}
 
 int i3c_device_do_setdasa(struct i3c_device *dev);
 
@@ -342,5 +358,6 @@ int i3c_device_request_ibi(struct i3c_device *dev,
 void i3c_device_free_ibi(struct i3c_device *dev);
 int i3c_device_enable_ibi(struct i3c_device *dev);
 int i3c_device_disable_ibi(struct i3c_device *dev);
+u32 i3c_device_get_supported_xfer_mode(struct i3c_device *dev);
 
 #endif /* I3C_DEV_H */
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 0b52da4f2346..2fd850f4678b 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -24,9 +24,16 @@
 
 struct i2c_client;
 
+/* notifier actions. notifier call data is the struct i3c_bus */
+enum {
+	I3C_NOTIFY_BUS_ADD,
+	I3C_NOTIFY_BUS_REMOVE,
+};
+
 struct i3c_master_controller;
 struct i3c_bus;
 struct i3c_device;
+extern const struct bus_type i3c_bus_type;
 
 /**
  * struct i3c_i2c_dev_desc - Common part of the I3C/I2C device descriptor
@@ -70,7 +77,6 @@ struct i2c_dev_boardinfo {
 /**
  * struct i2c_dev_desc - I2C device descriptor
  * @common: common part of the I2C device descriptor
- * @boardinfo: pointer to the boardinfo attached to this I2C device
  * @dev: I2C device object registered to the I2C framework
  * @addr: I2C device address
  * @lvr: LVR (Legacy Virtual Register) needed by the I3C core to know about
@@ -129,6 +135,7 @@ struct i3c_ibi_slot {
  *		     rejected by the master
  * @num_slots: number of IBI slots reserved for this device
  * @enabled: reflect the IBI status
+ * @wq: workqueue used to execute IBI handlers.
  * @handler: IBI handler specified at i3c_device_request_ibi() call time. This
  *	     handler will be called from the controller workqueue, and as such
  *	     is allowed to sleep (though it is recommended to process the IBI
@@ -151,6 +158,7 @@ struct i3c_device_ibi_info {
 	unsigned int max_payload_len;
 	unsigned int num_slots;
 	unsigned int enabled;
+	struct workqueue_struct *wq;
 	void (*handler)(struct i3c_device *dev,
 			const struct i3c_ibi_payload *payload);
 };
@@ -166,7 +174,7 @@ struct i3c_device_ibi_info {
  *		 assigned a dynamic address by the master. Will be used during
  *		 bus initialization to assign it a specific dynamic address
  *		 before starting DAA (Dynamic Address Assignment)
- * @pid: I3C Provisional ID exposed by the device. This is a unique identifier
+ * @pid: I3C Provisioned ID exposed by the device. This is a unique identifier
  *	 that may be used to attach boardinfo to i3c_dev_desc when the device
  *	 does not have a static address
  * @of_node: optional DT node in case the device has been described in the DT
@@ -241,10 +249,15 @@ struct i3c_device {
  */
 #define I3C_BUS_MAX_DEVS		11
 
-#define I3C_BUS_MAX_I3C_SCL_RATE	12900000
-#define I3C_BUS_TYP_I3C_SCL_RATE	12500000
-#define I3C_BUS_I2C_FM_PLUS_SCL_RATE	1000000
-#define I3C_BUS_I2C_FM_SCL_RATE		400000
+/* Taken from the I3C Spec V1.1.1, chapter 6.2. "Timing specification" */
+#define I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE	1000000
+#define I3C_BUS_I2C_FM_SCL_MAX_RATE		400000
+#define I3C_BUS_I3C_SCL_MAX_RATE	12900000
+#define I3C_BUS_I3C_SCL_TYP_RATE	12500000
+#define I3C_BUS_TAVAL_MIN_NS		1000
+#define I3C_BUS_TBUF_MIXED_FM_MIN_NS	1300
+#define I3C_BUS_THIGH_MIXED_MAX_NS	41
+#define I3C_BUS_TIDLE_MIN_NS		200000
 #define I3C_BUS_TLOW_OD_MIN_NS		200
 
 /**
@@ -270,13 +283,29 @@ enum i3c_bus_mode {
 };
 
 /**
+ * enum i3c_open_drain_speed - I3C open-drain speed
+ * @I3C_OPEN_DRAIN_SLOW_SPEED: Slow open-drain speed for sending the first
+ *				broadcast address. The first broadcast address at this speed
+ *				will be visible to all devices on the I3C bus. I3C devices
+ *				working in I2C mode will turn off their spike filter when
+ *				switching into I3C mode.
+ * @I3C_OPEN_DRAIN_NORMAL_SPEED: Normal open-drain speed in I3C bus mode.
+ */
+enum i3c_open_drain_speed {
+	I3C_OPEN_DRAIN_SLOW_SPEED,
+	I3C_OPEN_DRAIN_NORMAL_SPEED,
+};
+
+/**
  * enum i3c_addr_slot_status - I3C address slot status
  * @I3C_ADDR_SLOT_FREE: address is free
  * @I3C_ADDR_SLOT_RSVD: address is reserved
  * @I3C_ADDR_SLOT_I2C_DEV: address is assigned to an I2C device
  * @I3C_ADDR_SLOT_I3C_DEV: address is assigned to an I3C device
  * @I3C_ADDR_SLOT_STATUS_MASK: address slot mask
- *
+ * @I3C_ADDR_SLOT_EXT_STATUS_MASK: address slot mask with extended information
+ * @I3C_ADDR_SLOT_EXT_DESIRED: the bitmask represents addresses that are preferred by some devices,
+ *			       such as the "assigned-address" property in a device tree source.
  * On an I3C bus, addresses are assigned dynamically, and we need to know which
  * addresses are free to use and which ones are already assigned.
  *
@@ -289,8 +318,12 @@ enum i3c_addr_slot_status {
 	I3C_ADDR_SLOT_I2C_DEV,
 	I3C_ADDR_SLOT_I3C_DEV,
 	I3C_ADDR_SLOT_STATUS_MASK = 3,
+	I3C_ADDR_SLOT_EXT_STATUS_MASK = 7,
+	I3C_ADDR_SLOT_EXT_DESIRED = BIT(2),
 };
 
+#define I3C_ADDR_SLOT_STATUS_BITS 4
+
 /**
  * struct i3c_bus - I3C bus object
  * @cur_master: I3C master currently driving the bus. Since I3C is multi-master
@@ -332,7 +365,7 @@ enum i3c_addr_slot_status {
 struct i3c_bus {
 	struct i3c_dev_desc *cur_master;
 	int id;
-	unsigned long addrslots[((I2C_MAX_ADDR + 1) * 2) / BITS_PER_LONG];
+	unsigned long addrslots[((I2C_MAX_ADDR + 1) * I3C_ADDR_SLOT_STATUS_BITS) / BITS_PER_LONG];
 	enum i3c_bus_mode mode;
 	struct {
 		unsigned long i3c;
@@ -385,7 +418,11 @@ struct i3c_bus {
  * @send_ccc_cmd: send a CCC command
  *		  This method is mandatory.
  * @priv_xfers: do one or several private I3C SDR transfers
- *		This method is mandatory.
+ *		This method is mandatory when i3c_xfers is not implemented. It
+ *		is deprecated.
+ * @i3c_xfers: do one or several I3C SDR or HDR transfers
+ *	       This method is mandatory when priv_xfers is not implemented but
+ *	       should be implemented instead of priv_xfers.
  * @attach_i2c_dev: called every time an I2C device is attached to the bus.
  *		    This is a good place to attach master controller specific
  *		    data to I2C devices.
@@ -426,6 +463,9 @@ struct i3c_bus {
  *		      for a future IBI
  *		      This method is mandatory only if ->request_ibi is not
  *		      NULL.
+ * @enable_hotjoin: enable hot join event detect.
+ * @disable_hotjoin: disable hot join event detect.
+ * @set_speed: adjust I3C open drain mode timing.
  */
 struct i3c_master_controller_ops {
 	int (*bus_init)(struct i3c_master_controller *master);
@@ -438,13 +478,17 @@ struct i3c_master_controller_ops {
 				 const struct i3c_ccc_cmd *cmd);
 	int (*send_ccc_cmd)(struct i3c_master_controller *master,
 			    struct i3c_ccc_cmd *cmd);
+	/* Deprecated, please use i3c_xfers() */
 	int (*priv_xfers)(struct i3c_dev_desc *dev,
 			  struct i3c_priv_xfer *xfers,
 			  int nxfers);
+	int (*i3c_xfers)(struct i3c_dev_desc *dev,
+			 struct i3c_xfer *xfers,
+			 int nxfers, enum i3c_xfer_mode mode);
 	int (*attach_i2c_dev)(struct i2c_dev_desc *dev);
 	void (*detach_i2c_dev)(struct i2c_dev_desc *dev);
 	int (*i2c_xfers)(struct i2c_dev_desc *dev,
-			 const struct i2c_msg *xfers, int nxfers);
+			 struct i2c_msg *xfers, int nxfers);
 	int (*request_ibi)(struct i3c_dev_desc *dev,
 			   const struct i3c_ibi_setup *req);
 	void (*free_ibi)(struct i3c_dev_desc *dev);
@@ -452,6 +496,9 @@ struct i3c_master_controller_ops {
 	int (*disable_ibi)(struct i3c_dev_desc *dev);
 	void (*recycle_ibi_slot)(struct i3c_dev_desc *dev,
 				 struct i3c_ibi_slot *slot);
+	int (*enable_hotjoin)(struct i3c_master_controller *master);
+	int (*disable_hotjoin)(struct i3c_master_controller *master);
+	int (*set_speed)(struct i3c_master_controller *master, enum i3c_open_drain_speed speed);
 };
 
 /**
@@ -465,11 +512,12 @@ struct i3c_master_controller_ops {
  * @ops: master operations. See &struct i3c_master_controller_ops
  * @secondary: true if the master is a secondary master
  * @init_done: true when the bus initialization is done
+ * @hotjoin: true if the master support hotjoin
  * @boardinfo.i3c: list of I3C  boardinfo objects
  * @boardinfo.i2c: list of I2C boardinfo objects
  * @boardinfo: board-level information attached to devices connected on the bus
  * @bus: I3C bus exposed by this master
- * @wq: workqueue used to execute IBI handlers. Can also be used by master
+ * @wq: workqueue which can be used by master
  *	drivers if they need to postpone operations that need to take place
  *	in a thread context. Typical examples are Hot Join processing which
  *	requires taking the bus lock in maintenance, which in turn, can only
@@ -487,6 +535,7 @@ struct i3c_master_controller {
 	const struct i3c_master_controller_ops *ops;
 	unsigned int secondary : 1;
 	unsigned int init_done : 1;
+	unsigned int hotjoin: 1;
 	struct {
 		struct list_head i3c;
 		struct list_head i2c;
@@ -517,6 +566,26 @@ struct i3c_master_controller {
 #define i3c_bus_for_each_i3cdev(bus, dev)				\
 	list_for_each_entry(dev, &(bus)->devs.i3c, common.node)
 
+/**
+ * struct i3c_dma - DMA transfer and mapping descriptor
+ * @dev: device object of a device doing DMA
+ * @buf: destination/source buffer for DMA
+ * @len: length of transfer
+ * @map_len: length of DMA mapping
+ * @addr: mapped DMA address for a Host Controller Driver
+ * @dir: DMA direction
+ * @bounce_buf: an allocated bounce buffer if transfer needs it or NULL
+ */
+struct i3c_dma {
+	struct device *dev;
+	void *buf;
+	size_t len;
+	size_t map_len;
+	dma_addr_t addr;
+	enum dma_data_direction dir;
+	void *bounce_buf;
+};
+
 int i3c_master_do_i2c_xfers(struct i3c_master_controller *master,
 			    const struct i2c_msg *xfers,
 			    int nxfers);
@@ -534,6 +603,12 @@ int i3c_master_get_free_addr(struct i3c_master_controller *master,
 int i3c_master_add_i3c_dev_locked(struct i3c_master_controller *master,
 				  u8 addr);
 int i3c_master_do_daa(struct i3c_master_controller *master);
+struct i3c_dma *i3c_master_dma_map_single(struct device *dev, void *ptr,
+					  size_t len, bool force_bounce,
+					  enum dma_data_direction dir);
+void i3c_master_dma_unmap_single(struct i3c_dma *dma_xfer);
+DEFINE_FREE(i3c_master_dma_unmap_single, void *,
+	    if (_T) i3c_master_dma_unmap_single(_T))
 
 int i3c_master_set_info(struct i3c_master_controller *master,
 			const struct i3c_device_info *info);
@@ -543,6 +618,8 @@ int i3c_master_register(struct i3c_master_controller *master,
 			const struct i3c_master_controller_ops *ops,
 			bool secondary);
 void i3c_master_unregister(struct i3c_master_controller *master);
+int i3c_master_enable_hotjoin(struct i3c_master_controller *master);
+int i3c_master_disable_hotjoin(struct i3c_master_controller *master);
 
 /**
  * i3c_dev_get_master_data() - get master private data attached to an I3C
@@ -652,4 +729,9 @@ void i3c_master_queue_ibi(struct i3c_dev_desc *dev, struct i3c_ibi_slot *slot);
 
 struct i3c_ibi_slot *i3c_master_get_free_ibi_slot(struct i3c_dev_desc *dev);
 
+void i3c_for_each_bus_locked(int (*fn)(struct i3c_bus *bus, void *data),
+			     void *data);
+int i3c_register_notifier(struct notifier_block *nb);
+int i3c_unregister_notifier(struct notifier_block *nb);
+
 #endif /* I3C_MASTER_H */
diff --git a/include/linux/i8042.h b/include/linux/i8042.h
index 0261e2fb3636..00037c13abc8 100644
--- a/include/linux/i8042.h
+++ b/include/linux/i8042.h
@@ -3,6 +3,7 @@
 #define _LINUX_I8042_H
 
 
+#include <linux/errno.h>
 #include <linux/types.h>
 
 /*
@@ -53,15 +54,29 @@
 
 struct serio;
 
+/**
+ * typedef i8042_filter_t - i8042 filter callback
+ * @data: Data received by the i8042 controller
+ * @str: Status register of the i8042 controller
+ * @serio: Serio of the i8042 controller
+ * @context: Context pointer associated with this callback
+ *
+ * This represents a i8042 filter callback which can be used with i8042_install_filter()
+ * and i8042_remove_filter() to filter the i8042 input for platform-specific key codes.
+ *
+ * Context: Interrupt context.
+ * Returns: true if the data should be filtered out, false if otherwise.
+ */
+typedef bool (*i8042_filter_t)(unsigned char data, unsigned char str, struct serio *serio,
+			       void *context);
+
 #if defined(CONFIG_SERIO_I8042) || defined(CONFIG_SERIO_I8042_MODULE)
 
 void i8042_lock_chip(void);
 void i8042_unlock_chip(void);
 int i8042_command(unsigned char *param, int command);
-int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
-					struct serio *serio));
-int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str,
-				       struct serio *serio));
+int i8042_install_filter(i8042_filter_t filter, void *context);
+int i8042_remove_filter(i8042_filter_t filter);
 
 #else
 
@@ -78,14 +93,12 @@ static inline int i8042_command(unsigned char *param, int command)
 	return -ENODEV;
 }
 
-static inline int i8042_install_filter(bool (*filter)(unsigned char data, unsigned char str,
-					struct serio *serio))
+static inline int i8042_install_filter(i8042_filter_t filter, void *context)
 {
 	return -ENODEV;
 }
 
-static inline int i8042_remove_filter(bool (*filter)(unsigned char data, unsigned char str,
-				       struct serio *serio))
+static inline int i8042_remove_filter(i8042_filter_t filter)
 {
 	return -ENODEV;
 }
diff --git a/include/linux/i8253.h b/include/linux/i8253.h
index 8336b2f6f834..56c280eb2d4f 100644
--- a/include/linux/i8253.h
+++ b/include/linux/i8253.h
@@ -21,9 +21,9 @@
 #define PIT_LATCH	((PIT_TICK_RATE + HZ/2) / HZ)
 
 extern raw_spinlock_t i8253_lock;
-extern bool i8253_clear_counter_on_shutdown;
 extern struct clock_event_device i8253_clockevent;
 extern void clockevent_i8253_init(bool oneshot);
+extern void clockevent_i8253_disable(void);
 
 extern void setup_pit_timer(void);
 
diff --git a/include/linux/i8254.h b/include/linux/i8254.h
new file mode 100644
index 000000000000..a675c309232b
--- /dev/null
+++ b/include/linux/i8254.h
@@ -0,0 +1,21 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) William Breathitt Gray */
+#ifndef _I8254_H_
+#define _I8254_H_
+
+struct device;
+struct regmap;
+
+/**
+ * struct i8254_regmap_config - Configuration for the register map of an i8254
+ * @parent:	parent device
+ * @map:	regmap for the i8254
+ */
+struct i8254_regmap_config {
+	struct device *parent;
+	struct regmap *map;
+};
+
+int devm_i8254_regmap_register(struct device *dev, const struct i8254_regmap_config *config);
+
+#endif /* _I8254_H_ */
diff --git a/include/linux/icmp.h b/include/linux/icmp.h
index 0af4d210ee31..043ec5d9c882 100644
--- a/include/linux/icmp.h
+++ b/include/linux/icmp.h
@@ -40,4 +40,36 @@ void ip_icmp_error_rfc4884(const struct sk_buff *skb,
 			   struct sock_ee_data_rfc4884 *out,
 			   int thlen, int off);
 
+/* RFC 4884 */
+#define ICMP_EXT_ORIG_DGRAM_MIN_LEN	128
+#define ICMP_EXT_VERSION_2		2
+
+/* ICMP Extension Object Classes */
+#define ICMP_EXT_OBJ_CLASS_IIO		2	/* RFC 5837 */
+
+/* Interface Information Object - RFC 5837 */
+enum {
+	ICMP_EXT_CTYPE_IIO_ROLE_IIF,
+};
+
+#define ICMP_EXT_CTYPE_IIO_ROLE(ROLE)	((ROLE) << 6)
+#define ICMP_EXT_CTYPE_IIO_MTU		BIT(0)
+#define ICMP_EXT_CTYPE_IIO_NAME		BIT(1)
+#define ICMP_EXT_CTYPE_IIO_IPADDR	BIT(2)
+#define ICMP_EXT_CTYPE_IIO_IFINDEX	BIT(3)
+
+struct icmp_ext_iio_name_subobj {
+	u8 len;
+	char name[IFNAMSIZ];
+};
+
+enum {
+	/* RFC 5837 - Incoming IP Interface Role */
+	ICMP_ERR_EXT_IIO_IIF,
+	/* Add new constants above. Used by "icmp_errors_extension_mask"
+	 * sysctl.
+	 */
+	ICMP_ERR_EXT_COUNT,
+};
+
 #endif	/* _LINUX_ICMP_H */
diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h
index db0f4fcfdaf4..e3b3b0fa2a8f 100644
--- a/include/linux/icmpv6.h
+++ b/include/linux/icmpv6.h
@@ -85,12 +85,10 @@ extern void				icmpv6_param_prob_reason(struct sk_buff *skb,
 
 struct flowi6;
 struct in6_addr;
-extern void				icmpv6_flow_init(struct sock *sk,
-							 struct flowi6 *fl6,
-							 u8 type,
-							 const struct in6_addr *saddr,
-							 const struct in6_addr *daddr,
-							 int oif);
+
+void icmpv6_flow_init(const struct sock *sk, struct flowi6 *fl6, u8 type,
+		      const struct in6_addr *saddr,
+		      const struct in6_addr *daddr, int oif);
 
 static inline void icmpv6_param_prob(struct sk_buff *skb, u8 code, int pos)
 {
diff --git a/include/linux/idr.h b/include/linux/idr.h
index a0dce14090a9..789e23e67444 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -15,6 +15,7 @@
 #include <linux/radix-tree.h>
 #include <linux/gfp.h>
 #include <linux/percpu.h>
+#include <linux/cleanup.h>
 
 struct idr {
 	struct radix_tree_root	idr_rt;
@@ -124,6 +125,22 @@ void *idr_get_next_ul(struct idr *, unsigned long *nextid);
 void *idr_replace(struct idr *, void *, unsigned long id);
 void idr_destroy(struct idr *);
 
+struct __class_idr {
+	struct idr *idr;
+	int id;
+};
+
+#define idr_null ((struct __class_idr){ NULL, -1 })
+#define take_idr_id(id) __get_and_null(id, idr_null)
+
+DEFINE_CLASS(idr_alloc, struct __class_idr,
+	     if (_T.id >= 0) idr_remove(_T.idr, _T.id),
+	     ((struct __class_idr){
+	     	.idr = idr,
+		.id = idr_alloc(idr, ptr, start, end, gfp),
+	     }),
+	     struct idr *idr, void *ptr, int start, int end, gfp_t gfp);
+
 /**
  * idr_init_base() - Initialise an IDR.
  * @idr: IDR handle.
@@ -200,7 +217,7 @@ static inline void idr_preload_end(void)
  */
 #define idr_for_each_entry_ul(idr, entry, tmp, id)			\
 	for (tmp = 0, id = 0;						\
-	     tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \
+	     ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \
 	     tmp = id, ++id)
 
 /**
@@ -224,10 +241,12 @@ static inline void idr_preload_end(void)
  * @id: Entry ID.
  *
  * Continue to iterate over entries, continuing after the current position.
+ * After normal termination @entry is left with the value NULL.  This
+ * is convenient for a "not found" value.
  */
 #define idr_for_each_entry_continue_ul(idr, entry, tmp, id)		\
 	for (tmp = id;							\
-	     tmp <= id && ((entry) = idr_get_next_ul(idr, &(id))) != NULL; \
+	     ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \
 	     tmp = id, ++id)
 
 /*
@@ -255,6 +274,7 @@ struct ida {
 int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t);
 void ida_free(struct ida *, unsigned int id);
 void ida_destroy(struct ida *ida);
+int ida_find_first_range(struct ida *ida, unsigned int min, unsigned int max);
 
 /**
  * ida_alloc() - Allocate an unused ID.
@@ -314,16 +334,18 @@ static inline void ida_init(struct ida *ida)
 	xa_init_flags(&ida->xa, IDA_INIT_FLAGS);
 }
 
-/*
- * ida_simple_get() and ida_simple_remove() are deprecated. Use
- * ida_alloc() and ida_free() instead respectively.
- */
-#define ida_simple_get(ida, start, end, gfp)	\
-			ida_alloc_range(ida, start, (end) - 1, gfp)
-#define ida_simple_remove(ida, id)	ida_free(ida, id)
-
 static inline bool ida_is_empty(const struct ida *ida)
 {
 	return xa_empty(&ida->xa);
 }
+
+static inline bool ida_exists(struct ida *ida, unsigned int id)
+{
+	return ida_find_first_range(ida, id, id) == id;
+}
+
+static inline int ida_find_first(struct ida *ida)
+{
+	return ida_find_first_range(ida, 0, ~0);
+}
 #endif /* __IDR_H__ */
diff --git a/include/linux/ieee80211-eht.h b/include/linux/ieee80211-eht.h
new file mode 100644
index 000000000000..f9782e46c5e5
--- /dev/null
+++ b/include/linux/ieee80211-eht.h
@@ -0,0 +1,1182 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IEEE 802.11 EHT definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_EHT_H
+#define LINUX_IEEE80211_EHT_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+/* need HE definitions for the inlines here */
+#include <linux/ieee80211-he.h>
+
+#define IEEE80211_TTLM_MAX_CNT				2
+#define IEEE80211_TTLM_CONTROL_DIRECTION		0x03
+#define IEEE80211_TTLM_CONTROL_DEF_LINK_MAP		0x04
+#define IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT	0x08
+#define IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT	0x10
+#define IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE		0x20
+
+#define IEEE80211_TTLM_DIRECTION_DOWN		0
+#define IEEE80211_TTLM_DIRECTION_UP		1
+#define IEEE80211_TTLM_DIRECTION_BOTH		2
+
+/**
+ * struct ieee80211_ttlm_elem - TID-To-Link Mapping element
+ *
+ * Defined in section 9.4.2.314 in P802.11be_D4
+ *
+ * @control: the first part of control field
+ * @optional: the second part of control field
+ */
+struct ieee80211_ttlm_elem {
+	u8 control;
+	u8 optional[];
+} __packed;
+
+#define IEEE80211_EHT_MCS_NSS_RX 0x0f
+#define IEEE80211_EHT_MCS_NSS_TX 0xf0
+
+/**
+ * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max
+ * supported NSS for per MCS.
+ *
+ * For each field below, bits 0 - 3 indicate the maximal number of spatial
+ * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams
+ * for Tx.
+ *
+ * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 0 - 7.
+ * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 8 - 9.
+ * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 10 - 11.
+ * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 12 - 13.
+ * @rx_tx_max_nss: array of the previous fields for easier loop access
+ */
+struct ieee80211_eht_mcs_nss_supp_20mhz_only {
+	union {
+		struct {
+			u8 rx_tx_mcs7_max_nss;
+			u8 rx_tx_mcs9_max_nss;
+			u8 rx_tx_mcs11_max_nss;
+			u8 rx_tx_mcs13_max_nss;
+		};
+		u8 rx_tx_max_nss[4];
+	};
+};
+
+/**
+ * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except
+ * 20MHz only stations).
+ *
+ * For each field below, bits 0 - 3 indicate the maximal number of spatial
+ * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams
+ * for Tx.
+ *
+ * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 0 - 9.
+ * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 10 - 11.
+ * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams
+ *     supported for reception and the maximum number of spatial streams
+ *     supported for transmission for MCS 12 - 13.
+ * @rx_tx_max_nss: array of the previous fields for easier loop access
+ */
+struct ieee80211_eht_mcs_nss_supp_bw {
+	union {
+		struct {
+			u8 rx_tx_mcs9_max_nss;
+			u8 rx_tx_mcs11_max_nss;
+			u8 rx_tx_mcs13_max_nss;
+		};
+		u8 rx_tx_max_nss[3];
+	};
+};
+
+/**
+ * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data
+ *
+ * This structure is the "EHT Capabilities element" fixed fields as
+ * described in P802.11be_D2.0 section 9.4.2.313.
+ *
+ * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP*
+ * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP*
+ */
+struct ieee80211_eht_cap_elem_fixed {
+	u8 mac_cap_info[2];
+	u8 phy_cap_info[9];
+} __packed;
+
+/**
+ * struct ieee80211_eht_cap_elem - EHT capabilities element
+ * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed
+ * @optional: optional parts
+ */
+struct ieee80211_eht_cap_elem {
+	struct ieee80211_eht_cap_elem_fixed fixed;
+
+	/*
+	 * Followed by:
+	 * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets.
+	 * EHT PPE Thresholds field: variable length.
+	 */
+	u8 optional[];
+} __packed;
+
+#define IEEE80211_EHT_OPER_INFO_PRESENT	                        0x01
+#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT	0x02
+#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION	                0x04
+#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT         0x08
+#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK      0x30
+#define IEEE80211_EHT_OPER_MCS15_DISABLE                        0x40
+
+/**
+ * struct ieee80211_eht_operation - eht operation element
+ *
+ * This structure is the "EHT Operation Element" fields as
+ * described in P802.11be_D2.0 section 9.4.2.311
+ *
+ * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_*
+ * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in
+ *     EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and
+ *     receive.
+ * @optional: optional parts
+ */
+struct ieee80211_eht_operation {
+	u8 params;
+	struct ieee80211_eht_mcs_nss_supp_20mhz_only basic_mcs_nss;
+	u8 optional[];
+} __packed;
+
+/**
+ * struct ieee80211_eht_operation_info - eht operation information
+ *
+ * @control: EHT operation information control.
+ * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz
+ *     EHT BSS.
+ * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS.
+ * @optional: optional parts
+ */
+struct ieee80211_eht_operation_info {
+	u8 control;
+	u8 ccfs0;
+	u8 ccfs1;
+	u8 optional[];
+} __packed;
+
+/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */
+#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS			0x01
+#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL			0x02
+#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1		0x04
+#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2		0x08
+#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT			0x10
+#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC			0x20
+#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK		0xc0
+#define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895	        0
+#define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991	        1
+#define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454	        2
+
+#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK		0x01
+#define IEEE80211_EHT_MAC_CAP1_EHT_TRS				0x02
+#define IEEE80211_EHT_MAC_CAP1_TXOP_RET				0x04
+#define IEEE80211_EHT_MAC_CAP1_TWO_BQRS				0x08
+#define IEEE80211_EHT_MAC_CAP1_EHT_LINK_ADAPT_MASK		0x30
+#define IEEE80211_EHT_MAC_CAP1_UNSOL_EPCS_PRIO_ACCESS		0x40
+
+/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */
+#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ			0x02
+#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ		0x04
+#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI		0x08
+#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO		0x10
+#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER			0x20
+#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE			0x40
+
+/* EHT beamformee number of spatial streams <= 80MHz is split */
+#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK		0x80
+#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK		0x03
+
+#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK	0x1c
+#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK	0xe0
+
+#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK		0x07
+#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK		0x38
+
+/* EHT number of sounding dimensions for 320MHz is split */
+#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK		0xc0
+#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK		0x01
+#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK		0x02
+#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK		0x04
+#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK		0x08
+#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK		0x10
+#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK			0x20
+#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK		0x40
+#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK			0x80
+
+#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO		0x01
+#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP			0x02
+#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP		0x04
+#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI	0x08
+#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK			0xf0
+
+#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK		0x01
+#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP		0x02
+#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP		0x04
+#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT		0x08
+#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK	0x30
+#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US	0
+#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US	1
+#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US	2
+#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US	3
+
+/* Maximum number of supported EHT LTF is split */
+#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK	0xc0
+#define IEEE80211_EHT_PHY_CAP5_SUPP_EXTRA_EHT_LTF		0x40
+#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK	0x07
+
+#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_80MHZ			0x08
+#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_160MHZ		0x30
+#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_320MHZ		0x40
+#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK			0x78
+#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP		0x80
+
+#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW	0x01
+#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ	0x02
+#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ	0x04
+#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ	0x08
+#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ		0x10
+#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ		0x20
+#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ		0x40
+#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT	0x80
+
+#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA	0x01
+#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA	0x02
+
+/*
+ * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311
+ */
+#define IEEE80211_EHT_OPER_CHAN_WIDTH		0x7
+#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ	0
+#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ	1
+#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ	2
+#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ	3
+#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ	4
+
+/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */
+static inline u8
+ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap,
+			   const struct ieee80211_eht_cap_elem_fixed *eht_cap,
+			   bool from_ap)
+{
+	u8 count = 0;
+
+	/* on 2.4 GHz, if it supports 40 MHz, the result is 3 */
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G)
+		return 3;
+
+	/* on 2.4 GHz, these three bits are reserved, so should be 0 */
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G)
+		count += 3;
+
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
+		count += 3;
+
+	if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ)
+		count += 3;
+
+	if (count)
+		return count;
+
+	return from_ap ? 3 : 4;
+}
+
+/* 802.11be EHT PPE Thresholds */
+#define IEEE80211_EHT_PPE_THRES_NSS_POS			0
+#define IEEE80211_EHT_PPE_THRES_NSS_MASK		0xf
+#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK	0x1f0
+#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE		3
+#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE	9
+
+/*
+ * Calculate 802.11be EHT capabilities IE EHT field size
+ */
+static inline u8
+ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info)
+{
+	u32 n;
+
+	if (!(phy_cap_info[5] &
+	      IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT))
+		return 0;
+
+	n = hweight16(ppe_thres_hdr &
+		      IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
+	n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK);
+
+	/*
+	 * Each pair is 6 bits, and we need to add the 9 "header" bits to the
+	 * total size.
+	 */
+	n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 +
+	    IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE;
+	return DIV_ROUND_UP(n, 8);
+}
+
+static inline bool
+ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len,
+			   bool from_ap)
+{
+	const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data;
+	u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed);
+
+	if (len < needed || !he_capa)
+		return false;
+
+	needed += ieee80211_eht_mcs_nss_size((const void *)he_capa,
+					     (const void *)data,
+					     from_ap);
+	if (len < needed)
+		return false;
+
+	if (elem->phy_cap_info[5] &
+			IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) {
+		u16 ppe_thres_hdr;
+
+		if (len < needed + sizeof(ppe_thres_hdr))
+			return false;
+
+		ppe_thres_hdr = get_unaligned_le16(data + needed);
+		needed += ieee80211_eht_ppe_size(ppe_thres_hdr,
+						 elem->phy_cap_info);
+	}
+
+	return len >= needed;
+}
+
+static inline bool
+ieee80211_eht_oper_size_ok(const u8 *data, u8 len)
+{
+	const struct ieee80211_eht_operation *elem = (const void *)data;
+	u8 needed = sizeof(*elem);
+
+	if (len < needed)
+		return false;
+
+	if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) {
+		needed += 3;
+
+		if (elem->params &
+		    IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)
+			needed += 2;
+	}
+
+	return len >= needed;
+}
+
+/* must validate ieee80211_eht_oper_size_ok() first */
+static inline u16
+ieee80211_eht_oper_dis_subchan_bitmap(const struct ieee80211_eht_operation *eht_oper)
+{
+	const struct ieee80211_eht_operation_info *info =
+		(const void *)eht_oper->optional;
+
+	if (!(eht_oper->params & IEEE80211_EHT_OPER_INFO_PRESENT))
+		return 0;
+
+	if (!(eht_oper->params & IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT))
+		return 0;
+
+	return get_unaligned_le16(info->optional);
+}
+
+#define IEEE80211_BW_IND_DIS_SUBCH_PRESENT	BIT(1)
+
+struct ieee80211_bandwidth_indication {
+	u8 params;
+	struct ieee80211_eht_operation_info info;
+} __packed;
+
+static inline bool
+ieee80211_bandwidth_indication_size_ok(const u8 *data, u8 len)
+{
+	const struct ieee80211_bandwidth_indication *bwi = (const void *)data;
+
+	if (len < sizeof(*bwi))
+		return false;
+
+	if (bwi->params & IEEE80211_BW_IND_DIS_SUBCH_PRESENT &&
+	    len < sizeof(*bwi) + 2)
+		return false;
+
+	return true;
+}
+
+/* Protected EHT action codes */
+enum ieee80211_protected_eht_actioncode {
+	WLAN_PROTECTED_EHT_ACTION_TTLM_REQ = 0,
+	WLAN_PROTECTED_EHT_ACTION_TTLM_RES = 1,
+	WLAN_PROTECTED_EHT_ACTION_TTLM_TEARDOWN = 2,
+	WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_REQ = 3,
+	WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_RESP = 4,
+	WLAN_PROTECTED_EHT_ACTION_EPCS_ENABLE_TEARDOWN = 5,
+	WLAN_PROTECTED_EHT_ACTION_EML_OP_MODE_NOTIF = 6,
+	WLAN_PROTECTED_EHT_ACTION_LINK_RECOMMEND = 7,
+	WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_REQ = 8,
+	WLAN_PROTECTED_EHT_ACTION_ML_OP_UPDATE_RESP = 9,
+	WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_NOTIF = 10,
+	WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_REQ = 11,
+	WLAN_PROTECTED_EHT_ACTION_LINK_RECONFIG_RESP = 12,
+};
+
+/* multi-link device */
+#define IEEE80211_MLD_MAX_NUM_LINKS	15
+
+#define IEEE80211_ML_CONTROL_TYPE			0x0007
+#define IEEE80211_ML_CONTROL_TYPE_BASIC			0
+#define IEEE80211_ML_CONTROL_TYPE_PREQ			1
+#define IEEE80211_ML_CONTROL_TYPE_RECONF		2
+#define IEEE80211_ML_CONTROL_TYPE_TDLS			3
+#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS		4
+#define IEEE80211_ML_CONTROL_PRESENCE_MASK		0xfff0
+
+struct ieee80211_multi_link_elem {
+	__le16 control;
+	u8 variable[];
+} __packed;
+
+#define IEEE80211_MLC_BASIC_PRES_LINK_ID		0x0010
+#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT	0x0020
+#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY		0x0040
+#define IEEE80211_MLC_BASIC_PRES_EML_CAPA		0x0080
+#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP		0x0100
+#define IEEE80211_MLC_BASIC_PRES_MLD_ID			0x0200
+#define IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP	0x0400
+
+#define IEEE80211_MED_SYNC_DELAY_DURATION		0x00ff
+#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH	0x0f00
+#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS	0xf000
+
+/*
+ * Described in P802.11be_D3.0
+ * dot11MSDTimerDuration should default to 5484 (i.e. 171.375)
+ * dot11MSDOFDMEDthreshold defaults to -72 (i.e. 0)
+ * dot11MSDTXOPMAX defaults to 1
+ */
+#define IEEE80211_MED_SYNC_DELAY_DEFAULT		0x10ac
+
+#define IEEE80211_EML_CAP_EMLSR_SUPP			0x0001
+#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY		0x000e
+#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US		0
+#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US		1
+#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US		2
+#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US		3
+#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US		4
+#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY	0x0070
+#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US		0
+#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US		1
+#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US		2
+#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US		3
+#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US		4
+#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US		5
+#define IEEE80211_EML_CAP_EMLMR_SUPPORT			0x0080
+#define IEEE80211_EML_CAP_EMLMR_DELAY			0x0700
+#define  IEEE80211_EML_CAP_EMLMR_DELAY_0US			0
+#define  IEEE80211_EML_CAP_EMLMR_DELAY_32US			1
+#define  IEEE80211_EML_CAP_EMLMR_DELAY_64US			2
+#define  IEEE80211_EML_CAP_EMLMR_DELAY_128US			3
+#define  IEEE80211_EML_CAP_EMLMR_DELAY_256US			4
+#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT		0x7800
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0			0
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US		1
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US		2
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US		3
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU		4
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU		5
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU		6
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU		7
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU		8
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU		9
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU		10
+#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU		11
+
+#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS		0x000f
+#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT		0x0010
+#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP	0x0060
+#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_NO_SUPP	0
+#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_SAME	1
+#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_RESERVED	2
+#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP_DIFF	3
+#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND		0x0f80
+#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT		0x1000
+#define IEEE80211_MLD_CAP_OP_LINK_RECONF_SUPPORT	0x2000
+#define IEEE80211_MLD_CAP_OP_ALIGNED_TWT_SUPPORT	0x4000
+
+struct ieee80211_mle_basic_common_info {
+	u8 len;
+	u8 mld_mac_addr[ETH_ALEN];
+	u8 variable[];
+} __packed;
+
+#define IEEE80211_MLC_PREQ_PRES_MLD_ID			0x0010
+
+struct ieee80211_mle_preq_common_info {
+	u8 len;
+	u8 variable[];
+} __packed;
+
+#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR		0x0010
+#define IEEE80211_MLC_RECONF_PRES_EML_CAPA		0x0020
+#define IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP		0x0040
+#define IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP	0x0080
+
+/* no fixed fields in RECONF */
+
+struct ieee80211_mle_tdls_common_info {
+	u8 len;
+	u8 ap_mld_mac_addr[ETH_ALEN];
+} __packed;
+
+#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR	0x0010
+
+/* no fixed fields in PRIO_ACCESS */
+
+/**
+ * ieee80211_mle_common_size - check multi-link element common size
+ * @data: multi-link element, must already be checked for size using
+ *	ieee80211_mle_size_ok()
+ * Return: the size of the multi-link element's "common" subfield 
+ */
+static inline u8 ieee80211_mle_common_size(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+
+	switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) {
+	case IEEE80211_ML_CONTROL_TYPE_BASIC:
+	case IEEE80211_ML_CONTROL_TYPE_PREQ:
+	case IEEE80211_ML_CONTROL_TYPE_TDLS:
+	case IEEE80211_ML_CONTROL_TYPE_RECONF:
+	case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS:
+		/*
+		 * The length is the first octet pointed by mle->variable so no
+		 * need to add anything
+		 */
+		break;
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+
+	return sizeof(*mle) + mle->variable[0];
+}
+
+/**
+ * ieee80211_mle_get_link_id - returns the link ID
+ * @data: the basic multi link element
+ * Return: the link ID, or -1 if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline int ieee80211_mle_get_link_id(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/* common points now at the beginning of ieee80211_mle_basic_common_info */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_LINK_ID))
+		return -1;
+
+	return *common;
+}
+
+/**
+ * ieee80211_mle_get_bss_param_ch_cnt - returns the BSS parameter change count
+ * @data: pointer to the basic multi link element
+ * Return: the BSS Parameter Change Count field value, or -1 if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline int
+ieee80211_mle_get_bss_param_ch_cnt(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/* common points now at the beginning of ieee80211_mle_basic_common_info */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT))
+		return -1;
+
+	if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+		common += 1;
+
+	return *common;
+}
+
+/**
+ * ieee80211_mle_get_eml_med_sync_delay - returns the medium sync delay
+ * @data: pointer to the multi-link element
+ * Return: the medium synchronization delay field value from the multi-link
+ *	element, or the default value (%IEEE80211_MED_SYNC_DELAY_DEFAULT)
+ *	if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline u16 ieee80211_mle_get_eml_med_sync_delay(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/* common points now at the beginning of ieee80211_mle_basic_common_info */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY))
+		return IEEE80211_MED_SYNC_DELAY_DEFAULT;
+
+	if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
+		common += 1;
+
+	return get_unaligned_le16(common);
+}
+
+/**
+ * ieee80211_mle_get_eml_cap - returns the EML capability
+ * @data: pointer to the multi-link element
+ * Return: the EML capability field value from the multi-link element,
+ *	or 0 if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline u16 ieee80211_mle_get_eml_cap(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/* common points now at the beginning of ieee80211_mle_basic_common_info */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_EML_CAPA))
+		return 0;
+
+	if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)
+		common += 2;
+
+	return get_unaligned_le16(common);
+}
+
+/**
+ * ieee80211_mle_get_mld_capa_op - returns the MLD capabilities and operations.
+ * @data: pointer to the multi-link element
+ * Return: the MLD capabilities and operations field value from the multi-link
+ *	element, or 0 if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/*
+	 * common points now at the beginning of
+	 * ieee80211_mle_basic_common_info
+	 */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP))
+		return 0;
+
+	if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)
+		common += 2;
+	if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)
+		common += 2;
+
+	return get_unaligned_le16(common);
+}
+
+/* Defined in Figure 9-1074t in P802.11be_D7.0 */
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE           0x0001
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_RECO_MAX_LINKS_MASK    0x001e
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE               0x0020
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK     0x0040
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_BTM_MLD_RECO_MULTI_AP     0x0080
+
+/**
+ * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities
+ *	and operations.
+ * @data: pointer to the multi-link element
+ * Return: the extended MLD capabilities and operations field value from
+ *	the multi-link element, or 0 if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline u16 ieee80211_mle_get_ext_mld_capa_op(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/*
+	 * common points now at the beginning of
+	 * ieee80211_mle_basic_common_info
+	 */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP))
+		return 0;
+
+	if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)
+		common += 2;
+	if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)
+		common += 2;
+	if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)
+		common += 2;
+	if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID)
+		common += 1;
+
+	return get_unaligned_le16(common);
+}
+
+/**
+ * ieee80211_mle_get_mld_id - returns the MLD ID
+ * @data: pointer to the multi-link element
+ * Return: The MLD ID in the given multi-link element, or 0 if not present
+ *
+ * The element is assumed to be of the correct type (BASIC) and big enough,
+ * this must be checked using ieee80211_mle_type_ok().
+ */
+static inline u8 ieee80211_mle_get_mld_id(const u8 *data)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control = le16_to_cpu(mle->control);
+	const u8 *common = mle->variable;
+
+	/*
+	 * common points now at the beginning of
+	 * ieee80211_mle_basic_common_info
+	 */
+	common += sizeof(struct ieee80211_mle_basic_common_info);
+
+	if (!(control & IEEE80211_MLC_BASIC_PRES_MLD_ID))
+		return 0;
+
+	if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
+		common += 1;
+	if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)
+		common += 2;
+	if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)
+		common += 2;
+	if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)
+		common += 2;
+
+	return *common;
+}
+
+/**
+ * ieee80211_mle_size_ok - validate multi-link element size
+ * @data: pointer to the element data
+ * @len: length of the containing element
+ * Return: whether or not the multi-link element size is OK
+ */
+static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u8 fixed = sizeof(*mle);
+	u8 common = 0;
+	bool check_common_len = false;
+	u16 control;
+
+	if (!data || len < fixed)
+		return false;
+
+	control = le16_to_cpu(mle->control);
+
+	switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) {
+	case IEEE80211_ML_CONTROL_TYPE_BASIC:
+		common += sizeof(struct ieee80211_mle_basic_common_info);
+		check_common_len = true;
+		if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
+			common += 1;
+		if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
+			common += 1;
+		if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)
+			common += 2;
+		if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)
+			common += 2;
+		if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)
+			common += 2;
+		if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID)
+			common += 1;
+		if (control & IEEE80211_MLC_BASIC_PRES_EXT_MLD_CAPA_OP)
+			common += 2;
+		break;
+	case IEEE80211_ML_CONTROL_TYPE_PREQ:
+		common += sizeof(struct ieee80211_mle_preq_common_info);
+		if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID)
+			common += 1;
+		check_common_len = true;
+		break;
+	case IEEE80211_ML_CONTROL_TYPE_RECONF:
+		if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR)
+			common += ETH_ALEN;
+		if (control & IEEE80211_MLC_RECONF_PRES_EML_CAPA)
+			common += 2;
+		if (control & IEEE80211_MLC_RECONF_PRES_MLD_CAPA_OP)
+			common += 2;
+		if (control & IEEE80211_MLC_RECONF_PRES_EXT_MLD_CAPA_OP)
+			common += 2;
+		break;
+	case IEEE80211_ML_CONTROL_TYPE_TDLS:
+		common += sizeof(struct ieee80211_mle_tdls_common_info);
+		check_common_len = true;
+		break;
+	case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS:
+		common = ETH_ALEN + 1;
+		break;
+	default:
+		/* we don't know this type */
+		return true;
+	}
+
+	if (len < fixed + common)
+		return false;
+
+	if (!check_common_len)
+		return true;
+
+	/* if present, common length is the first octet there */
+	return mle->variable[0] >= common;
+}
+
+/**
+ * ieee80211_mle_type_ok - validate multi-link element type and size
+ * @data: pointer to the element data
+ * @type: expected type of the element
+ * @len: length of the containing element
+ * Return: whether or not the multi-link element type matches and size is OK
+ */
+static inline bool ieee80211_mle_type_ok(const u8 *data, u8 type, size_t len)
+{
+	const struct ieee80211_multi_link_elem *mle = (const void *)data;
+	u16 control;
+
+	if (!ieee80211_mle_size_ok(data, len))
+		return false;
+
+	control = le16_to_cpu(mle->control);
+
+	if (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE) == type)
+		return true;
+
+	return false;
+}
+
+enum ieee80211_mle_subelems {
+	IEEE80211_MLE_SUBELEM_PER_STA_PROFILE		= 0,
+	IEEE80211_MLE_SUBELEM_FRAGMENT		        = 254,
+};
+
+#define IEEE80211_MLE_STA_CONTROL_LINK_ID			0x000f
+#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE		0x0010
+#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT		0x0020
+#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT		0x0040
+#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT		0x0080
+#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT		0x0100
+#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT	0x0200
+#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE		0x0400
+#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT	0x0800
+
+struct ieee80211_mle_per_sta_profile {
+	__le16 control;
+	u8 sta_info_len;
+	u8 variable[];
+} __packed;
+
+/**
+ * ieee80211_mle_basic_sta_prof_size_ok - validate basic multi-link element sta
+ *	profile size
+ * @data: pointer to the sub element data
+ * @len: length of the containing sub element
+ * Return: %true if the STA profile is large enough, %false otherwise
+ */
+static inline bool ieee80211_mle_basic_sta_prof_size_ok(const u8 *data,
+							size_t len)
+{
+	const struct ieee80211_mle_per_sta_profile *prof = (const void *)data;
+	u16 control;
+	u8 fixed = sizeof(*prof);
+	u8 info_len = 1;
+
+	if (len < fixed)
+		return false;
+
+	control = le16_to_cpu(prof->control);
+
+	if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT)
+		info_len += 6;
+	if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT)
+		info_len += 2;
+	if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT)
+		info_len += 8;
+	if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT)
+		info_len += 2;
+	if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE &&
+	    control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) {
+		if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE)
+			info_len += 2;
+		else
+			info_len += 1;
+	}
+	if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)
+		info_len += 1;
+
+	return prof->sta_info_len >= info_len &&
+	       fixed + prof->sta_info_len - 1 <= len;
+}
+
+/**
+ * ieee80211_mle_basic_sta_prof_bss_param_ch_cnt - get per-STA profile BSS
+ *	parameter change count
+ * @prof: the per-STA profile, having been checked with
+ *	ieee80211_mle_basic_sta_prof_size_ok() for the correct length
+ *
+ * Return: The BSS parameter change count value if present, 0 otherwise.
+ */
+static inline u8
+ieee80211_mle_basic_sta_prof_bss_param_ch_cnt(const struct ieee80211_mle_per_sta_profile *prof)
+{
+	u16 control = le16_to_cpu(prof->control);
+	const u8 *pos = prof->variable;
+
+	if (!(control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT))
+		return 0;
+
+	if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT)
+		pos += 6;
+	if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT)
+		pos += 2;
+	if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT)
+		pos += 8;
+	if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT)
+		pos += 2;
+	if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE &&
+	    control & IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT) {
+		if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE)
+			pos += 2;
+		else
+			pos += 1;
+	}
+
+	return *pos;
+}
+
+#define IEEE80211_MLE_STA_RECONF_CONTROL_LINK_ID			0x000f
+#define IEEE80211_MLE_STA_RECONF_CONTROL_COMPLETE_PROFILE		0x0010
+#define IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT		0x0020
+#define IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT		0x0040
+#define	IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE                 0x0780
+#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_AP_REM          0
+#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_OP_PARAM_UPDATE 1
+#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_ADD_LINK        2
+#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_DEL_LINK        3
+#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_TYPE_NSTR_STATUS     4
+#define IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT       0x0800
+
+/**
+ * ieee80211_mle_reconf_sta_prof_size_ok - validate reconfiguration multi-link
+ *	element sta profile size.
+ * @data: pointer to the sub element data
+ * @len: length of the containing sub element
+ * Return: %true if the STA profile is large enough, %false otherwise
+ */
+static inline bool ieee80211_mle_reconf_sta_prof_size_ok(const u8 *data,
+							 size_t len)
+{
+	const struct ieee80211_mle_per_sta_profile *prof = (const void *)data;
+	u16 control;
+	u8 fixed = sizeof(*prof);
+	u8 info_len = 1;
+
+	if (len < fixed)
+		return false;
+
+	control = le16_to_cpu(prof->control);
+
+	if (control & IEEE80211_MLE_STA_RECONF_CONTROL_STA_MAC_ADDR_PRESENT)
+		info_len += ETH_ALEN;
+	if (control & IEEE80211_MLE_STA_RECONF_CONTROL_AP_REM_TIMER_PRESENT)
+		info_len += 2;
+	if (control & IEEE80211_MLE_STA_RECONF_CONTROL_OPERATION_PARAMS_PRESENT)
+		info_len += 2;
+
+	return prof->sta_info_len >= info_len &&
+	       fixed + prof->sta_info_len - 1 <= len;
+}
+
+#define IEEE80211_MLE_STA_EPCS_CONTROL_LINK_ID			0x000f
+#define IEEE80211_EPCS_ENA_RESP_BODY_LEN                        3
+
+static inline bool ieee80211_tid_to_link_map_size_ok(const u8 *data, size_t len)
+{
+	const struct ieee80211_ttlm_elem *t2l = (const void *)data;
+	u8 control, fixed = sizeof(*t2l), elem_len = 0;
+
+	if (len < fixed)
+		return false;
+
+	control = t2l->control;
+
+	if (control & IEEE80211_TTLM_CONTROL_SWITCH_TIME_PRESENT)
+		elem_len += 2;
+	if (control & IEEE80211_TTLM_CONTROL_EXPECTED_DUR_PRESENT)
+		elem_len += 3;
+
+	if (!(control & IEEE80211_TTLM_CONTROL_DEF_LINK_MAP)) {
+		u8 bm_size;
+
+		elem_len += 1;
+		if (len < fixed + elem_len)
+			return false;
+
+		if (control & IEEE80211_TTLM_CONTROL_LINK_MAP_SIZE)
+			bm_size = 1;
+		else
+			bm_size = 2;
+
+		elem_len += hweight8(t2l->optional[0]) * bm_size;
+	}
+
+	return len >= fixed + elem_len;
+}
+
+/**
+ * ieee80211_emlsr_pad_delay_in_us - Fetch the EMLSR Padding delay
+ *	in microseconds
+ * @eml_cap: EML capabilities field value from common info field of
+ *	the Multi-link element
+ * Return: the EMLSR Padding delay (in microseconds) encoded in the
+ *	EML Capabilities field
+ */
+
+static inline u32 ieee80211_emlsr_pad_delay_in_us(u16 eml_cap)
+{
+	/* IEEE Std 802.11be-2024 Table 9-417i—Encoding of the EMLSR
+	 * Padding Delay subfield.
+	 */
+	u32 pad_delay = u16_get_bits(eml_cap,
+				     IEEE80211_EML_CAP_EMLSR_PADDING_DELAY);
+
+	if (!pad_delay ||
+	    pad_delay > IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US)
+		return 0;
+
+	return 32 * (1 << (pad_delay - 1));
+}
+
+/**
+ * ieee80211_emlsr_trans_delay_in_us - Fetch the EMLSR Transition
+ *	delay in microseconds
+ * @eml_cap: EML capabilities field value from common info field of
+ *	the Multi-link element
+ * Return: the EMLSR Transition delay (in microseconds) encoded in the
+ *	EML Capabilities field
+ */
+
+static inline u32 ieee80211_emlsr_trans_delay_in_us(u16 eml_cap)
+{
+	/* IEEE Std 802.11be-2024 Table 9-417j—Encoding of the EMLSR
+	 * Transition Delay subfield.
+	 */
+	u32 trans_delay =
+		u16_get_bits(eml_cap,
+			     IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY);
+
+	/* invalid values also just use 0 */
+	if (!trans_delay ||
+	    trans_delay > IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US)
+		return 0;
+
+	return 16 * (1 << (trans_delay - 1));
+}
+
+/**
+ * ieee80211_eml_trans_timeout_in_us - Fetch the EMLSR Transition
+ *	timeout value in microseconds
+ * @eml_cap: EML capabilities field value from common info field of
+ *	the Multi-link element
+ * Return: the EMLSR Transition timeout (in microseconds) encoded in
+ *	the EML Capabilities field
+ */
+
+static inline u32 ieee80211_eml_trans_timeout_in_us(u16 eml_cap)
+{
+	/* IEEE Std 802.11be-2024 Table 9-417m—Encoding of the
+	 * Transition Timeout subfield.
+	 */
+	u8 timeout = u16_get_bits(eml_cap,
+				  IEEE80211_EML_CAP_TRANSITION_TIMEOUT);
+
+	/* invalid values also just use 0 */
+	if (!timeout || timeout > IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU)
+		return 0;
+
+	return 128 * (1 << (timeout - 1));
+}
+
+#define for_each_mle_subelement(_elem, _data, _len)			\
+	if (ieee80211_mle_size_ok(_data, _len))				\
+		for_each_element(_elem,					\
+				 _data + ieee80211_mle_common_size(_data),\
+				 _len - ieee80211_mle_common_size(_data))
+
+#endif /* LINUX_IEEE80211_H */
diff --git a/include/linux/ieee80211-he.h b/include/linux/ieee80211-he.h
new file mode 100644
index 000000000000..a08c446fbb04
--- /dev/null
+++ b/include/linux/ieee80211-he.h
@@ -0,0 +1,825 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IEEE 802.11 HE definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_HE_H
+#define LINUX_IEEE80211_HE_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define IEEE80211_TWT_CONTROL_NDP			BIT(0)
+#define IEEE80211_TWT_CONTROL_RESP_MODE			BIT(1)
+#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST	BIT(3)
+#define IEEE80211_TWT_CONTROL_RX_DISABLED		BIT(4)
+#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT		BIT(5)
+
+#define IEEE80211_TWT_REQTYPE_REQUEST			BIT(0)
+#define IEEE80211_TWT_REQTYPE_SETUP_CMD			GENMASK(3, 1)
+#define IEEE80211_TWT_REQTYPE_TRIGGER			BIT(4)
+#define IEEE80211_TWT_REQTYPE_IMPLICIT			BIT(5)
+#define IEEE80211_TWT_REQTYPE_FLOWTYPE			BIT(6)
+#define IEEE80211_TWT_REQTYPE_FLOWID			GENMASK(9, 7)
+#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP		GENMASK(14, 10)
+#define IEEE80211_TWT_REQTYPE_PROTECTION		BIT(15)
+
+enum ieee80211_twt_setup_cmd {
+	TWT_SETUP_CMD_REQUEST,
+	TWT_SETUP_CMD_SUGGEST,
+	TWT_SETUP_CMD_DEMAND,
+	TWT_SETUP_CMD_GROUPING,
+	TWT_SETUP_CMD_ACCEPT,
+	TWT_SETUP_CMD_ALTERNATE,
+	TWT_SETUP_CMD_DICTATE,
+	TWT_SETUP_CMD_REJECT,
+};
+
+struct ieee80211_twt_params {
+	__le16 req_type;
+	__le64 twt;
+	u8 min_twt_dur;
+	__le16 mantissa;
+	u8 channel;
+} __packed;
+
+struct ieee80211_twt_setup {
+	u8 dialog_token;
+	u8 element_id;
+	u8 length;
+	u8 control;
+	u8 params[];
+} __packed;
+
+/**
+ * struct ieee80211_he_cap_elem - HE capabilities element
+ * @mac_cap_info: HE MAC Capabilities Information
+ * @phy_cap_info: HE PHY Capabilities Information
+ *
+ * This structure represents the fixed fields of the payload of the
+ * "HE capabilities element" as described in IEEE Std 802.11ax-2021
+ * sections 9.4.2.248.2 and 9.4.2.248.3.
+ */
+struct ieee80211_he_cap_elem {
+	u8 mac_cap_info[6];
+	u8 phy_cap_info[11];
+} __packed;
+
+#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN	5
+
+/**
+ * enum ieee80211_he_mcs_support - HE MCS support definitions
+ * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
+ *	number of streams
+ * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported
+ * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported
+ * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported
+ *
+ * These definitions are used in each 2-bit subfield of the rx_mcs_*
+ * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are
+ * both split into 8 subfields by number of streams. These values indicate
+ * which MCSes are supported for the number of streams the value appears
+ * for.
+ */
+enum ieee80211_he_mcs_support {
+	IEEE80211_HE_MCS_SUPPORT_0_7	= 0,
+	IEEE80211_HE_MCS_SUPPORT_0_9	= 1,
+	IEEE80211_HE_MCS_SUPPORT_0_11	= 2,
+	IEEE80211_HE_MCS_NOT_SUPPORTED	= 3,
+};
+
+/**
+ * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field
+ *
+ * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field
+ * described in P802.11ax_D2.0 section 9.4.2.237.4
+ *
+ * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     widths less than 80MHz.
+ * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     widths less than 80MHz.
+ * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     width 160MHz.
+ * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel
+ *     width 160MHz.
+ * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for
+ *     channel width 80p80MHz.
+ * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for
+ *     channel width 80p80MHz.
+ */
+struct ieee80211_he_mcs_nss_supp {
+	__le16 rx_mcs_80;
+	__le16 tx_mcs_80;
+	__le16 rx_mcs_160;
+	__le16 tx_mcs_160;
+	__le16 rx_mcs_80p80;
+	__le16 tx_mcs_80p80;
+} __packed;
+
+/**
+ * struct ieee80211_he_operation - HE Operation element
+ * @he_oper_params: HE Operation Parameters + BSS Color Information
+ * @he_mcs_nss_set: Basic HE-MCS And NSS Set
+ * @optional: Optional fields VHT Operation Information, Max Co-Hosted
+ *            BSSID Indicator, and 6 GHz Operation Information
+ *
+ * This structure represents the payload of the "HE Operation
+ * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.249.
+ */
+struct ieee80211_he_operation {
+	__le32 he_oper_params;
+	__le16 he_mcs_nss_set;
+	u8 optional[];
+} __packed;
+
+/**
+ * struct ieee80211_he_spr - Spatial Reuse Parameter Set element
+ * @he_sr_control: SR Control
+ * @optional: Optional fields Non-SRG OBSS PD Max Offset, SRG OBSS PD
+ *            Min Offset, SRG OBSS PD Max Offset, SRG BSS Color
+ *            Bitmap, and SRG Partial BSSID Bitmap
+ *
+ * This structure represents the payload of the "Spatial Reuse
+ * Parameter Set element" as described in IEEE Std 802.11ax-2021
+ * section 9.4.2.252.
+ */
+struct ieee80211_he_spr {
+	u8 he_sr_control;
+	u8 optional[];
+} __packed;
+
+/**
+ * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field
+ * @aifsn: ACI/AIFSN
+ * @ecw_min_max: ECWmin/ECWmax
+ * @mu_edca_timer: MU EDCA Timer
+ *
+ * This structure represents the "MU AC Parameter Record" as described
+ * in IEEE Std 802.11ax-2021 section 9.4.2.251, Figure 9-788p.
+ */
+struct ieee80211_he_mu_edca_param_ac_rec {
+	u8 aifsn;
+	u8 ecw_min_max;
+	u8 mu_edca_timer;
+} __packed;
+
+/**
+ * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element
+ * @mu_qos_info: QoS Info
+ * @ac_be: MU AC_BE Parameter Record
+ * @ac_bk: MU AC_BK Parameter Record
+ * @ac_vi: MU AC_VI Parameter Record
+ * @ac_vo: MU AC_VO Parameter Record
+ *
+ * This structure represents the payload of the "MU EDCA Parameter Set
+ * element" as described in IEEE Std 802.11ax-2021 section 9.4.2.251.
+ */
+struct ieee80211_mu_edca_param_set {
+	u8 mu_qos_info;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_be;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_bk;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_vi;
+	struct ieee80211_he_mu_edca_param_ac_rec ac_vo;
+} __packed;
+
+/* 802.11ax HE MAC capabilities */
+#define IEEE80211_HE_MAC_CAP0_HTC_HE				0x01
+#define IEEE80211_HE_MAC_CAP0_TWT_REQ				0x02
+#define IEEE80211_HE_MAC_CAP0_TWT_RES				0x04
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP		0x00
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1		0x08
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2		0x10
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3		0x18
+#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK			0x18
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1		0x00
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2		0x20
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4		0x40
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8		0x60
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16		0x80
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32		0xa0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64		0xc0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED	0xe0
+#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK		0xe0
+
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED		0x00
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128			0x01
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256			0x02
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512			0x03
+#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK		0x03
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US		0x00
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US		0x04
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US		0x08
+#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK		0x0c
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1		0x00
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2		0x10
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3		0x20
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4		0x30
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5		0x40
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6		0x50
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7		0x60
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8		0x70
+#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK		0x70
+
+/* Link adaptation is split between byte HE_MAC_CAP1 and
+ * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE
+ * in which case the following values apply:
+ * 0 = No feedback.
+ * 1 = reserved.
+ * 2 = Unsolicited feedback.
+ * 3 = both
+ */
+#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION			0x80
+
+#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION			0x01
+#define IEEE80211_HE_MAC_CAP2_ALL_ACK				0x02
+#define IEEE80211_HE_MAC_CAP2_TRS				0x04
+#define IEEE80211_HE_MAC_CAP2_BSR				0x08
+#define IEEE80211_HE_MAC_CAP2_BCAST_TWT				0x10
+#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP			0x20
+#define IEEE80211_HE_MAC_CAP2_MU_CASCADING			0x40
+#define IEEE80211_HE_MAC_CAP2_ACK_EN				0x80
+
+#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL			0x02
+#define IEEE80211_HE_MAC_CAP3_OFDMA_RA				0x04
+
+/* The maximum length of an A-MDPU is defined by the combination of the Maximum
+ * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the
+ * same field in the HE capabilities.
+ */
+#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0		0x00
+#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1		0x08
+#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2		0x10
+#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3		0x18
+#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK		0x18
+#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG			0x20
+#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED			0x40
+#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS		0x80
+
+#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG		0x01
+#define IEEE80211_HE_MAC_CAP4_QTP				0x02
+#define IEEE80211_HE_MAC_CAP4_BQR				0x04
+#define IEEE80211_HE_MAC_CAP4_PSR_RESP				0x08
+#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP			0x10
+#define IEEE80211_HE_MAC_CAP4_OPS				0x20
+#define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU			0x40
+/* Multi TID agg TX is split between byte #4 and #5
+ * The value is a combination of B39,B40,B41
+ */
+#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39		0x80
+
+#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40		0x01
+#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41		0x02
+#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION	0x04
+#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU			0x08
+#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX		0x10
+#define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS			0x20
+#define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING		0x40
+#define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX		0x80
+
+#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR	20
+#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR	16
+#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR	13
+
+/* 802.11ax HE PHY capabilities */
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G		0x02
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G	0x04
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G		0x08
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G	0x10
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL		0x1e
+
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G	0x20
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G	0x40
+#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK			0xfe
+
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ	0x01
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ	0x02
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ	0x04
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ	0x08
+#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK			0x0f
+#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A				0x10
+#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD			0x20
+#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US		0x40
+/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */
+#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS			0x80
+
+#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS			0x01
+#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US			0x02
+#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ			0x04
+#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ			0x08
+#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX				0x10
+#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX				0x20
+
+/* Note that the meaning of UL MU below is different between an AP and a non-AP
+ * sta, where in the AP case it indicates support for Rx and in the non-AP sta
+ * case it indicates support for Tx.
+ */
+#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO			0x40
+#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO			0x80
+
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM			0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK			0x01
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK			0x02
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM			0x03
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK			0x03
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1				0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2				0x04
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM			0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK			0x08
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK			0x10
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM			0x18
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK			0x18
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1				0x00
+#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2				0x20
+#define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU		0x40
+#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER				0x80
+
+#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE				0x01
+#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER				0x02
+
+/* Minimal allowed value of Max STS under 80MHz is 3 */
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4		0x0c
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5		0x10
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6		0x14
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7		0x18
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8		0x1c
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK	0x1c
+
+/* Minimal allowed value of Max STS above 80MHz is 3 */
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4		0x60
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5		0x80
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6		0xa0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7		0xc0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8		0xe0
+#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK	0xe0
+
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1	0x00
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2	0x01
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3	0x02
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4	0x03
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5	0x04
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6	0x05
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7	0x06
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8	0x07
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK	0x07
+
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1	0x00
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2	0x08
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3	0x10
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4	0x18
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5	0x20
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6	0x28
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7	0x30
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8	0x38
+#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK	0x38
+
+#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK				0x40
+#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK				0x80
+
+#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU			0x01
+#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU			0x02
+#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB			0x04
+#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB		0x08
+#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB				0x10
+#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE			0x20
+#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO		0x40
+#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT			0x80
+
+#define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR				0x01
+#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP			0x02
+#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI		0x04
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_1					0x08
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_2					0x10
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_3					0x18
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_4					0x20
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_5					0x28
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_6					0x30
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_7					0x38
+#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK				0x38
+#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ			0x40
+#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ			0x80
+
+#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI		0x01
+#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G		0x02
+#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU			0x04
+#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU			0x08
+#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI		0x10
+#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF		0x20
+#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242				0x00
+#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484				0x40
+#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996				0x80
+#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996				0xc0
+#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK				0xc0
+
+#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM		0x01
+#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK		0x02
+#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU		0x04
+#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU		0x08
+#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB	0x10
+#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB	0x20
+#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US			0x0
+#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US			0x1
+#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US			0x2
+#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED		0x3
+#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS			6
+#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK			0xc0
+
+#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF			0x01
+
+/* 802.11ax HE TX/RX MCS NSS Support  */
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS			(3)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS			(6)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS			(11)
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK			0x07c0
+#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK			0xf800
+
+/* TX/RX HE MCS Support field Highest MCS subfield encoding */
+enum ieee80211_he_highest_mcs_supported_subfield_enc {
+	HIGHEST_MCS_SUPPORTED_MCS7 = 0,
+	HIGHEST_MCS_SUPPORTED_MCS8,
+	HIGHEST_MCS_SUPPORTED_MCS9,
+	HIGHEST_MCS_SUPPORTED_MCS10,
+	HIGHEST_MCS_SUPPORTED_MCS11,
+};
+
+/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */
+static inline u8
+ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap)
+{
+	u8 count = 4;
+
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
+		count += 4;
+
+	if (he_cap->phy_cap_info[0] &
+	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)
+		count += 4;
+
+	return count;
+}
+
+/* 802.11ax HE PPE Thresholds */
+#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS			(1)
+#define IEEE80211_PPE_THRES_NSS_POS				(0)
+#define IEEE80211_PPE_THRES_NSS_MASK				(7)
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU	\
+	(BIT(5) | BIT(6))
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK		0x78
+#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS		(3)
+#define IEEE80211_PPE_THRES_INFO_PPET_SIZE			(3)
+#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE			(7)
+
+/*
+ * Calculate 802.11ax HE capabilities IE PPE field size
+ * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8*
+ */
+static inline u8
+ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
+{
+	u8 n;
+
+	if ((phy_cap_info[6] &
+	     IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0)
+		return 0;
+
+	n = hweight8(ppe_thres_hdr &
+		     IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
+	n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >>
+		   IEEE80211_PPE_THRES_NSS_POS));
+
+	/*
+	 * Each pair is 6 bits, and we need to add the 7 "header" bits to the
+	 * total size.
+	 */
+	n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7;
+	n = DIV_ROUND_UP(n, 8);
+
+	return n;
+}
+
+static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len)
+{
+	const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data;
+	u8 needed = sizeof(*he_cap_ie_elem);
+
+	if (len < needed)
+		return false;
+
+	needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem);
+	if (len < needed)
+		return false;
+
+	if (he_cap_ie_elem->phy_cap_info[6] &
+			IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
+		if (len < needed + 1)
+			return false;
+		needed += ieee80211_he_ppe_size(data[needed],
+						he_cap_ie_elem->phy_cap_info);
+	}
+
+	return len >= needed;
+}
+
+/* HE Operation defines */
+#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000007
+#define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000008
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x00003ff0
+#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		4
+#define IEEE80211_HE_OPERATION_VHT_OPER_INFO			0x00004000
+#define IEEE80211_HE_OPERATION_CO_HOSTED_BSS			0x00008000
+#define IEEE80211_HE_OPERATION_ER_SU_DISABLE			0x00010000
+#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO			0x00020000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK			0x3f000000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET			24
+#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x40000000
+#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED		0x80000000
+
+#define IEEE80211_6GHZ_CTRL_REG_LPI_AP			0
+#define IEEE80211_6GHZ_CTRL_REG_SP_AP			1
+#define IEEE80211_6GHZ_CTRL_REG_VLP_AP			2
+#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP		3
+#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD	4
+#define IEEE80211_6GHZ_CTRL_REG_AP_ROLE_NOT_RELEVANT	7
+#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP		8
+
+/**
+ * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
+ * @primary: primary channel
+ * @control: control flags
+ * @ccfs0: channel center frequency segment 0
+ * @ccfs1: channel center frequency segment 1
+ * @minrate: minimum rate (in 1 Mbps units)
+ */
+struct ieee80211_he_6ghz_oper {
+	u8 primary;
+#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH	0x3
+#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ	0
+#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ	1
+#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ	2
+#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ	3
+#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON	0x4
+#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO	0x78
+	u8 control;
+	u8 ccfs0;
+	u8 ccfs1;
+	u8 minrate;
+} __packed;
+
+/**
+ * enum ieee80211_reg_conn_bits - represents Regulatory connectivity field bits.
+ *
+ * This enumeration defines bit flags used to represent regulatory connectivity
+ * field bits.
+ *
+ * @IEEE80211_REG_CONN_LPI_VALID: Indicates whether the LPI bit is valid.
+ * @IEEE80211_REG_CONN_LPI_VALUE: Represents the value of the LPI bit.
+ * @IEEE80211_REG_CONN_SP_VALID: Indicates whether the SP bit is valid.
+ * @IEEE80211_REG_CONN_SP_VALUE: Represents the value of the SP bit.
+ */
+enum ieee80211_reg_conn_bits {
+	IEEE80211_REG_CONN_LPI_VALID = BIT(0),
+	IEEE80211_REG_CONN_LPI_VALUE = BIT(1),
+	IEEE80211_REG_CONN_SP_VALID = BIT(2),
+	IEEE80211_REG_CONN_SP_VALUE = BIT(3),
+};
+
+/* transmit power interpretation type of transmit power envelope element */
+enum ieee80211_tx_power_intrpt_type {
+	IEEE80211_TPE_LOCAL_EIRP,
+	IEEE80211_TPE_LOCAL_EIRP_PSD,
+	IEEE80211_TPE_REG_CLIENT_EIRP,
+	IEEE80211_TPE_REG_CLIENT_EIRP_PSD,
+};
+
+/* category type of transmit power envelope element */
+enum ieee80211_tx_power_category_6ghz {
+	IEEE80211_TPE_CAT_6GHZ_DEFAULT = 0,
+	IEEE80211_TPE_CAT_6GHZ_SUBORDINATE = 1,
+};
+
+/*
+ * For IEEE80211_TPE_LOCAL_EIRP / IEEE80211_TPE_REG_CLIENT_EIRP,
+ * setting to 63.5 dBm means no constraint.
+ */
+#define IEEE80211_TPE_MAX_TX_PWR_NO_CONSTRAINT	127
+
+/*
+ * For IEEE80211_TPE_LOCAL_EIRP_PSD / IEEE80211_TPE_REG_CLIENT_EIRP_PSD,
+ * setting to 127 indicates no PSD limit for the 20 MHz channel.
+ */
+#define IEEE80211_TPE_PSD_NO_LIMIT		127
+
+/**
+ * struct ieee80211_tx_pwr_env - Transmit Power Envelope
+ * @info: Transmit Power Information field
+ * @variable: Maximum Transmit Power field
+ *
+ * This structure represents the payload of the "Transmit Power
+ * Envelope element" as described in IEEE Std 802.11ax-2021 section
+ * 9.4.2.161
+ */
+struct ieee80211_tx_pwr_env {
+	u8 info;
+	u8 variable[];
+} __packed;
+
+#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7
+#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38
+#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0
+
+#define IEEE80211_TX_PWR_ENV_EXT_COUNT	0xF
+
+static inline bool ieee80211_valid_tpe_element(const u8 *data, u8 len)
+{
+	const struct ieee80211_tx_pwr_env *env = (const void *)data;
+	u8 count, interpret, category;
+	u8 needed = sizeof(*env);
+	u8 N; /* also called N in the spec */
+
+	if (len < needed)
+		return false;
+
+	count = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_COUNT);
+	interpret = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_INTERPRET);
+	category = u8_get_bits(env->info, IEEE80211_TX_PWR_ENV_INFO_CATEGORY);
+
+	switch (category) {
+	case IEEE80211_TPE_CAT_6GHZ_DEFAULT:
+	case IEEE80211_TPE_CAT_6GHZ_SUBORDINATE:
+		break;
+	default:
+		return false;
+	}
+
+	switch (interpret) {
+	case IEEE80211_TPE_LOCAL_EIRP:
+	case IEEE80211_TPE_REG_CLIENT_EIRP:
+		if (count > 3)
+			return false;
+
+		/* count == 0 encodes 1 value for 20 MHz, etc. */
+		needed += count + 1;
+
+		if (len < needed)
+			return false;
+
+		/* there can be extension fields not accounted for in 'count' */
+
+		return true;
+	case IEEE80211_TPE_LOCAL_EIRP_PSD:
+	case IEEE80211_TPE_REG_CLIENT_EIRP_PSD:
+		if (count > 4)
+			return false;
+
+		N = count ? 1 << (count - 1) : 1;
+		needed += N;
+
+		if (len < needed)
+			return false;
+
+		if (len > needed) {
+			u8 K = u8_get_bits(env->variable[N],
+					   IEEE80211_TX_PWR_ENV_EXT_COUNT);
+
+			needed += 1 + K;
+			if (len < needed)
+				return false;
+		}
+
+		return true;
+	}
+
+	return false;
+}
+
+/*
+ * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size
+ * @he_oper_ie: byte data of the He Operations IE, stating from the byte
+ *	after the ext ID byte. It is assumed that he_oper_ie has at least
+ *	sizeof(struct ieee80211_he_operation) bytes, the caller must have
+ *	validated this.
+ * @return the actual size of the IE data (not including header), or 0 on error
+ */
+static inline u8
+ieee80211_he_oper_size(const u8 *he_oper_ie)
+{
+	const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie;
+	u8 oper_len = sizeof(struct ieee80211_he_operation);
+	u32 he_oper_params;
+
+	/* Make sure the input is not NULL */
+	if (!he_oper_ie)
+		return 0;
+
+	/* Calc required length */
+	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
+	if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
+		oper_len += 3;
+	if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS)
+		oper_len++;
+	if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)
+		oper_len += sizeof(struct ieee80211_he_6ghz_oper);
+
+	/* Add the first byte (extension ID) to the total length */
+	oper_len++;
+
+	return oper_len;
+}
+
+/**
+ * ieee80211_he_6ghz_oper - obtain 6 GHz operation field
+ * @he_oper: HE operation element (must be pre-validated for size)
+ *	but may be %NULL
+ *
+ * Return: a pointer to the 6 GHz operation field, or %NULL
+ */
+static inline const struct ieee80211_he_6ghz_oper *
+ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
+{
+	const u8 *ret;
+	u32 he_oper_params;
+
+	if (!he_oper)
+		return NULL;
+
+	ret = (const void *)&he_oper->optional;
+
+	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
+
+	if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO))
+		return NULL;
+	if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
+		ret += 3;
+	if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS)
+		ret++;
+
+	return (const void *)ret;
+}
+
+/* HE Spatial Reuse defines */
+#define IEEE80211_HE_SPR_PSR_DISALLOWED				BIT(0)
+#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED		BIT(1)
+#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			BIT(2)
+#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		BIT(3)
+#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED		BIT(4)
+
+/*
+ * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size
+ * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte
+ *	after the ext ID byte. It is assumed that he_spr_ie has at least
+ *	sizeof(struct ieee80211_he_spr) bytes, the caller must have validated
+ *	this
+ * @return the actual size of the IE data (not including header), or 0 on error
+ */
+static inline u8
+ieee80211_he_spr_size(const u8 *he_spr_ie)
+{
+	const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie;
+	u8 spr_len = sizeof(struct ieee80211_he_spr);
+	u8 he_spr_params;
+
+	/* Make sure the input is not NULL */
+	if (!he_spr_ie)
+		return 0;
+
+	/* Calc required length */
+	he_spr_params = he_spr->he_sr_control;
+	if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT)
+		spr_len++;
+	if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT)
+		spr_len += 18;
+
+	/* Add the first byte (extension ID) to the total length */
+	spr_len++;
+
+	return spr_len;
+}
+
+struct ieee80211_he_6ghz_capa {
+	/* uses IEEE80211_HE_6GHZ_CAP_* below */
+	__le16 capa;
+} __packed;
+
+/* HE 6 GHz band capabilities */
+/* uses enum ieee80211_min_mpdu_spacing values */
+#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START	0x0007
+/* uses enum ieee80211_vht_max_ampdu_length_exp values */
+#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP	0x0038
+/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */
+#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN	0x00c0
+/* WLAN_HT_CAP_SM_PS_* values */
+#define IEEE80211_HE_6GHZ_CAP_SM_PS		0x0600
+#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER	0x0800
+#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS	0x1000
+#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS	0x2000
+
+#endif /* LINUX_IEEE80211_HE_H */
diff --git a/include/linux/ieee80211-ht.h b/include/linux/ieee80211-ht.h
new file mode 100644
index 000000000000..21bbf470540f
--- /dev/null
+++ b/include/linux/ieee80211-ht.h
@@ -0,0 +1,292 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IEEE 802.11 HT definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_HT_H
+#define LINUX_IEEE80211_HT_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/* Maximal size of an A-MSDU that can be transported in a HT BA session */
+#define IEEE80211_MAX_MPDU_LEN_HT_BA		4095
+
+/* Maximal size of an A-MSDU */
+#define IEEE80211_MAX_MPDU_LEN_HT_3839		3839
+#define IEEE80211_MAX_MPDU_LEN_HT_7935		7935
+
+#define IEEE80211_HT_CTL_LEN		4
+
+enum ieee80211_ht_chanwidth_values {
+	IEEE80211_HT_CHANWIDTH_20MHZ = 0,
+	IEEE80211_HT_CHANWIDTH_ANY = 1,
+};
+
+/**
+ * struct ieee80211_bar - Block Ack Request frame format
+ * @frame_control: Frame Control
+ * @duration: Duration
+ * @ra: RA
+ * @ta: TA
+ * @control: BAR Control
+ * @start_seq_num: Starting Sequence Number (see Figure 9-37)
+ *
+ * This structure represents the "BlockAckReq frame format"
+ * as described in IEEE Std 802.11-2020 section 9.3.1.7.
+*/
+struct ieee80211_bar {
+	__le16 frame_control;
+	__le16 duration;
+	__u8 ra[ETH_ALEN];
+	__u8 ta[ETH_ALEN];
+	__le16 control;
+	__le16 start_seq_num;
+} __packed;
+
+/* 802.11 BAR control masks */
+#define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL	0x0000
+#define IEEE80211_BAR_CTRL_MULTI_TID		0x0002
+#define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA	0x0004
+#define IEEE80211_BAR_CTRL_TID_INFO_MASK	0xf000
+#define IEEE80211_BAR_CTRL_TID_INFO_SHIFT	12
+
+#define IEEE80211_HT_MCS_MASK_LEN		10
+
+/**
+ * struct ieee80211_mcs_info - Supported MCS Set field
+ * @rx_mask: RX mask
+ * @rx_highest: highest supported RX rate. If set represents
+ *	the highest supported RX data rate in units of 1 Mbps.
+ *	If this field is 0 this value should not be used to
+ *	consider the highest RX data rate supported.
+ * @tx_params: TX parameters
+ * @reserved: Reserved bits
+ *
+ * This structure represents the "Supported MCS Set field" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.55.4.
+ */
+struct ieee80211_mcs_info {
+	u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN];
+	__le16 rx_highest;
+	u8 tx_params;
+	u8 reserved[3];
+} __packed;
+
+/* 802.11n HT capability MSC set */
+#define IEEE80211_HT_MCS_RX_HIGHEST_MASK	0x3ff
+#define IEEE80211_HT_MCS_TX_DEFINED		0x01
+#define IEEE80211_HT_MCS_TX_RX_DIFF		0x02
+/* value 0 == 1 stream etc */
+#define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK	0x0C
+#define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT	2
+#define		IEEE80211_HT_MCS_TX_MAX_STREAMS	4
+#define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION	0x10
+
+#define IEEE80211_HT_MCS_CHAINS(mcs) ((mcs) == 32 ? 1 : (1 + ((mcs) >> 3)))
+
+/*
+ * 802.11n D5.0 20.3.5 / 20.6 says:
+ * - indices 0 to 7 and 32 are single spatial stream
+ * - 8 to 31 are multiple spatial streams using equal modulation
+ *   [8..15 for two streams, 16..23 for three and 24..31 for four]
+ * - remainder are multiple spatial streams using unequal modulation
+ */
+#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33
+#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \
+	(IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8)
+
+/**
+ * struct ieee80211_ht_cap - HT capabilities element
+ * @cap_info: HT Capability Information
+ * @ampdu_params_info: A-MPDU Parameters
+ * @mcs: Supported MCS Set
+ * @extended_ht_cap_info: HT Extended Capabilities
+ * @tx_BF_cap_info: Transmit Beamforming Capabilities
+ * @antenna_selection_info: ASEL Capability
+ *
+ * This structure represents the payload of the "HT Capabilities
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.55.
+ */
+struct ieee80211_ht_cap {
+	__le16 cap_info;
+	u8 ampdu_params_info;
+
+	/* 16 bytes MCS information */
+	struct ieee80211_mcs_info mcs;
+
+	__le16 extended_ht_cap_info;
+	__le32 tx_BF_cap_info;
+	u8 antenna_selection_info;
+} __packed;
+
+/* 802.11n HT capabilities masks (for cap_info) */
+#define IEEE80211_HT_CAP_LDPC_CODING		0x0001
+#define IEEE80211_HT_CAP_SUP_WIDTH_20_40	0x0002
+#define IEEE80211_HT_CAP_SM_PS			0x000C
+#define		IEEE80211_HT_CAP_SM_PS_SHIFT	2
+#define IEEE80211_HT_CAP_GRN_FLD		0x0010
+#define IEEE80211_HT_CAP_SGI_20			0x0020
+#define IEEE80211_HT_CAP_SGI_40			0x0040
+#define IEEE80211_HT_CAP_TX_STBC		0x0080
+#define IEEE80211_HT_CAP_RX_STBC		0x0300
+#define		IEEE80211_HT_CAP_RX_STBC_SHIFT	8
+#define IEEE80211_HT_CAP_DELAY_BA		0x0400
+#define IEEE80211_HT_CAP_MAX_AMSDU		0x0800
+#define IEEE80211_HT_CAP_DSSSCCK40		0x1000
+#define IEEE80211_HT_CAP_RESERVED		0x2000
+#define IEEE80211_HT_CAP_40MHZ_INTOLERANT	0x4000
+#define IEEE80211_HT_CAP_LSIG_TXOP_PROT		0x8000
+
+/* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */
+#define IEEE80211_HT_EXT_CAP_PCO		0x0001
+#define IEEE80211_HT_EXT_CAP_PCO_TIME		0x0006
+#define		IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT	1
+#define IEEE80211_HT_EXT_CAP_MCS_FB		0x0300
+#define		IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT	8
+#define IEEE80211_HT_EXT_CAP_HTC_SUP		0x0400
+#define IEEE80211_HT_EXT_CAP_RD_RESPONDER	0x0800
+
+/* 802.11n HT capability AMPDU settings (for ampdu_params_info) */
+#define IEEE80211_HT_AMPDU_PARM_FACTOR		0x03
+#define IEEE80211_HT_AMPDU_PARM_DENSITY		0x1C
+#define		IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT	2
+
+/*
+ * Maximum length of AMPDU that the STA can receive in high-throughput (HT).
+ * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets)
+ */
+enum ieee80211_max_ampdu_length_exp {
+	IEEE80211_HT_MAX_AMPDU_8K = 0,
+	IEEE80211_HT_MAX_AMPDU_16K = 1,
+	IEEE80211_HT_MAX_AMPDU_32K = 2,
+	IEEE80211_HT_MAX_AMPDU_64K = 3
+};
+
+#define IEEE80211_HT_MAX_AMPDU_FACTOR 13
+
+/* Minimum MPDU start spacing */
+enum ieee80211_min_mpdu_spacing {
+	IEEE80211_HT_MPDU_DENSITY_NONE = 0,	/* No restriction */
+	IEEE80211_HT_MPDU_DENSITY_0_25 = 1,	/* 1/4 usec */
+	IEEE80211_HT_MPDU_DENSITY_0_5 = 2,	/* 1/2 usec */
+	IEEE80211_HT_MPDU_DENSITY_1 = 3,	/* 1 usec */
+	IEEE80211_HT_MPDU_DENSITY_2 = 4,	/* 2 usec */
+	IEEE80211_HT_MPDU_DENSITY_4 = 5,	/* 4 usec */
+	IEEE80211_HT_MPDU_DENSITY_8 = 6,	/* 8 usec */
+	IEEE80211_HT_MPDU_DENSITY_16 = 7	/* 16 usec */
+};
+
+/**
+ * struct ieee80211_ht_operation - HT operation IE
+ * @primary_chan: Primary Channel
+ * @ht_param: HT Operation Information parameters
+ * @operation_mode: HT Operation Information operation mode
+ * @stbc_param: HT Operation Information STBC params
+ * @basic_set: Basic HT-MCS Set
+ *
+ * This structure represents the payload of the "HT Operation
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.56.
+ */
+struct ieee80211_ht_operation {
+	u8 primary_chan;
+	u8 ht_param;
+	__le16 operation_mode;
+	__le16 stbc_param;
+	u8 basic_set[16];
+} __packed;
+
+/* for ht_param */
+#define IEEE80211_HT_PARAM_CHA_SEC_OFFSET		0x03
+#define		IEEE80211_HT_PARAM_CHA_SEC_NONE		0x00
+#define		IEEE80211_HT_PARAM_CHA_SEC_ABOVE	0x01
+#define		IEEE80211_HT_PARAM_CHA_SEC_BELOW	0x03
+#define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY		0x04
+#define IEEE80211_HT_PARAM_RIFS_MODE			0x08
+
+/* for operation_mode */
+#define IEEE80211_HT_OP_MODE_PROTECTION			0x0003
+#define		IEEE80211_HT_OP_MODE_PROTECTION_NONE		0
+#define		IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER	1
+#define		IEEE80211_HT_OP_MODE_PROTECTION_20MHZ		2
+#define		IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED	3
+#define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT		0x0004
+#define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT		0x0010
+#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT		5
+#define IEEE80211_HT_OP_MODE_CCFS2_MASK			0x1fe0
+
+/* for stbc_param */
+#define IEEE80211_HT_STBC_PARAM_DUAL_BEACON		0x0040
+#define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT		0x0080
+#define IEEE80211_HT_STBC_PARAM_STBC_BEACON		0x0100
+#define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT	0x0200
+#define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE		0x0400
+#define IEEE80211_HT_STBC_PARAM_PCO_PHASE		0x0800
+
+
+/* block-ack parameters */
+#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001
+#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002
+#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C
+#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0
+#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000
+#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
+
+/*
+ * A-MPDU buffer sizes
+ * According to HT size varies from 8 to 64 frames
+ * HE adds the ability to have up to 256 frames.
+ * EHT adds the ability to have up to 1K frames.
+ */
+#define IEEE80211_MIN_AMPDU_BUF		0x8
+#define IEEE80211_MAX_AMPDU_BUF_HT	0x40
+#define IEEE80211_MAX_AMPDU_BUF_HE	0x100
+#define IEEE80211_MAX_AMPDU_BUF_EHT	0x400
+
+
+/* Spatial Multiplexing Power Save Modes (for capability) */
+#define WLAN_HT_CAP_SM_PS_STATIC	0
+#define WLAN_HT_CAP_SM_PS_DYNAMIC	1
+#define WLAN_HT_CAP_SM_PS_INVALID	2
+#define WLAN_HT_CAP_SM_PS_DISABLED	3
+
+/* for SM power control field lower two bits */
+#define WLAN_HT_SMPS_CONTROL_DISABLED	0
+#define WLAN_HT_SMPS_CONTROL_STATIC	1
+#define WLAN_HT_SMPS_CONTROL_DYNAMIC	3
+
+/* HT action codes */
+enum ieee80211_ht_actioncode {
+	WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0,
+	WLAN_HT_ACTION_SMPS = 1,
+	WLAN_HT_ACTION_PSMP = 2,
+	WLAN_HT_ACTION_PCO_PHASE = 3,
+	WLAN_HT_ACTION_CSI = 4,
+	WLAN_HT_ACTION_NONCOMPRESSED_BF = 5,
+	WLAN_HT_ACTION_COMPRESSED_BF = 6,
+	WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7,
+};
+
+/* BACK action code */
+enum ieee80211_back_actioncode {
+	WLAN_ACTION_ADDBA_REQ = 0,
+	WLAN_ACTION_ADDBA_RESP = 1,
+	WLAN_ACTION_DELBA = 2,
+};
+
+/* BACK (block-ack) parties */
+enum ieee80211_back_parties {
+	WLAN_BACK_RECIPIENT = 0,
+	WLAN_BACK_INITIATOR = 1,
+};
+
+#endif /* LINUX_IEEE80211_HT_H */
diff --git a/include/linux/ieee80211-mesh.h b/include/linux/ieee80211-mesh.h
new file mode 100644
index 000000000000..4b829bcb38b6
--- /dev/null
+++ b/include/linux/ieee80211-mesh.h
@@ -0,0 +1,230 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IEEE 802.11 mesh definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_MESH_H
+#define LINUX_IEEE80211_MESH_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define IEEE80211_MAX_MESH_ID_LEN	32
+
+struct ieee80211s_hdr {
+	u8 flags;
+	u8 ttl;
+	__le32 seqnum;
+	u8 eaddr1[ETH_ALEN];
+	u8 eaddr2[ETH_ALEN];
+} __packed __aligned(2);
+
+/* Mesh flags */
+#define MESH_FLAGS_AE_A4 	0x1
+#define MESH_FLAGS_AE_A5_A6	0x2
+#define MESH_FLAGS_AE		0x3
+#define MESH_FLAGS_PS_DEEP	0x4
+
+/**
+ * enum ieee80211_preq_flags - mesh PREQ element flags
+ *
+ * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield
+ */
+enum ieee80211_preq_flags {
+	IEEE80211_PREQ_PROACTIVE_PREP_FLAG	= 1<<2,
+};
+
+/**
+ * enum ieee80211_preq_target_flags - mesh PREQ element per target flags
+ *
+ * @IEEE80211_PREQ_TO_FLAG: target only subfield
+ * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield
+ */
+enum ieee80211_preq_target_flags {
+	IEEE80211_PREQ_TO_FLAG	= 1<<0,
+	IEEE80211_PREQ_USN_FLAG	= 1<<2,
+};
+
+/**
+ * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE
+ * @mesh_ttl: Time To Live
+ * @mesh_flags: Flags
+ * @mesh_reason: Reason Code
+ * @mesh_pre_value: Precedence Value
+ *
+ * This structure represents the payload of the "Mesh Channel Switch
+ * Parameters element" as described in IEEE Std 802.11-2020 section
+ * 9.4.2.102.
+ */
+struct ieee80211_mesh_chansw_params_ie {
+	u8 mesh_ttl;
+	u8 mesh_flags;
+	__le16 mesh_reason;
+	__le16 mesh_pre_value;
+} __packed;
+
+/**
+ * struct ieee80211_meshconf_ie - Mesh Configuration element
+ * @meshconf_psel: Active Path Selection Protocol Identifier
+ * @meshconf_pmetric: Active Path Selection Metric Identifier
+ * @meshconf_congest: Congestion Control Mode Identifier
+ * @meshconf_synch: Synchronization Method Identifier
+ * @meshconf_auth: Authentication Protocol Identifier
+ * @meshconf_form: Mesh Formation Info
+ * @meshconf_cap: Mesh Capability (see &enum mesh_config_capab_flags)
+ *
+ * This structure represents the payload of the "Mesh Configuration
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.97.
+ */
+struct ieee80211_meshconf_ie {
+	u8 meshconf_psel;
+	u8 meshconf_pmetric;
+	u8 meshconf_congest;
+	u8 meshconf_synch;
+	u8 meshconf_auth;
+	u8 meshconf_form;
+	u8 meshconf_cap;
+} __packed;
+
+/**
+ * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags
+ *
+ * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish
+ *	additional mesh peerings with other mesh STAs
+ * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs
+ * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure
+ *	is ongoing
+ * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has
+ *	neighbors in deep sleep mode
+ *
+ * Enumerates the "Mesh Capability" as described in IEEE Std
+ * 802.11-2020 section 9.4.2.97.7.
+ */
+enum mesh_config_capab_flags {
+	IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS		= 0x01,
+	IEEE80211_MESHCONF_CAPAB_FORWARDING		= 0x08,
+	IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING		= 0x20,
+	IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL	= 0x40,
+};
+
+#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1
+
+/*
+ * mesh channel switch parameters element's flag indicator
+ *
+ */
+#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0)
+#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1)
+#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2)
+
+/**
+ * struct ieee80211_rann_ie - RANN (root announcement) element
+ * @rann_flags: Flags
+ * @rann_hopcount: Hop Count
+ * @rann_ttl: Element TTL
+ * @rann_addr: Root Mesh STA Address
+ * @rann_seq: HWMP Sequence Number
+ * @rann_interval: Interval
+ * @rann_metric: Metric
+ *
+ * This structure represents the payload of the "RANN element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.111.
+ */
+struct ieee80211_rann_ie {
+	u8 rann_flags;
+	u8 rann_hopcount;
+	u8 rann_ttl;
+	u8 rann_addr[ETH_ALEN];
+	__le32 rann_seq;
+	__le32 rann_interval;
+	__le32 rann_metric;
+} __packed;
+
+enum ieee80211_rann_flags {
+	RANN_FLAG_IS_GATE = 1 << 0,
+};
+
+/* Mesh action codes */
+enum ieee80211_mesh_actioncode {
+	WLAN_MESH_ACTION_LINK_METRIC_REPORT,
+	WLAN_MESH_ACTION_HWMP_PATH_SELECTION,
+	WLAN_MESH_ACTION_GATE_ANNOUNCEMENT,
+	WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION,
+	WLAN_MESH_ACTION_MCCA_SETUP_REQUEST,
+	WLAN_MESH_ACTION_MCCA_SETUP_REPLY,
+	WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST,
+	WLAN_MESH_ACTION_MCCA_ADVERTISEMENT,
+	WLAN_MESH_ACTION_MCCA_TEARDOWN,
+	WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST,
+	WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE,
+};
+
+/**
+ * enum ieee80211_mesh_sync_method - mesh synchronization method identifier
+ *
+ * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method
+ * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method
+ *	that will be specified in a vendor specific information element
+ */
+enum ieee80211_mesh_sync_method {
+	IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1,
+	IEEE80211_SYNC_METHOD_VENDOR = 255,
+};
+
+/**
+ * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier
+ *
+ * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol
+ * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will
+ *	be specified in a vendor specific information element
+ */
+enum ieee80211_mesh_path_protocol {
+	IEEE80211_PATH_PROTOCOL_HWMP = 1,
+	IEEE80211_PATH_PROTOCOL_VENDOR = 255,
+};
+
+/**
+ * enum ieee80211_mesh_path_metric - mesh path selection metric identifier
+ *
+ * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric
+ * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be
+ *	specified in a vendor specific information element
+ */
+enum ieee80211_mesh_path_metric {
+	IEEE80211_PATH_METRIC_AIRTIME = 1,
+	IEEE80211_PATH_METRIC_VENDOR = 255,
+};
+
+/**
+ * enum ieee80211_root_mode_identifier - root mesh STA mode identifier
+ *
+ * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode
+ *
+ * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default)
+ * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than
+ *	this value
+ * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports
+ *	the proactive PREQ with proactive PREP subfield set to 0
+ * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA
+ *	supports the proactive PREQ with proactive PREP subfield set to 1
+ * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports
+ *	the proactive RANN
+ */
+enum ieee80211_root_mode_identifier {
+	IEEE80211_ROOTMODE_NO_ROOT = 0,
+	IEEE80211_ROOTMODE_ROOT = 1,
+	IEEE80211_PROACTIVE_PREQ_NO_PREP = 2,
+	IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3,
+	IEEE80211_PROACTIVE_RANN = 4,
+};
+
+#endif /* LINUX_IEEE80211_MESH_H */
diff --git a/include/linux/ieee80211-nan.h b/include/linux/ieee80211-nan.h
new file mode 100644
index 000000000000..d07959bf8a90
--- /dev/null
+++ b/include/linux/ieee80211-nan.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * WFA NAN definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_NAN_H
+#define LINUX_IEEE80211_NAN_H
+
+/* NAN operation mode, as defined in Wi-Fi Aware (TM) specification Table 81 */
+#define NAN_OP_MODE_PHY_MODE_VHT	0x01
+#define NAN_OP_MODE_PHY_MODE_HE		0x10
+#define NAN_OP_MODE_PHY_MODE_MASK	0x11
+#define NAN_OP_MODE_80P80MHZ		0x02
+#define NAN_OP_MODE_160MHZ		0x04
+#define NAN_OP_MODE_PNDL_SUPPRTED	0x08
+
+/* NAN Device capabilities, as defined in Wi-Fi Aware (TM) specification
+ * Table 79
+ */
+#define NAN_DEV_CAPA_DFS_OWNER			0x01
+#define NAN_DEV_CAPA_EXT_KEY_ID_SUPPORTED	0x02
+#define NAN_DEV_CAPA_SIM_NDP_RX_SUPPORTED	0x04
+#define NAN_DEV_CAPA_NDPE_SUPPORTED		0x08
+#define NAN_DEV_CAPA_S3_SUPPORTED		0x10
+
+#endif /* LINUX_IEEE80211_NAN_H */
diff --git a/include/linux/ieee80211-p2p.h b/include/linux/ieee80211-p2p.h
new file mode 100644
index 000000000000..180891c11f08
--- /dev/null
+++ b/include/linux/ieee80211-p2p.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * WFA P2P definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_P2P_H
+#define LINUX_IEEE80211_P2P_H
+
+#include <linux/types.h>
+/*
+ * Peer-to-Peer IE attribute related definitions.
+ */
+/*
+ * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute.
+ */
+enum ieee80211_p2p_attr_id {
+	IEEE80211_P2P_ATTR_STATUS = 0,
+	IEEE80211_P2P_ATTR_MINOR_REASON,
+	IEEE80211_P2P_ATTR_CAPABILITY,
+	IEEE80211_P2P_ATTR_DEVICE_ID,
+	IEEE80211_P2P_ATTR_GO_INTENT,
+	IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT,
+	IEEE80211_P2P_ATTR_LISTEN_CHANNEL,
+	IEEE80211_P2P_ATTR_GROUP_BSSID,
+	IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING,
+	IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR,
+	IEEE80211_P2P_ATTR_MANAGABILITY,
+	IEEE80211_P2P_ATTR_CHANNEL_LIST,
+	IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
+	IEEE80211_P2P_ATTR_DEVICE_INFO,
+	IEEE80211_P2P_ATTR_GROUP_INFO,
+	IEEE80211_P2P_ATTR_GROUP_ID,
+	IEEE80211_P2P_ATTR_INTERFACE,
+	IEEE80211_P2P_ATTR_OPER_CHANNEL,
+	IEEE80211_P2P_ATTR_INVITE_FLAGS,
+	/* 19 - 220: Reserved */
+	IEEE80211_P2P_ATTR_VENDOR_SPECIFIC = 221,
+
+	IEEE80211_P2P_ATTR_MAX
+};
+
+/* Notice of Absence attribute - described in P2P spec 4.1.14 */
+/* Typical max value used here */
+#define IEEE80211_P2P_NOA_DESC_MAX	4
+
+struct ieee80211_p2p_noa_desc {
+	u8 count;
+	__le32 duration;
+	__le32 interval;
+	__le32 start_time;
+} __packed;
+
+struct ieee80211_p2p_noa_attr {
+	u8 index;
+	u8 oppps_ctwindow;
+	struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX];
+} __packed;
+
+#define IEEE80211_P2P_OPPPS_ENABLE_BIT		BIT(7)
+#define IEEE80211_P2P_OPPPS_CTWINDOW_MASK	0x7F
+
+#endif /* LINUX_IEEE80211_P2P_H */
diff --git a/include/linux/ieee80211-s1g.h b/include/linux/ieee80211-s1g.h
new file mode 100644
index 000000000000..5b9ed2dcc00e
--- /dev/null
+++ b/include/linux/ieee80211-s1g.h
@@ -0,0 +1,575 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IEEE 802.11 S1G definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_S1G_H
+#define LINUX_IEEE80211_S1G_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+/* bits unique to S1G beacon frame control */
+#define IEEE80211_S1G_BCN_NEXT_TBTT	0x100
+#define IEEE80211_S1G_BCN_CSSID		0x200
+#define IEEE80211_S1G_BCN_ANO		0x400
+
+/* see 802.11ah-2016 9.9 NDP CMAC frames */
+#define IEEE80211_S1G_1MHZ_NDP_BITS	25
+#define IEEE80211_S1G_1MHZ_NDP_BYTES	4
+#define IEEE80211_S1G_2MHZ_NDP_BITS	37
+#define IEEE80211_S1G_2MHZ_NDP_BYTES	5
+
+/**
+ * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT &&
+ * IEEE80211_STYPE_S1G_BEACON
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an S1G beacon
+ */
+static inline bool ieee80211_is_s1g_beacon(__le16 fc)
+{
+	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE |
+				 IEEE80211_FCTL_STYPE)) ==
+	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON);
+}
+
+/**
+ * ieee80211_s1g_has_next_tbtt - check if IEEE80211_S1G_BCN_NEXT_TBTT
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame contains the variable-length
+ *	next TBTT field
+ */
+static inline bool ieee80211_s1g_has_next_tbtt(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT));
+}
+
+/**
+ * ieee80211_s1g_has_ano - check if IEEE80211_S1G_BCN_ANO
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame contains the variable-length
+ *	ANO field
+ */
+static inline bool ieee80211_s1g_has_ano(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_ANO));
+}
+
+/**
+ * ieee80211_s1g_has_cssid - check if IEEE80211_S1G_BCN_CSSID
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame contains the variable-length
+ *	compressed SSID field
+ */
+static inline bool ieee80211_s1g_has_cssid(__le16 fc)
+{
+	return ieee80211_is_s1g_beacon(fc) &&
+		(fc & cpu_to_le16(IEEE80211_S1G_BCN_CSSID));
+}
+
+/**
+ * enum ieee80211_s1g_chanwidth - S1G channel widths
+ * These are defined in IEEE802.11-2016ah Table 10-20
+ * as BSS Channel Width
+ *
+ * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel
+ * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel
+ */
+enum ieee80211_s1g_chanwidth {
+	IEEE80211_S1G_CHANWIDTH_1MHZ = 0,
+	IEEE80211_S1G_CHANWIDTH_2MHZ = 1,
+	IEEE80211_S1G_CHANWIDTH_4MHZ = 3,
+	IEEE80211_S1G_CHANWIDTH_8MHZ = 7,
+	IEEE80211_S1G_CHANWIDTH_16MHZ = 15,
+};
+
+/**
+ * enum ieee80211_s1g_pri_chanwidth - S1G primary channel widths
+ *	described in IEEE80211-2024 Table 10-39.
+ *
+ * @IEEE80211_S1G_PRI_CHANWIDTH_2MHZ: 2MHz primary channel
+ * @IEEE80211_S1G_PRI_CHANWIDTH_1MHZ: 1MHz primary channel
+ */
+enum ieee80211_s1g_pri_chanwidth {
+	IEEE80211_S1G_PRI_CHANWIDTH_2MHZ = 0,
+	IEEE80211_S1G_PRI_CHANWIDTH_1MHZ = 1,
+};
+
+/**
+ * struct ieee80211_s1g_bcn_compat_ie - S1G Beacon Compatibility element
+ * @compat_info: Compatibility Information
+ * @beacon_int: Beacon Interval
+ * @tsf_completion: TSF Completion
+ *
+ * This structure represents the payload of the "S1G Beacon
+ * Compatibility element" as described in IEEE Std 802.11-2020 section
+ * 9.4.2.196.
+ */
+struct ieee80211_s1g_bcn_compat_ie {
+	__le16 compat_info;
+	__le16 beacon_int;
+	__le32 tsf_completion;
+} __packed;
+
+/**
+ * struct ieee80211_s1g_oper_ie - S1G Operation element
+ * @ch_width: S1G Operation Information Channel Width
+ * @oper_class: S1G Operation Information Operating Class
+ * @primary_ch: S1G Operation Information Primary Channel Number
+ * @oper_ch: S1G Operation Information  Channel Center Frequency
+ * @basic_mcs_nss: Basic S1G-MCS and NSS Set
+ *
+ * This structure represents the payload of the "S1G Operation
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.212.
+ */
+struct ieee80211_s1g_oper_ie {
+	u8 ch_width;
+	u8 oper_class;
+	u8 primary_ch;
+	u8 oper_ch;
+	__le16 basic_mcs_nss;
+} __packed;
+
+/**
+ * struct ieee80211_aid_response_ie - AID Response element
+ * @aid: AID/Group AID
+ * @switch_count: AID Switch Count
+ * @response_int: AID Response Interval
+ *
+ * This structure represents the payload of the "AID Response element"
+ * as described in IEEE Std 802.11-2020 section 9.4.2.194.
+ */
+struct ieee80211_aid_response_ie {
+	__le16 aid;
+	u8 switch_count;
+	__le16 response_int;
+} __packed;
+
+struct ieee80211_s1g_cap {
+	u8 capab_info[10];
+	u8 supp_mcs_nss[5];
+} __packed;
+
+/**
+ * ieee80211_s1g_optional_len - determine length of optional S1G beacon fields
+ * @fc: frame control bytes in little-endian byteorder
+ * Return: total length in bytes of the optional fixed-length fields
+ *
+ * S1G beacons may contain up to three optional fixed-length fields that
+ * precede the variable-length elements. Whether these fields are present
+ * is indicated by flags in the frame control field.
+ *
+ * From IEEE 802.11-2024 section 9.3.4.3:
+ *  - Next TBTT field may be 0 or 3 bytes
+ *  - Short SSID field may be 0 or 4 bytes
+ *  - Access Network Options (ANO) field may be 0 or 1 byte
+ */
+static inline size_t
+ieee80211_s1g_optional_len(__le16 fc)
+{
+	size_t len = 0;
+
+	if (ieee80211_s1g_has_next_tbtt(fc))
+		len += 3;
+
+	if (ieee80211_s1g_has_cssid(fc))
+		len += 4;
+
+	if (ieee80211_s1g_has_ano(fc))
+		len += 1;
+
+	return len;
+}
+
+/* S1G Capabilities Information field */
+#define IEEE80211_S1G_CAPABILITY_LEN	15
+
+#define S1G_CAP0_S1G_LONG	BIT(0)
+#define S1G_CAP0_SGI_1MHZ	BIT(1)
+#define S1G_CAP0_SGI_2MHZ	BIT(2)
+#define S1G_CAP0_SGI_4MHZ	BIT(3)
+#define S1G_CAP0_SGI_8MHZ	BIT(4)
+#define S1G_CAP0_SGI_16MHZ	BIT(5)
+#define S1G_CAP0_SUPP_CH_WIDTH	GENMASK(7, 6)
+
+#define S1G_SUPP_CH_WIDTH_2	0
+#define S1G_SUPP_CH_WIDTH_4	1
+#define S1G_SUPP_CH_WIDTH_8	2
+#define S1G_SUPP_CH_WIDTH_16	3
+#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \
+						    cap[0])) << 1)
+
+#define S1G_CAP1_RX_LDPC	BIT(0)
+#define S1G_CAP1_TX_STBC	BIT(1)
+#define S1G_CAP1_RX_STBC	BIT(2)
+#define S1G_CAP1_SU_BFER	BIT(3)
+#define S1G_CAP1_SU_BFEE	BIT(4)
+#define S1G_CAP1_BFEE_STS	GENMASK(7, 5)
+
+#define S1G_CAP2_SOUNDING_DIMENSIONS	GENMASK(2, 0)
+#define S1G_CAP2_MU_BFER		BIT(3)
+#define S1G_CAP2_MU_BFEE		BIT(4)
+#define S1G_CAP2_PLUS_HTC_VHT		BIT(5)
+#define S1G_CAP2_TRAVELING_PILOT	GENMASK(7, 6)
+
+#define S1G_CAP3_RD_RESPONDER		BIT(0)
+#define S1G_CAP3_HT_DELAYED_BA		BIT(1)
+#define S1G_CAP3_MAX_MPDU_LEN		BIT(2)
+#define S1G_CAP3_MAX_AMPDU_LEN_EXP	GENMASK(4, 3)
+#define S1G_CAP3_MIN_MPDU_START		GENMASK(7, 5)
+
+#define S1G_CAP4_UPLINK_SYNC	BIT(0)
+#define S1G_CAP4_DYNAMIC_AID	BIT(1)
+#define S1G_CAP4_BAT		BIT(2)
+#define S1G_CAP4_TIME_ADE	BIT(3)
+#define S1G_CAP4_NON_TIM	BIT(4)
+#define S1G_CAP4_GROUP_AID	BIT(5)
+#define S1G_CAP4_STA_TYPE	GENMASK(7, 6)
+
+#define S1G_CAP5_CENT_AUTH_CONTROL	BIT(0)
+#define S1G_CAP5_DIST_AUTH_CONTROL	BIT(1)
+#define S1G_CAP5_AMSDU			BIT(2)
+#define S1G_CAP5_AMPDU			BIT(3)
+#define S1G_CAP5_ASYMMETRIC_BA		BIT(4)
+#define S1G_CAP5_FLOW_CONTROL		BIT(5)
+#define S1G_CAP5_SECTORIZED_BEAM	GENMASK(7, 6)
+
+#define S1G_CAP6_OBSS_MITIGATION	BIT(0)
+#define S1G_CAP6_FRAGMENT_BA		BIT(1)
+#define S1G_CAP6_NDP_PS_POLL		BIT(2)
+#define S1G_CAP6_RAW_OPERATION		BIT(3)
+#define S1G_CAP6_PAGE_SLICING		BIT(4)
+#define S1G_CAP6_TXOP_SHARING_IMP_ACK	BIT(5)
+#define S1G_CAP6_VHT_LINK_ADAPT		GENMASK(7, 6)
+
+#define S1G_CAP7_TACK_AS_PS_POLL		BIT(0)
+#define S1G_CAP7_DUP_1MHZ			BIT(1)
+#define S1G_CAP7_MCS_NEGOTIATION		BIT(2)
+#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE	BIT(3)
+#define S1G_CAP7_NDP_BFING_REPORT_POLL		BIT(4)
+#define S1G_CAP7_UNSOLICITED_DYN_AID		BIT(5)
+#define S1G_CAP7_SECTOR_TRAINING_OPERATION	BIT(6)
+#define S1G_CAP7_TEMP_PS_MODE_SWITCH		BIT(7)
+
+#define S1G_CAP8_TWT_GROUPING	BIT(0)
+#define S1G_CAP8_BDT		BIT(1)
+#define S1G_CAP8_COLOR		GENMASK(4, 2)
+#define S1G_CAP8_TWT_REQUEST	BIT(5)
+#define S1G_CAP8_TWT_RESPOND	BIT(6)
+#define S1G_CAP8_PV1_FRAME	BIT(7)
+
+#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0)
+
+#define S1G_OPER_CH_WIDTH_PRIMARY	BIT(0)
+#define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
+#define S1G_OPER_CH_PRIMARY_LOCATION	BIT(5)
+
+#define S1G_2M_PRIMARY_LOCATION_LOWER	0
+#define S1G_2M_PRIMARY_LOCATION_UPPER	1
+
+#define LISTEN_INT_USF	GENMASK(15, 14)
+#define LISTEN_INT_UI	GENMASK(13, 0)
+
+#define IEEE80211_MAX_USF	FIELD_MAX(LISTEN_INT_USF)
+#define IEEE80211_MAX_UI	FIELD_MAX(LISTEN_INT_UI)
+
+/* S1G encoding types */
+#define IEEE80211_S1G_TIM_ENC_MODE_BLOCK	0
+#define IEEE80211_S1G_TIM_ENC_MODE_SINGLE	1
+#define IEEE80211_S1G_TIM_ENC_MODE_OLB		2
+
+enum ieee80211_s1g_actioncode {
+	WLAN_S1G_AID_SWITCH_REQUEST,
+	WLAN_S1G_AID_SWITCH_RESPONSE,
+	WLAN_S1G_SYNC_CONTROL,
+	WLAN_S1G_STA_INFO_ANNOUNCE,
+	WLAN_S1G_EDCA_PARAM_SET,
+	WLAN_S1G_EL_OPERATION,
+	WLAN_S1G_TWT_SETUP,
+	WLAN_S1G_TWT_TEARDOWN,
+	WLAN_S1G_SECT_GROUP_ID_LIST,
+	WLAN_S1G_SECT_ID_FEEDBACK,
+	WLAN_S1G_TWT_INFORMATION = 11,
+};
+
+/**
+ * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
+ * @fc: frame control bytes in little-endian byteorder
+ * @variable: pointer to the beacon frame elements
+ * @variable_len: length of the frame elements
+ * Return: whether or not the frame is an S1G short beacon. As per
+ *	IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall
+ *	always be present as the first element in beacon frames generated at a
+ *	TBTT (Target Beacon Transmission Time), so any frame not containing
+ *	this element must have been generated at a TSBTT (Target Short Beacon
+ *	Transmission Time) that is not a TBTT. Additionally, short beacons are
+ *	prohibited from containing the S1G beacon compatibility element as per
+ *	IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with
+ *	either no elements or the first element is not the beacon compatibility
+ *	element, we have a short beacon.
+ */
+static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable,
+						 size_t variable_len)
+{
+	if (!ieee80211_is_s1g_beacon(fc))
+		return false;
+
+	/*
+	 * If the frame does not contain at least 1 element (this is perfectly
+	 * valid in a short beacon) and is an S1G beacon, we have a short
+	 * beacon.
+	 */
+	if (variable_len < 2)
+		return true;
+
+	return variable[0] != WLAN_EID_S1G_BCN_COMPAT;
+}
+
+struct s1g_tim_aid {
+	u16 aid;
+	u8 target_blk; /* Target block index */
+	u8 target_subblk; /* Target subblock index */
+	u8 target_subblk_bit; /* Target subblock bit */
+};
+
+struct s1g_tim_enc_block {
+	u8 enc_mode;
+	bool inverse;
+	const u8 *ptr;
+	u8 len;
+
+	/*
+	 * For an OLB encoded block that spans multiple blocks, this
+	 * is the offset into the span described by that encoded block.
+	 */
+	u8 olb_blk_offset;
+};
+
+/*
+ * Helper routines to quickly extract the length of an encoded block. Validation
+ * is also performed to ensure the length extracted lies within the TIM.
+ */
+
+static inline int ieee80211_s1g_len_bitmap(const u8 *ptr, const u8 *end)
+{
+	u8 blkmap;
+	u8 n_subblks;
+
+	if (ptr >= end)
+		return -EINVAL;
+
+	blkmap = *ptr;
+	n_subblks = hweight8(blkmap);
+
+	if (ptr + 1 + n_subblks > end)
+		return -EINVAL;
+
+	return 1 + n_subblks;
+}
+
+static inline int ieee80211_s1g_len_single(const u8 *ptr, const u8 *end)
+{
+	return (ptr + 1 > end) ? -EINVAL : 1;
+}
+
+static inline int ieee80211_s1g_len_olb(const u8 *ptr, const u8 *end)
+{
+	if (ptr >= end)
+		return -EINVAL;
+
+	return (ptr + 1 + *ptr > end) ? -EINVAL : 1 + *ptr;
+}
+
+/*
+ * Enumerate all encoded blocks until we find the encoded block that describes
+ * our target AID. OLB is a special case as a single encoded block can describe
+ * multiple blocks as a single encoded block.
+ */
+static inline int ieee80211_s1g_find_target_block(struct s1g_tim_enc_block *enc,
+						  const struct s1g_tim_aid *aid,
+						  const u8 *ptr, const u8 *end)
+{
+	/* need at least block-control octet */
+	while (ptr + 1 <= end) {
+		u8 ctrl = *ptr++;
+		u8 mode = ctrl & 0x03;
+		bool contains, inverse = ctrl & BIT(2);
+		u8 span, blk_off = ctrl >> 3;
+		int len;
+
+		switch (mode) {
+		case IEEE80211_S1G_TIM_ENC_MODE_BLOCK:
+			len = ieee80211_s1g_len_bitmap(ptr, end);
+			contains = blk_off == aid->target_blk;
+			break;
+		case IEEE80211_S1G_TIM_ENC_MODE_SINGLE:
+			len = ieee80211_s1g_len_single(ptr, end);
+			contains = blk_off == aid->target_blk;
+			break;
+		case IEEE80211_S1G_TIM_ENC_MODE_OLB:
+			len = ieee80211_s1g_len_olb(ptr, end);
+			/*
+			 * An OLB encoded block can describe more then one
+			 * block, meaning an encoded OLB block can span more
+			 * then a single block.
+			 */
+			if (len > 0) {
+				/* Minus one for the length octet */
+				span = DIV_ROUND_UP(len - 1, 8);
+				/*
+				 * Check if our target block lies within the
+				 * block span described by this encoded block.
+				 */
+				contains = (aid->target_blk >= blk_off) &&
+					   (aid->target_blk < blk_off + span);
+			}
+			break;
+		default:
+			return -EOPNOTSUPP;
+		}
+
+		if (len < 0)
+			return len;
+
+		if (contains) {
+			enc->enc_mode = mode;
+			enc->inverse = inverse;
+			enc->ptr = ptr;
+			enc->len = (u8)len;
+			enc->olb_blk_offset = blk_off;
+			return 0;
+		}
+
+		ptr += len;
+	}
+
+	return -ENOENT;
+}
+
+static inline bool ieee80211_s1g_parse_bitmap(struct s1g_tim_enc_block *enc,
+					      struct s1g_tim_aid *aid)
+{
+	const u8 *ptr = enc->ptr;
+	u8 blkmap = *ptr++;
+
+	/*
+	 * If our block bitmap does not contain a set bit that corresponds
+	 * to our AID, it could mean a variety of things depending on if
+	 * the encoding mode is inverted or not.
+	 *
+	 * 1. If inverted, it means the entire subblock is present and hence
+	 *    our AID has been set.
+	 * 2. If not inverted, it means our subblock is not present and hence
+	 *    it is all zero meaning our AID is not set.
+	 */
+	if (!(blkmap & BIT(aid->target_subblk)))
+		return enc->inverse;
+
+	/*
+	 * Increment ptr by the number of set subblocks that appear before our
+	 * target subblock. If our target subblock is 0, do nothing as ptr
+	 * already points to our target subblock.
+	 */
+	if (aid->target_subblk)
+		ptr += hweight8(blkmap & GENMASK(aid->target_subblk - 1, 0));
+
+	return !!(*ptr & BIT(aid->target_subblk_bit)) ^ enc->inverse;
+}
+
+static inline bool ieee80211_s1g_parse_single(struct s1g_tim_enc_block *enc,
+					      struct s1g_tim_aid *aid)
+{
+	/*
+	 * Single AID mode describes, as the name suggests, a single AID
+	 * within the block described by the encoded block. The octet
+	 * contains the 6 LSBs of the AID described in the block. The other
+	 * 2 bits are reserved. When inversed, every single AID described
+	 * by the current block have buffered traffic except for the AID
+	 * described in the single AID octet.
+	 */
+	return ((*enc->ptr & 0x3f) == (aid->aid & 0x3f)) ^ enc->inverse;
+}
+
+static inline bool ieee80211_s1g_parse_olb(struct s1g_tim_enc_block *enc,
+					   struct s1g_tim_aid *aid)
+{
+	const u8 *ptr = enc->ptr;
+	u8 blk_len = *ptr++;
+	/*
+	 * Given an OLB encoded block that describes multiple blocks,
+	 * calculate the offset into the span. Then calculate the
+	 * subblock location normally.
+	 */
+	u16 span_offset = aid->target_blk - enc->olb_blk_offset;
+	u16 subblk_idx = span_offset * 8 + aid->target_subblk;
+
+	if (subblk_idx >= blk_len)
+		return enc->inverse;
+
+	return !!(ptr[subblk_idx] & BIT(aid->target_subblk_bit)) ^ enc->inverse;
+}
+
+/*
+ * An S1G PVB has 3 non optional encoding types, each that can be inverted.
+ * An S1G PVB is constructed with zero or more encoded block subfields. Each
+ * encoded block represents a single "block" of AIDs (64), and each encoded
+ * block can contain one of the 3 encoding types alongside a single bit for
+ * whether the bits should be inverted.
+ *
+ * As the standard makes no guarantee about the ordering of encoded blocks,
+ * we must parse every encoded block in the worst case scenario given an
+ * AID that lies within the last block.
+ */
+static inline bool ieee80211_s1g_check_tim(const struct ieee80211_tim_ie *tim,
+					   u8 tim_len, u16 aid)
+{
+	int err;
+	struct s1g_tim_aid target_aid;
+	struct s1g_tim_enc_block enc_blk;
+
+	if (tim_len < 3)
+		return false;
+
+	target_aid.aid = aid;
+	target_aid.target_blk = (aid >> 6) & 0x1f;
+	target_aid.target_subblk = (aid >> 3) & 0x7;
+	target_aid.target_subblk_bit = aid & 0x7;
+
+	/*
+	 * Find our AIDs target encoded block and fill &enc_blk with the
+	 * encoded blocks information. If no entry is found or an error
+	 * occurs return false.
+	 */
+	err = ieee80211_s1g_find_target_block(&enc_blk, &target_aid,
+					      tim->virtual_map,
+					      (const u8 *)tim + tim_len + 2);
+	if (err)
+		return false;
+
+	switch (enc_blk.enc_mode) {
+	case IEEE80211_S1G_TIM_ENC_MODE_BLOCK:
+		return ieee80211_s1g_parse_bitmap(&enc_blk, &target_aid);
+	case IEEE80211_S1G_TIM_ENC_MODE_SINGLE:
+		return ieee80211_s1g_parse_single(&enc_blk, &target_aid);
+	case IEEE80211_S1G_TIM_ENC_MODE_OLB:
+		return ieee80211_s1g_parse_olb(&enc_blk, &target_aid);
+	default:
+		return false;
+	}
+}
+
+#endif /* LINUX_IEEE80211_H */
diff --git a/include/linux/ieee80211-vht.h b/include/linux/ieee80211-vht.h
new file mode 100644
index 000000000000..898dfb561fef
--- /dev/null
+++ b/include/linux/ieee80211-vht.h
@@ -0,0 +1,236 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * IEEE 802.11 VHT definitions
+ *
+ * Copyright (c) 2001-2002, SSH Communications Security Corp and Jouni Malinen
+ * <jkmaline@cc.hut.fi>
+ * Copyright (c) 2002-2003, Jouni Malinen <jkmaline@cc.hut.fi>
+ * Copyright (c) 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
+ * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
+ * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
+ * Copyright (c) 2018 - 2025 Intel Corporation
+ */
+
+#ifndef LINUX_IEEE80211_VHT_H
+#define LINUX_IEEE80211_VHT_H
+
+#include <linux/types.h>
+#include <linux/if_ether.h>
+
+#define IEEE80211_MAX_MPDU_LEN_VHT_3895		3895
+#define IEEE80211_MAX_MPDU_LEN_VHT_7991		7991
+#define IEEE80211_MAX_MPDU_LEN_VHT_11454	11454
+
+/**
+ * enum ieee80211_vht_opmode_bits - VHT operating mode field bits
+ * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask
+ * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width
+ * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width
+ * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width
+ * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width
+ * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag
+ * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask
+ *	(the NSS value is the value of this field + 1)
+ * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift
+ * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU
+ *	using a beamforming steering matrix
+ */
+enum ieee80211_vht_opmode_bits {
+	IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK	= 0x03,
+	IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ	= 0,
+	IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ	= 1,
+	IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ	= 2,
+	IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ	= 3,
+	IEEE80211_OPMODE_NOTIF_BW_160_80P80	= 0x04,
+	IEEE80211_OPMODE_NOTIF_RX_NSS_MASK	= 0x70,
+	IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT	= 4,
+	IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF	= 0x80,
+};
+
+/*
+ * Maximum length of AMPDU that the STA can receive in VHT.
+ * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets)
+ */
+enum ieee80211_vht_max_ampdu_length_exp {
+	IEEE80211_VHT_MAX_AMPDU_8K = 0,
+	IEEE80211_VHT_MAX_AMPDU_16K = 1,
+	IEEE80211_VHT_MAX_AMPDU_32K = 2,
+	IEEE80211_VHT_MAX_AMPDU_64K = 3,
+	IEEE80211_VHT_MAX_AMPDU_128K = 4,
+	IEEE80211_VHT_MAX_AMPDU_256K = 5,
+	IEEE80211_VHT_MAX_AMPDU_512K = 6,
+	IEEE80211_VHT_MAX_AMPDU_1024K = 7
+};
+
+/**
+ * struct ieee80211_vht_mcs_info - VHT MCS information
+ * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams
+ * @rx_highest: Indicates highest long GI VHT PPDU data rate
+ *	STA can receive. Rate expressed in units of 1 Mbps.
+ *	If this field is 0 this value should not be used to
+ *	consider the highest RX data rate supported.
+ *	The top 3 bits of this field indicate the Maximum NSTS,total
+ *	(a beamformee capability.)
+ * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams
+ * @tx_highest: Indicates highest long GI VHT PPDU data rate
+ *	STA can transmit. Rate expressed in units of 1 Mbps.
+ *	If this field is 0 this value should not be used to
+ *	consider the highest TX data rate supported.
+ *	The top 2 bits of this field are reserved, the
+ *	3rd bit from the top indiciates VHT Extended NSS BW
+ *	Capability.
+ */
+struct ieee80211_vht_mcs_info {
+	__le16 rx_mcs_map;
+	__le16 rx_highest;
+	__le16 tx_mcs_map;
+	__le16 tx_highest;
+} __packed;
+
+/* for rx_highest */
+#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT	13
+#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK	(7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT)
+
+/* for tx_highest */
+#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE	(1 << 13)
+
+/**
+ * enum ieee80211_vht_mcs_support - VHT MCS support definitions
+ * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
+ *	number of streams
+ * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported
+ * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported
+ * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported
+ *
+ * These definitions are used in each 2-bit subfield of the @rx_mcs_map
+ * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are
+ * both split into 8 subfields by number of streams. These values indicate
+ * which MCSes are supported for the number of streams the value appears
+ * for.
+ */
+enum ieee80211_vht_mcs_support {
+	IEEE80211_VHT_MCS_SUPPORT_0_7	= 0,
+	IEEE80211_VHT_MCS_SUPPORT_0_8	= 1,
+	IEEE80211_VHT_MCS_SUPPORT_0_9	= 2,
+	IEEE80211_VHT_MCS_NOT_SUPPORTED	= 3,
+};
+
+/**
+ * struct ieee80211_vht_cap - VHT capabilities
+ *
+ * This structure is the "VHT capabilities element" as
+ * described in 802.11ac D3.0 8.4.2.160
+ * @vht_cap_info: VHT capability info
+ * @supp_mcs: VHT MCS supported rates
+ */
+struct ieee80211_vht_cap {
+	__le32 vht_cap_info;
+	struct ieee80211_vht_mcs_info supp_mcs;
+} __packed;
+
+/**
+ * enum ieee80211_vht_chanwidth - VHT channel width
+ * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to
+ *	determine the channel width (20 or 40 MHz)
+ * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth
+ * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth
+ * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth
+ */
+enum ieee80211_vht_chanwidth {
+	IEEE80211_VHT_CHANWIDTH_USE_HT		= 0,
+	IEEE80211_VHT_CHANWIDTH_80MHZ		= 1,
+	IEEE80211_VHT_CHANWIDTH_160MHZ		= 2,
+	IEEE80211_VHT_CHANWIDTH_80P80MHZ	= 3,
+};
+
+/**
+ * struct ieee80211_vht_operation - VHT operation IE
+ *
+ * This structure is the "VHT operation element" as
+ * described in 802.11ac D3.0 8.4.2.161
+ * @chan_width: Operating channel width
+ * @center_freq_seg0_idx: center freq segment 0 index
+ * @center_freq_seg1_idx: center freq segment 1 index
+ * @basic_mcs_set: VHT Basic MCS rate set
+ */
+struct ieee80211_vht_operation {
+	u8 chan_width;
+	u8 center_freq_seg0_idx;
+	u8 center_freq_seg1_idx;
+	__le16 basic_mcs_set;
+} __packed;
+
+/* 802.11ac VHT Capabilities */
+#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895			0x00000000
+#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991			0x00000001
+#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454			0x00000002
+#define IEEE80211_VHT_CAP_MAX_MPDU_MASK				0x00000003
+#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ		0x00000004
+#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ	0x00000008
+#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK			0x0000000C
+#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT			2
+#define IEEE80211_VHT_CAP_RXLDPC				0x00000010
+#define IEEE80211_VHT_CAP_SHORT_GI_80				0x00000020
+#define IEEE80211_VHT_CAP_SHORT_GI_160				0x00000040
+#define IEEE80211_VHT_CAP_TXSTBC				0x00000080
+#define IEEE80211_VHT_CAP_RXSTBC_1				0x00000100
+#define IEEE80211_VHT_CAP_RXSTBC_2				0x00000200
+#define IEEE80211_VHT_CAP_RXSTBC_3				0x00000300
+#define IEEE80211_VHT_CAP_RXSTBC_4				0x00000400
+#define IEEE80211_VHT_CAP_RXSTBC_MASK				0x00000700
+#define IEEE80211_VHT_CAP_RXSTBC_SHIFT				8
+#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE			0x00000800
+#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE			0x00001000
+#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT                  13
+#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK			\
+		(7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT)
+#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT		16
+#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK		\
+		(7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT)
+#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE			0x00080000
+#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE			0x00100000
+#define IEEE80211_VHT_CAP_VHT_TXOP_PS				0x00200000
+#define IEEE80211_VHT_CAP_HTC_VHT				0x00400000
+#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT	23
+#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK	\
+		(7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT)
+#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB	0x08000000
+#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB	0x0c000000
+#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN			0x10000000
+#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN			0x20000000
+#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT			30
+#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK			0xc0000000
+
+/**
+ * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS
+ * @cap: VHT capabilities of the peer
+ * @bw: bandwidth to use
+ * @mcs: MCS index to use
+ * @ext_nss_bw_capable: indicates whether or not the local transmitter
+ *	(rate scaling algorithm) can deal with the new logic
+ *	(dot11VHTExtendedNSSBWCapable)
+ * @max_vht_nss: current maximum NSS as advertised by the STA in
+ *	operating mode notification, can be 0 in which case the
+ *	capability data will be used to derive this (from MCS support)
+ * Return: The maximum NSS that can be used for the given bandwidth/MCS
+ *	combination
+ *
+ * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can
+ * vary for a given BW/MCS. This function parses the data.
+ *
+ * Note: This function is exported by cfg80211.
+ */
+int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap,
+			      enum ieee80211_vht_chanwidth bw,
+			      int mcs, bool ext_nss_bw_capable,
+			      unsigned int max_vht_nss);
+
+/* VHT action codes */
+enum ieee80211_vht_actioncode {
+	WLAN_VHT_ACTION_COMPRESSED_BF = 0,
+	WLAN_VHT_ACTION_GROUPID_MGMT = 1,
+	WLAN_VHT_ACTION_OPMODE_NOTIF = 2,
+};
+
+#endif /* LINUX_IEEE80211_VHT_H */
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index c4cf296e7eaf..96439de55f07 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -9,7 +9,7 @@
  * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
  * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright (c) 2018 - 2023 Intel Corporation
+ * Copyright (c) 2018 - 2025 Intel Corporation
  */
 
 #ifndef LINUX_IEEE80211_H
@@ -20,7 +20,7 @@
 #include <linux/etherdevice.h>
 #include <linux/bitfield.h>
 #include <asm/byteorder.h>
-#include <asm/unaligned.h>
+#include <linux/unaligned.h>
 
 /*
  * DS bit usage
@@ -43,6 +43,7 @@
 #define IEEE80211_FCTL_VERS		0x0003
 #define IEEE80211_FCTL_FTYPE		0x000c
 #define IEEE80211_FCTL_STYPE		0x00f0
+#define IEEE80211_FCTL_TYPE		(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)
 #define IEEE80211_FCTL_TODS		0x0100
 #define IEEE80211_FCTL_FROMDS		0x0200
 #define IEEE80211_FCTL_MOREFRAGS	0x0400
@@ -109,15 +110,6 @@
 #define IEEE80211_STYPE_DMG_BEACON		0x0000
 #define IEEE80211_STYPE_S1G_BEACON		0x0010
 
-/* bits unique to S1G beacon */
-#define IEEE80211_S1G_BCN_NEXT_TBTT	0x100
-
-/* see 802.11ah-2016 9.9 NDP CMAC frames */
-#define IEEE80211_S1G_1MHZ_NDP_BITS	25
-#define IEEE80211_S1G_1MHZ_NDP_BYTES	4
-#define IEEE80211_S1G_2MHZ_NDP_BITS	37
-#define IEEE80211_S1G_2MHZ_NDP_BYTES	5
-
 #define IEEE80211_NDP_FTYPE_CTS			0
 #define IEEE80211_NDP_FTYPE_CF_END		0
 #define IEEE80211_NDP_FTYPE_PS_POLL		1
@@ -153,9 +145,6 @@
 
 #define IEEE80211_ANO_NETTYPE_WILD              15
 
-/* bits unique to S1G beacon */
-#define IEEE80211_S1G_BCN_NEXT_TBTT    0x100
-
 /* control extension - for IEEE80211_FTYPE_CTL | IEEE80211_STYPE_CTL_EXT */
 #define IEEE80211_CTL_EXT_POLL		0x2000
 #define IEEE80211_CTL_EXT_SPR		0x3000
@@ -172,11 +161,11 @@
 #define IEEE80211_SN_MODULO		(IEEE80211_MAX_SN + 1)
 
 
-/* PV1 Layout 11ah 9.8.3.1 */
+/* PV1 Layout IEEE 802.11-2020 9.8.3.1 */
 #define IEEE80211_PV1_FCTL_VERS		0x0003
 #define IEEE80211_PV1_FCTL_FTYPE	0x001c
 #define IEEE80211_PV1_FCTL_STYPE	0x00e0
-#define IEEE80211_PV1_FCTL_TODS		0x0100
+#define IEEE80211_PV1_FCTL_FROMDS		0x0100
 #define IEEE80211_PV1_FCTL_MOREFRAGS	0x0200
 #define IEEE80211_PV1_FCTL_PM		0x0400
 #define IEEE80211_PV1_FCTL_MOREDATA	0x0800
@@ -191,6 +180,11 @@ static inline bool ieee80211_sn_less(u16 sn1, u16 sn2)
 	return ((sn1 - sn2) & IEEE80211_SN_MASK) > (IEEE80211_SN_MODULO >> 1);
 }
 
+static inline bool ieee80211_sn_less_eq(u16 sn1, u16 sn2)
+{
+	return ((sn2 - sn1) & IEEE80211_SN_MASK) <= (IEEE80211_SN_MODULO >> 1);
+}
+
 static inline u16 ieee80211_sn_add(u16 sn1, u16 sn2)
 {
 	return (sn1 + sn2) & IEEE80211_SN_MASK;
@@ -216,6 +210,7 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 #define IEEE80211_MAX_AID_S1G		8191
 #define IEEE80211_MAX_TIM_LEN		251
 #define IEEE80211_MAX_MESH_PEERINGS	63
+
 /* Maximum size for the MA-UNITDATA primitive, 802.11 standard section
    6.2.1.1.2.
 
@@ -229,21 +224,8 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 /* 30 byte 4 addr hdr, 2 byte QoS, 2304 byte MSDU, 12 byte crypt, 4 byte FCS */
 #define IEEE80211_MAX_FRAME_LEN		2352
 
-/* Maximal size of an A-MSDU that can be transported in a HT BA session */
-#define IEEE80211_MAX_MPDU_LEN_HT_BA		4095
-
-/* Maximal size of an A-MSDU */
-#define IEEE80211_MAX_MPDU_LEN_HT_3839		3839
-#define IEEE80211_MAX_MPDU_LEN_HT_7935		7935
-
-#define IEEE80211_MAX_MPDU_LEN_VHT_3895		3895
-#define IEEE80211_MAX_MPDU_LEN_VHT_7991		7991
-#define IEEE80211_MAX_MPDU_LEN_VHT_11454	11454
-
 #define IEEE80211_MAX_SSID_LEN		32
 
-#define IEEE80211_MAX_MESH_ID_LEN	32
-
 #define IEEE80211_FIRST_TSPEC_TSID	8
 #define IEEE80211_NUM_TIDS		16
 
@@ -294,8 +276,6 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_MASK	0x03
 #define IEEE80211_WMM_IE_STA_QOSINFO_SP_SHIFT	5
 
-#define IEEE80211_HT_CTL_LEN		4
-
 /* trigger type within common_info of trigger frame */
 #define IEEE80211_TRIGGER_TYPE_MASK		0xf
 #define IEEE80211_TRIGGER_TYPE_BASIC		0x0
@@ -307,6 +287,13 @@ static inline u16 ieee80211_sn_sub(u16 sn1, u16 sn2)
 #define IEEE80211_TRIGGER_TYPE_BQRP		0x6
 #define IEEE80211_TRIGGER_TYPE_NFRP		0x7
 
+/* UL-bandwidth within common_info of trigger frame */
+#define IEEE80211_TRIGGER_ULBW_MASK		0xc0000
+#define IEEE80211_TRIGGER_ULBW_20MHZ		0x0
+#define IEEE80211_TRIGGER_ULBW_40MHZ		0x1
+#define IEEE80211_TRIGGER_ULBW_80MHZ		0x2
+#define IEEE80211_TRIGGER_ULBW_160_80P80MHZ	0x3
+
 struct ieee80211_hdr {
 	__le16 frame_control;
 	__le16 duration_id;
@@ -361,6 +348,7 @@ struct ieee80211_trigger {
 /**
  * ieee80211_has_tods - check if IEEE80211_FCTL_TODS is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame has to-DS set
  */
 static inline bool ieee80211_has_tods(__le16 fc)
 {
@@ -370,6 +358,7 @@ static inline bool ieee80211_has_tods(__le16 fc)
 /**
  * ieee80211_has_fromds - check if IEEE80211_FCTL_FROMDS is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame has from-DS set
  */
 static inline bool ieee80211_has_fromds(__le16 fc)
 {
@@ -379,6 +368,7 @@ static inline bool ieee80211_has_fromds(__le16 fc)
 /**
  * ieee80211_has_a4 - check if IEEE80211_FCTL_TODS and IEEE80211_FCTL_FROMDS are set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not it's a 4-address frame (from-DS and to-DS set)
  */
 static inline bool ieee80211_has_a4(__le16 fc)
 {
@@ -389,6 +379,7 @@ static inline bool ieee80211_has_a4(__le16 fc)
 /**
  * ieee80211_has_morefrags - check if IEEE80211_FCTL_MOREFRAGS is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame has more fragments (more frags bit set)
  */
 static inline bool ieee80211_has_morefrags(__le16 fc)
 {
@@ -398,6 +389,7 @@ static inline bool ieee80211_has_morefrags(__le16 fc)
 /**
  * ieee80211_has_retry - check if IEEE80211_FCTL_RETRY is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the retry flag is set
  */
 static inline bool ieee80211_has_retry(__le16 fc)
 {
@@ -407,6 +399,7 @@ static inline bool ieee80211_has_retry(__le16 fc)
 /**
  * ieee80211_has_pm - check if IEEE80211_FCTL_PM is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the power management flag is set
  */
 static inline bool ieee80211_has_pm(__le16 fc)
 {
@@ -416,6 +409,7 @@ static inline bool ieee80211_has_pm(__le16 fc)
 /**
  * ieee80211_has_moredata - check if IEEE80211_FCTL_MOREDATA is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the more data flag is set
  */
 static inline bool ieee80211_has_moredata(__le16 fc)
 {
@@ -425,6 +419,7 @@ static inline bool ieee80211_has_moredata(__le16 fc)
 /**
  * ieee80211_has_protected - check if IEEE80211_FCTL_PROTECTED is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the protected flag is set
  */
 static inline bool ieee80211_has_protected(__le16 fc)
 {
@@ -434,6 +429,7 @@ static inline bool ieee80211_has_protected(__le16 fc)
 /**
  * ieee80211_has_order - check if IEEE80211_FCTL_ORDER is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the order flag is set
  */
 static inline bool ieee80211_has_order(__le16 fc)
 {
@@ -443,6 +439,7 @@ static inline bool ieee80211_has_order(__le16 fc)
 /**
  * ieee80211_is_mgmt - check if type is IEEE80211_FTYPE_MGMT
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame type is management
  */
 static inline bool ieee80211_is_mgmt(__le16 fc)
 {
@@ -453,6 +450,7 @@ static inline bool ieee80211_is_mgmt(__le16 fc)
 /**
  * ieee80211_is_ctl - check if type is IEEE80211_FTYPE_CTL
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame type is control
  */
 static inline bool ieee80211_is_ctl(__le16 fc)
 {
@@ -463,6 +461,7 @@ static inline bool ieee80211_is_ctl(__le16 fc)
 /**
  * ieee80211_is_data - check if type is IEEE80211_FTYPE_DATA
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a data frame
  */
 static inline bool ieee80211_is_data(__le16 fc)
 {
@@ -473,6 +472,7 @@ static inline bool ieee80211_is_data(__le16 fc)
 /**
  * ieee80211_is_ext - check if type is IEEE80211_FTYPE_EXT
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame type is extended
  */
 static inline bool ieee80211_is_ext(__le16 fc)
 {
@@ -484,6 +484,7 @@ static inline bool ieee80211_is_ext(__le16 fc)
 /**
  * ieee80211_is_data_qos - check if type is IEEE80211_FTYPE_DATA and IEEE80211_STYPE_QOS_DATA is set
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a QoS data frame
  */
 static inline bool ieee80211_is_data_qos(__le16 fc)
 {
@@ -498,6 +499,8 @@ static inline bool ieee80211_is_data_qos(__le16 fc)
 /**
  * ieee80211_is_data_present - check if type is IEEE80211_FTYPE_DATA and has data
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a QoS data frame that has data
+ *	(i.e. is not null data)
  */
 static inline bool ieee80211_is_data_present(__le16 fc)
 {
@@ -512,6 +515,7 @@ static inline bool ieee80211_is_data_present(__le16 fc)
 /**
  * ieee80211_is_assoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an association request
  */
 static inline bool ieee80211_is_assoc_req(__le16 fc)
 {
@@ -522,6 +526,7 @@ static inline bool ieee80211_is_assoc_req(__le16 fc)
 /**
  * ieee80211_is_assoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ASSOC_RESP
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an association response
  */
 static inline bool ieee80211_is_assoc_resp(__le16 fc)
 {
@@ -532,6 +537,7 @@ static inline bool ieee80211_is_assoc_resp(__le16 fc)
 /**
  * ieee80211_is_reassoc_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a reassociation request
  */
 static inline bool ieee80211_is_reassoc_req(__le16 fc)
 {
@@ -542,6 +548,7 @@ static inline bool ieee80211_is_reassoc_req(__le16 fc)
 /**
  * ieee80211_is_reassoc_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_REASSOC_RESP
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a reassociation response
  */
 static inline bool ieee80211_is_reassoc_resp(__le16 fc)
 {
@@ -552,6 +559,7 @@ static inline bool ieee80211_is_reassoc_resp(__le16 fc)
 /**
  * ieee80211_is_probe_req - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a probe request
  */
 static inline bool ieee80211_is_probe_req(__le16 fc)
 {
@@ -562,6 +570,7 @@ static inline bool ieee80211_is_probe_req(__le16 fc)
 /**
  * ieee80211_is_probe_resp - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_PROBE_RESP
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a probe response
  */
 static inline bool ieee80211_is_probe_resp(__le16 fc)
 {
@@ -572,6 +581,7 @@ static inline bool ieee80211_is_probe_resp(__le16 fc)
 /**
  * ieee80211_is_beacon - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_BEACON
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a (regular, not S1G) beacon
  */
 static inline bool ieee80211_is_beacon(__le16 fc)
 {
@@ -580,42 +590,9 @@ static inline bool ieee80211_is_beacon(__le16 fc)
 }
 
 /**
- * ieee80211_is_s1g_beacon - check if IEEE80211_FTYPE_EXT &&
- * IEEE80211_STYPE_S1G_BEACON
- * @fc: frame control bytes in little-endian byteorder
- */
-static inline bool ieee80211_is_s1g_beacon(__le16 fc)
-{
-	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE |
-				 IEEE80211_FCTL_STYPE)) ==
-	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON);
-}
-
-/**
- * ieee80211_next_tbtt_present - check if IEEE80211_FTYPE_EXT &&
- * IEEE80211_STYPE_S1G_BEACON && IEEE80211_S1G_BCN_NEXT_TBTT
- * @fc: frame control bytes in little-endian byteorder
- */
-static inline bool ieee80211_next_tbtt_present(__le16 fc)
-{
-	return (fc & cpu_to_le16(IEEE80211_FCTL_FTYPE | IEEE80211_FCTL_STYPE)) ==
-	       cpu_to_le16(IEEE80211_FTYPE_EXT | IEEE80211_STYPE_S1G_BEACON) &&
-	       fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT);
-}
-
-/**
- * ieee80211_is_s1g_short_beacon - check if next tbtt present bit is set. Only
- * true for S1G beacons when they're short.
- * @fc: frame control bytes in little-endian byteorder
- */
-static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
-{
-	return ieee80211_is_s1g_beacon(fc) && ieee80211_next_tbtt_present(fc);
-}
-
-/**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an ATIM frame
  */
 static inline bool ieee80211_is_atim(__le16 fc)
 {
@@ -626,6 +603,7 @@ static inline bool ieee80211_is_atim(__le16 fc)
 /**
  * ieee80211_is_disassoc - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DISASSOC
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a disassociation frame
  */
 static inline bool ieee80211_is_disassoc(__le16 fc)
 {
@@ -636,6 +614,7 @@ static inline bool ieee80211_is_disassoc(__le16 fc)
 /**
  * ieee80211_is_auth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_AUTH
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an authentication frame
  */
 static inline bool ieee80211_is_auth(__le16 fc)
 {
@@ -646,6 +625,7 @@ static inline bool ieee80211_is_auth(__le16 fc)
 /**
  * ieee80211_is_deauth - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_DEAUTH
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a deauthentication frame
  */
 static inline bool ieee80211_is_deauth(__le16 fc)
 {
@@ -656,6 +636,7 @@ static inline bool ieee80211_is_deauth(__le16 fc)
 /**
  * ieee80211_is_action - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ACTION
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an action frame
  */
 static inline bool ieee80211_is_action(__le16 fc)
 {
@@ -666,6 +647,7 @@ static inline bool ieee80211_is_action(__le16 fc)
 /**
  * ieee80211_is_back_req - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK_REQ
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a block-ACK request frame
  */
 static inline bool ieee80211_is_back_req(__le16 fc)
 {
@@ -676,6 +658,7 @@ static inline bool ieee80211_is_back_req(__le16 fc)
 /**
  * ieee80211_is_back - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_BACK
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a block-ACK frame
  */
 static inline bool ieee80211_is_back(__le16 fc)
 {
@@ -686,6 +669,7 @@ static inline bool ieee80211_is_back(__le16 fc)
 /**
  * ieee80211_is_pspoll - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_PSPOLL
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a PS-poll frame
  */
 static inline bool ieee80211_is_pspoll(__le16 fc)
 {
@@ -696,6 +680,7 @@ static inline bool ieee80211_is_pspoll(__le16 fc)
 /**
  * ieee80211_is_rts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_RTS
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an RTS frame
  */
 static inline bool ieee80211_is_rts(__le16 fc)
 {
@@ -706,6 +691,7 @@ static inline bool ieee80211_is_rts(__le16 fc)
 /**
  * ieee80211_is_cts - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CTS
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a CTS frame
  */
 static inline bool ieee80211_is_cts(__le16 fc)
 {
@@ -716,6 +702,7 @@ static inline bool ieee80211_is_cts(__le16 fc)
 /**
  * ieee80211_is_ack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_ACK
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is an ACK frame
  */
 static inline bool ieee80211_is_ack(__le16 fc)
 {
@@ -726,6 +713,7 @@ static inline bool ieee80211_is_ack(__le16 fc)
 /**
  * ieee80211_is_cfend - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFEND
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a CF-end frame
  */
 static inline bool ieee80211_is_cfend(__le16 fc)
 {
@@ -736,6 +724,7 @@ static inline bool ieee80211_is_cfend(__le16 fc)
 /**
  * ieee80211_is_cfendack - check if IEEE80211_FTYPE_CTL && IEEE80211_STYPE_CFENDACK
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a CF-end-ack frame
  */
 static inline bool ieee80211_is_cfendack(__le16 fc)
 {
@@ -746,6 +735,7 @@ static inline bool ieee80211_is_cfendack(__le16 fc)
 /**
  * ieee80211_is_nullfunc - check if frame is a regular (non-QoS) nullfunc frame
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a nullfunc frame
  */
 static inline bool ieee80211_is_nullfunc(__le16 fc)
 {
@@ -756,6 +746,7 @@ static inline bool ieee80211_is_nullfunc(__le16 fc)
 /**
  * ieee80211_is_qos_nullfunc - check if frame is a QoS nullfunc frame
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a QoS nullfunc frame
  */
 static inline bool ieee80211_is_qos_nullfunc(__le16 fc)
 {
@@ -766,6 +757,7 @@ static inline bool ieee80211_is_qos_nullfunc(__le16 fc)
 /**
  * ieee80211_is_trigger - check if frame is trigger frame
  * @fc: frame control field in little-endian byteorder
+ * Return: whether or not the frame is a trigger frame
  */
 static inline bool ieee80211_is_trigger(__le16 fc)
 {
@@ -776,6 +768,7 @@ static inline bool ieee80211_is_trigger(__le16 fc)
 /**
  * ieee80211_is_any_nullfunc - check if frame is regular or QoS nullfunc frame
  * @fc: frame control bytes in little-endian byteorder
+ * Return: whether or not the frame is a nullfunc or QoS nullfunc frame
  */
 static inline bool ieee80211_is_any_nullfunc(__le16 fc)
 {
@@ -785,6 +778,8 @@ static inline bool ieee80211_is_any_nullfunc(__le16 fc)
 /**
  * ieee80211_is_first_frag - check if IEEE80211_SCTL_FRAG is not set
  * @seq_ctrl: frame sequence control bytes in little-endian byteorder
+ * Return: whether or not the frame is the first fragment (also true if
+ *	it's not fragmented at all)
  */
 static inline bool ieee80211_is_first_frag(__le16 seq_ctrl)
 {
@@ -794,6 +789,7 @@ static inline bool ieee80211_is_first_frag(__le16 seq_ctrl)
 /**
  * ieee80211_is_frag - check if a frame is a fragment
  * @hdr: 802.11 header of the frame
+ * Return: whether or not the frame is a fragment
  */
 static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr)
 {
@@ -801,44 +797,20 @@ static inline bool ieee80211_is_frag(struct ieee80211_hdr *hdr)
 	       hdr->seq_ctrl & cpu_to_le16(IEEE80211_SCTL_FRAG);
 }
 
-struct ieee80211s_hdr {
-	u8 flags;
-	u8 ttl;
-	__le32 seqnum;
-	u8 eaddr1[ETH_ALEN];
-	u8 eaddr2[ETH_ALEN];
-} __packed __aligned(2);
-
-/* Mesh flags */
-#define MESH_FLAGS_AE_A4 	0x1
-#define MESH_FLAGS_AE_A5_A6	0x2
-#define MESH_FLAGS_AE		0x3
-#define MESH_FLAGS_PS_DEEP	0x4
-
-/**
- * enum ieee80211_preq_flags - mesh PREQ element flags
- *
- * @IEEE80211_PREQ_PROACTIVE_PREP_FLAG: proactive PREP subfield
- */
-enum ieee80211_preq_flags {
-	IEEE80211_PREQ_PROACTIVE_PREP_FLAG	= 1<<2,
-};
-
-/**
- * enum ieee80211_preq_target_flags - mesh PREQ element per target flags
- *
- * @IEEE80211_PREQ_TO_FLAG: target only subfield
- * @IEEE80211_PREQ_USN_FLAG: unknown target HWMP sequence number subfield
- */
-enum ieee80211_preq_target_flags {
-	IEEE80211_PREQ_TO_FLAG	= 1<<0,
-	IEEE80211_PREQ_USN_FLAG	= 1<<2,
-};
+static inline u16 ieee80211_get_sn(struct ieee80211_hdr *hdr)
+{
+	return le16_get_bits(hdr->seq_ctrl, IEEE80211_SCTL_SEQ);
+}
 
 /**
- * struct ieee80211_quiet_ie
+ * struct ieee80211_quiet_ie - Quiet element
+ * @count: Quiet Count
+ * @period: Quiet Period
+ * @duration: Quiet Duration
+ * @offset: Quiet Offset
  *
- * This structure refers to "Quiet information element"
+ * This structure represents the payload of the "Quiet element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.22.
  */
 struct ieee80211_quiet_ie {
 	u8 count;
@@ -848,9 +820,15 @@ struct ieee80211_quiet_ie {
 } __packed;
 
 /**
- * struct ieee80211_msrment_ie
+ * struct ieee80211_msrment_ie - Measurement element
+ * @token: Measurement Token
+ * @mode: Measurement Report Mode
+ * @type: Measurement Type
+ * @request: Measurement Request or Measurement Report
  *
- * This structure refers to "Measurement Request/Report information element"
+ * This structure represents the payload of both the "Measurement
+ * Request element" and the "Measurement Report element" as described
+ * in IEEE Std 802.11-2020 sections 9.4.2.20 and 9.4.2.21.
  */
 struct ieee80211_msrment_ie {
 	u8 token;
@@ -860,9 +838,14 @@ struct ieee80211_msrment_ie {
 } __packed;
 
 /**
- * struct ieee80211_channel_sw_ie
+ * struct ieee80211_channel_sw_ie - Channel Switch Announcement element
+ * @mode: Channel Switch Mode
+ * @new_ch_num: New Channel Number
+ * @count: Channel Switch Count
  *
- * This structure refers to "Channel Switch Announcement information element"
+ * This structure represents the payload of the "Channel Switch
+ * Announcement element" as described in IEEE Std 802.11-2020 section
+ * 9.4.2.18.
  */
 struct ieee80211_channel_sw_ie {
 	u8 mode;
@@ -871,9 +854,14 @@ struct ieee80211_channel_sw_ie {
 } __packed;
 
 /**
- * struct ieee80211_ext_chansw_ie
+ * struct ieee80211_ext_chansw_ie - Extended Channel Switch Announcement element
+ * @mode: Channel Switch Mode
+ * @new_operating_class: New Operating Class
+ * @new_ch_num: New Channel Number
+ * @count: Channel Switch Count
  *
- * This structure represents the "Extended Channel Switch Announcement element"
+ * This structure represents the "Extended Channel Switch Announcement
+ * element" as described in IEEE Std 802.11-2020 section 9.4.2.52.
  */
 struct ieee80211_ext_chansw_ie {
 	u8 mode;
@@ -893,19 +881,14 @@ struct ieee80211_sec_chan_offs_ie {
 } __packed;
 
 /**
- * struct ieee80211_mesh_chansw_params_ie - mesh channel switch parameters IE
- *
- * This structure represents the "Mesh Channel Switch Paramters element"
- */
-struct ieee80211_mesh_chansw_params_ie {
-	u8 mesh_ttl;
-	u8 mesh_flags;
-	__le16 mesh_reason;
-	__le16 mesh_pre_value;
-} __packed;
-
-/**
  * struct ieee80211_wide_bw_chansw_ie - wide bandwidth channel switch IE
+ * @new_channel_width: New Channel Width
+ * @new_center_freq_seg0: New Channel Center Frequency Segment 0
+ * @new_center_freq_seg1: New Channel Center Frequency Segment 1
+ *
+ * This structure represents the payload of the "Wide Bandwidth
+ * Channel Switch element" as described in IEEE Std 802.11-2020
+ * section 9.4.2.160.
  */
 struct ieee80211_wide_bw_chansw_ie {
 	u8 new_channel_width;
@@ -913,138 +896,41 @@ struct ieee80211_wide_bw_chansw_ie {
 } __packed;
 
 /**
- * struct ieee80211_tim
+ * struct ieee80211_tim_ie - Traffic Indication Map information element
+ * @dtim_count: DTIM Count
+ * @dtim_period: DTIM Period
+ * @bitmap_ctrl: Bitmap Control
+ * @required_octet: "Syntatic sugar" to force the struct size to the
+ *                  minimum valid size when carried in a non-S1G PPDU
+ * @virtual_map: Partial Virtual Bitmap
  *
- * This structure refers to "Traffic Indication Map information element"
+ * This structure represents the payload of the "TIM element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.5. Note that this
+ * definition is only applicable when the element is carried in a
+ * non-S1G PPDU. When the TIM is carried in an S1G PPDU, the Bitmap
+ * Control and Partial Virtual Bitmap may not be present.
  */
 struct ieee80211_tim_ie {
 	u8 dtim_count;
 	u8 dtim_period;
 	u8 bitmap_ctrl;
-	/* variable size: 1 - 251 bytes */
-	u8 virtual_map[1];
-} __packed;
-
-/**
- * struct ieee80211_meshconf_ie
- *
- * This structure refers to "Mesh Configuration information element"
- */
-struct ieee80211_meshconf_ie {
-	u8 meshconf_psel;
-	u8 meshconf_pmetric;
-	u8 meshconf_congest;
-	u8 meshconf_synch;
-	u8 meshconf_auth;
-	u8 meshconf_form;
-	u8 meshconf_cap;
-} __packed;
-
-/**
- * enum mesh_config_capab_flags - Mesh Configuration IE capability field flags
- *
- * @IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS: STA is willing to establish
- *	additional mesh peerings with other mesh STAs
- * @IEEE80211_MESHCONF_CAPAB_FORWARDING: the STA forwards MSDUs
- * @IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING: TBTT adjustment procedure
- *	is ongoing
- * @IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL: STA is in deep sleep mode or has
- *	neighbors in deep sleep mode
- */
-enum mesh_config_capab_flags {
-	IEEE80211_MESHCONF_CAPAB_ACCEPT_PLINKS		= 0x01,
-	IEEE80211_MESHCONF_CAPAB_FORWARDING		= 0x08,
-	IEEE80211_MESHCONF_CAPAB_TBTT_ADJUSTING		= 0x20,
-	IEEE80211_MESHCONF_CAPAB_POWER_SAVE_LEVEL	= 0x40,
-};
-
-#define IEEE80211_MESHCONF_FORM_CONNECTED_TO_GATE 0x1
-
-/**
- * mesh channel switch parameters element's flag indicator
- *
- */
-#define WLAN_EID_CHAN_SWITCH_PARAM_TX_RESTRICT BIT(0)
-#define WLAN_EID_CHAN_SWITCH_PARAM_INITIATOR BIT(1)
-#define WLAN_EID_CHAN_SWITCH_PARAM_REASON BIT(2)
-
-/**
- * struct ieee80211_rann_ie
- *
- * This structure refers to "Root Announcement information element"
- */
-struct ieee80211_rann_ie {
-	u8 rann_flags;
-	u8 rann_hopcount;
-	u8 rann_ttl;
-	u8 rann_addr[ETH_ALEN];
-	__le32 rann_seq;
-	__le32 rann_interval;
-	__le32 rann_metric;
+	union {
+		u8 required_octet;
+		DECLARE_FLEX_ARRAY(u8, virtual_map);
+	};
 } __packed;
 
-enum ieee80211_rann_flags {
-	RANN_FLAG_IS_GATE = 1 << 0,
-};
-
-enum ieee80211_ht_chanwidth_values {
-	IEEE80211_HT_CHANWIDTH_20MHZ = 0,
-	IEEE80211_HT_CHANWIDTH_ANY = 1,
-};
-
-/**
- * enum ieee80211_opmode_bits - VHT operating mode field bits
- * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK: channel width mask
- * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ: 20 MHz channel width
- * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ: 40 MHz channel width
- * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ: 80 MHz channel width
- * @IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ: 160 MHz or 80+80 MHz channel width
- * @IEEE80211_OPMODE_NOTIF_BW_160_80P80: 160 / 80+80 MHz indicator flag
- * @IEEE80211_OPMODE_NOTIF_RX_NSS_MASK: number of spatial streams mask
- *	(the NSS value is the value of this field + 1)
- * @IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT: number of spatial streams shift
- * @IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF: indicates streams in SU-MIMO PPDU
- *	using a beamforming steering matrix
- */
-enum ieee80211_vht_opmode_bits {
-	IEEE80211_OPMODE_NOTIF_CHANWIDTH_MASK	= 0x03,
-	IEEE80211_OPMODE_NOTIF_CHANWIDTH_20MHZ	= 0,
-	IEEE80211_OPMODE_NOTIF_CHANWIDTH_40MHZ	= 1,
-	IEEE80211_OPMODE_NOTIF_CHANWIDTH_80MHZ	= 2,
-	IEEE80211_OPMODE_NOTIF_CHANWIDTH_160MHZ	= 3,
-	IEEE80211_OPMODE_NOTIF_BW_160_80P80	= 0x04,
-	IEEE80211_OPMODE_NOTIF_RX_NSS_MASK	= 0x70,
-	IEEE80211_OPMODE_NOTIF_RX_NSS_SHIFT	= 4,
-	IEEE80211_OPMODE_NOTIF_RX_NSS_TYPE_BF	= 0x80,
-};
-
-/**
- * enum ieee80211_s1g_chanwidth
- * These are defined in IEEE802.11-2016ah Table 10-20
- * as BSS Channel Width
- *
- * @IEEE80211_S1G_CHANWIDTH_1MHZ: 1MHz operating channel
- * @IEEE80211_S1G_CHANWIDTH_2MHZ: 2MHz operating channel
- * @IEEE80211_S1G_CHANWIDTH_4MHZ: 4MHz operating channel
- * @IEEE80211_S1G_CHANWIDTH_8MHZ: 8MHz operating channel
- * @IEEE80211_S1G_CHANWIDTH_16MHZ: 16MHz operating channel
- */
-enum ieee80211_s1g_chanwidth {
-	IEEE80211_S1G_CHANWIDTH_1MHZ = 0,
-	IEEE80211_S1G_CHANWIDTH_2MHZ = 1,
-	IEEE80211_S1G_CHANWIDTH_4MHZ = 3,
-	IEEE80211_S1G_CHANWIDTH_8MHZ = 7,
-	IEEE80211_S1G_CHANWIDTH_16MHZ = 15,
-};
-
 #define WLAN_SA_QUERY_TR_ID_LEN 2
 #define WLAN_MEMBERSHIP_LEN 8
 #define WLAN_USER_POSITION_LEN 16
 
 /**
- * struct ieee80211_tpc_report_ie
+ * struct ieee80211_tpc_report_ie - TPC Report element
+ * @tx_power: Transmit Power
+ * @link_margin: Link Margin
  *
- * This structure refers to "TPC Report element"
+ * This structure represents the payload of the "TPC Report element" as
+ * described in IEEE Std 802.11-2020 section 9.4.2.16.
  */
 struct ieee80211_tpc_report_ie {
 	u8 tx_power;
@@ -1061,46 +947,6 @@ struct ieee80211_addba_ext_ie {
 	u8 data;
 } __packed;
 
-/**
- * struct ieee80211_s1g_bcn_compat_ie
- *
- * S1G Beacon Compatibility element
- */
-struct ieee80211_s1g_bcn_compat_ie {
-	__le16 compat_info;
-	__le16 beacon_int;
-	__le32 tsf_completion;
-} __packed;
-
-/**
- * struct ieee80211_s1g_oper_ie
- *
- * S1G Operation element
- */
-struct ieee80211_s1g_oper_ie {
-	u8 ch_width;
-	u8 oper_class;
-	u8 primary_ch;
-	u8 oper_ch;
-	__le16 basic_mcs_nss;
-} __packed;
-
-/**
- * struct ieee80211_aid_response_ie
- *
- * AID Response element
- */
-struct ieee80211_aid_response_ie {
-	__le16 aid;
-	u8 switch_count;
-	__le16 response_int;
-} __packed;
-
-struct ieee80211_s1g_cap {
-	u8 capab_info[10];
-	u8 supp_mcs_nss[5];
-} __packed;
-
 struct ieee80211_ext {
 	__le16 frame_control;
 	__le16 duration;
@@ -1109,58 +955,27 @@ struct ieee80211_ext {
 			u8 sa[ETH_ALEN];
 			__le32 timestamp;
 			u8 change_seq;
-			u8 variable[0];
+			u8 variable[];
 		} __packed s1g_beacon;
-		struct {
-			u8 sa[ETH_ALEN];
-			__le32 timestamp;
-			u8 change_seq;
-			u8 next_tbtt[3];
-			u8 variable[0];
-		} __packed s1g_short_beacon;
 	} u;
 } __packed __aligned(2);
 
-#define IEEE80211_TWT_CONTROL_NDP			BIT(0)
-#define IEEE80211_TWT_CONTROL_RESP_MODE			BIT(1)
-#define IEEE80211_TWT_CONTROL_NEG_TYPE_BROADCAST	BIT(3)
-#define IEEE80211_TWT_CONTROL_RX_DISABLED		BIT(4)
-#define IEEE80211_TWT_CONTROL_WAKE_DUR_UNIT		BIT(5)
-
-#define IEEE80211_TWT_REQTYPE_REQUEST			BIT(0)
-#define IEEE80211_TWT_REQTYPE_SETUP_CMD			GENMASK(3, 1)
-#define IEEE80211_TWT_REQTYPE_TRIGGER			BIT(4)
-#define IEEE80211_TWT_REQTYPE_IMPLICIT			BIT(5)
-#define IEEE80211_TWT_REQTYPE_FLOWTYPE			BIT(6)
-#define IEEE80211_TWT_REQTYPE_FLOWID			GENMASK(9, 7)
-#define IEEE80211_TWT_REQTYPE_WAKE_INT_EXP		GENMASK(14, 10)
-#define IEEE80211_TWT_REQTYPE_PROTECTION		BIT(15)
-
-enum ieee80211_twt_setup_cmd {
-	TWT_SETUP_CMD_REQUEST,
-	TWT_SETUP_CMD_SUGGEST,
-	TWT_SETUP_CMD_DEMAND,
-	TWT_SETUP_CMD_GROUPING,
-	TWT_SETUP_CMD_ACCEPT,
-	TWT_SETUP_CMD_ALTERNATE,
-	TWT_SETUP_CMD_DICTATE,
-	TWT_SETUP_CMD_REJECT,
-};
-
-struct ieee80211_twt_params {
-	__le16 req_type;
-	__le64 twt;
-	u8 min_twt_dur;
-	__le16 mantissa;
-	u8 channel;
-} __packed;
-
-struct ieee80211_twt_setup {
-	u8 dialog_token;
-	u8 element_id;
-	u8 length;
-	u8 control;
-	u8 params[];
+/**
+ * struct ieee80211_bss_load_elem - BSS Load elemen
+ *
+ * Defined in section 9.4.2.26 in IEEE 802.11-REVme D4.1
+ *
+ * @sta_count: total number of STAs currently associated with the AP.
+ * @channel_util: Percentage of time that the access point sensed the channel
+ *	was busy. This value is in range [0, 255], the highest value means
+ *	100% busy.
+ * @avail_admission_capa: remaining amount of medium time used for admission
+ *	control.
+ */
+struct ieee80211_bss_load_elem {
+	__le16 sta_count;
+	u8 channel_util;
+	__le16 avail_admission_capa;
 } __packed;
 
 struct ieee80211_mgmt {
@@ -1269,6 +1084,8 @@ struct ieee80211_mgmt {
 					__le16 status;
 					__le16 capab;
 					__le16 timeout;
+					/* followed by BA Extension */
+					u8 variable[];
 				} __packed addba_resp;
 				struct{
 					u8 action_code;
@@ -1299,7 +1116,7 @@ struct ieee80211_mgmt {
 					u8 action_code;
 					u8 dialog_token;
 					__le16 capability;
-					u8 variable[0];
+					u8 variable[];
 				} __packed tdls_discover_resp;
 				struct {
 					u8 action_code;
@@ -1340,6 +1157,35 @@ struct ieee80211_mgmt {
 					u8 max_tod_error;
 					u8 max_toa_error;
 				} __packed wnm_timing_msr;
+				struct {
+					u8 action_code;
+					u8 dialog_token;
+					u8 variable[];
+				} __packed ttlm_req;
+				struct {
+					u8 action_code;
+					u8 dialog_token;
+					__le16 status_code;
+					u8 variable[];
+				} __packed ttlm_res;
+				struct {
+					u8 action_code;
+				} __packed ttlm_tear_down;
+				struct {
+					u8 action_code;
+					u8 dialog_token;
+					u8 variable[];
+				} __packed ml_reconf_req;
+				struct {
+					u8 action_code;
+					u8 dialog_token;
+					u8 count;
+					u8 variable[];
+				} __packed ml_reconf_resp;
+				struct {
+					u8 action_code;
+					u8 variable[];
+				} __packed epcs;
 			} u;
 		} __packed action;
 		DECLARE_FLEX_ARRAY(u8, body); /* Generic frame body */
@@ -1349,14 +1195,19 @@ struct ieee80211_mgmt {
 /* Supported rates membership selectors */
 #define BSS_MEMBERSHIP_SELECTOR_HT_PHY	127
 #define BSS_MEMBERSHIP_SELECTOR_VHT_PHY	126
-#define BSS_MEMBERSHIP_SELECTOR_HE_PHY	122
+#define BSS_MEMBERSHIP_SELECTOR_GLK	125
+#define BSS_MEMBERSHIP_SELECTOR_EPD	124
 #define BSS_MEMBERSHIP_SELECTOR_SAE_H2E 123
+#define BSS_MEMBERSHIP_SELECTOR_HE_PHY	122
+#define BSS_MEMBERSHIP_SELECTOR_EHT_PHY	121
+
+#define BSS_MEMBERSHIP_SELECTOR_MIN	BSS_MEMBERSHIP_SELECTOR_EHT_PHY
 
 /* mgmt header + 1 byte category code */
 #define IEEE80211_MIN_ACTION_SIZE offsetof(struct ieee80211_mgmt, u.action.u)
 
 
-/* Management MIC information element (IEEE 802.11w) */
+/* Management MIC information element (IEEE 802.11w) for CMAC */
 struct ieee80211_mmie {
 	u8 element_id;
 	u8 length;
@@ -1374,6 +1225,15 @@ struct ieee80211_mmie_16 {
 	u8 mic[16];
 } __packed;
 
+/* Management MIC information element (IEEE 802.11w) for all variants */
+struct ieee80211_mmie_var {
+	u8 element_id;
+	u8 length;
+	__le16 key_id;
+	u8 sequence_number[6];
+	u8 mic[]; /* 8 or 16 bytes */
+} __packed;
+
 struct ieee80211_vendor_ie {
 	u8 element_id;
 	u8 len;
@@ -1450,1559 +1310,39 @@ struct ieee80211_tdls_data {
 		struct {
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_req;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_resp;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_cfm;
 		struct {
 			__le16 reason_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed teardown;
 		struct {
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed discover_req;
 		struct {
 			u8 target_channel;
 			u8 oper_class;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_req;
 		struct {
 			__le16 status_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_resp;
 	} u;
 } __packed;
 
-/*
- * Peer-to-Peer IE attribute related definitions.
- */
-/**
- * enum ieee80211_p2p_attr_id - identifies type of peer-to-peer attribute.
- */
-enum ieee80211_p2p_attr_id {
-	IEEE80211_P2P_ATTR_STATUS = 0,
-	IEEE80211_P2P_ATTR_MINOR_REASON,
-	IEEE80211_P2P_ATTR_CAPABILITY,
-	IEEE80211_P2P_ATTR_DEVICE_ID,
-	IEEE80211_P2P_ATTR_GO_INTENT,
-	IEEE80211_P2P_ATTR_GO_CONFIG_TIMEOUT,
-	IEEE80211_P2P_ATTR_LISTEN_CHANNEL,
-	IEEE80211_P2P_ATTR_GROUP_BSSID,
-	IEEE80211_P2P_ATTR_EXT_LISTEN_TIMING,
-	IEEE80211_P2P_ATTR_INTENDED_IFACE_ADDR,
-	IEEE80211_P2P_ATTR_MANAGABILITY,
-	IEEE80211_P2P_ATTR_CHANNEL_LIST,
-	IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
-	IEEE80211_P2P_ATTR_DEVICE_INFO,
-	IEEE80211_P2P_ATTR_GROUP_INFO,
-	IEEE80211_P2P_ATTR_GROUP_ID,
-	IEEE80211_P2P_ATTR_INTERFACE,
-	IEEE80211_P2P_ATTR_OPER_CHANNEL,
-	IEEE80211_P2P_ATTR_INVITE_FLAGS,
-	/* 19 - 220: Reserved */
-	IEEE80211_P2P_ATTR_VENDOR_SPECIFIC = 221,
-
-	IEEE80211_P2P_ATTR_MAX
-};
-
-/* Notice of Absence attribute - described in P2P spec 4.1.14 */
-/* Typical max value used here */
-#define IEEE80211_P2P_NOA_DESC_MAX	4
-
-struct ieee80211_p2p_noa_desc {
-	u8 count;
-	__le32 duration;
-	__le32 interval;
-	__le32 start_time;
-} __packed;
-
-struct ieee80211_p2p_noa_attr {
-	u8 index;
-	u8 oppps_ctwindow;
-	struct ieee80211_p2p_noa_desc desc[IEEE80211_P2P_NOA_DESC_MAX];
-} __packed;
-
-#define IEEE80211_P2P_OPPPS_ENABLE_BIT		BIT(7)
-#define IEEE80211_P2P_OPPPS_CTWINDOW_MASK	0x7F
-
-/**
- * struct ieee80211_bar - HT Block Ack Request
- *
- * This structure refers to "HT BlockAckReq" as
- * described in 802.11n draft section 7.2.1.7.1
- */
-struct ieee80211_bar {
-	__le16 frame_control;
-	__le16 duration;
-	__u8 ra[ETH_ALEN];
-	__u8 ta[ETH_ALEN];
-	__le16 control;
-	__le16 start_seq_num;
-} __packed;
-
-/* 802.11 BAR control masks */
-#define IEEE80211_BAR_CTRL_ACK_POLICY_NORMAL	0x0000
-#define IEEE80211_BAR_CTRL_MULTI_TID		0x0002
-#define IEEE80211_BAR_CTRL_CBMTID_COMPRESSED_BA	0x0004
-#define IEEE80211_BAR_CTRL_TID_INFO_MASK	0xf000
-#define IEEE80211_BAR_CTRL_TID_INFO_SHIFT	12
-
-#define IEEE80211_HT_MCS_MASK_LEN		10
-
-/**
- * struct ieee80211_mcs_info - MCS information
- * @rx_mask: RX mask
- * @rx_highest: highest supported RX rate. If set represents
- *	the highest supported RX data rate in units of 1 Mbps.
- *	If this field is 0 this value should not be used to
- *	consider the highest RX data rate supported.
- * @tx_params: TX parameters
- */
-struct ieee80211_mcs_info {
-	u8 rx_mask[IEEE80211_HT_MCS_MASK_LEN];
-	__le16 rx_highest;
-	u8 tx_params;
-	u8 reserved[3];
-} __packed;
-
-/* 802.11n HT capability MSC set */
-#define IEEE80211_HT_MCS_RX_HIGHEST_MASK	0x3ff
-#define IEEE80211_HT_MCS_TX_DEFINED		0x01
-#define IEEE80211_HT_MCS_TX_RX_DIFF		0x02
-/* value 0 == 1 stream etc */
-#define IEEE80211_HT_MCS_TX_MAX_STREAMS_MASK	0x0C
-#define IEEE80211_HT_MCS_TX_MAX_STREAMS_SHIFT	2
-#define		IEEE80211_HT_MCS_TX_MAX_STREAMS	4
-#define IEEE80211_HT_MCS_TX_UNEQUAL_MODULATION	0x10
-
-/*
- * 802.11n D5.0 20.3.5 / 20.6 says:
- * - indices 0 to 7 and 32 are single spatial stream
- * - 8 to 31 are multiple spatial streams using equal modulation
- *   [8..15 for two streams, 16..23 for three and 24..31 for four]
- * - remainder are multiple spatial streams using unequal modulation
- */
-#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START 33
-#define IEEE80211_HT_MCS_UNEQUAL_MODULATION_START_BYTE \
-	(IEEE80211_HT_MCS_UNEQUAL_MODULATION_START / 8)
-
-/**
- * struct ieee80211_ht_cap - HT capabilities
- *
- * This structure is the "HT capabilities element" as
- * described in 802.11n D5.0 7.3.2.57
- */
-struct ieee80211_ht_cap {
-	__le16 cap_info;
-	u8 ampdu_params_info;
-
-	/* 16 bytes MCS information */
-	struct ieee80211_mcs_info mcs;
-
-	__le16 extended_ht_cap_info;
-	__le32 tx_BF_cap_info;
-	u8 antenna_selection_info;
-} __packed;
-
-/* 802.11n HT capabilities masks (for cap_info) */
-#define IEEE80211_HT_CAP_LDPC_CODING		0x0001
-#define IEEE80211_HT_CAP_SUP_WIDTH_20_40	0x0002
-#define IEEE80211_HT_CAP_SM_PS			0x000C
-#define		IEEE80211_HT_CAP_SM_PS_SHIFT	2
-#define IEEE80211_HT_CAP_GRN_FLD		0x0010
-#define IEEE80211_HT_CAP_SGI_20			0x0020
-#define IEEE80211_HT_CAP_SGI_40			0x0040
-#define IEEE80211_HT_CAP_TX_STBC		0x0080
-#define IEEE80211_HT_CAP_RX_STBC		0x0300
-#define		IEEE80211_HT_CAP_RX_STBC_SHIFT	8
-#define IEEE80211_HT_CAP_DELAY_BA		0x0400
-#define IEEE80211_HT_CAP_MAX_AMSDU		0x0800
-#define IEEE80211_HT_CAP_DSSSCCK40		0x1000
-#define IEEE80211_HT_CAP_RESERVED		0x2000
-#define IEEE80211_HT_CAP_40MHZ_INTOLERANT	0x4000
-#define IEEE80211_HT_CAP_LSIG_TXOP_PROT		0x8000
-
-/* 802.11n HT extended capabilities masks (for extended_ht_cap_info) */
-#define IEEE80211_HT_EXT_CAP_PCO		0x0001
-#define IEEE80211_HT_EXT_CAP_PCO_TIME		0x0006
-#define		IEEE80211_HT_EXT_CAP_PCO_TIME_SHIFT	1
-#define IEEE80211_HT_EXT_CAP_MCS_FB		0x0300
-#define		IEEE80211_HT_EXT_CAP_MCS_FB_SHIFT	8
-#define IEEE80211_HT_EXT_CAP_HTC_SUP		0x0400
-#define IEEE80211_HT_EXT_CAP_RD_RESPONDER	0x0800
-
-/* 802.11n HT capability AMPDU settings (for ampdu_params_info) */
-#define IEEE80211_HT_AMPDU_PARM_FACTOR		0x03
-#define IEEE80211_HT_AMPDU_PARM_DENSITY		0x1C
-#define		IEEE80211_HT_AMPDU_PARM_DENSITY_SHIFT	2
-
-/*
- * Maximum length of AMPDU that the STA can receive in high-throughput (HT).
- * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets)
- */
-enum ieee80211_max_ampdu_length_exp {
-	IEEE80211_HT_MAX_AMPDU_8K = 0,
-	IEEE80211_HT_MAX_AMPDU_16K = 1,
-	IEEE80211_HT_MAX_AMPDU_32K = 2,
-	IEEE80211_HT_MAX_AMPDU_64K = 3
-};
-
-/*
- * Maximum length of AMPDU that the STA can receive in VHT.
- * Length = 2 ^ (13 + max_ampdu_length_exp) - 1 (octets)
- */
-enum ieee80211_vht_max_ampdu_length_exp {
-	IEEE80211_VHT_MAX_AMPDU_8K = 0,
-	IEEE80211_VHT_MAX_AMPDU_16K = 1,
-	IEEE80211_VHT_MAX_AMPDU_32K = 2,
-	IEEE80211_VHT_MAX_AMPDU_64K = 3,
-	IEEE80211_VHT_MAX_AMPDU_128K = 4,
-	IEEE80211_VHT_MAX_AMPDU_256K = 5,
-	IEEE80211_VHT_MAX_AMPDU_512K = 6,
-	IEEE80211_VHT_MAX_AMPDU_1024K = 7
-};
-
-#define IEEE80211_HT_MAX_AMPDU_FACTOR 13
-
-/* Minimum MPDU start spacing */
-enum ieee80211_min_mpdu_spacing {
-	IEEE80211_HT_MPDU_DENSITY_NONE = 0,	/* No restriction */
-	IEEE80211_HT_MPDU_DENSITY_0_25 = 1,	/* 1/4 usec */
-	IEEE80211_HT_MPDU_DENSITY_0_5 = 2,	/* 1/2 usec */
-	IEEE80211_HT_MPDU_DENSITY_1 = 3,	/* 1 usec */
-	IEEE80211_HT_MPDU_DENSITY_2 = 4,	/* 2 usec */
-	IEEE80211_HT_MPDU_DENSITY_4 = 5,	/* 4 usec */
-	IEEE80211_HT_MPDU_DENSITY_8 = 6,	/* 8 usec */
-	IEEE80211_HT_MPDU_DENSITY_16 = 7	/* 16 usec */
-};
-
-/**
- * struct ieee80211_ht_operation - HT operation IE
- *
- * This structure is the "HT operation element" as
- * described in 802.11n-2009 7.3.2.57
- */
-struct ieee80211_ht_operation {
-	u8 primary_chan;
-	u8 ht_param;
-	__le16 operation_mode;
-	__le16 stbc_param;
-	u8 basic_set[16];
-} __packed;
-
-/* for ht_param */
-#define IEEE80211_HT_PARAM_CHA_SEC_OFFSET		0x03
-#define		IEEE80211_HT_PARAM_CHA_SEC_NONE		0x00
-#define		IEEE80211_HT_PARAM_CHA_SEC_ABOVE	0x01
-#define		IEEE80211_HT_PARAM_CHA_SEC_BELOW	0x03
-#define IEEE80211_HT_PARAM_CHAN_WIDTH_ANY		0x04
-#define IEEE80211_HT_PARAM_RIFS_MODE			0x08
-
-/* for operation_mode */
-#define IEEE80211_HT_OP_MODE_PROTECTION			0x0003
-#define		IEEE80211_HT_OP_MODE_PROTECTION_NONE		0
-#define		IEEE80211_HT_OP_MODE_PROTECTION_NONMEMBER	1
-#define		IEEE80211_HT_OP_MODE_PROTECTION_20MHZ		2
-#define		IEEE80211_HT_OP_MODE_PROTECTION_NONHT_MIXED	3
-#define IEEE80211_HT_OP_MODE_NON_GF_STA_PRSNT		0x0004
-#define IEEE80211_HT_OP_MODE_NON_HT_STA_PRSNT		0x0010
-#define IEEE80211_HT_OP_MODE_CCFS2_SHIFT		5
-#define IEEE80211_HT_OP_MODE_CCFS2_MASK			0x1fe0
-
-/* for stbc_param */
-#define IEEE80211_HT_STBC_PARAM_DUAL_BEACON		0x0040
-#define IEEE80211_HT_STBC_PARAM_DUAL_CTS_PROT		0x0080
-#define IEEE80211_HT_STBC_PARAM_STBC_BEACON		0x0100
-#define IEEE80211_HT_STBC_PARAM_LSIG_TXOP_FULLPROT	0x0200
-#define IEEE80211_HT_STBC_PARAM_PCO_ACTIVE		0x0400
-#define IEEE80211_HT_STBC_PARAM_PCO_PHASE		0x0800
-
-
-/* block-ack parameters */
-#define IEEE80211_ADDBA_PARAM_AMSDU_MASK 0x0001
-#define IEEE80211_ADDBA_PARAM_POLICY_MASK 0x0002
-#define IEEE80211_ADDBA_PARAM_TID_MASK 0x003C
-#define IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK 0xFFC0
-#define IEEE80211_DELBA_PARAM_TID_MASK 0xF000
-#define IEEE80211_DELBA_PARAM_INITIATOR_MASK 0x0800
-
-/*
- * A-MPDU buffer sizes
- * According to HT size varies from 8 to 64 frames
- * HE adds the ability to have up to 256 frames.
- * EHT adds the ability to have up to 1K frames.
- */
-#define IEEE80211_MIN_AMPDU_BUF		0x8
-#define IEEE80211_MAX_AMPDU_BUF_HT	0x40
-#define IEEE80211_MAX_AMPDU_BUF_HE	0x100
-#define IEEE80211_MAX_AMPDU_BUF_EHT	0x400
-
-
-/* Spatial Multiplexing Power Save Modes (for capability) */
-#define WLAN_HT_CAP_SM_PS_STATIC	0
-#define WLAN_HT_CAP_SM_PS_DYNAMIC	1
-#define WLAN_HT_CAP_SM_PS_INVALID	2
-#define WLAN_HT_CAP_SM_PS_DISABLED	3
-
-/* for SM power control field lower two bits */
-#define WLAN_HT_SMPS_CONTROL_DISABLED	0
-#define WLAN_HT_SMPS_CONTROL_STATIC	1
-#define WLAN_HT_SMPS_CONTROL_DYNAMIC	3
-
-/**
- * struct ieee80211_vht_mcs_info - VHT MCS information
- * @rx_mcs_map: RX MCS map 2 bits for each stream, total 8 streams
- * @rx_highest: Indicates highest long GI VHT PPDU data rate
- *	STA can receive. Rate expressed in units of 1 Mbps.
- *	If this field is 0 this value should not be used to
- *	consider the highest RX data rate supported.
- *	The top 3 bits of this field indicate the Maximum NSTS,total
- *	(a beamformee capability.)
- * @tx_mcs_map: TX MCS map 2 bits for each stream, total 8 streams
- * @tx_highest: Indicates highest long GI VHT PPDU data rate
- *	STA can transmit. Rate expressed in units of 1 Mbps.
- *	If this field is 0 this value should not be used to
- *	consider the highest TX data rate supported.
- *	The top 2 bits of this field are reserved, the
- *	3rd bit from the top indiciates VHT Extended NSS BW
- *	Capability.
- */
-struct ieee80211_vht_mcs_info {
-	__le16 rx_mcs_map;
-	__le16 rx_highest;
-	__le16 tx_mcs_map;
-	__le16 tx_highest;
-} __packed;
-
-/* for rx_highest */
-#define IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT	13
-#define IEEE80211_VHT_MAX_NSTS_TOTAL_MASK	(7 << IEEE80211_VHT_MAX_NSTS_TOTAL_SHIFT)
-
-/* for tx_highest */
-#define IEEE80211_VHT_EXT_NSS_BW_CAPABLE	(1 << 13)
-
-/**
- * enum ieee80211_vht_mcs_support - VHT MCS support definitions
- * @IEEE80211_VHT_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
- *	number of streams
- * @IEEE80211_VHT_MCS_SUPPORT_0_8: MCSes 0-8 are supported
- * @IEEE80211_VHT_MCS_SUPPORT_0_9: MCSes 0-9 are supported
- * @IEEE80211_VHT_MCS_NOT_SUPPORTED: This number of streams isn't supported
- *
- * These definitions are used in each 2-bit subfield of the @rx_mcs_map
- * and @tx_mcs_map fields of &struct ieee80211_vht_mcs_info, which are
- * both split into 8 subfields by number of streams. These values indicate
- * which MCSes are supported for the number of streams the value appears
- * for.
- */
-enum ieee80211_vht_mcs_support {
-	IEEE80211_VHT_MCS_SUPPORT_0_7	= 0,
-	IEEE80211_VHT_MCS_SUPPORT_0_8	= 1,
-	IEEE80211_VHT_MCS_SUPPORT_0_9	= 2,
-	IEEE80211_VHT_MCS_NOT_SUPPORTED	= 3,
-};
-
-/**
- * struct ieee80211_vht_cap - VHT capabilities
- *
- * This structure is the "VHT capabilities element" as
- * described in 802.11ac D3.0 8.4.2.160
- * @vht_cap_info: VHT capability info
- * @supp_mcs: VHT MCS supported rates
- */
-struct ieee80211_vht_cap {
-	__le32 vht_cap_info;
-	struct ieee80211_vht_mcs_info supp_mcs;
-} __packed;
-
-/**
- * enum ieee80211_vht_chanwidth - VHT channel width
- * @IEEE80211_VHT_CHANWIDTH_USE_HT: use the HT operation IE to
- *	determine the channel width (20 or 40 MHz)
- * @IEEE80211_VHT_CHANWIDTH_80MHZ: 80 MHz bandwidth
- * @IEEE80211_VHT_CHANWIDTH_160MHZ: 160 MHz bandwidth
- * @IEEE80211_VHT_CHANWIDTH_80P80MHZ: 80+80 MHz bandwidth
- */
-enum ieee80211_vht_chanwidth {
-	IEEE80211_VHT_CHANWIDTH_USE_HT		= 0,
-	IEEE80211_VHT_CHANWIDTH_80MHZ		= 1,
-	IEEE80211_VHT_CHANWIDTH_160MHZ		= 2,
-	IEEE80211_VHT_CHANWIDTH_80P80MHZ	= 3,
-};
-
-/**
- * struct ieee80211_vht_operation - VHT operation IE
- *
- * This structure is the "VHT operation element" as
- * described in 802.11ac D3.0 8.4.2.161
- * @chan_width: Operating channel width
- * @center_freq_seg0_idx: center freq segment 0 index
- * @center_freq_seg1_idx: center freq segment 1 index
- * @basic_mcs_set: VHT Basic MCS rate set
- */
-struct ieee80211_vht_operation {
-	u8 chan_width;
-	u8 center_freq_seg0_idx;
-	u8 center_freq_seg1_idx;
-	__le16 basic_mcs_set;
-} __packed;
-
-/**
- * struct ieee80211_he_cap_elem - HE capabilities element
- *
- * This structure is the "HE capabilities element" fixed fields as
- * described in P802.11ax_D4.0 section 9.4.2.242.2 and 9.4.2.242.3
- */
-struct ieee80211_he_cap_elem {
-	u8 mac_cap_info[6];
-	u8 phy_cap_info[11];
-} __packed;
-
-#define IEEE80211_TX_RX_MCS_NSS_DESC_MAX_LEN	5
-
-/**
- * enum ieee80211_he_mcs_support - HE MCS support definitions
- * @IEEE80211_HE_MCS_SUPPORT_0_7: MCSes 0-7 are supported for the
- *	number of streams
- * @IEEE80211_HE_MCS_SUPPORT_0_9: MCSes 0-9 are supported
- * @IEEE80211_HE_MCS_SUPPORT_0_11: MCSes 0-11 are supported
- * @IEEE80211_HE_MCS_NOT_SUPPORTED: This number of streams isn't supported
- *
- * These definitions are used in each 2-bit subfield of the rx_mcs_*
- * and tx_mcs_* fields of &struct ieee80211_he_mcs_nss_supp, which are
- * both split into 8 subfields by number of streams. These values indicate
- * which MCSes are supported for the number of streams the value appears
- * for.
- */
-enum ieee80211_he_mcs_support {
-	IEEE80211_HE_MCS_SUPPORT_0_7	= 0,
-	IEEE80211_HE_MCS_SUPPORT_0_9	= 1,
-	IEEE80211_HE_MCS_SUPPORT_0_11	= 2,
-	IEEE80211_HE_MCS_NOT_SUPPORTED	= 3,
-};
-
-/**
- * struct ieee80211_he_mcs_nss_supp - HE Tx/Rx HE MCS NSS Support Field
- *
- * This structure holds the data required for the Tx/Rx HE MCS NSS Support Field
- * described in P802.11ax_D2.0 section 9.4.2.237.4
- *
- * @rx_mcs_80: Rx MCS map 2 bits for each stream, total 8 streams, for channel
- *     widths less than 80MHz.
- * @tx_mcs_80: Tx MCS map 2 bits for each stream, total 8 streams, for channel
- *     widths less than 80MHz.
- * @rx_mcs_160: Rx MCS map 2 bits for each stream, total 8 streams, for channel
- *     width 160MHz.
- * @tx_mcs_160: Tx MCS map 2 bits for each stream, total 8 streams, for channel
- *     width 160MHz.
- * @rx_mcs_80p80: Rx MCS map 2 bits for each stream, total 8 streams, for
- *     channel width 80p80MHz.
- * @tx_mcs_80p80: Tx MCS map 2 bits for each stream, total 8 streams, for
- *     channel width 80p80MHz.
- */
-struct ieee80211_he_mcs_nss_supp {
-	__le16 rx_mcs_80;
-	__le16 tx_mcs_80;
-	__le16 rx_mcs_160;
-	__le16 tx_mcs_160;
-	__le16 rx_mcs_80p80;
-	__le16 tx_mcs_80p80;
-} __packed;
-
-/**
- * struct ieee80211_he_operation - HE capabilities element
- *
- * This structure is the "HE operation element" fields as
- * described in P802.11ax_D4.0 section 9.4.2.243
- */
-struct ieee80211_he_operation {
-	__le32 he_oper_params;
-	__le16 he_mcs_nss_set;
-	/* Optional 0,1,3,4,5,7 or 8 bytes: depends on @he_oper_params */
-	u8 optional[];
-} __packed;
-
-/**
- * struct ieee80211_he_spr - HE spatial reuse element
- *
- * This structure is the "HE spatial reuse element" element as
- * described in P802.11ax_D4.0 section 9.4.2.241
- */
-struct ieee80211_he_spr {
-	u8 he_sr_control;
-	/* Optional 0 to 19 bytes: depends on @he_sr_control */
-	u8 optional[];
-} __packed;
-
-/**
- * struct ieee80211_he_mu_edca_param_ac_rec - MU AC Parameter Record field
- *
- * This structure is the "MU AC Parameter Record" fields as
- * described in P802.11ax_D4.0 section 9.4.2.245
- */
-struct ieee80211_he_mu_edca_param_ac_rec {
-	u8 aifsn;
-	u8 ecw_min_max;
-	u8 mu_edca_timer;
-} __packed;
-
-/**
- * struct ieee80211_mu_edca_param_set - MU EDCA Parameter Set element
- *
- * This structure is the "MU EDCA Parameter Set element" fields as
- * described in P802.11ax_D4.0 section 9.4.2.245
- */
-struct ieee80211_mu_edca_param_set {
-	u8 mu_qos_info;
-	struct ieee80211_he_mu_edca_param_ac_rec ac_be;
-	struct ieee80211_he_mu_edca_param_ac_rec ac_bk;
-	struct ieee80211_he_mu_edca_param_ac_rec ac_vi;
-	struct ieee80211_he_mu_edca_param_ac_rec ac_vo;
-} __packed;
-
-#define IEEE80211_EHT_MCS_NSS_RX 0x0f
-#define IEEE80211_EHT_MCS_NSS_TX 0xf0
-
-/**
- * struct ieee80211_eht_mcs_nss_supp_20mhz_only - EHT 20MHz only station max
- * supported NSS for per MCS.
- *
- * For each field below, bits 0 - 3 indicate the maximal number of spatial
- * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams
- * for Tx.
- *
- * @rx_tx_mcs7_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 0 - 7.
- * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 8 - 9.
- * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 10 - 11.
- * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 12 - 13.
- */
-struct ieee80211_eht_mcs_nss_supp_20mhz_only {
-	u8 rx_tx_mcs7_max_nss;
-	u8 rx_tx_mcs9_max_nss;
-	u8 rx_tx_mcs11_max_nss;
-	u8 rx_tx_mcs13_max_nss;
-};
-
-/**
- * struct ieee80211_eht_mcs_nss_supp_bw - EHT max supported NSS per MCS (except
- * 20MHz only stations).
- *
- * For each field below, bits 0 - 3 indicate the maximal number of spatial
- * streams for Rx, and bits 4 - 7 indicate the maximal number of spatial streams
- * for Tx.
- *
- * @rx_tx_mcs9_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 0 - 9.
- * @rx_tx_mcs11_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 10 - 11.
- * @rx_tx_mcs13_max_nss: indicates the maximum number of spatial streams
- *     supported for reception and the maximum number of spatial streams
- *     supported for transmission for MCS 12 - 13.
- */
-struct ieee80211_eht_mcs_nss_supp_bw {
-	u8 rx_tx_mcs9_max_nss;
-	u8 rx_tx_mcs11_max_nss;
-	u8 rx_tx_mcs13_max_nss;
-};
-
-/**
- * struct ieee80211_eht_cap_elem_fixed - EHT capabilities fixed data
- *
- * This structure is the "EHT Capabilities element" fixed fields as
- * described in P802.11be_D2.0 section 9.4.2.313.
- *
- * @mac_cap_info: MAC capabilities, see IEEE80211_EHT_MAC_CAP*
- * @phy_cap_info: PHY capabilities, see IEEE80211_EHT_PHY_CAP*
- */
-struct ieee80211_eht_cap_elem_fixed {
-	u8 mac_cap_info[2];
-	u8 phy_cap_info[9];
-} __packed;
-
-/**
- * struct ieee80211_eht_cap_elem - EHT capabilities element
- * @fixed: fixed parts, see &ieee80211_eht_cap_elem_fixed
- * @optional: optional parts
- */
-struct ieee80211_eht_cap_elem {
-	struct ieee80211_eht_cap_elem_fixed fixed;
-
-	/*
-	 * Followed by:
-	 * Supported EHT-MCS And NSS Set field: 4, 3, 6 or 9 octets.
-	 * EHT PPE Thresholds field: variable length.
-	 */
-	u8 optional[];
-} __packed;
-
-#define IEEE80211_EHT_OPER_INFO_PRESENT	                        0x01
-#define IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT	0x02
-#define IEEE80211_EHT_OPER_EHT_DEF_PE_DURATION	                0x04
-#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_LIMIT         0x08
-#define IEEE80211_EHT_OPER_GROUP_ADDRESSED_BU_IND_EXP_MASK      0x30
-
-/**
- * struct ieee80211_eht_operation - eht operation element
- *
- * This structure is the "EHT Operation Element" fields as
- * described in P802.11be_D2.0 section 9.4.2.311
- *
- * @params: EHT operation element parameters. See &IEEE80211_EHT_OPER_*
- * @basic_mcs_nss: indicates the EHT-MCSs for each number of spatial streams in
- *     EHT PPDUs that are supported by all EHT STAs in the BSS in transmit and
- *     receive.
- * @optional: optional parts
- */
-struct ieee80211_eht_operation {
-	u8 params;
-	__le32 basic_mcs_nss;
-	u8 optional[];
-} __packed;
-
-/**
- * struct ieee80211_eht_operation_info - eht operation information
- *
- * @control: EHT operation information control.
- * @ccfs0: defines a channel center frequency for a 20, 40, 80, 160, or 320 MHz
- *     EHT BSS.
- * @ccfs1: defines a channel center frequency for a 160 or 320 MHz EHT BSS.
- * @optional: optional parts
- */
-struct ieee80211_eht_operation_info {
-	u8 control;
-	u8 ccfs0;
-	u8 ccfs1;
-	u8 optional[];
-} __packed;
-
-/* 802.11ac VHT Capabilities */
-#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_3895			0x00000000
-#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_7991			0x00000001
-#define IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_11454			0x00000002
-#define IEEE80211_VHT_CAP_MAX_MPDU_MASK				0x00000003
-#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ		0x00000004
-#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ	0x00000008
-#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK			0x0000000C
-#define IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_SHIFT			2
-#define IEEE80211_VHT_CAP_RXLDPC				0x00000010
-#define IEEE80211_VHT_CAP_SHORT_GI_80				0x00000020
-#define IEEE80211_VHT_CAP_SHORT_GI_160				0x00000040
-#define IEEE80211_VHT_CAP_TXSTBC				0x00000080
-#define IEEE80211_VHT_CAP_RXSTBC_1				0x00000100
-#define IEEE80211_VHT_CAP_RXSTBC_2				0x00000200
-#define IEEE80211_VHT_CAP_RXSTBC_3				0x00000300
-#define IEEE80211_VHT_CAP_RXSTBC_4				0x00000400
-#define IEEE80211_VHT_CAP_RXSTBC_MASK				0x00000700
-#define IEEE80211_VHT_CAP_RXSTBC_SHIFT				8
-#define IEEE80211_VHT_CAP_SU_BEAMFORMER_CAPABLE			0x00000800
-#define IEEE80211_VHT_CAP_SU_BEAMFORMEE_CAPABLE			0x00001000
-#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT                  13
-#define IEEE80211_VHT_CAP_BEAMFORMEE_STS_MASK			\
-		(7 << IEEE80211_VHT_CAP_BEAMFORMEE_STS_SHIFT)
-#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT		16
-#define IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_MASK		\
-		(7 << IEEE80211_VHT_CAP_SOUNDING_DIMENSIONS_SHIFT)
-#define IEEE80211_VHT_CAP_MU_BEAMFORMER_CAPABLE			0x00080000
-#define IEEE80211_VHT_CAP_MU_BEAMFORMEE_CAPABLE			0x00100000
-#define IEEE80211_VHT_CAP_VHT_TXOP_PS				0x00200000
-#define IEEE80211_VHT_CAP_HTC_VHT				0x00400000
-#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT	23
-#define IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_MASK	\
-		(7 << IEEE80211_VHT_CAP_MAX_A_MPDU_LENGTH_EXPONENT_SHIFT)
-#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_UNSOL_MFB	0x08000000
-#define IEEE80211_VHT_CAP_VHT_LINK_ADAPTATION_VHT_MRQ_MFB	0x0c000000
-#define IEEE80211_VHT_CAP_RX_ANTENNA_PATTERN			0x10000000
-#define IEEE80211_VHT_CAP_TX_ANTENNA_PATTERN			0x20000000
-#define IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT			30
-#define IEEE80211_VHT_CAP_EXT_NSS_BW_MASK			0xc0000000
-
-/**
- * ieee80211_get_vht_max_nss - return max NSS for a given bandwidth/MCS
- * @cap: VHT capabilities of the peer
- * @bw: bandwidth to use
- * @mcs: MCS index to use
- * @ext_nss_bw_capable: indicates whether or not the local transmitter
- *	(rate scaling algorithm) can deal with the new logic
- *	(dot11VHTExtendedNSSBWCapable)
- * @max_vht_nss: current maximum NSS as advertised by the STA in
- *	operating mode notification, can be 0 in which case the
- *	capability data will be used to derive this (from MCS support)
- *
- * Due to the VHT Extended NSS Bandwidth Support, the maximum NSS can
- * vary for a given BW/MCS. This function parses the data.
- *
- * Note: This function is exported by cfg80211.
- */
-int ieee80211_get_vht_max_nss(struct ieee80211_vht_cap *cap,
-			      enum ieee80211_vht_chanwidth bw,
-			      int mcs, bool ext_nss_bw_capable,
-			      unsigned int max_vht_nss);
-
-/**
- * enum ieee80211_ap_reg_power - regulatory power for a Access Point
- *
- * @IEEE80211_REG_UNSET_AP: Access Point has no regulatory power mode
- * @IEEE80211_REG_LPI: Indoor Access Point
- * @IEEE80211_REG_SP: Standard power Access Point
- * @IEEE80211_REG_VLP: Very low power Access Point
- * @IEEE80211_REG_AP_POWER_AFTER_LAST: internal
- * @IEEE80211_REG_AP_POWER_MAX: maximum value
- */
-enum ieee80211_ap_reg_power {
-	IEEE80211_REG_UNSET_AP,
-	IEEE80211_REG_LPI_AP,
-	IEEE80211_REG_SP_AP,
-	IEEE80211_REG_VLP_AP,
-	IEEE80211_REG_AP_POWER_AFTER_LAST,
-	IEEE80211_REG_AP_POWER_MAX =
-		IEEE80211_REG_AP_POWER_AFTER_LAST - 1,
-};
-
-/**
- * enum ieee80211_client_reg_power - regulatory power for a client
- *
- * @IEEE80211_REG_UNSET_CLIENT: Client has no regulatory power mode
- * @IEEE80211_REG_DEFAULT_CLIENT: Default Client
- * @IEEE80211_REG_SUBORDINATE_CLIENT: Subordinate Client
- * @IEEE80211_REG_CLIENT_POWER_AFTER_LAST: internal
- * @IEEE80211_REG_CLIENT_POWER_MAX: maximum value
- */
-enum ieee80211_client_reg_power {
-	IEEE80211_REG_UNSET_CLIENT,
-	IEEE80211_REG_DEFAULT_CLIENT,
-	IEEE80211_REG_SUBORDINATE_CLIENT,
-	IEEE80211_REG_CLIENT_POWER_AFTER_LAST,
-	IEEE80211_REG_CLIENT_POWER_MAX =
-		IEEE80211_REG_CLIENT_POWER_AFTER_LAST - 1,
-};
-
-/* 802.11ax HE MAC capabilities */
-#define IEEE80211_HE_MAC_CAP0_HTC_HE				0x01
-#define IEEE80211_HE_MAC_CAP0_TWT_REQ				0x02
-#define IEEE80211_HE_MAC_CAP0_TWT_RES				0x04
-#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_NOT_SUPP		0x00
-#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_1		0x08
-#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_2		0x10
-#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_LEVEL_3		0x18
-#define IEEE80211_HE_MAC_CAP0_DYNAMIC_FRAG_MASK			0x18
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_1		0x00
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_2		0x20
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_4		0x40
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_8		0x60
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_16		0x80
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_32		0xa0
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_64		0xc0
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_UNLIMITED	0xe0
-#define IEEE80211_HE_MAC_CAP0_MAX_NUM_FRAG_MSDU_MASK		0xe0
-
-#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_UNLIMITED		0x00
-#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_128			0x01
-#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_256			0x02
-#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_512			0x03
-#define IEEE80211_HE_MAC_CAP1_MIN_FRAG_SIZE_MASK		0x03
-#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_0US		0x00
-#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_8US		0x04
-#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_16US		0x08
-#define IEEE80211_HE_MAC_CAP1_TF_MAC_PAD_DUR_MASK		0x0c
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_1		0x00
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_2		0x10
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_3		0x20
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_4		0x30
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_5		0x40
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_6		0x50
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_7		0x60
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_8		0x70
-#define IEEE80211_HE_MAC_CAP1_MULTI_TID_AGG_RX_QOS_MASK		0x70
-
-/* Link adaptation is split between byte HE_MAC_CAP1 and
- * HE_MAC_CAP2. It should be set only if IEEE80211_HE_MAC_CAP0_HTC_HE
- * in which case the following values apply:
- * 0 = No feedback.
- * 1 = reserved.
- * 2 = Unsolicited feedback.
- * 3 = both
- */
-#define IEEE80211_HE_MAC_CAP1_LINK_ADAPTATION			0x80
-
-#define IEEE80211_HE_MAC_CAP2_LINK_ADAPTATION			0x01
-#define IEEE80211_HE_MAC_CAP2_ALL_ACK				0x02
-#define IEEE80211_HE_MAC_CAP2_TRS				0x04
-#define IEEE80211_HE_MAC_CAP2_BSR				0x08
-#define IEEE80211_HE_MAC_CAP2_BCAST_TWT				0x10
-#define IEEE80211_HE_MAC_CAP2_32BIT_BA_BITMAP			0x20
-#define IEEE80211_HE_MAC_CAP2_MU_CASCADING			0x40
-#define IEEE80211_HE_MAC_CAP2_ACK_EN				0x80
-
-#define IEEE80211_HE_MAC_CAP3_OMI_CONTROL			0x02
-#define IEEE80211_HE_MAC_CAP3_OFDMA_RA				0x04
-
-/* The maximum length of an A-MDPU is defined by the combination of the Maximum
- * A-MDPU Length Exponent field in the HT capabilities, VHT capabilities and the
- * same field in the HE capabilities.
- */
-#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_0		0x00
-#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_1		0x08
-#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_2		0x10
-#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_EXT_3		0x18
-#define IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK		0x18
-#define IEEE80211_HE_MAC_CAP3_AMSDU_FRAG			0x20
-#define IEEE80211_HE_MAC_CAP3_FLEX_TWT_SCHED			0x40
-#define IEEE80211_HE_MAC_CAP3_RX_CTRL_FRAME_TO_MULTIBSS		0x80
-
-#define IEEE80211_HE_MAC_CAP4_BSRP_BQRP_A_MPDU_AGG		0x01
-#define IEEE80211_HE_MAC_CAP4_QTP				0x02
-#define IEEE80211_HE_MAC_CAP4_BQR				0x04
-#define IEEE80211_HE_MAC_CAP4_PSR_RESP				0x08
-#define IEEE80211_HE_MAC_CAP4_NDP_FB_REP			0x10
-#define IEEE80211_HE_MAC_CAP4_OPS				0x20
-#define IEEE80211_HE_MAC_CAP4_AMSDU_IN_AMPDU			0x40
-/* Multi TID agg TX is split between byte #4 and #5
- * The value is a combination of B39,B40,B41
- */
-#define IEEE80211_HE_MAC_CAP4_MULTI_TID_AGG_TX_QOS_B39		0x80
-
-#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B40		0x01
-#define IEEE80211_HE_MAC_CAP5_MULTI_TID_AGG_TX_QOS_B41		0x02
-#define IEEE80211_HE_MAC_CAP5_SUBCHAN_SELECTIVE_TRANSMISSION	0x04
-#define IEEE80211_HE_MAC_CAP5_UL_2x996_TONE_RU			0x08
-#define IEEE80211_HE_MAC_CAP5_OM_CTRL_UL_MU_DATA_DIS_RX		0x10
-#define IEEE80211_HE_MAC_CAP5_HE_DYNAMIC_SM_PS			0x20
-#define IEEE80211_HE_MAC_CAP5_PUNCTURED_SOUNDING		0x40
-#define IEEE80211_HE_MAC_CAP5_HT_VHT_TRIG_FRAME_RX		0x80
-
-#define IEEE80211_HE_VHT_MAX_AMPDU_FACTOR	20
-#define IEEE80211_HE_HT_MAX_AMPDU_FACTOR	16
-#define IEEE80211_HE_6GHZ_MAX_AMPDU_FACTOR	13
-
-/* 802.11ax HE PHY capabilities */
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G		0x02
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G	0x04
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G		0x08
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G	0x10
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK_ALL		0x1e
-
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_2G	0x20
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_RU_MAPPING_IN_5G	0x40
-#define IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_MASK			0xfe
-
-#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_20MHZ	0x01
-#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_80MHZ_ONLY_SECOND_40MHZ	0x02
-#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_20MHZ	0x04
-#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_160MHZ_ONLY_SECOND_40MHZ	0x08
-#define IEEE80211_HE_PHY_CAP1_PREAMBLE_PUNC_RX_MASK			0x0f
-#define IEEE80211_HE_PHY_CAP1_DEVICE_CLASS_A				0x10
-#define IEEE80211_HE_PHY_CAP1_LDPC_CODING_IN_PAYLOAD			0x20
-#define IEEE80211_HE_PHY_CAP1_HE_LTF_AND_GI_FOR_HE_PPDUS_0_8US		0x40
-/* Midamble RX/TX Max NSTS is split between byte #2 and byte #3 */
-#define IEEE80211_HE_PHY_CAP1_MIDAMBLE_RX_TX_MAX_NSTS			0x80
-
-#define IEEE80211_HE_PHY_CAP2_MIDAMBLE_RX_TX_MAX_NSTS			0x01
-#define IEEE80211_HE_PHY_CAP2_NDP_4x_LTF_AND_3_2US			0x02
-#define IEEE80211_HE_PHY_CAP2_STBC_TX_UNDER_80MHZ			0x04
-#define IEEE80211_HE_PHY_CAP2_STBC_RX_UNDER_80MHZ			0x08
-#define IEEE80211_HE_PHY_CAP2_DOPPLER_TX				0x10
-#define IEEE80211_HE_PHY_CAP2_DOPPLER_RX				0x20
-
-/* Note that the meaning of UL MU below is different between an AP and a non-AP
- * sta, where in the AP case it indicates support for Rx and in the non-AP sta
- * case it indicates support for Tx.
- */
-#define IEEE80211_HE_PHY_CAP2_UL_MU_FULL_MU_MIMO			0x40
-#define IEEE80211_HE_PHY_CAP2_UL_MU_PARTIAL_MU_MIMO			0x80
-
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_NO_DCM			0x00
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_BPSK			0x01
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_QPSK			0x02
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_16_QAM			0x03
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_TX_MASK			0x03
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_1				0x00
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_TX_NSS_2				0x04
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_NO_DCM			0x00
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_BPSK			0x08
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_QPSK			0x10
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_16_QAM			0x18
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_CONST_RX_MASK			0x18
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_1				0x00
-#define IEEE80211_HE_PHY_CAP3_DCM_MAX_RX_NSS_2				0x20
-#define IEEE80211_HE_PHY_CAP3_RX_PARTIAL_BW_SU_IN_20MHZ_MU		0x40
-#define IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER				0x80
-
-#define IEEE80211_HE_PHY_CAP4_SU_BEAMFORMEE				0x01
-#define IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER				0x02
-
-/* Minimal allowed value of Max STS under 80MHz is 3 */
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_4		0x0c
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_5		0x10
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_6		0x14
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_7		0x18
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_8		0x1c
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_UNDER_80MHZ_MASK	0x1c
-
-/* Minimal allowed value of Max STS above 80MHz is 3 */
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_4		0x60
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_5		0x80
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_6		0xa0
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_7		0xc0
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_8		0xe0
-#define IEEE80211_HE_PHY_CAP4_BEAMFORMEE_MAX_STS_ABOVE_80MHZ_MASK	0xe0
-
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_1	0x00
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_2	0x01
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_3	0x02
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_4	0x03
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_5	0x04
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_6	0x05
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_7	0x06
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_8	0x07
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK	0x07
-
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_1	0x00
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_2	0x08
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_3	0x10
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_4	0x18
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_5	0x20
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_6	0x28
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_7	0x30
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_8	0x38
-#define IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_ABOVE_80MHZ_MASK	0x38
-
-#define IEEE80211_HE_PHY_CAP5_NG16_SU_FEEDBACK				0x40
-#define IEEE80211_HE_PHY_CAP5_NG16_MU_FEEDBACK				0x80
-
-#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_42_SU			0x01
-#define IEEE80211_HE_PHY_CAP6_CODEBOOK_SIZE_75_MU			0x02
-#define IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB			0x04
-#define IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB		0x08
-#define IEEE80211_HE_PHY_CAP6_TRIG_CQI_FB				0x10
-#define IEEE80211_HE_PHY_CAP6_PARTIAL_BW_EXT_RANGE			0x20
-#define IEEE80211_HE_PHY_CAP6_PARTIAL_BANDWIDTH_DL_MUMIMO		0x40
-#define IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT			0x80
-
-#define IEEE80211_HE_PHY_CAP7_PSR_BASED_SR				0x01
-#define IEEE80211_HE_PHY_CAP7_POWER_BOOST_FACTOR_SUPP			0x02
-#define IEEE80211_HE_PHY_CAP7_HE_SU_MU_PPDU_4XLTF_AND_08_US_GI		0x04
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_1					0x08
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_2					0x10
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_3					0x18
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_4					0x20
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_5					0x28
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_6					0x30
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_7					0x38
-#define IEEE80211_HE_PHY_CAP7_MAX_NC_MASK				0x38
-#define IEEE80211_HE_PHY_CAP7_STBC_TX_ABOVE_80MHZ			0x40
-#define IEEE80211_HE_PHY_CAP7_STBC_RX_ABOVE_80MHZ			0x80
-
-#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_PPDU_4XLTF_AND_08_US_GI		0x01
-#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_40MHZ_HE_PPDU_IN_2G		0x02
-#define IEEE80211_HE_PHY_CAP8_20MHZ_IN_160MHZ_HE_PPDU			0x04
-#define IEEE80211_HE_PHY_CAP8_80MHZ_IN_160MHZ_HE_PPDU			0x08
-#define IEEE80211_HE_PHY_CAP8_HE_ER_SU_1XLTF_AND_08_US_GI		0x10
-#define IEEE80211_HE_PHY_CAP8_MIDAMBLE_RX_TX_2X_AND_1XLTF		0x20
-#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_242				0x00
-#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_484				0x40
-#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_996				0x80
-#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_2x996				0xc0
-#define IEEE80211_HE_PHY_CAP8_DCM_MAX_RU_MASK				0xc0
-
-#define IEEE80211_HE_PHY_CAP9_LONGER_THAN_16_SIGB_OFDM_SYM		0x01
-#define IEEE80211_HE_PHY_CAP9_NON_TRIGGERED_CQI_FEEDBACK		0x02
-#define IEEE80211_HE_PHY_CAP9_TX_1024_QAM_LESS_THAN_242_TONE_RU		0x04
-#define IEEE80211_HE_PHY_CAP9_RX_1024_QAM_LESS_THAN_242_TONE_RU		0x08
-#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_COMP_SIGB	0x10
-#define IEEE80211_HE_PHY_CAP9_RX_FULL_BW_SU_USING_MU_WITH_NON_COMP_SIGB	0x20
-#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_0US			0x0
-#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_8US			0x1
-#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_16US			0x2
-#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_RESERVED		0x3
-#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_POS			6
-#define IEEE80211_HE_PHY_CAP9_NOMINAL_PKT_PADDING_MASK			0xc0
-
-#define IEEE80211_HE_PHY_CAP10_HE_MU_M1RU_MAX_LTF			0x01
-
-/* 802.11ax HE TX/RX MCS NSS Support  */
-#define IEEE80211_TX_RX_MCS_NSS_SUPP_HIGHEST_MCS_POS			(3)
-#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_POS			(6)
-#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_POS			(11)
-#define IEEE80211_TX_RX_MCS_NSS_SUPP_TX_BITMAP_MASK			0x07c0
-#define IEEE80211_TX_RX_MCS_NSS_SUPP_RX_BITMAP_MASK			0xf800
-
-/* TX/RX HE MCS Support field Highest MCS subfield encoding */
-enum ieee80211_he_highest_mcs_supported_subfield_enc {
-	HIGHEST_MCS_SUPPORTED_MCS7 = 0,
-	HIGHEST_MCS_SUPPORTED_MCS8,
-	HIGHEST_MCS_SUPPORTED_MCS9,
-	HIGHEST_MCS_SUPPORTED_MCS10,
-	HIGHEST_MCS_SUPPORTED_MCS11,
-};
-
-/* Calculate 802.11ax HE capabilities IE Tx/Rx HE MCS NSS Support Field size */
-static inline u8
-ieee80211_he_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap)
-{
-	u8 count = 4;
-
-	if (he_cap->phy_cap_info[0] &
-	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
-		count += 4;
-
-	if (he_cap->phy_cap_info[0] &
-	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_80PLUS80_MHZ_IN_5G)
-		count += 4;
-
-	return count;
-}
-
-/* 802.11ax HE PPE Thresholds */
-#define IEEE80211_PPE_THRES_NSS_SUPPORT_2NSS			(1)
-#define IEEE80211_PPE_THRES_NSS_POS				(0)
-#define IEEE80211_PPE_THRES_NSS_MASK				(7)
-#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_2x966_AND_966_RU	\
-	(BIT(5) | BIT(6))
-#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK		0x78
-#define IEEE80211_PPE_THRES_RU_INDEX_BITMASK_POS		(3)
-#define IEEE80211_PPE_THRES_INFO_PPET_SIZE			(3)
-#define IEEE80211_HE_PPE_THRES_INFO_HEADER_SIZE			(7)
-
-/*
- * Calculate 802.11ax HE capabilities IE PPE field size
- * Input: Header byte of ppe_thres (first byte), and HE capa IE's PHY cap u8*
- */
-static inline u8
-ieee80211_he_ppe_size(u8 ppe_thres_hdr, const u8 *phy_cap_info)
-{
-	u8 n;
-
-	if ((phy_cap_info[6] &
-	     IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) == 0)
-		return 0;
-
-	n = hweight8(ppe_thres_hdr &
-		     IEEE80211_PPE_THRES_RU_INDEX_BITMASK_MASK);
-	n *= (1 + ((ppe_thres_hdr & IEEE80211_PPE_THRES_NSS_MASK) >>
-		   IEEE80211_PPE_THRES_NSS_POS));
-
-	/*
-	 * Each pair is 6 bits, and we need to add the 7 "header" bits to the
-	 * total size.
-	 */
-	n = (n * IEEE80211_PPE_THRES_INFO_PPET_SIZE * 2) + 7;
-	n = DIV_ROUND_UP(n, 8);
-
-	return n;
-}
-
-static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len)
-{
-	const struct ieee80211_he_cap_elem *he_cap_ie_elem = (const void *)data;
-	u8 needed = sizeof(*he_cap_ie_elem);
-
-	if (len < needed)
-		return false;
-
-	needed += ieee80211_he_mcs_nss_size(he_cap_ie_elem);
-	if (len < needed)
-		return false;
-
-	if (he_cap_ie_elem->phy_cap_info[6] &
-			IEEE80211_HE_PHY_CAP6_PPE_THRESHOLD_PRESENT) {
-		if (len < needed + 1)
-			return false;
-		needed += ieee80211_he_ppe_size(data[needed],
-						he_cap_ie_elem->phy_cap_info);
-	}
-
-	return len >= needed;
-}
-
-/* HE Operation defines */
-#define IEEE80211_HE_OPERATION_DFLT_PE_DURATION_MASK		0x00000007
-#define IEEE80211_HE_OPERATION_TWT_REQUIRED			0x00000008
-#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_MASK		0x00003ff0
-#define IEEE80211_HE_OPERATION_RTS_THRESHOLD_OFFSET		4
-#define IEEE80211_HE_OPERATION_VHT_OPER_INFO			0x00004000
-#define IEEE80211_HE_OPERATION_CO_HOSTED_BSS			0x00008000
-#define IEEE80211_HE_OPERATION_ER_SU_DISABLE			0x00010000
-#define IEEE80211_HE_OPERATION_6GHZ_OP_INFO			0x00020000
-#define IEEE80211_HE_OPERATION_BSS_COLOR_MASK			0x3f000000
-#define IEEE80211_HE_OPERATION_BSS_COLOR_OFFSET			24
-#define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x40000000
-#define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED		0x80000000
-
-#define IEEE80211_6GHZ_CTRL_REG_LPI_AP	0
-#define IEEE80211_6GHZ_CTRL_REG_SP_AP	1
-
-/**
- * ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
- * @primary: primary channel
- * @control: control flags
- * @ccfs0: channel center frequency segment 0
- * @ccfs1: channel center frequency segment 1
- * @minrate: minimum rate (in 1 Mbps units)
- */
-struct ieee80211_he_6ghz_oper {
-	u8 primary;
-#define IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH	0x3
-#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_20MHZ	0
-#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_40MHZ	1
-#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ	2
-#define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ	3
-#define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON	0x4
-#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO	0x38
-	u8 control;
-	u8 ccfs0;
-	u8 ccfs1;
-	u8 minrate;
-} __packed;
-
-/*
- * In "9.4.2.161 Transmit Power Envelope element" of "IEEE Std 802.11ax-2021",
- * it show four types in "Table 9-275a-Maximum Transmit Power Interpretation
- * subfield encoding", and two category for each type in "Table E-12-Regulatory
- * Info subfield encoding in the United States".
- * So it it totally max 8 Transmit Power Envelope element.
- */
-#define IEEE80211_TPE_MAX_IE_COUNT	8
-/*
- * In "Table 9-277—Meaning of Maximum Transmit Power Count subfield"
- * of "IEEE Std 802.11ax™‐2021", the max power level is 8.
- */
-#define IEEE80211_MAX_NUM_PWR_LEVEL	8
-
-#define IEEE80211_TPE_MAX_POWER_COUNT	8
-
-/* transmit power interpretation type of transmit power envelope element */
-enum ieee80211_tx_power_intrpt_type {
-	IEEE80211_TPE_LOCAL_EIRP,
-	IEEE80211_TPE_LOCAL_EIRP_PSD,
-	IEEE80211_TPE_REG_CLIENT_EIRP,
-	IEEE80211_TPE_REG_CLIENT_EIRP_PSD,
-};
-
-/**
- * struct ieee80211_tx_pwr_env
- *
- * This structure represents the "Transmit Power Envelope element"
- */
-struct ieee80211_tx_pwr_env {
-	u8 tx_power_info;
-	s8 tx_power[IEEE80211_TPE_MAX_POWER_COUNT];
-} __packed;
-
-#define IEEE80211_TX_PWR_ENV_INFO_COUNT 0x7
-#define IEEE80211_TX_PWR_ENV_INFO_INTERPRET 0x38
-#define IEEE80211_TX_PWR_ENV_INFO_CATEGORY 0xC0
-
-/*
- * ieee80211_he_oper_size - calculate 802.11ax HE Operations IE size
- * @he_oper_ie: byte data of the He Operations IE, stating from the byte
- *	after the ext ID byte. It is assumed that he_oper_ie has at least
- *	sizeof(struct ieee80211_he_operation) bytes, the caller must have
- *	validated this.
- * @return the actual size of the IE data (not including header), or 0 on error
- */
-static inline u8
-ieee80211_he_oper_size(const u8 *he_oper_ie)
-{
-	const struct ieee80211_he_operation *he_oper = (const void *)he_oper_ie;
-	u8 oper_len = sizeof(struct ieee80211_he_operation);
-	u32 he_oper_params;
-
-	/* Make sure the input is not NULL */
-	if (!he_oper_ie)
-		return 0;
-
-	/* Calc required length */
-	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
-	if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
-		oper_len += 3;
-	if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS)
-		oper_len++;
-	if (he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO)
-		oper_len += sizeof(struct ieee80211_he_6ghz_oper);
-
-	/* Add the first byte (extension ID) to the total length */
-	oper_len++;
-
-	return oper_len;
-}
-
-/**
- * ieee80211_he_6ghz_oper - obtain 6 GHz operation field
- * @he_oper: HE operation element (must be pre-validated for size)
- *	but may be %NULL
- *
- * Return: a pointer to the 6 GHz operation field, or %NULL
- */
-static inline const struct ieee80211_he_6ghz_oper *
-ieee80211_he_6ghz_oper(const struct ieee80211_he_operation *he_oper)
-{
-	const u8 *ret = (const void *)&he_oper->optional;
-	u32 he_oper_params;
-
-	if (!he_oper)
-		return NULL;
-
-	he_oper_params = le32_to_cpu(he_oper->he_oper_params);
-
-	if (!(he_oper_params & IEEE80211_HE_OPERATION_6GHZ_OP_INFO))
-		return NULL;
-	if (he_oper_params & IEEE80211_HE_OPERATION_VHT_OPER_INFO)
-		ret += 3;
-	if (he_oper_params & IEEE80211_HE_OPERATION_CO_HOSTED_BSS)
-		ret++;
-
-	return (const void *)ret;
-}
-
-/* HE Spatial Reuse defines */
-#define IEEE80211_HE_SPR_PSR_DISALLOWED				BIT(0)
-#define IEEE80211_HE_SPR_NON_SRG_OBSS_PD_SR_DISALLOWED		BIT(1)
-#define IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT			BIT(2)
-#define IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT		BIT(3)
-#define IEEE80211_HE_SPR_HESIGA_SR_VAL15_ALLOWED		BIT(4)
-
-/*
- * ieee80211_he_spr_size - calculate 802.11ax HE Spatial Reuse IE size
- * @he_spr_ie: byte data of the He Spatial Reuse IE, stating from the byte
- *	after the ext ID byte. It is assumed that he_spr_ie has at least
- *	sizeof(struct ieee80211_he_spr) bytes, the caller must have validated
- *	this
- * @return the actual size of the IE data (not including header), or 0 on error
- */
-static inline u8
-ieee80211_he_spr_size(const u8 *he_spr_ie)
-{
-	const struct ieee80211_he_spr *he_spr = (const void *)he_spr_ie;
-	u8 spr_len = sizeof(struct ieee80211_he_spr);
-	u8 he_spr_params;
-
-	/* Make sure the input is not NULL */
-	if (!he_spr_ie)
-		return 0;
-
-	/* Calc required length */
-	he_spr_params = he_spr->he_sr_control;
-	if (he_spr_params & IEEE80211_HE_SPR_NON_SRG_OFFSET_PRESENT)
-		spr_len++;
-	if (he_spr_params & IEEE80211_HE_SPR_SRG_INFORMATION_PRESENT)
-		spr_len += 18;
-
-	/* Add the first byte (extension ID) to the total length */
-	spr_len++;
-
-	return spr_len;
-}
-
-/* S1G Capabilities Information field */
-#define IEEE80211_S1G_CAPABILITY_LEN	15
-
-#define S1G_CAP0_S1G_LONG	BIT(0)
-#define S1G_CAP0_SGI_1MHZ	BIT(1)
-#define S1G_CAP0_SGI_2MHZ	BIT(2)
-#define S1G_CAP0_SGI_4MHZ	BIT(3)
-#define S1G_CAP0_SGI_8MHZ	BIT(4)
-#define S1G_CAP0_SGI_16MHZ	BIT(5)
-#define S1G_CAP0_SUPP_CH_WIDTH	GENMASK(7, 6)
-
-#define S1G_SUPP_CH_WIDTH_2	0
-#define S1G_SUPP_CH_WIDTH_4	1
-#define S1G_SUPP_CH_WIDTH_8	2
-#define S1G_SUPP_CH_WIDTH_16	3
-#define S1G_SUPP_CH_WIDTH_MAX(cap) ((1 << FIELD_GET(S1G_CAP0_SUPP_CH_WIDTH, \
-						    cap[0])) << 1)
-
-#define S1G_CAP1_RX_LDPC	BIT(0)
-#define S1G_CAP1_TX_STBC	BIT(1)
-#define S1G_CAP1_RX_STBC	BIT(2)
-#define S1G_CAP1_SU_BFER	BIT(3)
-#define S1G_CAP1_SU_BFEE	BIT(4)
-#define S1G_CAP1_BFEE_STS	GENMASK(7, 5)
-
-#define S1G_CAP2_SOUNDING_DIMENSIONS	GENMASK(2, 0)
-#define S1G_CAP2_MU_BFER		BIT(3)
-#define S1G_CAP2_MU_BFEE		BIT(4)
-#define S1G_CAP2_PLUS_HTC_VHT		BIT(5)
-#define S1G_CAP2_TRAVELING_PILOT	GENMASK(7, 6)
-
-#define S1G_CAP3_RD_RESPONDER		BIT(0)
-#define S1G_CAP3_HT_DELAYED_BA		BIT(1)
-#define S1G_CAP3_MAX_MPDU_LEN		BIT(2)
-#define S1G_CAP3_MAX_AMPDU_LEN_EXP	GENMASK(4, 3)
-#define S1G_CAP3_MIN_MPDU_START		GENMASK(7, 5)
-
-#define S1G_CAP4_UPLINK_SYNC	BIT(0)
-#define S1G_CAP4_DYNAMIC_AID	BIT(1)
-#define S1G_CAP4_BAT		BIT(2)
-#define S1G_CAP4_TIME_ADE	BIT(3)
-#define S1G_CAP4_NON_TIM	BIT(4)
-#define S1G_CAP4_GROUP_AID	BIT(5)
-#define S1G_CAP4_STA_TYPE	GENMASK(7, 6)
-
-#define S1G_CAP5_CENT_AUTH_CONTROL	BIT(0)
-#define S1G_CAP5_DIST_AUTH_CONTROL	BIT(1)
-#define S1G_CAP5_AMSDU			BIT(2)
-#define S1G_CAP5_AMPDU			BIT(3)
-#define S1G_CAP5_ASYMMETRIC_BA		BIT(4)
-#define S1G_CAP5_FLOW_CONTROL		BIT(5)
-#define S1G_CAP5_SECTORIZED_BEAM	GENMASK(7, 6)
-
-#define S1G_CAP6_OBSS_MITIGATION	BIT(0)
-#define S1G_CAP6_FRAGMENT_BA		BIT(1)
-#define S1G_CAP6_NDP_PS_POLL		BIT(2)
-#define S1G_CAP6_RAW_OPERATION		BIT(3)
-#define S1G_CAP6_PAGE_SLICING		BIT(4)
-#define S1G_CAP6_TXOP_SHARING_IMP_ACK	BIT(5)
-#define S1G_CAP6_VHT_LINK_ADAPT		GENMASK(7, 6)
-
-#define S1G_CAP7_TACK_AS_PS_POLL		BIT(0)
-#define S1G_CAP7_DUP_1MHZ			BIT(1)
-#define S1G_CAP7_MCS_NEGOTIATION		BIT(2)
-#define S1G_CAP7_1MHZ_CTL_RESPONSE_PREAMBLE	BIT(3)
-#define S1G_CAP7_NDP_BFING_REPORT_POLL		BIT(4)
-#define S1G_CAP7_UNSOLICITED_DYN_AID		BIT(5)
-#define S1G_CAP7_SECTOR_TRAINING_OPERATION	BIT(6)
-#define S1G_CAP7_TEMP_PS_MODE_SWITCH		BIT(7)
-
-#define S1G_CAP8_TWT_GROUPING	BIT(0)
-#define S1G_CAP8_BDT		BIT(1)
-#define S1G_CAP8_COLOR		GENMASK(4, 2)
-#define S1G_CAP8_TWT_REQUEST	BIT(5)
-#define S1G_CAP8_TWT_RESPOND	BIT(6)
-#define S1G_CAP8_PV1_FRAME	BIT(7)
-
-#define S1G_CAP9_LINK_ADAPT_PER_CONTROL_RESPONSE BIT(0)
-
-#define S1G_OPER_CH_WIDTH_PRIMARY_1MHZ	BIT(0)
-#define S1G_OPER_CH_WIDTH_OPER		GENMASK(4, 1)
-
-/* EHT MAC capabilities as defined in P802.11be_D2.0 section 9.4.2.313.2 */
-#define IEEE80211_EHT_MAC_CAP0_EPCS_PRIO_ACCESS			0x01
-#define IEEE80211_EHT_MAC_CAP0_OM_CONTROL			0x02
-#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE1		0x04
-#define IEEE80211_EHT_MAC_CAP0_TRIG_TXOP_SHARING_MODE2		0x08
-#define IEEE80211_EHT_MAC_CAP0_RESTRICTED_TWT			0x10
-#define IEEE80211_EHT_MAC_CAP0_SCS_TRAFFIC_DESC			0x20
-#define IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_MASK		0xc0
-#define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_3895	        0
-#define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_7991	        1
-#define	IEEE80211_EHT_MAC_CAP0_MAX_MPDU_LEN_11454	        2
-
-#define IEEE80211_EHT_MAC_CAP1_MAX_AMPDU_LEN_MASK		0x01
-
-/* EHT PHY capabilities as defined in P802.11be_D2.0 section 9.4.2.313.3 */
-#define IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ			0x02
-#define IEEE80211_EHT_PHY_CAP0_242_TONE_RU_GT20MHZ		0x04
-#define IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI		0x08
-#define IEEE80211_EHT_PHY_CAP0_PARTIAL_BW_UL_MU_MIMO		0x10
-#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER			0x20
-#define IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE			0x40
-
-/* EHT beamformee number of spatial streams <= 80MHz is split */
-#define IEEE80211_EHT_PHY_CAP0_BEAMFORMEE_SS_80MHZ_MASK		0x80
-#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK		0x03
-
-#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK	0x1c
-#define IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK	0xe0
-
-#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK		0x07
-#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK		0x38
-
-/* EHT number of sounding dimensions for 320MHz is split */
-#define IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK		0xc0
-#define IEEE80211_EHT_PHY_CAP3_SOUNDING_DIM_320MHZ_MASK		0x01
-#define IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK		0x02
-#define IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK		0x04
-#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK		0x08
-#define IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK		0x10
-#define IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK			0x20
-#define IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK		0x40
-#define IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK			0x80
-
-#define IEEE80211_EHT_PHY_CAP4_PART_BW_DL_MU_MIMO		0x01
-#define IEEE80211_EHT_PHY_CAP4_PSR_SR_SUPP			0x02
-#define IEEE80211_EHT_PHY_CAP4_POWER_BOOST_FACT_SUPP		0x04
-#define IEEE80211_EHT_PHY_CAP4_EHT_MU_PPDU_4_EHT_LTF_08_GI	0x08
-#define IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK			0xf0
-
-#define IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK		0x01
-#define IEEE80211_EHT_PHY_CAP5_TX_LESS_242_TONE_RU_SUPP		0x02
-#define IEEE80211_EHT_PHY_CAP5_RX_LESS_242_TONE_RU_SUPP		0x04
-#define IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT		0x08
-#define IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK	0x30
-#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_0US	0
-#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_8US	1
-#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US	2
-#define   IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_20US	3
-
-/* Maximum number of supported EHT LTF is split */
-#define IEEE80211_EHT_PHY_CAP5_MAX_NUM_SUPP_EHT_LTF_MASK	0xc0
-#define IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK	0x07
-
-#define IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK			0x78
-#define IEEE80211_EHT_PHY_CAP6_EHT_DUP_6GHZ_SUPP		0x80
-
-#define IEEE80211_EHT_PHY_CAP7_20MHZ_STA_RX_NDP_WIDER_BW	0x01
-#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ	0x02
-#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ	0x04
-#define IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ	0x08
-#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ		0x10
-#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ		0x20
-#define IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ		0x40
-#define IEEE80211_EHT_PHY_CAP7_TB_SOUNDING_FDBK_RATE_LIMIT	0x80
-
-#define IEEE80211_EHT_PHY_CAP8_RX_1024QAM_WIDER_BW_DL_OFDMA	0x01
-#define IEEE80211_EHT_PHY_CAP8_RX_4096QAM_WIDER_BW_DL_OFDMA	0x02
-
-/*
- * EHT operation channel width as defined in P802.11be_D2.0 section 9.4.2.311
- */
-#define IEEE80211_EHT_OPER_CHAN_WIDTH		0x7
-#define IEEE80211_EHT_OPER_CHAN_WIDTH_20MHZ	0
-#define IEEE80211_EHT_OPER_CHAN_WIDTH_40MHZ	1
-#define IEEE80211_EHT_OPER_CHAN_WIDTH_80MHZ	2
-#define IEEE80211_EHT_OPER_CHAN_WIDTH_160MHZ	3
-#define IEEE80211_EHT_OPER_CHAN_WIDTH_320MHZ	4
-
-/* Calculate 802.11be EHT capabilities IE Tx/Rx EHT MCS NSS Support Field size */
-static inline u8
-ieee80211_eht_mcs_nss_size(const struct ieee80211_he_cap_elem *he_cap,
-			   const struct ieee80211_eht_cap_elem_fixed *eht_cap,
-			   bool from_ap)
-{
-	u8 count = 0;
-
-	/* on 2.4 GHz, if it supports 40 MHz, the result is 3 */
-	if (he_cap->phy_cap_info[0] &
-	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_IN_2G)
-		return 3;
-
-	/* on 2.4 GHz, these three bits are reserved, so should be 0 */
-	if (he_cap->phy_cap_info[0] &
-	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_40MHZ_80MHZ_IN_5G)
-		count += 3;
-
-	if (he_cap->phy_cap_info[0] &
-	    IEEE80211_HE_PHY_CAP0_CHANNEL_WIDTH_SET_160MHZ_IN_5G)
-		count += 3;
-
-	if (eht_cap->phy_cap_info[0] & IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ)
-		count += 3;
-
-	if (count)
-		return count;
-
-	return from_ap ? 3 : 4;
-}
-
-/* 802.11be EHT PPE Thresholds */
-#define IEEE80211_EHT_PPE_THRES_NSS_POS			0
-#define IEEE80211_EHT_PPE_THRES_NSS_MASK		0xf
-#define IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK	0x1f0
-#define IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE		3
-#define IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE	9
-
-/*
- * Calculate 802.11be EHT capabilities IE EHT field size
- */
-static inline u8
-ieee80211_eht_ppe_size(u16 ppe_thres_hdr, const u8 *phy_cap_info)
-{
-	u32 n;
-
-	if (!(phy_cap_info[5] &
-	      IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT))
-		return 0;
-
-	n = hweight16(ppe_thres_hdr &
-		      IEEE80211_EHT_PPE_THRES_RU_INDEX_BITMASK_MASK);
-	n *= 1 + u16_get_bits(ppe_thres_hdr, IEEE80211_EHT_PPE_THRES_NSS_MASK);
-
-	/*
-	 * Each pair is 6 bits, and we need to add the 9 "header" bits to the
-	 * total size.
-	 */
-	n = n * IEEE80211_EHT_PPE_THRES_INFO_PPET_SIZE * 2 +
-	    IEEE80211_EHT_PPE_THRES_INFO_HEADER_SIZE;
-	return DIV_ROUND_UP(n, 8);
-}
-
-static inline bool
-ieee80211_eht_capa_size_ok(const u8 *he_capa, const u8 *data, u8 len,
-			   bool from_ap)
-{
-	const struct ieee80211_eht_cap_elem_fixed *elem = (const void *)data;
-	u8 needed = sizeof(struct ieee80211_eht_cap_elem_fixed);
-
-	if (len < needed || !he_capa)
-		return false;
-
-	needed += ieee80211_eht_mcs_nss_size((const void *)he_capa,
-					     (const void *)data,
-					     from_ap);
-	if (len < needed)
-		return false;
-
-	if (elem->phy_cap_info[5] &
-			IEEE80211_EHT_PHY_CAP5_PPE_THRESHOLD_PRESENT) {
-		u16 ppe_thres_hdr;
-
-		if (len < needed + sizeof(ppe_thres_hdr))
-			return false;
-
-		ppe_thres_hdr = get_unaligned_le16(data + needed);
-		needed += ieee80211_eht_ppe_size(ppe_thres_hdr,
-						 elem->phy_cap_info);
-	}
-
-	return len >= needed;
-}
-
-static inline bool
-ieee80211_eht_oper_size_ok(const u8 *data, u8 len)
-{
-	const struct ieee80211_eht_operation *elem = (const void *)data;
-	u8 needed = sizeof(*elem);
-
-	if (len < needed)
-		return false;
-
-	if (elem->params & IEEE80211_EHT_OPER_INFO_PRESENT) {
-		needed += 3;
-
-		if (elem->params &
-		    IEEE80211_EHT_OPER_DISABLED_SUBCHANNEL_BITMAP_PRESENT)
-			needed += 2;
-	}
-
-	return len >= needed;
-}
-
-#define LISTEN_INT_USF	GENMASK(15, 14)
-#define LISTEN_INT_UI	GENMASK(13, 0)
-
-#define IEEE80211_MAX_USF	FIELD_MAX(LISTEN_INT_USF)
-#define IEEE80211_MAX_UI	FIELD_MAX(LISTEN_INT_UI)
-
 /* Authentication algorithms */
 #define WLAN_AUTH_OPEN 0
 #define WLAN_AUTH_SHARED_KEY 1
@@ -3153,10 +1493,12 @@ enum ieee80211_statuscode {
 	WLAN_STATUS_DENIED_WITH_SUGGESTED_BAND_AND_CHANNEL = 99,
 	WLAN_STATUS_DENIED_DUE_TO_SPECTRUM_MANAGEMENT = 103,
 	/* 802.11ai */
-	WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 108,
-	WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 109,
+	WLAN_STATUS_FILS_AUTHENTICATION_FAILURE = 112,
+	WLAN_STATUS_UNKNOWN_AUTHENTICATION_SERVER = 113,
 	WLAN_STATUS_SAE_HASH_TO_ELEMENT = 126,
 	WLAN_STATUS_SAE_PK = 127,
+	WLAN_STATUS_DENIED_TID_TO_LINK_MAPPING = 133,
+	WLAN_STATUS_PREF_TID_TO_LINK_MAPPING_SUGGESTED = 134,
 };
 
 
@@ -3433,6 +1775,7 @@ enum ieee80211_eid_ext {
 	WLAN_EID_EXT_FILS_PUBLIC_KEY = 12,
 	WLAN_EID_EXT_FILS_NONCE = 13,
 	WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14,
+	WLAN_EID_EXT_DH_PARAMETER = 32,
 	WLAN_EID_EXT_HE_CAPABILITY = 35,
 	WLAN_EID_EXT_HE_OPERATION = 36,
 	WLAN_EID_EXT_UORA = 37,
@@ -3454,6 +1797,10 @@ enum ieee80211_eid_ext {
 	WLAN_EID_EXT_EHT_OPERATION = 106,
 	WLAN_EID_EXT_EHT_MULTI_LINK = 107,
 	WLAN_EID_EXT_EHT_CAPABILITY = 108,
+	WLAN_EID_EXT_TID_TO_LINK_MAPPING = 109,
+	WLAN_EID_EXT_BANDWIDTH_INDICATION = 135,
+	WLAN_EID_EXT_KNOWN_STA_IDENTIFCATION = 136,
+	WLAN_EID_EXT_NON_AP_STA_REG_CON = 137,
 };
 
 /* Action category code */
@@ -3480,6 +1827,7 @@ enum ieee80211_category {
 	WLAN_CATEGORY_UNPROT_DMG = 20,
 	WLAN_CATEGORY_VHT = 21,
 	WLAN_CATEGORY_S1G = 22,
+	WLAN_CATEGORY_PROTECTED_EHT = 37,
 	WLAN_CATEGORY_VENDOR_SPECIFIC_PROTECTED = 126,
 	WLAN_CATEGORY_VENDOR_SPECIFIC = 127,
 };
@@ -3493,25 +1841,6 @@ enum ieee80211_spectrum_mgmt_actioncode {
 	WLAN_ACTION_SPCT_CHL_SWITCH = 4,
 };
 
-/* HT action codes */
-enum ieee80211_ht_actioncode {
-	WLAN_HT_ACTION_NOTIFY_CHANWIDTH = 0,
-	WLAN_HT_ACTION_SMPS = 1,
-	WLAN_HT_ACTION_PSMP = 2,
-	WLAN_HT_ACTION_PCO_PHASE = 3,
-	WLAN_HT_ACTION_CSI = 4,
-	WLAN_HT_ACTION_NONCOMPRESSED_BF = 5,
-	WLAN_HT_ACTION_COMPRESSED_BF = 6,
-	WLAN_HT_ACTION_ASEL_IDX_FEEDBACK = 7,
-};
-
-/* VHT action codes */
-enum ieee80211_vht_actioncode {
-	WLAN_VHT_ACTION_COMPRESSED_BF = 0,
-	WLAN_VHT_ACTION_GROUPID_MGMT = 1,
-	WLAN_VHT_ACTION_OPMODE_NOTIF = 2,
-};
-
 /* Self Protected Action codes */
 enum ieee80211_self_protected_actioncode {
 	WLAN_SP_RESERVED = 0,
@@ -3522,21 +1851,6 @@ enum ieee80211_self_protected_actioncode {
 	WLAN_SP_MGK_ACK = 5,
 };
 
-/* Mesh action codes */
-enum ieee80211_mesh_actioncode {
-	WLAN_MESH_ACTION_LINK_METRIC_REPORT,
-	WLAN_MESH_ACTION_HWMP_PATH_SELECTION,
-	WLAN_MESH_ACTION_GATE_ANNOUNCEMENT,
-	WLAN_MESH_ACTION_CONGESTION_CONTROL_NOTIFICATION,
-	WLAN_MESH_ACTION_MCCA_SETUP_REQUEST,
-	WLAN_MESH_ACTION_MCCA_SETUP_REPLY,
-	WLAN_MESH_ACTION_MCCA_ADVERTISEMENT_REQUEST,
-	WLAN_MESH_ACTION_MCCA_ADVERTISEMENT,
-	WLAN_MESH_ACTION_MCCA_TEARDOWN,
-	WLAN_MESH_ACTION_TBTT_ADJUSTMENT_REQUEST,
-	WLAN_MESH_ACTION_TBTT_ADJUSTMENT_RESPONSE,
-};
-
 /* Unprotected WNM action codes */
 enum ieee80211_unprotected_wnm_actioncode {
 	WLAN_UNPROTECTED_WNM_ACTION_TIM = 0,
@@ -3559,18 +1873,14 @@ enum ieee80211_key_len {
 	WLAN_KEY_LEN_BIP_GMAC_256 = 32,
 };
 
-enum ieee80211_s1g_actioncode {
-	WLAN_S1G_AID_SWITCH_REQUEST,
-	WLAN_S1G_AID_SWITCH_RESPONSE,
-	WLAN_S1G_SYNC_CONTROL,
-	WLAN_S1G_STA_INFO_ANNOUNCE,
-	WLAN_S1G_EDCA_PARAM_SET,
-	WLAN_S1G_EL_OPERATION,
-	WLAN_S1G_TWT_SETUP,
-	WLAN_S1G_TWT_TEARDOWN,
-	WLAN_S1G_SECT_GROUP_ID_LIST,
-	WLAN_S1G_SECT_ID_FEEDBACK,
-	WLAN_S1G_TWT_INFORMATION = 11,
+/* Radio measurement action codes as defined in IEEE 802.11-2024 - Table 9-470 */
+enum ieee80211_radio_measurement_actioncode {
+	WLAN_RM_ACTION_RADIO_MEASUREMENT_REQUEST = 0,
+	WLAN_RM_ACTION_RADIO_MEASUREMENT_REPORT  = 1,
+	WLAN_RM_ACTION_LINK_MEASUREMENT_REQUEST  = 2,
+	WLAN_RM_ACTION_LINK_MEASUREMENT_REPORT   = 3,
+	WLAN_RM_ACTION_NEIGHBOR_REPORT_REQUEST   = 4,
+	WLAN_RM_ACTION_NEIGHBOR_REPORT_RESPONSE  = 5,
 };
 
 #define IEEE80211_WEP_IV_LEN		4
@@ -3588,6 +1898,9 @@ enum ieee80211_s1g_actioncode {
 #define IEEE80211_GCMP_HDR_LEN		8
 #define IEEE80211_GCMP_MIC_LEN		16
 #define IEEE80211_GCMP_PN_LEN		6
+#define IEEE80211_CMAC_128_MIC_LEN	8
+#define IEEE80211_CMAC_256_MIC_LEN	16
+#define IEEE80211_GMAC_MIC_LEN		16
 
 #define FILS_NONCE_LEN			16
 #define FILS_MAX_KEK_LEN		64
@@ -3713,71 +2026,15 @@ enum ieee80211_tdls_actioncode {
 /* Defines support for enhanced multi-bssid advertisement*/
 #define WLAN_EXT_CAPA11_EMA_SUPPORT	BIT(3)
 
+/* Enable Beacon Protection */
+#define WLAN_EXT_CAPA11_BCN_PROTECT	BIT(4)
+
 /* TDLS specific payload type in the LLC/SNAP header */
 #define WLAN_TDLS_SNAP_RFTYPE	0x2
 
 /* BSS Coex IE information field bits */
 #define WLAN_BSS_COEX_INFORMATION_REQUEST	BIT(0)
 
-/**
- * enum ieee80211_mesh_sync_method - mesh synchronization method identifier
- *
- * @IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET: the default synchronization method
- * @IEEE80211_SYNC_METHOD_VENDOR: a vendor specific synchronization method
- *	that will be specified in a vendor specific information element
- */
-enum ieee80211_mesh_sync_method {
-	IEEE80211_SYNC_METHOD_NEIGHBOR_OFFSET = 1,
-	IEEE80211_SYNC_METHOD_VENDOR = 255,
-};
-
-/**
- * enum ieee80211_mesh_path_protocol - mesh path selection protocol identifier
- *
- * @IEEE80211_PATH_PROTOCOL_HWMP: the default path selection protocol
- * @IEEE80211_PATH_PROTOCOL_VENDOR: a vendor specific protocol that will
- *	be specified in a vendor specific information element
- */
-enum ieee80211_mesh_path_protocol {
-	IEEE80211_PATH_PROTOCOL_HWMP = 1,
-	IEEE80211_PATH_PROTOCOL_VENDOR = 255,
-};
-
-/**
- * enum ieee80211_mesh_path_metric - mesh path selection metric identifier
- *
- * @IEEE80211_PATH_METRIC_AIRTIME: the default path selection metric
- * @IEEE80211_PATH_METRIC_VENDOR: a vendor specific metric that will be
- *	specified in a vendor specific information element
- */
-enum ieee80211_mesh_path_metric {
-	IEEE80211_PATH_METRIC_AIRTIME = 1,
-	IEEE80211_PATH_METRIC_VENDOR = 255,
-};
-
-/**
- * enum ieee80211_root_mode_identifier - root mesh STA mode identifier
- *
- * These attribute are used by dot11MeshHWMPRootMode to set root mesh STA mode
- *
- * @IEEE80211_ROOTMODE_NO_ROOT: the mesh STA is not a root mesh STA (default)
- * @IEEE80211_ROOTMODE_ROOT: the mesh STA is a root mesh STA if greater than
- *	this value
- * @IEEE80211_PROACTIVE_PREQ_NO_PREP: the mesh STA is a root mesh STA supports
- *	the proactive PREQ with proactive PREP subfield set to 0
- * @IEEE80211_PROACTIVE_PREQ_WITH_PREP: the mesh STA is a root mesh STA
- *	supports the proactive PREQ with proactive PREP subfield set to 1
- * @IEEE80211_PROACTIVE_RANN: the mesh STA is a root mesh STA supports
- *	the proactive RANN
- */
-enum ieee80211_root_mode_identifier {
-	IEEE80211_ROOTMODE_NO_ROOT = 0,
-	IEEE80211_ROOTMODE_ROOT = 1,
-	IEEE80211_PROACTIVE_PREQ_NO_PREP = 2,
-	IEEE80211_PROACTIVE_PREQ_WITH_PREP = 3,
-	IEEE80211_PROACTIVE_RANN = 4,
-};
-
 /*
  * IEEE 802.11-2007 7.3.2.9 Country information element
  *
@@ -3870,7 +2127,7 @@ enum ieee80211_idle_options {
 };
 
 /**
- * struct ieee80211_bss_max_idle_period_ie
+ * struct ieee80211_bss_max_idle_period_ie - BSS max idle period element struct
  *
  * This structure refers to "BSS Max idle period element"
  *
@@ -3885,19 +2142,6 @@ struct ieee80211_bss_max_idle_period_ie {
 	u8 idle_options;
 } __packed;
 
-/* BACK action code */
-enum ieee80211_back_actioncode {
-	WLAN_ACTION_ADDBA_REQ = 0,
-	WLAN_ACTION_ADDBA_RESP = 1,
-	WLAN_ACTION_DELBA = 2,
-};
-
-/* BACK (block-ack) parties */
-enum ieee80211_back_parties {
-	WLAN_BACK_RECIPIENT = 0,
-	WLAN_BACK_INITIATOR = 1,
-};
-
 /* SA Query action */
 enum ieee80211_sa_query_action {
 	WLAN_ACTION_SA_QUERY_REQUEST = 0,
@@ -3905,7 +2149,7 @@ enum ieee80211_sa_query_action {
 };
 
 /**
- * struct ieee80211_bssid_index
+ * struct ieee80211_bssid_index - multiple BSSID index element structure
  *
  * This structure refers to "Multiple BSSID-index element"
  *
@@ -3920,7 +2164,8 @@ struct ieee80211_bssid_index {
 };
 
 /**
- * struct ieee80211_multiple_bssid_configuration
+ * struct ieee80211_multiple_bssid_configuration - multiple BSSID configuration
+ *	element structure
  *
  * This structure refers to "Multiple BSSID Configuration element"
  *
@@ -4030,27 +2275,10 @@ struct ieee80211_tspec_ie {
 	__le16 medium_time;
 } __packed;
 
-struct ieee80211_he_6ghz_capa {
-	/* uses IEEE80211_HE_6GHZ_CAP_* below */
-	__le16 capa;
-} __packed;
-
-/* HE 6 GHz band capabilities */
-/* uses enum ieee80211_min_mpdu_spacing values */
-#define IEEE80211_HE_6GHZ_CAP_MIN_MPDU_START	0x0007
-/* uses enum ieee80211_vht_max_ampdu_length_exp values */
-#define IEEE80211_HE_6GHZ_CAP_MAX_AMPDU_LEN_EXP	0x0038
-/* uses IEEE80211_VHT_CAP_MAX_MPDU_LENGTH_* values */
-#define IEEE80211_HE_6GHZ_CAP_MAX_MPDU_LEN	0x00c0
-/* WLAN_HT_CAP_SM_PS_* values */
-#define IEEE80211_HE_6GHZ_CAP_SM_PS		0x0600
-#define IEEE80211_HE_6GHZ_CAP_RD_RESPONDER	0x0800
-#define IEEE80211_HE_6GHZ_CAP_RX_ANTPAT_CONS	0x1000
-#define IEEE80211_HE_6GHZ_CAP_TX_ANTPAT_CONS	0x2000
-
 /**
  * ieee80211_get_qos_ctl - get pointer to qos control bytes
  * @hdr: the frame
+ * Return: a pointer to the QoS control field in the frame header
  *
  * The qos ctrl bytes come after the frame_control, duration, seq_num
  * and 3 or 4 addresses of length ETH_ALEN. Checks frame_control to choose
@@ -4073,6 +2301,7 @@ static inline u8 *ieee80211_get_qos_ctl(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_get_tid - get qos TID
  * @hdr: the frame
+ * Return: the TID from the QoS control field
  */
 static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr)
 {
@@ -4084,6 +2313,7 @@ static inline u8 ieee80211_get_tid(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_get_SA - get pointer to SA
  * @hdr: the frame
+ * Return: a pointer to the source address (SA)
  *
  * Given an 802.11 frame, this function returns the offset
  * to the source address (SA). It does not verify that the
@@ -4103,6 +2333,7 @@ static inline u8 *ieee80211_get_SA(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_get_DA - get pointer to DA
  * @hdr: the frame
+ * Return: a pointer to the destination address (DA)
  *
  * Given an 802.11 frame, this function returns the offset
  * to the destination address (DA). It does not verify that
@@ -4121,6 +2352,7 @@ static inline u8 *ieee80211_get_DA(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_is_bufferable_mmpdu - check if frame is bufferable MMPDU
  * @skb: the skb to check, starting with the 802.11 header
+ * Return: whether or not the MMPDU is bufferable
  */
 static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb)
 {
@@ -4159,6 +2391,7 @@ static inline bool ieee80211_is_bufferable_mmpdu(struct sk_buff *skb)
 /**
  * _ieee80211_is_robust_mgmt_frame - check if frame is a robust management frame
  * @hdr: the frame (buffer must include at least the first octet of payload)
+ * Return: whether or not the frame is a robust management frame
  */
 static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
 {
@@ -4195,6 +2428,7 @@ static inline bool _ieee80211_is_robust_mgmt_frame(struct ieee80211_hdr *hdr)
 /**
  * ieee80211_is_robust_mgmt_frame - check if skb contains a robust mgmt frame
  * @skb: the skb containing the frame, length will be checked
+ * Return: whether or not the frame is a robust management frame
  */
 static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb)
 {
@@ -4207,6 +2441,7 @@ static inline bool ieee80211_is_robust_mgmt_frame(struct sk_buff *skb)
  * ieee80211_is_public_action - check if frame is a public action frame
  * @hdr: the frame
  * @len: length of the frame
+ * Return: whether or not the frame is a public action frame
  */
 static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr,
 					      size_t len)
@@ -4221,9 +2456,40 @@ static inline bool ieee80211_is_public_action(struct ieee80211_hdr *hdr,
 }
 
 /**
+ * ieee80211_is_protected_dual_of_public_action - check if skb contains a
+ * protected dual of public action management frame
+ * @skb: the skb containing the frame, length will be checked
+ *
+ * Return: true if the skb contains a protected dual of public action
+ * management frame, false otherwise.
+ */
+static inline bool
+ieee80211_is_protected_dual_of_public_action(struct sk_buff *skb)
+{
+	u8 action;
+
+	if (!ieee80211_is_public_action((void *)skb->data, skb->len) ||
+	    skb->len < IEEE80211_MIN_ACTION_SIZE + 1)
+		return false;
+
+	action = *(u8 *)(skb->data + IEEE80211_MIN_ACTION_SIZE);
+
+	return action != WLAN_PUB_ACTION_20_40_BSS_COEX &&
+		action != WLAN_PUB_ACTION_DSE_REG_LOC_ANN &&
+		action != WLAN_PUB_ACTION_MSMT_PILOT &&
+		action != WLAN_PUB_ACTION_TDLS_DISCOVER_RES &&
+		action != WLAN_PUB_ACTION_LOC_TRACK_NOTI &&
+		action != WLAN_PUB_ACTION_FTM_REQUEST &&
+		action != WLAN_PUB_ACTION_FTM_RESPONSE &&
+		action != WLAN_PUB_ACTION_FILS_DISCOVERY &&
+		action != WLAN_PUB_ACTION_VENDOR_SPECIFIC;
+}
+
+/**
  * _ieee80211_is_group_privacy_action - check if frame is a group addressed
- * privacy action frame
+ *	privacy action frame
  * @hdr: the frame
+ * Return: whether or not the frame is a group addressed privacy action frame
  */
 static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr)
 {
@@ -4239,8 +2505,9 @@ static inline bool _ieee80211_is_group_privacy_action(struct ieee80211_hdr *hdr)
 
 /**
  * ieee80211_is_group_privacy_action - check if frame is a group addressed
- * privacy action frame
+ *	privacy action frame
  * @skb: the skb containing the frame, length will be checked
+ * Return: whether or not the frame is a group addressed privacy action frame
  */
 static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb)
 {
@@ -4252,20 +2519,15 @@ static inline bool ieee80211_is_group_privacy_action(struct sk_buff *skb)
 /**
  * ieee80211_tu_to_usec - convert time units (TU) to microseconds
  * @tu: the TUs
+ * Return: the time value converted to microseconds
  */
 static inline unsigned long ieee80211_tu_to_usec(unsigned long tu)
 {
 	return 1024 * tu;
 }
 
-/**
- * ieee80211_check_tim - check if AID bit is set in TIM
- * @tim: the TIM IE
- * @tim_len: length of the TIM IE
- * @aid: the AID to look for
- */
-static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
-				       u8 tim_len, u16 aid)
+static inline bool __ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
+					 u8 tim_len, u16 aid)
 {
 	u8 mask;
 	u8 index, indexn1, indexn2;
@@ -4289,14 +2551,15 @@ static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
 }
 
 /**
- * ieee80211_get_tdls_action - get tdls packet action (or -1, if not tdls packet)
+ * ieee80211_get_tdls_action - get TDLS action code
  * @skb: the skb containing the frame, length will not be checked
- * @hdr_size: the size of the ieee80211_hdr that starts at skb->data
+ * Return: the TDLS action code, or -1 if it's not an encapsulated TDLS action
+ *	frame
  *
  * This function assumes the frame is a data frame, and that the network header
  * is in the correct place.
  */
-static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size)
+static inline int ieee80211_get_tdls_action(struct sk_buff *skb)
 {
 	if (!skb_is_nonlinear(skb) &&
 	    skb->len > (skb_network_offset(skb) + 2)) {
@@ -4331,6 +2594,7 @@ static inline int ieee80211_get_tdls_action(struct sk_buff *skb, u32 hdr_size)
 /**
  * ieee80211_action_contains_tpc - checks if the frame contains TPC element
  * @skb: the skb containing the frame, length will be checked
+ * Return: %true if the frame contains a TPC element, %false otherwise
  *
  * This function checks if it's either TPC report action frame or Link
  * Measurement report action frame as defined in IEEE Std. 802.11-2012 8.5.2.5
@@ -4375,6 +2639,11 @@ static inline bool ieee80211_action_contains_tpc(struct sk_buff *skb)
 	return true;
 }
 
+/**
+ * ieee80211_is_timing_measurement - check if frame is timing measurement response
+ * @skb: the SKB to check
+ * Return: whether or not the frame is a valid timing measurement response
+ */
 static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb)
 {
 	struct ieee80211_mgmt *mgmt = (void *)skb->data;
@@ -4394,6 +2663,11 @@ static inline bool ieee80211_is_timing_measurement(struct sk_buff *skb)
 	return false;
 }
 
+/**
+ * ieee80211_is_ftm - check if frame is FTM response
+ * @skb: the SKB to check
+ * Return: whether or not the frame is a valid FTM response action frame
+ */
 static inline bool ieee80211_is_ftm(struct sk_buff *skb)
 {
 	struct ieee80211_mgmt *mgmt = (void *)skb->data;
@@ -4448,6 +2722,7 @@ struct element {
  * @element: element pointer after for_each_element() or friends
  * @data: same data pointer as passed to for_each_element() or friends
  * @datalen: same data length as passed to for_each_element() or friends
+ * Return: %true if all elements were iterated, %false otherwise; see notes
  *
  * This function returns %true if all the data was parsed or considered
  * while walking the elements. Only use this if your for_each_element()
@@ -4462,7 +2737,7 @@ static inline bool for_each_element_completed(const struct element *element,
 	return (const u8 *)element == (const u8 *)data + datalen;
 }
 
-/**
+/*
  * RSNX Capabilities:
  * bits 0-3: Field length (n-1)
  */
@@ -4477,8 +2752,8 @@ static inline bool for_each_element_completed(const struct element *element,
 #define IEEE80211_AP_INFO_TBTT_HDR_FILTERED			0x04
 #define IEEE80211_AP_INFO_TBTT_HDR_COLOC			0x08
 #define IEEE80211_AP_INFO_TBTT_HDR_COUNT			0xF0
-#define IEEE80211_TBTT_INFO_OFFSET_BSSID_BSS_PARAM		9
-#define IEEE80211_TBTT_INFO_OFFSET_BSSID_SSSID_BSS_PARAM	13
+#define IEEE80211_TBTT_INFO_TYPE_TBTT				0
+#define IEEE80211_TBTT_INFO_TYPE_MLD				1
 
 #define IEEE80211_RNR_TBTT_PARAMS_OCT_RECOMMENDED		0x01
 #define IEEE80211_RNR_TBTT_PARAMS_SAME_SSID			0x02
@@ -4488,6 +2763,9 @@ static inline bool for_each_element_completed(const struct element *element,
 #define IEEE80211_RNR_TBTT_PARAMS_PROBE_ACTIVE			0x20
 #define IEEE80211_RNR_TBTT_PARAMS_COLOC_AP			0x40
 
+#define IEEE80211_RNR_TBTT_PARAMS_PSD_NO_LIMIT			127
+#define IEEE80211_RNR_TBTT_PARAMS_PSD_RESERVED			-128
+
 struct ieee80211_neighbor_ap_info {
 	u8 tbtt_info_hdr;
 	u8 tbtt_info_len;
@@ -4502,269 +2780,64 @@ enum ieee80211_range_params_max_total_ltf {
 	IEEE80211_RANGE_PARAMS_MAX_TOTAL_LTF_UNSPECIFIED,
 };
 
-/* multi-link device */
-#define IEEE80211_MLD_MAX_NUM_LINKS	15
-
-#define IEEE80211_ML_CONTROL_TYPE			0x0007
-#define IEEE80211_ML_CONTROL_TYPE_BASIC			0
-#define IEEE80211_ML_CONTROL_TYPE_PREQ			1
-#define IEEE80211_ML_CONTROL_TYPE_RECONF		2
-#define IEEE80211_ML_CONTROL_TYPE_TDLS			3
-#define IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS		4
-#define IEEE80211_ML_CONTROL_PRESENCE_MASK		0xfff0
-
-struct ieee80211_multi_link_elem {
-	__le16 control;
-	u8 variable[];
+/*
+ * reduced neighbor report, based on Draft P802.11be_D3.0,
+ * section 9.4.2.170.2.
+ */
+struct ieee80211_rnr_mld_params {
+	u8 mld_id;
+	__le16 params;
 } __packed;
 
-#define IEEE80211_MLC_BASIC_PRES_LINK_ID		0x0010
-#define IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT	0x0020
-#define IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY		0x0040
-#define IEEE80211_MLC_BASIC_PRES_EML_CAPA		0x0080
-#define IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP		0x0100
-#define IEEE80211_MLC_BASIC_PRES_MLD_ID			0x0200
-
-#define IEEE80211_MED_SYNC_DELAY_DURATION		0x00ff
-#define IEEE80211_MED_SYNC_DELAY_SYNC_OFDM_ED_THRESH	0x0f00
-#define IEEE80211_MED_SYNC_DELAY_SYNC_MAX_NUM_TXOPS	0xf000
-
-#define IEEE80211_EML_CAP_EMLSR_SUPP			0x0001
-#define IEEE80211_EML_CAP_EMLSR_PADDING_DELAY		0x000e
-#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_0US		0
-#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_32US		1
-#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_64US		2
-#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_128US		3
-#define  IEEE80211_EML_CAP_EMLSR_PADDING_DELAY_256US		4
-#define IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY	0x0070
-#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_0US		0
-#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_16US		1
-#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_32US		2
-#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_64US		3
-#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_128US		4
-#define  IEEE80211_EML_CAP_EMLSR_TRANSITION_DELAY_256US		5
-#define IEEE80211_EML_CAP_EMLMR_SUPPORT			0x0080
-#define IEEE80211_EML_CAP_EMLMR_DELAY			0x0700
-#define  IEEE80211_EML_CAP_EMLMR_DELAY_0US			0
-#define  IEEE80211_EML_CAP_EMLMR_DELAY_32US			1
-#define  IEEE80211_EML_CAP_EMLMR_DELAY_64US			2
-#define  IEEE80211_EML_CAP_EMLMR_DELAY_128US			3
-#define  IEEE80211_EML_CAP_EMLMR_DELAY_256US			4
-#define IEEE80211_EML_CAP_TRANSITION_TIMEOUT		0x7800
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_0			0
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128US		1
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_256US		2
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_512US		3
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_1TU		4
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_2TU		5
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_4TU		6
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_8TU		7
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_16TU		8
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_32TU		9
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_64TU		10
-#define  IEEE80211_EML_CAP_TRANSITION_TIMEOUT_128TU		11
-
-#define IEEE80211_MLD_CAP_OP_MAX_SIMUL_LINKS		0x000f
-#define IEEE80211_MLD_CAP_OP_SRS_SUPPORT		0x0010
-#define IEEE80211_MLD_CAP_OP_TID_TO_LINK_MAP_NEG_SUPP	0x0060
-#define IEEE80211_MLD_CAP_OP_FREQ_SEP_TYPE_IND		0x0f80
-#define IEEE80211_MLD_CAP_OP_AAR_SUPPORT		0x1000
-
-struct ieee80211_mle_basic_common_info {
-	u8 len;
-	u8 mld_mac_addr[ETH_ALEN];
-	u8 variable[];
-} __packed;
+#define IEEE80211_RNR_MLD_PARAMS_LINK_ID			0x000F
+#define IEEE80211_RNR_MLD_PARAMS_BSS_CHANGE_COUNT		0x0FF0
+#define IEEE80211_RNR_MLD_PARAMS_UPDATES_INCLUDED		0x1000
+#define IEEE80211_RNR_MLD_PARAMS_DISABLED_LINK			0x2000
 
-#define IEEE80211_MLC_PREQ_PRES_MLD_ID			0x0010
+/* Format of the TBTT information element if it has 7, 8 or 9 bytes */
+struct ieee80211_tbtt_info_7_8_9 {
+	u8 tbtt_offset;
+	u8 bssid[ETH_ALEN];
 
-struct ieee80211_mle_preq_common_info {
-	u8 len;
-	u8 variable[];
+	/* The following element is optional, structure may not grow */
+	u8 bss_params;
+	s8 psd_20;
 } __packed;
 
-#define IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR		0x0010
-
-/* no fixed fields in RECONF */
+/* Format of the TBTT information element if it has >= 11 bytes */
+struct ieee80211_tbtt_info_ge_11 {
+	u8 tbtt_offset;
+	u8 bssid[ETH_ALEN];
+	__le32 short_ssid;
 
-struct ieee80211_mle_tdls_common_info {
-	u8 len;
-	u8 ap_mld_mac_addr[ETH_ALEN];
+	/* The following elements are optional, structure may grow */
+	u8 bss_params;
+	s8 psd_20;
+	struct ieee80211_rnr_mld_params mld_params;
 } __packed;
 
-#define IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR	0x0010
-
-/* no fixed fields in PRIO_ACCESS */
-
-/**
- * ieee80211_mle_common_size - check multi-link element common size
- * @data: multi-link element, must already be checked for size using
- *	ieee80211_mle_size_ok()
- */
-static inline u8 ieee80211_mle_common_size(const u8 *data)
-{
-	const struct ieee80211_multi_link_elem *mle = (const void *)data;
-	u16 control = le16_to_cpu(mle->control);
-	u8 common = 0;
-
-	switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) {
-	case IEEE80211_ML_CONTROL_TYPE_BASIC:
-	case IEEE80211_ML_CONTROL_TYPE_PREQ:
-	case IEEE80211_ML_CONTROL_TYPE_TDLS:
-		/*
-		 * The length is the first octet pointed by mle->variable so no
-		 * need to add anything
-		 */
-		break;
-	case IEEE80211_ML_CONTROL_TYPE_RECONF:
-		if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR)
-			common += ETH_ALEN;
-		return common;
-	case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS:
-		if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR)
-			common += ETH_ALEN;
-		return common;
-	default:
-		WARN_ON(1);
-		return 0;
-	}
-
-	return sizeof(*mle) + common + mle->variable[0];
-}
-
-/**
- * ieee80211_mle_size_ok - validate multi-link element size
- * @data: pointer to the element data
- * @len: length of the containing element
- */
-static inline bool ieee80211_mle_size_ok(const u8 *data, size_t len)
-{
-	const struct ieee80211_multi_link_elem *mle = (const void *)data;
-	u8 fixed = sizeof(*mle);
-	u8 common = 0;
-	bool check_common_len = false;
-	u16 control;
-
-	if (len < fixed)
-		return false;
-
-	control = le16_to_cpu(mle->control);
-
-	switch (u16_get_bits(control, IEEE80211_ML_CONTROL_TYPE)) {
-	case IEEE80211_ML_CONTROL_TYPE_BASIC:
-		common += sizeof(struct ieee80211_mle_basic_common_info);
-		check_common_len = true;
-		if (control & IEEE80211_MLC_BASIC_PRES_LINK_ID)
-			common += 1;
-		if (control & IEEE80211_MLC_BASIC_PRES_BSS_PARAM_CH_CNT)
-			common += 1;
-		if (control & IEEE80211_MLC_BASIC_PRES_MED_SYNC_DELAY)
-			common += 2;
-		if (control & IEEE80211_MLC_BASIC_PRES_EML_CAPA)
-			common += 2;
-		if (control & IEEE80211_MLC_BASIC_PRES_MLD_CAPA_OP)
-			common += 2;
-		if (control & IEEE80211_MLC_BASIC_PRES_MLD_ID)
-			common += 1;
-		break;
-	case IEEE80211_ML_CONTROL_TYPE_PREQ:
-		common += sizeof(struct ieee80211_mle_preq_common_info);
-		if (control & IEEE80211_MLC_PREQ_PRES_MLD_ID)
-			common += 1;
-		check_common_len = true;
-		break;
-	case IEEE80211_ML_CONTROL_TYPE_RECONF:
-		if (control & IEEE80211_MLC_RECONF_PRES_MLD_MAC_ADDR)
-			common += ETH_ALEN;
-		break;
-	case IEEE80211_ML_CONTROL_TYPE_TDLS:
-		common += sizeof(struct ieee80211_mle_tdls_common_info);
-		check_common_len = true;
-		break;
-	case IEEE80211_ML_CONTROL_TYPE_PRIO_ACCESS:
-		if (control & IEEE80211_MLC_PRIO_ACCESS_PRES_AP_MLD_MAC_ADDR)
-			common += ETH_ALEN;
-		break;
-	default:
-		/* we don't know this type */
-		return true;
-	}
-
-	if (len < fixed + common)
-		return false;
-
-	if (!check_common_len)
-		return true;
-
-	/* if present, common length is the first octet there */
-	return mle->variable[0] >= common;
-}
-
-enum ieee80211_mle_subelems {
-	IEEE80211_MLE_SUBELEM_PER_STA_PROFILE		= 0,
-	IEEE80211_MLE_SUBELEM_FRAGMENT		        = 254,
-};
-
-#define IEEE80211_MLE_STA_CONTROL_LINK_ID			0x000f
-#define IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE		0x0010
-#define IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT		0x0020
-#define IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT		0x0040
-#define IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT		0x0080
-#define IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT		0x0100
-#define IEEE80211_MLE_STA_CONTROL_NSTR_LINK_PAIR_PRESENT	0x0200
-#define IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE		0x0400
-#define IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT	0x0800
-
-struct ieee80211_mle_per_sta_profile {
-	__le16 control;
-	u8 sta_info_len;
-	u8 variable[];
-} __packed;
+#include "ieee80211-ht.h"
+#include "ieee80211-vht.h"
+#include "ieee80211-he.h"
+#include "ieee80211-eht.h"
+#include "ieee80211-mesh.h"
+#include "ieee80211-s1g.h"
+#include "ieee80211-p2p.h"
+#include "ieee80211-nan.h"
 
 /**
- * ieee80211_mle_sta_prof_size_ok - validate multi-link element sta profile size
- * @data: pointer to the sub element data
- * @len: length of the containing sub element
+ * ieee80211_check_tim - check if AID bit is set in TIM
+ * @tim: the TIM IE
+ * @tim_len: length of the TIM IE
+ * @aid: the AID to look for
+ * @s1g: whether the TIM is from an S1G PPDU
+ * Return: whether or not traffic is indicated in the TIM for the given AID
  */
-static inline bool ieee80211_mle_sta_prof_size_ok(const u8 *data, size_t len)
+static inline bool ieee80211_check_tim(const struct ieee80211_tim_ie *tim,
+				       u8 tim_len, u16 aid, bool s1g)
 {
-	const struct ieee80211_mle_per_sta_profile *prof = (const void *)data;
-	u16 control;
-	u8 fixed = sizeof(*prof);
-	u8 info_len = 1;
-
-	if (len < fixed)
-		return false;
-
-	control = le16_to_cpu(prof->control);
-
-	if (control & IEEE80211_MLE_STA_CONTROL_STA_MAC_ADDR_PRESENT)
-		info_len += 6;
-	if (control & IEEE80211_MLE_STA_CONTROL_BEACON_INT_PRESENT)
-		info_len += 2;
-	if (control & IEEE80211_MLE_STA_CONTROL_TSF_OFFS_PRESENT)
-		info_len += 8;
-	if (control & IEEE80211_MLE_STA_CONTROL_DTIM_INFO_PRESENT)
-		info_len += 2;
-	if (control & IEEE80211_MLE_STA_CONTROL_BSS_PARAM_CHANGE_CNT_PRESENT)
-		info_len += 1;
-
-	if (control & IEEE80211_MLE_STA_CONTROL_COMPLETE_PROFILE &&
-	    control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE) {
-		if (control & IEEE80211_MLE_STA_CONTROL_NSTR_BITMAP_SIZE)
-			info_len += 2;
-		else
-			info_len += 1;
-	}
-
-	return prof->sta_info_len >= info_len &&
-	       fixed + prof->sta_info_len <= len;
+	return s1g ? ieee80211_s1g_check_tim(tim, tim_len, aid) :
+		     __ieee80211_check_tim(tim, tim_len, aid);
 }
 
-#define for_each_mle_subelement(_elem, _data, _len)			\
-	if (ieee80211_mle_size_ok(_data, _len))				\
-		for_each_element(_elem,					\
-				 _data + ieee80211_mle_common_size(_data),\
-				 _len - ieee80211_mle_common_size(_data))
-
 #endif /* LINUX_IEEE80211_H */
diff --git a/include/linux/if_arp.h b/include/linux/if_arp.h
index 1ed52441972f..10a1e81434cb 100644
--- a/include/linux/if_arp.h
+++ b/include/linux/if_arp.h
@@ -53,6 +53,10 @@ static inline bool dev_is_mac_header_xmit(const struct net_device *dev)
 	case ARPHRD_NONE:
 	case ARPHRD_RAWIP:
 	case ARPHRD_PIMREG:
+	/* PPP adds its l2 header automatically in ppp_start_xmit().
+	 * This makes it look like an l3 device to __bpf_redirect() and tcf_mirred_init().
+	 */
+	case ARPHRD_PPP:
 		return false;
 	default:
 		return true;
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 3ff96ae31bf6..c5fe3b2a53e8 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -65,11 +65,9 @@ struct br_ip_list {
 #define BR_DEFAULT_AGEING_TIME	(300 * HZ)
 
 struct net_bridge;
-void brioctl_set(int (*hook)(struct net *net, struct net_bridge *br,
-			     unsigned int cmd, struct ifreq *ifr,
+void brioctl_set(int (*hook)(struct net *net, unsigned int cmd,
 			     void __user *uarg));
-int br_ioctl_call(struct net *net, struct net_bridge *br, unsigned int cmd,
-		  struct ifreq *ifr, void __user *uarg);
+int br_ioctl_call(struct net *net, unsigned int cmd, void __user *uarg);
 
 #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_IGMP_SNOOPING)
 int br_multicast_list_adjacent(struct net_device *dev,
diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h
index 8a9792a6427a..61b7335aa037 100644
--- a/include/linux/if_ether.h
+++ b/include/linux/if_ether.h
@@ -19,6 +19,9 @@
 #include <linux/skbuff.h>
 #include <uapi/linux/if_ether.h>
 
+/* XX:XX:XX:XX:XX:XX */
+#define MAC_ADDR_STR_LEN (3 * ETH_ALEN - 1)
+
 static inline struct ethhdr *eth_hdr(const struct sk_buff *skb)
 {
 	return (struct ethhdr *)skb_mac_header(skb);
diff --git a/include/linux/if_hsr.h b/include/linux/if_hsr.h
index 0404f5bf4f30..f4cf2dd36d19 100644
--- a/include/linux/if_hsr.h
+++ b/include/linux/if_hsr.h
@@ -13,6 +13,15 @@ enum hsr_version {
 	PRP_V1,
 };
 
+enum hsr_port_type {
+	HSR_PT_NONE = 0,	/* Must be 0, used by framereg */
+	HSR_PT_SLAVE_A,
+	HSR_PT_SLAVE_B,
+	HSR_PT_INTERLINK,
+	HSR_PT_MASTER,
+	HSR_PT_PORTS,	/* This must be the last item in the enum */
+};
+
 /* HSR Tag.
  * As defined in IEC-62439-3:2010, the HSR tag is really { ethertype = 0x88FB,
  * path, LSDU_size, sequence Nr }. But we let eth_header() create { h_dest,
@@ -32,6 +41,10 @@ struct hsr_tag {
 #if IS_ENABLED(CONFIG_HSR)
 extern bool is_hsr_master(struct net_device *dev);
 extern int hsr_get_version(struct net_device *dev, enum hsr_version *ver);
+struct net_device *hsr_get_port_ndev(struct net_device *ndev,
+				     enum hsr_port_type pt);
+int hsr_get_port_type(struct net_device *hsr_dev, struct net_device *dev,
+		      enum hsr_port_type *type);
 #else
 static inline bool is_hsr_master(struct net_device *dev)
 {
@@ -42,6 +55,19 @@ static inline int hsr_get_version(struct net_device *dev,
 {
 	return -EINVAL;
 }
+
+static inline struct net_device *hsr_get_port_ndev(struct net_device *ndev,
+						   enum hsr_port_type pt)
+{
+	return ERR_PTR(-EINVAL);
+}
+
+static inline int hsr_get_port_type(struct net_device *hsr_dev,
+				    struct net_device *dev,
+				    enum hsr_port_type *type)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_HSR */
 
 #endif /*_LINUX_IF_HSR_H_*/
diff --git a/include/linux/if_ltalk.h b/include/linux/if_ltalk.h
deleted file mode 100644
index 4cc1c0b77870..000000000000
--- a/include/linux/if_ltalk.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_LTALK_H
-#define __LINUX_LTALK_H
-
-#include <uapi/linux/if_ltalk.h>
-
-extern struct net_device *alloc_ltalkdev(int sizeof_priv);
-#endif
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 523025106a64..0f7281e3e448 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -59,8 +59,10 @@ static inline void macvlan_count_rx(const struct macvlan_dev *vlan,
 
 extern void macvlan_common_setup(struct net_device *dev);
 
-extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev,
-				  struct nlattr *tb[], struct nlattr *data[],
+struct rtnl_newlink_params;
+
+extern int macvlan_common_newlink(struct net_device *dev,
+				  struct rtnl_newlink_params *params,
 				  struct netlink_ext_ack *extack);
 
 extern void macvlan_dellink(struct net_device *dev, struct list_head *head);
diff --git a/include/linux/if_pppox.h b/include/linux/if_pppox.h
index ff3beda1312c..db45d6f1c4f4 100644
--- a/include/linux/if_pppox.h
+++ b/include/linux/if_pppox.h
@@ -43,7 +43,7 @@ struct pppox_sock {
 	/* struct sock must be the first member of pppox_sock */
 	struct sock sk;
 	struct ppp_channel chan;
-	struct pppox_sock	*next;	  /* for hash table */
+	struct pppox_sock __rcu	*next;	  /* for hash table */
 	union {
 		struct pppoe_opt pppoe;
 		struct pptp_opt  pptp;
diff --git a/include/linux/if_rmnet.h b/include/linux/if_rmnet.h
index 839d1e48b85e..c44bf6e80ecb 100644
--- a/include/linux/if_rmnet.h
+++ b/include/linux/if_rmnet.h
@@ -42,7 +42,7 @@ struct rmnet_map_ul_csum_header {
 
 /* csum_info field:
  *  OFFSET:	where (offset in bytes) to insert computed checksum
- *  UDP:	1 = UDP checksum (zero checkum means no checksum)
+ *  UDP:	1 = UDP checksum (zero checksum means no checksum)
  *  ENABLED:	1 = checksum computation requested
  */
 #define MAP_CSUM_UL_OFFSET_MASK		GENMASK(13, 0)
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index 8de6b6e67829..ce97d891cf72 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -162,8 +162,8 @@ struct team_option {
 	bool per_port;
 	unsigned int array_size; /* != 0 means the option is array */
 	enum team_option_type type;
-	int (*init)(struct team *team, struct team_option_inst_info *info);
-	int (*getter)(struct team *team, struct team_gsetter_ctx *ctx);
+	void (*init)(struct team *team, struct team_option_inst_info *info);
+	void (*getter)(struct team *team, struct team_gsetter_ctx *ctx);
 	int (*setter)(struct team *team, struct team_gsetter_ctx *ctx);
 };
 
@@ -189,7 +189,7 @@ struct team {
 	struct net_device *dev; /* associated netdevice */
 	struct team_pcpu_stats __percpu *pcpu_stats;
 
-	struct mutex lock; /* used for overall locking, e.g. port lists write */
+	const struct header_ops *header_ops_cache;
 
 	/*
 	 * List of enabled ports and their count
@@ -221,7 +221,6 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
-	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 2a7660843444..80166eb62f41 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -19,52 +19,57 @@ struct tun_msg_ctl {
 	void *ptr;
 };
 
-struct tun_xdp_hdr {
-	int buflen;
-	struct virtio_net_hdr gso;
-};
-
 #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
 struct socket *tun_get_socket(struct file *);
 struct ptr_ring *tun_get_tx_ring(struct file *file);
+
 static inline bool tun_is_xdp_frame(void *ptr)
 {
-       return (unsigned long)ptr & TUN_XDP_FLAG;
+	return (unsigned long)ptr & TUN_XDP_FLAG;
 }
+
 static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp)
 {
-       return (void *)((unsigned long)xdp | TUN_XDP_FLAG);
+	return (void *)((unsigned long)xdp | TUN_XDP_FLAG);
 }
+
 static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr)
 {
-       return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
+	return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
 }
+
 void tun_ptr_free(void *ptr);
 #else
 #include <linux/err.h>
 #include <linux/errno.h>
 struct file;
 struct socket;
+
 static inline struct socket *tun_get_socket(struct file *f)
 {
 	return ERR_PTR(-EINVAL);
 }
+
 static inline struct ptr_ring *tun_get_tx_ring(struct file *f)
 {
 	return ERR_PTR(-EINVAL);
 }
+
 static inline bool tun_is_xdp_frame(void *ptr)
 {
 	return false;
 }
+
 static inline void *tun_xdp_to_ptr(struct xdp_frame *xdp)
 {
 	return NULL;
 }
+
 static inline struct xdp_frame *tun_ptr_to_xdp(void *ptr)
 {
 	return NULL;
 }
+
 static inline void tun_ptr_free(void *ptr)
 {
 }
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 6ba71957851e..f7f34eb15e06 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -79,11 +79,6 @@ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb)
 /* found in socket.c */
 extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
-static inline bool is_vlan_dev(const struct net_device *dev)
-{
-        return dev->priv_flags & IFF_802_1Q_VLAN;
-}
-
 #define skb_vlan_tag_present(__skb)	(!!(__skb)->vlan_all)
 #define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci)
 #define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
@@ -136,7 +131,7 @@ struct vlan_pcpu_stats {
 	u32			tx_dropped;
 };
 
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
 
 extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
@@ -176,6 +171,7 @@ struct netpoll;
  *	@real_dev_addr: address of underlying netdevice
  *	@dent: proc dir entry
  *	@vlan_pcpu_stats: ptr to percpu rx stats
+ *	@netpoll: netpoll instance "propagated" down to @real_dev
  */
 struct vlan_dev_priv {
 	unsigned int				nr_ingress_mappings;
@@ -199,6 +195,11 @@ struct vlan_dev_priv {
 #endif
 };
 
+static inline bool is_vlan_dev(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN;
+}
+
 static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
 {
 	return netdev_priv(dev);
@@ -236,6 +237,11 @@ extern void vlan_vids_del_by_dev(struct net_device *dev,
 extern bool vlan_uses_dev(const struct net_device *dev);
 
 #else
+static inline bool is_vlan_dev(const struct net_device *dev)
+{
+	return false;
+}
+
 static inline struct net_device *
 __vlan_find_dev_deep_rcu(struct net_device *real_dev,
 		     __be16 vlan_proto, u16 vlan_id)
@@ -253,19 +259,19 @@ vlan_for_each(struct net_device *dev,
 
 static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return NULL;
 }
 
 static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return 0;
 }
 
 static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return 0;
 }
 
@@ -310,7 +316,7 @@ static inline bool vlan_uses_dev(const struct net_device *dev)
  * eth_type_vlan - check for valid vlan ether type.
  * @ethertype: ether type to check
  *
- * Returns true if the ether type is a vlan ether type.
+ * Returns: true if the ether type is a vlan ether type.
  */
 static inline bool eth_type_vlan(__be16 ethertype)
 {
@@ -341,24 +347,25 @@ static inline bool vlan_hw_offload_capable(netdev_features_t features,
  * @mac_len: MAC header length including outer vlan headers
  *
  * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
- * Returns error if skb_cow_head fails.
- *
  * Does not change skb->protocol so this function can be used during receive.
+ *
+ * Returns: error if skb_cow_head fails.
  */
 static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
 					  __be16 vlan_proto, u16 vlan_tci,
 					  unsigned int mac_len)
 {
+	const u8 meta_len = mac_len > ETH_TLEN ? skb_metadata_len(skb) : 0;
 	struct vlan_ethhdr *veth;
 
-	if (skb_cow_head(skb, VLAN_HLEN) < 0)
+	if (skb_cow_head(skb, meta_len + VLAN_HLEN) < 0)
 		return -ENOMEM;
 
 	skb_push(skb, VLAN_HLEN);
 
 	/* Move the mac header sans proto to the beginning of the new header. */
 	if (likely(mac_len > ETH_TLEN))
-		memmove(skb->data, skb->data + VLAN_HLEN, mac_len - ETH_TLEN);
+		skb_postpush_data_move(skb, VLAN_HLEN, mac_len - ETH_TLEN);
 	if (skb_mac_header_was_set(skb))
 		skb->mac_header -= VLAN_HLEN;
 
@@ -390,9 +397,9 @@ static inline int __vlan_insert_inner_tag(struct sk_buff *skb,
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
- * Returns error if skb_cow_head fails.
- *
  * Does not change skb->protocol so this function can be used during receive.
+ *
+ * Returns: error if skb_cow_head fails.
  */
 static inline int __vlan_insert_tag(struct sk_buff *skb,
 				    __be16 vlan_proto, u16 vlan_tci)
@@ -408,12 +415,14 @@ static inline int __vlan_insert_tag(struct sk_buff *skb,
  * @mac_len: MAC header length including outer vlan headers
  *
  * Inserts the VLAN tag into @skb as part of the payload at offset mac_len
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * Returns a VLAN tagged skb. This might change skb->head.
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
  *
  * Does not change skb->protocol so this function can be used during receive.
+ *
+ * Return: modified @skb on success, NULL on error (@skb is freed).
  */
 static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
 						    __be16 vlan_proto,
@@ -437,12 +446,14 @@ static inline struct sk_buff *vlan_insert_inner_tag(struct sk_buff *skb,
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * Returns a VLAN tagged skb. This might change skb->head.
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
  *
  * Does not change skb->protocol so this function can be used during receive.
+ *
+ * Return: modified @skb on success, NULL on error (@skb is freed).
  */
 static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
 					      __be16 vlan_proto, u16 vlan_tci)
@@ -457,10 +468,12 @@ static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb,
  * @vlan_tci: VLAN TCI to insert
  *
  * Inserts the VLAN tag into @skb as part of the payload
- * Returns a VLAN tagged skb. If a new skb is created, @skb is freed.
+ * Returns a VLAN tagged skb. This might change skb->head.
  *
  * Following the skb_unshare() example, in case of error, the calling function
  * doesn't have to worry about freeing the original skb.
+ *
+ * Return: modified @skb on success, NULL on error (@skb is freed).
  */
 static inline struct sk_buff *vlan_insert_tag_set_proto(struct sk_buff *skb,
 							__be16 vlan_proto,
@@ -533,14 +546,14 @@ static inline void __vlan_hwaccel_put_tag(struct sk_buff *skb,
  * @skb: skbuff to query
  * @vlan_tci: buffer to store value
  *
- * Returns error if the skb is not of VLAN type
+ * Returns: error if the skb is not of VLAN type
  */
 static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 {
 	struct vlan_ethhdr *veth = skb_vlan_eth_hdr(skb);
 
 	if (!eth_type_vlan(veth->h_vlan_proto))
-		return -EINVAL;
+		return -ENODATA;
 
 	*vlan_tci = ntohs(veth->h_vlan_TCI);
 	return 0;
@@ -551,7 +564,7 @@ static inline int __vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
  * @skb: skbuff to query
  * @vlan_tci: buffer to store value
  *
- * Returns error if @skb->vlan_tci is not set correctly
+ * Returns: error if @skb->vlan_tci is not set correctly
  */
 static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
 					 u16 *vlan_tci)
@@ -561,7 +574,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
 		return 0;
 	} else {
 		*vlan_tci = 0;
-		return -EINVAL;
+		return -ENODATA;
 	}
 }
 
@@ -570,7 +583,7 @@ static inline int __vlan_hwaccel_get_tag(const struct sk_buff *skb,
  * @skb: skbuff to query
  * @vlan_tci: buffer to store value
  *
- * Returns error if the skb is not VLAN tagged
+ * Returns: error if the skb is not VLAN tagged
  */
 static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 {
@@ -582,16 +595,19 @@ static inline int vlan_get_tag(const struct sk_buff *skb, u16 *vlan_tci)
 }
 
 /**
- * vlan_get_protocol - get protocol EtherType.
+ * __vlan_get_protocol_offset() - get protocol EtherType.
  * @skb: skbuff to query
  * @type: first vlan protocol
+ * @mac_offset: MAC offset
  * @depth: buffer to store length of eth and vlan tags in bytes
  *
- * Returns the EtherType of the packet, regardless of whether it is
+ * Returns: the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
-					 int *depth)
+static inline __be16 __vlan_get_protocol_offset(const struct sk_buff *skb,
+						__be16 type,
+						int mac_offset,
+						int *depth)
 {
 	unsigned int vlan_depth = skb->mac_len, parse_depth = VLAN_MAX_DEPTH;
 
@@ -610,7 +626,8 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 		do {
 			struct vlan_hdr vhdr, *vh;
 
-			vh = skb_header_pointer(skb, vlan_depth, sizeof(vhdr), &vhdr);
+			vh = skb_header_pointer(skb, mac_offset + vlan_depth,
+						sizeof(vhdr), &vhdr);
 			if (unlikely(!vh || !--parse_depth))
 				return 0;
 
@@ -625,11 +642,17 @@ static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
 	return type;
 }
 
+static inline __be16 __vlan_get_protocol(const struct sk_buff *skb, __be16 type,
+					 int *depth)
+{
+	return __vlan_get_protocol_offset(skb, type, 0, depth);
+}
+
 /**
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
  *
- * Returns the EtherType of the packet, regardless of whether it is
+ * Returns: the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
 static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
@@ -709,25 +732,23 @@ static inline void vlan_set_encap_proto(struct sk_buff *skb,
  *
  * Expects the skb to contain a VLAN tag in the payload, and to have skb->data
  * pointing at the MAC header.
- *
- * Returns a new pointer to skb->data, or NULL on failure to pull.
  */
-static inline void *vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci)
+static inline void vlan_remove_tag(struct sk_buff *skb, u16 *vlan_tci)
 {
 	struct vlan_hdr *vhdr = (struct vlan_hdr *)(skb->data + ETH_HLEN);
 
 	*vlan_tci = ntohs(vhdr->h_vlan_TCI);
 
-	memmove(skb->data + VLAN_HLEN, skb->data, 2 * ETH_ALEN);
 	vlan_set_encap_proto(skb, vhdr);
-	return __skb_pull(skb, VLAN_HLEN);
+	__skb_pull(skb, VLAN_HLEN);
+	skb_postpull_data_move(skb, VLAN_HLEN, 2 * ETH_ALEN);
 }
 
 /**
  * skb_vlan_tagged - check if skb is vlan tagged.
  * @skb: skbuff to query
  *
- * Returns true if the skb is tagged, regardless of whether it is hardware
+ * Returns: true if the skb is tagged, regardless of whether it is hardware
  * accelerated or not.
  */
 static inline bool skb_vlan_tagged(const struct sk_buff *skb)
@@ -743,7 +764,7 @@ static inline bool skb_vlan_tagged(const struct sk_buff *skb)
  * skb_vlan_tagged_multi - check if skb is vlan tagged with multiple headers.
  * @skb: skbuff to query
  *
- * Returns true if the skb is tagged with multiple vlan headers, regardless
+ * Returns: true if the skb is tagged with multiple vlan headers, regardless
  * of whether it is hardware accelerated or not.
  */
 static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
@@ -774,7 +795,7 @@ static inline bool skb_vlan_tagged_multi(struct sk_buff *skb)
  * @skb: skbuff to query
  * @features: features to be checked
  *
- * Returns features without unsafe ones if the skb has multiple tags.
+ * Returns: features without unsafe ones if the skb has multiple tags.
  */
 static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
 						    netdev_features_t features)
@@ -798,9 +819,11 @@ static inline netdev_features_t vlan_features_check(struct sk_buff *skb,
  * @h1: Pointer to vlan header
  * @h2: Pointer to vlan header
  *
- * Compare two vlan headers, returns 0 if equal.
+ * Compare two vlan headers.
  *
  * Please note that alignment of h1 & h2 are only guaranteed to be 16 bits.
+ *
+ * Return: 0 if equal, arbitrary non-zero value if not equal.
  */
 static inline unsigned long compare_vlan_header(const struct vlan_hdr *h1,
 						const struct vlan_hdr *h2)
diff --git a/include/linux/igmp.h b/include/linux/igmp.h
index ebf4349a53af..073b30a9b850 100644
--- a/include/linux/igmp.h
+++ b/include/linux/igmp.h
@@ -39,7 +39,7 @@ struct ip_sf_socklist {
 	unsigned int		sl_max;
 	unsigned int		sl_count;
 	struct rcu_head		rcu;
-	__be32			sl_addr[];
+	__be32			sl_addr[] __counted_by(sl_max);
 };
 
 #define IP_SFBLOCK	10	/* allocate this many at once */
@@ -87,6 +87,8 @@ struct ip_mc_list {
 	char			loaded;
 	unsigned char		gsquery;	/* check source marks? */
 	unsigned char		crcount;
+	unsigned long		mca_cstamp;
+	unsigned long		mca_tstamp;
 	struct rcu_head		rcu;
 };
 
diff --git a/include/linux/iio/adc-helpers.h b/include/linux/iio/adc-helpers.h
new file mode 100644
index 000000000000..56b092a2a4c4
--- /dev/null
+++ b/include/linux/iio/adc-helpers.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+/*
+ * The industrial I/O ADC firmware property parsing helpers
+ *
+ * Copyright (c) 2025 Matti Vaittinen <mazziesaccount@gmail.com>
+ */
+
+#ifndef _INDUSTRIAL_IO_ADC_HELPERS_H_
+#define _INDUSTRIAL_IO_ADC_HELPERS_H_
+
+#include <linux/property.h>
+
+struct device;
+struct iio_chan_spec;
+
+static inline int iio_adc_device_num_channels(struct device *dev)
+{
+	return device_get_named_child_node_count(dev, "channel");
+}
+
+int devm_iio_adc_device_alloc_chaninfo_se(struct device *dev,
+					  const struct iio_chan_spec *template,
+					  int max_chan_id,
+					  struct iio_chan_spec **cs);
+
+#endif /* _INDUSTRIAL_IO_ADC_HELPERS_H_ */
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 7852f6c9a714..6e70a412e218 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -8,6 +8,8 @@
 #ifndef __AD_SIGMA_DELTA_H__
 #define __AD_SIGMA_DELTA_H__
 
+#include <linux/iio/iio.h>
+
 enum ad_sigma_delta_mode {
 	AD_SD_MODE_CONTINUOUS = 0,
 	AD_SD_MODE_SINGLE = 1,
@@ -27,7 +29,10 @@ struct ad_sd_calib_data {
 
 struct ad_sigma_delta;
 struct device;
+struct gpio_desc;
 struct iio_dev;
+struct spi_offload;
+struct spi_offload_trigger;
 
 /**
  * struct ad_sigma_delta_info - Sigma Delta driver specific callbacks and options
@@ -35,10 +40,19 @@ struct iio_dev;
  * @append_status: Will be called to enable status append at the end of the sample, may be NULL.
  * @set_mode: Will be called to select the current mode, may be NULL.
  * @disable_all: Will be called to disable all channels, may be NULL.
+ * @disable_one: Will be called to disable a single channel after
+ *		ad_sigma_delta_single_conversion(), may be NULL.
+ *		Usage of this callback expects iio_chan_spec.address to contain
+ *		the value required for the driver to identify the channel.
  * @postprocess_sample: Is called for each sampled data word, can be used to
  *		modify or drop the sample data, it, may be NULL.
  * @has_registers: true if the device has writable and readable registers, false
  *		if there is just one read-only sample data shift register.
+ * @has_named_irqs: Set to true if there is more than one IRQ line.
+ * @supports_spi_offload: Set to true if the driver supports SPI offload. Often
+ *		special considerations are needed for scan_type and other channel
+ *		info, so individual drivers have to set this to let the core
+ *		code know that it can use SPI offload if it is available.
  * @addr_shift: Shift of the register address in the communications register.
  * @read_mask: Mask for the communications register having the read bit set.
  * @status_ch_mask: Mask for the channel number stored in status register.
@@ -46,20 +60,25 @@ struct iio_dev;
  *   be used.
  * @irq_flags: flags for the interrupt used by the triggered buffer
  * @num_slots: Number of sequencer slots
+ * @num_resetclks: Number of SPI clk cycles with MOSI=1 to reset the chip.
  */
 struct ad_sigma_delta_info {
 	int (*set_channel)(struct ad_sigma_delta *, unsigned int channel);
 	int (*append_status)(struct ad_sigma_delta *, bool append);
 	int (*set_mode)(struct ad_sigma_delta *, enum ad_sigma_delta_mode mode);
 	int (*disable_all)(struct ad_sigma_delta *);
+	int (*disable_one)(struct ad_sigma_delta *, unsigned int chan);
 	int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample);
 	bool has_registers;
+	bool has_named_irqs;
+	bool supports_spi_offload;
 	unsigned int addr_shift;
 	unsigned int read_mask;
 	unsigned int status_ch_mask;
 	unsigned int data_reg;
 	unsigned long irq_flags;
 	unsigned int num_slots;
+	unsigned int num_resetclks;
 };
 
 /**
@@ -76,21 +95,28 @@ struct ad_sigma_delta {
 
 /* private: */
 	struct completion	completion;
+	spinlock_t		irq_lock; /* protects .irq_dis and irq en/disable state */
 	bool			irq_dis;
 
 	bool			bus_locked;
 	bool			keep_cs_asserted;
 
-	uint8_t			comm;
+	u8			comm;
 
 	const struct ad_sigma_delta_info *info;
 	unsigned int		active_slots;
 	unsigned int		current_slot;
 	unsigned int		num_slots;
+	struct gpio_desc	*rdy_gpiod;
+	int			irq_line;
 	bool			status_appended;
 	/* map slots to channels in order to know what to expect from devices */
 	unsigned int		*slots;
-	uint8_t			*samples_buf;
+	struct spi_message	sample_msg;
+	struct spi_transfer	sample_xfer[2];
+	u8			*samples_buf;
+	struct spi_offload	*offload;
+	struct spi_offload_trigger *offload_trigger;
 
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
@@ -99,10 +125,16 @@ struct ad_sigma_delta {
 	 * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp,
 	 * rounded to 16 bytes to take into account padding.
 	 */
-	uint8_t				tx_buf[4] ____cacheline_aligned;
-	uint8_t				rx_buf[16] __aligned(8);
+	u8				tx_buf[4] __aligned(IIO_DMA_MINALIGN);
+	u8				rx_buf[16] __aligned(8);
+	u8				sample_addr;
 };
 
+static inline bool ad_sigma_delta_has_spi_offload(struct ad_sigma_delta *sd)
+{
+	return sd->offload != NULL;
+}
+
 static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd,
 	unsigned int channel)
 {
@@ -135,6 +167,15 @@ static inline int ad_sigma_delta_disable_all(struct ad_sigma_delta *sd)
 	return 0;
 }
 
+static inline int ad_sigma_delta_disable_one(struct ad_sigma_delta *sd,
+					     unsigned int chan)
+{
+	if (sd->info->disable_one)
+		return sd->info->disable_one(sd, chan);
+
+	return 0;
+}
+
 static inline int ad_sigma_delta_set_mode(struct ad_sigma_delta *sd,
 	unsigned int mode)
 {
@@ -153,14 +194,13 @@ static inline int ad_sigma_delta_postprocess_sample(struct ad_sigma_delta *sd,
 	return 0;
 }
 
-void ad_sd_set_comm(struct ad_sigma_delta *sigma_delta, uint8_t comm);
+void ad_sd_set_comm(struct ad_sigma_delta *sigma_delta, u8 comm);
 int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int val);
 int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int *val);
 
-int ad_sd_reset(struct ad_sigma_delta *sigma_delta,
-	unsigned int reset_length);
+int ad_sd_reset(struct ad_sigma_delta *sigma_delta);
 
 int ad_sigma_delta_single_conversion(struct iio_dev *indio_dev,
 	const struct iio_chan_spec *chan, int *val);
diff --git a/include/linux/iio/adc/adi-axi-adc.h b/include/linux/iio/adc/adi-axi-adc.h
deleted file mode 100644
index 52620e5b8052..000000000000
--- a/include/linux/iio/adc/adi-axi-adc.h
+++ /dev/null
@@ -1,64 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Analog Devices Generic AXI ADC IP core driver/library
- * Link: https://wiki.analog.com/resources/fpga/docs/axi_adc_ip
- *
- * Copyright 2012-2020 Analog Devices Inc.
- */
-#ifndef __ADI_AXI_ADC_H__
-#define __ADI_AXI_ADC_H__
-
-struct device;
-struct iio_chan_spec;
-
-/**
- * struct adi_axi_adc_chip_info - Chip specific information
- * @name		Chip name
- * @id			Chip ID (usually product ID)
- * @channels		Channel specifications of type @struct iio_chan_spec
- * @num_channels	Number of @channels
- * @scale_table		Supported scales by the chip; tuples of 2 ints
- * @num_scales		Number of scales in the table
- * @max_rate		Maximum sampling rate supported by the device
- */
-struct adi_axi_adc_chip_info {
-	const char			*name;
-	unsigned int			id;
-
-	const struct iio_chan_spec	*channels;
-	unsigned int			num_channels;
-
-	const unsigned int		(*scale_table)[2];
-	int				num_scales;
-
-	unsigned long			max_rate;
-};
-
-/**
- * struct adi_axi_adc_conv - data of the ADC attached to the AXI ADC
- * @chip_info		chip info details for the client ADC
- * @preenable_setup	op to run in the client before enabling the AXI ADC
- * @reg_access		IIO debugfs_reg_access hook for the client ADC
- * @read_raw		IIO read_raw hook for the client ADC
- * @write_raw		IIO write_raw hook for the client ADC
- */
-struct adi_axi_adc_conv {
-	const struct adi_axi_adc_chip_info		*chip_info;
-
-	int (*preenable_setup)(struct adi_axi_adc_conv *conv);
-	int (*reg_access)(struct adi_axi_adc_conv *conv, unsigned int reg,
-			  unsigned int writeval, unsigned int *readval);
-	int (*read_raw)(struct adi_axi_adc_conv *conv,
-			struct iio_chan_spec const *chan,
-			int *val, int *val2, long mask);
-	int (*write_raw)(struct adi_axi_adc_conv *conv,
-			 struct iio_chan_spec const *chan,
-			 int val, int val2, long mask);
-};
-
-struct adi_axi_adc_conv *devm_adi_axi_adc_conv_register(struct device *dev,
-							size_t sizeof_priv);
-
-void *adi_axi_adc_conv_priv(struct adi_axi_adc_conv *conv);
-
-#endif
diff --git a/include/linux/iio/adc/qcom-vadc-common.h b/include/linux/iio/adc/qcom-vadc-common.h
index aa21b032e861..3bf4c49726a7 100644
--- a/include/linux/iio/adc/qcom-vadc-common.h
+++ b/include/linux/iio/adc/qcom-vadc-common.h
@@ -83,27 +83,27 @@ struct vadc_linear_graph {
 /**
  * enum vadc_scale_fn_type - Scaling function to convert ADC code to
  *				physical scaled units for the channel.
- * SCALE_DEFAULT: Default scaling to convert raw adc code to voltage (uV).
- * SCALE_THERM_100K_PULLUP: Returns temperature in millidegC.
+ * @SCALE_DEFAULT: Default scaling to convert raw adc code to voltage (uV).
+ * @SCALE_THERM_100K_PULLUP: Returns temperature in millidegC.
  *				 Uses a mapping table with 100K pullup.
- * SCALE_PMIC_THERM: Returns result in milli degree's Centigrade.
- * SCALE_XOTHERM: Returns XO thermistor voltage in millidegC.
- * SCALE_PMI_CHG_TEMP: Conversion for PMI CHG temp
- * SCALE_HW_CALIB_DEFAULT: Default scaling to convert raw adc code to
+ * @SCALE_PMIC_THERM: Returns result in milli degree's Centigrade.
+ * @SCALE_XOTHERM: Returns XO thermistor voltage in millidegC.
+ * @SCALE_PMI_CHG_TEMP: Conversion for PMI CHG temp
+ * @SCALE_HW_CALIB_DEFAULT: Default scaling to convert raw adc code to
  *	voltage (uV) with hardware applied offset/slope values to adc code.
- * SCALE_HW_CALIB_THERM_100K_PULLUP: Returns temperature in millidegC using
+ * @SCALE_HW_CALIB_THERM_100K_PULLUP: Returns temperature in millidegC using
  *	lookup table. The hardware applies offset/slope to adc code.
- * SCALE_HW_CALIB_XOTHERM: Returns XO thermistor voltage in millidegC using
+ * @SCALE_HW_CALIB_XOTHERM: Returns XO thermistor voltage in millidegC using
  *	100k pullup. The hardware applies offset/slope to adc code.
- * SCALE_HW_CALIB_THERM_100K_PU_PM7: Returns temperature in millidegC using
+ * @SCALE_HW_CALIB_THERM_100K_PU_PM7: Returns temperature in millidegC using
  *	lookup table for PMIC7. The hardware applies offset/slope to adc code.
- * SCALE_HW_CALIB_PMIC_THERM: Returns result in milli degree's Centigrade.
+ * @SCALE_HW_CALIB_PMIC_THERM: Returns result in milli degree's Centigrade.
  *	The hardware applies offset/slope to adc code.
- * SCALE_HW_CALIB_PMIC_THERM: Returns result in milli degree's Centigrade.
+ * @SCALE_HW_CALIB_PMIC_THERM: Returns result in milli degree's Centigrade.
  *	The hardware applies offset/slope to adc code. This is for PMIC7.
- * SCALE_HW_CALIB_PM5_CHG_TEMP: Returns result in millidegrees for PMIC5
+ * @SCALE_HW_CALIB_PM5_CHG_TEMP: Returns result in millidegrees for PMIC5
  *	charger temperature.
- * SCALE_HW_CALIB_PM5_SMB_TEMP: Returns result in millidegrees for PMIC5
+ * @SCALE_HW_CALIB_PM5_SMB_TEMP: Returns result in millidegrees for PMIC5
  *	SMB1390 temperature.
  */
 enum vadc_scale_fn_type {
@@ -120,6 +120,7 @@ enum vadc_scale_fn_type {
 	SCALE_HW_CALIB_PMIC_THERM_PM7,
 	SCALE_HW_CALIB_PM5_CHG_TEMP,
 	SCALE_HW_CALIB_PM5_SMB_TEMP,
+	/* private: */
 	SCALE_HW_CALIB_INVALID,
 };
 
diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h
new file mode 100644
index 000000000000..7f815f3fed6a
--- /dev/null
+++ b/include/linux/iio/backend.h
@@ -0,0 +1,270 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _IIO_BACKEND_H_
+#define _IIO_BACKEND_H_
+
+#include <linux/types.h>
+#include <linux/iio/iio.h>
+
+struct iio_chan_spec;
+struct fwnode_handle;
+struct iio_backend;
+struct device;
+struct iio_dev;
+
+enum iio_backend_data_type {
+	IIO_BACKEND_TWOS_COMPLEMENT,
+	IIO_BACKEND_OFFSET_BINARY,
+	IIO_BACKEND_DATA_UNSIGNED,
+	IIO_BACKEND_DATA_TYPE_MAX
+};
+
+enum iio_backend_data_source {
+	IIO_BACKEND_INTERNAL_CONTINUOUS_WAVE,
+	IIO_BACKEND_EXTERNAL,
+	IIO_BACKEND_INTERNAL_RAMP_16BIT,
+	IIO_BACKEND_DATA_SOURCE_MAX
+};
+
+#define iio_backend_debugfs_ptr(ptr)	PTR_IF(IS_ENABLED(CONFIG_DEBUG_FS), ptr)
+
+/**
+ * IIO_BACKEND_EX_INFO - Helper for an IIO extended channel attribute
+ * @_name: Attribute name
+ * @_shared: Whether the attribute is shared between all channels
+ * @_what: Data private to the driver
+ */
+#define IIO_BACKEND_EX_INFO(_name, _shared, _what) {	\
+	.name = (_name),				\
+	.shared = (_shared),				\
+	.read =  iio_backend_ext_info_get,		\
+	.write = iio_backend_ext_info_set,		\
+	.private = (_what),				\
+}
+
+/**
+ * struct iio_backend_data_fmt - Backend data format
+ * @type: Data type.
+ * @sign_extend: Bool to tell if the data is sign extended.
+ * @enable: Enable/Disable the data format module. If disabled,
+ *	    not formatting will happen.
+ */
+struct iio_backend_data_fmt {
+	enum iio_backend_data_type type;
+	bool sign_extend;
+	bool enable;
+};
+
+/* vendor specific from 32 */
+enum iio_backend_test_pattern {
+	IIO_BACKEND_NO_TEST_PATTERN,
+	/* modified prbs9 */
+	IIO_BACKEND_ADI_PRBS_9A = 32,
+	/* modified prbs23 */
+	IIO_BACKEND_ADI_PRBS_23A,
+	IIO_BACKEND_TEST_PATTERN_MAX
+};
+
+enum iio_backend_sample_trigger {
+	IIO_BACKEND_SAMPLE_TRIGGER_EDGE_FALLING,
+	IIO_BACKEND_SAMPLE_TRIGGER_EDGE_RISING,
+	IIO_BACKEND_SAMPLE_TRIGGER_MAX
+};
+
+enum iio_backend_interface_type {
+	IIO_BACKEND_INTERFACE_SERIAL_LVDS,
+	IIO_BACKEND_INTERFACE_SERIAL_CMOS,
+	IIO_BACKEND_INTERFACE_MAX
+};
+
+enum iio_backend_filter_type {
+	IIO_BACKEND_FILTER_TYPE_DISABLED,
+	IIO_BACKEND_FILTER_TYPE_SINC1,
+	IIO_BACKEND_FILTER_TYPE_SINC5,
+	IIO_BACKEND_FILTER_TYPE_SINC5_PLUS_COMP,
+	IIO_BACKEND_FILTER_TYPE_MAX
+};
+
+/**
+ * struct iio_backend_ops - operations structure for an iio_backend
+ * @enable: Enable backend.
+ * @disable: Disable backend.
+ * @chan_enable: Enable one channel.
+ * @chan_disable: Disable one channel.
+ * @data_format_set: Configure the data format for a specific channel.
+ * @data_source_set: Configure the data source for a specific channel.
+ * @data_source_get: Data source getter for a specific channel.
+ * @set_sample_rate: Configure the sampling rate for a specific channel.
+ * @test_pattern_set: Configure a test pattern.
+ * @chan_status: Get the channel status.
+ * @iodelay_set: Set digital I/O delay.
+ * @data_sample_trigger: Control when to sample data.
+ * @request_buffer: Request an IIO buffer.
+ * @free_buffer: Free an IIO buffer.
+ * @extend_chan_spec: Extend an IIO channel.
+ * @ext_info_set: Extended info setter.
+ * @ext_info_get: Extended info getter.
+ * @interface_type_get: Interface type.
+ * @data_size_set: Data size.
+ * @oversampling_ratio_set: Set Oversampling ratio.
+ * @read_raw: Read a channel attribute from a backend device
+ * @debugfs_print_chan_status: Print channel status into a buffer.
+ * @debugfs_reg_access: Read or write register value of backend.
+ * @filter_type_set: Set filter type.
+ * @interface_data_align: Perform the data alignment process.
+ * @num_lanes_set: Set the number of lanes enabled.
+ * @ddr_enable: Enable interface DDR (Double Data Rate) mode.
+ * @ddr_disable: Disable interface DDR (Double Data Rate) mode.
+ * @data_stream_enable: Enable data stream.
+ * @data_stream_disable: Disable data stream.
+ * @data_transfer_addr: Set data address.
+ **/
+struct iio_backend_ops {
+	int (*enable)(struct iio_backend *back);
+	void (*disable)(struct iio_backend *back);
+	int (*chan_enable)(struct iio_backend *back, unsigned int chan);
+	int (*chan_disable)(struct iio_backend *back, unsigned int chan);
+	int (*data_format_set)(struct iio_backend *back, unsigned int chan,
+			       const struct iio_backend_data_fmt *data);
+	int (*data_source_set)(struct iio_backend *back, unsigned int chan,
+			       enum iio_backend_data_source data);
+	int (*data_source_get)(struct iio_backend *back, unsigned int chan,
+			       enum iio_backend_data_source *data);
+	int (*set_sample_rate)(struct iio_backend *back, unsigned int chan,
+			       u64 sample_rate_hz);
+	int (*test_pattern_set)(struct iio_backend *back,
+				unsigned int chan,
+				enum iio_backend_test_pattern pattern);
+	int (*chan_status)(struct iio_backend *back, unsigned int chan,
+			   bool *error);
+	int (*iodelay_set)(struct iio_backend *back, unsigned int chan,
+			   unsigned int taps);
+	int (*data_sample_trigger)(struct iio_backend *back,
+				   enum iio_backend_sample_trigger trigger);
+	struct iio_buffer *(*request_buffer)(struct iio_backend *back,
+					     struct iio_dev *indio_dev);
+	void (*free_buffer)(struct iio_backend *back,
+			    struct iio_buffer *buffer);
+	int (*extend_chan_spec)(struct iio_backend *back,
+				struct iio_chan_spec *chan);
+	int (*ext_info_set)(struct iio_backend *back, uintptr_t private,
+			    const struct iio_chan_spec *chan,
+			    const char *buf, size_t len);
+	int (*ext_info_get)(struct iio_backend *back, uintptr_t private,
+			    const struct iio_chan_spec *chan, char *buf);
+	int (*interface_type_get)(struct iio_backend *back,
+				  enum iio_backend_interface_type *type);
+	int (*data_size_set)(struct iio_backend *back, unsigned int size);
+	int (*oversampling_ratio_set)(struct iio_backend *back,
+				      unsigned int chan, unsigned int ratio);
+	int (*read_raw)(struct iio_backend *back,
+			struct iio_chan_spec const *chan, int *val, int *val2,
+			long mask);
+	int (*debugfs_print_chan_status)(struct iio_backend *back,
+					 unsigned int chan, char *buf,
+					 size_t len);
+	int (*debugfs_reg_access)(struct iio_backend *back, unsigned int reg,
+				  unsigned int writeval, unsigned int *readval);
+	int (*filter_type_set)(struct iio_backend *back,
+			       enum iio_backend_filter_type type);
+	int (*interface_data_align)(struct iio_backend *back, u32 timeout_us);
+	int (*num_lanes_set)(struct iio_backend *back, unsigned int num_lanes);
+	int (*ddr_enable)(struct iio_backend *back);
+	int (*ddr_disable)(struct iio_backend *back);
+	int (*data_stream_enable)(struct iio_backend *back);
+	int (*data_stream_disable)(struct iio_backend *back);
+	int (*data_transfer_addr)(struct iio_backend *back, u32 address);
+};
+
+/**
+ * struct iio_backend_info - info structure for an iio_backend
+ * @name: Backend name.
+ * @ops: Backend operations.
+ */
+struct iio_backend_info {
+	const char *name;
+	const struct iio_backend_ops *ops;
+};
+
+int iio_backend_chan_enable(struct iio_backend *back, unsigned int chan);
+int iio_backend_chan_disable(struct iio_backend *back, unsigned int chan);
+int devm_iio_backend_enable(struct device *dev, struct iio_backend *back);
+int iio_backend_enable(struct iio_backend *back);
+void iio_backend_disable(struct iio_backend *back);
+int iio_backend_data_format_set(struct iio_backend *back, unsigned int chan,
+				const struct iio_backend_data_fmt *data);
+int iio_backend_data_source_set(struct iio_backend *back, unsigned int chan,
+				enum iio_backend_data_source data);
+int iio_backend_data_source_get(struct iio_backend *back, unsigned int chan,
+				enum iio_backend_data_source *data);
+int iio_backend_set_sampling_freq(struct iio_backend *back, unsigned int chan,
+				  u64 sample_rate_hz);
+int iio_backend_test_pattern_set(struct iio_backend *back,
+				 unsigned int chan,
+				 enum iio_backend_test_pattern pattern);
+int iio_backend_chan_status(struct iio_backend *back, unsigned int chan,
+			    bool *error);
+int iio_backend_iodelay_set(struct iio_backend *back, unsigned int lane,
+			    unsigned int taps);
+int iio_backend_data_sample_trigger(struct iio_backend *back,
+				    enum iio_backend_sample_trigger trigger);
+int devm_iio_backend_request_buffer(struct device *dev,
+				    struct iio_backend *back,
+				    struct iio_dev *indio_dev);
+int iio_backend_filter_type_set(struct iio_backend *back,
+				enum iio_backend_filter_type type);
+int iio_backend_interface_data_align(struct iio_backend *back, u32 timeout_us);
+int iio_backend_num_lanes_set(struct iio_backend *back, unsigned int num_lanes);
+int iio_backend_ddr_enable(struct iio_backend *back);
+int iio_backend_ddr_disable(struct iio_backend *back);
+int iio_backend_data_stream_enable(struct iio_backend *back);
+int iio_backend_data_stream_disable(struct iio_backend *back);
+int iio_backend_data_transfer_addr(struct iio_backend *back, u32 address);
+ssize_t iio_backend_ext_info_set(struct iio_dev *indio_dev, uintptr_t private,
+				 const struct iio_chan_spec *chan,
+				 const char *buf, size_t len);
+ssize_t iio_backend_ext_info_get(struct iio_dev *indio_dev, uintptr_t private,
+				 const struct iio_chan_spec *chan, char *buf);
+int iio_backend_interface_type_get(struct iio_backend *back,
+				   enum iio_backend_interface_type *type);
+int iio_backend_data_size_set(struct iio_backend *back, unsigned int size);
+int iio_backend_oversampling_ratio_set(struct iio_backend *back,
+				       unsigned int chan,
+				       unsigned int ratio);
+int iio_backend_read_raw(struct iio_backend *back,
+			 struct iio_chan_spec const *chan, int *val, int *val2,
+			 long mask);
+int iio_backend_extend_chan_spec(struct iio_backend *back,
+				 struct iio_chan_spec *chan);
+void *iio_backend_get_priv(const struct iio_backend *conv);
+struct iio_backend *devm_iio_backend_get(struct device *dev, const char *name);
+struct iio_backend *devm_iio_backend_fwnode_get(struct device *dev,
+						const char *name,
+						struct fwnode_handle *fwnode);
+struct iio_backend *
+__devm_iio_backend_get_from_fwnode_lookup(struct device *dev,
+					  struct fwnode_handle *fwnode);
+
+int devm_iio_backend_register(struct device *dev,
+			      const struct iio_backend_info *info, void *priv);
+
+static inline int iio_backend_read_scale(struct iio_backend *back,
+					 struct iio_chan_spec const *chan,
+					 int *val, int *val2)
+{
+	return iio_backend_read_raw(back, chan, val, val2, IIO_CHAN_INFO_SCALE);
+}
+
+static inline int iio_backend_read_offset(struct iio_backend *back,
+					  struct iio_chan_spec const *chan,
+					  int *val, int *val2)
+{
+	return iio_backend_read_raw(back, chan, val, val2,
+				    IIO_CHAN_INFO_OFFSET);
+}
+
+ssize_t iio_backend_debugfs_print_chan_status(struct iio_backend *back,
+					      unsigned int chan, char *buf,
+					      size_t len);
+void iio_backend_debugfs_add(struct iio_backend *back,
+			     struct iio_dev *indio_dev);
+#endif
diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h
index 6564bdcdac66..4f33e6a39797 100644
--- a/include/linux/iio/buffer-dma.h
+++ b/include/linux/iio/buffer-dma.h
@@ -7,6 +7,7 @@
 #ifndef __INDUSTRIALIO_DMA_BUFFER_H__
 #define __INDUSTRIALIO_DMA_BUFFER_H__
 
+#include <linux/atomic.h>
 #include <linux/list.h>
 #include <linux/kref.h>
 #include <linux/spinlock.h>
@@ -16,17 +17,18 @@
 struct iio_dma_buffer_queue;
 struct iio_dma_buffer_ops;
 struct device;
+struct dma_buf_attachment;
+struct dma_fence;
+struct sg_table;
 
 /**
  * enum iio_block_state - State of a struct iio_dma_buffer_block
- * @IIO_BLOCK_STATE_DEQUEUED: Block is not queued
  * @IIO_BLOCK_STATE_QUEUED: Block is on the incoming queue
  * @IIO_BLOCK_STATE_ACTIVE: Block is currently being processed by the DMA
  * @IIO_BLOCK_STATE_DONE: Block is on the outgoing queue
  * @IIO_BLOCK_STATE_DEAD: Block has been marked as to be freed
  */
 enum iio_block_state {
-	IIO_BLOCK_STATE_DEQUEUED,
 	IIO_BLOCK_STATE_QUEUED,
 	IIO_BLOCK_STATE_ACTIVE,
 	IIO_BLOCK_STATE_DONE,
@@ -43,6 +45,10 @@ enum iio_block_state {
  * @queue: Parent DMA buffer queue
  * @kref: kref used to manage the lifetime of block
  * @state: Current state of the block
+ * @cyclic: True if this is a cyclic buffer
+ * @fileio: True if this buffer is used for fileio mode
+ * @sg_table: DMA table for the transfer when transferring a DMABUF
+ * @fence: DMA fence to be signaled when a DMABUF transfer is complete
  */
 struct iio_dma_buffer_block {
 	/* May only be accessed by the owner of the block */
@@ -65,6 +71,12 @@ struct iio_dma_buffer_block {
 	 * queue->list_lock if the block is not owned by the core.
 	 */
 	enum iio_block_state state;
+
+	bool cyclic;
+	bool fileio;
+
+	struct sg_table *sg_table;
+	struct dma_fence *fence;
 };
 
 /**
@@ -73,12 +85,17 @@ struct iio_dma_buffer_block {
  * @active_block: Block being used in read()
  * @pos: Read offset in the active block
  * @block_size: Size of each block
+ * @next_dequeue: index of next block that will be dequeued
+ * @enabled: Whether the buffer is operating in fileio mode
  */
 struct iio_dma_buffer_queue_fileio {
 	struct iio_dma_buffer_block *blocks[2];
 	struct iio_dma_buffer_block *active_block;
 	size_t pos;
 	size_t block_size;
+
+	unsigned int next_dequeue;
+	bool enabled;
 };
 
 /**
@@ -93,8 +110,8 @@ struct iio_dma_buffer_queue_fileio {
  *   list and typically also a list of active blocks in the part that handles
  *   the DMA controller
  * @incoming: List of buffers on the incoming queue
- * @outgoing: List of buffers on the outgoing queue
  * @active: Whether the buffer is currently active
+ * @num_dmabufs: Total number of DMABUFs attached to this queue
  * @fileio: FileIO state
  */
 struct iio_dma_buffer_queue {
@@ -105,9 +122,9 @@ struct iio_dma_buffer_queue {
 	struct mutex lock;
 	spinlock_t list_lock;
 	struct list_head incoming;
-	struct list_head outgoing;
 
 	bool active;
+	atomic_t num_dmabufs;
 
 	struct iio_dma_buffer_queue_fileio fileio;
 };
@@ -133,7 +150,9 @@ int iio_dma_buffer_disable(struct iio_buffer *buffer,
 	struct iio_dev *indio_dev);
 int iio_dma_buffer_read(struct iio_buffer *buffer, size_t n,
 	char __user *user_buffer);
-size_t iio_dma_buffer_data_available(struct iio_buffer *buffer);
+int iio_dma_buffer_write(struct iio_buffer *buffer, size_t n,
+			 const char __user *user_buffer);
+size_t iio_dma_buffer_usage(struct iio_buffer *buffer);
 int iio_dma_buffer_set_bytes_per_datum(struct iio_buffer *buffer, size_t bpd);
 int iio_dma_buffer_set_length(struct iio_buffer *buffer, unsigned int length);
 int iio_dma_buffer_request_update(struct iio_buffer *buffer);
@@ -143,4 +162,18 @@ int iio_dma_buffer_init(struct iio_dma_buffer_queue *queue,
 void iio_dma_buffer_exit(struct iio_dma_buffer_queue *queue);
 void iio_dma_buffer_release(struct iio_dma_buffer_queue *queue);
 
+struct iio_dma_buffer_block *
+iio_dma_buffer_attach_dmabuf(struct iio_buffer *buffer,
+			     struct dma_buf_attachment *attach);
+void iio_dma_buffer_detach_dmabuf(struct iio_buffer *buffer,
+				  struct iio_dma_buffer_block *block);
+int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer,
+				  struct iio_dma_buffer_block *block,
+				  struct dma_fence *fence,
+				  struct sg_table *sgt,
+				  size_t size, bool cyclic);
+void iio_dma_buffer_lock_queue(struct iio_buffer *buffer);
+void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer);
+struct device *iio_dma_buffer_get_dma_dev(struct iio_buffer *buffer);
+
 #endif
diff --git a/include/linux/iio/buffer-dmaengine.h b/include/linux/iio/buffer-dmaengine.h
index 5c355be89814..37f27545f69f 100644
--- a/include/linux/iio/buffer-dmaengine.h
+++ b/include/linux/iio/buffer-dmaengine.h
@@ -7,11 +7,33 @@
 #ifndef __IIO_DMAENGINE_H__
 #define __IIO_DMAENGINE_H__
 
+#include <linux/iio/buffer.h>
+
 struct iio_dev;
 struct device;
+struct dma_chan;
+
+void iio_dmaengine_buffer_teardown(struct iio_buffer *buffer);
+struct iio_buffer *iio_dmaengine_buffer_setup_ext(struct device *dev,
+						  struct iio_dev *indio_dev,
+						  const char *channel,
+						  enum iio_buffer_direction dir);
+
+#define iio_dmaengine_buffer_setup(dev, indio_dev, channel)	\
+	iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel,	\
+				       IIO_BUFFER_DIRECTION_IN)
+
+int devm_iio_dmaengine_buffer_setup_ext(struct device *dev,
+					struct iio_dev *indio_dev,
+					const char *channel,
+					enum iio_buffer_direction dir);
+int devm_iio_dmaengine_buffer_setup_with_handle(struct device *dev,
+						struct iio_dev *indio_dev,
+						struct dma_chan *chan,
+						enum iio_buffer_direction dir);
 
-int devm_iio_dmaengine_buffer_setup(struct device *dev,
-				    struct iio_dev *indio_dev,
-				    const char *channel);
+#define devm_iio_dmaengine_buffer_setup(dev, indio_dev, channel)	\
+	devm_iio_dmaengine_buffer_setup_ext(dev, indio_dev, channel,	\
+					    IIO_BUFFER_DIRECTION_IN)
 
 #endif
diff --git a/include/linux/iio/buffer.h b/include/linux/iio/buffer.h
index 418b1307d3f2..d37f82678f71 100644
--- a/include/linux/iio/buffer.h
+++ b/include/linux/iio/buffer.h
@@ -26,18 +26,14 @@ int iio_pop_from_buffer(struct iio_buffer *buffer, void *data);
  * @data:		sample data
  * @timestamp:		timestamp for the sample data
  *
- * Pushes data to the IIO device's buffers. If timestamps are enabled for the
- * device the function will store the supplied timestamp as the last element in
- * the sample data buffer before pushing it to the device buffers. The sample
- * data buffer needs to be large enough to hold the additional timestamp
- * (usually the buffer should be indio->scan_bytes bytes large).
+ * DEPRECATED: Use iio_push_to_buffers_with_ts() instead.
  *
  * Returns 0 on success, a negative error code otherwise.
  */
 static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev,
 	void *data, int64_t timestamp)
 {
-	if (indio_dev->scan_timestamp) {
+	if (ACCESS_PRIVATE(indio_dev, scan_timestamp)) {
 		size_t ts_offset = indio_dev->scan_bytes / sizeof(int64_t) - 1;
 		((int64_t *)data)[ts_offset] = timestamp;
 	}
@@ -45,6 +41,34 @@ static inline int iio_push_to_buffers_with_timestamp(struct iio_dev *indio_dev,
 	return iio_push_to_buffers(indio_dev, data);
 }
 
+/**
+ * iio_push_to_buffers_with_ts() - push data and timestamp to buffers
+ * @indio_dev:		iio_dev structure for device.
+ * @data:		Pointer to sample data buffer.
+ * @data_total_len:	The size of @data in bytes.
+ * @timestamp:		Timestamp for the sample data.
+ *
+ * Pushes data to the IIO device's buffers. If timestamps are enabled for the
+ * device the function will store the supplied timestamp as the last element in
+ * the sample data buffer before pushing it to the device buffers. The sample
+ * data buffer needs to be large enough to hold the additional timestamp
+ * (usually the buffer should be at least indio->scan_bytes bytes large).
+ *
+ * Context: Any context.
+ * Return: 0 on success, a negative error code otherwise.
+ */
+static inline int iio_push_to_buffers_with_ts(struct iio_dev *indio_dev,
+					      void *data, size_t data_total_len,
+					      s64 timestamp)
+{
+	if (unlikely(data_total_len < indio_dev->scan_bytes)) {
+		dev_err(&indio_dev->dev, "Undersized storage pushed to buffer\n");
+		return -ENOSPC;
+	}
+
+	return iio_push_to_buffers_with_timestamp(indio_dev, data, timestamp);
+}
+
 int iio_push_to_buffers_with_ts_unaligned(struct iio_dev *indio_dev,
 					  const void *data, size_t data_sz,
 					  int64_t timestamp);
diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h
index 89c3fd7c29ca..c0b0e0992a85 100644
--- a/include/linux/iio/buffer_impl.h
+++ b/include/linux/iio/buffer_impl.h
@@ -9,8 +9,12 @@
 #include <uapi/linux/iio/buffer.h>
 #include <linux/iio/buffer.h>
 
+struct dma_buf_attachment;
+struct dma_fence;
 struct iio_dev;
+struct iio_dma_buffer_block;
 struct iio_buffer;
+struct sg_table;
 
 /**
  * INDIO_BUFFER_FLAG_FIXED_WATERMARK - Watermark level of the buffer can not be
@@ -20,7 +24,8 @@ struct iio_buffer;
 
 /**
  * struct iio_buffer_access_funcs - access functions for buffers.
- * @store_to:		actually store stuff to the buffer
+ * @store_to:		actually store stuff to the buffer - must be safe to
+ *			call from any context (e.g. must not sleep).
  * @read:		try to get a specified number of bytes (must exist)
  * @data_available:	indicates how much data is available for reading from
  *			the buffer.
@@ -39,6 +44,17 @@ struct iio_buffer;
  *                      device stops sampling. Calles are balanced with @enable.
  * @release:		called when the last reference to the buffer is dropped,
  *			should free all resources allocated by the buffer.
+ * @attach_dmabuf:	called from userspace via ioctl to attach one external
+ *			DMABUF.
+ * @detach_dmabuf:	called from userspace via ioctl to detach one previously
+ *			attached DMABUF.
+ * @enqueue_dmabuf:	called from userspace via ioctl to queue this DMABUF
+ *			object to this buffer. Requires a valid DMABUF fd, that
+ *			was previouly attached to this buffer.
+ * @get_dma_dev:	called to get the DMA channel associated with this buffer.
+ * @lock_queue:		called when the core needs to lock the buffer queue;
+ *                      it is used when enqueueing DMABUF objects.
+ * @unlock_queue:       used to unlock a previously locked buffer queue
  * @modes:		Supported operating modes by this buffer type
  * @flags:		A bitmask combination of INDIO_BUFFER_FLAG_*
  *
@@ -68,6 +84,18 @@ struct iio_buffer_access_funcs {
 
 	void (*release)(struct iio_buffer *buffer);
 
+	struct iio_dma_buffer_block * (*attach_dmabuf)(struct iio_buffer *buffer,
+						       struct dma_buf_attachment *attach);
+	void (*detach_dmabuf)(struct iio_buffer *buffer,
+			      struct iio_dma_buffer_block *block);
+	int (*enqueue_dmabuf)(struct iio_buffer *buffer,
+			      struct iio_dma_buffer_block *block,
+			      struct dma_fence *fence, struct sg_table *sgt,
+			      size_t size, bool cyclic);
+	struct device * (*get_dma_dev)(struct iio_buffer *buffer);
+	void (*lock_queue)(struct iio_buffer *buffer);
+	void (*unlock_queue)(struct iio_buffer *buffer);
+
 	unsigned int modes;
 	unsigned int flags;
 };
@@ -136,6 +164,12 @@ struct iio_buffer {
 
 	/* @ref: Reference count of the buffer. */
 	struct kref ref;
+
+	/* @dmabufs: List of DMABUF attachments */
+	struct list_head dmabufs; /* P: dmabufs_mutex */
+
+	/* @dmabufs_mutex: Protects dmabufs */
+	struct mutex dmabufs_mutex;
 };
 
 /**
@@ -159,6 +193,8 @@ void iio_buffer_init(struct iio_buffer *buffer);
 struct iio_buffer *iio_buffer_get(struct iio_buffer *buffer);
 void iio_buffer_put(struct iio_buffer *buffer);
 
+void iio_buffer_signal_dmabuf_done(struct dma_fence *fence, int ret);
+
 #else /* CONFIG_IIO_BUFFER */
 
 static inline void iio_buffer_get(struct iio_buffer *buffer) {}
diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h
index e72167b96d27..bb966abcde53 100644
--- a/include/linux/iio/common/cros_ec_sensors_core.h
+++ b/include/linux/iio/common/cros_ec_sensors_core.h
@@ -126,5 +126,6 @@ extern const struct dev_pm_ops cros_ec_sensors_pm_ops;
 
 /* List of extended channel specification for all sensors. */
 extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[];
+extern const struct iio_chan_spec_ext_info cros_ec_sensors_limited_info[];
 
 #endif  /* __CROS_EC_SENSORS_CORE_H */
diff --git a/include/linux/iio/common/inv_sensors_timestamp.h b/include/linux/iio/common/inv_sensors_timestamp.h
new file mode 100644
index 000000000000..8d506f1e9df2
--- /dev/null
+++ b/include/linux/iio/common/inv_sensors_timestamp.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2020 Invensense, Inc.
+ */
+
+#ifndef INV_SENSORS_TIMESTAMP_H_
+#define INV_SENSORS_TIMESTAMP_H_
+
+/**
+ * struct inv_sensors_timestamp_chip - chip internal properties
+ * @clock_period:	internal clock period in ns
+ * @jitter:		acceptable jitter in per-mille
+ * @init_period:	chip initial period at reset in ns
+ */
+struct inv_sensors_timestamp_chip {
+	uint32_t clock_period;
+	uint32_t jitter;
+	uint32_t init_period;
+};
+
+/**
+ * struct inv_sensors_timestamp_interval - timestamps interval
+ * @lo:	interval lower bound
+ * @up:	interval upper bound
+ */
+struct inv_sensors_timestamp_interval {
+	int64_t lo;
+	int64_t up;
+};
+
+/**
+ * struct inv_sensors_timestamp_acc - accumulator for computing an estimation
+ * @val:	current estimation of the value, the mean of all values
+ * @idx:	current index of the next free place in values table
+ * @values:	table of all measured values, use for computing the mean
+ */
+struct inv_sensors_timestamp_acc {
+	uint32_t val;
+	size_t idx;
+	uint32_t values[32];
+};
+
+/**
+ * struct inv_sensors_timestamp - timestamp management states
+ * @chip:		chip internal characteristics
+ * @min_period:		minimal acceptable clock period
+ * @max_period:		maximal acceptable clock period
+ * @it:			interrupts interval timestamps
+ * @timestamp:		store last timestamp for computing next data timestamp
+ * @mult:		current internal period multiplier
+ * @new_mult:		new set internal period multiplier (not yet effective)
+ * @period:		measured current period of the sensor
+ * @chip_period:	accumulator for computing internal chip period
+ */
+struct inv_sensors_timestamp {
+	struct inv_sensors_timestamp_chip chip;
+	uint32_t min_period;
+	uint32_t max_period;
+	struct inv_sensors_timestamp_interval it;
+	int64_t timestamp;
+	uint32_t mult;
+	uint32_t new_mult;
+	uint32_t period;
+	struct inv_sensors_timestamp_acc chip_period;
+};
+
+void inv_sensors_timestamp_init(struct inv_sensors_timestamp *ts,
+				const struct inv_sensors_timestamp_chip *chip);
+
+int inv_sensors_timestamp_update_odr(struct inv_sensors_timestamp *ts,
+				     uint32_t period, bool fifo);
+
+void inv_sensors_timestamp_interrupt(struct inv_sensors_timestamp *ts,
+				     size_t sample_nb, int64_t timestamp);
+
+static inline int64_t inv_sensors_timestamp_pop(struct inv_sensors_timestamp *ts)
+{
+	ts->timestamp += ts->period;
+	return ts->timestamp;
+}
+
+void inv_sensors_timestamp_apply_odr(struct inv_sensors_timestamp *ts,
+				     uint32_t fifo_period, size_t fifo_nb,
+				     unsigned int fifo_no);
+
+static inline void inv_sensors_timestamp_reset(struct inv_sensors_timestamp *ts)
+{
+	const struct inv_sensors_timestamp_interval interval_init = {0LL, 0LL};
+
+	ts->it = interval_init;
+	ts->timestamp = 0;
+}
+
+#endif
diff --git a/include/linux/iio/common/st_sensors.h b/include/linux/iio/common/st_sensors.h
index f5f3ee57bc70..f9ae5cdd884f 100644
--- a/include/linux/iio/common/st_sensors.h
+++ b/include/linux/iio/common/st_sensors.h
@@ -22,6 +22,7 @@
 #include <linux/platform_data/st_sensors_pdata.h>
 
 #define LSM9DS0_IMU_DEV_NAME		"lsm9ds0"
+#define LSM303D_IMU_DEV_NAME		"lsm303d"
 
 /*
  * Buffer size max case: 2bytes per channel, 3 channels in total +
@@ -257,9 +258,9 @@ struct st_sensor_data {
 	bool hw_irq_trigger;
 	s64 hw_timestamp;
 
-	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] ____cacheline_aligned;
-
 	struct mutex odr_lock;
+
+	char buffer_data[ST_SENSORS_MAX_BUFFER_SIZE] __aligned(IIO_DMA_MINALIGN);
 };
 
 #ifdef CONFIG_IIO_BUFFER
diff --git a/include/linux/iio/consumer.h b/include/linux/iio/consumer.h
index 6802596b017c..5039558267e4 100644
--- a/include/linux/iio/consumer.h
+++ b/include/linux/iio/consumer.h
@@ -131,7 +131,8 @@ struct iio_cb_buffer;
 /**
  * iio_channel_get_all_cb() - register callback for triggered capture
  * @dev:		Pointer to client device.
- * @cb:			Callback function.
+ * @cb:			Callback function. Must be safe to call from any context
+ *			(e.g. must not sleep).
  * @private:		Private data passed to callback.
  *
  * NB right now we have no ability to mux data from multiple devices.
@@ -201,8 +202,9 @@ struct iio_dev
  * @chan:		The channel being queried.
  * @val:		Value read back.
  *
- * Note raw reads from iio channels are in adc counts and hence
- * scale will need to be applied if standard units required.
+ * Note, if standard units are required, raw reads from iio channels
+ * need the offset (default 0) and scale (default 1) to be applied
+ * as (raw + offset) * scale.
  */
 int iio_read_channel_raw(struct iio_channel *chan,
 			 int *val);
@@ -212,8 +214,9 @@ int iio_read_channel_raw(struct iio_channel *chan,
  * @chan:		The channel being queried.
  * @val:		Value read back.
  *
- * Note raw reads from iio channels are in adc counts and hence
- * scale will need to be applied if standard units required.
+ * Note, if standard units are required, raw reads from iio channels
+ * need the offset (default 0) and scale (default 1) to be applied
+ * as (raw + offset) * scale.
  *
  * In opposit to the normal iio_read_channel_raw this function
  * returns the average of multiple reads.
@@ -281,8 +284,9 @@ int iio_read_channel_attribute(struct iio_channel *chan, int *val,
  * @chan:		The channel being queried.
  * @val:		Value being written.
  *
- * Note raw writes to iio channels are in dac counts and hence
- * scale will need to be applied if standard units required.
+ * Note that for raw writes to iio channels, if the value provided is
+ * in standard units, the affect of the scale and offset must be removed
+ * as (value / scale) - offset.
  */
 int iio_write_channel_raw(struct iio_channel *chan, int val);
 
@@ -292,12 +296,25 @@ int iio_write_channel_raw(struct iio_channel *chan, int val);
  * @chan:		The channel being queried.
  * @val:		Value read back.
  *
- * Note raw reads from iio channels are in adc counts and hence
- * scale will need to be applied if standard units are required.
+ * Note, if standard units are required, raw reads from iio channels
+ * need the offset (default 0) and scale (default 1) to be applied
+ * as (raw + offset) * scale.
  */
 int iio_read_max_channel_raw(struct iio_channel *chan, int *val);
 
 /**
+ * iio_read_min_channel_raw() - read minimum available raw value from a given
+ *				channel, i.e. the minimum possible value.
+ * @chan:		The channel being queried.
+ * @val:		Value read back.
+ *
+ * Note, if standard units are required, raw reads from iio channels
+ * need the offset (default 0) and scale (default 1) to be applied
+ * as (raw + offset) * scale.
+ */
+int iio_read_min_channel_raw(struct iio_channel *chan, int *val);
+
+/**
  * iio_read_avail_channel_raw() - read available raw values from a given channel
  * @chan:		The channel being queried.
  * @vals:		Available values read back.
@@ -308,8 +325,9 @@ int iio_read_max_channel_raw(struct iio_channel *chan, int *val);
  * For ranges, three vals are always returned; min, step and max.
  * For lists, all the possible values are enumerated.
  *
- * Note raw available values from iio channels are in adc counts and
- * hence scale will need to be applied if standard units are required.
+ * Note, if standard units are required, raw available values from iio
+ * channels need the offset (default 0) and scale (default 1) to be applied
+ * as (raw + offset) * scale.
  */
 int iio_read_avail_channel_raw(struct iio_channel *chan,
 			       const int **vals, int *length);
@@ -365,6 +383,24 @@ int iio_read_channel_scale(struct iio_channel *chan, int *val,
 			   int *val2);
 
 /**
+ * iio_multiply_value() - Multiply an IIO value
+ * @result:	Destination pointer for the multiplication result
+ * @multiplier:	Multiplier.
+ * @type:	One of the IIO_VAL_* constants. This decides how the @val and
+ *		@val2 parameters are interpreted.
+ * @val:	Value being multiplied.
+ * @val2:	Value being multiplied. @val2 use depends on type.
+ *
+ * Multiply an IIO value with a s64 multiplier storing the result as
+ * IIO_VAL_INT. This is typically used for scaling.
+ *
+ * Returns:
+ * IIO_VAL_INT on success or a negative error-number on failure.
+ */
+int iio_multiply_value(int *result, s64 multiplier,
+		       unsigned int type, int val, int val2);
+
+/**
  * iio_convert_raw_to_processed() - Converts a raw value to a processed value
  * @chan:		The channel being queried
  * @raw:		The raw IIO to convert
@@ -401,7 +437,7 @@ unsigned int iio_get_channel_ext_info_count(struct iio_channel *chan);
  * @chan:		The channel being queried.
  * @attr:		The ext_info attribute to read.
  * @buf:		Where to store the attribute value. Assumed to hold
- *			at least PAGE_SIZE bytes.
+ *			at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE.
  *
  * Returns the number of bytes written to buf (perhaps w/o zero termination;
  * it need not even be a string), or an error code.
@@ -424,4 +460,14 @@ ssize_t iio_read_channel_ext_info(struct iio_channel *chan,
 ssize_t iio_write_channel_ext_info(struct iio_channel *chan, const char *attr,
 				   const char *buf, size_t len);
 
+/**
+ * iio_read_channel_label() - read label for a given channel
+ * @chan:		The channel being queried.
+ * @buf:		Where to store the attribute value. Assumed to hold
+ *			at least PAGE_SIZE bytes and to be aligned at PAGE_SIZE.
+ *
+ * Returns the number of bytes written to buf, or an error code.
+ */
+ssize_t iio_read_channel_label(struct iio_channel *chan, char *buf);
+
 #endif
diff --git a/include/linux/iio/driver.h b/include/linux/iio/driver.h
index 7a157ed218f6..7f8b55551ed0 100644
--- a/include/linux/iio/driver.h
+++ b/include/linux/iio/driver.h
@@ -18,7 +18,7 @@ struct iio_map;
  * @map:	array of mappings specifying association of channel with client
  */
 int iio_map_array_register(struct iio_dev *indio_dev,
-			   struct iio_map *map);
+			   const struct iio_map *map);
 
 /**
  * iio_map_array_unregister() - tell the core to remove consumer mappings for
@@ -38,6 +38,7 @@ int iio_map_array_unregister(struct iio_dev *indio_dev);
  * handle de-registration of the IIO map object when the device's refcount goes to
  * zero.
  */
-int devm_iio_map_array_register(struct device *dev, struct iio_dev *indio_dev, struct iio_map *maps);
+int devm_iio_map_array_register(struct device *dev, struct iio_dev *indio_dev,
+				const struct iio_map *maps);
 
 #endif
diff --git a/include/linux/iio/events.h b/include/linux/iio/events.h
index a4558c45a548..72062a0c7c87 100644
--- a/include/linux/iio/events.h
+++ b/include/linux/iio/events.h
@@ -10,7 +10,7 @@
 #include <uapi/linux/iio/events.h>
 
 /**
- * IIO_EVENT_CODE() - create event identifier
+ * _IIO_EVENT_CODE() - create event identifier
  * @chan_type:	Type of the channel. Should be one of enum iio_chan_type.
  * @diff:	Whether the event is for an differential channel or not.
  * @modifier:	Modifier for the channel. Should be one of enum iio_modifier.
@@ -19,10 +19,13 @@
  * @chan:	Channel number for non-differential channels.
  * @chan1:	First channel number for differential channels.
  * @chan2:	Second channel number for differential channels.
+ *
+ * Drivers should use the specialized macros below instead of using this one
+ * directly.
  */
 
-#define IIO_EVENT_CODE(chan_type, diff, modifier, direction,		\
-		       type, chan, chan1, chan2)			\
+#define _IIO_EVENT_CODE(chan_type, diff, modifier, direction,		\
+			type, chan, chan1, chan2)			\
 	(((u64)type << 56) | ((u64)diff << 55) |			\
 	 ((u64)direction << 48) | ((u64)modifier << 40) |		\
 	 ((u64)chan_type << 32) | (((u16)chan2) << 16) | ((u16)chan1) | \
@@ -30,7 +33,8 @@
 
 
 /**
- * IIO_MOD_EVENT_CODE() - create event identifier for modified channels
+ * IIO_MOD_EVENT_CODE() - create event identifier for modified (non
+ * differential) channels
  * @chan_type:	Type of the channel. Should be one of enum iio_chan_type.
  * @number:	Channel number.
  * @modifier:	Modifier for the channel. Should be one of enum iio_modifier.
@@ -40,10 +44,11 @@
 
 #define IIO_MOD_EVENT_CODE(chan_type, number, modifier,		\
 			   type, direction)				\
-	IIO_EVENT_CODE(chan_type, 0, modifier, direction, type, number, 0, 0)
+	_IIO_EVENT_CODE(chan_type, 0, modifier, direction, type, number, 0, 0)
 
 /**
- * IIO_UNMOD_EVENT_CODE() - create event identifier for unmodified channels
+ * IIO_UNMOD_EVENT_CODE() - create event identifier for unmodified (non
+ * differential) channels
  * @chan_type:	Type of the channel. Should be one of enum iio_chan_type.
  * @number:	Channel number.
  * @type:	Type of the event. Should be one of enum iio_event_type.
@@ -51,6 +56,18 @@
  */
 
 #define IIO_UNMOD_EVENT_CODE(chan_type, number, type, direction)	\
-	IIO_EVENT_CODE(chan_type, 0, 0, direction, type, number, 0, 0)
+	_IIO_EVENT_CODE(chan_type, 0, 0, direction, type, number, 0, 0)
+
+/**
+ * IIO_DIFF_EVENT_CODE() - create event identifier for differential channels
+ * @chan_type:	Type of the channel. Should be one of enum iio_chan_type.
+ * @chan1:	First channel number for differential channels.
+ * @chan2:	Second channel number for differential channels.
+ * @type:	Type of the event. Should be one of enum iio_event_type.
+ * @direction:	Direction of the event. One of enum iio_event_direction.
+ */
+
+#define IIO_DIFF_EVENT_CODE(chan_type, chan1, chan2, type, direction)	\
+	_IIO_EVENT_CODE(chan_type, 1, 0, direction, type, 0, chan1, chan2)
 
 #endif
diff --git a/include/linux/iio/frequency/adf4350.h b/include/linux/iio/frequency/adf4350.h
index de45cf2ee1e4..ce2086f97e3f 100644
--- a/include/linux/iio/frequency/adf4350.h
+++ b/include/linux/iio/frequency/adf4350.h
@@ -51,7 +51,7 @@
 
 /* REG3 Bit Definitions */
 #define ADF4350_REG3_12BIT_CLKDIV(x)		((x) << 3)
-#define ADF4350_REG3_12BIT_CLKDIV_MODE(x)	((x) << 16)
+#define ADF4350_REG3_12BIT_CLKDIV_MODE(x)	((x) << 15)
 #define ADF4350_REG3_12BIT_CSR_EN		(1 << 18)
 #define ADF4351_REG3_CHARGE_CANCELLATION_EN	(1 << 21)
 #define ADF4351_REG3_ANTI_BACKLASH_3ns_EN	(1 << 22)
diff --git a/include/linux/iio/iio-gts-helper.h b/include/linux/iio/iio-gts-helper.h
index dd64e544a3da..66f830ab9b49 100644
--- a/include/linux/iio/iio-gts-helper.h
+++ b/include/linux/iio/iio-gts-helper.h
@@ -135,7 +135,7 @@ static inline int iio_gts_find_int_time_by_sel(struct iio_gts *gts, int sel)
 /**
  * iio_gts_find_sel_by_int_time - find selector matching integration time
  * @gts:	Gain time scale descriptor
- * @gain:	HW-gain for which matching selector is searched for
+ * @time:	Integration time for which matching selector is searched for
  *
  * Return:	a selector matching given integration time or -EINVAL if
  *		selector was not found.
@@ -188,6 +188,9 @@ int iio_gts_total_gain_to_scale(struct iio_gts *gts, int total_gain,
 int iio_gts_find_gain_sel_for_scale_using_time(struct iio_gts *gts, int time_sel,
 					       int scale_int, int scale_nano,
 					       int *gain_sel);
+int iio_gts_find_gain_time_sel_for_scale(struct iio_gts *gts, int scale_int,
+					 int scale_nano, int *gain_sel,
+					 int *time_sel);
 int iio_gts_get_scale(struct iio_gts *gts, int gain, int time, int *scale_int,
 		      int *scale_nano);
 int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts,
@@ -196,11 +199,15 @@ int iio_gts_find_new_gain_sel_by_old_gain_time(struct iio_gts *gts,
 int iio_gts_find_new_gain_by_old_gain_time(struct iio_gts *gts, int old_gain,
 					   int old_time, int new_time,
 					   int *new_gain);
+int iio_gts_find_new_gain_by_gain_time_min(struct iio_gts *gts, int old_gain,
+					   int old_time, int new_time,
+					   int *new_gain, bool *in_range);
 int iio_gts_avail_times(struct iio_gts *gts,  const int **vals, int *type,
 			int *length);
 int iio_gts_all_avail_scales(struct iio_gts *gts, const int **vals, int *type,
 			     int *length);
 int iio_gts_avail_scales_for_time(struct iio_gts *gts, int time,
 				  const int **vals, int *type, int *length);
+int iio_gts_get_total_gain(struct iio_gts *gts, int gain, int time);
 
 #endif
diff --git a/include/linux/iio/iio-opaque.h b/include/linux/iio/iio-opaque.h
index 5aec3945555b..4247497f3f8b 100644
--- a/include/linux/iio/iio-opaque.h
+++ b/include/linux/iio/iio-opaque.h
@@ -28,7 +28,7 @@
  * @groupcounter:		index of next attribute group
  * @legacy_scan_el_group:	attribute group for legacy scan elements attribute group
  * @legacy_buffer_group:	attribute group for legacy buffer attributes group
- * @bounce_buffer:		for devices that call iio_push_to_buffers_with_timestamp_unaligned()
+ * @bounce_buffer:		for devices that call iio_push_to_buffers_with_ts_unaligned()
  * @bounce_buffer_size:		size of currently allocate bounce buffer
  * @scan_index_timestamp:	cache of the index to the timestamp
  * @clock_id:			timestamping clock posix identifier
@@ -70,7 +70,7 @@ struct iio_dev_opaque {
 
 #if defined(CONFIG_DEBUG_FS)
 	struct dentry			*debugfs_dentry;
-	unsigned			cached_reg_addr;
+	unsigned int			cached_reg_addr;
 	char				read_buf[20];
 	unsigned int			read_buf_len;
 #endif
diff --git a/include/linux/iio/iio.h b/include/linux/iio/iio.h
index 81413cd3a3e7..872ebdf0dd77 100644
--- a/include/linux/iio/iio.h
+++ b/include/linux/iio/iio.h
@@ -7,8 +7,11 @@
 #ifndef _INDUSTRIAL_IO_H_
 #define _INDUSTRIAL_IO_H_
 
+#include <linux/align.h>
 #include <linux/device.h>
 #include <linux/cdev.h>
+#include <linux/compiler_types.h>
+#include <linux/minmax.h>
 #include <linux/slab.h>
 #include <linux/iio/types.h>
 /* IIO TODO LIST */
@@ -173,6 +176,27 @@ struct iio_event_spec {
 };
 
 /**
+ * struct iio_scan_type - specification for channel data format in buffer
+ * @sign:		's' or 'u' to specify signed or unsigned
+ * @realbits:		Number of valid bits of data
+ * @storagebits:	Realbits + padding
+ * @shift:		Shift right by this before masking out realbits.
+ * @repeat:		Number of times real/storage bits repeats. When the
+ *			repeat element is more than 1, then the type element in
+ *			sysfs will show a repeat value. Otherwise, the number
+ *			of repetitions is omitted.
+ * @endianness:		little or big endian
+ */
+struct iio_scan_type {
+	char	sign;
+	u8	realbits;
+	u8	storagebits;
+	u8	shift;
+	u8	repeat;
+	enum iio_endian endianness;
+};
+
+/**
  * struct iio_chan_spec - specification of a single channel
  * @type:		What type of measurement is the channel making.
  * @channel:		What number do we wish to assign the channel.
@@ -182,18 +206,13 @@ struct iio_event_spec {
  * @address:		Driver specific identifier.
  * @scan_index:		Monotonic index to give ordering in scans when read
  *			from a buffer.
- * @scan_type:		struct describing the scan type
- * @scan_type.sign:		's' or 'u' to specify signed or unsigned
- * @scan_type.realbits:		Number of valid bits of data
- * @scan_type.storagebits:	Realbits + padding
- * @scan_type.shift:		Shift right by this before masking out
- *				realbits.
- * @scan_type.repeat:		Number of times real/storage bits repeats.
- *				When the repeat element is more than 1, then
- *				the type element in sysfs will show a repeat
- *				value. Otherwise, the number of repetitions
- *				is omitted.
- * @scan_type.endianness:	little or big endian
+ * @scan_type:		struct describing the scan type - mutually exclusive
+ *			with ext_scan_type.
+ * @ext_scan_type:	Used in rare cases where there is more than one scan
+ *			format for a channel. When this is used, the flag
+ *			has_ext_scan_type must be set and the driver must
+ *			implement get_current_scan_type in struct iio_info.
+ * @num_ext_scan_type:	Number of elements in ext_scan_type.
  * @info_mask_separate: What information is to be exported that is specific to
  *			this channel.
  * @info_mask_separate_available: What availability information is to be
@@ -221,6 +240,9 @@ struct iio_event_spec {
  * @extend_name:	Allows labeling of channel attributes with an
  *			informative name. Note this has no effect codes etc,
  *			unlike modifiers.
+ *			This field is deprecated in favour of providing
+ *			iio_info->read_label() to override the label, which
+ *			unlike @extend_name does not affect sysfs filenames.
  * @datasheet_name:	A name used in in-kernel mapping of channels. It should
  *			correspond to the first name that the channel is referred
  *			to by in the datasheet (e.g. IND), or the nearest
@@ -234,6 +256,7 @@ struct iio_event_spec {
  *			attributes but not for event codes.
  * @output:		Channel is output.
  * @differential:	Channel is differential.
+ * @has_ext_scan_type:	True if ext_scan_type is used instead of scan_type.
  */
 struct iio_chan_spec {
 	enum iio_chan_type	type;
@@ -241,31 +264,31 @@ struct iio_chan_spec {
 	int			channel2;
 	unsigned long		address;
 	int			scan_index;
-	struct {
-		char	sign;
-		u8	realbits;
-		u8	storagebits;
-		u8	shift;
-		u8	repeat;
-		enum iio_endian endianness;
-	} scan_type;
-	long			info_mask_separate;
-	long			info_mask_separate_available;
-	long			info_mask_shared_by_type;
-	long			info_mask_shared_by_type_available;
-	long			info_mask_shared_by_dir;
-	long			info_mask_shared_by_dir_available;
-	long			info_mask_shared_by_all;
-	long			info_mask_shared_by_all_available;
+	union {
+		struct iio_scan_type scan_type;
+		struct {
+			const struct iio_scan_type *ext_scan_type;
+			unsigned int num_ext_scan_type;
+		};
+	};
+	unsigned long			info_mask_separate;
+	unsigned long			info_mask_separate_available;
+	unsigned long			info_mask_shared_by_type;
+	unsigned long			info_mask_shared_by_type_available;
+	unsigned long			info_mask_shared_by_dir;
+	unsigned long			info_mask_shared_by_dir_available;
+	unsigned long			info_mask_shared_by_all;
+	unsigned long			info_mask_shared_by_all_available;
 	const struct iio_event_spec *event_spec;
 	unsigned int		num_event_specs;
 	const struct iio_chan_spec_ext_info *ext_info;
 	const char		*extend_name;
 	const char		*datasheet_name;
-	unsigned		modified:1;
-	unsigned		indexed:1;
-	unsigned		output:1;
-	unsigned		differential:1;
+	unsigned int		modified:1;
+	unsigned int		indexed:1;
+	unsigned int		output:1;
+	unsigned int		differential:1;
+	unsigned int		has_ext_scan_type:1;
 };
 
 
@@ -424,18 +447,17 @@ struct iio_trigger; /* forward declaration */
  * @write_event_config:	set if the event is enabled.
  * @read_event_value:	read a configuration value associated with the event.
  * @write_event_value:	write a configuration value for the event.
+ * @read_event_label:	function to request label name for a specified label,
+ *			for better event identification.
  * @validate_trigger:	function to validate the trigger when the
  *			current trigger gets changed.
+ * @get_current_scan_type: must be implemented by drivers that use ext_scan_type
+ *			in the channel spec to return the index of the currently
+ *			active ext_scan type for a channel.
  * @update_scan_mode:	function to configure device and scan buffer when
  *			channels have changed
  * @debugfs_reg_access:	function to read or write register value of device
- * @of_xlate:		function pointer to obtain channel specifier index.
- *			When #iio-cells is greater than '0', the driver could
- *			provide a custom of_xlate function that reads the
- *			*args* and returns the appropriate index in registered
- *			IIO channels array.
  * @fwnode_xlate:	fwnode based function pointer to obtain channel specifier index.
- *			Functionally the same as @of_xlate.
  * @hwfifo_set_watermark: function pointer to set the current hardware
  *			fifo watermark level; see hwfifo_* entries in
  *			Documentation/ABI/testing/sysfs-bus-iio for details on
@@ -494,7 +516,7 @@ struct iio_info {
 				  const struct iio_chan_spec *chan,
 				  enum iio_event_type type,
 				  enum iio_event_direction dir,
-				  int state);
+				  bool state);
 
 	int (*read_event_value)(struct iio_dev *indio_dev,
 				const struct iio_chan_spec *chan,
@@ -508,18 +530,26 @@ struct iio_info {
 				 enum iio_event_direction dir,
 				 enum iio_event_info info, int val, int val2);
 
+	int (*read_event_label)(struct iio_dev *indio_dev,
+				struct iio_chan_spec const *chan,
+				enum iio_event_type type,
+				enum iio_event_direction dir,
+				char *label);
+
 	int (*validate_trigger)(struct iio_dev *indio_dev,
 				struct iio_trigger *trig);
+	int (*get_current_scan_type)(const struct iio_dev *indio_dev,
+				     const struct iio_chan_spec *chan);
 	int (*update_scan_mode)(struct iio_dev *indio_dev,
 				const unsigned long *scan_mask);
 	int (*debugfs_reg_access)(struct iio_dev *indio_dev,
-				  unsigned reg, unsigned writeval,
-				  unsigned *readval);
+				  unsigned int reg, unsigned int writeval,
+				  unsigned int *readval);
 	int (*fwnode_xlate)(struct iio_dev *indio_dev,
 			    const struct fwnode_reference_args *iiospec);
-	int (*hwfifo_set_watermark)(struct iio_dev *indio_dev, unsigned val);
+	int (*hwfifo_set_watermark)(struct iio_dev *indio_dev, unsigned int val);
 	int (*hwfifo_flush_to_buffer)(struct iio_dev *indio_dev,
-				      unsigned count);
+				      unsigned int count);
 };
 
 /**
@@ -553,7 +583,9 @@ struct iio_buffer_setup_ops {
  *			and owner
  * @buffer:		[DRIVER] any buffer present
  * @scan_bytes:		[INTERN] num bytes captured to be fed to buffer demux
- * @available_scan_masks: [DRIVER] optional array of allowed bitmasks
+ * @available_scan_masks: [DRIVER] optional array of allowed bitmasks. Sort the
+ *			   array in order of preference, the most preferred
+ *			   masks first.
  * @masklength:		[INTERN] the length of the mask established from
  *			channels
  * @active_scan_mask:	[INTERN] union of all scan masks requested by buffers
@@ -579,9 +611,9 @@ struct iio_dev {
 	int				scan_bytes;
 
 	const unsigned long		*available_scan_masks;
-	unsigned			masklength;
+	unsigned int			__private masklength;
 	const unsigned long		*active_scan_mask;
-	bool				scan_timestamp;
+	bool				__private scan_timestamp;
 	struct iio_trigger		*trig;
 	struct iio_poll_func		*pollfunc;
 	struct iio_poll_func		*pollfunc_event;
@@ -594,7 +626,7 @@ struct iio_dev {
 	const struct iio_info		*info;
 	const struct iio_buffer_setup_ops	*setup_ops;
 
-	void				*priv;
+	void				*__private priv;
 };
 
 int iio_device_id(struct iio_dev *indio_dev);
@@ -629,12 +661,36 @@ void iio_device_unregister(struct iio_dev *indio_dev);
 int __devm_iio_device_register(struct device *dev, struct iio_dev *indio_dev,
 			       struct module *this_mod);
 int iio_push_event(struct iio_dev *indio_dev, u64 ev_code, s64 timestamp);
-int iio_device_claim_direct_mode(struct iio_dev *indio_dev);
-void iio_device_release_direct_mode(struct iio_dev *indio_dev);
+bool __iio_device_claim_direct(struct iio_dev *indio_dev);
+void __iio_device_release_direct(struct iio_dev *indio_dev);
+
+/*
+ * Helper functions that allow claim and release of direct mode
+ * in a fashion that doesn't generate many false positives from sparse.
+ * Note this must remain static inline in the header so that sparse
+ * can see the __acquire() marking. Revisit when sparse supports
+ * __cond_acquires()
+ */
+static inline bool iio_device_claim_direct(struct iio_dev *indio_dev)
+{
+	if (!__iio_device_claim_direct(indio_dev))
+		return false;
+
+	__acquire(iio_dev);
+
+	return true;
+}
+
+static inline void iio_device_release_direct(struct iio_dev *indio_dev)
+{
+	__iio_device_release_direct(indio_dev);
+	__release(indio_dev);
+}
+
 int iio_device_claim_buffer_mode(struct iio_dev *indio_dev);
 void iio_device_release_buffer_mode(struct iio_dev *indio_dev);
 
-extern struct bus_type iio_bus_type;
+extern const struct bus_type iio_bus_type;
 
 /**
  * iio_device_put() - reference counted deallocation of struct device
@@ -721,14 +777,51 @@ static inline void *iio_device_get_drvdata(const struct iio_dev *indio_dev)
  * to in turn include IIO_DMA_MINALIGN'd elements such as buffers which
  * must not share  cachelines with the rest of the structure, thus making
  * them safe for use with non-coherent DMA.
+ *
+ * A number of drivers also use this on buffers that include a 64-bit timestamp
+ * that is used with iio_push_to_buffers_with_ts(). Therefore, in the case where
+ * DMA alignment is not sufficient for proper timestamp alignment, we align to
+ * 8 bytes instead.
  */
-#define IIO_DMA_MINALIGN ARCH_KMALLOC_MINALIGN
+#define IIO_DMA_MINALIGN MAX(ARCH_DMA_MINALIGN, sizeof(s64))
+
+#define __IIO_DECLARE_BUFFER_WITH_TS(type, name, count) \
+	type name[ALIGN((count), sizeof(s64) / sizeof(type)) + sizeof(s64) / sizeof(type)]
+
+/**
+ * IIO_DECLARE_BUFFER_WITH_TS() - Declare a buffer with timestamp
+ * @type: element type of the buffer
+ * @name: identifier name of the buffer
+ * @count: number of elements in the buffer
+ *
+ * Declares a buffer that is safe to use with iio_push_to_buffers_with_ts(). In
+ * addition to allocating enough space for @count elements of @type, it also
+ * allocates space for a s64 timestamp at the end of the buffer and ensures
+ * proper alignment of the timestamp.
+ */
+#define IIO_DECLARE_BUFFER_WITH_TS(type, name, count) \
+	__IIO_DECLARE_BUFFER_WITH_TS(type, name, count) __aligned(sizeof(s64))
+
+/**
+ * IIO_DECLARE_DMA_BUFFER_WITH_TS() - Declare a DMA-aligned buffer with timestamp
+ * @type: element type of the buffer
+ * @name: identifier name of the buffer
+ * @count: number of elements in the buffer
+ *
+ * Same as IIO_DECLARE_BUFFER_WITH_TS(), but is uses __aligned(IIO_DMA_MINALIGN)
+ * to ensure that the buffer doesn't share cachelines with anything that comes
+ * before it in a struct. This should not be used for stack-allocated buffers
+ * as stack memory cannot generally be used for DMA.
+ */
+#define IIO_DECLARE_DMA_BUFFER_WITH_TS(type, name, count) \
+	__IIO_DECLARE_BUFFER_WITH_TS(type, name, count) __aligned(IIO_DMA_MINALIGN)
+
 struct iio_dev *iio_device_alloc(struct device *parent, int sizeof_priv);
 
 /* The information at the returned address is guaranteed to be cacheline aligned */
 static inline void *iio_priv(const struct iio_dev *indio_dev)
 {
-	return indio_dev->priv;
+	return ACCESS_PRIVATE(indio_dev, priv);
 }
 
 void iio_device_free(struct iio_dev *indio_dev);
@@ -753,6 +846,98 @@ static inline struct dentry *iio_get_debugfs_dentry(struct iio_dev *indio_dev)
 }
 #endif
 
+/**
+ * iio_device_suspend_triggering() - suspend trigger attached to an iio_dev
+ * @indio_dev: iio_dev associated with the device that will have triggers suspended
+ *
+ * Return 0 if successful, negative otherwise
+ **/
+int iio_device_suspend_triggering(struct iio_dev *indio_dev);
+
+/**
+ * iio_device_resume_triggering() - resume trigger attached to an iio_dev
+ *	that was previously suspended with iio_device_suspend_triggering()
+ * @indio_dev: iio_dev associated with the device that will have triggers resumed
+ *
+ * Return 0 if successful, negative otherwise
+ **/
+int iio_device_resume_triggering(struct iio_dev *indio_dev);
+
+#ifdef CONFIG_ACPI
+bool iio_read_acpi_mount_matrix(struct device *dev,
+				struct iio_mount_matrix *orientation,
+				char *acpi_method);
+const char *iio_get_acpi_device_name_and_data(struct device *dev, const void **data);
+#else
+static inline bool iio_read_acpi_mount_matrix(struct device *dev,
+					      struct iio_mount_matrix *orientation,
+					      char *acpi_method)
+{
+	return false;
+}
+static inline const char *
+iio_get_acpi_device_name_and_data(struct device *dev, const void **data)
+{
+	return NULL;
+}
+#endif
+static inline const char *iio_get_acpi_device_name(struct device *dev)
+{
+	return iio_get_acpi_device_name_and_data(dev, NULL);
+}
+
+/**
+ * iio_get_current_scan_type - Get the current scan type for a channel
+ * @indio_dev:	the IIO device to get the scan type for
+ * @chan:	the channel to get the scan type for
+ *
+ * Most devices only have one scan type per channel and can just access it
+ * directly without calling this function. Core IIO code and drivers that
+ * implement ext_scan_type in the channel spec should use this function to
+ * get the current scan type for a channel.
+ *
+ * Returns: the current scan type for the channel or error.
+ */
+static inline const struct iio_scan_type
+*iio_get_current_scan_type(const struct iio_dev *indio_dev,
+			   const struct iio_chan_spec *chan)
+{
+	int ret;
+
+	if (chan->has_ext_scan_type) {
+		ret = indio_dev->info->get_current_scan_type(indio_dev, chan);
+		if (ret < 0)
+			return ERR_PTR(ret);
+
+		if (ret >= chan->num_ext_scan_type)
+			return ERR_PTR(-EINVAL);
+
+		return &chan->ext_scan_type[ret];
+	}
+
+	return &chan->scan_type;
+}
+
+/**
+ * iio_get_masklength - Get length of the channels mask
+ * @indio_dev: the IIO device to get the masklength for
+ */
+static inline unsigned int iio_get_masklength(const struct iio_dev *indio_dev)
+{
+	return ACCESS_PRIVATE(indio_dev, masklength);
+}
+
+int iio_active_scan_mask_index(struct iio_dev *indio_dev);
+
+/**
+ * iio_for_each_active_channel - Iterated over active channels
+ * @indio_dev: the IIO device
+ * @chan: Holds the index of the enabled channel
+ */
+#define iio_for_each_active_channel(indio_dev, chan) \
+	for_each_set_bit((chan), (indio_dev)->active_scan_mask, \
+			 iio_get_masklength(indio_dev))
+
 ssize_t iio_format_value(char *buf, unsigned int type, int size, int *vals);
 
 int iio_str_to_fixpoint(const char *str, int fract_mult, int *integer,
diff --git a/include/linux/iio/imu/adis.h b/include/linux/iio/imu/adis.h
index dc9ea299e088..bfb6df68e6c9 100644
--- a/include/linux/iio/imu/adis.h
+++ b/include/linux/iio/imu/adis.h
@@ -9,8 +9,10 @@
 #ifndef __IIO_ADIS_H__
 #define __IIO_ADIS_H__
 
+#include <linux/cleanup.h>
 #include <linux/spi/spi.h>
 #include <linux/interrupt.h>
+#include <linux/iio/iio.h>
 #include <linux/iio/types.h>
 
 #define ADIS_WRITE_REG(reg) ((0x80 | (reg)))
@@ -20,6 +22,7 @@
 #define ADIS_REG_PAGE_ID 0x00
 
 struct adis;
+struct iio_dev_attr;
 
 /**
  * struct adis_timeouts - ADIS chip variant timeouts
@@ -41,6 +44,8 @@ struct adis_timeout {
  * @glob_cmd_reg: Register address of the GLOB_CMD register
  * @msc_ctrl_reg: Register address of the MSC_CTRL register
  * @diag_stat_reg: Register address of the DIAG_STAT register
+ * @diag_stat_size:	Length (in bytes) of the DIAG_STAT register. If 0 the
+ *			default length is 2 bytes long.
  * @prod_id_reg: Register address of the PROD_ID register
  * @prod_id: Product ID code that should be expected when reading @prod_id_reg
  * @self_test_mask: Bitmask of supported self-test operations
@@ -52,6 +57,7 @@ struct adis_timeout {
  * @enable_irq: Hook for ADIS devices that have a special IRQ enable/disable
  * @unmasked_drdy: True for devices that cannot mask/unmask the data ready pin
  * @has_paging: True if ADIS device has paged registers
+ * @has_fifo: True if ADIS device has a hardware FIFO
  * @burst_reg_cmd:	Register command that triggers burst
  * @burst_len:		Burst size in the SPI RX buffer. If @burst_max_len is defined,
  *			this should be the minimum size supported by the device.
@@ -67,6 +73,7 @@ struct adis_data {
 	unsigned int glob_cmd_reg;
 	unsigned int msc_ctrl_reg;
 	unsigned int diag_stat_reg;
+	unsigned int diag_stat_size;
 	unsigned int prod_id_reg;
 
 	unsigned int prod_id;
@@ -83,6 +90,7 @@ struct adis_data {
 	bool unmasked_drdy;
 
 	bool has_paging;
+	bool has_fifo;
 
 	unsigned int burst_reg_cmd;
 	unsigned int burst_len;
@@ -91,13 +99,28 @@ struct adis_data {
 };
 
 /**
+ * struct adis_ops: Custom ops for adis devices.
+ * @write: Custom spi write implementation.
+ * @read: Custom spi read implementation.
+ * @reset: Custom sw reset implementation. The custom implementation does not
+ *	   need to sleep after the reset. It's done by the library already.
+ */
+struct adis_ops {
+	int (*write)(struct adis *adis, unsigned int reg, unsigned int value,
+		     unsigned int size);
+	int (*read)(struct adis *adis, unsigned int reg, unsigned int *value,
+		    unsigned int size);
+	int (*reset)(struct adis *adis);
+};
+
+/**
  * struct adis - ADIS device instance data
  * @spi: Reference to SPI device which owns this ADIS IIO device
  * @trig: IIO trigger object data
  * @data: ADIS chip variant specific data
- * @burst: ADIS burst transfer information
  * @burst_extra_len: Burst extra length. Should only be used by devices that can
  *		     dynamically change their burst mode length.
+ * @ops: ops struct for custom read and write functions
  * @state_lock: Lock used by the device to protect state
  * @msg: SPI message object
  * @xfer: SPI transfer objects to be used for a @msg
@@ -113,7 +136,8 @@ struct adis {
 
 	const struct adis_data	*data;
 	unsigned int		burst_extra_len;
-	/**
+	const struct adis_ops	*ops;
+	/*
 	 * The state_lock is meant to be used during operations that require
 	 * a sequence of SPI R/W in order to protect the SPI transfer
 	 * information (fields 'xfer', 'msg' & 'current_page') between
@@ -131,7 +155,7 @@ struct adis {
 	unsigned long		irq_flag;
 	void			*buffer;
 
-	u8			tx[10] ____cacheline_aligned;
+	u8			tx[10] __aligned(IIO_DMA_MINALIGN);
 	u8			rx[4];
 };
 
@@ -143,17 +167,12 @@ int __adis_reset(struct adis *adis);
  * adis_reset() - Reset the device
  * @adis: The adis device
  *
- * Returns 0 on success, a negative error code otherwise
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_reset(struct adis *adis)
 {
-	int ret;
-
-	mutex_lock(&adis->state_lock);
-	ret = __adis_reset(adis);
-	mutex_unlock(&adis->state_lock);
-
-	return ret;
+	guard(mutex)(&adis->state_lock);
+	return __adis_reset(adis);
 }
 
 int __adis_write_reg(struct adis *adis, unsigned int reg,
@@ -165,36 +184,42 @@ int __adis_read_reg(struct adis *adis, unsigned int reg,
  * __adis_write_reg_8() - Write single byte to a register (unlocked)
  * @adis: The adis device
  * @reg: The address of the register to be written
- * @value: The value to write
+ * @val: The value to write
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int __adis_write_reg_8(struct adis *adis, unsigned int reg,
 				     u8 val)
 {
-	return __adis_write_reg(adis, reg, val, 1);
+	return adis->ops->write(adis, reg, val, 1);
 }
 
 /**
  * __adis_write_reg_16() - Write 2 bytes to a pair of registers (unlocked)
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
- * @value: Value to be written
+ * @val: Value to be written
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int __adis_write_reg_16(struct adis *adis, unsigned int reg,
 				      u16 val)
 {
-	return __adis_write_reg(adis, reg, val, 2);
+	return adis->ops->write(adis, reg, val, 2);
 }
 
 /**
  * __adis_write_reg_32() - write 4 bytes to four registers (unlocked)
  * @adis: The adis device
  * @reg: The address of the lower of the four register
- * @value: Value to be written
+ * @val: Value to be written
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg,
 				      u32 val)
 {
-	return __adis_write_reg(adis, reg, val, 4);
+	return adis->ops->write(adis, reg, val, 4);
 }
 
 /**
@@ -202,6 +227,8 @@ static inline int __adis_write_reg_32(struct adis *adis, unsigned int reg,
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
  * @val: The value read back from the device
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg,
 				     u16 *val)
@@ -209,7 +236,7 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg,
 	unsigned int tmp;
 	int ret;
 
-	ret = __adis_read_reg(adis, reg, &tmp, 2);
+	ret = adis->ops->read(adis, reg, &tmp, 2);
 	if (ret == 0)
 		*val = tmp;
 
@@ -221,6 +248,8 @@ static inline int __adis_read_reg_16(struct adis *adis, unsigned int reg,
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
  * @val: The value read back from the device
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg,
 				     u32 *val)
@@ -228,7 +257,7 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg,
 	unsigned int tmp;
 	int ret;
 
-	ret = __adis_read_reg(adis, reg, &tmp, 4);
+	ret = adis->ops->read(adis, reg, &tmp, 4);
 	if (ret == 0)
 		*val = tmp;
 
@@ -239,19 +268,16 @@ static inline int __adis_read_reg_32(struct adis *adis, unsigned int reg,
  * adis_write_reg() - write N bytes to register
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
- * @value: The value to write to device (up to 4 bytes)
+ * @val: The value to write to device (up to 4 bytes)
  * @size: The size of the @value (in bytes)
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_write_reg(struct adis *adis, unsigned int reg,
 				 unsigned int val, unsigned int size)
 {
-	int ret;
-
-	mutex_lock(&adis->state_lock);
-	ret = __adis_write_reg(adis, reg, val, size);
-	mutex_unlock(&adis->state_lock);
-
-	return ret;
+	guard(mutex)(&adis->state_lock);
+	return adis->ops->write(adis, reg, val, size);
 }
 
 /**
@@ -260,24 +286,23 @@ static inline int adis_write_reg(struct adis *adis, unsigned int reg,
  * @reg: The address of the lower of the two registers
  * @val: The value read back from the device
  * @size: The size of the @val buffer
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static int adis_read_reg(struct adis *adis, unsigned int reg,
 			 unsigned int *val, unsigned int size)
 {
-	int ret;
-
-	mutex_lock(&adis->state_lock);
-	ret = __adis_read_reg(adis, reg, val, size);
-	mutex_unlock(&adis->state_lock);
-
-	return ret;
+	guard(mutex)(&adis->state_lock);
+	return adis->ops->read(adis, reg, val, size);
 }
 
 /**
  * adis_write_reg_8() - Write single byte to a register
  * @adis: The adis device
  * @reg: The address of the register to be written
- * @value: The value to write
+ * @val: The value to write
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_write_reg_8(struct adis *adis, unsigned int reg,
 				   u8 val)
@@ -289,7 +314,9 @@ static inline int adis_write_reg_8(struct adis *adis, unsigned int reg,
  * adis_write_reg_16() - Write 2 bytes to a pair of registers
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
- * @value: Value to be written
+ * @val: Value to be written
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_write_reg_16(struct adis *adis, unsigned int reg,
 				    u16 val)
@@ -301,7 +328,9 @@ static inline int adis_write_reg_16(struct adis *adis, unsigned int reg,
  * adis_write_reg_32() - write 4 bytes to four registers
  * @adis: The adis device
  * @reg: The address of the lower of the four register
- * @value: Value to be written
+ * @val: Value to be written
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_write_reg_32(struct adis *adis, unsigned int reg,
 				    u32 val)
@@ -314,6 +343,8 @@ static inline int adis_write_reg_32(struct adis *adis, unsigned int reg,
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
  * @val: The value read back from the device
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_read_reg_16(struct adis *adis, unsigned int reg,
 				   u16 *val)
@@ -333,6 +364,8 @@ static inline int adis_read_reg_16(struct adis *adis, unsigned int reg,
  * @adis: The adis device
  * @reg: The address of the lower of the two registers
  * @val: The value read back from the device
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_read_reg_32(struct adis *adis, unsigned int reg,
 				   u32 *val)
@@ -358,16 +391,14 @@ int __adis_update_bits_base(struct adis *adis, unsigned int reg, const u32 mask,
  * @size: Size of the register to update
  *
  * Updates the desired bits of @reg in accordance with @mask and @val.
+ *
+ * Returns: %0 on success, a negative error code otherwise
  */
 static inline int adis_update_bits_base(struct adis *adis, unsigned int reg,
 					const u32 mask, const u32 val, u8 size)
 {
-	int ret;
-
-	mutex_lock(&adis->state_lock);
-	ret = __adis_update_bits_base(adis, reg, mask, val, size);
-	mutex_unlock(&adis->state_lock);
-	return ret;
+	guard(mutex)(&adis->state_lock);
+	return __adis_update_bits_base(adis, reg, mask, val, size);
 }
 
 /**
@@ -408,35 +439,19 @@ int __adis_enable_irq(struct adis *adis, bool enable);
 
 static inline int adis_enable_irq(struct adis *adis, bool enable)
 {
-	int ret;
-
-	mutex_lock(&adis->state_lock);
-	ret = __adis_enable_irq(adis, enable);
-	mutex_unlock(&adis->state_lock);
-
-	return ret;
+	guard(mutex)(&adis->state_lock);
+	return __adis_enable_irq(adis, enable);
 }
 
 static inline int adis_check_status(struct adis *adis)
 {
-	int ret;
-
-	mutex_lock(&adis->state_lock);
-	ret = __adis_check_status(adis);
-	mutex_unlock(&adis->state_lock);
-
-	return ret;
-}
-
-static inline void adis_dev_lock(struct adis *adis)
-{
-	mutex_lock(&adis->state_lock);
+	guard(mutex)(&adis->state_lock);
+	return __adis_check_status(adis);
 }
 
-static inline void adis_dev_unlock(struct adis *adis)
-{
-	mutex_unlock(&adis->state_lock);
-}
+#define adis_dev_auto_lock(adis)	guard(mutex)(&(adis)->state_lock)
+#define adis_dev_auto_scoped_lock(adis) \
+	scoped_guard(mutex, &(adis)->state_lock)
 
 int adis_single_conversion(struct iio_dev *indio_dev,
 			   const struct iio_chan_spec *chan,
@@ -514,11 +529,19 @@ int adis_single_conversion(struct iio_dev *indio_dev,
 #define ADIS_ROT_CHAN(mod, addr, si, info_sep, info_all, bits) \
 	ADIS_MOD_CHAN(IIO_ROT, mod, addr, si, info_sep, info_all, bits)
 
+#define devm_adis_setup_buffer_and_trigger(adis, indio_dev, trigger_handler)	\
+	devm_adis_setup_buffer_and_trigger_with_attrs((adis), (indio_dev),	\
+						      (trigger_handler), NULL,	\
+						      NULL)
+
 #ifdef CONFIG_IIO_ADIS_LIB_BUFFER
 
 int
-devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
-				   irq_handler_t trigger_handler);
+devm_adis_setup_buffer_and_trigger_with_attrs(struct adis *adis,
+					      struct iio_dev *indio_dev,
+					      irq_handler_t trigger_handler,
+					      const struct iio_buffer_setup_ops *ops,
+					      const struct iio_dev_attr **buffer_attrs);
 
 int devm_adis_probe_trigger(struct adis *adis, struct iio_dev *indio_dev);
 
@@ -528,8 +551,11 @@ int adis_update_scan_mode(struct iio_dev *indio_dev,
 #else /* CONFIG_IIO_BUFFER */
 
 static inline int
-devm_adis_setup_buffer_and_trigger(struct adis *adis, struct iio_dev *indio_dev,
-				   irq_handler_t trigger_handler)
+devm_adis_setup_buffer_and_trigger_with_attrs(struct adis *adis,
+					      struct iio_dev *indio_dev,
+					      irq_handler_t trigger_handler,
+					      const struct iio_buffer_setup_ops *ops,
+					      const struct iio_dev_attr **buffer_attrs)
 {
 	return 0;
 }
diff --git a/include/linux/iio/sw_device.h b/include/linux/iio/sw_device.h
index eff1e6b2595c..0f7fe7b522e3 100644
--- a/include/linux/iio/sw_device.h
+++ b/include/linux/iio/sw_device.h
@@ -51,9 +51,6 @@ void iio_unregister_sw_device_type(struct iio_sw_device_type *dt);
 struct iio_sw_device *iio_sw_device_create(const char *, const char *);
 void iio_sw_device_destroy(struct iio_sw_device *);
 
-int iio_sw_device_type_configfs_register(struct iio_sw_device_type *dt);
-void iio_sw_device_type_configfs_unregister(struct iio_sw_device_type *dt);
-
 static inline
 void iio_swd_group_init_type_name(struct iio_sw_device *d,
 				  const char *name,
diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h
index 47de2443e984..bc77f88df303 100644
--- a/include/linux/iio/sw_trigger.h
+++ b/include/linux/iio/sw_trigger.h
@@ -51,9 +51,6 @@ void iio_unregister_sw_trigger_type(struct iio_sw_trigger_type *tt);
 struct iio_sw_trigger *iio_sw_trigger_create(const char *, const char *);
 void iio_sw_trigger_destroy(struct iio_sw_trigger *);
 
-int iio_sw_trigger_type_configfs_register(struct iio_sw_trigger_type *tt);
-void iio_sw_trigger_type_configfs_unregister(struct iio_sw_trigger_type *tt);
-
 static inline
 void iio_swt_group_init_type_name(struct iio_sw_trigger *t,
 				  const char *name,
diff --git a/include/linux/iio/timer/stm32-lptim-trigger.h b/include/linux/iio/timer/stm32-lptim-trigger.h
index a34dcf6a6001..ce3cf0addb2e 100644
--- a/include/linux/iio/timer/stm32-lptim-trigger.h
+++ b/include/linux/iio/timer/stm32-lptim-trigger.h
@@ -14,6 +14,15 @@
 #define LPTIM1_OUT	"lptim1_out"
 #define LPTIM2_OUT	"lptim2_out"
 #define LPTIM3_OUT	"lptim3_out"
+#define LPTIM4_OUT	"lptim4_out"
+#define LPTIM5_OUT	"lptim5_out"
+
+#define LPTIM1_CH1	"lptim1_ch1"
+#define LPTIM1_CH2	"lptim1_ch2"
+#define LPTIM2_CH1	"lptim2_ch1"
+#define LPTIM2_CH2	"lptim2_ch2"
+#define LPTIM3_CH1	"lptim3_ch1"
+#define LPTIM4_CH1	"lptim4_ch1"
 
 #if IS_REACHABLE(CONFIG_IIO_STM32_LPTIMER_TRIGGER)
 bool is_stm32_lptim_trigger(struct iio_trigger *trig);
diff --git a/include/linux/iio/timer/stm32-timer-trigger.h b/include/linux/iio/timer/stm32-timer-trigger.h
index 37572e4dc73a..1ee237b56183 100644
--- a/include/linux/iio/timer/stm32-timer-trigger.h
+++ b/include/linux/iio/timer/stm32-timer-trigger.h
@@ -72,6 +72,12 @@
 
 #define TIM17_OC1	"tim17_oc1"
 
+#define TIM20_OC1	"tim20_oc1"
+#define TIM20_OC2	"tim20_oc2"
+#define TIM20_OC3	"tim20_oc3"
+#define TIM20_TRGO	"tim20_trgo"
+#define TIM20_TRGO2	"tim20_trgo2"
+
 #if IS_REACHABLE(CONFIG_IIO_STM32_TIMER_TRIGGER)
 bool is_stm32_timer_trigger(struct iio_trigger *trig);
 #else
diff --git a/include/linux/iio/trigger.h b/include/linux/iio/trigger.h
index 51f52c5c6092..bce3b1788199 100644
--- a/include/linux/iio/trigger.h
+++ b/include/linux/iio/trigger.h
@@ -171,6 +171,7 @@ void iio_trigger_free(struct iio_trigger *trig);
  */
 bool iio_trigger_using_own(struct iio_dev *indio_dev);
 
+int iio_validate_own_trigger(struct iio_dev *idev, struct iio_trigger *trig);
 int iio_trigger_validate_own_device(struct iio_trigger *trig,
 				     struct iio_dev *indio_dev);
 
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index 82faa98c719a..34eebad12d2c 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -19,6 +19,8 @@ enum iio_event_info {
 	IIO_EV_INFO_TIMEOUT,
 	IIO_EV_INFO_RESET_TIMEOUT,
 	IIO_EV_INFO_TAP2_MIN_DELAY,
+	IIO_EV_INFO_RUNNING_PERIOD,
+	IIO_EV_INFO_RUNNING_COUNT,
 };
 
 #define IIO_VAL_INT 1
@@ -66,6 +68,9 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_THERMOCOUPLE_TYPE,
 	IIO_CHAN_INFO_CALIBAMBIENT,
 	IIO_CHAN_INFO_ZEROPOINT,
+	IIO_CHAN_INFO_TROUGH,
+	IIO_CHAN_INFO_CONVDELAY,
+	IIO_CHAN_INFO_POWERFACTOR,
 };
 
 #endif /* _IIO_TYPES_H_ */
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 86b57757c7b1..8e29cb4e6a01 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -16,23 +16,6 @@ struct linux_binprm;
 
 #ifdef CONFIG_IMA
 extern enum hash_algo ima_get_current_hash_algo(void);
-extern int ima_bprm_check(struct linux_binprm *bprm);
-extern int ima_file_check(struct file *file, int mask);
-extern void ima_post_create_tmpfile(struct mnt_idmap *idmap,
-				    struct inode *inode);
-extern void ima_file_free(struct file *file);
-extern int ima_file_mmap(struct file *file, unsigned long reqprot,
-			 unsigned long prot, unsigned long flags);
-extern int ima_file_mprotect(struct vm_area_struct *vma, unsigned long prot);
-extern int ima_load_data(enum kernel_load_data_id id, bool contents);
-extern int ima_post_load_data(char *buf, loff_t size,
-			      enum kernel_load_data_id id, char *description);
-extern int ima_read_file(struct file *file, enum kernel_read_file_id id,
-			 bool contents);
-extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
-			      enum kernel_read_file_id id);
-extern void ima_post_path_mknod(struct mnt_idmap *idmap,
-				struct dentry *dentry);
 extern int ima_file_hash(struct file *file, char *buf, size_t buf_size);
 extern int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size);
 extern void ima_kexec_cmdline(int kernel_fd, const void *buf, int size);
@@ -49,6 +32,9 @@ static inline void ima_appraise_parse_cmdline(void) {}
 
 #ifdef CONFIG_IMA_KEXEC
 extern void ima_add_kexec_buffer(struct kimage *image);
+extern void ima_kexec_post_load(struct kimage *image);
+#else
+static inline void ima_kexec_post_load(struct kimage *image) {}
 #endif
 
 #else
@@ -57,68 +43,6 @@ static inline enum hash_algo ima_get_current_hash_algo(void)
 	return HASH_ALGO__LAST;
 }
 
-static inline int ima_bprm_check(struct linux_binprm *bprm)
-{
-	return 0;
-}
-
-static inline int ima_file_check(struct file *file, int mask)
-{
-	return 0;
-}
-
-static inline void ima_post_create_tmpfile(struct mnt_idmap *idmap,
-					   struct inode *inode)
-{
-}
-
-static inline void ima_file_free(struct file *file)
-{
-	return;
-}
-
-static inline int ima_file_mmap(struct file *file, unsigned long reqprot,
-				unsigned long prot, unsigned long flags)
-{
-	return 0;
-}
-
-static inline int ima_file_mprotect(struct vm_area_struct *vma,
-				    unsigned long prot)
-{
-	return 0;
-}
-
-static inline int ima_load_data(enum kernel_load_data_id id, bool contents)
-{
-	return 0;
-}
-
-static inline int ima_post_load_data(char *buf, loff_t size,
-				     enum kernel_load_data_id id,
-				     char *description)
-{
-	return 0;
-}
-
-static inline int ima_read_file(struct file *file, enum kernel_read_file_id id,
-				bool contents)
-{
-	return 0;
-}
-
-static inline int ima_post_read_file(struct file *file, void *buf, loff_t size,
-				     enum kernel_read_file_id id)
-{
-	return 0;
-}
-
-static inline void ima_post_path_mknod(struct mnt_idmap *idmap,
-				       struct dentry *dentry)
-{
-	return;
-}
-
 static inline int ima_file_hash(struct file *file, char *buf, size_t buf_size)
 {
 	return -EOPNOTSUPP;
@@ -169,76 +93,13 @@ static inline void ima_add_kexec_buffer(struct kimage *image)
 {}
 #endif
 
-#ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS
-extern void ima_post_key_create_or_update(struct key *keyring,
-					  struct key *key,
-					  const void *payload, size_t plen,
-					  unsigned long flags, bool create);
-#else
-static inline void ima_post_key_create_or_update(struct key *keyring,
-						 struct key *key,
-						 const void *payload,
-						 size_t plen,
-						 unsigned long flags,
-						 bool create) {}
-#endif  /* CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS */
-
 #ifdef CONFIG_IMA_APPRAISE
 extern bool is_ima_appraise_enabled(void);
-extern void ima_inode_post_setattr(struct mnt_idmap *idmap,
-				   struct dentry *dentry);
-extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,
-		       const void *xattr_value, size_t xattr_value_len);
-extern int ima_inode_set_acl(struct mnt_idmap *idmap,
-			     struct dentry *dentry, const char *acl_name,
-			     struct posix_acl *kacl);
-static inline int ima_inode_remove_acl(struct mnt_idmap *idmap,
-				       struct dentry *dentry,
-				       const char *acl_name)
-{
-	return ima_inode_set_acl(idmap, dentry, acl_name, NULL);
-}
-extern int ima_inode_removexattr(struct dentry *dentry, const char *xattr_name);
 #else
 static inline bool is_ima_appraise_enabled(void)
 {
 	return 0;
 }
-
-static inline void ima_inode_post_setattr(struct mnt_idmap *idmap,
-					  struct dentry *dentry)
-{
-	return;
-}
-
-static inline int ima_inode_setxattr(struct dentry *dentry,
-				     const char *xattr_name,
-				     const void *xattr_value,
-				     size_t xattr_value_len)
-{
-	return 0;
-}
-
-static inline int ima_inode_set_acl(struct mnt_idmap *idmap,
-				    struct dentry *dentry, const char *acl_name,
-				    struct posix_acl *kacl)
-{
-
-	return 0;
-}
-
-static inline int ima_inode_removexattr(struct dentry *dentry,
-					const char *xattr_name)
-{
-	return 0;
-}
-
-static inline int ima_inode_remove_acl(struct mnt_idmap *idmap,
-				       struct dentry *dentry,
-				       const char *acl_name)
-{
-	return 0;
-}
 #endif /* CONFIG_IMA_APPRAISE */
 
 #if defined(CONFIG_IMA_APPRAISE) && defined(CONFIG_INTEGRITY_TRUSTED_KEYRING)
diff --git a/include/linux/in6.h b/include/linux/in6.h
index 0777a21cbf86..403f926d33d8 100644
--- a/include/linux/in6.h
+++ b/include/linux/in6.h
@@ -18,6 +18,13 @@
 
 #include <uapi/linux/in6.h>
 
+/* Large enough to hold both sockaddr_in and sockaddr_in6. */
+struct sockaddr_inet {
+	unsigned short	sa_family;
+	char		sa_data[sizeof(struct sockaddr_in6) -
+				sizeof(unsigned short)];
+};
+
 /* IPv6 Wildcard Address (::) and Loopback Address (::1) defined in RFC2553
  * NOTE: Be aware the IN6ADDR_* constants and in6addr_* externals are defined
  * in network byte order, not in host byte order as are the IPv4 equivalents
diff --git a/include/linux/indirect_call_wrapper.h b/include/linux/indirect_call_wrapper.h
index c1c76a70a6ce..35227d47cfc9 100644
--- a/include/linux/indirect_call_wrapper.h
+++ b/include/linux/indirect_call_wrapper.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_INDIRECT_CALL_WRAPPER_H
 #define _LINUX_INDIRECT_CALL_WRAPPER_H
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 
 /*
  * INDIRECT_CALL_$NR - wrapper for indirect calls with $NR known builtin
@@ -11,7 +11,7 @@
  *  @__VA_ARGS__: arguments for @f
  *
  * Avoid retpoline overhead for known builtin, checking @f vs each of them and
- * eventually invoking directly the builtin function. The functions are check
+ * eventually invoking directly the builtin function. The functions are checked
  * in the given order. Fallback to the indirect call.
  */
 #define INDIRECT_CALL_1(f, f1, ...)					\
diff --git a/include/linux/inet.h b/include/linux/inet.h
index bd8276e96e60..9158772f3559 100644
--- a/include/linux/inet.h
+++ b/include/linux/inet.h
@@ -55,6 +55,6 @@ extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char
 
 extern int inet_pton_with_scope(struct net *net, unsigned short af,
 		const char *src, const char *port, struct sockaddr_storage *addr);
-extern bool inet_addr_is_any(struct sockaddr *addr);
+bool inet_addr_is_any(struct sockaddr_storage *addr);
 
 #endif	/* _LINUX_INET_H */
diff --git a/include/linux/inet_diag.h b/include/linux/inet_diag.h
index 84abb30a3fbb..704fd415c2b4 100644
--- a/include/linux/inet_diag.h
+++ b/include/linux/inet_diag.h
@@ -8,6 +8,7 @@
 struct inet_hashinfo;
 
 struct inet_diag_handler {
+	struct module	*owner;
 	void		(*dump)(struct sk_buff *skb,
 				struct netlink_callback *cb,
 				const struct inet_diag_req_v2 *r);
@@ -23,9 +24,6 @@ struct inet_diag_handler {
 					 bool net_admin,
 					 struct sk_buff *skb);
 
-	size_t		(*idiag_get_aux_size)(struct sock *sk,
-					      bool net_admin);
-
 	int		(*destroy)(struct sk_buff *in_skb,
 				   const struct inet_diag_req_v2 *req);
 
@@ -40,6 +38,11 @@ struct inet_diag_dump_data {
 #define inet_diag_nla_bpf_stgs req_nlas[INET_DIAG_REQ_SK_BPF_STORAGES]
 
 	struct bpf_sk_storage_diag *bpf_stg_diag;
+	bool mark_needed;	/* INET_DIAG_BC_MARK_COND present. */
+#ifdef CONFIG_SOCK_CGROUP_DATA
+	bool cgroup_needed;	/* INET_DIAG_BC_CGROUP_COND present. */
+#endif
+	bool userlocks_needed;	/* INET_DIAG_BC_AUTO present. */
 };
 
 struct inet_connection_sock;
@@ -47,18 +50,8 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk,
 		      struct sk_buff *skb, struct netlink_callback *cb,
 		      const struct inet_diag_req_v2 *req,
 		      u16 nlmsg_flags, bool net_admin);
-void inet_diag_dump_icsk(struct inet_hashinfo *h, struct sk_buff *skb,
-			 struct netlink_callback *cb,
-			 const struct inet_diag_req_v2 *r);
-int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo,
-			    struct netlink_callback *cb,
-			    const struct inet_diag_req_v2 *req);
-
-struct sock *inet_diag_find_one_icsk(struct net *net,
-				     struct inet_hashinfo *hashinfo,
-				     const struct inet_diag_req_v2 *req);
 
-int inet_diag_bc_sk(const struct nlattr *_bc, struct sock *sk);
+int inet_diag_bc_sk(const struct inet_diag_dump_data *cb_data, struct sock *sk);
 
 void inet_diag_msg_common_fill(struct inet_diag_msg *r, struct sock *sk);
 
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index ddb27fc0ee8c..5730ba6b1cfa 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -53,13 +53,15 @@ struct in_device {
 };
 
 #define IPV4_DEVCONF(cnf, attr) ((cnf).data[IPV4_DEVCONF_ ## attr - 1])
+#define IPV4_DEVCONF_RO(cnf, attr) READ_ONCE(IPV4_DEVCONF(cnf, attr))
 #define IPV4_DEVCONF_ALL(net, attr) \
 	IPV4_DEVCONF((*(net)->ipv4.devconf_all), attr)
+#define IPV4_DEVCONF_ALL_RO(net, attr) READ_ONCE(IPV4_DEVCONF_ALL(net, attr))
 
-static inline int ipv4_devconf_get(struct in_device *in_dev, int index)
+static inline int ipv4_devconf_get(const struct in_device *in_dev, int index)
 {
 	index--;
-	return in_dev->cnf.data[index];
+	return READ_ONCE(in_dev->cnf.data[index]);
 }
 
 static inline void ipv4_devconf_set(struct in_device *in_dev, int index,
@@ -67,7 +69,7 @@ static inline void ipv4_devconf_set(struct in_device *in_dev, int index,
 {
 	index--;
 	set_bit(index, in_dev->cnf.state);
-	in_dev->cnf.data[index] = val;
+	WRITE_ONCE(in_dev->cnf.data[index], val);
 }
 
 static inline void ipv4_devconf_setall(struct in_device *in_dev)
@@ -81,18 +83,18 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 	ipv4_devconf_set((in_dev), IPV4_DEVCONF_ ## attr, (val))
 
 #define IN_DEV_ANDCONF(in_dev, attr) \
-	(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr) && \
+	(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr) && \
 	 IN_DEV_CONF_GET((in_dev), attr))
 
 #define IN_DEV_NET_ORCONF(in_dev, net, attr) \
-	(IPV4_DEVCONF_ALL(net, attr) || \
+	(IPV4_DEVCONF_ALL_RO(net, attr) || \
 	 IN_DEV_CONF_GET((in_dev), attr))
 
 #define IN_DEV_ORCONF(in_dev, attr) \
 	IN_DEV_NET_ORCONF(in_dev, dev_net(in_dev->dev), attr)
 
 #define IN_DEV_MAXCONF(in_dev, attr) \
-	(max(IPV4_DEVCONF_ALL(dev_net(in_dev->dev), attr), \
+	(max(IPV4_DEVCONF_ALL_RO(dev_net(in_dev->dev), attr), \
 	     IN_DEV_CONF_GET((in_dev), attr)))
 
 #define IN_DEV_FORWARD(in_dev)		IN_DEV_CONF_GET((in_dev), FORWARDING)
@@ -139,7 +141,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 							  ARP_EVICT_NOCARRIER)
 
 struct in_ifaddr {
-	struct hlist_node	hash;
+	struct hlist_node	addr_lst;
 	struct in_ifaddr	__rcu *ifa_next;
 	struct in_device	*ifa_dev;
 	struct rcu_head		rcu_head;
@@ -224,6 +226,10 @@ static __inline__ bool bad_mask(__be32 mask, __be32 addr)
 	for (ifa = rtnl_dereference((in_dev)->ifa_list); ifa;	\
 	     ifa = rtnl_dereference(ifa->ifa_next))
 
+#define in_dev_for_each_ifa_rtnl_net(net, ifa, in_dev)			\
+	for (ifa = rtnl_net_dereference(net, (in_dev)->ifa_list); ifa;	\
+	     ifa = rtnl_net_dereference(net, ifa->ifa_next))
+
 #define in_dev_for_each_ifa_rcu(ifa, in_dev)			\
 	for (ifa = rcu_dereference((in_dev)->ifa_list); ifa;	\
 	     ifa = rcu_dereference(ifa->ifa_next))
@@ -250,6 +256,11 @@ static inline struct in_device *__in_dev_get_rtnl(const struct net_device *dev)
 	return rtnl_dereference(dev->ip_ptr);
 }
 
+static inline struct in_device *__in_dev_get_rtnl_net(const struct net_device *dev)
+{
+	return rtnl_net_dereference(dev_net(dev), dev->ip_ptr);
+}
+
 /* called with rcu_read_lock or rtnl held */
 static inline bool ip_ignore_linkdown(const struct net_device *dev)
 {
diff --git a/include/linux/init.h b/include/linux/init.h
index c5fe6d26f5b1..40331923b9f4 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -7,13 +7,6 @@
 #include <linux/stringify.h>
 #include <linux/types.h>
 
-/* Built-in __init functions needn't be compiled with retpoline */
-#if defined(__noretpoline) && !defined(MODULE)
-#define __noinitretpoline __noretpoline
-#else
-#define __noinitretpoline
-#endif
-
 /* These macros are used to mark some functions or 
  * initialized data (doesn't apply to uninitialized data)
  * as `initialization' functions. The kernel can take this
@@ -49,7 +42,8 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline
+#define __init		__section(".init.text") __cold __latent_entropy	\
+						__no_kstack_erase
 #define __initdata	__section(".init.data")
 #define __initconst	__section(".init.rodata")
 #define __exitdata	__section(".exit.data")
@@ -84,14 +78,15 @@
 
 #define __exit          __section(".exit.text") __exitused __cold notrace
 
-/* Used for MEMORY_HOTPLUG */
-#define __meminit        __section(".meminit.text") __cold notrace \
-						  __latent_entropy
-#define __meminitdata    __section(".meminit.data")
-#define __meminitconst   __section(".meminit.rodata")
-#define __memexit        __section(".memexit.text") __exitused __cold notrace
-#define __memexitdata    __section(".memexit.data")
-#define __memexitconst   __section(".memexit.rodata")
+#ifdef CONFIG_MEMORY_HOTPLUG
+#define __meminit
+#define __meminitdata
+#define __meminitconst
+#else
+#define __meminit	__init
+#define __meminitdata	__initdata
+#define __meminitconst	__initconst
+#endif
 
 /* For assembly routines */
 #define __HEAD		.section	".head.text","ax"
@@ -102,10 +97,6 @@
 #define __INITRODATA	.section	".init.rodata","a",%progbits
 #define __FINITDATA	.previous
 
-#define __MEMINIT        .section	".meminit.text", "ax"
-#define __MEMINITDATA    .section	".meminit.data", "aw"
-#define __MEMINITRODATA  .section	".meminit.rodata", "a"
-
 /* silence warnings when references are OK */
 #define __REF            .section       ".ref.text", "ax"
 #define __REFDATA        .section       ".ref.data", "aw"
@@ -152,19 +143,39 @@ extern unsigned int reset_devices;
 void setup_arch(char **);
 void prepare_namespace(void);
 void __init init_rootfs(void);
+
+void init_IRQ(void);
+void time_init(void);
+void poking_init(void);
+void pgtable_cache_init(void);
+
+extern initcall_entry_t __initcall_start[];
+extern initcall_entry_t __initcall0_start[];
+extern initcall_entry_t __initcall1_start[];
+extern initcall_entry_t __initcall2_start[];
+extern initcall_entry_t __initcall3_start[];
+extern initcall_entry_t __initcall4_start[];
+extern initcall_entry_t __initcall5_start[];
+extern initcall_entry_t __initcall6_start[];
+extern initcall_entry_t __initcall7_start[];
+extern initcall_entry_t __initcall_end[];
+
 extern struct file_system_type rootfs_fs_type;
 
-#if defined(CONFIG_STRICT_KERNEL_RWX) || defined(CONFIG_STRICT_MODULE_RWX)
 extern bool rodata_enabled;
-#endif
-#ifdef CONFIG_STRICT_KERNEL_RWX
 void mark_rodata_ro(void);
-#endif
 
 extern void (*late_time_init)(void);
 
 extern bool initcall_debug;
 
+#ifdef MODULE
+extern struct module __this_module;
+#define THIS_MODULE (&__this_module)
+#else
+#define THIS_MODULE ((struct module *)0)
+#endif
+
 #endif
   
 #ifndef MODULE
@@ -189,12 +200,13 @@ extern bool initcall_debug;
 
 /* Format: <modname>__<counter>_<line>_<fn> */
 #define __initcall_id(fn)					\
+	__PASTE(kmod_,						\
 	__PASTE(__KBUILD_MODNAME,				\
 	__PASTE(__,						\
 	__PASTE(__COUNTER__,					\
 	__PASTE(_,						\
 	__PASTE(__LINE__,					\
-	__PASTE(_, fn))))))
+	__PASTE(_, fn)))))))
 
 /* Format: __<prefix>__<iid><id> */
 #define __initcall_name(prefix, __iid, id)			\
@@ -309,6 +321,8 @@ struct obs_kernel_param {
 	int early;
 };
 
+extern const struct obs_kernel_param __setup_start[], __setup_end[];
+
 /*
  * Only for really core code.  See moduleparam.h for the normal way.
  *
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 40fc5813cf93..a6cb241ea00c 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -25,7 +25,6 @@
 extern struct files_struct init_files;
 extern struct fs_struct init_fs;
 extern struct nsproxy init_nsproxy;
-extern struct cred init_cred;
 
 #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 #define INIT_PREV_CPUTIME(x)	.prev_cputime = {			\
@@ -37,13 +36,6 @@ extern struct cred init_cred;
 
 #define INIT_TASK_COMM "swapper"
 
-/* Attach to the init_task data structure for proper alignment */
-#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
-#define __init_task_data __section(".data..init_task")
-#else
-#define __init_task_data /**/
-#endif
-
 /* Attach to the thread_info data structure for proper alignment */
 #define __init_thread_info __section(".data..init_thread_info")
 
diff --git a/include/linux/input.h b/include/linux/input.h
index 49790c1bd2c4..7d7cb0593a63 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -275,7 +275,8 @@ struct input_handle;
  *	it may not sleep
  * @events: event sequence handler. This method is being called by
  *	input core with interrupts disabled and dev->event_lock
- *	spinlock held and so it may not sleep
+ *	spinlock held and so it may not sleep. The method must return
+ *	number of events passed to it.
  * @filter: similar to @event; separates normal event handlers from
  *	"filters".
  * @match: called after comparing device's id with handler's id_table
@@ -285,6 +286,10 @@ struct input_handle;
  * @start: starts handler for given handle. This function is called by
  *	input core right after connect() method and also when a process
  *	that "grabbed" a device releases it
+ * @passive_observer: set to %true by drivers only interested in observing
+ *	data stream from devices if there are other users present. Such
+ *	drivers will not result in starting underlying hardware device
+ *	when input_open_device() is called for their handles
  * @legacy_minors: set to %true by drivers using legacy minor ranges
  * @minor: beginning of range of 32 legacy minors for devices this driver
  *	can provide
@@ -312,14 +317,15 @@ struct input_handler {
 	void *private;
 
 	void (*event)(struct input_handle *handle, unsigned int type, unsigned int code, int value);
-	void (*events)(struct input_handle *handle,
-		       const struct input_value *vals, unsigned int count);
+	unsigned int (*events)(struct input_handle *handle,
+			       struct input_value *vals, unsigned int count);
 	bool (*filter)(struct input_handle *handle, unsigned int type, unsigned int code, int value);
 	bool (*match)(struct input_handler *handler, struct input_dev *dev);
 	int (*connect)(struct input_handler *handler, struct input_dev *dev, const struct input_device_id *id);
 	void (*disconnect)(struct input_handle *handle);
 	void (*start)(struct input_handle *handle);
 
+	bool passive_observer;
 	bool legacy_minors;
 	int minor;
 	const char *name;
@@ -338,12 +344,16 @@ struct input_handler {
  * @name: name given to the handle by handler that created it
  * @dev: input device the handle is attached to
  * @handler: handler that works with the device through this handle
+ * @handle_events: event sequence handler. It is set up by the input core
+ *	according to event handling method specified in the @handler. See
+ *	input_handle_setup_event_handler().
+ *	This method is being called by the input core with interrupts disabled
+ *	and dev->event_lock spinlock held and so it may not sleep.
  * @d_node: used to put the handle on device's list of attached handles
  * @h_node: used to put the handle on handler's list of handles from which
  *	it gets events
  */
 struct input_handle {
-
 	void *private;
 
 	int open;
@@ -352,6 +362,10 @@ struct input_handle {
 	struct input_dev *dev;
 	struct input_handler *handler;
 
+	unsigned int (*handle_events)(struct input_handle *handle,
+				      struct input_value *vals,
+				      unsigned int count);
+
 	struct list_head	d_node;
 	struct list_head	h_node;
 };
@@ -514,7 +528,7 @@ void input_enable_softrepeat(struct input_dev *dev, int delay, int period);
 
 bool input_device_enabled(struct input_dev *dev);
 
-extern struct class input_class;
+extern const struct class input_class;
 
 /**
  * struct ff_device - force-feedback part of an input device
@@ -562,7 +576,7 @@ struct ff_device {
 
 	int max_effects;
 	struct ff_effect *effects;
-	struct file *effect_owners[];
+	struct file *effect_owners[] __counted_by(max_effects);
 };
 
 int input_ff_create(struct input_dev *dev, unsigned int max_effects);
diff --git a/include/linux/input/as5011.h b/include/linux/input/as5011.h
index 5fba52a56cd6..5705d5de3aea 100644
--- a/include/linux/input/as5011.h
+++ b/include/linux/input/as5011.h
@@ -7,7 +7,6 @@
  */
 
 struct as5011_platform_data {
-	unsigned int button_gpio;
 	unsigned int axis_irq; /* irq number */
 	unsigned long axis_irqflags;
 	char xp, xn; /* threshold for x axis */
diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h
index b8d8d69eba29..90867f44ab4d 100644
--- a/include/linux/input/matrix_keypad.h
+++ b/include/linux/input/matrix_keypad.h
@@ -34,52 +34,6 @@ struct matrix_keymap_data {
 	unsigned int	keymap_size;
 };
 
-/**
- * struct matrix_keypad_platform_data - platform-dependent keypad data
- * @keymap_data: pointer to &matrix_keymap_data
- * @row_gpios: pointer to array of gpio numbers representing rows
- * @col_gpios: pointer to array of gpio numbers reporesenting colums
- * @num_row_gpios: actual number of row gpios used by device
- * @num_col_gpios: actual number of col gpios used by device
- * @col_scan_delay_us: delay, measured in microseconds, that is
- *	needed before we can keypad after activating column gpio
- * @debounce_ms: debounce interval in milliseconds
- * @clustered_irq: may be specified if interrupts of all row/column GPIOs
- *	are bundled to one single irq
- * @clustered_irq_flags: flags that are needed for the clustered irq
- * @active_low: gpio polarity
- * @wakeup: controls whether the device should be set up as wakeup
- *	source
- * @no_autorepeat: disable key autorepeat
- * @drive_inactive_cols: drive inactive columns during scan, rather than
- *	making them inputs.
- *
- * This structure represents platform-specific data that use used by
- * matrix_keypad driver to perform proper initialization.
- */
-struct matrix_keypad_platform_data {
-	const struct matrix_keymap_data *keymap_data;
-
-	const unsigned int *row_gpios;
-	const unsigned int *col_gpios;
-
-	unsigned int	num_row_gpios;
-	unsigned int	num_col_gpios;
-
-	unsigned int	col_scan_delay_us;
-
-	/* key debounce interval in milli-second */
-	unsigned int	debounce_ms;
-
-	unsigned int	clustered_irq;
-	unsigned int	clustered_irq_flags;
-
-	bool		active_low;
-	bool		wakeup;
-	bool		no_autorepeat;
-	bool		drive_inactive_cols;
-};
-
 int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data,
 			       const char *keymap_name,
 			       unsigned int rows, unsigned int cols,
@@ -88,6 +42,4 @@ int matrix_keypad_build_keymap(const struct matrix_keymap_data *keymap_data,
 int matrix_keypad_parse_properties(struct device *dev,
 				   unsigned int *rows, unsigned int *cols);
 
-#define matrix_keypad_parse_of_params matrix_keypad_parse_properties
-
 #endif /* _MATRIX_KEYPAD_H */
diff --git a/include/linux/input/mt.h b/include/linux/input/mt.h
index 3b8580bd33c1..d30286298a00 100644
--- a/include/linux/input/mt.h
+++ b/include/linux/input/mt.h
@@ -17,6 +17,7 @@
 #define INPUT_MT_DROP_UNUSED	0x0004	/* drop contacts not seen in frame */
 #define INPUT_MT_TRACK		0x0008	/* use in-kernel tracking */
 #define INPUT_MT_SEMI_MT	0x0010	/* semi-mt device, finger count handled manually */
+#define INPUT_MT_TOTAL_FORCE	0x0020	/* calculate total force from slots pressure */
 
 /**
  * struct input_mt_slot - represents the state of an input MT slot
@@ -47,7 +48,7 @@ struct input_mt {
 	unsigned int flags;
 	unsigned int frame;
 	int *red;
-	struct input_mt_slot slots[];
+	struct input_mt_slot slots[] __counted_by(num_slots);
 };
 
 static inline void input_mt_set_value(struct input_mt_slot *slot,
diff --git a/include/linux/input/navpoint.h b/include/linux/input/navpoint.h
deleted file mode 100644
index d464ffb4db52..000000000000
--- a/include/linux/input/navpoint.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- *  Copyright (C) 2012 Paul Parsons <lost.distance@yahoo.com>
- */
-
-struct navpoint_platform_data {
-	int		port;		/* PXA SSP port for pxa_ssp_request() */
-	int		gpio;		/* GPIO for power on/off */
-};
diff --git a/include/linux/input/touch-overlay.h b/include/linux/input/touch-overlay.h
new file mode 100644
index 000000000000..0253e554d3cd
--- /dev/null
+++ b/include/linux/input/touch-overlay.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023 Javier Carrasco <javier.carrasco@wolfvision.net>
+ */
+
+#ifndef _TOUCH_OVERLAY
+#define _TOUCH_OVERLAY
+
+#include <linux/types.h>
+
+struct input_dev;
+
+int touch_overlay_map(struct list_head *list, struct input_dev *input);
+
+void touch_overlay_get_touchscreen_abs(struct list_head *list, u16 *x, u16 *y);
+
+bool touch_overlay_mapped_touchscreen(struct list_head *list);
+
+bool touch_overlay_process_contact(struct list_head *list,
+				   struct input_dev *input,
+				   struct input_mt_pos *pos, int slot);
+
+void touch_overlay_sync_frame(struct list_head *list, struct input_dev *input);
+
+#endif
diff --git a/include/linux/instruction_pointer.h b/include/linux/instruction_pointer.h
index cda1f706eaeb..aa0b3ffea935 100644
--- a/include/linux/instruction_pointer.h
+++ b/include/linux/instruction_pointer.h
@@ -2,7 +2,12 @@
 #ifndef _LINUX_INSTRUCTION_POINTER_H
 #define _LINUX_INSTRUCTION_POINTER_H
 
+#include <asm/linkage.h>
+
 #define _RET_IP_		(unsigned long)__builtin_return_address(0)
+
+#ifndef _THIS_IP_
 #define _THIS_IP_  ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
 
 #endif /* _LINUX_INSTRUCTION_POINTER_H */
diff --git a/include/linux/instrumentation.h b/include/linux/instrumentation.h
index bc7babe91b2e..bf675a8aef8a 100644
--- a/include/linux/instrumentation.h
+++ b/include/linux/instrumentation.h
@@ -4,14 +4,14 @@
 
 #ifdef CONFIG_NOINSTR_VALIDATION
 
+#include <linux/objtool.h>
 #include <linux/stringify.h>
 
 /* Begin/end of an instrumentation safe region */
 #define __instrumentation_begin(c) ({					\
 	asm volatile(__stringify(c) ": nop\n\t"				\
-		     ".pushsection .discard.instr_begin\n\t"		\
-		     ".long " __stringify(c) "b - .\n\t"		\
-		     ".popsection\n\t" : : "i" (c));			\
+		     ANNOTATE_INSTR_BEGIN(__ASM_BREF(c))		\
+		     : : "i" (c));					\
 })
 #define instrumentation_begin() __instrumentation_begin(__COUNTER__)
 
@@ -48,9 +48,8 @@
  */
 #define __instrumentation_end(c) ({					\
 	asm volatile(__stringify(c) ": nop\n\t"				\
-		     ".pushsection .discard.instr_end\n\t"		\
-		     ".long " __stringify(c) "b - .\n\t"		\
-		     ".popsection\n\t" : : "i" (c));			\
+		     ANNOTATE_INSTR_END(__ASM_BREF(c))			\
+		     : : "i" (c));					\
 })
 #define instrumentation_end() __instrumentation_end(__COUNTER__)
 #else /* !CONFIG_NOINSTR_VALIDATION */
diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h
index 1b608e00290a..711a1f0d1a73 100644
--- a/include/linux/instrumented.h
+++ b/include/linux/instrumented.h
@@ -148,6 +148,41 @@ instrument_copy_from_user_after(const void *to, const void __user *from,
 }
 
 /**
+ * instrument_memcpy_before - add instrumentation before non-instrumented memcpy
+ * @to: destination address
+ * @from: source address
+ * @n: number of bytes to copy
+ *
+ * Instrument memory accesses that happen in custom memcpy implementations. The
+ * instrumentation should be inserted before the memcpy call.
+ */
+static __always_inline void instrument_memcpy_before(void *to, const void *from,
+						     unsigned long n)
+{
+	kasan_check_write(to, n);
+	kasan_check_read(from, n);
+	kcsan_check_write(to, n);
+	kcsan_check_read(from, n);
+}
+
+/**
+ * instrument_memcpy_after - add instrumentation after non-instrumented memcpy
+ * @to: destination address
+ * @from: source address
+ * @n: number of bytes to copy
+ * @left: number of bytes not copied (if known)
+ *
+ * Instrument memory accesses that happen in custom memcpy implementations. The
+ * instrumentation should be inserted after the memcpy call.
+ */
+static __always_inline void instrument_memcpy_after(void *to, const void *from,
+						    unsigned long n,
+						    unsigned long left)
+{
+	kmsan_memmove(to, from, n - left);
+}
+
+/**
  * instrument_get_user() - add instrumentation to get_user()-like macros
  * @to: destination variable, may not be address-taken
  *
diff --git a/include/linux/int_log.h b/include/linux/int_log.h
new file mode 100644
index 000000000000..0a6f58c38b61
--- /dev/null
+++ b/include/linux/int_log.h
@@ -0,0 +1,56 @@
+/* SPDX-License-Identifier: LGPL-2.1-or-later */
+/*
+ * Provides fixed-point logarithm operations.
+ *
+ * Copyright (C) 2006 Christoph Pfister (christophpfister@gmail.com)
+ */
+
+#ifndef __LINUX_INT_LOG_H
+#define __LINUX_INT_LOG_H
+
+#include <linux/types.h>
+
+/**
+ * intlog2 - computes log2 of a value; the result is shifted left by 24 bits
+ *
+ * @value: The value (must be != 0)
+ *
+ * to use rational values you can use the following method:
+ *
+ *   intlog2(value) = intlog2(value * 2^x) - x * 2^24
+ *
+ * Some usecase examples:
+ *
+ *	intlog2(8) will give 3 << 24 = 3 * 2^24
+ *
+ *	intlog2(9) will give 3 << 24 + ... = 3.16... * 2^24
+ *
+ *	intlog2(1.5) = intlog2(3) - 2^24 = 0.584... * 2^24
+ *
+ *
+ * return: log2(value) * 2^24
+ */
+extern unsigned int intlog2(u32 value);
+
+/**
+ * intlog10 - computes log10 of a value; the result is shifted left by 24 bits
+ *
+ * @value: The value (must be != 0)
+ *
+ * to use rational values you can use the following method:
+ *
+ *   intlog10(value) = intlog10(value * 10^x) - x * 2^24
+ *
+ * An usecase example:
+ *
+ *	intlog10(1000) will give 3 << 24 = 3 * 2^24
+ *
+ *   due to the implementation intlog10(1000) might be not exactly 3 * 2^24
+ *
+ * look at intlog2 for similar examples
+ *
+ * return: log10(value) * 2^24
+ */
+extern unsigned int intlog10(u32 value);
+
+#endif
diff --git a/include/linux/integrity.h b/include/linux/integrity.h
index 2ea0f2f65ab6..f5842372359b 100644
--- a/include/linux/integrity.h
+++ b/include/linux/integrity.h
@@ -8,6 +8,7 @@
 #define _LINUX_INTEGRITY_H
 
 #include <linux/fs.h>
+#include <linux/iversion.h>
 
 enum integrity_status {
 	INTEGRITY_PASS = 0,
@@ -19,40 +20,46 @@ enum integrity_status {
 	INTEGRITY_UNKNOWN,
 };
 
-/* List of EVM protected security xattrs */
 #ifdef CONFIG_INTEGRITY
-extern struct integrity_iint_cache *integrity_inode_get(struct inode *inode);
-extern void integrity_inode_free(struct inode *inode);
 extern void __init integrity_load_keys(void);
 
 #else
-static inline struct integrity_iint_cache *
-				integrity_inode_get(struct inode *inode)
-{
-	return NULL;
-}
-
-static inline void integrity_inode_free(struct inode *inode)
-{
-	return;
-}
-
 static inline void integrity_load_keys(void)
 {
 }
 #endif /* CONFIG_INTEGRITY */
 
-#ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
-
-extern int integrity_kernel_module_request(char *kmod_name);
+/* An inode's attributes for detection of changes */
+struct integrity_inode_attributes {
+	u64 version;		/* track inode changes */
+	unsigned long ino;
+	dev_t dev;
+};
 
-#else
+/*
+ * On stacked filesystems the i_version alone is not enough to detect file data
+ * or metadata change. Additional metadata is required.
+ */
+static inline void
+integrity_inode_attrs_store(struct integrity_inode_attributes *attrs,
+			    u64 i_version, const struct inode *inode)
+{
+	attrs->version = i_version;
+	attrs->dev = inode->i_sb->s_dev;
+	attrs->ino = inode->i_ino;
+}
 
-static inline int integrity_kernel_module_request(char *kmod_name)
+/*
+ * On stacked filesystems detect whether the inode or its content has changed.
+ */
+static inline bool
+integrity_inode_attrs_changed(const struct integrity_inode_attributes *attrs,
+			      const struct inode *inode)
 {
-	return 0;
+	return (inode->i_sb->s_dev != attrs->dev ||
+		inode->i_ino != attrs->ino ||
+		!inode_eq_iversion(inode, attrs->version));
 }
 
-#endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */
 
 #endif /* _LINUX_INTEGRITY_H */
diff --git a/include/linux/intel-ish-client-if.h b/include/linux/intel-ish-client-if.h
index f45f13304add..2cd4f65aaa37 100644
--- a/include/linux/intel-ish-client-if.h
+++ b/include/linux/intel-ish-client-if.h
@@ -87,6 +87,8 @@ bool ishtp_wait_resume(struct ishtp_device *dev);
 ishtp_print_log ishtp_trace_callback(struct ishtp_cl_device *cl_device);
 /* Get device pointer of PCI device for DMA acces */
 struct device *ishtp_get_pci_device(struct ishtp_cl_device *cl_device);
+/* Get the ISHTP workqueue */
+struct workqueue_struct *ishtp_get_workqueue(struct ishtp_cl_device *cl_device);
 
 struct ishtp_cl *ishtp_cl_allocate(struct ishtp_cl_device *cl_device);
 void ishtp_cl_free(struct ishtp_cl *cl);
@@ -94,10 +96,12 @@ int ishtp_cl_link(struct ishtp_cl *cl);
 void ishtp_cl_unlink(struct ishtp_cl *cl);
 int ishtp_cl_disconnect(struct ishtp_cl *cl);
 int ishtp_cl_connect(struct ishtp_cl *cl);
+int ishtp_cl_establish_connection(struct ishtp_cl *cl, const guid_t *uuid,
+				  int tx_size, int rx_size, bool reset);
+void ishtp_cl_destroy_connection(struct ishtp_cl *cl, bool reset);
 int ishtp_cl_send(struct ishtp_cl *cl, uint8_t *buf, size_t length);
 int ishtp_cl_flush_queues(struct ishtp_cl *cl);
 int ishtp_cl_io_rb_recycle(struct ishtp_cl_rb *rb);
-bool ishtp_cl_tx_empty(struct ishtp_cl *cl);
 struct ishtp_cl_rb *ishtp_cl_rx_get_rb(struct ishtp_cl *cl);
 void *ishtp_get_client_data(struct ishtp_cl *cl);
 void ishtp_set_client_data(struct ishtp_cl *cl, void *data);
@@ -105,6 +109,7 @@ struct ishtp_device *ishtp_get_ishtp_device(struct ishtp_cl *cl);
 void ishtp_set_tx_ring_size(struct ishtp_cl *cl, int size);
 void ishtp_set_rx_ring_size(struct ishtp_cl *cl, int size);
 void ishtp_set_connection_state(struct ishtp_cl *cl, int state);
+int ishtp_get_connection_state(struct ishtp_cl *cl);
 void ishtp_cl_set_fw_client_id(struct ishtp_cl *cl, int fw_client_id);
 
 void ishtp_put_device(struct ishtp_cl_device *cl_dev);
diff --git a/include/linux/intel_dg_nvm_aux.h b/include/linux/intel_dg_nvm_aux.h
new file mode 100644
index 000000000000..625d46a6b96e
--- /dev/null
+++ b/include/linux/intel_dg_nvm_aux.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright(c) 2019-2025, Intel Corporation. All rights reserved.
+ */
+
+#ifndef __INTEL_DG_NVM_AUX_H__
+#define __INTEL_DG_NVM_AUX_H__
+
+#include <linux/auxiliary_bus.h>
+#include <linux/container_of.h>
+#include <linux/ioport.h>
+#include <linux/types.h>
+
+#define INTEL_DG_NVM_REGIONS 13
+
+struct intel_dg_nvm_region {
+	const char *name;
+};
+
+struct intel_dg_nvm_dev {
+	struct auxiliary_device aux_dev;
+	bool writable_override;
+	bool non_posted_erase;
+	struct resource bar;
+	struct resource bar2;
+	const struct intel_dg_nvm_region *regions;
+};
+
+#define auxiliary_dev_to_intel_dg_nvm_dev(auxiliary_dev) \
+	container_of(auxiliary_dev, struct intel_dg_nvm_dev, aux_dev)
+
+#endif /* __INTEL_DG_NVM_AUX_H__ */
diff --git a/include/linux/intel_pmt_features.h b/include/linux/intel_pmt_features.h
new file mode 100644
index 000000000000..53573a4a49b7
--- /dev/null
+++ b/include/linux/intel_pmt_features.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FEATURES_H
+#define _FEATURES_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+/* Common masks */
+#define PMT_CAP_TELEM			BIT(0)
+#define PMT_CAP_WATCHER			BIT(1)
+#define PMT_CAP_CRASHLOG		BIT(2)
+#define PMT_CAP_STREAMING		BIT(3)
+#define PMT_CAP_THRESHOLD		BIT(4)
+#define PMT_CAP_WINDOW			BIT(5)
+#define PMT_CAP_CONFIG			BIT(6)
+#define PMT_CAP_TRACING			BIT(7)
+#define PMT_CAP_INBAND			BIT(8)
+#define PMT_CAP_OOB			BIT(9)
+#define PMT_CAP_SECURED_CHAN		BIT(10)
+
+#define PMT_CAP_PMT_SP			BIT(11)
+#define PMT_CAP_PMT_SP_POLICY		GENMASK(17, 12)
+
+/* Per Core Performance Telemetry (PCPT) specific masks */
+#define PMT_CAP_PCPT_CORE_PERF		BIT(18)
+#define PMT_CAP_PCPT_CORE_C0_RES	BIT(19)
+#define PMT_CAP_PCPT_CORE_ACTIVITY	BIT(20)
+#define PMT_CAP_PCPT_CACHE_PERF		BIT(21)
+#define PMT_CAP_PCPT_QUALITY_TELEM	BIT(22)
+
+/* Per Core Environmental Telemetry (PCET) specific masks */
+#define PMT_CAP_PCET_WORKPOINT_HIST	BIT(18)
+#define PMT_CAP_PCET_CORE_CURR_TEMP	BIT(19)
+#define PMT_CAP_PCET_CORE_INST_RES	BIT(20)
+#define PMT_CAP_PCET_QUALITY_TELEM	BIT(21)	/* Same as PMT_CAP_PCPT */
+#define PMT_CAP_PCET_CORE_CDYN_LVL	BIT(22)
+#define PMT_CAP_PCET_CORE_STRESS_LVL	BIT(23)
+#define PMT_CAP_PCET_CORE_DAS		BIT(24)
+#define PMT_CAP_PCET_FIVR_HEALTH	BIT(25)
+#define PMT_CAP_PCET_ENERGY		BIT(26)
+#define PMT_CAP_PCET_PEM_STATUS		BIT(27)
+#define PMT_CAP_PCET_CORE_C_STATE	BIT(28)
+
+/* Per RMID Performance Telemetry specific masks */
+#define PMT_CAP_RMID_CORES_PERF		BIT(18)
+#define PMT_CAP_RMID_CACHE_PERF		BIT(19)
+#define PMT_CAP_RMID_PERF_QUAL		BIT(20)
+
+/* Accelerator Telemetry specific masks */
+#define PMT_CAP_ACCEL_CPM_TELEM		BIT(18)
+#define PMT_CAP_ACCEL_TIP_TELEM		BIT(19)
+
+/* Uncore Telemetry specific masks */
+#define PMT_CAP_UNCORE_IO_CA_TELEM	BIT(18)
+#define PMT_CAP_UNCORE_RMID_TELEM	BIT(19)
+#define PMT_CAP_UNCORE_D2D_ULA_TELEM	BIT(20)
+#define PMT_CAP_UNCORE_PKGC_TELEM	BIT(21)
+
+/* Crash Log specific masks */
+#define PMT_CAP_CRASHLOG_MAN_TRIG	BIT(11)
+#define PMT_CAP_CRASHLOG_CORE		BIT(12)
+#define PMT_CAP_CRASHLOG_UNCORE		BIT(13)
+#define PMT_CAP_CRASHLOG_TOR		BIT(14)
+#define PMT_CAP_CRASHLOG_S3M		BIT(15)
+#define PMT_CAP_CRASHLOG_PERSISTENCY	BIT(16)
+#define PMT_CAP_CRASHLOG_CLIP_GPIO	BIT(17)
+#define PMT_CAP_CRASHLOG_PRE_RESET	BIT(18)
+#define PMT_CAP_CRASHLOG_POST_RESET	BIT(19)
+
+/* PeTe Log specific masks */
+#define PMT_CAP_PETE_MAN_TRIG		BIT(11)
+#define PMT_CAP_PETE_ENCRYPTION		BIT(12)
+#define PMT_CAP_PETE_PERSISTENCY	BIT(13)
+#define PMT_CAP_PETE_REQ_TOKENS		BIT(14)
+#define PMT_CAP_PETE_PROD_ENABLED	BIT(15)
+#define PMT_CAP_PETE_DEBUG_ENABLED	BIT(16)
+
+/* TPMI control specific masks */
+#define PMT_CAP_TPMI_MAILBOX		BIT(11)
+#define PMT_CAP_TPMI_LOCK		BIT(12)
+
+/* Tracing specific masks */
+#define PMT_CAP_TRACE_SRAR		BIT(11)
+#define PMT_CAP_TRACE_CORRECTABLE	BIT(12)
+#define PMT_CAP_TRACE_MCTP		BIT(13)
+#define PMT_CAP_TRACE_MRT		BIT(14)
+
+/* Per RMID Energy Telemetry specific masks */
+#define PMT_CAP_RMID_ENERGY		BIT(18)
+#define PMT_CAP_RMID_ACTIVITY		BIT(19)
+#define PMT_CAP_RMID_ENERGY_QUAL	BIT(20)
+
+enum pmt_feature_id {
+	FEATURE_INVALID			= 0x0,
+	FEATURE_PER_CORE_PERF_TELEM	= 0x1,
+	FEATURE_PER_CORE_ENV_TELEM	= 0x2,
+	FEATURE_PER_RMID_PERF_TELEM	= 0x3,
+	FEATURE_ACCEL_TELEM		= 0x4,
+	FEATURE_UNCORE_TELEM		= 0x5,
+	FEATURE_CRASH_LOG		= 0x6,
+	FEATURE_PETE_LOG		= 0x7,
+	FEATURE_TPMI_CTRL		= 0x8,
+	FEATURE_RESERVED		= 0x9,
+	FEATURE_TRACING			= 0xA,
+	FEATURE_PER_RMID_ENERGY_TELEM	= 0xB,
+	FEATURE_MAX			= 0xB,
+};
+
+enum feature_layout {
+	LAYOUT_RMID,
+	LAYOUT_WATCHER,
+	LAYOUT_COMMAND,
+	LAYOUT_CAPS_ONLY,
+};
+
+struct pmt_cap {
+	u32		mask;
+	const char	*name;
+};
+
+extern const char * const pmt_feature_names[];
+extern enum feature_layout feature_layout[];
+extern struct pmt_cap pmt_cap_common[];
+extern struct pmt_cap pmt_cap_pcpt[];
+extern struct pmt_cap *pmt_caps_pcpt[];
+extern struct pmt_cap pmt_cap_pcet[];
+extern struct pmt_cap *pmt_caps_pcet[];
+extern struct pmt_cap pmt_cap_rmid_perf[];
+extern struct pmt_cap *pmt_caps_rmid_perf[];
+extern struct pmt_cap pmt_cap_accel[];
+extern struct pmt_cap *pmt_caps_accel[];
+extern struct pmt_cap pmt_cap_uncore[];
+extern struct pmt_cap *pmt_caps_uncore[];
+extern struct pmt_cap pmt_cap_crashlog[];
+extern struct pmt_cap *pmt_caps_crashlog[];
+extern struct pmt_cap pmt_cap_pete[];
+extern struct pmt_cap *pmt_caps_pete[];
+extern struct pmt_cap pmt_cap_tpmi[];
+extern struct pmt_cap *pmt_caps_tpmi[];
+extern struct pmt_cap pmt_cap_s3m[];
+extern struct pmt_cap *pmt_caps_s3m[];
+extern struct pmt_cap pmt_cap_tracing[];
+extern struct pmt_cap *pmt_caps_tracing[];
+extern struct pmt_cap pmt_cap_rmid_energy[];
+extern struct pmt_cap *pmt_caps_rmid_energy[];
+
+static inline bool pmt_feature_id_is_valid(enum pmt_feature_id id)
+{
+	if (id > FEATURE_MAX)
+		return false;
+
+	if (id == FEATURE_INVALID || id == FEATURE_RESERVED)
+		return false;
+
+	return true;
+}
+#endif
diff --git a/include/linux/intel_rapl.h b/include/linux/intel_rapl.h
index 9f4b6f5b822f..e9ade2ff4af6 100644
--- a/include/linux/intel_rapl.h
+++ b/include/linux/intel_rapl.h
@@ -14,6 +14,12 @@
 #include <linux/powercap.h>
 #include <linux/cpuhotplug.h>
 
+enum rapl_if_type {
+	RAPL_IF_MSR,	/* RAPL I/F using MSR registers */
+	RAPL_IF_MMIO,	/* RAPL I/F using MMIO registers */
+	RAPL_IF_TPMI,	/* RAPL I/F using TPMI registers */
+};
+
 enum rapl_domain_type {
 	RAPL_DOMAIN_PACKAGE,	/* entire package/socket */
 	RAPL_DOMAIN_PP0,	/* core power plane */
@@ -30,17 +36,23 @@ enum rapl_domain_reg_id {
 	RAPL_DOMAIN_REG_POLICY,
 	RAPL_DOMAIN_REG_INFO,
 	RAPL_DOMAIN_REG_PL4,
+	RAPL_DOMAIN_REG_UNIT,
+	RAPL_DOMAIN_REG_PL2,
 	RAPL_DOMAIN_REG_MAX,
 };
 
 struct rapl_domain;
 
 enum rapl_primitives {
-	ENERGY_COUNTER,
 	POWER_LIMIT1,
 	POWER_LIMIT2,
 	POWER_LIMIT4,
+	ENERGY_COUNTER,
 	FW_LOCK,
+	FW_HIGH_LOCK,
+	PL1_LOCK,
+	PL2_LOCK,
+	PL4_LOCK,
 
 	PL1_ENABLE,		/* power limit 1, aka long term */
 	PL1_CLAMP,		/* allow frequency to go below OS request */
@@ -74,12 +86,13 @@ struct rapl_domain_data {
 	unsigned long timestamp;
 };
 
-#define NR_POWER_LIMITS (3)
+#define NR_POWER_LIMITS	(POWER_LIMIT4 + 1)
+
 struct rapl_power_limit {
 	struct powercap_zone_constraint *constraint;
-	int prim_id;		/* primitive ID used to enable */
 	struct rapl_domain *domain;
 	const char *name;
+	bool locked;
 	u64 last_power_limit;
 };
 
@@ -87,21 +100,29 @@ struct rapl_package;
 
 #define RAPL_DOMAIN_NAME_LENGTH 16
 
+union rapl_reg {
+	void __iomem *mmio;
+	u32 msr;
+	u64 val;
+};
+
 struct rapl_domain {
 	char name[RAPL_DOMAIN_NAME_LENGTH];
 	enum rapl_domain_type id;
-	u64 regs[RAPL_DOMAIN_REG_MAX];
+	union rapl_reg regs[RAPL_DOMAIN_REG_MAX];
 	struct powercap_zone power_zone;
 	struct rapl_domain_data rdd;
 	struct rapl_power_limit rpl[NR_POWER_LIMITS];
 	u64 attr_map;		/* track capabilities */
 	unsigned int state;
-	unsigned int domain_energy_unit;
+	unsigned int power_unit;
+	unsigned int energy_unit;
+	unsigned int time_unit;
 	struct rapl_package *rp;
 };
 
 struct reg_action {
-	u64 reg;
+	union rapl_reg reg;
 	u64 mask;
 	u64 value;
 	int err;
@@ -121,18 +142,42 @@ struct reg_action {
  *				registers.
  * @write_raw:			Callback for writing RAPL interface specific
  *				registers.
+ * @defaults:			internal pointer to interface default settings
+ * @rpi:			internal pointer to interface primitive info
  */
 struct rapl_if_priv {
+	enum rapl_if_type type;
 	struct powercap_control_type *control_type;
-	struct rapl_domain *platform_rapl_domain;
 	enum cpuhp_state pcap_rapl_online;
-	u64 reg_unit;
-	u64 regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
+	union rapl_reg reg_unit;
+	union rapl_reg regs[RAPL_DOMAIN_MAX][RAPL_DOMAIN_REG_MAX];
 	int limits[RAPL_DOMAIN_MAX];
-	int (*read_raw)(int cpu, struct reg_action *ra);
-	int (*write_raw)(int cpu, struct reg_action *ra);
+	int (*read_raw)(int id, struct reg_action *ra, bool atomic);
+	int (*write_raw)(int id, struct reg_action *ra);
+	void *defaults;
+	void *rpi;
 };
 
+#ifdef CONFIG_PERF_EVENTS
+/**
+ * struct rapl_package_pmu_data: Per package data for PMU support
+ * @scale:		Scale of 2^-32 Joules for each energy counter increase.
+ * @lock:		Lock to protect n_active and active_list.
+ * @n_active:		Number of active events.
+ * @active_list:	List of active events.
+ * @timer_interval:	Maximum timer expiration time before counter overflow.
+ * @hrtimer:		Periodically update the counter to prevent overflow.
+ */
+struct rapl_package_pmu_data {
+	u64 scale[RAPL_DOMAIN_MAX];
+	raw_spinlock_t lock;
+	int n_active;
+	struct list_head active_list;
+	ktime_t timer_interval;
+	struct hrtimer hrtimer;
+};
+#endif
+
 /* maximum rapl package domain name: package-%d-die-%d */
 #define PACKAGE_DOMAIN_NAME_LENGTH 30
 
@@ -140,9 +185,6 @@ struct rapl_package {
 	unsigned int id;	/* logical die id, equals physical 1-die systems */
 	unsigned int nr_domains;
 	unsigned long domain_map;	/* bit map of active domains */
-	unsigned int power_unit;
-	unsigned int energy_unit;
-	unsigned int time_unit;
 	struct rapl_domain *domains;	/* array of domains, sized at runtime */
 	struct powercap_zone *power_zone;	/* keep track of parent zone */
 	unsigned long power_limit_irq;	/* keep track of package power limit
@@ -154,10 +196,28 @@ struct rapl_package {
 	struct cpumask cpumask;
 	char name[PACKAGE_DOMAIN_NAME_LENGTH];
 	struct rapl_if_priv *priv;
+#ifdef CONFIG_PERF_EVENTS
+	bool has_pmu;
+	struct rapl_package_pmu_data pmu_data;
+#endif
 };
 
-struct rapl_package *rapl_find_package_domain(int cpu, struct rapl_if_priv *priv);
-struct rapl_package *rapl_add_package(int cpu, struct rapl_if_priv *priv);
+struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv,
+						       bool id_is_cpu);
+struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *priv,
+						 bool id_is_cpu);
+void rapl_remove_package_cpuslocked(struct rapl_package *rp);
+
+struct rapl_package *rapl_find_package_domain(int id, struct rapl_if_priv *priv, bool id_is_cpu);
+struct rapl_package *rapl_add_package(int id, struct rapl_if_priv *priv, bool id_is_cpu);
 void rapl_remove_package(struct rapl_package *rp);
 
+#ifdef CONFIG_PERF_EVENTS
+int rapl_package_add_pmu(struct rapl_package *rp);
+void rapl_package_remove_pmu(struct rapl_package *rp);
+#else
+static inline int rapl_package_add_pmu(struct rapl_package *rp) { return 0; }
+static inline void rapl_package_remove_pmu(struct rapl_package *rp) { }
+#endif
+
 #endif /* __INTEL_RAPL_H__ */
diff --git a/include/linux/intel_tcc.h b/include/linux/intel_tcc.h
index f422612c28d6..fa788817acfc 100644
--- a/include/linux/intel_tcc.h
+++ b/include/linux/intel_tcc.h
@@ -13,6 +13,7 @@
 int intel_tcc_get_tjmax(int cpu);
 int intel_tcc_get_offset(int cpu);
 int intel_tcc_set_offset(int cpu, int offset);
-int intel_tcc_get_temp(int cpu, bool pkg);
+int intel_tcc_get_temp(int cpu, int *temp, bool pkg);
+u32 intel_tcc_get_offset_mask(void);
 
 #endif /* __INTEL_TCC_H__ */
diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h
index f505788c05da..94c06bf214fb 100644
--- a/include/linux/intel_tpmi.h
+++ b/include/linux/intel_tpmi.h
@@ -6,25 +6,32 @@
 #ifndef _INTEL_TPMI_H_
 #define _INTEL_TPMI_H_
 
-/**
- * struct intel_tpmi_plat_info - Platform information for a TPMI device instance
- * @package_id:	CPU Package id
- * @bus_number:	PCI bus number
- * @device_number: PCI device number
- * @function_number: PCI function number
- *
- * Structure to store platform data for a TPMI device instance. This
- * struct is used to return data via tpmi_get_platform_data().
+#include <linux/bitfield.h>
+
+struct oobmsm_plat_info;
+
+#define TPMI_VERSION_INVALID	0xff
+#define TPMI_MINOR_VERSION(val)	FIELD_GET(GENMASK(4, 0), val)
+#define TPMI_MAJOR_VERSION(val)	FIELD_GET(GENMASK(7, 5), val)
+
+/*
+ * List of supported TMPI IDs.
+ * Some TMPI IDs are not used by Linux, so the numbers are not consecutive.
  */
-struct intel_tpmi_plat_info {
-	u8 package_id;
-	u8 bus_number;
-	u8 device_number;
-	u8 function_number;
+enum intel_tpmi_id {
+	TPMI_ID_RAPL = 0,	/* Running Average Power Limit */
+	TPMI_ID_PEM = 1,	/* Power and Perf excursion Monitor */
+	TPMI_ID_UNCORE = 2,	/* Uncore Frequency Scaling */
+	TPMI_ID_SST = 5,	/* Speed Select Technology */
+	TPMI_ID_PLR = 0xc,	/* Performance Limit Reasons */
+	TPMI_CONTROL_ID = 0x80,	/* Special ID for getting feature status */
+	TPMI_INFO_ID = 0x81,	/* Special ID for PCI BDF and Package ID information */
 };
 
-struct intel_tpmi_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev);
+struct oobmsm_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev);
 struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index);
 int tpmi_get_resource_count(struct auxiliary_device *auxdev);
-
+int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked,
+			    bool *write_blocked);
+struct dentry *tpmi_get_debugfs_dir(struct auxiliary_device *auxdev);
 #endif
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
new file mode 100644
index 000000000000..53f6fe88e369
--- /dev/null
+++ b/include/linux/intel_vsec.h
@@ -0,0 +1,239 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _INTEL_VSEC_H
+#define _INTEL_VSEC_H
+
+#include <linux/auxiliary_bus.h>
+#include <linux/bits.h>
+#include <linux/err.h>
+#include <linux/intel_pmt_features.h>
+
+/*
+ * VSEC_CAP_UNUSED is reserved. It exists to prevent zero initialized
+ * intel_vsec devices from being automatically set to a known
+ * capability with ID 0
+ */
+#define VSEC_CAP_UNUSED		BIT(0)
+#define VSEC_CAP_TELEMETRY	BIT(1)
+#define VSEC_CAP_WATCHER	BIT(2)
+#define VSEC_CAP_CRASHLOG	BIT(3)
+#define VSEC_CAP_SDSI		BIT(4)
+#define VSEC_CAP_TPMI		BIT(5)
+#define VSEC_CAP_DISCOVERY	BIT(6)
+#define VSEC_FEATURE_COUNT	7
+
+/* Intel DVSEC offsets */
+#define INTEL_DVSEC_ENTRIES		0xA
+#define INTEL_DVSEC_SIZE		0xB
+#define INTEL_DVSEC_TABLE		0xC
+#define INTEL_DVSEC_TABLE_BAR(x)	((x) & GENMASK(2, 0))
+#define INTEL_DVSEC_TABLE_OFFSET(x)	((x) & GENMASK(31, 3))
+#define TABLE_OFFSET_SHIFT		3
+
+struct pci_dev;
+struct resource;
+
+enum intel_vsec_id {
+	VSEC_ID_TELEMETRY	= 2,
+	VSEC_ID_WATCHER		= 3,
+	VSEC_ID_CRASHLOG	= 4,
+	VSEC_ID_DISCOVERY	= 12,
+	VSEC_ID_SDSI		= 65,
+	VSEC_ID_TPMI		= 66,
+};
+
+/**
+ * struct intel_vsec_header - Common fields of Intel VSEC and DVSEC registers.
+ * @rev:         Revision ID of the VSEC/DVSEC register space
+ * @length:      Length of the VSEC/DVSEC register space
+ * @id:          ID of the feature
+ * @num_entries: Number of instances of the feature
+ * @entry_size:  Size of the discovery table for each feature
+ * @tbir:        BAR containing the discovery tables
+ * @offset:      BAR offset of start of the first discovery table
+ */
+struct intel_vsec_header {
+	u8	rev;
+	u16	length;
+	u16	id;
+	u8	num_entries;
+	u8	entry_size;
+	u8	tbir;
+	u32	offset;
+};
+
+enum intel_vsec_quirks {
+	/* Watcher feature not supported */
+	VSEC_QUIRK_NO_WATCHER	= BIT(0),
+
+	/* Crashlog feature not supported */
+	VSEC_QUIRK_NO_CRASHLOG	= BIT(1),
+
+	/* Use shift instead of mask to read discovery table offset */
+	VSEC_QUIRK_TABLE_SHIFT	= BIT(2),
+
+	/* DVSEC not present (provided in driver data) */
+	VSEC_QUIRK_NO_DVSEC	= BIT(3),
+
+	/* Platforms requiring quirk in the auxiliary driver */
+	VSEC_QUIRK_EARLY_HW     = BIT(4),
+};
+
+/**
+ * struct pmt_callbacks - Callback infrastructure for PMT devices
+ * ->read_telem() when specified, called by client driver to access PMT data (instead
+ * of direct copy).
+ * @pdev:  PCI device reference for the callback's use
+ * @guid:  ID of data to acccss
+ * @data:  buffer for the data to be copied
+ * @off:   offset into the requested buffer
+ * @count: size of buffer
+ */
+struct pmt_callbacks {
+	int (*read_telem)(struct pci_dev *pdev, u32 guid, u64 *data, loff_t off, u32 count);
+};
+
+struct vsec_feature_dependency {
+	unsigned long feature;
+	unsigned long supplier_bitmap;
+};
+
+/**
+ * struct intel_vsec_platform_info - Platform specific data
+ * @parent:    parent device in the auxbus chain
+ * @headers:   list of headers to define the PMT client devices to create
+ * @deps:      array of feature dependencies
+ * @priv_data: private data, usable by parent devices, currently a callback
+ * @caps:      bitmask of PMT capabilities for the given headers
+ * @quirks:    bitmask of VSEC device quirks
+ * @base_addr: allow a base address to be specified (rather than derived)
+ * @num_deps:  Count feature dependencies
+ */
+struct intel_vsec_platform_info {
+	struct device *parent;
+	struct intel_vsec_header **headers;
+	const struct vsec_feature_dependency *deps;
+	void *priv_data;
+	unsigned long caps;
+	unsigned long quirks;
+	u64 base_addr;
+	int num_deps;
+};
+
+/**
+ * struct intel_sec_device - Auxbus specific device information
+ * @auxdev:        auxbus device struct for auxbus access
+ * @pcidev:        pci device associated with the device
+ * @resource:      any resources shared by the parent
+ * @ida:           id reference
+ * @num_resources: number of resources
+ * @id:            xarray id
+ * @priv_data:     any private data needed
+ * @quirks:        specified quirks
+ * @base_addr:     base address of entries (if specified)
+ * @cap_id:        the enumerated id of the vsec feature
+ */
+struct intel_vsec_device {
+	struct auxiliary_device auxdev;
+	struct pci_dev *pcidev;
+	struct resource *resource;
+	struct ida *ida;
+	int num_resources;
+	int id; /* xa */
+	void *priv_data;
+	size_t priv_data_size;
+	unsigned long quirks;
+	u64 base_addr;
+	unsigned long cap_id;
+};
+
+/**
+ * struct oobmsm_plat_info - Platform information for a device instance
+ * @cdie_mask:       Mask of all compute dies in the partition
+ * @package_id:      CPU Package id
+ * @partition:       Package partition id when multiple VSEC PCI devices per package
+ * @segment:         PCI segment ID
+ * @bus_number:      PCI bus number
+ * @device_number:   PCI device number
+ * @function_number: PCI function number
+ *
+ * Structure to store platform data for a OOBMSM device instance.
+ */
+struct oobmsm_plat_info {
+	u16 cdie_mask;
+	u8 package_id;
+	u8 partition;
+	u8 segment;
+	u8 bus_number;
+	u8 device_number;
+	u8 function_number;
+};
+
+struct telemetry_region {
+	struct oobmsm_plat_info	plat_info;
+	void __iomem		*addr;
+	size_t			size;
+	u32			guid;
+	u32			num_rmids;
+};
+
+struct pmt_feature_group {
+	enum pmt_feature_id	id;
+	int			count;
+	struct kref		kref;
+	struct telemetry_region	regions[];
+};
+
+int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
+		       struct intel_vsec_device *intel_vsec_dev,
+		       const char *name);
+
+static inline struct intel_vsec_device *dev_to_ivdev(struct device *dev)
+{
+	return container_of(dev, struct intel_vsec_device, auxdev.dev);
+}
+
+static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device *auxdev)
+{
+	return container_of(auxdev, struct intel_vsec_device, auxdev);
+}
+
+#if IS_ENABLED(CONFIG_INTEL_VSEC)
+int intel_vsec_register(struct pci_dev *pdev,
+			 struct intel_vsec_platform_info *info);
+int intel_vsec_set_mapping(struct oobmsm_plat_info *plat_info,
+			   struct intel_vsec_device *vsec_dev);
+struct oobmsm_plat_info *intel_vsec_get_mapping(struct pci_dev *pdev);
+#else
+static inline int intel_vsec_register(struct pci_dev *pdev,
+				       struct intel_vsec_platform_info *info)
+{
+	return -ENODEV;
+}
+static inline int intel_vsec_set_mapping(struct oobmsm_plat_info *plat_info,
+					 struct intel_vsec_device *vsec_dev)
+{
+	return -ENODEV;
+}
+static inline struct oobmsm_plat_info *intel_vsec_get_mapping(struct pci_dev *pdev)
+{
+	return ERR_PTR(-ENODEV);
+}
+#endif
+
+#if IS_ENABLED(CONFIG_INTEL_PMT_TELEMETRY)
+struct pmt_feature_group *
+intel_pmt_get_regions_by_feature(enum pmt_feature_id id);
+
+void intel_pmt_put_feature_group(struct pmt_feature_group *feature_group);
+#else
+static inline struct pmt_feature_group *
+intel_pmt_get_regions_by_feature(enum pmt_feature_id id)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline void
+intel_pmt_put_feature_group(struct pmt_feature_group *feature_group) {}
+#endif
+
+#endif
diff --git a/include/linux/interconnect-clk.h b/include/linux/interconnect-clk.h
new file mode 100644
index 000000000000..9bcee3e9c56c
--- /dev/null
+++ b/include/linux/interconnect-clk.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023, Linaro Ltd.
+ */
+
+#ifndef __LINUX_INTERCONNECT_CLK_H
+#define __LINUX_INTERCONNECT_CLK_H
+
+struct device;
+
+struct icc_clk_data {
+	struct clk *clk;
+	const char *name;
+	unsigned int master_id;
+	unsigned int slave_id;
+};
+
+struct icc_provider *icc_clk_register(struct device *dev,
+				      unsigned int first_id,
+				      unsigned int num_clocks,
+				      const struct icc_clk_data *data);
+int devm_icc_clk_register(struct device *dev, unsigned int first_id,
+			  unsigned int num_clocks, const struct icc_clk_data *data);
+void icc_clk_unregister(struct icc_provider *provider);
+
+#endif
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index e6d8aca6886d..8a2f652a05ff 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -33,10 +33,10 @@ struct icc_node_data {
  */
 struct icc_onecell_data {
 	unsigned int num_nodes;
-	struct icc_node *nodes[];
+	struct icc_node *nodes[] __counted_by(num_nodes);
 };
 
-struct icc_node *of_icc_xlate_onecell(struct of_phandle_args *spec,
+struct icc_node *of_icc_xlate_onecell(const struct of_phandle_args *spec,
 				      void *data);
 
 /**
@@ -65,8 +65,9 @@ struct icc_provider {
 			 u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
 	void (*pre_aggregate)(struct icc_node *node);
 	int (*get_bw)(struct icc_node *node, u32 *avg, u32 *peak);
-	struct icc_node* (*xlate)(struct of_phandle_args *spec, void *data);
-	struct icc_node_data* (*xlate_extended)(struct of_phandle_args *spec, void *data);
+	struct icc_node* (*xlate)(const struct of_phandle_args *spec, void *data);
+	struct icc_node_data* (*xlate_extended)(const struct of_phandle_args *spec,
+						void *data);
 	struct device		*dev;
 	int			users;
 	bool			inter_set;
@@ -115,8 +116,11 @@ struct icc_node {
 
 int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw,
 		      u32 peak_bw, u32 *agg_avg, u32 *agg_peak);
+struct icc_node *icc_node_create_dyn(void);
 struct icc_node *icc_node_create(int id);
 void icc_node_destroy(int id);
+int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name);
+int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node);
 int icc_link_create(struct icc_node *node, const int dst_id);
 void icc_node_add(struct icc_node *node, struct icc_provider *provider);
 void icc_node_del(struct icc_node *node);
@@ -124,7 +128,7 @@ int icc_nodes_remove(struct icc_provider *provider);
 void icc_provider_init(struct icc_provider *provider);
 int icc_provider_register(struct icc_provider *provider);
 void icc_provider_deregister(struct icc_provider *provider);
-struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec);
+struct icc_node_data *of_icc_get_from_provider(const struct of_phandle_args *spec);
 void icc_sync_state(struct device *dev);
 
 #else
@@ -135,6 +139,11 @@ static inline int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw,
 	return -ENOTSUPP;
 }
 
+static inline struct icc_node *icc_node_create_dyn(void)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
 static inline struct icc_node *icc_node_create(int id)
 {
 	return ERR_PTR(-ENOTSUPP);
@@ -144,6 +153,17 @@ static inline void icc_node_destroy(int id)
 {
 }
 
+static inline int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider,
+				    const char *name)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int icc_link_create(struct icc_node *node, const int dst_id)
 {
 	return -ENOTSUPP;
@@ -171,7 +191,7 @@ static inline int icc_provider_register(struct icc_provider *provider)
 
 static inline void icc_provider_deregister(struct icc_provider *provider) { }
 
-static inline struct icc_node_data *of_icc_get_from_provider(struct of_phandle_args *spec)
+static inline struct icc_node_data *of_icc_get_from_provider(const struct of_phandle_args *spec)
 {
 	return ERR_PTR(-ENOTSUPP);
 }
diff --git a/include/linux/interconnect.h b/include/linux/interconnect.h
index 2b0e784ba771..4b12821528a6 100644
--- a/include/linux/interconnect.h
+++ b/include/linux/interconnect.h
@@ -16,10 +16,13 @@
 #define MBps_to_icc(x)	((x) * 1000)
 #define GBps_to_icc(x)	((x) * 1000 * 1000)
 #define bps_to_icc(x)	(1)
-#define kbps_to_icc(x)	((x) / 8 + ((x) % 8 ? 1 : 0))
+#define kbps_to_icc(x)	(((x) + 7) / 8)
 #define Mbps_to_icc(x)	((x) * 1000 / 8)
 #define Gbps_to_icc(x)	((x) * 1000 * 1000 / 8)
 
+/* macro to indicate dynamic id allocation */
+#define ICC_ALLOC_DYN_ID	-1
+
 struct icc_path;
 struct device;
 
@@ -40,8 +43,6 @@ struct icc_bulk_data {
 
 #if IS_ENABLED(CONFIG_INTERCONNECT)
 
-struct icc_path *icc_get(struct device *dev, const int src_id,
-			 const int dst_id);
 struct icc_path *of_icc_get(struct device *dev, const char *name);
 struct icc_path *devm_of_icc_get(struct device *dev, const char *name);
 int devm_of_icc_bulk_get(struct device *dev, int num_paths, struct icc_bulk_data *paths);
@@ -61,12 +62,6 @@ void icc_bulk_disable(int num_paths, const struct icc_bulk_data *paths);
 
 #else
 
-static inline struct icc_path *icc_get(struct device *dev, const int src_id,
-				       const int dst_id)
-{
-	return NULL;
-}
-
 static inline struct icc_path *of_icc_get(struct device *dev,
 					  const char *name)
 {
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a92bce40b04b..266f2b39213a 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -5,13 +5,14 @@
 
 #include <linux/kernel.h>
 #include <linux/bitops.h>
-#include <linux/cpumask.h>
+#include <linux/cleanup.h>
 #include <linux/irqreturn.h>
 #include <linux/irqnr.h>
 #include <linux/hardirq.h>
 #include <linux/irqflags.h>
 #include <linux/hrtimer.h>
 #include <linux/kref.h>
+#include <linux/cpumask_types.h>
 #include <linux/workqueue.h>
 #include <linux/jump_label.h>
 
@@ -67,6 +68,8 @@
  *                later.
  * IRQF_NO_DEBUG - Exclude from runnaway detection for IPI and similar handlers,
  *		   depends on IRQF_PERCPU.
+ * IRQF_COND_ONESHOT - Agree to do IRQF_ONESHOT if already set for a shared
+ *                 interrupt.
  */
 #define IRQF_SHARED		0x00000080
 #define IRQF_PROBE_SHARED	0x00000100
@@ -82,6 +85,7 @@
 #define IRQF_COND_SUSPEND	0x00040000
 #define IRQF_NO_AUTOEN		0x00080000
 #define IRQF_NO_DEBUG		0x00100000
+#define IRQF_COND_ONESHOT	0x00200000
 
 #define IRQF_TIMER		(__IRQF_TIMER | IRQF_NO_SUSPEND | IRQF_NO_THREAD)
 
@@ -105,6 +109,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  * @name:	name of the device
  * @dev_id:	cookie to identify the device
  * @percpu_dev_id:	cookie to identify the device
+ * @affinity:	CPUs this irqaction is allowed to run on
  * @next:	pointer to the next irqaction for shared interrupts
  * @irq:	interrupt number
  * @flags:	flags (see IRQF_* above)
@@ -117,8 +122,11 @@ typedef irqreturn_t (*irq_handler_t)(int, void *);
  */
 struct irqaction {
 	irq_handler_t		handler;
-	void			*dev_id;
-	void __percpu		*percpu_dev_id;
+	union {
+		void		*dev_id;
+		void __percpu	*percpu_dev_id;
+	};
+	const struct cpumask	*affinity;
 	struct irqaction	*next;
 	irq_handler_t		thread_fn;
 	struct task_struct	*thread;
@@ -136,7 +144,7 @@ extern irqreturn_t no_action(int cpl, void *dev_id);
 /*
  * If a (PCI) device interrupt is not connected we set dev->irq to
  * IRQ_NOTCONNECTED. This causes request_irq() to fail with -ENOTCONN, so we
- * can distingiush that case from other error returns.
+ * can distinguish that case from other error returns.
  *
  * 0x80000000 is guaranteed to be outside the available range of interrupts
  * and easy to distinguish from other possible incorrect values.
@@ -165,7 +173,7 @@ static inline int __must_check
 request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
 	    const char *name, void *dev)
 {
-	return request_threaded_irq(irq, handler, NULL, flags, name, dev);
+	return request_threaded_irq(irq, handler, NULL, flags | IRQF_COND_ONESHOT, name, dev);
 }
 
 extern int __must_check
@@ -175,7 +183,7 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler,
 extern int __must_check
 __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		     unsigned long flags, const char *devname,
-		     void __percpu *percpu_dev_id);
+		     const cpumask_t *affinity, void __percpu *percpu_dev_id);
 
 extern int __must_check
 request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags,
@@ -186,12 +194,21 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler,
 		   const char *devname, void __percpu *percpu_dev_id)
 {
 	return __request_percpu_irq(irq, handler, 0,
-				    devname, percpu_dev_id);
+				    devname, NULL, percpu_dev_id);
+}
+
+static inline int __must_check
+request_percpu_irq_affinity(unsigned int irq, irq_handler_t handler,
+			    const char *devname, const cpumask_t *affinity,
+			    void __percpu *percpu_dev_id)
+{
+	return __request_percpu_irq(irq, handler, 0,
+				    devname, affinity, percpu_dev_id);
 }
 
 extern int __must_check
-request_percpu_nmi(unsigned int irq, irq_handler_t handler,
-		   const char *devname, void __percpu *dev);
+request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name,
+		   const struct cpumask *affinity, void __percpu *dev_id);
 
 extern const void *free_irq(unsigned int, void *);
 extern void free_percpu_irq(unsigned int, void __percpu *);
@@ -232,6 +249,9 @@ extern void enable_percpu_irq(unsigned int irq, unsigned int type);
 extern bool irq_percpu_is_enabled(unsigned int irq);
 extern void irq_wake_thread(unsigned int irq, void *dev_id);
 
+DEFINE_LOCK_GUARD_1(disable_irq, int,
+		    disable_irq(*_T->lock), enable_irq(*_T->lock))
+
 extern void disable_nmi_nosync(unsigned int irq);
 extern void disable_percpu_nmi(unsigned int irq);
 extern void enable_nmi(unsigned int irq);
@@ -269,7 +289,7 @@ struct irq_affinity_notify {
 #define	IRQ_AFFINITY_MAX_SETS  4
 
 /**
- * struct irq_affinity - Description for automatic irq affinity assignements
+ * struct irq_affinity - Description for automatic irq affinity assignments
  * @pre_vectors:	Don't apply affinity to @pre_vectors at beginning of
  *			the MSI(-X) vector space
  * @post_vectors:	Don't apply affinity to @post_vectors at end of
@@ -441,7 +461,7 @@ irq_calc_affinity_vectors(unsigned int minvec, unsigned int maxvec,
 static inline void disable_irq_nosync_lockdep(unsigned int irq)
 {
 	disable_irq_nosync(irq);
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_disable();
 #endif
 }
@@ -449,22 +469,14 @@ static inline void disable_irq_nosync_lockdep(unsigned int irq)
 static inline void disable_irq_nosync_lockdep_irqsave(unsigned int irq, unsigned long *flags)
 {
 	disable_irq_nosync(irq);
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_save(*flags);
 #endif
 }
 
-static inline void disable_irq_lockdep(unsigned int irq)
-{
-	disable_irq(irq);
-#ifdef CONFIG_LOCKDEP
-	local_irq_disable();
-#endif
-}
-
 static inline void enable_irq_lockdep(unsigned int irq)
 {
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_enable();
 #endif
 	enable_irq(irq);
@@ -472,7 +484,7 @@ static inline void enable_irq_lockdep(unsigned int irq)
 
 static inline void enable_irq_lockdep_irqrestore(unsigned int irq, unsigned long *flags)
 {
-#ifdef CONFIG_LOCKDEP
+#if defined(CONFIG_LOCKDEP) && !defined(CONFIG_PREEMPT_RT)
 	local_irq_restore(*flags);
 #endif
 	enable_irq(irq);
@@ -566,11 +578,15 @@ enum
  *
  * _ RCU:
  * 	1) rcutree_migrate_callbacks() migrates the queue.
- * 	2) rcu_report_dead() reports the final quiescent states.
+ * 	2) rcutree_report_cpu_dead() reports the final quiescent states.
  *
  * _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue
+ *
+ * _ (HR)TIMER_SOFTIRQ: (hr)timers_dead_cpu() migrates the queue
  */
-#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ))
+#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(TIMER_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ) |\
+				   BIT(HRTIMER_SOFTIRQ) | BIT(RCU_SOFTIRQ))
+
 
 /* map softirq index to softirq name. update 'softirq_to_name' in
  * kernel/softirq.c when adding a new softirq.
@@ -583,7 +599,7 @@ extern const char * const softirq_to_name[NR_SOFTIRQS];
 
 struct softirq_action
 {
-	void	(*action)(struct softirq_action *);
+	void	(*action)(void);
 };
 
 asmlinkage void do_softirq(void);
@@ -598,13 +614,60 @@ static inline void do_softirq_post_smp_call_flush(unsigned int unused)
 }
 #endif
 
-extern void open_softirq(int nr, void (*action)(struct softirq_action *));
+extern void open_softirq(int nr, void (*action)(void));
 extern void softirq_init(void);
 extern void __raise_softirq_irqoff(unsigned int nr);
 
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 
+/*
+ * With forced-threaded interrupts enabled a raised softirq is deferred to
+ * ksoftirqd unless it can be handled within the threaded interrupt. This
+ * affects timer_list timers and hrtimers which are explicitly marked with
+ * HRTIMER_MODE_SOFT.
+ * With PREEMPT_RT enabled more hrtimers are moved to softirq for processing
+ * which includes all timers which are not explicitly marked HRTIMER_MODE_HARD.
+ * Userspace controlled timers (like the clock_nanosleep() interface) is divided
+ * into two categories: Tasks with elevated scheduling policy including
+ * SCHED_{FIFO|RR|DL} and the remaining scheduling policy. The tasks with the
+ * elevated scheduling policy are woken up directly from the HARDIRQ while all
+ * other wake ups are delayed to softirq and so to ksoftirqd.
+ *
+ * The ksoftirqd runs at SCHED_OTHER policy at which it should remain since it
+ * handles the softirq in an overloaded situation (not handled everything
+ * within its last run).
+ * If the timers are handled at SCHED_OTHER priority then they competes with all
+ * other SCHED_OTHER tasks for CPU resources are possibly delayed.
+ * Moving timers softirqs to a low priority SCHED_FIFO thread instead ensures
+ * that timer are performed before scheduling any SCHED_OTHER thread.
+ */
+DECLARE_PER_CPU(struct task_struct *, ktimerd);
+DECLARE_PER_CPU(unsigned long, pending_timer_softirq);
+void raise_ktimers_thread(unsigned int nr);
+
+static inline unsigned int local_timers_pending_force_th(void)
+{
+	return __this_cpu_read(pending_timer_softirq);
+}
+
+static inline void raise_timer_softirq(unsigned int nr)
+{
+	lockdep_assert_in_irq();
+	if (force_irqthreads())
+		raise_ktimers_thread(nr);
+	else
+		__raise_softirq_irqoff(nr);
+}
+
+static inline unsigned int local_timers_pending(void)
+{
+	if (force_irqthreads())
+		return local_timers_pending_force_th();
+	else
+		return local_softirq_pending();
+}
+
 DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
 
 static inline struct task_struct *this_cpu_ksoftirqd(void)
diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h
index 2b8026a39906..9d5791e9f737 100644
--- a/include/linux/interval_tree.h
+++ b/include/linux/interval_tree.h
@@ -20,6 +20,10 @@ interval_tree_remove(struct interval_tree_node *node,
 		     struct rb_root_cached *root);
 
 extern struct interval_tree_node *
+interval_tree_subtree_search(struct interval_tree_node *node,
+			     unsigned long start, unsigned long last);
+
+extern struct interval_tree_node *
 interval_tree_iter_first(struct rb_root_cached *root,
 			 unsigned long start, unsigned long last);
 
diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h
index aaa8a0767aa3..c5a2fed49eb0 100644
--- a/include/linux/interval_tree_generic.h
+++ b/include/linux/interval_tree_generic.h
@@ -77,7 +77,7 @@ ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node,			      \
  *   Cond2: start <= ITLAST(node)					      \
  */									      \
 									      \
-static ITSTRUCT *							      \
+ITSTATIC ITSTRUCT *							      \
 ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last)	      \
 {									      \
 	while (true) {							      \
@@ -104,12 +104,8 @@ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last)	      \
 		if (ITSTART(node) <= last) {		/* Cond1 */	      \
 			if (start <= ITLAST(node))	/* Cond2 */	      \
 				return node;	/* node is leftmost match */  \
-			if (node->ITRB.rb_right) {			      \
-				node = rb_entry(node->ITRB.rb_right,	      \
-						ITSTRUCT, ITRB);	      \
-				if (start <= node->ITSUBTREE)		      \
-					continue;			      \
-			}						      \
+			node = rb_entry(node->ITRB.rb_right, ITSTRUCT, ITRB); \
+			continue;					      \
 		}							      \
 		return NULL;	/* No match */				      \
 	}								      \
diff --git a/include/linux/io-64-nonatomic-hi-lo.h b/include/linux/io-64-nonatomic-hi-lo.h
index f32522bb3aa5..d3eade7cf663 100644
--- a/include/linux/io-64-nonatomic-hi-lo.h
+++ b/include/linux/io-64-nonatomic-hi-lo.h
@@ -101,22 +101,38 @@ static inline void iowrite64be_hi_lo(u64 val, void __iomem *addr)
 
 #ifndef ioread64
 #define ioread64_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define ioread64 __ioread64_hi_lo
+#else
 #define ioread64 ioread64_hi_lo
 #endif
+#endif
 
 #ifndef iowrite64
 #define iowrite64_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define iowrite64 __iowrite64_hi_lo
+#else
 #define iowrite64 iowrite64_hi_lo
 #endif
+#endif
 
 #ifndef ioread64be
 #define ioread64be_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define ioread64be __ioread64be_hi_lo
+#else
 #define ioread64be ioread64be_hi_lo
 #endif
+#endif
 
 #ifndef iowrite64be
 #define iowrite64be_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define iowrite64be __iowrite64be_hi_lo
+#else
 #define iowrite64be iowrite64be_hi_lo
 #endif
+#endif
 
 #endif	/* _LINUX_IO_64_NONATOMIC_HI_LO_H_ */
diff --git a/include/linux/io-64-nonatomic-lo-hi.h b/include/linux/io-64-nonatomic-lo-hi.h
index 448a21435dba..94e676ec3d3f 100644
--- a/include/linux/io-64-nonatomic-lo-hi.h
+++ b/include/linux/io-64-nonatomic-lo-hi.h
@@ -101,22 +101,38 @@ static inline void iowrite64be_lo_hi(u64 val, void __iomem *addr)
 
 #ifndef ioread64
 #define ioread64_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define ioread64 __ioread64_lo_hi
+#else
 #define ioread64 ioread64_lo_hi
 #endif
+#endif
 
 #ifndef iowrite64
 #define iowrite64_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define iowrite64 __iowrite64_lo_hi
+#else
 #define iowrite64 iowrite64_lo_hi
 #endif
+#endif
 
 #ifndef ioread64be
 #define ioread64be_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define ioread64be __ioread64be_lo_hi
+#else
 #define ioread64be ioread64be_lo_hi
 #endif
+#endif
 
 #ifndef iowrite64be
 #define iowrite64be_is_nonatomic
+#if defined(CONFIG_GENERIC_IOMAP) && defined(CONFIG_64BIT)
+#define iowrite64be __iowrite64be_lo_hi
+#else
 #define iowrite64be iowrite64be_lo_hi
 #endif
+#endif
 
 #endif	/* _LINUX_IO_64_NONATOMIC_LO_HI_H_ */
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 7376c1df9c90..c16353cc6e3c 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -225,7 +225,4 @@ io_mapping_free(struct io_mapping *iomap)
 	kfree(iomap);
 }
 
-int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pfn, unsigned long size);
-
 #endif /* _LINUX_IO_MAPPING_H */
diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h
index 1b7a44b35616..7a1516011ccf 100644
--- a/include/linux/io-pgtable.h
+++ b/include/linux/io-pgtable.h
@@ -15,8 +15,6 @@ enum io_pgtable_fmt {
 	ARM_64_LPAE_S2,
 	ARM_V7S,
 	ARM_MALI_LPAE,
-	AMD_IOMMU_V1,
-	AMD_IOMMU_V2,
 	APPLE_DART,
 	APPLE_DART2,
 	IO_PGTABLE_NUM_FMTS,
@@ -85,6 +83,16 @@ struct io_pgtable_cfg {
 	 *
 	 * IO_PGTABLE_QUIRK_ARM_OUTER_WBWA: Override the outer-cacheability
 	 *	attributes set in the TCR for a non-coherent page-table walker.
+	 *
+	 * IO_PGTABLE_QUIRK_ARM_HD: Enables dirty tracking in stage 1 pagetable.
+	 * IO_PGTABLE_QUIRK_ARM_S2FWB: Use the FWB format for the MemAttrs bits
+	 *
+	 * IO_PGTABLE_QUIRK_NO_WARN: Do not WARN_ON() on conflicting
+	 *	mappings, but silently return -EEXISTS.  Normally an attempt
+	 *	to map over an existing mapping would indicate some sort of
+	 *	kernel bug, which would justify the WARN_ON().  But for GPU
+	 *	drivers, this could be under control of userspace.  Which
+	 *	deserves an error return, but not to spam dmesg.
 	 */
 	#define IO_PGTABLE_QUIRK_ARM_NS			BIT(0)
 	#define IO_PGTABLE_QUIRK_NO_PERMS		BIT(1)
@@ -92,6 +100,9 @@ struct io_pgtable_cfg {
 	#define IO_PGTABLE_QUIRK_ARM_MTK_TTBR_EXT	BIT(4)
 	#define IO_PGTABLE_QUIRK_ARM_TTBR1		BIT(5)
 	#define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA		BIT(6)
+	#define IO_PGTABLE_QUIRK_ARM_HD			BIT(7)
+	#define IO_PGTABLE_QUIRK_ARM_S2FWB		BIT(8)
+	#define IO_PGTABLE_QUIRK_NO_WARN		BIT(9)
 	unsigned long			quirks;
 	unsigned long			pgsize_bitmap;
 	unsigned int			ias;
@@ -100,6 +111,30 @@ struct io_pgtable_cfg {
 	const struct iommu_flush_ops	*tlb;
 	struct device			*iommu_dev;
 
+	/**
+	 * @alloc: Custom page allocator.
+	 *
+	 * Optional hook used to allocate page tables. If this function is NULL,
+	 * @free must be NULL too.
+	 *
+	 * Memory returned should be zeroed and suitable for dma_map_single() and
+	 * virt_to_phys().
+	 *
+	 * Not all formats support custom page allocators. Before considering
+	 * passing a non-NULL value, make sure the chosen page format supports
+	 * this feature.
+	 */
+	void *(*alloc)(void *cookie, size_t size, gfp_t gfp);
+
+	/**
+	 * @free: Custom page de-allocator.
+	 *
+	 * Optional hook used to free page tables allocated with the @alloc
+	 * hook. Must be non-NULL if @alloc is not NULL, must be NULL
+	 * otherwise.
+	 */
+	void (*free)(void *cookie, void *pages, size_t size);
+
 	/* Low-level data specific to the table format */
 	union {
 		struct {
@@ -143,16 +178,31 @@ struct io_pgtable_cfg {
 		struct {
 			u64 ttbr[4];
 			u32 n_ttbrs;
+			u32 n_levels;
 		} apple_dart_cfg;
+
+		struct {
+			int nid;
+		} amd;
 	};
 };
 
 /**
+ * struct arm_lpae_io_pgtable_walk_data - information from a pgtable walk
+ *
+ * @ptes:     The recorded PTE values from the walk
+ */
+struct arm_lpae_io_pgtable_walk_data {
+	u64 ptes[4];
+};
+
+/**
  * struct io_pgtable_ops - Page table manipulation API for IOMMU drivers.
  *
  * @map_pages:    Map a physically contiguous range of pages of the same size.
  * @unmap_pages:  Unmap a range of virtually contiguous pages of the same size.
  * @iova_to_phys: Translate iova to physical address.
+ * @pgtable_walk: (optional) Perform a page table walk for a given iova.
  *
  * These functions map directly onto the iommu_ops member functions with
  * the same names.
@@ -166,6 +216,11 @@ struct io_pgtable_ops {
 			      struct iommu_iotlb_gather *gather);
 	phys_addr_t (*iova_to_phys)(struct io_pgtable_ops *ops,
 				    unsigned long iova);
+	int (*pgtable_walk)(struct io_pgtable_ops *ops, unsigned long iova, void *wd);
+	int (*read_and_clear_dirty)(struct io_pgtable_ops *ops,
+				    unsigned long iova, size_t size,
+				    unsigned long flags,
+				    struct iommu_dirty_bitmap *dirty);
 };
 
 /**
@@ -238,15 +293,25 @@ io_pgtable_tlb_add_page(struct io_pgtable *iop,
 }
 
 /**
+ * enum io_pgtable_caps - IO page table backend capabilities.
+ */
+enum io_pgtable_caps {
+	/** @IO_PGTABLE_CAP_CUSTOM_ALLOCATOR: Backend accepts custom page table allocators. */
+	IO_PGTABLE_CAP_CUSTOM_ALLOCATOR = BIT(0),
+};
+
+/**
  * struct io_pgtable_init_fns - Alloc/free a set of page tables for a
  *                              particular format.
  *
  * @alloc: Allocate a set of page tables described by cfg.
  * @free:  Free the page tables associated with iop.
+ * @caps:  Combination of @io_pgtable_caps flags encoding the backend capabilities.
  */
 struct io_pgtable_init_fns {
 	struct io_pgtable *(*alloc)(struct io_pgtable_cfg *cfg, void *cookie);
 	void (*free)(struct io_pgtable *iop);
+	u32 caps;
 };
 
 extern struct io_pgtable_init_fns io_pgtable_arm_32_lpae_s1_init_fns;
diff --git a/include/linux/io.h b/include/linux/io.h
index 308f4f0cfb93..0642c7ee41db 100644
--- a/include/linux/io.h
+++ b/include/linux/io.h
@@ -6,29 +6,40 @@
 #ifndef _LINUX_IO_H
 #define _LINUX_IO_H
 
+#include <linux/sizes.h>
 #include <linux/types.h>
 #include <linux/init.h>
-#include <linux/bug.h>
-#include <linux/err.h>
 #include <asm/io.h>
 #include <asm/page.h>
 
 struct device;
-struct resource;
 
-__visible void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
+#ifndef __iowrite32_copy
+void __iowrite32_copy(void __iomem *to, const void *from, size_t count);
+#endif
+
 void __ioread32_copy(void *to, const void __iomem *from, size_t count);
+
+#ifndef __iowrite64_copy
 void __iowrite64_copy(void __iomem *to, const void *from, size_t count);
+#endif
 
 #ifdef CONFIG_MMU
 int ioremap_page_range(unsigned long addr, unsigned long end,
 		       phys_addr_t phys_addr, pgprot_t prot);
+int vmap_page_range(unsigned long addr, unsigned long end,
+		    phys_addr_t phys_addr, pgprot_t prot);
 #else
 static inline int ioremap_page_range(unsigned long addr, unsigned long end,
 				     phys_addr_t phys_addr, pgprot_t prot)
 {
 	return 0;
 }
+static inline int vmap_page_range(unsigned long addr, unsigned long end,
+				  phys_addr_t phys_addr, pgprot_t prot)
+{
+	return 0;
+}
 #endif
 
 /*
@@ -51,8 +62,6 @@ static inline void devm_ioport_unmap(struct device *dev, void __iomem *addr)
 }
 #endif
 
-#define IOMEM_ERR_PTR(err) (__force void __iomem *)ERR_PTR(err)
-
 void __iomem *devm_ioremap(struct device *dev, resource_size_t offset,
 			   resource_size_t size);
 void __iomem *devm_ioremap_uc(struct device *dev, resource_size_t offset,
@@ -68,6 +77,11 @@ void *devm_memremap(struct device *dev, resource_size_t offset,
 		size_t size, unsigned long flags);
 void devm_memunmap(struct device *dev, void *addr);
 
+/* architectures can override this */
+pgprot_t __init early_memremap_pgprot_adjust(resource_size_t phys_addr,
+					unsigned long size, pgprot_t prot);
+
+
 #ifdef CONFIG_PCI
 /*
  * The PCI specifications (Rev 3.0, 3.2.5 "Transaction Ordering and
@@ -169,4 +183,25 @@ static inline void arch_io_free_memtype_wc(resource_size_t base,
 int devm_arch_io_reserve_memtype_wc(struct device *dev, resource_size_t start,
 				    resource_size_t size);
 
+#ifdef CONFIG_STRICT_DEVMEM
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	u64 from = ((u64)pfn) << PAGE_SHIFT;
+	u64 to = from + size;
+	u64 cursor = from;
+
+	while (cursor < to) {
+		if (!devmem_is_allowed(pfn))
+			return 0;
+		cursor += PAGE_SIZE;
+		pfn++;
+	}
+	return 1;
+}
+#else
+static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+{
+	return 1;
+}
+#endif
 #endif /* _LINUX_IO_H */
diff --git a/include/linux/io_uring.h b/include/linux/io_uring.h
index 7fe31b2cd02f..85fe4e6b275c 100644
--- a/include/linux/io_uring.h
+++ b/include/linux/io_uring.h
@@ -6,60 +6,17 @@
 #include <linux/xarray.h>
 #include <uapi/linux/io_uring.h>
 
-enum io_uring_cmd_flags {
-	IO_URING_F_COMPLETE_DEFER	= 1,
-	IO_URING_F_UNLOCKED		= 2,
-	/* the request is executed from poll, it should not be freed */
-	IO_URING_F_MULTISHOT		= 4,
-	/* executed by io-wq */
-	IO_URING_F_IOWQ			= 8,
-	/* int's last bit, sign checks are usually faster than a bit test */
-	IO_URING_F_NONBLOCK		= INT_MIN,
-
-	/* ctx state flags, for URING_CMD */
-	IO_URING_F_SQE128		= (1 << 8),
-	IO_URING_F_CQE32		= (1 << 9),
-	IO_URING_F_IOPOLL		= (1 << 10),
-};
-
-struct io_uring_cmd {
-	struct file	*file;
-	const struct io_uring_sqe *sqe;
-	union {
-		/* callback to defer completions to task context */
-		void (*task_work_cb)(struct io_uring_cmd *cmd, unsigned);
-		/* used for polled completion */
-		void *cookie;
-	};
-	u32		cmd_op;
-	u32		flags;
-	u8		pdu[32]; /* available inline for free use */
-};
-
-static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
-{
-	return sqe->cmd;
-}
-
 #if defined(CONFIG_IO_URING)
-int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd);
-void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret, ssize_t res2,
-			unsigned issue_flags);
-void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned));
-struct sock *io_uring_get_socket(struct file *file);
 void __io_uring_cancel(bool cancel_all);
 void __io_uring_free(struct task_struct *tsk);
 void io_uring_unreg_ringfd(void);
 const char *io_uring_get_opcode(u8 opcode);
+bool io_is_uring_fops(struct file *file);
 
 static inline void io_uring_files_cancel(void)
 {
-	if (current->io_uring) {
-		io_uring_unreg_ringfd();
+	if (current->io_uring)
 		__io_uring_cancel(false);
-	}
 }
 static inline void io_uring_task_cancel(void)
 {
@@ -72,23 +29,6 @@ static inline void io_uring_free(struct task_struct *tsk)
 		__io_uring_free(tsk);
 }
 #else
-static inline int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
-			      struct iov_iter *iter, void *ioucmd)
-{
-	return -EOPNOTSUPP;
-}
-static inline void io_uring_cmd_done(struct io_uring_cmd *cmd, ssize_t ret,
-		ssize_t ret2, unsigned issue_flags)
-{
-}
-static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
-			void (*task_work_cb)(struct io_uring_cmd *, unsigned))
-{
-}
-static inline struct sock *io_uring_get_socket(struct file *file)
-{
-	return NULL;
-}
 static inline void io_uring_task_cancel(void)
 {
 }
@@ -102,6 +42,10 @@ static inline const char *io_uring_get_opcode(u8 opcode)
 {
 	return "";
 }
+static inline bool io_is_uring_fops(struct file *file)
+{
+	return false;
+}
 #endif
 
 #endif
diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
new file mode 100644
index 000000000000..375fd048c4cb
--- /dev/null
+++ b/include/linux/io_uring/cmd.h
@@ -0,0 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_CMD_H
+#define _LINUX_IO_URING_CMD_H
+
+#include <uapi/linux/io_uring.h>
+#include <linux/io_uring_types.h>
+#include <linux/blk-mq.h>
+
+/* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
+#define IORING_URING_CMD_CANCELABLE	(1U << 30)
+/* io_uring_cmd is being issued again */
+#define IORING_URING_CMD_REISSUE	(1U << 31)
+
+struct io_uring_cmd {
+	struct file	*file;
+	const struct io_uring_sqe *sqe;
+	u32		cmd_op;
+	u32		flags;
+	u8		pdu[32]; /* available inline for free use */
+	u8		unused[8];
+};
+
+static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
+{
+	return sqe->cmd;
+}
+
+static inline void io_uring_cmd_private_sz_check(size_t cmd_sz)
+{
+	BUILD_BUG_ON(cmd_sz > sizeof_field(struct io_uring_cmd, pdu));
+}
+#define io_uring_cmd_to_pdu(cmd, pdu_type) ( \
+	io_uring_cmd_private_sz_check(sizeof(pdu_type)), \
+	((pdu_type *)&(cmd)->pdu) \
+)
+
+#if defined(CONFIG_IO_URING)
+int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			      struct iov_iter *iter,
+			      struct io_uring_cmd *ioucmd,
+			      unsigned int issue_flags);
+int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
+				  const struct iovec __user *uvec,
+				  size_t uvec_segs,
+				  int ddir, struct iov_iter *iter,
+				  unsigned issue_flags);
+
+/*
+ * Completes the request, i.e. posts an io_uring CQE and deallocates @ioucmd
+ * and the corresponding io_uring request.
+ *
+ * Note: the caller should never hard code @issue_flags and is only allowed
+ * to pass the mask provided by the core io_uring code.
+ */
+void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret, u64 res2,
+			 unsigned issue_flags, bool is_cqe32);
+
+void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    io_req_tw_func_t task_work_cb,
+			    unsigned flags);
+
+/*
+ * Note: the caller should never hard code @issue_flags and only use the
+ * mask provided by the core io_uring code.
+ */
+void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags);
+
+/* Execute the request from a blocking context */
+void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd);
+
+/*
+ * Select a buffer from the provided buffer group for multishot uring_cmd.
+ * Returns the selected buffer address and size.
+ */
+struct io_br_sel io_uring_cmd_buffer_select(struct io_uring_cmd *ioucmd,
+					    unsigned buf_group, size_t *len,
+					    unsigned int issue_flags);
+
+/*
+ * Complete a multishot uring_cmd event. This will post a CQE to the completion
+ * queue and update the provided buffer.
+ */
+bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
+				 struct io_br_sel *sel, unsigned int issue_flags);
+
+#else
+static inline int
+io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+			  struct iov_iter *iter, struct io_uring_cmd *ioucmd,
+			  unsigned int issue_flags)
+{
+	return -EOPNOTSUPP;
+}
+static inline int io_uring_cmd_import_fixed_vec(struct io_uring_cmd *ioucmd,
+						const struct iovec __user *uvec,
+						size_t uvec_segs,
+						int ddir, struct iov_iter *iter,
+						unsigned issue_flags)
+{
+	return -EOPNOTSUPP;
+}
+static inline void __io_uring_cmd_done(struct io_uring_cmd *cmd, s32 ret,
+		u64 ret2, unsigned issue_flags, bool is_cqe32)
+{
+}
+static inline void __io_uring_cmd_do_in_task(struct io_uring_cmd *ioucmd,
+			    io_req_tw_func_t task_work_cb, unsigned flags)
+{
+}
+static inline void io_uring_cmd_mark_cancelable(struct io_uring_cmd *cmd,
+		unsigned int issue_flags)
+{
+}
+static inline void io_uring_cmd_issue_blocking(struct io_uring_cmd *ioucmd)
+{
+}
+static inline struct io_br_sel
+io_uring_cmd_buffer_select(struct io_uring_cmd *ioucmd, unsigned buf_group,
+			   size_t *len, unsigned int issue_flags)
+{
+	return (struct io_br_sel) { .val = -EOPNOTSUPP };
+}
+static inline bool io_uring_mshot_cmd_post_cqe(struct io_uring_cmd *ioucmd,
+				struct io_br_sel *sel, unsigned int issue_flags)
+{
+	return true;
+}
+#endif
+
+static inline struct io_uring_cmd *io_uring_cmd_from_tw(struct io_tw_req tw_req)
+{
+	return io_kiocb_to_cmd(tw_req.req, struct io_uring_cmd);
+}
+
+/* task_work executor checks the deferred list completion */
+#define IO_URING_CMD_TASK_WORK_ISSUE_FLAGS IO_URING_F_COMPLETE_DEFER
+
+/* users must follow the IOU_F_TWQ_LAZY_WAKE semantics */
+static inline void io_uring_cmd_do_in_task_lazy(struct io_uring_cmd *ioucmd,
+			io_req_tw_func_t task_work_cb)
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, IOU_F_TWQ_LAZY_WAKE);
+}
+
+static inline void io_uring_cmd_complete_in_task(struct io_uring_cmd *ioucmd,
+			io_req_tw_func_t task_work_cb)
+{
+	__io_uring_cmd_do_in_task(ioucmd, task_work_cb, 0);
+}
+
+static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->tctx->task;
+}
+
+/*
+ * Return uring_cmd's context reference as its context handle for driver to
+ * track per-context resource, such as registered kernel IO buffer
+ */
+static inline void *io_uring_cmd_ctx_handle(struct io_uring_cmd *cmd)
+{
+	return cmd_to_io_kiocb(cmd)->ctx;
+}
+
+static inline void io_uring_cmd_done(struct io_uring_cmd *ioucmd, s32 ret,
+				     unsigned issue_flags)
+{
+	return __io_uring_cmd_done(ioucmd, ret, 0, issue_flags, false);
+}
+
+static inline void io_uring_cmd_done32(struct io_uring_cmd *ioucmd, s32 ret,
+				       u64 res2, unsigned issue_flags)
+{
+	return __io_uring_cmd_done(ioucmd, ret, res2, issue_flags, true);
+}
+
+int io_buffer_register_bvec(struct io_uring_cmd *cmd, struct request *rq,
+			    void (*release)(void *), unsigned int index,
+			    unsigned int issue_flags);
+int io_buffer_unregister_bvec(struct io_uring_cmd *cmd, unsigned int index,
+			      unsigned int issue_flags);
+
+#endif /* _LINUX_IO_URING_CMD_H */
diff --git a/include/linux/io_uring/net.h b/include/linux/io_uring/net.h
new file mode 100644
index 000000000000..b58f39fed4d5
--- /dev/null
+++ b/include/linux/io_uring/net.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_IO_URING_NET_H
+#define _LINUX_IO_URING_NET_H
+
+struct io_uring_cmd;
+
+#if defined(CONFIG_IO_URING)
+int io_uring_cmd_sock(struct io_uring_cmd *cmd, unsigned int issue_flags);
+
+#else
+static inline int io_uring_cmd_sock(struct io_uring_cmd *cmd,
+				    unsigned int issue_flags)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
+#endif
diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 1b2a20a42413..e1adb0d20a0a 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -2,11 +2,45 @@
 #define IO_URING_TYPES_H
 
 #include <linux/blkdev.h>
+#include <linux/hashtable.h>
 #include <linux/task_work.h>
 #include <linux/bitmap.h>
 #include <linux/llist.h>
 #include <uapi/linux/io_uring.h>
 
+enum {
+	/*
+	 * A hint to not wake right away but delay until there are enough of
+	 * tw's queued to match the number of CQEs the task is waiting for.
+	 *
+	 * Must not be used with requests generating more than one CQE.
+	 * It's also ignored unless IORING_SETUP_DEFER_TASKRUN is set.
+	 */
+	IOU_F_TWQ_LAZY_WAKE			= 1,
+};
+
+enum io_uring_cmd_flags {
+	IO_URING_F_COMPLETE_DEFER	= 1,
+	IO_URING_F_UNLOCKED		= 2,
+	/* the request is executed from poll, it should not be freed */
+	IO_URING_F_MULTISHOT		= 4,
+	/* executed by io-wq */
+	IO_URING_F_IOWQ			= 8,
+	/* executed inline from syscall */
+	IO_URING_F_INLINE		= 16,
+	/* int's last bit, sign checks are usually faster than a bit test */
+	IO_URING_F_NONBLOCK		= INT_MIN,
+
+	/* ctx state flags, for URING_CMD */
+	IO_URING_F_SQE128		= (1 << 8),
+	IO_URING_F_CQE32		= (1 << 9),
+	IO_URING_F_IOPOLL		= (1 << 10),
+
+	/* set when uring wants to cancel a previously issued command */
+	IO_URING_F_CANCEL		= (1 << 11),
+	IO_URING_F_COMPAT		= (1 << 12),
+};
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };
@@ -18,24 +52,23 @@ struct io_wq_work_list {
 
 struct io_wq_work {
 	struct io_wq_work_node list;
-	unsigned flags;
+	atomic_t flags;
 	/* place it here instead of io_kiocb as it fills padding and saves 4B */
 	int cancel_seq;
 };
 
-struct io_fixed_file {
-	/* file * with additional FFS_* flags */
-	unsigned long file_ptr;
+struct io_rsrc_data {
+	unsigned int			nr;
+	struct io_rsrc_node		**nodes;
 };
 
 struct io_file_table {
-	struct io_fixed_file *files;
+	struct io_rsrc_data data;
 	unsigned long *bitmap;
 	unsigned int alloc_hint;
 };
 
 struct io_hash_bucket {
-	spinlock_t		lock;
 	struct hlist_head	list;
 } ____cacheline_aligned_in_smp;
 
@@ -44,6 +77,32 @@ struct io_hash_table {
 	unsigned		hash_bits;
 };
 
+struct io_mapped_region {
+	struct page		**pages;
+	void			*ptr;
+	unsigned		nr_pages;
+	unsigned		flags;
+};
+
+/*
+ * Return value from io_buffer_list selection, to avoid stashing it in
+ * struct io_kiocb. For legacy/classic provided buffers, keeping a reference
+ * across execution contexts are fine. But for ring provided buffers, the
+ * list may go away as soon as ->uring_lock is dropped. As the io_kiocb
+ * persists, it's better to just keep the buffer local for those cases.
+ */
+struct io_br_sel {
+	struct io_buffer_list *buf_list;
+	/*
+	 * Some selection parts return the user address, others return an error.
+	 */
+	union {
+		void __user *addr;
+		ssize_t val;
+	};
+};
+
+
 /*
  * Arbitrary limit, can be raised if need be
  */
@@ -53,6 +112,7 @@ struct io_uring_task {
 	/* submission side */
 	int				cached_refs;
 	const struct io_ring_ctx 	*last;
+	struct task_struct		*task;
 	struct io_wq			*io_wq;
 	struct file			*registered_rings[IO_RINGFD_REG_MAX];
 
@@ -68,9 +128,17 @@ struct io_uring_task {
 	} ____cacheline_aligned_in_smp;
 };
 
+struct iou_vec {
+	union {
+		struct iovec	*iovec;
+		struct bio_vec	*bvec;
+	};
+	unsigned		nr; /* number of struct iovec it can hold */
+};
+
 struct io_uring {
-	u32 head ____cacheline_aligned_in_smp;
-	u32 tail ____cacheline_aligned_in_smp;
+	u32 head;
+	u32 tail;
 };
 
 /*
@@ -173,25 +241,17 @@ struct io_submit_state {
 
 	bool			plug_started;
 	bool			need_plug;
+	bool			cq_flush;
 	unsigned short		submit_nr;
-	unsigned int		cqes_count;
 	struct blk_plug		plug;
-	struct io_uring_cqe	cqes[16];
-};
-
-struct io_ev_fd {
-	struct eventfd_ctx	*cq_ev_fd;
-	unsigned int		eventfd_async: 1;
-	struct rcu_head		rcu;
-	atomic_t		refs;
-	atomic_t		ops;
 };
 
 struct io_alloc_cache {
-	struct io_wq_work_node	list;
+	void			**entries;
 	unsigned int		nr_cached;
 	unsigned int		max_cached;
-	size_t			elem_size;
+	unsigned int		elem_size;
+	unsigned int		init_clear;
 };
 
 struct io_ring_ctx {
@@ -205,15 +265,22 @@ struct io_ring_ctx {
 		unsigned int		has_evfd: 1;
 		/* all CQEs should be posted only by the submitter task */
 		unsigned int		task_complete: 1;
+		unsigned int		lockless_cq: 1;
 		unsigned int		syscall_iopoll: 1;
 		unsigned int		poll_activated: 1;
 		unsigned int		drain_disabled: 1;
 		unsigned int		compat: 1;
+		unsigned int		iowq_limits_set : 1;
+
+		struct task_struct	*submitter_task;
+		struct io_rings		*rings;
+		struct percpu_ref	refs;
+
+		clockid_t		clockid;
+		enum tk_offsets		clock_offset;
 
 		enum task_work_notify_mode	notify_method;
-		struct io_rings			*rings;
-		struct task_struct		*submitter_task;
-		struct percpu_ref		refs;
+		unsigned			sq_thread_idle;
 	} ____cacheline_aligned_in_smp;
 
 	/* submission data */
@@ -240,42 +307,48 @@ struct io_ring_ctx {
 		 * Fixed resources fast path, should be accessed only under
 		 * uring_lock, and updated through io_uring_register(2)
 		 */
-		struct io_rsrc_node	*rsrc_node;
 		atomic_t		cancel_seq;
+
+		/*
+		 * ->iopoll_list is protected by the ctx->uring_lock for
+		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
+		 * For SQPOLL, only the single threaded io_sq_thread() will
+		 * manipulate the list, hence no extra locking is needed there.
+		 */
+		bool			poll_multi_queue;
+		struct io_wq_work_list	iopoll_list;
+
 		struct io_file_table	file_table;
-		unsigned		nr_user_files;
-		unsigned		nr_user_bufs;
-		struct io_mapped_ubuf	**user_bufs;
+		struct io_rsrc_data	buf_table;
+		struct io_alloc_cache	node_cache;
+		struct io_alloc_cache	imu_cache;
 
 		struct io_submit_state	submit_state;
 
-		struct io_buffer_list	*io_bl;
+		/*
+		 * Modifications are protected by ->uring_lock and ->mmap_lock.
+		 * The buffer list's io mapped region should be stable once
+		 * published.
+		 */
 		struct xarray		io_bl_xa;
-		struct list_head	io_buffers_cache;
 
-		struct io_hash_table	cancel_table_locked;
-		struct list_head	cq_overflow_list;
+		struct io_hash_table	cancel_table;
 		struct io_alloc_cache	apoll_cache;
 		struct io_alloc_cache	netmsg_cache;
-	} ____cacheline_aligned_in_smp;
-
-	/* IRQ completion list, under ->completion_lock */
-	struct io_wq_work_list	locked_free_list;
-	unsigned int		locked_free_nr;
-
-	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
-	struct io_sq_data	*sq_data;	/* if using sq thread polling */
-
-	struct wait_queue_head	sqo_sq_wait;
-	struct list_head	sqd_list;
-
-	unsigned long		check_cq;
-
-	unsigned int		file_alloc_start;
-	unsigned int		file_alloc_end;
+		struct io_alloc_cache	rw_cache;
+		struct io_alloc_cache	cmd_cache;
 
-	struct xarray		personalities;
-	u32			pers_next;
+		/*
+		 * Any cancelable uring_cmd is added to this list in
+		 * ->uring_cmd() by io_uring_cmd_insert_cancelable()
+		 */
+		struct hlist_head	cancelable_uring_cmd;
+		/*
+		 * For Hybrid IOPOLL, runtime in hybrid polling, without
+		 * scheduling time
+		 */
+		u64					hybrid_poll_time;
+	} ____cacheline_aligned_in_smp;
 
 	struct {
 		/*
@@ -288,59 +361,62 @@ struct io_ring_ctx {
 		unsigned		cached_cq_tail;
 		unsigned		cq_entries;
 		struct io_ev_fd	__rcu	*io_ev_fd;
-		struct wait_queue_head	cq_wait;
-		unsigned		cq_extra;
+
+		void			*cq_wait_arg;
+		size_t			cq_wait_size;
 	} ____cacheline_aligned_in_smp;
 
+	/*
+	 * task_work and async notification delivery cacheline. Expected to
+	 * regularly bounce b/w CPUs.
+	 */
 	struct {
-		spinlock_t		completion_lock;
-
-		bool			poll_multi_queue;
-		atomic_t		cq_wait_nr;
-
-		/*
-		 * ->iopoll_list is protected by the ctx->uring_lock for
-		 * io_uring instances that don't use IORING_SETUP_SQPOLL.
-		 * For SQPOLL, only the single threaded io_sq_thread() will
-		 * manipulate the list, hence no extra locking is needed there.
-		 */
-		struct io_wq_work_list	iopoll_list;
-		struct io_hash_table	cancel_table;
-
 		struct llist_head	work_llist;
-
-		struct list_head	io_buffers_comp;
+		struct llist_head	retry_llist;
+		unsigned long		check_cq;
+		atomic_t		cq_wait_nr;
+		atomic_t		cq_timeouts;
+		struct wait_queue_head	cq_wait;
 	} ____cacheline_aligned_in_smp;
 
 	/* timeouts */
 	struct {
-		spinlock_t		timeout_lock;
-		atomic_t		cq_timeouts;
+		raw_spinlock_t		timeout_lock;
 		struct list_head	timeout_list;
 		struct list_head	ltimeout_list;
 		unsigned		cq_last_tm_flush;
 	} ____cacheline_aligned_in_smp;
 
+	spinlock_t		completion_lock;
+
+	struct list_head	cq_overflow_list;
+
+	struct hlist_head	waitid_list;
+
+#ifdef CONFIG_FUTEX
+	struct hlist_head	futex_list;
+	struct io_alloc_cache	futex_cache;
+#endif
+
+	const struct cred	*sq_creds;	/* cred used for __io_sq_thread() */
+	struct io_sq_data	*sq_data;	/* if using sq thread polling */
+
+	struct wait_queue_head	sqo_sq_wait;
+	struct list_head	sqd_list;
+
+	unsigned int		file_alloc_start;
+	unsigned int		file_alloc_end;
+
 	/* Keep this last, we don't need it for the fast path */
 	struct wait_queue_head		poll_wq;
 	struct io_restriction		restrictions;
 
-	/* slow path rsrc auxilary data, used by update/register */
-	struct io_mapped_ubuf		*dummy_ubuf;
-	struct io_rsrc_data		*file_data;
-	struct io_rsrc_data		*buf_data;
+	/* Stores zcrx object pointers of type struct io_zcrx_ifq */
+	struct xarray			zcrx_ctxs;
 
-	/* protected by ->uring_lock */
-	struct list_head		rsrc_ref_list;
-	struct io_alloc_cache		rsrc_node_cache;
-	struct wait_queue_head		rsrc_quiesce_wq;
-	unsigned			rsrc_quiesce;
-
-	struct list_head		io_buffers_pages;
+	u32			pers_next;
+	struct xarray		personalities;
 
-	#if defined(CONFIG_UNIX)
-		struct socket		*ring_sock;
-	#endif
 	/* hashed buffered write serialization */
 	struct io_wq_hash		*hash_map;
 
@@ -357,19 +433,50 @@ struct io_ring_ctx {
 
 	/* io-wq management, e.g. thread count */
 	u32				iowq_limits[2];
-	bool				iowq_limits_set;
 
 	struct callback_head		poll_wq_task_work;
 	struct list_head		defer_list;
-	unsigned			sq_thread_idle;
+	unsigned			nr_drained;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct list_head	napi_list;	/* track busy poll napi_id */
+	spinlock_t		napi_lock;	/* napi_list lock */
+
+	/* napi busy poll default timeout */
+	ktime_t			napi_busy_poll_dt;
+	bool			napi_prefer_busy_poll;
+	u8			napi_track_mode;
+
+	DECLARE_HASHTABLE(napi_ht, 4);
+#endif
+
 	/* protected by ->completion_lock */
 	unsigned			evfd_last_cq_tail;
+	unsigned			nr_req_allocated;
+
+	/*
+	 * Protection for resize vs mmap races - both the mmap and resize
+	 * side will need to grab this lock, to prevent either side from
+	 * being run concurrently with the other.
+	 */
+	struct mutex			mmap_lock;
+
+	struct io_mapped_region		sq_region;
+	struct io_mapped_region		ring_region;
+	/* used for optimised request parameter and wait argument passing  */
+	struct io_mapped_region		param_region;
 };
 
+/*
+ * Token indicating function is called in task work context:
+ * ctx->uring_lock is held and any completions generated will be flushed.
+ * ONLY core io_uring.c should instantiate this struct.
+ */
 struct io_tw_state {
-	/* ->uring_lock is taken, callbacks can use io_tw_lock to lock it */
-	bool locked;
+	bool cancel;
 };
+/* Alias to use in code that doesn't instantiate struct io_tw_state */
+typedef struct io_tw_state io_tw_token_t;
 
 enum {
 	REQ_F_FIXED_FILE_BIT	= IOSQE_FIXED_FILE_BIT,
@@ -388,6 +495,7 @@ enum {
 	REQ_F_LINK_TIMEOUT_BIT,
 	REQ_F_NEED_CLEANUP_BIT,
 	REQ_F_POLLED_BIT,
+	REQ_F_HYBRID_IOPOLL_STATE_BIT,
 	REQ_F_BUFFER_SELECTED_BIT,
 	REQ_F_BUFFER_RING_BIT,
 	REQ_F_REISSUE_BIT,
@@ -398,86 +506,119 @@ enum {
 	REQ_F_SKIP_LINK_CQES_BIT,
 	REQ_F_SINGLE_POLL_BIT,
 	REQ_F_DOUBLE_POLL_BIT,
-	REQ_F_PARTIAL_IO_BIT,
-	REQ_F_CQE32_INIT_BIT,
+	REQ_F_MULTISHOT_BIT,
 	REQ_F_APOLL_MULTISHOT_BIT,
 	REQ_F_CLEAR_POLLIN_BIT,
-	REQ_F_HASH_LOCKED_BIT,
 	/* keep async read/write and isreg together and in order */
 	REQ_F_SUPPORT_NOWAIT_BIT,
 	REQ_F_ISREG_BIT,
+	REQ_F_POLL_NO_LAZY_BIT,
+	REQ_F_CAN_POLL_BIT,
+	REQ_F_BL_EMPTY_BIT,
+	REQ_F_BL_NO_RECYCLE_BIT,
+	REQ_F_BUFFERS_COMMIT_BIT,
+	REQ_F_BUF_NODE_BIT,
+	REQ_F_HAS_METADATA_BIT,
+	REQ_F_IMPORT_BUFFER_BIT,
+	REQ_F_SQE_COPIED_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
 };
 
+typedef u64 __bitwise io_req_flags_t;
+#define IO_REQ_FLAG(bitno)	((__force io_req_flags_t) BIT_ULL((bitno)))
+
 enum {
 	/* ctx owns file */
-	REQ_F_FIXED_FILE	= BIT(REQ_F_FIXED_FILE_BIT),
+	REQ_F_FIXED_FILE	= IO_REQ_FLAG(REQ_F_FIXED_FILE_BIT),
 	/* drain existing IO first */
-	REQ_F_IO_DRAIN		= BIT(REQ_F_IO_DRAIN_BIT),
+	REQ_F_IO_DRAIN		= IO_REQ_FLAG(REQ_F_IO_DRAIN_BIT),
 	/* linked sqes */
-	REQ_F_LINK		= BIT(REQ_F_LINK_BIT),
+	REQ_F_LINK		= IO_REQ_FLAG(REQ_F_LINK_BIT),
 	/* doesn't sever on completion < 0 */
-	REQ_F_HARDLINK		= BIT(REQ_F_HARDLINK_BIT),
+	REQ_F_HARDLINK		= IO_REQ_FLAG(REQ_F_HARDLINK_BIT),
 	/* IOSQE_ASYNC */
-	REQ_F_FORCE_ASYNC	= BIT(REQ_F_FORCE_ASYNC_BIT),
+	REQ_F_FORCE_ASYNC	= IO_REQ_FLAG(REQ_F_FORCE_ASYNC_BIT),
 	/* IOSQE_BUFFER_SELECT */
-	REQ_F_BUFFER_SELECT	= BIT(REQ_F_BUFFER_SELECT_BIT),
+	REQ_F_BUFFER_SELECT	= IO_REQ_FLAG(REQ_F_BUFFER_SELECT_BIT),
 	/* IOSQE_CQE_SKIP_SUCCESS */
-	REQ_F_CQE_SKIP		= BIT(REQ_F_CQE_SKIP_BIT),
+	REQ_F_CQE_SKIP		= IO_REQ_FLAG(REQ_F_CQE_SKIP_BIT),
 
 	/* fail rest of links */
-	REQ_F_FAIL		= BIT(REQ_F_FAIL_BIT),
+	REQ_F_FAIL		= IO_REQ_FLAG(REQ_F_FAIL_BIT),
 	/* on inflight list, should be cancelled and waited on exit reliably */
-	REQ_F_INFLIGHT		= BIT(REQ_F_INFLIGHT_BIT),
+	REQ_F_INFLIGHT		= IO_REQ_FLAG(REQ_F_INFLIGHT_BIT),
 	/* read/write uses file position */
-	REQ_F_CUR_POS		= BIT(REQ_F_CUR_POS_BIT),
+	REQ_F_CUR_POS		= IO_REQ_FLAG(REQ_F_CUR_POS_BIT),
 	/* must not punt to workers */
-	REQ_F_NOWAIT		= BIT(REQ_F_NOWAIT_BIT),
+	REQ_F_NOWAIT		= IO_REQ_FLAG(REQ_F_NOWAIT_BIT),
 	/* has or had linked timeout */
-	REQ_F_LINK_TIMEOUT	= BIT(REQ_F_LINK_TIMEOUT_BIT),
+	REQ_F_LINK_TIMEOUT	= IO_REQ_FLAG(REQ_F_LINK_TIMEOUT_BIT),
 	/* needs cleanup */
-	REQ_F_NEED_CLEANUP	= BIT(REQ_F_NEED_CLEANUP_BIT),
+	REQ_F_NEED_CLEANUP	= IO_REQ_FLAG(REQ_F_NEED_CLEANUP_BIT),
 	/* already went through poll handler */
-	REQ_F_POLLED		= BIT(REQ_F_POLLED_BIT),
+	REQ_F_POLLED		= IO_REQ_FLAG(REQ_F_POLLED_BIT),
+	/* every req only blocks once in hybrid poll */
+	REQ_F_IOPOLL_STATE        = IO_REQ_FLAG(REQ_F_HYBRID_IOPOLL_STATE_BIT),
 	/* buffer already selected */
-	REQ_F_BUFFER_SELECTED	= BIT(REQ_F_BUFFER_SELECTED_BIT),
+	REQ_F_BUFFER_SELECTED	= IO_REQ_FLAG(REQ_F_BUFFER_SELECTED_BIT),
 	/* buffer selected from ring, needs commit */
-	REQ_F_BUFFER_RING	= BIT(REQ_F_BUFFER_RING_BIT),
+	REQ_F_BUFFER_RING	= IO_REQ_FLAG(REQ_F_BUFFER_RING_BIT),
 	/* caller should reissue async */
-	REQ_F_REISSUE		= BIT(REQ_F_REISSUE_BIT),
+	REQ_F_REISSUE		= IO_REQ_FLAG(REQ_F_REISSUE_BIT),
 	/* supports async reads/writes */
-	REQ_F_SUPPORT_NOWAIT	= BIT(REQ_F_SUPPORT_NOWAIT_BIT),
+	REQ_F_SUPPORT_NOWAIT	= IO_REQ_FLAG(REQ_F_SUPPORT_NOWAIT_BIT),
 	/* regular file */
-	REQ_F_ISREG		= BIT(REQ_F_ISREG_BIT),
+	REQ_F_ISREG		= IO_REQ_FLAG(REQ_F_ISREG_BIT),
 	/* has creds assigned */
-	REQ_F_CREDS		= BIT(REQ_F_CREDS_BIT),
+	REQ_F_CREDS		= IO_REQ_FLAG(REQ_F_CREDS_BIT),
 	/* skip refcounting if not set */
-	REQ_F_REFCOUNT		= BIT(REQ_F_REFCOUNT_BIT),
+	REQ_F_REFCOUNT		= IO_REQ_FLAG(REQ_F_REFCOUNT_BIT),
 	/* there is a linked timeout that has to be armed */
-	REQ_F_ARM_LTIMEOUT	= BIT(REQ_F_ARM_LTIMEOUT_BIT),
+	REQ_F_ARM_LTIMEOUT	= IO_REQ_FLAG(REQ_F_ARM_LTIMEOUT_BIT),
 	/* ->async_data allocated */
-	REQ_F_ASYNC_DATA	= BIT(REQ_F_ASYNC_DATA_BIT),
+	REQ_F_ASYNC_DATA	= IO_REQ_FLAG(REQ_F_ASYNC_DATA_BIT),
 	/* don't post CQEs while failing linked requests */
-	REQ_F_SKIP_LINK_CQES	= BIT(REQ_F_SKIP_LINK_CQES_BIT),
+	REQ_F_SKIP_LINK_CQES	= IO_REQ_FLAG(REQ_F_SKIP_LINK_CQES_BIT),
 	/* single poll may be active */
-	REQ_F_SINGLE_POLL	= BIT(REQ_F_SINGLE_POLL_BIT),
+	REQ_F_SINGLE_POLL	= IO_REQ_FLAG(REQ_F_SINGLE_POLL_BIT),
 	/* double poll may active */
-	REQ_F_DOUBLE_POLL	= BIT(REQ_F_DOUBLE_POLL_BIT),
-	/* request has already done partial IO */
-	REQ_F_PARTIAL_IO	= BIT(REQ_F_PARTIAL_IO_BIT),
+	REQ_F_DOUBLE_POLL	= IO_REQ_FLAG(REQ_F_DOUBLE_POLL_BIT),
+	/* request posts multiple completions, should be set at prep time */
+	REQ_F_MULTISHOT		= IO_REQ_FLAG(REQ_F_MULTISHOT_BIT),
 	/* fast poll multishot mode */
-	REQ_F_APOLL_MULTISHOT	= BIT(REQ_F_APOLL_MULTISHOT_BIT),
-	/* ->extra1 and ->extra2 are initialised */
-	REQ_F_CQE32_INIT	= BIT(REQ_F_CQE32_INIT_BIT),
+	REQ_F_APOLL_MULTISHOT	= IO_REQ_FLAG(REQ_F_APOLL_MULTISHOT_BIT),
 	/* recvmsg special flag, clear EPOLLIN */
-	REQ_F_CLEAR_POLLIN	= BIT(REQ_F_CLEAR_POLLIN_BIT),
-	/* hashed into ->cancel_hash_locked, protected by ->uring_lock */
-	REQ_F_HASH_LOCKED	= BIT(REQ_F_HASH_LOCKED_BIT),
+	REQ_F_CLEAR_POLLIN	= IO_REQ_FLAG(REQ_F_CLEAR_POLLIN_BIT),
+	/* don't use lazy poll wake for this request */
+	REQ_F_POLL_NO_LAZY	= IO_REQ_FLAG(REQ_F_POLL_NO_LAZY_BIT),
+	/* file is pollable */
+	REQ_F_CAN_POLL		= IO_REQ_FLAG(REQ_F_CAN_POLL_BIT),
+	/* buffer list was empty after selection of buffer */
+	REQ_F_BL_EMPTY		= IO_REQ_FLAG(REQ_F_BL_EMPTY_BIT),
+	/* don't recycle provided buffers for this request */
+	REQ_F_BL_NO_RECYCLE	= IO_REQ_FLAG(REQ_F_BL_NO_RECYCLE_BIT),
+	/* buffer ring head needs incrementing on put */
+	REQ_F_BUFFERS_COMMIT	= IO_REQ_FLAG(REQ_F_BUFFERS_COMMIT_BIT),
+	/* buf node is valid */
+	REQ_F_BUF_NODE		= IO_REQ_FLAG(REQ_F_BUF_NODE_BIT),
+	/* request has read/write metadata assigned */
+	REQ_F_HAS_METADATA	= IO_REQ_FLAG(REQ_F_HAS_METADATA_BIT),
+	/*
+	 * For vectored fixed buffers, resolve iovec to registered buffers.
+	 * For SEND_ZC, whether to import buffers (i.e. the first issue).
+	 */
+	REQ_F_IMPORT_BUFFER	= IO_REQ_FLAG(REQ_F_IMPORT_BUFFER_BIT),
+	/* ->sqe_copy() has been called, if necessary */
+	REQ_F_SQE_COPIED	= IO_REQ_FLAG(REQ_F_SQE_COPIED_BIT),
+};
+
+struct io_tw_req {
+	struct io_kiocb *req;
 };
 
-typedef void (*io_req_tw_func_t)(struct io_kiocb *req, struct io_tw_state *ts);
+typedef void (*io_req_tw_func_t)(struct io_tw_req tw_req, io_tw_token_t tw);
 
 struct io_task_work {
 	struct llist_node		node;
@@ -512,7 +653,11 @@ static inline void io_kiocb_cmd_sz_check(size_t cmd_sz)
 	io_kiocb_cmd_sz_check(sizeof(cmd_type)) , \
 	((cmd_type *)&(req)->cmd) \
 )
-#define cmd_to_io_kiocb(ptr)	((struct io_kiocb *) ptr)
+
+static inline struct io_kiocb *cmd_to_io_kiocb(void *ptr)
+{
+	return ptr;
+}
 
 struct io_kiocb {
 	union {
@@ -531,31 +676,25 @@ struct io_kiocb {
 	u8				iopoll_completed;
 	/*
 	 * Can be either a fixed buffer index, or used with provided buffers.
-	 * For the latter, before issue it points to the buffer group ID,
-	 * and after selection it points to the buffer ID itself.
+	 * For the latter, it points to the selected buffer ID.
 	 */
 	u16				buf_index;
-	unsigned int			flags;
+
+	unsigned			nr_tw;
+
+	/* REQ_F_* flags */
+	io_req_flags_t			flags;
 
 	struct io_cqe			cqe;
 
 	struct io_ring_ctx		*ctx;
-	struct task_struct		*task;
-
-	struct io_rsrc_node		*rsrc_node;
+	struct io_uring_task		*tctx;
 
 	union {
-		/* store used ubuf, so we can prevent reloading */
-		struct io_mapped_ubuf	*imu;
-
 		/* stores selected buf, valid IFF REQ_F_BUFFER_SELECTED is set */
 		struct io_buffer	*kbuf;
 
-		/*
-		 * stores buffer ID for ring provided buffers, valid IFF
-		 * REQ_F_BUFFER_RING is set.
-		 */
-		struct io_buffer_list	*buf_list;
+		struct io_rsrc_node	*buf_node;
 	};
 
 	union {
@@ -564,32 +703,42 @@ struct io_kiocb {
 		/* cache ->apoll->events */
 		__poll_t apoll_events;
 	};
+
+	struct io_rsrc_node		*file_node;
+
 	atomic_t			refs;
-	atomic_t			poll_refs;
+	bool				cancel_seq_set;
 	struct io_task_work		io_task_work;
-	unsigned			nr_tw;
-	/* for polled requests, i.e. IORING_OP_POLL_ADD and async armed poll */
 	union {
+		/*
+		 * for polled requests, i.e. IORING_OP_POLL_ADD and async armed
+		 * poll
+		 */
 		struct hlist_node	hash_node;
-		struct {
-			u64		extra1;
-			u64		extra2;
-		};
+		/* For IOPOLL setup queues, with hybrid polling */
+		u64                     iopoll_start;
+		/* for private io_kiocb freeing */
+		struct rcu_head		rcu_head;
 	};
 	/* internal polling, see IORING_FEAT_FAST_POLL */
 	struct async_poll		*apoll;
 	/* opcode allocated if it needs to store data for async defer */
 	void				*async_data;
 	/* linked requests, IFF REQ_F_HARDLINK or REQ_F_LINK are set */
+	atomic_t			poll_refs;
 	struct io_kiocb			*link;
 	/* custom credentials, valid IFF REQ_F_CREDS is set */
 	const struct cred		*creds;
 	struct io_wq_work		work;
+
+	struct io_big_cqe {
+		u64			extra1;
+		u64			extra2;
+	} big_cqe;
 };
 
 struct io_overflow_cqe {
 	struct list_head list;
 	struct io_uring_cqe cqe;
 };
-
 #endif
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 14f7eaf1b443..079d8773790c 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -118,8 +118,8 @@ struct task_struct;
 #ifdef CONFIG_BLOCK
 void put_io_context(struct io_context *ioc);
 void exit_io_context(struct task_struct *task);
-int __copy_io(unsigned long clone_flags, struct task_struct *tsk);
-static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+int __copy_io(u64 clone_flags, struct task_struct *tsk);
+static inline int copy_io(u64 clone_flags, struct task_struct *tsk)
 {
 	if (!current->io_context)
 		return 0;
@@ -129,7 +129,7 @@ static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
 struct io_context;
 static inline void put_io_context(struct io_context *ioc) { }
 static inline void exit_io_context(struct task_struct *task) { }
-static inline int copy_io(unsigned long clone_flags, struct task_struct *tsk)
+static inline int copy_io(u64 clone_flags, struct task_struct *tsk)
 {
 	return 0;
 }
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index e2b836c2e119..520e967cb501 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -9,6 +9,7 @@
 #include <linux/types.h>
 #include <linux/mm_types.h>
 #include <linux/blkdev.h>
+#include <linux/pagevec.h>
 
 struct address_space;
 struct fiemap_extent_info;
@@ -16,6 +17,7 @@ struct inode;
 struct iomap_iter;
 struct iomap_dio;
 struct iomap_writepage_ctx;
+struct iomap_read_folio_ctx;
 struct iov_iter;
 struct kiocb;
 struct page;
@@ -53,13 +55,35 @@ struct vm_fault;
  *
  * IOMAP_F_XATTR indicates that the iomap is for an extended attribute extent
  * rather than a file data extent.
+ *
+ * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must
+ * never be merged with the mapping before it.
+ *
+ * IOMAP_F_ANON_WRITE indicates that (write) I/O does not have a target block
+ * assigned to it yet and the file system will do that in the bio submission
+ * handler, splitting the I/O as needed.
+ *
+ * IOMAP_F_ATOMIC_BIO indicates that (write) I/O will be issued as an atomic
+ * bio, i.e. set REQ_ATOMIC.
  */
 #define IOMAP_F_NEW		(1U << 0)
 #define IOMAP_F_DIRTY		(1U << 1)
 #define IOMAP_F_SHARED		(1U << 2)
 #define IOMAP_F_MERGED		(1U << 3)
+#ifdef CONFIG_BUFFER_HEAD
 #define IOMAP_F_BUFFER_HEAD	(1U << 4)
+#else
+#define IOMAP_F_BUFFER_HEAD	0
+#endif /* CONFIG_BUFFER_HEAD */
 #define IOMAP_F_XATTR		(1U << 5)
+#define IOMAP_F_BOUNDARY	(1U << 6)
+#define IOMAP_F_ANON_WRITE	(1U << 7)
+#define IOMAP_F_ATOMIC_BIO	(1U << 8)
+
+/*
+ * Flag reserved for file system specific usage
+ */
+#define IOMAP_F_PRIVATE		(1U << 12)
 
 /*
  * Flags set by the core iomap code during operations:
@@ -71,22 +95,14 @@ struct vm_fault;
  * range it covers needs to be remapped by the high level before the operation
  * can proceed.
  */
-#define IOMAP_F_SIZE_CHANGED	(1U << 8)
-#define IOMAP_F_STALE		(1U << 9)
-
-/*
- * Flags from 0x1000 up are for file system specific usage:
- */
-#define IOMAP_F_PRIVATE		(1U << 12)
-
+#define IOMAP_F_SIZE_CHANGED	(1U << 14)
+#define IOMAP_F_STALE		(1U << 15)
 
 /*
  * Magic value for addr:
  */
 #define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
 
-struct iomap_folio_ops;
-
 struct iomap {
 	u64			addr; /* disk offset of mapping, bytes */
 	loff_t			offset;	/* file offset of mapping, bytes */
@@ -97,12 +113,13 @@ struct iomap {
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 	void			*inline_data;
 	void			*private; /* filesystem private */
-	const struct iomap_folio_ops *folio_ops;
 	u64			validity_cookie; /* used with .iomap_valid() */
 };
 
 static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos)
 {
+	if (iomap->flags & IOMAP_F_ANON_WRITE)
+		return U64_MAX; /* invalid */
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
@@ -125,16 +142,11 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap)
 }
 
 /*
- * When a filesystem sets folio_ops in an iomap mapping it returns, get_folio
- * and put_folio will be called for each folio written to.  This only applies
- * to buffered writes as unbuffered writes will not typically have folios
- * associated with them.
- *
  * When get_folio succeeds, put_folio will always be called to do any
  * cleanup work necessary.  put_folio is responsible for unlocking and putting
  * @folio.
  */
-struct iomap_folio_ops {
+struct iomap_write_ops {
 	struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos,
 			unsigned len);
 	void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
@@ -156,6 +168,16 @@ struct iomap_folio_ops {
 	 * locked by the iomap code.
 	 */
 	bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);
+
+	/*
+	 * Optional if the filesystem wishes to provide a custom handler for
+	 * reading in the contents of a folio, otherwise iomap will default to
+	 * submitting a bio read request.
+	 *
+	 * The read must be done synchronously.
+	 */
+	int (*read_folio_range)(const struct iomap_iter *iter,
+			struct folio *folio, loff_t pos, size_t len);
 };
 
 /*
@@ -174,6 +196,8 @@ struct iomap_folio_ops {
 #else
 #define IOMAP_DAX		0
 #endif /* CONFIG_FS_DAX */
+#define IOMAP_ATOMIC		(1 << 9) /* torn-write protection */
+#define IOMAP_DONTCACHE		(1 << 10)
 
 struct iomap_ops {
 	/*
@@ -202,8 +226,10 @@ struct iomap_ops {
  *	calls to iomap_iter().  Treat as read-only in the body.
  * @len: The remaining length of the file segment we're operating on.
  *	It is updated at the same time as @pos.
- * @processed: The number of bytes processed by the body in the most recent
- *	iteration, or a negative errno. 0 causes the iteration to stop.
+ * @iter_start_pos: The original start pos for the current iomap. Used for
+ *	incremental iter advance.
+ * @status: Status of the most recent iteration. Zero on success or a negative
+ *	errno on error.
  * @flags: Zero or more of the iomap_begin flags above.
  * @iomap: Map describing the I/O iteration
  * @srcmap: Source map for COW operations
@@ -212,28 +238,54 @@ struct iomap_iter {
 	struct inode *inode;
 	loff_t pos;
 	u64 len;
-	s64 processed;
+	loff_t iter_start_pos;
+	int status;
 	unsigned flags;
 	struct iomap iomap;
 	struct iomap srcmap;
+	struct folio_batch *fbatch;
 	void *private;
 };
 
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops);
+int iomap_iter_advance(struct iomap_iter *iter, u64 count);
 
 /**
- * iomap_length - length of the current iomap iteration
+ * iomap_length_trim - trimmed length of the current iomap iteration
  * @iter: iteration structure
+ * @pos: File position to trim from.
+ * @len: Length of the mapping to trim to.
  *
- * Returns the length that the operation applies to for the current iteration.
+ * Returns a trimmed length that the operation applies to for the current
+ * iteration.
  */
-static inline u64 iomap_length(const struct iomap_iter *iter)
+static inline u64 iomap_length_trim(const struct iomap_iter *iter, loff_t pos,
+		u64 len)
 {
 	u64 end = iter->iomap.offset + iter->iomap.length;
 
 	if (iter->srcmap.type != IOMAP_HOLE)
 		end = min(end, iter->srcmap.offset + iter->srcmap.length);
-	return min(iter->len, end - iter->pos);
+	return min(len, end - pos);
+}
+
+/**
+ * iomap_length - length of the current iomap iteration
+ * @iter: iteration structure
+ *
+ * Returns the length that the operation applies to for the current iteration.
+ */
+static inline u64 iomap_length(const struct iomap_iter *iter)
+{
+	return iomap_length_trim(iter, iter->pos, iter->len);
+}
+
+/**
+ * iomap_iter_advance_full - advance by the full length of current map
+ */
+static inline int iomap_iter_advance_full(struct iomap_iter *iter)
+{
+	return iomap_iter_advance(iter, iomap_length(iter));
 }
 
 /**
@@ -252,26 +304,70 @@ static inline const struct iomap *iomap_iter_srcmap(const struct iomap_iter *i)
 	return &i->iomap;
 }
 
-ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
-		const struct iomap_ops *ops);
-int iomap_file_buffered_write_punch_delalloc(struct inode *inode,
-		struct iomap *iomap, loff_t pos, loff_t length, ssize_t written,
-		int (*punch)(struct inode *inode, loff_t pos, loff_t length));
+/*
+ * Return the file offset for the first unchanged block after a short write.
+ *
+ * If nothing was written, round @pos down to point at the first block in
+ * the range, else round up to include the partially written block.
+ */
+static inline loff_t iomap_last_written_block(struct inode *inode, loff_t pos,
+		ssize_t written)
+{
+	if (unlikely(!written))
+		return round_down(pos, i_blocksize(inode));
+	return round_up(pos + written, i_blocksize(inode));
+}
+
+/*
+ * Check if the range needs to be unshared for a FALLOC_FL_UNSHARE_RANGE
+ * operation.
+ *
+ * Don't bother with blocks that are not shared to start with; or mappings that
+ * cannot be shared, such as inline data, delalloc reservations, holes or
+ * unwritten extents.
+ *
+ * Note that we use srcmap directly instead of iomap_iter_srcmap as unsharing
+ * requires providing a separate source map, and the presence of one is a good
+ * indicator that unsharing is needed, unlike IOMAP_F_SHARED which can be set
+ * for any data that goes into the COW fork for XFS.
+ */
+static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
+{
+	return (iter->iomap.flags & IOMAP_F_SHARED) &&
+		iter->srcmap.type == IOMAP_MAPPED;
+}
 
-int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
-void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
+ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private);
+void iomap_read_folio(const struct iomap_ops *ops,
+		struct iomap_read_folio_ctx *ctx);
+void iomap_readahead(const struct iomap_ops *ops,
+		struct iomap_read_folio_ctx *ctx);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
-struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos);
+struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len);
 bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
 void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
+bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
-		const struct iomap_ops *ops);
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops);
+loff_t iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t offset,
+		loff_t length);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-		bool *did_zero, const struct iomap_ops *ops);
+		bool *did_zero, const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops);
-vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
-			const struct iomap_ops *ops);
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private);
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
+		void *private);
+typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length,
+		struct iomap *iomap);
+void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
+		loff_t end_byte, unsigned flags, struct iomap *iomap,
+		iomap_punch_t punch);
+
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		u64 start, u64 len, const struct iomap_ops *ops);
 loff_t iomap_seek_hole(struct inode *inode, loff_t offset,
@@ -282,57 +378,138 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 		const struct iomap_ops *ops);
 
 /*
+ * Flags for iomap_ioend->io_flags.
+ */
+/* shared COW extent */
+#define IOMAP_IOEND_SHARED		(1U << 0)
+/* unwritten extent */
+#define IOMAP_IOEND_UNWRITTEN		(1U << 1)
+/* don't merge into previous ioend */
+#define IOMAP_IOEND_BOUNDARY		(1U << 2)
+/* is direct I/O */
+#define IOMAP_IOEND_DIRECT		(1U << 3)
+/* is DONTCACHE I/O */
+#define IOMAP_IOEND_DONTCACHE		(1U << 4)
+
+/*
+ * Flags that if set on either ioend prevent the merge of two ioends.
+ * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way)
+ */
+#define IOMAP_IOEND_NOMERGE_FLAGS \
+	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT | \
+	 IOMAP_IOEND_DONTCACHE)
+
+/*
  * Structure for writeback I/O completions.
+ *
+ * File systems can split a bio generated by iomap.  In that case the parent
+ * ioend it was split from is recorded in ioend->io_parent.
  */
 struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
-	u16			io_type;
-	u16			io_flags;	/* IOMAP_F_* */
-	u32			io_folios;	/* folios added to ioend */
+	u16			io_flags;	/* IOMAP_IOEND_* */
 	struct inode		*io_inode;	/* file being written to */
 	size_t			io_size;	/* size of the extent */
+	atomic_t		io_remaining;	/* completetion defer count */
+	int			io_error;	/* stashed away status */
+	struct iomap_ioend	*io_parent;	/* parent for completions */
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
-	struct bio		*io_bio;	/* bio being built */
-	struct bio		io_inline_bio;	/* MUST BE LAST! */
+	void			*io_private;	/* file system private data */
+	struct bio		io_bio;		/* MUST BE LAST! */
 };
 
-struct iomap_writeback_ops {
-	/*
-	 * Required, maps the blocks so that writeback can be performed on
-	 * the range starting at offset.
-	 */
-	int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
-				loff_t offset);
+static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
+{
+	return container_of(bio, struct iomap_ioend, io_bio);
+}
 
+struct iomap_writeback_ops {
 	/*
-	 * Optional, allows the file systems to perform actions just before
-	 * submitting the bio and/or override the bio end_io handler for complex
-	 * operations like copy on write extent manipulation or unwritten extent
-	 * conversions.
+	 * Performs writeback on the passed in range
+	 *
+	 * Can map arbitrarily large regions, but we need to call into it at
+	 * least once per folio to allow the file systems to synchronize with
+	 * the write path that could be invalidating mappings.
+	 *
+	 * An existing mapping from a previous call to this method can be reused
+	 * by the file system if it is still valid.
+	 *
+	 * If this succeeds, iomap_finish_folio_write() must be called once
+	 * writeback completes for the range, regardless of whether the
+	 * writeback succeeded or failed.
+	 *
+	 * Returns the number of bytes processed or a negative errno.
 	 */
-	int (*prepare_ioend)(struct iomap_ioend *ioend, int status);
+	ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc,
+			struct folio *folio, u64 pos, unsigned int len,
+			u64 end_pos);
 
 	/*
-	 * Optional, allows the file system to discard state on a page where
-	 * we failed to submit any I/O.
+	 * Submit a writeback context previously build up by ->writeback_range.
+	 *
+	 * Returns 0 if the context was successfully submitted, or a negative
+	 * error code if not.  If @error is non-zero a failure occurred, and
+	 * the writeback context should be completed with an error.
 	 */
-	void (*discard_folio)(struct folio *folio, loff_t pos);
+	int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error);
 };
 
 struct iomap_writepage_ctx {
 	struct iomap		iomap;
-	struct iomap_ioend	*ioend;
+	struct inode		*inode;
+	struct writeback_control *wbc;
 	const struct iomap_writeback_ops *ops;
+	u32			nr_folios;	/* folios added to the ioend */
+	void			*wb_ctx;	/* pending writeback context */
 };
 
+struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio,
+		loff_t file_offset, u16 ioend_flags);
+struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
+		unsigned int max_len, bool is_append);
 void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
 void iomap_sort_ioends(struct list_head *ioend_list);
-int iomap_writepages(struct address_space *mapping,
-		struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
-		const struct iomap_writeback_ops *ops);
+ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
+		loff_t pos, loff_t end_pos, unsigned int dirty_len);
+int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
+
+void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len,
+		int error);
+void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
+		size_t len);
+
+int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
+int iomap_writepages(struct iomap_writepage_ctx *wpc);
+
+struct iomap_read_folio_ctx {
+	const struct iomap_read_ops *ops;
+	struct folio		*cur_folio;
+	struct readahead_control *rac;
+	void			*read_ctx;
+};
+
+struct iomap_read_ops {
+	/*
+	 * Read in a folio range.
+	 *
+	 * If this succeeds, iomap_finish_folio_read() must be called after the
+	 * range is read in, regardless of whether the read succeeded or failed.
+	 *
+	 * Returns 0 on success or a negative error on failure.
+	 */
+	int (*read_folio_range)(const struct iomap_iter *iter,
+			struct iomap_read_folio_ctx *ctx, size_t len);
+
+	/*
+	 * Submit any pending read requests.
+	 *
+	 * This is optional.
+	 */
+	void (*submit_read)(struct iomap_read_folio_ctx *ctx);
+};
 
 /*
  * Flags for direct I/O ->end_io:
@@ -377,6 +554,14 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_PARTIAL		(1 << 2)
 
+/*
+ * Ensure each bio is aligned to fs block size.
+ *
+ * For filesystems which need to calculate/verify the checksum of each fs
+ * block. Otherwise they may not be able to handle unaligned bios.
+ */
+#define IOMAP_DIO_FSBLOCK_ALIGNED	(1 << 3)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before);
@@ -397,4 +582,32 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
 # define iomap_swapfile_activate(sis, swapfile, pagespan, ops)	(-EIO)
 #endif /* CONFIG_SWAP */
 
+extern struct bio_set iomap_ioend_bioset;
+
+#ifdef CONFIG_BLOCK
+extern const struct iomap_read_ops iomap_bio_read_ops;
+
+static inline void iomap_bio_read_folio(struct folio *folio,
+		const struct iomap_ops *ops)
+{
+	struct iomap_read_folio_ctx ctx = {
+		.ops		= &iomap_bio_read_ops,
+		.cur_folio	= folio,
+	};
+
+	iomap_read_folio(ops, &ctx);
+}
+
+static inline void iomap_bio_readahead(struct readahead_control *rac,
+		const struct iomap_ops *ops)
+{
+	struct iomap_read_folio_ctx ctx = {
+		.ops		= &iomap_bio_read_ops,
+		.rac		= rac,
+	};
+
+	iomap_readahead(ops, &ctx);
+}
+#endif /* CONFIG_BLOCK */
+
 #endif /* LINUX_IOMAP_H */
diff --git a/include/linux/iommu-dma.h b/include/linux/iommu-dma.h
new file mode 100644
index 000000000000..a92b3ff9b934
--- /dev/null
+++ b/include/linux/iommu-dma.h
@@ -0,0 +1,64 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ *
+ * DMA operations that map physical memory through IOMMU.
+ */
+#ifndef _LINUX_IOMMU_DMA_H
+#define _LINUX_IOMMU_DMA_H
+
+#include <linux/dma-direction.h>
+
+#ifdef CONFIG_IOMMU_DMA
+static inline bool use_dma_iommu(struct device *dev)
+{
+	return dev->dma_iommu;
+}
+#else
+static inline bool use_dma_iommu(struct device *dev)
+{
+	return false;
+}
+#endif /* CONFIG_IOMMU_DMA */
+
+dma_addr_t iommu_dma_map_phys(struct device *dev, phys_addr_t phys, size_t size,
+		enum dma_data_direction dir, unsigned long attrs);
+void iommu_dma_unmap_phys(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir, unsigned long attrs);
+int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
+		enum dma_data_direction dir, unsigned long attrs);
+void *iommu_dma_alloc(struct device *dev, size_t size, dma_addr_t *handle,
+		gfp_t gfp, unsigned long attrs);
+int iommu_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+int iommu_dma_get_sgtable(struct device *dev, struct sg_table *sgt,
+		void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		unsigned long attrs);
+unsigned long iommu_dma_get_merge_boundary(struct device *dev);
+size_t iommu_dma_opt_mapping_size(void);
+size_t iommu_dma_max_mapping_size(struct device *dev);
+void iommu_dma_free(struct device *dev, size_t size, void *cpu_addr,
+		dma_addr_t handle, unsigned long attrs);
+struct sg_table *iommu_dma_alloc_noncontiguous(struct device *dev, size_t size,
+		enum dma_data_direction dir, gfp_t gfp, unsigned long attrs);
+void iommu_dma_free_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt, enum dma_data_direction dir);
+void *iommu_dma_vmap_noncontiguous(struct device *dev, size_t size,
+		struct sg_table *sgt);
+#define iommu_dma_vunmap_noncontiguous(dev, vaddr) \
+	vunmap(vaddr);
+int iommu_dma_mmap_noncontiguous(struct device *dev, struct vm_area_struct *vma,
+		size_t size, struct sg_table *sgt);
+void iommu_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir);
+void iommu_dma_sync_single_for_device(struct device *dev, dma_addr_t dma_handle,
+		size_t size, enum dma_data_direction dir);
+void iommu_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir);
+void iommu_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sgl,
+		int nelems, enum dma_data_direction dir);
+
+#endif /* _LINUX_IOMMU_DMA_H */
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e8c9a7da1060..8c66284a91a8 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -13,7 +13,8 @@
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/of.h>
-#include <uapi/linux/iommu.h>
+#include <linux/iova_bitmap.h>
+#include <uapi/linux/iommufd.h>
 
 #define IOMMU_READ	(1 << 0)
 #define IOMMU_WRITE	(1 << 1)
@@ -37,10 +38,121 @@ struct bus_type;
 struct device;
 struct iommu_domain;
 struct iommu_domain_ops;
+struct iommu_dirty_ops;
 struct notifier_block;
 struct iommu_sva;
-struct iommu_fault_event;
 struct iommu_dma_cookie;
+struct iommu_dma_msi_cookie;
+struct iommu_fault_param;
+struct iommufd_ctx;
+struct iommufd_viommu;
+struct msi_desc;
+struct msi_msg;
+
+#define IOMMU_FAULT_PERM_READ	(1 << 0) /* read */
+#define IOMMU_FAULT_PERM_WRITE	(1 << 1) /* write */
+#define IOMMU_FAULT_PERM_EXEC	(1 << 2) /* exec */
+#define IOMMU_FAULT_PERM_PRIV	(1 << 3) /* privileged */
+
+/* Generic fault types, can be expanded IRQ remapping fault */
+enum iommu_fault_type {
+	IOMMU_FAULT_PAGE_REQ = 1,	/* page request fault */
+};
+
+/**
+ * struct iommu_fault_page_request - Page Request data
+ * @flags: encodes whether the corresponding fields are valid and whether this
+ *         is the last page in group (IOMMU_FAULT_PAGE_REQUEST_* values).
+ *         When IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID is set, the page response
+ *         must have the same PASID value as the page request. When it is clear,
+ *         the page response should not have a PASID.
+ * @pasid: Process Address Space ID
+ * @grpid: Page Request Group Index
+ * @perm: requested page permissions (IOMMU_FAULT_PERM_* values)
+ * @addr: page address
+ * @private_data: device-specific private information
+ */
+struct iommu_fault_page_request {
+#define IOMMU_FAULT_PAGE_REQUEST_PASID_VALID	(1 << 0)
+#define IOMMU_FAULT_PAGE_REQUEST_LAST_PAGE	(1 << 1)
+#define IOMMU_FAULT_PAGE_RESPONSE_NEEDS_PASID	(1 << 2)
+	u32	flags;
+	u32	pasid;
+	u32	grpid;
+	u32	perm;
+	u64	addr;
+	u64	private_data[2];
+};
+
+/**
+ * struct iommu_fault - Generic fault data
+ * @type: fault type from &enum iommu_fault_type
+ * @prm: Page Request message, when @type is %IOMMU_FAULT_PAGE_REQ
+ */
+struct iommu_fault {
+	u32 type;
+	struct iommu_fault_page_request prm;
+};
+
+/**
+ * enum iommu_page_response_code - Return status of fault handlers
+ * @IOMMU_PAGE_RESP_SUCCESS: Fault has been handled and the page tables
+ *	populated, retry the access. This is "Success" in PCI PRI.
+ * @IOMMU_PAGE_RESP_FAILURE: General error. Drop all subsequent faults from
+ *	this device if possible. This is "Response Failure" in PCI PRI.
+ * @IOMMU_PAGE_RESP_INVALID: Could not handle this fault, don't retry the
+ *	access. This is "Invalid Request" in PCI PRI.
+ */
+enum iommu_page_response_code {
+	IOMMU_PAGE_RESP_SUCCESS = 0,
+	IOMMU_PAGE_RESP_INVALID,
+	IOMMU_PAGE_RESP_FAILURE,
+};
+
+/**
+ * struct iommu_page_response - Generic page response information
+ * @pasid: Process Address Space ID
+ * @grpid: Page Request Group Index
+ * @code: response code from &enum iommu_page_response_code
+ */
+struct iommu_page_response {
+	u32	pasid;
+	u32	grpid;
+	u32	code;
+};
+
+struct iopf_fault {
+	struct iommu_fault fault;
+	/* node for pending lists */
+	struct list_head list;
+};
+
+struct iopf_group {
+	struct iopf_fault last_fault;
+	struct list_head faults;
+	size_t fault_count;
+	/* list node for iommu_fault_param::faults */
+	struct list_head pending_node;
+	struct work_struct work;
+	struct iommu_attach_handle *attach_handle;
+	/* The device's fault data parameter. */
+	struct iommu_fault_param *fault_param;
+	/* Used by handler provider to hook the group on its own lists. */
+	struct list_head node;
+	u32 cookie;
+};
+
+/**
+ * struct iopf_queue - IO Page Fault queue
+ * @wq: the fault workqueue
+ * @devices: devices attached to this queue
+ * @lock: protects the device list
+ */
+struct iopf_queue {
+	struct workqueue_struct *wq;
+	struct list_head devices;
+	struct mutex lock;
+};
 
 /* iommu fault flags */
 #define IOMMU_FAULT_READ	0x0
@@ -48,7 +160,6 @@ struct iommu_dma_cookie;
 
 typedef int (*iommu_fault_handler_t)(struct iommu_domain *,
 			struct device *, unsigned long, int, void *);
-typedef int (*iommu_dev_fault_handler_t)(struct iommu_fault *, void *);
 
 struct iommu_domain_geometry {
 	dma_addr_t aperture_start; /* First address that can be mapped    */
@@ -56,6 +167,15 @@ struct iommu_domain_geometry {
 	bool force_aperture;       /* DMA only allowed in mappable range? */
 };
 
+enum iommu_domain_cookie_type {
+	IOMMU_COOKIE_NONE,
+	IOMMU_COOKIE_DMA_IOVA,
+	IOMMU_COOKIE_DMA_MSI,
+	IOMMU_COOKIE_FAULT_HANDLER,
+	IOMMU_COOKIE_SVA,
+	IOMMU_COOKIE_IOMMUFD,
+};
+
 /* Domain feature flags */
 #define __IOMMU_DOMAIN_PAGING	(1U << 0)  /* Support for iommu_map/unmap */
 #define __IOMMU_DOMAIN_DMA_API	(1U << 1)  /* Domain for use in DMA-API
@@ -64,7 +184,12 @@ struct iommu_domain_geometry {
 #define __IOMMU_DOMAIN_DMA_FQ	(1U << 3)  /* DMA-API uses flush queue    */
 
 #define __IOMMU_DOMAIN_SVA	(1U << 4)  /* Shared process address space */
+#define __IOMMU_DOMAIN_PLATFORM	(1U << 5)
 
+#define __IOMMU_DOMAIN_NESTED	(1U << 6)  /* User-managed address space nested
+					      on a stage-2 translation        */
+
+#define IOMMU_DOMAIN_ALLOC_FLAGS ~__IOMMU_DOMAIN_DMA_FQ
 /*
  * This are the possible domain-types
  *
@@ -80,6 +205,8 @@ struct iommu_domain_geometry {
  *				  invalidation.
  *	IOMMU_DOMAIN_SVA	- DMA addresses are shared process addresses
  *				  represented by mm_struct's.
+ *	IOMMU_DOMAIN_PLATFORM	- Legacy domain for drivers that do their own
+ *				  dma_api stuff. Do not use in new drivers.
  */
 #define IOMMU_DOMAIN_BLOCKED	(0U)
 #define IOMMU_DOMAIN_IDENTITY	(__IOMMU_DOMAIN_PT)
@@ -90,17 +217,23 @@ struct iommu_domain_geometry {
 				 __IOMMU_DOMAIN_DMA_API |	\
 				 __IOMMU_DOMAIN_DMA_FQ)
 #define IOMMU_DOMAIN_SVA	(__IOMMU_DOMAIN_SVA)
+#define IOMMU_DOMAIN_PLATFORM	(__IOMMU_DOMAIN_PLATFORM)
+#define IOMMU_DOMAIN_NESTED	(__IOMMU_DOMAIN_NESTED)
 
 struct iommu_domain {
 	unsigned type;
+	enum iommu_domain_cookie_type cookie_type;
 	const struct iommu_domain_ops *ops;
+	const struct iommu_dirty_ops *dirty_ops;
+	const struct iommu_ops *owner; /* Whose domain_alloc we came from */
 	unsigned long pgsize_bitmap;	/* Bitmap of page sizes in use */
 	struct iommu_domain_geometry geometry;
-	struct iommu_dma_cookie *iova_cookie;
-	enum iommu_page_response_code (*iopf_handler)(struct iommu_fault *fault,
-						      void *data);
-	void *fault_data;
-	union {
+	int (*iopf_handler)(struct iopf_group *group);
+
+	union { /* cookie */
+		struct iommu_dma_cookie *iova_cookie;
+		struct iommu_dma_msi_cookie *msi_cookie;
+		struct iommufd_hw_pagetable *iommufd_hwpt;
 		struct {
 			iommu_fault_handler_t handler;
 			void *handler_token;
@@ -108,6 +241,11 @@ struct iommu_domain {
 		struct {	/* IOMMU_DOMAIN_SVA */
 			struct mm_struct *mm;
 			int users;
+			/*
+			 * Next iommu_domain in mm->iommu_mm->sva-domains list
+			 * protected by iommu_sva_lock.
+			 */
+			struct list_head next;
 		};
 	};
 };
@@ -127,6 +265,12 @@ enum iommu_cap {
 	 * this device.
 	 */
 	IOMMU_CAP_ENFORCE_CACHE_COHERENCY,
+	/*
+	 * IOMMU driver does not issue TLB maintenance during .unmap, so can
+	 * usefully support the non-strict DMA flush queue.
+	 */
+	IOMMU_CAP_DEFERRED_FLUSH,
+	IOMMU_CAP_DIRTY_TRACKING,	/* IOMMU supports dirty tracking */
 };
 
 /* These are the possible reserved region types */
@@ -173,25 +317,25 @@ struct iommu_iort_rmr_data {
 	u32 num_sids;
 };
 
-/**
- * enum iommu_dev_features - Per device IOMMU features
- * @IOMMU_DEV_FEAT_SVA: Shared Virtual Addresses
- * @IOMMU_DEV_FEAT_IOPF: I/O Page Faults such as PRI or Stall. Generally
- *			 enabling %IOMMU_DEV_FEAT_SVA requires
- *			 %IOMMU_DEV_FEAT_IOPF, but some devices manage I/O Page
- *			 Faults themselves instead of relying on the IOMMU. When
- *			 supported, this feature must be enabled before and
- *			 disabled after %IOMMU_DEV_FEAT_SVA.
- *
- * Device drivers enable a feature using iommu_dev_enable_feature().
+#define IOMMU_NO_PASID	(0U) /* Reserved for DMA w/o PASID */
+#define IOMMU_FIRST_GLOBAL_PASID	(1U) /*starting range for allocation */
+#define IOMMU_PASID_INVALID	(-1U)
+typedef unsigned int ioasid_t;
+
+/* Read but do not clear any dirty bits */
+#define IOMMU_DIRTY_NO_CLEAR (1 << 0)
+
+/*
+ * Pages allocated through iommu_alloc_pages_node_sz() can be placed on this
+ * list using iommu_pages_list_add(). Note: ONLY pages from
+ * iommu_alloc_pages_node_sz() can be used this way!
  */
-enum iommu_dev_features {
-	IOMMU_DEV_FEAT_SVA,
-	IOMMU_DEV_FEAT_IOPF,
+struct iommu_pages_list {
+	struct list_head pages;
 };
 
-#define IOMMU_PASID_INVALID	(-1U)
-typedef unsigned int ioasid_t;
+#define IOMMU_PAGES_LIST_INIT(name) \
+	((struct iommu_pages_list){ .pages = LIST_HEAD_INIT(name.pages) })
 
 #ifdef CONFIG_IOMMU_API
 
@@ -215,72 +359,357 @@ struct iommu_iotlb_gather {
 	unsigned long		start;
 	unsigned long		end;
 	size_t			pgsize;
-	struct list_head	freelist;
+	struct iommu_pages_list	freelist;
 	bool			queued;
 };
 
 /**
+ * struct iommu_dirty_bitmap - Dirty IOVA bitmap state
+ * @bitmap: IOVA bitmap
+ * @gather: Range information for a pending IOTLB flush
+ */
+struct iommu_dirty_bitmap {
+	struct iova_bitmap *bitmap;
+	struct iommu_iotlb_gather *gather;
+};
+
+/**
+ * struct iommu_dirty_ops - domain specific dirty tracking operations
+ * @set_dirty_tracking: Enable or Disable dirty tracking on the iommu domain
+ * @read_and_clear_dirty: Walk IOMMU page tables for dirtied PTEs marshalled
+ *                        into a bitmap, with a bit represented as a page.
+ *                        Reads the dirty PTE bits and clears it from IO
+ *                        pagetables.
+ */
+struct iommu_dirty_ops {
+	int (*set_dirty_tracking)(struct iommu_domain *domain, bool enabled);
+	int (*read_and_clear_dirty)(struct iommu_domain *domain,
+				    unsigned long iova, size_t size,
+				    unsigned long flags,
+				    struct iommu_dirty_bitmap *dirty);
+};
+
+/**
+ * struct iommu_user_data - iommu driver specific user space data info
+ * @type: The data type of the user buffer
+ * @uptr: Pointer to the user buffer for copy_from_user()
+ * @len: The length of the user buffer in bytes
+ *
+ * A user space data is an uAPI that is defined in include/uapi/linux/iommufd.h
+ * @type, @uptr and @len should be just copied from an iommufd core uAPI struct.
+ */
+struct iommu_user_data {
+	unsigned int type;
+	void __user *uptr;
+	size_t len;
+};
+
+/**
+ * struct iommu_user_data_array - iommu driver specific user space data array
+ * @type: The data type of all the entries in the user buffer array
+ * @uptr: Pointer to the user buffer array
+ * @entry_len: The fixed-width length of an entry in the array, in bytes
+ * @entry_num: The number of total entries in the array
+ *
+ * The user buffer includes an array of requests with format defined in
+ * include/uapi/linux/iommufd.h
+ */
+struct iommu_user_data_array {
+	unsigned int type;
+	void __user *uptr;
+	size_t entry_len;
+	u32 entry_num;
+};
+
+/**
+ * __iommu_copy_struct_from_user - Copy iommu driver specific user space data
+ * @dst_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @src_data: Pointer to a struct iommu_user_data for user space data info
+ * @data_type: The data type of the @dst_data. Must match with @src_data.type
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _dst)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int __iommu_copy_struct_from_user(
+	void *dst_data, const struct iommu_user_data *src_data,
+	unsigned int data_type, size_t data_len, size_t min_len)
+{
+	if (WARN_ON(!dst_data || !src_data))
+		return -EINVAL;
+	if (src_data->type != data_type)
+		return -EINVAL;
+	if (src_data->len < min_len || data_len < src_data->len)
+		return -EINVAL;
+	return copy_struct_from_user(dst_data, data_len, src_data->uptr,
+				     src_data->len);
+}
+
+/**
+ * iommu_copy_struct_from_user - Copy iommu driver specific user space data
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @user_data: Pointer to a struct iommu_user_data for user space data info
+ * @data_type: The data type of the @kdst. Must match with @user_data->type
+ * @min_last: The last member of the data structure @kdst points in the initial
+ *            version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_from_user(kdst, user_data, data_type, min_last) \
+	__iommu_copy_struct_from_user(kdst, user_data, data_type,         \
+				      sizeof(*kdst),                      \
+				      offsetofend(typeof(*kdst), min_last))
+
+/**
+ * __iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                       data from an iommu_user_data_array
+ * @dst_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @src_array: Pointer to a struct iommu_user_data_array for a user space array
+ * @data_type: The data type of the @dst_data. Must match with @src_array.type
+ * @index: Index to the location in the array to copy user data from
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _dst)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int __iommu_copy_struct_from_user_array(
+	void *dst_data, const struct iommu_user_data_array *src_array,
+	unsigned int data_type, unsigned int index, size_t data_len,
+	size_t min_len)
+{
+	struct iommu_user_data src_data;
+
+	if (WARN_ON(!src_array || index >= src_array->entry_num))
+		return -EINVAL;
+	if (!src_array->entry_num)
+		return -EINVAL;
+	src_data.uptr = src_array->uptr + src_array->entry_len * index;
+	src_data.len = src_array->entry_len;
+	src_data.type = src_array->type;
+
+	return __iommu_copy_struct_from_user(dst_data, &src_data, data_type,
+					     data_len, min_len);
+}
+
+/**
+ * iommu_copy_struct_from_user_array - Copy iommu driver specific user space
+ *                                     data from an iommu_user_data_array
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @user_array: Pointer to a struct iommu_user_data_array for a user space
+ *              array
+ * @data_type: The data type of the @kdst. Must match with @user_array->type
+ * @index: Index to the location in the array to copy user data from
+ * @min_last: The last member of the data structure @kdst points in the
+ *            initial version.
+ *
+ * Copy a single entry from a user array. Return 0 for success, otherwise
+ * -error.
+ */
+#define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \
+					  min_last)                           \
+	__iommu_copy_struct_from_user_array(                                  \
+		kdst, user_array, data_type, index, sizeof(*(kdst)),          \
+		offsetofend(typeof(*(kdst)), min_last))
+
+/**
+ * iommu_copy_struct_from_full_user_array - Copy iommu driver specific user
+ *         space data from an iommu_user_data_array
+ * @kdst: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @kdst_entry_size: sizeof(*kdst)
+ * @user_array: Pointer to a struct iommu_user_data_array for a user space
+ *              array
+ * @data_type: The data type of the @kdst. Must match with @user_array->type
+ *
+ * Copy the entire user array. kdst must have room for kdst_entry_size *
+ * user_array->entry_num bytes. Return 0 for success, otherwise -error.
+ */
+static inline int
+iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
+				       struct iommu_user_data_array *user_array,
+				       unsigned int data_type)
+{
+	unsigned int i;
+	int ret;
+
+	if (user_array->type != data_type)
+		return -EINVAL;
+	if (!user_array->entry_num)
+		return -EINVAL;
+	if (likely(user_array->entry_len == kdst_entry_size)) {
+		if (copy_from_user(kdst, user_array->uptr,
+				   user_array->entry_num *
+					   user_array->entry_len))
+			return -EFAULT;
+	}
+
+	/* Copy item by item */
+	for (i = 0; i != user_array->entry_num; i++) {
+		ret = copy_struct_from_user(
+			kdst + kdst_entry_size * i, kdst_entry_size,
+			user_array->uptr + user_array->entry_len * i,
+			user_array->entry_len);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+/**
+ * __iommu_copy_struct_to_user - Report iommu driver specific user space data
+ * @dst_data: Pointer to a struct iommu_user_data for user space data location
+ * @src_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @data_type: The data type of the @src_data. Must match with @dst_data.type
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _src)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int
+__iommu_copy_struct_to_user(const struct iommu_user_data *dst_data,
+			    void *src_data, unsigned int data_type,
+			    size_t data_len, size_t min_len)
+{
+	if (WARN_ON(!dst_data || !src_data))
+		return -EINVAL;
+	if (dst_data->type != data_type)
+		return -EINVAL;
+	if (dst_data->len < min_len || data_len < dst_data->len)
+		return -EINVAL;
+	return copy_struct_to_user(dst_data->uptr, dst_data->len, src_data,
+				   data_len, NULL);
+}
+
+/**
+ * iommu_copy_struct_to_user - Report iommu driver specific user space data
+ * @user_data: Pointer to a struct iommu_user_data for user space data location
+ * @ksrc: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @data_type: The data type of the @ksrc. Must match with @user_data->type
+ * @min_last: The last member of the data structure @ksrc points in the initial
+ *            version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_to_user(user_data, ksrc, data_type, min_last)        \
+	__iommu_copy_struct_to_user(user_data, ksrc, data_type, sizeof(*ksrc), \
+				    offsetofend(typeof(*ksrc), min_last))
+
+/**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
- * @domain_alloc: allocate iommu domain
+ * @hw_info: report iommu hardware information. The data buffer returned by this
+ *           op is allocated in the iommu driver and freed by the caller after
+ *           use. @type can input a requested type and output a supported type.
+ *           Driver should reject an unsupported data @type input
+ * @domain_alloc: Do not use in new drivers
+ * @domain_alloc_identity: allocate an IDENTITY domain. Drivers should prefer to
+ *                         use identity_domain instead. This should only be used
+ *                         if dynamic logic is necessary.
+ * @domain_alloc_paging_flags: Allocate an iommu domain corresponding to the
+ *                     input parameters as defined in
+ *                     include/uapi/linux/iommufd.h. The @user_data can be
+ *                     optionally provided, the new domain must support
+ *                     __IOMMU_DOMAIN_PAGING. Upon failure, ERR_PTR must be
+ *                     returned.
+ * @domain_alloc_paging: Allocate an iommu_domain that can be used for
+ *                       UNMANAGED, DMA, and DMA_FQ domain types. This is the
+ *                       same as invoking domain_alloc_paging_flags() with
+ *                       @flags=0, @user_data=NULL. A driver should implement
+ *                       only one of the two ops.
+ * @domain_alloc_sva: Allocate an iommu_domain for Shared Virtual Addressing.
+ * @domain_alloc_nested: Allocate an iommu_domain for nested translation.
  * @probe_device: Add device to iommu driver handling
  * @release_device: Remove device from iommu driver handling
  * @probe_finalize: Do final setup work after the device is added to an IOMMU
  *                  group and attached to the groups domain
- * @set_platform_dma_ops: Returning control back to the platform DMA ops. This op
- *                        is to support old IOMMU drivers, new drivers should use
- *                        default domains, and the common IOMMU DMA ops.
  * @device_group: find iommu group for a particular device
  * @get_resv_regions: Request list of reserved regions for a device
  * @of_xlate: add OF master IDs to iommu grouping
  * @is_attach_deferred: Check if domain attach should be deferred from iommu
  *                      driver init to device driver init (default no)
- * @dev_enable/disable_feat: per device entries to enable/disable
- *                               iommu specific features.
  * @page_response: handle page request response
  * @def_domain_type: device default domain type, return value:
  *		- IOMMU_DOMAIN_IDENTITY: must use an identity domain
  *		- IOMMU_DOMAIN_DMA: must use a dma domain
  *		- 0: use the default setting
  * @default_domain_ops: the default ops for domains
- * @remove_dev_pasid: Remove any translation configurations of a specific
- *                    pasid, so that any DMA transactions with this pasid
- *                    will be blocked by the hardware.
- * @pgsize_bitmap: bitmap of all possible supported page sizes
+ * @get_viommu_size: Get the size of a driver-level vIOMMU structure for a given
+ *                   @dev corresponding to @viommu_type. Driver should return 0
+ *                   if vIOMMU isn't supported accordingly. It is required for
+ *                   driver to use the VIOMMU_STRUCT_SIZE macro to sanitize the
+ *                   driver-level vIOMMU structure related to the core one
+ * @viommu_init: Init the driver-level struct of an iommufd_viommu on a physical
+ *               IOMMU instance @viommu->iommu_dev, as the set of virtualization
+ *               resources shared/passed to user space IOMMU instance. Associate
+ *               it with a nesting @parent_domain. It is required for driver to
+ *               set @viommu->ops pointing to its own viommu_ops
  * @owner: Driver module providing these ops
+ * @identity_domain: An always available, always attachable identity
+ *                   translation.
+ * @blocked_domain: An always available, always attachable blocking
+ *                  translation.
+ * @default_domain: If not NULL this will always be set as the default domain.
+ *                  This should be an IDENTITY/BLOCKED/PLATFORM domain.
+ *                  Do not use in new drivers.
+ * @user_pasid_table: IOMMU driver supports user-managed PASID table. There is
+ *                    no user domain for each PASID and the I/O page faults are
+ *                    forwarded through the user domain attached to the device
+ *                    RID.
  */
 struct iommu_ops {
 	bool (*capable)(struct device *dev, enum iommu_cap);
+	void *(*hw_info)(struct device *dev, u32 *length,
+			 enum iommu_hw_info_type *type);
 
 	/* Domain allocation and freeing by the iommu driver */
+#if IS_ENABLED(CONFIG_FSL_PAMU)
 	struct iommu_domain *(*domain_alloc)(unsigned iommu_domain_type);
+#endif
+	struct iommu_domain *(*domain_alloc_identity)(struct device *dev);
+	struct iommu_domain *(*domain_alloc_paging_flags)(
+		struct device *dev, u32 flags,
+		const struct iommu_user_data *user_data);
+	struct iommu_domain *(*domain_alloc_paging)(struct device *dev);
+	struct iommu_domain *(*domain_alloc_sva)(struct device *dev,
+						 struct mm_struct *mm);
+	struct iommu_domain *(*domain_alloc_nested)(
+		struct device *dev, struct iommu_domain *parent, u32 flags,
+		const struct iommu_user_data *user_data);
 
 	struct iommu_device *(*probe_device)(struct device *dev);
 	void (*release_device)(struct device *dev);
 	void (*probe_finalize)(struct device *dev);
-	void (*set_platform_dma_ops)(struct device *dev);
 	struct iommu_group *(*device_group)(struct device *dev);
 
 	/* Request/Free a list of reserved regions for a device */
 	void (*get_resv_regions)(struct device *dev, struct list_head *list);
 
-	int (*of_xlate)(struct device *dev, struct of_phandle_args *args);
+	int (*of_xlate)(struct device *dev, const struct of_phandle_args *args);
 	bool (*is_attach_deferred)(struct device *dev);
 
 	/* Per device IOMMU features */
-	int (*dev_enable_feat)(struct device *dev, enum iommu_dev_features f);
-	int (*dev_disable_feat)(struct device *dev, enum iommu_dev_features f);
-
-	int (*page_response)(struct device *dev,
-			     struct iommu_fault_event *evt,
-			     struct iommu_page_response *msg);
+	void (*page_response)(struct device *dev, struct iopf_fault *evt,
+			      struct iommu_page_response *msg);
 
 	int (*def_domain_type)(struct device *dev);
-	void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid);
+
+	size_t (*get_viommu_size)(struct device *dev,
+				  enum iommu_viommu_type viommu_type);
+	int (*viommu_init)(struct iommufd_viommu *viommu,
+			   struct iommu_domain *parent_domain,
+			   const struct iommu_user_data *user_data);
 
 	const struct iommu_domain_ops *default_domain_ops;
-	unsigned long pgsize_bitmap;
 	struct module *owner;
+	struct iommu_domain *identity_domain;
+	struct iommu_domain *blocked_domain;
+	struct iommu_domain *release_domain;
+	struct iommu_domain *default_domain;
+	u8 user_pasid_table:1;
 };
 
 /**
@@ -298,51 +727,54 @@ struct iommu_ops {
  * * EBUSY	- device is attached to a domain and cannot be changed
  * * ENODEV	- device specific errors, not able to be attached
  * * <others>	- treated as ENODEV by the caller. Use is discouraged
- * @set_dev_pasid: set an iommu domain to a pasid of device
- * @map: map a physically contiguous memory region to an iommu domain
+ * @set_dev_pasid: set or replace an iommu domain to a pasid of device. The pasid of
+ *                 the device should be left in the old config in error case.
  * @map_pages: map a physically contiguous set of pages of the same size to
  *             an iommu domain.
- * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @unmap_pages: unmap a number of pages of the same size from an iommu domain
  * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
+ * @cache_invalidate_user: Flush hardware cache for user space IO page table.
+ *                         The @domain must be IOMMU_DOMAIN_NESTED. The @array
+ *                         passes in the cache invalidation requests, in form
+ *                         of a driver data structure. The driver must update
+ *                         array->entry_num to report the number of handled
+ *                         invalidation requests. The driver data structure
+ *                         must be defined in include/uapi/linux/iommufd.h
  * @iova_to_phys: translate iova to physical address
  * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE,
  *                           including no-snoop TLPs on PCIe or other platform
  *                           specific mechanisms.
- * @enable_nesting: Enable nesting
  * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*)
  * @free: Release the domain after use.
  */
 struct iommu_domain_ops {
-	int (*attach_dev)(struct iommu_domain *domain, struct device *dev);
+	int (*attach_dev)(struct iommu_domain *domain, struct device *dev,
+			  struct iommu_domain *old);
 	int (*set_dev_pasid)(struct iommu_domain *domain, struct device *dev,
-			     ioasid_t pasid);
+			     ioasid_t pasid, struct iommu_domain *old);
 
-	int (*map)(struct iommu_domain *domain, unsigned long iova,
-		   phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
 	int (*map_pages)(struct iommu_domain *domain, unsigned long iova,
 			 phys_addr_t paddr, size_t pgsize, size_t pgcount,
 			 int prot, gfp_t gfp, size_t *mapped);
-	size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
-			size_t size, struct iommu_iotlb_gather *iotlb_gather);
 	size_t (*unmap_pages)(struct iommu_domain *domain, unsigned long iova,
 			      size_t pgsize, size_t pgcount,
 			      struct iommu_iotlb_gather *iotlb_gather);
 
 	void (*flush_iotlb_all)(struct iommu_domain *domain);
-	void (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
-			       size_t size);
+	int (*iotlb_sync_map)(struct iommu_domain *domain, unsigned long iova,
+			      size_t size);
 	void (*iotlb_sync)(struct iommu_domain *domain,
 			   struct iommu_iotlb_gather *iotlb_gather);
+	int (*cache_invalidate_user)(struct iommu_domain *domain,
+				     struct iommu_user_data_array *array);
 
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    dma_addr_t iova);
 
 	bool (*enforce_cache_coherency)(struct iommu_domain *domain);
-	int (*enable_nesting)(struct iommu_domain *domain);
 	int (*set_pgtable_quirks)(struct iommu_domain *domain,
 				  unsigned long quirks);
 
@@ -355,67 +787,72 @@ struct iommu_domain_ops {
  * @list: Used by the iommu-core to keep a list of registered iommus
  * @ops: iommu-ops for talking to this iommu
  * @dev: struct device for sysfs handling
+ * @singleton_group: Used internally for drivers that have only one group
  * @max_pasids: number of supported PASIDs
+ * @ready: set once iommu_device_register() has completed successfully
  */
 struct iommu_device {
 	struct list_head list;
 	const struct iommu_ops *ops;
 	struct fwnode_handle *fwnode;
 	struct device *dev;
+	struct iommu_group *singleton_group;
 	u32 max_pasids;
-};
-
-/**
- * struct iommu_fault_event - Generic fault event
- *
- * Can represent recoverable faults such as a page requests or
- * unrecoverable faults such as DMA or IRQ remapping faults.
- *
- * @fault: fault descriptor
- * @list: pending fault event list, used for tracking responses
- */
-struct iommu_fault_event {
-	struct iommu_fault fault;
-	struct list_head list;
+	bool ready;
 };
 
 /**
  * struct iommu_fault_param - per-device IOMMU fault data
- * @handler: Callback function to handle IOMMU faults at device level
- * @data: handler private data
- * @faults: holds the pending faults which needs response
  * @lock: protect pending faults list
+ * @users: user counter to manage the lifetime of the data
+ * @rcu: rcu head for kfree_rcu()
+ * @dev: the device that owns this param
+ * @queue: IOPF queue
+ * @queue_list: index into queue->devices
+ * @partial: faults that are part of a Page Request Group for which the last
+ *           request hasn't been submitted yet.
+ * @faults: holds the pending faults which need response
  */
 struct iommu_fault_param {
-	iommu_dev_fault_handler_t handler;
-	void *data;
-	struct list_head faults;
 	struct mutex lock;
+	refcount_t users;
+	struct rcu_head rcu;
+
+	struct device *dev;
+	struct iopf_queue *queue;
+	struct list_head queue_list;
+
+	struct list_head partial;
+	struct list_head faults;
 };
 
 /**
  * struct dev_iommu - Collection of per-device IOMMU data
  *
  * @fault_param: IOMMU detected device fault reporting data
- * @iopf_param:	 I/O Page Fault queue and data
  * @fwspec:	 IOMMU fwspec data
  * @iommu_dev:	 IOMMU device this device is linked to
  * @priv:	 IOMMU Driver private data
  * @max_pasids:  number of PASIDs this device can consume
  * @attach_deferred: the dma domain attachment is deferred
+ * @pci_32bit_workaround: Limit DMA allocations to 32-bit IOVAs
+ * @require_direct: device requires IOMMU_RESV_DIRECT regions
+ * @shadow_on_flush: IOTLB flushes are used to sync shadow tables
  *
  * TODO: migrate other per device data pointers under iommu_dev_data, e.g.
  *	struct iommu_group	*iommu_group;
  */
 struct dev_iommu {
 	struct mutex lock;
-	struct iommu_fault_param	*fault_param;
-	struct iopf_device_param	*iopf_param;
+	struct iommu_fault_param __rcu	*fault_param;
 	struct iommu_fwspec		*fwspec;
 	struct iommu_device		*iommu_dev;
 	void				*priv;
 	u32				max_pasids;
 	u32				attach_deferred:1;
+	u32				pci_32bit_workaround:1;
+	u32				require_direct:1;
+	u32				shadow_on_flush:1;
 };
 
 int iommu_device_register(struct iommu_device *iommu,
@@ -436,41 +873,50 @@ static inline struct iommu_device *dev_to_iommu_device(struct device *dev)
 	return (struct iommu_device *)dev_get_drvdata(dev);
 }
 
+/**
+ * iommu_get_iommu_dev - Get iommu_device for a device
+ * @dev: an end-point device
+ *
+ * Note that this function must be called from the iommu_ops
+ * to retrieve the iommu_device for a device, which the core code
+ * guarentees it will not invoke the op without an attached iommu.
+ */
+static inline struct iommu_device *__iommu_get_iommu_dev(struct device *dev)
+{
+	return dev->iommu->iommu_dev;
+}
+
+#define iommu_get_iommu_dev(dev, type, member) \
+	container_of(__iommu_get_iommu_dev(dev), type, member)
+
 static inline void iommu_iotlb_gather_init(struct iommu_iotlb_gather *gather)
 {
 	*gather = (struct iommu_iotlb_gather) {
 		.start	= ULONG_MAX,
-		.freelist = LIST_HEAD_INIT(gather->freelist),
+		.freelist = IOMMU_PAGES_LIST_INIT(gather->freelist),
 	};
 }
 
-static inline const struct iommu_ops *dev_iommu_ops(struct device *dev)
-{
-	/*
-	 * Assume that valid ops must be installed if iommu_probe_device()
-	 * has succeeded. The device ops are essentially for internal use
-	 * within the IOMMU subsystem itself, so we should be able to trust
-	 * ourselves not to misuse the helper.
-	 */
-	return dev->iommu->iommu_dev->ops;
-}
-
-extern int bus_iommu_probe(const struct bus_type *bus);
-extern bool iommu_present(const struct bus_type *bus);
 extern bool device_iommu_capable(struct device *dev, enum iommu_cap cap);
 extern bool iommu_group_has_isolated_msi(struct iommu_group *group);
-extern struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus);
+struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev, unsigned int flags);
+static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)
+{
+	return iommu_paging_domain_alloc_flags(dev, 0);
+}
 extern void iommu_domain_free(struct iommu_domain *domain);
 extern int iommu_attach_device(struct iommu_domain *domain,
 			       struct device *dev);
 extern void iommu_detach_device(struct iommu_domain *domain,
 				struct device *dev);
-extern int iommu_sva_unbind_gpasid(struct iommu_domain *domain,
-				   struct device *dev, ioasid_t pasid);
 extern struct iommu_domain *iommu_get_domain_for_dev(struct device *dev);
 extern struct iommu_domain *iommu_get_dma_domain(struct device *dev);
 extern int iommu_map(struct iommu_domain *domain, unsigned long iova,
 		     phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+int iommu_map_nosync(struct iommu_domain *domain, unsigned long iova,
+		phys_addr_t paddr, size_t size, int prot, gfp_t gfp);
+int iommu_sync_map(struct iommu_domain *domain, unsigned long iova,
+		size_t size);
 extern size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova,
 			  size_t size);
 extern size_t iommu_unmap_fast(struct iommu_domain *domain,
@@ -512,21 +958,10 @@ extern int iommu_group_for_each_dev(struct iommu_group *group, void *data,
 extern struct iommu_group *iommu_group_get(struct device *dev);
 extern struct iommu_group *iommu_group_ref_get(struct iommu_group *group);
 extern void iommu_group_put(struct iommu_group *group);
-extern int iommu_register_device_fault_handler(struct device *dev,
-					iommu_dev_fault_handler_t handler,
-					void *data);
-
-extern int iommu_unregister_device_fault_handler(struct device *dev);
-
-extern int iommu_report_device_fault(struct device *dev,
-				     struct iommu_fault_event *evt);
-extern int iommu_page_response(struct device *dev,
-			       struct iommu_page_response *msg);
 
 extern int iommu_group_id(struct iommu_group *group);
 extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *);
 
-int iommu_enable_nesting(struct iommu_domain *domain);
 int iommu_set_pgtable_quirks(struct iommu_domain *domain,
 		unsigned long quirks);
 
@@ -626,16 +1061,38 @@ static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather)
 	return gather && gather->queued;
 }
 
+static inline void iommu_dirty_bitmap_init(struct iommu_dirty_bitmap *dirty,
+					   struct iova_bitmap *bitmap,
+					   struct iommu_iotlb_gather *gather)
+{
+	if (gather)
+		iommu_iotlb_gather_init(gather);
+
+	dirty->bitmap = bitmap;
+	dirty->gather = gather;
+}
+
+static inline void iommu_dirty_bitmap_record(struct iommu_dirty_bitmap *dirty,
+					     unsigned long iova,
+					     unsigned long length)
+{
+	if (dirty->bitmap)
+		iova_bitmap_set(dirty->bitmap, iova, length);
+
+	if (dirty->gather)
+		iommu_iotlb_gather_add_range(dirty->gather, iova, length);
+}
+
 /* PCI device grouping function */
 extern struct iommu_group *pci_device_group(struct device *dev);
 /* Generic device grouping function */
 extern struct iommu_group *generic_device_group(struct device *dev);
 /* FSL-MC device grouping function */
 struct iommu_group *fsl_mc_device_group(struct device *dev);
+extern struct iommu_group *generic_single_device_group(struct device *dev);
 
 /**
  * struct iommu_fwspec - per-device IOMMU instance data
- * @ops: ops for this device's IOMMU
  * @iommu_fwnode: firmware handle for this device's IOMMU
  * @flags: IOMMU_FWSPEC_* flags
  * @num_ids: number of associated device IDs
@@ -646,7 +1103,6 @@ struct iommu_group *fsl_mc_device_group(struct device *dev);
  * consumers.
  */
 struct iommu_fwspec {
-	const struct iommu_ops	*ops;
 	struct fwnode_handle	*iommu_fwnode;
 	u32			flags;
 	unsigned int		num_ids;
@@ -655,20 +1111,37 @@ struct iommu_fwspec {
 
 /* ATS is supported */
 #define IOMMU_FWSPEC_PCI_RC_ATS			(1 << 0)
+/* CANWBS is supported */
+#define IOMMU_FWSPEC_PCI_RC_CANWBS		(1 << 1)
+
+/*
+ * An iommu attach handle represents a relationship between an iommu domain
+ * and a PASID or RID of a device. It is allocated and managed by the component
+ * that manages the domain and is stored in the iommu group during the time the
+ * domain is attached.
+ */
+struct iommu_attach_handle {
+	struct iommu_domain		*domain;
+};
 
 /**
  * struct iommu_sva - handle to a device-mm bond
  */
 struct iommu_sva {
+	struct iommu_attach_handle	handle;
 	struct device			*dev;
-	struct iommu_domain		*domain;
+	refcount_t			users;
+};
+
+struct iommu_mm_data {
+	u32			pasid;
+	struct mm_struct	*mm;
+	struct list_head	sva_domains;
+	struct list_head	mm_list_elm;
 };
 
-int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode,
-		      const struct iommu_ops *ops);
-void iommu_fwspec_free(struct device *dev);
-int iommu_fwspec_add_ids(struct device *dev, u32 *ids, int num_ids);
-const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode);
+int iommu_fwspec_init(struct device *dev, struct fwnode_handle *iommu_fwnode);
+int iommu_fwspec_add_ids(struct device *dev, const u32 *ids, int num_ids);
 
 static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 {
@@ -692,16 +1165,11 @@ static inline void *dev_iommu_priv_get(struct device *dev)
 		return NULL;
 }
 
-static inline void dev_iommu_priv_set(struct device *dev, void *priv)
-{
-	dev->iommu->priv = priv;
-}
+void dev_iommu_priv_set(struct device *dev, void *priv);
 
+extern struct mutex iommu_probe_device_lock;
 int iommu_probe_device(struct device *dev);
 
-int iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features f);
-int iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features f);
-
 int iommu_device_use_default_domain(struct device *dev);
 void iommu_device_unuse_default_domain(struct device *dev);
 
@@ -712,15 +1180,13 @@ bool iommu_group_dma_owner_claimed(struct iommu_group *group);
 int iommu_device_claim_dma_owner(struct device *dev, void *owner);
 void iommu_device_release_dma_owner(struct device *dev);
 
-struct iommu_domain *iommu_sva_domain_alloc(struct device *dev,
-					    struct mm_struct *mm);
 int iommu_attach_device_pasid(struct iommu_domain *domain,
-			      struct device *dev, ioasid_t pasid);
+			      struct device *dev, ioasid_t pasid,
+			      struct iommu_attach_handle *handle);
 void iommu_detach_device_pasid(struct iommu_domain *domain,
 			       struct device *dev, ioasid_t pasid);
-struct iommu_domain *
-iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
-			       unsigned int type);
+ioasid_t iommu_alloc_global_pasid(struct device *dev);
+void iommu_free_global_pasid(ioasid_t pasid);
 #else /* CONFIG_IOMMU_API */
 
 struct iommu_ops {};
@@ -729,20 +1195,23 @@ struct iommu_fwspec {};
 struct iommu_device {};
 struct iommu_fault_param {};
 struct iommu_iotlb_gather {};
+struct iommu_dirty_bitmap {};
+struct iommu_dirty_ops {};
 
-static inline bool iommu_present(const struct bus_type *bus)
+static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
 {
 	return false;
 }
 
-static inline bool device_iommu_capable(struct device *dev, enum iommu_cap cap)
+static inline struct iommu_domain *iommu_paging_domain_alloc_flags(struct device *dev,
+						     unsigned int flags)
 {
-	return false;
+	return ERR_PTR(-ENODEV);
 }
 
-static inline struct iommu_domain *iommu_domain_alloc(const struct bus_type *bus)
+static inline struct iommu_domain *iommu_paging_domain_alloc(struct device *dev)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline void iommu_domain_free(struct iommu_domain *domain)
@@ -898,31 +1367,6 @@ static inline void iommu_group_put(struct iommu_group *group)
 {
 }
 
-static inline
-int iommu_register_device_fault_handler(struct device *dev,
-					iommu_dev_fault_handler_t handler,
-					void *data)
-{
-	return -ENODEV;
-}
-
-static inline int iommu_unregister_device_fault_handler(struct device *dev)
-{
-	return 0;
-}
-
-static inline
-int iommu_report_device_fault(struct device *dev, struct iommu_fault_event *evt)
-{
-	return -ENODEV;
-}
-
-static inline int iommu_page_response(struct device *dev,
-				      struct iommu_page_response *msg)
-{
-	return -ENODEV;
-}
-
 static inline int iommu_group_id(struct iommu_group *group)
 {
 	return -ENODEV;
@@ -961,6 +1405,18 @@ static inline bool iommu_iotlb_gather_queued(struct iommu_iotlb_gather *gather)
 	return false;
 }
 
+static inline void iommu_dirty_bitmap_init(struct iommu_dirty_bitmap *dirty,
+					   struct iova_bitmap *bitmap,
+					   struct iommu_iotlb_gather *gather)
+{
+}
+
+static inline void iommu_dirty_bitmap_record(struct iommu_dirty_bitmap *dirty,
+					     unsigned long iova,
+					     unsigned long length)
+{
+}
+
 static inline void iommu_device_unregister(struct iommu_device *iommu)
 {
 }
@@ -987,40 +1443,17 @@ static inline void iommu_device_unlink(struct device *dev, struct device *link)
 }
 
 static inline int iommu_fwspec_init(struct device *dev,
-				    struct fwnode_handle *iommu_fwnode,
-				    const struct iommu_ops *ops)
+				    struct fwnode_handle *iommu_fwnode)
 {
 	return -ENODEV;
 }
 
-static inline void iommu_fwspec_free(struct device *dev)
-{
-}
-
 static inline int iommu_fwspec_add_ids(struct device *dev, u32 *ids,
 				       int num_ids)
 {
 	return -ENODEV;
 }
 
-static inline
-const struct iommu_ops *iommu_ops_from_fwnode(struct fwnode_handle *fwnode)
-{
-	return NULL;
-}
-
-static inline int
-iommu_dev_enable_feature(struct device *dev, enum iommu_dev_features feat)
-{
-	return -ENODEV;
-}
-
-static inline int
-iommu_dev_disable_feature(struct device *dev, enum iommu_dev_features feat)
-{
-	return -ENODEV;
-}
-
 static inline struct iommu_fwspec *dev_iommu_fwspec_get(struct device *dev)
 {
 	return NULL;
@@ -1059,14 +1492,9 @@ static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner)
 	return -ENODEV;
 }
 
-static inline struct iommu_domain *
-iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm)
-{
-	return NULL;
-}
-
 static inline int iommu_attach_device_pasid(struct iommu_domain *domain,
-					    struct device *dev, ioasid_t pasid)
+					    struct device *dev, ioasid_t pasid,
+					    struct iommu_attach_handle *handle)
 {
 	return -ENODEV;
 }
@@ -1076,13 +1504,33 @@ static inline void iommu_detach_device_pasid(struct iommu_domain *domain,
 {
 }
 
-static inline struct iommu_domain *
-iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
-			       unsigned int type)
+static inline ioasid_t iommu_alloc_global_pasid(struct device *dev)
 {
-	return NULL;
+	return IOMMU_PASID_INVALID;
+}
+
+static inline void iommu_free_global_pasid(ioasid_t pasid) {}
+#endif /* CONFIG_IOMMU_API */
+
+#ifdef CONFIG_IRQ_MSI_IOMMU
+#ifdef CONFIG_IOMMU_API
+int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr);
+#else
+static inline int iommu_dma_prepare_msi(struct msi_desc *desc,
+					phys_addr_t msi_addr)
+{
+	return 0;
 }
 #endif /* CONFIG_IOMMU_API */
+#endif /* CONFIG_IRQ_MSI_IOMMU */
+
+#if IS_ENABLED(CONFIG_LOCKDEP) && IS_ENABLED(CONFIG_IOMMU_API)
+void iommu_group_mutex_assert(struct device *dev);
+#else
+static inline void iommu_group_mutex_assert(struct device *dev)
+{
+}
+#endif
 
 /**
  * iommu_map_sgtable - Map the given buffer to the IOMMU domain
@@ -1094,7 +1542,7 @@ iommu_get_domain_for_dev_pasid(struct device *dev, ioasid_t pasid,
  * Creates a mapping at @iova for the buffer described by a scatterlist
  * stored in the given sg_table object in the provided IOMMU domain.
  */
-static inline size_t iommu_map_sgtable(struct iommu_domain *domain,
+static inline ssize_t iommu_map_sgtable(struct iommu_domain *domain,
 			unsigned long iova, struct sg_table *sgt, int prot)
 {
 	return iommu_map_sg(domain, iova, sgt->sgl, sgt->orig_nents, prot,
@@ -1109,39 +1557,12 @@ static inline void iommu_debugfs_setup(void) {}
 #endif
 
 #ifdef CONFIG_IOMMU_DMA
-#include <linux/msi.h>
-
-/* Setup call for arch DMA mapping code */
-void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit);
-
 int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base);
-
-int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr);
-void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg);
-
 #else /* CONFIG_IOMMU_DMA */
-
-struct msi_desc;
-struct msi_msg;
-
-static inline void iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 dma_limit)
-{
-}
-
 static inline int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
 {
 	return -ENODEV;
 }
-
-static inline int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
-{
-	return 0;
-}
-
-static inline void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
-{
-}
-
 #endif	/* CONFIG_IOMMU_DMA */
 
 /*
@@ -1165,25 +1586,44 @@ static inline bool tegra_dev_iommu_get_stream_id(struct device *dev, u32 *stream
 	return false;
 }
 
-#ifdef CONFIG_IOMMU_SVA
+#ifdef CONFIG_IOMMU_MM_DATA
 static inline void mm_pasid_init(struct mm_struct *mm)
 {
-	mm->pasid = IOMMU_PASID_INVALID;
+	/*
+	 * During dup_mm(), a new mm will be memcpy'd from an old one and that makes
+	 * the new mm and the old one point to a same iommu_mm instance. When either
+	 * one of the two mms gets released, the iommu_mm instance is freed, leaving
+	 * the other mm running into a use-after-free/double-free problem. To avoid
+	 * the problem, zeroing the iommu_mm pointer of a new mm is needed here.
+	 */
+	mm->iommu_mm = NULL;
 }
+
 static inline bool mm_valid_pasid(struct mm_struct *mm)
 {
-	return mm->pasid != IOMMU_PASID_INVALID;
+	return READ_ONCE(mm->iommu_mm);
+}
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	struct iommu_mm_data *iommu_mm = READ_ONCE(mm->iommu_mm);
+
+	if (!iommu_mm)
+		return IOMMU_PASID_INVALID;
+	return iommu_mm->pasid;
 }
+
 void mm_pasid_drop(struct mm_struct *mm);
 struct iommu_sva *iommu_sva_bind_device(struct device *dev,
 					struct mm_struct *mm);
 void iommu_sva_unbind_device(struct iommu_sva *handle);
 u32 iommu_sva_get_pasid(struct iommu_sva *handle);
+void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end);
 #else
 static inline struct iommu_sva *
 iommu_sva_bind_device(struct device *dev, struct mm_struct *mm)
 {
-	return NULL;
+	return ERR_PTR(-ENODEV);
 }
 
 static inline void iommu_sva_unbind_device(struct iommu_sva *handle)
@@ -1196,7 +1636,71 @@ static inline u32 iommu_sva_get_pasid(struct iommu_sva *handle)
 }
 static inline void mm_pasid_init(struct mm_struct *mm) {}
 static inline bool mm_valid_pasid(struct mm_struct *mm) { return false; }
+
+static inline u32 mm_get_enqcmd_pasid(struct mm_struct *mm)
+{
+	return IOMMU_PASID_INVALID;
+}
+
 static inline void mm_pasid_drop(struct mm_struct *mm) {}
+static inline void iommu_sva_invalidate_kva_range(unsigned long start, unsigned long end) {}
 #endif /* CONFIG_IOMMU_SVA */
 
+#ifdef CONFIG_IOMMU_IOPF
+int iopf_queue_add_device(struct iopf_queue *queue, struct device *dev);
+void iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev);
+int iopf_queue_flush_dev(struct device *dev);
+struct iopf_queue *iopf_queue_alloc(const char *name);
+void iopf_queue_free(struct iopf_queue *queue);
+int iopf_queue_discard_partial(struct iopf_queue *queue);
+void iopf_free_group(struct iopf_group *group);
+int iommu_report_device_fault(struct device *dev, struct iopf_fault *evt);
+void iopf_group_response(struct iopf_group *group,
+			 enum iommu_page_response_code status);
+#else
+static inline int
+iopf_queue_add_device(struct iopf_queue *queue, struct device *dev)
+{
+	return -ENODEV;
+}
+
+static inline void
+iopf_queue_remove_device(struct iopf_queue *queue, struct device *dev)
+{
+}
+
+static inline int iopf_queue_flush_dev(struct device *dev)
+{
+	return -ENODEV;
+}
+
+static inline struct iopf_queue *iopf_queue_alloc(const char *name)
+{
+	return NULL;
+}
+
+static inline void iopf_queue_free(struct iopf_queue *queue)
+{
+}
+
+static inline int iopf_queue_discard_partial(struct iopf_queue *queue)
+{
+	return -ENODEV;
+}
+
+static inline void iopf_free_group(struct iopf_group *group)
+{
+}
+
+static inline int
+iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
+{
+	return -ENODEV;
+}
+
+static inline void iopf_group_response(struct iopf_group *group,
+				       enum iommu_page_response_code status)
+{
+}
+#endif /* CONFIG_IOMMU_IOPF */
 #endif /* __LINUX_IOMMU_H */
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 1129a36a74c4..6e7efe83bc5d 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -6,23 +6,70 @@
 #ifndef __LINUX_IOMMUFD_H
 #define __LINUX_IOMMUFD_H
 
-#include <linux/types.h>
-#include <linux/errno.h>
 #include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/iommu.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+#include <linux/xarray.h>
+#include <uapi/linux/iommufd.h>
 
 struct device;
+struct file;
+struct iommu_group;
+struct iommu_user_data;
+struct iommu_user_data_array;
+struct iommufd_access;
+struct iommufd_ctx;
 struct iommufd_device;
+struct iommufd_viommu_ops;
 struct page;
-struct iommufd_ctx;
-struct iommufd_access;
-struct file;
+
+enum iommufd_object_type {
+	IOMMUFD_OBJ_NONE,
+	IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE,
+	IOMMUFD_OBJ_DEVICE,
+	IOMMUFD_OBJ_HWPT_PAGING,
+	IOMMUFD_OBJ_HWPT_NESTED,
+	IOMMUFD_OBJ_IOAS,
+	IOMMUFD_OBJ_ACCESS,
+	IOMMUFD_OBJ_FAULT,
+	IOMMUFD_OBJ_VIOMMU,
+	IOMMUFD_OBJ_VDEVICE,
+	IOMMUFD_OBJ_VEVENTQ,
+	IOMMUFD_OBJ_HW_QUEUE,
+#ifdef CONFIG_IOMMUFD_TEST
+	IOMMUFD_OBJ_SELFTEST,
+#endif
+	IOMMUFD_OBJ_MAX,
+};
+
+/* Base struct for all objects with a userspace ID handle. */
+struct iommufd_object {
+	/*
+	 * Destroy will sleep and wait for wait_cnt to go to zero. This allows
+	 * concurrent users of the ID to reliably avoid causing a spurious
+	 * destroy failure. Incrementing this count should either be short
+	 * lived or be revoked and blocked during pre_destroy().
+	 */
+	refcount_t wait_cnt;
+	refcount_t users;
+	enum iommufd_object_type type;
+	unsigned int id;
+};
 
 struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx,
 					   struct device *dev, u32 *id);
 void iommufd_device_unbind(struct iommufd_device *idev);
 
-int iommufd_device_attach(struct iommufd_device *idev, u32 *pt_id);
-void iommufd_device_detach(struct iommufd_device *idev);
+int iommufd_device_attach(struct iommufd_device *idev, ioasid_t pasid,
+			  u32 *pt_id);
+int iommufd_device_replace(struct iommufd_device *idev, ioasid_t pasid,
+			   u32 *pt_id);
+void iommufd_device_detach(struct iommufd_device *idev, ioasid_t pasid);
+
+struct iommufd_ctx *iommufd_device_to_ictx(struct iommufd_device *idev);
+u32 iommufd_device_to_id(struct iommufd_device *idev);
 
 struct iommufd_access_ops {
 	u8 needs_pin_pages : 1;
@@ -44,12 +91,117 @@ iommufd_access_create(struct iommufd_ctx *ictx,
 		      const struct iommufd_access_ops *ops, void *data, u32 *id);
 void iommufd_access_destroy(struct iommufd_access *access);
 int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id);
+int iommufd_access_replace(struct iommufd_access *access, u32 ioas_id);
+void iommufd_access_detach(struct iommufd_access *access);
 
 void iommufd_ctx_get(struct iommufd_ctx *ictx);
 
+struct iommufd_viommu {
+	struct iommufd_object obj;
+	struct iommufd_ctx *ictx;
+	struct iommu_device *iommu_dev;
+	struct iommufd_hwpt_paging *hwpt;
+
+	const struct iommufd_viommu_ops *ops;
+
+	struct xarray vdevs;
+	struct list_head veventqs;
+	struct rw_semaphore veventqs_rwsem;
+
+	enum iommu_viommu_type type;
+};
+
+struct iommufd_vdevice {
+	struct iommufd_object obj;
+	struct iommufd_viommu *viommu;
+	struct iommufd_device *idev;
+
+	/*
+	 * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of
+	 * AMD IOMMU, and vRID of Intel VT-d
+	 */
+	u64 virt_id;
+
+	/* Clean up all driver-specific parts of an iommufd_vdevice */
+	void (*destroy)(struct iommufd_vdevice *vdev);
+};
+
+struct iommufd_hw_queue {
+	struct iommufd_object obj;
+	struct iommufd_viommu *viommu;
+	struct iommufd_access *access;
+
+	u64 base_addr; /* in guest physical address space */
+	size_t length;
+
+	enum iommu_hw_queue_type type;
+
+	/* Clean up all driver-specific parts of an iommufd_hw_queue */
+	void (*destroy)(struct iommufd_hw_queue *hw_queue);
+};
+
+/**
+ * struct iommufd_viommu_ops - vIOMMU specific operations
+ * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory
+ *           of the vIOMMU will be free-ed by iommufd core after calling this op
+ * @alloc_domain_nested: Allocate a IOMMU_DOMAIN_NESTED on a vIOMMU that holds a
+ *                       nesting parent domain (IOMMU_DOMAIN_PAGING). @user_data
+ *                       must be defined in include/uapi/linux/iommufd.h.
+ *                       It must fully initialize the new iommu_domain before
+ *                       returning. Upon failure, ERR_PTR must be returned.
+ * @cache_invalidate: Flush hardware cache used by a vIOMMU. It can be used for
+ *                    any IOMMU hardware specific cache: TLB and device cache.
+ *                    The @array passes in the cache invalidation requests, in
+ *                    form of a driver data structure. A driver must update the
+ *                    array->entry_num to report the number of handled requests.
+ *                    The data structure of the array entry must be defined in
+ *                    include/uapi/linux/iommufd.h
+ * @vdevice_size: Size of the driver-defined vDEVICE structure per this vIOMMU
+ * @vdevice_init: Initialize the driver-level structure of a vDEVICE object, or
+ *                related HW procedure. @vdev is already initialized by iommufd
+ *                core: vdev->dev and vdev->viommu pointers; vdev->id carries a
+ *                per-vIOMMU virtual ID (refer to struct iommu_vdevice_alloc in
+ *                include/uapi/linux/iommufd.h)
+ *                If driver has a deinit function to revert what vdevice_init op
+ *                does, it should set it to the @vdev->destroy function pointer
+ * @get_hw_queue_size: Get the size of a driver-defined HW queue structure for a
+ *                     given @viommu corresponding to @queue_type. Driver should
+ *                     return 0 if HW queue aren't supported accordingly. It is
+ *                     required for driver to use the HW_QUEUE_STRUCT_SIZE macro
+ *                     to sanitize the driver-level HW queue structure related
+ *                     to the core one
+ * @hw_queue_init_phys: Initialize the driver-level structure of a HW queue that
+ *                      is initialized with its core-level structure that holds
+ *                      all the info about a guest queue memory.
+ *                      Driver providing this op indicates that HW accesses the
+ *                      guest queue memory via physical addresses.
+ *                      @index carries the logical HW QUEUE ID per vIOMMU in a
+ *                      guest VM, for a multi-queue model. @base_addr_pa carries
+ *                      the physical location of the guest queue
+ *                      If driver has a deinit function to revert what this op
+ *                      does, it should set it to the @hw_queue->destroy pointer
+ */
+struct iommufd_viommu_ops {
+	void (*destroy)(struct iommufd_viommu *viommu);
+	struct iommu_domain *(*alloc_domain_nested)(
+		struct iommufd_viommu *viommu, u32 flags,
+		const struct iommu_user_data *user_data);
+	int (*cache_invalidate)(struct iommufd_viommu *viommu,
+				struct iommu_user_data_array *array);
+	const size_t vdevice_size;
+	int (*vdevice_init)(struct iommufd_vdevice *vdev);
+	size_t (*get_hw_queue_size)(struct iommufd_viommu *viommu,
+				    enum iommu_hw_queue_type queue_type);
+	/* AMD's HW will add hw_queue_init simply using @hw_queue->base_addr */
+	int (*hw_queue_init_phys)(struct iommufd_hw_queue *hw_queue, u32 index,
+				  phys_addr_t base_addr_pa);
+};
+
 #if IS_ENABLED(CONFIG_IOMMUFD)
 struct iommufd_ctx *iommufd_ctx_from_file(struct file *file);
+struct iommufd_ctx *iommufd_ctx_from_fd(int fd);
 void iommufd_ctx_put(struct iommufd_ctx *ictx);
+bool iommufd_ctx_has_group(struct iommufd_ctx *ictx, struct iommu_group *group);
 
 int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
 			     unsigned long length, struct page **out_pages,
@@ -86,8 +238,9 @@ static inline void iommufd_access_unpin_pages(struct iommufd_access *access,
 {
 }
 
-static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
-		      void *data, size_t len, unsigned int flags)
+static inline int iommufd_access_rw(struct iommufd_access *access,
+				    unsigned long iova, void *data, size_t len,
+				    unsigned int flags)
 {
 	return -EOPNOTSUPP;
 }
@@ -102,4 +255,146 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx)
 	return -EOPNOTSUPP;
 }
 #endif /* CONFIG_IOMMUFD */
+
+#if IS_ENABLED(CONFIG_IOMMUFD_DRIVER_CORE)
+int _iommufd_object_depend(struct iommufd_object *obj_dependent,
+			   struct iommufd_object *obj_depended);
+void _iommufd_object_undepend(struct iommufd_object *obj_dependent,
+			      struct iommufd_object *obj_depended);
+int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner,
+			phys_addr_t mmio_addr, size_t length,
+			unsigned long *offset);
+void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
+			   struct iommufd_object *owner, unsigned long offset);
+struct device *iommufd_vdevice_to_device(struct iommufd_vdevice *vdev);
+struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
+				       unsigned long vdev_id);
+int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
+			       struct device *dev, unsigned long *vdev_id);
+int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
+				enum iommu_veventq_type type, void *event_data,
+				size_t data_len);
+#else /* !CONFIG_IOMMUFD_DRIVER_CORE */
+static inline int _iommufd_object_depend(struct iommufd_object *obj_dependent,
+					 struct iommufd_object *obj_depended)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+_iommufd_object_undepend(struct iommufd_object *obj_dependent,
+			 struct iommufd_object *obj_depended)
+{
+}
+
+static inline int _iommufd_alloc_mmap(struct iommufd_ctx *ictx,
+				      struct iommufd_object *owner,
+				      phys_addr_t mmio_addr, size_t length,
+				      unsigned long *offset)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
+					 struct iommufd_object *owner,
+					 unsigned long offset)
+{
+}
+
+static inline struct device *
+iommufd_vdevice_to_device(struct iommufd_vdevice *vdev)
+{
+	return NULL;
+}
+
+static inline struct device *
+iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
+{
+	return NULL;
+}
+
+static inline int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
+					     struct device *dev,
+					     unsigned long *vdev_id)
+{
+	return -ENOENT;
+}
+
+static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
+					      enum iommu_veventq_type type,
+					      void *event_data, size_t data_len)
+{
+	return -EOPNOTSUPP;
+}
+#endif /* CONFIG_IOMMUFD_DRIVER_CORE */
+
+#define VIOMMU_STRUCT_SIZE(drv_struct, member)                                 \
+	(sizeof(drv_struct) +                                                  \
+	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
+	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_viommu,                 \
+					((drv_struct *)NULL)->member)))
+
+#define VDEVICE_STRUCT_SIZE(drv_struct, member)                                \
+	(sizeof(drv_struct) +                                                  \
+	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
+	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_vdevice,                \
+					((drv_struct *)NULL)->member)))
+
+#define HW_QUEUE_STRUCT_SIZE(drv_struct, member)                               \
+	(sizeof(drv_struct) +                                                  \
+	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
+	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_hw_queue,               \
+					((drv_struct *)NULL)->member)))
+
+/*
+ * Helpers for IOMMU driver to build/destroy a dependency between two sibling
+ * structures created by one of the allocators above
+ */
+#define iommufd_hw_queue_depend(dependent, depended, member)                   \
+	({                                                                     \
+		int ret = -EINVAL;                                             \
+									       \
+		static_assert(__same_type(struct iommufd_hw_queue,             \
+					  dependent->member));                 \
+		static_assert(__same_type(typeof(*dependent), *depended));     \
+		if (!WARN_ON_ONCE(dependent->member.viommu !=                  \
+				  depended->member.viommu))                    \
+			ret = _iommufd_object_depend(&dependent->member.obj,   \
+						     &depended->member.obj);   \
+		ret;                                                           \
+	})
+
+#define iommufd_hw_queue_undepend(dependent, depended, member)                 \
+	({                                                                     \
+		static_assert(__same_type(struct iommufd_hw_queue,             \
+					  dependent->member));                 \
+		static_assert(__same_type(typeof(*dependent), *depended));     \
+		WARN_ON_ONCE(dependent->member.viommu !=                       \
+			     depended->member.viommu);                         \
+		_iommufd_object_undepend(&dependent->member.obj,               \
+					 &depended->member.obj);               \
+	})
+
+/*
+ * Helpers for IOMMU driver to alloc/destroy an mmapable area for a structure.
+ *
+ * To support an mmappable MMIO region, kernel driver must first register it to
+ * iommufd core to allocate an @offset, during a driver-structure initialization
+ * (e.g. viommu_init op). Then, it should report to user space this @offset and
+ * the @length of the MMIO region for mmap syscall.
+ */
+static inline int iommufd_viommu_alloc_mmap(struct iommufd_viommu *viommu,
+					    phys_addr_t mmio_addr,
+					    size_t length,
+					    unsigned long *offset)
+{
+	return _iommufd_alloc_mmap(viommu->ictx, &viommu->obj, mmio_addr,
+				   length, offset);
+}
+
+static inline void iommufd_viommu_destroy_mmap(struct iommufd_viommu *viommu,
+					       unsigned long offset)
+{
+	_iommufd_destroy_mmap(viommu->ictx, &viommu->obj, offset);
+}
 #endif
diff --git a/include/linux/iopoll.h b/include/linux/iopoll.h
index 2c8860e406bd..bdd2e0652bc3 100644
--- a/include/linux/iopoll.h
+++ b/include/linux/iopoll.h
@@ -14,108 +14,180 @@
 #include <linux/io.h>
 
 /**
- * read_poll_timeout - Periodically poll an address until a condition is
- *			met or a timeout occurs
- * @op: accessor function (takes @args as its arguments)
- * @val: Variable to read the value into
- * @cond: Break condition (usually involving @val)
- * @sleep_us: Maximum time to sleep between reads in us (0
- *            tight-loops).  Should be less than ~20ms since usleep_range
- *            is used (see Documentation/timers/timers-howto.rst).
- * @timeout_us: Timeout in us, 0 means never timeout
- * @sleep_before_read: if it is true, sleep @sleep_us before read.
- * @args: arguments for @op poll
+ * poll_timeout_us - Periodically poll and perform an operation until
+ *                   a condition is met or a timeout occurs
  *
- * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
- * case, the last read value at @args is stored in @val. Must not
- * be called from atomic context if sleep_us or timeout_us are used.
+ * @op: Operation
+ * @cond: Break condition
+ * @sleep_us: Maximum time to sleep between operations in us (0 tight-loops).
+ *            Please read usleep_range() function description for details and
+ *            limitations.
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @sleep_before_op: if it is true, sleep @sleep_us before operation.
  *
  * When available, you'll probably want to use one of the specialized
  * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
  */
-#define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \
-				sleep_before_read, args...) \
+#define poll_timeout_us(op, cond, sleep_us, timeout_us, sleep_before_op) \
 ({ \
 	u64 __timeout_us = (timeout_us); \
 	unsigned long __sleep_us = (sleep_us); \
 	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
+	int ___ret; \
 	might_sleep_if((__sleep_us) != 0); \
-	if (sleep_before_read && __sleep_us) \
+	if ((sleep_before_op) && __sleep_us) \
 		usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
 	for (;;) { \
-		(val) = op(args); \
-		if (cond) \
+		bool __expired = __timeout_us && \
+			ktime_compare(ktime_get(), __timeout) > 0; \
+		/* guarantee 'op' and 'cond' are evaluated after timeout expired */ \
+		barrier(); \
+		op; \
+		if (cond) { \
+			___ret = 0; \
 			break; \
-		if (__timeout_us && \
-		    ktime_compare(ktime_get(), __timeout) > 0) { \
-			(val) = op(args); \
+		} \
+		if (__expired) { \
+			___ret = -ETIMEDOUT; \
 			break; \
 		} \
 		if (__sleep_us) \
 			usleep_range((__sleep_us >> 2) + 1, __sleep_us); \
+		cpu_relax(); \
 	} \
-	(cond) ? 0 : -ETIMEDOUT; \
+	___ret; \
 })
 
 /**
- * read_poll_timeout_atomic - Periodically poll an address until a condition is
- * 				met or a timeout occurs
- * @op: accessor function (takes @args as its arguments)
- * @val: Variable to read the value into
- * @cond: Break condition (usually involving @val)
- * @delay_us: Time to udelay between reads in us (0 tight-loops).  Should
- *            be less than ~10us since udelay is used (see
- *            Documentation/timers/timers-howto.rst).
+ * poll_timeout_us_atomic - Periodically poll and perform an operation until
+ *                          a condition is met or a timeout occurs
+ *
+ * @op: Operation
+ * @cond: Break condition
+ * @delay_us: Time to udelay between operations in us (0 tight-loops).
+ *            Please read udelay() function description for details and
+ *            limitations.
  * @timeout_us: Timeout in us, 0 means never timeout
- * @delay_before_read: if it is true, delay @delay_us before read.
- * @args: arguments for @op poll
+ * @delay_before_op: if it is true, delay @delay_us before operation.
  *
- * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
- * case, the last read value at @args is stored in @val.
+ * This macro does not rely on timekeeping.  Hence it is safe to call even when
+ * timekeeping is suspended, at the expense of an underestimation of wall clock
+ * time, which is rather minimal with a non-zero delay_us.
  *
  * When available, you'll probably want to use one of the specialized
  * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout.
  */
-#define read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, \
-					delay_before_read, args...) \
+#define poll_timeout_us_atomic(op, cond, delay_us, timeout_us, \
+			       delay_before_op) \
 ({ \
 	u64 __timeout_us = (timeout_us); \
+	s64 __left_ns = __timeout_us * NSEC_PER_USEC; \
 	unsigned long __delay_us = (delay_us); \
-	ktime_t __timeout = ktime_add_us(ktime_get(), __timeout_us); \
-	if (delay_before_read && __delay_us) \
+	u64 __delay_ns = __delay_us * NSEC_PER_USEC; \
+	int ___ret; \
+	if ((delay_before_op) && __delay_us) { \
 		udelay(__delay_us); \
+		if (__timeout_us) \
+			__left_ns -= __delay_ns; \
+	} \
 	for (;;) { \
-		(val) = op(args); \
-		if (cond) \
+		bool __expired = __timeout_us && __left_ns < 0; \
+		/* guarantee 'op' and 'cond' are evaluated after timeout expired */ \
+		barrier(); \
+		op; \
+		if (cond) { \
+			___ret = 0; \
 			break; \
-		if (__timeout_us && \
-		    ktime_compare(ktime_get(), __timeout) > 0) { \
-			(val) = op(args); \
+		} \
+		if (__expired) { \
+			___ret = -ETIMEDOUT; \
 			break; \
 		} \
-		if (__delay_us) \
+		if (__delay_us) { \
 			udelay(__delay_us); \
+			if (__timeout_us) \
+				__left_ns -= __delay_ns; \
+		} \
+		cpu_relax(); \
+		if (__timeout_us) \
+			__left_ns--; \
 	} \
-	(cond) ? 0 : -ETIMEDOUT; \
+	___ret; \
 })
 
 /**
+ * read_poll_timeout - Periodically poll an address until a condition is
+ *                     met or a timeout occurs
+ * @op: accessor function (takes @args as its arguments)
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please
+ *            read usleep_range() function description for details and
+ *            limitations.
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @sleep_before_read: if it is true, sleep @sleep_us before read.
+ * @args: arguments for @op poll
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @args is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
+ */
+#define read_poll_timeout(op, val, cond, sleep_us, timeout_us, \
+			  sleep_before_read, args...) \
+	poll_timeout_us((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read)
+
+/**
+ * read_poll_timeout_atomic - Periodically poll an address until a condition is
+ *                            met or a timeout occurs
+ * @op: accessor function (takes @args as its arguments)
+ * @val: Variable to read the value into
+ * @cond: Break condition (usually involving @val)
+ * @delay_us: Time to udelay between reads in us (0 tight-loops). Please
+ *            read udelay() function description for details and
+ *            limitations.
+ * @timeout_us: Timeout in us, 0 means never timeout
+ * @delay_before_read: if it is true, delay @delay_us before read.
+ * @args: arguments for @op poll
+ *
+ * This macro does not rely on timekeeping.  Hence it is safe to call even when
+ * timekeeping is suspended, at the expense of an underestimation of wall clock
+ * time, which is rather minimal with a non-zero delay_us.
+ *
+ * When available, you'll probably want to use one of the specialized
+ * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @args is stored in @val.
+ */
+#define read_poll_timeout_atomic(op, val, cond, sleep_us, timeout_us, \
+				 sleep_before_read, args...) \
+	poll_timeout_us_atomic((val) = op(args), cond, sleep_us, timeout_us, sleep_before_read)
+
+/**
  * readx_poll_timeout - Periodically poll an address until a condition is met or a timeout occurs
  * @op: accessor function (takes @addr as its only argument)
  * @addr: Address to poll
  * @val: Variable to read the value into
  * @cond: Break condition (usually involving @val)
- * @sleep_us: Maximum time to sleep between reads in us (0
- *            tight-loops).  Should be less than ~20ms since usleep_range
- *            is used (see Documentation/timers/timers-howto.rst).
+ * @sleep_us: Maximum time to sleep between reads in us (0 tight-loops). Please
+ *            read usleep_range() function description for details and
+ *            limitations.
  * @timeout_us: Timeout in us, 0 means never timeout
  *
- * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
- * case, the last read value at @addr is stored in @val. Must not
- * be called from atomic context if sleep_us or timeout_us are used.
- *
  * When available, you'll probably want to use one of the specialized
  * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val. Must not
+ * be called from atomic context if sleep_us or timeout_us are used.
  */
 #define readx_poll_timeout(op, addr, val, cond, sleep_us, timeout_us)	\
 	read_poll_timeout(op, val, cond, sleep_us, timeout_us, false, addr)
@@ -126,16 +198,16 @@
  * @addr: Address to poll
  * @val: Variable to read the value into
  * @cond: Break condition (usually involving @val)
- * @delay_us: Time to udelay between reads in us (0 tight-loops).  Should
- *            be less than ~10us since udelay is used (see
- *            Documentation/timers/timers-howto.rst).
+ * @delay_us: Time to udelay between reads in us (0 tight-loops). Please
+ *            read udelay() function description for details and
+ *            limitations.
  * @timeout_us: Timeout in us, 0 means never timeout
  *
- * Returns 0 on success and -ETIMEDOUT upon a timeout. In either
- * case, the last read value at @addr is stored in @val.
- *
  * When available, you'll probably want to use one of the specialized
  * macros defined below rather than this macro directly.
+ *
+ * Returns: 0 on success and -ETIMEDOUT upon a timeout. In either
+ * case, the last read value at @addr is stored in @val.
  */
 #define readx_poll_timeout_atomic(op, addr, val, cond, delay_us, timeout_us) \
 	read_poll_timeout_atomic(op, val, cond, delay_us, timeout_us, false, addr)
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index 25d768d48970..9afa30f9346f 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -154,15 +154,20 @@ enum {
 };
 
 /* helpers to define resources */
-#define DEFINE_RES_NAMED(_start, _size, _name, _flags)			\
+#define DEFINE_RES_NAMED_DESC(_start, _size, _name, _flags, _desc)	\
 (struct resource) {							\
 		.start = (_start),					\
 		.end = (_start) + (_size) - 1,				\
 		.name = (_name),					\
 		.flags = (_flags),					\
-		.desc = IORES_DESC_NONE,				\
+		.desc = (_desc),					\
 	}
 
+#define DEFINE_RES_NAMED(_start, _size, _name, _flags)			\
+	DEFINE_RES_NAMED_DESC(_start, _size, _name, _flags, IORES_DESC_NONE)
+#define DEFINE_RES(_start, _size, _flags)				\
+	DEFINE_RES_NAMED(_start, _size, NULL, _flags)
+
 #define DEFINE_RES_IO_NAMED(_start, _size, _name)			\
 	DEFINE_RES_NAMED((_start), (_size), (_name), IORESOURCE_IO)
 #define DEFINE_RES_IO(_start, _size)					\
@@ -188,6 +193,42 @@ enum {
 #define DEFINE_RES_DMA(_dma)						\
 	DEFINE_RES_DMA_NAMED((_dma), NULL)
 
+/**
+ * typedef resource_alignf - Resource alignment callback
+ * @data:	Private data used by the callback
+ * @res:	Resource candidate range (an empty resource space)
+ * @size:	The minimum size of the empty space
+ * @align:	Alignment from the constraints
+ *
+ * Callback allows calculating resource placement and alignment beyond min,
+ * max, and align fields in the struct resource_constraint.
+ *
+ * Return: Start address for the resource.
+ */
+typedef resource_size_t (*resource_alignf)(void *data,
+					   const struct resource *res,
+					   resource_size_t size,
+					   resource_size_t align);
+
+/**
+ * struct resource_constraint - constraints to be met while searching empty
+ *				resource space
+ * @min:		The minimum address for the memory range
+ * @max:		The maximum address for the memory range
+ * @align:		Alignment for the start address of the empty space
+ * @alignf:		Additional alignment constraints callback
+ * @alignf_data:	Data provided for @alignf callback
+ *
+ * Contains the range and alignment constraints that have to be met during
+ * find_resource_space(). @alignf can be NULL indicating no alignment beyond
+ * @align is necessary.
+ */
+struct resource_constraint {
+	resource_size_t min, max, align;
+	resource_alignf alignf;
+	void *alignf_data;
+};
+
 /* PC/ISA/whatever - the normal PC address spaces: IO and memory */
 extern struct resource ioport_resource;
 extern struct resource iomem_resource;
@@ -207,15 +248,44 @@ extern void arch_remove_reservations(struct resource *avail);
 extern int allocate_resource(struct resource *root, struct resource *new,
 			     resource_size_t size, resource_size_t min,
 			     resource_size_t max, resource_size_t align,
-			     resource_size_t (*alignf)(void *,
-						       const struct resource *,
-						       resource_size_t,
-						       resource_size_t),
+			     resource_alignf alignf,
 			     void *alignf_data);
 struct resource *lookup_resource(struct resource *root, resource_size_t start);
 int adjust_resource(struct resource *res, resource_size_t start,
 		    resource_size_t size);
 resource_size_t resource_alignment(struct resource *res);
+
+/**
+ * resource_set_size - Calculate resource end address from size and start
+ * @res: Resource descriptor
+ * @size: Size of the resource
+ *
+ * Calculate the end address for @res based on @size.
+ *
+ * Note: The start address of @res must be set when calling this function.
+ * Prefer resource_set_range() if setting both the start address and @size.
+ */
+static inline void resource_set_size(struct resource *res, resource_size_t size)
+{
+	res->end = res->start + size - 1;
+}
+
+/**
+ * resource_set_range - Set resource start and end addresses
+ * @res: Resource descriptor
+ * @start: Start address for the resource
+ * @size: Size of the resource
+ *
+ * Set @res start address and calculate the end address based on @size.
+ */
+static inline void resource_set_range(struct resource *res,
+				      resource_size_t start,
+				      resource_size_t size)
+{
+	res->start = start;
+	resource_set_size(res, size);
+}
+
 static inline resource_size_t resource_size(const struct resource *res)
 {
 	return res->end - res->start + 1;
@@ -229,7 +299,7 @@ static inline unsigned long resource_ext_type(const struct resource *res)
 	return res->flags & IORESOURCE_EXT_TYPE_BITS;
 }
 /* True iff r1 completely contains r2 */
-static inline bool resource_contains(struct resource *r1, struct resource *r2)
+static inline bool resource_contains(const struct resource *r1, const struct resource *r2)
 {
 	if (resource_type(r1) != resource_type(r2))
 		return false;
@@ -239,13 +309,13 @@ static inline bool resource_contains(struct resource *r1, struct resource *r2)
 }
 
 /* True if any part of r1 overlaps r2 */
-static inline bool resource_overlaps(struct resource *r1, struct resource *r2)
+static inline bool resource_overlaps(const struct resource *r1, const struct resource *r2)
 {
        return r1->start <= r2->end && r1->end >= r2->start;
 }
 
-static inline bool
-resource_intersection(struct resource *r1, struct resource *r2, struct resource *r)
+static inline bool resource_intersection(const struct resource *r1, const struct resource *r2,
+					 struct resource *r)
 {
 	if (!resource_overlaps(r1, r2))
 		return false;
@@ -254,8 +324,8 @@ resource_intersection(struct resource *r1, struct resource *r2, struct resource
 	return true;
 }
 
-static inline bool
-resource_union(struct resource *r1, struct resource *r2, struct resource *r)
+static inline bool resource_union(const struct resource *r1, const struct resource *r2,
+				  struct resource *r)
 {
 	if (!resource_overlaps(r1, r2))
 		return false;
@@ -264,6 +334,18 @@ resource_union(struct resource *r1, struct resource *r2, struct resource *r)
 	return true;
 }
 
+/*
+ * Check if this resource is added to a resource tree or detached. Caller is
+ * responsible for not racing assignment.
+ */
+static inline bool resource_assigned(struct resource *res)
+{
+	return res->parent;
+}
+
+int find_resource_space(struct resource *root, struct resource *new,
+			resource_size_t size, struct resource_constraint *constraint);
+
 /* Convenience shorthand with allocation */
 #define request_region(start,n,name)		__request_region(&ioport_resource, (start), (n), (name), 0)
 #define request_muxed_region(start,n,name)	__request_region(&ioport_resource, (start), (n), (name), IORESOURCE_MUXED)
@@ -331,6 +413,9 @@ extern int
 walk_system_ram_res(u64 start, u64 end, void *arg,
 		    int (*func)(struct resource *, void *));
 extern int
+walk_system_ram_res_rev(u64 start, u64 end, void *arg,
+			int (*func)(struct resource *, void *));
+extern int
 walk_iomem_res_desc(unsigned long desc, unsigned long flags, u64 start, u64 end,
 		    void *arg, int (*func)(struct resource *, void *));
 
diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index 7578d4f6a969..5210e8371238 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -40,14 +40,38 @@ static inline int task_nice_ioclass(struct task_struct *task)
 {
 	if (task->policy == SCHED_IDLE)
 		return IOPRIO_CLASS_IDLE;
-	else if (task_is_realtime(task))
+	else if (rt_or_dl_task_policy(task))
 		return IOPRIO_CLASS_RT;
 	else
 		return IOPRIO_CLASS_BE;
 }
 
 #ifdef CONFIG_BLOCK
-int __get_task_ioprio(struct task_struct *p);
+/*
+ * If the task has set an I/O priority, use that. Otherwise, return
+ * the default I/O priority.
+ *
+ * Expected to be called for current task or with task_lock() held to keep
+ * io_context stable.
+ */
+static inline int __get_task_ioprio(struct task_struct *p)
+{
+	struct io_context *ioc = p->io_context;
+	int prio;
+
+	if (!ioc)
+		return IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+
+	if (p != current)
+		lockdep_assert_held(&p->alloc_lock);
+
+	prio = ioc->ioprio;
+	if (IOPRIO_PRIO_CLASS(prio) == IOPRIO_CLASS_NONE)
+		prio = IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
+	return prio;
+}
 #else
 static inline int __get_task_ioprio(struct task_struct *p)
 {
diff --git a/include/linux/ioremap.h b/include/linux/ioremap.h
new file mode 100644
index 000000000000..2bd1661fe9ad
--- /dev/null
+++ b/include/linux/ioremap.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IOREMAP_H
+#define _LINUX_IOREMAP_H
+
+#include <linux/kasan.h>
+#include <asm/pgtable.h>
+#include <asm/vmalloc.h>
+
+#if defined(CONFIG_HAS_IOMEM) || defined(CONFIG_GENERIC_IOREMAP)
+/*
+ * Ioremap often, but not always uses the generic vmalloc area. E.g on
+ * Power ARCH, it could have different ioremap space.
+ */
+#ifndef IOREMAP_START
+#define IOREMAP_START   VMALLOC_START
+#define IOREMAP_END     VMALLOC_END
+#endif
+static inline bool is_ioremap_addr(const void *x)
+{
+	unsigned long addr = (unsigned long)kasan_reset_tag(x);
+
+	return addr >= IOREMAP_START && addr < IOREMAP_END;
+}
+#else
+static inline bool is_ioremap_addr(const void *x)
+{
+	return false;
+}
+#endif
+
+#endif /* _LINUX_IOREMAP_H */
diff --git a/include/linux/iosys-map.h b/include/linux/iosys-map.h
index cb71aa616bd3..3e85afe794c0 100644
--- a/include/linux/iosys-map.h
+++ b/include/linux/iosys-map.h
@@ -34,7 +34,7 @@
  * the same driver for allocation, read and write operations.
  *
  * Open-coding access to :c:type:`struct iosys_map <iosys_map>` is considered
- * bad style. Rather then accessing its fields directly, use one of the provided
+ * bad style. Rather than accessing its fields directly, use one of the provided
  * helper functions, or implement your own. For example, instances of
  * :c:type:`struct iosys_map <iosys_map>` can be initialized statically with
  * IOSYS_MAP_INIT_VADDR(), or at runtime with iosys_map_set_vaddr(). These
@@ -168,9 +168,9 @@ struct iosys_map {
  * about the use of uninitialized variable.
  */
 #define IOSYS_MAP_INIT_OFFSET(map_, offset_) ({				\
-	struct iosys_map copy = *map_;					\
-	iosys_map_incr(&copy, offset_);					\
-	copy;								\
+	struct iosys_map copy_ = *map_;					\
+	iosys_map_incr(&copy_, offset_);				\
+	copy_;								\
 })
 
 /**
@@ -264,12 +264,7 @@ static inline bool iosys_map_is_set(const struct iosys_map *map)
  */
 static inline void iosys_map_clear(struct iosys_map *map)
 {
-	if (map->is_iomem) {
-		map->vaddr_iomem = NULL;
-		map->is_iomem = false;
-	} else {
-		map->vaddr = NULL;
-	}
+	memset(map, 0, sizeof(*map));
 }
 
 /**
@@ -391,14 +386,14 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset,
  * Returns:
  * The value read from the mapping.
  */
-#define iosys_map_rd(map__, offset__, type__) ({				\
-	type__ val;								\
-	if ((map__)->is_iomem) {						\
-		__iosys_map_rd_io(val, (map__)->vaddr_iomem + (offset__), type__);\
-	} else {								\
-		__iosys_map_rd_sys(val, (map__)->vaddr + (offset__), type__);	\
-	}									\
-	val;									\
+#define iosys_map_rd(map__, offset__, type__) ({					\
+	type__ val_;									\
+	if ((map__)->is_iomem) {							\
+		__iosys_map_rd_io(val_, (map__)->vaddr_iomem + (offset__), type__);	\
+	} else {									\
+		__iosys_map_rd_sys(val_, (map__)->vaddr + (offset__), type__);		\
+	}										\
+	val_;										\
 })
 
 /**
@@ -413,20 +408,20 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset,
  * or if pointer may be unaligned (and problematic for the architecture
  * supported), use iosys_map_memcpy_to()
  */
-#define iosys_map_wr(map__, offset__, type__, val__) ({				\
-	type__ val = (val__);							\
-	if ((map__)->is_iomem) {						\
-		__iosys_map_wr_io(val, (map__)->vaddr_iomem + (offset__), type__);\
-	} else {								\
-		__iosys_map_wr_sys(val, (map__)->vaddr + (offset__), type__);	\
-	}									\
+#define iosys_map_wr(map__, offset__, type__, val__) ({					\
+	type__ val_ = (val__);								\
+	if ((map__)->is_iomem) {							\
+		__iosys_map_wr_io(val_, (map__)->vaddr_iomem + (offset__), type__);	\
+	} else {									\
+		__iosys_map_wr_sys(val_, (map__)->vaddr + (offset__), type__);		\
+	}										\
 })
 
 /**
  * iosys_map_rd_field - Read a member from a struct in the iosys_map
  *
  * @map__:		The iosys_map structure
- * @struct_offset__:	Offset from the beggining of the map, where the struct
+ * @struct_offset__:	Offset from the beginning of the map, where the struct
  *			is located
  * @struct_type__:	The struct describing the layout of the mapping
  * @field__:		Member of the struct to read
@@ -485,16 +480,16 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset,
  * The value read from the mapping.
  */
 #define iosys_map_rd_field(map__, struct_offset__, struct_type__, field__) ({	\
-	struct_type__ *s;							\
+	struct_type__ *s_;							\
 	iosys_map_rd(map__, struct_offset__ + offsetof(struct_type__, field__),	\
-		     typeof(s->field__));					\
+		     typeof(s_->field__));					\
 })
 
 /**
  * iosys_map_wr_field - Write to a member of a struct in the iosys_map
  *
  * @map__:		The iosys_map structure
- * @struct_offset__:	Offset from the beggining of the map, where the struct
+ * @struct_offset__:	Offset from the beginning of the map, where the struct
  *			is located
  * @struct_type__:	The struct describing the layout of the mapping
  * @field__:		Member of the struct to read
@@ -508,9 +503,9 @@ static inline void iosys_map_memset(struct iosys_map *dst, size_t offset,
  * usage and memory layout.
  */
 #define iosys_map_wr_field(map__, struct_offset__, struct_type__, field__, val__) ({	\
-	struct_type__ *s;								\
+	struct_type__ *s_;								\
 	iosys_map_wr(map__, struct_offset__ + offsetof(struct_type__, field__),		\
-		     typeof(s->field__), val__);					\
+		     typeof(s_->field__), val__);					\
 })
 
 #endif /* __IOSYS_MAP_H__ */
diff --git a/include/linux/iov_iter.h b/include/linux/iov_iter.h
new file mode 100644
index 000000000000..f9a17fbbd398
--- /dev/null
+++ b/include/linux/iov_iter.h
@@ -0,0 +1,380 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* I/O iterator iteration building functions.
+ *
+ * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#ifndef _LINUX_IOV_ITER_H
+#define _LINUX_IOV_ITER_H
+
+#include <linux/uio.h>
+#include <linux/bvec.h>
+#include <linux/folio_queue.h>
+
+typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len,
+			     void *priv, void *priv2);
+typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len,
+			      void *priv, void *priv2);
+
+/*
+ * Handle ITER_UBUF.
+ */
+static __always_inline
+size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		    iov_ustep_f step)
+{
+	void __user *base = iter->ubuf;
+	size_t progress = 0, remain;
+
+	remain = step(base + iter->iov_offset, 0, len, priv, priv2);
+	progress = len - remain;
+	iter->iov_offset += progress;
+	iter->count -= progress;
+	return progress;
+}
+
+/*
+ * Handle ITER_IOVEC.
+ */
+static __always_inline
+size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		     iov_ustep_f step)
+{
+	const struct iovec *p = iter->__iov;
+	size_t progress = 0, skip = iter->iov_offset;
+
+	do {
+		size_t remain, consumed;
+		size_t part = min(len, p->iov_len - skip);
+
+		if (likely(part)) {
+			remain = step(p->iov_base + skip, progress, part, priv, priv2);
+			consumed = part - remain;
+			progress += consumed;
+			skip += consumed;
+			len -= consumed;
+			if (skip < p->iov_len)
+				break;
+		}
+		p++;
+		skip = 0;
+	} while (len);
+
+	iter->nr_segs -= p - iter->__iov;
+	iter->__iov = p;
+	iter->iov_offset = skip;
+	iter->count -= progress;
+	return progress;
+}
+
+/*
+ * Handle ITER_KVEC.
+ */
+static __always_inline
+size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		    iov_step_f step)
+{
+	const struct kvec *p = iter->kvec;
+	size_t progress = 0, skip = iter->iov_offset;
+
+	do {
+		size_t remain, consumed;
+		size_t part = min(len, p->iov_len - skip);
+
+		if (likely(part)) {
+			remain = step(p->iov_base + skip, progress, part, priv, priv2);
+			consumed = part - remain;
+			progress += consumed;
+			skip += consumed;
+			len -= consumed;
+			if (skip < p->iov_len)
+				break;
+		}
+		p++;
+		skip = 0;
+	} while (len);
+
+	iter->nr_segs -= p - iter->kvec;
+	iter->kvec = p;
+	iter->iov_offset = skip;
+	iter->count -= progress;
+	return progress;
+}
+
+/*
+ * Handle ITER_BVEC.
+ */
+static __always_inline
+size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		    iov_step_f step)
+{
+	const struct bio_vec *p = iter->bvec;
+	size_t progress = 0, skip = iter->iov_offset;
+
+	do {
+		size_t remain, consumed;
+		size_t offset = p->bv_offset + skip, part;
+		void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE);
+
+		part = min3(len,
+			   (size_t)(p->bv_len - skip),
+			   (size_t)(PAGE_SIZE - offset % PAGE_SIZE));
+		remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2);
+		kunmap_local(kaddr);
+		consumed = part - remain;
+		len -= consumed;
+		progress += consumed;
+		skip += consumed;
+		if (skip >= p->bv_len) {
+			skip = 0;
+			p++;
+		}
+		if (remain)
+			break;
+	} while (len);
+
+	iter->nr_segs -= p - iter->bvec;
+	iter->bvec = p;
+	iter->iov_offset = skip;
+	iter->count -= progress;
+	return progress;
+}
+
+/*
+ * Handle ITER_FOLIOQ.
+ */
+static __always_inline
+size_t iterate_folioq(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		      iov_step_f step)
+{
+	const struct folio_queue *folioq = iter->folioq;
+	unsigned int slot = iter->folioq_slot;
+	size_t progress = 0, skip = iter->iov_offset;
+
+	if (slot == folioq_nr_slots(folioq)) {
+		/* The iterator may have been extended. */
+		folioq = folioq->next;
+		slot = 0;
+	}
+
+	do {
+		struct folio *folio = folioq_folio(folioq, slot);
+		size_t part, remain = 0, consumed;
+		size_t fsize;
+		void *base;
+
+		if (!folio)
+			break;
+
+		fsize = folioq_folio_size(folioq, slot);
+		if (skip < fsize) {
+			base = kmap_local_folio(folio, skip);
+			part = umin(len, PAGE_SIZE - skip % PAGE_SIZE);
+			remain = step(base, progress, part, priv, priv2);
+			kunmap_local(base);
+			consumed = part - remain;
+			len -= consumed;
+			progress += consumed;
+			skip += consumed;
+		}
+		if (skip >= fsize) {
+			skip = 0;
+			slot++;
+			if (slot == folioq_nr_slots(folioq) && folioq->next) {
+				folioq = folioq->next;
+				slot = 0;
+			}
+		}
+		if (remain)
+			break;
+	} while (len);
+
+	iter->folioq_slot = slot;
+	iter->folioq = folioq;
+	iter->iov_offset = skip;
+	iter->count -= progress;
+	return progress;
+}
+
+/*
+ * Handle ITER_XARRAY.
+ */
+static __always_inline
+size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		      iov_step_f step)
+{
+	struct folio *folio;
+	size_t progress = 0;
+	loff_t start = iter->xarray_start + iter->iov_offset;
+	pgoff_t index = start / PAGE_SIZE;
+	XA_STATE(xas, iter->xarray, index);
+
+	rcu_read_lock();
+	xas_for_each(&xas, folio, ULONG_MAX) {
+		size_t remain, consumed, offset, part, flen;
+
+		if (xas_retry(&xas, folio))
+			continue;
+		if (WARN_ON(xa_is_value(folio)))
+			break;
+		if (WARN_ON(folio_test_hugetlb(folio)))
+			break;
+
+		offset = offset_in_folio(folio, start + progress);
+		flen = min(folio_size(folio) - offset, len);
+
+		while (flen) {
+			void *base = kmap_local_folio(folio, offset);
+
+			part = min_t(size_t, flen,
+				     PAGE_SIZE - offset_in_page(offset));
+			remain = step(base, progress, part, priv, priv2);
+			kunmap_local(base);
+
+			consumed = part - remain;
+			progress += consumed;
+			len -= consumed;
+
+			if (remain || len == 0)
+				goto out;
+			flen -= consumed;
+			offset += consumed;
+		}
+	}
+
+out:
+	rcu_read_unlock();
+	iter->iov_offset += progress;
+	iter->count -= progress;
+	return progress;
+}
+
+/*
+ * Handle ITER_DISCARD.
+ */
+static __always_inline
+size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2,
+		      iov_step_f step)
+{
+	size_t progress = len;
+
+	iter->count -= progress;
+	return progress;
+}
+
+/**
+ * iterate_and_advance2 - Iterate over an iterator
+ * @iter: The iterator to iterate over.
+ * @len: The amount to iterate over.
+ * @priv: Data for the step functions.
+ * @priv2: More data for the step functions.
+ * @ustep: Function for UBUF/IOVEC iterators; given __user addresses.
+ * @step: Function for other iterators; given kernel addresses.
+ *
+ * Iterate over the next part of an iterator, up to the specified length.  The
+ * buffer is presented in segments, which for kernel iteration are broken up by
+ * physical pages and mapped, with the mapped address being presented.
+ *
+ * Two step functions, @step and @ustep, must be provided, one for handling
+ * mapped kernel addresses and the other is given user addresses which have the
+ * potential to fault since no pinning is performed.
+ *
+ * The step functions are passed the address and length of the segment, @priv,
+ * @priv2 and the amount of data so far iterated over (which can, for example,
+ * be added to @priv to point to the right part of a second buffer).  The step
+ * functions should return the amount of the segment they didn't process (ie. 0
+ * indicates complete processsing).
+ *
+ * This function returns the amount of data processed (ie. 0 means nothing was
+ * processed and the value of @len means processes to completion).
+ */
+static __always_inline
+size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv,
+			    void *priv2, iov_ustep_f ustep, iov_step_f step)
+{
+	if (unlikely(iter->count < len))
+		len = iter->count;
+	if (unlikely(!len))
+		return 0;
+
+	if (likely(iter_is_ubuf(iter)))
+		return iterate_ubuf(iter, len, priv, priv2, ustep);
+	if (likely(iter_is_iovec(iter)))
+		return iterate_iovec(iter, len, priv, priv2, ustep);
+	if (iov_iter_is_bvec(iter))
+		return iterate_bvec(iter, len, priv, priv2, step);
+	if (iov_iter_is_kvec(iter))
+		return iterate_kvec(iter, len, priv, priv2, step);
+	if (iov_iter_is_folioq(iter))
+		return iterate_folioq(iter, len, priv, priv2, step);
+	if (iov_iter_is_xarray(iter))
+		return iterate_xarray(iter, len, priv, priv2, step);
+	return iterate_discard(iter, len, priv, priv2, step);
+}
+
+/**
+ * iterate_and_advance - Iterate over an iterator
+ * @iter: The iterator to iterate over.
+ * @len: The amount to iterate over.
+ * @priv: Data for the step functions.
+ * @ustep: Function for UBUF/IOVEC iterators; given __user addresses.
+ * @step: Function for other iterators; given kernel addresses.
+ *
+ * As iterate_and_advance2(), but priv2 is always NULL.
+ */
+static __always_inline
+size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv,
+			   iov_ustep_f ustep, iov_step_f step)
+{
+	return iterate_and_advance2(iter, len, priv, NULL, ustep, step);
+}
+
+/**
+ * iterate_and_advance_kernel - Iterate over a kernel-internal iterator
+ * @iter: The iterator to iterate over.
+ * @len: The amount to iterate over.
+ * @priv: Data for the step functions.
+ * @priv2: More data for the step functions.
+ * @step: Function for other iterators; given kernel addresses.
+ *
+ * Iterate over the next part of an iterator, up to the specified length.  The
+ * buffer is presented in segments, which for kernel iteration are broken up by
+ * physical pages and mapped, with the mapped address being presented.
+ *
+ * [!] Note This will only handle BVEC, KVEC, FOLIOQ, XARRAY and DISCARD-type
+ * iterators; it will not handle UBUF or IOVEC-type iterators.
+ *
+ * A step functions, @step, must be provided, one for handling mapped kernel
+ * addresses and the other is given user addresses which have the potential to
+ * fault since no pinning is performed.
+ *
+ * The step functions are passed the address and length of the segment, @priv,
+ * @priv2 and the amount of data so far iterated over (which can, for example,
+ * be added to @priv to point to the right part of a second buffer).  The step
+ * functions should return the amount of the segment they didn't process (ie. 0
+ * indicates complete processsing).
+ *
+ * This function returns the amount of data processed (ie. 0 means nothing was
+ * processed and the value of @len means processes to completion).
+ */
+static __always_inline
+size_t iterate_and_advance_kernel(struct iov_iter *iter, size_t len, void *priv,
+				  void *priv2, iov_step_f step)
+{
+	if (unlikely(iter->count < len))
+		len = iter->count;
+	if (unlikely(!len))
+		return 0;
+	if (iov_iter_is_bvec(iter))
+		return iterate_bvec(iter, len, priv, priv2, step);
+	if (iov_iter_is_kvec(iter))
+		return iterate_kvec(iter, len, priv, priv2, step);
+	if (iov_iter_is_folioq(iter))
+		return iterate_folioq(iter, len, priv, priv2, step);
+	if (iov_iter_is_xarray(iter))
+		return iterate_xarray(iter, len, priv, priv2, step);
+	return iterate_discard(iter, len, priv, priv2, step);
+}
+
+#endif /* _LINUX_IOV_ITER_H */
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 83c00fac2acb..d2c4fd923efa 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -65,6 +65,11 @@ static inline size_t iova_align(struct iova_domain *iovad, size_t size)
 	return ALIGN(size, iovad->granule);
 }
 
+static inline size_t iova_align_down(struct iova_domain *iovad, size_t size)
+{
+	return ALIGN_DOWN(size, iovad->granule);
+}
+
 static inline dma_addr_t iova_dma_addr(struct iova_domain *iovad, struct iova *iova)
 {
 	return (dma_addr_t)iova->pfn_lo << iova_shift(iovad);
diff --git a/include/linux/iova_bitmap.h b/include/linux/iova_bitmap.h
index c006cf0a25f3..1c338f5e5b7a 100644
--- a/include/linux/iova_bitmap.h
+++ b/include/linux/iova_bitmap.h
@@ -7,6 +7,7 @@
 #define _IOVA_BITMAP_H_
 
 #include <linux/types.h>
+#include <linux/errno.h>
 
 struct iova_bitmap;
 
@@ -14,6 +15,7 @@ typedef int (*iova_bitmap_fn_t)(struct iova_bitmap *bitmap,
 				unsigned long iova, size_t length,
 				void *opaque);
 
+#if IS_ENABLED(CONFIG_IOMMUFD_DRIVER)
 struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length,
 				      unsigned long page_size,
 				      u64 __user *data);
@@ -22,5 +24,29 @@ int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque,
 			 iova_bitmap_fn_t fn);
 void iova_bitmap_set(struct iova_bitmap *bitmap,
 		     unsigned long iova, size_t length);
+#else
+static inline struct iova_bitmap *iova_bitmap_alloc(unsigned long iova,
+						    size_t length,
+						    unsigned long page_size,
+						    u64 __user *data)
+{
+	return NULL;
+}
+
+static inline void iova_bitmap_free(struct iova_bitmap *bitmap)
+{
+}
+
+static inline int iova_bitmap_for_each(struct iova_bitmap *bitmap, void *opaque,
+				       iova_bitmap_fn_t fn)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void iova_bitmap_set(struct iova_bitmap *bitmap,
+				   unsigned long iova, size_t length)
+{
+}
+#endif
 
 #endif
diff --git a/include/linux/ipack.h b/include/linux/ipack.h
index 2c6936b8371f..455f6c2a1903 100644
--- a/include/linux/ipack.h
+++ b/include/linux/ipack.h
@@ -70,15 +70,13 @@ enum ipack_space {
 	IPACK_SPACE_COUNT,
 };
 
-/**
- */
 struct ipack_region {
 	phys_addr_t start;
 	size_t      size;
 };
 
 /**
- *	struct ipack_device
+ *	struct ipack_device - subsystem representation of an IPack device
  *
  *	@slot: Slot where the device is plugged in the carrier board
  *	@bus: ipack_bus_device where the device is plugged to.
@@ -89,7 +87,7 @@ struct ipack_region {
  *
  * Warning: Direct access to mapped memory is possible but the endianness
  * is not the same with PCI carrier or VME carrier. The endianness is managed
- * by the carrier board throught bus->ops.
+ * by the carrier board through bus->ops.
  */
 struct ipack_device {
 	unsigned int slot;
@@ -124,6 +122,7 @@ struct ipack_driver_ops {
  * struct ipack_driver -- Specific data to each ipack device driver
  *
  * @driver: Device driver kernel representation
+ * @id_table: Device ID table for this driver
  * @ops:    Callbacks provided by the IPack device driver
  */
 struct ipack_driver {
@@ -161,7 +160,7 @@ struct ipack_bus_ops {
 };
 
 /**
- *	struct ipack_bus_device
+ *	struct ipack_bus_device - IPack bus representation
  *
  *	@dev: pointer to carrier device
  *	@slots: number of slots available
@@ -185,6 +184,8 @@ struct ipack_bus_device {
  *
  * The carrier board device should call this function to register itself as
  * available bus device in ipack.
+ *
+ * Return: %NULL on error or &struct ipack_bus_device on success
  */
 struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
 					    const struct ipack_bus_ops *ops,
@@ -192,6 +193,8 @@ struct ipack_bus_device *ipack_bus_register(struct device *parent, int slots,
 
 /**
  *	ipack_bus_unregister -- unregister an ipack bus
+ *
+ *	Return: %0
  */
 int ipack_bus_unregister(struct ipack_bus_device *bus);
 
@@ -200,6 +203,8 @@ int ipack_bus_unregister(struct ipack_bus_device *bus);
  *
  * Called by a ipack driver to register itself as a driver
  * that can manage ipack devices.
+ *
+ * Return: zero on success or error code on failure.
  */
 int ipack_driver_register(struct ipack_driver *edrv, struct module *owner,
 			  const char *name);
@@ -215,7 +220,7 @@ void ipack_driver_unregister(struct ipack_driver *edrv);
  * function.  The rest of the fields will be allocated and populated
  * during initalization.
  *
- * Return zero on success or error code on failure.
+ * Return: zero on success or error code on failure.
  *
  * NOTE: _Never_ directly free @dev after calling this function, even
  * if it returned an error! Always use ipack_put_device() to give up the
@@ -230,7 +235,7 @@ int ipack_device_init(struct ipack_device *dev);
  * Add a new IPack device. The call is done by the carrier driver
  * after calling ipack_device_init().
  *
- * Return zero on success or error code on failure.
+ * Return: zero on success or error code on failure.
  *
  * NOTE: _Never_ directly free @dev after calling this function, even
  * if it returned an error! Always use ipack_put_device() to give up the
@@ -266,9 +271,11 @@ void ipack_put_device(struct ipack_device *dev);
 	 .device = (dev)
 
 /**
- * ipack_get_carrier - it increase the carrier ref. counter of
+ * ipack_get_carrier - try to increase the carrier ref. counter of
  *                     the carrier module
  * @dev: mezzanine device which wants to get the carrier
+ *
+ * Return: true on success.
  */
 static inline int ipack_get_carrier(struct ipack_device *dev)
 {
diff --git a/include/linux/ipc.h b/include/linux/ipc.h
index e1c9eea6015b..9b1434247aab 100644
--- a/include/linux/ipc.h
+++ b/include/linux/ipc.h
@@ -2,7 +2,7 @@
 #ifndef _LINUX_IPC_H
 #define _LINUX_IPC_H
 
-#include <linux/spinlock.h>
+#include <linux/spinlock_types.h>
 #include <linux/uidgid.h>
 #include <linux/rhashtable-types.h>
 #include <uapi/linux/ipc.h>
diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h
index e8240cf2611a..12faca29bbb9 100644
--- a/include/linux/ipc_namespace.h
+++ b/include/linux/ipc_namespace.h
@@ -129,20 +129,25 @@ static inline int mq_init_ns(struct ipc_namespace *ns) { return 0; }
 #endif
 
 #if defined(CONFIG_IPC_NS)
-extern struct ipc_namespace *copy_ipcs(unsigned long flags,
+static inline struct ipc_namespace *to_ipc_ns(struct ns_common *ns)
+{
+	return container_of(ns, struct ipc_namespace, ns);
+}
+
+extern struct ipc_namespace *copy_ipcs(u64 flags,
 	struct user_namespace *user_ns, struct ipc_namespace *ns);
 
 static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns)
 {
 	if (ns)
-		refcount_inc(&ns->ns.count);
+		ns_ref_inc(ns);
 	return ns;
 }
 
 static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns)
 {
 	if (ns) {
-		if (refcount_inc_not_zero(&ns->ns.count))
+		if (ns_ref_get(ns))
 			return ns;
 	}
 
@@ -151,7 +156,7 @@ static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns
 
 extern void put_ipc_ns(struct ipc_namespace *ns);
 #else
-static inline struct ipc_namespace *copy_ipcs(unsigned long flags,
+static inline struct ipc_namespace *copy_ipcs(u64 flags,
 	struct user_namespace *user_ns, struct ipc_namespace *ns)
 {
 	if (flags & CLONE_NEWIPC)
diff --git a/include/linux/ipmi.h b/include/linux/ipmi.h
index a1c9c0d48ebf..7da6602eab71 100644
--- a/include/linux/ipmi.h
+++ b/include/linux/ipmi.h
@@ -93,7 +93,8 @@ struct ipmi_user_hndl {
 
 	/*
 	 * Called when the interface detects a watchdog pre-timeout.  If
-	 * this is NULL, it will be ignored for the user.
+	 * this is NULL, it will be ignored for the user.  Note that you
+	 * can't do any IPMI calls from here, it's called with locks held.
 	 */
 	void (*ipmi_watchdog_pretimeout)(void *handler_data);
 
@@ -126,7 +127,7 @@ int ipmi_create_user(unsigned int          if_num,
  * the users before you destroy the callback structures, it should be
  * safe, too.
  */
-int ipmi_destroy_user(struct ipmi_user *user);
+void ipmi_destroy_user(struct ipmi_user *user);
 
 /* Get the IPMI version of the BMC we are talking to. */
 int ipmi_get_version(struct ipmi_user *user,
@@ -343,4 +344,14 @@ extern int ipmi_get_smi_info(int if_num, struct ipmi_smi_info *data);
 /* Helper function for computing the IPMB checksum of some data. */
 unsigned char ipmb_checksum(unsigned char *data, int size);
 
+/*
+ * For things that must send messages at panic time, like the IPMI watchdog
+ * driver that extends the reset time on a panic, use this to send messages
+ * from panic context.  Note that this puts the driver into a mode that
+ * only works at panic time, so only use it then.
+ */
+void ipmi_panic_request_and_wait(struct ipmi_user *user,
+				 struct ipmi_addr *addr,
+				 struct kernel_ipmi_msg *msg);
+
 #endif /* __LINUX_IPMI_H */
diff --git a/include/linux/ipmi_smi.h b/include/linux/ipmi_smi.h
index 5d69820d8b02..892e2d656e1e 100644
--- a/include/linux/ipmi_smi.h
+++ b/include/linux/ipmi_smi.h
@@ -109,8 +109,9 @@ struct ipmi_smi_msg {
 
 	enum ipmi_smi_msg_type type;
 
-	long    msgid;
-	void    *user_data;
+	long msgid;
+	/* Response to this message, will be NULL if not from a user request. */
+	struct ipmi_recv_msg *recv_msg;
 
 	int           data_size;
 	unsigned char data[IPMI_MAX_MSG_LENGTH];
@@ -168,9 +169,11 @@ struct ipmi_smi_handlers {
 	 * are held when this is run.  Message are delivered one at
 	 * a time by the message handler, a new message will not be
 	 * delivered until the previous message is returned.
+	 *
+	 * This can return an error if the SMI is not in a state where it
+	 * can send a message.
 	 */
-	void (*sender)(void                *send_info,
-		       struct ipmi_smi_msg *msg);
+	int (*sender)(void *send_info, struct ipmi_smi_msg *msg);
 
 	/*
 	 * Called by the upper layer to request that we try to get
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 839247a4f48e..7294e4e89b79 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -3,6 +3,7 @@
 #define _IPV6_H
 
 #include <uapi/linux/ipv6.h>
+#include <linux/cache.h>
 
 #define ipv6_optlen(p)  (((p)->hdrlen+1) << 3)
 #define ipv6_authlen(p) (((p)->hdrlen+2) << 2)
@@ -10,9 +11,17 @@
  * This structure contains configuration options per IPv6 link.
  */
 struct ipv6_devconf {
-	__s32		forwarding;
+	/* RX & TX fastpath fields. */
+	__cacheline_group_begin(ipv6_devconf_read_txrx);
+	__s32		disable_ipv6;
 	__s32		hop_limit;
 	__s32		mtu6;
+	__s32		forwarding;
+	__s32		force_forwarding;
+	__s32		disable_policy;
+	__s32		proxy_ndp;
+	__cacheline_group_end(ipv6_devconf_read_txrx);
+
 	__s32		accept_ra;
 	__s32		accept_redirects;
 	__s32		autoconf;
@@ -27,12 +36,14 @@ struct ipv6_devconf {
 	__s32		use_tempaddr;
 	__s32		temp_valid_lft;
 	__s32		temp_prefered_lft;
+	__s32		regen_min_advance;
 	__s32		regen_max_retry;
 	__s32		max_desync_factor;
 	__s32		max_addresses;
 	__s32		accept_ra_defrtr;
 	__u32		ra_defrtr_metric;
 	__s32		accept_ra_min_hop_limit;
+	__s32		accept_ra_min_lft;
 	__s32		accept_ra_pinfo;
 	__s32		ignore_routes_with_linkdown;
 #ifdef CONFIG_IPV6_ROUTER_PREF
@@ -43,7 +54,6 @@ struct ipv6_devconf {
 	__s32		accept_ra_rt_info_max_plen;
 #endif
 #endif
-	__s32		proxy_ndp;
 	__s32		accept_source_route;
 	__s32		accept_ra_from_local;
 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
@@ -53,7 +63,6 @@ struct ipv6_devconf {
 #ifdef CONFIG_IPV6_MROUTE
 	atomic_t	mc_forwarding;
 #endif
-	__s32		disable_ipv6;
 	__s32		drop_unicast_in_l2_multicast;
 	__s32		accept_dad;
 	__s32		force_tllao;
@@ -74,13 +83,14 @@ struct ipv6_devconf {
 #endif
 	__u32		enhanced_dad;
 	__u32		addr_gen_mode;
-	__s32		disable_policy;
 	__s32           ndisc_tclass;
 	__s32		rpl_seg_enabled;
 	__u32		ioam6_id;
 	__u32		ioam6_id_wide;
 	__u8		ioam6_enabled;
 	__u8		ndisc_evict_nocarrier;
+	__u8		ra_honor_pio_life;
+	__u8		ra_honor_pio_pflag;
 
 	struct ctl_table_header *sysctl_header;
 };
@@ -146,6 +156,8 @@ struct inet6_skb_parm {
 #define IP6SKB_JUMBOGRAM      128
 #define IP6SKB_SEG6	      256
 #define IP6SKB_FAKEJUMBO      512
+#define IP6SKB_MULTIPATH      1024
+#define IP6SKB_MCROUTE        2048
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
@@ -197,56 +209,34 @@ struct inet6_cork {
 	struct ipv6_txoptions *opt;
 	u8 hop_limit;
 	u8 tclass;
+	u8 dontfrag:1;
 };
 
-/**
- * struct ipv6_pinfo - ipv6 private area
- *
- * In the struct sock hierarchy (tcp6_sock, upd6_sock, etc)
- * this _must_ be the last member, so that inet6_sk_generic
- * is able to calculate its offset from the base struct sock
- * by using the struct proto->slab_obj_size member. -acme
- */
+/* struct ipv6_pinfo - ipv6 private area */
 struct ipv6_pinfo {
+	/* Used in tx path (inet6_csk_route_socket(), ip6_xmit()) */
 	struct in6_addr 	saddr;
-	struct in6_pktinfo	sticky_pktinfo;
-	const struct in6_addr		*daddr_cache;
+	__be32			flow_label;
+	u32			dst_cookie;
+	struct ipv6_txoptions __rcu	*opt;
+	s16			hop_limit;
+	u8			pmtudisc;
+	u8			tclass;
 #ifdef CONFIG_IPV6_SUBTREES
-	const struct in6_addr		*saddr_cache;
+	bool			saddr_cache;
 #endif
+	bool			daddr_cache;
 
-	__be32			flow_label;
-	__u32			frag_size;
-
-	/*
-	 * Packed in 16bits.
-	 * Omit one shift by putting the signed field at MSB.
-	 */
-#if defined(__BIG_ENDIAN_BITFIELD)
-	__s16			hop_limit:9;
-	__u16			__unused_1:7;
-#else
-	__u16			__unused_1:7;
-	__s16			hop_limit:9;
-#endif
+	u8			mcast_hops;
+	u32			frag_size;
 
-#if defined(__BIG_ENDIAN_BITFIELD)
-	/* Packed in 16bits. */
-	__s16			mcast_hops:9;
-	__u16			__unused_2:6,
-				mc_loop:1;
-#else
-	__u16			mc_loop:1,
-				__unused_2:6;
-	__s16			mcast_hops:9;
-#endif
 	int			ucast_oif;
 	int			mcast_oif;
 
 	/* pktoption flags */
 	union {
 		struct {
-			__u16	srcrt:1,
+			u16	srcrt:1,
 				osrcrt:1,
 			        rxinfo:1,
 			        rxoinfo:1,
@@ -263,41 +253,38 @@ struct ipv6_pinfo {
 				recvfragsize:1;
 				/* 1 bits hole */
 		} bits;
-		__u16		all;
+		u16		all;
 	} rxopt;
 
 	/* sockopt flags */
-	__u16			recverr:1,
-	                        sndflow:1,
-				repflow:1,
-				pmtudisc:3,
-				padding:1,	/* 1 bit hole */
-				srcprefs:3,	/* 001: prefer temporary address
+	u8			srcprefs;	/* 001: prefer temporary address
 						 * 010: prefer public address
 						 * 100: prefer care-of address
 						 */
-				dontfrag:1,
-				autoflowlabel:1,
-				autoflowlabel_set:1,
-				mc_all:1,
-				recverr_rfc4884:1,
-				rtalert_isolate:1;
-	__u8			min_hopcount;
-	__u8			tclass;
+	u8			min_hopcount;
 	__be32			rcv_flowinfo;
+	struct in6_pktinfo	sticky_pktinfo;
 
-	__u32			dst_cookie;
-
-	struct ipv6_mc_socklist	__rcu *ipv6_mc_list;
-	struct ipv6_ac_socklist	*ipv6_ac_list;
-	struct ipv6_fl_socklist __rcu *ipv6_fl_list;
-
-	struct ipv6_txoptions __rcu	*opt;
 	struct sk_buff		*pktoptions;
 	struct sk_buff		*rxpmtu;
 	struct inet6_cork	cork;
+
+	struct ipv6_mc_socklist	__rcu *ipv6_mc_list;
+	struct ipv6_ac_socklist	*ipv6_ac_list;
 };
 
+/* We currently use available bits from inet_sk(sk)->inet_flags,
+ * this could change in the future.
+ */
+#define inet6_test_bit(nr, sk)			\
+	test_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet6_set_bit(nr, sk)			\
+	set_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet6_clear_bit(nr, sk)			\
+	clear_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags)
+#define inet6_assign_bit(nr, sk, val)		\
+	assign_bit(INET_FLAGS_##nr, &inet_sk(sk)->inet_flags, val)
+
 /* WARNING: don't change the layout of the members in {raw,udp,tcp}6_sock! */
 struct raw6_sock {
 	/* inet_sock has to be the first member of raw6_sock */
@@ -306,19 +293,19 @@ struct raw6_sock {
 	__u32			offset;		/* checksum offset  */
 	struct icmp6_filter	filter;
 	__u32			ip6mr_table;
-	/* ipv6_pinfo has to be the last member of raw6_sock, see inet6_sk_generic */
+	struct numa_drop_counters drop_counters;
 	struct ipv6_pinfo	inet6;
 };
 
 struct udp6_sock {
 	struct udp_sock	  udp;
-	/* ipv6_pinfo has to be the last member of udp6_sock, see inet6_sk_generic */
+
 	struct ipv6_pinfo inet6;
 };
 
 struct tcp6_sock {
 	struct tcp_sock	  tcp;
-	/* ipv6_pinfo has to be the last member of tcp6_sock, see inet6_sk_generic */
+
 	struct ipv6_pinfo inet6;
 };
 
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
new file mode 100644
index 000000000000..6ab913e57da0
--- /dev/null
+++ b/include/linux/irq-entry-common.h
@@ -0,0 +1,458 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_IRQENTRYCOMMON_H
+#define __LINUX_IRQENTRYCOMMON_H
+
+#include <linux/context_tracking.h>
+#include <linux/kmsan.h>
+#include <linux/rseq_entry.h>
+#include <linux/static_call_types.h>
+#include <linux/syscalls.h>
+#include <linux/tick.h>
+#include <linux/unwind_deferred.h>
+
+#include <asm/entry-common.h>
+
+/*
+ * Define dummy _TIF work flags if not defined by the architecture or for
+ * disabled functionality.
+ */
+#ifndef _TIF_PATCH_PENDING
+# define _TIF_PATCH_PENDING		(0)
+#endif
+
+/*
+ * TIF flags handled in exit_to_user_mode_loop()
+ */
+#ifndef ARCH_EXIT_TO_USER_MODE_WORK
+# define ARCH_EXIT_TO_USER_MODE_WORK		(0)
+#endif
+
+#define EXIT_TO_USER_MODE_WORK						\
+	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
+	 _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY |			\
+	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | _TIF_RSEQ |		\
+	 ARCH_EXIT_TO_USER_MODE_WORK)
+
+/**
+ * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Defaults to an empty implementation. Can be replaced by architecture
+ * specific code.
+ *
+ * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
+ * section. Use __always_inline so the compiler cannot push it out of line
+ * and make it instrumentable.
+ */
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
+
+#ifndef arch_enter_from_user_mode
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
+#endif
+
+/**
+ * arch_in_rcu_eqs - Architecture specific check for RCU extended quiescent
+ * states.
+ *
+ * Returns: true if the CPU is potentially in an RCU EQS, false otherwise.
+ *
+ * Architectures only need to define this if threads other than the idle thread
+ * may have an interruptible EQS. This does not need to handle idle threads. It
+ * is safe to over-estimate at the cost of redundant RCU management work.
+ *
+ * Invoked from irqentry_enter()
+ */
+#ifndef arch_in_rcu_eqs
+static __always_inline bool arch_in_rcu_eqs(void) { return false; }
+#endif
+
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct and interrupts are still
+ * disabled. The subsequent functions can be instrumented.
+ *
+ * This is invoked when there is architecture specific functionality to be
+ * done between establishing state and enabling interrupts. The caller must
+ * enable interrupts before invoking syscall_enter_from_user_mode_work().
+ */
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_enter_from_user_mode(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(__ct_state() != CT_STATE_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
+/**
+ * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Defaults to local_irq_enable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
+
+#ifndef local_irq_enable_exit_to_user
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
+{
+	local_irq_enable();
+}
+#endif
+
+/**
+ * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
+ *
+ * Defaults to local_irq_disable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_disable_exit_to_user(void);
+
+#ifndef local_irq_disable_exit_to_user
+static inline void local_irq_disable_exit_to_user(void)
+{
+	local_irq_disable();
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
+ *				 to user mode.
+ * @regs:	Pointer to currents pt_regs
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_loop() with interrupt enabled
+ *
+ * Defaults to NOOP. Can be supplied by architecture specific code.
+ */
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+					       unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_work
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+					       unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_prepare - Architecture specific preparation for
+ *				    exit to user mode.
+ * @regs:	Pointer to currents pt_regs
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ */
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_prepare
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode - Architecture specific final work before
+ *			    exit to user mode.
+ *
+ * Invoked from exit_to_user_mode() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ *
+ * This needs to be __always_inline because it is non-instrumentable code
+ * invoked after context tracking switched to user mode.
+ *
+ * An architecture implementation must not do anything complex, no locking
+ * etc. The main purpose is for speculation mitigations.
+ */
+static __always_inline void arch_exit_to_user_mode(void);
+
+#ifndef arch_exit_to_user_mode
+static __always_inline void arch_exit_to_user_mode(void) { }
+#endif
+
+/**
+ * arch_do_signal_or_restart -  Architecture specific signal delivery function
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from exit_to_user_mode_loop().
+ */
+void arch_do_signal_or_restart(struct pt_regs *regs);
+
+/* Handle pending TIF work */
+unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work);
+
+/**
+ * __exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs:	Pointer to pt_regs on entry stack
+ *
+ * 1) check that interrupts are disabled
+ * 2) call tick_nohz_user_enter_prepare()
+ * 3) call exit_to_user_mode_loop() if any flags from
+ *    EXIT_TO_USER_MODE_WORK are set
+ * 4) check that interrupts are still disabled
+ *
+ * Don't invoke directly, use the syscall/irqentry_ prefixed variants below
+ */
+static __always_inline void __exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work;
+
+	lockdep_assert_irqs_disabled();
+
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	tick_nohz_user_enter_prepare();
+
+	ti_work = read_thread_flags();
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+}
+
+static __always_inline void __exit_to_user_mode_validate(void)
+{
+	/* Ensure that kernel state is sane for a return to userspace */
+	kmap_assert_nomap();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+/* Temporary workaround to keep ARM64 alive */
+static __always_inline void exit_to_user_mode_prepare_legacy(struct pt_regs *regs)
+{
+	__exit_to_user_mode_prepare(regs);
+	rseq_exit_to_user_mode_legacy();
+	__exit_to_user_mode_validate();
+}
+
+/**
+ * syscall_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs:	Pointer to pt_regs on entry stack
+ *
+ * Wrapper around __exit_to_user_mode_prepare() to separate the exit work for
+ * syscalls and interrupts.
+ */
+static __always_inline void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	__exit_to_user_mode_prepare(regs);
+	rseq_syscall_exit_to_user_mode();
+	__exit_to_user_mode_validate();
+}
+
+/**
+ * irqentry_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs:	Pointer to pt_regs on entry stack
+ *
+ * Wrapper around __exit_to_user_mode_prepare() to separate the exit work for
+ * syscalls and interrupts.
+ */
+static __always_inline void irqentry_exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	__exit_to_user_mode_prepare(regs);
+	rseq_irqentry_exit_to_user_mode();
+	__exit_to_user_mode_validate();
+}
+
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interrupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.: arch_exit_to_user_mode()
+ * 4) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code when syscall_exit_to_user_mode()
+ * is not suitable as the last step before returning to userspace. Must be
+ * invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke syscall_exit_to_user_mode_work() before this.
+ */
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	unwind_reset_info();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare();
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/**
+ * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from architecture specific entry code with interrupts disabled.
+ * Can only be called when the interrupt entry came from user mode. The
+ * calling code must be non-instrumentable.  When the function returns all
+ * state is correct and the subsequent functions can be instrumented.
+ *
+ * The function establishes state (lockdep, RCU (context tracking), tracing)
+ */
+static __always_inline void irqentry_enter_from_user_mode(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+	rseq_note_user_irq_entry();
+}
+
+/**
+ * irqentry_exit_to_user_mode - Interrupt exit work
+ * @regs:	Pointer to current's pt_regs
+ *
+ * Invoked with interrupts disabled and fully valid regs. Returns with all
+ * work handled, interrupts disabled such that the caller can immediately
+ * switch to user mode. Called from architecture specific interrupt
+ * handling code.
+ *
+ * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
+ * Interrupt exit is not invoking #1 which is the syscall specific one time
+ * work.
+ */
+static __always_inline void irqentry_exit_to_user_mode(struct pt_regs *regs)
+{
+	instrumentation_begin();
+	irqentry_exit_to_user_mode_prepare(regs);
+	instrumentation_end();
+	exit_to_user_mode();
+}
+
+#ifndef irqentry_state
+/**
+ * struct irqentry_state - Opaque object for exception state storage
+ * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
+ *            exit path has to invoke ct_irq_exit().
+ * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
+ *           lockdep state is restored correctly on exit from nmi.
+ *
+ * This opaque object is filled in by the irqentry_*_enter() functions and
+ * must be passed back into the corresponding irqentry_*_exit() functions
+ * when the exception is complete.
+ *
+ * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
+ * and all members private.  Descriptions of the members are provided to aid in
+ * the maintenance of the irqentry_*() functions.
+ */
+typedef struct irqentry_state {
+	union {
+		bool	exit_rcu;
+		bool	lockdep;
+	};
+} irqentry_state_t;
+#endif
+
+/**
+ * irqentry_enter - Handle state tracking on ordinary interrupt entries
+ * @regs:	Pointer to pt_regs of interrupted context
+ *
+ * Invokes:
+ *  - lockdep irqflag state tracking as low level ASM entry disabled
+ *    interrupts.
+ *
+ *  - Context tracking if the exception hit user mode.
+ *
+ *  - The hardirq tracer to keep the state consistent as low level ASM
+ *    entry disabled interrupts.
+ *
+ * As a precondition, this requires that the entry came from user mode,
+ * idle, or a kernel context in which RCU is watching.
+ *
+ * For kernel mode entries RCU handling is done conditional. If RCU is
+ * watching then the only RCU requirement is to check whether the tick has
+ * to be restarted. If RCU is not watching then ct_irq_enter() has to be
+ * invoked on entry and ct_irq_exit() on exit.
+ *
+ * Avoiding the ct_irq_enter/exit() calls is an optimization but also
+ * solves the problem of kernel mode pagefaults which can schedule, which
+ * is not possible after invoking ct_irq_enter() without undoing it.
+ *
+ * For user mode entries irqentry_enter_from_user_mode() is invoked to
+ * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
+ * would not be possible.
+ *
+ * Returns: An opaque object that must be passed to idtentry_exit()
+ */
+irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
+ *
+ * Conditional reschedule with additional sanity checks.
+ */
+void raw_irqentry_exit_cond_resched(void);
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
+#define irqentry_exit_cond_resched_dynamic_disabled	NULL
+DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void);
+#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
+#endif
+#else /* CONFIG_PREEMPT_DYNAMIC */
+#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
+#endif /* CONFIG_PREEMPT_DYNAMIC */
+
+/**
+ * irqentry_exit - Handle return from exception that used irqentry_enter()
+ * @regs:	Pointer to pt_regs (exception entry regs)
+ * @state:	Return value from matching call to irqentry_enter()
+ *
+ * Depending on the return target (kernel/user) this runs the necessary
+ * preemption and work checks if possible and required and returns to
+ * the caller with interrupts disabled and no further work pending.
+ *
+ * This is the last action before returning to the low level ASM code which
+ * just needs to return to the appropriate context.
+ *
+ * Counterpart to irqentry_enter().
+ */
+void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
+
+/**
+ * irqentry_nmi_enter - Handle NMI entry
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Similar to irqentry_enter() but taking care of the NMI constraints.
+ */
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_nmi_exit - Handle return from NMI handling
+ * @regs:	Pointer to pt_regs (NMI entry regs)
+ * @irq_state:	Return value from matching call to irqentry_nmi_enter()
+ *
+ * Last action before returning to the low level assembly code.
+ *
+ * Counterpart to irqentry_nmi_enter().
+ */
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
+
+#endif
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b1b28affb32a..4a9f1d7b08c3 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -64,7 +64,6 @@ enum irqchip_irq_state;
  * IRQ_NOAUTOEN			- Interrupt is not automatically enabled in
  *				  request/setup_irq()
  * IRQ_NO_BALANCING		- Interrupt cannot be balanced (affinity set)
- * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
  * IRQ_NESTED_THREAD		- Interrupt nests into another thread
  * IRQ_PER_CPU_DEVID		- Dev_id is a per-cpu variable
  * IRQ_IS_POLLED		- Always polled by another interrupt. Exclude
@@ -93,7 +92,6 @@ enum {
 	IRQ_NOREQUEST		= (1 << 11),
 	IRQ_NOAUTOEN		= (1 << 12),
 	IRQ_NO_BALANCING	= (1 << 13),
-	IRQ_MOVE_PCNTXT		= (1 << 14),
 	IRQ_NESTED_THREAD	= (1 << 15),
 	IRQ_NOTHREAD		= (1 << 16),
 	IRQ_PER_CPU_DEVID	= (1 << 17),
@@ -105,7 +103,7 @@ enum {
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
-	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
+	 IRQ_NOAUTOEN | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
 	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN)
 
@@ -115,7 +113,7 @@ enum {
  * Return value for chip->irq_set_affinity()
  *
  * IRQ_SET_MASK_OK	- OK, core updates irq_common_data.affinity
- * IRQ_SET_MASK_NOCPY	- OK, chip did update irq_common_data.affinity
+ * IRQ_SET_MASK_NOCOPY	- OK, chip did update irq_common_data.affinity
  * IRQ_SET_MASK_OK_DONE	- Same as IRQ_SET_MASK_OK for core. Special code to
  *			  support stacked irqchips, which indicates skipping
  *			  all descendant irqchips.
@@ -179,7 +177,7 @@ struct irq_common_data {
 struct irq_data {
 	u32			mask;
 	unsigned int		irq;
-	unsigned long		hwirq;
+	irq_hw_number_t		hwirq;
 	struct irq_common_data	*common;
 	struct irq_chip		*chip;
 	struct irq_domain	*domain;
@@ -201,8 +199,6 @@ struct irq_data {
  * IRQD_LEVEL			- Interrupt is level triggered
  * IRQD_WAKEUP_STATE		- Interrupt is configured for wakeup
  *				  from suspend
- * IRQD_MOVE_PCNTXT		- Interrupt can be moved in process
- *				  context
  * IRQD_IRQ_DISABLED		- Disabled state of the interrupt
  * IRQD_IRQ_MASKED		- Masked state of the interrupt
  * IRQD_IRQ_INPROGRESS		- In progress state of the interrupt
@@ -215,40 +211,39 @@ struct irq_data {
  * IRQD_SINGLE_TARGET		- IRQ allows only a single affinity target
  * IRQD_DEFAULT_TRIGGER_SET	- Expected trigger already been set
  * IRQD_CAN_RESERVE		- Can use reservation mode
- * IRQD_MSI_NOMASK_QUIRK	- Non-maskable MSI quirk for affinity change
- *				  required
  * IRQD_HANDLE_ENFORCE_IRQCTX	- Enforce that handle_irq_*() is only invoked
  *				  from actual interrupt context.
  * IRQD_AFFINITY_ON_ACTIVATE	- Affinity is set on activation. Don't call
  *				  irq_chip::irq_set_affinity() when deactivated.
  * IRQD_IRQ_ENABLED_ON_SUSPEND	- Interrupt is enabled on suspend by irq pm if
  *				  irqchip have flag IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND set.
+ * IRQD_RESEND_WHEN_IN_PROGRESS	- Interrupt may fire when already in progress in which
+ *				  case it must be resent at the next available opportunity.
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
-	IRQD_SETAFFINITY_PENDING	= (1 <<  8),
-	IRQD_ACTIVATED			= (1 <<  9),
-	IRQD_NO_BALANCING		= (1 << 10),
-	IRQD_PER_CPU			= (1 << 11),
-	IRQD_AFFINITY_SET		= (1 << 12),
-	IRQD_LEVEL			= (1 << 13),
-	IRQD_WAKEUP_STATE		= (1 << 14),
-	IRQD_MOVE_PCNTXT		= (1 << 15),
-	IRQD_IRQ_DISABLED		= (1 << 16),
-	IRQD_IRQ_MASKED			= (1 << 17),
-	IRQD_IRQ_INPROGRESS		= (1 << 18),
-	IRQD_WAKEUP_ARMED		= (1 << 19),
-	IRQD_FORWARDED_TO_VCPU		= (1 << 20),
-	IRQD_AFFINITY_MANAGED		= (1 << 21),
-	IRQD_IRQ_STARTED		= (1 << 22),
-	IRQD_MANAGED_SHUTDOWN		= (1 << 23),
-	IRQD_SINGLE_TARGET		= (1 << 24),
-	IRQD_DEFAULT_TRIGGER_SET	= (1 << 25),
-	IRQD_CAN_RESERVE		= (1 << 26),
-	IRQD_MSI_NOMASK_QUIRK		= (1 << 27),
-	IRQD_HANDLE_ENFORCE_IRQCTX	= (1 << 28),
-	IRQD_AFFINITY_ON_ACTIVATE	= (1 << 29),
-	IRQD_IRQ_ENABLED_ON_SUSPEND	= (1 << 30),
+	IRQD_SETAFFINITY_PENDING	= BIT(8),
+	IRQD_ACTIVATED			= BIT(9),
+	IRQD_NO_BALANCING		= BIT(10),
+	IRQD_PER_CPU			= BIT(11),
+	IRQD_AFFINITY_SET		= BIT(12),
+	IRQD_LEVEL			= BIT(13),
+	IRQD_WAKEUP_STATE		= BIT(14),
+	IRQD_IRQ_DISABLED		= BIT(16),
+	IRQD_IRQ_MASKED			= BIT(17),
+	IRQD_IRQ_INPROGRESS		= BIT(18),
+	IRQD_WAKEUP_ARMED		= BIT(19),
+	IRQD_FORWARDED_TO_VCPU		= BIT(20),
+	IRQD_AFFINITY_MANAGED		= BIT(21),
+	IRQD_IRQ_STARTED		= BIT(22),
+	IRQD_MANAGED_SHUTDOWN		= BIT(23),
+	IRQD_SINGLE_TARGET		= BIT(24),
+	IRQD_DEFAULT_TRIGGER_SET	= BIT(25),
+	IRQD_CAN_RESERVE		= BIT(26),
+	IRQD_HANDLE_ENFORCE_IRQCTX	= BIT(27),
+	IRQD_AFFINITY_ON_ACTIVATE	= BIT(28),
+	IRQD_IRQ_ENABLED_ON_SUSPEND	= BIT(29),
+	IRQD_RESEND_WHEN_IN_PROGRESS    = BIT(30),
 };
 
 #define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
@@ -338,11 +333,6 @@ static inline bool irqd_is_wakeup_set(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_WAKEUP_STATE;
 }
 
-static inline bool irqd_can_move_in_process_context(struct irq_data *d)
-{
-	return __irqd_to_state(d) & IRQD_MOVE_PCNTXT;
-}
-
 static inline bool irqd_irq_disabled(struct irq_data *d)
 {
 	return __irqd_to_state(d) & IRQD_IRQ_DISABLED;
@@ -423,29 +413,24 @@ static inline bool irqd_can_reserve(struct irq_data *d)
 	return __irqd_to_state(d) & IRQD_CAN_RESERVE;
 }
 
-static inline void irqd_set_msi_nomask_quirk(struct irq_data *d)
+static inline void irqd_set_affinity_on_activate(struct irq_data *d)
 {
-	__irqd_to_state(d) |= IRQD_MSI_NOMASK_QUIRK;
+	__irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE;
 }
 
-static inline void irqd_clr_msi_nomask_quirk(struct irq_data *d)
+static inline bool irqd_affinity_on_activate(struct irq_data *d)
 {
-	__irqd_to_state(d) &= ~IRQD_MSI_NOMASK_QUIRK;
+	return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE;
 }
 
-static inline bool irqd_msi_nomask_quirk(struct irq_data *d)
+static inline void irqd_set_resend_when_in_progress(struct irq_data *d)
 {
-	return __irqd_to_state(d) & IRQD_MSI_NOMASK_QUIRK;
+	__irqd_to_state(d) |= IRQD_RESEND_WHEN_IN_PROGRESS;
 }
 
-static inline void irqd_set_affinity_on_activate(struct irq_data *d)
+static inline bool irqd_needs_resend_when_in_progress(struct irq_data *d)
 {
-	__irqd_to_state(d) |= IRQD_AFFINITY_ON_ACTIVATE;
-}
-
-static inline bool irqd_affinity_on_activate(struct irq_data *d)
-{
-	return __irqd_to_state(d) & IRQD_AFFINITY_ON_ACTIVATE;
+	return __irqd_to_state(d) & IRQD_RESEND_WHEN_IN_PROGRESS;
 }
 
 #undef __irqd_to_state
@@ -501,6 +486,7 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  * @ipi_send_mask:	send an IPI to destination cpus in cpumask
  * @irq_nmi_setup:	function called from core code before enabling an NMI
  * @irq_nmi_teardown:	function called from core code after disabling an NMI
+ * @irq_force_complete_move:	optional function to force complete pending irq move
  * @flags:		chip specific flags
  */
 struct irq_chip {
@@ -552,6 +538,8 @@ struct irq_chip {
 	int		(*irq_nmi_setup)(struct irq_data *data);
 	void		(*irq_nmi_teardown)(struct irq_data *data);
 
+	void		(*irq_force_complete_move)(struct irq_data *data);
+
 	unsigned long	flags;
 };
 
@@ -572,6 +560,7 @@ struct irq_chip {
  *                                    in the suspend path if they are in disabled state
  * IRQCHIP_AFFINITY_PRE_STARTUP:      Default affinity update before startup
  * IRQCHIP_IMMUTABLE:		      Don't ever change anything in this chip
+ * IRQCHIP_MOVE_DEFERRED:	      Move the interrupt in actual interrupt context
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED			= (1 <<  0),
@@ -586,6 +575,7 @@ enum {
 	IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND	= (1 <<  9),
 	IRQCHIP_AFFINITY_PRE_STARTUP		= (1 << 10),
 	IRQCHIP_IMMUTABLE			= (1 << 11),
+	IRQCHIP_MOVE_DEFERRED			= (1 << 12),
 };
 
 #include <linux/irqdesc.h>
@@ -607,7 +597,6 @@ enum {
 
 struct irqaction;
 extern int setup_percpu_irq(unsigned int irq, struct irqaction *new);
-extern void remove_percpu_irq(unsigned int irq, struct irqaction *act);
 
 #ifdef CONFIG_DEPRECATED_IRQ_CPU_ONOFFLINE
 extern void irq_cpu_online(void);
@@ -625,6 +614,7 @@ extern int irq_affinity_online_cpu(unsigned int cpu);
 #endif
 
 #if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
+bool irq_can_move_in_process_context(struct irq_data *data);
 void __irq_move_irq(struct irq_data *data);
 static inline void irq_move_irq(struct irq_data *data)
 {
@@ -632,11 +622,10 @@ static inline void irq_move_irq(struct irq_data *data)
 		__irq_move_irq(data);
 }
 void irq_move_masked_irq(struct irq_data *data);
-void irq_force_complete_move(struct irq_desc *desc);
 #else
+static inline bool irq_can_move_in_process_context(struct irq_data *data) { return true; }
 static inline void irq_move_irq(struct irq_data *data) { }
 static inline void irq_move_masked_irq(struct irq_data *data) { }
-static inline void irq_force_complete_move(struct irq_desc *desc) { }
 #endif
 
 extern int no_irq_affinity;
@@ -666,7 +655,6 @@ extern void handle_bad_irq(struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
 extern void handle_fasteoi_nmi(struct irq_desc *desc);
-extern void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc);
 
 extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
 extern int irq_chip_pm_get(struct irq_data *data);
@@ -680,6 +668,8 @@ extern int irq_chip_set_parent_state(struct irq_data *data,
 extern int irq_chip_get_parent_state(struct irq_data *data,
 				     enum irqchip_irq_state which,
 				     bool *state);
+extern void irq_chip_shutdown_parent(struct irq_data *data);
+extern unsigned int irq_chip_startup_parent(struct irq_data *data);
 extern void irq_chip_enable_parent(struct irq_data *data);
 extern void irq_chip_disable_parent(struct irq_data *data);
 extern void irq_chip_ack_parent(struct irq_data *data);
@@ -699,6 +689,9 @@ extern int irq_chip_request_resources_parent(struct irq_data *data);
 extern void irq_chip_release_resources_parent(struct irq_data *data);
 #endif
 
+/* Disable or mask interrupts during a kernel kexec */
+extern void machine_kexec_mask_interrupts(void);
+
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret);
 
@@ -707,7 +700,7 @@ extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret);
 extern int noirqdebug_setup(char *str);
 
 /* Checks whether the interrupt can be requested by request_irq(): */
-extern int can_request_irq(unsigned int irq, unsigned long irqflags);
+extern bool can_request_irq(unsigned int irq, unsigned long irqflags);
 
 /* Dummy irq-chip implementations: */
 extern struct irq_chip no_irq_chip;
@@ -725,10 +718,6 @@ static inline void irq_set_chip_and_handler(unsigned int irq,
 }
 
 extern int irq_set_percpu_devid(unsigned int irq);
-extern int irq_set_percpu_devid_partition(unsigned int irq,
-					  const struct cpumask *affinity);
-extern int irq_get_percpu_devid_partition(unsigned int irq,
-					  struct cpumask *affinity);
 
 extern void
 __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
@@ -984,10 +973,6 @@ static inline void irq_free_desc(unsigned int irq)
 	irq_free_descs(irq, 1);
 }
 
-#ifdef CONFIG_GENERIC_IRQ_LEGACY
-void irq_init_desc(unsigned int irq);
-#endif
-
 /**
  * struct irq_chip_regs - register offsets for struct irq_gci
  * @enable:	Enable register offset to reg_base
@@ -996,7 +981,6 @@ void irq_init_desc(unsigned int irq);
  * @ack:	Ack register offset to reg_base
  * @eoi:	Eoi register offset to reg_base
  * @type:	Type configuration register offset to reg_base
- * @polarity:	Polarity configuration register offset to reg_base
  */
 struct irq_chip_regs {
 	unsigned long		enable;
@@ -1005,7 +989,6 @@ struct irq_chip_regs {
 	unsigned long		ack;
 	unsigned long		eoi;
 	unsigned long		type;
-	unsigned long		polarity;
 };
 
 /**
@@ -1045,8 +1028,6 @@ struct irq_chip_type {
  * @irq_base:		Interrupt base nr for this chip
  * @irq_cnt:		Number of interrupts handled by this chip
  * @mask_cache:		Cached mask register shared between all chip types
- * @type_cache:		Cached type register
- * @polarity_cache:	Cached polarity register
  * @wake_enabled:	Interrupt can wakeup from suspend
  * @wake_active:	Interrupt is marked as an wakeup from suspend source
  * @num_ct:		Number of available irq_chip_type instances (usually 1)
@@ -1073,8 +1054,6 @@ struct irq_chip_generic {
 	unsigned int		irq_base;
 	unsigned int		irq_cnt;
 	u32			mask_cache;
-	u32			type_cache;
-	u32			polarity_cache;
 	u32			wake_enabled;
 	u32			wake_active;
 	unsigned int		num_ct;
@@ -1111,6 +1090,7 @@ enum irq_gc_flags {
  * @irq_flags_to_set:	IRQ* flags to set on irq setup
  * @irq_flags_to_clear:	IRQ* flags to clear on irq setup
  * @gc_flags:		Generic chip specific setup flags
+ * @exit:		Function called on each chip when they are destroyed.
  * @gc:			Array of pointers to generic interrupt chips
  */
 struct irq_domain_chip_generic {
@@ -1119,9 +1099,37 @@ struct irq_domain_chip_generic {
 	unsigned int		irq_flags_to_clear;
 	unsigned int		irq_flags_to_set;
 	enum irq_gc_flags	gc_flags;
+	void			(*exit)(struct irq_chip_generic *gc);
 	struct irq_chip_generic	*gc[];
 };
 
+/**
+ * struct irq_domain_chip_generic_info - Generic chip information structure
+ * @name:		Name of the generic interrupt chip
+ * @handler:		Interrupt handler used by the generic interrupt chip
+ * @irqs_per_chip:	Number of interrupts each chip handles (max 32)
+ * @num_ct:		Number of irq_chip_type instances associated with each
+ *			chip
+ * @irq_flags_to_clear:	IRQ_* bits to clear in the mapping function
+ * @irq_flags_to_set:	IRQ_* bits to set in the mapping function
+ * @gc_flags:		Generic chip specific setup flags
+ * @init:		Function called on each chip when they are created.
+ *			Allow to do some additional chip initialisation.
+ * @exit:		Function called on each chip when they are destroyed.
+ *			Allow to do some chip cleanup operation.
+ */
+struct irq_domain_chip_generic_info {
+	const char		*name;
+	irq_flow_handler_t	handler;
+	unsigned int		irqs_per_chip;
+	unsigned int		num_ct;
+	unsigned int		irq_flags_to_clear;
+	unsigned int		irq_flags_to_set;
+	enum irq_gc_flags	gc_flags;
+	int			(*init)(struct irq_chip_generic *gc);
+	void			(*exit)(struct irq_chip_generic *gc);
+};
+
 /* Generic chip callback functions */
 void irq_gc_noop(struct irq_data *d);
 void irq_gc_mask_disable_reg(struct irq_data *d);
@@ -1158,6 +1166,20 @@ int devm_irq_setup_generic_chip(struct device *dev, struct irq_chip_generic *gc,
 
 struct irq_chip_generic *irq_get_domain_generic_chip(struct irq_domain *d, unsigned int hw_irq);
 
+#ifdef CONFIG_GENERIC_IRQ_CHIP
+int irq_domain_alloc_generic_chips(struct irq_domain *d,
+				   const struct irq_domain_chip_generic_info *info);
+void irq_domain_remove_generic_chips(struct irq_domain *d);
+#else
+static inline int
+irq_domain_alloc_generic_chips(struct irq_domain *d,
+			       const struct irq_domain_chip_generic_info *info)
+{
+	return -EINVAL;
+}
+static inline void irq_domain_remove_generic_chips(struct irq_domain *d) { }
+#endif /* CONFIG_GENERIC_IRQ_CHIP */
+
 int __irq_alloc_domain_generic_chips(struct irq_domain *d, int irqs_per_chip,
 				     int num_ct, const char *name,
 				     irq_flow_handler_t handler,
@@ -1192,31 +1214,6 @@ static inline struct irq_chip_type *irq_data_get_chip_type(struct irq_data *d)
 
 #define IRQ_MSK(n) (u32)((n) < 32 ? ((1 << (n)) - 1) : UINT_MAX)
 
-#ifdef CONFIG_SMP
-static inline void irq_gc_lock(struct irq_chip_generic *gc)
-{
-	raw_spin_lock(&gc->lock);
-}
-
-static inline void irq_gc_unlock(struct irq_chip_generic *gc)
-{
-	raw_spin_unlock(&gc->lock);
-}
-#else
-static inline void irq_gc_lock(struct irq_chip_generic *gc) { }
-static inline void irq_gc_unlock(struct irq_chip_generic *gc) { }
-#endif
-
-/*
- * The irqsave variants are for usage in non interrupt code. Do not use
- * them in irq_chip callbacks. Use irq_gc_lock() instead.
- */
-#define irq_gc_lock_irqsave(gc, flags)	\
-	raw_spin_lock_irqsave(&(gc)->lock, flags)
-
-#define irq_gc_unlock_irqrestore(gc, flags)	\
-	raw_spin_unlock_irqrestore(&(gc)->lock, flags)
-
 static inline void irq_reg_writel(struct irq_chip_generic *gc,
 				  u32 val, int reg_offset)
 {
diff --git a/include/linux/irq_sim.h b/include/linux/irq_sim.h
index ab831e5ae748..89b4d8ff274b 100644
--- a/include/linux/irq_sim.h
+++ b/include/linux/irq_sim.h
@@ -16,11 +16,28 @@
  * requested like normal irqs and enqueued from process context.
  */
 
+struct irq_sim_ops {
+	int (*irq_sim_irq_requested)(struct irq_domain *domain,
+				     irq_hw_number_t hwirq, void *data);
+	void (*irq_sim_irq_released)(struct irq_domain *domain,
+				     irq_hw_number_t hwirq, void *data);
+};
+
 struct irq_domain *irq_domain_create_sim(struct fwnode_handle *fwnode,
 					 unsigned int num_irqs);
 struct irq_domain *devm_irq_domain_create_sim(struct device *dev,
 					      struct fwnode_handle *fwnode,
 					      unsigned int num_irqs);
+struct irq_domain *irq_domain_create_sim_full(struct fwnode_handle *fwnode,
+					      unsigned int num_irqs,
+					      const struct irq_sim_ops *ops,
+					      void *data);
+struct irq_domain *
+devm_irq_domain_create_sim_full(struct device *dev,
+				struct fwnode_handle *fwnode,
+				unsigned int num_irqs,
+				const struct irq_sim_ops *ops,
+				void *data);
 void irq_domain_remove_sim(struct irq_domain *domain);
 
 #endif /* _LINUX_IRQ_SIM_H */
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 8cd11a223260..c5afd053ae32 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -2,8 +2,9 @@
 #ifndef _LINUX_IRQ_WORK_H
 #define _LINUX_IRQ_WORK_H
 
-#include <linux/smp_types.h>
+#include <linux/irq_work_types.h>
 #include <linux/rcuwait.h>
+#include <linux/smp_types.h>
 
 /*
  * An entry can be in one of four states:
@@ -14,12 +15,6 @@
  * busy      NULL, 2 -> {free, claimed} : callback in progress, can be claimed
  */
 
-struct irq_work {
-	struct __call_single_node node;
-	void (*func)(struct irq_work *);
-	struct rcuwait irqwait;
-};
-
 #define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){	\
 	.node = { .u_flags = (_flags), },			\
 	.func = (_func),					\
@@ -66,6 +61,9 @@ void irq_work_sync(struct irq_work *work);
 void irq_work_run(void);
 bool irq_work_needs_cpu(void);
 void irq_work_single(void *arg);
+
+void arch_irq_work_raise(void);
+
 #else
 static inline bool irq_work_needs_cpu(void) { return false; }
 static inline void irq_work_run(void) { }
diff --git a/include/linux/irq_work_types.h b/include/linux/irq_work_types.h
new file mode 100644
index 000000000000..73abec5bb06e
--- /dev/null
+++ b/include/linux/irq_work_types.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IRQ_WORK_TYPES_H
+#define _LINUX_IRQ_WORK_TYPES_H
+
+#include <linux/smp_types.h>
+#include <linux/types.h>
+
+struct irq_work {
+	struct __call_single_node	node;
+	void				(*func)(struct irq_work *);
+	struct rcuwait			irqwait;
+};
+
+#endif
diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h
index 9bdb2a781841..ede1fa938152 100644
--- a/include/linux/irqbypass.h
+++ b/include/linux/irqbypass.h
@@ -10,6 +10,7 @@
 
 #include <linux/list.h>
 
+struct eventfd_ctx;
 struct irq_bypass_consumer;
 
 /*
@@ -18,20 +19,22 @@ struct irq_bypass_consumer;
  * The IRQ bypass manager is a simple set of lists and callbacks that allows
  * IRQ producers (ex. physical interrupt sources) to be matched to IRQ
  * consumers (ex. virtualization hardware that allows IRQ bypass or offload)
- * via a shared token (ex. eventfd_ctx).  Producers and consumers register
- * independently.  When a token match is found, the optional @stop callback
- * will be called for each participant.  The pair will then be connected via
- * the @add_* callbacks, and finally the optional @start callback will allow
- * any final coordination.  When either participant is unregistered, the
- * process is repeated using the @del_* callbacks in place of the @add_*
- * callbacks.  Match tokens must be unique per producer/consumer, 1:N pairings
- * are not supported.
+ * via a shared eventfd_ctx.  Producers and consumers register independently.
+ * When a producer and consumer are paired, i.e. an eventfd match is found, the
+ * optional @stop callback will be called for each participant.  The pair will
+ * then be connected via the @add_* callbacks, and finally the optional @start
+ * callback will allow any final coordination.  When either participant is
+ * unregistered, the process is repeated using the @del_* callbacks in place of
+ * the @add_* callbacks.  eventfds must be unique per producer/consumer, 1:N
+ * pairings are not supported.
  */
 
+struct irq_bypass_consumer;
+
 /**
  * struct irq_bypass_producer - IRQ bypass producer definition
- * @node: IRQ bypass manager private list management
- * @token: opaque token to match between producer and consumer (non-NULL)
+ * @eventfd: eventfd context used to match producers and consumers
+ * @consumer: The connected consumer (NULL if no connection)
  * @irq: Linux IRQ number for the producer device
  * @add_consumer: Connect the IRQ producer to an IRQ consumer (optional)
  * @del_consumer: Disconnect the IRQ producer from an IRQ consumer (optional)
@@ -43,8 +46,8 @@ struct irq_bypass_consumer;
  * for a physical device assigned to a VM.
  */
 struct irq_bypass_producer {
-	struct list_head node;
-	void *token;
+	struct eventfd_ctx *eventfd;
+	struct irq_bypass_consumer *consumer;
 	int irq;
 	int (*add_consumer)(struct irq_bypass_producer *,
 			    struct irq_bypass_consumer *);
@@ -56,8 +59,8 @@ struct irq_bypass_producer {
 
 /**
  * struct irq_bypass_consumer - IRQ bypass consumer definition
- * @node: IRQ bypass manager private list management
- * @token: opaque token to match between producer and consumer (non-NULL)
+ * @eventfd: eventfd context used to match producers and consumers
+ * @producer: The connected producer (NULL if no connection)
  * @add_producer: Connect the IRQ consumer to an IRQ producer
  * @del_producer: Disconnect the IRQ consumer from an IRQ producer
  * @stop: Perform any quiesce operations necessary prior to add/del (optional)
@@ -69,8 +72,9 @@ struct irq_bypass_producer {
  * portions of the interrupt handling to the VM.
  */
 struct irq_bypass_consumer {
-	struct list_head node;
-	void *token;
+	struct eventfd_ctx *eventfd;
+	struct irq_bypass_producer *producer;
+
 	int (*add_producer)(struct irq_bypass_consumer *,
 			    struct irq_bypass_producer *);
 	void (*del_producer)(struct irq_bypass_consumer *,
@@ -79,9 +83,11 @@ struct irq_bypass_consumer {
 	void (*start)(struct irq_bypass_consumer *);
 };
 
-int irq_bypass_register_producer(struct irq_bypass_producer *);
-void irq_bypass_unregister_producer(struct irq_bypass_producer *);
-int irq_bypass_register_consumer(struct irq_bypass_consumer *);
-void irq_bypass_unregister_consumer(struct irq_bypass_consumer *);
+int irq_bypass_register_producer(struct irq_bypass_producer *producer,
+				 struct eventfd_ctx *eventfd, int irq);
+void irq_bypass_unregister_producer(struct irq_bypass_producer *producer);
+int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer,
+				 struct eventfd_ctx *eventfd);
+void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer);
 
 #endif /* IRQBYPASS_H */
diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h
index d5e6024cb2a8..bc4ddacd6ddc 100644
--- a/include/linux/irqchip.h
+++ b/include/linux/irqchip.h
@@ -17,12 +17,18 @@
 #include <linux/of_irq.h>
 #include <linux/platform_device.h>
 
+typedef int (*platform_irq_probe_t)(struct platform_device *, struct device_node *);
+
 /* Undefined on purpose */
 extern of_irq_init_cb_t typecheck_irq_init_cb;
+extern platform_irq_probe_t typecheck_irq_probe;
 
 #define typecheck_irq_init_cb(fn)					\
 	(__typecheck(typecheck_irq_init_cb, &fn) ? fn : fn)
 
+#define typecheck_irq_probe(fn)						\
+	(__typecheck(typecheck_irq_probe, &fn) ? fn : fn)
+
 /*
  * This macro must be used by the different irqchip drivers to declare
  * the association between their DT compatible string and their
@@ -42,7 +48,7 @@ extern int platform_irqchip_probe(struct platform_device *pdev);
 static const struct of_device_id drv_name##_irqchip_match_table[] = {
 
 #define IRQCHIP_MATCH(compat, fn) { .compatible = compat,		\
-				    .data = typecheck_irq_init_cb(fn), },
+				    .data = typecheck_irq_probe(fn), },
 
 
 #define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...)			\
diff --git a/include/linux/irqchip/arm-gic-common.h b/include/linux/irqchip/arm-gic-common.h
index 1177f3a1aed5..fc0246cc05ac 100644
--- a/include/linux/irqchip/arm-gic-common.h
+++ b/include/linux/irqchip/arm-gic-common.h
@@ -10,10 +10,6 @@
 #include <linux/irqchip/arm-vgic-info.h>
 
 #define GICD_INT_DEF_PRI		0xa0
-#define GICD_INT_DEF_PRI_X4		((GICD_INT_DEF_PRI << 24) |\
-					(GICD_INT_DEF_PRI << 16) |\
-					(GICD_INT_DEF_PRI << 8) |\
-					GICD_INT_DEF_PRI)
 
 struct irq_domain;
 struct fwnode_handle;
diff --git a/include/linux/irqchip/arm-gic-v3-prio.h b/include/linux/irqchip/arm-gic-v3-prio.h
new file mode 100644
index 000000000000..44157c9abb78
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v3-prio.h
@@ -0,0 +1,52 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H
+#define __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H
+
+/*
+ * GIC priorities from the view of the PMR/RPR.
+ *
+ * These values are chosen to be valid in either the absolute priority space or
+ * the NS view of the priority space. The value programmed into the distributor
+ * and ITS will be chosen at boot time such that these values appear in the
+ * PMR/RPR.
+ *
+ * GICV3_PRIO_UNMASKED is the PMR view of the priority to use to permit both
+ * IRQs and pseudo-NMIs.
+ *
+ * GICV3_PRIO_IRQ is the PMR view of the priority of regular interrupts. This
+ * can be written to the PMR to mask regular IRQs.
+ *
+ * GICV3_PRIO_NMI is the PMR view of the priority of pseudo-NMIs. This can be
+ * written to the PMR to mask pseudo-NMIs.
+ *
+ * On arm64 some code sections either automatically switch back to PSR.I or
+ * explicitly require to not use priority masking. If bit GICV3_PRIO_PSR_I_SET
+ * is included in the priority mask, it indicates that PSR.I should be set and
+ * interrupt disabling temporarily does not rely on IRQ priorities.
+ */
+#define GICV3_PRIO_UNMASKED	0xe0
+#define GICV3_PRIO_IRQ		0xc0
+#define GICV3_PRIO_NMI		0x80
+
+#define GICV3_PRIO_PSR_I_SET	(1 << 4)
+
+#ifndef __ASSEMBLER__
+
+#define __gicv3_prio_to_ns(p)	(0xff & ((p) << 1))
+#define __gicv3_ns_to_prio(ns)	(0x80 | ((ns) >> 1))
+
+#define __gicv3_prio_valid_ns(p) \
+	(__gicv3_ns_to_prio(__gicv3_prio_to_ns(p)) == (p))
+
+static_assert(__gicv3_prio_valid_ns(GICV3_PRIO_NMI));
+static_assert(__gicv3_prio_valid_ns(GICV3_PRIO_IRQ));
+
+static_assert(GICV3_PRIO_NMI < GICV3_PRIO_IRQ);
+static_assert(GICV3_PRIO_IRQ < GICV3_PRIO_UNMASKED);
+
+static_assert(GICV3_PRIO_IRQ < (GICV3_PRIO_IRQ | GICV3_PRIO_PSR_I_SET));
+
+#endif /* __ASSEMBLER */
+
+#endif /* __LINUX_IRQCHIP_ARM_GIC_V3_PRIO_H */
diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h
index 728691365464..70c0948f978e 100644
--- a/include/linux/irqchip/arm-gic-v3.h
+++ b/include/linux/irqchip/arm-gic-v3.h
@@ -638,7 +638,7 @@ struct fwnode_handle;
 int __init its_lpi_memreserve_init(void);
 int its_cpu_init(void);
 int its_init(struct fwnode_handle *handle, struct rdists *rdists,
-	     struct irq_domain *domain);
+	     struct irq_domain *domain, u8 irq_prio);
 int mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent);
 
 static inline bool gic_enable_sre(void)
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 2c63375bbd43..0b0887099fd7 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -25,6 +25,14 @@ struct its_vm {
 	irq_hw_number_t		db_lpi_base;
 	unsigned long		*db_bitmap;
 	int			nr_db_lpis;
+	/*
+	 * Ensures mutual exclusion between updates to vlpi_count[]
+	 * and map/unmap when using the ITSList mechanism.
+	 *
+	 * The lock order for any sequence involving the ITSList is
+	 * vmapp_lock -> vpe_lock ->vmovp_lock.
+	 */
+	raw_spinlock_t		vmapp_lock;
 	u32			vlpi_count[GICv4_ITS_LIST_MAX];
 };
 
@@ -58,10 +66,12 @@ struct its_vpe {
 				bool	enabled;
 				bool	group;
 			}			sgi_config[16];
-			atomic_t vmapp_count;
 		};
 	};
 
+	/* Track the VPE being mapped */
+	atomic_t vmapp_count;
+
 	/*
 	 * Ensures mutual exclusion between affinity setting of the
 	 * vPE and vLPI operations using vpe->col_idx.
@@ -136,7 +146,7 @@ int its_commit_vpe(struct its_vpe *vpe);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
-int its_unmap_vlpi(int irq);
+void its_unmap_vlpi(int irq);
 int its_prop_update_vlpi(int irq, u8 config, bool inv);
 int its_prop_update_vsgi(int irq, u8 priority, bool group);
 
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
new file mode 100644
index 000000000000..68ddcdb1cec5
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -0,0 +1,394 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025 ARM Limited, All Rights Reserved.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V5_H
+#define __LINUX_IRQCHIP_ARM_GIC_V5_H
+
+#include <linux/iopoll.h>
+
+#include <asm/cacheflush.h>
+#include <asm/smp.h>
+#include <asm/sysreg.h>
+
+#define GICV5_IPIS_PER_CPU		MAX_IPI
+
+/*
+ * INTID handling
+ */
+#define GICV5_HWIRQ_ID			GENMASK(23, 0)
+#define GICV5_HWIRQ_TYPE		GENMASK(31, 29)
+#define GICV5_HWIRQ_INTID		GENMASK_ULL(31, 0)
+
+#define GICV5_HWIRQ_TYPE_PPI		UL(0x1)
+#define GICV5_HWIRQ_TYPE_LPI		UL(0x2)
+#define GICV5_HWIRQ_TYPE_SPI		UL(0x3)
+
+/*
+ * Tables attributes
+ */
+#define GICV5_NO_READ_ALLOC		0b0
+#define GICV5_READ_ALLOC		0b1
+#define GICV5_NO_WRITE_ALLOC		0b0
+#define GICV5_WRITE_ALLOC		0b1
+
+#define GICV5_NON_CACHE			0b00
+#define GICV5_WB_CACHE			0b01
+#define GICV5_WT_CACHE			0b10
+
+#define GICV5_NON_SHARE			0b00
+#define GICV5_OUTER_SHARE		0b10
+#define GICV5_INNER_SHARE		0b11
+
+/*
+ * IRS registers and tables structures
+ */
+#define GICV5_IRS_IDR1			0x0004
+#define GICV5_IRS_IDR2			0x0008
+#define GICV5_IRS_IDR5			0x0014
+#define GICV5_IRS_IDR6			0x0018
+#define GICV5_IRS_IDR7			0x001c
+#define GICV5_IRS_CR0			0x0080
+#define GICV5_IRS_CR1			0x0084
+#define GICV5_IRS_SYNCR			0x00c0
+#define GICV5_IRS_SYNC_STATUSR		0x00c4
+#define GICV5_IRS_SPI_SELR		0x0108
+#define GICV5_IRS_SPI_CFGR		0x0114
+#define GICV5_IRS_SPI_STATUSR		0x0118
+#define GICV5_IRS_PE_SELR		0x0140
+#define GICV5_IRS_PE_STATUSR		0x0144
+#define GICV5_IRS_PE_CR0		0x0148
+#define GICV5_IRS_IST_BASER		0x0180
+#define GICV5_IRS_IST_CFGR		0x0190
+#define GICV5_IRS_IST_STATUSR		0x0194
+#define GICV5_IRS_MAP_L2_ISTR		0x01c0
+
+#define GICV5_IRS_IDR1_PRIORITY_BITS	GENMASK(22, 20)
+#define GICV5_IRS_IDR1_IAFFID_BITS	GENMASK(19, 16)
+
+#define GICV5_IRS_IDR1_PRIORITY_BITS_1BITS	0b000
+#define GICV5_IRS_IDR1_PRIORITY_BITS_2BITS	0b001
+#define GICV5_IRS_IDR1_PRIORITY_BITS_3BITS	0b010
+#define GICV5_IRS_IDR1_PRIORITY_BITS_4BITS	0b011
+#define GICV5_IRS_IDR1_PRIORITY_BITS_5BITS	0b100
+
+#define GICV5_IRS_IDR2_ISTMD_SZ		GENMASK(19, 15)
+#define GICV5_IRS_IDR2_ISTMD		BIT(14)
+#define GICV5_IRS_IDR2_IST_L2SZ		GENMASK(13, 11)
+#define GICV5_IRS_IDR2_IST_LEVELS	BIT(10)
+#define GICV5_IRS_IDR2_MIN_LPI_ID_BITS	GENMASK(9, 6)
+#define GICV5_IRS_IDR2_LPI		BIT(5)
+#define GICV5_IRS_IDR2_ID_BITS		GENMASK(4, 0)
+
+#define GICV5_IRS_IDR5_SPI_RANGE	GENMASK(24, 0)
+#define GICV5_IRS_IDR6_SPI_IRS_RANGE	GENMASK(24, 0)
+#define GICV5_IRS_IDR7_SPI_BASE		GENMASK(23, 0)
+
+#define GICV5_IRS_IST_L2SZ_SUPPORT_4KB(r)	FIELD_GET(BIT(11), (r))
+#define GICV5_IRS_IST_L2SZ_SUPPORT_16KB(r)	FIELD_GET(BIT(12), (r))
+#define GICV5_IRS_IST_L2SZ_SUPPORT_64KB(r)	FIELD_GET(BIT(13), (r))
+
+#define GICV5_IRS_CR0_IDLE		BIT(1)
+#define GICV5_IRS_CR0_IRSEN		BIT(0)
+
+#define GICV5_IRS_CR1_VPED_WA		BIT(15)
+#define GICV5_IRS_CR1_VPED_RA		BIT(14)
+#define GICV5_IRS_CR1_VMD_WA		BIT(13)
+#define GICV5_IRS_CR1_VMD_RA		BIT(12)
+#define GICV5_IRS_CR1_VPET_WA		BIT(11)
+#define GICV5_IRS_CR1_VPET_RA		BIT(10)
+#define GICV5_IRS_CR1_VMT_WA		BIT(9)
+#define GICV5_IRS_CR1_VMT_RA		BIT(8)
+#define GICV5_IRS_CR1_IST_WA		BIT(7)
+#define GICV5_IRS_CR1_IST_RA		BIT(6)
+#define GICV5_IRS_CR1_IC		GENMASK(5, 4)
+#define GICV5_IRS_CR1_OC		GENMASK(3, 2)
+#define GICV5_IRS_CR1_SH		GENMASK(1, 0)
+
+#define GICV5_IRS_SYNCR_SYNC		BIT(31)
+
+#define GICV5_IRS_SYNC_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_SPI_STATUSR_V		BIT(1)
+#define GICV5_IRS_SPI_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_SPI_SELR_ID		GENMASK(23, 0)
+
+#define GICV5_IRS_SPI_CFGR_TM		BIT(0)
+
+#define GICV5_IRS_PE_SELR_IAFFID	GENMASK(15, 0)
+
+#define GICV5_IRS_PE_STATUSR_V		BIT(1)
+#define GICV5_IRS_PE_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_PE_CR0_DPS		BIT(0)
+
+#define GICV5_IRS_IST_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_IST_CFGR_STRUCTURE	BIT(16)
+#define GICV5_IRS_IST_CFGR_ISTSZ	GENMASK(8, 7)
+#define GICV5_IRS_IST_CFGR_L2SZ		GENMASK(6, 5)
+#define GICV5_IRS_IST_CFGR_LPI_ID_BITS	GENMASK(4, 0)
+
+#define GICV5_IRS_IST_CFGR_STRUCTURE_LINEAR	0b0
+#define GICV5_IRS_IST_CFGR_STRUCTURE_TWO_LEVEL	0b1
+
+#define GICV5_IRS_IST_CFGR_ISTSZ_4	0b00
+#define GICV5_IRS_IST_CFGR_ISTSZ_8	0b01
+#define GICV5_IRS_IST_CFGR_ISTSZ_16	0b10
+
+#define GICV5_IRS_IST_CFGR_L2SZ_4K	0b00
+#define GICV5_IRS_IST_CFGR_L2SZ_16K	0b01
+#define GICV5_IRS_IST_CFGR_L2SZ_64K	0b10
+
+#define GICV5_IRS_IST_BASER_ADDR_MASK	GENMASK_ULL(55, 6)
+#define GICV5_IRS_IST_BASER_VALID	BIT_ULL(0)
+
+#define GICV5_IRS_MAP_L2_ISTR_ID	GENMASK(23, 0)
+
+#define GICV5_ISTL1E_VALID		BIT_ULL(0)
+
+#define GICV5_ISTL1E_L2_ADDR_MASK	GENMASK_ULL(55, 12)
+
+/*
+ * ITS registers and tables structures
+ */
+#define GICV5_ITS_IDR1		0x0004
+#define GICV5_ITS_IDR2		0x0008
+#define GICV5_ITS_CR0		0x0080
+#define GICV5_ITS_CR1		0x0084
+#define GICV5_ITS_DT_BASER	0x00c0
+#define GICV5_ITS_DT_CFGR	0x00d0
+#define GICV5_ITS_DIDR		0x0100
+#define GICV5_ITS_EIDR		0x0108
+#define GICV5_ITS_INV_EVENTR	0x010c
+#define GICV5_ITS_INV_DEVICER	0x0110
+#define GICV5_ITS_STATUSR	0x0120
+#define GICV5_ITS_SYNCR		0x0140
+#define GICV5_ITS_SYNC_STATUSR	0x0148
+
+#define GICV5_ITS_IDR1_L2SZ			GENMASK(10, 8)
+#define GICV5_ITS_IDR1_ITT_LEVELS		BIT(7)
+#define GICV5_ITS_IDR1_DT_LEVELS		BIT(6)
+#define GICV5_ITS_IDR1_DEVICEID_BITS		GENMASK(5, 0)
+
+#define GICV5_ITS_IDR1_L2SZ_SUPPORT_4KB(r)	FIELD_GET(BIT(8), (r))
+#define GICV5_ITS_IDR1_L2SZ_SUPPORT_16KB(r)	FIELD_GET(BIT(9), (r))
+#define GICV5_ITS_IDR1_L2SZ_SUPPORT_64KB(r)	FIELD_GET(BIT(10), (r))
+
+#define GICV5_ITS_IDR2_XDMN_EVENTs		GENMASK(6, 5)
+#define GICV5_ITS_IDR2_EVENTID_BITS		GENMASK(4, 0)
+
+#define GICV5_ITS_CR0_IDLE			BIT(1)
+#define GICV5_ITS_CR0_ITSEN			BIT(0)
+
+#define GICV5_ITS_CR1_ITT_RA			BIT(7)
+#define GICV5_ITS_CR1_DT_RA			BIT(6)
+#define GICV5_ITS_CR1_IC			GENMASK(5, 4)
+#define GICV5_ITS_CR1_OC			GENMASK(3, 2)
+#define GICV5_ITS_CR1_SH			GENMASK(1, 0)
+
+#define GICV5_ITS_DT_CFGR_STRUCTURE		BIT(16)
+#define GICV5_ITS_DT_CFGR_L2SZ			GENMASK(7, 6)
+#define GICV5_ITS_DT_CFGR_DEVICEID_BITS		GENMASK(5, 0)
+
+#define GICV5_ITS_DT_BASER_ADDR_MASK		GENMASK_ULL(55, 3)
+
+#define GICV5_ITS_INV_DEVICER_I			BIT(31)
+#define GICV5_ITS_INV_DEVICER_EVENTID_BITS	GENMASK(5, 1)
+#define GICV5_ITS_INV_DEVICER_L1		BIT(0)
+
+#define GICV5_ITS_DIDR_DEVICEID			GENMASK_ULL(31, 0)
+
+#define GICV5_ITS_EIDR_EVENTID			GENMASK(15, 0)
+
+#define GICV5_ITS_INV_EVENTR_I			BIT(31)
+#define GICV5_ITS_INV_EVENTR_ITT_L2SZ		GENMASK(2, 1)
+#define GICV5_ITS_INV_EVENTR_L1			BIT(0)
+
+#define GICV5_ITS_STATUSR_IDLE			BIT(0)
+
+#define GICV5_ITS_SYNCR_SYNC			BIT_ULL(63)
+#define GICV5_ITS_SYNCR_SYNCALL			BIT_ULL(32)
+#define GICV5_ITS_SYNCR_DEVICEID		GENMASK_ULL(31, 0)
+
+#define GICV5_ITS_SYNC_STATUSR_IDLE		BIT(0)
+
+#define GICV5_DTL1E_VALID			BIT_ULL(0)
+/* Note that there is no shift for the address by design */
+#define GICV5_DTL1E_L2_ADDR_MASK		GENMASK_ULL(55, 3)
+#define GICV5_DTL1E_SPAN			GENMASK_ULL(63, 60)
+
+#define GICV5_DTL2E_VALID			BIT_ULL(0)
+#define GICV5_DTL2E_ITT_L2SZ			GENMASK_ULL(2, 1)
+/* Note that there is no shift for the address by design */
+#define GICV5_DTL2E_ITT_ADDR_MASK		GENMASK_ULL(55, 3)
+#define GICV5_DTL2E_ITT_DSWE			BIT_ULL(57)
+#define GICV5_DTL2E_ITT_STRUCTURE		BIT_ULL(58)
+#define GICV5_DTL2E_EVENT_ID_BITS		GENMASK_ULL(63, 59)
+
+#define GICV5_ITTL1E_VALID			BIT_ULL(0)
+/* Note that there is no shift for the address by design */
+#define GICV5_ITTL1E_L2_ADDR_MASK		GENMASK_ULL(55, 3)
+#define GICV5_ITTL1E_SPAN			GENMASK_ULL(63, 60)
+
+#define GICV5_ITTL2E_LPI_ID			GENMASK_ULL(23, 0)
+#define GICV5_ITTL2E_DAC			GENMASK_ULL(29, 28)
+#define GICV5_ITTL2E_VIRTUAL			BIT_ULL(30)
+#define GICV5_ITTL2E_VALID			BIT_ULL(31)
+#define GICV5_ITTL2E_VM_ID			GENMASK_ULL(47, 32)
+
+#define GICV5_ITS_DT_ITT_CFGR_L2SZ_4k		0b00
+#define GICV5_ITS_DT_ITT_CFGR_L2SZ_16k		0b01
+#define GICV5_ITS_DT_ITT_CFGR_L2SZ_64k		0b10
+
+#define GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR		0
+#define GICV5_ITS_DT_ITT_CFGR_STRUCTURE_TWO_LEVEL	1
+
+#define GICV5_ITS_HWIRQ_DEVICE_ID		GENMASK_ULL(31, 0)
+#define GICV5_ITS_HWIRQ_EVENT_ID		GENMASK_ULL(63, 32)
+
+/*
+ * IWB registers
+ */
+#define GICV5_IWB_IDR0				0x0000
+#define GICV5_IWB_CR0				0x0080
+#define GICV5_IWB_WENABLE_STATUSR		0x00c0
+#define GICV5_IWB_WENABLER			0x2000
+#define GICV5_IWB_WTMR				0x4000
+
+#define GICV5_IWB_IDR0_INT_DOMS			GENMASK(14, 11)
+#define GICV5_IWB_IDR0_IW_RANGE			GENMASK(10, 0)
+
+#define GICV5_IWB_CR0_IDLE			BIT(1)
+#define GICV5_IWB_CR0_IWBEN			BIT(0)
+
+#define GICV5_IWB_WENABLE_STATUSR_IDLE		BIT(0)
+
+/*
+ * Global Data structures and functions
+ */
+struct gicv5_chip_data {
+	struct fwnode_handle	*fwnode;
+	struct irq_domain	*ppi_domain;
+	struct irq_domain	*spi_domain;
+	struct irq_domain	*lpi_domain;
+	struct irq_domain	*ipi_domain;
+	u32			global_spi_count;
+	u8			cpuif_pri_bits;
+	u8			cpuif_id_bits;
+	u8			irs_pri_bits;
+	struct {
+		__le64 *l1ist_addr;
+		u32 l2_size;
+		u8 l2_bits;
+		bool l2;
+	} ist;
+};
+
+extern struct gicv5_chip_data gicv5_global_data __read_mostly;
+
+struct gicv5_irs_chip_data {
+	struct list_head	entry;
+	struct fwnode_handle	*fwnode;
+	void __iomem		*irs_base;
+	u32			flags;
+	u32			spi_min;
+	u32			spi_range;
+	raw_spinlock_t		spi_config_lock;
+};
+
+static inline int gicv5_wait_for_op_s_atomic(void __iomem *addr, u32 offset,
+					     const char *reg_s, u32 mask,
+					     u32 *val)
+{
+	void __iomem *reg = addr + offset;
+	u32 tmp;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(reg, tmp, tmp & mask, 1, 10 * USEC_PER_MSEC);
+	if (unlikely(ret == -ETIMEDOUT)) {
+		pr_err_ratelimited("%s timeout...\n", reg_s);
+		return ret;
+	}
+
+	if (val)
+		*val = tmp;
+
+	return 0;
+}
+
+static inline int gicv5_wait_for_op_s(void __iomem *addr, u32 offset,
+				      const char *reg_s, u32 mask)
+{
+	void __iomem *reg = addr + offset;
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(reg, val, val & mask, 1, 10 * USEC_PER_MSEC);
+	if (unlikely(ret == -ETIMEDOUT)) {
+		pr_err_ratelimited("%s timeout...\n", reg_s);
+		return ret;
+	}
+
+	return 0;
+}
+
+#define gicv5_wait_for_op_atomic(base, reg, mask, val) \
+	gicv5_wait_for_op_s_atomic(base, reg, #reg, mask, val)
+
+#define gicv5_wait_for_op(base, reg, mask) \
+	gicv5_wait_for_op_s(base, reg, #reg, mask)
+
+void __init gicv5_init_lpi_domain(void);
+void __init gicv5_free_lpi_domain(void);
+
+int gicv5_irs_of_probe(struct device_node *parent);
+void gicv5_irs_remove(void);
+int gicv5_irs_enable(void);
+void gicv5_irs_its_probe(void);
+int gicv5_irs_register_cpu(int cpuid);
+int gicv5_irs_cpu_to_iaffid(int cpu_id, u16 *iaffid);
+struct gicv5_irs_chip_data *gicv5_irs_lookup_by_spi_id(u32 spi_id);
+int gicv5_spi_irq_set_type(struct irq_data *d, unsigned int type);
+int gicv5_irs_iste_alloc(u32 lpi);
+void gicv5_irs_syncr(void);
+
+struct gicv5_its_devtab_cfg {
+	union {
+		struct {
+			__le64	*devtab;
+		} linear;
+		struct {
+			__le64	*l1devtab;
+			__le64	**l2ptrs;
+		} l2;
+	};
+	u32	cfgr;
+};
+
+struct gicv5_its_itt_cfg {
+	union {
+		struct {
+			__le64		*itt;
+			unsigned int	num_ents;
+		} linear;
+		struct {
+			__le64		*l1itt;
+			__le64		**l2ptrs;
+			unsigned int	num_l1_ents;
+			u8		l2sz;
+		} l2;
+	};
+	u8	event_id_bits;
+	bool	l2itt;
+};
+
+void gicv5_init_lpis(u32 max);
+void gicv5_deinit_lpis(void);
+
+int gicv5_alloc_lpi(void);
+void gicv5_free_lpi(u32 lpi);
+
+void __init gicv5_its_of_probe(struct device_node *parent);
+#endif
diff --git a/include/linux/irqchip/arm-gic.h b/include/linux/irqchip/arm-gic.h
index 2223f95079ce..d45fa19f9e47 100644
--- a/include/linux/irqchip/arm-gic.h
+++ b/include/linux/irqchip/arm-gic.h
@@ -86,7 +86,13 @@
 
 #define GICH_HCR_EN			(1 << 0)
 #define GICH_HCR_UIE			(1 << 1)
+#define GICH_HCR_LRENPIE		(1 << 2)
 #define GICH_HCR_NPIE			(1 << 3)
+#define GICH_HCR_VGrp0EIE		(1 << 4)
+#define GICH_HCR_VGrp0DIE		(1 << 5)
+#define GICH_HCR_VGrp1EIE		(1 << 6)
+#define GICH_HCR_VGrp1DIE		(1 << 7)
+#define GICH_HCR_EOICOUNT		GENMASK(31, 27)
 
 #define GICH_LR_VIRTUALID		(0x3ff << 0)
 #define GICH_LR_PHYSID_CPUID_SHIFT	(10)
diff --git a/include/linux/irqchip/arm-vgic-info.h b/include/linux/irqchip/arm-vgic-info.h
index a75b2c7de69d..67d9d960273b 100644
--- a/include/linux/irqchip/arm-vgic-info.h
+++ b/include/linux/irqchip/arm-vgic-info.h
@@ -15,6 +15,8 @@ enum gic_type {
 	GIC_V2,
 	/* Full GICv3, optionally with v2 compat */
 	GIC_V3,
+	/* Full GICv5, optionally with v3 compat */
+	GIC_V5,
 };
 
 struct gic_kvm_info {
@@ -22,6 +24,8 @@ struct gic_kvm_info {
 	enum gic_type	type;
 	/* Virtual CPU interface */
 	struct resource vcpu;
+	/* GICv2 GICC VA */
+	void __iomem	*gicc_base;
 	/* Interrupt number */
 	unsigned int	maint_irq;
 	/* No interrupt mask, no need to use the above field */
diff --git a/include/linux/irqchip/irq-davinci-aintc.h b/include/linux/irqchip/irq-davinci-aintc.h
deleted file mode 100644
index ea4e087fac98..000000000000
--- a/include/linux/irqchip/irq-davinci-aintc.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2019 Texas Instruments
- */
-
-#ifndef _LINUX_IRQ_DAVINCI_AINTC_
-#define _LINUX_IRQ_DAVINCI_AINTC_
-
-#include <linux/ioport.h>
-
-/**
- * struct davinci_aintc_config - configuration data for davinci-aintc driver.
- *
- * @reg: register range to map
- * @num_irqs: number of HW interrupts supported by the controller
- * @prios: an array of size num_irqs containing priority settings for
- *         each interrupt
- */
-struct davinci_aintc_config {
-	struct resource reg;
-	unsigned int num_irqs;
-	u8 *prios;
-};
-
-void davinci_aintc_init(const struct davinci_aintc_config *config);
-
-#endif /* _LINUX_IRQ_DAVINCI_AINTC_ */
diff --git a/include/linux/irqchip/irq-davinci-cp-intc.h b/include/linux/irqchip/irq-davinci-cp-intc.h
deleted file mode 100644
index 8d71ed5b5a61..000000000000
--- a/include/linux/irqchip/irq-davinci-cp-intc.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Copyright (C) 2019 Texas Instruments
- */
-
-#ifndef _LINUX_IRQ_DAVINCI_CP_INTC_
-#define _LINUX_IRQ_DAVINCI_CP_INTC_
-
-#include <linux/ioport.h>
-
-/**
- * struct davinci_cp_intc_config - configuration data for davinci-cp-intc
- *                                 driver.
- *
- * @reg: register range to map
- * @num_irqs: number of HW interrupts supported by the controller
- */
-struct davinci_cp_intc_config {
-	struct resource reg;
-	unsigned int num_irqs;
-};
-
-int davinci_cp_intc_init(const struct davinci_cp_intc_config *config);
-
-#endif /* _LINUX_IRQ_DAVINCI_CP_INTC_ */
diff --git a/include/linux/irqchip/irq-msi-lib.h b/include/linux/irqchip/irq-msi-lib.h
new file mode 100644
index 000000000000..224ac28e88d7
--- /dev/null
+++ b/include/linux/irqchip/irq-msi-lib.h
@@ -0,0 +1,28 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (C) 2022 Linutronix GmbH
+// Copyright (C) 2022 Intel
+
+#ifndef _IRQCHIP_IRQ_MSI_LIB_H
+#define _IRQCHIP_IRQ_MSI_LIB_H
+
+#include <linux/bits.h>
+#include <linux/irqdomain.h>
+#include <linux/msi.h>
+
+#ifdef CONFIG_PCI_MSI
+#define MATCH_PCI_MSI		BIT(DOMAIN_BUS_PCI_MSI)
+#else
+#define MATCH_PCI_MSI		(0)
+#endif
+
+#define MATCH_PLATFORM_MSI	BIT(DOMAIN_BUS_PLATFORM_MSI)
+
+struct msi_domain_info;
+int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+			      enum irq_domain_bus_token bus_token);
+
+bool msi_lib_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
+			       struct irq_domain *real_parent,
+			       struct msi_domain_info *info);
+
+#endif /* _IRQCHIP_IRQ_MSI_LIB_H */
diff --git a/include/linux/irqchip/irq-partition-percpu.h b/include/linux/irqchip/irq-partition-percpu.h
deleted file mode 100644
index 2f6ae7551748..000000000000
--- a/include/linux/irqchip/irq-partition-percpu.h
+++ /dev/null
@@ -1,53 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2016 ARM Limited, All Rights Reserved.
- * Author: Marc Zyngier <marc.zyngier@arm.com>
- */
-
-#ifndef __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H
-#define __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H
-
-#include <linux/fwnode.h>
-#include <linux/cpumask.h>
-#include <linux/irqdomain.h>
-
-struct partition_affinity {
-	cpumask_t			mask;
-	void				*partition_id;
-};
-
-struct partition_desc;
-
-#ifdef CONFIG_PARTITION_PERCPU
-int partition_translate_id(struct partition_desc *desc, void *partition_id);
-struct partition_desc *partition_create_desc(struct fwnode_handle *fwnode,
-					     struct partition_affinity *parts,
-					     int nr_parts,
-					     int chained_irq,
-					     const struct irq_domain_ops *ops);
-struct irq_domain *partition_get_domain(struct partition_desc *dsc);
-#else
-static inline int partition_translate_id(struct partition_desc *desc,
-					 void *partition_id)
-{
-	return -EINVAL;
-}
-
-static inline
-struct partition_desc *partition_create_desc(struct fwnode_handle *fwnode,
-					     struct partition_affinity *parts,
-					     int nr_parts,
-					     int chained_irq,
-					     const struct irq_domain_ops *ops)
-{
-	return NULL;
-}
-
-static inline
-struct irq_domain *partition_get_domain(struct partition_desc *dsc)
-{
-	return NULL;
-}
-#endif
-
-#endif /* __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H */
diff --git a/include/linux/irqchip/irq-renesas-rzv2h.h b/include/linux/irqchip/irq-renesas-rzv2h.h
new file mode 100644
index 000000000000..618a60d2eac0
--- /dev/null
+++ b/include/linux/irqchip/irq-renesas-rzv2h.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Renesas RZ/V2H(P) Interrupt Control Unit (ICU)
+ *
+ * Copyright (C) 2025 Renesas Electronics Corporation.
+ */
+
+#ifndef __LINUX_IRQ_RENESAS_RZV2H
+#define __LINUX_IRQ_RENESAS_RZV2H
+
+#include <linux/platform_device.h>
+
+#define RZV2H_ICU_DMAC_REQ_NO_DEFAULT		0x3ff
+
+#ifdef CONFIG_RENESAS_RZV2H_ICU
+void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index, u8 dmac_channel,
+				u16 req_no);
+#else
+static inline void rzv2h_icu_register_dma_req(struct platform_device *icu_dev, u8 dmac_index,
+					      u8 dmac_channel, u16 req_no) { }
+#endif
+
+#endif /* __LINUX_IRQ_RENESAS_RZV2H */
diff --git a/include/linux/irqchip/mmp.h b/include/linux/irqchip/mmp.h
deleted file mode 100644
index aa1813749a4f..000000000000
--- a/include/linux/irqchip/mmp.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef	__IRQCHIP_MMP_H
-#define	__IRQCHIP_MMP_H
-
-extern struct irq_chip icu_irq_chip;
-
-extern void icu_init_irq(void);
-extern void mmp2_init_icu(void);
-
-#endif	/* __IRQCHIP_MMP_H */
diff --git a/include/linux/irqchip/mxs.h b/include/linux/irqchip/mxs.h
deleted file mode 100644
index 4f447e3f0f3a..000000000000
--- a/include/linux/irqchip/mxs.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2013 Freescale Semiconductor, Inc.
- */
-
-#ifndef __LINUX_IRQCHIP_MXS_H
-#define __LINUX_IRQCHIP_MXS_H
-
-extern void icoll_handle_irq(struct pt_regs *);
-
-#endif
diff --git a/include/linux/irqchip/riscv-aplic.h b/include/linux/irqchip/riscv-aplic.h
new file mode 100644
index 000000000000..ec8f7df50583
--- /dev/null
+++ b/include/linux/irqchip/riscv-aplic.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2022 Ventana Micro Systems Inc.
+ */
+#ifndef __LINUX_IRQCHIP_RISCV_APLIC_H
+#define __LINUX_IRQCHIP_RISCV_APLIC_H
+
+#include <linux/bitops.h>
+
+#define APLIC_MAX_IDC			BIT(14)
+#define APLIC_MAX_SOURCE		1024
+
+#define APLIC_DOMAINCFG			0x0000
+#define APLIC_DOMAINCFG_RDONLY		0x80000000
+#define APLIC_DOMAINCFG_IE		BIT(8)
+#define APLIC_DOMAINCFG_DM		BIT(2)
+#define APLIC_DOMAINCFG_BE		BIT(0)
+
+#define APLIC_SOURCECFG_BASE		0x0004
+#define APLIC_SOURCECFG_D		BIT(10)
+#define APLIC_SOURCECFG_CHILDIDX_MASK	0x000003ff
+#define APLIC_SOURCECFG_SM_MASK	0x00000007
+#define APLIC_SOURCECFG_SM_INACTIVE	0x0
+#define APLIC_SOURCECFG_SM_DETACH	0x1
+#define APLIC_SOURCECFG_SM_EDGE_RISE	0x4
+#define APLIC_SOURCECFG_SM_EDGE_FALL	0x5
+#define APLIC_SOURCECFG_SM_LEVEL_HIGH	0x6
+#define APLIC_SOURCECFG_SM_LEVEL_LOW	0x7
+
+#define APLIC_MMSICFGADDR		0x1bc0
+#define APLIC_MMSICFGADDRH		0x1bc4
+#define APLIC_SMSICFGADDR		0x1bc8
+#define APLIC_SMSICFGADDRH		0x1bcc
+
+#ifdef CONFIG_RISCV_M_MODE
+#define APLIC_xMSICFGADDR		APLIC_MMSICFGADDR
+#define APLIC_xMSICFGADDRH		APLIC_MMSICFGADDRH
+#else
+#define APLIC_xMSICFGADDR		APLIC_SMSICFGADDR
+#define APLIC_xMSICFGADDRH		APLIC_SMSICFGADDRH
+#endif
+
+#define APLIC_xMSICFGADDRH_L		BIT(31)
+#define APLIC_xMSICFGADDRH_HHXS_MASK	0x1f
+#define APLIC_xMSICFGADDRH_HHXS_SHIFT	24
+#define APLIC_xMSICFGADDRH_HHXS		(APLIC_xMSICFGADDRH_HHXS_MASK << \
+					 APLIC_xMSICFGADDRH_HHXS_SHIFT)
+#define APLIC_xMSICFGADDRH_LHXS_MASK	0x7
+#define APLIC_xMSICFGADDRH_LHXS_SHIFT	20
+#define APLIC_xMSICFGADDRH_LHXS		(APLIC_xMSICFGADDRH_LHXS_MASK << \
+					 APLIC_xMSICFGADDRH_LHXS_SHIFT)
+#define APLIC_xMSICFGADDRH_HHXW_MASK	0x7
+#define APLIC_xMSICFGADDRH_HHXW_SHIFT	16
+#define APLIC_xMSICFGADDRH_HHXW		(APLIC_xMSICFGADDRH_HHXW_MASK << \
+					 APLIC_xMSICFGADDRH_HHXW_SHIFT)
+#define APLIC_xMSICFGADDRH_LHXW_MASK	0xf
+#define APLIC_xMSICFGADDRH_LHXW_SHIFT	12
+#define APLIC_xMSICFGADDRH_LHXW		(APLIC_xMSICFGADDRH_LHXW_MASK << \
+					 APLIC_xMSICFGADDRH_LHXW_SHIFT)
+#define APLIC_xMSICFGADDRH_BAPPN_MASK	0xfff
+#define APLIC_xMSICFGADDRH_BAPPN_SHIFT	0
+#define APLIC_xMSICFGADDRH_BAPPN	(APLIC_xMSICFGADDRH_BAPPN_MASK << \
+					 APLIC_xMSICFGADDRH_BAPPN_SHIFT)
+
+#define APLIC_xMSICFGADDR_PPN_SHIFT	12
+
+#define APLIC_xMSICFGADDR_PPN_HART(__lhxs) \
+	(BIT(__lhxs) - 1)
+
+#define APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) \
+	(BIT(__lhxw) - 1)
+#define APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs) \
+	((__lhxs))
+#define APLIC_xMSICFGADDR_PPN_LHX(__lhxw, __lhxs) \
+	(APLIC_xMSICFGADDR_PPN_LHX_MASK(__lhxw) << \
+	 APLIC_xMSICFGADDR_PPN_LHX_SHIFT(__lhxs))
+
+#define APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) \
+	(BIT(__hhxw) - 1)
+#define APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs) \
+	((__hhxs) + APLIC_xMSICFGADDR_PPN_SHIFT)
+#define APLIC_xMSICFGADDR_PPN_HHX(__hhxw, __hhxs) \
+	(APLIC_xMSICFGADDR_PPN_HHX_MASK(__hhxw) << \
+	 APLIC_xMSICFGADDR_PPN_HHX_SHIFT(__hhxs))
+
+#define APLIC_IRQBITS_PER_REG		32
+
+#define APLIC_SETIP_BASE		0x1c00
+#define APLIC_SETIPNUM			0x1cdc
+
+#define APLIC_CLRIP_BASE		0x1d00
+#define APLIC_CLRIPNUM			0x1ddc
+
+#define APLIC_SETIE_BASE		0x1e00
+#define APLIC_SETIENUM			0x1edc
+
+#define APLIC_CLRIE_BASE		0x1f00
+#define APLIC_CLRIENUM			0x1fdc
+
+#define APLIC_SETIPNUM_LE		0x2000
+#define APLIC_SETIPNUM_BE		0x2004
+
+#define APLIC_GENMSI			0x3000
+
+#define APLIC_TARGET_BASE		0x3004
+#define APLIC_TARGET_HART_IDX_SHIFT	18
+#define APLIC_TARGET_HART_IDX_MASK	0x3fff
+#define APLIC_TARGET_HART_IDX		(APLIC_TARGET_HART_IDX_MASK << \
+					 APLIC_TARGET_HART_IDX_SHIFT)
+#define APLIC_TARGET_GUEST_IDX_SHIFT	12
+#define APLIC_TARGET_GUEST_IDX_MASK	0x3f
+#define APLIC_TARGET_GUEST_IDX		(APLIC_TARGET_GUEST_IDX_MASK << \
+					 APLIC_TARGET_GUEST_IDX_SHIFT)
+#define APLIC_TARGET_IPRIO_SHIFT	0
+#define APLIC_TARGET_IPRIO_MASK		0xff
+#define APLIC_TARGET_IPRIO		(APLIC_TARGET_IPRIO_MASK << \
+					 APLIC_TARGET_IPRIO_SHIFT)
+#define APLIC_TARGET_EIID_SHIFT		0
+#define APLIC_TARGET_EIID_MASK		0x7ff
+#define APLIC_TARGET_EIID		(APLIC_TARGET_EIID_MASK << \
+					 APLIC_TARGET_EIID_SHIFT)
+
+#define APLIC_IDC_BASE			0x4000
+#define APLIC_IDC_SIZE			32
+
+#define APLIC_IDC_IDELIVERY		0x00
+
+#define APLIC_IDC_IFORCE		0x04
+
+#define APLIC_IDC_ITHRESHOLD		0x08
+
+#define APLIC_IDC_TOPI			0x18
+#define APLIC_IDC_TOPI_ID_SHIFT		16
+#define APLIC_IDC_TOPI_ID_MASK		0x3ff
+#define APLIC_IDC_TOPI_ID		(APLIC_IDC_TOPI_ID_MASK << \
+					 APLIC_IDC_TOPI_ID_SHIFT)
+#define APLIC_IDC_TOPI_PRIO_SHIFT	0
+#define APLIC_IDC_TOPI_PRIO_MASK	0xff
+#define APLIC_IDC_TOPI_PRIO		(APLIC_IDC_TOPI_PRIO_MASK << \
+					 APLIC_IDC_TOPI_PRIO_SHIFT)
+
+#define APLIC_IDC_CLAIMI		0x1c
+
+#endif
diff --git a/include/linux/irqchip/riscv-imsic.h b/include/linux/irqchip/riscv-imsic.h
new file mode 100644
index 000000000000..7f3ff5c5ea53
--- /dev/null
+++ b/include/linux/irqchip/riscv-imsic.h
@@ -0,0 +1,95 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2021 Western Digital Corporation or its affiliates.
+ * Copyright (C) 2022 Ventana Micro Systems Inc.
+ */
+#ifndef __LINUX_IRQCHIP_RISCV_IMSIC_H
+#define __LINUX_IRQCHIP_RISCV_IMSIC_H
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/device.h>
+#include <linux/fwnode.h>
+
+#define IMSIC_MMIO_PAGE_SHIFT		12
+#define IMSIC_MMIO_PAGE_SZ		BIT(IMSIC_MMIO_PAGE_SHIFT)
+#define IMSIC_MMIO_PAGE_LE		0x00
+#define IMSIC_MMIO_PAGE_BE		0x04
+
+#define IMSIC_MIN_ID			63
+#define IMSIC_MAX_ID			2048
+
+#define IMSIC_EIDELIVERY		0x70
+
+#define IMSIC_EITHRESHOLD		0x72
+
+#define IMSIC_EIP0			0x80
+#define IMSIC_EIP63			0xbf
+#define IMSIC_EIPx_BITS			32
+
+#define IMSIC_EIE0			0xc0
+#define IMSIC_EIE63			0xff
+#define IMSIC_EIEx_BITS			32
+
+#define IMSIC_FIRST			IMSIC_EIDELIVERY
+#define IMSIC_LAST			IMSIC_EIE63
+
+#define IMSIC_MMIO_SETIPNUM_LE		0x00
+#define IMSIC_MMIO_SETIPNUM_BE		0x04
+
+struct imsic_local_config {
+	phys_addr_t				msi_pa;
+	void __iomem				*msi_va;
+};
+
+struct imsic_global_config {
+	/*
+	 * MSI Target Address Scheme
+	 *
+	 * XLEN-1                                                12     0
+	 * |                                                     |     |
+	 * -------------------------------------------------------------
+	 * |xxxxxx|Group Index|xxxxxxxxxxx|HART Index|Guest Index|  0  |
+	 * -------------------------------------------------------------
+	 */
+
+	/* Bits representing Guest index, HART index, and Group index */
+	u32					guest_index_bits;
+	u32					hart_index_bits;
+	u32					group_index_bits;
+	u32					group_index_shift;
+
+	/* Global base address matching all target MSI addresses */
+	phys_addr_t				base_addr;
+
+	/* Number of interrupt identities */
+	u32					nr_ids;
+
+	/* Number of guest interrupt identities */
+	u32					nr_guest_ids;
+
+	/* Per-CPU IMSIC addresses */
+	struct imsic_local_config __percpu	*local;
+};
+
+#ifdef CONFIG_RISCV_IMSIC
+
+const struct imsic_global_config *imsic_get_global_config(void);
+
+#else
+
+static inline const struct imsic_global_config *imsic_get_global_config(void)
+{
+	return NULL;
+}
+
+#endif
+
+#if IS_ENABLED(CONFIG_ACPI) && IS_ENABLED(CONFIG_RISCV_IMSIC)
+int imsic_platform_acpi_probe(struct fwnode_handle *fwnode);
+struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev);
+#else
+static inline struct fwnode_handle *imsic_acpi_get_fwnode(struct device *dev) { return NULL; }
+#endif
+
+#endif
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 844a8e30e6de..37e0b5b5600a 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -18,6 +18,18 @@ struct irq_domain;
 struct pt_regs;
 
 /**
+ * struct irqstat - interrupt statistics
+ * @cnt:	real-time interrupt count
+ * @ref:	snapshot of interrupt count
+ */
+struct irqstat {
+	unsigned int	cnt;
+#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
+	unsigned int	ref;
+#endif
+};
+
+/**
  * struct irq_desc - interrupt descriptor
  * @irq_common_data:	per irq and chip data passed down to chip functions
  * @kstat_irqs:		irq stats per cpu
@@ -55,7 +67,7 @@ struct pt_regs;
 struct irq_desc {
 	struct irq_common_data	irq_common_data;
 	struct irq_data		irq_data;
-	unsigned int __percpu	*kstat_irqs;
+	struct irqstat __percpu	*kstat_irqs;
 	irq_flow_handler_t	handle_irq;
 	struct irqaction	*action;	/* IRQ action list */
 	unsigned int		status_use_accessors;
@@ -70,7 +82,6 @@ struct irq_desc {
 	int			threads_handled_last;
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
-	const struct cpumask	*percpu_affinity;
 #ifdef CONFIG_SMP
 	const struct cpumask	*affinity_hint;
 	struct irq_affinity_notify *affinity_notify;
@@ -102,6 +113,9 @@ struct irq_desc {
 	int			parent_irq;
 	struct module		*owner;
 	const char		*name;
+#ifdef CONFIG_HARDIRQS_SW_RESEND
+	struct hlist_node	resend_node;
+#endif
 } ____cacheline_internodealigned_in_smp;
 
 #ifdef CONFIG_SPARSE_IRQ
@@ -116,7 +130,7 @@ extern struct irq_desc irq_desc[NR_IRQS];
 static inline unsigned int irq_desc_kstat_cpu(struct irq_desc *desc,
 					      unsigned int cpu)
 {
-	return desc->kstat_irqs ? *per_cpu_ptr(desc->kstat_irqs, cpu) : 0;
+	return desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0;
 }
 
 static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 51c254b7fec2..952d3c8dd6b7 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -1,30 +1,8 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * irq_domain - IRQ translation domains
+ * irq_domain - IRQ Translation Domains
  *
- * Translation infrastructure between hw and linux irq numbers.  This is
- * helpful for interrupt controllers to implement mapping between hardware
- * irq numbers and the Linux irq number space.
- *
- * irq_domains also have hooks for translating device tree or other
- * firmware interrupt representations into a hardware irq number that
- * can be mapped back to a Linux irq number without any extra platform
- * support code.
- *
- * Interrupt controller "domain" data structure. This could be defined as a
- * irq domain controller. That is, it handles the mapping between hardware
- * and virtual interrupt numbers for a given interrupt domain. The domain
- * structure is generally created by the PIC code for a given PIC instance
- * (though a domain can cover more than one PIC if they have a flat number
- * model). It's the domain callbacks that are responsible for setting the
- * irq_chip on a given irq_desc after it's been mapped.
- *
- * The host code and data structures use a fwnode_handle pointer to
- * identify the domain. In some cases, and in order to preserve source
- * code compatibility, this fwnode pointer is "upgraded" to a DT
- * device_node. For those firmware infrastructures that do not provide
- * a unique identifier for an interrupt controller, the irq_domain
- * code offers a fwnode allocator.
+ * See Documentation/core-api/irq/irq-domain.rst for the details.
  */
 
 #ifndef _LINUX_IRQDOMAIN_H
@@ -61,24 +39,57 @@ struct msi_parent_ops;
  * pass a device-specific description of an interrupt.
  */
 struct irq_fwspec {
-	struct fwnode_handle *fwnode;
-	int param_count;
-	u32 param[IRQ_DOMAIN_IRQ_SPEC_PARAMS];
+	struct fwnode_handle	*fwnode;
+	int			param_count;
+	u32			param[IRQ_DOMAIN_IRQ_SPEC_PARAMS];
 };
 
+/**
+ * struct irq_fwspec_info - firmware provided IRQ information structure
+ *
+ * @flags:		Information validity flags
+ * @affinity:		Affinity mask for this interrupt
+ *
+ * This structure reports firmware-specific information about an
+ * interrupt. The only significant information is the affinity of a
+ * per-CPU interrupt, but this is designed to be extended as required.
+ */
+struct irq_fwspec_info {
+	unsigned long		flags;
+	const struct cpumask	*affinity;
+};
+
+#define IRQ_FWSPEC_INFO_AFFINITY_VALID	BIT(0)
+
 /* Conversion function from of_phandle_args fields to fwspec  */
 void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
 			       unsigned int count, struct irq_fwspec *fwspec);
 
 /**
  * struct irq_domain_ops - Methods for irq_domain objects
- * @match: Match an interrupt controller device node to a host, returns
- *         1 on a match
- * @map: Create or update a mapping between a virtual irq number and a hw
- *       irq number. This is called only once for a given mapping.
- * @unmap: Dispose of such a mapping
- * @xlate: Given a device tree node and interrupt specifier, decode
- *         the hardware irq number and linux irq type value.
+ * @match:	Match an interrupt controller device node to a domain, returns
+ *		1 on a match
+ * @select:	Match an interrupt controller fw specification. It is more generic
+ *		than @match as it receives a complete struct irq_fwspec. Therefore,
+ *		@select is preferred if provided. Returns 1 on a match.
+ * @map:	Create or update a mapping between a virtual irq number and a hw
+ *		irq number. This is called only once for a given mapping.
+ * @unmap:	Dispose of such a mapping
+ * @xlate:	Given a device tree node and interrupt specifier, decode
+ *		the hardware irq number and linux irq type value.
+ * @alloc:	Allocate @nr_irqs interrupts starting from @virq.
+ * @free:	Free @nr_irqs interrupts starting from @virq.
+ * @activate:	Activate one interrupt in HW (@irqd). If @reserve is set, only
+ *		reserve the vector. If unset, assign the vector (called from
+ *		request_irq()).
+ * @deactivate:	Disarm one interrupt (@irqd).
+ * @translate:	Given @fwspec, decode the hardware irq number (@out_hwirq) and
+ *		linux irq type value (@out_type). This is a generalised @xlate
+ *		(over struct irq_fwspec) and is preferred if provided.
+ * @get_fwspec_info:
+ *		Given @fwspec, report additional firmware-provided information in
+ *		@info. Optional.
+ * @debug_show:	For domains to show specific data for an interrupt in debugfs.
  *
  * Functions below are provided by the driver and called whenever a new mapping
  * is created or an old mapping is disposed. The driver can then proceed to
@@ -86,29 +97,30 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
  * to setup the irq_desc when returning from map().
  */
 struct irq_domain_ops {
-	int (*match)(struct irq_domain *d, struct device_node *node,
-		     enum irq_domain_bus_token bus_token);
-	int (*select)(struct irq_domain *d, struct irq_fwspec *fwspec,
-		      enum irq_domain_bus_token bus_token);
-	int (*map)(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw);
-	void (*unmap)(struct irq_domain *d, unsigned int virq);
-	int (*xlate)(struct irq_domain *d, struct device_node *node,
-		     const u32 *intspec, unsigned int intsize,
-		     unsigned long *out_hwirq, unsigned int *out_type);
+	int	(*match)(struct irq_domain *d, struct device_node *node,
+			 enum irq_domain_bus_token bus_token);
+	int	(*select)(struct irq_domain *d, struct irq_fwspec *fwspec,
+			  enum irq_domain_bus_token bus_token);
+	int	(*map)(struct irq_domain *d, unsigned int virq, irq_hw_number_t hw);
+	void	(*unmap)(struct irq_domain *d, unsigned int virq);
+	int	(*xlate)(struct irq_domain *d, struct device_node *node,
+			 const u32 *intspec, unsigned int intsize,
+			 unsigned long *out_hwirq, unsigned int *out_type);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	/* extended V2 interfaces to support hierarchy irq_domains */
-	int (*alloc)(struct irq_domain *d, unsigned int virq,
-		     unsigned int nr_irqs, void *arg);
-	void (*free)(struct irq_domain *d, unsigned int virq,
-		     unsigned int nr_irqs);
-	int (*activate)(struct irq_domain *d, struct irq_data *irqd, bool reserve);
-	void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data);
-	int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec,
-			 unsigned long *out_hwirq, unsigned int *out_type);
+	int	(*alloc)(struct irq_domain *d, unsigned int virq,
+			 unsigned int nr_irqs, void *arg);
+	void	(*free)(struct irq_domain *d, unsigned int virq,
+			unsigned int nr_irqs);
+	int	(*activate)(struct irq_domain *d, struct irq_data *irqd, bool reserve);
+	void	(*deactivate)(struct irq_domain *d, struct irq_data *irq_data);
+	int	(*translate)(struct irq_domain *d, struct irq_fwspec *fwspec,
+			     unsigned long *out_hwirq, unsigned int *out_type);
+	int	(*get_fwspec_info)(struct irq_fwspec *fwspec, struct irq_fwspec_info *info);
 #endif
 #ifdef CONFIG_GENERIC_IRQ_DEBUGFS
-	void (*debug_show)(struct seq_file *m, struct irq_domain *d,
-			   struct irq_data *irqd, int ind);
+	void	(*debug_show)(struct seq_file *m, struct irq_domain *d,
+			      struct irq_data *irqd, int ind);
 #endif
 };
 
@@ -131,6 +143,9 @@ struct irq_domain_chip_generic;
  * Optional elements:
  * @fwnode:	Pointer to firmware node associated with the irq_domain. Pretty easy
  *		to swap it for the of_node via the irq_domain_get_of_node accessor
+ * @bus_token:	@fwnode's device_node might be used for several irq domains. But
+ *		in connection with @bus_token, the pair shall be unique in a
+ *		system.
  * @gc:		Pointer to a list of generic chips. There is a helper function for
  *		setting up one or more generic chips for interrupt controllers
  *		drivers using the generic chip library which uses this pointer.
@@ -141,9 +156,12 @@ struct irq_domain_chip_generic;
  *		purposes related to the irq domain.
  * @parent:	Pointer to parent irq_domain to support hierarchy irq_domains
  * @msi_parent_ops: Pointer to MSI parent domain methods for per device domain init
+ * @exit:	Function called when the domain is destroyed
  *
  * Revmap data, used internally by the irq domain code:
- * @revmap_size:	Size of the linear map table @revmap[]
+ * @hwirq_max:		Top limit for the HW irq number. Especially to avoid
+ *			conflicts/failures with reserved HW irqs. Can be ~0.
+ * @revmap_size:	Size of the linear map table @revmap
  * @revmap_tree:	Radix map tree for hwirqs that don't fit in the linear map
  * @revmap:		Linear table of irq_data pointers
  */
@@ -169,12 +187,13 @@ struct irq_domain {
 #ifdef CONFIG_GENERIC_MSI_IRQ
 	const struct msi_parent_ops	*msi_parent_ops;
 #endif
+	void				(*exit)(struct irq_domain *d);
 
 	/* reverse map data. The linear map gets appended to the irq_domain */
 	irq_hw_number_t			hwirq_max;
 	unsigned int			revmap_size;
 	struct radix_tree_root		revmap_tree;
-	struct irq_data __rcu		*revmap[];
+	struct irq_data __rcu		*revmap[] __counted_by(revmap_size);
 };
 
 /* Irq domain flags */
@@ -182,7 +201,7 @@ enum {
 	/* Irq domain is hierarchical */
 	IRQ_DOMAIN_FLAG_HIERARCHY	= (1 << 0),
 
-	/* Irq domain name was allocated in __irq_domain_add() */
+	/* Irq domain name was allocated internally */
 	IRQ_DOMAIN_NAME_ALLOCATED	= (1 << 1),
 
 	/* Irq domain is an IPI domain with virq per cpu */
@@ -208,6 +227,15 @@ enum {
 	/* Irq domain is a MSI device domain */
 	IRQ_DOMAIN_FLAG_MSI_DEVICE	= (1 << 9),
 
+	/* Irq domain must destroy generic chips when removed */
+	IRQ_DOMAIN_FLAG_DESTROY_GC	= (1 << 10),
+
+	/* Address and data pair is mutable when irq_set_affinity() */
+	IRQ_DOMAIN_FLAG_MSI_IMMUTABLE	= (1 << 11),
+
+	/* IRQ domain requires parent fwnode matching */
+	IRQ_DOMAIN_FLAG_FWNODE_PARENT	= (1 << 12),
+
 	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
@@ -221,8 +249,7 @@ static inline struct device_node *irq_domain_get_of_node(struct irq_domain *d)
 	return to_of_node(d->fwnode);
 }
 
-static inline void irq_domain_set_pm_device(struct irq_domain *d,
-					    struct device *dev)
+static inline void irq_domain_set_pm_device(struct irq_domain *d, struct device *dev)
 {
 	if (d)
 		d->pm_dev = dev;
@@ -238,14 +265,12 @@ enum {
 	IRQCHIP_FWNODE_NAMED_ID,
 };
 
-static inline
-struct fwnode_handle *irq_domain_alloc_named_fwnode(const char *name)
+static inline struct fwnode_handle *irq_domain_alloc_named_fwnode(const char *name)
 {
 	return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_NAMED, 0, name, NULL);
 }
 
-static inline
-struct fwnode_handle *irq_domain_alloc_named_id_fwnode(const char *name, int id)
+static inline struct fwnode_handle *irq_domain_alloc_named_id_fwnode(const char *name, int id)
 {
 	return __irq_domain_alloc_fwnode(IRQCHIP_FWNODE_NAMED_ID, id, name,
 					 NULL);
@@ -257,53 +282,87 @@ static inline struct fwnode_handle *irq_domain_alloc_fwnode(phys_addr_t *pa)
 }
 
 void irq_domain_free_fwnode(struct fwnode_handle *fwnode);
-struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, unsigned int size,
-				    irq_hw_number_t hwirq_max, int direct_max,
-				    const struct irq_domain_ops *ops,
-				    void *host_data);
-struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode,
-					    unsigned int size,
-					    unsigned int first_irq,
-					    const struct irq_domain_ops *ops,
-					    void *host_data);
-struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
-					 unsigned int size,
-					 unsigned int first_irq,
-					 irq_hw_number_t first_hwirq,
-					 const struct irq_domain_ops *ops,
-					 void *host_data);
-struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode,
-					    unsigned int size,
-					    unsigned int first_irq,
-					    irq_hw_number_t first_hwirq,
-					    const struct irq_domain_ops *ops,
-					    void *host_data);
-extern struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
-						   enum irq_domain_bus_token bus_token);
-extern void irq_set_default_host(struct irq_domain *host);
-extern struct irq_domain *irq_get_default_host(void);
-extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
-				  irq_hw_number_t hwirq, int node,
-				  const struct irq_affinity_desc *affinity);
 
-static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node)
-{
-	return node ? &node->fwnode : NULL;
-}
+DEFINE_FREE(irq_domain_free_fwnode, struct fwnode_handle *, if (_T) irq_domain_free_fwnode(_T))
+
+struct irq_domain_chip_generic_info;
+
+/**
+ * struct irq_domain_info - Domain information structure
+ * @fwnode:		firmware node for the interrupt controller
+ * @domain_flags:	Additional flags to add to the domain flags
+ * @size:		Size of linear map; 0 for radix mapping only
+ * @hwirq_max:		Maximum number of interrupts supported by controller
+ * @direct_max:		Maximum value of direct maps;
+ *			Use ~0 for no limit; 0 for no direct mapping
+ * @hwirq_base:		The first hardware interrupt number (legacy domains only)
+ * @virq_base:		The first Linux interrupt number for legacy domains to
+ *			immediately associate the interrupts after domain creation
+ * @bus_token:		Domain bus token
+ * @name_suffix:	Optional name suffix to avoid collisions when multiple
+ *			domains are added using same fwnode
+ * @ops:		Domain operation callbacks
+ * @host_data:		Controller private data pointer
+ * @dev:		Device which creates the domain
+ * @dgc_info:		Geneneric chip information structure pointer used to
+ *			create generic chips for the domain if not NULL.
+ * @init:		Function called when the domain is created.
+ *			Allow to do some additional domain initialisation.
+ * @exit:		Function called when the domain is destroyed.
+ *			Allow to do some additional cleanup operation.
+ */
+struct irq_domain_info {
+	struct fwnode_handle			*fwnode;
+	unsigned int				domain_flags;
+	unsigned int				size;
+	irq_hw_number_t				hwirq_max;
+	int					direct_max;
+	unsigned int				hwirq_base;
+	unsigned int				virq_base;
+	enum irq_domain_bus_token		bus_token;
+	const char				*name_suffix;
+	const struct irq_domain_ops		*ops;
+	void					*host_data;
+	struct device				*dev;
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+	/**
+	 * @parent: Pointer to the parent irq domain used in a hierarchy domain
+	 */
+	struct irq_domain			*parent;
+#endif
+	struct irq_domain_chip_generic_info	*dgc_info;
+	int					(*init)(struct irq_domain *d);
+	void					(*exit)(struct irq_domain *d);
+};
+
+struct irq_domain *irq_domain_instantiate(const struct irq_domain_info *info);
+struct irq_domain *devm_irq_domain_instantiate(struct device *dev,
+					       const struct irq_domain_info *info);
+
+struct irq_domain *irq_domain_create_simple(struct fwnode_handle *fwnode, unsigned int size,
+					    unsigned int first_irq,
+					    const struct irq_domain_ops *ops, void *host_data);
+struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode, unsigned int size,
+					    unsigned int first_irq, irq_hw_number_t first_hwirq,
+					    const struct irq_domain_ops *ops, void *host_data);
+struct irq_domain *irq_find_matching_fwspec(struct irq_fwspec *fwspec,
+					    enum irq_domain_bus_token bus_token);
+void irq_set_default_domain(struct irq_domain *domain);
+struct irq_domain *irq_get_default_domain(void);
+int irq_domain_alloc_descs(int virq, unsigned int nr_irqs, irq_hw_number_t hwirq, int node,
+			   const struct irq_affinity_desc *affinity);
 
 extern const struct fwnode_operations irqchip_fwnode_ops;
 
-static inline bool is_fwnode_irqchip(struct fwnode_handle *fwnode)
+static inline bool is_fwnode_irqchip(const struct fwnode_handle *fwnode)
 {
 	return fwnode && fwnode->ops == &irqchip_fwnode_ops;
 }
 
-extern void irq_domain_update_bus_token(struct irq_domain *domain,
-					enum irq_domain_bus_token bus_token);
+void irq_domain_update_bus_token(struct irq_domain *domain, enum irq_domain_bus_token bus_token);
 
-static inline
-struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode,
-					    enum irq_domain_bus_token bus_token)
+static inline struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode,
+							  enum irq_domain_bus_token bus_token)
 {
 	struct irq_fwspec fwspec = {
 		.fwnode = fwnode,
@@ -315,7 +374,7 @@ struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode,
 static inline struct irq_domain *irq_find_matching_host(struct device_node *node,
 							enum irq_domain_bus_token bus_token)
 {
-	return irq_find_matching_fwnode(of_node_to_fwnode(node), bus_token);
+	return irq_find_matching_fwnode(of_fwnode_handle(node), bus_token);
 }
 
 static inline struct irq_domain *irq_find_host(struct device_node *node)
@@ -329,88 +388,107 @@ static inline struct irq_domain *irq_find_host(struct device_node *node)
 	return d;
 }
 
-static inline struct irq_domain *irq_domain_add_simple(struct device_node *of_node,
-						       unsigned int size,
-						       unsigned int first_irq,
-						       const struct irq_domain_ops *ops,
-						       void *host_data)
-{
-	return irq_domain_create_simple(of_node_to_fwnode(of_node), size, first_irq, ops, host_data);
-}
-
-/**
- * irq_domain_add_linear() - Allocate and register a linear revmap irq_domain.
- * @of_node: pointer to interrupt controller's device tree node.
- * @size: Number of interrupts in the domain.
- * @ops: map/unmap domain callbacks
- * @host_data: Controller private data pointer
- */
-static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
-					 unsigned int size,
-					 const struct irq_domain_ops *ops,
-					 void *host_data)
-{
-	return __irq_domain_add(of_node_to_fwnode(of_node), size, size, 0, ops, host_data);
-}
-
 #ifdef CONFIG_IRQ_DOMAIN_NOMAP
-static inline struct irq_domain *irq_domain_add_nomap(struct device_node *of_node,
-					 unsigned int max_irq,
-					 const struct irq_domain_ops *ops,
-					 void *host_data)
-{
-	return __irq_domain_add(of_node_to_fwnode(of_node), 0, max_irq, max_irq, ops, host_data);
+static inline struct irq_domain *irq_domain_create_nomap(struct fwnode_handle *fwnode,
+							 unsigned int max_irq,
+							 const struct irq_domain_ops *ops,
+							 void *host_data)
+{
+	const struct irq_domain_info info = {
+		.fwnode		= fwnode,
+		.hwirq_max	= max_irq,
+		.direct_max	= max_irq,
+		.ops		= ops,
+		.host_data	= host_data,
+	};
+	struct irq_domain *d = irq_domain_instantiate(&info);
+
+	return IS_ERR(d) ? NULL : d;
 }
 
-extern unsigned int irq_create_direct_mapping(struct irq_domain *host);
+unsigned int irq_create_direct_mapping(struct irq_domain *domain);
 #endif
 
-static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
-					 const struct irq_domain_ops *ops,
-					 void *host_data)
-{
-	return __irq_domain_add(of_node_to_fwnode(of_node), 0, ~0, 0, ops, host_data);
-}
-
+/**
+ * irq_domain_create_linear - Allocate and register a linear revmap irq_domain.
+ * @fwnode:	pointer to interrupt controller's FW node.
+ * @size:	Number of interrupts in the domain.
+ * @ops:	map/unmap domain callbacks
+ * @host_data:	Controller private data pointer
+ *
+ * Returns: Newly created irq_domain
+ */
 static inline struct irq_domain *irq_domain_create_linear(struct fwnode_handle *fwnode,
-					 unsigned int size,
-					 const struct irq_domain_ops *ops,
-					 void *host_data)
-{
-	return __irq_domain_add(fwnode, size, size, 0, ops, host_data);
+							  unsigned int size,
+							  const struct irq_domain_ops *ops,
+							  void *host_data)
+{
+	const struct irq_domain_info info = {
+		.fwnode		= fwnode,
+		.size		= size,
+		.hwirq_max	= size,
+		.ops		= ops,
+		.host_data	= host_data,
+	};
+	struct irq_domain *d = irq_domain_instantiate(&info);
+
+	return IS_ERR(d) ? NULL : d;
 }
 
 static inline struct irq_domain *irq_domain_create_tree(struct fwnode_handle *fwnode,
-					 const struct irq_domain_ops *ops,
-					 void *host_data)
-{
-	return __irq_domain_add(fwnode, 0, ~0, 0, ops, host_data);
+							const struct irq_domain_ops *ops,
+							void *host_data)
+{
+	const struct irq_domain_info info = {
+		.fwnode		= fwnode,
+		.hwirq_max	= ~0,
+		.ops		= ops,
+		.host_data	= host_data,
+	};
+	struct irq_domain *d = irq_domain_instantiate(&info);
+
+	return IS_ERR(d) ? NULL : d;
 }
 
-extern void irq_domain_remove(struct irq_domain *host);
+void irq_domain_remove(struct irq_domain *domain);
 
-extern int irq_domain_associate(struct irq_domain *domain, unsigned int irq,
-					irq_hw_number_t hwirq);
-extern void irq_domain_associate_many(struct irq_domain *domain,
-				      unsigned int irq_base,
-				      irq_hw_number_t hwirq_base, int count);
+int irq_domain_associate(struct irq_domain *domain, unsigned int irq, irq_hw_number_t hwirq);
+void irq_domain_associate_many(struct irq_domain *domain, unsigned int irq_base,
+			       irq_hw_number_t hwirq_base, int count);
 
-extern unsigned int irq_create_mapping_affinity(struct irq_domain *host,
-				      irq_hw_number_t hwirq,
-				      const struct irq_affinity_desc *affinity);
-extern unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec);
-extern void irq_dispose_mapping(unsigned int virq);
+unsigned int irq_create_mapping_affinity(struct irq_domain *domain, irq_hw_number_t hwirq,
+					 const struct irq_affinity_desc *affinity);
+unsigned int irq_create_fwspec_mapping(struct irq_fwspec *fwspec);
+void irq_dispose_mapping(unsigned int virq);
 
-static inline unsigned int irq_create_mapping(struct irq_domain *host,
-					      irq_hw_number_t hwirq)
+/**
+ * irq_create_mapping - Map a hardware interrupt into linux irq space
+ * @domain:	domain owning this hardware interrupt or NULL for default domain
+ * @hwirq:	hardware irq number in that domain space
+ *
+ * Only one mapping per hardware interrupt is permitted.
+ *
+ * If the sense/trigger is to be specified, set_irq_type() should be called
+ * on the number returned from that call.
+ *
+ * Returns: Linux irq number or 0 on error
+ */
+static inline unsigned int irq_create_mapping(struct irq_domain *domain, irq_hw_number_t hwirq)
 {
-	return irq_create_mapping_affinity(host, hwirq, NULL);
+	return irq_create_mapping_affinity(domain, hwirq, NULL);
 }
 
-extern struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain,
-					      irq_hw_number_t hwirq,
-					      unsigned int *irq);
+struct irq_desc *__irq_resolve_mapping(struct irq_domain *domain,
+				       irq_hw_number_t hwirq,
+				       unsigned int *irq);
 
+/**
+ * irq_resolve_mapping - Find a linux irq from a hw irq number.
+ * @domain:	domain owning this hardware interrupt
+ * @hwirq:	hardware irq number in that domain space
+ *
+ * Returns: Interrupt descriptor
+ */
 static inline struct irq_desc *irq_resolve_mapping(struct irq_domain *domain,
 						   irq_hw_number_t hwirq)
 {
@@ -419,8 +497,10 @@ static inline struct irq_desc *irq_resolve_mapping(struct irq_domain *domain,
 
 /**
  * irq_find_mapping() - Find a linux irq from a hw irq number.
- * @domain: domain owning this hardware interrupt
- * @hwirq: hardware irq number in that domain space
+ * @domain:	domain owning this hardware interrupt
+ * @hwirq:	hardware irq number in that domain space
+ *
+ * Returns: Linux irq number or 0 if not found
  */
 static inline unsigned int irq_find_mapping(struct irq_domain *domain,
 					    irq_hw_number_t hwirq)
@@ -433,108 +513,117 @@ static inline unsigned int irq_find_mapping(struct irq_domain *domain,
 	return 0;
 }
 
-static inline unsigned int irq_linear_revmap(struct irq_domain *domain,
-					     irq_hw_number_t hwirq)
-{
-	return irq_find_mapping(domain, hwirq);
-}
-
 extern const struct irq_domain_ops irq_domain_simple_ops;
 
 /* stock xlate functions */
 int irq_domain_xlate_onecell(struct irq_domain *d, struct device_node *ctrlr,
-			const u32 *intspec, unsigned int intsize,
-			irq_hw_number_t *out_hwirq, unsigned int *out_type);
+			     const u32 *intspec, unsigned int intsize,
+			     irq_hw_number_t *out_hwirq, unsigned int *out_type);
 int irq_domain_xlate_twocell(struct irq_domain *d, struct device_node *ctrlr,
-			const u32 *intspec, unsigned int intsize,
-			irq_hw_number_t *out_hwirq, unsigned int *out_type);
+			     const u32 *intspec, unsigned int intsize,
+			     irq_hw_number_t *out_hwirq, unsigned int *out_type);
 int irq_domain_xlate_onetwocell(struct irq_domain *d, struct device_node *ctrlr,
-			const u32 *intspec, unsigned int intsize,
-			irq_hw_number_t *out_hwirq, unsigned int *out_type);
-
-int irq_domain_translate_twocell(struct irq_domain *d,
-				 struct irq_fwspec *fwspec,
-				 unsigned long *out_hwirq,
-				 unsigned int *out_type);
-
-int irq_domain_translate_onecell(struct irq_domain *d,
-				 struct irq_fwspec *fwspec,
-				 unsigned long *out_hwirq,
-				 unsigned int *out_type);
+				const u32 *intspec, unsigned int intsize,
+				irq_hw_number_t *out_hwirq, unsigned int *out_type);
+int irq_domain_xlate_twothreecell(struct irq_domain *d, struct device_node *ctrlr,
+				  const u32 *intspec, unsigned int intsize,
+				  irq_hw_number_t *out_hwirq, unsigned int *out_type);
+
+int irq_domain_translate_onecell(struct irq_domain *d, struct irq_fwspec *fwspec,
+				 unsigned long *out_hwirq, unsigned int *out_type);
+int irq_domain_translate_twocell(struct irq_domain *d, struct irq_fwspec *fwspec,
+				 unsigned long *out_hwirq, unsigned int *out_type);
+int irq_domain_translate_twothreecell(struct irq_domain *d, struct irq_fwspec *fwspec,
+				      unsigned long *out_hwirq, unsigned int *out_type);
 
 /* IPI functions */
 int irq_reserve_ipi(struct irq_domain *domain, const struct cpumask *dest);
 int irq_destroy_ipi(unsigned int irq, const struct cpumask *dest);
 
 /* V2 interfaces to support hierarchy IRQ domains. */
-extern struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain,
-						unsigned int virq);
-extern void irq_domain_set_info(struct irq_domain *domain, unsigned int virq,
-				irq_hw_number_t hwirq,
-				const struct irq_chip *chip,
-				void *chip_data, irq_flow_handler_t handler,
-				void *handler_data, const char *handler_name);
-extern void irq_domain_reset_irq_data(struct irq_data *irq_data);
+struct irq_data *irq_domain_get_irq_data(struct irq_domain *domain, unsigned int virq);
+void irq_domain_set_info(struct irq_domain *domain, unsigned int virq, irq_hw_number_t hwirq,
+			 const struct irq_chip *chip, void *chip_data, irq_flow_handler_t handler,
+			 void *handler_data, const char *handler_name);
+void irq_domain_reset_irq_data(struct irq_data *irq_data);
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
-extern struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
-			unsigned int flags, unsigned int size,
-			struct fwnode_handle *fwnode,
-			const struct irq_domain_ops *ops, void *host_data);
-
-static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *parent,
-					    unsigned int flags,
-					    unsigned int size,
-					    struct device_node *node,
-					    const struct irq_domain_ops *ops,
-					    void *host_data)
-{
-	return irq_domain_create_hierarchy(parent, flags, size,
-					   of_node_to_fwnode(node),
-					   ops, host_data);
-}
-
-extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
-				   unsigned int nr_irqs, int node, void *arg,
-				   bool realloc,
-				   const struct irq_affinity_desc *affinity);
-extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
-extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
-extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
-
-static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
-			unsigned int nr_irqs, int node, void *arg)
-{
-	return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false,
-				       NULL);
-}
-
-extern int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,
-					   unsigned int irq_base,
-					   unsigned int nr_irqs, void *arg);
-extern int irq_domain_set_hwirq_and_chip(struct irq_domain *domain,
-					 unsigned int virq,
-					 irq_hw_number_t hwirq,
-					 const struct irq_chip *chip,
-					 void *chip_data);
-extern void irq_domain_free_irqs_common(struct irq_domain *domain,
-					unsigned int virq,
-					unsigned int nr_irqs);
-extern void irq_domain_free_irqs_top(struct irq_domain *domain,
-				     unsigned int virq, unsigned int nr_irqs);
-
-extern int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg);
-extern int irq_domain_pop_irq(struct irq_domain *domain, int virq);
-
-extern int irq_domain_alloc_irqs_parent(struct irq_domain *domain,
-					unsigned int irq_base,
-					unsigned int nr_irqs, void *arg);
-
-extern void irq_domain_free_irqs_parent(struct irq_domain *domain,
-					unsigned int irq_base,
-					unsigned int nr_irqs);
-
-extern int irq_domain_disconnect_hierarchy(struct irq_domain *domain,
-					   unsigned int virq);
+/**
+ * irq_domain_create_hierarchy - Add a irqdomain into the hierarchy
+ * @parent:	Parent irq domain to associate with the new domain
+ * @flags:	Irq domain flags associated to the domain
+ * @size:	Size of the domain. See below
+ * @fwnode:	Optional fwnode of the interrupt controller
+ * @ops:	Pointer to the interrupt domain callbacks
+ * @host_data:	Controller private data pointer
+ *
+ * If @size is 0 a tree domain is created, otherwise a linear domain.
+ *
+ * If successful the parent is associated to the new domain and the
+ * domain flags are set.
+ *
+ * Returns: A pointer to IRQ domain, or %NULL on failure.
+ */
+static inline struct irq_domain *irq_domain_create_hierarchy(struct irq_domain *parent,
+							     unsigned int flags, unsigned int size,
+							     struct fwnode_handle *fwnode,
+							     const struct irq_domain_ops *ops,
+							     void *host_data)
+{
+	const struct irq_domain_info info = {
+		.fwnode		= fwnode,
+		.size		= size,
+		.hwirq_max	= size ? : ~0U,
+		.ops		= ops,
+		.host_data	= host_data,
+		.domain_flags	= flags,
+		.parent		= parent,
+	};
+	struct irq_domain *d = irq_domain_instantiate(&info);
+
+	return IS_ERR(d) ? NULL : d;
+}
+
+int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base, unsigned int nr_irqs,
+			    int node, void *arg, bool realloc,
+			    const struct irq_affinity_desc *affinity);
+void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
+int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
+void irq_domain_deactivate_irq(struct irq_data *irq_data);
+
+/**
+ * irq_domain_alloc_irqs - Allocate IRQs from domain
+ * @domain:	domain to allocate from
+ * @nr_irqs:	number of IRQs to allocate
+ * @node:	NUMA node id for memory allocation
+ * @arg:	domain specific argument
+ *
+ * See __irq_domain_alloc_irqs()' documentation.
+ */
+static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs,
+					int node, void *arg)
+{
+	return __irq_domain_alloc_irqs(domain, -1, nr_irqs, node, arg, false, NULL);
+}
+
+int irq_domain_set_hwirq_and_chip(struct irq_domain *domain, unsigned int virq,
+				  irq_hw_number_t hwirq, const struct irq_chip *chip,
+				  void *chip_data);
+void irq_domain_free_irqs_common(struct irq_domain *domain, unsigned int virq,
+				 unsigned int nr_irqs);
+void irq_domain_free_irqs_top(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs);
+
+int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg);
+int irq_domain_pop_irq(struct irq_domain *domain, int virq);
+
+int irq_domain_alloc_irqs_parent(struct irq_domain *domain, unsigned int irq_base,
+				 unsigned int nr_irqs, void *arg);
+
+void irq_domain_free_irqs_parent(struct irq_domain *domain, unsigned int irq_base,
+				 unsigned int nr_irqs);
+
+int irq_domain_disconnect_hierarchy(struct irq_domain *domain, unsigned int virq);
+
+int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info);
 
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
@@ -543,8 +632,7 @@ static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 
 static inline bool irq_domain_is_ipi(struct irq_domain *domain)
 {
-	return domain->flags &
-		(IRQ_DOMAIN_FLAG_IPI_PER_CPU | IRQ_DOMAIN_FLAG_IPI_SINGLE);
+	return domain->flags & (IRQ_DOMAIN_FLAG_IPI_PER_CPU | IRQ_DOMAIN_FLAG_IPI_SINGLE);
 }
 
 static inline bool irq_domain_is_ipi_per_cpu(struct irq_domain *domain)
@@ -572,15 +660,18 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain)
 	return domain->flags & IRQ_DOMAIN_FLAG_MSI_DEVICE;
 }
 
+static inline bool irq_domain_is_msi_immutable(struct irq_domain *domain)
+{
+	return domain->flags & IRQ_DOMAIN_FLAG_MSI_IMMUTABLE;
+}
 #else	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
-static inline int irq_domain_alloc_irqs(struct irq_domain *domain,
-			unsigned int nr_irqs, int node, void *arg)
+static inline int irq_domain_alloc_irqs(struct irq_domain *domain, unsigned int nr_irqs,
+					int node, void *arg)
 {
 	return -1;
 }
 
-static inline void irq_domain_free_irqs(unsigned int virq,
-					unsigned int nr_irqs) { }
+static inline void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs) { }
 
 static inline bool irq_domain_is_hierarchy(struct irq_domain *domain)
 {
@@ -617,12 +708,66 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain)
 	return false;
 }
 
+static inline int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info)
+{
+	return -EINVAL;
+}
 #endif	/* CONFIG_IRQ_DOMAIN_HIERARCHY */
 
+#ifdef CONFIG_GENERIC_MSI_IRQ
+int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq, unsigned int type);
+void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq);
+#else
+static inline int msi_device_domain_alloc_wired(struct irq_domain *domain, unsigned int hwirq,
+						unsigned int type)
+{
+	WARN_ON_ONCE(1);
+	return -EINVAL;
+}
+static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsigned int virq)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
+
+static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node,
+						     const struct irq_domain_ops *ops,
+						     void *host_data)
+{
+	struct irq_domain_info info = {
+		.fwnode		= of_fwnode_handle(of_node),
+		.hwirq_max	= ~0U,
+		.ops		= ops,
+		.host_data	= host_data,
+	};
+	struct irq_domain *d;
+
+	d = irq_domain_instantiate(&info);
+	return IS_ERR(d) ? NULL : d;
+}
+
+static inline struct irq_domain *irq_domain_add_linear(struct device_node *of_node,
+						       unsigned int size,
+						       const struct irq_domain_ops *ops,
+						       void *host_data)
+{
+	struct irq_domain_info info = {
+		.fwnode		= of_fwnode_handle(of_node),
+		.size		= size,
+		.hwirq_max	= size,
+		.ops		= ops,
+		.host_data	= host_data,
+	};
+	struct irq_domain *d;
+
+	d = irq_domain_instantiate(&info);
+	return IS_ERR(d) ? NULL : d;
+}
+
 #else /* CONFIG_IRQ_DOMAIN */
 static inline void irq_dispose_mapping(unsigned int virq) { }
-static inline struct irq_domain *irq_find_matching_fwnode(
-	struct fwnode_handle *fwnode, enum irq_domain_bus_token bus_token)
+static inline struct irq_domain *irq_find_matching_fwnode(struct fwnode_handle *fwnode,
+							  enum irq_domain_bus_token bus_token)
 {
 	return NULL;
 }
diff --git a/include/linux/irqdomain_defs.h b/include/linux/irqdomain_defs.h
index c29921fd8cd1..36653e2ee1c9 100644
--- a/include/linux/irqdomain_defs.h
+++ b/include/linux/irqdomain_defs.h
@@ -25,7 +25,8 @@ enum irq_domain_bus_token {
 	DOMAIN_BUS_PCI_DEVICE_MSIX,
 	DOMAIN_BUS_DMAR,
 	DOMAIN_BUS_AMDVI,
-	DOMAIN_BUS_PCI_DEVICE_IMS,
+	DOMAIN_BUS_DEVICE_MSI,
+	DOMAIN_BUS_WIRED_TO_MSI,
 };
 
 #endif /* _LINUX_IRQDOMAIN_DEFS_H */
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 5ec0fa71399e..57b074e0cfbb 100644
--- a/include/linux/irqflags.h
+++ b/include/linux/irqflags.h
@@ -12,10 +12,14 @@
 #ifndef _LINUX_TRACE_IRQFLAGS_H
 #define _LINUX_TRACE_IRQFLAGS_H
 
+#include <linux/irqflags_types.h>
 #include <linux/typecheck.h>
+#include <linux/cleanup.h>
 #include <asm/irqflags.h>
 #include <asm/percpu.h>
 
+struct task_struct;
+
 /* Currently lockdep_softirqs_on/off is used only by lockdep */
 #ifdef CONFIG_PROVE_LOCKING
   extern void lockdep_softirqs_on(unsigned long ip);
@@ -23,29 +27,20 @@
   extern void lockdep_hardirqs_on_prepare(void);
   extern void lockdep_hardirqs_on(unsigned long ip);
   extern void lockdep_hardirqs_off(unsigned long ip);
+  extern void lockdep_cleanup_dead_cpu(unsigned int cpu,
+				       struct task_struct *idle);
 #else
   static inline void lockdep_softirqs_on(unsigned long ip) { }
   static inline void lockdep_softirqs_off(unsigned long ip) { }
   static inline void lockdep_hardirqs_on_prepare(void) { }
   static inline void lockdep_hardirqs_on(unsigned long ip) { }
   static inline void lockdep_hardirqs_off(unsigned long ip) { }
+  static inline void lockdep_cleanup_dead_cpu(unsigned int cpu,
+					      struct task_struct *idle) {}
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 
-/* Per-task IRQ trace events information. */
-struct irqtrace_events {
-	unsigned int	irq_events;
-	unsigned long	hardirq_enable_ip;
-	unsigned long	hardirq_disable_ip;
-	unsigned int	hardirq_enable_event;
-	unsigned int	hardirq_disable_event;
-	unsigned long	softirq_disable_ip;
-	unsigned long	softirq_enable_ip;
-	unsigned int	softirq_disable_event;
-	unsigned int	softirq_enable_event;
-};
-
 DECLARE_PER_CPU(int, hardirqs_enabled);
 DECLARE_PER_CPU(int, hardirq_context);
 
@@ -125,7 +120,7 @@ do {						\
 # define lockdep_softirq_enter()		do { } while (0)
 # define lockdep_softirq_exit()			do { } while (0)
 # define lockdep_hrtimer_enter(__hrtimer)	false
-# define lockdep_hrtimer_exit(__context)	do { } while (0)
+# define lockdep_hrtimer_exit(__context)	do { (void)(__context); } while (0)
 # define lockdep_posixtimer_enter()		do { } while (0)
 # define lockdep_posixtimer_exit()		do { } while (0)
 # define lockdep_irq_work_enter(__work)		do { } while (0)
@@ -267,4 +262,10 @@ extern void warn_bogus_irq_restore(void);
 
 #define irqs_disabled_flags(flags) raw_irqs_disabled_flags(flags)
 
+DEFINE_LOCK_GUARD_0(irq, local_irq_disable(), local_irq_enable())
+DEFINE_LOCK_GUARD_0(irqsave,
+		    local_irq_save(_T->flags),
+		    local_irq_restore(_T->flags),
+		    unsigned long flags)
+
 #endif
diff --git a/include/linux/irqflags_types.h b/include/linux/irqflags_types.h
new file mode 100644
index 000000000000..c13f0d915097
--- /dev/null
+++ b/include/linux/irqflags_types.h
@@ -0,0 +1,22 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_IRQFLAGS_TYPES_H
+#define _LINUX_IRQFLAGS_TYPES_H
+
+#ifdef CONFIG_TRACE_IRQFLAGS
+
+/* Per-task IRQ trace events information. */
+struct irqtrace_events {
+	unsigned int	irq_events;
+	unsigned long	hardirq_enable_ip;
+	unsigned long	hardirq_disable_ip;
+	unsigned int	hardirq_enable_event;
+	unsigned int	hardirq_disable_event;
+	unsigned long	softirq_disable_ip;
+	unsigned long	softirq_enable_ip;
+	unsigned int	softirq_disable_event;
+	unsigned int	softirq_enable_event;
+};
+
+#endif
+
+#endif /* _LINUX_IRQFLAGS_TYPES_H */
diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h
index c30f454a9518..72dd1eb3a0e7 100644
--- a/include/linux/irqhandler.h
+++ b/include/linux/irqhandler.h
@@ -8,7 +8,7 @@
  */
 
 struct irq_desc;
-struct irq_data;
+
 typedef	void (*irq_flow_handler_t)(struct irq_desc *desc);
 
 #endif
diff --git a/include/linux/irqnr.h b/include/linux/irqnr.h
index 3496baa0b07f..e97206c721a0 100644
--- a/include/linux/irqnr.h
+++ b/include/linux/irqnr.h
@@ -5,30 +5,36 @@
 #include <uapi/linux/irqnr.h>
 
 
-extern int nr_irqs;
+unsigned int irq_get_nr_irqs(void) __pure;
+unsigned int irq_set_nr_irqs(unsigned int nr);
 extern struct irq_desc *irq_to_desc(unsigned int irq);
 unsigned int irq_get_next_irq(unsigned int offset);
 
-# define for_each_irq_desc(irq, desc)					\
-	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
-	     irq++, desc = irq_to_desc(irq))				\
-		if (!desc)						\
-			;						\
-		else
-
+#define for_each_irq_desc(irq, desc)                                      \
+	for (unsigned int __nr_irqs__ = irq_get_nr_irqs(); __nr_irqs__;   \
+	     __nr_irqs__ = 0)                                             \
+		for (irq = 0, desc = irq_to_desc(irq); irq < __nr_irqs__; \
+		     irq++, desc = irq_to_desc(irq))                      \
+			if (!desc)                                        \
+				;                                         \
+			else
 
 # define for_each_irq_desc_reverse(irq, desc)				\
-	for (irq = nr_irqs - 1, desc = irq_to_desc(irq); irq >= 0;	\
-	     irq--, desc = irq_to_desc(irq))				\
+	for (irq = irq_get_nr_irqs() - 1, desc = irq_to_desc(irq);	\
+	     irq >= 0; irq--, desc = irq_to_desc(irq))			\
 		if (!desc)						\
 			;						\
 		else
 
-# define for_each_active_irq(irq)			\
-	for (irq = irq_get_next_irq(0); irq < nr_irqs;	\
-	     irq = irq_get_next_irq(irq + 1))
+#define for_each_active_irq(irq)                                        \
+	for (unsigned int __nr_irqs__ = irq_get_nr_irqs(); __nr_irqs__; \
+	     __nr_irqs__ = 0)                                           \
+		for (irq = irq_get_next_irq(0); irq < __nr_irqs__;      \
+		     irq = irq_get_next_irq(irq + 1))
 
-#define for_each_irq_nr(irq)                   \
-       for (irq = 0; irq < nr_irqs; irq++)
+#define for_each_irq_nr(irq)                                            \
+	for (unsigned int __nr_irqs__ = irq_get_nr_irqs(); __nr_irqs__; \
+	     __nr_irqs__ = 0)                                           \
+		for (irq = 0; irq < __nr_irqs__; irq++)
 
 #endif
diff --git a/include/linux/iscsi_ibft.h b/include/linux/iscsi_ibft.h
index 790e7fcfc1a6..e2742748104d 100644
--- a/include/linux/iscsi_ibft.h
+++ b/include/linux/iscsi_ibft.h
@@ -21,12 +21,20 @@
  */
 extern phys_addr_t ibft_phys_addr;
 
+#ifdef CONFIG_ISCSI_IBFT_FIND
+
 /*
  * Routine used to find and reserve the iSCSI Boot Format Table. The
  * physical address is set in the ibft_phys_addr variable.
  */
-#ifdef CONFIG_ISCSI_IBFT_FIND
 void reserve_ibft_region(void);
+
+/*
+ * Physical bounds to search for the iSCSI Boot Format Table.
+ */
+#define IBFT_START 0x80000 /* 512kB */
+#define IBFT_END 0x100000 /* 1MB */
+
 #else
 static inline void reserve_ibft_region(void) {}
 #endif
diff --git a/include/linux/ism.h b/include/linux/ism.h
index ea2bcdae7401..b7feb4dcd5a8 100644
--- a/include/linux/ism.h
+++ b/include/linux/ism.h
@@ -11,42 +11,28 @@
 
 #include <linux/workqueue.h>
 
-struct ism_dmb {
-	u64 dmb_tok;
-	u64 rgid;
-	u32 dmb_len;
-	u32 sba_idx;
-	u32 vlan_valid;
-	u32 vlan_id;
-	void *cpu_addr;
-	dma_addr_t dma_addr;
-};
-
 /* Unless we gain unexpected popularity, this limit should hold for a while */
 #define MAX_CLIENTS		8
 #define ISM_NR_DMBS		1920
 
 struct ism_dev {
 	spinlock_t lock; /* protects the ism device */
+	spinlock_t cmd_lock; /* serializes cmds */
 	struct list_head list;
+	struct dibs_dev *dibs;
 	struct pci_dev *pdev;
 
 	struct ism_sba *sba;
 	dma_addr_t sba_dma_addr;
 	DECLARE_BITMAP(sba_bitmap, ISM_NR_DMBS);
-	u8 *sba_client_arr;	/* entries are indices into 'clients' array */
 	void *priv[MAX_CLIENTS];
 
 	struct ism_eq *ieq;
 	dma_addr_t ieq_dma_addr;
 
-	struct device dev;
-	u64 local_gid;
 	int ieq_idx;
 
-	atomic_t free_clients_cnt;
-	atomic_t add_dev_cnt;
-	wait_queue_head_t waitq;
+	struct ism_client *subs[MAX_CLIENTS];
 };
 
 struct ism_event {
@@ -59,18 +45,8 @@ struct ism_event {
 
 struct ism_client {
 	const char *name;
-	void (*add)(struct ism_dev *dev);
-	void (*remove)(struct ism_dev *dev);
 	void (*handle_event)(struct ism_dev *dev, struct ism_event *event);
-	/* Parameter dmbemask contains a bit vector with updated DMBEs, if sent
-	 * via ism_move_data(). Callback function must handle all active bits
-	 * indicated by dmbemask.
-	 */
-	void (*handle_irq)(struct ism_dev *dev, unsigned int bit, u16 dmbemask);
 	/* Private area - don't touch! */
-	struct work_struct remove_work;
-	struct work_struct add_work;
-	struct ism_dev *tgt_ism;
 	u8 id;
 };
 
@@ -86,13 +62,6 @@ static inline void ism_set_priv(struct ism_dev *dev, struct ism_client *client,
 	dev->priv[client->id] = priv;
 }
 
-int  ism_register_dmb(struct ism_dev *dev, struct ism_dmb *dmb,
-		      struct ism_client *client);
-int  ism_unregister_dmb(struct ism_dev *dev, struct ism_dmb *dmb);
-int  ism_move(struct ism_dev *dev, u64 dmb_tok, unsigned int idx, bool sf,
-	      unsigned int offset, void *data, unsigned int size);
-u8  *ism_get_seid(void);
-
 const struct smcd_ops *ism_get_smcd_ops(void);
 
 #endif	/* _ISM_H */
diff --git a/include/linux/iversion.h b/include/linux/iversion.h
index f174ff1b59ee..8f972eaca2ed 100644
--- a/include/linux/iversion.h
+++ b/include/linux/iversion.h
@@ -256,7 +256,7 @@ inode_peek_iversion(const struct inode *inode)
  * For filesystems without any sort of change attribute, the best we can
  * do is fake one up from the ctime:
  */
-static inline u64 time_to_chattr(struct timespec64 *t)
+static inline u64 time_to_chattr(const struct timespec64 *t)
 {
 	u64 chattr = t->tv_sec;
 
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index f619bae1dcc5..f5eaf76198f3 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -28,7 +28,7 @@
 #include <linux/slab.h>
 #include <linux/bit_spinlock.h>
 #include <linux/blkdev.h>
-#include <crypto/hash.h>
+#include <linux/crc32c.h>
 #endif
 
 #define journal_oom_retry 1
@@ -265,8 +265,10 @@ typedef struct journal_superblock_s
 	__u8	s_padding2[3];
 /* 0x0054 */
 	__be32	s_num_fc_blks;		/* Number of fast commit blocks */
-/* 0x0058 */
-	__u32	s_padding[41];
+	__be32	s_head;			/* blocknr of head of log, only uptodate
+					 * while the filesystem is clean */
+/* 0x005C */
+	__u32	s_padding[40];
 	__be32	s_checksum;		/* crc32c(superblock) */
 
 /* 0x0100 */
@@ -274,17 +276,6 @@ typedef struct journal_superblock_s
 /* 0x0400 */
 } journal_superblock_t;
 
-/* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */
-#define JBD2_HAS_COMPAT_FEATURE(j,mask)					\
-	((j)->j_format_version >= 2 &&					\
-	 ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask))))
-#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask)				\
-	((j)->j_format_version >= 2 &&					\
-	 ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask))))
-#define JBD2_HAS_INCOMPAT_FEATURE(j,mask)				\
-	((j)->j_format_version >= 2 &&					\
-	 ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask))))
-
 #define JBD2_FEATURE_COMPAT_CHECKSUM		0x00000001
 
 #define JBD2_FEATURE_INCOMPAT_REVOKE		0x00000001
@@ -468,7 +459,6 @@ struct jbd2_revoke_table_s;
  * @h_ref: Reference count on this handle.
  * @h_err: Field for caller's use to track errors through large fs operations.
  * @h_sync: Flag for sync-on-close.
- * @h_jdata: Flag to force data journaling.
  * @h_reserved: Flag for handle for reserved credits.
  * @h_aborted: Flag indicating fatal error on handle.
  * @h_type: For handle statistics.
@@ -500,7 +490,6 @@ struct jbd2_journal_handle
 
 	/* Flags [no locking] */
 	unsigned int	h_sync:		1;
-	unsigned int	h_jdata:	1;
 	unsigned int	h_reserved:	1;
 	unsigned int	h_aborted:	1;
 	unsigned int	h_type:		8;
@@ -623,12 +612,6 @@ struct transaction_s
 	struct journal_head	*t_checkpoint_list;
 
 	/*
-	 * Doubly-linked circular list of all buffers submitted for IO while
-	 * checkpointing. [j_list_lock]
-	 */
-	struct journal_head	*t_checkpoint_io_list;
-
-	/*
 	 * Doubly-linked circular list of metadata buffers being
 	 * shadowed by log IO.  The IO buffers on the iobuf list and
 	 * the shadow buffers on this list match each other one for
@@ -646,11 +629,6 @@ struct transaction_s
 	struct list_head	t_inode_list;
 
 	/*
-	 * Protects info related to handles
-	 */
-	spinlock_t		t_handle_lock;
-
-	/*
 	 * Longest time some handle had to wait for running transaction
 	 */
 	unsigned long		t_max_wait;
@@ -720,12 +698,6 @@ struct transaction_s
 
 	/* Disk flush needs to be sent to fs partition [no locking] */
 	int			t_need_data_flush;
-
-	/*
-	 * For use by the filesystem to store fs-specific data
-	 * structures associated with the transaction
-	 */
-	struct list_head	t_private_list;
 };
 
 struct transaction_run_stats_s {
@@ -776,11 +748,6 @@ struct journal_s
 	unsigned long		j_flags;
 
 	/**
-	 * @j_atomic_flags: Atomic journaling state flags.
-	 */
-	unsigned long		j_atomic_flags;
-
-	/**
 	 * @j_errno:
 	 *
 	 * Is there an outstanding uncleared error on the journal (from a prior
@@ -804,11 +771,6 @@ struct journal_s
 	journal_superblock_t	*j_superblock;
 
 	/**
-	 * @j_format_version: Version of the superblock format.
-	 */
-	int			j_format_version;
-
-	/**
 	 * @j_state_lock: Protect the various scalars in the journal.
 	 */
 	rwlock_t		j_state_lock;
@@ -911,7 +873,7 @@ struct journal_s
 	 * Journal head shrinker, reclaim buffer's journal head which
 	 * has been written back.
 	 */
-	struct shrinker		j_shrinker;
+	struct shrinker		*j_shrinker;
 
 	/**
 	 * @j_checkpoint_jh_count:
@@ -1024,6 +986,13 @@ struct journal_s
 	struct block_device	*j_fs_dev;
 
 	/**
+	 * @j_fs_dev_wb_err:
+	 *
+	 * Records the errseq of the client fs's backing block device.
+	 */
+	errseq_t		j_fs_dev_wb_err;
+
+	/**
 	 * @j_total_len: Total maximum capacity of the journal region on disk.
 	 */
 	unsigned int		j_total_len;
@@ -1109,6 +1078,13 @@ struct journal_s
 	int			j_revoke_records_per_block;
 
 	/**
+	 * @j_transaction_overhead_buffers:
+	 *
+	 * Number of blocks each transaction needs for its own bookkeeping
+	 */
+	int			j_transaction_overhead_buffers;
+
+	/**
 	 * @j_commit_interval:
 	 *
 	 * What is the maximum transaction lifetime before we begin a commit?
@@ -1258,13 +1234,6 @@ struct journal_s
 	void *j_private;
 
 	/**
-	 * @j_chksum_driver:
-	 *
-	 * Reference to checksum algorithm driver via cryptoapi.
-	 */
-	struct crypto_shash *j_chksum_driver;
-
-	/**
 	 * @j_csum_seed:
 	 *
 	 * Precomputed journal UUID checksum for seeding other checksums.
@@ -1284,6 +1253,12 @@ struct journal_s
 	 */
 	struct lockdep_map	j_trans_commit_map;
 #endif
+	/**
+	 * @jbd2_trans_commit_key:
+	 *
+	 * "struct lock_class_key" for @j_trans_commit_map
+	 */
+	struct lock_class_key	jbd2_trans_commit_key;
 
 	/**
 	 * @j_fc_cleanup_callback:
@@ -1324,11 +1299,22 @@ struct journal_s
 		rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \
 	} while (0)
 
+/*
+ * We can support any known requested features iff the
+ * superblock is not in version 1.  Otherwise we fail to support any
+ * extended sb features.
+ */
+static inline bool jbd2_format_support_feature(journal_t *j)
+{
+	return j->j_superblock->s_header.h_blocktype !=
+					cpu_to_be32(JBD2_SUPERBLOCK_V1);
+}
+
 /* journal feature predicate functions */
 #define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \
 static inline bool jbd2_has_feature_##name(journal_t *j) \
 { \
-	return ((j)->j_format_version >= 2 && \
+	return (jbd2_format_support_feature(j) && \
 		((j)->j_superblock->s_feature_compat & \
 		 cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \
 } \
@@ -1346,7 +1332,7 @@ static inline void jbd2_clear_feature_##name(journal_t *j) \
 #define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \
 static inline bool jbd2_has_feature_##name(journal_t *j) \
 { \
-	return ((j)->j_format_version >= 2 && \
+	return (jbd2_format_support_feature(j) && \
 		((j)->j_superblock->s_feature_ro_compat & \
 		 cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \
 } \
@@ -1364,7 +1350,7 @@ static inline void jbd2_clear_feature_##name(journal_t *j) \
 #define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \
 static inline bool jbd2_has_feature_##name(journal_t *j) \
 { \
-	return ((j)->j_format_version >= 2 && \
+	return (jbd2_format_support_feature(j) && \
 		((j)->j_superblock->s_feature_incompat & \
 		 cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \
 } \
@@ -1388,6 +1374,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
 JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 
+/* Journal high priority write IO operation flags */
+#define JBD2_JOURNAL_REQ_FLAGS		(REQ_META | REQ_SYNC | REQ_IDLE)
+
 /*
  * Journal flag definitions
  */
@@ -1397,9 +1386,9 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 #define JBD2_FLUSHED	0x008	/* The journal superblock has been flushed */
 #define JBD2_LOADED	0x010	/* The journal superblock has been loaded */
 #define JBD2_BARRIER	0x020	/* Use IDE barriers */
-#define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
-						 * data write error in ordered
-						 * mode */
+#define JBD2_CYCLE_RECORD		0x080	/* Journal cycled record log on
+						 * clean and empty filesystem
+						 * logging area */
 #define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
 #define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
 #define JBD2_JOURNAL_FLUSH_DISCARD	0x0001
@@ -1408,18 +1397,11 @@ JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)
 					JBD2_JOURNAL_FLUSH_ZEROOUT)
 
 /*
- * Journal atomic flag definitions
- */
-#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
-						 * buffer back to disk */
-
-/*
  * Function declarations for the journaling transaction and buffer
  * management
  */
 
 /* Filing buffers */
-extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *);
 extern bool __jbd2_journal_refile_buffer(struct journal_head *);
 extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *);
 extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
@@ -1446,9 +1428,12 @@ void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
 extern void jbd2_journal_commit_transaction(journal_t *);
 
 /* Checkpoint list management */
-void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy);
+enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP};
+
+void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type);
 unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan);
 int __jbd2_journal_remove_checkpoint(struct journal_head *);
+int jbd2_journal_try_remove_checkpoint(struct journal_head *jh);
 void jbd2_journal_destroy_checkpoint(journal_t *journal);
 void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);
 
@@ -1597,10 +1582,13 @@ void jbd2_journal_put_journal_head(struct journal_head *jh);
  */
 extern struct kmem_cache *jbd2_handle_cache;
 
-static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags)
-{
-	return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags);
-}
+/*
+ * This specialized allocator has to be a macro for its allocations to be
+ * accounted separately (to have a separate alloc_tag). The typecast is
+ * intentional to enforce typesafety.
+ */
+#define jbd2_alloc_handle(_gfp_flags)	\
+		((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags))
 
 static inline void jbd2_free_handle(handle_t *handle)
 {
@@ -1613,10 +1601,13 @@ static inline void jbd2_free_handle(handle_t *handle)
  */
 extern struct kmem_cache *jbd2_inode_cache;
 
-static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags)
-{
-	return kmem_cache_alloc(jbd2_inode_cache, gfp_flags);
-}
+/*
+ * This specialized allocator has to be a macro for its allocations to be
+ * accounted separately (to have a separate alloc_tag). The typecast is
+ * intentional to enforce typesafety.
+ */
+#define jbd2_alloc_inode(_gfp_flags)	\
+		((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags))
 
 static inline void jbd2_free_inode(struct jbd2_inode *jinode)
 {
@@ -1630,10 +1621,12 @@ extern void	   jbd2_journal_destroy_revoke_record_cache(void);
 extern void	   jbd2_journal_destroy_revoke_table_cache(void);
 extern int __init jbd2_journal_init_revoke_record_cache(void);
 extern int __init jbd2_journal_init_revoke_table_cache(void);
+struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size);
+void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table);
 
 extern void	   jbd2_journal_destroy_revoke(journal_t *);
 extern int	   jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);
-extern int	   jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
+extern void	   jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
 extern void	   jbd2_journal_write_revoke_records(transaction_t *transaction,
 						     struct list_head *log_bufs);
 
@@ -1671,12 +1664,7 @@ int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
 int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
 int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
-int jbd2_fc_release_bufs(journal_t *journal);
-
-static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
-{
-	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
-}
+void jbd2_fc_release_bufs(journal_t *journal);
 
 /*
  * is_journal_abort
@@ -1705,6 +1693,25 @@ static inline void jbd2_journal_abort_handle(handle_t *handle)
 	handle->h_aborted = 1;
 }
 
+static inline void jbd2_init_fs_dev_write_error(journal_t *journal)
+{
+	struct address_space *mapping = journal->j_fs_dev->bd_mapping;
+
+	/*
+	 * Save the original wb_err value of client fs's bdev mapping which
+	 * could be used to detect the client fs's metadata async write error.
+	 */
+	errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err);
+}
+
+static inline int jbd2_check_fs_dev_write_error(journal_t *journal)
+{
+	struct address_space *mapping = journal->j_fs_dev->bd_mapping;
+
+	return errseq_check(&mapping->wb_err,
+			    READ_ONCE(journal->j_fs_dev_wb_err));
+}
+
 #endif /* __KERNEL__   */
 
 /* Comparison functions for transaction IDs: perform comparisons using
@@ -1722,20 +1729,13 @@ static inline int tid_geq(tid_t x, tid_t y)
 	return (difference >= 0);
 }
 
-extern int jbd2_journal_blocks_per_page(struct inode *inode);
+extern int jbd2_journal_blocks_per_folio(struct inode *inode);
 extern size_t journal_tag_bytes(journal_t *journal);
 
-static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j)
-{
-	return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j);
-}
-
 static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
 {
-	WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) &&
-		     journal->j_chksum_driver == NULL);
-
-	return journal->j_chksum_driver != NULL;
+	return jbd2_has_feature_csum2(journal) ||
+	       jbd2_has_feature_csum3(journal);
 }
 
 static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb)
@@ -1772,28 +1772,9 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal)
 #define BJ_Reserved	4	/* Buffer is reserved for access by journal */
 #define BJ_Types	5
 
-/* JBD uses a CRC32 checksum */
-#define JBD_MAX_CHECKSUM_SIZE 4
-
-static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
-			      const void *address, unsigned int length)
+static inline u32 jbd2_chksum(u32 crc, const void *address, unsigned int length)
 {
-	struct {
-		struct shash_desc shash;
-		char ctx[JBD_MAX_CHECKSUM_SIZE];
-	} desc;
-	int err;
-
-	BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) >
-		JBD_MAX_CHECKSUM_SIZE);
-
-	desc.shash.tfm = journal->j_chksum_driver;
-	*(u32 *)desc.ctx = crc;
-
-	err = crypto_shash_update(&desc.shash, address, length);
-	BUG_ON(err);
-
-	return *(u32 *)desc.ctx;
+	return crc32c(crc, address, length);
 }
 
 /* Return most recent uncommitted transaction */
diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index ab7f8c152b89..7c1c1821c694 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -24,14 +24,14 @@
  * Jozsef
  */
 #include <linux/bitops.h>
-#include <linux/unaligned/packed_struct.h>
+#include <linux/unaligned.h>
 
 /* Best hash sizes are of power of two */
 #define jhash_size(n)   ((u32)1<<(n))
 /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */
 #define jhash_mask(n)   (jhash_size(n)-1)
 
-/* __jhash_mix -- mix 3 32-bit values reversibly. */
+/* __jhash_mix - mix 3 32-bit values reversibly. */
 #define __jhash_mix(a, b, c)			\
 {						\
 	a -= c;  a ^= rol32(c, 4);  c += b;	\
@@ -60,7 +60,7 @@
 /* jhash - hash an arbitrary key
  * @k: sequence of bytes as key
  * @length: the length of the key
- * @initval: the previous hash, or an arbitray value
+ * @initval: the previous hash, or an arbitrary value
  *
  * The generic version, hashes an arbitrary sequence of bytes.
  * No alignment or length assumptions are made about the input key.
@@ -77,9 +77,9 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 
 	/* All but the last block: affect some 32 bits of (a,b,c) */
 	while (length > 12) {
-		a += __get_unaligned_cpu32(k);
-		b += __get_unaligned_cpu32(k + 4);
-		c += __get_unaligned_cpu32(k + 8);
+		a += get_unaligned((u32 *)k);
+		b += get_unaligned((u32 *)(k + 4));
+		c += get_unaligned((u32 *)(k + 8));
 		__jhash_mix(a, b, c);
 		length -= 12;
 		k += 12;
@@ -110,7 +110,7 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 /* jhash2 - hash an array of u32's
  * @k: the key which must be an array of u32's
  * @length: the number of u32's in the key
- * @initval: the previous hash, or an arbitray value
+ * @initval: the previous hash, or an arbitrary value
  *
  * Returns the hash value of the key.
  */
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 5e13f801c902..fdef2c155c27 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -59,9 +59,9 @@
 /* LATCH is used in the interval timer and ftape setup. */
 #define LATCH ((CLOCK_TICK_RATE + HZ/2) / HZ)	/* For divider */
 
-extern int register_refined_jiffies(long clock_tick_rate);
+extern void register_refined_jiffies(long clock_tick_rate);
 
-/* TICK_USEC is the time between ticks in usec assuming SHIFTED_HZ */
+/* TICK_USEC is the time between ticks in usec */
 #define TICK_USEC ((USEC_PER_SEC + HZ/2) / HZ)
 
 /* USER_TICK_USEC is the time between ticks in usec assuming fake USER_HZ */
@@ -72,9 +72,15 @@ extern int register_refined_jiffies(long clock_tick_rate);
 #endif
 
 /*
- * The 64-bit value is not atomic - you MUST NOT read it
+ * The 64-bit value is not atomic on 32-bit systems - you MUST NOT read it
  * without sampling the sequence number in jiffies_lock.
  * get_jiffies_64() will do this for you as appropriate.
+ *
+ * jiffies and jiffies_64 are at the same address for little-endian systems
+ * and for 64-bit big-endian systems.
+ * On 32-bit big-endian systems, jiffies is the lower 32 bits of jiffies_64
+ * (i.e., at address @jiffies_64 + 4).
+ * See arch/ARCH/kernel/vmlinux.lds.S
  */
 extern u64 __cacheline_aligned_in_smp jiffies_64;
 extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffies;
@@ -82,46 +88,94 @@ extern unsigned long volatile __cacheline_aligned_in_smp __jiffy_arch_data jiffi
 #if (BITS_PER_LONG < 64)
 u64 get_jiffies_64(void);
 #else
+/**
+ * get_jiffies_64 - read the 64-bit non-atomic jiffies_64 value
+ *
+ * When BITS_PER_LONG < 64, this uses sequence number sampling using
+ * jiffies_lock to protect the 64-bit read.
+ *
+ * Return: current 64-bit jiffies value
+ */
 static inline u64 get_jiffies_64(void)
 {
 	return (u64)jiffies;
 }
 #endif
 
-/*
- *	These inlines deal with timer wrapping correctly. You are 
- *	strongly encouraged to use them
- *	1. Because people otherwise forget
- *	2. Because if the timer wrap changes in future you won't have to
- *	   alter your driver code.
+/**
+ * DOC: General information about time_* inlines
+ *
+ * These inlines deal with timer wrapping correctly. You are strongly encouraged
+ * to use them:
  *
- * time_after(a,b) returns true if the time a is after time b.
+ * #. Because people otherwise forget
+ * #. Because if the timer wrap changes in future you won't have to alter your
+ *    driver code.
+ */
+
+/**
+ * time_after - returns true if the time a is after time b.
+ * @a: first comparable as unsigned long
+ * @b: second comparable as unsigned long
  *
  * Do this with "<0" and ">=0" to only test the sign of the result. A
  * good compiler would generate better code (and a really good compiler
  * wouldn't care). Gcc is currently neither.
+ *
+ * Return: %true is time a is after time b, otherwise %false.
  */
 #define time_after(a,b)		\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
 	 ((long)((b) - (a)) < 0))
+/**
+ * time_before - returns true if the time a is before time b.
+ * @a: first comparable as unsigned long
+ * @b: second comparable as unsigned long
+ *
+ * Return: %true is time a is before time b, otherwise %false.
+ */
 #define time_before(a,b)	time_after(b,a)
 
+/**
+ * time_after_eq - returns true if the time a is after or the same as time b.
+ * @a: first comparable as unsigned long
+ * @b: second comparable as unsigned long
+ *
+ * Return: %true is time a is after or the same as time b, otherwise %false.
+ */
 #define time_after_eq(a,b)	\
 	(typecheck(unsigned long, a) && \
 	 typecheck(unsigned long, b) && \
 	 ((long)((a) - (b)) >= 0))
+/**
+ * time_before_eq - returns true if the time a is before or the same as time b.
+ * @a: first comparable as unsigned long
+ * @b: second comparable as unsigned long
+ *
+ * Return: %true is time a is before or the same as time b, otherwise %false.
+ */
 #define time_before_eq(a,b)	time_after_eq(b,a)
 
-/*
- * Calculate whether a is in the range of [b, c].
+/**
+ * time_in_range - Calculate whether a is in the range of [b, c].
+ * @a: time to test
+ * @b: beginning of the range
+ * @c: end of the range
+ *
+ * Return: %true is time a is in the range [b, c], otherwise %false.
  */
 #define time_in_range(a,b,c) \
 	(time_after_eq(a,b) && \
 	 time_before_eq(a,c))
 
-/*
- * Calculate whether a is in the range of [b, c).
+/**
+ * time_in_range_open - Calculate whether a is in the range of [b, c).
+ * @a: time to test
+ * @b: beginning of the range
+ * @c: end of the range
+ *
+ * Return: %true is time a is in the range [b, c), otherwise %false.
  */
 #define time_in_range_open(a,b,c) \
 	(time_after_eq(a,b) && \
@@ -129,45 +183,138 @@ static inline u64 get_jiffies_64(void)
 
 /* Same as above, but does so with platform independent 64bit types.
  * These must be used when utilizing jiffies_64 (i.e. return value of
- * get_jiffies_64() */
+ * get_jiffies_64()). */
+
+/**
+ * time_after64 - returns true if the time a is after time b.
+ * @a: first comparable as __u64
+ * @b: second comparable as __u64
+ *
+ * This must be used when utilizing jiffies_64 (i.e. return value of
+ * get_jiffies_64()).
+ *
+ * Return: %true is time a is after time b, otherwise %false.
+ */
 #define time_after64(a,b)	\
 	(typecheck(__u64, a) &&	\
 	 typecheck(__u64, b) && \
 	 ((__s64)((b) - (a)) < 0))
+/**
+ * time_before64 - returns true if the time a is before time b.
+ * @a: first comparable as __u64
+ * @b: second comparable as __u64
+ *
+ * This must be used when utilizing jiffies_64 (i.e. return value of
+ * get_jiffies_64()).
+ *
+ * Return: %true is time a is before time b, otherwise %false.
+ */
 #define time_before64(a,b)	time_after64(b,a)
 
+/**
+ * time_after_eq64 - returns true if the time a is after or the same as time b.
+ * @a: first comparable as __u64
+ * @b: second comparable as __u64
+ *
+ * This must be used when utilizing jiffies_64 (i.e. return value of
+ * get_jiffies_64()).
+ *
+ * Return: %true is time a is after or the same as time b, otherwise %false.
+ */
 #define time_after_eq64(a,b)	\
 	(typecheck(__u64, a) && \
 	 typecheck(__u64, b) && \
 	 ((__s64)((a) - (b)) >= 0))
+/**
+ * time_before_eq64 - returns true if the time a is before or the same as time b.
+ * @a: first comparable as __u64
+ * @b: second comparable as __u64
+ *
+ * This must be used when utilizing jiffies_64 (i.e. return value of
+ * get_jiffies_64()).
+ *
+ * Return: %true is time a is before or the same as time b, otherwise %false.
+ */
 #define time_before_eq64(a,b)	time_after_eq64(b,a)
 
+/**
+ * time_in_range64 - Calculate whether a is in the range of [b, c].
+ * @a: time to test
+ * @b: beginning of the range
+ * @c: end of the range
+ *
+ * Return: %true is time a is in the range [b, c], otherwise %false.
+ */
 #define time_in_range64(a, b, c) \
 	(time_after_eq64(a, b) && \
 	 time_before_eq64(a, c))
 
 /*
- * These four macros compare jiffies and 'a' for convenience.
+ * These eight macros compare jiffies[_64] and 'a' for convenience.
  */
 
-/* time_is_before_jiffies(a) return true if a is before jiffies */
+/**
+ * time_is_before_jiffies - return true if a is before jiffies
+ * @a: time (unsigned long) to compare to jiffies
+ *
+ * Return: %true is time a is before jiffies, otherwise %false.
+ */
 #define time_is_before_jiffies(a) time_after(jiffies, a)
+/**
+ * time_is_before_jiffies64 - return true if a is before jiffies_64
+ * @a: time (__u64) to compare to jiffies_64
+ *
+ * Return: %true is time a is before jiffies_64, otherwise %false.
+ */
 #define time_is_before_jiffies64(a) time_after64(get_jiffies_64(), a)
 
-/* time_is_after_jiffies(a) return true if a is after jiffies */
+/**
+ * time_is_after_jiffies - return true if a is after jiffies
+ * @a: time (unsigned long) to compare to jiffies
+ *
+ * Return: %true is time a is after jiffies, otherwise %false.
+ */
 #define time_is_after_jiffies(a) time_before(jiffies, a)
+/**
+ * time_is_after_jiffies64 - return true if a is after jiffies_64
+ * @a: time (__u64) to compare to jiffies_64
+ *
+ * Return: %true is time a is after jiffies_64, otherwise %false.
+ */
 #define time_is_after_jiffies64(a) time_before64(get_jiffies_64(), a)
 
-/* time_is_before_eq_jiffies(a) return true if a is before or equal to jiffies*/
+/**
+ * time_is_before_eq_jiffies - return true if a is before or equal to jiffies
+ * @a: time (unsigned long) to compare to jiffies
+ *
+ * Return: %true is time a is before or the same as jiffies, otherwise %false.
+ */
 #define time_is_before_eq_jiffies(a) time_after_eq(jiffies, a)
+/**
+ * time_is_before_eq_jiffies64 - return true if a is before or equal to jiffies_64
+ * @a: time (__u64) to compare to jiffies_64
+ *
+ * Return: %true is time a is before or the same jiffies_64, otherwise %false.
+ */
 #define time_is_before_eq_jiffies64(a) time_after_eq64(get_jiffies_64(), a)
 
-/* time_is_after_eq_jiffies(a) return true if a is after or equal to jiffies*/
+/**
+ * time_is_after_eq_jiffies - return true if a is after or equal to jiffies
+ * @a: time (unsigned long) to compare to jiffies
+ *
+ * Return: %true is time a is after or the same as jiffies, otherwise %false.
+ */
 #define time_is_after_eq_jiffies(a) time_before_eq(jiffies, a)
+/**
+ * time_is_after_eq_jiffies64 - return true if a is after or equal to jiffies_64
+ * @a: time (__u64) to compare to jiffies_64
+ *
+ * Return: %true is time a is after or the same as jiffies_64, otherwise %false.
+ */
 #define time_is_after_eq_jiffies64(a) time_before_eq64(get_jiffies_64(), a)
 
 /*
- * Have the 32 bit jiffies value wrap 5 minutes after boot
+ * Have the 32-bit jiffies value wrap 5 minutes after boot
  * so jiffies wrap bugs show up earlier.
  */
 #define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ))
@@ -271,14 +418,14 @@ extern unsigned long preset_lpj;
 #define NSEC_CONVERSION ((unsigned long)((((u64)1 << NSEC_JIFFIE_SC) +\
                                         TICK_NSEC -1) / (u64)TICK_NSEC))
 /*
- * The maximum jiffie value is (MAX_INT >> 1).  Here we translate that
+ * The maximum jiffy value is (MAX_INT >> 1).  Here we translate that
  * into seconds.  The 64-bit case will overflow if we are not careful,
  * so use the messy SH_DIV macro to do it.  Still all constants.
  */
 #if BITS_PER_LONG < 64
 # define MAX_SEC_IN_JIFFIES \
 	(long)((u64)((u64)MAX_JIFFY_OFFSET * TICK_NSEC) / NSEC_PER_SEC)
-#else	/* take care of overflow on 64 bits machines */
+#else	/* take care of overflow on 64-bit machines */
 # define MAX_SEC_IN_JIFFIES \
 	(SH_DIV((MAX_JIFFY_OFFSET >> SEC_JIFFIE_SC) * TICK_NSEC, NSEC_PER_SEC, 1) - 1)
 
@@ -290,6 +437,12 @@ extern unsigned long preset_lpj;
 extern unsigned int jiffies_to_msecs(const unsigned long j);
 extern unsigned int jiffies_to_usecs(const unsigned long j);
 
+/**
+ * jiffies_to_nsecs - Convert jiffies to nanoseconds
+ * @j: jiffies value
+ *
+ * Return: nanoseconds value
+ */
 static inline u64 jiffies_to_nsecs(const unsigned long j)
 {
 	return (u64)jiffies_to_usecs(j) * NSEC_PER_USEC;
@@ -349,16 +502,18 @@ static inline unsigned long _msecs_to_jiffies(const unsigned int m)
  * - all other values are converted to jiffies by either multiplying
  *   the input value by a factor or dividing it with a factor and
  *   handling any 32-bit overflows.
- *   for the details see __msecs_to_jiffies()
+ *   for the details see _msecs_to_jiffies()
  *
  * msecs_to_jiffies() checks for the passed in value being a constant
  * via __builtin_constant_p() allowing gcc to eliminate most of the
- * code, __msecs_to_jiffies() is called if the value passed does not
+ * code. __msecs_to_jiffies() is called if the value passed does not
  * allow constant folding and the actual conversion must be done at
  * runtime.
- * the HZ range specific helpers _msecs_to_jiffies() are called both
+ * The HZ range specific helpers _msecs_to_jiffies() are called both
  * directly here and from __msecs_to_jiffies() in the case where
  * constant folding is not possible.
+ *
+ * Return: jiffies value
  */
 static __always_inline unsigned long msecs_to_jiffies(const unsigned int m)
 {
@@ -371,6 +526,19 @@ static __always_inline unsigned long msecs_to_jiffies(const unsigned int m)
 	}
 }
 
+/**
+ * secs_to_jiffies: - convert seconds to jiffies
+ * @_secs: time in seconds
+ *
+ * Conversion is done by simple multiplication with HZ
+ *
+ * secs_to_jiffies() is defined as a macro rather than a static inline
+ * function so it can be used in static initializers.
+ *
+ * Return: jiffies value
+ */
+#define secs_to_jiffies(_secs) (unsigned long)((_secs) * HZ)
+
 extern unsigned long __usecs_to_jiffies(const unsigned int u);
 #if !(USEC_PER_SEC % HZ)
 static inline unsigned long _usecs_to_jiffies(const unsigned int u)
@@ -400,12 +568,14 @@ static inline unsigned long _usecs_to_jiffies(const unsigned int u)
  *
  * usecs_to_jiffies() checks for the passed in value being a constant
  * via __builtin_constant_p() allowing gcc to eliminate most of the
- * code, __usecs_to_jiffies() is called if the value passed does not
+ * code. __usecs_to_jiffies() is called if the value passed does not
  * allow constant folding and the actual conversion must be done at
  * runtime.
- * the HZ range specific helpers _usecs_to_jiffies() are called both
+ * The HZ range specific helpers _usecs_to_jiffies() are called both
  * directly here and from __msecs_to_jiffies() in the case where
  * constant folding is not possible.
+ *
+ * Return: jiffies value
  */
 static __always_inline unsigned long usecs_to_jiffies(const unsigned int u)
 {
@@ -422,6 +592,7 @@ extern unsigned long timespec64_to_jiffies(const struct timespec64 *value);
 extern void jiffies_to_timespec64(const unsigned long jiffies,
 				  struct timespec64 *value);
 extern clock_t jiffies_to_clock_t(unsigned long x);
+
 static inline clock_t jiffies_delta_to_clock_t(long delta)
 {
 	return jiffies_to_clock_t(max(0L, delta));
@@ -440,4 +611,16 @@ extern unsigned long nsecs_to_jiffies(u64 n);
 
 #define TIMESTAMP_SIZE	30
 
+struct ctl_table;
+int proc_dointvec_jiffies(const struct ctl_table *table, int dir, void *buffer,
+			  size_t *lenp, loff_t *ppos);
+int proc_dointvec_ms_jiffies_minmax(const struct ctl_table *table, int dir,
+				    void *buffer, size_t *lenp, loff_t *ppos);
+int proc_dointvec_userhz_jiffies(const struct ctl_table *table, int dir,
+				 void *buffer, size_t *lenp, loff_t *ppos);
+int proc_dointvec_ms_jiffies(const struct ctl_table *table, int dir, void *buffer,
+			     size_t *lenp, loff_t *ppos);
+int proc_doulongvec_ms_jiffies_minmax(const struct ctl_table *table, int dir,
+				      void *buffer, size_t *lenp, loff_t *ppos);
+
 #endif
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 4e968ebadce6..fdb79dd1ebd8 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -75,6 +75,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <linux/cleanup.h>
 
 extern bool static_key_initialized;
 
@@ -216,6 +217,7 @@ extern struct jump_entry __start___jump_table[];
 extern struct jump_entry __stop___jump_table[];
 
 extern void jump_label_init(void);
+extern void jump_label_init_ro(void);
 extern void jump_label_lock(void);
 extern void jump_label_unlock(void);
 extern void arch_jump_label_transform(struct jump_entry *entry,
@@ -257,7 +259,7 @@ extern enum jump_label_type jump_label_init_type(struct jump_entry *entry);
 
 static __always_inline int static_key_count(struct static_key *key)
 {
-	return arch_atomic_read(&key->enabled);
+	return raw_atomic_read(&key->enabled);
 }
 
 static __always_inline void jump_label_init(void)
@@ -265,6 +267,8 @@ static __always_inline void jump_label_init(void)
 	static_key_initialized = true;
 }
 
+static __always_inline void jump_label_init_ro(void) { }
+
 static __always_inline bool static_key_false(struct static_key *key)
 {
 	if (unlikely_notrace(static_key_count(key) > 0))
@@ -344,6 +348,8 @@ static inline void static_key_disable(struct static_key *key)
 
 #endif	/* CONFIG_JUMP_LABEL */
 
+DEFINE_LOCK_GUARD_0(jump_label_lock, jump_label_lock(), jump_label_unlock())
+
 #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE
 #define jump_label_enabled static_key_enabled
 
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index fe3c9993b5bf..d5dd54c53ace 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -55,9 +55,8 @@ static inline void *dereference_symbol_descriptor(void *ptr)
 	if (is_ksym_addr((unsigned long)ptr))
 		return ptr;
 
-	preempt_disable();
+	guard(rcu)();
 	mod = __module_address((unsigned long)ptr);
-	preempt_enable();
 
 	if (mod)
 		ptr = dereference_module_function_descriptor(mod, ptr);
@@ -65,6 +64,9 @@ static inline void *dereference_symbol_descriptor(void *ptr)
 	return ptr;
 }
 
+/* How and when do we show kallsyms values? */
+extern bool kallsyms_show_value(const struct cred *cred);
+
 #ifdef CONFIG_KALLSYMS
 unsigned long kallsyms_sym_address(int idx);
 int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long),
@@ -93,10 +95,6 @@ extern int sprint_backtrace(char *buffer, unsigned long address);
 extern int sprint_backtrace_build_id(char *buffer, unsigned long address);
 
 int lookup_symbol_name(unsigned long addr, char *symname);
-int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name);
-
-/* How and when do we show kallsyms values? */
-extern bool kallsyms_show_value(const struct cred *cred);
 
 #else /* !CONFIG_KALLSYMS */
 
@@ -155,16 +153,6 @@ static inline int lookup_symbol_name(unsigned long addr, char *symname)
 	return -ERANGE;
 }
 
-static inline int lookup_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name)
-{
-	return -ERANGE;
-}
-
-static inline bool kallsyms_show_value(const struct cred *cred)
-{
-	return false;
-}
-
 static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *, unsigned long),
 					  void *data)
 {
diff --git a/include/linux/kasan-enabled.h b/include/linux/kasan-enabled.h
index 6f612d69ea0c..9eca967d8526 100644
--- a/include/linux/kasan-enabled.h
+++ b/include/linux/kasan-enabled.h
@@ -4,32 +4,46 @@
 
 #include <linux/static_key.h>
 
-#ifdef CONFIG_KASAN_HW_TAGS
-
+#if defined(CONFIG_ARCH_DEFER_KASAN) || defined(CONFIG_KASAN_HW_TAGS)
+/*
+ * Global runtime flag for KASAN modes that need runtime control.
+ * Used by ARCH_DEFER_KASAN architectures and HW_TAGS mode.
+ */
 DECLARE_STATIC_KEY_FALSE(kasan_flag_enabled);
 
+/*
+ * Runtime control for shadow memory initialization or HW_TAGS mode.
+ * Uses static key for architectures that need deferred KASAN or HW_TAGS.
+ */
 static __always_inline bool kasan_enabled(void)
 {
 	return static_branch_likely(&kasan_flag_enabled);
 }
 
-static inline bool kasan_hw_tags_enabled(void)
+static inline void kasan_enable(void)
 {
-	return kasan_enabled();
+	static_branch_enable(&kasan_flag_enabled);
 }
-
-#else /* CONFIG_KASAN_HW_TAGS */
-
-static inline bool kasan_enabled(void)
+#else
+/* For architectures that can enable KASAN early, use compile-time check. */
+static __always_inline bool kasan_enabled(void)
 {
 	return IS_ENABLED(CONFIG_KASAN);
 }
 
+static inline void kasan_enable(void) {}
+#endif /* CONFIG_ARCH_DEFER_KASAN || CONFIG_KASAN_HW_TAGS */
+
+#ifdef CONFIG_KASAN_HW_TAGS
+static inline bool kasan_hw_tags_enabled(void)
+{
+	return kasan_enabled();
+}
+#else
 static inline bool kasan_hw_tags_enabled(void)
 {
 	return false;
 }
-
 #endif /* CONFIG_KASAN_HW_TAGS */
 
 #endif /* LINUX_KASAN_ENABLED_H */
diff --git a/include/linux/kasan.h b/include/linux/kasan.h
index 819b6bc8ac08..f335c1d7b61d 100644
--- a/include/linux/kasan.h
+++ b/include/linux/kasan.h
@@ -4,6 +4,7 @@
 
 #include <linux/bug.h>
 #include <linux/kasan-enabled.h>
+#include <linux/kasan-tags.h>
 #include <linux/kernel.h>
 #include <linux/static_key.h>
 #include <linux/types.h>
@@ -28,6 +29,9 @@ typedef unsigned int __bitwise kasan_vmalloc_flags_t;
 #define KASAN_VMALLOC_VM_ALLOC		((__force kasan_vmalloc_flags_t)0x02u)
 #define KASAN_VMALLOC_PROT_NORMAL	((__force kasan_vmalloc_flags_t)0x04u)
 
+#define KASAN_VMALLOC_PAGE_RANGE 0x1 /* Apply exsiting page range */
+#define KASAN_VMALLOC_TLB_FLUSH  0x2 /* TLB flush */
+
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
 #include <linux/pgtable.h>
@@ -54,11 +58,13 @@ extern p4d_t kasan_early_shadow_p4d[MAX_PTRS_PER_P4D];
 int kasan_populate_early_shadow(const void *shadow_start,
 				const void *shadow_end);
 
+#ifndef kasan_mem_to_shadow
 static inline void *kasan_mem_to_shadow(const void *addr)
 {
 	return (void *)((unsigned long)addr >> KASAN_SHADOW_SCALE_SHIFT)
 		+ KASAN_SHADOW_OFFSET;
 }
+#endif
 
 int kasan_add_zero_shadow(void *start, unsigned long size);
 void kasan_remove_zero_shadow(void *start, unsigned long size);
@@ -127,20 +133,39 @@ static __always_inline void kasan_poison_slab(struct slab *slab)
 		__kasan_poison_slab(slab);
 }
 
-void __kasan_unpoison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+void __kasan_unpoison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_unpoison_new_object - Temporarily unpoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * temporarily unpoisons an object from a newly allocated slab without doing
+ * anything else. The object must later be repoisoned by
+ * kasan_poison_new_object().
+ */
+static __always_inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 							void *object)
 {
 	if (kasan_enabled())
-		__kasan_unpoison_object_data(cache, object);
+		__kasan_unpoison_new_object(cache, object);
 }
 
-void __kasan_poison_object_data(struct kmem_cache *cache, void *object);
-static __always_inline void kasan_poison_object_data(struct kmem_cache *cache,
+void __kasan_poison_new_object(struct kmem_cache *cache, void *object);
+/**
+ * kasan_poison_new_object - Repoison a new slab object.
+ * @cache: Cache the object belong to.
+ * @object: Pointer to the object.
+ *
+ * This function is intended for the slab allocator's internal use. It
+ * repoisons an object that was previously unpoisoned by
+ * kasan_unpoison_new_object() without doing anything else.
+ */
+static __always_inline void kasan_poison_new_object(struct kmem_cache *cache,
 							void *object)
 {
 	if (kasan_enabled())
-		__kasan_poison_object_data(cache, object);
+		__kasan_poison_new_object(cache, object);
 }
 
 void * __must_check __kasan_init_slab_obj(struct kmem_cache *cache,
@@ -153,28 +178,69 @@ static __always_inline void * __must_check kasan_init_slab_obj(
 	return (void *)object;
 }
 
-bool __kasan_slab_free(struct kmem_cache *s, void *object,
-			unsigned long ip, bool init);
-static __always_inline bool kasan_slab_free(struct kmem_cache *s,
-						void *object, bool init)
+bool __kasan_slab_pre_free(struct kmem_cache *s, void *object,
+			unsigned long ip);
+/**
+ * kasan_slab_pre_free - Check whether freeing a slab object is safe.
+ * @object: Object to be freed.
+ *
+ * This function checks whether freeing the given object is safe. It may
+ * check for double-free and invalid-free bugs and report them.
+ *
+ * This function is intended only for use by the slab allocator.
+ *
+ * @Return true if freeing the object is unsafe; false otherwise.
+ */
+static __always_inline bool kasan_slab_pre_free(struct kmem_cache *s,
+						void *object)
 {
 	if (kasan_enabled())
-		return __kasan_slab_free(s, object, _RET_IP_, init);
+		return __kasan_slab_pre_free(s, object, _RET_IP_);
 	return false;
 }
 
-void __kasan_kfree_large(void *ptr, unsigned long ip);
-static __always_inline void kasan_kfree_large(void *ptr)
+bool __kasan_slab_free(struct kmem_cache *s, void *object, bool init,
+		       bool still_accessible, bool no_quarantine);
+/**
+ * kasan_slab_free - Poison, initialize, and quarantine a slab object.
+ * @object: Object to be freed.
+ * @init: Whether to initialize the object.
+ * @still_accessible: Whether the object contents are still accessible.
+ *
+ * This function informs that a slab object has been freed and is not
+ * supposed to be accessed anymore, except when @still_accessible is set
+ * (indicating that the object is in a SLAB_TYPESAFE_BY_RCU cache and an RCU
+ * grace period might not have passed yet).
+ *
+ * For KASAN modes that have integrated memory initialization
+ * (kasan_has_integrated_init() == true), this function also initializes
+ * the object's memory. For other modes, the @init argument is ignored.
+ *
+ * This function might also take ownership of the object to quarantine it.
+ * When this happens, KASAN will defer freeing the object to a later
+ * stage and handle it internally until then. The return value indicates
+ * whether KASAN took ownership of the object.
+ *
+ * This function is intended only for use by the slab allocator.
+ *
+ * @Return true if KASAN took ownership of the object; false otherwise.
+ */
+static __always_inline bool kasan_slab_free(struct kmem_cache *s,
+					    void *object, bool init,
+					    bool still_accessible,
+					    bool no_quarantine)
 {
 	if (kasan_enabled())
-		__kasan_kfree_large(ptr, _RET_IP_);
+		return __kasan_slab_free(s, object, init, still_accessible,
+					 no_quarantine);
+	return false;
 }
 
-void __kasan_slab_free_mempool(void *ptr, unsigned long ip);
-static __always_inline void kasan_slab_free_mempool(void *ptr)
+void __kasan_kfree_large(void *ptr, unsigned long ip);
+static __always_inline void kasan_kfree_large(void *ptr)
 {
 	if (kasan_enabled())
-		__kasan_slab_free_mempool(ptr, _RET_IP_);
+		__kasan_kfree_large(ptr, _RET_IP_);
 }
 
 void * __must_check __kasan_slab_alloc(struct kmem_cache *s,
@@ -217,6 +283,113 @@ static __always_inline void * __must_check kasan_krealloc(const void *object,
 	return (void *)object;
 }
 
+bool __kasan_mempool_poison_pages(struct page *page, unsigned int order,
+				  unsigned long ip);
+/**
+ * kasan_mempool_poison_pages - Check and poison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function is similar to kasan_mempool_poison_object() but operates on
+ * page allocations.
+ *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_pages().
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_pages(struct page *page,
+						       unsigned int order)
+{
+	if (kasan_enabled())
+		return __kasan_mempool_poison_pages(page, order, _RET_IP_);
+	return true;
+}
+
+void __kasan_mempool_unpoison_pages(struct page *page, unsigned int order,
+				    unsigned long ip);
+/**
+ * kasan_mempool_unpoison_pages - Unpoison a mempool page allocation.
+ * @page: Pointer to the page allocation.
+ * @order: Order of the allocation.
+ *
+ * This function is intended for kernel subsystems that cache page allocations
+ * to reuse them instead of freeing them back to page_alloc (e.g. mempool).
+ *
+ * This function unpoisons a page allocation that was previously poisoned by
+ * kasan_mempool_poison_pages() without zeroing the allocation's memory. For
+ * the tag-based modes, this function assigns a new tag to the allocation.
+ */
+static __always_inline void kasan_mempool_unpoison_pages(struct page *page,
+							 unsigned int order)
+{
+	if (kasan_enabled())
+		__kasan_mempool_unpoison_pages(page, order, _RET_IP_);
+}
+
+bool __kasan_mempool_poison_object(void *ptr, unsigned long ip);
+/**
+ * kasan_mempool_poison_object - Check and poison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function poisons a slab allocation and saves a free stack trace for it
+ * without initializing the allocation's memory and without putting it into the
+ * quarantine (for the Generic mode).
+ *
+ * This function also performs checks to detect double-free and invalid-free
+ * bugs and reports them. The caller can use the return value of this function
+ * to find out if the allocation is buggy.
+ *
+ * Before the poisoned allocation can be reused, it must be unpoisoned via
+ * kasan_mempool_unpoison_object().
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ *
+ * Return: true if the allocation can be safely reused; false otherwise.
+ */
+static __always_inline bool kasan_mempool_poison_object(void *ptr)
+{
+	if (kasan_enabled())
+		return __kasan_mempool_poison_object(ptr, _RET_IP_);
+	return true;
+}
+
+void __kasan_mempool_unpoison_object(void *ptr, size_t size, unsigned long ip);
+/**
+ * kasan_mempool_unpoison_object - Unpoison a mempool slab allocation.
+ * @ptr: Pointer to the slab allocation.
+ * @size: Size to be unpoisoned.
+ *
+ * This function is intended for kernel subsystems that cache slab allocations
+ * to reuse them instead of freeing them back to the slab allocator (e.g.
+ * mempool).
+ *
+ * This function unpoisons a slab allocation that was previously poisoned via
+ * kasan_mempool_poison_object() and saves an alloc stack trace for it without
+ * initializing the allocation's memory. For the tag-based modes, this function
+ * does not assign a new tag to the allocation and instead restores the
+ * original tags based on the pointer value.
+ *
+ * This function operates on all slab allocations including large kmalloc
+ * allocations (the ones returned by kmalloc_large() or by kmalloc() with the
+ * size > KMALLOC_MAX_SIZE).
+ */
+static __always_inline void kasan_mempool_unpoison_object(void *ptr,
+							  size_t size)
+{
+	if (kasan_enabled())
+		__kasan_mempool_unpoison_object(ptr, size, _RET_IP_);
+}
+
 /*
  * Unlike kasan_check_read/write(), kasan_check_byte() is performed even for
  * the hardware tag-based mode that doesn't rely on compiler instrumentation.
@@ -240,21 +413,28 @@ static inline bool kasan_unpoison_pages(struct page *page, unsigned int order,
 	return false;
 }
 static inline void kasan_poison_slab(struct slab *slab) {}
-static inline void kasan_unpoison_object_data(struct kmem_cache *cache,
+static inline void kasan_unpoison_new_object(struct kmem_cache *cache,
 					void *object) {}
-static inline void kasan_poison_object_data(struct kmem_cache *cache,
+static inline void kasan_poison_new_object(struct kmem_cache *cache,
 					void *object) {}
 static inline void *kasan_init_slab_obj(struct kmem_cache *cache,
 				const void *object)
 {
 	return (void *)object;
 }
-static inline bool kasan_slab_free(struct kmem_cache *s, void *object, bool init)
+
+static inline bool kasan_slab_pre_free(struct kmem_cache *s, void *object)
+{
+	return false;
+}
+
+static inline bool kasan_slab_free(struct kmem_cache *s, void *object,
+				   bool init, bool still_accessible,
+				   bool no_quarantine)
 {
 	return false;
 }
 static inline void kasan_kfree_large(void *ptr) {}
-static inline void kasan_slab_free_mempool(void *ptr) {}
 static inline void *kasan_slab_alloc(struct kmem_cache *s, void *object,
 				   gfp_t flags, bool init)
 {
@@ -274,6 +454,17 @@ static inline void *kasan_krealloc(const void *object, size_t new_size,
 {
 	return (void *)object;
 }
+static inline bool kasan_mempool_poison_pages(struct page *page, unsigned int order)
+{
+	return true;
+}
+static inline void kasan_mempool_unpoison_pages(struct page *page, unsigned int order) {}
+static inline bool kasan_mempool_poison_object(void *ptr)
+{
+	return true;
+}
+static inline void kasan_mempool_unpoison_object(void *ptr, size_t size) {}
+
 static inline bool kasan_check_byte(const void *address)
 {
 	return true;
@@ -283,8 +474,10 @@ static inline bool kasan_check_byte(const void *address)
 
 #if defined(CONFIG_KASAN) && defined(CONFIG_KASAN_STACK)
 void kasan_unpoison_task_stack(struct task_struct *task);
+asmlinkage void kasan_unpoison_task_stack_below(const void *watermark);
 #else
 static inline void kasan_unpoison_task_stack(struct task_struct *task) {}
+static inline void kasan_unpoison_task_stack_below(const void *watermark) {}
 #endif
 
 #ifdef CONFIG_KASAN_GENERIC
@@ -295,14 +488,12 @@ struct kasan_cache {
 };
 
 size_t kasan_metadata_size(struct kmem_cache *cache, bool in_object);
-slab_flags_t kasan_never_merge(void);
 void kasan_cache_create(struct kmem_cache *cache, unsigned int *size,
 			slab_flags_t *flags);
 
 void kasan_cache_shrink(struct kmem_cache *cache);
 void kasan_cache_shutdown(struct kmem_cache *cache);
 void kasan_record_aux_stack(void *ptr);
-void kasan_record_aux_stack_noalloc(void *ptr);
 
 #else /* CONFIG_KASAN_GENERIC */
 
@@ -312,11 +503,6 @@ static inline size_t kasan_metadata_size(struct kmem_cache *cache,
 {
 	return 0;
 }
-/* And thus nothing prevents cache merging. */
-static inline slab_flags_t kasan_never_merge(void)
-{
-	return 0;
-}
 /* And no cache-related metadata initialization is required. */
 static inline void kasan_cache_create(struct kmem_cache *cache,
 				      unsigned int *size,
@@ -325,7 +511,6 @@ static inline void kasan_cache_create(struct kmem_cache *cache,
 static inline void kasan_cache_shrink(struct kmem_cache *cache) {}
 static inline void kasan_cache_shutdown(struct kmem_cache *cache) {}
 static inline void kasan_record_aux_stack(void *ptr) {}
-static inline void kasan_record_aux_stack_noalloc(void *ptr) {}
 
 #endif /* CONFIG_KASAN_GENERIC */
 
@@ -361,6 +546,12 @@ void kasan_report_async(void);
 
 #endif /* CONFIG_KASAN_HW_TAGS */
 
+#ifdef CONFIG_KASAN_GENERIC
+void __init kasan_init_generic(void);
+#else
+static inline void kasan_init_generic(void) { }
+#endif
+
 #ifdef CONFIG_KASAN_SW_TAGS
 void __init kasan_init_sw_tags(void);
 #else
@@ -380,10 +571,27 @@ static inline void kasan_init_hw_tags(void) { }
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 
 void kasan_populate_early_vm_area_shadow(void *start, unsigned long size);
-int kasan_populate_vmalloc(unsigned long addr, unsigned long size);
-void kasan_release_vmalloc(unsigned long start, unsigned long end,
+int __kasan_populate_vmalloc(unsigned long addr, unsigned long size, gfp_t gfp_mask);
+static inline int kasan_populate_vmalloc(unsigned long addr,
+					 unsigned long size, gfp_t gfp_mask)
+{
+	if (kasan_enabled())
+		return __kasan_populate_vmalloc(addr, size, gfp_mask);
+	return 0;
+}
+void __kasan_release_vmalloc(unsigned long start, unsigned long end,
 			   unsigned long free_region_start,
-			   unsigned long free_region_end);
+			   unsigned long free_region_end,
+			   unsigned long flags);
+static inline void kasan_release_vmalloc(unsigned long start, unsigned long end,
+			   unsigned long free_region_start,
+			   unsigned long free_region_end,
+			   unsigned long flags)
+{
+	if (kasan_enabled())
+		return __kasan_release_vmalloc(start, end, free_region_start,
+					 free_region_end, flags);
+}
 
 #else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
@@ -391,14 +599,15 @@ static inline void kasan_populate_early_vm_area_shadow(void *start,
 						       unsigned long size)
 { }
 static inline int kasan_populate_vmalloc(unsigned long start,
-					unsigned long size)
+					unsigned long size, gfp_t gfp_mask)
 {
 	return 0;
 }
 static inline void kasan_release_vmalloc(unsigned long start,
 					 unsigned long end,
 					 unsigned long free_region_start,
-					 unsigned long free_region_end) { }
+					 unsigned long free_region_end,
+					 unsigned long flags) { }
 
 #endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
@@ -426,14 +635,15 @@ static __always_inline void kasan_poison_vmalloc(const void *start,
 static inline void kasan_populate_early_vm_area_shadow(void *start,
 						       unsigned long size) { }
 static inline int kasan_populate_vmalloc(unsigned long start,
-					unsigned long size)
+					unsigned long size, gfp_t gfp_mask)
 {
 	return 0;
 }
 static inline void kasan_release_vmalloc(unsigned long start,
 					 unsigned long end,
 					 unsigned long free_region_start,
-					 unsigned long free_region_end) { }
+					 unsigned long free_region_end,
+					 unsigned long flags) { }
 
 static inline void *kasan_unpoison_vmalloc(const void *start,
 					   unsigned long size,
@@ -464,10 +674,10 @@ static inline void kasan_free_module_shadow(const struct vm_struct *vm) {}
 
 #endif /* (CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS) && !CONFIG_KASAN_VMALLOC */
 
-#ifdef CONFIG_KASAN_INLINE
+#if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 void kasan_non_canonical_hook(unsigned long addr);
-#else /* CONFIG_KASAN_INLINE */
+#else /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 static inline void kasan_non_canonical_hook(unsigned long addr) { }
-#endif /* CONFIG_KASAN_INLINE */
+#endif /* CONFIG_KASAN_GENERIC || CONFIG_KASAN_SW_TAGS */
 
 #endif /* LINUX_KASAN_H */
diff --git a/include/linux/kcore.h b/include/linux/kcore.h
index 86c0f1d18998..9a2fa013c91d 100644
--- a/include/linux/kcore.h
+++ b/include/linux/kcore.h
@@ -20,19 +20,6 @@ struct kcore_list {
 	int type;
 };
 
-struct vmcore {
-	struct list_head list;
-	unsigned long long paddr;
-	unsigned long long size;
-	loff_t offset;
-};
-
-struct vmcoredd_node {
-	struct list_head list;	/* List of dumps */
-	void *buf;		/* Buffer containing device's dump */
-	unsigned int size;	/* Size of the buffer */
-};
-
 #ifdef CONFIG_PROC_KCORE
 void __init kclist_add(struct kcore_list *, void *, size_t, int type);
 
diff --git a/include/linux/kcov.h b/include/linux/kcov.h
index ee04256f28af..0143358874b0 100644
--- a/include/linux/kcov.h
+++ b/include/linux/kcov.h
@@ -21,6 +21,8 @@ enum kcov_mode {
 	KCOV_MODE_TRACE_PC = 2,
 	/* Collecting comparison operands mode. */
 	KCOV_MODE_TRACE_CMP = 3,
+	/* The process owns a KCOV remote reference. */
+	KCOV_MODE_REMOTE = 4,
 };
 
 #define KCOV_IN_CTXSW	(1 << 30)
@@ -62,16 +64,33 @@ static inline void kcov_remote_start_usb(u64 id)
 
 static inline void kcov_remote_start_usb_softirq(u64 id)
 {
-	if (in_serving_softirq())
+	if (in_serving_softirq() && !in_hardirq())
 		kcov_remote_start_usb(id);
 }
 
 static inline void kcov_remote_stop_softirq(void)
 {
-	if (in_serving_softirq())
+	if (in_serving_softirq() && !in_hardirq())
 		kcov_remote_stop();
 }
 
+#ifdef CONFIG_64BIT
+typedef unsigned long kcov_u64;
+#else
+typedef unsigned long long kcov_u64;
+#endif
+
+void __sanitizer_cov_trace_pc(void);
+void __sanitizer_cov_trace_cmp1(u8 arg1, u8 arg2);
+void __sanitizer_cov_trace_cmp2(u16 arg1, u16 arg2);
+void __sanitizer_cov_trace_cmp4(u32 arg1, u32 arg2);
+void __sanitizer_cov_trace_cmp8(kcov_u64 arg1, kcov_u64 arg2);
+void __sanitizer_cov_trace_const_cmp1(u8 arg1, u8 arg2);
+void __sanitizer_cov_trace_const_cmp2(u16 arg1, u16 arg2);
+void __sanitizer_cov_trace_const_cmp4(u32 arg1, u32 arg2);
+void __sanitizer_cov_trace_const_cmp8(kcov_u64 arg1, kcov_u64 arg2);
+void __sanitizer_cov_trace_switch(kcov_u64 val, void *cases);
+
 #else
 
 static inline void kcov_task_init(struct task_struct *t) {}
diff --git a/include/linux/kdb.h b/include/linux/kdb.h
index 07dfb6a20a1c..741c58e86431 100644
--- a/include/linux/kdb.h
+++ b/include/linux/kdb.h
@@ -14,6 +14,7 @@
  */
 
 #include <linux/list.h>
+#include <linux/smp.h>
 
 /* Shifted versions of the command enable bits are be used if the command
  * has no arguments (see kdb_check_flags). This allows commands, such as
@@ -104,7 +105,7 @@ extern int kdb_initial_cpu;
 #define KDB_NOENVVALUE	(-6)
 #define KDB_NOTIMP	(-7)
 #define KDB_ENVFULL	(-8)
-#define KDB_ENVBUFFULL	(-9)
+#define KDB_KMALLOCFAILED	(-9)
 #define KDB_TOOMANYBPT	(-10)
 #define KDB_TOOMANYDBREGS (-11)
 #define KDB_DUPBPT	(-12)
@@ -140,9 +141,6 @@ extern const char *kdb_diemsg;
 
 extern unsigned int kdb_flags;	/* Global flags, see kdb_state for per cpu state */
 
-extern void kdb_save_flags(void);
-extern void kdb_restore_flags(void);
-
 #define KDB_FLAG(flag)		(kdb_flags & KDB_FLAG_##flag)
 #define KDB_FLAG_SET(flag)	((void)(kdb_flags |= KDB_FLAG_##flag))
 #define KDB_FLAG_CLEAR(flag)	((void)(kdb_flags &= ~KDB_FLAG_##flag))
@@ -196,6 +194,8 @@ int kdb_process_cpu(const struct task_struct *p)
 	return cpu;
 }
 
+extern void kdb_send_sig(struct task_struct *p, int sig);
+
 #ifdef CONFIG_KALLSYMS
 extern const char *kdb_walk_kallsyms(loff_t *pos);
 #else /* ! CONFIG_KALLSYMS */
@@ -208,11 +208,26 @@ static inline const char *kdb_walk_kallsyms(loff_t *pos)
 /* Dynamic kdb shell command registration */
 extern int kdb_register(kdbtab_t *cmd);
 extern void kdb_unregister(kdbtab_t *cmd);
+
+/* Return true when KDB as locked for printing a message on this CPU. */
+static inline
+bool kdb_printf_on_this_cpu(void)
+{
+	/*
+	 * We can use raw_smp_processor_id() here because the task could
+	 * not get migrated when KDB has locked for printing on this CPU.
+	 */
+	return unlikely(READ_ONCE(kdb_printf_cpu) == raw_smp_processor_id());
+}
+
 #else /* ! CONFIG_KGDB_KDB */
 static inline __printf(1, 2) int kdb_printf(const char *fmt, ...) { return 0; }
 static inline void kdb_init(int level) {}
 static inline int kdb_register(kdbtab_t *cmd) { return 0; }
 static inline void kdb_unregister(kdbtab_t *cmd) {}
+
+static inline bool kdb_printf_on_this_cpu(void) { return false; }
+
 #endif	/* CONFIG_KGDB_KDB */
 enum {
 	KDB_NOT_INITIALIZED,
diff --git a/include/linux/kernel-page-flags.h b/include/linux/kernel-page-flags.h
index 859f4b0c1b2b..196778a087c4 100644
--- a/include/linux/kernel-page-flags.h
+++ b/include/linux/kernel-page-flags.h
@@ -10,12 +10,11 @@
  */
 #define KPF_RESERVED		32
 #define KPF_MLOCKED		33
-#define KPF_MAPPEDTODISK	34
+#define KPF_OWNER_2		34
 #define KPF_PRIVATE		35
 #define KPF_PRIVATE_2		36
 #define KPF_OWNER_PRIVATE	37
 #define KPF_ARCH		38
-#define KPF_UNCACHED		39
 #define KPF_SOFTDIRTY		40
 #define KPF_ARCH_2		41
 #define KPF_ARCH_3		42
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 0d91e0af0125..5b46924fdff5 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -13,6 +13,7 @@
 
 #include <linux/stdarg.h>
 #include <linux/align.h>
+#include <linux/array_size.h>
 #include <linux/limits.h>
 #include <linux/linkage.h>
 #include <linux/stddef.h>
@@ -29,69 +30,18 @@
 #include <linux/panic.h>
 #include <linux/printk.h>
 #include <linux/build_bug.h>
+#include <linux/sprintf.h>
 #include <linux/static_call_types.h>
 #include <linux/instruction_pointer.h>
+#include <linux/util_macros.h>
+#include <linux/wordpart.h>
+
 #include <asm/byteorder.h>
 
 #include <uapi/linux/kernel.h>
 
 #define STACK_MAGIC	0xdeadbeef
 
-/**
- * REPEAT_BYTE - repeat the value @x multiple times as an unsigned long value
- * @x: value to repeat
- *
- * NOTE: @x is not checked for > 0xff; larger values produce odd results.
- */
-#define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
-
-/* generic data direction definitions */
-#define READ			0
-#define WRITE			1
-
-/**
- * ARRAY_SIZE - get the number of elements in array @arr
- * @arr: array to be sized
- */
-#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]) + __must_be_array(arr))
-
-#define PTR_IF(cond, ptr)	((cond) ? (ptr) : NULL)
-
-#define u64_to_user_ptr(x) (		\
-{					\
-	typecheck(u64, (x));		\
-	(void __user *)(uintptr_t)(x);	\
-}					\
-)
-
-/**
- * upper_32_bits - return bits 32-63 of a number
- * @n: the number we're accessing
- *
- * A basic shift-right of a 64- or 32-bit quantity.  Use this to suppress
- * the "right shift count >= width of type" warning when that quantity is
- * 32-bits.
- */
-#define upper_32_bits(n) ((u32)(((n) >> 16) >> 16))
-
-/**
- * lower_32_bits - return bits 0-31 of a number
- * @n: the number we're accessing
- */
-#define lower_32_bits(n) ((u32)((n) & 0xffffffff))
-
-/**
- * upper_16_bits - return bits 16-31 of a number
- * @n: the number we're accessing
- */
-#define upper_16_bits(n) ((u16)((n) >> 16))
-
-/**
- * lower_16_bits - return bits 0-15 of a number
- * @n: the number we're accessing
- */
-#define lower_16_bits(n) ((u16)((n) & 0xffff))
-
 struct completion;
 struct user;
 
@@ -203,41 +153,6 @@ static inline void might_fault(void) { }
 
 void do_exit(long error_code) __noreturn;
 
-extern int num_to_str(char *buf, int size,
-		      unsigned long long num, unsigned int width);
-
-/* lib/printf utilities */
-
-extern __printf(2, 3) int sprintf(char *buf, const char * fmt, ...);
-extern __printf(2, 0) int vsprintf(char *buf, const char *, va_list);
-extern __printf(3, 4)
-int snprintf(char *buf, size_t size, const char *fmt, ...);
-extern __printf(3, 0)
-int vsnprintf(char *buf, size_t size, const char *fmt, va_list args);
-extern __printf(3, 4)
-int scnprintf(char *buf, size_t size, const char *fmt, ...);
-extern __printf(3, 0)
-int vscnprintf(char *buf, size_t size, const char *fmt, va_list args);
-extern __printf(2, 3) __malloc
-char *kasprintf(gfp_t gfp, const char *fmt, ...);
-extern __printf(2, 0) __malloc
-char *kvasprintf(gfp_t gfp, const char *fmt, va_list args);
-extern __printf(2, 0)
-const char *kvasprintf_const(gfp_t gfp, const char *fmt, va_list args);
-
-extern __scanf(2, 3)
-int sscanf(const char *, const char *, ...);
-extern __scanf(2, 0)
-int vsscanf(const char *, const char *, va_list);
-
-extern int no_hash_pointers_enable(char *str);
-
-extern int get_option(char **str, int *pint);
-extern char *get_options(const char *str, int nints, int *ints);
-extern unsigned long long memparse(const char *ptr, char **retptr);
-extern bool parse_option_str(const char *str, const char *option);
-extern char *next_arg(char *args, char **param, char **val);
-
 extern int core_kernel_text(unsigned long addr);
 extern int __kernel_text_address(unsigned long addr);
 extern int kernel_text_address(unsigned long addr);
@@ -249,11 +164,23 @@ extern int root_mountflags;
 
 extern bool early_boot_irqs_disabled;
 
-/*
- * Values used for system_state. Ordering of the states must not be changed
+/**
+ * enum system_states - Values used for system_state.
+ *
+ * @SYSTEM_BOOTING:	%0, no init needed
+ * @SYSTEM_SCHEDULING: system is ready for scheduling; OK to use RCU
+ * @SYSTEM_FREEING_INITMEM: system is freeing all of initmem; almost running
+ * @SYSTEM_RUNNING:	system is up and running
+ * @SYSTEM_HALT:	system entered clean system halt state
+ * @SYSTEM_POWER_OFF:	system entered shutdown/clean power off state
+ * @SYSTEM_RESTART:	system entered emergency power off or normal restart
+ * @SYSTEM_SUSPEND:	system entered suspend or hibernate state
+ *
+ * Note:
+ * Ordering of the states must not be changed
  * as code checks for <, <=, >, >= STATE.
  */
-extern enum system_states {
+enum system_states {
 	SYSTEM_BOOTING,
 	SYSTEM_SCHEDULING,
 	SYSTEM_FREEING_INITMEM,
@@ -262,7 +189,8 @@ extern enum system_states {
 	SYSTEM_POWER_OFF,
 	SYSTEM_RESTART,
 	SYSTEM_SUSPEND,
-} system_state;
+};
+extern enum system_states system_state;
 
 /*
  * General tracing related utility functions - trace_printk(),
@@ -288,6 +216,7 @@ enum ftrace_dump_mode {
 	DUMP_NONE,
 	DUMP_ALL,
 	DUMP_ORIG,
+	DUMP_PARAM,
 };
 
 #ifdef CONFIG_TRACING
@@ -457,16 +386,9 @@ ftrace_vprintk(const char *fmt, va_list ap)
 static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #endif /* CONFIG_TRACING */
 
-/* This counts to 12. Any more, it will return 13th argument. */
-#define __COUNT_ARGS(_0, _1, _2, _3, _4, _5, _6, _7, _8, _9, _10, _11, _12, _n, X...) _n
-#define COUNT_ARGS(X...) __COUNT_ARGS(, ##X, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0)
-
-#define __CONCAT(a, b) a ## b
-#define CONCATENATE(a, b) __CONCAT(a, b)
-
-/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
-# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
+/* Rebuild everything on CONFIG_DYNAMIC_FTRACE */
+#ifdef CONFIG_DYNAMIC_FTRACE
+# define REBUILD_DUE_TO_DYNAMIC_FTRACE
 #endif
 
 /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */
diff --git a/include/linux/kernel_read_file.h b/include/linux/kernel_read_file.h
index 90451e2e12bd..d613a7b4dd35 100644
--- a/include/linux/kernel_read_file.h
+++ b/include/linux/kernel_read_file.h
@@ -14,6 +14,7 @@
 	id(KEXEC_INITRAMFS, kexec-initramfs)	\
 	id(POLICY, security-policy)		\
 	id(X509_CERTIFICATE, x509-certificate)	\
+	id(MODULE_COMPRESSED, kernel-module-compressed) \
 	id(MAX_ID, )
 
 #define __fid_enumify(ENUM, dummy) READING_ ## ENUM,
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 9935f7ecbfb9..b97ce2df376f 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -5,7 +5,6 @@
 #include <linux/smp.h>
 #include <linux/threads.h>
 #include <linux/percpu.h>
-#include <linux/cpumask.h>
 #include <linux/interrupt.h>
 #include <linux/sched.h>
 #include <linux/vtime.h>
@@ -79,6 +78,14 @@ static inline unsigned int kstat_cpu_softirqs_sum(int cpu)
 	return sum;
 }
 
+#ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT
+extern void kstat_snapshot_irqs(void);
+extern unsigned int kstat_get_irq_since_snapshot(unsigned int irq);
+#else
+static inline void kstat_snapshot_irqs(void) { }
+static inline unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { return 0; }
+#endif
+
 /*
  * Number of interrupts per specific IRQ source, since bootup
  */
diff --git a/include/linux/kernfs.h b/include/linux/kernfs.h
index 73f5c120def8..b5a5f32fdfd1 100644
--- a/include/linux/kernfs.h
+++ b/include/linux/kernfs.h
@@ -147,6 +147,11 @@ enum kernfs_root_flag {
 	 * Support user xattrs to be written to nodes rooted at this root.
 	 */
 	KERNFS_ROOT_SUPPORT_USER_XATTR		= 0x0008,
+
+	/*
+	 * Renames must not change the parent node.
+	 */
+	KERNFS_ROOT_INVARIANT_PARENT		= 0x0010,
 };
 
 /* type-specific structures for kernfs_node union members */
@@ -199,30 +204,32 @@ struct kernfs_node {
 	 * never moved to a different parent, it is safe to access the
 	 * parent directly.
 	 */
-	struct kernfs_node	*parent;
-	const char		*name;
+	struct kernfs_node	__rcu *__parent;
+	const char		__rcu *name;
 
 	struct rb_node		rb;
 
 	const void		*ns;	/* namespace tag */
 	unsigned int		hash;	/* ns + name hash */
+	unsigned short		flags;
+	umode_t			mode;
+
 	union {
 		struct kernfs_elem_dir		dir;
 		struct kernfs_elem_symlink	symlink;
 		struct kernfs_elem_attr		attr;
 	};
 
-	void			*priv;
-
 	/*
 	 * 64bit unique ID.  On 64bit ino setups, id is the ino.  On 32bit,
 	 * the low 32bits are ino and upper generation.
 	 */
 	u64			id;
 
-	unsigned short		flags;
-	umode_t			mode;
+	void			*priv;
 	struct kernfs_iattrs	*iattr;
+
+	struct rcu_head		rcu;
 };
 
 /*
@@ -316,6 +323,7 @@ struct kernfs_ops {
 			 struct poll_table_struct *pt);
 
 	int (*mmap)(struct kernfs_open_file *of, struct vm_area_struct *vma);
+	loff_t (*llseek)(struct kernfs_open_file *of, loff_t offset, int whence);
 };
 
 /*
@@ -392,7 +400,7 @@ static inline bool kernfs_ns_enabled(struct kernfs_node *kn)
 }
 
 int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen);
-int kernfs_path_from_node(struct kernfs_node *root_kn, struct kernfs_node *kn,
+int kernfs_path_from_node(struct kernfs_node *kn_to, struct kernfs_node *kn_from,
 			  char *buf, size_t buflen);
 void pr_cont_kernfs_name(struct kernfs_node *kn);
 void pr_cont_kernfs_path(struct kernfs_node *kn);
@@ -413,6 +421,7 @@ struct dentry *kernfs_node_dentry(struct kernfs_node *kn,
 struct kernfs_root *kernfs_create_root(struct kernfs_syscall_ops *scops,
 				       unsigned int flags, void *priv);
 void kernfs_destroy_root(struct kernfs_root *root);
+unsigned int kernfs_root_flags(struct kernfs_node *kn);
 
 struct kernfs_node *kernfs_create_dir_ns(struct kernfs_node *parent,
 					 const char *name, umode_t mode,
@@ -511,6 +520,8 @@ kernfs_create_root(struct kernfs_syscall_ops *scops, unsigned int flags,
 { return ERR_PTR(-ENOSYS); }
 
 static inline void kernfs_destroy_root(struct kernfs_root *root) { }
+static inline unsigned int kernfs_root_flags(struct kernfs_node *kn)
+{ return 0; }
 
 static inline struct kernfs_node *
 kernfs_create_dir_ns(struct kernfs_node *parent, const char *name,
@@ -550,6 +561,10 @@ static inline int kernfs_setattr(struct kernfs_node *kn,
 				 const struct iattr *iattr)
 { return -ENOSYS; }
 
+static inline __poll_t kernfs_generic_poll(struct kernfs_open_file *of,
+					   struct poll_table_struct *pt)
+{ return -ENOSYS; }
+
 static inline void kernfs_notify(struct kernfs_node *kn) { }
 
 static inline int kernfs_xattr_get(struct kernfs_node *kn, const char *name,
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 22b5cd24f581..ff7e231b0485 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -15,25 +15,28 @@
 
 #if !defined(__ASSEMBLY__)
 
-#include <linux/crash_core.h>
+#include <linux/vmcore_info.h>
+#include <linux/crash_reserve.h>
 #include <asm/io.h>
 #include <linux/range.h>
 
 #include <uapi/linux/kexec.h>
 #include <linux/verification.h>
 
-/* Location of a reserved region to hold the crash kernel.
- */
-extern struct resource crashk_res;
-extern struct resource crashk_low_res;
 extern note_buf_t __percpu *crash_notes;
 
+#ifdef CONFIG_CRASH_DUMP
+#include <linux/prandom.h>
+#endif
+
 #ifdef CONFIG_KEXEC_CORE
 #include <linux/list.h>
 #include <linux/compat.h>
 #include <linux/ioport.h>
 #include <linux/module.h>
+#include <linux/highmem.h>
 #include <asm/kexec.h>
+#include <linux/crash_core.h>
 
 /* Verify architecture specific macros are defined */
 
@@ -69,8 +72,6 @@ extern note_buf_t __percpu *crash_notes;
 #define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE
 #endif
 
-#define KEXEC_CORE_NOTE_NAME	CRASH_CORE_NOTE_NAME
-
 /*
  * This structure is used to hold the arguments that are used when loading
  * kernel binaries.
@@ -78,6 +79,12 @@ extern note_buf_t __percpu *crash_notes;
 
 typedef unsigned long kimage_entry_t;
 
+/*
+ * This is a copy of the UAPI struct kexec_segment and must be identical
+ * to it because it gets copied straight from user space into kernel
+ * memory. Do not modify this structure unless you change the way segments
+ * get ingested from user space.
+ */
 struct kexec_segment {
 	/*
 	 * This pointer can point to user memory if kexec_load() system
@@ -171,7 +178,9 @@ int kexec_image_post_load_cleanup_default(struct kimage *image);
  * @buf_align:	Minimum alignment needed.
  * @buf_min:	The buffer can't be placed below this address.
  * @buf_max:	The buffer can't be placed above this address.
+ * @cma:	CMA page if the buffer is backed by CMA.
  * @top_down:	Allocate from top of memory.
+ * @random:	Place the buffer at a random position.
  */
 struct kexec_buf {
 	struct kimage *image;
@@ -182,9 +191,35 @@ struct kexec_buf {
 	unsigned long buf_align;
 	unsigned long buf_min;
 	unsigned long buf_max;
+	struct page *cma;
 	bool top_down;
+#ifdef CONFIG_CRASH_DUMP
+	bool random;
+#endif
 };
 
+
+#ifdef CONFIG_CRASH_DUMP
+static inline void kexec_random_range_start(unsigned long start,
+					    unsigned long end,
+					    struct kexec_buf *kbuf,
+					    unsigned long *temp_start)
+{
+	unsigned short i;
+
+	if (kbuf->random) {
+		get_random_bytes(&i, sizeof(unsigned short));
+		*temp_start = start + (end - start) / USHRT_MAX * i;
+	}
+}
+#else
+static inline void kexec_random_range_start(unsigned long start,
+					    unsigned long end,
+					    struct kexec_buf *kbuf,
+					    unsigned long *temp_start)
+{}
+#endif
+
 int kexec_load_purgatory(struct kimage *image, struct kexec_buf *kbuf);
 int kexec_purgatory_get_set_symbol(struct kimage *image, const char *name,
 				   void *buf, unsigned int size,
@@ -206,6 +241,15 @@ static inline int arch_kimage_file_post_load_cleanup(struct kimage *image)
 }
 #endif
 
+#ifndef arch_check_excluded_range
+static inline int arch_check_excluded_range(struct kimage *image,
+					    unsigned long start,
+					    unsigned long end)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_KEXEC_SIG
 #ifdef CONFIG_SIGNED_PE_FILE_VERIFICATION
 int kexec_kernel_verify_pe_sig(const char *kernel, unsigned long kernel_len);
@@ -230,21 +274,6 @@ static inline int arch_kexec_locate_mem_hole(struct kexec_buf *kbuf)
 }
 #endif
 
-/* Alignment required for elf header segment */
-#define ELF_CORE_HEADER_ALIGN   4096
-
-struct crash_mem {
-	unsigned int max_nr_ranges;
-	unsigned int nr_ranges;
-	struct range ranges[];
-};
-
-extern int crash_exclude_mem_range(struct crash_mem *mem,
-				   unsigned long long mstart,
-				   unsigned long long mend);
-extern int crash_prepare_elf64_headers(struct crash_mem *mem, int need_kernel_map,
-				       void **addr, unsigned long *sz);
-
 #ifndef arch_kexec_apply_relocations_add
 /*
  * arch_kexec_apply_relocations_add - apply relocations of type RELA
@@ -319,6 +348,7 @@ struct kimage {
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
+	struct page *segment_cma[KEXEC_SEGMENT_MAX];
 
 	struct list_head control_pages;
 	struct list_head dest_pages;
@@ -334,6 +364,13 @@ struct kimage {
 	unsigned int preserve_context : 1;
 	/* If set, we are using file mode kexec syscall */
 	unsigned int file_mode:1;
+#ifdef CONFIG_CRASH_HOTPLUG
+	/* If set, it is safe to update kexec segments that are
+	 * excluded from SHA calculation.
+	 */
+	unsigned int hotplug_support:1;
+#endif
+	unsigned int no_cma:1;
 
 #ifdef ARCH_HAS_KIMAGE_ARCH
 	struct kimage_arch arch;
@@ -358,6 +395,15 @@ struct kimage {
 
 	/* Information for loading purgatory */
 	struct purgatory_info purgatory_info;
+
+	/* Force carrying over the DTB from the current boot */
+	bool force_dtb;
+#endif
+
+#ifdef CONFIG_CRASH_HOTPLUG
+	int hp_action;
+	int elfcorehdr_index;
+	bool elfcorehdr_updated;
 #endif
 
 #ifdef CONFIG_IMA_KEXEC
@@ -366,12 +412,24 @@ struct kimage {
 
 	phys_addr_t ima_buffer_addr;
 	size_t ima_buffer_size;
+
+	unsigned long ima_segment_index;
+	bool is_ima_segment_index_set;
 #endif
 
+	struct {
+		struct kexec_segment *scratch;
+		phys_addr_t fdt;
+	} kho;
+
 	/* Core ELF header buffer */
 	void *elf_headers;
 	unsigned long elf_headers_sz;
 	unsigned long elf_load_addr;
+
+	/* dm crypt keys buffer */
+	unsigned long dm_crypt_keys_addr;
+	unsigned long dm_crypt_keys_sz;
 };
 
 /* kexec interface functions */
@@ -386,13 +444,6 @@ extern struct page *kimage_alloc_control_pages(struct kimage *image,
 static inline int machine_kexec_post_load(struct kimage *image) { return 0; }
 #endif
 
-extern void __crash_kexec(struct pt_regs *);
-extern void crash_kexec(struct pt_regs *);
-int kexec_should_crash(struct task_struct *);
-int kexec_crash_loaded(void);
-void crash_save_cpu(struct pt_regs *regs, int cpu);
-extern int kimage_crash_copy_vmcoreinfo(struct kimage *image);
-
 extern struct kimage *kexec_image;
 extern struct kimage *kexec_crash_image;
 
@@ -404,36 +455,20 @@ bool kexec_load_permitted(int kexec_image_type);
 
 /* List of defined/legal kexec flags */
 #ifndef CONFIG_KEXEC_JUMP
-#define KEXEC_FLAGS    KEXEC_ON_CRASH
+#define KEXEC_FLAGS    (KEXEC_ON_CRASH | KEXEC_UPDATE_ELFCOREHDR | KEXEC_CRASH_HOTPLUG_SUPPORT)
 #else
-#define KEXEC_FLAGS    (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT)
+#define KEXEC_FLAGS    (KEXEC_ON_CRASH | KEXEC_PRESERVE_CONTEXT | KEXEC_UPDATE_ELFCOREHDR | \
+			KEXEC_CRASH_HOTPLUG_SUPPORT)
 #endif
 
 /* List of defined/legal kexec file flags */
 #define KEXEC_FILE_FLAGS	(KEXEC_FILE_UNLOAD | KEXEC_FILE_ON_CRASH | \
-				 KEXEC_FILE_NO_INITRAMFS)
+				 KEXEC_FILE_NO_INITRAMFS | KEXEC_FILE_DEBUG | \
+				 KEXEC_FILE_NO_CMA | KEXEC_FILE_FORCE_DTB)
 
 /* flag to track if kexec reboot is in progress */
 extern bool kexec_in_progress;
 
-int crash_shrink_memory(unsigned long new_size);
-ssize_t crash_get_memory_size(void);
-
-#ifndef arch_kexec_protect_crashkres
-/*
- * Protection mechanism for crashkernel reserved memory after
- * the kdump kernel is loaded.
- *
- * Provide an empty default implementation here -- architecture
- * code may override this
- */
-static inline void arch_kexec_protect_crashkres(void) { }
-#endif
-
-#ifndef arch_kexec_unprotect_crashkres
-static inline void arch_kexec_unprotect_crashkres(void) { }
-#endif
-
 #ifndef page_to_boot_pfn
 static inline unsigned long page_to_boot_pfn(struct page *page)
 {
@@ -490,13 +525,24 @@ static inline int arch_kexec_post_alloc_pages(void *vaddr, unsigned int pages, g
 static inline void arch_kexec_pre_free_pages(void *vaddr, unsigned int pages) { }
 #endif
 
+extern bool kexec_file_dbg_print;
+
+#define kexec_dprintk(fmt, arg...) \
+        do { if (kexec_file_dbg_print) pr_info(fmt, ##arg); } while (0)
+
+extern void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size);
+extern void kimage_unmap_segment(void *buffer);
 #else /* !CONFIG_KEXEC_CORE */
 struct pt_regs;
 struct task_struct;
+struct kimage;
 static inline void __crash_kexec(struct pt_regs *regs) { }
 static inline void crash_kexec(struct pt_regs *regs) { }
 static inline int kexec_should_crash(struct task_struct *p) { return 0; }
 static inline int kexec_crash_loaded(void) { return 0; }
+static inline void *kimage_map_segment(struct kimage *image, unsigned long addr, unsigned long size)
+{ return NULL; }
+static inline void kimage_unmap_segment(void *buffer) { }
 #define kexec_in_progress false
 #endif /* CONFIG_KEXEC_CORE */
 
diff --git a/include/linux/kexec_handover.h b/include/linux/kexec_handover.h
new file mode 100644
index 000000000000..5f7b9de97e8d
--- /dev/null
+++ b/include/linux/kexec_handover.h
@@ -0,0 +1,143 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef LINUX_KEXEC_HANDOVER_H
+#define LINUX_KEXEC_HANDOVER_H
+
+#include <linux/err.h>
+#include <linux/errno.h>
+#include <linux/types.h>
+
+struct kho_scratch {
+	phys_addr_t addr;
+	phys_addr_t size;
+};
+
+struct folio;
+struct page;
+
+#define DECLARE_KHOSER_PTR(name, type) \
+	union {                        \
+		phys_addr_t phys;      \
+		type ptr;              \
+	} name
+#define KHOSER_STORE_PTR(dest, val)               \
+	({                                        \
+		typeof(val) v = val;              \
+		typecheck(typeof((dest).ptr), v); \
+		(dest).phys = virt_to_phys(v);    \
+	})
+#define KHOSER_LOAD_PTR(src)                                                 \
+	({                                                                   \
+		typeof(src) s = src;                                         \
+		(typeof((s).ptr))((s).phys ? phys_to_virt((s).phys) : NULL); \
+	})
+
+struct kho_vmalloc_chunk;
+struct kho_vmalloc {
+	DECLARE_KHOSER_PTR(first, struct kho_vmalloc_chunk *);
+	unsigned int total_pages;
+	unsigned short flags;
+	unsigned short order;
+};
+
+#ifdef CONFIG_KEXEC_HANDOVER
+bool kho_is_enabled(void);
+bool is_kho_boot(void);
+
+int kho_preserve_folio(struct folio *folio);
+void kho_unpreserve_folio(struct folio *folio);
+int kho_preserve_pages(struct page *page, unsigned int nr_pages);
+void kho_unpreserve_pages(struct page *page, unsigned int nr_pages);
+int kho_preserve_vmalloc(void *ptr, struct kho_vmalloc *preservation);
+void kho_unpreserve_vmalloc(struct kho_vmalloc *preservation);
+void *kho_alloc_preserve(size_t size);
+void kho_unpreserve_free(void *mem);
+void kho_restore_free(void *mem);
+struct folio *kho_restore_folio(phys_addr_t phys);
+struct page *kho_restore_pages(phys_addr_t phys, unsigned int nr_pages);
+void *kho_restore_vmalloc(const struct kho_vmalloc *preservation);
+int kho_add_subtree(const char *name, void *fdt);
+void kho_remove_subtree(void *fdt);
+int kho_retrieve_subtree(const char *name, phys_addr_t *phys);
+
+void kho_memory_init(void);
+
+void kho_populate(phys_addr_t fdt_phys, u64 fdt_len, phys_addr_t scratch_phys,
+		  u64 scratch_len);
+#else
+static inline bool kho_is_enabled(void)
+{
+	return false;
+}
+
+static inline bool is_kho_boot(void)
+{
+	return false;
+}
+
+static inline int kho_preserve_folio(struct folio *folio)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void kho_unpreserve_folio(struct folio *folio) { }
+
+static inline int kho_preserve_pages(struct page *page, unsigned int nr_pages)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void kho_unpreserve_pages(struct page *page, unsigned int nr_pages) { }
+
+static inline int kho_preserve_vmalloc(void *ptr,
+				       struct kho_vmalloc *preservation)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void kho_unpreserve_vmalloc(struct kho_vmalloc *preservation) { }
+
+static inline void *kho_alloc_preserve(size_t size)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void kho_unpreserve_free(void *mem) { }
+static inline void kho_restore_free(void *mem) { }
+
+static inline struct folio *kho_restore_folio(phys_addr_t phys)
+{
+	return NULL;
+}
+
+static inline struct page *kho_restore_pages(phys_addr_t phys,
+					     unsigned int nr_pages)
+{
+	return NULL;
+}
+
+static inline void *kho_restore_vmalloc(const struct kho_vmalloc *preservation)
+{
+	return NULL;
+}
+
+static inline int kho_add_subtree(const char *name, void *fdt)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void kho_remove_subtree(void *fdt) { }
+
+static inline int kho_retrieve_subtree(const char *name, phys_addr_t *phys)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void kho_memory_init(void) { }
+
+static inline void kho_populate(phys_addr_t fdt_phys, u64 fdt_len,
+				phys_addr_t scratch_phys, u64 scratch_len)
+{
+}
+#endif /* CONFIG_KEXEC_HANDOVER */
+
+#endif /* LINUX_KEXEC_HANDOVER_H */
diff --git a/include/linux/key-type.h b/include/linux/key-type.h
index 7d985a1dfe4a..bb97bd3e5af4 100644
--- a/include/linux/key-type.h
+++ b/include/linux/key-type.h
@@ -73,6 +73,7 @@ struct key_type {
 
 	unsigned int flags;
 #define KEY_TYPE_NET_DOMAIN	0x00000001 /* Keys of this type have a net namespace domain */
+#define KEY_TYPE_INSTANT_REAP	0x00000002 /* Keys of this type don't have a delay after expiring */
 
 	/* vet a description */
 	int (*vet_description)(const char *description);
@@ -106,11 +107,14 @@ struct key_type {
 	 */
 	int (*match_preparse)(struct key_match_data *match_data);
 
-	/* Free preparsed match data (optional).  This should be supplied it
-	 * ->match_preparse() is supplied. */
+	/*
+	 * Free preparsed match data (optional).  This should be supplied if
+	 * ->match_preparse() is supplied.
+	 */
 	void (*match_free)(struct key_match_data *match_data);
 
-	/* clear some of the data from a key on revokation (optional)
+	/*
+	 * Clear some of the data from a key on revocation (optional).
 	 * - the key's semaphore will be write-locked by the caller
 	 */
 	void (*revoke)(struct key *key);
diff --git a/include/linux/key.h b/include/linux/key.h
index 8dc7f7c3088b..81b8f05c6898 100644
--- a/include/linux/key.h
+++ b/include/linux/key.h
@@ -236,6 +236,7 @@ struct key {
 #define KEY_FLAG_ROOT_CAN_INVAL	7	/* set if key can be invalidated by root without permission */
 #define KEY_FLAG_KEEP		8	/* set if key should not be removed */
 #define KEY_FLAG_UID_KEYRING	9	/* set if key is a user or user session keyring */
+#define KEY_FLAG_USER_ALIVE	10	/* set if final put has not happened on key yet */
 
 	/* the key type and key description string
 	 * - the desc is used to match a key against search criteria
@@ -436,9 +437,6 @@ extern key_ref_t keyring_search(key_ref_t keyring,
 				const char *description,
 				bool recurse);
 
-extern int keyring_add_key(struct key *keyring,
-			   struct key *key);
-
 extern int keyring_restrict(key_ref_t keyring, const char *type,
 			    const char *restriction);
 
@@ -490,9 +488,6 @@ do {									\
 	rcu_assign_pointer((KEY)->payload.rcu_data0, (PAYLOAD));	\
 } while (0)
 
-#ifdef CONFIG_SYSCTL
-extern struct ctl_table key_sysctls[];
-#endif
 /*
  * the userspace interface
  */
@@ -518,6 +513,7 @@ extern void key_init(void);
 #define key_init()			do { } while(0)
 #define key_free_user_ns(ns)		do { } while(0)
 #define key_remove_domain(d)		do { } while(0)
+#define key_lookup(k)			NULL
 
 #endif /* CONFIG_KEYS */
 #endif /* __KERNEL__ */
diff --git a/include/linux/kfence.h b/include/linux/kfence.h
index 726857a4b680..0ad1ddbb8b99 100644
--- a/include/linux/kfence.h
+++ b/include/linux/kfence.h
@@ -59,15 +59,16 @@ static __always_inline bool is_kfence_address(const void *addr)
 }
 
 /**
- * kfence_alloc_pool() - allocate the KFENCE pool via memblock
+ * kfence_alloc_pool_and_metadata() - allocate the KFENCE pool and KFENCE
+ * metadata via memblock
  */
-void __init kfence_alloc_pool(void);
+void __init kfence_alloc_pool_and_metadata(void);
 
 /**
  * kfence_init() - perform KFENCE initialization at boot time
  *
- * Requires that kfence_alloc_pool() was called before. This sets up the
- * allocation gate timer, and requires that workqueues are available.
+ * Requires that kfence_alloc_pool_and_metadata() was called before. This sets
+ * up the allocation gate timer, and requires that workqueues are available.
  */
 void __init kfence_init(void);
 
@@ -123,7 +124,7 @@ static __always_inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp
 	if (!static_branch_likely(&kfence_allocation_key))
 		return NULL;
 #endif
-	if (likely(atomic_read(&kfence_allocation_gate)))
+	if (likely(atomic_read(&kfence_allocation_gate) > 0))
 		return NULL;
 	return __kfence_alloc(s, size, flags);
 }
@@ -222,8 +223,10 @@ bool __kfence_obj_info(struct kmem_obj_info *kpp, void *object, struct slab *sla
 
 #else /* CONFIG_KFENCE */
 
+#define kfence_sample_interval	(0)
+
 static inline bool is_kfence_address(const void *addr) { return false; }
-static inline void kfence_alloc_pool(void) { }
+static inline void kfence_alloc_pool_and_metadata(void) { }
 static inline void kfence_init(void) { }
 static inline void kfence_shutdown_cache(struct kmem_cache *s) { }
 static inline void *kfence_alloc(struct kmem_cache *s, size_t size, gfp_t flags) { return NULL; }
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 0b35a41440ff..8b81ac74829c 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -36,10 +36,15 @@
  * to lock the reader.
  */
 
-#include <linux/kernel.h>
+#include <linux/array_size.h>
 #include <linux/spinlock.h>
 #include <linux/stddef.h>
-#include <linux/scatterlist.h>
+#include <linux/types.h>
+
+#include <asm/barrier.h>
+#include <asm/errno.h>
+
+struct scatterlist;
 
 struct __kfifo {
 	unsigned int	in;
@@ -304,19 +309,25 @@ __kfifo_uint_must_check_helper( \
 )
 
 /**
- * kfifo_skip - skip output data
+ * kfifo_skip_count - skip output data
  * @fifo: address of the fifo to be used
+ * @count: count of data to skip
  */
-#define	kfifo_skip(fifo) \
-(void)({ \
+#define	kfifo_skip_count(fifo, count) do { \
 	typeof((fifo) + 1) __tmp = (fifo); \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	if (__recsize) \
 		__kfifo_skip_r(__kfifo, __recsize); \
 	else \
-		__kfifo->out++; \
-})
+		__kfifo->out += (count); \
+} while(0)
+
+/**
+ * kfifo_skip - skip output data
+ * @fifo: address of the fifo to be used
+ */
+#define	kfifo_skip(fifo)	kfifo_skip_count(fifo, 1)
 
 /**
  * kfifo_peek_len - gets the size of the next fifo record
@@ -359,6 +370,30 @@ __kfifo_int_must_check_helper( \
 )
 
 /**
+ * kfifo_alloc_node - dynamically allocates a new fifo buffer on a NUMA node
+ * @fifo: pointer to the fifo
+ * @size: the number of elements in the fifo, this must be a power of 2
+ * @gfp_mask: get_free_pages mask, passed to kmalloc()
+ * @node: NUMA node to allocate memory on
+ *
+ * This macro dynamically allocates a new fifo buffer with NUMA node awareness.
+ *
+ * The number of elements will be rounded-up to a power of 2.
+ * The fifo will be release with kfifo_free().
+ * Return 0 if no error, otherwise an error code.
+ */
+#define kfifo_alloc_node(fifo, size, gfp_mask, node) \
+__kfifo_int_must_check_helper( \
+({ \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	struct __kfifo *__kfifo = &__tmp->kfifo; \
+	__is_kfifo_ptr(__tmp) ? \
+	__kfifo_alloc_node(__kfifo, size, sizeof(*__tmp->type), gfp_mask, node) : \
+	-EINVAL; \
+}) \
+)
+
+/**
  * kfifo_free - frees the fifo
  * @fifo: the fifo to be freed
  */
@@ -578,7 +613,7 @@ __kfifo_uint_must_check_helper( \
  * @buf: pointer to the storage buffer
  * @n: max. number of elements to get
  *
- * This macro get some data from the fifo and return the numbers of elements
+ * This macro gets some data from the fifo and returns the numbers of elements
  * copied.
  *
  * Note that with only one concurrent reader and one concurrent
@@ -605,7 +640,7 @@ __kfifo_uint_must_check_helper( \
  * @n: max. number of elements to get
  * @lock: pointer to the spinlock to use for locking
  *
- * This macro get the data from the fifo and return the numbers of elements
+ * This macro gets the data from the fifo and returns the numbers of elements
  * copied.
  */
 #define	kfifo_out_spinlocked(fifo, buf, n, lock) \
@@ -703,11 +738,12 @@ __kfifo_int_must_check_helper( \
 )
 
 /**
- * kfifo_dma_in_prepare - setup a scatterlist for DMA input
+ * kfifo_dma_in_prepare_mapped - setup a scatterlist for DMA input
  * @fifo: address of the fifo to be used
  * @sgl: pointer to the scatterlist array
  * @nents: number of entries in the scatterlist array
  * @len: number of elements to transfer
+ * @dma: mapped dma address to fill into @sgl
  *
  * This macro fills a scatterlist for DMA input.
  * It returns the number entries in the scatterlist array.
@@ -715,7 +751,7 @@ __kfifo_int_must_check_helper( \
  * Note that with only one concurrent reader and one concurrent
  * writer, you don't need extra locking to use these macros.
  */
-#define	kfifo_dma_in_prepare(fifo, sgl, nents, len) \
+#define	kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, dma) \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo); \
 	struct scatterlist *__sgl = (sgl); \
@@ -724,16 +760,20 @@ __kfifo_int_must_check_helper( \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	(__recsize) ? \
-	__kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \
-	__kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len); \
+	__kfifo_dma_in_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \
+				 dma) : \
+	__kfifo_dma_in_prepare(__kfifo, __sgl, __nents, __len, dma); \
 })
 
+#define kfifo_dma_in_prepare(fifo, sgl, nents, len) \
+	kfifo_dma_in_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR)
+
 /**
  * kfifo_dma_in_finish - finish a DMA IN operation
  * @fifo: address of the fifo to be used
  * @len: number of bytes to received
  *
- * This macro finish a DMA IN operation. The in counter will be updated by
+ * This macro finishes a DMA IN operation. The in counter will be updated by
  * the len parameter. No error checking will be done.
  *
  * Note that with only one concurrent reader and one concurrent
@@ -752,11 +792,12 @@ __kfifo_int_must_check_helper( \
 })
 
 /**
- * kfifo_dma_out_prepare - setup a scatterlist for DMA output
+ * kfifo_dma_out_prepare_mapped - setup a scatterlist for DMA output
  * @fifo: address of the fifo to be used
  * @sgl: pointer to the scatterlist array
  * @nents: number of entries in the scatterlist array
  * @len: number of elements to transfer
+ * @dma: mapped dma address to fill into @sgl
  *
  * This macro fills a scatterlist for DMA output which at most @len bytes
  * to transfer.
@@ -766,7 +807,7 @@ __kfifo_int_must_check_helper( \
  * Note that with only one concurrent reader and one concurrent
  * writer, you don't need extra locking to use these macros.
  */
-#define	kfifo_dma_out_prepare(fifo, sgl, nents, len) \
+#define	kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, dma) \
 ({ \
 	typeof((fifo) + 1) __tmp = (fifo);  \
 	struct scatterlist *__sgl = (sgl); \
@@ -775,32 +816,29 @@ __kfifo_int_must_check_helper( \
 	const size_t __recsize = sizeof(*__tmp->rectype); \
 	struct __kfifo *__kfifo = &__tmp->kfifo; \
 	(__recsize) ? \
-	__kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize) : \
-	__kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len); \
+	__kfifo_dma_out_prepare_r(__kfifo, __sgl, __nents, __len, __recsize, \
+				  dma) : \
+	__kfifo_dma_out_prepare(__kfifo, __sgl, __nents, __len, dma); \
 })
 
+#define	kfifo_dma_out_prepare(fifo, sgl, nents, len) \
+	kfifo_dma_out_prepare_mapped(fifo, sgl, nents, len, DMA_MAPPING_ERROR)
+
 /**
  * kfifo_dma_out_finish - finish a DMA OUT operation
  * @fifo: address of the fifo to be used
  * @len: number of bytes transferred
  *
- * This macro finish a DMA OUT operation. The out counter will be updated by
+ * This macro finishes a DMA OUT operation. The out counter will be updated by
  * the len parameter. No error checking will be done.
  *
  * Note that with only one concurrent reader and one concurrent
  * writer, you don't need extra locking to use these macros.
  */
-#define kfifo_dma_out_finish(fifo, len) \
-(void)({ \
-	typeof((fifo) + 1) __tmp = (fifo); \
-	unsigned int __len = (len); \
-	const size_t __recsize = sizeof(*__tmp->rectype); \
-	struct __kfifo *__kfifo = &__tmp->kfifo; \
-	if (__recsize) \
-		__kfifo_dma_out_finish_r(__kfifo, __recsize); \
-	else \
-		__kfifo->out += __len / sizeof(*__tmp->type); \
-})
+#define kfifo_dma_out_finish(fifo, len) do { \
+	typeof((fifo) + 1) ___tmp = (fifo); \
+	kfifo_skip_count(___tmp, (len) / sizeof(*___tmp->type)); \
+} while (0)
 
 /**
  * kfifo_out_peek - gets some data from the fifo
@@ -808,7 +846,7 @@ __kfifo_int_must_check_helper( \
  * @buf: pointer to the storage buffer
  * @n: max. number of elements to get
  *
- * This macro get the data from the fifo and return the numbers of elements
+ * This macro gets the data from the fifo and returns the numbers of elements
  * copied. The data is not removed from the fifo.
  *
  * Note that with only one concurrent reader and one concurrent
@@ -828,8 +866,71 @@ __kfifo_uint_must_check_helper( \
 }) \
 )
 
-extern int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
-	size_t esize, gfp_t gfp_mask);
+/**
+ * kfifo_out_linear - gets a tail of/offset to available data
+ * @fifo: address of the fifo to be used
+ * @tail: pointer to an unsigned int to store the value of tail
+ * @n: max. number of elements to point at
+ *
+ * This macro obtains the offset (tail) to the available data in the fifo
+ * buffer and returns the
+ * numbers of elements available. It returns the available count till the end
+ * of data or till the end of the buffer. So that it can be used for linear
+ * data processing (like memcpy() of (@fifo->data + @tail) with count
+ * returned).
+ *
+ * Note that with only one concurrent reader and one concurrent
+ * writer, you don't need extra locking to use these macro.
+ */
+#define kfifo_out_linear(fifo, tail, n) \
+__kfifo_uint_must_check_helper( \
+({ \
+	typeof((fifo) + 1) __tmp = (fifo); \
+	unsigned int *__tail = (tail); \
+	unsigned long __n = (n); \
+	const size_t __recsize = sizeof(*__tmp->rectype); \
+	struct __kfifo *__kfifo = &__tmp->kfifo; \
+	(__recsize) ? \
+	__kfifo_out_linear_r(__kfifo, __tail, __n, __recsize) : \
+	__kfifo_out_linear(__kfifo, __tail, __n); \
+}) \
+)
+
+/**
+ * kfifo_out_linear_ptr - gets a pointer to the available data
+ * @fifo: address of the fifo to be used
+ * @ptr: pointer to data to store the pointer to tail
+ * @n: max. number of elements to point at
+ *
+ * Similarly to kfifo_out_linear(), this macro obtains the pointer to the
+ * available data in the fifo buffer and returns the numbers of elements
+ * available. It returns the available count till the end of available data or
+ * till the end of the buffer. So that it can be used for linear data
+ * processing (like memcpy() of @ptr with count returned).
+ *
+ * Note that with only one concurrent reader and one concurrent
+ * writer, you don't need extra locking to use these macro.
+ */
+#define kfifo_out_linear_ptr(fifo, ptr, n) \
+__kfifo_uint_must_check_helper( \
+({ \
+	typeof((fifo) + 1) ___tmp = (fifo); \
+	unsigned int ___tail; \
+	unsigned int ___n = kfifo_out_linear(___tmp, &___tail, (n)); \
+	*(ptr) = ___tmp->kfifo.data + ___tail * kfifo_esize(___tmp); \
+	___n; \
+}) \
+)
+
+
+extern int __kfifo_alloc_node(struct __kfifo *fifo, unsigned int size,
+	size_t esize, gfp_t gfp_mask, int node);
+
+static inline int __kfifo_alloc(struct __kfifo *fifo, unsigned int size,
+				size_t esize, gfp_t gfp_mask)
+{
+	return __kfifo_alloc_node(fifo, size, esize, gfp_mask, NUMA_NO_NODE);
+}
 
 extern void __kfifo_free(struct __kfifo *fifo);
 
@@ -849,14 +950,17 @@ extern int __kfifo_to_user(struct __kfifo *fifo,
 	void __user *to, unsigned long len, unsigned int *copied);
 
 extern unsigned int __kfifo_dma_in_prepare(struct __kfifo *fifo,
-	struct scatterlist *sgl, int nents, unsigned int len);
+	struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma);
 
 extern unsigned int __kfifo_dma_out_prepare(struct __kfifo *fifo,
-	struct scatterlist *sgl, int nents, unsigned int len);
+	struct scatterlist *sgl, int nents, unsigned int len, dma_addr_t dma);
 
 extern unsigned int __kfifo_out_peek(struct __kfifo *fifo,
 	void *buf, unsigned int len);
 
+extern unsigned int __kfifo_out_linear(struct __kfifo *fifo,
+	unsigned int *tail, unsigned int n);
+
 extern unsigned int __kfifo_in_r(struct __kfifo *fifo,
 	const void *buf, unsigned int len, size_t recsize);
 
@@ -871,15 +975,15 @@ extern int __kfifo_to_user_r(struct __kfifo *fifo, void __user *to,
 	unsigned long len, unsigned int *copied, size_t recsize);
 
 extern unsigned int __kfifo_dma_in_prepare_r(struct __kfifo *fifo,
-	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize);
+	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize,
+	dma_addr_t dma);
 
 extern void __kfifo_dma_in_finish_r(struct __kfifo *fifo,
 	unsigned int len, size_t recsize);
 
 extern unsigned int __kfifo_dma_out_prepare_r(struct __kfifo *fifo,
-	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize);
-
-extern void __kfifo_dma_out_finish_r(struct __kfifo *fifo, size_t recsize);
+	struct scatterlist *sgl, int nents, unsigned int len, size_t recsize,
+	dma_addr_t dma);
 
 extern unsigned int __kfifo_len_r(struct __kfifo *fifo, size_t recsize);
 
@@ -888,6 +992,9 @@ extern void __kfifo_skip_r(struct __kfifo *fifo, size_t recsize);
 extern unsigned int __kfifo_out_peek_r(struct __kfifo *fifo,
 	void *buf, unsigned int len, size_t recsize);
 
+extern unsigned int __kfifo_out_linear_r(struct __kfifo *fifo,
+	unsigned int *tail, unsigned int n, size_t recsize);
+
 extern unsigned int __kfifo_max_r(unsigned int len, size_t recsize);
 
 #endif
diff --git a/include/linux/kgdb.h b/include/linux/kgdb.h
index 258cdde8d356..5eebbe7a3545 100644
--- a/include/linux/kgdb.h
+++ b/include/linux/kgdb.h
@@ -257,7 +257,6 @@ extern void kgdb_arch_late(void);
  * hardware breakpoints.
  * @correct_hw_break: Allow an architecture to specify how to correct the
  * hardware debug registers.
- * @enable_nmi: Manage NMI-triggered entry to KGDB
  */
 struct kgdb_arch {
 	unsigned char		gdb_bpt_instr[BREAK_INSTR_SIZE];
@@ -270,8 +269,6 @@ struct kgdb_arch {
 	void	(*disable_hw_break)(struct pt_regs *regs);
 	void	(*remove_all_hw_break)(void);
 	void	(*correct_hw_break)(void);
-
-	void	(*enable_nmi)(bool on);
 };
 
 /**
@@ -306,16 +303,6 @@ extern const struct kgdb_arch		arch_kgdb_ops;
 
 extern unsigned long kgdb_arch_pc(int exception, struct pt_regs *regs);
 
-#ifdef CONFIG_SERIAL_KGDB_NMI
-extern int kgdb_register_nmi_console(void);
-extern int kgdb_unregister_nmi_console(void);
-extern bool kgdb_nmi_poll_knock(void);
-#else
-static inline int kgdb_register_nmi_console(void) { return 0; }
-static inline int kgdb_unregister_nmi_console(void) { return 0; }
-static inline bool kgdb_nmi_poll_knock(void) { return true; }
-#endif
-
 extern int kgdb_register_io_module(struct kgdb_io *local_kgdb_io_ops);
 extern void kgdb_unregister_io_module(struct kgdb_io *local_kgdb_io_ops);
 extern struct kgdb_io *dbg_io_ops;
@@ -365,5 +352,6 @@ extern void kgdb_free_init_mem(void);
 #define dbg_late_init()
 static inline void kgdb_panic(const char *msg) {}
 static inline void kgdb_free_init_mem(void) { }
+static inline int kgdb_nmicallback(int cpu, void *regs) { return 1; }
 #endif /* ! CONFIG_KGDB */
 #endif /* _KGDB_H_ */
diff --git a/include/linux/kho/abi/luo.h b/include/linux/kho/abi/luo.h
new file mode 100644
index 000000000000..bb099c92e469
--- /dev/null
+++ b/include/linux/kho/abi/luo.h
@@ -0,0 +1,166 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+
+/**
+ * DOC: Live Update Orchestrator ABI
+ *
+ * This header defines the stable Application Binary Interface used by the
+ * Live Update Orchestrator to pass state from a pre-update kernel to a
+ * post-update kernel. The ABI is built upon the Kexec HandOver framework
+ * and uses a Flattened Device Tree to describe the preserved data.
+ *
+ * This interface is a contract. Any modification to the FDT structure, node
+ * properties, compatible strings, or the layout of the `__packed` serialization
+ * structures defined here constitutes a breaking change. Such changes require
+ * incrementing the version number in the relevant `_COMPATIBLE` string to
+ * prevent a new kernel from misinterpreting data from an old kernel.
+ *
+ * Changes are allowed provided the compatibility version is incremented;
+ * however, backward/forward compatibility is only guaranteed for kernels
+ * supporting the same ABI version.
+ *
+ * FDT Structure Overview:
+ *   The entire LUO state is encapsulated within a single KHO entry named "LUO".
+ *   This entry contains an FDT with the following layout:
+ *
+ *   .. code-block:: none
+ *
+ *     / {
+ *         compatible = "luo-v1";
+ *         liveupdate-number = <...>;
+ *
+ *         luo-session {
+ *             compatible = "luo-session-v1";
+ *             luo-session-header = <phys_addr_of_session_header_ser>;
+ *         };
+ *     };
+ *
+ * Main LUO Node (/):
+ *
+ *   - compatible: "luo-v1"
+ *     Identifies the overall LUO ABI version.
+ *   - liveupdate-number: u64
+ *     A counter tracking the number of successful live updates performed.
+ *
+ * Session Node (luo-session):
+ *   This node describes all preserved user-space sessions.
+ *
+ *   - compatible: "luo-session-v1"
+ *     Identifies the session ABI version.
+ *   - luo-session-header: u64
+ *     The physical address of a `struct luo_session_header_ser`. This structure
+ *     is the header for a contiguous block of memory containing an array of
+ *     `struct luo_session_ser`, one for each preserved session.
+ *
+ * Serialization Structures:
+ *   The FDT properties point to memory regions containing arrays of simple,
+ *   `__packed` structures. These structures contain the actual preserved state.
+ *
+ *   - struct luo_session_header_ser:
+ *     Header for the session array. Contains the total page count of the
+ *     preserved memory block and the number of `struct luo_session_ser`
+ *     entries that follow.
+ *
+ *   - struct luo_session_ser:
+ *     Metadata for a single session, including its name and a physical pointer
+ *     to another preserved memory block containing an array of
+ *     `struct luo_file_ser` for all files in that session.
+ *
+ *   - struct luo_file_ser:
+ *     Metadata for a single preserved file. Contains the `compatible` string to
+ *     find the correct handler in the new kernel, a user-provided `token` for
+ *     identification, and an opaque `data` handle for the handler to use.
+ */
+
+#ifndef _LINUX_KHO_ABI_LUO_H
+#define _LINUX_KHO_ABI_LUO_H
+
+#include <uapi/linux/liveupdate.h>
+
+/*
+ * The LUO FDT hooks all LUO state for sessions, fds, etc.
+ * In the root it also carries "liveupdate-number" 64-bit property that
+ * corresponds to the number of live-updates performed on this machine.
+ */
+#define LUO_FDT_SIZE		PAGE_SIZE
+#define LUO_FDT_KHO_ENTRY_NAME	"LUO"
+#define LUO_FDT_COMPATIBLE	"luo-v1"
+#define LUO_FDT_LIVEUPDATE_NUM	"liveupdate-number"
+
+#define LIVEUPDATE_HNDL_COMPAT_LENGTH	48
+
+/**
+ * struct luo_file_ser - Represents the serialized preserves files.
+ * @compatible:  File handler compatible string.
+ * @data:        Private data
+ * @token:       User provided token for this file
+ *
+ * If this structure is modified, LUO_SESSION_COMPATIBLE must be updated.
+ */
+struct luo_file_ser {
+	char compatible[LIVEUPDATE_HNDL_COMPAT_LENGTH];
+	u64 data;
+	u64 token;
+} __packed;
+
+/**
+ * struct luo_file_set_ser - Represents the serialized metadata for file set
+ * @files:   The physical address of a contiguous memory block that holds
+ *           the serialized state of files (array of luo_file_ser) in this file
+ *           set.
+ * @count:   The total number of files that were part of this session during
+ *           serialization. Used for iteration and validation during
+ *           restoration.
+ */
+struct luo_file_set_ser {
+	u64 files;
+	u64 count;
+} __packed;
+
+/*
+ * LUO FDT session node
+ * LUO_FDT_SESSION_HEADER:  is a u64 physical address of struct
+ *                          luo_session_header_ser
+ */
+#define LUO_FDT_SESSION_NODE_NAME	"luo-session"
+#define LUO_FDT_SESSION_COMPATIBLE	"luo-session-v2"
+#define LUO_FDT_SESSION_HEADER		"luo-session-header"
+
+/**
+ * struct luo_session_header_ser - Header for the serialized session data block.
+ * @count: The number of `struct luo_session_ser` entries that immediately
+ *         follow this header in the memory block.
+ *
+ * This structure is located at the beginning of a contiguous block of
+ * physical memory preserved across the kexec. It provides the necessary
+ * metadata to interpret the array of session entries that follow.
+ *
+ * If this structure is modified, `LUO_FDT_SESSION_COMPATIBLE` must be updated.
+ */
+struct luo_session_header_ser {
+	u64 count;
+} __packed;
+
+/**
+ * struct luo_session_ser - Represents the serialized metadata for a LUO session.
+ * @name:         The unique name of the session, provided by the userspace at
+ *                the time of session creation.
+ * @file_set_ser: Serialized files belonging to this session,
+ *
+ * This structure is used to package session-specific metadata for transfer
+ * between kernels via Kexec Handover. An array of these structures (one per
+ * session) is created and passed to the new kernel, allowing it to reconstruct
+ * the session context.
+ *
+ * If this structure is modified, `LUO_FDT_SESSION_COMPATIBLE` must be updated.
+ */
+struct luo_session_ser {
+	char name[LIVEUPDATE_SESSION_NAME_LENGTH];
+	struct luo_file_set_ser file_set_ser;
+} __packed;
+
+#endif /* _LINUX_KHO_ABI_LUO_H */
diff --git a/include/linux/kho/abi/memfd.h b/include/linux/kho/abi/memfd.h
new file mode 100644
index 000000000000..da7d063474a1
--- /dev/null
+++ b/include/linux/kho/abi/memfd.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ *
+ * Copyright (C) 2025 Amazon.com Inc. or its affiliates.
+ * Pratyush Yadav <ptyadav@amazon.de>
+ */
+
+#ifndef _LINUX_KHO_ABI_MEMFD_H
+#define _LINUX_KHO_ABI_MEMFD_H
+
+#include <linux/types.h>
+#include <linux/kexec_handover.h>
+
+/**
+ * DOC: memfd Live Update ABI
+ *
+ * This header defines the ABI for preserving the state of a memfd across a
+ * kexec reboot using the LUO.
+ *
+ * The state is serialized into a packed structure `struct memfd_luo_ser`
+ * which is handed over to the next kernel via the KHO mechanism.
+ *
+ * This interface is a contract. Any modification to the structure layout
+ * constitutes a breaking change. Such changes require incrementing the
+ * version number in the MEMFD_LUO_FH_COMPATIBLE string.
+ */
+
+/**
+ * MEMFD_LUO_FOLIO_DIRTY - The folio is dirty.
+ *
+ * This flag indicates the folio contains data from user. A non-dirty folio is
+ * one that was allocated (say using fallocate(2)) but not written to.
+ */
+#define MEMFD_LUO_FOLIO_DIRTY		BIT(0)
+
+/**
+ * MEMFD_LUO_FOLIO_UPTODATE - The folio is up-to-date.
+ *
+ * An up-to-date folio has been zeroed out. shmem zeroes out folios on first
+ * use. This flag tracks which folios need zeroing.
+ */
+#define MEMFD_LUO_FOLIO_UPTODATE	BIT(1)
+
+/**
+ * struct memfd_luo_folio_ser - Serialized state of a single folio.
+ * @pfn:       The page frame number of the folio.
+ * @flags:     Flags to describe the state of the folio.
+ * @index:     The page offset (pgoff_t) of the folio within the original file.
+ */
+struct memfd_luo_folio_ser {
+	u64 pfn:52;
+	u64 flags:12;
+	u64 index;
+} __packed;
+
+/**
+ * struct memfd_luo_ser - Main serialization structure for a memfd.
+ * @pos:       The file's current position (f_pos).
+ * @size:      The total size of the file in bytes (i_size).
+ * @nr_folios: Number of folios in the folios array.
+ * @folios:    KHO vmalloc descriptor pointing to the array of
+ *             struct memfd_luo_folio_ser.
+ */
+struct memfd_luo_ser {
+	u64 pos;
+	u64 size;
+	u64 nr_folios;
+	struct kho_vmalloc folios;
+} __packed;
+
+/* The compatibility string for memfd file handler */
+#define MEMFD_LUO_FH_COMPATIBLE	"memfd-v1"
+
+#endif /* _LINUX_KHO_ABI_MEMFD_H */
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index f68865e19b0b..eb1946a70cff 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -2,8 +2,9 @@
 #ifndef _LINUX_KHUGEPAGED_H
 #define _LINUX_KHUGEPAGED_H
 
-#include <linux/sched/coredump.h> /* MMF_VM_HUGEPAGE */
+#include <linux/mm.h>
 
+extern unsigned int khugepaged_max_ptes_none __read_mostly;
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 extern struct attribute_group khugepaged_attr_group;
 
@@ -13,29 +14,21 @@ extern int start_stop_khugepaged(void);
 extern void __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern void khugepaged_enter_vma(struct vm_area_struct *vma,
-				 unsigned long vm_flags);
+				 vm_flags_t vm_flags);
 extern void khugepaged_min_free_kbytes_update(void);
 extern bool current_is_khugepaged(void);
-#ifdef CONFIG_SHMEM
 extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
 				   bool install_pmd);
-#else
-static inline int collapse_pte_mapped_thp(struct mm_struct *mm,
-					  unsigned long addr, bool install_pmd)
-{
-	return 0;
-}
-#endif
 
 static inline void khugepaged_fork(struct mm_struct *mm, struct mm_struct *oldmm)
 {
-	if (test_bit(MMF_VM_HUGEPAGE, &oldmm->flags))
+	if (mm_flags_test(MMF_VM_HUGEPAGE, oldmm))
 		__khugepaged_enter(mm);
 }
 
 static inline void khugepaged_exit(struct mm_struct *mm)
 {
-	if (test_bit(MMF_VM_HUGEPAGE, &mm->flags))
+	if (mm_flags_test(MMF_VM_HUGEPAGE, mm))
 		__khugepaged_exit(mm);
 }
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
@@ -46,7 +39,7 @@ static inline void khugepaged_exit(struct mm_struct *mm)
 {
 }
 static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
-					unsigned long vm_flags)
+					vm_flags_t vm_flags)
 {
 }
 static inline int collapse_pte_mapped_thp(struct mm_struct *mm,
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 6a3cd1bf4680..fbd424b2abb1 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -26,7 +26,9 @@ extern void kmemleak_free_part(const void *ptr, size_t size) __ref;
 extern void kmemleak_free_percpu(const void __percpu *ptr) __ref;
 extern void kmemleak_update_trace(const void *ptr) __ref;
 extern void kmemleak_not_leak(const void *ptr) __ref;
+extern void kmemleak_transient_leak(const void *ptr) __ref;
 extern void kmemleak_ignore(const void *ptr) __ref;
+extern void kmemleak_ignore_percpu(const void __percpu *ptr) __ref;
 extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref;
 extern void kmemleak_no_scan(const void *ptr) __ref;
 extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size,
@@ -93,6 +95,12 @@ static inline void kmemleak_update_trace(const void *ptr)
 static inline void kmemleak_not_leak(const void *ptr)
 {
 }
+static inline void kmemleak_transient_leak(const void *ptr)
+{
+}
+static inline void kmemleak_ignore_percpu(const void __percpu *ptr)
+{
+}
 static inline void kmemleak_ignore(const void *ptr)
 {
 }
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 68f69362d427..9a07c3215389 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -14,10 +14,7 @@
 #include <linux/workqueue.h>
 #include <linux/sysctl.h>
 
-#define KMOD_PATH_LEN 256
-
 #ifdef CONFIG_MODULES
-extern char modprobe_path[]; /* for sysctl */
 /* modprobe exit status on success, -ve on error.  Return value
  * usually useless though. */
 extern __printf(2, 3)
diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h
index c4cae333deec..e1082dc40abc 100644
--- a/include/linux/kmsan-checks.h
+++ b/include/linux/kmsan-checks.h
@@ -61,6 +61,17 @@ void kmsan_check_memory(const void *address, size_t size);
 void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy,
 			size_t left);
 
+/**
+ * kmsan_memmove() - Notify KMSAN about a data copy within kernel.
+ * @to:   destination address in the kernel.
+ * @from: source address in the kernel.
+ * @size: number of bytes to copy.
+ *
+ * Invoked after non-instrumented version (e.g. implemented using assembly
+ * code) of memmove()/memcpy() is called, in order to copy KMSAN's metadata.
+ */
+void kmsan_memmove(void *to, const void *from, size_t to_copy);
+
 #else
 
 static inline void kmsan_poison_memory(const void *address, size_t size,
@@ -78,6 +89,10 @@ static inline void kmsan_copy_to_user(void __user *to, const void *from,
 {
 }
 
+static inline void kmsan_memmove(void *to, const void *from, size_t to_copy)
+{
+}
+
 #endif
 
 #endif /* _LINUX_KMSAN_CHECKS_H */
diff --git a/include/linux/kmsan.h b/include/linux/kmsan.h
index e0c23a32cdf0..7da9fd506b39 100644
--- a/include/linux/kmsan.h
+++ b/include/linux/kmsan.h
@@ -133,6 +133,7 @@ void kmsan_kfree_large(const void *ptr);
  * @prot:	page protection flags used for vmap.
  * @pages:	array of pages.
  * @page_shift:	page_shift passed to vmap_range_noflush().
+ * @gfp_mask:	gfp_mask to use internally.
  *
  * KMSAN maps shadow and origin pages of @pages into contiguous ranges in
  * vmalloc metadata address range. Returns 0 on success, callers must check
@@ -142,7 +143,8 @@ int __must_check kmsan_vmap_pages_range_noflush(unsigned long start,
 						unsigned long end,
 						pgprot_t prot,
 						struct page **pages,
-						unsigned int page_shift);
+						unsigned int page_shift,
+						gfp_t gfp_mask);
 
 /**
  * kmsan_vunmap_kernel_range_noflush() - Notify KMSAN about a vunmap.
@@ -182,8 +184,7 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end);
 
 /**
  * kmsan_handle_dma() - Handle a DMA data transfer.
- * @page:   first page of the buffer.
- * @offset: offset of the buffer within the first page.
+ * @phys:   physical address of the buffer.
  * @size:   buffer size.
  * @dir:    one of possible dma_data_direction values.
  *
@@ -192,7 +193,7 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end);
  * * initializes the buffer, if it is copied from device;
  * * does both, if this is a DMA_BIDIRECTIONAL transfer.
  */
-void kmsan_handle_dma(struct page *page, size_t offset, size_t size,
+void kmsan_handle_dma(phys_addr_t phys, size_t size,
 		      enum dma_data_direction dir);
 
 /**
@@ -230,6 +231,67 @@ void kmsan_handle_urb(const struct urb *urb, bool is_out);
  */
 void kmsan_unpoison_entry_regs(const struct pt_regs *regs);
 
+/**
+ * kmsan_get_metadata() - Return a pointer to KMSAN shadow or origins.
+ * @addr:      kernel address.
+ * @is_origin: whether to return origins or shadow.
+ *
+ * Return NULL if metadata cannot be found.
+ */
+void *kmsan_get_metadata(void *addr, bool is_origin);
+
+/**
+ * kmsan_enable_current(): Enable KMSAN for the current task.
+ *
+ * Each kmsan_enable_current() current call must be preceded by a
+ * kmsan_disable_current() call. These call pairs may be nested.
+ */
+void kmsan_enable_current(void);
+
+/**
+ * kmsan_disable_current(): Disable KMSAN for the current task.
+ *
+ * Each kmsan_disable_current() current call must be followed by a
+ * kmsan_enable_current() call. These call pairs may be nested.
+ */
+void kmsan_disable_current(void);
+
+/**
+ * memset_no_sanitize_memory(): Fill memory without KMSAN instrumentation.
+ * @s: address of kernel memory to fill.
+ * @c: constant byte to fill the memory with.
+ * @n: number of bytes to fill.
+ *
+ * This is like memset(), but without KMSAN instrumentation.
+ */
+static inline void *memset_no_sanitize_memory(void *s, int c, size_t n)
+{
+	return __memset(s, c, n);
+}
+
+extern bool kmsan_enabled;
+extern int panic_on_kmsan;
+
+/*
+ * KMSAN performs a lot of consistency checks that are currently enabled by
+ * default. BUG_ON is normally discouraged in the kernel, unless used for
+ * debugging, but KMSAN itself is a debugging tool, so it makes little sense to
+ * recover if something goes wrong.
+ */
+#define KMSAN_WARN_ON(cond)                                           \
+	({                                                            \
+		const bool __cond = WARN_ON(cond);                    \
+		if (unlikely(__cond)) {                               \
+			WRITE_ONCE(kmsan_enabled, false);             \
+			if (panic_on_kmsan) {                         \
+				/* Can't call panic() here because */ \
+				/* of uaccess checks. */              \
+				BUG();                                \
+			}                                             \
+		}                                                     \
+		__cond;                                               \
+	})
+
 #else
 
 static inline void kmsan_init_shadow(void)
@@ -287,7 +349,7 @@ static inline void kmsan_kfree_large(const void *ptr)
 
 static inline int __must_check kmsan_vmap_pages_range_noflush(
 	unsigned long start, unsigned long end, pgprot_t prot,
-	struct page **pages, unsigned int page_shift)
+	struct page **pages, unsigned int page_shift, gfp_t gfp_mask)
 {
 	return 0;
 }
@@ -311,8 +373,8 @@ static inline void kmsan_iounmap_page_range(unsigned long start,
 {
 }
 
-static inline void kmsan_handle_dma(struct page *page, size_t offset,
-				    size_t size, enum dma_data_direction dir)
+static inline void kmsan_handle_dma(phys_addr_t phys, size_t size,
+				    enum dma_data_direction dir)
 {
 }
 
@@ -329,6 +391,21 @@ static inline void kmsan_unpoison_entry_regs(const struct pt_regs *regs)
 {
 }
 
+static inline void kmsan_enable_current(void)
+{
+}
+
+static inline void kmsan_disable_current(void)
+{
+}
+
+static inline void *memset_no_sanitize_memory(void *s, int c, size_t n)
+{
+	return memset(s, c, n);
+}
+
+#define KMSAN_WARN_ON WARN_ON
+
 #endif
 
 #endif /* _LINUX_KMSAN_H */
diff --git a/include/linux/kmsan_types.h b/include/linux/kmsan_types.h
index 8bfa6c98176d..dfc59918b3c0 100644
--- a/include/linux/kmsan_types.h
+++ b/include/linux/kmsan_types.h
@@ -9,6 +9,8 @@
 #ifndef _LINUX_KMSAN_TYPES_H
 #define _LINUX_KMSAN_TYPES_H
 
+#include <linux/types.h>
+
 /* These constants are defined in the MSan LLVM instrumentation pass. */
 #define KMSAN_RETVAL_SIZE 800
 #define KMSAN_PARAM_SIZE 800
@@ -29,7 +31,7 @@ struct kmsan_context_state {
 struct kmsan_ctx {
 	struct kmsan_context_state cstate;
 	int kmsan_in_runtime;
-	bool allow_reporting;
+	unsigned int depth;
 };
 
 #endif /* _LINUX_KMSAN_TYPES_H */
diff --git a/include/linux/kmsg_dump.h b/include/linux/kmsg_dump.h
index 906521c2329c..6055fc969877 100644
--- a/include/linux/kmsg_dump.h
+++ b/include/linux/kmsg_dump.h
@@ -40,6 +40,17 @@ struct kmsg_dump_iter {
 };
 
 /**
+ * struct kmsg_dump_detail - kernel crash detail
+ * @reason: reason for the crash, see kmsg_dump_reason.
+ * @description: optional short string, to provide additional information.
+ */
+
+struct kmsg_dump_detail {
+	enum kmsg_dump_reason reason;
+	const char *description;
+};
+
+/**
  * struct kmsg_dumper - kernel crash message dumper structure
  * @list:	Entry in the dumper list (private)
  * @dump:	Call into dumping code which will retrieve the data with
@@ -49,13 +60,13 @@ struct kmsg_dump_iter {
  */
 struct kmsg_dumper {
 	struct list_head list;
-	void (*dump)(struct kmsg_dumper *dumper, enum kmsg_dump_reason reason);
+	void (*dump)(struct kmsg_dumper *dumper, struct kmsg_dump_detail *detail);
 	enum kmsg_dump_reason max_reason;
 	bool registered;
 };
 
 #ifdef CONFIG_PRINTK
-void kmsg_dump(enum kmsg_dump_reason reason);
+void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc);
 
 bool kmsg_dump_get_line(struct kmsg_dump_iter *iter, bool syslog,
 			char *line, size_t size, size_t *len);
@@ -71,7 +82,7 @@ int kmsg_dump_unregister(struct kmsg_dumper *dumper);
 
 const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason);
 #else
-static inline void kmsg_dump(enum kmsg_dump_reason reason)
+static inline void kmsg_dump_desc(enum kmsg_dump_reason reason, const char *desc)
 {
 }
 
@@ -107,4 +118,9 @@ static inline const char *kmsg_dump_reason_str(enum kmsg_dump_reason reason)
 }
 #endif
 
+static inline void kmsg_dump(enum kmsg_dump_reason reason)
+{
+	kmsg_dump_desc(reason, NULL);
+}
+
 #endif /* _LINUX_KMSG_DUMP_H */
diff --git a/include/linux/kobject.h b/include/linux/kobject.h
index c392c811d9ad..c8219505a79f 100644
--- a/include/linux/kobject.h
+++ b/include/linux/kobject.h
@@ -38,7 +38,7 @@ extern char uevent_helper[];
 #endif
 
 /* counter to tag the uevent, read only except for the kobject core */
-extern u64 uevent_seqnum;
+extern atomic64_t uevent_seqnum;
 
 /*
  * The actions here must match the index to the string array
@@ -69,14 +69,16 @@ struct kobject {
 	const struct kobj_type	*ktype;
 	struct kernfs_node	*sd; /* sysfs directory entry */
 	struct kref		kref;
-#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
-	struct delayed_work	release;
-#endif
+
 	unsigned int state_initialized:1;
 	unsigned int state_in_sysfs:1;
 	unsigned int state_add_uevent_sent:1;
 	unsigned int state_remove_uevent_sent:1;
 	unsigned int uevent_suppress:1;
+
+#ifdef CONFIG_DEBUG_KOBJECT_RELEASE
+	struct delayed_work	release;
+#endif
 };
 
 __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...);
diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h
index be707748e7ce..150fe2ae1b6b 100644
--- a/include/linux/kobject_ns.h
+++ b/include/linux/kobject_ns.h
@@ -52,8 +52,6 @@ const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj);
 
 bool kobj_ns_current_may_mount(enum kobj_ns_type type);
 void *kobj_ns_grab_current(enum kobj_ns_type type);
-const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk);
-const void *kobj_ns_initial(enum kobj_ns_type type);
 void kobj_ns_drop(enum kobj_ns_type type, void *ns);
 
 #endif /* _LINUX_KOBJECT_NS_H */
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 85a64cb95d75..8c4f3bb24429 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -26,8 +26,7 @@
 #include <linux/rcupdate.h>
 #include <linux/mutex.h>
 #include <linux/ftrace.h>
-#include <linux/refcount.h>
-#include <linux/freelist.h>
+#include <linux/objpool.h>
 #include <linux/rethook.h>
 #include <asm/kprobes.h>
 
@@ -140,8 +139,8 @@ static inline bool kprobe_ftrace(struct kprobe *p)
  *
  */
 struct kretprobe_holder {
-	struct kretprobe	*rp;
-	refcount_t		ref;
+	struct kretprobe __rcu *rp;
+	struct objpool_head	pool;
 };
 
 struct kretprobe {
@@ -154,7 +153,6 @@ struct kretprobe {
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 	struct rethook *rh;
 #else
-	struct freelist_head freelist;
 	struct kretprobe_holder *rph;
 #endif
 };
@@ -165,10 +163,7 @@ struct kretprobe_instance {
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 	struct rethook_node node;
 #else
-	union {
-		struct freelist_node freelist;
-		struct rcu_head rcu;
-	};
+	struct rcu_head rcu;
 	struct llist_node llist;
 	struct kretprobe_holder *rph;
 	kprobe_opcode_t *ret_addr;
@@ -202,10 +197,8 @@ extern int arch_trampoline_kprobe(struct kprobe *p);
 #ifdef CONFIG_KRETPROBE_ON_RETHOOK
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return (struct kretprobe *)READ_ONCE(ri->node.rethook->data);
+	/* rethook::data is non-changed field, so that you can access it freely. */
+	return (struct kretprobe *)ri->node.rethook->data;
 }
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
 {
@@ -250,10 +243,7 @@ unsigned long kretprobe_trampoline_handler(struct pt_regs *regs,
 
 static nokprobe_inline struct kretprobe *get_kretprobe(struct kretprobe_instance *ri)
 {
-	RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(),
-		"Kretprobe is accessed from instance under preemptive context");
-
-	return READ_ONCE(ri->rph->rp);
+	return rcu_dereference_check(ri->rph->rp, rcu_read_lock_any_held());
 }
 
 static nokprobe_inline unsigned long get_kretprobe_retaddr(struct kretprobe_instance *ri)
@@ -279,15 +269,6 @@ extern unsigned long __stop_kprobe_blacklist[];
 
 extern struct kretprobe_blackpoint kretprobe_blacklist[];
 
-#ifdef CONFIG_KPROBES_SANITY_TEST
-extern int init_test_probes(void);
-#else /* !CONFIG_KPROBES_SANITY_TEST */
-static inline int init_test_probes(void)
-{
-	return 0;
-}
-#endif /* CONFIG_KPROBES_SANITY_TEST */
-
 extern int arch_prepare_kprobe(struct kprobe *p);
 extern void arch_arm_kprobe(struct kprobe *p);
 extern void arch_disarm_kprobe(struct kprobe *p);
@@ -388,11 +369,15 @@ static inline void wait_for_kprobe_optimizer(void) { }
 extern void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 				  struct ftrace_ops *ops, struct ftrace_regs *fregs);
 extern int arch_prepare_kprobe_ftrace(struct kprobe *p);
+/* Set when ftrace has been killed: kprobes on ftrace must be disabled for safety */
+extern bool kprobe_ftrace_disabled __read_mostly;
+extern void kprobe_ftrace_kill(void);
 #else
 static inline int arch_prepare_kprobe_ftrace(struct kprobe *p)
 {
 	return -EINVAL;
 }
+static inline void kprobe_ftrace_kill(void) {}
 #endif /* CONFIG_KPROBES_ON_FTRACE */
 
 /* Get the kprobe at this addr (if any) - called with preemption disabled */
@@ -450,6 +435,10 @@ int kprobe_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 
 int arch_kprobe_get_kallsym(unsigned int *symnum, unsigned long *value,
 			    char *type, char *sym);
+
+int kprobe_exceptions_notify(struct notifier_block *self,
+			     unsigned long val, void *data);
+
 #else /* !CONFIG_KPROBES: */
 
 static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
@@ -501,6 +490,9 @@ static inline void kprobe_flush_task(struct task_struct *tk)
 static inline void kprobe_free_init_mem(void)
 {
 }
+static inline void kprobe_ftrace_kill(void)
+{
+}
 static inline int disable_kprobe(struct kprobe *kp)
 {
 	return -EOPNOTSUPP;
diff --git a/include/linux/kref.h b/include/linux/kref.h
index d32e21a2538c..88e82ab1367c 100644
--- a/include/linux/kref.h
+++ b/include/linux/kref.h
@@ -46,18 +46,18 @@ static inline void kref_get(struct kref *kref)
 }
 
 /**
- * kref_put - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
+ * kref_put - Decrement refcount for object
+ * @kref: Object
+ * @release: Pointer to the function that will clean up the object when the
  *	     last reference to the object is released.
- *	     This pointer is required, and it is not acceptable to pass kfree
- *	     in as this function.
  *
- * Decrement the refcount, and if 0, call release().
- * Return 1 if the object was removed, otherwise return 0.  Beware, if this
- * function returns 0, you still can not count on the kref from remaining in
- * memory.  Only use the return value if you want to see if the kref is now
- * gone, not present.
+ * Decrement the refcount, and if 0, call @release.  The caller may not
+ * pass NULL or kfree() as the release function.
+ *
+ * Return: 1 if this call removed the object, otherwise return 0.  Beware,
+ * if this function returns 0, another caller may have removed the object
+ * by the time this function returns.  The return value is only certain
+ * if you want to see if the object is definitely released.
  */
 static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref))
 {
@@ -68,17 +68,37 @@ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)
 	return 0;
 }
 
+/**
+ * kref_put_mutex - Decrement refcount for object
+ * @kref: Object
+ * @release: Pointer to the function that will clean up the object when the
+ *	     last reference to the object is released.
+ * @mutex: Mutex which protects the release function.
+ *
+ * This variant of kref_lock() calls the @release function with the @mutex
+ * held.  The @release function will release the mutex.
+ */
 static inline int kref_put_mutex(struct kref *kref,
 				 void (*release)(struct kref *kref),
-				 struct mutex *lock)
+				 struct mutex *mutex)
 {
-	if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) {
+	if (refcount_dec_and_mutex_lock(&kref->refcount, mutex)) {
 		release(kref);
 		return 1;
 	}
 	return 0;
 }
 
+/**
+ * kref_put_lock - Decrement refcount for object
+ * @kref: Object
+ * @release: Pointer to the function that will clean up the object when the
+ *	     last reference to the object is released.
+ * @lock: Spinlock which protects the release function.
+ *
+ * This variant of kref_lock() calls the @release function with the @lock
+ * held.  The @release function will release the lock.
+ */
 static inline int kref_put_lock(struct kref *kref,
 				void (*release)(struct kref *kref),
 				spinlock_t *lock)
@@ -94,8 +114,6 @@ static inline int kref_put_lock(struct kref *kref,
  * kref_get_unless_zero - Increment refcount for object unless it is zero.
  * @kref: object.
  *
- * Return non-zero if the increment succeeded. Otherwise return 0.
- *
  * This function is intended to simplify locking around refcounting for
  * objects that can be looked up from a lookup structure, and which are
  * removed from that lookup structure in the object destructor.
@@ -105,6 +123,8 @@ static inline int kref_put_lock(struct kref *kref,
  * With a lookup followed by a kref_get_unless_zero *with return value check*
  * locking in the kref_put path can be deferred to the actual removal from
  * the lookup structure and RCU lookups become trivial.
+ *
+ * Return: non-zero if the increment succeeded. Otherwise return 0.
  */
 static inline int __must_check kref_get_unless_zero(struct kref *kref)
 {
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 899a314bc487..c982694c987b 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -13,39 +13,70 @@
 #include <linux/pagemap.h>
 #include <linux/rmap.h>
 #include <linux/sched.h>
-#include <linux/sched/coredump.h>
 
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
-		unsigned long end, int advice, unsigned long *vm_flags);
-
-void ksm_add_vma(struct vm_area_struct *vma);
+		unsigned long end, int advice, vm_flags_t *vm_flags);
+vm_flags_t ksm_vma_flags(struct mm_struct *mm, const struct file *file,
+			 vm_flags_t vm_flags);
 int ksm_enable_merge_any(struct mm_struct *mm);
 int ksm_disable_merge_any(struct mm_struct *mm);
 int ksm_disable(struct mm_struct *mm);
 
 int __ksm_enter(struct mm_struct *mm);
 void __ksm_exit(struct mm_struct *mm);
+/*
+ * To identify zeropages that were mapped by KSM, we reuse the dirty bit
+ * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when
+ * deduplicating memory.
+ */
+#define is_ksm_zero_pte(pte)	(is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte))
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+extern atomic_long_t ksm_zero_pages;
+
+static inline void ksm_map_zero_page(struct mm_struct *mm)
 {
-	int ret;
+	atomic_long_inc(&ksm_zero_pages);
+	atomic_long_inc(&mm->ksm_zero_pages);
+}
 
-	if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) {
-		ret = __ksm_enter(mm);
-		if (ret)
-			return ret;
+static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
+{
+	if (is_ksm_zero_pte(pte)) {
+		atomic_long_dec(&ksm_zero_pages);
+		atomic_long_dec(&mm->ksm_zero_pages);
 	}
+}
 
-	if (test_bit(MMF_VM_MERGE_ANY, &oldmm->flags))
-		set_bit(MMF_VM_MERGE_ANY, &mm->flags);
+static inline long mm_ksm_zero_pages(struct mm_struct *mm)
+{
+	return atomic_long_read(&mm->ksm_zero_pages);
+}
+
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+	/* Adding mm to ksm is best effort on fork. */
+	if (mm_flags_test(MMF_VM_MERGEABLE, oldmm)) {
+		long nr_ksm_zero_pages = atomic_long_read(&mm->ksm_zero_pages);
+
+		mm->ksm_merging_pages = 0;
+		mm->ksm_rmap_items = 0;
+		atomic_long_add(nr_ksm_zero_pages, &ksm_zero_pages);
+		__ksm_enter(mm);
+	}
+}
+
+static inline int ksm_execve(struct mm_struct *mm)
+{
+	if (mm_flags_test(MMF_VM_MERGE_ANY, mm))
+		return __ksm_enter(mm);
 
 	return 0;
 }
 
 static inline void ksm_exit(struct mm_struct *mm)
 {
-	if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
+	if (mm_flags_test(MMF_VM_MERGEABLE, mm))
 		__ksm_exit(mm);
 }
 
@@ -60,25 +91,22 @@ static inline void ksm_exit(struct mm_struct *mm)
  * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE,
  * but what if the vma was unmerged while the page was swapped out?
  */
-struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address);
+struct folio *ksm_might_need_to_copy(struct folio *folio,
+			struct vm_area_struct *vma, unsigned long addr);
 
 void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
 void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
-
-#ifdef CONFIG_MEMORY_FAILURE
-void collect_procs_ksm(struct page *page, struct list_head *to_kill,
-		       int force_early);
-#endif
-
-#ifdef CONFIG_PROC_FS
+void collect_procs_ksm(const struct folio *folio, const struct page *page,
+		struct list_head *to_kill, int force_early);
 long ksm_process_profit(struct mm_struct *);
-#endif /* CONFIG_PROC_FS */
+bool ksm_process_mergeable(struct mm_struct *mm);
 
 #else  /* !CONFIG_KSM */
 
-static inline void ksm_add_vma(struct vm_area_struct *vma)
+static inline vm_flags_t ksm_vma_flags(struct mm_struct *mm,
+		const struct file *file, vm_flags_t vm_flags)
 {
+	return vm_flags;
 }
 
 static inline int ksm_disable(struct mm_struct *mm)
@@ -86,7 +114,11 @@ static inline int ksm_disable(struct mm_struct *mm)
 	return 0;
 }
 
-static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+static inline void ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm)
+{
+}
+
+static inline int ksm_execve(struct mm_struct *mm)
 {
 	return 0;
 }
@@ -95,24 +127,27 @@ static inline void ksm_exit(struct mm_struct *mm)
 {
 }
 
-#ifdef CONFIG_MEMORY_FAILURE
-static inline void collect_procs_ksm(struct page *page,
-				     struct list_head *to_kill, int force_early)
+static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte)
+{
+}
+
+static inline void collect_procs_ksm(const struct folio *folio,
+		const struct page *page, struct list_head *to_kill,
+		int force_early)
 {
 }
-#endif
 
 #ifdef CONFIG_MMU
 static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
-		unsigned long end, int advice, unsigned long *vm_flags)
+		unsigned long end, int advice, vm_flags_t *vm_flags)
 {
 	return 0;
 }
 
-static inline struct page *ksm_might_need_to_copy(struct page *page,
-			struct vm_area_struct *vma, unsigned long address)
+static inline struct folio *ksm_might_need_to_copy(struct folio *folio,
+			struct vm_area_struct *vma, unsigned long addr)
 {
-	return page;
+	return folio;
 }
 
 static inline void rmap_walk_ksm(struct folio *folio,
diff --git a/include/linux/stackleak.h b/include/linux/kstack_erase.h
index c36e7a3b45e7..bf3bf1905557 100644
--- a/include/linux/stackleak.h
+++ b/include/linux/kstack_erase.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_STACKLEAK_H
-#define _LINUX_STACKLEAK_H
+#ifndef _LINUX_KSTACK_ERASE_H
+#define _LINUX_KSTACK_ERASE_H
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
@@ -9,11 +9,12 @@
  * Check that the poison value points to the unused hole in the
  * virtual memory map for your platform.
  */
-#define STACKLEAK_POISON -0xBEEF
-#define STACKLEAK_SEARCH_DEPTH 128
+#define KSTACK_ERASE_POISON -0xBEEF
+#define KSTACK_ERASE_SEARCH_DEPTH 128
 
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 #include <asm/stacktrace.h>
+#include <linux/linkage.h>
 
 /*
  * The lowest address on tsk's stack which we can plausibly erase.
@@ -49,7 +50,7 @@ stackleak_task_high_bound(const struct task_struct *tsk)
 static __always_inline unsigned long
 stackleak_find_top_of_poison(const unsigned long low, const unsigned long high)
 {
-	const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
+	const unsigned int depth = KSTACK_ERASE_SEARCH_DEPTH / sizeof(unsigned long);
 	unsigned int poison_count = 0;
 	unsigned long poison_high = high;
 	unsigned long sp = high;
@@ -57,7 +58,7 @@ stackleak_find_top_of_poison(const unsigned long low, const unsigned long high)
 	while (sp > low && poison_count < depth) {
 		sp -= sizeof(unsigned long);
 
-		if (*(unsigned long *)sp == STACKLEAK_POISON) {
+		if (*(unsigned long *)sp == KSTACK_ERASE_POISON) {
 			poison_count++;
 		} else {
 			poison_count = 0;
@@ -71,12 +72,17 @@ stackleak_find_top_of_poison(const unsigned long low, const unsigned long high)
 static inline void stackleak_task_init(struct task_struct *t)
 {
 	t->lowest_stack = stackleak_task_low_bound(t);
-# ifdef CONFIG_STACKLEAK_METRICS
+# ifdef CONFIG_KSTACK_ERASE_METRICS
 	t->prev_lowest_stack = t->lowest_stack;
 # endif
 }
 
-#else /* !CONFIG_GCC_PLUGIN_STACKLEAK */
+asmlinkage void noinstr stackleak_erase(void);
+asmlinkage void noinstr stackleak_erase_on_task_stack(void);
+asmlinkage void noinstr stackleak_erase_off_task_stack(void);
+void __no_caller_saved_registers noinstr __sanitizer_cov_stack_depth(void);
+
+#else /* !CONFIG_KSTACK_ERASE */
 static inline void stackleak_task_init(struct task_struct *t) { }
 #endif
 
diff --git a/include/linux/kstrtox.h b/include/linux/kstrtox.h
index 529974e22ea7..6ea897222af1 100644
--- a/include/linux/kstrtox.h
+++ b/include/linux/kstrtox.h
@@ -143,13 +143,9 @@ static inline int __must_check kstrtos32_from_user(const char __user *s, size_t
  */
 
 extern unsigned long simple_strtoul(const char *,char **,unsigned int);
+extern unsigned long simple_strntoul(const char *,char **,unsigned int,size_t);
 extern long simple_strtol(const char *,char **,unsigned int);
 extern unsigned long long simple_strtoull(const char *,char **,unsigned int);
 extern long long simple_strtoll(const char *,char **,unsigned int);
 
-static inline int strtobool(const char *s, bool *res)
-{
-	return kstrtobool(s, res);
-}
-
 #endif	/* _LINUX_KSTRTOX_H */
diff --git a/include/linux/kthread.h b/include/linux/kthread.h
index 30e5bec81d2b..8d27403888ce 100644
--- a/include/linux/kthread.h
+++ b/include/linux/kthread.h
@@ -85,10 +85,12 @@ kthread_run_on_cpu(int (*threadfn)(void *data), void *data,
 void free_kthread_struct(struct task_struct *k);
 void kthread_bind(struct task_struct *k, unsigned int cpu);
 void kthread_bind_mask(struct task_struct *k, const struct cpumask *mask);
+int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask);
 int kthread_stop(struct task_struct *k);
+int kthread_stop_put(struct task_struct *k);
 bool kthread_should_stop(void);
 bool kthread_should_park(void);
-bool __kthread_should_park(struct task_struct *k);
+bool kthread_should_stop_or_park(void);
 bool kthread_freezable_should_stop(bool *was_frozen);
 void *kthread_func(struct task_struct *k);
 void *kthread_data(struct task_struct *k);
@@ -185,13 +187,58 @@ extern void __kthread_init_worker(struct kthread_worker *worker,
 
 int kthread_worker_fn(void *worker_ptr);
 
-__printf(2, 3)
-struct kthread_worker *
-kthread_create_worker(unsigned int flags, const char namefmt[], ...);
+__printf(3, 4)
+struct kthread_worker *kthread_create_worker_on_node(unsigned int flags,
+						     int node,
+						     const char namefmt[], ...);
+
+#define kthread_create_worker(flags, namefmt, ...) \
+	kthread_create_worker_on_node(flags, NUMA_NO_NODE, namefmt, ## __VA_ARGS__);
+
+/**
+ * kthread_run_worker - create and wake a kthread worker.
+ * @flags: flags modifying the default behavior of the worker
+ * @namefmt: printf-style name for the thread.
+ *
+ * Description: Convenient wrapper for kthread_create_worker() followed by
+ * wake_up_process().  Returns the kthread_worker or ERR_PTR(-ENOMEM).
+ */
+#define kthread_run_worker(flags, namefmt, ...)					\
+({										\
+	struct kthread_worker *__kw						\
+		= kthread_create_worker(flags, namefmt, ## __VA_ARGS__);	\
+	if (!IS_ERR(__kw))							\
+		wake_up_process(__kw->task);					\
+	__kw;									\
+})
 
-__printf(3, 4) struct kthread_worker *
+struct kthread_worker *
 kthread_create_worker_on_cpu(int cpu, unsigned int flags,
-			     const char namefmt[], ...);
+			     const char namefmt[]);
+
+/**
+ * kthread_run_worker_on_cpu - create and wake a cpu bound kthread worker.
+ * @cpu: CPU number
+ * @flags: flags modifying the default behavior of the worker
+ * @namefmt: printf-style name for the thread. Format is restricted
+ *	     to "name.*%u". Code fills in cpu number.
+ *
+ * Description: Convenient wrapper for kthread_create_worker_on_cpu()
+ * followed by wake_up_process().  Returns the kthread_worker or
+ * ERR_PTR(-ENOMEM).
+ */
+static inline struct kthread_worker *
+kthread_run_worker_on_cpu(int cpu, unsigned int flags,
+			  const char namefmt[])
+{
+	struct kthread_worker *kw;
+
+	kw = kthread_create_worker_on_cpu(cpu, flags, namefmt);
+	if (!IS_ERR(kw))
+		wake_up_process(kw->task);
+
+	return kw;
+}
 
 bool kthread_queue_work(struct kthread_worker *worker,
 			struct kthread_work *work);
diff --git a/include/linux/ktime.h b/include/linux/ktime.h
index 73f20deb497d..383ed9985802 100644
--- a/include/linux/ktime.h
+++ b/include/linux/ktime.h
@@ -21,12 +21,10 @@
 #ifndef _LINUX_KTIME_H
 #define _LINUX_KTIME_H
 
-#include <linux/time.h>
-#include <linux/jiffies.h>
 #include <asm/bug.h>
-
-/* Nanosecond scalar representation for kernel time values */
-typedef s64	ktime_t;
+#include <linux/jiffies.h>
+#include <linux/time.h>
+#include <linux/types.h>
 
 /**
  * ktime_set - Set a ktime_t variable from a seconds/nanoseconds value
@@ -224,6 +222,11 @@ static inline ktime_t ns_to_ktime(u64 ns)
 	return ns;
 }
 
+static inline ktime_t us_to_ktime(u64 us)
+{
+	return us * NSEC_PER_USEC;
+}
+
 static inline ktime_t ms_to_ktime(u64 ms)
 {
 	return ms * NSEC_PER_MSEC;
diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index 4862c98d80d3..eb10d87adf7d 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -32,7 +32,7 @@ struct kvm_dirty_ring {
  * If CONFIG_HAVE_HVM_DIRTY_RING not defined, kvm_dirty_ring.o should
  * not be included as well, so define these nop functions for the arch.
  */
-static inline u32 kvm_dirty_ring_get_rsvd_entries(void)
+static inline u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm)
 {
 	return 0;
 }
@@ -42,16 +42,17 @@ static inline bool kvm_use_dirty_bitmap(struct kvm *kvm)
 	return true;
 }
 
-static inline int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring,
+static inline int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
 				       int index, u32 size)
 {
 	return 0;
 }
 
 static inline int kvm_dirty_ring_reset(struct kvm *kvm,
-				       struct kvm_dirty_ring *ring)
+				       struct kvm_dirty_ring *ring,
+				       int *nr_entries_reset)
 {
-	return 0;
+	return -ENOENT;
 }
 
 static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu,
@@ -71,22 +72,14 @@ static inline void kvm_dirty_ring_free(struct kvm_dirty_ring *ring)
 
 #else /* CONFIG_HAVE_KVM_DIRTY_RING */
 
-int kvm_cpu_dirty_log_size(void);
+int kvm_cpu_dirty_log_size(struct kvm *kvm);
 bool kvm_use_dirty_bitmap(struct kvm *kvm);
 bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm);
-u32 kvm_dirty_ring_get_rsvd_entries(void);
-int kvm_dirty_ring_alloc(struct kvm_dirty_ring *ring, int index, u32 size);
-
-/*
- * called with kvm->slots_lock held, returns the number of
- * processed pages.
- */
-int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
-
-/*
- * returns =0: successfully pushed
- *         <0: unable to push, need to wait
- */
+u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm);
+int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int index, u32 size);
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int *nr_entries_reset);
 void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset);
 
 bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 0e571e973bc2..d93f75b05ae2 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2,7 +2,7 @@
 #ifndef __KVM_HOST_H
 #define __KVM_HOST_H
 
-
+#include <linux/entry-virt.h>
 #include <linux/types.h>
 #include <linux/hardirq.h>
 #include <linux/list.h>
@@ -52,9 +52,10 @@
 /*
  * The bit 16 ~ bit 31 of kvm_userspace_memory_region::flags are internally
  * used in kvm, other bits are visible for userspace which are defined in
- * include/linux/kvm_h.
+ * include/uapi/linux/kvm.h.
  */
-#define KVM_MEMSLOT_INVALID	(1UL << 16)
+#define KVM_MEMSLOT_INVALID			(1UL << 16)
+#define KVM_MEMSLOT_GMEM_ONLY			(1UL << 17)
 
 /*
  * Bit 63 of the memslot generation number is an "update in-progress flag",
@@ -80,8 +81,8 @@
 /* Two fragments for cross MMIO pages. */
 #define KVM_MAX_MMIO_FRAGMENTS	2
 
-#ifndef KVM_ADDRESS_SPACE_NUM
-#define KVM_ADDRESS_SPACE_NUM	1
+#ifndef KVM_MAX_NR_ADDRESS_SPACES
+#define KVM_MAX_NR_ADDRESS_SPACES	1
 #endif
 
 /*
@@ -97,6 +98,7 @@
 #define KVM_PFN_ERR_HWPOISON	(KVM_PFN_ERR_MASK + 1)
 #define KVM_PFN_ERR_RO_FAULT	(KVM_PFN_ERR_MASK + 2)
 #define KVM_PFN_ERR_SIGPENDING	(KVM_PFN_ERR_MASK + 3)
+#define KVM_PFN_ERR_NEEDS_IO	(KVM_PFN_ERR_MASK + 4)
 
 /*
  * error pfns indicate that the gfn is in slot but faild to
@@ -148,11 +150,9 @@ static inline bool kvm_is_error_hva(unsigned long addr)
 
 #endif
 
-#define KVM_ERR_PTR_BAD_PAGE	(ERR_PTR(-ENOENT))
-
-static inline bool is_error_page(struct page *page)
+static inline bool kvm_is_error_gpa(gpa_t gpa)
 {
-	return IS_ERR(page);
+	return gpa == INVALID_GPA;
 }
 
 #define KVM_REQUEST_MASK           GENMASK(7,0)
@@ -188,13 +188,10 @@ static inline bool is_error_page(struct page *page)
 bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
 				 unsigned long *vcpu_bitmap);
 bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
-bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req,
-				      struct kvm_vcpu *except);
-bool kvm_make_cpus_request_mask(struct kvm *kvm, unsigned int req,
-				unsigned long *vcpu_bitmap);
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
+#define KVM_PIT_IRQ_SOURCE_ID			2
 
 extern struct mutex kvm_lock;
 extern struct list_head vm_list;
@@ -210,6 +207,7 @@ struct kvm_io_range {
 struct kvm_io_bus {
 	int dev_count;
 	int ioeventfd_count;
+	struct rcu_head rcu;
 	struct kvm_io_range range[];
 };
 
@@ -218,6 +216,7 @@ enum kvm_bus {
 	KVM_PIO_BUS,
 	KVM_VIRTIO_CCW_NOTIFY_BUS,
 	KVM_FAST_MMIO_BUS,
+	KVM_IOCSR_BUS,
 	KVM_NR_BUSES
 };
 
@@ -240,7 +239,6 @@ struct kvm_async_pf {
 	struct list_head link;
 	struct list_head queue;
 	struct kvm_vcpu *vcpu;
-	struct mm_struct *mm;
 	gpa_t cr2_or_gpa;
 	unsigned long addr;
 	struct kvm_arch_async_pf arch;
@@ -255,18 +253,28 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
 int kvm_async_pf_wakeup_all(struct kvm_vcpu *vcpu);
 #endif
 
-#ifdef KVM_ARCH_WANT_MMU_NOTIFIER
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
+union kvm_mmu_notifier_arg {
+	unsigned long attributes;
+};
+
+enum kvm_gfn_range_filter {
+	KVM_FILTER_SHARED		= BIT(0),
+	KVM_FILTER_PRIVATE		= BIT(1),
+};
+
 struct kvm_gfn_range {
 	struct kvm_memory_slot *slot;
 	gfn_t start;
 	gfn_t end;
-	pte_t pte;
+	union kvm_mmu_notifier_arg arg;
+	enum kvm_gfn_range_filter attr_filter;
 	bool may_block;
+	bool lockless;
 };
 bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
 bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
-bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range);
 #endif
 
 enum {
@@ -276,21 +284,19 @@ enum {
 	READING_SHADOW_PAGE_TABLES,
 };
 
-#define KVM_UNMAPPED_PAGE	((void *) 0x500 + POISON_POINTER_DELTA)
-
 struct kvm_host_map {
 	/*
 	 * Only valid if the 'pfn' is managed by the host kernel (i.e. There is
 	 * a 'struct page' for it. When using mem= kernel parameter some memory
 	 * can be used as guest memory but they are not managed by host
 	 * kernel).
-	 * If 'pfn' is not managed by the host kernel, this field is
-	 * initialized to KVM_UNMAPPED_PAGE.
 	 */
+	struct page *pinned_page;
 	struct page *page;
 	void *hva;
 	kvm_pfn_t pfn;
 	kvm_pfn_t gfn;
+	bool writable;
 };
 
 /*
@@ -339,7 +345,8 @@ struct kvm_vcpu {
 #ifndef __KVM_HAVE_ARCH_WQP
 	struct rcuwait wait;
 #endif
-	struct pid __rcu *pid;
+	struct pid *pid;
+	rwlock_t pid_lock;
 	int sigset_active;
 	sigset_t sigset;
 	unsigned int halt_poll_ns;
@@ -375,8 +382,10 @@ struct kvm_vcpu {
 		bool dy_eligible;
 	} spin_loop;
 #endif
+	bool wants_to_run;
 	bool preempted;
 	bool ready;
+	bool scheduled_out;
 	struct kvm_vcpu_arch arch;
 	struct kvm_vcpu_stat stat;
 	char stats_id[KVM_STATS_NAME_SIZE];
@@ -480,7 +489,15 @@ static __always_inline void guest_state_enter_irqoff(void)
  */
 static __always_inline void guest_context_exit_irqoff(void)
 {
-	context_tracking_guest_exit();
+	/*
+	 * Guest mode is treated as a quiescent state, see
+	 * guest_context_enter_irqoff() for more details.
+	 */
+	if (!context_tracking_guest_exit()) {
+		instrumentation_begin();
+		rcu_virt_note_context_switch();
+		instrumentation_end();
+	}
 }
 
 /*
@@ -586,8 +603,25 @@ struct kvm_memory_slot {
 	u32 flags;
 	short id;
 	u16 as_id;
+
+#ifdef CONFIG_KVM_GUEST_MEMFD
+	struct {
+		/*
+		 * Writes protected by kvm->slots_lock.  Acquiring a
+		 * reference via kvm_gmem_get_file() is protected by
+		 * either kvm->slots_lock or kvm->srcu.
+		 */
+		struct file *file;
+		pgoff_t pgoff;
+	} gmem;
+#endif
 };
 
+static inline bool kvm_slot_has_gmem(const struct kvm_memory_slot *slot)
+{
+	return slot && (slot->flags & KVM_MEM_GUEST_MEMFD);
+}
+
 static inline bool kvm_slot_dirty_track_enabled(const struct kvm_memory_slot *slot)
 {
 	return slot->flags & KVM_MEM_LOG_DIRTY_PAGES;
@@ -662,7 +696,7 @@ struct kvm_irq_routing_table {
 	 * Array indexed by gsi. Each entry contains list of irq chips
 	 * the gsi is connected to.
 	 */
-	struct hlist_head map[];
+	struct hlist_head map[] __counted_by(nr_rt_entries);
 };
 #endif
 
@@ -675,13 +709,46 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm);
 #define KVM_MEM_SLOTS_NUM SHRT_MAX
 #define KVM_USER_MEM_SLOTS (KVM_MEM_SLOTS_NUM - KVM_INTERNAL_MEM_SLOTS)
 
-#ifndef __KVM_VCPU_MULTIPLE_ADDRESS_SPACE
+#if KVM_MAX_NR_ADDRESS_SPACES == 1
+static inline int kvm_arch_nr_memslot_as_ids(struct kvm *kvm)
+{
+	return KVM_MAX_NR_ADDRESS_SPACES;
+}
+
 static inline int kvm_arch_vcpu_memslots_id(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }
 #endif
 
+#ifndef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline bool kvm_arch_has_private_mem(struct kvm *kvm)
+{
+	return false;
+}
+#endif
+
+#ifdef CONFIG_KVM_GUEST_MEMFD
+bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm);
+
+static inline u64 kvm_gmem_get_supported_flags(struct kvm *kvm)
+{
+	u64 flags = GUEST_MEMFD_FLAG_MMAP;
+
+	if (!kvm || kvm_arch_supports_gmem_init_shared(kvm))
+		flags |= GUEST_MEMFD_FLAG_INIT_SHARED;
+
+	return flags;
+}
+#endif
+
+#ifndef kvm_arch_has_readonly_mem
+static inline bool kvm_arch_has_readonly_mem(struct kvm *kvm)
+{
+	return IS_ENABLED(CONFIG_HAVE_KVM_READONLY_MEM);
+}
+#endif
+
 struct kvm_memslots {
 	u64 generation;
 	atomic_long_t last_used_slot;
@@ -719,9 +786,9 @@ struct kvm {
 	struct mm_struct *mm; /* userspace tied to this vm */
 	unsigned long nr_memslot_pages;
 	/* The two memslot sets - active and inactive (per address space) */
-	struct kvm_memslots __memslots[KVM_ADDRESS_SPACE_NUM][2];
+	struct kvm_memslots __memslots[KVM_MAX_NR_ADDRESS_SPACES][2];
 	/* The current active memslot set for each address space */
-	struct kvm_memslots __rcu *memslots[KVM_ADDRESS_SPACE_NUM];
+	struct kvm_memslots __rcu *memslots[KVM_MAX_NR_ADDRESS_SPACES];
 	struct xarray vcpu_array;
 	/*
 	 * Protected by slots_lock, but can be read outside if an
@@ -751,7 +818,7 @@ struct kvm {
 	struct list_head vm_list;
 	struct mutex lock;
 	struct kvm_io_bus __rcu *buses[KVM_NR_BUSES];
-#ifdef CONFIG_HAVE_KVM_EVENTFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 	struct {
 		spinlock_t        lock;
 		struct list_head  items;
@@ -759,8 +826,8 @@ struct kvm {
 		struct list_head  resampler_list;
 		struct mutex      resampler_lock;
 	} irqfds;
-	struct list_head ioeventfds;
 #endif
+	struct list_head ioeventfds;
 	struct kvm_vm_stat stat;
 	struct kvm_arch arch;
 	refcount_t users_count;
@@ -776,17 +843,16 @@ struct kvm {
 	 * Update side is protected by irq_lock.
 	 */
 	struct kvm_irq_routing_table __rcu *irq_routing;
-#endif
-#ifdef CONFIG_HAVE_KVM_IRQFD
+
 	struct hlist_head irq_ack_notifier_list;
 #endif
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 	struct mmu_notifier mmu_notifier;
 	unsigned long mmu_invalidate_seq;
 	long mmu_invalidate_in_progress;
-	unsigned long mmu_invalidate_range_start;
-	unsigned long mmu_invalidate_range_end;
+	gfn_t mmu_invalidate_range_start;
+	gfn_t mmu_invalidate_range_end;
 #endif
 	struct list_head devices;
 	u64 manual_dirty_log_protect;
@@ -805,6 +871,10 @@ struct kvm {
 #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER
 	struct notifier_block pm_notifier;
 #endif
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+	/* Protected by slots_lock (for writes) and RCU (for reads) */
+	struct xarray mem_attr_array;
+#endif
 	char stats_id[KVM_STATS_NAME_SIZE];
 };
 
@@ -849,7 +919,7 @@ static inline void kvm_vm_bugged(struct kvm *kvm)
 
 #define KVM_BUG(cond, kvm, fmt...)				\
 ({								\
-	int __ret = (cond);					\
+	bool __ret = !!(cond);					\
 								\
 	if (WARN_ONCE(__ret && !(kvm)->vm_bugged, fmt))		\
 		kvm_vm_bugged(kvm);				\
@@ -858,13 +928,32 @@ static inline void kvm_vm_bugged(struct kvm *kvm)
 
 #define KVM_BUG_ON(cond, kvm)					\
 ({								\
-	int __ret = (cond);					\
+	bool __ret = !!(cond);					\
 								\
 	if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged))		\
 		kvm_vm_bugged(kvm);				\
 	unlikely(__ret);					\
 })
 
+/*
+ * Note, "data corruption" refers to corruption of host kernel data structures,
+ * not guest data.  Guest data corruption, suspected or confirmed, that is tied
+ * and contained to a single VM should *never* BUG() and potentially panic the
+ * host, i.e. use this variant of KVM_BUG() if and only if a KVM data structure
+ * is corrupted and that corruption can have a cascading effect to other parts
+ * of the hosts and/or to other VMs.
+ */
+#define KVM_BUG_ON_DATA_CORRUPTION(cond, kvm)			\
+({								\
+	bool __ret = !!(cond);					\
+								\
+	if (IS_ENABLED(CONFIG_BUG_ON_DATA_CORRUPTION))		\
+		BUG_ON(__ret);					\
+	else if (WARN_ON_ONCE(__ret && !(kvm)->vm_bugged))	\
+		kvm_vm_bugged(kvm);				\
+	unlikely(__ret);					\
+})
+
 static inline void kvm_vcpu_srcu_read_lock(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_PROVE_RCU
@@ -889,16 +978,29 @@ static inline bool kvm_dirty_log_manual_protect_and_init_set(struct kvm *kvm)
 	return !!(kvm->manual_dirty_log_protect & KVM_DIRTY_LOG_INITIALLY_SET);
 }
 
+/*
+ * Get a bus reference under the update-side lock. No long-term SRCU reader
+ * references are permitted, to avoid stale reads vs concurrent IO
+ * registrations.
+ */
 static inline struct kvm_io_bus *kvm_get_bus(struct kvm *kvm, enum kvm_bus idx)
 {
-	return srcu_dereference_check(kvm->buses[idx], &kvm->srcu,
-				      lockdep_is_held(&kvm->slots_lock) ||
-				      !refcount_read(&kvm->users_count));
+	return rcu_dereference_protected(kvm->buses[idx],
+					 lockdep_is_held(&kvm->slots_lock));
 }
 
 static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 {
 	int num_vcpus = atomic_read(&kvm->online_vcpus);
+
+	/*
+	 * Explicitly verify the target vCPU is online, as the anti-speculation
+	 * logic only limits the CPU's ability to speculate, e.g. given a "bad"
+	 * index, clamping the index to 0 would return vCPU0, not NULL.
+	 */
+	if (i >= num_vcpus)
+		return NULL;
+
 	i = array_index_nospec(i, num_vcpus);
 
 	/* Pairs with smp_wmb() in kvm_vm_ioctl_create_vcpu.  */
@@ -906,9 +1008,10 @@ static inline struct kvm_vcpu *kvm_get_vcpu(struct kvm *kvm, int i)
 	return xa_load(&kvm->vcpu_array, i);
 }
 
-#define kvm_for_each_vcpu(idx, vcpup, kvm)		   \
-	xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0, \
-			  (atomic_read(&kvm->online_vcpus) - 1))
+#define kvm_for_each_vcpu(idx, vcpup, kvm)				\
+	if (atomic_read(&kvm->online_vcpus))				\
+		xa_for_each_range(&kvm->vcpu_array, idx, vcpup, 0,	\
+				  (atomic_read(&kvm->online_vcpus) - 1))
 
 static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 {
@@ -929,22 +1032,22 @@ static inline struct kvm_vcpu *kvm_get_vcpu_by_id(struct kvm *kvm, int id)
 
 void kvm_destroy_vcpus(struct kvm *kvm);
 
+int kvm_trylock_all_vcpus(struct kvm *kvm);
+int kvm_lock_all_vcpus(struct kvm *kvm);
+void kvm_unlock_all_vcpus(struct kvm *kvm);
+
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_KVM_IOAPIC
 void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm);
-void kvm_arch_post_irq_routing_update(struct kvm *kvm);
 #else
 static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
 {
 }
-static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
-{
-}
 #endif
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd_init(void);
 void kvm_irqfd_exit(void);
 #else
@@ -968,7 +1071,7 @@ void kvm_put_kvm_no_destroy(struct kvm *kvm);
 
 static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id)
 {
-	as_id = array_index_nospec(as_id, KVM_ADDRESS_SPACE_NUM);
+	as_id = array_index_nospec(as_id, KVM_MAX_NR_ADDRESS_SPACES);
 	return srcu_dereference_check(kvm->memslots[as_id], &kvm->srcu,
 			lockdep_is_held(&kvm->slots_lock) ||
 			!refcount_read(&kvm->users_count));
@@ -991,6 +1094,8 @@ static inline bool kvm_memslots_empty(struct kvm_memslots *slots)
 	return RB_EMPTY_ROOT(&slots->gfn_tree);
 }
 
+bool kvm_are_all_memslots_empty(struct kvm *kvm);
+
 #define kvm_for_each_memslot(memslot, bkt, slots)			      \
 	hash_for_each(slots->id_hash, bkt, memslot, id_node[slots->node_idx]) \
 		if (WARN_ON_ONCE(!memslot->npages)) {			      \
@@ -1104,6 +1209,10 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_
 	     kvm_memslot_iter_is_valid(iter, end);			\
 	     kvm_memslot_iter_next(iter))
 
+struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
+struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
+struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
+
 /*
  * KVM_SET_USER_MEMORY_REGION ioctl allows the following operations:
  * - create a new memory slot
@@ -1113,7 +1222,7 @@ static inline bool kvm_memslot_iter_is_valid(struct kvm_memslot_iter *iter, gfn_
  *   -- just change its flags
  *
  * Since flags can be changed by some of these operations, the following
- * differentiation is the best we can do for __kvm_set_memory_region():
+ * differentiation is the best we can do for kvm_set_memory_region():
  */
 enum kvm_mr_change {
 	KVM_MR_CREATE,
@@ -1122,10 +1231,8 @@ enum kvm_mr_change {
 	KVM_MR_FLAGS_ONLY,
 };
 
-int kvm_set_memory_region(struct kvm *kvm,
-			  const struct kvm_userspace_memory_region *mem);
-int __kvm_set_memory_region(struct kvm *kvm,
-			    const struct kvm_userspace_memory_region *mem);
+int kvm_set_internal_memslot(struct kvm *kvm,
+			     const struct kvm_userspace_memory_region2 *mem);
 void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot);
 void kvm_arch_memslots_updated(struct kvm *kvm, u64 gen);
 int kvm_arch_prepare_memory_region(struct kvm *kvm,
@@ -1142,33 +1249,70 @@ void kvm_arch_flush_shadow_all(struct kvm *kvm);
 void kvm_arch_flush_shadow_memslot(struct kvm *kvm,
 				   struct kvm_memory_slot *slot);
 
-int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn,
-			    struct page **pages, int nr_pages);
+int kvm_prefetch_pages(struct kvm_memory_slot *slot, gfn_t gfn,
+		       struct page **pages, int nr_pages);
+
+struct page *__gfn_to_page(struct kvm *kvm, gfn_t gfn, bool write);
+static inline struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
+{
+	return __gfn_to_page(kvm, gfn, true);
+}
 
-struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn);
 unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable);
 unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn);
 unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn,
 				      bool *writable);
+
+static inline void kvm_release_page_unused(struct page *page)
+{
+	if (!page)
+		return;
+
+	put_page(page);
+}
+
 void kvm_release_page_clean(struct page *page);
 void kvm_release_page_dirty(struct page *page);
 
-kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn);
-kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
-		      bool *writable);
-kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn);
-kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn);
-kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
-			       bool atomic, bool interruptible, bool *async,
-			       bool write_fault, bool *writable, hva_t *hva);
-
-void kvm_release_pfn_clean(kvm_pfn_t pfn);
-void kvm_release_pfn_dirty(kvm_pfn_t pfn);
-void kvm_set_pfn_dirty(kvm_pfn_t pfn);
-void kvm_set_pfn_accessed(kvm_pfn_t pfn);
-
-void kvm_release_pfn(kvm_pfn_t pfn, bool dirty);
+static inline void kvm_release_faultin_page(struct kvm *kvm, struct page *page,
+					    bool unused, bool dirty)
+{
+	lockdep_assert_once(lockdep_is_held(&kvm->mmu_lock) || unused);
+
+	if (!page)
+		return;
+
+	/*
+	 * If the page that KVM got from the *primary MMU* is writable, and KVM
+	 * installed or reused a SPTE, mark the page/folio dirty.  Note, this
+	 * may mark a folio dirty even if KVM created a read-only SPTE, e.g. if
+	 * the GFN is write-protected.  Folios can't be safely marked dirty
+	 * outside of mmu_lock as doing so could race with writeback on the
+	 * folio.  As a result, KVM can't mark folios dirty in the fast page
+	 * fault handler, and so KVM must (somewhat) speculatively mark the
+	 * folio dirty if KVM could locklessly make the SPTE writable.
+	 */
+	if (unused)
+		kvm_release_page_unused(page);
+	else if (dirty)
+		kvm_release_page_dirty(page);
+	else
+		kvm_release_page_clean(page);
+}
+
+kvm_pfn_t __kvm_faultin_pfn(const struct kvm_memory_slot *slot, gfn_t gfn,
+			    unsigned int foll, bool *writable,
+			    struct page **refcounted_page);
+
+static inline kvm_pfn_t kvm_faultin_pfn(struct kvm_vcpu *vcpu, gfn_t gfn,
+					bool write, bool *writable,
+					struct page **refcounted_page)
+{
+	return __kvm_faultin_pfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn,
+				 write ? FOLL_WRITE : 0, writable, refcounted_page);
+}
+
 int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 			int len);
 int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len);
@@ -1232,19 +1376,28 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 })
 
 int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len);
-struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn);
 bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn);
 bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn);
 void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn);
 void mark_page_dirty(struct kvm *kvm, gfn_t gfn);
 
-struct kvm_memslots *kvm_vcpu_memslots(struct kvm_vcpu *vcpu);
-struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn);
-kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn);
-int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map);
-void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty);
+int __kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa, struct kvm_host_map *map,
+		   bool writable);
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map);
+
+static inline int kvm_vcpu_map(struct kvm_vcpu *vcpu, gpa_t gpa,
+			       struct kvm_host_map *map)
+{
+	return __kvm_vcpu_map(vcpu, gpa, map, true);
+}
+
+static inline int kvm_vcpu_map_readonly(struct kvm_vcpu *vcpu, gpa_t gpa,
+					struct kvm_host_map *map)
+{
+	return __kvm_vcpu_map(vcpu, gpa, map, false);
+}
+
 unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn);
 unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable);
 int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset,
@@ -1264,21 +1417,12 @@ void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn);
  *
  * @gpc:	   struct gfn_to_pfn_cache object.
  * @kvm:	   pointer to kvm instance.
- * @vcpu:	   vCPU to be used for marking pages dirty and to be woken on
- *		   invalidation.
- * @usage:	   indicates if the resulting host physical PFN is used while
- *		   the @vcpu is IN_GUEST_MODE (in which case invalidation of 
- *		   the cache from MMU notifiers---but not for KVM memslot
- *		   changes!---will also force @vcpu to exit the guest and
- *		   refresh the cache); and/or if the PFN used directly
- *		   by KVM (and thus needs a kernel virtual mapping).
  *
  * This sets up a gfn_to_pfn_cache by initializing locks and assigning the
  * immutable attributes.  Note, the cache must be zero-allocated (or zeroed by
  * the caller before init).
  */
-void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm,
-		  struct kvm_vcpu *vcpu, enum pfn_cache_usage usage);
+void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm);
 
 /**
  * kvm_gpc_activate - prepare a cached kernel mapping and HPA for a given guest
@@ -1299,6 +1443,22 @@ void kvm_gpc_init(struct gfn_to_pfn_cache *gpc, struct kvm *kvm,
 int kvm_gpc_activate(struct gfn_to_pfn_cache *gpc, gpa_t gpa, unsigned long len);
 
 /**
+ * kvm_gpc_activate_hva - prepare a cached kernel mapping and HPA for a given HVA.
+ *
+ * @gpc:          struct gfn_to_pfn_cache object.
+ * @hva:          userspace virtual address to map.
+ * @len:          sanity check; the range being access must fit a single page.
+ *
+ * @return:       0 for success.
+ *                -EINVAL for a mapping which would cross a page boundary.
+ *                -EFAULT for an untranslatable guest physical address.
+ *
+ * The semantics of this function are the same as those of kvm_gpc_activate(). It
+ * merely bypasses a layer of address translation.
+ */
+int kvm_gpc_activate_hva(struct gfn_to_pfn_cache *gpc, unsigned long hva, unsigned long len);
+
+/**
  * kvm_gpc_check - check validity of a gfn_to_pfn_cache.
  *
  * @gpc:	   struct gfn_to_pfn_cache object.
@@ -1344,6 +1504,16 @@ int kvm_gpc_refresh(struct gfn_to_pfn_cache *gpc, unsigned long len);
  */
 void kvm_gpc_deactivate(struct gfn_to_pfn_cache *gpc);
 
+static inline bool kvm_gpc_is_gpa_active(struct gfn_to_pfn_cache *gpc)
+{
+	return gpc->active && !kvm_is_error_gpa(gpc->gpa);
+}
+
+static inline bool kvm_gpc_is_hva_active(struct gfn_to_pfn_cache *gpc)
+{
+	return gpc->active && kvm_is_error_gpa(gpc->gpa);
+}
+
 void kvm_sigset_activate(struct kvm_vcpu *vcpu);
 void kvm_sigset_deactivate(struct kvm_vcpu *vcpu);
 
@@ -1352,11 +1522,23 @@ bool kvm_vcpu_block(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_blocking(struct kvm_vcpu *vcpu);
 void kvm_arch_vcpu_unblocking(struct kvm_vcpu *vcpu);
 bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu);
-void kvm_vcpu_kick(struct kvm_vcpu *vcpu);
+
+#ifndef CONFIG_S390
+void __kvm_vcpu_kick(struct kvm_vcpu *vcpu, bool wait);
+
+static inline void kvm_vcpu_kick(struct kvm_vcpu *vcpu)
+{
+	__kvm_vcpu_kick(vcpu, false);
+}
+#endif
+
 int kvm_vcpu_yield_to(struct kvm_vcpu *target);
 void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu, bool yield_to_kernel_mode);
 
 void kvm_flush_remote_tlbs(struct kvm *kvm);
+void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
+void kvm_flush_remote_tlbs_memslot(struct kvm *kvm,
+				   const struct kvm_memory_slot *memslot);
 
 #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE
 int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min);
@@ -1366,15 +1548,17 @@ void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc);
 void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc);
 #endif
 
-void kvm_mmu_invalidate_begin(struct kvm *kvm, unsigned long start,
-			      unsigned long end);
-void kvm_mmu_invalidate_end(struct kvm *kvm, unsigned long start,
-			    unsigned long end);
+void kvm_mmu_invalidate_begin(struct kvm *kvm);
+void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end);
+void kvm_mmu_invalidate_end(struct kvm *kvm);
+bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range);
 
 long kvm_arch_dev_ioctl(struct file *filp,
 			unsigned int ioctl, unsigned long arg);
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg);
+long kvm_arch_vcpu_unlocked_ioctl(struct file *filp,
+				  unsigned int ioctl, unsigned long arg);
 vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf);
 
 int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext);
@@ -1385,10 +1569,7 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
 					unsigned long mask);
 void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot);
 
-#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
-void kvm_arch_flush_remote_tlbs_memslot(struct kvm *kvm,
-					const struct kvm_memory_slot *memslot);
-#else /* !CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */
+#ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
 int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log);
 int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log,
 		      int *is_dirty, struct kvm_memory_slot **memslot);
@@ -1422,8 +1603,6 @@ int kvm_arch_vcpu_ioctl_set_guest_debug(struct kvm_vcpu *vcpu,
 					struct kvm_guest_debug *dbg);
 int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu);
 
-void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu);
-
 void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id);
@@ -1442,17 +1621,32 @@ static inline void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) {}
 #endif
 
 #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
-int kvm_arch_hardware_enable(void);
-void kvm_arch_hardware_disable(void);
+/*
+ * kvm_arch_{enable,disable}_virtualization() are called on one CPU, under
+ * kvm_usage_lock, immediately after/before 0=>1 and 1=>0 transitions of
+ * kvm_usage_count, i.e. at the beginning of the generic hardware enabling
+ * sequence, and at the end of the generic hardware disabling sequence.
+ */
+void kvm_arch_enable_virtualization(void);
+void kvm_arch_disable_virtualization(void);
+/*
+ * kvm_arch_{enable,disable}_virtualization_cpu() are called on "every" CPU to
+ * do the actual twiddling of hardware bits.  The hooks are called on all
+ * online CPUs when KVM enables/disabled virtualization, and on a single CPU
+ * when that CPU is onlined/offlined (including for Resume/Suspend).
+ */
+int kvm_arch_enable_virtualization_cpu(void);
+void kvm_arch_disable_virtualization_cpu(void);
 #endif
+bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_vcpu_in_kernel(struct kvm_vcpu *vcpu);
 int kvm_arch_vcpu_should_kick(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_runnable(struct kvm_vcpu *vcpu);
 bool kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu);
-int kvm_arch_post_init_vm(struct kvm *kvm);
+bool kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu);
 void kvm_arch_pre_destroy_vm(struct kvm *kvm);
-int kvm_arch_create_vm_debugfs(struct kvm *kvm);
+void kvm_arch_create_vm_debugfs(struct kvm *kvm);
 
 #ifndef __KVM_HAVE_ARCH_VM_ALLOC
 /*
@@ -1477,11 +1671,23 @@ static inline void kvm_arch_free_vm(struct kvm *kvm)
 }
 #endif
 
-#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLB
-static inline int kvm_arch_flush_remote_tlb(struct kvm *kvm)
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS
+static inline int kvm_arch_flush_remote_tlbs(struct kvm *kvm)
 {
 	return -ENOTSUPP;
 }
+#else
+int kvm_arch_flush_remote_tlbs(struct kvm *kvm);
+#endif
+
+#ifndef __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE
+static inline int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm,
+						    gfn_t gfn, u64 nr_pages)
+{
+	return -EOPNOTSUPP;
+}
+#else
+int kvm_arch_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages);
 #endif
 
 #ifdef __KVM_HAVE_ARCH_NONCOHERENT_DMA
@@ -1502,24 +1708,6 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 	return false;
 }
 #endif
-#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE
-void kvm_arch_start_assignment(struct kvm *kvm);
-void kvm_arch_end_assignment(struct kvm *kvm);
-bool kvm_arch_has_assigned_device(struct kvm *kvm);
-#else
-static inline void kvm_arch_start_assignment(struct kvm *kvm)
-{
-}
-
-static inline void kvm_arch_end_assignment(struct kvm *kvm)
-{
-}
-
-static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
-{
-	return false;
-}
-#endif
 
 static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu)
 {
@@ -1570,13 +1758,9 @@ static inline void kvm_unregister_perf_callbacks(void) {}
 
 int kvm_arch_init_vm(struct kvm *kvm, unsigned long type);
 void kvm_arch_destroy_vm(struct kvm *kvm);
-void kvm_arch_sync_events(struct kvm *kvm);
 
 int kvm_cpu_has_pending_timer(struct kvm_vcpu *vcpu);
 
-struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn);
-bool kvm_is_zone_device_page(struct page *page);
-
 struct kvm_irq_ack_notifier {
 	struct hlist_node link;
 	unsigned gsi;
@@ -1601,8 +1785,6 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
 void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
-int kvm_request_irq_source_id(struct kvm *kvm);
-void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 
 /*
@@ -1721,11 +1903,21 @@ static inline hpa_t pfn_to_hpa(kvm_pfn_t pfn)
 	return (hpa_t)pfn << PAGE_SHIFT;
 }
 
-static inline bool kvm_is_error_gpa(struct kvm *kvm, gpa_t gpa)
+static inline bool kvm_is_gpa_in_memslot(struct kvm *kvm, gpa_t gpa)
 {
 	unsigned long hva = gfn_to_hva(kvm, gpa_to_gfn(gpa));
 
-	return kvm_is_error_hva(hva);
+	return !kvm_is_error_hva(hva);
+}
+
+static inline void kvm_gpc_mark_dirty_in_slot(struct gfn_to_pfn_cache *gpc)
+{
+	lockdep_assert_held(&gpc->lock);
+
+	if (!gpc->memslot)
+		return;
+
+	mark_page_dirty_in_slot(gpc->kvm, gpc->memslot, gpa_to_gfn(gpc->gpa));
 }
 
 enum kvm_stat_kind {
@@ -1860,8 +2052,6 @@ struct _kvm_stats_desc {
 			HALT_POLL_HIST_COUNT),				       \
 	STATS_DESC_IBOOLEAN(VCPU_GENERIC, blocking)
 
-extern struct dentry *kvm_debugfs_dir;
-
 ssize_t kvm_stats_read(char *id, const struct kvm_stats_header *header,
 		       const struct _kvm_stats_desc *desc,
 		       void *stats, size_t size_stats,
@@ -1912,7 +2102,7 @@ extern const struct _kvm_stats_desc kvm_vm_stats_desc[];
 extern const struct kvm_stats_header kvm_vcpu_stats_header;
 extern const struct _kvm_stats_desc kvm_vcpu_stats_desc[];
 
-#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+#ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER
 static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 {
 	if (unlikely(kvm->mmu_invalidate_in_progress))
@@ -1935,9 +2125,9 @@ static inline int mmu_invalidate_retry(struct kvm *kvm, unsigned long mmu_seq)
 	return 0;
 }
 
-static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
+static inline int mmu_invalidate_retry_gfn(struct kvm *kvm,
 					   unsigned long mmu_seq,
-					   unsigned long hva)
+					   gfn_t gfn)
 {
 	lockdep_assert_held(&kvm->mmu_lock);
 	/*
@@ -1946,14 +2136,50 @@ static inline int mmu_invalidate_retry_hva(struct kvm *kvm,
 	 * that might be being invalidated. Note that it may include some false
 	 * positives, due to shortcuts when handing concurrent invalidations.
 	 */
-	if (unlikely(kvm->mmu_invalidate_in_progress) &&
-	    hva >= kvm->mmu_invalidate_range_start &&
-	    hva < kvm->mmu_invalidate_range_end)
-		return 1;
+	if (unlikely(kvm->mmu_invalidate_in_progress)) {
+		/*
+		 * Dropping mmu_lock after bumping mmu_invalidate_in_progress
+		 * but before updating the range is a KVM bug.
+		 */
+		if (WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA ||
+				 kvm->mmu_invalidate_range_end == INVALID_GPA))
+			return 1;
+
+		if (gfn >= kvm->mmu_invalidate_range_start &&
+		    gfn < kvm->mmu_invalidate_range_end)
+			return 1;
+	}
+
 	if (kvm->mmu_invalidate_seq != mmu_seq)
 		return 1;
 	return 0;
 }
+
+/*
+ * This lockless version of the range-based retry check *must* be paired with a
+ * call to the locked version after acquiring mmu_lock, i.e. this is safe to
+ * use only as a pre-check to avoid contending mmu_lock.  This version *will*
+ * get false negatives and false positives.
+ */
+static inline bool mmu_invalidate_retry_gfn_unsafe(struct kvm *kvm,
+						   unsigned long mmu_seq,
+						   gfn_t gfn)
+{
+	/*
+	 * Use READ_ONCE() to ensure the in-progress flag and sequence counter
+	 * are always read from memory, e.g. so that checking for retry in a
+	 * loop won't result in an infinite retry loop.  Don't force loads for
+	 * start+end, as the key to avoiding infinite retry loops is observing
+	 * the 1=>0 transition of in-progress, i.e. getting false negatives
+	 * due to stale start+end values is acceptable.
+	 */
+	if (unlikely(READ_ONCE(kvm->mmu_invalidate_in_progress)) &&
+	    gfn >= kvm->mmu_invalidate_range_start &&
+	    gfn < kvm->mmu_invalidate_range_end)
+		return true;
+
+	return READ_ONCE(kvm->mmu_invalidate_seq) != mmu_seq;
+}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING
@@ -1965,6 +2191,7 @@ int kvm_set_irq_routing(struct kvm *kvm,
 			const struct kvm_irq_routing_entry *entries,
 			unsigned nr,
 			unsigned flags);
+int kvm_init_irq_routing(struct kvm *kvm);
 int kvm_set_routing_entry(struct kvm *kvm,
 			  struct kvm_kernel_irq_routing_entry *e,
 			  const struct kvm_irq_routing_entry *ue);
@@ -1974,16 +2201,19 @@ void kvm_free_irq_routing(struct kvm *kvm);
 
 static inline void kvm_free_irq_routing(struct kvm *kvm) {}
 
+static inline int kvm_init_irq_routing(struct kvm *kvm)
+{
+	return 0;
+}
+
 #endif
 
 int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi);
 
-#ifdef CONFIG_HAVE_KVM_EVENTFD
-
 void kvm_eventfd_init(struct kvm *kvm);
 int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args);
 
-#ifdef CONFIG_HAVE_KVM_IRQFD
+#ifdef CONFIG_HAVE_KVM_IRQCHIP
 int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args);
 void kvm_irqfd_release(struct kvm *kvm);
 bool kvm_notify_irqfd_resampler(struct kvm *kvm,
@@ -2004,31 +2234,7 @@ static inline bool kvm_notify_irqfd_resampler(struct kvm *kvm,
 {
 	return false;
 }
-#endif
-
-#else
-
-static inline void kvm_eventfd_init(struct kvm *kvm) {}
-
-static inline int kvm_irqfd(struct kvm *kvm, struct kvm_irqfd *args)
-{
-	return -EINVAL;
-}
-
-static inline void kvm_irqfd_release(struct kvm *kvm) {}
-
-#ifdef CONFIG_HAVE_KVM_IRQCHIP
-static inline void kvm_irq_routing_update(struct kvm *kvm)
-{
-}
-#endif
-
-static inline int kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
-{
-	return -ENOSYS;
-}
-
-#endif /* CONFIG_HAVE_KVM_EVENTFD */
+#endif /* CONFIG_HAVE_KVM_IRQCHIP */
 
 void kvm_arch_irq_routing_update(struct kvm *kvm);
 
@@ -2055,6 +2261,14 @@ static __always_inline void kvm_make_request(int req, struct kvm_vcpu *vcpu)
 	__kvm_make_request(req, vcpu);
 }
 
+#ifndef CONFIG_S390
+static inline void kvm_make_request_and_kick(int req, struct kvm_vcpu *vcpu)
+{
+	kvm_make_request(req, vcpu);
+	__kvm_vcpu_kick(vcpu, req & KVM_REQUEST_WAIT);
+}
+#endif
+
 static inline bool kvm_request_pending(struct kvm_vcpu *vcpu)
 {
 	return READ_ONCE(vcpu->requests);
@@ -2087,6 +2301,7 @@ static inline bool kvm_check_request(int req, struct kvm_vcpu *vcpu)
 }
 
 #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
+extern bool enable_virt_at_load;
 extern bool kvm_rebooting;
 #endif
 
@@ -2146,8 +2361,6 @@ struct kvm_device_ops {
 	int (*mmap)(struct kvm_device *dev, struct vm_area_struct *vma);
 };
 
-void kvm_device_get(struct kvm_device *dev);
-void kvm_device_put(struct kvm_device *dev);
 struct kvm_device *kvm_device_from_filp(struct file *filp);
 int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type);
 void kvm_unregister_device_ops(u32 type);
@@ -2187,7 +2400,9 @@ static inline bool kvm_is_visible_memslot(struct kvm_memory_slot *memslot)
 struct kvm_vcpu *kvm_get_running_vcpu(void);
 struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
-#ifdef CONFIG_HAVE_KVM_IRQ_BYPASS
+#if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
+struct kvm_kernel_irqfd;
+
 bool kvm_arch_has_irq_bypass(void);
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
 			   struct irq_bypass_producer *);
@@ -2195,10 +2410,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *,
 			   struct irq_bypass_producer *);
 void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *);
 void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
-int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
-				  uint32_t guest_irq, bool set);
-bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *,
-				  struct kvm_kernel_irq_routing_entry *);
+void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				   struct kvm_kernel_irq_routing_entry *old,
+				   struct kvm_kernel_irq_routing_entry *new);
 #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
 
 #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS
@@ -2225,21 +2439,6 @@ static inline bool kvm_arch_no_poll(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_HAVE_KVM_NO_POLL */
 
-#ifdef CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL
-long kvm_arch_vcpu_async_ioctl(struct file *filp,
-			       unsigned int ioctl, unsigned long arg);
-#else
-static inline long kvm_arch_vcpu_async_ioctl(struct file *filp,
-					     unsigned int ioctl,
-					     unsigned long arg)
-{
-	return -ENOIOCTLCMD;
-}
-#endif /* CONFIG_HAVE_KVM_VCPU_ASYNC_IOCTL */
-
-void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
-					    unsigned long start, unsigned long end);
-
 void kvm_arch_guest_memory_reclaimed(struct kvm *kvm);
 
 #ifdef CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE
@@ -2251,19 +2450,24 @@ static inline int kvm_arch_vcpu_run_pid_change(struct kvm_vcpu *vcpu)
 }
 #endif /* CONFIG_HAVE_KVM_VCPU_RUN_PID_CHANGE */
 
-typedef int (*kvm_vm_thread_fn_t)(struct kvm *kvm, uintptr_t data);
-
-int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
-				uintptr_t data, const char *name,
-				struct task_struct **thread_ptr);
-
-#ifdef CONFIG_KVM_XFER_TO_GUEST_WORK
+#ifdef CONFIG_VIRT_XFER_TO_GUEST_WORK
 static inline void kvm_handle_signal_exit(struct kvm_vcpu *vcpu)
 {
 	vcpu->run->exit_reason = KVM_EXIT_INTR;
 	vcpu->stat.signal_exits++;
 }
-#endif /* CONFIG_KVM_XFER_TO_GUEST_WORK */
+
+static inline int kvm_xfer_to_guest_mode_handle_work(struct kvm_vcpu *vcpu)
+{
+	int r = xfer_to_guest_mode_handle_work();
+
+	if (r) {
+		WARN_ON_ONCE(r != -EINTR);
+		kvm_handle_signal_exit(vcpu);
+	}
+	return r;
+}
+#endif /* CONFIG_VIRT_XFER_TO_GUEST_WORK */
 
 /*
  * If more than one page is being (un)accounted, @virt must be the address of
@@ -2288,4 +2492,116 @@ static inline void kvm_account_pgtable_pages(void *virt, int nr)
 /* Max number of entries allowed for each kvm dirty ring */
 #define  KVM_DIRTY_RING_MAX_ENTRIES  65536
 
+static inline void kvm_prepare_memory_fault_exit(struct kvm_vcpu *vcpu,
+						 gpa_t gpa, gpa_t size,
+						 bool is_write, bool is_exec,
+						 bool is_private)
+{
+	vcpu->run->exit_reason = KVM_EXIT_MEMORY_FAULT;
+	vcpu->run->memory_fault.gpa = gpa;
+	vcpu->run->memory_fault.size = size;
+
+	/* RWX flags are not (yet) defined or communicated to userspace. */
+	vcpu->run->memory_fault.flags = 0;
+	if (is_private)
+		vcpu->run->memory_fault.flags |= KVM_MEMORY_EXIT_FLAG_PRIVATE;
+}
+
+static inline bool kvm_memslot_is_gmem_only(const struct kvm_memory_slot *slot)
+{
+	if (!IS_ENABLED(CONFIG_KVM_GUEST_MEMFD))
+		return false;
+
+	return slot->flags & KVM_MEMSLOT_GMEM_ONLY;
+}
+
+#ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES
+static inline unsigned long kvm_get_memory_attributes(struct kvm *kvm, gfn_t gfn)
+{
+	return xa_to_value(xa_load(&kvm->mem_attr_array, gfn));
+}
+
+bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end,
+				     unsigned long mask, unsigned long attrs);
+bool kvm_arch_pre_set_memory_attributes(struct kvm *kvm,
+					struct kvm_gfn_range *range);
+bool kvm_arch_post_set_memory_attributes(struct kvm *kvm,
+					 struct kvm_gfn_range *range);
+
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return kvm_get_memory_attributes(kvm, gfn) & KVM_MEMORY_ATTRIBUTE_PRIVATE;
+}
+#else
+static inline bool kvm_mem_is_private(struct kvm *kvm, gfn_t gfn)
+{
+	return false;
+}
+#endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */
+
+#ifdef CONFIG_KVM_GUEST_MEMFD
+int kvm_gmem_get_pfn(struct kvm *kvm, struct kvm_memory_slot *slot,
+		     gfn_t gfn, kvm_pfn_t *pfn, struct page **page,
+		     int *max_order);
+#else
+static inline int kvm_gmem_get_pfn(struct kvm *kvm,
+				   struct kvm_memory_slot *slot, gfn_t gfn,
+				   kvm_pfn_t *pfn, struct page **page,
+				   int *max_order)
+{
+	KVM_BUG_ON(1, kvm);
+	return -EIO;
+}
+#endif /* CONFIG_KVM_GUEST_MEMFD */
+
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_PREPARE
+int kvm_arch_gmem_prepare(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn, int max_order);
+#endif
+
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_POPULATE
+/**
+ * kvm_gmem_populate() - Populate/prepare a GPA range with guest data
+ *
+ * @kvm: KVM instance
+ * @gfn: starting GFN to be populated
+ * @src: userspace-provided buffer containing data to copy into GFN range
+ *       (passed to @post_populate, and incremented on each iteration
+ *       if not NULL)
+ * @npages: number of pages to copy from userspace-buffer
+ * @post_populate: callback to issue for each gmem page that backs the GPA
+ *                 range
+ * @opaque: opaque data to pass to @post_populate callback
+ *
+ * This is primarily intended for cases where a gmem-backed GPA range needs
+ * to be initialized with userspace-provided data prior to being mapped into
+ * the guest as a private page. This should be called with the slots->lock
+ * held so that caller-enforced invariants regarding the expected memory
+ * attributes of the GPA range do not race with KVM_SET_MEMORY_ATTRIBUTES.
+ *
+ * Returns the number of pages that were populated.
+ */
+typedef int (*kvm_gmem_populate_cb)(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+				    void __user *src, int order, void *opaque);
+
+long kvm_gmem_populate(struct kvm *kvm, gfn_t gfn, void __user *src, long npages,
+		       kvm_gmem_populate_cb post_populate, void *opaque);
+#endif
+
+#ifdef CONFIG_HAVE_KVM_ARCH_GMEM_INVALIDATE
+void kvm_arch_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
+#endif
+
+#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
+long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+				    struct kvm_pre_fault_memory *range);
+#endif
+
+#ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING
+int kvm_enable_virtualization(void);
+void kvm_disable_virtualization(void);
+#else
+static inline int kvm_enable_virtualization(void) { return 0; }
+static inline void kvm_disable_virtualization(void) { }
+#endif
+
 #endif
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 8ad43692e3bb..ef8c134ded8a 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -55,10 +55,13 @@ struct kvm_kernel_irqfd {
 	/* Used for setup/shutdown */
 	struct eventfd_ctx *eventfd;
 	struct list_head list;
-	poll_table pt;
 	struct work_struct shutdown;
 	struct irq_bypass_consumer consumer;
 	struct irq_bypass_producer *producer;
+
+	struct kvm_vcpu *irq_bypass_vcpu;
+	struct list_head vcpu_list;
+	void *irq_bypass_data;
 };
 
 #endif /* __LINUX_KVM_IRQFD_H */
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 6f4737d5046a..a568d8e6f4e8 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -3,9 +3,41 @@
 #ifndef __KVM_TYPES_H__
 #define __KVM_TYPES_H__
 
+#include <linux/bits.h>
+#include <linux/export.h>
+#include <linux/types.h>
+#include <asm/kvm_types.h>
+
+#ifdef KVM_SUB_MODULES
+#define EXPORT_SYMBOL_FOR_KVM_INTERNAL(symbol) \
+	EXPORT_SYMBOL_FOR_MODULES(symbol, __stringify(KVM_SUB_MODULES))
+#define EXPORT_SYMBOL_FOR_KVM(symbol) \
+	EXPORT_SYMBOL_FOR_MODULES(symbol, "kvm," __stringify(KVM_SUB_MODULES))
+#else
+#define EXPORT_SYMBOL_FOR_KVM_INTERNAL(symbol)
+/*
+ * Allow architectures to provide a custom EXPORT_SYMBOL_FOR_KVM, but only
+ * if there are no submodules, e.g. to allow suppressing exports if KVM=m, but
+ * kvm.ko won't actually be built (due to lack of at least one submodule).
+ */
+#ifndef EXPORT_SYMBOL_FOR_KVM
+#if IS_MODULE(CONFIG_KVM)
+#define EXPORT_SYMBOL_FOR_KVM(symbol) EXPORT_SYMBOL_FOR_MODULES(symbol, "kvm")
+#else
+#define EXPORT_SYMBOL_FOR_KVM(symbol)
+#endif /* IS_MODULE(CONFIG_KVM) */
+#endif /* EXPORT_SYMBOL_FOR_KVM */
+#endif
+
+#ifndef __ASSEMBLER__
+
+#include <linux/mutex.h>
+#include <linux/spinlock_types.h>
+
 struct kvm;
 struct kvm_async_pf;
 struct kvm_device_ops;
+struct kvm_gfn_range;
 struct kvm_interrupt;
 struct kvm_irq_routing_table;
 struct kvm_memory_slot;
@@ -18,13 +50,6 @@ struct kvm_memslots;
 
 enum kvm_mr_change;
 
-#include <linux/bits.h>
-#include <linux/mutex.h>
-#include <linux/types.h>
-#include <linux/spinlock_types.h>
-
-#include <asm/kvm_types.h>
-
 /*
  * Address types:
  *
@@ -48,12 +73,6 @@ typedef u64            hfn_t;
 
 typedef hfn_t kvm_pfn_t;
 
-enum pfn_cache_usage {
-	KVM_GUEST_USES_PFN = BIT(0),
-	KVM_HOST_USES_PFN  = BIT(1),
-	KVM_GUEST_AND_HOST_USE_PFN = KVM_GUEST_USES_PFN | KVM_HOST_USES_PFN,
-};
-
 struct gfn_to_hva_cache {
 	u64 generation;
 	gpa_t gpa;
@@ -68,13 +87,11 @@ struct gfn_to_pfn_cache {
 	unsigned long uhva;
 	struct kvm_memory_slot *memslot;
 	struct kvm *kvm;
-	struct kvm_vcpu *vcpu;
 	struct list_head list;
 	rwlock_t lock;
 	struct mutex refresh_lock;
 	void *khva;
 	kvm_pfn_t pfn;
-	enum pfn_cache_usage usage;
 	bool active;
 	bool valid;
 };
@@ -93,6 +110,7 @@ struct gfn_to_pfn_cache {
 struct kvm_mmu_memory_cache {
 	gfp_t gfp_zero;
 	gfp_t gfp_custom;
+	u64 init_value;
 	struct kmem_cache *kmem_cache;
 	int capacity;
 	int nobjs;
@@ -122,5 +140,6 @@ struct kvm_vcpu_stat_generic {
 };
 
 #define KVM_STATS_NAME_SIZE	48
+#endif /* !__ASSEMBLER__ */
 
 #endif /* __KVM_TYPES_H__ */
diff --git a/include/linux/lcd.h b/include/linux/lcd.h
index 238fb1dfed98..d4fa03722b72 100644
--- a/include/linux/lcd.h
+++ b/include/linux/lcd.h
@@ -11,8 +11,11 @@
 
 #include <linux/device.h>
 #include <linux/mutex.h>
-#include <linux/notifier.h>
-#include <linux/fb.h>
+
+#define LCD_POWER_ON			(0)
+#define LCD_POWER_REDUCED		(1) // deprecated; don't use in new code
+#define LCD_POWER_REDUCED_VSYNC_SUSPEND	(2) // deprecated; don't use in new code
+#define LCD_POWER_OFF			(4)
 
 /* Notes on locking:
  *
@@ -30,7 +33,6 @@
  */
 
 struct lcd_device;
-struct fb_info;
 
 struct lcd_properties {
 	/* The maximum value for contrast (read-only) */
@@ -47,11 +49,23 @@ struct lcd_ops {
 	int (*get_contrast)(struct lcd_device *);
 	/* Set LCD panel contrast */
         int (*set_contrast)(struct lcd_device *, int contrast);
-	/* Set LCD panel mode (resolutions ...) */
-	int (*set_mode)(struct lcd_device *, struct fb_videomode *);
-	/* Check if given framebuffer device is the one LCD is bound to;
-	   return 0 if not, !=0 if it is. If NULL, lcd always matches the fb. */
-	int (*check_fb)(struct lcd_device *, struct fb_info *);
+
+	/*
+	 * Set LCD panel mode (resolutions ...)
+	 */
+	int (*set_mode)(struct lcd_device *lcd, u32 xres, u32 yres);
+
+	/*
+	 * Check if the LCD controls the given display device. This
+	 * operation is optional and if not implemented it is assumed that
+	 * the display is always the one controlled by the LCD.
+	 *
+	 * RETURNS:
+	 *
+	 * If display_dev is NULL or display_dev matches the device controlled by
+	 * the LCD, return true. Otherwise return false.
+	 */
+	bool (*controls_device)(struct lcd_device *lcd, struct device *display_device);
 };
 
 struct lcd_device {
@@ -61,11 +75,14 @@ struct lcd_device {
 	   points to something in the body of that driver, it is also invalid. */
 	struct mutex ops_lock;
 	/* If this is NULL, the backing module is unloaded */
-	struct lcd_ops *ops;
+	const struct lcd_ops *ops;
 	/* Serialise access to set_power method */
 	struct mutex update_lock;
-	/* The framebuffer notifier block */
-	struct notifier_block fb_notif;
+
+	/**
+	 * @entry: List entry of all registered lcd devices
+	 */
+	struct list_head entry;
 
 	struct device dev;
 };
@@ -102,14 +119,27 @@ static inline void lcd_set_power(struct lcd_device *ld, int power)
 }
 
 extern struct lcd_device *lcd_device_register(const char *name,
-	struct device *parent, void *devdata, struct lcd_ops *ops);
+	struct device *parent, void *devdata, const struct lcd_ops *ops);
 extern struct lcd_device *devm_lcd_device_register(struct device *dev,
 	const char *name, struct device *parent,
-	void *devdata, struct lcd_ops *ops);
+	void *devdata, const struct lcd_ops *ops);
 extern void lcd_device_unregister(struct lcd_device *ld);
 extern void devm_lcd_device_unregister(struct device *dev,
 	struct lcd_device *ld);
 
+#if IS_REACHABLE(CONFIG_LCD_CLASS_DEVICE)
+void lcd_notify_blank_all(struct device *display_dev, int power);
+void lcd_notify_mode_change_all(struct device *display_dev,
+				unsigned int width, unsigned int height);
+#else
+static inline void lcd_notify_blank_all(struct device *display_dev, int power)
+{}
+
+static inline void lcd_notify_mode_change_all(struct device *display_dev,
+					      unsigned int width, unsigned int height)
+{}
+#endif
+
 #define to_lcd_device(obj) container_of(obj, struct lcd_device, dev)
 
 static inline void * lcd_get_data(struct lcd_device *ld_dev)
diff --git a/include/linux/leafops.h b/include/linux/leafops.h
new file mode 100644
index 000000000000..cfafe7a5e7b1
--- /dev/null
+++ b/include/linux/leafops.h
@@ -0,0 +1,619 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Describes operations that can be performed on software-defined page table
+ * leaf entries. These are abstracted from the hardware page table entries
+ * themselves by the softleaf_t type, see mm_types.h.
+ */
+#ifndef _LINUX_LEAFOPS_H
+#define _LINUX_LEAFOPS_H
+
+#include <linux/mm_types.h>
+#include <linux/swapops.h>
+#include <linux/swap.h>
+
+#ifdef CONFIG_MMU
+
+/* Temporary until swp_entry_t eliminated. */
+#define LEAF_TYPE_SHIFT SWP_TYPE_SHIFT
+
+enum softleaf_type {
+	/* Fundamental types. */
+	SOFTLEAF_NONE,
+	SOFTLEAF_SWAP,
+	/* Migration types. */
+	SOFTLEAF_MIGRATION_READ,
+	SOFTLEAF_MIGRATION_READ_EXCLUSIVE,
+	SOFTLEAF_MIGRATION_WRITE,
+	/* Device types. */
+	SOFTLEAF_DEVICE_PRIVATE_READ,
+	SOFTLEAF_DEVICE_PRIVATE_WRITE,
+	SOFTLEAF_DEVICE_EXCLUSIVE,
+	/* H/W posion types. */
+	SOFTLEAF_HWPOISON,
+	/* Marker types. */
+	SOFTLEAF_MARKER,
+};
+
+/**
+ * softleaf_mk_none() - Create an empty ('none') leaf entry.
+ * Returns: empty leaf entry.
+ */
+static inline softleaf_t softleaf_mk_none(void)
+{
+	return ((softleaf_t) { 0 });
+}
+
+/**
+ * softleaf_from_pte() - Obtain a leaf entry from a PTE entry.
+ * @pte: PTE entry.
+ *
+ * If @pte is present (therefore not a leaf entry) the function returns an empty
+ * leaf entry. Otherwise, it returns a leaf entry.
+ *
+ * Returns: Leaf entry.
+ */
+static inline softleaf_t softleaf_from_pte(pte_t pte)
+{
+	softleaf_t arch_entry;
+
+	if (pte_present(pte) || pte_none(pte))
+		return softleaf_mk_none();
+
+	pte = pte_swp_clear_flags(pte);
+	arch_entry = __pte_to_swp_entry(pte);
+
+	/* Temporary until swp_entry_t eliminated. */
+	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
+}
+
+/**
+ * softleaf_to_pte() - Obtain a PTE entry from a leaf entry.
+ * @entry: Leaf entry.
+ *
+ * This generates an architecture-specific PTE entry that can be utilised to
+ * encode the metadata the leaf entry encodes.
+ *
+ * Returns: Architecture-specific PTE entry encoding leaf entry.
+ */
+static inline pte_t softleaf_to_pte(softleaf_t entry)
+{
+	/* Temporary until swp_entry_t eliminated. */
+	return swp_entry_to_pte(entry);
+}
+
+#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+/**
+ * softleaf_from_pmd() - Obtain a leaf entry from a PMD entry.
+ * @pmd: PMD entry.
+ *
+ * If @pmd is present (therefore not a leaf entry) the function returns an empty
+ * leaf entry. Otherwise, it returns a leaf entry.
+ *
+ * Returns: Leaf entry.
+ */
+static inline softleaf_t softleaf_from_pmd(pmd_t pmd)
+{
+	softleaf_t arch_entry;
+
+	if (pmd_present(pmd) || pmd_none(pmd))
+		return softleaf_mk_none();
+
+	if (pmd_swp_soft_dirty(pmd))
+		pmd = pmd_swp_clear_soft_dirty(pmd);
+	if (pmd_swp_uffd_wp(pmd))
+		pmd = pmd_swp_clear_uffd_wp(pmd);
+	arch_entry = __pmd_to_swp_entry(pmd);
+
+	/* Temporary until swp_entry_t eliminated. */
+	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
+}
+
+#else
+
+static inline softleaf_t softleaf_from_pmd(pmd_t pmd)
+{
+	return softleaf_mk_none();
+}
+
+#endif
+
+/**
+ * softleaf_is_none() - Is the leaf entry empty?
+ * @entry: Leaf entry.
+ *
+ * Empty entries are typically the result of a 'none' page table leaf entry
+ * being converted to a leaf entry.
+ *
+ * Returns: true if the entry is empty, false otherwise.
+ */
+static inline bool softleaf_is_none(softleaf_t entry)
+{
+	return entry.val == 0;
+}
+
+/**
+ * softleaf_type() - Identify the type of leaf entry.
+ * @enntry: Leaf entry.
+ *
+ * Returns: the leaf entry type associated with @entry.
+ */
+static inline enum softleaf_type softleaf_type(softleaf_t entry)
+{
+	unsigned int type_num;
+
+	if (softleaf_is_none(entry))
+		return SOFTLEAF_NONE;
+
+	type_num = entry.val >> LEAF_TYPE_SHIFT;
+
+	if (type_num < MAX_SWAPFILES)
+		return SOFTLEAF_SWAP;
+
+	switch (type_num) {
+#ifdef CONFIG_MIGRATION
+	case SWP_MIGRATION_READ:
+		return SOFTLEAF_MIGRATION_READ;
+	case SWP_MIGRATION_READ_EXCLUSIVE:
+		return SOFTLEAF_MIGRATION_READ_EXCLUSIVE;
+	case SWP_MIGRATION_WRITE:
+		return SOFTLEAF_MIGRATION_WRITE;
+#endif
+#ifdef CONFIG_DEVICE_PRIVATE
+	case SWP_DEVICE_WRITE:
+		return SOFTLEAF_DEVICE_PRIVATE_WRITE;
+	case SWP_DEVICE_READ:
+		return SOFTLEAF_DEVICE_PRIVATE_READ;
+	case SWP_DEVICE_EXCLUSIVE:
+		return SOFTLEAF_DEVICE_EXCLUSIVE;
+#endif
+#ifdef CONFIG_MEMORY_FAILURE
+	case SWP_HWPOISON:
+		return SOFTLEAF_HWPOISON;
+#endif
+	case SWP_PTE_MARKER:
+		return SOFTLEAF_MARKER;
+	}
+
+	/* Unknown entry type. */
+	VM_WARN_ON_ONCE(1);
+	return SOFTLEAF_NONE;
+}
+
+/**
+ * softleaf_is_swap() - Is this leaf entry a swap entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a swap entry, otherwise false.
+ */
+static inline bool softleaf_is_swap(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_SWAP;
+}
+
+/**
+ * softleaf_is_migration_write() - Is this leaf entry a writable migration entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a writable migration entry, otherwise
+ * false.
+ */
+static inline bool softleaf_is_migration_write(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_MIGRATION_WRITE;
+}
+
+/**
+ * softleaf_is_migration_read() - Is this leaf entry a readable migration entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a readable migration entry, otherwise
+ * false.
+ */
+static inline bool softleaf_is_migration_read(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_MIGRATION_READ;
+}
+
+/**
+ * softleaf_is_migration_read_exclusive() - Is this leaf entry an exclusive
+ * readable migration entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is an exclusive readable migration entry,
+ * otherwise false.
+ */
+static inline bool softleaf_is_migration_read_exclusive(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_MIGRATION_READ_EXCLUSIVE;
+}
+
+/**
+ * softleaf_is_migration() - Is this leaf entry a migration entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a migration entry, otherwise false.
+ */
+static inline bool softleaf_is_migration(softleaf_t entry)
+{
+	switch (softleaf_type(entry)) {
+	case SOFTLEAF_MIGRATION_READ:
+	case SOFTLEAF_MIGRATION_READ_EXCLUSIVE:
+	case SOFTLEAF_MIGRATION_WRITE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * softleaf_is_device_private_write() - Is this leaf entry a device private
+ * writable entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a device private writable entry, otherwise
+ * false.
+ */
+static inline bool softleaf_is_device_private_write(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_DEVICE_PRIVATE_WRITE;
+}
+
+/**
+ * softleaf_is_device_private() - Is this leaf entry a device private entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a device private entry, otherwise false.
+ */
+static inline bool softleaf_is_device_private(softleaf_t entry)
+{
+	switch (softleaf_type(entry)) {
+	case SOFTLEAF_DEVICE_PRIVATE_WRITE:
+	case SOFTLEAF_DEVICE_PRIVATE_READ:
+		return true;
+	default:
+		return false;
+	}
+}
+
+/**
+ * softleaf_is_device_exclusive() - Is this leaf entry a device-exclusive entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a device-exclusive entry, otherwise false.
+ */
+static inline bool softleaf_is_device_exclusive(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_DEVICE_EXCLUSIVE;
+}
+
+/**
+ * softleaf_is_hwpoison() - Is this leaf entry a hardware poison entry?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a hardware poison entry, otherwise false.
+ */
+static inline bool softleaf_is_hwpoison(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_HWPOISON;
+}
+
+/**
+ * softleaf_is_marker() - Is this leaf entry a marker?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a marker entry, otherwise false.
+ */
+static inline bool softleaf_is_marker(softleaf_t entry)
+{
+	return softleaf_type(entry) == SOFTLEAF_MARKER;
+}
+
+/**
+ * softleaf_to_marker() - Obtain marker associated with leaf entry.
+ * @entry: Leaf entry, softleaf_is_marker(@entry) must return true.
+ *
+ * Returns: Marker associated with the leaf entry.
+ */
+static inline pte_marker softleaf_to_marker(softleaf_t entry)
+{
+	VM_WARN_ON_ONCE(!softleaf_is_marker(entry));
+
+	return swp_offset(entry) & PTE_MARKER_MASK;
+}
+
+/**
+ * softleaf_has_pfn() - Does this leaf entry encode a valid PFN number?
+ * @entry: Leaf entry.
+ *
+ * A pfn swap entry is a special type of swap entry that always has a pfn stored
+ * in the swap offset. They can either be used to represent unaddressable device
+ * memory, to restrict access to a page undergoing migration or to represent a
+ * pfn which has been hwpoisoned and unmapped.
+ *
+ * Returns: true if the leaf entry encodes a PFN, otherwise false.
+ */
+static inline bool softleaf_has_pfn(softleaf_t entry)
+{
+	/* Make sure the swp offset can always store the needed fields. */
+	BUILD_BUG_ON(SWP_TYPE_SHIFT < SWP_PFN_BITS);
+
+	if (softleaf_is_migration(entry))
+		return true;
+	if (softleaf_is_device_private(entry))
+		return true;
+	if (softleaf_is_device_exclusive(entry))
+		return true;
+	if (softleaf_is_hwpoison(entry))
+		return true;
+
+	return false;
+}
+
+/**
+ * softleaf_to_pfn() - Obtain PFN encoded within leaf entry.
+ * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true.
+ *
+ * Returns: The PFN associated with the leaf entry.
+ */
+static inline unsigned long softleaf_to_pfn(softleaf_t entry)
+{
+	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
+
+	/* Temporary until swp_entry_t eliminated. */
+	return swp_offset(entry) & SWP_PFN_MASK;
+}
+
+/**
+ * softleaf_to_page() - Obtains struct page for PFN encoded within leaf entry.
+ * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true.
+ *
+ * Returns: Pointer to the struct page associated with the leaf entry's PFN.
+ */
+static inline struct page *softleaf_to_page(softleaf_t entry)
+{
+	struct page *page = pfn_to_page(softleaf_to_pfn(entry));
+
+	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
+	/*
+	 * Any use of migration entries may only occur while the
+	 * corresponding page is locked
+	 */
+	VM_WARN_ON_ONCE(softleaf_is_migration(entry) && !PageLocked(page));
+
+	return page;
+}
+
+/**
+ * softleaf_to_folio() - Obtains struct folio for PFN encoded within leaf entry.
+ * @entry: Leaf entry, softleaf_has_pfn(@entry) must return true.
+ *
+ * Returns: Pointer to the struct folio associated with the leaf entry's PFN.
+ */
+static inline struct folio *softleaf_to_folio(softleaf_t entry)
+{
+	struct folio *folio = pfn_folio(softleaf_to_pfn(entry));
+
+	VM_WARN_ON_ONCE(!softleaf_has_pfn(entry));
+	/*
+	 * Any use of migration entries may only occur while the
+	 * corresponding folio is locked.
+	 */
+	VM_WARN_ON_ONCE(softleaf_is_migration(entry) &&
+			!folio_test_locked(folio));
+
+	return folio;
+}
+
+/**
+ * softleaf_is_poison_marker() - Is this leaf entry a poison marker?
+ * @entry: Leaf entry.
+ *
+ * The poison marker is set via UFFDIO_POISON. Userfaultfd-specific.
+ *
+ * Returns: true if the leaf entry is a poison marker, otherwise false.
+ */
+static inline bool softleaf_is_poison_marker(softleaf_t entry)
+{
+	if (!softleaf_is_marker(entry))
+		return false;
+
+	return softleaf_to_marker(entry) & PTE_MARKER_POISONED;
+}
+
+/**
+ * softleaf_is_guard_marker() - Is this leaf entry a guard region marker?
+ * @entry: Leaf entry.
+ *
+ * Returns: true if the leaf entry is a guard marker, otherwise false.
+ */
+static inline bool softleaf_is_guard_marker(softleaf_t entry)
+{
+	if (!softleaf_is_marker(entry))
+		return false;
+
+	return softleaf_to_marker(entry) & PTE_MARKER_GUARD;
+}
+
+/**
+ * softleaf_is_uffd_wp_marker() - Is this leaf entry a userfautlfd write protect
+ * marker?
+ * @entry: Leaf entry.
+ *
+ * Userfaultfd-specific.
+ *
+ * Returns: true if the leaf entry is a UFFD WP marker, otherwise false.
+ */
+static inline bool softleaf_is_uffd_wp_marker(softleaf_t entry)
+{
+	if (!softleaf_is_marker(entry))
+		return false;
+
+	return softleaf_to_marker(entry) & PTE_MARKER_UFFD_WP;
+}
+
+#ifdef CONFIG_MIGRATION
+
+/**
+ * softleaf_is_migration_young() - Does this migration entry contain an accessed
+ * bit?
+ * @entry: Leaf entry.
+ *
+ * If the architecture can support storing A/D bits in migration entries, this
+ * determines whether the accessed (or 'young') bit was set on the migrated page
+ * table entry.
+ *
+ * Returns: true if the entry contains an accessed bit, otherwise false.
+ */
+static inline bool softleaf_is_migration_young(softleaf_t entry)
+{
+	VM_WARN_ON_ONCE(!softleaf_is_migration(entry));
+
+	if (migration_entry_supports_ad())
+		return swp_offset(entry) & SWP_MIG_YOUNG;
+	/* Keep the old behavior of aging page after migration */
+	return false;
+}
+
+/**
+ * softleaf_is_migration_dirty() - Does this migration entry contain a dirty bit?
+ * @entry: Leaf entry.
+ *
+ * If the architecture can support storing A/D bits in migration entries, this
+ * determines whether the dirty bit was set on the migrated page table entry.
+ *
+ * Returns: true if the entry contains a dirty bit, otherwise false.
+ */
+static inline bool softleaf_is_migration_dirty(softleaf_t entry)
+{
+	VM_WARN_ON_ONCE(!softleaf_is_migration(entry));
+
+	if (migration_entry_supports_ad())
+		return swp_offset(entry) & SWP_MIG_DIRTY;
+	/* Keep the old behavior of clean page after migration */
+	return false;
+}
+
+#else /* CONFIG_MIGRATION */
+
+static inline bool softleaf_is_migration_young(softleaf_t entry)
+{
+	return false;
+}
+
+static inline bool softleaf_is_migration_dirty(softleaf_t entry)
+{
+	return false;
+}
+#endif /* CONFIG_MIGRATION */
+
+/**
+ * pte_is_marker() - Does the PTE entry encode a marker leaf entry?
+ * @pte: PTE entry.
+ *
+ * Returns: true if this PTE is a marker leaf entry, otherwise false.
+ */
+static inline bool pte_is_marker(pte_t pte)
+{
+	return softleaf_is_marker(softleaf_from_pte(pte));
+}
+
+/**
+ * pte_is_uffd_wp_marker() - Does this PTE entry encode a userfaultfd write
+ * protect marker leaf entry?
+ * @pte: PTE entry.
+ *
+ * Returns: true if this PTE is a UFFD WP marker leaf entry, otherwise false.
+ */
+static inline bool pte_is_uffd_wp_marker(pte_t pte)
+{
+	const softleaf_t entry = softleaf_from_pte(pte);
+
+	return softleaf_is_uffd_wp_marker(entry);
+}
+
+/**
+ * pte_is_uffd_marker() - Does this PTE entry encode a userfault-specific marker
+ * leaf entry?
+ * @entry: Leaf entry.
+ *
+ * It's useful to be able to determine which leaf entries encode UFFD-specific
+ * markers so we can handle these correctly.
+ *
+ * Returns: true if this PTE entry is a UFFD-specific marker, otherwise false.
+ */
+static inline bool pte_is_uffd_marker(pte_t pte)
+{
+	const softleaf_t entry = softleaf_from_pte(pte);
+
+	if (!softleaf_is_marker(entry))
+		return false;
+
+	/* UFFD WP, poisoned swap entries are UFFD-handled. */
+	if (softleaf_is_uffd_wp_marker(entry))
+		return true;
+	if (softleaf_is_poison_marker(entry))
+		return true;
+
+	return false;
+}
+
+#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_ARCH_ENABLE_THP_MIGRATION)
+
+/**
+ * pmd_is_device_private_entry() - Check if PMD contains a device private swap
+ * entry.
+ * @pmd: The PMD to check.
+ *
+ * Returns true if the PMD contains a swap entry that represents a device private
+ * page mapping. This is used for zone device private pages that have been
+ * swapped out but still need special handling during various memory management
+ * operations.
+ *
+ * Return: true if PMD contains device private entry, false otherwise
+ */
+static inline bool pmd_is_device_private_entry(pmd_t pmd)
+{
+	return softleaf_is_device_private(softleaf_from_pmd(pmd));
+}
+
+#else  /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
+
+static inline bool pmd_is_device_private_entry(pmd_t pmd)
+{
+	return false;
+}
+
+#endif /* CONFIG_ZONE_DEVICE && CONFIG_ARCH_ENABLE_THP_MIGRATION */
+
+/**
+ * pmd_is_migration_entry() - Does this PMD entry encode a migration entry?
+ * @pmd: PMD entry.
+ *
+ * Returns: true if the PMD encodes a migration entry, otherwise false.
+ */
+static inline bool pmd_is_migration_entry(pmd_t pmd)
+{
+	return softleaf_is_migration(softleaf_from_pmd(pmd));
+}
+
+/**
+ * pmd_is_valid_softleaf() - Is this PMD entry a valid leaf entry?
+ * @pmd: PMD entry.
+ *
+ * PMD leaf entries are valid only if they are device private or migration
+ * entries. This function asserts that a PMD leaf entry is valid in this
+ * respect.
+ *
+ * Returns: true if the PMD entry is a valid leaf entry, otherwise false.
+ */
+static inline bool pmd_is_valid_softleaf(pmd_t pmd)
+{
+	const softleaf_t entry = softleaf_from_pmd(pmd);
+
+	/* Only device private, migration entries valid for PMD. */
+	return softleaf_is_device_private(entry) ||
+		softleaf_is_migration(entry);
+}
+
+#endif  /* CONFIG_MMU */
+#endif  /* _LINUX_LEAFOPS_H */
diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h
index 612b4cab3819..775a96217518 100644
--- a/include/linux/led-class-flash.h
+++ b/include/linux/led-class-flash.h
@@ -45,6 +45,8 @@ struct led_flash_ops {
 	int (*timeout_set)(struct led_classdev_flash *fled_cdev, u32 timeout);
 	/* get the flash LED fault */
 	int (*fault_get)(struct led_classdev_flash *fled_cdev, u32 *fault);
+	/* set flash duration */
+	int (*duration_set)(struct led_classdev_flash *fled_cdev, u32 duration);
 };
 
 /*
@@ -75,6 +77,9 @@ struct led_classdev_flash {
 	/* flash timeout value in microseconds along with its constraints */
 	struct led_flash_setting timeout;
 
+	/* flash timeout value in microseconds along with its constraints */
+	struct led_flash_setting duration;
+
 	/* LED Flash class sysfs groups */
 	const struct attribute_group *sysfs_groups[LED_FLASH_SYSFS_GROUPS_SIZE];
 };
@@ -85,7 +90,6 @@ static inline struct led_classdev_flash *lcdev_to_flcdev(
 	return container_of(lcdev, struct led_classdev_flash, led_cdev);
 }
 
-#if IS_ENABLED(CONFIG_LEDS_CLASS_FLASH)
 /**
  * led_classdev_flash_register_ext - register a new object of LED class with
  *				     init data and with support for flash LEDs
@@ -116,29 +120,6 @@ int devm_led_classdev_flash_register_ext(struct device *parent,
 void devm_led_classdev_flash_unregister(struct device *parent,
 					struct led_classdev_flash *fled_cdev);
 
-#else
-
-static inline int led_classdev_flash_register_ext(struct device *parent,
-				    struct led_classdev_flash *fled_cdev,
-				    struct led_init_data *init_data)
-{
-	return 0;
-}
-
-static inline void led_classdev_flash_unregister(struct led_classdev_flash *fled_cdev) {};
-static inline int devm_led_classdev_flash_register_ext(struct device *parent,
-				     struct led_classdev_flash *fled_cdev,
-				     struct led_init_data *init_data)
-{
-	return 0;
-}
-
-static inline void devm_led_classdev_flash_unregister(struct device *parent,
-					struct led_classdev_flash *fled_cdev)
-{};
-
-#endif  /* IS_ENABLED(CONFIG_LEDS_CLASS_FLASH) */
-
 static inline int led_classdev_flash_register(struct device *parent,
 					   struct led_classdev_flash *fled_cdev)
 {
@@ -216,7 +197,7 @@ int led_update_flash_brightness(struct led_classdev_flash *fled_cdev);
  * @fled_cdev: the flash LED to set
  * @timeout: the flash timeout to set it to
  *
- * Set the flash strobe duration.
+ * Set the flash strobe timeout.
  *
  * Returns: 0 on success or negative error value on failure
  */
@@ -233,4 +214,15 @@ int led_set_flash_timeout(struct led_classdev_flash *fled_cdev, u32 timeout);
  */
 int led_get_flash_fault(struct led_classdev_flash *fled_cdev, u32 *fault);
 
+/**
+ * led_set_flash_duration - set flash LED duration
+ * @fled_cdev: the flash LED to set
+ * @timeout: the flash duration to set it to
+ *
+ * Set the flash strobe duration.
+ *
+ * Returns: 0 on success or negative error value on failure
+ */
+int led_set_flash_duration(struct led_classdev_flash *fled_cdev, u32 duration);
+
 #endif	/* __LINUX_FLASH_LEDS_H_INCLUDED */
diff --git a/include/linux/led-class-multicolor.h b/include/linux/led-class-multicolor.h
index 210d57bcd767..db9f34c6736e 100644
--- a/include/linux/led-class-multicolor.h
+++ b/include/linux/led-class-multicolor.h
@@ -30,7 +30,6 @@ static inline struct led_classdev_mc *lcdev_to_mccdev(
 	return container_of(led_cdev, struct led_classdev_mc, led_cdev);
 }
 
-#if IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR)
 /**
  * led_classdev_multicolor_register_ext - register a new object of led_classdev
  *				      class with support for multicolor LEDs
@@ -64,34 +63,6 @@ int devm_led_classdev_multicolor_register_ext(struct device *parent,
 
 void devm_led_classdev_multicolor_unregister(struct device *parent,
 					    struct led_classdev_mc *mcled_cdev);
-#else
-
-static inline int led_classdev_multicolor_register_ext(struct device *parent,
-					    struct led_classdev_mc *mcled_cdev,
-					    struct led_init_data *init_data)
-{
-	return 0;
-}
-
-static inline void led_classdev_multicolor_unregister(struct led_classdev_mc *mcled_cdev) {};
-static inline int led_mc_calc_color_components(struct led_classdev_mc *mcled_cdev,
-					       enum led_brightness brightness)
-{
-	return 0;
-}
-
-static inline int devm_led_classdev_multicolor_register_ext(struct device *parent,
-					  struct led_classdev_mc *mcled_cdev,
-					  struct led_init_data *init_data)
-{
-	return 0;
-}
-
-static inline void devm_led_classdev_multicolor_unregister(struct device *parent,
-					    struct led_classdev_mc *mcled_cdev)
-{};
-
-#endif  /* IS_ENABLED(CONFIG_LEDS_CLASS_MULTICOLOR) */
 
 static inline int led_classdev_multicolor_register(struct device *parent,
 					    struct led_classdev_mc *mcled_cdev)
diff --git a/include/linux/leds-expresswire.h b/include/linux/leds-expresswire.h
new file mode 100644
index 000000000000..a422921f4159
--- /dev/null
+++ b/include/linux/leds-expresswire.h
@@ -0,0 +1,38 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Shared library for Kinetic's ExpressWire protocol.
+ * This protocol works by pulsing the ExpressWire IC's control GPIO.
+ * ktd2692 and ktd2801 are known to use this protocol.
+ */
+
+#ifndef _LEDS_EXPRESSWIRE_H
+#define _LEDS_EXPRESSWIRE_H
+
+#include <linux/types.h>
+
+struct gpio_desc;
+
+struct expresswire_timing {
+	unsigned long poweroff_us;
+	unsigned long detect_delay_us;
+	unsigned long detect_us;
+	unsigned long data_start_us;
+	unsigned long end_of_data_low_us;
+	unsigned long end_of_data_high_us;
+	unsigned long short_bitset_us;
+	unsigned long long_bitset_us;
+};
+
+struct expresswire_common_props {
+	struct gpio_desc *ctrl_gpio;
+	struct expresswire_timing timing;
+};
+
+void expresswire_power_off(struct expresswire_common_props *props);
+void expresswire_enable(struct expresswire_common_props *props);
+void expresswire_start(struct expresswire_common_props *props);
+void expresswire_end(struct expresswire_common_props *props);
+void expresswire_set_bit(struct expresswire_common_props *props, bool bit);
+void expresswire_write_u8(struct expresswire_common_props *props, u8 val);
+
+#endif /* _LEDS_EXPRESSWIRE_H */
diff --git a/include/linux/leds.h b/include/linux/leds.h
index c39bbf17a25b..b16b803cc1ac 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -82,15 +82,7 @@ struct led_init_data {
 	bool devname_mandatory;
 };
 
-#if IS_ENABLED(CONFIG_NEW_LEDS)
 enum led_default_state led_init_default_state_get(struct fwnode_handle *fwnode);
-#else
-static inline enum led_default_state
-led_init_default_state_get(struct fwnode_handle *fwnode)
-{
-	return LEDS_DEFSTATE_OFF;
-}
-#endif
 
 struct led_hw_trigger_type {
 	int dummy;
@@ -100,6 +92,7 @@ struct led_classdev {
 	const char		*name;
 	unsigned int brightness;
 	unsigned int max_brightness;
+	unsigned int color;
 	int			 flags;
 
 	/* Lower 16 bits reflect status */
@@ -114,6 +107,8 @@ struct led_classdev {
 #define LED_BRIGHT_HW_CHANGED	BIT(21)
 #define LED_RETAIN_AT_SHUTDOWN	BIT(22)
 #define LED_INIT_DEFAULT_TRIGGER BIT(23)
+#define LED_REJECT_NAME_CONFLICT BIT(24)
+#define LED_MULTI_COLOR		BIT(25)
 
 	/* set_brightness_work / blink_timer flags, atomic, private. */
 	unsigned long		work_flags;
@@ -124,6 +119,10 @@ struct led_classdev {
 #define LED_BLINK_INVERT		3
 #define LED_BLINK_BRIGHTNESS_CHANGE 	4
 #define LED_BLINK_DISABLE		5
+	/* Brightness off also disables hw-blinking so it is a separate action */
+#define LED_SET_BRIGHTNESS_OFF		6
+#define LED_SET_BRIGHTNESS		7
+#define LED_SET_BLINK			8
 
 	/* Set LED brightness level
 	 * Must not sleep. Use brightness_set_blocking for drivers
@@ -147,6 +146,10 @@ struct led_classdev {
 	 * match the values specified exactly.
 	 * Deactivate blinking again when the brightness is set to LED_OFF
 	 * via the brightness_set() callback.
+	 * For led_blink_set_nosleep() the LED core assumes that blink_set
+	 * implementations, of drivers which do not use brightness_set_blocking,
+	 * will not sleep. Therefor if brightness_set_blocking is not set
+	 * this function must not sleep!
 	 */
 	int		(*blink_set)(struct led_classdev *led_cdev,
 				     unsigned long *delay_on,
@@ -168,8 +171,11 @@ struct led_classdev {
 	int			 new_blink_brightness;
 	void			(*flash_resume)(struct led_classdev *led_cdev);
 
+	struct workqueue_struct *wq;			/* LED workqueue */
 	struct work_struct	set_brightness_work;
 	int			delayed_set_value;
+	unsigned long		delayed_delay_on;
+	unsigned long		delayed_delay_off;
 
 #ifdef CONFIG_LEDS_TRIGGERS
 	/* Protects the trigger data below */
@@ -183,6 +189,49 @@ struct led_classdev {
 
 	/* LEDs that have private triggers have this set */
 	struct led_hw_trigger_type	*trigger_type;
+
+	/* Unique trigger name supported by LED set in hw control mode */
+	const char		*hw_control_trigger;
+	/*
+	 * Check if the LED driver supports the requested mode provided by the
+	 * defined supported trigger to setup the LED to hw control mode.
+	 *
+	 * Return 0 on success. Return -EOPNOTSUPP when the passed flags are not
+	 * supported and software fallback needs to be used.
+	 * Return a negative error number on any other case  for check fail due
+	 * to various reason like device not ready or timeouts.
+	 */
+	int			(*hw_control_is_supported)(struct led_classdev *led_cdev,
+							   unsigned long flags);
+	/*
+	 * Activate hardware control, LED driver will use the provided flags
+	 * from the supported trigger and setup the LED to be driven by hardware
+	 * following the requested mode from the trigger flags.
+	 * Deactivate hardware blink control by setting brightness to LED_OFF via
+	 * the brightness_set() callback.
+	 *
+	 * Return 0 on success, a negative error number on flags apply fail.
+	 */
+	int			(*hw_control_set)(struct led_classdev *led_cdev,
+						  unsigned long flags);
+	/*
+	 * Get from the LED driver the current mode that the LED is set in hw
+	 * control mode and put them in flags.
+	 * Trigger can use this to get the initial state of a LED already set in
+	 * hardware blink control.
+	 *
+	 * Return 0 on success, a negative error number on failing parsing the
+	 * initial mode. Error from this function is NOT FATAL as the device
+	 * may be in a not supported initial state by the attached LED trigger.
+	 */
+	int			(*hw_control_get)(struct led_classdev *led_cdev,
+						  unsigned long *flags);
+	/*
+	 * Get the device this LED blinks in response to.
+	 * e.g. for a PHY LED, it is the network device. If the LED is
+	 * not yet associated to a device, return NULL.
+	 */
+	struct device		*(*hw_control_get_device)(struct led_classdev *led_cdev);
 #endif
 
 #ifdef CONFIG_LEDS_BRIGHTNESS_HW_CHANGED
@@ -190,7 +239,7 @@ struct led_classdev {
 	struct kernfs_node	*brightness_hw_changed_kn;
 #endif
 
-	/* Ensures consistent access to the LED Flash Class device */
+	/* Ensures consistent access to the LED class device */
 	struct mutex		led_access;
 };
 
@@ -225,20 +274,9 @@ static inline int led_classdev_register(struct device *parent,
 	return led_classdev_register_ext(parent, led_cdev, NULL);
 }
 
-#if IS_ENABLED(CONFIG_LEDS_CLASS)
 int devm_led_classdev_register_ext(struct device *parent,
 					  struct led_classdev *led_cdev,
 					  struct led_init_data *init_data);
-#else
-static inline int
-devm_led_classdev_register_ext(struct device *parent,
-			       struct led_classdev *led_cdev,
-			       struct led_init_data *init_data)
-{
-	return 0;
-}
-#endif
-
 static inline int devm_led_classdev_register(struct device *parent,
 					     struct led_classdev *led_cdev)
 {
@@ -256,10 +294,11 @@ void led_remove_lookup(struct led_lookup_data *led_lookup);
 struct led_classdev *__must_check led_get(struct device *dev, char *con_id);
 struct led_classdev *__must_check devm_led_get(struct device *dev, char *con_id);
 
-extern struct led_classdev *of_led_get(struct device_node *np, int index);
 extern void led_put(struct led_classdev *led_cdev);
 struct led_classdev *__must_check devm_of_led_get(struct device *dev,
 						  int index);
+struct led_classdev *__must_check devm_of_led_get_optional(struct device *dev,
+						  int index);
 
 /**
  * led_blink_set - set blinking with software fallback
@@ -272,12 +311,27 @@ struct led_classdev *__must_check devm_of_led_get(struct device *dev,
  * software blinking if there is no hardware blinking or if
  * the LED refuses the passed values.
  *
+ * This function may sleep!
+ *
  * Note that if software blinking is active, simply calling
  * led_cdev->brightness_set() will not stop the blinking,
  * use led_set_brightness() instead.
  */
 void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on,
 		   unsigned long *delay_off);
+
+/**
+ * led_blink_set_nosleep - set blinking, guaranteed to not sleep
+ * @led_cdev: the LED to start blinking
+ * @delay_on: the time it should be on (in ms)
+ * @delay_off: the time it should ble off (in ms)
+ *
+ * This function makes the LED blink and is guaranteed to not sleep. Otherwise
+ * this is the same as led_blink_set(), see led_blink_set() for details.
+ */
+void led_blink_set_nosleep(struct led_classdev *led_cdev, unsigned long delay_on,
+			   unsigned long delay_off);
+
 /**
  * led_blink_set_oneshot - do a oneshot software blink
  * @led_cdev: the LED to start blinking
@@ -291,6 +345,8 @@ void led_blink_set(struct led_classdev *led_cdev, unsigned long *delay_on,
  *
  * If invert is set, led blinks for delay_off first, then for
  * delay_on and leave the led on after the on-off cycle.
+ *
+ * This function is guaranteed not to sleep.
  */
 void led_blink_set_oneshot(struct led_classdev *led_cdev,
 			   unsigned long *delay_on, unsigned long *delay_off,
@@ -320,6 +376,25 @@ void led_set_brightness(struct led_classdev *led_cdev, unsigned int brightness);
 int led_set_brightness_sync(struct led_classdev *led_cdev, unsigned int value);
 
 /**
+ * led_mc_set_brightness - set mc LED color intensity values and brightness
+ * @led_cdev: the LED to set
+ * @intensity_value: array of per color intensity values to set
+ * @num_colors: amount of entries in intensity_value array
+ * @brightness: the brightness to set the LED to
+ *
+ * Set a multi-color LED's per color intensity values and brightness.
+ * If necessary, this cancels the software blink timer. This function is
+ * guaranteed not to sleep.
+ *
+ * Calling this function on a non multi-color led_classdev or with the wrong
+ * num_colors value is an error. In this case an error will be logged once
+ * and the call will do nothing.
+ */
+void led_mc_set_brightness(struct led_classdev *led_cdev,
+			   unsigned int *intensity_value, unsigned int num_colors,
+			   unsigned int brightness);
+
+/**
  * led_update_brightness - update LED brightness
  * @led_cdev: the LED to query
  *
@@ -374,6 +449,16 @@ int led_compose_name(struct device *dev, struct led_init_data *init_data,
 		     char *led_classdev_name);
 
 /**
+ * led_get_color_name - get string representation of color ID
+ * @color_id: The LED_COLOR_ID_* constant
+ *
+ * Get the string name of a LED_COLOR_ID_* constant.
+ *
+ * Returns: A string constant or NULL on an invalid ID.
+ */
+const char *led_get_color_name(u8 color_id);
+
+/**
  * led_sysfs_is_disabled - check if LED sysfs interface is disabled
  * @led_cdev: the LED to query
  *
@@ -401,6 +486,9 @@ struct led_trigger {
 	int		(*activate)(struct led_classdev *led_cdev);
 	void		(*deactivate)(struct led_classdev *led_cdev);
 
+	/* Brightness set by led_trigger_event */
+	enum led_brightness brightness;
+
 	/* LED-private triggers have this set */
 	struct led_hw_trigger_type *trigger_type;
 
@@ -433,11 +521,14 @@ void led_trigger_register_simple(const char *name,
 				struct led_trigger **trigger);
 void led_trigger_unregister_simple(struct led_trigger *trigger);
 void led_trigger_event(struct led_trigger *trigger,  enum led_brightness event);
-void led_trigger_blink(struct led_trigger *trigger, unsigned long *delay_on,
-		       unsigned long *delay_off);
+void led_mc_trigger_event(struct led_trigger *trig,
+			  unsigned int *intensity_value, unsigned int num_colors,
+			  enum led_brightness brightness);
+void led_trigger_blink(struct led_trigger *trigger, unsigned long delay_on,
+		       unsigned long delay_off);
 void led_trigger_blink_oneshot(struct led_trigger *trigger,
-			       unsigned long *delay_on,
-			       unsigned long *delay_off,
+			       unsigned long delay_on,
+			       unsigned long delay_off,
 			       int invert);
 void led_trigger_set_default(struct led_classdev *led_cdev);
 int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trigger);
@@ -454,22 +545,11 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 	return led_cdev->trigger_data;
 }
 
-/**
- * led_trigger_rename_static - rename a trigger
- * @name: the new trigger name
- * @trig: the LED trigger to rename
- *
- * Change a LED trigger name by copying the string passed in
- * name into current trigger name, which MUST be large
- * enough for the new string.
- *
- * Note that name must NOT point to the same string used
- * during LED registration, as that could lead to races.
- *
- * This is meant to be used on triggers with statically
- * allocated name.
- */
-void led_trigger_rename_static(const char *name, struct led_trigger *trig);
+static inline enum led_brightness
+led_trigger_get_brightness(const struct led_trigger *trigger)
+{
+	return trigger ? trigger->brightness : LED_OFF;
+}
 
 #define module_led_trigger(__led_trigger) \
 	module_driver(__led_trigger, led_trigger_register, \
@@ -486,12 +566,15 @@ static inline void led_trigger_register_simple(const char *name,
 static inline void led_trigger_unregister_simple(struct led_trigger *trigger) {}
 static inline void led_trigger_event(struct led_trigger *trigger,
 				enum led_brightness event) {}
+static inline void led_mc_trigger_event(struct led_trigger *trig,
+				unsigned int *intensity_value, unsigned int num_colors,
+				enum led_brightness brightness) {}
 static inline void led_trigger_blink(struct led_trigger *trigger,
-				      unsigned long *delay_on,
-				      unsigned long *delay_off) {}
+				      unsigned long delay_on,
+				      unsigned long delay_off) {}
 static inline void led_trigger_blink_oneshot(struct led_trigger *trigger,
-				      unsigned long *delay_on,
-				      unsigned long *delay_off,
+				      unsigned long delay_on,
+				      unsigned long delay_off,
 				      int invert) {}
 static inline void led_trigger_set_default(struct led_classdev *led_cdev) {}
 static inline int led_trigger_set(struct led_classdev *led_cdev,
@@ -507,8 +590,34 @@ static inline void *led_get_trigger_data(struct led_classdev *led_cdev)
 	return NULL;
 }
 
+static inline enum led_brightness
+led_trigger_get_brightness(const struct led_trigger *trigger)
+{
+	return LED_OFF;
+}
+
 #endif /* CONFIG_LEDS_TRIGGERS */
 
+/* Trigger specific enum */
+enum led_trigger_netdev_modes {
+	TRIGGER_NETDEV_LINK = 0,
+	TRIGGER_NETDEV_LINK_10,
+	TRIGGER_NETDEV_LINK_100,
+	TRIGGER_NETDEV_LINK_1000,
+	TRIGGER_NETDEV_LINK_2500,
+	TRIGGER_NETDEV_LINK_5000,
+	TRIGGER_NETDEV_LINK_10000,
+	TRIGGER_NETDEV_HALF_DUPLEX,
+	TRIGGER_NETDEV_FULL_DUPLEX,
+	TRIGGER_NETDEV_TX,
+	TRIGGER_NETDEV_RX,
+	TRIGGER_NETDEV_TX_ERR,
+	TRIGGER_NETDEV_RX_ERR,
+
+	/* Keep last */
+	__TRIGGER_NETDEV_MAX,
+};
+
 /* Trigger specific functions */
 #ifdef CONFIG_LEDS_TRIGGER_DISK
 void ledtrig_disk_activity(bool write);
@@ -530,6 +639,12 @@ static inline void ledtrig_flash_ctrl(bool on) {}
 static inline void ledtrig_torch_ctrl(bool on) {}
 #endif
 
+#if IS_REACHABLE(CONFIG_LEDS_TRIGGER_BACKLIGHT)
+void ledtrig_backlight_blank(bool blank);
+#else
+static inline void ledtrig_backlight_blank(bool blank) {}
+#endif
+
 /*
  * Generic LED platform data for describing LED names and default triggers.
  */
@@ -584,7 +699,7 @@ struct gpio_led_platform_data {
 	gpio_blink_set_t	gpio_blink_set;
 };
 
-#ifdef CONFIG_NEW_LEDS
+#ifdef CONFIG_LEDS_GPIO_REGISTER
 struct platform_device *gpio_led_register_device(
 		int id, const struct gpio_led_platform_data *pdata);
 #else
@@ -635,18 +750,4 @@ enum led_audio {
 	NUM_AUDIO_LEDS
 };
 
-#if IS_ENABLED(CONFIG_LEDS_TRIGGER_AUDIO)
-enum led_brightness ledtrig_audio_get(enum led_audio type);
-void ledtrig_audio_set(enum led_audio type, enum led_brightness state);
-#else
-static inline enum led_brightness ledtrig_audio_get(enum led_audio type)
-{
-	return LED_OFF;
-}
-static inline void ledtrig_audio_set(enum led_audio type,
-				     enum led_brightness state)
-{
-}
-#endif
-
 #endif		/* __LINUX_LEDS_H_INCLUDED */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 311cd93377c7..39534fafa36a 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -41,20 +41,90 @@
  */
 #undef ATA_IRQ_TRAP		/* define to ack screaming irqs */
 
-
-#define ata_print_version_once(dev, version)			\
-({								\
-	static bool __print_once;				\
-								\
-	if (!__print_once) {					\
-		__print_once = true;				\
-		ata_print_version(dev, version);		\
-	}							\
-})
-
 /* defines only for the constants which don't work well as enums */
 #define ATA_TAG_POISON		0xfafbfcfdU
 
+/*
+ * Quirk flags bits.
+ * ata_device->quirks is an unsigned int, so __ATA_QUIRK_MAX must not exceed 32.
+ */
+enum ata_quirks {
+	__ATA_QUIRK_DIAGNOSTIC,		/* Failed boot diag */
+	__ATA_QUIRK_NODMA,		/* DMA problems */
+	__ATA_QUIRK_NONCQ,		/* Don't use NCQ */
+	__ATA_QUIRK_MAX_SEC_128,	/* Limit max sects to 128 */
+	__ATA_QUIRK_BROKEN_HPA,		/* Broken HPA */
+	__ATA_QUIRK_DISABLE,		/* Disable it */
+	__ATA_QUIRK_HPA_SIZE,		/* Native size off by one */
+	__ATA_QUIRK_IVB,		/* cbl det validity bit bugs */
+	__ATA_QUIRK_STUCK_ERR,		/* Stuck ERR on next PACKET */
+	__ATA_QUIRK_BRIDGE_OK,		/* No bridge limits */
+	__ATA_QUIRK_ATAPI_MOD16_DMA,	/* Use ATAPI DMA for commands that */
+					/* are not a multiple of 16 bytes */
+	__ATA_QUIRK_FIRMWARE_WARN,	/* Firmware update warning */
+	__ATA_QUIRK_1_5_GBPS,		/* Force 1.5 Gbps */
+	__ATA_QUIRK_NOSETXFER,		/* Skip SETXFER, SATA only */
+	__ATA_QUIRK_BROKEN_FPDMA_AA,	/* Skip AA */
+	__ATA_QUIRK_DUMP_ID,		/* Dump IDENTIFY data */
+	__ATA_QUIRK_MAX_SEC_LBA48,	/* Set max sects to 65535 */
+	__ATA_QUIRK_ATAPI_DMADIR,	/* Device requires dmadir */
+	__ATA_QUIRK_NO_NCQ_TRIM,	/* Do not use queued TRIM */
+	__ATA_QUIRK_NOLPM,		/* Do not use LPM */
+	__ATA_QUIRK_WD_BROKEN_LPM,	/* Some WDs have broken LPM */
+	__ATA_QUIRK_ZERO_AFTER_TRIM,	/* Guarantees zero after trim */
+	__ATA_QUIRK_NO_DMA_LOG,		/* Do not use DMA for log read */
+	__ATA_QUIRK_NOTRIM,		/* Do not use TRIM */
+	__ATA_QUIRK_MAX_SEC_1024,	/* Limit max sects to 1024 */
+	__ATA_QUIRK_MAX_SEC_8191,	/* Limit max sects to 8191 */
+	__ATA_QUIRK_MAX_TRIM_128M,	/* Limit max trim size to 128M */
+	__ATA_QUIRK_NO_NCQ_ON_ATI,	/* Disable NCQ on ATI chipset */
+	__ATA_QUIRK_NO_LPM_ON_ATI,	/* Disable LPM on ATI chipset */
+	__ATA_QUIRK_NO_ID_DEV_LOG,	/* Identify device log missing */
+	__ATA_QUIRK_NO_LOG_DIR,		/* Do not read log directory */
+	__ATA_QUIRK_NO_FUA,		/* Do not use FUA */
+
+	__ATA_QUIRK_MAX,
+};
+
+/*
+ * Quirk flags: may be set by libata or controller drivers on drives.
+ * Some quirks may be drive/controller pair dependent.
+ */
+enum {
+	ATA_QUIRK_DIAGNOSTIC		= (1U << __ATA_QUIRK_DIAGNOSTIC),
+	ATA_QUIRK_NODMA			= (1U << __ATA_QUIRK_NODMA),
+	ATA_QUIRK_NONCQ			= (1U << __ATA_QUIRK_NONCQ),
+	ATA_QUIRK_MAX_SEC_128		= (1U << __ATA_QUIRK_MAX_SEC_128),
+	ATA_QUIRK_BROKEN_HPA		= (1U << __ATA_QUIRK_BROKEN_HPA),
+	ATA_QUIRK_DISABLE		= (1U << __ATA_QUIRK_DISABLE),
+	ATA_QUIRK_HPA_SIZE		= (1U << __ATA_QUIRK_HPA_SIZE),
+	ATA_QUIRK_IVB			= (1U << __ATA_QUIRK_IVB),
+	ATA_QUIRK_STUCK_ERR		= (1U << __ATA_QUIRK_STUCK_ERR),
+	ATA_QUIRK_BRIDGE_OK		= (1U << __ATA_QUIRK_BRIDGE_OK),
+	ATA_QUIRK_ATAPI_MOD16_DMA	= (1U << __ATA_QUIRK_ATAPI_MOD16_DMA),
+	ATA_QUIRK_FIRMWARE_WARN		= (1U << __ATA_QUIRK_FIRMWARE_WARN),
+	ATA_QUIRK_1_5_GBPS		= (1U << __ATA_QUIRK_1_5_GBPS),
+	ATA_QUIRK_NOSETXFER		= (1U << __ATA_QUIRK_NOSETXFER),
+	ATA_QUIRK_BROKEN_FPDMA_AA	= (1U << __ATA_QUIRK_BROKEN_FPDMA_AA),
+	ATA_QUIRK_DUMP_ID		= (1U << __ATA_QUIRK_DUMP_ID),
+	ATA_QUIRK_MAX_SEC_LBA48		= (1U << __ATA_QUIRK_MAX_SEC_LBA48),
+	ATA_QUIRK_ATAPI_DMADIR		= (1U << __ATA_QUIRK_ATAPI_DMADIR),
+	ATA_QUIRK_NO_NCQ_TRIM		= (1U << __ATA_QUIRK_NO_NCQ_TRIM),
+	ATA_QUIRK_NOLPM			= (1U << __ATA_QUIRK_NOLPM),
+	ATA_QUIRK_WD_BROKEN_LPM		= (1U << __ATA_QUIRK_WD_BROKEN_LPM),
+	ATA_QUIRK_ZERO_AFTER_TRIM	= (1U << __ATA_QUIRK_ZERO_AFTER_TRIM),
+	ATA_QUIRK_NO_DMA_LOG		= (1U << __ATA_QUIRK_NO_DMA_LOG),
+	ATA_QUIRK_NOTRIM		= (1U << __ATA_QUIRK_NOTRIM),
+	ATA_QUIRK_MAX_SEC_1024		= (1U << __ATA_QUIRK_MAX_SEC_1024),
+	ATA_QUIRK_MAX_SEC_8191		= (1U << __ATA_QUIRK_MAX_SEC_8191),
+	ATA_QUIRK_MAX_TRIM_128M		= (1U << __ATA_QUIRK_MAX_TRIM_128M),
+	ATA_QUIRK_NO_NCQ_ON_ATI		= (1U << __ATA_QUIRK_NO_NCQ_ON_ATI),
+	ATA_QUIRK_NO_LPM_ON_ATI		= (1U << __ATA_QUIRK_NO_LPM_ON_ATI),
+	ATA_QUIRK_NO_ID_DEV_LOG		= (1U << __ATA_QUIRK_NO_ID_DEV_LOG),
+	ATA_QUIRK_NO_LOG_DIR		= (1U << __ATA_QUIRK_NO_LOG_DIR),
+	ATA_QUIRK_NO_FUA		= (1U << __ATA_QUIRK_NO_FUA),
+};
+
 enum {
 	/* various global constants */
 	LIBATA_MAX_PRD		= ATA_MAX_PRD / 2,
@@ -94,28 +164,31 @@ enum {
 	ATA_DFLAG_DMADIR	= (1 << 10), /* device requires DMADIR */
 	ATA_DFLAG_NCQ_SEND_RECV = (1 << 11), /* device supports NCQ SEND and RECV */
 	ATA_DFLAG_NCQ_PRIO	= (1 << 12), /* device supports NCQ priority */
-	ATA_DFLAG_CFG_MASK	= (1 << 13) - 1,
-
-	ATA_DFLAG_PIO		= (1 << 13), /* device limited to PIO mode */
-	ATA_DFLAG_NCQ_OFF	= (1 << 14), /* device limited to non-NCQ mode */
-	ATA_DFLAG_SLEEPING	= (1 << 15), /* device is sleeping */
-	ATA_DFLAG_DUBIOUS_XFER	= (1 << 16), /* data transfer not verified */
-	ATA_DFLAG_NO_UNLOAD	= (1 << 17), /* device doesn't support unload */
-	ATA_DFLAG_UNLOCK_HPA	= (1 << 18), /* unlock HPA */
-	ATA_DFLAG_INIT_MASK	= (1 << 19) - 1,
-
-	ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 19), /* Priority cmds sent to dev */
+	ATA_DFLAG_CDL		= (1 << 13), /* supports cmd duration limits */
+	ATA_DFLAG_CFG_MASK	= (1 << 14) - 1,
+
+	ATA_DFLAG_PIO		= (1 << 14), /* device limited to PIO mode */
+	ATA_DFLAG_NCQ_OFF	= (1 << 15), /* device limited to non-NCQ mode */
+	ATA_DFLAG_SLEEPING	= (1 << 16), /* device is sleeping */
+	ATA_DFLAG_DUBIOUS_XFER	= (1 << 17), /* data transfer not verified */
+	ATA_DFLAG_NO_UNLOAD	= (1 << 18), /* device doesn't support unload */
+	ATA_DFLAG_UNLOCK_HPA	= (1 << 19), /* unlock HPA */
+	ATA_DFLAG_INIT_MASK	= (1 << 20) - 1,
+
+	ATA_DFLAG_NCQ_PRIO_ENABLED = (1 << 20), /* Priority cmds sent to dev */
+	ATA_DFLAG_CDL_ENABLED	= (1 << 21), /* cmd duration limits is enabled */
+	ATA_DFLAG_RESUMING	= (1 << 22),  /* Device is resuming */
 	ATA_DFLAG_DETACH	= (1 << 24),
 	ATA_DFLAG_DETACHED	= (1 << 25),
 	ATA_DFLAG_DA		= (1 << 26), /* device supports Device Attention */
 	ATA_DFLAG_DEVSLP	= (1 << 27), /* device supports Device Sleep */
 	ATA_DFLAG_ACPI_DISABLED = (1 << 28), /* ACPI for the device is disabled */
 	ATA_DFLAG_D_SENSE	= (1 << 29), /* Descriptor sense requested */
-	ATA_DFLAG_ZAC		= (1 << 30), /* ZAC device */
 
 	ATA_DFLAG_FEATURES_MASK	= (ATA_DFLAG_TRUSTED | ATA_DFLAG_DA |	\
 				   ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \
-				   ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA),
+				   ATA_DFLAG_NCQ_PRIO | ATA_DFLAG_FUA | \
+				   ATA_DFLAG_CDL),
 
 	ATA_DEV_UNKNOWN		= 0,	/* unknown device */
 	ATA_DEV_ATA		= 1,	/* ATA device */
@@ -189,6 +262,7 @@ enum {
 	ATA_PFLAG_UNLOADING	= (1 << 9), /* driver is being unloaded */
 	ATA_PFLAG_UNLOADED	= (1 << 10), /* driver is unloaded */
 
+	ATA_PFLAG_RESUMING	= (1 << 16),  /* port is being resumed */
 	ATA_PFLAG_SUSPENDED	= (1 << 17), /* port is suspended (power) */
 	ATA_PFLAG_PM_PENDING	= (1 << 18), /* PM operation pending */
 	ATA_PFLAG_INIT_GTM_VALID = (1 << 19), /* initial gtm data valid */
@@ -206,10 +280,12 @@ enum {
 	ATA_QCFLAG_CLEAR_EXCL	= (1 << 5), /* clear excl_link on completion */
 	ATA_QCFLAG_QUIET	= (1 << 6), /* don't report device error */
 	ATA_QCFLAG_RETRY	= (1 << 7), /* retry after failure */
+	ATA_QCFLAG_HAS_CDL	= (1 << 8), /* qc has CDL a descriptor set */
 
 	ATA_QCFLAG_EH		= (1 << 16), /* cmd aborted and owned by EH */
 	ATA_QCFLAG_SENSE_VALID	= (1 << 17), /* sense data valid */
 	ATA_QCFLAG_EH_SCHEDULED = (1 << 18), /* EH scheduled (obsolete) */
+	ATA_QCFLAG_EH_SUCCESS_CMD = (1 << 19), /* EH should fetch sense for this successful cmd */
 
 	/* host set flags */
 	ATA_HOST_SIMPLEX	= (1 << 0),	/* Host is simplex, one DMA channel per host only */
@@ -217,11 +293,13 @@ enum {
 	ATA_HOST_PARALLEL_SCAN	= (1 << 2),	/* Ports on this host can be scanned in parallel */
 	ATA_HOST_IGNORE_ATA	= (1 << 3),	/* Ignore ATA devices on this host. */
 
+	ATA_HOST_NO_PART	= (1 << 4), /* Host does not support partial */
+	ATA_HOST_NO_SSC		= (1 << 5), /* Host does not support slumber */
+	ATA_HOST_NO_DEVSLP	= (1 << 6), /* Host does not support devslp */
+
 	/* bits 24:31 of host->flags are reserved for LLD specific flags */
 
-	/* various lengths of time */
-	ATA_TMOUT_BOOT		= 30000,	/* heuristic */
-	ATA_TMOUT_BOOT_QUICK	=  7000,	/* heuristic */
+	/* Various lengths of time */
 	ATA_TMOUT_INTERNAL_QUICK = 5000,
 	ATA_TMOUT_MAX_PARK	= 30000,
 
@@ -250,7 +328,7 @@ enum {
 	 * advised to wait only for the following duration before
 	 * doing SRST.
 	 */
-	ATA_TMOUT_PMP_SRST_WAIT	= 5000,
+	ATA_TMOUT_PMP_SRST_WAIT	= 10000,
 
 	/* When the LPM policy is set to ATA_LPM_MAX_POWER, there might
 	 * be a spurious PHY event, so ignore the first PHY event that
@@ -308,8 +386,11 @@ enum {
 	ATA_EH_RESET		= ATA_EH_SOFTRESET | ATA_EH_HARDRESET,
 	ATA_EH_ENABLE_LINK	= (1 << 3),
 	ATA_EH_PARK		= (1 << 5), /* unload heads and stop I/O */
+	ATA_EH_GET_SUCCESS_SENSE = (1 << 6), /* Get sense data for successful cmd */
+	ATA_EH_SET_ACTIVE	= (1 << 7), /* Set a device to active power mode */
 
-	ATA_EH_PERDEV_MASK	= ATA_EH_REVALIDATE | ATA_EH_PARK,
+	ATA_EH_PERDEV_MASK	= ATA_EH_REVALIDATE | ATA_EH_PARK |
+				  ATA_EH_GET_SUCCESS_SENSE | ATA_EH_SET_ACTIVE,
 	ATA_EH_ALL_ACTIONS	= ATA_EH_REVALIDATE | ATA_EH_RESET |
 				  ATA_EH_ENABLE_LINK,
 
@@ -324,6 +405,7 @@ enum {
 	ATA_EHI_PRINTINFO	= (1 << 18), /* print configuration info */
 	ATA_EHI_SETMODE		= (1 << 19), /* configure transfer mode */
 	ATA_EHI_POST_SETMODE	= (1 << 20), /* revalidating after setmode */
+	ATA_EHI_DID_PRINT_QUIRKS = (1 << 21), /* already printed quirks info */
 
 	ATA_EHI_DID_RESET	= ATA_EHI_DID_SOFTRESET | ATA_EHI_DID_HARDRESET,
 
@@ -337,7 +419,6 @@ enum {
 	ATA_LINK_RESUME_TRIES	= 5,
 
 	/* how hard are we gonna try to probe/recover devices */
-	ATA_PROBE_MAX_TRIES	= 3,
 	ATA_EH_DEV_TRIES	= 3,
 	ATA_EH_PMP_TRIES	= 5,
 	ATA_EH_PMP_LINK_TRIES	= 3,
@@ -347,45 +428,9 @@ enum {
 	/* This should match the actual table size of
 	 * ata_eh_cmd_timeout_table in libata-eh.c.
 	 */
-	ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 7,
-
-	/* Horkage types. May be set by libata or controller on drives
-	   (some horkage may be drive/controller pair dependent */
-
-	ATA_HORKAGE_DIAGNOSTIC	= (1 << 0),	/* Failed boot diag */
-	ATA_HORKAGE_NODMA	= (1 << 1),	/* DMA problems */
-	ATA_HORKAGE_NONCQ	= (1 << 2),	/* Don't use NCQ */
-	ATA_HORKAGE_MAX_SEC_128	= (1 << 3),	/* Limit max sects to 128 */
-	ATA_HORKAGE_BROKEN_HPA	= (1 << 4),	/* Broken HPA */
-	ATA_HORKAGE_DISABLE	= (1 << 5),	/* Disable it */
-	ATA_HORKAGE_HPA_SIZE	= (1 << 6),	/* native size off by one */
-	ATA_HORKAGE_IVB		= (1 << 8),	/* cbl det validity bit bugs */
-	ATA_HORKAGE_STUCK_ERR	= (1 << 9),	/* stuck ERR on next PACKET */
-	ATA_HORKAGE_BRIDGE_OK	= (1 << 10),	/* no bridge limits */
-	ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands
-						    not multiple of 16 bytes */
-	ATA_HORKAGE_FIRMWARE_WARN = (1 << 12),	/* firmware update warning */
-	ATA_HORKAGE_1_5_GBPS	= (1 << 13),	/* force 1.5 Gbps */
-	ATA_HORKAGE_NOSETXFER	= (1 << 14),	/* skip SETXFER, SATA only */
-	ATA_HORKAGE_BROKEN_FPDMA_AA	= (1 << 15),	/* skip AA */
-	ATA_HORKAGE_DUMP_ID	= (1 << 16),	/* dump IDENTIFY data */
-	ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17),	/* Set max sects to 65535 */
-	ATA_HORKAGE_ATAPI_DMADIR = (1 << 18),	/* device requires dmadir */
-	ATA_HORKAGE_NO_NCQ_TRIM	= (1 << 19),	/* don't use queued TRIM */
-	ATA_HORKAGE_NOLPM	= (1 << 20),	/* don't use LPM */
-	ATA_HORKAGE_WD_BROKEN_LPM = (1 << 21),	/* some WDs have broken LPM */
-	ATA_HORKAGE_ZERO_AFTER_TRIM = (1 << 22),/* guarantees zero after trim */
-	ATA_HORKAGE_NO_DMA_LOG	= (1 << 23),	/* don't use DMA for log read */
-	ATA_HORKAGE_NOTRIM	= (1 << 24),	/* don't use TRIM */
-	ATA_HORKAGE_MAX_SEC_1024 = (1 << 25),	/* Limit max sects to 1024 */
-	ATA_HORKAGE_MAX_TRIM_128M = (1 << 26),	/* Limit max trim size to 128M */
-	ATA_HORKAGE_NO_NCQ_ON_ATI = (1 << 27),	/* Disable NCQ on ATI chipset */
-	ATA_HORKAGE_NO_ID_DEV_LOG = (1 << 28),	/* Identify device log missing */
-	ATA_HORKAGE_NO_LOG_DIR	= (1 << 29),	/* Do not read log directory */
-	ATA_HORKAGE_NO_FUA	= (1 << 30),	/* Do not use FUA */
-
-	 /* DMA mask for user DMA control: User visible values; DO NOT
-	    renumber */
+	ATA_EH_CMD_TIMEOUT_TABLE_SIZE = 8,
+
+	/* User visible DMA mask for DMA control. DO NOT renumber. */
 	ATA_DMA_MASK_ATA	= (1 << 0),	/* DMA on ATA Disk */
 	ATA_DMA_MASK_ATAPI	= (1 << 1),	/* DMA on ATAPI */
 	ATA_DMA_MASK_CFA	= (1 << 2),	/* DMA on CF Card */
@@ -458,16 +503,28 @@ enum ata_completion_errors {
 };
 
 /*
- * Link power management policy: If you alter this, you also need to
- * alter libata-scsi.c (for the ascii descriptions)
+ * Link Power Management (LPM) policies.
+ *
+ * The default LPM policy to use for a device link is defined using these values
+ * with the CONFIG_SATA_MOBILE_LPM_POLICY config option and applied through the
+ * target_lpm_policy field of struct ata_port.
+ *
+ * If you alter this, you also need to alter the policy names used with the
+ * sysfs attribute link_power_management_policy defined in libata-sata.c.
  */
 enum ata_lpm_policy {
+	/* Keep firmware settings */
 	ATA_LPM_UNKNOWN,
+	/* No power savings (maximum performance) */
 	ATA_LPM_MAX_POWER,
+	/* HIPM (Partial) */
 	ATA_LPM_MED_POWER,
-	ATA_LPM_MED_POWER_WITH_DIPM, /* Med power + DIPM as win IRST does */
-	ATA_LPM_MIN_POWER_WITH_PARTIAL, /* Min Power + partial and slumber */
-	ATA_LPM_MIN_POWER, /* Min power + no partial (slumber only) */
+	/* HIPM (Partial) and DIPM (Partial and Slumber) */
+	ATA_LPM_MED_POWER_WITH_DIPM,
+	/* HIPM (Partial and DevSleep) and DIPM (Partial and Slumber) */
+	ATA_LPM_MIN_POWER_WITH_PARTIAL,
+	/* HIPM (Slumber and DevSleep) and DIPM (Partial and Slumber) */
+	ATA_LPM_MIN_POWER,
 };
 
 enum ata_lpm_hints {
@@ -492,6 +549,7 @@ typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes)
 
 extern struct device_attribute dev_attr_unload_heads;
 #ifdef CONFIG_SATA_HOST
+extern struct device_attribute dev_attr_link_power_management_supported;
 extern struct device_attribute dev_attr_link_power_management_policy;
 extern struct device_attribute dev_attr_ncq_prio_supported;
 extern struct device_attribute dev_attr_ncq_prio_enable;
@@ -644,13 +702,28 @@ struct ata_cpr {
 
 struct ata_cpr_log {
 	u8			nr_cpr;
-	struct ata_cpr		cpr[];
+	struct ata_cpr		cpr[] __counted_by(nr_cpr);
+};
+
+struct ata_cdl {
+	/*
+	 * Buffer to cache the CDL log page 18h (command duration descriptors)
+	 * for SCSI-ATA translation.
+	 */
+	u8			desc_log_buf[ATA_LOG_CDL_SIZE];
+
+	/*
+	 * Buffer to handle reading the sense data for successful NCQ Commands
+	 * log page for commands using a CDL with one of the limits policy set
+	 * to 0xD (successful completion with sense data available bit set).
+	 */
+	u8			ncq_sense_log_buf[ATA_LOG_SENSE_NCQ_SIZE];
 };
 
 struct ata_device {
 	struct ata_link		*link;
 	unsigned int		devno;		/* 0 or 1 */
-	unsigned int		horkage;	/* List of broken features */
+	unsigned int		quirks;		/* List of broken features */
 	unsigned long		flags;		/* ATA_DFLAG_xxx */
 	struct scsi_device	*sdev;		/* attached SCSI device */
 	void			*private_data;
@@ -693,6 +766,9 @@ struct ata_device {
 		u32		gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */
 	} ____cacheline_aligned;
 
+	/* General Purpose Log Directory log page */
+	u8			gp_log_dir[ATA_SECT_SIZE] ____cacheline_aligned;
+
 	/* DEVSLP Timing Variables from Identify Device Data Log */
 	u8			devslp_timing[ATA_LOG_DEVSLP_SIZE];
 
@@ -709,10 +785,16 @@ struct ata_device {
 	/* Concurrent positioning ranges */
 	struct ata_cpr_log	*cpr_log;
 
+	/* Command Duration Limits support */
+	struct ata_cdl		*cdl;
+
 	/* error history */
 	int			spdn_cnt;
 	/* ering is CLEAR_END, read comment above CLEAR_END */
 	struct ata_ering	ering;
+
+	/* For EH */
+	u8			sector_buf[ATA_SECT_SIZE] ____cacheline_aligned;
 };
 
 /* Fields between ATA_DEVICE_CLEAR_BEGIN and ATA_DEVICE_CLEAR_END are
@@ -798,7 +880,6 @@ struct ata_port {
 	/* Flags that change dynamically, protected by ap->lock */
 	unsigned int		pflags; /* ATA_PFLAG_xxx */
 	unsigned int		print_id; /* user visible unique port ID */
-	unsigned int            local_port_no; /* host local port num */
 	unsigned int		port_no; /* 0 based port no. inside the host */
 
 #ifdef CONFIG_ATA_SFF
@@ -836,7 +917,7 @@ struct ata_port {
 
 	struct mutex		scsi_scan_mutex;
 	struct delayed_work	hotplug_task;
-	struct work_struct	scsi_rescan_task;
+	struct delayed_work	scsi_rescan_task;
 
 	unsigned int		hsm_task_state;
 
@@ -859,8 +940,6 @@ struct ata_port {
 #ifdef CONFIG_ATA_ACPI
 	struct ata_acpi_gtm	__acpi_init_gtm; /* use ata_acpi_init_gtm() */
 #endif
-	/* owned by EH */
-	u8			sector_buf[ATA_SECT_SIZE] ____cacheline_aligned;
 };
 
 /* The following initializer overrides a method to NULL whether one of
@@ -870,6 +949,13 @@ struct ata_port {
  */
 #define ATA_OP_NULL		(void *)(unsigned long)(-ENOENT)
 
+struct ata_reset_operations {
+	ata_prereset_fn_t	prereset;
+	ata_reset_fn_t		softreset;
+	ata_reset_fn_t		hardreset;
+	ata_postreset_fn_t	postreset;
+};
+
 struct ata_port_operations {
 	/*
 	 * Command execution
@@ -896,14 +982,8 @@ struct ata_port_operations {
 
 	void (*freeze)(struct ata_port *ap);
 	void (*thaw)(struct ata_port *ap);
-	ata_prereset_fn_t	prereset;
-	ata_reset_fn_t		softreset;
-	ata_reset_fn_t		hardreset;
-	ata_postreset_fn_t	postreset;
-	ata_prereset_fn_t	pmp_prereset;
-	ata_reset_fn_t		pmp_softreset;
-	ata_reset_fn_t		pmp_hardreset;
-	ata_postreset_fn_t	pmp_postreset;
+	struct ata_reset_operations reset;
+	struct ata_reset_operations pmp_reset;
 	void (*error_handler)(struct ata_port *ap);
 	void (*lost_interrupt)(struct ata_port *ap);
 	void (*post_internal_cmd)(struct ata_queued_cmd *qc);
@@ -966,12 +1046,6 @@ struct ata_port_operations {
 					ssize_t size);
 
 	/*
-	 * Obsolete
-	 */
-	void (*phy_reset)(struct ata_port *ap);
-	void (*eng_timeout)(struct ata_port *ap);
-
-	/*
 	 * ->inherits must be the last field and all the preceding
 	 * fields must be pointers.
 	 */
@@ -1054,11 +1128,9 @@ static inline bool ata_port_is_frozen(const struct ata_port *ap)
 extern int ata_std_prereset(struct ata_link *link, unsigned long deadline);
 extern int ata_wait_after_reset(struct ata_link *link, unsigned long deadline,
 				int (*check_ready)(struct ata_link *link));
-extern int sata_std_hardreset(struct ata_link *link, unsigned int *class,
-			      unsigned long deadline);
 extern void ata_std_postreset(struct ata_link *link, unsigned int *classes);
 
-extern struct ata_host *ata_host_alloc(struct device *dev, int max_ports);
+extern struct ata_host *ata_host_alloc(struct device *dev, int n_ports);
 extern struct ata_host *ata_host_alloc_pinfo(struct device *dev,
 			const struct ata_port_info * const * ppi, int n_ports);
 extern void ata_host_get(struct ata_host *host);
@@ -1071,7 +1143,6 @@ extern int ata_host_activate(struct ata_host *host, int irq,
 			     const struct scsi_host_template *sht);
 extern void ata_host_detach(struct ata_host *host);
 extern void ata_host_init(struct ata_host *, struct device *, struct ata_port_operations *);
-extern int ata_scsi_detect(struct scsi_host_template *sht);
 extern int ata_scsi_ioctl(struct scsi_device *dev, unsigned int cmd,
 			  void __user *arg);
 #ifdef CONFIG_COMPAT
@@ -1105,7 +1176,7 @@ static inline void ata_sas_port_resume(struct ata_port *ap)
 extern int ata_ratelimit(void);
 extern void ata_msleep(struct ata_port *ap, unsigned int msecs);
 extern u32 ata_wait_register(struct ata_port *ap, void __iomem *reg, u32 mask,
-			u32 val, unsigned long interval, unsigned long timeout);
+			     u32 val, unsigned int interval, unsigned int timeout);
 extern int atapi_cmd_type(u8 opcode);
 extern unsigned int ata_pack_xfermask(unsigned int pio_mask,
 				      unsigned int mwdma_mask,
@@ -1120,7 +1191,6 @@ extern int ata_xfer_mode2shift(u8 xfer_mode);
 extern const char *ata_mode_string(unsigned int xfer_mask);
 extern unsigned int ata_id_xfermask(const u16 *id);
 extern int ata_std_qc_defer(struct ata_queued_cmd *qc);
-extern enum ata_completion_errors ata_noop_qc_prep(struct ata_queued_cmd *qc);
 extern void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
 		 unsigned int n_elem);
 extern unsigned int ata_dev_classify(const struct ata_taskfile *tf);
@@ -1137,17 +1207,24 @@ extern void ata_qc_complete(struct ata_queued_cmd *qc);
 extern u64 ata_qc_get_active(struct ata_port *ap);
 extern void ata_scsi_simulate(struct ata_device *dev, struct scsi_cmnd *cmd);
 extern int ata_std_bios_param(struct scsi_device *sdev,
-			      struct block_device *bdev,
+			      struct gendisk *unused,
 			      sector_t capacity, int geom[]);
 extern void ata_scsi_unlock_native_capacity(struct scsi_device *sdev);
-extern int ata_scsi_slave_config(struct scsi_device *sdev);
-extern void ata_scsi_slave_destroy(struct scsi_device *sdev);
+extern int ata_scsi_sdev_init(struct scsi_device *sdev);
+int ata_scsi_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim);
+extern void ata_scsi_sdev_destroy(struct scsi_device *sdev);
 extern int ata_scsi_change_queue_depth(struct scsi_device *sdev,
 				       int queue_depth);
-extern int ata_change_queue_depth(struct ata_port *ap, struct ata_device *dev,
-				  struct scsi_device *sdev, int queue_depth);
+extern int ata_change_queue_depth(struct ata_port *ap, struct scsi_device *sdev,
+				  int queue_depth);
+extern int ata_ncq_prio_supported(struct ata_port *ap, struct scsi_device *sdev,
+				  bool *supported);
+extern int ata_ncq_prio_enabled(struct ata_port *ap, struct scsi_device *sdev,
+				bool *enabled);
+extern int ata_ncq_prio_enable(struct ata_port *ap, struct scsi_device *sdev,
+			       bool enable);
 extern struct ata_device *ata_dev_pair(struct ata_device *adev);
-extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
+int ata_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
 extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
 extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q);
 
@@ -1155,11 +1232,11 @@ extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *
  * SATA specific code - drivers/ata/libata-sata.c
  */
 #ifdef CONFIG_SATA_HOST
-extern const unsigned long sata_deb_timing_normal[];
-extern const unsigned long sata_deb_timing_hotplug[];
-extern const unsigned long sata_deb_timing_long[];
+extern const unsigned int sata_deb_timing_normal[];
+extern const unsigned int sata_deb_timing_hotplug[];
+extern const unsigned int sata_deb_timing_long[];
 
-static inline const unsigned long *
+static inline const unsigned int *
 sata_ehc_deb_timing(struct ata_eh_context *ehc)
 {
 	if (ehc->i.flags & ATA_EHI_HOTPLUGGED)
@@ -1173,14 +1250,16 @@ extern int sata_scr_read(struct ata_link *link, int reg, u32 *val);
 extern int sata_scr_write(struct ata_link *link, int reg, u32 val);
 extern int sata_scr_write_flush(struct ata_link *link, int reg, u32 val);
 extern int sata_set_spd(struct ata_link *link);
+int sata_std_hardreset(struct ata_link *link, unsigned int *class,
+		       unsigned long deadline);
 extern int sata_link_hardreset(struct ata_link *link,
-			const unsigned long *timing, unsigned long deadline,
+			const unsigned int *timing, unsigned long deadline,
 			bool *online, int (*check_ready)(struct ata_link *));
-extern int sata_link_resume(struct ata_link *link, const unsigned long *params,
+extern int sata_link_resume(struct ata_link *link, const unsigned int *params,
 			    unsigned long deadline);
 extern void ata_eh_analyze_ncq_error(struct ata_link *link);
 #else
-static inline const unsigned long *
+static inline const unsigned int *
 sata_ehc_deb_timing(struct ata_eh_context *ehc)
 {
 	return NULL;
@@ -1199,8 +1278,13 @@ static inline int sata_scr_write_flush(struct ata_link *link, int reg, u32 val)
 	return -EOPNOTSUPP;
 }
 static inline int sata_set_spd(struct ata_link *link) { return -EOPNOTSUPP; }
+static inline int sata_std_hardreset(struct ata_link *link, unsigned int *class,
+				     unsigned long deadline)
+{
+	return -EOPNOTSUPP;
+}
 static inline int sata_link_hardreset(struct ata_link *link,
-				      const unsigned long *timing,
+				      const unsigned int *timing,
 				      unsigned long deadline,
 				      bool *online,
 				      int (*check_ready)(struct ata_link *))
@@ -1210,7 +1294,7 @@ static inline int sata_link_hardreset(struct ata_link *link,
 	return -EOPNOTSUPP;
 }
 static inline int sata_link_resume(struct ata_link *link,
-				   const unsigned long *params,
+				   const unsigned int *params,
 				   unsigned long deadline)
 {
 	return -EOPNOTSUPP;
@@ -1218,21 +1302,17 @@ static inline int sata_link_resume(struct ata_link *link,
 static inline void ata_eh_analyze_ncq_error(struct ata_link *link) { }
 #endif
 extern int sata_link_debounce(struct ata_link *link,
-			const unsigned long *params, unsigned long deadline);
+			      const unsigned int *params, unsigned long deadline);
 extern int sata_link_scr_lpm(struct ata_link *link, enum ata_lpm_policy policy,
 			     bool spm_wakeup);
 extern int ata_slave_link_init(struct ata_port *ap);
-extern void ata_sas_port_destroy(struct ata_port *);
-extern struct ata_port *ata_sas_port_alloc(struct ata_host *,
-					   struct ata_port_info *, struct Scsi_Host *);
-extern void ata_sas_async_probe(struct ata_port *ap);
-extern int ata_sas_sync_probe(struct ata_port *ap);
-extern int ata_sas_port_init(struct ata_port *);
-extern int ata_sas_port_start(struct ata_port *ap);
-extern int ata_sas_tport_add(struct device *parent, struct ata_port *ap);
-extern void ata_sas_tport_delete(struct ata_port *ap);
-extern void ata_sas_port_stop(struct ata_port *ap);
-extern int ata_sas_slave_configure(struct scsi_device *, struct ata_port *);
+extern void ata_port_probe(struct ata_port *ap);
+extern struct ata_port *ata_port_alloc(struct ata_host *host);
+extern void ata_port_free(struct ata_port *ap);
+extern int ata_tport_add(struct device *parent, struct ata_port *ap);
+extern void ata_tport_delete(struct ata_port *ap);
+int ata_sas_sdev_configure(struct scsi_device *sdev, struct queue_limits *lim,
+			   struct ata_port *ap);
 extern int ata_sas_queuecmd(struct scsi_cmnd *cmd, struct ata_port *ap);
 extern void ata_tf_to_fis(const struct ata_taskfile *tf,
 			  u8 pmp, int is_cmd, u8 *fis);
@@ -1276,7 +1356,7 @@ extern int ata_pci_device_resume(struct pci_dev *pdev);
 
 struct platform_device;
 
-extern int ata_platform_remove_one(struct platform_device *pdev);
+extern void ata_platform_remove_one(struct platform_device *pdev);
 
 /*
  * ACPI - drivers/ata/libata-acpi.c
@@ -1292,7 +1372,7 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm);
 int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm);
 unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 				   const struct ata_acpi_gtm *gtm);
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm);
+int ata_acpi_cbl_pata_type(struct ata_port *ap);
 #else
 static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap)
 {
@@ -1317,10 +1397,9 @@ static inline unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 	return 0;
 }
 
-static inline int ata_acpi_cbl_80wire(struct ata_port *ap,
-				      const struct ata_acpi_gtm *gtm)
+static inline int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
-	return 0;
+	return ATA_CBL_PATA40;
 }
 #endif
 
@@ -1339,9 +1418,6 @@ extern void ata_eh_thaw_port(struct ata_port *ap);
 extern void ata_eh_qc_complete(struct ata_queued_cmd *qc);
 extern void ata_eh_qc_retry(struct ata_queued_cmd *qc);
 
-extern void ata_do_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
-		      ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
-		      ata_postreset_fn_t postreset);
 extern void ata_std_error_handler(struct ata_port *ap);
 extern void ata_std_sched_eh(struct ata_port *ap);
 extern void ata_std_end_eh(struct ata_port *ap);
@@ -1388,7 +1464,8 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 	.this_id		= ATA_SHT_THIS_ID,		\
 	.emulated		= ATA_SHT_EMULATED,		\
 	.proc_name		= drv_name,			\
-	.slave_destroy		= ata_scsi_slave_destroy,	\
+	.sdev_init		= ata_scsi_sdev_init,		\
+	.sdev_destroy		= ata_scsi_sdev_destroy,	\
 	.bios_param		= ata_std_bios_param,		\
 	.unlock_native_capacity	= ata_scsi_unlock_native_capacity,\
 	.max_sectors		= ATA_MAX_SECTORS_LBA48
@@ -1396,14 +1473,14 @@ extern const struct attribute_group *ata_common_sdev_groups[];
 #define ATA_SUBBASE_SHT(drv_name)				\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= ATA_DEF_QUEUE,		\
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
-	.slave_configure	= ata_scsi_slave_config
+	.tag_alloc_policy_rr	= true,				\
+	.sdev_configure		= ata_scsi_sdev_configure
 
 #define ATA_SUBBASE_SHT_QD(drv_name, drv_qd)			\
 	__ATA_BASE_SHT(drv_name),				\
 	.can_queue		= drv_qd,			\
-	.tag_alloc_policy	= BLK_TAG_ALLOC_RR,		\
-	.slave_configure	= ata_scsi_slave_config
+	.tag_alloc_policy_rr	= true,				\
+	.sdev_configure		= ata_scsi_sdev_configure
 
 #define ATA_BASE_SHT(drv_name)					\
 	ATA_SUBBASE_SHT(drv_name),				\
@@ -1521,7 +1598,17 @@ do {								\
 #define ata_dev_dbg(dev, fmt, ...)				\
 	ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__)
 
-void ata_print_version(const struct device *dev, const char *version);
+#define ata_dev_warn_once(dev, fmt, ...)			\
+	pr_warn_once("ata%u.%02u: " fmt,			\
+		     (dev)->link->ap->print_id,			\
+		     (dev)->link->pmp + (dev)->devno,		\
+		     ##__VA_ARGS__)
+
+static inline void ata_print_version_once(const struct device *dev,
+					  const char *version)
+{
+	dev_dbg_once(dev, "version %s\n", version);
+}
 
 /*
  * ata_eh_info helpers
@@ -1549,6 +1636,13 @@ void ata_port_desc(struct ata_port *ap, const char *fmt, ...);
 extern void ata_port_pbar_desc(struct ata_port *ap, int bar, ssize_t offset,
 			       const char *name);
 #endif
+static inline void ata_port_desc_misc(struct ata_port *ap, int irq)
+{
+	ata_port_desc(ap, "irq %d", irq);
+	ata_port_desc(ap, "lpm-pol %d", ap->target_lpm_policy);
+	if (ap->pflags & ATA_PFLAG_EXTERNAL)
+		ata_port_desc(ap, "ext");
+}
 
 static inline bool ata_tag_internal(unsigned int tag)
 {
@@ -1769,7 +1863,7 @@ static inline struct ata_queued_cmd *ata_qc_from_tag(struct ata_port *ap,
 {
 	struct ata_queued_cmd *qc = __ata_qc_from_tag(ap, tag);
 
-	if (unlikely(!qc) || !ap->ops->error_handler)
+	if (unlikely(!qc))
 		return qc;
 
 	if ((qc->flags & (ATA_QCFLAG_ACTIVE |
@@ -1860,7 +1954,7 @@ static inline int ata_check_ready(u8 status)
 }
 
 static inline unsigned long ata_deadline(unsigned long from_jiffies,
-					 unsigned long timeout_msecs)
+					 unsigned int timeout_msecs)
 {
 	return from_jiffies + msecs_to_jiffies(timeout_msecs);
 }
@@ -1869,23 +1963,21 @@ static inline unsigned long ata_deadline(unsigned long from_jiffies,
    change in future hardware and specs, secondly 0xFF means 'no DMA' but is
    > UDMA_0. Dyma ddreigiau */
 
-static inline int ata_using_mwdma(struct ata_device *adev)
+static inline bool ata_using_mwdma(struct ata_device *adev)
 {
-	if (adev->dma_mode >= XFER_MW_DMA_0 && adev->dma_mode <= XFER_MW_DMA_4)
-		return 1;
-	return 0;
+	return adev->dma_mode >= XFER_MW_DMA_0 &&
+		adev->dma_mode <= XFER_MW_DMA_4;
 }
 
-static inline int ata_using_udma(struct ata_device *adev)
+static inline bool ata_using_udma(struct ata_device *adev)
 {
-	if (adev->dma_mode >= XFER_UDMA_0 && adev->dma_mode <= XFER_UDMA_7)
-		return 1;
-	return 0;
+	return adev->dma_mode >= XFER_UDMA_0 &&
+		adev->dma_mode <= XFER_UDMA_7;
 }
 
-static inline int ata_dma_enabled(struct ata_device *adev)
+static inline bool ata_dma_enabled(struct ata_device *adev)
 {
-	return (adev->dma_mode == 0xFF ? 0 : 1);
+	return adev->dma_mode != 0xFF;
 }
 
 /**************************************************************************
@@ -1945,7 +2037,6 @@ extern unsigned int ata_sff_data_xfer(struct ata_queued_cmd *qc,
 extern unsigned int ata_sff_data_xfer32(struct ata_queued_cmd *qc,
 			unsigned char *buf, unsigned int buflen, int rw);
 extern void ata_sff_irq_on(struct ata_port *ap);
-extern void ata_sff_irq_clear(struct ata_port *ap);
 extern int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 			    u8 status, int in_wq);
 extern void ata_sff_queue_work(struct work_struct *work);
@@ -2070,6 +2161,12 @@ static inline u8 ata_wait_idle(struct ata_port *ap)
 
 	return status;
 }
+#else /* CONFIG_ATA_SFF */
+static inline int sata_sff_hardreset(struct ata_link *link, unsigned int *class,
+				     unsigned long deadline)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_ATA_SFF */
 
 #endif /* __LINUX_LIBATA_H__ */
diff --git a/include/linux/libgcc.h b/include/linux/libgcc.h
index fc388da6a027..0d68f9d6a6a7 100644
--- a/include/linux/libgcc.h
+++ b/include/linux/libgcc.h
@@ -34,4 +34,8 @@ long long notrace __lshrdi3(long long u, word_type b);
 long long notrace __muldi3(long long u, long long v);
 word_type notrace __ucmpdi2(unsigned long long a, unsigned long long b);
 
+#ifdef CONFIG_HAVE_ARCH_LIBGCC_H
+#include <asm/libgcc.h>
+#endif
+
 #endif /* __ASM_LIBGCC_H */
diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index e772aae71843..28f086c4a187 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -6,12 +6,12 @@
  */
 #ifndef __LIBNVDIMM_H__
 #define __LIBNVDIMM_H__
-#include <linux/kernel.h>
+
+#include <linux/io.h>
 #include <linux/sizes.h>
+#include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
-#include <linux/spinlock.h>
-#include <linux/bio.h>
 
 struct badrange_entry {
 	u64 start;
@@ -80,7 +80,9 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc);
 
+struct attribute_group;
 struct device_node;
+struct module;
 struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
 	unsigned long cmd_mask;
@@ -121,6 +123,8 @@ struct nd_mapping_desc {
 	int position;
 };
 
+struct bio;
+struct resource;
 struct nd_region;
 struct nd_region_desc {
 	struct resource *res;
@@ -147,8 +151,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev,
 	return (void __iomem *) devm_nvdimm_memremap(dev, offset, size, 0);
 }
 
-struct nvdimm_bus;
-
 /*
  * Note that separate bits for locked + unlocked are defined so that
  * 'flags == 0' corresponds to an error / not-supported state.
@@ -238,6 +240,9 @@ struct nvdimm_fw_ops {
 	int (*arm)(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arg);
 };
 
+struct kobject;
+struct nvdimm_bus;
+
 void badrange_init(struct badrange *badrange);
 int badrange_add(struct badrange *badrange, u64 addr, u64 length);
 void badrange_forget(struct badrange *badrange, phys_addr_t start,
diff --git a/include/linux/libps2.h b/include/linux/libps2.h
index 53f7e4d0f4b7..9ca9ce4e6e64 100644
--- a/include/linux/libps2.h
+++ b/include/linux/libps2.h
@@ -8,44 +8,59 @@
  */
 
 #include <linux/bitops.h>
+#include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/types.h>
 #include <linux/wait.h>
 
-#define PS2_CMD_SETSCALE11	0x00e6
-#define PS2_CMD_SETRES		0x10e8
-#define PS2_CMD_GETID		0x02f2
-#define PS2_CMD_RESET_BAT	0x02ff
+struct ps2dev;
 
-#define PS2_RET_BAT		0xaa
-#define PS2_RET_ID		0x00
-#define PS2_RET_ACK		0xfa
-#define PS2_RET_NAK		0xfe
-#define PS2_RET_ERR		0xfc
+/**
+ * enum ps2_disposition - indicates how received byte should be handled
+ * @PS2_PROCESS: pass to the main protocol handler, process normally
+ * @PS2_IGNORE: skip the byte
+ * @PS2_ERROR: do not process the byte, abort command in progress
+ */
+enum ps2_disposition {
+	PS2_PROCESS,
+	PS2_IGNORE,
+	PS2_ERROR,
+};
 
-#define PS2_FLAG_ACK		BIT(0)	/* Waiting for ACK/NAK */
-#define PS2_FLAG_CMD		BIT(1)	/* Waiting for a command to finish */
-#define PS2_FLAG_CMD1		BIT(2)	/* Waiting for the first byte of command response */
-#define PS2_FLAG_WAITID		BIT(3)	/* Command executing is GET ID */
-#define PS2_FLAG_NAK		BIT(4)	/* Last transmission was NAKed */
-#define PS2_FLAG_ACK_CMD	BIT(5)	/* Waiting to ACK the command (first) byte */
+typedef enum ps2_disposition (*ps2_pre_receive_handler_t)(struct ps2dev *, u8,
+							  unsigned int);
+typedef void (*ps2_receive_handler_t)(struct ps2dev *, u8);
 
+/**
+ * struct ps2dev - represents a device using PS/2 protocol
+ * @serio: a serio port used by the PS/2 device
+ * @cmd_mutex: a mutex ensuring that only one command is executing at a time
+ * @wait: a waitqueue used to signal completion from the serio interrupt handler
+ * @flags: various internal flags indicating stages of PS/2 command execution
+ * @cmdbuf: buffer holding command response
+ * @cmdcnt: outstanding number of bytes of the command response
+ * @nak: a byte transmitted by the device when it refuses command
+ * @pre_receive_handler: checks communication errors and returns disposition
+ * (&enum ps2_disposition) of the received data byte
+ * @receive_handler: main handler of particular PS/2 protocol, such as keyboard
+ *   or mouse protocol
+ */
 struct ps2dev {
 	struct serio *serio;
-
-	/* Ensures that only one command is executing at a time */
 	struct mutex cmd_mutex;
-
-	/* Used to signal completion from interrupt handler */
 	wait_queue_head_t wait;
-
 	unsigned long flags;
 	u8 cmdbuf[8];
 	u8 cmdcnt;
 	u8 nak;
+
+	ps2_pre_receive_handler_t pre_receive_handler;
+	ps2_receive_handler_t receive_handler;
 };
 
-void ps2_init(struct ps2dev *ps2dev, struct serio *serio);
+void ps2_init(struct ps2dev *ps2dev, struct serio *serio,
+	      ps2_pre_receive_handler_t pre_receive_handler,
+	      ps2_receive_handler_t receive_handler);
 int ps2_sendbyte(struct ps2dev *ps2dev, u8 byte, unsigned int timeout);
 void ps2_drain(struct ps2dev *ps2dev, size_t maxbytes, unsigned int timeout);
 void ps2_begin_command(struct ps2dev *ps2dev);
@@ -53,9 +68,8 @@ void ps2_end_command(struct ps2dev *ps2dev);
 int __ps2_command(struct ps2dev *ps2dev, u8 *param, unsigned int command);
 int ps2_command(struct ps2dev *ps2dev, u8 *param, unsigned int command);
 int ps2_sliced_command(struct ps2dev *ps2dev, u8 command);
-bool ps2_handle_ack(struct ps2dev *ps2dev, u8 data);
-bool ps2_handle_response(struct ps2dev *ps2dev, u8 data);
-void ps2_cmd_aborted(struct ps2dev *ps2dev);
 bool ps2_is_keyboard_id(u8 id);
 
+irqreturn_t ps2_interrupt(struct serio *serio, u8 data, unsigned int flags);
+
 #endif /* _LIBPS2_H */
diff --git a/include/linux/limits.h b/include/linux/limits.h
index f6bcc9369010..38eb7f6f7e88 100644
--- a/include/linux/limits.h
+++ b/include/linux/limits.h
@@ -10,6 +10,8 @@
 #define SSIZE_MAX	((ssize_t)(SIZE_MAX >> 1))
 #define PHYS_ADDR_MAX	(~(phys_addr_t)0)
 
+#define RESOURCE_SIZE_MAX	((resource_size_t)~0)
+
 #define U8_MAX		((u8)~0U)
 #define S8_MAX		((s8)(U8_MAX >> 1))
 #define S8_MIN		((s8)(-S8_MAX - 1))
diff --git a/include/linux/linkage.h b/include/linux/linkage.h
index 5c8865bb59d9..b11660b706c5 100644
--- a/include/linux/linkage.h
+++ b/include/linux/linkage.h
@@ -134,10 +134,6 @@
 	.size name, .-name
 #endif
 
-/* If symbol 'name' is treated as a subroutine (gets called, and returns)
- * then please use ENDPROC to mark 'name' as STT_FUNC for the benefit of
- * static analysis tools such as stack depth analyzer.
- */
 #ifndef ENDPROC
 /* deprecated, use SYM_FUNC_END */
 #define ENDPROC(name) \
diff --git a/include/linux/linkmode.h b/include/linux/linkmode.h
index 15e0e0209da4..3b9de09871f6 100644
--- a/include/linux/linkmode.h
+++ b/include/linux/linkmode.h
@@ -10,6 +10,11 @@ static inline void linkmode_zero(unsigned long *dst)
 	bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
+static inline void linkmode_fill(unsigned long *dst)
+{
+	bitmap_fill(dst, __ETHTOOL_LINK_MODE_MASK_NBITS);
+}
+
 static inline void linkmode_copy(unsigned long *dst, const unsigned long *src)
 {
 	bitmap_copy(dst, src, __ETHTOOL_LINK_MODE_MASK_NBITS);
@@ -32,16 +37,17 @@ static inline bool linkmode_empty(const unsigned long *src)
 	return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static inline int linkmode_andnot(unsigned long *dst, const unsigned long *src1,
-				  const unsigned long *src2)
+static inline bool linkmode_andnot(unsigned long *dst,
+				   const unsigned long *src1,
+				   const unsigned long *src2)
 {
 	return bitmap_andnot(dst, src1, src2,  __ETHTOOL_LINK_MODE_MASK_NBITS);
 }
 
-static inline void linkmode_set_bit(int nr, volatile unsigned long *addr)
-{
-	__set_bit(nr, addr);
-}
+#define linkmode_test_bit	test_bit
+#define linkmode_set_bit	__set_bit
+#define linkmode_clear_bit	__clear_bit
+#define linkmode_mod_bit	__assign_bit
 
 static inline void linkmode_set_bit_array(const int *array, int array_size,
 					  unsigned long *addr)
@@ -52,25 +58,6 @@ static inline void linkmode_set_bit_array(const int *array, int array_size,
 		linkmode_set_bit(array[i], addr);
 }
 
-static inline void linkmode_clear_bit(int nr, volatile unsigned long *addr)
-{
-	__clear_bit(nr, addr);
-}
-
-static inline void linkmode_mod_bit(int nr, volatile unsigned long *addr,
-				    int set)
-{
-	if (set)
-		linkmode_set_bit(nr, addr);
-	else
-		linkmode_clear_bit(nr, addr);
-}
-
-static inline int linkmode_test_bit(int nr, const volatile unsigned long *addr)
-{
-	return test_bit(nr, addr);
-}
-
 static inline int linkmode_equal(const unsigned long *src1,
 				 const unsigned long *src2)
 {
diff --git a/include/linux/linux_logo.h b/include/linux/linux_logo.h
index d4d5b93efe84..e37699b7e839 100644
--- a/include/linux/linux_logo.h
+++ b/include/linux/linux_logo.h
@@ -10,9 +10,6 @@
  *  Copyright (C) 2001 Greg Banks <gnb@alphalink.com.au>
  *  Copyright (C) 2001 Jan-Benedict Glaw <jbglaw@lug-owl.de>
  *  Copyright (C) 2003 Geert Uytterhoeven <geert@linux-m68k.org>
- *
- *  Serial_console ascii image can be any size,
- *  but should contain %s to display the version
  */
 
 #include <linux/init.h>
diff --git a/include/linux/list.h b/include/linux/list.h
index f10344dbad4d..00ea8e5fb88b 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -20,8 +20,16 @@
  * using the generic single-entry routines.
  */
 
+/**
+ * LIST_HEAD_INIT - initialize a &struct list_head's links to point to itself
+ * @name: name of the list_head
+ */
 #define LIST_HEAD_INIT(name) { &(name), &(name) }
 
+/**
+ * LIST_HEAD - definition of a &struct list_head with initialization values
+ * @name: name of the list_head
+ */
 #define LIST_HEAD(name) \
 	struct list_head name = LIST_HEAD_INIT(name)
 
@@ -38,11 +46,92 @@ static inline void INIT_LIST_HEAD(struct list_head *list)
 	WRITE_ONCE(list->prev, list);
 }
 
+#ifdef CONFIG_LIST_HARDENED
+
 #ifdef CONFIG_DEBUG_LIST
-extern bool __list_add_valid(struct list_head *new,
-			      struct list_head *prev,
-			      struct list_head *next);
-extern bool __list_del_entry_valid(struct list_head *entry);
+# define __list_valid_slowpath
+#else
+# define __list_valid_slowpath __cold __preserve_most
+#endif
+
+/*
+ * Performs the full set of list corruption checks before __list_add().
+ * On list corruption reports a warning, and returns false.
+ */
+bool __list_valid_slowpath __list_add_valid_or_report(struct list_head *new,
+						      struct list_head *prev,
+						      struct list_head *next);
+
+/*
+ * Performs list corruption checks before __list_add(). Returns false if a
+ * corruption is detected, true otherwise.
+ *
+ * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking
+ * inline to catch non-faulting corruptions, and only if a corruption is
+ * detected calls the reporting function __list_add_valid_or_report().
+ */
+static __always_inline bool __list_add_valid(struct list_head *new,
+					     struct list_head *prev,
+					     struct list_head *next)
+{
+	bool ret = true;
+
+	if (!IS_ENABLED(CONFIG_DEBUG_LIST)) {
+		/*
+		 * With the hardening version, elide checking if next and prev
+		 * are NULL, since the immediate dereference of them below would
+		 * result in a fault if NULL.
+		 *
+		 * With the reduced set of checks, we can afford to inline the
+		 * checks, which also gives the compiler a chance to elide some
+		 * of them completely if they can be proven at compile-time. If
+		 * one of the pre-conditions does not hold, the slow-path will
+		 * show a report which pre-condition failed.
+		 */
+		if (likely(next->prev == prev && prev->next == next && new != prev && new != next))
+			return true;
+		ret = false;
+	}
+
+	ret &= __list_add_valid_or_report(new, prev, next);
+	return ret;
+}
+
+/*
+ * Performs the full set of list corruption checks before __list_del_entry().
+ * On list corruption reports a warning, and returns false.
+ */
+bool __list_valid_slowpath __list_del_entry_valid_or_report(struct list_head *entry);
+
+/*
+ * Performs list corruption checks before __list_del_entry(). Returns false if a
+ * corruption is detected, true otherwise.
+ *
+ * With CONFIG_LIST_HARDENED only, performs minimal list integrity checking
+ * inline to catch non-faulting corruptions, and only if a corruption is
+ * detected calls the reporting function __list_del_entry_valid_or_report().
+ */
+static __always_inline bool __list_del_entry_valid(struct list_head *entry)
+{
+	bool ret = true;
+
+	if (!IS_ENABLED(CONFIG_DEBUG_LIST)) {
+		struct list_head *prev = entry->prev;
+		struct list_head *next = entry->next;
+
+		/*
+		 * With the hardening version, elide checking if next and prev
+		 * are NULL, LIST_POISON1 or LIST_POISON2, since the immediate
+		 * dereference of them below would result in a fault.
+		 */
+		if (likely(prev->next == entry && next->prev == entry))
+			return true;
+		ret = false;
+	}
+
+	ret &= __list_del_entry_valid_or_report(entry);
+	return ret;
+}
 #else
 static inline bool __list_add_valid(struct list_head *new,
 				struct list_head *prev,
@@ -556,6 +645,20 @@ static inline void list_splice_tail_init(struct list_head *list,
 })
 
 /**
+ * list_last_entry_or_null - get the last element from a list
+ * @ptr:	the list head to take the element from.
+ * @type:	the type of the struct this is embedded in.
+ * @member:	the name of the list_head within the struct.
+ *
+ * Note that if the list is empty, it returns NULL.
+ */
+#define list_last_entry_or_null(ptr, type, member) ({ \
+	struct list_head *head__ = (ptr); \
+	struct list_head *pos__ = READ_ONCE(head__->prev); \
+	pos__ != head__ ? list_entry(pos__, type, member) : NULL; \
+})
+
+/**
  * list_next_entry - get the next element in list
  * @pos:	the type * to cursor
  * @member:	the name of the list_head within the struct.
@@ -606,16 +709,6 @@ static inline void list_splice_tail_init(struct list_head *list,
 	for (pos = (head)->next; !list_is_head(pos, (head)); pos = pos->next)
 
 /**
- * list_for_each_rcu - Iterate over a list in an RCU-safe fashion
- * @pos:	the &struct list_head to use as a loop cursor.
- * @head:	the head for your list.
- */
-#define list_for_each_rcu(pos, head)		  \
-	for (pos = rcu_dereference((head)->next); \
-	     !list_is_head(pos, (head)); \
-	     pos = rcu_dereference(pos->next))
-
-/**
  * list_for_each_continue - continue iteration over a list
  * @pos:	the &struct list_head to use as a loop cursor.
  * @head:	the head for your list.
@@ -677,7 +770,7 @@ static inline size_t list_count_nodes(struct list_head *head)
  * @member:	the name of the list_head within the struct.
  */
 #define list_entry_is_head(pos, head, member)				\
-	(&pos->member == (head))
+	list_is_head(&pos->member, (head))
 
 /**
  * list_for_each_entry	-	iterate over list of given type
@@ -1030,6 +1123,26 @@ static inline void hlist_move_list(struct hlist_head *old,
 	old->first = NULL;
 }
 
+/**
+ * hlist_splice_init() - move all entries from one list to another
+ * @from: hlist_head from which entries will be moved
+ * @last: last entry on the @from list
+ * @to:   hlist_head to which entries will be moved
+ *
+ * @to can be empty, @from must contain at least @last.
+ */
+static inline void hlist_splice_init(struct hlist_head *from,
+				     struct hlist_node *last,
+				     struct hlist_head *to)
+{
+	if (to->first)
+		to->first->pprev = &last->next;
+	last->next = to->first;
+	to->first = from->first;
+	from->first->pprev = &to->first;
+	from->first = NULL;
+}
+
 #define hlist_entry(ptr, type, member) container_of(ptr,type,member)
 
 #define hlist_for_each(pos, head) \
@@ -1086,4 +1199,19 @@ static inline void hlist_move_list(struct hlist_head *old,
 	     pos && ({ n = pos->member.next; 1; });			\
 	     pos = hlist_entry_safe(n, typeof(*pos), member))
 
+/**
+ * hlist_count_nodes - count nodes in the hlist
+ * @head:	the head for your hlist.
+ */
+static inline size_t hlist_count_nodes(struct hlist_head *head)
+{
+	struct hlist_node *pos;
+	size_t count = 0;
+
+	hlist_for_each(pos, head)
+		count++;
+
+	return count;
+}
+
 #endif
diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h
index b35968ee9fb5..fe739d35a864 100644
--- a/include/linux/list_lru.h
+++ b/include/linux/list_lru.h
@@ -24,12 +24,16 @@ enum lru_status {
 	LRU_SKIP,		/* item cannot be locked, skip */
 	LRU_RETRY,		/* item not freeable. May drop the lock
 				   internally, but has to return locked. */
+	LRU_STOP,		/* stop lru list walking. May drop the lock
+				   internally, but has to return locked. */
 };
 
 struct list_lru_one {
 	struct list_head	list;
 	/* may become negative during memcg reparenting */
 	long			nr_items;
+	/* protects all fields above */
+	spinlock_t		lock;
 };
 
 struct list_lru_memcg {
@@ -39,33 +43,41 @@ struct list_lru_memcg {
 };
 
 struct list_lru_node {
-	/* protects all lists on the node, including per cgroup */
-	spinlock_t		lock;
 	/* global list, used for the root cgroup in cgroup aware lrus */
 	struct list_lru_one	lru;
-	long			nr_items;
+	atomic_long_t		nr_items;
 } ____cacheline_aligned_in_smp;
 
 struct list_lru {
 	struct list_lru_node	*node;
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 	struct list_head	list;
 	int			shrinker_id;
 	bool			memcg_aware;
 	struct xarray		xa;
 #endif
+#ifdef CONFIG_LOCKDEP
+	struct lock_class_key	*key;
+#endif
 };
 
 void list_lru_destroy(struct list_lru *lru);
 int __list_lru_init(struct list_lru *lru, bool memcg_aware,
-		    struct lock_class_key *key, struct shrinker *shrinker);
+		    struct shrinker *shrinker);
 
 #define list_lru_init(lru)				\
-	__list_lru_init((lru), false, NULL, NULL)
-#define list_lru_init_key(lru, key)			\
-	__list_lru_init((lru), false, (key), NULL)
+	__list_lru_init((lru), false, NULL)
 #define list_lru_init_memcg(lru, shrinker)		\
-	__list_lru_init((lru), true, NULL, shrinker)
+	__list_lru_init((lru), true, shrinker)
+
+static inline int list_lru_init_memcg_key(struct list_lru *lru, struct shrinker *shrinker,
+					  struct lock_class_key *key)
+{
+#ifdef CONFIG_LOCKDEP
+	lru->key = key;
+#endif
+	return list_lru_init_memcg(lru, shrinker);
+}
 
 int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru,
 			 gfp_t gfp);
@@ -73,34 +85,88 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren
 
 /**
  * list_lru_add: add an element to the lru list's tail
- * @list_lru: the lru pointer
+ * @lru: the lru pointer
  * @item: the item to be added.
+ * @nid: the node id of the sublist to add the item to.
+ * @memcg: the cgroup of the sublist to add the item to.
  *
  * If the element is already part of a list, this function returns doing
- * nothing. Therefore the caller does not need to keep state about whether or
- * not the element already belongs in the list and is allowed to lazy update
- * it. Note however that this is valid for *a* list, not *this* list. If
- * the caller organize itself in a way that elements can be in more than
- * one type of list, it is up to the caller to fully remove the item from
- * the previous list (with list_lru_del() for instance) before moving it
- * to @list_lru
- *
- * Return value: true if the list was updated, false otherwise
+ * nothing. This means that it is not necessary to keep state about whether or
+ * not the element already belongs in the list. That said, this logic only
+ * works if the item is in *this* list. If the item might be in some other
+ * list, then you cannot rely on this check and you must remove it from the
+ * other list before trying to insert it.
+ *
+ * The lru list consists of many sublists internally; the @nid and @memcg
+ * parameters are used to determine which sublist to insert the item into.
+ * It's important to use the right value of @nid and @memcg when deleting the
+ * item, since it might otherwise get deleted from the wrong sublist.
+ *
+ * This also applies when attempting to insert the item multiple times - if
+ * the item is currently in one sublist and you call list_lru_add() again, you
+ * must pass the right @nid and @memcg parameters so that the same sublist is
+ * used.
+ *
+ * You must ensure that the memcg is not freed during this call (e.g., with
+ * rcu or by taking a css refcnt).
+ *
+ * Return: true if the list was updated, false otherwise
+ */
+bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg);
+
+/**
+ * list_lru_add_obj: add an element to the lru list's tail
+ * @lru: the lru pointer
+ * @item: the item to be added.
+ *
+ * This function is similar to list_lru_add(), but the NUMA node and the
+ * memcg of the sublist is determined by @item list_head. This assumption is
+ * valid for slab objects LRU such as dentries, inodes, etc.
+ *
+ * Return: true if the list was updated, false otherwise
+ */
+bool list_lru_add_obj(struct list_lru *lru, struct list_head *item);
+
+/**
+ * list_lru_del: delete an element from the lru list
+ * @lru: the lru pointer
+ * @item: the item to be deleted.
+ * @nid: the node id of the sublist to delete the item from.
+ * @memcg: the cgroup of the sublist to delete the item from.
+ *
+ * This function works analogously as list_lru_add() in terms of list
+ * manipulation.
+ *
+ * The comments in list_lru_add() about an element already being in a list are
+ * also valid for list_lru_del(), that is, you can delete an item that has
+ * already been removed or never been added. However, if the item is in a
+ * list, it must be in *this* list, and you must pass the right value of @nid
+ * and @memcg so that the right sublist is used.
+ *
+ * You must ensure that the memcg is not freed during this call (e.g., with
+ * rcu or by taking a css refcnt). When a memcg is deleted, list_lru entries
+ * are automatically moved to the parent memcg. This is done in a race-free
+ * way, so during deletion of an memcg both the old and new memcg will resolve
+ * to the same sublist internally.
+ *
+ * Return: true if the list was updated, false otherwise
  */
-bool list_lru_add(struct list_lru *lru, struct list_head *item);
+bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+		    struct mem_cgroup *memcg);
 
 /**
- * list_lru_del: delete an element to the lru list
- * @list_lru: the lru pointer
+ * list_lru_del_obj: delete an element from the lru list
+ * @lru: the lru pointer
  * @item: the item to be deleted.
  *
- * This function works analogously as list_lru_add in terms of list
- * manipulation. The comments about an element already pertaining to
- * a list are also valid for list_lru_del.
+ * This function is similar to list_lru_del(), but the NUMA node and the
+ * memcg of the sublist is determined by @item list_head. This assumption is
+ * valid for slab objects LRU such as dentries, inodes, etc.
  *
- * Return value: true if the list was updated, false otherwise
+ * Return: true if the list was updated, false otherwise.
  */
-bool list_lru_del(struct list_lru *lru, struct list_head *item);
+bool list_lru_del_obj(struct list_lru *lru, struct list_head *item);
 
 /**
  * list_lru_count_one: return the number of objects currently held by @lru
@@ -108,9 +174,11 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item);
  * @nid: the node id to count from.
  * @memcg: the cgroup to count from.
  *
- * Always return a non-negative number, 0 for empty lists. There is no
- * guarantee that the list is not updated while the count is being computed.
- * Callers that want such a guarantee need to provide an outer lock.
+ * There is no guarantee that the list is not updated while the count is being
+ * computed. Callers that want such a guarantee need to provide an outer lock.
+ *
+ * Return: 0 for empty lists, otherwise the number of objects
+ * currently held by @lru.
  */
 unsigned long list_lru_count_one(struct list_lru *lru,
 				 int nid, struct mem_cgroup *memcg);
@@ -138,10 +206,10 @@ void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item,
 			   struct list_head *head);
 
 typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
-		struct list_lru_one *list, spinlock_t *lock, void *cb_arg);
+		struct list_lru_one *list, void *cb_arg);
 
 /**
- * list_lru_walk_one: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one: walk a @lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
  * @memcg: the cgroup to scan from.
@@ -150,24 +218,24 @@ typedef enum lru_status (*list_lru_walk_cb)(struct list_head *item,
  * @cb_arg: opaque type that will be passed to @isolate
  * @nr_to_walk: how many items to scan.
  *
- * This function will scan all elements in a particular list_lru, calling the
+ * This function will scan all elements in a particular @lru, calling the
  * @isolate callback for each of those items, along with the current list
  * spinlock and a caller-provided opaque. The @isolate callback can choose to
  * drop the lock internally, but *must* return with the lock held. The callback
- * will return an enum lru_status telling the list_lru infrastructure what to
+ * will return an enum lru_status telling the @lru infrastructure what to
  * do with the object being scanned.
  *
- * Please note that nr_to_walk does not mean how many objects will be freed,
+ * Please note that @nr_to_walk does not mean how many objects will be freed,
  * just how many objects will be scanned.
  *
- * Return value: the number of objects effectively removed from the LRU.
+ * Return: the number of objects effectively removed from the LRU.
  */
 unsigned long list_lru_walk_one(struct list_lru *lru,
 				int nid, struct mem_cgroup *memcg,
 				list_lru_walk_cb isolate, void *cb_arg,
 				unsigned long *nr_to_walk);
 /**
- * list_lru_walk_one_irq: walk a list_lru, isolating and disposing freeable items.
+ * list_lru_walk_one_irq: walk a @lru, isolating and disposing freeable items.
  * @lru: the lru pointer.
  * @nid: the node id to scan from.
  * @memcg: the cgroup to scan from.
@@ -176,7 +244,7 @@ unsigned long list_lru_walk_one(struct list_lru *lru,
  * @cb_arg: opaque type that will be passed to @isolate
  * @nr_to_walk: how many items to scan.
  *
- * Same as @list_lru_walk_one except that the spinlock is acquired with
+ * Same as list_lru_walk_one() except that the spinlock is acquired with
  * spin_lock_irq().
  */
 unsigned long list_lru_walk_one_irq(struct list_lru *lru,
diff --git a/include/linux/list_nulls.h b/include/linux/list_nulls.h
index fa6e8471bd22..248db9b77ee2 100644
--- a/include/linux/list_nulls.h
+++ b/include/linux/list_nulls.h
@@ -28,6 +28,7 @@ struct hlist_nulls_node {
 #define NULLS_MARKER(value) (1UL | (((long)value) << 1))
 #define INIT_HLIST_NULLS_HEAD(ptr, nulls) \
 	((ptr)->first = (struct hlist_nulls_node *) NULLS_MARKER(nulls))
+#define HLIST_NULLS_HEAD_INIT(nulls) {.first = (struct hlist_nulls_node *)NULLS_MARKER(nulls)}
 
 #define hlist_nulls_entry(ptr, type, member) container_of(ptr,type,member)
 
diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h
index 9b9b38e89563..772919e8096a 100644
--- a/include/linux/livepatch.h
+++ b/include/linux/livepatch.h
@@ -13,14 +13,15 @@
 #include <linux/ftrace.h>
 #include <linux/completion.h>
 #include <linux/list.h>
+#include <linux/livepatch_external.h>
 #include <linux/livepatch_sched.h>
 
 #if IS_ENABLED(CONFIG_LIVEPATCH)
 
 /* task patch states */
-#define KLP_UNDEFINED	-1
-#define KLP_UNPATCHED	 0
-#define KLP_PATCHED	 1
+#define KLP_TRANSITION_IDLE		-1
+#define KLP_TRANSITION_UNPATCHED	 0
+#define KLP_TRANSITION_PATCHED		 1
 
 /**
  * struct klp_func - function structure for live patching
@@ -77,30 +78,6 @@ struct klp_func {
 	bool transition;
 };
 
-struct klp_object;
-
-/**
- * struct klp_callbacks - pre/post live-(un)patch callback structure
- * @pre_patch:		executed before code patching
- * @post_patch:		executed after code patching
- * @pre_unpatch:	executed before code unpatching
- * @post_unpatch:	executed after code unpatching
- * @post_unpatch_enabled:	flag indicating if post-unpatch callback
- * 				should run
- *
- * All callbacks are optional.  Only the pre-patch callback, if provided,
- * will be unconditionally executed.  If the parent klp_object fails to
- * patch for any reason, including a non-zero error status returned from
- * the pre-patch callback, no further callbacks will be executed.
- */
-struct klp_callbacks {
-	int (*pre_patch)(struct klp_object *obj);
-	void (*post_patch)(struct klp_object *obj);
-	void (*pre_unpatch)(struct klp_object *obj);
-	void (*post_unpatch)(struct klp_object *obj);
-	bool post_unpatch_enabled;
-};
-
 /**
  * struct klp_object - kernel object structure for live patching
  * @name:	module name (or NULL for vmlinux)
diff --git a/include/linux/livepatch_external.h b/include/linux/livepatch_external.h
new file mode 100644
index 000000000000..138af19b0f5c
--- /dev/null
+++ b/include/linux/livepatch_external.h
@@ -0,0 +1,76 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * External livepatch interfaces for patch creation tooling
+ */
+
+#ifndef _LINUX_LIVEPATCH_EXTERNAL_H_
+#define _LINUX_LIVEPATCH_EXTERNAL_H_
+
+#include <linux/types.h>
+
+#define KLP_RELOC_SEC_PREFIX		".klp.rela."
+#define KLP_SYM_PREFIX			".klp.sym."
+
+#define __KLP_PRE_PATCH_PREFIX		__klp_pre_patch_callback_
+#define __KLP_POST_PATCH_PREFIX		__klp_post_patch_callback_
+#define __KLP_PRE_UNPATCH_PREFIX	__klp_pre_unpatch_callback_
+#define __KLP_POST_UNPATCH_PREFIX	__klp_post_unpatch_callback_
+
+#define KLP_PRE_PATCH_PREFIX		__stringify(__KLP_PRE_PATCH_PREFIX)
+#define KLP_POST_PATCH_PREFIX		__stringify(__KLP_POST_PATCH_PREFIX)
+#define KLP_PRE_UNPATCH_PREFIX		__stringify(__KLP_PRE_UNPATCH_PREFIX)
+#define KLP_POST_UNPATCH_PREFIX		__stringify(__KLP_POST_UNPATCH_PREFIX)
+
+struct klp_object;
+
+typedef int (*klp_pre_patch_t)(struct klp_object *obj);
+typedef void (*klp_post_patch_t)(struct klp_object *obj);
+typedef void (*klp_pre_unpatch_t)(struct klp_object *obj);
+typedef void (*klp_post_unpatch_t)(struct klp_object *obj);
+
+/**
+ * struct klp_callbacks - pre/post live-(un)patch callback structure
+ * @pre_patch:		executed before code patching
+ * @post_patch:		executed after code patching
+ * @pre_unpatch:	executed before code unpatching
+ * @post_unpatch:	executed after code unpatching
+ * @post_unpatch_enabled:	flag indicating if post-unpatch callback
+ *				should run
+ *
+ * All callbacks are optional.  Only the pre-patch callback, if provided,
+ * will be unconditionally executed.  If the parent klp_object fails to
+ * patch for any reason, including a non-zero error status returned from
+ * the pre-patch callback, no further callbacks will be executed.
+ */
+struct klp_callbacks {
+	klp_pre_patch_t		pre_patch;
+	klp_post_patch_t	post_patch;
+	klp_pre_unpatch_t	pre_unpatch;
+	klp_post_unpatch_t	post_unpatch;
+	bool post_unpatch_enabled;
+};
+
+/*
+ * 'struct klp_{func,object}_ext' are compact "external" representations of
+ * 'struct klp_{func,object}'.   They are used by objtool for livepatch
+ * generation.  The structs are then read by the livepatch module and converted
+ * to the real structs before calling klp_enable_patch().
+ *
+ * TODO make these the official API for klp_enable_patch().  That should
+ * simplify livepatch's interface as well as its data structure lifetime
+ * management.
+ */
+struct klp_func_ext {
+	const char *old_name;
+	void *new_func;
+	unsigned long sympos;
+};
+
+struct klp_object_ext {
+	const char *name;
+	struct klp_func_ext *funcs;
+	struct klp_callbacks callbacks;
+	unsigned int nr_funcs;
+};
+
+#endif /* _LINUX_LIVEPATCH_EXTERNAL_H_ */
diff --git a/include/linux/livepatch_helpers.h b/include/linux/livepatch_helpers.h
new file mode 100644
index 000000000000..99d68d0773fa
--- /dev/null
+++ b/include/linux/livepatch_helpers.h
@@ -0,0 +1,77 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_LIVEPATCH_HELPERS_H
+#define _LINUX_LIVEPATCH_HELPERS_H
+
+/*
+ * Interfaces for use by livepatch patches
+ */
+
+#include <linux/syscalls.h>
+#include <linux/livepatch.h>
+
+#ifdef MODULE
+#define KLP_OBJNAME __KBUILD_MODNAME
+#else
+#define KLP_OBJNAME vmlinux
+#endif
+
+/* Livepatch callback registration */
+
+#define KLP_CALLBACK_PTRS ".discard.klp_callback_ptrs"
+
+#define KLP_PRE_PATCH_CALLBACK(func)						\
+	klp_pre_patch_t __used __section(KLP_CALLBACK_PTRS)			\
+		__PASTE(__KLP_PRE_PATCH_PREFIX, KLP_OBJNAME) = func
+
+#define KLP_POST_PATCH_CALLBACK(func)						\
+	klp_post_patch_t __used __section(KLP_CALLBACK_PTRS)			\
+		__PASTE(__KLP_POST_PATCH_PREFIX, KLP_OBJNAME) = func
+
+#define KLP_PRE_UNPATCH_CALLBACK(func)						\
+	klp_pre_unpatch_t __used __section(KLP_CALLBACK_PTRS)			\
+		__PASTE(__KLP_PRE_UNPATCH_PREFIX, KLP_OBJNAME) = func
+
+#define KLP_POST_UNPATCH_CALLBACK(func)						\
+	klp_post_unpatch_t __used __section(KLP_CALLBACK_PTRS)			\
+		__PASTE(__KLP_POST_UNPATCH_PREFIX, KLP_OBJNAME) = func
+
+/*
+ * Replace static_call() usage with this macro when create-diff-object
+ * recommends it due to the original static call key living in a module.
+ *
+ * This converts the static call to a regular indirect call.
+ */
+#define KLP_STATIC_CALL(name) \
+	((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func))
+
+/* Syscall patching */
+
+#define KLP_SYSCALL_DEFINE1(name, ...) KLP_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__)
+#define KLP_SYSCALL_DEFINE2(name, ...) KLP_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__)
+#define KLP_SYSCALL_DEFINE3(name, ...) KLP_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__)
+#define KLP_SYSCALL_DEFINE4(name, ...) KLP_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__)
+#define KLP_SYSCALL_DEFINE5(name, ...) KLP_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__)
+#define KLP_SYSCALL_DEFINE6(name, ...) KLP_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__)
+
+#define KLP_SYSCALL_DEFINEx(x, sname, ...)				\
+	__KLP_SYSCALL_DEFINEx(x, sname, __VA_ARGS__)
+
+#ifdef CONFIG_X86_64
+// TODO move this to arch/x86/include/asm/syscall_wrapper.h and share code
+#define __KLP_SYSCALL_DEFINEx(x, name, ...)			\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__));	\
+	static inline long __klp_do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\
+	__X64_SYS_STUBx(x, name, __VA_ARGS__)				\
+	__IA32_SYS_STUBx(x, name, __VA_ARGS__)				\
+	static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__))	\
+	{								\
+		long ret = __klp_do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\
+		__MAP(x,__SC_TEST,__VA_ARGS__);				\
+		__PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__));	\
+		return ret;						\
+	}								\
+	static inline long __klp_do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__))
+
+#endif
+
+#endif /* _LINUX_LIVEPATCH_HELPERS_H */
diff --git a/include/linux/livepatch_sched.h b/include/linux/livepatch_sched.h
index 013794fb5da0..065c185f2763 100644
--- a/include/linux/livepatch_sched.h
+++ b/include/linux/livepatch_sched.h
@@ -3,27 +3,23 @@
 #define _LINUX_LIVEPATCH_SCHED_H_
 
 #include <linux/jump_label.h>
-#include <linux/static_call_types.h>
+#include <linux/sched.h>
 
 #ifdef CONFIG_LIVEPATCH
 
 void __klp_sched_try_switch(void);
 
-#if !defined(CONFIG_PREEMPT_DYNAMIC) || !defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-
 DECLARE_STATIC_KEY_FALSE(klp_sched_try_switch_key);
 
-static __always_inline void klp_sched_try_switch(void)
+static __always_inline void klp_sched_try_switch(struct task_struct *curr)
 {
-	if (static_branch_unlikely(&klp_sched_try_switch_key))
+	if (static_branch_unlikely(&klp_sched_try_switch_key) &&
+	    READ_ONCE(curr->__state) & TASK_FREEZABLE)
 		__klp_sched_try_switch();
 }
 
-#endif /* !CONFIG_PREEMPT_DYNAMIC || !CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-
 #else /* !CONFIG_LIVEPATCH */
-static inline void klp_sched_try_switch(void) {}
-static inline void __klp_sched_try_switch(void) {}
+static inline void klp_sched_try_switch(struct task_struct *curr) {}
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _LINUX_LIVEPATCH_SCHED_H_ */
diff --git a/include/linux/liveupdate.h b/include/linux/liveupdate.h
new file mode 100644
index 000000000000..a7f6ee5b6771
--- /dev/null
+++ b/include/linux/liveupdate.h
@@ -0,0 +1,138 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (c) 2025, Google LLC.
+ * Pasha Tatashin <pasha.tatashin@soleen.com>
+ */
+#ifndef _LINUX_LIVEUPDATE_H
+#define _LINUX_LIVEUPDATE_H
+
+#include <linux/bug.h>
+#include <linux/compiler.h>
+#include <linux/kho/abi/luo.h>
+#include <linux/list.h>
+#include <linux/types.h>
+#include <uapi/linux/liveupdate.h>
+
+struct liveupdate_file_handler;
+struct file;
+
+/**
+ * struct liveupdate_file_op_args - Arguments for file operation callbacks.
+ * @handler:          The file handler being called.
+ * @retrieved:        The retrieve status for the 'can_finish / finish'
+ *                    operation.
+ * @file:             The file object. For retrieve: [OUT] The callback sets
+ *                    this to the new file. For other ops: [IN] The caller sets
+ *                    this to the file being operated on.
+ * @serialized_data:  The opaque u64 handle, preserve/prepare/freeze may update
+ *                    this field.
+ * @private_data:     Private data for the file used to hold runtime state that
+ *                    is not preserved. Set by the handler's .preserve()
+ *                    callback, and must be freed in the handler's
+ *                    .unpreserve() callback.
+ *
+ * This structure bundles all parameters for the file operation callbacks.
+ * The 'data' and 'file' fields are used for both input and output.
+ */
+struct liveupdate_file_op_args {
+	struct liveupdate_file_handler *handler;
+	bool retrieved;
+	struct file *file;
+	u64 serialized_data;
+	void *private_data;
+};
+
+/**
+ * struct liveupdate_file_ops - Callbacks for live-updatable files.
+ * @can_preserve: Required. Lightweight check to see if this handler is
+ *                compatible with the given file.
+ * @preserve:     Required. Performs state-saving for the file.
+ * @unpreserve:   Required. Cleans up any resources allocated by @preserve.
+ * @freeze:       Optional. Final actions just before kernel transition.
+ * @unfreeze:     Optional. Undo freeze operations.
+ * @retrieve:     Required. Restores the file in the new kernel.
+ * @can_finish:   Optional. Check if this FD can finish, i.e. all restoration
+ *                pre-requirements for this FD are satisfied. Called prior to
+ *                finish, in order to do successful finish calls for all
+ *                resources in the session.
+ * @finish:       Required. Final cleanup in the new kernel.
+ * @owner:        Module reference
+ *
+ * All operations (except can_preserve) receive a pointer to a
+ * 'struct liveupdate_file_op_args' containing the necessary context.
+ */
+struct liveupdate_file_ops {
+	bool (*can_preserve)(struct liveupdate_file_handler *handler,
+			     struct file *file);
+	int (*preserve)(struct liveupdate_file_op_args *args);
+	void (*unpreserve)(struct liveupdate_file_op_args *args);
+	int (*freeze)(struct liveupdate_file_op_args *args);
+	void (*unfreeze)(struct liveupdate_file_op_args *args);
+	int (*retrieve)(struct liveupdate_file_op_args *args);
+	bool (*can_finish)(struct liveupdate_file_op_args *args);
+	void (*finish)(struct liveupdate_file_op_args *args);
+	struct module *owner;
+};
+
+/**
+ * struct liveupdate_file_handler - Represents a handler for a live-updatable file type.
+ * @ops:                Callback functions
+ * @compatible:         The compatibility string (e.g., "memfd-v1", "vfiofd-v1")
+ *                      that uniquely identifies the file type this handler
+ *                      supports. This is matched against the compatible string
+ *                      associated with individual &struct file instances.
+ *
+ * Modules that want to support live update for specific file types should
+ * register an instance of this structure. LUO uses this registration to
+ * determine if a given file can be preserved and to find the appropriate
+ * operations to manage its state across the update.
+ */
+struct liveupdate_file_handler {
+	const struct liveupdate_file_ops *ops;
+	const char compatible[LIVEUPDATE_HNDL_COMPAT_LENGTH];
+
+	/* private: */
+
+	/*
+	 * Used for linking this handler instance into a global list of
+	 * registered file handlers.
+	 */
+	struct list_head __private list;
+};
+
+#ifdef CONFIG_LIVEUPDATE
+
+/* Return true if live update orchestrator is enabled */
+bool liveupdate_enabled(void);
+
+/* Called during kexec to tell LUO that entered into reboot */
+int liveupdate_reboot(void);
+
+int liveupdate_register_file_handler(struct liveupdate_file_handler *fh);
+int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh);
+
+#else /* CONFIG_LIVEUPDATE */
+
+static inline bool liveupdate_enabled(void)
+{
+	return false;
+}
+
+static inline int liveupdate_reboot(void)
+{
+	return 0;
+}
+
+static inline int liveupdate_register_file_handler(struct liveupdate_file_handler *fh)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int liveupdate_unregister_file_handler(struct liveupdate_file_handler *fh)
+{
+	return -EOPNOTSUPP;
+}
+
+#endif /* CONFIG_LIVEUPDATE */
+#endif /* _LINUX_LIVEUPDATE_H */
diff --git a/include/linux/llist.h b/include/linux/llist.h
index 85bda2d02d65..607b2360c938 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -74,6 +74,33 @@ static inline void init_llist_head(struct llist_head *list)
 }
 
 /**
+ * init_llist_node - initialize lock-less list node
+ * @node:	the node to be initialised
+ *
+ * In cases where there is a need to test if a node is on
+ * a list or not, this initialises the node to clearly
+ * not be on any list.
+ */
+static inline void init_llist_node(struct llist_node *node)
+{
+	WRITE_ONCE(node->next, node);
+}
+
+/**
+ * llist_on_list - test if a lock-list list node is on a list
+ * @node:	the node to test
+ *
+ * When a node is on a list the ->next pointer will be NULL or
+ * some other node.  It can never point to itself.  We use that
+ * in init_llist_node() to record that a node is not on any list,
+ * and here to test whether it is on any list.
+ */
+static inline bool llist_on_list(const struct llist_node *node)
+{
+	return READ_ONCE(node->next) != node;
+}
+
+/**
  * llist_entry - get the struct of this entry
  * @ptr:	the &struct llist_node pointer.
  * @type:	the type of the struct this is embedded in.
@@ -193,12 +220,29 @@ static inline bool llist_empty(const struct llist_head *head)
 
 static inline struct llist_node *llist_next(struct llist_node *node)
 {
-	return node->next;
+	return READ_ONCE(node->next);
 }
 
-extern bool llist_add_batch(struct llist_node *new_first,
-			    struct llist_node *new_last,
-			    struct llist_head *head);
+/**
+ * llist_add_batch - add several linked entries in batch
+ * @new_first:	first entry in batch to be added
+ * @new_last:	last entry in batch to be added
+ * @head:	the head for your lock-less list
+ *
+ * Return whether list is empty before adding.
+ */
+static inline bool llist_add_batch(struct llist_node *new_first,
+				   struct llist_node *new_last,
+				   struct llist_head *head)
+{
+	struct llist_node *first = READ_ONCE(head->first);
+
+	do {
+		new_last->next = first;
+	} while (!try_cmpxchg(&head->first, &first, new_first));
+
+	return !first;
+}
 
 static inline bool __llist_add_batch(struct llist_node *new_first,
 				     struct llist_node *new_last,
@@ -249,6 +293,25 @@ static inline struct llist_node *__llist_del_all(struct llist_head *head)
 
 extern struct llist_node *llist_del_first(struct llist_head *head);
 
+/**
+ * llist_del_first_init - delete first entry from lock-list and mark is as being off-list
+ * @head:	the head of lock-less list to delete from.
+ *
+ * This behave the same as llist_del_first() except that llist_init_node() is called
+ * on the returned node so that llist_on_list() will report false for the node.
+ */
+static inline struct llist_node *llist_del_first_init(struct llist_head *head)
+{
+	struct llist_node *n = llist_del_first(head);
+
+	if (n)
+		init_llist_node(n);
+	return n;
+}
+
+extern bool llist_del_first_this(struct llist_head *head,
+				 struct llist_node *this);
+
 struct llist_node *llist_reverse_order(struct llist_node *head);
 
 #endif /* LLIST_H */
diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index e55010fa7329..b0e6ab329b00 100644
--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -6,6 +6,7 @@
 
 /**
  * local_lock_init - Runtime initialize a lock instance
+ * @lock:	The lock variable
  */
 #define local_lock_init(lock)		__local_lock_init(lock)
 
@@ -13,13 +14,13 @@
  * local_lock - Acquire a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_lock(lock)		__local_lock(lock)
+#define local_lock(lock)		__local_lock(this_cpu_ptr(lock))
 
 /**
  * local_lock_irq - Acquire a per CPU local lock and disable interrupts
  * @lock:	The lock variable
  */
-#define local_lock_irq(lock)		__local_lock_irq(lock)
+#define local_lock_irq(lock)		__local_lock_irq(this_cpu_ptr(lock))
 
 /**
  * local_lock_irqsave - Acquire a per CPU local lock, save and disable
@@ -28,19 +29,19 @@
  * @flags:	Storage for interrupt flags
  */
 #define local_lock_irqsave(lock, flags)				\
-	__local_lock_irqsave(lock, flags)
+	__local_lock_irqsave(this_cpu_ptr(lock), flags)
 
 /**
  * local_unlock - Release a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_unlock(lock)		__local_unlock(lock)
+#define local_unlock(lock)		__local_unlock(this_cpu_ptr(lock))
 
 /**
  * local_unlock_irq - Release a per CPU local lock and enable interrupts
  * @lock:	The lock variable
  */
-#define local_unlock_irq(lock)		__local_unlock_irq(lock)
+#define local_unlock_irq(lock)		__local_unlock_irq(this_cpu_ptr(lock))
 
 /**
  * local_unlock_irqrestore - Release a per CPU local lock and restore
@@ -49,6 +50,58 @@
  * @flags:      Interrupt flags to restore
  */
 #define local_unlock_irqrestore(lock, flags)			\
-	__local_unlock_irqrestore(lock, flags)
+	__local_unlock_irqrestore(this_cpu_ptr(lock), flags)
+
+/**
+ * local_trylock_init - Runtime initialize a lock instance
+ * @lock:	The lock variable
+ */
+#define local_trylock_init(lock)	__local_trylock_init(lock)
+
+/**
+ * local_trylock - Try to acquire a per CPU local lock
+ * @lock:	The lock variable
+ *
+ * The function can be used in any context such as NMI or HARDIRQ. Due to
+ * locking constrains it will _always_ fail to acquire the lock in NMI or
+ * HARDIRQ context on PREEMPT_RT.
+ */
+#define local_trylock(lock)		__local_trylock(this_cpu_ptr(lock))
+
+#define local_lock_is_locked(lock)	__local_lock_is_locked(lock)
+
+/**
+ * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
+ *			   interrupts if acquired
+ * @lock:	The lock variable
+ * @flags:	Storage for interrupt flags
+ *
+ * The function can be used in any context such as NMI or HARDIRQ. Due to
+ * locking constrains it will _always_ fail to acquire the lock in NMI or
+ * HARDIRQ context on PREEMPT_RT.
+ */
+#define local_trylock_irqsave(lock, flags)			\
+	__local_trylock_irqsave(this_cpu_ptr(lock), flags)
+
+DEFINE_GUARD(local_lock, local_lock_t __percpu*,
+	     local_lock(_T),
+	     local_unlock(_T))
+DEFINE_GUARD(local_lock_irq, local_lock_t __percpu*,
+	     local_lock_irq(_T),
+	     local_unlock_irq(_T))
+DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu,
+		    local_lock_irqsave(_T->lock, _T->flags),
+		    local_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+#define local_lock_nested_bh(_lock)				\
+	__local_lock_nested_bh(this_cpu_ptr(_lock))
+
+#define local_unlock_nested_bh(_lock)				\
+	__local_unlock_nested_bh(this_cpu_ptr(_lock))
+
+DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*,
+	     local_lock_nested_bh(_T),
+	     local_unlock_nested_bh(_T))
 
 #endif
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 975e33b793a7..8f82b4eb542f 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -15,6 +15,15 @@ typedef struct {
 #endif
 } local_lock_t;
 
+/* local_trylock() and local_trylock_irqsave() only work with local_trylock_t */
+typedef struct {
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+	struct task_struct	*owner;
+#endif
+	u8		acquired;
+} local_trylock_t;
+
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define LOCAL_LOCK_DEBUG_INIT(lockname)		\
 	.dep_map = {					\
@@ -24,6 +33,9 @@ typedef struct {
 	},						\
 	.owner = NULL,
 
+# define LOCAL_TRYLOCK_DEBUG_INIT(lockname)		\
+	LOCAL_LOCK_DEBUG_INIT(lockname)
+
 static inline void local_lock_acquire(local_lock_t *l)
 {
 	lock_map_acquire(&l->dep_map);
@@ -31,6 +43,13 @@ static inline void local_lock_acquire(local_lock_t *l)
 	l->owner = current;
 }
 
+static inline void local_trylock_acquire(local_lock_t *l)
+{
+	lock_map_acquire_try(&l->dep_map);
+	DEBUG_LOCKS_WARN_ON(l->owner);
+	l->owner = current;
+}
+
 static inline void local_lock_release(local_lock_t *l)
 {
 	DEBUG_LOCKS_WARN_ON(l->owner != current);
@@ -44,12 +63,15 @@ static inline void local_lock_debug_init(local_lock_t *l)
 }
 #else /* CONFIG_DEBUG_LOCK_ALLOC */
 # define LOCAL_LOCK_DEBUG_INIT(lockname)
+# define LOCAL_TRYLOCK_DEBUG_INIT(lockname)
 static inline void local_lock_acquire(local_lock_t *l) { }
+static inline void local_trylock_acquire(local_lock_t *l) { }
 static inline void local_lock_release(local_lock_t *l) { }
 static inline void local_lock_debug_init(local_lock_t *l) { }
 #endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 #define INIT_LOCAL_LOCK(lockname)	{ LOCAL_LOCK_DEBUG_INIT(lockname) }
+#define INIT_LOCAL_TRYLOCK(lockname)	{ LOCAL_TRYLOCK_DEBUG_INIT(lockname) }
 
 #define __local_lock_init(lock)					\
 do {								\
@@ -62,42 +84,133 @@ do {								\
 	local_lock_debug_init(lock);				\
 } while (0)
 
+#define __local_trylock_init(lock) __local_lock_init((local_lock_t *)lock)
+
+#define __spinlock_nested_bh_init(lock)				\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key,  \
+			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_NORMAL);			\
+	local_lock_debug_init(lock);				\
+} while (0)
+
+#define __local_lock_acquire(lock)					\
+	do {								\
+		local_trylock_t *__tl;					\
+		local_lock_t *__l;					\
+									\
+		__l = (local_lock_t *)(lock);				\
+		__tl = (local_trylock_t *)__l;				\
+		_Generic((lock),					\
+			local_trylock_t *: ({				\
+				lockdep_assert(__tl->acquired == 0);	\
+				WRITE_ONCE(__tl->acquired, 1);		\
+			}),						\
+			local_lock_t *: (void)0);			\
+		local_lock_acquire(__l);				\
+	} while (0)
+
 #define __local_lock(lock)					\
 	do {							\
 		preempt_disable();				\
-		local_lock_acquire(this_cpu_ptr(lock));		\
+		__local_lock_acquire(lock);			\
 	} while (0)
 
 #define __local_lock_irq(lock)					\
 	do {							\
 		local_irq_disable();				\
-		local_lock_acquire(this_cpu_ptr(lock));		\
+		__local_lock_acquire(lock);			\
 	} while (0)
 
 #define __local_lock_irqsave(lock, flags)			\
 	do {							\
 		local_irq_save(flags);				\
-		local_lock_acquire(this_cpu_ptr(lock));		\
+		__local_lock_acquire(lock);			\
+	} while (0)
+
+#define __local_trylock(lock)					\
+	({							\
+		local_trylock_t *__tl;				\
+								\
+		preempt_disable();				\
+		__tl = (lock);					\
+		if (READ_ONCE(__tl->acquired)) {		\
+			preempt_enable();			\
+			__tl = NULL;				\
+		} else {					\
+			WRITE_ONCE(__tl->acquired, 1);		\
+			local_trylock_acquire(			\
+				(local_lock_t *)__tl);		\
+		}						\
+		!!__tl;						\
+	})
+
+#define __local_trylock_irqsave(lock, flags)			\
+	({							\
+		local_trylock_t *__tl;				\
+								\
+		local_irq_save(flags);				\
+		__tl = (lock);					\
+		if (READ_ONCE(__tl->acquired)) {		\
+			local_irq_restore(flags);		\
+			__tl = NULL;				\
+		} else {					\
+			WRITE_ONCE(__tl->acquired, 1);		\
+			local_trylock_acquire(			\
+				(local_lock_t *)__tl);		\
+		}						\
+		!!__tl;						\
+	})
+
+/* preemption or migration must be disabled before calling __local_lock_is_locked */
+#define __local_lock_is_locked(lock) READ_ONCE(this_cpu_ptr(lock)->acquired)
+
+#define __local_lock_release(lock)					\
+	do {								\
+		local_trylock_t *__tl;					\
+		local_lock_t *__l;					\
+									\
+		__l = (local_lock_t *)(lock);				\
+		__tl = (local_trylock_t *)__l;				\
+		local_lock_release(__l);				\
+		_Generic((lock),					\
+			local_trylock_t *: ({				\
+				lockdep_assert(__tl->acquired == 1);	\
+				WRITE_ONCE(__tl->acquired, 0);		\
+			}),						\
+			local_lock_t *: (void)0);			\
 	} while (0)
 
 #define __local_unlock(lock)					\
 	do {							\
-		local_lock_release(this_cpu_ptr(lock));		\
+		__local_lock_release(lock);			\
 		preempt_enable();				\
 	} while (0)
 
 #define __local_unlock_irq(lock)				\
 	do {							\
-		local_lock_release(this_cpu_ptr(lock));		\
+		__local_lock_release(lock);			\
 		local_irq_enable();				\
 	} while (0)
 
 #define __local_unlock_irqrestore(lock, flags)			\
 	do {							\
-		local_lock_release(this_cpu_ptr(lock));		\
+		__local_lock_release(lock);			\
 		local_irq_restore(flags);			\
 	} while (0)
 
+#define __local_lock_nested_bh(lock)				\
+	do {							\
+		lockdep_assert_in_softirq();			\
+		local_lock_acquire((lock));			\
+	} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+	local_lock_release((lock))
+
 #else /* !CONFIG_PREEMPT_RT */
 
 /*
@@ -105,18 +218,22 @@ do {								\
  * critical section while staying preemptible.
  */
 typedef spinlock_t local_lock_t;
+typedef spinlock_t local_trylock_t;
 
 #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
+#define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname))
 
-#define __local_lock_init(l)					\
+#define __local_lock_init(__l)					\
 	do {							\
-		local_spin_lock_init((l));			\
+		local_spin_lock_init((__l));			\
 	} while (0)
 
+#define __local_trylock_init(__l)			__local_lock_init(__l)
+
 #define __local_lock(__lock)					\
 	do {							\
 		migrate_disable();				\
-		spin_lock(this_cpu_ptr((__lock)));		\
+		spin_lock((__lock));				\
 	} while (0)
 
 #define __local_lock_irq(lock)			__local_lock(lock)
@@ -130,7 +247,7 @@ typedef spinlock_t local_lock_t;
 
 #define __local_unlock(__lock)					\
 	do {							\
-		spin_unlock(this_cpu_ptr((__lock)));		\
+		spin_unlock((__lock));				\
 		migrate_enable();				\
 	} while (0)
 
@@ -138,4 +255,41 @@ typedef spinlock_t local_lock_t;
 
 #define __local_unlock_irqrestore(lock, flags)	__local_unlock(lock)
 
+#define __local_lock_nested_bh(lock)				\
+do {								\
+	lockdep_assert_in_softirq_func();			\
+	spin_lock((lock));					\
+} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+do {								\
+	spin_unlock((lock));					\
+} while (0)
+
+#define __local_trylock(lock)					\
+	({							\
+		int __locked;					\
+								\
+		if (in_nmi() | in_hardirq()) {			\
+			__locked = 0;				\
+		} else {					\
+			migrate_disable();			\
+			__locked = spin_trylock((lock));	\
+			if (!__locked)				\
+				migrate_enable();		\
+		}						\
+		__locked;					\
+	})
+
+#define __local_trylock_irqsave(lock, flags)			\
+	({							\
+		typecheck(unsigned long, flags);		\
+		flags = 0;					\
+		__local_trylock(lock);				\
+	})
+
+/* migration must be disabled before calling __local_lock_is_locked */
+#define __local_lock_is_locked(__lock)					\
+	(rt_mutex_owner(&this_cpu_ptr(__lock)->lock) == current)
+
 #endif /* CONFIG_PREEMPT_RT */
diff --git a/include/linux/lockd/bind.h b/include/linux/lockd/bind.h
index 3bc9f7410e21..c53c81242e72 100644
--- a/include/linux/lockd/bind.h
+++ b/include/linux/lockd/bind.h
@@ -20,6 +20,7 @@
 /* Dummy declarations */
 struct svc_rqst;
 struct rpc_task;
+struct rpc_clnt;
 
 /*
  * This is the set of functions for lockd->nfsd communication
@@ -56,6 +57,7 @@ struct nlmclnt_initdata {
 
 extern struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init);
 extern void	nlmclnt_done(struct nlm_host *host);
+extern struct rpc_clnt *nlmclnt_rpc_clnt(struct nlm_host *host);
 
 /*
  * NLM client operations provide a means to modify RPC processing of NLM
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index f42594a9efe0..330e38776bb2 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -12,6 +12,7 @@
 
 /* XXX: a lot of this should really be under fs/lockd. */
 
+#include <linux/exportfs.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <net/ipv6.h>
@@ -200,10 +201,12 @@ extern const struct svc_procedure nlmsvc_procedures[24];
 extern const struct svc_procedure nlmsvc_procedures4[24];
 #endif
 extern int			nlmsvc_grace_period;
-extern unsigned long		nlmsvc_timeout;
+extern unsigned long		nlm_timeout;
 extern bool			nsm_use_hostnames;
 extern u32			nsm_local_state;
 
+extern struct timer_list	nlmsvc_retry;
+
 /*
  * Lockd client functions
  */
@@ -276,11 +279,11 @@ __be32		  nlmsvc_lock(struct svc_rqst *, struct nlm_file *,
 			      struct nlm_host *, struct nlm_lock *, int,
 			      struct nlm_cookie *, int);
 __be32		  nlmsvc_unlock(struct net *net, struct nlm_file *, struct nlm_lock *);
-__be32		  nlmsvc_testlock(struct svc_rqst *, struct nlm_file *,
-			struct nlm_host *, struct nlm_lock *,
-			struct nlm_lock *, struct nlm_cookie *);
+__be32		  nlmsvc_testlock(struct svc_rqst *rqstp, struct nlm_file *file,
+			struct nlm_host *host, struct nlm_lock *lock,
+			struct nlm_lock *conflock);
 __be32		  nlmsvc_cancel_blocked(struct net *net, struct nlm_file *, struct nlm_lock *);
-unsigned long	  nlmsvc_retry_blocked(void);
+void		  nlmsvc_retry_blocked(struct svc_rqst *rqstp);
 void		  nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *,
 					nlm_host_match_fn_t match);
 void		  nlmsvc_grant_reply(struct nlm_cookie *, __be32);
@@ -305,7 +308,7 @@ void		  nlmsvc_invalidate_all(void);
 int           nlmsvc_unlock_all_by_sb(struct super_block *sb);
 int           nlmsvc_unlock_all_by_ip(struct sockaddr *server_addr);
 
-static inline struct file *nlmsvc_file_file(struct nlm_file *file)
+static inline struct file *nlmsvc_file_file(const struct nlm_file *file)
 {
 	return file->f_file[O_RDONLY] ?
 	       file->f_file[O_RDONLY] : file->f_file[O_WRONLY];
@@ -316,6 +319,12 @@ static inline struct inode *nlmsvc_file_inode(struct nlm_file *file)
 	return file_inode(nlmsvc_file_file(file));
 }
 
+static inline bool
+nlmsvc_file_cannot_lock(const struct nlm_file *file)
+{
+	return exportfs_cannot_lock(nlmsvc_file_file(file)->f_path.dentry->d_sb->s_export_op);
+}
+
 static inline int __nlm_privileged_request4(const struct sockaddr *sap)
 {
 	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
@@ -373,12 +382,12 @@ static inline int nlm_privileged_requester(const struct svc_rqst *rqstp)
 static inline int nlm_compare_locks(const struct file_lock *fl1,
 				    const struct file_lock *fl2)
 {
-	return file_inode(fl1->fl_file) == file_inode(fl2->fl_file)
-	     && fl1->fl_pid   == fl2->fl_pid
-	     && fl1->fl_owner == fl2->fl_owner
+	return file_inode(fl1->c.flc_file) == file_inode(fl2->c.flc_file)
+	     && fl1->c.flc_pid   == fl2->c.flc_pid
+	     && fl1->c.flc_owner == fl2->c.flc_owner
 	     && fl1->fl_start == fl2->fl_start
 	     && fl1->fl_end   == fl2->fl_end
-	     &&(fl1->fl_type  == fl2->fl_type || fl2->fl_type == F_UNLCK);
+	     &&(fl1->c.flc_type  == fl2->c.flc_type || fl2->c.flc_type == F_UNLCK);
 }
 
 extern const struct lock_manager_operations nlmsvc_lock_operations;
diff --git a/include/linux/lockd/xdr.h b/include/linux/lockd/xdr.h
index b60fbcd8cdfa..17d53165d9f2 100644
--- a/include/linux/lockd/xdr.h
+++ b/include/linux/lockd/xdr.h
@@ -52,7 +52,7 @@ struct nlm_lock {
  *	FreeBSD uses 16, Apple Mac OS X 10.3 uses 20. Therefore we set it to
  *	32 bytes.
  */
- 
+
 struct nlm_cookie
 {
 	unsigned char data[NLM_MAXCOOKIELEN];
@@ -73,8 +73,6 @@ struct nlm_args {
 	u32			fsm_mode;
 };
 
-typedef struct nlm_args nlm_args;
-
 /*
  * Generic lockd result
  */
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 74bd269a80a2..dd634103b014 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -82,63 +82,6 @@ struct lock_chain {
 	u64				chain_key;
 };
 
-#define MAX_LOCKDEP_KEYS_BITS		13
-#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
-#define INITIAL_CHAIN_KEY		-1
-
-struct held_lock {
-	/*
-	 * One-way hash of the dependency chain up to this point. We
-	 * hash the hashes step by step as the dependency chain grows.
-	 *
-	 * We use it for dependency-caching and we skip detection
-	 * passes and dependency-updates if there is a cache-hit, so
-	 * it is absolutely critical for 100% coverage of the validator
-	 * to have a unique key value for every unique dependency path
-	 * that can occur in the system, to make a unique hash value
-	 * as likely as possible - hence the 64-bit width.
-	 *
-	 * The task struct holds the current hash value (initialized
-	 * with zero), here we store the previous hash value:
-	 */
-	u64				prev_chain_key;
-	unsigned long			acquire_ip;
-	struct lockdep_map		*instance;
-	struct lockdep_map		*nest_lock;
-#ifdef CONFIG_LOCK_STAT
-	u64 				waittime_stamp;
-	u64				holdtime_stamp;
-#endif
-	/*
-	 * class_idx is zero-indexed; it points to the element in
-	 * lock_classes this held lock instance belongs to. class_idx is in
-	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
-	 */
-	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
-	/*
-	 * The lock-stack is unified in that the lock chains of interrupt
-	 * contexts nest ontop of process context chains, but we 'separate'
-	 * the hashes by starting with 0 if we cross into an interrupt
-	 * context, and we also keep do not add cross-context lock
-	 * dependencies - the lock usage graph walking covers that area
-	 * anyway, and we'd just unnecessarily increase the number of
-	 * dependencies otherwise. [Note: hardirq and softirq contexts
-	 * are separated from each other too.]
-	 *
-	 * The following field is used to detect when we cross into an
-	 * interrupt context:
-	 */
-	unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
-	unsigned int trylock:1;						/* 16 bits */
-
-	unsigned int read:2;        /* see lock_acquire() comment */
-	unsigned int check:1;       /* see lock_acquire() comment */
-	unsigned int hardirqs_off:1;
-	unsigned int sync:1;
-	unsigned int references:11;					/* 32 bits */
-	unsigned int pin_count;
-};
-
 /*
  * Initialization, self-test and debugging-output methods:
  */
@@ -230,14 +173,32 @@ static inline void lockdep_init_map(struct lockdep_map *lock, const char *name,
 			      (lock)->dep_map.lock_type)
 
 #define lockdep_set_subclass(lock, sub)					\
-	lockdep_init_map_type(&(lock)->dep_map, #lock, (lock)->dep_map.key, sub,\
+	lockdep_init_map_type(&(lock)->dep_map, (lock)->dep_map.name, (lock)->dep_map.key, sub,\
 			      (lock)->dep_map.wait_type_inner,		\
 			      (lock)->dep_map.wait_type_outer,		\
 			      (lock)->dep_map.lock_type)
 
+/**
+ * lockdep_set_novalidate_class: disable checking of lock ordering on a given
+ * lock
+ * @lock: Lock to mark
+ *
+ * Lockdep will still record that this lock has been taken, and print held
+ * instances when dumping locks
+ */
 #define lockdep_set_novalidate_class(lock) \
 	lockdep_set_class_and_name(lock, &__lockdep_no_validate__, #lock)
 
+/**
+ * lockdep_set_notrack_class: disable lockdep tracking of a given lock entirely
+ * @lock: Lock to mark
+ *
+ * Bigger hammer than lockdep_set_novalidate_class: so far just for bcachefs,
+ * which takes more locks than lockdep is able to track (48).
+ */
+#define lockdep_set_notrack_class(lock) \
+	lockdep_set_class_and_name(lock, &__lockdep_no_track__, #lock)
+
 /*
  * Compare locking classes
  */
@@ -395,6 +356,7 @@ static inline void lockdep_set_selftest_task(struct task_struct *task)
 #define lockdep_set_subclass(lock, sub)		do { } while (0)
 
 #define lockdep_set_novalidate_class(lock) do { } while (0)
+#define lockdep_set_notrack_class(lock) do { } while (0)
 
 /*
  * We don't define lockdep_match_class() and lockdep_match_key() for !LOCKDEP
@@ -447,6 +409,14 @@ extern int lockdep_is_held(const void *);
 
 #endif /* !LOCKDEP */
 
+#ifdef CONFIG_PROVE_LOCKING
+void lockdep_set_lock_cmp_fn(struct lockdep_map *, lock_cmp_fn, lock_print_fn);
+
+#define lock_set_cmp_fn(lock, ...)	lockdep_set_lock_cmp_fn(&(lock)->dep_map, __VA_ARGS__)
+#else
+#define lock_set_cmp_fn(lock, ...)	do { } while (0)
+#endif
+
 enum xhlock_context_t {
 	XHLOCK_HARD,
 	XHLOCK_SOFT,
@@ -617,6 +587,12 @@ do {									\
 	WARN_ON_ONCE(__lockdep_enabled && !this_cpu_read(hardirq_context)); \
 } while (0)
 
+#define lockdep_assert_no_hardirq()					\
+do {									\
+	WARN_ON_ONCE(__lockdep_enabled && (this_cpu_read(hardirq_context) || \
+					   !this_cpu_read(hardirqs_enabled))); \
+} while (0)
+
 #define lockdep_assert_preemption_enabled()				\
 do {									\
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_PREEMPT_COUNT)	&&		\
@@ -640,9 +616,11 @@ do {									\
 #define lockdep_assert_in_softirq()					\
 do {									\
 	WARN_ON_ONCE(__lockdep_enabled			&&		\
-		     (!in_softirq() || in_irq() || in_nmi()));		\
+		     (!in_softirq() || in_hardirq() || in_nmi()));	\
 } while (0)
 
+extern void lockdep_assert_in_softirq_func(void);
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
@@ -651,10 +629,12 @@ do {									\
 # define lockdep_assert_irqs_enabled() do { } while (0)
 # define lockdep_assert_irqs_disabled() do { } while (0)
 # define lockdep_assert_in_irq() do { } while (0)
+# define lockdep_assert_no_hardirq() do { } while (0)
 
 # define lockdep_assert_preemption_enabled() do { } while (0)
 # define lockdep_assert_preemption_disabled() do { } while (0)
 # define lockdep_assert_in_softirq() do { } while (0)
+# define lockdep_assert_in_softirq_func() do { } while (0)
 #endif
 
 #ifdef CONFIG_PROVE_RAW_LOCK_NESTING
diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 59f4fb1626ea..eae115a26488 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -80,11 +80,17 @@ struct lock_class_key {
 };
 
 extern struct lock_class_key __lockdep_no_validate__;
+extern struct lock_class_key __lockdep_no_track__;
 
 struct lock_trace;
 
 #define LOCKSTAT_POINTS		4
 
+struct lockdep_map;
+typedef int (*lock_cmp_fn)(const struct lockdep_map *a,
+			   const struct lockdep_map *b);
+typedef void (*lock_print_fn)(const struct lockdep_map *map);
+
 /*
  * The lock-class itself. The order of the structure members matters.
  * reinit_class() zeroes the key member and all subsequent members.
@@ -110,6 +116,9 @@ struct lock_class {
 	struct list_head		locks_after, locks_before;
 
 	const struct lockdep_subclass_key *key;
+	lock_cmp_fn			cmp_fn;
+	lock_print_fn			print_fn;
+
 	unsigned int			subclass;
 	unsigned int			dep_gen_id;
 
@@ -119,12 +128,12 @@ struct lock_class {
 	unsigned long			usage_mask;
 	const struct lock_trace		*usage_traces[LOCK_TRACE_STATES];
 
+	const char			*name;
 	/*
 	 * Generation counter, when doing certain classes of graph walking,
 	 * to ensure that we check one node only once:
 	 */
 	int				name_version;
-	const char			*name;
 
 	u8				wait_type_inner;
 	u8				wait_type_outer;
@@ -166,7 +175,7 @@ struct lock_class_stats {
 	unsigned long			bounces[nr_bounce_types];
 };
 
-struct lock_class_stats lock_stats(struct lock_class *class);
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats);
 void clear_lock_stats(struct lock_class *class);
 #endif
 
@@ -190,6 +199,63 @@ struct lockdep_map {
 
 struct pin_cookie { unsigned int val; };
 
+#define MAX_LOCKDEP_KEYS_BITS		13
+#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
+#define INITIAL_CHAIN_KEY		-1
+
+struct held_lock {
+	/*
+	 * One-way hash of the dependency chain up to this point. We
+	 * hash the hashes step by step as the dependency chain grows.
+	 *
+	 * We use it for dependency-caching and we skip detection
+	 * passes and dependency-updates if there is a cache-hit, so
+	 * it is absolutely critical for 100% coverage of the validator
+	 * to have a unique key value for every unique dependency path
+	 * that can occur in the system, to make a unique hash value
+	 * as likely as possible - hence the 64-bit width.
+	 *
+	 * The task struct holds the current hash value (initialized
+	 * with zero), here we store the previous hash value:
+	 */
+	u64				prev_chain_key;
+	unsigned long			acquire_ip;
+	struct lockdep_map		*instance;
+	struct lockdep_map		*nest_lock;
+#ifdef CONFIG_LOCK_STAT
+	u64 				waittime_stamp;
+	u64				holdtime_stamp;
+#endif
+	/*
+	 * class_idx is zero-indexed; it points to the element in
+	 * lock_classes this held lock instance belongs to. class_idx is in
+	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
+	 */
+	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
+	/*
+	 * The lock-stack is unified in that the lock chains of interrupt
+	 * contexts nest ontop of process context chains, but we 'separate'
+	 * the hashes by starting with 0 if we cross into an interrupt
+	 * context, and we also keep do not add cross-context lock
+	 * dependencies - the lock usage graph walking covers that area
+	 * anyway, and we'd just unnecessarily increase the number of
+	 * dependencies otherwise. [Note: hardirq and softirq contexts
+	 * are separated from each other too.]
+	 *
+	 * The following field is used to detect when we cross into an
+	 * interrupt context:
+	 */
+	unsigned int irq_context:2; /* bit 0 - soft, bit 1 - hard */
+	unsigned int trylock:1;						/* 16 bits */
+
+	unsigned int read:2;        /* see lock_acquire() comment */
+	unsigned int check:1;       /* see lock_acquire() comment */
+	unsigned int hardirqs_off:1;
+	unsigned int sync:1;
+	unsigned int references:11;					/* 32 bits */
+	unsigned int pin_count;
+};
+
 #else /* !CONFIG_LOCKDEP */
 
 /*
diff --git a/include/linux/lockref.h b/include/linux/lockref.h
index c3a1f78bc884..815d871fadfc 100644
--- a/include/linux/lockref.h
+++ b/include/linux/lockref.h
@@ -34,14 +34,27 @@ struct lockref {
 	};
 };
 
-extern void lockref_get(struct lockref *);
-extern int lockref_put_return(struct lockref *);
-extern int lockref_get_not_zero(struct lockref *);
-extern int lockref_put_not_zero(struct lockref *);
-extern int lockref_put_or_lock(struct lockref *);
-
-extern void lockref_mark_dead(struct lockref *);
-extern int lockref_get_not_dead(struct lockref *);
+/**
+ * lockref_init - Initialize a lockref
+ * @lockref: pointer to lockref structure
+ *
+ * Initializes @lockref->count to 1.
+ */
+static inline void lockref_init(struct lockref *lockref)
+{
+	spin_lock_init(&lockref->lock);
+	lockref->count = 1;
+}
+
+void lockref_get(struct lockref *lockref);
+int lockref_put_return(struct lockref *lockref);
+bool lockref_get_not_zero(struct lockref *lockref);
+bool lockref_put_or_lock(struct lockref *lockref);
+#define lockref_put_or_lock(_lockref) \
+	(!__cond_lock((_lockref)->lock, !lockref_put_or_lock(_lockref)))
+
+void lockref_mark_dead(struct lockref *lockref);
+bool lockref_get_not_dead(struct lockref *lockref);
 
 /* Must be called under spinlock for reliable results */
 static inline bool __lockref_is_dead(const struct lockref *l)
diff --git a/include/linux/log2.h b/include/linux/log2.h
index 9f30d087a128..2eac3fc9303d 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -41,7 +41,7 @@ int __ilog2_u64(u64 n)
  * *not* considered a power of two.
  * Return: true if @n is a power of 2, otherwise false.
  */
-static inline __attribute__((const))
+static __always_inline __attribute__((const))
 bool is_power_of_2(unsigned long n)
 {
 	return (n != 0 && ((n & (n - 1)) == 0));
@@ -255,4 +255,18 @@ int __bits_per(unsigned long n)
 	) :					\
 	__bits_per(n)				\
 )
+
+/**
+ * max_pow_of_two_factor - return highest power-of-2 factor
+ * @n: parameter
+ *
+ * find highest power-of-2 which is evenly divisible into n.
+ * 0 is returned for n == 0 or 1.
+ */
+static inline __attribute__((const))
+unsigned int max_pow_of_two_factor(unsigned int n)
+{
+	return n & -n;
+}
+
 #endif /* _LINUX_LOG2_H */
diff --git a/include/linux/logic_pio.h b/include/linux/logic_pio.h
index 54945aa824b4..8f1a9408302f 100644
--- a/include/linux/logic_pio.h
+++ b/include/linux/logic_pio.h
@@ -17,7 +17,7 @@ enum {
 
 struct logic_pio_hwaddr {
 	struct list_head list;
-	struct fwnode_handle *fwnode;
+	const struct fwnode_handle *fwnode;
 	resource_size_t hw_start;
 	resource_size_t io_start;
 	resource_size_t size; /* range size populated */
@@ -39,9 +39,6 @@ struct logic_pio_host_ops {
 
 #ifdef CONFIG_INDIRECT_PIO
 u8 logic_inb(unsigned long addr);
-void logic_outb(u8 value, unsigned long addr);
-void logic_outw(u16 value, unsigned long addr);
-void logic_outl(u32 value, unsigned long addr);
 u16 logic_inw(unsigned long addr);
 u32 logic_inl(unsigned long addr);
 void logic_outb(u8 value, unsigned long addr);
@@ -113,8 +110,8 @@ void logic_outsl(unsigned long addr, const void *buffer, unsigned int count);
 #endif /* CONFIG_INDIRECT_PIO */
 #define MMIO_UPPER_LIMIT (IO_SPACE_LIMIT - PIO_INDIRECT_SIZE)
 
-struct logic_pio_hwaddr *find_io_range_by_fwnode(struct fwnode_handle *fwnode);
-unsigned long logic_pio_trans_hwaddr(struct fwnode_handle *fwnode,
+struct logic_pio_hwaddr *find_io_range_by_fwnode(const struct fwnode_handle *fwnode);
+unsigned long logic_pio_trans_hwaddr(const struct fwnode_handle *fwnode,
 			resource_size_t hw_addr, resource_size_t size);
 int logic_pio_register_range(struct logic_pio_hwaddr *newrange);
 void logic_pio_unregister_range(struct logic_pio_hwaddr *range);
diff --git a/include/linux/lru_cache.h b/include/linux/lru_cache.h
index c9afcdd9324c..ff82ef85a084 100644
--- a/include/linux/lru_cache.h
+++ b/include/linux/lru_cache.h
@@ -119,7 +119,7 @@ write intent log information, three of which are mentioned here.
 */
 
 /* this defines an element in a tracked set
- * .colision is for hash table lookup.
+ * .collision is for hash table lookup.
  * When we process a new IO request, we know its sector, thus can deduce the
  * region number (label) easily.  To do the label -> object lookup without a
  * full list walk, we use a simple hash table.
@@ -145,7 +145,7 @@ write intent log information, three of which are mentioned here.
  * But it avoids high order page allocations in kmalloc.
  */
 struct lc_element {
-	struct hlist_node colision;
+	struct hlist_node collision;
 	struct list_head list;		 /* LRU list or free list */
 	unsigned refcnt;
 	/* back "pointer" into lc_cache->element[index],
diff --git a/include/linux/lsm/apparmor.h b/include/linux/lsm/apparmor.h
new file mode 100644
index 000000000000..612cbfacb072
--- /dev/null
+++ b/include/linux/lsm/apparmor.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linux Security Module interface to other subsystems.
+ * AppArmor presents single pointer to an aa_label structure.
+ */
+#ifndef __LINUX_LSM_APPARMOR_H
+#define __LINUX_LSM_APPARMOR_H
+
+struct aa_label;
+
+struct lsm_prop_apparmor {
+#ifdef CONFIG_SECURITY_APPARMOR
+	struct aa_label *label;
+#endif
+};
+
+#endif /* ! __LINUX_LSM_APPARMOR_H */
diff --git a/include/linux/lsm/bpf.h b/include/linux/lsm/bpf.h
new file mode 100644
index 000000000000..8106e206fcef
--- /dev/null
+++ b/include/linux/lsm/bpf.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linux Security Module interface to other subsystems.
+ * BPF may present a single u32 value.
+ */
+#ifndef __LINUX_LSM_BPF_H
+#define __LINUX_LSM_BPF_H
+#include <linux/types.h>
+
+struct lsm_prop_bpf {
+#ifdef CONFIG_BPF_LSM
+	u32 secid;
+#endif
+};
+
+#endif /* ! __LINUX_LSM_BPF_H */
diff --git a/include/linux/lsm/selinux.h b/include/linux/lsm/selinux.h
new file mode 100644
index 000000000000..9455a6b5b910
--- /dev/null
+++ b/include/linux/lsm/selinux.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linux Security Module interface to other subsystems.
+ * SELinux presents a single u32 value which is known as a secid.
+ */
+#ifndef __LINUX_LSM_SELINUX_H
+#define __LINUX_LSM_SELINUX_H
+#include <linux/types.h>
+
+struct lsm_prop_selinux {
+#ifdef CONFIG_SECURITY_SELINUX
+	u32 secid;
+#endif
+};
+
+#endif /* ! __LINUX_LSM_SELINUX_H */
diff --git a/include/linux/lsm/smack.h b/include/linux/lsm/smack.h
new file mode 100644
index 000000000000..ff730dd7a734
--- /dev/null
+++ b/include/linux/lsm/smack.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Linux Security Module interface to other subsystems.
+ * Smack presents a pointer into the global Smack label list.
+ */
+#ifndef __LINUX_LSM_SMACK_H
+#define __LINUX_LSM_SMACK_H
+
+struct smack_known;
+
+struct lsm_prop_smack {
+#ifdef CONFIG_SECURITY_SMACK
+	struct smack_known *skp;
+#endif
+};
+
+#endif /* ! __LINUX_LSM_SMACK_H */
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
index 97a8b21eb033..382c56a97bba 100644
--- a/include/linux/lsm_audit.h
+++ b/include/linux/lsm_audit.h
@@ -5,7 +5,7 @@
  *
  * Author : Etienne BASSET  <etienne.basset@ensta.org>
  *
- * All credits to : Stephen Smalley, <sds@tycho.nsa.gov>
+ * All credits to : Stephen Smalley
  * All BUGS to : Etienne BASSET  <etienne.basset@ensta.org>
  */
 #ifndef _LSM_COMMON_LOGGING_
@@ -77,6 +77,7 @@ struct common_audit_data {
 #define LSM_AUDIT_DATA_LOCKDOWN 15
 #define LSM_AUDIT_DATA_NOTIFICATION 16
 #define LSM_AUDIT_DATA_ANONINODE	17
+#define LSM_AUDIT_DATA_NLMSGTYPE	18
 	union 	{
 		struct path path;
 		struct dentry *dentry;
@@ -98,6 +99,7 @@ struct common_audit_data {
 		struct lsm_ibendport_audit *ibendport;
 		int reason;
 		const char *anonclass;
+		u16 nlmsg_type;
 	} u;
 	/* this union contains LSM specific data */
 	union {
@@ -116,14 +118,36 @@ struct common_audit_data {
 #define v4info fam.v4
 #define v6info fam.v6
 
+#ifdef CONFIG_AUDIT
+
 int ipv4_skb_to_auditdata(struct sk_buff *skb,
 		struct common_audit_data *ad, u8 *proto);
 
+#if IS_ENABLED(CONFIG_IPV6)
 int ipv6_skb_to_auditdata(struct sk_buff *skb,
 		struct common_audit_data *ad, u8 *proto);
+#endif /* IS_ENABLED(CONFIG_IPV6) */
 
 void common_lsm_audit(struct common_audit_data *a,
 	void (*pre_audit)(struct audit_buffer *, void *),
 	void (*post_audit)(struct audit_buffer *, void *));
 
+void audit_log_lsm_data(struct audit_buffer *ab,
+			const struct common_audit_data *a);
+
+#else /* CONFIG_AUDIT */
+
+static inline void common_lsm_audit(struct common_audit_data *a,
+	void (*pre_audit)(struct audit_buffer *, void *),
+	void (*post_audit)(struct audit_buffer *, void *))
+{
+}
+
+static inline void audit_log_lsm_data(struct audit_buffer *ab,
+			const struct common_audit_data *a)
+{
+}
+
+#endif /* CONFIG_AUDIT */
+
 #endif
diff --git a/include/linux/lsm_count.h b/include/linux/lsm_count.h
new file mode 100644
index 000000000000..16eb49761b25
--- /dev/null
+++ b/include/linux/lsm_count.h
@@ -0,0 +1,135 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+/*
+ * Copyright (C) 2023 Google LLC.
+ */
+
+#ifndef __LINUX_LSM_COUNT_H
+#define __LINUX_LSM_COUNT_H
+
+#include <linux/args.h>
+
+#ifdef CONFIG_SECURITY
+
+/*
+ * Macros to count the number of LSMs enabled in the kernel at compile time.
+ */
+
+/*
+ * Capabilities is enabled when CONFIG_SECURITY is enabled.
+ */
+#if IS_ENABLED(CONFIG_SECURITY)
+#define CAPABILITIES_ENABLED 1,
+#else
+#define CAPABILITIES_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_SELINUX)
+#define SELINUX_ENABLED 1,
+#else
+#define SELINUX_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_SMACK)
+#define SMACK_ENABLED 1,
+#else
+#define SMACK_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_APPARMOR)
+#define APPARMOR_ENABLED 1,
+#else
+#define APPARMOR_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_TOMOYO)
+#define TOMOYO_ENABLED 1,
+#else
+#define TOMOYO_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_YAMA)
+#define YAMA_ENABLED 1,
+#else
+#define YAMA_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_LOADPIN)
+#define LOADPIN_ENABLED 1,
+#else
+#define LOADPIN_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_LOCKDOWN_LSM)
+#define LOCKDOWN_ENABLED 1,
+#else
+#define LOCKDOWN_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_SAFESETID)
+#define SAFESETID_ENABLED 1,
+#else
+#define SAFESETID_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_BPF_LSM)
+#define BPF_LSM_ENABLED 1,
+#else
+#define BPF_LSM_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_LANDLOCK)
+#define LANDLOCK_ENABLED 1,
+#else
+#define LANDLOCK_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_IMA)
+#define IMA_ENABLED 1,
+#else
+#define IMA_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_EVM)
+#define EVM_ENABLED 1,
+#else
+#define EVM_ENABLED
+#endif
+
+#if IS_ENABLED(CONFIG_SECURITY_IPE)
+#define IPE_ENABLED 1,
+#else
+#define IPE_ENABLED
+#endif
+
+/*
+ *  There is a trailing comma that we need to be accounted for. This is done by
+ *  using a skipped argument in __COUNT_LSMS
+ */
+#define __COUNT_LSMS(skipped_arg, args...) COUNT_ARGS(args...)
+#define COUNT_LSMS(args...) __COUNT_LSMS(args)
+
+#define MAX_LSM_COUNT			\
+	COUNT_LSMS(			\
+		CAPABILITIES_ENABLED	\
+		SELINUX_ENABLED		\
+		SMACK_ENABLED		\
+		APPARMOR_ENABLED	\
+		TOMOYO_ENABLED		\
+		YAMA_ENABLED		\
+		LOADPIN_ENABLED		\
+		LOCKDOWN_ENABLED	\
+		SAFESETID_ENABLED	\
+		BPF_LSM_ENABLED		\
+		LANDLOCK_ENABLED	\
+		IMA_ENABLED		\
+		EVM_ENABLED		\
+		IPE_ENABLED)
+
+#else
+
+#define MAX_LSM_COUNT 0
+
+#endif /* CONFIG_SECURITY */
+
+#endif  /* __LINUX_LSM_COUNT_H */
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 6bb55e61e8e8..8c42b4bde09c 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -32,28 +32,29 @@ LSM_HOOK(int, 0, binder_transaction, const struct cred *from,
 LSM_HOOK(int, 0, binder_transfer_binder, const struct cred *from,
 	 const struct cred *to)
 LSM_HOOK(int, 0, binder_transfer_file, const struct cred *from,
-	 const struct cred *to, struct file *file)
+	 const struct cred *to, const struct file *file)
 LSM_HOOK(int, 0, ptrace_access_check, struct task_struct *child,
 	 unsigned int mode)
 LSM_HOOK(int, 0, ptrace_traceme, struct task_struct *parent)
-LSM_HOOK(int, 0, capget, struct task_struct *target, kernel_cap_t *effective,
+LSM_HOOK(int, 0, capget, const struct task_struct *target, kernel_cap_t *effective,
 	 kernel_cap_t *inheritable, kernel_cap_t *permitted)
 LSM_HOOK(int, 0, capset, struct cred *new, const struct cred *old,
 	 const kernel_cap_t *effective, const kernel_cap_t *inheritable,
 	 const kernel_cap_t *permitted)
 LSM_HOOK(int, 0, capable, const struct cred *cred, struct user_namespace *ns,
 	 int cap, unsigned int opts)
-LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, struct super_block *sb)
+LSM_HOOK(int, 0, quotactl, int cmds, int type, int id, const struct super_block *sb)
 LSM_HOOK(int, 0, quota_on, struct dentry *dentry)
 LSM_HOOK(int, 0, syslog, int type)
 LSM_HOOK(int, 0, settime, const struct timespec64 *ts,
 	 const struct timezone *tz)
 LSM_HOOK(int, 0, vm_enough_memory, struct mm_struct *mm, long pages)
 LSM_HOOK(int, 0, bprm_creds_for_exec, struct linux_binprm *bprm)
-LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, struct file *file)
+LSM_HOOK(int, 0, bprm_creds_from_file, struct linux_binprm *bprm, const struct file *file)
 LSM_HOOK(int, 0, bprm_check_security, struct linux_binprm *bprm)
-LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, struct linux_binprm *bprm)
-LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, struct linux_binprm *bprm)
+LSM_HOOK(void, LSM_RET_VOID, bprm_committing_creds, const struct linux_binprm *bprm)
+LSM_HOOK(void, LSM_RET_VOID, bprm_committed_creds, const struct linux_binprm *bprm)
+LSM_HOOK(int, 0, fs_context_submount, struct fs_context *fc, struct super_block *reference)
 LSM_HOOK(int, 0, fs_context_dup, struct fs_context *fc,
 	 struct fs_context *src_sc)
 LSM_HOOK(int, -ENOPARAM, fs_context_parse_param, struct fs_context *fc,
@@ -65,7 +66,7 @@ LSM_HOOK(void, LSM_RET_VOID, sb_free_mnt_opts, void *mnt_opts)
 LSM_HOOK(int, 0, sb_eat_lsm_opts, char *orig, void **mnt_opts)
 LSM_HOOK(int, 0, sb_mnt_opts_compat, struct super_block *sb, void *mnt_opts)
 LSM_HOOK(int, 0, sb_remount, struct super_block *sb, void *mnt_opts)
-LSM_HOOK(int, 0, sb_kern_mount, struct super_block *sb)
+LSM_HOOK(int, 0, sb_kern_mount, const struct super_block *sb)
 LSM_HOOK(int, 0, sb_show_options, struct seq_file *m, struct super_block *sb)
 LSM_HOOK(int, 0, sb_statfs, struct dentry *dentry)
 LSM_HOOK(int, 0, sb_mount, const char *dev_name, const struct path *path,
@@ -82,9 +83,9 @@ LSM_HOOK(int, 0, move_mount, const struct path *from_path,
 	 const struct path *to_path)
 LSM_HOOK(int, -EOPNOTSUPP, dentry_init_security, struct dentry *dentry,
 	 int mode, const struct qstr *name, const char **xattr_name,
-	 void **ctx, u32 *ctxlen)
+	 struct lsm_context *cp)
 LSM_HOOK(int, 0, dentry_create_files_as, struct dentry *dentry, int mode,
-	 struct qstr *name, const struct cred *old, struct cred *new)
+	 const struct qstr *name, const struct cred *old, struct cred *new)
 
 #ifdef CONFIG_SECURITY_PATH
 LSM_HOOK(int, 0, path_unlink, const struct path *dir, struct dentry *dentry)
@@ -93,6 +94,8 @@ LSM_HOOK(int, 0, path_mkdir, const struct path *dir, struct dentry *dentry,
 LSM_HOOK(int, 0, path_rmdir, const struct path *dir, struct dentry *dentry)
 LSM_HOOK(int, 0, path_mknod, const struct path *dir, struct dentry *dentry,
 	 umode_t mode, unsigned int dev)
+LSM_HOOK(void, LSM_RET_VOID, path_post_mknod, struct mnt_idmap *idmap,
+	 struct dentry *dentry)
 LSM_HOOK(int, 0, path_truncate, const struct path *path)
 LSM_HOOK(int, 0, path_symlink, const struct path *dir, struct dentry *dentry,
 	 const char *old_name)
@@ -111,13 +114,16 @@ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask,
 	 unsigned int obj_type)
 LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode)
 LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode)
-LSM_HOOK(int, 0, inode_init_security, struct inode *inode,
-	 struct inode *dir, const struct qstr *qstr, const char **name,
-	 void **value, size_t *len)
+LSM_HOOK(void, LSM_RET_VOID, inode_free_security_rcu, void *inode_security)
+LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode,
+	 struct inode *dir, const struct qstr *qstr, struct xattr *xattrs,
+	 int *xattr_count)
 LSM_HOOK(int, 0, inode_init_security_anon, struct inode *inode,
 	 const struct qstr *name, const struct inode *context_inode)
 LSM_HOOK(int, 0, inode_create, struct inode *dir, struct dentry *dentry,
 	 umode_t mode)
+LSM_HOOK(void, LSM_RET_VOID, inode_post_create_tmpfile, struct mnt_idmap *idmap,
+	 struct inode *inode)
 LSM_HOOK(int, 0, inode_link, struct dentry *old_dentry, struct inode *dir,
 	 struct dentry *new_dentry)
 LSM_HOOK(int, 0, inode_unlink, struct inode *dir, struct dentry *dentry)
@@ -134,8 +140,12 @@ LSM_HOOK(int, 0, inode_readlink, struct dentry *dentry)
 LSM_HOOK(int, 0, inode_follow_link, struct dentry *dentry, struct inode *inode,
 	 bool rcu)
 LSM_HOOK(int, 0, inode_permission, struct inode *inode, int mask)
-LSM_HOOK(int, 0, inode_setattr, struct dentry *dentry, struct iattr *attr)
+LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry,
+	 struct iattr *attr)
+LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap,
+	 struct dentry *dentry, int ia_valid)
 LSM_HOOK(int, 0, inode_getattr, const struct path *path)
+LSM_HOOK(int, 0, inode_xattr_skipcap, const char *name)
 LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *name, const void *value,
 	 size_t size, int flags)
@@ -145,12 +155,20 @@ LSM_HOOK(int, 0, inode_getxattr, struct dentry *dentry, const char *name)
 LSM_HOOK(int, 0, inode_listxattr, struct dentry *dentry)
 LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *name)
+LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry,
+	 const char *name)
+LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct file_kattr *fa)
+LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct file_kattr *fa)
 LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *acl_name, struct posix_acl *kacl)
+LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry,
+	 const char *acl_name, struct posix_acl *kacl)
 LSM_HOOK(int, 0, inode_get_acl, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *acl_name)
 LSM_HOOK(int, 0, inode_remove_acl, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *acl_name)
+LSM_HOOK(void, LSM_RET_VOID, inode_post_remove_acl, struct mnt_idmap *idmap,
+	 struct dentry *dentry, const char *acl_name)
 LSM_HOOK(int, 0, inode_need_killpriv, struct dentry *dentry)
 LSM_HOOK(int, 0, inode_killpriv, struct mnt_idmap *idmap,
 	 struct dentry *dentry)
@@ -160,16 +178,23 @@ LSM_HOOK(int, -EOPNOTSUPP, inode_setsecurity, struct inode *inode,
 	 const char *name, const void *value, size_t size, int flags)
 LSM_HOOK(int, 0, inode_listsecurity, struct inode *inode, char *buffer,
 	 size_t buffer_size)
-LSM_HOOK(void, LSM_RET_VOID, inode_getsecid, struct inode *inode, u32 *secid)
+LSM_HOOK(void, LSM_RET_VOID, inode_getlsmprop, struct inode *inode,
+	 struct lsm_prop *prop)
 LSM_HOOK(int, 0, inode_copy_up, struct dentry *src, struct cred **new)
-LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, const char *name)
+LSM_HOOK(int, -EOPNOTSUPP, inode_copy_up_xattr, struct dentry *src,
+	 const char *name)
+LSM_HOOK(int, 0, inode_setintegrity, const struct inode *inode,
+	 enum lsm_integrity_type type, const void *value, size_t size)
 LSM_HOOK(int, 0, kernfs_init_security, struct kernfs_node *kn_dir,
 	 struct kernfs_node *kn)
 LSM_HOOK(int, 0, file_permission, struct file *file, int mask)
 LSM_HOOK(int, 0, file_alloc_security, struct file *file)
+LSM_HOOK(void, LSM_RET_VOID, file_release, struct file *file)
 LSM_HOOK(void, LSM_RET_VOID, file_free_security, struct file *file)
 LSM_HOOK(int, 0, file_ioctl, struct file *file, unsigned int cmd,
 	 unsigned long arg)
+LSM_HOOK(int, 0, file_ioctl_compat, struct file *file, unsigned int cmd,
+	 unsigned long arg)
 LSM_HOOK(int, 0, mmap_addr, unsigned long addr)
 LSM_HOOK(int, 0, mmap_file, struct file *file, unsigned long reqprot,
 	 unsigned long prot, unsigned long flags)
@@ -183,9 +208,10 @@ LSM_HOOK(int, 0, file_send_sigiotask, struct task_struct *tsk,
 	 struct fown_struct *fown, int sig)
 LSM_HOOK(int, 0, file_receive, struct file *file)
 LSM_HOOK(int, 0, file_open, struct file *file)
+LSM_HOOK(int, 0, file_post_open, struct file *file, int mask)
 LSM_HOOK(int, 0, file_truncate, struct file *file)
 LSM_HOOK(int, 0, task_alloc, struct task_struct *task,
-	 unsigned long clone_flags)
+	 u64 clone_flags)
 LSM_HOOK(void, LSM_RET_VOID, task_free, struct task_struct *task)
 LSM_HOOK(int, 0, cred_alloc_blank, struct cred *cred, gfp_t gfp)
 LSM_HOOK(void, LSM_RET_VOID, cred_free, struct cred *cred)
@@ -194,6 +220,8 @@ LSM_HOOK(int, 0, cred_prepare, struct cred *new, const struct cred *old,
 LSM_HOOK(void, LSM_RET_VOID, cred_transfer, struct cred *new,
 	 const struct cred *old)
 LSM_HOOK(void, LSM_RET_VOID, cred_getsecid, const struct cred *c, u32 *secid)
+LSM_HOOK(void, LSM_RET_VOID, cred_getlsmprop, const struct cred *c,
+	 struct lsm_prop *prop)
 LSM_HOOK(int, 0, kernel_act_as, struct cred *new, u32 secid)
 LSM_HOOK(int, 0, kernel_create_files_as, struct cred *new, struct inode *inode)
 LSM_HOOK(int, 0, kernel_module_request, char *kmod_name)
@@ -212,9 +240,9 @@ LSM_HOOK(int, 0, task_fix_setgroups, struct cred *new, const struct cred * old)
 LSM_HOOK(int, 0, task_setpgid, struct task_struct *p, pid_t pgid)
 LSM_HOOK(int, 0, task_getpgid, struct task_struct *p)
 LSM_HOOK(int, 0, task_getsid, struct task_struct *p)
-LSM_HOOK(void, LSM_RET_VOID, current_getsecid_subj, u32 *secid)
-LSM_HOOK(void, LSM_RET_VOID, task_getsecid_obj,
-	 struct task_struct *p, u32 *secid)
+LSM_HOOK(void, LSM_RET_VOID, current_getlsmprop_subj, struct lsm_prop *prop)
+LSM_HOOK(void, LSM_RET_VOID, task_getlsmprop_obj,
+	 struct task_struct *p, struct lsm_prop *prop)
 LSM_HOOK(int, 0, task_setnice, struct task_struct *p, int nice)
 LSM_HOOK(int, 0, task_setioprio, struct task_struct *p, int ioprio)
 LSM_HOOK(int, 0, task_getioprio, struct task_struct *p)
@@ -233,8 +261,8 @@ LSM_HOOK(void, LSM_RET_VOID, task_to_inode, struct task_struct *p,
 	 struct inode *inode)
 LSM_HOOK(int, 0, userns_create, const struct cred *cred)
 LSM_HOOK(int, 0, ipc_permission, struct kern_ipc_perm *ipcp, short flag)
-LSM_HOOK(void, LSM_RET_VOID, ipc_getsecid, struct kern_ipc_perm *ipcp,
-	 u32 *secid)
+LSM_HOOK(void, LSM_RET_VOID, ipc_getlsmprop, struct kern_ipc_perm *ipcp,
+	 struct lsm_prop *prop)
 LSM_HOOK(int, 0, msg_msg_alloc_security, struct msg_msg *msg)
 LSM_HOOK(void, LSM_RET_VOID, msg_msg_free_security, struct msg_msg *msg)
 LSM_HOOK(int, 0, msg_queue_alloc_security, struct kern_ipc_perm *perm)
@@ -261,19 +289,24 @@ LSM_HOOK(int, 0, sem_semop, struct kern_ipc_perm *perm, struct sembuf *sops,
 LSM_HOOK(int, 0, netlink_send, struct sock *sk, struct sk_buff *skb)
 LSM_HOOK(void, LSM_RET_VOID, d_instantiate, struct dentry *dentry,
 	 struct inode *inode)
+LSM_HOOK(int, -EOPNOTSUPP, getselfattr, unsigned int attr,
+	 struct lsm_ctx __user *ctx, u32 *size, u32 flags)
+LSM_HOOK(int, -EOPNOTSUPP, setselfattr, unsigned int attr,
+	 struct lsm_ctx *ctx, u32 size, u32 flags)
 LSM_HOOK(int, -EINVAL, getprocattr, struct task_struct *p, const char *name,
 	 char **value)
 LSM_HOOK(int, -EINVAL, setprocattr, const char *name, void *value, size_t size)
 LSM_HOOK(int, 0, ismaclabel, const char *name)
-LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, char **secdata,
-	 u32 *seclen)
+LSM_HOOK(int, -EOPNOTSUPP, secid_to_secctx, u32 secid, struct lsm_context *cp)
+LSM_HOOK(int, -EOPNOTSUPP, lsmprop_to_secctx, struct lsm_prop *prop,
+	 struct lsm_context *cp)
 LSM_HOOK(int, 0, secctx_to_secid, const char *secdata, u32 seclen, u32 *secid)
-LSM_HOOK(void, LSM_RET_VOID, release_secctx, char *secdata, u32 seclen)
+LSM_HOOK(void, LSM_RET_VOID, release_secctx, struct lsm_context *cp)
 LSM_HOOK(void, LSM_RET_VOID, inode_invalidate_secctx, struct inode *inode)
 LSM_HOOK(int, 0, inode_notifysecctx, struct inode *inode, void *ctx, u32 ctxlen)
 LSM_HOOK(int, 0, inode_setsecctx, struct dentry *dentry, void *ctx, u32 ctxlen)
-LSM_HOOK(int, 0, inode_getsecctx, struct inode *inode, void **ctx,
-	 u32 *ctxlen)
+LSM_HOOK(int, -EOPNOTSUPP, inode_getsecctx, struct inode *inode,
+	 struct lsm_context *cp)
 
 #if defined(CONFIG_SECURITY) && defined(CONFIG_WATCH_QUEUE)
 LSM_HOOK(int, 0, post_notification, const struct cred *w_cred,
@@ -308,15 +341,15 @@ LSM_HOOK(int, 0, socket_getsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_setsockopt, struct socket *sock, int level, int optname)
 LSM_HOOK(int, 0, socket_shutdown, struct socket *sock, int how)
 LSM_HOOK(int, 0, socket_sock_rcv_skb, struct sock *sk, struct sk_buff *skb)
-LSM_HOOK(int, 0, socket_getpeersec_stream, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_stream, struct socket *sock,
 	 sockptr_t optval, sockptr_t optlen, unsigned int len)
-LSM_HOOK(int, 0, socket_getpeersec_dgram, struct socket *sock,
+LSM_HOOK(int, -ENOPROTOOPT, socket_getpeersec_dgram, struct socket *sock,
 	 struct sk_buff *skb, u32 *secid)
 LSM_HOOK(int, 0, sk_alloc_security, struct sock *sk, int family, gfp_t priority)
 LSM_HOOK(void, LSM_RET_VOID, sk_free_security, struct sock *sk)
 LSM_HOOK(void, LSM_RET_VOID, sk_clone_security, const struct sock *sk,
 	 struct sock *newsk)
-LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, struct sock *sk, u32 *secid)
+LSM_HOOK(void, LSM_RET_VOID, sk_getsecid, const struct sock *sk, u32 *secid)
 LSM_HOOK(void, LSM_RET_VOID, sock_graft, struct sock *sk, struct socket *parent)
 LSM_HOOK(int, 0, inet_conn_request, const struct sock *sk, struct sk_buff *skb,
 	 struct request_sock *req)
@@ -329,8 +362,7 @@ LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_inc, void)
 LSM_HOOK(void, LSM_RET_VOID, secmark_refcount_dec, void)
 LSM_HOOK(void, LSM_RET_VOID, req_classify_flow, const struct request_sock *req,
 	 struct flowi_common *flic)
-LSM_HOOK(int, 0, tun_dev_alloc_security, void **security)
-LSM_HOOK(void, LSM_RET_VOID, tun_dev_free_security, void *security)
+LSM_HOOK(int, 0, tun_dev_alloc_security, void *security)
 LSM_HOOK(int, 0, tun_dev_create, void)
 LSM_HOOK(int, 0, tun_dev_attach_queue, void *security)
 LSM_HOOK(int, 0, tun_dev_attach, struct sock *sk, void *security)
@@ -343,14 +375,14 @@ LSM_HOOK(void, LSM_RET_VOID, sctp_sk_clone, struct sctp_association *asoc,
 	 struct sock *sk, struct sock *newsk)
 LSM_HOOK(int, 0, sctp_assoc_established, struct sctp_association *asoc,
 	 struct sk_buff *skb)
+LSM_HOOK(int, 0, mptcp_add_subflow, struct sock *sk, struct sock *ssk)
 #endif /* CONFIG_SECURITY_NETWORK */
 
 #ifdef CONFIG_SECURITY_INFINIBAND
 LSM_HOOK(int, 0, ib_pkey_access, void *sec, u64 subnet_prefix, u16 pkey)
 LSM_HOOK(int, 0, ib_endport_manage_subnet, void *sec, const char *dev_name,
 	 u8 port_num)
-LSM_HOOK(int, 0, ib_alloc_security, void **sec)
-LSM_HOOK(void, LSM_RET_VOID, ib_free_security, void *sec)
+LSM_HOOK(int, 0, ib_alloc_security, void *sec)
 #endif /* CONFIG_SECURITY_INFINIBAND */
 
 #ifdef CONFIG_SECURITY_NETWORK_XFRM
@@ -378,36 +410,45 @@ LSM_HOOK(int, 0, xfrm_decode_session, struct sk_buff *skb, u32 *secid,
 #ifdef CONFIG_KEYS
 LSM_HOOK(int, 0, key_alloc, struct key *key, const struct cred *cred,
 	 unsigned long flags)
-LSM_HOOK(void, LSM_RET_VOID, key_free, struct key *key)
 LSM_HOOK(int, 0, key_permission, key_ref_t key_ref, const struct cred *cred,
 	 enum key_need_perm need_perm)
 LSM_HOOK(int, 0, key_getsecurity, struct key *key, char **buffer)
+LSM_HOOK(void, LSM_RET_VOID, key_post_create_or_update, struct key *keyring,
+	 struct key *key, const void *payload, size_t payload_len,
+	 unsigned long flags, bool create)
 #endif /* CONFIG_KEYS */
 
 #ifdef CONFIG_AUDIT
 LSM_HOOK(int, 0, audit_rule_init, u32 field, u32 op, char *rulestr,
-	 void **lsmrule)
+	 void **lsmrule, gfp_t gfp)
 LSM_HOOK(int, 0, audit_rule_known, struct audit_krule *krule)
-LSM_HOOK(int, 0, audit_rule_match, u32 secid, u32 field, u32 op, void *lsmrule)
+LSM_HOOK(int, 0, audit_rule_match, struct lsm_prop *prop, u32 field, u32 op,
+	 void *lsmrule)
 LSM_HOOK(void, LSM_RET_VOID, audit_rule_free, void *lsmrule)
 #endif /* CONFIG_AUDIT */
 
 #ifdef CONFIG_BPF_SYSCALL
-LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size)
+LSM_HOOK(int, 0, bpf, int cmd, union bpf_attr *attr, unsigned int size, bool kernel)
 LSM_HOOK(int, 0, bpf_map, struct bpf_map *map, fmode_t fmode)
 LSM_HOOK(int, 0, bpf_prog, struct bpf_prog *prog)
-LSM_HOOK(int, 0, bpf_map_alloc_security, struct bpf_map *map)
-LSM_HOOK(void, LSM_RET_VOID, bpf_map_free_security, struct bpf_map *map)
-LSM_HOOK(int, 0, bpf_prog_alloc_security, struct bpf_prog_aux *aux)
-LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free_security, struct bpf_prog_aux *aux)
+LSM_HOOK(int, 0, bpf_map_create, struct bpf_map *map, union bpf_attr *attr,
+	 struct bpf_token *token, bool kernel)
+LSM_HOOK(void, LSM_RET_VOID, bpf_map_free, struct bpf_map *map)
+LSM_HOOK(int, 0, bpf_prog_load, struct bpf_prog *prog, union bpf_attr *attr,
+	 struct bpf_token *token, bool kernel)
+LSM_HOOK(void, LSM_RET_VOID, bpf_prog_free, struct bpf_prog *prog)
+LSM_HOOK(int, 0, bpf_token_create, struct bpf_token *token, union bpf_attr *attr,
+	 const struct path *path)
+LSM_HOOK(void, LSM_RET_VOID, bpf_token_free, struct bpf_token *token)
+LSM_HOOK(int, 0, bpf_token_cmd, const struct bpf_token *token, enum bpf_cmd cmd)
+LSM_HOOK(int, 0, bpf_token_capable, const struct bpf_token *token, int cap)
 #endif /* CONFIG_BPF_SYSCALL */
 
 LSM_HOOK(int, 0, locked_down, enum lockdown_reason what)
 
 #ifdef CONFIG_PERF_EVENTS
-LSM_HOOK(int, 0, perf_event_open, struct perf_event_attr *attr, int type)
+LSM_HOOK(int, 0, perf_event_open, int type)
 LSM_HOOK(int, 0, perf_event_alloc, struct perf_event *event)
-LSM_HOOK(void, LSM_RET_VOID, perf_event_free, struct perf_event *event)
 LSM_HOOK(int, 0, perf_event_read, struct perf_event *event)
 LSM_HOOK(int, 0, perf_event_write, struct perf_event *event)
 #endif /* CONFIG_PERF_EVENTS */
@@ -416,4 +457,12 @@ LSM_HOOK(int, 0, perf_event_write, struct perf_event *event)
 LSM_HOOK(int, 0, uring_override_creds, const struct cred *new)
 LSM_HOOK(int, 0, uring_sqpoll, void)
 LSM_HOOK(int, 0, uring_cmd, struct io_uring_cmd *ioucmd)
+LSM_HOOK(int, 0, uring_allowed, void)
 #endif /* CONFIG_IO_URING */
+
+LSM_HOOK(void, LSM_RET_VOID, initramfs_populated, void)
+
+LSM_HOOK(int, 0, bdev_alloc_security, struct block_device *bdev)
+LSM_HOOK(void, LSM_RET_VOID, bdev_free_security, struct block_device *bdev)
+LSM_HOOK(int, 0, bdev_setintegrity, struct block_device *bdev,
+	 enum lsm_integrity_type type, const void *value, size_t size)
diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
index ab2b2fafa4a4..b92008641242 100644
--- a/include/linux/lsm_hooks.h
+++ b/include/linux/lsm_hooks.h
@@ -25,44 +25,100 @@
 #ifndef __LINUX_LSM_HOOKS_H
 #define __LINUX_LSM_HOOKS_H
 
+#include <uapi/linux/lsm.h>
 #include <linux/security.h>
 #include <linux/init.h>
 #include <linux/rculist.h>
+#include <linux/xattr.h>
+#include <linux/static_call.h>
+#include <linux/unroll.h>
+#include <linux/jump_label.h>
+#include <linux/lsm_count.h>
 
 union security_list_options {
 	#define LSM_HOOK(RET, DEFAULT, NAME, ...) RET (*NAME)(__VA_ARGS__);
 	#include "lsm_hook_defs.h"
 	#undef LSM_HOOK
+	void *lsm_func_addr;
 };
 
-struct security_hook_heads {
-	#define LSM_HOOK(RET, DEFAULT, NAME, ...) struct hlist_head NAME;
-	#include "lsm_hook_defs.h"
-	#undef LSM_HOOK
+/*
+ * @key: static call key as defined by STATIC_CALL_KEY
+ * @trampoline: static call trampoline as defined by STATIC_CALL_TRAMP
+ * @hl: The security_hook_list as initialized by the owning LSM.
+ * @active: Enabled when the static call has an LSM hook associated.
+ */
+struct lsm_static_call {
+	struct static_call_key *key;
+	void *trampoline;
+	struct security_hook_list *hl;
+	/* this needs to be true or false based on what the key defaults to */
+	struct static_key_false *active;
 } __randomize_layout;
 
 /*
+ * Table of the static calls for each LSM hook.
+ * Once the LSMs are initialized, their callbacks will be copied to these
+ * tables such that the calls are filled backwards (from last to first).
+ * This way, we can jump directly to the first used static call, and execute
+ * all of them after. This essentially makes the entry point
+ * dynamic to adapt the number of static calls to the number of callbacks.
+ */
+struct lsm_static_calls_table {
+	#define LSM_HOOK(RET, DEFAULT, NAME, ...) \
+		struct lsm_static_call NAME[MAX_LSM_COUNT];
+	#include <linux/lsm_hook_defs.h>
+	#undef LSM_HOOK
+} __packed __randomize_layout;
+
+/**
+ * struct lsm_id - Identify a Linux Security Module.
+ * @lsm: name of the LSM, must be approved by the LSM maintainers
+ * @id: LSM ID number from uapi/linux/lsm.h
+ *
+ * Contains the information that identifies the LSM.
+ */
+struct lsm_id {
+	const char *name;
+	u64 id;
+};
+
+/*
  * Security module hook list structure.
  * For use with generic list macros for common operations.
+ *
+ * struct security_hook_list - Contents of a cacheable, mappable object.
+ * @scalls: The beginning of the array of static calls assigned to this hook.
+ * @hook: The callback for the hook.
+ * @lsm: The name of the lsm that owns this hook.
  */
 struct security_hook_list {
-	struct hlist_node		list;
-	struct hlist_head		*head;
-	union security_list_options	hook;
-	const char			*lsm;
+	struct lsm_static_call *scalls;
+	union security_list_options hook;
+	const struct lsm_id *lsmid;
 } __randomize_layout;
 
 /*
  * Security blob size or offset data.
  */
 struct lsm_blob_sizes {
-	int	lbs_cred;
-	int	lbs_file;
-	int	lbs_inode;
-	int	lbs_superblock;
-	int	lbs_ipc;
-	int	lbs_msg_msg;
-	int	lbs_task;
+	unsigned int lbs_cred;
+	unsigned int lbs_file;
+	unsigned int lbs_ib;
+	unsigned int lbs_inode;
+	unsigned int lbs_sock;
+	unsigned int lbs_superblock;
+	unsigned int lbs_ipc;
+	unsigned int lbs_key;
+	unsigned int lbs_msg_msg;
+	unsigned int lbs_perf_event;
+	unsigned int lbs_task;
+	unsigned int lbs_xattr_count; /* num xattr slots in new_xattrs array */
+	unsigned int lbs_tun_dev;
+	unsigned int lbs_bdev;
+	unsigned int lbs_bpf_map;
+	unsigned int lbs_bpf_prog;
+	unsigned int lbs_bpf_token;
 };
 
 /*
@@ -77,14 +133,14 @@ struct lsm_blob_sizes {
  * care of the common case and reduces the amount of
  * text involved.
  */
-#define LSM_HOOK_INIT(HEAD, HOOK) \
-	{ .head = &security_hook_heads.HEAD, .hook = { .HEAD = HOOK } }
-
-extern struct security_hook_heads security_hook_heads;
-extern char *lsm_names;
+#define LSM_HOOK_INIT(NAME, HOOK)			\
+	{						\
+		.scalls = static_calls_table.NAME,	\
+		.hook = { .NAME = HOOK }		\
+	}
 
 extern void security_add_hooks(struct security_hook_list *hooks, int count,
-				const char *lsm);
+			       const struct lsm_id *lsmid);
 
 #define LSM_FLAG_LEGACY_MAJOR	BIT(0)
 #define LSM_FLAG_EXCLUSIVE	BIT(1)
@@ -95,18 +151,38 @@ enum lsm_order {
 	LSM_ORDER_LAST = 1,	/* This is only for integrity. */
 };
 
+/**
+ * struct lsm_info - Define an individual LSM for the LSM framework.
+ * @id: LSM name/ID info
+ * @order: ordering with respect to other LSMs, optional
+ * @flags: descriptive flags, optional
+ * @blobs: LSM blob sharing, optional
+ * @enabled: controlled by CONFIG_LSM, optional
+ * @init: LSM specific initialization routine
+ * @initcall_pure: LSM callback for initcall_pure() setup, optional
+ * @initcall_early: LSM callback for early_initcall setup, optional
+ * @initcall_core: LSM callback for core_initcall() setup, optional
+ * @initcall_subsys: LSM callback for subsys_initcall() setup, optional
+ * @initcall_fs: LSM callback for fs_initcall setup, optional
+ * @nitcall_device: LSM callback for device_initcall() setup, optional
+ * @initcall_late: LSM callback for late_initcall() setup, optional
+ */
 struct lsm_info {
-	const char *name;	/* Required. */
-	enum lsm_order order;	/* Optional: default is LSM_ORDER_MUTABLE */
-	unsigned long flags;	/* Optional: flags describing LSM */
-	int *enabled;		/* Optional: controlled by CONFIG_LSM */
-	int (*init)(void);	/* Required. */
-	struct lsm_blob_sizes *blobs; /* Optional: for blob sharing. */
+	const struct lsm_id *id;
+	enum lsm_order order;
+	unsigned long flags;
+	struct lsm_blob_sizes *blobs;
+	int *enabled;
+	int (*init)(void);
+	int (*initcall_pure)(void);
+	int (*initcall_early)(void);
+	int (*initcall_core)(void);
+	int (*initcall_subsys)(void);
+	int (*initcall_fs)(void);
+	int (*initcall_device)(void);
+	int (*initcall_late)(void);
 };
 
-extern struct lsm_info __start_lsm_info[], __end_lsm_info[];
-extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[];
-
 #define DEFINE_LSM(lsm)							\
 	static struct lsm_info __lsm_##lsm				\
 		__used __section(".lsm_info.init")			\
@@ -117,6 +193,26 @@ extern struct lsm_info __start_early_lsm_info[], __end_early_lsm_info[];
 		__used __section(".early_lsm_info.init")		\
 		__aligned(sizeof(unsigned long))
 
-extern int lsm_inode_alloc(struct inode *inode);
+
+/* DO NOT tamper with these variables outside of the LSM framework */
+extern struct lsm_static_calls_table static_calls_table __ro_after_init;
+
+/**
+ * lsm_get_xattr_slot - Return the next available slot and increment the index
+ * @xattrs: array storing LSM-provided xattrs
+ * @xattr_count: number of already stored xattrs (updated)
+ *
+ * Retrieve the first available slot in the @xattrs array to fill with an xattr,
+ * and increment @xattr_count.
+ *
+ * Return: The slot to fill in @xattrs if non-NULL, NULL otherwise.
+ */
+static inline struct xattr *lsm_get_xattr_slot(struct xattr *xattrs,
+					       int *xattr_count)
+{
+	if (unlikely(!xattrs))
+		return NULL;
+	return &xattrs[(*xattr_count)++];
+}
 
 #endif /* ! __LINUX_LSM_HOOKS_H */
diff --git a/include/linux/lwq.h b/include/linux/lwq.h
new file mode 100644
index 000000000000..d081d5cf8e33
--- /dev/null
+++ b/include/linux/lwq.h
@@ -0,0 +1,124 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef LWQ_H
+#define LWQ_H
+/*
+ * Light-weight single-linked queue built from llist
+ *
+ * Entries can be enqueued from any context with no locking.
+ * Entries can be dequeued from process context with integrated locking.
+ *
+ * This is particularly suitable when work items are queued in
+ * BH or IRQ context, and where work items are handled one at a time
+ * by dedicated threads.
+ */
+#include <linux/container_of.h>
+#include <linux/spinlock.h>
+#include <linux/llist.h>
+
+struct lwq_node {
+	struct llist_node node;
+};
+
+struct lwq {
+	spinlock_t		lock;
+	struct llist_node	*ready;		/* entries to be dequeued */
+	struct llist_head	new;		/* entries being enqueued */
+};
+
+/**
+ * lwq_init - initialise a lwq
+ * @q:	the lwq object
+ */
+static inline void lwq_init(struct lwq *q)
+{
+	spin_lock_init(&q->lock);
+	q->ready = NULL;
+	init_llist_head(&q->new);
+}
+
+/**
+ * lwq_empty - test if lwq contains any entry
+ * @q:	the lwq object
+ *
+ * This empty test contains an acquire barrier so that if a wakeup
+ * is sent when lwq_dequeue returns true, it is safe to go to sleep after
+ * a test on lwq_empty().
+ */
+static inline bool lwq_empty(struct lwq *q)
+{
+	/* acquire ensures ordering wrt lwq_enqueue() */
+	return smp_load_acquire(&q->ready) == NULL && llist_empty(&q->new);
+}
+
+struct llist_node *__lwq_dequeue(struct lwq *q);
+/**
+ * lwq_dequeue - dequeue first (oldest) entry from lwq
+ * @q:		the queue to dequeue from
+ * @type:	the type of object to return
+ * @member:	them member in returned object which is an lwq_node.
+ *
+ * Remove a single object from the lwq and return it.  This will take
+ * a spinlock and so must always be called in the same context, typcially
+ * process contet.
+ */
+#define lwq_dequeue(q, type, member)					\
+	({ struct llist_node *_n = __lwq_dequeue(q);			\
+	  _n ? container_of(_n, type, member.node) : NULL; })
+
+struct llist_node *lwq_dequeue_all(struct lwq *q);
+
+/**
+ * lwq_for_each_safe - iterate over detached queue allowing deletion
+ * @_n:		iterator variable
+ * @_t1:	temporary struct llist_node **
+ * @_t2:	temporary struct llist_node *
+ * @_l:		address of llist_node pointer from lwq_dequeue_all()
+ * @_member:	member in _n where lwq_node is found.
+ *
+ * Iterate over members in a dequeued list.  If the iterator variable
+ * is set to NULL, the iterator removes that entry from the queue.
+ */
+#define lwq_for_each_safe(_n, _t1, _t2, _l, _member)			\
+	for (_t1 = (_l);						\
+	     *(_t1) ? (_n = container_of(*(_t1), typeof(*(_n)), _member.node),\
+		       _t2 = ((*_t1)->next),				\
+		       true)						\
+	     : false;							\
+	     (_n) ? (_t1 = &(_n)->_member.node.next, 0)			\
+	     : ((*(_t1) = (_t2)),  0))
+
+/**
+ * lwq_enqueue - add a new item to the end of the queue
+ * @n	- the lwq_node embedded in the item to be added
+ * @q	- the lwq to append to.
+ *
+ * No locking is needed to append to the queue so this can
+ * be called from any context.
+ * Return %true is the list may have previously been empty.
+ */
+static inline bool lwq_enqueue(struct lwq_node *n, struct lwq *q)
+{
+	/* acquire enqures ordering wrt lwq_dequeue */
+	return llist_add(&n->node, &q->new) &&
+		smp_load_acquire(&q->ready) == NULL;
+}
+
+/**
+ * lwq_enqueue_batch - add a list of new items to the end of the queue
+ * @n	- the lwq_node embedded in the first item to be added
+ * @q	- the lwq to append to.
+ *
+ * No locking is needed to append to the queue so this can
+ * be called from any context.
+ * Return %true is the list may have previously been empty.
+ */
+static inline bool lwq_enqueue_batch(struct llist_node *n, struct lwq *q)
+{
+	struct llist_node *e = n;
+
+	/* acquire enqures ordering wrt lwq_dequeue */
+	return llist_add_batch(llist_reverse_order(n), e, &q->new) &&
+		smp_load_acquire(&q->ready) == NULL;
+}
+#endif /* LWQ_H */
diff --git a/include/linux/lz4.h b/include/linux/lz4.h
index b16e15b9587a..ad6042a718b5 100644
--- a/include/linux/lz4.h
+++ b/include/linux/lz4.h
@@ -645,4 +645,10 @@ int LZ4_decompress_safe_usingDict(const char *source, char *dest,
 int LZ4_decompress_fast_usingDict(const char *source, char *dest,
 	int originalSize, const char *dictStart, int dictSize);
 
+#define LZ4_DECOMPRESS_INPLACE_MARGIN(compressedSize)          (((compressedSize) >> 8) + 32)
+
+#ifndef LZ4_DISTANCE_MAX	/* history window size; can be user-defined at compile time */
+#define LZ4_DISTANCE_MAX 65535	/* set to maximum value by default */
+#endif
+
 #endif
diff --git a/include/linux/lzo.h b/include/linux/lzo.h
index e95c7d1092b2..4d30e3624acd 100644
--- a/include/linux/lzo.h
+++ b/include/linux/lzo.h
@@ -24,10 +24,18 @@
 int lzo1x_1_compress(const unsigned char *src, size_t src_len,
 		     unsigned char *dst, size_t *dst_len, void *wrkmem);
 
+/* Same as above but does not write more than dst_len to dst. */
+int lzo1x_1_compress_safe(const unsigned char *src, size_t src_len,
+			  unsigned char *dst, size_t *dst_len, void *wrkmem);
+
 /* This requires 'wrkmem' of size LZO1X_1_MEM_COMPRESS */
 int lzorle1x_1_compress(const unsigned char *src, size_t src_len,
 		     unsigned char *dst, size_t *dst_len, void *wrkmem);
 
+/* Same as above but does not write more than dst_len to dst. */
+int lzorle1x_1_compress_safe(const unsigned char *src, size_t src_len,
+			     unsigned char *dst, size_t *dst_len, void *wrkmem);
+
 /* safe decompression with overrun testing */
 int lzo1x_decompress_safe(const unsigned char *src, size_t src_len,
 			  unsigned char *dst, size_t *dst_len);
diff --git a/include/linux/mailbox/exynos-message.h b/include/linux/mailbox/exynos-message.h
new file mode 100644
index 000000000000..5a9ed5ce2046
--- /dev/null
+++ b/include/linux/mailbox/exynos-message.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Exynos mailbox message.
+ *
+ * Copyright 2024 Linaro Ltd.
+ */
+
+#ifndef _LINUX_EXYNOS_MESSAGE_H_
+#define _LINUX_EXYNOS_MESSAGE_H_
+
+#define EXYNOS_MBOX_CHAN_TYPE_DOORBELL		0
+#define EXYNOS_MBOX_CHAN_TYPE_DATA		1
+
+struct exynos_mbox_msg {
+	unsigned int chan_id;
+	unsigned int chan_type;
+};
+
+#endif /* _LINUX_EXYNOS_MESSAGE_H_ */
diff --git a/include/linux/mailbox/mchp-ipc.h b/include/linux/mailbox/mchp-ipc.h
new file mode 100644
index 000000000000..f084ac9e291b
--- /dev/null
+++ b/include/linux/mailbox/mchp-ipc.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ *Copyright (c) 2024 Microchip Technology Inc. All rights reserved.
+ */
+
+#ifndef _LINUX_MCHP_IPC_H_
+#define _LINUX_MCHP_IPC_H_
+
+#include <linux/mailbox_controller.h>
+#include <linux/types.h>
+
+struct mchp_ipc_msg {
+	u32 *buf;
+	u16 size;
+};
+
+struct mchp_ipc_sbi_chan {
+	void *buf_base_tx;
+	void *buf_base_rx;
+	void *msg_buf_tx;
+	void *msg_buf_rx;
+	phys_addr_t buf_base_tx_addr;
+	phys_addr_t buf_base_rx_addr;
+	phys_addr_t msg_buf_tx_addr;
+	phys_addr_t msg_buf_rx_addr;
+	int chan_aggregated_irq;
+	int mp_irq;
+	int mc_irq;
+	u32 id;
+	u32 max_msg_size;
+};
+
+#endif /* _LINUX_MCHP_IPC_H_ */
diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h
index a8f0070c7aa9..e1555e06e7e5 100644
--- a/include/linux/mailbox/mtk-cmdq-mailbox.h
+++ b/include/linux/mailbox/mtk-cmdq-mailbox.h
@@ -75,9 +75,18 @@ struct cmdq_pkt {
 	dma_addr_t		pa_base;
 	size_t			cmd_buf_size; /* command occupied size */
 	size_t			buf_size; /* real buffer size */
-	void			*cl;
 };
 
+/**
+ * cmdq_get_shift_pa() - get the shift bits of physical address
+ * @chan: mailbox channel
+ *
+ * GCE can only fetch the command buffer address from a 32-bit register.
+ * Some SOCs support more than 32-bit command buffer address for GCE, which
+ * requires some shift bits to make the address fit into the 32-bit register.
+ *
+ * Return: the shift bits of physical address
+ */
 u8 cmdq_get_shift_pa(struct mbox_chan *chan);
 
 #endif /* __MTK_CMDQ_MAILBOX_H__ */
diff --git a/include/linux/mailbox/riscv-rpmi-message.h b/include/linux/mailbox/riscv-rpmi-message.h
new file mode 100644
index 000000000000..e135c6564d0c
--- /dev/null
+++ b/include/linux/mailbox/riscv-rpmi-message.h
@@ -0,0 +1,243 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Ventana Micro Systems Inc. */
+
+#ifndef _LINUX_RISCV_RPMI_MESSAGE_H_
+#define _LINUX_RISCV_RPMI_MESSAGE_H_
+
+#include <linux/errno.h>
+#include <linux/mailbox_client.h>
+#include <linux/types.h>
+#include <linux/wordpart.h>
+
+/* RPMI version encode/decode macros */
+#define RPMI_VER_MAJOR(__ver)		upper_16_bits(__ver)
+#define RPMI_VER_MINOR(__ver)		lower_16_bits(__ver)
+#define RPMI_MKVER(__maj, __min)	(((u32)(__maj) << 16) | (u16)(__min))
+
+/* RPMI message header */
+struct rpmi_message_header {
+	__le16 servicegroup_id;
+	u8 service_id;
+	u8 flags;
+	__le16 datalen;
+	__le16 token;
+};
+
+/* RPMI message */
+struct rpmi_message {
+	struct rpmi_message_header header;
+	u8 data[];
+};
+
+/* RPMI notification event */
+struct rpmi_notification_event {
+	__le16 event_datalen;
+	u8 event_id;
+	u8 reserved;
+	u8 event_data[];
+};
+
+/* RPMI error codes */
+enum rpmi_error_codes {
+	RPMI_SUCCESS			= 0,
+	RPMI_ERR_FAILED			= -1,
+	RPMI_ERR_NOTSUPP		= -2,
+	RPMI_ERR_INVALID_PARAM		= -3,
+	RPMI_ERR_DENIED			= -4,
+	RPMI_ERR_INVALID_ADDR		= -5,
+	RPMI_ERR_ALREADY		= -6,
+	RPMI_ERR_EXTENSION		= -7,
+	RPMI_ERR_HW_FAULT		= -8,
+	RPMI_ERR_BUSY			= -9,
+	RPMI_ERR_INVALID_STATE		= -10,
+	RPMI_ERR_BAD_RANGE		= -11,
+	RPMI_ERR_TIMEOUT		= -12,
+	RPMI_ERR_IO			= -13,
+	RPMI_ERR_NO_DATA		= -14,
+	RPMI_ERR_RESERVED_START		= -15,
+	RPMI_ERR_RESERVED_END		= -127,
+	RPMI_ERR_VENDOR_START		= -128,
+};
+
+static inline int rpmi_to_linux_error(int rpmi_error)
+{
+	switch (rpmi_error) {
+	case RPMI_SUCCESS:
+		return 0;
+	case RPMI_ERR_INVALID_PARAM:
+	case RPMI_ERR_BAD_RANGE:
+	case RPMI_ERR_INVALID_STATE:
+		return -EINVAL;
+	case RPMI_ERR_DENIED:
+		return -EPERM;
+	case RPMI_ERR_INVALID_ADDR:
+	case RPMI_ERR_HW_FAULT:
+		return -EFAULT;
+	case RPMI_ERR_ALREADY:
+		return -EALREADY;
+	case RPMI_ERR_BUSY:
+		return -EBUSY;
+	case RPMI_ERR_TIMEOUT:
+		return -ETIMEDOUT;
+	case RPMI_ERR_IO:
+		return -ECOMM;
+	case RPMI_ERR_FAILED:
+	case RPMI_ERR_NOTSUPP:
+	case RPMI_ERR_NO_DATA:
+	case RPMI_ERR_EXTENSION:
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+/* RPMI service group IDs */
+#define RPMI_SRVGRP_SYSTEM_MSI		0x00002
+#define RPMI_SRVGRP_CLOCK		0x00008
+
+/* RPMI clock service IDs */
+enum rpmi_clock_service_id {
+	RPMI_CLK_SRV_ENABLE_NOTIFICATION = 0x01,
+	RPMI_CLK_SRV_GET_NUM_CLOCKS = 0x02,
+	RPMI_CLK_SRV_GET_ATTRIBUTES = 0x03,
+	RPMI_CLK_SRV_GET_SUPPORTED_RATES = 0x04,
+	RPMI_CLK_SRV_SET_CONFIG = 0x05,
+	RPMI_CLK_SRV_GET_CONFIG = 0x06,
+	RPMI_CLK_SRV_SET_RATE = 0x07,
+	RPMI_CLK_SRV_GET_RATE = 0x08,
+	RPMI_CLK_SRV_ID_MAX_COUNT
+};
+
+/* RPMI system MSI service IDs */
+enum rpmi_sysmsi_service_id {
+	RPMI_SYSMSI_SRV_ENABLE_NOTIFICATION = 0x01,
+	RPMI_SYSMSI_SRV_GET_ATTRIBUTES = 0x02,
+	RPMI_SYSMSI_SRV_GET_MSI_ATTRIBUTES = 0x03,
+	RPMI_SYSMSI_SRV_SET_MSI_STATE = 0x04,
+	RPMI_SYSMSI_SRV_GET_MSI_STATE = 0x05,
+	RPMI_SYSMSI_SRV_SET_MSI_TARGET = 0x06,
+	RPMI_SYSMSI_SRV_GET_MSI_TARGET = 0x07,
+	RPMI_SYSMSI_SRV_ID_MAX_COUNT
+};
+
+/* RPMI Linux mailbox attribute IDs */
+enum rpmi_mbox_attribute_id {
+	RPMI_MBOX_ATTR_SPEC_VERSION,
+	RPMI_MBOX_ATTR_MAX_MSG_DATA_SIZE,
+	RPMI_MBOX_ATTR_SERVICEGROUP_ID,
+	RPMI_MBOX_ATTR_SERVICEGROUP_VERSION,
+	RPMI_MBOX_ATTR_IMPL_ID,
+	RPMI_MBOX_ATTR_IMPL_VERSION,
+	RPMI_MBOX_ATTR_MAX_ID
+};
+
+/* RPMI Linux mailbox message types */
+enum rpmi_mbox_message_type {
+	RPMI_MBOX_MSG_TYPE_GET_ATTRIBUTE,
+	RPMI_MBOX_MSG_TYPE_SET_ATTRIBUTE,
+	RPMI_MBOX_MSG_TYPE_SEND_WITH_RESPONSE,
+	RPMI_MBOX_MSG_TYPE_SEND_WITHOUT_RESPONSE,
+	RPMI_MBOX_MSG_TYPE_NOTIFICATION_EVENT,
+	RPMI_MBOX_MSG_MAX_TYPE
+};
+
+/* RPMI Linux mailbox message instance */
+struct rpmi_mbox_message {
+	enum rpmi_mbox_message_type type;
+	union {
+		struct {
+			enum rpmi_mbox_attribute_id id;
+			u32 value;
+		} attr;
+
+		struct {
+			u32 service_id;
+			void *request;
+			unsigned long request_len;
+			void *response;
+			unsigned long max_response_len;
+			unsigned long out_response_len;
+		} data;
+
+		struct {
+			u16 event_datalen;
+			u8 event_id;
+			u8 *event_data;
+		} notif;
+	};
+	int error;
+};
+
+/* RPMI Linux mailbox message helper routines */
+static inline void rpmi_mbox_init_get_attribute(struct rpmi_mbox_message *msg,
+						enum rpmi_mbox_attribute_id id)
+{
+	msg->type = RPMI_MBOX_MSG_TYPE_GET_ATTRIBUTE;
+	msg->attr.id = id;
+	msg->attr.value = 0;
+	msg->error = 0;
+}
+
+static inline void rpmi_mbox_init_set_attribute(struct rpmi_mbox_message *msg,
+						enum rpmi_mbox_attribute_id id,
+						u32 value)
+{
+	msg->type = RPMI_MBOX_MSG_TYPE_SET_ATTRIBUTE;
+	msg->attr.id = id;
+	msg->attr.value = value;
+	msg->error = 0;
+}
+
+static inline void rpmi_mbox_init_send_with_response(struct rpmi_mbox_message *msg,
+						     u32 service_id,
+						     void *request,
+						     unsigned long request_len,
+						     void *response,
+						     unsigned long max_response_len)
+{
+	msg->type = RPMI_MBOX_MSG_TYPE_SEND_WITH_RESPONSE;
+	msg->data.service_id = service_id;
+	msg->data.request = request;
+	msg->data.request_len = request_len;
+	msg->data.response = response;
+	msg->data.max_response_len = max_response_len;
+	msg->data.out_response_len = 0;
+	msg->error = 0;
+}
+
+static inline void rpmi_mbox_init_send_without_response(struct rpmi_mbox_message *msg,
+							u32 service_id,
+							void *request,
+							unsigned long request_len)
+{
+	msg->type = RPMI_MBOX_MSG_TYPE_SEND_WITHOUT_RESPONSE;
+	msg->data.service_id = service_id;
+	msg->data.request = request;
+	msg->data.request_len = request_len;
+	msg->data.response = NULL;
+	msg->data.max_response_len = 0;
+	msg->data.out_response_len = 0;
+	msg->error = 0;
+}
+
+static inline void *rpmi_mbox_get_msg_response(struct rpmi_mbox_message *msg)
+{
+	return msg ? msg->data.response : NULL;
+}
+
+static inline int rpmi_mbox_send_message(struct mbox_chan *chan,
+					 struct rpmi_mbox_message *msg)
+{
+	int ret;
+
+	/* Send message for the underlying mailbox channel */
+	ret = mbox_send_message(chan, msg);
+	if (ret < 0)
+		return ret;
+
+	/* Explicitly signal txdone for mailbox channel */
+	ret = msg->error;
+	mbox_client_txdone(chan, ret);
+	return ret;
+}
+
+#endif /* _LINUX_RISCV_RPMI_MESSAGE_H_ */
diff --git a/include/linux/mailbox_client.h b/include/linux/mailbox_client.h
index 734694912ef7..c6eea9afb943 100644
--- a/include/linux/mailbox_client.h
+++ b/include/linux/mailbox_client.h
@@ -7,8 +7,8 @@
 #ifndef __MAILBOX_CLIENT_H
 #define __MAILBOX_CLIENT_H
 
-#include <linux/of.h>
 #include <linux/device.h>
+#include <linux/of.h>
 
 struct mbox_chan;
 
diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h
index 6fee33cb52f5..80a427c7ca29 100644
--- a/include/linux/mailbox_controller.h
+++ b/include/linux/mailbox_controller.h
@@ -3,11 +3,11 @@
 #ifndef __MAILBOX_CONTROLLER_H
 #define __MAILBOX_CONTROLLER_H
 
+#include <linux/completion.h>
+#include <linux/device.h>
+#include <linux/hrtimer.h>
 #include <linux/of.h>
 #include <linux/types.h>
-#include <linux/hrtimer.h>
-#include <linux/device.h>
-#include <linux/completion.h>
 
 struct mbox_chan;
 
@@ -66,6 +66,7 @@ struct mbox_chan_ops {
  *			no interrupt rises. Ignored if 'txdone_irq' is set.
  * @txpoll_period:	If 'txdone_poll' is in effect, the API polls for
  *			last TX's status after these many millisecs
+ * @fw_xlate:		Controller driver specific mapping of channel via fwnode
  * @of_xlate:		Controller driver specific mapping of channel via DT
  * @poll_hrt:		API private. hrtimer used to poll for TXDONE on all
  *			channels.
@@ -79,6 +80,8 @@ struct mbox_controller {
 	bool txdone_irq;
 	bool txdone_poll;
 	unsigned txpoll_period;
+	struct mbox_chan *(*fw_xlate)(struct mbox_controller *mbox,
+				      const struct fwnode_reference_args *sp);
 	struct mbox_chan *(*of_xlate)(struct mbox_controller *mbox,
 				      const struct of_phandle_args *sp);
 	/* Internal to API */
@@ -134,7 +137,4 @@ void mbox_chan_txdone(struct mbox_chan *chan, int r); /* atomic */
 
 int devm_mbox_controller_register(struct device *dev,
 				  struct mbox_controller *mbox);
-void devm_mbox_controller_unregister(struct device *dev,
-				     struct mbox_controller *mbox);
-
 #endif /* __MAILBOX_CONTROLLER_H */
diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h
deleted file mode 100644
index 62674c83bde4..000000000000
--- a/include/linux/map_benchmark.h
+++ /dev/null
@@ -1,31 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (C) 2022 HiSilicon Limited.
- */
-
-#ifndef _KERNEL_DMA_BENCHMARK_H
-#define _KERNEL_DMA_BENCHMARK_H
-
-#define DMA_MAP_BENCHMARK       _IOWR('d', 1, struct map_benchmark)
-#define DMA_MAP_MAX_THREADS     1024
-#define DMA_MAP_MAX_SECONDS     300
-#define DMA_MAP_MAX_TRANS_DELAY (10 * NSEC_PER_MSEC)
-
-#define DMA_MAP_BIDIRECTIONAL   0
-#define DMA_MAP_TO_DEVICE       1
-#define DMA_MAP_FROM_DEVICE     2
-
-struct map_benchmark {
-	__u64 avg_map_100ns; /* average map latency in 100ns */
-	__u64 map_stddev; /* standard deviation of map latency */
-	__u64 avg_unmap_100ns; /* as above */
-	__u64 unmap_stddev;
-	__u32 threads; /* how many threads will do map/unmap in parallel */
-	__u32 seconds; /* how long the test will last */
-	__s32 node; /* which numa node this benchmark will run on */
-	__u32 dma_bits; /* DMA addressing capability */
-	__u32 dma_dir; /* DMA data direction */
-	__u32 dma_trans_ns; /* time for DMA transmission in ns */
-	__u32 granule;  /* how many PAGE_SIZE will do map/unmap once a time */
-};
-#endif /* _KERNEL_DMA_BENCHMARK_H */
diff --git a/include/linux/maple.h b/include/linux/maple.h
index 9b140272ee16..3be4e567473c 100644
--- a/include/linux/maple.h
+++ b/include/linux/maple.h
@@ -5,7 +5,6 @@
 #include <mach/maple.h>
 
 struct device;
-extern struct bus_type maple_bus_type;
 
 /* Maple Bus command and response codes */
 enum maple_code {
@@ -98,7 +97,7 @@ int maple_add_packet(struct maple_device *mdev, u32 function,
 void maple_clear_dev(struct maple_device *mdev);
 
 #define to_maple_dev(n) container_of(n, struct maple_device, dev)
-#define to_maple_driver(n) container_of(n, struct maple_driver, drv)
+#define to_maple_driver(n) container_of_const(n, struct maple_driver, drv)
 
 #define maple_get_drvdata(d)		dev_get_drvdata(&(d)->dev)
 #define maple_set_drvdata(d,p)		dev_set_drvdata(&(d)->dev, (p))
diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index 295548cca8b3..66f98a3da8d8 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -29,14 +29,12 @@
 #define MAPLE_NODE_SLOTS	31	/* 256 bytes including ->parent */
 #define MAPLE_RANGE64_SLOTS	16	/* 256 bytes */
 #define MAPLE_ARANGE64_SLOTS	10	/* 240 bytes */
-#define MAPLE_ARANGE64_META_MAX	15	/* Out of range for metadata */
 #define MAPLE_ALLOC_SLOTS	(MAPLE_NODE_SLOTS - 1)
 #else
 /* 32bit sizes */
 #define MAPLE_NODE_SLOTS	63	/* 256 bytes including ->parent */
 #define MAPLE_RANGE64_SLOTS	32	/* 256 bytes */
 #define MAPLE_ARANGE64_SLOTS	21	/* 240 bytes */
-#define MAPLE_ARANGE64_META_MAX	31	/* Out of range for metadata */
 #define MAPLE_ALLOC_SLOTS	(MAPLE_NODE_SLOTS - 2)
 #endif /* defined(CONFIG_64BIT) || defined(BUILD_VDSO32_64) */
 
@@ -54,22 +52,22 @@
  * bit in the node type.  This is possible by using bit 1 to indicate if bit 2
  * is part of the type or the slot.
  *
- * Once the type is decided, the decision of an allocation range type or a range
- * type is done by examining the immutable tree flag for the MAPLE_ALLOC_RANGE
- * flag.
+ * Once the type is decided, the decision of an allocation range type or a
+ * range type is done by examining the immutable tree flag for the
+ * MT_FLAGS_ALLOC_RANGE flag.
  *
  *  Node types:
- *   0x??1 = Root
- *   0x?00 = 16 bit nodes
- *   0x010 = 32 bit nodes
- *   0x110 = 64 bit nodes
+ *   0b??1 = Root
+ *   0b?00 = 16 bit nodes
+ *   0b010 = 32 bit nodes
+ *   0b110 = 64 bit nodes
  *
  *  Slot size and location in the parent pointer:
  *   type  : slot location
- *   0x??1 : Root
- *   0x?00 : 16 bit values, type in 0-1, slot in 2-6
- *   0x010 : 32 bit values, type in 0-2, slot in 3-6
- *   0x110 : 64 bit values, type in 0-2, slot in 3-6
+ *   0b??1 : Root
+ *   0b?00 : 16 bit values, type in 0-1, slot in 2-6
+ *   0b010 : 32 bit values, type in 0-2, slot in 3-6
+ *   0b110 : 64 bit values, type in 0-2, slot in 3-6
  */
 
 /*
@@ -77,8 +75,8 @@
  * searching for gaps or any other code that needs to find the end of the data.
  */
 struct maple_metadata {
-	unsigned char end;
-	unsigned char gap;
+	unsigned char end;	/* end of data */
+	unsigned char gap;	/* offset of largest gap */
 };
 
 /*
@@ -150,6 +148,18 @@ enum maple_type {
 	maple_arange_64,
 };
 
+enum store_type {
+	wr_invalid,
+	wr_new_root,
+	wr_store_root,
+	wr_exact_fit,
+	wr_spanning_store,
+	wr_split_store,
+	wr_rebalance,
+	wr_append,
+	wr_node_store,
+	wr_slot_store,
+};
 
 /**
  * DOC: Maple tree flags
@@ -173,6 +183,7 @@ enum maple_type {
 #define MT_FLAGS_LOCK_IRQ	0x100
 #define MT_FLAGS_LOCK_BH	0x200
 #define MT_FLAGS_LOCK_EXTERN	0x300
+#define MT_FLAGS_ALLOC_WRAPPED	0x0800
 
 #define MAPLE_HEIGHT_MAX	31
 
@@ -183,14 +194,22 @@ enum maple_type {
 #define MAPLE_RESERVED_RANGE	4096
 
 #ifdef CONFIG_LOCKDEP
-typedef struct lockdep_map *lockdep_map_p;
-#define mt_lock_is_held(mt)	lock_is_held(mt->ma_external_lock)
+#define mt_lock_is_held(mt)                                             \
+	(!(mt)->ma_external_lock || lock_is_held((mt)->ma_external_lock))
+
+#define mt_write_lock_is_held(mt)					\
+	(!(mt)->ma_external_lock ||					\
+	 lock_is_held_type((mt)->ma_external_lock, 0))
+
 #define mt_set_external_lock(mt, lock)					\
 	(mt)->ma_external_lock = &(lock)->dep_map
+
+#define mt_on_stack(mt)			(mt).ma_external_lock = NULL
 #else
-typedef struct { /* nothing */ } lockdep_map_p;
-#define mt_lock_is_held(mt)	1
+#define mt_lock_is_held(mt)		1
+#define mt_write_lock_is_held(mt)	1
 #define mt_set_external_lock(mt, lock)	do { } while (0)
+#define mt_on_stack(mt)			do { } while (0)
 #endif
 
 /*
@@ -203,17 +222,19 @@ typedef struct { /* nothing */ } lockdep_map_p;
  * (set at tree creation time) and dynamic information set under the spinlock.
  *
  * Another use of flags are to indicate global states of the tree.  This is the
- * case with the MAPLE_USE_RCU flag, which indicates the tree is currently in
+ * case with the MT_FLAGS_USE_RCU flag, which indicates the tree is currently in
  * RCU mode.  This mode was added to allow the tree to reuse nodes instead of
  * re-allocating and RCU freeing nodes when there is a single user.
  */
 struct maple_tree {
 	union {
-		spinlock_t	ma_lock;
-		lockdep_map_p	ma_external_lock;
+		spinlock_t		ma_lock;
+#ifdef CONFIG_LOCKDEP
+		struct lockdep_map	*ma_external_lock;
+#endif
 	};
-	void __rcu      *ma_root;
 	unsigned int	ma_flags;
+	void __rcu      *ma_root;
 };
 
 /**
@@ -248,6 +269,8 @@ struct maple_tree {
 	struct maple_tree name = MTREE_INIT(name, 0)
 
 #define mtree_lock(mt)		spin_lock((&(mt)->ma_lock))
+#define mtree_lock_nested(mas, subclass) \
+		spin_lock_nested((&(mt)->ma_lock), subclass)
 #define mtree_unlock(mt)	spin_unlock((&(mt)->ma_lock))
 
 /*
@@ -309,6 +332,9 @@ int mtree_insert_range(struct maple_tree *mt, unsigned long first,
 int mtree_alloc_range(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp);
+int mtree_alloc_cyclic(struct maple_tree *mt, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp);
 int mtree_alloc_rrange(struct maple_tree *mt, unsigned long *startp,
 		void *entry, unsigned long size, unsigned long min,
 		unsigned long max, gfp_t gfp);
@@ -319,6 +345,9 @@ int mtree_store(struct maple_tree *mt, unsigned long index,
 		void *entry, gfp_t gfp);
 void *mtree_erase(struct maple_tree *mt, unsigned long index);
 
+int mtree_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
+int __mt_dup(struct maple_tree *mt, struct maple_tree *new, gfp_t gfp);
+
 void mtree_destroy(struct maple_tree *mt);
 void __mt_destroy(struct maple_tree *mt);
 
@@ -337,6 +366,36 @@ static inline bool mtree_empty(const struct maple_tree *mt)
 /* Advanced API */
 
 /*
+ * Maple State Status
+ * ma_active means the maple state is pointing to a node and offset and can
+ * continue operating on the tree.
+ * ma_start means we have not searched the tree.
+ * ma_root means we have searched the tree and the entry we found lives in
+ * the root of the tree (ie it has index 0, length 1 and is the only entry in
+ * the tree).
+ * ma_none means we have searched the tree and there is no node in the
+ * tree for this entry.  For example, we searched for index 1 in an empty
+ * tree.  Or we have a tree which points to a full leaf node and we
+ * searched for an entry which is larger than can be contained in that
+ * leaf node.
+ * ma_pause means the data within the maple state may be stale, restart the
+ * operation
+ * ma_overflow means the search has reached the upper limit of the search
+ * ma_underflow means the search has reached the lower limit of the search
+ * ma_error means there was an error, check the node for the error number.
+ */
+enum maple_status {
+	ma_active,
+	ma_start,
+	ma_root,
+	ma_none,
+	ma_pause,
+	ma_overflow,
+	ma_underflow,
+	ma_error,
+};
+
+/*
  * The maple state is defined in the struct ma_state and is used to keep track
  * of information during operations, and even between operations when using the
  * advanced API.
@@ -368,6 +427,13 @@ static inline bool mtree_empty(const struct maple_tree *mt)
  * When returning a value the maple state index and last respectively contain
  * the start and end of the range for the entry.  Ranges are inclusive in the
  * Maple Tree.
+ *
+ * The status of the state is used to determine how the next action should treat
+ * the state.  For instance, if the status is ma_start then the next action
+ * should start at the root of the tree and walk down.  If the status is
+ * ma_pause then the node may be stale data and should be discarded.  If the
+ * status is ma_overflow, then the last action hit the upper limit.
+ *
  */
 struct ma_state {
 	struct maple_tree *tree;	/* The tree we're operating in */
@@ -376,10 +442,15 @@ struct ma_state {
 	struct maple_enode *node;	/* The node containing this entry */
 	unsigned long min;		/* The minimum index of this node - implied pivot min */
 	unsigned long max;		/* The maximum index of this node - implied pivot max */
-	struct maple_alloc *alloc;	/* Allocated nodes for this operation */
+	struct slab_sheaf *sheaf;	/* Allocated nodes for this operation */
+	struct maple_node *alloc;	/* A single allocated node for fast path writes */
+	unsigned long node_request;	/* The number of nodes to allocate for this operation */
+	enum maple_status status;	/* The status of the state (active, start, none, etc) */
 	unsigned char depth;		/* depth of tree descent during write */
 	unsigned char offset;
 	unsigned char mas_flags;
+	unsigned char end;		/* The end of the node */
+	enum store_type store_type;	/* The type of store needed for this operation */
 };
 
 struct ma_wr_state {
@@ -389,50 +460,46 @@ struct ma_wr_state {
 	unsigned long r_max;		/* range max */
 	enum maple_type type;		/* mas->node type */
 	unsigned char offset_end;	/* The offset where the write ends */
-	unsigned char node_end;		/* mas->node end */
 	unsigned long *pivots;		/* mas->node->pivots pointer */
 	unsigned long end_piv;		/* The pivot at the offset end */
 	void __rcu **slots;		/* mas->node->slots pointer */
 	void *entry;			/* The entry to write */
 	void *content;			/* The existing entry that is being overwritten */
+	unsigned char vacant_height;	/* Height of lowest node with free space */
+	unsigned char sufficient_height;/* Height of lowest node with min sufficiency + 1 nodes */
 };
 
 #define mas_lock(mas)           spin_lock(&((mas)->tree->ma_lock))
+#define mas_lock_nested(mas, subclass) \
+		spin_lock_nested(&((mas)->tree->ma_lock), subclass)
 #define mas_unlock(mas)         spin_unlock(&((mas)->tree->ma_lock))
 
-
 /*
  * Special values for ma_state.node.
- * MAS_START means we have not searched the tree.
- * MAS_ROOT means we have searched the tree and the entry we found lives in
- * the root of the tree (ie it has index 0, length 1 and is the only entry in
- * the tree).
- * MAS_NONE means we have searched the tree and there is no node in the
- * tree for this entry.  For example, we searched for index 1 in an empty
- * tree.  Or we have a tree which points to a full leaf node and we
- * searched for an entry which is larger than can be contained in that
- * leaf node.
  * MA_ERROR represents an errno.  After dropping the lock and attempting
  * to resolve the error, the walk would have to be restarted from the
  * top of the tree as the tree may have been modified.
  */
-#define MAS_START	((struct maple_enode *)1UL)
-#define MAS_ROOT	((struct maple_enode *)5UL)
-#define MAS_NONE	((struct maple_enode *)9UL)
-#define MAS_PAUSE	((struct maple_enode *)17UL)
 #define MA_ERROR(err) \
 		((struct maple_enode *)(((unsigned long)err << 2) | 2UL))
 
+/*
+ * When changing MA_STATE, remember to also change rust/kernel/maple_tree.rs
+ */
 #define MA_STATE(name, mt, first, end)					\
 	struct ma_state name = {					\
 		.tree = mt,						\
 		.index = first,						\
 		.last = end,						\
-		.node = MAS_START,					\
+		.node = NULL,						\
+		.status = ma_start,					\
 		.min = 0,						\
 		.max = ULONG_MAX,					\
+		.sheaf = NULL,						\
 		.alloc = NULL,						\
+		.node_request = 0,					\
 		.mas_flags = 0,						\
+		.store_type = wr_invalid,				\
 	}
 
 #define MA_WR_STATE(name, ma_state, wr_entry)				\
@@ -440,6 +507,8 @@ struct ma_wr_state {
 		.mas = ma_state,					\
 		.content = NULL,					\
 		.entry = wr_entry,					\
+		.vacant_height = 0,					\
+		.sufficient_height = 0					\
 	}
 
 #define MA_TOPIARY(name, tree)						\
@@ -458,8 +527,10 @@ void *mas_find(struct ma_state *mas, unsigned long max);
 void *mas_find_range(struct ma_state *mas, unsigned long max);
 void *mas_find_rev(struct ma_state *mas, unsigned long min);
 void *mas_find_range_rev(struct ma_state *mas, unsigned long max);
-int mas_preallocate(struct ma_state *mas, gfp_t gfp);
-bool mas_is_err(struct ma_state *mas);
+int mas_preallocate(struct ma_state *mas, void *entry, gfp_t gfp);
+int mas_alloc_cyclic(struct ma_state *mas, unsigned long *startp,
+		void *entry, unsigned long range_lo, unsigned long range_hi,
+		unsigned long *next, gfp_t gfp);
 
 bool mas_nomem(struct ma_state *mas, gfp_t gfp);
 void mas_pause(struct ma_state *mas);
@@ -488,19 +559,18 @@ static inline void mas_init(struct ma_state *mas, struct maple_tree *tree,
 	mas->tree = tree;
 	mas->index = mas->last = addr;
 	mas->max = ULONG_MAX;
-	mas->node = MAS_START;
+	mas->status = ma_start;
+	mas->node = NULL;
 }
 
-/* Checks if a mas has not found anything */
-static inline bool mas_is_none(const struct ma_state *mas)
+static inline bool mas_is_active(struct ma_state *mas)
 {
-	return mas->node == MAS_NONE;
+	return mas->status == ma_active;
 }
 
-/* Checks if a mas has been paused */
-static inline bool mas_is_paused(const struct ma_state *mas)
+static inline bool mas_is_err(struct ma_state *mas)
 {
-	return mas->node == MAS_PAUSE;
+	return mas->status == ma_error;
 }
 
 /**
@@ -513,9 +583,10 @@ static inline bool mas_is_paused(const struct ma_state *mas)
  *
  * Context: Any context.
  */
-static inline void mas_reset(struct ma_state *mas)
+static __always_inline void mas_reset(struct ma_state *mas)
 {
-	mas->node = MAS_START;
+	mas->status = ma_start;
+	mas->node = NULL;
 }
 
 /**
@@ -533,6 +604,164 @@ static inline void mas_reset(struct ma_state *mas)
 	while (((__entry) = mas_find((__mas), (__max))) != NULL)
 
 /**
+ * mas_for_each_rev() - Iterate over a range of the maple tree in reverse order.
+ * @__mas: Maple Tree operation state (maple_state)
+ * @__entry: Entry retrieved from the tree
+ * @__min: minimum index to retrieve from the tree
+ *
+ * When returned, mas->index and mas->last will hold the entire range for the
+ * entry.
+ *
+ * Note: may return the zero entry.
+ */
+#define mas_for_each_rev(__mas, __entry, __min) \
+	while (((__entry) = mas_find_rev((__mas), (__min))) != NULL)
+
+#ifdef CONFIG_DEBUG_MAPLE_TREE
+enum mt_dump_format {
+	mt_dump_dec,
+	mt_dump_hex,
+};
+
+extern atomic_t maple_tree_tests_run;
+extern atomic_t maple_tree_tests_passed;
+
+void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
+void mas_dump(const struct ma_state *mas);
+void mas_wr_dump(const struct ma_wr_state *wr_mas);
+void mt_validate(struct maple_tree *mt);
+void mt_cache_shrink(void);
+#define MT_BUG_ON(__tree, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_BUG_ON(__mas, __x) do {					\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MAS_WR_BUG_ON(__wrmas, __x) do {				\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (__x) {							\
+		pr_info("BUG at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_wr_dump(__wrmas);					\
+		mas_dump((__wrmas)->mas);				\
+		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+} while (0)
+
+#define MT_WARN_ON(__tree, __x)  ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mt_dump(__tree, mt_dump_hex);				\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+
+#define MAS_WARN_ON(__mas, __x) ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_dump(__mas);					\
+		mt_dump((__mas)->tree, mt_dump_hex);			\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+
+#define MAS_WR_WARN_ON(__wrmas, __x) ({					\
+	int ret = !!(__x);						\
+	atomic_inc(&maple_tree_tests_run);				\
+	if (ret) {							\
+		pr_info("WARN at %s:%d (%u)\n",				\
+		__func__, __LINE__, __x);				\
+		mas_wr_dump(__wrmas);					\
+		mas_dump((__wrmas)->mas);				\
+		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
+		pr_info("Pass: %u Run:%u\n",				\
+			atomic_read(&maple_tree_tests_passed),		\
+			atomic_read(&maple_tree_tests_run));		\
+		dump_stack();						\
+	} else {							\
+		atomic_inc(&maple_tree_tests_passed);			\
+	}								\
+	unlikely(ret);							\
+})
+#else
+#define MT_BUG_ON(__tree, __x)		BUG_ON(__x)
+#define MAS_BUG_ON(__mas, __x)		BUG_ON(__x)
+#define MAS_WR_BUG_ON(__mas, __x)	BUG_ON(__x)
+#define MT_WARN_ON(__tree, __x)		WARN_ON(__x)
+#define MAS_WARN_ON(__mas, __x)		WARN_ON(__x)
+#define MAS_WR_WARN_ON(__mas, __x)	WARN_ON(__x)
+#endif /* CONFIG_DEBUG_MAPLE_TREE */
+
+/**
+ * __mas_set_range() - Set up Maple Tree operation state to a sub-range of the
+ * current location.
+ * @mas: Maple Tree operation state.
+ * @start: New start of range in the Maple Tree.
+ * @last: New end of range in the Maple Tree.
+ *
+ * set the internal maple state values to a sub-range.
+ * Please use mas_set_range() if you do not know where you are in the tree.
+ */
+static inline void __mas_set_range(struct ma_state *mas, unsigned long start,
+		unsigned long last)
+{
+	/* Ensure the range starts within the current slot */
+	MAS_WARN_ON(mas, mas_is_active(mas) &&
+		   (mas->index > start || mas->last < start));
+	mas->index = start;
+	mas->last = last;
+}
+
+/**
  * mas_set_range() - Set up Maple Tree operation state for a different index.
  * @mas: Maple Tree operation state.
  * @start: New start of range in the Maple Tree.
@@ -545,9 +774,8 @@ static inline void mas_reset(struct ma_state *mas)
 static inline
 void mas_set_range(struct ma_state *mas, unsigned long start, unsigned long last)
 {
-	       mas->index = start;
-	       mas->last = last;
-	       mas->node = MAS_START;
+	mas_reset(mas);
+	__mas_set_range(mas, start, last);
 }
 
 /**
@@ -662,138 +890,14 @@ void *mt_next(struct maple_tree *mt, unsigned long index, unsigned long max);
  * mt_for_each - Iterate over each entry starting at index until max.
  * @__tree: The Maple Tree
  * @__entry: The current entry
- * @__index: The index to update to track the location in the tree
+ * @__index: The index to start the search from. Subsequently used as iterator.
  * @__max: The maximum limit for @index
  *
- * Note: Will not return the zero entry.
+ * This iterator skips all entries, which resolve to a NULL pointer,
+ * e.g. entries which has been reserved with XA_ZERO_ENTRY.
  */
 #define mt_for_each(__tree, __entry, __index, __max) \
 	for (__entry = mt_find(__tree, &(__index), __max); \
 		__entry; __entry = mt_find_after(__tree, &(__index), __max))
 
-
-#ifdef CONFIG_DEBUG_MAPLE_TREE
-enum mt_dump_format {
-	mt_dump_dec,
-	mt_dump_hex,
-};
-
-extern atomic_t maple_tree_tests_run;
-extern atomic_t maple_tree_tests_passed;
-
-void mt_dump(const struct maple_tree *mt, enum mt_dump_format format);
-void mas_dump(const struct ma_state *mas);
-void mas_wr_dump(const struct ma_wr_state *wr_mas);
-void mt_validate(struct maple_tree *mt);
-void mt_cache_shrink(void);
-#define MT_BUG_ON(__tree, __x) do {					\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mt_dump(__tree, mt_dump_hex);				\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MAS_BUG_ON(__mas, __x) do {					\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_dump(__mas);					\
-		mt_dump((__mas)->tree, mt_dump_hex);			\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MAS_WR_BUG_ON(__wrmas, __x) do {				\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (__x) {							\
-		pr_info("BUG at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_wr_dump(__wrmas);					\
-		mas_dump((__wrmas)->mas);				\
-		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-} while (0)
-
-#define MT_WARN_ON(__tree, __x)  ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mt_dump(__tree, mt_dump_hex);				\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-
-#define MAS_WARN_ON(__mas, __x) ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_dump(__mas);					\
-		mt_dump((__mas)->tree, mt_dump_hex);			\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-
-#define MAS_WR_WARN_ON(__wrmas, __x) ({					\
-	int ret = !!(__x);						\
-	atomic_inc(&maple_tree_tests_run);				\
-	if (ret) {							\
-		pr_info("WARN at %s:%d (%u)\n",				\
-		__func__, __LINE__, __x);				\
-		mas_wr_dump(__wrmas);					\
-		mas_dump((__wrmas)->mas);				\
-		mt_dump((__wrmas)->mas->tree, mt_dump_hex);		\
-		pr_info("Pass: %u Run:%u\n",				\
-			atomic_read(&maple_tree_tests_passed),		\
-			atomic_read(&maple_tree_tests_run));		\
-		dump_stack();						\
-	} else {							\
-		atomic_inc(&maple_tree_tests_passed);			\
-	}								\
-	unlikely(ret);							\
-})
-#else
-#define MT_BUG_ON(__tree, __x)		BUG_ON(__x)
-#define MAS_BUG_ON(__mas, __x)		BUG_ON(__x)
-#define MAS_WR_BUG_ON(__mas, __x)	BUG_ON(__x)
-#define MT_WARN_ON(__tree, __x)		WARN_ON(__x)
-#define MAS_WARN_ON(__mas, __x)		WARN_ON(__x)
-#define MAS_WR_WARN_ON(__mas, __x)	WARN_ON(__x)
-#endif /* CONFIG_DEBUG_MAPLE_TREE */
-
 #endif /*_LINUX_MAPLE_TREE_H */
diff --git a/include/linux/marvell_phy.h b/include/linux/marvell_phy.h
index 0f06c2287b52..b1fbe4118414 100644
--- a/include/linux/marvell_phy.h
+++ b/include/linux/marvell_phy.h
@@ -7,6 +7,7 @@
 
 /* Known PHY IDs */
 #define MARVELL_PHY_ID_88E1101		0x01410c60
+#define MARVELL_PHY_ID_88E3082		0x01410c80
 #define MARVELL_PHY_ID_88E1112		0x01410c90
 #define MARVELL_PHY_ID_88E1111		0x01410cc0
 #define MARVELL_PHY_ID_88E1118		0x01410e10
@@ -25,10 +26,14 @@
 #define MARVELL_PHY_ID_88X3310		0x002b09a0
 #define MARVELL_PHY_ID_88E2110		0x002b09b0
 #define MARVELL_PHY_ID_88X2222		0x01410f10
+#define MARVELL_PHY_ID_88Q2110		0x002b0980
+#define MARVELL_PHY_ID_88Q2220		0x002b0b20
 
 /* Marvel 88E1111 in Finisar SFP module with modified PHY ID */
 #define MARVELL_PHY_ID_88E1111_FINISAR	0x01ff0cc0
 
+/* ID from 88E6020, assumed to be the same for the whole 6250 family */
+#define MARVELL_PHY_ID_88E6250_FAMILY	0x01410db0
 /* These Ethernet switch families contain embedded PHYs, but they do
  * not have a model ID. So the switch driver traps reads to the ID2
  * register and returns the switch family ID
diff --git a/include/linux/math.h b/include/linux/math.h
index 439b8f0b9ebd..6dc1d1d32fbc 100644
--- a/include/linux/math.h
+++ b/include/linux/math.h
@@ -34,6 +34,18 @@
  */
 #define round_down(x, y) ((x) & ~__round_mask(x, y))
 
+/**
+ * DIV_ROUND_UP_POW2 - divide and round up
+ * @n: numerator
+ * @d: denominator (must be a power of 2)
+ *
+ * Divides @n by @d and rounds up to next multiple of @d (which must be a power
+ * of 2). Avoids integer overflows that may occur with __KERNEL_DIV_ROUND_UP().
+ * Performance is roughly equivalent to __KERNEL_DIV_ROUND_UP().
+ */
+#define DIV_ROUND_UP_POW2(n, d) \
+	((n) / (d) + !!((n) & ((d) - 1)))
+
 #define DIV_ROUND_UP __KERNEL_DIV_ROUND_UP
 
 #define DIV_ROUND_DOWN_ULL(ll, d) \
@@ -112,33 +124,40 @@ struct type##_fract {					\
 	__##type numerator;				\
 	__##type denominator;				\
 };
+__STRUCT_FRACT(s8)
+__STRUCT_FRACT(u8)
 __STRUCT_FRACT(s16)
 __STRUCT_FRACT(u16)
 __STRUCT_FRACT(s32)
 __STRUCT_FRACT(u32)
 #undef __STRUCT_FRACT
 
-/*
- * Multiplies an integer by a fraction, while avoiding unnecessary
- * overflow or loss of precision.
- */
-#define mult_frac(x, numer, denom)(			\
-{							\
-	typeof(x) quot = (x) / (denom);			\
-	typeof(x) rem  = (x) % (denom);			\
-	(quot * (numer)) + ((rem * (numer)) / (denom));	\
-}							\
-)
+/* Calculate "x * n / d" without unnecessary overflow or loss of precision. */
+#define mult_frac(x, n, d)	\
+({				\
+	typeof(x) x_ = (x);	\
+	typeof(n) n_ = (n);	\
+	typeof(d) d_ = (d);	\
+				\
+	typeof(x_) q = x_ / d_;	\
+	typeof(x_) r = x_ % d_;	\
+	q * n_ + r * n_ / d_;	\
+})
 
 #define sector_div(a, b) do_div(a, b)
 
 /**
  * abs - return absolute value of an argument
- * @x: the value.  If it is unsigned type, it is converted to signed type first.
- *     char is treated as if it was signed (regardless of whether it really is)
- *     but the macro's return type is preserved as char.
+ * @x: the value.
+ *
+ * If it is unsigned type, @x is converted to signed type first.
+ * char is treated as if it was signed (regardless of whether it really is)
+ * but the macro's return type is preserved as char.
  *
- * Return: an absolute value of x.
+ * NOTE, for signed type if @x is the minimum, the returned result is undefined
+ * as there is not enough bits to represent it as a positive number.
+ *
+ * Return: an absolute value of @x.
  */
 #define abs(x)	__abs_choose_expr(x, long long,				\
 		__abs_choose_expr(x, long,				\
@@ -156,6 +175,25 @@ __STRUCT_FRACT(u32)
 	({ signed type __x = (x); __x < 0 ? -__x : __x; }), other)
 
 /**
+ * abs_diff - return absolute value of the difference between the arguments
+ * @a: the first argument
+ * @b: the second argument
+ *
+ * @a and @b have to be of the same type. With this restriction we compare
+ * signed to signed and unsigned to unsigned. The result is the subtraction
+ * the smaller of the two from the bigger, hence result is always a positive
+ * value.
+ *
+ * Return: an absolute value of the difference between the @a and @b.
+ */
+#define abs_diff(a, b) ({			\
+	typeof(a) __a = (a);			\
+	typeof(b) __b = (b);			\
+	(void)(&__a == &__b);			\
+	__a > __b ? (__a - __b) : (__b - __a);	\
+})
+
+/**
  * reciprocal_scale - "scale" a value into range [0, ep_ro)
  * @val: value
  * @ep_ro: right open interval endpoint
diff --git a/include/linux/math64.h b/include/linux/math64.h
index 8b9191a2849e..cc305206d89f 100644
--- a/include/linux/math64.h
+++ b/include/linux/math64.h
@@ -4,8 +4,8 @@
 
 #include <linux/types.h>
 #include <linux/math.h>
-#include <vdso/math64.h>
 #include <asm/div64.h>
+#include <vdso/math64.h>
 
 #if BITS_PER_LONG == 64
 
@@ -158,6 +158,17 @@ static inline u64 mul_u32_u32(u32 a, u32 b)
 }
 #endif
 
+#ifndef add_u64_u32
+/*
+ * Many a GCC version also messes this up.
+ * Zero extending b and then spilling everything to stack.
+ */
+static inline u64 add_u64_u32(u64 a, u32 b)
+{
+	return a + b;
+}
+#endif
+
 #if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__)
 
 #ifndef mul_u64_u32_shr
@@ -168,7 +179,7 @@ static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
 #endif /* mul_u64_u32_shr */
 
 #ifndef mul_u64_u64_shr
-static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift)
+static __always_inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift)
 {
 	return (u64)(((unsigned __int128)a * mul) >> shift);
 }
@@ -179,16 +190,12 @@ static inline u64 mul_u64_u64_shr(u64 a, u64 mul, unsigned int shift)
 #ifndef mul_u64_u32_shr
 static __always_inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift)
 {
-	u32 ah, al;
+	u32 ah = a >> 32, al = a;
 	u64 ret;
 
-	al = a;
-	ah = a >> 32;
-
 	ret = mul_u32_u32(al, mul) >> shift;
 	if (ah)
 		ret += mul_u32_u32(ah, mul) << (32 - shift);
-
 	return ret;
 }
 #endif /* mul_u64_u32_shr */
@@ -286,7 +293,53 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 }
 #endif /* mul_u64_u32_div */
 
-u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
+/**
+ * mul_u64_add_u64_div_u64 - unsigned 64bit multiply, add, and divide
+ * @a: first unsigned 64bit multiplicand
+ * @b: second unsigned 64bit multiplicand
+ * @c: unsigned 64bit addend
+ * @d: unsigned 64bit divisor
+ *
+ * Multiply two 64bit values together to generate a 128bit product
+ * add a third value and then divide by a fourth.
+ * The Generic code divides by 0 if @d is zero and returns ~0 on overflow.
+ * Architecture specific code may trap on zero or overflow.
+ *
+ * Return: (@a * @b + @c) / @d
+ */
+u64 mul_u64_add_u64_div_u64(u64 a, u64 b, u64 c, u64 d);
+
+/**
+ * mul_u64_u64_div_u64 - unsigned 64bit multiply and divide
+ * @a: first unsigned 64bit multiplicand
+ * @b: second unsigned 64bit multiplicand
+ * @d: unsigned 64bit divisor
+ *
+ * Multiply two 64bit values together to generate a 128bit product
+ * and then divide by a third value.
+ * The Generic code divides by 0 if @d is zero and returns ~0 on overflow.
+ * Architecture specific code may trap on zero or overflow.
+ *
+ * Return: @a * @b / @d
+ */
+#define mul_u64_u64_div_u64(a, b, d) mul_u64_add_u64_div_u64(a, b, 0, d)
+
+/**
+ * mul_u64_u64_div_u64_roundup - unsigned 64bit multiply and divide rounded up
+ * @a: first unsigned 64bit multiplicand
+ * @b: second unsigned 64bit multiplicand
+ * @d: unsigned 64bit divisor
+ *
+ * Multiply two 64bit values together to generate a 128bit product
+ * and then divide and round up.
+ * The Generic code divides by 0 if @d is zero and returns ~0 on overflow.
+ * Architecture specific code may trap on zero or overflow.
+ *
+ * Return: (@a * @b + @d - 1) / @d
+ */
+#define mul_u64_u64_div_u64_roundup(a, b, d) \
+	({ u64 _tmp = (d); mul_u64_add_u64_div_u64(a, b, _tmp - 1, _tmp); })
+
 
 /**
  * DIV64_U64_ROUND_UP - unsigned 64bit divide with 64bit divisor rounded up
@@ -302,6 +355,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
 	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
 
 /**
+ * DIV_U64_ROUND_UP - unsigned 64bit divide with 32bit divisor rounded up
+ * @ll: unsigned 64bit dividend
+ * @d: unsigned 32bit divisor
+ *
+ * Divide unsigned 64bit dividend by unsigned 32bit divisor
+ * and round up.
+ *
+ * Return: dividend / divisor rounded up
+ */
+#define DIV_U64_ROUND_UP(ll, d)		\
+	({ u32 _tmp = (d); div_u64((ll) + _tmp - 1, _tmp); })
+
+/**
  * DIV64_U64_ROUND_CLOSEST - unsigned 64bit divide with 64bit divisor rounded to nearest integer
  * @dividend: unsigned 64bit dividend
  * @divisor: unsigned 64bit divisor
@@ -346,4 +412,19 @@ u64 mul_u64_u64_div_u64(u64 a, u64 mul, u64 div);
 		div_s64((__x - (__d / 2)), __d);	\
 }							\
 )
+
+/**
+ * roundup_u64 - Round up a 64bit value to the next specified 32bit multiple
+ * @x: the value to up
+ * @y: 32bit multiple to round up to
+ *
+ * Rounds @x to the next multiple of @y. For 32bit @x values, see roundup and
+ * the faster round_up() for powers of 2.
+ *
+ * Return: rounded up value.
+ */
+static inline u64 roundup_u64(u64 x, u32 y)
+{
+	return DIV_U64_ROUND_UP(x, y) * y;
+}
 #endif /* _LINUX_MATH64_H */
diff --git a/include/linux/mc146818rtc.h b/include/linux/mc146818rtc.h
index b0da04fe087b..34dfcc77f505 100644
--- a/include/linux/mc146818rtc.h
+++ b/include/linux/mc146818rtc.h
@@ -126,10 +126,11 @@ struct cmos_rtc_board_info {
 #endif /* ARCH_RTC_LOCATION */
 
 bool mc146818_does_rtc_work(void);
-int mc146818_get_time(struct rtc_time *time);
+int mc146818_get_time(struct rtc_time *time, int timeout);
 int mc146818_set_time(struct rtc_time *time);
 
 bool mc146818_avoid_UIP(void (*callback)(unsigned char seconds, void *param),
+			int timeout,
 			void *param);
 
 #endif /* _MC146818RTC_H */
diff --git a/include/linux/mc33xs2410.h b/include/linux/mc33xs2410.h
new file mode 100644
index 000000000000..31c0edf10dd7
--- /dev/null
+++ b/include/linux/mc33xs2410.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Liebherr-Electronics and Drives GmbH
+ */
+#ifndef _MC33XS2410_H
+#define _MC33XS2410_H
+
+#include <linux/spi/spi.h>
+
+MODULE_IMPORT_NS("PWM_MC33XS2410");
+
+int mc33xs2410_read_reg_ctrl(struct spi_device *spi, u8 reg, u16 *val);
+int mc33xs2410_read_reg_diag(struct spi_device *spi, u8 reg, u16 *val);
+int mc33xs2410_modify_reg(struct spi_device *spi, u8 reg, u8 mask, u8 val);
+
+#endif /* _MC33XS2410_H */
diff --git a/include/linux/mcb.h b/include/linux/mcb.h
index 1e5893138afe..4ab2691f51a6 100644
--- a/include/linux/mcb.h
+++ b/include/linux/mcb.h
@@ -63,7 +63,6 @@ static inline struct mcb_bus *to_mcb_bus(struct device *dev)
 struct mcb_device {
 	struct device dev;
 	struct mcb_bus *bus;
-	bool is_added;
 	struct mcb_driver *driver;
 	u16 id;
 	int inst;
@@ -95,10 +94,7 @@ struct mcb_driver {
 	void (*shutdown)(struct mcb_device *mdev);
 };
 
-static inline struct mcb_driver *to_mcb_driver(struct device_driver *drv)
-{
-	return container_of(drv, struct mcb_driver, driver);
-}
+#define to_mcb_driver(__drv)	container_of_const(__drv, struct mcb_driver, driver)
 
 static inline void *mcb_get_drvdata(struct mcb_device *dev)
 {
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index 27013d6bf24a..42d6d47e445b 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -31,23 +31,21 @@ struct mdio_device {
 	struct mii_bus *bus;
 	char modalias[MDIO_NAME_SIZE];
 
-	int (*bus_match)(struct device *dev, struct device_driver *drv);
+	int (*bus_match)(struct device *dev, const struct device_driver *drv);
 	void (*device_free)(struct mdio_device *mdiodev);
 	void (*device_remove)(struct mdio_device *mdiodev);
 
 	/* Bus address of the MDIO device (0-31) */
 	int addr;
 	int flags;
+	int reset_state;
 	struct gpio_desc *reset_gpio;
 	struct reset_control *reset_ctrl;
 	unsigned int reset_assert_delay;
 	unsigned int reset_deassert_delay;
 };
 
-static inline struct mdio_device *to_mdio_device(const struct device *dev)
-{
-	return container_of(dev, struct mdio_device, dev);
-}
+#define to_mdio_device(__dev)	container_of_const(__dev, struct mdio_device, dev)
 
 /* struct mdio_driver_common: Common to all MDIO drivers */
 struct mdio_driver_common {
@@ -56,11 +54,8 @@ struct mdio_driver_common {
 };
 #define MDIO_DEVICE_FLAG_PHY		1
 
-static inline struct mdio_driver_common *
-to_mdio_common_driver(const struct device_driver *driver)
-{
-	return container_of(driver, struct mdio_driver_common, driver);
-}
+#define to_mdio_common_driver(__drv_c)	container_of_const(__drv_c, struct mdio_driver_common,	\
+							   driver)
 
 /* struct mdio_driver: Generic MDIO driver */
 struct mdio_driver {
@@ -79,12 +74,8 @@ struct mdio_driver {
 	void (*shutdown)(struct mdio_device *mdiodev);
 };
 
-static inline struct mdio_driver *
-to_mdio_driver(const struct device_driver *driver)
-{
-	return container_of(to_mdio_common_driver(driver), struct mdio_driver,
-			    mdiodrv);
-}
+#define to_mdio_driver(__drv_m)	container_of_const(to_mdio_common_driver(__drv_m),	\
+						   struct mdio_driver, mdiodrv)
 
 /* device driver data */
 static inline void mdiodev_set_drvdata(struct mdio_device *mdio, void *data)
@@ -104,7 +95,16 @@ void mdio_device_remove(struct mdio_device *mdiodev);
 void mdio_device_reset(struct mdio_device *mdiodev, int value);
 int mdio_driver_register(struct mdio_driver *drv);
 void mdio_driver_unregister(struct mdio_driver *drv);
-int mdio_device_bus_match(struct device *dev, struct device_driver *drv);
+
+static inline void mdio_device_get(struct mdio_device *mdiodev)
+{
+	get_device(&mdiodev->dev);
+}
+
+static inline void mdio_device_put(struct mdio_device *mdiodev)
+{
+	mdio_device_free(mdiodev);
+}
 
 static inline bool mdio_phy_id_is_c45(int phy_id)
 {
@@ -161,31 +161,12 @@ extern int mdio_set_flag(const struct mdio_if_info *mdio,
 			 bool sense);
 extern int mdio45_links_ok(const struct mdio_if_info *mdio, u32 mmds);
 extern int mdio45_nway_restart(const struct mdio_if_info *mdio);
-extern void mdio45_ethtool_gset_npage(const struct mdio_if_info *mdio,
-				      struct ethtool_cmd *ecmd,
-				      u32 npage_adv, u32 npage_lpa);
 extern void
 mdio45_ethtool_ksettings_get_npage(const struct mdio_if_info *mdio,
 				   struct ethtool_link_ksettings *cmd,
 				   u32 npage_adv, u32 npage_lpa);
 
 /**
- * mdio45_ethtool_gset - get settings for ETHTOOL_GSET
- * @mdio: MDIO interface
- * @ecmd: Ethtool request structure
- *
- * Since the CSRs for auto-negotiation using next pages are not fully
- * standardised, this function does not attempt to decode them.  Use
- * mdio45_ethtool_gset_npage() to specify advertisement bits from next
- * pages.
- */
-static inline void mdio45_ethtool_gset(const struct mdio_if_info *mdio,
-				       struct ethtool_cmd *ecmd)
-{
-	mdio45_ethtool_gset_npage(mdio, ecmd, 0, 0);
-}
-
-/**
  * mdio45_ethtool_ksettings_get - get settings for ETHTOOL_GLINKSETTINGS
  * @mdio: MDIO interface
  * @cmd: Ethtool request structure
@@ -362,6 +343,10 @@ static inline void mii_t1_adv_m_mod_linkmode_t(unsigned long *advertising, u32 l
 {
 	linkmode_mod_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT,
 			 advertising, lpa & MDIO_AN_T1_ADV_M_B10L);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT,
+			 advertising, lpa & MDIO_AN_T1_ADV_M_100BT1);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT,
+			 advertising, lpa & MDIO_AN_T1_ADV_M_1000BT1);
 }
 
 /**
@@ -398,6 +383,10 @@ static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising)
 
 	if (linkmode_test_bit(ETHTOOL_LINK_MODE_10baseT1L_Full_BIT, advertising))
 		result |= MDIO_AN_T1_ADV_M_B10L;
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_100baseT1_Full_BIT, advertising))
+		result |= MDIO_AN_T1_ADV_M_100BT1;
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_1000baseT1_Full_BIT, advertising))
+		result |= MDIO_AN_T1_ADV_M_1000BT1;
 
 	return result;
 }
@@ -410,7 +399,7 @@ static inline u32 linkmode_adv_to_mii_t1_adv_m_t(unsigned long *advertising)
  * A function that translates value of following registers to the linkmode:
  * IEEE 802.3-2018 45.2.3.10 "EEE control and capability 1" register (3.20)
  * IEEE 802.3-2018 45.2.7.13 "EEE advertisement 1" register (7.60)
- * IEEE 802.3-2018 45.2.7.14 "EEE "link partner ability 1 register (7.61)
+ * IEEE 802.3-2018 45.2.7.14 "EEE link partner ability 1" register (7.61)
  */
 static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val)
 {
@@ -429,6 +418,42 @@ static inline void mii_eee_cap1_mod_linkmode_t(unsigned long *adv, u32 val)
 }
 
 /**
+ * mii_eee_cap2_mod_linkmode_sup_t()
+ * @adv: target the linkmode settings
+ * @val: register value
+ *
+ * A function that translates value of following registers to the linkmode:
+ * IEEE 802.3-2022 45.2.3.11 "EEE control and capability 2" register (3.21)
+ */
+static inline void mii_eee_cap2_mod_linkmode_sup_t(unsigned long *adv, u32 val)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+			 adv, val & MDIO_EEE_2_5GT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+			 adv, val & MDIO_EEE_5GT);
+}
+
+/**
+ * mii_eee_cap2_mod_linkmode_adv_t()
+ * @adv: target the linkmode advertisement settings
+ * @val: register value
+ *
+ * A function that translates value of following registers to the linkmode:
+ * IEEE 802.3-2022 45.2.7.16 "EEE advertisement 2" register (7.62)
+ * IEEE 802.3-2022 45.2.7.17 "EEE link partner ability 2" register (7.63)
+ * Note: Currently this function is the same as mii_eee_cap2_mod_linkmode_sup_t.
+ *       For certain, not yet supported, modes however the bits differ.
+ *       Therefore create separate functions already.
+ */
+static inline void mii_eee_cap2_mod_linkmode_adv_t(unsigned long *adv, u32 val)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT,
+			 adv, val & MDIO_EEE_2_5GT);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT,
+			 adv, val & MDIO_EEE_5GT);
+}
+
+/**
  * linkmode_to_mii_eee_cap1_t()
  * @adv: the linkmode advertisement settings
  *
@@ -456,6 +481,25 @@ static inline u32 linkmode_to_mii_eee_cap1_t(unsigned long *adv)
 }
 
 /**
+ * linkmode_to_mii_eee_cap2_t()
+ * @adv: the linkmode advertisement settings
+ *
+ * A function that translates linkmode to value for IEEE 802.3-2022 45.2.7.16
+ * "EEE advertisement 2" register (7.62)
+ */
+static inline u32 linkmode_to_mii_eee_cap2_t(unsigned long *adv)
+{
+	u32 result = 0;
+
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_2500baseT_Full_BIT, adv))
+		result |= MDIO_EEE_2_5GT;
+	if (linkmode_test_bit(ETHTOOL_LINK_MODE_5000baseT_Full_BIT, adv))
+		result |= MDIO_EEE_5GT;
+
+	return result;
+}
+
+/**
  * mii_10base_t1_adv_mod_linkmode_t()
  * @adv: linkmode advertisement settings
  * @val: register value
@@ -486,8 +530,49 @@ static inline u32 linkmode_adv_to_mii_10base_t1_t(unsigned long *adv)
 	return result;
 }
 
+/**
+ * mii_c73_mod_linkmode - convert a Clause 73 advertisement to linkmodes
+ * @adv: linkmode advertisement setting
+ * @lpa: array of three u16s containing the advertisement
+ *
+ * Convert an IEEE 802.3 Clause 73 advertisement to ethtool link modes.
+ */
+static inline void mii_c73_mod_linkmode(unsigned long *adv, u16 *lpa)
+{
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Pause_BIT,
+			 adv, lpa[0] & MDIO_AN_C73_0_PAUSE);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT,
+			 adv, lpa[0] & MDIO_AN_C73_0_ASM_DIR);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_1000baseKX_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_1000BASE_KX);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_10GBASE_KX4);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_40000baseKR4_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_40GBASE_KR4);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_40000baseCR4_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_40GBASE_CR4);
+	/* 100GBASE_CR10 and 100GBASE_KP4 not implemented */
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_100GBASE_KR4);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_100GBASE_CR4);
+	/* 25GBASE_R_S not implemented */
+	/* The 25GBASE_R bit can be used for 25Gbase KR or CR modes */
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_25000baseKR_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_25GBASE_R);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_25000baseCR_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_25GBASE_R);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_10000baseKR_Full_BIT,
+			 adv, lpa[1] & MDIO_AN_C73_1_10GBASE_KR);
+	linkmode_mod_bit(ETHTOOL_LINK_MODE_2500baseX_Full_BIT,
+			 adv, lpa[2] & MDIO_AN_C73_2_2500BASE_KX);
+	/* 5GBASE_KR not implemented */
+}
+
 int __mdiobus_read(struct mii_bus *bus, int addr, u32 regnum);
 int __mdiobus_write(struct mii_bus *bus, int addr, u32 regnum, u16 val);
+int __mdiobus_modify(struct mii_bus *bus, int addr, u32 regnum, u16 mask,
+		     u16 set);
 int __mdiobus_modify_changed(struct mii_bus *bus, int addr, u32 regnum,
 			     u16 mask, u16 set);
 
@@ -515,6 +600,30 @@ int mdiobus_c45_modify(struct mii_bus *bus, int addr, int devad, u32 regnum,
 int mdiobus_c45_modify_changed(struct mii_bus *bus, int addr, int devad,
 			       u32 regnum, u16 mask, u16 set);
 
+static inline int __mdiodev_read(struct mdio_device *mdiodev, u32 regnum)
+{
+	return __mdiobus_read(mdiodev->bus, mdiodev->addr, regnum);
+}
+
+static inline int __mdiodev_write(struct mdio_device *mdiodev, u32 regnum,
+				  u16 val)
+{
+	return __mdiobus_write(mdiodev->bus, mdiodev->addr, regnum, val);
+}
+
+static inline int __mdiodev_modify(struct mdio_device *mdiodev, u32 regnum,
+				   u16 mask, u16 set)
+{
+	return __mdiobus_modify(mdiodev->bus, mdiodev->addr, regnum, mask, set);
+}
+
+static inline int __mdiodev_modify_changed(struct mdio_device *mdiodev,
+					   u32 regnum, u16 mask, u16 set)
+{
+	return __mdiobus_modify_changed(mdiodev->bus, mdiodev->addr, regnum,
+					mask, set);
+}
+
 static inline int mdiodev_read(struct mdio_device *mdiodev, u32 regnum)
 {
 	return mdiobus_read(mdiodev->bus, mdiodev->addr, regnum);
@@ -580,16 +689,7 @@ struct phy_device *mdiobus_get_phy(struct mii_bus *bus, int addr);
  * init/exit. Each module may only use this macro once, and calling it
  * replaces module_init() and module_exit().
  */
-#define mdio_module_driver(_mdio_driver)				\
-static int __init mdio_module_init(void)				\
-{									\
-	return mdio_driver_register(&_mdio_driver);			\
-}									\
-module_init(mdio_module_init);						\
-static void __exit mdio_module_exit(void)				\
-{									\
-	mdio_driver_unregister(&_mdio_driver);				\
-}									\
-module_exit(mdio_module_exit)
+#define mdio_module_driver(_mdio_driver) \
+	module_driver(_mdio_driver, mdio_driver_register, mdio_driver_unregister)
 
 #endif /* __LINUX_MDIO_H__ */
diff --git a/include/linux/mdio/mdio-regmap.h b/include/linux/mdio/mdio-regmap.h
new file mode 100644
index 000000000000..679d9069846b
--- /dev/null
+++ b/include/linux/mdio/mdio-regmap.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Driver for MMIO-Mapped MDIO devices. Some IPs expose internal PHYs or PCS
+ * within the MMIO-mapped area
+ *
+ * Copyright (C) 2023 Maxime Chevallier <maxime.chevallier@bootlin.com>
+ */
+#ifndef MDIO_REGMAP_H
+#define MDIO_REGMAP_H
+
+#include <linux/phy.h>
+
+struct device;
+struct regmap;
+
+struct mdio_regmap_config {
+	struct device *parent;
+	struct regmap *regmap;
+	char name[MII_BUS_ID_SIZE];
+	u8 valid_addr;
+	bool autoscan;
+};
+
+struct mii_bus *devm_mdio_regmap_register(struct device *dev,
+					  const struct mdio_regmap_config *config);
+
+#endif
diff --git a/include/linux/mei_cl_bus.h b/include/linux/mei_cl_bus.h
index fd6e0620658d..a82755e1fc40 100644
--- a/include/linux/mei_cl_bus.h
+++ b/include/linux/mei_cl_bus.h
@@ -31,11 +31,11 @@ typedef void (*mei_cldev_cb_t)(struct mei_cl_device *cldev);
  * @rx_work: async work to execute Rx event callback
  * @rx_cb: Drivers register this callback to get asynchronous ME
  *	Rx buffer pending notifications.
- * @notif_work: async work to execute FW notif event callback
+ * @notif_work: async work to execute FW notify event callback
  * @notif_cb: Drivers register this callback to get asynchronous ME
  *	FW notification pending notifications.
  *
- * @do_match: wheather device can be matched with a driver
+ * @do_match: whether the device can be matched with a driver
  * @is_added: device is already scanned
  * @priv_data: client private data
  */
@@ -94,22 +94,26 @@ void mei_cldev_driver_unregister(struct mei_cl_driver *cldrv);
 
 ssize_t mei_cldev_send(struct mei_cl_device *cldev, const u8 *buf,
 		       size_t length);
+ssize_t mei_cldev_send_timeout(struct mei_cl_device *cldev, const u8 *buf,
+			       size_t length, unsigned long timeout);
 ssize_t mei_cldev_recv(struct mei_cl_device *cldev, u8 *buf, size_t length);
-ssize_t mei_cldev_recv_nonblock(struct mei_cl_device *cldev, u8 *buf,
-				size_t length);
+ssize_t mei_cldev_recv_timeout(struct mei_cl_device *cldev, u8 *buf, size_t length,
+			       unsigned long timeout);
 ssize_t mei_cldev_send_vtag(struct mei_cl_device *cldev, const u8 *buf,
 			    size_t length, u8 vtag);
+ssize_t mei_cldev_send_vtag_timeout(struct mei_cl_device *cldev, const u8 *buf,
+				    size_t length, u8 vtag, unsigned long timeout);
 ssize_t mei_cldev_recv_vtag(struct mei_cl_device *cldev, u8 *buf, size_t length,
 			    u8 *vtag);
-ssize_t mei_cldev_recv_nonblock_vtag(struct mei_cl_device *cldev, u8 *buf,
-				     size_t length, u8 *vtag);
+ssize_t mei_cldev_recv_vtag_timeout(struct mei_cl_device *cldev, u8 *buf, size_t length,
+			    u8 *vtag, unsigned long timeout);
 
 int mei_cldev_register_rx_cb(struct mei_cl_device *cldev, mei_cldev_cb_t rx_cb);
 int mei_cldev_register_notif_cb(struct mei_cl_device *cldev,
 				mei_cldev_cb_t notif_cb);
 
-const uuid_le *mei_cldev_uuid(const struct mei_cl_device *cldev);
 u8 mei_cldev_ver(const struct mei_cl_device *cldev);
+size_t mei_cldev_mtu(const struct mei_cl_device *cldev);
 
 void *mei_cldev_get_drvdata(const struct mei_cl_device *cldev);
 void mei_cldev_set_drvdata(struct mei_cl_device *cldev, void *data);
diff --git a/include/linux/mem_encrypt.h b/include/linux/mem_encrypt.h
index ae4526389261..07584c5e36fb 100644
--- a/include/linux/mem_encrypt.h
+++ b/include/linux/mem_encrypt.h
@@ -26,11 +26,34 @@
  */
 #define __sme_set(x)		((x) | sme_me_mask)
 #define __sme_clr(x)		((x) & ~sme_me_mask)
+
+#define dma_addr_encrypted(x)	__sme_set(x)
+#define dma_addr_canonical(x)	__sme_clr(x)
+
 #else
 #define __sme_set(x)		(x)
 #define __sme_clr(x)		(x)
 #endif
 
+/*
+ * dma_addr_encrypted() and dma_addr_unencrypted() are for converting a given DMA
+ * address to the respective type of addressing.
+ *
+ * dma_addr_canonical() is used to reverse any conversions for encrypted/decrypted
+ * back to the canonical address.
+ */
+#ifndef dma_addr_encrypted
+#define dma_addr_encrypted(x)		(x)
+#endif
+
+#ifndef dma_addr_unencrypted
+#define dma_addr_unencrypted(x)		(x)
+#endif
+
+#ifndef dma_addr_canonical
+#define dma_addr_canonical(x)		(x)
+#endif
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __MEM_ENCRYPT_H__ */
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index f82ee3fac1cd..221118b5a16e 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -40,6 +40,17 @@ extern unsigned long long max_possible_pfn;
  * via a driver, and never indicated in the firmware-provided memory map as
  * system RAM. This corresponds to IORESOURCE_SYSRAM_DRIVER_MANAGED in the
  * kernel resource tree.
+ * @MEMBLOCK_RSRV_NOINIT: reserved memory region for which struct pages are not
+ * fully initialized. Users of this flag are responsible to properly initialize
+ * struct pages of this region
+ * @MEMBLOCK_RSRV_KERN: memory region that is reserved for kernel use,
+ * either explictitly with memblock_reserve_kern() or via memblock
+ * allocation APIs. All memblock allocations set this flag.
+ * @MEMBLOCK_KHO_SCRATCH: memory region that kexec can pass to the next
+ * kernel in handover mode. During early boot, we do not know about all
+ * memory reservations yet, so we get scratch memory from the previous
+ * kernel that we know is good to use. It is the only memory that
+ * allocations may happen from in this phase.
  */
 enum memblock_flags {
 	MEMBLOCK_NONE		= 0x0,	/* No special request */
@@ -47,6 +58,9 @@ enum memblock_flags {
 	MEMBLOCK_MIRROR		= 0x2,	/* mirrored region */
 	MEMBLOCK_NOMAP		= 0x4,	/* don't add to kernel direct mapping */
 	MEMBLOCK_DRIVER_MANAGED = 0x8,	/* always detected via a driver */
+	MEMBLOCK_RSRV_NOINIT	= 0x10,	/* don't initialize struct pages */
+	MEMBLOCK_RSRV_KERN	= 0x20,	/* memory reserved for kernel use */
+	MEMBLOCK_KHO_SCRATCH	= 0x40,	/* scratch memory for kexec handover */
 };
 
 /**
@@ -113,22 +127,38 @@ int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid,
 int memblock_add(phys_addr_t base, phys_addr_t size);
 int memblock_remove(phys_addr_t base, phys_addr_t size);
 int memblock_phys_free(phys_addr_t base, phys_addr_t size);
-int memblock_reserve(phys_addr_t base, phys_addr_t size);
+int __memblock_reserve(phys_addr_t base, phys_addr_t size, int nid,
+		       enum memblock_flags flags);
+
+static __always_inline int memblock_reserve(phys_addr_t base, phys_addr_t size)
+{
+	return __memblock_reserve(base, size, NUMA_NO_NODE, 0);
+}
+
+static __always_inline int memblock_reserve_kern(phys_addr_t base, phys_addr_t size)
+{
+	return __memblock_reserve(base, size, NUMA_NO_NODE, MEMBLOCK_RSRV_KERN);
+}
+
 #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
 int memblock_physmem_add(phys_addr_t base, phys_addr_t size);
 #endif
 void memblock_trim_memory(phys_addr_t align);
+unsigned long memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
+				     phys_addr_t base2, phys_addr_t size2);
 bool memblock_overlaps_region(struct memblock_type *type,
 			      phys_addr_t base, phys_addr_t size);
+bool memblock_validate_numa_coverage(unsigned long threshold_bytes);
 int memblock_mark_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_clear_hotplug(phys_addr_t base, phys_addr_t size);
 int memblock_mark_mirror(phys_addr_t base, phys_addr_t size);
 int memblock_mark_nomap(phys_addr_t base, phys_addr_t size);
 int memblock_clear_nomap(phys_addr_t base, phys_addr_t size);
+int memblock_reserved_mark_noinit(phys_addr_t base, phys_addr_t size);
+int memblock_mark_kho_scratch(phys_addr_t base, phys_addr_t size);
+int memblock_clear_kho_scratch(phys_addr_t base, phys_addr_t size);
 
-void memblock_free_all(void);
 void memblock_free(void *ptr, size_t size);
-void reset_node_managed_pages(pg_data_t *pgdat);
 void reset_all_zones_managed_pages(void);
 
 /* Low level functions */
@@ -260,11 +290,21 @@ static inline bool memblock_is_nomap(struct memblock_region *m)
 	return m->flags & MEMBLOCK_NOMAP;
 }
 
+static inline bool memblock_is_reserved_noinit(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_RSRV_NOINIT;
+}
+
 static inline bool memblock_is_driver_managed(struct memblock_region *m)
 {
 	return m->flags & MEMBLOCK_DRIVER_MANAGED;
 }
 
+static inline bool memblock_is_kho_scratch(struct memblock_region *m)
+{
+	return m->flags & MEMBLOCK_KHO_SCRATCH;
+}
+
 int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
 			    unsigned long  *end_pfn);
 void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
@@ -284,49 +324,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 	for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
 	     i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
 
-#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
-				  unsigned long *out_spfn,
-				  unsigned long *out_epfn);
-/**
- * for_each_free_mem_pfn_range_in_zone - iterate through zone specific free
- * memblock areas
- * @i: u64 used as loop variable
- * @zone: zone in which all of the memory blocks reside
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- *
- * Walks over free (memory && !reserved) areas of memblock in a specific
- * zone. Available once memblock and an empty zone is initialized. The main
- * assumption is that the zone start, end, and pgdat have been associated.
- * This way we can use the zone to determine NUMA node, and if a given part
- * of the memblock is valid for the zone.
- */
-#define for_each_free_mem_pfn_range_in_zone(i, zone, p_start, p_end)	\
-	for (i = 0,							\
-	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end);	\
-	     i != U64_MAX;					\
-	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
-
-/**
- * for_each_free_mem_pfn_range_in_zone_from - iterate through zone specific
- * free memblock areas from a given point
- * @i: u64 used as loop variable
- * @zone: zone in which all of the memory blocks reside
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- *
- * Walks over free (memory && !reserved) areas of memblock in a specific
- * zone, continuing from current position. Available as soon as memblock is
- * initialized.
- */
-#define for_each_free_mem_pfn_range_in_zone_from(i, zone, p_start, p_end) \
-	for (; i != U64_MAX;					  \
-	     __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
-
-int __init deferred_page_init_max_threads(const struct cpumask *node_cpumask);
-
-#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
 /**
  * for_each_free_mem_range - iterate through free memblock areas
@@ -388,6 +385,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r)
 /* Flags for memblock allocation APIs */
 #define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
 #define MEMBLOCK_ALLOC_ACCESSIBLE	0
+/*
+ *  MEMBLOCK_ALLOC_NOLEAKTRACE avoids kmemleak tracing. It implies
+ *  MEMBLOCK_ALLOC_ACCESSIBLE
+ */
 #define MEMBLOCK_ALLOC_NOLEAKTRACE	1
 
 /* We are using top down, so it is safe to use 0 here */
@@ -427,6 +428,12 @@ static __always_inline void *memblock_alloc(phys_addr_t size, phys_addr_t align)
 				      MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE);
 }
 
+void *__memblock_alloc_or_panic(phys_addr_t size, phys_addr_t align,
+				const char *func);
+
+#define memblock_alloc_or_panic(size, align)    \
+	 __memblock_alloc_or_panic(size, align, __func__)
+
 static inline void *memblock_alloc_raw(phys_addr_t size,
 					       phys_addr_t align)
 {
@@ -435,7 +442,7 @@ static inline void *memblock_alloc_raw(phys_addr_t size,
 					  NUMA_NO_NODE);
 }
 
-static inline void *memblock_alloc_from(phys_addr_t size,
+static __always_inline void *memblock_alloc_from(phys_addr_t size,
 						phys_addr_t align,
 						phys_addr_t min_addr)
 {
@@ -477,6 +484,8 @@ static inline __init_memblock bool memblock_bottom_up(void)
 
 phys_addr_t memblock_phys_mem_size(void);
 phys_addr_t memblock_reserved_size(void);
+phys_addr_t memblock_reserved_kern_size(phys_addr_t limit, int nid);
+unsigned long memblock_estimated_nr_free_pages(void);
 phys_addr_t memblock_start_of_DRAM(void);
 phys_addr_t memblock_end_of_DRAM(void);
 void memblock_enforce_memory_limit(phys_addr_t memory_limit);
@@ -554,7 +563,7 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo
 }
 
 /**
- * for_each_mem_region - itereate over memory regions
+ * for_each_mem_region - iterate over memory regions
  * @region: loop variable
  */
 #define for_each_mem_region(region)					\
@@ -582,9 +591,7 @@ extern void *alloc_large_system_hash(const char *tablename,
 				     unsigned long high_limit);
 
 #define HASH_EARLY	0x00000001	/* Allocating during early boot? */
-#define HASH_SMALL	0x00000002	/* sub-page allocation allowed, min
-					 * shift passed via *_hash_shift */
-#define HASH_ZERO	0x00000004	/* Zero allocated hash table */
+#define HASH_ZERO	0x00000002	/* Zero allocated hash table */
 
 /* Only NUMA needs hash distribution. 64bit NUMA architectures have
  * sufficient vmalloc space.
@@ -597,14 +604,21 @@ extern int hashdist;		/* Distribute hashes across NUMA nodes? */
 #endif
 
 #ifdef CONFIG_MEMTEST
-extern phys_addr_t early_memtest_bad_size;	/* Size of faulty ram found by memtest */
-extern bool early_memtest_done;			/* Was early memtest done? */
-extern void early_memtest(phys_addr_t start, phys_addr_t end);
+void early_memtest(phys_addr_t start, phys_addr_t end);
+void memtest_report_meminfo(struct seq_file *m);
 #else
-static inline void early_memtest(phys_addr_t start, phys_addr_t end)
-{
-}
+static inline void early_memtest(phys_addr_t start, phys_addr_t end) { }
+static inline void memtest_report_meminfo(struct seq_file *m) { }
 #endif
 
+#ifdef CONFIG_MEMBLOCK_KHO_SCRATCH
+void memblock_set_kho_scratch_only(void);
+void memblock_clear_kho_scratch_only(void);
+void memmap_init_kho_scratch_pages(void);
+#else
+static inline void memblock_set_kho_scratch_only(void) { }
+static inline void memblock_clear_kho_scratch_only(void) { }
+static inline void memmap_init_kho_scratch_pages(void) {}
+#endif
 
 #endif /* _LINUX_MEMBLOCK_H */
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 00a88cf947e1..0651865a4564 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -14,6 +14,7 @@
 #include <linux/vm_event_item.h>
 #include <linux/hardirq.h>
 #include <linux/jump_label.h>
+#include <linux/kernel.h>
 #include <linux/page_counter.h>
 #include <linux/vmpressure.h>
 #include <linux/eventfd.h>
@@ -21,6 +22,7 @@
 #include <linux/vmstat.h>
 #include <linux/writeback.h>
 #include <linux/page-flags.h>
+#include <linux/shrinker.h>
 
 struct mem_cgroup;
 struct obj_cgroup;
@@ -50,93 +52,74 @@ enum memcg_memory_event {
 	MEMCG_SWAP_HIGH,
 	MEMCG_SWAP_MAX,
 	MEMCG_SWAP_FAIL,
+	MEMCG_SOCK_THROTTLED,
 	MEMCG_NR_MEMORY_EVENTS,
 };
 
 struct mem_cgroup_reclaim_cookie {
 	pg_data_t *pgdat;
-	unsigned int generation;
+	int generation;
 };
 
 #ifdef CONFIG_MEMCG
 
 #define MEM_CGROUP_ID_SHIFT	16
-#define MEM_CGROUP_ID_MAX	USHRT_MAX
 
 struct mem_cgroup_id {
 	int id;
 	refcount_t ref;
 };
 
-/*
- * Per memcg event counter is incremented at every pagein/pageout. With THP,
- * it will be incremented by the number of pages. This counter is used
- * to trigger some periodic events. This is straightforward and better
- * than using jiffies etc. to handle periodic memcg event.
- */
-enum mem_cgroup_events_target {
-	MEM_CGROUP_TARGET_THRESH,
-	MEM_CGROUP_TARGET_SOFTLIMIT,
-	MEM_CGROUP_NTARGETS,
-};
-
 struct memcg_vmstats_percpu;
+struct memcg1_events_percpu;
 struct memcg_vmstats;
+struct lruvec_stats_percpu;
+struct lruvec_stats;
 
 struct mem_cgroup_reclaim_iter {
 	struct mem_cgroup *position;
 	/* scan generation, increased every round-trip */
-	unsigned int generation;
-};
-
-/*
- * Bitmap and deferred work of shrinker::id corresponding to memcg-aware
- * shrinkers, which have elements charged to this memcg.
- */
-struct shrinker_info {
-	struct rcu_head rcu;
-	atomic_long_t *nr_deferred;
-	unsigned long *map;
-	int map_nr_max;
-};
-
-struct lruvec_stats_percpu {
-	/* Local (CPU and cgroup) state */
-	long state[NR_VM_NODE_STAT_ITEMS];
-
-	/* Delta calculation for lockless upward propagation */
-	long state_prev[NR_VM_NODE_STAT_ITEMS];
-};
-
-struct lruvec_stats {
-	/* Aggregated (CPU and subtree) state */
-	long state[NR_VM_NODE_STAT_ITEMS];
-
-	/* Pending child counts during tree propagation */
-	long state_pending[NR_VM_NODE_STAT_ITEMS];
+	atomic_t generation;
 };
 
 /*
  * per-node information in memory controller.
  */
 struct mem_cgroup_per_node {
-	struct lruvec		lruvec;
+	/* Keep the read-only fields at the start */
+	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
+						/* use container_of	   */
 
 	struct lruvec_stats_percpu __percpu	*lruvec_stats_percpu;
-	struct lruvec_stats			lruvec_stats;
-
-	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
-
-	struct mem_cgroup_reclaim_iter	iter;
-
+	struct lruvec_stats			*lruvec_stats;
 	struct shrinker_info __rcu	*shrinker_info;
 
+#ifdef CONFIG_MEMCG_V1
+	/*
+	 * Memcg-v1 only stuff in middle as buffer between read mostly fields
+	 * and update often fields to avoid false sharing. If v1 stuff is
+	 * not present, an explicit padding is needed.
+	 */
+
 	struct rb_node		tree_node;	/* RB tree node */
 	unsigned long		usage_in_excess;/* Set to the value by which */
 						/* the soft limit is exceeded*/
 	bool			on_tree;
-	struct mem_cgroup	*memcg;		/* Back pointer, we cannot */
-						/* use container_of	   */
+#else
+	CACHELINE_PADDING(_pad1_);
+#endif
+
+	/* Fields which get updated often at the end. */
+	struct lruvec		lruvec;
+	CACHELINE_PADDING(_pad2_);
+	unsigned long		lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS];
+	struct mem_cgroup_reclaim_iter	iter;
+
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* slab stats for nmi context */
+	atomic_t		slab_reclaimable;
+	atomic_t		slab_unreclaimable;
+#endif
 };
 
 struct mem_cgroup_threshold {
@@ -151,7 +134,7 @@ struct mem_cgroup_threshold_ary {
 	/* Size of entries[] */
 	unsigned int size;
 	/* Array of thresholds */
-	struct mem_cgroup_threshold entries[];
+	struct mem_cgroup_threshold entries[] __counted_by(size);
 };
 
 struct mem_cgroup_thresholds {
@@ -218,18 +201,23 @@ struct mem_cgroup {
 		struct page_counter memsw;	/* v1 only */
 	};
 
-	/* Legacy consumer-oriented counters */
-	struct page_counter kmem;		/* v1 only */
-	struct page_counter tcpmem;		/* v1 only */
+	/* registered local peak watchers */
+	struct list_head memory_peaks;
+	struct list_head swap_peaks;
+	spinlock_t	 peaks_lock;
 
 	/* Range enforcement for interrupt charges */
 	struct work_struct high_work;
 
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+#ifdef CONFIG_ZSWAP
 	unsigned long zswap_max;
-#endif
 
-	unsigned long soft_limit;
+	/*
+	 * Prevent pages from this memcg from being written back from zswap to
+	 * swap, and from being swapped out on zswap store failures.
+	 */
+	bool zswap_writeback;
+#endif
 
 	/* vmpressure notifications */
 	struct vmpressure vmpressure;
@@ -239,13 +227,7 @@ struct mem_cgroup {
 	 */
 	bool oom_group;
 
-	/* protected by memcg_oom_lock */
-	bool		oom_lock;
-	int		under_oom;
-
-	int	swappiness;
-	/* OOM-Killer disable */
-	int		oom_kill_disable;
+	int swappiness;
 
 	/* memory.events and memory.events.local */
 	struct cgroup_file events_file;
@@ -254,29 +236,6 @@ struct mem_cgroup {
 	/* handle for "memory.swap.events" */
 	struct cgroup_file swap_events_file;
 
-	/* protect arrays of thresholds */
-	struct mutex thresholds_lock;
-
-	/* thresholds for memory usage. RCU-protected */
-	struct mem_cgroup_thresholds thresholds;
-
-	/* thresholds for mem+swap usage. RCU-protected */
-	struct mem_cgroup_thresholds memsw_thresholds;
-
-	/* For oom notifier event fd */
-	struct list_head oom_notify;
-
-	/*
-	 * Should we move charges of a task when a task is moved into this
-	 * mem_cgroup ? And what type of charges should we move ?
-	 */
-	unsigned long move_charge_at_immigrate;
-	/* taken only while moving_account > 0 */
-	spinlock_t		move_lock;
-	unsigned long		move_lock_flags;
-
-	CACHELINE_PADDING(_pad1_);
-
 	/* memory.stat */
 	struct memcg_vmstats	*vmstats;
 
@@ -284,26 +243,29 @@ struct mem_cgroup {
 	atomic_long_t		memory_events[MEMCG_NR_MEMORY_EVENTS];
 	atomic_long_t		memory_events_local[MEMCG_NR_MEMORY_EVENTS];
 
-	unsigned long		socket_pressure;
-
-	/* Legacy tcp memory accounting */
-	bool			tcpmem_active;
-	int			tcpmem_pressure;
-
-#ifdef CONFIG_MEMCG_KMEM
-	int kmemcg_id;
-	struct obj_cgroup __rcu *objcg;
-	/* list of inherited objcgs, protected by objcg_lock */
-	struct list_head objcg_list;
+#ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC
+	/* MEMCG_KMEM for nmi context */
+	atomic_t		kmem_stat;
 #endif
-
-	CACHELINE_PADDING(_pad2_);
-
 	/*
-	 * set > 0 if pages under this cgroup are moving to other cgroup.
+	 * Hint of reclaim pressure for socket memroy management. Note
+	 * that this indicator should NOT be used in legacy cgroup mode
+	 * where socket memory is accounted/charged separately.
+	 */
+	u64			socket_pressure;
+#if BITS_PER_LONG < 64
+	seqlock_t		socket_pressure_seqlock;
+#endif
+	int kmemcg_id;
+	/*
+	 * memcg->objcg is wiped out as a part of the objcg repaprenting
+	 * process. memcg->orig_objcg preserves a pointer (and a reference)
+	 * to the original objcg until the end of live of memcg.
 	 */
-	atomic_t		moving_account;
-	struct task_struct	*move_lock_task;
+	struct obj_cgroup __rcu	*objcg;
+	struct obj_cgroup	*orig_objcg;
+	/* list of inherited objcgs, protected by objcg_lock */
+	struct list_head objcg_list;
 
 	struct memcg_vmstats_percpu __percpu *vmstats_percpu;
 
@@ -313,19 +275,52 @@ struct mem_cgroup {
 	struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT];
 #endif
 
-	/* List of events which userspace want to receive */
-	struct list_head event_list;
-	spinlock_t event_list_lock;
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	struct deferred_split deferred_split_queue;
 #endif
 
-#ifdef CONFIG_LRU_GEN
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* per-memcg mm_struct list */
 	struct lru_gen_mm_list mm_list;
 #endif
 
+#ifdef CONFIG_MEMCG_V1
+	/* Legacy consumer-oriented counters */
+	struct page_counter kmem;		/* v1 only */
+	struct page_counter tcpmem;		/* v1 only */
+
+	struct memcg1_events_percpu __percpu *events_percpu;
+
+	unsigned long soft_limit;
+
+	/* protected by memcg_oom_lock */
+	bool oom_lock;
+	int under_oom;
+
+	/* OOM-Killer disable */
+	int oom_kill_disable;
+
+	/* protect arrays of thresholds */
+	struct mutex thresholds_lock;
+
+	/* thresholds for memory usage. RCU-protected */
+	struct mem_cgroup_thresholds thresholds;
+
+	/* thresholds for mem+swap usage. RCU-protected */
+	struct mem_cgroup_thresholds memsw_thresholds;
+
+	/* For oom notifier event fd */
+	struct list_head oom_notify;
+
+	/* Legacy tcp memory accounting */
+	bool tcpmem_active;
+	int tcpmem_pressure;
+
+	/* List of events which userspace want to receive */
+	struct list_head event_list;
+	spinlock_t event_list_lock;
+#endif /* CONFIG_MEMCG_V1 */
+
 	struct mem_cgroup_per_node *nodeinfo[];
 };
 
@@ -339,15 +334,40 @@ struct mem_cgroup {
 extern struct mem_cgroup *root_mem_cgroup;
 
 enum page_memcg_data_flags {
-	/* page->memcg_data is a pointer to an objcgs vector */
-	MEMCG_DATA_OBJCGS = (1UL << 0),
+	/* page->memcg_data is a pointer to an slabobj_ext vector */
+	MEMCG_DATA_OBJEXTS = (1UL << 0),
 	/* page has been accounted as a non-slab kernel page */
 	MEMCG_DATA_KMEM = (1UL << 1),
 	/* the next bit after the last actual flag */
 	__NR_MEMCG_DATA_FLAGS  = (1UL << 2),
 };
 
-#define MEMCG_DATA_FLAGS_MASK (__NR_MEMCG_DATA_FLAGS - 1)
+#define __OBJEXTS_ALLOC_FAIL	MEMCG_DATA_OBJEXTS
+#define __FIRST_OBJEXT_FLAG	__NR_MEMCG_DATA_FLAGS
+
+#else /* CONFIG_MEMCG */
+
+#define __OBJEXTS_ALLOC_FAIL	(1UL << 0)
+#define __FIRST_OBJEXT_FLAG	(1UL << 0)
+
+#endif /* CONFIG_MEMCG */
+
+enum objext_flags {
+	/*
+	 * Use bit 0 with zero other bits to signal that slabobj_ext vector
+	 * failed to allocate. The same bit 0 with valid upper bits means
+	 * MEMCG_DATA_OBJEXTS.
+	 */
+	OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL,
+	/* slabobj_ext vector allocated with kmalloc_nolock() */
+	OBJEXTS_NOSPIN_ALLOC = __FIRST_OBJEXT_FLAG,
+	/* the next bit after the last actual flag */
+	__NR_OBJEXTS_FLAGS  = (__FIRST_OBJEXT_FLAG << 1),
+};
+
+#define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1)
+
+#ifdef CONFIG_MEMCG
 
 static inline bool folio_memcg_kmem(struct folio *folio);
 
@@ -355,11 +375,11 @@ static inline bool folio_memcg_kmem(struct folio *folio);
  * After the initialization objcg->memcg is always pointing at
  * a valid memcg, but can be atomically swapped to the parent memcg.
  *
- * The caller must ensure that the returned memcg won't be released:
- * e.g. acquire the rcu_read_lock or css_set_lock.
+ * The caller must ensure that the returned memcg won't be released.
  */
 static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg)
 {
+	lockdep_assert_once(rcu_read_lock_held() || lockdep_is_held(&cgroup_mutex));
 	return READ_ONCE(objcg->memcg);
 }
 
@@ -378,10 +398,10 @@ static inline struct mem_cgroup *__folio_memcg(struct folio *folio)
 	unsigned long memcg_data = folio->memcg_data;
 
 	VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
-	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio);
 	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_KMEM, folio);
 
-	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+	return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
 }
 
 /*
@@ -399,10 +419,10 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
 	unsigned long memcg_data = folio->memcg_data;
 
 	VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
-	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJCGS, folio);
+	VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio);
 	VM_BUG_ON_FOLIO(!(memcg_data & MEMCG_DATA_KMEM), folio);
 
-	return (struct obj_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+	return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
 }
 
 /*
@@ -419,9 +439,7 @@ static inline struct obj_cgroup *__folio_objcg(struct folio *folio)
  *
  * - the folio lock
  * - LRU isolation
- * - lock_page_memcg()
  * - exclusive reference
- * - mem_cgroup_trylock_pages()
  *
  * For a kmem folio a caller should hold an rcu read lock to protect memcg
  * associated with a kmem folio from being released.
@@ -433,37 +451,15 @@ static inline struct mem_cgroup *folio_memcg(struct folio *folio)
 	return __folio_memcg(folio);
 }
 
-static inline struct mem_cgroup *page_memcg(struct page *page)
-{
-	return folio_memcg(page_folio(page));
-}
-
-/**
- * folio_memcg_rcu - Locklessly get the memory cgroup associated with a folio.
+/*
+ * folio_memcg_charged - If a folio is charged to a memory cgroup.
  * @folio: Pointer to the folio.
  *
- * This function assumes that the folio is known to have a
- * proper memory cgroup pointer. It's not safe to call this function
- * against some type of folios, e.g. slab folios or ex-slab folios.
- *
- * Return: A pointer to the memory cgroup associated with the folio,
- * or NULL.
+ * Returns true if folio is charged to a memory cgroup, otherwise returns false.
  */
-static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
+static inline bool folio_memcg_charged(struct folio *folio)
 {
-	unsigned long memcg_data = READ_ONCE(folio->memcg_data);
-
-	VM_BUG_ON_FOLIO(folio_test_slab(folio), folio);
-	WARN_ON_ONCE(!rcu_read_lock_held());
-
-	if (memcg_data & MEMCG_DATA_KMEM) {
-		struct obj_cgroup *objcg;
-
-		objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
-		return obj_cgroup_memcg(objcg);
-	}
-
-	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+	return folio->memcg_data != 0;
 }
 
 /*
@@ -481,9 +477,7 @@ static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
  *
  * - the folio lock
  * - LRU isolation
- * - lock_folio_memcg()
  * - exclusive reference
- * - mem_cgroup_trylock_pages()
  *
  * For a kmem folio a caller should hold an rcu read lock to protect memcg
  * associated with a kmem folio from being released.
@@ -496,17 +490,17 @@ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
 	 */
 	unsigned long memcg_data = READ_ONCE(folio->memcg_data);
 
-	if (memcg_data & MEMCG_DATA_OBJCGS)
+	if (memcg_data & MEMCG_DATA_OBJEXTS)
 		return NULL;
 
 	if (memcg_data & MEMCG_DATA_KMEM) {
 		struct obj_cgroup *objcg;
 
-		objcg = (void *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+		objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
 		return obj_cgroup_memcg(objcg);
 	}
 
-	return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK);
+	return (struct mem_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK);
 }
 
 static inline struct mem_cgroup *page_memcg_check(struct page *page)
@@ -530,7 +524,6 @@ retry:
 	return memcg;
 }
 
-#ifdef CONFIG_MEMCG_KMEM
 /*
  * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set.
  * @folio: Pointer to the folio.
@@ -542,19 +535,10 @@ retry:
 static inline bool folio_memcg_kmem(struct folio *folio)
 {
 	VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page);
-	VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJCGS, folio);
+	VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio);
 	return folio->memcg_data & MEMCG_DATA_KMEM;
 }
 
-
-#else
-static inline bool folio_memcg_kmem(struct folio *folio)
-{
-	return false;
-}
-
-#endif
-
 static inline bool PageMemcgKmem(struct page *page)
 {
 	return folio_memcg_kmem(page_folio(page));
@@ -583,7 +567,7 @@ static inline void mem_cgroup_protection(struct mem_cgroup *root,
 	/*
 	 * There is no reclaim protection applied to a targeted reclaim.
 	 * We are special casing this specific case here because
-	 * mem_cgroup_protected calculation is not robust enough to keep
+	 * mem_cgroup_calculate_protection is not robust enough to keep
 	 * the protection invariant for calculated effective values for
 	 * parallel reclaimers with different reclaim target. This is
 	 * especially a problem for tail memcgs (as they have pages on LRU)
@@ -679,9 +663,10 @@ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm,
 	return __mem_cgroup_charge(folio, mm, gfp);
 }
 
+int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp);
+
 int mem_cgroup_swapin_charge_folio(struct folio *folio, struct mm_struct *mm,
 				  gfp_t gfp, swp_entry_t entry);
-void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry);
 
 void __mem_cgroup_uncharge(struct folio *folio);
 
@@ -698,14 +683,15 @@ static inline void mem_cgroup_uncharge(struct folio *folio)
 	__mem_cgroup_uncharge(folio);
 }
 
-void __mem_cgroup_uncharge_list(struct list_head *page_list);
-static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
+void __mem_cgroup_uncharge_folios(struct folio_batch *folios);
+static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 {
 	if (mem_cgroup_disabled())
 		return;
-	__mem_cgroup_uncharge_list(page_list);
+	__mem_cgroup_uncharge_folios(folios);
 }
 
+void mem_cgroup_replace_folio(struct folio *old, struct folio *new);
 void mem_cgroup_migrate(struct folio *old, struct folio *new);
 
 /**
@@ -762,6 +748,10 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p);
 
 struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm);
 
+struct mem_cgroup *get_mem_cgroup_from_current(void);
+
+struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio);
+
 struct lruvec *folio_lruvec_lock(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irq(struct folio *folio);
 struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio,
@@ -799,7 +789,8 @@ static inline void obj_cgroup_get_many(struct obj_cgroup *objcg,
 
 static inline void obj_cgroup_put(struct obj_cgroup *objcg)
 {
-	percpu_ref_put(&objcg->refcnt);
+	if (objcg)
+		percpu_ref_put(&objcg->refcnt);
 }
 
 static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
@@ -807,6 +798,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return !memcg || css_tryget(&memcg->css);
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return !memcg || css_tryget_online(&memcg->css);
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 	if (memcg)
@@ -820,8 +816,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *,
 				   struct mem_cgroup *,
 				   struct mem_cgroup_reclaim_cookie *);
 void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *);
-int mem_cgroup_scan_tasks(struct mem_cgroup *,
-			  int (*)(struct task_struct *, void *), void *);
+void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
+			   int (*)(struct task_struct *, void *), void *arg);
 
 static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
 {
@@ -861,8 +857,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec)
  * parent_mem_cgroup - find the accounting parent of a memcg
  * @memcg: memcg whose parent to find
  *
- * Returns the parent memcg, or NULL if this is the root or the memory
- * controller is in legacy no-hierarchy mode.
+ * Returns the parent memcg, or NULL if this is the root.
  */
 static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg)
 {
@@ -914,7 +909,13 @@ unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec,
 	return READ_ONCE(mz->lru_zone_size[zone_idx][lru]);
 }
 
-void mem_cgroup_handle_over_high(void);
+void __mem_cgroup_handle_over_high(gfp_t gfp_mask);
+
+static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask)
+{
+	if (unlikely(current->memcg_nr_pages_over_high))
+		__mem_cgroup_handle_over_high(gfp_mask);
+}
 
 unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg);
 
@@ -925,65 +926,16 @@ void mem_cgroup_print_oom_context(struct mem_cgroup *memcg,
 
 void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg);
 
-static inline void mem_cgroup_enter_user_fault(void)
-{
-	WARN_ON(current->in_user_fault);
-	current->in_user_fault = 1;
-}
-
-static inline void mem_cgroup_exit_user_fault(void)
-{
-	WARN_ON(!current->in_user_fault);
-	current->in_user_fault = 0;
-}
-
-static inline bool task_in_memcg_oom(struct task_struct *p)
-{
-	return p->memcg_in_oom;
-}
-
-bool mem_cgroup_oom_synchronize(bool wait);
 struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim,
 					    struct mem_cgroup *oom_domain);
 void mem_cgroup_print_oom_group(struct mem_cgroup *memcg);
 
-void folio_memcg_lock(struct folio *folio);
-void folio_memcg_unlock(struct folio *folio);
-void lock_page_memcg(struct page *page);
-void unlock_page_memcg(struct page *page);
-
-void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val);
-
-/* try to stablize folio_memcg() for all the pages in a memcg */
-static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
-{
-	rcu_read_lock();
-
-	if (mem_cgroup_disabled() || !atomic_read(&memcg->moving_account))
-		return true;
-
-	rcu_read_unlock();
-	return false;
-}
-
-static inline void mem_cgroup_unlock_pages(void)
-{
-	rcu_read_unlock();
-}
-
 /* idx can be of type enum memcg_stat_item or node_stat_item */
-static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   int idx, int val)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_memcg_state(memcg, idx, val);
-	local_irq_restore(flags);
-}
+void mod_memcg_state(struct mem_cgroup *memcg,
+		     enum memcg_stat_item idx, int val);
 
 static inline void mod_memcg_page_state(struct page *page,
-					int idx, int val)
+					enum memcg_stat_item idx, int val)
 {
 	struct mem_cgroup *memcg;
 
@@ -991,101 +943,24 @@ static inline void mod_memcg_page_state(struct page *page,
 		return;
 
 	rcu_read_lock();
-	memcg = page_memcg(page);
+	memcg = folio_memcg(page_folio(page));
 	if (memcg)
 		mod_memcg_state(memcg, idx, val);
 	rcu_read_unlock();
 }
 
 unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx);
+unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx);
+unsigned long lruvec_page_state_local(struct lruvec *lruvec,
+				      enum node_stat_item idx);
 
-static inline unsigned long lruvec_page_state(struct lruvec *lruvec,
-					      enum node_stat_item idx)
-{
-	struct mem_cgroup_per_node *pn;
-	long x;
-
-	if (mem_cgroup_disabled())
-		return node_page_state(lruvec_pgdat(lruvec), idx);
-
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	x = READ_ONCE(pn->lruvec_stats.state[idx]);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
-
-static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
-						    enum node_stat_item idx)
-{
-	struct mem_cgroup_per_node *pn;
-	long x = 0;
-	int cpu;
-
-	if (mem_cgroup_disabled())
-		return node_page_state(lruvec_pgdat(lruvec), idx);
-
-	pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
-	for_each_possible_cpu(cpu)
-		x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
-#ifdef CONFIG_SMP
-	if (x < 0)
-		x = 0;
-#endif
-	return x;
-}
-
-void mem_cgroup_flush_stats(void);
-void mem_cgroup_flush_stats_ratelimited(void);
-
-void __mod_memcg_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx,
-			      int val);
-void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
+void mem_cgroup_flush_stats(struct mem_cgroup *memcg);
+void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg);
 
-static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
-					 int val)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_lruvec_kmem_state(p, idx, val);
-	local_irq_restore(flags);
-}
-
-static inline void mod_memcg_lruvec_state(struct lruvec *lruvec,
-					  enum node_stat_item idx, int val)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__mod_memcg_lruvec_state(lruvec, idx, val);
-	local_irq_restore(flags);
-}
+void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val);
 
-void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
-			  unsigned long count);
-
-static inline void count_memcg_events(struct mem_cgroup *memcg,
-				      enum vm_event_item idx,
-				      unsigned long count)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	__count_memcg_events(memcg, idx, count);
-	local_irq_restore(flags);
-}
-
-static inline void count_memcg_page_event(struct page *page,
-					  enum vm_event_item idx)
-{
-	struct mem_cgroup *memcg = page_memcg(page);
-
-	if (memcg)
-		count_memcg_events(memcg, idx, 1);
-}
+void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx,
+			unsigned long count);
 
 static inline void count_memcg_folio_events(struct folio *folio,
 		enum vm_event_item idx, unsigned long nr)
@@ -1096,8 +971,8 @@ static inline void count_memcg_folio_events(struct folio *folio,
 		count_memcg_events(memcg, idx, nr);
 }
 
-static inline void count_memcg_event_mm(struct mm_struct *mm,
-					enum vm_event_item idx)
+static inline void count_memcg_events_mm(struct mm_struct *mm,
+					enum vm_event_item idx, unsigned long count)
 {
 	struct mem_cgroup *memcg;
 
@@ -1107,33 +982,23 @@ static inline void count_memcg_event_mm(struct mm_struct *mm,
 	rcu_read_lock();
 	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
 	if (likely(memcg))
-		count_memcg_events(memcg, idx, 1);
+		count_memcg_events(memcg, idx, count);
 	rcu_read_unlock();
 }
 
-static inline void memcg_memory_event(struct mem_cgroup *memcg,
-				      enum memcg_memory_event event)
+static inline void count_memcg_event_mm(struct mm_struct *mm,
+					enum vm_event_item idx)
 {
-	bool swap_event = event == MEMCG_SWAP_HIGH || event == MEMCG_SWAP_MAX ||
-			  event == MEMCG_SWAP_FAIL;
-
-	atomic_long_inc(&memcg->memory_events_local[event]);
-	if (!swap_event)
-		cgroup_file_notify(&memcg->events_local_file);
+	count_memcg_events_mm(mm, idx, 1);
+}
 
-	do {
-		atomic_long_inc(&memcg->memory_events[event]);
-		if (swap_event)
-			cgroup_file_notify(&memcg->swap_events_file);
-		else
-			cgroup_file_notify(&memcg->events_file);
+void __memcg_memory_event(struct mem_cgroup *memcg,
+			  enum memcg_memory_event event, bool allow_spinning);
 
-		if (!cgroup_subsys_on_dfl(memory_cgrp_subsys))
-			break;
-		if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS)
-			break;
-	} while ((memcg = parent_mem_cgroup(memcg)) &&
-		 !mem_cgroup_is_root(memcg));
+static inline void memcg_memory_event(struct mem_cgroup *memcg,
+				      enum memcg_memory_event event)
+{
+	__memcg_memory_event(memcg, event, true);
 }
 
 static inline void memcg_memory_event_mm(struct mm_struct *mm,
@@ -1151,39 +1016,55 @@ static inline void memcg_memory_event_mm(struct mm_struct *mm,
 	rcu_read_unlock();
 }
 
-void split_page_memcg(struct page *head, unsigned int nr);
+void split_page_memcg(struct page *first, unsigned order);
+void folio_split_memcg_refs(struct folio *folio, unsigned old_order,
+		unsigned new_order);
+
+static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
+{
+	struct mem_cgroup *memcg;
+	u64 id;
+
+	if (mem_cgroup_disabled())
+		return 0;
 
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-						gfp_t gfp_mask,
-						unsigned long *total_scanned);
+	rcu_read_lock();
+	memcg = mem_cgroup_from_task(rcu_dereference(mm->owner));
+	if (!memcg)
+		memcg = root_mem_cgroup;
+	id = cgroup_id(memcg->css.cgroup);
+	rcu_read_unlock();
+	return id;
+}
 
+extern int mem_cgroup_init(void);
 #else /* CONFIG_MEMCG */
 
 #define MEM_CGROUP_ID_SHIFT	0
-#define MEM_CGROUP_ID_MAX	0
+
+#define root_mem_cgroup		(NULL)
 
 static inline struct mem_cgroup *folio_memcg(struct folio *folio)
 {
 	return NULL;
 }
 
-static inline struct mem_cgroup *page_memcg(struct page *page)
+static inline bool folio_memcg_charged(struct folio *folio)
 {
-	return NULL;
+	return false;
 }
 
-static inline struct mem_cgroup *folio_memcg_rcu(struct folio *folio)
+static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
 {
-	WARN_ON_ONCE(!rcu_read_lock_held());
 	return NULL;
 }
 
-static inline struct mem_cgroup *folio_memcg_check(struct folio *folio)
+static inline struct mem_cgroup *page_memcg_check(struct page *page)
 {
 	return NULL;
 }
 
-static inline struct mem_cgroup *page_memcg_check(struct page *page)
+static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg)
 {
 	return NULL;
 }
@@ -1254,21 +1135,27 @@ static inline int mem_cgroup_charge(struct folio *folio,
 	return 0;
 }
 
+static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp)
+{
+        return 0;
+}
+
 static inline int mem_cgroup_swapin_charge_folio(struct folio *folio,
 			struct mm_struct *mm, gfp_t gfp, swp_entry_t entry)
 {
 	return 0;
 }
 
-static inline void mem_cgroup_swapin_uncharge_swap(swp_entry_t entry)
+static inline void mem_cgroup_uncharge(struct folio *folio)
 {
 }
 
-static inline void mem_cgroup_uncharge(struct folio *folio)
+static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios)
 {
 }
 
-static inline void mem_cgroup_uncharge_list(struct list_head *page_list)
+static inline void mem_cgroup_replace_folio(struct folio *old,
+		struct folio *new)
 {
 }
 
@@ -1309,12 +1196,26 @@ static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 	return NULL;
 }
 
+static inline struct mem_cgroup *get_mem_cgroup_from_current(void)
+{
+	return NULL;
+}
+
+static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio)
+{
+	return NULL;
+}
+
 static inline
 struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css)
 {
 	return NULL;
 }
 
+static inline void obj_cgroup_get(struct obj_cgroup *objcg)
+{
+}
+
 static inline void obj_cgroup_put(struct obj_cgroup *objcg)
 {
 }
@@ -1324,6 +1225,11 @@ static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg)
 	return true;
 }
 
+static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg)
+{
+	return true;
+}
+
 static inline void mem_cgroup_put(struct mem_cgroup *memcg)
 {
 }
@@ -1366,10 +1272,9 @@ static inline void mem_cgroup_iter_break(struct mem_cgroup *root,
 {
 }
 
-static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
+static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg,
 		int (*fn)(struct task_struct *, void *), void *arg)
 {
-	return 0;
 }
 
 static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg)
@@ -1438,56 +1343,10 @@ mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg)
 {
 }
 
-static inline void lock_page_memcg(struct page *page)
+static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask)
 {
 }
 
-static inline void unlock_page_memcg(struct page *page)
-{
-}
-
-static inline void folio_memcg_lock(struct folio *folio)
-{
-}
-
-static inline void folio_memcg_unlock(struct folio *folio)
-{
-}
-
-static inline bool mem_cgroup_trylock_pages(struct mem_cgroup *memcg)
-{
-	/* to match folio_memcg_rcu() */
-	rcu_read_lock();
-	return true;
-}
-
-static inline void mem_cgroup_unlock_pages(void)
-{
-	rcu_read_unlock();
-}
-
-static inline void mem_cgroup_handle_over_high(void)
-{
-}
-
-static inline void mem_cgroup_enter_user_fault(void)
-{
-}
-
-static inline void mem_cgroup_exit_user_fault(void)
-{
-}
-
-static inline bool task_in_memcg_oom(struct task_struct *p)
-{
-	return false;
-}
-
-static inline bool mem_cgroup_oom_synchronize(bool wait)
-{
-	return false;
-}
-
 static inline struct mem_cgroup *mem_cgroup_get_oom_group(
 	struct task_struct *victim, struct mem_cgroup *oom_domain)
 {
@@ -1498,20 +1357,14 @@ static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg)
 {
 }
 
-static inline void __mod_memcg_state(struct mem_cgroup *memcg,
-				     int idx,
-				     int nr)
-{
-}
-
 static inline void mod_memcg_state(struct mem_cgroup *memcg,
-				   int idx,
+				   enum memcg_stat_item idx,
 				   int nr)
 {
 }
 
 static inline void mod_memcg_page_state(struct page *page,
-					int idx, int val)
+					enum memcg_stat_item idx, int val)
 {
 }
 
@@ -1532,25 +1385,12 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
 	return node_page_state(lruvec_pgdat(lruvec), idx);
 }
 
-static inline void mem_cgroup_flush_stats(void)
-{
-}
-
-static inline void mem_cgroup_flush_stats_ratelimited(void)
-{
-}
-
-static inline void __mod_memcg_lruvec_state(struct lruvec *lruvec,
-					    enum node_stat_item idx, int val)
+static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg)
 {
 }
 
-static inline void __mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
-					   int val)
+static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg)
 {
-	struct page *page = virt_to_head_page(p);
-
-	__mod_node_page_state(page_pgdat(page), idx, val);
 }
 
 static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
@@ -1562,24 +1402,18 @@ static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx,
 }
 
 static inline void count_memcg_events(struct mem_cgroup *memcg,
-				      enum vm_event_item idx,
-				      unsigned long count)
-{
-}
-
-static inline void __count_memcg_events(struct mem_cgroup *memcg,
 					enum vm_event_item idx,
 					unsigned long count)
 {
 }
 
-static inline void count_memcg_page_event(struct page *page,
-					  int idx)
+static inline void count_memcg_folio_events(struct folio *folio,
+		enum vm_event_item idx, unsigned long nr)
 {
 }
 
-static inline void count_memcg_folio_events(struct folio *folio,
-		enum vm_event_item idx, unsigned long nr)
+static inline void count_memcg_events_mm(struct mm_struct *mm,
+					enum vm_event_item idx, unsigned long count)
 {
 }
 
@@ -1588,28 +1422,35 @@ void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx)
 {
 }
 
-static inline void split_page_memcg(struct page *head, unsigned int nr)
+static inline void split_page_memcg(struct page *first, unsigned order)
 {
 }
 
-static inline
-unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
-					    gfp_t gfp_mask,
-					    unsigned long *total_scanned)
+static inline void folio_split_memcg_refs(struct folio *folio,
+		unsigned old_order, unsigned new_order)
 {
-	return 0;
 }
-#endif /* CONFIG_MEMCG */
 
-static inline void __inc_lruvec_kmem_state(void *p, enum node_stat_item idx)
+static inline u64 cgroup_id_from_mm(struct mm_struct *mm)
 {
-	__mod_lruvec_kmem_state(p, idx, 1);
+	return 0;
 }
 
-static inline void __dec_lruvec_kmem_state(void *p, enum node_stat_item idx)
-{
-	__mod_lruvec_kmem_state(p, idx, -1);
-}
+static inline int mem_cgroup_init(void) { return 0; }
+#endif /* CONFIG_MEMCG */
+
+/*
+ * Extended information for slab objects stored as an array in page->memcg_data
+ * if MEMCG_DATA_OBJEXTS is set.
+ */
+struct slabobj_ext {
+#ifdef CONFIG_MEMCG
+	struct obj_cgroup *objcg;
+#endif
+#ifdef CONFIG_MEM_ALLOC_PROFILING
+	union codetag_ref ref;
+#endif
+} __aligned(8);
 
 static inline struct lruvec *parent_lruvec(struct lruvec *lruvec)
 {
@@ -1640,7 +1481,7 @@ static inline void unlock_page_lruvec_irqrestore(struct lruvec *lruvec,
 	spin_unlock_irqrestore(&lruvec->lru_lock, flags);
 }
 
-/* Test requires a stable page->memcg binding, see page_memcg() */
+/* Test requires a stable folio->memcg binding, see folio_memcg() */
 static inline bool folio_matches_lruvec(struct folio *folio,
 		struct lruvec *lruvec)
 {
@@ -1662,18 +1503,18 @@ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio,
 	return folio_lruvec_lock_irq(folio);
 }
 
-/* Don't lock again iff page's lruvec locked */
-static inline struct lruvec *folio_lruvec_relock_irqsave(struct folio *folio,
-		struct lruvec *locked_lruvec, unsigned long *flags)
+/* Don't lock again iff folio's lruvec locked */
+static inline void folio_lruvec_relock_irqsave(struct folio *folio,
+		struct lruvec **lruvecp, unsigned long *flags)
 {
-	if (locked_lruvec) {
-		if (folio_matches_lruvec(folio, locked_lruvec))
-			return locked_lruvec;
+	if (*lruvecp) {
+		if (folio_matches_lruvec(folio, *lruvecp))
+			return;
 
-		unlock_page_lruvec_irqrestore(locked_lruvec, *flags);
+		unlock_page_lruvec_irqrestore(*lruvecp, *flags);
 	}
 
-	return folio_lruvec_lock_irqsave(folio, flags);
+	*lruvecp = folio_lruvec_lock_irqsave(folio, flags);
 }
 
 #ifdef CONFIG_CGROUP_WRITEBACK
@@ -1728,51 +1569,124 @@ static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb)
 #endif	/* CONFIG_CGROUP_WRITEBACK */
 
 struct sock;
-bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages,
-			     gfp_t gfp_mask);
-void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages);
 #ifdef CONFIG_MEMCG
 extern struct static_key_false memcg_sockets_enabled_key;
 #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
+
 void mem_cgroup_sk_alloc(struct sock *sk);
 void mem_cgroup_sk_free(struct sock *sk);
-static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
+void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk);
+bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages,
+			  gfp_t gfp_mask);
+void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages);
+
+#if BITS_PER_LONG < 64
+static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg)
 {
-	if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure)
-		return true;
+	u64 val = get_jiffies_64() + HZ;
+	unsigned long flags;
+
+	write_seqlock_irqsave(&memcg->socket_pressure_seqlock, flags);
+	memcg->socket_pressure = val;
+	write_sequnlock_irqrestore(&memcg->socket_pressure_seqlock, flags);
+}
+
+static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg)
+{
+	unsigned int seq;
+	u64 val;
+
 	do {
-		if (time_before(jiffies, READ_ONCE(memcg->socket_pressure)))
-			return true;
-	} while ((memcg = parent_mem_cgroup(memcg)));
-	return false;
+		seq = read_seqbegin(&memcg->socket_pressure_seqlock);
+		val = memcg->socket_pressure;
+	} while (read_seqretry(&memcg->socket_pressure_seqlock, seq));
+
+	return val;
+}
+#else
+static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg)
+{
+	WRITE_ONCE(memcg->socket_pressure, jiffies + HZ);
 }
 
+static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg)
+{
+	return READ_ONCE(memcg->socket_pressure);
+}
+#endif
+
 int alloc_shrinker_info(struct mem_cgroup *memcg);
 void free_shrinker_info(struct mem_cgroup *memcg);
 void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id);
 void reparent_shrinker_deferred(struct mem_cgroup *memcg);
+
+static inline int shrinker_id(struct shrinker *shrinker)
+{
+	return shrinker->id;
+}
 #else
 #define mem_cgroup_sockets_enabled 0
-static inline void mem_cgroup_sk_alloc(struct sock *sk) { };
-static inline void mem_cgroup_sk_free(struct sock *sk) { };
-static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
+
+static inline void mem_cgroup_sk_alloc(struct sock *sk)
+{
+}
+
+static inline void mem_cgroup_sk_free(struct sock *sk)
+{
+}
+
+static inline void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk)
+{
+}
+
+static inline bool mem_cgroup_sk_charge(const struct sock *sk,
+					unsigned int nr_pages,
+					gfp_t gfp_mask)
 {
 	return false;
 }
 
+static inline void mem_cgroup_sk_uncharge(const struct sock *sk,
+					  unsigned int nr_pages)
+{
+}
+
 static inline void set_shrinker_bit(struct mem_cgroup *memcg,
 				    int nid, int shrinker_id)
 {
 }
+
+static inline int shrinker_id(struct shrinker *shrinker)
+{
+	return -1;
+}
 #endif
 
-#ifdef CONFIG_MEMCG_KMEM
+#ifdef CONFIG_MEMCG
 bool mem_cgroup_kmem_disabled(void);
 int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order);
 void __memcg_kmem_uncharge_page(struct page *page, int order);
 
-struct obj_cgroup *get_obj_cgroup_from_current(void);
-struct obj_cgroup *get_obj_cgroup_from_page(struct page *page);
+/*
+ * The returned objcg pointer is safe to use without additional
+ * protection within a scope. The scope is defined either by
+ * the current task (similar to the "current" global variable)
+ * or by set_active_memcg() pair.
+ * Please, use obj_cgroup_get() to get a reference if the pointer
+ * needs to be used outside of the local scope.
+ */
+struct obj_cgroup *current_obj_cgroup(void);
+struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio);
+
+static inline struct obj_cgroup *get_obj_cgroup_from_current(void)
+{
+	struct obj_cgroup *objcg = current_obj_cgroup();
+
+	if (objcg)
+		obj_cgroup_get(objcg);
+
+	return objcg;
+}
 
 int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size);
 void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size);
@@ -1813,11 +1727,11 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 	return memcg ? memcg->kmemcg_id : -1;
 }
 
-struct mem_cgroup *mem_cgroup_from_obj(void *p);
 struct mem_cgroup *mem_cgroup_from_slab_obj(void *p);
 
-static inline void count_objcg_event(struct obj_cgroup *objcg,
-				     enum vm_event_item idx)
+static inline void count_objcg_events(struct obj_cgroup *objcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
 {
 	struct mem_cgroup *memcg;
 
@@ -1826,10 +1740,19 @@ static inline void count_objcg_event(struct obj_cgroup *objcg,
 
 	rcu_read_lock();
 	memcg = obj_cgroup_memcg(objcg);
-	count_memcg_events(memcg, idx, 1);
+	count_memcg_events(memcg, idx, count);
 	rcu_read_unlock();
 }
 
+bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid);
+
+void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg);
+
+static inline bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return memcg ? css_is_dying(&memcg->css) : false;
+}
+
 #else
 static inline bool mem_cgroup_kmem_disabled(void)
 {
@@ -1856,7 +1779,7 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order)
 {
 }
 
-static inline struct obj_cgroup *get_obj_cgroup_from_page(struct page *page)
+static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio)
 {
 	return NULL;
 }
@@ -1876,27 +1799,42 @@ static inline int memcg_kmem_id(struct mem_cgroup *memcg)
 	return -1;
 }
 
-static inline struct mem_cgroup *mem_cgroup_from_obj(void *p)
+static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
 {
 	return NULL;
 }
 
-static inline struct mem_cgroup *mem_cgroup_from_slab_obj(void *p)
+static inline void count_objcg_events(struct obj_cgroup *objcg,
+				      enum vm_event_item idx,
+				      unsigned long count)
 {
-	return NULL;
 }
 
-static inline void count_objcg_event(struct obj_cgroup *objcg,
-				     enum vm_event_item idx)
+static inline ino_t page_cgroup_ino(struct page *page)
+{
+	return 0;
+}
+
+static inline bool mem_cgroup_node_allowed(struct mem_cgroup *memcg, int nid)
+{
+	return true;
+}
+
+static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg)
 {
 }
 
-#endif /* CONFIG_MEMCG_KMEM */
+static inline bool memcg_is_dying(struct mem_cgroup *memcg)
+{
+	return false;
+}
+#endif /* CONFIG_MEMCG */
 
-#if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+#if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP)
 bool obj_cgroup_may_zswap(struct obj_cgroup *objcg);
 void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size);
 void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size);
+bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg);
 #else
 static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg)
 {
@@ -1910,6 +1848,78 @@ static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg,
 					     size_t size)
 {
 }
+static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+{
+	/* if zswap is disabled, do not block pages going to the swapping device */
+	return true;
+}
 #endif
 
+
+/* Cgroup v1-related declarations */
+
+#ifdef CONFIG_MEMCG_V1
+unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					gfp_t gfp_mask,
+					unsigned long *total_scanned);
+
+bool mem_cgroup_oom_synchronize(bool wait);
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return p->memcg_in_oom;
+}
+
+static inline void mem_cgroup_enter_user_fault(void)
+{
+	WARN_ON(current->in_user_fault);
+	current->in_user_fault = 1;
+}
+
+static inline void mem_cgroup_exit_user_fault(void)
+{
+	WARN_ON(!current->in_user_fault);
+	current->in_user_fault = 0;
+}
+
+void memcg1_swapout(struct folio *folio, swp_entry_t entry);
+void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages);
+
+#else /* CONFIG_MEMCG_V1 */
+static inline
+unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order,
+					gfp_t gfp_mask,
+					unsigned long *total_scanned)
+{
+	return 0;
+}
+
+static inline bool task_in_memcg_oom(struct task_struct *p)
+{
+	return false;
+}
+
+static inline bool mem_cgroup_oom_synchronize(bool wait)
+{
+	return false;
+}
+
+static inline void mem_cgroup_enter_user_fault(void)
+{
+}
+
+static inline void mem_cgroup_exit_user_fault(void)
+{
+}
+
+static inline void memcg1_swapout(struct folio *folio, swp_entry_t entry)
+{
+}
+
+static inline void memcg1_swapin(swp_entry_t entry, unsigned int nr_pages)
+{
+}
+
+#endif /* CONFIG_MEMCG_V1 */
+
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index e7abf6fa4c52..cc74de3dbcfe 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -4,13 +4,33 @@
 
 #include <linux/file.h>
 
+#define MEMFD_ANON_NAME "[memfd]"
+
 #ifdef CONFIG_MEMFD_CREATE
 extern long memfd_fcntl(struct file *file, unsigned int cmd, unsigned int arg);
+struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
+/*
+ * Check for any existing seals on mmap, return an error if access is denied due
+ * to sealing, or 0 otherwise.
+ *
+ * We also update VMA flags if appropriate by manipulating the VMA flags pointed
+ * to by vm_flags_ptr.
+ */
+int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr);
 #else
 static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
 {
 	return -EINVAL;
 }
+static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
+{
+	return ERR_PTR(-EINVAL);
+}
+static inline int memfd_check_seals_mmap(struct file *file,
+					 vm_flags_t *vm_flags_ptr)
+{
+	return 0;
+}
 #endif
 
 #endif /* __LINUX_MEMFD_H */
diff --git a/include/linux/memory-failure.h b/include/linux/memory-failure.h
new file mode 100644
index 000000000000..bc326503d2d2
--- /dev/null
+++ b/include/linux/memory-failure.h
@@ -0,0 +1,17 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_MEMORY_FAILURE_H
+#define _LINUX_MEMORY_FAILURE_H
+
+#include <linux/interval_tree.h>
+
+struct pfn_address_space;
+
+struct pfn_address_space {
+	struct interval_tree_node node;
+	struct address_space *mapping;
+};
+
+int register_pfn_address_space(struct pfn_address_space *pfn_space);
+void unregister_pfn_address_space(struct pfn_address_space *pfn_space);
+
+#endif /* _LINUX_MEMORY_FAILURE_H */
diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index fc9647b1b4f9..7a805796fcfd 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -6,6 +6,7 @@
 #include <linux/nodemask.h>
 #include <linux/kref.h>
 #include <linux/mmzone.h>
+#include <linux/notifier.h>
 /*
  * Each tier cover a abstrace distance chunk size of 128
  */
@@ -17,12 +18,14 @@
  * adistance value (slightly faster) than default DRAM adistance to be part of
  * the same memory tier.
  */
-#define MEMTIER_ADISTANCE_DRAM	((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
+#define MEMTIER_ADISTANCE_DRAM	((4L * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
 
 struct memory_tier;
 struct memory_dev_type {
 	/* list of memory types that are part of same tier as this type */
-	struct list_head tier_sibiling;
+	struct list_head tier_sibling;
+	/* list of memory types that are managed by one driver */
+	struct list_head list;
 	/* abstract distance for this specific memory type */
 	int adistance;
 	/* Nodes of same abstract distance */
@@ -30,12 +33,25 @@ struct memory_dev_type {
 	struct kref kref;
 };
 
+struct access_coordinate;
+
 #ifdef CONFIG_NUMA
 extern bool numa_demotion_enabled;
+extern struct memory_dev_type *default_dram_type;
+extern nodemask_t default_dram_nodes;
 struct memory_dev_type *alloc_memory_type(int adistance);
-void destroy_memory_type(struct memory_dev_type *memtype);
+void put_memory_type(struct memory_dev_type *memtype);
 void init_node_memory_type(int node, struct memory_dev_type *default_type);
 void clear_node_memory_type(int node, struct memory_dev_type *memtype);
+int register_mt_adistance_algorithm(struct notifier_block *nb);
+int unregister_mt_adistance_algorithm(struct notifier_block *nb);
+int mt_calc_adistance(int node, int *adist);
+int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
+			     const char *source);
+int mt_perf_to_adistance(struct access_coordinate *perf, int *adist);
+struct memory_dev_type *mt_find_alloc_memory_type(int adist,
+						  struct list_head *memory_types);
+void mt_put_memory_types(struct list_head *memory_types);
 #ifdef CONFIG_MIGRATION
 int next_demotion_node(int node);
 void node_get_allowed_targets(pg_data_t *pgdat, nodemask_t *targets);
@@ -60,6 +76,8 @@ static inline bool node_is_toptier(int node)
 #else
 
 #define numa_demotion_enabled	false
+#define default_dram_type	NULL
+#define default_dram_nodes	NODE_MASK_NONE
 /*
  * CONFIG_NUMA implementation returns non NULL error.
  */
@@ -68,7 +86,7 @@ static inline struct memory_dev_type *alloc_memory_type(int adistance)
 	return NULL;
 }
 
-static inline void destroy_memory_type(struct memory_dev_type *memtype)
+static inline void put_memory_type(struct memory_dev_type *memtype)
 {
 
 }
@@ -97,5 +115,41 @@ static inline bool node_is_toptier(int node)
 {
 	return true;
 }
+
+static inline int register_mt_adistance_algorithm(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int unregister_mt_adistance_algorithm(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int mt_calc_adistance(int node, int *adist)
+{
+	return NOTIFY_DONE;
+}
+
+static inline int mt_set_default_dram_perf(int nid, struct access_coordinate *perf,
+					   const char *source)
+{
+	return -EIO;
+}
+
+static inline int mt_perf_to_adistance(struct access_coordinate *perf, int *adist)
+{
+	return -EIO;
+}
+
+static inline struct memory_dev_type *mt_find_alloc_memory_type(int adist,
+								struct list_head *memory_types)
+{
+	return NULL;
+}
+
+static inline void mt_put_memory_types(struct list_head *memory_types)
+{
+}
 #endif	/* CONFIG_NUMA */
 #endif  /* _LINUX_MEMORY_TIERS_H */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 31343566c221..faeaa921e55b 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -25,7 +25,7 @@
 /**
  * struct memory_group - a logical group of memory blocks
  * @nid: The node id for all memory blocks inside the memory group.
- * @blocks: List of all memory blocks belonging to this memory group.
+ * @memory_blocks: List of all memory blocks belonging to this memory group.
  * @present_kernel_pages: Present (online) memory outside ZONE_MOVABLE of this
  *			  memory group.
  * @present_movable_pages: Present (online) memory in ZONE_MOVABLE of this
@@ -64,9 +64,19 @@ struct memory_group {
 	};
 };
 
+enum memory_block_state {
+	/* These states are exposed to userspace as text strings in sysfs */
+	MEM_ONLINE,		/* exposed to userspace */
+	MEM_GOING_OFFLINE,	/* exposed to userspace */
+	MEM_OFFLINE,		/* exposed to userspace */
+	MEM_GOING_ONLINE,
+	MEM_CANCEL_ONLINE,
+	MEM_CANCEL_OFFLINE,
+};
+
 struct memory_block {
 	unsigned long start_section_nr;
-	unsigned long state;		/* serialized by the dev->lock */
+	enum memory_block_state state;	/* serialized by the dev->lock */
 	int online_type;		/* for passing data to online routine */
 	int nid;			/* NID for this memory block */
 	/*
@@ -77,11 +87,7 @@ struct memory_block {
 	 */
 	struct zone *zone;
 	struct device dev;
-	/*
-	 * Number of vmemmap pages. These pages
-	 * lay at the beginning of the memory block.
-	 */
-	unsigned long nr_vmemmap_pages;
+	struct vmem_altmap *altmap;
 	struct memory_group *group;	/* group (if any) for this block */
 	struct list_head group_next;	/* next block inside memory group */
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
@@ -93,31 +99,22 @@ int arch_get_memory_phys_device(unsigned long start_pfn);
 unsigned long memory_block_size_bytes(void);
 int set_memory_block_size_order(unsigned int order);
 
-/* These states are exposed to userspace as text strings in sysfs */
-#define	MEM_ONLINE		(1<<0) /* exposed to userspace */
-#define	MEM_GOING_OFFLINE	(1<<1) /* exposed to userspace */
-#define	MEM_OFFLINE		(1<<2) /* exposed to userspace */
-#define	MEM_GOING_ONLINE	(1<<3)
-#define	MEM_CANCEL_ONLINE	(1<<4)
-#define	MEM_CANCEL_OFFLINE	(1<<5)
-
 struct memory_notify {
 	unsigned long start_pfn;
 	unsigned long nr_pages;
-	int status_change_nid_normal;
-	int status_change_nid;
 };
 
 struct notifier_block;
 struct mem_section;
 
 /*
- * Priorities for the hotplug memory callback routines (stored in decreasing
- * order in the callback chain)
+ * Priorities for the hotplug memory callback routines. Invoked from
+ * high to low. Higher priorities correspond to higher numbers.
  */
 #define DEFAULT_CALLBACK_PRI	0
 #define SLAB_CALLBACK_PRI	1
-#define HMAT_CALLBACK_PRI	2
+#define CXL_CALLBACK_PRI	5
+#define HMAT_CALLBACK_PRI	6
 #define MM_COMPUTE_BATCH_PRI	10
 #define CPUSET_CALLBACK_PRI	10
 #define MEMTIER_HOTPLUG_PRI	100
@@ -135,7 +132,7 @@ static inline int register_memory_notifier(struct notifier_block *nb)
 static inline void unregister_memory_notifier(struct notifier_block *nb)
 {
 }
-static inline int memory_notify(unsigned long val, void *v)
+static inline int memory_notify(enum memory_block_state state, void *v)
 {
 	return 0;
 }
@@ -143,15 +140,23 @@ static inline int hotplug_memory_notifier(notifier_fn_t fn, int pri)
 {
 	return 0;
 }
+static inline int memory_block_advise_max_size(unsigned long size)
+{
+	return -ENODEV;
+}
+static inline unsigned long memory_block_advised_max_size(void)
+{
+	return 0;
+}
 #else /* CONFIG_MEMORY_HOTPLUG */
 extern int register_memory_notifier(struct notifier_block *nb);
 extern void unregister_memory_notifier(struct notifier_block *nb);
 int create_memory_block_devices(unsigned long start, unsigned long size,
-				unsigned long vmemmap_pages,
+				int nid, struct vmem_altmap *altmap,
 				struct memory_group *group);
 void remove_memory_block_devices(unsigned long start, unsigned long size);
 extern void memory_dev_init(void);
-extern int memory_notify(unsigned long val, void *v);
+extern int memory_notify(enum memory_block_state state, void *v);
 extern struct memory_block *find_memory_block(unsigned long section_nr);
 typedef int (*walk_memory_blocks_func_t)(struct memory_block *, void *);
 extern int walk_memory_blocks(unsigned long start, unsigned long size,
@@ -165,16 +170,35 @@ struct memory_group *memory_group_find_by_id(int mgid);
 typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
 int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 			       struct memory_group *excluded, void *arg);
+struct memory_block *find_memory_block_by_id(unsigned long block_id);
 #define hotplug_memory_notifier(fn, pri) ({		\
 	static __meminitdata struct notifier_block fn##_mem_nb =\
 		{ .notifier_call = fn, .priority = pri };\
 	register_memory_notifier(&fn##_mem_nb);			\
 })
 
+extern int sections_per_block;
+
+static inline unsigned long memory_block_id(unsigned long section_nr)
+{
+	return section_nr / sections_per_block;
+}
+
+static inline unsigned long pfn_to_block_id(unsigned long pfn)
+{
+	return memory_block_id(pfn_to_section_nr(pfn));
+}
+
+static inline unsigned long phys_to_block_id(unsigned long phys)
+{
+	return pfn_to_block_id(PFN_DOWN(phys));
+}
+
 #ifdef CONFIG_NUMA
-void memory_block_add_nid(struct memory_block *mem, int nid,
-			  enum meminit_context context);
+void memory_block_add_nid_early(struct memory_block *mem, int nid);
 #endif /* CONFIG_NUMA */
+int memory_block_advise_max_size(unsigned long size);
+unsigned long memory_block_advised_max_size(void);
 #endif	/* CONFIG_MEMORY_HOTPLUG */
 
 /*
diff --git a/include/linux/memory/ti-aemif.h b/include/linux/memory/ti-aemif.h
new file mode 100644
index 000000000000..da94a9d985e7
--- /dev/null
+++ b/include/linux/memory/ti-aemif.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __MEMORY_TI_AEMIF_H
+#define __MEMORY_TI_AEMIF_H
+
+/**
+ * struct aemif_cs_timings: structure to hold CS timing configuration
+ * values are expressed in number of clock cycles - 1
+ * @ta: minimum turn around time
+ * @rhold: read hold width
+ * @rstrobe: read strobe width
+ * @rsetup: read setup width
+ * @whold: write hold width
+ * @wstrobe: write strobe width
+ * @wsetup: write setup width
+ */
+struct aemif_cs_timings {
+	u32	ta;
+	u32	rhold;
+	u32	rstrobe;
+	u32	rsetup;
+	u32	whold;
+	u32	wstrobe;
+	u32	wsetup;
+};
+
+struct aemif_device;
+
+int aemif_set_cs_timings(struct aemif_device *aemif, u8 cs, struct aemif_cs_timings *timings);
+int aemif_check_cs_timings(struct aemif_cs_timings *timings);
+
+#endif // __MEMORY_TI_AEMIF_H
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 04bc286eed42..f2f16cdd73ee 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -16,54 +16,6 @@ struct resource;
 struct vmem_altmap;
 struct dev_pagemap;
 
-#ifdef CONFIG_HAVE_ARCH_NODEDATA_EXTENSION
-/*
- * For supporting node-hotadd, we have to allocate a new pgdat.
- *
- * If an arch has generic style NODE_DATA(),
- * node_data[nid] = kzalloc() works well. But it depends on the architecture.
- *
- * In general, generic_alloc_nodedata() is used.
- *
- */
-extern pg_data_t *arch_alloc_nodedata(int nid);
-extern void arch_refresh_nodedata(int nid, pg_data_t *pgdat);
-
-#else /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
-
-#define arch_alloc_nodedata(nid)	generic_alloc_nodedata(nid)
-
-#ifdef CONFIG_NUMA
-/*
- * XXX: node aware allocation can't work well to get new node's memory at this time.
- *	Because, pgdat for the new node is not allocated/initialized yet itself.
- *	To use new node's memory, more consideration will be necessary.
- */
-#define generic_alloc_nodedata(nid)				\
-({								\
-	memblock_alloc(sizeof(*pgdat), SMP_CACHE_BYTES);	\
-})
-
-extern pg_data_t *node_data[];
-static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
-{
-	node_data[nid] = pgdat;
-}
-
-#else /* !CONFIG_NUMA */
-
-/* never called */
-static inline pg_data_t *generic_alloc_nodedata(int nid)
-{
-	BUG();
-	return NULL;
-}
-static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
-{
-}
-#endif /* CONFIG_NUMA */
-#endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 struct page *pfn_to_online_page(unsigned long pfn);
 
@@ -97,6 +49,8 @@ typedef int __bitwise mhp_t;
  * To do so, we will use the beginning of the hot-added range to build
  * the page tables for the memmap array that describes the entire range.
  * Only selected architectures support it with SPARSE_VMEMMAP.
+ * This is only a hint, the core kernel can decide to not do this based on
+ * different alignment checks.
  */
 #define MHP_MEMMAP_ON_MEMORY   ((__force mhp_t)BIT(1))
 /*
@@ -119,6 +73,7 @@ struct mhp_params {
 
 bool mhp_range_allowed(u64 start, u64 size, bool need_mapping);
 struct range mhp_get_pluggable_range(bool need_mapping);
+bool mhp_supports_memmap_on_memory(void);
 
 /*
  * Zone resizing functions
@@ -156,8 +111,8 @@ extern int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 extern void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages);
 extern int online_pages(unsigned long pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group);
-extern void __offline_isolated_pages(unsigned long start_pfn,
-				     unsigned long end_pfn);
+extern unsigned long __offline_isolated_pages(unsigned long start_pfn,
+		unsigned long end_pfn);
 
 typedef void (*online_page_callback_t)(struct page *page, unsigned int order);
 
@@ -173,8 +128,6 @@ extern u64 max_mem_size;
 
 extern int mhp_online_type_from_str(const char *str);
 
-/* Default online_type (MMOP_*) when new memory blocks are added. */
-extern int mhp_default_online_type;
 /* If movable_node boot option specified */
 extern bool movable_node_enabled;
 static inline bool movable_node_is_enabled(void)
@@ -260,6 +213,11 @@ static inline bool movable_node_is_enabled(void)
 	return false;
 }
 
+static inline bool mhp_supports_memmap_on_memory(void)
+{
+	return false;
+}
+
 static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {}
 static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {}
 static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {}
@@ -327,6 +285,9 @@ static inline void __remove_memory(u64 start, u64 size) {}
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+/* Default online_type (MMOP_*) when new memory blocks are added. */
+extern int mhp_get_default_online_type(void);
+extern void mhp_set_default_online_type(int online_type);
 extern void __ref free_area_init_core_hotplug(struct pglist_data *pgdat);
 extern int __add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
 extern int add_memory(int nid, u64 start, u64 size, mhp_t mhp_flags);
@@ -337,16 +298,16 @@ extern int add_memory_driver_managed(int nid, u64 start, u64 size,
 				     mhp_t mhp_flags);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 				   unsigned long nr_pages,
-				   struct vmem_altmap *altmap, int migratetype);
+				   struct vmem_altmap *altmap, int migratetype,
+				   bool isolate_pageblock);
 extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long start_pfn,
 				       unsigned long nr_pages);
 extern int sparse_add_section(int nid, unsigned long pfn,
 		unsigned long nr_pages, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
-extern void sparse_remove_section(struct mem_section *ms,
-		unsigned long pfn, unsigned long nr_pages,
-		unsigned long map_offset, struct vmem_altmap *altmap);
+extern void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
+				  struct vmem_altmap *altmap);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 extern struct zone *zone_for_pfn_range(int online_type, int nid,
@@ -355,7 +316,6 @@ extern struct zone *zone_for_pfn_range(int online_type, int nid,
 extern int arch_create_linear_mapping(int nid, u64 start, u64 size,
 				      struct mhp_params *params);
 void arch_remove_linear_mapping(u64 start, u64 size);
-extern bool mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index d232de7cdc56..0fe96f3ab3ef 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -11,12 +11,15 @@
 #include <linux/slab.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
+#include <linux/node.h>
 #include <linux/nodemask.h>
 #include <linux/pagemap.h>
 #include <uapi/linux/mempolicy.h>
 
 struct mm_struct;
 
+#define NO_INTERLEAVE_INDEX (-1UL)	/* use task il_prev for interleaving */
+
 #ifdef CONFIG_NUMA
 
 /*
@@ -45,7 +48,7 @@ struct mempolicy {
 	atomic_t refcnt;
 	unsigned short mode; 	/* See MPOL_* above */
 	unsigned short flags;	/* See set_mempolicy() MPOL_F_* above */
-	nodemask_t nodes;	/* interleave/bind/perfer */
+	nodemask_t nodes;	/* interleave/bind/preferred/etc */
 	int home_node;		/* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */
 
 	union {
@@ -89,8 +92,6 @@ static inline struct mempolicy *mpol_dup(struct mempolicy *pol)
 	return pol;
 }
 
-#define vma_policy(vma) ((vma)->vm_policy)
-
 static inline void mpol_get(struct mempolicy *pol)
 {
 	if (pol)
@@ -107,35 +108,30 @@ static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
 
 /*
  * Tree of shared policies for a shared memory region.
- * Maintain the policies in a pseudo mm that contains vmas. The vmas
- * carry the policy. As a special twist the pseudo mm is indexed in pages, not
- * bytes, so that we can work with shared memory segments bigger than
- * unsigned long.
  */
-
-struct sp_node {
-	struct rb_node nd;
-	unsigned long start, end;
-	struct mempolicy *policy;
-};
-
 struct shared_policy {
 	struct rb_root root;
 	rwlock_t lock;
 };
+struct sp_node {
+	struct rb_node nd;
+	pgoff_t start, end;
+	struct mempolicy *policy;
+};
 
 int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst);
 void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol);
-int mpol_set_shared_policy(struct shared_policy *info,
-				struct vm_area_struct *vma,
-				struct mempolicy *new);
-void mpol_free_shared_policy(struct shared_policy *p);
+int mpol_set_shared_policy(struct shared_policy *sp,
+			   struct vm_area_struct *vma, struct mempolicy *mpol);
+void mpol_free_shared_policy(struct shared_policy *sp);
 struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp,
-					    unsigned long idx);
+					    pgoff_t idx);
 
 struct mempolicy *get_task_policy(struct task_struct *p);
 struct mempolicy *__get_vma_policy(struct vm_area_struct *vma,
-		unsigned long addr);
+		unsigned long addr, pgoff_t *ilx);
+struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+		unsigned long addr, int order, pgoff_t *ilx);
 bool vma_policy_mof(struct vm_area_struct *vma);
 
 extern void numa_default_policy(void);
@@ -149,8 +145,6 @@ extern int huge_node(struct vm_area_struct *vma,
 extern bool init_nodemask_of_mempolicy(nodemask_t *mask);
 extern bool mempolicy_in_oom_domain(struct task_struct *tsk,
 				const nodemask_t *mask);
-extern nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy);
-
 extern unsigned int mempolicy_slab_node(void);
 
 extern enum zone_type policy_zone;
@@ -174,7 +168,8 @@ extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol);
 /* Check if a vma is migratable */
 extern bool vma_migratable(struct vm_area_struct *vma);
 
-extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long);
+int mpol_misplaced(struct folio *folio, struct vm_fault *vmf,
+					unsigned long addr);
 extern void mpol_put_task_policy(struct task_struct *);
 
 static inline bool mpol_is_preferred_many(struct mempolicy *pol)
@@ -184,16 +179,24 @@ static inline bool mpol_is_preferred_many(struct mempolicy *pol)
 
 extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone);
 
+extern int mempolicy_set_node_perf(unsigned int node,
+				   struct access_coordinate *coords);
+
 #else
 
 struct mempolicy {};
 
+static inline struct mempolicy *get_task_policy(struct task_struct *p)
+{
+	return NULL;
+}
+
 static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b)
 {
 	return true;
 }
 
-static inline void mpol_put(struct mempolicy *p)
+static inline void mpol_put(struct mempolicy *pol)
 {
 }
 
@@ -212,17 +215,22 @@ static inline void mpol_shared_policy_init(struct shared_policy *sp,
 {
 }
 
-static inline void mpol_free_shared_policy(struct shared_policy *p)
+static inline void mpol_free_shared_policy(struct shared_policy *sp)
 {
 }
 
 static inline struct mempolicy *
-mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
+mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx)
 {
 	return NULL;
 }
 
-#define vma_policy(vma) NULL
+static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma,
+				unsigned long addr, int order, pgoff_t *ilx)
+{
+	*ilx = 0;
+	return NULL;
+}
 
 static inline int
 vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst)
@@ -278,7 +286,8 @@ static inline int mpol_parse_str(char *str, struct mempolicy **mpol)
 }
 #endif
 
-static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma,
+static inline int mpol_misplaced(struct folio *folio,
+				 struct vm_fault *vmf,
 				 unsigned long address)
 {
 	return -1; /* no node preference */
diff --git a/include/linux/mempool.h b/include/linux/mempool.h
index 4aae6c06c5f2..e8e440e04a06 100644
--- a/include/linux/mempool.h
+++ b/include/linux/mempool.h
@@ -5,6 +5,8 @@
 #ifndef _LINUX_MEMPOOL_H
 #define _LINUX_MEMPOOL_H
 
+#include <linux/sched.h>
+#include <linux/alloc_tag.h>
 #include <linux/wait.h>
 #include <linux/compiler.h>
 
@@ -13,7 +15,7 @@ struct kmem_cache;
 typedef void * (mempool_alloc_t)(gfp_t gfp_mask, void *pool_data);
 typedef void (mempool_free_t)(void *element, void *pool_data);
 
-typedef struct mempool_s {
+typedef struct mempool {
 	spinlock_t lock;
 	int min_nr;		/* nr of elements at *elements */
 	int curr_nr;		/* Current nr of elements at *elements */
@@ -25,33 +27,53 @@ typedef struct mempool_s {
 	wait_queue_head_t wait;
 } mempool_t;
 
-static inline bool mempool_initialized(mempool_t *pool)
+static inline bool mempool_initialized(struct mempool *pool)
 {
 	return pool->elements != NULL;
 }
 
-static inline bool mempool_is_saturated(mempool_t *pool)
+static inline bool mempool_is_saturated(struct mempool *pool)
 {
 	return READ_ONCE(pool->curr_nr) >= pool->min_nr;
 }
 
-void mempool_exit(mempool_t *pool);
-int mempool_init_node(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
-		      mempool_free_t *free_fn, void *pool_data,
-		      gfp_t gfp_mask, int node_id);
-int mempool_init(mempool_t *pool, int min_nr, mempool_alloc_t *alloc_fn,
-		 mempool_free_t *free_fn, void *pool_data);
-
-extern mempool_t *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
-			mempool_free_t *free_fn, void *pool_data);
-extern mempool_t *mempool_create_node(int min_nr, mempool_alloc_t *alloc_fn,
-			mempool_free_t *free_fn, void *pool_data,
-			gfp_t gfp_mask, int nid);
-
-extern int mempool_resize(mempool_t *pool, int new_min_nr);
-extern void mempool_destroy(mempool_t *pool);
-extern void *mempool_alloc(mempool_t *pool, gfp_t gfp_mask) __malloc;
-extern void mempool_free(void *element, mempool_t *pool);
+void mempool_exit(struct mempool *pool);
+int mempool_init_node(struct mempool *pool, int min_nr,
+		mempool_alloc_t *alloc_fn, mempool_free_t *free_fn,
+		void *pool_data, gfp_t gfp_mask, int node_id);
+int mempool_init_noprof(struct mempool *pool, int min_nr,
+		mempool_alloc_t *alloc_fn, mempool_free_t *free_fn,
+		void *pool_data);
+#define mempool_init(...)						\
+	alloc_hooks(mempool_init_noprof(__VA_ARGS__))
+
+struct mempool *mempool_create(int min_nr, mempool_alloc_t *alloc_fn,
+		mempool_free_t *free_fn, void *pool_data);
+struct mempool *mempool_create_node_noprof(int min_nr,
+		mempool_alloc_t *alloc_fn, mempool_free_t *free_fn,
+		void *pool_data, gfp_t gfp_mask, int nid);
+#define mempool_create_node(...)					\
+	alloc_hooks(mempool_create_node_noprof(__VA_ARGS__))
+
+#define mempool_create(_min_nr, _alloc_fn, _free_fn, _pool_data)	\
+	mempool_create_node(_min_nr, _alloc_fn, _free_fn, _pool_data,	\
+			    GFP_KERNEL, NUMA_NO_NODE)
+
+int mempool_resize(struct mempool *pool, int new_min_nr);
+void mempool_destroy(struct mempool *pool);
+
+void *mempool_alloc_noprof(struct mempool *pool, gfp_t gfp_mask) __malloc;
+#define mempool_alloc(...)						\
+	alloc_hooks(mempool_alloc_noprof(__VA_ARGS__))
+int mempool_alloc_bulk_noprof(struct mempool *pool, void **elem,
+		unsigned int count, unsigned int allocated);
+#define mempool_alloc_bulk(...)						\
+	alloc_hooks(mempool_alloc_bulk_noprof(__VA_ARGS__))
+
+void *mempool_alloc_preallocated(struct mempool *pool) __malloc;
+void mempool_free(void *element, struct mempool *pool);
+unsigned int mempool_free_bulk(struct mempool *pool, void **elem,
+		unsigned int count);
 
 /*
  * A mempool_alloc_t and mempool_free_t that get the memory from
@@ -61,19 +83,10 @@ extern void mempool_free(void *element, mempool_t *pool);
 void *mempool_alloc_slab(gfp_t gfp_mask, void *pool_data);
 void mempool_free_slab(void *element, void *pool_data);
 
-static inline int
-mempool_init_slab_pool(mempool_t *pool, int min_nr, struct kmem_cache *kc)
-{
-	return mempool_init(pool, min_nr, mempool_alloc_slab,
-			    mempool_free_slab, (void *) kc);
-}
-
-static inline mempool_t *
-mempool_create_slab_pool(int min_nr, struct kmem_cache *kc)
-{
-	return mempool_create(min_nr, mempool_alloc_slab, mempool_free_slab,
-			      (void *) kc);
-}
+#define mempool_init_slab_pool(_pool, _min_nr, _kc)			\
+	mempool_init(_pool, (_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc))
+#define mempool_create_slab_pool(_min_nr, _kc)			\
+	mempool_create((_min_nr), mempool_alloc_slab, mempool_free_slab, (void *)(_kc))
 
 /*
  * a mempool_alloc_t and a mempool_free_t to kmalloc and kfree the
@@ -82,17 +95,12 @@ mempool_create_slab_pool(int min_nr, struct kmem_cache *kc)
 void *mempool_kmalloc(gfp_t gfp_mask, void *pool_data);
 void mempool_kfree(void *element, void *pool_data);
 
-static inline int mempool_init_kmalloc_pool(mempool_t *pool, int min_nr, size_t size)
-{
-	return mempool_init(pool, min_nr, mempool_kmalloc,
-			    mempool_kfree, (void *) size);
-}
-
-static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
-{
-	return mempool_create(min_nr, mempool_kmalloc, mempool_kfree,
-			      (void *) size);
-}
+#define mempool_init_kmalloc_pool(_pool, _min_nr, _size)		\
+	mempool_init(_pool, (_min_nr), mempool_kmalloc, mempool_kfree,	\
+		     (void *)(unsigned long)(_size))
+#define mempool_create_kmalloc_pool(_min_nr, _size)			\
+	mempool_create((_min_nr), mempool_kmalloc, mempool_kfree,	\
+		       (void *)(unsigned long)(_size))
 
 /*
  * A mempool_alloc_t and mempool_free_t for a simple page allocator that
@@ -101,16 +109,11 @@ static inline mempool_t *mempool_create_kmalloc_pool(int min_nr, size_t size)
 void *mempool_alloc_pages(gfp_t gfp_mask, void *pool_data);
 void mempool_free_pages(void *element, void *pool_data);
 
-static inline int mempool_init_page_pool(mempool_t *pool, int min_nr, int order)
-{
-	return mempool_init(pool, min_nr, mempool_alloc_pages,
-			    mempool_free_pages, (void *)(long)order);
-}
-
-static inline mempool_t *mempool_create_page_pool(int min_nr, int order)
-{
-	return mempool_create(min_nr, mempool_alloc_pages, mempool_free_pages,
-			      (void *)(long)order);
-}
+#define mempool_init_page_pool(_pool, _min_nr, _order)			\
+	mempool_init(_pool, (_min_nr), mempool_alloc_pages,		\
+		     mempool_free_pages, (void *)(long)(_order))
+#define mempool_create_page_pool(_min_nr, _order)			\
+	mempool_create((_min_nr), mempool_alloc_pages,			\
+		       mempool_free_pages, (void *)(long)(_order))
 
 #endif /* _LINUX_MEMPOOL_H */
diff --git a/include/linux/memregion.h b/include/linux/memregion.h
index c01321467789..a55f62cc5266 100644
--- a/include/linux/memregion.h
+++ b/include/linux/memregion.h
@@ -26,8 +26,10 @@ static inline void memregion_free(int id)
 
 /**
  * cpu_cache_invalidate_memregion - drop any CPU cached data for
- *     memregions described by @res_desc
- * @res_desc: one of the IORES_DESC_* types
+ *     memregion
+ * @start: start physical address of the target memory region.
+ * @len: length of the target memory region. -1 for all the regions of
+ *       the target type.
  *
  * Perform cache maintenance after a memory event / operation that
  * changes the contents of physical memory in a cache-incoherent manner.
@@ -46,7 +48,7 @@ static inline void memregion_free(int id)
  * the cache maintenance.
  */
 #ifdef CONFIG_ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
-int cpu_cache_invalidate_memregion(int res_desc);
+int cpu_cache_invalidate_memregion(phys_addr_t start, size_t len);
 bool cpu_cache_has_invalidate_memregion(void);
 #else
 static inline bool cpu_cache_has_invalidate_memregion(void)
@@ -54,10 +56,16 @@ static inline bool cpu_cache_has_invalidate_memregion(void)
 	return false;
 }
 
-static inline int cpu_cache_invalidate_memregion(int res_desc)
+static inline int cpu_cache_invalidate_memregion(phys_addr_t start, size_t len)
 {
 	WARN_ON_ONCE("CPU cache invalidation required");
 	return -ENXIO;
 }
 #endif
+
+static inline int cpu_cache_invalidate_all(void)
+{
+	return cpu_cache_invalidate_memregion(0, -1);
+}
+
 #endif /* _MEMREGION_H_ */
diff --git a/include/linux/memremap.h b/include/linux/memremap.h
index 1314d9c5f05b..713ec0435b48 100644
--- a/include/linux/memremap.h
+++ b/include/linux/memremap.h
@@ -76,11 +76,11 @@ enum memory_type {
 
 struct dev_pagemap_ops {
 	/*
-	 * Called once the page refcount reaches 0.  The reference count will be
+	 * Called once the folio refcount reaches 0.  The reference count will be
 	 * reset to one by the core code after the method is called to prepare
-	 * for handing out the page again.
+	 * for handing out the folio again.
 	 */
-	void (*page_free)(struct page *page);
+	void (*folio_free)(struct folio *folio);
 
 	/*
 	 * Used for private (un-addressable) device memory only.  Must migrate
@@ -99,6 +99,13 @@ struct dev_pagemap_ops {
 	 */
 	int (*memory_failure)(struct dev_pagemap *pgmap, unsigned long pfn,
 			      unsigned long nr_pages, int mf_flags);
+
+	/*
+	 * Used for private (un-addressable) device memory only.
+	 * This callback is used when a folio is split into
+	 * a smaller folio
+	 */
+	void (*folio_split)(struct folio *head, struct folio *tail);
 };
 
 #define PGMAP_ALTMAP_VALID	(1 << 0)
@@ -108,7 +115,7 @@ struct dev_pagemap_ops {
  * @altmap: pre-allocated/reserved memory for vmemmap allocations
  * @ref: reference count that pins the devm_memremap_pages() mapping
  * @done: completion for @ref
- * @type: memory type: see MEMORY_* in memory_hotplug.h
+ * @type: memory type: see MEMORY_* above in memremap.h
  * @flags: PGMAP_* flags to specify defailed behavior
  * @vmemmap_shift: structural definition of how the vmemmap page metadata
  *      is populated, specifically the metadata page order.
@@ -156,49 +163,101 @@ static inline unsigned long pgmap_vmemmap_nr(struct dev_pagemap *pgmap)
 	return 1 << pgmap->vmemmap_shift;
 }
 
+static inline bool folio_is_device_private(const struct folio *folio)
+{
+	return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
+		folio_is_zone_device(folio) &&
+		folio->pgmap->type == MEMORY_DEVICE_PRIVATE;
+}
+
 static inline bool is_device_private_page(const struct page *page)
 {
 	return IS_ENABLED(CONFIG_DEVICE_PRIVATE) &&
-		is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PRIVATE;
+		folio_is_device_private(page_folio(page));
 }
 
-static inline bool folio_is_device_private(const struct folio *folio)
+static inline bool folio_is_pci_p2pdma(const struct folio *folio)
 {
-	return is_device_private_page(&folio->page);
+	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
+		folio_is_zone_device(folio) &&
+		folio->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
+}
+
+static inline void *folio_zone_device_data(const struct folio *folio)
+{
+	VM_WARN_ON_FOLIO(!folio_is_device_private(folio), folio);
+	return folio->page.zone_device_data;
+}
+
+static inline void folio_set_zone_device_data(struct folio *folio, void *data)
+{
+	VM_WARN_ON_FOLIO(!folio_is_device_private(folio), folio);
+	folio->page.zone_device_data = data;
 }
 
 static inline bool is_pci_p2pdma_page(const struct page *page)
 {
 	return IS_ENABLED(CONFIG_PCI_P2PDMA) &&
-		is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_PCI_P2PDMA;
+		folio_is_pci_p2pdma(page_folio(page));
+}
+
+static inline bool folio_is_device_coherent(const struct folio *folio)
+{
+	return folio_is_zone_device(folio) &&
+		folio->pgmap->type == MEMORY_DEVICE_COHERENT;
 }
 
 static inline bool is_device_coherent_page(const struct page *page)
 {
-	return is_zone_device_page(page) &&
-		page->pgmap->type == MEMORY_DEVICE_COHERENT;
+	return folio_is_device_coherent(page_folio(page));
 }
 
-static inline bool folio_is_device_coherent(const struct folio *folio)
+static inline bool folio_is_fsdax(const struct folio *folio)
 {
-	return is_device_coherent_page(&folio->page);
+	return folio_is_zone_device(folio) &&
+		folio->pgmap->type == MEMORY_DEVICE_FS_DAX;
+}
+
+static inline bool is_fsdax_page(const struct page *page)
+{
+	return folio_is_fsdax(page_folio(page));
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-void zone_device_page_init(struct page *page);
+void zone_device_page_init(struct page *page, unsigned int order);
 void *memremap_pages(struct dev_pagemap *pgmap, int nid);
 void memunmap_pages(struct dev_pagemap *pgmap);
 void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
 void devm_memunmap_pages(struct device *dev, struct dev_pagemap *pgmap);
-struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
-		struct dev_pagemap *pgmap);
+struct dev_pagemap *get_dev_pagemap(unsigned long pfn);
 bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn);
 
-unsigned long vmem_altmap_offset(struct vmem_altmap *altmap);
-void vmem_altmap_free(struct vmem_altmap *altmap, unsigned long nr_pfns);
 unsigned long memremap_compat_align(void);
+
+static inline void zone_device_folio_init(struct folio *folio, unsigned int order)
+{
+	zone_device_page_init(&folio->page, order);
+	if (order)
+		folio_set_large_rmappable(folio);
+}
+
+static inline void zone_device_private_split_cb(struct folio *original_folio,
+						struct folio *new_folio)
+{
+	if (folio_is_device_private(original_folio)) {
+		if (!original_folio->pgmap->ops->folio_split) {
+			if (new_folio) {
+				new_folio->pgmap = original_folio->pgmap;
+				new_folio->page.mapping =
+					original_folio->page.mapping;
+			}
+		} else {
+			original_folio->pgmap->ops->folio_split(original_folio,
+								 new_folio);
+		}
+	}
+}
+
 #else
 static inline void *devm_memremap_pages(struct device *dev,
 		struct dev_pagemap *pgmap)
@@ -217,8 +276,7 @@ static inline void devm_memunmap_pages(struct device *dev,
 {
 }
 
-static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
-		struct dev_pagemap *pgmap)
+static inline struct dev_pagemap *get_dev_pagemap(unsigned long pfn)
 {
 	return NULL;
 }
@@ -228,21 +286,16 @@ static inline bool pgmap_pfn_valid(struct dev_pagemap *pgmap, unsigned long pfn)
 	return false;
 }
 
-static inline unsigned long vmem_altmap_offset(struct vmem_altmap *altmap)
-{
-	return 0;
-}
-
-static inline void vmem_altmap_free(struct vmem_altmap *altmap,
-		unsigned long nr_pfns)
-{
-}
-
 /* when memremap_pages() is disabled all archs can remap a single page */
 static inline unsigned long memremap_compat_align(void)
 {
 	return PAGE_SIZE;
 }
+
+static inline void zone_device_private_split_cb(struct folio *original_folio,
+						struct folio *new_folio)
+{
+}
 #endif /* CONFIG_ZONE_DEVICE */
 
 static inline void put_dev_pagemap(struct dev_pagemap *pgmap)
diff --git a/include/linux/memstick.h b/include/linux/memstick.h
index ebf73d4ee969..107bdcbedf79 100644
--- a/include/linux/memstick.h
+++ b/include/linux/memstick.h
@@ -293,7 +293,7 @@ struct memstick_host {
 };
 
 struct memstick_driver {
-	struct memstick_device_id *id_table;
+	const struct memstick_device_id *id_table;
 	int                       (*probe)(struct memstick_dev *card);
 	void                      (*remove)(struct memstick_dev *card);
 	int                       (*suspend)(struct memstick_dev *card,
diff --git a/include/linux/mfd/88pm80x.h b/include/linux/mfd/88pm80x.h
index def5df6e74bf..551ef1c367d6 100644
--- a/include/linux/mfd/88pm80x.h
+++ b/include/linux/mfd/88pm80x.h
@@ -294,7 +294,7 @@ struct pm80x_chip {
 	struct i2c_client *client;
 	struct i2c_client *companion;
 	struct regmap *regmap;
-	struct regmap_irq_chip *regmap_irq_chip;
+	const struct regmap_irq_chip *regmap_irq_chip;
 	struct regmap_irq_chip_data *irq_data;
 	int type;
 	int irq;
diff --git a/include/linux/mfd/88pm860x.h b/include/linux/mfd/88pm860x.h
index 473545a2c425..6fa21791fc85 100644
--- a/include/linux/mfd/88pm860x.h
+++ b/include/linux/mfd/88pm860x.h
@@ -472,13 +472,7 @@ extern int pm860x_bulk_read(struct i2c_client *, int, int, unsigned char *);
 extern int pm860x_bulk_write(struct i2c_client *, int, int, unsigned char *);
 extern int pm860x_set_bits(struct i2c_client *, int, unsigned char,
 			   unsigned char);
-extern int pm860x_page_reg_read(struct i2c_client *, int);
 extern int pm860x_page_reg_write(struct i2c_client *, int, unsigned char);
 extern int pm860x_page_bulk_read(struct i2c_client *, int, int,
 				 unsigned char *);
-extern int pm860x_page_bulk_write(struct i2c_client *, int, int,
-				  unsigned char *);
-extern int pm860x_page_set_bits(struct i2c_client *, int, unsigned char,
-				unsigned char);
-
 #endif /* __LINUX_MFD_88PM860X_H */
diff --git a/include/linux/mfd/88pm886.h b/include/linux/mfd/88pm886.h
new file mode 100644
index 000000000000..38892ba7b8a4
--- /dev/null
+++ b/include/linux/mfd/88pm886.h
@@ -0,0 +1,136 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __MFD_88PM886_H
+#define __MFD_88PM886_H
+
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+
+#define PM886_A1_CHIP_ID		0xa1
+
+#define PM886_IRQ_ONKEY			0
+
+#define PM886_PAGE_OFFSET_REGULATORS	1
+#define PM886_PAGE_OFFSET_GPADC		2
+
+#define PM886_REG_ID			0x00
+
+#define PM886_REG_STATUS1		0x01
+#define PM886_ONKEY_STS1		BIT(0)
+
+#define PM886_REG_INT_STATUS1		0x05
+
+#define PM886_REG_INT_ENA_1		0x0a
+#define PM886_INT_ENA1_ONKEY		BIT(0)
+
+#define PM886_REG_MISC_CONFIG1		0x14
+#define PM886_SW_PDOWN			BIT(5)
+
+#define PM886_REG_MISC_CONFIG2		0x15
+#define PM886_INT_INV			BIT(0)
+#define PM886_INT_CLEAR			BIT(1)
+#define PM886_INT_RC			0x00
+#define PM886_INT_WC			BIT(1)
+#define PM886_INT_MASK_MODE		BIT(2)
+
+#define PM886_REG_RTC_CNT1		0xd1
+#define PM886_REG_RTC_CNT2		0xd2
+#define PM886_REG_RTC_CNT3		0xd3
+#define PM886_REG_RTC_CNT4		0xd4
+#define PM886_REG_RTC_SPARE1		0xea
+#define PM886_REG_RTC_SPARE2		0xeb
+#define PM886_REG_RTC_SPARE3		0xec
+#define PM886_REG_RTC_SPARE4		0xed
+#define PM886_REG_RTC_SPARE5		0xee
+#define PM886_REG_RTC_SPARE6		0xef
+
+#define PM886_REG_BUCK_EN		0x08
+#define PM886_REG_LDO_EN1		0x09
+#define PM886_REG_LDO_EN2		0x0a
+#define PM886_REG_LDO1_VOUT		0x20
+#define PM886_REG_LDO2_VOUT		0x26
+#define PM886_REG_LDO3_VOUT		0x2c
+#define PM886_REG_LDO4_VOUT		0x32
+#define PM886_REG_LDO5_VOUT		0x38
+#define PM886_REG_LDO6_VOUT		0x3e
+#define PM886_REG_LDO7_VOUT		0x44
+#define PM886_REG_LDO8_VOUT		0x4a
+#define PM886_REG_LDO9_VOUT		0x50
+#define PM886_REG_LDO10_VOUT		0x56
+#define PM886_REG_LDO11_VOUT		0x5c
+#define PM886_REG_LDO12_VOUT		0x62
+#define PM886_REG_LDO13_VOUT		0x68
+#define PM886_REG_LDO14_VOUT		0x6e
+#define PM886_REG_LDO15_VOUT		0x74
+#define PM886_REG_LDO16_VOUT		0x7a
+#define PM886_REG_BUCK1_VOUT		0xa5
+#define PM886_REG_BUCK2_VOUT		0xb3
+#define PM886_REG_BUCK3_VOUT		0xc1
+#define PM886_REG_BUCK4_VOUT		0xcf
+#define PM886_REG_BUCK5_VOUT		0xdd
+
+#define PM886_LDO_VSEL_MASK		0x0f
+#define PM886_BUCK_VSEL_MASK		0x7f
+
+/* GPADC enable/disable registers */
+#define PM886_REG_GPADC_CONFIG(n)	(n)
+
+#define PM886_GPADC_VSC_EN		BIT(0)
+#define PM886_GPADC_VBAT_EN		BIT(1)
+#define PM886_GPADC_GNDDET1_EN		BIT(3)
+#define PM886_GPADC_VBUS_EN		BIT(4)
+#define PM886_GPADC_VCHG_PWR_EN		BIT(5)
+#define PM886_GPADC_VCF_OUT_EN		BIT(6)
+#define PM886_GPADC_CONFIG1_EN_ALL	\
+	(PM886_GPADC_VSC_EN |		\
+	 PM886_GPADC_VBAT_EN |		\
+	 PM886_GPADC_GNDDET1_EN |	\
+	 PM886_GPADC_VBUS_EN |		\
+	 PM886_GPADC_VCHG_PWR_EN |	\
+	 PM886_GPADC_VCF_OUT_EN)
+
+#define PM886_GPADC_TINT_EN		BIT(0)
+#define PM886_GPADC_PMODE_EN		BIT(1)
+#define PM886_GPADC_GPADC0_EN		BIT(2)
+#define PM886_GPADC_GPADC1_EN		BIT(3)
+#define PM886_GPADC_GPADC2_EN		BIT(4)
+#define PM886_GPADC_GPADC3_EN		BIT(5)
+#define PM886_GPADC_MIC_DET_EN		BIT(6)
+#define PM886_GPADC_CONFIG2_EN_ALL	\
+	(PM886_GPADC_TINT_EN |		\
+	 PM886_GPADC_GPADC0_EN |	\
+	 PM886_GPADC_GPADC1_EN |	\
+	 PM886_GPADC_GPADC2_EN |	\
+	 PM886_GPADC_GPADC3_EN |	\
+	 PM886_GPADC_MIC_DET_EN)
+
+/* No CONFIG3_EN_ALL because this is the only bit there. */
+#define PM886_GPADC_GND_DET2_EN		BIT(0)
+
+/* GPADC channel registers */
+#define PM886_REG_GPADC_VSC		0x40
+#define PM886_REG_GPADC_VCHG_PWR	0x4c
+#define PM886_REG_GPADC_VCF_OUT		0x4e
+#define PM886_REG_GPADC_TINT		0x50
+#define PM886_REG_GPADC_GPADC0		0x54
+#define PM886_REG_GPADC_GPADC1		0x56
+#define PM886_REG_GPADC_GPADC2		0x58
+#define PM886_REG_GPADC_VBAT		0xa0
+#define PM886_REG_GPADC_GND_DET1	0xa4
+#define PM886_REG_GPADC_GND_DET2	0xa6
+#define PM886_REG_GPADC_VBUS		0xa8
+#define PM886_REG_GPADC_GPADC3		0xaa
+#define PM886_REG_GPADC_MIC_DET		0xac
+#define PM886_REG_GPADC_VBAT_SLP	0xb0
+
+/* VBAT_SLP is the last register and is 2 bytes wide like other channels. */
+#define PM886_GPADC_MAX_REGISTER	(PM886_REG_GPADC_VBAT_SLP + 1)
+
+#define PM886_GPADC_BIAS_LEVELS		16
+#define PM886_GPADC_INDEX_TO_BIAS_uA(i)	(1 + (i) * 5)
+
+struct pm886_chip {
+	struct i2c_client *client;
+	unsigned int chip_id;
+	struct regmap *regmap;
+};
+#endif /* __MFD_88PM886_H */
diff --git a/include/linux/mfd/aat2870.h b/include/linux/mfd/aat2870.h
index 2445842d482d..c7a3c53eba68 100644
--- a/include/linux/mfd/aat2870.h
+++ b/include/linux/mfd/aat2870.h
@@ -133,9 +133,6 @@ struct aat2870_data {
 	int (*read)(struct aat2870_data *aat2870, u8 addr, u8 *val);
 	int (*write)(struct aat2870_data *aat2870, u8 addr, u8 val);
 	int (*update)(struct aat2870_data *aat2870, u8 addr, u8 mask, u8 val);
-
-	/* for debugfs */
-	struct dentry *dentry_root;
 };
 
 struct aat2870_subdev_info {
diff --git a/include/linux/mfd/abx500/ab8500.h b/include/linux/mfd/abx500/ab8500.h
index 302a330c5c84..76d326ea8eba 100644
--- a/include/linux/mfd/abx500/ab8500.h
+++ b/include/linux/mfd/abx500/ab8500.h
@@ -382,10 +382,6 @@ struct ab8500_platform_data {
 	struct ab8500_sysctrl_platform_data *sysctrl;
 };
 
-extern int ab8500_init(struct ab8500 *ab8500,
-				 enum ab8500_version version);
-extern int ab8500_exit(struct ab8500 *ab8500);
-
 extern int ab8500_suspend(struct ab8500 *ab8500);
 
 static inline int is_ab8500(struct ab8500 *ab)
@@ -503,13 +499,7 @@ static inline int is_ab9540_2p0_or_earlier(struct ab8500 *ab)
 
 void ab8500_override_turn_on_stat(u8 mask, u8 set);
 
-#ifdef CONFIG_AB8500_DEBUG
-extern int prcmu_abb_read(u8 slave, u8 reg, u8 *value, u8 size);
-void ab8500_dump_all_banks(struct device *dev);
-void ab8500_debug_register_interrupt(int line);
-#else
 static inline void ab8500_dump_all_banks(struct device *dev) {}
 static inline void ab8500_debug_register_interrupt(int line) {}
-#endif
 
 #endif /* MFD_AB8500_H */
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
new file mode 100644
index 000000000000..5237da6b4a9f
--- /dev/null
+++ b/include/linux/mfd/adp5585.h
@@ -0,0 +1,226 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Analog Devices ADP5585 I/O expander, PWM controller and keypad controller
+ *
+ * Copyright 2022 NXP
+ * Copyright 2024 Ideas on Board Oy
+ */
+
+#ifndef __MFD_ADP5585_H_
+#define __MFD_ADP5585_H_
+
+#include <linux/bits.h>
+#include <linux/notifier.h>
+
+#define ADP5585_ID			0x00
+#define		ADP5585_MAN_ID_VALUE		0x20
+#define		ADP5585_MAN_ID_MASK		GENMASK(7, 4)
+#define		ADP5585_REV_ID_MASK		GENMASK(3, 0)
+#define ADP5585_INT_STATUS		0x01
+#define		ADP5585_OVRFLOW_INT		BIT(2)
+#define		ADP5585_EVENT_INT		BIT(0)
+#define ADP5585_STATUS			0x02
+#define		ADP5585_EC_MASK			GENMASK(4, 0)
+#define ADP5585_FIFO_1			0x03
+#define		ADP5585_KEV_EV_PRESS_MASK	BIT(7)
+#define		ADP5585_KEY_EVENT_MASK		GENMASK(6, 0)
+#define ADP5585_FIFO_2			0x04
+#define ADP5585_FIFO_3			0x05
+#define ADP5585_FIFO_4			0x06
+#define ADP5585_FIFO_5			0x07
+#define ADP5585_FIFO_6			0x08
+#define ADP5585_FIFO_7			0x09
+#define ADP5585_FIFO_8			0x0a
+#define ADP5585_FIFO_9			0x0b
+#define ADP5585_FIFO_10			0x0c
+#define ADP5585_FIFO_11			0x0d
+#define ADP5585_FIFO_12			0x0e
+#define ADP5585_FIFO_13			0x0f
+#define ADP5585_FIFO_14			0x10
+#define ADP5585_FIFO_15			0x11
+#define ADP5585_FIFO_16			0x12
+#define		ADP5585_EV_MAX			(ADP5585_FIFO_16 - ADP5585_FIFO_1 + 1)
+#define ADP5585_GPI_INT_STAT_A		0x13
+#define ADP5585_GPI_INT_STAT_B		0x14
+#define ADP5585_GPI_STATUS_A		0x15
+#define ADP5585_GPI_STATUS_B		0x16
+#define ADP5585_RPULL_CONFIG_A		0x17
+#define ADP5585_RPULL_CONFIG_B		0x18
+#define ADP5585_RPULL_CONFIG_C		0x19
+#define ADP5585_RPULL_CONFIG_D		0x1a
+#define		ADP5585_Rx_PULL_CFG_PU_300K	0
+#define		ADP5585_Rx_PULL_CFG_PD_300K	1
+#define		ADP5585_Rx_PULL_CFG_PU_100K	2
+#define		ADP5585_Rx_PULL_CFG_DISABLE	3
+#define		ADP5585_Rx_PULL_CFG_MASK	3
+#define ADP5585_GPI_INT_LEVEL_A		0x1b
+#define ADP5585_GPI_INT_LEVEL_B		0x1c
+#define ADP5585_GPI_EVENT_EN_A		0x1d
+#define ADP5585_GPI_EVENT_EN_B		0x1e
+#define ADP5585_GPI_INTERRUPT_EN_A	0x1f
+#define ADP5585_GPI_INTERRUPT_EN_B	0x20
+#define ADP5585_DEBOUNCE_DIS_A		0x21
+#define ADP5585_DEBOUNCE_DIS_B		0x22
+#define ADP5585_GPO_DATA_OUT_A		0x23
+#define ADP5585_GPO_DATA_OUT_B		0x24
+#define ADP5585_GPO_OUT_MODE_A		0x25
+#define ADP5585_GPO_OUT_MODE_B		0x26
+#define ADP5585_GPIO_DIRECTION_A	0x27
+#define ADP5585_GPIO_DIRECTION_B	0x28
+#define ADP5585_RESET1_EVENT_A		0x29
+#define		ADP5585_RESET_EV_PRESS		BIT(7)
+#define ADP5585_RESET1_EVENT_B		0x2a
+#define ADP5585_RESET1_EVENT_C		0x2b
+#define ADP5585_RESET2_EVENT_A		0x2c
+#define ADP5585_RESET2_EVENT_B		0x2d
+#define ADP5585_RESET_CFG		0x2e
+#define ADP5585_PWM_OFFT_LOW		0x2f
+#define ADP5585_PWM_OFFT_HIGH		0x30
+#define ADP5585_PWM_ONT_LOW		0x31
+#define ADP5585_PWM_ONT_HIGH		0x32
+#define ADP5585_PWM_CFG			0x33
+#define		ADP5585_PWM_IN_AND		BIT(2)
+#define		ADP5585_PWM_MODE		BIT(1)
+#define		ADP5585_PWM_EN			BIT(0)
+#define ADP5585_LOGIC_CFG		0x34
+#define ADP5585_LOGIC_FF_CFG		0x35
+#define ADP5585_LOGIC_INT_EVENT_EN	0x36
+#define ADP5585_POLL_PTIME_CFG		0x37
+#define ADP5585_PIN_CONFIG_A		0x38
+#define ADP5585_PIN_CONFIG_B		0x39
+#define ADP5585_PIN_CONFIG_C		0x3a
+#define		ADP5585_PULL_SELECT		BIT(7)
+#define		ADP5585_C4_EXTEND_CFG_GPIO11	(0U << 6)
+#define		ADP5585_C4_EXTEND_CFG_RESET2	(1U << 6)
+#define		ADP5585_C4_EXTEND_CFG_MASK	GENMASK(6, 6)
+#define		ADP5585_R4_EXTEND_CFG_GPIO5	(0U << 5)
+#define		ADP5585_R4_EXTEND_CFG_RESET1	(1U << 5)
+#define		ADP5585_R4_EXTEND_CFG_MASK	GENMASK(5, 5)
+#define		ADP5585_R3_EXTEND_CFG_GPIO4	(0U << 2)
+#define		ADP5585_R3_EXTEND_CFG_LC	(1U << 2)
+#define		ADP5585_R3_EXTEND_CFG_PWM_OUT	(2U << 2)
+#define		ADP5585_R3_EXTEND_CFG_MASK	GENMASK(3, 2)
+#define		ADP5585_R0_EXTEND_CFG_GPIO1	(0U << 0)
+#define		ADP5585_R0_EXTEND_CFG_LY	(1U << 0)
+#define		ADP5585_R0_EXTEND_CFG_MASK	GENMASK(0, 0)
+#define ADP5585_GENERAL_CFG		0x3b
+#define		ADP5585_OSC_EN			BIT(7)
+#define		ADP5585_OSC_FREQ_50KHZ		(0U << 5)
+#define		ADP5585_OSC_FREQ_100KHZ		(1U << 5)
+#define		ADP5585_OSC_FREQ_200KHZ		(2U << 5)
+#define		ADP5585_OSC_FREQ_500KHZ		(3U << 5)
+#define		ADP5585_OSC_FREQ_MASK		GENMASK(6, 5)
+#define		ADP5585_INT_CFG			BIT(1)
+#define		ADP5585_RST_CFG			BIT(0)
+#define ADP5585_INT_EN			0x3c
+#define		ADP5585_OVRFLOW_IEN		BIT(2)
+#define		ADP5585_EVENT_IEN		BIT(0)
+
+#define ADP5585_MAX_REG			ADP5585_INT_EN
+
+#define ADP5585_PIN_MAX			11
+#define ADP5585_MAX_UNLOCK_TIME_SEC	7
+#define ADP5585_KEY_EVENT_START		1
+#define ADP5585_KEY_EVENT_END		25
+#define ADP5585_GPI_EVENT_START		37
+#define ADP5585_GPI_EVENT_END		47
+#define ADP5585_ROW5_KEY_EVENT_START	1
+#define ADP5585_ROW5_KEY_EVENT_END	30
+#define ADP5585_PWM_OUT			3
+#define ADP5585_RESET1_OUT		4
+#define ADP5585_RESET2_OUT		9
+#define ADP5585_ROW5			5
+
+/* ADP5589 */
+#define		ADP5589_MAN_ID_VALUE		0x10
+#define ADP5589_GPI_STATUS_A		0x16
+#define ADP5589_GPI_STATUS_C		0x18
+#define ADP5589_RPULL_CONFIG_A		0x19
+#define ADP5589_GPI_INT_LEVEL_A		0x1e
+#define ADP5589_GPI_EVENT_EN_A		0x21
+#define ADP5589_DEBOUNCE_DIS_A		0x27
+#define ADP5589_GPO_DATA_OUT_A		0x2a
+#define ADP5589_GPO_OUT_MODE_A		0x2d
+#define		ADP5589_GPIO_DIRECTION_A	0x30
+#define ADP5589_UNLOCK1			0x33
+#define		ADP5589_UNLOCK_EV_PRESS		BIT(7)
+#define ADP5589_UNLOCK_TIMERS		0x36
+#define		ADP5589_UNLOCK_TIMER		GENMASK(2, 0)
+#define ADP5589_LOCK_CFG		0x37
+#define		ADP5589_LOCK_EN			BIT(0)
+#define ADP5589_RESET1_EVENT_A		0x38
+#define ADP5589_RESET2_EVENT_A		0x3B
+#define ADP5589_RESET_CFG		0x3D
+#define		ADP5585_RESET2_POL		BIT(7)
+#define		ADP5585_RESET1_POL		BIT(6)
+#define		ADP5585_RST_PASSTHRU_EN		BIT(5)
+#define		ADP5585_RESET_TRIG_TIME		GENMASK(4, 2)
+#define		ADP5585_PULSE_WIDTH		GENMASK(1, 0)
+#define ADP5589_PWM_OFFT_LOW		0x3e
+#define ADP5589_PWM_ONT_LOW		0x40
+#define ADP5589_PWM_CFG			0x42
+#define ADP5589_POLL_PTIME_CFG		0x48
+#define ADP5589_PIN_CONFIG_A		0x49
+#define ADP5589_PIN_CONFIG_D		0x4C
+#define ADP5589_GENERAL_CFG		0x4d
+#define ADP5589_INT_EN			0x4e
+#define ADP5589_MAX_REG			ADP5589_INT_EN
+
+#define ADP5589_PIN_MAX			19
+#define ADP5589_KEY_EVENT_START		1
+#define ADP5589_KEY_EVENT_END		88
+#define ADP5589_GPI_EVENT_START		97
+#define ADP5589_GPI_EVENT_END		115
+#define ADP5589_UNLOCK_WILDCARD		127
+#define ADP5589_RESET2_OUT		12
+
+struct regmap;
+
+enum adp5585_variant {
+	ADP5585_00 = 1,
+	ADP5585_01,
+	ADP5585_02,
+	ADP5585_03,
+	ADP5585_04,
+	ADP5589_00,
+	ADP5589_01,
+	ADP5589_02,
+	ADP5585_MAX
+};
+
+struct adp5585_regs {
+	unsigned int gen_cfg;
+	unsigned int ext_cfg;
+	unsigned int int_en;
+	unsigned int poll_ptime_cfg;
+	unsigned int reset_cfg;
+	unsigned int reset1_event_a;
+	unsigned int reset2_event_a;
+	unsigned int pin_cfg_a;
+};
+
+struct adp5585_dev {
+	struct device *dev;
+	struct regmap *regmap;
+	const struct adp5585_regs *regs;
+	struct blocking_notifier_head event_notifier;
+	unsigned long *pin_usage;
+	unsigned int n_pins;
+	unsigned int reset2_out;
+	enum adp5585_variant variant;
+	unsigned int id;
+	bool has_unlock;
+	bool has_pin6;
+	int irq;
+	unsigned int ev_poll_time;
+	unsigned int unlock_time;
+	unsigned int unlock_keys[2];
+	unsigned int nkeys_unlock;
+	unsigned int reset1_keys[3];
+	unsigned int nkeys_reset1;
+	unsigned int reset2_keys[2];
+	unsigned int nkeys_reset2;
+	u8 reset_cfg;
+};
+
+#endif
diff --git a/include/linux/mfd/arizona/pdata.h b/include/linux/mfd/arizona/pdata.h
index 2d13bbea4f3a..f72e6d4b14a7 100644
--- a/include/linux/mfd/arizona/pdata.h
+++ b/include/linux/mfd/arizona/pdata.h
@@ -117,8 +117,10 @@ struct arizona_pdata {
 	/** Check for line output with HPDET method */
 	bool hpdet_acc_id_line;
 
+#ifdef CONFIG_GPIOLIB_LEGACY
 	/** GPIO used for mic isolation with HPDET */
 	int hpdet_id_gpio;
+#endif
 
 	/** Channel to use for headphone detection */
 	unsigned int hpdet_channel;
@@ -129,8 +131,10 @@ struct arizona_pdata {
 	/** Extra debounce timeout used during initial mic detection (ms) */
 	unsigned int micd_detect_debounce;
 
+#ifdef CONFIG_GPIOLIB_LEGACY
 	/** GPIO for mic detection polarity */
 	int micd_pol_gpio;
+#endif
 
 	/** Mic detect ramp rate */
 	unsigned int micd_bias_start_time;
@@ -184,8 +188,10 @@ struct arizona_pdata {
 	/** Haptic actuator type */
 	unsigned int hap_act;
 
+#ifdef CONFIG_GPIOLIB_LEGACY
 	/** GPIO for primary IRQ (used for edge triggered emulation) */
 	int irq_gpio;
+#endif
 
 	/** General purpose switch control */
 	unsigned int gpsw;
diff --git a/include/linux/mfd/atmel-hlcdc.h b/include/linux/mfd/atmel-hlcdc.h
index a186119a49b5..80d675a03b39 100644
--- a/include/linux/mfd/atmel-hlcdc.h
+++ b/include/linux/mfd/atmel-hlcdc.h
@@ -22,6 +22,8 @@
 #define ATMEL_HLCDC_DITHER		BIT(6)
 #define ATMEL_HLCDC_DISPDLY		BIT(7)
 #define ATMEL_HLCDC_MODE_MASK		GENMASK(9, 8)
+#define ATMEL_XLCDC_MODE_MASK		GENMASK(10, 8)
+#define ATMEL_XLCDC_DPI			BIT(11)
 #define ATMEL_HLCDC_PP			BIT(10)
 #define ATMEL_HLCDC_VSPSU		BIT(12)
 #define ATMEL_HLCDC_VSPHO		BIT(13)
@@ -34,6 +36,12 @@
 #define ATMEL_HLCDC_IDR			0x30
 #define ATMEL_HLCDC_IMR			0x34
 #define ATMEL_HLCDC_ISR			0x38
+#define ATMEL_XLCDC_ATTRE		0x3c
+
+#define ATMEL_XLCDC_BASE_UPDATE		BIT(0)
+#define ATMEL_XLCDC_OVR1_UPDATE		BIT(1)
+#define ATMEL_XLCDC_OVR3_UPDATE		BIT(2)
+#define ATMEL_XLCDC_HEO_UPDATE		BIT(3)
 
 #define ATMEL_HLCDC_CLKPOL		BIT(0)
 #define ATMEL_HLCDC_CLKSEL		BIT(2)
@@ -48,6 +56,8 @@
 #define ATMEL_HLCDC_DISP		BIT(2)
 #define ATMEL_HLCDC_PWM			BIT(3)
 #define ATMEL_HLCDC_SIP			BIT(4)
+#define ATMEL_XLCDC_SD			BIT(5)
+#define ATMEL_XLCDC_CM			BIT(6)
 
 #define ATMEL_HLCDC_SOF			BIT(0)
 #define ATMEL_HLCDC_SYNCDIS		BIT(1)
diff --git a/include/linux/mfd/axp20x.h b/include/linux/mfd/axp20x.h
index beb3f44f85c5..3c5aecf1d4b5 100644
--- a/include/linux/mfd/axp20x.h
+++ b/include/linux/mfd/axp20x.h
@@ -12,11 +12,15 @@
 
 enum axp20x_variants {
 	AXP152_ID = 0,
+	AXP192_ID,
 	AXP202_ID,
 	AXP209_ID,
 	AXP221_ID,
 	AXP223_ID,
 	AXP288_ID,
+	AXP313A_ID,
+	AXP323_ID,
+	AXP717_ID,
 	AXP803_ID,
 	AXP806_ID,
 	AXP809_ID,
@@ -25,6 +29,7 @@ enum axp20x_variants {
 	NR_AXP20X_VARIANTS,
 };
 
+#define AXP192_DATACACHE(m)		(0x06 + (m))
 #define AXP20X_DATACACHE(m)		(0x04 + (m))
 
 /* Power supply */
@@ -46,6 +51,13 @@ enum axp20x_variants {
 #define AXP152_DCDC_FREQ		0x37
 #define AXP152_DCDC_MODE		0x80
 
+#define AXP192_USB_OTG_STATUS		0x04
+#define AXP192_PWR_OUT_CTRL		0x12
+#define AXP192_DCDC2_V_OUT		0x23
+#define AXP192_DCDC1_V_OUT		0x26
+#define AXP192_DCDC3_V_OUT		0x27
+#define AXP192_LDO2_3_V_OUT		0x28
+
 #define AXP20X_PWR_INPUT_STATUS		0x00
 #define AXP20X_PWR_OP_MODE		0x01
 #define AXP20X_USB_OTG_STATUS		0x02
@@ -92,6 +104,77 @@ enum axp20x_variants {
 #define AXP22X_ALDO3_V_OUT		0x2a
 #define AXP22X_CHRG_CTRL3		0x35
 
+#define AXP313A_ON_INDICATE		0x00
+#define AXP313A_OUTPUT_CONTROL		0x10
+#define AXP313A_DCDC1_CONTROL		0x13
+#define AXP313A_DCDC2_CONTROL		0x14
+#define AXP313A_DCDC3_CONTROL		0x15
+#define AXP313A_ALDO1_CONTROL		0x16
+#define AXP313A_DLDO1_CONTROL		0x17
+#define AXP313A_SHUTDOWN_CTRL		0x1a
+#define AXP313A_IRQ_EN			0x20
+#define AXP313A_IRQ_STATE		0x21
+#define AXP323_DCDC_MODE_CTRL2		0x22
+
+#define AXP717_ON_INDICATE		0x00
+#define AXP717_PMU_STATUS_2		0x01
+#define AXP717_BC_DETECT		0x05
+#define AXP717_PMU_FAULT		0x08
+#define AXP717_MODULE_EN_CONTROL_1	0x0b
+#define AXP717_MIN_SYS_V_CONTROL	0x15
+#define AXP717_INPUT_VOL_LIMIT_CTRL	0x16
+#define AXP717_INPUT_CUR_LIMIT_CTRL	0x17
+#define AXP717_MODULE_EN_CONTROL_2	0x19
+#define AXP717_BOOST_CONTROL		0x1e
+#define AXP717_VSYS_V_POWEROFF		0x24
+#define AXP717_IRQ0_EN			0x40
+#define AXP717_IRQ1_EN			0x41
+#define AXP717_IRQ2_EN			0x42
+#define AXP717_IRQ3_EN			0x43
+#define AXP717_IRQ4_EN			0x44
+#define AXP717_IRQ0_STATE		0x48
+#define AXP717_IRQ1_STATE		0x49
+#define AXP717_IRQ2_STATE		0x4a
+#define AXP717_IRQ3_STATE		0x4b
+#define AXP717_IRQ4_STATE		0x4c
+#define AXP717_TS_PIN_CFG		0x50
+#define AXP717_ICC_CHG_SET		0x62
+#define AXP717_ITERM_CHG_SET		0x63
+#define AXP717_CV_CHG_SET		0x64
+#define AXP717_DCDC_OUTPUT_CONTROL	0x80
+#define AXP717_DCDC1_CONTROL		0x83
+#define AXP717_DCDC2_CONTROL		0x84
+#define AXP717_DCDC3_CONTROL		0x85
+#define AXP717_DCDC4_CONTROL		0x86
+#define AXP717_LDO0_OUTPUT_CONTROL	0x90
+#define AXP717_LDO1_OUTPUT_CONTROL	0x91
+#define AXP717_ALDO1_CONTROL		0x93
+#define AXP717_ALDO2_CONTROL		0x94
+#define AXP717_ALDO3_CONTROL		0x95
+#define AXP717_ALDO4_CONTROL		0x96
+#define AXP717_BLDO1_CONTROL		0x97
+#define AXP717_BLDO2_CONTROL		0x98
+#define AXP717_BLDO3_CONTROL		0x99
+#define AXP717_BLDO4_CONTROL		0x9a
+#define AXP717_CLDO1_CONTROL		0x9b
+#define AXP717_CLDO2_CONTROL		0x9c
+#define AXP717_CLDO3_CONTROL		0x9d
+#define AXP717_CLDO4_CONTROL		0x9e
+#define AXP717_CPUSLDO_CONTROL		0x9f
+#define AXP717_BATT_PERCENT_DATA	0xa4
+#define AXP717_ADC_CH_EN_CONTROL	0xc0
+#define AXP717_BATT_V_H			0xc4
+#define AXP717_BATT_V_L			0xc5
+#define AXP717_VBUS_V_H			0xc6
+#define AXP717_VBUS_V_L			0xc7
+#define AXP717_VSYS_V_H			0xc8
+#define AXP717_VSYS_V_L			0xc9
+#define AXP717_BATT_CHRG_I_H		0xca
+#define AXP717_BATT_CHRG_I_L		0xcb
+#define AXP717_ADC_DATA_SEL		0xcd
+#define AXP717_ADC_DATA_H		0xce
+#define AXP717_ADC_DATA_L		0xcf
+
 #define AXP806_STARTUP_SRC		0x00
 #define AXP806_CHIP_ID			0x03
 #define AXP806_PWR_OUT_CTRL1		0x10
@@ -173,6 +256,17 @@ enum axp20x_variants {
 #define AXP152_IRQ2_STATE		0x49
 #define AXP152_IRQ3_STATE		0x4a
 
+#define AXP192_IRQ1_EN			0x40
+#define AXP192_IRQ2_EN			0x41
+#define AXP192_IRQ3_EN			0x42
+#define AXP192_IRQ4_EN			0x43
+#define AXP192_IRQ1_STATE		0x44
+#define AXP192_IRQ2_STATE		0x45
+#define AXP192_IRQ3_STATE		0x46
+#define AXP192_IRQ4_STATE		0x47
+#define AXP192_IRQ5_EN			0x4a
+#define AXP192_IRQ5_STATE		0x4d
+
 #define AXP20X_IRQ1_EN			0x40
 #define AXP20X_IRQ2_EN			0x41
 #define AXP20X_IRQ3_EN			0x42
@@ -192,6 +286,11 @@ enum axp20x_variants {
 #define AXP15060_IRQ2_STATE		0x49
 
 /* ADC */
+#define AXP192_GPIO2_V_ADC_H		0x68
+#define AXP192_GPIO2_V_ADC_L		0x69
+#define AXP192_GPIO3_V_ADC_H		0x6a
+#define AXP192_GPIO3_V_ADC_L		0x6b
+
 #define AXP20X_ACIN_V_ADC_H		0x56
 #define AXP20X_ACIN_V_ADC_L		0x57
 #define AXP20X_ACIN_I_ADC_H		0x58
@@ -221,6 +320,8 @@ enum axp20x_variants {
 #define AXP20X_IPSOUT_V_HIGH_L		0x7f
 
 /* Power supply */
+#define AXP192_GPIO30_IN_RANGE		0x85
+
 #define AXP20X_DCDC_MODE		0x80
 #define AXP20X_ADC_EN1			0x82
 #define AXP20X_ADC_EN2			0x83
@@ -249,6 +350,16 @@ enum axp20x_variants {
 #define AXP152_PWM1_FREQ_Y		0x9c
 #define AXP152_PWM1_DUTY_CYCLE		0x9d
 
+#define AXP192_GPIO0_CTRL		0x90
+#define AXP192_LDO_IO0_V_OUT		0x91
+#define AXP192_GPIO1_CTRL		0x92
+#define AXP192_GPIO2_CTRL		0x93
+#define AXP192_GPIO2_0_STATE		0x94
+#define AXP192_GPIO4_3_CTRL		0x95
+#define AXP192_GPIO4_3_STATE		0x96
+#define AXP192_GPIO2_0_PULL		0x97
+#define AXP192_N_RSTO_CTRL		0x9e
+
 #define AXP20X_GPIO0_CTRL		0x90
 #define AXP20X_LDO5_V_OUT		0x91
 #define AXP20X_GPIO1_CTRL		0x92
@@ -329,6 +440,17 @@ enum axp20x_variants {
 
 /* Regulators IDs */
 enum {
+	AXP192_DCDC1 = 0,
+	AXP192_DCDC2,
+	AXP192_DCDC3,
+	AXP192_LDO1,
+	AXP192_LDO2,
+	AXP192_LDO3,
+	AXP192_LDO_IO0,
+	AXP192_REG_ID_MAX
+};
+
+enum {
 	AXP20X_LDO1 = 0,
 	AXP20X_LDO2,
 	AXP20X_LDO3,
@@ -364,6 +486,38 @@ enum {
 };
 
 enum {
+	AXP313A_DCDC1 = 0,
+	AXP313A_DCDC2,
+	AXP313A_DCDC3,
+	AXP313A_ALDO1,
+	AXP313A_DLDO1,
+	AXP313A_RTC_LDO,
+	AXP313A_REG_ID_MAX,
+};
+
+enum {
+	AXP717_DCDC1 = 0,
+	AXP717_DCDC2,
+	AXP717_DCDC3,
+	AXP717_DCDC4,
+	AXP717_ALDO1,
+	AXP717_ALDO2,
+	AXP717_ALDO3,
+	AXP717_ALDO4,
+	AXP717_BLDO1,
+	AXP717_BLDO2,
+	AXP717_BLDO3,
+	AXP717_BLDO4,
+	AXP717_CLDO1,
+	AXP717_CLDO2,
+	AXP717_CLDO3,
+	AXP717_CLDO4,
+	AXP717_CPUSLDO,
+	AXP717_BOOST,
+	AXP717_REG_ID_MAX,
+};
+
+enum {
 	AXP806_DCDCA = 0,
 	AXP806_DCDCB,
 	AXP806_DCDCC,
@@ -509,6 +663,42 @@ enum {
 	AXP152_IRQ_GPIO0_INPUT,
 };
 
+enum axp192_irqs {
+	AXP192_IRQ_ACIN_OVER_V = 1,
+	AXP192_IRQ_ACIN_PLUGIN,
+	AXP192_IRQ_ACIN_REMOVAL,
+	AXP192_IRQ_VBUS_OVER_V,
+	AXP192_IRQ_VBUS_PLUGIN,
+	AXP192_IRQ_VBUS_REMOVAL,
+	AXP192_IRQ_VBUS_V_LOW,
+	AXP192_IRQ_BATT_PLUGIN,
+	AXP192_IRQ_BATT_REMOVAL,
+	AXP192_IRQ_BATT_ENT_ACT_MODE,
+	AXP192_IRQ_BATT_EXIT_ACT_MODE,
+	AXP192_IRQ_CHARG,
+	AXP192_IRQ_CHARG_DONE,
+	AXP192_IRQ_BATT_TEMP_HIGH,
+	AXP192_IRQ_BATT_TEMP_LOW,
+	AXP192_IRQ_DIE_TEMP_HIGH,
+	AXP192_IRQ_CHARG_I_LOW,
+	AXP192_IRQ_DCDC1_V_LONG,
+	AXP192_IRQ_DCDC2_V_LONG,
+	AXP192_IRQ_DCDC3_V_LONG,
+	AXP192_IRQ_PEK_SHORT = 22,
+	AXP192_IRQ_PEK_LONG,
+	AXP192_IRQ_N_OE_PWR_ON,
+	AXP192_IRQ_N_OE_PWR_OFF,
+	AXP192_IRQ_VBUS_VALID,
+	AXP192_IRQ_VBUS_NOT_VALID,
+	AXP192_IRQ_VBUS_SESS_VALID,
+	AXP192_IRQ_VBUS_SESS_END,
+	AXP192_IRQ_LOW_PWR_LVL = 31,
+	AXP192_IRQ_TIMER,
+	AXP192_IRQ_GPIO2_INPUT = 37,
+	AXP192_IRQ_GPIO1_INPUT,
+	AXP192_IRQ_GPIO0_INPUT,
+};
+
 enum {
 	AXP20X_IRQ_ACIN_OVER_V = 1,
 	AXP20X_IRQ_ACIN_PLUGIN,
@@ -616,6 +806,50 @@ enum axp288_irqs {
 	AXP288_IRQ_BC_USB_CHNG,
 };
 
+enum axp313a_irqs {
+	AXP313A_IRQ_DIE_TEMP_HIGH,
+	AXP313A_IRQ_DCDC2_V_LOW = 2,
+	AXP313A_IRQ_DCDC3_V_LOW,
+	AXP313A_IRQ_PEK_LONG,
+	AXP313A_IRQ_PEK_SHORT,
+	AXP313A_IRQ_PEK_FAL_EDGE,
+	AXP313A_IRQ_PEK_RIS_EDGE,
+};
+
+enum axp717_irqs {
+	AXP717_IRQ_VBUS_FAULT,
+	AXP717_IRQ_VBUS_OVER_V,
+	AXP717_IRQ_BOOST_OVER_V,
+	AXP717_IRQ_GAUGE_NEW_SOC = 4,
+	AXP717_IRQ_SOC_DROP_LVL1 = 6,
+	AXP717_IRQ_SOC_DROP_LVL2,
+	AXP717_IRQ_PEK_RIS_EDGE,
+	AXP717_IRQ_PEK_FAL_EDGE,
+	AXP717_IRQ_PEK_LONG,
+	AXP717_IRQ_PEK_SHORT,
+	AXP717_IRQ_BATT_REMOVAL,
+	AXP717_IRQ_BATT_PLUGIN,
+	AXP717_IRQ_VBUS_REMOVAL,
+	AXP717_IRQ_VBUS_PLUGIN,
+	AXP717_IRQ_BATT_OVER_V,
+	AXP717_IRQ_CHARG_TIMER,
+	AXP717_IRQ_DIE_TEMP_HIGH,
+	AXP717_IRQ_CHARG,
+	AXP717_IRQ_CHARG_DONE,
+	AXP717_IRQ_BATT_OVER_CURR,
+	AXP717_IRQ_LDO_OVER_CURR,
+	AXP717_IRQ_WDOG_EXPIRE,
+	AXP717_IRQ_BATT_ACT_TEMP_LOW,
+	AXP717_IRQ_BATT_ACT_TEMP_HIGH,
+	AXP717_IRQ_BATT_CHG_TEMP_LOW,
+	AXP717_IRQ_BATT_CHG_TEMP_HIGH,
+	AXP717_IRQ_BATT_QUIT_TEMP_HIGH,
+	AXP717_IRQ_BC_USB_CHNG = 30,
+	AXP717_IRQ_BC_USB_DONE,
+	AXP717_IRQ_TYPEC_PLUGIN = 37,
+	AXP717_IRQ_TYPEC_REMOVE,
+};
+
 enum axp803_irqs {
 	AXP803_IRQ_ACIN_OVER_V = 1,
 	AXP803_IRQ_ACIN_PLUGIN,
@@ -728,7 +962,7 @@ struct axp20x_dev {
 	unsigned long			irq_flags;
 	struct regmap			*regmap;
 	struct regmap_irq_chip_data	*regmap_irqc;
-	long				variant;
+	enum axp20x_variants		variant;
 	int                             nr_cells;
 	const struct mfd_cell           *cells;
 	const struct regmap_config	*regmap_cfg;
diff --git a/include/linux/mfd/bcm590xx.h b/include/linux/mfd/bcm590xx.h
index 6b8791da6119..5a5783abd47b 100644
--- a/include/linux/mfd/bcm590xx.h
+++ b/include/linux/mfd/bcm590xx.h
@@ -13,6 +13,26 @@
 #include <linux/i2c.h>
 #include <linux/regmap.h>
 
+/* PMU ID register values; also used as device type */
+#define BCM590XX_PMUID_BCM59054		0x54
+#define BCM590XX_PMUID_BCM59056		0x56
+
+/* Known chip revision IDs */
+#define BCM59054_REV_DIGITAL_A1		1
+#define BCM59054_REV_ANALOG_A1		2
+
+#define BCM59056_REV_DIGITAL_A0		1
+#define BCM59056_REV_ANALOG_A0		1
+
+#define BCM59056_REV_DIGITAL_B0		2
+#define BCM59056_REV_ANALOG_B0		2
+
+/* regmap types */
+enum bcm590xx_regmap_type {
+	BCM590XX_REGMAP_PRI,
+	BCM590XX_REGMAP_SEC,
+};
+
 /* max register address */
 #define BCM590XX_MAX_REGISTER_PRI	0xe7
 #define BCM590XX_MAX_REGISTER_SEC	0xf0
@@ -23,7 +43,13 @@ struct bcm590xx {
 	struct i2c_client *i2c_sec;
 	struct regmap *regmap_pri;
 	struct regmap *regmap_sec;
-	unsigned int id;
+
+	/* PMU ID value; also used as device type */
+	u8 pmu_id;
+
+	/* Chip revision, read from PMUREV reg */
+	u8 rev_digital;
+	u8 rev_analog;
 };
 
 #endif /*  __LINUX_MFD_BCM590XX_H */
diff --git a/include/linux/mfd/bq257xx.h b/include/linux/mfd/bq257xx.h
new file mode 100644
index 000000000000..1d6ddc7fb09f
--- /dev/null
+++ b/include/linux/mfd/bq257xx.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Register definitions for TI BQ257XX
+ * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com/
+ */
+
+#define BQ25703_CHARGE_OPTION_0			0x00
+#define BQ25703_CHARGE_CURRENT			0x02
+#define BQ25703_MAX_CHARGE_VOLT			0x04
+#define BQ25703_OTG_VOLT			0x06
+#define BQ25703_OTG_CURRENT			0x08
+#define BQ25703_INPUT_VOLTAGE			0x0a
+#define BQ25703_MIN_VSYS			0x0c
+#define BQ25703_IIN_HOST			0x0e
+#define BQ25703_CHARGER_STATUS			0x20
+#define BQ25703_PROCHOT_STATUS			0x22
+#define BQ25703_IIN_DPM				0x24
+#define BQ25703_ADCIBAT_CHG			0x28
+#define BQ25703_ADCIINCMPIN			0x2a
+#define BQ25703_ADCVSYSVBAT			0x2c
+#define BQ25703_MANUFACT_DEV_ID			0x2e
+#define BQ25703_CHARGE_OPTION_1			0x30
+#define BQ25703_CHARGE_OPTION_2			0x32
+#define BQ25703_CHARGE_OPTION_3			0x34
+#define BQ25703_ADC_OPTION			0x3a
+
+#define BQ25703_EN_LWPWR			BIT(15)
+#define BQ25703_WDTMR_ADJ_MASK			GENMASK(14, 13)
+#define BQ25703_WDTMR_DISABLE			0
+#define BQ25703_WDTMR_5_SEC			1
+#define BQ25703_WDTMR_88_SEC			2
+#define BQ25703_WDTMR_175_SEC			3
+
+#define BQ25703_ICHG_MASK			GENMASK(12, 6)
+#define BQ25703_ICHG_STEP_UA			64000
+#define BQ25703_ICHG_MIN_UA			64000
+#define BQ25703_ICHG_MAX_UA			8128000
+
+#define BQ25703_MAX_CHARGE_VOLT_MASK		GENMASK(15, 4)
+#define BQ25703_VBATREG_STEP_UV			16000
+#define BQ25703_VBATREG_MIN_UV			1024000
+#define BQ25703_VBATREG_MAX_UV			19200000
+
+#define BQ25703_OTG_VOLT_MASK			GENMASK(13, 6)
+#define BQ25703_OTG_VOLT_STEP_UV		64000
+#define BQ25703_OTG_VOLT_MIN_UV			4480000
+#define BQ25703_OTG_VOLT_MAX_UV			20800000
+#define BQ25703_OTG_VOLT_NUM_VOLT		256
+
+#define BQ25703_OTG_CUR_MASK			GENMASK(14, 8)
+#define BQ25703_OTG_CUR_STEP_UA			50000
+#define BQ25703_OTG_CUR_MAX_UA			6350000
+
+#define BQ25703_MINVSYS_MASK			GENMASK(13, 8)
+#define BQ25703_MINVSYS_STEP_UV			256000
+#define BQ25703_MINVSYS_MIN_UV			1024000
+#define BQ25703_MINVSYS_MAX_UV			16128000
+
+#define BQ25703_STS_AC_STAT			BIT(15)
+#define BQ25703_STS_IN_FCHRG			BIT(10)
+#define BQ25703_STS_IN_PCHRG			BIT(9)
+#define BQ25703_STS_FAULT_ACOV			BIT(7)
+#define BQ25703_STS_FAULT_BATOC			BIT(6)
+#define BQ25703_STS_FAULT_ACOC			BIT(5)
+
+#define BQ25703_IINDPM_MASK			GENMASK(14, 8)
+#define BQ25703_IINDPM_STEP_UA			50000
+#define BQ25703_IINDPM_MIN_UA			50000
+#define BQ25703_IINDPM_MAX_UA			6400000
+#define BQ25703_IINDPM_DEFAULT_UA		3300000
+#define BQ25703_IINDPM_OFFSET_UA		50000
+
+#define BQ25703_ADCIBAT_DISCHG_MASK		GENMASK(6, 0)
+#define BQ25703_ADCIBAT_CHG_MASK		GENMASK(14, 8)
+#define BQ25703_ADCIBAT_CHG_STEP_UA		64000
+#define BQ25703_ADCIBAT_DIS_STEP_UA		256000
+
+#define BQ25703_ADCIIN				GENMASK(15, 8)
+#define BQ25703_ADCIINCMPIN_STEP		50000
+
+#define BQ25703_ADCVSYS_MASK			GENMASK(15, 8)
+#define BQ25703_ADCVBAT_MASK			GENMASK(7, 0)
+#define BQ25703_ADCVSYSVBAT_OFFSET_UV		2880000
+#define BQ25703_ADCVSYSVBAT_STEP		64000
+
+#define BQ25703_ADC_CH_MASK			GENMASK(7, 0)
+#define BQ25703_ADC_CONV_EN			BIT(15)
+#define BQ25703_ADC_START			BIT(14)
+#define BQ25703_ADC_FULL_SCALE			BIT(13)
+#define BQ25703_ADC_CMPIN_EN			BIT(7)
+#define BQ25703_ADC_VBUS_EN			BIT(6)
+#define BQ25703_ADC_PSYS_EN			BIT(5)
+#define BQ25703_ADC_IIN_EN			BIT(4)
+#define BQ25703_ADC_IDCHG_EN			BIT(3)
+#define BQ25703_ADC_ICHG_EN			BIT(2)
+#define BQ25703_ADC_VSYS_EN			BIT(1)
+#define BQ25703_ADC_VBAT_EN			BIT(0)
+
+#define BQ25703_EN_OTG_MASK			BIT(12)
+
+struct bq257xx_device {
+	struct i2c_client *client;
+	struct regmap *regmap;
+};
diff --git a/include/linux/mfd/cgbc.h b/include/linux/mfd/cgbc.h
new file mode 100644
index 000000000000..badbec4c7033
--- /dev/null
+++ b/include/linux/mfd/cgbc.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Congatec Board Controller driver definitions
+ *
+ * Copyright (C) 2024 Bootlin
+ * Author: Thomas Richard <thomas.richard@bootlin.com>
+ */
+
+#ifndef _LINUX_MFD_CGBC_H_
+
+/**
+ * struct cgbc_version - Board Controller device version structure
+ * @feature:	Board Controller feature number
+ * @major:	Board Controller major revision
+ * @minor:	Board Controller minor revision
+ */
+struct cgbc_version {
+	unsigned char feature;
+	unsigned char major;
+	unsigned char minor;
+};
+
+/**
+ * struct cgbc_device_data - Internal representation of the Board Controller device
+ * @io_session:		Pointer to the session IO memory
+ * @io_cmd:		Pointer to the command IO memory
+ * @session:		Session id returned by the Board Controller
+ * @dev:		Pointer to kernel device structure
+ * @cgbc_version:	Board Controller version structure
+ * @mutex:		Board Controller mutex
+ */
+struct cgbc_device_data {
+	void __iomem		*io_session;
+	void __iomem		*io_cmd;
+	u8			session;
+	struct device		*dev;
+	struct cgbc_version	version;
+	struct mutex		lock;
+};
+
+int cgbc_command(struct cgbc_device_data *cgbc, void *cmd, unsigned int cmd_size,
+		 void *data, unsigned int data_size, u8 *status);
+
+#endif /*_LINUX_MFD_CGBC_H_*/
diff --git a/include/linux/mfd/core.h b/include/linux/mfd/core.h
index 47e7a3a61ce6..faeea7abd688 100644
--- a/include/linux/mfd/core.h
+++ b/include/linux/mfd/core.h
@@ -72,7 +72,7 @@ struct mfd_cell {
 	int			(*resume)(struct platform_device *dev);
 
 	/* platform data passed to the sub devices drivers */
-	void			*platform_data;
+	const void		*platform_data;
 	size_t			pdata_size;
 
 	/* Matches ACPI */
@@ -92,7 +92,7 @@ struct mfd_cell {
 	 * (above) when matching OF nodes with devices that have identical
 	 * compatible strings
 	 */
-	const u64 of_reg;
+	u64 of_reg;
 
 	/* Set to 'true' to use 'of_reg' (above) - allows for of_reg=0 */
 	bool use_of_reg;
diff --git a/include/linux/mfd/cs40l50.h b/include/linux/mfd/cs40l50.h
new file mode 100644
index 000000000000..e5dc49860944
--- /dev/null
+++ b/include/linux/mfd/cs40l50.h
@@ -0,0 +1,137 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * CS40L50 Advanced Haptic Driver with waveform memory,
+ * integrated DSP, and closed-loop algorithms
+ *
+ * Copyright 2024 Cirrus Logic, Inc.
+ *
+ * Author: James Ogletree <james.ogletree@cirrus.com>
+ */
+
+#ifndef __MFD_CS40L50_H__
+#define __MFD_CS40L50_H__
+
+#include <linux/firmware/cirrus/cs_dsp.h>
+#include <linux/gpio/consumer.h>
+#include <linux/pm.h>
+#include <linux/regmap.h>
+
+/* Power Supply Configuration */
+#define CS40L50_BLOCK_ENABLES2		0x201C
+#define CS40L50_ERR_RLS			0x2034
+#define CS40L50_BST_LPMODE_SEL		0x3810
+#define CS40L50_DCM_LOW_POWER		0x1
+#define CS40L50_OVERTEMP_WARN		0x4000010
+
+/* Interrupts */
+#define CS40L50_IRQ1_INT_1		0xE010
+#define CS40L50_IRQ1_BASE		CS40L50_IRQ1_INT_1
+#define CS40L50_IRQ1_INT_2		0xE014
+#define CS40L50_IRQ1_INT_8		0xE02C
+#define CS40L50_IRQ1_INT_9		0xE030
+#define CS40L50_IRQ1_INT_10		0xE034
+#define CS40L50_IRQ1_INT_18		0xE054
+#define CS40L50_IRQ1_MASK_1		0xE090
+#define CS40L50_IRQ1_MASK_2		0xE094
+#define CS40L50_IRQ1_MASK_20		0xE0DC
+#define CS40L50_IRQ1_INT_1_OFFSET	(CS40L50_IRQ1_INT_1 - CS40L50_IRQ1_BASE)
+#define CS40L50_IRQ1_INT_2_OFFSET	(CS40L50_IRQ1_INT_2 - CS40L50_IRQ1_BASE)
+#define CS40L50_IRQ1_INT_8_OFFSET	(CS40L50_IRQ1_INT_8 - CS40L50_IRQ1_BASE)
+#define CS40L50_IRQ1_INT_9_OFFSET	(CS40L50_IRQ1_INT_9 - CS40L50_IRQ1_BASE)
+#define CS40L50_IRQ1_INT_10_OFFSET	(CS40L50_IRQ1_INT_10 - CS40L50_IRQ1_BASE)
+#define CS40L50_IRQ1_INT_18_OFFSET	(CS40L50_IRQ1_INT_18 - CS40L50_IRQ1_BASE)
+#define CS40L50_IRQ_MASK_2_OVERRIDE	0xFFDF7FFF
+#define CS40L50_IRQ_MASK_20_OVERRIDE	0x15C01000
+#define CS40L50_AMP_SHORT_MASK		BIT(31)
+#define CS40L50_DSP_QUEUE_MASK		BIT(21)
+#define CS40L50_TEMP_ERR_MASK		BIT(31)
+#define CS40L50_BST_UVP_MASK		BIT(6)
+#define CS40L50_BST_SHORT_MASK		BIT(7)
+#define CS40L50_BST_ILIMIT_MASK		BIT(18)
+#define CS40L50_UVLO_VDDBATT_MASK	BIT(16)
+#define CS40L50_GLOBAL_ERROR_MASK	BIT(15)
+
+enum cs40l50_irq_list {
+	CS40L50_DSP_QUEUE_IRQ,
+	CS40L50_GLOBAL_ERROR_IRQ,
+	CS40L50_UVLO_VDDBATT_IRQ,
+	CS40L50_BST_ILIMIT_IRQ,
+	CS40L50_BST_SHORT_IRQ,
+	CS40L50_BST_UVP_IRQ,
+	CS40L50_TEMP_ERR_IRQ,
+	CS40L50_AMP_SHORT_IRQ,
+};
+
+/* DSP */
+#define CS40L50_XMEM_PACKED_0		0x2000000
+#define CS40L50_XMEM_UNPACKED24_0	0x2800000
+#define CS40L50_SYS_INFO_ID		0x25E0000
+#define CS40L50_DSP_QUEUE_WT		0x28042C8
+#define CS40L50_DSP_QUEUE_RD		0x28042CC
+#define CS40L50_NUM_WAVES		0x2805C18
+#define CS40L50_CORE_BASE		0x2B80000
+#define CS40L50_YMEM_PACKED_0		0x2C00000
+#define CS40L50_YMEM_UNPACKED24_0	0x3400000
+#define CS40L50_PMEM_0			0x3800000
+#define CS40L50_DSP_POLL_US		1000
+#define CS40L50_DSP_TIMEOUT_COUNT	100
+#define CS40L50_RESET_PULSE_US		2200
+#define CS40L50_CP_READY_US		3100
+#define CS40L50_AUTOSUSPEND_MS		2000
+#define CS40L50_PM_ALGO			0x9F206
+#define CS40L50_GLOBAL_ERR_RLS_SET	BIT(11)
+#define CS40L50_GLOBAL_ERR_RLS_CLEAR	0
+
+enum cs40l50_wseqs {
+	CS40L50_PWR_ON,
+	CS40L50_STANDBY,
+	CS40L50_ACTIVE,
+	CS40L50_NUM_WSEQS,
+};
+
+/* DSP Queue */
+#define CS40L50_DSP_QUEUE_BASE		0x11004
+#define CS40L50_DSP_QUEUE_END		0x1101C
+#define CS40L50_DSP_QUEUE		0x11020
+#define CS40L50_PREVENT_HIBER		0x2000003
+#define CS40L50_ALLOW_HIBER		0x2000004
+#define CS40L50_SHUTDOWN		0x2000005
+#define CS40L50_SYSTEM_RESET		0x2000007
+#define CS40L50_START_I2S		0x3000002
+#define CS40L50_OWT_PUSH		0x3000008
+#define CS40L50_STOP_PLAYBACK		0x5000000
+#define CS40L50_OWT_DELETE		0xD000000
+
+/* Firmware files */
+#define CS40L50_FW			"cs40l50.wmfw"
+#define CS40L50_WT			"cs40l50.bin"
+
+/* Device */
+#define CS40L50_DEVID			0x0
+#define CS40L50_REVID			0x4
+#define CS40L50_DEVID_A			0x40A50
+#define CS40L50_REVID_B0		0xB0
+
+struct cs40l50 {
+	struct device *dev;
+	struct regmap *regmap;
+	struct mutex lock;
+	struct cs_dsp dsp;
+	struct gpio_desc *reset_gpio;
+	struct regmap_irq_chip_data *irq_data;
+	const struct firmware *fw;
+	const struct firmware *bin;
+	struct cs_dsp_wseq wseqs[CS40L50_NUM_WSEQS];
+	int irq;
+	u32 devid;
+	u32 revid;
+};
+
+int cs40l50_dsp_write(struct device *dev, struct regmap *regmap, u32 val);
+int cs40l50_probe(struct cs40l50 *cs40l50);
+int cs40l50_remove(struct cs40l50 *cs40l50);
+
+extern const struct regmap_config cs40l50_regmap;
+extern const struct dev_pm_ops cs40l50_pm_ops;
+
+#endif /* __MFD_CS40L50_H__ */
diff --git a/include/linux/mfd/cs42l43-regs.h b/include/linux/mfd/cs42l43-regs.h
new file mode 100644
index 000000000000..c39a49269cb7
--- /dev/null
+++ b/include/linux/mfd/cs42l43-regs.h
@@ -0,0 +1,1184 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * cs42l43 register definitions
+ *
+ * Copyright (c) 2022-2023 Cirrus Logic, Inc. and
+ *                         Cirrus Logic International Semiconductor Ltd.
+ */
+
+#ifndef CS42L43_CORE_REGS_H
+#define CS42L43_CORE_REGS_H
+
+/* Registers */
+#define CS42L43_GEN_INT_STAT_1					0x000000C0
+#define CS42L43_GEN_INT_MASK_1					0x000000C1
+#define CS42L43_DEVID						0x00003000
+#define CS42L43_REVID						0x00003004
+#define CS42L43_RELID						0x0000300C
+#define CS42L43_SFT_RESET					0x00003020
+#define CS42L43_DRV_CTRL1					0x00006004
+#define CS42L43_DRV_CTRL3					0x0000600C
+#define CS42L43_DRV_CTRL4					0x00006010
+#define CS42L43_DRV_CTRL_5					0x00006014
+#define CS42L43_GPIO_CTRL1					0x00006034
+#define CS42L43_GPIO_CTRL2					0x00006038
+#define CS42L43_GPIO_STS					0x0000603C
+#define CS42L43_GPIO_FN_SEL					0x00006040
+#define CS42L43_MCLK_SRC_SEL					0x00007004
+#define CS42L43_CCM_BLK_CLK_CONTROL				0x00007010
+#define CS42L43_SAMPLE_RATE1					0x00007014
+#define CS42L43_SAMPLE_RATE2					0x00007018
+#define CS42L43_SAMPLE_RATE3					0x0000701C
+#define CS42L43_SAMPLE_RATE4					0x00007020
+#define CS42L43_PLL_CONTROL					0x00007034
+#define CS42L43_FS_SELECT1					0x00007038
+#define CS42L43_FS_SELECT2					0x0000703C
+#define CS42L43_FS_SELECT3					0x00007040
+#define CS42L43_FS_SELECT4					0x00007044
+#define CS42L43_PDM_CONTROL					0x0000704C
+#define CS42L43_ASP_CLK_CONFIG1					0x00007058
+#define CS42L43_ASP_CLK_CONFIG2					0x0000705C
+#define CS42L43_OSC_DIV_SEL					0x00007068
+#define CS42L43_ADC_B_CTRL1					0x00008000
+#define CS42L43_ADC_B_CTRL2					0x00008004
+#define CS42L43_DECIM_HPF_WNF_CTRL1				0x0000803C
+#define CS42L43_DECIM_HPF_WNF_CTRL2				0x00008040
+#define CS42L43_DECIM_HPF_WNF_CTRL3				0x00008044
+#define CS42L43_DECIM_HPF_WNF_CTRL4				0x00008048
+#define CS42L43_DMIC_PDM_CTRL					0x0000804C
+#define CS42L43_DECIM_VOL_CTRL_CH1_CH2				0x00008050
+#define CS42L43_DECIM_VOL_CTRL_CH3_CH4				0x00008054
+#define CS42L43_DECIM_VOL_CTRL_UPDATE				0x00008058
+#define CS42L43_INTP_VOLUME_CTRL1				0x00009008
+#define CS42L43_INTP_VOLUME_CTRL2				0x0000900C
+#define CS42L43_AMP1_2_VOL_RAMP					0x00009010
+#define CS42L43_ASP_CTRL					0x0000A000
+#define CS42L43_ASP_FSYNC_CTRL1					0x0000A004
+#define CS42L43_ASP_FSYNC_CTRL2					0x0000A008
+#define CS42L43_ASP_FSYNC_CTRL3					0x0000A00C
+#define CS42L43_ASP_FSYNC_CTRL4					0x0000A010
+#define CS42L43_ASP_DATA_CTRL					0x0000A018
+#define CS42L43_ASP_RX_EN					0x0000A020
+#define CS42L43_ASP_TX_EN					0x0000A024
+#define CS42L43_ASP_RX_CH1_CTRL					0x0000A028
+#define CS42L43_ASP_RX_CH2_CTRL					0x0000A02C
+#define CS42L43_ASP_RX_CH3_CTRL					0x0000A030
+#define CS42L43_ASP_RX_CH4_CTRL					0x0000A034
+#define CS42L43_ASP_RX_CH5_CTRL					0x0000A038
+#define CS42L43_ASP_RX_CH6_CTRL					0x0000A03C
+#define CS42L43_ASP_TX_CH1_CTRL					0x0000A068
+#define CS42L43_ASP_TX_CH2_CTRL					0x0000A06C
+#define CS42L43_ASP_TX_CH3_CTRL					0x0000A070
+#define CS42L43_ASP_TX_CH4_CTRL					0x0000A074
+#define CS42L43_ASP_TX_CH5_CTRL					0x0000A078
+#define CS42L43_ASP_TX_CH6_CTRL					0x0000A07C
+#define CS42L43_OTP_REVISION_ID					0x0000B02C
+#define CS42L43_ASPTX1_INPUT					0x0000C200
+#define CS42L43_ASPTX2_INPUT					0x0000C210
+#define CS42L43_ASPTX3_INPUT					0x0000C220
+#define CS42L43_ASPTX4_INPUT					0x0000C230
+#define CS42L43_ASPTX5_INPUT					0x0000C240
+#define CS42L43_ASPTX6_INPUT					0x0000C250
+#define CS42L43_SWIRE_DP1_CH1_INPUT				0x0000C280
+#define CS42L43_SWIRE_DP1_CH2_INPUT				0x0000C290
+#define CS42L43_SWIRE_DP1_CH3_INPUT				0x0000C2A0
+#define CS42L43_SWIRE_DP1_CH4_INPUT				0x0000C2B0
+#define CS42L43_SWIRE_DP2_CH1_INPUT				0x0000C2C0
+#define CS42L43_SWIRE_DP2_CH2_INPUT				0x0000C2D0
+#define CS42L43_SWIRE_DP3_CH1_INPUT				0x0000C2E0
+#define CS42L43_SWIRE_DP3_CH2_INPUT				0x0000C2F0
+#define CS42L43_SWIRE_DP4_CH1_INPUT				0x0000C300
+#define CS42L43_SWIRE_DP4_CH2_INPUT				0x0000C310
+#define CS42L43_ASRC_INT1_INPUT1				0x0000C400
+#define CS42L43_ASRC_INT2_INPUT1				0x0000C410
+#define CS42L43_ASRC_INT3_INPUT1				0x0000C420
+#define CS42L43_ASRC_INT4_INPUT1				0x0000C430
+#define CS42L43_ASRC_DEC1_INPUT1				0x0000C440
+#define CS42L43_ASRC_DEC2_INPUT1				0x0000C450
+#define CS42L43_ASRC_DEC3_INPUT1				0x0000C460
+#define CS42L43_ASRC_DEC4_INPUT1				0x0000C470
+#define CS42L43_ISRC1INT1_INPUT1				0x0000C500
+#define CS42L43_ISRC1INT2_INPUT1				0x0000C510
+#define CS42L43_ISRC1DEC1_INPUT1				0x0000C520
+#define CS42L43_ISRC1DEC2_INPUT1				0x0000C530
+#define CS42L43_ISRC2INT1_INPUT1				0x0000C540
+#define CS42L43_ISRC2INT2_INPUT1				0x0000C550
+#define CS42L43_ISRC2DEC1_INPUT1				0x0000C560
+#define CS42L43_ISRC2DEC2_INPUT1				0x0000C570
+#define CS42L43_EQ1MIX_INPUT1					0x0000C580
+#define CS42L43_EQ1MIX_INPUT2					0x0000C584
+#define CS42L43_EQ1MIX_INPUT3					0x0000C588
+#define CS42L43_EQ1MIX_INPUT4					0x0000C58C
+#define CS42L43_EQ2MIX_INPUT1					0x0000C590
+#define CS42L43_EQ2MIX_INPUT2					0x0000C594
+#define CS42L43_EQ2MIX_INPUT3					0x0000C598
+#define CS42L43_EQ2MIX_INPUT4					0x0000C59C
+#define CS42L43_SPDIF1_INPUT1					0x0000C600
+#define CS42L43_SPDIF2_INPUT1					0x0000C610
+#define CS42L43_AMP1MIX_INPUT1					0x0000C620
+#define CS42L43_AMP1MIX_INPUT2					0x0000C624
+#define CS42L43_AMP1MIX_INPUT3					0x0000C628
+#define CS42L43_AMP1MIX_INPUT4					0x0000C62C
+#define CS42L43_AMP2MIX_INPUT1					0x0000C630
+#define CS42L43_AMP2MIX_INPUT2					0x0000C634
+#define CS42L43_AMP2MIX_INPUT3					0x0000C638
+#define CS42L43_AMP2MIX_INPUT4					0x0000C63C
+#define CS42L43_AMP3MIX_INPUT1					0x0000C640
+#define CS42L43_AMP3MIX_INPUT2					0x0000C644
+#define CS42L43_AMP3MIX_INPUT3					0x0000C648
+#define CS42L43_AMP3MIX_INPUT4					0x0000C64C
+#define CS42L43_AMP4MIX_INPUT1					0x0000C650
+#define CS42L43_AMP4MIX_INPUT2					0x0000C654
+#define CS42L43_AMP4MIX_INPUT3					0x0000C658
+#define CS42L43_AMP4MIX_INPUT4					0x0000C65C
+#define CS42L43_ASRC_INT_ENABLES				0x0000E000
+#define CS42L43_ASRC_DEC_ENABLES				0x0000E004
+#define CS42L43_PDNCNTL						0x00010000
+#define CS42L43_RINGSENSE_DEB_CTRL				0x0001001C
+#define CS42L43_TIPSENSE_DEB_CTRL				0x00010020
+#define CS42L43_TIP_RING_SENSE_INTERRUPT_STATUS			0x00010028
+#define CS42L43_HS2						0x00010040
+#define CS42L43_HS_STAT						0x00010048
+#define CS42L43_MCU_SW_INTERRUPT				0x00010094
+#define CS42L43_STEREO_MIC_CTRL					0x000100A4
+#define CS42L43_STEREO_MIC_CLAMP_CTRL				0x000100C4
+#define CS42L43_BLOCK_EN2					0x00010104
+#define CS42L43_BLOCK_EN3					0x00010108
+#define CS42L43_BLOCK_EN4					0x0001010C
+#define CS42L43_BLOCK_EN5					0x00010110
+#define CS42L43_BLOCK_EN6					0x00010114
+#define CS42L43_BLOCK_EN7					0x00010118
+#define CS42L43_BLOCK_EN8					0x0001011C
+#define CS42L43_BLOCK_EN9					0x00010120
+#define CS42L43_BLOCK_EN10					0x00010124
+#define CS42L43_BLOCK_EN11					0x00010128
+#define CS42L43_TONE_CH1_CTRL					0x00010134
+#define CS42L43_TONE_CH2_CTRL					0x00010138
+#define CS42L43_MIC_DETECT_CONTROL_1				0x00011074
+#define CS42L43_DETECT_STATUS_1					0x0001107C
+#define CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL		0x00011090
+#define CS42L43_MIC_DETECT_CONTROL_ANDROID			0x000110B0
+#define CS42L43_ISRC1_CTRL					0x00012004
+#define CS42L43_ISRC2_CTRL					0x00013004
+#define CS42L43_CTRL_REG					0x00014000
+#define CS42L43_FDIV_FRAC					0x00014004
+#define CS42L43_CAL_RATIO					0x00014008
+#define CS42L43_SPI_CLK_CONFIG1					0x00016004
+#define CS42L43_SPI_CONFIG1					0x00016010
+#define CS42L43_SPI_CONFIG2					0x00016014
+#define CS42L43_SPI_CONFIG3					0x00016018
+#define CS42L43_SPI_CONFIG4					0x00016024
+#define CS42L43_SPI_STATUS1					0x00016100
+#define CS42L43_SPI_STATUS2					0x00016104
+#define CS42L43_TRAN_CONFIG1					0x00016200
+#define CS42L43_TRAN_CONFIG2					0x00016204
+#define CS42L43_TRAN_CONFIG3					0x00016208
+#define CS42L43_TRAN_CONFIG4					0x0001620C
+#define CS42L43_TRAN_CONFIG5					0x00016220
+#define CS42L43_TRAN_CONFIG6					0x00016224
+#define CS42L43_TRAN_CONFIG7					0x00016228
+#define CS42L43_TRAN_CONFIG8					0x0001622C
+#define CS42L43_TRAN_STATUS1					0x00016300
+#define CS42L43_TRAN_STATUS2					0x00016304
+#define CS42L43_TRAN_STATUS3					0x00016308
+#define CS42L43_TX_DATA						0x00016400
+#define CS42L43_RX_DATA						0x00016600
+#define CS42L43_DACCNFG1					0x00017000
+#define CS42L43_DACCNFG2					0x00017004
+#define CS42L43_HPPATHVOL					0x0001700C
+#define CS42L43_PGAVOL						0x00017014
+#define CS42L43_LOADDETRESULTS					0x00017018
+#define CS42L43_LOADDETENA					0x00017024
+#define CS42L43_CTRL						0x00017028
+#define CS42L43_COEFF_DATA_IN0					0x00018000
+#define CS42L43_COEFF_RD_WR0					0x00018008
+#define CS42L43_INIT_DONE0					0x00018010
+#define CS42L43_START_EQZ0					0x00018014
+#define CS42L43_MUTE_EQ_IN0					0x0001801C
+#define CS42L43_DECIM_INT					0x0001B000
+#define CS42L43_EQ_INT						0x0001B004
+#define CS42L43_ASP_INT						0x0001B008
+#define CS42L43_PLL_INT						0x0001B00C
+#define CS42L43_SOFT_INT					0x0001B010
+#define CS42L43_SWIRE_INT					0x0001B014
+#define CS42L43_MSM_INT						0x0001B018
+#define CS42L43_ACC_DET_INT					0x0001B01C
+#define CS42L43_I2C_TGT_INT					0x0001B020
+#define CS42L43_SPI_MSTR_INT					0x0001B024
+#define CS42L43_SW_TO_SPI_BRIDGE_INT				0x0001B028
+#define CS42L43_OTP_INT						0x0001B02C
+#define CS42L43_CLASS_D_AMP_INT					0x0001B030
+#define CS42L43_GPIO_INT					0x0001B034
+#define CS42L43_ASRC_INT					0x0001B038
+#define CS42L43_HPOUT_INT					0x0001B03C
+#define CS42L43_DECIM_MASK					0x0001B0A0
+#define CS42L43_EQ_MIX_MASK					0x0001B0A4
+#define CS42L43_ASP_MASK					0x0001B0A8
+#define CS42L43_PLL_MASK					0x0001B0AC
+#define CS42L43_SOFT_MASK					0x0001B0B0
+#define CS42L43_SWIRE_MASK					0x0001B0B4
+#define CS42L43_MSM_MASK					0x0001B0B8
+#define CS42L43_ACC_DET_MASK					0x0001B0BC
+#define CS42L43_I2C_TGT_MASK					0x0001B0C0
+#define CS42L43_SPI_MSTR_MASK					0x0001B0C4
+#define CS42L43_SW_TO_SPI_BRIDGE_MASK				0x0001B0C8
+#define CS42L43_OTP_MASK					0x0001B0CC
+#define CS42L43_CLASS_D_AMP_MASK				0x0001B0D0
+#define CS42L43_GPIO_INT_MASK					0x0001B0D4
+#define CS42L43_ASRC_MASK					0x0001B0D8
+#define CS42L43_HPOUT_MASK					0x0001B0DC
+#define CS42L43_DECIM_INT_SHADOW				0x0001B300
+#define CS42L43_EQ_MIX_INT_SHADOW				0x0001B304
+#define CS42L43_ASP_INT_SHADOW					0x0001B308
+#define CS42L43_PLL_INT_SHADOW					0x0001B30C
+#define CS42L43_SOFT_INT_SHADOW					0x0001B310
+#define CS42L43_SWIRE_INT_SHADOW				0x0001B314
+#define CS42L43_MSM_INT_SHADOW					0x0001B318
+#define CS42L43_ACC_DET_INT_SHADOW				0x0001B31C
+#define CS42L43_I2C_TGT_INT_SHADOW				0x0001B320
+#define CS42L43_SPI_MSTR_INT_SHADOW				0x0001B324
+#define CS42L43_SW_TO_SPI_BRIDGE_SHADOW				0x0001B328
+#define CS42L43_OTP_INT_SHADOW					0x0001B32C
+#define CS42L43_CLASS_D_AMP_INT_SHADOW				0x0001B330
+#define CS42L43_GPIO_SHADOW					0x0001B334
+#define CS42L43_ASRC_SHADOW					0x0001B338
+#define CS42L43_HP_OUT_SHADOW					0x0001B33C
+#define CS42L43_BOOT_CONTROL					0x00101000
+#define CS42L43_BLOCK_EN					0x00101008
+#define CS42L43_SHUTTER_CONTROL					0x0010100C
+#define CS42L43_MCU_SW_REV					0x00114000
+#define CS42L43_PATCH_START_ADDR				0x00114004
+#define CS42L43_NEED_CONFIGS					0x0011400C
+#define CS42L43_BOOT_STATUS					0x0011401C
+#define CS42L43_FW_SH_BOOT_CFG_NEED_CONFIGS			0x0011F8F8
+#define CS42L43_FW_MISSION_CTRL_NEED_CONFIGS			0x0011FE00
+#define CS42L43_FW_MISSION_CTRL_HAVE_CONFIGS			0x0011FE04
+#define CS42L43_FW_MISSION_CTRL_MM_CTRL_SELECTION		0x0011FE0C
+#define CS42L43_FW_MISSION_CTRL_MM_MCU_CFG_REG			0x0011FE10
+#define CS42L43_MCU_RAM_MAX					0x0011FFFF
+
+/* CS42L43_DEVID */
+#define CS42L43_DEVID_VAL					0x00042A43
+
+/* CS42L43_GEN_INT_STAT_1 */
+#define CS42L43_INT_STAT_GEN1_MASK				0x00000001
+#define CS42L43_INT_STAT_GEN1_SHIFT				0
+
+/* CS42L43_SFT_RESET */
+#define CS42L43_SFT_RESET_MASK					0xFF000000
+#define CS42L43_SFT_RESET_SHIFT					24
+
+#define CS42L43_SFT_RESET_VAL					0x5A000000
+
+/* CS42L43_DRV_CTRL1 */
+#define CS42L43_ASP_DOUT_DRV_MASK				0x00038000
+#define CS42L43_ASP_DOUT_DRV_SHIFT				15
+#define CS42L43_ASP_FSYNC_DRV_MASK				0x00000E00
+#define CS42L43_ASP_FSYNC_DRV_SHIFT				9
+#define CS42L43_ASP_BCLK_DRV_MASK				0x000001C0
+#define CS42L43_ASP_BCLK_DRV_SHIFT				6
+
+/* CS42L43_DRV_CTRL3 */
+#define CS42L43_I2C_ADDR_DRV_MASK				0x30000000
+#define CS42L43_I2C_ADDR_DRV_SHIFT				28
+#define CS42L43_I2C_SDA_DRV_MASK				0x0C000000
+#define CS42L43_I2C_SDA_DRV_SHIFT				26
+#define CS42L43_PDMOUT2_CLK_DRV_MASK				0x00E00000
+#define CS42L43_PDMOUT2_CLK_DRV_SHIFT				21
+#define CS42L43_PDMOUT2_DATA_DRV_MASK				0x001C0000
+#define CS42L43_PDMOUT2_DATA_DRV_SHIFT				18
+#define CS42L43_PDMOUT1_CLK_DRV_MASK				0x00038000
+#define CS42L43_PDMOUT1_CLK_DRV_SHIFT				15
+#define CS42L43_PDMOUT1_DATA_DRV_MASK				0x00007000
+#define CS42L43_PDMOUT1_DATA_DRV_SHIFT				12
+#define CS42L43_SPI_MISO_DRV_MASK				0x00000038
+#define CS42L43_SPI_MISO_DRV_SHIFT				3
+
+/* CS42L43_DRV_CTRL4 */
+#define CS42L43_GPIO3_DRV_MASK					0x00000E00
+#define CS42L43_GPIO3_DRV_SHIFT					9
+#define CS42L43_GPIO2_DRV_MASK					0x000001C0
+#define CS42L43_GPIO2_DRV_SHIFT					6
+#define CS42L43_GPIO1_DRV_MASK					0x00000038
+#define CS42L43_GPIO1_DRV_SHIFT					3
+
+/* CS42L43_DRV_CTRL_5 */
+#define CS42L43_I2C_SCL_DRV_MASK				0x18000000
+#define CS42L43_I2C_SCL_DRV_SHIFT				27
+#define CS42L43_SPI_SCK_DRV_MASK				0x07000000
+#define CS42L43_SPI_SCK_DRV_SHIFT				24
+#define CS42L43_SPI_MOSI_DRV_MASK				0x00E00000
+#define CS42L43_SPI_MOSI_DRV_SHIFT				21
+#define CS42L43_SPI_SSB_DRV_MASK				0x001C0000
+#define CS42L43_SPI_SSB_DRV_SHIFT				18
+#define CS42L43_ASP_DIN_DRV_MASK				0x000001C0
+#define CS42L43_ASP_DIN_DRV_SHIFT				6
+
+/* CS42L43_GPIO_CTRL1 */
+#define CS42L43_GPIO3_POL_MASK					0x00040000
+#define CS42L43_GPIO3_POL_SHIFT					18
+#define CS42L43_GPIO2_POL_MASK					0x00020000
+#define CS42L43_GPIO2_POL_SHIFT					17
+#define CS42L43_GPIO1_POL_MASK					0x00010000
+#define CS42L43_GPIO1_POL_SHIFT					16
+#define CS42L43_GPIO3_LVL_MASK					0x00000400
+#define CS42L43_GPIO3_LVL_SHIFT					10
+#define CS42L43_GPIO2_LVL_MASK					0x00000200
+#define CS42L43_GPIO2_LVL_SHIFT					9
+#define CS42L43_GPIO1_LVL_MASK					0x00000100
+#define CS42L43_GPIO1_LVL_SHIFT					8
+#define CS42L43_GPIO3_DIR_MASK					0x00000004
+#define CS42L43_GPIO3_DIR_SHIFT					2
+#define CS42L43_GPIO2_DIR_MASK					0x00000002
+#define CS42L43_GPIO2_DIR_SHIFT					1
+#define CS42L43_GPIO1_DIR_MASK					0x00000001
+#define CS42L43_GPIO1_DIR_SHIFT					0
+
+/* CS42L43_GPIO_CTRL2 */
+#define CS42L43_GPIO3_DEGLITCH_BYP_MASK				0x00000004
+#define CS42L43_GPIO3_DEGLITCH_BYP_SHIFT			2
+#define CS42L43_GPIO2_DEGLITCH_BYP_MASK				0x00000002
+#define CS42L43_GPIO2_DEGLITCH_BYP_SHIFT			1
+#define CS42L43_GPIO1_DEGLITCH_BYP_MASK				0x00000001
+#define CS42L43_GPIO1_DEGLITCH_BYP_SHIFT			0
+
+/* CS42L43_GPIO_STS */
+#define CS42L43_GPIO3_STS_MASK					0x00000004
+#define CS42L43_GPIO3_STS_SHIFT					2
+#define CS42L43_GPIO2_STS_MASK					0x00000002
+#define CS42L43_GPIO2_STS_SHIFT					1
+#define CS42L43_GPIO1_STS_MASK					0x00000001
+#define CS42L43_GPIO1_STS_SHIFT					0
+
+/* CS42L43_GPIO_FN_SEL */
+#define CS42L43_GPIO3_FN_SEL_MASK				0x00000004
+#define CS42L43_GPIO3_FN_SEL_SHIFT				2
+#define CS42L43_GPIO1_FN_SEL_MASK				0x00000001
+#define CS42L43_GPIO1_FN_SEL_SHIFT				0
+
+/* CS42L43_MCLK_SRC_SEL */
+#define CS42L43_OSC_PLL_MCLK_SEL_MASK				0x00000001
+#define CS42L43_OSC_PLL_MCLK_SEL_SHIFT				0
+
+/* CS42L43_SAMPLE_RATE1..CS42L43_SAMPLE_RATE4 */
+#define CS42L43_SAMPLE_RATE_MASK				0x0000001F
+#define CS42L43_SAMPLE_RATE_SHIFT				0
+
+/* CS42L43_PLL_CONTROL */
+#define CS42L43_PLL_REFCLK_EN_MASK				0x00000008
+#define CS42L43_PLL_REFCLK_EN_SHIFT				3
+#define CS42L43_PLL_REFCLK_DIV_MASK				0x00000006
+#define CS42L43_PLL_REFCLK_DIV_SHIFT				1
+#define CS42L43_PLL_REFCLK_SRC_MASK				0x00000001
+#define CS42L43_PLL_REFCLK_SRC_SHIFT				0
+
+/* CS42L43_FS_SELECT1 */
+#define CS42L43_ASP_RATE_MASK					0x00000003
+#define CS42L43_ASP_RATE_SHIFT					0
+
+/* CS42L43_FS_SELECT2 */
+#define CS42L43_ASRC_DEC_OUT_RATE_MASK				0x000000C0
+#define CS42L43_ASRC_DEC_OUT_RATE_SHIFT				6
+#define CS42L43_ASRC_INT_OUT_RATE_MASK				0x00000030
+#define CS42L43_ASRC_INT_OUT_RATE_SHIFT				4
+#define CS42L43_ASRC_DEC_IN_RATE_MASK				0x0000000C
+#define CS42L43_ASRC_DEC_IN_RATE_SHIFT				2
+#define CS42L43_ASRC_INT_IN_RATE_MASK				0x00000003
+#define CS42L43_ASRC_INT_IN_RATE_SHIFT				0
+
+/* CS42L43_FS_SELECT3 */
+#define CS42L43_HPOUT_RATE_MASK					0x0000C000
+#define CS42L43_HPOUT_RATE_SHIFT				14
+#define CS42L43_EQZ_RATE_MASK					0x00003000
+#define CS42L43_EQZ_RATE_SHIFT					12
+#define CS42L43_DIAGGEN_RATE_MASK				0x00000C00
+#define CS42L43_DIAGGEN_RATE_SHIFT				10
+#define CS42L43_DECIM_CH4_RATE_MASK				0x00000300
+#define CS42L43_DECIM_CH4_RATE_SHIFT				8
+#define CS42L43_DECIM_CH3_RATE_MASK				0x000000C0
+#define CS42L43_DECIM_CH3_RATE_SHIFT				6
+#define CS42L43_DECIM_CH2_RATE_MASK				0x00000030
+#define CS42L43_DECIM_CH2_RATE_SHIFT				4
+#define CS42L43_DECIM_CH1_RATE_MASK				0x0000000C
+#define CS42L43_DECIM_CH1_RATE_SHIFT				2
+#define CS42L43_AMP1_2_RATE_MASK				0x00000003
+#define CS42L43_AMP1_2_RATE_SHIFT				0
+
+/* CS42L43_FS_SELECT4 */
+#define CS42L43_SW_DP7_RATE_MASK				0x00C00000
+#define CS42L43_SW_DP7_RATE_SHIFT				22
+#define CS42L43_SW_DP6_RATE_MASK				0x00300000
+#define CS42L43_SW_DP6_RATE_SHIFT				20
+#define CS42L43_SPDIF_RATE_MASK					0x000C0000
+#define CS42L43_SPDIF_RATE_SHIFT				18
+#define CS42L43_SW_DP5_RATE_MASK				0x00030000
+#define CS42L43_SW_DP5_RATE_SHIFT				16
+#define CS42L43_SW_DP4_RATE_MASK				0x0000C000
+#define CS42L43_SW_DP4_RATE_SHIFT				14
+#define CS42L43_SW_DP3_RATE_MASK				0x00003000
+#define CS42L43_SW_DP3_RATE_SHIFT				12
+#define CS42L43_SW_DP2_RATE_MASK				0x00000C00
+#define CS42L43_SW_DP2_RATE_SHIFT				10
+#define CS42L43_SW_DP1_RATE_MASK				0x00000300
+#define CS42L43_SW_DP1_RATE_SHIFT				8
+#define CS42L43_ISRC2_LOW_RATE_MASK				0x000000C0
+#define CS42L43_ISRC2_LOW_RATE_SHIFT				6
+#define CS42L43_ISRC2_HIGH_RATE_MASK				0x00000030
+#define CS42L43_ISRC2_HIGH_RATE_SHIFT				4
+#define CS42L43_ISRC1_LOW_RATE_MASK				0x0000000C
+#define CS42L43_ISRC1_LOW_RATE_SHIFT				2
+#define CS42L43_ISRC1_HIGH_RATE_MASK				0x00000003
+#define CS42L43_ISRC1_HIGH_RATE_SHIFT				0
+
+/* CS42L43_PDM_CONTROL */
+#define CS42L43_PDM2_CLK_DIV_MASK				0x0000000C
+#define CS42L43_PDM2_CLK_DIV_SHIFT				2
+#define CS42L43_PDM1_CLK_DIV_MASK				0x00000003
+#define CS42L43_PDM1_CLK_DIV_SHIFT				0
+
+/* CS42L43_ASP_CLK_CONFIG1 */
+#define CS42L43_ASP_BCLK_N_MASK					0x03FF0000
+#define CS42L43_ASP_BCLK_N_SHIFT				16
+#define CS42L43_ASP_BCLK_M_MASK					0x000003FF
+#define CS42L43_ASP_BCLK_M_SHIFT				0
+
+/* CS42L43_ASP_CLK_CONFIG2 */
+#define CS42L43_ASP_MASTER_MODE_MASK				0x00000002
+#define CS42L43_ASP_MASTER_MODE_SHIFT				1
+#define CS42L43_ASP_BCLK_INV_MASK				0x00000001
+#define CS42L43_ASP_BCLK_INV_SHIFT				0
+
+/* CS42L43_OSC_DIV_SEL */
+#define CS42L43_OSC_DIV2_EN_MASK				0x00000001
+#define CS42L43_OSC_DIV2_EN_SHIFT				0
+
+/* CS42L43_ADC_B_CTRL1..CS42L43_ADC_B_CTRL1 */
+#define CS42L43_PGA_WIDESWING_MODE_EN_MASK			0x00000080
+#define CS42L43_PGA_WIDESWING_MODE_EN_SHIFT			7
+#define CS42L43_ADC_AIN_SEL_MASK				0x00000010
+#define CS42L43_ADC_AIN_SEL_SHIFT				4
+#define CS42L43_ADC_PGA_GAIN_MASK				0x0000000F
+#define CS42L43_ADC_PGA_GAIN_SHIFT				0
+
+/* CS42L43_DECIM_HPF_WNF_CTRL1..CS42L43_DECIM_HPF_WNF_CTRL4 */
+#define CS42L43_DECIM_WNF_CF_MASK				0x00000070
+#define CS42L43_DECIM_WNF_CF_SHIFT				4
+#define CS42L43_DECIM_WNF_EN_MASK				0x00000008
+#define CS42L43_DECIM_WNF_EN_SHIFT				3
+#define CS42L43_DECIM_HPF_CF_MASK				0x00000006
+#define CS42L43_DECIM_HPF_CF_SHIFT				1
+#define CS42L43_DECIM_HPF_EN_MASK				0x00000001
+#define CS42L43_DECIM_HPF_EN_SHIFT				0
+
+/* CS42L43_DMIC_PDM_CTRL */
+#define CS42L43_PDM2R_INV_MASK					0x00000020
+#define CS42L43_PDM2R_INV_SHIFT					5
+#define CS42L43_PDM2L_INV_MASK					0x00000010
+#define CS42L43_PDM2L_INV_SHIFT					4
+#define CS42L43_PDM1R_INV_MASK					0x00000008
+#define CS42L43_PDM1R_INV_SHIFT					3
+#define CS42L43_PDM1L_INV_MASK					0x00000004
+#define CS42L43_PDM1L_INV_SHIFT					2
+
+/* CS42L43_DECIM_VOL_CTRL_CH1_CH2 */
+#define CS42L43_DECIM2_MUTE_MASK				0x80000000
+#define CS42L43_DECIM2_MUTE_SHIFT				31
+#define CS42L43_DECIM2_VOL_MASK					0x3FC00000
+#define CS42L43_DECIM2_VOL_SHIFT				22
+#define CS42L43_DECIM2_VD_RAMP_MASK				0x00380000
+#define CS42L43_DECIM2_VD_RAMP_SHIFT				19
+#define CS42L43_DECIM2_VI_RAMP_MASK				0x00070000
+#define CS42L43_DECIM2_VI_RAMP_SHIFT				16
+#define CS42L43_DECIM1_MUTE_MASK				0x00008000
+#define CS42L43_DECIM1_MUTE_SHIFT				15
+#define CS42L43_DECIM1_VOL_MASK					0x00003FC0
+#define CS42L43_DECIM1_VOL_SHIFT				6
+#define CS42L43_DECIM1_VD_RAMP_MASK				0x00000038
+#define CS42L43_DECIM1_VD_RAMP_SHIFT				3
+#define CS42L43_DECIM1_VI_RAMP_MASK				0x00000007
+#define CS42L43_DECIM1_VI_RAMP_SHIFT				0
+
+/* CS42L43_DECIM_VOL_CTRL_CH3_CH4 */
+#define CS42L43_DECIM4_MUTE_MASK				0x80000000
+#define CS42L43_DECIM4_MUTE_SHIFT				31
+#define CS42L43_DECIM4_VOL_MASK					0x3FC00000
+#define CS42L43_DECIM4_VOL_SHIFT				22
+#define CS42L43_DECIM4_VD_RAMP_MASK				0x00380000
+#define CS42L43_DECIM4_VD_RAMP_SHIFT				19
+#define CS42L43_DECIM4_VI_RAMP_MASK				0x00070000
+#define CS42L43_DECIM4_VI_RAMP_SHIFT				16
+#define CS42L43_DECIM3_MUTE_MASK				0x00008000
+#define CS42L43_DECIM3_MUTE_SHIFT				15
+#define CS42L43_DECIM3_VOL_MASK					0x00003FC0
+#define CS42L43_DECIM3_VOL_SHIFT				6
+#define CS42L43_DECIM3_VD_RAMP_MASK				0x00000038
+#define CS42L43_DECIM3_VD_RAMP_SHIFT				3
+#define CS42L43_DECIM3_VI_RAMP_MASK				0x00000007
+#define CS42L43_DECIM3_VI_RAMP_SHIFT				0
+
+/* CS42L43_DECIM_VOL_CTRL_UPDATE */
+#define CS42L43_DECIM4_VOL_UPDATE_MASK				0x00000008
+#define CS42L43_DECIM4_VOL_UPDATE_SHIFT				3
+#define CS42L43_DECIM3_VOL_UPDATE_MASK				0x00000004
+#define CS42L43_DECIM3_VOL_UPDATE_SHIFT				2
+#define CS42L43_DECIM2_VOL_UPDATE_MASK				0x00000002
+#define CS42L43_DECIM2_VOL_UPDATE_SHIFT				1
+#define CS42L43_DECIM1_VOL_UPDATE_MASK				0x00000001
+#define CS42L43_DECIM1_VOL_UPDATE_SHIFT				0
+
+/* CS42L43_INTP_VOLUME_CTRL1..CS42L43_INTP_VOLUME_CTRL2 */
+#define CS42L43_AMP1_2_VU_MASK					0x00000200
+#define CS42L43_AMP1_2_VU_SHIFT					9
+#define CS42L43_AMP_MUTE_MASK					0x00000100
+#define CS42L43_AMP_MUTE_SHIFT					8
+#define CS42L43_AMP_VOL_MASK					0x000000FF
+#define CS42L43_AMP_VOL_SHIFT					0
+
+/* CS42L43_AMP1_2_VOL_RAMP */
+#define CS42L43_AMP1_2_VD_RAMP_MASK				0x00000070
+#define CS42L43_AMP1_2_VD_RAMP_SHIFT				4
+#define CS42L43_AMP1_2_VI_RAMP_MASK				0x00000007
+#define CS42L43_AMP1_2_VI_RAMP_SHIFT				0
+
+/* CS42L43_ASP_CTRL */
+#define CS42L43_ASP_FSYNC_MODE_MASK				0x00000004
+#define CS42L43_ASP_FSYNC_MODE_SHIFT				2
+#define CS42L43_ASP_BCLK_EN_MASK				0x00000002
+#define CS42L43_ASP_BCLK_EN_SHIFT				1
+#define CS42L43_ASP_FSYNC_EN_MASK				0x00000001
+#define CS42L43_ASP_FSYNC_EN_SHIFT				0
+
+/* CS42L43_ASP_FSYNC_CTRL1 */
+#define CS42L43_ASP_FSYNC_M_MASK				0x0007FFFF
+#define CS42L43_ASP_FSYNC_M_SHIFT				0
+
+/* CS42L43_ASP_FSYNC_CTRL3 */
+#define CS42L43_ASP_FSYNC_IN_INV_MASK				0x00000002
+#define CS42L43_ASP_FSYNC_IN_INV_SHIFT				1
+#define CS42L43_ASP_FSYNC_OUT_INV_MASK				0x00000001
+#define CS42L43_ASP_FSYNC_OUT_INV_SHIFT				0
+
+/* CS42L43_ASP_FSYNC_CTRL4 */
+#define CS42L43_ASP_NUM_BCLKS_PER_FSYNC_MASK			0x00001FFE
+#define CS42L43_ASP_NUM_BCLKS_PER_FSYNC_SHIFT			1
+
+/* CS42L43_ASP_DATA_CTRL */
+#define CS42L43_ASP_FSYNC_FRAME_START_PHASE_MASK		0x00000008
+#define CS42L43_ASP_FSYNC_FRAME_START_PHASE_SHIFT		3
+#define CS42L43_ASP_FSYNC_FRAME_START_DLY_MASK			0x00000007
+#define CS42L43_ASP_FSYNC_FRAME_START_DLY_SHIFT			0
+
+/* CS42L43_ASP_RX_EN */
+#define CS42L43_ASP_RX_CH6_EN_MASK				0x00000020
+#define CS42L43_ASP_RX_CH6_EN_SHIFT				5
+#define CS42L43_ASP_RX_CH5_EN_MASK				0x00000010
+#define CS42L43_ASP_RX_CH5_EN_SHIFT				4
+#define CS42L43_ASP_RX_CH4_EN_MASK				0x00000008
+#define CS42L43_ASP_RX_CH4_EN_SHIFT				3
+#define CS42L43_ASP_RX_CH3_EN_MASK				0x00000004
+#define CS42L43_ASP_RX_CH3_EN_SHIFT				2
+#define CS42L43_ASP_RX_CH2_EN_MASK				0x00000002
+#define CS42L43_ASP_RX_CH2_EN_SHIFT				1
+#define CS42L43_ASP_RX_CH1_EN_MASK				0x00000001
+#define CS42L43_ASP_RX_CH1_EN_SHIFT				0
+
+/* CS42L43_ASP_TX_EN */
+#define CS42L43_ASP_TX_CH6_EN_MASK				0x00000020
+#define CS42L43_ASP_TX_CH6_EN_SHIFT				5
+#define CS42L43_ASP_TX_CH5_EN_MASK				0x00000010
+#define CS42L43_ASP_TX_CH5_EN_SHIFT				4
+#define CS42L43_ASP_TX_CH4_EN_MASK				0x00000008
+#define CS42L43_ASP_TX_CH4_EN_SHIFT				3
+#define CS42L43_ASP_TX_CH3_EN_MASK				0x00000004
+#define CS42L43_ASP_TX_CH3_EN_SHIFT				2
+#define CS42L43_ASP_TX_CH2_EN_MASK				0x00000002
+#define CS42L43_ASP_TX_CH2_EN_SHIFT				1
+#define CS42L43_ASP_TX_CH1_EN_MASK				0x00000001
+#define CS42L43_ASP_TX_CH1_EN_SHIFT				0
+
+/* CS42L43_ASP_RX_CH1_CTRL..CS42L43_ASP_TX_CH6_CTRL */
+#define CS42L43_ASP_CH_WIDTH_MASK				0x001F0000
+#define CS42L43_ASP_CH_WIDTH_SHIFT				16
+#define CS42L43_ASP_CH_SLOT_MASK				0x00001FFE
+#define CS42L43_ASP_CH_SLOT_SHIFT				1
+#define CS42L43_ASP_CH_SLOT_PHASE_MASK				0x00000001
+#define CS42L43_ASP_CH_SLOT_PHASE_SHIFT				0
+
+/* CS42L43_ASPTX1_INPUT..CS42L43_AMP4MIX_INPUT4 */
+#define CS42L43_MIXER_VOL_MASK					0x00FE0000
+#define CS42L43_MIXER_VOL_SHIFT					17
+#define CS42L43_MIXER_SRC_MASK					0x000001FF
+#define CS42L43_MIXER_SRC_SHIFT					0
+
+/* CS42L43_ASRC_INT_ENABLES */
+#define CS42L43_ASRC_INT4_EN_MASK				0x00000008
+#define CS42L43_ASRC_INT4_EN_SHIFT				3
+#define CS42L43_ASRC_INT3_EN_MASK				0x00000004
+#define CS42L43_ASRC_INT3_EN_SHIFT				2
+#define CS42L43_ASRC_INT2_EN_MASK				0x00000002
+#define CS42L43_ASRC_INT2_EN_SHIFT				1
+#define CS42L43_ASRC_INT1_EN_MASK				0x00000001
+#define CS42L43_ASRC_INT1_EN_SHIFT				0
+
+/* CS42L43_ASRC_DEC_ENABLES */
+#define CS42L43_ASRC_DEC4_EN_MASK				0x00000008
+#define CS42L43_ASRC_DEC4_EN_SHIFT				3
+#define CS42L43_ASRC_DEC3_EN_MASK				0x00000004
+#define CS42L43_ASRC_DEC3_EN_SHIFT				2
+#define CS42L43_ASRC_DEC2_EN_MASK				0x00000002
+#define CS42L43_ASRC_DEC2_EN_SHIFT				1
+#define CS42L43_ASRC_DEC1_EN_MASK				0x00000001
+#define CS42L43_ASRC_DEC1_EN_SHIFT				0
+
+/* CS42L43_PDNCNTL */
+#define CS42L43_RING_SENSE_EN_MASK				0x00000002
+#define CS42L43_RING_SENSE_EN_SHIFT				1
+
+/* CS42L43_RINGSENSE_DEB_CTRL */
+#define CS42L43_RINGSENSE_INV_MASK				0x00000080
+#define CS42L43_RINGSENSE_INV_SHIFT				7
+#define CS42L43_RINGSENSE_PULLUP_PDNB_MASK			0x00000040
+#define CS42L43_RINGSENSE_PULLUP_PDNB_SHIFT			6
+#define CS42L43_RINGSENSE_FALLING_DB_TIME_MASK			0x00000038
+#define CS42L43_RINGSENSE_FALLING_DB_TIME_SHIFT			3
+#define CS42L43_RINGSENSE_RISING_DB_TIME_MASK			0x00000007
+#define CS42L43_RINGSENSE_RISING_DB_TIME_SHIFT			0
+
+/* CS42L43_TIPSENSE_DEB_CTRL */
+#define CS42L43_TIPSENSE_INV_MASK				0x00000080
+#define CS42L43_TIPSENSE_INV_SHIFT				7
+#define CS42L43_TIPSENSE_FALLING_DB_TIME_MASK			0x00000038
+#define CS42L43_TIPSENSE_FALLING_DB_TIME_SHIFT			3
+#define CS42L43_TIPSENSE_RISING_DB_TIME_MASK			0x00000007
+#define CS42L43_TIPSENSE_RISING_DB_TIME_SHIFT			0
+
+/* CS42L43_TIP_RING_SENSE_INTERRUPT_STATUS */
+#define CS42L43_TIPSENSE_UNPLUG_DB_STS_MASK			0x00000008
+#define CS42L43_TIPSENSE_UNPLUG_DB_STS_SHIFT			3
+#define CS42L43_TIPSENSE_PLUG_DB_STS_MASK			0x00000004
+#define CS42L43_TIPSENSE_PLUG_DB_STS_SHIFT			2
+#define CS42L43_RINGSENSE_UNPLUG_DB_STS_MASK			0x00000002
+#define CS42L43_RINGSENSE_UNPLUG_DB_STS_SHIFT			1
+#define CS42L43_RINGSENSE_PLUG_DB_STS_MASK			0x00000001
+#define CS42L43_RINGSENSE_PLUG_DB_STS_SHIFT			0
+
+/* CS42L43_HS2 */
+#define CS42L43_HS_CLAMP_DISABLE_MASK				0x10000000
+#define CS42L43_HS_CLAMP_DISABLE_SHIFT				28
+#define CS42L43_HSBIAS_RAMP_MASK				0x0C000000
+#define CS42L43_HSBIAS_RAMP_SHIFT				26
+#define CS42L43_HSDET_MODE_MASK					0x00018000
+#define CS42L43_HSDET_MODE_SHIFT				15
+#define CS42L43_HSDET_MANUAL_MODE_MASK				0x00006000
+#define CS42L43_HSDET_MANUAL_MODE_SHIFT				13
+#define CS42L43_AUTO_HSDET_TIME_MASK				0x00000700
+#define CS42L43_AUTO_HSDET_TIME_SHIFT				8
+#define CS42L43_AMP3_4_GNDREF_HS3_SEL_MASK			0x00000080
+#define CS42L43_AMP3_4_GNDREF_HS3_SEL_SHIFT			7
+#define CS42L43_AMP3_4_GNDREF_HS4_SEL_MASK			0x00000040
+#define CS42L43_AMP3_4_GNDREF_HS4_SEL_SHIFT			6
+#define CS42L43_HSBIAS_GNDREF_HS3_SEL_MASK			0x00000020
+#define CS42L43_HSBIAS_GNDREF_HS3_SEL_SHIFT			5
+#define CS42L43_HSBIAS_GNDREF_HS4_SEL_MASK			0x00000010
+#define CS42L43_HSBIAS_GNDREF_HS4_SEL_SHIFT			4
+#define CS42L43_HSBIAS_OUT_HS3_SEL_MASK				0x00000008
+#define CS42L43_HSBIAS_OUT_HS3_SEL_SHIFT			3
+#define CS42L43_HSBIAS_OUT_HS4_SEL_MASK				0x00000004
+#define CS42L43_HSBIAS_OUT_HS4_SEL_SHIFT			2
+#define CS42L43_HSGND_HS3_SEL_MASK				0x00000002
+#define CS42L43_HSGND_HS3_SEL_SHIFT				1
+#define CS42L43_HSGND_HS4_SEL_MASK				0x00000001
+#define CS42L43_HSGND_HS4_SEL_SHIFT				0
+
+/* CS42L43_HS_STAT */
+#define CS42L43_HSDET_TYPE_STS_MASK				0x00000007
+#define CS42L43_HSDET_TYPE_STS_SHIFT				0
+
+/* CS42L43_MCU_SW_INTERRUPT */
+#define CS42L43_CONTROL_IND_MASK				0x00000004
+#define CS42L43_CONTROL_IND_SHIFT				2
+#define CS42L43_CONFIGS_IND_MASK				0x00000002
+#define CS42L43_CONFIGS_IND_SHIFT				1
+#define CS42L43_PATCH_IND_MASK					0x00000001
+#define CS42L43_PATCH_IND_SHIFT					0
+
+/* CS42L43_STEREO_MIC_CTRL */
+#define CS42L43_HS2_BIAS_SENSE_EN_MASK				0x00000020
+#define CS42L43_HS2_BIAS_SENSE_EN_SHIFT				5
+#define CS42L43_HS1_BIAS_SENSE_EN_MASK				0x00000010
+#define CS42L43_HS1_BIAS_SENSE_EN_SHIFT				4
+#define CS42L43_HS2_BIAS_EN_MASK				0x00000008
+#define CS42L43_HS2_BIAS_EN_SHIFT				3
+#define CS42L43_HS1_BIAS_EN_MASK				0x00000004
+#define CS42L43_HS1_BIAS_EN_SHIFT				2
+#define CS42L43_JACK_STEREO_CONFIG_MASK				0x00000003
+#define CS42L43_JACK_STEREO_CONFIG_SHIFT			0
+
+/* CS42L43_STEREO_MIC_CLAMP_CTRL */
+#define CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_MASK		0x00000002
+#define CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_VAL_SHIFT		1
+#define CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_MASK			0x00000001
+#define CS42L43_SMIC_HPAMP_CLAMP_DIS_FRC_SHIFT			0
+
+/* CS42L43_BLOCK_EN2 */
+#define CS42L43_SPI_MSTR_EN_MASK				0x00000001
+#define CS42L43_SPI_MSTR_EN_SHIFT				0
+
+/* CS42L43_BLOCK_EN3 */
+#define CS42L43_PDM2_DIN_R_EN_MASK				0x00000020
+#define CS42L43_PDM2_DIN_R_EN_SHIFT				5
+#define CS42L43_PDM2_DIN_L_EN_MASK				0x00000010
+#define CS42L43_PDM2_DIN_L_EN_SHIFT				4
+#define CS42L43_PDM1_DIN_R_EN_MASK				0x00000008
+#define CS42L43_PDM1_DIN_R_EN_SHIFT				3
+#define CS42L43_PDM1_DIN_L_EN_MASK				0x00000004
+#define CS42L43_PDM1_DIN_L_EN_SHIFT				2
+#define CS42L43_ADC2_EN_MASK					0x00000002
+#define CS42L43_ADC2_EN_SHIFT					1
+#define CS42L43_ADC1_EN_MASK					0x00000001
+#define CS42L43_ADC1_EN_SHIFT					0
+
+/* CS42L43_BLOCK_EN4 */
+#define CS42L43_ASRC_DEC_BANK_EN_MASK				0x00000002
+#define CS42L43_ASRC_DEC_BANK_EN_SHIFT				1
+#define CS42L43_ASRC_INT_BANK_EN_MASK				0x00000001
+#define CS42L43_ASRC_INT_BANK_EN_SHIFT				0
+
+/* CS42L43_BLOCK_EN5 */
+#define CS42L43_ISRC2_BANK_EN_MASK				0x00000002
+#define CS42L43_ISRC2_BANK_EN_SHIFT				1
+#define CS42L43_ISRC1_BANK_EN_MASK				0x00000001
+#define CS42L43_ISRC1_BANK_EN_SHIFT				0
+
+/* CS42L43_BLOCK_EN6 */
+#define CS42L43_MIXER_EN_MASK					0x00000001
+#define CS42L43_MIXER_EN_SHIFT					0
+
+/* CS42L43_BLOCK_EN7 */
+#define CS42L43_EQ_EN_MASK					0x00000001
+#define CS42L43_EQ_EN_SHIFT					0
+
+/* CS42L43_BLOCK_EN8 */
+#define CS42L43_HP_EN_MASK					0x00000001
+#define CS42L43_HP_EN_SHIFT					0
+
+/* CS42L43_BLOCK_EN9 */
+#define CS42L43_TONE_EN_MASK					0x00000001
+#define CS42L43_TONE_EN_SHIFT					0
+
+/* CS42L43_BLOCK_EN10 */
+#define CS42L43_AMP2_EN_MASK					0x00000002
+#define CS42L43_AMP2_EN_SHIFT					1
+#define CS42L43_AMP1_EN_MASK					0x00000001
+#define CS42L43_AMP1_EN_SHIFT					0
+
+/* CS42L43_BLOCK_EN11 */
+#define CS42L43_SPDIF_EN_MASK					0x00000001
+#define CS42L43_SPDIF_EN_SHIFT					0
+
+/* CS42L43_TONE_CH1_CTRL..CS42L43_TONE_CH2_CTRL  */
+#define CS42L43_TONE_FREQ_MASK					0x00000070
+#define CS42L43_TONE_FREQ_SHIFT					4
+#define CS42L43_TONE_SEL_MASK					0x0000000F
+#define CS42L43_TONE_SEL_SHIFT					0
+
+/* CS42L43_MIC_DETECT_CONTROL_1 */
+#define CS42L43_BUTTON_DETECT_MODE_MASK				0x00000018
+#define CS42L43_BUTTON_DETECT_MODE_SHIFT			3
+#define CS42L43_HSBIAS_MODE_MASK				0x00000006
+#define CS42L43_HSBIAS_MODE_SHIFT				1
+#define CS42L43_MIC_LVL_DET_DISABLE_MASK			0x00000001
+#define CS42L43_MIC_LVL_DET_DISABLE_SHIFT			0
+
+/* CS42L43_DETECT_STATUS_1 */
+#define CS42L43_HSDET_DC_STS_MASK				0x01FF0000
+#define CS42L43_HSDET_DC_STS_SHIFT				16
+#define CS42L43_JACKDET_STS_MASK				0x00000080
+#define CS42L43_JACKDET_STS_SHIFT				7
+#define CS42L43_HSBIAS_CLAMP_STS_MASK				0x00000040
+#define CS42L43_HSBIAS_CLAMP_STS_SHIFT				6
+
+/* CS42L43_HS_BIAS_SENSE_AND_CLAMP_AUTOCONTROL */
+#define CS42L43_JACKDET_MODE_MASK				0xC0000000
+#define CS42L43_JACKDET_MODE_SHIFT				30
+#define CS42L43_JACKDET_INV_MASK				0x20000000
+#define CS42L43_JACKDET_INV_SHIFT				29
+#define CS42L43_JACKDET_DB_TIME_MASK				0x03000000
+#define CS42L43_JACKDET_DB_TIME_SHIFT				24
+#define CS42L43_S0_AUTO_ADCMUTE_DISABLE_MASK			0x00800000
+#define CS42L43_S0_AUTO_ADCMUTE_DISABLE_SHIFT			23
+#define CS42L43_HSBIAS_SENSE_EN_MASK				0x00000080
+#define CS42L43_HSBIAS_SENSE_EN_SHIFT				7
+#define CS42L43_AUTO_HSBIAS_CLAMP_EN_MASK			0x00000040
+#define CS42L43_AUTO_HSBIAS_CLAMP_EN_SHIFT			6
+#define CS42L43_JACKDET_SENSE_EN_MASK				0x00000020
+#define CS42L43_JACKDET_SENSE_EN_SHIFT				5
+#define CS42L43_HSBIAS_SENSE_TRIP_MASK				0x00000007
+#define CS42L43_HSBIAS_SENSE_TRIP_SHIFT				0
+
+/* CS42L43_MIC_DETECT_CONTROL_ANDROID */
+#define CS42L43_HSDET_LVL_COMBWIDTH_MASK			0xC0000000
+#define CS42L43_HSDET_LVL_COMBWIDTH_SHIFT			30
+#define CS42L43_HSDET_LVL2_THRESH_MASK				0x01FF0000
+#define CS42L43_HSDET_LVL2_THRESH_SHIFT				16
+#define CS42L43_HSDET_LVL1_THRESH_MASK				0x000001FF
+#define CS42L43_HSDET_LVL1_THRESH_SHIFT				0
+
+/* CS42L43_ISRC1_CTRL..CS42L43_ISRC2_CTRL */
+#define CS42L43_ISRC_INT2_EN_MASK				0x00000200
+#define CS42L43_ISRC_INT2_EN_SHIFT				9
+#define CS42L43_ISRC_INT1_EN_MASK				0x00000100
+#define CS42L43_ISRC_INT1_EN_SHIFT				8
+#define CS42L43_ISRC_DEC2_EN_MASK				0x00000002
+#define CS42L43_ISRC_DEC2_EN_SHIFT				1
+#define CS42L43_ISRC_DEC1_EN_MASK				0x00000001
+#define CS42L43_ISRC_DEC1_EN_SHIFT				0
+
+/* CS42L43_CTRL_REG */
+#define CS42L43_PLL_MODE_BYPASS_500_MASK			0x00000004
+#define CS42L43_PLL_MODE_BYPASS_500_SHIFT			2
+#define CS42L43_PLL_MODE_BYPASS_1029_MASK			0x00000002
+#define CS42L43_PLL_MODE_BYPASS_1029_SHIFT			1
+#define CS42L43_PLL_EN_MASK					0x00000001
+#define CS42L43_PLL_EN_SHIFT					0
+
+/* CS42L43_FDIV_FRAC */
+#define CS42L43_PLL_DIV_INT_MASK				0xFF000000
+#define CS42L43_PLL_DIV_INT_SHIFT				24
+#define CS42L43_PLL_DIV_FRAC_BYTE2_MASK				0x00FF0000
+#define CS42L43_PLL_DIV_FRAC_BYTE2_SHIFT			16
+#define CS42L43_PLL_DIV_FRAC_BYTE1_MASK				0x0000FF00
+#define CS42L43_PLL_DIV_FRAC_BYTE1_SHIFT			8
+#define CS42L43_PLL_DIV_FRAC_BYTE0_MASK				0x000000FF
+#define CS42L43_PLL_DIV_FRAC_BYTE0_SHIFT			0
+
+/* CS42L43_CAL_RATIO */
+#define CS42L43_PLL_CAL_RATIO_MASK				0x000000FF
+#define CS42L43_PLL_CAL_RATIO_SHIFT				0
+
+/* CS42L43_SPI_CLK_CONFIG1 */
+#define CS42L43_SCLK_DIV_MASK					0x0000000F
+#define CS42L43_SCLK_DIV_SHIFT					0
+
+/* CS42L43_SPI_CONFIG1 */
+#define CS42L43_SPI_SS_IDLE_DUR_MASK				0x0F000000
+#define CS42L43_SPI_SS_IDLE_DUR_SHIFT				24
+#define CS42L43_SPI_SS_DELAY_DUR_MASK				0x000F0000
+#define CS42L43_SPI_SS_DELAY_DUR_SHIFT				16
+#define CS42L43_SPI_THREE_WIRE_MASK				0x00000100
+#define CS42L43_SPI_THREE_WIRE_SHIFT				8
+#define CS42L43_SPI_DPHA_MASK					0x00000040
+#define CS42L43_SPI_DPHA_SHIFT					6
+#define CS42L43_SPI_CPHA_MASK					0x00000020
+#define CS42L43_SPI_CPHA_SHIFT					5
+#define CS42L43_SPI_CPOL_MASK					0x00000010
+#define CS42L43_SPI_CPOL_SHIFT					4
+#define CS42L43_SPI_SS_SEL_MASK					0x00000007
+#define CS42L43_SPI_SS_SEL_SHIFT				0
+
+/* CS42L43_SPI_CONFIG2 */
+#define CS42L43_SPI_SS_FRC_MASK					0x00000001
+#define CS42L43_SPI_SS_FRC_SHIFT				0
+
+/* CS42L43_SPI_CONFIG3 */
+#define CS42L43_SPI_WDT_ENA_MASK				0x00000001
+#define CS42L43_SPI_WDT_ENA_SHIFT				0
+
+/* CS42L43_SPI_CONFIG4 */
+#define CS42L43_SPI_STALL_ENA_MASK				0x00010000
+#define CS42L43_SPI_STALL_ENA_SHIFT				16
+
+/* CS42L43_SPI_STATUS1 */
+#define CS42L43_SPI_ABORT_STS_MASK				0x00000002
+#define CS42L43_SPI_ABORT_STS_SHIFT				1
+#define CS42L43_SPI_DONE_STS_MASK				0x00000001
+#define CS42L43_SPI_DONE_STS_SHIFT				0
+
+/* CS42L43_SPI_STATUS2 */
+#define CS42L43_SPI_RX_DONE_STS_MASK				0x00000010
+#define CS42L43_SPI_RX_DONE_STS_SHIFT				4
+#define CS42L43_SPI_TX_DONE_STS_MASK				0x00000001
+#define CS42L43_SPI_TX_DONE_STS_SHIFT				0
+
+/* CS42L43_TRAN_CONFIG1 */
+#define CS42L43_SPI_START_MASK					0x00000001
+#define CS42L43_SPI_START_SHIFT					0
+
+/* CS42L43_TRAN_CONFIG2 */
+#define CS42L43_SPI_ABORT_MASK					0x00000001
+#define CS42L43_SPI_ABORT_SHIFT					0
+
+/* CS42L43_TRAN_CONFIG3 */
+#define CS42L43_SPI_WORD_SIZE_MASK				0x00070000
+#define CS42L43_SPI_WORD_SIZE_SHIFT				16
+#define CS42L43_SPI_CMD_MASK					0x00000003
+#define CS42L43_SPI_CMD_SHIFT					0
+
+/* CS42L43_TRAN_CONFIG4 */
+#define CS42L43_SPI_TX_LENGTH_MASK				0x0000FFFF
+#define CS42L43_SPI_TX_LENGTH_SHIFT				0
+
+/* CS42L43_TRAN_CONFIG5 */
+#define CS42L43_SPI_RX_LENGTH_MASK				0x0000FFFF
+#define CS42L43_SPI_RX_LENGTH_SHIFT				0
+
+/* CS42L43_TRAN_CONFIG6 */
+#define CS42L43_SPI_TX_BLOCK_LENGTH_MASK			0x0000000F
+#define CS42L43_SPI_TX_BLOCK_LENGTH_SHIFT			0
+
+/* CS42L43_TRAN_CONFIG7 */
+#define CS42L43_SPI_RX_BLOCK_LENGTH_MASK			0x0000000F
+#define CS42L43_SPI_RX_BLOCK_LENGTH_SHIFT			0
+
+/* CS42L43_TRAN_CONFIG8 */
+#define CS42L43_SPI_RX_DONE_MASK				0x00000010
+#define CS42L43_SPI_RX_DONE_SHIFT				4
+#define CS42L43_SPI_TX_DONE_MASK				0x00000001
+#define CS42L43_SPI_TX_DONE_SHIFT				0
+
+/* CS42L43_TRAN_STATUS1 */
+#define CS42L43_SPI_BUSY_STS_MASK				0x00000100
+#define CS42L43_SPI_BUSY_STS_SHIFT				8
+#define CS42L43_SPI_RX_REQUEST_MASK				0x00000010
+#define CS42L43_SPI_RX_REQUEST_SHIFT				4
+#define CS42L43_SPI_TX_REQUEST_MASK				0x00000001
+#define CS42L43_SPI_TX_REQUEST_SHIFT				0
+
+/* CS42L43_TRAN_STATUS2 */
+#define CS42L43_SPI_TX_BYTE_COUNT_MASK				0x0000FFFF
+#define CS42L43_SPI_TX_BYTE_COUNT_SHIFT				0
+
+/* CS42L43_TRAN_STATUS3 */
+#define CS42L43_SPI_RX_BYTE_COUNT_MASK				0x0000FFFF
+#define CS42L43_SPI_RX_BYTE_COUNT_SHIFT				0
+
+/* CS42L43_TX_DATA */
+#define CS42L43_SPI_TX_DATA_MASK				0xFFFFFFFF
+#define CS42L43_SPI_TX_DATA_SHIFT				0
+
+/* CS42L43_RX_DATA */
+#define CS42L43_SPI_RX_DATA_MASK				0xFFFFFFFF
+#define CS42L43_SPI_RX_DATA_SHIFT				0
+
+/* CS42L43_DACCNFG1 */
+#define CS42L43_HP_MSTR_VOL_CTRL_EN_MASK			0x00000008
+#define CS42L43_HP_MSTR_VOL_CTRL_EN_SHIFT			3
+#define CS42L43_AMP4_INV_MASK					0x00000002
+#define CS42L43_AMP4_INV_SHIFT					1
+#define CS42L43_AMP3_INV_MASK					0x00000001
+#define CS42L43_AMP3_INV_SHIFT					0
+
+/* CS42L43_DACCNFG2 */
+#define CS42L43_HP_AUTO_CLAMP_DISABLE_MASK			0x00000002
+#define CS42L43_HP_AUTO_CLAMP_DISABLE_SHIFT			1
+#define CS42L43_HP_HPF_EN_MASK					0x00000001
+#define CS42L43_HP_HPF_EN_SHIFT					0
+
+/* CS42L43_HPPATHVOL */
+#define CS42L43_AMP4_PATH_VOL_MASK				0x01FF0000
+#define CS42L43_AMP4_PATH_VOL_SHIFT				16
+#define CS42L43_AMP3_PATH_VOL_MASK				0x000001FF
+#define CS42L43_AMP3_PATH_VOL_SHIFT				0
+
+/* CS42L43_PGAVOL */
+#define CS42L43_HP_PATH_VOL_RAMP_MASK				0x0003C000
+#define CS42L43_HP_PATH_VOL_RAMP_SHIFT				14
+#define CS42L43_HP_PATH_VOL_ZC_MASK				0x00002000
+#define CS42L43_HP_PATH_VOL_ZC_SHIFT				13
+#define CS42L43_HP_PATH_VOL_SFT_MASK				0x00001000
+#define CS42L43_HP_PATH_VOL_SFT_SHIFT				12
+#define CS42L43_HP_DIG_VOL_RAMP_MASK				0x00000F00
+#define CS42L43_HP_DIG_VOL_RAMP_SHIFT				8
+#define CS42L43_HP_ANA_VOL_RAMP_MASK				0x0000000F
+#define CS42L43_HP_ANA_VOL_RAMP_SHIFT				0
+
+/* CS42L43_LOADDETRESULTS */
+#define CS42L43_AMP3_RES_DET_MASK				0x00000003
+#define CS42L43_AMP3_RES_DET_SHIFT				0
+
+/* CS42L43_LOADDETENA */
+#define CS42L43_HPLOAD_DET_EN_MASK				0x00000001
+#define CS42L43_HPLOAD_DET_EN_SHIFT				0
+
+/* CS42L43_CTRL */
+#define CS42L43_ADPTPWR_MODE_MASK				0x00000007
+#define CS42L43_ADPTPWR_MODE_SHIFT				0
+
+/* CS42L43_COEFF_RD_WR0 */
+#define CS42L43_WRITE_MODE_MASK					0x00000002
+#define CS42L43_WRITE_MODE_SHIFT				1
+
+/* CS42L43_INIT_DONE0 */
+#define CS42L43_INITIALIZE_DONE_MASK				0x00000001
+#define CS42L43_INITIALIZE_DONE_SHIFT				0
+
+/* CS42L43_START_EQZ0 */
+#define CS42L43_START_FILTER_MASK				0x00000001
+#define CS42L43_START_FILTER_SHIFT				0
+
+/* CS42L43_MUTE_EQ_IN0 */
+#define CS42L43_MUTE_EQ_CH2_MASK				0x00000002
+#define CS42L43_MUTE_EQ_CH2_SHIFT				1
+#define CS42L43_MUTE_EQ_CH1_MASK				0x00000001
+#define CS42L43_MUTE_EQ_CH1_SHIFT				0
+
+/* CS42L43_PLL_INT */
+#define CS42L43_PLL_LOST_LOCK_INT_MASK				0x00000002
+#define CS42L43_PLL_LOST_LOCK_INT_SHIFT				1
+#define CS42L43_PLL_READY_INT_MASK				0x00000001
+#define CS42L43_PLL_READY_INT_SHIFT				0
+
+/* CS42L43_SOFT_INT */
+#define CS42L43_CONTROL_APPLIED_INT_MASK			0x00000010
+#define CS42L43_CONTROL_APPLIED_INT_SHIFT			4
+#define CS42L43_CONTROL_WARN_INT_MASK				0x00000008
+#define CS42L43_CONTROL_WARN_INT_SHIFT				3
+#define CS42L43_PATCH_WARN_INT_MASK				0x00000002
+#define CS42L43_PATCH_WARN_INT_SHIFT				1
+#define CS42L43_PATCH_APPLIED_INT_MASK				0x00000001
+#define CS42L43_PATCH_APPLIED_INT_SHIFT				0
+
+/* CS42L43_MSM_INT */
+#define CS42L43_HP_STARTUP_DONE_INT_MASK			0x00000800
+#define CS42L43_HP_STARTUP_DONE_INT_SHIFT			11
+#define CS42L43_HP_SHUTDOWN_DONE_INT_MASK			0x00000400
+#define CS42L43_HP_SHUTDOWN_DONE_INT_SHIFT			10
+#define CS42L43_HSDET_DONE_INT_MASK				0x00000200
+#define CS42L43_HSDET_DONE_INT_SHIFT				9
+#define CS42L43_TIPSENSE_UNPLUG_DB_INT_MASK			0x00000080
+#define CS42L43_TIPSENSE_UNPLUG_DB_INT_SHIFT			7
+#define CS42L43_TIPSENSE_PLUG_DB_INT_MASK			0x00000040
+#define CS42L43_TIPSENSE_PLUG_DB_INT_SHIFT			6
+#define CS42L43_RINGSENSE_UNPLUG_DB_INT_MASK			0x00000020
+#define CS42L43_RINGSENSE_UNPLUG_DB_INT_SHIFT			5
+#define CS42L43_RINGSENSE_PLUG_DB_INT_MASK			0x00000010
+#define CS42L43_RINGSENSE_PLUG_DB_INT_SHIFT			4
+#define CS42L43_TIPSENSE_UNPLUG_PDET_INT_MASK			0x00000008
+#define CS42L43_TIPSENSE_UNPLUG_PDET_INT_SHIFT			3
+#define CS42L43_TIPSENSE_PLUG_PDET_INT_MASK			0x00000004
+#define CS42L43_TIPSENSE_PLUG_PDET_INT_SHIFT			2
+#define CS42L43_RINGSENSE_UNPLUG_PDET_INT_MASK			0x00000002
+#define CS42L43_RINGSENSE_UNPLUG_PDET_INT_SHIFT			1
+#define CS42L43_RINGSENSE_PLUG_PDET_INT_MASK			0x00000001
+#define CS42L43_RINGSENSE_PLUG_PDET_INT_SHIFT			0
+
+/* CS42L43_ACC_DET_INT */
+#define CS42L43_HS2_BIAS_SENSE_INT_MASK				0x00000800
+#define CS42L43_HS2_BIAS_SENSE_INT_SHIFT			11
+#define CS42L43_HS1_BIAS_SENSE_INT_MASK				0x00000400
+#define CS42L43_HS1_BIAS_SENSE_INT_SHIFT			10
+#define CS42L43_DC_DETECT1_FALSE_INT_MASK			0x00000080
+#define CS42L43_DC_DETECT1_FALSE_INT_SHIFT			7
+#define CS42L43_DC_DETECT1_TRUE_INT_MASK			0x00000040
+#define CS42L43_DC_DETECT1_TRUE_INT_SHIFT			6
+#define CS42L43_HSBIAS_CLAMPED_INT_MASK				0x00000008
+#define CS42L43_HSBIAS_CLAMPED_INT_SHIFT			3
+#define CS42L43_HS3_4_BIAS_SENSE_INT_MASK			0x00000001
+#define CS42L43_HS3_4_BIAS_SENSE_INT_SHIFT			0
+
+/* CS42L43_SPI_MSTR_INT */
+#define CS42L43_IRQ_SPI_STALLING_INT_MASK			0x00000004
+#define CS42L43_IRQ_SPI_STALLING_INT_SHIFT			2
+#define CS42L43_IRQ_SPI_STS_INT_MASK				0x00000002
+#define CS42L43_IRQ_SPI_STS_INT_SHIFT				1
+#define CS42L43_IRQ_SPI_BLOCK_INT_MASK				0x00000001
+#define CS42L43_IRQ_SPI_BLOCK_INT_SHIFT				0
+
+/* CS42L43_SW_TO_SPI_BRIDGE_INT */
+#define CS42L43_SW2SPI_BUF_OVF_UDF_INT_MASK			0x00000001
+#define CS42L43_SW2SPI_BUF_OVF_UDF_INT_SHIFT			0
+
+/* CS42L43_CLASS_D_AMP_INT */
+#define CS42L43_AMP2_CLK_STOP_FAULT_INT_MASK			0x00002000
+#define CS42L43_AMP2_CLK_STOP_FAULT_INT_SHIFT			13
+#define CS42L43_AMP1_CLK_STOP_FAULT_INT_MASK			0x00001000
+#define CS42L43_AMP1_CLK_STOP_FAULT_INT_SHIFT			12
+#define CS42L43_AMP2_VDDSPK_FAULT_INT_MASK			0x00000800
+#define CS42L43_AMP2_VDDSPK_FAULT_INT_SHIFT			11
+#define CS42L43_AMP1_VDDSPK_FAULT_INT_MASK			0x00000400
+#define CS42L43_AMP1_VDDSPK_FAULT_INT_SHIFT			10
+#define CS42L43_AMP2_SHUTDOWN_DONE_INT_MASK			0x00000200
+#define CS42L43_AMP2_SHUTDOWN_DONE_INT_SHIFT			9
+#define CS42L43_AMP1_SHUTDOWN_DONE_INT_MASK			0x00000100
+#define CS42L43_AMP1_SHUTDOWN_DONE_INT_SHIFT			8
+#define CS42L43_AMP2_STARTUP_DONE_INT_MASK			0x00000080
+#define CS42L43_AMP2_STARTUP_DONE_INT_SHIFT			7
+#define CS42L43_AMP1_STARTUP_DONE_INT_MASK			0x00000040
+#define CS42L43_AMP1_STARTUP_DONE_INT_SHIFT			6
+#define CS42L43_AMP2_THERM_SHDN_INT_MASK			0x00000020
+#define CS42L43_AMP2_THERM_SHDN_INT_SHIFT			5
+#define CS42L43_AMP1_THERM_SHDN_INT_MASK			0x00000010
+#define CS42L43_AMP1_THERM_SHDN_INT_SHIFT			4
+#define CS42L43_AMP2_THERM_WARN_INT_MASK			0x00000008
+#define CS42L43_AMP2_THERM_WARN_INT_SHIFT			3
+#define CS42L43_AMP1_THERM_WARN_INT_MASK			0x00000004
+#define CS42L43_AMP1_THERM_WARN_INT_SHIFT			2
+#define CS42L43_AMP2_SCDET_INT_MASK				0x00000002
+#define CS42L43_AMP2_SCDET_INT_SHIFT				1
+#define CS42L43_AMP1_SCDET_INT_MASK				0x00000001
+#define CS42L43_AMP1_SCDET_INT_SHIFT				0
+
+/* CS42L43_GPIO_INT */
+#define CS42L43_GPIO3_FALL_INT_MASK				0x00000020
+#define CS42L43_GPIO3_FALL_INT_SHIFT				5
+#define CS42L43_GPIO3_RISE_INT_MASK				0x00000010
+#define CS42L43_GPIO3_RISE_INT_SHIFT				4
+#define CS42L43_GPIO2_FALL_INT_MASK				0x00000008
+#define CS42L43_GPIO2_FALL_INT_SHIFT				3
+#define CS42L43_GPIO2_RISE_INT_MASK				0x00000004
+#define CS42L43_GPIO2_RISE_INT_SHIFT				2
+#define CS42L43_GPIO1_FALL_INT_MASK				0x00000002
+#define CS42L43_GPIO1_FALL_INT_SHIFT				1
+#define CS42L43_GPIO1_RISE_INT_MASK				0x00000001
+#define CS42L43_GPIO1_RISE_INT_SHIFT				0
+
+/* CS42L43_HPOUT_INT */
+#define CS42L43_HP_ILIMIT_INT_MASK				0x00000002
+#define CS42L43_HP_ILIMIT_INT_SHIFT				1
+#define CS42L43_HP_LOADDET_DONE_INT_MASK			0x00000001
+#define CS42L43_HP_LOADDET_DONE_INT_SHIFT			0
+
+/* CS42L43_BOOT_CONTROL */
+#define CS42L43_LOCK_HW_STS_MASK				0x00000002
+#define CS42L43_LOCK_HW_STS_SHIFT				1
+
+/* CS42L43_BLOCK_EN */
+#define CS42L43_MCU_EN_MASK					0x00000001
+#define CS42L43_MCU_EN_SHIFT					0
+
+/* CS42L43_SHUTTER_CONTROL */
+#define CS42L43_STATUS_SPK_SHUTTER_MUTE_MASK			0x00008000
+#define CS42L43_STATUS_SPK_SHUTTER_MUTE_SHIFT			15
+#define CS42L43_SPK_SHUTTER_CFG_MASK				0x00000F00
+#define CS42L43_SPK_SHUTTER_CFG_SHIFT				8
+#define CS42L43_STATUS_MIC_SHUTTER_MUTE_MASK			0x00000080
+#define CS42L43_STATUS_MIC_SHUTTER_MUTE_SHIFT			7
+#define CS42L43_MIC_SHUTTER_CFG_MASK				0x0000000F
+#define CS42L43_MIC_SHUTTER_CFG_SHIFT				0
+
+/* CS42L43_MCU_SW_REV */
+#define CS42L43_BIOS_SUBMINOR_REV_MASK				0xFF000000
+#define CS42L43_BIOS_SUBMINOR_REV_SHIFT				24
+#define CS42L43_BIOS_MINOR_REV_MASK				0x00F00000
+#define CS42L43_BIOS_MINOR_REV_SHIFT				20
+#define CS42L43_BIOS_MAJOR_REV_MASK				0x000F0000
+#define CS42L43_BIOS_MAJOR_REV_SHIFT				16
+#define CS42L43_FW_SUBMINOR_REV_MASK				0x0000FF00
+#define CS42L43_FW_SUBMINOR_REV_SHIFT				8
+#define CS42L43_FW_MINOR_REV_MASK				0x000000F0
+#define CS42L43_FW_MINOR_REV_SHIFT				4
+#define CS42L43_FW_MAJOR_REV_MASK				0x0000000F
+#define CS42L43_FW_MAJOR_REV_SHIFT				0
+
+/* CS42L43_NEED_CONFIGS */
+#define CS42L43_FW_PATCH_NEED_CFG_MASK				0x80000000
+#define CS42L43_FW_PATCH_NEED_CFG_SHIFT				31
+
+/* CS42L43_FW_MISSION_CTRL_MM_CTRL_SELECTION */
+#define CS42L43_FW_MM_CTRL_MCU_SEL_MASK				0x00000001
+#define CS42L43_FW_MM_CTRL_MCU_SEL_SHIFT			0
+
+/* CS42L43_FW_MISSION_CTRL_MM_MCU_CFG_REG */
+#define CS42L43_FW_MISSION_CTRL_MM_MCU_CFG_DISABLE_VAL		0xF05AA50F
+
+#endif /* CS42L43_CORE_REGS_H */
diff --git a/include/linux/mfd/cs42l43.h b/include/linux/mfd/cs42l43.h
new file mode 100644
index 000000000000..2239d8585e78
--- /dev/null
+++ b/include/linux/mfd/cs42l43.h
@@ -0,0 +1,103 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * CS42L43 core driver external data
+ *
+ * Copyright (C) 2022-2023 Cirrus Logic, Inc. and
+ *                         Cirrus Logic International Semiconductor Ltd.
+ */
+
+#ifndef CS42L43_CORE_EXT_H
+#define CS42L43_CORE_EXT_H
+
+#include <linux/completion.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+#include <linux/regulator/consumer.h>
+#include <linux/workqueue.h>
+
+#define CS42L43_N_SUPPLIES		3
+
+struct device;
+struct gpio_desc;
+struct sdw_slave;
+
+enum cs42l43_irq_numbers {
+	CS42L43_PLL_LOST_LOCK,
+	CS42L43_PLL_READY,
+
+	CS42L43_HP_STARTUP_DONE,
+	CS42L43_HP_SHUTDOWN_DONE,
+	CS42L43_HSDET_DONE,
+	CS42L43_TIPSENSE_UNPLUG_DB,
+	CS42L43_TIPSENSE_PLUG_DB,
+	CS42L43_RINGSENSE_UNPLUG_DB,
+	CS42L43_RINGSENSE_PLUG_DB,
+	CS42L43_TIPSENSE_UNPLUG_PDET,
+	CS42L43_TIPSENSE_PLUG_PDET,
+	CS42L43_RINGSENSE_UNPLUG_PDET,
+	CS42L43_RINGSENSE_PLUG_PDET,
+
+	CS42L43_HS2_BIAS_SENSE,
+	CS42L43_HS1_BIAS_SENSE,
+	CS42L43_DC_DETECT1_FALSE,
+	CS42L43_DC_DETECT1_TRUE,
+	CS42L43_HSBIAS_CLAMPED,
+	CS42L43_HS3_4_BIAS_SENSE,
+
+	CS42L43_AMP2_CLK_STOP_FAULT,
+	CS42L43_AMP1_CLK_STOP_FAULT,
+	CS42L43_AMP2_VDDSPK_FAULT,
+	CS42L43_AMP1_VDDSPK_FAULT,
+	CS42L43_AMP2_SHUTDOWN_DONE,
+	CS42L43_AMP1_SHUTDOWN_DONE,
+	CS42L43_AMP2_STARTUP_DONE,
+	CS42L43_AMP1_STARTUP_DONE,
+	CS42L43_AMP2_THERM_SHDN,
+	CS42L43_AMP1_THERM_SHDN,
+	CS42L43_AMP2_THERM_WARN,
+	CS42L43_AMP1_THERM_WARN,
+	CS42L43_AMP2_SCDET,
+	CS42L43_AMP1_SCDET,
+
+	CS42L43_GPIO3_FALL,
+	CS42L43_GPIO3_RISE,
+	CS42L43_GPIO2_FALL,
+	CS42L43_GPIO2_RISE,
+	CS42L43_GPIO1_FALL,
+	CS42L43_GPIO1_RISE,
+
+	CS42L43_HP_ILIMIT,
+	CS42L43_HP_LOADDET_DONE,
+};
+
+struct cs42l43 {
+	struct device *dev;
+	struct regmap *regmap;
+	struct sdw_slave *sdw;
+
+	struct regulator *vdd_p;
+	struct regulator *vdd_d;
+	struct regulator_bulk_data core_supplies[CS42L43_N_SUPPLIES];
+
+	struct gpio_desc *reset;
+
+	int irq;
+	struct regmap_irq_chip irq_chip;
+	struct regmap_irq_chip_data *irq_data;
+
+	struct work_struct boot_work;
+	struct completion device_attach;
+	struct completion device_detach;
+	struct completion firmware_download;
+	int firmware_error;
+
+	unsigned int sdw_freq;
+	/* Lock to gate control of the PLL and its sources. */
+	struct mutex pll_lock;
+
+	bool sdw_pll_active;
+	bool attached;
+	bool hw_lock;
+};
+
+#endif /* CS42L43_CORE_EXT_H */
diff --git a/include/linux/mfd/da9052/da9052.h b/include/linux/mfd/da9052/da9052.h
index 76feb3a7066d..9cb2fc2938ce 100644
--- a/include/linux/mfd/da9052/da9052.h
+++ b/include/linux/mfd/da9052/da9052.h
@@ -93,6 +93,8 @@ struct da9052 {
 
 	int chip_irq;
 
+	int fault_log;
+
 	/* SOC I/O transfer related fixes for DA9052/53 */
 	int (*fix_io) (struct da9052 *da9052, unsigned char reg);
 };
diff --git a/include/linux/mfd/da9055/pdata.h b/include/linux/mfd/da9055/pdata.h
index d3f126990ad0..137a2b067512 100644
--- a/include/linux/mfd/da9055/pdata.h
+++ b/include/linux/mfd/da9055/pdata.h
@@ -7,7 +7,6 @@
 #define DA9055_MAX_REGULATORS	8
 
 struct da9055;
-struct gpio_desc;
 
 enum gpio_select {
 	NO_GPIO = 0,
@@ -24,16 +23,6 @@ struct da9055_pdata {
 	/* Enable RTC in RESET Mode */
 	bool reset_enable;
 	/*
-	 * GPI muxed pin to control
-	 * regulator state A/B, 0 if not available.
-	 */
-	int *gpio_ren;
-	/*
-	 * GPI muxed pin to control
-	 * regulator set, 0 if not available.
-	 */
-	int *gpio_rsel;
-	/*
 	 * Regulator mode control bits value (GPI offset) that
 	 * controls the regulator state, 0 if not available.
 	 */
@@ -43,7 +32,5 @@ struct da9055_pdata {
 	 * controls the regulator set A/B, 0 if  not available.
 	 */
 	enum gpio_select *reg_rsel;
-	/* GPIO descriptors to enable regulator, NULL if not available */
-	struct gpio_desc **ena_gpiods;
 };
 #endif /* __DA9055_PDATA_H */
diff --git a/include/linux/mfd/da9063/core.h b/include/linux/mfd/da9063/core.h
index 8db52324f416..eae82f421414 100644
--- a/include/linux/mfd/da9063/core.h
+++ b/include/linux/mfd/da9063/core.h
@@ -78,6 +78,7 @@ struct da9063 {
 	enum da9063_type type;
 	unsigned char	variant_code;
 	unsigned int	flags;
+	bool use_sw_pm;
 
 	/* Control interface */
 	struct regmap	*regmap;
diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h
index 556375b91316..9acd703dd5ca 100644
--- a/include/linux/mfd/davinci_voicecodec.h
+++ b/include/linux/mfd/davinci_voicecodec.h
@@ -10,11 +10,13 @@
 #ifndef __LINUX_MFD_DAVINCI_VOICECODEC_H_
 #define __LINUX_MFD_DAVINCI_VOICECODEC_H_
 
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
+#include <linux/bits.h>
 #include <linux/mfd/core.h>
-#include <linux/platform_data/edma.h>
+#include <linux/types.h>
 
+struct clk;
+struct device;
+struct platform_device;
 struct regmap;
 
 /*
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index e7a7e70fdb38..828362b7860c 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -213,9 +213,9 @@ struct prcmu_fw_version {
 
 #if defined(CONFIG_UX500_SOC_DB8500)
 
-static inline void prcmu_early_init(void)
+static inline void __init prcmu_early_init(void)
 {
-	return db8500_prcmu_early_init();
+	db8500_prcmu_early_init();
 }
 
 static inline int prcmu_set_power_state(u8 state, bool keep_ulp_clk,
@@ -302,7 +302,7 @@ static inline int prcmu_request_ape_opp_100_voltage(bool enable)
 
 static inline void prcmu_system_reset(u16 reset_code)
 {
-	return db8500_prcmu_system_reset(reset_code);
+	db8500_prcmu_system_reset(reset_code);
 }
 
 static inline u16 prcmu_get_reset_code(void)
@@ -314,7 +314,7 @@ int prcmu_ac_wake_req(void);
 void prcmu_ac_sleep_req(void);
 static inline void prcmu_modem_reset(void)
 {
-	return db8500_prcmu_modem_reset();
+	db8500_prcmu_modem_reset();
 }
 
 static inline bool prcmu_is_ac_wake_requested(void)
@@ -556,16 +556,6 @@ static inline void prcmu_clear(unsigned int reg, u32 bits)
 #define PRCMU_QOS_ARM_OPP 3
 #define PRCMU_QOS_DEFAULT_VALUE -1
 
-static inline unsigned long prcmu_qos_get_cpufreq_opp_delay(void)
-{
-	return 0;
-}
-
-static inline int prcmu_qos_requirement(int prcmu_qos_class)
-{
-	return 0;
-}
-
 static inline int prcmu_qos_add_requirement(int prcmu_qos_class,
 					    char *name, s32 value)
 {
@@ -582,15 +572,4 @@ static inline void prcmu_qos_remove_requirement(int prcmu_qos_class, char *name)
 {
 }
 
-static inline int prcmu_qos_add_notifier(int prcmu_qos_class,
-					 struct notifier_block *notifier)
-{
-	return 0;
-}
-static inline int prcmu_qos_remove_notifier(int prcmu_qos_class,
-					    struct notifier_block *notifier)
-{
-	return 0;
-}
-
 #endif /* __MACH_PRCMU_H */
diff --git a/include/linux/mfd/ds1wm.h b/include/linux/mfd/ds1wm.h
deleted file mode 100644
index 43dfca1c9702..000000000000
--- a/include/linux/mfd/ds1wm.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* MFD cell driver data for the DS1WM driver
- *
- * to be defined in the MFD device that is
- * using this driver for one of his sub devices
- */
-
-struct ds1wm_driver_data {
-	int active_high;
-	int clock_rate;
-	/* in milliseconds, the amount of time to
-	 * sleep following a reset pulse. Zero
-	 * should work if your bus devices recover
-	 * time respects the 1-wire spec since the
-	 * ds1wm implements the precise timings of
-	 * a reset pulse/presence detect sequence.
-	 */
-	unsigned int reset_recover_delay;
-
-	/* Say 1 here for big endian Hardware
-	 * (only relevant with bus-shift > 0
-	 */
-	bool is_hw_big_endian;
-
-	/* left shift of register number to get register address offsett.
-	 * Only 0,1,2 allowed for 8,16 or 32 bit bus width respectively
-	 */
-	unsigned int bus_shift;
-};
diff --git a/include/linux/mfd/ezx-pcap.h b/include/linux/mfd/ezx-pcap.h
index ffde195e12b7..ea51b1cdca5a 100644
--- a/include/linux/mfd/ezx-pcap.h
+++ b/include/linux/mfd/ezx-pcap.h
@@ -31,7 +31,6 @@ int ezx_pcap_set_bits(struct pcap_chip *, u8, u32, u32);
 int pcap_to_irq(struct pcap_chip *, int);
 int irq_to_pcap(struct pcap_chip *, int);
 int pcap_adc_async(struct pcap_chip *, u8, u32, u8[], void *, void *);
-int pcap_adc_sync(struct pcap_chip *, u8, u32, u8[], u16[]);
 void pcap_set_ts_bits(struct pcap_chip *, u32);
 
 #define PCAP_SECOND_PORT	1
diff --git a/include/linux/mfd/hi655x-pmic.h b/include/linux/mfd/hi655x-pmic.h
index 6a012784dd1b..194556851ccf 100644
--- a/include/linux/mfd/hi655x-pmic.h
+++ b/include/linux/mfd/hi655x-pmic.h
@@ -52,7 +52,6 @@
 #define OTMP_D1R_INT_MASK               BIT(OTMP_D1R_INT)
 
 struct hi655x_pmic {
-	struct resource *res;
 	struct device *dev;
 	struct regmap *regmap;
 	struct gpio_desc *gpio;
diff --git a/include/linux/mfd/idt8a340_reg.h b/include/linux/mfd/idt8a340_reg.h
index 0c706085c205..53a222605526 100644
--- a/include/linux/mfd/idt8a340_reg.h
+++ b/include/linux/mfd/idt8a340_reg.h
@@ -61,7 +61,7 @@
 #define HW_Q8_CTRL_SPARE  (0xa7d4)
 #define HW_Q11_CTRL_SPARE (0xa7ec)
 
-/**
+/*
  * Select FOD5 as sync_trigger for Q8 divider.
  * Transition from logic zero to one
  * sets trigger to sync Q8 divider.
@@ -70,7 +70,7 @@
  */
 #define Q9_TO_Q8_SYNC_TRIG  BIT(1)
 
-/**
+/*
  * Enable FOD5 as driver for clock and sync for Q8 divider.
  * Enable fanout buffer for FOD5.
  *
@@ -78,7 +78,7 @@
  */
 #define Q9_TO_Q8_FANOUT_AND_CLOCK_SYNC_ENABLE_MASK  (BIT(0) | BIT(2))
 
-/**
+/*
  * Select FOD6 as sync_trigger for Q11 divider.
  * Transition from logic zero to one
  * sets trigger to sync Q11 divider.
@@ -87,7 +87,7 @@
  */
 #define Q10_TO_Q11_SYNC_TRIG  BIT(1)
 
-/**
+/*
  * Enable FOD6 as driver for clock and sync for Q11 divider.
  * Enable fanout buffer for FOD6.
  *
diff --git a/include/linux/mfd/idtRC38xxx_reg.h b/include/linux/mfd/idtRC38xxx_reg.h
new file mode 100644
index 000000000000..ec11872f51ad
--- /dev/null
+++ b/include/linux/mfd/idtRC38xxx_reg.h
@@ -0,0 +1,273 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Register Map - Based on PolarBear_CSRs.RevA.xlsx (2023-04-21)
+ *
+ * Copyright (C) 2023 Integrated Device Technology, Inc., a Renesas Company.
+ */
+#ifndef MFD_IDTRC38XXX_REG
+#define MFD_IDTRC38XXX_REG
+
+/* GLOBAL */
+#define SOFT_RESET_CTRL		(0x15) /* Specific to FC3W */
+#define MISC_CTRL		(0x14) /* Specific to FC3A */
+#define APLL_REINIT		BIT(1)
+#define APLL_REINIT_VFC3A	BIT(2)
+
+#define DEVICE_ID		(0x2)
+#define DEVICE_ID_MASK		(0x1000) /* Bit 12 is 1 if FC3W and 0 if FC3A */
+#define DEVICE_ID_SHIFT		(12)
+
+/* FOD */
+#define FOD_0		(0x300)
+#define FOD_0_VFC3A	(0x400)
+#define FOD_1		(0x340)
+#define FOD_1_VFC3A	(0x440)
+#define FOD_2		(0x380)
+#define FOD_2_VFC3A	(0x480)
+
+/* TDCAPLL */
+#define TDC_CTRL		(0x44a) /* Specific to FC3W */
+#define TDC_ENABLE_CTRL		(0x169) /* Specific to FC3A */
+#define TDC_DAC_CAL_CTRL	(0x16a) /* Specific to FC3A */
+#define TDC_EN			BIT(0)
+#define TDC_DAC_RECAL_REQ	BIT(1)
+#define TDC_DAC_RECAL_REQ_VFC3A	BIT(0)
+
+#define TDC_FB_DIV_INT_CNFG		(0x442)
+#define TDC_FB_DIV_INT_CNFG_VFC3A	(0x162)
+#define TDC_FB_DIV_INT_MASK		GENMASK(7, 0)
+#define TDC_REF_DIV_CNFG		(0x443)
+#define TDC_REF_DIV_CNFG_VFC3A		(0x163)
+#define TDC_REF_DIV_CONFIG_MASK		GENMASK(2, 0)
+
+/* TIME SYNC CHANNEL */
+#define TIME_CLOCK_SRC		(0xa01) /* Specific to FC3W */
+#define TIME_CLOCK_COUNT	(0xa00) /* Specific to FC3W */
+#define TIME_CLOCK_COUNT_MASK	GENMASK(5, 0)
+
+#define SUB_SYNC_GEN_CNFG	(0xa04)
+
+#define TOD_COUNTER_READ_REQ		(0xa5f)
+#define TOD_COUNTER_READ_REQ_VFC3A	(0x6df)
+#define TOD_SYNC_LOAD_VAL_CTRL		(0xa10)
+#define TOD_SYNC_LOAD_VAL_CTRL_VFC3A	(0x690)
+#define SYNC_COUNTER_MASK		GENMASK_ULL(51, 0)
+#define SUB_SYNC_COUNTER_MASK		GENMASK(30, 0)
+#define TOD_SYNC_LOAD_REQ_CTRL		(0xa21)
+#define TOD_SYNC_LOAD_REQ_CTRL_VFC3A	(0x6a1)
+#define SYNC_LOAD_ENABLE		BIT(1)
+#define SUB_SYNC_LOAD_ENABLE		BIT(0)
+#define SYNC_LOAD_REQ			BIT(0)
+
+#define LPF_MODE_CNFG		(0xa80)
+#define LPF_MODE_CNFG_VFC3A	(0x700)
+enum lpf_mode {
+	LPF_DISABLED = 0,
+	LPF_WP       = 1,
+	LPF_HOLDOVER = 2,
+	LPF_WF       = 3,
+	LPF_INVALID  = 4
+};
+#define LPF_CTRL	(0xa98)
+#define LPF_CTRL_VFC3A	(0x718)
+#define LPF_EN		BIT(0)
+
+#define LPF_BW_CNFG	(0xa81)
+#define LPF_BW_SHIFT	GENMASK(7, 3)
+#define LPF_BW_MULT		GENMASK(2, 0)
+#define LPF_BW_SHIFT_DEFAULT	(0xb)
+#define LPF_BW_MULT_DEFAULT		(0x0)
+#define LPF_BW_SHIFT_1PPS		(0x5)
+
+#define LPF_WR_PHASE_CTRL	(0xaa8)
+#define LPF_WR_PHASE_CTRL_VFC3A	(0x728)
+#define LPF_WR_FREQ_CTRL	(0xab0)
+#define LPF_WR_FREQ_CTRL_VFC3A	(0x730)
+
+#define TIME_CLOCK_TDC_FANOUT_CNFG	(0xB00)
+#define TIME_SYNC_TO_TDC_EN	BIT(0)
+#define SIG1_MUX_SEL_MASK	GENMASK(7, 4)
+#define SIG2_MUX_SEL_MASK	GENMASK(11, 8)
+enum tdc_mux_sel {
+	REF0 = 0,
+	REF1 = 1,
+	REF2 = 2,
+	REF3 = 3,
+	REF_CLK5 = 4,
+	REF_CLK6 = 5,
+	DPLL_FB_TO_TDC = 6,
+	DPLL_FB_DIVIDED_TO_TDC = 7,
+	TIME_CLK_DIVIDED = 8,
+	TIME_SYNC = 9,
+};
+
+#define TIME_CLOCK_MEAS_CNFG	(0xB04)
+#define TDC_MEAS_MODE	BIT(0)
+enum tdc_meas_mode {
+	CONTINUOUS = 0,
+	ONE_SHOT = 1,
+	MEAS_MODE_INVALID = 2,
+};
+
+#define TIME_CLOCK_MEAS_DIV_CNFG	(0xB08)
+#define TIME_REF_DIV_MASK	GENMASK(29, 24)
+
+#define TIME_CLOCK_MEAS_CTRL	(0xB10)
+#define TDC_MEAS_EN	BIT(0)
+#define TDC_MEAS_START	BIT(1)
+
+#define TDC_FIFO_READ_REQ	(0xB2F)
+#define TDC_FIFO_READ		(0xB30)
+#define COARSE_MEAS_MASK	GENMASK_ULL(39, 13)
+#define FINE_MEAS_MASK		GENMASK(12, 0)
+
+#define TDC_FIFO_CTRL		(0xB12)
+#define FIFO_CLEAR		BIT(0)
+#define TDC_FIFO_STS		(0xB38)
+#define FIFO_FULL		BIT(1)
+#define FIFO_EMPTY		BIT(0)
+#define TDC_FIFO_EVENT		(0xB39)
+#define FIFO_OVERRUN		BIT(1)
+
+/* DPLL */
+#define MAX_REFERENCE_INDEX	(3)
+#define MAX_NUM_REF_PRIORITY	(4)
+
+#define MAX_DPLL_INDEX	(2)
+
+#define DPLL_STS		(0x580)
+#define DPLL_STS_VFC3A		(0x571)
+#define DPLL_STATE_STS_MASK	(0x70)
+#define DPLL_STATE_STS_SHIFT	(4)
+#define DPLL_REF_SEL_STS_MASK	(0x6)
+#define DPLL_REF_SEL_STS_SHIFT	(1)
+
+#define DPLL_REF_PRIORITY_CNFG			(0x502)
+#define DPLL_REFX_PRIORITY_DISABLE_MASK		(0xf)
+#define DPLL_REF0_PRIORITY_ENABLE_AND_SET_MASK	(0x31)
+#define DPLL_REF1_PRIORITY_ENABLE_AND_SET_MASK	(0xc2)
+#define DPLL_REF2_PRIORITY_ENABLE_AND_SET_MASK	(0x304)
+#define DPLL_REF3_PRIORITY_ENABLE_AND_SET_MASK	(0xc08)
+#define DPLL_REF0_PRIORITY_SHIFT		(4)
+#define DPLL_REF1_PRIORITY_SHIFT		(6)
+#define DPLL_REF2_PRIORITY_SHIFT		(8)
+#define DPLL_REF3_PRIORITY_SHIFT		(10)
+
+enum dpll_state {
+	DPLL_STATE_MIN             = 0,
+	DPLL_STATE_FREERUN         = DPLL_STATE_MIN,
+	DPLL_STATE_LOCKED          = 1,
+	DPLL_STATE_HOLDOVER        = 2,
+	DPLL_STATE_WRITE_FREQUENCY = 3,
+	DPLL_STATE_ACQUIRE         = 4,
+	DPLL_STATE_HITLESS_SWITCH  = 5,
+	DPLL_STATE_MAX             = DPLL_STATE_HITLESS_SWITCH
+};
+
+/* REFMON */
+#define LOSMON_STS_0		(0x81e)
+#define LOSMON_STS_0_VFC3A	(0x18e)
+#define LOSMON_STS_1		(0x82e)
+#define LOSMON_STS_1_VFC3A	(0x19e)
+#define LOSMON_STS_2		(0x83e)
+#define LOSMON_STS_2_VFC3A	(0x1ae)
+#define LOSMON_STS_3		(0x84e)
+#define LOSMON_STS_3_VFC3A	(0x1be)
+#define LOS_STS_MASK		(0x1)
+
+#define FREQMON_STS_0		(0x874)
+#define FREQMON_STS_0_VFC3A	(0x1d4)
+#define FREQMON_STS_1		(0x894)
+#define FREQMON_STS_1_VFC3A	(0x1f4)
+#define FREQMON_STS_2		(0x8b4)
+#define FREQMON_STS_2_VFC3A	(0x214)
+#define FREQMON_STS_3		(0x8d4)
+#define FREQMON_STS_3_VFC3A	(0x234)
+#define FREQ_FAIL_STS_SHIFT	(31)
+
+/* Firmware interface */
+#define TIME_CLK_FREQ_ADDR	(0xffa0)
+#define XTAL_FREQ_ADDR		(0xffa1)
+
+/*
+ * Return register address and field mask based on passed in firmware version
+ */
+#define IDTFC3_FW_REG(FW, VER, REG)	(((FW) < (VER)) ? (REG) : (REG##_##VER))
+#define IDTFC3_FW_FIELD(FW, VER, FIELD)	(((FW) < (VER)) ? (FIELD) : (FIELD##_##VER))
+enum fw_version {
+	V_DEFAULT = 0,
+	VFC3W     = 1,
+	VFC3A     = 2
+};
+
+/* XTAL_FREQ_ADDR/TIME_CLK_FREQ_ADDR */
+enum {
+	FREQ_MIN     = 0,
+	FREQ_25M     = 1,
+	FREQ_49_152M = 2,
+	FREQ_50M     = 3,
+	FREQ_100M    = 4,
+	FREQ_125M    = 5,
+	FREQ_250M    = 6,
+	FREQ_MAX
+};
+
+struct idtfc3_hw_param {
+	u32 xtal_freq;
+	u32 time_clk_freq;
+};
+
+struct idtfc3_fwrc {
+	u8 hiaddr;
+	u8 loaddr;
+	u8 value;
+	u8 reserved;
+} __packed;
+
+static inline void idtfc3_default_hw_param(struct idtfc3_hw_param *hw_param)
+{
+	hw_param->xtal_freq = 49152000;
+	hw_param->time_clk_freq = 25000000;
+}
+
+static inline int idtfc3_set_hw_param(struct idtfc3_hw_param *hw_param,
+				      u16 addr, u8 val)
+{
+	if (addr == XTAL_FREQ_ADDR)
+		switch (val) {
+		case FREQ_49_152M:
+			hw_param->xtal_freq = 49152000;
+			break;
+		case FREQ_50M:
+			hw_param->xtal_freq = 50000000;
+			break;
+		default:
+			return -EINVAL;
+		}
+	else if (addr == TIME_CLK_FREQ_ADDR)
+		switch (val) {
+		case FREQ_25M:
+			hw_param->time_clk_freq = 25000000;
+			break;
+		case FREQ_50M:
+			hw_param->time_clk_freq = 50000000;
+			break;
+		case FREQ_100M:
+			hw_param->time_clk_freq = 100000000;
+			break;
+		case FREQ_125M:
+			hw_param->time_clk_freq = 125000000;
+			break;
+		case FREQ_250M:
+			hw_param->time_clk_freq = 250000000;
+			break;
+		default:
+			return -EINVAL;
+		}
+	else
+		return -EFAULT;
+
+	return 0;
+}
+
+#endif
diff --git a/include/linux/mfd/intel-m10-bmc.h b/include/linux/mfd/intel-m10-bmc.h
index 1812ebfa11a8..988f1cd90032 100644
--- a/include/linux/mfd/intel-m10-bmc.h
+++ b/include/linux/mfd/intel-m10-bmc.h
@@ -11,6 +11,7 @@
 #include <linux/bits.h>
 #include <linux/dev_printk.h>
 #include <linux/regmap.h>
+#include <linux/rwsem.h>
 
 #define M10BMC_N3000_LEGACY_BUILD_VER	0x300468
 #define M10BMC_N3000_SYS_BASE		0x300800
@@ -39,6 +40,11 @@
 #define M10BMC_N3000_VER_PCB_INFO_MSK	GENMASK(31, 24)
 #define M10BMC_N3000_VER_LEGACY_INVALID	0xffffffff
 
+/* Telemetry registers */
+#define M10BMC_N3000_TELEM_START	0x100
+#define M10BMC_N3000_TELEM_END		0x250
+#define M10BMC_D5005_TELEM_END		0x300
+
 /* Secure update doorbell register, in system register region */
 #define M10BMC_N3000_DOORBELL		0x400
 
@@ -199,17 +205,22 @@ struct m10bmc_csr_map {
 	unsigned int pr_reh_addr;
 	unsigned int pr_magic;
 	unsigned int rsu_update_counter;
+	unsigned int staging_size;
 };
 
 /**
  * struct intel_m10bmc_platform_info - Intel MAX 10 BMC platform specific information
  * @cells: MFD cells
  * @n_cells: MFD cells ARRAY_SIZE()
+ * @handshake_sys_reg_ranges: array of register ranges for fw handshake regs
+ * @handshake_sys_reg_nranges: number of register ranges for fw handshake regs
  * @csr_map: the mappings for register definition of MAX10 BMC
  */
 struct intel_m10bmc_platform_info {
 	struct mfd_cell *cells;
 	int n_cells;
+	const struct regmap_range *handshake_sys_reg_ranges;
+	unsigned int handshake_sys_reg_nranges;
 	const struct m10bmc_csr_map *csr_map;
 };
 
@@ -232,18 +243,30 @@ struct intel_m10bmc_flash_bulk_ops {
 	void (*unlock_write)(struct intel_m10bmc *m10bmc);
 };
 
+enum m10bmc_fw_state {
+	M10BMC_FW_STATE_NORMAL,
+	M10BMC_FW_STATE_SEC_UPDATE_PREPARE,
+	M10BMC_FW_STATE_SEC_UPDATE_WRITE,
+	M10BMC_FW_STATE_SEC_UPDATE_PROGRAM,
+};
+
 /**
  * struct intel_m10bmc - Intel MAX 10 BMC parent driver data structure
  * @dev: this device
  * @regmap: the regmap used to access registers by m10bmc itself
  * @info: the platform information for MAX10 BMC
  * @flash_bulk_ops: optional device specific operations for flash R/W
+ * @bmcfw_lock: read/write semaphore to BMC firmware running state
+ * @bmcfw_state: BMC firmware running state. Available only when
+ *		 handshake_sys_reg_nranges > 0.
  */
 struct intel_m10bmc {
 	struct device *dev;
 	struct regmap *regmap;
 	const struct intel_m10bmc_platform_info *info;
 	const struct intel_m10bmc_flash_bulk_ops *flash_bulk_ops;
+	struct rw_semaphore bmcfw_lock;		/* Protects bmcfw_state */
+	enum m10bmc_fw_state bmcfw_state;
 };
 
 /*
@@ -251,6 +274,7 @@ struct intel_m10bmc {
  *
  * m10bmc_raw_read - read m10bmc register per addr
  * m10bmc_sys_read - read m10bmc system register per offset
+ * m10bmc_sys_update_bits - update m10bmc system register per offset
  */
 static inline int
 m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr,
@@ -266,21 +290,15 @@ m10bmc_raw_read(struct intel_m10bmc *m10bmc, unsigned int addr,
 	return ret;
 }
 
+int m10bmc_sys_read(struct intel_m10bmc *m10bmc, unsigned int offset, unsigned int *val);
+int m10bmc_sys_update_bits(struct intel_m10bmc *m10bmc, unsigned int offset,
+			   unsigned int msk, unsigned int val);
+
 /*
- * The base of the system registers could be configured by HW developers, and
- * in HW SPEC, the base is not added to the addresses of the system registers.
- *
- * This function helps to simplify the accessing of the system registers. And if
- * the base is reconfigured in HW, SW developers could simply change the
- * csr_map's base accordingly.
+ * Track the state of the firmware, as it is not available for register
+ * handshakes during secure updates on some MAX 10 cards.
  */
-static inline int m10bmc_sys_read(struct intel_m10bmc *m10bmc, unsigned int offset,
-				  unsigned int *val)
-{
-	const struct m10bmc_csr_map *csr_map = m10bmc->info->csr_map;
-
-	return m10bmc_raw_read(m10bmc, csr_map->base + offset, val);
-}
+void m10bmc_fw_state_set(struct intel_m10bmc *m10bmc, enum m10bmc_fw_state new_state);
 
 /*
  * MAX10 BMC Core support
diff --git a/include/linux/mfd/lm3533.h b/include/linux/mfd/lm3533.h
index 77092f6363ad..69059a7a2ce5 100644
--- a/include/linux/mfd/lm3533.h
+++ b/include/linux/mfd/lm3533.h
@@ -16,6 +16,7 @@
 	DEVICE_ATTR(_name, S_IRUGO | S_IWUSR , show_##_name, store_##_name)
 
 struct device;
+struct gpio_desc;
 struct regmap;
 
 struct lm3533 {
@@ -23,7 +24,7 @@ struct lm3533 {
 
 	struct regmap *regmap;
 
-	int gpio_hwen;
+	struct gpio_desc *hwen;
 	int irq;
 
 	unsigned have_als:1;
@@ -69,8 +70,6 @@ enum lm3533_boost_ovp {
 };
 
 struct lm3533_platform_data {
-	int gpio_hwen;
-
 	enum lm3533_boost_ovp boost_ovp;
 	enum lm3533_boost_freq boost_freq;
 
diff --git a/include/linux/mfd/loongson-se.h b/include/linux/mfd/loongson-se.h
new file mode 100644
index 000000000000..07afa0c2524d
--- /dev/null
+++ b/include/linux/mfd/loongson-se.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/* Copyright (C) 2025 Loongson Technology Corporation Limited */
+
+#ifndef __MFD_LOONGSON_SE_H__
+#define __MFD_LOONGSON_SE_H__
+
+#define LOONGSON_ENGINE_CMD_TIMEOUT_US	10000
+#define SE_SEND_CMD_REG			0x0
+#define SE_SEND_CMD_REG_LEN		0x8
+/* Controller command ID */
+#define SE_CMD_START			0x0
+#define SE_CMD_SET_DMA			0x3
+#define SE_CMD_SET_ENGINE_CMDBUF	0x4
+
+#define SE_S2LINT_STAT			0x88
+#define SE_S2LINT_EN			0x8c
+#define SE_S2LINT_CL			0x94
+#define SE_L2SINT_STAT			0x98
+#define SE_L2SINT_SET			0xa0
+
+#define SE_INT_ALL			0xffffffff
+#define SE_INT_CONTROLLER		BIT(0)
+
+#define SE_ENGINE_MAX			16
+#define SE_ENGINE_RNG			1
+#define SE_CMD_RNG			0x100
+
+#define SE_ENGINE_TPM			5
+#define SE_CMD_TPM			0x500
+
+#define SE_ENGINE_CMD_SIZE		32
+
+struct loongson_se_engine {
+	struct loongson_se *se;
+	int id;
+
+	/* Command buffer */
+	void *command;
+	void *command_ret;
+
+	void *data_buffer;
+	uint buffer_size;
+	/* Data buffer offset to DMA base */
+	uint buffer_off;
+
+	struct completion completion;
+
+};
+
+struct loongson_se_engine *loongson_se_init_engine(struct device *dev, int id);
+int loongson_se_send_engine_cmd(struct loongson_se_engine *engine);
+
+#endif
diff --git a/include/linux/mfd/lp3943.h b/include/linux/mfd/lp3943.h
index 020a339f96e8..402f01078fcc 100644
--- a/include/linux/mfd/lp3943.h
+++ b/include/linux/mfd/lp3943.h
@@ -11,7 +11,6 @@
 #define __MFD_LP3943_H__
 
 #include <linux/gpio.h>
-#include <linux/pwm.h>
 #include <linux/regmap.h>
 
 /* Registers */
diff --git a/include/linux/mfd/lp8788.h b/include/linux/mfd/lp8788.h
index 3d5c480d58ea..fd17bec2a33e 100644
--- a/include/linux/mfd/lp8788.h
+++ b/include/linux/mfd/lp8788.h
@@ -10,9 +10,7 @@
 #ifndef __MFD_LP8788_H__
 #define __MFD_LP8788_H__
 
-#include <linux/gpio.h>
 #include <linux/irqdomain.h>
-#include <linux/pwm.h>
 #include <linux/regmap.h>
 
 #define LP8788_DEV_BUCK		"lp8788-buck"
@@ -88,12 +86,6 @@ enum lp8788_charger_event {
 	CHARGER_DETECTED,
 };
 
-enum lp8788_bl_ctrl_mode {
-	LP8788_BL_REGISTER_ONLY,
-	LP8788_BL_COMB_PWM_BASED,	/* PWM + I2C, changed by PWM input */
-	LP8788_BL_COMB_REGISTER_BASED,	/* PWM + I2C, changed by I2C */
-};
-
 enum lp8788_bl_dim_mode {
 	LP8788_DIM_EXPONENTIAL,
 	LP8788_DIM_LINEAR,
@@ -159,21 +151,17 @@ struct lp8788;
 
 /*
  * lp8788_buck1_dvs
- * @gpio         : gpio pin number for dvs control
  * @vsel         : dvs selector for buck v1 register
  */
 struct lp8788_buck1_dvs {
-	int gpio;
 	enum lp8788_dvs_sel vsel;
 };
 
 /*
  * lp8788_buck2_dvs
- * @gpio         : two gpio pin numbers are used for dvs
  * @vsel         : dvs selector for buck v2 register
  */
 struct lp8788_buck2_dvs {
-	int gpio[LP8788_NUM_BUCK2_DVS];
 	enum lp8788_dvs_sel vsel;
 };
 
@@ -207,31 +195,6 @@ struct lp8788_charger_platform_data {
 };
 
 /*
- * struct lp8788_backlight_platform_data
- * @name                  : backlight driver name. (default: "lcd-backlight")
- * @initial_brightness    : initial value of backlight brightness
- * @bl_mode               : brightness control by pwm or lp8788 register
- * @dim_mode              : dimming mode selection
- * @full_scale            : full scale current setting
- * @rise_time             : brightness ramp up step time
- * @fall_time             : brightness ramp down step time
- * @pwm_pol               : pwm polarity setting when bl_mode is pwm based
- * @period_ns             : platform specific pwm period value. unit is nano.
-			    Only valid when bl_mode is LP8788_BL_COMB_PWM_BASED
- */
-struct lp8788_backlight_platform_data {
-	char *name;
-	int initial_brightness;
-	enum lp8788_bl_ctrl_mode bl_mode;
-	enum lp8788_bl_dim_mode dim_mode;
-	enum lp8788_bl_full_scale_current full_scale;
-	enum lp8788_bl_ramp_step rise_time;
-	enum lp8788_bl_ramp_step fall_time;
-	enum pwm_polarity pwm_pol;
-	unsigned int period_ns;
-};
-
-/*
  * struct lp8788_led_platform_data
  * @name         : led driver name. (default: "keyboard-backlight")
  * @scale        : current scale
@@ -268,11 +231,10 @@ struct lp8788_vib_platform_data {
  * @buck_data    : regulator initial data for buck
  * @dldo_data    : regulator initial data for digital ldo
  * @aldo_data    : regulator initial data for analog ldo
- * @buck1_dvs    : gpio configurations for buck1 dvs
- * @buck2_dvs    : gpio configurations for buck2 dvs
+ * @buck1_dvs    : configurations for buck1 dvs
+ * @buck2_dvs    : configurations for buck2 dvs
  * @chg_pdata    : platform data for charger driver
  * @alarm_sel    : rtc alarm selection (1 or 2)
- * @bl_pdata     : configurable data for backlight driver
  * @led_pdata    : configurable data for led driver
  * @vib_pdata    : configurable data for vibrator driver
  * @adc_pdata    : iio map data for adc driver
@@ -294,9 +256,6 @@ struct lp8788_platform_data {
 	/* rtc alarm */
 	enum lp8788_alarm_sel alarm_sel;
 
-	/* backlight */
-	struct lp8788_backlight_platform_data *bl_pdata;
-
 	/* current sinks */
 	struct lp8788_led_platform_data *led_pdata;
 	struct lp8788_vib_platform_data *vib_pdata;
diff --git a/include/linux/mfd/lpc_ich.h b/include/linux/mfd/lpc_ich.h
index ea4a4b1b246a..1fbda1f8967d 100644
--- a/include/linux/mfd/lpc_ich.h
+++ b/include/linux/mfd/lpc_ich.h
@@ -15,7 +15,7 @@
 #define ICH_RES_GPE0	1
 
 /* GPIO compatibility */
-enum {
+enum lpc_gpio_versions {
 	ICH_I3100_GPIO,
 	ICH_V5_GPIO,
 	ICH_V6_GPIO,
@@ -26,11 +26,14 @@ enum {
 	AVOTON_GPIO,
 };
 
+struct lpc_ich_gpio_info;
+
 struct lpc_ich_info {
 	char name[32];
 	unsigned int iTCO_version;
-	unsigned int gpio_version;
+	enum lpc_gpio_versions gpio_version;
 	enum intel_spi_type spi_type;
+	const struct lpc_ich_gpio_info *gpio_info;
 	u8 use_gpio;
 };
 
diff --git a/include/linux/mfd/macsmc.h b/include/linux/mfd/macsmc.h
new file mode 100644
index 000000000000..cc09ecce0df7
--- /dev/null
+++ b/include/linux/mfd/macsmc.h
@@ -0,0 +1,280 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple SMC (System Management Controller) core definitions
+ *
+ * Copyright (C) The Asahi Linux Contributors
+ */
+
+#ifndef _LINUX_MFD_MACSMC_H
+#define _LINUX_MFD_MACSMC_H
+
+#include <linux/soc/apple/rtkit.h>
+
+/**
+ * typedef smc_key - Alias for u32 to be used for SMC keys
+ *
+ * SMC keys are 32bit integers containing packed ASCII characters in natural
+ * integer order, i.e. 0xAABBCCDD, which represent the FourCC ABCD.
+ * The SMC driver is designed with this assumption and ensures the right
+ * endianness is used when these are stored to memory and sent to or received
+ * from the actual SMC firmware (which can be done in either shared memory or
+ * as 64bit mailbox message on Apple Silicon).
+ * Internally, SMC stores these keys in a table sorted lexicographically and
+ * allows resolving an index into this table to the corresponding SMC key.
+ * Thus, storing keys as u32 is very convenient as it allows to e.g. use
+ * normal comparison operators which directly map to the natural order used
+ * by SMC firmware.
+ *
+ * This simple type alias is introduced to allow easy recognition of SMC key
+ * variables and arguments.
+ */
+typedef u32 smc_key;
+
+/**
+ * SMC_KEY - Convert FourCC SMC keys in source code to smc_key
+ *
+ * This macro can be used to easily define FourCC SMC keys in source code
+ * and convert these to u32 / smc_key, e.g. SMC_KEY(NTAP) will expand to
+ * 0x4e544150.
+ *
+ * @s: FourCC SMC key to be converted
+ */
+#define SMC_KEY(s) (smc_key)(_SMC_KEY(#s))
+#define _SMC_KEY(s) (((s)[0] << 24) | ((s)[1] << 16) | ((s)[2] << 8) | (s)[3])
+#define __SMC_KEY(a, b, c, d) (((u32)(a) << 24) | ((u32)(b) << 16) | ((u32)(c) << 8) | ((u32)(d)))
+
+#define APPLE_SMC_READABLE BIT(7)
+#define APPLE_SMC_WRITABLE BIT(6)
+#define APPLE_SMC_FUNCTION BIT(4)
+
+/**
+ * struct apple_smc_key_info - Information for a SMC key as returned by SMC
+ * @type_code: FourCC code indicating the type for this key.
+ *             Known types:
+ *              ch8*: ASCII string
+ *              flag: Boolean, 1 or 0
+ *              flt: 32-bit single-precision IEEE 754 float
+ *              hex: Binary data
+ *              ioft: 64bit Unsigned fixed-point intger (48.16)
+ *              {si,ui}{8,16,32,64}: Signed/Unsigned 8-/16-/32-/64-bit integer
+ * @size: Size of the buffer associated with this key
+ * @flags: Bitfield encoding flags (APPLE_SMC_{READABLE,WRITABLE,FUNCTION})
+ */
+struct apple_smc_key_info {
+	u32 type_code;
+	u8 size;
+	u8 flags;
+};
+
+/**
+ * enum apple_smc_boot_stage - SMC boot stage
+ * @APPLE_SMC_BOOTING: SMC is booting
+ * @APPLE_SMC_INITIALIZED: SMC is initialized and ready to use
+ * @APPLE_SMC_ERROR_NO_SHMEM: Shared memory could not be initialized during boot
+ * @APPLE_SMC_ERROR_CRASHED: SMC has crashed
+ */
+enum apple_smc_boot_stage {
+	APPLE_SMC_BOOTING,
+	APPLE_SMC_INITIALIZED,
+	APPLE_SMC_ERROR_NO_SHMEM,
+	APPLE_SMC_ERROR_CRASHED
+};
+
+/**
+ * struct apple_smc
+ * @dev: Underlying device struct for the physical backend device
+ * @key_count: Number of available SMC keys
+ * @first_key: First valid SMC key
+ * @last_key: Last valid SMC key
+ * @event_handlers: Notifier call chain for events received from SMC
+ * @rtk: Pointer to Apple RTKit instance
+ * @init_done: Completion for initialization
+ * @boot_stage: Current boot stage of SMC
+ * @sram: Pointer to SRAM resource
+ * @sram_base: SRAM base address
+ * @shmem: RTKit shared memory structure for SRAM
+ * @msg_id: Current message id for commands, will be incremented for each command
+ * @atomic_mode: Flag set when atomic mode is entered
+ * @atomic_pending: Flag indicating pending atomic command
+ * @cmd_done: Completion for command execution in non-atomic mode
+ * @cmd_ret: Return value from SMC for last command
+ * @mutex: Mutex for non-atomic mode
+ * @lock: Spinlock for atomic mode
+ */
+struct apple_smc {
+	struct device *dev;
+
+	u32 key_count;
+	smc_key first_key;
+	smc_key last_key;
+
+	struct blocking_notifier_head event_handlers;
+
+	struct apple_rtkit *rtk;
+
+	struct completion init_done;
+	enum apple_smc_boot_stage boot_stage;
+
+	struct resource *sram;
+	void __iomem *sram_base;
+	struct apple_rtkit_shmem shmem;
+
+	unsigned int msg_id;
+
+	bool atomic_mode;
+	bool atomic_pending;
+	struct completion cmd_done;
+	u64 cmd_ret;
+
+	struct mutex mutex;
+	spinlock_t lock;
+};
+
+/**
+ * apple_smc_read - Read size bytes from given SMC key into buf
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key to be read
+ * @buf: Buffer into which size bytes of data will be read from SMC
+ * @size: Number of bytes to be read into buf
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_read(struct apple_smc *smc, smc_key key, void *buf, size_t size);
+
+/**
+ * apple_smc_write - Write size bytes into given SMC key from buf
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key data will be written to
+ * @buf: Buffer from which size bytes of data will be written to SMC
+ * @size: Number of bytes to be written
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_write(struct apple_smc *smc, smc_key key, const void *buf, size_t size);
+
+/**
+ * apple_smc_enter_atomic - Enter atomic mode to be able to use apple_smc_write_atomic
+ * @smc: Pointer to apple_smc struct
+ *
+ * This function switches the SMC backend to atomic mode which allows the
+ * use of apple_smc_write_atomic while disabling *all* other functions.
+ * This is only used for shutdown/reboot which requires writing to a SMC
+ * key from atomic context.
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_enter_atomic(struct apple_smc *smc);
+
+/**
+ * apple_smc_write_atomic - Write size bytes into given SMC key from buf without sleeping
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key data will be written to
+ * @buf: Buffer from which size bytes of data will be written to SMC
+ * @size: Number of bytes to be written
+ *
+ * Note that this function will fail if apple_smc_enter_atomic hasn't been
+ * called before.
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_write_atomic(struct apple_smc *smc, smc_key key, const void *buf, size_t size);
+
+/**
+ * apple_smc_rw - Write and then read using the given SMC key
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key data will be written to
+ * @wbuf: Buffer from which size bytes of data will be written to SMC
+ * @wsize: Number of bytes to be written
+ * @rbuf: Buffer to which size bytes of data will be read from SMC
+ * @rsize: Number of bytes to be read
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_rw(struct apple_smc *smc, smc_key key, const void *wbuf, size_t wsize,
+		 void *rbuf, size_t rsize);
+
+/**
+ * apple_smc_get_key_by_index - Given an index return the corresponding SMC key
+ * @smc: Pointer to apple_smc struct
+ * @index: Index to be resolved
+ * @key: Buffer for SMC key to be returned
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_get_key_by_index(struct apple_smc *smc, int index, smc_key *key);
+
+/**
+ * apple_smc_get_key_info - Get key information from SMC
+ * @smc: Pointer to apple_smc struct
+ * @key: Key to acquire information for
+ * @info: Pointer to struct apple_smc_key_info which will be filled
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_get_key_info(struct apple_smc *smc, smc_key key, struct apple_smc_key_info *info);
+
+/**
+ * apple_smc_key_exists - Check if the given SMC key exists
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key to be checked
+ *
+ * Return: True if the key exists, false otherwise
+ */
+static inline bool apple_smc_key_exists(struct apple_smc *smc, smc_key key)
+{
+	return apple_smc_get_key_info(smc, key, NULL) >= 0;
+}
+
+#define APPLE_SMC_TYPE_OPS(type) \
+	static inline int apple_smc_read_##type(struct apple_smc *smc, smc_key key, type *p) \
+	{ \
+		int ret = apple_smc_read(smc, key, p, sizeof(*p)); \
+		return (ret < 0) ? ret : ((ret != sizeof(*p)) ? -EINVAL : 0); \
+	} \
+	static inline int apple_smc_write_##type(struct apple_smc *smc, smc_key key, type p) \
+	{ \
+		return apple_smc_write(smc, key, &p, sizeof(p)); \
+	} \
+	static inline int apple_smc_write_##type##_atomic(struct apple_smc *smc, smc_key key, type p) \
+	{ \
+		return apple_smc_write_atomic(smc, key, &p, sizeof(p)); \
+	} \
+	static inline int apple_smc_rw_##type(struct apple_smc *smc, smc_key key, \
+					      type w, type *r) \
+	{ \
+		int ret = apple_smc_rw(smc, key, &w, sizeof(w), r, sizeof(*r)); \
+		return (ret < 0) ? ret : ((ret != sizeof(*r)) ? -EINVAL : 0); \
+	}
+
+APPLE_SMC_TYPE_OPS(u64)
+APPLE_SMC_TYPE_OPS(u32)
+APPLE_SMC_TYPE_OPS(u16)
+APPLE_SMC_TYPE_OPS(u8)
+APPLE_SMC_TYPE_OPS(s64)
+APPLE_SMC_TYPE_OPS(s32)
+APPLE_SMC_TYPE_OPS(s16)
+APPLE_SMC_TYPE_OPS(s8)
+
+static inline int apple_smc_read_flag(struct apple_smc *smc, smc_key key, bool *flag)
+{
+	u8 val;
+	int ret = apple_smc_read_u8(smc, key, &val);
+
+	if (ret < 0)
+		return ret;
+
+	*flag = val ? true : false;
+	return ret;
+}
+
+static inline int apple_smc_write_flag(struct apple_smc *smc, smc_key key, bool state)
+{
+	return apple_smc_write_u8(smc, key, state ? 1 : 0);
+}
+
+static inline int apple_smc_write_flag_atomic(struct apple_smc *smc, smc_key key, bool state)
+{
+	return apple_smc_write_u8_atomic(smc, key, state ? 1 : 0);
+}
+
+#endif
diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h
index 32e3470708ed..7e84738cbb20 100644
--- a/include/linux/mfd/madera/pdata.h
+++ b/include/linux/mfd/madera/pdata.h
@@ -8,10 +8,11 @@
 #ifndef MADERA_PDATA_H
 #define MADERA_PDATA_H
 
-#include <linux/kernel.h>
 #include <linux/regulator/arizona-ldo1.h>
 #include <linux/regulator/arizona-micsupp.h>
 #include <linux/regulator/machine.h>
+#include <linux/types.h>
+
 #include <sound/madera-pdata.h>
 
 #define MADERA_MAX_MICBIAS		4
diff --git a/include/linux/mfd/max14577-private.h b/include/linux/mfd/max14577-private.h
index a21374f8ad26..dd51a37fa37f 100644
--- a/include/linux/mfd/max14577-private.h
+++ b/include/linux/mfd/max14577-private.h
@@ -2,7 +2,7 @@
 /*
  * max14577-private.h - Common API for the Maxim 14577/77836 internal sub chip
  *
- * Copyright (C) 2014 Samsung Electrnoics
+ * Copyright (C) 2014 Samsung Electronics
  * Chanwoo Choi <cw00.choi@samsung.com>
  * Krzysztof Kozlowski <krzk@kernel.org>
  */
diff --git a/include/linux/mfd/max14577.h b/include/linux/mfd/max14577.h
index 8b3ef891ba42..0fda5c2e745a 100644
--- a/include/linux/mfd/max14577.h
+++ b/include/linux/mfd/max14577.h
@@ -2,7 +2,7 @@
 /*
  * max14577.h - Driver for the Maxim 14577/77836
  *
- * Copyright (C) 2014 Samsung Electrnoics
+ * Copyright (C) 2014 Samsung Electronics
  * Chanwoo Choi <cw00.choi@samsung.com>
  * Krzysztof Kozlowski <krzk@kernel.org>
  *
diff --git a/include/linux/mfd/max597x.h b/include/linux/mfd/max5970.h
index a850b2e02e6a..fc50e89edfaa 100644
--- a/include/linux/mfd/max597x.h
+++ b/include/linux/mfd/max5970.h
@@ -7,26 +7,14 @@
  * Author: Patrick Rudolph <patrick.rudolph@9elements.com>
  */
 
-#ifndef _MFD_MAX597X_H
-#define _MFD_MAX597X_H
+#ifndef _MFD_MAX5970_H
+#define _MFD_MAX5970_H
 
 #include <linux/regmap.h>
 
 #define MAX5970_NUM_SWITCHES 2
 #define MAX5978_NUM_SWITCHES 1
-#define MAX597X_NUM_LEDS     4
-
-struct max597x_data {
-	int num_switches;
-	u32 irng[MAX5970_NUM_SWITCHES];
-	u32 mon_rng[MAX5970_NUM_SWITCHES];
-	u32 shunt_micro_ohms[MAX5970_NUM_SWITCHES];
-};
-
-enum max597x_chip_type {
-	MAX597x_TYPE_MAX5978 = 1,
-	MAX597x_TYPE_MAX5970,
-};
+#define MAX5970_NUM_LEDS     4
 
 #define MAX5970_REG_CURRENT_L(ch)		(0x01 + (ch) * 4)
 #define MAX5970_REG_CURRENT_H(ch)		(0x00 + (ch) * 4)
@@ -93,4 +81,4 @@ enum max597x_chip_type {
 #define MAX_REGISTERS			0x49
 #define ADC_MASK			0x3FF
 
-#endif				/* _MFD_MAX597X_H */
+#endif				/* _MFD_MAX5970_H */
diff --git a/include/linux/mfd/max7360.h b/include/linux/mfd/max7360.h
new file mode 100644
index 000000000000..44cf2bf651a2
--- /dev/null
+++ b/include/linux/mfd/max7360.h
@@ -0,0 +1,109 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#ifndef __LINUX_MFD_MAX7360_H
+#define __LINUX_MFD_MAX7360_H
+
+#include <linux/bits.h>
+
+#define MAX7360_MAX_KEY_ROWS		8
+#define MAX7360_MAX_KEY_COLS		8
+#define MAX7360_MAX_KEY_NUM		(MAX7360_MAX_KEY_ROWS * MAX7360_MAX_KEY_COLS)
+#define MAX7360_ROW_SHIFT		3
+
+#define MAX7360_MAX_GPIO		8
+#define MAX7360_MAX_GPO			6
+#define MAX7360_PORT_PWM_COUNT		8
+#define MAX7360_PORT_RTR_PIN		(MAX7360_PORT_PWM_COUNT - 1)
+
+/*
+ * MAX7360 registers
+ */
+#define MAX7360_REG_KEYFIFO		0x00
+#define MAX7360_REG_CONFIG		0x01
+#define MAX7360_REG_DEBOUNCE		0x02
+#define MAX7360_REG_INTERRUPT		0x03
+#define MAX7360_REG_PORTS		0x04
+#define MAX7360_REG_KEYREP		0x05
+#define MAX7360_REG_SLEEP		0x06
+
+/*
+ * MAX7360 GPIO registers
+ *
+ * All these registers are reset together when writing bit 3 of
+ * MAX7360_REG_GPIOCFG.
+ */
+#define MAX7360_REG_GPIOCFG		0x40
+#define MAX7360_REG_GPIOCTRL		0x41
+#define MAX7360_REG_GPIODEB		0x42
+#define MAX7360_REG_GPIOCURR		0x43
+#define MAX7360_REG_GPIOOUTM		0x44
+#define MAX7360_REG_PWMCOM		0x45
+#define MAX7360_REG_RTRCFG		0x46
+#define MAX7360_REG_I2C_TIMEOUT		0x48
+#define MAX7360_REG_GPIOIN		0x49
+#define MAX7360_REG_RTR_CNT		0x4A
+#define MAX7360_REG_PWMBASE		0x50
+#define MAX7360_REG_PWMCFGBASE		0x58
+
+#define MAX7360_REG_GPIO_LAST		0x5F
+
+#define MAX7360_REG_PWM(x)		(MAX7360_REG_PWMBASE + (x))
+#define MAX7360_REG_PWMCFG(x)		(MAX7360_REG_PWMCFGBASE + (x))
+
+/*
+ * Configuration register bits
+ */
+#define MAX7360_FIFO_EMPTY		0x3F
+#define MAX7360_FIFO_OVERFLOW		0x7F
+#define MAX7360_FIFO_RELEASE		BIT(6)
+#define MAX7360_FIFO_COL		GENMASK(5, 3)
+#define MAX7360_FIFO_ROW		GENMASK(2, 0)
+
+#define MAX7360_CFG_SLEEP		BIT(7)
+#define MAX7360_CFG_INTERRUPT		BIT(5)
+#define MAX7360_CFG_KEY_RELEASE		BIT(3)
+#define MAX7360_CFG_WAKEUP		BIT(1)
+#define MAX7360_CFG_TIMEOUT		BIT(0)
+
+#define MAX7360_DEBOUNCE		GENMASK(4, 0)
+#define MAX7360_DEBOUNCE_MIN		9
+#define MAX7360_DEBOUNCE_MAX		40
+#define MAX7360_PORTS			GENMASK(8, 5)
+
+#define MAX7360_INTERRUPT_TIME_MASK	GENMASK(4, 0)
+#define MAX7360_INTERRUPT_FIFO_MASK	GENMASK(7, 5)
+
+#define MAX7360_PORT_CFG_INTERRUPT_MASK		BIT(7)
+#define MAX7360_PORT_CFG_INTERRUPT_EDGES	BIT(6)
+#define MAX7360_PORT_CFG_COMMON_PWM		BIT(5)
+
+/*
+ * Autosleep register values
+ */
+#define MAX7360_AUTOSLEEP_8192MS	0x01
+#define MAX7360_AUTOSLEEP_4096MS	0x02
+#define MAX7360_AUTOSLEEP_2048MS	0x03
+#define MAX7360_AUTOSLEEP_1024MS	0x04
+#define MAX7360_AUTOSLEEP_512MS		0x05
+#define MAX7360_AUTOSLEEP_256MS		0x06
+
+#define MAX7360_GPIO_CFG_RTR_EN		BIT(7)
+#define MAX7360_GPIO_CFG_GPIO_EN	BIT(4)
+#define MAX7360_GPIO_CFG_GPIO_RST	BIT(3)
+
+#define MAX7360_ROT_DEBOUNCE		GENMASK(3, 0)
+#define MAX7360_ROT_DEBOUNCE_MIN	0
+#define MAX7360_ROT_DEBOUNCE_MAX	15
+#define MAX7360_ROT_INTCNT		GENMASK(6, 4)
+#define MAX7360_ROT_INTCNT_DLY		BIT(7)
+
+#define MAX7360_INT_INTI		0
+#define MAX7360_INT_INTK		1
+
+#define MAX7360_INT_GPIO		0
+#define MAX7360_INT_KEYPAD		1
+#define MAX7360_INT_ROTARY		2
+
+#define MAX7360_NR_INTERNAL_IRQS	3
+
+#endif
diff --git a/include/linux/mfd/max77541.h b/include/linux/mfd/max77541.h
new file mode 100644
index 000000000000..fe5c0a3dc637
--- /dev/null
+++ b/include/linux/mfd/max77541.h
@@ -0,0 +1,91 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef __MFD_MAX77541_H
+#define __MFD_MAX77541_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+/* REGISTERS */
+#define MAX77541_REG_INT_SRC                    0x00
+#define MAX77541_REG_INT_SRC_M                  0x01
+
+#define MAX77541_BIT_INT_SRC_TOPSYS             BIT(0)
+#define MAX77541_BIT_INT_SRC_BUCK               BIT(1)
+
+#define MAX77541_REG_TOPSYS_INT                 0x02
+#define MAX77541_REG_TOPSYS_INT_M               0x03
+
+#define MAX77541_BIT_TOPSYS_INT_TJ_120C         BIT(0)
+#define MAX77541_BIT_TOPSYS_INT_TJ_140C         BIT(1)
+#define MAX77541_BIT_TOPSYS_INT_TSHDN           BIT(2)
+#define MAX77541_BIT_TOPSYS_INT_UVLO            BIT(3)
+#define MAX77541_BIT_TOPSYS_INT_ALT_SWO         BIT(4)
+#define MAX77541_BIT_TOPSYS_INT_EXT_FREQ_DET    BIT(5)
+
+/* REGULATORS */
+#define MAX77541_REG_BUCK_INT                   0x20
+#define MAX77541_REG_BUCK_INT_M                 0x21
+
+#define MAX77541_BIT_BUCK_INT_M1_POK_FLT        BIT(0)
+#define MAX77541_BIT_BUCK_INT_M2_POK_FLT        BIT(1)
+#define MAX77541_BIT_BUCK_INT_M1_SCFLT          BIT(4)
+#define MAX77541_BIT_BUCK_INT_M2_SCFLT          BIT(5)
+
+#define MAX77541_REG_EN_CTRL                    0x0B
+
+#define MAX77541_BIT_M1_EN                      BIT(0)
+#define MAX77541_BIT_M2_EN                      BIT(1)
+
+#define MAX77541_REG_M1_VOUT                    0x23
+#define MAX77541_REG_M2_VOUT                    0x33
+
+#define MAX77541_BITS_MX_VOUT                   GENMASK(7, 0)
+
+#define MAX77541_REG_M1_CFG1                    0x25
+#define MAX77541_REG_M2_CFG1                    0x35
+
+#define MAX77541_BITS_MX_CFG1_RNG               GENMASK(7, 6)
+
+/* ADC */
+#define MAX77541_REG_ADC_INT                    0x70
+#define MAX77541_REG_ADC_INT_M                  0x71
+
+#define MAX77541_BIT_ADC_INT_CH1_I              BIT(0)
+#define MAX77541_BIT_ADC_INT_CH2_I              BIT(1)
+#define MAX77541_BIT_ADC_INT_CH3_I              BIT(2)
+#define MAX77541_BIT_ADC_INT_CH6_I              BIT(5)
+
+#define MAX77541_REG_ADC_DATA_CH1               0x72
+#define MAX77541_REG_ADC_DATA_CH2               0x73
+#define MAX77541_REG_ADC_DATA_CH3               0x74
+#define MAX77541_REG_ADC_DATA_CH6               0x77
+
+/* INTERRUPT MASKS*/
+#define MAX77541_REG_INT_SRC_MASK               0x00
+#define MAX77541_REG_TOPSYS_INT_MASK            0x00
+#define MAX77541_REG_BUCK_INT_MASK              0x00
+
+#define MAX77541_MAX_REGULATORS 2
+
+enum max7754x_ids {
+	MAX77540 = 1,
+	MAX77541,
+};
+
+struct regmap;
+struct regmap_irq_chip_data;
+struct i2c_client;
+
+struct max77541 {
+	struct i2c_client *i2c;
+	struct regmap *regmap;
+	enum max7754x_ids id;
+
+	struct regmap_irq_chip_data *irq_data;
+	struct regmap_irq_chip_data *irq_buck;
+	struct regmap_irq_chip_data *irq_topsys;
+	struct regmap_irq_chip_data *irq_adc;
+};
+
+#endif /* __MFD_MAX77541_H */
diff --git a/include/linux/mfd/max77686-private.h b/include/linux/mfd/max77686-private.h
index 3acceeedbaba..e6b8b4014dc0 100644
--- a/include/linux/mfd/max77686-private.h
+++ b/include/linux/mfd/max77686-private.h
@@ -2,7 +2,7 @@
 /*
  * max77686-private.h - Voltage regulator driver for the Maxim 77686/802
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  Chiwoong Byun <woong.byun@samsung.com>
  */
 
@@ -441,8 +441,4 @@ enum max77686_types {
 	TYPE_MAX77802,
 };
 
-extern int max77686_irq_init(struct max77686_dev *max77686);
-extern void max77686_irq_exit(struct max77686_dev *max77686);
-extern int max77686_irq_resume(struct max77686_dev *max77686);
-
 #endif /*  __LINUX_MFD_MAX77686_PRIV_H */
diff --git a/include/linux/mfd/max77686.h b/include/linux/mfd/max77686.h
index d0fb510875e6..7c4624acd1db 100644
--- a/include/linux/mfd/max77686.h
+++ b/include/linux/mfd/max77686.h
@@ -2,7 +2,7 @@
 /*
  * max77686.h - Driver for the Maxim 77686/802
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  Chiwoong Byun <woong.byun@samsung.com>
  *
  * This driver is based on max8997.h
diff --git a/include/linux/mfd/max77693-common.h b/include/linux/mfd/max77693-common.h
index a5bce099f1ed..ec2e1b2dceb8 100644
--- a/include/linux/mfd/max77693-common.h
+++ b/include/linux/mfd/max77693-common.h
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0+ */
 /*
- * Common data shared between Maxim 77693 and 77843 drivers
+ * Common data shared between Maxim 77693, 77705 and 77843 drivers
  *
  * Copyright (C) 2015 Samsung Electronics
  */
@@ -11,6 +11,7 @@
 enum max77693_types {
 	TYPE_MAX77693_UNKNOWN,
 	TYPE_MAX77693,
+	TYPE_MAX77705,
 	TYPE_MAX77843,
 
 	TYPE_MAX77693_NUM,
@@ -32,6 +33,7 @@ struct max77693_dev {
 	struct regmap *regmap_muic;
 	struct regmap *regmap_haptic;	/* Only MAX77693 */
 	struct regmap *regmap_chg;	/* Only MAX77843 */
+	struct regmap *regmap_leds;	/* Only MAX77705 */
 
 	struct regmap_irq_chip_data *irq_data_led;
 	struct regmap_irq_chip_data *irq_data_topsys;
diff --git a/include/linux/mfd/max77693-private.h b/include/linux/mfd/max77693-private.h
index 311f7d3d2323..8e7c35b5ea1c 100644
--- a/include/linux/mfd/max77693-private.h
+++ b/include/linux/mfd/max77693-private.h
@@ -2,7 +2,7 @@
 /*
  * max77693-private.h - Voltage regulator driver for the Maxim 77693
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  SangYoung Son <hello.son@samsung.com>
  *
  * This program is not provided / owned by Maxim Integrated Products.
@@ -217,6 +217,10 @@ enum max77693_charger_battery_state {
 #define CHG_CNFG_01_CHGRSTRT_MASK	(0x3 << CHG_CNFG_01_CHGRSTRT_SHIFT)
 #define CHG_CNFG_01_PQEN_MAKS		BIT(CHG_CNFG_01_PQEN_SHIFT)
 
+/* MAX77693_CHG_REG_CHG_CNFG_02 register */
+#define CHG_CNFG_02_CC_SHIFT		0
+#define CHG_CNFG_02_CC_MASK		0x3F
+
 /* MAX77693_CHG_REG_CHG_CNFG_03 register */
 #define CHG_CNFG_03_TOITH_SHIFT		0
 #define CHG_CNFG_03_TOTIME_SHIFT	3
@@ -244,6 +248,7 @@ enum max77693_charger_battery_state {
 #define CHG_CNFG_12_VCHGINREG_MASK	(0x3 << CHG_CNFG_12_VCHGINREG_SHIFT)
 
 /* MAX77693 CHG_CNFG_09 Register */
+#define CHG_CNFG_09_CHGIN_ILIM_SHIFT	0
 #define CHG_CNFG_09_CHGIN_ILIM_MASK	0x7F
 
 /* MAX77693 CHG_CTRL Register */
@@ -405,7 +410,7 @@ enum max77693_haptic_reg {
 	MAX77693_HAPTIC_REG_END,
 };
 
-/* max77693-pmic LSCNFG configuraton register */
+/* max77693-pmic LSCNFG configuration register */
 #define MAX77693_PMIC_LOW_SYS_MASK      0x80
 #define MAX77693_PMIC_LOW_SYS_SHIFT     7
 
@@ -414,17 +419,6 @@ enum max77693_haptic_reg {
 #define MAX77693_CONFIG2_MEN            6
 #define MAX77693_CONFIG2_HTYP           5
 
-enum max77693_irq_source {
-	LED_INT = 0,
-	TOPSYS_INT,
-	CHG_INT,
-	MUIC_INT1,
-	MUIC_INT2,
-	MUIC_INT3,
-
-	MAX77693_IRQ_GROUP_NR,
-};
-
 #define SRC_IRQ_CHARGER			BIT(0)
 #define SRC_IRQ_TOP			BIT(1)
 #define SRC_IRQ_FLASH			BIT(2)
diff --git a/include/linux/mfd/max77693.h b/include/linux/mfd/max77693.h
index c67c16ba8649..8e77ebeb7cf1 100644
--- a/include/linux/mfd/max77693.h
+++ b/include/linux/mfd/max77693.h
@@ -2,7 +2,7 @@
 /*
  * max77693.h - Driver for the Maxim 77693
  *
- *  Copyright (C) 2012 Samsung Electrnoics
+ *  Copyright (C) 2012 Samsung Electronics
  *  SangYoung Son <hello.son@samsung.com>
  *
  * This program is not provided / owned by Maxim Integrated Products.
diff --git a/include/linux/mfd/max77705-private.h b/include/linux/mfd/max77705-private.h
new file mode 100644
index 000000000000..214de7feeb8c
--- /dev/null
+++ b/include/linux/mfd/max77705-private.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Maxim MAX77705 definitions.
+ *
+ * Copyright (C) 2015 Samsung Electronics, Inc.
+ * Copyright (C) 2025 Dzmitry Sankouski <dsankouski@gmail.com>
+ */
+
+#ifndef __LINUX_MFD_MAX77705_PRIV_H
+#define __LINUX_MFD_MAX77705_PRIV_H
+
+#define MAX77705_SRC_IRQ_CHG	BIT(0)
+#define MAX77705_SRC_IRQ_TOP	BIT(1)
+#define MAX77705_SRC_IRQ_FG	BIT(2)
+#define MAX77705_SRC_IRQ_USBC	BIT(3)
+#define MAX77705_SRC_IRQ_ALL	(MAX77705_SRC_IRQ_CHG | MAX77705_SRC_IRQ_TOP | \
+				MAX77705_SRC_IRQ_FG | MAX77705_SRC_IRQ_USBC)
+
+/* MAX77705_PMIC_REG_PMICREV register */
+#define MAX77705_VERSION_SHIFT	3
+#define MAX77705_REVISION_MASK	GENMASK(2, 0)
+#define MAX77705_VERSION_MASK	GENMASK(7, MAX77705_VERSION_SHIFT)
+/* MAX77705_PMIC_REG_MAINCTRL1 register */
+#define MAX77705_MAINCTRL1_BIASEN_SHIFT	7
+#define MAX77705_MAINCTRL1_BIASEN_MASK	BIT(MAX77705_MAINCTRL1_BIASEN_SHIFT)
+/* MAX77705_PMIC_REG_MCONFIG2 (haptics) register */
+#define MAX77705_CONFIG2_MEN_SHIFT	6
+#define MAX77705_CONFIG2_MODE_SHIFT	7
+#define MAX77705_CONFIG2_HTYP_SHIFT	5
+/* MAX77705_PMIC_REG_SYSTEM_INT_MASK register */
+#define MAX77705_SYSTEM_IRQ_BSTEN_INT	BIT(3)
+#define MAX77705_SYSTEM_IRQ_SYSUVLO_INT	BIT(4)
+#define MAX77705_SYSTEM_IRQ_SYSOVLO_INT	BIT(5)
+#define MAX77705_SYSTEM_IRQ_TSHDN_INT	BIT(6)
+#define MAX77705_SYSTEM_IRQ_TM_INT	BIT(7)
+/* MAX77705_RGBLED_REG_LEDEN register */
+#define MAX77705_RGBLED_EN_WIDTH	2
+/* MAX77705_RGBLED_REG_LEDBLNK register */
+#define MAX77705_RGB_DELAY_100_STEP_LIM 500
+#define MAX77705_RGB_DELAY_100_STEP_COUNT 4
+#define MAX77705_RGB_DELAY_100_STEP 100
+#define MAX77705_RGB_DELAY_250_STEP_LIM 3250
+#define MAX77705_RGB_DELAY_250_STEP 250
+#define MAX77705_RGB_DELAY_500_STEP 500
+#define MAX77705_RGB_DELAY_500_STEP_COUNT 10
+#define MAX77705_RGB_DELAY_500_STEP_LIM 5000
+#define MAX77705_RGB_DELAY_1000_STEP_LIM 8000
+#define MAX77705_RGB_DELAY_1000_STEP_COUNT 13
+#define MAX77705_RGB_DELAY_1000_STEP 1000
+#define MAX77705_RGB_DELAY_2000_STEP 2000
+#define MAX77705_RGB_DELAY_2000_STEP_COUNT 13
+#define MAX77705_RGB_DELAY_2000_STEP_LIM 12000
+
+enum max77705_hw_rev {
+	MAX77705_PASS1 = 1,
+	MAX77705_PASS2,
+	MAX77705_PASS3
+};
+
+enum max77705_reg {
+	MAX77705_PMIC_REG_PMICID1		= 0x00,
+	MAX77705_PMIC_REG_PMICREV		= 0x01,
+	MAX77705_PMIC_REG_MAINCTRL1		= 0x02,
+	MAX77705_PMIC_REG_BSTOUT_MASK		= 0x03,
+	MAX77705_PMIC_REG_FORCE_EN_MASK		= 0x08,
+	MAX77705_PMIC_REG_MCONFIG		= 0x10,
+	MAX77705_PMIC_REG_MCONFIG2		= 0x11,
+	MAX77705_PMIC_REG_INTSRC		= 0x22,
+	MAX77705_PMIC_REG_INTSRC_MASK		= 0x23,
+	MAX77705_PMIC_REG_SYSTEM_INT		= 0x24,
+	MAX77705_PMIC_REG_RESERVED_25		= 0x25,
+	MAX77705_PMIC_REG_SYSTEM_INT_MASK	= 0x26,
+	MAX77705_PMIC_REG_RESERVED_27		= 0x27,
+	MAX77705_PMIC_REG_RESERVED_28		= 0x28,
+	MAX77705_PMIC_REG_RESERVED_29		= 0x29,
+	MAX77705_PMIC_REG_BOOSTCONTROL1		= 0x4C,
+	MAX77705_PMIC_REG_BOOSTCONTROL2		= 0x4F,
+	MAX77705_PMIC_REG_SW_RESET		= 0x50,
+	MAX77705_PMIC_REG_USBC_RESET		= 0x51,
+
+	MAX77705_PMIC_REG_END
+};
+
+enum max77705_chg_reg {
+	MAX77705_CHG_REG_BASE			= 0xB0,
+	MAX77705_CHG_REG_INT			= 0,
+	MAX77705_CHG_REG_INT_MASK,
+	MAX77705_CHG_REG_INT_OK,
+	MAX77705_CHG_REG_DETAILS_00,
+	MAX77705_CHG_REG_DETAILS_01,
+	MAX77705_CHG_REG_DETAILS_02,
+	MAX77705_CHG_REG_DTLS_03,
+	MAX77705_CHG_REG_CNFG_00,
+	MAX77705_CHG_REG_CNFG_01,
+	MAX77705_CHG_REG_CNFG_02,
+	MAX77705_CHG_REG_CNFG_03,
+	MAX77705_CHG_REG_CNFG_04,
+	MAX77705_CHG_REG_CNFG_05,
+	MAX77705_CHG_REG_CNFG_06,
+	MAX77705_CHG_REG_CNFG_07,
+	MAX77705_CHG_REG_CNFG_08,
+	MAX77705_CHG_REG_CNFG_09,
+	MAX77705_CHG_REG_CNFG_10,
+	MAX77705_CHG_REG_CNFG_11,
+
+	MAX77705_CHG_REG_CNFG_12,
+	MAX77705_CHG_REG_CNFG_13,
+	MAX77705_CHG_REG_CNFG_14,
+	MAX77705_CHG_REG_SAFEOUT_CTRL
+};
+
+enum max77705_fuelgauge_reg {
+	STATUS_REG				= 0x00,
+	VALRT_THRESHOLD_REG			= 0x01,
+	TALRT_THRESHOLD_REG			= 0x02,
+	SALRT_THRESHOLD_REG			= 0x03,
+	REMCAP_REP_REG				= 0x05,
+	SOCREP_REG				= 0x06,
+	TEMPERATURE_REG				= 0x08,
+	VCELL_REG				= 0x09,
+	TIME_TO_EMPTY_REG			= 0x11,
+	FULLSOCTHR_REG				= 0x13,
+	CURRENT_REG				= 0x0A,
+	AVG_CURRENT_REG				= 0x0B,
+	SOCMIX_REG				= 0x0D,
+	SOCAV_REG				= 0x0E,
+	REMCAP_MIX_REG				= 0x0F,
+	FULLCAP_REG				= 0x10,
+	RFAST_REG				= 0x15,
+	AVR_TEMPERATURE_REG			= 0x16,
+	CYCLES_REG				= 0x17,
+	DESIGNCAP_REG				= 0x18,
+	AVR_VCELL_REG				= 0x19,
+	TIME_TO_FULL_REG			= 0x20,
+	CONFIG_REG				= 0x1D,
+	ICHGTERM_REG				= 0x1E,
+	REMCAP_AV_REG				= 0x1F,
+	FULLCAP_NOM_REG				= 0x23,
+	LEARN_CFG_REG				= 0x28,
+	FILTER_CFG_REG				= 0x29,
+	MISCCFG_REG				= 0x2B,
+	QRTABLE20_REG				= 0x32,
+	FULLCAP_REP_REG				= 0x35,
+	RCOMP_REG				= 0x38,
+	VEMPTY_REG				= 0x3A,
+	FSTAT_REG				= 0x3D,
+	DISCHARGE_THRESHOLD_REG			= 0x40,
+	QRTABLE30_REG				= 0x42,
+	ISYS_REG				= 0x43,
+	DQACC_REG				= 0x45,
+	DPACC_REG				= 0x46,
+	AVGISYS_REG				= 0x4B,
+	QH_REG					= 0x4D,
+	VSYS_REG				= 0xB1,
+	TALRTTH2_REG				= 0xB2,
+	VBYP_REG				= 0xB3,
+	CONFIG2_REG				= 0xBB,
+	IIN_REG					= 0xD0,
+	OCV_REG					= 0xEE,
+	VFOCV_REG				= 0xFB,
+	VFSOC_REG				= 0xFF,
+
+	MAX77705_FG_END
+};
+
+enum max77705_led_reg {
+	MAX77705_RGBLED_REG_BASE		= 0x30,
+	MAX77705_RGBLED_REG_LEDEN		= 0,
+	MAX77705_RGBLED_REG_LED0BRT,
+	MAX77705_RGBLED_REG_LED1BRT,
+	MAX77705_RGBLED_REG_LED2BRT,
+	MAX77705_RGBLED_REG_LED3BRT,
+	MAX77705_RGBLED_REG_LEDRMP,
+	MAX77705_RGBLED_REG_LEDBLNK,
+	MAX77705_LED_REG_END
+};
+
+enum max77705_charger_battery_state {
+	MAX77705_BATTERY_NOBAT,
+	MAX77705_BATTERY_PREQUALIFICATION,
+	MAX77705_BATTERY_DEAD,
+	MAX77705_BATTERY_GOOD,
+	MAX77705_BATTERY_LOWVOLTAGE,
+	MAX77705_BATTERY_OVERVOLTAGE,
+	MAX77705_BATTERY_RESERVED
+};
+
+enum max77705_charger_charge_type {
+	MAX77705_CHARGER_CONSTANT_CURRENT	= 1,
+	MAX77705_CHARGER_CONSTANT_VOLTAGE,
+	MAX77705_CHARGER_END_OF_CHARGE,
+	MAX77705_CHARGER_DONE
+};
+
+#endif /* __LINUX_MFD_MAX77705_PRIV_H */
diff --git a/include/linux/mfd/max77759.h b/include/linux/mfd/max77759.h
new file mode 100644
index 000000000000..c6face34e385
--- /dev/null
+++ b/include/linux/mfd/max77759.h
@@ -0,0 +1,165 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2020 Google Inc.
+ * Copyright 2025 Linaro Ltd.
+ *
+ * Maxim MAX77759 core driver
+ */
+
+#ifndef __LINUX_MFD_MAX77759_H
+#define __LINUX_MFD_MAX77759_H
+
+#include <linux/completion.h>
+#include <linux/mutex.h>
+#include <linux/regmap.h>
+
+#define MAX77759_PMIC_REG_PMIC_ID               0x00
+#define MAX77759_PMIC_REG_PMIC_REVISION         0x01
+#define MAX77759_PMIC_REG_OTP_REVISION          0x02
+#define MAX77759_PMIC_REG_INTSRC                0x22
+#define MAX77759_PMIC_REG_INTSRCMASK            0x23
+#define   MAX77759_PMIC_REG_INTSRC_MAXQ         BIT(3)
+#define   MAX77759_PMIC_REG_INTSRC_TOPSYS       BIT(1)
+#define   MAX77759_PMIC_REG_INTSRC_CHGR         BIT(0)
+#define MAX77759_PMIC_REG_TOPSYS_INT            0x24
+#define MAX77759_PMIC_REG_TOPSYS_INT_MASK       0x26
+#define   MAX77759_PMIC_REG_TOPSYS_INT_TSHDN    BIT(6)
+#define   MAX77759_PMIC_REG_TOPSYS_INT_SYSOVLO  BIT(5)
+#define   MAX77759_PMIC_REG_TOPSYS_INT_SYSUVLO  BIT(4)
+#define   MAX77759_PMIC_REG_TOPSYS_INT_FSHIP    BIT(0)
+#define MAX77759_PMIC_REG_I2C_CNFG              0x40
+#define MAX77759_PMIC_REG_SWRESET               0x50
+#define MAX77759_PMIC_REG_CONTROL_FG            0x51
+
+#define MAX77759_MAXQ_REG_UIC_INT1              0x64
+#define   MAX77759_MAXQ_REG_UIC_INT1_APCMDRESI  BIT(7)
+#define   MAX77759_MAXQ_REG_UIC_INT1_SYSMSGI    BIT(6)
+#define   MAX77759_MAXQ_REG_UIC_INT1_GPIO6I     BIT(1)
+#define   MAX77759_MAXQ_REG_UIC_INT1_GPIO5I     BIT(0)
+#define   MAX77759_MAXQ_REG_UIC_INT1_GPIOxI(offs, en)  (((en) & 1) << (offs))
+#define   MAX77759_MAXQ_REG_UIC_INT1_GPIOxI_MASK(offs) \
+				MAX77759_MAXQ_REG_UIC_INT1_GPIOxI(offs, ~0)
+#define MAX77759_MAXQ_REG_UIC_INT2              0x65
+#define MAX77759_MAXQ_REG_UIC_INT3              0x66
+#define MAX77759_MAXQ_REG_UIC_INT4              0x67
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS1       0x68
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS2       0x69
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS3       0x6a
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS4       0x6b
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS5       0x6c
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS6       0x6d
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS7       0x6f
+#define MAX77759_MAXQ_REG_UIC_UIC_STATUS8       0x6f
+#define MAX77759_MAXQ_REG_UIC_INT1_M            0x70
+#define MAX77759_MAXQ_REG_UIC_INT2_M            0x71
+#define MAX77759_MAXQ_REG_UIC_INT3_M            0x72
+#define MAX77759_MAXQ_REG_UIC_INT4_M            0x73
+#define MAX77759_MAXQ_REG_AP_DATAOUT0           0x81
+#define MAX77759_MAXQ_REG_AP_DATAOUT32          0xa1
+#define MAX77759_MAXQ_REG_AP_DATAIN0            0xb1
+#define MAX77759_MAXQ_REG_UIC_SWRST             0xe0
+
+#define MAX77759_CHGR_REG_CHG_INT               0xb0
+#define MAX77759_CHGR_REG_CHG_INT2              0xb1
+#define MAX77759_CHGR_REG_CHG_INT_MASK          0xb2
+#define MAX77759_CHGR_REG_CHG_INT2_MASK         0xb3
+#define MAX77759_CHGR_REG_CHG_INT_OK            0xb4
+#define MAX77759_CHGR_REG_CHG_DETAILS_00        0xb5
+#define MAX77759_CHGR_REG_CHG_DETAILS_01        0xb6
+#define MAX77759_CHGR_REG_CHG_DETAILS_02        0xb7
+#define MAX77759_CHGR_REG_CHG_DETAILS_03        0xb8
+#define MAX77759_CHGR_REG_CHG_CNFG_00           0xb9
+#define MAX77759_CHGR_REG_CHG_CNFG_01           0xba
+#define MAX77759_CHGR_REG_CHG_CNFG_02           0xbb
+#define MAX77759_CHGR_REG_CHG_CNFG_03           0xbc
+#define MAX77759_CHGR_REG_CHG_CNFG_04           0xbd
+#define MAX77759_CHGR_REG_CHG_CNFG_05           0xbe
+#define MAX77759_CHGR_REG_CHG_CNFG_06           0xbf
+#define MAX77759_CHGR_REG_CHG_CNFG_07           0xc0
+#define MAX77759_CHGR_REG_CHG_CNFG_08           0xc1
+#define MAX77759_CHGR_REG_CHG_CNFG_09           0xc2
+#define MAX77759_CHGR_REG_CHG_CNFG_10           0xc3
+#define MAX77759_CHGR_REG_CHG_CNFG_11           0xc4
+#define MAX77759_CHGR_REG_CHG_CNFG_12           0xc5
+#define MAX77759_CHGR_REG_CHG_CNFG_13           0xc6
+#define MAX77759_CHGR_REG_CHG_CNFG_14           0xc7
+#define MAX77759_CHGR_REG_CHG_CNFG_15           0xc8
+#define MAX77759_CHGR_REG_CHG_CNFG_16           0xc9
+#define MAX77759_CHGR_REG_CHG_CNFG_17           0xca
+#define MAX77759_CHGR_REG_CHG_CNFG_18           0xcb
+#define MAX77759_CHGR_REG_CHG_CNFG_19           0xcc
+
+/* MaxQ opcodes for max77759_maxq_command() */
+#define MAX77759_MAXQ_OPCODE_MAXLENGTH (MAX77759_MAXQ_REG_AP_DATAOUT32 - \
+					MAX77759_MAXQ_REG_AP_DATAOUT0 + \
+					1)
+
+#define MAX77759_MAXQ_OPCODE_GPIO_TRIGGER_READ   0x21
+#define MAX77759_MAXQ_OPCODE_GPIO_TRIGGER_WRITE  0x22
+#define MAX77759_MAXQ_OPCODE_GPIO_CONTROL_READ   0x23
+#define MAX77759_MAXQ_OPCODE_GPIO_CONTROL_WRITE  0x24
+#define MAX77759_MAXQ_OPCODE_USER_SPACE_READ     0x81
+#define MAX77759_MAXQ_OPCODE_USER_SPACE_WRITE    0x82
+
+/**
+ * struct max77759 - core max77759 internal data structure
+ *
+ * @regmap_top: Regmap for accessing TOP registers
+ * @maxq_lock: Lock for serializing access to MaxQ
+ * @regmap_maxq: Regmap for accessing MaxQ registers
+ * @cmd_done: Used to signal completion of a MaxQ command
+ * @regmap_charger: Regmap for accessing charger registers
+ *
+ * The MAX77759 comprises several sub-blocks, namely TOP, MaxQ, Charger,
+ * Fuel Gauge, and TCPCI.
+ */
+struct max77759 {
+	struct regmap *regmap_top;
+
+	/* This protects MaxQ commands - only one can be active */
+	struct mutex maxq_lock;
+	struct regmap *regmap_maxq;
+	struct completion cmd_done;
+
+	struct regmap *regmap_charger;
+};
+
+/**
+ * struct max77759_maxq_command - structure containing the MaxQ command to
+ * send
+ *
+ * @length: The number of bytes to send.
+ * @cmd: The data to send.
+ */
+struct max77759_maxq_command {
+	u8 length;
+	u8 cmd[] __counted_by(length);
+};
+
+/**
+ * struct max77759_maxq_response - structure containing the MaxQ response
+ *
+ * @length: The number of bytes to receive.
+ * @rsp: The data received. Must have at least @length bytes space.
+ */
+struct max77759_maxq_response {
+	u8 length;
+	u8 rsp[] __counted_by(length);
+};
+
+/**
+ * max77759_maxq_command() - issue a MaxQ command and wait for the response
+ * and associated data
+ *
+ * @max77759: The core max77759 device handle.
+ * @cmd: The command to be sent.
+ * @rsp: Any response data associated with the command will be copied here;
+ *     can be %NULL if the command has no response (other than ACK).
+ *
+ * Return: 0 on success, a negative error number otherwise.
+ */
+int max77759_maxq_command(struct max77759 *max77759,
+			  const struct max77759_maxq_command *cmd,
+			  struct max77759_maxq_response *rsp);
+
+#endif /* __LINUX_MFD_MAX77759_H */
diff --git a/include/linux/mfd/max77843-private.h b/include/linux/mfd/max77843-private.h
index 0bc7454c4dbe..2fb4db67f110 100644
--- a/include/linux/mfd/max77843-private.h
+++ b/include/linux/mfd/max77843-private.h
@@ -198,7 +198,7 @@ enum max77843_irq_muic {
 #define MAX77843_MCONFIG_MEN_MASK		BIT(MCONFIG_MEN_SHIFT)
 #define MAX77843_MCONFIG_PDIV_MASK		(0x3 << MCONFIG_PDIV_SHIFT)
 
-/* Max77843 charger insterrupts */
+/* Max77843 charger interrupts */
 #define MAX77843_CHG_BYP_I			BIT(0)
 #define MAX77843_CHG_BATP_I			BIT(2)
 #define MAX77843_CHG_BAT_I			BIT(3)
diff --git a/include/linux/mfd/max8997-private.h b/include/linux/mfd/max8997-private.h
index a10cd6945232..261c0aae7d00 100644
--- a/include/linux/mfd/max8997-private.h
+++ b/include/linux/mfd/max8997-private.h
@@ -2,7 +2,7 @@
 /*
  * max8997-private.h - Voltage regulator driver for the Maxim 8997
  *
- *  Copyright (C) 2010 Samsung Electrnoics
+ *  Copyright (C) 2010 Samsung Electronics
  *  MyungJoo Ham <myungjoo.ham@samsung.com>
  */
 
@@ -397,7 +397,6 @@ enum max8997_types {
 };
 
 extern int max8997_irq_init(struct max8997_dev *max8997);
-extern void max8997_irq_exit(struct max8997_dev *max8997);
 extern int max8997_irq_resume(struct max8997_dev *max8997);
 
 extern int max8997_read_reg(struct i2c_client *i2c, u8 reg, u8 *dest);
diff --git a/include/linux/mfd/max8997.h b/include/linux/mfd/max8997.h
index 6193905abbb5..fb36e1386069 100644
--- a/include/linux/mfd/max8997.h
+++ b/include/linux/mfd/max8997.h
@@ -2,7 +2,7 @@
 /*
  * max8997.h - Driver for the Maxim 8997/8966
  *
- *  Copyright (C) 2009-2010 Samsung Electrnoics
+ *  Copyright (C) 2009-2010 Samsung Electronics
  *  MyungJoo Ham <myungjoo.ham@samsung.com>
  *
  * This driver is based on max8998.h
@@ -178,7 +178,6 @@ struct max8997_platform_data {
 	 *
 	 */
 	bool ignore_gpiodvs_side_effect;
-	int buck125_gpios[3]; /* GPIO of [0]SET1, [1]SET2, [2]SET3 */
 	int buck125_default_idx; /* Default value of SET1, 2, 3 */
 	unsigned int buck1_voltage[8]; /* buckx_voltage in uV */
 	bool buck1_gpiodvs;
diff --git a/include/linux/mfd/max8998-private.h b/include/linux/mfd/max8998-private.h
index 6deb5f577602..d77dc18db6eb 100644
--- a/include/linux/mfd/max8998-private.h
+++ b/include/linux/mfd/max8998-private.h
@@ -2,7 +2,7 @@
 /*
  * max8998-private.h - Voltage regulator driver for the Maxim 8998
  *
- *  Copyright (C) 2009-2010 Samsung Electrnoics
+ *  Copyright (C) 2009-2010 Samsung Electronics
  *  Kyungmin Park <kyungmin.park@samsung.com>
  *  Marek Szyprowski <m.szyprowski@samsung.com>
  */
diff --git a/include/linux/mfd/max8998.h b/include/linux/mfd/max8998.h
index 79c020bd0c70..5473f1983e31 100644
--- a/include/linux/mfd/max8998.h
+++ b/include/linux/mfd/max8998.h
@@ -2,7 +2,7 @@
 /*
  * max8998.h - Voltage regulator driver for the Maxim 8998
  *
- *  Copyright (C) 2009-2010 Samsung Electrnoics
+ *  Copyright (C) 2009-2010 Samsung Electronics
  *  Kyungmin Park <kyungmin.park@samsung.com>
  *  Marek Szyprowski <m.szyprowski@samsung.com>
  */
@@ -65,10 +65,7 @@ struct max8998_regulator_data {
  *   be other than the preset values.
  * @buck1_voltage: BUCK1 DVS mode 1 voltage registers
  * @buck2_voltage: BUCK2 DVS mode 2 voltage registers
- * @buck1_set1: BUCK1 gpio pin 1 to set output voltage
- * @buck1_set2: BUCK1 gpio pin 2 to set output voltage
  * @buck1_default_idx: Default for BUCK1 gpio pin 1, 2
- * @buck2_set3: BUCK2 gpio pin to set output voltage
  * @buck2_default_idx: Default for BUCK2 gpio pin.
  * @wakeup: Allow to wake up from suspend
  * @rtc_delay: LP3974 RTC chip bug that requires delay after a register
@@ -91,10 +88,7 @@ struct max8998_platform_data {
 	bool				buck_voltage_lock;
 	int				buck1_voltage[4];
 	int				buck2_voltage[2];
-	int				buck1_set1;
-	int				buck1_set2;
 	int				buck1_default_idx;
-	int				buck2_set3;
 	int				buck2_default_idx;
 	bool				wakeup;
 	bool				rtc_delay;
diff --git a/include/linux/mfd/mc13xxx.h b/include/linux/mfd/mc13xxx.h
index f372926d5894..dd46fe424a80 100644
--- a/include/linux/mfd/mc13xxx.h
+++ b/include/linux/mfd/mc13xxx.h
@@ -31,12 +31,6 @@ int mc13xxx_adc_do_conversion(struct mc13xxx *mc13xxx,
 		unsigned int mode, unsigned int channel,
 		u8 ato, bool atox, unsigned int *sample);
 
-/* Deprecated calls */
-static inline int mc13xxx_irq_ack(struct mc13xxx *mc13xxx, int irq)
-{
-	return 0;
-}
-
 static inline int mc13xxx_irq_request_nounmask(struct mc13xxx *mc13xxx, int irq,
 					       irq_handler_t handler,
 					       const char *name, void *dev)
diff --git a/include/linux/mfd/mt6328/core.h b/include/linux/mfd/mt6328/core.h
new file mode 100644
index 000000000000..9a08aed72b9f
--- /dev/null
+++ b/include/linux/mfd/mt6328/core.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2015 MediaTek Inc.
+ * Copyright (c) 2022 Yassine Oudjana <y.oudjana@protonmail.com>
+ */
+
+#ifndef __MFD_MT6328_CORE_H__
+#define __MFD_MT6328_CORE_H__
+
+enum mt6328_irq_status_numbers {
+	MT6328_IRQ_STATUS_PWRKEY = 0,
+	MT6328_IRQ_STATUS_HOMEKEY,
+	MT6328_IRQ_STATUS_PWRKEY_R,
+	MT6328_IRQ_STATUS_HOMEKEY_R,
+	MT6328_IRQ_STATUS_THR_H,
+	MT6328_IRQ_STATUS_THR_L,
+	MT6328_IRQ_STATUS_BAT_H,
+	MT6328_IRQ_STATUS_BAT_L,
+	MT6328_IRQ_STATUS_RTC,
+	MT6328_IRQ_STATUS_AUDIO,
+	MT6328_IRQ_STATUS_ACCDET,
+	MT6328_IRQ_STATUS_ACCDET_EINT,
+	MT6328_IRQ_STATUS_ACCDET_NEGV,
+	MT6328_IRQ_STATUS_NI_LBAT_INT,
+	MT6328_IRQ_STATUS_VPROC_OC = 16,
+	MT6328_IRQ_STATUS_VSYS_OC,
+	MT6328_IRQ_STATUS_VLTE_OC,
+	MT6328_IRQ_STATUS_VCORE_OC,
+	MT6328_IRQ_STATUS_VPA_OC,
+	MT6328_IRQ_STATUS_LDO_OC,
+	MT6328_IRQ_STATUS_BAT2_H,
+	MT6328_IRQ_STATUS_BAT2_L,
+	MT6328_IRQ_STATUS_VISMPS0_H,
+	MT6328_IRQ_STATUS_VISMPS0_L,
+	MT6328_IRQ_STATUS_AUXADC_IMP,
+	MT6328_IRQ_STATUS_OV = 32,
+	MT6328_IRQ_STATUS_BVALID_DET,
+	MT6328_IRQ_STATUS_VBATON_HV,
+	MT6328_IRQ_STATUS_VBATON_UNDET,
+	MT6328_IRQ_STATUS_WATCHDOG,
+	MT6328_IRQ_STATUS_PCHR_CM_VDEC,
+	MT6328_IRQ_STATUS_CHRDET,
+	MT6328_IRQ_STATUS_PCHR_CM_VINC,
+	MT6328_IRQ_STATUS_FG_BAT_H,
+	MT6328_IRQ_STATUS_FG_BAT_L,
+	MT6328_IRQ_STATUS_FG_CUR_H,
+	MT6328_IRQ_STATUS_FG_CUR_L,
+	MT6328_IRQ_STATUS_FG_ZCV,
+	MT6328_IRQ_STATUS_SPKL_D,
+	MT6328_IRQ_STATUS_SPKL_AB,
+};
+
+#endif /* __MFD_MT6323_CORE_H__ */
diff --git a/include/linux/mfd/mt6328/registers.h b/include/linux/mfd/mt6328/registers.h
new file mode 100644
index 000000000000..8199aaea27b9
--- /dev/null
+++ b/include/linux/mfd/mt6328/registers.h
@@ -0,0 +1,822 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022 Yassine Oudjana <y.oudjana@protonmail.com>
+ */
+
+#ifndef __MFD_MT6328_REGISTERS_H__
+#define __MFD_MT6328_REGISTERS_H__
+
+/* PMIC Registers */
+#define MT6328_STRUP_CON0            0x0000
+#define MT6328_STRUP_CON2            0x0002
+#define MT6328_STRUP_CON3            0x0004
+#define MT6328_STRUP_CON4            0x0006
+#define MT6328_STRUP_CON5            0x0008
+#define MT6328_STRUP_CON6            0x000a
+#define MT6328_STRUP_CON7            0x000c
+#define MT6328_STRUP_CON8            0x000e
+#define MT6328_STRUP_CON9            0x0010
+#define MT6328_STRUP_CON10           0x0012
+#define MT6328_STRUP_CON11           0x0014
+#define MT6328_STRUP_CON12           0x0016
+#define MT6328_STRUP_CON13           0x0018
+#define MT6328_STRUP_CON14           0x001a
+#define MT6328_STRUP_CON15           0x001c
+#define MT6328_STRUP_CON16           0x001e
+#define MT6328_STRUP_CON17           0x0020
+#define MT6328_STRUP_CON18           0x0022
+#define MT6328_STRUP_CON19           0x0024
+#define MT6328_STRUP_CON20           0x0026
+#define MT6328_STRUP_CON21           0x0028
+#define MT6328_STRUP_CON22           0x002a
+#define MT6328_STRUP_CON23           0x002c
+#define MT6328_STRUP_CON24           0x002e
+#define MT6328_STRUP_CON25           0x0030
+#define MT6328_STRUP_CON26           0x0032
+#define MT6328_STRUP_CON27           0x0034
+#define MT6328_STRUP_CON28           0x0036
+#define MT6328_STRUP_CON29           0x0038
+#define MT6328_STRUP_CON30           0x003a
+#define MT6328_STRUP_CON31           0x003c
+#define MT6328_STRUP_CON32           0x003e
+#define MT6328_STRUP_ANA_CON0        0x0040
+#define MT6328_HWCID                 0x0200
+#define MT6328_SWCID                 0x0202
+#define MT6328_TOP_CON               0x0204
+#define MT6328_TEST_OUT              0x0206
+#define MT6328_TEST_CON0             0x0208
+#define MT6328_TEST_CON1             0x020a
+#define MT6328_TESTMODE_SW           0x020c
+#define MT6328_EN_STATUS0            0x020e
+#define MT6328_EN_STATUS1            0x0210
+#define MT6328_EN_STATUS2            0x0212
+#define MT6328_OCSTATUS0             0x0214
+#define MT6328_OCSTATUS1             0x0216
+#define MT6328_OCSTATUS2             0x0218
+#define MT6328_PGDEBSTATUS           0x021a
+#define MT6328_PGSTATUS              0x021c
+#define MT6328_THERMALSTATUS         0x021e
+#define MT6328_TOPSTATUS             0x0220
+#define MT6328_TDSEL_CON             0x0222
+#define MT6328_RDSEL_CON             0x0224
+#define MT6328_SMT_CON0              0x0226
+#define MT6328_SMT_CON1              0x0228
+#define MT6328_SMT_CON2              0x022a
+#define MT6328_DRV_CON0              0x022c
+#define MT6328_DRV_CON1              0x022e
+#define MT6328_DRV_CON2              0x0230
+#define MT6328_DRV_CON3              0x0232
+#define MT6328_TOP_STATUS            0x0234
+#define MT6328_TOP_STATUS_SET        0x0236
+#define MT6328_TOP_STATUS_CLR        0x0238
+#define MT6328_RGS_ANA_MON           0x023a
+#define MT6328_TOP_CKPDN_CON0        0x023c
+#define MT6328_TOP_CKPDN_CON0_SET    0x023e
+#define MT6328_TOP_CKPDN_CON0_CLR    0x0240
+#define MT6328_TOP_CKPDN_CON1        0x0242
+#define MT6328_TOP_CKPDN_CON1_SET    0x0244
+#define MT6328_TOP_CKPDN_CON1_CLR    0x0246
+#define MT6328_TOP_CKPDN_CON2        0x0248
+#define MT6328_TOP_CKPDN_CON2_SET    0x024a
+#define MT6328_TOP_CKPDN_CON2_CLR    0x024c
+#define MT6328_TOP_CKPDN_CON3        0x024e
+#define MT6328_TOP_CKPDN_CON3_SET    0x0250
+#define MT6328_TOP_CKPDN_CON3_CLR    0x0252
+#define MT6328_TOP_CKPDN_CON4        0x0254
+#define MT6328_TOP_CKPDN_CON4_SET    0x0256
+#define MT6328_TOP_CKPDN_CON4_CLR    0x0258
+#define MT6328_TOP_CKSEL_CON0        0x025a
+#define MT6328_TOP_CKSEL_CON0_SET    0x025c
+#define MT6328_TOP_CKSEL_CON0_CLR    0x025e
+#define MT6328_TOP_CKSEL_CON1        0x0260
+#define MT6328_TOP_CKSEL_CON1_SET    0x0262
+#define MT6328_TOP_CKSEL_CON1_CLR    0x0264
+#define MT6328_TOP_CKSEL_CON2        0x0266
+#define MT6328_TOP_CKSEL_CON2_SET    0x0268
+#define MT6328_TOP_CKSEL_CON2_CLR    0x026a
+#define MT6328_TOP_CKDIVSEL_CON0     0x026c
+#define MT6328_TOP_CKDIVSEL_CON0_SET 0x026e
+#define MT6328_TOP_CKDIVSEL_CON0_CLR 0x0270
+#define MT6328_TOP_CKDIVSEL_CON1     0x0272
+#define MT6328_TOP_CKDIVSEL_CON1_SET 0x0274
+#define MT6328_TOP_CKDIVSEL_CON1_CLR 0x0276
+#define MT6328_TOP_CKHWEN_CON0       0x0278
+#define MT6328_TOP_CKHWEN_CON0_SET   0x027a
+#define MT6328_TOP_CKHWEN_CON0_CLR   0x027c
+#define MT6328_TOP_CKHWEN_CON1       0x027e
+#define MT6328_TOP_CKHWEN_CON1_SET   0x0280
+#define MT6328_TOP_CKHWEN_CON1_CLR   0x0282
+#define MT6328_TOP_CKTST_CON0        0x0284
+#define MT6328_TOP_CKTST_CON1        0x0286
+#define MT6328_TOP_CKTST_CON2        0x0288
+#define MT6328_TOP_CLKSQ             0x028a
+#define MT6328_TOP_CLKSQ_SET         0x028c
+#define MT6328_TOP_CLKSQ_CLR         0x028e
+#define MT6328_TOP_CLKSQ_RTC         0x0290
+#define MT6328_TOP_CLKSQ_RTC_SET     0x0292
+#define MT6328_TOP_CLKSQ_RTC_CLR     0x0294
+#define MT6328_TOP_CLK_TRIM          0x0296
+#define MT6328_TOP_RST_CON0          0x0298
+#define MT6328_TOP_RST_CON0_SET      0x029a
+#define MT6328_TOP_RST_CON0_CLR      0x029c
+#define MT6328_TOP_RST_CON1          0x029e
+#define MT6328_TOP_RST_MISC          0x02a0
+#define MT6328_TOP_RST_MISC_SET      0x02a2
+#define MT6328_TOP_RST_MISC_CLR      0x02a4
+#define MT6328_TOP_RST_STATUS        0x02a6
+#define MT6328_TOP_RST_STATUS_SET    0x02a8
+#define MT6328_TOP_RST_STATUS_CLR    0x02aa
+#define MT6328_INT_CON0              0x02ac
+#define MT6328_INT_CON0_SET          0x02ae
+#define MT6328_INT_CON0_CLR          0x02b0
+#define MT6328_INT_CON1              0x02b2
+#define MT6328_INT_CON1_SET          0x02b4
+#define MT6328_INT_CON1_CLR          0x02b6
+#define MT6328_INT_CON2              0x02b8
+#define MT6328_INT_CON2_SET          0x02ba
+#define MT6328_INT_CON2_CLR          0x02bc
+#define MT6328_INT_MISC_CON          0x02be
+#define MT6328_INT_MISC_CON_SET      0x02c0
+#define MT6328_INT_MISC_CON_CLR      0x02c2
+#define MT6328_INT_STATUS0           0x02c4
+#define MT6328_INT_STATUS1           0x02c6
+#define MT6328_INT_STATUS2           0x02c8
+#define MT6328_OC_GEAR_0             0x02ca
+#define MT6328_FQMTR_CON0            0x02cc
+#define MT6328_FQMTR_CON1            0x02ce
+#define MT6328_FQMTR_CON2            0x02d0
+#define MT6328_RG_SPI_CON            0x02d2
+#define MT6328_DEW_DIO_EN            0x02d4
+#define MT6328_DEW_READ_TEST         0x02d6
+#define MT6328_DEW_WRITE_TEST        0x02d8
+#define MT6328_DEW_CRC_SWRST         0x02da
+#define MT6328_DEW_CRC_EN            0x02dc
+#define MT6328_DEW_CRC_VAL           0x02de
+#define MT6328_DEW_DBG_MON_SEL       0x02e0
+#define MT6328_DEW_CIPHER_KEY_SEL    0x02e2
+#define MT6328_DEW_CIPHER_IV_SEL     0x02e4
+#define MT6328_DEW_CIPHER_EN         0x02e6
+#define MT6328_DEW_CIPHER_RDY        0x02e8
+#define MT6328_DEW_CIPHER_MODE       0x02ea
+#define MT6328_DEW_CIPHER_SWRST      0x02ec
+#define MT6328_DEW_RDDMY_NO          0x02ee
+#define MT6328_INT_TYPE_CON0         0x02f0
+#define MT6328_INT_TYPE_CON0_SET     0x02f2
+#define MT6328_INT_TYPE_CON0_CLR     0x02f4
+#define MT6328_INT_TYPE_CON1         0x02f6
+#define MT6328_INT_TYPE_CON1_SET     0x02f8
+#define MT6328_INT_TYPE_CON1_CLR     0x02fa
+#define MT6328_INT_TYPE_CON2         0x02fc
+#define MT6328_INT_TYPE_CON2_SET     0x02fe
+#define MT6328_INT_TYPE_CON2_CLR     0x0300
+#define MT6328_INT_STA               0x0302
+#define MT6328_BUCK_ALL_CON0         0x0400
+#define MT6328_BUCK_ALL_CON1         0x0402
+#define MT6328_BUCK_ALL_CON2         0x0404
+#define MT6328_BUCK_ALL_CON3         0x0406
+#define MT6328_BUCK_ALL_CON4         0x0408
+#define MT6328_BUCK_ALL_CON5         0x040a
+#define MT6328_BUCK_ALL_CON6         0x040c
+#define MT6328_BUCK_ALL_CON9         0x040e
+#define MT6328_BUCK_ALL_CON12        0x0410
+#define MT6328_BUCK_ALL_CON13        0x0412
+#define MT6328_BUCK_ALL_CON14        0x0414
+#define MT6328_BUCK_ALL_CON16        0x0416
+#define MT6328_BUCK_ALL_CON18        0x0418
+#define MT6328_BUCK_ALL_CON19        0x041a
+#define MT6328_BUCK_ALL_CON20        0x041c
+#define MT6328_BUCK_ALL_CON21        0x041e
+#define MT6328_BUCK_ALL_CON22        0x0420
+#define MT6328_BUCK_ALL_CON23        0x0422
+#define MT6328_BUCK_ALL_CON24        0x0424
+#define MT6328_BUCK_ALL_CON25        0x0426
+#define MT6328_BUCK_ALL_CON26        0x0428
+#define MT6328_BUCK_ALL_CON27        0x042a
+#define MT6328_BUCK_ALL_CON28        0x042c
+#define MT6328_SMPS_TOP_ANA_CON0     0x042e
+#define MT6328_SMPS_TOP_ANA_CON1     0x0430
+#define MT6328_SMPS_TOP_ANA_CON2     0x0432
+#define MT6328_SMPS_TOP_ANA_CON3     0x0434
+#define MT6328_SMPS_TOP_ANA_CON4     0x0436
+#define MT6328_SMPS_TOP_ANA_CON5     0x0438
+#define MT6328_SMPS_TOP_ANA_CON6     0x043a
+#define MT6328_SMPS_TOP_ANA_CON7     0x043c
+#define MT6328_SMPS_TOP_ANA_CON8     0x043e
+#define MT6328_VCORE_ANA_CON0        0x0440
+#define MT6328_VCORE_ANA_CON1        0x0442
+#define MT6328_VCORE_ANA_CON2        0x0444
+#define MT6328_VCORE_ANA_CON3        0x0446
+#define MT6328_VCORE_ANA_CON4        0x0448
+#define MT6328_VSYS22_ANA_CON0       0x044a
+#define MT6328_VSYS22_ANA_CON1       0x044c
+#define MT6328_VSYS22_ANA_CON2       0x044e
+#define MT6328_VSYS22_ANA_CON3       0x0450
+#define MT6328_VSYS22_ANA_CON4       0x0452
+#define MT6328_VPROC_ANA_CON0        0x0454
+#define MT6328_VPROC_ANA_CON1        0x0456
+#define MT6328_VPROC_ANA_CON2        0x0458
+#define MT6328_VPROC_ANA_CON3        0x045a
+#define MT6328_VPROC_ANA_CON4        0x045c
+#define MT6328_OSC32_ANA_CON0        0x045e
+#define MT6328_OSC32_ANA_CON1        0x0460
+#define MT6328_VPA_ANA_CON0          0x0462
+#define MT6328_VPA_ANA_CON1          0x0464
+#define MT6328_VPA_ANA_CON2          0x0466
+#define MT6328_VPA_ANA_CON3          0x0468
+#define MT6328_VLTE_ANA_CON0         0x046a
+#define MT6328_VLTE_ANA_CON1         0x046c
+#define MT6328_VLTE_ANA_CON2         0x046e
+#define MT6328_VLTE_ANA_CON3         0x0470
+#define MT6328_VLTE_ANA_CON4         0x0472
+#define MT6328_VPROC_CON0            0x0474
+#define MT6328_VPROC_CON1            0x0476
+#define MT6328_VPROC_CON2            0x0478
+#define MT6328_VPROC_CON3            0x047a
+#define MT6328_VPROC_CON4            0x047c
+#define MT6328_VPROC_CON5            0x047e
+#define MT6328_VPROC_CON6            0x0480
+#define MT6328_VPROC_CON7            0x0482
+#define MT6328_VPROC_CON8            0x0484
+#define MT6328_VPROC_CON9            0x0486
+#define MT6328_VPROC_CON10           0x0488
+#define MT6328_VPROC_CON11           0x048a
+#define MT6328_VPROC_CON12           0x048c
+#define MT6328_VPROC_CON13           0x048e
+#define MT6328_VPROC_CON14           0x0490
+#define MT6328_VPROC_CON15           0x0492
+#define MT6328_VPROC_CON16           0x0494
+#define MT6328_VPROC_CON17           0x0496
+#define MT6328_VPROC_CON18           0x0498
+#define MT6328_VPROC_CON19           0x049a
+#define MT6328_VSRAM_CON0            0x049c
+#define MT6328_VSRAM_CON1            0x049e
+#define MT6328_VSRAM_CON2            0x04a0
+#define MT6328_VSRAM_CON3            0x04a2
+#define MT6328_VSRAM_CON4            0x04a4
+#define MT6328_VSRAM_CON5            0x04a6
+#define MT6328_VSRAM_CON6            0x04a8
+#define MT6328_VSRAM_CON7            0x04aa
+#define MT6328_VSRAM_CON8            0x04ac
+#define MT6328_VSRAM_CON9            0x04ae
+#define MT6328_VSRAM_CON10           0x04b0
+#define MT6328_VSRAM_CON11           0x04b2
+#define MT6328_VSRAM_CON12           0x04b4
+#define MT6328_VSRAM_CON13           0x04b6
+#define MT6328_VSRAM_CON14           0x04b8
+#define MT6328_VSRAM_CON15           0x04ba
+#define MT6328_VSRAM_CON16           0x04bc
+#define MT6328_VSRAM_CON17           0x04be
+#define MT6328_VSRAM_CON18           0x04c0
+#define MT6328_VSRAM_CON19           0x04c2
+#define MT6328_VLTE_CON0             0x04c4
+#define MT6328_VLTE_CON1             0x04c6
+#define MT6328_VLTE_CON2             0x04c8
+#define MT6328_VLTE_CON3             0x04ca
+#define MT6328_VLTE_CON4             0x04cc
+#define MT6328_VLTE_CON5             0x04ce
+#define MT6328_VLTE_CON6             0x04d0
+#define MT6328_VLTE_CON7             0x04d2
+#define MT6328_VLTE_CON8             0x04d4
+#define MT6328_VLTE_CON9             0x04d6
+#define MT6328_VLTE_CON10            0x04d8
+#define MT6328_VLTE_CON11            0x04da
+#define MT6328_VLTE_CON12            0x04dc
+#define MT6328_VLTE_CON13            0x04de
+#define MT6328_VLTE_CON14            0x04e0
+#define MT6328_VLTE_CON15            0x04e2
+#define MT6328_VLTE_CON16            0x04e4
+#define MT6328_VLTE_CON17            0x04e6
+#define MT6328_VLTE_CON18            0x04e8
+#define MT6328_VLTE_CON19            0x04ea
+#define MT6328_VCORE1_CON0           0x0600
+#define MT6328_VCORE1_CON1           0x0602
+#define MT6328_VCORE1_CON2           0x0604
+#define MT6328_VCORE1_CON3           0x0606
+#define MT6328_VCORE1_CON4           0x0608
+#define MT6328_VCORE1_CON5           0x060a
+#define MT6328_VCORE1_CON6           0x060c
+#define MT6328_VCORE1_CON7           0x060e
+#define MT6328_VCORE1_CON8           0x0610
+#define MT6328_VCORE1_CON9           0x0612
+#define MT6328_VCORE1_CON10          0x0614
+#define MT6328_VCORE1_CON11          0x0616
+#define MT6328_VCORE1_CON12          0x0618
+#define MT6328_VCORE1_CON13          0x061a
+#define MT6328_VCORE1_CON14          0x061c
+#define MT6328_VCORE1_CON15          0x061e
+#define MT6328_VCORE1_CON16          0x0620
+#define MT6328_VCORE1_CON17          0x0622
+#define MT6328_VCORE1_CON18          0x0624
+#define MT6328_VCORE1_CON19          0x0626
+#define MT6328_VSYS22_CON0           0x0628
+#define MT6328_VSYS22_CON1           0x062a
+#define MT6328_VSYS22_CON2           0x062c
+#define MT6328_VSYS22_CON3           0x062e
+#define MT6328_VSYS22_CON4           0x0630
+#define MT6328_VSYS22_CON5           0x0632
+#define MT6328_VSYS22_CON6           0x0634
+#define MT6328_VSYS22_CON7           0x0636
+#define MT6328_VSYS22_CON8           0x0638
+#define MT6328_VSYS22_CON9           0x063a
+#define MT6328_VSYS22_CON10          0x063c
+#define MT6328_VSYS22_CON11          0x063e
+#define MT6328_VSYS22_CON12          0x0640
+#define MT6328_VSYS22_CON13          0x0642
+#define MT6328_VSYS22_CON14          0x0644
+#define MT6328_VSYS22_CON15          0x0646
+#define MT6328_VSYS22_CON16          0x0648
+#define MT6328_VSYS22_CON17          0x064a
+#define MT6328_VSYS22_CON18          0x064c
+#define MT6328_VSYS22_CON19          0x064e
+#define MT6328_VPA_CON0              0x0650
+#define MT6328_VPA_CON1              0x0652
+#define MT6328_VPA_CON2              0x0654
+#define MT6328_VPA_CON3              0x0656
+#define MT6328_VPA_CON4              0x0658
+#define MT6328_VPA_CON5              0x065a
+#define MT6328_VPA_CON6              0x065c
+#define MT6328_VPA_CON7              0x065e
+#define MT6328_VPA_CON8              0x0660
+#define MT6328_VPA_CON9              0x0662
+#define MT6328_VPA_CON10             0x0664
+#define MT6328_VPA_CON11             0x0666
+#define MT6328_VPA_CON12             0x0668
+#define MT6328_VPA_CON13             0x066a
+#define MT6328_VPA_CON14             0x066c
+#define MT6328_VPA_CON15             0x066e
+#define MT6328_VPA_CON16             0x0670
+#define MT6328_VPA_CON17             0x0672
+#define MT6328_VPA_CON18             0x0674
+#define MT6328_VPA_CON19             0x0676
+#define MT6328_VPA_CON20             0x0678
+#define MT6328_VPA_CON21             0x067a
+#define MT6328_VPA_CON22             0x067c
+#define MT6328_VPA_CON23             0x067e
+#define MT6328_VPA_CON24             0x0680
+#define MT6328_BUCK_K_CON0           0x0682
+#define MT6328_BUCK_K_CON1           0x0684
+#define MT6328_BUCK_K_CON2           0x0686
+#define MT6328_BUCK_K_CON3           0x0688
+#define MT6328_ZCD_CON0              0x0800
+#define MT6328_ZCD_CON1              0x0802
+#define MT6328_ZCD_CON2              0x0804
+#define MT6328_ZCD_CON3              0x0806
+#define MT6328_ZCD_CON4              0x0808
+#define MT6328_ZCD_CON5              0x080a
+#define MT6328_ISINK0_CON0           0x080c
+#define MT6328_ISINK0_CON1           0x080e
+#define MT6328_ISINK0_CON2           0x0810
+#define MT6328_ISINK0_CON3           0x0812
+#define MT6328_ISINK1_CON0           0x0814
+#define MT6328_ISINK1_CON1           0x0816
+#define MT6328_ISINK1_CON2           0x0818
+#define MT6328_ISINK1_CON3           0x081a
+#define MT6328_ISINK2_CON1           0x081c
+#define MT6328_ISINK3_CON1           0x081e
+#define MT6328_ISINK_ANA0            0x0820
+#define MT6328_ISINK_ANA1            0x0822
+#define MT6328_ISINK_PHASE_DLY       0x0824
+#define MT6328_ISINK_SFSTR           0x0826
+#define MT6328_ISINK_EN_CTRL         0x0828
+#define MT6328_ISINK_MODE_CTRL       0x082a
+#define MT6328_VTCXO_0_CON0          0x0a00
+#define MT6328_VTCXO_1_CON0          0x0a02
+#define MT6328_VAUD28_CON0           0x0a04
+#define MT6328_VAUX18_CON0           0x0a06
+#define MT6328_VRF18_0_CON0          0x0a08
+#define MT6328_VRF18_0_CON1          0x0a0a
+#define MT6328_VCAMA_CON0            0x0a0c
+#define MT6328_VCN28_CON0            0x0a0e
+#define MT6328_VCN33_CON0            0x0a10
+#define MT6328_VCN33_CON1            0x0a12
+#define MT6328_VCN33_CON2            0x0a14
+#define MT6328_VRF18_1_CON0          0x0a16
+#define MT6328_VRF18_1_CON1          0x0a18
+#define MT6328_VUSB33_CON0           0x0a1a
+#define MT6328_VMCH_CON0             0x0a1c
+#define MT6328_VMCH_CON1             0x0a1e
+#define MT6328_VMC_CON0              0x0a20
+#define MT6328_VMC_CON1              0x0a22
+#define MT6328_VEMC_3V3_CON0         0x0a24
+#define MT6328_VEMC_3V3_CON1         0x0a26
+#define MT6328_VIO28_CON0            0x0a28
+#define MT6328_VCAMAF_CON0           0x0a2a
+#define MT6328_VGP1_CON0             0x0a2c
+#define MT6328_VGP1_CON1             0x0a2e
+#define MT6328_VEFUSE_CON0           0x0a30
+#define MT6328_VSIM1_CON0            0x0a32
+#define MT6328_VSIM2_CON0            0x0a34
+#define MT6328_VIO18_CON0            0x0a36
+#define MT6328_VIBR_CON0             0x0a38
+#define MT6328_VCN18_CON0            0x0a3a
+#define MT6328_VCAM_CON0             0x0a3c
+#define MT6328_VCAMIO_CON0           0x0a3e
+#define MT6328_LDO_VSRAM_CON0        0x0a40
+#define MT6328_LDO_VSRAM_CON1        0x0a42
+#define MT6328_VTREF_CON0            0x0a44
+#define MT6328_VM_CON0               0x0a46
+#define MT6328_VM_CON1               0x0a48
+#define MT6328_VRTC_CON0             0x0a4a
+#define MT6328_LDO_OCFB0             0x0a4c
+#define MT6328_ALDO_ANA_CON0         0x0a4e
+#define MT6328_ADLDO_ANA_CON1        0x0a50
+#define MT6328_ADLDO_ANA_CON2        0x0a52
+#define MT6328_ADLDO_ANA_CON3        0x0a54
+#define MT6328_ADLDO_ANA_CON4        0x0a56
+#define MT6328_ADLDO_ANA_CON5        0x0a58
+#define MT6328_ADLDO_ANA_CON6        0x0a5a
+#define MT6328_ADLDO_ANA_CON7        0x0a5c
+#define MT6328_ADLDO_ANA_CON8        0x0a5e
+#define MT6328_ADLDO_ANA_CON9        0x0a60
+#define MT6328_ADLDO_ANA_CON10       0x0a62
+#define MT6328_ADLDO_ANA_CON11       0x0a64
+#define MT6328_ADLDO_ANA_CON12       0x0a66
+#define MT6328_ADLDO_ANA_CON13       0x0a68
+#define MT6328_DLDO_ANA_CON0         0x0a6a
+#define MT6328_DLDO_ANA_CON1         0x0a6c
+#define MT6328_DLDO_ANA_CON2         0x0a6e
+#define MT6328_DLDO_ANA_CON3         0x0a70
+#define MT6328_DLDO_ANA_CON4         0x0a72
+#define MT6328_DLDO_ANA_CON5         0x0a74
+#define MT6328_SLDO_ANA_CON0         0x0a76
+#define MT6328_SLDO_ANA_CON1         0x0a78
+#define MT6328_SLDO_ANA_CON2         0x0a7a
+#define MT6328_SLDO_ANA_CON3         0x0a7c
+#define MT6328_SLDO_ANA_CON4         0x0a7e
+#define MT6328_SLDO_ANA_CON5         0x0a80
+#define MT6328_SLDO_ANA_CON6         0x0a82
+#define MT6328_SLDO_ANA_CON7         0x0a84
+#define MT6328_SLDO_ANA_CON8         0x0a86
+#define MT6328_SLDO_ANA_CON9         0x0a88
+#define MT6328_SLDO_ANA_CON10        0x0a8a
+#define MT6328_LDO_RSV_CON0          0x0a8c
+#define MT6328_LDO_RSV_CON1          0x0a8e
+#define MT6328_SPK_CON0              0x0a90
+#define MT6328_SPK_CON1              0x0a92
+#define MT6328_SPK_CON2              0x0a94
+#define MT6328_SPK_CON3              0x0a96
+#define MT6328_SPK_CON4              0x0a98
+#define MT6328_SPK_CON5              0x0a9a
+#define MT6328_SPK_CON6              0x0a9c
+#define MT6328_SPK_CON7              0x0a9e
+#define MT6328_SPK_CON8              0x0aa0
+#define MT6328_SPK_CON9              0x0aa2
+#define MT6328_SPK_CON10             0x0aa4
+#define MT6328_SPK_CON11             0x0aa6
+#define MT6328_SPK_CON12             0x0aa8
+#define MT6328_SPK_CON13             0x0aaa
+#define MT6328_SPK_CON14             0x0aac
+#define MT6328_SPK_CON15             0x0aae
+#define MT6328_SPK_CON16             0x0ab0
+#define MT6328_SPK_ANA_CON0          0x0ab2
+#define MT6328_SPK_ANA_CON1          0x0ab4
+#define MT6328_SPK_ANA_CON3          0x0ab6
+#define MT6328_OTP_CON0              0x0c00
+#define MT6328_OTP_CON1              0x0c02
+#define MT6328_OTP_CON2              0x0c04
+#define MT6328_OTP_CON3              0x0c06
+#define MT6328_OTP_CON4              0x0c08
+#define MT6328_OTP_CON5              0x0c0a
+#define MT6328_OTP_CON6              0x0c0c
+#define MT6328_OTP_CON7              0x0c0e
+#define MT6328_OTP_CON8              0x0c10
+#define MT6328_OTP_CON9              0x0c12
+#define MT6328_OTP_CON10             0x0c14
+#define MT6328_OTP_CON11             0x0c16
+#define MT6328_OTP_CON12             0x0c18
+#define MT6328_OTP_CON13             0x0c1a
+#define MT6328_OTP_CON14             0x0c1c
+#define MT6328_OTP_DOUT_0_15         0x0c1e
+#define MT6328_OTP_DOUT_16_31        0x0c20
+#define MT6328_OTP_DOUT_32_47        0x0c22
+#define MT6328_OTP_DOUT_48_63        0x0c24
+#define MT6328_OTP_DOUT_64_79        0x0c26
+#define MT6328_OTP_DOUT_80_95        0x0c28
+#define MT6328_OTP_DOUT_96_111       0x0c2a
+#define MT6328_OTP_DOUT_112_127      0x0c2c
+#define MT6328_OTP_DOUT_128_143      0x0c2e
+#define MT6328_OTP_DOUT_144_159      0x0c30
+#define MT6328_OTP_DOUT_160_175      0x0c32
+#define MT6328_OTP_DOUT_176_191      0x0c34
+#define MT6328_OTP_DOUT_192_207      0x0c36
+#define MT6328_OTP_DOUT_208_223      0x0c38
+#define MT6328_OTP_DOUT_224_239      0x0c3a
+#define MT6328_OTP_DOUT_240_255      0x0c3c
+#define MT6328_OTP_DOUT_256_271      0x0c3e
+#define MT6328_OTP_DOUT_272_287      0x0c40
+#define MT6328_OTP_DOUT_288_303      0x0c42
+#define MT6328_OTP_DOUT_304_319      0x0c44
+#define MT6328_OTP_DOUT_320_335      0x0c46
+#define MT6328_OTP_DOUT_336_351      0x0c48
+#define MT6328_OTP_DOUT_352_367      0x0c4a
+#define MT6328_OTP_DOUT_368_383      0x0c4c
+#define MT6328_OTP_DOUT_384_399      0x0c4e
+#define MT6328_OTP_DOUT_400_415      0x0c50
+#define MT6328_OTP_DOUT_416_431      0x0c52
+#define MT6328_OTP_DOUT_432_447      0x0c54
+#define MT6328_OTP_DOUT_448_463      0x0c56
+#define MT6328_OTP_DOUT_464_479      0x0c58
+#define MT6328_OTP_DOUT_480_495      0x0c5a
+#define MT6328_OTP_DOUT_496_511      0x0c5c
+#define MT6328_OTP_VAL_0_15          0x0c5e
+#define MT6328_OTP_VAL_16_31         0x0c60
+#define MT6328_OTP_VAL_32_47         0x0c62
+#define MT6328_OTP_VAL_48_63         0x0c64
+#define MT6328_OTP_VAL_64_79         0x0c66
+#define MT6328_OTP_VAL_80_95         0x0c68
+#define MT6328_OTP_VAL_96_111        0x0c6a
+#define MT6328_OTP_VAL_112_127       0x0c6c
+#define MT6328_OTP_VAL_128_143       0x0c6e
+#define MT6328_OTP_VAL_144_159       0x0c70
+#define MT6328_OTP_VAL_160_175       0x0c72
+#define MT6328_OTP_VAL_176_191       0x0c74
+#define MT6328_OTP_VAL_192_207       0x0c76
+#define MT6328_OTP_VAL_208_223       0x0c78
+#define MT6328_OTP_VAL_224_239       0x0c7a
+#define MT6328_OTP_VAL_240_255       0x0c7c
+#define MT6328_OTP_VAL_256_271       0x0c7e
+#define MT6328_OTP_VAL_272_287       0x0c80
+#define MT6328_OTP_VAL_288_303       0x0c82
+#define MT6328_OTP_VAL_304_319       0x0c84
+#define MT6328_OTP_VAL_320_335       0x0c86
+#define MT6328_OTP_VAL_336_351       0x0c88
+#define MT6328_OTP_VAL_352_367       0x0c8a
+#define MT6328_OTP_VAL_368_383       0x0c8c
+#define MT6328_OTP_VAL_384_399       0x0c8e
+#define MT6328_OTP_VAL_400_415       0x0c90
+#define MT6328_OTP_VAL_416_431       0x0c92
+#define MT6328_OTP_VAL_432_447       0x0c94
+#define MT6328_OTP_VAL_448_463       0x0c96
+#define MT6328_OTP_VAL_464_479       0x0c98
+#define MT6328_OTP_VAL_480_495       0x0c9a
+#define MT6328_OTP_VAL_496_511       0x0c9c
+#define MT6328_RTC_MIX_CON0          0x0c9e
+#define MT6328_RTC_MIX_CON1          0x0ca0
+#define MT6328_RTC_MIX_CON2          0x0ca2
+#define MT6328_FGADC_CON0            0x0ca4
+#define MT6328_FGADC_CON1            0x0ca6
+#define MT6328_FGADC_CON2            0x0ca8
+#define MT6328_FGADC_CON3            0x0caa
+#define MT6328_FGADC_CON4            0x0cac
+#define MT6328_FGADC_CON5            0x0cae
+#define MT6328_FGADC_CON6            0x0cb0
+#define MT6328_FGADC_CON7            0x0cb2
+#define MT6328_FGADC_CON8            0x0cb4
+#define MT6328_FGADC_CON9            0x0cb6
+#define MT6328_FGADC_CON10           0x0cb8
+#define MT6328_FGADC_CON11           0x0cba
+#define MT6328_FGADC_CON12           0x0cbc
+#define MT6328_FGADC_CON13           0x0cbe
+#define MT6328_FGADC_CON14           0x0cc0
+#define MT6328_FGADC_CON15           0x0cc2
+#define MT6328_FGADC_CON16           0x0cc4
+#define MT6328_FGADC_CON17           0x0cc6
+#define MT6328_FGADC_CON18           0x0cc8
+#define MT6328_FGADC_CON19           0x0cca
+#define MT6328_FGADC_CON20           0x0ccc
+#define MT6328_FGADC_CON21           0x0cce
+#define MT6328_FGADC_CON22           0x0cd0
+#define MT6328_FGADC_CON23           0x0cd2
+#define MT6328_FGADC_CON24           0x0cd4
+#define MT6328_FGADC_CON25           0x0cd6
+#define MT6328_FGADC_CON26           0x0cd8
+#define MT6328_FGADC_CON27           0x0cda
+#define MT6328_AUDDEC_ANA_CON0       0x0cdc
+#define MT6328_AUDDEC_ANA_CON1       0x0cde
+#define MT6328_AUDDEC_ANA_CON2       0x0ce0
+#define MT6328_AUDDEC_ANA_CON3       0x0ce2
+#define MT6328_AUDDEC_ANA_CON4       0x0ce4
+#define MT6328_AUDDEC_ANA_CON5       0x0ce6
+#define MT6328_AUDDEC_ANA_CON6       0x0ce8
+#define MT6328_AUDDEC_ANA_CON7       0x0cea
+#define MT6328_AUDDEC_ANA_CON8       0x0cec
+#define MT6328_AUDENC_ANA_CON0       0x0cee
+#define MT6328_AUDENC_ANA_CON1       0x0cf0
+#define MT6328_AUDENC_ANA_CON2       0x0cf2
+#define MT6328_AUDENC_ANA_CON3       0x0cf4
+#define MT6328_AUDENC_ANA_CON4       0x0cf6
+#define MT6328_AUDENC_ANA_CON5       0x0cf8
+#define MT6328_AUDENC_ANA_CON6       0x0cfa
+#define MT6328_AUDENC_ANA_CON7       0x0cfc
+#define MT6328_AUDENC_ANA_CON8       0x0cfe
+#define MT6328_AUDENC_ANA_CON9       0x0d00
+#define MT6328_AUDENC_ANA_CON10      0x0d02
+#define MT6328_AUDNCP_CLKDIV_CON0    0x0d04
+#define MT6328_AUDNCP_CLKDIV_CON1    0x0d06
+#define MT6328_AUDNCP_CLKDIV_CON2    0x0d08
+#define MT6328_AUDNCP_CLKDIV_CON3    0x0d0a
+#define MT6328_AUDNCP_CLKDIV_CON4    0x0d0c
+#define MT6328_AUXADC_ADC0           0x0e00
+#define MT6328_AUXADC_ADC1           0x0e02
+#define MT6328_AUXADC_ADC2           0x0e04
+#define MT6328_AUXADC_ADC3           0x0e06
+#define MT6328_AUXADC_ADC4           0x0e08
+#define MT6328_AUXADC_ADC5           0x0e0a
+#define MT6328_AUXADC_ADC6           0x0e0c
+#define MT6328_AUXADC_ADC7           0x0e0e
+#define MT6328_AUXADC_ADC8           0x0e10
+#define MT6328_AUXADC_ADC9           0x0e12
+#define MT6328_AUXADC_ADC10          0x0e14
+#define MT6328_AUXADC_ADC11          0x0e16
+#define MT6328_AUXADC_ADC12          0x0e18
+#define MT6328_AUXADC_ADC13          0x0e1a
+#define MT6328_AUXADC_ADC14          0x0e1c
+#define MT6328_AUXADC_ADC15          0x0e1e
+#define MT6328_AUXADC_ADC16          0x0e20
+#define MT6328_AUXADC_ADC17          0x0e22
+#define MT6328_AUXADC_ADC18          0x0e24
+#define MT6328_AUXADC_ADC19          0x0e26
+#define MT6328_AUXADC_ADC20          0x0e28
+#define MT6328_AUXADC_ADC21          0x0e2a
+#define MT6328_AUXADC_ADC22          0x0e2c
+#define MT6328_AUXADC_ADC23          0x0e2e
+#define MT6328_AUXADC_ADC24          0x0e30
+#define MT6328_AUXADC_ADC25          0x0e32
+#define MT6328_AUXADC_ADC26          0x0e34
+#define MT6328_AUXADC_ADC27          0x0e36
+#define MT6328_AUXADC_ADC28          0x0e38
+#define MT6328_AUXADC_ADC29          0x0e3a
+#define MT6328_AUXADC_ADC30          0x0e3c
+#define MT6328_AUXADC_ADC31          0x0e3e
+#define MT6328_AUXADC_ADC32          0x0e40
+#define MT6328_AUXADC_ADC33          0x0e42
+#define MT6328_AUXADC_BUF0           0x0e44
+#define MT6328_AUXADC_BUF1           0x0e46
+#define MT6328_AUXADC_BUF2           0x0e48
+#define MT6328_AUXADC_BUF3           0x0e4a
+#define MT6328_AUXADC_BUF4           0x0e4c
+#define MT6328_AUXADC_BUF5           0x0e4e
+#define MT6328_AUXADC_BUF6           0x0e50
+#define MT6328_AUXADC_BUF7           0x0e52
+#define MT6328_AUXADC_BUF8           0x0e54
+#define MT6328_AUXADC_BUF9           0x0e56
+#define MT6328_AUXADC_BUF10          0x0e58
+#define MT6328_AUXADC_BUF11          0x0e5a
+#define MT6328_AUXADC_BUF12          0x0e5c
+#define MT6328_AUXADC_BUF13          0x0e5e
+#define MT6328_AUXADC_BUF14          0x0e60
+#define MT6328_AUXADC_BUF15          0x0e62
+#define MT6328_AUXADC_BUF16          0x0e64
+#define MT6328_AUXADC_BUF17          0x0e66
+#define MT6328_AUXADC_BUF18          0x0e68
+#define MT6328_AUXADC_BUF19          0x0e6a
+#define MT6328_AUXADC_BUF20          0x0e6c
+#define MT6328_AUXADC_BUF21          0x0e6e
+#define MT6328_AUXADC_BUF22          0x0e70
+#define MT6328_AUXADC_BUF23          0x0e72
+#define MT6328_AUXADC_BUF24          0x0e74
+#define MT6328_AUXADC_BUF25          0x0e76
+#define MT6328_AUXADC_BUF26          0x0e78
+#define MT6328_AUXADC_BUF27          0x0e7a
+#define MT6328_AUXADC_BUF28          0x0e7c
+#define MT6328_AUXADC_BUF29          0x0e7e
+#define MT6328_AUXADC_BUF30          0x0e80
+#define MT6328_AUXADC_BUF31          0x0e82
+#define MT6328_AUXADC_STA0           0x0e84
+#define MT6328_AUXADC_STA1           0x0e86
+#define MT6328_AUXADC_RQST0          0x0e88
+#define MT6328_AUXADC_RQST0_SET      0x0e8a
+#define MT6328_AUXADC_RQST0_CLR      0x0e8c
+#define MT6328_AUXADC_RQST1          0x0e8e
+#define MT6328_AUXADC_RQST1_SET      0x0e90
+#define MT6328_AUXADC_RQST1_CLR      0x0e92
+#define MT6328_AUXADC_CON0           0x0e94
+#define MT6328_AUXADC_CON0_SET       0x0e96
+#define MT6328_AUXADC_CON0_CLR       0x0e98
+#define MT6328_AUXADC_CON1           0x0e9a
+#define MT6328_AUXADC_CON2           0x0e9c
+#define MT6328_AUXADC_CON3           0x0e9e
+#define MT6328_AUXADC_CON4           0x0ea0
+#define MT6328_AUXADC_CON5           0x0ea2
+#define MT6328_AUXADC_CON6           0x0ea4
+#define MT6328_AUXADC_CON7           0x0ea6
+#define MT6328_AUXADC_CON8           0x0ea8
+#define MT6328_AUXADC_CON9           0x0eaa
+#define MT6328_AUXADC_CON10          0x0eac
+#define MT6328_AUXADC_CON11          0x0eae
+#define MT6328_AUXADC_CON12          0x0eb0
+#define MT6328_AUXADC_CON13          0x0eb2
+#define MT6328_AUXADC_CON14          0x0eb4
+#define MT6328_AUXADC_CON15          0x0eb6
+#define MT6328_AUXADC_CON16          0x0eb8
+#define MT6328_AUXADC_AUTORPT0       0x0eba
+#define MT6328_AUXADC_LBAT0          0x0ebc
+#define MT6328_AUXADC_LBAT1          0x0ebe
+#define MT6328_AUXADC_LBAT2          0x0ec0
+#define MT6328_AUXADC_LBAT3          0x0ec2
+#define MT6328_AUXADC_LBAT4          0x0ec4
+#define MT6328_AUXADC_LBAT5          0x0ec6
+#define MT6328_AUXADC_LBAT6          0x0ec8
+#define MT6328_AUXADC_ACCDET         0x0eca
+#define MT6328_AUXADC_THR0           0x0ecc
+#define MT6328_AUXADC_THR1           0x0ece
+#define MT6328_AUXADC_THR2           0x0ed0
+#define MT6328_AUXADC_THR3           0x0ed2
+#define MT6328_AUXADC_THR4           0x0ed4
+#define MT6328_AUXADC_THR5           0x0ed6
+#define MT6328_AUXADC_THR6           0x0ed8
+#define MT6328_AUXADC_EFUSE0         0x0eda
+#define MT6328_AUXADC_EFUSE1         0x0edc
+#define MT6328_AUXADC_EFUSE2         0x0ede
+#define MT6328_AUXADC_EFUSE3         0x0ee0
+#define MT6328_AUXADC_EFUSE4         0x0ee2
+#define MT6328_AUXADC_EFUSE5         0x0ee4
+#define MT6328_AUXADC_DBG0           0x0ee6
+#define MT6328_AUXADC_IMP0           0x0ee8
+#define MT6328_AUXADC_IMP1           0x0eea
+#define MT6328_AUXADC_VISMPS0_1      0x0eec
+#define MT6328_AUXADC_VISMPS0_2      0x0eee
+#define MT6328_AUXADC_VISMPS0_3      0x0ef0
+#define MT6328_AUXADC_VISMPS0_4      0x0ef2
+#define MT6328_AUXADC_VISMPS0_5      0x0ef4
+#define MT6328_AUXADC_VISMPS0_6      0x0ef6
+#define MT6328_AUXADC_VISMPS0_7      0x0ef8
+#define MT6328_AUXADC_LBAT2_1        0x0efa
+#define MT6328_AUXADC_LBAT2_2        0x0efc
+#define MT6328_AUXADC_LBAT2_3        0x0efe
+#define MT6328_AUXADC_LBAT2_4        0x0f00
+#define MT6328_AUXADC_LBAT2_5        0x0f02
+#define MT6328_AUXADC_LBAT2_6        0x0f04
+#define MT6328_AUXADC_LBAT2_7        0x0f06
+#define MT6328_AUXADC_MDBG_0         0x0f08
+#define MT6328_AUXADC_MDBG_1         0x0f0a
+#define MT6328_AUXADC_MDBG_2         0x0f0c
+#define MT6328_AUXADC_MDRT_0         0x0f0e
+#define MT6328_AUXADC_MDRT_1         0x0f10
+#define MT6328_AUXADC_MDRT_2         0x0f12
+#define MT6328_ACCDET_CON0           0x0f14
+#define MT6328_ACCDET_CON1           0x0f16
+#define MT6328_ACCDET_CON2           0x0f18
+#define MT6328_ACCDET_CON3           0x0f1a
+#define MT6328_ACCDET_CON4           0x0f1c
+#define MT6328_ACCDET_CON5           0x0f1e
+#define MT6328_ACCDET_CON6           0x0f20
+#define MT6328_ACCDET_CON7           0x0f22
+#define MT6328_ACCDET_CON8           0x0f24
+#define MT6328_ACCDET_CON9           0x0f26
+#define MT6328_ACCDET_CON10          0x0f28
+#define MT6328_ACCDET_CON11          0x0f2a
+#define MT6328_ACCDET_CON12          0x0f2c
+#define MT6328_ACCDET_CON13          0x0f2e
+#define MT6328_ACCDET_CON14          0x0f30
+#define MT6328_ACCDET_CON15          0x0f32
+#define MT6328_ACCDET_CON16          0x0f34
+#define MT6328_ACCDET_CON17          0x0f36
+#define MT6328_ACCDET_CON18          0x0f38
+#define MT6328_ACCDET_CON19          0x0f3a
+#define MT6328_ACCDET_CON20          0x0f3c
+#define MT6328_ACCDET_CON21          0x0f3e
+#define MT6328_ACCDET_CON22          0x0f40
+#define MT6328_ACCDET_CON23          0x0f42
+#define MT6328_ACCDET_CON24          0x0f44
+#define MT6328_ACCDET_CON25          0x0f46
+#define MT6328_CHR_CON0              0x0f48
+#define MT6328_CHR_CON1              0x0f4a
+#define MT6328_CHR_CON2              0x0f4c
+#define MT6328_CHR_CON3              0x0f4e
+#define MT6328_CHR_CON4              0x0f50
+#define MT6328_CHR_CON5              0x0f52
+#define MT6328_CHR_CON6              0x0f54
+#define MT6328_CHR_CON7              0x0f56
+#define MT6328_CHR_CON8              0x0f58
+#define MT6328_CHR_CON9              0x0f5a
+#define MT6328_CHR_CON10             0x0f5c
+#define MT6328_CHR_CON11             0x0f5e
+#define MT6328_CHR_CON12             0x0f60
+#define MT6328_CHR_CON13             0x0f62
+#define MT6328_CHR_CON14             0x0f64
+#define MT6328_CHR_CON15             0x0f66
+#define MT6328_CHR_CON16             0x0f68
+#define MT6328_CHR_CON17             0x0f6a
+#define MT6328_CHR_CON18             0x0f6c
+#define MT6328_CHR_CON19             0x0f6e
+#define MT6328_CHR_CON20             0x0f70
+#define MT6328_CHR_CON21             0x0f72
+#define MT6328_CHR_CON22             0x0f74
+#define MT6328_CHR_CON23             0x0f76
+#define MT6328_CHR_CON24             0x0f78
+#define MT6328_CHR_CON25             0x0f7a
+#define MT6328_CHR_CON26             0x0f7c
+#define MT6328_CHR_CON27             0x0f7e
+#define MT6328_CHR_CON28             0x0f80
+#define MT6328_CHR_CON29             0x0f82
+#define MT6328_CHR_CON30             0x0f84
+#define MT6328_CHR_CON31             0x0f86
+#define MT6328_CHR_CON32             0x0f88
+#define MT6328_CHR_CON33             0x0f8a
+#define MT6328_CHR_CON34             0x0f8c
+#define MT6328_CHR_CON35             0x0f8e
+#define MT6328_CHR_CON36             0x0f90
+#define MT6328_CHR_CON37             0x0f92
+#define MT6328_CHR_CON38             0x0f94
+#define MT6328_CHR_CON39             0x0f96
+#define MT6328_CHR_CON40             0x0f98
+#define MT6328_CHR_CON41             0x0f9a
+#define MT6328_CHR_CON42             0x0f9c
+#define MT6328_BATON_CON0            0x0f9e
+#define MT6328_CHR_CON43             0x0fa0
+#define MT6328_EOSC_CALI_CON0        0x0faa
+#define MT6328_EOSC_CALI_CON1        0x0fac
+#define MT6328_VRTC_PWM_CON0         0x0fae
+
+#endif /* __MFD_MT6328_REGISTERS_H__ */
diff --git a/include/linux/mfd/mt6358/registers.h b/include/linux/mfd/mt6358/registers.h
index 3d33517f178c..d83e87298ac4 100644
--- a/include/linux/mfd/mt6358/registers.h
+++ b/include/linux/mfd/mt6358/registers.h
@@ -262,6 +262,12 @@
 #define MT6358_LDO_VBIF28_CON3                0x1db0
 #define MT6358_VCAMA1_ANA_CON0                0x1e08
 #define MT6358_VCAMA2_ANA_CON0                0x1e0c
+#define MT6358_VFE28_ANA_CON0                 0x1e10
+#define MT6358_VCN28_ANA_CON0                 0x1e14
+#define MT6358_VBIF28_ANA_CON0                0x1e18
+#define MT6358_VAUD28_ANA_CON0                0x1e1c
+#define MT6358_VAUX18_ANA_CON0                0x1e20
+#define MT6358_VXO22_ANA_CON0                 0x1e24
 #define MT6358_VCN33_ANA_CON0                 0x1e28
 #define MT6358_VSIM1_ANA_CON0                 0x1e2c
 #define MT6358_VSIM2_ANA_CON0                 0x1e30
@@ -288,4 +294,21 @@
 #define MT6358_AUD_TOP_INT_CON0               0x2228
 #define MT6358_AUD_TOP_INT_STATUS0            0x2234
 
+/*
+ * MT6366 has no VCAM*, but has other regulators in its place. The names
+ * keep the MT6358 prefix for ease of use in the regulator driver.
+ */
+#define MT6358_LDO_VSRAM_CON5                 0x1bf8
+#define MT6358_LDO_VM18_CON0                  MT6358_LDO_VCAMA1_CON0
+#define MT6358_LDO_VM18_CON1                  MT6358_LDO_VCAMA1_CON1
+#define MT6358_LDO_VM18_CON2                  MT6358_LDO_VCAMA1_CON2
+#define MT6358_LDO_VMDDR_CON0                 MT6358_LDO_VCAMA2_CON0
+#define MT6358_LDO_VMDDR_CON1                 MT6358_LDO_VCAMA2_CON1
+#define MT6358_LDO_VMDDR_CON2                 MT6358_LDO_VCAMA2_CON2
+#define MT6358_LDO_VSRAM_CORE_CON0            MT6358_LDO_VCAMD_CON0
+#define MT6358_LDO_VSRAM_CORE_DBG0            0x1cb6
+#define MT6358_LDO_VSRAM_CORE_DBG1            0x1cb8
+#define MT6358_VM18_ANA_CON0                  MT6358_VCAMA1_ANA_CON0
+#define MT6358_VMDDR_ANA_CON0                 MT6358_VCAMD_ANA_CON0
+
 #endif /* __MFD_MT6358_REGISTERS_H__ */
diff --git a/include/linux/mfd/mt6397/core.h b/include/linux/mfd/mt6397/core.h
index 627487e26287..b774c3a4bb62 100644
--- a/include/linux/mfd/mt6397/core.h
+++ b/include/linux/mfd/mt6397/core.h
@@ -12,6 +12,7 @@
 
 enum chip_id {
 	MT6323_CHIP_ID = 0x23,
+	MT6328_CHIP_ID = 0x30,
 	MT6331_CHIP_ID = 0x20,
 	MT6332_CHIP_ID = 0x20,
 	MT6357_CHIP_ID = 0x57,
@@ -65,11 +66,11 @@ struct mt6397_chip {
 	int irq;
 	struct irq_domain *irq_domain;
 	struct mutex irqlock;
-	u16 wake_mask[2];
-	u16 irq_masks_cur[2];
-	u16 irq_masks_cache[2];
-	u16 int_con[2];
-	u16 int_status[2];
+	u16 wake_mask[3];
+	u16 irq_masks_cur[3];
+	u16 irq_masks_cache[3];
+	u16 int_con[3];
+	u16 int_status[3];
 	u16 chip_id;
 	void *irq_data;
 };
diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h
index 068ae1c0f0e8..27883af44f87 100644
--- a/include/linux/mfd/mt6397/rtc.h
+++ b/include/linux/mfd/mt6397/rtc.h
@@ -60,11 +60,6 @@
 #define RTC_PDN2               0x002e
 #define RTC_PDN2_PWRON_ALARM   BIT(4)
 
-#define RTC_MIN_YEAR           1968
-#define RTC_BASE_YEAR          1900
-#define RTC_NUM_YEARS          128
-#define RTC_MIN_YEAR_OFFSET    (RTC_MIN_YEAR - RTC_BASE_YEAR)
-
 #define MTK_RTC_POLL_DELAY_US  10
 #define MTK_RTC_POLL_TIMEOUT   (jiffies_to_usecs(HZ))
 
diff --git a/include/linux/mfd/nct6694.h b/include/linux/mfd/nct6694.h
new file mode 100644
index 000000000000..6eb9be2cd4a0
--- /dev/null
+++ b/include/linux/mfd/nct6694.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2025 Nuvoton Technology Corp.
+ *
+ * Nuvoton NCT6694 USB transaction and data structure.
+ */
+
+#ifndef __MFD_NCT6694_H
+#define __MFD_NCT6694_H
+
+#define NCT6694_VENDOR_ID	0x0416
+#define NCT6694_PRODUCT_ID	0x200B
+#define NCT6694_INT_IN_EP	0x81
+#define NCT6694_BULK_IN_EP	0x02
+#define NCT6694_BULK_OUT_EP	0x03
+
+#define NCT6694_HCTRL_SET	0x40
+#define NCT6694_HCTRL_GET	0x80
+
+#define NCT6694_URB_TIMEOUT	1000
+
+enum nct6694_irq_id {
+	NCT6694_IRQ_GPIO0 = 0,
+	NCT6694_IRQ_GPIO1,
+	NCT6694_IRQ_GPIO2,
+	NCT6694_IRQ_GPIO3,
+	NCT6694_IRQ_GPIO4,
+	NCT6694_IRQ_GPIO5,
+	NCT6694_IRQ_GPIO6,
+	NCT6694_IRQ_GPIO7,
+	NCT6694_IRQ_GPIO8,
+	NCT6694_IRQ_GPIO9,
+	NCT6694_IRQ_GPIOA,
+	NCT6694_IRQ_GPIOB,
+	NCT6694_IRQ_GPIOC,
+	NCT6694_IRQ_GPIOD,
+	NCT6694_IRQ_GPIOE,
+	NCT6694_IRQ_GPIOF,
+	NCT6694_IRQ_CAN0,
+	NCT6694_IRQ_CAN1,
+	NCT6694_IRQ_RTC,
+	NCT6694_NR_IRQS,
+};
+
+enum nct6694_response_err_status {
+	NCT6694_NO_ERROR = 0,
+	NCT6694_FORMAT_ERROR,
+	NCT6694_RESERVED1,
+	NCT6694_RESERVED2,
+	NCT6694_NOT_SUPPORT_ERROR,
+	NCT6694_NO_RESPONSE_ERROR,
+	NCT6694_TIMEOUT_ERROR,
+	NCT6694_PENDING,
+};
+
+struct __packed nct6694_cmd_header {
+	u8 rsv1;
+	u8 mod;
+	union __packed {
+		__le16 offset;
+		struct __packed {
+			u8 cmd;
+			u8 sel;
+		};
+	};
+	u8 hctrl;
+	u8 rsv2;
+	__le16 len;
+};
+
+struct __packed nct6694_response_header {
+	u8 sequence_id;
+	u8 sts;
+	u8 reserved[4];
+	__le16 len;
+};
+
+union __packed nct6694_usb_msg {
+	struct nct6694_cmd_header cmd_header;
+	struct nct6694_response_header response_header;
+};
+
+struct nct6694 {
+	struct device *dev;
+	struct ida gpio_ida;
+	struct ida i2c_ida;
+	struct ida canfd_ida;
+	struct ida wdt_ida;
+	struct irq_domain *domain;
+	struct mutex access_lock;
+	spinlock_t irq_lock;
+	struct urb *int_in_urb;
+	struct usb_device *udev;
+	union nct6694_usb_msg *usb_msg;
+	__le32 *int_buffer;
+	unsigned int irq_enable;
+};
+
+int nct6694_read_msg(struct nct6694 *nct6694, const struct nct6694_cmd_header *cmd_hd, void *buf);
+int nct6694_write_msg(struct nct6694 *nct6694, const struct nct6694_cmd_header *cmd_hd, void *buf);
+
+#endif
diff --git a/include/linux/mfd/palmas.h b/include/linux/mfd/palmas.h
index eda1ffd99c1a..dabcc0dea802 100644
--- a/include/linux/mfd/palmas.h
+++ b/include/linux/mfd/palmas.h
@@ -98,8 +98,8 @@ struct palmas_sleep_requestor_info {
 };
 
 struct palmas_regs_info {
-	char	*name;
-	char	*sname;
+	const char	*name;
+	const char	*sname;
 	u8	vsel_addr;
 	u8	ctrl_addr;
 	u8	tstep_addr;
diff --git a/include/linux/mfd/pcf50633/adc.h b/include/linux/mfd/pcf50633/adc.h
deleted file mode 100644
index 6a81896d4889..000000000000
--- a/include/linux/mfd/pcf50633/adc.h
+++ /dev/null
@@ -1,69 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * adc.h  -- Driver for NXP PCF50633 ADC
- *
- * (C) 2006-2008 by Openmoko, Inc.
- * All rights reserved.
- */
-
-#ifndef __LINUX_MFD_PCF50633_ADC_H
-#define __LINUX_MFD_PCF50633_ADC_H
-
-#include <linux/mfd/pcf50633/core.h>
-#include <linux/platform_device.h>
-
-/* ADC Registers */
-#define PCF50633_REG_ADCC3		0x52
-#define PCF50633_REG_ADCC2		0x53
-#define PCF50633_REG_ADCC1		0x54
-#define PCF50633_REG_ADCS1		0x55
-#define PCF50633_REG_ADCS2		0x56
-#define PCF50633_REG_ADCS3		0x57
-
-#define PCF50633_ADCC1_ADCSTART		0x01
-#define PCF50633_ADCC1_RES_8BIT		0x02
-#define PCF50633_ADCC1_RES_10BIT	0x00
-#define PCF50633_ADCC1_AVERAGE_NO	0x00
-#define PCF50633_ADCC1_AVERAGE_4	0x04
-#define PCF50633_ADCC1_AVERAGE_8	0x08
-#define PCF50633_ADCC1_AVERAGE_16	0x0c
-#define PCF50633_ADCC1_MUX_BATSNS_RES	0x00
-#define PCF50633_ADCC1_MUX_BATSNS_SUBTR	0x10
-#define PCF50633_ADCC1_MUX_ADCIN2_RES	0x20
-#define PCF50633_ADCC1_MUX_ADCIN2_SUBTR	0x30
-#define PCF50633_ADCC1_MUX_BATTEMP	0x60
-#define PCF50633_ADCC1_MUX_ADCIN1	0x70
-#define PCF50633_ADCC1_AVERAGE_MASK	0x0c
-#define PCF50633_ADCC1_ADCMUX_MASK	0xf0
-
-#define PCF50633_ADCC2_RATIO_NONE	0x00
-#define PCF50633_ADCC2_RATIO_BATTEMP	0x01
-#define PCF50633_ADCC2_RATIO_ADCIN1	0x02
-#define PCF50633_ADCC2_RATIO_BOTH	0x03
-#define PCF50633_ADCC2_RATIOSETTL_100US 0x04
-
-#define PCF50633_ADCC3_ACCSW_EN		0x01
-#define PCF50633_ADCC3_NTCSW_EN		0x04
-#define PCF50633_ADCC3_RES_DIV_TWO	0x10
-#define PCF50633_ADCC3_RES_DIV_THREE	0x00
-
-#define PCF50633_ADCS3_REF_NTCSW	0x00
-#define PCF50633_ADCS3_REF_ACCSW	0x10
-#define PCF50633_ADCS3_REF_2V0		0x20
-#define PCF50633_ADCS3_REF_VISA		0x30
-#define PCF50633_ADCS3_REF_2V0_2	0x70
-#define PCF50633_ADCS3_ADCRDY		0x80
-
-#define PCF50633_ADCS3_ADCDAT1L_MASK	0x03
-#define PCF50633_ADCS3_ADCDAT2L_MASK	0x0c
-#define PCF50633_ADCS3_ADCDAT2L_SHIFT	2
-#define PCF50633_ASCS3_REF_MASK		0x70
-
-extern int
-pcf50633_adc_async_read(struct pcf50633 *pcf, int mux, int avg,
-		void (*callback)(struct pcf50633 *, void *, int),
-		void *callback_param);
-extern int
-pcf50633_adc_sync_read(struct pcf50633 *pcf, int mux, int avg);
-
-#endif /* __LINUX_PCF50633_ADC_H */
diff --git a/include/linux/mfd/pcf50633/backlight.h b/include/linux/mfd/pcf50633/backlight.h
deleted file mode 100644
index fd4a4f8d6c13..000000000000
--- a/include/linux/mfd/pcf50633/backlight.h
+++ /dev/null
@@ -1,42 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- *  Copyright (C) 2009-2010, Lars-Peter Clausen <lars@metafoo.de>
- *      PCF50633 backlight device driver
- */
-
-#ifndef __LINUX_MFD_PCF50633_BACKLIGHT
-#define __LINUX_MFD_PCF50633_BACKLIGHT
-
-/*
-* @default_brightness: Backlight brightness is initialized to this value
-*
-* Brightness to be used after the driver has been probed.
-* Valid range 0-63.
-*
-* @default_brightness_limit: The actual brightness is limited by this value
-*
-* Brightness limit to be used after the driver has been probed. This is useful
-* when it is not known how much power is available for the backlight during
-* probe.
-* Valid range 0-63. Can be changed later with pcf50633_bl_set_brightness_limit.
-*
-* @ramp_time: Display ramp time when changing brightness
-*
-* When changing the backlights brightness the change is not instant, instead
-* it fades smooth from one state to another. This value specifies how long
-* the fade should take. The lower the value the higher the fade time.
-* Valid range 0-255
-*/
-struct pcf50633_bl_platform_data {
-	unsigned int	default_brightness;
-	unsigned int	default_brightness_limit;
-	uint8_t		ramp_time;
-};
-
-
-struct pcf50633;
-
-int pcf50633_bl_set_brightness_limit(struct pcf50633 *pcf, unsigned int limit);
-
-#endif
-
diff --git a/include/linux/mfd/pcf50633/core.h b/include/linux/mfd/pcf50633/core.h
deleted file mode 100644
index 539f27f8bd89..000000000000
--- a/include/linux/mfd/pcf50633/core.h
+++ /dev/null
@@ -1,232 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * core.h  -- Core driver for NXP PCF50633
- *
- * (C) 2006-2008 by Openmoko, Inc.
- * All rights reserved.
- */
-
-#ifndef __LINUX_MFD_PCF50633_CORE_H
-#define __LINUX_MFD_PCF50633_CORE_H
-
-#include <linux/i2c.h>
-#include <linux/workqueue.h>
-#include <linux/regulator/driver.h>
-#include <linux/regulator/machine.h>
-#include <linux/pm.h>
-#include <linux/power_supply.h>
-#include <linux/mfd/pcf50633/backlight.h>
-
-struct pcf50633;
-struct regmap;
-
-#define PCF50633_NUM_REGULATORS	11
-
-struct pcf50633_platform_data {
-	struct regulator_init_data reg_init_data[PCF50633_NUM_REGULATORS];
-
-	char **batteries;
-	int num_batteries;
-
-	/*
-	 * Should be set accordingly to the reference resistor used, see
-	 * I_{ch(ref)} charger reference current in the pcf50633 User
-	 * Manual.
-	 */
-	int charger_reference_current_ma;
-
-	/* Callbacks */
-	void (*probe_done)(struct pcf50633 *);
-	void (*mbc_event_callback)(struct pcf50633 *, int);
-	void (*regulator_registered)(struct pcf50633 *, int);
-	void (*force_shutdown)(struct pcf50633 *);
-
-	u8 resumers[5];
-
-	struct pcf50633_bl_platform_data *backlight_data;
-};
-
-struct pcf50633_irq {
-	void (*handler) (int, void *);
-	void *data;
-};
-
-int pcf50633_register_irq(struct pcf50633 *pcf, int irq,
-			void (*handler) (int, void *), void *data);
-int pcf50633_free_irq(struct pcf50633 *pcf, int irq);
-
-int pcf50633_irq_mask(struct pcf50633 *pcf, int irq);
-int pcf50633_irq_unmask(struct pcf50633 *pcf, int irq);
-int pcf50633_irq_mask_get(struct pcf50633 *pcf, int irq);
-
-int pcf50633_read_block(struct pcf50633 *, u8 reg,
-					int nr_regs, u8 *data);
-int pcf50633_write_block(struct pcf50633 *pcf, u8 reg,
-					int nr_regs, u8 *data);
-u8 pcf50633_reg_read(struct pcf50633 *, u8 reg);
-int pcf50633_reg_write(struct pcf50633 *pcf, u8 reg, u8 val);
-
-int pcf50633_reg_set_bit_mask(struct pcf50633 *pcf, u8 reg, u8 mask, u8 val);
-int pcf50633_reg_clear_bits(struct pcf50633 *pcf, u8 reg, u8 bits);
-
-/* Interrupt registers */
-
-#define PCF50633_REG_INT1	0x02
-#define PCF50633_REG_INT2	0x03
-#define PCF50633_REG_INT3	0x04
-#define PCF50633_REG_INT4	0x05
-#define PCF50633_REG_INT5	0x06
-
-#define PCF50633_REG_INT1M	0x07
-#define PCF50633_REG_INT2M	0x08
-#define PCF50633_REG_INT3M	0x09
-#define PCF50633_REG_INT4M	0x0a
-#define PCF50633_REG_INT5M	0x0b
-
-enum {
-	/* Chip IRQs */
-	PCF50633_IRQ_ADPINS,
-	PCF50633_IRQ_ADPREM,
-	PCF50633_IRQ_USBINS,
-	PCF50633_IRQ_USBREM,
-	PCF50633_IRQ_RESERVED1,
-	PCF50633_IRQ_RESERVED2,
-	PCF50633_IRQ_ALARM,
-	PCF50633_IRQ_SECOND,
-	PCF50633_IRQ_ONKEYR,
-	PCF50633_IRQ_ONKEYF,
-	PCF50633_IRQ_EXTON1R,
-	PCF50633_IRQ_EXTON1F,
-	PCF50633_IRQ_EXTON2R,
-	PCF50633_IRQ_EXTON2F,
-	PCF50633_IRQ_EXTON3R,
-	PCF50633_IRQ_EXTON3F,
-	PCF50633_IRQ_BATFULL,
-	PCF50633_IRQ_CHGHALT,
-	PCF50633_IRQ_THLIMON,
-	PCF50633_IRQ_THLIMOFF,
-	PCF50633_IRQ_USBLIMON,
-	PCF50633_IRQ_USBLIMOFF,
-	PCF50633_IRQ_ADCRDY,
-	PCF50633_IRQ_ONKEY1S,
-	PCF50633_IRQ_LOWSYS,
-	PCF50633_IRQ_LOWBAT,
-	PCF50633_IRQ_HIGHTMP,
-	PCF50633_IRQ_AUTOPWRFAIL,
-	PCF50633_IRQ_DWN1PWRFAIL,
-	PCF50633_IRQ_DWN2PWRFAIL,
-	PCF50633_IRQ_LEDPWRFAIL,
-	PCF50633_IRQ_LEDOVP,
-	PCF50633_IRQ_LDO1PWRFAIL,
-	PCF50633_IRQ_LDO2PWRFAIL,
-	PCF50633_IRQ_LDO3PWRFAIL,
-	PCF50633_IRQ_LDO4PWRFAIL,
-	PCF50633_IRQ_LDO5PWRFAIL,
-	PCF50633_IRQ_LDO6PWRFAIL,
-	PCF50633_IRQ_HCLDOPWRFAIL,
-	PCF50633_IRQ_HCLDOOVL,
-
-	/* Always last */
-	PCF50633_NUM_IRQ,
-};
-
-struct pcf50633 {
-	struct device *dev;
-	struct regmap *regmap;
-
-	struct pcf50633_platform_data *pdata;
-	int irq;
-	struct pcf50633_irq irq_handler[PCF50633_NUM_IRQ];
-	struct work_struct irq_work;
-	struct workqueue_struct *work_queue;
-	struct mutex lock;
-
-	u8 mask_regs[5];
-
-	u8 suspend_irq_masks[5];
-	u8 resume_reason[5];
-	int is_suspended;
-
-	int onkey1s_held;
-
-	struct platform_device *rtc_pdev;
-	struct platform_device *mbc_pdev;
-	struct platform_device *adc_pdev;
-	struct platform_device *input_pdev;
-	struct platform_device *bl_pdev;
-	struct platform_device *regulator_pdev[PCF50633_NUM_REGULATORS];
-};
-
-enum pcf50633_reg_int1 {
-	PCF50633_INT1_ADPINS	= 0x01,	/* Adapter inserted */
-	PCF50633_INT1_ADPREM	= 0x02,	/* Adapter removed */
-	PCF50633_INT1_USBINS	= 0x04,	/* USB inserted */
-	PCF50633_INT1_USBREM	= 0x08,	/* USB removed */
-	/* reserved */
-	PCF50633_INT1_ALARM	= 0x40, /* RTC alarm time is reached */
-	PCF50633_INT1_SECOND	= 0x80,	/* RTC periodic second interrupt */
-};
-
-enum pcf50633_reg_int2 {
-	PCF50633_INT2_ONKEYR	= 0x01, /* ONKEY rising edge */
-	PCF50633_INT2_ONKEYF	= 0x02, /* ONKEY falling edge */
-	PCF50633_INT2_EXTON1R	= 0x04, /* EXTON1 rising edge */
-	PCF50633_INT2_EXTON1F	= 0x08, /* EXTON1 falling edge */
-	PCF50633_INT2_EXTON2R	= 0x10, /* EXTON2 rising edge */
-	PCF50633_INT2_EXTON2F	= 0x20, /* EXTON2 falling edge */
-	PCF50633_INT2_EXTON3R	= 0x40, /* EXTON3 rising edge */
-	PCF50633_INT2_EXTON3F	= 0x80, /* EXTON3 falling edge */
-};
-
-enum pcf50633_reg_int3 {
-	PCF50633_INT3_BATFULL	= 0x01, /* Battery full */
-	PCF50633_INT3_CHGHALT	= 0x02,	/* Charger halt */
-	PCF50633_INT3_THLIMON	= 0x04,
-	PCF50633_INT3_THLIMOFF	= 0x08,
-	PCF50633_INT3_USBLIMON	= 0x10,
-	PCF50633_INT3_USBLIMOFF	= 0x20,
-	PCF50633_INT3_ADCRDY	= 0x40, /* ADC result ready */
-	PCF50633_INT3_ONKEY1S	= 0x80,	/* ONKEY pressed 1 second */
-};
-
-enum pcf50633_reg_int4 {
-	PCF50633_INT4_LOWSYS		= 0x01,
-	PCF50633_INT4_LOWBAT		= 0x02,
-	PCF50633_INT4_HIGHTMP		= 0x04,
-	PCF50633_INT4_AUTOPWRFAIL	= 0x08,
-	PCF50633_INT4_DWN1PWRFAIL	= 0x10,
-	PCF50633_INT4_DWN2PWRFAIL	= 0x20,
-	PCF50633_INT4_LEDPWRFAIL	= 0x40,
-	PCF50633_INT4_LEDOVP		= 0x80,
-};
-
-enum pcf50633_reg_int5 {
-	PCF50633_INT5_LDO1PWRFAIL	= 0x01,
-	PCF50633_INT5_LDO2PWRFAIL	= 0x02,
-	PCF50633_INT5_LDO3PWRFAIL	= 0x04,
-	PCF50633_INT5_LDO4PWRFAIL	= 0x08,
-	PCF50633_INT5_LDO5PWRFAIL	= 0x10,
-	PCF50633_INT5_LDO6PWRFAIL	= 0x20,
-	PCF50633_INT5_HCLDOPWRFAIL	= 0x40,
-	PCF50633_INT5_HCLDOOVL		= 0x80,
-};
-
-/* misc. registers */
-#define PCF50633_REG_OOCSHDWN	0x0c
-
-/* LED registers */
-#define PCF50633_REG_LEDOUT 0x28
-#define PCF50633_REG_LEDENA 0x29
-#define PCF50633_REG_LEDCTL 0x2a
-#define PCF50633_REG_LEDDIM 0x2b
-
-static inline struct pcf50633 *dev_to_pcf50633(struct device *dev)
-{
-	return dev_get_drvdata(dev);
-}
-
-int pcf50633_irq_init(struct pcf50633 *pcf, int irq);
-void pcf50633_irq_free(struct pcf50633 *pcf);
-extern const struct dev_pm_ops pcf50633_pm;
-
-#endif
diff --git a/include/linux/mfd/pcf50633/gpio.h b/include/linux/mfd/pcf50633/gpio.h
deleted file mode 100644
index f589e35795f1..000000000000
--- a/include/linux/mfd/pcf50633/gpio.h
+++ /dev/null
@@ -1,48 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * gpio.h -- GPIO driver for NXP PCF50633
- *
- * (C) 2006-2008 by Openmoko, Inc.
- * All rights reserved.
- */
-
-#ifndef __LINUX_MFD_PCF50633_GPIO_H
-#define __LINUX_MFD_PCF50633_GPIO_H
-
-#include <linux/mfd/pcf50633/core.h>
-
-#define PCF50633_GPIO1		1
-#define PCF50633_GPIO2		2
-#define PCF50633_GPIO3		3
-#define PCF50633_GPO		4
-
-#define PCF50633_REG_GPIO1CFG	0x14
-#define PCF50633_REG_GPIO2CFG	0x15
-#define PCF50633_REG_GPIO3CFG	0x16
-#define PCF50633_REG_GPOCFG 	0x17
-
-#define PCF50633_GPOCFG_GPOSEL_MASK	0x07
-
-enum pcf50633_reg_gpocfg {
-	PCF50633_GPOCFG_GPOSEL_0	= 0x00,
-	PCF50633_GPOCFG_GPOSEL_LED_NFET	= 0x01,
-	PCF50633_GPOCFG_GPOSEL_SYSxOK	= 0x02,
-	PCF50633_GPOCFG_GPOSEL_CLK32K	= 0x03,
-	PCF50633_GPOCFG_GPOSEL_ADAPUSB	= 0x04,
-	PCF50633_GPOCFG_GPOSEL_USBxOK	= 0x05,
-	PCF50633_GPOCFG_GPOSEL_ACTPH4	= 0x06,
-	PCF50633_GPOCFG_GPOSEL_1	= 0x07,
-	PCF50633_GPOCFG_GPOSEL_INVERSE	= 0x08,
-};
-
-int pcf50633_gpio_set(struct pcf50633 *pcf, int gpio, u8 val);
-u8 pcf50633_gpio_get(struct pcf50633 *pcf, int gpio);
-
-int pcf50633_gpio_invert_set(struct pcf50633 *, int gpio, int invert);
-int pcf50633_gpio_invert_get(struct pcf50633 *pcf, int gpio);
-
-int pcf50633_gpio_power_supply_set(struct pcf50633 *,
-					int gpio, int regulator, int on);
-#endif /* __LINUX_MFD_PCF50633_GPIO_H */
-
-
diff --git a/include/linux/mfd/pcf50633/mbc.h b/include/linux/mfd/pcf50633/mbc.h
deleted file mode 100644
index fa5cb9256d99..000000000000
--- a/include/linux/mfd/pcf50633/mbc.h
+++ /dev/null
@@ -1,130 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * mbc.h  -- Driver for NXP PCF50633 Main Battery Charger
- *
- * (C) 2006-2008 by Openmoko, Inc.
- * All rights reserved.
- */
-
-#ifndef __LINUX_MFD_PCF50633_MBC_H
-#define __LINUX_MFD_PCF50633_MBC_H
-
-#include <linux/mfd/pcf50633/core.h>
-#include <linux/platform_device.h>
-
-#define PCF50633_REG_MBCC1	0x43
-#define PCF50633_REG_MBCC2	0x44
-#define PCF50633_REG_MBCC3	0x45
-#define PCF50633_REG_MBCC4	0x46
-#define PCF50633_REG_MBCC5	0x47
-#define PCF50633_REG_MBCC6	0x48
-#define PCF50633_REG_MBCC7	0x49
-#define PCF50633_REG_MBCC8	0x4a
-#define PCF50633_REG_MBCS1	0x4b
-#define PCF50633_REG_MBCS2	0x4c
-#define PCF50633_REG_MBCS3	0x4d
-
-enum pcf50633_reg_mbcc1 {
-	PCF50633_MBCC1_CHGENA		= 0x01,	/* Charger enable */
-	PCF50633_MBCC1_AUTOSTOP		= 0x02,
-	PCF50633_MBCC1_AUTORES		= 0x04, /* automatic resume */
-	PCF50633_MBCC1_RESUME		= 0x08, /* explicit resume cmd */
-	PCF50633_MBCC1_RESTART		= 0x10, /* restart charging */
-	PCF50633_MBCC1_PREWDTIME_60M	= 0x20,	/* max. precharging time */
-	PCF50633_MBCC1_WDTIME_1H	= 0x00,
-	PCF50633_MBCC1_WDTIME_2H	= 0x40,
-	PCF50633_MBCC1_WDTIME_4H	= 0x80,
-	PCF50633_MBCC1_WDTIME_6H	= 0xc0,
-};
-#define PCF50633_MBCC1_WDTIME_MASK	  0xc0
-
-enum pcf50633_reg_mbcc2 {
-	PCF50633_MBCC2_VBATCOND_2V7	= 0x00,
-	PCF50633_MBCC2_VBATCOND_2V85	= 0x01,
-	PCF50633_MBCC2_VBATCOND_3V0	= 0x02,
-	PCF50633_MBCC2_VBATCOND_3V15	= 0x03,
-	PCF50633_MBCC2_VMAX_4V		= 0x00,
-	PCF50633_MBCC2_VMAX_4V20	= 0x28,
-	PCF50633_MBCC2_VRESDEBTIME_64S	= 0x80,	/* debounce time (32/64sec) */
-};
-
-enum pcf50633_reg_mbcc7 {
-	PCF50633_MBCC7_USB_100mA	= 0x00,
-	PCF50633_MBCC7_USB_500mA	= 0x01,
-	PCF50633_MBCC7_USB_1000mA	= 0x02,
-	PCF50633_MBCC7_USB_SUSPEND	= 0x03,
-	PCF50633_MBCC7_BATTEMP_EN	= 0x04,
-	PCF50633_MBCC7_BATSYSIMAX_1A6	= 0x00,
-	PCF50633_MBCC7_BATSYSIMAX_1A8	= 0x40,
-	PCF50633_MBCC7_BATSYSIMAX_2A0	= 0x80,
-	PCF50633_MBCC7_BATSYSIMAX_2A2	= 0xc0,
-};
-#define PCF50633_MBCC7_USB_MASK 0x03
-
-enum pcf50633_reg_mbcc8 {
-	PCF50633_MBCC8_USBENASUS	= 0x10,
-};
-
-enum pcf50633_reg_mbcs1 {
-	PCF50633_MBCS1_USBPRES		= 0x01,
-	PCF50633_MBCS1_USBOK		= 0x02,
-	PCF50633_MBCS1_ADAPTPRES	= 0x04,
-	PCF50633_MBCS1_ADAPTOK		= 0x08,
-	PCF50633_MBCS1_TBAT_OK		= 0x00,
-	PCF50633_MBCS1_TBAT_ABOVE	= 0x10,
-	PCF50633_MBCS1_TBAT_BELOW	= 0x20,
-	PCF50633_MBCS1_TBAT_UNDEF	= 0x30,
-	PCF50633_MBCS1_PREWDTEXP	= 0x40,
-	PCF50633_MBCS1_WDTEXP		= 0x80,
-};
-
-enum pcf50633_reg_mbcs2_mbcmod {
-	PCF50633_MBCS2_MBC_PLAY		= 0x00,
-	PCF50633_MBCS2_MBC_USB_PRE	= 0x01,
-	PCF50633_MBCS2_MBC_USB_PRE_WAIT	= 0x02,
-	PCF50633_MBCS2_MBC_USB_FAST	= 0x03,
-	PCF50633_MBCS2_MBC_USB_FAST_WAIT = 0x04,
-	PCF50633_MBCS2_MBC_USB_SUSPEND	= 0x05,
-	PCF50633_MBCS2_MBC_ADP_PRE	= 0x06,
-	PCF50633_MBCS2_MBC_ADP_PRE_WAIT	= 0x07,
-	PCF50633_MBCS2_MBC_ADP_FAST	= 0x08,
-	PCF50633_MBCS2_MBC_ADP_FAST_WAIT = 0x09,
-	PCF50633_MBCS2_MBC_BAT_FULL	= 0x0a,
-	PCF50633_MBCS2_MBC_HALT		= 0x0b,
-};
-#define PCF50633_MBCS2_MBC_MASK		0x0f
-enum pcf50633_reg_mbcs2_chgstat {
-	PCF50633_MBCS2_CHGS_NONE	= 0x00,
-	PCF50633_MBCS2_CHGS_ADAPTER	= 0x10,
-	PCF50633_MBCS2_CHGS_USB		= 0x20,
-	PCF50633_MBCS2_CHGS_BOTH	= 0x30,
-};
-#define PCF50633_MBCS2_RESSTAT_AUTO	0x40
-
-enum pcf50633_reg_mbcs3 {
-	PCF50633_MBCS3_USBLIM_PLAY	= 0x01,
-	PCF50633_MBCS3_USBLIM_CGH	= 0x02,
-	PCF50633_MBCS3_TLIM_PLAY	= 0x04,
-	PCF50633_MBCS3_TLIM_CHG		= 0x08,
-	PCF50633_MBCS3_ILIM		= 0x10,	/* 1: Ibat > Icutoff */
-	PCF50633_MBCS3_VLIM		= 0x20,	/* 1: Vbat == Vmax */
-	PCF50633_MBCS3_VBATSTAT		= 0x40,	/* 1: Vbat > Vbatcond */
-	PCF50633_MBCS3_VRES		= 0x80, /* 1: Vbat > Vth(RES) */
-};
-
-#define PCF50633_MBCC2_VBATCOND_MASK	  0x03
-#define PCF50633_MBCC2_VMAX_MASK	  0x3c
-
-/* Charger status */
-#define PCF50633_MBC_USB_ONLINE		0x01
-#define PCF50633_MBC_USB_ACTIVE		0x02
-#define PCF50633_MBC_ADAPTER_ONLINE	0x04
-#define PCF50633_MBC_ADAPTER_ACTIVE	0x08
-
-int pcf50633_mbc_usb_curlim_set(struct pcf50633 *pcf, int ma);
-
-int pcf50633_mbc_get_status(struct pcf50633 *);
-int pcf50633_mbc_get_usb_online_status(struct pcf50633 *);
-
-#endif
-
diff --git a/include/linux/mfd/pcf50633/pmic.h b/include/linux/mfd/pcf50633/pmic.h
deleted file mode 100644
index eac0c3d8e984..000000000000
--- a/include/linux/mfd/pcf50633/pmic.h
+++ /dev/null
@@ -1,68 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __LINUX_MFD_PCF50633_PMIC_H
-#define __LINUX_MFD_PCF50633_PMIC_H
-
-#include <linux/mfd/pcf50633/core.h>
-#include <linux/platform_device.h>
-
-#define PCF50633_REG_AUTOOUT	0x1a
-#define PCF50633_REG_AUTOENA	0x1b
-#define PCF50633_REG_AUTOCTL	0x1c
-#define PCF50633_REG_AUTOMXC	0x1d
-#define PCF50633_REG_DOWN1OUT	0x1e
-#define PCF50633_REG_DOWN1ENA	0x1f
-#define PCF50633_REG_DOWN1CTL	0x20
-#define PCF50633_REG_DOWN1MXC	0x21
-#define PCF50633_REG_DOWN2OUT	0x22
-#define PCF50633_REG_DOWN2ENA	0x23
-#define PCF50633_REG_DOWN2CTL	0x24
-#define PCF50633_REG_DOWN2MXC	0x25
-#define PCF50633_REG_MEMLDOOUT	0x26
-#define PCF50633_REG_MEMLDOENA	0x27
-#define PCF50633_REG_LDO1OUT	0x2d
-#define PCF50633_REG_LDO1ENA	0x2e
-#define PCF50633_REG_LDO2OUT	0x2f
-#define PCF50633_REG_LDO2ENA	0x30
-#define PCF50633_REG_LDO3OUT	0x31
-#define PCF50633_REG_LDO3ENA	0x32
-#define PCF50633_REG_LDO4OUT	0x33
-#define PCF50633_REG_LDO4ENA	0x34
-#define PCF50633_REG_LDO5OUT	0x35
-#define PCF50633_REG_LDO5ENA	0x36
-#define PCF50633_REG_LDO6OUT	0x37
-#define PCF50633_REG_LDO6ENA	0x38
-#define PCF50633_REG_HCLDOOUT	0x39
-#define PCF50633_REG_HCLDOENA	0x3a
-#define PCF50633_REG_HCLDOOVL	0x40
-
-enum pcf50633_regulator_enable {
-	PCF50633_REGULATOR_ON		= 0x01,
-	PCF50633_REGULATOR_ON_GPIO1	= 0x02,
-	PCF50633_REGULATOR_ON_GPIO2	= 0x04,
-	PCF50633_REGULATOR_ON_GPIO3	= 0x08,
-};
-#define PCF50633_REGULATOR_ON_MASK	0x0f
-
-enum pcf50633_regulator_phase {
-	PCF50633_REGULATOR_ACTPH1	= 0x00,
-	PCF50633_REGULATOR_ACTPH2	= 0x10,
-	PCF50633_REGULATOR_ACTPH3	= 0x20,
-	PCF50633_REGULATOR_ACTPH4	= 0x30,
-};
-#define PCF50633_REGULATOR_ACTPH_MASK	0x30
-
-enum pcf50633_regulator_id {
-	PCF50633_REGULATOR_AUTO,
-	PCF50633_REGULATOR_DOWN1,
-	PCF50633_REGULATOR_DOWN2,
-	PCF50633_REGULATOR_LDO1,
-	PCF50633_REGULATOR_LDO2,
-	PCF50633_REGULATOR_LDO3,
-	PCF50633_REGULATOR_LDO4,
-	PCF50633_REGULATOR_LDO5,
-	PCF50633_REGULATOR_LDO6,
-	PCF50633_REGULATOR_HCLDO,
-	PCF50633_REGULATOR_MEMLDO,
-};
-#endif
-
diff --git a/include/linux/mfd/pf1550.h b/include/linux/mfd/pf1550.h
new file mode 100644
index 000000000000..7cb2340ff2bd
--- /dev/null
+++ b/include/linux/mfd/pf1550.h
@@ -0,0 +1,273 @@
+/* SPDX-License-Identifier: GPL-2.0
+ *
+ * Declarations for the PF1550 PMIC
+ *
+ * Copyright (C) 2016 Freescale Semiconductor, Inc.
+ * Robin Gong <yibin.gong@freescale.com>
+ *
+ * Portions Copyright (c) 2025 Savoir-faire Linux Inc.
+ * Samuel Kayode <samuel.kayode@savoirfairelinux.com>
+ */
+
+#ifndef __LINUX_MFD_PF1550_H
+#define __LINUX_MFD_PF1550_H
+
+#include <linux/i2c.h>
+#include <linux/regmap.h>
+
+enum pf1550_pmic_reg {
+	/* PMIC regulator part */
+	PF1550_PMIC_REG_DEVICE_ID		= 0x00,
+	PF1550_PMIC_REG_OTP_FLAVOR		= 0x01,
+	PF1550_PMIC_REG_SILICON_REV		= 0x02,
+
+	PF1550_PMIC_REG_INT_CATEGORY		= 0x06,
+	PF1550_PMIC_REG_SW_INT_STAT0		= 0x08,
+	PF1550_PMIC_REG_SW_INT_MASK0		= 0x09,
+	PF1550_PMIC_REG_SW_INT_SENSE0		= 0x0a,
+	PF1550_PMIC_REG_SW_INT_STAT1		= 0x0b,
+	PF1550_PMIC_REG_SW_INT_MASK1		= 0x0c,
+	PF1550_PMIC_REG_SW_INT_SENSE1		= 0x0d,
+	PF1550_PMIC_REG_SW_INT_STAT2		= 0x0e,
+	PF1550_PMIC_REG_SW_INT_MASK2		= 0x0f,
+	PF1550_PMIC_REG_SW_INT_SENSE2		= 0x10,
+	PF1550_PMIC_REG_LDO_INT_STAT0		= 0x18,
+	PF1550_PMIC_REG_LDO_INT_MASK0		= 0x19,
+	PF1550_PMIC_REG_LDO_INT_SENSE0		= 0x1a,
+	PF1550_PMIC_REG_TEMP_INT_STAT0		= 0x20,
+	PF1550_PMIC_REG_TEMP_INT_MASK0		= 0x21,
+	PF1550_PMIC_REG_TEMP_INT_SENSE0		= 0x22,
+	PF1550_PMIC_REG_ONKEY_INT_STAT0		= 0x24,
+	PF1550_PMIC_REG_ONKEY_INT_MASK0		= 0x25,
+	PF1550_PMIC_REG_ONKEY_INT_SENSE0	= 0x26,
+	PF1550_PMIC_REG_MISC_INT_STAT0		= 0x28,
+	PF1550_PMIC_REG_MISC_INT_MASK0		= 0x29,
+	PF1550_PMIC_REG_MISC_INT_SENSE0		= 0x2a,
+
+	PF1550_PMIC_REG_COINCELL_CONTROL	= 0x30,
+
+	PF1550_PMIC_REG_SW1_VOLT		= 0x32,
+	PF1550_PMIC_REG_SW1_STBY_VOLT		= 0x33,
+	PF1550_PMIC_REG_SW1_SLP_VOLT		= 0x34,
+	PF1550_PMIC_REG_SW1_CTRL		= 0x35,
+	PF1550_PMIC_REG_SW1_CTRL1		= 0x36,
+	PF1550_PMIC_REG_SW2_VOLT		= 0x38,
+	PF1550_PMIC_REG_SW2_STBY_VOLT		= 0x39,
+	PF1550_PMIC_REG_SW2_SLP_VOLT		= 0x3a,
+	PF1550_PMIC_REG_SW2_CTRL		= 0x3b,
+	PF1550_PMIC_REG_SW2_CTRL1		= 0x3c,
+	PF1550_PMIC_REG_SW3_VOLT		= 0x3e,
+	PF1550_PMIC_REG_SW3_STBY_VOLT		= 0x3f,
+	PF1550_PMIC_REG_SW3_SLP_VOLT		= 0x40,
+	PF1550_PMIC_REG_SW3_CTRL		= 0x41,
+	PF1550_PMIC_REG_SW3_CTRL1		= 0x42,
+	PF1550_PMIC_REG_VSNVS_CTRL		= 0x48,
+	PF1550_PMIC_REG_VREFDDR_CTRL		= 0x4a,
+	PF1550_PMIC_REG_LDO1_VOLT		= 0x4c,
+	PF1550_PMIC_REG_LDO1_CTRL		= 0x4d,
+	PF1550_PMIC_REG_LDO2_VOLT		= 0x4f,
+	PF1550_PMIC_REG_LDO2_CTRL		= 0x50,
+	PF1550_PMIC_REG_LDO3_VOLT		= 0x52,
+	PF1550_PMIC_REG_LDO3_CTRL		= 0x53,
+	PF1550_PMIC_REG_PWRCTRL0		= 0x58,
+	PF1550_PMIC_REG_PWRCTRL1		= 0x59,
+	PF1550_PMIC_REG_PWRCTRL2		= 0x5a,
+	PF1550_PMIC_REG_PWRCTRL3		= 0x5b,
+	PF1550_PMIC_REG_SW1_PWRDN_SEQ		= 0x5f,
+	PF1550_PMIC_REG_SW2_PWRDN_SEQ		= 0x60,
+	PF1550_PMIC_REG_SW3_PWRDN_SEQ		= 0x61,
+	PF1550_PMIC_REG_LDO1_PWRDN_SEQ		= 0x62,
+	PF1550_PMIC_REG_LDO2_PWRDN_SEQ		= 0x63,
+	PF1550_PMIC_REG_LDO3_PWRDN_SEQ		= 0x64,
+	PF1550_PMIC_REG_VREFDDR_PWRDN_SEQ	= 0x65,
+
+	PF1550_PMIC_REG_STATE_INFO		= 0x67,
+	PF1550_PMIC_REG_I2C_ADDR		= 0x68,
+	PF1550_PMIC_REG_IO_DRV0			= 0x69,
+	PF1550_PMIC_REG_IO_DRV1			= 0x6a,
+	PF1550_PMIC_REG_RC_16MHZ		= 0x6b,
+	PF1550_PMIC_REG_KEY			= 0x6f,
+
+	/* Charger part */
+	PF1550_CHARG_REG_CHG_INT		= 0x80,
+	PF1550_CHARG_REG_CHG_INT_MASK		= 0x82,
+	PF1550_CHARG_REG_CHG_INT_OK		= 0x84,
+	PF1550_CHARG_REG_VBUS_SNS		= 0x86,
+	PF1550_CHARG_REG_CHG_SNS		= 0x87,
+	PF1550_CHARG_REG_BATT_SNS		= 0x88,
+	PF1550_CHARG_REG_CHG_OPER		= 0x89,
+	PF1550_CHARG_REG_CHG_TMR		= 0x8a,
+	PF1550_CHARG_REG_CHG_EOC_CNFG		= 0x8d,
+	PF1550_CHARG_REG_CHG_CURR_CNFG		= 0x8e,
+	PF1550_CHARG_REG_BATT_REG		= 0x8f,
+	PF1550_CHARG_REG_BATFET_CNFG		= 0x91,
+	PF1550_CHARG_REG_THM_REG_CNFG		= 0x92,
+	PF1550_CHARG_REG_VBUS_INLIM_CNFG	= 0x94,
+	PF1550_CHARG_REG_VBUS_LIN_DPM		= 0x95,
+	PF1550_CHARG_REG_USB_PHY_LDO_CNFG	= 0x96,
+	PF1550_CHARG_REG_DBNC_DELAY_TIME	= 0x98,
+	PF1550_CHARG_REG_CHG_INT_CNFG		= 0x99,
+	PF1550_CHARG_REG_THM_ADJ_SETTING	= 0x9a,
+	PF1550_CHARG_REG_VBUS2SYS_CNFG		= 0x9b,
+	PF1550_CHARG_REG_LED_PWM		= 0x9c,
+	PF1550_CHARG_REG_FAULT_BATFET_CNFG	= 0x9d,
+	PF1550_CHARG_REG_LED_CNFG		= 0x9e,
+	PF1550_CHARG_REG_CHGR_KEY2		= 0x9f,
+
+	PF1550_TEST_REG_FMRADDR			= 0xc4,
+	PF1550_TEST_REG_FMRDATA			= 0xc5,
+	PF1550_TEST_REG_KEY3			= 0xdf,
+
+	PF1550_PMIC_REG_END			= 0xff,
+};
+
+/* One-Time Programmable(OTP) memory */
+enum pf1550_otp_reg {
+	PF1550_OTP_SW1_SW2			= 0x1e,
+	PF1550_OTP_SW2_SW3			= 0x1f,
+};
+
+#define PF1550_DEVICE_ID		0x7c
+
+/* Keys for reading OTP */
+#define PF1550_OTP_PMIC_KEY		0x15
+#define PF1550_OTP_CHGR_KEY		0x50
+#define PF1550_OTP_TEST_KEY		0xab
+
+/* Supported charger modes */
+#define PF1550_CHG_BAT_OFF		1
+#define PF1550_CHG_BAT_ON		2
+
+#define PF1550_CHG_PRECHARGE		0
+#define PF1550_CHG_CONSTANT_CURRENT	1
+#define PF1550_CHG_CONSTANT_VOL		2
+#define PF1550_CHG_EOC			3
+#define PF1550_CHG_DONE			4
+#define PF1550_CHG_TIMER_FAULT		6
+#define PF1550_CHG_SUSPEND		7
+#define PF1550_CHG_OFF_INV		8
+#define PF1550_CHG_BAT_OVER		9
+#define PF1550_CHG_OFF_TEMP		10
+#define PF1550_CHG_LINEAR_ONLY		12
+#define PF1550_CHG_SNS_MASK		0xf
+#define PF1550_CHG_INT_MASK		0x51
+
+#define PF1550_BAT_NO_VBUS		0
+#define PF1550_BAT_LOW_THAN_PRECHARG	1
+#define PF1550_BAT_CHARG_FAIL		2
+#define PF1550_BAT_HIGH_THAN_PRECHARG	4
+#define PF1550_BAT_OVER_VOL		5
+#define PF1550_BAT_NO_DETECT		6
+#define PF1550_BAT_SNS_MASK		0x7
+
+#define PF1550_VBUS_UVLO		BIT(2)
+#define PF1550_VBUS_IN2SYS		BIT(3)
+#define PF1550_VBUS_OVLO		BIT(4)
+#define PF1550_VBUS_VALID		BIT(5)
+
+#define PF1550_CHARG_REG_BATT_REG_CHGCV_MASK		0x3f
+#define PF1550_CHARG_REG_BATT_REG_VMINSYS_SHIFT		6
+#define PF1550_CHARG_REG_BATT_REG_VMINSYS_MASK		GENMASK(7, 6)
+#define PF1550_CHARG_REG_THM_REG_CNFG_REGTEMP_SHIFT	2
+#define PF1550_CHARG_REG_THM_REG_CNFG_REGTEMP_MASK	GENMASK(3, 2)
+
+#define PF1550_ONKEY_RST_EN		BIT(7)
+
+/* DVS enable masks */
+#define OTP_SW1_DVS_ENB		BIT(1)
+#define OTP_SW2_DVS_ENB		BIT(3)
+
+/* Top level interrupt masks */
+#define IRQ_REGULATOR		(BIT(1) | BIT(2) | BIT(3) | BIT(4) | BIT(6))
+#define IRQ_ONKEY		BIT(5)
+#define IRQ_CHG			BIT(0)
+
+/* Regulator interrupt masks */
+#define PMIC_IRQ_SW1_LS		BIT(0)
+#define PMIC_IRQ_SW2_LS		BIT(1)
+#define PMIC_IRQ_SW3_LS		BIT(2)
+#define PMIC_IRQ_SW1_HS		BIT(0)
+#define PMIC_IRQ_SW2_HS		BIT(1)
+#define PMIC_IRQ_SW3_HS		BIT(2)
+#define PMIC_IRQ_LDO1_FAULT	BIT(0)
+#define PMIC_IRQ_LDO2_FAULT	BIT(1)
+#define PMIC_IRQ_LDO3_FAULT	BIT(2)
+#define PMIC_IRQ_TEMP_110	BIT(0)
+#define PMIC_IRQ_TEMP_125	BIT(1)
+
+/* Onkey interrupt masks */
+#define ONKEY_IRQ_PUSHI		BIT(0)
+#define ONKEY_IRQ_1SI		BIT(1)
+#define ONKEY_IRQ_2SI		BIT(2)
+#define ONKEY_IRQ_3SI		BIT(3)
+#define ONKEY_IRQ_4SI		BIT(4)
+#define ONKEY_IRQ_8SI		BIT(5)
+
+/* Charger interrupt masks */
+#define CHARG_IRQ_BAT2SOCI	BIT(1)
+#define CHARG_IRQ_BATI		BIT(2)
+#define CHARG_IRQ_CHGI		BIT(3)
+#define CHARG_IRQ_VBUSI		BIT(5)
+#define CHARG_IRQ_DPMI		BIT(6)
+#define CHARG_IRQ_THMI		BIT(7)
+
+enum pf1550_irq {
+	PF1550_IRQ_CHG,
+	PF1550_IRQ_REGULATOR,
+	PF1550_IRQ_ONKEY,
+};
+
+enum pf1550_pmic_irq {
+	PF1550_PMIC_IRQ_SW1_LS,
+	PF1550_PMIC_IRQ_SW2_LS,
+	PF1550_PMIC_IRQ_SW3_LS,
+	PF1550_PMIC_IRQ_SW1_HS,
+	PF1550_PMIC_IRQ_SW2_HS,
+	PF1550_PMIC_IRQ_SW3_HS,
+	PF1550_PMIC_IRQ_LDO1_FAULT,
+	PF1550_PMIC_IRQ_LDO2_FAULT,
+	PF1550_PMIC_IRQ_LDO3_FAULT,
+	PF1550_PMIC_IRQ_TEMP_110,
+	PF1550_PMIC_IRQ_TEMP_125,
+};
+
+enum pf1550_onkey_irq {
+	PF1550_ONKEY_IRQ_PUSHI,
+	PF1550_ONKEY_IRQ_1SI,
+	PF1550_ONKEY_IRQ_2SI,
+	PF1550_ONKEY_IRQ_3SI,
+	PF1550_ONKEY_IRQ_4SI,
+	PF1550_ONKEY_IRQ_8SI,
+};
+
+enum pf1550_charg_irq {
+	PF1550_CHARG_IRQ_BAT2SOCI,
+	PF1550_CHARG_IRQ_BATI,
+	PF1550_CHARG_IRQ_CHGI,
+	PF1550_CHARG_IRQ_VBUSI,
+	PF1550_CHARG_IRQ_THMI,
+};
+
+enum pf1550_regulators {
+	PF1550_SW1,
+	PF1550_SW2,
+	PF1550_SW3,
+	PF1550_VREFDDR,
+	PF1550_LDO1,
+	PF1550_LDO2,
+	PF1550_LDO3,
+};
+
+struct pf1550_ddata {
+	struct regmap_irq_chip_data *irq_data_regulator;
+	struct regmap_irq_chip_data *irq_data_charger;
+	struct regmap_irq_chip_data *irq_data_onkey;
+	struct regmap_irq_chip_data *irq_data;
+	struct regmap *regmap;
+	struct device *dev;
+	bool dvs1_enable;
+	bool dvs2_enable;
+	int irq;
+};
+
+#endif /* __LINUX_MFD_PF1550_H */
diff --git a/include/linux/mfd/qnap-mcu.h b/include/linux/mfd/qnap-mcu.h
new file mode 100644
index 000000000000..42bf523f9a5b
--- /dev/null
+++ b/include/linux/mfd/qnap-mcu.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Core definitions for QNAP MCU MFD driver.
+ * Copyright (C) 2024 Heiko Stuebner <heiko@sntech.de>
+ */
+
+#ifndef _LINUX_QNAP_MCU_H_
+#define _LINUX_QNAP_MCU_H_
+
+#include <linux/types.h>
+
+struct qnap_mcu;
+
+struct qnap_mcu_variant {
+	u32 baud_rate;
+	int num_drives;
+	int fan_pwm_min;
+	int fan_pwm_max;
+	bool usb_led;
+};
+
+int qnap_mcu_exec(struct qnap_mcu *mcu,
+		  const u8 *cmd_data, size_t cmd_data_size,
+		  u8 *reply_data, size_t reply_data_size);
+int qnap_mcu_exec_with_ack(struct qnap_mcu *mcu,
+			   const u8 *cmd_data, size_t cmd_data_size);
+
+#endif /* _LINUX_QNAP_MCU_H_ */
diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h
index 9af1f3105f80..28170ee08898 100644
--- a/include/linux/mfd/rk808.h
+++ b/include/linux/mfd/rk808.h
@@ -113,6 +113,148 @@ enum rk808_reg {
 #define RK808_INT_STS_MSK_REG2	0x4f
 #define RK808_IO_POL_REG	0x50
 
+/* RK816 */
+enum rk816_reg {
+	RK816_ID_DCDC1,
+	RK816_ID_DCDC2,
+	RK816_ID_DCDC3,
+	RK816_ID_DCDC4,
+	RK816_ID_LDO1,
+	RK816_ID_LDO2,
+	RK816_ID_LDO3,
+	RK816_ID_LDO4,
+	RK816_ID_LDO5,
+	RK816_ID_LDO6,
+	RK816_ID_BOOST,
+	RK816_ID_OTG_SW,
+};
+
+enum rk816_irqs {
+	/* INT_STS_REG1 */
+	RK816_IRQ_PWRON_FALL,
+	RK816_IRQ_PWRON_RISE,
+
+	/* INT_STS_REG2 */
+	RK816_IRQ_VB_LOW,
+	RK816_IRQ_PWRON,
+	RK816_IRQ_PWRON_LP,
+	RK816_IRQ_HOTDIE,
+	RK816_IRQ_RTC_ALARM,
+	RK816_IRQ_RTC_PERIOD,
+	RK816_IRQ_USB_OV,
+
+	/* INT_STS_REG3 */
+	RK816_IRQ_PLUG_IN,
+	RK816_IRQ_PLUG_OUT,
+	RK816_IRQ_CHG_OK,
+	RK816_IRQ_CHG_TE,
+	RK816_IRQ_CHG_TS,
+	RK816_IRQ_CHG_CVTLIM,
+	RK816_IRQ_DISCHG_ILIM,
+};
+
+/* power channel registers */
+#define RK816_DCDC_EN_REG1		0x23
+
+#define RK816_DCDC_EN_REG2		0x24
+#define	RK816_BOOST_EN			BIT(1)
+#define RK816_OTG_EN			BIT(2)
+#define	RK816_BOOST_EN_MSK		BIT(5)
+#define RK816_OTG_EN_MSK		BIT(6)
+#define RK816_BUCK_DVS_CONFIRM		BIT(7)
+
+#define RK816_LDO_EN_REG1		0x27
+
+#define RK816_LDO_EN_REG2		0x28
+
+/* interrupt registers and irq definitions */
+#define RK816_INT_STS_REG1		0x49
+#define RK816_INT_STS_MSK_REG1		0x4a
+#define RK816_INT_STS_PWRON_FALL	BIT(5)
+#define RK816_INT_STS_PWRON_RISE	BIT(6)
+
+#define RK816_INT_STS_REG2		0x4c
+#define RK816_INT_STS_MSK_REG2		0x4d
+#define RK816_INT_STS_VB_LOW		BIT(1)
+#define RK816_INT_STS_PWRON		BIT(2)
+#define RK816_INT_STS_PWRON_LP		BIT(3)
+#define RK816_INT_STS_HOTDIE		BIT(4)
+#define RK816_INT_STS_RTC_ALARM		BIT(5)
+#define RK816_INT_STS_RTC_PERIOD	BIT(6)
+#define RK816_INT_STS_USB_OV		BIT(7)
+
+#define RK816_INT_STS_REG3		0x4e
+#define RK816_INT_STS_MSK_REG3		0x4f
+#define RK816_INT_STS_PLUG_IN		BIT(0)
+#define RK816_INT_STS_PLUG_OUT		BIT(1)
+#define RK816_INT_STS_CHG_OK		BIT(2)
+#define RK816_INT_STS_CHG_TE		BIT(3)
+#define RK816_INT_STS_CHG_TS		BIT(4)
+#define RK816_INT_STS_CHG_CVTLIM	BIT(6)
+#define RK816_INT_STS_DISCHG_ILIM	BIT(7)
+
+#define RK816_IRQ_STS_OFFSET(x)		((x) - RK816_INT_STS_REG1)
+#define RK816_IRQ_MSK_OFFSET(x)		((x) - RK816_INT_STS_MSK_REG1)
+
+/* charger, boost and OTG registers */
+#define RK816_OTG_BUCK_LDO_CONFIG_REG	0x2a
+#define RK816_CHRG_CONFIG_REG		0x2b
+#define RK816_BOOST_ON_VESL_REG		0x54
+#define RK816_BOOST_SLP_VSEL_REG	0x55
+#define RK816_CHRG_BOOST_CONFIG_REG	0x9a
+#define RK816_SUP_STS_REG		0xa0
+#define RK816_USB_CTRL_REG		0xa1
+#define RK816_CHRG_CTRL(x)		(0xa3 + (x))
+#define RK816_BAT_CTRL_REG		0xa6
+#define RK816_BAT_HTS_TS_REG		0xa8
+#define RK816_BAT_LTS_TS_REG		0xa9
+
+/* adc and fuel gauge registers */
+#define RK816_TS_CTRL_REG		0xac
+#define RK816_ADC_CTRL_REG		0xad
+#define RK816_GGCON_REG			0xb0
+#define RK816_GGSTS_REG			0xb1
+#define RK816_ZERO_CUR_ADC_REGH		0xb2
+#define RK816_ZERO_CUR_ADC_REGL		0xb3
+#define RK816_GASCNT_CAL_REG(x)		(0xb7 - (x))
+#define RK816_GASCNT_REG(x)		(0xbb - (x))
+#define RK816_BAT_CUR_AVG_REGH		0xbc
+#define RK816_BAT_CUR_AVG_REGL		0xbd
+#define RK816_TS_ADC_REGH		0xbe
+#define RK816_TS_ADC_REGL		0xbf
+#define RK816_USB_ADC_REGH		0xc0
+#define RK816_USB_ADC_REGL		0xc1
+#define RK816_BAT_OCV_REGH		0xc2
+#define RK816_BAT_OCV_REGL		0xc3
+#define RK816_BAT_VOL_REGH		0xc4
+#define RK816_BAT_VOL_REGL		0xc5
+#define RK816_RELAX_ENTRY_THRES_REGH	0xc6
+#define RK816_RELAX_ENTRY_THRES_REGL	0xc7
+#define RK816_RELAX_EXIT_THRES_REGH	0xc8
+#define RK816_RELAX_EXIT_THRES_REGL	0xc9
+#define RK816_RELAX_VOL1_REGH		0xca
+#define RK816_RELAX_VOL1_REGL		0xcb
+#define RK816_RELAX_VOL2_REGH		0xcc
+#define RK816_RELAX_VOL2_REGL		0xcd
+#define RK816_RELAX_CUR1_REGH		0xce
+#define RK816_RELAX_CUR1_REGL		0xcf
+#define RK816_RELAX_CUR2_REGH		0xd0
+#define RK816_RELAX_CUR2_REGL		0xd1
+#define RK816_CAL_OFFSET_REGH		0xd2
+#define RK816_CAL_OFFSET_REGL		0xd3
+#define RK816_NON_ACT_TIMER_CNT_REG	0xd4
+#define RK816_VCALIB0_REGH		0xd5
+#define RK816_VCALIB0_REGL		0xd6
+#define RK816_VCALIB1_REGH		0xd7
+#define RK816_VCALIB1_REGL		0xd8
+#define RK816_FCC_GASCNT_REG(x)		(0xdc - (x))
+#define RK816_IOFFSET_REGH		0xdd
+#define RK816_IOFFSET_REGL		0xde
+#define RK816_SLEEP_CON_SAMP_CUR_REG	0xdf
+
+/* general purpose data registers 0xe0 ~ 0xf2 */
+#define RK816_DATA_REG(x)		(0xe0 + (x))
+
 /* RK818 */
 #define RK818_DCDC1			0
 #define RK818_LDO1			4
@@ -289,6 +431,416 @@ enum rk805_reg {
 #define RK805_INT_ALARM_EN		(1 << 3)
 #define RK805_INT_TIMER_EN		(1 << 2)
 
+/* RK806 */
+#define RK806_POWER_EN0			0x0
+#define RK806_POWER_EN1			0x1
+#define RK806_POWER_EN2			0x2
+#define RK806_POWER_EN3			0x3
+#define RK806_POWER_EN4			0x4
+#define RK806_POWER_EN5			0x5
+#define RK806_POWER_SLP_EN0		0x6
+#define RK806_POWER_SLP_EN1		0x7
+#define RK806_POWER_SLP_EN2		0x8
+#define RK806_POWER_DISCHRG_EN0		0x9
+#define RK806_POWER_DISCHRG_EN1		0xA
+#define RK806_POWER_DISCHRG_EN2		0xB
+#define RK806_BUCK_FB_CONFIG		0xC
+#define RK806_SLP_LP_CONFIG		0xD
+#define RK806_POWER_FPWM_EN0		0xE
+#define RK806_POWER_FPWM_EN1		0xF
+#define RK806_BUCK1_CONFIG		0x10
+#define RK806_BUCK2_CONFIG		0x11
+#define RK806_BUCK3_CONFIG		0x12
+#define RK806_BUCK4_CONFIG		0x13
+#define RK806_BUCK5_CONFIG		0x14
+#define RK806_BUCK6_CONFIG		0x15
+#define RK806_BUCK7_CONFIG		0x16
+#define RK806_BUCK8_CONFIG		0x17
+#define RK806_BUCK9_CONFIG		0x18
+#define RK806_BUCK10_CONFIG		0x19
+#define RK806_BUCK1_ON_VSEL		0x1A
+#define RK806_BUCK2_ON_VSEL		0x1B
+#define RK806_BUCK3_ON_VSEL		0x1C
+#define RK806_BUCK4_ON_VSEL		0x1D
+#define RK806_BUCK5_ON_VSEL		0x1E
+#define RK806_BUCK6_ON_VSEL		0x1F
+#define RK806_BUCK7_ON_VSEL		0x20
+#define RK806_BUCK8_ON_VSEL		0x21
+#define RK806_BUCK9_ON_VSEL		0x22
+#define RK806_BUCK10_ON_VSEL		0x23
+#define RK806_BUCK1_SLP_VSEL		0x24
+#define RK806_BUCK2_SLP_VSEL		0x25
+#define RK806_BUCK3_SLP_VSEL		0x26
+#define RK806_BUCK4_SLP_VSEL		0x27
+#define RK806_BUCK5_SLP_VSEL		0x28
+#define RK806_BUCK6_SLP_VSEL		0x29
+#define RK806_BUCK7_SLP_VSEL		0x2A
+#define RK806_BUCK8_SLP_VSEL		0x2B
+#define RK806_BUCK9_SLP_VSEL		0x2D
+#define RK806_BUCK10_SLP_VSEL		0x2E
+#define RK806_BUCK_DEBUG1		0x30
+#define RK806_BUCK_DEBUG2		0x31
+#define RK806_BUCK_DEBUG3		0x32
+#define RK806_BUCK_DEBUG4		0x33
+#define RK806_BUCK_DEBUG5		0x34
+#define RK806_BUCK_DEBUG6		0x35
+#define RK806_BUCK_DEBUG7		0x36
+#define RK806_BUCK_DEBUG8		0x37
+#define RK806_BUCK_DEBUG9		0x38
+#define RK806_BUCK_DEBUG10		0x39
+#define RK806_BUCK_DEBUG11		0x3A
+#define RK806_BUCK_DEBUG12		0x3B
+#define RK806_BUCK_DEBUG13		0x3C
+#define RK806_BUCK_DEBUG14		0x3D
+#define RK806_BUCK_DEBUG15		0x3E
+#define RK806_BUCK_DEBUG16		0x3F
+#define RK806_BUCK_DEBUG17		0x40
+#define RK806_BUCK_DEBUG18		0x41
+#define RK806_NLDO_IMAX			0x42
+#define RK806_NLDO1_ON_VSEL		0x43
+#define RK806_NLDO2_ON_VSEL		0x44
+#define RK806_NLDO3_ON_VSEL		0x45
+#define RK806_NLDO4_ON_VSEL		0x46
+#define RK806_NLDO5_ON_VSEL		0x47
+#define RK806_NLDO1_SLP_VSEL		0x48
+#define RK806_NLDO2_SLP_VSEL		0x49
+#define RK806_NLDO3_SLP_VSEL		0x4A
+#define RK806_NLDO4_SLP_VSEL		0x4B
+#define RK806_NLDO5_SLP_VSEL		0x4C
+#define RK806_PLDO_IMAX			0x4D
+#define RK806_PLDO1_ON_VSEL		0x4E
+#define RK806_PLDO2_ON_VSEL		0x4F
+#define RK806_PLDO3_ON_VSEL		0x50
+#define RK806_PLDO4_ON_VSEL		0x51
+#define RK806_PLDO5_ON_VSEL		0x52
+#define RK806_PLDO6_ON_VSEL		0x53
+#define RK806_PLDO1_SLP_VSEL		0x54
+#define RK806_PLDO2_SLP_VSEL		0x55
+#define RK806_PLDO3_SLP_VSEL		0x56
+#define RK806_PLDO4_SLP_VSEL		0x57
+#define RK806_PLDO5_SLP_VSEL		0x58
+#define RK806_PLDO6_SLP_VSEL		0x59
+#define RK806_CHIP_NAME			0x5A
+#define RK806_CHIP_VER			0x5B
+#define RK806_OTP_VER			0x5C
+#define RK806_SYS_STS			0x5D
+#define RK806_SYS_CFG0			0x5E
+#define RK806_SYS_CFG1			0x5F
+#define RK806_SYS_OPTION		0x61
+#define RK806_SLEEP_CONFIG0		0x62
+#define RK806_SLEEP_CONFIG1		0x63
+#define RK806_SLEEP_CTR_SEL0		0x64
+#define RK806_SLEEP_CTR_SEL1		0x65
+#define RK806_SLEEP_CTR_SEL2		0x66
+#define RK806_SLEEP_CTR_SEL3		0x67
+#define RK806_SLEEP_CTR_SEL4		0x68
+#define RK806_SLEEP_CTR_SEL5		0x69
+#define RK806_DVS_CTRL_SEL0		0x6A
+#define RK806_DVS_CTRL_SEL1		0x6B
+#define RK806_DVS_CTRL_SEL2		0x6C
+#define RK806_DVS_CTRL_SEL3		0x6D
+#define RK806_DVS_CTRL_SEL4		0x6E
+#define RK806_DVS_CTRL_SEL5		0x6F
+#define RK806_DVS_START_CTRL		0x70
+#define RK806_SLEEP_GPIO		0x71
+#define RK806_SYS_CFG3			0x72
+#define RK806_ON_SOURCE			0x74
+#define RK806_OFF_SOURCE		0x75
+#define RK806_PWRON_KEY			0x76
+#define RK806_INT_STS0			0x77
+#define RK806_INT_MSK0			0x78
+#define RK806_INT_STS1			0x79
+#define RK806_INT_MSK1			0x7A
+#define RK806_GPIO_INT_CONFIG		0x7B
+#define RK806_DATA_REG0			0x7C
+#define RK806_DATA_REG1			0x7D
+#define RK806_DATA_REG2			0x7E
+#define RK806_DATA_REG3			0x7F
+#define RK806_DATA_REG4			0x80
+#define RK806_DATA_REG5			0x81
+#define RK806_DATA_REG6			0x82
+#define RK806_DATA_REG7			0x83
+#define RK806_DATA_REG8			0x84
+#define RK806_DATA_REG9			0x85
+#define RK806_DATA_REG10		0x86
+#define RK806_DATA_REG11		0x87
+#define RK806_DATA_REG12		0x88
+#define RK806_DATA_REG13		0x89
+#define RK806_DATA_REG14		0x8A
+#define RK806_DATA_REG15		0x8B
+#define RK806_TM_REG			0x8C
+#define RK806_OTP_EN_REG		0x8D
+#define RK806_FUNC_OTP_EN_REG		0x8E
+#define RK806_TEST_REG1			0x8F
+#define RK806_TEST_REG2			0x90
+#define RK806_TEST_REG3			0x91
+#define RK806_TEST_REG4			0x92
+#define RK806_TEST_REG5			0x93
+#define RK806_BUCK_VSEL_OTP_REG0	0x94
+#define RK806_BUCK_VSEL_OTP_REG1	0x95
+#define RK806_BUCK_VSEL_OTP_REG2	0x96
+#define RK806_BUCK_VSEL_OTP_REG3	0x97
+#define RK806_BUCK_VSEL_OTP_REG4	0x98
+#define RK806_BUCK_VSEL_OTP_REG5	0x99
+#define RK806_BUCK_VSEL_OTP_REG6	0x9A
+#define RK806_BUCK_VSEL_OTP_REG7	0x9B
+#define RK806_BUCK_VSEL_OTP_REG8	0x9C
+#define RK806_BUCK_VSEL_OTP_REG9	0x9D
+#define RK806_NLDO1_VSEL_OTP_REG0	0x9E
+#define RK806_NLDO1_VSEL_OTP_REG1	0x9F
+#define RK806_NLDO1_VSEL_OTP_REG2	0xA0
+#define RK806_NLDO1_VSEL_OTP_REG3	0xA1
+#define RK806_NLDO1_VSEL_OTP_REG4	0xA2
+#define RK806_PLDO_VSEL_OTP_REG0	0xA3
+#define RK806_PLDO_VSEL_OTP_REG1	0xA4
+#define RK806_PLDO_VSEL_OTP_REG2	0xA5
+#define RK806_PLDO_VSEL_OTP_REG3	0xA6
+#define RK806_PLDO_VSEL_OTP_REG4	0xA7
+#define RK806_PLDO_VSEL_OTP_REG5	0xA8
+#define RK806_BUCK_EN_OTP_REG1		0xA9
+#define RK806_NLDO_EN_OTP_REG1		0xAA
+#define RK806_PLDO_EN_OTP_REG1		0xAB
+#define RK806_BUCK_FB_RES_OTP_REG1	0xAC
+#define RK806_OTP_RESEV_REG0		0xAD
+#define RK806_OTP_RESEV_REG1		0xAE
+#define RK806_OTP_RESEV_REG2		0xAF
+#define RK806_OTP_RESEV_REG3		0xB0
+#define RK806_OTP_RESEV_REG4		0xB1
+#define RK806_BUCK_SEQ_REG0		0xB2
+#define RK806_BUCK_SEQ_REG1		0xB3
+#define RK806_BUCK_SEQ_REG2		0xB4
+#define RK806_BUCK_SEQ_REG3		0xB5
+#define RK806_BUCK_SEQ_REG4		0xB6
+#define RK806_BUCK_SEQ_REG5		0xB7
+#define RK806_BUCK_SEQ_REG6		0xB8
+#define RK806_BUCK_SEQ_REG7		0xB9
+#define RK806_BUCK_SEQ_REG8		0xBA
+#define RK806_BUCK_SEQ_REG9		0xBB
+#define RK806_BUCK_SEQ_REG10		0xBC
+#define RK806_BUCK_SEQ_REG11		0xBD
+#define RK806_BUCK_SEQ_REG12		0xBE
+#define RK806_BUCK_SEQ_REG13		0xBF
+#define RK806_BUCK_SEQ_REG14		0xC0
+#define RK806_BUCK_SEQ_REG15		0xC1
+#define RK806_BUCK_SEQ_REG16		0xC2
+#define RK806_BUCK_SEQ_REG17		0xC3
+#define RK806_HK_TRIM_REG1		0xC4
+#define RK806_HK_TRIM_REG2		0xC5
+#define RK806_BUCK_REF_TRIM_REG1	0xC6
+#define RK806_BUCK_REF_TRIM_REG2	0xC7
+#define RK806_BUCK_REF_TRIM_REG3	0xC8
+#define RK806_BUCK_REF_TRIM_REG4	0xC9
+#define RK806_BUCK_REF_TRIM_REG5	0xCA
+#define RK806_BUCK_OSC_TRIM_REG1	0xCB
+#define RK806_BUCK_OSC_TRIM_REG2	0xCC
+#define RK806_BUCK_OSC_TRIM_REG3	0xCD
+#define RK806_BUCK_OSC_TRIM_REG4	0xCE
+#define RK806_BUCK_OSC_TRIM_REG5	0xCF
+#define RK806_BUCK_TRIM_ZCDIOS_REG1	0xD0
+#define RK806_BUCK_TRIM_ZCDIOS_REG2	0xD1
+#define RK806_NLDO_TRIM_REG1		0xD2
+#define RK806_NLDO_TRIM_REG2		0xD3
+#define RK806_NLDO_TRIM_REG3		0xD4
+#define RK806_PLDO_TRIM_REG1		0xD5
+#define RK806_PLDO_TRIM_REG2		0xD6
+#define RK806_PLDO_TRIM_REG3		0xD7
+#define RK806_TRIM_ICOMP_REG1		0xD8
+#define RK806_TRIM_ICOMP_REG2		0xD9
+#define RK806_EFUSE_CONTROL_REGH	0xDA
+#define RK806_FUSE_PROG_REG		0xDB
+#define RK806_MAIN_FSM_STS_REG		0xDD
+#define RK806_FSM_REG			0xDE
+#define RK806_TOP_RESEV_OFFR		0xEC
+#define RK806_TOP_RESEV_POR		0xED
+#define RK806_BUCK_VRSN_REG1		0xEE
+#define RK806_BUCK_VRSN_REG2		0xEF
+#define RK806_NLDO_RLOAD_SEL_REG1	0xF0
+#define RK806_PLDO_RLOAD_SEL_REG1	0xF1
+#define RK806_PLDO_RLOAD_SEL_REG2	0xF2
+#define RK806_BUCK_CMIN_MX_REG1		0xF3
+#define RK806_BUCK_CMIN_MX_REG2		0xF4
+#define RK806_BUCK_FREQ_SET_REG1	0xF5
+#define RK806_BUCK_FREQ_SET_REG2	0xF6
+#define RK806_BUCK_RS_MEABS_REG1	0xF7
+#define RK806_BUCK_RS_MEABS_REG2	0xF8
+#define RK806_BUCK_RS_ZDLEB_REG1	0xF9
+#define RK806_BUCK_RS_ZDLEB_REG2	0xFA
+#define RK806_BUCK_RSERVE_REG1		0xFB
+#define RK806_BUCK_RSERVE_REG2		0xFC
+#define RK806_BUCK_RSERVE_REG3		0xFD
+#define RK806_BUCK_RSERVE_REG4		0xFE
+#define RK806_BUCK_RSERVE_REG5		0xFF
+
+/* INT_STS Register field definitions */
+#define RK806_INT_STS_PWRON_FALL	BIT(0)
+#define RK806_INT_STS_PWRON_RISE	BIT(1)
+#define RK806_INT_STS_PWRON		BIT(2)
+#define RK806_INT_STS_PWRON_LP		BIT(3)
+#define RK806_INT_STS_HOTDIE		BIT(4)
+#define RK806_INT_STS_VDC_RISE		BIT(5)
+#define RK806_INT_STS_VDC_FALL		BIT(6)
+#define RK806_INT_STS_VB_LO		BIT(7)
+#define RK806_INT_STS_REV0		BIT(0)
+#define RK806_INT_STS_REV1		BIT(1)
+#define RK806_INT_STS_REV2		BIT(2)
+#define RK806_INT_STS_CRC_ERROR		BIT(3)
+#define RK806_INT_STS_SLP3_GPIO		BIT(4)
+#define RK806_INT_STS_SLP2_GPIO		BIT(5)
+#define RK806_INT_STS_SLP1_GPIO		BIT(6)
+#define RK806_INT_STS_WDT		BIT(7)
+
+/* SPI command */
+#define RK806_CMD_READ			0
+#define RK806_CMD_WRITE			BIT(7)
+#define RK806_CMD_CRC_EN		BIT(6)
+#define RK806_CMD_CRC_DIS		0
+#define RK806_CMD_LEN_MSK		0x0f
+#define RK806_REG_H			0x00
+
+#define VERSION_AB		0x01
+
+enum rk806_reg_id {
+	RK806_ID_DCDC1 = 0,
+	RK806_ID_DCDC2,
+	RK806_ID_DCDC3,
+	RK806_ID_DCDC4,
+	RK806_ID_DCDC5,
+	RK806_ID_DCDC6,
+	RK806_ID_DCDC7,
+	RK806_ID_DCDC8,
+	RK806_ID_DCDC9,
+	RK806_ID_DCDC10,
+
+	RK806_ID_NLDO1,
+	RK806_ID_NLDO2,
+	RK806_ID_NLDO3,
+	RK806_ID_NLDO4,
+	RK806_ID_NLDO5,
+
+	RK806_ID_PLDO1,
+	RK806_ID_PLDO2,
+	RK806_ID_PLDO3,
+	RK806_ID_PLDO4,
+	RK806_ID_PLDO5,
+	RK806_ID_PLDO6,
+	RK806_ID_END,
+};
+
+/* Define the RK806 IRQ numbers */
+enum rk806_irqs {
+	/* INT_STS0 registers */
+	RK806_IRQ_PWRON_FALL,
+	RK806_IRQ_PWRON_RISE,
+	RK806_IRQ_PWRON,
+	RK806_IRQ_PWRON_LP,
+	RK806_IRQ_HOTDIE,
+	RK806_IRQ_VDC_RISE,
+	RK806_IRQ_VDC_FALL,
+	RK806_IRQ_VB_LO,
+
+	/* INT_STS0 registers */
+	RK806_IRQ_REV0,
+	RK806_IRQ_REV1,
+	RK806_IRQ_REV2,
+	RK806_IRQ_CRC_ERROR,
+	RK806_IRQ_SLP3_GPIO,
+	RK806_IRQ_SLP2_GPIO,
+	RK806_IRQ_SLP1_GPIO,
+	RK806_IRQ_WDT,
+};
+
+/* VCC1 Low Voltage Threshold */
+enum rk806_lv_sel {
+	VB_LO_SEL_2800,
+	VB_LO_SEL_2900,
+	VB_LO_SEL_3000,
+	VB_LO_SEL_3100,
+	VB_LO_SEL_3200,
+	VB_LO_SEL_3300,
+	VB_LO_SEL_3400,
+	VB_LO_SEL_3500,
+};
+
+/* System Shutdown Voltage Select */
+enum rk806_uv_sel {
+	VB_UV_SEL_2700,
+	VB_UV_SEL_2800,
+	VB_UV_SEL_2900,
+	VB_UV_SEL_3000,
+	VB_UV_SEL_3100,
+	VB_UV_SEL_3200,
+	VB_UV_SEL_3300,
+	VB_UV_SEL_3400,
+};
+
+/* Pin Function */
+enum rk806_pwrctrl_fun {
+	PWRCTRL_NULL_FUN,
+	PWRCTRL_SLP_FUN,
+	PWRCTRL_POWOFF_FUN,
+	PWRCTRL_RST_FUN,
+	PWRCTRL_DVS_FUN,
+	PWRCTRL_GPIO_FUN,
+};
+
+/* Pin Polarity */
+enum rk806_pin_level {
+	POL_LOW,
+	POL_HIGH,
+};
+
+enum rk806_vsel_ctr_sel {
+	CTR_BY_NO_EFFECT,
+	CTR_BY_PWRCTRL1,
+	CTR_BY_PWRCTRL2,
+	CTR_BY_PWRCTRL3,
+};
+
+enum rk806_dvs_ctr_sel {
+	CTR_SEL_NO_EFFECT,
+	CTR_SEL_DVS_START1,
+	CTR_SEL_DVS_START2,
+	CTR_SEL_DVS_START3,
+};
+
+enum rk806_pin_dr_sel {
+	RK806_PIN_INPUT,
+	RK806_PIN_OUTPUT,
+};
+
+#define RK806_INT_POL_MSK		BIT(1)
+#define RK806_INT_POL_H			BIT(1)
+#define RK806_INT_POL_L			0
+
+/* SYS_CFG3 */
+#define RK806_RST_FUN_MSK		GENMASK(7, 6)
+#define RK806_SLAVE_RESTART_FUN_MSK	BIT(1)
+#define RK806_SLAVE_RESTART_FUN_EN	BIT(1)
+#define RK806_SLAVE_RESTART_FUN_OFF	0
+
+#define RK806_SYS_ENB2_2M_MSK		BIT(1)
+#define RK806_SYS_ENB2_2M_EN		BIT(1)
+#define RK806_SYS_ENB2_2M_OFF		0
+
+enum rk806_int_fun {
+	RK806_INT_ONLY,
+	RK806_INT_ADN_WKUP,
+};
+
+enum rk806_dvs_mode {
+	RK806_DVS_NOT_SUPPORT,
+	RK806_DVS_START1,
+	RK806_DVS_START2,
+	RK806_DVS_START3,
+	RK806_DVS_PWRCTRL1,
+	RK806_DVS_PWRCTRL2,
+	RK806_DVS_PWRCTRL3,
+	RK806_DVS_START_PWRCTR1,
+	RK806_DVS_START_PWRCTR2,
+	RK806_DVS_START_PWRCTR3,
+	RK806_DVS_END,
+};
+
 /* RK808 IRQ Definitions */
 #define RK808_IRQ_VOUT_LO	0
 #define RK808_IRQ_VB_LO		1
@@ -383,6 +935,7 @@ enum rk805_reg {
 #define VOUT_LO_INT	BIT(0)
 #define CLK32KOUT2_EN	BIT(0)
 
+#define TEMP105C			0x08
 #define TEMP115C			0x0c
 #define TEMP_HOTDIE_MSK			0x0c
 #define SLP_SD_MSK			(0x3 << 2)
@@ -780,18 +1333,26 @@ enum {
 
 enum {
 	RK805_ID = 0x8050,
+	RK806_ID = 0x8060,
 	RK808_ID = 0x0000,
 	RK809_ID = 0x8090,
+	RK816_ID = 0x8160,
 	RK817_ID = 0x8170,
 	RK818_ID = 0x8180,
 };
 
 struct rk808 {
-	struct i2c_client		*i2c;
+	struct device			*dev;
 	struct regmap_irq_chip_data	*irq_data;
 	struct regmap			*regmap;
 	long				variant;
 	const struct regmap_config	*regmap_cfg;
 	const struct regmap_irq_chip	*regmap_irq_chip;
 };
+
+void rk8xx_shutdown(struct device *dev);
+int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap *regmap);
+int rk8xx_suspend(struct device *dev);
+int rk8xx_resume(struct device *dev);
+
 #endif /* __LINUX_REGULATOR_RK808_H */
diff --git a/include/linux/mfd/rohm-bd71828.h b/include/linux/mfd/rohm-bd71828.h
index 3b5f3a7db4bd..73a71ef69152 100644
--- a/include/linux/mfd/rohm-bd71828.h
+++ b/include/linux/mfd/rohm-bd71828.h
@@ -4,6 +4,7 @@
 #ifndef __LINUX_MFD_BD71828_H__
 #define __LINUX_MFD_BD71828_H__
 
+#include <linux/bits.h>
 #include <linux/mfd/rohm-generic.h>
 #include <linux/mfd/rohm-shared.h>
 
@@ -41,7 +42,8 @@ enum {
 #define BD71828_REG_PS_CTRL_2		0x05
 #define BD71828_REG_PS_CTRL_3		0x06
 
-//#define BD71828_REG_SWRESET		0x06
+#define BD71828_MASK_STATE_HBNT		BIT(1)
+
 #define BD71828_MASK_RUN_LVL_CTRL	0x30
 
 /* Regulator control masks */
@@ -133,7 +135,6 @@ enum {
 #define BD71828_REG_LDO5_VOLT		0x43
 #define BD71828_REG_LDO5_VOLT_OPT	0x42
 #define BD71828_REG_LDO6_EN		0x44
-//#define BD71828_REG_LDO6_VOLT		0x4
 #define BD71828_REG_LDO7_EN		0x45
 #define BD71828_REG_LDO7_VOLT		0x46
 
@@ -188,6 +189,69 @@ enum {
 /* Charger/Battey */
 #define BD71828_REG_CHG_STATE		0x65
 #define BD71828_REG_CHG_FULL		0xd2
+#define BD71828_REG_CHG_EN		0x6F
+#define BD71828_REG_DCIN_STAT		0x68
+#define BD71828_MASK_DCIN_DET		0x01
+#define BD71828_REG_VDCIN_U		0x9c
+#define BD71828_MASK_CHG_EN		0x01
+#define BD71828_CHG_MASK_DCIN_U		0x0f
+#define BD71828_REG_BAT_STAT		0x67
+#define BD71828_REG_BAT_TEMP		0x6c
+#define BD71828_MASK_BAT_TEMP		0x07
+#define BD71828_BAT_TEMP_OPEN		0x07
+#define BD71828_MASK_BAT_DET		0x20
+#define BD71828_MASK_BAT_DET_DONE	0x10
+#define BD71828_REG_CHG_STATE		0x65
+#define BD71828_REG_VBAT_U		0x8c
+#define BD71828_MASK_VBAT_U		0x0f
+#define BD71828_REG_VBAT_REX_AVG_U	0x92
+
+#define BD71828_REG_OCV_PWRON_U		0x8A
+
+#define BD71828_REG_VBAT_MIN_AVG_U	0x8e
+#define BD71828_REG_VBAT_MIN_AVG_L	0x8f
+
+#define BD71828_REG_CC_CNT3		0xb5
+#define BD71828_REG_CC_CNT2		0xb6
+#define BD71828_REG_CC_CNT1		0xb7
+#define BD71828_REG_CC_CNT0		0xb8
+#define BD71828_REG_CC_CURCD_AVG_U	0xb2
+#define BD71828_MASK_CC_CURCD_AVG_U	0x3f
+#define BD71828_MASK_CC_CUR_DIR		0x80
+#define BD71828_REG_VM_BTMP_U		0xa1
+#define BD71828_REG_VM_BTMP_L		0xa2
+#define BD71828_MASK_VM_BTMP_U		0x0f
+#define BD71828_REG_COULOMB_CTRL	0xc4
+#define BD71828_REG_COULOMB_CTRL2	0xd2
+#define BD71828_MASK_REX_CC_CLR		0x01
+#define BD71828_MASK_FULL_CC_CLR	0x10
+#define BD71828_REG_CC_CNT_FULL3	0xbd
+#define BD71828_REG_CC_CNT_CHG3		0xc1
+
+#define BD71828_REG_VBAT_INITIAL1_U	0x86
+#define BD71828_REG_VBAT_INITIAL1_L	0x87
+
+#define BD71828_REG_VBAT_INITIAL2_U	0x88
+#define BD71828_REG_VBAT_INITIAL2_L	0x89
+
+#define BD71828_REG_IBAT_U		0xb0
+#define BD71828_REG_IBAT_L		0xb1
+
+#define BD71828_REG_IBAT_AVG_U		0xb2
+#define BD71828_REG_IBAT_AVG_L		0xb3
+
+#define BD71828_REG_VSYS_AVG_U		0x96
+#define BD71828_REG_VSYS_AVG_L		0x97
+#define BD71828_REG_VSYS_MIN_AVG_U	0x98
+#define BD71828_REG_VSYS_MIN_AVG_L	0x99
+#define BD71828_REG_CHG_SET1		0x75
+#define BD71828_REG_ALM_VBAT_LIMIT_U	0xaa
+#define BD71828_REG_BATCAP_MON_LIMIT_U	0xcc
+#define BD71828_REG_CONF		0x64
+
+#define BD71828_REG_DCIN_CLPS		0x71
+
+#define BD71828_REG_MEAS_CLEAR		0xaf
 
 /* LEDs */
 #define BD71828_REG_LED_CTRL		0x4A
diff --git a/include/linux/mfd/rohm-bd96801.h b/include/linux/mfd/rohm-bd96801.h
new file mode 100644
index 000000000000..68c8ac8ad409
--- /dev/null
+++ b/include/linux/mfd/rohm-bd96801.h
@@ -0,0 +1,217 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/* Copyright (C) 2024 ROHM Semiconductors */
+
+#ifndef __MFD_BD96801_H__
+#define __MFD_BD96801_H__
+
+#define BD96801_REG_SSCG_CTRL		0x09
+#define BD96801_REG_SHD_INTB            0x20
+#define BD96801_LDO5_VOL_LVL_REG	0x2c
+#define BD96801_LDO6_VOL_LVL_REG	0x2d
+#define BD96801_LDO7_VOL_LVL_REG	0x2e
+#define BD96801_REG_BUCK_OVP		0x30
+#define BD96801_REG_BUCK_OVD		0x35
+#define BD96801_REG_LDO_OVP		0x31
+#define BD96801_REG_LDO_OVD		0x36
+#define BD96801_REG_BOOT_OVERTIME	0x3a
+#define BD96801_REG_WD_TMO		0x40
+#define BD96801_REG_WD_CONF		0x41
+#define BD96801_REG_WD_FEED		0x42
+#define BD96801_REG_WD_FAILCOUNT	0x43
+#define BD96801_REG_WD_ASK		0x46
+#define BD96801_REG_WD_STATUS		0x4a
+#define BD96801_REG_PMIC_STATE		0x4f
+#define BD96801_REG_EXT_STATE		0x50
+
+#define BD96801_STATE_STBY		0x09
+
+#define BD96801_LOCK_REG		0x04
+#define BD96801_UNLOCK			0x9d
+#define BD96801_LOCK			0x00
+
+/* IRQ register area */
+#define BD96801_REG_INT_MAIN		0x51
+
+/*
+ * The BD96801 has two physical IRQ lines, INTB and ERRB.
+ *
+ * The 'main status register' is located at 0x51.
+ * The ERRB status registers are located at 0x52 ... 0x5B
+ * INTB status registers are at range 0x5c ... 0x63
+ */
+#define BD96801_REG_INT_SYS_ERRB1	0x52
+#define BD96801_REG_INT_BUCK2_ERRB	0x56
+#define BD96801_REG_INT_SYS_INTB	0x5c
+#define BD96801_REG_INT_BUCK2_INTB	0x5e
+#define BD96801_REG_INT_LDO7_INTB	0x63
+
+/* MASK registers */
+#define BD96801_REG_MASK_SYS_INTB	0x73
+#define BD96801_REG_MASK_SYS_ERRB	0x69
+
+#define BD96801_MAX_REGISTER		0x7a
+
+#define BD96801_OTP_ERR_MASK		BIT(0)
+#define BD96801_DBIST_ERR_MASK		BIT(1)
+#define BD96801_EEP_ERR_MASK		BIT(2)
+#define BD96801_ABIST_ERR_MASK		BIT(3)
+#define BD96801_PRSTB_ERR_MASK		BIT(4)
+#define BD96801_DRMOS1_ERR_MASK		BIT(5)
+#define BD96801_DRMOS2_ERR_MASK		BIT(6)
+#define BD96801_SLAVE_ERR_MASK		BIT(7)
+#define BD96801_VREF_ERR_MASK		BIT(0)
+#define BD96801_TSD_ERR_MASK		BIT(1)
+#define BD96801_UVLO_ERR_MASK		BIT(2)
+#define BD96801_OVLO_ERR_MASK		BIT(3)
+#define BD96801_OSC_ERR_MASK		BIT(4)
+#define BD96801_PON_ERR_MASK		BIT(5)
+#define BD96801_POFF_ERR_MASK		BIT(6)
+#define BD96801_CMD_SHDN_ERR_MASK	BIT(7)
+#define BD96801_INT_PRSTB_WDT_ERR_MASK	BIT(0)
+#define BD96801_INT_CHIP_IF_ERR_MASK	BIT(3)
+#define BD96801_INT_SHDN_ERR_MASK	BIT(7)
+#define BD96801_OUT_PVIN_ERR_MASK	BIT(0)
+#define BD96801_OUT_OVP_ERR_MASK	BIT(1)
+#define BD96801_OUT_UVP_ERR_MASK	BIT(2)
+#define BD96801_OUT_SHDN_ERR_MASK	BIT(7)
+
+/* ERRB IRQs */
+enum {
+	/* Reg 0x52, 0x53, 0x54 - ERRB system IRQs */
+	BD96801_OTP_ERR_STAT,
+	BD96801_DBIST_ERR_STAT,
+	BD96801_EEP_ERR_STAT,
+	BD96801_ABIST_ERR_STAT,
+	BD96801_PRSTB_ERR_STAT,
+	BD96801_DRMOS1_ERR_STAT,
+	BD96801_DRMOS2_ERR_STAT,
+	BD96801_SLAVE_ERR_STAT,
+	BD96801_VREF_ERR_STAT,
+	BD96801_TSD_ERR_STAT,
+	BD96801_UVLO_ERR_STAT,
+	BD96801_OVLO_ERR_STAT,
+	BD96801_OSC_ERR_STAT,
+	BD96801_PON_ERR_STAT,
+	BD96801_POFF_ERR_STAT,
+	BD96801_CMD_SHDN_ERR_STAT,
+	BD96801_INT_PRSTB_WDT_ERR,
+	BD96801_INT_CHIP_IF_ERR,
+	BD96801_INT_SHDN_ERR_STAT,
+
+	/* Reg 0x55 BUCK1 ERR IRQs */
+	BD96801_BUCK1_PVIN_ERR_STAT,
+	BD96801_BUCK1_OVP_ERR_STAT,
+	BD96801_BUCK1_UVP_ERR_STAT,
+	BD96801_BUCK1_SHDN_ERR_STAT,
+
+	/* Reg 0x56 BUCK2 ERR IRQs */
+	BD96801_BUCK2_PVIN_ERR_STAT,
+	BD96801_BUCK2_OVP_ERR_STAT,
+	BD96801_BUCK2_UVP_ERR_STAT,
+	BD96801_BUCK2_SHDN_ERR_STAT,
+
+	/* Reg 0x57 BUCK3 ERR IRQs */
+	BD96801_BUCK3_PVIN_ERR_STAT,
+	BD96801_BUCK3_OVP_ERR_STAT,
+	BD96801_BUCK3_UVP_ERR_STAT,
+	BD96801_BUCK3_SHDN_ERR_STAT,
+
+	/* Reg 0x58 BUCK4 ERR IRQs */
+	BD96801_BUCK4_PVIN_ERR_STAT,
+	BD96801_BUCK4_OVP_ERR_STAT,
+	BD96801_BUCK4_UVP_ERR_STAT,
+	BD96801_BUCK4_SHDN_ERR_STAT,
+
+	/* Reg 0x59 LDO5 ERR IRQs */
+	BD96801_LDO5_PVIN_ERR_STAT,
+	BD96801_LDO5_OVP_ERR_STAT,
+	BD96801_LDO5_UVP_ERR_STAT,
+	BD96801_LDO5_SHDN_ERR_STAT,
+
+	/* Reg 0x5a LDO6 ERR IRQs */
+	BD96801_LDO6_PVIN_ERR_STAT,
+	BD96801_LDO6_OVP_ERR_STAT,
+	BD96801_LDO6_UVP_ERR_STAT,
+	BD96801_LDO6_SHDN_ERR_STAT,
+
+	/* Reg 0x5b LDO7 ERR IRQs */
+	BD96801_LDO7_PVIN_ERR_STAT,
+	BD96801_LDO7_OVP_ERR_STAT,
+	BD96801_LDO7_UVP_ERR_STAT,
+	BD96801_LDO7_SHDN_ERR_STAT,
+};
+
+/* INTB IRQs */
+enum {
+	/* Reg 0x5c (System INTB) */
+	BD96801_TW_STAT,
+	BD96801_WDT_ERR_STAT,
+	BD96801_I2C_ERR_STAT,
+	BD96801_CHIP_IF_ERR_STAT,
+
+	/* Reg 0x5d (BUCK1 INTB) */
+	BD96801_BUCK1_OCPH_STAT,
+	BD96801_BUCK1_OCPL_STAT,
+	BD96801_BUCK1_OCPN_STAT,
+	BD96801_BUCK1_OVD_STAT,
+	BD96801_BUCK1_UVD_STAT,
+	BD96801_BUCK1_TW_CH_STAT,
+
+	/* Reg 0x5e (BUCK2 INTB) */
+	BD96801_BUCK2_OCPH_STAT,
+	BD96801_BUCK2_OCPL_STAT,
+	BD96801_BUCK2_OCPN_STAT,
+	BD96801_BUCK2_OVD_STAT,
+	BD96801_BUCK2_UVD_STAT,
+	BD96801_BUCK2_TW_CH_STAT,
+
+	/* Reg 0x5f (BUCK3 INTB)*/
+	BD96801_BUCK3_OCPH_STAT,
+	BD96801_BUCK3_OCPL_STAT,
+	BD96801_BUCK3_OCPN_STAT,
+	BD96801_BUCK3_OVD_STAT,
+	BD96801_BUCK3_UVD_STAT,
+	BD96801_BUCK3_TW_CH_STAT,
+
+	/* Reg 0x60 (BUCK4 INTB)*/
+	BD96801_BUCK4_OCPH_STAT,
+	BD96801_BUCK4_OCPL_STAT,
+	BD96801_BUCK4_OCPN_STAT,
+	BD96801_BUCK4_OVD_STAT,
+	BD96801_BUCK4_UVD_STAT,
+	BD96801_BUCK4_TW_CH_STAT,
+
+	/* Reg 0x61 (LDO5 INTB) */
+	BD96801_LDO5_OCPH_STAT, /* bit [0] */
+	BD96801_LDO5_OVD_STAT,	/* bit [3] */
+	BD96801_LDO5_UVD_STAT,  /* bit [4] */
+
+	/* Reg 0x62 (LDO6 INTB) */
+	BD96801_LDO6_OCPH_STAT, /* bit [0] */
+	BD96801_LDO6_OVD_STAT,	/* bit [3] */
+	BD96801_LDO6_UVD_STAT,  /* bit [4] */
+
+	/* Reg 0x63 (LDO7 INTB) */
+	BD96801_LDO7_OCPH_STAT, /* bit [0] */
+	BD96801_LDO7_OVD_STAT,	/* bit [3] */
+	BD96801_LDO7_UVD_STAT,  /* bit [4] */
+};
+
+/* IRQ MASKs */
+#define BD96801_TW_STAT_MASK		BIT(0)
+#define BD96801_WDT_ERR_STAT_MASK	BIT(1)
+#define BD96801_I2C_ERR_STAT_MASK	BIT(2)
+#define BD96801_CHIP_IF_ERR_STAT_MASK	BIT(3)
+
+#define BD96801_BUCK_OCPH_STAT_MASK	BIT(0)
+#define BD96801_BUCK_OCPL_STAT_MASK	BIT(1)
+#define BD96801_BUCK_OCPN_STAT_MASK	BIT(2)
+#define BD96801_BUCK_OVD_STAT_MASK	BIT(3)
+#define BD96801_BUCK_UVD_STAT_MASK	BIT(4)
+#define BD96801_BUCK_TW_CH_STAT_MASK	BIT(5)
+
+#define BD96801_LDO_OCPH_STAT_MASK	BIT(0)
+#define BD96801_LDO_OVD_STAT_MASK	BIT(3)
+#define BD96801_LDO_UVD_STAT_MASK	BIT(4)
+
+#endif
diff --git a/include/linux/mfd/rohm-bd96802.h b/include/linux/mfd/rohm-bd96802.h
new file mode 100644
index 000000000000..bf4b77944edf
--- /dev/null
+++ b/include/linux/mfd/rohm-bd96802.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Copyright (C) 2025 ROHM Semiconductors
+ *
+ * The digital interface of trhe BD96802 PMIC is a reduced version of the
+ * BD96801. Hence the BD96801 definitions are used for registers and masks
+ * while this header only holds the IRQ definitions - mainly to avoid gaps in
+ * IRQ numbers caused by the lack of some BUCKs / LDOs and their respective
+ * IRQs.
+ */
+
+#ifndef __LINUX_MFD_BD96802_H__
+#define __LINUX_MFD_BD96802_H__
+
+/* ERRB IRQs */
+enum {
+	/* Reg 0x52, 0x53, 0x54 - ERRB system IRQs */
+	BD96802_OTP_ERR_STAT,
+	BD96802_DBIST_ERR_STAT,
+	BD96802_EEP_ERR_STAT,
+	BD96802_ABIST_ERR_STAT,
+	BD96802_PRSTB_ERR_STAT,
+	BD96802_DRMOS1_ERR_STAT,
+	BD96802_DRMOS2_ERR_STAT,
+	BD96802_SLAVE_ERR_STAT,
+	BD96802_VREF_ERR_STAT,
+	BD96802_TSD_ERR_STAT,
+	BD96802_UVLO_ERR_STAT,
+	BD96802_OVLO_ERR_STAT,
+	BD96802_OSC_ERR_STAT,
+	BD96802_PON_ERR_STAT,
+	BD96802_POFF_ERR_STAT,
+	BD96802_CMD_SHDN_ERR_STAT,
+	BD96802_INT_SHDN_ERR_STAT,
+
+	/* Reg 0x55 BUCK1 ERR IRQs */
+	BD96802_BUCK1_PVIN_ERR_STAT,
+	BD96802_BUCK1_OVP_ERR_STAT,
+	BD96802_BUCK1_UVP_ERR_STAT,
+	BD96802_BUCK1_SHDN_ERR_STAT,
+
+	/* Reg 0x56 BUCK2 ERR IRQs */
+	BD96802_BUCK2_PVIN_ERR_STAT,
+	BD96802_BUCK2_OVP_ERR_STAT,
+	BD96802_BUCK2_UVP_ERR_STAT,
+	BD96802_BUCK2_SHDN_ERR_STAT,
+};
+
+/* INTB IRQs */
+enum {
+	/* Reg 0x5c (System INTB) */
+	BD96802_TW_STAT,
+	BD96802_WDT_ERR_STAT,
+	BD96802_I2C_ERR_STAT,
+	BD96802_CHIP_IF_ERR_STAT,
+
+	/* Reg 0x5d (BUCK1 INTB) */
+	BD96802_BUCK1_OCPH_STAT,
+	BD96802_BUCK1_OCPL_STAT,
+	BD96802_BUCK1_OCPN_STAT,
+	BD96802_BUCK1_OVD_STAT,
+	BD96802_BUCK1_UVD_STAT,
+	BD96802_BUCK1_TW_CH_STAT,
+
+	/* Reg 0x5e (BUCK2 INTB) */
+	BD96802_BUCK2_OCPH_STAT,
+	BD96802_BUCK2_OCPL_STAT,
+	BD96802_BUCK2_OCPN_STAT,
+	BD96802_BUCK2_OVD_STAT,
+	BD96802_BUCK2_UVD_STAT,
+	BD96802_BUCK2_TW_CH_STAT,
+};
+
+#endif
diff --git a/include/linux/mfd/rohm-generic.h b/include/linux/mfd/rohm-generic.h
index 4eeb22876bad..579e8dcfcca4 100644
--- a/include/linux/mfd/rohm-generic.h
+++ b/include/linux/mfd/rohm-generic.h
@@ -16,6 +16,10 @@ enum rohm_chip_type {
 	ROHM_CHIP_TYPE_BD71828,
 	ROHM_CHIP_TYPE_BD71837,
 	ROHM_CHIP_TYPE_BD71847,
+	ROHM_CHIP_TYPE_BD96801,
+	ROHM_CHIP_TYPE_BD96802,
+	ROHM_CHIP_TYPE_BD96805,
+	ROHM_CHIP_TYPE_BD96806,
 	ROHM_CHIP_TYPE_AMOUNT
 };
 
diff --git a/include/linux/mfd/rt5033-private.h b/include/linux/mfd/rt5033-private.h
index 6bb432f6a96c..0221f806d139 100644
--- a/include/linux/mfd/rt5033-private.h
+++ b/include/linux/mfd/rt5033-private.h
@@ -55,21 +55,28 @@ enum rt5033_reg {
 };
 
 /* RT5033 Charger state register */
-#define RT5033_CHG_STAT_MASK		0x20
+#define RT5033_CHG_STAT_TYPE_MASK	0x60
+#define RT5033_CHG_STAT_TYPE_PRE	0x20
+#define RT5033_CHG_STAT_TYPE_FAST	0x60
+#define RT5033_CHG_STAT_MASK		0x30
 #define RT5033_CHG_STAT_DISCHARGING	0x00
 #define RT5033_CHG_STAT_FULL		0x10
 #define RT5033_CHG_STAT_CHARGING	0x20
 #define RT5033_CHG_STAT_NOT_CHARGING	0x30
-#define RT5033_CHG_STAT_TYPE_MASK	0x60
-#define RT5033_CHG_STAT_TYPE_PRE	0x20
-#define RT5033_CHG_STAT_TYPE_FAST	0x60
 
 /* RT5033 CHGCTRL1 register */
 #define RT5033_CHGCTRL1_IAICR_MASK	0xe0
+#define RT5033_CHGCTRL1_TE_EN_MASK	0x08
+#define RT5033_CHGCTRL1_HZ_MASK		0x02
 #define RT5033_CHGCTRL1_MODE_MASK	0x01
 
 /* RT5033 CHGCTRL2 register */
 #define RT5033_CHGCTRL2_CV_MASK		0xfc
+#define RT5033_CHGCTRL2_CV_SHIFT	0x02
+
+/* RT5033 DEVICE_ID register */
+#define RT5033_VENDOR_ID_MASK		0xf0
+#define RT5033_CHIP_REV_MASK		0x0f
 
 /* RT5033 CHGCTRL3 register */
 #define RT5033_CHGCTRL3_CFO_EN_MASK	0x40
@@ -77,18 +84,18 @@ enum rt5033_reg {
 #define RT5033_CHGCTRL3_TIMER_EN_MASK	0x01
 
 /* RT5033 CHGCTRL4 register */
-#define RT5033_CHGCTRL4_EOC_MASK	0x07
+#define RT5033_CHGCTRL4_MIVR_MASK	0xe0
 #define RT5033_CHGCTRL4_IPREC_MASK	0x18
+#define RT5033_CHGCTRL4_IPREC_SHIFT	0x03
+#define RT5033_CHGCTRL4_EOC_MASK	0x07
 
 /* RT5033 CHGCTRL5 register */
-#define RT5033_CHGCTRL5_VPREC_MASK	0x0f
 #define RT5033_CHGCTRL5_ICHG_MASK	0xf0
 #define RT5033_CHGCTRL5_ICHG_SHIFT	0x04
-#define RT5033_CHG_MAX_CURRENT		0x0d
+#define RT5033_CHGCTRL5_VPREC_MASK	0x0f
 
 /* RT5033 RT CTRL1 register */
 #define RT5033_RT_CTRL1_UUG_MASK	0x02
-#define RT5033_RT_HZ_MASK		0x01
 
 /* RT5033 control register */
 #define RT5033_CTRL_FCCM_BUCK_MASK		BIT(0)
@@ -115,28 +122,37 @@ enum rt5033_reg {
  * register), AICR mode limits the input current. For example, the AIRC 100
  * mode limits the input current to 100 mA.
  */
+#define RT5033_AICR_DISABLE			0x00
 #define RT5033_AICR_100_MODE			0x20
 #define RT5033_AICR_500_MODE			0x40
 #define RT5033_AICR_700_MODE			0x60
 #define RT5033_AICR_900_MODE			0x80
+#define RT5033_AICR_1000_MODE			0xa0
 #define RT5033_AICR_1500_MODE			0xc0
 #define RT5033_AICR_2000_MODE			0xe0
-#define RT5033_AICR_MODE_MASK			0xe0
 
-/* RT5033 use internal timer need to set time */
-#define RT5033_FAST_CHARGE_TIMER4		0x00
-#define RT5033_FAST_CHARGE_TIMER6		0x01
-#define RT5033_FAST_CHARGE_TIMER8		0x02
-#define RT5033_FAST_CHARGE_TIMER9		0x03
-#define RT5033_FAST_CHARGE_TIMER12		0x04
-#define RT5033_FAST_CHARGE_TIMER14		0x05
-#define RT5033_FAST_CHARGE_TIMER16		0x06
+/* RT5033 charger minimum input voltage regulation */
+#define RT5033_CHARGER_MIVR_DISABLE		0x00
+#define RT5033_CHARGER_MIVR_4200MV		0x20
+#define RT5033_CHARGER_MIVR_4300MV		0x40
+#define RT5033_CHARGER_MIVR_4400MV		0x60
+#define RT5033_CHARGER_MIVR_4500MV		0x80
+#define RT5033_CHARGER_MIVR_4600MV		0xa0
+#define RT5033_CHARGER_MIVR_4700MV		0xc0
+#define RT5033_CHARGER_MIVR_4800MV		0xe0
 
+/* RT5033 use internal timer need to set time */
+#define RT5033_FAST_CHARGE_TIMER4		0x00 /*  4 hrs */
+#define RT5033_FAST_CHARGE_TIMER6		0x08 /*  6 hrs */
+#define RT5033_FAST_CHARGE_TIMER8		0x10 /*  8 hrs */
+#define RT5033_FAST_CHARGE_TIMER10		0x18 /* 10 hrs */
+#define RT5033_FAST_CHARGE_TIMER12		0x20 /* 12 hrs */
+#define RT5033_FAST_CHARGE_TIMER14		0x28 /* 14 hrs */
+#define RT5033_FAST_CHARGE_TIMER16		0x30 /* 16 hrs */
+
+#define RT5033_INT_TIMER_DISABLE		0x00
 #define RT5033_INT_TIMER_ENABLE			0x01
 
-/* RT5033 charger termination enable mask */
-#define RT5033_TE_ENABLE_MASK			0x08
-
 /*
  * RT5033 charger opa mode. RT5033 has two opa modes for OTG: charger mode
  * and boost mode.
@@ -145,25 +161,30 @@ enum rt5033_reg {
 #define RT5033_BOOST_MODE			0x01
 
 /* RT5033 charger termination enable */
+#define RT5033_TE_DISABLE			0x00
 #define RT5033_TE_ENABLE			0x08
 
 /* RT5033 charger CFO enable */
+#define RT5033_CFO_DISABLE			0x00
 #define RT5033_CFO_ENABLE			0x40
 
 /* RT5033 charger constant charge voltage (as in CHGCTRL2 register), uV */
 #define RT5033_CHARGER_CONST_VOLTAGE_LIMIT_MIN	3650000U
 #define RT5033_CHARGER_CONST_VOLTAGE_STEP_NUM   25000U
 #define RT5033_CHARGER_CONST_VOLTAGE_LIMIT_MAX	4400000U
+#define RT5033_CV_MAX_VOLTAGE			0x1e
 
 /* RT5033 charger pre-charge current limits (as in CHGCTRL4 register), uA */
 #define RT5033_CHARGER_PRE_CURRENT_LIMIT_MIN	350000U
 #define RT5033_CHARGER_PRE_CURRENT_STEP_NUM	100000U
 #define RT5033_CHARGER_PRE_CURRENT_LIMIT_MAX	650000U
+#define RT5033_CHG_MAX_PRE_CURRENT		0x03
 
 /* RT5033 charger fast-charge current (as in CHGCTRL5 register), uA */
 #define RT5033_CHARGER_FAST_CURRENT_MIN		700000U
 #define RT5033_CHARGER_FAST_CURRENT_STEP_NUM	100000U
 #define RT5033_CHARGER_FAST_CURRENT_MAX		2000000U
+#define RT5033_CHG_MAX_CURRENT			0x0d
 
 /*
  * RT5033 charger const-charge end of charger current (
@@ -187,11 +208,12 @@ enum rt5033_reg {
  * RT5033 charger UUG. It enables MOS auto control by H/W charger
  * circuit.
  */
+#define RT5033_CHARGER_UUG_DISABLE		0x00
 #define RT5033_CHARGER_UUG_ENABLE		0x02
 
 /* RT5033 charger high impedance mode */
 #define RT5033_CHARGER_HZ_DISABLE		0x00
-#define RT5033_CHARGER_HZ_ENABLE		0x01
+#define RT5033_CHARGER_HZ_ENABLE		0x02
 
 /* RT5033 regulator BUCK output voltage uV */
 #define RT5033_REGULATOR_BUCK_VOLTAGE_MIN		1000000U
diff --git a/include/linux/mfd/rt5033.h b/include/linux/mfd/rt5033.h
index 8f306ac15a27..bb3d18945d21 100644
--- a/include/linux/mfd/rt5033.h
+++ b/include/linux/mfd/rt5033.h
@@ -12,7 +12,6 @@
 #include <linux/regulator/consumer.h>
 #include <linux/i2c.h>
 #include <linux/regmap.h>
-#include <linux/power_supply.h>
 
 /* RT5033 regulator IDs */
 enum rt5033_regulators {
@@ -32,27 +31,4 @@ struct rt5033_dev {
 	bool wakeup;
 };
 
-struct rt5033_battery {
-	struct i2c_client	*client;
-	struct rt5033_dev	*rt5033;
-	struct regmap		*regmap;
-	struct power_supply	*psy;
-};
-
-/* RT5033 charger platform data */
-struct rt5033_charger_data {
-	unsigned int pre_uamp;
-	unsigned int pre_uvolt;
-	unsigned int const_uvolt;
-	unsigned int eoc_uamp;
-	unsigned int fast_uamp;
-};
-
-struct rt5033_charger {
-	struct device			*dev;
-	struct rt5033_dev		*rt5033;
-	struct power_supply		psy;
-	struct rt5033_charger_data	*chg;
-};
-
 #endif /* __RT5033_H__ */
diff --git a/include/linux/mfd/rz-mtu3.h b/include/linux/mfd/rz-mtu3.h
index c5173bc06270..8421d49500bf 100644
--- a/include/linux/mfd/rz-mtu3.h
+++ b/include/linux/mfd/rz-mtu3.h
@@ -151,7 +151,6 @@ struct rz_mtu3 {
 	void *priv_data;
 };
 
-#if IS_ENABLED(CONFIG_RZ_MTU3)
 static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch)
 {
 	mutex_lock(&ch->lock);
@@ -188,70 +187,5 @@ void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val);
 void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val);
 void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch, u16 off,
 				   u16 pos, u8 val);
-#else
-static inline bool rz_mtu3_request_channel(struct rz_mtu3_channel *ch)
-{
-	return false;
-}
-
-static inline void rz_mtu3_release_channel(struct rz_mtu3_channel *ch)
-{
-}
-
-static inline bool rz_mtu3_is_enabled(struct rz_mtu3_channel *ch)
-{
-	return false;
-}
-
-static inline void rz_mtu3_disable(struct rz_mtu3_channel *ch)
-{
-}
-
-static inline int rz_mtu3_enable(struct rz_mtu3_channel *ch)
-{
-	return 0;
-}
-
-static inline u8 rz_mtu3_8bit_ch_read(struct rz_mtu3_channel *ch, u16 off)
-{
-	return 0;
-}
-
-static inline u16 rz_mtu3_16bit_ch_read(struct rz_mtu3_channel *ch, u16 off)
-{
-	return 0;
-}
-
-static inline u32 rz_mtu3_32bit_ch_read(struct rz_mtu3_channel *ch, u16 off)
-{
-	return 0;
-}
-
-static inline u16 rz_mtu3_shared_reg_read(struct rz_mtu3_channel *ch, u16 off)
-{
-	return 0;
-}
-
-static inline void rz_mtu3_8bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u8 val)
-{
-}
-
-static inline void rz_mtu3_16bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u16 val)
-{
-}
-
-static inline void rz_mtu3_32bit_ch_write(struct rz_mtu3_channel *ch, u16 off, u32 val)
-{
-}
-
-static inline void rz_mtu3_shared_reg_write(struct rz_mtu3_channel *ch, u16 off, u16 val)
-{
-}
-
-static inline void rz_mtu3_shared_reg_update_bit(struct rz_mtu3_channel *ch,
-						 u16 off, u16 pos, u8 val)
-{
-}
-#endif
 
 #endif /* __MFD_RZ_MTU3_H__ */
diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h
index a212b9f72bc9..d785e101fe79 100644
--- a/include/linux/mfd/samsung/core.h
+++ b/include/linux/mfd/samsung/core.h
@@ -37,12 +37,15 @@ struct gpio_desc;
 
 enum sec_device_type {
 	S5M8767X,
+	S2DOS05,
 	S2MPA01,
+	S2MPG10,
 	S2MPS11X,
 	S2MPS13X,
 	S2MPS14X,
 	S2MPS15X,
 	S2MPU02,
+	S2MPU05,
 };
 
 /**
@@ -64,15 +67,11 @@ struct sec_pmic_dev {
 	struct regmap *regmap_pmic;
 	struct i2c_client *i2c;
 
-	unsigned long device_type;
+	int device_type;
 	int irq;
 	struct regmap_irq_chip_data *irq_data;
 };
 
-int sec_irq_init(struct sec_pmic_dev *sec_pmic);
-void sec_irq_exit(struct sec_pmic_dev *sec_pmic);
-int sec_irq_resume(struct sec_pmic_dev *sec_pmic);
-
 struct sec_platform_data {
 	struct sec_regulator_data	*regulators;
 	struct sec_opmode_data		*opmode;
diff --git a/include/linux/mfd/samsung/irq.h b/include/linux/mfd/samsung/irq.h
index 3fd2775eb9bb..8402a5f8e18a 100644
--- a/include/linux/mfd/samsung/irq.h
+++ b/include/linux/mfd/samsung/irq.h
@@ -57,6 +57,115 @@ enum s2mpa01_irq {
 #define S2MPA01_IRQ_B24_TSD_MASK	(1 << 4)
 #define S2MPA01_IRQ_B35_TSD_MASK	(1 << 5)
 
+enum s2mpg10_common_irq {
+	/* Top-level (common) block */
+	S2MPG10_COMMON_IRQ_PMIC,
+	S2MPG10_COMMON_IRQ_UNUSED,
+};
+
+enum s2mpg10_irq {
+	/* PMIC */
+	S2MPG10_IRQ_PWRONF,
+	S2MPG10_IRQ_PWRONR,
+	S2MPG10_IRQ_JIGONBF,
+	S2MPG10_IRQ_JIGONBR,
+	S2MPG10_IRQ_ACOKBF,
+	S2MPG10_IRQ_ACOKBR,
+	S2MPG10_IRQ_PWRON1S,
+	S2MPG10_IRQ_MRB,
+#define S2MPG10_IRQ_PWRONF_MASK		BIT(0)
+#define S2MPG10_IRQ_PWRONR_MASK		BIT(1)
+#define S2MPG10_IRQ_JIGONBF_MASK	BIT(2)
+#define S2MPG10_IRQ_JIGONBR_MASK	BIT(3)
+#define S2MPG10_IRQ_ACOKBF_MASK		BIT(4)
+#define S2MPG10_IRQ_ACOKBR_MASK		BIT(5)
+#define S2MPG10_IRQ_PWRON1S_MASK	BIT(6)
+#define S2MPG10_IRQ_MRB_MASK		BIT(7)
+
+	S2MPG10_IRQ_RTC60S,
+	S2MPG10_IRQ_RTCA1,
+	S2MPG10_IRQ_RTCA0,
+	S2MPG10_IRQ_RTC1S,
+	S2MPG10_IRQ_WTSR_COLDRST,
+	S2MPG10_IRQ_WTSR,
+	S2MPG10_IRQ_WRST,
+	S2MPG10_IRQ_SMPL,
+#define S2MPG10_IRQ_RTC60S_MASK		BIT(0)
+#define S2MPG10_IRQ_RTCA1_MASK		BIT(1)
+#define S2MPG10_IRQ_RTCA0_MASK		BIT(2)
+#define S2MPG10_IRQ_RTC1S_MASK		BIT(3)
+#define S2MPG10_IRQ_WTSR_COLDRST_MASK	BIT(4)
+#define S2MPG10_IRQ_WTSR_MASK		BIT(5)
+#define S2MPG10_IRQ_WRST_MASK		BIT(6)
+#define S2MPG10_IRQ_SMPL_MASK		BIT(7)
+
+	S2MPG10_IRQ_120C,
+	S2MPG10_IRQ_140C,
+	S2MPG10_IRQ_TSD,
+	S2MPG10_IRQ_PIF_TIMEOUT1,
+	S2MPG10_IRQ_PIF_TIMEOUT2,
+	S2MPG10_IRQ_SPD_PARITY_ERR,
+	S2MPG10_IRQ_SPD_ABNORMAL_STOP,
+	S2MPG10_IRQ_PMETER_OVERF,
+#define S2MPG10_IRQ_INT120C_MASK		BIT(0)
+#define S2MPG10_IRQ_INT140C_MASK		BIT(1)
+#define S2MPG10_IRQ_TSD_MASK			BIT(2)
+#define S2MPG10_IRQ_PIF_TIMEOUT1_MASK		BIT(3)
+#define S2MPG10_IRQ_PIF_TIMEOUT2_MASK		BIT(4)
+#define S2MPG10_IRQ_SPD_PARITY_ERR_MASK		BIT(5)
+#define S2MPG10_IRQ_SPD_ABNORMAL_STOP_MASK	BIT(6)
+#define S2MPG10_IRQ_PMETER_OVERF_MASK		BIT(7)
+
+	S2MPG10_IRQ_OCP_B1M,
+	S2MPG10_IRQ_OCP_B2M,
+	S2MPG10_IRQ_OCP_B3M,
+	S2MPG10_IRQ_OCP_B4M,
+	S2MPG10_IRQ_OCP_B5M,
+	S2MPG10_IRQ_OCP_B6M,
+	S2MPG10_IRQ_OCP_B7M,
+	S2MPG10_IRQ_OCP_B8M,
+#define S2MPG10_IRQ_OCP_B1M_MASK	BIT(0)
+#define S2MPG10_IRQ_OCP_B2M_MASK	BIT(1)
+#define S2MPG10_IRQ_OCP_B3M_MASK	BIT(2)
+#define S2MPG10_IRQ_OCP_B4M_MASK	BIT(3)
+#define S2MPG10_IRQ_OCP_B5M_MASK	BIT(4)
+#define S2MPG10_IRQ_OCP_B6M_MASK	BIT(5)
+#define S2MPG10_IRQ_OCP_B7M_MASK	BIT(6)
+#define S2MPG10_IRQ_OCP_B8M_MASK	BIT(7)
+
+	S2MPG10_IRQ_OCP_B9M,
+	S2MPG10_IRQ_OCP_B10M,
+	S2MPG10_IRQ_WLWP_ACC,
+	S2MPG10_IRQ_SMPL_TIMEOUT,
+	S2MPG10_IRQ_WTSR_TIMEOUT,
+	S2MPG10_IRQ_SPD_SRP_PKT_RST,
+#define S2MPG10_IRQ_OCP_B9M_MASK		BIT(0)
+#define S2MPG10_IRQ_OCP_B10M_MASK		BIT(1)
+#define S2MPG10_IRQ_WLWP_ACC_MASK		BIT(2)
+#define S2MPG10_IRQ_SMPL_TIMEOUT_MASK		BIT(5)
+#define S2MPG10_IRQ_WTSR_TIMEOUT_MASK		BIT(6)
+#define S2MPG10_IRQ_SPD_SRP_PKT_RST_MASK	BIT(7)
+
+	S2MPG10_IRQ_PWR_WARN_CH0,
+	S2MPG10_IRQ_PWR_WARN_CH1,
+	S2MPG10_IRQ_PWR_WARN_CH2,
+	S2MPG10_IRQ_PWR_WARN_CH3,
+	S2MPG10_IRQ_PWR_WARN_CH4,
+	S2MPG10_IRQ_PWR_WARN_CH5,
+	S2MPG10_IRQ_PWR_WARN_CH6,
+	S2MPG10_IRQ_PWR_WARN_CH7,
+#define S2MPG10_IRQ_PWR_WARN_CH0_MASK	BIT(0)
+#define S2MPG10_IRQ_PWR_WARN_CH1_MASK	BIT(1)
+#define S2MPG10_IRQ_PWR_WARN_CH2_MASK	BIT(2)
+#define S2MPG10_IRQ_PWR_WARN_CH3_MASK	BIT(3)
+#define S2MPG10_IRQ_PWR_WARN_CH4_MASK	BIT(4)
+#define S2MPG10_IRQ_PWR_WARN_CH5_MASK	BIT(5)
+#define S2MPG10_IRQ_PWR_WARN_CH6_MASK	BIT(6)
+#define S2MPG10_IRQ_PWR_WARN_CH7_MASK	BIT(7)
+
+	S2MPG10_IRQ_NR,
+};
+
 enum s2mps11_irq {
 	S2MPS11_IRQ_PWRONF,
 	S2MPS11_IRQ_PWRONR,
@@ -150,6 +259,50 @@ enum s2mpu02_irq {
 /* Masks for interrupts are the same as in s2mps11 */
 #define S2MPS14_IRQ_TSD_MASK		(1 << 2)
 
+enum s2mpu05_irq {
+	S2MPU05_IRQ_PWRONF,
+	S2MPU05_IRQ_PWRONR,
+	S2MPU05_IRQ_JIGONBF,
+	S2MPU05_IRQ_JIGONBR,
+	S2MPU05_IRQ_ACOKF,
+	S2MPU05_IRQ_ACOKR,
+	S2MPU05_IRQ_PWRON1S,
+	S2MPU05_IRQ_MRB,
+
+	S2MPU05_IRQ_RTC60S,
+	S2MPU05_IRQ_RTCA1,
+	S2MPU05_IRQ_RTCA0,
+	S2MPU05_IRQ_SMPL,
+	S2MPU05_IRQ_RTC1S,
+	S2MPU05_IRQ_WTSR,
+
+	S2MPU05_IRQ_INT120C,
+	S2MPU05_IRQ_INT140C,
+	S2MPU05_IRQ_TSD,
+
+	S2MPU05_IRQ_NR,
+};
+
+#define S2MPU05_IRQ_PWRONF_MASK		BIT(0)
+#define S2MPU05_IRQ_PWRONR_MASK		BIT(1)
+#define S2MPU05_IRQ_JIGONBF_MASK	BIT(2)
+#define S2MPU05_IRQ_JIGONBR_MASK	BIT(3)
+#define S2MPU05_IRQ_ACOKF_MASK		BIT(4)
+#define S2MPU05_IRQ_ACOKR_MASK		BIT(5)
+#define S2MPU05_IRQ_PWRON1S_MASK	BIT(6)
+#define S2MPU05_IRQ_MRB_MASK		BIT(7)
+
+#define S2MPU05_IRQ_RTC60S_MASK		BIT(0)
+#define S2MPU05_IRQ_RTCA1_MASK		BIT(1)
+#define S2MPU05_IRQ_RTCA0_MASK		BIT(2)
+#define S2MPU05_IRQ_SMPL_MASK		BIT(3)
+#define S2MPU05_IRQ_RTC1S_MASK		BIT(4)
+#define S2MPU05_IRQ_WTSR_MASK		BIT(5)
+
+#define S2MPU05_IRQ_INT120C_MASK	BIT(0)
+#define S2MPU05_IRQ_INT140C_MASK	BIT(1)
+#define S2MPU05_IRQ_TSD_MASK		BIT(2)
+
 enum s5m8767_irq {
 	S5M8767_IRQ_PWRR,
 	S5M8767_IRQ_PWRF,
diff --git a/include/linux/mfd/samsung/rtc.h b/include/linux/mfd/samsung/rtc.h
index 0204decfc9aa..51c4239a1fa6 100644
--- a/include/linux/mfd/samsung/rtc.h
+++ b/include/linux/mfd/samsung/rtc.h
@@ -72,6 +72,37 @@ enum s2mps_rtc_reg {
 	S2MPS_RTC_REG_MAX,
 };
 
+enum s2mpg10_rtc_reg {
+	S2MPG10_RTC_CTRL,
+	S2MPG10_RTC_UPDATE,
+	S2MPG10_RTC_SMPL,
+	S2MPG10_RTC_WTSR,
+	S2MPG10_RTC_CAP_SEL,
+	S2MPG10_RTC_MSEC,
+	S2MPG10_RTC_SEC,
+	S2MPG10_RTC_MIN,
+	S2MPG10_RTC_HOUR,
+	S2MPG10_RTC_WEEK,
+	S2MPG10_RTC_DAY,
+	S2MPG10_RTC_MON,
+	S2MPG10_RTC_YEAR,
+	S2MPG10_RTC_A0SEC,
+	S2MPG10_RTC_A0MIN,
+	S2MPG10_RTC_A0HOUR,
+	S2MPG10_RTC_A0WEEK,
+	S2MPG10_RTC_A0DAY,
+	S2MPG10_RTC_A0MON,
+	S2MPG10_RTC_A0YEAR,
+	S2MPG10_RTC_A1SEC,
+	S2MPG10_RTC_A1MIN,
+	S2MPG10_RTC_A1HOUR,
+	S2MPG10_RTC_A1WEEK,
+	S2MPG10_RTC_A1DAY,
+	S2MPG10_RTC_A1MON,
+	S2MPG10_RTC_A1YEAR,
+	S2MPG10_RTC_OSC_CTRL,
+};
+
 #define RTC_I2C_ADDR		(0x0C >> 1)
 
 #define HOUR_12			(1 << 7)
@@ -124,10 +155,16 @@ enum s2mps_rtc_reg {
 #define ALARM_ENABLE_SHIFT	7
 #define ALARM_ENABLE_MASK	(1 << ALARM_ENABLE_SHIFT)
 
+/* WTSR & SMPL registers */
 #define SMPL_ENABLE_SHIFT	7
 #define SMPL_ENABLE_MASK	(1 << SMPL_ENABLE_SHIFT)
 
 #define WTSR_ENABLE_SHIFT	6
 #define WTSR_ENABLE_MASK	(1 << WTSR_ENABLE_SHIFT)
 
+#define S2MPG10_WTSR_COLDTIMER	GENMASK(6, 5)
+#define S2MPG10_WTSR_COLDRST	BIT(4)
+#define S2MPG10_WTSR_WTSRT	GENMASK(3, 1)
+#define S2MPG10_WTSR_WTSR_EN	BIT(0)
+
 #endif /*  __LINUX_MFD_SEC_RTC_H */
diff --git a/include/linux/mfd/samsung/s2mpg10.h b/include/linux/mfd/samsung/s2mpg10.h
new file mode 100644
index 000000000000..9f5919b89a3c
--- /dev/null
+++ b/include/linux/mfd/samsung/s2mpg10.h
@@ -0,0 +1,454 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright 2015 Samsung Electronics
+ * Copyright 2020 Google Inc
+ * Copyright 2025 Linaro Ltd.
+ */
+
+#ifndef __LINUX_MFD_S2MPG10_H
+#define __LINUX_MFD_S2MPG10_H
+
+/* Common registers (type 0x000) */
+enum s2mpg10_common_reg {
+	S2MPG10_COMMON_CHIPID,
+	S2MPG10_COMMON_INT,
+	S2MPG10_COMMON_INT_MASK,
+	S2MPG10_COMMON_SPD_CTRL1 = 0x0a,
+	S2MPG10_COMMON_SPD_CTRL2,
+	S2MPG10_COMMON_SPD_CTRL3,
+	S2MPG10_COMMON_MON1SEL = 0x1a,
+	S2MPG10_COMMON_MON2SEL,
+	S2MPG10_COMMON_MONR,
+	S2MPG10_COMMON_DEBUG_CTRL1,
+	S2MPG10_COMMON_DEBUG_CTRL2,
+	S2MPG10_COMMON_DEBUG_CTRL3,
+	S2MPG10_COMMON_DEBUG_CTRL4,
+	S2MPG10_COMMON_DEBUG_CTRL5,
+	S2MPG10_COMMON_DEBUG_CTRL6,
+	S2MPG10_COMMON_DEBUG_CTRL7,
+	S2MPG10_COMMON_DEBUG_CTRL8,
+	S2MPG10_COMMON_TEST_MODE1,
+	S2MPG10_COMMON_TEST_MODE2,
+	S2MPG10_COMMON_SPD_DEBUG1,
+	S2MPG10_COMMON_SPD_DEBUG2,
+	S2MPG10_COMMON_SPD_DEBUG3,
+	S2MPG10_COMMON_SPD_DEBUG4,
+};
+
+/* For S2MPG10_COMMON_INT and S2MPG10_COMMON_INT_MASK */
+#define S2MPG10_COMMON_INT_SRC       GENMASK(7, 0)
+#define S2MPG10_COMMON_INT_SRC_PMIC  BIT(0)
+
+/* PMIC registers (type 0x100) */
+enum s2mpg10_pmic_reg {
+	S2MPG10_PMIC_INT1,
+	S2MPG10_PMIC_INT2,
+	S2MPG10_PMIC_INT3,
+	S2MPG10_PMIC_INT4,
+	S2MPG10_PMIC_INT5,
+	S2MPG10_PMIC_INT6,
+	S2MPG10_PMIC_INT1M,
+	S2MPG10_PMIC_INT2M,
+	S2MPG10_PMIC_INT3M,
+	S2MPG10_PMIC_INT4M,
+	S2MPG10_PMIC_INT5M,
+	S2MPG10_PMIC_INT6M,
+	S2MPG10_PMIC_STATUS1,
+	S2MPG10_PMIC_STATUS2,
+	S2MPG10_PMIC_PWRONSRC,
+	S2MPG10_PMIC_OFFSRC,
+	S2MPG10_PMIC_BU_CHG,
+	S2MPG10_PMIC_RTCBUF,
+	S2MPG10_PMIC_COMMON_CTRL1,
+	S2MPG10_PMIC_COMMON_CTRL2,
+	S2MPG10_PMIC_COMMON_CTRL3,
+	S2MPG10_PMIC_COMMON_CTRL4,
+	S2MPG10_PMIC_SMPL_WARN_CTRL,
+	S2MPG10_PMIC_MIMICKING_CTRL,
+	S2MPG10_PMIC_B1M_CTRL,
+	S2MPG10_PMIC_B1M_OUT1,
+	S2MPG10_PMIC_B1M_OUT2,
+	S2MPG10_PMIC_B2M_CTRL,
+	S2MPG10_PMIC_B2M_OUT1,
+	S2MPG10_PMIC_B2M_OUT2,
+	S2MPG10_PMIC_B3M_CTRL,
+	S2MPG10_PMIC_B3M_OUT1,
+	S2MPG10_PMIC_B3M_OUT2,
+	S2MPG10_PMIC_B4M_CTRL,
+	S2MPG10_PMIC_B4M_OUT1,
+	S2MPG10_PMIC_B4M_OUT2,
+	S2MPG10_PMIC_B5M_CTRL,
+	S2MPG10_PMIC_B5M_OUT1,
+	S2MPG10_PMIC_B5M_OUT2,
+	S2MPG10_PMIC_B6M_CTRL,
+	S2MPG10_PMIC_B6M_OUT1,
+	S2MPG10_PMIC_B6M_OUT2,
+	S2MPG10_PMIC_B7M_CTRL,
+	S2MPG10_PMIC_B7M_OUT1,
+	S2MPG10_PMIC_B7M_OUT2,
+	S2MPG10_PMIC_B8M_CTRL,
+	S2MPG10_PMIC_B8M_OUT1,
+	S2MPG10_PMIC_B8M_OUT2,
+	S2MPG10_PMIC_B9M_CTRL,
+	S2MPG10_PMIC_B9M_OUT1,
+	S2MPG10_PMIC_B9M_OUT2,
+	S2MPG10_PMIC_B10M_CTRL,
+	S2MPG10_PMIC_B10M_OUT1,
+	S2MPG10_PMIC_B10M_OUT2,
+	S2MPG10_PMIC_BUCK1M_USONIC,
+	S2MPG10_PMIC_BUCK2M_USONIC,
+	S2MPG10_PMIC_BUCK3M_USONIC,
+	S2MPG10_PMIC_BUCK4M_USONIC,
+	S2MPG10_PMIC_BUCK5M_USONIC,
+	S2MPG10_PMIC_BUCK6M_USONIC,
+	S2MPG10_PMIC_BUCK7M_USONIC,
+	S2MPG10_PMIC_BUCK8M_USONIC,
+	S2MPG10_PMIC_BUCK9M_USONIC,
+	S2MPG10_PMIC_BUCK10M_USONIC,
+	S2MPG10_PMIC_L1M_CTRL,
+	S2MPG10_PMIC_L2M_CTRL,
+	S2MPG10_PMIC_L3M_CTRL,
+	S2MPG10_PMIC_L4M_CTRL,
+	S2MPG10_PMIC_L5M_CTRL,
+	S2MPG10_PMIC_L6M_CTRL,
+	S2MPG10_PMIC_L7M_CTRL,
+	S2MPG10_PMIC_L8M_CTRL,
+	S2MPG10_PMIC_L9M_CTRL,
+	S2MPG10_PMIC_L10M_CTRL,
+	S2MPG10_PMIC_L11M_CTRL1,
+	S2MPG10_PMIC_L11M_CTRL2,
+	S2MPG10_PMIC_L12M_CTRL1,
+	S2MPG10_PMIC_L12M_CTRL2,
+	S2MPG10_PMIC_L13M_CTRL1,
+	S2MPG10_PMIC_L13M_CTRL2,
+	S2MPG10_PMIC_L14M_CTRL,
+	S2MPG10_PMIC_L15M_CTRL1,
+	S2MPG10_PMIC_L15M_CTRL2,
+	S2MPG10_PMIC_L16M_CTRL,
+	S2MPG10_PMIC_L17M_CTRL,
+	S2MPG10_PMIC_L18M_CTRL,
+	S2MPG10_PMIC_L19M_CTRL,
+	S2MPG10_PMIC_L20M_CTRL,
+	S2MPG10_PMIC_L21M_CTRL,
+	S2MPG10_PMIC_L22M_CTRL,
+	S2MPG10_PMIC_L23M_CTRL,
+	S2MPG10_PMIC_L24M_CTRL,
+	S2MPG10_PMIC_L25M_CTRL,
+	S2MPG10_PMIC_L26M_CTRL,
+	S2MPG10_PMIC_L27M_CTRL,
+	S2MPG10_PMIC_L28M_CTRL,
+	S2MPG10_PMIC_L29M_CTRL,
+	S2MPG10_PMIC_L30M_CTRL,
+	S2MPG10_PMIC_L31M_CTRL,
+	S2MPG10_PMIC_LDO_CTRL1,
+	S2MPG10_PMIC_LDO_CTRL2,
+	S2MPG10_PMIC_LDO_DSCH1,
+	S2MPG10_PMIC_LDO_DSCH2,
+	S2MPG10_PMIC_LDO_DSCH3,
+	S2MPG10_PMIC_LDO_DSCH4,
+	S2MPG10_PMIC_LDO_BUCK7M_HLIMIT,
+	S2MPG10_PMIC_LDO_BUCK7M_LLIMIT,
+	S2MPG10_PMIC_LDO_LDO21M_HLIMIT,
+	S2MPG10_PMIC_LDO_LDO21M_LLIMIT,
+	S2MPG10_PMIC_LDO_LDO11M_HLIMIT,
+	S2MPG10_PMIC_DVS_RAMP1,
+	S2MPG10_PMIC_DVS_RAMP2,
+	S2MPG10_PMIC_DVS_RAMP3,
+	S2MPG10_PMIC_DVS_RAMP4,
+	S2MPG10_PMIC_DVS_RAMP5,
+	S2MPG10_PMIC_DVS_RAMP6,
+	S2MPG10_PMIC_DVS_SYNC_CTRL1,
+	S2MPG10_PMIC_DVS_SYNC_CTRL2,
+	S2MPG10_PMIC_DVS_SYNC_CTRL3,
+	S2MPG10_PMIC_DVS_SYNC_CTRL4,
+	S2MPG10_PMIC_DVS_SYNC_CTRL5,
+	S2MPG10_PMIC_DVS_SYNC_CTRL6,
+	S2MPG10_PMIC_OFF_CTRL1,
+	S2MPG10_PMIC_OFF_CTRL2,
+	S2MPG10_PMIC_OFF_CTRL3,
+	S2MPG10_PMIC_OFF_CTRL4,
+	S2MPG10_PMIC_SEQ_CTRL1,
+	S2MPG10_PMIC_SEQ_CTRL2,
+	S2MPG10_PMIC_SEQ_CTRL3,
+	S2MPG10_PMIC_SEQ_CTRL4,
+	S2MPG10_PMIC_SEQ_CTRL5,
+	S2MPG10_PMIC_SEQ_CTRL6,
+	S2MPG10_PMIC_SEQ_CTRL7,
+	S2MPG10_PMIC_SEQ_CTRL8,
+	S2MPG10_PMIC_SEQ_CTRL9,
+	S2MPG10_PMIC_SEQ_CTRL10,
+	S2MPG10_PMIC_SEQ_CTRL11,
+	S2MPG10_PMIC_SEQ_CTRL12,
+	S2MPG10_PMIC_SEQ_CTRL13,
+	S2MPG10_PMIC_SEQ_CTRL14,
+	S2MPG10_PMIC_SEQ_CTRL15,
+	S2MPG10_PMIC_SEQ_CTRL16,
+	S2MPG10_PMIC_SEQ_CTRL17,
+	S2MPG10_PMIC_SEQ_CTRL18,
+	S2MPG10_PMIC_SEQ_CTRL19,
+	S2MPG10_PMIC_SEQ_CTRL20,
+	S2MPG10_PMIC_SEQ_CTRL21,
+	S2MPG10_PMIC_SEQ_CTRL22,
+	S2MPG10_PMIC_SEQ_CTRL23,
+	S2MPG10_PMIC_SEQ_CTRL24,
+	S2MPG10_PMIC_SEQ_CTRL25,
+	S2MPG10_PMIC_SEQ_CTRL26,
+	S2MPG10_PMIC_SEQ_CTRL27,
+	S2MPG10_PMIC_SEQ_CTRL28,
+	S2MPG10_PMIC_SEQ_CTRL29,
+	S2MPG10_PMIC_SEQ_CTRL30,
+	S2MPG10_PMIC_SEQ_CTRL31,
+	S2MPG10_PMIC_SEQ_CTRL32,
+	S2MPG10_PMIC_SEQ_CTRL33,
+	S2MPG10_PMIC_SEQ_CTRL34,
+	S2MPG10_PMIC_SEQ_CTRL35,
+	S2MPG10_PMIC_OFF_SEQ_CTRL1,
+	S2MPG10_PMIC_OFF_SEQ_CTRL2,
+	S2MPG10_PMIC_OFF_SEQ_CTRL3,
+	S2MPG10_PMIC_OFF_SEQ_CTRL4,
+	S2MPG10_PMIC_OFF_SEQ_CTRL5,
+	S2MPG10_PMIC_OFF_SEQ_CTRL6,
+	S2MPG10_PMIC_OFF_SEQ_CTRL7,
+	S2MPG10_PMIC_OFF_SEQ_CTRL8,
+	S2MPG10_PMIC_OFF_SEQ_CTRL9,
+	S2MPG10_PMIC_OFF_SEQ_CTRL10,
+	S2MPG10_PMIC_OFF_SEQ_CTRL11,
+	S2MPG10_PMIC_OFF_SEQ_CTRL12,
+	S2MPG10_PMIC_OFF_SEQ_CTRL13,
+	S2MPG10_PMIC_OFF_SEQ_CTRL14,
+	S2MPG10_PMIC_OFF_SEQ_CTRL15,
+	S2MPG10_PMIC_OFF_SEQ_CTRL16,
+	S2MPG10_PMIC_OFF_SEQ_CTRL17,
+	S2MPG10_PMIC_OFF_SEQ_CTRL18,
+	S2MPG10_PMIC_PCTRLSEL1,
+	S2MPG10_PMIC_PCTRLSEL2,
+	S2MPG10_PMIC_PCTRLSEL3,
+	S2MPG10_PMIC_PCTRLSEL4,
+	S2MPG10_PMIC_PCTRLSEL5,
+	S2MPG10_PMIC_PCTRLSEL6,
+	S2MPG10_PMIC_PCTRLSEL7,
+	S2MPG10_PMIC_PCTRLSEL8,
+	S2MPG10_PMIC_PCTRLSEL9,
+	S2MPG10_PMIC_PCTRLSEL10,
+	S2MPG10_PMIC_PCTRLSEL11,
+	S2MPG10_PMIC_PCTRLSEL12,
+	S2MPG10_PMIC_PCTRLSEL13,
+	S2MPG10_PMIC_DCTRLSEL1,
+	S2MPG10_PMIC_DCTRLSEL2,
+	S2MPG10_PMIC_DCTRLSEL3,
+	S2MPG10_PMIC_DCTRLSEL4,
+	S2MPG10_PMIC_DCTRLSEL5,
+	S2MPG10_PMIC_DCTRLSEL6,
+	S2MPG10_PMIC_DCTRLSEL7,
+	S2MPG10_PMIC_GPIO_CTRL1,
+	S2MPG10_PMIC_GPIO_CTRL2,
+	S2MPG10_PMIC_GPIO_CTRL3,
+	S2MPG10_PMIC_GPIO_CTRL4,
+	S2MPG10_PMIC_GPIO_CTRL5,
+	S2MPG10_PMIC_GPIO_CTRL6,
+	S2MPG10_PMIC_GPIO_CTRL7,
+	S2MPG10_PMIC_B2M_OCP_WARN,
+	S2MPG10_PMIC_B2M_OCP_WARN_X,
+	S2MPG10_PMIC_B2M_OCP_WARN_Y,
+	S2MPG10_PMIC_B2M_OCP_WARN_Z,
+	S2MPG10_PMIC_B3M_OCP_WARN,
+	S2MPG10_PMIC_B3M_OCP_WARN_X,
+	S2MPG10_PMIC_B3M_OCP_WARN_Y,
+	S2MPG10_PMIC_B3M_OCP_WARN_Z,
+	S2MPG10_PMIC_B10M_OCP_WARN,
+	S2MPG10_PMIC_B10M_OCP_WARN_X,
+	S2MPG10_PMIC_B10M_OCP_WARN_Y,
+	S2MPG10_PMIC_B10M_OCP_WARN_Z,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN_X,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN_Y,
+	S2MPG10_PMIC_B2M_SOFT_OCP_WARN_Z,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN_X,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN_Y,
+	S2MPG10_PMIC_B3M_SOFT_OCP_WARN_Z,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN_X,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN_Y,
+	S2MPG10_PMIC_B10M_SOFT_OCP_WARN_Z,
+	S2MPG10_PMIC_BUCK_OCP_EN1,
+	S2MPG10_PMIC_BUCK_OCP_EN2,
+	S2MPG10_PMIC_BUCK_OCP_PD_EN1,
+	S2MPG10_PMIC_BUCK_OCP_PD_EN2,
+	S2MPG10_PMIC_BUCK_OCP_CTRL1,
+	S2MPG10_PMIC_BUCK_OCP_CTRL2,
+	S2MPG10_PMIC_BUCK_OCP_CTRL3,
+	S2MPG10_PMIC_BUCK_OCP_CTRL4,
+	S2MPG10_PMIC_BUCK_OCP_CTRL5,
+	S2MPG10_PMIC_PIF_CTRL,
+	S2MPG10_PMIC_BUCK_HR_MODE1,
+	S2MPG10_PMIC_BUCK_HR_MODE2,
+	S2MPG10_PMIC_FAULTOUT_CTRL,
+	S2MPG10_PMIC_LDO_SENSE1,
+	S2MPG10_PMIC_LDO_SENSE2,
+	S2MPG10_PMIC_LDO_SENSE3,
+	S2MPG10_PMIC_LDO_SENSE4,
+};
+
+/* Meter registers (type 0xa00) */
+enum s2mpg10_meter_reg {
+	S2MPG10_METER_CTRL1,
+	S2MPG10_METER_CTRL2,
+	S2MPG10_METER_CTRL3,
+	S2MPG10_METER_CTRL4,
+	S2MPG10_METER_BUCKEN1,
+	S2MPG10_METER_BUCKEN2,
+	S2MPG10_METER_MUXSEL0,
+	S2MPG10_METER_MUXSEL1,
+	S2MPG10_METER_MUXSEL2,
+	S2MPG10_METER_MUXSEL3,
+	S2MPG10_METER_MUXSEL4,
+	S2MPG10_METER_MUXSEL5,
+	S2MPG10_METER_MUXSEL6,
+	S2MPG10_METER_MUXSEL7,
+	S2MPG10_METER_LPF_C0_0,
+	S2MPG10_METER_LPF_C0_1,
+	S2MPG10_METER_LPF_C0_2,
+	S2MPG10_METER_LPF_C0_3,
+	S2MPG10_METER_LPF_C0_4,
+	S2MPG10_METER_LPF_C0_5,
+	S2MPG10_METER_LPF_C0_6,
+	S2MPG10_METER_LPF_C0_7,
+	S2MPG10_METER_PWR_WARN0,
+	S2MPG10_METER_PWR_WARN1,
+	S2MPG10_METER_PWR_WARN2,
+	S2MPG10_METER_PWR_WARN3,
+	S2MPG10_METER_PWR_WARN4,
+	S2MPG10_METER_PWR_WARN5,
+	S2MPG10_METER_PWR_WARN6,
+	S2MPG10_METER_PWR_WARN7,
+	S2MPG10_METER_PWR_HYS1,
+	S2MPG10_METER_PWR_HYS2,
+	S2MPG10_METER_PWR_HYS3,
+	S2MPG10_METER_PWR_HYS4,
+	S2MPG10_METER_ACC_DATA_CH0_1 = 0x40,
+	S2MPG10_METER_ACC_DATA_CH0_2,
+	S2MPG10_METER_ACC_DATA_CH0_3,
+	S2MPG10_METER_ACC_DATA_CH0_4,
+	S2MPG10_METER_ACC_DATA_CH0_5,
+	S2MPG10_METER_ACC_DATA_CH0_6,
+	S2MPG10_METER_ACC_DATA_CH1_1,
+	S2MPG10_METER_ACC_DATA_CH1_2,
+	S2MPG10_METER_ACC_DATA_CH1_3,
+	S2MPG10_METER_ACC_DATA_CH1_4,
+	S2MPG10_METER_ACC_DATA_CH1_5,
+	S2MPG10_METER_ACC_DATA_CH1_6,
+	S2MPG10_METER_ACC_DATA_CH2_1,
+	S2MPG10_METER_ACC_DATA_CH2_2,
+	S2MPG10_METER_ACC_DATA_CH2_3,
+	S2MPG10_METER_ACC_DATA_CH2_4,
+	S2MPG10_METER_ACC_DATA_CH2_5,
+	S2MPG10_METER_ACC_DATA_CH2_6,
+	S2MPG10_METER_ACC_DATA_CH3_1,
+	S2MPG10_METER_ACC_DATA_CH3_2,
+	S2MPG10_METER_ACC_DATA_CH3_3,
+	S2MPG10_METER_ACC_DATA_CH3_4,
+	S2MPG10_METER_ACC_DATA_CH3_5,
+	S2MPG10_METER_ACC_DATA_CH3_6,
+	S2MPG10_METER_ACC_DATA_CH4_1,
+	S2MPG10_METER_ACC_DATA_CH4_2,
+	S2MPG10_METER_ACC_DATA_CH4_3,
+	S2MPG10_METER_ACC_DATA_CH4_4,
+	S2MPG10_METER_ACC_DATA_CH4_5,
+	S2MPG10_METER_ACC_DATA_CH4_6,
+	S2MPG10_METER_ACC_DATA_CH5_1,
+	S2MPG10_METER_ACC_DATA_CH5_2,
+	S2MPG10_METER_ACC_DATA_CH5_3,
+	S2MPG10_METER_ACC_DATA_CH5_4,
+	S2MPG10_METER_ACC_DATA_CH5_5,
+	S2MPG10_METER_ACC_DATA_CH5_6,
+	S2MPG10_METER_ACC_DATA_CH6_1,
+	S2MPG10_METER_ACC_DATA_CH6_2,
+	S2MPG10_METER_ACC_DATA_CH6_3,
+	S2MPG10_METER_ACC_DATA_CH6_4,
+	S2MPG10_METER_ACC_DATA_CH6_5,
+	S2MPG10_METER_ACC_DATA_CH6_6,
+	S2MPG10_METER_ACC_DATA_CH7_1,
+	S2MPG10_METER_ACC_DATA_CH7_2,
+	S2MPG10_METER_ACC_DATA_CH7_3,
+	S2MPG10_METER_ACC_DATA_CH7_4,
+	S2MPG10_METER_ACC_DATA_CH7_5,
+	S2MPG10_METER_ACC_DATA_CH7_6,
+	S2MPG10_METER_ACC_COUNT_1,
+	S2MPG10_METER_ACC_COUNT_2,
+	S2MPG10_METER_ACC_COUNT_3,
+	S2MPG10_METER_LPF_DATA_CH0_1,
+	S2MPG10_METER_LPF_DATA_CH0_2,
+	S2MPG10_METER_LPF_DATA_CH0_3,
+	S2MPG10_METER_LPF_DATA_CH1_1,
+	S2MPG10_METER_LPF_DATA_CH1_2,
+	S2MPG10_METER_LPF_DATA_CH1_3,
+	S2MPG10_METER_LPF_DATA_CH2_1,
+	S2MPG10_METER_LPF_DATA_CH2_2,
+	S2MPG10_METER_LPF_DATA_CH2_3,
+	S2MPG10_METER_LPF_DATA_CH3_1,
+	S2MPG10_METER_LPF_DATA_CH3_2,
+	S2MPG10_METER_LPF_DATA_CH3_3,
+	S2MPG10_METER_LPF_DATA_CH4_1,
+	S2MPG10_METER_LPF_DATA_CH4_2,
+	S2MPG10_METER_LPF_DATA_CH4_3,
+	S2MPG10_METER_LPF_DATA_CH5_1,
+	S2MPG10_METER_LPF_DATA_CH5_2,
+	S2MPG10_METER_LPF_DATA_CH5_3,
+	S2MPG10_METER_LPF_DATA_CH6_1,
+	S2MPG10_METER_LPF_DATA_CH6_2,
+	S2MPG10_METER_LPF_DATA_CH6_3,
+	S2MPG10_METER_LPF_DATA_CH7_1,
+	S2MPG10_METER_LPF_DATA_CH7_2,
+	S2MPG10_METER_LPF_DATA_CH7_3,
+	S2MPG10_METER_DSM_TRIM_OFFSET = 0xee,
+	S2MPG10_METER_BUCK_METER_TRIM3 = 0xf1,
+};
+
+/* S2MPG10 regulator IDs */
+enum s2mpg10_regulators {
+	S2MPG10_LDO1,
+	S2MPG10_LDO2,
+	S2MPG10_LDO3,
+	S2MPG10_LDO4,
+	S2MPG10_LDO5,
+	S2MPG10_LDO6,
+	S2MPG10_LDO7,
+	S2MPG10_LDO8,
+	S2MPG10_LDO9,
+	S2MPG10_LDO10,
+	S2MPG10_LDO11,
+	S2MPG10_LDO12,
+	S2MPG10_LDO13,
+	S2MPG10_LDO14,
+	S2MPG10_LDO15,
+	S2MPG10_LDO16,
+	S2MPG10_LDO17,
+	S2MPG10_LDO18,
+	S2MPG10_LDO19,
+	S2MPG10_LDO20,
+	S2MPG10_LDO21,
+	S2MPG10_LDO22,
+	S2MPG10_LDO23,
+	S2MPG10_LDO24,
+	S2MPG10_LDO25,
+	S2MPG10_LDO26,
+	S2MPG10_LDO27,
+	S2MPG10_LDO28,
+	S2MPG10_LDO29,
+	S2MPG10_LDO30,
+	S2MPG10_LDO31,
+	S2MPG10_BUCK1,
+	S2MPG10_BUCK2,
+	S2MPG10_BUCK3,
+	S2MPG10_BUCK4,
+	S2MPG10_BUCK5,
+	S2MPG10_BUCK6,
+	S2MPG10_BUCK7,
+	S2MPG10_BUCK8,
+	S2MPG10_BUCK9,
+	S2MPG10_BUCK10,
+	S2MPG10_REGULATOR_MAX,
+};
+
+#endif /* __LINUX_MFD_S2MPG10_H */
diff --git a/include/linux/mfd/samsung/s2mpu05.h b/include/linux/mfd/samsung/s2mpu05.h
new file mode 100644
index 000000000000..fcdb6c8adb03
--- /dev/null
+++ b/include/linux/mfd/samsung/s2mpu05.h
@@ -0,0 +1,183 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * Copyright (c) 2015 Samsung Electronics Co., Ltd
+ * Copyright (c) 2025 Kaustabh Chakraborty <kauschluss@disroot.org>
+ */
+
+#ifndef __LINUX_MFD_S2MPU05_H
+#define __LINUX_MFD_S2MPU05_H
+
+/* S2MPU05 registers */
+enum S2MPU05_reg {
+	S2MPU05_REG_ID,
+	S2MPU05_REG_INT1,
+	S2MPU05_REG_INT2,
+	S2MPU05_REG_INT3,
+	S2MPU05_REG_INT1M,
+	S2MPU05_REG_INT2M,
+	S2MPU05_REG_INT3M,
+	S2MPU05_REG_ST1,
+	S2MPU05_REG_ST2,
+	S2MPU05_REG_PWRONSRC,
+	S2MPU05_REG_OFFSRC,
+	S2MPU05_REG_BU_CHG,
+	S2MPU05_REG_RTC_BUF,
+	S2MPU05_REG_CTRL1,
+	S2MPU05_REG_CTRL2,
+	S2MPU05_REG_ETC_TEST,
+	S2MPU05_REG_OTP_ADRL,
+	S2MPU05_REG_OTP_ADRH,
+	S2MPU05_REG_OTP_DATA,
+	S2MPU05_REG_MON1SEL,
+	S2MPU05_REG_MON2SEL,
+	S2MPU05_REG_CTRL3,
+	S2MPU05_REG_ETC_OTP,
+	S2MPU05_REG_UVLO,
+	S2MPU05_REG_TIME_CTRL1,
+	S2MPU05_REG_TIME_CTRL2,
+	S2MPU05_REG_B1CTRL1,
+	S2MPU05_REG_B1CTRL2,
+	S2MPU05_REG_B2CTRL1,
+	S2MPU05_REG_B2CTRL2,
+	S2MPU05_REG_B2CTRL3,
+	S2MPU05_REG_B2CTRL4,
+	S2MPU05_REG_B3CTRL1,
+	S2MPU05_REG_B3CTRL2,
+	S2MPU05_REG_B3CTRL3,
+	S2MPU05_REG_B4CTRL1,
+	S2MPU05_REG_B4CTRL2,
+	S2MPU05_REG_B5CTRL1,
+	S2MPU05_REG_B5CTRL2,
+	S2MPU05_REG_BUCK_RAMP,
+	S2MPU05_REG_LDO_DVS1,
+	S2MPU05_REG_LDO_DVS9,
+	S2MPU05_REG_LDO_DVS10,
+	S2MPU05_REG_L1CTRL,
+	S2MPU05_REG_L2CTRL,
+	S2MPU05_REG_L3CTRL,
+	S2MPU05_REG_L4CTRL,
+	S2MPU05_REG_L5CTRL,
+	S2MPU05_REG_L6CTRL,
+	S2MPU05_REG_L7CTRL,
+	S2MPU05_REG_L8CTRL,
+	S2MPU05_REG_L9CTRL1,
+	S2MPU05_REG_L9CTRL2,
+	S2MPU05_REG_L10CTRL,
+	S2MPU05_REG_L11CTRL1,
+	S2MPU05_REG_L11CTRL2,
+	S2MPU05_REG_L12CTRL,
+	S2MPU05_REG_L13CTRL,
+	S2MPU05_REG_L14CTRL,
+	S2MPU05_REG_L15CTRL,
+	S2MPU05_REG_L16CTRL,
+	S2MPU05_REG_L17CTRL1,
+	S2MPU05_REG_L17CTRL2,
+	S2MPU05_REG_L18CTRL1,
+	S2MPU05_REG_L18CTRL2,
+	S2MPU05_REG_L19CTRL,
+	S2MPU05_REG_L20CTRL,
+	S2MPU05_REG_L21CTRL,
+	S2MPU05_REG_L22CTRL,
+	S2MPU05_REG_L23CTRL,
+	S2MPU05_REG_L24CTRL,
+	S2MPU05_REG_L25CTRL,
+	S2MPU05_REG_L26CTRL,
+	S2MPU05_REG_L27CTRL,
+	S2MPU05_REG_L28CTRL,
+	S2MPU05_REG_L29CTRL,
+	S2MPU05_REG_L30CTRL,
+	S2MPU05_REG_L31CTRL,
+	S2MPU05_REG_L32CTRL,
+	S2MPU05_REG_L33CTRL,
+	S2MPU05_REG_L34CTRL,
+	S2MPU05_REG_L35CTRL,
+	S2MPU05_REG_LDO_DSCH1,
+	S2MPU05_REG_LDO_DSCH2,
+	S2MPU05_REG_LDO_DSCH3,
+	S2MPU05_REG_LDO_DSCH4,
+	S2MPU05_REG_LDO_DSCH5,
+	S2MPU05_REG_LDO_CTRL1,
+	S2MPU05_REG_LDO_CTRL2,
+	S2MPU05_REG_TCXO_CTRL,
+	S2MPU05_REG_SELMIF,
+};
+
+/* S2MPU05 regulator ids */
+enum S2MPU05_regulators {
+	S2MPU05_LDO1,
+	S2MPU05_LDO2,
+	S2MPU05_LDO3,
+	S2MPU05_LDO4,
+	S2MPU05_LDO5,
+	S2MPU05_LDO6,
+	S2MPU05_LDO7,
+	S2MPU05_LDO8,
+	S2MPU05_LDO9,
+	S2MPU05_LDO10,
+	S2MPU05_LDO11,
+	S2MPU05_LDO12,
+	S2MPU05_LDO13,
+	S2MPU05_LDO14,
+	S2MPU05_LDO15,
+	S2MPU05_LDO16,
+	S2MPU05_LDO17,
+	S2MPU05_LDO18,
+	S2MPU05_LDO19,
+	S2MPU05_LDO20,
+	S2MPU05_LDO21,
+	S2MPU05_LDO22,
+	S2MPU05_LDO23,
+	S2MPU05_LDO24,
+	S2MPU05_LDO25,
+	S2MPU05_LDO26,
+	S2MPU05_LDO27,
+	S2MPU05_LDO28,
+	S2MPU05_LDO29,
+	S2MPU05_LDO30,
+	S2MPU05_LDO31,
+	S2MPU05_LDO32,
+	S2MPU05_LDO33,
+	S2MPU05_LDO34,
+	S2MPU05_LDO35,
+	S2MPU05_BUCK1,
+	S2MPU05_BUCK2,
+	S2MPU05_BUCK3,
+	S2MPU05_BUCK4,
+	S2MPU05_BUCK5,
+
+	S2MPU05_REGULATOR_MAX,
+};
+
+#define S2MPU05_SW_ENABLE_MASK	0x03
+
+#define S2MPU05_ENABLE_TIME_LDO		128
+#define S2MPU05_ENABLE_TIME_BUCK1	110
+#define S2MPU05_ENABLE_TIME_BUCK2	110
+#define S2MPU05_ENABLE_TIME_BUCK3	110
+#define S2MPU05_ENABLE_TIME_BUCK4	150
+#define S2MPU05_ENABLE_TIME_BUCK5	150
+
+#define S2MPU05_LDO_MIN1	800000
+#define S2MPU05_LDO_MIN2	1800000
+#define S2MPU05_LDO_MIN3	400000
+#define S2MPU05_LDO_STEP1	12500
+#define S2MPU05_LDO_STEP2	25000
+
+#define S2MPU05_BUCK_MIN1	400000
+#define S2MPU05_BUCK_MIN2	600000
+#define S2MPU05_BUCK_STEP1	6250
+#define S2MPU05_BUCK_STEP2	12500
+
+#define S2MPU05_RAMP_DELAY	12000	/* uV/uS */
+
+#define S2MPU05_ENABLE_SHIFT	6
+#define S2MPU05_ENABLE_MASK	(0x03 << S2MPU05_ENABLE_SHIFT)
+
+#define S2MPU05_LDO_VSEL_MASK	0x3F
+#define S2MPU05_BUCK_VSEL_MASK	0xFF
+#define S2MPU05_LDO_N_VOLTAGES	(S2MPU05_LDO_VSEL_MASK + 1)
+#define S2MPU05_BUCK_N_VOLTAGES (S2MPU05_BUCK_VSEL_MASK + 1)
+
+#define S2MPU05_PMIC_EN_SHIFT	6
+
+#endif /*  __LINUX_MFD_S2MPU05_H */
diff --git a/include/linux/mfd/si476x-platform.h b/include/linux/mfd/si476x-platform.h
index 18363b773d07..cb99e16ca947 100644
--- a/include/linux/mfd/si476x-platform.h
+++ b/include/linux/mfd/si476x-platform.h
@@ -10,7 +10,7 @@
 #ifndef __SI476X_PLATFORM_H__
 #define __SI476X_PLATFORM_H__
 
-/* It is possible to select one of the four adresses using pins A0
+/* It is possible to select one of the four addresses using pins A0
  * and A1 on SI476x */
 #define SI476X_I2C_ADDR_1	0x60
 #define SI476X_I2C_ADDR_2	0x61
diff --git a/include/linux/mfd/sta2x11-mfd.h b/include/linux/mfd/sta2x11-mfd.h
deleted file mode 100644
index 2001ca5c44a9..000000000000
--- a/include/linux/mfd/sta2x11-mfd.h
+++ /dev/null
@@ -1,506 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (c) 2009-2011 Wind River Systems, Inc.
- * Copyright (c) 2011 ST Microelectronics (Alessandro Rubini)
- *
- * The STMicroelectronics ConneXt (STA2X11) chip has several unrelated
- * functions in one PCI endpoint functions. This driver simply
- * registers the platform devices in this iomemregion and exports a few
- * functions to access common registers
- */
-
-#ifndef __STA2X11_MFD_H
-#define __STA2X11_MFD_H
-#include <linux/types.h>
-#include <linux/pci.h>
-
-enum sta2x11_mfd_plat_dev {
-	sta2x11_sctl = 0,
-	sta2x11_gpio,
-	sta2x11_scr,
-	sta2x11_time,
-	sta2x11_apbreg,
-	sta2x11_apb_soc_regs,
-	sta2x11_vic,
-	sta2x11_n_mfd_plat_devs,
-};
-
-#define STA2X11_MFD_SCTL_NAME	       "sta2x11-sctl"
-#define STA2X11_MFD_GPIO_NAME	       "sta2x11-gpio"
-#define STA2X11_MFD_SCR_NAME	       "sta2x11-scr"
-#define STA2X11_MFD_TIME_NAME	       "sta2x11-time"
-#define STA2X11_MFD_APBREG_NAME	       "sta2x11-apbreg"
-#define STA2X11_MFD_APB_SOC_REGS_NAME  "sta2x11-apb-soc-regs"
-#define STA2X11_MFD_VIC_NAME	       "sta2x11-vic"
-
-extern u32
-__sta2x11_mfd_mask(struct pci_dev *, u32, u32, u32, enum sta2x11_mfd_plat_dev);
-
-/*
- * The MFD PCI block includes the GPIO peripherals and other register blocks.
- * For GPIO, we have 32*4 bits (I use "gsta" for "gpio sta2x11".)
- */
-#define GSTA_GPIO_PER_BLOCK	32
-#define GSTA_NR_BLOCKS		4
-#define GSTA_NR_GPIO		(GSTA_GPIO_PER_BLOCK * GSTA_NR_BLOCKS)
-
-/* Pinconfig is set by the board definition: altfunc, pull-up, pull-down */
-struct sta2x11_gpio_pdata {
-	unsigned pinconfig[GSTA_NR_GPIO];
-};
-
-/* Macros below lifted from sh_pfc.h, with minor differences */
-#define PINMUX_TYPE_NONE		0
-#define PINMUX_TYPE_FUNCTION		1
-#define PINMUX_TYPE_OUTPUT_LOW		2
-#define PINMUX_TYPE_OUTPUT_HIGH		3
-#define PINMUX_TYPE_INPUT		4
-#define PINMUX_TYPE_INPUT_PULLUP	5
-#define PINMUX_TYPE_INPUT_PULLDOWN	6
-
-/* Give names to GPIO pins, like PXA does, taken from the manual */
-#define STA2X11_GPIO0			0
-#define STA2X11_GPIO1			1
-#define STA2X11_GPIO2			2
-#define STA2X11_GPIO3			3
-#define STA2X11_GPIO4			4
-#define STA2X11_GPIO5			5
-#define STA2X11_GPIO6			6
-#define STA2X11_GPIO7			7
-#define STA2X11_GPIO8_RGBOUT_RED7	8
-#define STA2X11_GPIO9_RGBOUT_RED6	9
-#define STA2X11_GPIO10_RGBOUT_RED5	10
-#define STA2X11_GPIO11_RGBOUT_RED4	11
-#define STA2X11_GPIO12_RGBOUT_RED3	12
-#define STA2X11_GPIO13_RGBOUT_RED2	13
-#define STA2X11_GPIO14_RGBOUT_RED1	14
-#define STA2X11_GPIO15_RGBOUT_RED0	15
-#define STA2X11_GPIO16_RGBOUT_GREEN7	16
-#define STA2X11_GPIO17_RGBOUT_GREEN6	17
-#define STA2X11_GPIO18_RGBOUT_GREEN5	18
-#define STA2X11_GPIO19_RGBOUT_GREEN4	19
-#define STA2X11_GPIO20_RGBOUT_GREEN3	20
-#define STA2X11_GPIO21_RGBOUT_GREEN2	21
-#define STA2X11_GPIO22_RGBOUT_GREEN1	22
-#define STA2X11_GPIO23_RGBOUT_GREEN0	23
-#define STA2X11_GPIO24_RGBOUT_BLUE7	24
-#define STA2X11_GPIO25_RGBOUT_BLUE6	25
-#define STA2X11_GPIO26_RGBOUT_BLUE5	26
-#define STA2X11_GPIO27_RGBOUT_BLUE4	27
-#define STA2X11_GPIO28_RGBOUT_BLUE3	28
-#define STA2X11_GPIO29_RGBOUT_BLUE2	29
-#define STA2X11_GPIO30_RGBOUT_BLUE1	30
-#define STA2X11_GPIO31_RGBOUT_BLUE0	31
-#define STA2X11_GPIO32_RGBOUT_VSYNCH	32
-#define STA2X11_GPIO33_RGBOUT_HSYNCH	33
-#define STA2X11_GPIO34_RGBOUT_DEN	34
-#define STA2X11_GPIO35_ETH_CRS_DV	35
-#define STA2X11_GPIO36_ETH_TXD1		36
-#define STA2X11_GPIO37_ETH_TXD0		37
-#define STA2X11_GPIO38_ETH_TX_EN	38
-#define STA2X11_GPIO39_MDIO		39
-#define STA2X11_GPIO40_ETH_REF_CLK	40
-#define STA2X11_GPIO41_ETH_RXD1		41
-#define STA2X11_GPIO42_ETH_RXD0		42
-#define STA2X11_GPIO43_MDC		43
-#define STA2X11_GPIO44_CAN_TX		44
-#define STA2X11_GPIO45_CAN_RX		45
-#define STA2X11_GPIO46_MLB_DAT		46
-#define STA2X11_GPIO47_MLB_SIG		47
-#define STA2X11_GPIO48_SPI0_CLK		48
-#define STA2X11_GPIO49_SPI0_TXD		49
-#define STA2X11_GPIO50_SPI0_RXD		50
-#define STA2X11_GPIO51_SPI0_FRM		51
-#define STA2X11_GPIO52_SPI1_CLK		52
-#define STA2X11_GPIO53_SPI1_TXD		53
-#define STA2X11_GPIO54_SPI1_RXD		54
-#define STA2X11_GPIO55_SPI1_FRM		55
-#define STA2X11_GPIO56_SPI2_CLK		56
-#define STA2X11_GPIO57_SPI2_TXD		57
-#define STA2X11_GPIO58_SPI2_RXD		58
-#define STA2X11_GPIO59_SPI2_FRM		59
-#define STA2X11_GPIO60_I2C0_SCL		60
-#define STA2X11_GPIO61_I2C0_SDA		61
-#define STA2X11_GPIO62_I2C1_SCL		62
-#define STA2X11_GPIO63_I2C1_SDA		63
-#define STA2X11_GPIO64_I2C2_SCL		64
-#define STA2X11_GPIO65_I2C2_SDA		65
-#define STA2X11_GPIO66_I2C3_SCL		66
-#define STA2X11_GPIO67_I2C3_SDA		67
-#define STA2X11_GPIO68_MSP0_RCK		68
-#define STA2X11_GPIO69_MSP0_RXD		69
-#define STA2X11_GPIO70_MSP0_RFS		70
-#define STA2X11_GPIO71_MSP0_TCK		71
-#define STA2X11_GPIO72_MSP0_TXD		72
-#define STA2X11_GPIO73_MSP0_TFS		73
-#define STA2X11_GPIO74_MSP0_SCK		74
-#define STA2X11_GPIO75_MSP1_CK		75
-#define STA2X11_GPIO76_MSP1_RXD		76
-#define STA2X11_GPIO77_MSP1_FS		77
-#define STA2X11_GPIO78_MSP1_TXD		78
-#define STA2X11_GPIO79_MSP2_CK		79
-#define STA2X11_GPIO80_MSP2_RXD		80
-#define STA2X11_GPIO81_MSP2_FS		81
-#define STA2X11_GPIO82_MSP2_TXD		82
-#define STA2X11_GPIO83_MSP3_CK		83
-#define STA2X11_GPIO84_MSP3_RXD		84
-#define STA2X11_GPIO85_MSP3_FS		85
-#define STA2X11_GPIO86_MSP3_TXD		86
-#define STA2X11_GPIO87_MSP4_CK		87
-#define STA2X11_GPIO88_MSP4_RXD		88
-#define STA2X11_GPIO89_MSP4_FS		89
-#define STA2X11_GPIO90_MSP4_TXD		90
-#define STA2X11_GPIO91_MSP5_CK		91
-#define STA2X11_GPIO92_MSP5_RXD		92
-#define STA2X11_GPIO93_MSP5_FS		93
-#define STA2X11_GPIO94_MSP5_TXD		94
-#define STA2X11_GPIO95_SDIO3_DAT3	95
-#define STA2X11_GPIO96_SDIO3_DAT2	96
-#define STA2X11_GPIO97_SDIO3_DAT1	97
-#define STA2X11_GPIO98_SDIO3_DAT0	98
-#define STA2X11_GPIO99_SDIO3_CLK	99
-#define STA2X11_GPIO100_SDIO3_CMD	100
-#define STA2X11_GPIO101			101
-#define STA2X11_GPIO102			102
-#define STA2X11_GPIO103			103
-#define STA2X11_GPIO104			104
-#define STA2X11_GPIO105_SDIO2_DAT3	105
-#define STA2X11_GPIO106_SDIO2_DAT2	106
-#define STA2X11_GPIO107_SDIO2_DAT1	107
-#define STA2X11_GPIO108_SDIO2_DAT0	108
-#define STA2X11_GPIO109_SDIO2_CLK	109
-#define STA2X11_GPIO110_SDIO2_CMD	110
-#define STA2X11_GPIO111			111
-#define STA2X11_GPIO112			112
-#define STA2X11_GPIO113			113
-#define STA2X11_GPIO114			114
-#define STA2X11_GPIO115_SDIO1_DAT3	115
-#define STA2X11_GPIO116_SDIO1_DAT2	116
-#define STA2X11_GPIO117_SDIO1_DAT1	117
-#define STA2X11_GPIO118_SDIO1_DAT0	118
-#define STA2X11_GPIO119_SDIO1_CLK	119
-#define STA2X11_GPIO120_SDIO1_CMD	120
-#define STA2X11_GPIO121			121
-#define STA2X11_GPIO122			122
-#define STA2X11_GPIO123			123
-#define STA2X11_GPIO124			124
-#define STA2X11_GPIO125_UART2_TXD	125
-#define STA2X11_GPIO126_UART2_RXD	126
-#define STA2X11_GPIO127_UART3_TXD	127
-
-/*
- * The APB bridge has its own registers, needed by our users as well.
- * They are accessed with the following read/mask/write function.
- */
-static inline u32
-sta2x11_apbreg_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
-{
-	return __sta2x11_mfd_mask(pdev, reg, mask, val, sta2x11_apbreg);
-}
-
-/* CAN and MLB */
-#define APBREG_BSR	0x00	/* Bridge Status Reg */
-#define APBREG_PAER	0x08	/* Peripherals Address Error Reg */
-#define APBREG_PWAC	0x20	/* Peripheral Write Access Control reg */
-#define APBREG_PRAC	0x40	/* Peripheral Read Access Control reg */
-#define APBREG_PCG	0x60	/* Peripheral Clock Gating Reg */
-#define APBREG_PUR	0x80	/* Peripheral Under Reset Reg */
-#define APBREG_EMU_PCG	0xA0	/* Emulator Peripheral Clock Gating Reg */
-
-#define APBREG_CAN	(1 << 1)
-#define APBREG_MLB	(1 << 3)
-
-/* SARAC */
-#define APBREG_BSR_SARAC     0x100 /* Bridge Status Reg */
-#define APBREG_PAER_SARAC    0x108 /* Peripherals Address Error Reg */
-#define APBREG_PWAC_SARAC    0x120 /* Peripheral Write Access Control reg */
-#define APBREG_PRAC_SARAC    0x140 /* Peripheral Read Access Control reg */
-#define APBREG_PCG_SARAC     0x160 /* Peripheral Clock Gating Reg */
-#define APBREG_PUR_SARAC     0x180 /* Peripheral Under Reset Reg */
-#define APBREG_EMU_PCG_SARAC 0x1A0 /* Emulator Peripheral Clock Gating Reg */
-
-#define APBREG_SARAC	(1 << 2)
-
-/*
- * The system controller has its own registers. Some of these are accessed
- * by out users as well, using the following read/mask/write/function
- */
-static inline
-u32 sta2x11_sctl_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
-{
-	return __sta2x11_mfd_mask(pdev, reg, mask, val, sta2x11_sctl);
-}
-
-#define SCTL_SCCTL		0x00	/* System controller control register */
-#define SCTL_ARMCFG		0x04	/* ARM configuration register */
-#define SCTL_SCPLLCTL		0x08	/* PLL control status register */
-
-#define SCTL_SCPLLCTL_AUDIO_PLL_PD	     BIT(1)
-#define SCTL_SCPLLCTL_FRAC_CONTROL	     BIT(3)
-#define SCTL_SCPLLCTL_STRB_BYPASS	     BIT(6)
-#define SCTL_SCPLLCTL_STRB_INPUT	     BIT(8)
-
-#define SCTL_SCPLLFCTRL		0x0c	/* PLL frequency control register */
-
-#define SCTL_SCPLLFCTRL_AUDIO_PLL_NDIV_MASK	0xff
-#define SCTL_SCPLLFCTRL_AUDIO_PLL_NDIV_SHIFT	  10
-#define SCTL_SCPLLFCTRL_AUDIO_PLL_IDF_MASK	   7
-#define SCTL_SCPLLFCTRL_AUDIO_PLL_IDF_SHIFT	  21
-#define SCTL_SCPLLFCTRL_AUDIO_PLL_ODF_MASK	   7
-#define SCTL_SCPLLFCTRL_AUDIO_PLL_ODF_SHIFT	  18
-#define SCTL_SCPLLFCTRL_DITHER_DISABLE_MASK     0x03
-#define SCTL_SCPLLFCTRL_DITHER_DISABLE_SHIFT       4
-
-
-#define SCTL_SCRESFRACT		0x10	/* PLL fractional input register */
-
-#define SCTL_SCRESFRACT_MASK	0x0000ffff
-
-
-#define SCTL_SCRESCTRL1		0x14	/* Peripheral reset control 1 */
-#define SCTL_SCRESXTRL2		0x18	/* Peripheral reset control 2 */
-#define SCTL_SCPEREN0		0x1c	/* Peripheral clock enable register 0 */
-#define SCTL_SCPEREN1		0x20	/* Peripheral clock enable register 1 */
-#define SCTL_SCPEREN2		0x24	/* Peripheral clock enable register 2 */
-#define SCTL_SCGRST		0x28	/* Peripheral global reset */
-#define SCTL_SCPCIECSBRST       0x2c    /* PCIe PAB CSB reset status register */
-#define SCTL_SCPCIPMCR1		0x30	/* PCI power management control 1 */
-#define SCTL_SCPCIPMCR2		0x34	/* PCI power management control 2 */
-#define SCTL_SCPCIPMSR1		0x38	/* PCI power management status 1 */
-#define SCTL_SCPCIPMSR2		0x3c	/* PCI power management status 2 */
-#define SCTL_SCPCIPMSR3		0x40	/* PCI power management status 3 */
-#define SCTL_SCINTREN		0x44	/* Interrupt enable */
-#define SCTL_SCRISR		0x48	/* RAW interrupt status */
-#define SCTL_SCCLKSTAT0		0x4c	/* Peripheral clocks status 0 */
-#define SCTL_SCCLKSTAT1		0x50	/* Peripheral clocks status 1 */
-#define SCTL_SCCLKSTAT2		0x54	/* Peripheral clocks status 2 */
-#define SCTL_SCRSTSTA		0x58	/* Reset status register */
-
-#define SCTL_SCRESCTRL1_USB_PHY_POR	(1 << 0)
-#define SCTL_SCRESCTRL1_USB_OTG	(1 << 1)
-#define SCTL_SCRESCTRL1_USB_HRST	(1 << 2)
-#define SCTL_SCRESCTRL1_USB_PHY_HOST	(1 << 3)
-#define SCTL_SCRESCTRL1_SATAII	(1 << 4)
-#define SCTL_SCRESCTRL1_VIP		(1 << 5)
-#define SCTL_SCRESCTRL1_PER_MMC0	(1 << 6)
-#define SCTL_SCRESCTRL1_PER_MMC1	(1 << 7)
-#define SCTL_SCRESCTRL1_PER_GPIO0	(1 << 8)
-#define SCTL_SCRESCTRL1_PER_GPIO1	(1 << 9)
-#define SCTL_SCRESCTRL1_PER_GPIO2	(1 << 10)
-#define SCTL_SCRESCTRL1_PER_GPIO3	(1 << 11)
-#define SCTL_SCRESCTRL1_PER_MTU0	(1 << 12)
-#define SCTL_SCRESCTRL1_KER_SPI0	(1 << 13)
-#define SCTL_SCRESCTRL1_KER_SPI1	(1 << 14)
-#define SCTL_SCRESCTRL1_KER_SPI2	(1 << 15)
-#define SCTL_SCRESCTRL1_KER_MCI0	(1 << 16)
-#define SCTL_SCRESCTRL1_KER_MCI1	(1 << 17)
-#define SCTL_SCRESCTRL1_PRE_HSI2C0	(1 << 18)
-#define SCTL_SCRESCTRL1_PER_HSI2C1	(1 << 19)
-#define SCTL_SCRESCTRL1_PER_HSI2C2	(1 << 20)
-#define SCTL_SCRESCTRL1_PER_HSI2C3	(1 << 21)
-#define SCTL_SCRESCTRL1_PER_MSP0	(1 << 22)
-#define SCTL_SCRESCTRL1_PER_MSP1	(1 << 23)
-#define SCTL_SCRESCTRL1_PER_MSP2	(1 << 24)
-#define SCTL_SCRESCTRL1_PER_MSP3	(1 << 25)
-#define SCTL_SCRESCTRL1_PER_MSP4	(1 << 26)
-#define SCTL_SCRESCTRL1_PER_MSP5	(1 << 27)
-#define SCTL_SCRESCTRL1_PER_MMC	(1 << 28)
-#define SCTL_SCRESCTRL1_KER_MSP0	(1 << 29)
-#define SCTL_SCRESCTRL1_KER_MSP1	(1 << 30)
-#define SCTL_SCRESCTRL1_KER_MSP2	(1 << 31)
-
-#define SCTL_SCPEREN0_UART0		(1 << 0)
-#define SCTL_SCPEREN0_UART1		(1 << 1)
-#define SCTL_SCPEREN0_UART2		(1 << 2)
-#define SCTL_SCPEREN0_UART3		(1 << 3)
-#define SCTL_SCPEREN0_MSP0		(1 << 4)
-#define SCTL_SCPEREN0_MSP1		(1 << 5)
-#define SCTL_SCPEREN0_MSP2		(1 << 6)
-#define SCTL_SCPEREN0_MSP3		(1 << 7)
-#define SCTL_SCPEREN0_MSP4		(1 << 8)
-#define SCTL_SCPEREN0_MSP5		(1 << 9)
-#define SCTL_SCPEREN0_SPI0		(1 << 10)
-#define SCTL_SCPEREN0_SPI1		(1 << 11)
-#define SCTL_SCPEREN0_SPI2		(1 << 12)
-#define SCTL_SCPEREN0_I2C0		(1 << 13)
-#define SCTL_SCPEREN0_I2C1		(1 << 14)
-#define SCTL_SCPEREN0_I2C2		(1 << 15)
-#define SCTL_SCPEREN0_I2C3		(1 << 16)
-#define SCTL_SCPEREN0_SVDO_LVDS		(1 << 17)
-#define SCTL_SCPEREN0_USB_HOST		(1 << 18)
-#define SCTL_SCPEREN0_USB_OTG		(1 << 19)
-#define SCTL_SCPEREN0_MCI0		(1 << 20)
-#define SCTL_SCPEREN0_MCI1		(1 << 21)
-#define SCTL_SCPEREN0_MCI2		(1 << 22)
-#define SCTL_SCPEREN0_MCI3		(1 << 23)
-#define SCTL_SCPEREN0_SATA		(1 << 24)
-#define SCTL_SCPEREN0_ETHERNET		(1 << 25)
-#define SCTL_SCPEREN0_VIC		(1 << 26)
-#define SCTL_SCPEREN0_DMA_AUDIO		(1 << 27)
-#define SCTL_SCPEREN0_DMA_SOC		(1 << 28)
-#define SCTL_SCPEREN0_RAM		(1 << 29)
-#define SCTL_SCPEREN0_VIP		(1 << 30)
-#define SCTL_SCPEREN0_ARM		(1 << 31)
-
-#define SCTL_SCPEREN1_UART0		(1 << 0)
-#define SCTL_SCPEREN1_UART1		(1 << 1)
-#define SCTL_SCPEREN1_UART2		(1 << 2)
-#define SCTL_SCPEREN1_UART3		(1 << 3)
-#define SCTL_SCPEREN1_MSP0		(1 << 4)
-#define SCTL_SCPEREN1_MSP1		(1 << 5)
-#define SCTL_SCPEREN1_MSP2		(1 << 6)
-#define SCTL_SCPEREN1_MSP3		(1 << 7)
-#define SCTL_SCPEREN1_MSP4		(1 << 8)
-#define SCTL_SCPEREN1_MSP5		(1 << 9)
-#define SCTL_SCPEREN1_SPI0		(1 << 10)
-#define SCTL_SCPEREN1_SPI1		(1 << 11)
-#define SCTL_SCPEREN1_SPI2		(1 << 12)
-#define SCTL_SCPEREN1_I2C0		(1 << 13)
-#define SCTL_SCPEREN1_I2C1		(1 << 14)
-#define SCTL_SCPEREN1_I2C2		(1 << 15)
-#define SCTL_SCPEREN1_I2C3		(1 << 16)
-#define SCTL_SCPEREN1_USB_PHY		(1 << 17)
-
-/*
- * APB-SOC registers
- */
-static inline
-u32 sta2x11_apb_soc_regs_mask(struct pci_dev *pdev, u32 reg, u32 mask, u32 val)
-{
-	return __sta2x11_mfd_mask(pdev, reg, mask, val, sta2x11_apb_soc_regs);
-}
-
-#define PCIE_EP1_FUNC3_0_INTR_REG	0x000
-#define PCIE_EP1_FUNC7_4_INTR_REG	0x004
-#define PCIE_EP2_FUNC3_0_INTR_REG	0x008
-#define PCIE_EP2_FUNC7_4_INTR_REG	0x00c
-#define PCIE_EP3_FUNC3_0_INTR_REG	0x010
-#define PCIE_EP3_FUNC7_4_INTR_REG	0x014
-#define PCIE_EP4_FUNC3_0_INTR_REG	0x018
-#define PCIE_EP4_FUNC7_4_INTR_REG	0x01c
-#define PCIE_INTR_ENABLE0_REG		0x020
-#define PCIE_INTR_ENABLE1_REG		0x024
-#define PCIE_EP1_FUNC_TC_REG		0x028
-#define PCIE_EP2_FUNC_TC_REG		0x02c
-#define PCIE_EP3_FUNC_TC_REG		0x030
-#define PCIE_EP4_FUNC_TC_REG		0x034
-#define PCIE_EP1_FUNC_F_REG		0x038
-#define PCIE_EP2_FUNC_F_REG		0x03c
-#define PCIE_EP3_FUNC_F_REG		0x040
-#define PCIE_EP4_FUNC_F_REG		0x044
-#define PCIE_PAB_AMBA_SW_RST_REG	0x048
-#define PCIE_PM_STATUS_0_PORT_0_4	0x04c
-#define PCIE_PM_STATUS_7_0_EP1		0x050
-#define PCIE_PM_STATUS_7_0_EP2		0x054
-#define PCIE_PM_STATUS_7_0_EP3		0x058
-#define PCIE_PM_STATUS_7_0_EP4		0x05c
-#define PCIE_DEV_ID_0_EP1_REG		0x060
-#define PCIE_CC_REV_ID_0_EP1_REG	0x064
-#define PCIE_DEV_ID_1_EP1_REG		0x068
-#define PCIE_CC_REV_ID_1_EP1_REG	0x06c
-#define PCIE_DEV_ID_2_EP1_REG		0x070
-#define PCIE_CC_REV_ID_2_EP1_REG	0x074
-#define PCIE_DEV_ID_3_EP1_REG		0x078
-#define PCIE_CC_REV_ID_3_EP1_REG	0x07c
-#define PCIE_DEV_ID_4_EP1_REG		0x080
-#define PCIE_CC_REV_ID_4_EP1_REG	0x084
-#define PCIE_DEV_ID_5_EP1_REG		0x088
-#define PCIE_CC_REV_ID_5_EP1_REG	0x08c
-#define PCIE_DEV_ID_6_EP1_REG		0x090
-#define PCIE_CC_REV_ID_6_EP1_REG	0x094
-#define PCIE_DEV_ID_7_EP1_REG		0x098
-#define PCIE_CC_REV_ID_7_EP1_REG	0x09c
-#define PCIE_DEV_ID_0_EP2_REG		0x0a0
-#define PCIE_CC_REV_ID_0_EP2_REG	0x0a4
-#define PCIE_DEV_ID_1_EP2_REG		0x0a8
-#define PCIE_CC_REV_ID_1_EP2_REG	0x0ac
-#define PCIE_DEV_ID_2_EP2_REG		0x0b0
-#define PCIE_CC_REV_ID_2_EP2_REG	0x0b4
-#define PCIE_DEV_ID_3_EP2_REG		0x0b8
-#define PCIE_CC_REV_ID_3_EP2_REG	0x0bc
-#define PCIE_DEV_ID_4_EP2_REG		0x0c0
-#define PCIE_CC_REV_ID_4_EP2_REG	0x0c4
-#define PCIE_DEV_ID_5_EP2_REG		0x0c8
-#define PCIE_CC_REV_ID_5_EP2_REG	0x0cc
-#define PCIE_DEV_ID_6_EP2_REG		0x0d0
-#define PCIE_CC_REV_ID_6_EP2_REG	0x0d4
-#define PCIE_DEV_ID_7_EP2_REG		0x0d8
-#define PCIE_CC_REV_ID_7_EP2_REG	0x0dC
-#define PCIE_DEV_ID_0_EP3_REG		0x0e0
-#define PCIE_CC_REV_ID_0_EP3_REG	0x0e4
-#define PCIE_DEV_ID_1_EP3_REG		0x0e8
-#define PCIE_CC_REV_ID_1_EP3_REG	0x0ec
-#define PCIE_DEV_ID_2_EP3_REG		0x0f0
-#define PCIE_CC_REV_ID_2_EP3_REG	0x0f4
-#define PCIE_DEV_ID_3_EP3_REG		0x0f8
-#define PCIE_CC_REV_ID_3_EP3_REG	0x0fc
-#define PCIE_DEV_ID_4_EP3_REG		0x100
-#define PCIE_CC_REV_ID_4_EP3_REG	0x104
-#define PCIE_DEV_ID_5_EP3_REG		0x108
-#define PCIE_CC_REV_ID_5_EP3_REG	0x10c
-#define PCIE_DEV_ID_6_EP3_REG		0x110
-#define PCIE_CC_REV_ID_6_EP3_REG	0x114
-#define PCIE_DEV_ID_7_EP3_REG		0x118
-#define PCIE_CC_REV_ID_7_EP3_REG	0x11c
-#define PCIE_DEV_ID_0_EP4_REG		0x120
-#define PCIE_CC_REV_ID_0_EP4_REG	0x124
-#define PCIE_DEV_ID_1_EP4_REG		0x128
-#define PCIE_CC_REV_ID_1_EP4_REG	0x12c
-#define PCIE_DEV_ID_2_EP4_REG		0x130
-#define PCIE_CC_REV_ID_2_EP4_REG	0x134
-#define PCIE_DEV_ID_3_EP4_REG		0x138
-#define PCIE_CC_REV_ID_3_EP4_REG	0x13c
-#define PCIE_DEV_ID_4_EP4_REG		0x140
-#define PCIE_CC_REV_ID_4_EP4_REG	0x144
-#define PCIE_DEV_ID_5_EP4_REG		0x148
-#define PCIE_CC_REV_ID_5_EP4_REG	0x14c
-#define PCIE_DEV_ID_6_EP4_REG		0x150
-#define PCIE_CC_REV_ID_6_EP4_REG	0x154
-#define PCIE_DEV_ID_7_EP4_REG		0x158
-#define PCIE_CC_REV_ID_7_EP4_REG	0x15c
-#define PCIE_SUBSYS_VEN_ID_REG		0x160
-#define PCIE_COMMON_CLOCK_CONFIG_0_4_0	0x164
-#define PCIE_MIPHYP_SSC_EN_REG		0x168
-#define PCIE_MIPHYP_ADDR_REG		0x16c
-#define PCIE_L1_ASPM_READY_REG		0x170
-#define PCIE_EXT_CFG_RDY_REG		0x174
-#define PCIE_SoC_INT_ROUTER_STATUS0_REG 0x178
-#define PCIE_SoC_INT_ROUTER_STATUS1_REG 0x17c
-#define PCIE_SoC_INT_ROUTER_STATUS2_REG 0x180
-#define PCIE_SoC_INT_ROUTER_STATUS3_REG 0x184
-#define DMA_IP_CTRL_REG			0x324
-#define DISP_BRIDGE_PU_PD_CTRL_REG	0x328
-#define VIP_PU_PD_CTRL_REG		0x32c
-#define USB_MLB_PU_PD_CTRL_REG		0x330
-#define SDIO_PU_PD_MISCFUNC_CTRL_REG1	0x334
-#define SDIO_PU_PD_MISCFUNC_CTRL_REG2	0x338
-#define UART_PU_PD_CTRL_REG		0x33c
-#define ARM_Lock			0x340
-#define SYS_IO_CHAR_REG1		0x344
-#define SYS_IO_CHAR_REG2		0x348
-#define SATA_CORE_ID_REG		0x34c
-#define SATA_CTRL_REG			0x350
-#define I2C_HSFIX_MISC_REG		0x354
-#define SPARE2_RESERVED			0x358
-#define SPARE3_RESERVED			0x35c
-#define MASTER_LOCK_REG			0x368
-#define SYSTEM_CONFIG_STATUS_REG	0x36c
-#define MSP_CLK_CTRL_REG		0x39c
-#define COMPENSATION_REG1		0x3c4
-#define COMPENSATION_REG2		0x3c8
-#define COMPENSATION_REG3		0x3cc
-#define TEST_CTL_REG			0x3d0
-
-/*
- * SECR (OTP) registers
- */
-#define STA2X11_SECR_CR			0x00
-#define STA2X11_SECR_FVR0		0x10
-#define STA2X11_SECR_FVR1		0x14
-
-extern int sta2x11_mfd_get_regs_data(struct platform_device *pdev,
-				     enum sta2x11_mfd_plat_dev index,
-				     void __iomem **regs,
-				     spinlock_t **lock);
-
-#endif /* __STA2X11_MFD_H */
diff --git a/include/linux/mfd/stm32-lptimer.h b/include/linux/mfd/stm32-lptimer.h
index 06d3f11dc3c9..a592c8dc716d 100644
--- a/include/linux/mfd/stm32-lptimer.h
+++ b/include/linux/mfd/stm32-lptimer.h
@@ -17,20 +17,30 @@
 #define STM32_LPTIM_IER		0x08	/* Interrupt Enable Reg      */
 #define STM32_LPTIM_CFGR	0x0C	/* Configuration Reg         */
 #define STM32_LPTIM_CR		0x10	/* Control Reg               */
-#define STM32_LPTIM_CMP		0x14	/* Compare Reg               */
+#define STM32_LPTIM_CMP		0x14	/* Compare Reg (MP25 CCR1)   */
 #define STM32_LPTIM_ARR		0x18	/* Autoreload Reg            */
 #define STM32_LPTIM_CNT		0x1C	/* Counter Reg               */
+#define STM32_LPTIM_CCMR1	0x2C	/* Capture/Compare Mode MP25 */
+#define STM32_LPTIM_CCR2	0x34	/* Compare Reg2 MP25         */
+
+#define STM32_LPTIM_HWCFGR2	0x3EC	/* Hardware configuration register 2 - MP25 */
+#define STM32_LPTIM_HWCFGR1	0x3F0	/* Hardware configuration register 1 - MP15 */
+#define STM32_LPTIM_VERR	0x3F4	/* Version identification register - MP15 */
 
 /* STM32_LPTIM_ISR - bit fields */
+#define STM32_LPTIM_DIEROK_ARROK	(BIT(24) | BIT(4)) /* MP25 */
+#define STM32_LPTIM_CMP2_ARROK		(BIT(19) | BIT(4))
 #define STM32_LPTIM_CMPOK_ARROK		GENMASK(4, 3)
 #define STM32_LPTIM_ARROK		BIT(4)
 #define STM32_LPTIM_CMPOK		BIT(3)
 
 /* STM32_LPTIM_ICR - bit fields */
-#define STM32_LPTIM_ARRMCF		BIT(1)
+#define STM32_LPTIM_DIEROKCF_ARROKCF	(BIT(24) | BIT(4)) /* MP25 */
+#define STM32_LPTIM_CMP2OKCF_ARROKCF	(BIT(19) | BIT(4))
 #define STM32_LPTIM_CMPOKCF_ARROKCF	GENMASK(4, 3)
+#define STM32_LPTIM_ARRMCF		BIT(1)
 
-/* STM32_LPTIM_IER - bit flieds */
+/* STM32_LPTIM_IER - bit fields */
 #define STM32_LPTIM_ARRMIE	BIT(1)
 
 /* STM32_LPTIM_CR - bit fields */
@@ -53,16 +63,37 @@
 /* STM32_LPTIM_ARR */
 #define STM32_LPTIM_MAX_ARR	0xFFFF
 
+/* STM32_LPTIM_CCMR1 */
+#define STM32_LPTIM_CC2P	GENMASK(19, 18)
+#define STM32_LPTIM_CC2E	BIT(17)
+#define STM32_LPTIM_CC2SEL	BIT(16)
+#define STM32_LPTIM_CC1P	GENMASK(3, 2)
+#define STM32_LPTIM_CC1E	BIT(1)
+#define STM32_LPTIM_CC1SEL	BIT(0)
+
+/* STM32_LPTIM_HWCFGR1 */
+#define STM32_LPTIM_HWCFGR1_ENCODER	BIT(16)
+
+/* STM32_LPTIM_HWCFGR2 */
+#define STM32_LPTIM_HWCFGR2_CHAN_NUM	GENMASK(3, 0)
+
+/* STM32_LPTIM_VERR */
+#define STM32_LPTIM_VERR_23	0x23	/* STM32MP25 */
+
 /**
  * struct stm32_lptimer - STM32 Low-Power Timer data assigned by parent device
  * @clk: clock reference for this instance
  * @regmap: register map reference for this instance
  * @has_encoder: indicates this Low-Power Timer supports encoder mode
+ * @num_cc_chans: indicates the number of capture/compare channels
+ * @version: indicates the major and minor revision of the controller
  */
 struct stm32_lptimer {
 	struct clk *clk;
 	struct regmap *regmap;
 	bool has_encoder;
+	unsigned int num_cc_chans;
+	u32 version;
 };
 
 #endif
diff --git a/include/linux/mfd/stm32-timers.h b/include/linux/mfd/stm32-timers.h
index 1b94325febb3..23b0cae4a9f8 100644
--- a/include/linux/mfd/stm32-timers.h
+++ b/include/linux/mfd/stm32-timers.h
@@ -12,84 +12,114 @@
 #include <linux/dma-mapping.h>
 #include <linux/regmap.h>
 
-#define TIM_CR1		0x00	/* Control Register 1      */
-#define TIM_CR2		0x04	/* Control Register 2      */
-#define TIM_SMCR	0x08	/* Slave mode control reg  */
-#define TIM_DIER	0x0C	/* DMA/interrupt register  */
-#define TIM_SR		0x10	/* Status register	   */
-#define TIM_EGR		0x14	/* Event Generation Reg    */
-#define TIM_CCMR1	0x18	/* Capt/Comp 1 Mode Reg    */
-#define TIM_CCMR2	0x1C	/* Capt/Comp 2 Mode Reg    */
-#define TIM_CCER	0x20	/* Capt/Comp Enable Reg    */
-#define TIM_CNT		0x24	/* Counter		   */
-#define TIM_PSC		0x28	/* Prescaler               */
-#define TIM_ARR		0x2c	/* Auto-Reload Register    */
-#define TIM_CCR1	0x34	/* Capt/Comp Register 1    */
-#define TIM_CCR2	0x38	/* Capt/Comp Register 2    */
-#define TIM_CCR3	0x3C	/* Capt/Comp Register 3    */
-#define TIM_CCR4	0x40	/* Capt/Comp Register 4    */
-#define TIM_BDTR	0x44	/* Break and Dead-Time Reg */
-#define TIM_DCR		0x48	/* DMA control register    */
-#define TIM_DMAR	0x4C	/* DMA register for transfer */
-#define TIM_TISEL	0x68	/* Input Selection         */
+#define TIM_CR1		0x00			/* Control Register 1			*/
+#define TIM_CR2		0x04			/* Control Register 2			*/
+#define TIM_SMCR	0x08			/* Slave mode control reg		*/
+#define TIM_DIER	0x0C			/* DMA/interrupt register		*/
+#define TIM_SR		0x10			/* Status register			*/
+#define TIM_EGR		0x14			/* Event Generation Reg			*/
+#define TIM_CCMR1	0x18			/* Capt/Comp 1 Mode Reg			*/
+#define TIM_CCMR2	0x1C			/* Capt/Comp 2 Mode Reg			*/
+#define TIM_CCER	0x20			/* Capt/Comp Enable Reg			*/
+#define TIM_CNT		0x24			/* Counter				*/
+#define TIM_PSC		0x28			/* Prescaler				*/
+#define TIM_ARR		0x2c			/* Auto-Reload Register			*/
+#define TIM_CCRx(x)	(0x34 + 4 * ((x) - 1))	/* Capt/Comp Register x (x ∈ {1, .. 4})	*/
+#define TIM_CCR1	TIM_CCRx(1)		/* Capt/Comp Register 1			*/
+#define TIM_CCR2	TIM_CCRx(2)		/* Capt/Comp Register 2			*/
+#define TIM_CCR3	TIM_CCRx(3)		/* Capt/Comp Register 3			*/
+#define TIM_CCR4	TIM_CCRx(4)		/* Capt/Comp Register 4			*/
+#define TIM_BDTR	0x44			/* Break and Dead-Time Reg		*/
+#define TIM_DCR		0x48			/* DMA control register			*/
+#define TIM_DMAR	0x4C			/* DMA register for transfer		*/
+#define TIM_TISEL	0x68			/* Input Selection			*/
+#define TIM_HWCFGR2	0x3EC			/* hardware configuration 2 Reg (MP25)	*/
+#define TIM_HWCFGR1	0x3F0			/* hardware configuration 1 Reg (MP25)	*/
+#define TIM_IPIDR	0x3F8			/* IP identification Reg (MP25)		*/
 
-#define TIM_CR1_CEN	BIT(0)	/* Counter Enable	   */
-#define TIM_CR1_DIR	BIT(4)  /* Counter Direction	   */
-#define TIM_CR1_ARPE	BIT(7)	/* Auto-reload Preload Ena */
-#define TIM_CR2_MMS	(BIT(4) | BIT(5) | BIT(6)) /* Master mode selection */
-#define TIM_CR2_MMS2	GENMASK(23, 20) /* Master mode selection 2 */
-#define TIM_SMCR_SMS	(BIT(0) | BIT(1) | BIT(2)) /* Slave mode selection */
-#define TIM_SMCR_TS	(BIT(4) | BIT(5) | BIT(6)) /* Trigger selection */
-#define TIM_DIER_UIE	BIT(0)	/* Update interrupt	   */
-#define TIM_DIER_UDE	BIT(8)  /* Update DMA request Enable */
-#define TIM_DIER_CC1DE	BIT(9)  /* CC1 DMA request Enable  */
-#define TIM_DIER_CC2DE	BIT(10) /* CC2 DMA request Enable  */
-#define TIM_DIER_CC3DE	BIT(11) /* CC3 DMA request Enable  */
-#define TIM_DIER_CC4DE	BIT(12) /* CC4 DMA request Enable  */
-#define TIM_DIER_COMDE	BIT(13) /* COM DMA request Enable  */
-#define TIM_DIER_TDE	BIT(14) /* Trigger DMA request Enable */
-#define TIM_SR_UIF	BIT(0)	/* Update interrupt flag   */
-#define TIM_EGR_UG	BIT(0)	/* Update Generation       */
-#define TIM_CCMR_PE	BIT(3)	/* Channel Preload Enable  */
-#define TIM_CCMR_M1	(BIT(6) | BIT(5))  /* Channel PWM Mode 1 */
-#define TIM_CCMR_CC1S		(BIT(0) | BIT(1)) /* Capture/compare 1 sel */
-#define TIM_CCMR_IC1PSC		GENMASK(3, 2)	/* Input capture 1 prescaler */
-#define TIM_CCMR_CC2S		(BIT(8) | BIT(9)) /* Capture/compare 2 sel */
-#define TIM_CCMR_IC2PSC		GENMASK(11, 10)	/* Input capture 2 prescaler */
-#define TIM_CCMR_CC1S_TI1	BIT(0)	/* IC1/IC3 selects TI1/TI3 */
-#define TIM_CCMR_CC1S_TI2	BIT(1)	/* IC1/IC3 selects TI2/TI4 */
-#define TIM_CCMR_CC2S_TI2	BIT(8)	/* IC2/IC4 selects TI2/TI4 */
-#define TIM_CCMR_CC2S_TI1	BIT(9)	/* IC2/IC4 selects TI1/TI3 */
-#define TIM_CCER_CC1E	BIT(0)	/* Capt/Comp 1  out Ena    */
-#define TIM_CCER_CC1P	BIT(1)	/* Capt/Comp 1  Polarity   */
-#define TIM_CCER_CC1NE	BIT(2)	/* Capt/Comp 1N out Ena    */
-#define TIM_CCER_CC1NP	BIT(3)	/* Capt/Comp 1N Polarity   */
-#define TIM_CCER_CC2E	BIT(4)	/* Capt/Comp 2  out Ena    */
-#define TIM_CCER_CC2P	BIT(5)	/* Capt/Comp 2  Polarity   */
-#define TIM_CCER_CC3E	BIT(8)	/* Capt/Comp 3  out Ena    */
-#define TIM_CCER_CC3P	BIT(9)	/* Capt/Comp 3  Polarity   */
-#define TIM_CCER_CC4E	BIT(12)	/* Capt/Comp 4  out Ena    */
-#define TIM_CCER_CC4P	BIT(13)	/* Capt/Comp 4  Polarity   */
-#define TIM_CCER_CCXE	(BIT(0) | BIT(4) | BIT(8) | BIT(12))
-#define TIM_BDTR_BKE(x)	BIT(12 + (x) * 12) /* Break input enable */
-#define TIM_BDTR_BKP(x)	BIT(13 + (x) * 12) /* Break input polarity */
-#define TIM_BDTR_AOE	BIT(14)	/* Automatic Output Enable */
-#define TIM_BDTR_MOE	BIT(15)	/* Main Output Enable      */
-#define TIM_BDTR_BKF(x)	(0xf << (16 + (x) * 4))
-#define TIM_DCR_DBA	GENMASK(4, 0)	/* DMA base addr */
-#define TIM_DCR_DBL	GENMASK(12, 8)	/* DMA burst len */
+#define TIM_CR1_CEN		BIT(0)					/* Counter Enable				*/
+#define TIM_CR1_DIR		BIT(4)					/* Counter Direction				*/
+#define TIM_CR1_ARPE		BIT(7)					/* Auto-reload Preload Ena			*/
+#define TIM_CR2_MMS		(BIT(4) | BIT(5) | BIT(6))		/* Master mode selection			*/
+#define TIM_CR2_MMS2		GENMASK(23, 20)				/* Master mode selection 2			*/
+#define TIM_SMCR_SMS		(BIT(0) | BIT(1) | BIT(2))		/* Slave mode selection				*/
+#define TIM_SMCR_TS		(BIT(4) | BIT(5) | BIT(6))		/* Trigger selection				*/
+#define TIM_DIER_UIE		BIT(0)					/* Update interrupt				*/
+#define TIM_DIER_CCxIE(x)	BIT(1 + ((x) - 1))			/* CCx Interrupt Enable	(x ∈ {1, .. 4})		*/
+#define TIM_DIER_CC1IE		TIM_DIER_CCxIE(1)			/* CC1 Interrupt Enable				*/
+#define TIM_DIER_CC2IE		TIM_DIER_CCxIE(2)			/* CC2 Interrupt Enable				*/
+#define TIM_DIER_CC3IE		TIM_DIER_CCxIE(3)			/* CC3 Interrupt Enable				*/
+#define TIM_DIER_CC4IE		TIM_DIER_CCxIE(4)			/* CC4 Interrupt Enable				*/
+#define TIM_DIER_UDE		BIT(8)					/* Update DMA request Enable			*/
+#define TIM_DIER_CCxDE(x)	BIT(9 + ((x) - 1))			/* CCx DMA request Enable (x ∈ {1, .. 4})	*/
+#define TIM_DIER_CC1DE		TIM_DIER_CCxDE(1)			/* CC1 DMA request Enable			*/
+#define TIM_DIER_CC2DE		TIM_DIER_CCxDE(2)			/* CC2 DMA request Enable			*/
+#define TIM_DIER_CC3DE		TIM_DIER_CCxDE(3)			/* CC3 DMA request Enable			*/
+#define TIM_DIER_CC4DE		TIM_DIER_CCxDE(4)			/* CC4 DMA request Enable			*/
+#define TIM_DIER_COMDE		BIT(13)					/* COM DMA request Enable			*/
+#define TIM_DIER_TDE		BIT(14)					/* Trigger DMA request Enable			*/
+#define TIM_SR_UIF		BIT(0)					/* Update interrupt flag			*/
+#define TIM_SR_CC_IF(x)		BIT((x) + 1)				/* CC1, CC2, CC3, CC4 interrupt flag		*/
+#define TIM_EGR_UG		BIT(0)					/* Update Generation				*/
+#define TIM_CCMR_PE		BIT(3)					/* Channel Preload Enable			*/
+#define TIM_CCMR_M1		(BIT(6) | BIT(5))			/* Channel PWM Mode 1				*/
+#define TIM_CCMR_CC1S		(BIT(0) | BIT(1))			/* Capture/compare 1 sel			*/
+#define TIM_CCMR_IC1PSC		GENMASK(3, 2)				/* Input capture 1 prescaler			*/
+#define TIM_CCMR_CC2S		(BIT(8) | BIT(9))			/* Capture/compare 2 sel			*/
+#define TIM_CCMR_IC2PSC		GENMASK(11, 10)				/* Input capture 2 prescaler			*/
+#define TIM_CCMR_CC1S_TI1	BIT(0)					/* IC1/IC3 selects TI1/TI3			*/
+#define TIM_CCMR_CC1S_TI2	BIT(1)					/* IC1/IC3 selects TI2/TI4			*/
+#define TIM_CCMR_CC2S_TI2	BIT(8)					/* IC2/IC4 selects TI2/TI4			*/
+#define TIM_CCMR_CC2S_TI1	BIT(9)					/* IC2/IC4 selects TI1/TI3			*/
+#define TIM_CCMR_CC3S		(BIT(0) | BIT(1))			/* Capture/compare 3 sel			*/
+#define TIM_CCMR_CC4S		(BIT(8) | BIT(9))			/* Capture/compare 4 sel			*/
+#define TIM_CCMR_CC3S_TI3	BIT(0)					/* IC3 selects TI3				*/
+#define TIM_CCMR_CC4S_TI4	BIT(8)					/* IC4 selects TI4				*/
+#define TIM_CCER_CCxE(x)	BIT(0 + 4 * ((x) - 1))			/* Capt/Comp x  out Ena (x ∈ {1, .. 4})		*/
+#define TIM_CCER_CCxP(x)	BIT(1 + 4 * ((x) - 1))			/* Capt/Comp x  Polarity (x ∈ {1, .. 4})	*/
+#define TIM_CCER_CCxNE(x)	BIT(2 + 4 * ((x) - 1))			/* Capt/Comp xN out Ena (x ∈ {1, .. 4})		*/
+#define TIM_CCER_CCxNP(x)	BIT(3 + 4 * ((x) - 1))			/* Capt/Comp xN Polarity (x ∈ {1, .. 4})	*/
+#define TIM_CCER_CC1E		TIM_CCER_CCxE(1)			/* Capt/Comp 1  out Ena				*/
+#define TIM_CCER_CC1P		TIM_CCER_CCxP(1)			/* Capt/Comp 1  Polarity			*/
+#define TIM_CCER_CC1NE		TIM_CCER_CCxNE(1)			/* Capt/Comp 1N out Ena				*/
+#define TIM_CCER_CC1NP		TIM_CCER_CCxNP(1)			/* Capt/Comp 1N Polarity			*/
+#define TIM_CCER_CC2E		TIM_CCER_CCxE(2)			/* Capt/Comp 2  out Ena				*/
+#define TIM_CCER_CC2P		TIM_CCER_CCxP(2)			/* Capt/Comp 2  Polarity			*/
+#define TIM_CCER_CC2NE		TIM_CCER_CCxNE(2)			/* Capt/Comp 2N out Ena				*/
+#define TIM_CCER_CC2NP		TIM_CCER_CCxNP(2)			/* Capt/Comp 2N Polarity			*/
+#define TIM_CCER_CC3E		TIM_CCER_CCxE(3)			/* Capt/Comp 3  out Ena				*/
+#define TIM_CCER_CC3P		TIM_CCER_CCxP(3)			/* Capt/Comp 3  Polarity			*/
+#define TIM_CCER_CC3NE		TIM_CCER_CCxNE(3)			/* Capt/Comp 3N out Ena				*/
+#define TIM_CCER_CC3NP		TIM_CCER_CCxNP(3)			/* Capt/Comp 3N Polarity			*/
+#define TIM_CCER_CC4E		TIM_CCER_CCxE(4)			/* Capt/Comp 4  out Ena				*/
+#define TIM_CCER_CC4P		TIM_CCER_CCxP(4)			/* Capt/Comp 4  Polarity			*/
+#define TIM_CCER_CC4NE		TIM_CCER_CCxNE(4)			/* Capt/Comp 4N out Ena				*/
+#define TIM_CCER_CC4NP		TIM_CCER_CCxNP(4)			/* Capt/Comp 4N Polarity			*/
+#define TIM_CCER_CCXE		(BIT(0) | BIT(4) | BIT(8) | BIT(12))
+#define TIM_BDTR_BKE(x)		BIT(12 + (x) * 12)			/* Break input enable				*/
+#define TIM_BDTR_BKP(x)		BIT(13 + (x) * 12)			/* Break input polarity				*/
+#define TIM_BDTR_AOE		BIT(14)					/* Automatic Output Enable			*/
+#define TIM_BDTR_MOE		BIT(15)					/* Main Output Enable				*/
+#define TIM_BDTR_BKF(x)		(0xf << (16 + (x) * 4))
+#define TIM_DCR_DBA		GENMASK(4, 0)				/* DMA base addr				*/
+#define TIM_DCR_DBL		GENMASK(12, 8)				/* DMA burst len				*/
+#define TIM_HWCFGR1_NB_OF_CC	GENMASK(3, 0)				/* Capture/compare channels			*/
+#define TIM_HWCFGR1_NB_OF_DT	GENMASK(7, 4)				/* Complementary outputs & dead-time generators */
+#define TIM_HWCFGR2_CNT_WIDTH	GENMASK(15, 8)				/* Counter width				*/
 
-#define MAX_TIM_PSC		0xFFFF
-#define MAX_TIM_ICPSC		0x3
-#define TIM_CR2_MMS_SHIFT	4
-#define TIM_CR2_MMS2_SHIFT	20
+#define MAX_TIM_PSC				0xFFFF
+#define MAX_TIM_ICPSC				0x3
+#define TIM_CR2_MMS_SHIFT			4
+#define TIM_CR2_MMS2_SHIFT			20
 #define TIM_SMCR_SMS_SLAVE_MODE_DISABLED	0 /* counts on internal clock when CEN=1 */
 #define TIM_SMCR_SMS_ENCODER_MODE_1		1 /* counts TI1FP1 edges, depending on TI2FP2 level */
 #define TIM_SMCR_SMS_ENCODER_MODE_2		2 /* counts TI2FP2 edges, depending on TI1FP1 level */
 #define TIM_SMCR_SMS_ENCODER_MODE_3		3 /* counts on both TI1FP1 and TI2FP2 edges */
-#define TIM_SMCR_TS_SHIFT	4
-#define TIM_BDTR_BKF_MASK	0xF
-#define TIM_BDTR_BKF_SHIFT(x)	(16 + (x) * 4)
+#define TIM_SMCR_TS_SHIFT			4
+#define TIM_BDTR_BKF_MASK			0xF
+#define TIM_BDTR_BKF_SHIFT(x)			(16 + (x) * 4)
+
+#define STM32MP25_TIM_IPIDR	0x00120002
 
 enum stm32_timers_dmas {
 	STM32_TIMERS_DMA_CH1,
@@ -102,6 +132,15 @@ enum stm32_timers_dmas {
 	STM32_TIMERS_MAX_DMAS,
 };
 
+/* STM32 Timer may have either a unique global interrupt or 4 interrupt lines */
+enum stm32_timers_irqs {
+	STM32_TIMERS_IRQ_GLOBAL_BRK, /* global or brk IRQ */
+	STM32_TIMERS_IRQ_UP,
+	STM32_TIMERS_IRQ_TRG_COM,
+	STM32_TIMERS_IRQ_CC,
+	STM32_TIMERS_MAX_IRQS,
+};
+
 /**
  * struct stm32_timers_dma - STM32 timer DMA handling.
  * @completion:		end of DMA transfer completion
@@ -120,9 +159,12 @@ struct stm32_timers_dma {
 
 struct stm32_timers {
 	struct clk *clk;
+	u32 ipidr;
 	struct regmap *regmap;
 	u32 max_arr;
 	struct stm32_timers_dma dma; /* Only to be used by the parent */
+	unsigned int nr_irqs;
+	int irq[STM32_TIMERS_MAX_IRQS];
 };
 
 #if IS_REACHABLE(CONFIG_MFD_STM32_TIMERS)
diff --git a/include/linux/mfd/stpmic1.h b/include/linux/mfd/stpmic1.h
index fa3f99f7e9a1..dc00bac24f5a 100644
--- a/include/linux/mfd/stpmic1.h
+++ b/include/linux/mfd/stpmic1.h
@@ -15,7 +15,7 @@
 #define RREQ_STATE_SR		0x5
 #define VERSION_SR		0x6
 
-#define SWOFF_PWRCTRL_CR	0x10
+#define MAIN_CR			0x10
 #define PADS_PULL_CR		0x11
 #define BUCKS_PD_CR		0x12
 #define LDO14_PD_CR		0x13
@@ -148,14 +148,14 @@
 #define LDO_BYPASS_MASK			BIT(7)
 
 /* Main PMIC Control Register
- * SWOFF_PWRCTRL_CR
+ * MAIN_CR
  * Address : 0x10
  */
-#define ICC_EVENT_ENABLED		BIT(4)
+#define OCP_OFF_DBG			BIT(4)
 #define PWRCTRL_POLARITY_HIGH		BIT(3)
-#define PWRCTRL_PIN_VALID		BIT(2)
-#define RESTART_REQUEST_ENABLED		BIT(1)
-#define SOFTWARE_SWITCH_OFF_ENABLED	BIT(0)
+#define PWRCTRL_ENABLE			BIT(2)
+#define RESTART_REQUEST_ENABLE		BIT(1)
+#define SOFTWARE_SWITCH_OFF		BIT(0)
 
 /* Main PMIC PADS Control Register
  * PADS_PULL_CR
diff --git a/include/linux/mfd/sun4i-gpadc.h b/include/linux/mfd/sun4i-gpadc.h
index ea0ccf33a459..021f820f9d52 100644
--- a/include/linux/mfd/sun4i-gpadc.h
+++ b/include/linux/mfd/sun4i-gpadc.h
@@ -81,8 +81,8 @@
 #define SUN4I_GPADC_TEMP_DATA				0x20
 #define SUN4I_GPADC_DATA				0x24
 
-#define SUN4I_GPADC_IRQ_FIFO_DATA			0
-#define SUN4I_GPADC_IRQ_TEMP_DATA			1
+#define SUN4I_GPADC_IRQ_FIFO_DATA			1
+#define SUN4I_GPADC_IRQ_TEMP_DATA			2
 
 /* 10s delay before suspending the IP */
 #define SUN4I_GPADC_AUTOSUSPEND_DELAY			10000
diff --git a/include/linux/mfd/syscon.h b/include/linux/mfd/syscon.h
index fecc2fa2a364..aad9c6b50463 100644
--- a/include/linux/mfd/syscon.h
+++ b/include/linux/mfd/syscon.h
@@ -17,20 +17,19 @@
 struct device_node;
 
 #ifdef CONFIG_MFD_SYSCON
-extern struct regmap *device_node_to_regmap(struct device_node *np);
-extern struct regmap *syscon_node_to_regmap(struct device_node *np);
-extern struct regmap *syscon_regmap_lookup_by_compatible(const char *s);
-extern struct regmap *syscon_regmap_lookup_by_phandle(
-					struct device_node *np,
-					const char *property);
-extern struct regmap *syscon_regmap_lookup_by_phandle_args(
-					struct device_node *np,
-					const char *property,
-					int arg_count,
-					unsigned int *out_args);
-extern struct regmap *syscon_regmap_lookup_by_phandle_optional(
-					struct device_node *np,
-					const char *property);
+struct regmap *device_node_to_regmap(struct device_node *np);
+struct regmap *syscon_node_to_regmap(struct device_node *np);
+struct regmap *syscon_regmap_lookup_by_compatible(const char *s);
+struct regmap *syscon_regmap_lookup_by_phandle(struct device_node *np,
+					       const char *property);
+struct regmap *syscon_regmap_lookup_by_phandle_args(struct device_node *np,
+						    const char *property,
+						    int arg_count,
+						    unsigned int *out_args);
+struct regmap *syscon_regmap_lookup_by_phandle_optional(struct device_node *np,
+							const char *property);
+int of_syscon_register_regmap(struct device_node *np,
+			      struct regmap *regmap);
 #else
 static inline struct regmap *device_node_to_regmap(struct device_node *np)
 {
@@ -70,6 +69,12 @@ static inline struct regmap *syscon_regmap_lookup_by_phandle_optional(
 	return NULL;
 }
 
+static inline int of_syscon_register_regmap(struct device_node *np,
+					struct regmap *regmap)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif
 
 #endif /* __LINUX_MFD_SYSCON_H__ */
diff --git a/include/linux/mfd/syscon/atmel-smc.h b/include/linux/mfd/syscon/atmel-smc.h
index e9e24f4c4578..9b9119c742a2 100644
--- a/include/linux/mfd/syscon/atmel-smc.h
+++ b/include/linux/mfd/syscon/atmel-smc.h
@@ -11,9 +11,11 @@
 #ifndef _LINUX_MFD_SYSCON_ATMEL_SMC_H_
 #define _LINUX_MFD_SYSCON_ATMEL_SMC_H_
 
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/regmap.h>
+#include <linux/bits.h>
+#include <linux/types.h>
+
+struct device_node;
+struct regmap;
 
 #define ATMEL_SMC_SETUP(cs)			(((cs) * 0x10))
 #define ATMEL_HSMC_SETUP(layout, cs)		\
diff --git a/include/linux/mfd/tmio.h b/include/linux/mfd/tmio.h
deleted file mode 100644
index eace8ea6cda0..000000000000
--- a/include/linux/mfd/tmio.h
+++ /dev/null
@@ -1,133 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef MFD_TMIO_H
-#define MFD_TMIO_H
-
-#include <linux/device.h>
-#include <linux/fb.h>
-#include <linux/io.h>
-#include <linux/jiffies.h>
-#include <linux/mmc/card.h>
-#include <linux/platform_device.h>
-#include <linux/pm_runtime.h>
-
-#define tmio_ioread8(addr) readb(addr)
-#define tmio_ioread16(addr) readw(addr)
-#define tmio_ioread16_rep(r, b, l) readsw(r, b, l)
-#define tmio_ioread32(addr) \
-	(((u32)readw((addr))) | (((u32)readw((addr) + 2)) << 16))
-
-#define tmio_iowrite8(val, addr) writeb((val), (addr))
-#define tmio_iowrite16(val, addr) writew((val), (addr))
-#define tmio_iowrite16_rep(r, b, l) writesw(r, b, l)
-#define tmio_iowrite32(val, addr) \
-	do { \
-		writew((val),       (addr)); \
-		writew((val) >> 16, (addr) + 2); \
-	} while (0)
-
-#define sd_config_write8(base, shift, reg, val) \
-	tmio_iowrite8((val), (base) + ((reg) << (shift)))
-#define sd_config_write16(base, shift, reg, val) \
-	tmio_iowrite16((val), (base) + ((reg) << (shift)))
-#define sd_config_write32(base, shift, reg, val) \
-	do { \
-		tmio_iowrite16((val), (base) + ((reg) << (shift)));   \
-		tmio_iowrite16((val) >> 16, (base) + ((reg + 2) << (shift))); \
-	} while (0)
-
-/* tmio MMC platform flags */
-/*
- * Some controllers can support a 2-byte block size when the bus width
- * is configured in 4-bit mode.
- */
-#define TMIO_MMC_BLKSZ_2BYTES		BIT(1)
-/*
- * Some controllers can support SDIO IRQ signalling.
- */
-#define TMIO_MMC_SDIO_IRQ		BIT(2)
-
-/* Some features are only available or tested on R-Car Gen2 or later */
-#define TMIO_MMC_MIN_RCAR2		BIT(3)
-
-/*
- * Some controllers require waiting for the SD bus to become
- * idle before writing to some registers.
- */
-#define TMIO_MMC_HAS_IDLE_WAIT		BIT(4)
-
-/*
- * Use the busy timeout feature. Probably all TMIO versions support it. Yet,
- * we don't have documentation for old variants, so we enable only known good
- * variants with this flag. Can be removed once all variants are known good.
- */
-#define TMIO_MMC_USE_BUSY_TIMEOUT	BIT(5)
-
-/*
- * Some controllers have CMD12 automatically
- * issue/non-issue register
- */
-#define TMIO_MMC_HAVE_CMD12_CTRL	BIT(7)
-
-/* Controller has some SDIO status bits which must be 1 */
-#define TMIO_MMC_SDIO_STATUS_SETBITS	BIT(8)
-
-/*
- * Some controllers have a 32-bit wide data port register
- */
-#define TMIO_MMC_32BIT_DATA_PORT	BIT(9)
-
-/*
- * Some controllers allows to set SDx actual clock
- */
-#define TMIO_MMC_CLK_ACTUAL		BIT(10)
-
-/* Some controllers have a CBSY bit */
-#define TMIO_MMC_HAVE_CBSY		BIT(11)
-
-struct dma_chan;
-
-/*
- * data for the MMC controller
- */
-struct tmio_mmc_data {
-	void				*chan_priv_tx;
-	void				*chan_priv_rx;
-	unsigned int			hclk;
-	unsigned long			capabilities;
-	unsigned long			capabilities2;
-	unsigned long			flags;
-	u32				ocr_mask;	/* available voltages */
-	dma_addr_t			dma_rx_offset;
-	unsigned int			max_blk_count;
-	unsigned short			max_segs;
-	void (*set_pwr)(struct platform_device *host, int state);
-	void (*set_clk_div)(struct platform_device *host, int state);
-};
-
-/*
- * data for the NAND controller
- */
-struct tmio_nand_data {
-	struct nand_bbt_descr	*badblock_pattern;
-	struct mtd_partition	*partition;
-	unsigned int		num_partitions;
-	const char *const	*part_parsers;
-};
-
-#define FBIO_TMIO_ACC_WRITE	0x7C639300
-#define FBIO_TMIO_ACC_SYNC	0x7C639301
-
-struct tmio_fb_data {
-	int			(*lcd_set_power)(struct platform_device *fb_dev,
-						 bool on);
-	int			(*lcd_mode)(struct platform_device *fb_dev,
-					    const struct fb_videomode *mode);
-	int			num_modes;
-	struct fb_videomode	*modes;
-
-	/* in mm: size of screen */
-	int			height;
-	int			width;
-};
-
-#endif
diff --git a/include/linux/mfd/tps65010.h b/include/linux/mfd/tps65010.h
index a1fb9bc5311d..5edf1aef1118 100644
--- a/include/linux/mfd/tps65010.h
+++ b/include/linux/mfd/tps65010.h
@@ -28,6 +28,8 @@
 #ifndef __LINUX_I2C_TPS65010_H
 #define __LINUX_I2C_TPS65010_H
 
+struct gpio_chip;
+
 /*
  * ----------------------------------------------------------------------------
  * Registers, all 8 bits
@@ -176,12 +178,10 @@ struct i2c_client;
 
 /**
  * struct tps65010_board - packages GPIO and LED lines
- * @base: the GPIO number to assign to GPIO-1
  * @outmask: bit (N-1) is set to allow GPIO-N to be used as an
  *	(open drain) output
  * @setup: optional callback issued once the GPIOs are valid
  * @teardown: optional callback issued before the GPIOs are invalidated
- * @context: optional parameter passed to setup() and teardown()
  *
  * Board data may be used to package the GPIO (and LED) lines for use
  * in by the generic GPIO and LED frameworks.  The first four GPIOs
@@ -193,12 +193,9 @@ struct i2c_client;
  * devices in their initial states using these GPIOs.
  */
 struct tps65010_board {
-	int				base;
 	unsigned			outmask;
-
-	int		(*setup)(struct i2c_client *client, void *context);
-	int		(*teardown)(struct i2c_client *client, void *context);
-	void		*context;
+	int		(*setup)(struct i2c_client *client, struct gpio_chip *gc);
+	void		(*teardown)(struct i2c_client *client, struct gpio_chip *gc);
 };
 
 #endif /*  __LINUX_I2C_TPS65010_H */
diff --git a/include/linux/mfd/tps65086.h b/include/linux/mfd/tps65086.h
index 16f87cccc003..9185b5cd8371 100644
--- a/include/linux/mfd/tps65086.h
+++ b/include/linux/mfd/tps65086.h
@@ -13,8 +13,9 @@
 #include <linux/regmap.h>
 
 /* List of registers for TPS65086 */
-#define TPS65086_DEVICEID		0x01
-#define TPS65086_IRQ			0x02
+#define TPS65086_DEVICEID1		0x00
+#define TPS65086_DEVICEID2		0x01
+#define TPS65086_IRQ		0x02
 #define TPS65086_IRQ_MASK		0x03
 #define TPS65086_PMICSTAT		0x04
 #define TPS65086_SHUTDNSRC		0x05
@@ -75,10 +76,16 @@
 #define TPS65086_IRQ_SHUTDN_MASK	BIT(3)
 #define TPS65086_IRQ_FAULT_MASK		BIT(7)
 
-/* DEVICEID Register field definitions */
-#define TPS65086_DEVICEID_PART_MASK	GENMASK(3, 0)
-#define TPS65086_DEVICEID_OTP_MASK	GENMASK(5, 4)
-#define TPS65086_DEVICEID_REV_MASK	GENMASK(7, 6)
+/* DEVICEID1 Register field definitions */
+#define TPS6508640_ID			0x00
+#define TPS65086401_ID			0x01
+#define TPS6508641_ID			0x10
+#define TPS65086470_ID			0x70
+
+/* DEVICEID2 Register field definitions */
+#define TPS65086_DEVICEID2_PART_MASK	GENMASK(3, 0)
+#define TPS65086_DEVICEID2_OTP_MASK	GENMASK(5, 4)
+#define TPS65086_DEVICEID2_REV_MASK	GENMASK(7, 6)
 
 /* VID Masks */
 #define BUCK_VID_MASK			GENMASK(7, 1)
@@ -92,6 +99,8 @@ enum tps65086_irqs {
 	TPS65086_IRQ_FAULT,
 };
 
+struct tps65086_regulator_config;
+
 /**
  * struct tps65086 - state holder for the tps65086 driver
  *
@@ -100,6 +109,8 @@ enum tps65086_irqs {
 struct tps65086 {
 	struct device *dev;
 	struct regmap *regmap;
+	unsigned int chip_id;
+	const struct tps65086_regulator_config *reg_config;
 
 	/* IRQ Data */
 	int irq;
diff --git a/include/linux/mfd/tps65219.h b/include/linux/mfd/tps65219.h
index e6826e34e2a6..55234e771ba7 100644
--- a/include/linux/mfd/tps65219.h
+++ b/include/linux/mfd/tps65219.h
@@ -1,25 +1,24 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /*
- * Functions to access TPS65219 Power Management IC.
+ * Functions to access TPS65215/TPS65219 Power Management Integrated Chips
  *
  * Copyright (C) 2022 BayLibre Incorporated - https://www.baylibre.com/
+ * Copyright (C) 2024 Texas Instruments Incorporated - https://www.ti.com/
  */
 
 #ifndef MFD_TPS65219_H
 #define MFD_TPS65219_H
 
 #include <linux/bitops.h>
-#include <linux/notifier.h>
+#include <linux/regmap.h>
 #include <linux/regulator/driver.h>
 
-struct regmap;
-struct regmap_irq_chip_data;
-
-#define TPS65219_1V35					1350000
-#define TPS65219_1V8					1800000
-
-/* TPS chip id list */
-#define TPS65219					0xF0
+/* Chip id list*/
+enum pmic_id {
+	TPS65214,
+	TPS65215,
+	TPS65219,
+};
 
 /* I2C ID for TPS65219 part */
 #define TPS65219_I2C_ID					0x24
@@ -29,15 +28,23 @@ struct regmap_irq_chip_data;
 #define TPS65219_REG_NVM_ID				0x01
 #define TPS65219_REG_ENABLE_CTRL			0x02
 #define TPS65219_REG_BUCKS_CONFIG			0x03
+#define TPS65214_REG_LOCK				0x03
 #define TPS65219_REG_LDO4_VOUT				0x04
+#define TPS65214_REG_LDO1_VOUT_STBY			0x04
 #define TPS65219_REG_LDO3_VOUT				0x05
+#define TPS65215_REG_LDO2_VOUT                          0x05
+#define TPS65214_REG_LDO1_VOUT				0x05
 #define TPS65219_REG_LDO2_VOUT				0x06
+#define TPS65214_REG_LDO2_VOUT				0x06
 #define TPS65219_REG_LDO1_VOUT				0x07
+#define TPS65214_REG_LDO2_VOUT_STBY			0x07
 #define TPS65219_REG_BUCK3_VOUT				0x8
 #define TPS65219_REG_BUCK2_VOUT				0x9
 #define TPS65219_REG_BUCK1_VOUT				0xA
 #define TPS65219_REG_LDO4_SEQUENCE_SLOT			0xB
 #define TPS65219_REG_LDO3_SEQUENCE_SLOT			0xC
+#define TPS65215_REG_LDO2_SEQUENCE_SLOT                 0xC
+#define TPS65214_REG_LDO1_SEQUENCE_SLOT			0xC
 #define TPS65219_REG_LDO2_SEQUENCE_SLOT			0xD
 #define TPS65219_REG_LDO1_SEQUENCE_SLOT			0xE
 #define TPS65219_REG_BUCK3_SEQUENCE_SLOT		0xF
@@ -46,15 +53,21 @@ struct regmap_irq_chip_data;
 #define TPS65219_REG_nRST_SEQUENCE_SLOT			0x12
 #define TPS65219_REG_GPIO_SEQUENCE_SLOT			0x13
 #define TPS65219_REG_GPO2_SEQUENCE_SLOT			0x14
+#define TPS65214_REG_GPIO_GPI_SEQUENCE_SLOT		0x14
 #define TPS65219_REG_GPO1_SEQUENCE_SLOT			0x15
+#define TPS65214_REG_GPO_SEQUENCE_SLOT			0x15
 #define TPS65219_REG_POWER_UP_SLOT_DURATION_1		0x16
 #define TPS65219_REG_POWER_UP_SLOT_DURATION_2		0x17
+/* _SLOT_DURATION_3 doesn't apply to TPS65215*/
 #define TPS65219_REG_POWER_UP_SLOT_DURATION_3		0x18
 #define TPS65219_REG_POWER_UP_SLOT_DURATION_4		0x19
+#define TPS65214_REG_BUCK3_VOUT_STBY				0x19
 #define TPS65219_REG_POWER_DOWN_SLOT_DURATION_1		0x1A
 #define TPS65219_REG_POWER_DOWN_SLOT_DURATION_2		0x1B
 #define TPS65219_REG_POWER_DOWN_SLOT_DURATION_3		0x1C
+#define TPS65214_REG_BUCK2_VOUT_STBY				0x1C
 #define TPS65219_REG_POWER_DOWN_SLOT_DURATION_4		0x1D
+#define TPS65214_REG_BUCK1_VOUT_STBY				0x1D
 #define TPS65219_REG_GENERAL_CONFIG			0x1E
 #define TPS65219_REG_MFP_1_CONFIG			0x1F
 #define TPS65219_REG_MFP_2_CONFIG			0x20
@@ -72,9 +85,19 @@ struct regmap_irq_chip_data;
 #define TPS65219_REG_DISCHARGE_CONFIG			0x2A
 /* main irq registers */
 #define TPS65219_REG_INT_SOURCE				0x2B
-/* 'sub irq' registers */
+
+/* TPS65219 'sub irq' registers */
 #define TPS65219_REG_INT_LDO_3_4			0x2C
 #define TPS65219_REG_INT_LDO_1_2			0x2D
+
+/* TPS65215 specific 'sub irq' registers */
+#define TPS65215_REG_INT_LDO_2				0x2C
+#define TPS65215_REG_INT_LDO_1				0x2D
+
+/* TPS65214 specific 'sub irq' register */
+#define TPS65214_REG_INT_LDO_1_2			0x2D
+
+/* Common TPS65215 & TPS65219 'sub irq' registers */
 #define TPS65219_REG_INT_BUCK_3				0x2E
 #define TPS65219_REG_INT_BUCK_1_2			0x2F
 #define TPS65219_REG_INT_SYSTEM				0x30
@@ -91,6 +114,17 @@ struct regmap_irq_chip_data;
 #define TPS65219_REG_INT_TO_RV_POS			6
 #define TPS65219_REG_INT_PB_POS				7
 
+#define TPS65215_REG_INT_LDO_2_POS			0
+#define TPS65215_REG_INT_LDO_1_POS			1
+
+#define TPS65214_REG_INT_LDO_1_2_POS		0
+#define TPS65214_REG_INT_BUCK_3_POS			1
+#define TPS65214_REG_INT_BUCK_1_2_POS			2
+#define TPS65214_REG_INT_SYS_POS			3
+#define TPS65214_REG_INT_RV_POS				4
+#define TPS65214_REG_INT_TO_RV_POS			5
+#define TPS65214_REG_INT_PB_POS				6
+
 #define TPS65219_REG_USER_NVM_CMD			0x34
 #define TPS65219_REG_POWER_UP_STATUS			0x35
 #define TPS65219_REG_SPARE_2				0x36
@@ -112,6 +146,8 @@ struct regmap_irq_chip_data;
 #define TPS65219_ENABLE_LDO1_EN_MASK			BIT(3)
 #define TPS65219_ENABLE_LDO2_EN_MASK			BIT(4)
 #define TPS65219_ENABLE_LDO3_EN_MASK			BIT(5)
+#define TPS65215_ENABLE_LDO2_EN_MASK                    BIT(5)
+#define TPS65214_ENABLE_LDO1_EN_MASK			BIT(5)
 #define TPS65219_ENABLE_LDO4_EN_MASK			BIT(6)
 /* power ON-OFF sequence slot */
 #define TPS65219_BUCKS_LDOS_SEQUENCE_OFF_SLOT_MASK	GENMASK(3, 0)
@@ -163,20 +199,27 @@ struct regmap_irq_chip_data;
 #define TPS65219_REG_MASK_EFFECT_MASK			GENMASK(2, 1)
 #define TPS65219_REG_MASK_INT_FOR_PB_MASK		BIT(7)
 /* UnderVoltage - Short to GND - OverCurrent*/
-/* LDO3-4 */
+/* LDO3-4: only for TPS65219*/
 #define TPS65219_INT_LDO3_SCG_MASK			BIT(0)
 #define TPS65219_INT_LDO3_OC_MASK			BIT(1)
 #define TPS65219_INT_LDO3_UV_MASK			BIT(2)
 #define TPS65219_INT_LDO4_SCG_MASK			BIT(3)
 #define TPS65219_INT_LDO4_OC_MASK			BIT(4)
 #define TPS65219_INT_LDO4_UV_MASK			BIT(5)
-/* LDO1-2 */
+/* LDO1-2: TPS65214 & TPS65219 */
 #define TPS65219_INT_LDO1_SCG_MASK			BIT(0)
 #define TPS65219_INT_LDO1_OC_MASK			BIT(1)
 #define TPS65219_INT_LDO1_UV_MASK			BIT(2)
 #define TPS65219_INT_LDO2_SCG_MASK			BIT(3)
 #define TPS65219_INT_LDO2_OC_MASK			BIT(4)
 #define TPS65219_INT_LDO2_UV_MASK			BIT(5)
+/* TPS65215 LDO1-2*/
+#define TPS65215_INT_LDO1_SCG_MASK			BIT(0)
+#define TPS65215_INT_LDO1_OC_MASK			BIT(1)
+#define TPS65215_INT_LDO1_UV_MASK			BIT(2)
+#define TPS65215_INT_LDO2_SCG_MASK			BIT(0)
+#define TPS65215_INT_LDO2_OC_MASK			BIT(1)
+#define TPS65215_INT_LDO2_UV_MASK			BIT(2)
 /* BUCK3 */
 #define TPS65219_INT_BUCK3_SCG_MASK			BIT(0)
 #define TPS65219_INT_BUCK3_OC_MASK			BIT(1)
@@ -191,12 +234,13 @@ struct regmap_irq_chip_data;
 #define TPS65219_INT_BUCK2_OC_MASK			BIT(5)
 #define TPS65219_INT_BUCK2_NEG_OC_MASK			BIT(6)
 #define TPS65219_INT_BUCK2_UV_MASK			BIT(7)
-/* Thermal Sensor  */
+/* Thermal Sensor: TPS65219/TPS65215 */
 #define TPS65219_INT_SENSOR_3_WARM_MASK			BIT(0)
+#define TPS65219_INT_SENSOR_3_HOT_MASK			BIT(4)
+/* Thermal Sensor: TPS65219/TPS65215/TPS65214 */
 #define TPS65219_INT_SENSOR_2_WARM_MASK			BIT(1)
 #define TPS65219_INT_SENSOR_1_WARM_MASK			BIT(2)
 #define TPS65219_INT_SENSOR_0_WARM_MASK			BIT(3)
-#define TPS65219_INT_SENSOR_3_HOT_MASK			BIT(4)
 #define TPS65219_INT_SENSOR_2_HOT_MASK			BIT(5)
 #define TPS65219_INT_SENSOR_1_HOT_MASK			BIT(6)
 #define TPS65219_INT_SENSOR_0_HOT_MASK			BIT(7)
@@ -207,6 +251,8 @@ struct regmap_irq_chip_data;
 #define TPS65219_INT_LDO1_RV_MASK			BIT(3)
 #define TPS65219_INT_LDO2_RV_MASK			BIT(4)
 #define TPS65219_INT_LDO3_RV_MASK			BIT(5)
+#define TPS65215_INT_LDO2_RV_MASK			BIT(5)
+#define TPS65214_INT_LDO2_RV_MASK			BIT(5)
 #define TPS65219_INT_LDO4_RV_MASK			BIT(6)
 /* Residual Voltage ShutDown */
 #define TPS65219_INT_BUCK1_RV_SD_MASK			BIT(0)
@@ -215,6 +261,8 @@ struct regmap_irq_chip_data;
 #define TPS65219_INT_LDO1_RV_SD_MASK			BIT(3)
 #define TPS65219_INT_LDO2_RV_SD_MASK			BIT(4)
 #define TPS65219_INT_LDO3_RV_SD_MASK			BIT(5)
+#define TPS65215_INT_LDO2_RV_SD_MASK			BIT(5)
+#define TPS65214_INT_LDO1_RV_SD_MASK			BIT(5)
 #define TPS65219_INT_LDO4_RV_SD_MASK			BIT(6)
 #define TPS65219_INT_TIMEOUT_MASK			BIT(7)
 /* Power Button */
@@ -240,7 +288,15 @@ enum {
 	TPS65219_INT_LDO4_SCG,
 	TPS65219_INT_LDO4_OC,
 	TPS65219_INT_LDO4_UV,
-	/* LDO1-2 */
+	/* TPS65215 LDO1*/
+	TPS65215_INT_LDO1_SCG,
+	TPS65215_INT_LDO1_OC,
+	TPS65215_INT_LDO1_UV,
+	/* TPS65215 LDO2*/
+	TPS65215_INT_LDO2_SCG,
+	TPS65215_INT_LDO2_OC,
+	TPS65215_INT_LDO2_UV,
+	/* LDO1-2: TPS65219/TPS65214 */
 	TPS65219_INT_LDO1_SCG,
 	TPS65219_INT_LDO1_OC,
 	TPS65219_INT_LDO1_UV,
@@ -276,6 +332,8 @@ enum {
 	TPS65219_INT_BUCK3_RV,
 	TPS65219_INT_LDO1_RV,
 	TPS65219_INT_LDO2_RV,
+	TPS65215_INT_LDO2_RV,
+	TPS65214_INT_LDO2_RV,
 	TPS65219_INT_LDO3_RV,
 	TPS65219_INT_LDO4_RV,
 	/* Residual Voltage ShutDown */
@@ -283,6 +341,8 @@ enum {
 	TPS65219_INT_BUCK2_RV_SD,
 	TPS65219_INT_BUCK3_RV_SD,
 	TPS65219_INT_LDO1_RV_SD,
+	TPS65214_INT_LDO1_RV_SD,
+	TPS65215_INT_LDO2_RV_SD,
 	TPS65219_INT_LDO2_RV_SD,
 	TPS65219_INT_LDO3_RV_SD,
 	TPS65219_INT_LDO4_RV_SD,
@@ -292,6 +352,23 @@ enum {
 	TPS65219_INT_PB_RISING_EDGE_DETECT,
 };
 
+enum tps65214_regulator_id {
+	/*
+	 * DCDC's same as TPS65219
+	 * LDO1 maps to TPS65219's LDO3
+	 * LDO2 is the same as TPS65219
+	 *
+	 */
+	TPS65214_LDO_1 = 3,
+	TPS65214_LDO_2 = 4,
+};
+
+enum tps65215_regulator_id {
+	/* DCDC's same as TPS65219 */
+	/* LDO1 is the same as TPS65219 */
+	TPS65215_LDO_2 = 4,
+};
+
 enum tps65219_regulator_id {
 	/* DCDC's */
 	TPS65219_BUCK_1,
@@ -305,11 +382,40 @@ enum tps65219_regulator_id {
 };
 
 /* Number of step-down converters available */
-#define TPS65219_NUM_DCDC		3
+#define TPS6521X_NUM_BUCKS		3
 /* Number of LDO voltage regulators available */
 #define TPS65219_NUM_LDO		4
+#define TPS65215_NUM_LDO		2
+#define TPS65214_NUM_LDO		2
 /* Number of total regulators available */
-#define TPS65219_NUM_REGULATOR		(TPS65219_NUM_DCDC + TPS65219_NUM_LDO)
+#define TPS65219_NUM_REGULATOR		(TPS6521X_NUM_BUCKS + TPS65219_NUM_LDO)
+#define TPS65215_NUM_REGULATOR		(TPS6521X_NUM_BUCKS + TPS65215_NUM_LDO)
+#define TPS65214_NUM_REGULATOR		(TPS6521X_NUM_BUCKS + TPS65214_NUM_LDO)
+
+/* Define the TPS65214 IRQ numbers */
+enum tps65214_irqs {
+	/* INT source registers */
+	TPS65214_TO_RV_SD_SET_IRQ,
+	TPS65214_RV_SET_IRQ,
+	TPS65214_SYS_SET_IRQ,
+	TPS65214_BUCK_1_2_SET_IRQ,
+	TPS65214_BUCK_3_SET_IRQ,
+	TPS65214_LDO_1_2_SET_IRQ,
+	TPS65214_PB_SET_IRQ = 7,
+};
+
+/* Define the TPS65215 IRQ numbers */
+enum tps65215_irqs {
+	/* INT source registers */
+	TPS65215_TO_RV_SD_SET_IRQ,
+	TPS65215_RV_SET_IRQ,
+	TPS65215_SYS_SET_IRQ,
+	TPS65215_BUCK_1_2_SET_IRQ,
+	TPS65215_BUCK_3_SET_IRQ,
+	TPS65215_LDO_1_SET_IRQ,
+	TPS65215_LDO_2_SET_IRQ,
+	TPS65215_PB_SET_IRQ,
+};
 
 /* Define the TPS65219 IRQ numbers */
 enum tps65219_irqs {
@@ -332,14 +438,12 @@ enum tps65219_irqs {
  * @dev: MFD device
  * @regmap: Regmap for accessing the device registers
  * @irq_data: Regmap irq data used for the irq chip
- * @nb: notifier block for the restart handler
  */
 struct tps65219 {
 	struct device *dev;
 	struct regmap *regmap;
 
 	struct regmap_irq_chip_data *irq_data;
-	struct notifier_block nb;
 };
 
 #endif /* MFD_TPS65219_H */
diff --git a/include/linux/mfd/tps65910.h b/include/linux/mfd/tps65910.h
index 701925db75b3..f67ef0a4e041 100644
--- a/include/linux/mfd/tps65910.h
+++ b/include/linux/mfd/tps65910.h
@@ -749,7 +749,7 @@
 #define VDDCTRL_ST_SHIFT                                 0
 
 
-/*Register VDDCTRL_OP  (0x28) bit definitios */
+/*Register VDDCTRL_OP  (0x28) bit definitions */
 #define VDDCTRL_OP_CMD_MASK                              0x80
 #define VDDCTRL_OP_CMD_SHIFT                             7
 #define VDDCTRL_OP_SEL_MASK                              0x7F
diff --git a/include/linux/mfd/tps65912.h b/include/linux/mfd/tps65912.h
index 860ec0a16c96..e5373c302722 100644
--- a/include/linux/mfd/tps65912.h
+++ b/include/linux/mfd/tps65912.h
@@ -314,6 +314,5 @@ struct tps65912 {
 extern const struct regmap_config tps65912_regmap_config;
 
 int tps65912_device_init(struct tps65912 *tps);
-void tps65912_device_exit(struct tps65912 *tps);
 
 #endif /*  __LINUX_MFD_TPS65912_H */
diff --git a/include/linux/mfd/tps6594.h b/include/linux/mfd/tps6594.h
new file mode 100644
index 000000000000..021db8875963
--- /dev/null
+++ b/include/linux/mfd/tps6594.h
@@ -0,0 +1,1346 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Functions to access TPS6594 Power Management IC
+ *
+ * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
+ */
+
+#ifndef __LINUX_MFD_TPS6594_H
+#define __LINUX_MFD_TPS6594_H
+
+#include <linux/device.h>
+#include <linux/regmap.h>
+
+struct regmap_irq_chip_data;
+
+/* Chip id list */
+enum pmic_id {
+	TPS6594,
+	TPS6593,
+	LP8764,
+	TPS65224,
+	TPS652G1,
+};
+
+/* Macro to get page index from register address */
+#define TPS6594_REG_TO_PAGE(reg)	((reg) >> 8)
+
+/* Registers for page 0 */
+#define TPS6594_REG_DEV_REV				0x01
+
+#define TPS6594_REG_NVM_CODE_1				0x02
+#define TPS6594_REG_NVM_CODE_2				0x03
+
+#define TPS6594_REG_BUCKX_CTRL(buck_inst)		(0x04 + ((buck_inst) << 1))
+#define TPS6594_REG_BUCKX_CONF(buck_inst)		(0x05 + ((buck_inst) << 1))
+#define TPS6594_REG_BUCKX_VOUT_1(buck_inst)		(0x0e + ((buck_inst) << 1))
+#define TPS6594_REG_BUCKX_VOUT_2(buck_inst)		(0x0f + ((buck_inst) << 1))
+#define TPS6594_REG_BUCKX_PG_WINDOW(buck_inst)		(0x18 + (buck_inst))
+
+#define TPS6594_REG_LDOX_CTRL(ldo_inst)			(0x1d + (ldo_inst))
+#define TPS6594_REG_LDORTC_CTRL				0x22
+#define TPS6594_REG_LDOX_VOUT(ldo_inst)			(0x23 + (ldo_inst))
+#define TPS6594_REG_LDOX_PG_WINDOW(ldo_inst)		(0x27 + (ldo_inst))
+
+#define TPS6594_REG_VCCA_VMON_CTRL			0x2b
+#define TPS6594_REG_VCCA_PG_WINDOW			0x2c
+#define TPS6594_REG_VMON1_PG_WINDOW			0x2d
+#define TPS6594_REG_VMON1_PG_LEVEL			0x2e
+#define TPS6594_REG_VMON2_PG_WINDOW			0x2f
+#define TPS6594_REG_VMON2_PG_LEVEL			0x30
+
+#define TPS6594_REG_GPIOX_CONF(gpio_inst)		(0x31 + (gpio_inst))
+#define TPS6594_REG_NPWRON_CONF				0x3c
+#define TPS6594_REG_GPIO_OUT_1				0x3d
+#define TPS6594_REG_GPIO_OUT_2				0x3e
+#define TPS6594_REG_GPIO_IN_1				0x3f
+#define TPS6594_REG_GPIO_IN_2				0x40
+#define TPS6594_REG_GPIOX_OUT(gpio_inst)		(TPS6594_REG_GPIO_OUT_1 + (gpio_inst) / 8)
+#define TPS6594_REG_GPIOX_IN(gpio_inst)			(TPS6594_REG_GPIO_IN_1 + (gpio_inst) / 8)
+
+#define TPS6594_REG_RAIL_SEL_1				0x41
+#define TPS6594_REG_RAIL_SEL_2				0x42
+#define TPS6594_REG_RAIL_SEL_3				0x43
+
+#define TPS6594_REG_FSM_TRIG_SEL_1			0x44
+#define TPS6594_REG_FSM_TRIG_SEL_2			0x45
+#define TPS6594_REG_FSM_TRIG_MASK_1			0x46
+#define TPS6594_REG_FSM_TRIG_MASK_2			0x47
+#define TPS6594_REG_FSM_TRIG_MASK_3			0x48
+
+#define TPS6594_REG_MASK_BUCK1_2			0x49
+#define TPS65224_REG_MASK_BUCKS				0x49
+#define TPS6594_REG_MASK_BUCK3_4			0x4a
+#define TPS6594_REG_MASK_BUCK5				0x4b
+#define TPS6594_REG_MASK_LDO1_2				0x4c
+#define TPS65224_REG_MASK_LDOS				0x4c
+#define TPS6594_REG_MASK_LDO3_4				0x4d
+#define TPS6594_REG_MASK_VMON				0x4e
+#define TPS6594_REG_MASK_GPIO_FALL			0x4f
+#define TPS6594_REG_MASK_GPIO_RISE			0x50
+#define TPS6594_REG_MASK_GPIO9_11			0x51
+#define TPS6594_REG_MASK_STARTUP			0x52
+#define TPS6594_REG_MASK_MISC				0x53
+#define TPS6594_REG_MASK_MODERATE_ERR			0x54
+#define TPS6594_REG_MASK_FSM_ERR			0x56
+#define TPS6594_REG_MASK_COMM_ERR			0x57
+#define TPS6594_REG_MASK_READBACK_ERR			0x58
+#define TPS6594_REG_MASK_ESM				0x59
+
+#define TPS6594_REG_INT_TOP				0x5a
+#define TPS6594_REG_INT_BUCK				0x5b
+#define TPS6594_REG_INT_BUCK1_2				0x5c
+#define TPS6594_REG_INT_BUCK3_4				0x5d
+#define TPS6594_REG_INT_BUCK5				0x5e
+#define TPS6594_REG_INT_LDO_VMON			0x5f
+#define TPS6594_REG_INT_LDO1_2				0x60
+#define TPS6594_REG_INT_LDO3_4				0x61
+#define TPS6594_REG_INT_VMON				0x62
+#define TPS6594_REG_INT_GPIO				0x63
+#define TPS6594_REG_INT_GPIO1_8				0x64
+#define TPS6594_REG_INT_STARTUP				0x65
+#define TPS6594_REG_INT_MISC				0x66
+#define TPS6594_REG_INT_MODERATE_ERR			0x67
+#define TPS6594_REG_INT_SEVERE_ERR			0x68
+#define TPS6594_REG_INT_FSM_ERR				0x69
+#define TPS6594_REG_INT_COMM_ERR			0x6a
+#define TPS6594_REG_INT_READBACK_ERR			0x6b
+#define TPS6594_REG_INT_ESM				0x6c
+
+#define TPS6594_REG_STAT_BUCK1_2			0x6d
+#define TPS6594_REG_STAT_BUCK3_4			0x6e
+#define TPS6594_REG_STAT_BUCK5				0x6f
+#define TPS6594_REG_STAT_LDO1_2				0x70
+#define TPS6594_REG_STAT_LDO3_4				0x71
+#define TPS6594_REG_STAT_VMON				0x72
+#define TPS6594_REG_STAT_STARTUP			0x73
+#define TPS6594_REG_STAT_MISC				0x74
+#define TPS6594_REG_STAT_MODERATE_ERR			0x75
+#define TPS6594_REG_STAT_SEVERE_ERR			0x76
+#define TPS6594_REG_STAT_READBACK_ERR			0x77
+
+#define TPS6594_REG_PGOOD_SEL_1				0x78
+#define TPS6594_REG_PGOOD_SEL_2				0x79
+#define TPS6594_REG_PGOOD_SEL_3				0x7a
+#define TPS6594_REG_PGOOD_SEL_4				0x7b
+
+#define TPS6594_REG_PLL_CTRL				0x7c
+
+#define TPS6594_REG_CONFIG_1				0x7d
+#define TPS6594_REG_CONFIG_2				0x7e
+
+#define TPS6594_REG_ENABLE_DRV_REG			0x80
+
+#define TPS6594_REG_MISC_CTRL				0x81
+
+#define TPS6594_REG_ENABLE_DRV_STAT			0x82
+
+#define TPS6594_REG_RECOV_CNT_REG_1			0x83
+#define TPS6594_REG_RECOV_CNT_REG_2			0x84
+
+#define TPS6594_REG_FSM_I2C_TRIGGERS			0x85
+#define TPS6594_REG_FSM_NSLEEP_TRIGGERS			0x86
+
+#define TPS6594_REG_BUCK_RESET_REG			0x87
+
+#define TPS6594_REG_SPREAD_SPECTRUM_1			0x88
+
+#define TPS6594_REG_FREQ_SEL				0x8a
+
+#define TPS6594_REG_FSM_STEP_SIZE			0x8b
+
+#define TPS6594_REG_LDO_RV_TIMEOUT_REG_1		0x8c
+#define TPS6594_REG_LDO_RV_TIMEOUT_REG_2		0x8d
+
+#define TPS6594_REG_USER_SPARE_REGS			0x8e
+
+#define TPS6594_REG_ESM_MCU_START_REG			0x8f
+#define TPS6594_REG_ESM_MCU_DELAY1_REG			0x90
+#define TPS6594_REG_ESM_MCU_DELAY2_REG			0x91
+#define TPS6594_REG_ESM_MCU_MODE_CFG			0x92
+#define TPS6594_REG_ESM_MCU_HMAX_REG			0x93
+#define TPS6594_REG_ESM_MCU_HMIN_REG			0x94
+#define TPS6594_REG_ESM_MCU_LMAX_REG			0x95
+#define TPS6594_REG_ESM_MCU_LMIN_REG			0x96
+#define TPS6594_REG_ESM_MCU_ERR_CNT_REG			0x97
+#define TPS6594_REG_ESM_SOC_START_REG			0x98
+#define TPS6594_REG_ESM_SOC_DELAY1_REG			0x99
+#define TPS6594_REG_ESM_SOC_DELAY2_REG			0x9a
+#define TPS6594_REG_ESM_SOC_MODE_CFG			0x9b
+#define TPS6594_REG_ESM_SOC_HMAX_REG			0x9c
+#define TPS6594_REG_ESM_SOC_HMIN_REG			0x9d
+#define TPS6594_REG_ESM_SOC_LMAX_REG			0x9e
+#define TPS6594_REG_ESM_SOC_LMIN_REG			0x9f
+#define TPS6594_REG_ESM_SOC_ERR_CNT_REG			0xa0
+
+#define TPS6594_REG_REGISTER_LOCK			0xa1
+
+#define TPS65224_REG_SRAM_ACCESS_1			0xa2
+#define TPS65224_REG_SRAM_ACCESS_2			0xa3
+#define TPS65224_REG_SRAM_ADDR_CTRL			0xa4
+#define TPS65224_REG_RECOV_CNT_PFSM_INCR		0xa5
+#define TPS6594_REG_MANUFACTURING_VER			0xa6
+
+#define TPS6594_REG_CUSTOMER_NVM_ID_REG			0xa7
+
+#define TPS6594_REG_VMON_CONF_REG			0xa8
+
+#define TPS6594_REG_SOFT_REBOOT_REG			0xab
+
+#define TPS65224_REG_ADC_CTRL				0xac
+#define TPS65224_REG_ADC_RESULT_REG_1			0xad
+#define TPS65224_REG_ADC_RESULT_REG_2			0xae
+#define TPS6594_REG_RTC_SECONDS				0xb5
+#define TPS6594_REG_RTC_MINUTES				0xb6
+#define TPS6594_REG_RTC_HOURS				0xb7
+#define TPS6594_REG_RTC_DAYS				0xb8
+#define TPS6594_REG_RTC_MONTHS				0xb9
+#define TPS6594_REG_RTC_YEARS				0xba
+#define TPS6594_REG_RTC_WEEKS				0xbb
+
+#define TPS6594_REG_ALARM_SECONDS			0xbc
+#define TPS6594_REG_ALARM_MINUTES			0xbd
+#define TPS6594_REG_ALARM_HOURS				0xbe
+#define TPS6594_REG_ALARM_DAYS				0xbf
+#define TPS6594_REG_ALARM_MONTHS			0xc0
+#define TPS6594_REG_ALARM_YEARS				0xc1
+
+#define TPS6594_REG_RTC_CTRL_1				0xc2
+#define TPS6594_REG_RTC_CTRL_2				0xc3
+#define TPS65224_REG_STARTUP_CTRL			0xc3
+#define TPS6594_REG_RTC_STATUS				0xc4
+#define TPS6594_REG_RTC_INTERRUPTS			0xc5
+#define TPS6594_REG_RTC_COMP_LSB			0xc6
+#define TPS6594_REG_RTC_COMP_MSB			0xc7
+#define TPS6594_REG_RTC_RESET_STATUS			0xc8
+
+#define TPS6594_REG_SCRATCH_PAD_REG_1			0xc9
+#define TPS6594_REG_SCRATCH_PAD_REG_2			0xca
+#define TPS6594_REG_SCRATCH_PAD_REG_3			0xcb
+#define TPS6594_REG_SCRATCH_PAD_REG_4			0xcc
+
+#define TPS6594_REG_PFSM_DELAY_REG_1			0xcd
+#define TPS6594_REG_PFSM_DELAY_REG_2			0xce
+#define TPS6594_REG_PFSM_DELAY_REG_3			0xcf
+#define TPS6594_REG_PFSM_DELAY_REG_4			0xd0
+#define TPS65224_REG_ADC_GAIN_COMP_REG			0xd0
+#define TPS65224_REG_CRC_CALC_CONTROL			0xef
+#define TPS65224_REG_REGMAP_USER_CRC_LOW		0xf0
+#define TPS65224_REG_REGMAP_USER_CRC_HIGH		0xf1
+
+/* Registers for page 1 */
+#define TPS6594_REG_SERIAL_IF_CONFIG			0x11a
+#define TPS6594_REG_I2C1_ID				0x122
+#define TPS6594_REG_I2C2_ID				0x123
+
+/* Registers for page 4 */
+#define TPS6594_REG_WD_ANSWER_REG			0x401
+#define TPS6594_REG_WD_QUESTION_ANSW_CNT		0x402
+#define TPS6594_REG_WD_WIN1_CFG				0x403
+#define TPS6594_REG_WD_WIN2_CFG				0x404
+#define TPS6594_REG_WD_LONGWIN_CFG			0x405
+#define TPS6594_REG_WD_MODE_REG				0x406
+#define TPS6594_REG_WD_QA_CFG				0x407
+#define TPS6594_REG_WD_ERR_STATUS			0x408
+#define TPS6594_REG_WD_THR_CFG				0x409
+#define TPS6594_REG_DWD_FAIL_CNT_REG			0x40a
+
+/* BUCKX_CTRL register field definition */
+#define TPS6594_BIT_BUCK_EN				BIT(0)
+#define TPS6594_BIT_BUCK_FPWM				BIT(1)
+#define TPS6594_BIT_BUCK_FPWM_MP			BIT(2)
+#define TPS6594_BIT_BUCK_VSEL				BIT(3)
+#define TPS6594_BIT_BUCK_VMON_EN			BIT(4)
+#define TPS6594_BIT_BUCK_PLDN				BIT(5)
+#define TPS6594_BIT_BUCK_RV_SEL				BIT(7)
+
+/* TPS6594 BUCKX_CONF register field definition */
+#define TPS6594_MASK_BUCK_SLEW_RATE			GENMASK(2, 0)
+#define TPS6594_MASK_BUCK_ILIM				GENMASK(5, 3)
+
+/* TPS65224 BUCKX_CONF register field definition */
+#define TPS65224_MASK_BUCK_SLEW_RATE			GENMASK(1, 0)
+
+/* TPS6594 BUCKX_PG_WINDOW register field definition */
+#define TPS6594_MASK_BUCK_OV_THR			GENMASK(2, 0)
+#define TPS6594_MASK_BUCK_UV_THR			GENMASK(5, 3)
+
+/* TPS65224 BUCKX_PG_WINDOW register field definition */
+#define TPS65224_MASK_BUCK_VMON_THR			GENMASK(1, 0)
+
+/* TPS6594 BUCKX_VOUT register field definition */
+#define TPS6594_MASK_BUCKS_VSET				GENMASK(7, 0)
+
+/* TPS65224 BUCKX_VOUT register field definition */
+#define TPS65224_MASK_BUCK1_VSET			GENMASK(7, 0)
+#define TPS65224_MASK_BUCKS_VSET			GENMASK(6, 0)
+
+/* LDOX_CTRL register field definition */
+#define TPS6594_BIT_LDO_EN				BIT(0)
+#define TPS6594_BIT_LDO_SLOW_RAMP			BIT(1)
+#define TPS6594_BIT_LDO_VMON_EN				BIT(4)
+#define TPS6594_MASK_LDO_PLDN				GENMASK(6, 5)
+#define TPS6594_BIT_LDO_RV_SEL				BIT(7)
+#define TPS65224_BIT_LDO_DISCHARGE_EN			BIT(5)
+
+/* LDORTC_CTRL register field definition */
+#define TPS6594_BIT_LDORTC_DIS				BIT(0)
+
+/* LDOX_VOUT register field definition */
+#define TPS6594_MASK_LDO123_VSET			GENMASK(6, 1)
+#define TPS6594_MASK_LDO4_VSET				GENMASK(6, 0)
+#define TPS6594_BIT_LDO_BYPASS				BIT(7)
+
+/* LDOX_PG_WINDOW register field definition */
+#define TPS6594_MASK_LDO_OV_THR				GENMASK(2, 0)
+#define TPS6594_MASK_LDO_UV_THR				GENMASK(5, 3)
+
+/* LDOX_PG_WINDOW register field definition */
+#define TPS65224_MASK_LDO_VMON_THR			GENMASK(1, 0)
+
+/* VCCA_VMON_CTRL register field definition */
+#define TPS6594_BIT_VMON_EN				BIT(0)
+#define TPS6594_BIT_VMON1_EN				BIT(1)
+#define TPS6594_BIT_VMON1_RV_SEL			BIT(2)
+#define TPS6594_BIT_VMON2_EN				BIT(3)
+#define TPS6594_BIT_VMON2_RV_SEL			BIT(4)
+#define TPS6594_BIT_VMON_DEGLITCH_SEL			BIT(5)
+#define TPS65224_BIT_VMON_DEGLITCH_SEL			GENMASK(7, 5)
+
+/* VCCA_PG_WINDOW register field definition */
+#define TPS6594_MASK_VCCA_OV_THR			GENMASK(2, 0)
+#define TPS6594_MASK_VCCA_UV_THR			GENMASK(5, 3)
+#define TPS65224_MASK_VCCA_VMON_THR			GENMASK(1, 0)
+#define TPS6594_BIT_VCCA_PG_SET				BIT(6)
+
+/* VMONX_PG_WINDOW register field definition */
+#define TPS6594_MASK_VMONX_OV_THR			GENMASK(2, 0)
+#define TPS6594_MASK_VMONX_UV_THR			GENMASK(5, 3)
+#define TPS6594_BIT_VMONX_RANGE				BIT(6)
+
+/* VMONX_PG_WINDOW register field definition */
+#define TPS65224_MASK_VMONX_THR				GENMASK(1, 0)
+
+/* GPIOX_CONF register field definition */
+#define TPS6594_BIT_GPIO_DIR				BIT(0)
+#define TPS6594_BIT_GPIO_OD				BIT(1)
+#define TPS6594_BIT_GPIO_PU_SEL				BIT(2)
+#define TPS6594_BIT_GPIO_PU_PD_EN			BIT(3)
+#define TPS6594_BIT_GPIO_DEGLITCH_EN			BIT(4)
+#define TPS6594_MASK_GPIO_SEL				GENMASK(7, 5)
+#define TPS65224_MASK_GPIO_SEL				GENMASK(6, 5)
+#define TPS65224_MASK_GPIO_SEL_GPIO6			GENMASK(7, 5)
+
+/* NPWRON_CONF register field definition */
+#define TPS6594_BIT_NRSTOUT_OD				BIT(0)
+#define TPS6594_BIT_ENABLE_PU_SEL			BIT(2)
+#define TPS6594_BIT_ENABLE_PU_PD_EN			BIT(3)
+#define TPS6594_BIT_ENABLE_DEGLITCH_EN			BIT(4)
+#define TPS6594_BIT_ENABLE_POL				BIT(5)
+#define TPS6594_MASK_NPWRON_SEL				GENMASK(7, 6)
+
+/* POWER_ON_CONFIG register field definition */
+#define TPS65224_BIT_NINT_ENDRV_PU_SEL			BIT(0)
+#define TPS65224_BIT_NINT_ENDRV_SEL			BIT(1)
+#define TPS65224_BIT_EN_PB_DEGL				BIT(5)
+#define TPS65224_MASK_EN_PB_VSENSE_CONFIG		GENMASK(7, 6)
+
+/* GPIO_OUT_X register field definition */
+#define TPS6594_BIT_GPIOX_OUT(gpio_inst)		BIT((gpio_inst) % 8)
+
+/* GPIO_IN_X register field definition */
+#define TPS6594_BIT_GPIOX_IN(gpio_inst)			BIT((gpio_inst) % 8)
+#define TPS6594_BIT_NPWRON_IN				BIT(3)
+
+/* GPIO_OUT_X register field definition */
+#define TPS65224_BIT_GPIOX_OUT(gpio_inst)		BIT((gpio_inst))
+
+/* GPIO_IN_X register field definition */
+#define TPS65224_BIT_GPIOX_IN(gpio_inst)		BIT((gpio_inst))
+
+/* RAIL_SEL_1 register field definition */
+#define TPS6594_MASK_BUCK1_GRP_SEL			GENMASK(1, 0)
+#define TPS6594_MASK_BUCK2_GRP_SEL			GENMASK(3, 2)
+#define TPS6594_MASK_BUCK3_GRP_SEL			GENMASK(5, 4)
+#define TPS6594_MASK_BUCK4_GRP_SEL			GENMASK(7, 6)
+
+/* RAIL_SEL_2 register field definition */
+#define TPS6594_MASK_BUCK5_GRP_SEL			GENMASK(1, 0)
+#define TPS6594_MASK_LDO1_GRP_SEL			GENMASK(3, 2)
+#define TPS6594_MASK_LDO2_GRP_SEL			GENMASK(5, 4)
+#define TPS6594_MASK_LDO3_GRP_SEL			GENMASK(7, 6)
+
+/* RAIL_SEL_3 register field definition */
+#define TPS6594_MASK_LDO4_GRP_SEL			GENMASK(1, 0)
+#define TPS6594_MASK_VCCA_GRP_SEL			GENMASK(3, 2)
+#define TPS6594_MASK_VMON1_GRP_SEL			GENMASK(5, 4)
+#define TPS6594_MASK_VMON2_GRP_SEL			GENMASK(7, 6)
+
+/* FSM_TRIG_SEL_1 register field definition */
+#define TPS6594_MASK_MCU_RAIL_TRIG			GENMASK(1, 0)
+#define TPS6594_MASK_SOC_RAIL_TRIG			GENMASK(3, 2)
+#define TPS6594_MASK_OTHER_RAIL_TRIG			GENMASK(5, 4)
+#define TPS6594_MASK_SEVERE_ERR_TRIG			GENMASK(7, 6)
+
+/* FSM_TRIG_SEL_2 register field definition */
+#define TPS6594_MASK_MODERATE_ERR_TRIG			GENMASK(1, 0)
+
+/* FSM_TRIG_MASK_X register field definition */
+#define TPS6594_BIT_GPIOX_FSM_MASK(gpio_inst)		BIT(((gpio_inst) << 1) % 8)
+#define TPS6594_BIT_GPIOX_FSM_MASK_POL(gpio_inst)	BIT(((gpio_inst) << 1) % 8 + 1)
+
+#define TPS65224_BIT_GPIOX_FSM_MASK(gpio_inst)		BIT(((gpio_inst) << 1) % 6)
+#define TPS65224_BIT_GPIOX_FSM_MASK_POL(gpio_inst)	BIT(((gpio_inst) << 1) % 6 + 1)
+
+/* MASK_BUCKX register field definition */
+#define TPS6594_BIT_BUCKX_OV_MASK(buck_inst)		BIT(((buck_inst) << 2) % 8)
+#define TPS6594_BIT_BUCKX_UV_MASK(buck_inst)		BIT(((buck_inst) << 2) % 8 + 1)
+#define TPS6594_BIT_BUCKX_ILIM_MASK(buck_inst)		BIT(((buck_inst) << 2) % 8 + 3)
+
+/* MASK_LDOX register field definition */
+#define TPS6594_BIT_LDOX_OV_MASK(ldo_inst)		BIT(((ldo_inst) << 2) % 8)
+#define TPS6594_BIT_LDOX_UV_MASK(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 1)
+#define TPS6594_BIT_LDOX_ILIM_MASK(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 3)
+
+/* MASK_VMON register field definition */
+#define TPS6594_BIT_VCCA_OV_MASK			BIT(0)
+#define TPS6594_BIT_VCCA_UV_MASK			BIT(1)
+#define TPS6594_BIT_VMON1_OV_MASK			BIT(2)
+#define TPS6594_BIT_VMON1_UV_MASK			BIT(3)
+#define TPS6594_BIT_VMON2_OV_MASK			BIT(5)
+#define TPS6594_BIT_VMON2_UV_MASK			BIT(6)
+
+/* MASK_BUCK Register field definition */
+#define TPS65224_BIT_BUCK1_UVOV_MASK			BIT(0)
+#define TPS65224_BIT_BUCK2_UVOV_MASK			BIT(1)
+#define TPS65224_BIT_BUCK3_UVOV_MASK			BIT(2)
+#define TPS65224_BIT_BUCK4_UVOV_MASK			BIT(4)
+
+/* MASK_LDO_VMON register field definition */
+#define TPS65224_BIT_LDO1_UVOV_MASK			BIT(0)
+#define TPS65224_BIT_LDO2_UVOV_MASK			BIT(1)
+#define TPS65224_BIT_LDO3_UVOV_MASK			BIT(2)
+#define TPS65224_BIT_VCCA_UVOV_MASK			BIT(4)
+#define TPS65224_BIT_VMON1_UVOV_MASK			BIT(5)
+#define TPS65224_BIT_VMON2_UVOV_MASK			BIT(6)
+
+/* MASK_GPIOX register field definition */
+#define TPS6594_BIT_GPIOX_FALL_MASK(gpio_inst)		BIT((gpio_inst) < 8 ? \
+							    (gpio_inst) : (gpio_inst) % 8)
+#define TPS6594_BIT_GPIOX_RISE_MASK(gpio_inst)		BIT((gpio_inst) < 8 ? \
+							    (gpio_inst) : (gpio_inst) % 8 + 3)
+/* MASK_GPIOX register field definition */
+#define TPS65224_BIT_GPIOX_FALL_MASK(gpio_inst)		BIT((gpio_inst))
+#define TPS65224_BIT_GPIOX_RISE_MASK(gpio_inst)		BIT((gpio_inst))
+
+/* MASK_STARTUP register field definition */
+#define TPS6594_BIT_NPWRON_START_MASK			BIT(0)
+#define TPS6594_BIT_ENABLE_MASK				BIT(1)
+#define TPS6594_BIT_FSD_MASK				BIT(4)
+#define TPS6594_BIT_SOFT_REBOOT_MASK			BIT(5)
+#define TPS65224_BIT_VSENSE_MASK			BIT(0)
+#define TPS65224_BIT_PB_SHORT_MASK			BIT(2)
+
+/* MASK_MISC register field definition */
+#define TPS6594_BIT_BIST_PASS_MASK			BIT(0)
+#define TPS6594_BIT_EXT_CLK_MASK			BIT(1)
+#define TPS65224_BIT_REG_UNLOCK_MASK			BIT(2)
+#define TPS6594_BIT_TWARN_MASK				BIT(3)
+#define TPS65224_BIT_PB_LONG_MASK			BIT(4)
+#define TPS65224_BIT_PB_FALL_MASK			BIT(5)
+#define TPS65224_BIT_PB_RISE_MASK			BIT(6)
+#define TPS65224_BIT_ADC_CONV_READY_MASK		BIT(7)
+
+/* MASK_MODERATE_ERR register field definition */
+#define TPS6594_BIT_BIST_FAIL_MASK			BIT(1)
+#define TPS6594_BIT_REG_CRC_ERR_MASK			BIT(2)
+#define TPS6594_BIT_SPMI_ERR_MASK			BIT(4)
+#define TPS6594_BIT_NPWRON_LONG_MASK			BIT(5)
+#define TPS6594_BIT_NINT_READBACK_MASK			BIT(6)
+#define TPS6594_BIT_NRSTOUT_READBACK_MASK		BIT(7)
+
+/* MASK_FSM_ERR register field definition */
+#define TPS6594_BIT_IMM_SHUTDOWN_MASK			BIT(0)
+#define TPS6594_BIT_ORD_SHUTDOWN_MASK			BIT(1)
+#define TPS6594_BIT_MCU_PWR_ERR_MASK			BIT(2)
+#define TPS6594_BIT_SOC_PWR_ERR_MASK			BIT(3)
+#define TPS65224_BIT_COMM_ERR_MASK			BIT(4)
+#define TPS65224_BIT_I2C2_ERR_MASK			BIT(5)
+
+/* MASK_COMM_ERR register field definition */
+#define TPS6594_BIT_COMM_FRM_ERR_MASK			BIT(0)
+#define TPS6594_BIT_COMM_CRC_ERR_MASK			BIT(1)
+#define TPS6594_BIT_COMM_ADR_ERR_MASK			BIT(3)
+#define TPS6594_BIT_I2C2_CRC_ERR_MASK			BIT(5)
+#define TPS6594_BIT_I2C2_ADR_ERR_MASK			BIT(7)
+
+/* MASK_READBACK_ERR register field definition */
+#define TPS6594_BIT_EN_DRV_READBACK_MASK		BIT(0)
+#define TPS6594_BIT_NRSTOUT_SOC_READBACK_MASK		BIT(3)
+
+/* MASK_ESM register field definition */
+#define TPS6594_BIT_ESM_SOC_PIN_MASK			BIT(0)
+#define TPS6594_BIT_ESM_SOC_FAIL_MASK			BIT(1)
+#define TPS6594_BIT_ESM_SOC_RST_MASK			BIT(2)
+#define TPS6594_BIT_ESM_MCU_PIN_MASK			BIT(3)
+#define TPS6594_BIT_ESM_MCU_FAIL_MASK			BIT(4)
+#define TPS6594_BIT_ESM_MCU_RST_MASK			BIT(5)
+
+/* INT_TOP register field definition */
+#define TPS6594_BIT_BUCK_INT				BIT(0)
+#define TPS6594_BIT_LDO_VMON_INT			BIT(1)
+#define TPS6594_BIT_GPIO_INT				BIT(2)
+#define TPS6594_BIT_STARTUP_INT				BIT(3)
+#define TPS6594_BIT_MISC_INT				BIT(4)
+#define TPS6594_BIT_MODERATE_ERR_INT			BIT(5)
+#define TPS6594_BIT_SEVERE_ERR_INT			BIT(6)
+#define TPS6594_BIT_FSM_ERR_INT				BIT(7)
+
+/* INT_BUCK register field definition */
+#define TPS6594_BIT_BUCK1_2_INT				BIT(0)
+#define TPS6594_BIT_BUCK3_4_INT				BIT(1)
+#define TPS6594_BIT_BUCK5_INT				BIT(2)
+
+/* INT_BUCK register field definition */
+#define TPS65224_BIT_BUCK1_UVOV_INT			BIT(0)
+#define TPS65224_BIT_BUCK2_UVOV_INT			BIT(1)
+#define TPS65224_BIT_BUCK3_UVOV_INT			BIT(2)
+#define TPS65224_BIT_BUCK4_UVOV_INT			BIT(3)
+
+/* INT_BUCKX register field definition */
+#define TPS6594_BIT_BUCKX_OV_INT(buck_inst)		BIT(((buck_inst) << 2) % 8)
+#define TPS6594_BIT_BUCKX_UV_INT(buck_inst)		BIT(((buck_inst) << 2) % 8 + 1)
+#define TPS6594_BIT_BUCKX_SC_INT(buck_inst)		BIT(((buck_inst) << 2) % 8 + 2)
+#define TPS6594_BIT_BUCKX_ILIM_INT(buck_inst)		BIT(((buck_inst) << 2) % 8 + 3)
+
+/* INT_LDO_VMON register field definition */
+#define TPS6594_BIT_LDO1_2_INT				BIT(0)
+#define TPS6594_BIT_LDO3_4_INT				BIT(1)
+#define TPS6594_BIT_VCCA_INT				BIT(4)
+
+/* INT_LDO_VMON register field definition */
+#define TPS65224_BIT_LDO1_UVOV_INT			BIT(0)
+#define TPS65224_BIT_LDO2_UVOV_INT			BIT(1)
+#define TPS65224_BIT_LDO3_UVOV_INT			BIT(2)
+#define TPS65224_BIT_VCCA_UVOV_INT			BIT(4)
+#define TPS65224_BIT_VMON1_UVOV_INT			BIT(5)
+#define TPS65224_BIT_VMON2_UVOV_INT			BIT(6)
+
+/* INT_LDOX register field definition */
+#define TPS6594_BIT_LDOX_OV_INT(ldo_inst)		BIT(((ldo_inst) << 2) % 8)
+#define TPS6594_BIT_LDOX_UV_INT(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 1)
+#define TPS6594_BIT_LDOX_SC_INT(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 2)
+#define TPS6594_BIT_LDOX_ILIM_INT(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 3)
+
+/* INT_VMON register field definition */
+#define TPS6594_BIT_VCCA_OV_INT				BIT(0)
+#define TPS6594_BIT_VCCA_UV_INT				BIT(1)
+#define TPS6594_BIT_VMON1_OV_INT			BIT(2)
+#define TPS6594_BIT_VMON1_UV_INT			BIT(3)
+#define TPS6594_BIT_VMON1_RV_INT			BIT(4)
+#define TPS6594_BIT_VMON2_OV_INT			BIT(5)
+#define TPS6594_BIT_VMON2_UV_INT			BIT(6)
+#define TPS6594_BIT_VMON2_RV_INT			BIT(7)
+
+/* INT_GPIO register field definition */
+#define TPS6594_BIT_GPIO9_INT				BIT(0)
+#define TPS6594_BIT_GPIO10_INT				BIT(1)
+#define TPS6594_BIT_GPIO11_INT				BIT(2)
+#define TPS6594_BIT_GPIO1_8_INT				BIT(3)
+
+/* INT_GPIOX register field definition */
+#define TPS6594_BIT_GPIOX_INT(gpio_inst)		BIT(gpio_inst)
+
+/* INT_GPIO register field definition */
+#define TPS65224_BIT_GPIO1_INT				BIT(0)
+#define TPS65224_BIT_GPIO2_INT				BIT(1)
+#define TPS65224_BIT_GPIO3_INT				BIT(2)
+#define TPS65224_BIT_GPIO4_INT				BIT(3)
+#define TPS65224_BIT_GPIO5_INT				BIT(4)
+#define TPS65224_BIT_GPIO6_INT				BIT(5)
+
+/* INT_STARTUP register field definition */
+#define TPS6594_BIT_NPWRON_START_INT			BIT(0)
+#define TPS65224_BIT_VSENSE_INT				BIT(0)
+#define TPS6594_BIT_ENABLE_INT				BIT(1)
+#define TPS6594_BIT_RTC_INT				BIT(2)
+#define TPS65224_BIT_PB_SHORT_INT			BIT(2)
+#define TPS6594_BIT_FSD_INT				BIT(4)
+#define TPS6594_BIT_SOFT_REBOOT_INT			BIT(5)
+
+/* INT_MISC register field definition */
+#define TPS6594_BIT_BIST_PASS_INT			BIT(0)
+#define TPS6594_BIT_EXT_CLK_INT				BIT(1)
+#define TPS65224_BIT_REG_UNLOCK_INT			BIT(2)
+#define TPS6594_BIT_TWARN_INT				BIT(3)
+#define TPS65224_BIT_PB_LONG_INT			BIT(4)
+#define TPS65224_BIT_PB_FALL_INT			BIT(5)
+#define TPS65224_BIT_PB_RISE_INT			BIT(6)
+#define TPS65224_BIT_ADC_CONV_READY_INT			BIT(7)
+
+/* INT_MODERATE_ERR register field definition */
+#define TPS6594_BIT_TSD_ORD_INT				BIT(0)
+#define TPS6594_BIT_BIST_FAIL_INT			BIT(1)
+#define TPS6594_BIT_REG_CRC_ERR_INT			BIT(2)
+#define TPS6594_BIT_RECOV_CNT_INT			BIT(3)
+#define TPS6594_BIT_SPMI_ERR_INT			BIT(4)
+#define TPS6594_BIT_NPWRON_LONG_INT			BIT(5)
+#define TPS6594_BIT_NINT_READBACK_INT			BIT(6)
+#define TPS6594_BIT_NRSTOUT_READBACK_INT		BIT(7)
+
+/* INT_SEVERE_ERR register field definition */
+#define TPS6594_BIT_TSD_IMM_INT				BIT(0)
+#define TPS6594_BIT_VCCA_OVP_INT			BIT(1)
+#define TPS6594_BIT_PFSM_ERR_INT			BIT(2)
+#define TPS65224_BIT_BG_XMON_INT			BIT(3)
+
+/* INT_FSM_ERR register field definition */
+#define TPS6594_BIT_IMM_SHUTDOWN_INT			BIT(0)
+#define TPS6594_BIT_ORD_SHUTDOWN_INT			BIT(1)
+#define TPS6594_BIT_MCU_PWR_ERR_INT			BIT(2)
+#define TPS6594_BIT_SOC_PWR_ERR_INT			BIT(3)
+#define TPS6594_BIT_COMM_ERR_INT			BIT(4)
+#define TPS6594_BIT_READBACK_ERR_INT			BIT(5)
+#define TPS65224_BIT_I2C2_ERR_INT			BIT(5)
+#define TPS6594_BIT_ESM_INT				BIT(6)
+#define TPS6594_BIT_WD_INT				BIT(7)
+
+/* INT_COMM_ERR register field definition */
+#define TPS6594_BIT_COMM_FRM_ERR_INT			BIT(0)
+#define TPS6594_BIT_COMM_CRC_ERR_INT			BIT(1)
+#define TPS6594_BIT_COMM_ADR_ERR_INT			BIT(3)
+#define TPS6594_BIT_I2C2_CRC_ERR_INT			BIT(5)
+#define TPS6594_BIT_I2C2_ADR_ERR_INT			BIT(7)
+
+/* INT_READBACK_ERR register field definition */
+#define TPS6594_BIT_EN_DRV_READBACK_INT			BIT(0)
+#define TPS6594_BIT_NRSTOUT_SOC_READBACK_INT		BIT(3)
+
+/* INT_ESM register field definition */
+#define TPS6594_BIT_ESM_SOC_PIN_INT			BIT(0)
+#define TPS6594_BIT_ESM_SOC_FAIL_INT			BIT(1)
+#define TPS6594_BIT_ESM_SOC_RST_INT			BIT(2)
+#define TPS6594_BIT_ESM_MCU_PIN_INT			BIT(3)
+#define TPS6594_BIT_ESM_MCU_FAIL_INT			BIT(4)
+#define TPS6594_BIT_ESM_MCU_RST_INT			BIT(5)
+
+/* STAT_BUCKX register field definition */
+#define TPS6594_BIT_BUCKX_OV_STAT(buck_inst)		BIT(((buck_inst) << 2) % 8)
+#define TPS6594_BIT_BUCKX_UV_STAT(buck_inst)		BIT(((buck_inst) << 2) % 8 + 1)
+#define TPS6594_BIT_BUCKX_ILIM_STAT(buck_inst)		BIT(((buck_inst) << 2) % 8 + 3)
+
+/* STAT_LDOX register field definition */
+#define TPS6594_BIT_LDOX_OV_STAT(ldo_inst)		BIT(((ldo_inst) << 2) % 8)
+#define TPS6594_BIT_LDOX_UV_STAT(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 1)
+#define TPS6594_BIT_LDOX_ILIM_STAT(ldo_inst)		BIT(((ldo_inst) << 2) % 8 + 3)
+
+/* STAT_VMON register field definition */
+#define TPS6594_BIT_VCCA_OV_STAT			BIT(0)
+#define TPS6594_BIT_VCCA_UV_STAT			BIT(1)
+#define TPS6594_BIT_VMON1_OV_STAT			BIT(2)
+#define TPS6594_BIT_VMON1_UV_STAT			BIT(3)
+#define TPS6594_BIT_VMON2_OV_STAT			BIT(5)
+#define TPS6594_BIT_VMON2_UV_STAT			BIT(6)
+
+/* STAT_LDO_VMON register field definition */
+#define TPS65224_BIT_LDO1_UVOV_STAT			BIT(0)
+#define TPS65224_BIT_LDO2_UVOV_STAT			BIT(1)
+#define TPS65224_BIT_LDO3_UVOV_STAT			BIT(2)
+#define TPS65224_BIT_VCCA_UVOV_STAT			BIT(4)
+#define TPS65224_BIT_VMON1_UVOV_STAT			BIT(5)
+#define TPS65224_BIT_VMON2_UVOV_STAT			BIT(6)
+
+/* STAT_STARTUP register field definition */
+#define TPS65224_BIT_VSENSE_STAT			BIT(0)
+#define TPS6594_BIT_ENABLE_STAT				BIT(1)
+#define TPS65224_BIT_PB_LEVEL_STAT			BIT(2)
+
+/* STAT_MISC register field definition */
+#define TPS6594_BIT_EXT_CLK_STAT			BIT(1)
+#define TPS6594_BIT_TWARN_STAT				BIT(3)
+
+/* STAT_MODERATE_ERR register field definition */
+#define TPS6594_BIT_TSD_ORD_STAT			BIT(0)
+
+/* STAT_SEVERE_ERR register field definition */
+#define TPS6594_BIT_TSD_IMM_STAT			BIT(0)
+#define TPS6594_BIT_VCCA_OVP_STAT			BIT(1)
+#define TPS65224_BIT_BG_XMON_STAT			BIT(3)
+
+/* STAT_READBACK_ERR register field definition */
+#define TPS6594_BIT_EN_DRV_READBACK_STAT		BIT(0)
+#define TPS6594_BIT_NINT_READBACK_STAT			BIT(1)
+#define TPS6594_BIT_NRSTOUT_READBACK_STAT		BIT(2)
+#define TPS6594_BIT_NRSTOUT_SOC_READBACK_STAT		BIT(3)
+
+/* PGOOD_SEL_1 register field definition */
+#define TPS6594_MASK_PGOOD_SEL_BUCK1			GENMASK(1, 0)
+#define TPS6594_MASK_PGOOD_SEL_BUCK2			GENMASK(3, 2)
+#define TPS6594_MASK_PGOOD_SEL_BUCK3			GENMASK(5, 4)
+#define TPS6594_MASK_PGOOD_SEL_BUCK4			GENMASK(7, 6)
+
+/* PGOOD_SEL_2 register field definition */
+#define TPS6594_MASK_PGOOD_SEL_BUCK5			GENMASK(1, 0)
+
+/* PGOOD_SEL_3 register field definition */
+#define TPS6594_MASK_PGOOD_SEL_LDO1			GENMASK(1, 0)
+#define TPS6594_MASK_PGOOD_SEL_LDO2			GENMASK(3, 2)
+#define TPS6594_MASK_PGOOD_SEL_LDO3			GENMASK(5, 4)
+#define TPS6594_MASK_PGOOD_SEL_LDO4			GENMASK(7, 6)
+
+/* PGOOD_SEL_4 register field definition */
+#define TPS6594_BIT_PGOOD_SEL_VCCA			BIT(0)
+#define TPS6594_BIT_PGOOD_SEL_VMON1			BIT(1)
+#define TPS6594_BIT_PGOOD_SEL_VMON2			BIT(2)
+#define TPS6594_BIT_PGOOD_SEL_TDIE_WARN			BIT(3)
+#define TPS6594_BIT_PGOOD_SEL_NRSTOUT			BIT(4)
+#define TPS6594_BIT_PGOOD_SEL_NRSTOUT_SOC		BIT(5)
+#define TPS6594_BIT_PGOOD_POL				BIT(6)
+#define TPS6594_BIT_PGOOD_WINDOW			BIT(7)
+
+/* PLL_CTRL register field definition */
+#define TPS6594_MASK_EXT_CLK_FREQ			GENMASK(1, 0)
+
+/* CONFIG_1 register field definition */
+#define TPS6594_BIT_TWARN_LEVEL				BIT(0)
+#define TPS6594_BIT_TSD_ORD_LEVEL			BIT(1)
+#define TPS6594_BIT_I2C1_HS				BIT(3)
+#define TPS6594_BIT_I2C2_HS				BIT(4)
+#define TPS6594_BIT_EN_ILIM_FSM_CTRL			BIT(5)
+#define TPS6594_BIT_NSLEEP1_MASK			BIT(6)
+#define TPS6594_BIT_NSLEEP2_MASK			BIT(7)
+
+/* CONFIG_2 register field definition */
+#define TPS6594_BIT_BB_CHARGER_EN			BIT(0)
+#define TPS6594_BIT_BB_ICHR				BIT(1)
+#define TPS6594_MASK_BB_VEOC				GENMASK(3, 2)
+#define TPS65224_BIT_I2C1_SPI_CRC_EN			BIT(4)
+#define TPS65224_BIT_I2C2_CRC_EN			BIT(5)
+#define TPS6594_BB_EOC_RDY				BIT(7)
+
+/* ENABLE_DRV_REG register field definition */
+#define TPS6594_BIT_ENABLE_DRV				BIT(0)
+
+/* MISC_CTRL register field definition */
+#define TPS6594_BIT_NRSTOUT				BIT(0)
+#define TPS6594_BIT_NRSTOUT_SOC				BIT(1)
+#define TPS6594_BIT_LPM_EN				BIT(2)
+#define TPS6594_BIT_CLKMON_EN				BIT(3)
+#define TPS6594_BIT_AMUXOUT_EN				BIT(4)
+#define TPS6594_BIT_SEL_EXT_CLK				BIT(5)
+#define TPS6594_MASK_SYNCCLKOUT_FREQ_SEL		GENMASK(7, 6)
+
+/* ENABLE_DRV_STAT register field definition */
+#define TPS6594_BIT_EN_DRV_IN				BIT(0)
+#define TPS6594_BIT_NRSTOUT_IN				BIT(1)
+#define TPS6594_BIT_NRSTOUT_SOC_IN			BIT(2)
+#define TPS6594_BIT_FORCE_EN_DRV_LOW			BIT(3)
+#define TPS6594_BIT_SPMI_LPM_EN				BIT(4)
+#define TPS65224_BIT_TSD_DISABLE			BIT(5)
+
+/* RECOV_CNT_REG_1 register field definition */
+#define TPS6594_MASK_RECOV_CNT				GENMASK(3, 0)
+
+/* RECOV_CNT_REG_2 register field definition */
+#define TPS6594_MASK_RECOV_CNT_THR			GENMASK(3, 0)
+#define TPS6594_BIT_RECOV_CNT_CLR			BIT(4)
+
+/* FSM_I2C_TRIGGERS register field definition */
+#define TPS6594_BIT_TRIGGER_I2C(bit)			BIT(bit)
+
+/* FSM_NSLEEP_TRIGGERS register field definition */
+#define TPS6594_BIT_NSLEEP1B				BIT(0)
+#define TPS6594_BIT_NSLEEP2B				BIT(1)
+
+/* BUCK_RESET_REG register field definition */
+#define TPS6594_BIT_BUCKX_RESET(buck_inst)		BIT(buck_inst)
+
+/* SPREAD_SPECTRUM_1 register field definition */
+#define TPS6594_MASK_SS_DEPTH				GENMASK(1, 0)
+#define TPS6594_BIT_SS_EN				BIT(2)
+
+/* FREQ_SEL register field definition */
+#define TPS6594_BIT_BUCKX_FREQ_SEL(buck_inst)		BIT(buck_inst)
+
+/* FSM_STEP_SIZE register field definition */
+#define TPS6594_MASK_PFSM_DELAY_STEP			GENMASK(4, 0)
+
+/* LDO_RV_TIMEOUT_REG_1 register field definition */
+#define TPS6594_MASK_LDO1_RV_TIMEOUT			GENMASK(3, 0)
+#define TPS6594_MASK_LDO2_RV_TIMEOUT			GENMASK(7, 4)
+
+/* LDO_RV_TIMEOUT_REG_2 register field definition */
+#define TPS6594_MASK_LDO3_RV_TIMEOUT			GENMASK(3, 0)
+#define TPS6594_MASK_LDO4_RV_TIMEOUT			GENMASK(7, 4)
+
+/* USER_SPARE_REGS register field definition */
+#define TPS6594_BIT_USER_SPARE(bit)			BIT(bit)
+
+/* ESM_MCU_START_REG register field definition */
+#define TPS6594_BIT_ESM_MCU_START			BIT(0)
+
+/* ESM_MCU_MODE_CFG register field definition */
+#define TPS6594_MASK_ESM_MCU_ERR_CNT_TH			GENMASK(3, 0)
+#define TPS6594_BIT_ESM_MCU_ENDRV			BIT(5)
+#define TPS6594_BIT_ESM_MCU_EN				BIT(6)
+#define TPS6594_BIT_ESM_MCU_MODE			BIT(7)
+
+/* ESM_MCU_ERR_CNT_REG register field definition */
+#define TPS6594_MASK_ESM_MCU_ERR_CNT			GENMASK(4, 0)
+
+/* ESM_SOC_START_REG register field definition */
+#define TPS6594_BIT_ESM_SOC_START			BIT(0)
+
+/* ESM_MCU_START_REG register field definition */
+#define TPS65224_BIT_ESM_MCU_START			BIT(0)
+
+/* ESM_SOC_MODE_CFG register field definition */
+#define TPS6594_MASK_ESM_SOC_ERR_CNT_TH			GENMASK(3, 0)
+#define TPS6594_BIT_ESM_SOC_ENDRV			BIT(5)
+#define TPS6594_BIT_ESM_SOC_EN				BIT(6)
+#define TPS6594_BIT_ESM_SOC_MODE			BIT(7)
+
+/* ESM_MCU_MODE_CFG register field definition */
+#define TPS65224_MASK_ESM_MCU_ERR_CNT_TH		GENMASK(3, 0)
+#define TPS65224_BIT_ESM_MCU_ENDRV			BIT(5)
+#define TPS65224_BIT_ESM_MCU_EN				BIT(6)
+#define TPS65224_BIT_ESM_MCU_MODE			BIT(7)
+
+/* ESM_SOC_ERR_CNT_REG register field definition */
+#define TPS6594_MASK_ESM_SOC_ERR_CNT			GENMASK(4, 0)
+
+/* ESM_MCU_ERR_CNT_REG register field definition */
+#define TPS6594_MASK_ESM_MCU_ERR_CNT			GENMASK(4, 0)
+
+/* REGISTER_LOCK register field definition */
+#define TPS6594_BIT_REGISTER_LOCK_STATUS		BIT(0)
+
+/* VMON_CONF register field definition */
+#define TPS6594_MASK_VMON1_SLEW_RATE			GENMASK(2, 0)
+#define TPS6594_MASK_VMON2_SLEW_RATE			GENMASK(5, 3)
+
+/* SRAM_ACCESS_1 Register field definition */
+#define TPS65224_MASk_SRAM_UNLOCK_SEQ			GENMASK(7, 0)
+
+/* SRAM_ACCESS_2 Register field definition */
+#define TPS65224_BIT_SRAM_WRITE_MODE			BIT(0)
+#define TPS65224_BIT_OTP_PROG_USER			BIT(1)
+#define TPS65224_BIT_OTP_PROG_PFSM			BIT(2)
+#define TPS65224_BIT_OTP_PROG_STATUS			BIT(3)
+#define TPS65224_BIT_SRAM_UNLOCKED			BIT(6)
+#define TPS65224_USER_PROG_ALLOWED			BIT(7)
+
+/* SRAM_ADDR_CTRL Register field definition */
+#define TPS65224_MASk_SRAM_SEL				GENMASK(1, 0)
+
+/* RECOV_CNT_PFSM_INCR Register field definition */
+#define TPS65224_BIT_INCREMENT_RECOV_CNT		BIT(0)
+
+/* MANUFACTURING_VER Register field definition */
+#define TPS65224_MASK_SILICON_REV			GENMASK(7, 0)
+
+/* CUSTOMER_NVM_ID_REG Register field definition */
+#define TPS65224_MASK_CUSTOMER_NVM_ID			GENMASK(7, 0)
+
+/* SOFT_REBOOT_REG register field definition */
+#define TPS6594_BIT_SOFT_REBOOT				BIT(0)
+
+/* RTC_SECONDS & ALARM_SECONDS register field definition */
+#define TPS6594_MASK_SECOND_0				GENMASK(3, 0)
+#define TPS6594_MASK_SECOND_1				GENMASK(6, 4)
+
+/* RTC_MINUTES & ALARM_MINUTES register field definition */
+#define TPS6594_MASK_MINUTE_0				GENMASK(3, 0)
+#define TPS6594_MASK_MINUTE_1				GENMASK(6, 4)
+
+/* RTC_HOURS & ALARM_HOURS register field definition */
+#define TPS6594_MASK_HOUR_0				GENMASK(3, 0)
+#define TPS6594_MASK_HOUR_1				GENMASK(5, 4)
+#define TPS6594_BIT_PM_NAM				BIT(7)
+
+/* RTC_DAYS & ALARM_DAYS register field definition */
+#define TPS6594_MASK_DAY_0				GENMASK(3, 0)
+#define TPS6594_MASK_DAY_1				GENMASK(5, 4)
+
+/* RTC_MONTHS & ALARM_MONTHS register field definition */
+#define TPS6594_MASK_MONTH_0				GENMASK(3, 0)
+#define TPS6594_BIT_MONTH_1				BIT(4)
+
+/* RTC_YEARS & ALARM_YEARS register field definition */
+#define TPS6594_MASK_YEAR_0				GENMASK(3, 0)
+#define TPS6594_MASK_YEAR_1				GENMASK(7, 4)
+
+/* RTC_WEEKS register field definition */
+#define TPS6594_MASK_WEEK				GENMASK(2, 0)
+
+/* RTC_CTRL_1 register field definition */
+#define TPS6594_BIT_STOP_RTC				BIT(0)
+#define TPS6594_BIT_ROUND_30S				BIT(1)
+#define TPS6594_BIT_AUTO_COMP				BIT(2)
+#define TPS6594_BIT_MODE_12_24				BIT(3)
+#define TPS6594_BIT_SET_32_COUNTER			BIT(5)
+#define TPS6594_BIT_GET_TIME				BIT(6)
+#define TPS6594_BIT_RTC_V_OPT				BIT(7)
+
+/* RTC_CTRL_2 register field definition */
+#define TPS6594_BIT_XTAL_EN				BIT(0)
+#define TPS6594_MASK_XTAL_SEL				GENMASK(2, 1)
+#define TPS6594_BIT_LP_STANDBY_SEL			BIT(3)
+#define TPS6594_BIT_FAST_BIST				BIT(4)
+#define TPS6594_MASK_STARTUP_DEST			GENMASK(6, 5)
+#define TPS6594_BIT_FIRST_STARTUP_DONE			BIT(7)
+
+/* RTC_STATUS register field definition */
+#define TPS6594_BIT_RUN					BIT(1)
+#define TPS6594_BIT_TIMER				BIT(5)
+#define TPS6594_BIT_ALARM				BIT(6)
+#define TPS6594_BIT_POWER_UP				BIT(7)
+
+/* RTC_INTERRUPTS register field definition */
+#define TPS6594_MASK_EVERY				GENMASK(1, 0)
+#define TPS6594_BIT_IT_TIMER				BIT(2)
+#define TPS6594_BIT_IT_ALARM				BIT(3)
+
+/* RTC_RESET_STATUS register field definition */
+#define TPS6594_BIT_RESET_STATUS_RTC			BIT(0)
+
+/* SERIAL_IF_CONFIG register field definition */
+#define TPS6594_BIT_I2C_SPI_SEL				BIT(0)
+#define TPS6594_BIT_I2C1_SPI_CRC_EN			BIT(1)
+#define TPS6594_BIT_I2C2_CRC_EN				BIT(2)
+#define TPS6594_MASK_T_CRC				GENMASK(7, 3)
+
+/* ADC_CTRL Register field definition */
+#define TPS65224_BIT_ADC_START				BIT(0)
+#define TPS65224_BIT_ADC_CONT_CONV			BIT(1)
+#define TPS65224_BIT_ADC_THERMAL_SEL			BIT(2)
+#define TPS65224_BIT_ADC_RDIV_EN			BIT(3)
+#define TPS65224_BIT_ADC_STATUS				BIT(7)
+
+/* ADC_RESULT_REG_1 Register field definition */
+#define TPS65224_MASK_ADC_RESULT_11_4			GENMASK(7, 0)
+
+/* ADC_RESULT_REG_2 Register field definition */
+#define TPS65224_MASK_ADC_RESULT_3_0			GENMASK(7, 4)
+
+/* STARTUP_CTRL Register field definition */
+#define TPS65224_MASK_STARTUP_DEST			GENMASK(6, 5)
+#define TPS65224_BIT_FIRST_STARTUP_DONE			BIT(7)
+
+/* SCRATCH_PAD_REG_1 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_1			GENMASK(7, 0)
+
+/* SCRATCH_PAD_REG_2 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_2			GENMASK(7, 0)
+
+/* SCRATCH_PAD_REG_3 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_3			GENMASK(7, 0)
+
+/* SCRATCH_PAD_REG_4 Register field definition */
+#define TPS6594_MASK_SCRATCH_PAD_4			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_1 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY1			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_2 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY2			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_3 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY3			GENMASK(7, 0)
+
+/* PFSM_DELAY_REG_4 Register field definition */
+#define TPS6594_MASK_PFSM_DELAY4			GENMASK(7, 0)
+
+/* CRC_CALC_CONTROL Register field definition */
+#define TPS65224_BIT_RUN_CRC_BIST			BIT(0)
+#define TPS65224_BIT_RUN_CRC_UPDATE			BIT(1)
+
+/* ADC_GAIN_COMP_REG Register field definition */
+#define TPS65224_MASK_ADC_GAIN_COMP			GENMASK(7, 0)
+
+/* REGMAP_USER_CRC_LOW Register field definition */
+#define TPS65224_MASK_REGMAP_USER_CRC16_LOW		GENMASK(7, 0)
+
+/* REGMAP_USER_CRC_HIGH Register field definition */
+#define TPS65224_MASK_REGMAP_USER_CRC16_HIGH		GENMASK(7, 0)
+
+/* WD_ANSWER_REG Register field definition */
+#define TPS6594_MASK_WD_ANSWER				GENMASK(7, 0)
+
+/* WD_QUESTION_ANSW_CNT register field definition */
+#define TPS6594_MASK_WD_QUESTION			GENMASK(3, 0)
+#define TPS6594_MASK_WD_ANSW_CNT			GENMASK(5, 4)
+#define TPS65224_BIT_INT_TOP_STATUS			BIT(7)
+
+/* WD WIN1_CFG register field definition */
+#define TPS6594_MASK_WD_WIN1_CFG			GENMASK(6, 0)
+
+/* WD WIN2_CFG register field definition */
+#define TPS6594_MASK_WD_WIN2_CFG			GENMASK(6, 0)
+
+/* WD LongWin register field definition */
+#define TPS6594_MASK_WD_LONGWIN_CFG			GENMASK(7, 0)
+
+/* WD_MODE_REG register field definition */
+#define TPS6594_BIT_WD_RETURN_LONGWIN			BIT(0)
+#define TPS6594_BIT_WD_MODE_SELECT			BIT(1)
+#define TPS6594_BIT_WD_PWRHOLD				BIT(2)
+#define TPS65224_BIT_WD_ENDRV_SEL			BIT(6)
+#define TPS65224_BIT_WD_CNT_SEL				BIT(7)
+
+/* WD_QA_CFG register field definition */
+#define TPS6594_MASK_WD_QUESTION_SEED			GENMASK(3, 0)
+#define TPS6594_MASK_WD_QA_LFSR				GENMASK(5, 4)
+#define TPS6594_MASK_WD_QA_FDBK				GENMASK(7, 6)
+
+/* WD_ERR_STATUS register field definition */
+#define TPS6594_BIT_WD_LONGWIN_TIMEOUT_INT		BIT(0)
+#define TPS6594_BIT_WD_TIMEOUT				BIT(1)
+#define TPS6594_BIT_WD_TRIG_EARLY			BIT(2)
+#define TPS6594_BIT_WD_ANSW_EARLY			BIT(3)
+#define TPS6594_BIT_WD_SEQ_ERR				BIT(4)
+#define TPS6594_BIT_WD_ANSW_ERR				BIT(5)
+#define TPS6594_BIT_WD_FAIL_INT				BIT(6)
+#define TPS6594_BIT_WD_RST_INT				BIT(7)
+
+/* WD_THR_CFG register field definition */
+#define TPS6594_MASK_WD_RST_TH				GENMASK(2, 0)
+#define TPS6594_MASK_WD_FAIL_TH				GENMASK(5, 3)
+#define TPS6594_BIT_WD_EN				BIT(6)
+#define TPS6594_BIT_WD_RST_EN				BIT(7)
+
+/* WD_FAIL_CNT_REG register field definition */
+#define TPS6594_MASK_WD_FAIL_CNT			GENMASK(3, 0)
+#define TPS6594_BIT_WD_FIRST_OK				BIT(5)
+#define TPS6594_BIT_WD_BAD_EVENT			BIT(6)
+
+/* CRC8 polynomial for I2C & SPI protocols */
+#define TPS6594_CRC8_POLYNOMIAL	0x07
+
+/* IRQs */
+enum tps6594_irqs {
+	/* INT_BUCK1_2 register */
+	TPS6594_IRQ_BUCK1_OV,
+	TPS6594_IRQ_BUCK1_UV,
+	TPS6594_IRQ_BUCK1_SC,
+	TPS6594_IRQ_BUCK1_ILIM,
+	TPS6594_IRQ_BUCK2_OV,
+	TPS6594_IRQ_BUCK2_UV,
+	TPS6594_IRQ_BUCK2_SC,
+	TPS6594_IRQ_BUCK2_ILIM,
+	/* INT_BUCK3_4 register */
+	TPS6594_IRQ_BUCK3_OV,
+	TPS6594_IRQ_BUCK3_UV,
+	TPS6594_IRQ_BUCK3_SC,
+	TPS6594_IRQ_BUCK3_ILIM,
+	TPS6594_IRQ_BUCK4_OV,
+	TPS6594_IRQ_BUCK4_UV,
+	TPS6594_IRQ_BUCK4_SC,
+	TPS6594_IRQ_BUCK4_ILIM,
+	/* INT_BUCK5 register */
+	TPS6594_IRQ_BUCK5_OV,
+	TPS6594_IRQ_BUCK5_UV,
+	TPS6594_IRQ_BUCK5_SC,
+	TPS6594_IRQ_BUCK5_ILIM,
+	/* INT_LDO1_2 register */
+	TPS6594_IRQ_LDO1_OV,
+	TPS6594_IRQ_LDO1_UV,
+	TPS6594_IRQ_LDO1_SC,
+	TPS6594_IRQ_LDO1_ILIM,
+	TPS6594_IRQ_LDO2_OV,
+	TPS6594_IRQ_LDO2_UV,
+	TPS6594_IRQ_LDO2_SC,
+	TPS6594_IRQ_LDO2_ILIM,
+	/* INT_LDO3_4 register */
+	TPS6594_IRQ_LDO3_OV,
+	TPS6594_IRQ_LDO3_UV,
+	TPS6594_IRQ_LDO3_SC,
+	TPS6594_IRQ_LDO3_ILIM,
+	TPS6594_IRQ_LDO4_OV,
+	TPS6594_IRQ_LDO4_UV,
+	TPS6594_IRQ_LDO4_SC,
+	TPS6594_IRQ_LDO4_ILIM,
+	/* INT_VMON register */
+	TPS6594_IRQ_VCCA_OV,
+	TPS6594_IRQ_VCCA_UV,
+	TPS6594_IRQ_VMON1_OV,
+	TPS6594_IRQ_VMON1_UV,
+	TPS6594_IRQ_VMON1_RV,
+	TPS6594_IRQ_VMON2_OV,
+	TPS6594_IRQ_VMON2_UV,
+	TPS6594_IRQ_VMON2_RV,
+	/* INT_GPIO register */
+	TPS6594_IRQ_GPIO9,
+	TPS6594_IRQ_GPIO10,
+	TPS6594_IRQ_GPIO11,
+	/* INT_GPIO1_8 register */
+	TPS6594_IRQ_GPIO1,
+	TPS6594_IRQ_GPIO2,
+	TPS6594_IRQ_GPIO3,
+	TPS6594_IRQ_GPIO4,
+	TPS6594_IRQ_GPIO5,
+	TPS6594_IRQ_GPIO6,
+	TPS6594_IRQ_GPIO7,
+	TPS6594_IRQ_GPIO8,
+	/* INT_STARTUP register */
+	TPS6594_IRQ_NPWRON_START,
+	TPS6594_IRQ_ENABLE,
+	TPS6594_IRQ_FSD,
+	TPS6594_IRQ_SOFT_REBOOT,
+	/* INT_MISC register */
+	TPS6594_IRQ_BIST_PASS,
+	TPS6594_IRQ_EXT_CLK,
+	TPS6594_IRQ_TWARN,
+	/* INT_MODERATE_ERR register */
+	TPS6594_IRQ_TSD_ORD,
+	TPS6594_IRQ_BIST_FAIL,
+	TPS6594_IRQ_REG_CRC_ERR,
+	TPS6594_IRQ_RECOV_CNT,
+	TPS6594_IRQ_SPMI_ERR,
+	TPS6594_IRQ_NPWRON_LONG,
+	TPS6594_IRQ_NINT_READBACK,
+	TPS6594_IRQ_NRSTOUT_READBACK,
+	/* INT_SEVERE_ERR register */
+	TPS6594_IRQ_TSD_IMM,
+	TPS6594_IRQ_VCCA_OVP,
+	TPS6594_IRQ_PFSM_ERR,
+	/* INT_FSM_ERR register */
+	TPS6594_IRQ_IMM_SHUTDOWN,
+	TPS6594_IRQ_ORD_SHUTDOWN,
+	TPS6594_IRQ_MCU_PWR_ERR,
+	TPS6594_IRQ_SOC_PWR_ERR,
+	/* INT_COMM_ERR register */
+	TPS6594_IRQ_COMM_FRM_ERR,
+	TPS6594_IRQ_COMM_CRC_ERR,
+	TPS6594_IRQ_COMM_ADR_ERR,
+	TPS6594_IRQ_I2C2_CRC_ERR,
+	TPS6594_IRQ_I2C2_ADR_ERR,
+	/* INT_READBACK_ERR register */
+	TPS6594_IRQ_EN_DRV_READBACK,
+	TPS6594_IRQ_NRSTOUT_SOC_READBACK,
+	/* INT_ESM register */
+	TPS6594_IRQ_ESM_SOC_PIN,
+	TPS6594_IRQ_ESM_SOC_FAIL,
+	TPS6594_IRQ_ESM_SOC_RST,
+	/* RTC_STATUS register */
+	TPS6594_IRQ_TIMER,
+	TPS6594_IRQ_ALARM,
+	TPS6594_IRQ_POWER_UP,
+};
+
+#define TPS6594_IRQ_NAME_BUCK1_OV		"buck1_ov"
+#define TPS6594_IRQ_NAME_BUCK1_UV		"buck1_uv"
+#define TPS6594_IRQ_NAME_BUCK1_SC		"buck1_sc"
+#define TPS6594_IRQ_NAME_BUCK1_ILIM		"buck1_ilim"
+#define TPS6594_IRQ_NAME_BUCK2_OV		"buck2_ov"
+#define TPS6594_IRQ_NAME_BUCK2_UV		"buck2_uv"
+#define TPS6594_IRQ_NAME_BUCK2_SC		"buck2_sc"
+#define TPS6594_IRQ_NAME_BUCK2_ILIM		"buck2_ilim"
+#define TPS6594_IRQ_NAME_BUCK3_OV		"buck3_ov"
+#define TPS6594_IRQ_NAME_BUCK3_UV		"buck3_uv"
+#define TPS6594_IRQ_NAME_BUCK3_SC		"buck3_sc"
+#define TPS6594_IRQ_NAME_BUCK3_ILIM		"buck3_ilim"
+#define TPS6594_IRQ_NAME_BUCK4_OV		"buck4_ov"
+#define TPS6594_IRQ_NAME_BUCK4_UV		"buck4_uv"
+#define TPS6594_IRQ_NAME_BUCK4_SC		"buck4_sc"
+#define TPS6594_IRQ_NAME_BUCK4_ILIM		"buck4_ilim"
+#define TPS6594_IRQ_NAME_BUCK5_OV		"buck5_ov"
+#define TPS6594_IRQ_NAME_BUCK5_UV		"buck5_uv"
+#define TPS6594_IRQ_NAME_BUCK5_SC		"buck5_sc"
+#define TPS6594_IRQ_NAME_BUCK5_ILIM		"buck5_ilim"
+#define TPS6594_IRQ_NAME_LDO1_OV		"ldo1_ov"
+#define TPS6594_IRQ_NAME_LDO1_UV		"ldo1_uv"
+#define TPS6594_IRQ_NAME_LDO1_SC		"ldo1_sc"
+#define TPS6594_IRQ_NAME_LDO1_ILIM		"ldo1_ilim"
+#define TPS6594_IRQ_NAME_LDO2_OV		"ldo2_ov"
+#define TPS6594_IRQ_NAME_LDO2_UV		"ldo2_uv"
+#define TPS6594_IRQ_NAME_LDO2_SC		"ldo2_sc"
+#define TPS6594_IRQ_NAME_LDO2_ILIM		"ldo2_ilim"
+#define TPS6594_IRQ_NAME_LDO3_OV		"ldo3_ov"
+#define TPS6594_IRQ_NAME_LDO3_UV		"ldo3_uv"
+#define TPS6594_IRQ_NAME_LDO3_SC		"ldo3_sc"
+#define TPS6594_IRQ_NAME_LDO3_ILIM		"ldo3_ilim"
+#define TPS6594_IRQ_NAME_LDO4_OV		"ldo4_ov"
+#define TPS6594_IRQ_NAME_LDO4_UV		"ldo4_uv"
+#define TPS6594_IRQ_NAME_LDO4_SC		"ldo4_sc"
+#define TPS6594_IRQ_NAME_LDO4_ILIM		"ldo4_ilim"
+#define TPS6594_IRQ_NAME_VCCA_OV		"vcca_ov"
+#define TPS6594_IRQ_NAME_VCCA_UV		"vcca_uv"
+#define TPS6594_IRQ_NAME_VMON1_OV		"vmon1_ov"
+#define TPS6594_IRQ_NAME_VMON1_UV		"vmon1_uv"
+#define TPS6594_IRQ_NAME_VMON1_RV		"vmon1_rv"
+#define TPS6594_IRQ_NAME_VMON2_OV		"vmon2_ov"
+#define TPS6594_IRQ_NAME_VMON2_UV		"vmon2_uv"
+#define TPS6594_IRQ_NAME_VMON2_RV		"vmon2_rv"
+#define TPS6594_IRQ_NAME_GPIO9			"gpio9"
+#define TPS6594_IRQ_NAME_GPIO10			"gpio10"
+#define TPS6594_IRQ_NAME_GPIO11			"gpio11"
+#define TPS6594_IRQ_NAME_GPIO1			"gpio1"
+#define TPS6594_IRQ_NAME_GPIO2			"gpio2"
+#define TPS6594_IRQ_NAME_GPIO3			"gpio3"
+#define TPS6594_IRQ_NAME_GPIO4			"gpio4"
+#define TPS6594_IRQ_NAME_GPIO5			"gpio5"
+#define TPS6594_IRQ_NAME_GPIO6			"gpio6"
+#define TPS6594_IRQ_NAME_GPIO7			"gpio7"
+#define TPS6594_IRQ_NAME_GPIO8			"gpio8"
+#define TPS6594_IRQ_NAME_NPWRON_START		"npwron_start"
+#define TPS6594_IRQ_NAME_ENABLE			"enable"
+#define TPS6594_IRQ_NAME_FSD			"fsd"
+#define TPS6594_IRQ_NAME_SOFT_REBOOT		"soft_reboot"
+#define TPS6594_IRQ_NAME_BIST_PASS		"bist_pass"
+#define TPS6594_IRQ_NAME_EXT_CLK		"ext_clk"
+#define TPS6594_IRQ_NAME_TWARN			"twarn"
+#define TPS6594_IRQ_NAME_TSD_ORD		"tsd_ord"
+#define TPS6594_IRQ_NAME_BIST_FAIL		"bist_fail"
+#define TPS6594_IRQ_NAME_REG_CRC_ERR		"reg_crc_err"
+#define TPS6594_IRQ_NAME_RECOV_CNT		"recov_cnt"
+#define TPS6594_IRQ_NAME_SPMI_ERR		"spmi_err"
+#define TPS6594_IRQ_NAME_NPWRON_LONG		"npwron_long"
+#define TPS6594_IRQ_NAME_NINT_READBACK		"nint_readback"
+#define TPS6594_IRQ_NAME_NRSTOUT_READBACK	"nrstout_readback"
+#define TPS6594_IRQ_NAME_TSD_IMM		"tsd_imm"
+#define TPS6594_IRQ_NAME_VCCA_OVP		"vcca_ovp"
+#define TPS6594_IRQ_NAME_PFSM_ERR		"pfsm_err"
+#define TPS6594_IRQ_NAME_IMM_SHUTDOWN		"imm_shutdown"
+#define TPS6594_IRQ_NAME_ORD_SHUTDOWN		"ord_shutdown"
+#define TPS6594_IRQ_NAME_MCU_PWR_ERR		"mcu_pwr_err"
+#define TPS6594_IRQ_NAME_SOC_PWR_ERR		"soc_pwr_err"
+#define TPS6594_IRQ_NAME_COMM_FRM_ERR		"comm_frm_err"
+#define TPS6594_IRQ_NAME_COMM_CRC_ERR		"comm_crc_err"
+#define TPS6594_IRQ_NAME_COMM_ADR_ERR		"comm_adr_err"
+#define TPS6594_IRQ_NAME_EN_DRV_READBACK	"en_drv_readback"
+#define TPS6594_IRQ_NAME_NRSTOUT_SOC_READBACK	"nrstout_soc_readback"
+#define TPS6594_IRQ_NAME_ESM_SOC_PIN		"esm_soc_pin"
+#define TPS6594_IRQ_NAME_ESM_SOC_FAIL		"esm_soc_fail"
+#define TPS6594_IRQ_NAME_ESM_SOC_RST		"esm_soc_rst"
+#define TPS6594_IRQ_NAME_TIMER			"timer"
+#define TPS6594_IRQ_NAME_ALARM			"alarm"
+#define TPS6594_IRQ_NAME_POWERUP		"powerup"
+
+/* IRQs */
+enum tps65224_irqs {
+	/* INT_BUCK register */
+	TPS65224_IRQ_BUCK1_UVOV,
+	TPS65224_IRQ_BUCK2_UVOV,
+	TPS65224_IRQ_BUCK3_UVOV,
+	TPS65224_IRQ_BUCK4_UVOV,
+	/* INT_LDO_VMON register */
+	TPS65224_IRQ_LDO1_UVOV,
+	TPS65224_IRQ_LDO2_UVOV,
+	TPS65224_IRQ_LDO3_UVOV,
+	TPS65224_IRQ_VCCA_UVOV,
+	TPS65224_IRQ_VMON1_UVOV,
+	TPS65224_IRQ_VMON2_UVOV,
+	/* INT_GPIO register */
+	TPS65224_IRQ_GPIO1,
+	TPS65224_IRQ_GPIO2,
+	TPS65224_IRQ_GPIO3,
+	TPS65224_IRQ_GPIO4,
+	TPS65224_IRQ_GPIO5,
+	TPS65224_IRQ_GPIO6,
+	/* INT_STARTUP register */
+	TPS65224_IRQ_VSENSE,
+	TPS65224_IRQ_ENABLE,
+	TPS65224_IRQ_PB_SHORT,
+	TPS65224_IRQ_FSD,
+	TPS65224_IRQ_SOFT_REBOOT,
+	/* INT_MISC register */
+	TPS65224_IRQ_BIST_PASS,
+	TPS65224_IRQ_EXT_CLK,
+	TPS65224_IRQ_REG_UNLOCK,
+	TPS65224_IRQ_TWARN,
+	TPS65224_IRQ_PB_LONG,
+	TPS65224_IRQ_PB_FALL,
+	TPS65224_IRQ_PB_RISE,
+	TPS65224_IRQ_ADC_CONV_READY,
+	/* INT_MODERATE_ERR register */
+	TPS65224_IRQ_TSD_ORD,
+	TPS65224_IRQ_BIST_FAIL,
+	TPS65224_IRQ_REG_CRC_ERR,
+	TPS65224_IRQ_RECOV_CNT,
+	/* INT_SEVERE_ERR register */
+	TPS65224_IRQ_TSD_IMM,
+	TPS65224_IRQ_VCCA_OVP,
+	TPS65224_IRQ_PFSM_ERR,
+	TPS65224_IRQ_BG_XMON,
+	/* INT_FSM_ERR register */
+	TPS65224_IRQ_IMM_SHUTDOWN,
+	TPS65224_IRQ_ORD_SHUTDOWN,
+	TPS65224_IRQ_MCU_PWR_ERR,
+	TPS65224_IRQ_SOC_PWR_ERR,
+	TPS65224_IRQ_COMM_ERR,
+	TPS65224_IRQ_I2C2_ERR,
+};
+
+#define TPS65224_IRQ_NAME_BUCK1_UVOV		"buck1_uvov"
+#define TPS65224_IRQ_NAME_BUCK2_UVOV		"buck2_uvov"
+#define TPS65224_IRQ_NAME_BUCK3_UVOV		"buck3_uvov"
+#define TPS65224_IRQ_NAME_BUCK4_UVOV		"buck4_uvov"
+#define TPS65224_IRQ_NAME_LDO1_UVOV		"ldo1_uvov"
+#define TPS65224_IRQ_NAME_LDO2_UVOV		"ldo2_uvov"
+#define TPS65224_IRQ_NAME_LDO3_UVOV		"ldo3_uvov"
+#define TPS65224_IRQ_NAME_VCCA_UVOV		"vcca_uvov"
+#define TPS65224_IRQ_NAME_VMON1_UVOV		"vmon1_uvov"
+#define TPS65224_IRQ_NAME_VMON2_UVOV		"vmon2_uvov"
+#define TPS65224_IRQ_NAME_GPIO1			"gpio1"
+#define TPS65224_IRQ_NAME_GPIO2			"gpio2"
+#define TPS65224_IRQ_NAME_GPIO3			"gpio3"
+#define TPS65224_IRQ_NAME_GPIO4			"gpio4"
+#define TPS65224_IRQ_NAME_GPIO5			"gpio5"
+#define TPS65224_IRQ_NAME_GPIO6			"gpio6"
+#define TPS65224_IRQ_NAME_VSENSE	        "vsense"
+#define TPS65224_IRQ_NAME_ENABLE		"enable"
+#define TPS65224_IRQ_NAME_PB_SHORT		"pb_short"
+#define TPS65224_IRQ_NAME_FSD			"fsd"
+#define TPS65224_IRQ_NAME_SOFT_REBOOT		"soft_reboot"
+#define TPS65224_IRQ_NAME_BIST_PASS		"bist_pass"
+#define TPS65224_IRQ_NAME_EXT_CLK		"ext_clk"
+#define TPS65224_IRQ_NAME_REG_UNLOCK		"reg_unlock"
+#define TPS65224_IRQ_NAME_TWARN			"twarn"
+#define TPS65224_IRQ_NAME_PB_LONG		"pb_long"
+#define TPS65224_IRQ_NAME_PB_FALL		"pb_fall"
+#define TPS65224_IRQ_NAME_PB_RISE		"pb_rise"
+#define TPS65224_IRQ_NAME_ADC_CONV_READY	"adc_conv_ready"
+#define TPS65224_IRQ_NAME_TSD_ORD		"tsd_ord"
+#define TPS65224_IRQ_NAME_BIST_FAIL		"bist_fail"
+#define TPS65224_IRQ_NAME_REG_CRC_ERR		"reg_crc_err"
+#define TPS65224_IRQ_NAME_RECOV_CNT		"recov_cnt"
+#define TPS65224_IRQ_NAME_TSD_IMM		"tsd_imm"
+#define TPS65224_IRQ_NAME_VCCA_OVP		"vcca_ovp"
+#define TPS65224_IRQ_NAME_PFSM_ERR		"pfsm_err"
+#define TPS65224_IRQ_NAME_BG_XMON		"bg_xmon"
+#define TPS65224_IRQ_NAME_IMM_SHUTDOWN		"imm_shutdown"
+#define TPS65224_IRQ_NAME_ORD_SHUTDOWN		"ord_shutdown"
+#define TPS65224_IRQ_NAME_MCU_PWR_ERR		"mcu_pwr_err"
+#define TPS65224_IRQ_NAME_SOC_PWR_ERR		"soc_pwr_err"
+#define TPS65224_IRQ_NAME_COMM_ERR		"comm_err"
+#define TPS65224_IRQ_NAME_I2C2_ERR		"i2c2_err"
+#define TPS65224_IRQ_NAME_POWERUP		"powerup"
+
+/**
+ * struct tps6594 - device private data structure
+ *
+ * @dev:      MFD parent device
+ * @chip_id:  chip ID
+ * @reg:      I2C slave address or SPI chip select number
+ * @use_crc:  if true, use CRC for I2C and SPI interface protocols
+ * @regmap:   regmap for accessing the device registers
+ * @irq:      irq generated by the device
+ * @irq_data: regmap irq data used for the irq chip
+ */
+struct tps6594 {
+	struct device *dev;
+	unsigned long chip_id;
+	unsigned short reg;
+	bool use_crc;
+	struct regmap *regmap;
+	int irq;
+	struct regmap_irq_chip_data *irq_data;
+};
+
+extern const struct regmap_access_table tps6594_volatile_table;
+extern const struct regmap_access_table tps65224_volatile_table;
+
+int tps6594_device_init(struct tps6594 *tps, bool enable_crc);
+
+#endif /*  __LINUX_MFD_TPS6594_H */
diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h
index 6e3d99b7a0ee..b31e07fa4d51 100644
--- a/include/linux/mfd/twl.h
+++ b/include/linux/mfd/twl.h
@@ -205,27 +205,6 @@ int twl_get_hfclk_rate(void);
 int twl6030_interrupt_unmask(u8 bit_mask, u8 offset);
 int twl6030_interrupt_mask(u8 bit_mask, u8 offset);
 
-/* Card detect Configuration for MMC1 Controller on OMAP4 */
-#ifdef CONFIG_TWL4030_CORE
-int twl6030_mmc_card_detect_config(void);
-#else
-static inline int twl6030_mmc_card_detect_config(void)
-{
-	pr_debug("twl6030_mmc_card_detect_config not supported\n");
-	return 0;
-}
-#endif
-
-/* MMC1 Controller on OMAP4 uses Phoenix irq for Card detect */
-#ifdef CONFIG_TWL4030_CORE
-int twl6030_mmc_card_detect(struct device *dev, int slot);
-#else
-static inline int twl6030_mmc_card_detect(struct device *dev, int slot)
-{
-	pr_debug("Call back twl6030_mmc_card_detect not supported\n");
-	return -EIO;
-}
-#endif
 /*----------------------------------------------------------------------*/
 
 /*
@@ -461,6 +440,7 @@ static inline int twl6030_mmc_card_detect(struct device *dev, int slot)
 
 #define TWL4030_PM_MASTER_GLOBAL_TST		0xb6
 
+#define TWL6030_PHOENIX_DEV_ON                  0x06
 /*----------------------------------------------------------------------*/
 
 /* Power bus message definitions */
@@ -593,9 +573,6 @@ struct twl4030_gpio_platform_data {
 	 */
 	u32		pullups;
 	u32		pulldowns;
-
-	int		(*setup)(struct device *dev,
-				unsigned gpio, unsigned ngpio);
 };
 
 struct twl4030_madc_platform_data {
diff --git a/include/linux/mfd/upboard-fpga.h b/include/linux/mfd/upboard-fpga.h
new file mode 100644
index 000000000000..12231e40f5da
--- /dev/null
+++ b/include/linux/mfd/upboard-fpga.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * UP Board CPLD/FPGA driver
+ *
+ * Copyright (c) AAEON. All rights reserved.
+ * Copyright (C) 2024 Bootlin
+ *
+ * Author: Gary Wang <garywang@aaeon.com.tw>
+ * Author: Thomas Richard <thomas.richard@bootlin.com>
+ *
+ */
+
+#ifndef __LINUX_MFD_UPBOARD_FPGA_H
+#define __LINUX_MFD_UPBOARD_FPGA_H
+
+#define UPBOARD_REGISTER_SIZE 16
+
+enum upboard_fpgareg {
+	UPBOARD_REG_PLATFORM_ID   = 0x10,
+	UPBOARD_REG_FIRMWARE_ID   = 0x11,
+	UPBOARD_REG_FUNC_EN0      = 0x20,
+	UPBOARD_REG_FUNC_EN1      = 0x21,
+	UPBOARD_REG_GPIO_EN0      = 0x30,
+	UPBOARD_REG_GPIO_EN1      = 0x31,
+	UPBOARD_REG_GPIO_EN2      = 0x32,
+	UPBOARD_REG_GPIO_DIR0     = 0x40,
+	UPBOARD_REG_GPIO_DIR1     = 0x41,
+	UPBOARD_REG_GPIO_DIR2     = 0x42,
+	UPBOARD_REG_MAX,
+};
+
+enum upboard_fpga_type {
+	UPBOARD_UP_FPGA,
+	UPBOARD_UP2_FPGA,
+};
+
+struct upboard_fpga_data {
+	enum upboard_fpga_type type;
+	const struct regmap_config *regmap_config;
+};
+
+struct upboard_fpga {
+	struct device *dev;
+	struct regmap *regmap;
+	struct gpio_desc *enable_gpio;
+	struct gpio_desc *reset_gpio;
+	struct gpio_desc *clear_gpio;
+	struct gpio_desc *strobe_gpio;
+	struct gpio_desc *datain_gpio;
+	struct gpio_desc *dataout_gpio;
+	unsigned int firmware_version;
+	const struct upboard_fpga_data *fpga_data;
+};
+
+#endif /*  __LINUX_MFD_UPBOARD_FPGA_H */
diff --git a/include/linux/mfd/wl1273-core.h b/include/linux/mfd/wl1273-core.h
deleted file mode 100644
index c28cf76d5c31..000000000000
--- a/include/linux/mfd/wl1273-core.h
+++ /dev/null
@@ -1,277 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * include/linux/mfd/wl1273-core.h
- *
- * Some definitions for the wl1273 radio receiver/transmitter chip.
- *
- * Copyright (C) 2010 Nokia Corporation
- * Author: Matti J. Aaltonen <matti.j.aaltonen@nokia.com>
- */
-
-#ifndef WL1273_CORE_H
-#define WL1273_CORE_H
-
-#include <linux/i2c.h>
-#include <linux/mfd/core.h>
-
-#define WL1273_FM_DRIVER_NAME	"wl1273-fm"
-#define RX71_FM_I2C_ADDR	0x22
-
-#define WL1273_STEREO_GET		0
-#define WL1273_RSSI_LVL_GET		1
-#define WL1273_IF_COUNT_GET		2
-#define WL1273_FLAG_GET			3
-#define WL1273_RDS_SYNC_GET		4
-#define WL1273_RDS_DATA_GET		5
-#define WL1273_FREQ_SET			10
-#define WL1273_AF_FREQ_SET		11
-#define WL1273_MOST_MODE_SET		12
-#define WL1273_MOST_BLEND_SET		13
-#define WL1273_DEMPH_MODE_SET		14
-#define WL1273_SEARCH_LVL_SET		15
-#define WL1273_BAND_SET			16
-#define WL1273_MUTE_STATUS_SET		17
-#define WL1273_RDS_PAUSE_LVL_SET	18
-#define WL1273_RDS_PAUSE_DUR_SET	19
-#define WL1273_RDS_MEM_SET		20
-#define WL1273_RDS_BLK_B_SET		21
-#define WL1273_RDS_MSK_B_SET		22
-#define WL1273_RDS_PI_MASK_SET		23
-#define WL1273_RDS_PI_SET		24
-#define WL1273_RDS_SYSTEM_SET		25
-#define WL1273_INT_MASK_SET		26
-#define WL1273_SEARCH_DIR_SET		27
-#define WL1273_VOLUME_SET		28
-#define WL1273_AUDIO_ENABLE		29
-#define WL1273_PCM_MODE_SET		30
-#define WL1273_I2S_MODE_CONFIG_SET	31
-#define WL1273_POWER_SET		32
-#define WL1273_INTX_CONFIG_SET		33
-#define WL1273_PULL_EN_SET		34
-#define WL1273_HILO_SET			35
-#define WL1273_SWITCH2FREF		36
-#define WL1273_FREQ_DRIFT_REPORT	37
-
-#define WL1273_PCE_GET			40
-#define WL1273_FIRM_VER_GET		41
-#define WL1273_ASIC_VER_GET		42
-#define WL1273_ASIC_ID_GET		43
-#define WL1273_MAN_ID_GET		44
-#define WL1273_TUNER_MODE_SET		45
-#define WL1273_STOP_SEARCH		46
-#define WL1273_RDS_CNTRL_SET		47
-
-#define WL1273_WRITE_HARDWARE_REG	100
-#define WL1273_CODE_DOWNLOAD		101
-#define WL1273_RESET			102
-
-#define WL1273_FM_POWER_MODE		254
-#define WL1273_FM_INTERRUPT		255
-
-/* Transmitter API */
-
-#define WL1273_CHANL_SET			55
-#define WL1273_SCAN_SPACING_SET			56
-#define WL1273_REF_SET				57
-#define WL1273_POWER_ENB_SET			90
-#define WL1273_POWER_ATT_SET			58
-#define WL1273_POWER_LEV_SET			59
-#define WL1273_AUDIO_DEV_SET			60
-#define WL1273_PILOT_DEV_SET			61
-#define WL1273_RDS_DEV_SET			62
-#define WL1273_PUPD_SET				91
-#define WL1273_AUDIO_IO_SET			63
-#define WL1273_PREMPH_SET			64
-#define WL1273_MONO_SET				66
-#define WL1273_MUTE				92
-#define WL1273_MPX_LMT_ENABLE			67
-#define WL1273_PI_SET				93
-#define WL1273_ECC_SET				69
-#define WL1273_PTY				70
-#define WL1273_AF				71
-#define WL1273_DISPLAY_MODE			74
-#define WL1273_RDS_REP_SET			77
-#define WL1273_RDS_CONFIG_DATA_SET		98
-#define WL1273_RDS_DATA_SET			99
-#define WL1273_RDS_DATA_ENB			94
-#define WL1273_TA_SET				78
-#define WL1273_TP_SET				79
-#define WL1273_DI_SET				80
-#define WL1273_MS_SET				81
-#define WL1273_PS_SCROLL_SPEED			82
-#define WL1273_TX_AUDIO_LEVEL_TEST		96
-#define WL1273_TX_AUDIO_LEVEL_TEST_THRESHOLD	73
-#define WL1273_TX_AUDIO_INPUT_LEVEL_RANGE_SET	54
-#define WL1273_RX_ANTENNA_SELECT		87
-#define WL1273_I2C_DEV_ADDR_SET			86
-#define WL1273_REF_ERR_CALIB_PARAM_SET		88
-#define WL1273_REF_ERR_CALIB_PERIODICITY_SET	89
-#define WL1273_SOC_INT_TRIGGER			52
-#define WL1273_SOC_AUDIO_PATH_SET		83
-#define WL1273_SOC_PCMI_OVERRIDE		84
-#define WL1273_SOC_I2S_OVERRIDE			85
-#define WL1273_RSSI_BLOCK_SCAN_FREQ_SET		95
-#define WL1273_RSSI_BLOCK_SCAN_START		97
-#define WL1273_RSSI_BLOCK_SCAN_DATA_GET		5
-#define WL1273_READ_FMANT_TUNE_VALUE		104
-
-#define WL1273_RDS_OFF		0
-#define WL1273_RDS_ON		1
-#define WL1273_RDS_RESET	2
-
-#define WL1273_AUDIO_DIGITAL	0
-#define WL1273_AUDIO_ANALOG	1
-
-#define WL1273_MODE_RX		BIT(0)
-#define WL1273_MODE_TX		BIT(1)
-#define WL1273_MODE_OFF		BIT(2)
-#define WL1273_MODE_SUSPENDED	BIT(3)
-
-#define WL1273_RADIO_CHILD	BIT(0)
-#define WL1273_CODEC_CHILD	BIT(1)
-
-#define WL1273_RX_MONO		1
-#define WL1273_RX_STEREO	0
-#define WL1273_TX_MONO		0
-#define WL1273_TX_STEREO	1
-
-#define WL1273_MAX_VOLUME	0xffff
-#define WL1273_DEFAULT_VOLUME	0x78b8
-
-/* I2S protocol, left channel first, data width 16 bits */
-#define WL1273_PCM_DEF_MODE		0x00
-
-/* Rx */
-#define WL1273_AUDIO_ENABLE_I2S		BIT(0)
-#define WL1273_AUDIO_ENABLE_ANALOG	BIT(1)
-
-/* Tx */
-#define WL1273_AUDIO_IO_SET_ANALOG	0
-#define WL1273_AUDIO_IO_SET_I2S		1
-
-#define WL1273_PUPD_SET_OFF		0x00
-#define WL1273_PUPD_SET_ON		0x01
-#define WL1273_PUPD_SET_RETENTION	0x10
-
-/* I2S mode */
-#define WL1273_IS2_WIDTH_32	0x0
-#define WL1273_IS2_WIDTH_40	0x1
-#define WL1273_IS2_WIDTH_22_23	0x2
-#define WL1273_IS2_WIDTH_23_22	0x3
-#define WL1273_IS2_WIDTH_48	0x4
-#define WL1273_IS2_WIDTH_50	0x5
-#define WL1273_IS2_WIDTH_60	0x6
-#define WL1273_IS2_WIDTH_64	0x7
-#define WL1273_IS2_WIDTH_80	0x8
-#define WL1273_IS2_WIDTH_96	0x9
-#define WL1273_IS2_WIDTH_128	0xa
-#define WL1273_IS2_WIDTH	0xf
-
-#define WL1273_IS2_FORMAT_STD	(0x0 << 4)
-#define WL1273_IS2_FORMAT_LEFT	(0x1 << 4)
-#define WL1273_IS2_FORMAT_RIGHT	(0x2 << 4)
-#define WL1273_IS2_FORMAT_USER	(0x3 << 4)
-
-#define WL1273_IS2_MASTER	(0x0 << 6)
-#define WL1273_IS2_SLAVEW	(0x1 << 6)
-
-#define WL1273_IS2_TRI_AFTER_SENDING	(0x0 << 7)
-#define WL1273_IS2_TRI_ALWAYS_ACTIVE	(0x1 << 7)
-
-#define WL1273_IS2_SDOWS_RR	(0x0 << 8)
-#define WL1273_IS2_SDOWS_RF	(0x1 << 8)
-#define WL1273_IS2_SDOWS_FR	(0x2 << 8)
-#define WL1273_IS2_SDOWS_FF	(0x3 << 8)
-
-#define WL1273_IS2_TRI_OPT	(0x0 << 10)
-#define WL1273_IS2_TRI_ALWAYS	(0x1 << 10)
-
-#define WL1273_IS2_RATE_48K	(0x0 << 12)
-#define WL1273_IS2_RATE_44_1K	(0x1 << 12)
-#define WL1273_IS2_RATE_32K	(0x2 << 12)
-#define WL1273_IS2_RATE_22_05K	(0x4 << 12)
-#define WL1273_IS2_RATE_16K	(0x5 << 12)
-#define WL1273_IS2_RATE_12K	(0x8 << 12)
-#define WL1273_IS2_RATE_11_025	(0x9 << 12)
-#define WL1273_IS2_RATE_8K	(0xa << 12)
-#define WL1273_IS2_RATE		(0xf << 12)
-
-#define WL1273_I2S_DEF_MODE	(WL1273_IS2_WIDTH_32 | \
-				 WL1273_IS2_FORMAT_STD | \
-				 WL1273_IS2_MASTER | \
-				 WL1273_IS2_TRI_AFTER_SENDING | \
-				 WL1273_IS2_SDOWS_RR | \
-				 WL1273_IS2_TRI_OPT | \
-				 WL1273_IS2_RATE_48K)
-
-#define SCHAR_MIN (-128)
-#define SCHAR_MAX 127
-
-#define WL1273_FR_EVENT			BIT(0)
-#define WL1273_BL_EVENT			BIT(1)
-#define WL1273_RDS_EVENT		BIT(2)
-#define WL1273_BBLK_EVENT		BIT(3)
-#define WL1273_LSYNC_EVENT		BIT(4)
-#define WL1273_LEV_EVENT		BIT(5)
-#define WL1273_IFFR_EVENT		BIT(6)
-#define WL1273_PI_EVENT			BIT(7)
-#define WL1273_PD_EVENT			BIT(8)
-#define WL1273_STIC_EVENT		BIT(9)
-#define WL1273_MAL_EVENT		BIT(10)
-#define WL1273_POW_ENB_EVENT		BIT(11)
-#define WL1273_SCAN_OVER_EVENT		BIT(12)
-#define WL1273_ERROR_EVENT		BIT(13)
-
-#define TUNER_MODE_STOP_SEARCH		0
-#define TUNER_MODE_PRESET		1
-#define TUNER_MODE_AUTO_SEEK		2
-#define TUNER_MODE_AF			3
-#define TUNER_MODE_AUTO_SEEK_PI		4
-#define TUNER_MODE_AUTO_SEEK_BULK	5
-
-#define RDS_BLOCK_SIZE	3
-
-struct wl1273_fm_platform_data {
-	int (*request_resources) (struct i2c_client *client);
-	void (*free_resources) (void);
-	void (*enable) (void);
-	void (*disable) (void);
-
-	u8 forbidden_modes;
-	unsigned int children;
-};
-
-#define WL1273_FM_CORE_CELLS	2
-
-#define WL1273_BAND_OTHER	0
-#define WL1273_BAND_JAPAN	1
-
-#define WL1273_BAND_JAPAN_LOW	76000
-#define WL1273_BAND_JAPAN_HIGH	90000
-#define WL1273_BAND_OTHER_LOW	87500
-#define WL1273_BAND_OTHER_HIGH	108000
-
-#define WL1273_BAND_TX_LOW	76000
-#define WL1273_BAND_TX_HIGH	108000
-
-struct wl1273_core {
-	struct mfd_cell cells[WL1273_FM_CORE_CELLS];
-	struct wl1273_fm_platform_data *pdata;
-
-	unsigned int mode;
-	unsigned int i2s_mode;
-	unsigned int volume;
-	unsigned int audio_mode;
-	unsigned int channel_number;
-	struct mutex lock; /* for serializing fm radio operations */
-
-	struct i2c_client *client;
-
-	int (*read)(struct wl1273_core *core, u8, u16 *);
-	int (*write)(struct wl1273_core *core, u8, u16);
-	int (*write_data)(struct wl1273_core *core, u8 *, u16);
-	int (*set_audio)(struct wl1273_core *core, unsigned int);
-	int (*set_volume)(struct wl1273_core *core, unsigned int);
-};
-
-#endif	/* ifndef WL1273_CORE_H */
diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index a3241e4d7548..5f70d3b5d1b1 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -8,11 +8,12 @@
 #ifndef __LINUX_MFD_WM8350_CORE_H_
 #define __LINUX_MFD_WM8350_CORE_H_
 
-#include <linux/kernel.h>
-#include <linux/mutex.h>
-#include <linux/interrupt.h>
 #include <linux/completion.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
 #include <linux/regmap.h>
+#include <linux/types.h>
 
 #include <linux/mfd/wm8350/audio.h>
 #include <linux/mfd/wm8350/gpio.h>
@@ -21,6 +22,9 @@
 #include <linux/mfd/wm8350/supply.h>
 #include <linux/mfd/wm8350/wdt.h>
 
+struct device;
+struct platform_device;
+
 /*
  * Register values.
  */
diff --git a/include/linux/mhi.h b/include/linux/mhi.h
index f6de4b6ecfc7..dd372b0123a6 100644
--- a/include/linux/mhi.h
+++ b/include/linux/mhi.h
@@ -266,6 +266,7 @@ struct mhi_event_config {
  * struct mhi_controller_config - Root MHI controller configuration
  * @max_channels: Maximum number of channels supported
  * @timeout_ms: Timeout value for operations. 0 means use default
+ * @ready_timeout_ms: Timeout value for waiting device to be ready (optional)
  * @buf_len: Size of automatically allocated buffers. 0 means use default
  * @num_channels: Number of channels defined in @ch_cfg
  * @ch_cfg: Array of defined channels
@@ -277,6 +278,7 @@ struct mhi_event_config {
 struct mhi_controller_config {
 	u32 max_channels;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 buf_len;
 	u32 num_channels;
 	const struct mhi_channel_config *ch_cfg;
@@ -288,6 +290,7 @@ struct mhi_controller_config {
 
 /**
  * struct mhi_controller - Master MHI controller structure
+ * @name: Device name of the MHI controller
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
  *            controller (required)
  * @mhi_dev: MHI device instance for the controller
@@ -299,6 +302,10 @@ struct mhi_controller_config {
  * @iova_start: IOMMU starting address for data (required)
  * @iova_stop: IOMMU stop address for data (required)
  * @fw_image: Firmware image name for normal booting (optional)
+ * @fw_data: Firmware image data content for normal booting, used only
+ *           if fw_image is NULL and fbc_download is true (optional)
+ * @fw_sz: Firmware image data size for normal booting, used only if fw_image
+ *         is NULL and fbc_download is true (optional)
  * @edl_image: Firmware image name for emergency download mode (optional)
  * @rddm_size: RAM dump size that host should allocate for debugging purpose
  * @sbl_size: SBL image size downloaded through BHIe (optional)
@@ -314,18 +321,14 @@ struct mhi_controller_config {
  * @hw_ev_rings: Number of hardware event rings
  * @sw_ev_rings: Number of software event rings
  * @nr_irqs: Number of IRQ allocated by bus master (required)
- * @family_number: MHI controller family number
- * @device_number: MHI controller device number
- * @major_version: MHI controller major revision number
- * @minor_version: MHI controller minor revision number
  * @serial_number: MHI controller serial number obtained from BHI
- * @oem_pk_hash: MHI controller OEM PK Hash obtained from BHI
  * @mhi_event: MHI event ring configurations table
  * @mhi_cmd: MHI command ring configurations table
  * @mhi_ctxt: MHI device context, shared memory between host and device
  * @pm_mutex: Mutex for suspend/resume operation
  * @pm_lock: Lock for protecting MHI power management state
  * @timeout_ms: Timeout in ms for state transitions
+ * @ready_timeout_ms: Timeout in ms for waiting device to be ready (optional)
  * @pm_state: MHI power management state
  * @db_access: DB access states
  * @ee: MHI device execution environment
@@ -351,6 +354,7 @@ struct mhi_controller_config {
  * @read_reg: Read a MHI register via the physical link (required)
  * @write_reg: Write a MHI register via the physical link (required)
  * @reset: Controller specific reset function (optional)
+ * @edl_trigger: CB function to trigger EDL mode (optional)
  * @buffer_len: Bounce buffer length
  * @index: Index of the MHI controller instance
  * @bounce_buf: Use of bounce buffer
@@ -362,17 +366,9 @@ struct mhi_controller_config {
  * Fields marked as (required) need to be populated by the controller driver
  * before calling mhi_register_controller(). For the fields marked as (optional)
  * they can be populated depending on the usecase.
- *
- * The following fields are present for the purpose of implementing any device
- * specific quirks or customizations for specific MHI revisions used in device
- * by the controller drivers. The MHI stack will just populate these fields
- * during mhi_register_controller():
- *  family_number
- *  device_number
- *  major_version
- *  minor_version
  */
 struct mhi_controller {
+	const char *name;
 	struct device *cntrl_dev;
 	struct mhi_device *mhi_dev;
 	struct dentry *debugfs_dentry;
@@ -384,6 +380,8 @@ struct mhi_controller {
 	dma_addr_t iova_start;
 	dma_addr_t iova_stop;
 	const char *fw_image;
+	const u8 *fw_data;
+	size_t fw_sz;
 	const char *edl_image;
 	size_t rddm_size;
 	size_t sbl_size;
@@ -399,12 +397,7 @@ struct mhi_controller {
 	u32 hw_ev_rings;
 	u32 sw_ev_rings;
 	u32 nr_irqs;
-	u32 family_number;
-	u32 device_number;
-	u32 major_version;
-	u32 minor_version;
 	u32 serial_number;
-	u32 oem_pk_hash[MHI_MAX_OEM_PK_HASH_SEGMENTS];
 
 	struct mhi_event *mhi_event;
 	struct mhi_cmd *mhi_cmd;
@@ -413,6 +406,7 @@ struct mhi_controller {
 	struct mutex pm_mutex;
 	rwlock_t pm_lock;
 	u32 timeout_ms;
+	u32 ready_timeout_ms;
 	u32 pm_state;
 	u32 db_access;
 	enum mhi_ee_type ee;
@@ -444,6 +438,7 @@ struct mhi_controller {
 	void (*write_reg)(struct mhi_controller *mhi_cntrl, void __iomem *addr,
 			  u32 val);
 	void (*reset)(struct mhi_controller *mhi_cntrl);
+	int (*edl_trigger)(struct mhi_controller *mhi_cntrl);
 
 	size_t buffer_len;
 	int index;
@@ -533,7 +528,7 @@ struct mhi_driver {
 	struct device_driver driver;
 };
 
-#define to_mhi_driver(drv) container_of(drv, struct mhi_driver, driver)
+#define to_mhi_driver(drv) container_of_const(drv, struct mhi_driver, driver)
 #define to_mhi_device(dev) container_of(dev, struct mhi_device, dev)
 
 /**
@@ -639,13 +634,29 @@ int mhi_async_power_up(struct mhi_controller *mhi_cntrl);
 int mhi_sync_power_up(struct mhi_controller *mhi_cntrl);
 
 /**
- * mhi_power_down - Start MHI power down sequence
+ * mhi_power_down - Power down the MHI device and also destroy the
+ *                  'struct device' for the channels associated with it.
+ *                  See also mhi_power_down_keep_dev() which is a variant
+ *                  of this API that keeps the 'struct device' for channels
+ *                  (useful during suspend/hibernation).
  * @mhi_cntrl: MHI controller
  * @graceful: Link is still accessible, so do a graceful shutdown process
  */
 void mhi_power_down(struct mhi_controller *mhi_cntrl, bool graceful);
 
 /**
+ * mhi_power_down_keep_dev - Power down the MHI device but keep the 'struct
+ *                           device' for the channels associated with it.
+ *                           This is a variant of 'mhi_power_down()' and
+ *                           useful in scenarios such as suspend/hibernation
+ *                           where destroying of the 'struct device' is not
+ *                           needed.
+ * @mhi_cntrl: MHI controller
+ * @graceful: Link is still accessible, so do a graceful shutdown process
+ */
+void mhi_power_down_keep_dev(struct mhi_controller *mhi_cntrl, bool graceful);
+
+/**
  * mhi_unprepare_after_power_down - Free any allocated memory after power down
  * @mhi_cntrl: MHI controller
  */
@@ -710,12 +721,6 @@ enum mhi_state mhi_get_mhi_state(struct mhi_controller *mhi_cntrl);
 void mhi_soc_reset(struct mhi_controller *mhi_cntrl);
 
 /**
- * mhi_device_get - Disable device low power mode
- * @mhi_dev: Device associated with the channel
- */
-void mhi_device_get(struct mhi_device *mhi_dev);
-
-/**
  * mhi_device_get_sync - Disable device low power mode. Synchronously
  *                       take the controller out of suspended state
  * @mhi_dev: Device associated with the channel
@@ -766,18 +771,6 @@ int mhi_prepare_for_transfer_autoqueue(struct mhi_device *mhi_dev);
 void mhi_unprepare_from_transfer(struct mhi_device *mhi_dev);
 
 /**
- * mhi_queue_dma - Send or receive DMA mapped buffers from client device
- *                 over MHI channel
- * @mhi_dev: Device associated with the channels
- * @dir: DMA direction for the channel
- * @mhi_buf: Buffer for holding the DMA mapped data
- * @len: Buffer length
- * @mflags: MHI transfer flags used for the transfer
- */
-int mhi_queue_dma(struct mhi_device *mhi_dev, enum dma_data_direction dir,
-		  struct mhi_buf *mhi_buf, size_t len, enum mhi_flags mflags);
-
-/**
  * mhi_queue_buf - Send or receive raw buffers from client device over MHI
  *                 channel
  * @mhi_dev: Device associated with the channels
@@ -807,4 +800,13 @@ int mhi_queue_skb(struct mhi_device *mhi_dev, enum dma_data_direction dir,
  */
 bool mhi_queue_is_full(struct mhi_device *mhi_dev, enum dma_data_direction dir);
 
+/**
+ * mhi_get_channel_doorbell_offset - Get the channel doorbell offset
+ * @mhi_cntrl: MHI controller
+ * @chdb_offset: Read channel doorbell offset
+ *
+ * Return: 0 if the read succeeds, a negative error code otherwise
+ */
+int mhi_get_channel_doorbell_offset(struct mhi_controller *mhi_cntrl, u32 *chdb_offset);
+
 #endif /* _MHI_H_ */
diff --git a/include/linux/mhi_ep.h b/include/linux/mhi_ep.h
index f198a8ac7ee7..7b40fc8cbe77 100644
--- a/include/linux/mhi_ep.h
+++ b/include/linux/mhi_ep.h
@@ -50,6 +50,27 @@ struct mhi_ep_db_info {
 };
 
 /**
+ * struct mhi_ep_buf_info - MHI Endpoint transfer buffer info
+ * @mhi_dev: MHI device associated with this buffer
+ * @dev_addr: Address of the buffer in endpoint
+ * @host_addr: Address of the bufffer in host
+ * @size: Size of the buffer
+ * @code: Transfer completion code
+ * @cb: Callback to be executed by controller drivers after transfer completion (async)
+ * @cb_buf: Opaque buffer to be passed to the callback
+ */
+struct mhi_ep_buf_info {
+	struct mhi_ep_device *mhi_dev;
+	void *dev_addr;
+	u64 host_addr;
+	size_t size;
+	int code;
+
+	void (*cb)(struct mhi_ep_buf_info *buf_info);
+	void *cb_buf;
+};
+
+/**
  * struct mhi_ep_cntrl - MHI Endpoint controller structure
  * @cntrl_dev: Pointer to the struct device of physical bus acting as the MHI
  *             Endpoint controller
@@ -82,8 +103,10 @@ struct mhi_ep_db_info {
  * @raise_irq: CB function for raising IRQ to the host
  * @alloc_map: CB function for allocating memory in endpoint for storing host context and mapping it
  * @unmap_free: CB function to unmap and free the allocated memory in endpoint for storing host context
- * @read_from_host: CB function for reading from host memory from endpoint
- * @write_to_host: CB function for writing to host memory from endpoint
+ * @read_sync: CB function for reading from host memory synchronously
+ * @write_sync: CB function for writing to host memory synchronously
+ * @read_async: CB function for reading from host memory asynchronously
+ * @write_async: CB function for writing to host memory asynchronously
  * @mhi_state: MHI Endpoint state
  * @max_chan: Maximum channels supported by the endpoint controller
  * @mru: MRU (Maximum Receive Unit) value of the endpoint controller
@@ -128,14 +151,19 @@ struct mhi_ep_cntrl {
 	struct work_struct reset_work;
 	struct work_struct cmd_ring_work;
 	struct work_struct ch_ring_work;
+	struct kmem_cache *ring_item_cache;
+	struct kmem_cache *ev_ring_el_cache;
+	struct kmem_cache *tre_buf_cache;
 
 	void (*raise_irq)(struct mhi_ep_cntrl *mhi_cntrl, u32 vector);
 	int (*alloc_map)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t *phys_ptr,
 			 void __iomem **virt, size_t size);
 	void (*unmap_free)(struct mhi_ep_cntrl *mhi_cntrl, u64 pci_addr, phys_addr_t phys,
 			   void __iomem *virt, size_t size);
-	int (*read_from_host)(struct mhi_ep_cntrl *mhi_cntrl, u64 from, void *to, size_t size);
-	int (*write_to_host)(struct mhi_ep_cntrl *mhi_cntrl, void *from, u64 to, size_t size);
+	int (*read_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_sync)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*read_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
+	int (*write_async)(struct mhi_ep_cntrl *mhi_cntrl, struct mhi_ep_buf_info *buf_info);
 
 	enum mhi_state mhi_state;
 
@@ -193,7 +221,7 @@ struct mhi_ep_driver {
 };
 
 #define to_mhi_ep_device(dev) container_of(dev, struct mhi_ep_device, dev)
-#define to_mhi_ep_driver(drv) container_of(drv, struct mhi_ep_driver, driver)
+#define to_mhi_ep_driver(drv) container_of_const(drv, struct mhi_ep_driver, driver)
 
 /*
  * module_mhi_ep_driver() - Helper macro for drivers that don't do
diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h
index 8bef1ab62bba..ca691641788b 100644
--- a/include/linux/micrel_phy.h
+++ b/include/linux/micrel_phy.h
@@ -32,6 +32,7 @@
 #define PHY_ID_LAN8814		0x00221660
 #define PHY_ID_LAN8804		0x00221670
 #define PHY_ID_LAN8841		0x00221650
+#define PHY_ID_LAN8842		0x002216C0
 
 #define PHY_ID_KSZ886X		0x00221430
 #define PHY_ID_KSZ8863		0x00221435
@@ -41,9 +42,9 @@
 #define	PHY_ID_KSZ9477		0x00221631
 
 /* struct phy_device dev_flags definitions */
-#define MICREL_PHY_50MHZ_CLK	0x00000001
-#define MICREL_PHY_FXEN		0x00000002
-#define MICREL_KSZ8_P1_ERRATA	0x00000003
+#define MICREL_PHY_50MHZ_CLK	BIT(0)
+#define MICREL_PHY_FXEN		BIT(1)
+#define MICREL_KSZ8_P1_ERRATA	BIT(2)
 
 #define MICREL_KSZ9021_EXTREG_CTRL	0xB
 #define MICREL_KSZ9021_EXTREG_DATA_WRITE	0xC
@@ -63,6 +64,10 @@
 #define KSZ886X_BMCR_DISABLE_TRANSMIT		BIT(1)
 #define KSZ886X_BMCR_DISABLE_LED		BIT(0)
 
+/* PHY Special Control/Status Register (Reg 31) */
 #define KSZ886X_CTRL_MDIX_STAT			BIT(4)
+#define KSZ886X_CTRL_FORCE_LINK			BIT(3)
+#define KSZ886X_CTRL_PWRSAVE			BIT(2)
+#define KSZ886X_CTRL_REMOTE_LOOPBACK		BIT(1)
 
 #endif /* _MICREL_PHY_H */
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 6de5756d8533..26ca00c325d9 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -12,14 +12,6 @@ typedef void free_folio_t(struct folio *folio, unsigned long private);
 
 struct migration_target_control;
 
-/*
- * Return values from addresss_space_operations.migratepage():
- * - negative errno on page migration failure;
- * - zero on page migration success;
- */
-#define MIGRATEPAGE_SUCCESS		0
-#define MIGRATEPAGE_UNMAP		1
-
 /**
  * struct movable_operations - Driver page migration
  * @isolate_page:
@@ -35,8 +27,7 @@ struct migration_target_control;
  * @src page.  The driver should copy the contents of the
  * @src page to the @dst page and set up the fields of @dst page.
  * Both pages are locked.
- * If page migration is successful, the driver should call
- * __ClearPageMovable(@src) and return MIGRATEPAGE_SUCCESS.
+ * If page migration is successful, the driver should return 0.
  * If the driver cannot migrate the page at the moment, it can return
  * -EAGAIN.  The VM interprets this as a temporary migration failure and
  * will retry it later.  Any other error value is a permanent migration
@@ -63,24 +54,23 @@ extern const char *migrate_reason_names[MR_TYPES];
 #ifdef CONFIG_MIGRATION
 
 void putback_movable_pages(struct list_head *l);
-int migrate_folio_extra(struct address_space *mapping, struct folio *dst,
-		struct folio *src, enum migrate_mode mode, int extra_count);
 int migrate_folio(struct address_space *mapping, struct folio *dst,
 		struct folio *src, enum migrate_mode mode);
 int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free,
 		  unsigned long private, enum migrate_mode mode, int reason,
 		  unsigned int *ret_succeeded);
 struct folio *alloc_migration_target(struct folio *src, unsigned long private);
-bool isolate_movable_page(struct page *page, isolate_mode_t mode);
+bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode);
+bool isolate_folio_to_list(struct folio *folio, struct list_head *list);
 
 int migrate_huge_page_move_mapping(struct address_space *mapping,
 		struct folio *dst, struct folio *src);
-void migration_entry_wait_on_locked(swp_entry_t entry, pte_t *ptep,
-				spinlock_t *ptl);
+void migration_entry_wait_on_locked(softleaf_t entry, spinlock_t *ptl)
+		__releases(ptl);
 void folio_migrate_flags(struct folio *newfolio, struct folio *folio);
-void folio_migrate_copy(struct folio *newfolio, struct folio *folio);
 int folio_migrate_mapping(struct address_space *mapping,
 		struct folio *newfolio, struct folio *folio, int extra_count);
+int set_movable_ops(const struct movable_operations *ops, enum pagetype type);
 
 #else
 
@@ -92,7 +82,9 @@ static inline int migrate_pages(struct list_head *l, new_folio_t new,
 static inline struct folio *alloc_migration_target(struct folio *src,
 		unsigned long private)
 	{ return NULL; }
-static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode)
+static inline bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
+	{ return false; }
+static inline bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
 	{ return false; }
 
 static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
@@ -100,53 +92,24 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 {
 	return -ENOSYS;
 }
-
-#endif /* CONFIG_MIGRATION */
-
-#ifdef CONFIG_COMPACTION
-bool PageMovable(struct page *page);
-void __SetPageMovable(struct page *page, const struct movable_operations *ops);
-void __ClearPageMovable(struct page *page);
-#else
-static inline bool PageMovable(struct page *page) { return false; }
-static inline void __SetPageMovable(struct page *page,
-		const struct movable_operations *ops)
-{
-}
-static inline void __ClearPageMovable(struct page *page)
-{
-}
-#endif
-
-static inline bool folio_test_movable(struct folio *folio)
+static inline int set_movable_ops(const struct movable_operations *ops, enum pagetype type)
 {
-	return PageMovable(&folio->page);
-}
-
-static inline
-const struct movable_operations *folio_movable_ops(struct folio *folio)
-{
-	VM_BUG_ON(!__folio_test_movable(folio));
-
-	return (const struct movable_operations *)
-		((unsigned long)folio->mapping - PAGE_MAPPING_MOVABLE);
+	return -ENOSYS;
 }
 
-static inline
-const struct movable_operations *page_movable_ops(struct page *page)
-{
-	VM_BUG_ON(!__PageMovable(page));
-
-	return (const struct movable_operations *)
-		((unsigned long)page->mapping - PAGE_MAPPING_MOVABLE);
-}
+#endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_NUMA_BALANCING
-int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
-			   int node);
+int migrate_misplaced_folio_prepare(struct folio *folio,
+		struct vm_area_struct *vma, int node);
+int migrate_misplaced_folio(struct folio *folio, int node);
 #else
-static inline int migrate_misplaced_page(struct page *page,
-					 struct vm_area_struct *vma, int node)
+static inline int migrate_misplaced_folio_prepare(struct folio *folio,
+		struct vm_area_struct *vma, int node)
+{
+	return -EAGAIN; /* can't migrate now */
+}
+static inline int migrate_misplaced_folio(struct folio *folio, int node)
 {
 	return -EAGAIN; /* can't migrate now */
 }
@@ -162,6 +125,7 @@ static inline int migrate_misplaced_page(struct page *page,
 #define MIGRATE_PFN_VALID	(1UL << 0)
 #define MIGRATE_PFN_MIGRATE	(1UL << 1)
 #define MIGRATE_PFN_WRITE	(1UL << 3)
+#define MIGRATE_PFN_COMPOUND	(1UL << 4)
 #define MIGRATE_PFN_SHIFT	6
 
 static inline struct page *migrate_pfn_to_page(unsigned long mpfn)
@@ -180,6 +144,7 @@ enum migrate_vma_direction {
 	MIGRATE_VMA_SELECT_SYSTEM = 1 << 0,
 	MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1,
 	MIGRATE_VMA_SELECT_DEVICE_COHERENT = 1 << 2,
+	MIGRATE_VMA_SELECT_COMPOUND = 1 << 3,
 };
 
 struct migrate_vma {
@@ -200,8 +165,8 @@ struct migrate_vma {
 	unsigned long		end;
 
 	/*
-	 * Set to the owner value also stored in page->pgmap->owner for
-	 * migrating out of device private memory. The flags also need to
+	 * Set to the owner value also stored in page_pgmap(page)->owner
+	 * for migrating out of device private memory. The flags also need to
 	 * be set to MIGRATE_VMA_SELECT_DEVICE_PRIVATE.
 	 * The caller should always set this field when using mmu notifier
 	 * callbacks to avoid device MMU invalidations for device private
@@ -222,6 +187,7 @@ void migrate_vma_pages(struct migrate_vma *migrate);
 void migrate_vma_finalize(struct migrate_vma *migrate);
 int migrate_device_range(unsigned long *src_pfns, unsigned long start,
 			unsigned long npages);
+int migrate_device_pfns(unsigned long *src_pfns, unsigned long npages);
 void migrate_device_pages(unsigned long *src_pfns, unsigned long *dst_pfns,
 			unsigned long npages);
 void migrate_device_finalize(unsigned long *src_pfns,
diff --git a/include/linux/migrate_mode.h b/include/linux/migrate_mode.h
index f37cc03f9369..265c4328b36a 100644
--- a/include/linux/migrate_mode.h
+++ b/include/linux/migrate_mode.h
@@ -7,16 +7,11 @@
  *	on most operations but not ->writepage as the potential stall time
  *	is too significant
  * MIGRATE_SYNC will block when migrating pages
- * MIGRATE_SYNC_NO_COPY will block when migrating pages but will not copy pages
- *	with the CPU. Instead, page copy happens outside the migratepage()
- *	callback and is likely using a DMA engine. See migrate_vma() and HMM
- *	(mm/hmm.c) for users of this mode.
  */
 enum migrate_mode {
 	MIGRATE_ASYNC,
 	MIGRATE_SYNC_LIGHT,
 	MIGRATE_SYNC,
-	MIGRATE_SYNC_NO_COPY,
 };
 
 enum migrate_reason {
@@ -29,6 +24,7 @@ enum migrate_reason {
 	MR_CONTIG_RANGE,
 	MR_LONGTERM_PIN,
 	MR_DEMOTION,
+	MR_DAMON,
 	MR_TYPES
 };
 
diff --git a/include/linux/mii.h b/include/linux/mii.h
index d5a959ce4877..b8f26d4513c3 100644
--- a/include/linux/mii.h
+++ b/include/linux/mii.h
@@ -140,7 +140,7 @@ static inline u32 ethtool_adv_to_mii_adv_t(u32 ethadv)
  * settings to phy autonegotiation advertisements for the
  * MII_ADVERTISE register.
  */
-static inline u32 linkmode_adv_to_mii_adv_t(unsigned long *advertising)
+static inline u32 linkmode_adv_to_mii_adv_t(const unsigned long *advertising)
 {
 	u32 result = 0;
 
@@ -215,7 +215,8 @@ static inline u32 ethtool_adv_to_mii_ctrl1000_t(u32 ethadv)
  * settings to phy autonegotiation advertisements for the
  * MII_CTRL1000 register when in 1000T mode.
  */
-static inline u32 linkmode_adv_to_mii_ctrl1000_t(unsigned long *advertising)
+static inline u32
+linkmode_adv_to_mii_ctrl1000_t(const unsigned long *advertising)
 {
 	u32 result = 0;
 
@@ -453,7 +454,7 @@ static inline void mii_ctrl1000_mod_linkmode_adv_t(unsigned long *advertising,
  * A small helper function that translates linkmode advertising to LVL
  * pause capabilities.
  */
-static inline u32 linkmode_adv_to_lcl_adv_t(unsigned long *advertising)
+static inline u32 linkmode_adv_to_lcl_adv_t(const unsigned long *advertising)
 {
 	u32 lcl_adv = 0;
 
diff --git a/include/linux/mii_timestamper.h b/include/linux/mii_timestamper.h
index fa940bbaf8ae..3102c425c8e0 100644
--- a/include/linux/mii_timestamper.h
+++ b/include/linux/mii_timestamper.h
@@ -9,6 +9,7 @@
 #include <linux/device.h>
 #include <linux/ethtool.h>
 #include <linux/skbuff.h>
+#include <linux/net_tstamp.h>
 
 struct phy_device;
 
@@ -26,7 +27,9 @@ struct phy_device;
  *		as soon as a timestamp becomes available. One of the PTP_CLASS_
  *		values is passed in 'type'.
  *
- * @hwtstamp:	Handles SIOCSHWTSTAMP ioctl for hardware time stamping.
+ * @hwtstamp_set: Handles SIOCSHWTSTAMP ioctl for hardware time stamping.
+ *
+ * @hwtstamp_get: Handles SIOCGHWTSTAMP ioctl for hardware time stamping.
  *
  * @link_state: Allows the device to respond to changes in the link
  *		state.  The caller invokes this function while holding
@@ -50,14 +53,18 @@ struct mii_timestamper {
 	void (*txtstamp)(struct mii_timestamper *mii_ts,
 			 struct sk_buff *skb, int type);
 
-	int  (*hwtstamp)(struct mii_timestamper *mii_ts,
-			 struct ifreq *ifreq);
+	int  (*hwtstamp_set)(struct mii_timestamper *mii_ts,
+			     struct kernel_hwtstamp_config *kernel_config,
+			     struct netlink_ext_ack *extack);
+
+	int  (*hwtstamp_get)(struct mii_timestamper *mii_ts,
+			     struct kernel_hwtstamp_config *kernel_config);
 
 	void (*link_state)(struct mii_timestamper *mii_ts,
 			   struct phy_device *phydev);
 
 	int  (*ts_info)(struct mii_timestamper *mii_ts,
-			struct ethtool_ts_info *ts_info);
+			struct kernel_ethtool_ts_info *ts_info);
 
 	struct device *device;
 };
diff --git a/include/linux/min_heap.h b/include/linux/min_heap.h
index 44077837385f..79ddc0adbf2b 100644
--- a/include/linux/min_heap.h
+++ b/include/linux/min_heap.h
@@ -6,129 +6,472 @@
 #include <linux/string.h>
 #include <linux/types.h>
 
+/*
+ * The Min Heap API provides utilities for managing min-heaps, a binary tree
+ * structure where each node's value is less than or equal to its children's
+ * values, ensuring the smallest element is at the root.
+ *
+ * Users should avoid directly calling functions prefixed with __min_heap_*().
+ * Instead, use the provided macro wrappers.
+ *
+ * For further details and examples, refer to Documentation/core-api/min_heap.rst.
+ */
+
 /**
- * struct min_heap - Data structure to hold a min-heap.
- * @data: Start of array holding the heap elements.
+ * Data structure to hold a min-heap.
  * @nr: Number of elements currently in the heap.
  * @size: Maximum number of elements that can be held in current storage.
+ * @data: Pointer to the start of array holding the heap elements.
+ * @preallocated: Start of the static preallocated array holding the heap elements.
  */
-struct min_heap {
-	void *data;
-	int nr;
-	int size;
-};
+#define MIN_HEAP_PREALLOCATED(_type, _name, _nr)	\
+struct _name {	\
+	size_t nr;	\
+	size_t size;	\
+	_type *data;	\
+	_type preallocated[_nr];	\
+}
+
+#define DEFINE_MIN_HEAP(_type, _name) MIN_HEAP_PREALLOCATED(_type, _name, 0)
+
+typedef DEFINE_MIN_HEAP(char, min_heap_char) min_heap_char;
+
+#define __minheap_cast(_heap)		(typeof((_heap)->data[0]) *)
+#define __minheap_obj_size(_heap)	sizeof((_heap)->data[0])
 
 /**
  * struct min_heap_callbacks - Data/functions to customise the min_heap.
- * @elem_size: The nr of each element in bytes.
  * @less: Partial order function for this heap.
  * @swp: Swap elements function.
  */
 struct min_heap_callbacks {
-	int elem_size;
-	bool (*less)(const void *lhs, const void *rhs);
-	void (*swp)(void *lhs, void *rhs);
+	bool (*less)(const void *lhs, const void *rhs, void *args);
+	void (*swp)(void *lhs, void *rhs, void *args);
 };
 
+/**
+ * is_aligned - is this pointer & size okay for word-wide copying?
+ * @base: pointer to data
+ * @size: size of each element
+ * @align: required alignment (typically 4 or 8)
+ *
+ * Returns true if elements can be copied using word loads and stores.
+ * The size must be a multiple of the alignment, and the base address must
+ * be if we do not have CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS.
+ *
+ * For some reason, gcc doesn't know to optimize "if (a & mask || b & mask)"
+ * to "if ((a | b) & mask)", so we do that by hand.
+ */
+__attribute_const__ __always_inline
+static bool is_aligned(const void *base, size_t size, unsigned char align)
+{
+	unsigned char lsbits = (unsigned char)size;
+
+	(void)base;
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+	lsbits |= (unsigned char)(uintptr_t)base;
+#endif
+	return (lsbits & (align - 1)) == 0;
+}
+
+/**
+ * swap_words_32 - swap two elements in 32-bit chunks
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size (must be a multiple of 4)
+ *
+ * Exchange the two objects in memory.  This exploits base+index addressing,
+ * which basically all CPUs have, to minimize loop overhead computations.
+ *
+ * For some reason, on x86 gcc 7.3.0 adds a redundant test of n at the
+ * bottom of the loop, even though the zero flag is still valid from the
+ * subtract (since the intervening mov instructions don't alter the flags).
+ * Gcc 8.1.0 doesn't have that problem.
+ */
+static __always_inline
+void swap_words_32(void *a, void *b, size_t n)
+{
+	do {
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+	} while (n);
+}
+
+/**
+ * swap_words_64 - swap two elements in 64-bit chunks
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size (must be a multiple of 8)
+ *
+ * Exchange the two objects in memory.  This exploits base+index
+ * addressing, which basically all CPUs have, to minimize loop overhead
+ * computations.
+ *
+ * We'd like to use 64-bit loads if possible.  If they're not, emulating
+ * one requires base+index+4 addressing which x86 has but most other
+ * processors do not.  If CONFIG_64BIT, we definitely have 64-bit loads,
+ * but it's possible to have 64-bit loads without 64-bit pointers (e.g.
+ * x32 ABI).  Are there any cases the kernel needs to worry about?
+ */
+static __always_inline
+void swap_words_64(void *a, void *b, size_t n)
+{
+	do {
+#ifdef CONFIG_64BIT
+		u64 t = *(u64 *)(a + (n -= 8));
+		*(u64 *)(a + n) = *(u64 *)(b + n);
+		*(u64 *)(b + n) = t;
+#else
+		/* Use two 32-bit transfers to avoid base+index+4 addressing */
+		u32 t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+
+		t = *(u32 *)(a + (n -= 4));
+		*(u32 *)(a + n) = *(u32 *)(b + n);
+		*(u32 *)(b + n) = t;
+#endif
+	} while (n);
+}
+
+/**
+ * swap_bytes - swap two elements a byte at a time
+ * @a: pointer to the first element to swap
+ * @b: pointer to the second element to swap
+ * @n: element size
+ *
+ * This is the fallback if alignment doesn't allow using larger chunks.
+ */
+static __always_inline
+void swap_bytes(void *a, void *b, size_t n)
+{
+	do {
+		char t = ((char *)a)[--n];
+		((char *)a)[n] = ((char *)b)[n];
+		((char *)b)[n] = t;
+	} while (n);
+}
+
+/*
+ * The values are arbitrary as long as they can't be confused with
+ * a pointer, but small integers make for the smallest compare
+ * instructions.
+ */
+#define SWAP_WORDS_64 ((void (*)(void *, void *, void *))0)
+#define SWAP_WORDS_32 ((void (*)(void *, void *, void *))1)
+#define SWAP_BYTES    ((void (*)(void *, void *, void *))2)
+
+/*
+ * Selects the appropriate swap function based on the element size.
+ */
+static __always_inline
+void *select_swap_func(const void *base, size_t size)
+{
+	if (is_aligned(base, size, 8))
+		return SWAP_WORDS_64;
+	else if (is_aligned(base, size, 4))
+		return SWAP_WORDS_32;
+	else
+		return SWAP_BYTES;
+}
+
+static __always_inline
+void do_swap(void *a, void *b, size_t size, void (*swap_func)(void *lhs, void *rhs, void *args),
+	     void *priv)
+{
+	if (swap_func == SWAP_WORDS_64)
+		swap_words_64(a, b, size);
+	else if (swap_func == SWAP_WORDS_32)
+		swap_words_32(a, b, size);
+	else if (swap_func == SWAP_BYTES)
+		swap_bytes(a, b, size);
+	else
+		swap_func(a, b, priv);
+}
+
+/**
+ * parent - given the offset of the child, find the offset of the parent.
+ * @i: the offset of the heap element whose parent is sought.  Non-zero.
+ * @lsbit: a precomputed 1-bit mask, equal to "size & -size"
+ * @size: size of each element
+ *
+ * In terms of array indexes, the parent of element j = @i/@size is simply
+ * (j-1)/2.  But when working in byte offsets, we can't use implicit
+ * truncation of integer divides.
+ *
+ * Fortunately, we only need one bit of the quotient, not the full divide.
+ * @size has a least significant bit.  That bit will be clear if @i is
+ * an even multiple of @size, and set if it's an odd multiple.
+ *
+ * Logically, we're doing "if (i & lsbit) i -= size;", but since the
+ * branch is unpredictable, it's done with a bit of clever branch-free
+ * code instead.
+ */
+__attribute_const__ __always_inline
+static size_t parent(size_t i, unsigned int lsbit, size_t size)
+{
+	i -= size;
+	i -= size & -(i & lsbit);
+	return i / 2;
+}
+
+/* Initialize a min-heap. */
+static __always_inline
+void __min_heap_init_inline(min_heap_char *heap, void *data, size_t size)
+{
+	heap->nr = 0;
+	heap->size = size;
+	if (data)
+		heap->data = data;
+	else
+		heap->data = heap->preallocated;
+}
+
+#define min_heap_init_inline(_heap, _data, _size)	\
+	__min_heap_init_inline(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size)
+
+/* Get the minimum element from the heap. */
+static __always_inline
+void *__min_heap_peek_inline(struct min_heap_char *heap)
+{
+	return heap->nr ? heap->data : NULL;
+}
+
+#define min_heap_peek_inline(_heap)	\
+	(__minheap_cast(_heap)	\
+	 __min_heap_peek_inline(container_of(&(_heap)->nr, min_heap_char, nr)))
+
+/* Check if the heap is full. */
+static __always_inline
+bool __min_heap_full_inline(min_heap_char *heap)
+{
+	return heap->nr == heap->size;
+}
+
+#define min_heap_full_inline(_heap)	\
+	__min_heap_full_inline(container_of(&(_heap)->nr, min_heap_char, nr))
+
 /* Sift the element at pos down the heap. */
 static __always_inline
-void min_heapify(struct min_heap *heap, int pos,
-		const struct min_heap_callbacks *func)
+void __min_heap_sift_down_inline(min_heap_char *heap, size_t pos, size_t elem_size,
+				 const struct min_heap_callbacks *func, void *args)
 {
-	void *left, *right, *parent, *smallest;
+	const unsigned long lsbit = elem_size & -elem_size;
 	void *data = heap->data;
+	void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
+	/* pre-scale counters for performance */
+	size_t a = pos * elem_size;
+	size_t b, c, d;
+	size_t n = heap->nr * elem_size;
 
-	for (;;) {
-		if (pos * 2 + 1 >= heap->nr)
-			break;
+	if (!swp)
+		swp = select_swap_func(data, elem_size);
+
+	/* Find the sift-down path all the way to the leaves. */
+	for (b = a; c = 2 * b + elem_size, (d = c + elem_size) < n;)
+		b = func->less(data + c, data + d, args) ? c : d;
+
+	/* Special case for the last leaf with no sibling. */
+	if (d == n)
+		b = c;
+
+	/* Backtrack to the correct location. */
+	while (b != a && func->less(data + a, data + b, args))
+		b = parent(b, lsbit, elem_size);
+
+	/* Shift the element into its correct place. */
+	c = b;
+	while (b != a) {
+		b = parent(b, lsbit, elem_size);
+		do_swap(data + b, data + c, elem_size, swp, args);
+	}
+}
+
+#define min_heap_sift_down_inline(_heap, _pos, _func, _args)	\
+	__min_heap_sift_down_inline(container_of(&(_heap)->nr, min_heap_char, nr), _pos,	\
+				    __minheap_obj_size(_heap), _func, _args)
+
+/* Sift up ith element from the heap, O(log2(nr)). */
+static __always_inline
+void __min_heap_sift_up_inline(min_heap_char *heap, size_t elem_size, size_t idx,
+			       const struct min_heap_callbacks *func, void *args)
+{
+	const unsigned long lsbit = elem_size & -elem_size;
+	void *data = heap->data;
+	void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
+	/* pre-scale counters for performance */
+	size_t a = idx * elem_size, b;
 
-		left = data + ((pos * 2 + 1) * func->elem_size);
-		parent = data + (pos * func->elem_size);
-		smallest = parent;
-		if (func->less(left, smallest))
-			smallest = left;
-
-		if (pos * 2 + 2 < heap->nr) {
-			right = data + ((pos * 2 + 2) * func->elem_size);
-			if (func->less(right, smallest))
-				smallest = right;
-		}
-		if (smallest == parent)
+	if (!swp)
+		swp = select_swap_func(data, elem_size);
+
+	while (a) {
+		b = parent(a, lsbit, elem_size);
+		if (func->less(data + b, data + a, args))
 			break;
-		func->swp(smallest, parent);
-		if (smallest == left)
-			pos = (pos * 2) + 1;
-		else
-			pos = (pos * 2) + 2;
+		do_swap(data + a, data + b, elem_size, swp, args);
+		a = b;
 	}
 }
 
+#define min_heap_sift_up_inline(_heap, _idx, _func, _args)	\
+	__min_heap_sift_up_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+				  __minheap_obj_size(_heap), _idx, _func, _args)
+
 /* Floyd's approach to heapification that is O(nr). */
 static __always_inline
-void min_heapify_all(struct min_heap *heap,
-		const struct min_heap_callbacks *func)
+void __min_heapify_all_inline(min_heap_char *heap, size_t elem_size,
+			      const struct min_heap_callbacks *func, void *args)
 {
-	int i;
+	ssize_t i;
 
-	for (i = heap->nr / 2; i >= 0; i--)
-		min_heapify(heap, i, func);
+	for (i = heap->nr / 2 - 1; i >= 0; i--)
+		__min_heap_sift_down_inline(heap, i, elem_size, func, args);
 }
 
+#define min_heapify_all_inline(_heap, _func, _args)	\
+	__min_heapify_all_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+				 __minheap_obj_size(_heap), _func, _args)
+
 /* Remove minimum element from the heap, O(log2(nr)). */
 static __always_inline
-void min_heap_pop(struct min_heap *heap,
-		const struct min_heap_callbacks *func)
+bool __min_heap_pop_inline(min_heap_char *heap, size_t elem_size,
+			   const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
 
 	if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
-		return;
+		return false;
 
 	/* Place last element at the root (position 0) and then sift down. */
 	heap->nr--;
-	memcpy(data, data + (heap->nr * func->elem_size), func->elem_size);
-	min_heapify(heap, 0, func);
+	memcpy(data, data + (heap->nr * elem_size), elem_size);
+	__min_heap_sift_down_inline(heap, 0, elem_size, func, args);
+
+	return true;
 }
 
+#define min_heap_pop_inline(_heap, _func, _args)	\
+	__min_heap_pop_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			      __minheap_obj_size(_heap), _func, _args)
+
 /*
  * Remove the minimum element and then push the given element. The
  * implementation performs 1 sift (O(log2(nr))) and is therefore more
  * efficient than a pop followed by a push that does 2.
  */
 static __always_inline
-void min_heap_pop_push(struct min_heap *heap,
-		const void *element,
-		const struct min_heap_callbacks *func)
+void __min_heap_pop_push_inline(min_heap_char *heap, const void *element, size_t elem_size,
+				const struct min_heap_callbacks *func, void *args)
 {
-	memcpy(heap->data, element, func->elem_size);
-	min_heapify(heap, 0, func);
+	memcpy(heap->data, element, elem_size);
+	__min_heap_sift_down_inline(heap, 0, elem_size, func, args);
 }
 
+#define min_heap_pop_push_inline(_heap, _element, _func, _args)	\
+	__min_heap_pop_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+				   __minheap_obj_size(_heap), _func, _args)
+
 /* Push an element on to the heap, O(log2(nr)). */
 static __always_inline
-void min_heap_push(struct min_heap *heap, const void *element,
-		const struct min_heap_callbacks *func)
+bool __min_heap_push_inline(min_heap_char *heap, const void *element, size_t elem_size,
+			    const struct min_heap_callbacks *func, void *args)
 {
 	void *data = heap->data;
-	void *child, *parent;
-	int pos;
+	size_t pos;
 
 	if (WARN_ONCE(heap->nr >= heap->size, "Pushing on a full heap"))
-		return;
+		return false;
 
 	/* Place at the end of data. */
 	pos = heap->nr;
-	memcpy(data + (pos * func->elem_size), element, func->elem_size);
+	memcpy(data + (pos * elem_size), element, elem_size);
 	heap->nr++;
 
 	/* Sift child at pos up. */
-	for (; pos > 0; pos = (pos - 1) / 2) {
-		child = data + (pos * func->elem_size);
-		parent = data + ((pos - 1) / 2) * func->elem_size;
-		if (func->less(parent, child))
-			break;
-		func->swp(parent, child);
-	}
+	__min_heap_sift_up_inline(heap, elem_size, pos, func, args);
+
+	return true;
 }
 
+#define min_heap_push_inline(_heap, _element, _func, _args)	\
+	__min_heap_push_inline(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+					    __minheap_obj_size(_heap), _func, _args)
+
+/* Remove ith element from the heap, O(log2(nr)). */
+static __always_inline
+bool __min_heap_del_inline(min_heap_char *heap, size_t elem_size, size_t idx,
+			   const struct min_heap_callbacks *func, void *args)
+{
+	void *data = heap->data;
+	void (*swp)(void *lhs, void *rhs, void *args) = func->swp;
+
+	if (WARN_ONCE(heap->nr <= 0, "Popping an empty heap"))
+		return false;
+
+	if (!swp)
+		swp = select_swap_func(data, elem_size);
+
+	/* Place last element at the root (position 0) and then sift down. */
+	heap->nr--;
+	if (idx == heap->nr)
+		return true;
+	do_swap(data + (idx * elem_size), data + (heap->nr * elem_size), elem_size, swp, args);
+	__min_heap_sift_up_inline(heap, elem_size, idx, func, args);
+	__min_heap_sift_down_inline(heap, idx, elem_size, func, args);
+
+	return true;
+}
+
+#define min_heap_del_inline(_heap, _idx, _func, _args)	\
+	__min_heap_del_inline(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			      __minheap_obj_size(_heap), _idx, _func, _args)
+
+void __min_heap_init(min_heap_char *heap, void *data, size_t size);
+void *__min_heap_peek(struct min_heap_char *heap);
+bool __min_heap_full(min_heap_char *heap);
+void __min_heap_sift_down(min_heap_char *heap, size_t pos, size_t elem_size,
+			  const struct min_heap_callbacks *func, void *args);
+void __min_heap_sift_up(min_heap_char *heap, size_t elem_size, size_t idx,
+			const struct min_heap_callbacks *func, void *args);
+void __min_heapify_all(min_heap_char *heap, size_t elem_size,
+		       const struct min_heap_callbacks *func, void *args);
+bool __min_heap_pop(min_heap_char *heap, size_t elem_size,
+		    const struct min_heap_callbacks *func, void *args);
+void __min_heap_pop_push(min_heap_char *heap, const void *element, size_t elem_size,
+			 const struct min_heap_callbacks *func, void *args);
+bool __min_heap_push(min_heap_char *heap, const void *element, size_t elem_size,
+		     const struct min_heap_callbacks *func, void *args);
+bool __min_heap_del(min_heap_char *heap, size_t elem_size, size_t idx,
+		    const struct min_heap_callbacks *func, void *args);
+
+#define min_heap_init(_heap, _data, _size)	\
+	__min_heap_init(container_of(&(_heap)->nr, min_heap_char, nr), _data, _size)
+#define min_heap_peek(_heap)	\
+	(__minheap_cast(_heap) __min_heap_peek(container_of(&(_heap)->nr, min_heap_char, nr)))
+#define min_heap_full(_heap)	\
+	__min_heap_full(container_of(&(_heap)->nr, min_heap_char, nr))
+#define min_heap_sift_down(_heap, _pos, _func, _args)	\
+	__min_heap_sift_down(container_of(&(_heap)->nr, min_heap_char, nr), _pos,	\
+			     __minheap_obj_size(_heap), _func, _args)
+#define min_heap_sift_up(_heap, _idx, _func, _args)	\
+	__min_heap_sift_up(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			   __minheap_obj_size(_heap), _idx, _func, _args)
+#define min_heapify_all(_heap, _func, _args)	\
+	__min_heapify_all(container_of(&(_heap)->nr, min_heap_char, nr),	\
+			  __minheap_obj_size(_heap), _func, _args)
+#define min_heap_pop(_heap, _func, _args)	\
+	__min_heap_pop(container_of(&(_heap)->nr, min_heap_char, nr),	\
+		       __minheap_obj_size(_heap), _func, _args)
+#define min_heap_pop_push(_heap, _element, _func, _args)	\
+	__min_heap_pop_push(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+			    __minheap_obj_size(_heap), _func, _args)
+#define min_heap_push(_heap, _element, _func, _args)	\
+	__min_heap_push(container_of(&(_heap)->nr, min_heap_char, nr), _element,	\
+			__minheap_obj_size(_heap), _func, _args)
+#define min_heap_del(_heap, _idx, _func, _args)	\
+	__min_heap_del(container_of(&(_heap)->nr, min_heap_char, nr),	\
+		       __minheap_obj_size(_heap), _idx, _func, _args)
+
 #endif /* _LINUX_MIN_HEAP_H */
diff --git a/include/linux/minmax.h b/include/linux/minmax.h
index 396df1121bff..a0158db54a04 100644
--- a/include/linux/minmax.h
+++ b/include/linux/minmax.h
@@ -2,76 +2,137 @@
 #ifndef _LINUX_MINMAX_H
 #define _LINUX_MINMAX_H
 
+#include <linux/build_bug.h>
+#include <linux/compiler.h>
 #include <linux/const.h>
+#include <linux/types.h>
 
 /*
- * min()/max()/clamp() macros must accomplish three things:
+ * min()/max()/clamp() macros must accomplish several things:
  *
- * - avoid multiple evaluations of the arguments (so side-effects like
+ * - Avoid multiple evaluations of the arguments (so side-effects like
  *   "x++" happen only once) when non-constant.
- * - perform strict type-checking (to generate warnings instead of
- *   nasty runtime surprises). See the "unnecessary" pointer comparison
- *   in __typecheck().
- * - retain result as a constant expressions when called with only
- *   constant expressions (to avoid tripping VLA warnings in stack
- *   allocation usage).
+ * - Perform signed v unsigned type-checking (to generate compile
+ *   errors instead of nasty runtime surprises).
+ * - Unsigned char/short are always promoted to signed int and can be
+ *   compared against signed or unsigned arguments.
+ * - Unsigned arguments can be compared against non-negative signed constants.
+ * - Comparison of a signed argument against an unsigned constant fails
+ *   even if the constant is below __INT_MAX__ and could be cast to int.
  */
 #define __typecheck(x, y) \
 	(!!(sizeof((typeof(x) *)1 == (typeof(y) *)1)))
 
-#define __no_side_effects(x, y) \
-		(__is_constexpr(x) && __is_constexpr(y))
+/*
+ * __sign_use for integer expressions:
+ *   bit #0 set if ok for unsigned comparisons
+ *   bit #1 set if ok for signed comparisons
+ *
+ * In particular, statically non-negative signed integer expressions
+ * are ok for both.
+ *
+ * NOTE! Unsigned types smaller than 'int' are implicitly converted to 'int'
+ * in expressions, and are accepted for signed conversions for now.
+ * This is debatable.
+ *
+ * Note that 'x' is the original expression, and 'ux' is the unique variable
+ * that contains the value.
+ *
+ * We use 'ux' for pure type checking, and 'x' for when we need to look at the
+ * value (but without evaluating it for side effects!
+ * Careful to only ever evaluate it with sizeof() or __builtin_constant_p() etc).
+ *
+ * Pointers end up being checked by the normal C type rules at the actual
+ * comparison, and these expressions only need to be careful to not cause
+ * warnings for pointer use.
+ */
+#define __sign_use(ux) (is_signed_type(typeof(ux)) ? \
+	(2 + __is_nonneg(ux)) : (1 + 2 * (sizeof(ux) < 4)))
+
+/*
+ * Check whether a signed value is always non-negative.
+ *
+ * A cast is needed to avoid any warnings from values that aren't signed
+ * integer types (in which case the result doesn't matter).
+ *
+ * On 64-bit any integer or pointer type can safely be cast to 'long long'.
+ * But on 32-bit we need to avoid warnings about casting pointers to integers
+ * of different sizes without truncating 64-bit values so 'long' or 'long long'
+ * must be used depending on the size of the value.
+ *
+ * This does not work for 128-bit signed integers since the cast would truncate
+ * them, but we do not use s128 types in the kernel (we do use 'u128',
+ * but they are handled by the !is_signed_type() case).
+ */
+#if __SIZEOF_POINTER__ == __SIZEOF_LONG_LONG__
+#define __is_nonneg(ux) statically_true((long long)(ux) >= 0)
+#else
+#define __is_nonneg(ux) statically_true( \
+	(typeof(__builtin_choose_expr(sizeof(ux) > 4, 1LL, 1L)))(ux) >= 0)
+#endif
 
-#define __safe_cmp(x, y) \
-		(__typecheck(x, y) && __no_side_effects(x, y))
+#define __types_ok(ux, uy) \
+	(__sign_use(ux) & __sign_use(uy))
 
-#define __cmp(x, y, op)	((x) op (y) ? (x) : (y))
+#define __types_ok3(ux, uy, uz) \
+	(__sign_use(ux) & __sign_use(uy) & __sign_use(uz))
 
-#define __cmp_once(x, y, unique_x, unique_y, op) ({	\
-		typeof(x) unique_x = (x);		\
-		typeof(y) unique_y = (y);		\
-		__cmp(unique_x, unique_y, op); })
+#define __cmp_op_min <
+#define __cmp_op_max >
 
-#define __careful_cmp(x, y, op) \
-	__builtin_choose_expr(__safe_cmp(x, y), \
-		__cmp(x, y, op), \
-		__cmp_once(x, y, __UNIQUE_ID(__x), __UNIQUE_ID(__y), op))
+#define __cmp(op, x, y)	((x) __cmp_op_##op (y) ? (x) : (y))
 
-#define __clamp(val, lo, hi)	\
-	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
+#define __cmp_once_unique(op, type, x, y, ux, uy) \
+	({ type ux = (x); type uy = (y); __cmp(op, ux, uy); })
 
-#define __clamp_once(val, lo, hi, unique_val, unique_lo, unique_hi) ({	\
-		typeof(val) unique_val = (val);				\
-		typeof(lo) unique_lo = (lo);				\
-		typeof(hi) unique_hi = (hi);				\
-		__clamp(unique_val, unique_lo, unique_hi); })
+#define __cmp_once(op, type, x, y) \
+	__cmp_once_unique(op, type, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
-#define __clamp_input_check(lo, hi)					\
-        (BUILD_BUG_ON_ZERO(__builtin_choose_expr(			\
-                __is_constexpr((lo) > (hi)), (lo) > (hi), false)))
+#define __careful_cmp_once(op, x, y, ux, uy) ({		\
+	auto ux = (x); auto uy = (y);			\
+	BUILD_BUG_ON_MSG(!__types_ok(ux, uy),		\
+		#op"("#x", "#y") signedness error");	\
+	__cmp(op, ux, uy); })
 
-#define __careful_clamp(val, lo, hi) ({					\
-	__clamp_input_check(lo, hi) +					\
-	__builtin_choose_expr(__typecheck(val, lo) && __typecheck(val, hi) && \
-			      __typecheck(hi, lo) && __is_constexpr(val) && \
-			      __is_constexpr(lo) && __is_constexpr(hi),	\
-		__clamp(val, lo, hi),					\
-		__clamp_once(val, lo, hi, __UNIQUE_ID(__val),		\
-			     __UNIQUE_ID(__lo), __UNIQUE_ID(__hi))); })
+#define __careful_cmp(op, x, y) \
+	__careful_cmp_once(op, x, y, __UNIQUE_ID(x_), __UNIQUE_ID(y_))
 
 /**
  * min - return minimum of two values of the same or compatible types
  * @x: first value
  * @y: second value
  */
-#define min(x, y)	__careful_cmp(x, y, <)
+#define min(x, y)	__careful_cmp(min, x, y)
 
 /**
  * max - return maximum of two values of the same or compatible types
  * @x: first value
  * @y: second value
  */
-#define max(x, y)	__careful_cmp(x, y, >)
+#define max(x, y)	__careful_cmp(max, x, y)
+
+/**
+ * umin - return minimum of two non-negative values
+ *   Signed types are zero extended to match a larger unsigned type.
+ * @x: first value
+ * @y: second value
+ */
+#define umin(x, y)	\
+	__careful_cmp(min, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull)
+
+/**
+ * umax - return maximum of two non-negative values
+ * @x: first value
+ * @y: second value
+ */
+#define umax(x, y)	\
+	__careful_cmp(max, (x) + 0u + 0ul + 0ull, (y) + 0u + 0ul + 0ull)
+
+#define __careful_op3(op, x, y, z, ux, uy, uz) ({			\
+	auto ux = (x); auto uy = (y); auto uz = (z);			\
+	BUILD_BUG_ON_MSG(!__types_ok3(ux, uy, uz),			\
+		#op"3("#x", "#y", "#z") signedness error");		\
+	__cmp(op, ux, __cmp(op, uy, uz)); })
 
 /**
  * min3 - return minimum of three values
@@ -79,7 +140,8 @@
  * @y: second value
  * @z: third value
  */
-#define min3(x, y, z) min((typeof(x))min(x, y), z)
+#define min3(x, y, z) \
+	__careful_op3(min, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_))
 
 /**
  * max3 - return maximum of three values
@@ -87,7 +149,24 @@
  * @y: second value
  * @z: third value
  */
-#define max3(x, y, z) max((typeof(x))max(x, y), z)
+#define max3(x, y, z) \
+	__careful_op3(max, x, y, z, __UNIQUE_ID(x_), __UNIQUE_ID(y_), __UNIQUE_ID(z_))
+
+/**
+ * min_t - return minimum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define min_t(type, x, y) __cmp_once(min, type, x, y)
+
+/**
+ * max_t - return maximum of two values, using the specified type
+ * @type: data type to use
+ * @x: first value
+ * @y: second value
+ */
+#define max_t(type, x, y) __cmp_once(max, type, x, y)
 
 /**
  * min_not_zero - return the minimum that is _not_ zero, unless both are zero
@@ -99,39 +178,32 @@
 	typeof(y) __y = (y);			\
 	__x == 0 ? __y : ((__y == 0) ? __x : min(__x, __y)); })
 
+#define __clamp(val, lo, hi)	\
+	((val) >= (hi) ? (hi) : ((val) <= (lo) ? (lo) : (val)))
+
+#define __clamp_once(type, val, lo, hi, uval, ulo, uhi) ({			\
+	type uval = (val);							\
+	type ulo = (lo);							\
+	type uhi = (hi);							\
+	BUILD_BUG_ON_MSG(statically_true(ulo > uhi),				\
+		"clamp() low limit " #lo " greater than high limit " #hi);	\
+	BUILD_BUG_ON_MSG(!__types_ok3(uval, ulo, uhi),				\
+		"clamp("#val", "#lo", "#hi") signedness error");		\
+	__clamp(uval, ulo, uhi); })
+
+#define __careful_clamp(type, val, lo, hi) \
+	__clamp_once(type, val, lo, hi, __UNIQUE_ID(v_), __UNIQUE_ID(l_), __UNIQUE_ID(h_))
+
 /**
- * clamp - return a value clamped to a given range with strict typechecking
+ * clamp - return a value clamped to a given range with typechecking
  * @val: current value
  * @lo: lowest allowable value
  * @hi: highest allowable value
  *
- * This macro does strict typechecking of @lo/@hi to make sure they are of the
- * same type as @val.  See the unnecessary pointer comparisons.
- */
-#define clamp(val, lo, hi) __careful_clamp(val, lo, hi)
-
-/*
- * ..and if you can't take the strict
- * types, you can specify one yourself.
- *
- * Or not use min/max/clamp at all, of course.
+ * This macro checks @val/@lo/@hi to make sure they have compatible
+ * signedness.
  */
-
-/**
- * min_t - return minimum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define min_t(type, x, y)	__careful_cmp((type)(x), (type)(y), <)
-
-/**
- * max_t - return maximum of two values, using the specified type
- * @type: data type to use
- * @x: first value
- * @y: second value
- */
-#define max_t(type, x, y)	__careful_cmp((type)(x), (type)(y), >)
+#define clamp(val, lo, hi) __careful_clamp(auto, val, lo, hi)
 
 /**
  * clamp_t - return a value clamped to a given range using a given type
@@ -143,7 +215,7 @@
  * This macro does no typechecking and uses temporary variables of type
  * @type to make all the comparisons.
  */
-#define clamp_t(type, val, lo, hi) __careful_clamp((type)(val), (type)(lo), (type)(hi))
+#define clamp_t(type, val, lo, hi) __careful_clamp(type, val, lo, hi)
 
 /**
  * clamp_val - return a value clamped to a given range using val's type
@@ -156,7 +228,76 @@
  * type and @lo and @hi are literals that will otherwise be assigned a signed
  * integer type.
  */
-#define clamp_val(val, lo, hi) clamp_t(typeof(val), val, lo, hi)
+#define clamp_val(val, lo, hi) __careful_clamp(typeof(val), val, lo, hi)
+
+/*
+ * Do not check the array parameter using __must_be_array().
+ * In the following legit use-case where the "array" passed is a simple pointer,
+ * __must_be_array() will return a failure.
+ * --- 8< ---
+ * int *buff
+ * ...
+ * min = min_array(buff, nb_items);
+ * --- 8< ---
+ *
+ * The first typeof(&(array)[0]) is needed in order to support arrays of both
+ * 'int *buff' and 'int buff[N]' types.
+ *
+ * The array can be an array of const items.
+ * typeof() keeps the const qualifier. Use __unqual_scalar_typeof() in order
+ * to discard the const qualifier for the __element variable.
+ */
+#define __minmax_array(op, array, len) ({				\
+	typeof(&(array)[0]) __array = (array);				\
+	typeof(len) __len = (len);					\
+	__unqual_scalar_typeof(__array[0]) __element = __array[--__len];\
+	while (__len--)							\
+		__element = op(__element, __array[__len]);		\
+	__element; })
+
+/**
+ * min_array - return minimum of values present in an array
+ * @array: array
+ * @len: array length
+ *
+ * Note that @len must not be zero (empty array).
+ */
+#define min_array(array, len) __minmax_array(min, array, len)
+
+/**
+ * max_array - return maximum of values present in an array
+ * @array: array
+ * @len: array length
+ *
+ * Note that @len must not be zero (empty array).
+ */
+#define max_array(array, len) __minmax_array(max, array, len)
+
+static inline bool in_range64(u64 val, u64 start, u64 len)
+{
+	return (val - start) < len;
+}
+
+static inline bool in_range32(u32 val, u32 start, u32 len)
+{
+	return (val - start) < len;
+}
+
+/**
+ * in_range - Determine if a value lies within a range.
+ * @val: Value to test.
+ * @start: First value in range.
+ * @len: Number of values in range.
+ *
+ * This is more efficient than "if (start <= val && val < (start + len))".
+ * It also gives a different answer if @start + @len overflows the size of
+ * the type by a sufficient amount to encompass @val.  Decide for yourself
+ * which behaviour you want, or prove that start + len never overflow.
+ * Do not blindly replace one form with the other.
+ */
+#define in_range(val, start, len)					\
+	((sizeof(start) | sizeof(len) | sizeof(val)) <= sizeof(u32) ?	\
+		in_range32(val, start, len) : in_range64(val, start, len))
 
 /**
  * swap - swap values of @a and @b
@@ -166,4 +307,13 @@
 #define swap(a, b) \
 	do { typeof(a) __tmp = (a); (a) = (b); (b) = __tmp; } while (0)
 
+/*
+ * Use these carefully: no type checking, and uses the arguments
+ * multiple times. Use for obvious constants only.
+ */
+#define MIN(a, b) __cmp(min, a, b)
+#define MAX(a, b) __cmp(max, a, b)
+#define MIN_T(type, a, b) __cmp(min, (type)(a), (type)(b))
+#define MAX_T(type, a, b) __cmp(max, (type)(a), (type)(b))
+
 #endif	/* _LINUX_MINMAX_H */
diff --git a/include/linux/misc/keba.h b/include/linux/misc/keba.h
new file mode 100644
index 000000000000..a81d6fa70851
--- /dev/null
+++ b/include/linux/misc/keba.h
@@ -0,0 +1,72 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2024, KEBA Industrial Automation Gmbh */
+
+#ifndef _LINUX_MISC_KEBA_H
+#define _LINUX_MISC_KEBA_H
+
+#include <linux/auxiliary_bus.h>
+
+struct i2c_board_info;
+struct spi_board_info;
+
+/**
+ * struct keba_i2c_auxdev - KEBA I2C auxiliary device
+ * @auxdev: auxiliary device object
+ * @io: address range of I2C controller IO memory
+ * @info_size: number of I2C devices to be probed
+ * @info: I2C devices to be probed
+ */
+struct keba_i2c_auxdev {
+	struct auxiliary_device auxdev;
+	struct resource io;
+	int info_size;
+	struct i2c_board_info *info;
+};
+
+/**
+ * struct keba_spi_auxdev - KEBA SPI auxiliary device
+ * @auxdev: auxiliary device object
+ * @io: address range of SPI controller IO memory
+ * @info_size: number of SPI devices to be probed
+ * @info: SPI devices to be probed
+ */
+struct keba_spi_auxdev {
+	struct auxiliary_device auxdev;
+	struct resource io;
+	int info_size;
+	struct spi_board_info *info;
+};
+
+/**
+ * struct keba_fan_auxdev - KEBA fan auxiliary device
+ * @auxdev: auxiliary device object
+ * @io: address range of fan controller IO memory
+ */
+struct keba_fan_auxdev {
+	struct auxiliary_device auxdev;
+	struct resource io;
+};
+
+/**
+ * struct keba_batt_auxdev - KEBA battery auxiliary device
+ * @auxdev: auxiliary device object
+ * @io: address range of battery controller IO memory
+ */
+struct keba_batt_auxdev {
+	struct auxiliary_device auxdev;
+	struct resource io;
+};
+
+/**
+ * struct keba_uart_auxdev - KEBA UART auxiliary device
+ * @auxdev: auxiliary device object
+ * @io: address range of UART controller IO memory
+ * @irq: number of UART controller interrupt
+ */
+struct keba_uart_auxdev {
+	struct auxiliary_device auxdev;
+	struct resource io;
+	unsigned int irq;
+};
+
+#endif /* _LINUX_MISC_KEBA_H */
diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h
index c238207d1615..0cb36a3ffc47 100644
--- a/include/linux/misc_cgroup.h
+++ b/include/linux/misc_cgroup.h
@@ -9,15 +9,20 @@
 #define _MISC_CGROUP_H_
 
 /**
- * Types of misc cgroup entries supported by the host.
+ * enum misc_res_type - Types of misc cgroup entries supported by the host.
  */
 enum misc_res_type {
 #ifdef CONFIG_KVM_AMD_SEV
-	/* AMD SEV ASIDs resource */
+	/** @MISC_CG_RES_SEV: AMD SEV ASIDs resource */
 	MISC_CG_RES_SEV,
-	/* AMD SEV-ES ASIDs resource */
+	/** @MISC_CG_RES_SEV_ES: AMD SEV-ES ASIDs resource */
 	MISC_CG_RES_SEV_ES,
 #endif
+#ifdef CONFIG_INTEL_TDX_HOST
+	/** @MISC_CG_RES_TDX: Intel TDX HKIDs resource */
+	MISC_CG_RES_TDX,
+#endif
+	/** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */
 	MISC_CG_RES_TYPES
 };
 
@@ -30,18 +35,22 @@ struct misc_cg;
 /**
  * struct misc_res: Per cgroup per misc type resource
  * @max: Maximum limit on the resource.
+ * @watermark: Historical maximum usage of the resource.
  * @usage: Current usage of the resource.
- * @failed: True if charged failed for the resource in a cgroup.
+ * @events: Number of times, the resource limit exceeded.
  */
 struct misc_res {
-	unsigned long max;
-	atomic_long_t usage;
-	atomic_long_t events;
+	u64 max;
+	atomic64_t watermark;
+	atomic64_t usage;
+	atomic64_t events;
+	atomic64_t events_local;
 };
 
 /**
  * struct misc_cg - Miscellaneous controller's cgroup structure.
  * @css: cgroup subsys state object.
+ * @events_file: Handle for the misc resources events file.
  * @res: Array of misc resources usage in the cgroup.
  */
 struct misc_cg {
@@ -49,16 +58,15 @@ struct misc_cg {
 
 	/* misc.events */
 	struct cgroup_file events_file;
+	/* misc.events.local */
+	struct cgroup_file events_local_file;
 
 	struct misc_res res[MISC_CG_RES_TYPES];
 };
 
-unsigned long misc_cg_res_total_usage(enum misc_res_type type);
-int misc_cg_set_capacity(enum misc_res_type type, unsigned long capacity);
-int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg,
-		       unsigned long amount);
-void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg,
-		      unsigned long amount);
+int misc_cg_set_capacity(enum misc_res_type type, u64 capacity);
+int misc_cg_try_charge(enum misc_res_type type, struct misc_cg *cg, u64 amount);
+void misc_cg_uncharge(enum misc_res_type type, struct misc_cg *cg, u64 amount);
 
 /**
  * css_misc() - Get misc cgroup from the css.
@@ -99,27 +107,21 @@ static inline void put_misc_cg(struct misc_cg *cg)
 
 #else /* !CONFIG_CGROUP_MISC */
 
-static inline unsigned long misc_cg_res_total_usage(enum misc_res_type type)
-{
-	return 0;
-}
-
-static inline int misc_cg_set_capacity(enum misc_res_type type,
-				       unsigned long capacity)
+static inline int misc_cg_set_capacity(enum misc_res_type type, u64 capacity)
 {
 	return 0;
 }
 
 static inline int misc_cg_try_charge(enum misc_res_type type,
 				     struct misc_cg *cg,
-				     unsigned long amount)
+				     u64 amount)
 {
 	return 0;
 }
 
 static inline void misc_cg_uncharge(enum misc_res_type type,
 				    struct misc_cg *cg,
-				    unsigned long amount)
+				    u64 amount)
 {
 }
 
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index c0fea6ca5076..7d0aa718499c 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -70,13 +70,19 @@
 #define UHID_MINOR		239
 #define USERIO_MINOR		240
 #define VHOST_VSOCK_MINOR	241
+#define EISA_EEPROM_MINOR	241
 #define RFKILL_MINOR		242
-#define MISC_DYNAMIC_MINOR	255
 
-struct device;
-struct attribute_group;
+/*
+ * Misc char device minor code space division related to below macro:
+ *
+ * <  255  : Fixed minor code
+ * == 255  : Indicator to request dynamic minor code
+ * >  255  : Dynamic minor code requested, 1048320 minor codes totally.
+ */
+#define MISC_DYNAMIC_MINOR	255
 
-struct miscdevice  {
+struct miscdevice {
 	int minor;
 	const char *name;
 	const struct file_operations *fops;
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 6646634a0b9d..f016263e1fcf 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -33,6 +33,7 @@
 #ifndef MLX4_DEVICE_H
 #define MLX4_DEVICE_H
 
+#include <linux/auxiliary_bus.h>
 #include <linux/if_ether.h>
 #include <linux/pci.h>
 #include <linux/completion.h>
@@ -889,6 +890,12 @@ struct mlx4_dev {
 	u8  uar_page_shift;
 };
 
+struct mlx4_adev {
+	struct auxiliary_device adev;
+	struct mlx4_dev *mdev;
+	int idx;
+};
+
 struct mlx4_clock_params {
 	u64 offset;
 	u8 bar;
@@ -1087,6 +1094,19 @@ static inline void *mlx4_buf_offset(struct mlx4_buf *buf, int offset)
 			(offset & (PAGE_SIZE - 1));
 }
 
+static inline int mlx4_is_bonded(struct mlx4_dev *dev)
+{
+	return !!(dev->flags & MLX4_FLAG_BONDED);
+}
+
+static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev)
+{
+	return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev));
+}
+
+int mlx4_queue_bond_work(struct mlx4_dev *dev, int is_bonded, u8 v2p_p1,
+			 u8 v2p_p2);
+
 int mlx4_pd_alloc(struct mlx4_dev *dev, u32 *pdn);
 void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn);
 int mlx4_xrcd_alloc(struct mlx4_dev *dev, u32 *xrcdn);
@@ -1115,7 +1135,7 @@ int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 		       struct mlx4_buf *buf);
 
-int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, int order);
+int mlx4_db_alloc(struct mlx4_dev *dev, struct mlx4_db *db, unsigned int order);
 void mlx4_db_free(struct mlx4_dev *dev, struct mlx4_db *db);
 
 int mlx4_alloc_hwq_res(struct mlx4_dev *dev, struct mlx4_hwq_resources *wqres,
@@ -1395,7 +1415,6 @@ int mlx4_get_is_vlan_offload_disabled(struct mlx4_dev *dev, u8 port,
 				      bool *vlan_offload_disabled);
 void mlx4_handle_eth_header_mcast_prio(struct mlx4_net_trans_rule_hw_ctrl *ctrl,
 				       struct _rule_hw *eth_header);
-int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
diff --git a/include/linux/mlx4/driver.h b/include/linux/mlx4/driver.h
index 1834c8fad12e..69825223081f 100644
--- a/include/linux/mlx4/driver.h
+++ b/include/linux/mlx4/driver.h
@@ -34,8 +34,12 @@
 #define MLX4_DRIVER_H
 
 #include <net/devlink.h>
+#include <linux/auxiliary_bus.h>
+#include <linux/notifier.h>
 #include <linux/mlx4/device.h>
 
+#define MLX4_ADEV_NAME "mlx4_core"
+
 struct mlx4_dev;
 
 #define MLX4_MAC_MASK	   0xffffffffffffULL
@@ -54,41 +58,19 @@ enum {
 	MLX4_INTFF_BONDING	= 1 << 0
 };
 
-struct mlx4_interface {
-	void *			(*add)	 (struct mlx4_dev *dev);
-	void			(*remove)(struct mlx4_dev *dev, void *context);
-	void			(*event) (struct mlx4_dev *dev, void *context,
-					  enum mlx4_dev_event event, unsigned long param);
-	void *			(*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
-	void			(*activate)(struct mlx4_dev *dev, void *context);
-	struct list_head	list;
+struct mlx4_adrv {
+	struct auxiliary_driver	adrv;
 	enum mlx4_protocol	protocol;
 	int			flags;
 };
 
-int mlx4_register_interface(struct mlx4_interface *intf);
-void mlx4_unregister_interface(struct mlx4_interface *intf);
-
-int mlx4_bond(struct mlx4_dev *dev);
-int mlx4_unbond(struct mlx4_dev *dev);
-static inline int mlx4_is_bonded(struct mlx4_dev *dev)
-{
-	return !!(dev->flags & MLX4_FLAG_BONDED);
-}
-
-static inline int mlx4_is_mf_bonded(struct mlx4_dev *dev)
-{
-	return (mlx4_is_bonded(dev) && mlx4_is_mfunc(dev));
-}
-
-struct mlx4_port_map {
-	u8	port1;
-	u8	port2;
-};
-
-int mlx4_port_map_set(struct mlx4_dev *dev, struct mlx4_port_map *v2p);
+int mlx4_register_auxiliary_driver(struct mlx4_adrv *madrv);
+void mlx4_unregister_auxiliary_driver(struct mlx4_adrv *madrv);
 
-void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
+int mlx4_register_event_notifier(struct mlx4_dev *dev,
+				 struct notifier_block *nb);
+int mlx4_unregister_event_notifier(struct mlx4_dev *dev,
+				   struct notifier_block *nb);
 
 struct devlink_port *mlx4_get_devlink_port(struct mlx4_dev *dev, int port);
 
diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h
index cb15308b5cb0..9d47cdc727ad 100644
--- a/include/linux/mlx5/cq.h
+++ b/include/linux/mlx5/cq.h
@@ -41,7 +41,6 @@ struct mlx5_core_cq {
 	int			cqe_sz;
 	__be32		       *set_ci_db;
 	__be32		       *arm_db;
-	struct mlx5_uars_page  *uar;
 	refcount_t		refcount;
 	struct completion	free;
 	unsigned		vector;
@@ -95,9 +94,10 @@ enum {
 };
 
 enum {
-	MLX5_CQ_MODIFY_PERIOD	= 1 << 0,
-	MLX5_CQ_MODIFY_COUNT	= 1 << 1,
-	MLX5_CQ_MODIFY_OVERRUN	= 1 << 2,
+	MLX5_CQ_MODIFY_PERIOD		= BIT(0),
+	MLX5_CQ_MODIFY_COUNT		= BIT(1),
+	MLX5_CQ_MODIFY_OVERRUN		= BIT(2),
+	MLX5_CQ_MODIFY_PERIOD_MODE	= BIT(4),
 };
 
 enum {
@@ -183,6 +183,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq)
 		complete(&cq->free);
 }
 
+void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe);
 int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		   u32 *in, int inlen, u32 *out, int outlen);
 int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index c0af74efd3cb..d7f46a8fbfa1 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -68,7 +68,7 @@
 #define MLX5_UN_SZ_BYTES(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 8)
 #define MLX5_UN_SZ_DW(typ) (sizeof(union mlx5_ifc_##typ##_bits) / 32)
 #define MLX5_BYTE_OFF(typ, fld) (__mlx5_bit_off(typ, fld) / 8)
-#define MLX5_ADDR_OF(typ, p, fld) ((void *)((uint8_t *)(p) + MLX5_BYTE_OFF(typ, fld)))
+#define MLX5_ADDR_OF(typ, p, fld) ((void *)((u8 *)(p) + MLX5_BYTE_OFF(typ, fld)))
 
 /* insert a value to a struct */
 #define MLX5_SET(typ, p, fld, v) do { \
@@ -211,6 +211,7 @@ enum {
 enum {
 	MLX5_PFAULT_SUBTYPE_WQE = 0,
 	MLX5_PFAULT_SUBTYPE_RDMA = 1,
+	MLX5_PFAULT_SUBTYPE_MEMORY = 2,
 };
 
 enum wqe_page_fault_type {
@@ -279,6 +280,7 @@ enum {
 	MLX5_MKEY_MASK_SMALL_FENCE	= 1ull << 23,
 	MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE	= 1ull << 25,
 	MLX5_MKEY_MASK_FREE			= 1ull << 29,
+	MLX5_MKEY_MASK_PAGE_SIZE_5		= 1ull << 42,
 	MLX5_MKEY_MASK_RELAXED_ORDERING_READ	= 1ull << 47,
 };
 
@@ -294,6 +296,7 @@ enum {
 #define MLX5_UMR_FLEX_ALIGNMENT 0x40
 #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt))
 #define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm))
+#define MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_ksm))
 
 #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8)
 
@@ -364,6 +367,12 @@ enum mlx5_event {
 enum mlx5_driver_event {
 	MLX5_DRIVER_EVENT_TYPE_TRAP = 0,
 	MLX5_DRIVER_EVENT_UPLINK_NETDEV,
+	MLX5_DRIVER_EVENT_MACSEC_SA_ADDED,
+	MLX5_DRIVER_EVENT_MACSEC_SA_DELETED,
+	MLX5_DRIVER_EVENT_SF_PEER_DEVLINK,
+	MLX5_DRIVER_EVENT_AFFILIATION_DONE,
+	MLX5_DRIVER_EVENT_AFFILIATION_REMOVED,
+	MLX5_DRIVER_EVENT_ACTIVE_BACKUP_LAG_CHANGE_LOWERSTATE,
 };
 
 enum {
@@ -530,6 +539,7 @@ struct mlx5_cmd_layout {
 };
 
 enum mlx5_rfr_severity_bit_offsets {
+	MLX5_CRR_BIT_OFFSET = 0x6,
 	MLX5_RFR_BIT_OFFSET = 0x7,
 };
 
@@ -640,10 +650,11 @@ struct mlx5_eqe_page_req {
 	__be32		rsvd1[5];
 };
 
+#define MEMORY_SCHEME_PAGE_FAULT_GRANULARITY 4096
 struct mlx5_eqe_page_fault {
-	__be32 bytes_committed;
 	union {
 		struct {
+			__be32  bytes_committed;
 			u16     reserved1;
 			__be16  wqe_index;
 			u16	reserved2;
@@ -653,6 +664,7 @@ struct mlx5_eqe_page_fault {
 			__be32  pftype_wq;
 		} __packed wqe;
 		struct {
+			__be32  bytes_committed;
 			__be32  r_key;
 			u16	reserved1;
 			__be16  packet_length;
@@ -660,6 +672,23 @@ struct mlx5_eqe_page_fault {
 			__be64  rdma_va;
 			__be32  pftype_token;
 		} __packed rdma;
+		struct {
+			u8      flags;
+			u8      reserved1;
+			__be16  post_demand_fault_pages;
+			__be16  pre_demand_fault_pages;
+			__be16  token47_32;
+			__be32  token31_0;
+			/*
+			 * FW changed from specifying the fault size in byte
+			 * count to 4k pages granularity. The size specified
+			 * in pages uses bits 31:12, to keep backward
+			 * compatibility.
+			 */
+			__be32 demand_fault_pages;
+			__be32  mkey;
+			__be64  va;
+		} __packed memory;
 	} __packed;
 } __packed;
 
@@ -716,6 +745,7 @@ enum sync_rst_state_type {
 	MLX5_SYNC_RST_STATE_RESET_REQUEST	= 0x0,
 	MLX5_SYNC_RST_STATE_RESET_NOW		= 0x1,
 	MLX5_SYNC_RST_STATE_RESET_ABORT		= 0x2,
+	MLX5_SYNC_RST_STATE_RESET_UNLOAD	= 0x3,
 };
 
 struct mlx5_eqe_sync_fw_update {
@@ -912,7 +942,7 @@ static inline u8 get_cqe_tls_offload(struct mlx5_cqe64 *cqe)
 	return (cqe->tls_outer_l3_tunneled >> 3) & 0x3;
 }
 
-static inline bool cqe_has_vlan(struct mlx5_cqe64 *cqe)
+static inline bool cqe_has_vlan(const struct mlx5_cqe64 *cqe)
 {
 	return cqe->l4_l3_hdr_type & 0x1;
 }
@@ -1207,9 +1237,7 @@ enum mlx5_cap_type {
 	MLX5_CAP_FLOW_TABLE,
 	MLX5_CAP_ESWITCH_FLOW_TABLE,
 	MLX5_CAP_ESWITCH,
-	MLX5_CAP_RESERVED,
-	MLX5_CAP_VECTOR_CALC,
-	MLX5_CAP_QOS,
+	MLX5_CAP_QOS = 0xc,
 	MLX5_CAP_DEBUG,
 	MLX5_CAP_RESERVED_14,
 	MLX5_CAP_DEV_MEM,
@@ -1219,11 +1247,13 @@ enum mlx5_cap_type {
 	MLX5_CAP_DEV_EVENT = 0x14,
 	MLX5_CAP_IPSEC,
 	MLX5_CAP_CRYPTO = 0x1a,
-	MLX5_CAP_DEV_SHAMPO = 0x1d,
+	MLX5_CAP_SHAMPO = 0x1d,
+	MLX5_CAP_PSP = 0x1e,
 	MLX5_CAP_MACSEC = 0x1f,
 	MLX5_CAP_GENERAL_2 = 0x20,
 	MLX5_CAP_PORT_SELECTION = 0x25,
 	MLX5_CAP_ADV_VIRTUALIZATION = 0x26,
+	MLX5_CAP_ADV_RDMA = 0x28,
 	/* NUM OF CAP Types */
 	MLX5_CAP_NUM
 };
@@ -1238,9 +1268,9 @@ enum mlx5_pcam_feature_groups {
 
 enum mlx5_mcam_reg_groups {
 	MLX5_MCAM_REGS_FIRST_128                    = 0x0,
-	MLX5_MCAM_REGS_0x9080_0x90FF                = 0x1,
 	MLX5_MCAM_REGS_0x9100_0x917F                = 0x2,
-	MLX5_MCAM_REGS_NUM                          = 0x3,
+	MLX5_MCAM_REGS_0x9180_0x91FF                = 0x3,
+	MLX5_MCAM_REGS_NUM                          = 0x4,
 };
 
 enum mlx5_mcam_feature_groups {
@@ -1278,10 +1308,6 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(per_protocol_networking_offload_caps,\
 		 mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->cur, cap)
 
-#define MLX5_CAP_ETH_MAX(mdev, cap) \
-	MLX5_GET(per_protocol_networking_offload_caps,\
-		 mdev->caps.hca[MLX5_CAP_ETHERNET_OFFLOADS]->max, cap)
-
 #define MLX5_CAP_IPOIB_ENHANCED(mdev, cap) \
 	MLX5_GET(per_protocol_networking_offload_caps,\
 		 mdev->caps.hca[MLX5_CAP_IPOIB_ENHANCED_OFFLOADS]->cur, cap)
@@ -1304,76 +1330,48 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP64_FLOWTABLE(mdev, cap) \
 	MLX5_GET64(flow_table_nic_cap, (mdev)->caps.hca[MLX5_CAP_FLOW_TABLE]->cur, cap)
 
-#define MLX5_CAP_FLOWTABLE_MAX(mdev, cap) \
-	MLX5_GET(flow_table_nic_cap, mdev->caps.hca[MLX5_CAP_FLOW_TABLE]->max, cap)
-
 #define MLX5_CAP_FLOWTABLE_NIC_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive.cap)
 
-#define MLX5_CAP_FLOWTABLE_NIC_RX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive.cap)
-
 #define MLX5_CAP_FLOWTABLE_NIC_TX(mdev, cap) \
 		MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit.cap)
 
-#define MLX5_CAP_FLOWTABLE_NIC_TX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit.cap)
-
 #define MLX5_CAP_FLOWTABLE_SNIFFER_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_sniffer.cap)
 
-#define MLX5_CAP_FLOWTABLE_SNIFFER_RX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_sniffer.cap)
-
 #define MLX5_CAP_FLOWTABLE_SNIFFER_TX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_sniffer.cap)
 
-#define MLX5_CAP_FLOWTABLE_SNIFFER_TX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_sniffer.cap)
-
 #define MLX5_CAP_FLOWTABLE_RDMA_RX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_receive_rdma.cap)
 
-#define MLX5_CAP_FLOWTABLE_RDMA_RX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_receive_rdma.cap)
-
 #define MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, cap) \
 	MLX5_CAP_FLOWTABLE(mdev, flow_table_properties_nic_transmit_rdma.cap)
 
-#define MLX5_CAP_FLOWTABLE_RDMA_TX_MAX(mdev, cap) \
-	MLX5_CAP_FLOWTABLE_MAX(mdev, flow_table_properties_nic_transmit_rdma.cap)
+#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_RX(mdev, cap) \
+	MLX5_CAP_ADV_RDMA(mdev, rdma_transport_rx_flow_table_properties.cap)
+
+#define MLX5_CAP_FLOWTABLE_RDMA_TRANSPORT_TX(mdev, cap) \
+	MLX5_CAP_ADV_RDMA(mdev, rdma_transport_tx_flow_table_properties.cap)
 
 #define MLX5_CAP_ESW_FLOWTABLE(mdev, cap) \
 	MLX5_GET(flow_table_eswitch_cap, \
 		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
 
-#define MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, cap) \
-	MLX5_GET(flow_table_eswitch_cap, \
-		 mdev->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->max, cap)
-
 #define MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_nic_esw_fdb.cap)
 
-#define MLX5_CAP_ESW_FLOWTABLE_FDB_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_nic_esw_fdb.cap)
-
 #define MLX5_CAP_ESW_EGRESS_ACL(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_egress.cap)
 
-#define MLX5_CAP_ESW_EGRESS_ACL_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_egress.cap)
-
 #define MLX5_CAP_ESW_INGRESS_ACL(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, flow_table_properties_esw_acl_ingress.cap)
 
-#define MLX5_CAP_ESW_INGRESS_ACL_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, flow_table_properties_esw_acl_ingress.cap)
-
 #define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2(mdev, cap) \
 	MLX5_CAP_ESW_FLOWTABLE(mdev, ft_field_support_2_esw_fdb.cap)
 
-#define MLX5_CAP_ESW_FT_FIELD_SUPPORT_2_MAX(mdev, cap) \
-	MLX5_CAP_ESW_FLOWTABLE_MAX(mdev, ft_field_support_2_esw_fdb.cap)
+#define MLX5_CAP_NIC_RX_FT_FIELD_SUPPORT_2(mdev, cap) \
+		MLX5_CAP_FLOWTABLE(mdev, ft_field_support_2_nic_receive.cap)
 
 #define MLX5_CAP_ESW(mdev, cap) \
 	MLX5_GET(e_switch_cap, \
@@ -1383,10 +1381,6 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET64(flow_table_eswitch_cap, \
 		(mdev)->caps.hca[MLX5_CAP_ESWITCH_FLOW_TABLE]->cur, cap)
 
-#define MLX5_CAP_ESW_MAX(mdev, cap) \
-	MLX5_GET(e_switch_cap, \
-		 mdev->caps.hca[MLX5_CAP_ESWITCH]->max, cap)
-
 #define MLX5_CAP_PORT_SELECTION(mdev, cap) \
 	MLX5_GET(port_selection_cap, \
 		 mdev->caps.hca[MLX5_CAP_PORT_SELECTION]->cur, cap)
@@ -1399,26 +1393,30 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(adv_virtualization_cap, \
 		 mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->cur, cap)
 
-#define MLX5_CAP_ADV_VIRTUALIZATION_MAX(mdev, cap) \
-	MLX5_GET(adv_virtualization_cap, \
-		 mdev->caps.hca[MLX5_CAP_ADV_VIRTUALIZATION]->max, cap)
+#define MLX5_CAP_ADV_RDMA(mdev, cap) \
+	MLX5_GET(adv_rdma_cap, \
+		 mdev->caps.hca[MLX5_CAP_ADV_RDMA]->cur, cap)
 
 #define MLX5_CAP_FLOWTABLE_PORT_SELECTION(mdev, cap) \
 	MLX5_CAP_PORT_SELECTION(mdev, flow_table_properties_port_selection.cap)
 
-#define MLX5_CAP_FLOWTABLE_PORT_SELECTION_MAX(mdev, cap) \
-	MLX5_CAP_PORT_SELECTION_MAX(mdev, flow_table_properties_port_selection.cap)
+#define MLX5_CAP_PORT_SELECTION_FT_FIELD_SUPPORT_2(mdev, cap) \
+	MLX5_CAP_PORT_SELECTION(mdev, ft_field_support_2_port_selection.cap)
 
 #define MLX5_CAP_ODP(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, cap)
 
+#define MLX5_CAP_ODP_SCHEME(mdev, cap)                                \
+	(MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur,         \
+		  mem_page_fault) ?                                   \
+		 MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
+			  memory_page_fault_scheme_cap.cap) :         \
+		 MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->cur, \
+			  transport_page_fault_scheme_cap.cap))
+
 #define MLX5_CAP_ODP_MAX(mdev, cap)\
 	MLX5_GET(odp_cap, mdev->caps.hca[MLX5_CAP_ODP]->max, cap)
 
-#define MLX5_CAP_VECTOR_CALC(mdev, cap) \
-	MLX5_GET(vector_calc_cap, \
-		 mdev->caps.hca[MLX5_CAP_VECTOR_CALC]->cur, cap)
-
 #define MLX5_CAP_QOS(mdev, cap)\
 	MLX5_GET(qos_cap, mdev->caps.hca[MLX5_CAP_QOS]->cur, cap)
 
@@ -1435,14 +1433,14 @@ enum mlx5_qcam_feature_groups {
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_FIRST_128], \
 		 mng_access_reg_cap_mask.access_regs.reg)
 
-#define MLX5_CAP_MCAM_REG1(mdev, reg) \
-	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9080_0x90FF], \
-		 mng_access_reg_cap_mask.access_regs1.reg)
-
 #define MLX5_CAP_MCAM_REG2(mdev, reg) \
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9100_0x917F], \
 		 mng_access_reg_cap_mask.access_regs2.reg)
 
+#define MLX5_CAP_MCAM_REG3(mdev, reg) \
+	MLX5_GET(mcam_reg, (mdev)->caps.mcam[MLX5_MCAM_REGS_0x9180_0x91FF], \
+		 mng_access_reg_cap_mask.access_regs3.reg)
+
 #define MLX5_CAP_MCAM_FEATURE(mdev, fld) \
 	MLX5_GET(mcam_reg, (mdev)->caps.mcam, mng_feature_cap_mask.enhanced_features.fld)
 
@@ -1484,12 +1482,15 @@ enum mlx5_qcam_feature_groups {
 #define MLX5_CAP_CRYPTO(mdev, cap)\
 	MLX5_GET(crypto_cap, (mdev)->caps.hca[MLX5_CAP_CRYPTO]->cur, cap)
 
-#define MLX5_CAP_DEV_SHAMPO(mdev, cap)\
-	MLX5_GET(shampo_cap, mdev->caps.hca_cur[MLX5_CAP_DEV_SHAMPO], cap)
-
 #define MLX5_CAP_MACSEC(mdev, cap)\
 	MLX5_GET(macsec_cap, (mdev)->caps.hca[MLX5_CAP_MACSEC]->cur, cap)
 
+#define MLX5_CAP_SHAMPO(mdev, cap) \
+	MLX5_GET(shampo_cap, mdev->caps.hca[MLX5_CAP_SHAMPO]->cur, cap)
+
+#define MLX5_CAP_PSP(mdev, cap)\
+	MLX5_GET(psp_cap, (mdev)->caps.hca[MLX5_CAP_PSP]->cur, cap)
+
 enum {
 	MLX5_CMD_STAT_OK			= 0x0,
 	MLX5_CMD_STAT_INT_ERR			= 0x1,
@@ -1498,6 +1499,7 @@ enum {
 	MLX5_CMD_STAT_BAD_SYS_STATE_ERR		= 0x4,
 	MLX5_CMD_STAT_BAD_RES_ERR		= 0x5,
 	MLX5_CMD_STAT_RES_BUSY			= 0x6,
+	MLX5_CMD_STAT_NOT_READY			= 0x7,
 	MLX5_CMD_STAT_LIM_ERR			= 0x8,
 	MLX5_CMD_STAT_BAD_RES_STATE_ERR		= 0x9,
 	MLX5_CMD_STAT_IX_ERR			= 0xa,
@@ -1520,7 +1522,10 @@ enum {
 	MLX5_PHYSICAL_LAYER_COUNTERS_GROUP    = 0x12,
 	MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP = 0x13,
 	MLX5_PHYSICAL_LAYER_STATISTICAL_GROUP = 0x16,
+	MLX5_PHYSICAL_LAYER_RECOVERY_GROUP    = 0x1a,
 	MLX5_INFINIBAND_PORT_COUNTERS_GROUP   = 0x20,
+	MLX5_INFINIBAND_EXTENDED_PORT_COUNTERS_GROUP = 0x21,
+	MLX5_RS_FEC_HISTOGRAM_GROUP = 0x23,
 };
 
 enum {
@@ -1534,8 +1539,8 @@ static inline u16 mlx5_to_sw_pkey_sz(int pkey_sz)
 	return MLX5_MIN_PKEY_TABLE_SIZE << pkey_sz;
 }
 
-#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 2
-#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 1
+#define MLX5_RDMA_RX_NUM_COUNTERS_PRIOS 6
+#define MLX5_RDMA_TX_NUM_COUNTERS_PRIOS 4
 #define MLX5_BY_PASS_NUM_REGULAR_PRIOS 16
 #define MLX5_BY_PASS_NUM_DONT_TRAP_PRIOS 16
 #define MLX5_BY_PASS_NUM_MULTICAST_PRIOS 1
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index a4c4f737f9c1..1c54aa6f74fb 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -36,6 +36,7 @@
 #include <linux/kernel.h>
 #include <linux/completion.h>
 #include <linux/pci.h>
+#include <linux/pci-tph.h>
 #include <linux/irq.h>
 #include <linux/spinlock_types.h>
 #include <linux/semaphore.h>
@@ -45,7 +46,6 @@
 #include <linux/workqueue.h>
 #include <linux/mempool.h>
 #include <linux/interrupt.h>
-#include <linux/idr.h>
 #include <linux/notifier.h>
 #include <linux/refcount.h>
 #include <linux/auxiliary_bus.h>
@@ -55,7 +55,6 @@
 #include <linux/mlx5/doorbell.h>
 #include <linux/mlx5/eq.h>
 #include <linux/timecounter.h>
-#include <linux/ptp_clock_kernel.h>
 #include <net/devlink.h>
 
 #define MLX5_ADEV_NAME "mlx5_core"
@@ -85,7 +84,7 @@ enum mlx5_sqp_t {
 };
 
 enum {
-	MLX5_MAX_PORTS	= 4,
+	MLX5_MAX_PORTS	= 8,
 };
 
 enum {
@@ -131,11 +130,14 @@ enum {
 	MLX5_REG_PDDR		 = 0x5031,
 	MLX5_REG_PMLP		 = 0x5002,
 	MLX5_REG_PPLM		 = 0x5023,
+	MLX5_REG_PPHCR		 = 0x503E,
 	MLX5_REG_PCAM		 = 0x507f,
 	MLX5_REG_NODE_DESC	 = 0x6001,
 	MLX5_REG_HOST_ENDIANNESS = 0x7004,
+	MLX5_REG_MTCAP		 = 0x9009,
 	MLX5_REG_MTMP		 = 0x900A,
 	MLX5_REG_MCIA		 = 0x9014,
+	MLX5_REG_MNVDA		 = 0x9024,
 	MLX5_REG_MFRL		 = 0x9028,
 	MLX5_REG_MLCR		 = 0x902b,
 	MLX5_REG_MRTC		 = 0x902d,
@@ -149,15 +151,23 @@ enum {
 	MLX5_REG_MTPPSE		 = 0x9054,
 	MLX5_REG_MTUTC		 = 0x9055,
 	MLX5_REG_MPEGC		 = 0x9056,
+	MLX5_REG_MPIR		 = 0x9059,
 	MLX5_REG_MCQS		 = 0x9060,
 	MLX5_REG_MCQI		 = 0x9061,
 	MLX5_REG_MCC		 = 0x9062,
 	MLX5_REG_MCDA		 = 0x9063,
 	MLX5_REG_MCAM		 = 0x907f,
+	MLX5_REG_MSECQ		 = 0x9155,
+	MLX5_REG_MSEES		 = 0x9156,
 	MLX5_REG_MIRC		 = 0x9162,
+	MLX5_REG_MTPTM		 = 0x9180,
+	MLX5_REG_MTCTR		 = 0x9181,
+	MLX5_REG_MRTCQ		 = 0x9182,
 	MLX5_REG_SBCAM		 = 0xB01F,
 	MLX5_REG_RESOURCE_DUMP   = 0xC000,
+	MLX5_REG_NIC_CAP	 = 0xC00D,
 	MLX5_REG_DTOR            = 0xC00E,
+	MLX5_REG_VHCA_ICM_CTRL	 = 0xC010,
 };
 
 enum mlx5_qpts_trust_state {
@@ -287,18 +297,25 @@ struct mlx5_cmd_stats {
 struct mlx5_cmd {
 	struct mlx5_nb    nb;
 
+	/* members which needs to be queried or reinitialized each reload */
+	struct {
+		u16		cmdif_rev;
+		u8		log_sz;
+		u8		log_stride;
+		int		max_reg_cmds;
+		unsigned long	bitmask;
+		struct semaphore sem;
+		struct semaphore pages_sem;
+		struct semaphore throttle_sem;
+		struct semaphore unprivileged_sem;
+		struct xarray	privileged_uids;
+	} vars;
 	enum mlx5_cmdif_state	state;
 	void	       *cmd_alloc_buf;
 	dma_addr_t	alloc_dma;
 	int		alloc_size;
 	void	       *cmd_buf;
 	dma_addr_t	dma;
-	u16		cmdif_rev;
-	u8		log_sz;
-	u8		log_stride;
-	int		max_reg_cmds;
-	int		events;
-	u32 __iomem    *vector;
 
 	/* protect command queue allocations
 	 */
@@ -308,12 +325,8 @@ struct mlx5_cmd {
 	 */
 	spinlock_t	token_lock;
 	u8		token;
-	unsigned long	bitmask;
 	char		wq_name[MLX5_CMD_WQ_MAX_NAME];
 	struct workqueue_struct *wq;
-	struct semaphore sem;
-	struct semaphore pages_sem;
-	struct semaphore throttle_sem;
 	int	mode;
 	u16     allowed_opcode;
 	struct mlx5_cmd_work_ent *ent_arr[MLX5_MAX_COMMANDS];
@@ -321,7 +334,7 @@ struct mlx5_cmd {
 	struct mlx5_cmd_debug dbg;
 	struct cmd_msg_cache cache[MLX5_NUM_COMMAND_CACHES];
 	int checksum_disabled;
-	struct mlx5_cmd_stats stats[MLX5_CMD_OP_MAX];
+	struct xarray stats;
 };
 
 struct mlx5_cmd_mailbox {
@@ -382,13 +395,13 @@ enum mlx5_res_type {
 	MLX5_RES_SRQ	= 3,
 	MLX5_RES_XSRQ	= 4,
 	MLX5_RES_XRQ	= 5,
-	MLX5_RES_DCT	= MLX5_EVENT_QUEUE_TYPE_DCT,
 };
 
 struct mlx5_core_rsc_common {
 	enum mlx5_res_type	res;
 	refcount_t		refcount;
 	struct completion	free;
+	bool			invalid;
 };
 
 struct mlx5_uars_page {
@@ -421,7 +434,6 @@ struct mlx5_sq_bfreg {
 	struct mlx5_uars_page  *up;
 	bool			wc;
 	u32			index;
-	unsigned int		offset;
 };
 
 struct mlx5_core_health {
@@ -443,15 +455,6 @@ struct mlx5_core_health {
 	struct delayed_work		update_fw_log_ts_work;
 };
 
-struct mlx5_qp_table {
-	struct notifier_block   nb;
-
-	/* protect radix tree
-	 */
-	spinlock_t		lock;
-	struct radix_tree_root	tree;
-};
-
 enum {
 	MLX5_PF_NOTIFY_DISABLE_VF,
 	MLX5_PF_NOTIFY_ENABLE_VF,
@@ -474,47 +477,17 @@ struct mlx5_core_sriov {
 	struct mlx5_vf_context	*vfs_ctx;
 	int			num_vfs;
 	u16			max_vfs;
-};
-
-struct mlx5_fc_pool {
-	struct mlx5_core_dev *dev;
-	struct mutex pool_lock; /* protects pool lists */
-	struct list_head fully_used;
-	struct list_head partially_used;
-	struct list_head unused;
-	int available_fcs;
-	int used_fcs;
-	int threshold;
-};
-
-struct mlx5_fc_stats {
-	spinlock_t counters_idr_lock; /* protects counters_idr */
-	struct idr counters_idr;
-	struct list_head counters;
-	struct llist_head addlist;
-	struct llist_head dellist;
-
-	struct workqueue_struct *wq;
-	struct delayed_work work;
-	unsigned long next_query;
-	unsigned long sampling_interval; /* jiffies */
-	u32 *bulk_query_out;
-	int bulk_query_len;
-	size_t num_counters;
-	bool bulk_query_alloc_failed;
-	unsigned long next_bulk_query_alloc;
-	struct mlx5_fc_pool fc_pool;
+	u16			max_ec_vfs;
 };
 
 struct mlx5_events;
 struct mlx5_mpfs;
 struct mlx5_eswitch;
 struct mlx5_lag;
-struct mlx5_devcom;
+struct mlx5_devcom_dev;
 struct mlx5_fw_reset;
 struct mlx5_eq_table;
 struct mlx5_irq_table;
-struct mlx5_vhca_state_notifier;
 struct mlx5_sf_dev_table;
 struct mlx5_sf_hw_table;
 struct mlx5_sf_table;
@@ -557,6 +530,7 @@ enum {
 	 * creation/deletion on drivers rescan. Unset during device attach.
 	 */
 	MLX5_PRIV_FLAGS_DETACH = 1 << 2,
+	MLX5_PRIV_FLAGS_SWITCH_LEGACY = 1 << 3,
 };
 
 struct mlx5_adev {
@@ -580,6 +554,7 @@ enum mlx5_func_type {
 	MLX5_VF,
 	MLX5_SF,
 	MLX5_HOST_PF,
+	MLX5_EC_VF,
 	MLX5_FUNC_TYPE_NUM,
 };
 
@@ -619,31 +594,41 @@ struct mlx5_priv {
 	int			adev_idx;
 	int			sw_vhca_id;
 	struct mlx5_events      *events;
+	struct mlx5_vhca_events *vhca_events;
 
 	struct mlx5_flow_steering *steering;
 	struct mlx5_mpfs        *mpfs;
+	struct blocking_notifier_head esw_n_head;
 	struct mlx5_eswitch     *eswitch;
 	struct mlx5_core_sriov	sriov;
 	struct mlx5_lag		*lag;
 	u32			flags;
-	struct mlx5_devcom	*devcom;
+	struct mlx5_devcom_dev	*devc;
+	struct mlx5_devcom_comp_dev *hca_devcom_comp;
 	struct mlx5_fw_reset	*fw_reset;
 	struct mlx5_core_roce	roce;
-	struct mlx5_fc_stats		fc_stats;
+	struct mlx5_fc_stats		*fc_stats;
 	struct mlx5_rl_table            rl_table;
 	struct mlx5_ft_pool		*ft_pool;
 
 	struct mlx5_bfreg_data		bfregs;
-	struct mlx5_uars_page	       *uar;
+	struct mlx5_sq_bfreg bfreg;
 #ifdef CONFIG_MLX5_SF
-	struct mlx5_vhca_state_notifier *vhca_state_notifier;
+	struct mlx5_nb vhca_state_nb;
+	struct blocking_notifier_head vhca_state_n_head;
+	struct notifier_block sf_dev_nb;
 	struct mlx5_sf_dev_table *sf_dev_table;
 	struct mlx5_core_dev *parent_mdev;
 #endif
 #ifdef CONFIG_MLX5_SF_MANAGER
+	struct notifier_block sf_hw_table_vhca_nb;
 	struct mlx5_sf_hw_table *sf_hw_table;
+	struct notifier_block sf_table_esw_nb;
+	struct notifier_block sf_table_vhca_nb;
+	struct notifier_block sf_table_mdev_nb;
 	struct mlx5_sf_table *sf_table;
 #endif
+	struct blocking_notifier_head lag_nh;
 };
 
 enum mlx5_device_state {
@@ -679,9 +664,14 @@ struct mlx5e_resources {
 		u32                        pdn;
 		struct mlx5_td             td;
 		u32			   mkey;
-		struct mlx5_sq_bfreg       bfreg;
+		struct mlx5_sq_bfreg      *bfregs;
+		unsigned int               num_bfregs;
+#define MLX5_MAX_NUM_TC 8
+		u32                        tisn[MLX5_MAX_PORTS][MLX5_MAX_NUM_TC];
+		bool			   tisn_valid;
 	} hw_objs;
 	struct net_device *uplink_netdev;
+	netdevice_tracker tracker;
 	struct mutex uplink_netdev_lock;
 	struct mlx5_crypto_dek_priv *dek_priv;
 };
@@ -690,6 +680,7 @@ enum mlx5_sw_icm_type {
 	MLX5_SW_ICM_TYPE_STEERING,
 	MLX5_SW_ICM_TYPE_HEADER_MODIFY,
 	MLX5_SW_ICM_TYPE_HEADER_MODIFY_PATTERN,
+	MLX5_SW_ICM_TYPE_SW_ENCAP,
 };
 
 #define MLX5_MAX_RESERVED_GIDS 8
@@ -700,40 +691,14 @@ struct mlx5_rsvd_gids {
 	struct ida ida;
 };
 
-#define MAX_PIN_NUM	8
-struct mlx5_pps {
-	u8                         pin_caps[MAX_PIN_NUM];
-	struct work_struct         out_work;
-	u64                        start[MAX_PIN_NUM];
-	u8                         enabled;
-	u64                        min_npps_period;
-	u64                        min_out_pulse_duration_ns;
-};
-
-struct mlx5_timer {
-	struct cyclecounter        cycles;
-	struct timecounter         tc;
-	u32                        nominal_c_mult;
-	unsigned long              overflow_period;
-	struct delayed_work        overflow_work;
-};
-
-struct mlx5_clock {
-	struct mlx5_nb             pps_nb;
-	seqlock_t                  lock;
-	struct hwtstamp_config     hwtstamp_config;
-	struct ptp_clock          *ptp;
-	struct ptp_clock_info      ptp_info;
-	struct mlx5_pps            pps_info;
-	struct mlx5_timer          timer;
-};
-
+struct mlx5_clock;
+struct mlx5_clock_dev_state;
 struct mlx5_dm;
 struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 struct mlx5_geneve;
 struct mlx5_hv_vhca;
-struct mlx5_thermal;
+struct mlx5_st;
 
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
 #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
@@ -764,6 +729,12 @@ struct mlx5_hca_cap {
 	u32 max[MLX5_UN_SZ_DW(hca_cap_union)];
 };
 
+enum mlx5_wc_state {
+	MLX5_WC_STATE_UNINITIALIZED,
+	MLX5_WC_STATE_UNSUPPORTED,
+	MLX5_WC_STATE_SUPPORTED,
+};
+
 struct mlx5_core_dev {
 	struct device *device;
 	enum mlx5_coredev_type coredev_type;
@@ -797,6 +768,7 @@ struct mlx5_core_dev {
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
+	struct mlx5_st          *st;
 	struct mlx5_vxlan       *vxlan;
 	struct mlx5_geneve      *geneve;
 	struct {
@@ -806,13 +778,26 @@ struct mlx5_core_dev {
 #ifdef CONFIG_MLX5_FPGA
 	struct mlx5_fpga_device *fpga;
 #endif
-	struct mlx5_clock        clock;
+	struct mlx5_clock       *clock;
+	struct mlx5_clock_dev_state *clock_state;
 	struct mlx5_ib_clock_info  *clock_info;
 	struct mlx5_fw_tracer   *tracer;
 	struct mlx5_rsc_dump    *rsc_dump;
 	u32                      vsc_addr;
 	struct mlx5_hv_vhca	*hv_vhca;
-	struct mlx5_thermal	*thermal;
+	struct mlx5_hwmon	*hwmon;
+	u64			num_block_tc;
+	u64			num_block_ipsec;
+#ifdef CONFIG_MLX5_MACSEC
+	struct mlx5_macsec_fs *macsec_fs;
+	/* MACsec notifier chain to sync MACsec core and IB database */
+	struct blocking_notifier_head macsec_nh;
+#endif
+	u64 num_ipsec_offloads;
+	struct mlx5_sd          *sd;
+	enum mlx5_wc_state wc_state;
+	/* sync write combining state */
+	struct mutex wc_state_lock;
 };
 
 struct mlx5_db {
@@ -825,6 +810,8 @@ struct mlx5_db {
 	int			index;
 };
 
+#define MLX5_DEFAULT_NUM_DOORBELLS 8
+
 enum {
 	MLX5_COMP_EQ_SIZE = 1024,
 };
@@ -838,6 +825,7 @@ typedef void (*mlx5_cmd_cbk_t)(int status, void *context);
 
 enum {
 	MLX5_CMD_ENT_STATE_PENDING_COMP,
+	MLX5_CMD_ENT_STATE_TIMEDOUT,
 };
 
 struct mlx5_cmd_work_ent {
@@ -851,6 +839,7 @@ struct mlx5_cmd_work_ent {
 	void		       *context;
 	int			idx;
 	struct completion	handling;
+	struct completion	slotted;
 	struct completion	done;
 	struct mlx5_cmd        *cmd;
 	struct work_struct	work;
@@ -896,6 +885,7 @@ struct mlx5_hca_vport_context {
 	u16			qkey_violation_counter;
 	u16			pkey_violation_counter;
 	bool			grh_required;
+	u8			num_plane;
 };
 
 #define STRUCT_FIELD(header, field) \
@@ -992,6 +982,8 @@ struct mlx5_async_work {
 	mlx5_async_cbk_t user_callback;
 	u16 opcode; /* cmd opcode */
 	u16 op_mod; /* cmd op_mod */
+	u8 throttle_locked:1;
+	u8 unpriv_locked:1;
 	void *out; /* pointer to the cmd output buffer */
 };
 
@@ -1022,11 +1014,14 @@ int mlx5_cmd_exec(struct mlx5_core_dev *dev, void *in, int in_size, void *out,
 int mlx5_cmd_exec_polling(struct mlx5_core_dev *dev, void *in, int in_size,
 			  void *out, int out_size);
 bool mlx5_cmd_is_down(struct mlx5_core_dev *dev);
+int mlx5_cmd_add_privileged_uid(struct mlx5_core_dev *dev, u16 uid);
+void mlx5_cmd_remove_privileged_uid(struct mlx5_core_dev *dev, u16 uid);
 
 void mlx5_core_uplink_netdev_set(struct mlx5_core_dev *mdev, struct net_device *netdev);
 void mlx5_core_uplink_netdev_event_replay(struct mlx5_core_dev *mdev);
 
-int mlx5_core_get_caps(struct mlx5_core_dev *dev, enum mlx5_cap_type cap_type);
+void mlx5_core_mp_event_replay(struct mlx5_core_dev *dev, u32 event, void *data);
+
 void mlx5_health_cleanup(struct mlx5_core_dev *dev);
 int mlx5_health_init(struct mlx5_core_dev *dev);
 void mlx5_start_health_poll(struct mlx5_core_dev *dev);
@@ -1037,10 +1032,6 @@ void mlx5_trigger_health_work(struct mlx5_core_dev *dev);
 int mlx5_frag_buf_alloc_node(struct mlx5_core_dev *dev, int size,
 			     struct mlx5_frag_buf *buf, int node);
 void mlx5_frag_buf_free(struct mlx5_core_dev *dev, struct mlx5_frag_buf *buf);
-struct mlx5_cmd_mailbox *mlx5_alloc_cmd_mailbox_chain(struct mlx5_core_dev *dev,
-						      gfp_t flags, int npages);
-void mlx5_free_cmd_mailbox_chain(struct mlx5_core_dev *dev,
-				 struct mlx5_cmd_mailbox *head);
 int mlx5_core_create_mkey(struct mlx5_core_dev *dev, u32 *mkey, u32 *in,
 			  int inlen);
 int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, u32 mkey);
@@ -1054,8 +1045,6 @@ void mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
 void mlx5_pages_debugfs_init(struct mlx5_core_dev *dev);
 void mlx5_pages_debugfs_cleanup(struct mlx5_core_dev *dev);
-void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
-				 s32 npages, bool ec_function);
 int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
 int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
 void mlx5_register_debugfs(void);
@@ -1063,7 +1052,7 @@ void mlx5_unregister_debugfs(void);
 
 void mlx5_fill_page_frag_array_perm(struct mlx5_frag_buf *buf, __be64 *pas, u8 perm);
 void mlx5_fill_page_frag_array(struct mlx5_frag_buf *frag_buf, __be64 *pas);
-int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn);
+int mlx5_comp_eqn_get(struct mlx5_core_dev *dev, u16 vecidx, int *eqn);
 int mlx5_core_attach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 int mlx5_core_detach_mcg(struct mlx5_core_dev *dev, union ib_gid *mgid, u32 qpn);
 
@@ -1093,9 +1082,8 @@ void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev);
 int mlx5_core_create_psv(struct mlx5_core_dev *dev, u32 pdn,
 			 int npsvs, u32 *sig_index);
 int mlx5_core_destroy_psv(struct mlx5_core_dev *dev, int psv_num);
+__be32 mlx5_core_get_terminate_scatter_list_mkey(struct mlx5_core_dev *dev);
 void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common);
-int mlx5_query_odp_caps(struct mlx5_core_dev *dev,
-			struct mlx5_odp_caps *odp_caps);
 
 int mlx5_init_rl_table(struct mlx5_core_dev *dev);
 void mlx5_cleanup_rl_table(struct mlx5_core_dev *dev);
@@ -1112,9 +1100,8 @@ int mlx5_alloc_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg,
 		     bool map_wc, bool fast_path);
 void mlx5_free_bfreg(struct mlx5_core_dev *mdev, struct mlx5_sq_bfreg *bfreg);
 
-unsigned int mlx5_comp_vectors_count(struct mlx5_core_dev *dev);
-struct cpumask *
-mlx5_comp_irq_get_affinity_mask(struct mlx5_core_dev *dev, int vector);
+unsigned int mlx5_comp_vectors_max(struct mlx5_core_dev *dev);
+int mlx5_comp_vector_get_cpu(struct mlx5_core_dev *dev, int vector);
 unsigned int mlx5_core_reserved_gids_count(struct mlx5_core_dev *dev);
 int mlx5_core_roce_gid_set(struct mlx5_core_dev *dev, unsigned int index,
 			   u8 roce_version, u8 roce_l3_type, const u8 *gid,
@@ -1166,14 +1153,19 @@ bool mlx5_lag_mode_is_hash(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_master(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_shared_fdb(struct mlx5_core_dev *dev);
 bool mlx5_lag_is_mpesw(struct mlx5_core_dev *dev);
-struct net_device *mlx5_lag_get_roce_netdev(struct mlx5_core_dev *dev);
 u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
 			   struct net_device *slave);
 int mlx5_lag_query_cong_counters(struct mlx5_core_dev *dev,
 				 u64 *values,
 				 int num_counters,
 				 size_t *offsets);
-struct mlx5_core_dev *mlx5_lag_get_peer_mdev(struct mlx5_core_dev *dev);
+struct mlx5_core_dev *mlx5_lag_get_next_peer_mdev(struct mlx5_core_dev *dev, int *i);
+
+#define mlx5_lag_for_each_peer_mdev(dev, peer, i)				\
+	for (i = 0, peer = mlx5_lag_get_next_peer_mdev(dev, &i);		\
+	     peer;								\
+	     peer = mlx5_lag_get_next_peer_mdev(dev, &i))
+
 u8 mlx5_lag_get_num_ports(struct mlx5_core_dev *dev);
 struct mlx5_uars_page *mlx5_get_uars_page(struct mlx5_core_dev *mdev);
 void mlx5_put_uars_page(struct mlx5_core_dev *mdev, struct mlx5_uars_page *up);
@@ -1183,6 +1175,23 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id);
 
+#ifdef CONFIG_PCIE_TPH
+int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *st_index);
+int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index);
+#else
+static inline int mlx5_st_alloc_index(struct mlx5_core_dev *dev,
+				      enum tph_mem_type mem_type,
+				      unsigned int cpu_uid, u16 *st_index)
+{
+	return -EOPNOTSUPP;
+}
+static inline int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
 void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
 
@@ -1192,12 +1201,6 @@ int mlx5_sriov_blocking_notifier_register(struct mlx5_core_dev *mdev,
 void mlx5_sriov_blocking_notifier_unregister(struct mlx5_core_dev *mdev,
 					     int vf_id,
 					     struct notifier_block *nb);
-#ifdef CONFIG_MLX5_CORE_IPOIB
-struct net_device *mlx5_rdma_netdev_alloc(struct mlx5_core_dev *mdev,
-					  struct ib_device *ibdev,
-					  const char *name,
-					  void (*setup)(struct net_device *));
-#endif /* CONFIG_MLX5_CORE_IPOIB */
 int mlx5_rdma_rn_get_params(struct mlx5_core_dev *mdev,
 			    struct ib_device *device,
 			    struct rdma_netdev_alloc_params *params);
@@ -1216,6 +1219,12 @@ static inline bool mlx5_core_is_vf(const struct mlx5_core_dev *dev)
 	return dev->coredev_type == MLX5_COREDEV_VF;
 }
 
+static inline bool mlx5_core_same_coredev_type(const struct mlx5_core_dev *dev1,
+					       const struct mlx5_core_dev *dev2)
+{
+	return dev1->coredev_type == dev2->coredev_type;
+}
+
 static inline bool mlx5_core_is_ecpf(const struct mlx5_core_dev *dev)
 {
 	return dev->caps.embedded_cpu;
@@ -1237,6 +1246,23 @@ static inline u16 mlx5_core_max_vfs(const struct mlx5_core_dev *dev)
 	return dev->priv.sriov.max_vfs;
 }
 
+static inline int mlx5_lag_is_lacp_owner(struct mlx5_core_dev *dev)
+{
+	/* LACP owner conditions:
+	 * 1) Function is physical.
+	 * 2) LAG is supported by FW.
+	 * 3) LAG is managed by driver (currently the only option).
+	 */
+	return  MLX5_CAP_GEN(dev, vport_group_manager) &&
+		   (MLX5_CAP_GEN(dev, num_lag_ports) > 1) &&
+		    MLX5_CAP_GEN(dev, lag_master);
+}
+
+static inline u16 mlx5_core_max_ec_vfs(const struct mlx5_core_dev *dev)
+{
+	return dev->priv.sriov.max_ec_vfs;
+}
+
 static inline int mlx5_get_gid_table_len(u16 param)
 {
 	if (param > 4) {
@@ -1304,14 +1330,63 @@ static inline bool mlx5_get_roce_state(struct mlx5_core_dev *dev)
 	return mlx5_is_roce_on(dev);
 }
 
+#ifdef CONFIG_MLX5_MACSEC
+static inline bool mlx5e_is_macsec_device(const struct mlx5_core_dev *mdev)
+{
+	if (!(MLX5_CAP_GEN_64(mdev, general_obj_types) &
+	    MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD))
+		return false;
+
+	if (!MLX5_CAP_GEN(mdev, log_max_dek))
+		return false;
+
+	if (!MLX5_CAP_MACSEC(mdev, log_max_macsec_offload))
+		return false;
+
+	if (!MLX5_CAP_FLOWTABLE_NIC_RX(mdev, macsec_decrypt) ||
+	    !MLX5_CAP_FLOWTABLE_NIC_RX(mdev, reformat_remove_macsec))
+		return false;
+
+	if (!MLX5_CAP_FLOWTABLE_NIC_TX(mdev, macsec_encrypt) ||
+	    !MLX5_CAP_FLOWTABLE_NIC_TX(mdev, reformat_add_macsec))
+		return false;
+
+	if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_encrypt) &&
+	    !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_encrypt))
+		return false;
+
+	if (!MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_128_decrypt) &&
+	    !MLX5_CAP_MACSEC(mdev, macsec_crypto_esp_aes_gcm_256_decrypt))
+		return false;
+
+	return true;
+}
+
+#define NIC_RDMA_BOTH_DIRS_CAPS (MLX5_FT_NIC_RX_2_NIC_RX_RDMA | MLX5_FT_NIC_TX_RDMA_2_NIC_TX)
+
+static inline bool mlx5_is_macsec_roce_supported(struct mlx5_core_dev *mdev)
+{
+	if (((MLX5_CAP_GEN_2(mdev, flow_table_type_2_type) &
+	     NIC_RDMA_BOTH_DIRS_CAPS) != NIC_RDMA_BOTH_DIRS_CAPS) ||
+	     !MLX5_CAP_FLOWTABLE_RDMA_TX(mdev, max_modify_header_actions) ||
+	     !mlx5e_is_macsec_device(mdev) || !mdev->macsec_fs)
+		return false;
+
+	return true;
+}
+#endif
+
 enum {
 	MLX5_OCTWORD = 16,
 };
 
-struct msi_map mlx5_msix_alloc(struct mlx5_core_dev *dev,
-			       irqreturn_t (*handler)(int, void *),
-			       const struct irq_affinity_desc *affdesc,
-			       const char *name);
-void mlx5_msix_free(struct mlx5_core_dev *dev, struct msi_map map);
+bool mlx5_wc_support_get(struct mlx5_core_dev *mdev);
+
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
+
+#define MLX5_SW_IMAGE_GUID_MAX_BYTES 9
 
 #endif /* MLX5_DRIVER_H */
diff --git a/include/linux/mlx5/eswitch.h b/include/linux/mlx5/eswitch.h
index e2701ed0200e..67256e776566 100644
--- a/include/linux/mlx5/eswitch.h
+++ b/include/linux/mlx5/eswitch.h
@@ -7,6 +7,7 @@
 #define _MLX5_ESWITCH_
 
 #include <linux/mlx5/driver.h>
+#include <linux/mlx5/vport.h>
 #include <net/devlink.h>
 
 #define MLX5_ESWITCH_MANAGER(mdev) MLX5_CAP_GEN(mdev, eswitch_manager)
@@ -144,6 +145,11 @@ u32 mlx5_eswitch_get_vport_metadata_for_set(struct mlx5_eswitch *esw,
 	GENMASK(31 - ESW_TUN_ID_BITS - ESW_RESERVED_BITS, \
 		ESW_TUN_OPTS_OFFSET + 1)
 
+/* reuse tun_opts for the mapped ipsec obj id when tun_id is 0 (invalid) */
+#define ESW_IPSEC_RX_MAPPED_ID_MASK GENMASK(ESW_TUN_OPTS_BITS - 1, 0)
+#define ESW_IPSEC_RX_MAPPED_ID_MATCH_MASK \
+	GENMASK(31 - ESW_RESERVED_BITS, ESW_ZONE_ID_BITS)
+
 u8 mlx5_eswitch_mode(const struct mlx5_core_dev *dev);
 u16 mlx5_eswitch_get_total_vports(const struct mlx5_core_dev *dev);
 struct mlx5_core_dev *mlx5_eswitch_get_core_dev(struct mlx5_eswitch *esw);
@@ -207,4 +213,11 @@ static inline bool is_mdev_switchdev_mode(struct mlx5_core_dev *dev)
 	return mlx5_eswitch_mode(dev) == MLX5_ESWITCH_OFFLOADS;
 }
 
+/* The returned number is valid only when the dev is eswitch manager. */
+static inline u16 mlx5_eswitch_manager_vport(struct mlx5_core_dev *dev)
+{
+	return mlx5_core_is_ecpf_esw_manager(dev) ?
+		MLX5_VPORT_ECPF : MLX5_VPORT_PF;
+}
+
 #endif
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 2cb404c7ea13..9cadb1d5e6df 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,6 +40,9 @@
 
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
+#define MLX5_RDMA_TRANSPORT_BYPASS_PRIO 16
+#define MLX5_FS_MAX_POOL_SIZE BIT(30)
+
 enum mlx5_flow_destination_type {
 	MLX5_FLOW_DESTINATION_TYPE_NONE,
 	MLX5_FLOW_DESTINATION_TYPE_VPORT,
@@ -67,6 +70,8 @@ enum {
 	MLX5_FLOW_TABLE_TERMINATION = BIT(2),
 	MLX5_FLOW_TABLE_UNMANAGED = BIT(3),
 	MLX5_FLOW_TABLE_OTHER_VPORT = BIT(4),
+	MLX5_FLOW_TABLE_UPLINK_VPORT = BIT(5),
+	MLX5_FLOW_TABLE_OTHER_ESWITCH = BIT(6),
 };
 
 #define LEFTOVERS_RULE_NUM	 2
@@ -105,18 +110,43 @@ enum mlx5_flow_namespace_type {
 	MLX5_FLOW_NAMESPACE_RDMA_TX_COUNTERS,
 	MLX5_FLOW_NAMESPACE_RDMA_RX_IPSEC,
 	MLX5_FLOW_NAMESPACE_RDMA_TX_IPSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_RX_MACSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_TX_MACSEC,
+	MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_RX,
+	MLX5_FLOW_NAMESPACE_RDMA_TRANSPORT_TX,
 };
 
 enum {
+	FDB_DROP_ROOT,
 	FDB_BYPASS_PATH,
+	FDB_CRYPTO_INGRESS,
 	FDB_TC_OFFLOAD,
 	FDB_FT_OFFLOAD,
 	FDB_TC_MISS,
 	FDB_BR_OFFLOAD,
 	FDB_SLOW_PATH,
+	FDB_CRYPTO_EGRESS,
 	FDB_PER_VPORT,
 };
 
+enum fs_flow_table_type {
+	FS_FT_NIC_RX          = 0x0,
+	FS_FT_NIC_TX          = 0x1,
+	FS_FT_ESW_EGRESS_ACL  = 0x2,
+	FS_FT_ESW_INGRESS_ACL = 0x3,
+	FS_FT_FDB             = 0X4,
+	FS_FT_SNIFFER_RX	= 0X5,
+	FS_FT_SNIFFER_TX	= 0X6,
+	FS_FT_RDMA_RX		= 0X7,
+	FS_FT_RDMA_TX		= 0X8,
+	FS_FT_PORT_SEL		= 0X9,
+	FS_FT_FDB_RX		= 0xa,
+	FS_FT_FDB_TX		= 0xb,
+	FS_FT_RDMA_TRANSPORT_RX	= 0xd,
+	FS_FT_RDMA_TRANSPORT_TX	= 0xe,
+	FS_FT_MAX_TYPE = FS_FT_RDMA_TRANSPORT_TX,
+};
+
 struct mlx5_pkt_reformat;
 struct mlx5_modify_hdr;
 struct mlx5_flow_definer;
@@ -127,6 +157,7 @@ struct mlx5_flow_handle;
 
 enum {
 	FLOW_CONTEXT_HAS_TAG = BIT(0),
+	FLOW_CONTEXT_UPLINK_HAIRPIN_EN = BIT(1),
 };
 
 struct mlx5_flow_context {
@@ -157,7 +188,7 @@ struct mlx5_flow_destination {
 		u32			tir_num;
 		u32			ft_num;
 		struct mlx5_flow_table	*ft;
-		u32			counter_id;
+		struct mlx5_fc          *counter;
 		struct {
 			u16		num;
 			u16		vhca_id;
@@ -186,9 +217,9 @@ struct mlx5_flow_namespace *
 mlx5_get_flow_namespace(struct mlx5_core_dev *dev,
 			enum mlx5_flow_namespace_type type);
 struct mlx5_flow_namespace *
-mlx5_get_flow_vport_acl_namespace(struct mlx5_core_dev *dev,
-				  enum mlx5_flow_namespace_type type,
-				  int vport);
+mlx5_get_flow_vport_namespace(struct mlx5_core_dev *dev,
+			      enum mlx5_flow_namespace_type type,
+			      int vport_idx);
 
 struct mlx5_flow_table_attr {
 	int prio;
@@ -196,6 +227,8 @@ struct mlx5_flow_table_attr {
 	u32 level;
 	u32 flags;
 	u16 uid;
+	u16 vport;
+	u16 esw_owner_vhca_id;
 	struct mlx5_flow_table *next_ft;
 
 	struct {
@@ -232,6 +265,7 @@ void mlx5_destroy_flow_group(struct mlx5_flow_group *fg);
 
 struct mlx5_exe_aso {
 	u32 object_id;
+	int base_id;
 	u8 type;
 	u8 return_reg_id;
 	union {
@@ -292,10 +326,11 @@ int mlx5_modify_rule_destination(struct mlx5_flow_handle *handler,
 
 struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging);
 
-/* As mlx5_fc_create() but doesn't queue stats refresh thread. */
-struct mlx5_fc *mlx5_fc_create_ex(struct mlx5_core_dev *dev, bool aging);
-
 void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter);
+struct mlx5_fc *mlx5_fc_local_create(u32 counter_id, u32 offset, u32 bulk_size);
+void mlx5_fc_local_destroy(struct mlx5_fc *counter);
+void mlx5_fc_local_get(struct mlx5_fc *counter);
+void mlx5_fc_local_put(struct mlx5_fc *counter);
 u64 mlx5_fc_query_lastuse(struct mlx5_fc *counter);
 void mlx5_fc_query_cached(struct mlx5_fc *counter,
 			  u64 *bytes, u64 *packets, u64 *lastuse);
@@ -336,4 +371,11 @@ void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev,
 				  struct mlx5_pkt_reformat *reformat);
 
 u32 mlx5_flow_table_id(struct mlx5_flow_table *ft);
+
+struct mlx5_flow_root_namespace *
+mlx5_get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type);
+
+int mlx5_fs_set_root_dev(struct mlx5_core_dev *dev,
+			 struct mlx5_core_dev *new_dev,
+			 enum fs_flow_table_type table_type);
 #endif
diff --git a/include/linux/mlx5/macsec.h b/include/linux/mlx5/macsec.h
new file mode 100644
index 000000000000..f7ff4c2a95d0
--- /dev/null
+++ b/include/linux/mlx5/macsec.h
@@ -0,0 +1,32 @@
+/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */
+/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. */
+
+#ifndef MLX5_MACSEC_H
+#define MLX5_MACSEC_H
+
+#ifdef CONFIG_MLX5_MACSEC
+struct mlx5_macsec_event_data {
+	struct mlx5_macsec_fs *macsec_fs;
+	void *macdev;
+	u32 fs_id;
+	bool is_tx;
+};
+
+int mlx5_macsec_add_roce_rule(void *macdev, const struct sockaddr *addr, u16 gid_idx,
+			      struct list_head *tx_rules_list, struct list_head *rx_rules_list,
+			      struct mlx5_macsec_fs *macsec_fs);
+
+void mlx5_macsec_del_roce_rule(u16 gid_idx, struct mlx5_macsec_fs *macsec_fs,
+			       struct list_head *tx_rules_list, struct list_head *rx_rules_list);
+
+void mlx5_macsec_add_roce_sa_rules(u32 fs_id, const struct sockaddr *addr, u16 gid_idx,
+				   struct list_head *tx_rules_list,
+				   struct list_head *rx_rules_list,
+				   struct mlx5_macsec_fs *macsec_fs, bool is_tx);
+
+void mlx5_macsec_del_roce_sa_rules(u32 fs_id, struct mlx5_macsec_fs *macsec_fs,
+				   struct list_head *tx_rules_list,
+				   struct list_head *rx_rules_list, bool is_tx);
+
+#endif
+#endif /* MLX5_MACSEC_H */
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index b89778d0d326..e9dcd4bf355d 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -65,9 +65,11 @@ enum {
 
 enum {
 	MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE        = 0x0,
+	MLX5_SET_HCA_CAP_OP_MOD_ETHERNET_OFFLOADS     = 0x1,
 	MLX5_SET_HCA_CAP_OP_MOD_ODP                   = 0x2,
 	MLX5_SET_HCA_CAP_OP_MOD_ATOMIC                = 0x3,
 	MLX5_SET_HCA_CAP_OP_MOD_ROCE                  = 0x4,
+	MLX5_SET_HCA_CAP_OP_MOD_IPSEC                 = 0x15,
 	MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2       = 0x20,
 	MLX5_SET_HCA_CAP_OP_MOD_PORT_SELECTION        = 0x25,
 };
@@ -78,23 +80,15 @@ enum {
 
 enum {
 	MLX5_OBJ_TYPE_SW_ICM = 0x0008,
-	MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT  = 0x23,
-};
-
-enum {
-	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
-	MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
-	MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13),
-	MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT =
-		(1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT),
-	MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39),
-};
-
-enum {
 	MLX5_OBJ_TYPE_GENEVE_TLV_OPT = 0x000b,
 	MLX5_OBJ_TYPE_VIRTIO_NET_Q = 0x000d,
 	MLX5_OBJ_TYPE_VIRTIO_Q_COUNTERS = 0x001c,
 	MLX5_OBJ_TYPE_MATCH_DEFINER = 0x0018,
+	MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT  = 0x23,
+	MLX5_OBJ_TYPE_STC = 0x0040,
+	MLX5_OBJ_TYPE_RTC = 0x0041,
+	MLX5_OBJ_TYPE_STE = 0x0042,
+	MLX5_OBJ_TYPE_MODIFY_HDR_PATTERN = 0x0043,
 	MLX5_OBJ_TYPE_PAGE_TRACK = 0x46,
 	MLX5_OBJ_TYPE_MKEY = 0xff01,
 	MLX5_OBJ_TYPE_QP = 0xff02,
@@ -110,6 +104,16 @@ enum {
 	MLX5_OBJ_TYPE_RQT = 0xff0e,
 	MLX5_OBJ_TYPE_FLOW_COUNTER = 0xff0f,
 	MLX5_OBJ_TYPE_CQ = 0xff10,
+	MLX5_OBJ_TYPE_FT_ALIAS = 0xff15,
+};
+
+enum {
+	MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM = (1ULL << MLX5_OBJ_TYPE_SW_ICM),
+	MLX5_GENERAL_OBJ_TYPES_CAP_GENEVE_TLV_OPT = (1ULL << 11),
+	MLX5_GENERAL_OBJ_TYPES_CAP_VIRTIO_NET_Q = (1ULL << 13),
+	MLX5_GENERAL_OBJ_TYPES_CAP_HEADER_MODIFY_ARGUMENT =
+		(1ULL << MLX5_OBJ_TYPE_HEADER_MODIFY_ARGUMENT),
+	MLX5_GENERAL_OBJ_TYPES_CAP_MACSEC_OFFLOAD = (1ULL << 39),
 };
 
 enum {
@@ -185,6 +189,9 @@ enum {
 	MLX5_CMD_OP_QUERY_XRQ_ERROR_PARAMS        = 0x727,
 	MLX5_CMD_OP_RELEASE_XRQ_ERROR             = 0x729,
 	MLX5_CMD_OP_MODIFY_XRQ                    = 0x72a,
+	MLX5_CMD_OPCODE_QUERY_DELEGATED_VHCA      = 0x732,
+	MLX5_CMD_OPCODE_CREATE_ESW_VPORT          = 0x733,
+	MLX5_CMD_OPCODE_DESTROY_ESW_VPORT         = 0x734,
 	MLX5_CMD_OP_QUERY_ESW_FUNCTIONS           = 0x740,
 	MLX5_CMD_OP_QUERY_VPORT_STATE             = 0x750,
 	MLX5_CMD_OP_MODIFY_VPORT_STATE            = 0x751,
@@ -307,9 +314,14 @@ enum {
 	MLX5_CMD_OP_CREATE_UMEM                   = 0xa08,
 	MLX5_CMD_OP_DESTROY_UMEM                  = 0xa0a,
 	MLX5_CMD_OP_SYNC_STEERING                 = 0xb00,
+	MLX5_CMD_OP_PSP_GEN_SPI                   = 0xb10,
+	MLX5_CMD_OP_PSP_ROTATE_KEY                = 0xb11,
 	MLX5_CMD_OP_QUERY_VHCA_STATE              = 0xb0d,
 	MLX5_CMD_OP_MODIFY_VHCA_STATE             = 0xb0e,
 	MLX5_CMD_OP_SYNC_CRYPTO                   = 0xb12,
+	MLX5_CMD_OP_ALLOW_OTHER_VHCA_ACCESS       = 0xb16,
+	MLX5_CMD_OP_GENERATE_WQE                  = 0xb17,
+	MLX5_CMD_OPCODE_QUERY_VUID                = 0xb22,
 	MLX5_CMD_OP_MAX
 };
 
@@ -413,13 +425,21 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 
 /* Table 2170 - Flow Table Fields Supported 2 Format */
 struct mlx5_ifc_flow_table_fields_supported_2_bits {
-	u8         reserved_at_0[0xe];
+	u8         inner_l4_type_ext[0x1];
+	u8         outer_l4_type_ext[0x1];
+	u8         inner_l4_type[0x1];
+	u8         outer_l4_type[0x1];
+	u8         reserved_at_4[0xa];
 	u8         bth_opcode[0x1];
 	u8         reserved_at_f[0x1];
 	u8         tunnel_header_0_1[0x1];
 	u8         reserved_at_11[0xf];
 
-	u8         reserved_at_20[0x60];
+	u8         reserved_at_20[0xf];
+	u8         ipsec_next_header[0x1];
+	u8         reserved_at_30[0x10];
+
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_flow_table_prop_layout_bits {
@@ -432,7 +452,7 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 	u8         flow_table_modify[0x1];
 	u8         reformat[0x1];
 	u8         decap[0x1];
-	u8         reserved_at_9[0x1];
+	u8         reset_root_to_default[0x1];
 	u8         pop_vlan[0x1];
 	u8         push_vlan[0x1];
 	u8         reserved_at_c[0x1];
@@ -464,22 +484,30 @@ struct mlx5_ifc_flow_table_prop_layout_bits {
 
 	u8         reformat_add_esp_trasport[0x1];
 	u8         reformat_l2_to_l3_esp_tunnel[0x1];
-	u8         reserved_at_42[0x1];
+	u8         reformat_add_esp_transport_over_udp[0x1];
 	u8         reformat_del_esp_trasport[0x1];
 	u8         reformat_l3_esp_tunnel_to_l2[0x1];
-	u8         reserved_at_45[0x1];
+	u8         reformat_del_esp_transport_over_udp[0x1];
 	u8         execute_aso[0x1];
 	u8         reserved_at_47[0x19];
 
-	u8         reserved_at_60[0x2];
+	u8         reformat_l2_to_l3_psp_tunnel[0x1];
+	u8         reformat_l3_psp_tunnel_to_l2[0x1];
 	u8         reformat_insert[0x1];
 	u8         reformat_remove[0x1];
 	u8         macsec_encrypt[0x1];
 	u8         macsec_decrypt[0x1];
-	u8         reserved_at_66[0x2];
+	u8         psp_encrypt[0x1];
+	u8         psp_decrypt[0x1];
 	u8         reformat_add_macsec[0x1];
 	u8         reformat_remove_macsec[0x1];
-	u8         reserved_at_6a[0xe];
+	u8         reparse[0x1];
+	u8         reserved_at_6b[0x1];
+	u8         cross_vhca_object[0x1];
+	u8         reformat_l2_to_l3_audp_tunnel[0x1];
+	u8         reformat_l3_audp_tunnel_to_l2[0x1];
+	u8         ignore_flow_level_rtc_valid[0x1];
+	u8         reserved_at_70[0x8];
 	u8         log_max_ft_num[0x8];
 
 	u8         reserved_at_80[0x10];
@@ -516,12 +544,33 @@ struct mlx5_ifc_ipv6_layout_bits {
 	u8         ipv6[16][0x8];
 };
 
+struct mlx5_ifc_ipv6_simple_layout_bits {
+	u8         ipv6_127_96[0x20];
+	u8         ipv6_95_64[0x20];
+	u8         ipv6_63_32[0x20];
+	u8         ipv6_31_0[0x20];
+};
+
 union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits {
+	struct mlx5_ifc_ipv6_simple_layout_bits ipv6_simple_layout;
 	struct mlx5_ifc_ipv6_layout_bits ipv6_layout;
 	struct mlx5_ifc_ipv4_layout_bits ipv4_layout;
 	u8         reserved_at_0[0x80];
 };
 
+enum {
+	MLX5_PACKET_L4_TYPE_NONE,
+	MLX5_PACKET_L4_TYPE_TCP,
+	MLX5_PACKET_L4_TYPE_UDP,
+};
+
+enum {
+	MLX5_PACKET_L4_TYPE_EXT_NONE,
+	MLX5_PACKET_L4_TYPE_EXT_TCP,
+	MLX5_PACKET_L4_TYPE_EXT_UDP,
+	MLX5_PACKET_L4_TYPE_EXT_ICMP,
+};
+
 struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         smac_47_16[0x20];
 
@@ -547,10 +596,11 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         tcp_sport[0x10];
 	u8         tcp_dport[0x10];
 
-	u8         reserved_at_c0[0x10];
+	u8         l4_type[0x2];
+	u8         l4_type_ext[0x4];
+	u8         reserved_at_c6[0xa];
 	u8         ipv4_ihl[0x4];
-	u8         reserved_at_c4[0x4];
-
+	u8         reserved_at_d4[0x4];
 	u8         ttl_hoplimit[0x8];
 
 	u8         udp_sport[0x10];
@@ -618,7 +668,7 @@ struct mlx5_ifc_fte_match_set_misc_bits {
 
 	u8         reserved_at_140[0x8];
 	u8         bth_dst_qp[0x18];
-	u8	   reserved_at_160[0x20];
+	u8	   inner_esp_spi[0x20];
 	u8	   outer_esp_spi[0x20];
 	u8         reserved_at_1a0[0x60];
 };
@@ -657,11 +707,10 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 
 	u8         metadata_reg_a[0x20];
 
-	u8         reserved_at_1a0[0x8];
-
+	u8         psp_syndrome[0x8];
 	u8         macsec_syndrome[0x8];
 	u8         ipsec_syndrome[0x8];
-	u8         reserved_at_1b8[0x8];
+	u8         ipsec_next_header[0x8];
 
 	u8         reserved_at_1c0[0x40];
 };
@@ -780,7 +829,7 @@ struct mlx5_ifc_ads_bits {
 	u8         reserved_at_2[0xe];
 	u8         pkey_index[0x10];
 
-	u8         reserved_at_20[0x8];
+	u8         plane_index[0x8];
 	u8         grh[0x1];
 	u8         mlid[0x7];
 	u8         rlid[0x10];
@@ -843,7 +892,11 @@ struct mlx5_ifc_flow_table_nic_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_nic_transmit_sniffer;
 
-	u8         reserved_at_e00[0x700];
+	u8         reserved_at_e00[0x600];
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive;
+
+	u8         reserved_at_1480[0x80];
 
 	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_nic_receive_rdma;
 
@@ -873,7 +926,9 @@ struct mlx5_ifc_port_selection_cap_bits {
 
 	struct mlx5_ifc_flow_table_prop_layout_bits flow_table_properties_port_selection;
 
-	u8         reserved_at_400[0x7c00];
+	struct mlx5_ifc_flow_table_fields_supported_2_bits ft_field_support_2_port_selection;
+
+	u8         reserved_at_480[0x7b80];
 };
 
 enum {
@@ -892,7 +947,9 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      reserved_at_8[0x5];
 	u8      fdb_uplink_hairpin[0x1];
 	u8      fdb_multi_path_any_table_limit_regc[0x1];
-	u8      reserved_at_f[0x3];
+	u8      reserved_at_f[0x1];
+	u8      fdb_dynamic_tunnel[0x1];
+	u8      reserved_at_11[0x1];
 	u8      fdb_multi_path_any_table[0x1];
 	u8      reserved_at_13[0x2];
 	u8      fdb_modify_header_fwd_to_table[0x1];
@@ -931,6 +988,73 @@ struct mlx5_ifc_flow_table_eswitch_cap_bits {
 	u8      reserved_at_1900[0x6700];
 };
 
+struct mlx5_ifc_wqe_based_flow_table_cap_bits {
+	u8         reserved_at_0[0x3];
+	u8         log_max_num_ste[0x5];
+	u8         reserved_at_8[0x3];
+	u8         log_max_num_stc[0x5];
+	u8         reserved_at_10[0x3];
+	u8         log_max_num_rtc[0x5];
+	u8         reserved_at_18[0x3];
+	u8         log_max_num_header_modify_pattern[0x5];
+
+	u8         rtc_hash_split_table[0x1];
+	u8         rtc_linear_lookup_table[0x1];
+	u8         reserved_at_22[0x1];
+	u8         stc_alloc_log_granularity[0x5];
+	u8         reserved_at_28[0x3];
+	u8         stc_alloc_log_max[0x5];
+	u8         reserved_at_30[0x3];
+	u8         ste_alloc_log_granularity[0x5];
+	u8         reserved_at_38[0x3];
+	u8         ste_alloc_log_max[0x5];
+
+	u8         reserved_at_40[0xb];
+	u8         rtc_reparse_mode[0x5];
+	u8         reserved_at_50[0x3];
+	u8         rtc_index_mode[0x5];
+	u8         reserved_at_58[0x3];
+	u8         rtc_log_depth_max[0x5];
+
+	u8         reserved_at_60[0x10];
+	u8         ste_format[0x10];
+
+	u8         stc_action_type[0x80];
+
+	u8         header_insert_type[0x10];
+	u8         header_remove_type[0x10];
+
+	u8         trivial_match_definer[0x20];
+
+	u8         reserved_at_140[0x1b];
+	u8         rtc_max_num_hash_definer_gen_wqe[0x5];
+
+	u8         reserved_at_160[0x18];
+	u8         access_index_mode[0x8];
+
+	u8         reserved_at_180[0x10];
+	u8         ste_format_gen_wqe[0x10];
+
+	u8         linear_match_definer_reg_c3[0x20];
+
+	u8         fdb_jump_to_tir_stc[0x1];
+	u8         reserved_at_1c1[0x1f];
+};
+
+struct mlx5_ifc_esw_cap_bits {
+	u8         reserved_at_0[0x1d];
+	u8         merged_eswitch[0x1];
+	u8         reserved_at_1e[0x2];
+
+	u8         reserved_at_20[0x40];
+
+	u8         esw_manager_vport_number_valid[0x1];
+	u8         reserved_at_61[0xf];
+	u8         esw_manager_vport_number[0x10];
+
+	u8         reserved_at_80[0x780];
+};
+
 enum {
 	MLX5_COUNTER_SOURCE_ESWITCH = 0x0,
 	MLX5_COUNTER_FLOW_ESWITCH   = 0x1,
@@ -989,7 +1113,9 @@ struct mlx5_ifc_qos_cap_bits {
 	u8         log_esw_max_sched_depth[0x4];
 	u8         reserved_at_10[0x10];
 
-	u8         reserved_at_20[0xb];
+	u8         reserved_at_20[0x9];
+	u8         esw_cross_esw_sched[0x1];
+	u8         reserved_at_2a[0x1];
 	u8         log_max_qos_nic_queue_group[0x5];
 	u8         reserved_at_30[0x10];
 
@@ -997,7 +1123,8 @@ struct mlx5_ifc_qos_cap_bits {
 
 	u8         packet_pacing_min_rate[0x20];
 
-	u8         reserved_at_80[0x10];
+	u8         reserved_at_80[0xb];
+	u8         log_esw_max_rate_limit[0x5];
 	u8         packet_pacing_rate_table_size[0x10];
 
 	u8         esw_element_type[0x10];
@@ -1008,7 +1135,8 @@ struct mlx5_ifc_qos_cap_bits {
 
 	u8         max_tsar_bw_share[0x20];
 
-	u8         reserved_at_100[0x20];
+	u8         nic_element_type[0x10];
+	u8         nic_tsar_type[0x10];
 
 	u8         reserved_at_120[0x3];
 	u8         log_meter_aso_granularity[0x5];
@@ -1074,7 +1202,8 @@ struct mlx5_ifc_per_protocol_networking_offload_caps_bits {
 	u8         tunnel_stateless_ip_over_ip_tx[0x1];
 	u8         reserved_at_2e[0x2];
 	u8         max_vxlan_udp_ports[0x8];
-	u8         reserved_at_38[0x6];
+	u8         swp_csum_l4_partial[0x1];
+	u8         reserved_at_39[0x5];
 	u8         max_geneve_opt_len[0x1];
 	u8         tunnel_stateless_geneve_rx[0x1];
 
@@ -1100,7 +1229,7 @@ struct mlx5_ifc_roce_cap_bits {
 	u8         sw_r_roce_src_udp_port[0x1];
 	u8         fl_rc_qp_when_roce_disabled[0x1];
 	u8         fl_rc_qp_when_roce_enabled[0x1];
-	u8         reserved_at_7[0x1];
+	u8         roce_cc_general[0x1];
 	u8	   qp_ooo_transmit_default[0x1];
 	u8         reserved_at_9[0x15];
 	u8	   qp_ts_format[0x2];
@@ -1190,7 +1319,8 @@ struct mlx5_ifc_device_mem_cap_bits {
 	u8         log_sw_icm_alloc_granularity[0x6];
 	u8         log_steering_sw_icm_size[0x8];
 
-	u8         reserved_at_120[0x18];
+	u8         log_indirect_encap_sw_icm_size[0x8];
+	u8         reserved_at_128[0x10];
 	u8         log_header_modify_pattern_sw_icm_size[0x8];
 
 	u8         header_modify_sw_icm_start_address[0x40];
@@ -1201,7 +1331,11 @@ struct mlx5_ifc_device_mem_cap_bits {
 
 	u8         memic_operations[0x20];
 
-	u8         reserved_at_220[0x5e0];
+	u8         reserved_at_220[0x20];
+
+	u8         indirect_encap_sw_icm_start_address[0x40];
+
+	u8         reserved_at_280[0x580];
 };
 
 struct mlx5_ifc_device_event_cap_bits {
@@ -1229,7 +1363,14 @@ struct mlx5_ifc_virtio_emulation_cap_bits {
 	u8         max_emulated_devices[0x8];
 	u8         max_num_virtio_queues[0x18];
 
-	u8         reserved_at_a0[0x60];
+	u8         reserved_at_a0[0x20];
+
+	u8	   reserved_at_c0[0x13];
+	u8         desc_group_mkey_supported[0x1];
+	u8         freeze_to_rdy_supported[0x1];
+	u8         reserved_at_d5[0xb];
+
+	u8         reserved_at_e0[0x20];
 
 	u8         umem_1_buffer_param_a[0x20];
 
@@ -1293,11 +1434,13 @@ struct mlx5_ifc_atomic_caps_bits {
 	u8         reserved_at_e0[0x720];
 };
 
-struct mlx5_ifc_odp_cap_bits {
+struct mlx5_ifc_odp_scheme_cap_bits {
 	u8         reserved_at_0[0x40];
 
 	u8         sig[0x1];
-	u8         reserved_at_41[0x1f];
+	u8         reserved_at_41[0x4];
+	u8         page_prefetch[0x1];
+	u8         reserved_at_46[0x1a];
 
 	u8         reserved_at_60[0x20];
 
@@ -1311,34 +1454,20 @@ struct mlx5_ifc_odp_cap_bits {
 
 	struct mlx5_ifc_odp_per_transport_service_cap_bits dc_odp_caps;
 
-	u8         reserved_at_120[0x6E0];
+	u8         reserved_at_120[0xe0];
 };
 
-struct mlx5_ifc_calc_op {
-	u8        reserved_at_0[0x10];
-	u8        reserved_at_10[0x9];
-	u8        op_swap_endianness[0x1];
-	u8        op_min[0x1];
-	u8        op_xor[0x1];
-	u8        op_or[0x1];
-	u8        op_and[0x1];
-	u8        op_max[0x1];
-	u8        op_add[0x1];
-};
+struct mlx5_ifc_odp_cap_bits {
+	struct mlx5_ifc_odp_scheme_cap_bits transport_page_fault_scheme_cap;
 
-struct mlx5_ifc_vector_calc_cap_bits {
-	u8         calc_matrix[0x1];
-	u8         reserved_at_1[0x1f];
-	u8         reserved_at_20[0x8];
-	u8         max_vec_count[0x8];
-	u8         reserved_at_30[0xd];
-	u8         max_chunk_size[0x3];
-	struct mlx5_ifc_calc_op calc0;
-	struct mlx5_ifc_calc_op calc1;
-	struct mlx5_ifc_calc_op calc2;
-	struct mlx5_ifc_calc_op calc3;
+	struct mlx5_ifc_odp_scheme_cap_bits memory_page_fault_scheme_cap;
+
+	u8         reserved_at_400[0x200];
 
-	u8         reserved_at_c0[0x720];
+	u8         mem_page_fault[0x1];
+	u8         reserved_at_601[0x1f];
+
+	u8         reserved_at_620[0x1e0];
 };
 
 struct mlx5_ifc_tls_cap_bits {
@@ -1386,6 +1515,21 @@ struct mlx5_ifc_macsec_cap_bits {
 	u8    reserved_at_40[0x7c0];
 };
 
+struct mlx5_ifc_psp_cap_bits {
+	u8         reserved_at_0[0x1];
+	u8         psp_crypto_offload[0x1];
+	u8         reserved_at_2[0x1];
+	u8         psp_crypto_esp_aes_gcm_256_encrypt[0x1];
+	u8         psp_crypto_esp_aes_gcm_128_encrypt[0x1];
+	u8         psp_crypto_esp_aes_gcm_256_decrypt[0x1];
+	u8         psp_crypto_esp_aes_gcm_128_decrypt[0x1];
+	u8         reserved_at_7[0x4];
+	u8         log_max_num_of_psp_spi[0x5];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x7e0];
+};
+
 enum {
 	MLX5_WQ_TYPE_LINKED_LIST  = 0x0,
 	MLX5_WQ_TYPE_CYCLIC       = 0x1,
@@ -1438,9 +1582,13 @@ enum {
 };
 
 enum {
+	MLX5_FLEX_IPV4_OVER_VXLAN_ENABLED	= 1 << 0,
+	MLX5_FLEX_IPV6_OVER_VXLAN_ENABLED	= 1 << 1,
+	MLX5_FLEX_IPV6_OVER_IP_ENABLED		= 1 << 2,
 	MLX5_FLEX_PARSER_GENEVE_ENABLED		= 1 << 3,
 	MLX5_FLEX_PARSER_MPLS_OVER_GRE_ENABLED	= 1 << 4,
 	MLX5_FLEX_PARSER_MPLS_OVER_UDP_ENABLED	= 1 << 5,
+	MLX5_FLEX_P_BIT_VXLAN_GPE_ENABLED	= 1 << 6,
 	MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED	= 1 << 7,
 	MLX5_FLEX_PARSER_ICMP_V4_ENABLED	= 1 << 8,
 	MLX5_FLEX_PARSER_ICMP_V6_ENABLED	= 1 << 9,
@@ -1455,6 +1603,8 @@ enum {
 enum {
 	MLX5_UCTX_CAP_RAW_TX = 1UL << 0,
 	MLX5_UCTX_CAP_INTERNAL_DEV_RES = 1UL << 1,
+	MLX5_UCTX_CAP_RDMA_CTRL = 1UL << 3,
+	MLX5_UCTX_CAP_RDMA_CTRL_OTHER_VHCA = 1UL << 4,
 };
 
 #define MLX5_FC_BULK_SIZE_FACTOR 128
@@ -1478,10 +1628,14 @@ enum {
 	MLX5_STEERING_FORMAT_CONNECTX_5   = 0,
 	MLX5_STEERING_FORMAT_CONNECTX_6DX = 1,
 	MLX5_STEERING_FORMAT_CONNECTX_7   = 2,
+	MLX5_STEERING_FORMAT_CONNECTX_8   = 3,
 };
 
 struct mlx5_ifc_cmd_hca_cap_bits {
-	u8         reserved_at_0[0x10];
+	u8         reserved_at_0[0x6];
+	u8         page_request_disable[0x1];
+	u8         abs_native_port_num[0x1];
+	u8         reserved_at_8[0x8];
 	u8         shared_object_to_user_object_allowed[0x1];
 	u8         reserved_at_13[0xe];
 	u8         vhca_resource_manager[0x1];
@@ -1520,8 +1674,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         ts_cqe_to_dest_cqn[0x1];
 	u8         reserved_at_b3[0x6];
 	u8         go_back_n[0x1];
-	u8         shampo[0x1];
-	u8         reserved_at_bb[0x5];
+	u8         reserved_at_ba[0x6];
 
 	u8         max_sgl_for_optimized_performance[0x8];
 	u8         log_max_cq_sz[0x8];
@@ -1644,7 +1797,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         pci_sync_for_fw_update_event[0x1];
 	u8         reserved_at_1f2[0x6];
 	u8         init2_lag_tx_port_affinity[0x1];
-	u8         reserved_at_1fa[0x3];
+	u8         reserved_at_1fa[0x2];
+	u8         wqe_based_flow_table_update_cap[0x1];
 	u8         cqe_version[0x4];
 
 	u8         compact_address_vector[0x1];
@@ -1680,7 +1834,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         cq_oi[0x1];
 	u8         cq_resize[0x1];
 	u8         cq_moderation[0x1];
-	u8         reserved_at_223[0x3];
+	u8         cq_period_mode_modify[0x1];
+	u8         reserved_at_224[0x2];
 	u8         cq_eq_remap[0x1];
 	u8         pg[0x1];
 	u8         block_lb_mc[0x1];
@@ -1710,9 +1865,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         regexp_params[0x1];
 	u8         uar_sz[0x6];
 	u8         port_selection_cap[0x1];
-	u8         reserved_at_248[0x1];
+	u8         nic_cap_reg[0x1];
 	u8         umem_uid_0[0x1];
-	u8         reserved_at_250[0x5];
+	u8         reserved_at_253[0x5];
 	u8         log_pg_sz[0x8];
 
 	u8         bf[0x1];
@@ -1724,7 +1879,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_bf_reg_size[0x5];
 
-	u8         reserved_at_270[0x3];
+	u8         disciplined_fr_counter[0x1];
+	u8         reserved_at_271[0x2];
 	u8	   qp_error_syndrome[0x1];
 	u8	   reserved_at_274[0x2];
 	u8         lag_dct[0x2];
@@ -1737,7 +1893,14 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_280[0x10];
 	u8         max_wqe_sz_sq[0x10];
 
-	u8         reserved_at_2a0[0x10];
+	u8         reserved_at_2a0[0x7];
+	u8         mkey_pcie_tph[0x1];
+	u8         reserved_at_2a8[0x1];
+	u8         tis_tir_td_order[0x1];
+
+	u8         psp[0x1];
+	u8         shampo[0x1];
+	u8         reserved_at_2ac[0x4];
 	u8         max_wqe_sz_rq[0x10];
 
 	u8         max_flow_counter_31_16[0x10];
@@ -1755,7 +1918,15 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_328[0x2];
 	u8	   relaxed_ordering_read[0x1];
 	u8         log_max_pd[0x5];
-	u8         reserved_at_330[0x9];
+	u8         dp_ordering_ooo_all_ud[0x1];
+	u8         dp_ordering_ooo_all_uc[0x1];
+	u8         dp_ordering_ooo_all_xrc[0x1];
+	u8         dp_ordering_ooo_all_dc[0x1];
+	u8         dp_ordering_ooo_all_rc[0x1];
+	u8         pcie_reset_using_hotreset_method[0x1];
+	u8         pci_sync_for_fw_update_with_driver_unload[0x1];
+	u8         vnic_env_cnt_steering_fail[0x1];
+	u8         vport_counter_local_loopback[0x1];
 	u8         q_counter_aggregation[0x1];
 	u8         q_counter_other_vport[0x1];
 	u8         log_max_xrcd[0x5];
@@ -1788,7 +1959,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         log_max_rqt[0x5];
 	u8         reserved_at_390[0x3];
 	u8         log_max_rqt_size[0x5];
-	u8         reserved_at_398[0x3];
+	u8         reserved_at_398[0x1];
+	u8	   vnic_env_cnt_bar_uar_access[0x1];
+	u8	   vnic_env_cnt_odp_page_fault[0x1];
 	u8         log_max_tis_per_sq[0x5];
 
 	u8         ext_stride_num_range[0x1];
@@ -1816,7 +1989,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         disable_local_lb_uc[0x1];
 	u8         disable_local_lb_mc[0x1];
 	u8         log_min_hairpin_wq_data_sz[0x5];
-	u8         reserved_at_3e8[0x2];
+	u8         reserved_at_3e8[0x1];
+	u8         silent_mode[0x1];
 	u8         vhca_state[0x1];
 	u8         log_max_vlan_list[0x5];
 	u8         reserved_at_3f0[0x3];
@@ -1833,7 +2007,7 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_460[0x1];
 	u8         ats[0x1];
-	u8         reserved_at_462[0x1];
+	u8         cross_vhca_rqt[0x1];
 	u8         log_max_uctx[0x5];
 	u8         reserved_at_468[0x1];
 	u8         crypto[0x1];
@@ -1860,7 +2034,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         max_geneve_tlv_options[0x8];
 	u8         reserved_at_568[0x3];
 	u8         max_geneve_tlv_option_data_len[0x5];
-	u8         reserved_at_570[0x9];
+	u8         reserved_at_570[0x1];
+	u8         adv_rdma[0x1];
+	u8         reserved_at_572[0x7];
 	u8         adv_virtualization[0x1];
 	u8         reserved_at_57a[0x6];
 
@@ -1872,7 +2048,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         reserved_at_5a0[0x10];
 	u8         enhanced_cqe_compression[0x1];
-	u8         reserved_at_5b1[0x2];
+	u8         reserved_at_5b1[0x1];
+	u8         crossing_vhca_mkey[0x1];
 	u8         log_max_dek[0x5];
 	u8         reserved_at_5b8[0x4];
 	u8         mini_cqe_resp_stride_index[0x1];
@@ -1941,12 +2118,14 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8	   dynamic_msix_table_size[0xc];
 	u8	   reserved_at_740[0xc];
 	u8	   min_dynamic_vf_msix_table_size[0x4];
-	u8	   reserved_at_750[0x4];
+	u8	   reserved_at_750[0x2];
+	u8	   data_direct[0x1];
+	u8	   reserved_at_753[0x1];
 	u8	   max_dynamic_vf_msix_table_size[0xc];
 
 	u8         reserved_at_760[0x3];
 	u8         log_max_num_header_modify_argument[0x5];
-	u8         reserved_at_768[0x4];
+	u8         log_header_modify_argument_granularity_offset[0x4];
 	u8         log_header_modify_argument_granularity[0x4];
 	u8         reserved_at_770[0x3];
 	u8         log_header_modify_argument_max_alloc[0x5];
@@ -1956,11 +2135,26 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         match_definer_format_supported[0x40];
 };
 
+enum {
+	MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_TO_REMOTE_FLOW_TABLE_MISS  = 0x80000,
+	MLX5_CROSS_VHCA_OBJ_TO_OBJ_SUPPORTED_LOCAL_FLOW_TABLE_ROOT_TO_REMOTE_FLOW_TABLE  = (1ULL << 20),
+};
+
+enum {
+	MLX5_ALLOWED_OBJ_FOR_OTHER_VHCA_ACCESS_FLOW_TABLE       = 0x200,
+};
+
 struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_0[0x80];
 
 	u8         migratable[0x1];
-	u8         reserved_at_81[0x1f];
+	u8         reserved_at_81[0x7];
+	u8         dp_ordering_force[0x1];
+	u8         reserved_at_89[0x9];
+	u8         query_vuid[0x1];
+	u8         reserved_at_93[0x5];
+	u8         umr_log_entity_size_5[0x1];
+	u8         reserved_at_99[0x7];
 
 	u8	   max_reformat_insert_size[0x8];
 	u8	   max_reformat_insert_offset[0x8];
@@ -1970,16 +2164,29 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   reserved_at_c0[0x8];
 	u8	   migration_multi_load[0x1];
 	u8	   migration_tracking_state[0x1];
-	u8	   reserved_at_ca[0x16];
+	u8	   multiplane_qp_ud[0x1];
+	u8	   reserved_at_cb[0x5];
+	u8	   migration_in_chunks[0x1];
+	u8	   reserved_at_d1[0x1];
+	u8	   sf_eq_usage[0x1];
+	u8	   reserved_at_d3[0x5];
+	u8	   multiplane[0x1];
+	u8	   reserved_at_d9[0x7];
 
-	u8	   reserved_at_e0[0xc0];
+	u8	   cross_vhca_object_to_object_supported[0x20];
+
+	u8	   allowed_object_for_other_vhca_access[0x40];
+
+	u8	   reserved_at_140[0x60];
 
 	u8	   flow_table_type_2_type[0x8];
-	u8	   reserved_at_1a8[0x3];
+	u8	   reserved_at_1a8[0x2];
+	u8         format_select_dw_8_6_ext[0x1];
 	u8	   log_min_mkey_entity_size[0x5];
 	u8	   reserved_at_1b0[0x10];
 
-	u8	   reserved_at_1c0[0x60];
+	u8	   general_obj_types_127_64[0x40];
+	u8	   reserved_at_200[0x20];
 
 	u8	   reserved_at_220[0x1];
 	u8	   sw_vhca_id_valid[0x1];
@@ -1990,7 +2197,60 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   ts_cqe_metadata_size2wqe_counter[0x5];
 	u8	   reserved_at_250[0x10];
 
-	u8	   reserved_at_260[0x5a0];
+	u8	   reserved_at_260[0x20];
+
+	u8	   format_select_dw_gtpu_dw_0[0x8];
+	u8	   format_select_dw_gtpu_dw_1[0x8];
+	u8	   format_select_dw_gtpu_dw_2[0x8];
+	u8	   format_select_dw_gtpu_first_ext_dw_0[0x8];
+
+	u8	   generate_wqe_type[0x20];
+
+	u8	   reserved_at_2c0[0xc0];
+
+	u8	   reserved_at_380[0xb];
+	u8	   min_mkey_log_entity_size_fixed_buffer[0x5];
+	u8	   ec_vf_vport_base[0x10];
+
+	u8	   reserved_at_3a0[0x2];
+	u8	   max_mkey_log_entity_size_fixed_buffer[0x6];
+	u8	   reserved_at_3a8[0x2];
+	u8	   max_mkey_log_entity_size_mtt[0x6];
+	u8	   max_rqt_vhca_id[0x10];
+
+	u8	   reserved_at_3c0[0x20];
+
+	u8	   reserved_at_3e0[0x10];
+	u8	   pcc_ifa2[0x1];
+	u8	   reserved_at_3f1[0xf];
+
+	u8	   reserved_at_400[0x1];
+	u8	   min_mkey_log_entity_size_fixed_buffer_valid[0x1];
+	u8	   reserved_at_402[0xe];
+	u8	   return_reg_id[0x10];
+
+	u8	   reserved_at_420[0x1c];
+	u8	   flow_table_hash_type[0x4];
+
+	u8	   reserved_at_440[0x8];
+	u8	   max_num_eqs_24b[0x18];
+
+	u8         reserved_at_460[0x144];
+	u8         load_balance_id[0x4];
+	u8         reserved_at_5a8[0x18];
+
+	u8         query_adjacent_functions_id[0x1];
+	u8         ingress_egress_esw_vport_connect[0x1];
+	u8         function_id_type_vhca_id[0x1];
+	u8         reserved_at_5c3[0x1];
+	u8         lag_per_mp_group[0x1];
+	u8         reserved_at_5c5[0xb];
+	u8         delegate_vhca_management_profiles[0x10];
+
+	u8         delegated_vhca_max[0x10];
+	u8         delegate_vhca_max[0x10];
+
+	u8         reserved_at_600[0x200];
 };
 
 enum mlx5_ifc_flow_destination_type {
@@ -2033,7 +2293,7 @@ struct mlx5_ifc_extended_dest_format_bits {
 	u8         reserved_at_60[0x20];
 };
 
-union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits {
+union mlx5_ifc_dest_format_flow_counter_list_auto_bits {
 	struct mlx5_ifc_extended_dest_format_bits extended_dest_format;
 	struct mlx5_ifc_flow_counter_list_bits flow_counter_list;
 };
@@ -2125,12 +2385,17 @@ struct mlx5_ifc_wq_bits {
 	u8         reserved_at_139[0x4];
 	u8         log_wqe_stride_size[0x3];
 
-	u8         reserved_at_140[0x80];
+	u8         dbr_umem_id[0x20];
+	u8         wq_umem_id[0x20];
+
+	u8         wq_umem_offset[0x40];
 
 	u8         headers_mkey[0x20];
 
 	u8         shampo_enable[0x1];
-	u8         reserved_at_1e1[0x4];
+	u8         reserved_at_1e1[0x1];
+	u8         shampo_mode[0x2];
+	u8         reserved_at_1e4[0x1];
 	u8         log_reservation_size[0x3];
 	u8         reserved_at_1e8[0x5];
 	u8         log_max_num_of_packets_per_reservation[0x3];
@@ -2149,6 +2414,13 @@ struct mlx5_ifc_rq_num_bits {
 	u8         rq_num[0x18];
 };
 
+struct mlx5_ifc_rq_vhca_bits {
+	u8         reserved_at_0[0x8];
+	u8         rq_num[0x18];
+	u8         reserved_at_20[0x10];
+	u8         rq_vhca_id[0x10];
+};
+
 struct mlx5_ifc_mac_address_layout_bits {
 	u8         reserved_at_0[0x10];
 	u8         mac_addr_47_32[0x10];
@@ -2432,6 +2704,12 @@ struct mlx5_ifc_field_select_802_1qau_rp_bits {
 	u8         field_select_8021qaurp[0x20];
 };
 
+struct mlx5_ifc_phys_layer_recovery_cntrs_bits {
+	u8         total_successful_recovery_events[0x20];
+
+	u8         reserved_at_20[0x7a0];
+};
+
 struct mlx5_ifc_phys_layer_cntrs_bits {
 	u8         time_since_last_clear_high[0x20];
 
@@ -2604,6 +2882,46 @@ struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits {
 	u8         port_xmit_wait[0x20];
 };
 
+struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits {
+	u8         reserved_at_0[0x300];
+
+	u8         port_xmit_data_high[0x20];
+
+	u8         port_xmit_data_low[0x20];
+
+	u8         port_rcv_data_high[0x20];
+
+	u8         port_rcv_data_low[0x20];
+
+	u8         port_xmit_pkts_high[0x20];
+
+	u8         port_xmit_pkts_low[0x20];
+
+	u8         port_rcv_pkts_high[0x20];
+
+	u8         port_rcv_pkts_low[0x20];
+
+	u8         reserved_at_400[0x80];
+
+	u8         port_unicast_xmit_pkts_high[0x20];
+
+	u8         port_unicast_xmit_pkts_low[0x20];
+
+	u8         port_multicast_xmit_pkts_high[0x20];
+
+	u8         port_multicast_xmit_pkts_low[0x20];
+
+	u8         port_unicast_rcv_pkts_high[0x20];
+
+	u8         port_unicast_rcv_pkts_low[0x20];
+
+	u8         port_multicast_rcv_pkts_high[0x20];
+
+	u8         port_multicast_rcv_pkts_low[0x20];
+
+	u8         reserved_at_580[0x240];
+};
+
 struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits {
 	u8         transmit_queue_high[0x20];
 
@@ -3081,6 +3399,14 @@ struct mlx5_ifc_dropped_packet_logged_bits {
 	u8         reserved_at_0[0xe0];
 };
 
+struct mlx5_ifc_nic_cap_reg_bits {
+	u8	   reserved_at_0[0x1a];
+	u8	   vhca_icm_ctrl[0x1];
+	u8	   reserved_at_1b[0x5];
+
+	u8	   reserved_at_20[0x60];
+};
+
 struct mlx5_ifc_default_timeout_bits {
 	u8         to_multiplier[0x3];
 	u8         reserved_at_3[0x9];
@@ -3112,7 +3438,21 @@ struct mlx5_ifc_dtor_reg_bits {
 
 	struct mlx5_ifc_default_timeout_bits reclaim_vfs_pages_to;
 
-	u8         reserved_at_1c0[0x40];
+	struct mlx5_ifc_default_timeout_bits reset_unload_to;
+
+	u8         reserved_at_1c0[0x20];
+};
+
+struct mlx5_ifc_vhca_icm_ctrl_reg_bits {
+	u8	   vhca_id_valid[0x1];
+	u8	   reserved_at_1[0xf];
+	u8	   vhca_id[0x10];
+
+	u8	   reserved_at_20[0xa0];
+
+	u8	   cur_alloc_icm[0x20];
+
+	u8	   reserved_at_e0[0x120];
 };
 
 enum {
@@ -3289,7 +3629,8 @@ struct mlx5_ifc_qpc_bits {
 	u8         latency_sensitive[0x1];
 	u8         reserved_at_24[0x1];
 	u8         drain_sigerr[0x1];
-	u8         reserved_at_26[0x2];
+	u8         reserved_at_26[0x1];
+	u8         dp_ordering_force[0x1];
 	u8         pd[0x18];
 
 	u8         mtu[0x3];
@@ -3362,7 +3703,8 @@ struct mlx5_ifc_qpc_bits {
 	u8         rae[0x1];
 	u8         reserved_at_493[0x1];
 	u8         page_offset[0x6];
-	u8         reserved_at_49a[0x3];
+	u8         reserved_at_49a[0x2];
+	u8         dp_ordering_1[0x1];
 	u8         cd_slave_receive[0x1];
 	u8         cd_slave_send[0x1];
 	u8         cd_master[0x1];
@@ -3427,20 +3769,6 @@ struct mlx5_ifc_roce_addr_layout_bits {
 	u8         reserved_at_e0[0x20];
 };
 
-struct mlx5_ifc_shampo_cap_bits {
-	u8    reserved_at_0[0x3];
-	u8    shampo_log_max_reservation_size[0x5];
-	u8    reserved_at_8[0x3];
-	u8    shampo_log_min_reservation_size[0x5];
-	u8    shampo_min_mss_size[0x10];
-
-	u8    reserved_at_20[0x3];
-	u8    shampo_max_log_headers_entry_size[0x5];
-	u8    reserved_at_28[0x18];
-
-	u8    reserved_at_40[0x7c0];
-};
-
 struct mlx5_ifc_crypto_cap_bits {
 	u8    reserved_at_0[0x3];
 	u8    synchronize_dek[0x1];
@@ -3465,6 +3793,22 @@ struct mlx5_ifc_crypto_cap_bits {
 	u8    reserved_at_80[0x780];
 };
 
+struct mlx5_ifc_shampo_cap_bits {
+	u8    reserved_at_0[0x3];
+	u8    shampo_log_max_reservation_size[0x5];
+	u8    reserved_at_8[0x3];
+	u8    shampo_log_min_reservation_size[0x5];
+	u8    shampo_min_mss_size[0x10];
+
+	u8    shampo_header_split[0x1];
+	u8    shampo_header_split_data_merge[0x1];
+	u8    reserved_at_22[0x1];
+	u8    shampo_log_max_headers_entry_size[0x5];
+	u8    reserved_at_28[0x18];
+
+	u8    reserved_at_40[0x7c0];
+};
+
 union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_cmd_hca_cap_bits cmd_hca_cap;
 	struct mlx5_ifc_cmd_hca_cap_2_bits cmd_hca_cap_2;
@@ -3474,18 +3818,20 @@ union mlx5_ifc_hca_cap_union_bits {
 	struct mlx5_ifc_per_protocol_networking_offload_caps_bits per_protocol_networking_offload_caps;
 	struct mlx5_ifc_flow_table_nic_cap_bits flow_table_nic_cap;
 	struct mlx5_ifc_flow_table_eswitch_cap_bits flow_table_eswitch_cap;
+	struct mlx5_ifc_wqe_based_flow_table_cap_bits wqe_based_flow_table_cap;
+	struct mlx5_ifc_esw_cap_bits esw_cap;
 	struct mlx5_ifc_e_switch_cap_bits e_switch_cap;
 	struct mlx5_ifc_port_selection_cap_bits port_selection_cap;
-	struct mlx5_ifc_vector_calc_cap_bits vector_calc_cap;
 	struct mlx5_ifc_qos_cap_bits qos_cap;
 	struct mlx5_ifc_debug_cap_bits debug_cap;
 	struct mlx5_ifc_fpga_cap_bits fpga_cap;
 	struct mlx5_ifc_tls_cap_bits tls_cap;
 	struct mlx5_ifc_device_mem_cap_bits device_mem_cap;
 	struct mlx5_ifc_virtio_emulation_cap_bits virtio_emulation_cap;
-	struct mlx5_ifc_shampo_cap_bits shampo_cap;
 	struct mlx5_ifc_macsec_cap_bits macsec_cap;
 	struct mlx5_ifc_crypto_cap_bits crypto_cap;
+	struct mlx5_ifc_ipsec_cap_bits ipsec_cap;
+	struct mlx5_ifc_psp_cap_bits psp_cap;
 	u8         reserved_at_0[0x8000];
 };
 
@@ -3515,6 +3861,7 @@ enum {
 enum {
 	MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_IPSEC   = 0x0,
 	MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_MACSEC  = 0x1,
+	MLX5_FLOW_CONTEXT_ENCRYPT_DECRYPT_TYPE_PSP     = 0x2,
 };
 
 struct mlx5_ifc_vlan_bits {
@@ -3568,7 +3915,7 @@ struct mlx5_ifc_flow_context_bits {
 	u8         action[0x10];
 
 	u8         extended_destination[0x1];
-	u8         reserved_at_81[0x1];
+	u8         uplink_hairpin_en[0x1];
 	u8         flow_source[0x2];
 	u8         encrypt_decrypt_type[0x4];
 	u8         destination_list_size[0x18];
@@ -3591,7 +3938,7 @@ struct mlx5_ifc_flow_context_bits {
 
 	u8         reserved_at_1300[0x500];
 
-	union mlx5_ifc_dest_format_struct_flow_counter_list_auto_bits destination[];
+	union mlx5_ifc_dest_format_flow_counter_list_auto_bits destination[];
 };
 
 enum {
@@ -3673,7 +4020,19 @@ struct mlx5_ifc_vnic_diagnostic_statistics_bits {
 
 	u8         eth_wqe_too_small[0x20];
 
-	u8         reserved_at_220[0xdc0];
+	u8         reserved_at_220[0xc0];
+
+	u8         generated_pkt_steering_fail[0x40];
+
+	u8         handled_pkt_steering_fail[0x40];
+
+	u8         bar_uar_access[0x20];
+
+	u8         odp_local_triggered_page_fault[0x20];
+
+	u8         odp_remote_triggered_page_fault[0x20];
+
+	u8         reserved_at_3c0[0xc20];
 };
 
 struct mlx5_ifc_traffic_counter_bits {
@@ -3826,7 +4185,8 @@ struct mlx5_ifc_sqc_bits {
 	u8         reg_umr[0x1];
 	u8         allow_swp[0x1];
 	u8         hairpin[0x1];
-	u8         reserved_at_f[0xb];
+	u8         non_wire[0x1];
+	u8         reserved_at_10[0xa];
 	u8	   ts_format[0x2];
 	u8	   reserved_at_1c[0x4];
 
@@ -3866,20 +4226,65 @@ enum {
 	SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC = 0x2,
 	SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC = 0x3,
 	SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP = 0x4,
+	SCHEDULING_CONTEXT_ELEMENT_TYPE_RATE_LIMIT = 0x5,
 };
 
 enum {
-	ELEMENT_TYPE_CAP_MASK_TASR		= 1 << 0,
+	ELEMENT_TYPE_CAP_MASK_TSAR		= 1 << 0,
 	ELEMENT_TYPE_CAP_MASK_VPORT		= 1 << 1,
 	ELEMENT_TYPE_CAP_MASK_VPORT_TC		= 1 << 2,
 	ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC	= 1 << 3,
+	ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP	= 1 << 4,
+	ELEMENT_TYPE_CAP_MASK_RATE_LIMIT	= 1 << 5,
+};
+
+enum {
+	TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0,
+	TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1,
+	TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2,
+	TSAR_ELEMENT_TSAR_TYPE_TC_ARB = 0x3,
+};
+
+enum {
+	TSAR_TYPE_CAP_MASK_DWRR		= 1 << 0,
+	TSAR_TYPE_CAP_MASK_ROUND_ROBIN	= 1 << 1,
+	TSAR_TYPE_CAP_MASK_ETS		= 1 << 2,
+	TSAR_TYPE_CAP_MASK_TC_ARB       = 1 << 3,
+};
+
+struct mlx5_ifc_tsar_element_bits {
+	u8         traffic_class[0x4];
+	u8         reserved_at_4[0x4];
+	u8         tsar_type[0x8];
+	u8         reserved_at_10[0x10];
+};
+
+struct mlx5_ifc_vport_element_bits {
+	u8         reserved_at_0[0x4];
+	u8         eswitch_owner_vhca_id_valid[0x1];
+	u8         eswitch_owner_vhca_id[0xb];
+	u8         vport_number[0x10];
+};
+
+struct mlx5_ifc_vport_tc_element_bits {
+	u8         traffic_class[0x4];
+	u8         eswitch_owner_vhca_id_valid[0x1];
+	u8         eswitch_owner_vhca_id[0xb];
+	u8         vport_number[0x10];
+};
+
+union mlx5_ifc_element_attributes_bits {
+	struct mlx5_ifc_tsar_element_bits tsar;
+	struct mlx5_ifc_vport_element_bits vport;
+	struct mlx5_ifc_vport_tc_element_bits vport_tc;
+	u8 reserved_at_0[0x20];
 };
 
 struct mlx5_ifc_scheduling_context_bits {
 	u8         element_type[0x8];
 	u8         reserved_at_8[0x18];
 
-	u8         element_attributes[0x20];
+	union mlx5_ifc_element_attributes_bits element_attributes;
 
 	u8         parent_element_id[0x20];
 
@@ -3889,7 +4294,9 @@ struct mlx5_ifc_scheduling_context_bits {
 
 	u8         max_average_bw[0x20];
 
-	u8         reserved_at_e0[0x120];
+	u8         max_bw_obj_id[0x20];
+
+	u8         reserved_at_100[0x100];
 };
 
 struct mlx5_ifc_rqtc_bits {
@@ -3906,7 +4313,10 @@ struct mlx5_ifc_rqtc_bits {
 
 	u8    reserved_at_e0[0x6a0];
 
-	struct mlx5_ifc_rq_num_bits rq_num[];
+	union {
+		DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_num_bits, rq_num);
+		DECLARE_FLEX_ARRAY(struct mlx5_ifc_rq_vhca_bits, rq_vhca);
+	};
 };
 
 enum {
@@ -4019,8 +4429,13 @@ struct mlx5_ifc_nic_vport_context_bits {
 	u8	   affiliation_criteria[0x4];
 	u8	   affiliated_vhca_id[0x10];
 
-	u8	   reserved_at_60[0xd0];
+	u8	   reserved_at_60[0xa0];
+
+	u8	   reserved_at_100[0x1];
+	u8         sd_group[0x3];
+	u8	   reserved_at_104[0x1c];
 
+	u8	   reserved_at_120[0x10];
 	u8         mtu[0x10];
 
 	u8         system_image_guid[0x40];
@@ -4053,6 +4468,11 @@ enum {
 	MLX5_MKC_ACCESS_MODE_KSM   = 0x3,
 	MLX5_MKC_ACCESS_MODE_SW_ICM = 0x4,
 	MLX5_MKC_ACCESS_MODE_MEMIC = 0x5,
+	MLX5_MKC_ACCESS_MODE_CROSSING = 0x6,
+};
+
+enum {
+	MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX = 0,
 };
 
 struct mlx5_ifc_mkc_bits {
@@ -4095,16 +4515,22 @@ struct mlx5_ifc_mkc_bits {
 
 	u8         bsf_octword_size[0x20];
 
-	u8         reserved_at_120[0x80];
+	u8         reserved_at_120[0x60];
+
+	u8         crossing_target_vhca_id[0x10];
+	u8         reserved_at_190[0x10];
 
 	u8         translations_octword_size[0x20];
 
 	u8         reserved_at_1c0[0x19];
 	u8         relaxed_ordering_read[0x1];
-	u8         reserved_at_1d9[0x1];
-	u8         log_page_size[0x5];
+	u8         log_page_size[0x6];
 
-	u8         reserved_at_1e0[0x20];
+	u8         reserved_at_1e0[0x5];
+	u8         pcie_tph_en[0x1];
+	u8         pcie_tph_ph[0x2];
+	u8         pcie_tph_steering_tag_index[0x8];
+	u8         reserved_at_1f0[0x10];
 };
 
 struct mlx5_ifc_pkey_bits {
@@ -4125,7 +4551,8 @@ struct mlx5_ifc_hca_vport_context_bits {
 	u8         has_smi[0x1];
 	u8         has_raw[0x1];
 	u8         grh_required[0x1];
-	u8         reserved_at_104[0xc];
+	u8         reserved_at_104[0x4];
+	u8         num_port_plane[0x8];
 	u8         port_physical_state[0x4];
 	u8         vport_state_policy[0x4];
 	u8         port_state[0x4];
@@ -4265,7 +4692,8 @@ struct mlx5_ifc_dctc_bits {
 	u8         state[0x4];
 	u8         reserved_at_8[0x18];
 
-	u8         reserved_at_20[0x8];
+	u8         reserved_at_20[0x7];
+	u8         dp_ordering_force[0x1];
 	u8         user_index[0x18];
 
 	u8         reserved_at_40[0x8];
@@ -4280,7 +4708,9 @@ struct mlx5_ifc_dctc_bits {
 	u8         latency_sensitive[0x1];
 	u8         rlky[0x1];
 	u8         free_ar[0x1];
-	u8         reserved_at_73[0xd];
+	u8         reserved_at_73[0x1];
+	u8         dp_ordering_1[0x1];
+	u8         reserved_at_75[0xb];
 
 	u8         reserved_at_80[0x8];
 	u8         cs_res[0x8];
@@ -4339,10 +4769,10 @@ enum {
 	MLX5_CQC_ST_FIRED                                 = 0xa,
 };
 
-enum {
+enum mlx5_cq_period_mode {
 	MLX5_CQ_PERIOD_MODE_START_FROM_EQE = 0x0,
 	MLX5_CQ_PERIOD_MODE_START_FROM_CQE = 0x1,
-	MLX5_CQ_PERIOD_NUM_MODES
+	MLX5_CQ_PERIOD_NUM_MODES,
 };
 
 struct mlx5_ifc_cqc_bits {
@@ -4484,6 +4914,11 @@ union mlx5_ifc_field_select_802_1_r_roce_auto_bits {
 	u8         reserved_at_0[0x20];
 };
 
+struct mlx5_ifc_rs_histogram_cntrs_bits {
+	u8         hist[16][0x40];
+	u8         reserved_at_400[0x2c0];
+};
+
 union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_eth_802_3_cntrs_grp_data_layout_bits eth_802_3_cntrs_grp_data_layout;
 	struct mlx5_ifc_eth_2863_cntrs_grp_data_layout_bits eth_2863_cntrs_grp_data_layout;
@@ -4494,8 +4929,11 @@ union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits {
 	struct mlx5_ifc_eth_per_tc_prio_grp_data_layout_bits eth_per_tc_prio_grp_data_layout;
 	struct mlx5_ifc_eth_per_tc_congest_prio_grp_data_layout_bits eth_per_tc_congest_prio_grp_data_layout;
 	struct mlx5_ifc_ib_port_cntrs_grp_data_layout_bits ib_port_cntrs_grp_data_layout;
+	struct mlx5_ifc_ib_ext_port_cntrs_grp_data_layout_bits ib_ext_port_cntrs_grp_data_layout;
 	struct mlx5_ifc_phys_layer_cntrs_bits phys_layer_cntrs;
 	struct mlx5_ifc_phys_layer_statistical_cntrs_bits phys_layer_statistical_cntrs;
+	struct mlx5_ifc_phys_layer_recovery_cntrs_bits phys_layer_recovery_cntrs;
+	struct mlx5_ifc_rs_histogram_cntrs_bits rs_histogram_cntrs;
 	u8         reserved_at_0[0x7c0];
 };
 
@@ -4555,29 +4993,6 @@ struct mlx5_ifc_register_loopback_control_bits {
 	u8         reserved_at_20[0x60];
 };
 
-struct mlx5_ifc_vport_tc_element_bits {
-	u8         traffic_class[0x4];
-	u8         reserved_at_4[0xc];
-	u8         vport_number[0x10];
-};
-
-struct mlx5_ifc_vport_element_bits {
-	u8         reserved_at_0[0x10];
-	u8         vport_number[0x10];
-};
-
-enum {
-	TSAR_ELEMENT_TSAR_TYPE_DWRR = 0x0,
-	TSAR_ELEMENT_TSAR_TYPE_ROUND_ROBIN = 0x1,
-	TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2,
-};
-
-struct mlx5_ifc_tsar_element_bits {
-	u8         reserved_at_0[0x8];
-	u8         tsar_type[0x8];
-	u8         reserved_at_10[0x10];
-};
-
 enum {
 	MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_SUCCESS = 0x0,
 	MLX5_TEARDOWN_HCA_OUT_FORCE_STATE_FAIL = 0x1,
@@ -4749,7 +5164,10 @@ struct mlx5_ifc_set_l2_table_entry_in_bits {
 
 	u8         reserved_at_c0[0x20];
 
-	u8         reserved_at_e0[0x13];
+	u8         reserved_at_e0[0x10];
+	u8         silent_mode_valid[0x1];
+	u8         silent_mode[0x1];
+	u8         reserved_at_f2[0x1];
 	u8         vlan_valid[0x1];
 	u8         vlan[0xc];
 
@@ -4797,7 +5215,10 @@ struct mlx5_ifc_set_hca_cap_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_function[0x1];
-	u8         reserved_at_41[0xf];
+	u8         ec_vf_function[0x1];
+	u8         reserved_at_42[0x1];
+	u8         function_id_type[0x1];
+	u8         reserved_at_44[0xc];
 	u8         function_id[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -4830,13 +5251,15 @@ struct mlx5_ifc_set_fte_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x8];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -4854,6 +5277,16 @@ struct mlx5_ifc_set_fte_in_bits {
 	struct mlx5_ifc_flow_context_bits flow_context;
 };
 
+struct mlx5_ifc_dest_format_bits {
+	u8         destination_type[0x8];
+	u8         destination_id[0x18];
+
+	u8         destination_eswitch_owner_vhca_id_valid[0x1];
+	u8         packet_reformat[0x1];
+	u8         reserved_at_22[0xe];
+	u8         destination_eswitch_owner_vhca_id[0x10];
+};
+
 struct mlx5_ifc_rts2rts_qp_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -5017,6 +5450,36 @@ struct mlx5_ifc_query_vport_state_out_bits {
 	u8         state[0x4];
 };
 
+struct mlx5_ifc_array1024_auto_bits {
+	u8         array1024_auto[32][0x20];
+};
+
+struct mlx5_ifc_query_vuid_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x40];
+
+	u8         query_vfs_vuid[0x1];
+	u8         data_direct[0x1];
+	u8         reserved_at_62[0xe];
+	u8         vhca_id[0x10];
+};
+
+struct mlx5_ifc_query_vuid_out_bits {
+	u8        status[0x8];
+	u8        reserved_at_8[0x18];
+
+	u8        syndrome[0x20];
+
+	u8        reserved_at_40[0x1a0];
+
+	u8        reserved_at_1e0[0x10];
+	u8        num_of_entries[0x10];
+
+	struct mlx5_ifc_array1024_auto_bits vuid[];
+};
+
 enum {
 	MLX5_VPORT_STATE_OP_MOD_VNIC_VPORT  = 0x0,
 	MLX5_VPORT_STATE_OP_MOD_ESW_VPORT   = 0x1,
@@ -5175,7 +5638,9 @@ struct mlx5_ifc_query_vport_counter_out_bits {
 
 	struct mlx5_ifc_traffic_counter_bits transmitted_eth_multicast;
 
-	u8         reserved_at_680[0xa00];
+	struct mlx5_ifc_traffic_counter_bits local_loopback;
+
+	u8         reserved_at_700[0x980];
 };
 
 enum {
@@ -5576,7 +6041,11 @@ struct mlx5_ifc_query_q_counter_out_bits {
 
 	u8         local_ack_timeout_err[0x20];
 
-	u8         reserved_at_320[0xa0];
+	u8         reserved_at_320[0x60];
+
+	u8         req_rnr_retries_exceeded[0x20];
+
+	u8         reserved_at_3a0[0x20];
 
 	u8         resp_local_length_error[0x20];
 
@@ -5948,7 +6417,10 @@ struct mlx5_ifc_query_hca_cap_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_function[0x1];
-	u8         reserved_at_41[0xf];
+	u8         ec_vf_function[0x1];
+	u8         reserved_at_42[0x1];
+	u8         function_id_type[0x1];
+	u8         reserved_at_44[0xc];
 	u8         function_id[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -6006,6 +6478,20 @@ struct mlx5_ifc_modify_other_hca_cap_in_bits {
 	struct     mlx5_ifc_other_hca_cap_bits other_capability;
 };
 
+struct mlx5_ifc_sw_owner_icm_root_params_bits {
+	u8         sw_owner_icm_root_1[0x40];
+
+	u8         sw_owner_icm_root_0[0x40];
+};
+
+struct mlx5_ifc_rtc_params_bits {
+	u8         rtc_id_0[0x20];
+
+	u8         rtc_id_1[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_flow_table_context_bits {
 	u8         reformat_en[0x1];
 	u8         decap_en[0x1];
@@ -6013,7 +6499,8 @@ struct mlx5_ifc_flow_table_context_bits {
 	u8         termination_table[0x1];
 	u8         table_miss_action[0x4];
 	u8         level[0x8];
-	u8         reserved_at_10[0x8];
+	u8         rtc_valid[0x1];
+	u8         reserved_at_11[0x7];
 	u8         log_size[0x8];
 
 	u8         reserved_at_20[0x8];
@@ -6024,10 +6511,10 @@ struct mlx5_ifc_flow_table_context_bits {
 
 	u8         reserved_at_60[0x60];
 
-	u8         sw_owner_icm_root_1[0x40];
-
-	u8         sw_owner_icm_root_0[0x40];
-
+	union {
+		struct mlx5_ifc_sw_owner_icm_root_params_bits sws;
+		struct mlx5_ifc_rtc_params_bits hws;
+	};
 };
 
 struct mlx5_ifc_query_flow_table_out_bits {
@@ -6391,6 +6878,28 @@ struct mlx5_ifc_general_obj_out_cmd_hdr_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_allow_other_vhca_access_in_bits {
+	u8 opcode[0x10];
+	u8 uid[0x10];
+	u8 reserved_at_20[0x10];
+	u8 op_mod[0x10];
+	u8 reserved_at_40[0x50];
+	u8 object_type_to_be_accessed[0x10];
+	u8 object_id_to_be_accessed[0x20];
+	u8 reserved_at_c0[0x40];
+	union {
+		u8 access_key_raw[0x100];
+		u8 access_key[8][0x20];
+	};
+};
+
+struct mlx5_ifc_allow_other_vhca_access_out_bits {
+	u8 status[0x8];
+	u8 reserved_at_8[0x18];
+	u8 syndrome[0x20];
+	u8 reserved_at_40[0x40];
+};
+
 struct mlx5_ifc_modify_header_arg_bits {
 	u8         reserved_at_0[0x80];
 
@@ -6413,6 +6922,24 @@ struct mlx5_ifc_create_match_definer_out_bits {
 	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
 };
 
+struct mlx5_ifc_alias_context_bits {
+	u8 vhca_id_to_be_accessed[0x10];
+	u8 reserved_at_10[0xd];
+	u8 status[0x3];
+	u8 object_id_to_be_accessed[0x20];
+	u8 reserved_at_40[0x40];
+	union {
+		u8 access_key_raw[0x100];
+		u8 access_key[8][0x20];
+	};
+	u8 metadata[0x80];
+};
+
+struct mlx5_ifc_create_alias_obj_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_alias_context_bits alias_ctx;
+};
+
 enum {
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_OUTER_HEADERS    = 0x0,
 	MLX5_QUERY_FLOW_GROUP_OUT_MATCH_CRITERIA_ENABLE_MISC_PARAMETERS  = 0x1,
@@ -6519,6 +7046,28 @@ struct mlx5_ifc_query_esw_vport_context_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_destroy_esw_vport_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x20];
+};
+
+struct mlx5_ifc_destroy_esw_vport_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         vport_num[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_modify_esw_vport_context_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -6635,6 +7184,7 @@ struct mlx5_ifc_alloc_packet_reformat_context_out_bits {
 
 enum {
 	MLX5_REFORMAT_CONTEXT_ANCHOR_MAC_START = 0x1,
+	MLX5_REFORMAT_CONTEXT_ANCHOR_VLAN_START = 0x2,
 	MLX5_REFORMAT_CONTEXT_ANCHOR_IP_START = 0x7,
 	MLX5_REFORMAT_CONTEXT_ANCHOR_TCP_UDP_START = 0x9,
 };
@@ -6647,9 +7197,14 @@ enum mlx5_reformat_ctx_type {
 	MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4,
 	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5,
 	MLX5_REFORMAT_TYPE_L2_TO_L3_ESP_TUNNEL = 0x6,
+	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV4 = 0x7,
 	MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8,
 	MLX5_REFORMAT_TYPE_L3_ESP_TUNNEL_TO_L2 = 0x9,
+	MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT_OVER_UDP = 0xa,
 	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb,
+	MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_UDPV6 = 0xc,
+	MLX5_REFORMAT_TYPE_ADD_PSP_TUNNEL = 0xd,
+	MLX5_REFORMAT_TYPE_DEL_PSP_TUNNEL = 0xe,
 	MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf,
 	MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10,
 	MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11,
@@ -6776,6 +7331,7 @@ enum {
 	MLX5_ACTION_IN_FIELD_IPSEC_SYNDROME    = 0x5D,
 	MLX5_ACTION_IN_FIELD_OUT_EMD_47_32     = 0x6F,
 	MLX5_ACTION_IN_FIELD_OUT_EMD_31_0      = 0x70,
+	MLX5_ACTION_IN_FIELD_PSP_SYNDROME      = 0x71,
 };
 
 struct mlx5_ifc_alloc_modify_header_context_out_bits {
@@ -7016,6 +7572,85 @@ struct mlx5_ifc_query_adapter_in_bits {
 	u8         reserved_at_40[0x40];
 };
 
+struct mlx5_ifc_function_vhca_rid_info_reg_bits {
+	u8         host_number[0x8];
+	u8         host_pci_device_function[0x8];
+	u8         host_pci_bus[0x8];
+	u8         reserved_at_18[0x3];
+	u8         pci_bus_assigned[0x1];
+	u8         function_type[0x4];
+
+	u8         parent_pci_device_function[0x8];
+	u8         parent_pci_bus[0x8];
+	u8         vhca_id[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         function_id[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
+struct mlx5_ifc_delegated_function_vhca_rid_info_bits {
+	struct mlx5_ifc_function_vhca_rid_info_reg_bits function_vhca_rid_info;
+
+	u8         reserved_at_80[0x18];
+	u8         manage_profile[0x8];
+
+	u8         reserved_at_a0[0x60];
+};
+
+struct mlx5_ifc_query_delegated_vhca_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x20];
+
+	u8         reserved_at_60[0x10];
+	u8         functions_count[0x10];
+
+	u8         reserved_at_80[0x80];
+
+	struct mlx5_ifc_delegated_function_vhca_rid_info_bits
+			delegated_function_vhca_rid_info[];
+};
+
+struct mlx5_ifc_query_delegated_vhca_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_create_esw_vport_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x20];
+
+	u8         reserved_at_60[0x10];
+	u8         vport_num[0x10];
+};
+
+struct mlx5_ifc_create_esw_vport_in_bits {
+	u8         opcode[0x10];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x10];
+	u8         managed_vhca_id[0x10];
+
+	u8         reserved_at_60[0x20];
+};
+
 struct mlx5_ifc_qp_2rst_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -7060,6 +7695,30 @@ struct mlx5_ifc_qp_2err_in_bits {
 	u8         reserved_at_60[0x20];
 };
 
+struct mlx5_ifc_trans_page_fault_info_bits {
+	u8         error[0x1];
+	u8         reserved_at_1[0x4];
+	u8         page_fault_type[0x3];
+	u8         wq_number[0x18];
+
+	u8         reserved_at_20[0x8];
+	u8         fault_token[0x18];
+};
+
+struct mlx5_ifc_mem_page_fault_info_bits {
+	u8          error[0x1];
+	u8          reserved_at_1[0xf];
+	u8          fault_token_47_32[0x10];
+
+	u8          fault_token_31_0[0x20];
+};
+
+union mlx5_ifc_page_fault_resume_in_page_fault_info_auto_bits {
+	struct mlx5_ifc_trans_page_fault_info_bits trans_page_fault_info;
+	struct mlx5_ifc_mem_page_fault_info_bits mem_page_fault_info;
+	u8          reserved_at_0[0x40];
+};
+
 struct mlx5_ifc_page_fault_resume_out_bits {
 	u8         status[0x8];
 	u8         reserved_at_8[0x18];
@@ -7076,13 +7735,8 @@ struct mlx5_ifc_page_fault_resume_in_bits {
 	u8         reserved_at_20[0x10];
 	u8         op_mod[0x10];
 
-	u8         error[0x1];
-	u8         reserved_at_41[0x4];
-	u8         page_fault_type[0x3];
-	u8         wq_number[0x18];
-
-	u8         reserved_at_60[0x8];
-	u8         token[0x18];
+	union mlx5_ifc_page_fault_resume_in_page_fault_info_auto_bits
+		page_fault_info;
 };
 
 struct mlx5_ifc_nop_out_bits {
@@ -7124,7 +7778,12 @@ struct mlx5_ifc_modify_vport_state_in_bits {
 	u8         reserved_at_41[0xf];
 	u8         vport_number[0x10];
 
-	u8         reserved_at_60[0x18];
+	u8         reserved_at_60[0x10];
+	u8         ingress_connect[0x1];
+	u8         egress_connect[0x1];
+	u8         ingress_connect_valid[0x1];
+	u8         egress_connect_valid[0x1];
+	u8         reserved_at_74[0x4];
 	u8         admin_state[0x4];
 	u8         reserved_at_7c[0x4];
 };
@@ -7591,7 +8250,7 @@ struct mlx5_ifc_mad_ifc_in_bits {
 	u8         op_mod[0x10];
 
 	u8         remote_lid[0x10];
-	u8         reserved_at_50[0x8];
+	u8         plane_index[0x8];
 	u8         port[0x8];
 
 	u8         reserved_at_60[0x20];
@@ -8152,13 +8811,15 @@ struct mlx5_ifc_destroy_flow_table_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x8];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -8183,13 +8844,15 @@ struct mlx5_ifc_destroy_flow_group_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x8];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -8328,13 +8991,15 @@ struct mlx5_ifc_delete_fte_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x8];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -8766,7 +9431,9 @@ struct mlx5_ifc_create_qp_in_bits {
 
 	struct mlx5_ifc_qpc_bits qpc;
 
-	u8         reserved_at_800[0x60];
+	u8         wq_umem_offset[0x40];
+
+	u8         wq_umem_id[0x20];
 
 	u8         wq_umem_valid[0x1];
 	u8         reserved_at_861[0x1f];
@@ -8832,7 +9499,8 @@ struct mlx5_ifc_create_mkey_in_bits {
 
 	u8         pg_access[0x1];
 	u8         mkey_umem_valid[0x1];
-	u8         reserved_at_62[0x1e];
+	u8         data_direct[0x1];
+	u8         reserved_at_63[0x1d];
 
 	struct mlx5_ifc_mkc_bits memory_key_mkey_entry;
 
@@ -8875,13 +9543,15 @@ struct mlx5_ifc_create_flow_table_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x20];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x8];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x20];
 
@@ -8920,7 +9590,8 @@ struct mlx5_ifc_create_flow_group_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -8928,7 +9599,7 @@ struct mlx5_ifc_create_flow_group_in_bits {
 	u8         table_type[0x8];
 	u8         reserved_at_88[0x4];
 	u8         group_type[0x4];
-	u8         reserved_at_90[0x10];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -9514,13 +10185,19 @@ struct mlx5_ifc_pude_reg_bits {
 	u8         reserved_at_20[0x60];
 };
 
+enum {
+	MLX5_PTYS_CONNECTOR_TYPE_PORT_DA = 0x7,
+};
+
 struct mlx5_ifc_ptys_reg_bits {
 	u8         reserved_at_0[0x1];
 	u8         an_disable_admin[0x1];
 	u8         an_disable_cap[0x1];
 	u8         reserved_at_3[0x5];
 	u8         local_port[0x8];
-	u8         reserved_at_10[0xd];
+	u8         reserved_at_10[0x8];
+	u8         plane_ind[0x4];
+	u8         reserved_at_1c[0x1];
 	u8         proto_mask[0x3];
 
 	u8         an_status[0x4];
@@ -9548,7 +10225,8 @@ struct mlx5_ifc_ptys_reg_bits {
 	u8         ib_link_width_oper[0x10];
 	u8         ib_proto_oper[0x10];
 
-	u8         reserved_at_160[0x1c];
+	u8         reserved_at_160[0x8];
+	u8         lane_rate_oper[0x14];
 	u8         connector_type[0x4];
 
 	u8         eth_proto_lp_advertise[0x20];
@@ -9721,7 +10399,35 @@ struct mlx5_ifc_pplm_reg_bits {
 	u8         fec_override_admin_100g_2x[0x10];
 	u8         fec_override_admin_50g_1x[0x10];
 
-	u8         reserved_at_140[0x140];
+	u8         fec_override_cap_800g_8x[0x10];
+	u8         fec_override_cap_400g_4x[0x10];
+
+	u8         fec_override_cap_200g_2x[0x10];
+	u8         fec_override_cap_100g_1x[0x10];
+
+	u8         reserved_at_180[0xa0];
+
+	u8         fec_override_admin_800g_8x[0x10];
+	u8         fec_override_admin_400g_4x[0x10];
+
+	u8         fec_override_admin_200g_2x[0x10];
+	u8         fec_override_admin_100g_1x[0x10];
+
+	u8         reserved_at_260[0x60];
+
+	u8         fec_override_cap_1600g_8x[0x10];
+	u8         fec_override_cap_800g_4x[0x10];
+
+	u8         fec_override_cap_400g_2x[0x10];
+	u8         fec_override_cap_200g_1x[0x10];
+
+	u8         fec_override_admin_1600g_8x[0x10];
+	u8         fec_override_admin_800g_4x[0x10];
+
+	u8         fec_override_admin_400g_2x[0x10];
+	u8         fec_override_admin_200g_1x[0x10];
+
+	u8         reserved_at_340[0x80];
 };
 
 struct mlx5_ifc_ppcnt_reg_bits {
@@ -9732,8 +10438,10 @@ struct mlx5_ifc_ppcnt_reg_bits {
 	u8         grp[0x6];
 
 	u8         clr[0x1];
-	u8         reserved_at_21[0x1c];
-	u8         prio_tc[0x3];
+	u8         reserved_at_21[0x13];
+	u8         plane_ind[0x4];
+	u8         reserved_at_38[0x3];
+	u8         prio_tc[0x5];
 
 	union mlx5_ifc_eth_cntrs_grp_data_layout_auto_bits counter_set;
 };
@@ -9962,10 +10670,19 @@ struct mlx5_ifc_pifr_reg_bits {
 	u8         port_filter_update_en[8][0x20];
 };
 
+enum {
+	MLX5_BUF_OWNERSHIP_UNKNOWN	= 0x0,
+	MLX5_BUF_OWNERSHIP_FW_OWNED	= 0x1,
+	MLX5_BUF_OWNERSHIP_SW_OWNED	= 0x2,
+};
+
 struct mlx5_ifc_pfcc_reg_bits {
-	u8         reserved_at_0[0x8];
+	u8         reserved_at_0[0x4];
+	u8	   buf_ownership[0x2];
+	u8	   reserved_at_6[0x2];
 	u8         local_port[0x8];
-	u8         reserved_at_10[0xb];
+	u8         reserved_at_10[0xa];
+	u8	   cable_length_mask[0x1];
 	u8         ppan_mask_n[0x1];
 	u8         minor_stall_mask[0x1];
 	u8         critical_stall_mask[0x1];
@@ -9994,7 +10711,10 @@ struct mlx5_ifc_pfcc_reg_bits {
 	u8         device_stall_minor_watermark[0x10];
 	u8         device_stall_critical_watermark[0x10];
 
-	u8         reserved_at_a0[0x60];
+	u8	   reserved_at_a0[0x18];
+	u8	   cable_length[0x8];
+
+	u8         reserved_at_c0[0x40];
 };
 
 struct mlx5_ifc_pelc_reg_bits {
@@ -10047,6 +10767,19 @@ struct mlx5_ifc_mpegc_reg_bits {
 	u8         reserved_at_60[0x100];
 };
 
+struct mlx5_ifc_mpir_reg_bits {
+	u8         sdm[0x1];
+	u8         reserved_at_1[0x1b];
+	u8         host_buses[0x4];
+
+	u8         reserved_at_20[0x20];
+
+	u8         local_port[0x8];
+	u8         reserved_at_28[0x18];
+
+	u8         reserved_at_60[0x20];
+};
+
 enum {
 	MLX5_MTUTC_FREQ_ADJ_UNITS_PPB          = 0x0,
 	MLX5_MTUTC_FREQ_ADJ_UNITS_SCALED_PPM   = 0x1,
@@ -10061,7 +10794,10 @@ enum {
 struct mlx5_ifc_mtutc_reg_bits {
 	u8         reserved_at_0[0x5];
 	u8         freq_adj_units[0x3];
-	u8         reserved_at_8[0x14];
+	u8         reserved_at_8[0x3];
+	u8         log_max_freq_adjustment[0x5];
+
+	u8         reserved_at_10[0xc];
 	u8         operation[0x4];
 
 	u8         freq_adjustment[0x20];
@@ -10077,7 +10813,17 @@ struct mlx5_ifc_mtutc_reg_bits {
 };
 
 struct mlx5_ifc_pcam_enhanced_features_bits {
-	u8         reserved_at_0[0x68];
+	u8         reserved_at_0[0x10];
+	u8         ppcnt_recovery_counters[0x1];
+	u8         reserved_at_11[0x7];
+	u8	   cable_length[0x1];
+	u8	   reserved_at_19[0x4];
+	u8         fec_200G_per_lane_in_pplm[0x1];
+	u8         reserved_at_1e[0x2a];
+	u8         fec_100G_per_lane_in_pplm[0x1];
+	u8         reserved_at_49[0xa];
+	u8	   buffer_ownership[0x1];
+	u8	   resereved_at_54[0x14];
 	u8         fec_50G_per_lane_in_pplm[0x1];
 	u8         reserved_at_69[0x4];
 	u8         rx_icrc_encapsulated_counter[0x1];
@@ -10098,7 +10844,9 @@ struct mlx5_ifc_pcam_regs_5000_to_507f_bits {
 	u8         port_access_reg_cap_mask_127_to_96[0x20];
 	u8         port_access_reg_cap_mask_95_to_64[0x20];
 
-	u8         port_access_reg_cap_mask_63_to_36[0x1c];
+	u8         port_access_reg_cap_mask_63[0x1];
+	u8         pphcr[0x1];
+	u8         port_access_reg_cap_mask_61_to_36[0x1a];
 	u8         pplm[0x1];
 	u8         port_access_reg_cap_mask_34_to_32[0x3];
 
@@ -10165,7 +10913,9 @@ struct mlx5_ifc_mcam_access_reg_bits {
 	u8         mcqi[0x1];
 	u8         mcqs[0x1];
 
-	u8         regs_95_to_87[0x9];
+	u8         regs_95_to_90[0x6];
+	u8         mpir[0x1];
+	u8         regs_88_to_87[0x2];
 	u8         mpegc[0x1];
 	u8         mtutc[0x1];
 	u8         regs_84_to_68[0x11];
@@ -10173,9 +10923,13 @@ struct mlx5_ifc_mcam_access_reg_bits {
 
 	u8         regs_63_to_46[0x12];
 	u8         mrtc[0x1];
-	u8         regs_44_to_32[0xd];
+	u8         regs_44_to_41[0x4];
+	u8         mfrl[0x1];
+	u8         regs_39_to_32[0x8];
 
-	u8         regs_31_to_0[0x20];
+	u8         regs_31_to_11[0x15];
+	u8         mtmp[0x1];
+	u8         regs_9_to_0[0xa];
 };
 
 struct mlx5_ifc_mcam_access_reg_bits1 {
@@ -10193,13 +10947,28 @@ struct mlx5_ifc_mcam_access_reg_bits2 {
 	u8         mirc[0x1];
 	u8         regs_97_to_96[0x2];
 
-	u8         regs_95_to_64[0x20];
+	u8         regs_95_to_87[0x09];
+	u8         synce_registers[0x2];
+	u8         regs_84_to_64[0x15];
 
 	u8         regs_63_to_32[0x20];
 
 	u8         regs_31_to_0[0x20];
 };
 
+struct mlx5_ifc_mcam_access_reg_bits3 {
+	u8         regs_127_to_96[0x20];
+
+	u8         regs_95_to_64[0x20];
+
+	u8         regs_63_to_32[0x20];
+
+	u8         regs_31_to_3[0x1d];
+	u8         mrtcq[0x1];
+	u8         mtctr[0x1];
+	u8         mtptm[0x1];
+};
+
 struct mlx5_ifc_mcam_reg_bits {
 	u8         reserved_at_0[0x8];
 	u8         feature_group[0x8];
@@ -10212,6 +10981,7 @@ struct mlx5_ifc_mcam_reg_bits {
 		struct mlx5_ifc_mcam_access_reg_bits access_regs;
 		struct mlx5_ifc_mcam_access_reg_bits1 access_regs1;
 		struct mlx5_ifc_mcam_access_reg_bits2 access_regs2;
+		struct mlx5_ifc_mcam_access_reg_bits3 access_regs3;
 		u8         reserved_at_0[0x80];
 	} mng_access_reg_cap_mask;
 
@@ -10569,6 +11339,7 @@ enum {
 	MLX5_INITIAL_SEG_NIC_INTERFACE_FULL_DRIVER  = 0x0,
 	MLX5_INITIAL_SEG_NIC_INTERFACE_DISABLED     = 0x1,
 	MLX5_INITIAL_SEG_NIC_INTERFACE_NO_DRAM_NIC  = 0x2,
+	MLX5_INITIAL_SEG_NIC_INTERFACE_SW_RESET     = 0x7,
 };
 
 enum {
@@ -10589,6 +11360,8 @@ enum {
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_EQ_INV                       = 0xe,
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_FFSER_ERR                    = 0xf,
 	MLX5_INITIAL_SEG_HEALTH_SYNDROME_HIGH_TEMP_ERR                = 0x10,
+	MLX5_INITIAL_SEG_HEALTH_SYNDROME_ICM_PCI_POISONED_ERR         = 0x12,
+	MLX5_INITIAL_SEG_HEALTH_SYNDROME_TRUST_LOCKDOWN_ERR           = 0x13,
 };
 
 struct mlx5_ifc_initial_seg_bits {
@@ -10832,11 +11605,17 @@ struct mlx5_ifc_mcda_reg_bits {
 };
 
 enum {
+	MLX5_MFRL_REG_PCI_RESET_METHOD_LINK_TOGGLE = 0,
+	MLX5_MFRL_REG_PCI_RESET_METHOD_HOT_RESET = 1,
+};
+
+enum {
 	MLX5_MFRL_REG_RESET_STATE_IDLE = 0,
 	MLX5_MFRL_REG_RESET_STATE_IN_NEGOTIATION = 1,
 	MLX5_MFRL_REG_RESET_STATE_RESET_IN_PROGRESS = 2,
-	MLX5_MFRL_REG_RESET_STATE_TIMEOUT = 3,
+	MLX5_MFRL_REG_RESET_STATE_NEG_TIMEOUT = 3,
 	MLX5_MFRL_REG_RESET_STATE_NACK = 4,
+	MLX5_MFRL_REG_RESET_STATE_UNLOAD_TIMEOUT = 5,
 };
 
 enum {
@@ -10857,7 +11636,8 @@ struct mlx5_ifc_mfrl_reg_bits {
 	u8         pci_sync_for_fw_update_start[0x1];
 	u8         pci_sync_for_fw_update_resp[0x2];
 	u8         rst_type_sel[0x3];
-	u8         reserved_at_28[0x4];
+	u8         pci_reset_req_method[0x3];
+	u8         reserved_at_2b[0x1];
 	u8         reset_state[0x4];
 	u8         reset_type[0x8];
 	u8         reset_level[0x8];
@@ -10928,6 +11708,15 @@ struct mlx5_ifc_mrtc_reg_bits {
 	u8         time_l[0x20];
 };
 
+struct mlx5_ifc_mtcap_reg_bits {
+	u8         reserved_at_0[0x19];
+	u8         sensor_count[0x7];
+
+	u8         reserved_at_20[0x20];
+
+	u8         sensor_map[0x40];
+};
+
 struct mlx5_ifc_mtmp_reg_bits {
 	u8         reserved_at_0[0x14];
 	u8         sensor_index[0xc];
@@ -10953,6 +11742,56 @@ struct mlx5_ifc_mtmp_reg_bits {
 	u8         sensor_name_lo[0x20];
 };
 
+struct mlx5_ifc_mtptm_reg_bits {
+	u8         reserved_at_0[0x10];
+	u8         psta[0x1];
+	u8         reserved_at_11[0xf];
+
+	u8         reserved_at_20[0x60];
+};
+
+enum {
+	MLX5_MTCTR_REQUEST_NOP = 0x0,
+	MLX5_MTCTR_REQUEST_PTM_ROOT_CLOCK = 0x1,
+	MLX5_MTCTR_REQUEST_FREE_RUNNING_COUNTER = 0x2,
+	MLX5_MTCTR_REQUEST_REAL_TIME_CLOCK = 0x3,
+};
+
+struct mlx5_ifc_mtctr_reg_bits {
+	u8         first_clock_timestamp_request[0x8];
+	u8         second_clock_timestamp_request[0x8];
+	u8         reserved_at_10[0x10];
+
+	u8         first_clock_valid[0x1];
+	u8         second_clock_valid[0x1];
+	u8         reserved_at_22[0x1e];
+
+	u8         first_clock_timestamp[0x40];
+	u8         second_clock_timestamp[0x40];
+};
+
+struct mlx5_ifc_bin_range_layout_bits {
+	u8         reserved_at_0[0xa];
+	u8         high_val[0x6];
+	u8         reserved_at_10[0xa];
+	u8         low_val[0x6];
+};
+
+struct mlx5_ifc_pphcr_reg_bits {
+	u8         active_hist_type[0x4];
+	u8         reserved_at_4[0x4];
+	u8         local_port[0x8];
+	u8         reserved_at_10[0x10];
+
+	u8         reserved_at_20[0x8];
+	u8         num_of_bins[0x8];
+	u8         reserved_at_30[0x10];
+
+	u8         reserved_at_40[0x40];
+
+	struct mlx5_ifc_bin_range_layout_bits bin_range[16];
+};
+
 union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_bufferx_reg_bits bufferx_reg;
 	struct mlx5_ifc_eth_2819_cntrs_grp_data_layout_bits eth_2819_cntrs_grp_data_layout;
@@ -11015,7 +11854,11 @@ union mlx5_ifc_ports_control_registers_document_bits {
 	struct mlx5_ifc_mfrl_reg_bits mfrl_reg;
 	struct mlx5_ifc_mtutc_reg_bits mtutc_reg;
 	struct mlx5_ifc_mrtc_reg_bits mrtc_reg;
+	struct mlx5_ifc_mtcap_reg_bits mtcap_reg;
 	struct mlx5_ifc_mtmp_reg_bits mtmp_reg;
+	struct mlx5_ifc_mtptm_reg_bits mtptm_reg;
+	struct mlx5_ifc_mtctr_reg_bits mtctr_reg;
+	struct mlx5_ifc_pphcr_reg_bits pphcr_reg;
 	u8         reserved_at_0[0x60e0];
 };
 
@@ -11046,10 +11889,12 @@ struct mlx5_ifc_set_flow_table_root_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
-	u8         reserved_at_60[0x20];
+	u8         reserved_at_60[0x10];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         table_type[0x8];
 	u8         reserved_at_88[0x7];
@@ -11089,14 +11934,16 @@ struct mlx5_ifc_modify_flow_table_in_bits {
 	u8         op_mod[0x10];
 
 	u8         other_vport[0x1];
-	u8         reserved_at_41[0xf];
+	u8         other_eswitch[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vport_number[0x10];
 
 	u8         reserved_at_60[0x10];
 	u8         modify_field_select[0x10];
 
 	u8         table_type[0x8];
-	u8         reserved_at_88[0x18];
+	u8         reserved_at_88[0x8];
+	u8         eswitch_owner_vhca_id[0x10];
 
 	u8         reserved_at_a0[0x8];
 	u8         table_id[0x18];
@@ -11788,7 +12635,9 @@ struct mlx5_ifc_mtrc_ctrl_bits {
 
 struct mlx5_ifc_host_params_context_bits {
 	u8         host_number[0x8];
-	u8         reserved_at_8[0x7];
+	u8         reserved_at_8[0x5];
+	u8         host_pf_not_exist[0x1];
+	u8         reserved_at_14[0x1];
 	u8         host_pf_disabled[0x1];
 	u8         host_num_of_vfs[0x10];
 
@@ -11910,19 +12759,33 @@ struct mlx5_ifc_affiliated_event_header_bits {
 };
 
 enum {
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24),
-};
-
-enum {
 	MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc,
 	MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13,
 	MLX5_GENERAL_OBJECT_TYPES_SAMPLER = 0x20,
 	MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = 0x24,
 	MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27,
 	MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47,
+	MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL = 0x53,
+	MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT = 0x58,
+	MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15,
+};
+
+enum {
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_IPSEC),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_SAMPLER),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO),
+};
+
+enum {
+	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL - 0x40),
+	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT - 0x40),
 };
 
 enum {
@@ -11942,6 +12805,13 @@ enum {
 	MLX5_IPSEC_ASO_INC_SN            = 0x2,
 };
 
+enum {
+	MLX5_IPSEC_ASO_REPLAY_WIN_32BIT  = 0x0,
+	MLX5_IPSEC_ASO_REPLAY_WIN_64BIT  = 0x1,
+	MLX5_IPSEC_ASO_REPLAY_WIN_128BIT = 0x2,
+	MLX5_IPSEC_ASO_REPLAY_WIN_256BIT = 0x3,
+};
+
 struct mlx5_ifc_ipsec_aso_bits {
 	u8         valid[0x1];
 	u8         reserved_at_201[0x1];
@@ -12294,6 +13164,7 @@ enum {
 	MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_TLS = 0x1,
 	MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_IPSEC = 0x2,
 	MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_MACSEC = 0x4,
+	MLX5_GENERAL_OBJECT_TYPE_ENCRYPTION_KEY_PURPOSE_PSP = 0x6,
 };
 
 struct mlx5_ifc_tls_static_params_bits {
@@ -12398,7 +13269,8 @@ struct mlx5_ifc_query_vhca_migration_state_in_bits {
 	u8         op_mod[0x10];
 
 	u8         incremental[0x1];
-	u8         reserved_at_41[0xf];
+	u8         chunk[0x1];
+	u8         reserved_at_42[0xe];
 	u8         vhca_id[0x10];
 
 	u8         reserved_at_60[0x20];
@@ -12414,7 +13286,11 @@ struct mlx5_ifc_query_vhca_migration_state_out_bits {
 
 	u8         required_umem_size[0x20];
 
-	u8         reserved_at_a0[0x160];
+	u8         reserved_at_a0[0x20];
+
+	u8         remaining_total_size[0x40];
+
+	u8         reserved_at_100[0x100];
 };
 
 struct mlx5_ifc_save_vhca_state_in_bits {
@@ -12446,7 +13322,7 @@ struct mlx5_ifc_save_vhca_state_out_bits {
 
 	u8         actual_image_size[0x20];
 
-	u8         reserved_at_60[0x20];
+	u8         next_required_umem_size[0x20];
 };
 
 struct mlx5_ifc_load_vhca_state_in_bits {
@@ -12477,6 +13353,44 @@ struct mlx5_ifc_load_vhca_state_out_bits {
 	u8         reserved_at_40[0x40];
 };
 
+struct mlx5_ifc_adv_rdma_cap_bits {
+	u8         rdma_transport_manager[0x1];
+	u8         rdma_transport_manager_other_eswitch[0x1];
+	u8         reserved_at_2[0x1e];
+
+	u8         rcx_type[0x8];
+	u8         reserved_at_28[0x2];
+	u8         ps_entry_log_max_value[0x6];
+	u8         reserved_at_30[0x6];
+	u8         qp_max_ps_num_entry[0xa];
+
+	u8         mp_max_num_queues[0x8];
+	u8         ps_user_context_max_log_size[0x8];
+	u8         message_based_qp_and_striding_wq[0x8];
+	u8         reserved_at_58[0x8];
+
+	u8         max_receive_send_message_size_stride[0x10];
+	u8         reserved_at_70[0x10];
+
+	u8         max_receive_send_message_size_byte[0x20];
+
+	u8         reserved_at_a0[0x160];
+
+	struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_rx_flow_table_properties;
+
+	struct mlx5_ifc_flow_table_prop_layout_bits rdma_transport_tx_flow_table_properties;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_support_2;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_support_2;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_rx_ft_field_bitmask_support_2;
+
+	struct mlx5_ifc_flow_table_fields_supported_2_bits rdma_transport_tx_ft_field_bitmask_support_2;
+
+	u8         reserved_at_800[0x3800];
+};
+
 struct mlx5_ifc_adv_virtualization_cap_bits {
 	u8         reserved_at_0[0x3];
 	u8         pg_track_log_max_num[0x5];
@@ -12555,4 +13469,177 @@ struct mlx5_ifc_modify_page_track_obj_in_bits {
 	struct mlx5_ifc_page_track_bits obj_context;
 };
 
+struct mlx5_ifc_query_page_track_obj_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits general_obj_out_cmd_hdr;
+	struct mlx5_ifc_page_track_bits obj_context;
+};
+
+struct mlx5_ifc_msecq_reg_bits {
+	u8         reserved_at_0[0x20];
+
+	u8         reserved_at_20[0x12];
+	u8         network_option[0x2];
+	u8         local_ssm_code[0x4];
+	u8         local_enhanced_ssm_code[0x8];
+
+	u8         local_clock_identity[0x40];
+
+	u8         reserved_at_80[0x180];
+};
+
+enum {
+	MLX5_MSEES_FIELD_SELECT_ENABLE			= BIT(0),
+	MLX5_MSEES_FIELD_SELECT_ADMIN_STATUS		= BIT(1),
+	MLX5_MSEES_FIELD_SELECT_ADMIN_FREQ_MEASURE	= BIT(2),
+};
+
+enum mlx5_msees_admin_status {
+	MLX5_MSEES_ADMIN_STATUS_FREE_RUNNING		= 0x0,
+	MLX5_MSEES_ADMIN_STATUS_TRACK			= 0x1,
+};
+
+enum mlx5_msees_oper_status {
+	MLX5_MSEES_OPER_STATUS_FREE_RUNNING		= 0x0,
+	MLX5_MSEES_OPER_STATUS_SELF_TRACK		= 0x1,
+	MLX5_MSEES_OPER_STATUS_OTHER_TRACK		= 0x2,
+	MLX5_MSEES_OPER_STATUS_HOLDOVER			= 0x3,
+	MLX5_MSEES_OPER_STATUS_FAIL_HOLDOVER		= 0x4,
+	MLX5_MSEES_OPER_STATUS_FAIL_FREE_RUNNING	= 0x5,
+};
+
+enum mlx5_msees_failure_reason {
+	MLX5_MSEES_FAILURE_REASON_UNDEFINED_ERROR		= 0x0,
+	MLX5_MSEES_FAILURE_REASON_PORT_DOWN			= 0x1,
+	MLX5_MSEES_FAILURE_REASON_TOO_HIGH_FREQUENCY_DIFF	= 0x2,
+	MLX5_MSEES_FAILURE_REASON_NET_SYNCHRONIZER_DEVICE_ERROR	= 0x3,
+	MLX5_MSEES_FAILURE_REASON_LACK_OF_RESOURCES		= 0x4,
+};
+
+struct mlx5_ifc_msees_reg_bits {
+	u8         reserved_at_0[0x8];
+	u8         local_port[0x8];
+	u8         pnat[0x2];
+	u8         lp_msb[0x2];
+	u8         reserved_at_14[0xc];
+
+	u8         field_select[0x20];
+
+	u8         admin_status[0x4];
+	u8         oper_status[0x4];
+	u8         ho_acq[0x1];
+	u8         reserved_at_49[0xc];
+	u8         admin_freq_measure[0x1];
+	u8         oper_freq_measure[0x1];
+	u8         failure_reason[0x9];
+
+	u8         frequency_diff[0x20];
+
+	u8         reserved_at_80[0x180];
+};
+
+struct mlx5_ifc_mrtcq_reg_bits {
+	u8         reserved_at_0[0x40];
+
+	u8         rt_clock_identity[0x40];
+
+	u8         reserved_at_80[0x180];
+};
+
+struct mlx5_ifc_pcie_cong_event_obj_bits {
+	u8         modify_select_field[0x40];
+
+	u8         inbound_event_en[0x1];
+	u8         outbound_event_en[0x1];
+	u8         reserved_at_42[0x1e];
+
+	u8         reserved_at_60[0x1];
+	u8         inbound_cong_state[0x3];
+	u8         reserved_at_64[0x1];
+	u8         outbound_cong_state[0x3];
+	u8         reserved_at_68[0x18];
+
+	u8         inbound_cong_low_threshold[0x10];
+	u8         inbound_cong_high_threshold[0x10];
+
+	u8         outbound_cong_low_threshold[0x10];
+	u8         outbound_cong_high_threshold[0x10];
+
+	u8         reserved_at_e0[0x340];
+};
+
+struct mlx5_ifc_pcie_cong_event_cmd_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_pcie_cong_event_obj_bits cong_obj;
+};
+
+struct mlx5_ifc_pcie_cong_event_cmd_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits hdr;
+	struct mlx5_ifc_pcie_cong_event_obj_bits cong_obj;
+};
+
+enum mlx5e_pcie_cong_event_mod_field {
+	MLX5_PCIE_CONG_EVENT_MOD_EVENT_EN = BIT(0),
+	MLX5_PCIE_CONG_EVENT_MOD_THRESH   = BIT(2),
+};
+
+struct mlx5_ifc_psp_rotate_key_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x40];
+};
+
+struct mlx5_ifc_psp_rotate_key_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x40];
+};
+
+enum mlx5_psp_gen_spi_in_key_size {
+	MLX5_PSP_GEN_SPI_IN_KEY_SIZE_128 = 0x0,
+	MLX5_PSP_GEN_SPI_IN_KEY_SIZE_256 = 0x1,
+};
+
+struct mlx5_ifc_key_spi_bits {
+	u8         spi[0x20];
+
+	u8         reserved_at_20[0x60];
+
+	u8         key[8][0x20];
+};
+
+struct mlx5_ifc_psp_gen_spi_in_bits {
+	u8         opcode[0x10];
+	u8         uid[0x10];
+
+	u8         reserved_at_20[0x10];
+	u8         op_mod[0x10];
+
+	u8         reserved_at_40[0x20];
+
+	u8         key_size[0x2];
+	u8         reserved_at_62[0xe];
+	u8         num_of_spi[0x10];
+};
+
+struct mlx5_ifc_psp_gen_spi_out_bits {
+	u8         status[0x8];
+	u8         reserved_at_8[0x18];
+
+	u8         syndrome[0x20];
+
+	u8         reserved_at_40[0x10];
+	u8         num_of_spi[0x10];
+
+	u8         reserved_at_60[0x20];
+
+	struct mlx5_ifc_key_spi_bits key_spi[];
+};
+
 #endif /* MLX5_IFC_H */
diff --git a/include/linux/mlx5/mlx5_ifc_vdpa.h b/include/linux/mlx5/mlx5_ifc_vdpa.h
index 9becdc3fa503..58dfa2ee7c83 100644
--- a/include/linux/mlx5/mlx5_ifc_vdpa.h
+++ b/include/linux/mlx5/mlx5_ifc_vdpa.h
@@ -74,7 +74,11 @@ struct mlx5_ifc_virtio_q_bits {
 	u8    reserved_at_320[0x8];
 	u8    pd[0x18];
 
-	u8    reserved_at_340[0xc0];
+	u8    reserved_at_340[0x20];
+
+	u8    desc_group_mkey[0x20];
+
+	u8    reserved_at_380[0x80];
 };
 
 struct mlx5_ifc_virtio_net_q_object_bits {
@@ -141,6 +145,13 @@ enum {
 	MLX5_VIRTQ_MODIFY_MASK_STATE                    = (u64)1 << 0,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_PARAMS      = (u64)1 << 3,
 	MLX5_VIRTQ_MODIFY_MASK_DIRTY_BITMAP_DUMP_ENABLE = (u64)1 << 4,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_ADDRS           = (u64)1 << 6,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_AVAIL_IDX       = (u64)1 << 7,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_USED_IDX        = (u64)1 << 8,
+	MLX5_VIRTQ_MODIFY_MASK_QUEUE_VIRTIO_VERSION	= (u64)1 << 10,
+	MLX5_VIRTQ_MODIFY_MASK_VIRTIO_Q_MKEY            = (u64)1 << 11,
+	MLX5_VIRTQ_MODIFY_MASK_QUEUE_FEATURES		= (u64)1 << 12,
+	MLX5_VIRTQ_MODIFY_MASK_DESC_GROUP_MKEY          = (u64)1 << 14,
 };
 
 enum {
diff --git a/include/linux/mlx5/port.h b/include/linux/mlx5/port.h
index 98b2e1e149f9..1df9d9a57bbc 100644
--- a/include/linux/mlx5/port.h
+++ b/include/linux/mlx5/port.h
@@ -61,15 +61,6 @@ enum mlx5_an_status {
 #define MLX5_EEPROM_PAGE_LENGTH		256
 #define MLX5_EEPROM_HIGH_PAGE_LENGTH	128
 
-struct mlx5_module_eeprom_query_params {
-	u16 size;
-	u16 offset;
-	u16 i2c_address;
-	u32 page;
-	u32 bank;
-	u32 module_number;
-};
-
 enum mlx5e_link_mode {
 	MLX5E_1000BASE_CX_SGMII	 = 0,
 	MLX5E_1000BASE_KX	 = 1,
@@ -115,8 +106,13 @@ enum mlx5e_ext_link_mode {
 	MLX5E_100GAUI_1_100GBASE_CR_KR		= 11,
 	MLX5E_200GAUI_4_200GBASE_CR4_KR4	= 12,
 	MLX5E_200GAUI_2_200GBASE_CR2_KR2	= 13,
-	MLX5E_400GAUI_8				= 15,
+	MLX5E_200GAUI_1_200GBASE_CR1_KR1	= 14,
+	MLX5E_400GAUI_8_400GBASE_CR8		= 15,
 	MLX5E_400GAUI_4_400GBASE_CR4_KR4	= 16,
+	MLX5E_400GAUI_2_400GBASE_CR2_KR2	= 17,
+	MLX5E_800GAUI_8_800GBASE_CR8_KR8	= 19,
+	MLX5E_800GAUI_4_800GBASE_CR4_KR4	= 20,
+	MLX5E_1600TAUI_8_1600TBASE_CR8_KR8	= 23,
 	MLX5E_EXT_LINK_MODES_NUMBER,
 };
 
@@ -141,12 +137,6 @@ enum mlx5_ptys_width {
 	MLX5_PTYS_WIDTH_12X	= 1 << 4,
 };
 
-struct mlx5_port_eth_proto {
-	u32 cap;
-	u32 admin;
-	u32 oper;
-};
-
 #define MLX5E_PROT_MASK(link_mode) (1U << link_mode)
 #define MLX5_GET_ETH_PROTO(reg, out, ext, field)	\
 	(ext ? MLX5_GET(reg, out, ext_##field) :	\
@@ -154,18 +144,12 @@ struct mlx5_port_eth_proto {
 
 int mlx5_set_port_caps(struct mlx5_core_dev *dev, u8 port_num, u32 caps);
 int mlx5_query_port_ptys(struct mlx5_core_dev *dev, u32 *ptys,
-			 int ptys_size, int proto_mask, u8 local_port);
+			 int ptys_size, int proto_mask,
+			 u8 local_port, u8 plane_index);
 
 int mlx5_query_ib_port_oper(struct mlx5_core_dev *dev, u16 *link_width_oper,
-			    u16 *proto_oper, u8 local_port);
-void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
-int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
-			       enum mlx5_port_status status);
-int mlx5_query_port_admin_status(struct mlx5_core_dev *dev,
-				 enum mlx5_port_status *status);
-int mlx5_set_port_beacon(struct mlx5_core_dev *dev, u16 beacon_duration);
-
-int mlx5_set_port_mtu(struct mlx5_core_dev *dev, u16 mtu, u8 port);
+			    u16 *proto_oper, u8 local_port, u8 plane_index);
+
 void mlx5_query_port_max_mtu(struct mlx5_core_dev *dev, u16 *max_mtu, u8 port);
 void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 			      u8 port);
@@ -173,65 +157,4 @@ void mlx5_query_port_oper_mtu(struct mlx5_core_dev *dev, u16 *oper_mtu,
 int mlx5_query_port_vl_hw_cap(struct mlx5_core_dev *dev,
 			      u8 *vl_hw_cap, u8 local_port);
 
-int mlx5_set_port_pause(struct mlx5_core_dev *dev, u32 rx_pause, u32 tx_pause);
-int mlx5_query_port_pause(struct mlx5_core_dev *dev,
-			  u32 *rx_pause, u32 *tx_pause);
-
-int mlx5_set_port_pfc(struct mlx5_core_dev *dev, u8 pfc_en_tx, u8 pfc_en_rx);
-int mlx5_query_port_pfc(struct mlx5_core_dev *dev, u8 *pfc_en_tx,
-			u8 *pfc_en_rx);
-
-int mlx5_set_port_stall_watermark(struct mlx5_core_dev *dev,
-				  u16 stall_critical_watermark,
-				  u16 stall_minor_watermark);
-int mlx5_query_port_stall_watermark(struct mlx5_core_dev *dev,
-				    u16 *stall_critical_watermark, u16 *stall_minor_watermark);
-
-int mlx5_max_tc(struct mlx5_core_dev *mdev);
-
-int mlx5_set_port_prio_tc(struct mlx5_core_dev *mdev, u8 *prio_tc);
-int mlx5_query_port_prio_tc(struct mlx5_core_dev *mdev,
-			    u8 prio, u8 *tc);
-int mlx5_set_port_tc_group(struct mlx5_core_dev *mdev, u8 *tc_group);
-int mlx5_query_port_tc_group(struct mlx5_core_dev *mdev,
-			     u8 tc, u8 *tc_group);
-int mlx5_set_port_tc_bw_alloc(struct mlx5_core_dev *mdev, u8 *tc_bw);
-int mlx5_query_port_tc_bw_alloc(struct mlx5_core_dev *mdev,
-				u8 tc, u8 *bw_pct);
-int mlx5_modify_port_ets_rate_limit(struct mlx5_core_dev *mdev,
-				    u8 *max_bw_value,
-				    u8 *max_bw_unit);
-int mlx5_query_port_ets_rate_limit(struct mlx5_core_dev *mdev,
-				   u8 *max_bw_value,
-				   u8 *max_bw_unit);
-int mlx5_set_port_wol(struct mlx5_core_dev *mdev, u8 wol_mode);
-int mlx5_query_port_wol(struct mlx5_core_dev *mdev, u8 *wol_mode);
-
-int mlx5_query_ports_check(struct mlx5_core_dev *mdev, u32 *out, int outlen);
-int mlx5_set_ports_check(struct mlx5_core_dev *mdev, u32 *in, int inlen);
-int mlx5_set_port_fcs(struct mlx5_core_dev *mdev, u8 enable);
-void mlx5_query_port_fcs(struct mlx5_core_dev *mdev, bool *supported,
-			 bool *enabled);
-int mlx5_query_module_eeprom(struct mlx5_core_dev *dev,
-			     u16 offset, u16 size, u8 *data);
-int mlx5_query_module_eeprom_by_page(struct mlx5_core_dev *dev,
-				     struct mlx5_module_eeprom_query_params *params, u8 *data);
-
-int mlx5_query_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *out);
-int mlx5_set_port_dcbx_param(struct mlx5_core_dev *mdev, u32 *in);
-
-int mlx5_set_trust_state(struct mlx5_core_dev *mdev, u8 trust_state);
-int mlx5_query_trust_state(struct mlx5_core_dev *mdev, u8 *trust_state);
-int mlx5_set_dscp2prio(struct mlx5_core_dev *mdev, u8 dscp, u8 prio);
-int mlx5_query_dscp2prio(struct mlx5_core_dev *mdev, u8 *dscp2prio);
-
-int mlx5_port_query_eth_proto(struct mlx5_core_dev *dev, u8 port, bool ext,
-			      struct mlx5_port_eth_proto *eproto);
-bool mlx5_ptys_ext_supported(struct mlx5_core_dev *mdev);
-u32 mlx5_port_ptys2speed(struct mlx5_core_dev *mdev, u32 eth_proto_oper,
-			 bool force_legacy);
-u32 mlx5_port_speed2linkmodes(struct mlx5_core_dev *mdev, u32 speed,
-			      bool force_legacy);
-int mlx5_port_max_linkspeed(struct mlx5_core_dev *mdev, u32 *speed);
-
 #endif /* __MLX5_PORT_H__ */
diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
index bd53cf4be7bd..d67aedc6ea68 100644
--- a/include/linux/mlx5/qp.h
+++ b/include/linux/mlx5/qp.h
@@ -149,6 +149,7 @@ enum {
 	MLX5_WQE_CTRL_CQ_UPDATE		= 2 << 2,
 	MLX5_WQE_CTRL_CQ_UPDATE_AND_EQE	= 3 << 2,
 	MLX5_WQE_CTRL_SOLICITED		= 1 << 1,
+	MLX5_WQE_CTRL_INITIATOR_SMALL_FENCE = 1 << 5,
 };
 
 enum {
@@ -236,13 +237,11 @@ enum {
 };
 
 enum {
-	MLX5_ETH_WQE_SVLAN              = 1 << 0,
 	MLX5_ETH_WQE_TRAILER_HDR_OUTER_IP_ASSOC = 1 << 26,
 	MLX5_ETH_WQE_TRAILER_HDR_OUTER_L4_ASSOC = 1 << 27,
 	MLX5_ETH_WQE_TRAILER_HDR_INNER_IP_ASSOC = 3 << 26,
 	MLX5_ETH_WQE_TRAILER_HDR_INNER_L4_ASSOC = 1 << 28,
 	MLX5_ETH_WQE_INSERT_TRAILER     = 1 << 30,
-	MLX5_ETH_WQE_INSERT_VLAN        = 1 << 15,
 };
 
 enum {
@@ -252,9 +251,15 @@ enum {
 	MLX5_ETH_WQE_SWP_OUTER_L4_UDP   = 1 << 5,
 };
 
+/* Metadata bits 0-7 are used by timestamping */
+/* Base shift for metadata bits used by IPsec and MACsec */
+#define MLX5_ETH_WQE_FT_META_SHIFT 8
+
 enum {
-	MLX5_ETH_WQE_FT_META_IPSEC = BIT(0),
-	MLX5_ETH_WQE_FT_META_MACSEC = BIT(1),
+	MLX5_ETH_WQE_FT_META_IPSEC = BIT(0) << MLX5_ETH_WQE_FT_META_SHIFT,
+	MLX5_ETH_WQE_FT_META_MACSEC = BIT(1) << MLX5_ETH_WQE_FT_META_SHIFT,
+	MLX5_ETH_WQE_FT_META_MACSEC_FS_ID_MASK =
+		GENMASK(5, 2) << MLX5_ETH_WQE_FT_META_SHIFT,
 };
 
 struct mlx5_wqe_eth_seg {
@@ -269,12 +274,11 @@ struct mlx5_wqe_eth_seg {
 	union {
 		struct {
 			__be16 sz;
-			u8     start[2];
+			union {
+				u8     start[2];
+				DECLARE_FLEX_ARRAY(u8, data);
+			};
 		} inline_hdr;
-		struct {
-			__be16 type;
-			__be16 vlan_tci;
-		} insert;
 		__be32 trailer;
 	};
 };
@@ -573,9 +577,12 @@ static inline const char *mlx5_qp_state_str(int state)
 
 static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev)
 {
-	return !MLX5_CAP_ROCE(dev, qp_ts_format) ?
-		       MLX5_TIMESTAMP_FORMAT_FREE_RUNNING :
-		       MLX5_TIMESTAMP_FORMAT_DEFAULT;
+	u8 supported_ts_cap = mlx5_get_roce_state(dev) ?
+			      MLX5_CAP_ROCE(dev, qp_ts_format) :
+			      MLX5_CAP_GEN(dev, sq_ts_format);
+
+	return supported_ts_cap ? MLX5_TIMESTAMP_FORMAT_DEFAULT :
+	       MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
 }
 
 #endif /* MLX5_QP_H */
diff --git a/include/linux/mlx5/vport.h b/include/linux/mlx5/vport.h
index 7f31432f44c2..f876bfc0669c 100644
--- a/include/linux/mlx5/vport.h
+++ b/include/linux/mlx5/vport.h
@@ -72,7 +72,9 @@ int mlx5_query_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 *mtu);
 int mlx5_modify_nic_vport_mtu(struct mlx5_core_dev *mdev, u16 mtu);
 int mlx5_query_nic_vport_system_image_guid(struct mlx5_core_dev *mdev,
 					   u64 *system_image_guid);
-int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev, u64 *node_guid);
+int mlx5_query_nic_vport_sd_group(struct mlx5_core_dev *mdev, u8 *sd_group);
+int mlx5_query_nic_vport_node_guid(struct mlx5_core_dev *mdev,
+				   u16 vport, bool other_vport, u64 *node_guid);
 int mlx5_modify_nic_vport_node_guid(struct mlx5_core_dev *mdev,
 				    u16 vport, u64 node_guid);
 int mlx5_query_nic_vport_qkey_viol_cntr(struct mlx5_core_dev *mdev,
@@ -132,6 +134,8 @@ int mlx5_nic_vport_affiliate_multiport(struct mlx5_core_dev *master_mdev,
 int mlx5_nic_vport_unaffiliate_multiport(struct mlx5_core_dev *port_mdev);
 
 u64 mlx5_query_nic_system_image_guid(struct mlx5_core_dev *mdev);
-int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 function_id, void *out,
+int mlx5_vport_get_other_func_cap(struct mlx5_core_dev *dev, u16 vport, void *out,
 				  u16 opmod);
+int mlx5_vport_get_vhca_id(struct mlx5_core_dev *dev, u16 vport, u16 *vhca_id);
+
 #endif /* __MLX5_VPORT_H__ */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 66032f0d515c..7a1819c20643 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -5,12 +5,14 @@
 #include <linux/errno.h>
 #include <linux/mmdebug.h>
 #include <linux/gfp.h>
+#include <linux/pgalloc_tag.h>
 #include <linux/bug.h>
 #include <linux/list.h>
 #include <linux/mmzone.h>
 #include <linux/rbtree.h>
 #include <linux/atomic.h>
 #include <linux/debug_locks.h>
+#include <linux/compiler.h>
 #include <linux/mm_types.h>
 #include <linux/mmap_lock.h>
 #include <linux/range.h>
@@ -30,29 +32,22 @@
 #include <linux/kasan.h>
 #include <linux/memremap.h>
 #include <linux/slab.h>
+#include <linux/cacheinfo.h>
+#include <linux/rcuwait.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
 
 struct mempolicy;
 struct anon_vma;
 struct anon_vma_chain;
 struct user_struct;
 struct pt_regs;
+struct folio_batch;
 
-extern int sysctl_page_lock_unfairness;
-
+void arch_mm_preinit(void);
 void mm_core_init(void);
 void init_mm_internals(void);
 
-#ifndef CONFIG_NUMA		/* Don't use mapnrs, do it properly */
-extern unsigned long max_mapnr;
-
-static inline void set_max_mapnr(unsigned long limit)
-{
-	max_mapnr = limit;
-}
-#else
-static inline void set_max_mapnr(unsigned long limit) { }
-#endif
-
 extern atomic_long_t _totalram_pages;
 static inline unsigned long totalram_pages(void)
 {
@@ -75,8 +70,15 @@ static inline void totalram_pages_add(long count)
 }
 
 extern void * high_memory;
-extern int page_cluster;
-extern const int page_cluster_max;
+
+/*
+ * Convert between pages and MB
+ * 20 is the shift for 1MB (2^20 = 1MB)
+ * PAGE_SHIFT is the shift for page size (e.g., 12 for 4KB pages)
+ * So (20 - PAGE_SHIFT) converts between pages and MB
+ */
+#define PAGES_TO_MB(pages) ((pages) >> (20 - PAGE_SHIFT))
+#define MB_TO_PAGES(mb)    ((mb) << (20 - PAGE_SHIFT))
 
 #ifdef CONFIG_SYSCTL
 extern int sysctl_legacy_va_layout;
@@ -86,7 +88,7 @@ extern int sysctl_legacy_va_layout;
 
 #ifdef CONFIG_HAVE_ARCH_MMAP_RND_BITS
 extern const int mmap_rnd_bits_min;
-extern const int mmap_rnd_bits_max;
+extern int mmap_rnd_bits_max __ro_after_init;
 extern int mmap_rnd_bits __read_mostly;
 #endif
 #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
@@ -95,6 +97,16 @@ extern const int mmap_rnd_compat_bits_max;
 extern int mmap_rnd_compat_bits __read_mostly;
 #endif
 
+#ifndef DIRECT_MAP_PHYSMEM_END
+# ifdef MAX_PHYSMEM_BITS
+# define DIRECT_MAP_PHYSMEM_END	((1ULL << MAX_PHYSMEM_BITS) - 1)
+# else
+# define DIRECT_MAP_PHYSMEM_END	(((phys_addr_t)-1)&~(1ULL<<63))
+# endif
+#endif
+
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
+
 #include <asm/page.h>
 #include <asm/processor.h>
 
@@ -198,23 +210,14 @@ extern int sysctl_max_map_count;
 extern unsigned long sysctl_user_reserve_kbytes;
 extern unsigned long sysctl_admin_reserve_kbytes;
 
-extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
-extern unsigned long sysctl_overcommit_kbytes;
-
-int overcommit_ratio_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int overcommit_kbytes_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-
 #if defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
-#define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
-#define folio_page_idx(folio, p)	(page_to_pfn(p) - folio_pfn(folio))
+bool page_range_contiguous(const struct page *page, unsigned long nr_pages);
 #else
-#define nth_page(page,n) ((page) + (n))
-#define folio_page_idx(folio, p)	((p) - &(folio)->page)
+static inline bool page_range_contiguous(const struct page *page,
+		unsigned long nr_pages)
+{
+	return true;
+}
 #endif
 
 /* to align the pointer to the (next) page boundary */
@@ -226,7 +229,20 @@ int overcommit_policy_handler(struct ctl_table *, int, void *, size_t *,
 /* test whether an address (unsigned long or pointer) is aligned to PAGE_SIZE */
 #define PAGE_ALIGNED(addr)	IS_ALIGNED((unsigned long)(addr), PAGE_SIZE)
 
-#define lru_to_page(head) (list_entry((head)->prev, struct page, lru))
+/**
+ * folio_page_idx - Return the number of a page in a folio.
+ * @folio: The folio.
+ * @page: The folio page.
+ *
+ * This function expects that the page is actually part of the folio.
+ * The returned number is relative to the start of the folio.
+ */
+static inline unsigned long folio_page_idx(const struct folio *folio,
+		const struct page *page)
+{
+	return page - &folio->page;
+}
+
 static inline struct folio *lru_to_folio(struct list_head *head)
 {
 	return list_entry((head)->prev, struct folio, lru);
@@ -247,8 +263,6 @@ void setup_initial_init_mm(void *start_code, void *end_code,
 struct vm_area_struct *vm_area_alloc(struct mm_struct *);
 struct vm_area_struct *vm_area_dup(struct vm_area_struct *);
 void vm_area_free(struct vm_area_struct *);
-/* Use only if VMA has no other users */
-void __vm_area_free(struct vm_area_struct *vma);
 
 #ifndef CONFIG_MMU
 extern struct rb_root nommu_region_tree;
@@ -261,123 +275,239 @@ extern unsigned int kobjsize(const void *objp);
  * vm_flags in vm_area_struct, see mm_types.h.
  * When changing, update also include/trace/events/mmflags.h
  */
-#define VM_NONE		0x00000000
 
-#define VM_READ		0x00000001	/* currently active flags */
-#define VM_WRITE	0x00000002
-#define VM_EXEC		0x00000004
-#define VM_SHARED	0x00000008
+#define VM_NONE		0x00000000
 
-/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
-#define VM_MAYREAD	0x00000010	/* limits for mprotect() etc */
-#define VM_MAYWRITE	0x00000020
-#define VM_MAYEXEC	0x00000040
-#define VM_MAYSHARE	0x00000080
+/**
+ * typedef vma_flag_t - specifies an individual VMA flag by bit number.
+ *
+ * This value is made type safe by sparse to avoid passing invalid flag values
+ * around.
+ */
+typedef int __bitwise vma_flag_t;
 
-#define VM_GROWSDOWN	0x00000100	/* general info on the segment */
+#define DECLARE_VMA_BIT(name, bitnum) \
+	VMA_ ## name ## _BIT = ((__force vma_flag_t)bitnum)
+#define DECLARE_VMA_BIT_ALIAS(name, aliased) \
+	VMA_ ## name ## _BIT = (VMA_ ## aliased ## _BIT)
+enum {
+	DECLARE_VMA_BIT(READ, 0),
+	DECLARE_VMA_BIT(WRITE, 1),
+	DECLARE_VMA_BIT(EXEC, 2),
+	DECLARE_VMA_BIT(SHARED, 3),
+	/* mprotect() hardcodes VM_MAYREAD >> 4 == VM_READ, and so for r/w/x bits. */
+	DECLARE_VMA_BIT(MAYREAD, 4),	/* limits for mprotect() etc. */
+	DECLARE_VMA_BIT(MAYWRITE, 5),
+	DECLARE_VMA_BIT(MAYEXEC, 6),
+	DECLARE_VMA_BIT(MAYSHARE, 7),
+	DECLARE_VMA_BIT(GROWSDOWN, 8),	/* general info on the segment */
 #ifdef CONFIG_MMU
-#define VM_UFFD_MISSING	0x00000200	/* missing pages tracking */
-#else /* CONFIG_MMU */
-#define VM_MAYOVERLAY	0x00000200	/* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */
-#define VM_UFFD_MISSING	0
+	DECLARE_VMA_BIT(UFFD_MISSING, 9),/* missing pages tracking */
+#else
+	/* nommu: R/O MAP_PRIVATE mapping that might overlay a file mapping */
+	DECLARE_VMA_BIT(MAYOVERLAY, 9),
 #endif /* CONFIG_MMU */
-#define VM_PFNMAP	0x00000400	/* Page-ranges managed without "struct page", just pure PFN */
-#define VM_UFFD_WP	0x00001000	/* wrprotect pages tracking */
-
-#define VM_LOCKED	0x00002000
-#define VM_IO           0x00004000	/* Memory mapped I/O or similar */
-
-					/* Used by sys_madvise() */
-#define VM_SEQ_READ	0x00008000	/* App will access data sequentially */
-#define VM_RAND_READ	0x00010000	/* App will not benefit from clustered reads */
-
-#define VM_DONTCOPY	0x00020000      /* Do not copy this vma on fork */
-#define VM_DONTEXPAND	0x00040000	/* Cannot expand with mremap() */
-#define VM_LOCKONFAULT	0x00080000	/* Lock the pages covered when they are faulted in */
-#define VM_ACCOUNT	0x00100000	/* Is a VM accounted object */
-#define VM_NORESERVE	0x00200000	/* should the VM suppress accounting */
-#define VM_HUGETLB	0x00400000	/* Huge TLB Page VM */
-#define VM_SYNC		0x00800000	/* Synchronous page faults */
-#define VM_ARCH_1	0x01000000	/* Architecture-specific flag */
-#define VM_WIPEONFORK	0x02000000	/* Wipe VMA contents in child. */
-#define VM_DONTDUMP	0x04000000	/* Do not include in the core dump */
-
+	/* Page-ranges managed without "struct page", just pure PFN */
+	DECLARE_VMA_BIT(PFNMAP, 10),
+	DECLARE_VMA_BIT(MAYBE_GUARD, 11),
+	DECLARE_VMA_BIT(UFFD_WP, 12),	/* wrprotect pages tracking */
+	DECLARE_VMA_BIT(LOCKED, 13),
+	DECLARE_VMA_BIT(IO, 14),	/* Memory mapped I/O or similar */
+	DECLARE_VMA_BIT(SEQ_READ, 15),	/* App will access data sequentially */
+	DECLARE_VMA_BIT(RAND_READ, 16),	/* App will not benefit from clustered reads */
+	DECLARE_VMA_BIT(DONTCOPY, 17),	/* Do not copy this vma on fork */
+	DECLARE_VMA_BIT(DONTEXPAND, 18),/* Cannot expand with mremap() */
+	DECLARE_VMA_BIT(LOCKONFAULT, 19),/* Lock pages covered when faulted in */
+	DECLARE_VMA_BIT(ACCOUNT, 20),	/* Is a VM accounted object */
+	DECLARE_VMA_BIT(NORESERVE, 21),	/* should the VM suppress accounting */
+	DECLARE_VMA_BIT(HUGETLB, 22),	/* Huge TLB Page VM */
+	DECLARE_VMA_BIT(SYNC, 23),	/* Synchronous page faults */
+	DECLARE_VMA_BIT(ARCH_1, 24),	/* Architecture-specific flag */
+	DECLARE_VMA_BIT(WIPEONFORK, 25),/* Wipe VMA contents in child. */
+	DECLARE_VMA_BIT(DONTDUMP, 26),	/* Do not include in the core dump */
+	DECLARE_VMA_BIT(SOFTDIRTY, 27),	/* NOT soft dirty clean area */
+	DECLARE_VMA_BIT(MIXEDMAP, 28),	/* Can contain struct page and pure PFN pages */
+	DECLARE_VMA_BIT(HUGEPAGE, 29),	/* MADV_HUGEPAGE marked this vma */
+	DECLARE_VMA_BIT(NOHUGEPAGE, 30),/* MADV_NOHUGEPAGE marked this vma */
+	DECLARE_VMA_BIT(MERGEABLE, 31),	/* KSM may merge identical pages */
+	/* These bits are reused, we define specific uses below. */
+	DECLARE_VMA_BIT(HIGH_ARCH_0, 32),
+	DECLARE_VMA_BIT(HIGH_ARCH_1, 33),
+	DECLARE_VMA_BIT(HIGH_ARCH_2, 34),
+	DECLARE_VMA_BIT(HIGH_ARCH_3, 35),
+	DECLARE_VMA_BIT(HIGH_ARCH_4, 36),
+	DECLARE_VMA_BIT(HIGH_ARCH_5, 37),
+	DECLARE_VMA_BIT(HIGH_ARCH_6, 38),
+	/*
+	 * This flag is used to connect VFIO to arch specific KVM code. It
+	 * indicates that the memory under this VMA is safe for use with any
+	 * non-cachable memory type inside KVM. Some VFIO devices, on some
+	 * platforms, are thought to be unsafe and can cause machine crashes
+	 * if KVM does not lock down the memory type.
+	 */
+	DECLARE_VMA_BIT(ALLOW_ANY_UNCACHED, 39),
+#ifdef CONFIG_PPC32
+	DECLARE_VMA_BIT_ALIAS(DROPPABLE, ARCH_1),
+#else
+	DECLARE_VMA_BIT(DROPPABLE, 40),
+#endif
+	DECLARE_VMA_BIT(UFFD_MINOR, 41),
+	DECLARE_VMA_BIT(SEALED, 42),
+	/* Flags that reuse flags above. */
+	DECLARE_VMA_BIT_ALIAS(PKEY_BIT0, HIGH_ARCH_0),
+	DECLARE_VMA_BIT_ALIAS(PKEY_BIT1, HIGH_ARCH_1),
+	DECLARE_VMA_BIT_ALIAS(PKEY_BIT2, HIGH_ARCH_2),
+	DECLARE_VMA_BIT_ALIAS(PKEY_BIT3, HIGH_ARCH_3),
+	DECLARE_VMA_BIT_ALIAS(PKEY_BIT4, HIGH_ARCH_4),
+#if defined(CONFIG_X86_USER_SHADOW_STACK)
+	/*
+	 * VM_SHADOW_STACK should not be set with VM_SHARED because of lack of
+	 * support core mm.
+	 *
+	 * These VMAs will get a single end guard page. This helps userspace
+	 * protect itself from attacks. A single page is enough for current
+	 * shadow stack archs (x86). See the comments near alloc_shstk() in
+	 * arch/x86/kernel/shstk.c for more details on the guard size.
+	 */
+	DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_5),
+#elif defined(CONFIG_ARM64_GCS)
+	/*
+	 * arm64's Guarded Control Stack implements similar functionality and
+	 * has similar constraints to shadow stacks.
+	 */
+	DECLARE_VMA_BIT_ALIAS(SHADOW_STACK, HIGH_ARCH_6),
+#endif
+	DECLARE_VMA_BIT_ALIAS(SAO, ARCH_1),		/* Strong Access Ordering (powerpc) */
+	DECLARE_VMA_BIT_ALIAS(GROWSUP, ARCH_1),		/* parisc */
+	DECLARE_VMA_BIT_ALIAS(SPARC_ADI, ARCH_1),	/* sparc64 */
+	DECLARE_VMA_BIT_ALIAS(ARM64_BTI, ARCH_1),	/* arm64 */
+	DECLARE_VMA_BIT_ALIAS(ARCH_CLEAR, ARCH_1),	/* sparc64, arm64 */
+	DECLARE_VMA_BIT_ALIAS(MAPPED_COPY, ARCH_1),	/* !CONFIG_MMU */
+	DECLARE_VMA_BIT_ALIAS(MTE, HIGH_ARCH_4),	/* arm64 */
+	DECLARE_VMA_BIT_ALIAS(MTE_ALLOWED, HIGH_ARCH_5),/* arm64 */
+#ifdef CONFIG_STACK_GROWSUP
+	DECLARE_VMA_BIT_ALIAS(STACK, GROWSUP),
+	DECLARE_VMA_BIT_ALIAS(STACK_EARLY, GROWSDOWN),
+#else
+	DECLARE_VMA_BIT_ALIAS(STACK, GROWSDOWN),
+#endif
+};
+#undef DECLARE_VMA_BIT
+#undef DECLARE_VMA_BIT_ALIAS
+
+#define INIT_VM_FLAG(name) BIT((__force int) VMA_ ## name ## _BIT)
+#define VM_READ		INIT_VM_FLAG(READ)
+#define VM_WRITE	INIT_VM_FLAG(WRITE)
+#define VM_EXEC		INIT_VM_FLAG(EXEC)
+#define VM_SHARED	INIT_VM_FLAG(SHARED)
+#define VM_MAYREAD	INIT_VM_FLAG(MAYREAD)
+#define VM_MAYWRITE	INIT_VM_FLAG(MAYWRITE)
+#define VM_MAYEXEC	INIT_VM_FLAG(MAYEXEC)
+#define VM_MAYSHARE	INIT_VM_FLAG(MAYSHARE)
+#define VM_GROWSDOWN	INIT_VM_FLAG(GROWSDOWN)
+#ifdef CONFIG_MMU
+#define VM_UFFD_MISSING	INIT_VM_FLAG(UFFD_MISSING)
+#else
+#define VM_UFFD_MISSING	VM_NONE
+#define VM_MAYOVERLAY	INIT_VM_FLAG(MAYOVERLAY)
+#endif
+#define VM_PFNMAP	INIT_VM_FLAG(PFNMAP)
+#define VM_MAYBE_GUARD	INIT_VM_FLAG(MAYBE_GUARD)
+#define VM_UFFD_WP	INIT_VM_FLAG(UFFD_WP)
+#define VM_LOCKED	INIT_VM_FLAG(LOCKED)
+#define VM_IO		INIT_VM_FLAG(IO)
+#define VM_SEQ_READ	INIT_VM_FLAG(SEQ_READ)
+#define VM_RAND_READ	INIT_VM_FLAG(RAND_READ)
+#define VM_DONTCOPY	INIT_VM_FLAG(DONTCOPY)
+#define VM_DONTEXPAND	INIT_VM_FLAG(DONTEXPAND)
+#define VM_LOCKONFAULT	INIT_VM_FLAG(LOCKONFAULT)
+#define VM_ACCOUNT	INIT_VM_FLAG(ACCOUNT)
+#define VM_NORESERVE	INIT_VM_FLAG(NORESERVE)
+#define VM_HUGETLB	INIT_VM_FLAG(HUGETLB)
+#define VM_SYNC		INIT_VM_FLAG(SYNC)
+#define VM_ARCH_1	INIT_VM_FLAG(ARCH_1)
+#define VM_WIPEONFORK	INIT_VM_FLAG(WIPEONFORK)
+#define VM_DONTDUMP	INIT_VM_FLAG(DONTDUMP)
 #ifdef CONFIG_MEM_SOFT_DIRTY
-# define VM_SOFTDIRTY	0x08000000	/* Not soft dirty clean area */
+#define VM_SOFTDIRTY	INIT_VM_FLAG(SOFTDIRTY)
 #else
-# define VM_SOFTDIRTY	0
-#endif
-
-#define VM_MIXEDMAP	0x10000000	/* Can contain "struct page" and pure PFN pages */
-#define VM_HUGEPAGE	0x20000000	/* MADV_HUGEPAGE marked this vma */
-#define VM_NOHUGEPAGE	0x40000000	/* MADV_NOHUGEPAGE marked this vma */
-#define VM_MERGEABLE	0x80000000	/* KSM may merge identical pages */
-
-#ifdef CONFIG_ARCH_USES_HIGH_VMA_FLAGS
-#define VM_HIGH_ARCH_BIT_0	32	/* bit only usable on 64-bit architectures */
-#define VM_HIGH_ARCH_BIT_1	33	/* bit only usable on 64-bit architectures */
-#define VM_HIGH_ARCH_BIT_2	34	/* bit only usable on 64-bit architectures */
-#define VM_HIGH_ARCH_BIT_3	35	/* bit only usable on 64-bit architectures */
-#define VM_HIGH_ARCH_BIT_4	36	/* bit only usable on 64-bit architectures */
-#define VM_HIGH_ARCH_0	BIT(VM_HIGH_ARCH_BIT_0)
-#define VM_HIGH_ARCH_1	BIT(VM_HIGH_ARCH_BIT_1)
-#define VM_HIGH_ARCH_2	BIT(VM_HIGH_ARCH_BIT_2)
-#define VM_HIGH_ARCH_3	BIT(VM_HIGH_ARCH_BIT_3)
-#define VM_HIGH_ARCH_4	BIT(VM_HIGH_ARCH_BIT_4)
-#endif /* CONFIG_ARCH_USES_HIGH_VMA_FLAGS */
-
-#ifdef CONFIG_ARCH_HAS_PKEYS
-# define VM_PKEY_SHIFT	VM_HIGH_ARCH_BIT_0
-# define VM_PKEY_BIT0	VM_HIGH_ARCH_0	/* A protection key is a 4-bit value */
-# define VM_PKEY_BIT1	VM_HIGH_ARCH_1	/* on x86 and 5-bit value on ppc64   */
-# define VM_PKEY_BIT2	VM_HIGH_ARCH_2
-# define VM_PKEY_BIT3	VM_HIGH_ARCH_3
-#ifdef CONFIG_PPC
-# define VM_PKEY_BIT4  VM_HIGH_ARCH_4
+#define VM_SOFTDIRTY	VM_NONE
+#endif
+#define VM_MIXEDMAP	INIT_VM_FLAG(MIXEDMAP)
+#define VM_HUGEPAGE	INIT_VM_FLAG(HUGEPAGE)
+#define VM_NOHUGEPAGE	INIT_VM_FLAG(NOHUGEPAGE)
+#define VM_MERGEABLE	INIT_VM_FLAG(MERGEABLE)
+#define VM_STACK	INIT_VM_FLAG(STACK)
+#ifdef CONFIG_STACK_GROWS_UP
+#define VM_STACK_EARLY	INIT_VM_FLAG(STACK_EARLY)
 #else
-# define VM_PKEY_BIT4  0
+#define VM_STACK_EARLY	VM_NONE
 #endif
+#ifdef CONFIG_ARCH_HAS_PKEYS
+#define VM_PKEY_SHIFT ((__force int)VMA_HIGH_ARCH_0_BIT)
+/* Despite the naming, these are FLAGS not bits. */
+#define VM_PKEY_BIT0 INIT_VM_FLAG(PKEY_BIT0)
+#define VM_PKEY_BIT1 INIT_VM_FLAG(PKEY_BIT1)
+#define VM_PKEY_BIT2 INIT_VM_FLAG(PKEY_BIT2)
+#if CONFIG_ARCH_PKEY_BITS > 3
+#define VM_PKEY_BIT3 INIT_VM_FLAG(PKEY_BIT3)
+#else
+#define VM_PKEY_BIT3  VM_NONE
+#endif /* CONFIG_ARCH_PKEY_BITS > 3 */
+#if CONFIG_ARCH_PKEY_BITS > 4
+#define VM_PKEY_BIT4 INIT_VM_FLAG(PKEY_BIT4)
+#else
+#define VM_PKEY_BIT4  VM_NONE
+#endif /* CONFIG_ARCH_PKEY_BITS > 4 */
 #endif /* CONFIG_ARCH_HAS_PKEYS */
-
-#if defined(CONFIG_X86)
-# define VM_PAT		VM_ARCH_1	/* PAT reserves whole VMA at once (x86) */
-#elif defined(CONFIG_PPC)
-# define VM_SAO		VM_ARCH_1	/* Strong Access Ordering (powerpc) */
+#if defined(CONFIG_X86_USER_SHADOW_STACK) || defined(CONFIG_ARM64_GCS)
+#define VM_SHADOW_STACK	INIT_VM_FLAG(SHADOW_STACK)
+#else
+#define VM_SHADOW_STACK	VM_NONE
+#endif
+#if defined(CONFIG_PPC64)
+#define VM_SAO		INIT_VM_FLAG(SAO)
 #elif defined(CONFIG_PARISC)
-# define VM_GROWSUP	VM_ARCH_1
-#elif defined(CONFIG_IA64)
-# define VM_GROWSUP	VM_ARCH_1
+#define VM_GROWSUP	INIT_VM_FLAG(GROWSUP)
 #elif defined(CONFIG_SPARC64)
-# define VM_SPARC_ADI	VM_ARCH_1	/* Uses ADI tag for access control */
-# define VM_ARCH_CLEAR	VM_SPARC_ADI
+#define VM_SPARC_ADI	INIT_VM_FLAG(SPARC_ADI)
+#define VM_ARCH_CLEAR	INIT_VM_FLAG(ARCH_CLEAR)
 #elif defined(CONFIG_ARM64)
-# define VM_ARM64_BTI	VM_ARCH_1	/* BTI guarded page, a.k.a. GP bit */
-# define VM_ARCH_CLEAR	VM_ARM64_BTI
+#define VM_ARM64_BTI	INIT_VM_FLAG(ARM64_BTI)
+#define VM_ARCH_CLEAR	INIT_VM_FLAG(ARCH_CLEAR)
 #elif !defined(CONFIG_MMU)
-# define VM_MAPPED_COPY	VM_ARCH_1	/* T if mapped copy of data (nommu mmap) */
-#endif
-
-#if defined(CONFIG_ARM64_MTE)
-# define VM_MTE		VM_HIGH_ARCH_0	/* Use Tagged memory for access control */
-# define VM_MTE_ALLOWED	VM_HIGH_ARCH_1	/* Tagged memory permitted */
-#else
-# define VM_MTE		VM_NONE
-# define VM_MTE_ALLOWED	VM_NONE
+#define VM_MAPPED_COPY	INIT_VM_FLAG(MAPPED_COPY)
 #endif
-
 #ifndef VM_GROWSUP
-# define VM_GROWSUP	VM_NONE
+#define VM_GROWSUP	VM_NONE
+#endif
+#ifdef CONFIG_ARM64_MTE
+#define VM_MTE		INIT_VM_FLAG(MTE)
+#define VM_MTE_ALLOWED	INIT_VM_FLAG(MTE_ALLOWED)
+#else
+#define VM_MTE		VM_NONE
+#define VM_MTE_ALLOWED	VM_NONE
 #endif
-
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
-# define VM_UFFD_MINOR_BIT	37
-# define VM_UFFD_MINOR		BIT(VM_UFFD_MINOR_BIT)	/* UFFD minor faults */
-#else /* !CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
-# define VM_UFFD_MINOR		VM_NONE
-#endif /* CONFIG_HAVE_ARCH_USERFAULTFD_MINOR */
+#define VM_UFFD_MINOR	INIT_VM_FLAG(UFFD_MINOR)
+#else
+#define VM_UFFD_MINOR	VM_NONE
+#endif
+#ifdef CONFIG_64BIT
+#define VM_ALLOW_ANY_UNCACHED	INIT_VM_FLAG(ALLOW_ANY_UNCACHED)
+#define VM_SEALED		INIT_VM_FLAG(SEALED)
+#else
+#define VM_ALLOW_ANY_UNCACHED	VM_NONE
+#define VM_SEALED		VM_NONE
+#endif
+#if defined(CONFIG_64BIT) || defined(CONFIG_PPC32)
+#define VM_DROPPABLE		INIT_VM_FLAG(DROPPABLE)
+#else
+#define VM_DROPPABLE		VM_NONE
+#endif
 
 /* Bits set in the VMA until the stack is in its final location */
-#define VM_STACK_INCOMPLETE_SETUP	(VM_RAND_READ | VM_SEQ_READ)
+#define VM_STACK_INCOMPLETE_SETUP (VM_RAND_READ | VM_SEQ_READ | VM_STACK_EARLY)
 
 #define TASK_EXEC ((current->personality & READ_IMPLIES_EXEC) ? VM_EXEC : 0)
 
@@ -397,10 +527,12 @@ extern unsigned int kobjsize(const void *objp);
 #define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
 #endif
 
-#ifdef CONFIG_STACK_GROWSUP
-#define VM_STACK	VM_GROWSUP
+#define VM_STARTGAP_FLAGS (VM_GROWSDOWN | VM_SHADOW_STACK)
+
+#ifdef CONFIG_MSEAL_SYSTEM_MAPPINGS
+#define VM_SEALED_SYSMAP	VM_SEALED
 #else
-#define VM_STACK	VM_GROWSDOWN
+#define VM_SEALED_SYSMAP	VM_NONE
 #endif
 
 #define VM_STACK_FLAGS	(VM_STACK | VM_STACK_DEFAULT_FLAGS | VM_ACCOUNT)
@@ -408,12 +540,26 @@ extern unsigned int kobjsize(const void *objp);
 /* VMA basic access permission flags */
 #define VM_ACCESS_FLAGS (VM_READ | VM_WRITE | VM_EXEC)
 
-
 /*
  * Special vmas that are non-mergable, non-mlock()able.
  */
 #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_PFNMAP | VM_MIXEDMAP)
 
+/*
+ * Physically remapped pages are special. Tell the
+ * rest of the world about it:
+ *   VM_IO tells people not to look at these pages
+ *	(accesses can have side effects).
+ *   VM_PFNMAP tells the core MM that the base pages are just
+ *	raw PFN mappings, and do not have a "struct page" associated
+ *	with them.
+ *   VM_DONTEXPAND
+ *      Disable vma merging and expanding with mremap().
+ *   VM_DONTDUMP
+ *      Omit vma from core dump, even when VM_IO turned off.
+ */
+#define VM_REMAP_FLAGS (VM_IO | VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP)
+
 /* This mask prevents VMA from being scanned with khugepaged */
 #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
 
@@ -423,13 +569,69 @@ extern unsigned int kobjsize(const void *objp);
 /* This mask represents all the VMA flag bits used by mlock */
 #define VM_LOCKED_MASK	(VM_LOCKED | VM_LOCKONFAULT)
 
+/* These flags can be updated atomically via VMA/mmap read lock. */
+#define VM_ATOMIC_SET_ALLOWED VM_MAYBE_GUARD
+
 /* Arch-specific flags to clear when updating VM flags on protection change */
 #ifndef VM_ARCH_CLEAR
-# define VM_ARCH_CLEAR	VM_NONE
+#define VM_ARCH_CLEAR	VM_NONE
 #endif
 #define VM_FLAGS_CLEAR	(ARCH_VM_PKEY_FLAGS | VM_ARCH_CLEAR)
 
 /*
+ * Flags which should be 'sticky' on merge - that is, flags which, when one VMA
+ * possesses it but the other does not, the merged VMA should nonetheless have
+ * applied to it:
+ *
+ *   VM_SOFTDIRTY - if a VMA is marked soft-dirty, that is has not had its
+ *                  references cleared via /proc/$pid/clear_refs, any merged VMA
+ *                  should be considered soft-dirty also as it operates at a VMA
+ *                  granularity.
+ *
+ * VM_MAYBE_GUARD - If a VMA may have guard regions in place it implies that
+ *                  mapped page tables may contain metadata not described by the
+ *                  VMA and thus any merged VMA may also contain this metadata,
+ *                  and thus we must make this flag sticky.
+ */
+#define VM_STICKY (VM_SOFTDIRTY | VM_MAYBE_GUARD)
+
+/*
+ * VMA flags we ignore for the purposes of merge, i.e. one VMA possessing one
+ * of these flags and the other not does not preclude a merge.
+ *
+ *    VM_STICKY - When merging VMAs, VMA flags must match, unless they are
+ *                'sticky'. If any sticky flags exist in either VMA, we simply
+ *                set all of them on the merged VMA.
+ */
+#define VM_IGNORE_MERGE VM_STICKY
+
+/*
+ * Flags which should result in page tables being copied on fork. These are
+ * flags which indicate that the VMA maps page tables which cannot be
+ * reconsistuted upon page fault, so necessitate page table copying upon
+ *
+ * VM_PFNMAP / VM_MIXEDMAP - These contain kernel-mapped data which cannot be
+ *                           reasonably reconstructed on page fault.
+ *
+ *              VM_UFFD_WP - Encodes metadata about an installed uffd
+ *                           write protect handler, which cannot be
+ *                           reconstructed on page fault.
+ *
+ *                           We always copy pgtables when dst_vma has uffd-wp
+ *                           enabled even if it's file-backed
+ *                           (e.g. shmem). Because when uffd-wp is enabled,
+ *                           pgtable contains uffd-wp protection information,
+ *                           that's something we can't retrieve from page cache,
+ *                           and skip copying will lose those info.
+ *
+ *          VM_MAYBE_GUARD - Could contain page guard region markers which
+ *                           by design are a property of the page tables
+ *                           only and thus cannot be reconstructed on page
+ *                           fault.
+ */
+#define VM_COPY_ON_FORK (VM_PFNMAP | VM_MIXEDMAP | VM_UFFD_WP | VM_MAYBE_GUARD)
+
+/*
  * mapping from the currently active vm_flags protection bits (the
  * low four bits) to a page protection mask..
  */
@@ -530,13 +732,6 @@ struct vm_fault {
 					 */
 };
 
-/* page entry size for vm->huge_fault() */
-enum page_entry_size {
-	PE_SIZE_PTE = 0,
-	PE_SIZE_PMD,
-	PE_SIZE_PUD,
-};
-
 /*
  * These are the virtual MM functions - opening of an area, closing and
  * unmapping it (needed to keep files on disk up-to-date etc), pointer
@@ -560,8 +755,7 @@ struct vm_operations_struct {
 	int (*mprotect)(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end, unsigned long newflags);
 	vm_fault_t (*fault)(struct vm_fault *vmf);
-	vm_fault_t (*huge_fault)(struct vm_fault *vmf,
-			enum page_entry_size pe_size);
+	vm_fault_t (*huge_fault)(struct vm_fault *vmf, unsigned int order);
 	vm_fault_t (*map_pages)(struct vm_fault *vmf,
 			pgoff_t start_pgoff, pgoff_t end_pgoff);
 	unsigned long (*pagesize)(struct vm_area_struct * area);
@@ -606,15 +800,23 @@ struct vm_operations_struct {
 	 * policy.
 	 */
 	struct mempolicy *(*get_policy)(struct vm_area_struct *vma,
-					unsigned long addr);
+					unsigned long addr, pgoff_t *ilx);
 #endif
+#ifdef CONFIG_FIND_NORMAL_PAGE
 	/*
-	 * Called by vm_normal_page() for special PTEs to find the
-	 * page for @addr.  This is useful if the default behavior
-	 * (using pte_page()) would not find the correct page.
+	 * Called by vm_normal_page() for special PTEs in @vma at @addr. This
+	 * allows for returning a "normal" page from vm_normal_page() even
+	 * though the PTE indicates that the "struct page" either does not exist
+	 * or should not be touched: "special".
+	 *
+	 * Do not add new users: this really only works when a "normal" page
+	 * was mapped, but then the PTE got changed to something weird (+
+	 * marked special) that would not make pte_pfn() identify the originally
+	 * inserted page.
 	 */
-	struct page *(*find_special_page)(struct vm_area_struct *vma,
-					  unsigned long addr);
+	struct page *(*find_normal_page)(struct vm_area_struct *vma,
+					 unsigned long addr);
+#endif /* CONFIG_FIND_NORMAL_PAGE */
 };
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -631,163 +833,132 @@ static inline void vma_numab_state_init(struct vm_area_struct *vma) {}
 static inline void vma_numab_state_free(struct vm_area_struct *vma) {}
 #endif /* CONFIG_NUMA_BALANCING */
 
-#ifdef CONFIG_PER_VMA_LOCK
 /*
- * Try to read-lock a vma. The function is allowed to occasionally yield false
- * locked result to avoid performance overhead, in which case we fall back to
- * using mmap_lock. The function should never yield false unlocked result.
+ * These must be here rather than mmap_lock.h as dependent on vm_fault type,
+ * declared in this header.
  */
-static inline bool vma_start_read(struct vm_area_struct *vma)
+#ifdef CONFIG_PER_VMA_LOCK
+static inline void release_fault_lock(struct vm_fault *vmf)
 {
-	/* Check before locking. A race might cause false locked result. */
-	if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))
-		return false;
-
-	if (unlikely(down_read_trylock(&vma->vm_lock->lock) == 0))
-		return false;
-
-	/*
-	 * Overflow might produce false locked result.
-	 * False unlocked result is impossible because we modify and check
-	 * vma->vm_lock_seq under vma->vm_lock protection and mm->mm_lock_seq
-	 * modification invalidates all existing locks.
-	 */
-	if (unlikely(vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq))) {
-		up_read(&vma->vm_lock->lock);
-		return false;
-	}
-	return true;
+	if (vmf->flags & FAULT_FLAG_VMA_LOCK)
+		vma_end_read(vmf->vma);
+	else
+		mmap_read_unlock(vmf->vma->vm_mm);
 }
 
-static inline void vma_end_read(struct vm_area_struct *vma)
+static inline void assert_fault_locked(const struct vm_fault *vmf)
 {
-	rcu_read_lock(); /* keeps vma alive till the end of up_read */
-	up_read(&vma->vm_lock->lock);
-	rcu_read_unlock();
+	if (vmf->flags & FAULT_FLAG_VMA_LOCK)
+		vma_assert_locked(vmf->vma);
+	else
+		mmap_assert_locked(vmf->vma->vm_mm);
 }
-
-static bool __is_vma_write_locked(struct vm_area_struct *vma, int *mm_lock_seq)
+#else
+static inline void release_fault_lock(struct vm_fault *vmf)
 {
-	mmap_assert_write_locked(vma->vm_mm);
-
-	/*
-	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
-	 * mm->mm_lock_seq can't be concurrently modified.
-	 */
-	*mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
-	return (vma->vm_lock_seq == *mm_lock_seq);
+	mmap_read_unlock(vmf->vma->vm_mm);
 }
 
-static inline void vma_start_write(struct vm_area_struct *vma)
+static inline void assert_fault_locked(const struct vm_fault *vmf)
 {
-	int mm_lock_seq;
-
-	if (__is_vma_write_locked(vma, &mm_lock_seq))
-		return;
-
-	down_write(&vma->vm_lock->lock);
-	vma->vm_lock_seq = mm_lock_seq;
-	up_write(&vma->vm_lock->lock);
+	mmap_assert_locked(vmf->vma->vm_mm);
 }
+#endif /* CONFIG_PER_VMA_LOCK */
 
-static inline bool vma_try_start_write(struct vm_area_struct *vma)
+static inline bool mm_flags_test(int flag, const struct mm_struct *mm)
 {
-	int mm_lock_seq;
-
-	if (__is_vma_write_locked(vma, &mm_lock_seq))
-		return true;
-
-	if (!down_write_trylock(&vma->vm_lock->lock))
-		return false;
-
-	vma->vm_lock_seq = mm_lock_seq;
-	up_write(&vma->vm_lock->lock);
-	return true;
+	return test_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
 }
 
-static inline void vma_assert_write_locked(struct vm_area_struct *vma)
+static inline bool mm_flags_test_and_set(int flag, struct mm_struct *mm)
 {
-	int mm_lock_seq;
-
-	VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
+	return test_and_set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
 }
 
-static inline void vma_mark_detached(struct vm_area_struct *vma, bool detached)
+static inline bool mm_flags_test_and_clear(int flag, struct mm_struct *mm)
 {
-	/* When detaching vma should be write-locked */
-	if (detached)
-		vma_assert_write_locked(vma);
-	vma->detached = detached;
+	return test_and_clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
 }
 
-struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
-					  unsigned long address);
+static inline void mm_flags_set(int flag, struct mm_struct *mm)
+{
+	set_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
+}
 
-#else /* CONFIG_PER_VMA_LOCK */
+static inline void mm_flags_clear(int flag, struct mm_struct *mm)
+{
+	clear_bit(flag, ACCESS_PRIVATE(&mm->flags, __mm_flags));
+}
 
-static inline void vma_init_lock(struct vm_area_struct *vma) {}
-static inline bool vma_start_read(struct vm_area_struct *vma)
-		{ return false; }
-static inline void vma_end_read(struct vm_area_struct *vma) {}
-static inline void vma_start_write(struct vm_area_struct *vma) {}
-static inline bool vma_try_start_write(struct vm_area_struct *vma)
-		{ return true; }
-static inline void vma_assert_write_locked(struct vm_area_struct *vma) {}
-static inline void vma_mark_detached(struct vm_area_struct *vma,
-				     bool detached) {}
+static inline void mm_flags_clear_all(struct mm_struct *mm)
+{
+	bitmap_zero(ACCESS_PRIVATE(&mm->flags, __mm_flags), NUM_MM_FLAG_BITS);
+}
 
-#endif /* CONFIG_PER_VMA_LOCK */
+extern const struct vm_operations_struct vma_dummy_vm_ops;
 
-/*
- * WARNING: vma_init does not initialize vma->vm_lock.
- * Use vm_area_alloc()/vm_area_free() if vma needs locking.
- */
 static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
 {
-	static const struct vm_operations_struct dummy_vm_ops = {};
-
 	memset(vma, 0, sizeof(*vma));
 	vma->vm_mm = mm;
-	vma->vm_ops = &dummy_vm_ops;
+	vma->vm_ops = &vma_dummy_vm_ops;
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
-	vma_mark_detached(vma, false);
-	vma_numab_state_init(vma);
+	vma_lock_init(vma, false);
 }
 
 /* Use when VMA is not part of the VMA tree and needs no locking */
 static inline void vm_flags_init(struct vm_area_struct *vma,
 				 vm_flags_t flags)
 {
-	ACCESS_PRIVATE(vma, __vm_flags) = flags;
+	VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY));
+	vma_flags_clear_all(&vma->flags);
+	vma_flags_overwrite_word(&vma->flags, flags);
 }
 
-/* Use when VMA is part of the VMA tree and modifications need coordination */
+/*
+ * Use when VMA is part of the VMA tree and modifications need coordination
+ * Note: vm_flags_reset and vm_flags_reset_once do not lock the vma and
+ * it should be locked explicitly beforehand.
+ */
 static inline void vm_flags_reset(struct vm_area_struct *vma,
 				  vm_flags_t flags)
 {
-	vma_start_write(vma);
+	VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY));
+	vma_assert_write_locked(vma);
 	vm_flags_init(vma, flags);
 }
 
 static inline void vm_flags_reset_once(struct vm_area_struct *vma,
 				       vm_flags_t flags)
 {
-	vma_start_write(vma);
-	WRITE_ONCE(ACCESS_PRIVATE(vma, __vm_flags), flags);
+	vma_assert_write_locked(vma);
+	/*
+	 * If VMA flags exist beyond the first system word, also clear these. It
+	 * is assumed the write once behaviour is required only for the first
+	 * system word.
+	 */
+	if (NUM_VMA_FLAG_BITS > BITS_PER_LONG) {
+		unsigned long *bitmap = ACCESS_PRIVATE(&vma->flags, __vma_flags);
+
+		bitmap_zero(&bitmap[1], NUM_VMA_FLAG_BITS - BITS_PER_LONG);
+	}
+
+	vma_flags_overwrite_word_once(&vma->flags, flags);
 }
 
 static inline void vm_flags_set(struct vm_area_struct *vma,
 				vm_flags_t flags)
 {
 	vma_start_write(vma);
-	ACCESS_PRIVATE(vma, __vm_flags) |= flags;
+	vma_flags_set_word(&vma->flags, flags);
 }
 
 static inline void vm_flags_clear(struct vm_area_struct *vma,
 				  vm_flags_t flags)
 {
+	VM_WARN_ON_ONCE(!pgtable_supports_soft_dirty() && (flags & VM_SOFTDIRTY));
 	vma_start_write(vma);
-	ACCESS_PRIVATE(vma, __vm_flags) &= ~flags;
+	vma_flags_clear_word(&vma->flags, flags);
 }
 
 /*
@@ -811,6 +982,51 @@ static inline void vm_flags_mod(struct vm_area_struct *vma,
 	__vm_flags_mod(vma, set, clear);
 }
 
+static inline bool __vma_flag_atomic_valid(struct vm_area_struct *vma,
+					   vma_flag_t bit)
+{
+	const vm_flags_t mask = BIT((__force int)bit);
+
+	/* Only specific flags are permitted */
+	if (WARN_ON_ONCE(!(mask & VM_ATOMIC_SET_ALLOWED)))
+		return false;
+
+	return true;
+}
+
+/*
+ * Set VMA flag atomically. Requires only VMA/mmap read lock. Only specific
+ * valid flags are allowed to do this.
+ */
+static inline void vma_flag_set_atomic(struct vm_area_struct *vma,
+				       vma_flag_t bit)
+{
+	unsigned long *bitmap = ACCESS_PRIVATE(&vma->flags, __vma_flags);
+
+	/* mmap read lock/VMA read lock must be held. */
+	if (!rwsem_is_locked(&vma->vm_mm->mmap_lock))
+		vma_assert_locked(vma);
+
+	if (__vma_flag_atomic_valid(vma, bit))
+		set_bit((__force int)bit, bitmap);
+}
+
+/*
+ * Test for VMA flag atomically. Requires no locks. Only specific valid flags
+ * are allowed to do this.
+ *
+ * This is necessarily racey, so callers must ensure that serialisation is
+ * achieved through some other means, or that races are permissible.
+ */
+static inline bool vma_flag_test_atomic(struct vm_area_struct *vma,
+					vma_flag_t bit)
+{
+	if (__vma_flag_atomic_valid(vma, bit))
+		return test_bit((__force int)bit, &vma->vm_flags);
+
+	return false;
+}
+
 static inline void vma_set_anonymous(struct vm_area_struct *vma)
 {
 	vma->vm_ops = NULL;
@@ -821,7 +1037,32 @@ static inline bool vma_is_anonymous(struct vm_area_struct *vma)
 	return !vma->vm_ops;
 }
 
-static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
+/*
+ * Indicate if the VMA is a heap for the given task; for
+ * /proc/PID/maps that is the heap of the main task.
+ */
+static inline bool vma_is_initial_heap(const struct vm_area_struct *vma)
+{
+	return vma->vm_start < vma->vm_mm->brk &&
+		vma->vm_end > vma->vm_mm->start_brk;
+}
+
+/*
+ * Indicate if the VMA is a stack for the given task; for
+ * /proc/PID/maps that is the stack of the main task.
+ */
+static inline bool vma_is_initial_stack(const struct vm_area_struct *vma)
+{
+	/*
+	 * We make no effort to guess what a given thread considers to be
+	 * its "stack".  It's not even well-defined for programs written
+	 * languages like Go.
+	 */
+	return vma->vm_start <= vma->vm_mm->start_stack &&
+		vma->vm_end >= vma->vm_mm->start_stack;
+}
+
+static inline bool vma_is_temporary_stack(const struct vm_area_struct *vma)
 {
 	int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP);
 
@@ -835,7 +1076,7 @@ static inline bool vma_is_temporary_stack(struct vm_area_struct *vma)
 	return false;
 }
 
-static inline bool vma_is_foreign(struct vm_area_struct *vma)
+static inline bool vma_is_foreign(const struct vm_area_struct *vma)
 {
 	if (!current->mm)
 		return true;
@@ -846,11 +1087,22 @@ static inline bool vma_is_foreign(struct vm_area_struct *vma)
 	return false;
 }
 
-static inline bool vma_is_accessible(struct vm_area_struct *vma)
+static inline bool vma_is_accessible(const struct vm_area_struct *vma)
 {
 	return vma->vm_flags & VM_ACCESS_FLAGS;
 }
 
+static inline bool is_shared_maywrite(vm_flags_t vm_flags)
+{
+	return (vm_flags & (VM_SHARED | VM_MAYWRITE)) ==
+		(VM_SHARED | VM_MAYWRITE);
+}
+
+static inline bool vma_is_shared_maywrite(const struct vm_area_struct *vma)
+{
+	return is_shared_maywrite(vma->vm_flags);
+}
+
 static inline
 struct vm_area_struct *vma_find(struct vma_iterator *vmi, unsigned long max)
 {
@@ -878,25 +1130,15 @@ static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
 	return mas_prev(&vmi->mas, 0);
 }
 
-static inline
-struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi)
-{
-	return mas_prev_range(&vmi->mas, 0);
-}
-
-static inline unsigned long vma_iter_addr(struct vma_iterator *vmi)
+static inline int vma_iter_clear_gfp(struct vma_iterator *vmi,
+			unsigned long start, unsigned long end, gfp_t gfp)
 {
-	return vmi->mas.index;
-}
+	__mas_set_range(&vmi->mas, start, end - 1);
+	mas_store_gfp(&vmi->mas, NULL, gfp);
+	if (unlikely(mas_is_err(&vmi->mas)))
+		return -ENOMEM;
 
-static inline unsigned long vma_iter_end(struct vma_iterator *vmi)
-{
-	return vmi->mas.last + 1;
-}
-static inline int vma_iter_bulk_alloc(struct vma_iterator *vmi,
-				      unsigned long count)
-{
-	return mas_expected_entries(&vmi->mas, count);
+	return 0;
 }
 
 /* Free any unused preallocations */
@@ -914,6 +1156,7 @@ static inline int vma_iter_bulk_store(struct vma_iterator *vmi,
 	if (unlikely(mas_is_err(&vmi->mas)))
 		return -ENOMEM;
 
+	vma_mark_attached(vma);
 	return 0;
 }
 
@@ -939,14 +1182,14 @@ static inline void vma_iter_set(struct vma_iterator *vmi, unsigned long addr)
  * The vma_is_shmem is not inline because it is used only by slow
  * paths in userfault.
  */
-bool vma_is_shmem(struct vm_area_struct *vma);
-bool vma_is_anon_shmem(struct vm_area_struct *vma);
+bool vma_is_shmem(const struct vm_area_struct *vma);
+bool vma_is_anon_shmem(const struct vm_area_struct *vma);
 #else
-static inline bool vma_is_shmem(struct vm_area_struct *vma) { return false; }
-static inline bool vma_is_anon_shmem(struct vm_area_struct *vma) { return false; }
+static inline bool vma_is_shmem(const struct vm_area_struct *vma) { return false; }
+static inline bool vma_is_anon_shmem(const struct vm_area_struct *vma) { return false; }
 #endif
 
-int vma_is_stack_for_current(struct vm_area_struct *vma);
+int vma_is_stack_for_current(const struct vm_area_struct *vma);
 
 /* flush_tlb_range() takes a vma, not a mm, and can care about flags */
 #define TLB_FLUSH_VMA(mm,flags) { .vm_mm = (mm), .vm_flags = (flags) }
@@ -954,20 +1197,39 @@ int vma_is_stack_for_current(struct vm_area_struct *vma);
 struct mmu_gather;
 struct inode;
 
+extern void prep_compound_page(struct page *page, unsigned int order);
+
+static inline unsigned int folio_large_order(const struct folio *folio)
+{
+	return folio->_flags_1 & 0xff;
+}
+
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+static inline unsigned long folio_large_nr_pages(const struct folio *folio)
+{
+	return folio->_nr_pages;
+}
+#else
+static inline unsigned long folio_large_nr_pages(const struct folio *folio)
+{
+	return 1L << folio_large_order(folio);
+}
+#endif
+
 /*
  * compound_order() can be called without holding a reference, which means
  * that niceties like page_folio() don't work.  These callers should be
  * prepared to handle wild return values.  For example, PG_head may be
- * set before _folio_order is initialised, or this may be a tail page.
+ * set before the order is initialised, or this may be a tail page.
  * See compaction.c for some good examples.
  */
-static inline unsigned int compound_order(struct page *page)
+static inline unsigned int compound_order(const struct page *page)
 {
-	struct folio *folio = (struct folio *)page;
+	const struct folio *folio = (struct folio *)page;
 
-	if (!test_bit(PG_head, &folio->flags))
+	if (!test_bit(PG_head, &folio->flags.f))
 		return 0;
-	return folio->_folio_order;
+	return folio_large_order(folio);
 }
 
 /**
@@ -979,11 +1241,28 @@ static inline unsigned int compound_order(struct page *page)
  *
  * Return: The order of the folio.
  */
-static inline unsigned int folio_order(struct folio *folio)
+static inline unsigned int folio_order(const struct folio *folio)
 {
 	if (!folio_test_large(folio))
 		return 0;
-	return folio->_folio_order;
+	return folio_large_order(folio);
+}
+
+/**
+ * folio_reset_order - Reset the folio order and derived _nr_pages
+ * @folio: The folio.
+ *
+ * Reset the order and derived _nr_pages to 0. Must only be used in the
+ * process of splitting large folios.
+ */
+static inline void folio_reset_order(struct folio *folio)
+{
+	if (WARN_ON_ONCE(!folio_test_large(folio)))
+		return;
+	folio->_flags_1 &= ~0xffUL;
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+	folio->_nr_pages = 0;
+#endif
 }
 
 #include <linux/huge_mm.h>
@@ -1054,11 +1333,6 @@ unsigned long vmalloc_to_pfn(const void *addr);
  * On nommu, vmalloc/vfree wrap through kmalloc/kfree directly, so there
  * is no special casing required.
  */
-
-#ifndef is_ioremap_addr
-#define is_ioremap_addr(x) is_vmalloc_addr(x)
-#endif
-
 #ifdef CONFIG_MMU
 extern bool is_vmalloc_addr(const void *x);
 extern int is_vmalloc_or_module_addr(const void *x);
@@ -1076,82 +1350,53 @@ static inline int is_vmalloc_or_module_addr(const void *x)
 /*
  * How many times the entire folio is mapped as a single unit (eg by a
  * PMD or PUD entry).  This is probably not what you want, except for
- * debugging purposes - it does not include PTE-mapped sub-pages; look
- * at folio_mapcount() or page_mapcount() or total_mapcount() instead.
+ * debugging purposes or implementation of other core folio_*() primitives.
  */
-static inline int folio_entire_mapcount(struct folio *folio)
+static inline int folio_entire_mapcount(const struct folio *folio)
 {
 	VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
+	if (!IS_ENABLED(CONFIG_64BIT) && unlikely(folio_large_order(folio) == 1))
+		return 0;
 	return atomic_read(&folio->_entire_mapcount) + 1;
 }
 
-/*
- * The atomic page->_mapcount, starts from -1: so that transitions
- * both from it and to it can be tracked, using atomic_inc_and_test
- * and atomic_add_negative(-1).
- */
-static inline void page_mapcount_reset(struct page *page)
+static inline int folio_large_mapcount(const struct folio *folio)
 {
-	atomic_set(&(page)->_mapcount, -1);
+	VM_WARN_ON_FOLIO(!folio_test_large(folio), folio);
+	return atomic_read(&folio->_large_mapcount) + 1;
 }
 
 /**
- * page_mapcount() - Number of times this precise page is mapped.
- * @page: The page.
+ * folio_mapcount() - Number of mappings of this folio.
+ * @folio: The folio.
  *
- * The number of times this page is mapped.  If this page is part of
- * a large folio, it includes the number of times this page is mapped
- * as part of that folio.
+ * The folio mapcount corresponds to the number of present user page table
+ * entries that reference any part of a folio. Each such present user page
+ * table entry must be paired with exactly on folio reference.
  *
- * The result is undefined for pages which cannot be mapped into userspace.
- * For example SLAB or special types of pages. See function page_has_type().
- * They use this field in struct page differently.
- */
-static inline int page_mapcount(struct page *page)
-{
-	int mapcount = atomic_read(&page->_mapcount) + 1;
-
-	if (unlikely(PageCompound(page)))
-		mapcount += folio_entire_mapcount(page_folio(page));
-
-	return mapcount;
-}
-
-int folio_total_mapcount(struct folio *folio);
-
-/**
- * folio_mapcount() - Calculate the number of mappings of this folio.
- * @folio: The folio.
+ * For ordindary folios, each user page table entry (PTE/PMD/PUD/...) counts
+ * exactly once.
+ *
+ * For hugetlb folios, each abstracted "hugetlb" user page table entry that
+ * references the entire folio counts exactly once, even when such special
+ * page table entries are comprised of multiple ordinary page table entries.
  *
- * A large folio tracks both how many times the entire folio is mapped,
- * and how many times each individual page in the folio is mapped.
- * This function calculates the total number of times the folio is
- * mapped.
+ * Will report 0 for pages which cannot be mapped into userspace, such as
+ * slab, page tables and similar.
  *
  * Return: The number of times this folio is mapped.
  */
-static inline int folio_mapcount(struct folio *folio)
-{
-	if (likely(!folio_test_large(folio)))
-		return atomic_read(&folio->_mapcount) + 1;
-	return folio_total_mapcount(folio);
-}
-
-static inline int total_mapcount(struct page *page)
+static inline int folio_mapcount(const struct folio *folio)
 {
-	if (likely(!PageCompound(page)))
-		return atomic_read(&page->_mapcount) + 1;
-	return folio_total_mapcount(page_folio(page));
-}
+	int mapcount;
 
-static inline bool folio_large_is_mapped(struct folio *folio)
-{
-	/*
-	 * Reading _entire_mapcount below could be omitted if hugetlb
-	 * participated in incrementing nr_pages_mapped when compound mapped.
-	 */
-	return atomic_read(&folio->_nr_pages_mapped) > 0 ||
-		atomic_read(&folio->_entire_mapcount) >= 0;
+	if (likely(!folio_test_large(folio))) {
+		mapcount = atomic_read(&folio->_mapcount) + 1;
+		if (page_mapcount_is_type(mapcount))
+			mapcount = 0;
+		return mapcount;
+	}
+	return folio_large_mapcount(folio);
 }
 
 /**
@@ -1160,11 +1405,9 @@ static inline bool folio_large_is_mapped(struct folio *folio)
  *
  * Return: True if any page in this folio is referenced by user page tables.
  */
-static inline bool folio_mapped(struct folio *folio)
+static inline bool folio_mapped(const struct folio *folio)
 {
-	if (likely(!folio_test_large(folio)))
-		return atomic_read(&folio->_mapcount) >= 0;
-	return folio_large_is_mapped(folio);
+	return folio_mapcount(folio) >= 1;
 }
 
 /*
@@ -1172,11 +1415,9 @@ static inline bool folio_mapped(struct folio *folio)
  * For compound page it returns true if any sub-page of compound page is mapped,
  * even if this particular sub-page is not itself mapped by any PTE or PMD.
  */
-static inline bool page_mapped(struct page *page)
+static inline bool page_mapped(const struct page *page)
 {
-	if (likely(!PageCompound(page)))
-		return atomic_read(&page->_mapcount) >= 0;
-	return folio_large_is_mapped(page_folio(page));
+	return folio_mapped(page_folio(page));
 }
 
 static inline struct page *virt_to_head_page(const void *x)
@@ -1195,65 +1436,14 @@ static inline struct folio *virt_to_folio(const void *x)
 
 void __folio_put(struct folio *folio);
 
-void put_pages_list(struct list_head *pages);
-
 void split_page(struct page *page, unsigned int order);
 void folio_copy(struct folio *dst, struct folio *src);
+int folio_mc_copy(struct folio *dst, struct folio *src);
 
 unsigned long nr_free_buffer_pages(void);
 
-/*
- * Compound pages have a destructor function.  Provide a
- * prototype for that function and accessor functions.
- * These are _only_ valid on the head of a compound page.
- */
-typedef void compound_page_dtor(struct page *);
-
-/* Keep the enum in sync with compound_page_dtors array in mm/page_alloc.c */
-enum compound_dtor_id {
-	NULL_COMPOUND_DTOR,
-	COMPOUND_PAGE_DTOR,
-#ifdef CONFIG_HUGETLB_PAGE
-	HUGETLB_PAGE_DTOR,
-#endif
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	TRANSHUGE_PAGE_DTOR,
-#endif
-	NR_COMPOUND_DTORS,
-};
-extern compound_page_dtor * const compound_page_dtors[NR_COMPOUND_DTORS];
-
-static inline void set_compound_page_dtor(struct page *page,
-		enum compound_dtor_id compound_dtor)
-{
-	struct folio *folio = (struct folio *)page;
-
-	VM_BUG_ON_PAGE(compound_dtor >= NR_COMPOUND_DTORS, page);
-	VM_BUG_ON_PAGE(!PageHead(page), page);
-	folio->_folio_dtor = compound_dtor;
-}
-
-static inline void folio_set_compound_dtor(struct folio *folio,
-		enum compound_dtor_id compound_dtor)
-{
-	VM_BUG_ON_FOLIO(compound_dtor >= NR_COMPOUND_DTORS, folio);
-	folio->_folio_dtor = compound_dtor;
-}
-
-void destroy_large_folio(struct folio *folio);
-
-static inline void set_compound_order(struct page *page, unsigned int order)
-{
-	struct folio *folio = (struct folio *)page;
-
-	folio->_folio_order = order;
-#ifdef CONFIG_64BIT
-	folio->_folio_nr_pages = 1U << order;
-#endif
-}
-
 /* Returns the number of bytes in this potentially compound page. */
-static inline unsigned long page_size(struct page *page)
+static inline unsigned long page_size(const struct page *page)
 {
 	return PAGE_SIZE << compound_order(page);
 }
@@ -1285,8 +1475,6 @@ static inline unsigned long thp_size(struct page *page)
 	return PAGE_SIZE << thp_order(page);
 }
 
-void free_compound_page(struct page *page);
-
 #ifdef CONFIG_MMU
 /*
  * Do pte_mkwrite, but only if the vma says VM_WRITE.  We do this when
@@ -1297,15 +1485,15 @@ void free_compound_page(struct page *page);
 static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
 {
 	if (likely(vma->vm_flags & VM_WRITE))
-		pte = pte_mkwrite(pte);
+		pte = pte_mkwrite(pte, vma);
 	return pte;
 }
 
-vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page);
-void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr);
+vm_fault_t do_set_pmd(struct vm_fault *vmf, struct folio *folio, struct page *page);
+void set_pte_range(struct vm_fault *vmf, struct folio *folio,
+		struct page *page, unsigned int nr, unsigned long addr);
 
 vm_fault_t finish_fault(struct vm_fault *vmf);
-vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
 #endif
 
 /*
@@ -1342,9 +1530,9 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
  * the page's disk buffers. PG_private must be set to tell the VM to call
  * into the filesystem to release these pages.
  *
- * A page may belong to an inode's memory mapping. In this case, page->mapping
- * is the pointer to the inode, and page->index is the file offset of the page,
- * in units of PAGE_SIZE.
+ * A folio may belong to an inode's memory mapping. In this case,
+ * folio->mapping points to the inode, and folio->index is the file
+ * offset of the folio, in units of PAGE_SIZE.
  *
  * If pagecache pages are not associated with an inode, they are said to be
  * anonymous pages. These may become associated with the swapcache, and in that
@@ -1368,30 +1556,6 @@ vm_fault_t finish_mkwrite_fault(struct vm_fault *vmf);
  *   back into memory.
  */
 
-#if defined(CONFIG_ZONE_DEVICE) && defined(CONFIG_FS_DAX)
-DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
-
-bool __put_devmap_managed_page_refs(struct page *page, int refs);
-static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
-{
-	if (!static_branch_unlikely(&devmap_managed_key))
-		return false;
-	if (!is_zone_device_page(page))
-		return false;
-	return __put_devmap_managed_page_refs(page, refs);
-}
-#else /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-static inline bool put_devmap_managed_page_refs(struct page *page, int refs)
-{
-	return false;
-}
-#endif /* CONFIG_ZONE_DEVICE && CONFIG_FS_DAX */
-
-static inline bool put_devmap_managed_page(struct page *page)
-{
-	return put_devmap_managed_page_refs(page, 1);
-}
-
 /* 127: arbitrary random number, small enough to assemble well */
 #define folio_ref_zero_or_close_to_overflow(folio) \
 	((unsigned int) folio_ref_count(folio) + 127u <= 127u)
@@ -1412,7 +1576,12 @@ static inline void folio_get(struct folio *folio)
 
 static inline void get_page(struct page *page)
 {
-	folio_get(page_folio(page));
+	struct folio *folio = page_folio(page);
+	if (WARN_ON_ONCE(folio_test_slab(folio)))
+		return;
+	if (WARN_ON_ONCE(folio_test_large_kmalloc(folio)))
+		return;
+	folio_get(folio);
 }
 
 static inline __must_check bool try_get_page(struct page *page)
@@ -1463,6 +1632,8 @@ static inline void folio_put_refs(struct folio *folio, int refs)
 		__folio_put(folio);
 }
 
+void folios_put_refs(struct folio_batch *folios, unsigned int *refs);
+
 /*
  * union release_pages_arg - an array of pages or folios
  *
@@ -1485,30 +1656,28 @@ void release_pages(release_pages_arg, int nr);
 /**
  * folios_put - Decrement the reference count on an array of folios.
  * @folios: The folios.
- * @nr: How many folios there are.
  *
- * Like folio_put(), but for an array of folios.  This is more efficient
- * than writing the loop yourself as it will optimise the locks which
- * need to be taken if the folios are freed.
+ * Like folio_put(), but for a batch of folios.  This is more efficient
+ * than writing the loop yourself as it will optimise the locks which need
+ * to be taken if the folios are freed.  The folios batch is returned
+ * empty and ready to be reused for another batch; there is no need to
+ * reinitialise it.
  *
  * Context: May be called in process or interrupt context, but not in NMI
  * context.  May be called while holding a spinlock.
  */
-static inline void folios_put(struct folio **folios, unsigned int nr)
+static inline void folios_put(struct folio_batch *folios)
 {
-	release_pages(folios, nr);
+	folios_put_refs(folios, NULL);
 }
 
 static inline void put_page(struct page *page)
 {
 	struct folio *folio = page_folio(page);
 
-	/*
-	 * For some devmap managed pages we need to catch refcount transition
-	 * from 2 to 1:
-	 */
-	if (put_devmap_managed_page(&folio->page))
+	if (folio_test_slab(folio) || folio_test_large_kmalloc(folio))
 		return;
+
 	folio_put(folio);
 }
 
@@ -1539,17 +1708,20 @@ static inline void put_page(struct page *page)
  * issue.
  *
  * Locking: the lockless algorithm described in folio_try_get_rcu()
- * provides safe operation for get_user_pages(), page_mkclean() and
+ * provides safe operation for get_user_pages(), folio_mkclean() and
  * other calls that race to set up page table entries.
  */
 #define GUP_PIN_COUNTING_BIAS (1U << 10)
 
 void unpin_user_page(struct page *page);
+void unpin_folio(struct folio *folio);
 void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages,
 				 bool make_dirty);
 void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages,
 				      bool make_dirty);
 void unpin_user_pages(struct page **pages, unsigned long npages);
+void unpin_user_folio(struct folio *folio, unsigned long npages);
+void unpin_folios(struct folio **folios, unsigned long nfolios);
 
 static inline bool is_cow_mapping(vm_flags_t flags)
 {
@@ -1585,23 +1757,26 @@ static inline bool is_nommu_shared_mapping(vm_flags_t flags)
  */
 static inline int page_zone_id(struct page *page)
 {
-	return (page->flags >> ZONEID_PGSHIFT) & ZONEID_MASK;
+	return (page->flags.f >> ZONEID_PGSHIFT) & ZONEID_MASK;
 }
 
 #ifdef NODE_NOT_IN_PAGE_FLAGS
-extern int page_to_nid(const struct page *page);
+int memdesc_nid(memdesc_flags_t mdf);
 #else
-static inline int page_to_nid(const struct page *page)
+static inline int memdesc_nid(memdesc_flags_t mdf)
 {
-	struct page *p = (struct page *)page;
-
-	return (PF_POISONED_CHECK(p)->flags >> NODES_PGSHIFT) & NODES_MASK;
+	return (mdf.f >> NODES_PGSHIFT) & NODES_MASK;
 }
 #endif
 
+static inline int page_to_nid(const struct page *page)
+{
+	return memdesc_nid(PF_POISONED_CHECK(page)->flags);
+}
+
 static inline int folio_nid(const struct folio *folio)
 {
-	return page_to_nid(&folio->page);
+	return memdesc_nid(folio->flags);
 }
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -1654,38 +1829,39 @@ static inline bool __cpupid_match_pid(pid_t task_pid, int cpupid)
 
 #define cpupid_match_pid(task, cpupid) __cpupid_match_pid(task->pid, cpupid)
 #ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
-static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
+static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
 {
-	return xchg(&page->_last_cpupid, cpupid & LAST_CPUPID_MASK);
+	return xchg(&folio->_last_cpupid, cpupid & LAST_CPUPID_MASK);
 }
 
-static inline int page_cpupid_last(struct page *page)
+static inline int folio_last_cpupid(struct folio *folio)
 {
-	return page->_last_cpupid;
+	return folio->_last_cpupid;
 }
 static inline void page_cpupid_reset_last(struct page *page)
 {
 	page->_last_cpupid = -1 & LAST_CPUPID_MASK;
 }
 #else
-static inline int page_cpupid_last(struct page *page)
+static inline int folio_last_cpupid(struct folio *folio)
 {
-	return (page->flags >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
+	return (folio->flags.f >> LAST_CPUPID_PGSHIFT) & LAST_CPUPID_MASK;
 }
 
-extern int page_cpupid_xchg_last(struct page *page, int cpupid);
+int folio_xchg_last_cpupid(struct folio *folio, int cpupid);
 
 static inline void page_cpupid_reset_last(struct page *page)
 {
-	page->flags |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT;
+	page->flags.f |= LAST_CPUPID_MASK << LAST_CPUPID_PGSHIFT;
 }
 #endif /* LAST_CPUPID_NOT_IN_PAGE_FLAGS */
 
-static inline int xchg_page_access_time(struct page *page, int time)
+static inline int folio_xchg_access_time(struct folio *folio, int time)
 {
 	int last_time;
 
-	last_time = page_cpupid_xchg_last(page, time >> PAGE_ACCESS_TIME_BUCKETS);
+	last_time = folio_xchg_last_cpupid(folio,
+					   time >> PAGE_ACCESS_TIME_BUCKETS);
 	return last_time << PAGE_ACCESS_TIME_BUCKETS;
 }
 
@@ -1694,24 +1870,26 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 	unsigned int pid_bit;
 
 	pid_bit = hash_32(current->pid, ilog2(BITS_PER_LONG));
-	if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->access_pids[1])) {
-		__set_bit(pid_bit, &vma->numab_state->access_pids[1]);
+	if (vma->numab_state && !test_bit(pid_bit, &vma->numab_state->pids_active[1])) {
+		__set_bit(pid_bit, &vma->numab_state->pids_active[1]);
 	}
 }
+
+bool folio_use_access_time(struct folio *folio);
 #else /* !CONFIG_NUMA_BALANCING */
-static inline int page_cpupid_xchg_last(struct page *page, int cpupid)
+static inline int folio_xchg_last_cpupid(struct folio *folio, int cpupid)
 {
-	return page_to_nid(page); /* XXX */
+	return folio_nid(folio); /* XXX */
 }
 
-static inline int xchg_page_access_time(struct page *page, int time)
+static inline int folio_xchg_access_time(struct folio *folio, int time)
 {
 	return 0;
 }
 
-static inline int page_cpupid_last(struct page *page)
+static inline int folio_last_cpupid(struct folio *folio)
 {
-	return page_to_nid(page); /* XXX */
+	return folio_nid(folio); /* XXX */
 }
 
 static inline int cpupid_to_nid(int cpupid)
@@ -1751,6 +1929,10 @@ static inline bool cpupid_match_pid(struct task_struct *task, int cpupid)
 static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 {
 }
+static inline bool folio_use_access_time(struct folio *folio)
+{
+	return false;
+}
 #endif /* CONFIG_NUMA_BALANCING */
 
 #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
@@ -1763,10 +1945,10 @@ static inline void vma_set_access_pid_bit(struct vm_area_struct *vma)
 
 static inline u8 page_kasan_tag(const struct page *page)
 {
-	u8 tag = 0xff;
+	u8 tag = KASAN_TAG_KERNEL;
 
 	if (kasan_enabled()) {
-		tag = (page->flags >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
+		tag = (page->flags.f >> KASAN_TAG_PGSHIFT) & KASAN_TAG_MASK;
 		tag ^= 0xff;
 	}
 
@@ -1781,18 +1963,18 @@ static inline void page_kasan_tag_set(struct page *page, u8 tag)
 		return;
 
 	tag ^= 0xff;
-	old_flags = READ_ONCE(page->flags);
+	old_flags = READ_ONCE(page->flags.f);
 	do {
 		flags = old_flags;
 		flags &= ~(KASAN_TAG_MASK << KASAN_TAG_PGSHIFT);
 		flags |= (tag & KASAN_TAG_MASK) << KASAN_TAG_PGSHIFT;
-	} while (unlikely(!try_cmpxchg(&page->flags, &old_flags, flags)));
+	} while (unlikely(!try_cmpxchg(&page->flags.f, &old_flags, flags)));
 }
 
 static inline void page_kasan_tag_reset(struct page *page)
 {
 	if (kasan_enabled())
-		page_kasan_tag_set(page, 0xff);
+		page_kasan_tag_set(page, KASAN_TAG_KERNEL);
 }
 
 #else /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */
@@ -1817,28 +1999,33 @@ static inline pg_data_t *page_pgdat(const struct page *page)
 	return NODE_DATA(page_to_nid(page));
 }
 
-static inline struct zone *folio_zone(const struct folio *folio)
+static inline pg_data_t *folio_pgdat(const struct folio *folio)
 {
-	return page_zone(&folio->page);
+	return NODE_DATA(folio_nid(folio));
 }
 
-static inline pg_data_t *folio_pgdat(const struct folio *folio)
+static inline struct zone *folio_zone(const struct folio *folio)
 {
-	return page_pgdat(&folio->page);
+	return &folio_pgdat(folio)->node_zones[folio_zonenum(folio)];
 }
 
 #ifdef SECTION_IN_PAGE_FLAGS
 static inline void set_page_section(struct page *page, unsigned long section)
 {
-	page->flags &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
-	page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
+	page->flags.f &= ~(SECTIONS_MASK << SECTIONS_PGSHIFT);
+	page->flags.f |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT;
 }
 
-static inline unsigned long page_to_section(const struct page *page)
+static inline unsigned long memdesc_section(memdesc_flags_t mdf)
 {
-	return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
+	return (mdf.f >> SECTIONS_PGSHIFT) & SECTIONS_MASK;
 }
-#endif
+#else /* !SECTION_IN_PAGE_FLAGS */
+static inline unsigned long memdesc_section(memdesc_flags_t mdf)
+{
+	return 0;
+}
+#endif /* SECTION_IN_PAGE_FLAGS */
 
 /**
  * folio_pfn - Return the Page Frame Number of a folio.
@@ -1849,7 +2036,7 @@ static inline unsigned long page_to_section(const struct page *page)
  *
  * Return: The Page Frame Number of the first page in the folio.
  */
-static inline unsigned long folio_pfn(struct folio *folio)
+static inline unsigned long folio_pfn(const struct folio *folio)
 {
 	return page_to_pfn(&folio->page);
 }
@@ -1859,6 +2046,69 @@ static inline struct folio *pfn_folio(unsigned long pfn)
 	return page_folio(pfn_to_page(pfn));
 }
 
+#ifdef CONFIG_MMU
+static inline pte_t mk_pte(const struct page *page, pgprot_t pgprot)
+{
+	return pfn_pte(page_to_pfn(page), pgprot);
+}
+
+/**
+ * folio_mk_pte - Create a PTE for this folio
+ * @folio: The folio to create a PTE for
+ * @pgprot: The page protection bits to use
+ *
+ * Create a page table entry for the first page of this folio.
+ * This is suitable for passing to set_ptes().
+ *
+ * Return: A page table entry suitable for mapping this folio.
+ */
+static inline pte_t folio_mk_pte(const struct folio *folio, pgprot_t pgprot)
+{
+	return pfn_pte(folio_pfn(folio), pgprot);
+}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+/**
+ * folio_mk_pmd - Create a PMD for this folio
+ * @folio: The folio to create a PMD for
+ * @pgprot: The page protection bits to use
+ *
+ * Create a page table entry for the first page of this folio.
+ * This is suitable for passing to set_pmd_at().
+ *
+ * Return: A page table entry suitable for mapping this folio.
+ */
+static inline pmd_t folio_mk_pmd(const struct folio *folio, pgprot_t pgprot)
+{
+	return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot));
+}
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/**
+ * folio_mk_pud - Create a PUD for this folio
+ * @folio: The folio to create a PUD for
+ * @pgprot: The page protection bits to use
+ *
+ * Create a page table entry for the first page of this folio.
+ * This is suitable for passing to set_pud_at().
+ *
+ * Return: A page table entry suitable for mapping this folio.
+ */
+static inline pud_t folio_mk_pud(const struct folio *folio, pgprot_t pgprot)
+{
+	return pud_mkhuge(pfn_pud(folio_pfn(folio), pgprot));
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+#endif /* CONFIG_MMU */
+
+static inline bool folio_has_pincount(const struct folio *folio)
+{
+	if (IS_ENABLED(CONFIG_64BIT))
+		return folio_test_large(folio);
+	return folio_order(folio) > 1;
+}
+
 /**
  * folio_maybe_dma_pinned - Report if a folio may be pinned for DMA.
  * @folio: The folio.
@@ -1875,18 +2125,18 @@ static inline struct folio *pfn_folio(unsigned long pfn)
  * get that many refcounts, and b) all the callers of this routine are
  * expected to be able to deal gracefully with a false positive.
  *
- * For large folios, the result will be exactly correct. That's because
+ * For most large folios, the result will be exactly correct. That's because
  * we have more tracking data available: the _pincount field is used
  * instead of the GUP_PIN_COUNTING_BIAS scheme.
  *
  * For more information, please see Documentation/core-api/pin_user_pages.rst.
  *
- * Return: True, if it is likely that the page has been "dma-pinned".
- * False, if the page is definitely not dma-pinned.
+ * Return: True, if it is likely that the folio has been "dma-pinned".
+ * False, if the folio is definitely not dma-pinned.
  */
 static inline bool folio_maybe_dma_pinned(struct folio *folio)
 {
-	if (folio_test_large(folio))
+	if (folio_has_pincount(folio))
 		return atomic_read(&folio->_pincount) > 0;
 
 	/*
@@ -1901,71 +2151,91 @@ static inline bool folio_maybe_dma_pinned(struct folio *folio)
 		GUP_PIN_COUNTING_BIAS;
 }
 
-static inline bool page_maybe_dma_pinned(struct page *page)
-{
-	return folio_maybe_dma_pinned(page_folio(page));
-}
-
 /*
  * This should most likely only be called during fork() to see whether we
  * should break the cow immediately for an anon page on the src mm.
  *
  * The caller has to hold the PT lock and the vma->vm_mm->->write_protect_seq.
  */
-static inline bool page_needs_cow_for_dma(struct vm_area_struct *vma,
-					  struct page *page)
+static inline bool folio_needs_cow_for_dma(struct vm_area_struct *vma,
+					  struct folio *folio)
 {
 	VM_BUG_ON(!(raw_read_seqcount(&vma->vm_mm->write_protect_seq) & 1));
 
-	if (!test_bit(MMF_HAS_PINNED, &vma->vm_mm->flags))
+	if (!mm_flags_test(MMF_HAS_PINNED, vma->vm_mm))
 		return false;
 
-	return page_maybe_dma_pinned(page);
+	return folio_maybe_dma_pinned(folio);
 }
 
-/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin pages */
+/**
+ * is_zero_page - Query if a page is a zero page
+ * @page: The page to query
+ *
+ * This returns true if @page is one of the permanent zero pages.
+ */
+static inline bool is_zero_page(const struct page *page)
+{
+	return is_zero_pfn(page_to_pfn(page));
+}
+
+/**
+ * is_zero_folio - Query if a folio is a zero page
+ * @folio: The folio to query
+ *
+ * This returns true if @folio is one of the permanent zero pages.
+ */
+static inline bool is_zero_folio(const struct folio *folio)
+{
+	return is_zero_page(&folio->page);
+}
+
+/* MIGRATE_CMA and ZONE_MOVABLE do not allow pin folios */
 #ifdef CONFIG_MIGRATION
-static inline bool is_longterm_pinnable_page(struct page *page)
+static inline bool folio_is_longterm_pinnable(struct folio *folio)
 {
 #ifdef CONFIG_CMA
-	int mt = get_pageblock_migratetype(page);
+	int mt = folio_migratetype(folio);
 
 	if (mt == MIGRATE_CMA || mt == MIGRATE_ISOLATE)
 		return false;
 #endif
-	/* The zero page may always be pinned */
-	if (is_zero_pfn(page_to_pfn(page)))
+	/* The zero page can be "pinned" but gets special handling. */
+	if (is_zero_folio(folio))
 		return true;
 
 	/* Coherent device memory must always allow eviction. */
-	if (is_device_coherent_page(page))
+	if (folio_is_device_coherent(folio))
 		return false;
 
-	/* Otherwise, non-movable zone pages can be pinned. */
-	return !is_zone_movable_page(page);
+	/*
+	 * Filesystems can only tolerate transient delays to truncate and
+	 * hole-punch operations
+	 */
+	if (folio_is_fsdax(folio))
+		return false;
+
+	/* Otherwise, non-movable zone folios can be pinned. */
+	return !folio_is_zone_movable(folio);
+
 }
 #else
-static inline bool is_longterm_pinnable_page(struct page *page)
+static inline bool folio_is_longterm_pinnable(struct folio *folio)
 {
 	return true;
 }
 #endif
 
-static inline bool folio_is_longterm_pinnable(struct folio *folio)
-{
-	return is_longterm_pinnable_page(&folio->page);
-}
-
 static inline void set_page_zone(struct page *page, enum zone_type zone)
 {
-	page->flags &= ~(ZONES_MASK << ZONES_PGSHIFT);
-	page->flags |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
+	page->flags.f &= ~(ZONES_MASK << ZONES_PGSHIFT);
+	page->flags.f |= (zone & ZONES_MASK) << ZONES_PGSHIFT;
 }
 
 static inline void set_page_node(struct page *page, unsigned long node)
 {
-	page->flags &= ~(NODES_MASK << NODES_PGSHIFT);
-	page->flags |= (node & NODES_MASK) << NODES_PGSHIFT;
+	page->flags.f &= ~(NODES_MASK << NODES_PGSHIFT);
+	page->flags.f |= (node & NODES_MASK) << NODES_PGSHIFT;
 }
 
 static inline void set_page_links(struct page *page, enum zone_type zone,
@@ -1984,42 +2254,55 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
  *
  * Return: A positive power of two.
  */
-static inline long folio_nr_pages(struct folio *folio)
+static inline unsigned long folio_nr_pages(const struct folio *folio)
 {
 	if (!folio_test_large(folio))
 		return 1;
-#ifdef CONFIG_64BIT
-	return folio->_folio_nr_pages;
+	return folio_large_nr_pages(folio);
+}
+
+#if !defined(CONFIG_HAVE_GIGANTIC_FOLIOS)
+/*
+ * We don't expect any folios that exceed buddy sizes (and consequently
+ * memory sections).
+ */
+#define MAX_FOLIO_ORDER		MAX_PAGE_ORDER
+#elif defined(CONFIG_SPARSEMEM) && !defined(CONFIG_SPARSEMEM_VMEMMAP)
+/*
+ * Only pages within a single memory section are guaranteed to be
+ * contiguous. By limiting folios to a single memory section, all folio
+ * pages are guaranteed to be contiguous.
+ */
+#define MAX_FOLIO_ORDER		PFN_SECTION_SHIFT
+#elif defined(CONFIG_HUGETLB_PAGE)
+/*
+ * There is no real limit on the folio size. We limit them to the maximum we
+ * currently expect (see CONFIG_HAVE_GIGANTIC_FOLIOS): with hugetlb, we expect
+ * no folios larger than 16 GiB on 64bit and 1 GiB on 32bit.
+ */
+#define MAX_FOLIO_ORDER		get_order(IS_ENABLED(CONFIG_64BIT) ? SZ_16G : SZ_1G)
 #else
-	return 1L << folio->_folio_order;
+/*
+ * Without hugetlb, gigantic folios that are bigger than a single PUD are
+ * currently impossible.
+ */
+#define MAX_FOLIO_ORDER		PUD_ORDER
 #endif
-}
+
+#define MAX_FOLIO_NR_PAGES	(1UL << MAX_FOLIO_ORDER)
 
 /*
  * compound_nr() returns the number of pages in this potentially compound
  * page.  compound_nr() can be called on a tail page, and is defined to
  * return 1 in that case.
  */
-static inline unsigned long compound_nr(struct page *page)
+static inline unsigned long compound_nr(const struct page *page)
 {
-	struct folio *folio = (struct folio *)page;
+	const struct folio *folio = (struct folio *)page;
 
-	if (!test_bit(PG_head, &folio->flags))
+	if (!test_bit(PG_head, &folio->flags.f))
 		return 1;
-#ifdef CONFIG_64BIT
-	return folio->_folio_nr_pages;
-#else
-	return 1L << folio->_folio_order;
-#endif
-}
-
-/**
- * thp_nr_pages - The number of regular pages in this huge page.
- * @page: The head page of a huge page.
- */
-static inline int thp_nr_pages(struct page *page)
-{
-	return folio_nr_pages((struct folio *)page);
+	return folio_large_nr_pages(folio);
 }
 
 /**
@@ -2053,7 +2336,7 @@ static inline struct folio *folio_next(struct folio *folio)
  * it from being split.  It is not necessary for the folio to be locked.
  * Return: The base-2 logarithm of the size of this folio.
  */
-static inline unsigned int folio_shift(struct folio *folio)
+static inline unsigned int folio_shift(const struct folio *folio)
 {
 	return PAGE_SHIFT + folio_order(folio);
 }
@@ -2066,49 +2349,134 @@ static inline unsigned int folio_shift(struct folio *folio)
  * it from being split.  It is not necessary for the folio to be locked.
  * Return: The number of bytes in this folio.
  */
-static inline size_t folio_size(struct folio *folio)
+static inline size_t folio_size(const struct folio *folio)
 {
 	return PAGE_SIZE << folio_order(folio);
 }
 
 /**
- * folio_estimated_sharers - Estimate the number of sharers of a folio.
+ * folio_maybe_mapped_shared - Whether the folio is mapped into the page
+ *			       tables of more than one MM
  * @folio: The folio.
  *
- * folio_estimated_sharers() aims to serve as a function to efficiently
- * estimate the number of processes sharing a folio. This is done by
- * looking at the precise mapcount of the first subpage in the folio, and
- * assuming the other subpages are the same. This may not be true for large
- * folios. If you want exact mapcounts for exact calculations, look at
- * page_mapcount() or folio_total_mapcount().
+ * This function checks if the folio maybe currently mapped into more than one
+ * MM ("maybe mapped shared"), or if the folio is certainly mapped into a single
+ * MM ("mapped exclusively").
+ *
+ * For KSM folios, this function also returns "mapped shared" when a folio is
+ * mapped multiple times into the same MM, because the individual page mappings
+ * are independent.
+ *
+ * For small anonymous folios and anonymous hugetlb folios, the return
+ * value will be exactly correct: non-KSM folios can only be mapped at most once
+ * into an MM, and they cannot be partially mapped. KSM folios are
+ * considered shared even if mapped multiple times into the same MM.
+ *
+ * For other folios, the result can be fuzzy:
+ *    #. For partially-mappable large folios (THP), the return value can wrongly
+ *       indicate "mapped shared" (false positive) if a folio was mapped by
+ *       more than two MMs at one point in time.
+ *    #. For pagecache folios (including hugetlb), the return value can wrongly
+ *       indicate "mapped shared" (false positive) when two VMAs in the same MM
+ *       cover the same file range.
+ *
+ * Further, this function only considers current page table mappings that
+ * are tracked using the folio mapcount(s).
  *
- * Return: The estimated number of processes sharing a folio.
+ * This function does not consider:
+ *    #. If the folio might get mapped in the (near) future (e.g., swapcache,
+ *       pagecache, temporary unmapping for migration).
+ *    #. If the folio is mapped differently (VM_PFNMAP).
+ *    #. If hugetlb page table sharing applies. Callers might want to check
+ *       hugetlb_pmd_shared().
+ *
+ * Return: Whether the folio is estimated to be mapped into more than one MM.
  */
-static inline int folio_estimated_sharers(struct folio *folio)
+static inline bool folio_maybe_mapped_shared(struct folio *folio)
 {
-	return page_mapcount(folio_page(folio, 0));
+	int mapcount = folio_mapcount(folio);
+
+	/* Only partially-mappable folios require more care. */
+	if (!folio_test_large(folio) || unlikely(folio_test_hugetlb(folio)))
+		return mapcount > 1;
+
+	/*
+	 * vm_insert_page() without CONFIG_TRANSPARENT_HUGEPAGE ...
+	 * simply assume "mapped shared", nobody should really care
+	 * about this for arbitrary kernel allocations.
+	 */
+	if (!IS_ENABLED(CONFIG_MM_ID))
+		return true;
+
+	/*
+	 * A single mapping implies "mapped exclusively", even if the
+	 * folio flag says something different: it's easier to handle this
+	 * case here instead of on the RMAP hot path.
+	 */
+	if (mapcount <= 1)
+		return false;
+	return test_bit(FOLIO_MM_IDS_SHARED_BITNUM, &folio->_mm_ids);
 }
 
-#ifndef HAVE_ARCH_MAKE_PAGE_ACCESSIBLE
-static inline int arch_make_page_accessible(struct page *page)
+/**
+ * folio_expected_ref_count - calculate the expected folio refcount
+ * @folio: the folio
+ *
+ * Calculate the expected folio refcount, taking references from the pagecache,
+ * swapcache, PG_private and page table mappings into account. Useful in
+ * combination with folio_ref_count() to detect unexpected references (e.g.,
+ * GUP or other temporary references).
+ *
+ * Does currently not consider references from the LRU cache. If the folio
+ * was isolated from the LRU (which is the case during migration or split),
+ * the LRU cache does not apply.
+ *
+ * Calling this function on an unmapped folio -- !folio_mapped() -- that is
+ * locked will return a stable result.
+ *
+ * Calling this function on a mapped folio will not result in a stable result,
+ * because nothing stops additional page table mappings from coming (e.g.,
+ * fork()) or going (e.g., munmap()).
+ *
+ * Calling this function without the folio lock will also not result in a
+ * stable result: for example, the folio might get dropped from the swapcache
+ * concurrently.
+ *
+ * However, even when called without the folio lock or on a mapped folio,
+ * this function can be used to detect unexpected references early (for example,
+ * if it makes sense to even lock the folio and unmap it).
+ *
+ * The caller must add any reference (e.g., from folio_try_get()) it might be
+ * holding itself to the result.
+ *
+ * Returns the expected folio refcount.
+ */
+static inline int folio_expected_ref_count(const struct folio *folio)
 {
-	return 0;
+	const int order = folio_order(folio);
+	int ref_count = 0;
+
+	if (WARN_ON_ONCE(page_has_type(&folio->page) && !folio_test_hugetlb(folio)))
+		return 0;
+
+	if (folio_test_anon(folio)) {
+		/* One reference per page from the swapcache. */
+		ref_count += folio_test_swapcache(folio) << order;
+	} else {
+		/* One reference per page from the pagecache. */
+		ref_count += !!folio->mapping << order;
+		/* One reference from PG_private. */
+		ref_count += folio_test_private(folio);
+	}
+
+	/* One reference per page table mapping. */
+	return ref_count + folio_mapcount(folio);
 }
-#endif
 
 #ifndef HAVE_ARCH_MAKE_FOLIO_ACCESSIBLE
 static inline int arch_make_folio_accessible(struct folio *folio)
 {
-	int ret;
-	long i, nr = folio_nr_pages(folio);
-
-	for (i = 0; i < nr; i++) {
-		ret = arch_make_page_accessible(folio_page(folio, i));
-		if (ret)
-			break;
-	}
-
-	return ret;
+	return 0;
 }
 #endif
 
@@ -2117,11 +2485,6 @@ static inline int arch_make_folio_accessible(struct folio *folio)
  */
 #include <linux/vmstat.h>
 
-static __always_inline void *lowmem_page_address(const struct page *page)
-{
-	return page_to_virt(page);
-}
-
 #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL)
 #define HASHED_PAGE_VIRTUAL
 #endif
@@ -2144,6 +2507,11 @@ void set_page_address(struct page *page, void *virtual);
 void page_address_init(void);
 #endif
 
+static __always_inline void *lowmem_page_address(const struct page *page)
+{
+	return page_to_virt(page);
+}
+
 #if !defined(HASHED_PAGE_VIRTUAL) && !defined(WANT_PAGE_VIRTUAL)
 #define page_address(page) lowmem_page_address(page)
 #define set_page_address(page, address)  do { } while(0)
@@ -2155,20 +2523,6 @@ static inline void *folio_address(const struct folio *folio)
 	return page_address(&folio->page);
 }
 
-extern void *page_rmapping(struct page *page);
-extern pgoff_t __page_file_index(struct page *page);
-
-/*
- * Return the pagecache index of the passed page.  Regular pagecache pages
- * use ->index whereas swapcache pages use swp_offset(->private)
- */
-static inline pgoff_t page_index(struct page *page)
-{
-	if (unlikely(PageSwapCache(page)))
-		return __page_file_index(page);
-	return page->index;
-}
-
 /*
  * Return true only if the page has been allocated with
  * ALLOC_NO_WATERMARKS and the low watermark was not
@@ -2219,27 +2573,15 @@ static inline void clear_page_pfmemalloc(struct page *page)
 extern void pagefault_out_of_memory(void);
 
 #define offset_in_page(p)	((unsigned long)(p) & ~PAGE_MASK)
-#define offset_in_thp(page, p)	((unsigned long)(p) & (thp_size(page) - 1))
 #define offset_in_folio(folio, p) ((unsigned long)(p) & (folio_size(folio) - 1))
 
 /*
- * Flags passed to show_mem() and show_free_areas() to suppress output in
- * various contexts.
- */
-#define SHOW_MEM_FILTER_NODES		(0x0001u)	/* disallowed nodes */
-
-extern void __show_free_areas(unsigned int flags, nodemask_t *nodemask, int max_zone_idx);
-static void __maybe_unused show_free_areas(unsigned int flags, nodemask_t *nodemask)
-{
-	__show_free_areas(flags, nodemask, MAX_NR_ZONES - 1);
-}
-
-/*
  * Parameter block passed down to zap_pte_range in exceptional cases.
  */
 struct zap_details {
 	struct folio *single_folio;	/* Locked folio to be unmapped */
 	bool even_cows;			/* Zap COWed private pages too? */
+	bool reclaim_pt;		/* Need reclaim page tables? */
 	zap_flags_t zap_flags;		/* Extra flags for zapping */
 };
 
@@ -2253,31 +2595,6 @@ struct zap_details {
 /* Set in unmap_vmas() to indicate a final unmap call.  Only used by hugetlb */
 #define  ZAP_FLAG_UNMAP              ((__force zap_flags_t) BIT(1))
 
-#ifdef CONFIG_SCHED_MM_CID
-void sched_mm_cid_before_execve(struct task_struct *t);
-void sched_mm_cid_after_execve(struct task_struct *t);
-void sched_mm_cid_fork(struct task_struct *t);
-void sched_mm_cid_exit_signals(struct task_struct *t);
-static inline int task_mm_cid(struct task_struct *t)
-{
-	return t->mm_cid;
-}
-#else
-static inline void sched_mm_cid_before_execve(struct task_struct *t) { }
-static inline void sched_mm_cid_after_execve(struct task_struct *t) { }
-static inline void sched_mm_cid_fork(struct task_struct *t) { }
-static inline void sched_mm_cid_exit_signals(struct task_struct *t) { }
-static inline int task_mm_cid(struct task_struct *t)
-{
-	/*
-	 * Use the processor id as a fall-back when the mm cid feature is
-	 * disabled. This provides functional per-cpu data structure accesses
-	 * in user-space, althrough it won't provide the memory usage benefits.
-	 */
-	return raw_smp_processor_id();
-}
-#endif
-
 #ifdef CONFIG_MMU
 extern bool can_do_mlock(void);
 #else
@@ -2290,8 +2607,12 @@ struct folio *vm_normal_folio(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
+struct folio *vm_normal_folio_pmd(struct vm_area_struct *vma,
+				  unsigned long addr, pmd_t pmd);
 struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 				pmd_t pmd);
+struct page *vm_normal_page_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t pud);
 
 void zap_vma_ptes(struct vm_area_struct *vma, unsigned long address,
 		  unsigned long size);
@@ -2302,9 +2623,9 @@ static inline void zap_vma_pages(struct vm_area_struct *vma)
 	zap_page_range_single(vma, vma->vm_start,
 			      vma->vm_end - vma->vm_start, NULL);
 }
-void unmap_vmas(struct mmu_gather *tlb, struct maple_tree *mt,
+void unmap_vmas(struct mmu_gather *tlb, struct ma_state *mas,
 		struct vm_area_struct *start_vma, unsigned long start,
-		unsigned long end, bool mm_wr_locked);
+		unsigned long end, unsigned long tree_end);
 
 struct mmu_notifier_range;
 
@@ -2312,20 +2633,51 @@ void free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 int
 copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma);
-int follow_pte(struct mm_struct *mm, unsigned long address,
-	       pte_t **ptepp, spinlock_t **ptlp);
-int follow_pfn(struct vm_area_struct *vma, unsigned long address,
-	unsigned long *pfn);
-int follow_phys(struct vm_area_struct *vma, unsigned long address,
-		unsigned int flags, unsigned long *prot, resource_size_t *phys);
 int generic_access_phys(struct vm_area_struct *vma, unsigned long addr,
 			void *buf, int len, int write);
 
+struct follow_pfnmap_args {
+	/**
+	 * Inputs:
+	 * @vma: Pointer to @vm_area_struct struct
+	 * @address: the virtual address to walk
+	 */
+	struct vm_area_struct *vma;
+	unsigned long address;
+	/**
+	 * Internals:
+	 *
+	 * The caller shouldn't touch any of these.
+	 */
+	spinlock_t *lock;
+	pte_t *ptep;
+	/**
+	 * Outputs:
+	 *
+	 * @pfn: the PFN of the address
+	 * @addr_mask: address mask covering pfn
+	 * @pgprot: the pgprot_t of the mapping
+	 * @writable: whether the mapping is writable
+	 * @special: whether the mapping is a special mapping (real PFN maps)
+	 */
+	unsigned long pfn;
+	unsigned long addr_mask;
+	pgprot_t pgprot;
+	bool writable;
+	bool special;
+};
+int follow_pfnmap_start(struct follow_pfnmap_args *args);
+void follow_pfnmap_end(struct follow_pfnmap_args *args);
+
 extern void truncate_pagecache(struct inode *inode, loff_t new);
 extern void truncate_setsize(struct inode *inode, loff_t newsize);
 void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to);
 void truncate_pagecache_range(struct inode *inode, loff_t offset, loff_t end);
-int generic_error_remove_page(struct address_space *mapping, struct page *page);
+int generic_error_remove_folio(struct address_space *mapping,
+		struct folio *folio);
+
+struct vm_area_struct *lock_mm_and_find_vma(struct mm_struct *mm,
+		unsigned long address, struct pt_regs *regs);
 
 #ifdef CONFIG_MMU
 extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
@@ -2373,8 +2725,11 @@ extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
-extern int __access_remote_vm(struct mm_struct *mm, unsigned long addr,
+
+#ifdef CONFIG_BPF_SYSCALL
+extern int copy_remote_vm_str(struct task_struct *tsk, unsigned long addr,
 			      void *buf, int len, unsigned int gup_flags);
+#endif
 
 long get_user_pages_remote(struct mm_struct *mm,
 			   unsigned long start, unsigned long nr_pages,
@@ -2385,6 +2740,9 @@ long pin_user_pages_remote(struct mm_struct *mm,
 			   unsigned int gup_flags, struct page **pages,
 			   int *locked);
 
+/*
+ * Retrieves a single page alongside its VMA. Does not support FOLL_NOWAIT.
+ */
 static inline struct page *get_user_page_vma_remote(struct mm_struct *mm,
 						    unsigned long addr,
 						    int gup_flags,
@@ -2392,12 +2750,15 @@ static inline struct page *get_user_page_vma_remote(struct mm_struct *mm,
 {
 	struct page *page;
 	struct vm_area_struct *vma;
-	int got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL);
+	int got;
+
+	if (WARN_ON_ONCE(unlikely(gup_flags & FOLL_NOWAIT)))
+		return ERR_PTR(-EINVAL);
+
+	got = get_user_pages_remote(mm, addr, 1, gup_flags, &page, NULL);
 
 	if (got < 0)
 		return ERR_PTR(got);
-	if (got == 0)
-		return NULL;
 
 	vma = vma_lookup(mm, addr);
 	if (WARN_ON_ONCE(!vma)) {
@@ -2417,30 +2778,31 @@ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
 long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages,
 		    struct page **pages, unsigned int gup_flags);
+long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end,
+		      struct folio **folios, unsigned int max_folios,
+		      pgoff_t *offset);
+int folio_add_pins(struct folio *folio, unsigned int pins);
 
 int get_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
 int pin_user_pages_fast(unsigned long start, int nr_pages,
 			unsigned int gup_flags, struct page **pages);
+void folio_add_pin(struct folio *folio);
 
 int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc);
 int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
-			struct task_struct *task, bool bypass_rlim);
+			const struct task_struct *task, bool bypass_rlim);
 
 struct kvec;
-struct page *get_dump_page(unsigned long addr);
+struct page *get_dump_page(unsigned long addr, int *locked);
 
 bool folio_mark_dirty(struct folio *folio);
+bool folio_mark_dirty_lock(struct folio *folio);
 bool set_page_dirty(struct page *page);
 int set_page_dirty_lock(struct page *page);
 
 int get_cmdline(struct task_struct *task, char *buffer, int buflen);
 
-extern unsigned long move_page_tables(struct vm_area_struct *vma,
-		unsigned long old_addr, struct vm_area_struct *new_vma,
-		unsigned long new_addr, unsigned long len,
-		bool need_rmap_locks);
-
 /*
  * Flags used by change_protection().  For now we make it a bitmap so
  * that we can pass in multiple flags just like parameters.  However
@@ -2461,21 +2823,6 @@ extern unsigned long move_page_tables(struct vm_area_struct *vma,
 #define  MM_CP_UFFD_WP_ALL                 (MM_CP_UFFD_WP | \
 					    MM_CP_UFFD_WP_RESOLVE)
 
-bool vma_needs_dirty_tracking(struct vm_area_struct *vma);
-int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
-static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma)
-{
-	/*
-	 * We want to check manually if we can change individual PTEs writable
-	 * if we can't do that automatically for all PTEs in a mapping. For
-	 * private mappings, that's always the case when we have write
-	 * permissions as we properly have to handle COW.
-	 */
-	if (vma->vm_flags & VM_SHARED)
-		return vma_wants_writenotify(vma, vma->vm_page_prot);
-	return !!(vma->vm_flags & VM_WRITE);
-
-}
 bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t pte);
 extern long change_protection(struct mmu_gather *tlb,
@@ -2483,7 +2830,7 @@ extern long change_protection(struct mmu_gather *tlb,
 			      unsigned long end, unsigned long cp_flags);
 extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
 	  struct vm_area_struct *vma, struct vm_area_struct **pprev,
-	  unsigned long start, unsigned long end, unsigned long newflags);
+	  unsigned long start, unsigned long end, vm_flags_t newflags);
 
 /*
  * doesn't attempt to fault and will return short.
@@ -2504,6 +2851,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 	return percpu_counter_read_positive(&mm->rss_stat[member]);
 }
 
+static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
+{
+	return percpu_counter_sum_positive(&mm->rss_stat[member]);
+}
+
 void mm_trace_rss_stat(struct mm_struct *mm, int member);
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
@@ -2527,19 +2879,19 @@ static inline void dec_mm_counter(struct mm_struct *mm, int member)
 	mm_trace_rss_stat(mm, member);
 }
 
-/* Optimized variant when page is already known not to be PageAnon */
-static inline int mm_counter_file(struct page *page)
+/* Optimized variant when folio is already known not to be anon */
+static inline int mm_counter_file(struct folio *folio)
 {
-	if (PageSwapBacked(page))
+	if (folio_test_swapbacked(folio))
 		return MM_SHMEMPAGES;
 	return MM_FILEPAGES;
 }
 
-static inline int mm_counter(struct page *page)
+static inline int mm_counter(struct folio *folio)
 {
-	if (PageAnon(page))
+	if (folio_test_anon(folio))
 		return MM_ANONPAGES;
-	return mm_counter_file(page);
+	return mm_counter_file(folio);
 }
 
 static inline unsigned long get_mm_rss(struct mm_struct *mm)
@@ -2563,8 +2915,8 @@ static inline void update_hiwater_rss(struct mm_struct *mm)
 {
 	unsigned long _rss = get_mm_rss(mm);
 
-	if ((mm)->hiwater_rss < _rss)
-		(mm)->hiwater_rss = _rss;
+	if (data_race(mm->hiwater_rss) < _rss)
+		data_race(mm->hiwater_rss = _rss);
 }
 
 static inline void update_hiwater_vm(struct mm_struct *mm)
@@ -2587,14 +2939,6 @@ static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
 		*maxrss = hiwater_rss;
 }
 
-#if defined(SPLIT_RSS_COUNTING)
-void sync_mm_rss(struct mm_struct *mm);
-#else
-static inline void sync_mm_rss(struct mm_struct *mm)
-{
-}
-#endif
-
 #ifndef CONFIG_ARCH_HAS_PTE_SPECIAL
 static inline int pte_special(pte_t pte)
 {
@@ -2607,12 +2951,29 @@ static inline pte_t pte_mkspecial(pte_t pte)
 }
 #endif
 
-#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pte_devmap(pte_t pte)
+#ifndef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
+static inline bool pmd_special(pmd_t pmd)
 {
-	return 0;
+	return false;
 }
-#endif
+
+static inline pmd_t pmd_mkspecial(pmd_t pmd)
+{
+	return pmd;
+}
+#endif	/* CONFIG_ARCH_SUPPORTS_PMD_PFNMAP */
+
+#ifndef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
+static inline bool pud_special(pud_t pud)
+{
+	return false;
+}
+
+static inline pud_t pud_mkspecial(pud_t pud)
+{
+	return pud;
+}
+#endif	/* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
 
 extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			       spinlock_t **ptl);
@@ -2747,42 +3108,166 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a
 }
 #endif /* CONFIG_MMU */
 
-#if USE_SPLIT_PTE_PTLOCKS
+enum pt_flags {
+	PT_kernel = PG_referenced,
+	PT_reserved = PG_reserved,
+	/* High bits are used for zone/node/section */
+};
+
+static inline struct ptdesc *virt_to_ptdesc(const void *x)
+{
+	return page_ptdesc(virt_to_page(x));
+}
+
+/**
+ * ptdesc_address - Virtual address of page table.
+ * @pt: Page table descriptor.
+ *
+ * Return: The first byte of the page table described by @pt.
+ */
+static inline void *ptdesc_address(const struct ptdesc *pt)
+{
+	return folio_address(ptdesc_folio(pt));
+}
+
+static inline bool pagetable_is_reserved(struct ptdesc *pt)
+{
+	return test_bit(PT_reserved, &pt->pt_flags.f);
+}
+
+/**
+ * ptdesc_set_kernel - Mark a ptdesc used to map the kernel
+ * @ptdesc: The ptdesc to be marked
+ *
+ * Kernel page tables often need special handling. Set a flag so that
+ * the handling code knows this ptdesc will not be used for userspace.
+ */
+static inline void ptdesc_set_kernel(struct ptdesc *ptdesc)
+{
+	set_bit(PT_kernel, &ptdesc->pt_flags.f);
+}
+
+/**
+ * ptdesc_clear_kernel - Mark a ptdesc as no longer used to map the kernel
+ * @ptdesc: The ptdesc to be unmarked
+ *
+ * Use when the ptdesc is no longer used to map the kernel and no longer
+ * needs special handling.
+ */
+static inline void ptdesc_clear_kernel(struct ptdesc *ptdesc)
+{
+	/*
+	 * Note: the 'PG_referenced' bit does not strictly need to be
+	 * cleared before freeing the page. But this is nice for
+	 * symmetry.
+	 */
+	clear_bit(PT_kernel, &ptdesc->pt_flags.f);
+}
+
+/**
+ * ptdesc_test_kernel - Check if a ptdesc is used to map the kernel
+ * @ptdesc: The ptdesc being tested
+ *
+ * Call to tell if the ptdesc used to map the kernel.
+ */
+static inline bool ptdesc_test_kernel(const struct ptdesc *ptdesc)
+{
+	return test_bit(PT_kernel, &ptdesc->pt_flags.f);
+}
+
+/**
+ * pagetable_alloc - Allocate pagetables
+ * @gfp:    GFP flags
+ * @order:  desired pagetable order
+ *
+ * pagetable_alloc allocates memory for page tables as well as a page table
+ * descriptor to describe that memory.
+ *
+ * Return: The ptdesc describing the allocated page tables.
+ */
+static inline struct ptdesc *pagetable_alloc_noprof(gfp_t gfp, unsigned int order)
+{
+	struct page *page = alloc_pages_noprof(gfp | __GFP_COMP, order);
+
+	return page_ptdesc(page);
+}
+#define pagetable_alloc(...)	alloc_hooks(pagetable_alloc_noprof(__VA_ARGS__))
+
+static inline void __pagetable_free(struct ptdesc *pt)
+{
+	struct page *page = ptdesc_page(pt);
+
+	__free_pages(page, compound_order(page));
+}
+
+#ifdef CONFIG_ASYNC_KERNEL_PGTABLE_FREE
+void pagetable_free_kernel(struct ptdesc *pt);
+#else
+static inline void pagetable_free_kernel(struct ptdesc *pt)
+{
+	__pagetable_free(pt);
+}
+#endif
+/**
+ * pagetable_free - Free pagetables
+ * @pt:	The page table descriptor
+ *
+ * pagetable_free frees the memory of all page tables described by a page
+ * table descriptor and the memory for the descriptor itself.
+ */
+static inline void pagetable_free(struct ptdesc *pt)
+{
+	if (ptdesc_test_kernel(pt)) {
+		ptdesc_clear_kernel(pt);
+		pagetable_free_kernel(pt);
+	} else {
+		__pagetable_free(pt);
+	}
+}
+
+#if defined(CONFIG_SPLIT_PTE_PTLOCKS)
 #if ALLOC_SPLIT_PTLOCKS
 void __init ptlock_cache_init(void);
-extern bool ptlock_alloc(struct page *page);
-extern void ptlock_free(struct page *page);
+bool ptlock_alloc(struct ptdesc *ptdesc);
+void ptlock_free(struct ptdesc *ptdesc);
 
-static inline spinlock_t *ptlock_ptr(struct page *page)
+static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc)
 {
-	return page->ptl;
+	return ptdesc->ptl;
 }
 #else /* ALLOC_SPLIT_PTLOCKS */
 static inline void ptlock_cache_init(void)
 {
 }
 
-static inline bool ptlock_alloc(struct page *page)
+static inline bool ptlock_alloc(struct ptdesc *ptdesc)
 {
 	return true;
 }
 
-static inline void ptlock_free(struct page *page)
+static inline void ptlock_free(struct ptdesc *ptdesc)
 {
 }
 
-static inline spinlock_t *ptlock_ptr(struct page *page)
+static inline spinlock_t *ptlock_ptr(struct ptdesc *ptdesc)
 {
-	return &page->ptl;
+	return &ptdesc->ptl;
 }
 #endif /* ALLOC_SPLIT_PTLOCKS */
 
 static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
-	return ptlock_ptr(pmd_page(*pmd));
+	return ptlock_ptr(page_ptdesc(pmd_page(*pmd)));
+}
+
+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
+{
+	BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE));
+	BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE);
+	return ptlock_ptr(virt_to_ptdesc(pte));
 }
 
-static inline bool ptlock_init(struct page *page)
+static inline bool ptlock_init(struct ptdesc *ptdesc)
 {
 	/*
 	 * prep_new_page() initialize page->private (and therefore page->ptl)
@@ -2791,14 +3276,14 @@ static inline bool ptlock_init(struct page *page)
 	 * It can happen if arch try to use slab for page table allocation:
 	 * slab code uses page->slab_cache, which share storage with page->ptl.
 	 */
-	VM_BUG_ON_PAGE(*(unsigned long *)&page->ptl, page);
-	if (!ptlock_alloc(page))
+	VM_BUG_ON_PAGE(*(unsigned long *)&ptdesc->ptl, ptdesc_page(ptdesc));
+	if (!ptlock_alloc(ptdesc))
 		return false;
-	spin_lock_init(ptlock_ptr(page));
+	spin_lock_init(ptlock_ptr(ptdesc));
 	return true;
 }
 
-#else	/* !USE_SPLIT_PTE_PTLOCKS */
+#else	/* !defined(CONFIG_SPLIT_PTE_PTLOCKS) */
 /*
  * We use mm->page_table_lock to guard all pagetable pages of the mm.
  */
@@ -2806,35 +3291,83 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
 	return &mm->page_table_lock;
 }
+static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
+{
+	return &mm->page_table_lock;
+}
 static inline void ptlock_cache_init(void) {}
-static inline bool ptlock_init(struct page *page) { return true; }
-static inline void ptlock_free(struct page *page) {}
-#endif /* USE_SPLIT_PTE_PTLOCKS */
+static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
+static inline void ptlock_free(struct ptdesc *ptdesc) {}
+#endif /* defined(CONFIG_SPLIT_PTE_PTLOCKS) */
+
+static inline unsigned long ptdesc_nr_pages(const struct ptdesc *ptdesc)
+{
+	return compound_nr(ptdesc_page(ptdesc));
+}
+
+static inline void __pagetable_ctor(struct ptdesc *ptdesc)
+{
+	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+
+	__SetPageTable(ptdesc_page(ptdesc));
+	mod_node_page_state(pgdat, NR_PAGETABLE, ptdesc_nr_pages(ptdesc));
+}
 
-static inline bool pgtable_pte_page_ctor(struct page *page)
+static inline void pagetable_dtor(struct ptdesc *ptdesc)
 {
-	if (!ptlock_init(page))
+	pg_data_t *pgdat = NODE_DATA(memdesc_nid(ptdesc->pt_flags));
+
+	ptlock_free(ptdesc);
+	__ClearPageTable(ptdesc_page(ptdesc));
+	mod_node_page_state(pgdat, NR_PAGETABLE, -ptdesc_nr_pages(ptdesc));
+}
+
+static inline void pagetable_dtor_free(struct ptdesc *ptdesc)
+{
+	pagetable_dtor(ptdesc);
+	pagetable_free(ptdesc);
+}
+
+static inline bool pagetable_pte_ctor(struct mm_struct *mm,
+				      struct ptdesc *ptdesc)
+{
+	if (mm != &init_mm && !ptlock_init(ptdesc))
 		return false;
-	__SetPageTable(page);
-	inc_lruvec_page_state(page, NR_PAGETABLE);
+	__pagetable_ctor(ptdesc);
 	return true;
 }
 
-static inline void pgtable_pte_page_dtor(struct page *page)
+pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp);
+static inline pte_t *__pte_offset_map(pmd_t *pmd, unsigned long addr,
+			pmd_t *pmdvalp)
+{
+	pte_t *pte;
+
+	__cond_lock(RCU, pte = ___pte_offset_map(pmd, addr, pmdvalp));
+	return pte;
+}
+static inline pte_t *pte_offset_map(pmd_t *pmd, unsigned long addr)
 {
-	ptlock_free(page);
-	__ClearPageTable(page);
-	dec_lruvec_page_state(page, NR_PAGETABLE);
+	return __pte_offset_map(pmd, addr, NULL);
 }
 
-#define pte_offset_map_lock(mm, pmd, address, ptlp)	\
-({							\
-	spinlock_t *__ptl = pte_lockptr(mm, pmd);	\
-	pte_t *__pte = pte_offset_map(pmd, address);	\
-	*(ptlp) = __ptl;				\
-	spin_lock(__ptl);				\
-	__pte;						\
-})
+pte_t *__pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, spinlock_t **ptlp);
+static inline pte_t *pte_offset_map_lock(struct mm_struct *mm, pmd_t *pmd,
+			unsigned long addr, spinlock_t **ptlp)
+{
+	pte_t *pte;
+
+	__cond_lock(RCU, __cond_lock(*ptlp,
+			pte = __pte_offset_map_lock(mm, pmd, addr, ptlp)));
+	return pte;
+}
+
+pte_t *pte_offset_map_ro_nolock(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long addr, spinlock_t **ptlp);
+pte_t *pte_offset_map_rw_nolock(struct mm_struct *mm, pmd_t *pmd,
+				unsigned long addr, pmd_t *pmdvalp,
+				spinlock_t **ptlp);
 
 #define pte_unmap_unlock(pte, ptl)	do {		\
 	spin_unlock(ptl);				\
@@ -2854,7 +3387,7 @@ static inline void pgtable_pte_page_dtor(struct page *page)
 	((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \
 		NULL: pte_offset_kernel(pmd, address))
 
-#if USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_SPLIT_PMD_PTLOCKS)
 
 static inline struct page *pmd_pgtable_page(pmd_t *pmd)
 {
@@ -2862,28 +3395,25 @@ static inline struct page *pmd_pgtable_page(pmd_t *pmd)
 	return virt_to_page((void *)((unsigned long) pmd & mask));
 }
 
-static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
+static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd)
 {
-	return ptlock_ptr(pmd_pgtable_page(pmd));
+	return page_ptdesc(pmd_pgtable_page(pmd));
 }
 
-static inline bool pmd_ptlock_init(struct page *page)
+static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 {
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	page->pmd_huge_pte = NULL;
-#endif
-	return ptlock_init(page);
+	return ptlock_ptr(pmd_ptdesc(pmd));
 }
 
-static inline void pmd_ptlock_free(struct page *page)
+static inline bool pmd_ptlock_init(struct ptdesc *ptdesc)
 {
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON_PAGE(page->pmd_huge_pte, page);
+	ptdesc->pmd_huge_pte = NULL;
 #endif
-	ptlock_free(page);
+	return ptlock_init(ptdesc);
 }
 
-#define pmd_huge_pte(mm, pmd) (pmd_pgtable_page(pmd)->pmd_huge_pte)
+#define pmd_huge_pte(mm, pmd) (pmd_ptdesc(pmd)->pmd_huge_pte)
 
 #else
 
@@ -2892,8 +3422,7 @@ static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
 	return &mm->page_table_lock;
 }
 
-static inline bool pmd_ptlock_init(struct page *page) { return true; }
-static inline void pmd_ptlock_free(struct page *page) {}
+static inline bool pmd_ptlock_init(struct ptdesc *ptdesc) { return true; }
 
 #define pmd_huge_pte(mm, pmd) ((mm)->pmd_huge_pte)
 
@@ -2906,22 +3435,16 @@ static inline spinlock_t *pmd_lock(struct mm_struct *mm, pmd_t *pmd)
 	return ptl;
 }
 
-static inline bool pgtable_pmd_page_ctor(struct page *page)
+static inline bool pagetable_pmd_ctor(struct mm_struct *mm,
+				      struct ptdesc *ptdesc)
 {
-	if (!pmd_ptlock_init(page))
+	if (mm != &init_mm && !pmd_ptlock_init(ptdesc))
 		return false;
-	__SetPageTable(page);
-	inc_lruvec_page_state(page, NR_PAGETABLE);
+	ptdesc_pmd_pts_init(ptdesc);
+	__pagetable_ctor(ptdesc);
 	return true;
 }
 
-static inline void pgtable_pmd_page_dtor(struct page *page)
-{
-	pmd_ptlock_free(page);
-	__ClearPageTable(page);
-	dec_lruvec_page_state(page, NR_PAGETABLE);
-}
-
 /*
  * No scalability reason to split PUD locks yet, but follow the same pattern
  * as the PMD locks to make it easier if we decide to.  The VM should not be
@@ -2941,6 +3464,21 @@ static inline spinlock_t *pud_lock(struct mm_struct *mm, pud_t *pud)
 	return ptl;
 }
 
+static inline void pagetable_pud_ctor(struct ptdesc *ptdesc)
+{
+	__pagetable_ctor(ptdesc);
+}
+
+static inline void pagetable_p4d_ctor(struct ptdesc *ptdesc)
+{
+	__pagetable_ctor(ptdesc);
+}
+
+static inline void pagetable_pgd_ctor(struct ptdesc *ptdesc)
+{
+	__pagetable_ctor(ptdesc);
+}
+
 extern void __init pagecache_init(void);
 extern void free_initmem(void);
 
@@ -2955,17 +3493,11 @@ extern unsigned long free_reserved_area(void *start, void *end,
 
 extern void adjust_managed_page_count(struct page *page, long count);
 
-extern void reserve_bootmem_region(phys_addr_t start, phys_addr_t end);
+extern void reserve_bootmem_region(phys_addr_t start,
+				   phys_addr_t end, int nid);
 
 /* Free the reserved page into the buddy system, so it gets managed. */
-static inline void free_reserved_page(struct page *page)
-{
-	ClearPageReserved(page);
-	init_page_count(page);
-	__free_page(page);
-	adjust_managed_page_count(page, 1);
-}
-#define free_highmem_page(page) free_reserved_page(page)
+void free_reserved_page(struct page *page);
 
 static inline void mark_page_reserved(struct page *page)
 {
@@ -2973,6 +3505,11 @@ static inline void mark_page_reserved(struct page *page)
 	adjust_managed_page_count(page, -1);
 }
 
+static inline void free_reserved_ptdesc(struct ptdesc *pt)
+{
+	free_reserved_page(ptdesc_page(pt));
+}
+
 /*
  * Default method to free all the __init memory into the buddy system.
  * The freed pages will be poisoned with pattern "poison" if it's within
@@ -3016,8 +3553,6 @@ static inline unsigned long get_num_physpages(void)
  */
 void free_area_init(unsigned long *max_zone_pfn);
 unsigned long node_map_pfn_alignment(void);
-unsigned long __absent_pages_in_range(int nid, unsigned long start_pfn,
-						unsigned long end_pfn);
 extern unsigned long absent_pages_in_range(unsigned long start_pfn,
 						unsigned long end_pfn);
 extern void get_pfn_range_for_nid(unsigned int nid,
@@ -3033,21 +3568,17 @@ static inline int early_pfn_to_nid(unsigned long pfn)
 extern int __meminit early_pfn_to_nid(unsigned long pfn);
 #endif
 
-extern void set_dma_reserve(unsigned long new_dma_reserve);
 extern void mem_init(void);
 extern void __init mmap_init(void);
 
 extern void __show_mem(unsigned int flags, nodemask_t *nodemask, int max_zone_idx);
-static inline void show_mem(unsigned int flags, nodemask_t *nodemask)
+static inline void show_mem(void)
 {
-	__show_mem(flags, nodemask, MAX_NR_ZONES - 1);
+	__show_mem(0, NULL, MAX_NR_ZONES - 1);
 }
 extern long si_mem_available(void);
 extern void si_meminfo(struct sysinfo * val);
 extern void si_meminfo_node(struct sysinfo *val, int nid);
-#ifdef __HAVE_ARCH_RESERVED_KERNEL_PAGES
-extern unsigned long arch_reserved_kernel_pages(void);
-#endif
 
 extern __printf(3, 4)
 void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...);
@@ -3066,6 +3597,8 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node,
 				    struct rb_root_cached *root);
 void vma_interval_tree_remove(struct vm_area_struct *node,
 			      struct rb_root_cached *root);
+struct vm_area_struct *vma_interval_tree_subtree_search(struct vm_area_struct *node,
+				unsigned long start, unsigned long last);
 struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root,
 				unsigned long start, unsigned long last);
 struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node,
@@ -3093,28 +3626,11 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node);
 	     avc; avc = anon_vma_interval_tree_iter_next(avc, start, last))
 
 /* mmap.c */
-extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
-extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		      unsigned long start, unsigned long end, pgoff_t pgoff,
-		      struct vm_area_struct *next);
-extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		       unsigned long start, unsigned long end, pgoff_t pgoff);
-extern struct vm_area_struct *vma_merge(struct vma_iterator *vmi,
-	struct mm_struct *, struct vm_area_struct *prev, unsigned long addr,
-	unsigned long end, unsigned long vm_flags, struct anon_vma *,
-	struct file *, pgoff_t, struct mempolicy *, struct vm_userfaultfd_ctx,
-	struct anon_vma_name *);
-extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
-extern int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *,
-		       unsigned long addr, int new_below);
-extern int split_vma(struct vma_iterator *vmi, struct vm_area_struct *,
-			 unsigned long addr, int new_below);
+extern int __vm_enough_memory(const struct mm_struct *mm, long pages, int cap_sys_admin);
 extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
-extern void unlink_file_vma(struct vm_area_struct *);
-extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
-	unsigned long addr, unsigned long len, pgoff_t pgoff,
-	bool *need_rmap_locks);
 extern void exit_mmap(struct mm_struct *);
+bool mmap_read_lock_maybe_expand(struct mm_struct *mm, struct vm_area_struct *vma,
+				 unsigned long addr, bool write);
 
 static inline int check_data_rlimit(unsigned long rlim,
 				    unsigned long new,
@@ -3143,37 +3659,40 @@ extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
 
 extern bool vma_is_special_mapping(const struct vm_area_struct *vma,
 				   const struct vm_special_mapping *sm);
-extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
+struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
-				   unsigned long flags,
+				   vm_flags_t vm_flags,
 				   const struct vm_special_mapping *spec);
-/* This is an obsolete alternative to _install_special_mapping. */
-extern int install_special_mapping(struct mm_struct *mm,
-				   unsigned long addr, unsigned long len,
-				   unsigned long flags, struct page **pages);
 
 unsigned long randomize_stack_top(unsigned long stack_top);
 unsigned long randomize_page(unsigned long start, unsigned long range);
 
-extern unsigned long get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
+unsigned long
+__get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
+		    unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags);
+
+static inline unsigned long
+get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
+		  unsigned long pgoff, unsigned long flags)
+{
+	return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
+}
 
-extern unsigned long mmap_region(struct file *file, unsigned long addr,
-	unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
-	struct list_head *uf);
 extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
-	unsigned long pgoff, unsigned long *populate, struct list_head *uf);
+	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
+	struct list_head *uf);
 extern int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm,
 			 unsigned long start, size_t len, struct list_head *uf,
-			 bool downgrade);
+			 bool unlock);
+int do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
+		    struct mm_struct *mm, unsigned long start,
+		    unsigned long end, struct list_head *uf, bool unlock);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
 extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
 
 #ifdef CONFIG_MMU
-extern int do_vma_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma,
-			 unsigned long start, unsigned long end,
-			 struct list_head *uf, bool downgrade);
 extern int __mm_populate(unsigned long addr, unsigned long len,
 			 int ignore_errors);
 static inline void mm_populate(unsigned long addr, unsigned long len)
@@ -3185,8 +3704,7 @@ static inline void mm_populate(unsigned long addr, unsigned long len)
 static inline void mm_populate(unsigned long addr, unsigned long len) {}
 #endif
 
-/* These take the mm semaphore themselves */
-extern int __must_check vm_brk(unsigned long, unsigned long);
+/* This takes the mm semaphore itself */
 extern int __must_check vm_brk_flags(unsigned long, unsigned long, unsigned long);
 extern int vm_munmap(unsigned long, size_t);
 extern unsigned long __must_check vm_mmap(struct file *, unsigned long,
@@ -3201,15 +3719,16 @@ struct vm_unmapped_area_info {
 	unsigned long high_limit;
 	unsigned long align_mask;
 	unsigned long align_offset;
+	unsigned long start_gap;
 };
 
 extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info);
 
 /* truncate.c */
-extern void truncate_inode_pages(struct address_space *, loff_t);
-extern void truncate_inode_pages_range(struct address_space *,
-				       loff_t lstart, loff_t lend);
-extern void truncate_inode_pages_final(struct address_space *);
+void truncate_inode_pages(struct address_space *mapping, loff_t lstart);
+void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart,
+		uoff_t lend);
+void truncate_inode_pages_final(struct address_space *mapping);
 
 /* generic vm_area_ops exported for stackable file systems */
 extern vm_fault_t filemap_fault(struct vm_fault *vmf);
@@ -3219,16 +3738,8 @@ extern vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf);
 
 extern unsigned long stack_guard_gap;
 /* Generic expand stack which grows the stack according to GROWS{UP,DOWN} */
-extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
-
-/* CONFIG_STACK_GROWSUP still needs to grow downwards at some places */
-extern int expand_downwards(struct vm_area_struct *vma,
-		unsigned long address);
-#if VM_GROWSUP
-extern int expand_upwards(struct vm_area_struct *vma, unsigned long address);
-#else
-  #define expand_upwards(vma, address) (0)
-#endif
+int expand_stack_locked(struct vm_area_struct *vma, unsigned long address);
+struct vm_area_struct *expand_stack(struct mm_struct * mm, unsigned long addr);
 
 /* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
 extern struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr);
@@ -3255,19 +3766,30 @@ struct vm_area_struct *vma_lookup(struct mm_struct *mm, unsigned long addr)
 	return mtree_load(&mm->mm_mt, addr);
 }
 
-static inline unsigned long vm_start_gap(struct vm_area_struct *vma)
+static inline unsigned long stack_guard_start_gap(const struct vm_area_struct *vma)
+{
+	if (vma->vm_flags & VM_GROWSDOWN)
+		return stack_guard_gap;
+
+	/* See reasoning around the VM_SHADOW_STACK definition */
+	if (vma->vm_flags & VM_SHADOW_STACK)
+		return PAGE_SIZE;
+
+	return 0;
+}
+
+static inline unsigned long vm_start_gap(const struct vm_area_struct *vma)
 {
+	unsigned long gap = stack_guard_start_gap(vma);
 	unsigned long vm_start = vma->vm_start;
 
-	if (vma->vm_flags & VM_GROWSDOWN) {
-		vm_start -= stack_guard_gap;
-		if (vm_start > vma->vm_start)
-			vm_start = 0;
-	}
+	vm_start -= gap;
+	if (vm_start > vma->vm_start)
+		vm_start = 0;
 	return vm_start;
 }
 
-static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
+static inline unsigned long vm_end_gap(const struct vm_area_struct *vma)
 {
 	unsigned long vm_end = vma->vm_end;
 
@@ -3279,11 +3801,95 @@ static inline unsigned long vm_end_gap(struct vm_area_struct *vma)
 	return vm_end;
 }
 
-static inline unsigned long vma_pages(struct vm_area_struct *vma)
+static inline unsigned long vma_pages(const struct vm_area_struct *vma)
 {
 	return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 }
 
+static inline unsigned long vma_desc_size(const struct vm_area_desc *desc)
+{
+	return desc->end - desc->start;
+}
+
+static inline unsigned long vma_desc_pages(const struct vm_area_desc *desc)
+{
+	return vma_desc_size(desc) >> PAGE_SHIFT;
+}
+
+/**
+ * mmap_action_remap - helper for mmap_prepare hook to specify that a pure PFN
+ * remap is required.
+ * @desc: The VMA descriptor for the VMA requiring remap.
+ * @start: The virtual address to start the remap from, must be within the VMA.
+ * @start_pfn: The first PFN in the range to remap.
+ * @size: The size of the range to remap, in bytes, at most spanning to the end
+ * of the VMA.
+ */
+static inline void mmap_action_remap(struct vm_area_desc *desc,
+				     unsigned long start,
+				     unsigned long start_pfn,
+				     unsigned long size)
+{
+	struct mmap_action *action = &desc->action;
+
+	/* [start, start + size) must be within the VMA. */
+	WARN_ON_ONCE(start < desc->start || start >= desc->end);
+	WARN_ON_ONCE(start + size > desc->end);
+
+	action->type = MMAP_REMAP_PFN;
+	action->remap.start = start;
+	action->remap.start_pfn = start_pfn;
+	action->remap.size = size;
+	action->remap.pgprot = desc->page_prot;
+}
+
+/**
+ * mmap_action_remap_full - helper for mmap_prepare hook to specify that the
+ * entirety of a VMA should be PFN remapped.
+ * @desc: The VMA descriptor for the VMA requiring remap.
+ * @start_pfn: The first PFN in the range to remap.
+ */
+static inline void mmap_action_remap_full(struct vm_area_desc *desc,
+					  unsigned long start_pfn)
+{
+	mmap_action_remap(desc, desc->start, start_pfn, vma_desc_size(desc));
+}
+
+/**
+ * mmap_action_ioremap - helper for mmap_prepare hook to specify that a pure PFN
+ * I/O remap is required.
+ * @desc: The VMA descriptor for the VMA requiring remap.
+ * @start: The virtual address to start the remap from, must be within the VMA.
+ * @start_pfn: The first PFN in the range to remap.
+ * @size: The size of the range to remap, in bytes, at most spanning to the end
+ * of the VMA.
+ */
+static inline void mmap_action_ioremap(struct vm_area_desc *desc,
+				       unsigned long start,
+				       unsigned long start_pfn,
+				       unsigned long size)
+{
+	mmap_action_remap(desc, start, start_pfn, size);
+	desc->action.type = MMAP_IO_REMAP_PFN;
+}
+
+/**
+ * mmap_action_ioremap_full - helper for mmap_prepare hook to specify that the
+ * entirety of a VMA should be PFN I/O remapped.
+ * @desc: The VMA descriptor for the VMA requiring remap.
+ * @start_pfn: The first PFN in the range to remap.
+ */
+static inline void mmap_action_ioremap_full(struct vm_area_desc *desc,
+					  unsigned long start_pfn)
+{
+	mmap_action_ioremap(desc, desc->start, start_pfn, vma_desc_size(desc));
+}
+
+void mmap_action_prepare(struct mmap_action *action,
+			 struct vm_area_desc *desc);
+int mmap_action_complete(struct mmap_action *action,
+			 struct vm_area_struct *vma);
+
 /* Look up the first VMA which exactly match the interval vm_start ... vm_end */
 static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
 				unsigned long vm_start, unsigned long vm_end)
@@ -3296,17 +3902,17 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
 	return vma;
 }
 
-static inline bool range_in_vma(struct vm_area_struct *vma,
+static inline bool range_in_vma(const struct vm_area_struct *vma,
 				unsigned long start, unsigned long end)
 {
 	return (vma && vma->vm_start <= start && end <= vma->vm_end);
 }
 
 #ifdef CONFIG_MMU
-pgprot_t vm_get_page_prot(unsigned long vm_flags);
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags);
 void vma_set_page_prot(struct vm_area_struct *vma);
 #else
-static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
+static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	return __pgprot(0);
 }
@@ -3323,11 +3929,11 @@ unsigned long change_prot_numa(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end);
 #endif
 
-struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
-int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
-			unsigned long pfn, unsigned long size, pgprot_t);
-int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
-		unsigned long pfn, unsigned long size, pgprot_t prot);
+struct vm_area_struct *find_extend_vma_locked(struct mm_struct *,
+		unsigned long addr);
+int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr,
+		    unsigned long pfn, unsigned long size, pgprot_t pgprot);
+
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
 int vm_insert_pages(struct vm_area_struct *vma, unsigned long addr,
 			struct page **pages, unsigned long *num);
@@ -3335,14 +3941,16 @@ int vm_map_pages(struct vm_area_struct *vma, struct page **pages,
 				unsigned long num);
 int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
 				unsigned long num);
+vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
+			bool write);
 vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
 vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot);
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn);
+			unsigned long pfn);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn);
+		unsigned long addr, unsigned long pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
 
 static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
@@ -3358,24 +3966,50 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
-#ifndef io_remap_pfn_range
-static inline int io_remap_pfn_range(struct vm_area_struct *vma,
-				     unsigned long addr, unsigned long pfn,
-				     unsigned long size, pgprot_t prot)
+#ifndef io_remap_pfn_range_pfn
+static inline unsigned long io_remap_pfn_range_pfn(unsigned long pfn,
+		unsigned long size)
 {
-	return remap_pfn_range(vma, addr, pfn, size, pgprot_decrypted(prot));
+	return pfn;
 }
 #endif
 
+static inline int io_remap_pfn_range(struct vm_area_struct *vma,
+				     unsigned long addr, unsigned long orig_pfn,
+				     unsigned long size, pgprot_t orig_prot)
+{
+	const unsigned long pfn = io_remap_pfn_range_pfn(orig_pfn, size);
+	const pgprot_t prot = pgprot_decrypted(orig_prot);
+
+	return remap_pfn_range(vma, addr, pfn, size, prot);
+}
+
 static inline vm_fault_t vmf_error(int err)
 {
 	if (err == -ENOMEM)
 		return VM_FAULT_OOM;
+	else if (err == -EHWPOISON)
+		return VM_FAULT_HWPOISON;
 	return VM_FAULT_SIGBUS;
 }
 
-struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
-			 unsigned int foll_flags);
+/*
+ * Convert errno to return value for ->page_mkwrite() calls.
+ *
+ * This should eventually be merged with vmf_error() above, but will need a
+ * careful audit of all vmf_error() callers.
+ */
+static inline vm_fault_t vmf_fs_error(int err)
+{
+	if (err == 0)
+		return VM_FAULT_LOCKED;
+	if (err == -EFAULT || err == -EAGAIN)
+		return VM_FAULT_NOPAGE;
+	if (err == -ENOMEM)
+		return VM_FAULT_OOM;
+	/* -ENOSPC, -EDQUOT, -EIO ... */
+	return VM_FAULT_SIGBUS;
+}
 
 static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
 {
@@ -3392,15 +4026,24 @@ static inline int vm_fault_to_errno(vm_fault_t vm_fault, int foll_flags)
  * Indicates whether GUP can follow a PROT_NONE mapped page, or whether
  * a (NUMA hinting) fault is required.
  */
-static inline bool gup_can_follow_protnone(unsigned int flags)
+static inline bool gup_can_follow_protnone(const struct vm_area_struct *vma,
+					   unsigned int flags)
 {
 	/*
-	 * FOLL_FORCE has to be able to make progress even if the VMA is
-	 * inaccessible. Further, FOLL_FORCE access usually does not represent
-	 * application behaviour and we should avoid triggering NUMA hinting
-	 * faults.
+	 * If callers don't want to honor NUMA hinting faults, no need to
+	 * determine if we would actually have to trigger a NUMA hinting fault.
+	 */
+	if (!(flags & FOLL_HONOR_NUMA_FAULT))
+		return true;
+
+	/*
+	 * NUMA hinting faults don't apply in inaccessible (PROT_NONE) VMAs.
+	 *
+	 * Requiring a fault here even for inaccessible VMAs would mean that
+	 * FOLL_FORCE cannot make any progress, because handle_mm_fault()
+	 * refuses to process NUMA hinting faults in inaccessible VMAs.
 	 */
-	return flags & FOLL_FORCE;
+	return !vma_is_accessible(vma);
 }
 
 typedef int (*pte_fn_t)(pte_t *pte, unsigned long addr, void *data);
@@ -3471,8 +4114,8 @@ static inline bool debug_pagealloc_enabled(void)
 }
 
 /*
- * For use in fast paths after init_debug_pagealloc() has run, or when a
- * false negative result is not harmful when called too early.
+ * For use in fast paths after mem_debugging_and_hardening_init() has run,
+ * or when a false negative result is not harmful when called too early.
  */
 static inline bool debug_pagealloc_enabled_static(void)
 {
@@ -3482,13 +4125,12 @@ static inline bool debug_pagealloc_enabled_static(void)
 	return static_branch_unlikely(&_debug_pagealloc_enabled);
 }
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
 /*
  * To support DEBUG_PAGEALLOC architecture must ensure that
  * __kernel_map_pages() never fails
  */
 extern void __kernel_map_pages(struct page *page, int numpages, int enable);
-
+#ifdef CONFIG_DEBUG_PAGEALLOC
 static inline void debug_pagealloc_map_pages(struct page *page, int numpages)
 {
 	if (debug_pagealloc_enabled_static())
@@ -3514,7 +4156,7 @@ static inline bool debug_guardpage_enabled(void)
 	return static_branch_unlikely(&_debug_guardpage_enabled);
 }
 
-static inline bool page_is_guard(struct page *page)
+static inline bool page_is_guard(const struct page *page)
 {
 	if (!debug_guardpage_enabled())
 		return false;
@@ -3522,24 +4164,22 @@ static inline bool page_is_guard(struct page *page)
 	return PageGuard(page);
 }
 
-bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order,
-		      int migratetype);
+bool __set_page_guard(struct zone *zone, struct page *page, unsigned int order);
 static inline bool set_page_guard(struct zone *zone, struct page *page,
-				  unsigned int order, int migratetype)
+				  unsigned int order)
 {
 	if (!debug_guardpage_enabled())
 		return false;
-	return __set_page_guard(zone, page, order, migratetype);
+	return __set_page_guard(zone, page, order);
 }
 
-void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order,
-			int migratetype);
+void __clear_page_guard(struct zone *zone, struct page *page, unsigned int order);
 static inline void clear_page_guard(struct zone *zone, struct page *page,
-				    unsigned int order, int migratetype)
+				    unsigned int order)
 {
 	if (!debug_guardpage_enabled())
 		return;
-	__clear_page_guard(zone, page, order, migratetype);
+	__clear_page_guard(zone, page, order);
 }
 
 #else	/* CONFIG_DEBUG_PAGEALLOC */
@@ -3547,11 +4187,11 @@ static inline void debug_pagealloc_map_pages(struct page *page, int numpages) {}
 static inline void debug_pagealloc_unmap_pages(struct page *page, int numpages) {}
 static inline unsigned int debug_guardpage_minorder(void) { return 0; }
 static inline bool debug_guardpage_enabled(void) { return false; }
-static inline bool page_is_guard(struct page *page) { return false; }
+static inline bool page_is_guard(const struct page *page) { return false; }
 static inline bool set_page_guard(struct zone *zone, struct page *page,
-			unsigned int order, int migratetype) { return false; }
+			unsigned int order) { return false; }
 static inline void clear_page_guard(struct zone *zone, struct page *page,
-				unsigned int order, int migratetype) {}
+				unsigned int order) {}
 #endif	/* CONFIG_DEBUG_PAGEALLOC */
 
 #ifdef __HAVE_ARCH_GATE_AREA
@@ -3570,13 +4210,7 @@ static inline int in_gate_area(struct mm_struct *mm, unsigned long addr)
 }
 #endif	/* __HAVE_ARCH_GATE_AREA */
 
-extern bool process_shares_mm(struct task_struct *p, struct mm_struct *mm);
-
-#ifdef CONFIG_SYSCTL
-extern int sysctl_drop_caches;
-int drop_caches_sysctl_handler(struct ctl_table *, int, void *, size_t *,
-		loff_t *);
-#endif
+bool process_shares_mm(const struct task_struct *p, const struct mm_struct *mm);
 
 void drop_slab(void);
 
@@ -3596,17 +4230,17 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
 #endif
 
 void *sparse_buffer_alloc(unsigned long size);
+unsigned long section_map_size(void);
 struct page * __populate_section_memmap(unsigned long pfn,
 		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
-void pmd_init(void *addr);
-void pud_init(void *addr);
 pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
 p4d_t *vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node);
 pud_t *vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node);
 pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
 pte_t *vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node,
-			    struct vmem_altmap *altmap, struct page *reuse);
+			    struct vmem_altmap *altmap, unsigned long ptpfn,
+			    unsigned long flags);
 void *vmemmap_alloc_block(unsigned long size, int node);
 struct vmem_altmap;
 void *vmemmap_alloc_block_buf(unsigned long size, int node,
@@ -3622,19 +4256,70 @@ int vmemmap_populate_hugepages(unsigned long start, unsigned long end,
 			       int node, struct vmem_altmap *altmap);
 int vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap);
+int vmemmap_populate_hvo(unsigned long start, unsigned long end, int node,
+			 unsigned long headsize);
+int vmemmap_undo_hvo(unsigned long start, unsigned long end, int node,
+		     unsigned long headsize);
+void vmemmap_wrprotect_hvo(unsigned long start, unsigned long end, int node,
+			  unsigned long headsize);
 void vmemmap_populate_print_last(void);
 #ifdef CONFIG_MEMORY_HOTPLUG
 void vmemmap_free(unsigned long start, unsigned long end,
 		struct vmem_altmap *altmap);
 #endif
 
-#ifdef CONFIG_ARCH_WANT_OPTIMIZE_VMEMMAP
-static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
-					   struct dev_pagemap *pgmap)
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap)
+{
+	/* number of pfns from base where pfn_to_page() is valid */
+	if (altmap)
+		return altmap->reserve + altmap->free;
+	return 0;
+}
+
+static inline void vmem_altmap_free(struct vmem_altmap *altmap,
+				    unsigned long nr_pfns)
+{
+	altmap->alloc -= nr_pfns;
+}
+#else
+static inline unsigned long vmem_altmap_offset(const struct vmem_altmap *altmap)
+{
+	return 0;
+}
+
+static inline void vmem_altmap_free(struct vmem_altmap *altmap,
+				    unsigned long nr_pfns)
 {
-	return is_power_of_2(sizeof(struct page)) &&
-		pgmap && (pgmap_vmemmap_nr(pgmap) > 1) && !altmap;
 }
+#endif
+
+#define VMEMMAP_RESERVE_NR	2
+#ifdef CONFIG_ARCH_WANT_OPTIMIZE_DAX_VMEMMAP
+static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap,
+					  struct dev_pagemap *pgmap)
+{
+	unsigned long nr_pages;
+	unsigned long nr_vmemmap_pages;
+
+	if (!pgmap || !is_power_of_2(sizeof(struct page)))
+		return false;
+
+	nr_pages = pgmap_vmemmap_nr(pgmap);
+	nr_vmemmap_pages = ((nr_pages * sizeof(struct page)) >> PAGE_SHIFT);
+	/*
+	 * For vmemmap optimization with DAX we need minimum 2 vmemmap
+	 * pages. See layout diagram in Documentation/mm/vmemmap_dedup.rst
+	 */
+	return !altmap && (nr_vmemmap_pages > VMEMMAP_RESERVE_NR);
+}
+/*
+ * If we don't have an architecture override, use the generic rule
+ */
+#ifndef vmemmap_can_optimize
+#define vmemmap_can_optimize __vmemmap_can_optimize
+#endif
+
 #else
 static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
 					   struct dev_pagemap *pgmap)
@@ -3643,9 +4328,6 @@ static inline bool vmemmap_can_optimize(struct vmem_altmap *altmap,
 }
 #endif
 
-void register_page_bootmem_memmap(unsigned long section_nr, struct page *map,
-				  unsigned long nr_pages);
-
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
 	MF_ACTION_REQUIRED = 1 << 1,
@@ -3654,13 +4336,12 @@ enum mf_flags {
 	MF_UNPOISON = 1 << 4,
 	MF_SW_SIMULATED = 1 << 5,
 	MF_NO_RETRY = 1 << 6,
+	MF_MEM_PRE_REMOVE = 1 << 7,
 };
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
-extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
-extern void shake_page(struct page *p);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
 #ifdef CONFIG_MEMORY_FAILURE
@@ -3673,7 +4354,6 @@ extern int __get_huge_page_for_hwpoison(unsigned long pfn, int flags,
 					bool *migratable_cleared);
 void num_poisoned_pages_inc(unsigned long pfn);
 void num_poisoned_pages_sub(unsigned long pfn, long i);
-struct task_struct *task_early_kill(struct task_struct *tsk, int force_early);
 #else
 static inline void memory_failure_queue(unsigned long pfn, int flags)
 {
@@ -3694,12 +4374,6 @@ static inline void num_poisoned_pages_sub(unsigned long pfn, long i)
 }
 #endif
 
-#if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_KSM)
-void add_to_kill_ksm(struct task_struct *tsk, struct page *p,
-		     struct vm_area_struct *vma, struct list_head *to_kill,
-		     unsigned long ksm_addr);
-#endif
-
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_MEMORY_HOTPLUG)
 extern void memblk_nr_poison_inc(unsigned long pfn);
 extern void memblk_nr_poison_sub(unsigned long pfn, long i);
@@ -3740,10 +4414,10 @@ enum mf_result {
 enum mf_action_page_type {
 	MF_MSG_KERNEL,
 	MF_MSG_KERNEL_HIGH_ORDER,
-	MF_MSG_SLAB,
 	MF_MSG_DIFFERENT_COMPOUND,
 	MF_MSG_HUGE,
 	MF_MSG_FREE_HUGE,
+	MF_MSG_GET_HWPOISON,
 	MF_MSG_UNMAP_FAILED,
 	MF_MSG_DIRTY_SWAPCACHE,
 	MF_MSG_CLEAN_SWAPCACHE,
@@ -3757,13 +4431,13 @@ enum mf_action_page_type {
 	MF_MSG_BUDDY,
 	MF_MSG_DAX,
 	MF_MSG_UNSPLIT_THP,
+	MF_MSG_ALREADY_POISONED,
+	MF_MSG_PFN_MAP,
 	MF_MSG_UNKNOWN,
 };
 
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) || defined(CONFIG_HUGETLBFS)
-extern void clear_huge_page(struct page *page,
-			    unsigned long addr_hint,
-			    unsigned int pages_per_huge_page);
+void folio_zero_user(struct folio *folio, unsigned long addr_hint);
 int copy_user_large_folio(struct folio *dst, struct folio *src,
 			  unsigned long addr_hint,
 			  struct vm_area_struct *vma);
@@ -3814,56 +4488,158 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 				      pgoff_t first_index, pgoff_t nr);
 #endif
 
-extern int sysctl_nr_trim_pages;
+#ifdef CONFIG_ANON_VMA_NAME
+int set_anon_vma_name(unsigned long addr, unsigned long size,
+		      const char __user *uname);
+#else
+static inline
+int set_anon_vma_name(unsigned long addr, unsigned long size,
+		      const char __user *uname)
+{
+	return -EINVAL;
+}
+#endif
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+
+bool range_contains_unaccepted_memory(phys_addr_t start, unsigned long size);
+void accept_memory(phys_addr_t start, unsigned long size);
 
-#ifdef CONFIG_PRINTK
-void mem_dump_obj(void *object);
 #else
-static inline void mem_dump_obj(void *object) {}
+
+static inline bool range_contains_unaccepted_memory(phys_addr_t start,
+						    unsigned long size)
+{
+	return false;
+}
+
+static inline void accept_memory(phys_addr_t start, unsigned long size)
+{
+}
+
 #endif
 
-/**
- * seal_check_future_write - Check for F_SEAL_FUTURE_WRITE flag and handle it
- * @seals: the seals to check
- * @vma: the vma to operate on
- *
- * Check whether F_SEAL_FUTURE_WRITE is set; if so, do proper check/handling on
- * the vma flags.  Return 0 if check pass, or <0 for errors.
- */
-static inline int seal_check_future_write(int seals, struct vm_area_struct *vma)
-{
-	if (seals & F_SEAL_FUTURE_WRITE) {
-		/*
-		 * New PROT_WRITE and MAP_SHARED mmaps are not allowed when
-		 * "future write" seal active.
-		 */
-		if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_WRITE))
-			return -EPERM;
-
-		/*
-		 * Since an F_SEAL_FUTURE_WRITE sealed memfd can be mapped as
-		 * MAP_SHARED and read-only, take care to not allow mprotect to
-		 * revert protections on such mappings. Do this only for shared
-		 * mappings. For private mappings, don't need to mask
-		 * VM_MAYWRITE as we still want them to be COW-writable.
-		 */
-		if (vma->vm_flags & VM_SHARED)
-			vm_flags_clear(vma, VM_MAYWRITE);
-	}
+static inline bool pfn_is_unaccepted_memory(unsigned long pfn)
+{
+	return range_contains_unaccepted_memory(pfn << PAGE_SHIFT, PAGE_SIZE);
+}
 
+void vma_pgtable_walk_begin(struct vm_area_struct *vma);
+void vma_pgtable_walk_end(struct vm_area_struct *vma);
+
+int reserve_mem_find_by_name(const char *name, phys_addr_t *start, phys_addr_t *size);
+int reserve_mem_release_by_name(const char *name);
+
+#ifdef CONFIG_64BIT
+int do_mseal(unsigned long start, size_t len_in, unsigned long flags);
+#else
+static inline int do_mseal(unsigned long start, size_t len_in, unsigned long flags)
+{
+	/* noop on 32 bit */
 	return 0;
 }
+#endif
+
+/*
+ * user_alloc_needs_zeroing checks if a user folio from page allocator needs to
+ * be zeroed or not.
+ */
+static inline bool user_alloc_needs_zeroing(void)
+{
+	/*
+	 * for user folios, arch with cache aliasing requires cache flush and
+	 * arc changes folio->flags to make icache coherent with dcache, so
+	 * always return false to make caller use
+	 * clear_user_page()/clear_user_highpage().
+	 */
+	return cpu_dcache_is_aliasing() || cpu_icache_is_aliasing() ||
+	       !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
+				   &init_on_alloc);
+}
 
-#ifdef CONFIG_ANON_VMA_NAME
-int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
-			  unsigned long len_in,
-			  struct anon_vma_name *anon_name);
+int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
+int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
+int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
+
+/*
+ * DMA mapping IDs for page_pool
+ *
+ * When DMA-mapping a page, page_pool allocates an ID (from an xarray) and
+ * stashes it in the upper bits of page->pp_magic. We always want to be able to
+ * unambiguously identify page pool pages (using page_pool_page_is_pp()). Non-PP
+ * pages can have arbitrary kernel pointers stored in the same field as pp_magic
+ * (since it overlaps with page->lru.next), so we must ensure that we cannot
+ * mistake a valid kernel pointer with any of the values we write into this
+ * field.
+ *
+ * On architectures that set POISON_POINTER_DELTA, this is already ensured,
+ * since this value becomes part of PP_SIGNATURE; meaning we can just use the
+ * space between the PP_SIGNATURE value (without POISON_POINTER_DELTA), and the
+ * lowest bits of POISON_POINTER_DELTA. On arches where POISON_POINTER_DELTA is
+ * 0, we use the lowest bit of PAGE_OFFSET as the boundary if that value is
+ * known at compile-time.
+ *
+ * If the value of PAGE_OFFSET is not known at compile time, or if it is too
+ * small to leave at least 8 bits available above PP_SIGNATURE, we define the
+ * number of bits to be 0, which turns off the DMA index tracking altogether
+ * (see page_pool_register_dma_index()).
+ */
+#define PP_DMA_INDEX_SHIFT (1 + __fls(PP_SIGNATURE - POISON_POINTER_DELTA))
+#if POISON_POINTER_DELTA > 0
+/* PP_SIGNATURE includes POISON_POINTER_DELTA, so limit the size of the DMA
+ * index to not overlap with that if set
+ */
+#define PP_DMA_INDEX_BITS MIN(32, __ffs(POISON_POINTER_DELTA) - PP_DMA_INDEX_SHIFT)
 #else
-static inline int
-madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
-		      unsigned long len_in, struct anon_vma_name *anon_name) {
-	return 0;
+/* Use the lowest bit of PAGE_OFFSET if there's at least 8 bits available; see above */
+#define PP_DMA_INDEX_MIN_OFFSET (1 << (PP_DMA_INDEX_SHIFT + 8))
+#define PP_DMA_INDEX_BITS ((__builtin_constant_p(PAGE_OFFSET) && \
+			    PAGE_OFFSET >= PP_DMA_INDEX_MIN_OFFSET && \
+			    !(PAGE_OFFSET & (PP_DMA_INDEX_MIN_OFFSET - 1))) ? \
+			      MIN(32, __ffs(PAGE_OFFSET) - PP_DMA_INDEX_SHIFT) : 0)
+
+#endif
+
+#define PP_DMA_INDEX_MASK GENMASK(PP_DMA_INDEX_BITS + PP_DMA_INDEX_SHIFT - 1, \
+				  PP_DMA_INDEX_SHIFT)
+
+/* Mask used for checking in page_pool_page_is_pp() below. page->pp_magic is
+ * OR'ed with PP_SIGNATURE after the allocation in order to preserve bit 0 for
+ * the head page of compound page and bit 1 for pfmemalloc page, as well as the
+ * bits used for the DMA index. page_is_pfmemalloc() is checked in
+ * __page_pool_put_page() to avoid recycling the pfmemalloc page.
+ */
+#define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
+
+#ifdef CONFIG_PAGE_POOL
+static inline bool page_pool_page_is_pp(const struct page *page)
+{
+	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
+}
+#else
+static inline bool page_pool_page_is_pp(const struct page *page)
+{
+	return false;
 }
 #endif
 
+#define PAGE_SNAPSHOT_FAITHFUL (1 << 0)
+#define PAGE_SNAPSHOT_PG_BUDDY (1 << 1)
+#define PAGE_SNAPSHOT_PG_IDLE  (1 << 2)
+
+struct page_snapshot {
+	struct folio folio_snapshot;
+	struct page page_snapshot;
+	unsigned long pfn;
+	unsigned long idx;
+	unsigned long flags;
+};
+
+static inline bool snapshot_page_is_faithful(const struct page_snapshot *ps)
+{
+	return ps->flags & PAGE_SNAPSHOT_FAITHFUL;
+}
+
+void snapshot_page(struct page_snapshot *ps, const struct page *page);
+
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h
index 0e1d239a882c..fa2d6ba811b5 100644
--- a/include/linux/mm_inline.h
+++ b/include/linux/mm_inline.h
@@ -4,10 +4,11 @@
 
 #include <linux/atomic.h>
 #include <linux/huge_mm.h>
+#include <linux/mm_types.h>
 #include <linux/swap.h>
 #include <linux/string.h>
 #include <linux/userfaultfd_k.h>
-#include <linux/swapops.h>
+#include <linux/leafops.h>
 
 /**
  * folio_is_file_lru - Should the folio be on a file LRU or anon LRU?
@@ -24,7 +25,7 @@
  * 0 if @folio is a normal anonymous folio, a tmpfs folio or otherwise
  * ram or swap backed folio.
  */
-static inline int folio_is_file_lru(struct folio *folio)
+static inline int folio_is_file_lru(const struct folio *folio)
 {
 	return !folio_test_swapbacked(folio);
 }
@@ -43,7 +44,7 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
 	lockdep_assert_held(&lruvec->lru_lock);
 	WARN_ON_ONCE(nr_pages != (int)nr_pages);
 
-	__mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
+	mod_lruvec_state(lruvec, NR_LRU_BASE + lru, nr_pages);
 	__mod_zone_page_state(&pgdat->node_zones[zid],
 				NR_ZONE_LRU_BASE + lru, nr_pages);
 }
@@ -83,7 +84,7 @@ static __always_inline void __folio_clear_lru_flags(struct folio *folio)
  * Return: The LRU list a folio should be on, as an index
  * into the array of LRU lists.
  */
-static __always_inline enum lru_list folio_lru_list(struct folio *folio)
+static __always_inline enum lru_list folio_lru_list(const struct folio *folio)
 {
 	enum lru_list lru;
 
@@ -132,36 +133,35 @@ static inline int lru_hist_from_seq(unsigned long seq)
 	return seq % NR_HIST_GENS;
 }
 
-static inline int lru_tier_from_refs(int refs)
+static inline int lru_tier_from_refs(int refs, bool workingset)
 {
 	VM_WARN_ON_ONCE(refs > BIT(LRU_REFS_WIDTH));
 
-	/* see the comment in folio_lru_refs() */
-	return order_base_2(refs + 1);
+	/* see the comment on MAX_NR_TIERS */
+	return workingset ? MAX_NR_TIERS - 1 : order_base_2(refs);
 }
 
-static inline int folio_lru_refs(struct folio *folio)
+static inline int folio_lru_refs(const struct folio *folio)
 {
-	unsigned long flags = READ_ONCE(folio->flags);
-	bool workingset = flags & BIT(PG_workingset);
+	unsigned long flags = READ_ONCE(folio->flags.f);
 
+	if (!(flags & BIT(PG_referenced)))
+		return 0;
 	/*
-	 * Return the number of accesses beyond PG_referenced, i.e., N-1 if the
-	 * total number of accesses is N>1, since N=0,1 both map to the first
-	 * tier. lru_tier_from_refs() will account for this off-by-one. Also see
-	 * the comment on MAX_NR_TIERS.
+	 * Return the total number of accesses including PG_referenced. Also see
+	 * the comment on LRU_REFS_FLAGS.
 	 */
-	return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + workingset;
+	return ((flags & LRU_REFS_MASK) >> LRU_REFS_PGOFF) + 1;
 }
 
-static inline int folio_lru_gen(struct folio *folio)
+static inline int folio_lru_gen(const struct folio *folio)
 {
-	unsigned long flags = READ_ONCE(folio->flags);
+	unsigned long flags = READ_ONCE(folio->flags.f);
 
 	return ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
 }
 
-static inline bool lru_gen_is_active(struct lruvec *lruvec, int gen)
+static inline bool lru_gen_is_active(const struct lruvec *lruvec, int gen)
 {
 	unsigned long max_seq = lruvec->lrugen.max_seq;
 
@@ -217,6 +217,40 @@ static inline void lru_gen_update_size(struct lruvec *lruvec, struct folio *foli
 	VM_WARN_ON_ONCE(lru_gen_is_active(lruvec, old_gen) && !lru_gen_is_active(lruvec, new_gen));
 }
 
+static inline unsigned long lru_gen_folio_seq(const struct lruvec *lruvec,
+					      const struct folio *folio,
+					      bool reclaiming)
+{
+	int gen;
+	int type = folio_is_file_lru(folio);
+	const struct lru_gen_folio *lrugen = &lruvec->lrugen;
+
+	/*
+	 * +-----------------------------------+-----------------------------------+
+	 * | Accessed through page tables and  | Accessed through file descriptors |
+	 * | promoted by folio_update_gen()    | and protected by folio_inc_gen()  |
+	 * +-----------------------------------+-----------------------------------+
+	 * | PG_active (set while isolated)    |                                   |
+	 * +-----------------+-----------------+-----------------+-----------------+
+	 * |  PG_workingset  |  PG_referenced  |  PG_workingset  |  LRU_REFS_FLAGS |
+	 * +-----------------------------------+-----------------------------------+
+	 * |<---------- MIN_NR_GENS ---------->|                                   |
+	 * |<---------------------------- MAX_NR_GENS ---------------------------->|
+	 */
+	if (folio_test_active(folio))
+		gen = MIN_NR_GENS - folio_test_workingset(folio);
+	else if (reclaiming)
+		gen = MAX_NR_GENS;
+	else if ((!folio_is_file_lru(folio) && !folio_test_swapcache(folio)) ||
+		 (folio_test_reclaim(folio) &&
+		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
+		gen = MIN_NR_GENS;
+	else
+		gen = MAX_NR_GENS - folio_test_workingset(folio);
+
+	return max(READ_ONCE(lrugen->max_seq) - gen + 1, READ_ONCE(lrugen->min_seq[type]));
+}
+
 static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio, bool reclaiming)
 {
 	unsigned long seq;
@@ -230,28 +264,12 @@ static inline bool lru_gen_add_folio(struct lruvec *lruvec, struct folio *folio,
 
 	if (folio_test_unevictable(folio) || !lrugen->enabled)
 		return false;
-	/*
-	 * There are three common cases for this page:
-	 * 1. If it's hot, e.g., freshly faulted in or previously hot and
-	 *    migrated, add it to the youngest generation.
-	 * 2. If it's cold but can't be evicted immediately, i.e., an anon page
-	 *    not in swapcache or a dirty page pending writeback, add it to the
-	 *    second oldest generation.
-	 * 3. Everything else (clean, cold) is added to the oldest generation.
-	 */
-	if (folio_test_active(folio))
-		seq = lrugen->max_seq;
-	else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) ||
-		 (folio_test_reclaim(folio) &&
-		  (folio_test_dirty(folio) || folio_test_writeback(folio))))
-		seq = lrugen->min_seq[type] + 1;
-	else
-		seq = lrugen->min_seq[type];
 
+	seq = lru_gen_folio_seq(lruvec, folio, reclaiming);
 	gen = lru_gen_from_seq(seq);
 	flags = (gen + 1UL) << LRU_GEN_PGOFF;
 	/* see the comment on MIN_NR_GENS about PG_active */
-	set_mask_bits(&folio->flags, LRU_GEN_MASK | BIT(PG_active), flags);
+	set_mask_bits(&folio->flags.f, LRU_GEN_MASK | BIT(PG_active), flags);
 
 	lru_gen_update_size(lruvec, folio, -1, gen);
 	/* for folio_rotate_reclaimable() */
@@ -276,7 +294,7 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio,
 
 	/* for folio_migrate_flags() */
 	flags = !reclaiming && lru_gen_is_active(lruvec, gen) ? BIT(PG_active) : 0;
-	flags = set_mask_bits(&folio->flags, LRU_GEN_MASK, flags);
+	flags = set_mask_bits(&folio->flags.f, LRU_GEN_MASK, flags);
 	gen = ((flags & LRU_GEN_MASK) >> LRU_GEN_PGOFF) - 1;
 
 	lru_gen_update_size(lruvec, folio, gen, -1);
@@ -285,6 +303,12 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio,
 	return true;
 }
 
+static inline void folio_migrate_refs(struct folio *new, const struct folio *old)
+{
+	unsigned long refs = READ_ONCE(old->flags.f) & LRU_REFS_MASK;
+
+	set_mask_bits(&new->flags.f, LRU_REFS_MASK, refs);
+}
 #else /* !CONFIG_LRU_GEN */
 
 static inline bool lru_gen_enabled(void)
@@ -307,6 +331,10 @@ static inline bool lru_gen_del_folio(struct lruvec *lruvec, struct folio *folio,
 	return false;
 }
 
+static inline void folio_migrate_refs(struct folio *new, const struct folio *old)
+{
+
+}
 #endif /* CONFIG_LRU_GEN */
 
 static __always_inline
@@ -323,12 +351,6 @@ void lruvec_add_folio(struct lruvec *lruvec, struct folio *folio)
 		list_add(&folio->lru, &lruvec->lists[lru]);
 }
 
-static __always_inline void add_page_to_lru_list(struct page *page,
-				struct lruvec *lruvec)
-{
-	lruvec_add_folio(lruvec, page_folio(page));
-}
-
 static __always_inline
 void lruvec_add_folio_tail(struct lruvec *lruvec, struct folio *folio)
 {
@@ -357,22 +379,7 @@ void lruvec_del_folio(struct lruvec *lruvec, struct folio *folio)
 			-folio_nr_pages(folio));
 }
 
-static __always_inline void del_page_from_lru_list(struct page *page,
-				struct lruvec *lruvec)
-{
-	lruvec_del_folio(lruvec, page_folio(page));
-}
-
 #ifdef CONFIG_ANON_VMA_NAME
-/*
- * mmap_lock should be read-locked when calling anon_vma_name(). Caller should
- * either keep holding the lock while using the returned pointer or it should
- * raise anon_vma_name refcount before releasing the lock.
- */
-extern struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma);
-extern struct anon_vma_name *anon_vma_name_alloc(const char *name);
-extern void anon_vma_name_free(struct kref *kref);
-
 /* mmap_lock should be read-locked */
 static inline void anon_vma_name_get(struct anon_vma_name *anon_name)
 {
@@ -427,16 +434,6 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
 }
 
 #else /* CONFIG_ANON_VMA_NAME */
-static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
-{
-	return NULL;
-}
-
-static inline struct anon_vma_name *anon_vma_name_alloc(const char *name)
-{
-	return NULL;
-}
-
 static inline void anon_vma_name_get(struct anon_vma_name *anon_name) {}
 static inline void anon_vma_name_put(struct anon_vma_name *anon_name) {}
 static inline void dup_anon_vma_name(struct vm_area_struct *orig_vma,
@@ -451,6 +448,8 @@ static inline bool anon_vma_name_eq(struct anon_vma_name *anon_name1,
 
 #endif  /* CONFIG_ANON_VMA_NAME */
 
+void pfnmap_track_ctx_release(struct kref *ref);
+
 static inline void init_tlb_flush_pending(struct mm_struct *mm)
 {
 	atomic_set(&mm->tlb_flush_pending, 0);
@@ -510,7 +509,7 @@ static inline void dec_tlb_flush_pending(struct mm_struct *mm)
 	atomic_dec(&mm->tlb_flush_pending);
 }
 
-static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+static inline bool mm_tlb_flush_pending(const struct mm_struct *mm)
 {
 	/*
 	 * Must be called after having acquired the PTL; orders against that
@@ -523,7 +522,7 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
 	return atomic_read(&mm->tlb_flush_pending);
 }
 
-static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
+static inline bool mm_tlb_flush_nested(const struct mm_struct *mm)
 {
 	/*
 	 * Similar to mm_tlb_flush_pending(), we must have acquired the PTL
@@ -535,6 +534,26 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
 	return atomic_read(&mm->tlb_flush_pending) > 1;
 }
 
+#ifdef CONFIG_MMU
+/*
+ * Computes the pte marker to copy from the given source entry into dst_vma.
+ * If no marker should be copied, returns 0.
+ * The caller should insert a new pte created with make_pte_marker().
+ */
+static inline pte_marker copy_pte_marker(
+		softleaf_t entry, struct vm_area_struct *dst_vma)
+{
+	const pte_marker srcm = softleaf_to_marker(entry);
+	/* Always copy error entries. */
+	pte_marker dstm = srcm & (PTE_MARKER_POISONED | PTE_MARKER_GUARD);
+
+	/* Only copy PTE markers if UFFD register matches. */
+	if ((srcm & PTE_MARKER_UFFD_WP) && userfaultfd_wp(dst_vma))
+		dstm |= PTE_MARKER_UFFD_WP;
+
+	return dstm;
+}
+
 /*
  * If this pte is wr-protected by uffd-wp in any form, arm the special pte to
  * replace a none pte.  NOTE!  This should only be called when *pte is already
@@ -545,17 +564,19 @@ static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
  * Must be called with pgtable lock held so that no thread will see the none
  * pte, and if they see it, they'll fault and serialize at the pgtable lock.
  *
- * This function is a no-op if PTE_MARKER_UFFD_WP is not enabled.
+ * Returns true if an uffd-wp pte was installed, false otherwise.
  */
-static inline void
+static inline bool
 pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 			      pte_t *pte, pte_t pteval)
 {
-#ifdef CONFIG_PTE_MARKER_UFFD_WP
 	bool arm_uffd_pte = false;
 
+	if (!uffd_supports_wp_marker())
+		return false;
+
 	/* The current status of the pte should be "cleared" before calling */
-	WARN_ON_ONCE(!pte_none(*pte));
+	WARN_ON_ONCE(!pte_none(ptep_get(pte)));
 
 	/*
 	 * NOTE: userfaultfd_wp_unpopulated() doesn't need this whole
@@ -564,7 +585,7 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 	 * with a swap pte.  There's no way of leaking the bit.
 	 */
 	if (vma_is_anonymous(vma) || !userfaultfd_wp(vma))
-		return;
+		return false;
 
 	/* A uffd-wp wr-protected normal pte */
 	if (unlikely(pte_present(pteval) && pte_uffd_wp(pteval)))
@@ -577,13 +598,16 @@ pte_install_uffd_wp_if_needed(struct vm_area_struct *vma, unsigned long addr,
 	if (unlikely(pte_swp_uffd_wp_any(pteval)))
 		arm_uffd_pte = true;
 
-	if (unlikely(arm_uffd_pte))
+	if (unlikely(arm_uffd_pte)) {
 		set_pte_at(vma->vm_mm, addr, pte,
 			   make_pte_marker(PTE_MARKER_UFFD_WP));
-#endif
+		return true;
+	}
+
+	return false;
 }
 
-static inline bool vma_has_recency(struct vm_area_struct *vma)
+static inline bool vma_has_recency(const struct vm_area_struct *vma)
 {
 	if (vma->vm_flags & (VM_SEQ_READ | VM_RAND_READ))
 		return false;
@@ -593,5 +617,42 @@ static inline bool vma_has_recency(struct vm_area_struct *vma)
 
 	return true;
 }
+#endif
+
+/**
+ * num_pages_contiguous() - determine the number of contiguous pages
+ *			    that represent contiguous PFNs
+ * @pages: an array of page pointers
+ * @nr_pages: length of the array, at least 1
+ *
+ * Determine the number of contiguous pages that represent contiguous PFNs
+ * in @pages, starting from the first page.
+ *
+ * In some kernel configs contiguous PFNs will not have contiguous struct
+ * pages. In these configurations num_pages_contiguous() will return a num
+ * smaller than ideal number. The caller should continue to check for pfn
+ * contiguity after each call to num_pages_contiguous().
+ *
+ * Returns the number of contiguous pages.
+ */
+static inline size_t num_pages_contiguous(struct page **pages, size_t nr_pages)
+{
+	struct page *cur_page = pages[0];
+	unsigned long section = memdesc_section(cur_page->flags);
+	size_t i;
+
+	for (i = 1; i < nr_pages; i++) {
+		if (++cur_page != pages[i])
+			break;
+		/*
+		 * In unproblematic kernel configs, page_to_section() == 0 and
+		 * the whole check will get optimized out.
+		 */
+		if (memdesc_section(cur_page->flags) != section)
+			break;
+	}
+
+	return i;
+}
 
 #endif
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 306a3d1a0fa6..9f6de068295d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -19,6 +19,9 @@
 #include <linux/workqueue.h>
 #include <linux/seqlock.h>
 #include <linux/percpu_counter.h>
+#include <linux/types.h>
+#include <linux/rseq_types.h>
+#include <linux/bitmap.h>
 
 #include <asm/mmu.h>
 
@@ -27,11 +30,15 @@
 #endif
 #define AT_VECTOR_SIZE (2*(AT_VECTOR_SIZE_ARCH + AT_VECTOR_SIZE_BASE + 1))
 
-#define INIT_PASID	0
 
 struct address_space;
+struct futex_private_hash;
 struct mem_cgroup;
 
+typedef struct {
+	unsigned long f;
+} memdesc_flags_t;
+
 /*
  * Each physical page in the system has a struct page associated with
  * it to keep track of whatever it is we are using the page for at the
@@ -46,9 +53,7 @@ struct mem_cgroup;
  * which is guaranteed to be aligned.  If you use the same storage as
  * page->mapping, you must restore it to NULL before freeing the page.
  *
- * If your page will not be mapped to userspace, you can also use the four
- * bytes in the mapcount union, but you must call page_mapcount_reset()
- * before freeing it.
+ * The mapcount field must not be used for own purposes.
  *
  * If you want to use the refcount field, it must be used in such a way
  * that other CPUs temporarily incrementing and then decrementing the
@@ -72,7 +77,7 @@ struct mem_cgroup;
 #endif
 
 struct page {
-	unsigned long flags;		/* Atomic flags, some possibly
+	memdesc_flags_t flags;		/* Atomic flags, some possibly
 					 * updated asynchronously */
 	/*
 	 * Five words (20/40 bytes) are available in this union.
@@ -90,29 +95,22 @@ struct page {
 			union {
 				struct list_head lru;
 
-				/* Or, for the Unevictable "LRU list" slot */
-				struct {
-					/* Always even, to negate PageTail */
-					void *__filler;
-					/* Count page's or folio's mlocks */
-					unsigned int mlock_count;
-				};
-
 				/* Or, free page */
 				struct list_head buddy_list;
 				struct list_head pcp_list;
+				struct llist_node pcp_llist;
 			};
-			/* See page-flags.h for PAGE_MAPPING_FLAGS */
 			struct address_space *mapping;
 			union {
-				pgoff_t index;		/* Our offset within mapping. */
+				pgoff_t __folio_index;		/* Our offset within mapping. */
 				unsigned long share;	/* share count for fsdax */
 			};
 			/**
 			 * @private: Mapping-private opaque data.
 			 * Usually used for buffer_heads if PagePrivate.
-			 * Used for swp_entry_t if PageSwapCache.
-			 * Indicates order in the buddy system if PageBuddy.
+			 * Used for swp_entry_t if swapcache flag set.
+			 * Indicates order in the buddy system if PageBuddy
+			 * or on pcp_llist.
 			 */
 			unsigned long private;
 		};
@@ -125,39 +123,17 @@ struct page {
 			struct page_pool *pp;
 			unsigned long _pp_mapping_pad;
 			unsigned long dma_addr;
-			union {
-				/**
-				 * dma_addr_upper: might require a 64-bit
-				 * value on 32-bit architectures.
-				 */
-				unsigned long dma_addr_upper;
-				/**
-				 * For frag page support, not supported in
-				 * 32-bit architectures with 64-bit DMA.
-				 */
-				atomic_long_t pp_frag_count;
-			};
+			atomic_long_t pp_ref_count;
 		};
 		struct {	/* Tail pages of compound page */
 			unsigned long compound_head;	/* Bit zero is set */
 		};
-		struct {	/* Page table pages */
-			unsigned long _pt_pad_1;	/* compound_head */
-			pgtable_t pmd_huge_pte; /* protected by page->ptl */
-			unsigned long _pt_pad_2;	/* mapping */
-			union {
-				struct mm_struct *pt_mm; /* x86 pgds only */
-				atomic_t pt_frag_refcount; /* powerpc */
-			};
-#if ALLOC_SPLIT_PTLOCKS
-			spinlock_t *ptl;
-#else
-			spinlock_t ptl;
-#endif
-		};
 		struct {	/* ZONE_DEVICE pages */
-			/** @pgmap: Points to the hosting device page map. */
-			struct dev_pagemap *pgmap;
+			/*
+			 * The first word is used for compound_head or folio
+			 * pgmap
+			 */
+			void *_unused_pgmap_compound_head;
 			void *zone_device_data;
 			/*
 			 * ZONE_DEVICE private pages are counted as being
@@ -177,18 +153,31 @@ struct page {
 
 	union {		/* This union is 4 bytes in size. */
 		/*
-		 * If the page can be mapped to userspace, encodes the number
-		 * of times this page is referenced by a page table.
+		 * For head pages of typed folios, the value stored here
+		 * allows for determining what this page is used for. The
+		 * tail pages of typed folios will not store a type
+		 * (page_type == _mapcount == -1).
+		 *
+		 * See page-flags.h for a list of page types which are currently
+		 * stored here.
+		 *
+		 * Owners of typed folios may reuse the lower 16 bit of the
+		 * head page page_type field after setting the page type,
+		 * but must reset these 16 bit to -1 before clearing the
+		 * page type.
 		 */
-		atomic_t _mapcount;
+		unsigned int page_type;
 
 		/*
-		 * If the page is neither PageSlab nor mappable to userspace,
-		 * the value stored here may help determine what this page
-		 * is used for.  See page-flags.h for a list of page types
-		 * which are currently stored here.
+		 * For pages that are part of non-typed folios for which mappings
+		 * are tracked via the RMAP, encodes the number of times this page
+		 * is directly referenced by a page table.
+		 *
+		 * Note that the mapcount is always initialized to -1, so that
+		 * transitions both from it and to it can be tracked, using
+		 * atomic_inc_and_test() and atomic_add_negative(-1).
 		 */
-		unsigned int page_type;
+		atomic_t _mapcount;
 	};
 
 	/* Usage count. *DO NOT USE DIRECTLY*. See page_ref.h */
@@ -196,6 +185,8 @@ struct page {
 
 #ifdef CONFIG_MEMCG
 	unsigned long memcg_data;
+#elif defined(CONFIG_SLAB_OBJ_EXT)
+	unsigned long _unused_slab_obj_exts;
 #endif
 
 	/*
@@ -213,6 +204,10 @@ struct page {
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
 
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+	int _last_cpupid;
+#endif
+
 #ifdef CONFIG_KMSAN
 	/*
 	 * KMSAN metadata for this page:
@@ -224,10 +219,6 @@ struct page {
 	struct page *kmsan_shadow;
 	struct page *kmsan_origin;
 #endif
-
-#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
-	int _last_cpupid;
-#endif
 } _struct_page_alignment;
 
 /*
@@ -235,8 +226,8 @@ struct page {
  *
  * An 'encoded_page' pointer is a pointer to a regular 'struct page', but
  * with the low bits of the pointer indicating extra context-dependent
- * information. Not super-common, but happens in mmu_gather and mlock
- * handling, and this acts as a type system check on that use.
+ * information. Only used in mmu_gather handling, and this acts as a type
+ * system check on that use.
  *
  * We only really have two guaranteed bits in general, although you could
  * play with 'struct page' alignment (see CONFIG_HAVE_ALIGNED_STRUCT_PAGE)
@@ -245,23 +236,124 @@ struct page {
  * Use the supplied helper functions to endcode/decode the pointer and bits.
  */
 struct encoded_page;
-#define ENCODE_PAGE_BITS 3ul
+
+#define ENCODED_PAGE_BITS			3ul
+
+/* Perform rmap removal after we have flushed the TLB. */
+#define ENCODED_PAGE_BIT_DELAY_RMAP		1ul
+
+/*
+ * The next item in an encoded_page array is the "nr_pages" argument, specifying
+ * the number of consecutive pages starting from this page, that all belong to
+ * the same folio. For example, "nr_pages" corresponds to the number of folio
+ * references that must be dropped. If this bit is not set, "nr_pages" is
+ * implicitly 1.
+ */
+#define ENCODED_PAGE_BIT_NR_PAGES_NEXT		2ul
+
 static __always_inline struct encoded_page *encode_page(struct page *page, unsigned long flags)
 {
-	BUILD_BUG_ON(flags > ENCODE_PAGE_BITS);
+	BUILD_BUG_ON(flags > ENCODED_PAGE_BITS);
 	return (struct encoded_page *)(flags | (unsigned long)page);
 }
 
 static inline unsigned long encoded_page_flags(struct encoded_page *page)
 {
-	return ENCODE_PAGE_BITS & (unsigned long)page;
+	return ENCODED_PAGE_BITS & (unsigned long)page;
 }
 
 static inline struct page *encoded_page_ptr(struct encoded_page *page)
 {
-	return (struct page *)(~ENCODE_PAGE_BITS & (unsigned long)page);
+	return (struct page *)(~ENCODED_PAGE_BITS & (unsigned long)page);
+}
+
+static __always_inline struct encoded_page *encode_nr_pages(unsigned long nr)
+{
+	VM_WARN_ON_ONCE((nr << 2) >> 2 != nr);
+	return (struct encoded_page *)(nr << 2);
+}
+
+static __always_inline unsigned long encoded_nr_pages(struct encoded_page *page)
+{
+	return ((unsigned long)page) >> 2;
 }
 
+/*
+ * A swap entry has to fit into a "unsigned long", as the entry is hidden
+ * in the "index" field of the swapper address space.
+ */
+typedef struct {
+	unsigned long val;
+} swp_entry_t;
+
+/**
+ * typedef softleaf_t - Describes a page table software leaf entry, abstracted
+ * from its architecture-specific encoding.
+ *
+ * Page table leaf entries are those which do not reference any descendent page
+ * tables but rather either reference a data page, are an empty (or 'none'
+ * entry), or contain a non-present entry.
+ *
+ * If referencing another page table or a data page then the page table entry is
+ * pertinent to hardware - that is it tells the hardware how to decode the page
+ * table entry.
+ *
+ * Otherwise it is a software-defined leaf page table entry, which this type
+ * describes. See leafops.h and specifically @softleaf_type for a list of all
+ * possible kinds of software leaf entry.
+ *
+ * A softleaf_t entry is abstracted from the hardware page table entry, so is
+ * not architecture-specific.
+ *
+ * NOTE: While we transition from the confusing swp_entry_t type used for this
+ *       purpose, we simply alias this type. This will be removed once the
+ *       transition is complete.
+ */
+typedef swp_entry_t softleaf_t;
+
+#if defined(CONFIG_MEMCG) || defined(CONFIG_SLAB_OBJ_EXT)
+/* We have some extra room after the refcount in tail pages. */
+#define NR_PAGES_IN_LARGE_FOLIO
+#endif
+
+/*
+ * On 32bit, we can cut the required metadata in half, because:
+ * (a) PID_MAX_LIMIT implicitly limits the number of MMs we could ever have,
+ *     so we can limit MM IDs to 15 bit (32767).
+ * (b) We don't expect folios where even a single complete PTE mapping by
+ *     one MM would exceed 15 bits (order-15).
+ */
+#ifdef CONFIG_64BIT
+typedef int mm_id_mapcount_t;
+#define MM_ID_MAPCOUNT_MAX		INT_MAX
+typedef unsigned int mm_id_t;
+#else /* !CONFIG_64BIT */
+typedef short mm_id_mapcount_t;
+#define MM_ID_MAPCOUNT_MAX		SHRT_MAX
+typedef unsigned short mm_id_t;
+#endif /* CONFIG_64BIT */
+
+/* We implicitly use the dummy ID for init-mm etc. where we never rmap pages. */
+#define MM_ID_DUMMY			0
+#define MM_ID_MIN			(MM_ID_DUMMY + 1)
+
+/*
+ * We leave the highest bit of each MM id unused, so we can store a flag
+ * in the highest bit of each folio->_mm_id[].
+ */
+#define MM_ID_BITS			((sizeof(mm_id_t) * BITS_PER_BYTE) - 1)
+#define MM_ID_MASK			((1U << MM_ID_BITS) - 1)
+#define MM_ID_MAX			MM_ID_MASK
+
+/*
+ * In order to use bit_spin_lock(), which requires an unsigned long, we
+ * operate on folio->_mm_ids when working on flags.
+ */
+#define FOLIO_MM_IDS_LOCK_BITNUM	MM_ID_BITS
+#define FOLIO_MM_IDS_LOCK_BIT		BIT(FOLIO_MM_IDS_LOCK_BITNUM)
+#define FOLIO_MM_IDS_SHARED_BITNUM	(2 * MM_ID_BITS + 1)
+#define FOLIO_MM_IDS_SHARED_BIT		BIT(FOLIO_MM_IDS_SHARED_BITNUM)
+
 /**
  * struct folio - Represents a contiguous set of bytes.
  * @flags: Identical to the page flags.
@@ -271,24 +363,32 @@ static inline struct page *encoded_page_ptr(struct encoded_page *page)
  *    anonymous memory.
  * @index: Offset within the file, in units of pages.  For anonymous memory,
  *    this is the index from the beginning of the mmap.
+ * @share: number of DAX mappings that reference this folio. See
+ *    dax_associate_entry.
  * @private: Filesystem per-folio data (see folio_attach_private()).
- *    Used for swp_entry_t if folio_test_swapcache().
+ * @swap: Used for swp_entry_t if folio_test_swapcache().
  * @_mapcount: Do not access this member directly.  Use folio_mapcount() to
  *    find out how many times this folio is mapped by userspace.
  * @_refcount: Do not access this member directly.  Use folio_ref_count()
  *    to find how many references there are to this folio.
  * @memcg_data: Memory Control Group data.
- * @_folio_dtor: Which destructor to use for this folio.
- * @_folio_order: Do not use directly, call folio_order().
+ * @pgmap: Metadata for ZONE_DEVICE mappings
+ * @virtual: Virtual address in the kernel direct map.
+ * @_last_cpupid: IDs of last CPU and last process that accessed the folio.
  * @_entire_mapcount: Do not use directly, call folio_entire_mapcount().
- * @_nr_pages_mapped: Do not use directly, call folio_mapcount().
+ * @_large_mapcount: Do not use directly, call folio_mapcount().
+ * @_nr_pages_mapped: Do not use outside of rmap and debug code.
  * @_pincount: Do not use directly, call folio_maybe_dma_pinned().
- * @_folio_nr_pages: Do not use directly, call folio_nr_pages().
+ * @_nr_pages: Do not use directly, call folio_nr_pages().
+ * @_mm_id: Do not use outside of rmap code.
+ * @_mm_ids: Do not use outside of rmap code.
+ * @_mm_id_mapcount: Do not use outside of rmap code.
  * @_hugetlb_subpool: Do not use directly, use accessor in hugetlb.h.
  * @_hugetlb_cgroup: Do not use directly, use accessor in hugetlb_cgroup.h.
  * @_hugetlb_cgroup_rsvd: Do not use directly, use accessor in hugetlb_cgroup.h.
  * @_hugetlb_hwpoison: Do not use directly, call raw_hwp_list_head().
  * @_deferred_list: Folios to be split under memory pressure.
+ * @_unused_slab_obj_exts: Placeholder to match obj_exts in struct slab.
  *
  * A folio is a physically, virtually and logically contiguous set
  * of bytes.  It is a power-of-two in size, and it is aligned to that
@@ -303,25 +403,42 @@ struct folio {
 	union {
 		struct {
 	/* public: */
-			unsigned long flags;
+			memdesc_flags_t flags;
 			union {
 				struct list_head lru;
 	/* private: avoid cluttering the output */
+				/* For the Unevictable "LRU list" slot */
 				struct {
+					/* Avoid compound_head */
 					void *__filler;
 	/* public: */
 					unsigned int mlock_count;
 	/* private: */
 				};
 	/* public: */
+				struct dev_pagemap *pgmap;
 			};
 			struct address_space *mapping;
-			pgoff_t index;
-			void *private;
+			union {
+				pgoff_t index;
+				unsigned long share;
+			};
+			union {
+				void *private;
+				swp_entry_t swap;
+			};
 			atomic_t _mapcount;
 			atomic_t _refcount;
 #ifdef CONFIG_MEMCG
 			unsigned long memcg_data;
+#elif defined(CONFIG_SLAB_OBJ_EXT)
+			unsigned long _unused_slab_obj_exts;
+#endif
+#if defined(WANT_PAGE_VIRTUAL)
+			void *virtual;
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+			int _last_cpupid;
 #endif
 	/* private: the union with struct page is transitional */
 		};
@@ -331,15 +448,30 @@ struct folio {
 		struct {
 			unsigned long _flags_1;
 			unsigned long _head_1;
+			union {
+				struct {
 	/* public: */
-			unsigned char _folio_dtor;
-			unsigned char _folio_order;
-			atomic_t _entire_mapcount;
-			atomic_t _nr_pages_mapped;
-			atomic_t _pincount;
+					atomic_t _large_mapcount;
+					atomic_t _nr_pages_mapped;
 #ifdef CONFIG_64BIT
-			unsigned int _folio_nr_pages;
-#endif
+					atomic_t _entire_mapcount;
+					atomic_t _pincount;
+#endif /* CONFIG_64BIT */
+					mm_id_mapcount_t _mm_id_mapcount[2];
+					union {
+						mm_id_t _mm_id[2];
+						unsigned long _mm_ids;
+					};
+	/* private: the union with struct page is transitional */
+				};
+				unsigned long _usable_1[4];
+			};
+			atomic_t _mapcount_1;
+			atomic_t _refcount_1;
+	/* public: */
+#ifdef NR_PAGES_IN_LARGE_FOLIO
+			unsigned int _nr_pages;
+#endif /* NR_PAGES_IN_LARGE_FOLIO */
 	/* private: the union with struct page is transitional */
 		};
 		struct page __page_1;
@@ -349,20 +481,27 @@ struct folio {
 			unsigned long _flags_2;
 			unsigned long _head_2;
 	/* public: */
-			void *_hugetlb_subpool;
-			void *_hugetlb_cgroup;
-			void *_hugetlb_cgroup_rsvd;
-			void *_hugetlb_hwpoison;
+			struct list_head _deferred_list;
+#ifndef CONFIG_64BIT
+			atomic_t _entire_mapcount;
+			atomic_t _pincount;
+#endif /* !CONFIG_64BIT */
 	/* private: the union with struct page is transitional */
 		};
+		struct page __page_2;
+	};
+	union {
 		struct {
-			unsigned long _flags_2a;
-			unsigned long _head_2a;
+			unsigned long _flags_3;
+			unsigned long _head_3;
 	/* public: */
-			struct list_head _deferred_list;
+			void *_hugetlb_subpool;
+			void *_hugetlb_cgroup;
+			void *_hugetlb_cgroup_rsvd;
+			void *_hugetlb_hwpoison;
 	/* private: the union with struct page is transitional */
 		};
-		struct page __page_2;
+		struct page __page_3;
 	};
 };
 
@@ -372,19 +511,27 @@ FOLIO_MATCH(flags, flags);
 FOLIO_MATCH(lru, lru);
 FOLIO_MATCH(mapping, mapping);
 FOLIO_MATCH(compound_head, lru);
-FOLIO_MATCH(index, index);
+FOLIO_MATCH(__folio_index, index);
 FOLIO_MATCH(private, private);
 FOLIO_MATCH(_mapcount, _mapcount);
 FOLIO_MATCH(_refcount, _refcount);
 #ifdef CONFIG_MEMCG
 FOLIO_MATCH(memcg_data, memcg_data);
 #endif
+#if defined(WANT_PAGE_VIRTUAL)
+FOLIO_MATCH(virtual, virtual);
+#endif
+#ifdef LAST_CPUPID_NOT_IN_PAGE_FLAGS
+FOLIO_MATCH(_last_cpupid, _last_cpupid);
+#endif
 #undef FOLIO_MATCH
 #define FOLIO_MATCH(pg, fl)						\
 	static_assert(offsetof(struct folio, fl) ==			\
 			offsetof(struct page, pg) + sizeof(struct page))
 FOLIO_MATCH(flags, _flags_1);
 FOLIO_MATCH(compound_head, _head_1);
+FOLIO_MATCH(_mapcount, _mapcount_1);
+FOLIO_MATCH(_refcount, _refcount_1);
 #undef FOLIO_MATCH
 #define FOLIO_MATCH(pg, fl)						\
 	static_assert(offsetof(struct folio, fl) ==			\
@@ -392,15 +539,137 @@ FOLIO_MATCH(compound_head, _head_1);
 FOLIO_MATCH(flags, _flags_2);
 FOLIO_MATCH(compound_head, _head_2);
 #undef FOLIO_MATCH
+#define FOLIO_MATCH(pg, fl)						\
+	static_assert(offsetof(struct folio, fl) ==			\
+			offsetof(struct page, pg) + 3 * sizeof(struct page))
+FOLIO_MATCH(flags, _flags_3);
+FOLIO_MATCH(compound_head, _head_3);
+#undef FOLIO_MATCH
+
+/**
+ * struct ptdesc -    Memory descriptor for page tables.
+ * @pt_flags: enum pt_flags plus zone/node/section.
+ * @pt_rcu_head:      For freeing page table pages.
+ * @pt_list:          List of used page tables. Used for s390 gmap shadow pages
+ *                    (which are not linked into the user page tables) and x86
+ *                    pgds.
+ * @_pt_pad_1:        Padding that aliases with page's compound head.
+ * @pmd_huge_pte:     Protected by ptdesc->ptl, used for THPs.
+ * @__page_mapping:   Aliases with page->mapping. Unused for page tables.
+ * @pt_index:         Used for s390 gmap.
+ * @pt_mm:            Used for x86 pgds.
+ * @pt_frag_refcount: For fragmented page table tracking. Powerpc only.
+ * @pt_share_count:   Used for HugeTLB PMD page table share count.
+ * @_pt_pad_2:        Padding to ensure proper alignment.
+ * @ptl:              Lock for the page table.
+ * @__page_type:      Same as page->page_type. Unused for page tables.
+ * @__page_refcount:  Same as page refcount.
+ * @pt_memcg_data:    Memcg data. Tracked for page tables here.
+ *
+ * This struct overlays struct page for now. Do not modify without a good
+ * understanding of the issues.
+ */
+struct ptdesc {
+	memdesc_flags_t pt_flags;
+
+	union {
+		struct rcu_head pt_rcu_head;
+		struct list_head pt_list;
+		struct {
+			unsigned long _pt_pad_1;
+			pgtable_t pmd_huge_pte;
+		};
+	};
+	unsigned long __page_mapping;
+
+	union {
+		pgoff_t pt_index;
+		struct mm_struct *pt_mm;
+		atomic_t pt_frag_refcount;
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+		atomic_t pt_share_count;
+#endif
+	};
+
+	union {
+		unsigned long _pt_pad_2;
+#if ALLOC_SPLIT_PTLOCKS
+		spinlock_t *ptl;
+#else
+		spinlock_t ptl;
+#endif
+	};
+	unsigned int __page_type;
+	atomic_t __page_refcount;
+#ifdef CONFIG_MEMCG
+	unsigned long pt_memcg_data;
+#endif
+};
+
+#define TABLE_MATCH(pg, pt)						\
+	static_assert(offsetof(struct page, pg) == offsetof(struct ptdesc, pt))
+TABLE_MATCH(flags, pt_flags);
+TABLE_MATCH(compound_head, pt_list);
+TABLE_MATCH(compound_head, _pt_pad_1);
+TABLE_MATCH(mapping, __page_mapping);
+TABLE_MATCH(__folio_index, pt_index);
+TABLE_MATCH(rcu_head, pt_rcu_head);
+TABLE_MATCH(page_type, __page_type);
+TABLE_MATCH(_refcount, __page_refcount);
+#ifdef CONFIG_MEMCG
+TABLE_MATCH(memcg_data, pt_memcg_data);
+#endif
+#undef TABLE_MATCH
+static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
+
+#define ptdesc_page(pt)			(_Generic((pt),			\
+	const struct ptdesc *:		(const struct page *)(pt),	\
+	struct ptdesc *:		(struct page *)(pt)))
+
+#define ptdesc_folio(pt)		(_Generic((pt),			\
+	const struct ptdesc *:		(const struct folio *)(pt),	\
+	struct ptdesc *:		(struct folio *)(pt)))
+
+#define page_ptdesc(p)			(_Generic((p),			\
+	const struct page *:		(const struct ptdesc *)(p),	\
+	struct page *:			(struct ptdesc *)(p)))
+
+#ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+	atomic_set(&ptdesc->pt_share_count, 0);
+}
+
+static inline void ptdesc_pmd_pts_inc(struct ptdesc *ptdesc)
+{
+	atomic_inc(&ptdesc->pt_share_count);
+}
+
+static inline void ptdesc_pmd_pts_dec(struct ptdesc *ptdesc)
+{
+	atomic_dec(&ptdesc->pt_share_count);
+}
+
+static inline int ptdesc_pmd_pts_count(const struct ptdesc *ptdesc)
+{
+	return atomic_read(&ptdesc->pt_share_count);
+}
+
+static inline bool ptdesc_pmd_is_shared(struct ptdesc *ptdesc)
+{
+	return !!ptdesc_pmd_pts_count(ptdesc);
+}
+#else
+static inline void ptdesc_pmd_pts_init(struct ptdesc *ptdesc)
+{
+}
+#endif
 
 /*
  * Used for sizing the vmemmap region on some architectures
  */
 #define STRUCT_PAGE_MAX_SHIFT	(order_base_2(sizeof(struct page)))
 
-#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
-#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
-
 /*
  * page_private can be used on tail pages.  However, PagePrivate is only
  * checked by the VM on the head page.  So page_private on the tail pages
@@ -414,29 +683,20 @@ static inline void set_page_private(struct page *page, unsigned long private)
 	page->private = private;
 }
 
-static inline void *folio_get_private(struct folio *folio)
+static inline void *folio_get_private(const struct folio *folio)
 {
 	return folio->private;
 }
 
-struct page_frag_cache {
-	void * va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	__u16 offset;
-	__u16 size;
-#else
-	__u32 offset;
-#endif
-	/* we maintain a pagecount bias, so that we dont dirty cache line
-	 * containing page->_refcount every time we allocate a fragment.
-	 */
-	unsigned int		pagecnt_bias;
-	bool pfmemalloc;
-};
-
 typedef unsigned long vm_flags_t;
 
 /*
+ * freeptr_t represents a SLUB freelist pointer, which might be encoded
+ * and not dereferenceable if CONFIG_SLAB_FREELIST_HARDENED is enabled.
+ */
+typedef struct { unsigned long v; } freeptr_t;
+
+/*
  * A region containing a mapping of a non-memory backed file under NOMMU
  * conditions.  These are held in a global tree and are pinned by the VMAs that
  * map parts of them.
@@ -471,14 +731,162 @@ struct anon_vma_name {
 	char name[];
 };
 
-struct vma_lock {
-	struct rw_semaphore lock;
-};
+#ifdef CONFIG_ANON_VMA_NAME
+/*
+ * mmap_lock should be read-locked when calling anon_vma_name(). Caller should
+ * either keep holding the lock while using the returned pointer or it should
+ * raise anon_vma_name refcount before releasing the lock.
+ */
+struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma);
+struct anon_vma_name *anon_vma_name_alloc(const char *name);
+void anon_vma_name_free(struct kref *kref);
+#else /* CONFIG_ANON_VMA_NAME */
+static inline struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
+{
+	return NULL;
+}
+
+static inline struct anon_vma_name *anon_vma_name_alloc(const char *name)
+{
+	return NULL;
+}
+#endif
+
+#define VMA_LOCK_OFFSET	0x40000000
+#define VMA_REF_LIMIT	(VMA_LOCK_OFFSET - 1)
 
 struct vma_numab_state {
+	/*
+	 * Initialised as time in 'jiffies' after which VMA
+	 * should be scanned.  Delays first scan of new VMA by at
+	 * least sysctl_numa_balancing_scan_delay:
+	 */
 	unsigned long next_scan;
-	unsigned long next_pid_reset;
-	unsigned long access_pids[2];
+
+	/*
+	 * Time in jiffies when pids_active[] is reset to
+	 * detect phase change behaviour:
+	 */
+	unsigned long pids_active_reset;
+
+	/*
+	 * Approximate tracking of PIDs that trapped a NUMA hinting
+	 * fault. May produce false positives due to hash collisions.
+	 *
+	 *   [0] Previous PID tracking
+	 *   [1] Current PID tracking
+	 *
+	 * Window moves after next_pid_reset has expired approximately
+	 * every VMA_PID_RESET_PERIOD jiffies:
+	 */
+	unsigned long pids_active[2];
+
+	/* MM scan sequence ID when scan first started after VMA creation */
+	int start_scan_seq;
+
+	/*
+	 * MM scan sequence ID when the VMA was last completely scanned.
+	 * A VMA is not eligible for scanning if prev_scan_seq == numa_scan_seq
+	 */
+	int prev_scan_seq;
+};
+
+#ifdef __HAVE_PFNMAP_TRACKING
+struct pfnmap_track_ctx {
+	struct kref kref;
+	unsigned long pfn;
+	unsigned long size;	/* in bytes */
+};
+#endif
+
+/* What action should be taken after an .mmap_prepare call is complete? */
+enum mmap_action_type {
+	MMAP_NOTHING,		/* Mapping is complete, no further action. */
+	MMAP_REMAP_PFN,		/* Remap PFN range. */
+	MMAP_IO_REMAP_PFN,	/* I/O remap PFN range. */
+};
+
+/*
+ * Describes an action an mmap_prepare hook can instruct to be taken to complete
+ * the mapping of a VMA. Specified in vm_area_desc.
+ */
+struct mmap_action {
+	union {
+		/* Remap range. */
+		struct {
+			unsigned long start;
+			unsigned long start_pfn;
+			unsigned long size;
+			pgprot_t pgprot;
+		} remap;
+	};
+	enum mmap_action_type type;
+
+	/*
+	 * If specified, this hook is invoked after the selected action has been
+	 * successfully completed. Note that the VMA write lock still held.
+	 *
+	 * The absolute minimum ought to be done here.
+	 *
+	 * Returns 0 on success, or an error code.
+	 */
+	int (*success_hook)(const struct vm_area_struct *vma);
+
+	/*
+	 * If specified, this hook is invoked when an error occurred when
+	 * attempting the selection action.
+	 *
+	 * The hook can return an error code in order to filter the error, but
+	 * it is not valid to clear the error here.
+	 */
+	int (*error_hook)(int err);
+
+	/*
+	 * This should be set in rare instances where the operation required
+	 * that the rmap should not be able to access the VMA until
+	 * completely set up.
+	 */
+	bool hide_from_rmap_until_complete :1;
+};
+
+/*
+ * Opaque type representing current VMA (vm_area_struct) flag state. Must be
+ * accessed via vma_flags_xxx() helper functions.
+ */
+#define NUM_VMA_FLAG_BITS BITS_PER_LONG
+typedef struct {
+	DECLARE_BITMAP(__vma_flags, NUM_VMA_FLAG_BITS);
+} __private vma_flags_t;
+
+/*
+ * Describes a VMA that is about to be mmap()'ed. Drivers may choose to
+ * manipulate mutable fields which will cause those fields to be updated in the
+ * resultant VMA.
+ *
+ * Helper functions are not required for manipulating any field.
+ */
+struct vm_area_desc {
+	/* Immutable state. */
+	const struct mm_struct *const mm;
+	struct file *const file; /* May vary from vm_file in stacked callers. */
+	unsigned long start;
+	unsigned long end;
+
+	/* Mutable fields. Populated with initial state. */
+	pgoff_t pgoff;
+	struct file *vm_file;
+	union {
+		vm_flags_t vm_flags;
+		vma_flags_t vma_flags;
+	};
+	pgprot_t page_prot;
+
+	/* Write-only fields. */
+	const struct vm_operations_struct *vm_ops;
+	void *private_data;
+
+	/* Take further action? */
+	struct mmap_action action;
 };
 
 /*
@@ -486,6 +894,12 @@ struct vma_numab_state {
  * per VM-area/task. A VM area is any part of the process virtual memory
  * space that has a special rule for the page-fault handlers (ie a shared
  * library, the executable area etc).
+ *
+ * Only explicitly marked struct members may be accessed by RCU readers before
+ * getting a stable reference.
+ *
+ * WARNING: when adding new members, please update vm_area_init_from() to copy
+ * them during vm_area_struct content duplication.
  */
 struct vm_area_struct {
 	/* The first cache line has the info for VMA tree walking. */
@@ -496,41 +910,44 @@ struct vm_area_struct {
 			unsigned long vm_start;
 			unsigned long vm_end;
 		};
-#ifdef CONFIG_PER_VMA_LOCK
-		struct rcu_head vm_rcu;	/* Used for deferred freeing. */
-#endif
+		freeptr_t vm_freeptr; /* Pointer used by SLAB_TYPESAFE_BY_RCU */
 	};
 
-	struct mm_struct *vm_mm;	/* The address space we belong to. */
+	/*
+	 * The address space we belong to.
+	 * Unstable RCU readers are allowed to read this.
+	 */
+	struct mm_struct *vm_mm;
 	pgprot_t vm_page_prot;          /* Access permissions of this VMA. */
 
 	/*
 	 * Flags, see mm.h.
 	 * To modify use vm_flags_{init|reset|set|clear|mod} functions.
+	 * Preferably, use vma_flags_xxx() functions.
 	 */
 	union {
+		/* Temporary while VMA flags are being converted. */
 		const vm_flags_t vm_flags;
-		vm_flags_t __private __vm_flags;
+		vma_flags_t flags;
 	};
 
 #ifdef CONFIG_PER_VMA_LOCK
-	int vm_lock_seq;
-	struct vma_lock *vm_lock;
-
-	/* Flag to indicate areas detached from the mm->mm_mt tree */
-	bool detached;
-#endif
-
 	/*
-	 * For areas with an address space and backing store,
-	 * linkage into the address_space->i_mmap interval tree.
+	 * Can only be written (using WRITE_ONCE()) while holding both:
+	 *  - mmap_lock (in write mode)
+	 *  - vm_refcnt bit at VMA_LOCK_OFFSET is set
+	 * Can be read reliably while holding one of:
+	 *  - mmap_lock (in read or write mode)
+	 *  - vm_refcnt bit at VMA_LOCK_OFFSET is set or vm_refcnt > 1
+	 * Can be read unreliably (using READ_ONCE()) for pessimistic bailout
+	 * while holding nothing (except RCU to keep the VMA struct allocated).
 	 *
+	 * This sequence counter is explicitly allowed to overflow; sequence
+	 * counter reuse can only lead to occasional unnecessary use of the
+	 * slowpath.
 	 */
-	struct {
-		struct rb_node rb;
-		unsigned long rb_subtree_last;
-	} shared;
-
+	unsigned int vm_lock_seq;
+#endif
 	/*
 	 * A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
 	 * list, after a COW of one of the file pages.	A MAP_SHARED vma
@@ -550,14 +967,6 @@ struct vm_area_struct {
 	struct file * vm_file;		/* File we map to (can be NULL). */
 	void * vm_private_data;		/* was vm_pte (shared mem) */
 
-#ifdef CONFIG_ANON_VMA_NAME
-	/*
-	 * For private and shared anonymous mappings, a pointer to a null
-	 * terminated string containing the name given to the vma, or NULL if
-	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
-	 */
-	struct anon_vma_name *anon_name;
-#endif
 #ifdef CONFIG_SWAP
 	atomic_long_t swap_readahead_info;
 #endif
@@ -570,25 +979,118 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA_BALANCING
 	struct vma_numab_state *numab_state;	/* NUMA Balancing state */
 #endif
+#ifdef CONFIG_PER_VMA_LOCK
+	/* Unstable RCU readers are allowed to read this. */
+	refcount_t vm_refcnt ____cacheline_aligned_in_smp;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map vmlock_dep_map;
+#endif
+#endif
+	/*
+	 * For areas with an address space and backing store,
+	 * linkage into the address_space->i_mmap interval tree.
+	 *
+	 */
+	struct {
+		struct rb_node rb;
+		unsigned long rb_subtree_last;
+	} shared;
+#ifdef CONFIG_ANON_VMA_NAME
+	/*
+	 * For private and shared anonymous mappings, a pointer to a null
+	 * terminated string containing the name given to the vma, or NULL if
+	 * unnamed. Serialized by mmap_lock. Use anon_vma_name to access.
+	 */
+	struct anon_vma_name *anon_name;
+#endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+#ifdef __HAVE_PFNMAP_TRACKING
+	struct pfnmap_track_ctx *pfnmap_track_ctx;
+#endif
 } __randomize_layout;
 
-#ifdef CONFIG_SCHED_MM_CID
-struct mm_cid {
-	u64 time;
-	int cid;
-};
+/* Clears all bits in the VMA flags bitmap, non-atomically. */
+static inline void vma_flags_clear_all(vma_flags_t *flags)
+{
+	bitmap_zero(ACCESS_PRIVATE(flags, __vma_flags), NUM_VMA_FLAG_BITS);
+}
+
+/*
+ * Copy value to the first system word of VMA flags, non-atomically.
+ *
+ * IMPORTANT: This does not overwrite bytes past the first system word. The
+ * caller must account for this.
+ */
+static inline void vma_flags_overwrite_word(vma_flags_t *flags, unsigned long value)
+{
+	*ACCESS_PRIVATE(flags, __vma_flags) = value;
+}
+
+/*
+ * Copy value to the first system word of VMA flags ONCE, non-atomically.
+ *
+ * IMPORTANT: This does not overwrite bytes past the first system word. The
+ * caller must account for this.
+ */
+static inline void vma_flags_overwrite_word_once(vma_flags_t *flags, unsigned long value)
+{
+	unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+	WRITE_ONCE(*bitmap, value);
+}
+
+/* Update the first system word of VMA flags setting bits, non-atomically. */
+static inline void vma_flags_set_word(vma_flags_t *flags, unsigned long value)
+{
+	unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+	*bitmap |= value;
+}
+
+/* Update the first system word of VMA flags clearing bits, non-atomically. */
+static inline void vma_flags_clear_word(vma_flags_t *flags, unsigned long value)
+{
+	unsigned long *bitmap = ACCESS_PRIVATE(flags, __vma_flags);
+
+	*bitmap &= ~value;
+}
+
+#ifdef CONFIG_NUMA
+#define vma_policy(vma) ((vma)->vm_policy)
+#else
+#define vma_policy(vma) NULL
 #endif
 
+/*
+ * Opaque type representing current mm_struct flag state. Must be accessed via
+ * mm_flags_xxx() helper functions.
+ */
+#define NUM_MM_FLAG_BITS (64)
+typedef struct {
+	DECLARE_BITMAP(__mm_flags, NUM_MM_FLAG_BITS);
+} __private mm_flags_t;
+
 struct kioctx_table;
+struct iommu_mm_data;
 struct mm_struct {
 	struct {
+		/*
+		 * Fields which are often written to are placed in a separate
+		 * cache line.
+		 */
+		struct {
+			/**
+			 * @mm_count: The number of references to &struct
+			 * mm_struct (@mm_users count as 1).
+			 *
+			 * Use mmgrab()/mmdrop() to modify. When this drops to
+			 * 0, the &struct mm_struct is freed.
+			 */
+			atomic_t mm_count;
+		} ____cacheline_aligned_in_smp;
+
 		struct maple_tree mm_mt;
-#ifdef CONFIG_MMU
-		unsigned long (*get_unmapped_area) (struct file *filp,
-				unsigned long addr, unsigned long len,
-				unsigned long pgoff, unsigned long flags);
-#endif
+
 		unsigned long mmap_base;	/* base of mmap area */
 		unsigned long mmap_legacy_base;	/* base of mmap area in bottom-up allocations */
 #ifdef CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES
@@ -620,30 +1122,9 @@ struct mm_struct {
 		 */
 		atomic_t mm_users;
 
-		/**
-		 * @mm_count: The number of references to &struct mm_struct
-		 * (@mm_users count as 1).
-		 *
-		 * Use mmgrab()/mmdrop() to modify. When this drops to 0, the
-		 * &struct mm_struct is freed.
-		 */
-		atomic_t mm_count;
-#ifdef CONFIG_SCHED_MM_CID
-		/**
-		 * @pcpu_cid: Per-cpu current cid.
-		 *
-		 * Keep track of the currently allocated mm_cid for each cpu.
-		 * The per-cpu mm_cid values are serialized by their respective
-		 * runqueue locks.
-		 */
-		struct mm_cid __percpu *pcpu_cid;
-		/*
-		 * @mm_cid_next_scan: Next mm_cid scan (in jiffies).
-		 *
-		 * When the next mm_cid scan is due (in jiffies).
-		 */
-		unsigned long mm_cid_next_scan;
-#endif
+		/* MM CID related storage */
+		struct mm_mm_cid mm_cid;
+
 #ifdef CONFIG_MMU
 		atomic_long_t pgtables_bytes;	/* size of all page tables */
 #endif
@@ -653,10 +1134,10 @@ struct mm_struct {
 					     * counters
 					     */
 		/*
-		 * With some kernel config, the current mmap_lock's offset
-		 * inside 'mm_struct' is at 0x120, which is very optimal, as
+		 * Typically the current mmap_lock's offset is 56 bytes from
+		 * the last cacheline boundary, which is very optimal, as
 		 * its two hot fields 'count' and 'owner' sit in 2 different
-		 * cachelines,  and when mmap_lock is highly contended, both
+		 * cachelines, and when mmap_lock is highly contended, both
 		 * of the 2 fields will be accessed frequently, current layout
 		 * will help to reduce cache bouncing.
 		 *
@@ -672,9 +1153,36 @@ struct mm_struct {
 					  * by mmlist_lock
 					  */
 #ifdef CONFIG_PER_VMA_LOCK
-		int mm_lock_seq;
+		struct rcuwait vma_writer_wait;
+		/*
+		 * This field has lock-like semantics, meaning it is sometimes
+		 * accessed with ACQUIRE/RELEASE semantics.
+		 * Roughly speaking, incrementing the sequence number is
+		 * equivalent to releasing locks on VMAs; reading the sequence
+		 * number can be part of taking a read lock on a VMA.
+		 * Incremented every time mmap_lock is write-locked/unlocked.
+		 * Initialized to 0, therefore odd values indicate mmap_lock
+		 * is write-locked and even values that it's released.
+		 *
+		 * Can be modified under write mmap_lock using RELEASE
+		 * semantics.
+		 * Can be read with no other protection when holding write
+		 * mmap_lock.
+		 * Can be read with ACQUIRE semantics if not holding write
+		 * mmap_lock.
+		 */
+		seqcount_t mm_lock_seq;
+#endif
+#ifdef CONFIG_FUTEX_PRIVATE_HASH
+		struct mutex			futex_hash_lock;
+		struct futex_private_hash	__rcu *futex_phash;
+		struct futex_private_hash	*futex_phash_new;
+		/* futex-ref */
+		unsigned long			futex_batches;
+		struct rcu_head			futex_rcu;
+		atomic_long_t			futex_atomic;
+		unsigned int			__percpu *futex_ref;
 #endif
-
 
 		unsigned long hiwater_rss; /* High-watermark of RSS usage */
 		unsigned long hiwater_vm;  /* High-water virtual memory usage */
@@ -685,7 +1193,7 @@ struct mm_struct {
 		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
 		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
 		unsigned long stack_vm;	   /* VM_STACK */
-		unsigned long def_flags;
+		vm_flags_t def_flags;
 
 		/**
 		 * @write_protect_seq: Locked when any thread is write
@@ -702,6 +1210,11 @@ struct mm_struct {
 
 		unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
+#ifdef CONFIG_ARCH_HAS_ELF_CORE_EFLAGS
+		/* the ABI-related flags from the ELF header. Used for core dump */
+		unsigned long saved_e_flags;
+#endif
+
 		struct percpu_counter rss_stat[NR_MM_COUNTERS];
 
 		struct linux_binfmt *binfmt;
@@ -709,7 +1222,7 @@ struct mm_struct {
 		/* Architecture-specific MM context */
 		mm_context_t context;
 
-		unsigned long flags; /* Must use atomic bitops to access */
+		mm_flags_t flags; /* Must use mm_flags_* hlpers to access */
 
 #ifdef CONFIG_AIO
 		spinlock_t			ioctx_lock;
@@ -735,7 +1248,7 @@ struct mm_struct {
 #ifdef CONFIG_MMU_NOTIFIER
 		struct mmu_notifier_subscriptions *notifier_subscriptions;
 #endif
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !USE_SPLIT_PMD_PTLOCKS
+#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
 		pgtable_t pmd_huge_pte; /* protected by page_table_lock */
 #endif
 #ifdef CONFIG_NUMA_BALANCING
@@ -771,13 +1284,13 @@ struct mm_struct {
 #endif
 		struct work_struct async_put_work;
 
-#ifdef CONFIG_IOMMU_SVA
-		u32 pasid;
+#ifdef CONFIG_IOMMU_MM_DATA
+		struct iommu_mm_data *iommu_mm;
 #endif
 #ifdef CONFIG_KSM
 		/*
 		 * Represent how many pages of this process are involved in KSM
-		 * merging.
+		 * merging (not including ksm_zero_pages).
 		 */
 		unsigned long ksm_merging_pages;
 		/*
@@ -785,8 +1298,13 @@ struct mm_struct {
 		 * including merged and not merged.
 		 */
 		unsigned long ksm_rmap_items;
-#endif
-#ifdef CONFIG_LRU_GEN
+		/*
+		 * Represent how many empty pages are merged with kernel zero
+		 * pages when enabling KSM use_zero_pages.
+		 */
+		atomic_long_t ksm_zero_pages;
+#endif /* CONFIG_KSM */
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 		struct {
 			/* this mm_struct is on lru_gen_mm_list */
 			struct list_head list;
@@ -801,7 +1319,10 @@ struct mm_struct {
 			struct mem_cgroup *memcg;
 #endif
 		} lru_gen;
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
+#ifdef CONFIG_MM_ID
+		mm_id_t mm_id;
+#endif /* CONFIG_MM_ID */
 	} __randomize_layout;
 
 	/*
@@ -811,6 +1332,36 @@ struct mm_struct {
 	unsigned long cpu_bitmap[];
 };
 
+/* Copy value to the first system word of mm flags, non-atomically. */
+static inline void __mm_flags_overwrite_word(struct mm_struct *mm, unsigned long value)
+{
+	*ACCESS_PRIVATE(&mm->flags, __mm_flags) = value;
+}
+
+/* Obtain a read-only view of the mm flags bitmap. */
+static inline const unsigned long *__mm_flags_get_bitmap(const struct mm_struct *mm)
+{
+	return (const unsigned long *)ACCESS_PRIVATE(&mm->flags, __mm_flags);
+}
+
+/* Read the first system word of mm flags, non-atomically. */
+static inline unsigned long __mm_flags_get_word(const struct mm_struct *mm)
+{
+	return *__mm_flags_get_bitmap(mm);
+}
+
+/*
+ * Update the first system word of mm flags ONLY, applying the specified mask to
+ * it, then setting all flags specified by bits.
+ */
+static inline void __mm_flags_set_mask_bits_word(struct mm_struct *mm,
+		unsigned long mask, unsigned long bits)
+{
+	unsigned long *bitmap = ACCESS_PRIVATE(&mm->flags, __mm_flags);
+
+	set_mask_bits(bitmap, mask, bits);
+}
+
 #define MM_MT_FLAGS	(MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \
 			 MT_FLAGS_USE_RCU)
 extern struct mm_struct init_mm;
@@ -839,11 +1390,13 @@ struct lru_gen_mm_list {
 	spinlock_t lock;
 };
 
+#endif /* CONFIG_LRU_GEN */
+
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
+
 void lru_gen_add_mm(struct mm_struct *mm);
 void lru_gen_del_mm(struct mm_struct *mm);
-#ifdef CONFIG_MEMCG
 void lru_gen_migrate_mm(struct mm_struct *mm);
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -864,7 +1417,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 	WRITE_ONCE(mm->lru_gen.bitmap, -1);
 }
 
-#else /* !CONFIG_LRU_GEN */
+#else /* !CONFIG_LRU_GEN_WALKS_MMU */
 
 static inline void lru_gen_add_mm(struct mm_struct *mm)
 {
@@ -874,11 +1427,9 @@ static inline void lru_gen_del_mm(struct mm_struct *mm)
 {
 }
 
-#ifdef CONFIG_MEMCG
 static inline void lru_gen_migrate_mm(struct mm_struct *mm)
 {
 }
-#endif
 
 static inline void lru_gen_init_mm(struct mm_struct *mm)
 {
@@ -888,7 +1439,7 @@ static inline void lru_gen_use_mm(struct mm_struct *mm)
 {
 }
 
-#endif /* CONFIG_LRU_GEN */
+#endif /* CONFIG_LRU_GEN_WALKS_MMU */
 
 struct vma_iterator {
 	struct ma_state mas;
@@ -899,7 +1450,8 @@ struct vma_iterator {
 		.mas = {						\
 			.tree = &(__mm)->mm_mt,				\
 			.index = __addr,				\
-			.node = MAS_START,				\
+			.node = NULL,					\
+			.status = ma_start,				\
 		},							\
 	}
 
@@ -910,83 +1462,56 @@ static inline void vma_iter_init(struct vma_iterator *vmi,
 }
 
 #ifdef CONFIG_SCHED_MM_CID
-
-enum mm_cid_state {
-	MM_CID_UNSET = -1U,		/* Unset state has lazy_put flag set. */
-	MM_CID_LAZY_PUT = (1U << 31),
-};
-
-static inline bool mm_cid_is_unset(int cid)
-{
-	return cid == MM_CID_UNSET;
-}
-
-static inline bool mm_cid_is_lazy_put(int cid)
-{
-	return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT);
-}
-
-static inline bool mm_cid_is_valid(int cid)
-{
-	return !(cid & MM_CID_LAZY_PUT);
-}
-
-static inline int mm_cid_set_lazy_put(int cid)
+/*
+ * mm_cpus_allowed: Union of all mm's threads allowed CPUs.
+ */
+static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm)
 {
-	return cid | MM_CID_LAZY_PUT;
-}
+	unsigned long bitmap = (unsigned long)mm;
 
-static inline int mm_cid_clear_lazy_put(int cid)
-{
-	return cid & ~MM_CID_LAZY_PUT;
+	bitmap += offsetof(struct mm_struct, cpu_bitmap);
+	/* Skip cpu_bitmap */
+	bitmap += cpumask_size();
+	return (struct cpumask *)bitmap;
 }
 
 /* Accessor for struct mm_struct's cidmask. */
-static inline cpumask_t *mm_cidmask(struct mm_struct *mm)
+static inline unsigned long *mm_cidmask(struct mm_struct *mm)
 {
-	unsigned long cid_bitmap = (unsigned long)mm;
+	unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm);
 
-	cid_bitmap += offsetof(struct mm_struct, cpu_bitmap);
-	/* Skip cpu_bitmap */
+	/* Skip mm_cpus_allowed */
 	cid_bitmap += cpumask_size();
-	return (struct cpumask *)cid_bitmap;
+	return (unsigned long *)cid_bitmap;
 }
 
-static inline void mm_init_cid(struct mm_struct *mm)
-{
-	int i;
+void mm_init_cid(struct mm_struct *mm, struct task_struct *p);
 
-	for_each_possible_cpu(i) {
-		struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i);
-
-		pcpu_cid->cid = MM_CID_UNSET;
-		pcpu_cid->time = 0;
-	}
-	cpumask_clear(mm_cidmask(mm));
-}
-
-static inline int mm_alloc_cid(struct mm_struct *mm)
+static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p)
 {
-	mm->pcpu_cid = alloc_percpu(struct mm_cid);
-	if (!mm->pcpu_cid)
+	mm->mm_cid.pcpu = alloc_percpu_noprof(struct mm_cid_pcpu);
+	if (!mm->mm_cid.pcpu)
 		return -ENOMEM;
-	mm_init_cid(mm);
+	mm_init_cid(mm, p);
 	return 0;
 }
+#define mm_alloc_cid(...)	alloc_hooks(mm_alloc_cid_noprof(__VA_ARGS__))
 
 static inline void mm_destroy_cid(struct mm_struct *mm)
 {
-	free_percpu(mm->pcpu_cid);
-	mm->pcpu_cid = NULL;
+	free_percpu(mm->mm_cid.pcpu);
+	mm->mm_cid.pcpu = NULL;
 }
 
 static inline unsigned int mm_cid_size(void)
 {
-	return cpumask_size();
+	/* mm_cpus_allowed(), mm_cidmask(). */
+	return cpumask_size() + bitmap_size(num_possible_cpus());
 }
+
 #else /* CONFIG_SCHED_MM_CID */
-static inline void mm_init_cid(struct mm_struct *mm) { }
-static inline int mm_alloc_cid(struct mm_struct *mm) { return 0; }
+static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { }
+static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; }
 static inline void mm_destroy_cid(struct mm_struct *mm) { }
 static inline unsigned int mm_cid_size(void)
 {
@@ -1070,7 +1595,8 @@ enum vm_fault_reason {
 	{ VM_FAULT_RETRY,               "RETRY" },	\
 	{ VM_FAULT_FALLBACK,            "FALLBACK" },	\
 	{ VM_FAULT_DONE_COW,            "DONE_COW" },	\
-	{ VM_FAULT_NEEDDSYNC,           "NEEDDSYNC" }
+	{ VM_FAULT_NEEDDSYNC,           "NEEDDSYNC" },	\
+	{ VM_FAULT_COMPLETED,           "COMPLETED" }
 
 struct vm_special_mapping {
 	const char *name;	/* The name, e.g. "[vdso]". */
@@ -1093,6 +1619,9 @@ struct vm_special_mapping {
 
 	int (*mremap)(const struct vm_special_mapping *sm,
 		     struct vm_area_struct *new_vma);
+
+	void (*close)(const struct vm_special_mapping *sm,
+		      struct vm_area_struct *vma);
 };
 
 enum tlb_flush_reason {
@@ -1101,17 +1630,10 @@ enum tlb_flush_reason {
 	TLB_LOCAL_SHOOTDOWN,
 	TLB_LOCAL_MM_SHOOTDOWN,
 	TLB_REMOTE_SEND_IPI,
+	TLB_REMOTE_WRONG_CPU,
 	NR_TLB_FLUSH_REASONS,
 };
 
- /*
-  * A swap entry has to fit into a "unsigned long", as the entry is hidden
-  * in the "index" field of the swapper address space.
-  */
-typedef struct {
-	unsigned long val;
-} swp_entry_t;
-
 /**
  * enum fault_flag - Fault flag definitions.
  * @FAULT_FLAG_WRITE: Fault was a write fault.
@@ -1172,6 +1694,15 @@ enum fault_flag {
 
 typedef unsigned int __bitwise zap_flags_t;
 
+/* Flags for clear_young_dirty_ptes(). */
+typedef int __bitwise cydp_t;
+
+/* Clear the access bit */
+#define CYDP_CLEAR_YOUNG		((__force cydp_t)BIT(0))
+
+/* Clear the dirty bit */
+#define CYDP_CLEAR_DIRTY		((__force cydp_t)BIT(1))
+
 /*
  * FOLL_PIN and FOLL_LONGTERM may be used in various combinations with each
  * other. Here is what they mean, and how to use them:
@@ -1251,8 +1782,104 @@ enum {
 	FOLL_PCI_P2PDMA = 1 << 10,
 	/* allow interrupts from generic signals */
 	FOLL_INTERRUPTIBLE = 1 << 11,
+	/*
+	 * Always honor (trigger) NUMA hinting faults.
+	 *
+	 * FOLL_WRITE implicitly honors NUMA hinting faults because a
+	 * PROT_NONE-mapped page is not writable (exceptions with FOLL_FORCE
+	 * apply). get_user_pages_fast_only() always implicitly honors NUMA
+	 * hinting faults.
+	 */
+	FOLL_HONOR_NUMA_FAULT = 1 << 12,
 
 	/* See also internal only FOLL flags in mm/internal.h */
 };
 
+/* mm flags */
+
+/*
+ * The first two bits represent core dump modes for set-user-ID,
+ * the modes are SUID_DUMP_* defined in linux/sched/coredump.h
+ */
+#define MMF_DUMPABLE_BITS 2
+#define MMF_DUMPABLE_MASK (BIT(MMF_DUMPABLE_BITS) - 1)
+/* coredump filter bits */
+#define MMF_DUMP_ANON_PRIVATE	2
+#define MMF_DUMP_ANON_SHARED	3
+#define MMF_DUMP_MAPPED_PRIVATE	4
+#define MMF_DUMP_MAPPED_SHARED	5
+#define MMF_DUMP_ELF_HEADERS	6
+#define MMF_DUMP_HUGETLB_PRIVATE 7
+#define MMF_DUMP_HUGETLB_SHARED  8
+#define MMF_DUMP_DAX_PRIVATE	9
+#define MMF_DUMP_DAX_SHARED	10
+
+#define MMF_DUMP_FILTER_SHIFT	MMF_DUMPABLE_BITS
+#define MMF_DUMP_FILTER_BITS	9
+#define MMF_DUMP_FILTER_MASK \
+	((BIT(MMF_DUMP_FILTER_BITS) - 1) << MMF_DUMP_FILTER_SHIFT)
+#define MMF_DUMP_FILTER_DEFAULT \
+	(BIT(MMF_DUMP_ANON_PRIVATE) | BIT(MMF_DUMP_ANON_SHARED) | \
+	 BIT(MMF_DUMP_HUGETLB_PRIVATE) | MMF_DUMP_MASK_DEFAULT_ELF)
+
+#ifdef CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS
+# define MMF_DUMP_MASK_DEFAULT_ELF	BIT(MMF_DUMP_ELF_HEADERS)
+#else
+# define MMF_DUMP_MASK_DEFAULT_ELF	0
+#endif
+					/* leave room for more dump flags */
+#define MMF_VM_MERGEABLE	16	/* KSM may merge identical pages */
+#define MMF_VM_HUGEPAGE		17	/* set when mm is available for khugepaged */
+
+#define MMF_HUGE_ZERO_FOLIO	18      /* mm has ever used the global huge zero folio */
+
+#define MMF_HAS_UPROBES		19	/* has uprobes */
+#define MMF_RECALC_UPROBES	20	/* MMF_HAS_UPROBES can be wrong */
+#define MMF_OOM_SKIP		21	/* mm is of no interest for the OOM killer */
+#define MMF_UNSTABLE		22	/* mm is unstable for copy_from_user */
+#define MMF_DISABLE_THP_EXCEPT_ADVISED	23	/* no THP except when advised (e.g., VM_HUGEPAGE) */
+#define MMF_DISABLE_THP_COMPLETELY	24	/* no THP for all VMAs */
+#define MMF_DISABLE_THP_MASK	(BIT(MMF_DISABLE_THP_COMPLETELY) | \
+				 BIT(MMF_DISABLE_THP_EXCEPT_ADVISED))
+#define MMF_OOM_REAP_QUEUED	25	/* mm was queued for oom_reaper */
+#define MMF_MULTIPROCESS	26	/* mm is shared between processes */
+/*
+ * MMF_HAS_PINNED: Whether this mm has pinned any pages.  This can be either
+ * replaced in the future by mm.pinned_vm when it becomes stable, or grow into
+ * a counter on its own. We're aggresive on this bit for now: even if the
+ * pinned pages were unpinned later on, we'll still keep this bit set for the
+ * lifecycle of this mm, just for simplicity.
+ */
+#define MMF_HAS_PINNED		27	/* FOLL_PIN has run, never cleared */
+
+#define MMF_HAS_MDWE		28
+#define MMF_HAS_MDWE_MASK	BIT(MMF_HAS_MDWE)
+
+#define MMF_HAS_MDWE_NO_INHERIT	29
+
+#define MMF_VM_MERGE_ANY	30
+#define MMF_VM_MERGE_ANY_MASK	BIT(MMF_VM_MERGE_ANY)
+
+#define MMF_TOPDOWN		31	/* mm searches top down by default */
+#define MMF_TOPDOWN_MASK	BIT(MMF_TOPDOWN)
+
+#define MMF_INIT_LEGACY_MASK	(MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK |\
+				 MMF_DISABLE_THP_MASK | MMF_HAS_MDWE_MASK |\
+				 MMF_VM_MERGE_ANY_MASK | MMF_TOPDOWN_MASK)
+
+/* Legacy flags must fit within 32 bits. */
+static_assert((u64)MMF_INIT_LEGACY_MASK <= (u64)UINT_MAX);
+
+/*
+ * Initialise legacy flags according to masks, propagating selected flags on
+ * fork. Further flag manipulation can be performed by the caller.
+ */
+static inline unsigned long mmf_init_legacy_flags(unsigned long flags)
+{
+	if (flags & (1UL << MMF_HAS_MDWE_NO_INHERIT))
+		flags &= ~((1UL << MMF_HAS_MDWE) |
+			   (1UL << MMF_HAS_MDWE_NO_INHERIT));
+	return flags & MMF_INIT_LEGACY_MASK;
+}
+
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 5414b5c6a103..a82aa80c0ba4 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -8,10 +8,8 @@
  * (These are defined separately to decouple sched.h from mm_types.h as much as possible.)
  */
 
+#include <linux/align.h>
 #include <linux/types.h>
-#include <linux/threads.h>
-#include <linux/atomic.h>
-#include <linux/cpumask.h>
 
 #include <asm/page.h>
 
@@ -19,9 +17,6 @@
 #include <asm/tlbbatch.h>
 #endif
 
-#define USE_SPLIT_PTE_PTLOCKS	(NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS)
-#define USE_SPLIT_PMD_PTLOCKS	(USE_SPLIT_PTE_PTLOCKS && \
-		IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK))
 #define ALLOC_SPLIT_PTLOCKS	(SPINLOCK_SIZE > BITS_PER_LONG/8)
 
 /*
@@ -36,6 +31,8 @@ enum {
 	NR_MM_COUNTERS
 };
 
+struct page;
+
 struct page_frag {
 	struct page *page;
 #if (BITS_PER_LONG > 32) || (PAGE_SIZE >= 65536)
@@ -47,13 +44,33 @@ struct page_frag {
 #endif
 };
 
+#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
+#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
+struct page_frag_cache {
+	/* encoded_page consists of the virtual address, pfmemalloc bit and
+	 * order of a page.
+	 */
+	unsigned long encoded_page;
+
+	/* we maintain a pagecount bias, so that we dont dirty cache line
+	 * containing page->_refcount every time we allocate a fragment.
+	 */
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32)
+	__u16 offset;
+	__u16 pagecnt_bias;
+#else
+	__u32 offset;
+	__u32 pagecnt_bias;
+#endif
+};
+
 /* Track pages that require TLB flushes */
 struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
 	/*
 	 * The arch code makes the following promise: generic code can modify a
-	 * PTE, then call arch_tlbbatch_add_mm() (which internally provides all
-	 * needed barriers), then call arch_tlbbatch_flush(), and the entries
+	 * PTE, then call arch_tlbbatch_add_pending() (which internally provides
+	 * all needed barriers), then call arch_tlbbatch_flush(), and the entries
 	 * will be flushed on all CPUs by the time that arch_tlbbatch_flush()
 	 * returns.
 	 */
diff --git a/include/linux/mman.h b/include/linux/mman.h
index cee1e4b566d8..0ba8a7e8b90a 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_MMAN_H
 #define _LINUX_MMAN_H
 
+#include <linux/fs.h>
 #include <linux/mm.h>
 #include <linux/percpu_counter.h>
 
@@ -15,6 +16,9 @@
 #ifndef MAP_32BIT
 #define MAP_32BIT 0
 #endif
+#ifndef MAP_ABOVE4G
+#define MAP_ABOVE4G 0
+#endif
 #ifndef MAP_HUGE_2MB
 #define MAP_HUGE_2MB 0
 #endif
@@ -50,12 +54,11 @@
 		| MAP_STACK \
 		| MAP_HUGETLB \
 		| MAP_32BIT \
+		| MAP_ABOVE4G \
 		| MAP_HUGE_2MB \
 		| MAP_HUGE_1GB)
 
 extern int sysctl_overcommit_memory;
-extern int sysctl_overcommit_ratio;
-extern unsigned long sysctl_overcommit_kbytes;
 extern struct percpu_counter vm_committed_as;
 
 #ifdef CONFIG_SMP
@@ -90,7 +93,7 @@ static inline void vm_unacct_memory(long pages)
 #endif
 
 #ifndef arch_calc_vm_flag_bits
-#define arch_calc_vm_flag_bits(flags) 0
+#define arch_calc_vm_flag_bits(file, flags) 0
 #endif
 
 #ifndef arch_validate_prot
@@ -134,7 +137,7 @@ static inline bool arch_validate_flags(unsigned long flags)
 /*
  * Combine the mmap "prot" argument into "vm_flags" used internally.
  */
-static inline unsigned long
+static inline vm_flags_t
 calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
 {
 	return _calc_vm_trans(prot, PROT_READ,  VM_READ ) |
@@ -146,17 +149,28 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
 /*
  * Combine the mmap "flags" argument into "vm_flags" used internally.
  */
-static inline unsigned long
-calc_vm_flag_bits(unsigned long flags)
+static inline vm_flags_t
+calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
 	       _calc_vm_trans(flags, MAP_LOCKED,     VM_LOCKED    ) |
 	       _calc_vm_trans(flags, MAP_SYNC,	     VM_SYNC      ) |
-	       arch_calc_vm_flag_bits(flags);
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	       _calc_vm_trans(flags, MAP_STACK,	     VM_NOHUGEPAGE) |
+#endif
+	       arch_calc_vm_flag_bits(file, flags);
 }
 
 unsigned long vm_commit_limit(void);
 
+#ifndef arch_memory_deny_write_exec_supported
+static inline bool arch_memory_deny_write_exec_supported(void)
+{
+	return true;
+}
+#define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported
+#endif
+
 /*
  * Denies creating a writable executable mapping or gaining executable permissions.
  *
@@ -175,16 +189,31 @@ unsigned long vm_commit_limit(void);
  *
  *	d)	mmap(PROT_READ | PROT_EXEC)
  *		mmap(PROT_READ | PROT_EXEC | PROT_BTI)
+ *
+ * This is only applicable if the user has set the Memory-Deny-Write-Execute
+ * (MDWE) protection mask for the current process.
+ *
+ * @old specifies the VMA flags the VMA originally possessed, and @new the ones
+ * we propose to set.
+ *
+ * Return: false if proposed change is OK, true if not ok and should be denied.
  */
-static inline bool map_deny_write_exec(struct vm_area_struct *vma,  unsigned long vm_flags)
+static inline bool map_deny_write_exec(unsigned long old, unsigned long new)
 {
-	if (!test_bit(MMF_HAS_MDWE, &current->mm->flags))
+	/* If MDWE is disabled, we have nothing to deny. */
+	if (!mm_flags_test(MMF_HAS_MDWE, current->mm))
+		return false;
+
+	/* If the new VMA is not executable, we have nothing to deny. */
+	if (!(new & VM_EXEC))
 		return false;
 
-	if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE))
+	/* Under MDWE we do not accept newly writably executable VMAs... */
+	if (new & VM_WRITE)
 		return true;
 
-	if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC))
+	/* ...nor previously non-executable VMAs becoming executable. */
+	if (!(old & VM_EXEC))
 		return true;
 
 	return false;
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index aab8f1b28d26..d53f72dba7fe 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -1,12 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_MMAP_LOCK_H
 #define _LINUX_MMAP_LOCK_H
 
+/* Avoid a dependency loop by declaring here. */
+extern int rcuwait_wake_up(struct rcuwait *w);
+
 #include <linux/lockdep.h>
 #include <linux/mm_types.h>
 #include <linux/mmdebug.h>
 #include <linux/rwsem.h>
 #include <linux/tracepoint-defs.h>
 #include <linux/types.h>
+#include <linux/cleanup.h>
+#include <linux/sched/mm.h>
 
 #define MMAP_LOCK_INITIALIZER(name) \
 	.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),
@@ -60,38 +66,274 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write)
 
 #endif /* CONFIG_TRACING */
 
-static inline void mmap_assert_locked(struct mm_struct *mm)
+static inline void mmap_assert_locked(const struct mm_struct *mm)
 {
-	lockdep_assert_held(&mm->mmap_lock);
-	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
+	rwsem_assert_held(&mm->mmap_lock);
 }
 
-static inline void mmap_assert_write_locked(struct mm_struct *mm)
+static inline void mmap_assert_write_locked(const struct mm_struct *mm)
 {
-	lockdep_assert_held_write(&mm->mmap_lock);
-	VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
+	rwsem_assert_held_write(&mm->mmap_lock);
 }
 
 #ifdef CONFIG_PER_VMA_LOCK
-static inline void vma_end_write_all(struct mm_struct *mm)
+
+static inline void mm_lock_seqcount_init(struct mm_struct *mm)
 {
-	mmap_assert_write_locked(mm);
-	/* No races during update due to exclusive mmap_lock being held */
-	WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+	seqcount_init(&mm->mm_lock_seq);
+}
+
+static inline void mm_lock_seqcount_begin(struct mm_struct *mm)
+{
+	do_raw_write_seqcount_begin(&mm->mm_lock_seq);
+}
+
+static inline void mm_lock_seqcount_end(struct mm_struct *mm)
+{
+	ASSERT_EXCLUSIVE_WRITER(mm->mm_lock_seq);
+	do_raw_write_seqcount_end(&mm->mm_lock_seq);
 }
-#else
-static inline void vma_end_write_all(struct mm_struct *mm) {}
+
+static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq)
+{
+	/*
+	 * Since mmap_lock is a sleeping lock, and waiting for it to become
+	 * unlocked is more or less equivalent with taking it ourselves, don't
+	 * bother with the speculative path if mmap_lock is already write-locked
+	 * and take the slow path, which takes the lock.
+	 */
+	return raw_seqcount_try_begin(&mm->mm_lock_seq, *seq);
+}
+
+static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq)
+{
+	return read_seqcount_retry(&mm->mm_lock_seq, seq);
+}
+
+static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	static struct lock_class_key lockdep_key;
+
+	lockdep_init_map(&vma->vmlock_dep_map, "vm_lock", &lockdep_key, 0);
 #endif
+	if (reset_refcnt)
+		refcount_set(&vma->vm_refcnt, 0);
+	vma->vm_lock_seq = UINT_MAX;
+}
+
+static inline bool is_vma_writer_only(int refcnt)
+{
+	/*
+	 * With a writer and no readers, refcnt is VMA_LOCK_OFFSET if the vma
+	 * is detached and (VMA_LOCK_OFFSET + 1) if it is attached. Waiting on
+	 * a detached vma happens only in vma_mark_detached() and is a rare
+	 * case, therefore most of the time there will be no unnecessary wakeup.
+	 */
+	return (refcnt & VMA_LOCK_OFFSET) && refcnt <= VMA_LOCK_OFFSET + 1;
+}
+
+static inline void vma_refcount_put(struct vm_area_struct *vma)
+{
+	/* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
+	struct mm_struct *mm = vma->vm_mm;
+	int oldcnt;
+
+	rwsem_release(&vma->vmlock_dep_map, _RET_IP_);
+	if (!__refcount_dec_and_test(&vma->vm_refcnt, &oldcnt)) {
+
+		if (is_vma_writer_only(oldcnt - 1))
+			rcuwait_wake_up(&mm->vma_writer_wait);
+	}
+}
+
+/*
+ * Use only while holding mmap read lock which guarantees that locking will not
+ * fail (nobody can concurrently write-lock the vma). vma_start_read() should
+ * not be used in such cases because it might fail due to mm_lock_seq overflow.
+ * This functionality is used to obtain vma read lock and drop the mmap read lock.
+ */
+static inline bool vma_start_read_locked_nested(struct vm_area_struct *vma, int subclass)
+{
+	int oldcnt;
+
+	mmap_assert_locked(vma->vm_mm);
+	if (unlikely(!__refcount_inc_not_zero_limited_acquire(&vma->vm_refcnt, &oldcnt,
+							      VMA_REF_LIMIT)))
+		return false;
+
+	rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
+	return true;
+}
+
+/*
+ * Use only while holding mmap read lock which guarantees that locking will not
+ * fail (nobody can concurrently write-lock the vma). vma_start_read() should
+ * not be used in such cases because it might fail due to mm_lock_seq overflow.
+ * This functionality is used to obtain vma read lock and drop the mmap read lock.
+ */
+static inline bool vma_start_read_locked(struct vm_area_struct *vma)
+{
+	return vma_start_read_locked_nested(vma, 0);
+}
+
+static inline void vma_end_read(struct vm_area_struct *vma)
+{
+	vma_refcount_put(vma);
+}
+
+/* WARNING! Can only be used if mmap_lock is expected to be write-locked */
+static inline bool __is_vma_write_locked(struct vm_area_struct *vma, unsigned int *mm_lock_seq)
+{
+	mmap_assert_write_locked(vma->vm_mm);
+
+	/*
+	 * current task is holding mmap_write_lock, both vma->vm_lock_seq and
+	 * mm->mm_lock_seq can't be concurrently modified.
+	 */
+	*mm_lock_seq = vma->vm_mm->mm_lock_seq.sequence;
+	return (vma->vm_lock_seq == *mm_lock_seq);
+}
+
+int __vma_start_write(struct vm_area_struct *vma, unsigned int mm_lock_seq,
+		int state);
+
+/*
+ * Begin writing to a VMA.
+ * Exclude concurrent readers under the per-VMA lock until the currently
+ * write-locked mmap_lock is dropped or downgraded.
+ */
+static inline void vma_start_write(struct vm_area_struct *vma)
+{
+	unsigned int mm_lock_seq;
 
-static inline void mmap_init_lock(struct mm_struct *mm)
+	if (__is_vma_write_locked(vma, &mm_lock_seq))
+		return;
+
+	__vma_start_write(vma, mm_lock_seq, TASK_UNINTERRUPTIBLE);
+}
+
+/**
+ * vma_start_write_killable - Begin writing to a VMA.
+ * @vma: The VMA we are going to modify.
+ *
+ * Exclude concurrent readers under the per-VMA lock until the currently
+ * write-locked mmap_lock is dropped or downgraded.
+ *
+ * Context: May sleep while waiting for readers to drop the vma read lock.
+ * Caller must already hold the mmap_lock for write.
+ *
+ * Return: 0 for a successful acquisition.  -EINTR if a fatal signal was
+ * received.
+ */
+static inline __must_check
+int vma_start_write_killable(struct vm_area_struct *vma)
+{
+	unsigned int mm_lock_seq;
+
+	if (__is_vma_write_locked(vma, &mm_lock_seq))
+		return 0;
+	return __vma_start_write(vma, mm_lock_seq, TASK_KILLABLE);
+}
+
+static inline void vma_assert_write_locked(struct vm_area_struct *vma)
+{
+	unsigned int mm_lock_seq;
+
+	VM_BUG_ON_VMA(!__is_vma_write_locked(vma, &mm_lock_seq), vma);
+}
+
+static inline void vma_assert_locked(struct vm_area_struct *vma)
 {
-	init_rwsem(&mm->mmap_lock);
+	unsigned int mm_lock_seq;
+
+	VM_BUG_ON_VMA(refcount_read(&vma->vm_refcnt) <= 1 &&
+		      !__is_vma_write_locked(vma, &mm_lock_seq), vma);
 }
 
+/*
+ * WARNING: to avoid racing with vma_mark_attached()/vma_mark_detached(), these
+ * assertions should be made either under mmap_write_lock or when the object
+ * has been isolated under mmap_write_lock, ensuring no competing writers.
+ */
+static inline void vma_assert_attached(struct vm_area_struct *vma)
+{
+	WARN_ON_ONCE(!refcount_read(&vma->vm_refcnt));
+}
+
+static inline void vma_assert_detached(struct vm_area_struct *vma)
+{
+	WARN_ON_ONCE(refcount_read(&vma->vm_refcnt));
+}
+
+static inline void vma_mark_attached(struct vm_area_struct *vma)
+{
+	vma_assert_write_locked(vma);
+	vma_assert_detached(vma);
+	refcount_set_release(&vma->vm_refcnt, 1);
+}
+
+void vma_mark_detached(struct vm_area_struct *vma);
+
+struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
+					  unsigned long address);
+
+/*
+ * Locks next vma pointed by the iterator. Confirms the locked vma has not
+ * been modified and will retry under mmap_lock protection if modification
+ * was detected. Should be called from read RCU section.
+ * Returns either a valid locked VMA, NULL if no more VMAs or -EINTR if the
+ * process was interrupted.
+ */
+struct vm_area_struct *lock_next_vma(struct mm_struct *mm,
+				     struct vma_iterator *iter,
+				     unsigned long address);
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline void mm_lock_seqcount_init(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_begin(struct mm_struct *mm) {}
+static inline void mm_lock_seqcount_end(struct mm_struct *mm) {}
+
+static inline bool mmap_lock_speculate_try_begin(struct mm_struct *mm, unsigned int *seq)
+{
+	return false;
+}
+
+static inline bool mmap_lock_speculate_retry(struct mm_struct *mm, unsigned int seq)
+{
+	return true;
+}
+static inline void vma_lock_init(struct vm_area_struct *vma, bool reset_refcnt) {}
+static inline void vma_end_read(struct vm_area_struct *vma) {}
+static inline void vma_start_write(struct vm_area_struct *vma) {}
+static inline __must_check
+int vma_start_write_killable(struct vm_area_struct *vma) { return 0; }
+static inline void vma_assert_write_locked(struct vm_area_struct *vma)
+		{ mmap_assert_write_locked(vma->vm_mm); }
+static inline void vma_assert_attached(struct vm_area_struct *vma) {}
+static inline void vma_assert_detached(struct vm_area_struct *vma) {}
+static inline void vma_mark_attached(struct vm_area_struct *vma) {}
+static inline void vma_mark_detached(struct vm_area_struct *vma) {}
+
+static inline struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
+		unsigned long address)
+{
+	return NULL;
+}
+
+static inline void vma_assert_locked(struct vm_area_struct *vma)
+{
+	mmap_assert_locked(vma->vm_mm);
+}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
 static inline void mmap_write_lock(struct mm_struct *mm)
 {
 	__mmap_lock_trace_start_locking(mm, true);
 	down_write(&mm->mmap_lock);
+	mm_lock_seqcount_begin(mm);
 	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
@@ -99,6 +341,7 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
 {
 	__mmap_lock_trace_start_locking(mm, true);
 	down_write_nested(&mm->mmap_lock, subclass);
+	mm_lock_seqcount_begin(mm);
 	__mmap_lock_trace_acquire_returned(mm, true, true);
 }
 
@@ -108,18 +351,24 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm)
 
 	__mmap_lock_trace_start_locking(mm, true);
 	ret = down_write_killable(&mm->mmap_lock);
+	if (!ret)
+		mm_lock_seqcount_begin(mm);
 	__mmap_lock_trace_acquire_returned(mm, true, ret == 0);
 	return ret;
 }
 
-static inline bool mmap_write_trylock(struct mm_struct *mm)
+/*
+ * Drop all currently-held per-VMA locks.
+ * This is called from the mmap_lock implementation directly before releasing
+ * a write-locked mmap_lock (or downgrading it to read-locked).
+ * This should normally NOT be called manually from other places.
+ * If you want to call this manually anyway, keep in mind that this will release
+ * *all* VMA write locks, including ones from further up the stack.
+ */
+static inline void vma_end_write_all(struct mm_struct *mm)
 {
-	bool ret;
-
-	__mmap_lock_trace_start_locking(mm, true);
-	ret = down_write_trylock(&mm->mmap_lock) != 0;
-	__mmap_lock_trace_acquire_returned(mm, true, ret);
-	return ret;
+	mmap_assert_write_locked(mm);
+	mm_lock_seqcount_end(mm);
 }
 
 static inline void mmap_write_unlock(struct mm_struct *mm)
@@ -169,6 +418,9 @@ static inline void mmap_read_unlock(struct mm_struct *mm)
 	up_read(&mm->mmap_lock);
 }
 
+DEFINE_GUARD(mmap_read_lock, struct mm_struct *,
+	     mmap_read_lock(_T), mmap_read_unlock(_T))
+
 static inline void mmap_read_unlock_non_owner(struct mm_struct *mm)
 {
 	__mmap_lock_trace_released(mm, false);
diff --git a/include/linux/mmc/card.h b/include/linux/mmc/card.h
index c726ea781255..e9e964c20e53 100644
--- a/include/linux/mmc/card.h
+++ b/include/linux/mmc/card.h
@@ -32,9 +32,10 @@ struct mmc_csd {
 	unsigned int		r2w_factor;
 	unsigned int		max_dtr;
 	unsigned int		erase_size;		/* In sectors */
+	unsigned int		wp_grp_size;
 	unsigned int		read_blkbits;
 	unsigned int		write_blkbits;
-	unsigned int		capacity;
+	sector_t		capacity;
 	unsigned int		read_partial:1,
 				read_misalign:1,
 				write_partial:1,
@@ -52,9 +53,6 @@ struct mmc_ext_csd {
 	u8			part_config;
 	u8			cache_ctrl;
 	u8			rst_n_function;
-	u8			max_packed_writes;
-	u8			max_packed_reads;
-	u8			packed_event_en;
 	unsigned int		part_time;		/* Units: ms */
 	unsigned int		sa_timeout;		/* Units: 100ns */
 	unsigned int		generic_cmd6_time;	/* Units: 10ms */
@@ -184,12 +182,17 @@ struct sd_switch_caps {
 #define SD_SET_CURRENT_LIMIT_400	1
 #define SD_SET_CURRENT_LIMIT_600	2
 #define SD_SET_CURRENT_LIMIT_800	3
-#define SD_SET_CURRENT_NO_CHANGE	(-1)
 
 #define SD_MAX_CURRENT_200	(1 << SD_SET_CURRENT_LIMIT_200)
 #define SD_MAX_CURRENT_400	(1 << SD_SET_CURRENT_LIMIT_400)
 #define SD_MAX_CURRENT_600	(1 << SD_SET_CURRENT_LIMIT_600)
 #define SD_MAX_CURRENT_800	(1 << SD_SET_CURRENT_LIMIT_800)
+
+#define SD4_SET_POWER_LIMIT_0_72W	0
+#define SD4_SET_POWER_LIMIT_1_44W	1
+#define SD4_SET_POWER_LIMIT_2_16W	2
+#define SD4_SET_POWER_LIMIT_2_88W	3
+#define SD4_SET_POWER_LIMIT_1_80W	4
 };
 
 struct sd_ext_reg {
@@ -211,6 +214,34 @@ struct sd_ext_reg {
 #define SD_EXT_PERF_CMD_QUEUE	(1<<4)
 };
 
+struct sd_uhs2_config {
+	u32			node_id;
+
+	u32			n_fcu;
+	u32			maxblk_len;
+	u8			n_lanes;
+	u8			dadr_len;
+	u8			app_type;
+	u8			phy_minor_rev;
+	u8			phy_major_rev;
+	u8			can_hibernate;
+	u8			n_lss_sync;
+	u8			n_lss_dir;
+	u8			link_minor_rev;
+	u8			link_major_rev;
+	u8			dev_type;
+	u8			n_data_gap;
+
+	u32			n_fcu_set;
+	u32			maxblk_len_set;
+	u8			n_lanes_set;
+	u8			speed_range_set;
+	u8			n_lss_sync_set;
+	u8			n_lss_dir_set;
+	u8			n_data_gap_set;
+	u8			max_retry_set;
+};
+
 struct sdio_cccr {
 	unsigned int		sdio_vsn;
 	unsigned int		sd_vsn;
@@ -294,7 +325,12 @@ struct mmc_card {
 #define MMC_QUIRK_TRIM_BROKEN	(1<<12)		/* Skip trim */
 #define MMC_QUIRK_BROKEN_HPI	(1<<13)		/* Disable broken HPI support */
 #define MMC_QUIRK_BROKEN_SD_DISCARD	(1<<14)	/* Disable broken SD discard support */
+#define MMC_QUIRK_BROKEN_SD_CACHE	(1<<15)	/* Disable broken SD cache support */
+#define MMC_QUIRK_BROKEN_CACHE_FLUSH	(1<<16)	/* Don't flush cache until the write has occurred */
+#define MMC_QUIRK_BROKEN_SD_POWEROFF_NOTIFY	(1<<17) /* Disable broken SD poweroff notify support */
+#define MMC_QUIRK_NO_UHS_DDR50_TUNING	(1<<18) /* Disable DDR50 tuning */
 
+	bool			written_flag;	/* Indicates eMMC has been written since power on */
 	bool			reenable_cmdq;	/* Re-enable Command Queue */
 
 	unsigned int		erase_size;	/* erase size in sectors */
@@ -303,6 +339,7 @@ struct mmc_card {
 	unsigned int		eg_boundary;	/* don't cross erase-group boundaries */
 	unsigned int		erase_arg;	/* erase / trim / discard */
  	u8			erased_byte;	/* value of erased bytes */
+	unsigned int		wp_grp_size;	/* write group size in sectors */
 
 	u32			raw_cid[4];	/* raw card CID */
 	u32			raw_csd[4];	/* raw card CSD */
@@ -317,6 +354,8 @@ struct mmc_card {
 	struct sd_ext_reg	ext_power;	/* SD extension reg for PM */
 	struct sd_ext_reg	ext_perf;	/* SD extension reg for PERF */
 
+	struct sd_uhs2_config	uhs2_config;	/* SD UHS-II config */
+
 	unsigned int		sdio_funcs;	/* number of SDIO functions */
 	atomic_t		sdio_funcs_probed; /* number of probed SDIO funcs */
 	struct sdio_cccr	cccr;		/* common card info */
diff --git a/include/linux/mmc/core.h b/include/linux/mmc/core.h
index 6efec0b9820c..01e0f591a20b 100644
--- a/include/linux/mmc/core.h
+++ b/include/linux/mmc/core.h
@@ -11,23 +11,24 @@
 struct mmc_data;
 struct mmc_request;
 
-enum mmc_blk_status {
-	MMC_BLK_SUCCESS = 0,
-	MMC_BLK_PARTIAL,
-	MMC_BLK_CMD_ERR,
-	MMC_BLK_RETRY,
-	MMC_BLK_ABORT,
-	MMC_BLK_DATA_ERR,
-	MMC_BLK_ECC_ERR,
-	MMC_BLK_NOMEDIUM,
-	MMC_BLK_NEW_REQUEST,
+#define UHS2_MAX_PAYLOAD_LEN 2
+#define UHS2_MAX_RESP_LEN 20
+
+struct uhs2_command {
+	u16	header;
+	u16	arg;
+	__be32	payload[UHS2_MAX_PAYLOAD_LEN];
+	u8	payload_len;
+	u8	packet_len;
+	u8	tmode_half_duplex;
+	u8	uhs2_resp[UHS2_MAX_RESP_LEN];	/* UHS2 native cmd resp */
+	u8	uhs2_resp_len;			/* UHS2 native cmd resp len */
 };
 
 struct mmc_command {
 	u32			opcode;
 	u32			arg;
 #define MMC_CMD23_ARG_REL_WR	(1 << 31)
-#define MMC_CMD23_ARG_PACKED	((0 << 31) | (1 << 30))
 #define MMC_CMD23_ARG_TAG_REQ	(1 << 29)
 	u32			resp[4];
 	unsigned int		flags;		/* expected response type */
@@ -56,6 +57,7 @@ struct mmc_command {
 #define MMC_RSP_NONE	(0)
 #define MMC_RSP_R1	(MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE)
 #define MMC_RSP_R1B	(MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE|MMC_RSP_BUSY)
+#define MMC_RSP_R1B_NO_CRC (MMC_RSP_PRESENT|MMC_RSP_OPCODE|MMC_RSP_BUSY)
 #define MMC_RSP_R2	(MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC)
 #define MMC_RSP_R3	(MMC_RSP_PRESENT)
 #define MMC_RSP_R4	(MMC_RSP_PRESENT)
@@ -63,9 +65,6 @@ struct mmc_command {
 #define MMC_RSP_R6	(MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE)
 #define MMC_RSP_R7	(MMC_RSP_PRESENT|MMC_RSP_CRC|MMC_RSP_OPCODE)
 
-/* Can be used by core to poll after switch to MMC HS mode */
-#define MMC_RSP_R1_NO_CRC	(MMC_RSP_PRESENT|MMC_RSP_OPCODE)
-
 #define mmc_resp_type(cmd)	((cmd)->flags & (MMC_RSP_PRESENT|MMC_RSP_136|MMC_RSP_CRC|MMC_RSP_BUSY|MMC_RSP_OPCODE))
 
 /*
@@ -109,6 +108,12 @@ struct mmc_command {
 	unsigned int		busy_timeout;	/* busy detect timeout in ms */
 	struct mmc_data		*data;		/* data segment associated with cmd */
 	struct mmc_request	*mrq;		/* associated request */
+
+	struct uhs2_command	*uhs2_cmd;	/* UHS2 command */
+
+	/* for SDUC */
+	bool has_ext_addr;
+	u8 ext_addr;
 };
 
 struct mmc_data {
@@ -167,6 +172,7 @@ struct mmc_request {
 	const struct bio_crypt_ctx *crypto_ctx;
 	int			crypto_key_slot;
 #endif
+	struct uhs2_command	uhs2_cmd;
 };
 
 struct mmc_card;
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 461d1543893b..e0e2c265e5d1 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -10,12 +10,14 @@
 #include <linux/sched.h>
 #include <linux/device.h>
 #include <linux/fault-inject.h>
+#include <linux/debugfs.h>
 
 #include <linux/mmc/core.h>
 #include <linux/mmc/card.h>
 #include <linux/mmc/pm.h>
 #include <linux/dma-direction.h>
 #include <linux/blk-crypto-profile.h>
+#include <linux/mmc/sd_uhs2.h>
 
 struct mmc_ios {
 	unsigned int	clock;			/* clock rate */
@@ -63,6 +65,10 @@ struct mmc_ios {
 #define MMC_TIMING_MMC_HS400	10
 #define MMC_TIMING_SD_EXP	11
 #define MMC_TIMING_SD_EXP_1_2V	12
+#define MMC_TIMING_UHS2_SPEED_A    13
+#define MMC_TIMING_UHS2_SPEED_A_HD 14
+#define MMC_TIMING_UHS2_SPEED_B    15
+#define MMC_TIMING_UHS2_SPEED_B_HD 16
 
 	unsigned char	signal_voltage;		/* signalling voltage (1.8V or 3.3V) */
 
@@ -70,6 +76,9 @@ struct mmc_ios {
 #define MMC_SIGNAL_VOLTAGE_180	1
 #define MMC_SIGNAL_VOLTAGE_120	2
 
+	unsigned char	vqmmc2_voltage;
+#define MMC_VQMMC2_VOLTAGE_180	0
+
 	unsigned char	drv_type;		/* driver type (A, B, C, D) */
 
 #define MMC_SET_DRIVER_TYPE_B	0
@@ -91,6 +100,43 @@ struct mmc_clk_phase_map {
 	struct mmc_clk_phase phase[MMC_NUM_CLK_PHASES];
 };
 
+struct sd_uhs2_caps {
+	u32	dap;
+	u32	gap;
+	u32	group_desc;
+	u32	maxblk_len;
+	u32	n_fcu;
+	u8	n_lanes;
+	u8	addr64;
+	u8	card_type;
+	u8	phy_rev;
+	u8	speed_range;
+	u8	n_lss_sync;
+	u8	n_lss_dir;
+	u8	link_rev;
+	u8	host_type;
+	u8	n_data_gap;
+
+	u32	maxblk_len_set;
+	u32	n_fcu_set;
+	u8	n_lanes_set;
+	u8	n_lss_sync_set;
+	u8	n_lss_dir_set;
+	u8	n_data_gap_set;
+	u8	max_retry_set;
+};
+
+enum sd_uhs2_operation {
+	UHS2_PHY_INIT = 0,
+	UHS2_SET_CONFIG,
+	UHS2_ENABLE_INT,
+	UHS2_DISABLE_INT,
+	UHS2_ENABLE_CLK,
+	UHS2_DISABLE_CLK,
+	UHS2_CHECK_DORMANT,
+	UHS2_SET_IOS,
+};
+
 struct mmc_host;
 
 enum mmc_err_stat {
@@ -184,6 +230,12 @@ struct mmc_host_ops {
 	/* Execute HS400 tuning depending host driver */
 	int	(*execute_hs400_tuning)(struct mmc_host *host, struct mmc_card *card);
 
+	/* Optional callback to prepare for SD high-speed tuning */
+	int	(*prepare_sd_hs_tuning)(struct mmc_host *host, struct mmc_card *card);
+
+	/* Optional callback to execute SD high-speed tuning */
+	int	(*execute_sd_hs_tuning)(struct mmc_host *host, struct mmc_card *card);
+
 	/* Prepare switch to DDR during the HS400 init sequence */
 	int	(*hs400_prepare_ddr)(struct mmc_host *host);
 
@@ -212,6 +264,14 @@ struct mmc_host_ops {
 
 	/* Initialize an SD express card, mandatory for MMC_CAP2_SD_EXP. */
 	int	(*init_sd_express)(struct mmc_host *host, struct mmc_ios *ios);
+
+	/*
+	 * The uhs2_control callback is used to execute SD UHS-II specific
+	 * operations. It's mandatory to implement for hosts that supports the
+	 * SD UHS-II interface (MMC_CAP2_SD_UHS2). Expected return values are a
+	 * negative errno in case of a failure or zero for success.
+	 */
+	int	(*uhs2_control)(struct mmc_host *host, enum sd_uhs2_operation op);
 };
 
 struct mmc_cqe_ops {
@@ -258,16 +318,6 @@ struct mmc_cqe_ops {
 	void	(*cqe_recovery_finish)(struct mmc_host *host);
 };
 
-struct mmc_async_req {
-	/* active mmc request */
-	struct mmc_request	*mrq;
-	/*
-	 * Check error status of completed mmc request.
-	 * Returns 0 if success otherwise non zero.
-	 */
-	enum mmc_blk_status (*err_check)(struct mmc_card *, struct mmc_async_req *);
-};
-
 /**
  * struct mmc_slot - MMC slot functions
  *
@@ -285,26 +335,17 @@ struct mmc_slot {
 	void *handler_priv;
 };
 
-/**
- * mmc_context_info - synchronization details for mmc context
- * @is_done_rcv		wake up reason was done request
- * @is_new_req		wake up reason was new request
- * @is_waiting_last_req	mmc context waiting for single running request
- * @wait		wait queue
- */
-struct mmc_context_info {
-	bool			is_done_rcv;
-	bool			is_new_req;
-	bool			is_waiting_last_req;
-	wait_queue_head_t	wait;
-};
-
 struct regulator;
 struct mmc_pwrseq;
+struct notifier_block;
 
 struct mmc_supply {
 	struct regulator *vmmc;		/* Card power supply */
 	struct regulator *vqmmc;	/* Optional Vccq supply */
+	struct regulator *vqmmc2;	/* Optional supply for phy */
+
+	struct notifier_block vmmc_nb;	/* Notifier for vmmc */
+	struct work_struct uv_work;	/* Undervoltage work */
 };
 
 struct mmc_ctx {
@@ -396,6 +437,7 @@ struct mmc_host {
 				 MMC_CAP2_HS200_1_2V_SDR)
 #define MMC_CAP2_SD_EXP		(1 << 7)	/* SD express via PCIe */
 #define MMC_CAP2_SD_EXP_1_2V	(1 << 8)	/* SD express 1.2V */
+#define MMC_CAP2_SD_UHS2	(1 << 9)	/* SD UHS-II support */
 #define MMC_CAP2_CD_ACTIVE_HIGH	(1 << 10)	/* Card-detect signal active high */
 #define MMC_CAP2_RO_ACTIVE_HIGH	(1 << 11)	/* Write-protect signal active high */
 #define MMC_CAP2_NO_PRESCAN_POWERUP (1 << 14)	/* Don't power up before scan */
@@ -422,13 +464,17 @@ struct mmc_host {
 #endif
 #define MMC_CAP2_ALT_GPT_TEGRA	(1 << 28)	/* Host with eMMC that has GPT entry at a non-standard location */
 
+	bool			uhs2_sd_tran;	/* UHS-II flag for SD_TRAN state */
+	bool			uhs2_app_cmd;	/* UHS-II flag for APP command */
+	struct sd_uhs2_caps	uhs2_caps;	/* Host UHS-II capabilities */
+
 	int			fixed_drv_type;	/* fixed driver type for non-removable media */
 
 	mmc_pm_flag_t		pm_caps;	/* supported pm features */
 
 	/* host specific block data */
-	unsigned int		max_seg_size;	/* see blk_queue_max_segment_size */
-	unsigned short		max_segs;	/* see blk_queue_max_segments */
+	unsigned int		max_seg_size;	/* lim->max_segment_size */
+	unsigned short		max_segs;	/* lim->max_segments */
 	unsigned short		unused;
 	unsigned int		max_req_size;	/* maximum number of bytes in one req */
 	unsigned int		max_blk_size;	/* maximum size of one mmc block */
@@ -452,6 +498,13 @@ struct mmc_host {
 	unsigned int		can_dma_map_merge:1; /* merging can be used */
 	unsigned int		vqmmc_enabled:1; /* vqmmc regulator is enabled */
 
+	/*
+	 * Indicates if an undervoltage event has already been handled.
+	 * This prevents repeated regulator notifiers from triggering
+	 * multiple REGULATOR_EVENT_UNDER_VOLTAGE events.
+	 */
+	unsigned int		undervoltage:1;	 /* Undervoltage state */
+
 	int			rescan_disable;	/* disable card detection */
 	int			rescan_entered;	/* used with nonremovable devices */
 
@@ -520,8 +573,10 @@ struct mmc_host {
 
 	/* Host Software Queue support */
 	bool			hsq_enabled;
+	int			hsq_depth;
 
 	u32			err_stats[MMC_ERR_MAX];
+	u32			max_sd_hs_hz;
 	unsigned long		private[] ____cacheline_aligned;
 };
 
@@ -532,7 +587,7 @@ struct mmc_host *devm_mmc_alloc_host(struct device *dev, int extra);
 int mmc_add_host(struct mmc_host *);
 void mmc_remove_host(struct mmc_host *);
 void mmc_free_host(struct mmc_host *);
-void mmc_of_parse_clk_phase(struct mmc_host *host,
+void mmc_of_parse_clk_phase(struct device *dev,
 			    struct mmc_clk_phase_map *map);
 int mmc_of_parse(struct mmc_host *host);
 int mmc_of_parse_voltage(struct mmc_host *host, u32 *mask);
@@ -547,6 +602,14 @@ static inline struct mmc_host *mmc_from_priv(void *priv)
 	return container_of(priv, struct mmc_host, private);
 }
 
+#ifdef CONFIG_MMC_CRYPTO
+static inline struct mmc_host *
+mmc_from_crypto_profile(struct blk_crypto_profile *profile)
+{
+	return container_of(profile, struct mmc_host, crypto_profile);
+}
+#endif
+
 #define mmc_host_is_spi(host)	((host)->caps & MMC_CAP_SPI)
 
 #define mmc_dev(x)	((x)->parent)
@@ -583,6 +646,7 @@ int mmc_regulator_set_ocr(struct mmc_host *mmc,
 			struct regulator *supply,
 			unsigned short vdd_bit);
 int mmc_regulator_set_vqmmc(struct mmc_host *mmc, struct mmc_ios *ios);
+int mmc_regulator_set_vqmmc2(struct mmc_host *mmc, struct mmc_ios *ios);
 #else
 static inline int mmc_regulator_set_ocr(struct mmc_host *mmc,
 				 struct regulator *supply,
@@ -596,6 +660,12 @@ static inline int mmc_regulator_set_vqmmc(struct mmc_host *mmc,
 {
 	return -EINVAL;
 }
+
+static inline int mmc_regulator_set_vqmmc2(struct mmc_host *mmc,
+					   struct mmc_ios *ios)
+{
+	return -EINVAL;
+}
 #endif
 
 int mmc_regulator_get_supply(struct mmc_host *mmc);
@@ -631,6 +701,14 @@ static inline int mmc_card_uhs(struct mmc_card *card)
 		card->host->ios.timing <= MMC_TIMING_UHS_DDR50;
 }
 
+static inline bool mmc_card_uhs2(struct mmc_host *host)
+{
+	return host->ios.timing == MMC_TIMING_UHS2_SPEED_A ||
+	       host->ios.timing == MMC_TIMING_UHS2_SPEED_A_HD ||
+	       host->ios.timing == MMC_TIMING_UHS2_SPEED_B ||
+	       host->ios.timing == MMC_TIMING_UHS2_SPEED_B_HD;
+}
+
 void mmc_retune_timer_stop(struct mmc_host *host);
 
 static inline void mmc_retune_needed(struct mmc_host *host)
@@ -665,8 +743,18 @@ static inline void mmc_debugfs_err_stats_inc(struct mmc_host *host,
 	host->err_stats[stat] += 1;
 }
 
+static inline int mmc_card_uhs2_hd_mode(struct mmc_host *host)
+{
+	return host->ios.timing == MMC_TIMING_UHS2_SPEED_A_HD ||
+	       host->ios.timing == MMC_TIMING_UHS2_SPEED_B_HD;
+}
+
+int mmc_sd_switch(struct mmc_card *card, bool mode, int group,
+		u8 value, u8 *resp);
+int mmc_send_status(struct mmc_card *card, u32 *status);
 int mmc_send_tuning(struct mmc_host *host, u32 opcode, int *cmd_error);
 int mmc_send_abort_tuning(struct mmc_host *host, u32 opcode);
 int mmc_get_ext_csd(struct mmc_card *card, u8 **new_ext_csd);
+int mmc_read_tuning(struct mmc_host *host, unsigned int blksz, unsigned int blocks);
 
 #endif /* LINUX_MMC_HOST_H */
diff --git a/include/linux/mmc/mmc.h b/include/linux/mmc/mmc.h
index 6f7993803ee7..cf2bcb5da30d 100644
--- a/include/linux/mmc/mmc.h
+++ b/include/linux/mmc/mmc.h
@@ -257,8 +257,6 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_FLUSH_CACHE		32      /* W */
 #define EXT_CSD_CACHE_CTRL		33      /* R/W */
 #define EXT_CSD_POWER_OFF_NOTIFICATION	34	/* R/W */
-#define EXT_CSD_PACKED_FAILURE_INDEX	35	/* RO */
-#define EXT_CSD_PACKED_CMD_STATUS	36	/* RO */
 #define EXT_CSD_EXP_EVENTS_STATUS	54	/* RO, 2 bytes */
 #define EXT_CSD_EXP_EVENTS_CTRL		56	/* R/W, 2 bytes */
 #define EXT_CSD_DATA_SECTOR_SIZE	61	/* R */
@@ -321,8 +319,6 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_SUPPORTED_MODE		493	/* RO */
 #define EXT_CSD_TAG_UNIT_SIZE		498	/* RO */
 #define EXT_CSD_DATA_TAG_SUPPORT	499	/* RO */
-#define EXT_CSD_MAX_PACKED_WRITES	500	/* RO */
-#define EXT_CSD_MAX_PACKED_READS	501	/* RO */
 #define EXT_CSD_BKOPS_SUPPORT		502	/* RO */
 #define EXT_CSD_HPI_FEATURES		503	/* RO */
 
@@ -402,18 +398,12 @@ static inline bool mmc_ready_for_data(u32 status)
 #define EXT_CSD_PWR_CL_8BIT_SHIFT	4
 #define EXT_CSD_PWR_CL_4BIT_SHIFT	0
 
-#define EXT_CSD_PACKED_EVENT_EN	BIT(3)
-
 /*
  * EXCEPTION_EVENT_STATUS field
  */
 #define EXT_CSD_URGENT_BKOPS		BIT(0)
 #define EXT_CSD_DYNCAP_NEEDED		BIT(1)
 #define EXT_CSD_SYSPOOL_EXHAUSTED	BIT(2)
-#define EXT_CSD_PACKED_FAILURE		BIT(3)
-
-#define EXT_CSD_PACKED_GENERIC_ERROR	BIT(0)
-#define EXT_CSD_PACKED_INDEXED_ERROR	BIT(1)
 
 /*
  * BKOPS status level
diff --git a/include/linux/mmc/sd.h b/include/linux/mmc/sd.h
index 6727576a8755..af5fc70e09a2 100644
--- a/include/linux/mmc/sd.h
+++ b/include/linux/mmc/sd.h
@@ -15,6 +15,9 @@
 #define SD_SEND_IF_COND           8   /* bcr  [11:0] See below   R7  */
 #define SD_SWITCH_VOLTAGE         11  /* ac                      R1  */
 
+/* Class 2 */
+#define SD_ADDR_EXT		 22   /* ac   [5:0]              R1  */
+
   /* class 10 */
 #define SD_SWITCH                 6   /* adtc [31:0] See below   R1  */
 
@@ -36,6 +39,7 @@
 /* OCR bit definitions */
 #define SD_OCR_S18R		(1 << 24)    /* 1.8V switching request */
 #define SD_ROCR_S18A		SD_OCR_S18R  /* 1.8V switching accepted by card */
+#define SD_OCR_2T		(1 << 27)    /* HO2T/CO2T - SDUC support */
 #define SD_OCR_XPC		(1 << 28)    /* SDXC power control */
 #define SD_OCR_CCS		(1 << 30)    /* Card Capacity Status */
 
diff --git a/include/linux/mmc/sd_uhs2.h b/include/linux/mmc/sd_uhs2.h
new file mode 100644
index 000000000000..7abe9bd870c7
--- /dev/null
+++ b/include/linux/mmc/sd_uhs2.h
@@ -0,0 +1,240 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * Header file for UHS-II packets, Host Controller registers and I/O
+ * accessors.
+ *
+ *  Copyright (C) 2014 Intel Corp, All Rights Reserved.
+ */
+#ifndef LINUX_MMC_UHS2_H
+#define LINUX_MMC_UHS2_H
+
+/* LINK Layer definition */
+/*
+ * UHS2 Header:
+ * Refer to UHS-II Addendum Version 1.02 Figure 5-2, the format of CCMD Header is described below:
+ *      bit [3:0]  : DID(Destination ID = Node ID of UHS2 card)
+ *      bit [6:4]  : TYP(Packet Type)
+ *                   000b: CCMD(Control command packet)
+ *                   001b: DCMD(Data command packet)
+ *                   010b: RES(Response packet)
+ *                   011b: DATA(Data payload packet)
+ *                   111b: MSG(Message packet)
+ *                   Others: Reserved
+ *      bit [7]    : NP(Native Packet)
+ *      bit [10:8] : TID(Transaction ID)
+ *      bit [11]   : Reserved
+ *      bit [15:12]: SID(Source ID 0: Node ID of Host)
+ *
+ * Broadcast CCMD issued by Host is represented as DID=SID=0.
+ */
+/*
+ * UHS2 Argument:
+ * Refer to UHS-II Addendum Version 1.02 Figure 6-5, the format of CCMD Argument is described below:
+ *      bit [3:0]  : MSB of IOADR
+ *      bit [5:4]  : PLEN(Payload Length)
+ *                   00b: 0 byte
+ *                   01b: 4 bytes
+ *                   10b: 8 bytes
+ *                   11b: 16 bytes
+ *      bit [6]    : Reserved
+ *      bit [7]    : R/W(Read/Write)
+ *                   0: Control read command
+ *                   1: Control write command
+ *      bit [15:8] : LSB of IOADR
+ *
+ * I/O Address specifies the address of register in UHS-II I/O space accessed by CCMD.
+ * The unit of I/O Address is 4 Bytes. It is transmitted in MSB first, LSB last.
+ */
+#define UHS2_NATIVE_PACKET_POS	7
+#define UHS2_NATIVE_PACKET	(1 << UHS2_NATIVE_PACKET_POS)
+
+#define UHS2_PACKET_TYPE_POS	4
+#define UHS2_PACKET_TYPE_CCMD	(0 << UHS2_PACKET_TYPE_POS)
+#define UHS2_PACKET_TYPE_DCMD	(1 << UHS2_PACKET_TYPE_POS)
+#define UHS2_PACKET_TYPE_RES	(2 << UHS2_PACKET_TYPE_POS)
+#define UHS2_PACKET_TYPE_DATA	(3 << UHS2_PACKET_TYPE_POS)
+#define UHS2_PACKET_TYPE_MSG	(7 << UHS2_PACKET_TYPE_POS)
+
+#define UHS2_DEST_ID_MASK	0x0F
+#define UHS2_DEST_ID		0x1
+
+#define UHS2_SRC_ID_POS		12
+#define UHS2_SRC_ID_MASK	0xF000
+
+#define UHS2_TRANS_ID_POS	8
+#define UHS2_TRANS_ID_MASK	0x0700
+
+/* UHS2 MSG */
+#define UHS2_MSG_CTG_POS	5
+#define UHS2_MSG_CTG_LMSG	0x00
+#define UHS2_MSG_CTG_INT	0x60
+#define UHS2_MSG_CTG_AMSG	0x80
+
+#define UHS2_MSG_CTG_FCREQ	0x00
+#define UHS2_MSG_CTG_FCRDY	0x01
+#define UHS2_MSG_CTG_STAT	0x02
+
+#define UHS2_MSG_CODE_POS			8
+#define UHS2_MSG_CODE_FC_UNRECOVER_ERR		0x8
+#define UHS2_MSG_CODE_STAT_UNRECOVER_ERR	0x8
+#define UHS2_MSG_CODE_STAT_RECOVER_ERR		0x1
+
+/* TRANS Layer definition */
+
+/* Native packets*/
+#define UHS2_NATIVE_CMD_RW_POS	7
+#define UHS2_NATIVE_CMD_WRITE	(1 << UHS2_NATIVE_CMD_RW_POS)
+#define UHS2_NATIVE_CMD_READ	(0 << UHS2_NATIVE_CMD_RW_POS)
+
+#define UHS2_NATIVE_CMD_PLEN_POS	4
+#define UHS2_NATIVE_CMD_PLEN_4B		(1 << UHS2_NATIVE_CMD_PLEN_POS)
+#define UHS2_NATIVE_CMD_PLEN_8B		(2 << UHS2_NATIVE_CMD_PLEN_POS)
+#define UHS2_NATIVE_CMD_PLEN_16B	(3 << UHS2_NATIVE_CMD_PLEN_POS)
+
+#define UHS2_NATIVE_CCMD_GET_MIOADR_MASK	0xF00
+#define UHS2_NATIVE_CCMD_MIOADR_MASK		0x0F
+
+#define UHS2_NATIVE_CCMD_LIOADR_POS		8
+#define UHS2_NATIVE_CCMD_GET_LIOADR_MASK	0x0FF
+
+#define UHS2_CCMD_DEV_INIT_COMPLETE_FLAG	BIT(11)
+#define UHS2_DEV_INIT_PAYLOAD_LEN		1
+#define UHS2_DEV_INIT_RESP_LEN			6
+#define UHS2_DEV_ENUM_PAYLOAD_LEN		1
+#define UHS2_DEV_ENUM_RESP_LEN			8
+#define UHS2_CFG_WRITE_PAYLOAD_LEN		2
+#define UHS2_CFG_WRITE_PHY_SET_RESP_LEN		4
+#define UHS2_CFG_WRITE_GENERIC_SET_RESP_LEN	5
+#define UHS2_GO_DORMANT_PAYLOAD_LEN		1
+
+/*
+ * UHS2 Argument:
+ * Refer to UHS-II Addendum Version 1.02 Figure 6-8, the format of DCMD Argument is described below:
+ *      bit [3:0]  : Reserved
+ *      bit [6:3]  : TMODE(Transfer Mode)
+ *                   bit 3: DAM(Data Access Mode)
+ *                   bit 4: TLUM(TLEN Unit Mode)
+ *                   bit 5: LM(Length Mode)
+ *                   bit 6: DM(Duplex Mode)
+ *      bit [7]    : R/W(Read/Write)
+ *                   0: Control read command
+ *                   1: Control write command
+ *      bit [15:8] : Reserved
+ *
+ * I/O Address specifies the address of register in UHS-II I/O space accessed by CCMD.
+ * The unit of I/O Address is 4 Bytes. It is transmitted in MSB first, LSB last.
+ */
+#define UHS2_DCMD_DM_POS		6
+#define UHS2_DCMD_2L_HD_MODE		(1 << UHS2_DCMD_DM_POS)
+#define UHS2_DCMD_LM_POS		5
+#define UHS2_DCMD_LM_TLEN_EXIST		(1 << UHS2_DCMD_LM_POS)
+#define UHS2_DCMD_TLUM_POS		4
+#define UHS2_DCMD_TLUM_BYTE_MODE	(1 << UHS2_DCMD_TLUM_POS)
+#define UHS2_NATIVE_DCMD_DAM_POS	3
+#define UHS2_NATIVE_DCMD_DAM_IO		(1 << UHS2_NATIVE_DCMD_DAM_POS)
+
+#define UHS2_RES_NACK_POS	7
+#define UHS2_RES_NACK_MASK	(0x1 << UHS2_RES_NACK_POS)
+
+#define UHS2_RES_ECODE_POS	4
+#define UHS2_RES_ECODE_MASK	0x7
+#define UHS2_RES_ECODE_COND	1
+#define UHS2_RES_ECODE_ARG	2
+#define UHS2_RES_ECODE_GEN	3
+
+/* IOADR of device registers */
+#define UHS2_IOADR_GENERIC_CAPS		0x00
+#define UHS2_IOADR_PHY_CAPS		0x02
+#define UHS2_IOADR_LINK_CAPS		0x04
+#define UHS2_IOADR_RSV_CAPS		0x06
+#define UHS2_IOADR_GENERIC_SETTINGS	0x08
+#define UHS2_IOADR_PHY_SETTINGS		0x0A
+#define UHS2_IOADR_LINK_SETTINGS	0x0C
+#define UHS2_IOADR_PRESET		0x40
+
+/* SD application packets */
+#define UHS2_SD_CMD_INDEX_POS	8
+
+#define UHS2_SD_CMD_APP_POS	14
+#define UHS2_SD_CMD_APP		(1 << UHS2_SD_CMD_APP_POS)
+
+/* UHS-II Device Registers */
+#define UHS2_DEV_CONFIG_REG	0x000
+
+/* General Caps and Settings registers */
+#define UHS2_DEV_CONFIG_GEN_CAPS	(UHS2_DEV_CONFIG_REG + 0x000)
+#define UHS2_DEV_CONFIG_N_LANES_POS	8
+#define UHS2_DEV_CONFIG_N_LANES_MASK	0x3F
+#define UHS2_DEV_CONFIG_2L_HD_FD	0x1
+#define UHS2_DEV_CONFIG_2D1U_FD		0x2
+#define UHS2_DEV_CONFIG_1D2U_FD		0x4
+#define UHS2_DEV_CONFIG_2D2U_FD		0x8
+#define UHS2_DEV_CONFIG_DADR_POS	14
+#define UHS2_DEV_CONFIG_DADR_MASK	0x1
+#define UHS2_DEV_CONFIG_APP_POS		16
+#define UHS2_DEV_CONFIG_APP_MASK	0xFF
+#define UHS2_DEV_CONFIG_APP_SD_MEM	0x1
+
+#define UHS2_DEV_CONFIG_GEN_SET			(UHS2_DEV_CONFIG_REG + 0x008)
+#define UHS2_DEV_CONFIG_GEN_SET_N_LANES_POS	8
+#define UHS2_DEV_CONFIG_GEN_SET_2L_FD_HD	0x0
+#define UHS2_DEV_CONFIG_GEN_SET_2D1U_FD		0x2
+#define UHS2_DEV_CONFIG_GEN_SET_1D2U_FD		0x3
+#define UHS2_DEV_CONFIG_GEN_SET_2D2U_FD		0x4
+#define UHS2_DEV_CONFIG_GEN_SET_CFG_COMPLETE	BIT(31)
+
+/* PHY Caps and Settings registers */
+#define UHS2_DEV_CONFIG_PHY_CAPS	(UHS2_DEV_CONFIG_REG + 0x002)
+#define UHS2_DEV_CONFIG_PHY_MINOR_MASK	0xF
+#define UHS2_DEV_CONFIG_PHY_MAJOR_POS	4
+#define UHS2_DEV_CONFIG_PHY_MAJOR_MASK	0x3
+#define UHS2_DEV_CONFIG_CAN_HIBER_POS	15
+#define UHS2_DEV_CONFIG_CAN_HIBER_MASK	0x1
+#define UHS2_DEV_CONFIG_PHY_CAPS1	(UHS2_DEV_CONFIG_REG + 0x003)
+#define UHS2_DEV_CONFIG_N_LSS_SYN_MASK	0xF
+#define UHS2_DEV_CONFIG_N_LSS_DIR_POS	4
+#define UHS2_DEV_CONFIG_N_LSS_DIR_MASK	0xF
+
+#define UHS2_DEV_CONFIG_PHY_SET			(UHS2_DEV_CONFIG_REG + 0x00A)
+#define UHS2_DEV_CONFIG_PHY_SET_SPEED_POS	6
+#define UHS2_DEV_CONFIG_PHY_SET_SPEED_A		0x0
+#define UHS2_DEV_CONFIG_PHY_SET_SPEED_B		0x1
+
+/* LINK-TRAN Caps and Settings registers */
+#define UHS2_DEV_CONFIG_LINK_TRAN_CAPS		(UHS2_DEV_CONFIG_REG + 0x004)
+#define UHS2_DEV_CONFIG_LT_MINOR_MASK		0xF
+#define UHS2_DEV_CONFIG_LT_MAJOR_POS		4
+#define UHS2_DEV_CONFIG_LT_MAJOR_MASK		0x3
+#define UHS2_DEV_CONFIG_N_FCU_POS		8
+#define UHS2_DEV_CONFIG_N_FCU_MASK		0xFF
+#define UHS2_DEV_CONFIG_DEV_TYPE_POS		16
+#define UHS2_DEV_CONFIG_DEV_TYPE_MASK		0x7
+#define UHS2_DEV_CONFIG_MAX_BLK_LEN_POS		20
+#define UHS2_DEV_CONFIG_MAX_BLK_LEN_MASK	0xFFF
+#define UHS2_DEV_CONFIG_LINK_TRAN_CAPS1		(UHS2_DEV_CONFIG_REG + 0x005)
+#define UHS2_DEV_CONFIG_N_DATA_GAP_MASK		0xFF
+
+#define UHS2_DEV_CONFIG_LINK_TRAN_SET		(UHS2_DEV_CONFIG_REG + 0x00C)
+#define UHS2_DEV_CONFIG_LT_SET_MAX_BLK_LEN	0x200
+#define UHS2_DEV_CONFIG_LT_SET_MAX_RETRY_POS	16
+
+/* Preset register */
+#define UHS2_DEV_CONFIG_PRESET	(UHS2_DEV_CONFIG_REG + 0x040)
+
+#define UHS2_DEV_INT_REG	0x100
+
+#define UHS2_DEV_STATUS_REG	0x180
+
+#define UHS2_DEV_CMD_REG		0x200
+#define UHS2_DEV_CMD_FULL_RESET		(UHS2_DEV_CMD_REG + 0x000)
+#define UHS2_DEV_CMD_GO_DORMANT_STATE	(UHS2_DEV_CMD_REG + 0x001)
+#define UHS2_DEV_CMD_DORMANT_HIBER	BIT(7)
+#define UHS2_DEV_CMD_DEVICE_INIT	(UHS2_DEV_CMD_REG + 0x002)
+#define UHS2_DEV_INIT_COMPLETE_FLAG	BIT(11)
+#define UHS2_DEV_CMD_ENUMERATE		(UHS2_DEV_CMD_REG + 0x003)
+#define UHS2_DEV_CMD_TRANS_ABORT	(UHS2_DEV_CMD_REG + 0x004)
+
+#define UHS2_RCLK_MAX	52000000
+#define UHS2_RCLK_MIN	26000000
+
+#endif /* LINUX_MMC_UHS2_H */
diff --git a/include/linux/mmc/sdio_func.h b/include/linux/mmc/sdio_func.h
index 478855b8e406..fed1f5f4a8d3 100644
--- a/include/linux/mmc/sdio_func.h
+++ b/include/linux/mmc/sdio_func.h
@@ -106,7 +106,10 @@ struct sdio_driver {
 	.class = (dev_class), \
 	.vendor = SDIO_ANY_ID, .device = SDIO_ANY_ID
 
-extern int sdio_register_driver(struct sdio_driver *);
+/* use a macro to avoid include chaining to get THIS_MODULE */
+#define sdio_register_driver(drv) \
+	__sdio_register_driver(drv, THIS_MODULE)
+extern int __sdio_register_driver(struct sdio_driver *, struct module *);
 extern void sdio_unregister_driver(struct sdio_driver *);
 
 /**
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index c653accdc7fd..673cbdf43453 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -76,7 +76,8 @@
 #define SDIO_DEVICE_ID_BROADCOM_43430		0xa9a6
 #define SDIO_DEVICE_ID_BROADCOM_43439		0xa9af
 #define SDIO_DEVICE_ID_BROADCOM_43455		0xa9bf
-#define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752	0xaae8
+#define SDIO_DEVICE_ID_BROADCOM_43751		0xaae7
+#define SDIO_DEVICE_ID_BROADCOM_43752		0xaae8
 
 #define SDIO_VENDOR_ID_CYPRESS			0x04b4
 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43439	0xbd3d
@@ -121,8 +122,10 @@
 #define SDIO_DEVICE_ID_REALTEK_RTW8822BS	0xb822
 #define SDIO_DEVICE_ID_REALTEK_RTW8821CS	0xc821
 #define SDIO_DEVICE_ID_REALTEK_RTW8822CS	0xc822
-#define SDIO_DEVICE_ID_REALTEK_RTW8723DS	0xd723
+#define SDIO_DEVICE_ID_REALTEK_RTW8723DS_2ANT	0xd723
+#define SDIO_DEVICE_ID_REALTEK_RTW8723DS_1ANT	0xd724
 #define SDIO_DEVICE_ID_REALTEK_RTW8821DS	0xd821
+#define SDIO_DEVICE_ID_REALTEK_RTW8723CS	0xb703
 
 #define SDIO_VENDOR_ID_SIANO			0x039a
 #define SDIO_DEVICE_ID_SIANO_NOVA_B0		0x0201
diff --git a/include/linux/mmc/slot-gpio.h b/include/linux/mmc/slot-gpio.h
index 5d3d15e97868..23ac5696fa38 100644
--- a/include/linux/mmc/slot-gpio.h
+++ b/include/linux/mmc/slot-gpio.h
@@ -8,8 +8,8 @@
 #ifndef MMC_SLOT_GPIO_H
 #define MMC_SLOT_GPIO_H
 
+#include <linux/interrupt.h>
 #include <linux/types.h>
-#include <linux/irqreturn.h>
 
 struct mmc_host;
 
@@ -21,11 +21,10 @@ int mmc_gpiod_request_cd(struct mmc_host *host, const char *con_id,
 			 unsigned int debounce);
 int mmc_gpiod_request_ro(struct mmc_host *host, const char *con_id,
 			 unsigned int idx, unsigned int debounce);
-void mmc_gpio_set_cd_isr(struct mmc_host *host,
-			 irqreturn_t (*isr)(int irq, void *dev_id));
+int mmc_gpiod_set_cd_config(struct mmc_host *host, unsigned long config);
 int mmc_gpio_set_cd_wake(struct mmc_host *host, bool on);
 void mmc_gpiod_request_cd_irq(struct mmc_host *host);
-bool mmc_can_gpio_cd(struct mmc_host *host);
-bool mmc_can_gpio_ro(struct mmc_host *host);
+bool mmc_host_can_gpio_cd(struct mmc_host *host);
+bool mmc_host_can_gpio_ro(struct mmc_host *host);
 
 #endif
diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index 7c3e7b0b0e8f..14a45979cccc 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -9,10 +9,12 @@ struct page;
 struct vm_area_struct;
 struct mm_struct;
 struct vma_iterator;
+struct vma_merge_struct;
 
-void dump_page(struct page *page, const char *reason);
+void dump_page(const struct page *page, const char *reason);
 void dump_vma(const struct vm_area_struct *vma);
 void dump_mm(const struct mm_struct *mm);
+void dump_vmg(const struct vma_merge_struct *vmg, const char *reason);
 void vma_iter_dump_tree(const struct vma_iterator *vmi);
 
 #ifdef CONFIG_DEBUG_VM
@@ -46,7 +48,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 		}							\
 	} while (0)
 #define VM_WARN_ON_ONCE_PAGE(cond, page)	({			\
-	static bool __section(".data.once") __warned;			\
+	static bool __section(".data..once") __warned;			\
 	int __ret_warn_once = !!(cond);					\
 									\
 	if (unlikely(__ret_warn_once && !__warned)) {			\
@@ -66,7 +68,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 	unlikely(__ret_warn);						\
 })
 #define VM_WARN_ON_ONCE_FOLIO(cond, folio)	({			\
-	static bool __section(".data.once") __warned;			\
+	static bool __section(".data..once") __warned;			\
 	int __ret_warn_once = !!(cond);					\
 									\
 	if (unlikely(__ret_warn_once && !__warned)) {			\
@@ -77,7 +79,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 	unlikely(__ret_warn_once);					\
 })
 #define VM_WARN_ON_ONCE_MM(cond, mm)		({			\
-	static bool __section(".data.once") __warned;			\
+	static bool __section(".data..once") __warned;			\
 	int __ret_warn_once = !!(cond);					\
 									\
 	if (unlikely(__ret_warn_once && !__warned)) {			\
@@ -87,6 +89,26 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 	}								\
 	unlikely(__ret_warn_once);					\
 })
+#define VM_WARN_ON_ONCE_VMA(cond, vma)		({			\
+	static bool __section(".data..once") __warned;			\
+	int __ret_warn_once = !!(cond);					\
+									\
+	if (unlikely(__ret_warn_once && !__warned)) {			\
+		dump_vma(vma);						\
+		__warned = true;					\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn_once);					\
+})
+#define VM_WARN_ON_VMG(cond, vmg)		({			\
+	int __ret_warn = !!(cond);					\
+									\
+	if (unlikely(__ret_warn)) {					\
+		dump_vmg(vmg, "VM_WARN_ON_VMG(" __stringify(cond)")");	\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn);						\
+})
 
 #define VM_WARN_ON(cond) (void)WARN_ON(cond)
 #define VM_WARN_ON_ONCE(cond) (void)WARN_ON_ONCE(cond)
@@ -104,9 +126,11 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 #define VM_WARN_ON_FOLIO(cond, folio)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE_FOLIO(cond, folio)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE_MM(cond, mm)  BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_VMA(cond, vma)  BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_VMG(cond, vmg)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
-#endif
+#endif /* CONFIG_DEBUG_VM */
 
 #ifdef CONFIG_DEBUG_VM_IRQSOFF
 #define VM_WARN_ON_IRQS_ENABLED() WARN_ON_ONCE(!irqs_disabled())
diff --git a/include/linux/mmu_context.h b/include/linux/mmu_context.h
index f2b7a3f04099..ac01dc4eb2ce 100644
--- a/include/linux/mmu_context.h
+++ b/include/linux/mmu_context.h
@@ -11,7 +11,7 @@
 #endif
 
 #ifndef leave_mm
-static inline void leave_mm(int cpu) { }
+static inline void leave_mm(void) { }
 #endif
 
 /*
@@ -24,6 +24,7 @@ static inline void leave_mm(int cpu) { }
 #ifndef task_cpu_possible_mask
 # define task_cpu_possible_mask(p)	cpu_possible_mask
 # define task_cpu_possible(cpu, p)	true
+# define task_cpu_fallback_mask(p)	housekeeping_cpumask(HK_TYPE_TICK)
 #else
 # define task_cpu_possible(cpu, p)	cpumask_test_cpu((cpu), task_cpu_possible_mask(p))
 #endif
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 64a3e051c3c4..d1094c2d5fb6 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -43,10 +43,10 @@ struct mmu_interval_notifier;
  * a device driver to possibly ignore the invalidation if the
  * owner field matches the driver's device private pgmap owner.
  *
- * @MMU_NOTIFY_EXCLUSIVE: to signal a device driver that the device will no
- * longer have exclusive access to the page. When sent during creation of an
- * exclusive range the owner will be initialised to the value provided by the
- * caller of make_device_exclusive_range(), otherwise the owner will be NULL.
+ * @MMU_NOTIFY_EXCLUSIVE: conversion of a page table entry to device-exclusive.
+ * The owner is initialized to the value provided by the caller of
+ * make_device_exclusive(), such that this caller can filter out these
+ * events.
  */
 enum mmu_notifier_event {
 	MMU_NOTIFY_UNMAP = 0,
@@ -123,15 +123,6 @@ struct mmu_notifier_ops {
 			  unsigned long address);
 
 	/*
-	 * change_pte is called in cases that pte mapping to page is changed:
-	 * for example, when ksm remaps pte to point to a new shared page.
-	 */
-	void (*change_pte)(struct mmu_notifier *subscription,
-			   struct mm_struct *mm,
-			   unsigned long address,
-			   pte_t pte);
-
-	/*
 	 * invalidate_range_start() and invalidate_range_end() must be
 	 * paired and are called only when the mmap_lock and/or the
 	 * locks protecting the reverse maps are held. If the subsystem
@@ -187,27 +178,27 @@ struct mmu_notifier_ops {
 				     const struct mmu_notifier_range *range);
 
 	/*
-	 * invalidate_range() is either called between
-	 * invalidate_range_start() and invalidate_range_end() when the
-	 * VM has to free pages that where unmapped, but before the
-	 * pages are actually freed, or outside of _start()/_end() when
-	 * a (remote) TLB is necessary.
+	 * arch_invalidate_secondary_tlbs() is used to manage a non-CPU TLB
+	 * which shares page-tables with the CPU. The
+	 * invalidate_range_start()/end() callbacks should not be implemented as
+	 * invalidate_secondary_tlbs() already catches the points in time when
+	 * an external TLB needs to be flushed.
 	 *
-	 * If invalidate_range() is used to manage a non-CPU TLB with
-	 * shared page-tables, it not necessary to implement the
-	 * invalidate_range_start()/end() notifiers, as
-	 * invalidate_range() already catches the points in time when an
-	 * external TLB range needs to be flushed. For more in depth
-	 * discussion on this see Documentation/mm/mmu_notifier.rst
+	 * This requires arch_invalidate_secondary_tlbs() to be called while
+	 * holding the ptl spin-lock and therefore this callback is not allowed
+	 * to sleep.
 	 *
-	 * Note that this function might be called with just a sub-range
-	 * of what was passed to invalidate_range_start()/end(), if
-	 * called between those functions.
+	 * This is called by architecture code whenever invalidating a TLB
+	 * entry. It is assumed that any secondary TLB has the same rules for
+	 * when invalidations are required. If this is not the case architecture
+	 * code will need to call this explicitly when required for secondary
+	 * TLB invalidation.
 	 */
-	void (*invalidate_range)(struct mmu_notifier *subscription,
-				 struct mm_struct *mm,
-				 unsigned long start,
-				 unsigned long end);
+	void (*arch_invalidate_secondary_tlbs)(
+					struct mmu_notifier *subscription,
+					struct mm_struct *mm,
+					unsigned long start,
+					unsigned long end);
 
 	/*
 	 * These callbacks are used with the get/put interface to manage the
@@ -392,13 +383,10 @@ extern int __mmu_notifier_clear_young(struct mm_struct *mm,
 				      unsigned long end);
 extern int __mmu_notifier_test_young(struct mm_struct *mm,
 				     unsigned long address);
-extern void __mmu_notifier_change_pte(struct mm_struct *mm,
-				      unsigned long address, pte_t pte);
 extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r);
-extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r,
-				  bool only_end);
-extern void __mmu_notifier_invalidate_range(struct mm_struct *mm,
-				  unsigned long start, unsigned long end);
+extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r);
+extern void __mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
+					unsigned long start, unsigned long end);
 extern bool
 mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range);
 
@@ -440,13 +428,6 @@ static inline int mmu_notifier_test_young(struct mm_struct *mm,
 	return 0;
 }
 
-static inline void mmu_notifier_change_pte(struct mm_struct *mm,
-					   unsigned long address, pte_t pte)
-{
-	if (mm_has_notifiers(mm))
-		__mmu_notifier_change_pte(mm, address, pte);
-}
-
 static inline void
 mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 {
@@ -460,7 +441,14 @@ mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 	lock_map_release(&__mmu_notifier_invalidate_range_start_map);
 }
 
-static inline int
+/*
+ * This version of mmu_notifier_invalidate_range_start() avoids blocking, but it
+ * can return an error if a notifier can't proceed without blocking, in which
+ * case you're not allowed to modify PTEs in the specified range.
+ *
+ * This is mainly intended for OOM handling.
+ */
+static inline int __must_check
 mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range)
 {
 	int ret = 0;
@@ -481,21 +469,14 @@ mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
 		might_sleep();
 
 	if (mm_has_notifiers(range->mm))
-		__mmu_notifier_invalidate_range_end(range, false);
-}
-
-static inline void
-mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range)
-{
-	if (mm_has_notifiers(range->mm))
-		__mmu_notifier_invalidate_range_end(range, true);
+		__mmu_notifier_invalidate_range_end(range);
 }
 
-static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
-				  unsigned long start, unsigned long end)
+static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
+					unsigned long start, unsigned long end)
 {
 	if (mm_has_notifiers(mm))
-		__mmu_notifier_invalidate_range(mm, start, end);
+		__mmu_notifier_arch_invalidate_secondary_tlbs(mm, start, end);
 }
 
 static inline void mmu_notifier_subscriptions_init(struct mm_struct *mm)
@@ -582,65 +563,6 @@ static inline void mmu_notifier_range_init_owner(
 	__young;							\
 })
 
-#define	ptep_clear_flush_notify(__vma, __address, __ptep)		\
-({									\
-	unsigned long ___addr = __address & PAGE_MASK;			\
-	struct mm_struct *___mm = (__vma)->vm_mm;			\
-	pte_t ___pte;							\
-									\
-	___pte = ptep_clear_flush(__vma, __address, __ptep);		\
-	mmu_notifier_invalidate_range(___mm, ___addr,			\
-					___addr + PAGE_SIZE);		\
-									\
-	___pte;								\
-})
-
-#define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd)		\
-({									\
-	unsigned long ___haddr = __haddr & HPAGE_PMD_MASK;		\
-	struct mm_struct *___mm = (__vma)->vm_mm;			\
-	pmd_t ___pmd;							\
-									\
-	___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd);		\
-	mmu_notifier_invalidate_range(___mm, ___haddr,			\
-				      ___haddr + HPAGE_PMD_SIZE);	\
-									\
-	___pmd;								\
-})
-
-#define pudp_huge_clear_flush_notify(__vma, __haddr, __pud)		\
-({									\
-	unsigned long ___haddr = __haddr & HPAGE_PUD_MASK;		\
-	struct mm_struct *___mm = (__vma)->vm_mm;			\
-	pud_t ___pud;							\
-									\
-	___pud = pudp_huge_clear_flush(__vma, __haddr, __pud);		\
-	mmu_notifier_invalidate_range(___mm, ___haddr,			\
-				      ___haddr + HPAGE_PUD_SIZE);	\
-									\
-	___pud;								\
-})
-
-/*
- * set_pte_at_notify() sets the pte _after_ running the notifier.
- * This is safe to start by updating the secondary MMUs, because the primary MMU
- * pte invalidate must have already happened with a ptep_clear_flush() before
- * set_pte_at_notify() has been invoked.  Updating the secondary MMUs first is
- * required when we change both the protection of the mapping from read-only to
- * read-write and the pfn (like during copy on write page faults). Otherwise the
- * old page would remain mapped readonly in the secondary MMUs after the new
- * page is already writable by some CPU through the primary MMU.
- */
-#define set_pte_at_notify(__mm, __address, __ptep, __pte)		\
-({									\
-	struct mm_struct *___mm = __mm;					\
-	unsigned long ___address = __address;				\
-	pte_t ___pte = __pte;						\
-									\
-	mmu_notifier_change_pte(___mm, ___address, ___pte);		\
-	set_pte_at(___mm, ___address, __ptep, ___pte);			\
-})
-
 #else /* CONFIG_MMU_NOTIFIER */
 
 struct mmu_notifier_range {
@@ -684,15 +606,17 @@ static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm,
 	return 0;
 }
 
-static inline int mmu_notifier_test_young(struct mm_struct *mm,
-					  unsigned long address)
+static inline int mmu_notifier_clear_young(struct mm_struct *mm,
+					   unsigned long start,
+					   unsigned long end)
 {
 	return 0;
 }
 
-static inline void mmu_notifier_change_pte(struct mm_struct *mm,
-					   unsigned long address, pte_t pte)
+static inline int mmu_notifier_test_young(struct mm_struct *mm,
+					  unsigned long address)
 {
+	return 0;
 }
 
 static inline void
@@ -711,12 +635,7 @@ void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range)
 {
 }
 
-static inline void
-mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range)
-{
-}
-
-static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
+static inline void mmu_notifier_arch_invalidate_secondary_tlbs(struct mm_struct *mm,
 				  unsigned long start, unsigned long end)
 {
 }
@@ -735,10 +654,6 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
 #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
 #define ptep_clear_young_notify ptep_test_and_clear_young
 #define pmdp_clear_young_notify pmdp_test_and_clear_young
-#define	ptep_clear_flush_notify ptep_clear_flush
-#define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush
-#define pudp_huge_clear_flush_notify pudp_huge_clear_flush
-#define set_pte_at_notify set_pte_at
 
 static inline void mmu_notifier_synchronize(void)
 {
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5a7ada0413da..4398e027f450 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -22,18 +22,37 @@
 #include <linux/mm_types.h>
 #include <linux/page-flags.h>
 #include <linux/local_lock.h>
+#include <linux/zswap.h>
 #include <asm/page.h>
 
 /* Free memory management - zoned buddy allocator.  */
 #ifndef CONFIG_ARCH_FORCE_MAX_ORDER
-#define MAX_ORDER 10
+#define MAX_PAGE_ORDER 10
 #else
-#define MAX_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
+#define MAX_PAGE_ORDER CONFIG_ARCH_FORCE_MAX_ORDER
 #endif
-#define MAX_ORDER_NR_PAGES (1 << MAX_ORDER)
+#define MAX_ORDER_NR_PAGES (1 << MAX_PAGE_ORDER)
 
 #define IS_MAX_ORDER_ALIGNED(pfn) IS_ALIGNED(pfn, MAX_ORDER_NR_PAGES)
 
+#define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1)
+
+/* Defines the order for the number of pages that have a migrate type. */
+#ifndef CONFIG_PAGE_BLOCK_MAX_ORDER
+#define PAGE_BLOCK_MAX_ORDER MAX_PAGE_ORDER
+#else
+#define PAGE_BLOCK_MAX_ORDER CONFIG_PAGE_BLOCK_MAX_ORDER
+#endif /* CONFIG_PAGE_BLOCK_MAX_ORDER */
+
+/*
+ * The MAX_PAGE_ORDER, which defines the max order of pages to be allocated
+ * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_MAX_ORDER,
+ * which defines the order for the number of pages that can have a migrate type
+ */
+#if (PAGE_BLOCK_MAX_ORDER > MAX_PAGE_ORDER)
+#error MAX_PAGE_ORDER must be >= PAGE_BLOCK_MAX_ORDER
+#endif
+
 /*
  * PAGE_ALLOC_COSTLY_ORDER is the order at which allocations are deemed
  * costly to service.  That is between allocation orders which should
@@ -60,6 +79,9 @@ enum migratetype {
 	 * __free_pageblock_cma() function.
 	 */
 	MIGRATE_CMA,
+	__MIGRATE_TYPE_END = MIGRATE_CMA,
+#else
+	__MIGRATE_TYPE_END = MIGRATE_HIGHATOMIC,
 #endif
 #ifdef CONFIG_MEMORY_ISOLATION
 	MIGRATE_ISOLATE,	/* can't allocate from here */
@@ -73,9 +95,16 @@ extern const char * const migratetype_names[MIGRATE_TYPES];
 #ifdef CONFIG_CMA
 #  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
 #  define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
+/*
+ * __dump_folio() in mm/debug.c passes a folio pointer to on-stack struct folio,
+ * so folio_pfn() cannot be used and pfn is needed.
+ */
+#  define is_migrate_cma_folio(folio, pfn) \
+	(get_pfnblock_migratetype(&folio->page, pfn) == MIGRATE_CMA)
 #else
 #  define is_migrate_cma(migratetype) false
 #  define is_migrate_cma_page(_page) false
+#  define is_migrate_cma_folio(folio, pfn) false
 #endif
 
 static inline bool is_migrate_movable(int mt)
@@ -95,15 +124,16 @@ static inline bool migratetype_is_mergeable(int mt)
 }
 
 #define for_each_migratetype_order(order, type) \
-	for (order = 0; order <= MAX_ORDER; order++) \
+	for (order = 0; order < NR_PAGE_ORDERS; order++) \
 		for (type = 0; type < MIGRATE_TYPES; type++)
 
 extern int page_group_by_mobility_disabled;
 
-#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1)
+#define get_pageblock_migratetype(page) \
+	get_pfnblock_migratetype(page, page_to_pfn(page))
 
-#define get_pageblock_migratetype(page)					\
-	get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK)
+#define folio_migratetype(folio) \
+	get_pageblock_migratetype(&folio->page)
 
 struct free_area {
 	struct list_head	free_list[MIGRATE_TYPES];
@@ -129,6 +159,7 @@ enum numa_stat_item {
 enum zone_stat_item {
 	/* First 128 byte cacheline (assuming 64 bit words) */
 	NR_FREE_PAGES,
+	NR_FREE_PAGES_BLOCKS,
 	NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
 	NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
 	NR_ZONE_ACTIVE_ANON,
@@ -138,11 +169,13 @@ enum zone_stat_item {
 	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */
 	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */
 	/* Second 128 byte cacheline */
-	NR_BOUNCE,
 #if IS_ENABLED(CONFIG_ZSMALLOC)
 	NR_ZSPAGES,		/* allocated in zsmalloc */
 #endif
 	NR_FREE_CMA_PAGES,
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	NR_UNACCEPTED,
+#endif
 	NR_VM_ZONE_STAT_ITEMS };
 
 enum node_stat_item {
@@ -173,7 +206,6 @@ enum node_stat_item {
 	NR_FILE_PAGES,
 	NR_FILE_DIRTY,
 	NR_WRITEBACK,
-	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
 	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_SHMEM_THPS,
 	NR_SHMEM_PMDMAPPED,
@@ -193,14 +225,41 @@ enum node_stat_item {
 	NR_KERNEL_SCS_KB,	/* measured in KiB */
 #endif
 	NR_PAGETABLE,		/* used for pagetables */
-	NR_SECONDARY_PAGETABLE, /* secondary pagetables, e.g. KVM pagetables */
+	NR_SECONDARY_PAGETABLE, /* secondary pagetables, KVM & IOMMU */
+#ifdef CONFIG_IOMMU_SUPPORT
+	NR_IOMMU_PAGES,		/* # of pages allocated by IOMMU */
+#endif
 #ifdef CONFIG_SWAP
 	NR_SWAPCACHE,
 #endif
 #ifdef CONFIG_NUMA_BALANCING
 	PGPROMOTE_SUCCESS,	/* promote successfully */
-	PGPROMOTE_CANDIDATE,	/* candidate pages to promote */
-#endif
+	/**
+	 * Candidate pages for promotion based on hint fault latency.  This
+	 * counter is used to control the promotion rate and adjust the hot
+	 * threshold.
+	 */
+	PGPROMOTE_CANDIDATE,
+	/**
+	 * Not rate-limited (NRL) candidate pages for those can be promoted
+	 * without considering hot threshold because of enough free pages in
+	 * fast-tier node.  These promotions bypass the regular hotness checks
+	 * and do NOT influence the promotion rate-limiter or
+	 * threshold-adjustment logic.
+	 * This is for statistics/monitoring purposes.
+	 */
+	PGPROMOTE_CANDIDATE_NRL,
+#endif
+	/* PGDEMOTE_*: pages demoted */
+	PGDEMOTE_KSWAPD,
+	PGDEMOTE_DIRECT,
+	PGDEMOTE_KHUGEPAGED,
+	PGDEMOTE_PROACTIVE,
+#ifdef CONFIG_HUGETLB_PAGE
+	NR_HUGETLB,
+#endif
+	NR_BALLOON_PAGES,
+	NR_KERNEL_FILE_PAGES,
 	NR_VM_NODE_STAT_ITEMS
 };
 
@@ -290,74 +349,108 @@ static inline bool is_active_lru(enum lru_list lru)
 #define ANON_AND_FILE 2
 
 enum lruvec_flags {
-	LRUVEC_CONGESTED,		/* lruvec has many dirty pages
-					 * backed by a congested BDI
-					 */
+	/*
+	 * An lruvec has many dirty pages backed by a congested BDI:
+	 * 1. LRUVEC_CGROUP_CONGESTED is set by cgroup-level reclaim.
+	 *    It can be cleared by cgroup reclaim or kswapd.
+	 * 2. LRUVEC_NODE_CONGESTED is set by kswapd node-level reclaim.
+	 *    It can only be cleared by kswapd.
+	 *
+	 * Essentially, kswapd can unthrottle an lruvec throttled by cgroup
+	 * reclaim, but not vice versa. This only applies to the root cgroup.
+	 * The goal is to prevent cgroup reclaim on the root cgroup (e.g.
+	 * memory.reclaim) to unthrottle an unbalanced node (that was throttled
+	 * by kswapd).
+	 */
+	LRUVEC_CGROUP_CONGESTED,
+	LRUVEC_NODE_CONGESTED,
 };
 
 #endif /* !__GENERATING_BOUNDS_H */
 
 /*
- * Evictable pages are divided into multiple generations. The youngest and the
+ * Evictable folios are divided into multiple generations. The youngest and the
  * oldest generation numbers, max_seq and min_seq, are monotonically increasing.
  * They form a sliding window of a variable size [MIN_NR_GENS, MAX_NR_GENS]. An
  * offset within MAX_NR_GENS, i.e., gen, indexes the LRU list of the
  * corresponding generation. The gen counter in folio->flags stores gen+1 while
- * a page is on one of lrugen->folios[]. Otherwise it stores 0.
+ * a folio is on one of lrugen->folios[]. Otherwise it stores 0.
  *
- * A page is added to the youngest generation on faulting. The aging needs to
- * check the accessed bit at least twice before handing this page over to the
- * eviction. The first check takes care of the accessed bit set on the initial
- * fault; the second check makes sure this page hasn't been used since then.
- * This process, AKA second chance, requires a minimum of two generations,
- * hence MIN_NR_GENS. And to maintain ABI compatibility with the active/inactive
- * LRU, e.g., /proc/vmstat, these two generations are considered active; the
- * rest of generations, if they exist, are considered inactive. See
- * lru_gen_is_active().
+ * After a folio is faulted in, the aging needs to check the accessed bit at
+ * least twice before handing this folio over to the eviction. The first check
+ * clears the accessed bit from the initial fault; the second check makes sure
+ * this folio hasn't been used since then. This process, AKA second chance,
+ * requires a minimum of two generations, hence MIN_NR_GENS. And to maintain ABI
+ * compatibility with the active/inactive LRU, e.g., /proc/vmstat, these two
+ * generations are considered active; the rest of generations, if they exist,
+ * are considered inactive. See lru_gen_is_active().
  *
- * PG_active is always cleared while a page is on one of lrugen->folios[] so
- * that the aging needs not to worry about it. And it's set again when a page
- * considered active is isolated for non-reclaiming purposes, e.g., migration.
- * See lru_gen_add_folio() and lru_gen_del_folio().
+ * PG_active is always cleared while a folio is on one of lrugen->folios[] so
+ * that the sliding window needs not to worry about it. And it's set again when
+ * a folio considered active is isolated for non-reclaiming purposes, e.g.,
+ * migration. See lru_gen_add_folio() and lru_gen_del_folio().
  *
  * MAX_NR_GENS is set to 4 so that the multi-gen LRU can support twice the
  * number of categories of the active/inactive LRU when keeping track of
  * accesses through page tables. This requires order_base_2(MAX_NR_GENS+1) bits
- * in folio->flags.
+ * in folio->flags, masked by LRU_GEN_MASK.
  */
 #define MIN_NR_GENS		2U
 #define MAX_NR_GENS		4U
 
 /*
- * Each generation is divided into multiple tiers. A page accessed N times
- * through file descriptors is in tier order_base_2(N). A page in the first tier
- * (N=0,1) is marked by PG_referenced unless it was faulted in through page
- * tables or read ahead. A page in any other tier (N>1) is marked by
- * PG_referenced and PG_workingset. This implies a minimum of two tiers is
- * supported without using additional bits in folio->flags.
+ * Each generation is divided into multiple tiers. A folio accessed N times
+ * through file descriptors is in tier order_base_2(N). A folio in the first
+ * tier (N=0,1) is marked by PG_referenced unless it was faulted in through page
+ * tables or read ahead. A folio in the last tier (MAX_NR_TIERS-1) is marked by
+ * PG_workingset. A folio in any other tier (1<N<5) between the first and last
+ * is marked by additional bits of LRU_REFS_WIDTH in folio->flags.
  *
  * In contrast to moving across generations which requires the LRU lock, moving
  * across tiers only involves atomic operations on folio->flags and therefore
  * has a negligible cost in the buffered access path. In the eviction path,
- * comparisons of refaulted/(evicted+protected) from the first tier and the
- * rest infer whether pages accessed multiple times through file descriptors
- * are statistically hot and thus worth protecting.
+ * comparisons of refaulted/(evicted+protected) from the first tier and the rest
+ * infer whether folios accessed multiple times through file descriptors are
+ * statistically hot and thus worth protecting.
  *
  * MAX_NR_TIERS is set to 4 so that the multi-gen LRU can support twice the
  * number of categories of the active/inactive LRU when keeping track of
  * accesses through file descriptors. This uses MAX_NR_TIERS-2 spare bits in
- * folio->flags.
+ * folio->flags, masked by LRU_REFS_MASK.
  */
 #define MAX_NR_TIERS		4U
 
 #ifndef __GENERATING_BOUNDS_H
 
-struct lruvec;
-struct page_vma_mapped_walk;
-
 #define LRU_GEN_MASK		((BIT(LRU_GEN_WIDTH) - 1) << LRU_GEN_PGOFF)
 #define LRU_REFS_MASK		((BIT(LRU_REFS_WIDTH) - 1) << LRU_REFS_PGOFF)
 
+/*
+ * For folios accessed multiple times through file descriptors,
+ * lru_gen_inc_refs() sets additional bits of LRU_REFS_WIDTH in folio->flags
+ * after PG_referenced, then PG_workingset after LRU_REFS_WIDTH. After all its
+ * bits are set, i.e., LRU_REFS_FLAGS|BIT(PG_workingset), a folio is lazily
+ * promoted into the second oldest generation in the eviction path. And when
+ * folio_inc_gen() does that, it clears LRU_REFS_FLAGS so that
+ * lru_gen_inc_refs() can start over. Note that for this case, LRU_REFS_MASK is
+ * only valid when PG_referenced is set.
+ *
+ * For folios accessed multiple times through page tables, folio_update_gen()
+ * from a page table walk or lru_gen_set_refs() from a rmap walk sets
+ * PG_referenced after the accessed bit is cleared for the first time.
+ * Thereafter, those two paths set PG_workingset and promote folios to the
+ * youngest generation. Like folio_inc_gen(), folio_update_gen() also clears
+ * PG_referenced. Note that for this case, LRU_REFS_MASK is not used.
+ *
+ * For both cases above, after PG_workingset is set on a folio, it remains until
+ * this folio is either reclaimed, or "deactivated" by lru_gen_clear_refs(). It
+ * can be set again if lru_gen_test_recent() returns true upon a refault.
+ */
+#define LRU_REFS_FLAGS		(LRU_REFS_MASK | BIT(PG_referenced))
+
+struct lruvec;
+struct page_vma_mapped_walk;
+
 #ifdef CONFIG_LRU_GEN
 
 enum {
@@ -385,12 +478,11 @@ enum {
 /*
  * The youngest generation number is stored in max_seq for both anon and file
  * types as they are aged on an equal footing. The oldest generation numbers are
- * stored in min_seq[] separately for anon and file types as clean file pages
- * can be evicted regardless of swap constraints.
- *
- * Normally anon and file min_seq are in sync. But if swapping is constrained,
- * e.g., out of swap space, file min_seq is allowed to advance and leave anon
- * min_seq behind.
+ * stored in min_seq[] separately for anon and file types so that they can be
+ * incremented independently. Ideally min_seq[] are kept in sync when both anon
+ * and file types are evictable. However, to adapt to situations like extreme
+ * swappiness, they are allowed to be out of sync by at most
+ * MAX_NR_GENS-MIN_NR_GENS-1.
  *
  * The number of pages in each generation is eventually consistent and therefore
  * can be transiently negative when reset_batch_size() is pending.
@@ -410,28 +502,24 @@ struct lru_gen_folio {
 	unsigned long avg_refaulted[ANON_AND_FILE][MAX_NR_TIERS];
 	/* the exponential moving average of evicted+protected */
 	unsigned long avg_total[ANON_AND_FILE][MAX_NR_TIERS];
-	/* the first tier doesn't need protection, hence the minus one */
-	unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS - 1];
+	/* can only be modified under the LRU lock */
+	unsigned long protected[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	/* can be modified without holding the LRU lock */
 	atomic_long_t evicted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	atomic_long_t refaulted[NR_HIST_GENS][ANON_AND_FILE][MAX_NR_TIERS];
 	/* whether the multi-gen LRU is enabled */
 	bool enabled;
-#ifdef CONFIG_MEMCG
 	/* the memcg generation this lru_gen_folio belongs to */
 	u8 gen;
 	/* the list segment this lru_gen_folio belongs to */
 	u8 seg;
 	/* per-node lru_gen_folio list for global reclaim */
 	struct hlist_nulls_node list;
-#endif
 };
 
 enum {
 	MM_LEAF_TOTAL,		/* total leaf entries */
-	MM_LEAF_OLD,		/* old leaf entries */
 	MM_LEAF_YOUNG,		/* young leaf entries */
-	MM_NONLEAF_TOTAL,	/* total non-leaf entries */
 	MM_NONLEAF_FOUND,	/* non-leaf entries found in Bloom filters */
 	MM_NONLEAF_ADDED,	/* non-leaf entries added to Bloom filters */
 	NR_MM_STATS
@@ -441,7 +529,7 @@ enum {
 #define NR_BLOOM_FILTERS	2
 
 struct lru_gen_mm_state {
-	/* set to max_seq after each iteration */
+	/* synced with max_seq after each iteration */
 	unsigned long seq;
 	/* where the current iteration continues after */
 	struct list_head *head;
@@ -456,8 +544,8 @@ struct lru_gen_mm_state {
 struct lru_gen_mm_walk {
 	/* the lruvec under reclaim */
 	struct lruvec *lruvec;
-	/* unstable max_seq from lru_gen_folio */
-	unsigned long max_seq;
+	/* max_seq from lru_gen_folio: can be out of date */
+	unsigned long seq;
 	/* the next address within an mm to scan */
 	unsigned long next_addr;
 	/* to batch promoted pages */
@@ -466,15 +554,10 @@ struct lru_gen_mm_walk {
 	int mm_stats[NR_MM_STATS];
 	/* total batched items */
 	int batched;
-	bool can_swap;
+	int swappiness;
 	bool force_scan;
 };
 
-void lru_gen_init_lruvec(struct lruvec *lruvec);
-void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
-
-#ifdef CONFIG_MEMCG
-
 /*
  * For each node, memcgs are divided into two generations: the old and the
  * young. For each generation, memcgs are randomly sharded into multiple bins
@@ -487,33 +570,37 @@ void lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
  * the old generation, is incremented when all its bins become empty.
  *
  * There are four operations:
- * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its
+ * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its
  *    current generation (old or young) and updates its "seg" to "head";
- * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its
+ * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its
  *    current generation (old or young) and updates its "seg" to "tail";
- * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old
+ * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old
  *    generation, updates its "gen" to "old" and resets its "seg" to "default";
- * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the
+ * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the
  *    young generation, updates its "gen" to "young" and resets its "seg" to
  *    "default".
  *
  * The events that trigger the above operations are:
  * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD;
- * 2. The first attempt to reclaim an memcg below low, which triggers
+ * 2. The first attempt to reclaim a memcg below low, which triggers
  *    MEMCG_LRU_TAIL;
- * 3. The first attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_TAIL;
- * 4. The second attempt to reclaim an memcg below reclaimable size threshold,
- *    which triggers MEMCG_LRU_YOUNG;
- * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG;
+ * 3. The first attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_TAIL;
+ * 4. The second attempt to reclaim a memcg offlined or below reclaimable size
+ *    threshold, which triggers MEMCG_LRU_YOUNG;
+ * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG;
  * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG;
- * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD.
+ * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD.
  *
- * Note that memcg LRU only applies to global reclaim, and the round-robin
- * incrementing of their max_seq counters ensures the eventual fairness to all
- * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * Notes:
+ * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing
+ *    of their max_seq counters ensures the eventual fairness to all eligible
+ *    memcgs. For memcg reclaim, it still relies on mem_cgroup_iter().
+ * 2. There are only two valid generations: old (seq) and young (seq+1).
+ *    MEMCG_NR_GENS is set to three so that when reading the generation counter
+ *    locklessly, a stale value (seq-1) does not wraparound to young.
  */
-#define MEMCG_NR_GENS	2
+#define MEMCG_NR_GENS	3
 #define MEMCG_NR_BINS	8
 
 struct lru_gen_memcg {
@@ -528,6 +615,8 @@ struct lru_gen_memcg {
 };
 
 void lru_gen_init_pgdat(struct pglist_data *pgdat);
+void lru_gen_init_lruvec(struct lruvec *lruvec);
+bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw);
 
 void lru_gen_init_memcg(struct mem_cgroup *memcg);
 void lru_gen_exit_memcg(struct mem_cgroup *memcg);
@@ -536,19 +625,6 @@ void lru_gen_offline_memcg(struct mem_cgroup *memcg);
 void lru_gen_release_memcg(struct mem_cgroup *memcg);
 void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid);
 
-#else /* !CONFIG_MEMCG */
-
-#define MEMCG_NR_GENS	1
-
-struct lru_gen_memcg {
-};
-
-static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
-{
-}
-
-#endif /* CONFIG_MEMCG */
-
 #else /* !CONFIG_LRU_GEN */
 
 static inline void lru_gen_init_pgdat(struct pglist_data *pgdat)
@@ -559,12 +635,11 @@ static inline void lru_gen_init_lruvec(struct lruvec *lruvec)
 {
 }
 
-static inline void lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
+static inline bool lru_gen_look_around(struct page_vma_mapped_walk *pvmw)
 {
+	return false;
 }
 
-#ifdef CONFIG_MEMCG
-
 static inline void lru_gen_init_memcg(struct mem_cgroup *memcg)
 {
 }
@@ -589,8 +664,6 @@ static inline void lru_gen_soft_reclaim(struct mem_cgroup *memcg, int nid)
 {
 }
 
-#endif /* CONFIG_MEMCG */
-
 #endif /* CONFIG_LRU_GEN */
 
 struct lruvec {
@@ -613,16 +686,17 @@ struct lruvec {
 #ifdef CONFIG_LRU_GEN
 	/* evictable pages divided into generations */
 	struct lru_gen_folio		lrugen;
+#ifdef CONFIG_LRU_GEN_WALKS_MMU
 	/* to concurrently iterate lru_gen_mm_list */
 	struct lru_gen_mm_state		mm_state;
 #endif
+#endif /* CONFIG_LRU_GEN */
 #ifdef CONFIG_MEMCG
 	struct pglist_data *pgdat;
 #endif
+	struct zswap_lruvec_state zswap_lruvec_state;
 };
 
-/* Isolate unmapped pages */
-#define ISOLATE_UNMAPPED	((__force isolate_mode_t)0x2)
 /* Isolate for asynchronous migration */
 #define ISOLATE_ASYNC_MIGRATE	((__force isolate_mode_t)0x4)
 /* Isolate unevictable pages */
@@ -640,34 +714,46 @@ enum zone_watermarks {
 };
 
 /*
- * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. One additional list
- * for THP which will usually be GFP_MOVABLE. Even if it is another type,
- * it should not contribute to serious fragmentation causing THP allocation
- * failures.
+ * One per migratetype for each PAGE_ALLOC_COSTLY_ORDER. Two additional lists
+ * are added for THP. One PCP list is used by GPF_MOVABLE, and the other PCP list
+ * is used by GFP_UNMOVABLE and GFP_RECLAIMABLE.
  */
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define NR_PCP_THP 1
+#define NR_PCP_THP 2
 #else
 #define NR_PCP_THP 0
 #endif
 #define NR_LOWORDER_PCP_LISTS (MIGRATE_PCPTYPES * (PAGE_ALLOC_COSTLY_ORDER + 1))
 #define NR_PCP_LISTS (NR_LOWORDER_PCP_LISTS + NR_PCP_THP)
 
-#define min_wmark_pages(z) (z->_watermark[WMARK_MIN] + z->watermark_boost)
-#define low_wmark_pages(z) (z->_watermark[WMARK_LOW] + z->watermark_boost)
-#define high_wmark_pages(z) (z->_watermark[WMARK_HIGH] + z->watermark_boost)
-#define wmark_pages(z, i) (z->_watermark[i] + z->watermark_boost)
+/*
+ * Flags used in pcp->flags field.
+ *
+ * PCPF_PREV_FREE_HIGH_ORDER: a high-order page is freed in the
+ * previous page freeing.  To avoid to drain PCP for an accident
+ * high-order page freeing.
+ *
+ * PCPF_FREE_HIGH_BATCH: preserve "pcp->batch" pages in PCP before
+ * draining PCP for consecutive high-order pages freeing without
+ * allocation if data cache slice of CPU is large enough.  To reduce
+ * zone lock contention and keep cache-hot pages reusing.
+ */
+#define	PCPF_PREV_FREE_HIGH_ORDER	BIT(0)
+#define	PCPF_FREE_HIGH_BATCH		BIT(1)
 
-/* Fields and list protected by pagesets local_lock in page_alloc.c */
 struct per_cpu_pages {
 	spinlock_t lock;	/* Protects lists field */
 	int count;		/* number of pages in the list */
 	int high;		/* high watermark, emptying needed */
+	int high_min;		/* min high watermark */
+	int high_max;		/* max high watermark */
 	int batch;		/* chunk size for buddy add/remove */
-	short free_factor;	/* batch scaling factor during free */
+	u8 flags;		/* protected by pcp->lock */
+	u8 alloc_factor;	/* batch scaling factor during allocate */
 #ifdef CONFIG_NUMA
-	short expire;		/* When 0, remote pagesets are drained */
+	u8 expire;		/* When 0, remote pagesets are drained */
 #endif
+	short free_count;	/* consecutive free count */
 
 	/* Lists of pages, one per migrate type stored on the pcp-lists */
 	struct list_head lists[NR_PCP_LISTS];
@@ -798,6 +884,7 @@ struct zone {
 	unsigned long watermark_boost;
 
 	unsigned long nr_reserved_highatomic;
+	unsigned long nr_free_highatomic;
 
 	/*
 	 * We don't know if the memory that we're going to allocate will be
@@ -820,7 +907,8 @@ struct zone {
 	 * the high and batch values are copied to individual pagesets for
 	 * faster access
 	 */
-	int pageset_high;
+	int pageset_high_min;
+	int pageset_high_max;
 	int pageset_batch;
 
 #ifndef CONFIG_SPARSEMEM
@@ -908,7 +996,15 @@ struct zone {
 	CACHELINE_PADDING(_pad1_);
 
 	/* free areas of different sizes */
-	struct free_area	free_area[MAX_ORDER + 1];
+	struct free_area	free_area[NR_PAGE_ORDERS];
+
+#ifdef CONFIG_UNACCEPTED_MEMORY
+	/* Pages to be accepted. All pages on the list are MAX_PAGE_ORDER */
+	struct list_head	unaccepted_pages;
+
+	/* To be called once the last page in the zone is accepted */
+	struct work_struct	unaccepted_cleanup;
+#endif
 
 	/* zone flags, see below */
 	unsigned long		flags;
@@ -916,6 +1012,9 @@ struct zone {
 	/* Primarily protects free_area */
 	spinlock_t		lock;
 
+	/* Pages to be freed when next trylock succeeds */
+	struct llist_head	trylock_free_pages;
+
 	/* Write-intensive fields used by compaction and vmstats. */
 	CACHELINE_PADDING(_pad2_);
 
@@ -961,10 +1060,6 @@ struct zone {
 } ____cacheline_internodealigned_in_smp;
 
 enum pgdat_flags {
-	PGDAT_DIRTY,			/* reclaim scanning has recently found
-					 * many dirty file pages at the tail
-					 * of the LRU.
-					 */
 	PGDAT_WRITEBACK,		/* reclaim scanning has recently found
 					 * many pages under writeback
 					 */
@@ -976,9 +1071,36 @@ enum zone_flags {
 					 * Cleared when kswapd is woken.
 					 */
 	ZONE_RECLAIM_ACTIVE,		/* kswapd may be scanning the zone. */
+	ZONE_BELOW_HIGH,		/* zone is below high watermark. */
 };
 
-static inline unsigned long zone_managed_pages(struct zone *zone)
+static inline unsigned long wmark_pages(const struct zone *z,
+					enum zone_watermarks w)
+{
+	return z->_watermark[w] + z->watermark_boost;
+}
+
+static inline unsigned long min_wmark_pages(const struct zone *z)
+{
+	return wmark_pages(z, WMARK_MIN);
+}
+
+static inline unsigned long low_wmark_pages(const struct zone *z)
+{
+	return wmark_pages(z, WMARK_LOW);
+}
+
+static inline unsigned long high_wmark_pages(const struct zone *z)
+{
+	return wmark_pages(z, WMARK_HIGH);
+}
+
+static inline unsigned long promo_wmark_pages(const struct zone *z)
+{
+	return wmark_pages(z, WMARK_PROMO);
+}
+
+static inline unsigned long zone_managed_pages(const struct zone *zone)
 {
 	return (unsigned long)atomic_long_read(&zone->managed_pages);
 }
@@ -1002,12 +1124,12 @@ static inline bool zone_spans_pfn(const struct zone *zone, unsigned long pfn)
 	return zone->zone_start_pfn <= pfn && pfn < zone_end_pfn(zone);
 }
 
-static inline bool zone_is_initialized(struct zone *zone)
+static inline bool zone_is_initialized(const struct zone *zone)
 {
 	return zone->initialized;
 }
 
-static inline bool zone_is_empty(struct zone *zone)
+static inline bool zone_is_empty(const struct zone *zone)
 {
 	return zone->spanned_pages == 0;
 }
@@ -1058,21 +1180,32 @@ static inline bool zone_is_empty(struct zone *zone)
 #define KASAN_TAG_MASK		((1UL << KASAN_TAG_WIDTH) - 1)
 #define ZONEID_MASK		((1UL << ZONEID_SHIFT) - 1)
 
+static inline enum zone_type memdesc_zonenum(memdesc_flags_t flags)
+{
+	ASSERT_EXCLUSIVE_BITS(flags.f, ZONES_MASK << ZONES_PGSHIFT);
+	return (flags.f >> ZONES_PGSHIFT) & ZONES_MASK;
+}
+
 static inline enum zone_type page_zonenum(const struct page *page)
 {
-	ASSERT_EXCLUSIVE_BITS(page->flags, ZONES_MASK << ZONES_PGSHIFT);
-	return (page->flags >> ZONES_PGSHIFT) & ZONES_MASK;
+	return memdesc_zonenum(page->flags);
 }
 
 static inline enum zone_type folio_zonenum(const struct folio *folio)
 {
-	return page_zonenum(&folio->page);
+	return memdesc_zonenum(folio->flags);
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-static inline bool is_zone_device_page(const struct page *page)
+static inline bool memdesc_is_zone_device(memdesc_flags_t mdf)
 {
-	return page_zonenum(page) == ZONE_DEVICE;
+	return memdesc_zonenum(mdf) == ZONE_DEVICE;
+}
+
+static inline struct dev_pagemap *page_pgmap(const struct page *page)
+{
+	VM_WARN_ON_ONCE_PAGE(!memdesc_is_zone_device(page->flags), page);
+	return page_folio(page)->pgmap;
 }
 
 /*
@@ -1086,17 +1219,17 @@ static inline bool is_zone_device_page(const struct page *page)
 static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
 						     const struct page *b)
 {
-	if (is_zone_device_page(a) != is_zone_device_page(b))
+	if (memdesc_is_zone_device(a->flags) != memdesc_is_zone_device(b->flags))
 		return false;
-	if (!is_zone_device_page(a))
+	if (!memdesc_is_zone_device(a->flags))
 		return true;
-	return a->pgmap == b->pgmap;
+	return page_pgmap(a) == page_pgmap(b);
 }
 
 extern void memmap_init_zone_device(struct zone *, unsigned long,
 				    unsigned long, struct dev_pagemap *);
 #else
-static inline bool is_zone_device_page(const struct page *page)
+static inline bool memdesc_is_zone_device(memdesc_flags_t mdf)
 {
 	return false;
 }
@@ -1105,24 +1238,38 @@ static inline bool zone_device_pages_have_same_pgmap(const struct page *a,
 {
 	return true;
 }
+static inline struct dev_pagemap *page_pgmap(const struct page *page)
+{
+	return NULL;
+}
 #endif
 
+static inline bool is_zone_device_page(const struct page *page)
+{
+	return memdesc_is_zone_device(page->flags);
+}
+
 static inline bool folio_is_zone_device(const struct folio *folio)
 {
-	return is_zone_device_page(&folio->page);
+	return memdesc_is_zone_device(folio->flags);
 }
 
 static inline bool is_zone_movable_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_MOVABLE;
 }
+
+static inline bool folio_is_zone_movable(const struct folio *folio)
+{
+	return folio_zonenum(folio) == ZONE_MOVABLE;
+}
 #endif
 
 /*
  * Return true if [start_pfn, start_pfn + nr_pages) range has a non-empty
  * intersection with the given zone
  */
-static inline bool zone_intersects(struct zone *zone,
+static inline bool zone_intersects(const struct zone *zone,
 		unsigned long start_pfn, unsigned long nr_pages)
 {
 	if (zone_is_empty(zone))
@@ -1289,7 +1436,7 @@ typedef struct pglist_data {
 	int kswapd_order;
 	enum zone_type kswapd_highest_zoneidx;
 
-	int kswapd_failures;		/* Number of 'reclaimed == 0' runs */
+	atomic_t kswapd_failures;	/* Number of 'reclaimed == 0' runs */
 
 #ifdef CONFIG_COMPACTION
 	int kcompactd_max_order;
@@ -1395,8 +1542,6 @@ bool __zone_watermark_ok(struct zone *z, unsigned int order, unsigned long mark,
 bool zone_watermark_ok(struct zone *z, unsigned int order,
 		unsigned long mark, int highest_zoneidx,
 		unsigned int alloc_flags);
-bool zone_watermark_ok_safe(struct zone *z, unsigned int order,
-		unsigned long mark, int highest_zoneidx);
 /*
  * Memory initialization context, use to differentiate memory added by
  * the platform statically or via memory hotplug interface.
@@ -1432,12 +1577,12 @@ static inline int local_memory_node(int node_id) { return node_id; };
 #define zone_idx(zone)		((zone) - (zone)->zone_pgdat->node_zones)
 
 #ifdef CONFIG_ZONE_DEVICE
-static inline bool zone_is_zone_device(struct zone *zone)
+static inline bool zone_is_zone_device(const struct zone *zone)
 {
 	return zone_idx(zone) == ZONE_DEVICE;
 }
 #else
-static inline bool zone_is_zone_device(struct zone *zone)
+static inline bool zone_is_zone_device(const struct zone *zone)
 {
 	return false;
 }
@@ -1449,19 +1594,19 @@ static inline bool zone_is_zone_device(struct zone *zone)
  * populated_zone(). If the whole zone is reserved then we can easily
  * end up with populated_zone() && !managed_zone().
  */
-static inline bool managed_zone(struct zone *zone)
+static inline bool managed_zone(const struct zone *zone)
 {
 	return zone_managed_pages(zone);
 }
 
 /* Returns true if a zone has memory */
-static inline bool populated_zone(struct zone *zone)
+static inline bool populated_zone(const struct zone *zone)
 {
 	return zone->present_pages;
 }
 
 #ifdef CONFIG_NUMA
-static inline int zone_to_nid(struct zone *zone)
+static inline int zone_to_nid(const struct zone *zone)
 {
 	return zone->node;
 }
@@ -1471,7 +1616,7 @@ static inline void zone_set_nid(struct zone *zone, int nid)
 	zone->node = nid;
 }
 #else
-static inline int zone_to_nid(struct zone *zone)
+static inline int zone_to_nid(const struct zone *zone)
 {
 	return 0;
 }
@@ -1498,7 +1643,7 @@ static inline int is_highmem_idx(enum zone_type idx)
  * @zone: pointer to struct zone variable
  * Return: 1 for a highmem zone, 0 otherwise
  */
-static inline int is_highmem(struct zone *zone)
+static inline int is_highmem(const struct zone *zone)
 {
 	return is_highmem_idx(zone_idx(zone));
 }
@@ -1564,12 +1709,12 @@ static inline struct zone *zonelist_zone(struct zoneref *zoneref)
 	return zoneref->zone;
 }
 
-static inline int zonelist_zone_idx(struct zoneref *zoneref)
+static inline int zonelist_zone_idx(const struct zoneref *zoneref)
 {
 	return zoneref->zone_idx;
 }
 
-static inline int zonelist_node_idx(struct zoneref *zoneref)
+static inline int zonelist_node_idx(const struct zoneref *zoneref)
 {
 	return zone_to_nid(zoneref->zone);
 }
@@ -1645,7 +1790,7 @@ static inline struct zoneref *first_zones_zonelist(struct zonelist *zonelist,
 			zone = zonelist_zone(z))
 
 #define for_next_zone_zonelist_nodemask(zone, z, highidx, nodemask) \
-	for (zone = z->zone;	\
+	for (zone = zonelist_zone(z);	\
 		zone;							\
 		z = next_zones_zonelist(++z, highidx, nodemask),	\
 			zone = zonelist_zone(z))
@@ -1681,7 +1826,7 @@ static inline bool movable_only_nodes(nodemask_t *nodes)
 	nid = first_node(*nodes);
 	zonelist = &NODE_DATA(nid)->node_zonelists[ZONELIST_FALLBACK];
 	z = first_zones_zonelist(zonelist, ZONE_NORMAL,	nodes);
-	return (!z->zone) ? true : false;
+	return (!zonelist_zone(z)) ? true : false;
 }
 
 
@@ -1710,8 +1855,8 @@ static inline bool movable_only_nodes(nodemask_t *nodes)
 #define SECTION_BLOCKFLAGS_BITS \
 	((1UL << (PFN_SECTION_SHIFT - pageblock_order)) * NR_PAGEBLOCK_BITS)
 
-#if (MAX_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
-#error Allocator MAX_ORDER exceeds SECTION_SIZE
+#if (MAX_PAGE_ORDER + PAGE_SHIFT) > SECTION_SIZE_BITS
+#error Allocator MAX_PAGE_ORDER exceeds SECTION_SIZE
 #endif
 
 static inline unsigned long pfn_to_section_nr(unsigned long pfn)
@@ -1743,6 +1888,7 @@ static inline unsigned long section_nr_to_pfn(unsigned long sec)
 #define SUBSECTION_ALIGN_DOWN(pfn) ((pfn) & PAGE_SUBSECTION_MASK)
 
 struct mem_section_usage {
+	struct rcu_head rcu;
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 	DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION);
 #endif
@@ -1845,6 +1991,9 @@ enum {
 #ifdef CONFIG_ZONE_DEVICE
 	SECTION_TAINT_ZONE_DEVICE_BIT,
 #endif
+#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
+	SECTION_IS_VMEMMAP_PREINIT_BIT,
+#endif
 	SECTION_MAP_LAST_BIT,
 };
 
@@ -1855,6 +2004,9 @@ enum {
 #ifdef CONFIG_ZONE_DEVICE
 #define SECTION_TAINT_ZONE_DEVICE	BIT(SECTION_TAINT_ZONE_DEVICE_BIT)
 #endif
+#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
+#define SECTION_IS_VMEMMAP_PREINIT	BIT(SECTION_IS_VMEMMAP_PREINIT_BIT)
+#endif
 #define SECTION_MAP_MASK		(~(BIT(SECTION_MAP_LAST_BIT) - 1))
 #define SECTION_NID_SHIFT		SECTION_MAP_LAST_BIT
 
@@ -1865,7 +2017,7 @@ static inline struct page *__section_mem_map_addr(struct mem_section *section)
 	return (struct page *)map;
 }
 
-static inline int present_section(struct mem_section *section)
+static inline int present_section(const struct mem_section *section)
 {
 	return (section && (section->section_mem_map & SECTION_MARKED_PRESENT));
 }
@@ -1875,12 +2027,12 @@ static inline int present_section_nr(unsigned long nr)
 	return present_section(__nr_to_section(nr));
 }
 
-static inline int valid_section(struct mem_section *section)
+static inline int valid_section(const struct mem_section *section)
 {
 	return (section && (section->section_mem_map & SECTION_HAS_MEM_MAP));
 }
 
-static inline int early_section(struct mem_section *section)
+static inline int early_section(const struct mem_section *section)
 {
 	return (section && (section->section_mem_map & SECTION_IS_EARLY));
 }
@@ -1890,25 +2042,49 @@ static inline int valid_section_nr(unsigned long nr)
 	return valid_section(__nr_to_section(nr));
 }
 
-static inline int online_section(struct mem_section *section)
+static inline int online_section(const struct mem_section *section)
 {
 	return (section && (section->section_mem_map & SECTION_IS_ONLINE));
 }
 
 #ifdef CONFIG_ZONE_DEVICE
-static inline int online_device_section(struct mem_section *section)
+static inline int online_device_section(const struct mem_section *section)
 {
 	unsigned long flags = SECTION_IS_ONLINE | SECTION_TAINT_ZONE_DEVICE;
 
 	return section && ((section->section_mem_map & flags) == flags);
 }
 #else
-static inline int online_device_section(struct mem_section *section)
+static inline int online_device_section(const struct mem_section *section)
 {
 	return 0;
 }
 #endif
 
+#ifdef CONFIG_SPARSEMEM_VMEMMAP_PREINIT
+static inline int preinited_vmemmap_section(const struct mem_section *section)
+{
+	return (section &&
+		(section->section_mem_map & SECTION_IS_VMEMMAP_PREINIT));
+}
+
+void sparse_vmemmap_init_nid_early(int nid);
+void sparse_vmemmap_init_nid_late(int nid);
+
+#else
+static inline int preinited_vmemmap_section(const struct mem_section *section)
+{
+	return 0;
+}
+static inline void sparse_vmemmap_init_nid_early(int nid)
+{
+}
+
+static inline void sparse_vmemmap_init_nid_late(int nid)
+{
+}
+#endif
+
 static inline int online_section_nr(unsigned long nr)
 {
 	return online_section(__nr_to_section(nr));
@@ -1935,16 +2111,46 @@ static inline int subsection_map_index(unsigned long pfn)
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	int idx = subsection_map_index(pfn);
+	struct mem_section_usage *usage = READ_ONCE(ms->usage);
+
+	return usage ? test_bit(idx, usage->subsection_map) : 0;
+}
+
+static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn)
+{
+	struct mem_section_usage *usage = READ_ONCE(ms->usage);
+	int idx = subsection_map_index(*pfn);
+	unsigned long bit;
 
-	return test_bit(idx, ms->usage->subsection_map);
+	if (!usage)
+		return false;
+
+	if (test_bit(idx, usage->subsection_map))
+		return true;
+
+	/* Find the next subsection that exists */
+	bit = find_next_bit(usage->subsection_map, SUBSECTIONS_PER_SECTION, idx);
+	if (bit == SUBSECTIONS_PER_SECTION)
+		return false;
+
+	*pfn = (*pfn & PAGE_SECTION_MASK) + (bit * PAGES_PER_SUBSECTION);
+	return true;
 }
 #else
 static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 {
 	return 1;
 }
+
+static inline bool pfn_section_first_valid(struct mem_section *ms, unsigned long *pfn)
+{
+	return true;
+}
 #endif
 
+void sparse_init_early_section(int nid, struct page *map, unsigned long pnum,
+			       unsigned long flags);
+
 #ifndef CONFIG_HAVE_ARCH_PFN_VALID
 /**
  * pfn_valid - check if there is a valid memory map entry for a PFN
@@ -1960,6 +2166,7 @@ static inline int pfn_section_valid(struct mem_section *ms, unsigned long pfn)
 static inline int pfn_valid(unsigned long pfn)
 {
 	struct mem_section *ms;
+	int ret;
 
 	/*
 	 * Ensure the upper PAGE_SHIFT bits are clear in the
@@ -1973,14 +2180,72 @@ static inline int pfn_valid(unsigned long pfn)
 	if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS)
 		return 0;
 	ms = __pfn_to_section(pfn);
-	if (!valid_section(ms))
+	rcu_read_lock_sched();
+	if (!valid_section(ms)) {
+		rcu_read_unlock_sched();
 		return 0;
+	}
 	/*
 	 * Traditionally early sections always returned pfn_valid() for
 	 * the entire section-sized span.
 	 */
-	return early_section(ms) || pfn_section_valid(ms, pfn);
+	ret = early_section(ms) || pfn_section_valid(ms, pfn);
+	rcu_read_unlock_sched();
+
+	return ret;
 }
+
+/* Returns end_pfn or higher if no valid PFN remaining in range */
+static inline unsigned long first_valid_pfn(unsigned long pfn, unsigned long end_pfn)
+{
+	unsigned long nr = pfn_to_section_nr(pfn);
+
+	rcu_read_lock_sched();
+
+	while (nr <= __highest_present_section_nr && pfn < end_pfn) {
+		struct mem_section *ms = __pfn_to_section(pfn);
+
+		if (valid_section(ms) &&
+		    (early_section(ms) || pfn_section_first_valid(ms, &pfn))) {
+			rcu_read_unlock_sched();
+			return pfn;
+		}
+
+		/* Nothing left in this section? Skip to next section */
+		nr++;
+		pfn = section_nr_to_pfn(nr);
+	}
+
+	rcu_read_unlock_sched();
+	return end_pfn;
+}
+
+static inline unsigned long next_valid_pfn(unsigned long pfn, unsigned long end_pfn)
+{
+	pfn++;
+
+	if (pfn >= end_pfn)
+		return end_pfn;
+
+	/*
+	 * Either every PFN within the section (or subsection for VMEMMAP) is
+	 * valid, or none of them are. So there's no point repeating the check
+	 * for every PFN; only call first_valid_pfn() again when crossing a
+	 * (sub)section boundary (i.e. !(pfn & ~PAGE_{SUB,}SECTION_MASK)).
+	 */
+	if (pfn & ~(IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP) ?
+		   PAGE_SUBSECTION_MASK : PAGE_SECTION_MASK))
+		return pfn;
+
+	return first_valid_pfn(pfn, end_pfn);
+}
+
+
+#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn)			\
+	for ((_pfn) = first_valid_pfn((_start_pfn), (_end_pfn));	\
+	     (_pfn) < (_end_pfn);					\
+	     (_pfn) = next_valid_pfn((_pfn), (_end_pfn)))
+
 #endif
 
 static inline int pfn_in_present_section(unsigned long pfn)
@@ -2000,6 +2265,11 @@ static inline unsigned long next_present_section_nr(unsigned long section_nr)
 	return -1;
 }
 
+#define for_each_present_section_nr(start, section_nr)		\
+	for (section_nr = next_present_section_nr(start - 1);	\
+	     section_nr != -1;					\
+	     section_nr = next_present_section_nr(section_nr))
+
 /*
  * These are _only_ used during initialisation, therefore they
  * can use __initdata ...  They could have names to indicate
@@ -2019,10 +2289,22 @@ void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
 #define sparse_index_init(_sec, _nid)  do {} while (0)
+#define sparse_vmemmap_init_nid_early(_nid, _use) do {} while (0)
+#define sparse_vmemmap_init_nid_late(_nid) do {} while (0)
 #define pfn_in_present_section pfn_valid
 #define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
+/*
+ * Fallback case for when the architecture provides its own pfn_valid() but
+ * not a corresponding for_each_valid_pfn().
+ */
+#ifndef for_each_valid_pfn
+#define for_each_valid_pfn(_pfn, _start_pfn, _end_pfn)			\
+	for ((_pfn) = (_start_pfn); (_pfn) < (_end_pfn); (_pfn)++)	\
+		if (pfn_valid(_pfn))
+#endif
+
 #endif /* !__GENERATING_BOUNDS.H */
 #endif /* !__ASSEMBLY__ */
 #endif /* _LINUX_MMZONE_H */
diff --git a/include/linux/mnt_idmapping.h b/include/linux/mnt_idmapping.h
index 057c89867aa2..e71a6070a8f8 100644
--- a/include/linux/mnt_idmapping.h
+++ b/include/linux/mnt_idmapping.h
@@ -9,6 +9,7 @@ struct mnt_idmap;
 struct user_namespace;
 
 extern struct mnt_idmap nop_mnt_idmap;
+extern struct mnt_idmap invalid_mnt_idmap;
 extern struct user_namespace init_user_ns;
 
 typedef struct {
@@ -24,6 +25,11 @@ static_assert(sizeof(vfsgid_t) == sizeof(kgid_t));
 static_assert(offsetof(vfsuid_t, val) == offsetof(kuid_t, val));
 static_assert(offsetof(vfsgid_t, val) == offsetof(kgid_t, val));
 
+static inline bool is_valid_mnt_idmap(const struct mnt_idmap *idmap)
+{
+	return idmap != &nop_mnt_idmap && idmap != &invalid_mnt_idmap;
+}
+
 #ifdef CONFIG_MULTIUSER
 static inline uid_t __vfsuid_val(vfsuid_t uid)
 {
@@ -115,6 +121,9 @@ static inline bool vfsgid_eq_kgid(vfsgid_t vfsgid, kgid_t kgid)
 
 int vfsgid_in_group_p(vfsgid_t vfsgid);
 
+struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap);
+void mnt_idmap_put(struct mnt_idmap *idmap);
+
 vfsuid_t make_vfsuid(struct mnt_idmap *idmap,
 		     struct user_namespace *fs_userns, kuid_t kuid);
 
@@ -241,7 +250,4 @@ static inline kgid_t mapped_fsgid(struct mnt_idmap *idmap,
 	return from_vfsgid(idmap, fs_userns, VFSGIDT_INIT(current_fsgid()));
 }
 
-bool check_fsmapping(const struct mnt_idmap *idmap,
-		     const struct super_block *sb);
-
 #endif /* _LINUX_MNT_IDMAPPING_H */
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 8f882f5881e8..0acd1089d149 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -3,14 +3,20 @@
 #define _NAMESPACE_H_
 #ifdef __KERNEL__
 
+#include <linux/cleanup.h>
+#include <linux/err.h>
+
 struct mnt_namespace;
 struct fs_struct;
 struct user_namespace;
 struct ns_common;
 
-extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
+extern struct mnt_namespace init_mnt_ns;
+
+extern struct mnt_namespace *copy_mnt_ns(u64, struct mnt_namespace *,
 		struct user_namespace *, struct fs_struct *);
 extern void put_mnt_ns(struct mnt_namespace *ns);
+DEFINE_FREE(put_mnt_ns, struct mnt_namespace *, if (!IS_ERR_OR_NULL(_T)) put_mnt_ns(_T))
 extern struct ns_common *from_mnt_ns(struct mnt_namespace *);
 
 extern const struct file_operations proc_mounts_operations;
diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h
index ccaaeda792c0..24eb5a88a5c5 100644
--- a/include/linux/mod_devicetable.h
+++ b/include/linux/mod_devicetable.h
@@ -221,6 +221,19 @@ struct acpi_device_id {
 	__u32 cls_msk;
 };
 
+/**
+ * ACPI_DEVICE_CLASS - macro used to describe an ACPI device with
+ * the PCI-defined class-code information
+ *
+ * @_cls : the class, subclass, prog-if triple for this device
+ * @_msk : the class mask for this device
+ *
+ * This macro is used to create a struct acpi_device_id that matches a
+ * specific PCI class. The .id and .driver_data fields will be left
+ * initialized with the default value.
+ */
+#define ACPI_DEVICE_CLASS(_cls, _msk)	.cls = (_cls), .cls_msk = (_msk),
+
 #define PNP_ID_LEN	8
 #define PNP_MAX_DEVICES	8
 
@@ -327,7 +340,7 @@ struct pcmcia_device_id {
 #define INPUT_DEVICE_ID_LED_MAX		0x0f
 #define INPUT_DEVICE_ID_SND_MAX		0x07
 #define INPUT_DEVICE_ID_FF_MAX		0x7f
-#define INPUT_DEVICE_ID_SW_MAX		0x10
+#define INPUT_DEVICE_ID_SW_MAX		0x11
 #define INPUT_DEVICE_ID_PROP_MAX	0x1f
 
 #define INPUT_DEVICE_ID_MATCH_BUS	1
@@ -588,7 +601,7 @@ struct dmi_system_id {
 #define DMI_MATCH(a, b)	{ .slot = a, .substr = b }
 #define DMI_EXACT_MATCH(a, b)	{ .slot = a, .substr = b, .exact_match = 1 }
 
-#define PLATFORM_NAME_SIZE	20
+#define PLATFORM_NAME_SIZE	24
 #define PLATFORM_MODULE_PREFIX	"platform:"
 
 struct platform_device_id {
@@ -677,6 +690,9 @@ struct x86_cpu_id {
 	__u16 model;
 	__u16 steppings;
 	__u16 feature;	/* bit index */
+	/* Solely for kernel-internal use: DO NOT EXPORT to userspace! */
+	__u16 flags;
+	__u8  type;
 	kernel_ulong_t driver_data;
 };
 
@@ -685,7 +701,10 @@ struct x86_cpu_id {
 #define X86_FAMILY_ANY 0
 #define X86_MODEL_ANY  0
 #define X86_STEPPING_ANY 0
+#define X86_STEP_MIN 0
+#define X86_STEP_MAX 0xf
 #define X86_FEATURE_ANY 0	/* Same as FPU, you can't test for that */
+#define X86_CPU_TYPE_ANY 0
 
 /*
  * Generic table type for matching CPU features.
@@ -848,7 +867,7 @@ struct mhi_device_id {
 	kernel_ulong_t driver_data;
 };
 
-#define AUXILIARY_NAME_SIZE 32
+#define AUXILIARY_NAME_SIZE 40
 #define AUXILIARY_MODULE_PREFIX "auxiliary:"
 
 struct auxiliary_device_id {
@@ -912,10 +931,22 @@ struct ishtp_device_id {
 	kernel_ulong_t driver_data;
 };
 
+#define CDX_ANY_ID (0xFFFF)
+
+enum {
+	CDX_ID_F_VFIO_DRIVER_OVERRIDE = 1,
+};
+
 /**
  * struct cdx_device_id - CDX device identifier
  * @vendor: Vendor ID
  * @device: Device ID
+ * @subvendor: Subsystem vendor ID (or CDX_ANY_ID)
+ * @subdevice: Subsystem device ID (or CDX_ANY_ID)
+ * @class: Device class
+ *         Most drivers do not need to specify class/class_mask
+ *         as vendor/device is normally sufficient.
+ * @class_mask: Limit which sub-fields of the class field are compared.
  * @override_only: Match only when dev->driver_override is this driver.
  *
  * Type of entries in the "device Id" table for CDX devices supported by
@@ -924,7 +955,25 @@ struct ishtp_device_id {
 struct cdx_device_id {
 	__u16 vendor;
 	__u16 device;
+	__u16 subvendor;
+	__u16 subdevice;
+	__u32 class;
+	__u32 class_mask;
 	__u32 override_only;
 };
 
+struct vchiq_device_id {
+	char name[32];
+};
+
+/**
+ * struct coreboot_device_id - Identifies a coreboot table entry
+ * @tag: tag ID
+ * @driver_data: driver specific data
+ */
+struct coreboot_device_id {
+	__u32 tag;
+	kernel_ulong_t driver_data;
+};
+
 #endif /* LINUX_MOD_DEVICETABLE_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index 9e56763dff81..d80c3ea57472 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -14,6 +14,7 @@
 #include <linux/buildid.h>
 #include <linux/compiler.h>
 #include <linux/cache.h>
+#include <linux/cleanup.h>
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/elf.h>
@@ -32,7 +33,7 @@
 #include <linux/percpu.h>
 #include <asm/module.h>
 
-#define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
+#define MODULE_NAME_LEN __MODULE_NAME_LEN
 
 struct modversion_info {
 	unsigned long crc;
@@ -52,9 +53,9 @@ struct module_kobject {
 
 struct module_attribute {
 	struct attribute attr;
-	ssize_t (*show)(struct module_attribute *, struct module_kobject *,
+	ssize_t (*show)(const struct module_attribute *, struct module_kobject *,
 			char *);
-	ssize_t (*store)(struct module_attribute *, struct module_kobject *,
+	ssize_t (*store)(const struct module_attribute *, struct module_kobject *,
 			 const char *, size_t count);
 	void (*setup)(struct module *, const char *);
 	int (*test)(struct module *);
@@ -67,10 +68,10 @@ struct module_version_attribute {
 	const char *version;
 };
 
-extern ssize_t __modver_version_show(struct module_attribute *,
+extern ssize_t __modver_version_show(const struct module_attribute *,
 				     struct module_kobject *, char *);
 
-extern struct module_attribute module_uevent;
+extern const struct module_attribute module_uevent;
 
 /* These are either module local, or the kernel's dummy ones. */
 extern int init_module(void);
@@ -162,8 +163,7 @@ extern void cleanup_module(void);
 #define __INITRODATA_OR_MODULE __INITRODATA
 #endif /*CONFIG_MODULES*/
 
-/* Generic info of form tag = "info" */
-#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
+struct module_kobject *lookup_or_create_module_kobject(const char *name);
 
 /* For userspace: you can also call me... */
 #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias)
@@ -174,6 +174,12 @@ extern void cleanup_module(void);
 #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep)
 
 /*
+ * Weak module dependencies. See man modprobe.d for details.
+ * Example: MODULE_WEAKDEP("module-foo")
+ */
+#define MODULE_WEAKDEP(_weakdep) MODULE_INFO(weakdep, _weakdep)
+
+/*
  * MODULE_FILE is used for generating modules.builtin
  * So, make it no-op when this is being built as a module
  */
@@ -238,14 +244,23 @@ extern void cleanup_module(void);
 /* What your module does. */
 #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description)
 
-#ifdef MODULE
+/*
+ * Format: __mod_device_table__kmod_<modname>__<type>__<name>
+ * Parts of the string `__kmod_` and `__` are used as delimiters when parsing
+ * a symbol in file2alias.c
+ */
+#define __mod_device_table(type, name)	\
+	__PASTE(__mod_device_table__,	\
+	__PASTE(kmod_,			\
+	__PASTE(__KBUILD_MODNAME,	\
+	__PASTE(__,			\
+	__PASTE(type,			\
+	__PASTE(__, name))))))
+
 /* Creates an alias so file2alias.c can find device table. */
 #define MODULE_DEVICE_TABLE(type, name)					\
-extern typeof(name) __mod_##type##__##name##_device_table		\
-  __attribute__ ((unused, alias(__stringify(name))))
-#else  /* !MODULE */
-#define MODULE_DEVICE_TABLE(type, name)
-#endif
+static typeof(name) __mod_device_table(type, name)			\
+  __attribute__ ((used, alias(__stringify(name))))
 
 /* Version of form [<epoch>:]<version>[-<extra-version>].
  * Or for CVS/RCS ID version, everything but the number is stripped.
@@ -269,7 +284,7 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
 #else
 #define MODULE_VERSION(_version)					\
 	MODULE_INFO(version, _version);					\
-	static struct module_version_attribute __modver_attr		\
+	static const struct module_version_attribute __modver_attr	\
 		__used __section("__modver")				\
 		__aligned(__alignof__(struct module_version_attribute)) \
 		= {							\
@@ -290,25 +305,10 @@ extern typeof(name) __mod_##type##__##name##_device_table		\
  * files require multiple MODULE_FIRMWARE() specifiers */
 #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware)
 
-#define MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, __stringify(ns))
+#define MODULE_IMPORT_NS(ns)	MODULE_INFO(import_ns, ns)
 
 struct notifier_block;
 
-#ifdef CONFIG_MODULES
-
-extern int modules_disabled; /* for sysctl */
-/* Get/put a kernel symbol (calls must be symmetric) */
-void *__symbol_get(const char *symbol);
-void *__symbol_get_gpl(const char *symbol);
-#define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x))))
-
-/* modules using other modules: kdb wants to see this. */
-struct module_use {
-	struct list_head source_list;
-	struct list_head target_list;
-	struct module *source, *target;
-};
-
 enum module_state {
 	MODULE_STATE_LIVE,	/* Normal state. */
 	MODULE_STATE_COMING,	/* Full formed, running module_init. */
@@ -361,6 +361,7 @@ enum mod_mem_type {
 
 struct module_memory {
 	void *base;
+	bool is_rox;
 	unsigned int size;
 
 #ifdef CONFIG_MODULES_TREE_LOOKUP
@@ -422,7 +423,7 @@ struct module {
 
 	/* Exported symbols */
 	const struct kernel_symbol *syms;
-	const s32 *crcs;
+	const u32 *crcs;
 	unsigned int num_syms;
 
 #ifdef CONFIG_ARCH_USES_CFI_TRAPS
@@ -440,7 +441,7 @@ struct module {
 	/* GPL-only exported symbols. */
 	unsigned int num_gpl_syms;
 	const struct kernel_symbol *gpl_syms;
-	const s32 *gpl_crcs;
+	const u32 *gpl_crcs;
 	bool using_gplonly_symbols;
 
 #ifdef CONFIG_MODULE_SIG
@@ -509,7 +510,9 @@ struct module {
 #endif
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 	unsigned int btf_data_size;
+	unsigned int btf_base_data_size;
 	void *btf_data;
+	void *btf_base_data;
 #endif
 #ifdef CONFIG_JUMP_LABEL
 	struct jump_entry *jump_entries;
@@ -525,7 +528,7 @@ struct module {
 	struct trace_eval_map **trace_evals;
 	unsigned int num_trace_evals;
 #endif
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned int num_ftrace_callsites;
 	unsigned long *ftrace_callsites;
 #endif
@@ -540,6 +543,8 @@ struct module {
 	struct static_call_site *static_call_sites;
 #endif
 #if IS_ENABLED(CONFIG_KUNIT)
+	int num_kunit_init_suites;
+	struct kunit_suite **kunit_init_suites;
 	int num_kunit_suites;
 	struct kunit_suite **kunit_suites;
 #endif
@@ -588,6 +593,16 @@ struct module {
 #define MODULE_ARCH_INIT {}
 #endif
 
+#ifdef CONFIG_MODULES
+
+/* Get/put a kernel symbol (calls must be symmetric) */
+void *__symbol_get(const char *symbol);
+void *__symbol_get_gpl(const char *symbol);
+#define symbol_get(x)	({ \
+	static const char __notrim[] \
+		__used __section(".no_trim_symbol") = __stringify(x); \
+	(typeof(&x))(__symbol_get(__stringify(x))); })
+
 #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE
 static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym)
 {
@@ -603,6 +618,11 @@ static inline bool module_is_live(struct module *mod)
 	return mod->state != MODULE_STATE_GOING;
 }
 
+static inline bool module_is_coming(struct module *mod)
+{
+        return mod->state == MODULE_STATE_COMING;
+}
+
 struct module *__module_text_address(unsigned long addr);
 struct module *__module_address(unsigned long addr);
 bool is_module_address(unsigned long addr);
@@ -646,7 +666,7 @@ static inline bool within_module(unsigned long addr, const struct module *mod)
 	return within_module_init(addr, mod) || within_module_core(addr, mod);
 }
 
-/* Search for module by name: must be in a RCU-sched critical section. */
+/* Search for module by name: must be in a RCU critical section. */
 struct module *find_module(const char *name);
 
 extern void __noreturn __module_put_and_kthread_exit(struct module *mod,
@@ -668,7 +688,7 @@ extern void __module_get(struct module *module);
  * @module: the module we should check for
  *
  * Only try to get a module reference count if the module is not being removed.
- * This call will fail if the module is already being removed.
+ * This call will fail if the module is in the process of being removed.
  *
  * Care must also be taken to ensure the module exists and is alive prior to
  * usage of this call. This can be gauranteed through two means:
@@ -752,6 +772,8 @@ static inline bool is_livepatch_module(struct module *mod)
 
 void set_module_sig_enforced(void);
 
+void module_for_each_mod(int(*func)(struct module *mod, void *data), void *data);
+
 #else /* !CONFIG_MODULES... */
 
 static inline struct module *__module_address(unsigned long addr)
@@ -855,6 +877,14 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr)
 	return ptr;
 }
 
+static inline bool module_is_coming(struct module *mod)
+{
+	return false;
+}
+
+static inline void module_for_each_mod(int(*func)(struct module *mod, void *data), void *data)
+{
+}
 #endif /* CONFIG_MODULES */
 
 #ifdef CONFIG_SYSFS
@@ -883,7 +913,7 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr,
 static inline void module_bug_cleanup(struct module *mod) {}
 #endif	/* CONFIG_GENERIC_BUG */
 
-#ifdef CONFIG_RETPOLINE
+#ifdef CONFIG_MITIGATION_RETPOLINE
 extern bool retpoline_module_ok(bool has_retpoline);
 #else
 static inline bool retpoline_module_ok(bool has_retpoline)
@@ -920,11 +950,11 @@ int module_kallsyms_on_each_symbol(const char *modname,
  * least KSYM_NAME_LEN long: a pointer to namebuf is returned if
  * found, otherwise NULL.
  */
-const char *module_address_lookup(unsigned long addr,
-				  unsigned long *symbolsize,
-				  unsigned long *offset,
-				  char **modname, const unsigned char **modbuildid,
-				  char *namebuf);
+int module_address_lookup(unsigned long addr,
+			  unsigned long *symbolsize,
+			  unsigned long *offset,
+			  char **modname, const unsigned char **modbuildid,
+			  char *namebuf);
 int lookup_module_symbol_name(unsigned long addr, char *symname);
 int lookup_module_symbol_attrs(unsigned long addr,
 			       unsigned long *size,
@@ -953,14 +983,14 @@ static inline int module_kallsyms_on_each_symbol(const char *modname,
 }
 
 /* For kallsyms to ask for address resolution.  NULL means not found. */
-static inline const char *module_address_lookup(unsigned long addr,
+static inline int module_address_lookup(unsigned long addr,
 						unsigned long *symbolsize,
 						unsigned long *offset,
 						char **modname,
 						const unsigned char **modbuildid,
 						char *namebuf)
 {
-	return NULL;
+	return 0;
 }
 
 static inline int lookup_module_symbol_name(unsigned long addr, char *symname)
@@ -968,15 +998,6 @@ static inline int lookup_module_symbol_name(unsigned long addr, char *symname)
 	return -ERANGE;
 }
 
-static inline int lookup_module_symbol_attrs(unsigned long addr,
-					     unsigned long *size,
-					     unsigned long *offset,
-					     char *modname,
-					     char *name)
-{
-	return -ERANGE;
-}
-
 static inline int module_get_kallsym(unsigned int symnum, unsigned long *value,
 				     char *type, char *name,
 				     char *module_name, int *exported)
@@ -997,4 +1018,7 @@ static inline unsigned long find_kallsyms_symbol_value(struct module *mod,
 
 #endif  /* CONFIG_MODULES && CONFIG_KALLSYMS */
 
+/* Define __free(module_put) macro for struct module *. */
+DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T))
+
 #endif /* _LINUX_MODULE_H */
diff --git a/include/linux/module_symbol.h b/include/linux/module_symbol.h
index 7ace7ba30203..77c9895b9ddb 100644
--- a/include/linux/module_symbol.h
+++ b/include/linux/module_symbol.h
@@ -3,15 +3,13 @@
 #define _LINUX_MODULE_SYMBOL_H
 
 /* This ignores the intensely annoying "mapping symbols" found in ELF files. */
-static inline int is_mapping_symbol(const char *str)
+static inline bool is_mapping_symbol(const char *str)
 {
 	if (str[0] == '.' && str[1] == 'L')
 		return true;
 	if (str[0] == 'L' && str[1] == '0')
 		return true;
-	return str[0] == '$' &&
-	       (str[1] == 'a' || str[1] == 'd' || str[1] == 't' || str[1] == 'x')
-	       && (str[2] == '\0' || str[2] == '.');
+	return str[0] == '$';
 }
 
 #endif /* _LINUX_MODULE_SYMBOL_H */
diff --git a/include/linux/moduleloader.h b/include/linux/moduleloader.h
index 03be088fb439..e395461d59e5 100644
--- a/include/linux/moduleloader.h
+++ b/include/linux/moduleloader.h
@@ -25,13 +25,6 @@ int module_frob_arch_sections(Elf_Ehdr *hdr,
 /* Additional bytes needed by arch in front of individual sections */
 unsigned int arch_mod_section_prepend(struct module *mod, unsigned int section);
 
-/* Allocator used for allocating struct module, core sections and init
-   sections.  Returns NULL on failure. */
-void *module_alloc(unsigned long size);
-
-/* Free memory returned from module_alloc. */
-void module_memfree(void *module_region);
-
 /* Determines if the section name is an init section (that is only used during
  * module loading).
  */
@@ -42,6 +35,11 @@ bool module_init_section(const char *name);
  */
 bool module_exit_section(const char *name);
 
+/* Describes whether within_module_init() will consider this an init section
+ * or not. This behaviour changes with CONFIG_MODULE_UNLOAD.
+ */
+bool module_init_layout_section(const char *sname);
+
 /*
  * Apply the given relocation to the (simplified) ELF.  Return -error
  * or 0.
@@ -110,18 +108,18 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    const Elf_Shdr *sechdrs,
 		    struct module *mod);
 
+#ifdef CONFIG_MODULES
+void flush_module_init_free_work(void);
+#else
+static inline void flush_module_init_free_work(void)
+{
+}
+#endif
+
 /* Any cleanup needed when module leaves. */
 void module_arch_cleanup(struct module *mod);
 
 /* Any cleanup before freeing mod->module_init */
 void module_arch_freeing_init(struct module *mod);
 
-#if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \
-		!defined(CONFIG_KASAN_VMALLOC)
-#include <linux/kasan.h>
-#define MODULE_ALIGN (PAGE_SIZE << KASAN_SHADOW_SCALE_SHIFT)
-#else
-#define MODULE_ALIGN PAGE_SIZE
-#endif
-
 #endif
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 962cd41a2cb5..915f32f7d888 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -6,6 +6,13 @@
 #include <linux/stringify.h>
 #include <linux/kernel.h>
 
+/*
+ * The maximum module name length, including the NUL byte.
+ * Chosen so that structs with an unsigned long line up, specifically
+ * modversion_info.
+ */
+#define __MODULE_NAME_LEN (64 - sizeof(unsigned long))
+
 /* You can override this manually, but generally this should match the
    module name. */
 #ifdef MODULE
@@ -17,21 +24,22 @@
 #define __MODULE_INFO_PREFIX KBUILD_MODNAME "."
 #endif
 
-/* Chosen so that structs with an unsigned long line up. */
-#define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long))
-
-#define __MODULE_INFO(tag, name, info)					  \
-	static const char __UNIQUE_ID(name)[]				  \
+/* Generic info of form tag = "info" */
+#define MODULE_INFO(tag, info)					  \
+	static_assert(						  \
+		sizeof(info) - 1 == __builtin_strlen(info),	  \
+		"MODULE_INFO(" #tag ", ...) contains embedded NUL byte"); \
+	static const char __UNIQUE_ID(modinfo)[]			  \
 		__used __section(".modinfo") __aligned(1)		  \
 		= __MODULE_INFO_PREFIX __stringify(tag) "=" info
 
 #define __MODULE_PARM_TYPE(name, _type)					  \
-	__MODULE_INFO(parmtype, name##type, #name ":" _type)
+	MODULE_INFO(parmtype, #name ":" _type)
 
 /* One for each parameter, describing how to use it.  Some files do
    multiple of these per line, so can't just use MODULE_INFO. */
 #define MODULE_PARM_DESC(_parm, desc) \
-	__MODULE_INFO(parm, _parm, #_parm ":" desc)
+	MODULE_INFO(parm, #_parm ":" desc)
 
 struct kernel_param;
 
@@ -276,16 +284,15 @@ struct kparam_array
    read-only sections (which is part of respective UNIX ABI on these
    platforms). So 'const' makes no sense and even causes compile failures
    with some compilers. */
-#if defined(CONFIG_ALPHA) || defined(CONFIG_IA64) || defined(CONFIG_PPC64)
+#if defined(CONFIG_ALPHA) || defined(CONFIG_PPC64)
 #define __moduleparam_const
 #else
 #define __moduleparam_const const
 #endif
 
-/* This is the fundamental function for registering boot/module
-   parameters. */
+/* This is the fundamental function for registering boot/module parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
-	/* Default value instead of permissions? */			\
+	static_assert(sizeof(""prefix) - 1 <= __MODULE_NAME_LEN);	\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used __section("__param")					\
@@ -293,7 +300,11 @@ struct kparam_array
 	= { __param_str_##name, THIS_MODULE, ops,			\
 	    VERIFY_OCTAL_PERMISSIONS(perm), level, flags, { arg } }
 
-/* Obsolete - use module_param_cb() */
+/*
+ * Useful for describing a set/get pair used only once (i.e. for this
+ * parameter). For repeated set/get pairs (i.e. the same struct
+ * kernel_param_ops), use module_param_cb() instead.
+ */
 #define module_param_call(name, _set, _get, arg, perm)			\
 	static const struct kernel_param_ops __param_ops_##name =	\
 		{ .flags = 0, .set = _set, .get = _get };		\
@@ -341,6 +352,19 @@ static inline void kernel_param_unlock(struct module *mod)
 	__module_param_call("", name, &param_ops_##type, &var, perm,	\
 			    -1, KERNEL_PARAM_FL_UNSAFE)
 
+/**
+ * __core_param_cb - similar like core_param, with a set/get ops instead of type.
+ * @name: the name of the cmdline and sysfs parameter (often the same as var)
+ * @var: the variable
+ * @ops: the set & get operations for this parameter.
+ * @perm: visibility in sysfs
+ *
+ * Ideally this should be called 'core_param_cb', but the name has been
+ * used for module core parameter, so add the '__' prefix
+ */
+#define __core_param_cb(name, ops, arg, perm) \
+	__module_param_call("", name, ops, arg, perm, -1, 0)
+
 #endif /* !MODULE */
 
 /**
@@ -381,6 +405,8 @@ extern bool parameq(const char *name1, const char *name2);
  */
 extern bool parameqn(const char *name1, const char *name2, size_t n);
 
+typedef int (*parse_unknown_fn)(char *param, char *val, const char *doing, void *arg);
+
 /* Called on module insert or kernel boot */
 extern char *parse_args(const char *name,
 		      char *args,
@@ -388,9 +414,7 @@ extern char *parse_args(const char *name,
 		      unsigned num,
 		      s16 level_min,
 		      s16 level_max,
-		      void *arg,
-		      int (*unknown)(char *param, char *val,
-				     const char *doing, void *arg));
+		      void *arg, parse_unknown_fn unknown);
 
 /* Called by module remove. */
 #ifdef CONFIG_SYSFS
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 1ea326c368f7..acfe7ef86a1b 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -22,50 +22,38 @@ struct fs_context;
 struct file;
 struct path;
 
-#define MNT_NOSUID	0x01
-#define MNT_NODEV	0x02
-#define MNT_NOEXEC	0x04
-#define MNT_NOATIME	0x08
-#define MNT_NODIRATIME	0x10
-#define MNT_RELATIME	0x20
-#define MNT_READONLY	0x40	/* does the user want this to be r/o? */
-#define MNT_NOSYMFOLLOW	0x80
-
-#define MNT_SHRINKABLE	0x100
-#define MNT_WRITE_HOLD	0x200
-
-#define MNT_SHARED	0x1000	/* if the vfsmount is a shared mount */
-#define MNT_UNBINDABLE	0x2000	/* if the vfsmount is a unbindable mount */
-/*
- * MNT_SHARED_MASK is the set of flags that should be cleared when a
- * mount becomes shared.  Currently, this is only the flag that says a
- * mount cannot be bind mounted, since this is how we create a mount
- * that shares events with another mount.  If you add a new MNT_*
- * flag, consider how it interacts with shared mounts.
- */
-#define MNT_SHARED_MASK	(MNT_UNBINDABLE)
-#define MNT_USER_SETTABLE_MASK  (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \
-				 | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \
-				 | MNT_READONLY | MNT_NOSYMFOLLOW)
-#define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME )
-
-#define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \
-			    MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | \
-			    MNT_CURSOR)
-
-#define MNT_INTERNAL	0x4000
-
-#define MNT_LOCK_ATIME		0x040000
-#define MNT_LOCK_NOEXEC		0x080000
-#define MNT_LOCK_NOSUID		0x100000
-#define MNT_LOCK_NODEV		0x200000
-#define MNT_LOCK_READONLY	0x400000
-#define MNT_LOCKED		0x800000
-#define MNT_DOOMED		0x1000000
-#define MNT_SYNC_UMOUNT		0x2000000
-#define MNT_MARKED		0x4000000
-#define MNT_UMOUNT		0x8000000
-#define MNT_CURSOR		0x10000000
+enum mount_flags {
+	MNT_NOSUID	= 0x01,
+	MNT_NODEV	= 0x02,
+	MNT_NOEXEC	= 0x04,
+	MNT_NOATIME	= 0x08,
+	MNT_NODIRATIME	= 0x10,
+	MNT_RELATIME	= 0x20,
+	MNT_READONLY	= 0x40, /* does the user want this to be r/o? */
+	MNT_NOSYMFOLLOW	= 0x80,
+
+	MNT_SHRINKABLE	= 0x100,
+
+	MNT_INTERNAL	= 0x4000,
+
+	MNT_LOCK_ATIME		= 0x040000,
+	MNT_LOCK_NOEXEC		= 0x080000,
+	MNT_LOCK_NOSUID		= 0x100000,
+	MNT_LOCK_NODEV		= 0x200000,
+	MNT_LOCK_READONLY	= 0x400000,
+	MNT_LOCKED		= 0x800000,
+	MNT_DOOMED		= 0x1000000,
+	MNT_SYNC_UMOUNT		= 0x2000000,
+	MNT_UMOUNT		= 0x8000000,
+
+	MNT_USER_SETTABLE_MASK  = MNT_NOSUID | MNT_NODEV | MNT_NOEXEC
+				  | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME
+				  | MNT_READONLY | MNT_NOSYMFOLLOW,
+	MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME,
+
+	MNT_INTERNAL_FLAGS = MNT_INTERNAL | MNT_DOOMED |
+			     MNT_SYNC_UMOUNT | MNT_LOCKED
+};
 
 struct vfsmount {
 	struct dentry *mnt_root;	/* root of the mounted tree */
@@ -77,7 +65,7 @@ struct vfsmount {
 static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt)
 {
 	/* Pairs with smp_store_release() in do_idmap_mount(). */
-	return smp_load_acquire(&mnt->mnt_idmap);
+	return READ_ONCE(mnt->mnt_idmap);
 }
 
 extern int mnt_want_write(struct vfsmount *mnt);
@@ -88,26 +76,23 @@ extern void mntput(struct vfsmount *mnt);
 extern struct vfsmount *mntget(struct vfsmount *mnt);
 extern void mnt_make_shortterm(struct vfsmount *mnt);
 extern struct vfsmount *mnt_clone_internal(const struct path *path);
-extern bool __mnt_is_readonly(struct vfsmount *mnt);
+extern bool __mnt_is_readonly(const struct vfsmount *mnt);
 extern bool mnt_may_suid(struct vfsmount *mnt);
 
 extern struct vfsmount *clone_private_mount(const struct path *path);
-extern int __mnt_want_write(struct vfsmount *);
-extern void __mnt_drop_write(struct vfsmount *);
+int mnt_get_write_access(struct vfsmount *mnt);
+void mnt_put_write_access(struct vfsmount *mnt);
 
 extern struct vfsmount *fc_mount(struct fs_context *fc);
+extern struct vfsmount *fc_mount_longterm(struct fs_context *fc);
 extern struct vfsmount *vfs_create_mount(struct fs_context *fc);
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,
 				      void *data);
-extern struct vfsmount *vfs_submount(const struct dentry *mountpoint,
-				     struct file_system_type *type,
-				     const char *name, void *data);
 
 extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list);
 extern void mark_mounts_for_expiry(struct list_head *mounts);
 
-extern dev_t name_to_dev_t(const char *name);
 extern bool path_is_mountpoint(const struct path *path);
 
 extern bool our_mnt(struct vfsmount *mnt);
@@ -116,12 +101,12 @@ extern struct vfsmount *kern_mount(struct file_system_type *);
 extern void kern_unmount(struct vfsmount *mnt);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
-extern long do_mount(const char *, const char __user *,
+int do_mount(const char *, const char __user *,
 		     const char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(const struct path *);
-extern void drop_collected_mounts(struct vfsmount *);
-extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
-			  struct vfsmount *);
+extern const struct path *collect_paths(const struct path *, struct path *, unsigned);
+extern void drop_collected_paths(const struct path *, const struct path *);
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
 
+extern int cifs_root_data(char **dev, char **opts);
+
 #endif /* _LINUX_MOUNT_H */
diff --git a/include/linux/moxtet.h b/include/linux/moxtet.h
index 79184948fab4..dfa4800306ee 100644
--- a/include/linux/moxtet.h
+++ b/include/linux/moxtet.h
@@ -35,8 +35,6 @@ enum turris_mox_module_id {
 
 #define MOXTET_NIRQS	16
 
-extern struct bus_type moxtet_type;
-
 struct moxtet {
 	struct device			*dev;
 	struct mutex			lock;
@@ -63,13 +61,8 @@ struct moxtet_driver {
 	struct device_driver		driver;
 };
 
-static inline struct moxtet_driver *
-to_moxtet_driver(struct device_driver *drv)
-{
-	if (!drv)
-		return NULL;
-	return container_of(drv, struct moxtet_driver, driver);
-}
+#define to_moxtet_driver(__drv)	\
+	( __drv ? container_of_const(__drv, struct moxtet_driver, driver) : NULL )
 
 extern int __moxtet_register_driver(struct module *owner,
 				    struct moxtet_driver *mdrv);
diff --git a/include/linux/mpi.h b/include/linux/mpi.h
index eb0d1c1db208..47be46f36435 100644
--- a/include/linux/mpi.h
+++ b/include/linux/mpi.h
@@ -40,79 +40,26 @@ struct gcry_mpi {
 typedef struct gcry_mpi *MPI;
 
 #define mpi_get_nlimbs(a)     ((a)->nlimbs)
-#define mpi_has_sign(a)       ((a)->sign)
 
 /*-- mpiutil.c --*/
 MPI mpi_alloc(unsigned nlimbs);
-void mpi_clear(MPI a);
 void mpi_free(MPI a);
 int mpi_resize(MPI a, unsigned nlimbs);
 
-static inline MPI mpi_new(unsigned int nbits)
-{
-	return mpi_alloc((nbits + BITS_PER_MPI_LIMB - 1) / BITS_PER_MPI_LIMB);
-}
-
 MPI mpi_copy(MPI a);
-MPI mpi_alloc_like(MPI a);
-void mpi_snatch(MPI w, MPI u);
-MPI mpi_set(MPI w, MPI u);
-MPI mpi_set_ui(MPI w, unsigned long u);
-MPI mpi_alloc_set_ui(unsigned long u);
-void mpi_swap_cond(MPI a, MPI b, unsigned long swap);
-
-/* Constants used to return constant MPIs.  See mpi_init if you
- * want to add more constants.
- */
-#define MPI_NUMBER_OF_CONSTANTS 6
-enum gcry_mpi_constants {
-	MPI_C_ZERO,
-	MPI_C_ONE,
-	MPI_C_TWO,
-	MPI_C_THREE,
-	MPI_C_FOUR,
-	MPI_C_EIGHT
-};
-
-MPI mpi_const(enum gcry_mpi_constants no);
 
 /*-- mpicoder.c --*/
-
-/* Different formats of external big integer representation. */
-enum gcry_mpi_format {
-	GCRYMPI_FMT_NONE = 0,
-	GCRYMPI_FMT_STD = 1,    /* Twos complement stored without length. */
-	GCRYMPI_FMT_PGP = 2,    /* As used by OpenPGP (unsigned only). */
-	GCRYMPI_FMT_SSH = 3,    /* As used by SSH (like STD but with length). */
-	GCRYMPI_FMT_HEX = 4,    /* Hex format. */
-	GCRYMPI_FMT_USG = 5,    /* Like STD but unsigned. */
-	GCRYMPI_FMT_OPAQUE = 8  /* Opaque format (some functions only). */
-};
-
 MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes);
 MPI mpi_read_from_buffer(const void *buffer, unsigned *ret_nread);
-int mpi_fromstr(MPI val, const char *str);
-MPI mpi_scanval(const char *string);
 MPI mpi_read_raw_from_sgl(struct scatterlist *sgl, unsigned int len);
 void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign);
 int mpi_read_buffer(MPI a, uint8_t *buf, unsigned buf_len, unsigned *nbytes,
 		    int *sign);
 int mpi_write_to_sgl(MPI a, struct scatterlist *sg, unsigned nbytes,
 		     int *sign);
-int mpi_print(enum gcry_mpi_format format, unsigned char *buffer,
-			size_t buflen, size_t *nwritten, MPI a);
 
 /*-- mpi-mod.c --*/
-void mpi_mod(MPI rem, MPI dividend, MPI divisor);
-
-/* Context used with Barrett reduction.  */
-struct barrett_ctx_s;
-typedef struct barrett_ctx_s *mpi_barrett_t;
-
-mpi_barrett_t mpi_barrett_init(MPI m, int copy);
-void mpi_barrett_free(mpi_barrett_t ctx);
-void mpi_mod_barrett(MPI r, MPI x, mpi_barrett_t ctx);
-void mpi_mul_barrett(MPI w, MPI u, MPI v, mpi_barrett_t ctx);
+int mpi_mod(MPI rem, MPI dividend, MPI divisor);
 
 /*-- mpi-pow.c --*/
 int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
@@ -120,7 +67,6 @@ int mpi_powm(MPI res, MPI base, MPI exp, MPI mod);
 /*-- mpi-cmp.c --*/
 int mpi_cmp_ui(MPI u, ulong v);
 int mpi_cmp(MPI u, MPI v);
-int mpi_cmpabs(MPI u, MPI v);
 
 /*-- mpi-sub-ui.c --*/
 int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
@@ -129,138 +75,22 @@ int mpi_sub_ui(MPI w, MPI u, unsigned long vval);
 void mpi_normalize(MPI a);
 unsigned mpi_get_nbits(MPI a);
 int mpi_test_bit(MPI a, unsigned int n);
-void mpi_set_bit(MPI a, unsigned int n);
-void mpi_set_highbit(MPI a, unsigned int n);
-void mpi_clear_highbit(MPI a, unsigned int n);
-void mpi_clear_bit(MPI a, unsigned int n);
-void mpi_rshift_limbs(MPI a, unsigned int count);
-void mpi_rshift(MPI x, MPI a, unsigned int n);
-void mpi_lshift_limbs(MPI a, unsigned int count);
-void mpi_lshift(MPI x, MPI a, unsigned int n);
+int mpi_set_bit(MPI a, unsigned int n);
+int mpi_rshift(MPI x, MPI a, unsigned int n);
 
 /*-- mpi-add.c --*/
-void mpi_add_ui(MPI w, MPI u, unsigned long v);
-void mpi_add(MPI w, MPI u, MPI v);
-void mpi_sub(MPI w, MPI u, MPI v);
-void mpi_addm(MPI w, MPI u, MPI v, MPI m);
-void mpi_subm(MPI w, MPI u, MPI v, MPI m);
+int mpi_add(MPI w, MPI u, MPI v);
+int mpi_sub(MPI w, MPI u, MPI v);
+int mpi_addm(MPI w, MPI u, MPI v, MPI m);
+int mpi_subm(MPI w, MPI u, MPI v, MPI m);
 
 /*-- mpi-mul.c --*/
-void mpi_mul(MPI w, MPI u, MPI v);
-void mpi_mulm(MPI w, MPI u, MPI v, MPI m);
+int mpi_mul(MPI w, MPI u, MPI v);
+int mpi_mulm(MPI w, MPI u, MPI v, MPI m);
 
 /*-- mpi-div.c --*/
-void mpi_tdiv_r(MPI rem, MPI num, MPI den);
-void mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor);
-void mpi_fdiv_q(MPI quot, MPI dividend, MPI divisor);
-
-/*-- mpi-inv.c --*/
-int mpi_invm(MPI x, MPI a, MPI n);
-
-/*-- ec.c --*/
-
-/* Object to represent a point in projective coordinates */
-struct gcry_mpi_point {
-	MPI x;
-	MPI y;
-	MPI z;
-};
-
-typedef struct gcry_mpi_point *MPI_POINT;
-
-/* Models describing an elliptic curve */
-enum gcry_mpi_ec_models {
-	/* The Short Weierstrass equation is
-	 *      y^2 = x^3 + ax + b
-	 */
-	MPI_EC_WEIERSTRASS = 0,
-	/* The Montgomery equation is
-	 *      by^2 = x^3 + ax^2 + x
-	 */
-	MPI_EC_MONTGOMERY,
-	/* The Twisted Edwards equation is
-	 *      ax^2 + y^2 = 1 + bx^2y^2
-	 * Note that we use 'b' instead of the commonly used 'd'.
-	 */
-	MPI_EC_EDWARDS
-};
-
-/* Dialects used with elliptic curves */
-enum ecc_dialects {
-	ECC_DIALECT_STANDARD = 0,
-	ECC_DIALECT_ED25519,
-	ECC_DIALECT_SAFECURVE
-};
-
-/* This context is used with all our EC functions. */
-struct mpi_ec_ctx {
-	enum gcry_mpi_ec_models model; /* The model describing this curve. */
-	enum ecc_dialects dialect;     /* The ECC dialect used with the curve. */
-	int flags;                     /* Public key flags (not always used). */
-	unsigned int nbits;            /* Number of bits.  */
-
-	/* Domain parameters.  Note that they may not all be set and if set
-	 * the MPIs may be flagged as constant.
-	 */
-	MPI p;         /* Prime specifying the field GF(p).  */
-	MPI a;         /* First coefficient of the Weierstrass equation.  */
-	MPI b;         /* Second coefficient of the Weierstrass equation.  */
-	MPI_POINT G;   /* Base point (generator).  */
-	MPI n;         /* Order of G.  */
-	unsigned int h;       /* Cofactor.  */
-
-	/* The actual key.  May not be set.  */
-	MPI_POINT Q;   /* Public key.   */
-	MPI d;         /* Private key.  */
-
-	const char *name;      /* Name of the curve.  */
-
-	/* This structure is private to mpi/ec.c! */
-	struct {
-		struct {
-			unsigned int a_is_pminus3:1;
-			unsigned int two_inv_p:1;
-		} valid; /* Flags to help setting the helper vars below.  */
-
-		int a_is_pminus3;  /* True if A = P - 3. */
-
-		MPI two_inv_p;
-
-		mpi_barrett_t p_barrett;
-
-		/* Scratch variables.  */
-		MPI scratch[11];
-
-		/* Helper for fast reduction.  */
-		/*   int nist_nbits; /\* If this is a NIST curve, the # of bits. *\/ */
-		/*   MPI s[10]; */
-		/*   MPI c; */
-	} t;
-
-	/* Curve specific computation routines for the field.  */
-	void (*addm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
-	void (*subm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ec);
-	void (*mulm)(MPI w, MPI u, MPI v, struct mpi_ec_ctx *ctx);
-	void (*pow2)(MPI w, const MPI b, struct mpi_ec_ctx *ctx);
-	void (*mul2)(MPI w, MPI u, struct mpi_ec_ctx *ctx);
-};
-
-void mpi_ec_init(struct mpi_ec_ctx *ctx, enum gcry_mpi_ec_models model,
-			enum ecc_dialects dialect,
-			int flags, MPI p, MPI a, MPI b);
-void mpi_ec_deinit(struct mpi_ec_ctx *ctx);
-MPI_POINT mpi_point_new(unsigned int nbits);
-void mpi_point_release(MPI_POINT p);
-void mpi_point_init(MPI_POINT p);
-void mpi_point_free_parts(MPI_POINT p);
-int mpi_ec_get_affine(MPI x, MPI y, MPI_POINT point, struct mpi_ec_ctx *ctx);
-void mpi_ec_add_points(MPI_POINT result,
-			MPI_POINT p1, MPI_POINT p2,
-			struct mpi_ec_ctx *ctx);
-void mpi_ec_mul_point(MPI_POINT result,
-			MPI scalar, MPI_POINT point,
-			struct mpi_ec_ctx *ctx);
-int mpi_ec_curve_point(MPI_POINT point, struct mpi_ec_ctx *ctx);
+int mpi_tdiv_r(MPI rem, MPI num, MPI den);
+int mpi_fdiv_r(MPI rem, MPI dividend, MPI divisor);
 
 /* inline functions */
 
diff --git a/include/linux/mroute.h b/include/linux/mroute.h
index 80b8400ab8b2..4c5003afee6c 100644
--- a/include/linux/mroute.h
+++ b/include/linux/mroute.h
@@ -18,10 +18,11 @@ static inline int ip_mroute_opt(int opt)
 
 int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
 int ip_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t);
-int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg);
+int ipmr_ioctl(struct sock *sk, int cmd, void *arg);
 int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 int ip_mr_init(void);
 bool ipmr_rule_default(const struct fib_rule *rule);
+int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 #else
 static inline int ip_mroute_setsockopt(struct sock *sock, int optname,
 				       sockptr_t optval, unsigned int optlen)
@@ -35,7 +36,7 @@ static inline int ip_mroute_getsockopt(struct sock *sk, int optname,
 	return -ENOPROTOOPT;
 }
 
-static inline int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
+static inline int ipmr_ioctl(struct sock *sk, int cmd, void *arg)
 {
 	return -ENOIOCTLCMD;
 }
@@ -54,6 +55,12 @@ static inline bool ipmr_rule_default(const struct fib_rule *rule)
 {
 	return true;
 }
+
+static inline int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd,
+				void __user *arg)
+{
+	return 1;
+}
 #endif
 
 #define VIFF_STATIC 0x8000
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index 8f2b307fb124..fddafdc168f7 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -29,10 +29,11 @@ struct sock;
 extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int);
 extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t);
 extern int ip6_mr_input(struct sk_buff *skb);
-extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg);
 extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 extern int ip6_mr_init(void);
+extern int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 extern void ip6_mr_cleanup(void);
+int ip6mr_ioctl(struct sock *sk, int cmd, void *arg);
 #else
 static inline int ip6_mroute_setsockopt(struct sock *sock, int optname,
 		sockptr_t optval, unsigned int optlen)
@@ -48,7 +49,7 @@ int ip6_mroute_getsockopt(struct sock *sock,
 }
 
 static inline
-int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
+int ip6mr_ioctl(struct sock *sk, int cmd, void *arg)
 {
 	return -ENOIOCTLCMD;
 }
@@ -58,6 +59,12 @@ static inline int ip6_mr_init(void)
 	return 0;
 }
 
+static inline int
+ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	return ip6_output(net, sk, skb);
+}
+
 static inline void ip6_mr_cleanup(void)
 {
 	return;
@@ -100,6 +107,27 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb,
 #ifdef CONFIG_IPV6_MROUTE
 bool mroute6_is_socket(struct net *net, struct sk_buff *skb);
 extern int ip6mr_sk_done(struct sock *sk);
+static inline int ip6mr_sk_ioctl(struct sock *sk, unsigned int cmd,
+				 void __user *arg)
+{
+	switch (cmd) {
+	/* These userspace buffers will be consumed by ip6mr_ioctl() */
+	case SIOCGETMIFCNT_IN6: {
+		struct sioc_mif_req6 buffer;
+
+		return sock_ioctl_inout(sk, cmd, arg, &buffer,
+					sizeof(buffer));
+		}
+	case SIOCGETSGCNT_IN6: {
+		struct sioc_sg_req6 buffer;
+
+		return sock_ioctl_inout(sk, cmd, arg, &buffer,
+					sizeof(buffer));
+		}
+	}
+
+	return 1;
+}
 #else
 static inline bool mroute6_is_socket(struct net *net, struct sk_buff *skb)
 {
@@ -109,5 +137,11 @@ static inline int ip6mr_sk_done(struct sock *sk)
 {
 	return 0;
 }
+
+static inline int ip6mr_sk_ioctl(struct sock *sk, unsigned int cmd,
+				 void __user *arg)
+{
+	return 1;
+}
 #endif
 #endif
diff --git a/include/linux/mroute_base.h b/include/linux/mroute_base.h
index 9dd4bf157255..0075f6e5c3da 100644
--- a/include/linux/mroute_base.h
+++ b/include/linux/mroute_base.h
@@ -146,9 +146,9 @@ struct mr_mfc {
 			unsigned long last_assert;
 			int minvif;
 			int maxvif;
-			unsigned long bytes;
-			unsigned long pkt;
-			unsigned long wrong_if;
+			atomic_long_t bytes;
+			atomic_long_t pkt;
+			atomic_long_t wrong_if;
 			unsigned long lastuse;
 			unsigned char ttls[MAXVIFS];
 			refcount_t refcount;
@@ -262,6 +262,11 @@ struct mr_table {
 	int			mroute_reg_vif_num;
 };
 
+static inline bool mr_can_free_table(struct net *net)
+{
+	return !check_net(net) || !net_initialized(net);
+}
+
 #ifdef CONFIG_IP_MROUTE_COMMON
 void vif_device_init(struct vif_device *v,
 		     struct net_device *dev,
diff --git a/include/linux/msi.h b/include/linux/msi.h
index a50ea79522f8..8003e3218c46 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -19,13 +19,9 @@
  */
 
 #include <linux/irqdomain_defs.h>
-#include <linux/cpumask.h>
+#include <linux/cpumask_types.h>
 #include <linux/msi_api.h>
-#include <linux/xarray.h>
-#include <linux/mutex.h>
-#include <linux/list.h>
 #include <linux/irq.h>
-#include <linux/bits.h>
 
 #include <asm/msi.h>
 
@@ -77,11 +73,9 @@ struct msi_msg {
 	};
 };
 
-extern int pci_msi_ignore_mask;
 /* Helper functions */
 struct msi_desc;
 struct pci_dev;
-struct platform_msi_priv_data;
 struct device_attribute;
 struct irq_domain;
 struct irq_affinity_desc;
@@ -171,6 +165,10 @@ struct msi_desc_data {
  * @dev:	Pointer to the device which uses this descriptor
  * @msg:	The last set MSI message cached for reuse
  * @affinity:	Optional pointer to a cpu affinity mask for this descriptor
+ * @iommu_msi_iova: Optional shifted IOVA from the IOMMU to override the msi_addr.
+ *                  Only used if iommu_msi_shift != 0
+ * @iommu_msi_shift: Indicates how many bits of the original address should be
+ *                   preserved when using iommu_msi_iova.
  * @sysfs_attr:	Pointer to sysfs device attribute
  *
  * @write_msi_msg:	Callback that may be called when the MSI message
@@ -189,7 +187,8 @@ struct msi_desc {
 	struct msi_msg			msg;
 	struct irq_affinity_desc	*affinity;
 #ifdef CONFIG_IRQ_MSI_IOMMU
-	const void			*iommu_cookie;
+	u64				iommu_msi_iova : 58;
+	u64				iommu_msi_shift : 6;
 #endif
 #ifdef CONFIG_SYSFS
 	struct device_attribute		*sysfs_attrs;
@@ -228,26 +227,13 @@ struct msi_dev_domain {
 	struct irq_domain	*domain;
 };
 
-/**
- * msi_device_data - MSI per device data
- * @properties:		MSI properties which are interesting to drivers
- * @platform_data:	Platform-MSI specific data
- * @mutex:		Mutex protecting the MSI descriptor store
- * @__domains:		Internal data for per device MSI domains
- * @__iter_idx:		Index to search the next entry for iterators
- */
-struct msi_device_data {
-	unsigned long			properties;
-	struct platform_msi_priv_data	*platform_data;
-	struct mutex			mutex;
-	struct msi_dev_domain		__domains[MSI_MAX_DEVICE_IRQDOMAINS];
-	unsigned long			__iter_idx;
-};
-
 int msi_setup_device_data(struct device *dev);
 
-void msi_lock_descs(struct device *dev);
-void msi_unlock_descs(struct device *dev);
+void __msi_lock_descs(struct device *dev);
+void __msi_unlock_descs(struct device *dev);
+
+DEFINE_LOCK_GUARD_1(msi_descs_lock, struct device, __msi_lock_descs(_T->lock),
+		    __msi_unlock_descs(_T->lock));
 
 struct msi_desc *msi_domain_first_desc(struct device *dev, unsigned int domid,
 				       enum msi_desc_filter filter);
@@ -306,28 +292,42 @@ struct msi_desc *msi_next_desc(struct device *dev, unsigned int domid,
 
 #define msi_desc_to_dev(desc)		((desc)->dev)
 
-#ifdef CONFIG_IRQ_MSI_IOMMU
-static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc)
-{
-	return desc->iommu_cookie;
-}
-
-static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc,
-					     const void *iommu_cookie)
+static inline void msi_desc_set_iommu_msi_iova(struct msi_desc *desc, u64 msi_iova,
+					       unsigned int msi_shift)
 {
-	desc->iommu_cookie = iommu_cookie;
-}
-#else
-static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc)
-{
-	return NULL;
+#ifdef CONFIG_IRQ_MSI_IOMMU
+	desc->iommu_msi_iova = msi_iova >> msi_shift;
+	desc->iommu_msi_shift = msi_shift;
+#endif
 }
 
-static inline void msi_desc_set_iommu_cookie(struct msi_desc *desc,
-					     const void *iommu_cookie)
+/**
+ * msi_msg_set_addr() - Set MSI address in an MSI message
+ *
+ * @desc:	MSI descriptor that may carry an IOVA base address for MSI via @iommu_msi_iova/shift
+ * @msg:	Target MSI message to set its address_hi and address_lo
+ * @msi_addr:	Physical address to set the MSI message
+ *
+ * Notes:
+ *  - Override @msi_addr using the IOVA base address in the @desc if @iommu_msi_shift is set
+ *  - Otherwise, simply set @msi_addr to @msg
+ */
+static inline void msi_msg_set_addr(struct msi_desc *desc, struct msi_msg *msg,
+				    phys_addr_t msi_addr)
 {
-}
+#ifdef CONFIG_IRQ_MSI_IOMMU
+	if (desc->iommu_msi_shift) {
+		u64 msi_iova = desc->iommu_msi_iova << desc->iommu_msi_shift;
+
+		msg->address_hi = upper_32_bits(msi_iova);
+		msg->address_lo = lower_32_bits(msi_iova) |
+				  (msi_addr & ((1 << desc->iommu_msi_shift) - 1));
+		return;
+	}
 #endif
+	msg->address_hi = upper_32_bits(msi_addr);
+	msg->address_lo = lower_32_bits(msi_addr);
+}
 
 int msi_domain_insert_msi_desc(struct device *dev, unsigned int domid,
 			       struct msi_desc *init_desc);
@@ -412,6 +412,7 @@ bool arch_restore_msi_irqs(struct pci_dev *dev);
 struct irq_domain;
 struct irq_domain_ops;
 struct irq_chip;
+struct irq_fwspec;
 struct device_node;
 struct fwnode_handle;
 struct msi_domain_info;
@@ -422,6 +423,7 @@ struct msi_domain_info;
  * @msi_init:		Domain specific init function for MSI interrupts
  * @msi_free:		Domain specific function to free a MSI interrupts
  * @msi_prepare:	Prepare the allocation of the interrupts in the domain
+ * @msi_teardown:	Reverse the effects of @msi_prepare
  * @prepare_desc:	Optional function to prepare the allocated MSI descriptor
  *			in the domain
  * @set_desc:		Set the msi descriptor for an interrupt
@@ -429,14 +431,15 @@ struct msi_domain_info;
  *			function.
  * @domain_free_irqs:	Optional function to override the default free
  *			function.
- * @msi_post_free:	Optional function which is invoked after freeing
- *			all interrupts.
+ * @msi_translate:	Optional translate callback to support the odd wire to
+ *			MSI bridges, e.g. MBIGEN
  *
  * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying
  * irqdomain.
  *
- * @msi_check, @msi_prepare, @prepare_desc and @set_desc are callbacks used by the
- * msi_domain_alloc/free_irqs*() variants.
+ * @msi_check, @msi_prepare, @msi_teardown, @prepare_desc and
+ * @set_desc are callbacks used by the msi_domain_alloc/free_irqs*()
+ * variants.
  *
  * @domain_alloc_irqs, @domain_free_irqs can be used to override the
  * default allocation/free functions (__msi_domain_alloc/free_irqs). This
@@ -458,6 +461,8 @@ struct msi_domain_ops {
 	int		(*msi_prepare)(struct irq_domain *domain,
 				       struct device *dev, int nvec,
 				       msi_alloc_info_t *arg);
+	void		(*msi_teardown)(struct irq_domain *domain,
+					msi_alloc_info_t *arg);
 	void		(*prepare_desc)(struct irq_domain *domain, msi_alloc_info_t *arg,
 					struct msi_desc *desc);
 	void		(*set_desc)(msi_alloc_info_t *arg,
@@ -466,8 +471,8 @@ struct msi_domain_ops {
 					     struct device *dev, int nvec);
 	void		(*domain_free_irqs)(struct irq_domain *domain,
 					    struct device *dev);
-	void		(*msi_post_free)(struct irq_domain *domain,
-					 struct device *dev);
+	int		(*msi_translate)(struct irq_domain *domain, struct irq_fwspec *fwspec,
+					 irq_hw_number_t *hwirq, unsigned int *type);
 };
 
 /**
@@ -479,11 +484,13 @@ struct msi_domain_ops {
  *			gets initialized to the maximum software index limit
  *			by the domain creation code.
  * @ops:		The callback data structure
+ * @dev:		Device which creates the domain
  * @chip:		Optional: associated interrupt chip
  * @chip_data:		Optional: associated interrupt chip data
  * @handler:		Optional: associated interrupt flow handler
  * @handler_data:	Optional: associated interrupt flow handler data
  * @handler_name:	Optional: associated interrupt flow handler name
+ * @alloc_data:		Optional: associated interrupt allocation data
  * @data:		Optional: domain specific data
  */
 struct msi_domain_info {
@@ -491,11 +498,13 @@ struct msi_domain_info {
 	enum irq_domain_bus_token	bus_token;
 	unsigned int			hwsize;
 	struct msi_domain_ops		*ops;
+	struct device			*dev;
 	struct irq_chip			*chip;
 	void				*chip_data;
 	irq_flow_handler_t		handler;
 	void				*handler_data;
 	const char			*handler_name;
+	msi_alloc_info_t		*alloc_data;
 	void				*data;
 };
 
@@ -505,12 +514,14 @@ struct msi_domain_info {
  * @chip:	Interrupt chip for this domain
  * @ops:	MSI domain ops
  * @info:	MSI domain info data
+ * @alloc_info:	MSI domain allocation data (architecture specific)
  */
 struct msi_domain_template {
 	char			name[48];
 	struct irq_chip		chip;
 	struct msi_domain_ops	ops;
 	struct msi_domain_info	info;
+	msi_alloc_info_t	alloc_info;
 };
 
 /*
@@ -547,12 +558,14 @@ enum {
 	MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS	= (1 << 5),
 	/* Free MSI descriptors */
 	MSI_FLAG_FREE_MSI_DESCS		= (1 << 6),
-	/*
-	 * Quirk to handle MSI implementations which do not provide
-	 * masking. Currently known to affect x86, but has to be partially
-	 * handled in the core MSI code.
-	 */
-	MSI_FLAG_NOMASK_QUIRK		= (1 << 7),
+	/* Use dev->fwnode for MSI device domain creation */
+	MSI_FLAG_USE_DEV_FWNODE		= (1 << 7),
+	/* Set parent->dev into domain->pm_dev on device domain creation */
+	MSI_FLAG_PARENT_PM_DEV		= (1 << 8),
+	/* Support for parent mask/unmask */
+	MSI_FLAG_PCI_MSI_MASK_PARENT	= (1 << 9),
+	/* Support for parent startup/shutdown */
+	MSI_FLAG_PCI_MSI_STARTUP_PARENT	= (1 << 10),
 
 	/* Mask for the generic functionality */
 	MSI_GENERIC_FLAGS_MASK		= GENMASK(15, 0),
@@ -570,14 +583,31 @@ enum {
 	MSI_FLAG_MSIX_CONTIGUOUS	= (1 << 19),
 	/* PCI/MSI-X vectors can be dynamically allocated/freed post MSI-X enable */
 	MSI_FLAG_PCI_MSIX_ALLOC_DYN	= (1 << 20),
-	/* Support for PCI/IMS */
-	MSI_FLAG_PCI_IMS		= (1 << 21),
+	/* PCI MSIs cannot be steered separately to CPU cores */
+	MSI_FLAG_NO_AFFINITY		= (1 << 21),
+	/* Inhibit usage of entry masking */
+	MSI_FLAG_NO_MASK		= (1 << 22),
+};
+
+/*
+ * Flags for msi_parent_ops::chip_flags
+ */
+enum {
+	MSI_CHIP_FLAG_SET_EOI		= (1 << 0),
+	MSI_CHIP_FLAG_SET_ACK		= (1 << 1),
 };
 
 /**
  * struct msi_parent_ops - MSI parent domain callbacks and configuration info
  *
  * @supported_flags:	Required: The supported MSI flags of the parent domain
+ * @required_flags:	Optional: The required MSI flags of the parent MSI domain
+ * @chip_flags:		Optional: Select MSI chip callbacks to update with defaults
+ *			in msi_lib_init_dev_msi_info().
+ * @bus_select_token:	Optional: The bus token of the real parent domain for
+ *			irq_domain::select()
+ * @bus_select_mask:	Optional: A mask of supported BUS_DOMAINs for
+ *			irq_domain::select()
  * @prefix:		Optional: Prefix for the domain and chip name
  * @init_dev_msi_info:	Required: Callback for MSI parent domains to setup parent
  *			domain specific domain flags, domain ops and interrupt chip
@@ -585,6 +615,10 @@ enum {
  */
 struct msi_parent_ops {
 	u32		supported_flags;
+	u32		required_flags;
+	u32		chip_flags;
+	u32		bus_select_token;
+	u32		bus_select_mask;
 	const char	*prefix;
 	bool		(*init_dev_msi_info)(struct device *dev, struct irq_domain *domain,
 					     struct irq_domain *msi_parent_domain,
@@ -602,6 +636,10 @@ struct irq_domain *msi_create_irq_domain(struct fwnode_handle *fwnode,
 					 struct msi_domain_info *info,
 					 struct irq_domain *parent);
 
+struct irq_domain_info;
+struct irq_domain *msi_create_parent_irq_domain(struct irq_domain_info *info,
+						const struct msi_parent_ops *msi_parent_ops);
+
 bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 				  const struct msi_domain_template *template,
 				  unsigned int hwsize, void *domain_data,
@@ -630,40 +668,18 @@ void msi_domain_free_irqs_all(struct device *dev, unsigned int domid);
 
 struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 
-struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode,
-						  struct msi_domain_info *info,
-						  struct irq_domain *parent);
-int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
-				   irq_write_msi_msg_t write_msi_msg);
-void platform_msi_domain_free_irqs(struct device *dev);
-
-/* When an MSI domain is used as an intermediate domain */
-int msi_domain_prepare_irqs(struct irq_domain *domain, struct device *dev,
-			    int nvec, msi_alloc_info_t *args);
-int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
-			     int virq, int nvec, msi_alloc_info_t *args);
-void msi_domain_depopulate_descs(struct device *dev, int virq, int nvec);
-
-struct irq_domain *
-__platform_msi_create_device_domain(struct device *dev,
-				    unsigned int nvec,
-				    bool is_tree,
-				    irq_write_msi_msg_t write_msi_msg,
-				    const struct irq_domain_ops *ops,
-				    void *host_data);
-
-#define platform_msi_create_device_domain(dev, nvec, write, ops, data)	\
-	__platform_msi_create_device_domain(dev, nvec, false, write, ops, data)
-#define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \
-	__platform_msi_create_device_domain(dev, nvec, true, write, ops, data)
-
-int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq,
-				     unsigned int nr_irqs);
-void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq,
-				     unsigned int nvec);
-void *platform_msi_get_host_data(struct irq_domain *domain);
+/* Per device platform MSI */
+int platform_device_msi_init_and_alloc_irqs(struct device *dev, unsigned int nvec,
+					    irq_write_msi_msg_t write_msi_msg);
+void platform_device_msi_free_irqs_all(struct device *dev);
 
 bool msi_device_has_isolated_msi(struct device *dev);
+
+static inline int msi_domain_alloc_irqs(struct device *dev, unsigned int domid, int nirqs)
+{
+	return msi_domain_alloc_irqs_range(dev, domid, 0, nirqs - 1);
+}
+
 #else /* CONFIG_GENERIC_MSI_IRQ */
 static inline bool msi_device_has_isolated_msi(struct device *dev)
 {
@@ -685,11 +701,11 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void pci_msi_mask_irq(struct irq_data *data);
 void pci_msi_unmask_irq(struct irq_data *data);
-struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
-					     struct msi_domain_info *info,
-					     struct irq_domain *parent);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
+u32 pci_msi_map_rid_ctlr_node(struct pci_dev *pdev, struct device_node **node);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+			   struct msi_desc *desc);
 #else /* CONFIG_PCI_MSI */
 static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 {
diff --git a/include/linux/msi_api.h b/include/linux/msi_api.h
index 391087ad99b1..5ae72d1912c4 100644
--- a/include/linux/msi_api.h
+++ b/include/linux/msi_api.h
@@ -15,7 +15,6 @@ struct device;
  */
 enum msi_domain_ids {
 	MSI_DEFAULT_DOMAIN,
-	MSI_SECONDARY_DOMAIN,
 	MSI_MAX_DEVICE_IRQDOMAINS,
 };
 
diff --git a/include/linux/mtd/blktrans.h b/include/linux/mtd/blktrans.h
index 15cc9b95e32b..6e471436bba5 100644
--- a/include/linux/mtd/blktrans.h
+++ b/include/linux/mtd/blktrans.h
@@ -34,7 +34,7 @@ struct mtd_blktrans_dev {
 	struct blk_mq_tag_set *tag_set;
 	spinlock_t queue_lock;
 	void *priv;
-	fmode_t file_mode;
+	bool writable;
 };
 
 struct mtd_blktrans_ops {
diff --git a/include/linux/mtd/cfi.h b/include/linux/mtd/cfi.h
index d88bb56c18e2..35ca19ae21ae 100644
--- a/include/linux/mtd/cfi.h
+++ b/include/linux/mtd/cfi.h
@@ -287,7 +287,7 @@ struct cfi_private {
 	unsigned long chipshift; /* Because they're of the same type */
 	const char *im_name;	 /* inter_module name for cmdset_setup */
 	unsigned long quirks;
-	struct flchip chips[];  /* per-chip data structure for each chip */
+	struct flchip chips[] __counted_by(numchips);  /* per-chip data structure for each chip */
 };
 
 uint32_t cfi_build_cmd_addr(uint32_t cmd_ofs,
@@ -308,32 +308,32 @@ static inline uint8_t cfi_read_query(struct map_info *map, uint32_t addr)
 {
 	map_word val = map_read(map, addr);
 
-	if (map_bankwidth_is_1(map)) {
+	if (map_bankwidth_is_1(map))
 		return val.x[0];
-	} else if (map_bankwidth_is_2(map)) {
+	if (map_bankwidth_is_2(map))
 		return cfi16_to_cpu(map, val.x[0]);
-	} else {
-		/* No point in a 64-bit byteswap since that would just be
-		   swapping the responses from different chips, and we are
-		   only interested in one chip (a representative sample) */
-		return cfi32_to_cpu(map, val.x[0]);
-	}
+	/*
+	 * No point in a 64-bit byteswap since that would just be
+	 * swapping the responses from different chips, and we are
+	 * only interested in one chip (a representative sample)
+	 */
+	return cfi32_to_cpu(map, val.x[0]);
 }
 
 static inline uint16_t cfi_read_query16(struct map_info *map, uint32_t addr)
 {
 	map_word val = map_read(map, addr);
 
-	if (map_bankwidth_is_1(map)) {
+	if (map_bankwidth_is_1(map))
 		return val.x[0] & 0xff;
-	} else if (map_bankwidth_is_2(map)) {
+	if (map_bankwidth_is_2(map))
 		return cfi16_to_cpu(map, val.x[0]);
-	} else {
-		/* No point in a 64-bit byteswap since that would just be
-		   swapping the responses from different chips, and we are
-		   only interested in one chip (a representative sample) */
-		return cfi32_to_cpu(map, val.x[0]);
-	}
+	/*
+	 * No point in a 64-bit byteswap since that would just be
+	 * swapping the responses from different chips, and we are
+	 * only interested in one chip (a representative sample)
+	 */
+	return cfi32_to_cpu(map, val.x[0]);
 }
 
 void cfi_udelay(int us);
diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h
index c04f690871ca..9798c1a1d3b6 100644
--- a/include/linux/mtd/flashchip.h
+++ b/include/linux/mtd/flashchip.h
@@ -13,6 +13,7 @@
  */
 #include <linux/sched.h>
 #include <linux/mutex.h>
+#include <linux/wait.h>
 
 typedef enum {
 	FL_READY,
diff --git a/include/linux/mtd/jedec.h b/include/linux/mtd/jedec.h
index 0b6b59f7cfbd..56047a4e54c9 100644
--- a/include/linux/mtd/jedec.h
+++ b/include/linux/mtd/jedec.h
@@ -21,6 +21,9 @@ struct jedec_ecc_info {
 /* JEDEC features */
 #define JEDEC_FEATURE_16_BIT_BUS	(1 << 0)
 
+/* JEDEC Optional Commands */
+#define JEDEC_OPT_CMD_READ_CACHE	BIT(1)
+
 struct nand_jedec_params {
 	/* rev info and features block */
 	/* 'J' 'E' 'S' 'D'  */
diff --git a/include/linux/mtd/lpc32xx_mlc.h b/include/linux/mtd/lpc32xx_mlc.h
index d168c628c0d5..35e971be0950 100644
--- a/include/linux/mtd/lpc32xx_mlc.h
+++ b/include/linux/mtd/lpc32xx_mlc.h
@@ -11,7 +11,7 @@
 #include <linux/dmaengine.h>
 
 struct lpc32xx_mlc_platform_data {
-	bool (*dma_filter)(struct dma_chan *chan, void *filter_param);
+	dma_filter_fn dma_filter;
 };
 
 #endif  /* __LINUX_MTD_LPC32XX_MLC_H */
diff --git a/include/linux/mtd/lpc32xx_slc.h b/include/linux/mtd/lpc32xx_slc.h
index cf54a9f80460..a044b806566b 100644
--- a/include/linux/mtd/lpc32xx_slc.h
+++ b/include/linux/mtd/lpc32xx_slc.h
@@ -11,7 +11,7 @@
 #include <linux/dmaengine.h>
 
 struct lpc32xx_slc_platform_data {
-	bool (*dma_filter)(struct dma_chan *chan, void *filter_param);
+	dma_filter_fn dma_filter;
 };
 
 #endif  /* __LINUX_MTD_LPC32XX_SLC_H */
diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index b4fa92a6e44b..75b0b2abc880 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -8,16 +8,17 @@
 #ifndef __LINUX_MTD_MAP_H__
 #define __LINUX_MTD_MAP_H__
 
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/string.h>
 #include <linux/bug.h>
-#include <linux/kernel.h>
 #include <linux/io.h>
-
-#include <asm/unaligned.h>
+#include <linux/ioport.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/unaligned.h>
 #include <asm/barrier.h>
 
+struct device_node;
+struct module;
+
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1
 #define map_bankwidth(map) 1
 #define map_bankwidth_is_1(map) (map_bankwidth(map) == 1)
@@ -188,6 +189,7 @@ typedef union {
    of living.
 */
 
+struct mtd_chip_driver;
 struct map_info {
 	const char *name;
 	unsigned long size;
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 7c58c44662b8..8d10d9d2e830 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -223,7 +223,7 @@ struct mtd_part {
  * @partitions_lock: lock protecting accesses to the partition list. Protects
  *		     not only the master partition list, but also all
  *		     sub-partitions.
- * @suspended: et to 1 when the device is suspended, 0 otherwise
+ * @suspended: set to 1 when the device is suspended, 0 otherwise
  *
  * This struct is embedded in mtd_info and contains master-specific
  * properties/fields. The master is the root MTD device from the MTD partition
@@ -379,7 +379,7 @@ struct mtd_info {
 
 	struct module *owner;
 	struct device dev;
-	int usecount;
+	struct kref refcnt;
 	struct mtd_debug_info dbg;
 	struct nvmem_device *nvmem;
 	struct nvmem_device *otp_user_nvmem;
diff --git a/include/linux/mtd/nand-ecc-mxic.h b/include/linux/mtd/nand-ecc-mxic.h
index b125926e458c..0da4b2999576 100644
--- a/include/linux/mtd/nand-ecc-mxic.h
+++ b/include/linux/mtd/nand-ecc-mxic.h
@@ -16,7 +16,7 @@ struct mxic_ecc_engine;
 
 #if IS_ENABLED(CONFIG_MTD_NAND_ECC_MXIC) && IS_REACHABLE(CONFIG_MTD_NAND_CORE)
 
-struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void);
+const struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void);
 struct nand_ecc_engine *mxic_ecc_get_pipelined_engine(struct platform_device *spi_pdev);
 void mxic_ecc_put_pipelined_engine(struct nand_ecc_engine *eng);
 int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng,
@@ -24,7 +24,7 @@ int mxic_ecc_process_data_pipelined(struct nand_ecc_engine *eng,
 
 #else /* !CONFIG_MTD_NAND_ECC_MXIC */
 
-static inline struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void)
+static inline const struct nand_ecc_engine_ops *mxic_ecc_get_pipelined_ops(void)
 {
 	return NULL;
 }
diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h
new file mode 100644
index 000000000000..e8201d1b7cf9
--- /dev/null
+++ b/include/linux/mtd/nand-qpic-common.h
@@ -0,0 +1,483 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * QCOM QPIC common APIs header file
+ *
+ * Copyright (c) 2023 Qualcomm Inc.
+ * Authors:	Md sadre Alam	<quic_mdalam@quicinc.com>
+ *
+ */
+#ifndef __MTD_NAND_QPIC_COMMON_H__
+#define __MTD_NAND_QPIC_COMMON_H__
+
+/* NANDc reg offsets */
+#define	NAND_FLASH_CMD			0x00
+#define	NAND_ADDR0			0x04
+#define	NAND_ADDR1			0x08
+#define	NAND_FLASH_CHIP_SELECT		0x0c
+#define	NAND_EXEC_CMD			0x10
+#define	NAND_FLASH_STATUS		0x14
+#define	NAND_BUFFER_STATUS		0x18
+#define	NAND_DEV0_CFG0			0x20
+#define	NAND_DEV0_CFG1			0x24
+#define	NAND_DEV0_ECC_CFG		0x28
+#define	NAND_AUTO_STATUS_EN		0x2c
+#define	NAND_DEV1_CFG0			0x30
+#define	NAND_DEV1_CFG1			0x34
+#define	NAND_READ_ID			0x40
+#define	NAND_READ_STATUS		0x44
+#define	NAND_DEV_CMD0			0xa0
+#define	NAND_DEV_CMD1			0xa4
+#define	NAND_DEV_CMD2			0xa8
+#define	NAND_DEV_CMD_VLD		0xac
+#define	SFLASHC_BURST_CFG		0xe0
+#define	NAND_ERASED_CW_DETECT_CFG	0xe8
+#define	NAND_ERASED_CW_DETECT_STATUS	0xec
+#define	NAND_EBI2_ECC_BUF_CFG		0xf0
+#define	FLASH_BUF_ACC			0x100
+
+#define	NAND_CTRL			0xf00
+#define	NAND_VERSION			0xf08
+#define	NAND_READ_LOCATION_0		0xf20
+#define	NAND_READ_LOCATION_1		0xf24
+#define	NAND_READ_LOCATION_2		0xf28
+#define	NAND_READ_LOCATION_3		0xf2c
+#define	NAND_READ_LOCATION_LAST_CW_0	0xf40
+#define	NAND_READ_LOCATION_LAST_CW_1	0xf44
+#define	NAND_READ_LOCATION_LAST_CW_2	0xf48
+#define	NAND_READ_LOCATION_LAST_CW_3	0xf4c
+
+/* dummy register offsets, used by qcom_write_reg_dma */
+#define	NAND_DEV_CMD1_RESTORE		0xdead
+#define	NAND_DEV_CMD_VLD_RESTORE	0xbeef
+
+/* NAND_FLASH_CMD bits */
+#define	PAGE_ACC			BIT(4)
+#define	LAST_PAGE			BIT(5)
+
+/* NAND_FLASH_CHIP_SELECT bits */
+#define	NAND_DEV_SEL			0
+#define	DM_EN				BIT(2)
+
+/* NAND_FLASH_STATUS bits */
+#define	FS_OP_ERR			BIT(4)
+#define	FS_READY_BSY_N			BIT(5)
+#define	FS_MPU_ERR			BIT(8)
+#define	FS_DEVICE_STS_ERR		BIT(16)
+#define	FS_DEVICE_WP			BIT(23)
+
+/* NAND_BUFFER_STATUS bits */
+#define	BS_UNCORRECTABLE_BIT		BIT(8)
+#define	BS_CORRECTABLE_ERR_MSK		0x1f
+
+/* NAND_DEVn_CFG0 bits */
+#define	DISABLE_STATUS_AFTER_WRITE	BIT(4)
+#define	CW_PER_PAGE_MASK		GENMASK(8, 6)
+#define	UD_SIZE_BYTES_MASK		GENMASK(18, 9)
+#define	ECC_PARITY_SIZE_BYTES_RS	GENMASK(22, 19)
+#define	SPARE_SIZE_BYTES_MASK		GENMASK(26, 23)
+#define	NUM_ADDR_CYCLES_MASK		GENMASK(29, 27)
+#define	STATUS_BFR_READ			BIT(30)
+#define	SET_RD_MODE_AFTER_STATUS	BIT(31)
+
+/* NAND_DEVn_CFG0 bits */
+#define	DEV0_CFG1_ECC_DISABLE		BIT(0)
+#define	WIDE_FLASH			BIT(1)
+#define	NAND_RECOVERY_CYCLES_MASK	GENMASK(4, 2)
+#define	CS_ACTIVE_BSY			BIT(5)
+#define	BAD_BLOCK_BYTE_NUM_MASK		GENMASK(15, 6)
+#define	BAD_BLOCK_IN_SPARE_AREA		BIT(16)
+#define	WR_RD_BSY_GAP_MASK		GENMASK(22, 17)
+#define	ENABLE_BCH_ECC			BIT(27)
+
+/* NAND_DEV0_ECC_CFG bits */
+#define	ECC_CFG_ECC_DISABLE		BIT(0)
+#define	ECC_SW_RESET			BIT(1)
+#define	ECC_MODE_MASK			GENMASK(5, 4)
+#define	ECC_MODE_4BIT			0
+#define	ECC_MODE_8BIT			1
+#define	ECC_PARITY_SIZE_BYTES_BCH_MASK	GENMASK(12, 8)
+#define	ECC_NUM_DATA_BYTES_MASK		GENMASK(25, 16)
+#define	ECC_FORCE_CLK_OPEN		BIT(30)
+
+/* NAND_DEV_CMD1 bits */
+#define	READ_ADDR_MASK			GENMASK(7, 0)
+
+/* NAND_DEV_CMD_VLD bits */
+#define	READ_START_VLD			BIT(0)
+#define	READ_STOP_VLD			BIT(1)
+#define	WRITE_START_VLD			BIT(2)
+#define	ERASE_START_VLD			BIT(3)
+#define	SEQ_READ_START_VLD		BIT(4)
+
+/* NAND_EBI2_ECC_BUF_CFG bits */
+#define	NUM_STEPS_MASK			GENMASK(9, 0)
+
+/* NAND_ERASED_CW_DETECT_CFG bits */
+#define	ERASED_CW_ECC_MASK		1
+#define	AUTO_DETECT_RES			0
+#define	MASK_ECC			BIT(ERASED_CW_ECC_MASK)
+#define	RESET_ERASED_DET		BIT(AUTO_DETECT_RES)
+#define	ACTIVE_ERASED_DET		(0 << AUTO_DETECT_RES)
+#define	CLR_ERASED_PAGE_DET		(RESET_ERASED_DET | MASK_ECC)
+#define	SET_ERASED_PAGE_DET		(ACTIVE_ERASED_DET | MASK_ECC)
+
+/* NAND_ERASED_CW_DETECT_STATUS bits */
+#define	PAGE_ALL_ERASED			BIT(7)
+#define	CODEWORD_ALL_ERASED		BIT(6)
+#define	PAGE_ERASED			BIT(5)
+#define	CODEWORD_ERASED			BIT(4)
+#define	ERASED_PAGE			(PAGE_ALL_ERASED | PAGE_ERASED)
+#define	ERASED_CW			(CODEWORD_ALL_ERASED | CODEWORD_ERASED)
+
+/* NAND_READ_LOCATION_n bits */
+#define READ_LOCATION_OFFSET_MASK	GENMASK(9, 0)
+#define READ_LOCATION_SIZE_MASK		GENMASK(25, 16)
+#define READ_LOCATION_LAST_MASK		BIT(31)
+
+/* Version Mask */
+#define	NAND_VERSION_MAJOR_MASK		0xf0000000
+#define	NAND_VERSION_MAJOR_SHIFT	28
+#define	NAND_VERSION_MINOR_MASK		0x0fff0000
+#define	NAND_VERSION_MINOR_SHIFT	16
+
+/* NAND OP_CMDs */
+#define	OP_PAGE_READ			0x2
+#define	OP_PAGE_READ_WITH_ECC		0x3
+#define	OP_PAGE_READ_WITH_ECC_SPARE	0x4
+#define	OP_PAGE_READ_ONFI_READ		0x5
+#define	OP_PROGRAM_PAGE			0x6
+#define	OP_PAGE_PROGRAM_WITH_ECC	0x7
+#define	OP_PROGRAM_PAGE_SPARE		0x9
+#define	OP_BLOCK_ERASE			0xa
+#define	OP_CHECK_STATUS			0xc
+#define	OP_FETCH_ID			0xb
+#define	OP_RESET_DEVICE			0xd
+
+/* Default Value for NAND_DEV_CMD_VLD */
+#define NAND_DEV_CMD_VLD_VAL		(READ_START_VLD | WRITE_START_VLD | \
+					 ERASE_START_VLD | SEQ_READ_START_VLD)
+
+/* NAND_CTRL bits */
+#define	BAM_MODE_EN			BIT(0)
+
+/*
+ * the NAND controller performs reads/writes with ECC in 516 byte chunks.
+ * the driver calls the chunks 'step' or 'codeword' interchangeably
+ */
+#define	NANDC_STEP_SIZE			512
+
+/*
+ * the largest page size we support is 8K, this will have 16 steps/codewords
+ * of 512 bytes each
+ */
+#define	MAX_NUM_STEPS			(SZ_8K / NANDC_STEP_SIZE)
+
+/* we read at most 3 registers per codeword scan */
+#define	MAX_REG_RD			(3 * MAX_NUM_STEPS)
+
+/* ECC modes supported by the controller */
+#define	ECC_NONE	BIT(0)
+#define	ECC_RS_4BIT	BIT(1)
+#define	ECC_BCH_4BIT	BIT(2)
+#define	ECC_BCH_8BIT	BIT(3)
+
+/*
+ * Returns the actual register address for all NAND_DEV_ registers
+ * (i.e. NAND_DEV_CMD0, NAND_DEV_CMD1, NAND_DEV_CMD2 and NAND_DEV_CMD_VLD)
+ */
+#define dev_cmd_reg_addr(nandc, reg) ((nandc)->props->dev_cmd_reg_start + (reg))
+
+/* Returns the dma address for reg read buffer */
+#define reg_buf_dma_addr(chip, vaddr) \
+	((chip)->reg_read_dma + \
+	((u8 *)(vaddr) - (u8 *)(chip)->reg_read_buf))
+
+#define QPIC_PER_CW_CMD_ELEMENTS	32
+#define QPIC_PER_CW_CMD_SGL		32
+#define QPIC_PER_CW_DATA_SGL		8
+
+#define QPIC_NAND_COMPLETION_TIMEOUT	msecs_to_jiffies(2000)
+
+/*
+ * Flags used in DMA descriptor preparation helper functions
+ * (i.e. qcom_read_reg_dma/qcom_write_reg_dma/qcom_read_data_dma/qcom_write_data_dma)
+ */
+/* Don't set the EOT in current tx BAM sgl */
+#define NAND_BAM_NO_EOT			BIT(0)
+/* Set the NWD flag in current BAM sgl */
+#define NAND_BAM_NWD			BIT(1)
+/* Finish writing in the current BAM sgl and start writing in another BAM sgl */
+#define NAND_BAM_NEXT_SGL		BIT(2)
+/*
+ * Erased codeword status is being used two times in single transfer so this
+ * flag will determine the current value of erased codeword status register
+ */
+#define NAND_ERASED_CW_SET		BIT(4)
+
+#define MAX_ADDRESS_CYCLE		5
+
+/*
+ * This data type corresponds to the BAM transaction which will be used for all
+ * NAND transfers.
+ * @bam_ce - the array of BAM command elements
+ * @cmd_sgl - sgl for NAND BAM command pipe
+ * @data_sgl - sgl for NAND BAM consumer/producer pipe
+ * @last_data_desc - last DMA desc in data channel (tx/rx).
+ * @last_cmd_desc - last DMA desc in command channel.
+ * @txn_done - completion for NAND transfer.
+ * @bam_ce_nitems - the number of elements in the @bam_ce array
+ * @cmd_sgl_nitems - the number of elements in the @cmd_sgl array
+ * @data_sgl_nitems - the number of elements in the @data_sgl array
+ * @bam_ce_pos - the index in bam_ce which is available for next sgl
+ * @bam_ce_start - the index in bam_ce which marks the start position ce
+ *		   for current sgl. It will be used for size calculation
+ *		   for current sgl
+ * @cmd_sgl_pos - current index in command sgl.
+ * @cmd_sgl_start - start index in command sgl.
+ * @tx_sgl_pos - current index in data sgl for tx.
+ * @tx_sgl_start - start index in data sgl for tx.
+ * @rx_sgl_pos - current index in data sgl for rx.
+ * @rx_sgl_start - start index in data sgl for rx.
+ */
+struct bam_transaction {
+	struct bam_cmd_element *bam_ce;
+	struct scatterlist *cmd_sgl;
+	struct scatterlist *data_sgl;
+	struct dma_async_tx_descriptor *last_data_desc;
+	struct dma_async_tx_descriptor *last_cmd_desc;
+	struct completion txn_done;
+
+	unsigned int bam_ce_nitems;
+	unsigned int cmd_sgl_nitems;
+	unsigned int data_sgl_nitems;
+
+	struct_group(bam_positions,
+		u32 bam_ce_pos;
+		u32 bam_ce_start;
+		u32 cmd_sgl_pos;
+		u32 cmd_sgl_start;
+		u32 tx_sgl_pos;
+		u32 tx_sgl_start;
+		u32 rx_sgl_pos;
+		u32 rx_sgl_start;
+
+	);
+};
+
+/*
+ * This data type corresponds to the nand dma descriptor
+ * @dma_desc - low level DMA engine descriptor
+ * @list - list for desc_info
+ *
+ * @adm_sgl - sgl which will be used for single sgl dma descriptor. Only used by
+ *	      ADM
+ * @bam_sgl - sgl which will be used for dma descriptor. Only used by BAM
+ * @sgl_cnt - number of SGL in bam_sgl. Only used by BAM
+ * @dir - DMA transfer direction
+ */
+struct desc_info {
+	struct dma_async_tx_descriptor *dma_desc;
+	struct list_head node;
+
+	union {
+		struct scatterlist adm_sgl;
+		struct {
+			struct scatterlist *bam_sgl;
+			int sgl_cnt;
+		};
+	};
+	enum dma_data_direction dir;
+};
+
+/*
+ * holds the current register values that we want to write. acts as a contiguous
+ * chunk of memory which we use to write the controller registers through DMA.
+ */
+struct nandc_regs {
+	__le32 cmd;
+	__le32 addr0;
+	__le32 addr1;
+	__le32 chip_sel;
+	__le32 exec;
+
+	__le32 cfg0;
+	__le32 cfg1;
+	__le32 ecc_bch_cfg;
+
+	__le32 clrflashstatus;
+	__le32 clrreadstatus;
+
+	__le32 cmd1;
+	__le32 vld;
+
+	__le32 orig_cmd1;
+	__le32 orig_vld;
+
+	__le32 ecc_buf_cfg;
+	__le32 read_location0;
+	__le32 read_location1;
+	__le32 read_location2;
+	__le32 read_location3;
+	__le32 read_location_last0;
+	__le32 read_location_last1;
+	__le32 read_location_last2;
+	__le32 read_location_last3;
+	__le32 spi_cfg;
+	__le32 num_addr_cycle;
+	__le32 busy_wait_cnt;
+	__le32 flash_feature;
+
+	__le32 erased_cw_detect_cfg_clr;
+	__le32 erased_cw_detect_cfg_set;
+};
+
+/*
+ * NAND controller data struct
+ *
+ * @dev:			parent device
+ *
+ * @base:			MMIO base
+ *
+ * @core_clk:			controller clock
+ * @aon_clk:			another controller clock
+ * @iomacro_clk:		io macro clock
+ *
+ * @regs:			a contiguous chunk of memory for DMA register
+ *				writes. contains the register values to be
+ *				written to controller
+ *
+ * @props:			properties of current NAND controller,
+ *				initialized via DT match data
+ *
+ * @controller:			base controller structure
+ * @qspi:			qpic spi structure
+ * @host_list:			list containing all the chips attached to the
+ *				controller
+ *
+ * @chan:			dma channel
+ * @cmd_crci:			ADM DMA CRCI for command flow control
+ * @data_crci:			ADM DMA CRCI for data flow control
+ *
+ * @desc_list:			DMA descriptor list (list of desc_infos)
+ *
+ * @data_buffer:		our local DMA buffer for page read/writes,
+ *				used when we can't use the buffer provided
+ *				by upper layers directly
+ * @reg_read_buf:		local buffer for reading back registers via DMA
+ *
+ * @base_phys:			physical base address of controller registers
+ * @base_dma:			dma base address of controller registers
+ * @reg_read_dma:		contains dma address for register read buffer
+ *
+ * @buf_size/count/start:	markers for chip->legacy.read_buf/write_buf
+ *				functions
+ * @max_cwperpage:		maximum QPIC codewords required. calculated
+ *				from all connected NAND devices pagesize
+ *
+ * @reg_read_pos:		marker for data read in reg_read_buf
+ *
+ * @cmd1/vld:			some fixed controller register values
+ *
+ * @exec_opwrite:		flag to select correct number of code word
+ *				while reading status
+ */
+struct qcom_nand_controller {
+	struct device *dev;
+
+	void __iomem *base;
+
+	struct clk *core_clk;
+	struct clk *aon_clk;
+
+	struct nandc_regs *regs;
+	struct bam_transaction *bam_txn;
+
+	const struct qcom_nandc_props *props;
+
+	struct nand_controller *controller;
+	struct qpic_spi_nand *qspi;
+	struct list_head host_list;
+
+	union {
+		/* will be used only by QPIC for BAM DMA */
+		struct {
+			struct dma_chan *tx_chan;
+			struct dma_chan *rx_chan;
+			struct dma_chan *cmd_chan;
+		};
+
+		/* will be used only by EBI2 for ADM DMA */
+		struct {
+			struct dma_chan *chan;
+			unsigned int cmd_crci;
+			unsigned int data_crci;
+		};
+	};
+
+	struct list_head desc_list;
+
+	u8		*data_buffer;
+	__le32		*reg_read_buf;
+
+	phys_addr_t base_phys;
+	dma_addr_t base_dma;
+	dma_addr_t reg_read_dma;
+
+	int		buf_size;
+	int		buf_count;
+	int		buf_start;
+	unsigned int	max_cwperpage;
+
+	int reg_read_pos;
+
+	u32 cmd1, vld;
+	bool exec_opwrite;
+};
+
+/*
+ * This data type corresponds to the NAND controller properties which varies
+ * among different NAND controllers.
+ * @ecc_modes - ecc mode for NAND
+ * @dev_cmd_reg_start - NAND_DEV_CMD_* registers starting offset
+ * @supports_bam - whether NAND controller is using BAM
+ * @nandc_part_of_qpic - whether NAND controller is part of qpic IP
+ * @qpic_version2 - flag to indicate QPIC IP version 2
+ * @use_codeword_fixup - whether NAND has different layout for boot partitions
+ */
+struct qcom_nandc_props {
+	u32 ecc_modes;
+	u32 dev_cmd_reg_start;
+	u32 bam_offset;
+	bool supports_bam;
+	bool nandc_part_of_qpic;
+	bool qpic_version2;
+	bool use_codeword_fixup;
+};
+
+void qcom_free_bam_transaction(struct qcom_nand_controller *nandc);
+struct bam_transaction *qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc);
+void qcom_clear_bam_transaction(struct qcom_nand_controller *nandc);
+void qcom_qpic_bam_dma_done(void *data);
+void qcom_nandc_dev_to_mem(struct qcom_nand_controller *nandc, bool is_cpu);
+int qcom_prepare_bam_async_desc(struct qcom_nand_controller *nandc,
+				struct dma_chan *chan, unsigned long flags);
+int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read,
+			       int reg_off, const void *vaddr, int size, unsigned int flags);
+int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read,
+				const void *vaddr, int size, unsigned int flags);
+int qcom_prep_adm_dma_desc(struct qcom_nand_controller *nandc, bool read, int reg_off,
+			   const void *vaddr, int size, bool flow_control);
+int qcom_read_reg_dma(struct qcom_nand_controller *nandc, int first, int num_regs,
+		      unsigned int flags);
+int qcom_write_reg_dma(struct qcom_nand_controller *nandc, __le32 *vaddr, int first,
+		       int num_regs, unsigned int flags);
+int qcom_read_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr,
+		       int size, unsigned int flags);
+int qcom_write_data_dma(struct qcom_nand_controller *nandc, int reg_off, const u8 *vaddr,
+			int size, unsigned int flags);
+int qcom_submit_descs(struct qcom_nand_controller *nandc);
+void qcom_clear_read_regs(struct qcom_nand_controller *nandc);
+void qcom_nandc_unalloc(struct qcom_nand_controller *nandc);
+int qcom_nandc_alloc(struct qcom_nand_controller *nandc);
+#endif
+
diff --git a/include/linux/mtd/nand.h b/include/linux/mtd/nand.h
index b2996dc987ff..09c8c93e4dba 100644
--- a/include/linux/mtd/nand.h
+++ b/include/linux/mtd/nand.h
@@ -21,7 +21,7 @@ struct nand_device;
  * @oobsize: OOB area size
  * @pages_per_eraseblock: number of pages per eraseblock
  * @eraseblocks_per_lun: number of eraseblocks per LUN (Logical Unit Number)
- * @max_bad_eraseblocks_per_lun: maximum number of eraseblocks per LUN
+ * @max_bad_eraseblocks_per_lun: maximum number of bad eraseblocks per LUN
  * @planes_per_lun: number of planes per LUN
  * @luns_per_target: number of LUN per target (target is a synonym for die)
  * @ntargets: total number of targets exposed by the NAND device
@@ -103,6 +103,8 @@ enum nand_page_io_req_type {
  * @ooblen: the number of OOB bytes to read from/write to this page
  * @oobbuf: buffer to store OOB data in or get OOB data from
  * @mode: one of the %MTD_OPS_XXX mode
+ * @continuous: no need to start over the operation at the end of each page, the
+ * NAND device will automatically prepare the next one
  *
  * This object is used to pass per-page I/O requests to NAND sub-layers. This
  * way all useful information are already formatted in a useful way and
@@ -125,6 +127,7 @@ struct nand_page_io_req {
 		void *in;
 	} oobbuf;
 	int mode;
+	bool continuous;
 };
 
 const struct mtd_ooblayout_ops *nand_get_small_page_ooblayout(void);
@@ -290,7 +293,7 @@ enum nand_ecc_engine_integration {
 struct nand_ecc_engine {
 	struct device *dev;
 	struct list_head node;
-	struct nand_ecc_engine_ops *ops;
+	const struct nand_ecc_engine_ops *ops;
 	enum nand_ecc_engine_integration integration;
 	void *priv;
 };
@@ -906,19 +909,19 @@ static inline void nanddev_pos_next_page(struct nand_device *nand,
 }
 
 /**
- * nand_io_iter_init - Initialize a NAND I/O iterator
+ * nand_io_page_iter_init - Initialize a NAND I/O iterator
  * @nand: NAND device
  * @offs: absolute offset
  * @req: MTD request
  * @iter: NAND I/O iterator
  *
  * Initializes a NAND iterator based on the information passed by the MTD
- * layer.
+ * layer for page jumps.
  */
-static inline void nanddev_io_iter_init(struct nand_device *nand,
-					enum nand_page_io_req_type reqtype,
-					loff_t offs, struct mtd_oob_ops *req,
-					struct nand_io_iter *iter)
+static inline void nanddev_io_page_iter_init(struct nand_device *nand,
+					     enum nand_page_io_req_type reqtype,
+					     loff_t offs, struct mtd_oob_ops *req,
+					     struct nand_io_iter *iter)
 {
 	struct mtd_info *mtd = nanddev_to_mtd(nand);
 
@@ -937,6 +940,43 @@ static inline void nanddev_io_iter_init(struct nand_device *nand,
 	iter->req.ooblen = min_t(unsigned int,
 				 iter->oobbytes_per_page - iter->req.ooboffs,
 				 iter->oobleft);
+	iter->req.continuous = false;
+}
+
+/**
+ * nand_io_block_iter_init - Initialize a NAND I/O iterator
+ * @nand: NAND device
+ * @offs: absolute offset
+ * @req: MTD request
+ * @iter: NAND I/O iterator
+ *
+ * Initializes a NAND iterator based on the information passed by the MTD
+ * layer for block jumps (no OOB)
+ *
+ * In practice only reads may leverage this iterator.
+ */
+static inline void nanddev_io_block_iter_init(struct nand_device *nand,
+					      enum nand_page_io_req_type reqtype,
+					      loff_t offs, struct mtd_oob_ops *req,
+					      struct nand_io_iter *iter)
+{
+	unsigned int offs_in_eb;
+
+	iter->req.type = reqtype;
+	iter->req.mode = req->mode;
+	iter->req.dataoffs = nanddev_offs_to_pos(nand, offs, &iter->req.pos);
+	iter->req.ooboffs = 0;
+	iter->oobbytes_per_page = 0;
+	iter->dataleft = req->len;
+	iter->oobleft = 0;
+	iter->req.databuf.in = req->datbuf;
+	offs_in_eb = (nand->memorg.pagesize * iter->req.pos.page) + iter->req.dataoffs;
+	iter->req.datalen = min_t(unsigned int,
+				  nanddev_eraseblock_size(nand) - offs_in_eb,
+				  iter->dataleft);
+	iter->req.oobbuf.in = NULL;
+	iter->req.ooblen = 0;
+	iter->req.continuous = true;
 }
 
 /**
@@ -963,6 +1003,25 @@ static inline void nanddev_io_iter_next_page(struct nand_device *nand,
 }
 
 /**
+ * nand_io_iter_next_block - Move to the next block
+ * @nand: NAND device
+ * @iter: NAND I/O iterator
+ *
+ * Updates the @iter to point to the next block.
+ * No OOB handling available.
+ */
+static inline void nanddev_io_iter_next_block(struct nand_device *nand,
+					      struct nand_io_iter *iter)
+{
+	nanddev_pos_next_eraseblock(nand, &iter->req.pos);
+	iter->dataleft -= iter->req.datalen;
+	iter->req.databuf.in += iter->req.datalen;
+	iter->req.dataoffs = 0;
+	iter->req.datalen = min_t(unsigned int, nanddev_eraseblock_size(nand),
+				  iter->dataleft);
+}
+
+/**
  * nand_io_iter_end - Should end iteration or not
  * @nand: NAND device
  * @iter: NAND I/O iterator
@@ -990,13 +1049,28 @@ static inline bool nanddev_io_iter_end(struct nand_device *nand,
  * @req: MTD I/O request
  * @iter: NAND I/O iterator
  *
- * Should be used for iterate over pages that are contained in an MTD request.
+ * Should be used for iterating over pages that are contained in an MTD request.
  */
 #define nanddev_io_for_each_page(nand, type, start, req, iter)		\
-	for (nanddev_io_iter_init(nand, type, start, req, iter);	\
+	for (nanddev_io_page_iter_init(nand, type, start, req, iter);	\
 	     !nanddev_io_iter_end(nand, iter);				\
 	     nanddev_io_iter_next_page(nand, iter))
 
+/**
+ * nand_io_for_each_block - Iterate over all NAND pages contained in an MTD I/O
+ *			    request, one block at a time
+ * @nand: NAND device
+ * @start: start address to read/write from
+ * @req: MTD I/O request
+ * @iter: NAND I/O iterator
+ *
+ * Should be used for iterating over blocks that are contained in an MTD request.
+ */
+#define nanddev_io_for_each_block(nand, type, start, req, iter)		\
+	for (nanddev_io_block_iter_init(nand, type, start, req, iter);	\
+	     !nanddev_io_iter_end(nand, iter);				\
+	     nanddev_io_iter_next_block(nand, iter))
+
 bool nanddev_isbad(struct nand_device *nand, const struct nand_pos *pos);
 bool nanddev_isreserved(struct nand_device *nand, const struct nand_pos *pos);
 int nanddev_markbad(struct nand_device *nand, const struct nand_pos *pos);
@@ -1062,4 +1136,9 @@ static inline bool nanddev_bbt_is_initialized(struct nand_device *nand)
 int nanddev_mtd_erase(struct mtd_info *mtd, struct erase_info *einfo);
 int nanddev_mtd_max_bad_blocks(struct mtd_info *mtd, loff_t offs, size_t len);
 
+int nand_check_erased_ecc_chunk(void *data, int datalen,
+				void *ecc, int ecclen,
+				void *extraoob, int extraooblen,
+				int threshold);
+
 #endif /* __LINUX_MTD_NAND_H */
diff --git a/include/linux/mtd/onfi.h b/include/linux/mtd/onfi.h
index a7376f9beddf..55ab2e4d62f9 100644
--- a/include/linux/mtd/onfi.h
+++ b/include/linux/mtd/onfi.h
@@ -55,6 +55,7 @@
 #define ONFI_SUBFEATURE_PARAM_LEN	4
 
 /* ONFI optional commands SET/GET FEATURES supported? */
+#define ONFI_OPT_CMD_READ_CACHE		BIT(1)
 #define ONFI_OPT_CMD_SET_GET_FEATURES	BIT(2)
 
 struct nand_onfi_params {
diff --git a/include/linux/mtd/qinfo.h b/include/linux/mtd/qinfo.h
index 2e3f43788d48..0421f12156b5 100644
--- a/include/linux/mtd/qinfo.h
+++ b/include/linux/mtd/qinfo.h
@@ -24,7 +24,7 @@ struct lpddr_private {
 	struct qinfo_chip *qinfo;
 	int numchips;
 	unsigned long chipshift;
-	struct flchip chips[];
+	struct flchip chips[] __counted_by(numchips);
 };
 
 /* qinfo_query_info structure contains request information for
diff --git a/include/linux/mtd/rawnand.h b/include/linux/mtd/rawnand.h
index 5159d692f9ce..d30bdc3fcfd7 100644
--- a/include/linux/mtd/rawnand.h
+++ b/include/linux/mtd/rawnand.h
@@ -225,6 +225,7 @@ struct gpio_desc;
  * struct nand_parameters - NAND generic parameters from the parameter page
  * @model: Model name
  * @supports_set_get_features: The NAND chip supports setting/getting features
+ * @supports_read_cache: The NAND chip supports read cache operations
  * @set_feature_list: Bitmap of features that can be set
  * @get_feature_list: Bitmap of features that can be get
  * @onfi: ONFI specific parameters
@@ -233,6 +234,7 @@ struct nand_parameters {
 	/* Generic parameters */
 	const char *model;
 	bool supports_set_get_features;
+	bool supports_read_cache;
 	DECLARE_BITMAP(set_feature_list, ONFI_FEATURE_NUMBER);
 	DECLARE_BITMAP(get_feature_list, ONFI_FEATURE_NUMBER);
 
@@ -1001,6 +1003,8 @@ struct nand_op_parser {
 /**
  * struct nand_operation - NAND operation descriptor
  * @cs: the CS line to select for this NAND operation
+ * @deassert_wp: set to true when the operation requires the WP pin to be
+ *		 de-asserted (ERASE, PROG, ...)
  * @instrs: array of instructions to execute
  * @ninstrs: length of the @instrs array
  *
@@ -1008,6 +1012,7 @@ struct nand_op_parser {
  */
 struct nand_operation {
 	unsigned int cs;
+	bool deassert_wp;
 	const struct nand_op_instr *instrs;
 	unsigned int ninstrs;
 };
@@ -1019,6 +1024,14 @@ struct nand_operation {
 		.ninstrs = ARRAY_SIZE(_instrs),			\
 	}
 
+#define NAND_DESTRUCTIVE_OPERATION(_cs, _instrs)		\
+	{							\
+		.cs = _cs,					\
+		.deassert_wp = true,				\
+		.instrs = _instrs,				\
+		.ninstrs = ARRAY_SIZE(_instrs),			\
+	}
+
 int nand_op_parser_exec_op(struct nand_chip *chip,
 			   const struct nand_op_parser *parser,
 			   const struct nand_operation *op, bool check_only);
@@ -1102,6 +1115,7 @@ struct nand_controller_ops {
  *			the bus without restarting an entire read operation nor
  *			changing the column.
  * @supported_op.cont_read: The controller supports sequential cache reads.
+ * @controller_wp:	the controller is in charge of handling the WP pin.
  */
 struct nand_controller {
 	struct mutex lock;
@@ -1110,6 +1124,7 @@ struct nand_controller {
 		unsigned int data_only_read: 1;
 		unsigned int cont_read: 1;
 	} supported_op;
+	bool controller_wp;
 };
 
 static inline void nand_controller_init(struct nand_controller *nfc)
@@ -1263,6 +1278,7 @@ struct nand_secure_region {
  * @cont_read: Sequential page read internals
  * @cont_read.ongoing: Whether a continuous read is ongoing or not
  * @cont_read.first_page: Start of the continuous read operation
+ * @cont_read.pause_page: End of the current sequential cache read operation
  * @cont_read.last_page: End of the continuous read operation
  * @controller: The hardware controller	structure which is shared among multiple
  *              independent devices
@@ -1319,6 +1335,7 @@ struct nand_chip {
 	struct {
 		bool ongoing;
 		unsigned int first_page;
+		unsigned int pause_page;
 		unsigned int last_page;
 	} cont_read;
 
@@ -1502,11 +1519,6 @@ int rawnand_sw_bch_correct(struct nand_chip *chip, unsigned char *buf,
 			   unsigned char *read_ecc, unsigned char *calc_ecc);
 void rawnand_sw_bch_cleanup(struct nand_chip *chip);
 
-int nand_check_erased_ecc_chunk(void *data, int datalen,
-				void *ecc, int ecclen,
-				void *extraoob, int extraooblen,
-				int threshold);
-
 int nand_ecc_choose_conf(struct nand_chip *chip,
 			 const struct nand_ecc_caps *caps, int oobavail);
 
@@ -1540,6 +1552,7 @@ int nand_reset_op(struct nand_chip *chip);
 int nand_readid_op(struct nand_chip *chip, u8 addr, void *buf,
 		   unsigned int len);
 int nand_status_op(struct nand_chip *chip, u8 *status);
+int nand_exit_status_op(struct nand_chip *chip);
 int nand_erase_op(struct nand_chip *chip, unsigned int eraseblock);
 int nand_read_page_op(struct nand_chip *chip, unsigned int page,
 		      unsigned int offset_in_page, void *buf, unsigned int len);
diff --git a/include/linux/mtd/spear_smi.h b/include/linux/mtd/spear_smi.h
index 581603ac1277..871634862627 100644
--- a/include/linux/mtd/spear_smi.h
+++ b/include/linux/mtd/spear_smi.h
@@ -31,12 +31,12 @@
  * struct spear_smi_flash_info - platform structure for passing flash
  * information
  *
- * name: name of the serial nor flash for identification
- * mem_base: the memory base on which the flash is mapped
- * size: size of the flash in bytes
- * partitions: parition details
- * nr_partitions: number of partitions
- * fast_mode: whether flash supports fast mode
+ * @name: name of the serial nor flash for identification
+ * @mem_base: the memory base on which the flash is mapped
+ * @size: size of the flash in bytes
+ * @partitions: parition details
+ * @nr_partitions: number of partitions
+ * @fast_mode: whether flash supports fast mode
  */
 
 struct spear_smi_flash_info {
@@ -51,9 +51,10 @@ struct spear_smi_flash_info {
 /**
  * struct spear_smi_plat_data - platform structure for configuring smi
  *
- * clk_rate: clk rate at which SMI must operate
- * num_flashes: number of flashes present on board
- * board_flash_info: specific details of each flash present on board
+ * @clk_rate: clk rate at which SMI must operate
+ * @num_flashes: number of flashes present on board
+ * @board_flash_info: specific details of each flash present on board
+ * @np: array of DT node pointers for all possible flash chip devices
  */
 struct spear_smi_plat_data {
 	unsigned long clk_rate;
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 3e285c09d16d..ce76f5c632e1 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -20,126 +20,218 @@
  * Standard SPI NAND flash operations
  */
 
-#define SPINAND_RESET_OP						\
+#define SPINAND_RESET_1S_0_0_OP						\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xff, 1),				\
 		   SPI_MEM_OP_NO_ADDR,					\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_WR_EN_DIS_OP(enable)					\
+#define SPINAND_WR_EN_DIS_1S_0_0_OP(enable)					\
 	SPI_MEM_OP(SPI_MEM_OP_CMD((enable) ? 0x06 : 0x04, 1),		\
 		   SPI_MEM_OP_NO_ADDR,					\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_READID_OP(naddr, ndummy, buf, len)			\
+#define SPINAND_READID_1S_1S_1S_OP(naddr, ndummy, buf, len)		\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x9f, 1),				\
 		   SPI_MEM_OP_ADDR(naddr, 0, 1),			\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 1))
 
-#define SPINAND_SET_FEATURE_OP(reg, valptr)				\
+#define SPINAND_SET_FEATURE_1S_1S_1S_OP(reg, valptr)			\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x1f, 1),				\
 		   SPI_MEM_OP_ADDR(1, reg, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_DATA_OUT(1, valptr, 1))
 
-#define SPINAND_GET_FEATURE_OP(reg, valptr)				\
+#define SPINAND_GET_FEATURE_1S_1S_1S_OP(reg, valptr)			\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0f, 1),				\
 		   SPI_MEM_OP_ADDR(1, reg, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_DATA_IN(1, valptr, 1))
 
-#define SPINAND_BLK_ERASE_OP(addr)					\
+#define SPINAND_BLK_ERASE_1S_1S_0_OP(addr)				\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xd8, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_PAGE_READ_OP(addr)					\
+#define SPINAND_PAGE_READ_1S_1S_0_OP(addr)				\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x13, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_PAGE_READ_FROM_CACHE_OP(fast, addr, ndummy, buf, len)	\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_OP_3A(fast, addr, ndummy, buf, len) \
-	SPI_MEM_OP(SPI_MEM_OP_CMD(fast ? 0x0b : 0x03, 1),		\
-		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+#define SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP(addr, ndummy, buf, len)	\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
-		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_X2_OP_3A(addr, ndummy, buf, len)	\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
+#define SPINAND_PAGE_READ_FROM_CACHE_FAST_3A_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP(addr, ndummy, buf, len)	\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_X4_OP_3A(addr, ndummy, buf, len)	\
-	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_2S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP(addr, ndummy, buf, len)	\
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 2),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_DUALIO_OP_3A(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_2S_2S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 2),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbd, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 2),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 2),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP(addr, ndummy, buf, len)	\
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_4S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
+		   SPI_MEM_OP_ADDR(3, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 4),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_QUADIO_OP_3A(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_4S_4S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 4),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
-
-#define SPINAND_PROG_EXEC_OP(addr)					\
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xed, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 4),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 4),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_8S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x8b, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 8),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0xcb, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 8),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 8),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 8),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_8D_OP(addr, ndummy, buf, len, freq) \
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x9d, 1),				\
+		   SPI_MEM_DTR_OP_ADDR(2, addr, 1),			\
+		   SPI_MEM_DTR_OP_DUMMY(ndummy, 1),			\
+		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 8),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
+
+#define SPINAND_PROG_EXEC_1S_1S_0_OP(addr)				\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x10, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_PROG_LOAD(reset, addr, buf, len)			\
+#define SPINAND_PROG_LOAD_1S_1S_1S_OP(reset, addr, buf, len)		\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x02 : 0x84, 1),		\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_DATA_OUT(len, buf, 1))
 
-#define SPINAND_PROG_LOAD_X4(reset, addr, buf, len)			\
+#define SPINAND_PROG_LOAD_1S_1S_4S_OP(reset, addr, buf, len)		\
 	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0x32 : 0x34, 1),		\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_DATA_OUT(len, buf, 4))
 
+#define SPINAND_PROG_LOAD_1S_1S_8S_OP(addr, buf, len)			\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(0x82, 1),				\
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 8))
+
+#define SPINAND_PROG_LOAD_1S_8S_8S_OP(reset, addr, buf, len)		\
+	SPI_MEM_OP(SPI_MEM_OP_CMD(reset ? 0xc2 : 0xc4, 1),		\
+		   SPI_MEM_OP_ADDR(2, addr, 8),				\
+		   SPI_MEM_OP_NO_DUMMY,					\
+		   SPI_MEM_OP_DATA_OUT(len, buf, 8))
+
 /**
  * Standard SPI NAND flash commands
  */
@@ -169,7 +261,7 @@
 struct spinand_op;
 struct spinand_device;
 
-#define SPINAND_MAX_ID_LEN	4
+#define SPINAND_MAX_ID_LEN	5
 /*
  * For erase, write and read operation, we got the following timings :
  * tBERS (erase) 1ms to 4ms
@@ -262,11 +354,15 @@ struct spinand_manufacturer {
 /* SPI NAND manufacturers */
 extern const struct spinand_manufacturer alliancememory_spinand_manufacturer;
 extern const struct spinand_manufacturer ato_spinand_manufacturer;
+extern const struct spinand_manufacturer esmt_8c_spinand_manufacturer;
 extern const struct spinand_manufacturer esmt_c8_spinand_manufacturer;
+extern const struct spinand_manufacturer fmsh_spinand_manufacturer;
+extern const struct spinand_manufacturer foresee_spinand_manufacturer;
 extern const struct spinand_manufacturer gigadevice_spinand_manufacturer;
 extern const struct spinand_manufacturer macronix_spinand_manufacturer;
 extern const struct spinand_manufacturer micron_spinand_manufacturer;
 extern const struct spinand_manufacturer paragon_spinand_manufacturer;
+extern const struct spinand_manufacturer skyhigh_spinand_manufacturer;
 extern const struct spinand_manufacturer toshiba_spinand_manufacturer;
 extern const struct spinand_manufacturer winbond_spinand_manufacturer;
 extern const struct spinand_manufacturer xtx_spinand_manufacturer;
@@ -311,6 +407,9 @@ struct spinand_ecc_info {
 
 #define SPINAND_HAS_QE_BIT		BIT(0)
 #define SPINAND_HAS_CR_FEAT_BIT		BIT(1)
+#define SPINAND_HAS_PROG_PLANE_SELECT_BIT		BIT(2)
+#define SPINAND_HAS_READ_PLANE_SELECT_BIT		BIT(3)
+#define SPINAND_NO_RAW_ACCESS				BIT(4)
 
 /**
  * struct spinand_ondie_ecc_conf - private SPI-NAND on-die ECC engine structure
@@ -322,6 +421,67 @@ struct spinand_ondie_ecc_conf {
 };
 
 /**
+ * struct spinand_otp_layout - structure to describe the SPI NAND OTP area
+ * @npages: number of pages in the OTP
+ * @start_page: start page of the user/factory OTP area.
+ */
+struct spinand_otp_layout {
+	unsigned int npages;
+	unsigned int start_page;
+};
+
+/**
+ * struct spinand_fact_otp_ops - SPI NAND OTP methods for factory area
+ * @info: get the OTP area information
+ * @read: read from the SPI NAND OTP area
+ */
+struct spinand_fact_otp_ops {
+	int (*info)(struct spinand_device *spinand, size_t len,
+		    struct otp_info *buf, size_t *retlen);
+	int (*read)(struct spinand_device *spinand, loff_t from, size_t len,
+		    size_t *retlen, u8 *buf);
+};
+
+/**
+ * struct spinand_user_otp_ops - SPI NAND OTP methods for user area
+ * @info: get the OTP area information
+ * @lock: lock an OTP region
+ * @erase: erase an OTP region
+ * @read: read from the SPI NAND OTP area
+ * @write: write to the SPI NAND OTP area
+ */
+struct spinand_user_otp_ops {
+	int (*info)(struct spinand_device *spinand, size_t len,
+		    struct otp_info *buf, size_t *retlen);
+	int (*lock)(struct spinand_device *spinand, loff_t from, size_t len);
+	int (*erase)(struct spinand_device *spinand, loff_t from, size_t len);
+	int (*read)(struct spinand_device *spinand, loff_t from, size_t len,
+		    size_t *retlen, u8 *buf);
+	int (*write)(struct spinand_device *spinand, loff_t from, size_t len,
+		     size_t *retlen, const u8 *buf);
+};
+
+/**
+ * struct spinand_fact_otp - SPI NAND OTP grouping structure for factory area
+ * @layout: OTP region layout
+ * @ops: OTP access ops
+ */
+struct spinand_fact_otp {
+	const struct spinand_otp_layout layout;
+	const struct spinand_fact_otp_ops *ops;
+};
+
+/**
+ * struct spinand_user_otp - SPI NAND OTP grouping structure for user area
+ * @layout: OTP region layout
+ * @ops: OTP access ops
+ */
+struct spinand_user_otp {
+	const struct spinand_otp_layout layout;
+	const struct spinand_user_otp_ops *ops;
+};
+
+/**
  * struct spinand_info - Structure used to describe SPI NAND chips
  * @model: model name
  * @devid: device ID
@@ -335,6 +495,12 @@ struct spinand_ondie_ecc_conf {
  * @op_variants.update_cache: variants of the update-cache operation
  * @select_target: function used to select a target/die. Required only for
  *		   multi-die chips
+ * @configure_chip: Align the chip configuration with the core settings
+ * @set_cont_read: enable/disable continuous cached reads
+ * @fact_otp: SPI NAND factory OTP info.
+ * @user_otp: SPI NAND user OTP info.
+ * @read_retries: the number of read retry modes supported
+ * @set_read_retry: enable/disable read retry for data recovery
  *
  * Each SPI NAND manufacturer driver should have a spinand_info table
  * describing all the chips supported by the driver.
@@ -353,6 +519,14 @@ struct spinand_info {
 	} op_variants;
 	int (*select_target)(struct spinand_device *spinand,
 			     unsigned int target);
+	int (*configure_chip)(struct spinand_device *spinand);
+	int (*set_cont_read)(struct spinand_device *spinand,
+			     bool enable);
+	struct spinand_fact_otp fact_otp;
+	struct spinand_user_otp user_otp;
+	unsigned int read_retries;
+	int (*set_read_retry)(struct spinand_device *spinand,
+			     unsigned int read_retry);
 };
 
 #define SPINAND_ID(__method, ...)					\
@@ -376,7 +550,35 @@ struct spinand_info {
 	}
 
 #define SPINAND_SELECT_TARGET(__func)					\
-	.select_target = __func,
+	.select_target = __func
+
+#define SPINAND_CONFIGURE_CHIP(__configure_chip)			\
+	.configure_chip = __configure_chip
+
+#define SPINAND_CONT_READ(__set_cont_read)				\
+	.set_cont_read = __set_cont_read
+
+#define SPINAND_FACT_OTP_INFO(__npages, __start_page, __ops)		\
+	.fact_otp = {							\
+		.layout = {						\
+			.npages = __npages,				\
+			.start_page = __start_page,			\
+		},							\
+		.ops = __ops,						\
+	}
+
+#define SPINAND_USER_OTP_INFO(__npages, __start_page, __ops)		\
+	.user_otp = {							\
+		.layout = {						\
+			.npages = __npages,				\
+			.start_page = __start_page,			\
+		},							\
+		.ops = __ops,						\
+	}
+
+#define SPINAND_READ_RETRY(__read_retries, __set_read_retry)		\
+	.read_retries = __read_retries,					\
+	.set_read_retry = __set_read_retry
 
 #define SPINAND_INFO(__model, __id, __memorg, __eccreq, __op_variants,	\
 		     __flags, ...)					\
@@ -421,7 +623,18 @@ struct spinand_dirmap {
  *		passed in spi_mem_op be DMA-able, so we can't based the bufs on
  *		the stack
  * @manufacturer: SPI NAND manufacturer information
+ * @configure_chip: Align the chip configuration with the core settings
+ * @cont_read_possible: Field filled by the core once the whole system
+ *		configuration is known to tell whether continuous reads are
+ *		suitable to use or not in general with this chip/configuration.
+ *		A per-transfer check must of course be done to ensure it is
+ *		actually relevant to enable this feature.
+ * @set_cont_read: Enable/disable the continuous read feature
  * @priv: manufacturer private data
+ * @fact_otp: SPI NAND factory OTP info.
+ * @user_otp: SPI NAND user OTP info.
+ * @read_retries: the number of read retry modes supported
+ * @set_read_retry: Enable/disable the read retry feature
  */
 struct spinand_device {
 	struct nand_device base;
@@ -450,6 +663,18 @@ struct spinand_device {
 	u8 *scratchbuf;
 	const struct spinand_manufacturer *manufacturer;
 	void *priv;
+
+	int (*configure_chip)(struct spinand_device *spinand);
+	bool cont_read_possible;
+	int (*set_cont_read)(struct spinand_device *spinand,
+			     bool enable);
+
+	const struct spinand_fact_otp *fact_otp;
+	const struct spinand_user_otp *user_otp;
+
+	unsigned int read_retries;
+	int (*set_read_retry)(struct spinand_device *spinand,
+			     unsigned int retry_mode);
 };
 
 /**
@@ -516,6 +741,31 @@ int spinand_match_and_init(struct spinand_device *spinand,
 			   enum spinand_readid_method rdid_method);
 
 int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val);
+int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val);
+int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val);
+int spinand_write_enable_op(struct spinand_device *spinand);
 int spinand_select_target(struct spinand_device *spinand, unsigned int target);
 
+int spinand_wait(struct spinand_device *spinand, unsigned long initial_delay_us,
+		 unsigned long poll_delay_us, u8 *s);
+
+int spinand_read_page(struct spinand_device *spinand,
+		      const struct nand_page_io_req *req);
+
+int spinand_write_page(struct spinand_device *spinand,
+		       const struct nand_page_io_req *req);
+
+size_t spinand_otp_page_size(struct spinand_device *spinand);
+size_t spinand_fact_otp_size(struct spinand_device *spinand);
+size_t spinand_user_otp_size(struct spinand_device *spinand);
+
+int spinand_fact_otp_read(struct spinand_device *spinand, loff_t ofs,
+			  size_t len, size_t *retlen, u8 *buf);
+int spinand_user_otp_read(struct spinand_device *spinand, loff_t ofs,
+			  size_t len, size_t *retlen, u8 *buf);
+int spinand_user_otp_write(struct spinand_device *spinand, loff_t ofs,
+			   size_t len, size_t *retlen, const u8 *buf);
+
+int spinand_set_mtd_otp_ops(struct spinand_device *spinand);
+
 #endif /* __LINUX_MTD_SPINAND_H */
diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h
index a529347fd75b..c3f79c4be1cc 100644
--- a/include/linux/mtd/ubi.h
+++ b/include/linux/mtd/ubi.h
@@ -192,6 +192,7 @@ struct ubi_device_info {
  *			or a volume was removed)
  * @UBI_VOLUME_RESIZED: a volume has been re-sized
  * @UBI_VOLUME_RENAMED: a volume has been re-named
+ * @UBI_VOLUME_SHUTDOWN: a volume is going to removed, shutdown users
  * @UBI_VOLUME_UPDATED: data has been written to a volume
  *
  * These constants define which type of event has happened when a volume
@@ -202,6 +203,7 @@ enum {
 	UBI_VOLUME_REMOVED,
 	UBI_VOLUME_RESIZED,
 	UBI_VOLUME_RENAMED,
+	UBI_VOLUME_SHUTDOWN,
 	UBI_VOLUME_UPDATED,
 };
 
@@ -248,7 +250,6 @@ int ubi_leb_unmap(struct ubi_volume_desc *desc, int lnum);
 int ubi_leb_map(struct ubi_volume_desc *desc, int lnum);
 int ubi_is_mapped(struct ubi_volume_desc *desc, int lnum);
 int ubi_sync(int ubi_num);
-int ubi_flush(int ubi_num, int vol_id, int lnum);
 
 /*
  * This function is the same as the 'ubi_leb_read()' function, but it does not
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 8f226d460f51..bf535f0118bb 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -19,6 +19,10 @@
 #include <asm/processor.h>
 #include <linux/osq_lock.h>
 #include <linux/debug_locks.h>
+#include <linux/cleanup.h>
+#include <linux/mutex_types.h>
+
+struct device;
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname)			\
@@ -30,54 +34,9 @@
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname)
 #endif
 
-#ifndef CONFIG_PREEMPT_RT
-
-/*
- * Simple, straightforward mutexes with strict semantics:
- *
- * - only one task can hold the mutex at a time
- * - only the owner can unlock the mutex
- * - multiple unlocks are not permitted
- * - recursive locking is not permitted
- * - a mutex object must be initialized via the API
- * - a mutex object must not be initialized via memset or copying
- * - task may not exit with mutex held
- * - memory areas where held locks reside must not be freed
- * - held mutexes must not be reinitialized
- * - mutexes may not be used in hardware or software interrupt
- *   contexts such as tasklets and timers
- *
- * These semantics are fully enforced when DEBUG_MUTEXES is
- * enabled. Furthermore, besides enforcing the above rules, the mutex
- * debugging code also implements a number of additional features
- * that make lock debugging easier and faster:
- *
- * - uses symbolic names of mutexes, whenever they are printed in debug output
- * - point-of-acquire tracking, symbolic lookup of function names
- * - list of all locks held in the system, printout of them
- * - owner tracking
- * - detects self-recursing locks and prints out all relevant info
- * - detects multi-task circular deadlocks and prints out all affected
- *   locks and tasks (and only those tasks)
- */
-struct mutex {
-	atomic_long_t		owner;
-	raw_spinlock_t		wait_lock;
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-	struct optimistic_spin_queue osq; /* Spinner MCS lock */
-#endif
-	struct list_head	wait_list;
-#ifdef CONFIG_DEBUG_MUTEXES
-	void			*magic;
-#endif
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
-
 #ifdef CONFIG_DEBUG_MUTEXES
 
-#define __DEBUG_MUTEX_INITIALIZER(lockname)				\
+# define __DEBUG_MUTEX_INITIALIZER(lockname)				\
 	, .magic = &lockname
 
 extern void mutex_destroy(struct mutex *lock);
@@ -105,6 +64,18 @@ do {									\
 	__mutex_init((mutex), #mutex, &__key);				\
 } while (0)
 
+/**
+ * mutex_init_with_key - initialize a mutex with a given lockdep key
+ * @mutex: the mutex to be initialized
+ * @key: the lockdep key to be associated with the mutex
+ *
+ * Initialize the mutex to the unlocked state.
+ *
+ * It is not allowed to initialize an already locked mutex.
+ */
+#define mutex_init_with_key(mutex, key) __mutex_init((mutex), #mutex, (key))
+
+#ifndef CONFIG_PREEMPT_RT
 #define __MUTEX_INITIALIZER(lockname) \
 		{ .owner = ATOMIC_LONG_INIT(0) \
 		, .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
@@ -115,8 +86,23 @@ do {									\
 #define DEFINE_MUTEX(mutexname) \
 	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
 
-extern void __mutex_init(struct mutex *lock, const char *name,
-			 struct lock_class_key *key);
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+void mutex_init_lockep(struct mutex *lock, const char *name, struct lock_class_key *key);
+
+static inline void __mutex_init(struct mutex *lock, const char *name,
+				struct lock_class_key *key)
+{
+	mutex_init_lockep(lock, name, key);
+}
+#else
+extern void mutex_init_generic(struct mutex *lock);
+
+static inline void __mutex_init(struct mutex *lock, const char *name,
+				struct lock_class_key *key)
+{
+	mutex_init_generic(lock);
+}
+#endif /* !CONFIG_DEBUG_LOCK_ALLOC */
 
 /**
  * mutex_is_locked - is the mutex locked
@@ -130,14 +116,6 @@ extern bool mutex_is_locked(struct mutex *lock);
 /*
  * Preempt-RT variant based on rtmutexes.
  */
-#include <linux/rtmutex.h>
-
-struct mutex {
-	struct rt_mutex_base	rtmutex;
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map	dep_map;
-#endif
-};
 
 #define __MUTEX_INITIALIZER(mutexname)					\
 {									\
@@ -148,28 +126,57 @@ struct mutex {
 #define DEFINE_MUTEX(mutexname)						\
 	struct mutex mutexname = __MUTEX_INITIALIZER(mutexname)
 
-extern void __mutex_rt_init(struct mutex *lock, const char *name,
-			    struct lock_class_key *key);
-extern int mutex_trylock(struct mutex *lock);
+#define mutex_is_locked(l)	rt_mutex_base_is_locked(&(l)->rtmutex)
 
-static inline void mutex_destroy(struct mutex *lock) { }
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern void mutex_rt_init_lockdep(struct mutex *mutex, const char *name,
+			     struct lock_class_key *key);
 
-#define mutex_is_locked(l)	rt_mutex_base_is_locked(&(l)->rtmutex)
+static inline void __mutex_init(struct mutex *lock, const char *name,
+				struct lock_class_key *key)
+{
+	mutex_rt_init_lockdep(lock, name, key);
+}
 
-#define __mutex_init(mutex, name, key)			\
-do {							\
-	rt_mutex_base_init(&(mutex)->rtmutex);		\
-	__mutex_rt_init((mutex), name, key);		\
-} while (0)
+#else
+extern void mutex_rt_init_generic(struct mutex *mutex);
 
-#define mutex_init(mutex)				\
-do {							\
-	static struct lock_class_key __key;		\
-							\
-	__mutex_init((mutex), #mutex, &__key);		\
-} while (0)
+static inline void __mutex_init(struct mutex *lock, const char *name,
+				struct lock_class_key *key)
+{
+	mutex_rt_init_generic(lock);
+}
+#endif /* !CONFIG_LOCKDEP */
 #endif /* CONFIG_PREEMPT_RT */
 
+#ifdef CONFIG_DEBUG_MUTEXES
+
+int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock);
+
+#else
+
+static inline int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock)
+{
+	/*
+	 * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so
+	 * no really need to register it in the devm subsystem.
+	 */
+	return 0;
+}
+
+#endif
+
+#define __mutex_init_ret(mutex)				\
+({							\
+	typeof(mutex) mutex_ = (mutex);			\
+							\
+	mutex_init(mutex_);				\
+	mutex_;						\
+})
+
+#define devm_mutex_init(dev, mutex) \
+	__devm_mutex_init(dev, __mutex_init_ret(mutex))
+
 /*
  * See kernel/locking/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/locking/mutex-design.rst.
@@ -177,16 +184,15 @@ do {							\
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 extern void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
 extern void _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
-
 extern int __must_check mutex_lock_interruptible_nested(struct mutex *lock,
 					unsigned int subclass);
-extern int __must_check mutex_lock_killable_nested(struct mutex *lock,
-					unsigned int subclass);
+extern int __must_check _mutex_lock_killable(struct mutex *lock,
+		unsigned int subclass, struct lockdep_map *nest_lock);
 extern void mutex_lock_io_nested(struct mutex *lock, unsigned int subclass);
 
 #define mutex_lock(lock) mutex_lock_nested(lock, 0)
 #define mutex_lock_interruptible(lock) mutex_lock_interruptible_nested(lock, 0)
-#define mutex_lock_killable(lock) mutex_lock_killable_nested(lock, 0)
+#define mutex_lock_killable(lock) _mutex_lock_killable(lock, 0, NULL)
 #define mutex_lock_io(lock) mutex_lock_io_nested(lock, 0)
 
 #define mutex_lock_nest_lock(lock, nest_lock)				\
@@ -195,6 +201,15 @@ do {									\
 	_mutex_lock_nest_lock(lock, &(nest_lock)->dep_map);		\
 } while (0)
 
+#define mutex_lock_killable_nest_lock(lock, nest_lock)			\
+(									\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map),		\
+	_mutex_lock_killable(lock, 0, &(nest_lock)->dep_map)		\
+)
+
+#define mutex_lock_killable_nested(lock, subclass) \
+	_mutex_lock_killable(lock, subclass, NULL)
+
 #else
 extern void mutex_lock(struct mutex *lock);
 extern int __must_check mutex_lock_interruptible(struct mutex *lock);
@@ -204,6 +219,7 @@ extern void mutex_lock_io(struct mutex *lock);
 # define mutex_lock_nested(lock, subclass) mutex_lock(lock)
 # define mutex_lock_interruptible_nested(lock, subclass) mutex_lock_interruptible(lock)
 # define mutex_lock_killable_nested(lock, subclass) mutex_lock_killable(lock)
+# define mutex_lock_killable_nest_lock(lock, nest_lock) mutex_lock_killable(lock)
 # define mutex_lock_nest_lock(lock, nest_lock) mutex_lock(lock)
 # define mutex_lock_io_nested(lock, subclass) mutex_lock_io(lock)
 #endif
@@ -214,9 +230,30 @@ extern void mutex_lock_io(struct mutex *lock);
  *
  * Returns 1 if the mutex has been acquired successfully, and 0 on contention.
  */
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+extern int _mutex_trylock_nest_lock(struct mutex *lock, struct lockdep_map *nest_lock);
+
+#define mutex_trylock_nest_lock(lock, nest_lock)		\
+(								\
+	typecheck(struct lockdep_map *, &(nest_lock)->dep_map),	\
+	_mutex_trylock_nest_lock(lock, &(nest_lock)->dep_map)	\
+)
+
+#define mutex_trylock(lock) _mutex_trylock_nest_lock(lock, NULL)
+#else
 extern int mutex_trylock(struct mutex *lock);
+#define mutex_trylock_nest_lock(lock, nest_lock) mutex_trylock(lock)
+#endif
+
 extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
+DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T))
+DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T))
+DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T), _RET == 0)
+
+extern unsigned long mutex_get_owner(struct mutex *lock);
+
 #endif /* __LINUX_MUTEX_H */
diff --git a/include/linux/mutex_types.h b/include/linux/mutex_types.h
new file mode 100644
index 000000000000..fdf7f515fde8
--- /dev/null
+++ b/include/linux/mutex_types.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_MUTEX_TYPES_H
+#define __LINUX_MUTEX_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/lockdep_types.h>
+#include <linux/osq_lock.h>
+#include <linux/spinlock_types.h>
+#include <linux/types.h>
+
+#ifndef CONFIG_PREEMPT_RT
+
+/*
+ * Simple, straightforward mutexes with strict semantics:
+ *
+ * - only one task can hold the mutex at a time
+ * - only the owner can unlock the mutex
+ * - multiple unlocks are not permitted
+ * - recursive locking is not permitted
+ * - a mutex object must be initialized via the API
+ * - a mutex object must not be initialized via memset or copying
+ * - task may not exit with mutex held
+ * - memory areas where held locks reside must not be freed
+ * - held mutexes must not be reinitialized
+ * - mutexes may not be used in hardware or software interrupt
+ *   contexts such as tasklets and timers
+ *
+ * These semantics are fully enforced when DEBUG_MUTEXES is
+ * enabled. Furthermore, besides enforcing the above rules, the mutex
+ * debugging code also implements a number of additional features
+ * that make lock debugging easier and faster:
+ *
+ * - uses symbolic names of mutexes, whenever they are printed in debug output
+ * - point-of-acquire tracking, symbolic lookup of function names
+ * - list of all locks held in the system, printout of them
+ * - owner tracking
+ * - detects self-recursing locks and prints out all relevant info
+ * - detects multi-task circular deadlocks and prints out all affected
+ *   locks and tasks (and only those tasks)
+ */
+struct mutex {
+	atomic_long_t		owner;
+	raw_spinlock_t		wait_lock;
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	struct optimistic_spin_queue osq; /* Spinner MCS lock */
+#endif
+	struct list_head	wait_list;
+#ifdef CONFIG_DEBUG_MUTEXES
+	void			*magic;
+#endif
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#else /* !CONFIG_PREEMPT_RT */
+/*
+ * Preempt-RT variant based on rtmutexes.
+ */
+#include <linux/rtmutex.h>
+
+struct mutex {
+	struct rt_mutex_base	rtmutex;
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map	dep_map;
+#endif
+};
+
+#endif /* CONFIG_PREEMPT_RT */
+
+#endif /* __LINUX_MUTEX_TYPES_H */
diff --git a/include/linux/mux/driver.h b/include/linux/mux/driver.h
index 18824064f8c0..e58e59354e23 100644
--- a/include/linux/mux/driver.h
+++ b/include/linux/mux/driver.h
@@ -56,18 +56,18 @@ struct mux_control {
 /**
  * struct mux_chip -	Represents a chip holding mux controllers.
  * @controllers:	Number of mux controllers handled by the chip.
- * @mux:		Array of mux controllers that are handled.
  * @dev:		Device structure.
  * @id:			Used to identify the device internally.
  * @ops:		Mux controller operations.
+ * @mux:		Array of mux controllers that are handled.
  */
 struct mux_chip {
 	unsigned int controllers;
-	struct mux_control *mux;
 	struct device dev;
 	int id;
 
 	const struct mux_control_ops *ops;
+	struct mux_control mux[] __counted_by(controllers);
 };
 
 #define to_mux_chip(x) container_of((x), struct mux_chip, dev)
diff --git a/include/linux/mv643xx.h b/include/linux/mv643xx.h
deleted file mode 100644
index 000b126acfb6..000000000000
--- a/include/linux/mv643xx.h
+++ /dev/null
@@ -1,921 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * mv643xx.h - MV-643XX Internal registers definition file.
- *
- * Copyright 2002 Momentum Computer, Inc.
- * 	Author: Matthew Dharm <mdharm@momenco.com>
- * Copyright 2002 GALILEO TECHNOLOGY, LTD. 
- */
-#ifndef __ASM_MV643XX_H
-#define __ASM_MV643XX_H
-
-#include <asm/types.h>
-#include <linux/mv643xx_eth.h>
-#include <linux/mv643xx_i2c.h>
-
-/****************************************/
-/* Processor Address Space              */
-/****************************************/
-
-/* DDR SDRAM BAR and size registers */
-
-#define MV64340_CS_0_BASE_ADDR                                      0x008
-#define MV64340_CS_0_SIZE                                           0x010
-#define MV64340_CS_1_BASE_ADDR                                      0x208
-#define MV64340_CS_1_SIZE                                           0x210
-#define MV64340_CS_2_BASE_ADDR                                      0x018
-#define MV64340_CS_2_SIZE                                           0x020
-#define MV64340_CS_3_BASE_ADDR                                      0x218
-#define MV64340_CS_3_SIZE                                           0x220
-
-/* Devices BAR and size registers */
-
-#define MV64340_DEV_CS0_BASE_ADDR                                   0x028
-#define MV64340_DEV_CS0_SIZE                                        0x030
-#define MV64340_DEV_CS1_BASE_ADDR                                   0x228
-#define MV64340_DEV_CS1_SIZE                                        0x230
-#define MV64340_DEV_CS2_BASE_ADDR                                   0x248
-#define MV64340_DEV_CS2_SIZE                                        0x250
-#define MV64340_DEV_CS3_BASE_ADDR                                   0x038
-#define MV64340_DEV_CS3_SIZE                                        0x040
-#define MV64340_BOOTCS_BASE_ADDR                                    0x238
-#define MV64340_BOOTCS_SIZE                                         0x240
-
-/* PCI 0 BAR and size registers */
-
-#define MV64340_PCI_0_IO_BASE_ADDR                                  0x048
-#define MV64340_PCI_0_IO_SIZE                                       0x050
-#define MV64340_PCI_0_MEMORY0_BASE_ADDR                             0x058
-#define MV64340_PCI_0_MEMORY0_SIZE                                  0x060
-#define MV64340_PCI_0_MEMORY1_BASE_ADDR                             0x080
-#define MV64340_PCI_0_MEMORY1_SIZE                                  0x088
-#define MV64340_PCI_0_MEMORY2_BASE_ADDR                             0x258
-#define MV64340_PCI_0_MEMORY2_SIZE                                  0x260
-#define MV64340_PCI_0_MEMORY3_BASE_ADDR                             0x280
-#define MV64340_PCI_0_MEMORY3_SIZE                                  0x288
-
-/* PCI 1 BAR and size registers */
-#define MV64340_PCI_1_IO_BASE_ADDR                                  0x090
-#define MV64340_PCI_1_IO_SIZE                                       0x098
-#define MV64340_PCI_1_MEMORY0_BASE_ADDR                             0x0a0
-#define MV64340_PCI_1_MEMORY0_SIZE                                  0x0a8
-#define MV64340_PCI_1_MEMORY1_BASE_ADDR                             0x0b0
-#define MV64340_PCI_1_MEMORY1_SIZE                                  0x0b8
-#define MV64340_PCI_1_MEMORY2_BASE_ADDR                             0x2a0
-#define MV64340_PCI_1_MEMORY2_SIZE                                  0x2a8
-#define MV64340_PCI_1_MEMORY3_BASE_ADDR                             0x2b0
-#define MV64340_PCI_1_MEMORY3_SIZE                                  0x2b8
-
-/* SRAM base address */
-#define MV64340_INTEGRATED_SRAM_BASE_ADDR                           0x268
-
-/* internal registers space base address */
-#define MV64340_INTERNAL_SPACE_BASE_ADDR                            0x068
-
-/* Enables the CS , DEV_CS , PCI 0 and PCI 1 
-   windows above */
-#define MV64340_BASE_ADDR_ENABLE                                    0x278
-
-/****************************************/
-/* PCI remap registers                  */
-/****************************************/
-      /* PCI 0 */
-#define MV64340_PCI_0_IO_ADDR_REMAP                                 0x0f0
-#define MV64340_PCI_0_MEMORY0_LOW_ADDR_REMAP                        0x0f8
-#define MV64340_PCI_0_MEMORY0_HIGH_ADDR_REMAP                       0x320
-#define MV64340_PCI_0_MEMORY1_LOW_ADDR_REMAP                        0x100
-#define MV64340_PCI_0_MEMORY1_HIGH_ADDR_REMAP                       0x328
-#define MV64340_PCI_0_MEMORY2_LOW_ADDR_REMAP                        0x2f8
-#define MV64340_PCI_0_MEMORY2_HIGH_ADDR_REMAP                       0x330
-#define MV64340_PCI_0_MEMORY3_LOW_ADDR_REMAP                        0x300
-#define MV64340_PCI_0_MEMORY3_HIGH_ADDR_REMAP                       0x338
-      /* PCI 1 */
-#define MV64340_PCI_1_IO_ADDR_REMAP                                 0x108
-#define MV64340_PCI_1_MEMORY0_LOW_ADDR_REMAP                        0x110
-#define MV64340_PCI_1_MEMORY0_HIGH_ADDR_REMAP                       0x340
-#define MV64340_PCI_1_MEMORY1_LOW_ADDR_REMAP                        0x118
-#define MV64340_PCI_1_MEMORY1_HIGH_ADDR_REMAP                       0x348
-#define MV64340_PCI_1_MEMORY2_LOW_ADDR_REMAP                        0x310
-#define MV64340_PCI_1_MEMORY2_HIGH_ADDR_REMAP                       0x350
-#define MV64340_PCI_1_MEMORY3_LOW_ADDR_REMAP                        0x318
-#define MV64340_PCI_1_MEMORY3_HIGH_ADDR_REMAP                       0x358
- 
-#define MV64340_CPU_PCI_0_HEADERS_RETARGET_CONTROL                  0x3b0
-#define MV64340_CPU_PCI_0_HEADERS_RETARGET_BASE                     0x3b8
-#define MV64340_CPU_PCI_1_HEADERS_RETARGET_CONTROL                  0x3c0
-#define MV64340_CPU_PCI_1_HEADERS_RETARGET_BASE                     0x3c8
-#define MV64340_CPU_GE_HEADERS_RETARGET_CONTROL                     0x3d0
-#define MV64340_CPU_GE_HEADERS_RETARGET_BASE                        0x3d8
-#define MV64340_CPU_IDMA_HEADERS_RETARGET_CONTROL                   0x3e0
-#define MV64340_CPU_IDMA_HEADERS_RETARGET_BASE                      0x3e8
-
-/****************************************/
-/*         CPU Control Registers        */
-/****************************************/
-
-#define MV64340_CPU_CONFIG                                          0x000
-#define MV64340_CPU_MODE                                            0x120
-#define MV64340_CPU_MASTER_CONTROL                                  0x160
-#define MV64340_CPU_CROSS_BAR_CONTROL_LOW                           0x150
-#define MV64340_CPU_CROSS_BAR_CONTROL_HIGH                          0x158
-#define MV64340_CPU_CROSS_BAR_TIMEOUT                               0x168
-
-/****************************************/
-/* SMP RegisterS                        */
-/****************************************/
-
-#define MV64340_SMP_WHO_AM_I                                        0x200
-#define MV64340_SMP_CPU0_DOORBELL                                   0x214
-#define MV64340_SMP_CPU0_DOORBELL_CLEAR                             0x21C
-#define MV64340_SMP_CPU1_DOORBELL                                   0x224
-#define MV64340_SMP_CPU1_DOORBELL_CLEAR                             0x22C
-#define MV64340_SMP_CPU0_DOORBELL_MASK                              0x234
-#define MV64340_SMP_CPU1_DOORBELL_MASK                              0x23C
-#define MV64340_SMP_SEMAPHOR0                                       0x244
-#define MV64340_SMP_SEMAPHOR1                                       0x24c
-#define MV64340_SMP_SEMAPHOR2                                       0x254
-#define MV64340_SMP_SEMAPHOR3                                       0x25c
-#define MV64340_SMP_SEMAPHOR4                                       0x264
-#define MV64340_SMP_SEMAPHOR5                                       0x26c
-#define MV64340_SMP_SEMAPHOR6                                       0x274
-#define MV64340_SMP_SEMAPHOR7                                       0x27c
-
-/****************************************/
-/*  CPU Sync Barrier Register           */
-/****************************************/
-
-#define MV64340_CPU_0_SYNC_BARRIER_TRIGGER                          0x0c0
-#define MV64340_CPU_0_SYNC_BARRIER_VIRTUAL                          0x0c8
-#define MV64340_CPU_1_SYNC_BARRIER_TRIGGER                          0x0d0
-#define MV64340_CPU_1_SYNC_BARRIER_VIRTUAL                          0x0d8
-
-/****************************************/
-/* CPU Access Protect                   */
-/****************************************/
-
-#define MV64340_CPU_PROTECT_WINDOW_0_BASE_ADDR                      0x180
-#define MV64340_CPU_PROTECT_WINDOW_0_SIZE                           0x188
-#define MV64340_CPU_PROTECT_WINDOW_1_BASE_ADDR                      0x190
-#define MV64340_CPU_PROTECT_WINDOW_1_SIZE                           0x198
-#define MV64340_CPU_PROTECT_WINDOW_2_BASE_ADDR                      0x1a0
-#define MV64340_CPU_PROTECT_WINDOW_2_SIZE                           0x1a8
-#define MV64340_CPU_PROTECT_WINDOW_3_BASE_ADDR                      0x1b0
-#define MV64340_CPU_PROTECT_WINDOW_3_SIZE                           0x1b8
-
-
-/****************************************/
-/*          CPU Error Report            */
-/****************************************/
-
-#define MV64340_CPU_ERROR_ADDR_LOW                                  0x070
-#define MV64340_CPU_ERROR_ADDR_HIGH                                 0x078
-#define MV64340_CPU_ERROR_DATA_LOW                                  0x128
-#define MV64340_CPU_ERROR_DATA_HIGH                                 0x130
-#define MV64340_CPU_ERROR_PARITY                                    0x138
-#define MV64340_CPU_ERROR_CAUSE                                     0x140
-#define MV64340_CPU_ERROR_MASK                                      0x148
-
-/****************************************/
-/*      CPU Interface Debug Registers 	*/
-/****************************************/
-
-#define MV64340_PUNIT_SLAVE_DEBUG_LOW                               0x360
-#define MV64340_PUNIT_SLAVE_DEBUG_HIGH                              0x368
-#define MV64340_PUNIT_MASTER_DEBUG_LOW                              0x370
-#define MV64340_PUNIT_MASTER_DEBUG_HIGH                             0x378
-#define MV64340_PUNIT_MMASK                                         0x3e4
-
-/****************************************/
-/*  Integrated SRAM Registers           */
-/****************************************/
-
-#define MV64340_SRAM_CONFIG                                         0x380
-#define MV64340_SRAM_TEST_MODE                                      0X3F4
-#define MV64340_SRAM_ERROR_CAUSE                                    0x388
-#define MV64340_SRAM_ERROR_ADDR                                     0x390
-#define MV64340_SRAM_ERROR_ADDR_HIGH                                0X3F8
-#define MV64340_SRAM_ERROR_DATA_LOW                                 0x398
-#define MV64340_SRAM_ERROR_DATA_HIGH                                0x3a0
-#define MV64340_SRAM_ERROR_DATA_PARITY                              0x3a8
-
-/****************************************/
-/* SDRAM Configuration                  */
-/****************************************/
-
-#define MV64340_SDRAM_CONFIG                                        0x1400
-#define MV64340_D_UNIT_CONTROL_LOW                                  0x1404
-#define MV64340_D_UNIT_CONTROL_HIGH                                 0x1424
-#define MV64340_SDRAM_TIMING_CONTROL_LOW                            0x1408
-#define MV64340_SDRAM_TIMING_CONTROL_HIGH                           0x140c
-#define MV64340_SDRAM_ADDR_CONTROL                                  0x1410
-#define MV64340_SDRAM_OPEN_PAGES_CONTROL                            0x1414
-#define MV64340_SDRAM_OPERATION                                     0x1418
-#define MV64340_SDRAM_MODE                                          0x141c
-#define MV64340_EXTENDED_DRAM_MODE                                  0x1420
-#define MV64340_SDRAM_CROSS_BAR_CONTROL_LOW                         0x1430
-#define MV64340_SDRAM_CROSS_BAR_CONTROL_HIGH                        0x1434
-#define MV64340_SDRAM_CROSS_BAR_TIMEOUT                             0x1438
-#define MV64340_SDRAM_ADDR_CTRL_PADS_CALIBRATION                    0x14c0
-#define MV64340_SDRAM_DATA_PADS_CALIBRATION                         0x14c4
-
-/****************************************/
-/* SDRAM Error Report                   */
-/****************************************/
-
-#define MV64340_SDRAM_ERROR_DATA_LOW                                0x1444
-#define MV64340_SDRAM_ERROR_DATA_HIGH                               0x1440
-#define MV64340_SDRAM_ERROR_ADDR                                    0x1450
-#define MV64340_SDRAM_RECEIVED_ECC                                  0x1448
-#define MV64340_SDRAM_CALCULATED_ECC                                0x144c
-#define MV64340_SDRAM_ECC_CONTROL                                   0x1454
-#define MV64340_SDRAM_ECC_ERROR_COUNTER                             0x1458
-
-/******************************************/
-/*  Controlled Delay Line (CDL) Registers */
-/******************************************/
-
-#define MV64340_DFCDL_CONFIG0                                       0x1480
-#define MV64340_DFCDL_CONFIG1                                       0x1484
-#define MV64340_DLL_WRITE                                           0x1488
-#define MV64340_DLL_READ                                            0x148c
-#define MV64340_SRAM_ADDR                                           0x1490
-#define MV64340_SRAM_DATA0                                          0x1494
-#define MV64340_SRAM_DATA1                                          0x1498
-#define MV64340_SRAM_DATA2                                          0x149c
-#define MV64340_DFCL_PROBE                                          0x14a0
-
-/******************************************/
-/*   Debug Registers                      */
-/******************************************/
-
-#define MV64340_DUNIT_DEBUG_LOW                                     0x1460
-#define MV64340_DUNIT_DEBUG_HIGH                                    0x1464
-#define MV64340_DUNIT_MMASK                                         0X1b40
-
-/****************************************/
-/* Device Parameters			*/
-/****************************************/
-
-#define MV64340_DEVICE_BANK0_PARAMETERS				    0x45c
-#define MV64340_DEVICE_BANK1_PARAMETERS				    0x460
-#define MV64340_DEVICE_BANK2_PARAMETERS				    0x464
-#define MV64340_DEVICE_BANK3_PARAMETERS				    0x468
-#define MV64340_DEVICE_BOOT_BANK_PARAMETERS			    0x46c
-#define MV64340_DEVICE_INTERFACE_CONTROL                            0x4c0
-#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_LOW              0x4c8
-#define MV64340_DEVICE_INTERFACE_CROSS_BAR_CONTROL_HIGH             0x4cc
-#define MV64340_DEVICE_INTERFACE_CROSS_BAR_TIMEOUT                  0x4c4
-
-/****************************************/
-/* Device interrupt registers		*/
-/****************************************/
-
-#define MV64340_DEVICE_INTERRUPT_CAUSE				    0x4d0
-#define MV64340_DEVICE_INTERRUPT_MASK				    0x4d4
-#define MV64340_DEVICE_ERROR_ADDR				    0x4d8
-#define MV64340_DEVICE_ERROR_DATA   				    0x4dc
-#define MV64340_DEVICE_ERROR_PARITY     			    0x4e0
-
-/****************************************/
-/* Device debug registers   		*/
-/****************************************/
-
-#define MV64340_DEVICE_DEBUG_LOW     				    0x4e4
-#define MV64340_DEVICE_DEBUG_HIGH     				    0x4e8
-#define MV64340_RUNIT_MMASK                                         0x4f0
-
-/****************************************/
-/* PCI Slave Address Decoding registers */
-/****************************************/
-
-#define MV64340_PCI_0_CS_0_BANK_SIZE                                0xc08
-#define MV64340_PCI_1_CS_0_BANK_SIZE                                0xc88
-#define MV64340_PCI_0_CS_1_BANK_SIZE                                0xd08
-#define MV64340_PCI_1_CS_1_BANK_SIZE                                0xd88
-#define MV64340_PCI_0_CS_2_BANK_SIZE                                0xc0c
-#define MV64340_PCI_1_CS_2_BANK_SIZE                                0xc8c
-#define MV64340_PCI_0_CS_3_BANK_SIZE                                0xd0c
-#define MV64340_PCI_1_CS_3_BANK_SIZE                                0xd8c
-#define MV64340_PCI_0_DEVCS_0_BANK_SIZE                             0xc10
-#define MV64340_PCI_1_DEVCS_0_BANK_SIZE                             0xc90
-#define MV64340_PCI_0_DEVCS_1_BANK_SIZE                             0xd10
-#define MV64340_PCI_1_DEVCS_1_BANK_SIZE                             0xd90
-#define MV64340_PCI_0_DEVCS_2_BANK_SIZE                             0xd18
-#define MV64340_PCI_1_DEVCS_2_BANK_SIZE                             0xd98
-#define MV64340_PCI_0_DEVCS_3_BANK_SIZE                             0xc14
-#define MV64340_PCI_1_DEVCS_3_BANK_SIZE                             0xc94
-#define MV64340_PCI_0_DEVCS_BOOT_BANK_SIZE                          0xd14
-#define MV64340_PCI_1_DEVCS_BOOT_BANK_SIZE                          0xd94
-#define MV64340_PCI_0_P2P_MEM0_BAR_SIZE                             0xd1c
-#define MV64340_PCI_1_P2P_MEM0_BAR_SIZE                             0xd9c
-#define MV64340_PCI_0_P2P_MEM1_BAR_SIZE                             0xd20
-#define MV64340_PCI_1_P2P_MEM1_BAR_SIZE                             0xda0
-#define MV64340_PCI_0_P2P_I_O_BAR_SIZE                              0xd24
-#define MV64340_PCI_1_P2P_I_O_BAR_SIZE                              0xda4
-#define MV64340_PCI_0_CPU_BAR_SIZE                                  0xd28
-#define MV64340_PCI_1_CPU_BAR_SIZE                                  0xda8
-#define MV64340_PCI_0_INTERNAL_SRAM_BAR_SIZE                        0xe00
-#define MV64340_PCI_1_INTERNAL_SRAM_BAR_SIZE                        0xe80
-#define MV64340_PCI_0_EXPANSION_ROM_BAR_SIZE                        0xd2c
-#define MV64340_PCI_1_EXPANSION_ROM_BAR_SIZE                        0xd9c
-#define MV64340_PCI_0_BASE_ADDR_REG_ENABLE                          0xc3c
-#define MV64340_PCI_1_BASE_ADDR_REG_ENABLE                          0xcbc
-#define MV64340_PCI_0_CS_0_BASE_ADDR_REMAP			    0xc48
-#define MV64340_PCI_1_CS_0_BASE_ADDR_REMAP			    0xcc8
-#define MV64340_PCI_0_CS_1_BASE_ADDR_REMAP			    0xd48
-#define MV64340_PCI_1_CS_1_BASE_ADDR_REMAP			    0xdc8
-#define MV64340_PCI_0_CS_2_BASE_ADDR_REMAP			    0xc4c
-#define MV64340_PCI_1_CS_2_BASE_ADDR_REMAP			    0xccc
-#define MV64340_PCI_0_CS_3_BASE_ADDR_REMAP			    0xd4c
-#define MV64340_PCI_1_CS_3_BASE_ADDR_REMAP			    0xdcc
-#define MV64340_PCI_0_CS_0_BASE_HIGH_ADDR_REMAP			    0xF04
-#define MV64340_PCI_1_CS_0_BASE_HIGH_ADDR_REMAP			    0xF84
-#define MV64340_PCI_0_CS_1_BASE_HIGH_ADDR_REMAP			    0xF08
-#define MV64340_PCI_1_CS_1_BASE_HIGH_ADDR_REMAP			    0xF88
-#define MV64340_PCI_0_CS_2_BASE_HIGH_ADDR_REMAP			    0xF0C
-#define MV64340_PCI_1_CS_2_BASE_HIGH_ADDR_REMAP			    0xF8C
-#define MV64340_PCI_0_CS_3_BASE_HIGH_ADDR_REMAP			    0xF10
-#define MV64340_PCI_1_CS_3_BASE_HIGH_ADDR_REMAP			    0xF90
-#define MV64340_PCI_0_DEVCS_0_BASE_ADDR_REMAP			    0xc50
-#define MV64340_PCI_1_DEVCS_0_BASE_ADDR_REMAP			    0xcd0
-#define MV64340_PCI_0_DEVCS_1_BASE_ADDR_REMAP			    0xd50
-#define MV64340_PCI_1_DEVCS_1_BASE_ADDR_REMAP			    0xdd0
-#define MV64340_PCI_0_DEVCS_2_BASE_ADDR_REMAP			    0xd58
-#define MV64340_PCI_1_DEVCS_2_BASE_ADDR_REMAP			    0xdd8
-#define MV64340_PCI_0_DEVCS_3_BASE_ADDR_REMAP           	    0xc54
-#define MV64340_PCI_1_DEVCS_3_BASE_ADDR_REMAP           	    0xcd4
-#define MV64340_PCI_0_DEVCS_BOOTCS_BASE_ADDR_REMAP      	    0xd54
-#define MV64340_PCI_1_DEVCS_BOOTCS_BASE_ADDR_REMAP      	    0xdd4
-#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_LOW                  0xd5c
-#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_LOW                  0xddc
-#define MV64340_PCI_0_P2P_MEM0_BASE_ADDR_REMAP_HIGH                 0xd60
-#define MV64340_PCI_1_P2P_MEM0_BASE_ADDR_REMAP_HIGH                 0xde0
-#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_LOW                  0xd64
-#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_LOW                  0xde4
-#define MV64340_PCI_0_P2P_MEM1_BASE_ADDR_REMAP_HIGH                 0xd68
-#define MV64340_PCI_1_P2P_MEM1_BASE_ADDR_REMAP_HIGH                 0xde8
-#define MV64340_PCI_0_P2P_I_O_BASE_ADDR_REMAP                       0xd6c
-#define MV64340_PCI_1_P2P_I_O_BASE_ADDR_REMAP                       0xdec 
-#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_LOW                       0xd70
-#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_LOW                       0xdf0
-#define MV64340_PCI_0_CPU_BASE_ADDR_REMAP_HIGH                      0xd74
-#define MV64340_PCI_1_CPU_BASE_ADDR_REMAP_HIGH                      0xdf4
-#define MV64340_PCI_0_INTEGRATED_SRAM_BASE_ADDR_REMAP               0xf00
-#define MV64340_PCI_1_INTEGRATED_SRAM_BASE_ADDR_REMAP               0xf80
-#define MV64340_PCI_0_EXPANSION_ROM_BASE_ADDR_REMAP                 0xf38
-#define MV64340_PCI_1_EXPANSION_ROM_BASE_ADDR_REMAP                 0xfb8
-#define MV64340_PCI_0_ADDR_DECODE_CONTROL                           0xd3c
-#define MV64340_PCI_1_ADDR_DECODE_CONTROL                           0xdbc
-#define MV64340_PCI_0_HEADERS_RETARGET_CONTROL                      0xF40
-#define MV64340_PCI_1_HEADERS_RETARGET_CONTROL                      0xFc0
-#define MV64340_PCI_0_HEADERS_RETARGET_BASE                         0xF44
-#define MV64340_PCI_1_HEADERS_RETARGET_BASE                         0xFc4
-#define MV64340_PCI_0_HEADERS_RETARGET_HIGH                         0xF48
-#define MV64340_PCI_1_HEADERS_RETARGET_HIGH                         0xFc8
-
-/***********************************/
-/*   PCI Control Register Map      */
-/***********************************/
-
-#define MV64340_PCI_0_DLL_STATUS_AND_COMMAND                        0x1d20
-#define MV64340_PCI_1_DLL_STATUS_AND_COMMAND                        0x1da0
-#define MV64340_PCI_0_MPP_PADS_DRIVE_CONTROL                        0x1d1C
-#define MV64340_PCI_1_MPP_PADS_DRIVE_CONTROL                        0x1d9C
-#define MV64340_PCI_0_COMMAND			         	    0xc00
-#define MV64340_PCI_1_COMMAND					    0xc80
-#define MV64340_PCI_0_MODE                                          0xd00
-#define MV64340_PCI_1_MODE                                          0xd80
-#define MV64340_PCI_0_RETRY	        	 		    0xc04
-#define MV64340_PCI_1_RETRY				            0xc84
-#define MV64340_PCI_0_READ_BUFFER_DISCARD_TIMER                     0xd04
-#define MV64340_PCI_1_READ_BUFFER_DISCARD_TIMER                     0xd84
-#define MV64340_PCI_0_MSI_TRIGGER_TIMER                             0xc38
-#define MV64340_PCI_1_MSI_TRIGGER_TIMER                             0xcb8
-#define MV64340_PCI_0_ARBITER_CONTROL                               0x1d00
-#define MV64340_PCI_1_ARBITER_CONTROL                               0x1d80
-#define MV64340_PCI_0_CROSS_BAR_CONTROL_LOW                         0x1d08
-#define MV64340_PCI_1_CROSS_BAR_CONTROL_LOW                         0x1d88
-#define MV64340_PCI_0_CROSS_BAR_CONTROL_HIGH                        0x1d0c
-#define MV64340_PCI_1_CROSS_BAR_CONTROL_HIGH                        0x1d8c
-#define MV64340_PCI_0_CROSS_BAR_TIMEOUT                             0x1d04
-#define MV64340_PCI_1_CROSS_BAR_TIMEOUT                             0x1d84
-#define MV64340_PCI_0_SYNC_BARRIER_TRIGGER_REG                      0x1D18
-#define MV64340_PCI_1_SYNC_BARRIER_TRIGGER_REG                      0x1D98
-#define MV64340_PCI_0_SYNC_BARRIER_VIRTUAL_REG                      0x1d10
-#define MV64340_PCI_1_SYNC_BARRIER_VIRTUAL_REG                      0x1d90
-#define MV64340_PCI_0_P2P_CONFIG                                    0x1d14
-#define MV64340_PCI_1_P2P_CONFIG                                    0x1d94
-
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_LOW                     0x1e00
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_0_HIGH                    0x1e04
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_0                         0x1e08
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_LOW                     0x1e10
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_1_HIGH                    0x1e14
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_1                         0x1e18
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_LOW                     0x1e20
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_2_HIGH                    0x1e24
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_2                         0x1e28
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_LOW                     0x1e30
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_3_HIGH                    0x1e34
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_3                         0x1e38
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_LOW                     0x1e40
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_4_HIGH                    0x1e44
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_4                         0x1e48
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_LOW                     0x1e50
-#define MV64340_PCI_0_ACCESS_CONTROL_BASE_5_HIGH                    0x1e54
-#define MV64340_PCI_0_ACCESS_CONTROL_SIZE_5                         0x1e58
-
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_LOW                     0x1e80
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_0_HIGH                    0x1e84
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_0                         0x1e88
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_LOW                     0x1e90
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_1_HIGH                    0x1e94
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_1                         0x1e98
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_LOW                     0x1ea0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_2_HIGH                    0x1ea4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_2                         0x1ea8
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_LOW                     0x1eb0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_3_HIGH                    0x1eb4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_3                         0x1eb8
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_LOW                     0x1ec0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_4_HIGH                    0x1ec4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_4                         0x1ec8
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_LOW                     0x1ed0
-#define MV64340_PCI_1_ACCESS_CONTROL_BASE_5_HIGH                    0x1ed4
-#define MV64340_PCI_1_ACCESS_CONTROL_SIZE_5                         0x1ed8
-
-/****************************************/
-/*   PCI Configuration Access Registers */
-/****************************************/
-
-#define MV64340_PCI_0_CONFIG_ADDR 				    0xcf8
-#define MV64340_PCI_0_CONFIG_DATA_VIRTUAL_REG                       0xcfc
-#define MV64340_PCI_1_CONFIG_ADDR 				    0xc78
-#define MV64340_PCI_1_CONFIG_DATA_VIRTUAL_REG                       0xc7c
-#define MV64340_PCI_0_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG	            0xc34
-#define MV64340_PCI_1_INTERRUPT_ACKNOWLEDGE_VIRTUAL_REG	            0xcb4
-
-/****************************************/
-/*   PCI Error Report Registers         */
-/****************************************/
-
-#define MV64340_PCI_0_SERR_MASK					    0xc28
-#define MV64340_PCI_1_SERR_MASK					    0xca8
-#define MV64340_PCI_0_ERROR_ADDR_LOW                                0x1d40
-#define MV64340_PCI_1_ERROR_ADDR_LOW                                0x1dc0
-#define MV64340_PCI_0_ERROR_ADDR_HIGH                               0x1d44
-#define MV64340_PCI_1_ERROR_ADDR_HIGH                               0x1dc4
-#define MV64340_PCI_0_ERROR_ATTRIBUTE                               0x1d48
-#define MV64340_PCI_1_ERROR_ATTRIBUTE                               0x1dc8
-#define MV64340_PCI_0_ERROR_COMMAND                                 0x1d50
-#define MV64340_PCI_1_ERROR_COMMAND                                 0x1dd0
-#define MV64340_PCI_0_ERROR_CAUSE                                   0x1d58
-#define MV64340_PCI_1_ERROR_CAUSE                                   0x1dd8
-#define MV64340_PCI_0_ERROR_MASK                                    0x1d5c
-#define MV64340_PCI_1_ERROR_MASK                                    0x1ddc
-
-/****************************************/
-/*   PCI Debug Registers                */
-/****************************************/
-
-#define MV64340_PCI_0_MMASK                                         0X1D24
-#define MV64340_PCI_1_MMASK                                         0X1DA4
-
-/*********************************************/
-/* PCI Configuration, Function 0, Registers  */
-/*********************************************/
-
-#define MV64340_PCI_DEVICE_AND_VENDOR_ID 			    0x000
-#define MV64340_PCI_STATUS_AND_COMMAND				    0x004
-#define MV64340_PCI_CLASS_CODE_AND_REVISION_ID			    0x008
-#define MV64340_PCI_BIST_HEADER_TYPE_LATENCY_TIMER_CACHE_LINE 	    0x00C
-
-#define MV64340_PCI_SCS_0_BASE_ADDR_LOW   	      		    0x010
-#define MV64340_PCI_SCS_0_BASE_ADDR_HIGH   		            0x014
-#define MV64340_PCI_SCS_1_BASE_ADDR_LOW  	     	            0x018
-#define MV64340_PCI_SCS_1_BASE_ADDR_HIGH 		            0x01C
-#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_LOW      	    0x020
-#define MV64340_PCI_INTERNAL_REG_MEM_MAPPED_BASE_ADDR_HIGH     	    0x024
-#define MV64340_PCI_SUBSYSTEM_ID_AND_SUBSYSTEM_VENDOR_ID	    0x02c
-#define MV64340_PCI_EXPANSION_ROM_BASE_ADDR_REG	                    0x030
-#define MV64340_PCI_CAPABILTY_LIST_POINTER                          0x034
-#define MV64340_PCI_INTERRUPT_PIN_AND_LINE 			    0x03C
-       /* capability list */
-#define MV64340_PCI_POWER_MANAGEMENT_CAPABILITY                     0x040
-#define MV64340_PCI_POWER_MANAGEMENT_STATUS_AND_CONTROL             0x044
-#define MV64340_PCI_VPD_ADDR                                        0x048
-#define MV64340_PCI_VPD_DATA                                        0x04c
-#define MV64340_PCI_MSI_MESSAGE_CONTROL                             0x050
-#define MV64340_PCI_MSI_MESSAGE_ADDR                                0x054
-#define MV64340_PCI_MSI_MESSAGE_UPPER_ADDR                          0x058
-#define MV64340_PCI_MSI_MESSAGE_DATA                                0x05c
-#define MV64340_PCI_X_COMMAND                                       0x060
-#define MV64340_PCI_X_STATUS                                        0x064
-#define MV64340_PCI_COMPACT_PCI_HOT_SWAP                            0x068
-
-/***********************************************/
-/*   PCI Configuration, Function 1, Registers  */
-/***********************************************/
-
-#define MV64340_PCI_SCS_2_BASE_ADDR_LOW   			    0x110
-#define MV64340_PCI_SCS_2_BASE_ADDR_HIGH			    0x114
-#define MV64340_PCI_SCS_3_BASE_ADDR_LOW 			    0x118
-#define MV64340_PCI_SCS_3_BASE_ADDR_HIGH			    0x11c
-#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_LOW          	    0x120
-#define MV64340_PCI_INTERNAL_SRAM_BASE_ADDR_HIGH         	    0x124
-
-/***********************************************/
-/*  PCI Configuration, Function 2, Registers   */
-/***********************************************/
-
-#define MV64340_PCI_DEVCS_0_BASE_ADDR_LOW	    		    0x210
-#define MV64340_PCI_DEVCS_0_BASE_ADDR_HIGH 			    0x214
-#define MV64340_PCI_DEVCS_1_BASE_ADDR_LOW 			    0x218
-#define MV64340_PCI_DEVCS_1_BASE_ADDR_HIGH      		    0x21c
-#define MV64340_PCI_DEVCS_2_BASE_ADDR_LOW 			    0x220
-#define MV64340_PCI_DEVCS_2_BASE_ADDR_HIGH      		    0x224
-
-/***********************************************/
-/*  PCI Configuration, Function 3, Registers   */
-/***********************************************/
-
-#define MV64340_PCI_DEVCS_3_BASE_ADDR_LOW	    		    0x310
-#define MV64340_PCI_DEVCS_3_BASE_ADDR_HIGH 			    0x314
-#define MV64340_PCI_BOOT_CS_BASE_ADDR_LOW			    0x318
-#define MV64340_PCI_BOOT_CS_BASE_ADDR_HIGH      		    0x31c
-#define MV64340_PCI_CPU_BASE_ADDR_LOW 				    0x220
-#define MV64340_PCI_CPU_BASE_ADDR_HIGH      			    0x224
-
-/***********************************************/
-/*  PCI Configuration, Function 4, Registers   */
-/***********************************************/
-
-#define MV64340_PCI_P2P_MEM0_BASE_ADDR_LOW  			    0x410
-#define MV64340_PCI_P2P_MEM0_BASE_ADDR_HIGH 			    0x414
-#define MV64340_PCI_P2P_MEM1_BASE_ADDR_LOW   			    0x418
-#define MV64340_PCI_P2P_MEM1_BASE_ADDR_HIGH 			    0x41c
-#define MV64340_PCI_P2P_I_O_BASE_ADDR                 	            0x420
-#define MV64340_PCI_INTERNAL_REGS_I_O_MAPPED_BASE_ADDR              0x424
-
-/****************************************/
-/* Messaging Unit Registers (I20)   	*/
-/****************************************/
-
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_0_SIDE		    0x010
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_0_SIDE  		    0x014
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_0_SIDE 		    0x018
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_0_SIDE  		    0x01C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_0_SIDE  		    0x020
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE          0x024
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE	    0x028
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_0_SIDE 		    0x02C
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_0_SIDE         0x030
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_0_SIDE          0x034
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE       0x040
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_0_SIDE      0x044
-#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_0_SIDE 		    0x050
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_0_SIDE 		    0x054
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE        0x060
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE        0x064
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE        0x068
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE        0x06C
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_0_SIDE       0x070
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_0_SIDE       0x074
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_0_SIDE       0x0F8
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_0_SIDE       0x0FC
-
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_PCI_1_SIDE		    0x090
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_PCI_1_SIDE  		    0x094
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_PCI_1_SIDE 		    0x098
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_PCI_1_SIDE  		    0x09C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_PCI_1_SIDE  		    0x0A0
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE          0x0A4
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE	    0x0A8
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_PCI_1_SIDE 		    0x0AC
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_PCI_1_SIDE         0x0B0
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_PCI_1_SIDE          0x0B4
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE       0x0C0
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_PCI_1_SIDE      0x0C4
-#define MV64340_I2O_QUEUE_CONTROL_REG_PCI_1_SIDE 		    0x0D0
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_PCI_1_SIDE 		    0x0D4
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE        0x0E0
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE        0x0E4
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE        0x0E8
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE        0x0EC
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_PCI_1_SIDE       0x0F0
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_PCI_1_SIDE       0x0F4
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_PCI_1_SIDE       0x078
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_PCI_1_SIDE       0x07C
-
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU0_SIDE		    0x1C10
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU0_SIDE  		    0x1C14
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU0_SIDE 		    0x1C18
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU0_SIDE  		    0x1C1C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU0_SIDE  		    0x1C20
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE  	    0x1C24
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU0_SIDE	    0x1C28
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU0_SIDE 		    0x1C2C
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU0_SIDE          0x1C30
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU0_SIDE           0x1C34
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE        0x1C40
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU0_SIDE       0x1C44
-#define MV64340_I2O_QUEUE_CONTROL_REG_CPU0_SIDE 		    0x1C50
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU0_SIDE 		    0x1C54
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE         0x1C60
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE         0x1C64
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE         0x1C68
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE         0x1C6C
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU0_SIDE        0x1C70
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU0_SIDE        0x1C74
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU0_SIDE        0x1CF8
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU0_SIDE        0x1CFC
-#define MV64340_I2O_INBOUND_MESSAGE_REG0_CPU1_SIDE		    0x1C90
-#define MV64340_I2O_INBOUND_MESSAGE_REG1_CPU1_SIDE  		    0x1C94
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG0_CPU1_SIDE 		    0x1C98
-#define MV64340_I2O_OUTBOUND_MESSAGE_REG1_CPU1_SIDE  		    0x1C9C
-#define MV64340_I2O_INBOUND_DOORBELL_REG_CPU1_SIDE  		    0x1CA0
-#define MV64340_I2O_INBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE  	    0x1CA4
-#define MV64340_I2O_INBOUND_INTERRUPT_MASK_REG_CPU1_SIDE	    0x1CA8
-#define MV64340_I2O_OUTBOUND_DOORBELL_REG_CPU1_SIDE 		    0x1CAC
-#define MV64340_I2O_OUTBOUND_INTERRUPT_CAUSE_REG_CPU1_SIDE          0x1CB0
-#define MV64340_I2O_OUTBOUND_INTERRUPT_MASK_REG_CPU1_SIDE           0x1CB4
-#define MV64340_I2O_INBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE        0x1CC0
-#define MV64340_I2O_OUTBOUND_QUEUE_PORT_VIRTUAL_REG_CPU1_SIDE       0x1CC4
-#define MV64340_I2O_QUEUE_CONTROL_REG_CPU1_SIDE 		    0x1CD0
-#define MV64340_I2O_QUEUE_BASE_ADDR_REG_CPU1_SIDE 		    0x1CD4
-#define MV64340_I2O_INBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE         0x1CE0
-#define MV64340_I2O_INBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE         0x1CE4
-#define MV64340_I2O_INBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE         0x1CE8
-#define MV64340_I2O_INBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE         0x1CEC
-#define MV64340_I2O_OUTBOUND_FREE_HEAD_POINTER_REG_CPU1_SIDE        0x1CF0
-#define MV64340_I2O_OUTBOUND_FREE_TAIL_POINTER_REG_CPU1_SIDE        0x1CF4
-#define MV64340_I2O_OUTBOUND_POST_HEAD_POINTER_REG_CPU1_SIDE        0x1C78
-#define MV64340_I2O_OUTBOUND_POST_TAIL_POINTER_REG_CPU1_SIDE        0x1C7C
-
-/****************************************/
-/*        Ethernet Unit Registers  		*/
-/****************************************/
-
-/*******************************************/
-/*          CUNIT  Registers               */
-/*******************************************/
-
-         /* Address Decoding Register Map */
-           
-#define MV64340_CUNIT_BASE_ADDR_REG0                                0xf200
-#define MV64340_CUNIT_BASE_ADDR_REG1                                0xf208
-#define MV64340_CUNIT_BASE_ADDR_REG2                                0xf210
-#define MV64340_CUNIT_BASE_ADDR_REG3                                0xf218
-#define MV64340_CUNIT_SIZE0                                         0xf204
-#define MV64340_CUNIT_SIZE1                                         0xf20c
-#define MV64340_CUNIT_SIZE2                                         0xf214
-#define MV64340_CUNIT_SIZE3                                         0xf21c
-#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG0                          0xf240
-#define MV64340_CUNIT_HIGH_ADDR_REMAP_REG1                          0xf244
-#define MV64340_CUNIT_BASE_ADDR_ENABLE_REG                          0xf250
-#define MV64340_MPSC0_ACCESS_PROTECTION_REG                         0xf254
-#define MV64340_MPSC1_ACCESS_PROTECTION_REG                         0xf258
-#define MV64340_CUNIT_INTERNAL_SPACE_BASE_ADDR_REG                  0xf25C
-
-        /*  Error Report Registers  */
-
-#define MV64340_CUNIT_INTERRUPT_CAUSE_REG                           0xf310
-#define MV64340_CUNIT_INTERRUPT_MASK_REG                            0xf314
-#define MV64340_CUNIT_ERROR_ADDR                                    0xf318
-
-        /*  Cunit Control Registers */
-
-#define MV64340_CUNIT_ARBITER_CONTROL_REG                           0xf300
-#define MV64340_CUNIT_CONFIG_REG                                    0xb40c
-#define MV64340_CUNIT_CRROSBAR_TIMEOUT_REG                          0xf304
-
-        /*  Cunit Debug Registers   */
-
-#define MV64340_CUNIT_DEBUG_LOW                                     0xf340
-#define MV64340_CUNIT_DEBUG_HIGH                                    0xf344
-#define MV64340_CUNIT_MMASK                                         0xf380
-
-        /*  MPSCs Clocks Routing Registers  */
-
-#define MV64340_MPSC_ROUTING_REG                                    0xb400
-#define MV64340_MPSC_RX_CLOCK_ROUTING_REG                           0xb404
-#define MV64340_MPSC_TX_CLOCK_ROUTING_REG                           0xb408
-
-        /*  MPSCs Interrupts Registers    */
-
-#define MV64340_MPSC_CAUSE_REG(port)                               (0xb804 + (port<<3))
-#define MV64340_MPSC_MASK_REG(port)                                (0xb884 + (port<<3))
- 
-#define MV64340_MPSC_MAIN_CONFIG_LOW(port)                         (0x8000 + (port<<12))
-#define MV64340_MPSC_MAIN_CONFIG_HIGH(port)                        (0x8004 + (port<<12))    
-#define MV64340_MPSC_PROTOCOL_CONFIG(port)                         (0x8008 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG1(port)                            (0x800c + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG2(port)                            (0x8010 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG3(port)                            (0x8014 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG4(port)                            (0x8018 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG5(port)                            (0x801c + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG6(port)                            (0x8020 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG7(port)                            (0x8024 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG8(port)                            (0x8028 + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG9(port)                            (0x802c + (port<<12))    
-#define MV64340_MPSC_CHANNEL_REG10(port)                           (0x8030 + (port<<12))    
-        
-        /*  MPSC0 Registers      */
-
-
-/***************************************/
-/*          SDMA Registers             */
-/***************************************/
-
-#define MV64340_SDMA_CONFIG_REG(channel)                        (0x4000 + (channel<<13))        
-#define MV64340_SDMA_COMMAND_REG(channel)                       (0x4008 + (channel<<13))        
-#define MV64340_SDMA_CURRENT_RX_DESCRIPTOR_POINTER(channel)     (0x4810 + (channel<<13))        
-#define MV64340_SDMA_CURRENT_TX_DESCRIPTOR_POINTER(channel)     (0x4c10 + (channel<<13))        
-#define MV64340_SDMA_FIRST_TX_DESCRIPTOR_POINTER(channel)       (0x4c14 + (channel<<13)) 
-
-#define MV64340_SDMA_CAUSE_REG                                      0xb800
-#define MV64340_SDMA_MASK_REG                                       0xb880
-         
-/* BRG Interrupts */
-
-#define MV64340_BRG_CONFIG_REG(brg)                              (0xb200 + (brg<<3))
-#define MV64340_BRG_BAUDE_TUNING_REG(brg)                        (0xb208 + (brg<<3))
-#define MV64340_BRG_CAUSE_REG                                       0xb834
-#define MV64340_BRG_MASK_REG                                        0xb8b4
-
-/****************************************/
-/* DMA Channel Control			*/
-/****************************************/
-
-#define MV64340_DMA_CHANNEL0_CONTROL 				    0x840
-#define MV64340_DMA_CHANNEL0_CONTROL_HIGH			    0x880
-#define MV64340_DMA_CHANNEL1_CONTROL 				    0x844
-#define MV64340_DMA_CHANNEL1_CONTROL_HIGH			    0x884
-#define MV64340_DMA_CHANNEL2_CONTROL 				    0x848
-#define MV64340_DMA_CHANNEL2_CONTROL_HIGH			    0x888
-#define MV64340_DMA_CHANNEL3_CONTROL 				    0x84C
-#define MV64340_DMA_CHANNEL3_CONTROL_HIGH			    0x88C
-
-
-/****************************************/
-/*           IDMA Registers             */
-/****************************************/
-
-#define MV64340_DMA_CHANNEL0_BYTE_COUNT                             0x800
-#define MV64340_DMA_CHANNEL1_BYTE_COUNT                             0x804
-#define MV64340_DMA_CHANNEL2_BYTE_COUNT                             0x808
-#define MV64340_DMA_CHANNEL3_BYTE_COUNT                             0x80C
-#define MV64340_DMA_CHANNEL0_SOURCE_ADDR                            0x810
-#define MV64340_DMA_CHANNEL1_SOURCE_ADDR                            0x814
-#define MV64340_DMA_CHANNEL2_SOURCE_ADDR                            0x818
-#define MV64340_DMA_CHANNEL3_SOURCE_ADDR                            0x81c
-#define MV64340_DMA_CHANNEL0_DESTINATION_ADDR                       0x820
-#define MV64340_DMA_CHANNEL1_DESTINATION_ADDR                       0x824
-#define MV64340_DMA_CHANNEL2_DESTINATION_ADDR                       0x828
-#define MV64340_DMA_CHANNEL3_DESTINATION_ADDR                       0x82C
-#define MV64340_DMA_CHANNEL0_NEXT_DESCRIPTOR_POINTER                0x830
-#define MV64340_DMA_CHANNEL1_NEXT_DESCRIPTOR_POINTER                0x834
-#define MV64340_DMA_CHANNEL2_NEXT_DESCRIPTOR_POINTER                0x838
-#define MV64340_DMA_CHANNEL3_NEXT_DESCRIPTOR_POINTER                0x83C
-#define MV64340_DMA_CHANNEL0_CURRENT_DESCRIPTOR_POINTER             0x870
-#define MV64340_DMA_CHANNEL1_CURRENT_DESCRIPTOR_POINTER             0x874
-#define MV64340_DMA_CHANNEL2_CURRENT_DESCRIPTOR_POINTER             0x878
-#define MV64340_DMA_CHANNEL3_CURRENT_DESCRIPTOR_POINTER             0x87C
-
- /*  IDMA Address Decoding Base Address Registers  */
- 
-#define MV64340_DMA_BASE_ADDR_REG0                                  0xa00
-#define MV64340_DMA_BASE_ADDR_REG1                                  0xa08
-#define MV64340_DMA_BASE_ADDR_REG2                                  0xa10
-#define MV64340_DMA_BASE_ADDR_REG3                                  0xa18
-#define MV64340_DMA_BASE_ADDR_REG4                                  0xa20
-#define MV64340_DMA_BASE_ADDR_REG5                                  0xa28
-#define MV64340_DMA_BASE_ADDR_REG6                                  0xa30
-#define MV64340_DMA_BASE_ADDR_REG7                                  0xa38
- 
- /*  IDMA Address Decoding Size Address Register   */
- 
-#define MV64340_DMA_SIZE_REG0                                       0xa04
-#define MV64340_DMA_SIZE_REG1                                       0xa0c
-#define MV64340_DMA_SIZE_REG2                                       0xa14
-#define MV64340_DMA_SIZE_REG3                                       0xa1c
-#define MV64340_DMA_SIZE_REG4                                       0xa24
-#define MV64340_DMA_SIZE_REG5                                       0xa2c
-#define MV64340_DMA_SIZE_REG6                                       0xa34
-#define MV64340_DMA_SIZE_REG7                                       0xa3C
-
- /* IDMA Address Decoding High Address Remap and Access 
-                  Protection Registers                    */
-                  
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG0                            0xa60
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG1                            0xa64
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG2                            0xa68
-#define MV64340_DMA_HIGH_ADDR_REMAP_REG3                            0xa6C
-#define MV64340_DMA_BASE_ADDR_ENABLE_REG                            0xa80
-#define MV64340_DMA_CHANNEL0_ACCESS_PROTECTION_REG                  0xa70
-#define MV64340_DMA_CHANNEL1_ACCESS_PROTECTION_REG                  0xa74
-#define MV64340_DMA_CHANNEL2_ACCESS_PROTECTION_REG                  0xa78
-#define MV64340_DMA_CHANNEL3_ACCESS_PROTECTION_REG                  0xa7c
-#define MV64340_DMA_ARBITER_CONTROL                                 0x860
-#define MV64340_DMA_CROSS_BAR_TIMEOUT                               0x8d0
-
- /*  IDMA Headers Retarget Registers   */
-
-#define MV64340_DMA_HEADERS_RETARGET_CONTROL                        0xa84
-#define MV64340_DMA_HEADERS_RETARGET_BASE                           0xa88
-
- /*  IDMA Interrupt Register  */
-
-#define MV64340_DMA_INTERRUPT_CAUSE_REG                             0x8c0
-#define MV64340_DMA_INTERRUPT_CAUSE_MASK                            0x8c4
-#define MV64340_DMA_ERROR_ADDR                                      0x8c8
-#define MV64340_DMA_ERROR_SELECT                                    0x8cc
-
- /*  IDMA Debug Register ( for internal use )    */
-
-#define MV64340_DMA_DEBUG_LOW                                       0x8e0
-#define MV64340_DMA_DEBUG_HIGH                                      0x8e4
-#define MV64340_DMA_SPARE                                           0xA8C
-
-/****************************************/
-/* Timer_Counter 			*/
-/****************************************/
-
-#define MV64340_TIMER_COUNTER0					    0x850
-#define MV64340_TIMER_COUNTER1					    0x854
-#define MV64340_TIMER_COUNTER2					    0x858
-#define MV64340_TIMER_COUNTER3					    0x85C
-#define MV64340_TIMER_COUNTER_0_3_CONTROL			    0x864
-#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_CAUSE		    0x868
-#define MV64340_TIMER_COUNTER_0_3_INTERRUPT_MASK      		    0x86c
-
-/****************************************/
-/*         Watchdog registers  	        */
-/****************************************/
-
-#define MV64340_WATCHDOG_CONFIG_REG                                 0xb410
-#define MV64340_WATCHDOG_VALUE_REG                                  0xb414
-
-/****************************************/
-/* I2C Registers                        */
-/****************************************/
-
-#define MV64XXX_I2C_OFFSET                                          0xc000
-#define MV64XXX_I2C_REG_BLOCK_SIZE                                  0x0020
-
-/****************************************/
-/* GPP Interface Registers              */
-/****************************************/
-
-#define MV64340_GPP_IO_CONTROL                                      0xf100
-#define MV64340_GPP_LEVEL_CONTROL                                   0xf110
-#define MV64340_GPP_VALUE                                           0xf104
-#define MV64340_GPP_INTERRUPT_CAUSE                                 0xf108
-#define MV64340_GPP_INTERRUPT_MASK0                                 0xf10c
-#define MV64340_GPP_INTERRUPT_MASK1                                 0xf114
-#define MV64340_GPP_VALUE_SET                                       0xf118
-#define MV64340_GPP_VALUE_CLEAR                                     0xf11c
-
-/****************************************/
-/* Interrupt Controller Registers       */
-/****************************************/
-
-/****************************************/
-/* Interrupts	  			*/
-/****************************************/
-
-#define MV64340_MAIN_INTERRUPT_CAUSE_LOW                            0x004
-#define MV64340_MAIN_INTERRUPT_CAUSE_HIGH                           0x00c
-#define MV64340_CPU_INTERRUPT0_MASK_LOW                             0x014
-#define MV64340_CPU_INTERRUPT0_MASK_HIGH                            0x01c
-#define MV64340_CPU_INTERRUPT0_SELECT_CAUSE                         0x024
-#define MV64340_CPU_INTERRUPT1_MASK_LOW                             0x034
-#define MV64340_CPU_INTERRUPT1_MASK_HIGH                            0x03c
-#define MV64340_CPU_INTERRUPT1_SELECT_CAUSE                         0x044
-#define MV64340_INTERRUPT0_MASK_0_LOW                               0x054
-#define MV64340_INTERRUPT0_MASK_0_HIGH                              0x05c
-#define MV64340_INTERRUPT0_SELECT_CAUSE                             0x064
-#define MV64340_INTERRUPT1_MASK_0_LOW                               0x074
-#define MV64340_INTERRUPT1_MASK_0_HIGH                              0x07c
-#define MV64340_INTERRUPT1_SELECT_CAUSE                             0x084
-
-/****************************************/
-/*      MPP Interface Registers         */
-/****************************************/
-
-#define MV64340_MPP_CONTROL0                                        0xf000
-#define MV64340_MPP_CONTROL1                                        0xf004
-#define MV64340_MPP_CONTROL2                                        0xf008
-#define MV64340_MPP_CONTROL3                                        0xf00c
-
-/****************************************/
-/*    Serial Initialization registers   */
-/****************************************/
-
-#define MV64340_SERIAL_INIT_LAST_DATA                               0xf324
-#define MV64340_SERIAL_INIT_CONTROL                                 0xf328
-#define MV64340_SERIAL_INIT_STATUS                                  0xf32c
-
-extern void mv64340_irq_init(unsigned int base);
-
-#endif /* __ASM_MV643XX_H */
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 1463cbda4888..58600cf234bc 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -7,6 +7,7 @@
 #include <linux/path.h>
 #include <linux/fcntl.h>
 #include <linux/errno.h>
+#include <linux/fs_struct.h>
 
 enum { MAX_NESTED_LINKS = 8 };
 
@@ -18,71 +19,150 @@ enum { MAX_NESTED_LINKS = 8 };
 enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT};
 
 /* pathwalk mode */
-#define LOOKUP_FOLLOW		0x0001	/* follow links at the end */
-#define LOOKUP_DIRECTORY	0x0002	/* require a directory */
-#define LOOKUP_AUTOMOUNT	0x0004  /* force terminal automount */
-#define LOOKUP_EMPTY		0x4000	/* accept empty path [user_... only] */
-#define LOOKUP_DOWN		0x8000	/* follow mounts in the starting point */
-#define LOOKUP_MOUNTPOINT	0x0080	/* follow mounts in the end */
-
-#define LOOKUP_REVAL		0x0020	/* tell ->d_revalidate() to trust no cache */
-#define LOOKUP_RCU		0x0040	/* RCU pathwalk mode; semi-internal */
+#define LOOKUP_FOLLOW		BIT(0)	/* follow links at the end */
+#define LOOKUP_DIRECTORY	BIT(1)	/* require a directory */
+#define LOOKUP_AUTOMOUNT	BIT(2)  /* force terminal automount */
+#define LOOKUP_EMPTY		BIT(3)	/* accept empty path [user_... only] */
+#define LOOKUP_LINKAT_EMPTY	BIT(4) /* Linkat request with empty path. */
+#define LOOKUP_DOWN		BIT(5)	/* follow mounts in the starting point */
+#define LOOKUP_MOUNTPOINT	BIT(6)	/* follow mounts in the end */
+#define LOOKUP_REVAL		BIT(7)	/* tell ->d_revalidate() to trust no cache */
+#define LOOKUP_RCU		BIT(8)	/* RCU pathwalk mode; semi-internal */
+#define LOOKUP_CACHED		BIT(9) /* Only do cached lookup */
+#define LOOKUP_PARENT		BIT(10)	/* Looking up final parent in path */
+/* 5 spare bits for pathwalk */
 
 /* These tell filesystem methods that we are dealing with the final component... */
-#define LOOKUP_OPEN		0x0100	/* ... in open */
-#define LOOKUP_CREATE		0x0200	/* ... in object creation */
-#define LOOKUP_EXCL		0x0400	/* ... in exclusive creation */
-#define LOOKUP_RENAME_TARGET	0x0800	/* ... in destination of rename() */
+#define LOOKUP_OPEN		BIT(16)	/* ... in open */
+#define LOOKUP_CREATE		BIT(17)	/* ... in object creation */
+#define LOOKUP_EXCL		BIT(18)	/* ... in target must not exist */
+#define LOOKUP_RENAME_TARGET	BIT(19)	/* ... in destination of rename() */
 
-/* internal use only */
-#define LOOKUP_PARENT		0x0010
+/* 4 spare bits for intent */
 
 /* Scoping flags for lookup. */
-#define LOOKUP_NO_SYMLINKS	0x010000 /* No symlink crossing. */
-#define LOOKUP_NO_MAGICLINKS	0x020000 /* No nd_jump_link() crossing. */
-#define LOOKUP_NO_XDEV		0x040000 /* No mountpoint crossing. */
-#define LOOKUP_BENEATH		0x080000 /* No escaping from starting point. */
-#define LOOKUP_IN_ROOT		0x100000 /* Treat dirfd as fs root. */
-#define LOOKUP_CACHED		0x200000 /* Only do cached lookup */
+#define LOOKUP_NO_SYMLINKS	BIT(24) /* No symlink crossing. */
+#define LOOKUP_NO_MAGICLINKS	BIT(25) /* No nd_jump_link() crossing. */
+#define LOOKUP_NO_XDEV		BIT(26) /* No mountpoint crossing. */
+#define LOOKUP_BENEATH		BIT(27) /* No escaping from starting point. */
+#define LOOKUP_IN_ROOT		BIT(28) /* Treat dirfd as fs root. */
 /* LOOKUP_* flags which do scope-related checks based on the dirfd. */
 #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT)
+/* 3 spare bits for scoping */
 
 extern int path_pts(struct path *path);
 
-extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty);
-
-static inline int user_path_at(int dfd, const char __user *name, unsigned flags,
-		 struct path *path)
-{
-	return user_path_at_empty(dfd, name, flags, path, NULL);
-}
+extern int user_path_at(int, const char __user *, unsigned, struct path *);
 
 struct dentry *lookup_one_qstr_excl(const struct qstr *name,
 				    struct dentry *base,
 				    unsigned int flags);
 extern int kern_path(const char *, unsigned, struct path *);
-
-extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int);
-extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int);
-extern void done_path_create(struct path *, struct dentry *);
-extern struct dentry *kern_path_locked(const char *, struct path *);
+struct dentry *kern_path_parent(const char *name, struct path *parent);
+
+extern struct dentry *start_creating_path(int, const char *, struct path *, unsigned int);
+extern struct dentry *start_creating_user_path(int, const char __user *, struct path *, unsigned int);
+extern void end_creating_path(const struct path *, struct dentry *);
+extern struct dentry *start_removing_path(const char *, struct path *);
+extern struct dentry *start_removing_user_path_at(int , const char __user *, struct path *);
+static inline void end_removing_path(const struct path *path , struct dentry *dentry)
+{
+	end_creating_path(path, dentry);
+}
 int vfs_path_parent_lookup(struct filename *filename, unsigned int flags,
 			   struct path *parent, struct qstr *last, int *type,
 			   const struct path *root);
 int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *,
 		    unsigned int, struct path *);
 
-extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int);
-extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
-extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int);
-extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int);
-struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int);
+extern struct dentry *try_lookup_noperm(struct qstr *, struct dentry *);
+extern struct dentry *lookup_noperm(struct qstr *, struct dentry *);
+extern struct dentry *lookup_noperm_unlocked(struct qstr *, struct dentry *);
+extern struct dentry *lookup_noperm_positive_unlocked(struct qstr *, struct dentry *);
+struct dentry *lookup_one(struct mnt_idmap *, struct qstr *, struct dentry *);
 struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap,
-				   const char *name, struct dentry *base,
-				   int len);
+				   struct qstr *name, struct dentry *base);
 struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap,
-					    const char *name,
-					    struct dentry *base, int len);
+					    struct qstr *name,
+					    struct dentry *base);
+struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap,
+					    struct qstr *name,
+					    struct dentry *base);
+
+struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent,
+			      struct qstr *name);
+struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent,
+			      struct qstr *name);
+struct dentry *start_creating_killable(struct mnt_idmap *idmap,
+				       struct dentry *parent,
+				       struct qstr *name);
+struct dentry *start_removing_killable(struct mnt_idmap *idmap,
+				       struct dentry *parent,
+				       struct qstr *name);
+struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name);
+struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name);
+struct dentry *start_creating_dentry(struct dentry *parent,
+				     struct dentry *child);
+struct dentry *start_removing_dentry(struct dentry *parent,
+				     struct dentry *child);
+
+/* end_creating - finish action started with start_creating
+ * @child: dentry returned by start_creating() or vfs_mkdir()
+ *
+ * Unlock and release the child. This can be called after
+ * start_creating() whether that function succeeded or not,
+ * but it is not needed on failure.
+ *
+ * If vfs_mkdir() was called then the value returned from that function
+ * should be given for @child rather than the original dentry, as vfs_mkdir()
+ * may have provided a new dentry.
+ *
+ *
+ * If vfs_mkdir() was not called, then @child will be a valid dentry and
+ * @parent will be ignored.
+ */
+static inline void end_creating(struct dentry *child)
+{
+	end_dirop(child);
+}
+
+/* end_creating_keep - finish action started with start_creating() and return result
+ * @child: dentry returned by start_creating() or vfs_mkdir()
+ *
+ * Unlock and return the child. This can be called after
+ * start_creating() whether that function succeeded or not,
+ * but it is not needed on failure.
+ *
+ * If vfs_mkdir() was called then the value returned from that function
+ * should be given for @child rather than the original dentry, as vfs_mkdir()
+ * may have provided a new dentry.
+ *
+ * Returns: @child, which may be a dentry or an error.
+ *
+ */
+static inline struct dentry *end_creating_keep(struct dentry *child)
+{
+	if (!IS_ERR(child))
+		dget(child);
+	end_dirop(child);
+	return child;
+}
+
+/**
+ * end_removing - finish action started with start_removing
+ * @child:  dentry returned by start_removing()
+ * @parent: dentry given to start_removing()
+ *
+ * Unlock and release the child.
+ *
+ * This is identical to end_dirop().  It can be passed the result of
+ * start_removing() whether that was successful or not, but it not needed
+ * if start_removing() failed.
+ */
+static inline void end_removing(struct dentry *child)
+{
+	end_dirop(child);
+}
 
 extern int follow_down_one(struct path *);
 extern int follow_down(struct path *path, unsigned int flags);
@@ -91,6 +171,37 @@ extern int follow_up(struct path *);
 extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern struct dentry *lock_rename_child(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
+int start_renaming(struct renamedata *rd, int lookup_flags,
+		   struct qstr *old_last, struct qstr *new_last);
+int start_renaming_dentry(struct renamedata *rd, int lookup_flags,
+			  struct dentry *old_dentry, struct qstr *new_last);
+int start_renaming_two_dentries(struct renamedata *rd,
+				struct dentry *old_dentry, struct dentry *new_dentry);
+void end_renaming(struct renamedata *rd);
+
+/**
+ * mode_strip_umask - handle vfs umask stripping
+ * @dir:	parent directory of the new inode
+ * @mode:	mode of the new inode to be created in @dir
+ *
+ * In most filesystems, umask stripping depends on whether or not the
+ * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask
+ * stripping is done directly in here. If the filesystem does support POSIX
+ * ACLs umask stripping is deferred until the filesystem calls
+ * posix_acl_create().
+ *
+ * Some filesystems (like NFSv4) also want to avoid umask stripping by the
+ * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK
+ * to get this effect without declaring that they support POSIX ACLs.
+ *
+ * Returns: mode
+ */
+static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode)
+{
+	if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK))
+		mode &= ~current_umask();
+	return mode;
+}
 
 extern int __must_check nd_jump_link(const struct path *path);
 
@@ -112,7 +223,7 @@ static inline void nd_terminate_link(void *name, size_t len, size_t maxlen)
 static inline bool
 retry_estale(const long error, const unsigned int flags)
 {
-	return error == -ESTALE && !(flags & LOOKUP_REVAL);
+	return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL));
 }
 
 #endif /* _LINUX_NAMEI_H */
diff --git a/include/linux/nd.h b/include/linux/nd.h
index b9771ba1ef87..fa099e295f78 100644
--- a/include/linux/nd.h
+++ b/include/linux/nd.h
@@ -84,11 +84,7 @@ struct nd_device_driver {
 	void (*notify)(struct device *dev, enum nvdimm_event event);
 };
 
-static inline struct nd_device_driver *to_nd_device_driver(
-		struct device_driver *drv)
-{
-	return container_of(drv, struct nd_device_driver, drv);
-};
+#define to_nd_device_driver(__drv)	container_of_const(__drv, struct nd_device_driver, drv)
 
 /**
  * struct nd_namespace_common - core infrastructure of a namespace
diff --git a/include/linux/net.h b/include/linux/net.h
index b73ad8e3c212..f58b38ab37f8 100644
--- a/include/linux/net.h
+++ b/include/linux/net.h
@@ -36,13 +36,13 @@ struct net;
  * in sock->flags, but moved into sk->sk_wq->flags to be RCU protected.
  * Eventually all flags will be in sk->sk_wq->flags.
  */
-#define SOCKWQ_ASYNC_NOSPACE	0
-#define SOCKWQ_ASYNC_WAITDATA	1
-#define SOCK_NOSPACE		2
-#define SOCK_PASSCRED		3
-#define SOCK_PASSSEC		4
-#define SOCK_SUPPORT_ZC		5
-#define SOCK_CUSTOM_SOCKOPT	6
+enum socket_flags {
+	SOCKWQ_ASYNC_NOSPACE,
+	SOCKWQ_ASYNC_WAITDATA,
+	SOCK_NOSPACE,
+	SOCK_SUPPORT_ZC,
+	SOCK_CUSTOM_SOCKOPT,
+};
 
 #ifndef ARCH_HAS_SOCKET_TYPES
 /**
@@ -69,6 +69,7 @@ enum sock_type {
 	SOCK_DCCP	= 6,
 	SOCK_PACKET	= 10,
 };
+#endif /* ARCH_HAS_SOCKET_TYPES */
 
 #define SOCK_MAX (SOCK_PACKET + 1)
 /* Mask which covers at least up to SOCK_MASK-1.  The
@@ -80,8 +81,7 @@ enum sock_type {
 #ifndef SOCK_NONBLOCK
 #define SOCK_NONBLOCK	O_NONBLOCK
 #endif
-
-#endif /* ARCH_HAS_SOCKET_TYPES */
+#define SOCK_COREDUMP	O_NOCTTY
 
 /**
  * enum sock_shutdown_cmd - Shutdown types
@@ -122,7 +122,7 @@ struct socket {
 
 	struct file		*file;
 	struct sock		*sk;
-	const struct proto_ops	*ops;
+	const struct proto_ops	*ops; /* Might change with IPV6_ADDRFORM or MPTCP. */
 
 	struct socket_wq	wq;
 };
@@ -148,10 +148,10 @@ typedef struct {
 
 struct vm_area_struct;
 struct page;
-struct sockaddr;
 struct msghdr;
 struct module;
 struct sk_buff;
+struct proto_accept_arg;
 typedef int (*sk_read_actor_t)(read_descriptor_t *, struct sk_buff *,
 			       unsigned int, size_t);
 typedef int (*skb_read_actor_t)(struct sock *, struct sk_buff *);
@@ -162,15 +162,16 @@ struct proto_ops {
 	struct module	*owner;
 	int		(*release)   (struct socket *sock);
 	int		(*bind)	     (struct socket *sock,
-				      struct sockaddr *myaddr,
+				      struct sockaddr_unsized *myaddr,
 				      int sockaddr_len);
 	int		(*connect)   (struct socket *sock,
-				      struct sockaddr *vaddr,
+				      struct sockaddr_unsized *vaddr,
 				      int sockaddr_len, int flags);
 	int		(*socketpair)(struct socket *sock1,
 				      struct socket *sock2);
 	int		(*accept)    (struct socket *sock,
-				      struct socket *newsock, int flags, bool kern);
+				      struct socket *newsock,
+				      struct proto_accept_arg *arg);
 	int		(*getname)   (struct socket *sock,
 				      struct sockaddr *addr,
 				      int peer);
@@ -206,10 +207,9 @@ struct proto_ops {
 				      size_t total_len, int flags);
 	int		(*mmap)	     (struct file *file, struct socket *sock,
 				      struct vm_area_struct * vma);
-	ssize_t		(*sendpage)  (struct socket *sock, struct page *page,
-				      int offset, size_t size, int flags);
 	ssize_t 	(*splice_read)(struct socket *sock,  loff_t *ppos,
 				       struct pipe_inode_info *pipe, size_t len, unsigned int flags);
+	void		(*splice_eof)(struct socket *sock);
 	int		(*set_peek_off)(struct sock *sk, int val);
 	int		(*peek_len)(struct socket *sock);
 
@@ -220,8 +220,6 @@ struct proto_ops {
 				     sk_read_actor_t recv_actor);
 	/* This is different from read_sock(), it reads an entire skb at a time. */
 	int		(*read_skb)(struct sock *sk, skb_read_actor_t recv_actor);
-	int		(*sendpage_locked)(struct sock *sk, struct page *page,
-					   int offset, size_t size, int flags);
 	int		(*sendmsg_locked)(struct sock *sk, struct msghdr *msg,
 					  size_t size);
 	int		(*set_rcvlowat)(struct sock *sk, int val);
@@ -301,10 +299,7 @@ do {									\
 	net_ratelimited_function(pr_debug, fmt, ##__VA_ARGS__)
 #else
 #define net_dbg_ratelimited(fmt, ...)				\
-	do {							\
-		if (0)						\
-			no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__); \
-	} while (0)
+	no_printk(KERN_DEBUG pr_fmt(fmt), ##__VA_ARGS__)
 #endif
 
 #define net_get_random_once(buf, nbytes)			\
@@ -325,24 +320,37 @@ static inline bool sendpage_ok(struct page *page)
 	return !PageSlab(page) && page_count(page) >= 1;
 }
 
+/*
+ * Check sendpage_ok on contiguous pages.
+ */
+static inline bool sendpages_ok(struct page *page, size_t len, size_t offset)
+{
+	struct page *p = page + (offset >> PAGE_SHIFT);
+	size_t count = 0;
+
+	while (count < len) {
+		if (!sendpage_ok(p))
+			return false;
+
+		p++;
+		count += PAGE_SIZE;
+	}
+
+	return true;
+}
+
 int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len);
-int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg,
-			  struct kvec *vec, size_t num, size_t len);
 int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec,
 		   size_t num, size_t len, int flags);
 
-int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen);
+int kernel_bind(struct socket *sock, struct sockaddr_unsized *addr, int addrlen);
 int kernel_listen(struct socket *sock, int backlog);
 int kernel_accept(struct socket *sock, struct socket **newsock, int flags);
-int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen,
+int kernel_connect(struct socket *sock, struct sockaddr_unsized *addr, int addrlen,
 		   int flags);
 int kernel_getsockname(struct socket *sock, struct sockaddr *addr);
 int kernel_getpeername(struct socket *sock, struct sockaddr *addr);
-int kernel_sendpage(struct socket *sock, struct page *page, int offset,
-		    size_t size, int flags);
-int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset,
-			   size_t size, int flags);
 int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how);
 
 /* Routine returns the IP overhead imposed by a (caller-protected) socket. */
diff --git a/include/linux/net/intel/i40e_client.h b/include/linux/net/intel/i40e_client.h
index ed42bd5f639f..0aa4411528fc 100644
--- a/include/linux/net/intel/i40e_client.h
+++ b/include/linux/net/intel/i40e_client.h
@@ -45,7 +45,7 @@ struct i40e_qv_info {
 
 struct i40e_qvlist_info {
 	u32 num_vectors;
-	struct i40e_qv_info qv_info[];
+	struct i40e_qv_info qv_info[] __counted_by(num_vectors);
 };
 
 
diff --git a/include/linux/net/intel/iidc.h b/include/linux/net/intel/iidc.h
deleted file mode 100644
index 1c1332e4df26..000000000000
--- a/include/linux/net/intel/iidc.h
+++ /dev/null
@@ -1,107 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/* Copyright (C) 2021, Intel Corporation. */
-
-#ifndef _IIDC_H_
-#define _IIDC_H_
-
-#include <linux/auxiliary_bus.h>
-#include <linux/dcbnl.h>
-#include <linux/device.h>
-#include <linux/if_ether.h>
-#include <linux/kernel.h>
-#include <linux/netdevice.h>
-
-enum iidc_event_type {
-	IIDC_EVENT_BEFORE_MTU_CHANGE,
-	IIDC_EVENT_AFTER_MTU_CHANGE,
-	IIDC_EVENT_BEFORE_TC_CHANGE,
-	IIDC_EVENT_AFTER_TC_CHANGE,
-	IIDC_EVENT_CRIT_ERR,
-	IIDC_EVENT_NBITS		/* must be last */
-};
-
-enum iidc_reset_type {
-	IIDC_PFR,
-	IIDC_CORER,
-	IIDC_GLOBR,
-};
-
-enum iidc_rdma_protocol {
-	IIDC_RDMA_PROTOCOL_IWARP = BIT(0),
-	IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1),
-};
-
-#define IIDC_MAX_USER_PRIORITY		8
-#define IIDC_MAX_DSCP_MAPPING		64
-#define IIDC_DSCP_PFC_MODE		0x1
-
-/* Struct to hold per RDMA Qset info */
-struct iidc_rdma_qset_params {
-	/* Qset TEID returned to the RDMA driver in
-	 * ice_add_rdma_qset and used by RDMA driver
-	 * for calls to ice_del_rdma_qset
-	 */
-	u32 teid;	/* Qset TEID */
-	u16 qs_handle; /* RDMA driver provides this */
-	u16 vport_id; /* VSI index */
-	u8 tc; /* TC branch the Qset should belong to */
-};
-
-struct iidc_qos_info {
-	u64 tc_ctx;
-	u8 rel_bw;
-	u8 prio_type;
-	u8 egress_virt_up;
-	u8 ingress_virt_up;
-};
-
-/* Struct to pass QoS info */
-struct iidc_qos_params {
-	struct iidc_qos_info tc_info[IEEE_8021QAZ_MAX_TCS];
-	u8 up2tc[IIDC_MAX_USER_PRIORITY];
-	u8 vport_relative_bw;
-	u8 vport_priority_type;
-	u8 num_tc;
-	u8 pfc_mode;
-	u8 dscp_map[IIDC_MAX_DSCP_MAPPING];
-};
-
-struct iidc_event {
-	DECLARE_BITMAP(type, IIDC_EVENT_NBITS);
-	u32 reg;
-};
-
-struct ice_pf;
-
-int ice_add_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
-int ice_del_rdma_qset(struct ice_pf *pf, struct iidc_rdma_qset_params *qset);
-int ice_rdma_request_reset(struct ice_pf *pf, enum iidc_reset_type reset_type);
-int ice_rdma_update_vsi_filter(struct ice_pf *pf, u16 vsi_id, bool enable);
-void ice_get_qos_params(struct ice_pf *pf, struct iidc_qos_params *qos);
-
-/* Structure representing auxiliary driver tailored information about the core
- * PCI dev, each auxiliary driver using the IIDC interface will have an
- * instance of this struct dedicated to it.
- */
-
-struct iidc_auxiliary_dev {
-	struct auxiliary_device adev;
-	struct ice_pf *pf;
-};
-
-/* structure representing the auxiliary driver. This struct is to be
- * allocated and populated by the auxiliary driver's owner. The core PCI
- * driver will access these ops by performing a container_of on the
- * auxiliary_device->dev.driver.
- */
-struct iidc_auxiliary_drv {
-	struct auxiliary_driver adrv;
-	/* This event_handler is meant to be a blocking call.  For instance,
-	 * when a BEFORE_MTU_CHANGE event comes in, the event_handler will not
-	 * return until the auxiliary driver is ready for the MTU change to
-	 * happen.
-	 */
-	void (*event_handler)(struct ice_pf *pf, struct iidc_event *event);
-};
-
-#endif /* _IIDC_H_*/
diff --git a/include/linux/net/intel/iidc_rdma.h b/include/linux/net/intel/iidc_rdma.h
new file mode 100644
index 000000000000..8baad1082042
--- /dev/null
+++ b/include/linux/net/intel/iidc_rdma.h
@@ -0,0 +1,68 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Intel Corporation. */
+
+#ifndef _IIDC_RDMA_H_
+#define _IIDC_RDMA_H_
+
+#include <linux/auxiliary_bus.h>
+#include <linux/device.h>
+#include <linux/if_ether.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <net/dscp.h>
+
+enum iidc_rdma_event_type {
+	IIDC_RDMA_EVENT_BEFORE_MTU_CHANGE,
+	IIDC_RDMA_EVENT_AFTER_MTU_CHANGE,
+	IIDC_RDMA_EVENT_BEFORE_TC_CHANGE,
+	IIDC_RDMA_EVENT_AFTER_TC_CHANGE,
+	IIDC_RDMA_EVENT_WARN_RESET,
+	IIDC_RDMA_EVENT_CRIT_ERR,
+	IIDC_RDMA_EVENT_NBITS		/* must be last */
+};
+
+struct iidc_rdma_event {
+	DECLARE_BITMAP(type, IIDC_RDMA_EVENT_NBITS);
+	u32 reg;
+};
+
+enum iidc_rdma_reset_type {
+	IIDC_FUNC_RESET,
+	IIDC_DEV_RESET,
+};
+
+enum iidc_rdma_protocol {
+	IIDC_RDMA_PROTOCOL_IWARP = BIT(0),
+	IIDC_RDMA_PROTOCOL_ROCEV2 = BIT(1),
+};
+
+/* Structure to be populated by core LAN PCI driver */
+struct iidc_rdma_core_dev_info {
+	struct pci_dev *pdev; /* PCI device of corresponding to main function */
+	struct auxiliary_device *adev;
+	/* Current active RDMA protocol */
+	enum iidc_rdma_protocol rdma_protocol;
+	void *iidc_priv; /* elements unique to each driver */
+};
+
+/* Structure representing auxiliary driver tailored information about the core
+ * PCI dev, each auxiliary driver using the IIDC interface will have an
+ * instance of this struct dedicated to it.
+ */
+struct iidc_rdma_core_auxiliary_dev {
+	struct auxiliary_device adev;
+	struct iidc_rdma_core_dev_info *cdev_info;
+};
+
+/* structure representing the auxiliary driver. This struct is to be
+ * allocated and populated by the auxiliary driver's owner. The core PCI
+ * driver will access these ops by performing a container_of on the
+ * auxiliary_device->dev.driver.
+ */
+struct iidc_rdma_core_auxiliary_drv {
+	struct auxiliary_driver adrv;
+	void (*event_handler)(struct iidc_rdma_core_dev_info *cdev,
+			      struct iidc_rdma_event *event);
+};
+
+#endif /* _IIDC_RDMA_H_*/
diff --git a/include/linux/net/intel/iidc_rdma_ice.h b/include/linux/net/intel/iidc_rdma_ice.h
new file mode 100644
index 000000000000..b40eed0e13fe
--- /dev/null
+++ b/include/linux/net/intel/iidc_rdma_ice.h
@@ -0,0 +1,70 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2021-2025, Intel Corporation. */
+
+#ifndef _IIDC_RDMA_ICE_H_
+#define _IIDC_RDMA_ICE_H_
+
+#include <linux/dcbnl.h>
+
+#define IIDC_MAX_USER_PRIORITY         8
+#define IIDC_DSCP_PFC_MODE             0x1
+
+/**
+ * struct iidc_rdma_qset_params - Struct to hold per RDMA Qset info
+ * @teid: TEID of the Qset node
+ * @qs_handle: SW index of the Qset, RDMA provides this
+ * @vport_id: VSI index
+ * @tc: Traffic Class branch the QSet should belong to
+ */
+struct iidc_rdma_qset_params {
+	/* Qset TEID returned to the RDMA driver in
+	 * ice_add_rdma_qset and used by RDMA driver
+	 * for calls to ice_del_rdma_qset
+	 */
+	u32 teid;
+	u16 qs_handle;
+	u16 vport_id;
+	u8 tc;
+};
+
+struct iidc_rdma_qos_info {
+	u64 tc_ctx;
+	u8 rel_bw;
+	u8 prio_type;
+	u8 egress_virt_up;
+	u8 ingress_virt_up;
+};
+
+/* Struct to pass QoS info */
+struct iidc_rdma_qos_params {
+	struct iidc_rdma_qos_info tc_info[IEEE_8021QAZ_MAX_TCS];
+	u8 up2tc[IIDC_MAX_USER_PRIORITY];
+	u8 vport_relative_bw;
+	u8 vport_priority_type;
+	u8 num_tc;
+	u8 pfc_mode;
+	u8 dscp_map[DSCP_MAX];
+};
+
+struct iidc_rdma_priv_dev_info {
+	u8 pf_id;
+	u16 vport_id;
+	struct net_device *netdev;
+	struct iidc_rdma_qos_params qos_info;
+	u8 __iomem *hw_addr;
+};
+
+int ice_add_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset);
+int ice_del_rdma_qset(struct iidc_rdma_core_dev_info *cdev,
+		      struct iidc_rdma_qset_params *qset);
+int ice_rdma_request_reset(struct iidc_rdma_core_dev_info *cdev,
+			   enum iidc_rdma_reset_type reset_type);
+int ice_rdma_update_vsi_filter(struct iidc_rdma_core_dev_info *cdev, u16 vsi_id,
+			       bool enable);
+int ice_alloc_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry);
+void ice_free_rdma_qvector(struct iidc_rdma_core_dev_info *cdev,
+			   struct msix_entry *entry);
+
+#endif /* _IIDC_RDMA_ICE_H_*/
diff --git a/include/linux/net/intel/iidc_rdma_idpf.h b/include/linux/net/intel/iidc_rdma_idpf.h
new file mode 100644
index 000000000000..bab697e18fd6
--- /dev/null
+++ b/include/linux/net/intel/iidc_rdma_idpf.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2025 Intel Corporation. */
+
+#ifndef _IIDC_RDMA_IDPF_H_
+#define _IIDC_RDMA_IDPF_H_
+
+#include <linux/auxiliary_bus.h>
+
+/* struct to be populated by core LAN PCI driver */
+struct iidc_rdma_vport_dev_info {
+	struct auxiliary_device *adev;
+	struct auxiliary_device *core_adev;
+	struct net_device *netdev;
+	u16 vport_id;
+};
+
+struct iidc_rdma_vport_auxiliary_dev {
+	struct auxiliary_device adev;
+	struct iidc_rdma_vport_dev_info *vdev_info;
+};
+
+struct iidc_rdma_vport_auxiliary_drv {
+	struct auxiliary_driver adrv;
+	void (*event_handler)(struct iidc_rdma_vport_dev_info *vdev,
+			      struct iidc_rdma_event *event);
+};
+
+/* struct to be populated by core LAN PCI driver */
+enum iidc_function_type {
+	IIDC_FUNCTION_TYPE_PF,
+	IIDC_FUNCTION_TYPE_VF,
+};
+
+struct iidc_rdma_lan_mapped_mem_region {
+	u8 __iomem *region_addr;
+	__le64 size;
+	__le64 start_offset;
+};
+
+struct iidc_rdma_priv_dev_info {
+	struct msix_entry *msix_entries;
+	u16 msix_count; /* How many vectors are reserved for this device */
+	enum iidc_function_type ftype;
+	__le16 num_memory_regions;
+	struct iidc_rdma_lan_mapped_mem_region *mapped_mem_regions;
+};
+
+int idpf_idc_vport_dev_ctrl(struct iidc_rdma_core_dev_info *cdev_info, bool up);
+int idpf_idc_request_reset(struct iidc_rdma_core_dev_info *cdev_info,
+			   enum iidc_rdma_reset_type __always_unused reset_type);
+int idpf_idc_rdma_vc_send_sync(struct iidc_rdma_core_dev_info *cdev_info,
+			       u8 *send_msg, u16 msg_size,
+			       u8 *recv_msg, u16 *recv_len);
+
+#endif /* _IIDC_RDMA_IDPF_H_ */
diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h
new file mode 100644
index 000000000000..ab13bd777a28
--- /dev/null
+++ b/include/linux/net/intel/libie/adminq.h
@@ -0,0 +1,399 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef __LIBIE_ADMINQ_H
+#define __LIBIE_ADMINQ_H
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+
+#define LIBIE_CHECK_STRUCT_LEN(n, X)	\
+	static_assert((n) == sizeof(struct X))
+#define LIBIE_AQ_MAX_BUF_LEN 4096
+
+/**
+ * struct libie_aqc_generic - Generic structure used in adminq communication
+ * @param0: generic parameter high 32bit
+ * @param1: generic parameter lower 32bit
+ * @addr_high: generic address high 32bit
+ * @addr_low: generic address lower 32bit
+ */
+struct libie_aqc_generic {
+	__le32 param0;
+	__le32 param1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_generic);
+
+/**
+ * struct libie_aqc_get_ver -  Used in command get version (direct 0x0001)
+ * @rom_ver: rom version
+ * @fw_build: number coressponding to firmware build
+ * @fw_branch: branch identifier of firmware version
+ * @fw_major: major number of firmware version
+ * @fw_minor: minor number of firmware version
+ * @fw_patch: patch of firmware version
+ * @api_branch: brancch identifier of API version
+ * @api_major: major number of API version
+ * @api_minor: minor number of API version
+ * @api_patch: patch of API version
+ */
+struct libie_aqc_get_ver {
+	__le32	rom_ver;
+	__le32	fw_build;
+	u8	fw_branch;
+	u8	fw_major;
+	u8	fw_minor;
+	u8	fw_patch;
+	u8	api_branch;
+	u8	api_major;
+	u8	api_minor;
+	u8	api_patch;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_get_ver);
+
+/**
+ * struct libie_aqc_driver_ver - Used in command send driver version
+ *				 (indirect 0x0002)
+ * @major_ver: driver major version
+ * @minor_ver: driver minor version
+ * @build_ver: driver build version
+ * @subbuild_ver: driver subbuild version
+ * @reserved: for feature use
+ * @addr_high: high part of response address buff
+ * @addr_low: low part of response address buff
+ */
+struct libie_aqc_driver_ver {
+	u8	major_ver;
+	u8	minor_ver;
+	u8	build_ver;
+	u8	subbuild_ver;
+	u8	reserved[4];
+	__le32	addr_high;
+	__le32	addr_low;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_driver_ver);
+
+enum libie_aq_res_id {
+	LIBIE_AQC_RES_ID_NVM				= 1,
+	LIBIE_AQC_RES_ID_SDP				= 2,
+	LIBIE_AQC_RES_ID_CHNG_LOCK			= 3,
+	LIBIE_AQC_RES_ID_GLBL_LOCK			= 4,
+};
+
+enum libie_aq_res_access_type {
+	LIBIE_AQC_RES_ACCESS_READ			= 1,
+	LIBIE_AQC_RES_ACCESS_WRITE			= 2,
+};
+
+#define LIBIE_AQ_RES_NVM_READ_DFLT_TIMEOUT_MS		3000
+#define LIBIE_AQ_RES_NVM_WRITE_DFLT_TIMEOUT_MS		180000
+#define LIBIE_AQ_RES_CHNG_LOCK_DFLT_TIMEOUT_MS		1000
+#define LIBIE_AQ_RES_GLBL_LOCK_DFLT_TIMEOUT_MS		3000
+
+#define LIBIE_AQ_RES_GLBL_SUCCESS			0
+#define LIBIE_AQ_RES_GLBL_IN_PROG			1
+#define LIBIE_AQ_RES_GLBL_DONE				2
+
+/**
+ * struct libie_aqc_req_res - Request resource ownership
+ * @res_id: resource ID (look at enum definition above)
+ * @access_type: read or write (enum definition above)
+ * @timeout: Upon successful completion, FW writes this value and driver is
+ * expected to release resource before timeout. This value is provided in
+ * milliseconds.
+ * @res_number: for SDP, this is the pin ID of the SDP
+ * @status: status only used for LIBIE_AQC_RES_ID_GLBL_LOCK, for others reserved
+ * @reserved: reserved for future use
+ *
+ * Used in commands:
+ * request resource ownership (direct 0x0008)
+ * request resource ownership (direct 0x0009)
+ */
+struct libie_aqc_req_res {
+	__le16	res_id;
+	__le16	access_type;
+
+	__le32	timeout;
+	__le32	res_number;
+	__le16	status;
+	u8	reserved[2];
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_req_res);
+
+/**
+ * struct libie_aqc_list_caps - Getting capabilities
+ * @cmd_flags: command flags
+ * @pf_index: index of PF to get caps from
+ * @reserved: reserved for future use
+ * @count: number of capabilities records
+ * @addr_high: high part of response address buff
+ * @addr_low: low part of response address buff
+ *
+ * Used in commands:
+ * get function capabilities (indirect 0x000A)
+ * get device capabilities (indirect 0x000B)
+ */
+struct libie_aqc_list_caps {
+	u8	cmd_flags;
+	u8	pf_index;
+	u8	reserved[2];
+	__le32	count;
+	__le32	addr_high;
+	__le32	addr_low;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
+
+/* Device/Function buffer entry, repeated per reported capability */
+#define LIBIE_AQC_CAPS_SWITCH_MODE			0x0001
+#define LIBIE_AQC_CAPS_MNG_MODE				0x0002
+#define LIBIE_AQC_CAPS_NPAR_ACTIVE			0x0003
+#define LIBIE_AQC_CAPS_OS2BMC_CAP			0x0004
+#define LIBIE_AQC_CAPS_VALID_FUNCTIONS			0x0005
+#define LIBIE_AQC_MAX_VALID_FUNCTIONS			0x8
+#define LIBIE_AQC_CAPS_SRIOV				0x0012
+#define LIBIE_AQC_CAPS_VF				0x0013
+#define LIBIE_AQC_CAPS_VMDQ				0x0014
+#define LIBIE_AQC_CAPS_8021QBG				0x0015
+#define LIBIE_AQC_CAPS_8021QBR				0x0016
+#define LIBIE_AQC_CAPS_VSI				0x0017
+#define LIBIE_AQC_CAPS_DCB				0x0018
+#define LIBIE_AQC_CAPS_FCOE				0x0021
+#define LIBIE_AQC_CAPS_ISCSI				0x0022
+#define LIBIE_AQC_CAPS_RSS				0x0040
+#define LIBIE_AQC_CAPS_RXQS				0x0041
+#define LIBIE_AQC_CAPS_TXQS				0x0042
+#define LIBIE_AQC_CAPS_MSIX				0x0043
+#define LIBIE_AQC_CAPS_VF_MSIX				0x0044
+#define LIBIE_AQC_CAPS_FD				0x0045
+#define LIBIE_AQC_CAPS_1588				0x0046
+#define LIBIE_AQC_CAPS_MAX_MTU				0x0047
+#define LIBIE_AQC_CAPS_NVM_VER				0x0048
+#define LIBIE_AQC_CAPS_PENDING_NVM_VER			0x0049
+#define LIBIE_AQC_CAPS_OROM_VER				0x004A
+#define LIBIE_AQC_CAPS_PENDING_OROM_VER			0x004B
+#define LIBIE_AQC_CAPS_NET_VER				0x004C
+#define LIBIE_AQC_CAPS_PENDING_NET_VER			0x004D
+#define LIBIE_AQC_CAPS_RDMA				0x0051
+#define LIBIE_AQC_CAPS_LED				0x0061
+#define LIBIE_AQC_CAPS_SDP				0x0062
+#define LIBIE_AQC_CAPS_MDIO				0x0063
+#define LIBIE_AQC_CAPS_WSR_PROT				0x0064
+#define LIBIE_AQC_CAPS_SENSOR_READING			0x0067
+#define LIBIE_AQC_INLINE_IPSEC				0x0070
+#define LIBIE_AQC_CAPS_NUM_ENABLED_PORTS		0x0072
+#define LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
+#define LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT	0x0077
+#define LIBIE_AQC_CAPS_NVM_MGMT				0x0080
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG0		0x0081
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG1		0x0082
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG2		0x0083
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG3		0x0084
+#define LIBIE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
+#define LIBIE_AQC_CAPS_NAC_TOPOLOGY			0x0087
+#define LIBIE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
+#define LIBIE_AQC_BIT_ROCEV2_LAG			BIT(0)
+#define LIBIE_AQC_BIT_SRIOV_LAG				BIT(1)
+#define LIBIE_AQC_BIT_SRIOV_AA_LAG			BIT(2)
+#define LIBIE_AQC_CAPS_FLEX10				0x00F1
+#define LIBIE_AQC_CAPS_CEM				0x00F2
+
+/**
+ * struct libie_aqc_list_caps_elem - Getting list of caps elements
+ * @cap: one from the defines list above
+ * @major_ver: major version
+ * @minor_ver: minor version
+ * @number: number of resources described by this capability
+ * @logical_id: logical ID, only meaningful for some types of resources
+ * @phys_id: physical ID, only meaningful for some types of resources
+ * @rsvd1: reserved for future use
+ * @rsvd2: reserved for future use
+ */
+struct libie_aqc_list_caps_elem {
+	__le16	cap;
+
+	u8	major_ver;
+	u8	minor_ver;
+	__le32	number;
+	__le32	logical_id;
+	__le32	phys_id;
+	__le64	rsvd1;
+	__le64	rsvd2;
+};
+LIBIE_CHECK_STRUCT_LEN(32, libie_aqc_list_caps_elem);
+
+/* Admin Queue command opcodes */
+enum libie_adminq_opc {
+	/* FW Logging Commands */
+	libie_aqc_opc_fw_logs_config			= 0xFF30,
+	libie_aqc_opc_fw_logs_register			= 0xFF31,
+	libie_aqc_opc_fw_logs_query			= 0xFF32,
+	libie_aqc_opc_fw_logs_event			= 0xFF33,
+};
+
+enum libie_aqc_fw_logging_mod {
+	LIBIE_AQC_FW_LOG_ID_GENERAL = 0,
+	LIBIE_AQC_FW_LOG_ID_CTRL,
+	LIBIE_AQC_FW_LOG_ID_LINK,
+	LIBIE_AQC_FW_LOG_ID_LINK_TOPO,
+	LIBIE_AQC_FW_LOG_ID_DNL,
+	LIBIE_AQC_FW_LOG_ID_I2C,
+	LIBIE_AQC_FW_LOG_ID_SDP,
+	LIBIE_AQC_FW_LOG_ID_MDIO,
+	LIBIE_AQC_FW_LOG_ID_ADMINQ,
+	LIBIE_AQC_FW_LOG_ID_HDMA,
+	LIBIE_AQC_FW_LOG_ID_LLDP,
+	LIBIE_AQC_FW_LOG_ID_DCBX,
+	LIBIE_AQC_FW_LOG_ID_DCB,
+	LIBIE_AQC_FW_LOG_ID_XLR,
+	LIBIE_AQC_FW_LOG_ID_NVM,
+	LIBIE_AQC_FW_LOG_ID_AUTH,
+	LIBIE_AQC_FW_LOG_ID_VPD,
+	LIBIE_AQC_FW_LOG_ID_IOSF,
+	LIBIE_AQC_FW_LOG_ID_PARSER,
+	LIBIE_AQC_FW_LOG_ID_SW,
+	LIBIE_AQC_FW_LOG_ID_SCHEDULER,
+	LIBIE_AQC_FW_LOG_ID_TXQ,
+	LIBIE_AQC_FW_LOG_ID_RSVD,
+	LIBIE_AQC_FW_LOG_ID_POST,
+	LIBIE_AQC_FW_LOG_ID_WATCHDOG,
+	LIBIE_AQC_FW_LOG_ID_TASK_DISPATCH,
+	LIBIE_AQC_FW_LOG_ID_MNG,
+	LIBIE_AQC_FW_LOG_ID_SYNCE,
+	LIBIE_AQC_FW_LOG_ID_HEALTH,
+	LIBIE_AQC_FW_LOG_ID_TSDRV,
+	LIBIE_AQC_FW_LOG_ID_PFREG,
+	LIBIE_AQC_FW_LOG_ID_MDLVER,
+	LIBIE_AQC_FW_LOG_ID_MAX
+};
+
+/* Set FW Logging configuration (indirect 0xFF30)
+ * Register for FW Logging (indirect 0xFF31)
+ * Query FW Logging (indirect 0xFF32)
+ * FW Log Event (indirect 0xFF33)
+ */
+#define LIBIE_AQC_FW_LOG_CONF_UART_EN		BIT(0)
+#define LIBIE_AQC_FW_LOG_CONF_AQ_EN		BIT(1)
+#define LIBIE_AQC_FW_LOG_QUERY_REGISTERED	BIT(2)
+#define LIBIE_AQC_FW_LOG_CONF_SET_VALID		BIT(3)
+#define LIBIE_AQC_FW_LOG_AQ_REGISTER		BIT(0)
+#define LIBIE_AQC_FW_LOG_AQ_QUERY		BIT(2)
+
+#define LIBIE_AQC_FW_LOG_MIN_RESOLUTION		1
+#define LIBIE_AQC_FW_LOG_MAX_RESOLUTION		128
+
+struct libie_aqc_fw_log {
+	u8 cmd_flags;
+
+	u8 rsp_flag;
+	__le16 fw_rt_msb;
+	union {
+		struct {
+			__le32 fw_rt_lsb;
+		} sync;
+		struct {
+			__le16 log_resolution;
+			__le16 mdl_cnt;
+		} cfg;
+	} ops;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+
+/* Response Buffer for:
+ *    Set Firmware Logging Configuration (0xFF30)
+ *    Query FW Logging (0xFF32)
+ */
+struct libie_aqc_fw_log_cfg_resp {
+	__le16 module_identifier;
+	u8 log_level;
+	u8 rsvd0;
+};
+
+/**
+ * struct libie_aq_desc - Admin Queue (AQ) descriptor
+ * @flags: LIBIE_AQ_FLAG_* flags
+ * @opcode: AQ command opcode
+ * @datalen: length in bytes of indirect/external data buffer
+ * @retval: return value from firmware
+ * @cookie_high: opaque data high-half
+ * @cookie_low: opaque data low-half
+ * @params: command-specific parameters
+ *
+ * Descriptor format for commands the driver posts on the Admin Transmit Queue
+ * (ATQ). The firmware writes back onto the command descriptor and returns
+ * the result of the command. Asynchronous events that are not an immediate
+ * result of the command are written to the Admin Receive Queue (ARQ) using
+ * the same descriptor format. Descriptors are in little-endian notation with
+ * 32-bit words.
+ */
+struct libie_aq_desc {
+	__le16	flags;
+	__le16	opcode;
+	__le16	datalen;
+	__le16	retval;
+	__le32	cookie_high;
+	__le32	cookie_low;
+	union {
+		u8	raw[16];
+		struct	libie_aqc_generic generic;
+		struct	libie_aqc_get_ver get_ver;
+		struct	libie_aqc_driver_ver driver_ver;
+		struct	libie_aqc_req_res res_owner;
+		struct	libie_aqc_list_caps get_cap;
+		struct	libie_aqc_fw_log fw_log;
+	} params;
+};
+LIBIE_CHECK_STRUCT_LEN(32, libie_aq_desc);
+
+/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
+#define LIBIE_AQ_LG_BUF				512
+
+/* Flags sub-structure
+ * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
+ * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
+ */
+#define LIBIE_AQ_FLAG_DD			BIT(0)	/* 0x1    */
+#define LIBIE_AQ_FLAG_CMP			BIT(1)	/* 0x2    */
+#define LIBIE_AQ_FLAG_ERR			BIT(2)	/* 0x4    */
+#define LIBIE_AQ_FLAG_VFE			BIT(3)	/* 0x8    */
+#define LIBIE_AQ_FLAG_LB			BIT(9)	/* 0x200  */
+#define LIBIE_AQ_FLAG_RD			BIT(10)	/* 0x400  */
+#define LIBIE_AQ_FLAG_VFC			BIT(11) /* 0x800  */
+#define LIBIE_AQ_FLAG_BUF			BIT(12)	/* 0x1000 */
+#define LIBIE_AQ_FLAG_SI			BIT(13)	/* 0x2000 */
+#define LIBIE_AQ_FLAG_EI			BIT(14)	/* 0x4000 */
+#define LIBIE_AQ_FLAG_FE			BIT(15)	/* 0x8000 */
+
+/* error codes */
+enum libie_aq_err {
+	LIBIE_AQ_RC_OK		= 0,  /* Success */
+	LIBIE_AQ_RC_EPERM	= 1,  /* Operation not permitted */
+	LIBIE_AQ_RC_ENOENT	= 2,  /* No such element */
+	LIBIE_AQ_RC_ESRCH	= 3,  /* Bad opcode */
+	LIBIE_AQ_RC_EIO		= 5,  /* I/O error */
+	LIBIE_AQ_RC_EAGAIN	= 8,  /* Try again */
+	LIBIE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
+	LIBIE_AQ_RC_EACCES	= 10, /* Permission denied */
+	LIBIE_AQ_RC_EBUSY	= 12, /* Device or resource busy */
+	LIBIE_AQ_RC_EEXIST	= 13, /* Object already exists */
+	LIBIE_AQ_RC_EINVAL	= 14, /* Invalid argument */
+	LIBIE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
+	LIBIE_AQ_RC_ENOSYS	= 17, /* Function not implemented */
+	LIBIE_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
+	LIBIE_AQ_RC_ENOSEC	= 24, /* Missing security manifest */
+	LIBIE_AQ_RC_EBADSIG	= 25, /* Bad RSA signature */
+	LIBIE_AQ_RC_ESVN	= 26, /* SVN number prohibits this package */
+	LIBIE_AQ_RC_EBADMAN	= 27, /* Manifest hash mismatch */
+	LIBIE_AQ_RC_EBADBUF	= 28, /* Buffer hash mismatches manifest */
+};
+
+static inline void *libie_aq_raw(struct libie_aq_desc *desc)
+{
+	return &desc->params.raw;
+}
+
+const char *libie_aq_str(enum libie_aq_err err);
+
+#endif /* __LIBIE_ADMINQ_H */
diff --git a/include/linux/net/intel/libie/fwlog.h b/include/linux/net/intel/libie/fwlog.h
new file mode 100644
index 000000000000..7273c78c826b
--- /dev/null
+++ b/include/linux/net/intel/libie/fwlog.h
@@ -0,0 +1,97 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2022, Intel Corporation. */
+
+#ifndef _LIBIE_FWLOG_H_
+#define _LIBIE_FWLOG_H_
+
+#include <linux/net/intel/libie/adminq.h>
+
+/* Only a single log level should be set and all log levels under the set value
+ * are enabled, e.g. if log level is set to LIBIE_FW_LOG_LEVEL_VERBOSE, then all
+ * other log levels are included (except LIBIE_FW_LOG_LEVEL_NONE)
+ */
+enum libie_fwlog_level {
+	LIBIE_FWLOG_LEVEL_NONE = 0,
+	LIBIE_FWLOG_LEVEL_ERROR = 1,
+	LIBIE_FWLOG_LEVEL_WARNING = 2,
+	LIBIE_FWLOG_LEVEL_NORMAL = 3,
+	LIBIE_FWLOG_LEVEL_VERBOSE = 4,
+	LIBIE_FWLOG_LEVEL_INVALID, /* all values >= this entry are invalid */
+};
+
+struct libie_fwlog_module_entry {
+	/* module ID for the corresponding firmware logging event */
+	u16 module_id;
+	/* verbosity level for the module_id */
+	u8 log_level;
+};
+
+struct libie_fwlog_cfg {
+	/* list of modules for configuring log level */
+	struct libie_fwlog_module_entry module_entries[LIBIE_AQC_FW_LOG_ID_MAX];
+	/* options used to configure firmware logging */
+	u16 options;
+#define LIBIE_FWLOG_OPTION_ARQ_ENA		BIT(0)
+#define LIBIE_FWLOG_OPTION_UART_ENA		BIT(1)
+	/* set before calling libie_fwlog_init() so the PF registers for
+	 * firmware logging on initialization
+	 */
+#define LIBIE_FWLOG_OPTION_REGISTER_ON_INIT	BIT(2)
+	/* set in the libie_aq_fwlog_get() response if the PF is registered for
+	 * FW logging events over ARQ
+	 */
+#define LIBIE_FWLOG_OPTION_IS_REGISTERED	BIT(3)
+
+	/* minimum number of log events sent per Admin Receive Queue event */
+	u16 log_resolution;
+};
+
+struct libie_fwlog_data {
+	u16 data_size;
+	u8 *data;
+};
+
+struct libie_fwlog_ring {
+	struct libie_fwlog_data *rings;
+	u16 index;
+	u16 size;
+	u16 head;
+	u16 tail;
+};
+
+#define LIBIE_FWLOG_RING_SIZE_INDEX_DFLT 3
+#define LIBIE_FWLOG_RING_SIZE_DFLT 256
+#define LIBIE_FWLOG_RING_SIZE_MAX 512
+
+struct libie_fwlog {
+	struct libie_fwlog_cfg cfg;
+	bool supported; /* does hardware support FW logging? */
+	struct libie_fwlog_ring ring;
+	struct dentry *debugfs;
+	/* keep track of all the dentrys for FW log modules */
+	struct dentry **debugfs_modules;
+	struct_group_tagged(libie_fwlog_api, api,
+		struct pci_dev *pdev;
+		int (*send_cmd)(void *, struct libie_aq_desc *, void *, u16);
+		void *priv;
+		struct dentry *debugfs_root;
+	);
+};
+
+#if IS_ENABLED(CONFIG_LIBIE_FWLOG)
+int libie_fwlog_init(struct libie_fwlog *fwlog, struct libie_fwlog_api *api);
+void libie_fwlog_deinit(struct libie_fwlog *fwlog);
+void libie_fwlog_reregister(struct libie_fwlog *fwlog);
+void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, u16 len);
+#else
+static inline int libie_fwlog_init(struct libie_fwlog *fwlog,
+				   struct libie_fwlog_api *api)
+{
+	return -EOPNOTSUPP;
+}
+static inline void libie_fwlog_deinit(struct libie_fwlog *fwlog) { }
+static inline void libie_fwlog_reregister(struct libie_fwlog *fwlog) { }
+static inline void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf,
+					u16 len) { }
+#endif /* CONFIG_LIBIE_FWLOG */
+#endif /* _LIBIE_FWLOG_H_ */
diff --git a/include/linux/net/intel/libie/pctype.h b/include/linux/net/intel/libie/pctype.h
new file mode 100644
index 000000000000..d783417fbf36
--- /dev/null
+++ b/include/linux/net/intel/libie/pctype.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef __LIBIE_PCTYPE_H
+#define __LIBIE_PCTYPE_H
+
+/* Packet Classifier Type indexes, used to set the xxQF_HENA registers. Also
+ * communicated over the virtchnl API as part of struct virtchnl_rss_hashena.
+ */
+enum libie_filter_pctype {
+	/* Note: Values 0-28 are reserved for future use.
+	 * Value 29, 30, 32 are not supported on XL710 and X710.
+	 */
+	LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
+	LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK	= 32,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
+	LIBIE_FILTER_PCTYPE_FRAG_IPV4			= 36,
+	/* Note: Values 37-38 are reserved for future use.
+	 * Value 39, 40, 42 are not supported on XL710 and X710.
+	 */
+	LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
+	LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK	= 42,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP		= 44,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER		= 45,
+	LIBIE_FILTER_PCTYPE_FRAG_IPV6			= 46,
+	/* Note: Value 47 is reserved for future use */
+	LIBIE_FILTER_PCTYPE_FCOE_OX			= 48,
+	LIBIE_FILTER_PCTYPE_FCOE_RX			= 49,
+	LIBIE_FILTER_PCTYPE_FCOE_OTHER			= 50,
+	/* Note: Values 51-62 are reserved for future use */
+	LIBIE_FILTER_PCTYPE_L2_PAYLOAD			= 63
+};
+
+#endif /* __LIBIE_PCTYPE_H */
diff --git a/include/linux/net/intel/libie/rx.h b/include/linux/net/intel/libie/rx.h
new file mode 100644
index 000000000000..8e97775f1d66
--- /dev/null
+++ b/include/linux/net/intel/libie/rx.h
@@ -0,0 +1,50 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2024 Intel Corporation */
+
+#ifndef __LIBIE_RX_H
+#define __LIBIE_RX_H
+
+#include <net/libeth/rx.h>
+
+/* Rx buffer management */
+
+/* The largest size for a single descriptor as per HW */
+#define LIBIE_MAX_RX_BUF_LEN	9728U
+/* "True" HW-writeable space: minimum from SW and HW values */
+#define LIBIE_RX_BUF_LEN(hr)	min_t(u32, LIBETH_RX_PAGE_LEN(hr),	\
+				      LIBIE_MAX_RX_BUF_LEN)
+
+/* The maximum frame size as per HW (S/G) */
+#define __LIBIE_MAX_RX_FRM_LEN	16382U
+/* ATST, HW can chain up to 5 Rx descriptors */
+#define LIBIE_MAX_RX_FRM_LEN(hr)					\
+	min_t(u32, __LIBIE_MAX_RX_FRM_LEN, LIBIE_RX_BUF_LEN(hr) * 5)
+/* Maximum frame size minus LL overhead */
+#define LIBIE_MAX_MTU							\
+	(LIBIE_MAX_RX_FRM_LEN(LIBETH_MAX_HEADROOM) - LIBETH_RX_LL_LEN)
+
+/* O(1) converting i40e/ice/iavf's 8/10-bit hardware packet type to a parsed
+ * bitfield struct.
+ */
+
+#define LIBIE_RX_PT_NUM		154
+
+extern const struct libeth_rx_pt libie_rx_pt_lut[LIBIE_RX_PT_NUM];
+
+/**
+ * libie_rx_pt_parse - convert HW packet type to software bitfield structure
+ * @pt: 10-bit hardware packet type value from the descriptor
+ *
+ * ```libie_rx_pt_lut``` must be accessed only using this wrapper.
+ *
+ * Return: parsed bitfield struct corresponding to the provided ptype.
+ */
+static inline struct libeth_rx_pt libie_rx_pt_parse(u32 pt)
+{
+	if (unlikely(pt >= LIBIE_RX_PT_NUM))
+		pt = 0;
+
+	return libie_rx_pt_lut[pt];
+}
+
+#endif /* __LIBIE_RX_H */
diff --git a/include/linux/net_tstamp.h b/include/linux/net_tstamp.h
index fd67f3cc0c4b..f4936d9c2b3c 100644
--- a/include/linux/net_tstamp.h
+++ b/include/linux/net_tstamp.h
@@ -4,6 +4,42 @@
 #define _LINUX_NET_TIMESTAMPING_H_
 
 #include <uapi/linux/net_tstamp.h>
+#include <uapi/linux/ethtool_netlink_generated.h>
+
+#define SOF_TIMESTAMPING_SOFTWARE_MASK	(SOF_TIMESTAMPING_RX_SOFTWARE | \
+					 SOF_TIMESTAMPING_TX_SOFTWARE | \
+					 SOF_TIMESTAMPING_SOFTWARE)
+
+#define SOF_TIMESTAMPING_HARDWARE_MASK	(SOF_TIMESTAMPING_RX_HARDWARE | \
+					 SOF_TIMESTAMPING_TX_HARDWARE | \
+					 SOF_TIMESTAMPING_RAW_HARDWARE)
+
+/**
+ * struct hwtstamp_provider_desc - hwtstamp provider description
+ *
+ * @index: index of the hwtstamp provider.
+ * @qualifier: hwtstamp provider qualifier.
+ */
+struct hwtstamp_provider_desc {
+	int index;
+	enum hwtstamp_provider_qualifier qualifier;
+};
+
+/**
+ * struct hwtstamp_provider - hwtstamp provider object
+ *
+ * @rcu_head: RCU callback used to free the struct.
+ * @source: source of the hwtstamp provider.
+ * @phydev: pointer of the phydev source in case a PTP coming from phylib
+ * @desc: hwtstamp provider description.
+ */
+
+struct hwtstamp_provider {
+	struct rcu_head rcu_head;
+	enum hwtstamp_source source;
+	struct phy_device *phydev;
+	struct hwtstamp_provider_desc desc;
+};
 
 /**
  * struct kernel_hwtstamp_config - Kernel copy of struct hwtstamp_config
@@ -11,6 +47,13 @@
  * @flags: see struct hwtstamp_config
  * @tx_type: see struct hwtstamp_config
  * @rx_filter: see struct hwtstamp_config
+ * @ifr: pointer to ifreq structure from the original ioctl request, to pass to
+ *	a legacy implementation of a lower driver
+ * @copied_to_user: request was passed to a legacy implementation which already
+ *	copied the ioctl request back to user space
+ * @source: indication whether timestamps should come from the netdev or from
+ *	an attached phylib PHY
+ * @qualifier: qualifier of the hwtstamp provider
  *
  * Prefer using this structure for in-kernel processing of hardware
  * timestamping configuration, over the inextensible struct hwtstamp_config
@@ -20,6 +63,10 @@ struct kernel_hwtstamp_config {
 	int flags;
 	int tx_type;
 	int rx_filter;
+	struct ifreq *ifr;
+	bool copied_to_user;
+	enum hwtstamp_source source;
+	enum hwtstamp_provider_qualifier qualifier;
 };
 
 static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kernel_cfg,
@@ -30,4 +77,20 @@ static inline void hwtstamp_config_to_kernel(struct kernel_hwtstamp_config *kern
 	kernel_cfg->rx_filter = cfg->rx_filter;
 }
 
+static inline void hwtstamp_config_from_kernel(struct hwtstamp_config *cfg,
+					       const struct kernel_hwtstamp_config *kernel_cfg)
+{
+	cfg->flags = kernel_cfg->flags;
+	cfg->tx_type = kernel_cfg->tx_type;
+	cfg->rx_filter = kernel_cfg->rx_filter;
+}
+
+static inline bool kernel_hwtstamp_config_changed(const struct kernel_hwtstamp_config *a,
+						  const struct kernel_hwtstamp_config *b)
+{
+	return a->flags != b->flags ||
+	       a->tx_type != b->tx_type ||
+	       a->rx_filter != b->rx_filter;
+}
+
 #endif /* _LINUX_NET_TIMESTAMPING_H_ */
diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h
index 7c2d77d75a88..93e4da7046a1 100644
--- a/include/linux/netdev_features.h
+++ b/include/linux/netdev_features.h
@@ -24,9 +24,8 @@ enum {
 	NETIF_F_HW_VLAN_CTAG_FILTER_BIT,/* Receive filtering on VLAN CTAGs */
 	NETIF_F_VLAN_CHALLENGED_BIT,	/* Device cannot handle VLAN packets */
 	NETIF_F_GSO_BIT,		/* Enable software GSO. */
-	NETIF_F_LLTX_BIT,		/* LockLess TX - deprecated. Please */
-					/* do not use LLTX in new drivers */
-	NETIF_F_NETNS_LOCAL_BIT,	/* Does not change network namespaces */
+	__UNUSED_NETIF_F_12,
+	__UNUSED_NETIF_F_13,
 	NETIF_F_GRO_BIT,		/* Generic receive offload */
 	NETIF_F_LRO_BIT,		/* large receive offload */
 
@@ -54,12 +53,12 @@ enum {
 	NETIF_F_GSO_UDP_BIT,		/* ... UFO, deprecated except tuntap */
 	NETIF_F_GSO_UDP_L4_BIT,		/* ... UDP payload GSO (not UFO) */
 	NETIF_F_GSO_FRAGLIST_BIT,		/* ... Fraglist GSO */
+	NETIF_F_GSO_ACCECN_BIT,		/* TCP AccECN w/ TSO (no clear CWR) */
 	/**/NETIF_F_GSO_LAST =		/* last bit, see GSO_MASK */
-		NETIF_F_GSO_FRAGLIST_BIT,
+		NETIF_F_GSO_ACCECN_BIT,
 
 	NETIF_F_FCOE_CRC_BIT,		/* FCoE CRC32 */
 	NETIF_F_SCTP_CRC_BIT,		/* SCTP checksum offload */
-	NETIF_F_FCOE_MTU_BIT,		/* Supports max FCoE MTU, 2158 bytes*/
 	NETIF_F_NTUPLE_BIT,		/* N-tuple filters supported */
 	NETIF_F_RXHASH_BIT,		/* Receive hashing offload */
 	NETIF_F_RXCSUM_BIT,		/* Receive checksumming offload */
@@ -106,7 +105,6 @@ enum {
 #define __NETIF_F(name)		__NETIF_F_BIT(NETIF_F_##name##_BIT)
 
 #define NETIF_F_FCOE_CRC	__NETIF_F(FCOE_CRC)
-#define NETIF_F_FCOE_MTU	__NETIF_F(FCOE_MTU)
 #define NETIF_F_FRAGLIST	__NETIF_F(FRAGLIST)
 #define NETIF_F_FSO		__NETIF_F(FSO)
 #define NETIF_F_GRO		__NETIF_F(GRO)
@@ -120,10 +118,8 @@ enum {
 #define NETIF_F_HW_VLAN_CTAG_TX	__NETIF_F(HW_VLAN_CTAG_TX)
 #define NETIF_F_IP_CSUM		__NETIF_F(IP_CSUM)
 #define NETIF_F_IPV6_CSUM	__NETIF_F(IPV6_CSUM)
-#define NETIF_F_LLTX		__NETIF_F(LLTX)
 #define NETIF_F_LOOPBACK	__NETIF_F(LOOPBACK)
 #define NETIF_F_LRO		__NETIF_F(LRO)
-#define NETIF_F_NETNS_LOCAL	__NETIF_F(NETNS_LOCAL)
 #define NETIF_F_NOCACHE_COPY	__NETIF_F(NOCACHE_COPY)
 #define NETIF_F_NTUPLE		__NETIF_F(NTUPLE)
 #define NETIF_F_RXCSUM		__NETIF_F(RXCSUM)
@@ -132,6 +128,7 @@ enum {
 #define NETIF_F_SG		__NETIF_F(SG)
 #define NETIF_F_TSO6		__NETIF_F(TSO6)
 #define NETIF_F_TSO_ECN		__NETIF_F(TSO_ECN)
+#define NETIF_F_GSO_ACCECN	__NETIF_F(GSO_ACCECN)
 #define NETIF_F_TSO		__NETIF_F(TSO)
 #define NETIF_F_VLAN_CHALLENGED	__NETIF_F(VLAN_CHALLENGED)
 #define NETIF_F_RXFCS		__NETIF_F(RXFCS)
@@ -192,8 +189,7 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 
 /* Features valid for ethtool to change */
 /* = all defined minus driver/device-class-related */
-#define NETIF_F_NEVER_CHANGE	(NETIF_F_VLAN_CHALLENGED | \
-				 NETIF_F_LLTX | NETIF_F_NETNS_LOCAL)
+#define NETIF_F_NEVER_CHANGE	NETIF_F_VLAN_CHALLENGED
 
 /* remember that ((t)1 << t_BITS) is undefined in C99 */
 #define NETIF_F_ETHTOOL_BITS	((__NETIF_F_BIT(NETDEV_FEATURE_COUNT - 1) | \
@@ -214,11 +210,9 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 #define NETIF_F_ALL_TSO 	(NETIF_F_TSO | NETIF_F_TSO6 | \
 				 NETIF_F_TSO_ECN | NETIF_F_TSO_MANGLEID)
 
-#define NETIF_F_ALL_FCOE	(NETIF_F_FCOE_CRC | NETIF_F_FCOE_MTU | \
-				 NETIF_F_FSO)
-
 /* List of features with software fallbacks. */
-#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | NETIF_F_GSO_SCTP |	     \
+#define NETIF_F_GSO_SOFTWARE	(NETIF_F_ALL_TSO | \
+				 NETIF_F_GSO_ACCECN | NETIF_F_GSO_SCTP | \
 				 NETIF_F_GSO_UDP_L4 | NETIF_F_GSO_FRAGLIST)
 
 /*
@@ -261,4 +255,29 @@ static inline int find_next_netdev_feature(u64 feature, unsigned long start)
 				 NETIF_F_GSO_UDP_TUNNEL |		\
 				 NETIF_F_GSO_UDP_TUNNEL_CSUM)
 
+/* virtual device features */
+#define MASTER_UPPER_DEV_VLAN_FEATURES	 (NETIF_F_HW_CSUM | NETIF_F_SG | \
+					  NETIF_F_FRAGLIST | NETIF_F_GSO_SOFTWARE | \
+					  NETIF_F_GSO_ENCAP_ALL | \
+					  NETIF_F_HIGHDMA | NETIF_F_LRO)
+
+#define MASTER_UPPER_DEV_ENC_FEATURES	 (NETIF_F_HW_CSUM | NETIF_F_SG | \
+					  NETIF_F_RXCSUM | NETIF_F_GSO_SOFTWARE | \
+					  NETIF_F_GSO_PARTIAL)
+
+#define MASTER_UPPER_DEV_MPLS_FEATURES	 (NETIF_F_HW_CSUM | NETIF_F_SG | \
+					  NETIF_F_GSO_SOFTWARE)
+
+#define MASTER_UPPER_DEV_XFRM_FEATURES	 (NETIF_F_HW_ESP | NETIF_F_HW_ESP_TX_CSUM | \
+					  NETIF_F_GSO_ESP)
+
+#define MASTER_UPPER_DEV_GSO_PARTIAL_FEATURES (NETIF_F_GSO_ESP)
+
+static inline netdev_features_t netdev_base_features(netdev_features_t features)
+{
+	features &= ~NETIF_F_ONE_FOR_ALL;
+	features |= NETIF_F_ALL_FOR_ALL;
+	return features;
+}
+
 #endif	/* _LINUX_NETDEV_FEATURES_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 08fbd4622ccf..5870a9e514a5 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -40,10 +40,9 @@
 #include <net/dcbnl.h>
 #endif
 #include <net/netprio_cgroup.h>
-#include <net/xdp.h>
-
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
+#include <linux/netdevice_xmit.h>
 #include <uapi/linux/netdevice.h>
 #include <uapi/linux/if_bonding.h>
 #include <uapi/linux/pkt_cls.h>
@@ -53,15 +52,18 @@
 #include <net/net_trackers.h>
 #include <net/net_debug.h>
 #include <net/dropreason-core.h>
+#include <net/neighbour_tables.h>
 
 struct netpoll_info;
 struct device;
 struct ethtool_ops;
+struct kernel_hwtstamp_config;
 struct phy_device;
 struct dsa_port;
-struct ip_tunnel_parm;
+struct ip_tunnel_parm_kern;
 struct macsec_context;
 struct macsec_ops;
+struct netdev_config;
 struct netdev_name_node;
 struct sd_flow_limit;
 struct sfp_bus;
@@ -76,7 +78,14 @@ struct udp_tunnel_nic_info;
 struct udp_tunnel_nic;
 struct bpf_prog;
 struct xdp_buff;
+struct xdp_frame;
+struct xdp_metadata_ops;
 struct xdp_md;
+struct ethtool_netdev_state;
+struct phy_link_topology;
+struct hwtstamp_provider;
+
+typedef u32 xdp_features_t;
 
 void synchronize_net(void);
 void netdev_set_default_ethtool_ops(struct net_device *dev,
@@ -221,12 +230,6 @@ struct net_device_core_stats {
 #include <linux/cache.h>
 #include <linux/skbuff.h>
 
-#ifdef CONFIG_RPS
-#include <linux/static_key.h>
-extern struct static_key_false rps_needed;
-extern struct static_key_false rfs_needed;
-#endif
-
 struct neighbour;
 struct neigh_parms;
 struct sk_buff;
@@ -337,15 +340,45 @@ struct gro_list {
 };
 
 /*
- * size of gro hash buckets, must less than bit number of
- * napi_struct::gro_bitmask
+ * size of gro hash buckets, must be <= the number of bits in
+ * gro_node::bitmask
  */
 #define GRO_HASH_BUCKETS	8
 
+/**
+ * struct gro_node - structure to support Generic Receive Offload
+ * @bitmask: bitmask to indicate used buckets in @hash
+ * @hash: hashtable of pending aggregated skbs, separated by flows
+ * @rx_list: list of pending ``GRO_NORMAL`` skbs
+ * @rx_count: cached current length of @rx_list
+ * @cached_napi_id: napi_struct::napi_id cached for hotpath, 0 for standalone
+ */
+struct gro_node {
+	unsigned long		bitmask;
+	struct gro_list		hash[GRO_HASH_BUCKETS];
+	struct list_head	rx_list;
+	u32			rx_count;
+	u32			cached_napi_id;
+};
+
+/*
+ * Structure for per-NAPI config
+ */
+struct napi_config {
+	u64 gro_flush_timeout;
+	u64 irq_suspend_timeout;
+	u32 defer_hard_irqs;
+	cpumask_t affinity_mask;
+	u8 threaded;
+	unsigned int napi_id;
+};
+
 /*
  * Structure for NAPI scheduling similar to tasklet but with weighting
  */
 struct napi_struct {
+	/* This field should be first or softnet_data.backlog needs tweaks. */
+	unsigned long		state;
 	/* The poll_list must only be managed by the entity which
 	 * changes the state of the NAPI_STATE_SCHED bit.  This means
 	 * whoever atomically sets that bit can add this napi_struct
@@ -354,10 +387,8 @@ struct napi_struct {
 	 */
 	struct list_head	poll_list;
 
-	unsigned long		state;
 	int			weight;
-	int			defer_hard_irqs_count;
-	unsigned long		gro_bitmask;
+	u32			defer_hard_irqs_count;
 	int			(*poll)(struct napi_struct *, int);
 #ifdef CONFIG_NETPOLL
 	/* CPU actively polling if netpoll is configured */
@@ -366,16 +397,23 @@ struct napi_struct {
 	/* CPU on which NAPI has been scheduled for processing */
 	int			list_owner;
 	struct net_device	*dev;
-	struct gro_list		gro_hash[GRO_HASH_BUCKETS];
 	struct sk_buff		*skb;
-	struct list_head	rx_list; /* Pending GRO_NORMAL skbs */
-	int			rx_count; /* length of rx_list */
-	unsigned int		napi_id;
+	struct gro_node		gro;
 	struct hrtimer		timer;
+	/* all fields past this point are write-protected by netdev_lock */
 	struct task_struct	*thread;
+	unsigned long		gro_flush_timeout;
+	unsigned long		irq_suspend_timeout;
+	u32			defer_hard_irqs;
 	/* control-path-only fields follow */
+	u32			napi_id;
 	struct list_head	dev_list;
 	struct hlist_node	napi_hash_node;
+	int			irq;
+	struct irq_affinity_notify notify;
+	int			napi_rmap_idx;
+	int			index;
+	struct napi_config	*config;
 };
 
 enum {
@@ -385,10 +423,12 @@ enum {
 	NAPI_STATE_NPSVC,		/* Netpoll - don't dequeue from poll_list */
 	NAPI_STATE_LISTED,		/* NAPI added to system lists */
 	NAPI_STATE_NO_BUSY_POLL,	/* Do not add in napi_hash, no busy polling */
-	NAPI_STATE_IN_BUSY_POLL,	/* sk_busy_loop() owns this NAPI */
+	NAPI_STATE_IN_BUSY_POLL,	/* Do not rearm NAPI interrupt */
 	NAPI_STATE_PREFER_BUSY_POLL,	/* prefer busy-polling over softirq processing*/
 	NAPI_STATE_THREADED,		/* The poll is performed inside its own thread*/
 	NAPI_STATE_SCHED_THREADED,	/* Napi is currently scheduled in threaded mode */
+	NAPI_STATE_HAS_NOTIFIER,	/* Napi has an IRQ notifier */
+	NAPI_STATE_THREADED_BUSY_POLL,	/* The threaded NAPI poller will busy poll */
 };
 
 enum {
@@ -402,6 +442,8 @@ enum {
 	NAPIF_STATE_PREFER_BUSY_POLL	= BIT(NAPI_STATE_PREFER_BUSY_POLL),
 	NAPIF_STATE_THREADED		= BIT(NAPI_STATE_THREADED),
 	NAPIF_STATE_SCHED_THREADED	= BIT(NAPI_STATE_SCHED_THREADED),
+	NAPIF_STATE_HAS_NOTIFIER	= BIT(NAPI_STATE_HAS_NOTIFIER),
+	NAPIF_STATE_THREADED_BUSY_POLL	= BIT(NAPI_STATE_THREADED_BUSY_POLL),
 };
 
 enum gro_result {
@@ -476,6 +518,29 @@ static inline bool napi_prefer_busy_poll(struct napi_struct *n)
 	return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
 }
 
+/**
+ * napi_is_scheduled - test if NAPI is scheduled
+ * @n: NAPI context
+ *
+ * This check is "best-effort". With no locking implemented,
+ * a NAPI can be scheduled or terminate right after this check
+ * and produce not precise results.
+ *
+ * NAPI_STATE_SCHED is an internal state, napi_is_scheduled
+ * should not be used normally and napi_schedule should be
+ * used instead.
+ *
+ * Use only if the driver really needs to check if a NAPI
+ * is scheduled for example in the context of delayed timer
+ * that can be skipped if a NAPI is already scheduled.
+ *
+ * Return: True if NAPI is scheduled, False otherwise.
+ */
+static inline bool napi_is_scheduled(struct napi_struct *n)
+{
+	return test_bit(NAPI_STATE_SCHED, &n->state);
+}
+
 bool napi_schedule_prep(struct napi_struct *n);
 
 /**
@@ -484,11 +549,18 @@ bool napi_schedule_prep(struct napi_struct *n);
  *
  * Schedule NAPI poll routine to be called if it is not already
  * running.
+ * Return: true if we schedule a NAPI or false if not.
+ * Refer to napi_schedule_prep() for additional reason on why
+ * a NAPI might not be scheduled.
  */
-static inline void napi_schedule(struct napi_struct *n)
+static inline bool napi_schedule(struct napi_struct *n)
 {
-	if (napi_schedule_prep(n))
+	if (napi_schedule_prep(n)) {
 		__napi_schedule(n);
+		return true;
+	}
+
+	return false;
 }
 
 /**
@@ -503,16 +575,6 @@ static inline void napi_schedule_irqoff(struct napi_struct *n)
 		__napi_schedule_irqoff(n);
 }
 
-/* Try to reschedule poll. Called by dev->poll() after napi_complete().  */
-static inline bool napi_reschedule(struct napi_struct *napi)
-{
-	if (napi_schedule_prep(napi)) {
-		__napi_schedule(napi);
-		return true;
-	}
-	return false;
-}
-
 /**
  * napi_complete_done - NAPI processing complete
  * @n: NAPI context
@@ -521,7 +583,7 @@ static inline bool napi_reschedule(struct napi_struct *napi)
  * Mark NAPI processing as complete. Should only be called if poll budget
  * has not been completely consumed.
  * Prefer over napi_complete().
- * Return false if device should avoid rearming interrupts.
+ * Return: false if device should avoid rearming interrupts.
  */
 bool napi_complete_done(struct napi_struct *n, int work_done);
 
@@ -530,18 +592,15 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
-int dev_set_threaded(struct net_device *dev, bool threaded);
+void netif_threaded_enable(struct net_device *dev);
+int dev_set_threaded(struct net_device *dev,
+		     enum netdev_napi_threaded threaded);
 
-/**
- *	napi_disable - prevent NAPI from scheduling
- *	@n: NAPI context
- *
- * Stop NAPI from being scheduled on this context.
- * Waits till any outstanding processing completes.
- */
 void napi_disable(struct napi_struct *n);
+void napi_disable_locked(struct napi_struct *n);
 
 void napi_enable(struct napi_struct *n);
+void napi_enable_locked(struct napi_struct *n);
 
 /**
  *	napi_synchronize - wait until NAPI is not running
@@ -620,12 +679,10 @@ struct netdev_queue {
 	netdevice_tracker	dev_tracker;
 
 	struct Qdisc __rcu	*qdisc;
-	struct Qdisc		*qdisc_sleeping;
+	struct Qdisc __rcu	*qdisc_sleeping;
 #ifdef CONFIG_SYSFS
 	struct kobject		kobj;
-#endif
-#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
-	int			numa_node;
+	const struct attribute_group	**groups;
 #endif
 	unsigned long		tx_maxrate;
 	/*
@@ -637,11 +694,16 @@ struct netdev_queue {
 	/* Subordinate device that the queue has been assigned to */
 	struct net_device	*sb_dev;
 #ifdef CONFIG_XDP_SOCKETS
+	/* "ops protected", see comment about net_device::lock */
 	struct xsk_buff_pool    *pool;
 #endif
+
 /*
  * write-mostly part
  */
+#ifdef CONFIG_BQL
+	struct dql		dql;
+#endif
 	spinlock_t		_xmit_lock ____cacheline_aligned_in_smp;
 	int			xmit_lock_owner;
 	/*
@@ -651,8 +713,16 @@ struct netdev_queue {
 
 	unsigned long		state;
 
-#ifdef CONFIG_BQL
-	struct dql		dql;
+/*
+ * slow- / control-path part
+ */
+	/* NAPI instance for the queue
+	 * "ops protected", see comment about net_device::lock
+	 */
+	struct napi_struct	*napi;
+
+#if defined(CONFIG_XPS) && defined(CONFIG_NUMA)
+	int			numa_node;
 #endif
 } ____cacheline_aligned_in_smp;
 
@@ -701,109 +771,10 @@ static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node
 #endif
 }
 
-#ifdef CONFIG_RPS
-/*
- * This structure holds an RPS map which can be of variable length.  The
- * map is an array of CPUs.
- */
-struct rps_map {
-	unsigned int len;
-	struct rcu_head rcu;
-	u16 cpus[];
-};
-#define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + ((_num) * sizeof(u16)))
-
-/*
- * The rps_dev_flow structure contains the mapping of a flow to a CPU, the
- * tail pointer for that CPU's input queue at the time of last enqueue, and
- * a hardware filter index.
- */
-struct rps_dev_flow {
-	u16 cpu;
-	u16 filter;
-	unsigned int last_qtail;
-};
-#define RPS_NO_FILTER 0xffff
-
-/*
- * The rps_dev_flow_table structure contains a table of flow mappings.
- */
-struct rps_dev_flow_table {
-	unsigned int mask;
-	struct rcu_head rcu;
-	struct rps_dev_flow flows[];
-};
-#define RPS_DEV_FLOW_TABLE_SIZE(_num) (sizeof(struct rps_dev_flow_table) + \
-    ((_num) * sizeof(struct rps_dev_flow)))
-
-/*
- * The rps_sock_flow_table contains mappings of flows to the last CPU
- * on which they were processed by the application (set in recvmsg).
- * Each entry is a 32bit value. Upper part is the high-order bits
- * of flow hash, lower part is CPU number.
- * rps_cpu_mask is used to partition the space, depending on number of
- * possible CPUs : rps_cpu_mask = roundup_pow_of_two(nr_cpu_ids) - 1
- * For example, if 64 CPUs are possible, rps_cpu_mask = 0x3f,
- * meaning we use 32-6=26 bits for the hash.
- */
-struct rps_sock_flow_table {
-	u32	mask;
-
-	u32	ents[] ____cacheline_aligned_in_smp;
-};
-#define	RPS_SOCK_FLOW_TABLE_SIZE(_num) (offsetof(struct rps_sock_flow_table, ents[_num]))
-
-#define RPS_NO_CPU 0xffff
-
-extern u32 rps_cpu_mask;
-extern struct rps_sock_flow_table __rcu *rps_sock_flow_table;
-
-static inline void rps_record_sock_flow(struct rps_sock_flow_table *table,
-					u32 hash)
-{
-	if (table && hash) {
-		unsigned int index = hash & table->mask;
-		u32 val = hash & ~rps_cpu_mask;
-
-		/* We only give a hint, preemption can change CPU under us */
-		val |= raw_smp_processor_id();
-
-		if (table->ents[index] != val)
-			table->ents[index] = val;
-	}
-}
-
 #ifdef CONFIG_RFS_ACCEL
 bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id,
 			 u16 filter_id);
 #endif
-#endif /* CONFIG_RPS */
-
-/* This structure contains an instance of an RX queue. */
-struct netdev_rx_queue {
-	struct xdp_rxq_info		xdp_rxq;
-#ifdef CONFIG_RPS
-	struct rps_map __rcu		*rps_map;
-	struct rps_dev_flow_table __rcu	*rps_flow_table;
-#endif
-	struct kobject			kobj;
-	struct net_device		*dev;
-	netdevice_tracker		dev_tracker;
-
-#ifdef CONFIG_XDP_SOCKETS
-	struct xsk_buff_pool            *pool;
-#endif
-} ____cacheline_aligned_in_smp;
-
-/*
- * RX queue sysfs structures and functions.
- */
-struct rx_queue_attribute {
-	struct attribute attr;
-	ssize_t (*show)(struct netdev_rx_queue *queue, char *buf);
-	ssize_t (*store)(struct netdev_rx_queue *queue,
-			 const char *buf, size_t len);
-};
 
 /* XPS map type and offset of the xps map within net_device->xps_maps[]. */
 enum xps_map_type {
@@ -906,6 +877,7 @@ enum net_device_path_type {
 	DEV_PATH_PPPOE,
 	DEV_PATH_DSA,
 	DEV_PATH_MTK_WDMA,
+	DEV_PATH_TUN,
 };
 
 struct net_device_path {
@@ -918,6 +890,18 @@ struct net_device_path {
 			u8		h_dest[ETH_ALEN];
 		} encap;
 		struct {
+			union {
+				struct in_addr	src_v4;
+				struct in6_addr	src_v6;
+			};
+			union {
+				struct in_addr	dst_v4;
+				struct in6_addr	dst_v6;
+			};
+
+			u8	l3_proto;
+		} tun;
+		struct {
 			enum {
 				DEV_PATH_BR_VLAN_KEEP,
 				DEV_PATH_BR_VLAN_TAG,
@@ -936,6 +920,7 @@ struct net_device_path {
 			u8 queue;
 			u16 wcid;
 			u8 bss;
+			u8 amsdu;
 		} mtk_wdma;
 	};
 };
@@ -1047,13 +1032,17 @@ struct netdev_bpf {
 
 #ifdef CONFIG_XFRM_OFFLOAD
 struct xfrmdev_ops {
-	int	(*xdo_dev_state_add) (struct xfrm_state *x, struct netlink_ext_ack *extack);
-	void	(*xdo_dev_state_delete) (struct xfrm_state *x);
-	void	(*xdo_dev_state_free) (struct xfrm_state *x);
+	int	(*xdo_dev_state_add)(struct net_device *dev,
+				     struct xfrm_state *x,
+				     struct netlink_ext_ack *extack);
+	void	(*xdo_dev_state_delete)(struct net_device *dev,
+					struct xfrm_state *x);
+	void	(*xdo_dev_state_free)(struct net_device *dev,
+				      struct xfrm_state *x);
 	bool	(*xdo_dev_offload_ok) (struct sk_buff *skb,
 				       struct xfrm_state *x);
 	void	(*xdo_dev_state_advance_esn) (struct xfrm_state *x);
-	void	(*xdo_dev_state_update_curlft) (struct xfrm_state *x);
+	void	(*xdo_dev_state_update_stats) (struct xfrm_state *x);
 	int	(*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack);
 	void	(*xdo_dev_policy_delete) (struct xfrm_policy *x);
 	void	(*xdo_dev_policy_free) (struct xfrm_policy *x);
@@ -1139,8 +1128,8 @@ struct netdev_net_notifier {
  *
  * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd);
  *	Old-style ioctl entry point. This is used internally by the
- *	appletalk and ieee802154 subsystems but is no longer called by
- *	the device ioctl handler.
+ *	ieee802154 subsystem but is no longer called by the device
+ *	ioctl handler.
  *
  * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd);
  *	Used by the bonding driver for its device specific ioctls:
@@ -1300,15 +1289,18 @@ struct netdev_net_notifier {
  * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[],
  *		      struct net_device *dev,
  *		      const unsigned char *addr, u16 vid, u16 flags,
- *		      struct netlink_ext_ack *extack);
+ *		      bool *notified, struct netlink_ext_ack *extack);
  *	Adds an FDB entry to dev for addr.
+ *	Callee shall set *notified to true if it sent any appropriate
+ *	notification(s). Otherwise core will send a generic one.
  * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[],
  *		      struct net_device *dev,
- *		      const unsigned char *addr, u16 vid)
- *	Deletes the FDB entry from dev coresponding to addr.
- * int (*ndo_fdb_del_bulk)(struct ndmsg *ndm, struct nlattr *tb[],
- *			   struct net_device *dev,
- *			   u16 vid,
+ *		      const unsigned char *addr, u16 vid
+ *		      bool *notified, struct netlink_ext_ack *extack);
+ *	Deletes the FDB entry from dev corresponding to addr.
+ *	Callee shall set *notified to true if it sent any appropriate
+ *	notification(s). Otherwise core will send a generic one.
+ * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev,
  *			   struct netlink_ext_ack *extack);
  * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb,
  *		       struct net_device *dev, struct net_device *filter_dev,
@@ -1322,6 +1314,9 @@ struct netdev_net_notifier {
  * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[],
  *		      struct netlink_ext_ack *extack);
  *	Deletes the MDB entry from dev.
+ * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[],
+ *			   struct netlink_ext_ack *extack);
+ *	Bulk deletes MDB entries from dev.
  * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb,
  *		       struct netlink_callback *cb);
  *	Dumps MDB entries from dev. The first argument (marker) in the netlink
@@ -1401,7 +1396,7 @@ struct netdev_net_notifier {
  *	queue id bound to an AF_XDP socket. The flags field specifies if
  *	only RX, only Tx, or both should be woken up using the flags
  *	XDP_WAKEUP_RX and XDP_WAKEUP_TX.
- * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
+ * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p,
  *			 int cmd);
  *	Add, change, delete or get information on an IPv4 tunnel.
  * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
@@ -1415,6 +1410,16 @@ struct netdev_net_notifier {
  *	Get hardware timestamp based on normal/adjustable time or free running
  *	cycle counter. This function is required if physical clock supports a
  *	free running cycle counter.
+ *
+ * int (*ndo_hwtstamp_get)(struct net_device *dev,
+ *			   struct kernel_hwtstamp_config *kernel_config);
+ *	Get the currently configured hardware timestamping parameters for the
+ *	NIC device.
+ *
+ * int (*ndo_hwtstamp_set)(struct net_device *dev,
+ *			   struct kernel_hwtstamp_config *kernel_config,
+ *			   struct netlink_ext_ack *extack);
+ *	Change the hardware timestamping parameters for NIC device.
  */
 struct net_device_ops {
 	int			(*ndo_init)(struct net_device *dev);
@@ -1469,8 +1474,7 @@ struct net_device_ops {
 						        __be16 proto, u16 vid);
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	void                    (*ndo_poll_controller)(struct net_device *dev);
-	int			(*ndo_netpoll_setup)(struct net_device *dev,
-						     struct netpoll_info *info);
+	int			(*ndo_netpoll_setup)(struct net_device *dev);
 	void			(*ndo_netpoll_cleanup)(struct net_device *dev);
 #endif
 	int			(*ndo_set_vf_mac)(struct net_device *dev,
@@ -1567,16 +1571,17 @@ struct net_device_ops {
 					       const unsigned char *addr,
 					       u16 vid,
 					       u16 flags,
+					       bool *notified,
 					       struct netlink_ext_ack *extack);
 	int			(*ndo_fdb_del)(struct ndmsg *ndm,
 					       struct nlattr *tb[],
 					       struct net_device *dev,
 					       const unsigned char *addr,
-					       u16 vid, struct netlink_ext_ack *extack);
-	int			(*ndo_fdb_del_bulk)(struct ndmsg *ndm,
-						    struct nlattr *tb[],
+					       u16 vid,
+					       bool *notified,
+					       struct netlink_ext_ack *extack);
+	int			(*ndo_fdb_del_bulk)(struct nlmsghdr *nlh,
 						    struct net_device *dev,
-						    u16 vid,
 						    struct netlink_ext_ack *extack);
 	int			(*ndo_fdb_dump)(struct sk_buff *skb,
 						struct netlink_callback *cb,
@@ -1596,9 +1601,16 @@ struct net_device_ops {
 	int			(*ndo_mdb_del)(struct net_device *dev,
 					       struct nlattr *tb[],
 					       struct netlink_ext_ack *extack);
+	int			(*ndo_mdb_del_bulk)(struct net_device *dev,
+						    struct nlattr *tb[],
+						    struct netlink_ext_ack *extack);
 	int			(*ndo_mdb_dump)(struct net_device *dev,
 						struct sk_buff *skb,
 						struct netlink_callback *cb);
+	int			(*ndo_mdb_get)(struct net_device *dev,
+					       struct nlattr *tb[], u32 portid,
+					       u32 seq,
+					       struct netlink_ext_ack *extack);
 	int			(*ndo_bridge_setlink)(struct net_device *dev,
 						      struct nlmsghdr *nlh,
 						      u16 flags,
@@ -1642,19 +1654,27 @@ struct net_device_ops {
 	int			(*ndo_xsk_wakeup)(struct net_device *dev,
 						  u32 queue_id, u32 flags);
 	int			(*ndo_tunnel_ctl)(struct net_device *dev,
-						  struct ip_tunnel_parm *p, int cmd);
+						  struct ip_tunnel_parm_kern *p,
+						  int cmd);
 	struct net_device *	(*ndo_get_peer_dev)(struct net_device *dev);
 	int                     (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
                                                          struct net_device_path *path);
 	ktime_t			(*ndo_get_tstamp)(struct net_device *dev,
 						  const struct skb_shared_hwtstamps *hwtstamps,
 						  bool cycles);
-};
+	int			(*ndo_hwtstamp_get)(struct net_device *dev,
+						    struct kernel_hwtstamp_config *kernel_config);
+	int			(*ndo_hwtstamp_set)(struct net_device *dev,
+						    struct kernel_hwtstamp_config *kernel_config,
+						    struct netlink_ext_ack *extack);
 
-struct xdp_metadata_ops {
-	int	(*xmo_rx_timestamp)(const struct xdp_md *ctx, u64 *timestamp);
-	int	(*xmo_rx_hash)(const struct xdp_md *ctx, u32 *hash,
-			       enum xdp_rss_hash_type *rss_type);
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	/**
+	 * @net_shaper_ops: Device shaping offload operations
+	 * see include/net/net_shapers.h
+	 */
+	const struct net_shaper_ops *net_shaper_ops;
+#endif
 };
 
 /**
@@ -1665,7 +1685,8 @@ struct xdp_metadata_ops {
  * userspace; this means that the order of these flags can change
  * during any kernel release.
  *
- * You should have a pretty good reason to be extending these flags.
+ * You should add bitfield booleans after either net_device::priv_flags
+ * (hotpath) or ::threaded (slowpath) instead of extending these flags.
  *
  * @IFF_802_1Q_VLAN: 802.1Q VLAN device
  * @IFF_EBRIDGE: Ethernet bridging device
@@ -1704,7 +1725,6 @@ struct xdp_metadata_ops {
  * @IFF_NO_ADDRCONF: prevent ipv6 addrconf
  * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with
  *	skb_headlen(skb) == 0 (data starts from frag0)
- * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN
  */
 enum netdev_priv_flags {
 	IFF_802_1Q_VLAN			= 1<<0,
@@ -1739,47 +1759,30 @@ enum netdev_priv_flags {
 	IFF_L3MDEV_RX_HANDLER		= 1<<29,
 	IFF_NO_ADDRCONF			= BIT_ULL(30),
 	IFF_TX_SKB_NO_LINEAR		= BIT_ULL(31),
-	IFF_CHANGE_PROTO_DOWN		= BIT_ULL(32),
 };
 
-#define IFF_802_1Q_VLAN			IFF_802_1Q_VLAN
-#define IFF_EBRIDGE			IFF_EBRIDGE
-#define IFF_BONDING			IFF_BONDING
-#define IFF_ISATAP			IFF_ISATAP
-#define IFF_WAN_HDLC			IFF_WAN_HDLC
-#define IFF_XMIT_DST_RELEASE		IFF_XMIT_DST_RELEASE
-#define IFF_DONT_BRIDGE			IFF_DONT_BRIDGE
-#define IFF_DISABLE_NETPOLL		IFF_DISABLE_NETPOLL
-#define IFF_MACVLAN_PORT		IFF_MACVLAN_PORT
-#define IFF_BRIDGE_PORT			IFF_BRIDGE_PORT
-#define IFF_OVS_DATAPATH		IFF_OVS_DATAPATH
-#define IFF_TX_SKB_SHARING		IFF_TX_SKB_SHARING
-#define IFF_UNICAST_FLT			IFF_UNICAST_FLT
-#define IFF_TEAM_PORT			IFF_TEAM_PORT
-#define IFF_SUPP_NOFCS			IFF_SUPP_NOFCS
-#define IFF_LIVE_ADDR_CHANGE		IFF_LIVE_ADDR_CHANGE
-#define IFF_MACVLAN			IFF_MACVLAN
-#define IFF_XMIT_DST_RELEASE_PERM	IFF_XMIT_DST_RELEASE_PERM
-#define IFF_L3MDEV_MASTER		IFF_L3MDEV_MASTER
-#define IFF_NO_QUEUE			IFF_NO_QUEUE
-#define IFF_OPENVSWITCH			IFF_OPENVSWITCH
-#define IFF_L3MDEV_SLAVE		IFF_L3MDEV_SLAVE
-#define IFF_TEAM			IFF_TEAM
-#define IFF_RXFH_CONFIGURED		IFF_RXFH_CONFIGURED
-#define IFF_PHONY_HEADROOM		IFF_PHONY_HEADROOM
-#define IFF_MACSEC			IFF_MACSEC
-#define IFF_NO_RX_HANDLER		IFF_NO_RX_HANDLER
-#define IFF_FAILOVER			IFF_FAILOVER
-#define IFF_FAILOVER_SLAVE		IFF_FAILOVER_SLAVE
-#define IFF_L3MDEV_RX_HANDLER		IFF_L3MDEV_RX_HANDLER
-#define IFF_TX_SKB_NO_LINEAR		IFF_TX_SKB_NO_LINEAR
-
 /* Specifies the type of the struct net_device::ml_priv pointer */
 enum netdev_ml_priv_type {
 	ML_PRIV_NONE,
 	ML_PRIV_CAN,
 };
 
+enum netdev_stat_type {
+	NETDEV_PCPU_STAT_NONE,
+	NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */
+	NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */
+	NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */
+};
+
+enum netdev_reg_state {
+	NETREG_UNINITIALIZED = 0,
+	NETREG_REGISTERED,	/* completed register_netdevice */
+	NETREG_UNREGISTERING,	/* called unregister_netdevice */
+	NETREG_UNREGISTERED,	/* completed unregister todo */
+	NETREG_RELEASED,	/* called free_netdev */
+	NETREG_DUMMY,		/* dummy device for NAPI poll */
+};
+
 /**
  *	struct net_device - The DEVICE structure.
  *
@@ -1787,6 +1790,13 @@ enum netdev_ml_priv_type {
  *	data with strictly "high-level" data, and it has to know about
  *	almost every data structure used in the INET module.
  *
+ *	@priv_flags:	flags invisible to userspace defined as bits, see
+ *			enum netdev_priv_flags for the definitions
+ *	@lltx:		device supports lockless Tx. Deprecated for real HW
+ *			drivers. Mainly used by logical interfaces, such as
+ *			bonding and tunnels
+ *	@netmem_tx:	device support netmem_tx.
+ *
  *	@name:	This is the first field of the "visible" part of this structure
  *		(i.e. as seen by users in the "Space.c" file).  It is the name
  *		of the interface.
@@ -1836,11 +1846,11 @@ enum netdev_ml_priv_type {
  *	@wireless_handlers:	List of functions to handle Wireless Extensions,
  *				instead of ioctl,
  *				see <net/iw_handler.h> for details.
- *	@wireless_data:	Instance data managed by the core of wireless extensions
  *
  *	@netdev_ops:	Includes several pointers to callbacks,
  *			if one wants to override the ndo_*() functions
  *	@xdp_metadata_ops:	Includes pointers to XDP metadata callbacks.
+ *	@xsk_tx_metadata_ops:	Includes pointers to AF_XDP TX metadata callbacks.
  *	@ethtool_ops:	Management operations
  *	@l3mdev_ops:	Layer 3 master device operations
  *	@ndisc_ops:	Includes callbacks for different IPv6 neighbour
@@ -1852,10 +1862,9 @@ enum netdev_ml_priv_type {
  *
  *	@flags:		Interface flags (a la BSD)
  *	@xdp_features:	XDP capability supported by the device
- *	@priv_flags:	Like 'flags' but invisible to userspace,
- *			see if.h for the definitions
  *	@gflags:	Global flags ( kept as legacy )
- *	@padded:	How much padding added by alloc_netdev()
+ *	@priv_len:	Size of the ->priv flexible array
+ *	@priv:		Flexible array containing private data
  *	@operstate:	RFC2863 operstate
  *	@link_mode:	Mapping policy to operstate
  *	@if_port:	Selectable AUI, TP, ...
@@ -1880,6 +1889,7 @@ enum netdev_ml_priv_type {
  * 	@addr_len:		Hardware address length
  *	@upper_level:		Maximum depth level of upper devices.
  *	@lower_level:		Maximum depth level of lower devices.
+ *	@threaded:		napi threaded state.
  *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
@@ -1912,6 +1922,7 @@ enum netdev_ml_priv_type {
  *			 device struct
  *	@mpls_ptr:	mpls_dev struct pointer
  *	@mctp_ptr:	MCTP specific data
+ *	@psp_dev:	PSP crypto device registered for this netdev
  *
  *	@dev_addr:	Hw address (before bcast,
  *			because most packets are unicast)
@@ -1921,14 +1932,10 @@ enum netdev_ml_priv_type {
  *				allocated at register_netdev() time
  *	@real_num_rx_queues: 	Number of RX queues currently active in device
  *	@xdp_prog:		XDP sockets filter program pointer
- *	@gro_flush_timeout:	timeout for GRO layer in NAPI
- *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
- *				allow to avoid NIC hard IRQ, on busy queues.
  *
  *	@rx_handler:		handler for received packets
  *	@rx_handler_data: 	XXX: need comments on this one
- *	@miniq_ingress:		ingress/clsact qdisc specific data for
- *				ingress processing
+ *	@tcx_ingress:		BPF & clsact qdisc specific data for ingress processing
  *	@ingress_queue:		XXX: need comments on this one
  *	@nf_hooks_ingress:	netfilter hooks executed for ingress packets
  *	@broadcast:		hw bcast address
@@ -1949,8 +1956,7 @@ enum netdev_ml_priv_type {
  *	@xps_maps:		all CPUs/RXQs maps for XPS device
  *
  *	@xps_maps:	XXX: need comments on this one
- *	@miniq_egress:		clsact qdisc specific data for
- *				egress processing
+ *	@tcx_egress:		BPF & clsact qdisc specific data for egress processing
  *	@nf_hooks_egress:	netfilter hooks executed for egress packets
  *	@qdisc_hash:		qdisc hash table
  *	@watchdog_timeo:	Represents the timeout that is used by
@@ -1966,20 +1972,22 @@ enum netdev_ml_priv_type {
  *
  *	@reg_state:		Register/unregister state machine
  *	@dismantle:		Device is going to be freed
- *	@rtnl_link_state:	This enum represents the phases of creating
- *				a new link
- *
  *	@needs_free_netdev:	Should unregister perform free_netdev?
  *	@priv_destructor:	Called from unregister
  *	@npinfo:		XXX: need comments on this one
  * 	@nd_net:		Network namespace this network device is inside
+ *				protected by @lock
  *
  * 	@ml_priv:	Mid-layer private
  *	@ml_priv_type:  Mid-layer private type
- * 	@lstats:	Loopback statistics
- * 	@tstats:	Tunnel statistics
- * 	@dstats:	Dummy statistics
- * 	@vstats:	Virtual ethernet statistics
+ *
+ *	@pcpu_stat_type:	Type of device statistics which the core should
+ *				allocate/free: none, lstats, tstats, dstats. none
+ *				means the driver is handling statistics allocation/
+ *				freeing internally.
+ *	@lstats:		Loopback statistics: packets, bytes
+ *	@tstats:		Tunnel statistics: RX/TX packets, RX/TX bytes
+ *	@dstats:		Dummy statistics: RX/TX/drop packets, RX/TX bytes
  *
  *	@garp_port:	GARP
  *	@mrp_port:	MRP
@@ -1992,6 +2000,8 @@ enum netdev_ml_priv_type {
  *
  *	@sysfs_rx_queue_group:	Space for optional per-rx queue attributes
  *	@rtnl_link_ops:	Rtnl_link_ops
+ *	@stat_ops:	Optional ops for queue-aware statistics
+ *	@queue_mgmt_ops:	Optional ops for queue management
  *
  *	@gso_max_size:	Maximum size of generic segmentation offload
  *	@tso_max_size:	Device (as in HW) limit on the max TSO request size
@@ -2009,6 +2019,7 @@ enum netdev_ml_priv_type {
  *	@fcoe_ddp_xid:	Max exchange id for FCoE LRO by ddp
  *
  *	@priomap:	XXX: need comments on this one
+ *	@link_topo:	Physical link topology tracking attached PHYs
  *	@phydev:	Physical device may attach itself
  *			for hardware timestamping
  *	@sfp_bus:	attached &struct sfp_bus structure.
@@ -2019,9 +2030,22 @@ enum netdev_ml_priv_type {
  *			switch driver and used to set the phys state of the
  *			switch port.
  *
- *	@wol_enabled:	Wake-on-LAN is enabled
+ *	@irq_affinity_auto: driver wants the core to store and re-assign the IRQ
+ *			    affinity. Set by netif_enable_irq_affinity(), then
+ *			    the driver must create a persistent napi by
+ *			    netif_napi_add_config() and finally bind the napi to
+ *			    IRQ (via netif_napi_set_irq()).
  *
- *	@threaded:	napi threaded mode is enabled
+ *	@rx_cpu_rmap_auto: driver wants the core to manage the ARFS rmap.
+ *	                   Set by calling netif_enable_cpu_rmap().
+ *
+ *	@see_all_hwtstamp_requests: device wants to see calls to
+ *			ndo_hwtstamp_set() for all timestamp requests
+ *			regardless of source, even if those aren't
+ *			HWTSTAMP_SOURCE_NETDEV
+ *	@change_proto_down: device supports setting carrier via IFLA_PROTO_DOWN
+ *	@netns_immutable: interface can't change network namespaces
+ *	@fcoe_mtu:	device supports maximum FCoE MTU, 2158 bytes
  *
  *	@net_notifier_list:	List of per-net netdev notifier block
  *				that follow this device when it is moved
@@ -2032,6 +2056,7 @@ enum netdev_ml_priv_type {
  *	@udp_tunnel_nic_info:	static structure describing the UDP tunnel
  *				offload capabilities of the device
  *	@udp_tunnel_nic:	UDP tunnel offload state
+ *	@ethtool:	ethtool related state
  *	@xdp_state:		stores info on attached XDP BPF programs
  *
  *	@nested_level:	Used as a parameter of spin_lock_nested() of
@@ -2042,6 +2067,8 @@ enum netdev_ml_priv_type {
  *			receive offload (GRO)
  * 	@gro_ipv4_max_size:	Maximum size of aggregated packet in generic
  * 				receive offload (GRO), for IPv4.
+ *	@xdp_zc_max_segs:	Maximum number of segments supported by AF_XDP
+ *				zero copy driver
  *
  *	@dev_addr_shadow:	Copy of @dev_addr to catch direct writes.
  *	@linkwatch_dev_tracker:	refcount tracker used by linkwatch.
@@ -2055,11 +2082,101 @@ enum netdev_ml_priv_type {
  *			SET_NETDEV_DEVLINK_PORT macro. This pointer is static
  *			during the time netdevice is registered.
  *
+ *	@dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem,
+ *		   where the clock is recovered.
+ *
+ *	@max_pacing_offload_horizon: max EDT offload horizon in nsec.
+ *	@napi_config: An array of napi_config structures containing per-NAPI
+ *		      settings.
+ *	@num_napi_configs:	number of allocated NAPI config structs,
+ *		always >= max(num_rx_queues, num_tx_queues).
+ *	@gro_flush_timeout:	timeout for GRO layer in NAPI
+ *	@napi_defer_hard_irqs:	If not zero, provides a counter that would
+ *				allow to avoid NIC hard IRQ, on busy queues.
+ *
+ *	@neighbours:	List heads pointing to this device's neighbours'
+ *			dev_list, one per address-family.
+ *	@hwprov: Tracks which PTP performs hardware packet time stamping.
+ *
  *	FIXME: cleanup struct net_device such that network protocol info
  *	moves out.
  */
 
 struct net_device {
+	/* Cacheline organization can be found documented in
+	 * Documentation/networking/net_cachelines/net_device.rst.
+	 * Please update the document when adding new fields.
+	 */
+
+	/* TX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_tx);
+	struct_group(priv_flags_fast,
+		unsigned long		priv_flags:32;
+		unsigned long		lltx:1;
+		unsigned long		netmem_tx:1;
+	);
+	const struct net_device_ops *netdev_ops;
+	const struct header_ops *header_ops;
+	struct netdev_queue	*_tx;
+	netdev_features_t	gso_partial_features;
+	unsigned int		real_num_tx_queues;
+	unsigned int		gso_max_size;
+	unsigned int		gso_ipv4_max_size;
+	u16			gso_max_segs;
+	s16			num_tc;
+	/* Note : dev->mtu is often read without holding a lock.
+	 * Writers usually hold RTNL.
+	 * It is recommended to use READ_ONCE() to annotate the reads,
+	 * and to use WRITE_ONCE() to annotate the writes.
+	 */
+	unsigned int		mtu;
+	unsigned short		needed_headroom;
+	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
+#ifdef CONFIG_XPS
+	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
+#endif
+#ifdef CONFIG_NETFILTER_EGRESS
+	struct nf_hook_entries __rcu *nf_hooks_egress;
+#endif
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_egress;
+#endif
+	__cacheline_group_end(net_device_read_tx);
+
+	/* TXRX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_txrx);
+	union {
+		struct pcpu_lstats __percpu		*lstats;
+		struct pcpu_sw_netstats __percpu	*tstats;
+		struct pcpu_dstats __percpu		*dstats;
+	};
+	unsigned long		state;
+	unsigned int		flags;
+	unsigned short		hard_header_len;
+	netdev_features_t	features;
+	struct inet6_dev __rcu	*ip6_ptr;
+	__cacheline_group_end(net_device_read_txrx);
+
+	/* RX read-mostly hotpath */
+	__cacheline_group_begin(net_device_read_rx);
+	struct bpf_prog __rcu	*xdp_prog;
+	struct list_head	ptype_specific;
+	int			ifindex;
+	unsigned int		real_num_rx_queues;
+	struct netdev_rx_queue	*_rx;
+	unsigned int		gro_max_size;
+	unsigned int		gro_ipv4_max_size;
+	rx_handler_func_t __rcu	*rx_handler;
+	void __rcu		*rx_handler_data;
+	possible_net_t			nd_net;
+#ifdef CONFIG_NETPOLL
+	struct netpoll_info __rcu	*npinfo;
+#endif
+#ifdef CONFIG_NET_XGRESS
+	struct bpf_mprog_entry __rcu *tcx_ingress;
+#endif
+	__cacheline_group_end(net_device_read_rx);
+
 	char			name[IFNAMSIZ];
 	struct netdev_name_node	*name_node;
 	struct dev_ifalias	__rcu *ifalias;
@@ -2077,14 +2194,12 @@ struct net_device {
 	 *	part of the usual set specified in Space.c.
 	 */
 
-	unsigned long		state;
 
 	struct list_head	dev_list;
 	struct list_head	napi_list;
 	struct list_head	unreg_list;
 	struct list_head	close_list;
 	struct list_head	ptype_all;
-	struct list_head	ptype_specific;
 
 	struct {
 		struct list_head upper;
@@ -2092,31 +2207,18 @@ struct net_device {
 	} adj_list;
 
 	/* Read-mostly cache-line for fast-path access */
-	unsigned int		flags;
 	xdp_features_t		xdp_features;
-	unsigned long long	priv_flags;
-	const struct net_device_ops *netdev_ops;
 	const struct xdp_metadata_ops *xdp_metadata_ops;
-	int			ifindex;
+	const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops;
 	unsigned short		gflags;
-	unsigned short		hard_header_len;
 
-	/* Note : dev->mtu is often read without holding a lock.
-	 * Writers usually hold RTNL.
-	 * It is recommended to use READ_ONCE() to annotate the reads,
-	 * and to use WRITE_ONCE() to annotate the writes.
-	 */
-	unsigned int		mtu;
-	unsigned short		needed_headroom;
 	unsigned short		needed_tailroom;
 
-	netdev_features_t	features;
 	netdev_features_t	hw_features;
 	netdev_features_t	wanted_features;
 	netdev_features_t	vlan_features;
 	netdev_features_t	hw_enc_features;
 	netdev_features_t	mpls_features;
-	netdev_features_t	gso_partial_features;
 
 	unsigned int		min_mtu;
 	unsigned int		max_mtu;
@@ -2136,7 +2238,6 @@ struct net_device {
 
 #ifdef CONFIG_WIRELESS_EXT
 	const struct iw_handler_def *wireless_handlers;
-	struct iw_public_data	*wireless_data;
 #endif
 	const struct ethtool_ops *ethtool_ops;
 #ifdef CONFIG_NET_L3_MASTER_DEV
@@ -2154,9 +2255,7 @@ struct net_device {
 	const struct tlsdev_ops *tlsdev_ops;
 #endif
 
-	const struct header_ops *header_ops;
-
-	unsigned char		operstate;
+	unsigned int		operstate;
 	unsigned char		link_mode;
 
 	unsigned char		if_port;
@@ -2168,14 +2267,15 @@ struct net_device {
 	unsigned char		addr_len;
 	unsigned char		upper_level;
 	unsigned char		lower_level;
+	u8			threaded;
 
 	unsigned short		neigh_priv_len;
 	unsigned short          dev_id;
 	unsigned short          dev_port;
-	unsigned short		padded;
+	int			irq;
+	u32			priv_len;
 
 	spinlock_t		addr_list_lock;
-	int			irq;
 
 	struct netdev_hw_addr_list	uc;
 	struct netdev_hw_addr_list	mc;
@@ -2196,9 +2296,10 @@ struct net_device {
 
 
 	/* Protocol-specific pointers */
-
 	struct in_device __rcu	*ip_ptr;
-	struct inet6_dev __rcu	*ip6_ptr;
+	/** @fib_nh_head: nexthops associated with this netdev */
+	struct hlist_head	fib_nh_head;
+
 #if IS_ENABLED(CONFIG_VLAN_8021Q)
 	struct vlan_info __rcu	*vlan_info;
 #endif
@@ -2212,7 +2313,7 @@ struct net_device {
 	void 			*atalk_ptr;
 #endif
 #if IS_ENABLED(CONFIG_AX25)
-	void			*ax25_ptr;
+	struct ax25_dev	__rcu	*ax25_ptr;
 #endif
 #if IS_ENABLED(CONFIG_CFG80211)
 	struct wireless_dev	*ieee80211_ptr;
@@ -2226,6 +2327,9 @@ struct net_device {
 #if IS_ENABLED(CONFIG_MCTP)
 	struct mctp_dev __rcu	*mctp_ptr;
 #endif
+#if IS_ENABLED(CONFIG_INET_PSP)
+	struct psp_dev __rcu	*psp_dev;
+#endif
 
 /*
  * Cache lines mostly used on receive path (including eth_type_trans())
@@ -2233,26 +2337,13 @@ struct net_device {
 	/* Interface address info used in eth_type_trans() */
 	const unsigned char	*dev_addr;
 
-	struct netdev_rx_queue	*_rx;
 	unsigned int		num_rx_queues;
-	unsigned int		real_num_rx_queues;
-
-	struct bpf_prog __rcu	*xdp_prog;
-	unsigned long		gro_flush_timeout;
-	int			napi_defer_hard_irqs;
 #define GRO_LEGACY_MAX_SIZE	65536u
 /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE),
  * and shinfo->gso_segs is a 16bit field.
  */
 #define GRO_MAX_SIZE		(8 * 65535u)
-	unsigned int		gro_max_size;
-	unsigned int		gro_ipv4_max_size;
-	rx_handler_func_t __rcu	*rx_handler;
-	void __rcu		*rx_handler_data;
-
-#ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc __rcu	*miniq_ingress;
-#endif
+	unsigned int		xdp_zc_max_segs;
 	struct netdev_queue __rcu *ingress_queue;
 #ifdef CONFIG_NETFILTER_INGRESS
 	struct nf_hook_entries __rcu *nf_hooks_ingress;
@@ -2267,25 +2358,13 @@ struct net_device {
 /*
  * Cache lines mostly used on transmit path
  */
-	struct netdev_queue	*_tx ____cacheline_aligned_in_smp;
 	unsigned int		num_tx_queues;
-	unsigned int		real_num_tx_queues;
 	struct Qdisc __rcu	*qdisc;
 	unsigned int		tx_queue_len;
 	spinlock_t		tx_global_lock;
 
 	struct xdp_dev_bulk_queue __percpu *xdp_bulkq;
 
-#ifdef CONFIG_XPS
-	struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX];
-#endif
-#ifdef CONFIG_NET_CLS_ACT
-	struct mini_Qdisc __rcu	*miniq_egress;
-#endif
-#ifdef CONFIG_NETFILTER_EGRESS
-	struct nf_hook_entries __rcu *nf_hooks_egress;
-#endif
-
 #ifdef CONFIG_NET_SCHED
 	DECLARE_HASHTABLE	(qdisc_hash, 4);
 #endif
@@ -2306,39 +2385,23 @@ struct net_device {
 
 	struct list_head	link_watch_list;
 
-	enum { NETREG_UNINITIALIZED=0,
-	       NETREG_REGISTERED,	/* completed register_netdevice */
-	       NETREG_UNREGISTERING,	/* called unregister_netdevice */
-	       NETREG_UNREGISTERED,	/* completed unregister todo */
-	       NETREG_RELEASED,		/* called free_netdev */
-	       NETREG_DUMMY,		/* dummy device for NAPI poll */
-	} reg_state:8;
+	u8 reg_state;
 
 	bool dismantle;
 
-	enum {
-		RTNL_LINK_INITIALIZED,
-		RTNL_LINK_INITIALIZING,
-	} rtnl_link_state:16;
+	/** @moving_ns: device is changing netns, protected by @lock */
+	bool moving_ns;
+	/** @rtnl_link_initializing: Device being created, suppress events */
+	bool rtnl_link_initializing;
 
 	bool needs_free_netdev;
 	void (*priv_destructor)(struct net_device *dev);
 
-#ifdef CONFIG_NETPOLL
-	struct netpoll_info __rcu	*npinfo;
-#endif
-
-	possible_net_t			nd_net;
-
 	/* mid-layer private */
 	void				*ml_priv;
 	enum netdev_ml_priv_type	ml_priv_type;
 
-	union {
-		struct pcpu_lstats __percpu		*lstats;
-		struct pcpu_sw_netstats __percpu	*tstats;
-		struct pcpu_dstats __percpu		*dstats;
-	};
+	enum netdev_stat_type		pcpu_stat_type:8;
 
 #if IS_ENABLED(CONFIG_GARP)
 	struct garp_port __rcu	*garp_port;
@@ -2350,11 +2413,15 @@ struct net_device {
 	struct dm_hw_stat_delta __rcu *dm_private;
 #endif
 	struct device		dev;
-	const struct attribute_group *sysfs_groups[4];
+	const struct attribute_group *sysfs_groups[5];
 	const struct attribute_group *sysfs_rx_queue_group;
 
 	const struct rtnl_link_ops *rtnl_link_ops;
 
+	const struct netdev_stat_ops *stat_ops;
+
+	const struct netdev_queue_mgmt_ops *queue_mgmt_ops;
+
 	/* for setting kernel sock attribute on TCP connection setup */
 #define GSO_MAX_SEGS		65535u
 #define GSO_LEGACY_MAX_SIZE	65536u
@@ -2363,20 +2430,15 @@ struct net_device {
  */
 #define GSO_MAX_SIZE		(8 * GSO_MAX_SEGS)
 
-	unsigned int		gso_max_size;
 #define TSO_LEGACY_MAX_SIZE	65536
 #define TSO_MAX_SIZE		UINT_MAX
 	unsigned int		tso_max_size;
-	u16			gso_max_segs;
 #define TSO_MAX_SEGS		U16_MAX
 	u16			tso_max_segs;
-	unsigned int		gso_ipv4_max_size;
 
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
-	s16			num_tc;
-	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
 	u8			prio_tc_map[TC_BITMASK + 1];
 
 #if IS_ENABLED(CONFIG_FCOE)
@@ -2385,12 +2447,19 @@ struct net_device {
 #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO)
 	struct netprio_map __rcu *priomap;
 #endif
+	struct phy_link_topology	*link_topo;
 	struct phy_device	*phydev;
 	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
 	bool			proto_down;
-	unsigned		wol_enabled:1;
-	unsigned		threaded:1;
+	bool			irq_affinity_auto;
+	bool			rx_cpu_rmap_auto;
+
+	/* priv_flags_slow, ungrouped to save space */
+	unsigned long		see_all_hwtstamp_requests:1;
+	unsigned long		change_proto_down:1;
+	unsigned long		netns_immutable:1;
+	unsigned long		fcoe_mtu:1;
 
 	struct list_head	net_notifier_list;
 
@@ -2401,6 +2470,16 @@ struct net_device {
 	const struct udp_tunnel_nic_info	*udp_tunnel_nic_info;
 	struct udp_tunnel_nic	*udp_tunnel_nic;
 
+	/** @cfg: net_device queue-related configuration */
+	struct netdev_config	*cfg;
+	/**
+	 * @cfg_pending: same as @cfg but when device is being actively
+	 *	reconfigured includes any changes to the configuration
+	 *	requested by the user, but which may or may not be rejected.
+	 */
+	struct netdev_config	*cfg_pending;
+	struct ethtool_netdev_state *ethtool;
+
 	/* protected by rtnl_lock */
 	struct bpf_xdp_entity	xdp_state[__MAX_XDP_MODE];
 
@@ -2411,7 +2490,94 @@ struct net_device {
 	struct rtnl_hw_stats64	*offload_xstats_l3;
 
 	struct devlink_port	*devlink_port;
-};
+
+#if IS_ENABLED(CONFIG_DPLL)
+	struct dpll_pin	__rcu	*dpll_pin;
+#endif
+#if IS_ENABLED(CONFIG_PAGE_POOL)
+	/** @page_pools: page pools created for this netdevice */
+	struct hlist_head	page_pools;
+#endif
+
+	/** @irq_moder: dim parameters used if IS_ENABLED(CONFIG_DIMLIB). */
+	struct dim_irq_moder	*irq_moder;
+
+	u64			max_pacing_offload_horizon;
+	struct napi_config	*napi_config;
+	u32			num_napi_configs;
+	u32			napi_defer_hard_irqs;
+	unsigned long		gro_flush_timeout;
+
+	/**
+	 * @up: copy of @state's IFF_UP, but safe to read with just @lock.
+	 *	May report false negatives while the device is being opened
+	 *	or closed (@lock does not protect .ndo_open, or .ndo_close).
+	 */
+	bool			up;
+
+	/**
+	 * @request_ops_lock: request the core to run all @netdev_ops and
+	 * @ethtool_ops under the @lock.
+	 */
+	bool			request_ops_lock;
+
+	/**
+	 * @lock: netdev-scope lock, protects a small selection of fields.
+	 * Should always be taken using netdev_lock() / netdev_unlock() helpers.
+	 * Drivers are free to use it for other protection.
+	 *
+	 * For the drivers that implement shaper or queue API, the scope
+	 * of this lock is expanded to cover most ndo/queue/ethtool/sysfs
+	 * operations. Drivers may opt-in to this behavior by setting
+	 * @request_ops_lock.
+	 *
+	 * @lock protection mixes with rtnl_lock in multiple ways, fields are
+	 * either:
+	 *
+	 * - simply protected by the instance @lock;
+	 *
+	 * - double protected - writers hold both locks, readers hold either;
+	 *
+	 * - ops protected - protected by the lock held around the NDOs
+	 *   and other callbacks, that is the instance lock on devices for
+	 *   which netdev_need_ops_lock() returns true, otherwise by rtnl_lock;
+	 *
+	 * - double ops protected - always protected by rtnl_lock but for
+	 *   devices for which netdev_need_ops_lock() returns true - also
+	 *   the instance lock.
+	 *
+	 * Simply protects:
+	 *	@gro_flush_timeout, @napi_defer_hard_irqs, @napi_list,
+	 *	@net_shaper_hierarchy, @reg_state, @threaded
+	 *
+	 * Double protects:
+	 *	@up, @moving_ns, @nd_net, @xdp_features
+	 *
+	 * Double ops protects:
+	 *	@real_num_rx_queues, @real_num_tx_queues
+	 *
+	 * Also protects some fields in:
+	 *	struct napi_struct, struct netdev_queue, struct netdev_rx_queue
+	 *
+	 * Ordering: take after rtnl_lock.
+	 */
+	struct mutex		lock;
+
+#if IS_ENABLED(CONFIG_NET_SHAPER)
+	/**
+	 * @net_shaper_hierarchy: data tracking the current shaper status
+	 *  see include/net/net_shapers.h
+	 */
+	struct net_shaper_hierarchy *net_shaper_hierarchy;
+#endif
+
+	struct hlist_head neighbours[NEIGH_NR_TABLES];
+
+	struct hwtstamp_provider __rcu	*hwprov;
+
+	u8			priv[] ____cacheline_aligned
+				       __counted_by(priv_len);
+} ____cacheline_aligned;
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
 /*
@@ -2514,21 +2680,6 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 		f(dev, &dev->_tx[i], arg);
 }
 
-#define netdev_lockdep_set_classes(dev)				\
-{								\
-	static struct lock_class_key qdisc_tx_busylock_key;	\
-	static struct lock_class_key qdisc_xmit_lock_key;	\
-	static struct lock_class_key dev_addr_list_lock_key;	\
-	unsigned int i;						\
-								\
-	(dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key;	\
-	lockdep_set_class(&(dev)->addr_list_lock,		\
-			  &dev_addr_list_lock_key);		\
-	for (i = 0; i < (dev)->num_tx_queues; i++)		\
-		lockdep_set_class(&(dev)->_tx[i]._xmit_lock,	\
-				  &qdisc_xmit_lock_key);	\
-}
-
 u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
 struct netdev_queue *netdev_core_pick_tx(struct net_device *dev,
@@ -2588,6 +2739,12 @@ struct net *dev_net(const struct net_device *dev)
 }
 
 static inline
+struct net *dev_net_rcu(const struct net_device *dev)
+{
+	return read_pnet_rcu(&dev->nd_net);
+}
+
+static inline
 void dev_net_set(struct net_device *dev, struct net *net)
 {
 	write_pnet(&dev->nd_net, net);
@@ -2601,7 +2758,7 @@ void dev_net_set(struct net_device *dev, struct net *net)
  */
 static inline void *netdev_priv(const struct net_device *dev)
 {
-	return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN);
+	return (void *)dev->priv;
 }
 
 /* Set the sysfs physical device reference for the network logical device
@@ -2615,13 +2772,48 @@ static inline void *netdev_priv(const struct net_device *dev)
  */
 #define SET_NETDEV_DEVTYPE(net, devtype)	((net)->dev.type = (devtype))
 
+void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+			  enum netdev_queue_type type,
+			  struct napi_struct *napi);
+
+static inline void netdev_lock(struct net_device *dev)
+{
+	mutex_lock(&dev->lock);
+}
+
+static inline void netdev_unlock(struct net_device *dev)
+{
+	mutex_unlock(&dev->lock);
+}
+/* Additional netdev_lock()-related helpers are in net/netdev_lock.h */
+
+void netif_napi_set_irq_locked(struct napi_struct *napi, int irq);
+
+static inline void netif_napi_set_irq(struct napi_struct *napi, int irq)
+{
+	netdev_lock(napi->dev);
+	netif_napi_set_irq_locked(napi, irq);
+	netdev_unlock(napi->dev);
+}
+
 /* Default NAPI poll() weight
  * Device drivers are strongly advised to not use bigger value
  */
 #define NAPI_POLL_WEIGHT 64
 
-void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
-			   int (*poll)(struct napi_struct *, int), int weight);
+void netif_napi_add_weight_locked(struct net_device *dev,
+				  struct napi_struct *napi,
+				  int (*poll)(struct napi_struct *, int),
+				  int weight);
+
+static inline void
+netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi,
+		      int (*poll)(struct napi_struct *, int), int weight)
+{
+	netdev_lock(dev);
+	netif_napi_add_weight_locked(dev, napi, poll, weight);
+	netdev_unlock(dev);
+}
 
 /**
  * netif_napi_add() - initialize a NAPI context
@@ -2640,6 +2832,13 @@ netif_napi_add(struct net_device *dev, struct napi_struct *napi,
 }
 
 static inline void
+netif_napi_add_locked(struct net_device *dev, struct napi_struct *napi,
+		      int (*poll)(struct napi_struct *, int))
+{
+	netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT);
+}
+
+static inline void
 netif_napi_add_tx_weight(struct net_device *dev,
 			 struct napi_struct *napi,
 			 int (*poll)(struct napi_struct *, int),
@@ -2649,6 +2848,31 @@ netif_napi_add_tx_weight(struct net_device *dev,
 	netif_napi_add_weight(dev, napi, poll, weight);
 }
 
+static inline void
+netif_napi_add_config_locked(struct net_device *dev, struct napi_struct *napi,
+			     int (*poll)(struct napi_struct *, int), int index)
+{
+	napi->index = index;
+	napi->config = &dev->napi_config[index];
+	netif_napi_add_weight_locked(dev, napi, poll, NAPI_POLL_WEIGHT);
+}
+
+/**
+ * netif_napi_add_config - initialize a NAPI context with persistent config
+ * @dev: network device
+ * @napi: NAPI context
+ * @poll: polling function
+ * @index: the NAPI index
+ */
+static inline void
+netif_napi_add_config(struct net_device *dev, struct napi_struct *napi,
+		      int (*poll)(struct napi_struct *, int), int index)
+{
+	netdev_lock(dev);
+	netif_napi_add_config_locked(dev, napi, poll, index);
+	netdev_unlock(dev);
+}
+
 /**
  * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only
  * @dev:  network device
@@ -2666,6 +2890,8 @@ static inline void netif_napi_add_tx(struct net_device *dev,
 	netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT);
 }
 
+void __netif_napi_del_locked(struct napi_struct *napi);
+
 /**
  *  __netif_napi_del - remove a NAPI context
  *  @napi: NAPI context
@@ -2674,7 +2900,18 @@ static inline void netif_napi_add_tx(struct net_device *dev,
  * containing @napi. Drivers might want to call this helper to combine
  * all the needed RCU grace periods into a single one.
  */
-void __netif_napi_del(struct napi_struct *napi);
+static inline void __netif_napi_del(struct napi_struct *napi)
+{
+	netdev_lock(napi->dev);
+	__netif_napi_del_locked(napi);
+	netdev_unlock(napi->dev);
+}
+
+static inline void netif_napi_del_locked(struct napi_struct *napi)
+{
+	__netif_napi_del_locked(napi);
+	synchronize_net();
+}
 
 /**
  *  netif_napi_del - remove a NAPI context
@@ -2688,6 +2925,9 @@ static inline void netif_napi_del(struct napi_struct *napi)
 	synchronize_net();
 }
 
+int netif_enable_cpu_rmap(struct net_device *dev, unsigned int num_irqs);
+void netif_set_affinity_auto(struct net_device *dev);
+
 struct packet_type {
 	__be16			type;	/* This is really htons(ether_type). */
 	bool			ignore_outgoing;
@@ -2731,6 +2971,16 @@ struct pcpu_sw_netstats {
 	struct u64_stats_sync   syncp;
 } __aligned(4 * sizeof(u64));
 
+struct pcpu_dstats {
+	u64_stats_t		rx_packets;
+	u64_stats_t		rx_bytes;
+	u64_stats_t		tx_packets;
+	u64_stats_t		tx_bytes;
+	u64_stats_t		rx_drops;
+	u64_stats_t		tx_drops;
+	struct u64_stats_sync	syncp;
+} __aligned(8 * sizeof(u64));
+
 struct pcpu_lstats {
 	u64_stats_t packets;
 	u64_stats_t bytes;
@@ -2771,6 +3021,56 @@ static inline void dev_lstats_add(struct net_device *dev, unsigned int len)
 	u64_stats_update_end(&lstats->syncp);
 }
 
+static inline void dev_dstats_rx_add(struct net_device *dev,
+				     unsigned int len)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	u64_stats_inc(&dstats->rx_packets);
+	u64_stats_add(&dstats->rx_bytes, len);
+	u64_stats_update_end(&dstats->syncp);
+}
+
+static inline void dev_dstats_rx_dropped(struct net_device *dev)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	u64_stats_inc(&dstats->rx_drops);
+	u64_stats_update_end(&dstats->syncp);
+}
+
+static inline void dev_dstats_rx_dropped_add(struct net_device *dev,
+					     unsigned int packets)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	u64_stats_add(&dstats->rx_drops, packets);
+	u64_stats_update_end(&dstats->syncp);
+}
+
+static inline void dev_dstats_tx_add(struct net_device *dev,
+				     unsigned int len)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	u64_stats_inc(&dstats->tx_packets);
+	u64_stats_add(&dstats->tx_bytes, len);
+	u64_stats_update_end(&dstats->syncp);
+}
+
+static inline void dev_dstats_tx_dropped(struct net_device *dev)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	u64_stats_inc(&dstats->tx_drops);
+	u64_stats_update_end(&dstats->syncp);
+}
+
 #define __netdev_alloc_pcpu_stats(type, gfp)				\
 ({									\
 	typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\
@@ -2991,8 +3291,6 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev);
 int call_netdevice_notifiers_info(unsigned long val,
 				  struct netdev_notifier_info *info);
 
-extern rwlock_t				dev_base_lock;		/* Device list lock */
-
 #define for_each_netdev(net, d)		\
 		list_for_each_entry(d, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_reverse(net, d)	\
@@ -3009,10 +3307,14 @@ extern rwlock_t				dev_base_lock;		/* Device list lock */
 #define for_each_netdev_continue_rcu(net, d)		\
 	list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list)
 #define for_each_netdev_in_bond_rcu(bond, slave)	\
-		for_each_netdev_rcu(&init_net, slave)	\
+		for_each_netdev_rcu(dev_net_rcu(bond), slave)	\
 			if (netdev_master_upper_dev_get_rcu(slave) == (bond))
 #define net_device_entry(lh)	list_entry(lh, struct net_device, dev_list)
 
+#define for_each_netdev_dump(net, d, ifindex)				\
+	for (; (d = xa_find(&(net)->dev_by_index, &ifindex,		\
+			    ULONG_MAX, XA_PRESENT)); ifindex++)
+
 static inline struct net_device *next_net_device(struct net_device *dev)
 {
 	struct list_head *lh;
@@ -3039,14 +3341,9 @@ static inline struct net_device *first_net_device(struct net *net)
 		net_device_entry(net->dev_base_head.next);
 }
 
-static inline struct net_device *first_net_device_rcu(struct net *net)
-{
-	struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head));
-
-	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
-}
-
 int netdev_boot_setup_check(struct net_device *dev);
+struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
+				   const char *hwaddr);
 struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type,
 				       const char *hwaddr);
 struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type);
@@ -3060,22 +3357,21 @@ int dev_get_iflink(const struct net_device *dev);
 int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
 int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
 			  struct net_device_path_stack *stack);
-struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
-				      unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
 bool netdev_name_in_use(struct net *net, const char *name);
 int dev_alloc_name(struct net_device *dev, const char *name);
+int netif_open(struct net_device *dev, struct netlink_ext_ack *extack);
 int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
+void netif_close(struct net_device *dev);
 void dev_close(struct net_device *dev);
-void dev_close_many(struct list_head *head, bool unlink);
+void netif_close_many(struct list_head *head, bool unlink);
+void netif_disable_lro(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb,
 		     struct net_device *sb_dev);
-u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb,
-		       struct net_device *sb_dev);
 
 int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev);
 int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
@@ -3111,8 +3407,6 @@ static inline void unregister_netdevice(struct net_device *dev)
 
 int netdev_refcnt_read(const struct net_device *dev);
 void free_netdev(struct net_device *dev);
-void netdev_freemem(struct net_device *dev);
-int init_dummy_netdev(struct net_device *dev);
 
 struct net_device *netdev_get_xmit_slave(struct net_device *dev,
 					 struct sk_buff *skb,
@@ -3121,10 +3415,15 @@ struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev,
 					    struct sock *sk);
 struct net_device *dev_get_by_index(struct net *net, int ifindex);
 struct net_device *__dev_get_by_index(struct net *net, int ifindex);
+struct net_device *netdev_get_by_index(struct net *net, int ifindex,
+				       netdevice_tracker *tracker, gfp_t gfp);
+struct net_device *netdev_get_by_index_lock(struct net *net, int ifindex);
+struct net_device *netdev_get_by_name(struct net *net, const char *name,
+				      netdevice_tracker *tracker, gfp_t gfp);
+struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker,
+					   unsigned short flags, unsigned short mask);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
-struct net_device *dev_get_by_napi_id(unsigned int napi_id);
-int dev_restart(struct net_device *dev);
-
+void netdev_copy_name(struct net_device *dev, char *name);
 
 static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev,
 				  unsigned short type,
@@ -3181,12 +3480,39 @@ static inline bool dev_has_header(const struct net_device *dev)
 	return dev->header_ops && dev->header_ops->create;
 }
 
+struct numa_drop_counters {
+	atomic_t	drops0 ____cacheline_aligned_in_smp;
+	atomic_t	drops1 ____cacheline_aligned_in_smp;
+};
+
+static inline int numa_drop_read(const struct numa_drop_counters *ndc)
+{
+	return atomic_read(&ndc->drops0) + atomic_read(&ndc->drops1);
+}
+
+static inline void numa_drop_add(struct numa_drop_counters *ndc, int val)
+{
+	int n = numa_node_id() % 2;
+
+	if (n)
+		atomic_add(val, &ndc->drops1);
+	else
+		atomic_add(val, &ndc->drops0);
+}
+
+static inline void numa_drop_reset(struct numa_drop_counters *ndc)
+{
+	atomic_set(&ndc->drops0, 0);
+	atomic_set(&ndc->drops1, 0);
+}
+
 /*
  * Incoming packets are placed on per-CPU queues
  */
 struct softnet_data {
 	struct list_head	poll_list;
 	struct sk_buff_head	process_queue;
+	local_lock_t		process_queue_bh_lock;
 
 	/* stats */
 	unsigned int		processed;
@@ -3195,6 +3521,7 @@ struct softnet_data {
 	struct softnet_data	*rps_ipi_list;
 #endif
 
+	unsigned int		received_rps;
 	bool			in_net_rx_action;
 	bool			in_napi_threaded_poll;
 
@@ -3208,13 +3535,7 @@ struct softnet_data {
 	struct sk_buff_head	xfrm_backlog;
 #endif
 	/* written and read only by owning cpu: */
-	struct {
-		u16 recursion;
-		u8  more;
-#ifdef CONFIG_NET_EGRESS
-		u8  skip_txqueue;
-#endif
-	} xmit;
+	struct netdev_xmit xmit;
 #ifdef CONFIG_RPS
 	/* input_queue_head should be written by cpu owning this struct,
 	 * and only read by other cpus. Worth using a cache line.
@@ -3225,59 +3546,45 @@ struct softnet_data {
 	call_single_data_t	csd ____cacheline_aligned_in_smp;
 	struct softnet_data	*rps_ipi_next;
 	unsigned int		cpu;
+
+	/* We force a cacheline alignment from here, to hold together
+	 * input_queue_tail, input_pkt_queue and backlog.state.
+	 * We add holes so that backlog.state is the last field
+	 * of this cache line.
+	 */
+	long			pad[3] ____cacheline_aligned_in_smp;
 	unsigned int		input_queue_tail;
 #endif
-	unsigned int		received_rps;
-	unsigned int		dropped;
 	struct sk_buff_head	input_pkt_queue;
+
 	struct napi_struct	backlog;
 
-	/* Another possibly contended cache line */
-	spinlock_t		defer_lock ____cacheline_aligned_in_smp;
-	int			defer_count;
-	int			defer_ipi_scheduled;
-	struct sk_buff		*defer_list;
+	struct numa_drop_counters drop_counters;
+
+	int			defer_ipi_scheduled ____cacheline_aligned_in_smp;
 	call_single_data_t	defer_csd;
 };
 
-static inline void input_queue_head_incr(struct softnet_data *sd)
-{
-#ifdef CONFIG_RPS
-	sd->input_queue_head++;
-#endif
-}
-
-static inline void input_queue_tail_incr_save(struct softnet_data *sd,
-					      unsigned int *qtail)
-{
-#ifdef CONFIG_RPS
-	*qtail = ++sd->input_queue_tail;
-#endif
-}
-
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
+struct page_pool_bh {
+	struct page_pool *pool;
+	local_lock_t bh_lock;
+};
+DECLARE_PER_CPU(struct page_pool_bh, system_page_pool);
+
+#ifndef CONFIG_PREEMPT_RT
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
-
-#define XMIT_RECURSION_LIMIT	8
-static inline bool dev_xmit_recursion(void)
-{
-	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
-			XMIT_RECURSION_LIMIT);
-}
-
-static inline void dev_xmit_recursion_inc(void)
+#else
+static inline int dev_recursion_level(void)
 {
-	__this_cpu_inc(softnet_data.xmit.recursion);
+	return current->net_xmit.recursion;
 }
 
-static inline void dev_xmit_recursion_dec(void)
-{
-	__this_cpu_dec(softnet_data.xmit.recursion);
-}
+#endif
 
 void __netif_schedule(struct Qdisc *q);
 void netif_schedule_queue(struct netdev_queue *txq);
@@ -3342,6 +3649,12 @@ static inline void netif_tx_wake_all_queues(struct net_device *dev)
 
 static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue)
 {
+	/* Paired with READ_ONCE() from dev_watchdog() */
+	WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+	/* This barrier is paired with smp_mb() from dev_watchdog() */
+	smp_mb__before_atomic();
+
 	/* Must be an atomic op see netif_txq_try_stop() */
 	set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state);
 }
@@ -3411,6 +3724,16 @@ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue
 #endif
 }
 
+static inline int netdev_queue_dql_avail(const struct netdev_queue *txq)
+{
+#ifdef CONFIG_BQL
+	/* Non-BQL migrated drivers will return 0, too. */
+	return dql_avail(&txq->dql);
+#else
+	return 0;
+#endif
+}
+
 /**
  *	netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write
  *	@dev_queue: pointer to transmit queue
@@ -3458,6 +3781,12 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 	if (likely(dql_avail(&dev_queue->dql) >= 0))
 		return;
 
+	/* Paired with READ_ONCE() from dev_watchdog() */
+	WRITE_ONCE(dev_queue->trans_start, jiffies);
+
+	/* This barrier is paired with smp_mb() from dev_watchdog() */
+	smp_mb__before_atomic();
+
 	set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state);
 
 	/*
@@ -3465,7 +3794,7 @@ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue,
 	 * because in netdev_tx_completed_queue we update the dql_completed
 	 * before checking the XOFF flag.
 	 */
-	smp_mb();
+	smp_mb__after_atomic();
 
 	/* check again in case another CPU has just made room avail */
 	if (unlikely(dql_avail(&dev_queue->dql) >= 0))
@@ -3535,7 +3864,7 @@ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue,
 	dql_completed(&dev_queue->dql, bytes);
 
 	/*
-	 * Without the memory barrier there is a small possiblity that
+	 * Without the memory barrier there is a small possibility that
 	 * netdev_tx_sent_queue will miss the update and cause the queue to
 	 * be stopped forever
 	 */
@@ -3574,6 +3903,17 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
 }
 
 /**
+ * netdev_tx_reset_subqueue - reset the BQL stats and state of a netdev queue
+ * @dev: network device
+ * @qid: stack index of the queue to reset
+ */
+static inline void netdev_tx_reset_subqueue(const struct net_device *dev,
+					    u32 qid)
+{
+	netdev_tx_reset_queue(netdev_get_tx_queue(dev, qid));
+}
+
+/**
  * 	netdev_reset_queue - reset the packets and bytes count of a network device
  * 	@dev_queue: network device
  *
@@ -3582,7 +3922,7 @@ static inline void netdev_tx_reset_queue(struct netdev_queue *q)
  */
 static inline void netdev_reset_queue(struct net_device *dev_queue)
 {
-	netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0));
+	netdev_tx_reset_subqueue(dev_queue, 0);
 }
 
 /**
@@ -3720,7 +4060,7 @@ static inline bool netif_attr_test_mask(unsigned long j,
  *	@online_mask: bitmask for CPUs/Rx queues that are online
  *	@nr_bits: number of bits in the bitmask
  *
- * Returns true if a CPU/Rx queue is online.
+ * Returns: true if a CPU/Rx queue is online.
  */
 static inline bool netif_attr_test_online(unsigned long j,
 					  const unsigned long *online_mask,
@@ -3740,7 +4080,8 @@ static inline bool netif_attr_test_online(unsigned long j,
  *	@srcp: the cpumask/Rx queue mask pointer
  *	@nr_bits: number of bits in the bitmask
  *
- * Returns >= nr_bits if no further CPUs/Rx queues set.
+ * Returns: next (after n) CPU/Rx queue index in the mask;
+ * >= nr_bits if no further CPUs/Rx queues set.
  */
 static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp,
 					       unsigned int nr_bits)
@@ -3762,7 +4103,8 @@ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp,
  *	@src2p: the second CPUs/Rx queues mask pointer
  *	@nr_bits: number of bits in the bitmask
  *
- * Returns >= nr_bits if no further CPUs/Rx queues set in both.
+ * Returns: next (after n) CPU/Rx queue index set in both masks;
+ * >= nr_bits if no further CPUs/Rx queues set in both.
  */
 static inline int netif_attrmask_next_and(int n, const unsigned long *src1p,
 					  const unsigned long *src2p,
@@ -3809,38 +4151,10 @@ static inline bool netif_is_multiqueue(const struct net_device *dev)
 }
 
 int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq);
-
-#ifdef CONFIG_SYSFS
 int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq);
-#else
-static inline int netif_set_real_num_rx_queues(struct net_device *dev,
-						unsigned int rxqs)
-{
-	dev->real_num_rx_queues = rxqs;
-	return 0;
-}
-#endif
 int netif_set_real_num_queues(struct net_device *dev,
 			      unsigned int txq, unsigned int rxq);
 
-static inline struct netdev_rx_queue *
-__netif_get_rx_queue(struct net_device *dev, unsigned int rxq)
-{
-	return dev->_rx + rxq;
-}
-
-#ifdef CONFIG_SYSFS
-static inline unsigned int get_netdev_rx_queue_index(
-		struct netdev_rx_queue *queue)
-{
-	struct net_device *dev = queue->dev;
-	int index = queue - dev->_rx;
-
-	BUG_ON(index >= dev->num_rx_queues);
-	return index;
-}
-#endif
-
 int netif_get_num_default_rss_queues(void);
 
 void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason);
@@ -3886,9 +4200,9 @@ static inline void dev_consume_skb_any(struct sk_buff *skb)
 }
 
 u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp,
-			     struct bpf_prog *xdp_prog);
-void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog);
-int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb);
+			     const struct bpf_prog *xdp_prog);
+void generic_xdp_tx(struct sk_buff *skb, const struct bpf_prog *xdp_prog);
+int do_xdp_generic(const struct bpf_prog *xdp_prog, struct sk_buff **pskb);
 int netif_rx(struct sk_buff *skb);
 int __netif_rx(struct sk_buff *skb);
 
@@ -3896,13 +4210,16 @@ int netif_receive_skb(struct sk_buff *skb);
 int netif_receive_skb_core(struct sk_buff *skb);
 void netif_receive_skb_list_internal(struct list_head *head);
 void netif_receive_skb_list(struct list_head *head);
-gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb);
-void napi_gro_flush(struct napi_struct *napi, bool flush_old);
+gro_result_t gro_receive_skb(struct gro_node *gro, struct sk_buff *skb);
+
+static inline gro_result_t napi_gro_receive(struct napi_struct *napi,
+					    struct sk_buff *skb)
+{
+	return gro_receive_skb(&napi->gro, skb);
+}
+
 struct sk_buff *napi_get_frags(struct napi_struct *napi);
-void napi_get_frags_check(struct napi_struct *napi);
 gro_result_t napi_gro_frags(struct napi_struct *napi);
-struct packet_offload *gro_find_receive_by_type(__be16 type);
-struct packet_offload *gro_find_complete_by_type(__be16 type);
 
 static inline void napi_free_frags(struct napi_struct *napi)
 {
@@ -3926,42 +4243,58 @@ int put_user_ifreq(struct ifreq *ifr, void __user *arg);
 int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 		void __user *data, bool *need_copyout);
 int dev_ifconf(struct net *net, struct ifconf __user *ifc);
+int dev_eth_ioctl(struct net_device *dev,
+		  struct ifreq *ifr, unsigned int cmd);
+int generic_hwtstamp_get_lower(struct net_device *dev,
+			       struct kernel_hwtstamp_config *kernel_cfg);
+int generic_hwtstamp_set_lower(struct net_device *dev,
+			       struct kernel_hwtstamp_config *kernel_cfg,
+			       struct netlink_ext_ack *extack);
 int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
-unsigned int dev_get_flags(const struct net_device *);
+unsigned int netif_get_flags(const struct net_device *dev);
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		       struct netlink_ext_ack *extack);
+int netif_change_flags(struct net_device *dev, unsigned int flags,
+		       struct netlink_ext_ack *extack);
 int dev_change_flags(struct net_device *dev, unsigned int flags,
 		     struct netlink_ext_ack *extack);
+int netif_set_alias(struct net_device *dev, const char *alias, size_t len);
 int dev_set_alias(struct net_device *, const char *, size_t);
 int dev_get_alias(const struct net_device *, char *, size_t);
 int __dev_change_net_namespace(struct net_device *dev, struct net *net,
-			       const char *pat, int new_ifindex);
-static inline
+			       const char *pat, int new_ifindex,
+			       struct netlink_ext_ack *extack);
 int dev_change_net_namespace(struct net_device *dev, struct net *net,
-			     const char *pat)
-{
-	return __dev_change_net_namespace(dev, net, pat, 0);
-}
-int __dev_set_mtu(struct net_device *, int);
+			     const char *pat);
+int __netif_set_mtu(struct net_device *dev, int new_mtu);
+int netif_set_mtu(struct net_device *dev, int new_mtu);
 int dev_set_mtu(struct net_device *, int);
-int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
-			      struct netlink_ext_ack *extack);
-int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa,
+int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+				struct netlink_ext_ack *extack);
+int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
+			  struct netlink_ext_ack *extack);
+int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 			struct netlink_ext_ack *extack);
-int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa,
+int dev_set_mac_address_user(struct net_device *dev, struct sockaddr_storage *ss,
 			     struct netlink_ext_ack *extack);
-int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
-int dev_get_port_parent_id(struct net_device *dev,
-			   struct netdev_phys_item_id *ppid, bool recurse);
+int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
+int netif_get_port_parent_id(struct net_device *dev,
+			     struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
+
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
 struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 				    struct netdev_queue *txq, int *ret);
 
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
 u8 dev_xdp_prog_count(struct net_device *dev);
+int netif_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
+int dev_xdp_propagate(struct net_device *dev, struct netdev_bpf *bpf);
+u8 dev_xdp_sb_prog_count(struct net_device *dev);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 
+u32 dev_get_min_mp_channel_count(const struct net_device *dev);
+
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb(struct net_device *dev, struct sk_buff *skb);
 int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb);
@@ -3994,32 +4327,19 @@ static __always_inline bool __is_skb_forwardable(const struct net_device *dev,
 	return false;
 }
 
-struct net_device_core_stats __percpu *netdev_core_stats_alloc(struct net_device *dev);
-
-static inline struct net_device_core_stats __percpu *dev_core_stats(struct net_device *dev)
-{
-	/* This READ_ONCE() pairs with the write in netdev_core_stats_alloc() */
-	struct net_device_core_stats __percpu *p = READ_ONCE(dev->core_stats);
-
-	if (likely(p))
-		return p;
-
-	return netdev_core_stats_alloc(dev);
-}
+void netdev_core_stats_inc(struct net_device *dev, u32 offset);
 
 #define DEV_CORE_STATS_INC(FIELD)						\
 static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev)		\
 {										\
-	struct net_device_core_stats __percpu *p;				\
-										\
-	p = dev_core_stats(dev);						\
-	if (p)									\
-		this_cpu_inc(p->FIELD);						\
+	netdev_core_stats_inc(dev,						\
+			offsetof(struct net_device_core_stats, FIELD));		\
 }
 DEV_CORE_STATS_INC(rx_dropped)
 DEV_CORE_STATS_INC(tx_dropped)
 DEV_CORE_STATS_INC(rx_nohandler)
 DEV_CORE_STATS_INC(rx_otherhost_dropped)
+#undef DEV_CORE_STATS_INC
 
 static __always_inline int ____dev_forward_skb(struct net_device *dev,
 					       struct sk_buff *skb,
@@ -4037,7 +4357,17 @@ static __always_inline int ____dev_forward_skb(struct net_device *dev,
 	return 0;
 }
 
-bool dev_nit_active(struct net_device *dev);
+bool dev_nit_active_rcu(const struct net_device *dev);
+static inline bool dev_nit_active(const struct net_device *dev)
+{
+	bool ret;
+
+	rcu_read_lock();
+	ret = dev_nit_active_rcu(dev);
+	rcu_read_unlock();
+	return ret;
+}
+
 void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev);
 
 static inline void __dev_put(struct net_device *dev)
@@ -4133,6 +4463,8 @@ static inline void dev_put(struct net_device *dev)
 	netdev_put(dev, NULL);
 }
 
+DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T))
+
 static inline void netdev_ref_replace(struct net_device *odev,
 				      struct net_device *ndev,
 				      netdevice_tracker *tracker,
@@ -4159,6 +4491,16 @@ static inline void netdev_ref_replace(struct net_device *odev,
 void linkwatch_fire_event(struct net_device *dev);
 
 /**
+ * linkwatch_sync_dev - sync linkwatch for the given device
+ * @dev: network device to sync linkwatch for
+ *
+ * Sync linkwatch for the given device, removing it from the
+ * pending work list (if queued).
+ */
+void linkwatch_sync_dev(struct net_device *dev);
+void __linkwatch_sync_dev(struct net_device *dev);
+
+/**
  *	netif_carrier_ok - test if carrier present
  *	@dev: network device
  *
@@ -4171,7 +4513,7 @@ static inline bool netif_carrier_ok(const struct net_device *dev)
 
 unsigned long dev_trans_start(struct net_device *dev);
 
-void __netdev_watchdog_up(struct net_device *dev);
+void netdev_watchdog_up(struct net_device *dev);
 
 void netif_carrier_on(struct net_device *dev);
 void netif_carrier_off(struct net_device *dev);
@@ -4267,8 +4609,10 @@ static inline bool netif_testing(const struct net_device *dev)
  */
 static inline bool netif_oper_up(const struct net_device *dev)
 {
-	return (dev->operstate == IF_OPER_UP ||
-		dev->operstate == IF_OPER_UNKNOWN /* backward compat */);
+	unsigned int operstate = READ_ONCE(dev->operstate);
+
+	return	operstate == IF_OPER_UP ||
+		operstate == IF_OPER_UNKNOWN /* backward compat */;
 }
 
 /**
@@ -4414,9 +4758,10 @@ static inline void __netif_tx_unlock_bh(struct netdev_queue *txq)
 /*
  * txq->trans_start can be read locklessly from dev_watchdog()
  */
-static inline void txq_trans_update(struct netdev_queue *txq)
+static inline void txq_trans_update(const struct net_device *dev,
+				    struct netdev_queue *txq)
 {
-	if (txq->xmit_lock_owner != -1)
+	if (!dev->lltx)
 		WRITE_ONCE(txq->trans_start, jiffies);
 }
 
@@ -4459,7 +4804,7 @@ static inline void netif_tx_unlock_bh(struct net_device *dev)
 }
 
 #define HARD_TX_LOCK(dev, txq, cpu) {			\
-	if ((dev->features & NETIF_F_LLTX) == 0) {	\
+	if (!(dev)->lltx) {				\
 		__netif_tx_lock(txq, cpu);		\
 	} else {					\
 		__netif_tx_acquire(txq);		\
@@ -4467,12 +4812,12 @@ static inline void netif_tx_unlock_bh(struct net_device *dev)
 }
 
 #define HARD_TX_TRYLOCK(dev, txq)			\
-	(((dev->features & NETIF_F_LLTX) == 0) ?	\
+	(!(dev)->lltx ?					\
 		__netif_tx_trylock(txq) :		\
 		__netif_tx_acquire(txq))
 
 #define HARD_TX_UNLOCK(dev, txq) {			\
-	if ((dev->features & NETIF_F_LLTX) == 0) {	\
+	if (!(dev)->lltx) {				\
 		__netif_tx_unlock(txq);			\
 	} else {					\
 		__netif_tx_release(txq);		\
@@ -4540,6 +4885,9 @@ static inline void netif_addr_unlock_bh(struct net_device *dev)
 
 void ether_setup(struct net_device *dev);
 
+/* Allocate dummy net_device */
+struct net_device *alloc_netdev_dummy(int sizeof_priv);
+
 /* Support for loadable net-drivers */
 struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 				    unsigned char name_assign_type,
@@ -4560,6 +4908,9 @@ int devm_register_netdev(struct device *dev, struct net_device *ndev);
 /* General hardware address lists handling functions */
 int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
 		   struct netdev_hw_addr_list *from_list, int addr_len);
+int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
+			    struct netdev_hw_addr_list *from_list,
+			    int addr_len);
 void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
 		      struct netdev_hw_addr_list *from_list, int addr_len);
 int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
@@ -4614,7 +4965,7 @@ void dev_uc_flush(struct net_device *dev);
 void dev_uc_init(struct net_device *dev);
 
 /**
- *  __dev_uc_sync - Synchonize device's unicast list
+ *  __dev_uc_sync - Synchronize device's unicast list
  *  @dev:  device to sync
  *  @sync: function to call if address should be added
  *  @unsync: function to call if address should be removed
@@ -4658,7 +5009,7 @@ void dev_mc_flush(struct net_device *dev);
 void dev_mc_init(struct net_device *dev);
 
 /**
- *  __dev_mc_sync - Synchonize device's multicast list
+ *  __dev_mc_sync - Synchronize device's multicast list
  *  @dev:  device to sync
  *  @sync: function to call if address should be added
  *  @unsync: function to call if address should be removed
@@ -4691,8 +5042,11 @@ static inline void __dev_mc_unsync(struct net_device *dev,
 
 /* Functions used for secondary unicast and multicast support */
 void dev_set_rx_mode(struct net_device *dev);
+int netif_set_promiscuity(struct net_device *dev, int inc);
 int dev_set_promiscuity(struct net_device *dev, int inc);
+int netif_set_allmulti(struct net_device *dev, int inc, bool notify);
 int dev_set_allmulti(struct net_device *dev, int inc);
+void netif_state_change(struct net_device *dev);
 void netdev_state_change(struct net_device *dev);
 void __netdev_notify_peers(struct net_device *dev);
 void netdev_notify_peers(struct net_device *dev);
@@ -4707,11 +5061,6 @@ void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s,
 			   const struct pcpu_sw_netstats __percpu *netstats);
 void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s);
 
-extern int		netdev_max_backlog;
-extern int		dev_rx_weight;
-extern int		dev_tx_weight;
-extern int		gro_normal_batch;
-
 enum {
 	NESTED_SYNC_IMM_BIT,
 	NESTED_SYNC_TODO_BIT,
@@ -4824,13 +5173,6 @@ int skb_crc32c_csum_help(struct sk_buff *skb);
 int skb_csum_hwoffload_help(struct sk_buff *skb,
 			    const netdev_features_t features);
 
-struct sk_buff *__skb_gso_segment(struct sk_buff *skb,
-				  netdev_features_t features, bool tx_path);
-struct sk_buff *skb_eth_gso_segment(struct sk_buff *skb,
-				    netdev_features_t features, __be16 type);
-struct sk_buff *skb_mac_gso_segment(struct sk_buff *skb,
-				    netdev_features_t features);
-
 struct netdev_bonding_info {
 	ifslave	slave;
 	ifbond	master;
@@ -4845,19 +5187,13 @@ void netdev_bonding_info_change(struct net_device *dev,
 				struct netdev_bonding_info *bonding_info);
 
 #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK)
-void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data);
+void ethtool_notify(struct net_device *dev, unsigned int cmd);
 #else
-static inline void ethtool_notify(struct net_device *dev, unsigned int cmd,
-				  const void *data)
+static inline void ethtool_notify(struct net_device *dev, unsigned int cmd)
 {
 }
 #endif
 
-static inline
-struct sk_buff *skb_gso_segment(struct sk_buff *skb, netdev_features_t features)
-{
-	return __skb_gso_segment(skb, features, true);
-}
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth);
 
 static inline bool can_checksum_protocol(netdev_features_t features,
@@ -4907,18 +5243,35 @@ static inline ktime_t netdev_get_tstamp(struct net_device *dev,
 	return hwtstamps->hwtstamp;
 }
 
-static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
-					      struct sk_buff *skb, struct net_device *dev,
-					      bool more)
+#ifndef CONFIG_PREEMPT_RT
+static inline void netdev_xmit_set_more(bool more)
 {
 	__this_cpu_write(softnet_data.xmit.more, more);
-	return ops->ndo_start_xmit(skb, dev);
 }
 
 static inline bool netdev_xmit_more(void)
 {
 	return __this_cpu_read(softnet_data.xmit.more);
 }
+#else
+static inline void netdev_xmit_set_more(bool more)
+{
+	current->net_xmit.more = more;
+}
+
+static inline bool netdev_xmit_more(void)
+{
+	return current->net_xmit.more;
+}
+#endif
+
+static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
+					      struct sk_buff *skb, struct net_device *dev,
+					      bool more)
+{
+	netdev_xmit_set_more(more);
+	return ops->ndo_start_xmit(skb, dev);
+}
 
 static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
 					    struct netdev_queue *txq, bool more)
@@ -4928,7 +5281,7 @@ static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_devi
 
 	rc = __netdev_start_xmit(ops, skb, dev, more);
 	if (rc == NETDEV_TX_OK)
-		txq_trans_update(txq);
+		txq_trans_update(dev, txq);
 
 	return rc;
 }
@@ -4976,6 +5329,7 @@ static inline netdev_features_t netdev_add_tso_features(netdev_features_t featur
 int __netdev_update_features(struct net_device *dev);
 void netdev_update_features(struct net_device *dev);
 void netdev_change_features(struct net_device *dev);
+void netdev_compute_master_upper_features(struct net_device *dev, bool update_header);
 
 void netif_stacked_transfer_operstate(const struct net_device *rootdev,
 					struct net_device *dev);
@@ -4984,16 +5338,22 @@ netdev_features_t passthru_features_check(struct sk_buff *skb,
 					  struct net_device *dev,
 					  netdev_features_t features);
 netdev_features_t netif_skb_features(struct sk_buff *skb);
+void skb_warn_bad_offload(const struct sk_buff *skb);
 
 static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 {
-	netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT;
+	netdev_features_t feature;
+
+	if (gso_type & (SKB_GSO_TCP_FIXEDID | SKB_GSO_TCP_FIXEDID_INNER))
+		gso_type |= __SKB_GSO_TCP_FIXEDID;
+
+	feature = ((netdev_features_t)gso_type << NETIF_F_GSO_SHIFT) & NETIF_F_GSO_MASK;
 
 	/* check flags correspondence */
 	BUILD_BUG_ON(SKB_GSO_TCPV4   != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_DODGY   != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT));
-	BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(__SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_TCPV6   != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FCOE    != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_GRE     != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT));
@@ -5009,6 +5369,8 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type)
 	BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT));
 	BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT));
+	BUILD_BUG_ON(SKB_GSO_TCP_ACCECN !=
+		     (NETIF_F_GSO_ACCECN >> NETIF_F_GSO_SHIFT));
 
 	return (features & feature) == feature;
 }
@@ -5032,17 +5394,22 @@ void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs);
 void netif_inherit_tso_max(struct net_device *to,
 			   const struct net_device *from);
 
-static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol,
-					int pulled_hlen, u16 mac_offset,
-					int mac_len)
+static inline unsigned int
+netif_get_gro_max_size(const struct net_device *dev, const struct sk_buff *skb)
+{
+	/* pairs with WRITE_ONCE() in netif_set_gro(_ipv4)_max_size() */
+	return skb->protocol == htons(ETH_P_IPV6) ?
+	       READ_ONCE(dev->gro_max_size) :
+	       READ_ONCE(dev->gro_ipv4_max_size);
+}
+
+static inline unsigned int
+netif_get_gso_max_size(const struct net_device *dev, const struct sk_buff *skb)
 {
-	skb->protocol = protocol;
-	skb->encapsulation = 1;
-	skb_push(skb, pulled_hlen);
-	skb_reset_transport_header(skb);
-	skb->mac_header = mac_offset;
-	skb->network_header = skb->mac_header + mac_len;
-	skb->mac_len = mac_len;
+	/* pairs with WRITE_ONCE() in netif_set_gso(_ipv4)_max_size() */
+	return skb->protocol == htons(ETH_P_IPV6) ?
+	       READ_ONCE(dev->gso_max_size) :
+	       READ_ONCE(dev->gso_ipv4_max_size);
 }
 
 static inline bool netif_is_macsec(const struct net_device *dev)
@@ -5090,6 +5457,15 @@ static inline bool netif_is_l3_slave(const struct net_device *dev)
 	return dev->priv_flags & IFF_L3MDEV_SLAVE;
 }
 
+static inline int dev_sdif(const struct net_device *dev)
+{
+#ifdef CONFIG_NET_L3_MASTER_DEV
+	if (netif_is_l3_slave(dev))
+		return dev->ifindex;
+#endif
+	return 0;
+}
+
 static inline bool netif_is_bridge_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_EBRIDGE;
@@ -5110,6 +5486,11 @@ static inline bool netif_is_ovs_port(const struct net_device *dev)
 	return dev->priv_flags & IFF_OVS_DATAPATH;
 }
 
+static inline bool netif_is_any_bridge_master(const struct net_device *dev)
+{
+	return netif_is_bridge_master(dev) || netif_is_ovs_master(dev);
+}
+
 static inline bool netif_is_any_bridge_port(const struct net_device *dev)
 {
 	return netif_is_bridge_port(dev) || netif_is_ovs_port(dev);
@@ -5178,7 +5559,9 @@ static inline const char *netdev_name(const struct net_device *dev)
 
 static inline const char *netdev_reg_state(const struct net_device *dev)
 {
-	switch (dev->reg_state) {
+	u8 reg_state = READ_ONCE(dev->reg_state);
+
+	switch (reg_state) {
 	case NETREG_UNINITIALIZED: return " (uninitialized)";
 	case NETREG_REGISTERED: return "";
 	case NETREG_UNREGISTERING: return " (unregistering)";
@@ -5187,7 +5570,7 @@ static inline const char *netdev_reg_state(const struct net_device *dev)
 	case NETREG_DUMMY: return " (dummy)";
 	}
 
-	WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, dev->reg_state);
+	WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, reg_state);
 	return " (unknown)";
 }
 
@@ -5229,7 +5612,6 @@ static inline const char *netdev_reg_state(const struct net_device *dev)
 #define PTYPE_HASH_SIZE	(16)
 #define PTYPE_HASH_MASK	(PTYPE_HASH_SIZE - 1)
 
-extern struct list_head ptype_all __read_mostly;
 extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
 
 extern struct net_device *blackhole_netdev;
@@ -5238,5 +5620,6 @@ extern struct net_device *blackhole_netdev;
 #define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD)
 #define DEV_STATS_ADD(DEV, FIELD, VAL) 	\
 		atomic_long_add((VAL), &(DEV)->stats.__##FIELD)
+#define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD)
 
 #endif	/* _LINUX_NETDEVICE_H */
diff --git a/include/linux/netdevice_xmit.h b/include/linux/netdevice_xmit.h
new file mode 100644
index 000000000000..cc232508e695
--- /dev/null
+++ b/include/linux/netdevice_xmit.h
@@ -0,0 +1,26 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_NETDEVICE_XMIT_H
+#define _LINUX_NETDEVICE_XMIT_H
+
+#if IS_ENABLED(CONFIG_NET_ACT_MIRRED)
+#define MIRRED_NEST_LIMIT	4
+#endif
+
+struct net_device;
+
+struct netdev_xmit {
+	u16 recursion;
+	u8  more;
+#ifdef CONFIG_NET_EGRESS
+	u8  skip_txqueue;
+#endif
+#if IS_ENABLED(CONFIG_NET_ACT_MIRRED)
+	u8			sched_mirred_nest;
+	struct net_device	*sched_mirred_dev[MIRRED_NEST_LIMIT];
+#endif
+#if IS_ENABLED(CONFIG_NF_DUP_NETDEV)
+	u8 nf_dup_skb_recursion;
+#endif
+};
+
+#endif
diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 0762444e3767..efbbfa770d66 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -11,6 +11,7 @@
 #include <linux/wait.h>
 #include <linux/list.h>
 #include <linux/static_key.h>
+#include <linux/module.h>
 #include <linux/netfilter_defs.h>
 #include <linux/netdevice.h>
 #include <linux/sockptr.h>
@@ -21,6 +22,16 @@ static inline int NF_DROP_GETERR(int verdict)
 	return -(verdict >> NF_VERDICT_QBITS);
 }
 
+static __always_inline int
+NF_DROP_REASON(struct sk_buff *skb, enum skb_drop_reason reason, u32 err)
+{
+	BUILD_BUG_ON(err > 0xffff);
+
+	kfree_skb_reason(skb, reason);
+
+	return ((err << 16) | NF_STOLEN);
+}
+
 static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1,
 				   const union nf_inet_addr *a2)
 {
@@ -81,9 +92,13 @@ enum nf_hook_ops_type {
 	NF_HOOK_OP_UNDEFINED,
 	NF_HOOK_OP_NF_TABLES,
 	NF_HOOK_OP_BPF,
+	NF_HOOK_OP_NFT_FT,
 };
 
 struct nf_hook_ops {
+	struct list_head	list;
+	struct rcu_head		rcu;
+
 	/* User fills in from here down. */
 	nf_hookfn		*hook;
 	struct net_device	*dev;
@@ -359,22 +374,17 @@ __sum16 nf_checksum_partial(struct sk_buff *skb, unsigned int hook,
 			    u_int8_t protocol, unsigned short family);
 int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl,
 	     bool strict, unsigned short family);
-int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry);
 
 #include <net/flow.h>
 
 struct nf_conn;
 enum nf_nat_manip_type;
 struct nlattr;
-enum ip_conntrack_dir;
 
 struct nf_nat_hook {
 	int (*parse_nat_setup)(struct nf_conn *ct, enum nf_nat_manip_type manip,
 			       const struct nlattr *attr);
 	void (*decode_session)(struct sk_buff *skb, struct flowi *fl);
-	unsigned int (*manip_pkt)(struct sk_buff *skb, struct nf_conn *ct,
-				  enum nf_nat_manip_type mtype,
-				  enum ip_conntrack_dir dir);
 	void (*remove_nat_bysrc)(struct nf_conn *ct);
 };
 
@@ -463,6 +473,8 @@ struct nf_ct_hook {
 			      const struct sk_buff *);
 	void (*attach)(struct sk_buff *nskb, const struct sk_buff *skb);
 	void (*set_closing)(struct nf_conntrack *nfct);
+	int (*confirm)(struct sk_buff *skb);
+	u32 (*get_id)(const struct nf_conntrack *nfct);
 };
 extern const struct nf_ct_hook __rcu *nf_ct_hook;
 
@@ -481,18 +493,16 @@ struct nfnl_ct_hook {
 };
 extern const struct nfnl_ct_hook __rcu *nfnl_ct_hook;
 
-/**
- * nf_skb_duplicated - TEE target has sent a packet
- *
- * When a xtables target sends a packet, the OUTPUT and POSTROUTING
- * hooks are traversed again, i.e. nft and xtables are invoked recursively.
- *
- * This is used by xtables TEE target to prevent the duplicated skb from
- * being duplicated again.
- */
-DECLARE_PER_CPU(bool, nf_skb_duplicated);
+struct nf_defrag_hook {
+	struct module *owner;
+	int (*enable)(struct net *net);
+	void (*disable)(struct net *net);
+};
 
-/**
+extern const struct nf_defrag_hook __rcu *nf_defrag_v4_hook;
+extern const struct nf_defrag_hook __rcu *nf_defrag_v6_hook;
+
+/*
  * Contains bitmask of ctnetlink event subscribers, if any.
  * Can't be pernet due to NETLINK_LISTEN_ALL_NSID setsockopt flag.
  */
diff --git a/include/linux/netfilter/ipset/ip_set.h b/include/linux/netfilter/ipset/ip_set.h
index e8c350a3ade1..e9f4f845d760 100644
--- a/include/linux/netfilter/ipset/ip_set.h
+++ b/include/linux/netfilter/ipset/ip_set.h
@@ -186,6 +186,8 @@ struct ip_set_type_variant {
 	/* Return true if "b" set is the same as "a"
 	 * according to the create set parameters */
 	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+	/* Cancel ongoing garbage collectors before destroying the set*/
+	void (*cancel_gc)(struct ip_set *set);
 	/* Region-locking is used */
 	bool region_lock;
 };
@@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type);
 
 /* A generic IP set */
 struct ip_set {
+	/* For call_cru in destroy */
+	struct rcu_head rcu;
 	/* The name of the set */
 	char name[IPSET_MAXNAMELEN];
 	/* Lock protecting the set data */
diff --git a/include/linux/netfilter/nf_conntrack_dccp.h b/include/linux/netfilter/nf_conntrack_dccp.h
deleted file mode 100644
index c509ed76e714..000000000000
--- a/include/linux/netfilter/nf_conntrack_dccp.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NF_CONNTRACK_DCCP_H
-#define _NF_CONNTRACK_DCCP_H
-
-/* Exposed to userspace over nfnetlink */
-enum ct_dccp_states {
-	CT_DCCP_NONE,
-	CT_DCCP_REQUEST,
-	CT_DCCP_RESPOND,
-	CT_DCCP_PARTOPEN,
-	CT_DCCP_OPEN,
-	CT_DCCP_CLOSEREQ,
-	CT_DCCP_CLOSING,
-	CT_DCCP_TIMEWAIT,
-	CT_DCCP_IGNORE,
-	CT_DCCP_INVALID,
-	__CT_DCCP_MAX
-};
-#define CT_DCCP_MAX		(__CT_DCCP_MAX - 1)
-
-enum ct_dccp_roles {
-	CT_DCCP_ROLE_CLIENT,
-	CT_DCCP_ROLE_SERVER,
-	__CT_DCCP_ROLE_MAX
-};
-#define CT_DCCP_ROLE_MAX	(__CT_DCCP_ROLE_MAX - 1)
-
-#include <linux/netfilter/nf_conntrack_tuple_common.h>
-
-struct nf_ct_dccp {
-	u_int8_t	role[IP_CT_DIR_MAX];
-	u_int8_t	state;
-	u_int8_t	last_pkt;
-	u_int8_t	last_dir;
-	u_int64_t	handshake_seq;
-};
-
-#endif /* _NF_CONNTRACK_DCCP_H */
diff --git a/include/linux/netfilter/nf_conntrack_h323.h b/include/linux/netfilter/nf_conntrack_h323.h
index 9e937f64a1ad..81286c499325 100644
--- a/include/linux/netfilter/nf_conntrack_h323.h
+++ b/include/linux/netfilter/nf_conntrack_h323.h
@@ -34,10 +34,6 @@ struct nf_ct_h323_master {
 int get_h225_addr(struct nf_conn *ct, unsigned char *data,
 		  TransportAddress *taddr, union nf_inet_addr *addr,
 		  __be16 *port);
-void nf_conntrack_h245_expect(struct nf_conn *new,
-			      struct nf_conntrack_expect *this);
-void nf_conntrack_q931_expect(struct nf_conn *new,
-			      struct nf_conntrack_expect *this);
 
 struct nfct_h323_nat_hooks {
 	int (*set_h245_addr)(struct sk_buff *skb, unsigned int protoff,
diff --git a/include/linux/netfilter/nf_conntrack_proto_gre.h b/include/linux/netfilter/nf_conntrack_proto_gre.h
index f33aa6021364..34ce5d2f37a2 100644
--- a/include/linux/netfilter/nf_conntrack_proto_gre.h
+++ b/include/linux/netfilter/nf_conntrack_proto_gre.h
@@ -25,7 +25,6 @@ struct nf_ct_gre_keymap {
 int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir,
 			 struct nf_conntrack_tuple *t);
 
-void nf_ct_gre_keymap_flush(struct net *net);
 /* delete keymap entries */
 void nf_ct_gre_keymap_destroy(struct nf_conn *ct);
 
diff --git a/include/linux/netfilter/nf_conntrack_sctp.h b/include/linux/netfilter/nf_conntrack_sctp.h
index 625f491b95de..fb31312825ae 100644
--- a/include/linux/netfilter/nf_conntrack_sctp.h
+++ b/include/linux/netfilter/nf_conntrack_sctp.h
@@ -9,6 +9,7 @@ struct ip_ct_sctp {
 	enum sctp_conntrack state;
 
 	__be32 vtag[IP_CT_DIR_MAX];
+	u8 init[IP_CT_DIR_MAX];
 	u8 last_dir;
 	u8 flags;
 };
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 5897f3dbaf7c..77c778d84d4c 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -51,21 +51,11 @@ static inline struct net_device *xt_in(const struct xt_action_param *par)
 	return par->state->in;
 }
 
-static inline const char *xt_inname(const struct xt_action_param *par)
-{
-	return par->state->in->name;
-}
-
 static inline struct net_device *xt_out(const struct xt_action_param *par)
 {
 	return par->state->out;
 }
 
-static inline const char *xt_outname(const struct xt_action_param *par)
-{
-	return par->state->out->name;
-}
-
 static inline unsigned int xt_hooknum(const struct xt_action_param *par)
 {
 	return par->state->hook;
@@ -357,7 +347,7 @@ extern struct static_key xt_tee_enabled;
  * Begin packet processing : all readers must wait the end
  * 1) Must be called with preemption disabled
  * 2) softirqs must be disabled too (or we should use this_cpu_add())
- * Returns :
+ * Returns:
  *  1 if no recursion on this cpu
  *  0 if recursion detected
  */
diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h
index f980edfdd278..743475ca7e9d 100644
--- a/include/linux/netfilter_bridge.h
+++ b/include/linux/netfilter_bridge.h
@@ -42,7 +42,7 @@ static inline int nf_bridge_get_physinif(const struct sk_buff *skb)
 	if (!nf_bridge)
 		return 0;
 
-	return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0;
+	return nf_bridge->physinif;
 }
 
 static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
@@ -56,11 +56,11 @@ static inline int nf_bridge_get_physoutif(const struct sk_buff *skb)
 }
 
 static inline struct net_device *
-nf_bridge_get_physindev(const struct sk_buff *skb)
+nf_bridge_get_physindev(const struct sk_buff *skb, struct net *net)
 {
 	const struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
-	return nf_bridge ? nf_bridge->physindev : NULL;
+	return nf_bridge ? dev_get_by_index_rcu(net, nf_bridge->physinif) : NULL;
 }
 
 static inline struct net_device *
diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h
index 7834c0be2831..61aa48f46dd7 100644
--- a/include/linux/netfilter_ipv6.h
+++ b/include/linux/netfilter_ipv6.h
@@ -51,7 +51,7 @@ struct nf_ipv6_ops {
 	u32 (*cookie_init_sequence)(const struct ipv6hdr *iph,
 				    const struct tcphdr *th, u16 *mssp);
 	int (*cookie_v6_check)(const struct ipv6hdr *iph,
-			       const struct tcphdr *th, __u32 cookie);
+			       const struct tcphdr *th);
 #endif
 	void (*route_input)(struct sk_buff *skb);
 	int (*fragment)(struct net *net, struct sock *sk, struct sk_buff *skb,
@@ -179,16 +179,16 @@ static inline u32 nf_ipv6_cookie_init_sequence(const struct ipv6hdr *iph,
 }
 
 static inline int nf_cookie_v6_check(const struct ipv6hdr *iph,
-				     const struct tcphdr *th, __u32 cookie)
+				     const struct tcphdr *th)
 {
 #if IS_ENABLED(CONFIG_SYN_COOKIES)
 #if IS_MODULE(CONFIG_IPV6)
 	const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops();
 
 	if (v6_ops)
-		return v6_ops->cookie_v6_check(iph, th, cookie);
+		return v6_ops->cookie_v6_check(iph, th);
 #elif IS_BUILTIN(CONFIG_IPV6)
-	return __cookie_v6_check(iph, th, cookie);
+	return __cookie_v6_check(iph, th);
 #endif
 #endif
 	return 0;
diff --git a/include/linux/netfilter_netdev.h b/include/linux/netfilter_netdev.h
index 8676316547cc..3175073a66ba 100644
--- a/include/linux/netfilter_netdev.h
+++ b/include/linux/netfilter_netdev.h
@@ -66,7 +66,6 @@ static inline bool nf_hook_egress_active(void)
  * @rc: result code which shall be returned by __dev_queue_xmit() on failure
  * @dev: netdev whose egress hooks shall be applied to @skb
  *
- * Returns @skb on success or %NULL if the packet was consumed or filtered.
  * Caller must hold rcu_read_lock.
  *
  * On ingress, packets are classified first by tc, then by netfilter.
@@ -81,6 +80,8 @@ static inline bool nf_hook_egress_active(void)
  * called recursively by tunnel drivers such as vxlan, the flag is reverted to
  * false after sch_handle_egress().  This ensures that netfilter is applied
  * both on the overlay and underlying network.
+ *
+ * Returns: @skb on success or %NULL if the packet was consumed or filtered.
  */
 static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc,
 					     struct net_device *dev)
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index a1f3522daa69..72ee7d210a74 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -18,117 +18,139 @@
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/uio.h>
+#include <linux/rolling_buffer.h>
 
 enum netfs_sreq_ref_trace;
-
-/*
- * Overload PG_private_2 to give us PG_fscache - this is used to indicate that
- * a page is currently backed by a local disk cache
- */
-#define folio_test_fscache(folio)	folio_test_private_2(folio)
-#define PageFsCache(page)		PagePrivate2((page))
-#define SetPageFsCache(page)		SetPagePrivate2((page))
-#define ClearPageFsCache(page)		ClearPagePrivate2((page))
-#define TestSetPageFsCache(page)	TestSetPagePrivate2((page))
-#define TestClearPageFsCache(page)	TestClearPagePrivate2((page))
+typedef struct mempool mempool_t;
+struct folio_queue;
 
 /**
- * folio_start_fscache - Start an fscache write on a folio.
+ * folio_start_private_2 - Start an fscache write on a folio.  [DEPRECATED]
  * @folio: The folio.
  *
  * Call this function before writing a folio to a local cache.  Starting a
  * second write before the first one finishes is not allowed.
+ *
+ * Note that this should no longer be used.
  */
-static inline void folio_start_fscache(struct folio *folio)
+static inline void folio_start_private_2(struct folio *folio)
 {
 	VM_BUG_ON_FOLIO(folio_test_private_2(folio), folio);
 	folio_get(folio);
 	folio_set_private_2(folio);
 }
 
-/**
- * folio_end_fscache - End an fscache write on a folio.
- * @folio: The folio.
- *
- * Call this function after the folio has been written to the local cache.
- * This will wake any sleepers waiting on this folio.
+enum netfs_io_source {
+	NETFS_SOURCE_UNKNOWN,
+	NETFS_FILL_WITH_ZEROES,
+	NETFS_DOWNLOAD_FROM_SERVER,
+	NETFS_READ_FROM_CACHE,
+	NETFS_INVALID_READ,
+	NETFS_UPLOAD_TO_SERVER,
+	NETFS_WRITE_TO_CACHE,
+} __mode(byte);
+
+typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error);
+
+/*
+ * Per-inode context.  This wraps the VFS inode.
  */
-static inline void folio_end_fscache(struct folio *folio)
-{
-	folio_end_private_2(folio);
-}
+struct netfs_inode {
+	struct inode		inode;		/* The VFS inode */
+	const struct netfs_request_ops *ops;
+#if IS_ENABLED(CONFIG_FSCACHE)
+	struct fscache_cookie	*cache;
+#endif
+	struct mutex		wb_lock;	/* Writeback serialisation */
+	loff_t			remote_i_size;	/* Size of the remote file */
+	loff_t			zero_point;	/* Size after which we assume there's no data
+						 * on the server */
+	atomic_t		io_count;	/* Number of outstanding reqs */
+	unsigned long		flags;
+#define NETFS_ICTX_ODIRECT	0		/* The file has DIO in progress */
+#define NETFS_ICTX_UNBUFFERED	1		/* I/O should not use the pagecache */
+#define NETFS_ICTX_MODIFIED_ATTR 3		/* Indicate change in mtime/ctime */
+#define NETFS_ICTX_SINGLE_NO_UPLOAD 4		/* Monolithic payload, cache but no upload */
+};
 
-/**
- * folio_wait_fscache - Wait for an fscache write on this folio to end.
- * @folio: The folio.
- *
- * If this folio is currently being written to a local cache, wait for
- * the write to finish.  Another write may start after this one finishes,
- * unless the caller holds the folio lock.
+/*
+ * A netfs group - for instance a ceph snap.  This is marked on dirty pages and
+ * pages marked with a group must be flushed before they can be written under
+ * the domain of another group.
  */
-static inline void folio_wait_fscache(struct folio *folio)
-{
-	folio_wait_private_2(folio);
-}
+struct netfs_group {
+	refcount_t		ref;
+	void (*free)(struct netfs_group *netfs_group);
+};
 
-/**
- * folio_wait_fscache_killable - Wait for an fscache write on this folio to end.
- * @folio: The folio.
- *
- * If this folio is currently being written to a local cache, wait
- * for the write to finish or for a fatal signal to be received.
- * Another write may start after this one finishes, unless the caller
- * holds the folio lock.
- *
- * Return:
- * - 0 if successful.
- * - -EINTR if a fatal signal was encountered.
+/*
+ * Information about a dirty page (attached only if necessary).
+ * folio->private
  */
-static inline int folio_wait_fscache_killable(struct folio *folio)
-{
-	return folio_wait_private_2_killable(folio);
-}
+struct netfs_folio {
+	struct netfs_group	*netfs_group;	/* Filesystem's grouping marker (or NULL). */
+	unsigned int		dirty_offset;	/* Write-streaming dirty data offset */
+	unsigned int		dirty_len;	/* Write-streaming dirty data length */
+};
+#define NETFS_FOLIO_INFO	0x1UL	/* OR'd with folio->private. */
+#define NETFS_FOLIO_COPY_TO_CACHE ((struct netfs_group *)0x356UL) /* Write to the cache only */
 
-static inline void set_page_fscache(struct page *page)
+static inline bool netfs_is_folio_info(const void *priv)
 {
-	folio_start_fscache(page_folio(page));
+	return (unsigned long)priv & NETFS_FOLIO_INFO;
 }
 
-static inline void end_page_fscache(struct page *page)
+static inline struct netfs_folio *__netfs_folio_info(const void *priv)
 {
-	folio_end_private_2(page_folio(page));
+	if (netfs_is_folio_info(priv))
+		return (struct netfs_folio *)((unsigned long)priv & ~NETFS_FOLIO_INFO);
+	return NULL;
 }
 
-static inline void wait_on_page_fscache(struct page *page)
+static inline struct netfs_folio *netfs_folio_info(struct folio *folio)
 {
-	folio_wait_private_2(page_folio(page));
+	return __netfs_folio_info(folio_get_private(folio));
 }
 
-static inline int wait_on_page_fscache_killable(struct page *page)
+static inline struct netfs_group *netfs_folio_group(struct folio *folio)
 {
-	return folio_wait_private_2_killable(page_folio(page));
-}
+	struct netfs_folio *finfo;
+	void *priv = folio_get_private(folio);
 
-enum netfs_io_source {
-	NETFS_FILL_WITH_ZEROES,
-	NETFS_DOWNLOAD_FROM_SERVER,
-	NETFS_READ_FROM_CACHE,
-	NETFS_INVALID_READ,
-} __mode(byte);
-
-typedef void (*netfs_io_terminated_t)(void *priv, ssize_t transferred_or_error,
-				      bool was_async);
+	finfo = netfs_folio_info(folio);
+	if (finfo)
+		return finfo->netfs_group;
+	return priv;
+}
 
 /*
- * Per-inode context.  This wraps the VFS inode.
+ * Stream of I/O subrequests going to a particular destination, such as the
+ * server or the local cache.  This is mainly intended for writing where we may
+ * have to write to multiple destinations concurrently.
  */
-struct netfs_inode {
-	struct inode		inode;		/* The VFS inode */
-	const struct netfs_request_ops *ops;
-#if IS_ENABLED(CONFIG_FSCACHE)
-	struct fscache_cookie	*cache;
-#endif
-	loff_t			remote_i_size;	/* Size of the remote file */
+struct netfs_io_stream {
+	/* Submission tracking */
+	struct netfs_io_subrequest *construct;	/* Op being constructed */
+	size_t			sreq_max_len;	/* Maximum size of a subrequest */
+	unsigned int		sreq_max_segs;	/* 0 or max number of segments in an iterator */
+	unsigned int		submit_off;	/* Folio offset we're submitting from */
+	unsigned int		submit_len;	/* Amount of data left to submit */
+	unsigned int		submit_extendable_to; /* Amount I/O can be rounded up to */
+	void (*prepare_write)(struct netfs_io_subrequest *subreq);
+	void (*issue_write)(struct netfs_io_subrequest *subreq);
+	/* Collection tracking */
+	struct list_head	subrequests;	/* Contributory I/O operations */
+	struct netfs_io_subrequest *front;	/* Op being collected */
+	unsigned long long	collected_to;	/* Position we've collected results to */
+	size_t			transferred;	/* The amount transferred from this stream */
+	unsigned short		error;		/* Aggregate error for the stream */
+	enum netfs_io_source	source;		/* Where to read from/write to */
+	unsigned char		stream_nr;	/* Index of stream in parent table */
+	bool			avail;		/* T if stream is available */
+	bool			active;		/* T if stream is active */
+	bool			need_retry;	/* T if this stream needs retrying */
+	bool			failed;		/* T if this stream failed */
+	bool			transferred_valid; /* T is ->transferred is valid */
 };
 
 /*
@@ -143,31 +165,54 @@ struct netfs_cache_resources {
 };
 
 /*
- * Descriptor for a single component subrequest.
+ * Descriptor for a single component subrequest.  Each operation represents an
+ * individual read/write from/to a server, a cache, a journal, etc..
+ *
+ * The buffer iterator is persistent for the life of the subrequest struct and
+ * the pages it points to can be relied on to exist for the duration.
  */
 struct netfs_io_subrequest {
 	struct netfs_io_request *rreq;		/* Supervising I/O request */
+	struct work_struct	work;
 	struct list_head	rreq_link;	/* Link in rreq->subrequests */
-	loff_t			start;		/* Where to start the I/O */
+	struct iov_iter		io_iter;	/* Iterator for this subrequest */
+	unsigned long long	start;		/* Where to start the I/O */
 	size_t			len;		/* Size of the I/O */
 	size_t			transferred;	/* Amount of data transferred */
 	refcount_t		ref;
 	short			error;		/* 0 or error that occurred */
 	unsigned short		debug_index;	/* Index in list (for debugging output) */
+	unsigned int		nr_segs;	/* Number of segs in io_iter */
+	u8			retry_count;	/* The number of retries (0 on initial pass) */
 	enum netfs_io_source	source;		/* Where to read from/write to */
+	unsigned char		stream_nr;	/* I/O stream this belongs to */
 	unsigned long		flags;
 #define NETFS_SREQ_COPY_TO_CACHE	0	/* Set if should copy the data to the cache */
 #define NETFS_SREQ_CLEAR_TAIL		1	/* Set if the rest of the read should be cleared */
-#define NETFS_SREQ_SHORT_IO		2	/* Set if the I/O was short */
-#define NETFS_SREQ_SEEK_DATA_READ	3	/* Set if ->read() should SEEK_DATA first */
-#define NETFS_SREQ_NO_PROGRESS		4	/* Set if we didn't manage to read any data */
+#define NETFS_SREQ_MADE_PROGRESS	4	/* Set if we transferred at least some data */
 #define NETFS_SREQ_ONDEMAND		5	/* Set if it's from on-demand read mode */
+#define NETFS_SREQ_BOUNDARY		6	/* Set if ends on hard boundary (eg. ceph object) */
+#define NETFS_SREQ_HIT_EOF		7	/* Set if short due to EOF */
+#define NETFS_SREQ_IN_PROGRESS		8	/* Unlocked when the subrequest completes */
+#define NETFS_SREQ_NEED_RETRY		9	/* Set if the filesystem requests a retry */
+#define NETFS_SREQ_FAILED		10	/* Set if the subreq failed unretryably */
 };
 
 enum netfs_io_origin {
 	NETFS_READAHEAD,		/* This read was triggered by readahead */
 	NETFS_READPAGE,			/* This read is a synchronous read */
+	NETFS_READ_GAPS,		/* This read is a synchronous read to fill gaps */
+	NETFS_READ_SINGLE,		/* This read should be treated as a single object */
 	NETFS_READ_FOR_WRITE,		/* This read is to prepare a write */
+	NETFS_UNBUFFERED_READ,		/* This is an unbuffered read */
+	NETFS_DIO_READ,			/* This is a direct I/O read */
+	NETFS_WRITEBACK,		/* This write was triggered by writepages */
+	NETFS_WRITEBACK_SINGLE,		/* This monolithic write was triggered by writepages */
+	NETFS_WRITETHROUGH,		/* This write was made by netfs_perform_write() */
+	NETFS_UNBUFFERED_WRITE,		/* This is an unbuffered write */
+	NETFS_DIO_WRITE,		/* This is a direct I/O write */
+	NETFS_PGPRIV2_COPY_TO_CACHE,	/* [DEPRECATED] This is writing read data to the cache */
+	nr__netfs_io_origin
 } __mode(byte);
 
 /*
@@ -175,30 +220,65 @@ enum netfs_io_origin {
  * operations to a variety of data stores and then stitch the result together.
  */
 struct netfs_io_request {
-	struct work_struct	work;
+	union {
+		struct work_struct cleanup_work; /* Deferred cleanup work */
+		struct rcu_head rcu;
+	};
+	struct work_struct	work;		/* Result collector work */
 	struct inode		*inode;		/* The file being accessed */
 	struct address_space	*mapping;	/* The mapping being accessed */
+	struct kiocb		*iocb;		/* AIO completion vector */
 	struct netfs_cache_resources cache_resources;
-	struct list_head	subrequests;	/* Contributory I/O operations */
+	struct netfs_io_request	*copy_to_cache;	/* Request to write just-read data to the cache */
+#ifdef CONFIG_PROC_FS
+	struct list_head	proc_link;	/* Link in netfs_iorequests */
+#endif
+	struct netfs_io_stream	io_streams[2];	/* Streams of parallel I/O operations */
+#define NR_IO_STREAMS 2 //wreq->nr_io_streams
+	struct netfs_group	*group;		/* Writeback group being written back */
+	struct rolling_buffer	buffer;		/* Unencrypted buffer */
+#define NETFS_ROLLBUF_PUT_MARK		ROLLBUF_MARK_1
+#define NETFS_ROLLBUF_PAGECACHE_MARK	ROLLBUF_MARK_2
+	wait_queue_head_t	waitq;		/* Processor waiter */
 	void			*netfs_priv;	/* Private data for the netfs */
+	void			*netfs_priv2;	/* Private data for the netfs */
+	struct bio_vec		*direct_bv;	/* DIO buffer list (when handling iovec-iter) */
+	unsigned long long	submitted;	/* Amount submitted for I/O so far */
+	unsigned long long	len;		/* Length of the request */
+	size_t			transferred;	/* Amount to be indicated as transferred */
+	long			error;		/* 0 or error that occurred */
+	unsigned long long	i_size;		/* Size of the file */
+	unsigned long long	start;		/* Start position */
+	atomic64_t		issued_to;	/* Write issuer folio cursor */
+	unsigned long long	collected_to;	/* Point we've collected to */
+	unsigned long long	cleaned_to;	/* Position we've cleaned folios to */
+	unsigned long long	abandon_to;	/* Position to abandon folios to */
+	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
+	unsigned int		direct_bv_count; /* Number of elements in direct_bv[] */
 	unsigned int		debug_id;
-	atomic_t		nr_outstanding;	/* Number of ops in progress */
-	atomic_t		nr_copy_ops;	/* Number of copy-to-cache ops in progress */
-	size_t			submitted;	/* Amount submitted for I/O so far */
-	size_t			len;		/* Length of the request */
-	short			error;		/* 0 or error that occurred */
+	unsigned int		rsize;		/* Maximum read size (0 for none) */
+	unsigned int		wsize;		/* Maximum write size (0 for none) */
+	atomic_t		subreq_counter;	/* Next subreq->debug_index */
+	unsigned int		nr_group_rel;	/* Number of refs to release on ->group */
+	spinlock_t		lock;		/* Lock for queuing subreqs */
+	unsigned char		front_folio_order; /* Order (size) of front folio */
 	enum netfs_io_origin	origin;		/* Origin of the request */
-	loff_t			i_size;		/* Size of the file */
-	loff_t			start;		/* Start position */
-	pgoff_t			no_unlock_folio; /* Don't unlock this folio after read */
+	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	refcount_t		ref;
 	unsigned long		flags;
-#define NETFS_RREQ_INCOMPLETE_IO	0	/* Some ioreqs terminated short or with error */
-#define NETFS_RREQ_COPY_TO_CACHE	1	/* Need to write to the cache */
-#define NETFS_RREQ_NO_UNLOCK_FOLIO	2	/* Don't unlock no_unlock_folio on completion */
-#define NETFS_RREQ_DONT_UNLOCK_FOLIOS	3	/* Don't unlock the folios on completion */
-#define NETFS_RREQ_FAILED		4	/* The request failed */
-#define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes */
+#define NETFS_RREQ_IN_PROGRESS		0	/* Unlocked when the request completes (has ref) */
+#define NETFS_RREQ_ALL_QUEUED		1	/* All subreqs are now queued */
+#define NETFS_RREQ_PAUSE		2	/* Pause subrequest generation */
+#define NETFS_RREQ_FAILED		3	/* The request failed */
+#define NETFS_RREQ_RETRYING		4	/* Set if we're in the retry path */
+#define NETFS_RREQ_SHORT_TRANSFER	5	/* Set if we have a short transfer */
+#define NETFS_RREQ_OFFLOAD_COLLECTION	8	/* Offload collection to workqueue */
+#define NETFS_RREQ_NO_UNLOCK_FOLIO	9	/* Don't unlock no_unlock_folio on completion */
+#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	10	/* Copy current folio to cache from read */
+#define NETFS_RREQ_UPLOAD_TO_SERVER	11	/* Need to write to the server */
+#define NETFS_RREQ_USE_IO_ITER		12	/* Use ->io_iter rather than ->i_pages */
+#define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
+						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
 };
 
@@ -206,17 +286,31 @@ struct netfs_io_request {
  * Operations the network filesystem can/must provide to the helpers.
  */
 struct netfs_request_ops {
+	mempool_t *request_pool;
+	mempool_t *subrequest_pool;
 	int (*init_request)(struct netfs_io_request *rreq, struct file *file);
 	void (*free_request)(struct netfs_io_request *rreq);
-	int (*begin_cache_operation)(struct netfs_io_request *rreq);
+	void (*free_subrequest)(struct netfs_io_subrequest *rreq);
 
+	/* Read request handling */
 	void (*expand_readahead)(struct netfs_io_request *rreq);
-	bool (*clamp_length)(struct netfs_io_subrequest *subreq);
+	int (*prepare_read)(struct netfs_io_subrequest *subreq);
 	void (*issue_read)(struct netfs_io_subrequest *subreq);
 	bool (*is_still_valid)(struct netfs_io_request *rreq);
 	int (*check_write_begin)(struct file *file, loff_t pos, unsigned len,
 				 struct folio **foliop, void **_fsdata);
 	void (*done)(struct netfs_io_request *rreq);
+
+	/* Modification handling */
+	void (*update_i_size)(struct inode *inode, loff_t i_size);
+	void (*post_modify)(struct inode *inode);
+
+	/* Write request handling */
+	void (*begin_writeback)(struct netfs_io_request *wreq);
+	void (*prepare_write)(struct netfs_io_subrequest *subreq);
+	void (*issue_write)(struct netfs_io_subrequest *subreq);
+	void (*retry_request)(struct netfs_io_request *wreq, struct netfs_io_stream *stream);
+	void (*invalidate_cache)(struct netfs_io_request *wreq);
 };
 
 /*
@@ -224,13 +318,11 @@ struct netfs_request_ops {
  */
 enum netfs_read_from_hole {
 	NETFS_READ_HOLE_IGNORE,
-	NETFS_READ_HOLE_CLEAR,
 	NETFS_READ_HOLE_FAIL,
 };
 
 /*
- * Table of operations for access to a cache.  This is obtained by
- * rreq->ops->begin_cache_operation().
+ * Table of operations for access to a cache.
  */
 struct netfs_cache_ops {
 	/* End an operation */
@@ -251,22 +343,34 @@ struct netfs_cache_ops {
 		     netfs_io_terminated_t term_func,
 		     void *term_func_priv);
 
+	/* Write data to the cache from a netfs subrequest. */
+	void (*issue_write)(struct netfs_io_subrequest *subreq);
+
 	/* Expand readahead request */
 	void (*expand_readahead)(struct netfs_cache_resources *cres,
-				 loff_t *_start, size_t *_len, loff_t i_size);
+				 unsigned long long *_start,
+				 unsigned long long *_len,
+				 unsigned long long i_size);
 
 	/* Prepare a read operation, shortening it to a cached/uncached
 	 * boundary as appropriate.
 	 */
 	enum netfs_io_source (*prepare_read)(struct netfs_io_subrequest *subreq,
-					     loff_t i_size);
+					     unsigned long long i_size);
+
+	/* Prepare a write subrequest, working out if we're allowed to do it
+	 * and finding out the maximum amount of data to gather before
+	 * attempting to submit.  If we're not permitted to do it, the
+	 * subrequest should be marked failed.
+	 */
+	void (*prepare_write_subreq)(struct netfs_io_subrequest *subreq);
 
 	/* Prepare a write operation, working out what part of the write we can
 	 * actually do.
 	 */
 	int (*prepare_write)(struct netfs_cache_resources *cres,
-			     loff_t *_start, size_t *_len, loff_t i_size,
-			     bool no_space_allocated_yet);
+			     loff_t *_start, size_t *_len, size_t upper_len,
+			     loff_t i_size, bool no_space_allocated_yet);
 
 	/* Prepare an on-demand read operation, shortening it to a cached/uncached
 	 * boundary as appropriate.
@@ -284,26 +388,80 @@ struct netfs_cache_ops {
 			       loff_t *_data_start, size_t *_data_len);
 };
 
+/* High-level read API. */
+ssize_t netfs_unbuffered_read_iter_locked(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_unbuffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_buffered_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+ssize_t netfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter);
+
+/* High-level write API */
+ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+			    struct netfs_group *netfs_group);
+ssize_t netfs_buffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *from,
+					 struct netfs_group *netfs_group);
+ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from);
+ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *iter,
+					   struct netfs_group *netfs_group);
+ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from);
+
+/* Single, monolithic object read/write API. */
+void netfs_single_mark_inode_dirty(struct inode *inode);
+ssize_t netfs_read_single(struct inode *inode, struct file *file, struct iov_iter *iter);
+int netfs_writeback_single(struct address_space *mapping,
+			   struct writeback_control *wbc,
+			   struct iov_iter *iter);
+
+/* Address operations API */
 struct readahead_control;
 void netfs_readahead(struct readahead_control *);
 int netfs_read_folio(struct file *, struct folio *);
 int netfs_write_begin(struct netfs_inode *, struct file *,
-		struct address_space *, loff_t pos, unsigned int len,
-		struct folio **, void **fsdata);
-
-void netfs_subreq_terminated(struct netfs_io_subrequest *, ssize_t, bool);
+		      struct address_space *, loff_t pos, unsigned int len,
+		      struct folio **, void **fsdata);
+int netfs_writepages(struct address_space *mapping,
+		     struct writeback_control *wbc);
+bool netfs_dirty_folio(struct address_space *mapping, struct folio *folio);
+int netfs_unpin_writeback(struct inode *inode, struct writeback_control *wbc);
+void netfs_clear_inode_writeback(struct inode *inode, const void *aux);
+void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length);
+bool netfs_release_folio(struct folio *folio, gfp_t gfp);
+
+/* VMA operations API. */
+vm_fault_t netfs_page_mkwrite(struct vm_fault *vmf, struct netfs_group *netfs_group);
+
+/* (Sub)request management API. */
+void netfs_read_subreq_progress(struct netfs_io_subrequest *subreq);
+void netfs_read_subreq_terminated(struct netfs_io_subrequest *subreq);
 void netfs_get_subrequest(struct netfs_io_subrequest *subreq,
 			  enum netfs_sreq_ref_trace what);
 void netfs_put_subrequest(struct netfs_io_subrequest *subreq,
-			  bool was_async, enum netfs_sreq_ref_trace what);
-void netfs_stats_show(struct seq_file *);
+			  enum netfs_sreq_ref_trace what);
 ssize_t netfs_extract_user_iter(struct iov_iter *orig, size_t orig_len,
 				struct iov_iter *new,
 				iov_iter_extraction_t extraction_flags);
-struct sg_table;
-ssize_t netfs_extract_iter_to_sg(struct iov_iter *iter, size_t len,
-				 struct sg_table *sgtable, unsigned int sg_max,
-				 iov_iter_extraction_t extraction_flags);
+size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
+			size_t max_size, size_t max_segs);
+void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq);
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error);
+
+int netfs_start_io_read(struct inode *inode);
+void netfs_end_io_read(struct inode *inode);
+int netfs_start_io_write(struct inode *inode);
+void netfs_end_io_write(struct inode *inode);
+int netfs_start_io_direct(struct inode *inode);
+void netfs_end_io_direct(struct inode *inode);
+
+/* Miscellaneous APIs. */
+struct folio_queue *netfs_folioq_alloc(unsigned int rreq_id, gfp_t gfp,
+				       unsigned int trace /*enum netfs_folioq_trace*/);
+void netfs_folioq_free(struct folio_queue *folioq,
+		       unsigned int trace /*enum netfs_trace_folioq*/);
+
+/* Buffer wrangling helpers API. */
+int netfs_alloc_folioq_buffer(struct address_space *mapping,
+			      struct folio_queue **_buffer,
+			      size_t *_cur_size, ssize_t size, gfp_t gfp);
+void netfs_free_folioq_buffer(struct folio_queue *fq);
 
 /**
  * netfs_inode - Get the netfs inode context from the inode
@@ -321,30 +479,46 @@ static inline struct netfs_inode *netfs_inode(struct inode *inode)
  * netfs_inode_init - Initialise a netfslib inode context
  * @ctx: The netfs inode to initialise
  * @ops: The netfs's operations list
+ * @use_zero_point: True to use the zero_point read optimisation
  *
  * Initialise the netfs library context struct.  This is expected to follow on
  * directly from the VFS inode struct.
  */
 static inline void netfs_inode_init(struct netfs_inode *ctx,
-				    const struct netfs_request_ops *ops)
+				    const struct netfs_request_ops *ops,
+				    bool use_zero_point)
 {
 	ctx->ops = ops;
 	ctx->remote_i_size = i_size_read(&ctx->inode);
+	ctx->zero_point = LLONG_MAX;
+	ctx->flags = 0;
+	atomic_set(&ctx->io_count, 0);
 #if IS_ENABLED(CONFIG_FSCACHE)
 	ctx->cache = NULL;
 #endif
+	mutex_init(&ctx->wb_lock);
+	/* ->releasepage() drives zero_point */
+	if (use_zero_point) {
+		ctx->zero_point = ctx->remote_i_size;
+		mapping_set_release_always(ctx->inode.i_mapping);
+	}
 }
 
 /**
  * netfs_resize_file - Note that a file got resized
  * @ctx: The netfs inode being resized
  * @new_i_size: The new file size
+ * @changed_on_server: The change was applied to the server
  *
  * Inform the netfs lib that a file got resized so that it can adjust its state.
  */
-static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size)
+static inline void netfs_resize_file(struct netfs_inode *ctx, loff_t new_i_size,
+				     bool changed_on_server)
 {
-	ctx->remote_i_size = new_i_size;
+	if (changed_on_server)
+		ctx->remote_i_size = new_i_size;
+	if (new_i_size < ctx->zero_point)
+		ctx->zero_point = new_i_size;
 }
 
 /**
@@ -362,4 +536,20 @@ static inline struct fscache_cookie *netfs_i_cookie(struct netfs_inode *ctx)
 #endif
 }
 
+/**
+ * netfs_wait_for_outstanding_io - Wait for outstanding I/O to complete
+ * @inode: The netfs inode to wait on
+ *
+ * Wait for outstanding I/O requests of any type to complete.  This is intended
+ * to be called from inode eviction routines.  This makes sure that any
+ * resources held by those requests are cleaned up before we let the inode get
+ * cleaned up.
+ */
+static inline void netfs_wait_for_outstanding_io(struct inode *inode)
+{
+	struct netfs_inode *ictx = netfs_inode(inode);
+
+	wait_var_event(&ictx->io_count, atomic_read(&ictx->io_count) == 0);
+}
+
 #endif /* _LINUX_NETFS_H */
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 19c0791ed9d5..882e9c1b6c1d 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -34,6 +34,7 @@ struct netlink_skb_parms {
 
 #define NETLINK_CB(skb)		(*(struct netlink_skb_parms*)&((skb)->cb))
 #define NETLINK_CREDS(skb)	(&NETLINK_CB((skb)).creds)
+#define NETLINK_CTX_SIZE	48
 
 
 void netlink_table_grab(void);
@@ -47,9 +48,9 @@ struct netlink_kernel_cfg {
 	unsigned int	groups;
 	unsigned int	flags;
 	void		(*input)(struct sk_buff *skb);
-	struct mutex	*cb_mutex;
 	int		(*bind)(struct net *net, int group);
 	void		(*unbind)(struct net *net, int group);
+	void            (*release) (struct sock *sk, unsigned long *groups);
 };
 
 struct sock *__netlink_kernel_create(struct net *net, int unit,
@@ -62,7 +63,7 @@ netlink_kernel_create(struct net *net, int unit, struct netlink_kernel_cfg *cfg)
 }
 
 /* this can be increased when necessary - don't expose to userland */
-#define NETLINK_MAX_COOKIE_LEN	20
+#define NETLINK_MAX_COOKIE_LEN	8
 #define NETLINK_MAX_FMTMSG_LEN	80
 
 /**
@@ -211,6 +212,7 @@ static inline void nl_set_extack_cookie_u64(struct netlink_ext_ack *extack,
 {
 	if (!extack)
 		return;
+	BUILD_BUG_ON(sizeof(extack->cookie) < sizeof(cookie));
 	memcpy(extack->cookie, &cookie, sizeof(cookie));
 	extack->cookie_len = sizeof(cookie);
 }
@@ -227,12 +229,19 @@ bool netlink_strict_get_check(struct sk_buff *skb);
 int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 portid, int nonblock);
 int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 portid,
 		      __u32 group, gfp_t allocation);
+
+typedef int (*netlink_filter_fn)(struct sock *dsk, struct sk_buff *skb, void *data);
+
+int netlink_broadcast_filtered(struct sock *ssk, struct sk_buff *skb,
+			       __u32 portid, __u32 group, gfp_t allocation,
+			       netlink_filter_fn filter,
+			       void *filter_data);
 int netlink_set_err(struct sock *ssk, __u32 portid, __u32 group, int code);
 int netlink_register_notifier(struct notifier_block *nb);
 int netlink_unregister_notifier(struct notifier_block *nb);
 
 /* finegrained unicast helpers: */
-struct sock *netlink_getsockbyfilp(struct file *filp);
+struct sock *netlink_getsockbyfd(int fd);
 int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 		      long *timeo, struct sock *ssk);
 void netlink_detachskb(struct sock *sk, struct sk_buff *skb);
@@ -283,9 +292,10 @@ struct netlink_callback {
 	u16			answer_flags;
 	u32			min_dump_alloc;
 	unsigned int		prev_seq, seq;
+	int			flags;
 	bool			strict_check;
 	union {
-		u8		ctx[48];
+		u8		ctx[NETLINK_CTX_SIZE];
 
 		/* args is deprecated. Cast a struct over ctx instead
 		 * for proper type safety.
@@ -294,7 +304,7 @@ struct netlink_callback {
 	};
 };
 
-#define NL_ASSERT_DUMP_CTX_FITS(type_name)				\
+#define NL_ASSERT_CTX_FITS(type_name)					\
 	BUILD_BUG_ON(sizeof(type_name) >				\
 		     sizeof_field(struct netlink_callback, ctx))
 
@@ -311,9 +321,11 @@ struct netlink_dump_control {
 	int (*start)(struct netlink_callback *);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *);
 	int (*done)(struct netlink_callback *);
+	struct netlink_ext_ack *extack;
 	void *data;
 	struct module *module;
 	u32 min_dump_alloc;
+	int flags;
 };
 
 int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
@@ -344,5 +356,6 @@ bool netlink_ns_capable(const struct sk_buff *skb,
 			struct user_namespace *ns, int cap);
 bool netlink_capable(const struct sk_buff *skb, int cap);
 bool netlink_net_capable(const struct sk_buff *skb, int cap);
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast);
 
 #endif	/* __LINUX_NETLINK_H */
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index bd19c4b91e31..f22eec466040 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -15,25 +15,37 @@
 #include <linux/refcount.h>
 
 union inet_addr {
-	__u32		all[4];
 	__be32		ip;
-	__be32		ip6[4];
-	struct in_addr	in;
 	struct in6_addr	in6;
 };
 
 struct netpoll {
 	struct net_device *dev;
 	netdevice_tracker dev_tracker;
+	/*
+	 * Either dev_name or dev_mac can be used to specify the local
+	 * interface - dev_name is used if it is a nonempty string, else
+	 * dev_mac is used.
+	 */
 	char dev_name[IFNAMSIZ];
+	u8 dev_mac[ETH_ALEN];
 	const char *name;
 
 	union inet_addr local_ip, remote_ip;
 	bool ipv6;
 	u16 local_port, remote_port;
 	u8 remote_mac[ETH_ALEN];
+	struct sk_buff_head skb_pool;
+	struct work_struct refill_wq;
 };
 
+#define np_info(np, fmt, ...)				\
+	pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_err(np, fmt, ...)				\
+	pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_notice(np, fmt, ...)				\
+	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
+
 struct netpoll_info {
 	refcount_t refcnt;
 
@@ -43,7 +55,6 @@ struct netpoll_info {
 
 	struct delayed_work tx_work;
 
-	struct netpoll *netpoll;
 	struct rcu_head rcu;
 };
 
@@ -56,14 +67,12 @@ static inline void netpoll_poll_disable(struct net_device *dev) { return; }
 static inline void netpoll_poll_enable(struct net_device *dev) { return; }
 #endif
 
-void netpoll_send_udp(struct netpoll *np, const char *msg, int len);
-void netpoll_print_options(struct netpoll *np);
-int netpoll_parse_options(struct netpoll *np, char *opt);
+int netpoll_send_udp(struct netpoll *np, const char *msg, int len);
 int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
 int netpoll_setup(struct netpoll *np);
-void __netpoll_cleanup(struct netpoll *np);
 void __netpoll_free(struct netpoll *np);
 void netpoll_cleanup(struct netpoll *np);
+void do_netpoll_cleanup(struct netpoll *np);
 netdev_tx_t netpoll_send_skb(struct netpoll *np, struct sk_buff *skb);
 
 #ifdef CONFIG_NETPOLL
@@ -71,7 +80,7 @@ static inline void *netpoll_poll_lock(struct napi_struct *napi)
 {
 	struct net_device *dev = napi->dev;
 
-	if (dev && dev->npinfo) {
+	if (dev && rcu_access_pointer(dev->npinfo)) {
 		int owner = smp_processor_id();
 
 		while (cmpxchg(&napi->poll_owner, -1, owner) != -1)
diff --git a/include/linux/nfs.h b/include/linux/nfs.h
index ceb70a926b95..0906a0b40c6a 100644
--- a/include/linux/nfs.h
+++ b/include/linux/nfs.h
@@ -8,11 +8,20 @@
 #ifndef _LINUX_NFS_H
 #define _LINUX_NFS_H
 
+#include <linux/cred.h>
+#include <linux/sunrpc/auth.h>
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/string.h>
 #include <linux/crc32.h>
 #include <uapi/linux/nfs.h>
 
+/* The LOCALIO program is entirely private to Linux and is
+ * NOT part of the uapi.
+ */
+#define NFS_LOCALIO_PROGRAM		400122
+#define LOCALIOPROC_NULL		0
+#define LOCALIOPROC_UUID_IS_LOCAL	1
+
 /*
  * This is the kernel NFS client file handle representation
  */
@@ -46,7 +55,6 @@ enum nfs3_stable_how {
 	NFS_INVALID_STABLE_HOW = -1
 };
 
-#ifdef CONFIG_CRC32
 /**
  * nfs_fhandle_hash - calculate the crc32 hash for the filehandle
  * @fh - pointer to filehandle
@@ -58,10 +66,4 @@ static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
 {
 	return ~crc32_le(0xFFFFFFFF, &fh->data[0], fh->size);
 }
-#else /* CONFIG_CRC32 */
-static inline u32 nfs_fhandle_hash(const struct nfs_fh *fh)
-{
-	return 0;
-}
-#endif /* CONFIG_CRC32 */
 #endif /* _LINUX_NFS_H */
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 730003c4f4af..e947af6a3684 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -17,6 +17,7 @@
 #include <linux/uidgid.h>
 #include <uapi/linux/nfs4.h>
 #include <linux/sunrpc/msg_prot.h>
+#include <linux/sunrpc/xdrgen/nfs4_1.h>
 
 enum nfs4_acl_whotype {
 	NFS4_ACL_WHO_NAMED = 0,
@@ -46,6 +47,7 @@ struct nfs4_acl {
 struct nfs4_label {
 	uint32_t	lfs;
 	uint32_t	pi;
+	u32		lsmid;
 	u32		len;
 	char	*label;
 };
@@ -70,6 +72,7 @@ struct nfs4_stateid_struct {
 		NFS4_LAYOUT_STATEID_TYPE,
 		NFS4_PNFS_DS_STATEID_TYPE,
 		NFS4_REVOKED_STATEID_TYPE,
+		NFS4_FREED_STATEID_TYPE,
 	} type;
 };
 
@@ -150,7 +153,7 @@ enum nfs_opnum4 {
 	OP_WRITE_SAME = 70,
 	OP_CLONE = 71,
 
-	/* xattr support (RFC8726) */
+	/* xattr support (RFC8276) */
 	OP_GETXATTR                = 72,
 	OP_SETXATTR                = 73,
 	OP_LISTXATTRS              = 74,
@@ -281,20 +284,24 @@ enum nfsstat4 {
 	/* nfs42 */
 	NFS4ERR_PARTNER_NOTSUPP	= 10088,
 	NFS4ERR_PARTNER_NO_AUTH	= 10089,
-	NFS4ERR_UNION_NOTSUPP = 10090,
-	NFS4ERR_OFFLOAD_DENIED = 10091,
-	NFS4ERR_WRONG_LFS = 10092,
-	NFS4ERR_BADLABEL = 10093,
-	NFS4ERR_OFFLOAD_NO_REQS = 10094,
+	NFS4ERR_UNION_NOTSUPP	= 10090,
+	NFS4ERR_OFFLOAD_DENIED	= 10091,
+	NFS4ERR_WRONG_LFS	= 10092,
+	NFS4ERR_BADLABEL	= 10093,
+	NFS4ERR_OFFLOAD_NO_REQS	= 10094,
 
 	/* xattr (RFC8276) */
-	NFS4ERR_NOXATTR        = 10095,
-	NFS4ERR_XATTR2BIG      = 10096,
+	NFS4ERR_NOXATTR		= 10095,
+	NFS4ERR_XATTR2BIG	= 10096,
+
+	/* can be used for internal errors */
+	NFS4ERR_FIRST_FREE
 };
 
 /* error codes for internal client use */
 #define NFS4ERR_RESET_TO_MDS   12001
 #define NFS4ERR_RESET_TO_PNFS  12002
+#define NFS4ERR_FATAL_IOERROR  12003
 
 static inline bool seqid_mutating_err(u32 err)
 {
@@ -362,11 +369,13 @@ enum limit_by4 {
 	NFS4_LIMIT_BLOCKS = 2
 };
 
-enum open_delegation_type4 {
+enum nfs4_open_delegation_type4 {
 	NFS4_OPEN_DELEGATE_NONE = 0,
 	NFS4_OPEN_DELEGATE_READ = 1,
 	NFS4_OPEN_DELEGATE_WRITE = 2,
 	NFS4_OPEN_DELEGATE_NONE_EXT = 3, /* 4.1 */
+	NFS4_OPEN_DELEGATE_READ_ATTRS_DELEG = 4,
+	NFS4_OPEN_DELEGATE_WRITE_ATTRS_DELEG = 5,
 };
 
 enum why_no_delegation4 { /* new to v4.1 */
@@ -389,79 +398,206 @@ enum lock_type4 {
 	NFS4_WRITEW_LT = 4
 };
 
+/*
+ * Symbol names and values are from RFC 7531 Section 2.
+ * "XDR Description of NFSv4.0"
+ */
+enum {
+	FATTR4_SUPPORTED_ATTRS		= 0,
+	FATTR4_TYPE			= 1,
+	FATTR4_FH_EXPIRE_TYPE		= 2,
+	FATTR4_CHANGE			= 3,
+	FATTR4_SIZE			= 4,
+	FATTR4_LINK_SUPPORT		= 5,
+	FATTR4_SYMLINK_SUPPORT		= 6,
+	FATTR4_NAMED_ATTR		= 7,
+	FATTR4_FSID			= 8,
+	FATTR4_UNIQUE_HANDLES		= 9,
+	FATTR4_LEASE_TIME		= 10,
+	FATTR4_RDATTR_ERROR		= 11,
+	FATTR4_ACL			= 12,
+	FATTR4_ACLSUPPORT		= 13,
+	FATTR4_ARCHIVE			= 14,
+	FATTR4_CANSETTIME		= 15,
+	FATTR4_CASE_INSENSITIVE		= 16,
+	FATTR4_CASE_PRESERVING		= 17,
+	FATTR4_CHOWN_RESTRICTED		= 18,
+	FATTR4_FILEHANDLE		= 19,
+	FATTR4_FILEID			= 20,
+	FATTR4_FILES_AVAIL		= 21,
+	FATTR4_FILES_FREE		= 22,
+	FATTR4_FILES_TOTAL		= 23,
+	FATTR4_FS_LOCATIONS		= 24,
+	FATTR4_HIDDEN			= 25,
+	FATTR4_HOMOGENEOUS		= 26,
+	FATTR4_MAXFILESIZE		= 27,
+	FATTR4_MAXLINK			= 28,
+	FATTR4_MAXNAME			= 29,
+	FATTR4_MAXREAD			= 30,
+	FATTR4_MAXWRITE			= 31,
+	FATTR4_MIMETYPE			= 32,
+	FATTR4_MODE			= 33,
+	FATTR4_NO_TRUNC			= 34,
+	FATTR4_NUMLINKS			= 35,
+	FATTR4_OWNER			= 36,
+	FATTR4_OWNER_GROUP		= 37,
+	FATTR4_QUOTA_AVAIL_HARD		= 38,
+	FATTR4_QUOTA_AVAIL_SOFT		= 39,
+	FATTR4_QUOTA_USED		= 40,
+	FATTR4_RAWDEV			= 41,
+	FATTR4_SPACE_AVAIL		= 42,
+	FATTR4_SPACE_FREE		= 43,
+	FATTR4_SPACE_TOTAL		= 44,
+	FATTR4_SPACE_USED		= 45,
+	FATTR4_SYSTEM			= 46,
+	FATTR4_TIME_ACCESS		= 47,
+	FATTR4_TIME_ACCESS_SET		= 48,
+	FATTR4_TIME_BACKUP		= 49,
+	FATTR4_TIME_CREATE		= 50,
+	FATTR4_TIME_DELTA		= 51,
+	FATTR4_TIME_METADATA		= 52,
+	FATTR4_TIME_MODIFY		= 53,
+	FATTR4_TIME_MODIFY_SET		= 54,
+	FATTR4_MOUNTED_ON_FILEID	= 55,
+};
+
+/*
+ * Symbol names and values are from RFC 5662 Section 2.
+ * "XDR Description of NFSv4.1"
+ */
+enum {
+	FATTR4_DIR_NOTIF_DELAY		= 56,
+	FATTR4_DIRENT_NOTIF_DELAY	= 57,
+	FATTR4_DACL			= 58,
+	FATTR4_SACL			= 59,
+	FATTR4_CHANGE_POLICY		= 60,
+	FATTR4_FS_STATUS		= 61,
+	FATTR4_FS_LAYOUT_TYPES		= 62,
+	FATTR4_LAYOUT_HINT		= 63,
+	FATTR4_LAYOUT_TYPES		= 64,
+	FATTR4_LAYOUT_BLKSIZE		= 65,
+	FATTR4_LAYOUT_ALIGNMENT		= 66,
+	FATTR4_FS_LOCATIONS_INFO	= 67,
+	FATTR4_MDSTHRESHOLD		= 68,
+	FATTR4_RETENTION_GET		= 69,
+	FATTR4_RETENTION_SET		= 70,
+	FATTR4_RETENTEVT_GET		= 71,
+	FATTR4_RETENTEVT_SET		= 72,
+	FATTR4_RETENTION_HOLD		= 73,
+	FATTR4_MODE_SET_MASKED		= 74,
+	FATTR4_SUPPATTR_EXCLCREAT	= 75,
+	FATTR4_FS_CHARSET_CAP		= 76,
+};
+
+/*
+ * Symbol names and values are from RFC 7863 Section 2.
+ * "XDR Description of NFSv4.2"
+ */
+enum {
+	FATTR4_CLONE_BLKSIZE		= 77,
+	FATTR4_SPACE_FREED		= 78,
+	FATTR4_CHANGE_ATTR_TYPE		= 79,
+	FATTR4_SEC_LABEL		= 80,
+};
+
+/*
+ * Symbol names and values are from RFC 8275 Section 5.
+ * "The mode_umask Attribute"
+ */
+enum {
+	FATTR4_MODE_UMASK		= 81,
+};
+
+/*
+ * Symbol names and values are from RFC 8276 Section 8.6.
+ * "Numeric Values Assigned to Protocol Extensions"
+ */
+enum {
+	FATTR4_XATTR_SUPPORT		= 82,
+};
+
+/*
+ * The following internal definitions enable processing the above
+ * attribute bits within 32-bit word boundaries.
+ */
 
 /* Mandatory Attributes */
-#define FATTR4_WORD0_SUPPORTED_ATTRS    (1UL << 0)
-#define FATTR4_WORD0_TYPE               (1UL << 1)
-#define FATTR4_WORD0_FH_EXPIRE_TYPE     (1UL << 2)
-#define FATTR4_WORD0_CHANGE             (1UL << 3)
-#define FATTR4_WORD0_SIZE               (1UL << 4)
-#define FATTR4_WORD0_LINK_SUPPORT       (1UL << 5)
-#define FATTR4_WORD0_SYMLINK_SUPPORT    (1UL << 6)
-#define FATTR4_WORD0_NAMED_ATTR         (1UL << 7)
-#define FATTR4_WORD0_FSID               (1UL << 8)
-#define FATTR4_WORD0_UNIQUE_HANDLES     (1UL << 9)
-#define FATTR4_WORD0_LEASE_TIME         (1UL << 10)
-#define FATTR4_WORD0_RDATTR_ERROR       (1UL << 11)
+#define FATTR4_WORD0_SUPPORTED_ATTRS    BIT(FATTR4_SUPPORTED_ATTRS)
+#define FATTR4_WORD0_TYPE               BIT(FATTR4_TYPE)
+#define FATTR4_WORD0_FH_EXPIRE_TYPE     BIT(FATTR4_FH_EXPIRE_TYPE)
+#define FATTR4_WORD0_CHANGE             BIT(FATTR4_CHANGE)
+#define FATTR4_WORD0_SIZE               BIT(FATTR4_SIZE)
+#define FATTR4_WORD0_LINK_SUPPORT       BIT(FATTR4_LINK_SUPPORT)
+#define FATTR4_WORD0_SYMLINK_SUPPORT    BIT(FATTR4_SYMLINK_SUPPORT)
+#define FATTR4_WORD0_NAMED_ATTR         BIT(FATTR4_NAMED_ATTR)
+#define FATTR4_WORD0_FSID               BIT(FATTR4_FSID)
+#define FATTR4_WORD0_UNIQUE_HANDLES     BIT(FATTR4_UNIQUE_HANDLES)
+#define FATTR4_WORD0_LEASE_TIME         BIT(FATTR4_LEASE_TIME)
+#define FATTR4_WORD0_RDATTR_ERROR       BIT(FATTR4_RDATTR_ERROR)
 /* Mandatory in NFSv4.1 */
-#define FATTR4_WORD2_SUPPATTR_EXCLCREAT (1UL << 11)
+#define FATTR4_WORD2_SUPPATTR_EXCLCREAT BIT(FATTR4_SUPPATTR_EXCLCREAT - 64)
 
 /* Recommended Attributes */
-#define FATTR4_WORD0_ACL                (1UL << 12)
-#define FATTR4_WORD0_ACLSUPPORT         (1UL << 13)
-#define FATTR4_WORD0_ARCHIVE            (1UL << 14)
-#define FATTR4_WORD0_CANSETTIME         (1UL << 15)
-#define FATTR4_WORD0_CASE_INSENSITIVE   (1UL << 16)
-#define FATTR4_WORD0_CASE_PRESERVING    (1UL << 17)
-#define FATTR4_WORD0_CHOWN_RESTRICTED   (1UL << 18)
-#define FATTR4_WORD0_FILEHANDLE         (1UL << 19)
-#define FATTR4_WORD0_FILEID             (1UL << 20)
-#define FATTR4_WORD0_FILES_AVAIL        (1UL << 21)
-#define FATTR4_WORD0_FILES_FREE         (1UL << 22)
-#define FATTR4_WORD0_FILES_TOTAL        (1UL << 23)
-#define FATTR4_WORD0_FS_LOCATIONS       (1UL << 24)
-#define FATTR4_WORD0_HIDDEN             (1UL << 25)
-#define FATTR4_WORD0_HOMOGENEOUS        (1UL << 26)
-#define FATTR4_WORD0_MAXFILESIZE        (1UL << 27)
-#define FATTR4_WORD0_MAXLINK            (1UL << 28)
-#define FATTR4_WORD0_MAXNAME            (1UL << 29)
-#define FATTR4_WORD0_MAXREAD            (1UL << 30)
-#define FATTR4_WORD0_MAXWRITE           (1UL << 31)
-#define FATTR4_WORD1_MIMETYPE           (1UL << 0)
-#define FATTR4_WORD1_MODE               (1UL << 1)
-#define FATTR4_WORD1_NO_TRUNC           (1UL << 2)
-#define FATTR4_WORD1_NUMLINKS           (1UL << 3)
-#define FATTR4_WORD1_OWNER              (1UL << 4)
-#define FATTR4_WORD1_OWNER_GROUP        (1UL << 5)
-#define FATTR4_WORD1_QUOTA_HARD         (1UL << 6)
-#define FATTR4_WORD1_QUOTA_SOFT         (1UL << 7)
-#define FATTR4_WORD1_QUOTA_USED         (1UL << 8)
-#define FATTR4_WORD1_RAWDEV             (1UL << 9)
-#define FATTR4_WORD1_SPACE_AVAIL        (1UL << 10)
-#define FATTR4_WORD1_SPACE_FREE         (1UL << 11)
-#define FATTR4_WORD1_SPACE_TOTAL        (1UL << 12)
-#define FATTR4_WORD1_SPACE_USED         (1UL << 13)
-#define FATTR4_WORD1_SYSTEM             (1UL << 14)
-#define FATTR4_WORD1_TIME_ACCESS        (1UL << 15)
-#define FATTR4_WORD1_TIME_ACCESS_SET    (1UL << 16)
-#define FATTR4_WORD1_TIME_BACKUP        (1UL << 17)
-#define FATTR4_WORD1_TIME_CREATE        (1UL << 18)
-#define FATTR4_WORD1_TIME_DELTA         (1UL << 19)
-#define FATTR4_WORD1_TIME_METADATA      (1UL << 20)
-#define FATTR4_WORD1_TIME_MODIFY        (1UL << 21)
-#define FATTR4_WORD1_TIME_MODIFY_SET    (1UL << 22)
-#define FATTR4_WORD1_MOUNTED_ON_FILEID  (1UL << 23)
-#define FATTR4_WORD1_DACL               (1UL << 26)
-#define FATTR4_WORD1_SACL               (1UL << 27)
-#define FATTR4_WORD1_FS_LAYOUT_TYPES    (1UL << 30)
-#define FATTR4_WORD2_LAYOUT_TYPES       (1UL << 0)
-#define FATTR4_WORD2_LAYOUT_BLKSIZE     (1UL << 1)
-#define FATTR4_WORD2_MDSTHRESHOLD       (1UL << 4)
-#define FATTR4_WORD2_CLONE_BLKSIZE	(1UL << 13)
-#define FATTR4_WORD2_CHANGE_ATTR_TYPE	(1UL << 15)
-#define FATTR4_WORD2_SECURITY_LABEL     (1UL << 16)
-#define FATTR4_WORD2_MODE_UMASK		(1UL << 17)
-#define FATTR4_WORD2_XATTR_SUPPORT	(1UL << 18)
+#define FATTR4_WORD0_ACL                BIT(FATTR4_ACL)
+#define FATTR4_WORD0_ACLSUPPORT         BIT(FATTR4_ACLSUPPORT)
+#define FATTR4_WORD0_ARCHIVE            BIT(FATTR4_ARCHIVE)
+#define FATTR4_WORD0_CANSETTIME         BIT(FATTR4_CANSETTIME)
+#define FATTR4_WORD0_CASE_INSENSITIVE   BIT(FATTR4_CASE_INSENSITIVE)
+#define FATTR4_WORD0_CASE_PRESERVING    BIT(FATTR4_CASE_PRESERVING)
+#define FATTR4_WORD0_CHOWN_RESTRICTED   BIT(FATTR4_CHOWN_RESTRICTED)
+#define FATTR4_WORD0_FILEHANDLE         BIT(FATTR4_FILEHANDLE)
+#define FATTR4_WORD0_FILEID             BIT(FATTR4_FILEID)
+#define FATTR4_WORD0_FILES_AVAIL        BIT(FATTR4_FILES_AVAIL)
+#define FATTR4_WORD0_FILES_FREE         BIT(FATTR4_FILES_FREE)
+#define FATTR4_WORD0_FILES_TOTAL        BIT(FATTR4_FILES_TOTAL)
+#define FATTR4_WORD0_FS_LOCATIONS       BIT(FATTR4_FS_LOCATIONS)
+#define FATTR4_WORD0_HIDDEN             BIT(FATTR4_HIDDEN)
+#define FATTR4_WORD0_HOMOGENEOUS        BIT(FATTR4_HOMOGENEOUS)
+#define FATTR4_WORD0_MAXFILESIZE        BIT(FATTR4_MAXFILESIZE)
+#define FATTR4_WORD0_MAXLINK            BIT(FATTR4_MAXLINK)
+#define FATTR4_WORD0_MAXNAME            BIT(FATTR4_MAXNAME)
+#define FATTR4_WORD0_MAXREAD            BIT(FATTR4_MAXREAD)
+#define FATTR4_WORD0_MAXWRITE           BIT(FATTR4_MAXWRITE)
+
+#define FATTR4_WORD1_MIMETYPE           BIT(FATTR4_MIMETYPE - 32)
+#define FATTR4_WORD1_MODE               BIT(FATTR4_MODE	- 32)
+#define FATTR4_WORD1_NO_TRUNC           BIT(FATTR4_NO_TRUNC - 32)
+#define FATTR4_WORD1_NUMLINKS           BIT(FATTR4_NUMLINKS - 32)
+#define FATTR4_WORD1_OWNER              BIT(FATTR4_OWNER - 32)
+#define FATTR4_WORD1_OWNER_GROUP        BIT(FATTR4_OWNER_GROUP - 32)
+#define FATTR4_WORD1_QUOTA_HARD         BIT(FATTR4_QUOTA_AVAIL_HARD - 32)
+#define FATTR4_WORD1_QUOTA_SOFT         BIT(FATTR4_QUOTA_AVAIL_SOFT - 32)
+#define FATTR4_WORD1_QUOTA_USED         BIT(FATTR4_QUOTA_USED - 32)
+#define FATTR4_WORD1_RAWDEV             BIT(FATTR4_RAWDEV - 32)
+#define FATTR4_WORD1_SPACE_AVAIL        BIT(FATTR4_SPACE_AVAIL - 32)
+#define FATTR4_WORD1_SPACE_FREE         BIT(FATTR4_SPACE_FREE - 32)
+#define FATTR4_WORD1_SPACE_TOTAL        BIT(FATTR4_SPACE_TOTAL - 32)
+#define FATTR4_WORD1_SPACE_USED         BIT(FATTR4_SPACE_USED - 32)
+#define FATTR4_WORD1_SYSTEM             BIT(FATTR4_SYSTEM - 32)
+#define FATTR4_WORD1_TIME_ACCESS        BIT(FATTR4_TIME_ACCESS - 32)
+#define FATTR4_WORD1_TIME_ACCESS_SET    BIT(FATTR4_TIME_ACCESS_SET - 32)
+#define FATTR4_WORD1_TIME_BACKUP        BIT(FATTR4_TIME_BACKUP - 32)
+#define FATTR4_WORD1_TIME_CREATE        BIT(FATTR4_TIME_CREATE - 32)
+#define FATTR4_WORD1_TIME_DELTA         BIT(FATTR4_TIME_DELTA - 32)
+#define FATTR4_WORD1_TIME_METADATA      BIT(FATTR4_TIME_METADATA - 32)
+#define FATTR4_WORD1_TIME_MODIFY        BIT(FATTR4_TIME_MODIFY - 32)
+#define FATTR4_WORD1_TIME_MODIFY_SET    BIT(FATTR4_TIME_MODIFY_SET - 32)
+#define FATTR4_WORD1_MOUNTED_ON_FILEID  BIT(FATTR4_MOUNTED_ON_FILEID - 32)
+#define FATTR4_WORD1_DACL               BIT(FATTR4_DACL	- 32)
+#define FATTR4_WORD1_SACL               BIT(FATTR4_SACL	- 32)
+#define FATTR4_WORD1_FS_LAYOUT_TYPES    BIT(FATTR4_FS_LAYOUT_TYPES - 32)
+
+#define FATTR4_WORD2_LAYOUT_TYPES       BIT(FATTR4_LAYOUT_TYPES - 64)
+#define FATTR4_WORD2_LAYOUT_BLKSIZE     BIT(FATTR4_LAYOUT_BLKSIZE - 64)
+#define FATTR4_WORD2_MDSTHRESHOLD       BIT(FATTR4_MDSTHRESHOLD	- 64)
+#define FATTR4_WORD2_CLONE_BLKSIZE	BIT(FATTR4_CLONE_BLKSIZE - 64)
+#define FATTR4_WORD2_CHANGE_ATTR_TYPE	BIT(FATTR4_CHANGE_ATTR_TYPE - 64)
+#define FATTR4_WORD2_SECURITY_LABEL     BIT(FATTR4_SEC_LABEL - 64)
+#define FATTR4_WORD2_MODE_UMASK		BIT(FATTR4_MODE_UMASK - 64)
+#define FATTR4_WORD2_XATTR_SUPPORT	BIT(FATTR4_XATTR_SUPPORT - 64)
+#define FATTR4_WORD2_TIME_DELEG_ACCESS	BIT(FATTR4_TIME_DELEG_ACCESS - 64)
+#define FATTR4_WORD2_TIME_DELEG_MODIFY	BIT(FATTR4_TIME_DELEG_MODIFY - 64)
+#define FATTR4_WORD2_OPEN_ARGUMENTS	BIT(FATTR4_OPEN_ARGUMENTS - 64)
 
 /* MDS threshold bitmap bits */
 #define THRESHOLD_RD                    (1UL << 0)
@@ -543,6 +679,7 @@ enum {
 	NFSPROC4_CLNT_SEEK,
 	NFSPROC4_CLNT_ALLOCATE,
 	NFSPROC4_CLNT_DEALLOCATE,
+	NFSPROC4_CLNT_ZERO_RANGE,
 	NFSPROC4_CLNT_LAYOUTSTATS,
 	NFSPROC4_CLNT_CLONE,
 	NFSPROC4_CLNT_COPY,
@@ -557,6 +694,7 @@ enum {
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
 	NFSPROC4_CLNT_READ_PLUS,
+	NFSPROC4_CLNT_OFFLOAD_STATUS,
 };
 
 /* nfs41 types */
@@ -577,6 +715,12 @@ enum state_protect_how4 {
 	SP4_SSV		= 2
 };
 
+/* GET_DIR_DELEGATION non-fatal status codes */
+enum gddrnf4_status {
+	GDD4_OK		= 0,
+	GDD4_UNAVAIL	= 1
+};
+
 enum pnfs_layouttype {
 	LAYOUT_NFSV4_1_FILES  = 1,
 	LAYOUT_OSD2_OBJECTS = 2,
@@ -745,4 +889,26 @@ enum {
 	RCA4_TYPE_MASK_OTHER_LAYOUT_MAX	= 15,
 };
 
+enum nfs_cb_opnum4 {
+	OP_CB_GETATTR = 3,
+	OP_CB_RECALL  = 4,
+
+	/* Callback operations new to NFSv4.1 */
+	OP_CB_LAYOUTRECALL  = 5,
+	OP_CB_NOTIFY        = 6,
+	OP_CB_PUSH_DELEG    = 7,
+	OP_CB_RECALL_ANY    = 8,
+	OP_CB_RECALLABLE_OBJ_AVAIL = 9,
+	OP_CB_RECALL_SLOT   = 10,
+	OP_CB_SEQUENCE      = 11,
+	OP_CB_WANTS_CANCELLED = 12,
+	OP_CB_NOTIFY_LOCK   = 13,
+	OP_CB_NOTIFY_DEVICEID = 14,
+
+	/* Callback operations new to NFSv4.2 */
+	OP_CB_OFFLOAD = 15,
+
+	OP_CB_ILLEGAL = 10044,
+};
+
 #endif
diff --git a/include/linux/nfs_common.h b/include/linux/nfs_common.h
new file mode 100644
index 000000000000..a541c3a02887
--- /dev/null
+++ b/include/linux/nfs_common.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * This file contains constants and methods used by both NFS client and server.
+ */
+#ifndef _LINUX_NFS_COMMON_H
+#define _LINUX_NFS_COMMON_H
+
+#include <linux/errno.h>
+#include <uapi/linux/nfs.h>
+
+/* Mapping from NFS error code to "errno" error code. */
+
+int nfs_stat_to_errno(enum nfs_stat status);
+int nfs4_stat_to_errno(int stat);
+
+__u32 nfs_localio_errno_to_nfs4_stat(int errno);
+
+#endif /* _LINUX_NFS_COMMON_H */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 279262057a92..c585939b6cd6 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -77,6 +77,23 @@ struct nfs_lock_context {
 	struct rcu_head	rcu_head;
 };
 
+struct nfs_file_localio {
+	struct nfsd_file __rcu *ro_file;
+	struct nfsd_file __rcu *rw_file;
+	struct list_head list;
+	void __rcu *nfs_uuid; /* opaque pointer to 'nfs_uuid_t' */
+};
+
+static inline void nfs_localio_file_init(struct nfs_file_localio *nfl)
+{
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	nfl->ro_file = NULL;
+	nfl->rw_file = NULL;
+	INIT_LIST_HEAD(&nfl->list);
+	nfl->nfs_uuid = NULL;
+#endif
+}
+
 struct nfs4_state;
 struct nfs_open_context {
 	struct nfs_lock_context lock_context;
@@ -87,15 +104,16 @@ struct nfs_open_context {
 	struct nfs4_state *state;
 	fmode_t mode;
 
+	int error;
 	unsigned long flags;
 #define NFS_CONTEXT_BAD			(2)
 #define NFS_CONTEXT_UNLOCK	(3)
 #define NFS_CONTEXT_FILE_OPEN		(4)
-	int error;
 
-	struct list_head list;
 	struct nfs4_threshold	*mdsthreshold;
+	struct list_head list;
 	struct rcu_head	rcu_head;
+	struct nfs_file_localio nfl;
 };
 
 struct nfs_open_dir_context {
@@ -143,6 +161,12 @@ struct nfs_inode {
 	unsigned long		cache_validity;		/* bit mask */
 
 	/*
+	 * NFS Attributes not included in struct inode
+	 */
+
+	struct timespec64	btime;
+
+	/*
 	 * read_cache_jiffies is when we started read-caching this inode.
 	 * attrtimeo is for how long the cached information is assumed
 	 * to be valid. A successful attribute revalidation doubles
@@ -298,10 +322,12 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALID_XATTR	BIT(15)		/* xattrs are invalid */
 #define NFS_INO_INVALID_NLINK	BIT(16)		/* cached nlinks is invalid */
 #define NFS_INO_INVALID_MODE	BIT(17)		/* cached mode is invalid */
+#define NFS_INO_INVALID_BTIME	BIT(18)		/* cached btime is invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
 		| NFS_INO_INVALID_MTIME \
+		| NFS_INO_INVALID_BTIME \
 		| NFS_INO_INVALID_SIZE \
 		| NFS_INO_INVALID_NLINK \
 		| NFS_INO_INVALID_MODE \
@@ -561,6 +587,9 @@ extern int nfs_may_open(struct inode *inode, const struct cred *cred, int openfl
 extern void nfs_access_zap_cache(struct inode *inode);
 extern int nfs_access_get_cached(struct inode *inode, const struct cred *cred,
 				 u32 *mask, bool may_block);
+extern int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
+			       struct file *file, unsigned int open_flags,
+			       umode_t mode);
 
 /*
  * linux/fs/nfs/symlink.c
@@ -595,7 +624,6 @@ extern void nfs_complete_unlink(struct dentry *dentry, struct inode *);
  * linux/fs/nfs/write.c
  */
 extern int  nfs_congestion_kb;
-extern int  nfs_writepage(struct page *page, struct writeback_control *wbc);
 extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct folio *folio);
 extern int  nfs_update_folio(struct file *file, struct folio *folio,
@@ -612,6 +640,7 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio);
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_commit_data *nfs_commitdata_alloc(void);
 extern void nfs_commit_free(struct nfs_commit_data *data);
+void nfs_commit_begin(struct nfs_mds_commit_info *cinfo);
 bool nfs_commit_end(struct nfs_mds_commit_info *cinfo);
 
 static inline bool nfs_have_writebacks(const struct inode *inode)
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index ea2f7e6b1b0b..d30c0245031c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -8,6 +8,7 @@
 #include <linux/wait.h>
 #include <linux/nfs_xdr.h>
 #include <linux/sunrpc/xprt.h>
+#include <linux/nfslocalio.h>
 
 #include <linux/atomic.h>
 #include <linux/refcount.h>
@@ -48,6 +49,8 @@ struct nfs_client {
 #define NFS_CS_NOPING		6		/* - don't ping on connect */
 #define NFS_CS_DS		7		/* - Server is a DS */
 #define NFS_CS_REUSEPORT	8		/* - reuse src port on reconnect */
+#define NFS_CS_PNFS		9		/* - Server used for pnfs */
+#define NFS_CS_NETUNREACH_FATAL	10		/* - ENETUNREACH errors are fatal */
 	struct sockaddr_storage	cl_addr;	/* server identifier */
 	size_t			cl_addrlen;
 	char *			cl_hostname;	/* hostname of server */
@@ -63,7 +66,8 @@ struct nfs_client {
 	u32			cl_minorversion;/* NFSv4 minorversion */
 	unsigned int		cl_nconnect;	/* Number of connections */
 	unsigned int		cl_max_connect; /* max number of xprts allowed */
-	const char *		cl_principal;  /* used for machine cred */
+	const char *		cl_principal;	/* used for machine cred */
+	struct xprtsec_parms	cl_xprtsec;	/* xprt security policy */
 
 #if IS_ENABLED(CONFIG_NFS_V4)
 	struct list_head	cl_ds_clients; /* auth flavor data servers */
@@ -121,7 +125,16 @@ struct nfs_client {
 	 */
 	char			cl_ipaddr[48];
 	struct net		*cl_net;
+	netns_tracker		cl_ns_tracker;
 	struct list_head	pending_cb_stateids;
+	struct rcu_head		rcu;
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+	struct timespec64	cl_nfssvc_boot;
+	seqlock_t		cl_boot_lock;
+	nfs_uuid_t		cl_uuid;
+	struct work_struct	cl_local_probe_work;
+#endif /* CONFIG_NFS_LOCALIO */
 };
 
 /*
@@ -137,6 +150,7 @@ struct nfs_server {
 	struct rpc_clnt *	client_acl;	/* ACL RPC client handle */
 	struct nlm_host		*nlm_host;	/* NLM client handle */
 	struct nfs_iostats __percpu *io_stats;	/* I/O statistics */
+	wait_queue_head_t	write_congestion_wait;	/* wait until write congestion eases */
 	atomic_long_t		writeback;	/* number of writeback pages */
 	unsigned int		write_congested;/* flag set when writeback gets too high */
 	unsigned int		flags;		/* various flags */
@@ -153,13 +167,16 @@ struct nfs_server {
 #define NFS_MOUNT_WRITE_EAGER		0x01000000
 #define NFS_MOUNT_WRITE_WAIT		0x02000000
 #define NFS_MOUNT_TRUNK_DISCOVERY	0x04000000
+#define NFS_MOUNT_SHUTDOWN			0x08000000
+#define NFS_MOUNT_NO_ALIGNWRITE		0x10000000
+#define NFS_MOUNT_FORCE_RDIRPLUS	0x20000000
+#define NFS_MOUNT_NETUNREACH_FATAL	0x40000000
 
-	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
+	__u64			fattr_valid;	/* Valid attributes */
 	unsigned int		rsize;		/* read size */
 	unsigned int		rpages;		/* read size (in pages) */
 	unsigned int		wsize;		/* write size */
-	unsigned int		wpages;		/* write size (in pages) */
 	unsigned int		wtmult;		/* server disk block size */
 	unsigned int		dtsize;		/* readdir size */
 	unsigned short		port;		/* "port=" setting */
@@ -183,8 +200,8 @@ struct nfs_server {
 				change_attr_type;/* Description of change attribute */
 
 	struct nfs_fsid		fsid;
+	int			s_sysfs_id;	/* sysfs dentry index */
 	__u64			maxfilesize;	/* maximum file size */
-	struct timespec64	time_delta;	/* smallest time granularity */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	struct super_block	*super;		/* VFS super block */
 	dev_t			s_dev;		/* superblock dev numbers */
@@ -195,6 +212,15 @@ struct nfs_server {
 	char			*fscache_uniq;	/* Uniquifier (or NULL) */
 #endif
 
+	/* The following #defines numerically match the NFSv4 equivalents */
+#define NFS_FH_NOEXPIRE_WITH_OPEN (0x1)
+#define NFS_FH_VOLATILE_ANY (0x2)
+#define NFS_FH_VOL_MIGRATION (0x4)
+#define NFS_FH_VOL_RENAME (0x8)
+#define NFS_FH_RENAME_UNSAFE (NFS_FH_VOLATILE_ANY | NFS_FH_VOL_RENAME)
+	u32			fh_expire_type;	/* V4 bitmask representing file
+						   handle volatility type for
+						   this filesystem */
 	u32			pnfs_blksize;	/* layout_blksize attr */
 #if IS_ENABLED(CONFIG_NFS_V4)
 	u32			attr_bitmask[3];/* V4 bitmask representing the set
@@ -218,23 +244,27 @@ struct nfs_server {
 	u32			acl_bitmask;	/* V4 bitmask representing the ACEs
 						   that are supported on this
 						   filesystem */
-	u32			fh_expire_type;	/* V4 bitmask representing file
-						   handle volatility type for
-						   this filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
-	void			*pnfs_ld_data;	/* per mount point data */
 
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;
 #endif
-	struct ida		openowner_id;
-	struct ida		lockowner_id;
+	atomic64_t		owner_ctr;
 	struct list_head	state_owners_lru;
 	struct list_head	layouts;
 	struct list_head	delegations;
+	atomic_long_t		nr_active_delegations;
+	unsigned int		delegation_hash_mask;
+	struct hlist_head	*delegation_hash_table;
 	struct list_head	ss_copies;
+	struct list_head	ss_src_copies;
 
+	unsigned long		delegation_flags;
+#define NFS4SERV_DELEGRETURN		(1)
+#define NFS4SERV_DELEGATION_EXPIRED	(2)
+#define NFS4SERV_DELEGRETURN_DELAYED	(3)
+	unsigned long		delegation_gen;
 	unsigned long		mig_gen;
 	unsigned long		mig_status;
 #define NFS_MIG_IN_TRANSITION		(1)
@@ -259,6 +289,8 @@ struct nfs_server {
 	/* User namespace info */
 	const struct cred	*cred;
 	bool			has_sec_mnt_opts;
+	struct kobject		kobj;
+	struct rcu_head		rcu;
 };
 
 /* Server capabilities */
@@ -270,6 +302,11 @@ struct nfs_server {
 #define NFS_CAP_LGOPEN		(1U << 5)
 #define NFS_CAP_CASE_INSENSITIVE	(1U << 6)
 #define NFS_CAP_CASE_PRESERVING	(1U << 7)
+#define NFS_CAP_REBOOT_LAYOUTRETURN	(1U << 8)
+#define NFS_CAP_OFFLOAD_STATUS	(1U << 9)
+#define NFS_CAP_ZERO_RANGE	(1U << 10)
+#define NFS_CAP_OPEN_XOR	(1U << 12)
+#define NFS_CAP_DELEGTIME	(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
 #define NFS_CAP_UIDGID_NOMAP	(1U << 15)
 #define NFS_CAP_STATEID_NFSV41	(1U << 16)
diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h
index aa9f4c6ebe26..afe1d8f09d89 100644
--- a/include/linux/nfs_page.h
+++ b/include/linux/nfs_page.h
@@ -122,8 +122,6 @@ struct nfs_pageio_descriptor {
 /* arbitrarily selected limit to number of mirrors */
 #define NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX 16
 
-#define NFS_WBACK_BUSY(req)	(test_bit(PG_BUSY,&(req)->wb_flags))
-
 extern struct nfs_page *nfs_page_create_from_page(struct nfs_open_context *ctx,
 						  struct page *page,
 						  unsigned int pgbase,
@@ -152,15 +150,15 @@ extern	void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *, pgoff_t);
 extern size_t nfs_generic_pg_test(struct nfs_pageio_descriptor *desc,
 				struct nfs_page *prev,
 				struct nfs_page *req);
-extern  int nfs_wait_on_request(struct nfs_page *);
 extern	void nfs_unlock_request(struct nfs_page *req);
 extern	void nfs_unlock_and_release_request(struct nfs_page *);
-extern	struct nfs_page *nfs_page_group_lock_head(struct nfs_page *req);
-extern	int nfs_page_group_lock_subrequests(struct nfs_page *head);
-extern	void nfs_join_page_group(struct nfs_page *head, struct inode *inode);
+extern void nfs_join_page_group(struct nfs_page *head,
+				struct nfs_commit_info *cinfo,
+				struct inode *inode);
 extern int nfs_page_group_lock(struct nfs_page *);
 extern void nfs_page_group_unlock(struct nfs_page *);
 extern bool nfs_page_group_sync_on_bit(struct nfs_page *, unsigned int);
+extern bool nfs_page_group_sync_on_bit_locked(struct nfs_page *, unsigned int);
 extern	int nfs_page_set_headlock(struct nfs_page *req);
 extern void nfs_page_clear_headlock(struct nfs_page *req);
 extern bool nfs_async_iocounter_wait(struct rpc_task *, struct nfs_lock_context *);
@@ -206,8 +204,8 @@ static inline struct inode *nfs_page_to_inode(const struct nfs_page *req)
 	struct folio *folio = nfs_page_to_folio(req);
 
 	if (folio == NULL)
-		return page_file_mapping(req->wb_page)->host;
-	return folio_file_mapping(folio)->host;
+		return req->wb_page->mapping->host;
+	return folio->mapping->host;
 }
 
 /**
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 29a1b39794bf..31463286402f 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -45,7 +45,7 @@ struct nfs4_threshold {
 };
 
 struct nfs_fattr {
-	unsigned int		valid;		/* which fields are valid */
+	__u64			valid;		/* which fields are valid */
 	umode_t			mode;
 	__u32			nlink;
 	kuid_t			uid;
@@ -67,6 +67,7 @@ struct nfs_fattr {
 	struct timespec64	atime;
 	struct timespec64	mtime;
 	struct timespec64	ctime;
+	struct timespec64	btime;
 	__u64			change_attr;	/* NFSv4 change attribute */
 	__u64			pre_change_attr;/* pre-op NFSv4 change attribute */
 	__u64			pre_size;	/* pre_op_attr.size	  */
@@ -80,32 +81,33 @@ struct nfs_fattr {
 	struct nfs4_label	*label;
 };
 
-#define NFS_ATTR_FATTR_TYPE		(1U << 0)
-#define NFS_ATTR_FATTR_MODE		(1U << 1)
-#define NFS_ATTR_FATTR_NLINK		(1U << 2)
-#define NFS_ATTR_FATTR_OWNER		(1U << 3)
-#define NFS_ATTR_FATTR_GROUP		(1U << 4)
-#define NFS_ATTR_FATTR_RDEV		(1U << 5)
-#define NFS_ATTR_FATTR_SIZE		(1U << 6)
-#define NFS_ATTR_FATTR_PRESIZE		(1U << 7)
-#define NFS_ATTR_FATTR_BLOCKS_USED	(1U << 8)
-#define NFS_ATTR_FATTR_SPACE_USED	(1U << 9)
-#define NFS_ATTR_FATTR_FSID		(1U << 10)
-#define NFS_ATTR_FATTR_FILEID		(1U << 11)
-#define NFS_ATTR_FATTR_ATIME		(1U << 12)
-#define NFS_ATTR_FATTR_MTIME		(1U << 13)
-#define NFS_ATTR_FATTR_CTIME		(1U << 14)
-#define NFS_ATTR_FATTR_PREMTIME		(1U << 15)
-#define NFS_ATTR_FATTR_PRECTIME		(1U << 16)
-#define NFS_ATTR_FATTR_CHANGE		(1U << 17)
-#define NFS_ATTR_FATTR_PRECHANGE	(1U << 18)
-#define NFS_ATTR_FATTR_V4_LOCATIONS	(1U << 19)
-#define NFS_ATTR_FATTR_V4_REFERRAL	(1U << 20)
-#define NFS_ATTR_FATTR_MOUNTPOINT	(1U << 21)
-#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID (1U << 22)
-#define NFS_ATTR_FATTR_OWNER_NAME	(1U << 23)
-#define NFS_ATTR_FATTR_GROUP_NAME	(1U << 24)
-#define NFS_ATTR_FATTR_V4_SECURITY_LABEL (1U << 25)
+#define NFS_ATTR_FATTR_TYPE		BIT_ULL(0)
+#define NFS_ATTR_FATTR_MODE		BIT_ULL(1)
+#define NFS_ATTR_FATTR_NLINK		BIT_ULL(2)
+#define NFS_ATTR_FATTR_OWNER		BIT_ULL(3)
+#define NFS_ATTR_FATTR_GROUP		BIT_ULL(4)
+#define NFS_ATTR_FATTR_RDEV		BIT_ULL(5)
+#define NFS_ATTR_FATTR_SIZE		BIT_ULL(6)
+#define NFS_ATTR_FATTR_PRESIZE		BIT_ULL(7)
+#define NFS_ATTR_FATTR_BLOCKS_USED	BIT_ULL(8)
+#define NFS_ATTR_FATTR_SPACE_USED	BIT_ULL(9)
+#define NFS_ATTR_FATTR_FSID		BIT_ULL(10)
+#define NFS_ATTR_FATTR_FILEID		BIT_ULL(11)
+#define NFS_ATTR_FATTR_ATIME		BIT_ULL(12)
+#define NFS_ATTR_FATTR_MTIME		BIT_ULL(13)
+#define NFS_ATTR_FATTR_CTIME		BIT_ULL(14)
+#define NFS_ATTR_FATTR_PREMTIME		BIT_ULL(15)
+#define NFS_ATTR_FATTR_PRECTIME		BIT_ULL(16)
+#define NFS_ATTR_FATTR_CHANGE		BIT_ULL(17)
+#define NFS_ATTR_FATTR_PRECHANGE	BIT_ULL(18)
+#define NFS_ATTR_FATTR_V4_LOCATIONS	BIT_ULL(19)
+#define NFS_ATTR_FATTR_V4_REFERRAL	BIT_ULL(20)
+#define NFS_ATTR_FATTR_MOUNTPOINT	BIT_ULL(21)
+#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID BIT_ULL(22)
+#define NFS_ATTR_FATTR_OWNER_NAME	BIT_ULL(23)
+#define NFS_ATTR_FATTR_GROUP_NAME	BIT_ULL(24)
+#define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
+#define NFS_ATTR_FATTR_BTIME		BIT_ULL(26)
 
 #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
 		| NFS_ATTR_FATTR_MODE \
@@ -126,6 +128,7 @@ struct nfs_fattr {
 		| NFS_ATTR_FATTR_SPACE_USED)
 #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
 		| NFS_ATTR_FATTR_SPACE_USED \
+		| NFS_ATTR_FATTR_BTIME \
 		| NFS_ATTR_FATTR_V4_SECURITY_LABEL)
 
 /*
@@ -446,7 +449,23 @@ struct nfs42_clone_res {
 
 struct stateowner_id {
 	__u64	create_time;
-	__u32	uniquifier;
+	__u64	uniquifier;
+};
+
+struct nfs4_open_delegation {
+	__u32 open_delegation_type;
+	union {
+		struct {
+			fmode_t			type;
+			__u32			do_recall;
+			nfs4_stateid		stateid;
+			unsigned long		pagemod_limit;
+		};
+		struct {
+			__u32			why_no_delegation;
+			__u32			will_notify;
+		};
+	};
 };
 
 /*
@@ -468,7 +487,7 @@ struct nfs_openargs {
 			nfs4_verifier   verifier; /* EXCLUSIVE */
 		};
 		nfs4_stateid	delegation;		/* CLAIM_DELEGATE_CUR */
-		fmode_t		delegation_type;	/* CLAIM_PREVIOUS */
+		__u32		delegation_type;	/* CLAIM_PREVIOUS */
 	} u;
 	const struct qstr *	name;
 	const struct nfs_server *server;	 /* Needed for ID mapping */
@@ -490,13 +509,10 @@ struct nfs_openres {
 	struct nfs_fattr *      f_attr;
 	struct nfs_seqid *	seqid;
 	const struct nfs_server *server;
-	fmode_t			delegation_type;
-	nfs4_stateid		delegation;
-	unsigned long		pagemod_limit;
-	__u32			do_recall;
 	__u32			attrset[NFS4_BITMAP_SIZE];
 	struct nfs4_string	*owner;
 	struct nfs4_string	*group_owner;
+	struct nfs4_open_delegation	delegation;
 	__u32			access_request;
 	__u32			access_supported;
 	__u32			access_result;
@@ -609,6 +625,13 @@ struct nfs_release_lockowner_res {
 	struct nfs4_sequence_res	seq_res;
 };
 
+struct nfs4_delegattr {
+	struct timespec64	atime;
+	struct timespec64	mtime;
+	bool			atime_set;
+	bool			mtime_set;
+};
+
 struct nfs4_delegreturnargs {
 	struct nfs4_sequence_args	seq_args;
 	const struct nfs_fh *fhandle;
@@ -616,6 +639,7 @@ struct nfs4_delegreturnargs {
 	const u32 *bitmask;
 	u32 bitmask_store[NFS_BITMASK_SZ];
 	struct nfs4_layoutreturn_args *lr_args;
+	struct nfs4_delegattr *sattr_args;
 };
 
 struct nfs4_delegreturnres {
@@ -624,6 +648,8 @@ struct nfs4_delegreturnres {
 	struct nfs_server *server;
 	struct nfs4_layoutreturn_res *lr_res;
 	int lr_ret;
+	bool sattr_res;
+	int sattr_ret;
 };
 
 /*
@@ -836,7 +862,7 @@ struct nfs_getaclres {
 	size_t				acl_len;
 	size_t				acl_data_offset;
 	int				acl_flags;
-	struct page *			acl_scratch;
+	struct folio *			acl_scratch;
 };
 
 struct nfs_setattrres {
@@ -1190,6 +1216,14 @@ struct nfs4_statfs_res {
 	struct nfs_fsstat	       *fsstat;
 };
 
+struct nfs4_open_caps {
+	u32				oa_share_access[1];
+	u32				oa_share_deny[1];
+	u32				oa_share_access_want[1];
+	u32				oa_open_claim[1];
+	u32				oa_createmode[1];
+};
+
 struct nfs4_server_caps_arg {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh		       *fhandle;
@@ -1206,6 +1240,7 @@ struct nfs4_server_caps_res {
 	u32				fh_expire_type;
 	u32				case_insensitive;
 	u32				case_preserving;
+	struct nfs4_open_caps		open_caps;
 };
 
 #define NFS4_PATHNAME_MAXCOMPONENTS 512
@@ -1283,11 +1318,6 @@ struct nfs4_fsid_present_res {
 
 #endif /* CONFIG_NFS_V4 */
 
-struct nfstime4 {
-	u64	seconds;
-	u32	nseconds;
-};
-
 #ifdef CONFIG_NFS_V4_1
 
 struct pnfs_commit_bucket {
@@ -1304,7 +1334,7 @@ struct pnfs_commit_array {
 	struct rcu_head rcu;
 	refcount_t refcount;
 	unsigned int nbuckets;
-	struct pnfs_commit_bucket buckets[];
+	struct pnfs_commit_bucket buckets[] __counted_by(nbuckets);
 };
 
 struct pnfs_ds_commit_info {
@@ -1406,7 +1436,7 @@ struct nfs41_secinfo_no_name_args {
 
 struct nfs41_test_stateid_args {
 	struct nfs4_sequence_args	seq_args;
-	nfs4_stateid			*stateid;
+	nfs4_stateid			stateid;
 };
 
 struct nfs41_test_stateid_res {
@@ -1488,8 +1518,9 @@ struct nfs42_offload_status_args {
 
 struct nfs42_offload_status_res {
 	struct nfs4_sequence_res	osr_seq_res;
-	uint64_t			osr_count;
-	int				osr_status;
+	u64				osr_count;
+	int				complete_count;
+	u32				osr_complete;
 };
 
 struct nfs42_copy_notify_args {
@@ -1528,6 +1559,7 @@ struct nfs42_seek_res {
 struct nfs42_setxattrargs {
 	struct nfs4_sequence_args	seq_args;
 	struct nfs_fh			*fh;
+	const u32			*bitmask;
 	const char			*xattr_name;
 	u32				xattr_flags;
 	size_t				xattr_len;
@@ -1537,6 +1569,8 @@ struct nfs42_setxattrargs {
 struct nfs42_setxattrres {
 	struct nfs4_sequence_res	seq_res;
 	struct nfs4_change_info		cinfo;
+	struct nfs_fattr		*fattr;
+	const struct nfs_server		*server;
 };
 
 struct nfs42_getxattrargs {
@@ -1562,7 +1596,7 @@ struct nfs42_listxattrsargs {
 
 struct nfs42_listxattrsres {
 	struct nfs4_sequence_res	seq_res;
-	struct page			*scratch;
+	struct folio			*scratch;
 	void				*xattr_buf;
 	size_t				xattr_len;
 	u64				cookie;
@@ -1602,6 +1636,7 @@ enum {
 	NFS_IOHDR_RESEND_PNFS,
 	NFS_IOHDR_RESEND_MDS,
 	NFS_IOHDR_UNSTABLE_WRITES,
+	NFS_IOHDR_ODIRECT,
 };
 
 struct nfs_io_completion;
@@ -1624,6 +1659,7 @@ struct nfs_pgio_header {
 	void			*netfs;
 #endif
 
+	unsigned short		retrans;
 	int			pnfs_error;
 	int			error;		/* merge with pnfs_error */
 	unsigned int		good_bytes;	/* boundary of good data */
@@ -1750,7 +1786,7 @@ struct nfs_rpc_ops {
 			    struct nfs_fattr *, struct inode *);
 	int	(*setattr) (struct dentry *, struct nfs_fattr *,
 			    struct iattr *);
-	int	(*lookup)  (struct inode *, struct dentry *,
+	int	(*lookup)  (struct inode *, struct dentry *, const struct qstr *,
 			    struct nfs_fh *, struct nfs_fattr *);
 	int	(*lookupp) (struct inode *, struct nfs_fh *,
 			    struct nfs_fattr *);
@@ -1769,9 +1805,9 @@ struct nfs_rpc_ops {
 	void	(*rename_rpc_prepare)(struct rpc_task *task, struct nfs_renamedata *);
 	int	(*rename_done) (struct rpc_task *task, struct inode *old_dir, struct inode *new_dir);
 	int	(*link)    (struct inode *, struct inode *, const struct qstr *);
-	int	(*symlink) (struct inode *, struct dentry *, struct page *,
+	int	(*symlink) (struct inode *, struct dentry *, struct folio *,
 			    unsigned int, struct iattr *);
-	int	(*mkdir)   (struct inode *, struct dentry *, struct iattr *);
+	struct dentry *(*mkdir)   (struct inode *, struct dentry *, struct iattr *);
 	int	(*rmdir)   (struct inode *, const struct qstr *);
 	int	(*readdir) (struct nfs_readdir_arg *, struct nfs_readdir_res *);
 	int	(*mknod)   (struct inode *, struct dentry *, struct iattr *,
@@ -1804,7 +1840,8 @@ struct nfs_rpc_ops {
 				int open_flags,
 				struct iattr *iattr,
 				int *);
-	int (*have_delegation)(struct inode *, fmode_t);
+	int (*have_delegation)(struct inode *, fmode_t, int);
+	int (*return_delegation)(struct inode *);
 	struct nfs_client *(*alloc_client) (const struct nfs_client_initdata *);
 	struct nfs_client *(*init_client) (struct nfs_client *,
 				const struct nfs_client_initdata *);
@@ -1818,11 +1855,22 @@ struct nfs_rpc_ops {
 };
 
 /*
- * 	NFS_CALL(getattr, inode, (fattr));
- * into
- *	NFS_PROTO(inode)->getattr(fattr);
+ * Helper functions used by NFS client and/or server
  */
-#define NFS_CALL(op, inode, args)	NFS_PROTO(inode)->op args
+static inline void encode_opaque_fixed(struct xdr_stream *xdr,
+				       const void *buf, size_t len)
+{
+	WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
+}
+
+static inline int decode_opaque_fixed(struct xdr_stream *xdr,
+				      void *buf, size_t len)
+{
+	ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
+	if (unlikely(ret < 0))
+		return -EIO;
+	return 0;
+}
 
 /*
  * Function vectors etc. for the NFS client
@@ -1837,4 +1885,4 @@ extern const struct rpc_version nfs_version4;
 extern const struct rpc_version nfsacl_version3;
 extern const struct rpc_program nfsacl_program;
 
-#endif
+#endif /* _LINUX_NFS_XDR_H */
diff --git a/include/linux/nfslocalio.h b/include/linux/nfslocalio.h
new file mode 100644
index 000000000000..3d91043254e6
--- /dev/null
+++ b/include/linux/nfslocalio.h
@@ -0,0 +1,123 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Mike Snitzer <snitzer@hammerspace.com>
+ * Copyright (C) 2024 NeilBrown <neilb@suse.de>
+ */
+#ifndef __LINUX_NFSLOCALIO_H
+#define __LINUX_NFSLOCALIO_H
+
+#if IS_ENABLED(CONFIG_NFS_LOCALIO)
+
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/uuid.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/svcauth.h>
+#include <linux/nfs.h>
+#include <net/net_namespace.h>
+
+struct nfs_client;
+struct nfs_file_localio;
+
+/*
+ * Useful to allow a client to negotiate if localio
+ * possible with its server.
+ *
+ * See Documentation/filesystems/nfs/localio.rst for more detail.
+ */
+typedef struct {
+	uuid_t uuid;
+	unsigned nfs3_localio_probe_count;
+	/* this struct is over a cacheline, avoid bouncing */
+	spinlock_t ____cacheline_aligned lock;
+	struct list_head list;
+	spinlock_t *list_lock; /* nn->local_clients_lock */
+	struct net __rcu *net; /* nfsd's network namespace */
+	struct auth_domain *dom; /* auth_domain for localio */
+	/* Local files to close when net is shut down or exports change */
+	struct list_head files;
+} nfs_uuid_t;
+
+void nfs_uuid_init(nfs_uuid_t *);
+bool nfs_uuid_begin(nfs_uuid_t *);
+void nfs_uuid_end(nfs_uuid_t *);
+void nfs_uuid_is_local(const uuid_t *, struct list_head *, spinlock_t *,
+		       struct net *, struct auth_domain *, struct module *);
+
+void nfs_localio_enable_client(struct nfs_client *clp);
+void nfs_localio_disable_client(struct nfs_client *clp);
+void nfs_localio_invalidate_clients(struct list_head *nn_local_clients,
+				    spinlock_t *nn_local_clients_lock);
+
+/* localio needs to map filehandle -> struct nfsd_file */
+void nfs_close_local_fh(struct nfs_file_localio *);
+
+struct nfsd_localio_operations {
+	bool (*nfsd_net_try_get)(struct net *);
+	void (*nfsd_net_put)(struct net *);
+	struct nfsd_file *(*nfsd_open_local_fh)(struct net *,
+						struct auth_domain *,
+						struct rpc_clnt *,
+						const struct cred *,
+						const struct nfs_fh *,
+						struct nfsd_file __rcu **pnf,
+						const fmode_t);
+	struct net *(*nfsd_file_put_local)(struct nfsd_file __rcu **);
+	struct file *(*nfsd_file_file)(struct nfsd_file *);
+	void (*nfsd_file_dio_alignment)(struct nfsd_file *,
+					u32 *, u32 *, u32 *);
+} ____cacheline_aligned;
+
+extern void nfsd_localio_ops_init(void);
+extern const struct nfsd_localio_operations *nfs_to;
+
+struct nfsd_file *nfs_open_local_fh(nfs_uuid_t *,
+		   struct rpc_clnt *, const struct cred *,
+		   const struct nfs_fh *, struct nfs_file_localio *,
+		   struct nfsd_file __rcu **pnf,
+		   const fmode_t);
+
+static inline void nfs_to_nfsd_net_put(struct net *net)
+{
+	/*
+	 * Once reference to net (and associated nfsd_serv) is dropped, NFSD
+	 * could be unloaded, so ensure safe return from nfsd_net_put() by
+	 * always taking RCU.
+	 */
+	rcu_read_lock();
+	nfs_to->nfsd_net_put(net);
+	rcu_read_unlock();
+}
+
+static inline void nfs_to_nfsd_file_put_local(struct nfsd_file __rcu **localio)
+{
+	/*
+	 * Either *localio must be guaranteed to be non-NULL, or caller
+	 * must prevent nfsd shutdown from completing as nfs_close_local_fh()
+	 * does by blocking the nfs_uuid from being finally put.
+	 */
+	struct net *net;
+
+	net = nfs_to->nfsd_file_put_local(localio);
+
+	if (net)
+		nfs_to_nfsd_net_put(net);
+}
+
+#else   /* CONFIG_NFS_LOCALIO */
+
+struct nfs_file_localio;
+static inline void nfs_close_local_fh(struct nfs_file_localio *nfl)
+{
+}
+static inline void nfsd_localio_ops_init(void)
+{
+}
+struct nfs_client;
+static inline void nfs_localio_disable_client(struct nfs_client *clp)
+{
+}
+
+#endif  /* CONFIG_NFS_LOCALIO */
+
+#endif  /* __LINUX_NFSLOCALIO_H */
diff --git a/include/linux/nls.h b/include/linux/nls.h
index 499e486b3722..e0bf8367b274 100644
--- a/include/linux/nls.h
+++ b/include/linux/nls.h
@@ -47,7 +47,7 @@ enum utf16_endian {
 /* nls_base.c */
 extern int __register_nls(struct nls_table *, struct module *);
 extern int unregister_nls(struct nls_table *);
-extern struct nls_table *load_nls(char *);
+extern struct nls_table *load_nls(const char *charset);
 extern void unload_nls(struct nls_table *);
 extern struct nls_table *load_nls_default(void);
 #define register_nls(nls) __register_nls((nls), THIS_MODULE)
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index 048c0b9aa623..cf3c6ab408aa 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -7,19 +7,18 @@
 
 #include <linux/sched.h>
 #include <asm/irq.h>
-#if defined(CONFIG_HAVE_NMI_WATCHDOG)
+
+/* Arch specific watchdogs might need to share extra watchdog-related APIs. */
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_ARCH) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64)
 #include <asm/nmi.h>
 #endif
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 void lockup_detector_init(void);
+void lockup_detector_retry_init(void);
 void lockup_detector_soft_poweroff(void);
-void lockup_detector_cleanup(void);
-bool is_hardlockup(void);
 
 extern int watchdog_user_enabled;
-extern int nmi_watchdog_user_enabled;
-extern int soft_watchdog_user_enabled;
 extern int watchdog_thresh;
 extern unsigned long watchdog_enabled;
 
@@ -35,8 +34,8 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 
 #else /* CONFIG_LOCKUP_DETECTOR */
 static inline void lockup_detector_init(void) { }
+static inline void lockup_detector_retry_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
-static inline void lockup_detector_cleanup(void) { }
 #endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -69,17 +68,17 @@ static inline void reset_hung_task_detector(void) { }
  * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
  * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
  *
- * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and
- * 'soft_watchdog_user_enabled' are variables that are only used as an
+ * 'watchdog_user_enabled', 'watchdog_hardlockup_user_enabled' and
+ * 'watchdog_softlockup_user_enabled' are variables that are only used as an
  * 'interface' between the parameters in /proc/sys/kernel and the internal
  * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is
  * handled differently because its value is not boolean, and the lockup
  * detectors are 'suspended' while 'watchdog_thresh' is equal zero.
  */
-#define NMI_WATCHDOG_ENABLED_BIT   0
-#define SOFT_WATCHDOG_ENABLED_BIT  1
-#define NMI_WATCHDOG_ENABLED      (1 << NMI_WATCHDOG_ENABLED_BIT)
-#define SOFT_WATCHDOG_ENABLED     (1 << SOFT_WATCHDOG_ENABLED_BIT)
+#define WATCHDOG_HARDLOCKUP_ENABLED_BIT  0
+#define WATCHDOG_SOFTOCKUP_ENABLED_BIT   1
+#define WATCHDOG_HARDLOCKUP_ENABLED     (1 << WATCHDOG_HARDLOCKUP_ENABLED_BIT)
+#define WATCHDOG_SOFTOCKUP_ENABLED      (1 << WATCHDOG_SOFTOCKUP_ENABLED_BIT)
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR)
 extern void hardlockup_detector_disable(void);
@@ -88,52 +87,65 @@ extern unsigned int hardlockup_panic;
 static inline void hardlockup_detector_disable(void) {}
 #endif
 
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
-# define NMI_WATCHDOG_SYSCTL_PERM	0644
+/* Sparc64 has special implemetantion that is always enabled. */
+#if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HARDLOCKUP_DETECTOR_SPARC64)
+void arch_touch_nmi_watchdog(void);
 #else
-# define NMI_WATCHDOG_SYSCTL_PERM	0444
+static inline void arch_touch_nmi_watchdog(void) { }
+#endif
+
+#if defined(CONFIG_HARDLOCKUP_DETECTOR_COUNTS_HRTIMER)
+void watchdog_hardlockup_touch_cpu(unsigned int cpu);
+void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs);
 #endif
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
-extern void arch_touch_nmi_watchdog(void);
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
-extern void hardlockup_detector_perf_disable(void);
-extern void hardlockup_detector_perf_enable(void);
-extern void hardlockup_detector_perf_cleanup(void);
-extern int hardlockup_detector_perf_init(void);
+extern void hardlockup_config_perf_event(const char *str);
+extern void hardlockup_detector_perf_adjust_period(u64 period);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
-static inline void hardlockup_detector_perf_disable(void) { }
-static inline void hardlockup_detector_perf_enable(void) { }
-static inline void hardlockup_detector_perf_cleanup(void) { }
-# if !defined(CONFIG_HAVE_NMI_WATCHDOG)
-static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
-static inline void arch_touch_nmi_watchdog(void) {}
-# else
-static inline int hardlockup_detector_perf_init(void) { return 0; }
-# endif
+static inline void hardlockup_config_perf_event(const char *str) { }
+static inline void hardlockup_detector_perf_adjust_period(u64 period) { }
 #endif
 
-void watchdog_nmi_stop(void);
-void watchdog_nmi_start(void);
-int watchdog_nmi_probe(void);
-int watchdog_nmi_enable(unsigned int cpu);
-void watchdog_nmi_disable(unsigned int cpu);
+void watchdog_hardlockup_stop(void);
+void watchdog_hardlockup_start(void);
+int watchdog_hardlockup_probe(void);
+void watchdog_hardlockup_enable(unsigned int cpu);
+void watchdog_hardlockup_disable(unsigned int cpu);
 
 void lockup_detector_reconfigure(void);
 
+#ifdef CONFIG_HARDLOCKUP_DETECTOR_BUDDY
+void watchdog_buddy_check_hardlockup(int hrtimer_interrupts);
+#else
+static inline void watchdog_buddy_check_hardlockup(int hrtimer_interrupts) {}
+#endif
+
 /**
- * touch_nmi_watchdog - restart NMI watchdog timeout.
+ * touch_nmi_watchdog - manually reset the hardlockup watchdog timeout.
+ *
+ * If we support detecting hardlockups, touch_nmi_watchdog() may be
+ * used to pet the watchdog (reset the timeout) - for code which
+ * intentionally disables interrupts for a long time. This call is stateless.
  *
- * If the architecture supports the NMI watchdog, touch_nmi_watchdog()
- * may be used to reset the timeout - for code which intentionally
- * disables interrupts for a long time. This call is stateless.
+ * Though this function has "nmi" in the name, the hardlockup watchdog might
+ * not be backed by NMIs. This function will likely be renamed to
+ * touch_hardlockup_watchdog() in the future.
  */
 static inline void touch_nmi_watchdog(void)
 {
+	/*
+	 * Pass on to the hardlockup detector selected via CONFIG_. Note that
+	 * the hardlockup detector may not be arch-specific nor using NMIs
+	 * and the arch_touch_nmi_watchdog() function will likely be renamed
+	 * in the future.
+	 */
 	arch_touch_nmi_watchdog();
+
 	touch_softlockup_watchdog();
 }
 
@@ -145,31 +157,31 @@ static inline void touch_nmi_watchdog(void)
 #ifdef arch_trigger_cpumask_backtrace
 static inline bool trigger_all_cpu_backtrace(void)
 {
-	arch_trigger_cpumask_backtrace(cpu_online_mask, false);
+	arch_trigger_cpumask_backtrace(cpu_online_mask, -1);
 	return true;
 }
 
-static inline bool trigger_allbutself_cpu_backtrace(void)
+static inline bool trigger_allbutcpu_cpu_backtrace(int exclude_cpu)
 {
-	arch_trigger_cpumask_backtrace(cpu_online_mask, true);
+	arch_trigger_cpumask_backtrace(cpu_online_mask, exclude_cpu);
 	return true;
 }
 
 static inline bool trigger_cpumask_backtrace(struct cpumask *mask)
 {
-	arch_trigger_cpumask_backtrace(mask, false);
+	arch_trigger_cpumask_backtrace(mask, -1);
 	return true;
 }
 
 static inline bool trigger_single_cpu_backtrace(int cpu)
 {
-	arch_trigger_cpumask_backtrace(cpumask_of(cpu), false);
+	arch_trigger_cpumask_backtrace(cpumask_of(cpu), -1);
 	return true;
 }
 
 /* generic implementation */
 void nmi_trigger_cpumask_backtrace(const cpumask_t *mask,
-				   bool exclude_self,
+				   int exclude_cpu,
 				   void (*raise)(cpumask_t *mask));
 bool nmi_cpu_backtrace(struct pt_regs *regs);
 
@@ -178,7 +190,7 @@ static inline bool trigger_all_cpu_backtrace(void)
 {
 	return false;
 }
-static inline bool trigger_allbutself_cpu_backtrace(void)
+static inline bool trigger_allbutcpu_cpu_backtrace(int exclude_cpu)
 {
 	return false;
 }
@@ -194,22 +206,16 @@ static inline bool trigger_single_cpu_backtrace(int cpu)
 
 #ifdef CONFIG_HARDLOCKUP_DETECTOR_PERF
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
+bool arch_perf_nmi_is_available(void);
 #endif
 
 #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \
-    defined(CONFIG_HARDLOCKUP_DETECTOR)
+    defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 void watchdog_update_hrtimer_threshold(u64 period);
 #else
 static inline void watchdog_update_hrtimer_threshold(u64 period) { }
 #endif
 
-struct ctl_table;
-int proc_watchdog(struct ctl_table *, int, void *, size_t *, loff_t *);
-int proc_nmi_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *);
-int proc_soft_watchdog(struct ctl_table *, int , void *, size_t *, loff_t *);
-int proc_watchdog_thresh(struct ctl_table *, int , void *, size_t *, loff_t *);
-int proc_watchdog_cpumask(struct ctl_table *, int, void *, size_t *, loff_t *);
-
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
 #include <asm/nmi.h>
 #endif
diff --git a/include/linux/node.h b/include/linux/node.h
index 427a5975cf40..0269b064ba65 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -16,24 +16,35 @@
 #define _LINUX_NODE_H_
 
 #include <linux/device.h>
-#include <linux/cpumask.h>
 #include <linux/list.h>
 
 /**
- * struct node_hmem_attrs - heterogeneous memory performance attributes
+ * struct access_coordinate - generic performance coordinates container
  *
  * @read_bandwidth:	Read bandwidth in MB/s
  * @write_bandwidth:	Write bandwidth in MB/s
  * @read_latency:	Read latency in nanoseconds
  * @write_latency:	Write latency in nanoseconds
  */
-struct node_hmem_attrs {
+struct access_coordinate {
 	unsigned int read_bandwidth;
 	unsigned int write_bandwidth;
 	unsigned int read_latency;
 	unsigned int write_latency;
 };
 
+/*
+ * ACCESS_COORDINATE_LOCAL correlates to ACCESS CLASS 0
+ *	- access_coordinate between target node and nearest initiator node
+ * ACCESS_COORDINATE_CPU correlates to ACCESS CLASS 1
+ *	- access_coordinate between target node and nearest CPU node
+ */
+enum access_coordinate_class {
+	ACCESS_COORDINATE_LOCAL,
+	ACCESS_COORDINATE_CPU,
+	ACCESS_COORDINATE_MAX
+};
+
 enum cache_indexing {
 	NODE_CACHE_DIRECT_MAP,
 	NODE_CACHE_INDEXED,
@@ -46,6 +57,11 @@ enum cache_write_policy {
 	NODE_CACHE_WRITE_OTHER,
 };
 
+enum cache_mode {
+	NODE_CACHE_ADDR_MODE_RESERVED,
+	NODE_CACHE_ADDR_MODE_EXTENDED_LINEAR,
+};
+
 /**
  * struct node_cache_attrs - system memory caching attributes
  *
@@ -54,6 +70,7 @@ enum cache_write_policy {
  * @size:		Total size of cache in bytes
  * @line_size:		Number of bytes fetched on a cache miss
  * @level:		The cache hierarchy level
+ * @address_mode:		The address mode
  */
 struct node_cache_attrs {
 	enum cache_indexing indexing;
@@ -61,12 +78,15 @@ struct node_cache_attrs {
 	u64 size;
 	u16 line_size;
 	u8 level;
+	u16 address_mode;
 };
 
 #ifdef CONFIG_HMEM_REPORTING
 void node_add_cache(unsigned int nid, struct node_cache_attrs *cache_attrs);
-void node_set_perf_attrs(unsigned int nid, struct node_hmem_attrs *hmem_attrs,
-			 unsigned access);
+void node_set_perf_attrs(unsigned int nid, struct access_coordinate *coord,
+			 enum access_coordinate_class access);
+void node_update_perf_attrs(unsigned int nid, struct access_coordinate *coord,
+			    enum access_coordinate_class access);
 #else
 static inline void node_add_cache(unsigned int nid,
 				  struct node_cache_attrs *cache_attrs)
@@ -74,8 +94,14 @@ static inline void node_add_cache(unsigned int nid,
 }
 
 static inline void node_set_perf_attrs(unsigned int nid,
-				       struct node_hmem_attrs *hmem_attrs,
-				       unsigned access)
+				       struct access_coordinate *coord,
+				       enum access_coordinate_class access)
+{
+}
+
+static inline void node_update_perf_attrs(unsigned int nid,
+					  struct access_coordinate *coord,
+					  enum access_coordinate_class access)
 {
 }
 #endif
@@ -93,64 +119,79 @@ struct memory_block;
 extern struct node *node_devices[];
 
 #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA)
-void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
-				       unsigned long end_pfn,
-				       enum meminit_context context);
+void register_memory_blocks_under_node_hotplug(int nid, unsigned long start_pfn,
+					       unsigned long end_pfn);
 #else
-static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
-						     unsigned long end_pfn,
-						     enum meminit_context context)
+static inline void register_memory_blocks_under_node_hotplug(int nid,
+							     unsigned long start_pfn,
+							     unsigned long end_pfn)
 {
 }
-#endif
-
-extern void unregister_node(struct node *node);
-#ifdef CONFIG_NUMA
-extern void node_dev_init(void);
-/* Core of the node registration - only memory hotplug should use this */
-extern int __register_one_node(int nid);
-
-/* Registers an online node */
-static inline int register_one_node(int nid)
+static inline void register_memory_blocks_under_nodes(void)
 {
-	int error = 0;
+}
+#endif
 
-	if (node_online(nid)) {
-		struct pglist_data *pgdat = NODE_DATA(nid);
-		unsigned long start_pfn = pgdat->node_start_pfn;
-		unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
+struct node_notify {
+	int nid;
+};
 
-		error = __register_one_node(nid);
-		if (error)
-			return error;
-		register_memory_blocks_under_node(nid, start_pfn, end_pfn,
-						  MEMINIT_EARLY);
-	}
+#define NODE_ADDING_FIRST_MEMORY                (1<<0)
+#define NODE_ADDED_FIRST_MEMORY                 (1<<1)
+#define NODE_CANCEL_ADDING_FIRST_MEMORY         (1<<2)
+#define NODE_REMOVING_LAST_MEMORY               (1<<3)
+#define NODE_REMOVED_LAST_MEMORY                (1<<4)
+#define NODE_CANCEL_REMOVING_LAST_MEMORY        (1<<5)
 
-	return error;
+#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA)
+extern int register_node_notifier(struct notifier_block *nb);
+extern void unregister_node_notifier(struct notifier_block *nb);
+extern int node_notify(unsigned long val, void *v);
+
+#define hotplug_node_notifier(fn, pri) ({		\
+	static __meminitdata struct notifier_block fn##_node_nb =\
+		{ .notifier_call = fn, .priority = pri };\
+	register_node_notifier(&fn##_node_nb);			\
+})
+#else
+static inline int register_node_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+static inline void unregister_node_notifier(struct notifier_block *nb)
+{
+}
+static inline int node_notify(unsigned long val, void *v)
+{
+	return 0;
+}
+static inline int hotplug_node_notifier(notifier_fn_t fn, int pri)
+{
+	return 0;
 }
+#endif
 
-extern void unregister_one_node(int nid);
+#ifdef CONFIG_NUMA
+extern void node_dev_init(void);
+/* Core of the node registration - only memory hotplug should use this */
+int register_node(int nid);
+void unregister_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern void unregister_memory_block_under_nodes(struct memory_block *mem_blk);
 
 extern int register_memory_node_under_compute_node(unsigned int mem_nid,
 						   unsigned int cpu_nid,
-						   unsigned access);
+						   enum access_coordinate_class access);
 #else
 static inline void node_dev_init(void)
 {
 }
-static inline int __register_one_node(int nid)
-{
-	return 0;
-}
-static inline int register_one_node(int nid)
+static inline int register_node(int nid)
 {
 	return 0;
 }
-static inline int unregister_one_node(int nid)
+static inline int unregister_node(int nid)
 {
 	return 0;
 }
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index bb0ee80526b2..bd38648c998d 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -39,9 +39,6 @@
  * int nodes_full(mask)			Is mask full (all bits sets)?
  * int nodes_weight(mask)		Hamming weight - number of set bits
  *
- * void nodes_shift_right(dst, src, n)	Shift right
- * void nodes_shift_left(dst, src, n)	Shift left
- *
  * unsigned int first_node(mask)	Number lowest set bit, or MAX_NUMNODES
  * unsigend int next_node(node, mask)	Next node past 'node', or MAX_NUMNODES
  * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first,
@@ -93,10 +90,9 @@
 #include <linux/threads.h>
 #include <linux/bitmap.h>
 #include <linux/minmax.h>
-#include <linux/numa.h>
+#include <linux/nodemask_types.h>
 #include <linux/random.h>
 
-typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
 extern nodemask_t _unused_nodemask_arg_;
 
 /**
@@ -107,11 +103,11 @@ extern nodemask_t _unused_nodemask_arg_;
  */
 #define nodemask_pr_args(maskp)	__nodemask_pr_numnodes(maskp), \
 				__nodemask_pr_bits(maskp)
-static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
+static __always_inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m)
 {
 	return m ? MAX_NUMNODES : 0;
 }
-static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
+static __always_inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m)
 {
 	return m ? m->bits : NULL;
 }
@@ -132,19 +128,19 @@ static __always_inline void __node_set(int node, volatile nodemask_t *dstp)
 }
 
 #define node_clear(node, dst) __node_clear((node), &(dst))
-static inline void __node_clear(int node, volatile nodemask_t *dstp)
+static __always_inline void __node_clear(int node, volatile nodemask_t *dstp)
 {
 	clear_bit(node, dstp->bits);
 }
 
 #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES)
-static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
+static __always_inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_fill(dstp->bits, nbits);
 }
 
 #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES)
-static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
+static __always_inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 {
 	bitmap_zero(dstp->bits, nbits);
 }
@@ -154,14 +150,14 @@ static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits)
 
 #define node_test_and_set(node, nodemask) \
 			__node_test_and_set((node), &(nodemask))
-static inline bool __node_test_and_set(int node, nodemask_t *addr)
+static __always_inline bool __node_test_and_set(int node, nodemask_t *addr)
 {
 	return test_and_set_bit(node, addr->bits);
 }
 
 #define nodes_and(dst, src1, src2) \
 			__nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -169,7 +165,7 @@ static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_or(dst, src1, src2) \
 			__nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -177,7 +173,7 @@ static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_xor(dst, src1, src2) \
 			__nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits);
@@ -185,15 +181,22 @@ static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p,
 
 #define nodes_andnot(dst, src1, src2) \
 			__nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES)
-static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
+static __always_inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
+#define nodes_copy(dst, src) __nodes_copy(&(dst), &(src), MAX_NUMNODES)
+static __always_inline void __nodes_copy(nodemask_t *dstp,
+					const nodemask_t *srcp, unsigned int nbits)
+{
+	bitmap_copy(dstp->bits, srcp->bits, nbits);
+}
+
 #define nodes_complement(dst, src) \
 			__nodes_complement(&(dst), &(src), MAX_NUMNODES)
-static inline void __nodes_complement(nodemask_t *dstp,
+static __always_inline void __nodes_complement(nodemask_t *dstp,
 					const nodemask_t *srcp, unsigned int nbits)
 {
 	bitmap_complement(dstp->bits, srcp->bits, nbits);
@@ -201,7 +204,7 @@ static inline void __nodes_complement(nodemask_t *dstp,
 
 #define nodes_equal(src1, src2) \
 			__nodes_equal(&(src1), &(src2), MAX_NUMNODES)
-static inline bool __nodes_equal(const nodemask_t *src1p,
+static __always_inline bool __nodes_equal(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_equal(src1p->bits, src2p->bits, nbits);
@@ -209,7 +212,7 @@ static inline bool __nodes_equal(const nodemask_t *src1p,
 
 #define nodes_intersects(src1, src2) \
 			__nodes_intersects(&(src1), &(src2), MAX_NUMNODES)
-static inline bool __nodes_intersects(const nodemask_t *src1p,
+static __always_inline bool __nodes_intersects(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_intersects(src1p->bits, src2p->bits, nbits);
@@ -217,59 +220,43 @@ static inline bool __nodes_intersects(const nodemask_t *src1p,
 
 #define nodes_subset(src1, src2) \
 			__nodes_subset(&(src1), &(src2), MAX_NUMNODES)
-static inline bool __nodes_subset(const nodemask_t *src1p,
+static __always_inline bool __nodes_subset(const nodemask_t *src1p,
 					const nodemask_t *src2p, unsigned int nbits)
 {
 	return bitmap_subset(src1p->bits, src2p->bits, nbits);
 }
 
 #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES)
-static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
+static __always_inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_empty(srcp->bits, nbits);
 }
 
 #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES)
-static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
+static __always_inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_full(srcp->bits, nbits);
 }
 
 #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES)
-static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
+static __always_inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits)
 {
 	return bitmap_weight(srcp->bits, nbits);
 }
 
-#define nodes_shift_right(dst, src, n) \
-			__nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES)
-static inline void __nodes_shift_right(nodemask_t *dstp,
-					const nodemask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_right(dstp->bits, srcp->bits, n, nbits);
-}
-
-#define nodes_shift_left(dst, src, n) \
-			__nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES)
-static inline void __nodes_shift_left(nodemask_t *dstp,
-					const nodemask_t *srcp, int n, int nbits)
-{
-	bitmap_shift_left(dstp->bits, srcp->bits, n, nbits);
-}
-
 /* FIXME: better would be to fix all architectures to never return
-          > MAX_NUMNODES, then the silly min_ts could be dropped. */
+          > MAX_NUMNODES, then the silly min()s could be dropped. */
 
 #define first_node(src) __first_node(&(src))
-static inline unsigned int __first_node(const nodemask_t *srcp)
+static __always_inline unsigned int __first_node(const nodemask_t *srcp)
 {
-	return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
+	return min(MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES));
 }
 
 #define next_node(n, src) __next_node((n), &(src))
-static inline unsigned int __next_node(int n, const nodemask_t *srcp)
+static __always_inline unsigned int __next_node(int n, const nodemask_t *srcp)
 {
-	return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
+	return min(MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1));
 }
 
 /*
@@ -277,7 +264,7 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp)
  * the first node in src if needed.  Returns MAX_NUMNODES if src is empty.
  */
 #define next_node_in(n, src) __next_node_in((n), &(src))
-static inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
+static __always_inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
 {
 	unsigned int ret = __next_node(node, srcp);
 
@@ -286,7 +273,7 @@ static inline unsigned int __next_node_in(int node, const nodemask_t *srcp)
 	return ret;
 }
 
-static inline void init_nodemask_of_node(nodemask_t *mask, int node)
+static __always_inline void init_nodemask_of_node(nodemask_t *mask, int node)
 {
 	nodes_clear(*mask);
 	node_set(node, *mask);
@@ -304,10 +291,9 @@ static inline void init_nodemask_of_node(nodemask_t *mask, int node)
 })
 
 #define first_unset_node(mask) __first_unset_node(&(mask))
-static inline unsigned int __first_unset_node(const nodemask_t *maskp)
+static __always_inline unsigned int __first_unset_node(const nodemask_t *maskp)
 {
-	return min_t(unsigned int, MAX_NUMNODES,
-			find_first_zero_bit(maskp->bits, MAX_NUMNODES));
+	return min(MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES));
 }
 
 #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES)
@@ -338,21 +324,21 @@ static inline unsigned int __first_unset_node(const nodemask_t *maskp)
 
 #define nodemask_parse_user(ubuf, ulen, dst) \
 		__nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES)
-static inline int __nodemask_parse_user(const char __user *buf, int len,
+static __always_inline int __nodemask_parse_user(const char __user *buf, int len,
 					nodemask_t *dstp, int nbits)
 {
 	return bitmap_parse_user(buf, len, dstp->bits, nbits);
 }
 
 #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES)
-static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits)
+static __always_inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits)
 {
 	return bitmap_parselist(buf, dstp->bits, nbits);
 }
 
 #define node_remap(oldbit, old, new) \
 		__node_remap((oldbit), &(old), &(new), MAX_NUMNODES)
-static inline int __node_remap(int oldbit,
+static __always_inline int __node_remap(int oldbit,
 		const nodemask_t *oldp, const nodemask_t *newp, int nbits)
 {
 	return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits);
@@ -360,7 +346,7 @@ static inline int __node_remap(int oldbit,
 
 #define nodes_remap(dst, src, old, new) \
 		__nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES)
-static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
+static __always_inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
 		const nodemask_t *oldp, const nodemask_t *newp, int nbits)
 {
 	bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits);
@@ -368,7 +354,7 @@ static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp,
 
 #define nodes_onto(dst, orig, relmap) \
 		__nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES)
-static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
+static __always_inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
 		const nodemask_t *relmapp, int nbits)
 {
 	bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits);
@@ -376,7 +362,7 @@ static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp,
 
 #define nodes_fold(dst, orig, sz) \
 		__nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES)
-static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
+static __always_inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
 		int sz, int nbits)
 {
 	bitmap_fold(dstp->bits, origp->bits, sz, nbits);
@@ -385,7 +371,7 @@ static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp,
 #if MAX_NUMNODES > 1
 #define for_each_node_mask(node, mask)				    \
 	for ((node) = first_node(mask);				    \
-	     (node >= 0) && (node) < MAX_NUMNODES;		    \
+	     (node) < MAX_NUMNODES;				    \
 	     (node) = next_node((node), (mask)))
 #else /* MAX_NUMNODES == 1 */
 #define for_each_node_mask(node, mask)                                  \
@@ -418,22 +404,22 @@ enum node_states {
 extern nodemask_t node_states[NR_NODE_STATES];
 
 #if MAX_NUMNODES > 1
-static inline int node_state(int node, enum node_states state)
+static __always_inline int node_state(int node, enum node_states state)
 {
 	return node_isset(node, node_states[state]);
 }
 
-static inline void node_set_state(int node, enum node_states state)
+static __always_inline void node_set_state(int node, enum node_states state)
 {
 	__node_set(node, &node_states[state]);
 }
 
-static inline void node_clear_state(int node, enum node_states state)
+static __always_inline void node_clear_state(int node, enum node_states state)
 {
 	__node_clear(node, &node_states[state]);
 }
 
-static inline int num_node_state(enum node_states state)
+static __always_inline int num_node_state(enum node_states state)
 {
 	return nodes_weight(node_states[state]);
 }
@@ -443,11 +429,11 @@ static inline int num_node_state(enum node_states state)
 
 #define first_online_node	first_node(node_states[N_ONLINE])
 #define first_memory_node	first_node(node_states[N_MEMORY])
-static inline unsigned int next_online_node(int nid)
+static __always_inline unsigned int next_online_node(int nid)
 {
 	return next_node(nid, node_states[N_ONLINE]);
 }
-static inline unsigned int next_memory_node(int nid)
+static __always_inline unsigned int next_memory_node(int nid)
 {
 	return next_node(nid, node_states[N_MEMORY]);
 }
@@ -455,13 +441,13 @@ static inline unsigned int next_memory_node(int nid)
 extern unsigned int nr_node_ids;
 extern unsigned int nr_online_nodes;
 
-static inline void node_set_online(int nid)
+static __always_inline void node_set_online(int nid)
 {
 	node_set_state(nid, N_ONLINE);
 	nr_online_nodes = num_node_state(N_ONLINE);
 }
 
-static inline void node_set_offline(int nid)
+static __always_inline void node_set_offline(int nid)
 {
 	node_clear_state(nid, N_ONLINE);
 	nr_online_nodes = num_node_state(N_ONLINE);
@@ -469,20 +455,20 @@ static inline void node_set_offline(int nid)
 
 #else
 
-static inline int node_state(int node, enum node_states state)
+static __always_inline int node_state(int node, enum node_states state)
 {
 	return node == 0;
 }
 
-static inline void node_set_state(int node, enum node_states state)
+static __always_inline void node_set_state(int node, enum node_states state)
 {
 }
 
-static inline void node_clear_state(int node, enum node_states state)
+static __always_inline void node_clear_state(int node, enum node_states state)
 {
 }
 
-static inline int num_node_state(enum node_states state)
+static __always_inline int num_node_state(enum node_states state)
 {
 	return 1;
 }
@@ -502,24 +488,12 @@ static inline int num_node_state(enum node_states state)
 
 #endif
 
-static inline int node_random(const nodemask_t *maskp)
+static __always_inline int node_random(const nodemask_t *maskp)
 {
 #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1)
-	int w, bit;
-
-	w = nodes_weight(*maskp);
-	switch (w) {
-	case 0:
-		bit = NUMA_NO_NODE;
-		break;
-	case 1:
-		bit = first_node(*maskp);
-		break;
-	default:
-		bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_u32_below(w));
-		break;
-	}
-	return bit;
+	int node = find_random_bit(maskp->bits, MAX_NUMNODES);
+
+	return node < MAX_NUMNODES ? node : NUMA_NO_NODE;
 #else
 	return 0;
 #endif
@@ -535,6 +509,7 @@ static inline int node_random(const nodemask_t *maskp)
 
 #define for_each_node(node)	   for_each_node_state(node, N_POSSIBLE)
 #define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
+#define for_each_node_with_cpus(node)	for_each_node_state(node, N_CPU)
 
 /*
  * For nodemask scratch area.
diff --git a/include/linux/nodemask_types.h b/include/linux/nodemask_types.h
new file mode 100644
index 000000000000..f850a48742f1
--- /dev/null
+++ b/include/linux/nodemask_types.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_NODEMASK_TYPES_H
+#define __LINUX_NODEMASK_TYPES_H
+
+#include <linux/bitops.h>
+
+#ifdef CONFIG_NODES_SHIFT
+#define NODES_SHIFT     CONFIG_NODES_SHIFT
+#else
+#define NODES_SHIFT     0
+#endif
+
+#define MAX_NUMNODES    (1 << NODES_SHIFT)
+
+#define	NUMA_NO_NODE	(-1)
+
+typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t;
+
+#endif /* __LINUX_NODEMASK_TYPES_H */
diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 2aba75145144..01b6c9d9956f 100644
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -73,9 +73,7 @@ struct raw_notifier_head {
 
 struct srcu_notifier_head {
 	struct mutex mutex;
-#ifdef CONFIG_TREE_SRCU
 	struct srcu_usage srcuu;
-#endif
 	struct srcu_struct srcu;
 	struct notifier_block __rcu *head;
 };
@@ -110,7 +108,8 @@ extern void srcu_init_notifier_head(struct srcu_notifier_head *nh);
 	{							\
 		.mutex = __MUTEX_INITIALIZER(name.mutex),	\
 		.head = NULL,					\
-		.srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu), \
+		.srcuu = __SRCU_USAGE_INIT(name.srcuu),		\
+		.srcu = __SRCU_STRUCT_INIT(name.srcu, name.srcuu, pcpu, 0), \
 	}
 
 #define ATOMIC_NOTIFIER_HEAD(name)				\
@@ -238,7 +237,5 @@ static inline int notifier_to_errno(int ret)
 #define KBD_KEYSYM		0x0004 /* Keyboard keysym */
 #define KBD_POST_KEYSYM		0x0005 /* Called after keyboard keysym interpretation */
 
-extern struct blocking_notifier_head reboot_notifier_list;
-
 #endif /* __KERNEL__ */
 #endif /* _LINUX_NOTIFIER_H */
diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h
new file mode 100644
index 000000000000..b332b019b29c
--- /dev/null
+++ b/include/linux/ns/ns_common_types.h
@@ -0,0 +1,196 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_NS_COMMON_TYPES_H
+#define _LINUX_NS_COMMON_TYPES_H
+
+#include <linux/atomic.h>
+#include <linux/ns/nstree_types.h>
+#include <linux/rbtree.h>
+#include <linux/refcount.h>
+#include <linux/types.h>
+
+struct cgroup_namespace;
+struct dentry;
+struct ipc_namespace;
+struct mnt_namespace;
+struct net;
+struct pid_namespace;
+struct proc_ns_operations;
+struct time_namespace;
+struct user_namespace;
+struct uts_namespace;
+
+extern struct cgroup_namespace init_cgroup_ns;
+extern struct ipc_namespace init_ipc_ns;
+extern struct mnt_namespace init_mnt_ns;
+extern struct net init_net;
+extern struct pid_namespace init_pid_ns;
+extern struct time_namespace init_time_ns;
+extern struct user_namespace init_user_ns;
+extern struct uts_namespace init_uts_ns;
+
+extern const struct proc_ns_operations cgroupns_operations;
+extern const struct proc_ns_operations ipcns_operations;
+extern const struct proc_ns_operations mntns_operations;
+extern const struct proc_ns_operations netns_operations;
+extern const struct proc_ns_operations pidns_operations;
+extern const struct proc_ns_operations pidns_for_children_operations;
+extern const struct proc_ns_operations timens_operations;
+extern const struct proc_ns_operations timens_for_children_operations;
+extern const struct proc_ns_operations userns_operations;
+extern const struct proc_ns_operations utsns_operations;
+
+/*
+ * Namespace lifetimes are managed via a two-tier reference counting model:
+ *
+ * (1) __ns_ref (refcount_t): Main reference count tracking memory
+ *     lifetime. Controls when the namespace structure itself is freed.
+ *     It also pins the namespace on the namespace trees whereas (2)
+ *     only regulates their visibility to userspace.
+ *
+ * (2) __ns_ref_active (atomic_t): Reference count tracking active users.
+ *     Controls visibility of the namespace in the namespace trees.
+ *     Any live task that uses the namespace (via nsproxy or cred) holds
+ *     an active reference. Any open file descriptor or bind-mount of
+ *     the namespace holds an active reference. Once all tasks have
+ *     called exited their namespaces and all file descriptors and
+ *     bind-mounts have been released the active reference count drops
+ *     to zero and the namespace becomes inactive. IOW, the namespace
+ *     cannot be listed or opened via file handles anymore.
+ *
+ *     Note that it is valid to transition from active to inactive and
+ *     back from inactive to active e.g., when resurrecting an inactive
+ *     namespace tree via the SIOCGSKNS ioctl().
+ *
+ * Relationship and lifecycle states:
+ *
+ * - Active (__ns_ref_active > 0):
+ *   Namespace is actively used and visible to userspace. The namespace
+ *   can be reopened via /proc/<pid>/ns/<ns_type>, via namespace file
+ *   handles, or discovered via listns().
+ *
+ * - Inactive (__ns_ref_active == 0, __ns_ref > 0):
+ *   No tasks are actively using the namespace and it isn't pinned by
+ *   any bind-mounts or open file descriptors anymore. But the namespace
+ *   is still kept alive by internal references. For example, the user
+ *   namespace could be pinned by an open file through file->f_cred
+ *   references when one of the now defunct tasks had opened a file and
+ *   handed the file descriptor off to another process via a UNIX
+ *   sockets. Such references keep the namespace structure alive through
+ *   __ns_ref but will not hold an active reference.
+ *
+ * - Destroyed (__ns_ref == 0):
+ *   No references remain. The namespace is removed from the tree and freed.
+ *
+ * State transitions:
+ *
+ * Active -> Inactive:
+ *   When the last task using the namespace exits it drops its active
+ *   references to all namespaces. However, user and pid namespaces
+ *   remain accessible until the task has been reaped.
+ *
+ * Inactive -> Active:
+ *   An inactive namespace tree might be resurrected due to e.g., the
+ *   SIOCGSKNS ioctl() on a socket.
+ *
+ * Inactive -> Destroyed:
+ *   When __ns_ref drops to zero the namespace is removed from the
+ *   namespaces trees and the memory is freed (after RCU grace period).
+ *
+ * Initial namespaces:
+ *   Boot-time namespaces (init_net, init_pid_ns, etc.) start with
+ *   __ns_ref_active = 1 and remain active forever.
+ *
+ * @ns_type: type of namespace (e.g., CLONE_NEWNET)
+ * @stashed: cached dentry to be used by the vfs
+ * @ops: namespace operations
+ * @inum: namespace inode number (quickly recycled for non-initial namespaces)
+ * @__ns_ref: main reference count (do not use directly)
+ * @ns_tree: namespace tree nodes and active reference count
+ */
+struct ns_common {
+	u32 ns_type;
+	struct dentry *stashed;
+	const struct proc_ns_operations *ops;
+	unsigned int inum;
+	refcount_t __ns_ref; /* do not use directly */
+	union {
+		struct ns_tree;
+		struct rcu_head ns_rcu;
+	};
+};
+
+#define to_ns_common(__ns)                                    \
+	_Generic((__ns),                                      \
+		struct cgroup_namespace *:       &(__ns)->ns, \
+		const struct cgroup_namespace *: &(__ns)->ns, \
+		struct ipc_namespace *:          &(__ns)->ns, \
+		const struct ipc_namespace *:    &(__ns)->ns, \
+		struct mnt_namespace *:          &(__ns)->ns, \
+		const struct mnt_namespace *:    &(__ns)->ns, \
+		struct net *:                    &(__ns)->ns, \
+		const struct net *:              &(__ns)->ns, \
+		struct pid_namespace *:          &(__ns)->ns, \
+		const struct pid_namespace *:    &(__ns)->ns, \
+		struct time_namespace *:         &(__ns)->ns, \
+		const struct time_namespace *:   &(__ns)->ns, \
+		struct user_namespace *:         &(__ns)->ns, \
+		const struct user_namespace *:   &(__ns)->ns, \
+		struct uts_namespace *:          &(__ns)->ns, \
+		const struct uts_namespace *:    &(__ns)->ns)
+
+#define ns_init_inum(__ns)                                     \
+	_Generic((__ns),                                       \
+		struct cgroup_namespace *: CGROUP_NS_INIT_INO, \
+		struct ipc_namespace *:    IPC_NS_INIT_INO,    \
+		struct mnt_namespace *:    MNT_NS_INIT_INO,    \
+		struct net *:              NET_NS_INIT_INO,    \
+		struct pid_namespace *:    PID_NS_INIT_INO,    \
+		struct time_namespace *:   TIME_NS_INIT_INO,   \
+		struct user_namespace *:   USER_NS_INIT_INO,   \
+		struct uts_namespace *:    UTS_NS_INIT_INO)
+
+#define ns_init_ns(__ns)                                    \
+	_Generic((__ns),                                    \
+		struct cgroup_namespace *: &init_cgroup_ns, \
+		struct ipc_namespace *:    &init_ipc_ns,    \
+		struct mnt_namespace *:    &init_mnt_ns,     \
+		struct net *:              &init_net,       \
+		struct pid_namespace *:    &init_pid_ns,    \
+		struct time_namespace *:   &init_time_ns,   \
+		struct user_namespace *:   &init_user_ns,   \
+		struct uts_namespace *:    &init_uts_ns)
+
+#define ns_init_id(__ns)						\
+	_Generic((__ns),						\
+		struct cgroup_namespace *:	CGROUP_NS_INIT_ID,	\
+		struct ipc_namespace *:		IPC_NS_INIT_ID,		\
+		struct mnt_namespace *:		MNT_NS_INIT_ID,		\
+		struct net *:			NET_NS_INIT_ID,		\
+		struct pid_namespace *:		PID_NS_INIT_ID,		\
+		struct time_namespace *:	TIME_NS_INIT_ID,	\
+		struct user_namespace *:	USER_NS_INIT_ID,	\
+		struct uts_namespace *:		UTS_NS_INIT_ID)
+
+#define to_ns_operations(__ns)                                                                         \
+	_Generic((__ns),                                                                               \
+		struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \
+		struct ipc_namespace *:    (IS_ENABLED(CONFIG_IPC_NS)  ? &ipcns_operations    : NULL), \
+		struct mnt_namespace *:    &mntns_operations,                                          \
+		struct net *:              (IS_ENABLED(CONFIG_NET_NS)  ? &netns_operations    : NULL), \
+		struct pid_namespace *:    (IS_ENABLED(CONFIG_PID_NS)  ? &pidns_operations    : NULL), \
+		struct time_namespace *:   (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations   : NULL), \
+		struct user_namespace *:   (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations   : NULL), \
+		struct uts_namespace *:    (IS_ENABLED(CONFIG_UTS_NS)  ? &utsns_operations    : NULL))
+
+#define ns_common_type(__ns)                                \
+	_Generic((__ns),                                    \
+		struct cgroup_namespace *: CLONE_NEWCGROUP, \
+		struct ipc_namespace *:    CLONE_NEWIPC,    \
+		struct mnt_namespace *:    CLONE_NEWNS,     \
+		struct net *:              CLONE_NEWNET,    \
+		struct pid_namespace *:    CLONE_NEWPID,    \
+		struct time_namespace *:   CLONE_NEWTIME,   \
+		struct user_namespace *:   CLONE_NEWUSER,   \
+		struct uts_namespace *:    CLONE_NEWUTS)
+
+#endif /* _LINUX_NS_COMMON_TYPES_H */
diff --git a/include/linux/ns/nstree_types.h b/include/linux/ns/nstree_types.h
new file mode 100644
index 000000000000..2fb28ee31efb
--- /dev/null
+++ b/include/linux/ns/nstree_types.h
@@ -0,0 +1,55 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */
+#ifndef _LINUX_NSTREE_TYPES_H
+#define _LINUX_NSTREE_TYPES_H
+
+#include <linux/rbtree.h>
+#include <linux/list.h>
+
+/**
+ * struct ns_tree_root - Root of a namespace tree
+ * @ns_rb: Red-black tree root for efficient lookups
+ * @ns_list_head: List head for sequential iteration
+ *
+ * Each namespace tree maintains both an rbtree (for O(log n) lookups)
+ * and a list (for efficient sequential iteration). The list is kept in
+ * the same sorted order as the rbtree.
+ */
+struct ns_tree_root {
+	struct rb_root ns_rb;
+	struct list_head ns_list_head;
+};
+
+/**
+ * struct ns_tree_node - Node in a namespace tree
+ * @ns_node: Red-black tree node
+ * @ns_list_entry: List entry for sequential iteration
+ *
+ * Represents a namespace's position in a tree. Each namespace has
+ * multiple tree nodes for different trees (unified, per-type, owner).
+ */
+struct ns_tree_node {
+	struct rb_node ns_node;
+	struct list_head ns_list_entry;
+};
+
+/**
+ * struct ns_tree - Namespace tree nodes and active reference count
+ * @ns_id: Unique namespace identifier
+ * @__ns_ref_active: Active reference count (do not use directly)
+ * @ns_unified_node: Node in the global namespace tree
+ * @ns_tree_node: Node in the per-type namespace tree
+ * @ns_owner_node: Node in the owner namespace's tree of owned namespaces
+ * @ns_owner_root: Root of the tree of namespaces owned by this namespace
+ *                 (only used when this namespace is an owner)
+ */
+struct ns_tree {
+	u64 ns_id;
+	atomic_t __ns_ref_active;
+	struct ns_tree_node ns_unified_node;
+	struct ns_tree_node ns_tree_node;
+	struct ns_tree_node ns_owner_node;
+	struct ns_tree_root ns_owner_root;
+};
+
+#endif /* _LINUX_NSTREE_TYPES_H */
diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h
index 0f1d024bd958..825f5865bfc5 100644
--- a/include/linux/ns_common.h
+++ b/include/linux/ns_common.h
@@ -2,15 +2,149 @@
 #ifndef _LINUX_NS_COMMON_H
 #define _LINUX_NS_COMMON_H
 
+#include <linux/ns/ns_common_types.h>
 #include <linux/refcount.h>
+#include <linux/vfsdebug.h>
+#include <uapi/linux/sched.h>
+#include <uapi/linux/nsfs.h>
 
-struct proc_ns_operations;
+bool is_current_namespace(struct ns_common *ns);
+int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum);
+void __ns_common_free(struct ns_common *ns);
+struct ns_common *__must_check ns_owner(struct ns_common *ns);
 
-struct ns_common {
-	atomic_long_t stashed;
-	const struct proc_ns_operations *ops;
-	unsigned int inum;
-	refcount_t count;
-};
+static __always_inline bool is_ns_init_inum(const struct ns_common *ns)
+{
+	VFS_WARN_ON_ONCE(ns->inum == 0);
+	return unlikely(in_range(ns->inum, MNT_NS_INIT_INO,
+				 IPC_NS_INIT_INO - MNT_NS_INIT_INO + 1));
+}
+
+static __always_inline bool is_ns_init_id(const struct ns_common *ns)
+{
+	VFS_WARN_ON_ONCE(ns->ns_id == 0);
+	return ns->ns_id <= NS_LAST_INIT_ID;
+}
+
+#define NS_COMMON_INIT(nsname)										\
+{													\
+	.ns_type			= ns_common_type(&nsname),					\
+	.ns_id				= ns_init_id(&nsname),						\
+	.inum				= ns_init_inum(&nsname),					\
+	.ops				= to_ns_operations(&nsname),					\
+	.stashed			= NULL,								\
+	.__ns_ref			= REFCOUNT_INIT(1),						\
+	.__ns_ref_active		= ATOMIC_INIT(1),						\
+	.ns_unified_node.ns_list_entry	= LIST_HEAD_INIT(nsname.ns.ns_unified_node.ns_list_entry),	\
+	.ns_tree_node.ns_list_entry	= LIST_HEAD_INIT(nsname.ns.ns_tree_node.ns_list_entry),		\
+	.ns_owner_node.ns_list_entry	= LIST_HEAD_INIT(nsname.ns.ns_owner_node.ns_list_entry),	\
+	.ns_owner_root.ns_list_head	= LIST_HEAD_INIT(nsname.ns.ns_owner_root.ns_list_head),		\
+}
+
+#define ns_common_init(__ns)                     \
+	__ns_common_init(to_ns_common(__ns),     \
+			 ns_common_type(__ns),   \
+			 to_ns_operations(__ns), \
+			 (((__ns) == ns_init_ns(__ns)) ? ns_init_inum(__ns) : 0))
+
+#define ns_common_init_inum(__ns, __inum)        \
+	__ns_common_init(to_ns_common(__ns),     \
+			 ns_common_type(__ns),   \
+			 to_ns_operations(__ns), \
+			 __inum)
+
+#define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns)))
+
+static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns)
+{
+	return atomic_read(&ns->__ns_ref_active);
+}
+
+static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns)
+{
+	return refcount_read(&ns->__ns_ref);
+}
+
+static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns)
+{
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return false;
+	}
+	if (refcount_dec_and_test(&ns->__ns_ref)) {
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns));
+		return true;
+	}
+	return false;
+}
+
+static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns)
+{
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return true;
+	}
+	if (refcount_inc_not_zero(&ns->__ns_ref))
+		return true;
+	VFS_WARN_ON_ONCE(__ns_ref_active_read(ns));
+	return false;
+}
+
+static __always_inline void __ns_ref_inc(struct ns_common *ns)
+{
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return;
+	}
+	refcount_inc(&ns->__ns_ref);
+}
+
+static __always_inline __must_check bool __ns_ref_dec_and_lock(struct ns_common *ns,
+							       spinlock_t *ns_lock)
+{
+	if (is_ns_init_id(ns)) {
+		VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1);
+		VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1);
+		return false;
+	}
+	return refcount_dec_and_lock(&ns->__ns_ref, ns_lock);
+}
+
+#define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns)))
+#define ns_ref_inc(__ns) \
+	do { if (__ns) __ns_ref_inc(to_ns_common((__ns))); } while (0)
+#define ns_ref_get(__ns) \
+	((__ns) ? __ns_ref_get(to_ns_common((__ns))) : false)
+#define ns_ref_put(__ns) \
+	((__ns) ? __ns_ref_put(to_ns_common((__ns))) : false)
+#define ns_ref_put_and_lock(__ns, __ns_lock) \
+	((__ns) ? __ns_ref_dec_and_lock(to_ns_common((__ns)), __ns_lock) : false)
+
+#define ns_ref_active_read(__ns) \
+	((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0)
+
+void __ns_ref_active_put(struct ns_common *ns);
+
+#define ns_ref_active_put(__ns) \
+	do { if (__ns) __ns_ref_active_put(to_ns_common(__ns)); } while (0)
+
+static __always_inline struct ns_common *__must_check ns_get_unless_inactive(struct ns_common *ns)
+{
+	if (!__ns_ref_active_read(ns)) {
+		VFS_WARN_ON_ONCE(is_ns_init_id(ns));
+		return NULL;
+	}
+	if (!__ns_ref_get(ns))
+		return NULL;
+	return ns;
+}
+
+void __ns_ref_active_get(struct ns_common *ns);
+
+#define ns_ref_active_get(__ns) \
+	do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0)
 
 #endif
diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h
new file mode 100644
index 000000000000..731b67fc2fec
--- /dev/null
+++ b/include/linux/nsfs.h
@@ -0,0 +1,43 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */
+
+#ifndef _LINUX_NSFS_H
+#define _LINUX_NSFS_H
+
+#include <linux/ns_common.h>
+#include <linux/cred.h>
+#include <linux/pid_namespace.h>
+
+struct path;
+struct task_struct;
+struct proc_ns_operations;
+
+int ns_get_path(struct path *path, struct task_struct *task,
+		const struct proc_ns_operations *ns_ops);
+typedef struct ns_common *ns_get_path_helper_t(void *);
+int ns_get_path_cb(struct path *path, ns_get_path_helper_t ns_get_cb,
+		   void *private_data);
+
+bool ns_match(const struct ns_common *ns, dev_t dev, ino_t ino);
+
+int ns_get_name(char *buf, size_t size, struct task_struct *task,
+			const struct proc_ns_operations *ns_ops);
+void nsfs_init(void);
+
+#define __current_namespace_from_type(__ns)				\
+	_Generic((__ns),						\
+		struct cgroup_namespace *: current->nsproxy->cgroup_ns,	\
+		struct ipc_namespace *:    current->nsproxy->ipc_ns,	\
+		struct net *:              current->nsproxy->net_ns,	\
+		struct pid_namespace *:    task_active_pid_ns(current),	\
+		struct mnt_namespace *:    current->nsproxy->mnt_ns,	\
+		struct time_namespace *:   current->nsproxy->time_ns,	\
+		struct user_namespace *:   current_user_ns(),		\
+		struct uts_namespace *:    current->nsproxy->uts_ns)
+
+#define current_in_namespace(__ns) (__current_namespace_from_type(__ns) == __ns)
+
+void nsproxy_ns_active_get(struct nsproxy *ns);
+void nsproxy_ns_active_put(struct nsproxy *ns);
+
+#endif /* _LINUX_NSFS_H */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index fee881cded01..5a67648721c7 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -2,6 +2,7 @@
 #ifndef _LINUX_NSPROXY_H
 #define _LINUX_NSPROXY_H
 
+#include <linux/refcount.h>
 #include <linux/spinlock.h>
 #include <linux/sched.h>
 
@@ -29,7 +30,7 @@ struct fs_struct;
  * nsproxy is copied.
  */
 struct nsproxy {
-	atomic_t count;
+	refcount_t count;
 	struct uts_namespace *uts_ns;
 	struct ipc_namespace *ipc_ns;
 	struct mnt_namespace *mnt_ns;
@@ -91,25 +92,29 @@ static inline struct cred *nsset_cred(struct nsset *set)
  *
  */
 
-int copy_namespaces(unsigned long flags, struct task_struct *tsk);
-void exit_task_namespaces(struct task_struct *tsk);
+int copy_namespaces(u64 flags, struct task_struct *tsk);
+void switch_cred_namespaces(const struct cred *old, const struct cred *new);
+void exit_nsproxy_namespaces(struct task_struct *tsk);
+void get_cred_namespaces(struct task_struct *tsk);
+void exit_cred_namespaces(struct task_struct *tsk);
 void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new);
 int exec_task_namespaces(void);
-void free_nsproxy(struct nsproxy *ns);
+void deactivate_nsproxy(struct nsproxy *ns);
 int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **,
 	struct cred *, struct fs_struct *);
 int __init nsproxy_cache_init(void);
 
 static inline void put_nsproxy(struct nsproxy *ns)
 {
-	if (atomic_dec_and_test(&ns->count)) {
-		free_nsproxy(ns);
-	}
+	if (refcount_dec_and_test(&ns->count))
+		deactivate_nsproxy(ns);
 }
 
 static inline void get_nsproxy(struct nsproxy *ns)
 {
-	atomic_inc(&ns->count);
+	refcount_inc(&ns->count);
 }
 
+DEFINE_FREE(put_nsproxy, struct nsproxy *, if (_T) put_nsproxy(_T))
+
 #endif
diff --git a/include/linux/nstree.h b/include/linux/nstree.h
new file mode 100644
index 000000000000..175e4625bfa6
--- /dev/null
+++ b/include/linux/nstree.h
@@ -0,0 +1,96 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */
+#ifndef _LINUX_NSTREE_H
+#define _LINUX_NSTREE_H
+
+#include <linux/ns/nstree_types.h>
+#include <linux/nsproxy.h>
+#include <linux/rbtree.h>
+#include <linux/seqlock.h>
+#include <linux/rculist.h>
+#include <linux/cookie.h>
+#include <uapi/linux/nsfs.h>
+
+struct ns_common;
+
+extern struct ns_tree_root cgroup_ns_tree;
+extern struct ns_tree_root ipc_ns_tree;
+extern struct ns_tree_root mnt_ns_tree;
+extern struct ns_tree_root net_ns_tree;
+extern struct ns_tree_root pid_ns_tree;
+extern struct ns_tree_root time_ns_tree;
+extern struct ns_tree_root user_ns_tree;
+extern struct ns_tree_root uts_ns_tree;
+
+void ns_tree_node_init(struct ns_tree_node *node);
+void ns_tree_root_init(struct ns_tree_root *root);
+bool ns_tree_node_empty(const struct ns_tree_node *node);
+struct rb_node *ns_tree_node_add(struct ns_tree_node *node,
+				  struct ns_tree_root *root,
+				  int (*cmp)(struct rb_node *, const struct rb_node *));
+void ns_tree_node_del(struct ns_tree_node *node, struct ns_tree_root *root);
+
+#define to_ns_tree(__ns)					\
+	_Generic((__ns),					\
+		struct cgroup_namespace *: &(cgroup_ns_tree),	\
+		struct ipc_namespace *:    &(ipc_ns_tree),	\
+		struct net *:              &(net_ns_tree),	\
+		struct pid_namespace *:    &(pid_ns_tree),	\
+		struct mnt_namespace *:    &(mnt_ns_tree),	\
+		struct time_namespace *:   &(time_ns_tree),	\
+		struct user_namespace *:   &(user_ns_tree),	\
+		struct uts_namespace *:    &(uts_ns_tree))
+
+#define ns_tree_gen_id(__ns)                 \
+	__ns_tree_gen_id(to_ns_common(__ns), \
+			 (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0))
+
+u64 __ns_tree_gen_id(struct ns_common *ns, u64 id);
+void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree_root *ns_tree);
+void __ns_tree_remove(struct ns_common *ns, struct ns_tree_root *ns_tree);
+struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type);
+struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns,
+					 struct ns_tree_root *ns_tree,
+					 bool previous);
+
+static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree_root *ns_tree, u64 id)
+{
+	__ns_tree_gen_id(ns, id);
+	__ns_tree_add_raw(ns, ns_tree);
+}
+
+/**
+ * ns_tree_add_raw - Add a namespace to a namespace
+ * @ns: Namespace to add
+ *
+ * This function adds a namespace to the appropriate namespace tree
+ * without assigning a id.
+ */
+#define ns_tree_add_raw(__ns) __ns_tree_add_raw(to_ns_common(__ns), to_ns_tree(__ns))
+
+/**
+ * ns_tree_add - Add a namespace to a namespace tree
+ * @ns: Namespace to add
+ *
+ * This function assigns a new id to the namespace and adds it to the
+ * appropriate namespace tree and list.
+ */
+#define ns_tree_add(__ns)                                   \
+	__ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns), \
+		      (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0))
+
+/**
+ * ns_tree_remove - Remove a namespace from a namespace tree
+ * @ns: Namespace to remove
+ *
+ * This function removes a namespace from the appropriate namespace
+ * tree and list.
+ */
+#define ns_tree_remove(__ns)  __ns_tree_remove(to_ns_common(__ns), to_ns_tree(__ns))
+
+#define ns_tree_adjoined_rcu(__ns, __previous) \
+	__ns_tree_adjoined_rcu(to_ns_common(__ns), to_ns_tree(__ns), __previous)
+
+#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node.ns_node))
+
+#endif /* _LINUX_NSTREE_H */
diff --git a/include/linux/nubus.h b/include/linux/nubus.h
index 392fc6c53e96..4d103ac8f5c7 100644
--- a/include/linux/nubus.h
+++ b/include/linux/nubus.h
@@ -89,10 +89,9 @@ struct nubus_driver {
 	void (*remove)(struct nubus_board *board);
 };
 
-extern struct bus_type nubus_bus_type;
-
 /* Generic NuBus interface functions, modelled after the PCI interface */
 #ifdef CONFIG_PROC_FS
+extern bool nubus_populate_procfs;
 void nubus_proc_init(void);
 struct proc_dir_entry *nubus_proc_add_board(struct nubus_board *board);
 struct proc_dir_entry *nubus_proc_add_rsrc_dir(struct proc_dir_entry *procdir,
diff --git a/include/linux/numa.h b/include/linux/numa.h
index 59df211d051f..e6baaf6051bc 100644
--- a/include/linux/numa.h
+++ b/include/linux/numa.h
@@ -1,17 +1,16 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 #ifndef _LINUX_NUMA_H
 #define _LINUX_NUMA_H
+#include <linux/init.h>
 #include <linux/types.h>
+#include <linux/nodemask.h>
 
-#ifdef CONFIG_NODES_SHIFT
-#define NODES_SHIFT     CONFIG_NODES_SHIFT
-#else
-#define NODES_SHIFT     0
-#endif
+#define	NUMA_NO_MEMBLK	(-1)
 
-#define MAX_NUMNODES    (1 << NODES_SHIFT)
-
-#define	NUMA_NO_NODE	(-1)
+static inline bool numa_valid_node(int nid)
+{
+	return nid >= 0 && nid < MAX_NUMNODES;
+}
 
 /* optionally keep NUMA memory info available post init */
 #ifdef CONFIG_NUMA_KEEP_MEMINFO
@@ -21,33 +20,40 @@
 #endif
 
 #ifdef CONFIG_NUMA
-#include <linux/printk.h>
 #include <asm/sparsemem.h>
 
+extern struct pglist_data *node_data[];
+#define NODE_DATA(nid)	(node_data[nid])
+
+void __init alloc_node_data(int nid);
+void __init alloc_offline_node_data(int nid);
+
 /* Generic implementation available */
-int numa_map_to_online_node(int node);
+int numa_nearest_node(int node, unsigned int state);
+
+int nearest_node_nodemask(int node, nodemask_t *mask);
 
 #ifndef memory_add_physaddr_to_nid
-static inline int memory_add_physaddr_to_nid(u64 start)
-{
-	pr_info_once("Unknown online node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
+int memory_add_physaddr_to_nid(u64 start);
 #endif
+
 #ifndef phys_to_target_node
-static inline int phys_to_target_node(u64 start)
-{
-	pr_info_once("Unknown target node for memory at 0x%llx, assuming node 0\n",
-			start);
-	return 0;
-}
+int phys_to_target_node(u64 start);
 #endif
+
+int numa_fill_memblks(u64 start, u64 end);
+
 #else /* !CONFIG_NUMA */
-static inline int numa_map_to_online_node(int node)
+static inline int numa_nearest_node(int node, unsigned int state)
 {
 	return NUMA_NO_NODE;
 }
+
+static inline int nearest_node_nodemask(int node, nodemask_t *mask)
+{
+	return NUMA_NO_NODE;
+}
+
 static inline int memory_add_physaddr_to_nid(u64 start)
 {
 	return 0;
@@ -56,8 +62,12 @@ static inline int phys_to_target_node(u64 start)
 {
 	return 0;
 }
+
+static inline void alloc_offline_node_data(int nid) {}
 #endif
 
+#define numa_map_to_online_node(node) numa_nearest_node(node, N_ONLINE)
+
 #ifdef CONFIG_HAVE_ARCH_NODE_DEV_GROUP
 extern const struct attribute_group arch_node_dev_group;
 #endif
diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h
new file mode 100644
index 000000000000..991076cba7c5
--- /dev/null
+++ b/include/linux/numa_memblks.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NUMA_MEMBLKS_H
+#define __NUMA_MEMBLKS_H
+
+#ifdef CONFIG_NUMA_MEMBLKS
+#include <linux/types.h>
+
+#define NR_NODE_MEMBLKS		(MAX_NUMNODES * 2)
+
+void __init numa_set_distance(int from, int to, int distance);
+void __init numa_reset_distance(void);
+
+struct numa_memblk {
+	u64			start;
+	u64			end;
+	int			nid;
+};
+
+struct numa_meminfo {
+	int			nr_blks;
+	struct numa_memblk	blk[NR_NODE_MEMBLKS];
+};
+
+int __init numa_add_memblk(int nodeid, u64 start, u64 end);
+int __init numa_add_reserved_memblk(int nid, u64 start, u64 end);
+void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi);
+
+int __init numa_cleanup_meminfo(struct numa_meminfo *mi);
+
+int __init numa_memblks_init(int (*init_func)(void),
+			     bool memblock_force_top_down);
+
+extern int numa_distance_cnt;
+
+#ifdef CONFIG_NUMA_EMU
+extern int emu_nid_to_phys[MAX_NUMNODES];
+int numa_emu_cmdline(char *str);
+void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
+					unsigned int nr_emu_nids);
+u64 __init numa_emu_dma_end(void);
+void __init numa_emulation(struct numa_meminfo *numa_meminfo,
+			   int numa_dist_cnt);
+#else
+static inline void numa_emulation(struct numa_meminfo *numa_meminfo,
+				  int numa_dist_cnt)
+{ }
+static inline int numa_emu_cmdline(char *str)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_NUMA_EMU */
+
+#ifdef CONFIG_NUMA_KEEP_MEMINFO
+extern int phys_to_target_node(u64 start);
+#define phys_to_target_node phys_to_target_node
+extern int memory_add_physaddr_to_nid(u64 start);
+#define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
+#endif /* CONFIG_NUMA_KEEP_MEMINFO */
+
+#endif /* CONFIG_NUMA_MEMBLKS */
+
+#endif	/* __NUMA_MEMBLKS_H */
diff --git a/include/linux/nvme-auth.h b/include/linux/nvme-auth.h
index dcb8030062dd..60e069a6757f 100644
--- a/include/linux/nvme-auth.h
+++ b/include/linux/nvme-auth.h
@@ -9,9 +9,9 @@
 #include <crypto/kpp.h>
 
 struct nvme_dhchap_key {
-	u8 *key;
 	size_t len;
 	u8 hash;
+	u8 key[];
 };
 
 u32 nvme_auth_get_seqnum(void);
@@ -24,10 +24,13 @@ const char *nvme_auth_digest_name(u8 hmac_id);
 size_t nvme_auth_hmac_hash_len(u8 hmac_id);
 u8 nvme_auth_hmac_id(const char *hmac_name);
 
+u32 nvme_auth_key_struct_size(u32 key_len);
 struct nvme_dhchap_key *nvme_auth_extract_key(unsigned char *secret,
 					      u8 key_hash);
 void nvme_auth_free_key(struct nvme_dhchap_key *key);
-u8 *nvme_auth_transform_key(struct nvme_dhchap_key *key, char *nqn);
+struct nvme_dhchap_key *nvme_auth_alloc_key(u32 len, u8 hash);
+struct nvme_dhchap_key *nvme_auth_transform_key(
+				struct nvme_dhchap_key *key, char *nqn);
 int nvme_auth_generate_key(u8 *secret, struct nvme_dhchap_key **ret_key);
 int nvme_auth_augmented_challenge(u8 hmac_id, u8 *skey, size_t skey_len,
 				  u8 *challenge, u8 *aug, size_t hlen);
@@ -37,5 +40,12 @@ int nvme_auth_gen_pubkey(struct crypto_kpp *dh_tfm,
 int nvme_auth_gen_shared_secret(struct crypto_kpp *dh_tfm,
 				u8 *ctrl_key, size_t ctrl_key_len,
 				u8 *sess_key, size_t sess_key_len);
+int nvme_auth_generate_psk(u8 hmac_id, u8 *skey, size_t skey_len,
+			   u8 *c1, u8 *c2, size_t hash_len,
+			   u8 **ret_psk, size_t *ret_len);
+int nvme_auth_generate_digest(u8 hmac_id, u8 *psk, size_t psk_len,
+		char *subsysnqn, char *hostnqn, u8 **ret_digest);
+int nvme_auth_derive_tls_psk(int hmac_id, u8 *psk, size_t psk_len,
+		u8 *psk_digest, u8 **ret_psk);
 
 #endif /* _NVME_AUTH_H */
diff --git a/include/linux/nvme-fc-driver.h b/include/linux/nvme-fc-driver.h
index fa092b9be2fd..9f6acadfe0c8 100644
--- a/include/linux/nvme-fc-driver.h
+++ b/include/linux/nvme-fc-driver.h
@@ -185,7 +185,6 @@ enum nvmefc_fcp_datadir {
  * @first_sgl: memory for 1st scatter/gather list segment for payload data
  * @sg_cnt:    number of elements in the scatter/gather list
  * @io_dir:    direction of the FCP request (see NVMEFC_FCP_xxx)
- * @sqid:      The nvme SQID the command is being issued on
  * @done:      The callback routine the LLDD is to invoke upon completion of
  *             the FCP operation. req argument is the pointer to the original
  *             FCP IO operation.
@@ -194,12 +193,13 @@ enum nvmefc_fcp_datadir {
  *             while processing the operation. The length of the buffer
  *             corresponds to the fcprqst_priv_sz value specified in the
  *             nvme_fc_port_template supplied by the LLDD.
+ * @sqid:      The nvme SQID the command is being issued on
  *
  * Values set by the LLDD indicating completion status of the FCP operation.
  * Must be set prior to calling the done() callback.
+ * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @transferred_length: amount of payload data, in bytes, that were
  *             transferred. Should equal payload_length on success.
- * @rcv_rsplen: length, in bytes, of the FCP RSP IU received.
  * @status:    Completion status of the FCP operation. must be 0 upon success,
  *             negative errno value upon failure (ex: -EIO). Note: this is
  *             NOT a reflection of the NVME CQE completion status. Only the
@@ -219,14 +219,14 @@ struct nvmefc_fcp_req {
 	int			sg_cnt;
 	enum nvmefc_fcp_datadir	io_dir;
 
-	__le16			sqid;
-
 	void (*done)(struct nvmefc_fcp_req *req);
 
 	void			*private;
 
-	u32			transferred_length;
+	__le16			sqid;
+
 	u16			rcv_rsplen;
+	u32			transferred_length;
 	u32			status;
 } __aligned(sizeof(u64));	/* alignment for other things alloc'd with */
 
@@ -620,7 +620,7 @@ enum {
  *
  * Structure used between LLDD and nvmet-fc layer to represent the exchange
  * context for a FC-NVME FCP I/O operation (e.g. a nvme sqe, the sqe-related
- * memory transfers, and its assocated cqe transfer).
+ * memory transfers, and its associated cqe transfer).
  *
  * The structure is allocated by the LLDD whenever a FCP CMD IU is received
  * from the FC link. The address of the structure is passed to the nvmet-fc
@@ -920,6 +920,9 @@ struct nvmet_fc_target_port {
  *       further references to hosthandle.
  *       Entrypoint is Mandatory if the lldd calls nvmet_fc_invalidate_host().
  *
+ * @host_traddr: called by the transport to retrieve the node name and
+ *       port name of the host port address.
+ *
  * @max_hw_queues:  indicates the maximum number of hw queues the LLDD
  *       supports for cpu affinitization.
  *       Value is Mandatory. Must be at least 1.
@@ -975,6 +978,7 @@ struct nvmet_fc_target_template {
 	void (*ls_abort)(struct nvmet_fc_target_port *targetport,
 				void *hosthandle, struct nvmefc_ls_req *lsreq);
 	void (*host_release)(void *hosthandle);
+	int (*host_traddr)(void *hosthandle, u64 *wwnn, u64 *wwpn);
 
 	u32	max_hw_queues;
 	u16	max_sgl_segments;
diff --git a/include/linux/nvme-keyring.h b/include/linux/nvme-keyring.h
new file mode 100644
index 000000000000..ab8971afa973
--- /dev/null
+++ b/include/linux/nvme-keyring.h
@@ -0,0 +1,42 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 Hannes Reinecke, SUSE Labs
+ */
+
+#ifndef _NVME_KEYRING_H
+#define _NVME_KEYRING_H
+
+#include <linux/key.h>
+
+#if IS_ENABLED(CONFIG_NVME_KEYRING)
+
+struct key *nvme_tls_psk_refresh(struct key *keyring,
+		const char *hostnqn, const char *subnqn, u8 hmac_id,
+		u8 *data, size_t data_len, const char *digest);
+key_serial_t nvme_tls_psk_default(struct key *keyring,
+		const char *hostnqn, const char *subnqn);
+
+key_serial_t nvme_keyring_id(void);
+struct key *nvme_tls_key_lookup(key_serial_t key_id);
+#else
+static inline struct key *nvme_tls_psk_refresh(struct key *keyring,
+		const char *hostnqn, char *subnqn, u8 hmac_id,
+		u8 *data, size_t data_len, const char *digest)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+static inline key_serial_t nvme_tls_psk_default(struct key *keyring,
+		const char *hostnqn, const char *subnqn)
+{
+	return 0;
+}
+static inline key_serial_t nvme_keyring_id(void)
+{
+	return 0;
+}
+static inline struct key *nvme_tls_key_lookup(key_serial_t key_id)
+{
+	return ERR_PTR(-ENOTSUPP);
+}
+#endif /* !CONFIG_NVME_KEYRING */
+#endif /* _NVME_KEYRING_H */
diff --git a/include/linux/nvme-rdma.h b/include/linux/nvme-rdma.h
index 4dd7e6fe92fb..97c5f00b9aa3 100644
--- a/include/linux/nvme-rdma.h
+++ b/include/linux/nvme-rdma.h
@@ -6,7 +6,11 @@
 #ifndef _LINUX_NVME_RDMA_H
 #define _LINUX_NVME_RDMA_H
 
-#define NVME_RDMA_MAX_QUEUE_SIZE	128
+#define NVME_RDMA_IP_PORT		4420
+
+#define NVME_RDMA_MAX_QUEUE_SIZE 256
+#define NVME_RDMA_MAX_METADATA_QUEUE_SIZE 128
+#define NVME_RDMA_DEFAULT_QUEUE_SIZE 128
 
 enum nvme_rdma_cm_fmt {
 	NVME_RDMA_CM_FMT_1_0 = 0x0,
@@ -21,6 +25,7 @@ enum nvme_rdma_cm_status {
 	NVME_RDMA_CM_NO_RSC		= 0x06,
 	NVME_RDMA_CM_INVALID_IRD	= 0x07,
 	NVME_RDMA_CM_INVALID_ORD	= 0x08,
+	NVME_RDMA_CM_INVALID_CNTLID	= 0x09,
 };
 
 static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
@@ -42,6 +47,8 @@ static inline const char *nvme_rdma_cm_msg(enum nvme_rdma_cm_status status)
 		return "invalid IRD";
 	case NVME_RDMA_CM_INVALID_ORD:
 		return "Invalid ORD";
+	case NVME_RDMA_CM_INVALID_CNTLID:
+		return "invalid controller ID";
 	default:
 		return "unrecognized reason";
 	}
@@ -60,7 +67,8 @@ struct nvme_rdma_cm_req {
 	__le16		qid;
 	__le16		hrqsize;
 	__le16		hsqsize;
-	u8		rsvd[24];
+	__le16		cntlid;
+	u8		rsvd[22];
 };
 
 /**
diff --git a/include/linux/nvme-tcp.h b/include/linux/nvme-tcp.h
index 57ebe1267f7f..e435250fcb4d 100644
--- a/include/linux/nvme-tcp.h
+++ b/include/linux/nvme-tcp.h
@@ -13,11 +13,19 @@
 #define NVME_TCP_ADMIN_CCSZ	SZ_8K
 #define NVME_TCP_DIGEST_LENGTH	4
 #define NVME_TCP_MIN_MAXH2CDATA 4096
+#define NVME_TCP_MIN_C2HTERM_PLEN	24
+#define NVME_TCP_MAX_C2HTERM_PLEN	152
 
 enum nvme_tcp_pfv {
 	NVME_TCP_PFV_1_0 = 0x0,
 };
 
+enum nvme_tcp_tls_cipher {
+	NVME_TCP_TLS_CIPHER_INVALID     = 0,
+	NVME_TCP_TLS_CIPHER_SHA256      = 1,
+	NVME_TCP_TLS_CIPHER_SHA384      = 2,
+};
+
 enum nvme_tcp_fatal_error_status {
 	NVME_TCP_FES_INVALID_PDU_HDR		= 0x01,
 	NVME_TCP_FES_PDU_SEQ_ERR		= 0x02,
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index 779507ac750b..655d194f8e72 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -20,14 +20,14 @@
 #define NVMF_TRSVCID_SIZE	32
 #define NVMF_TRADDR_SIZE	256
 #define NVMF_TSAS_SIZE		256
-#define NVMF_AUTH_HASH_LEN	64
 
 #define NVME_DISC_SUBSYS_NAME	"nqn.2014-08.org.nvmexpress.discovery"
 
-#define NVME_RDMA_IP_PORT	4420
-
 #define NVME_NSID_ALL		0xffffffff
 
+/* Special NSSR value, 'NVMe' */
+#define NVME_SUBSYS_RESET	0x4E564D65
+
 enum nvme_subsys_type {
 	/* Referral to another discovery type target subsystem */
 	NVME_NQN_DISC	= 1,
@@ -64,6 +64,7 @@ enum {
 
 /* Transport Type codes for Discovery Log Page entry TRTYPE field */
 enum {
+	NVMF_TRTYPE_PCI		= 0,	/* PCI */
 	NVMF_TRTYPE_RDMA	= 1,	/* RDMA */
 	NVMF_TRTYPE_FC		= 2,	/* Fibre Channel */
 	NVMF_TRTYPE_TCP		= 3,	/* TCP/IP */
@@ -88,10 +89,11 @@ enum {
 enum {
 	NVMF_RDMA_QPTYPE_CONNECTED	= 1, /* Reliable Connected */
 	NVMF_RDMA_QPTYPE_DATAGRAM	= 2, /* Reliable Datagram */
+	NVMF_RDMA_QPTYPE_INVALID	= 0xff,
 };
 
-/* RDMA QP Service Type codes for Discovery Log Page entry TSAS
- * RDMA_QPTYPE field
+/* RDMA Provider Type codes for Discovery Log Page entry TSAS
+ * RDMA_PRTYPE field
  */
 enum {
 	NVMF_RDMA_PRTYPE_NOT_SPECIFIED	= 1, /* No Provider Specified */
@@ -108,6 +110,14 @@ enum {
 	NVMF_RDMA_CMS_RDMA_CM	= 1, /* Sockets based endpoint addressing */
 };
 
+/* TSAS SECTYPE for TCP transport */
+enum {
+	NVMF_TCP_SECTYPE_NONE = 0, /* No Security */
+	NVMF_TCP_SECTYPE_TLS12 = 1, /* TLSv1.2, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */
+	NVMF_TCP_SECTYPE_TLS13 = 2, /* TLSv1.3, NVMe-oF 1.1 and NVMe-TCP 3.6.1.1 */
+	NVMF_TCP_SECTYPE_INVALID = 0xff,
+};
+
 #define NVME_AQ_DEPTH		32
 #define NVME_NR_AEN_COMMANDS	1
 #define NVME_AQ_BLK_MQ_DEPTH	(NVME_AQ_DEPTH - NVME_NR_AEN_COMMANDS)
@@ -189,28 +199,54 @@ enum {
 #define NVME_NVM_IOSQES		6
 #define NVME_NVM_IOCQES		4
 
+/*
+ * Controller Configuration (CC) register (Offset 14h)
+ */
 enum {
+	/* Enable (EN): bit 0 */
 	NVME_CC_ENABLE		= 1 << 0,
 	NVME_CC_EN_SHIFT	= 0,
+
+	/* Bits 03:01 are reserved (NVMe Base Specification rev 2.1) */
+
+	/* I/O Command Set Selected (CSS): bits 06:04 */
 	NVME_CC_CSS_SHIFT	= 4,
-	NVME_CC_MPS_SHIFT	= 7,
-	NVME_CC_AMS_SHIFT	= 11,
-	NVME_CC_SHN_SHIFT	= 14,
-	NVME_CC_IOSQES_SHIFT	= 16,
-	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_NVM		= 0 << NVME_CC_CSS_SHIFT,
 	NVME_CC_CSS_CSI		= 6 << NVME_CC_CSS_SHIFT,
-	NVME_CC_CSS_MASK	= 7 << NVME_CC_CSS_SHIFT,
+
+	/* Memory Page Size (MPS): bits 10:07 */
+	NVME_CC_MPS_SHIFT	= 7,
+	NVME_CC_MPS_MASK	= 0xf << NVME_CC_MPS_SHIFT,
+
+	/* Arbitration Mechanism Selected (AMS): bits 13:11 */
+	NVME_CC_AMS_SHIFT	= 11,
+	NVME_CC_AMS_MASK	= 7 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_RR		= 0 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_WRRU	= 1 << NVME_CC_AMS_SHIFT,
 	NVME_CC_AMS_VS		= 7 << NVME_CC_AMS_SHIFT,
+
+	/* Shutdown Notification (SHN): bits 15:14 */
+	NVME_CC_SHN_SHIFT	= 14,
+	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NONE	= 0 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_NORMAL	= 1 << NVME_CC_SHN_SHIFT,
 	NVME_CC_SHN_ABRUPT	= 2 << NVME_CC_SHN_SHIFT,
-	NVME_CC_SHN_MASK	= 3 << NVME_CC_SHN_SHIFT,
+
+	/* I/O Submission Queue Entry Size (IOSQES): bits 19:16 */
+	NVME_CC_IOSQES_SHIFT	= 16,
+	NVME_CC_IOSQES_MASK	= 0xf << NVME_CC_IOSQES_SHIFT,
 	NVME_CC_IOSQES		= NVME_NVM_IOSQES << NVME_CC_IOSQES_SHIFT,
+
+	/* I/O Completion Queue Entry Size (IOCQES): bits 23:20 */
+	NVME_CC_IOCQES_SHIFT	= 20,
+	NVME_CC_IOCQES_MASK	= 0xf << NVME_CC_IOCQES_SHIFT,
 	NVME_CC_IOCQES		= NVME_NVM_IOCQES << NVME_CC_IOCQES_SHIFT,
+
+	/* Controller Ready Independent of Media Enable (CRIME): bit 24 */
 	NVME_CC_CRIME		= 1 << 24,
+
+	/* Bits 25:31 are reserved (NVMe Base Specification rev 2.1) */
 };
 
 enum {
@@ -266,6 +302,8 @@ enum nvme_ctrl_attr {
 	NVME_CTRL_ATTR_HID_128_BIT	= (1 << 0),
 	NVME_CTRL_ATTR_TBKAS		= (1 << 6),
 	NVME_CTRL_ATTR_ELBAS		= (1 << 15),
+	NVME_CTRL_ATTR_RHII		= (1 << 18),
+	NVME_CTRL_ATTR_FDPS		= (1 << 19),
 };
 
 struct nvme_id_ctrl {
@@ -318,7 +356,8 @@ struct nvme_id_ctrl {
 	__le32			sanicap;
 	__le32			hmminds;
 	__le16			hmmaxd;
-	__u8			rsvd338[4];
+	__le16			nvmsetidmax;
+	__le16			endgidmax;
 	__u8			anatt;
 	__u8			anacap;
 	__le32			anagrpmax;
@@ -379,6 +418,11 @@ enum {
 	NVME_CTRL_CTRATT_PREDICTABLE_LAT	= 1 << 5,
 	NVME_CTRL_CTRATT_NAMESPACE_GRANULARITY	= 1 << 7,
 	NVME_CTRL_CTRATT_UUID_LIST		= 1 << 9,
+	NVME_CTRL_SGLS_BYTE_ALIGNED             = 1,
+	NVME_CTRL_SGLS_DWORD_ALIGNED            = 2,
+	NVME_CTRL_SGLS_KSDBDS			= 1 << 2,
+	NVME_CTRL_SGLS_MSDS                     = 1 << 19,
+	NVME_CTRL_SGLS_SAOS                     = 1 << 20,
 };
 
 struct nvme_lbaf {
@@ -473,9 +517,12 @@ struct nvme_id_ns_nvm {
 };
 
 enum {
-	NVME_ID_NS_NVM_STS_MASK		= 0x3f,
+	NVME_ID_NS_NVM_STS_MASK		= 0x7f,
 	NVME_ID_NS_NVM_GUARD_SHIFT	= 7,
 	NVME_ID_NS_NVM_GUARD_MASK	= 0x3,
+	NVME_ID_NS_NVM_QPIF_SHIFT	= 9,
+	NVME_ID_NS_NVM_QPIF_MASK	= 0xf,
+	NVME_ID_NS_NVM_QPIFS		= 1 << 3,
 };
 
 static inline __u8 nvme_elbaf_sts(__u32 elbaf)
@@ -488,6 +535,11 @@ static inline __u8 nvme_elbaf_guard_type(__u32 elbaf)
 	return (elbaf >> NVME_ID_NS_NVM_GUARD_SHIFT) & NVME_ID_NS_NVM_GUARD_MASK;
 }
 
+static inline __u8 nvme_elbaf_qualified_guard_type(__u32 elbaf)
+{
+	return (elbaf >> NVME_ID_NS_NVM_QPIF_SHIFT) & NVME_ID_NS_NVM_QPIF_MASK;
+}
+
 struct nvme_id_ctrl_nvm {
 	__u8	vsl;
 	__u8	wzsl;
@@ -505,6 +557,7 @@ enum {
 	NVME_ID_CNS_NS_DESC_LIST	= 0x03,
 	NVME_ID_CNS_CS_NS		= 0x05,
 	NVME_ID_CNS_CS_CTRL		= 0x06,
+	NVME_ID_CNS_NS_ACTIVE_LIST_CS	= 0x07,
 	NVME_ID_CNS_NS_CS_INDEP		= 0x08,
 	NVME_ID_CNS_NS_PRESENT_LIST	= 0x10,
 	NVME_ID_CNS_NS_PRESENT		= 0x11,
@@ -513,6 +566,7 @@ enum {
 	NVME_ID_CNS_SCNDRY_CTRL_LIST	= 0x15,
 	NVME_ID_CNS_NS_GRANULARITY	= 0x16,
 	NVME_ID_CNS_UUID_LIST		= 0x17,
+	NVME_ID_CNS_ENDGRP_LIST		= 0x19,
 };
 
 enum {
@@ -543,6 +597,8 @@ enum {
 	NVME_NS_FLBAS_LBA_SHIFT	= 1,
 	NVME_NS_FLBAS_META_EXT	= 0x10,
 	NVME_NS_NMIC_SHARED	= 1 << 0,
+	NVME_NS_ROTATIONAL	= 1 << 4,
+	NVME_NS_VWC_NOT_PRESENT = 1 << 5,
 	NVME_LBAF_RP_BEST	= 0,
 	NVME_LBAF_RP_BETTER	= 1,
 	NVME_LBAF_RP_GOOD	= 2,
@@ -567,6 +623,7 @@ enum {
 	NVME_NVM_NS_16B_GUARD	= 0,
 	NVME_NVM_NS_32B_GUARD	= 1,
 	NVME_NVM_NS_64B_GUARD	= 2,
+	NVME_NVM_NS_QTYPE_GUARD	= 3,
 };
 
 static inline __u8 nvme_lbaf_index(__u8 flbas)
@@ -599,6 +656,78 @@ enum {
 	NVME_NIDT_CSI		= 0x04,
 };
 
+struct nvme_endurance_group_log {
+	__u8	egcw;
+	__u8	egfeat;
+	__u8	rsvd2;
+	__u8	avsp;
+	__u8	avspt;
+	__u8	pused;
+	__le16	did;
+	__u8	rsvd8[24];
+	__u8	ee[16];
+	__u8	dur[16];
+	__u8	duw[16];
+	__u8	muw[16];
+	__u8	hrc[16];
+	__u8	hwc[16];
+	__u8	mdie[16];
+	__u8	neile[16];
+	__u8	tegcap[16];
+	__u8	uegcap[16];
+	__u8	rsvd192[320];
+};
+
+struct nvme_rotational_media_log {
+	__le16	endgid;
+	__le16	numa;
+	__le16	nrs;
+	__u8	rsvd6[2];
+	__le32	spinc;
+	__le32	fspinc;
+	__le32	ldc;
+	__le32	fldc;
+	__u8	rsvd24[488];
+};
+
+struct nvme_fdp_config {
+	__u8			flags;
+#define FDPCFG_FDPE	(1U << 0)
+	__u8			fdpcidx;
+	__le16			reserved;
+};
+
+struct nvme_fdp_ruh_desc {
+	__u8			ruht;
+	__u8			reserved[3];
+};
+
+struct nvme_fdp_config_desc {
+	__le16			dsze;
+	__u8			fdpa;
+	__u8			vss;
+	__le32			nrg;
+	__le16			nruh;
+	__le16			maxpids;
+	__le32			nns;
+	__le64			runs;
+	__le32			erutl;
+	__u8			rsvd28[36];
+	struct nvme_fdp_ruh_desc ruhs[];
+};
+
+struct nvme_fdp_config_log {
+	__le16			numfdpc;
+	__u8			ver;
+	__u8			rsvd3;
+	__le32			sze;
+	__u8			rsvd8[8];
+	/*
+	 * This is followed by variable number of nvme_fdp_config_desc
+	 * structures, but sparse doesn't like nested variable sized arrays.
+	 */
+};
+
 struct nvme_smart_log {
 	__u8			critical_warning;
 	__u8			temperature[2];
@@ -640,6 +769,7 @@ enum {
 	NVME_CMD_EFFECTS_NCC		= 1 << 2,
 	NVME_CMD_EFFECTS_NIC		= 1 << 3,
 	NVME_CMD_EFFECTS_CCC		= 1 << 4,
+	NVME_CMD_EFFECTS_CSER_MASK	= GENMASK(15, 14),
 	NVME_CMD_EFFECTS_CSE_MASK	= GENMASK(18, 16),
 	NVME_CMD_EFFECTS_UUID_SEL	= 1 << 19,
 	NVME_CMD_EFFECTS_SCOPE_MASK	= GENMASK(31, 20),
@@ -759,26 +889,55 @@ enum {
 	NVME_LBART_ATTRIB_HIDE	= 1 << 1,
 };
 
+enum nvme_pr_type {
+	NVME_PR_WRITE_EXCLUSIVE			= 1,
+	NVME_PR_EXCLUSIVE_ACCESS		= 2,
+	NVME_PR_WRITE_EXCLUSIVE_REG_ONLY	= 3,
+	NVME_PR_EXCLUSIVE_ACCESS_REG_ONLY	= 4,
+	NVME_PR_WRITE_EXCLUSIVE_ALL_REGS	= 5,
+	NVME_PR_EXCLUSIVE_ACCESS_ALL_REGS	= 6,
+};
+
+enum nvme_eds {
+	NVME_EXTENDED_DATA_STRUCT	= 0x1,
+};
+
+struct nvme_registered_ctrl {
+	__le16	cntlid;
+	__u8	rcsts;
+	__u8	rsvd3[5];
+	__le64	hostid;
+	__le64	rkey;
+};
+
 struct nvme_reservation_status {
 	__le32	gen;
 	__u8	rtype;
 	__u8	regctl[2];
 	__u8	resv5[2];
 	__u8	ptpls;
-	__u8	resv10[13];
-	struct {
-		__le16	cntlid;
-		__u8	rcsts;
-		__u8	resv3[5];
-		__le64	hostid;
-		__le64	rkey;
-	} regctl_ds[];
+	__u8	resv10[14];
+	struct nvme_registered_ctrl regctl_ds[];
 };
 
-enum nvme_async_event_type {
-	NVME_AER_TYPE_ERROR	= 0,
-	NVME_AER_TYPE_SMART	= 1,
-	NVME_AER_TYPE_NOTICE	= 2,
+struct nvme_registered_ctrl_ext {
+	__le16	cntlid;
+	__u8	rcsts;
+	__u8	rsvd3[5];
+	__le64	rkey;
+	__u8	hostid[16];
+	__u8	rsvd32[32];
+};
+
+struct nvme_reservation_status_ext {
+	__le32	gen;
+	__u8	rtype;
+	__u8	regctl[2];
+	__u8	resv5[2];
+	__u8	ptpls;
+	__u8	resv10[14];
+	__u8	rsvd24[40];
+	struct nvme_registered_ctrl_ext regctl_eds[];
 };
 
 /* I/O commands */
@@ -795,6 +954,7 @@ enum nvme_opcode {
 	nvme_cmd_resv_register	= 0x0d,
 	nvme_cmd_resv_report	= 0x0e,
 	nvme_cmd_resv_acquire	= 0x11,
+	nvme_cmd_io_mgmt_recv	= 0x12,
 	nvme_cmd_resv_release	= 0x15,
 	nvme_cmd_zone_mgmt_send	= 0x79,
 	nvme_cmd_zone_mgmt_recv	= 0x7a,
@@ -816,6 +976,7 @@ enum nvme_opcode {
 		nvme_opcode_name(nvme_cmd_resv_register),	\
 		nvme_opcode_name(nvme_cmd_resv_report),		\
 		nvme_opcode_name(nvme_cmd_resv_acquire),	\
+		nvme_opcode_name(nvme_cmd_io_mgmt_recv),	\
 		nvme_opcode_name(nvme_cmd_resv_release),	\
 		nvme_opcode_name(nvme_cmd_zone_mgmt_send),	\
 		nvme_opcode_name(nvme_cmd_zone_mgmt_recv),	\
@@ -939,8 +1100,8 @@ struct nvme_rw_command {
 	__le16			control;
 	__le32			dsmgmt;
 	__le32			reftag;
-	__le16			apptag;
-	__le16			appmask;
+	__le16			lbat;
+	__le16			lbatm;
 };
 
 enum {
@@ -967,6 +1128,7 @@ enum {
 	NVME_RW_PRINFO_PRCHK_GUARD	= 1 << 12,
 	NVME_RW_PRINFO_PRACT		= 1 << 13,
 	NVME_RW_DTYPE_STREAMS		= 1 << 4,
+	NVME_RW_DTYPE_DPLCMT		= 2 << 4,
 	NVME_WZ_DEAC			= 1 << 9,
 };
 
@@ -1009,8 +1171,8 @@ struct nvme_write_zeroes_cmd {
 	__le16			control;
 	__le32			dsmgmt;
 	__le32			reftag;
-	__le16			apptag;
-	__le16			appmask;
+	__le16			lbat;
+	__le16			lbatm;
 };
 
 enum nvme_zone_mgmt_action {
@@ -1054,6 +1216,38 @@ struct nvme_zone_mgmt_recv_cmd {
 	__le32			cdw14[2];
 };
 
+struct nvme_io_mgmt_recv_cmd {
+	__u8			opcode;
+	__u8			flags;
+	__u16			command_id;
+	__le32			nsid;
+	__le64			rsvd2[2];
+	union nvme_data_ptr	dptr;
+	__u8			mo;
+	__u8			rsvd11;
+	__u16			mos;
+	__le32			numd;
+	__le32			cdw12[4];
+};
+
+enum {
+	NVME_IO_MGMT_RECV_MO_RUHS	= 1,
+};
+
+struct nvme_fdp_ruh_status_desc {
+	__le16			pid;
+	__le16			ruhid;
+	__le32			earutr;
+	__le64			ruamw;
+	__u8			reserved[16];
+};
+
+struct nvme_fdp_ruh_status {
+	__u8			rsvd0[14];
+	__le16			nruhsd;
+	struct nvme_fdp_ruh_status_desc ruhsd[];
+};
+
 enum {
 	NVME_ZRA_ZONE_REPORT		= 0,
 	NVME_ZRASF_ZONE_REPORT_ALL	= 0,
@@ -1189,6 +1383,7 @@ enum {
 	NVME_FEAT_PLM_WINDOW	= 0x14,
 	NVME_FEAT_HOST_BEHAVIOR	= 0x16,
 	NVME_FEAT_SANITIZE	= 0x17,
+	NVME_FEAT_FDP		= 0x1d,
 	NVME_FEAT_SW_PROGRESS	= 0x80,
 	NVME_FEAT_HOST_ID	= 0x81,
 	NVME_FEAT_RESV_MASK	= 0x82,
@@ -1196,6 +1391,7 @@ enum {
 	NVME_FEAT_WRITE_PROTECT	= 0x84,
 	NVME_FEAT_VENDOR_START	= 0xC0,
 	NVME_FEAT_VENDOR_END	= 0xFF,
+	NVME_LOG_SUPPORTED	= 0x00,
 	NVME_LOG_ERROR		= 0x01,
 	NVME_LOG_SMART		= 0x02,
 	NVME_LOG_FW_SLOT	= 0x03,
@@ -1206,6 +1402,9 @@ enum {
 	NVME_LOG_TELEMETRY_CTRL = 0x08,
 	NVME_LOG_ENDURANCE_GROUP = 0x09,
 	NVME_LOG_ANA		= 0x0c,
+	NVME_LOG_FEATURES	= 0x12,
+	NVME_LOG_RMI		= 0x16,
+	NVME_LOG_FDP_CONFIGS	= 0x20,
 	NVME_LOG_DISC		= 0x70,
 	NVME_LOG_RESERVATION	= 0x80,
 	NVME_FWACT_REPL		= (0 << 3),
@@ -1213,6 +1412,24 @@ enum {
 	NVME_FWACT_ACTV		= (2 << 3),
 };
 
+struct nvme_supported_log {
+	__le32	lids[256];
+};
+
+enum {
+	NVME_LIDS_LSUPP	= 1 << 0,
+};
+
+struct nvme_supported_features_log {
+	__le32	fis[256];
+};
+
+enum {
+	NVME_FIS_FSUPP	= 1 << 0,
+	NVME_FIS_NSCPE	= 1 << 20,
+	NVME_FIS_CSCPE	= 1 << 21,
+};
+
 /* NVMe Namespace Write Protect State */
 enum {
 	NVME_NS_NO_WRITE_PROTECT = 0,
@@ -1233,7 +1450,8 @@ struct nvme_identify {
 	__u8			cns;
 	__u8			rsvd3;
 	__le16			ctrlid;
-	__u8			rsvd11[3];
+	__le16			cnssid;
+	__u8			rsvd11;
 	__u8			csi;
 	__u32			rsvd12[4];
 };
@@ -1341,7 +1559,7 @@ struct nvme_get_log_page_command {
 	__u8			lsp; /* upper 4 bits reserved */
 	__le16			numdl;
 	__le16			numdu;
-	__u16			rsvd11;
+	__le16			lsi;
 	union {
 		struct {
 			__le32 lpol;
@@ -1458,6 +1676,9 @@ struct nvmf_disc_rsp_page_entry {
 			__u16	pkey;
 			__u8	resv10[246];
 		} rdma;
+		struct tcp {
+			__u8	sectype;
+		} tcp;
 	} tsas;
 };
 
@@ -1627,6 +1848,13 @@ enum {
 	NVME_AUTH_DHGROUP_INVALID	= 0xff,
 };
 
+enum {
+	NVME_AUTH_SECP_NOSC		= 0x00,
+	NVME_AUTH_SECP_SC		= 0x01,
+	NVME_AUTH_SECP_NEWTLSPSK	= 0x02,
+	NVME_AUTH_SECP_REPLACETLSPSK	= 0x03,
+};
+
 union nvmf_auth_protocol {
 	struct nvmf_auth_dhchap_protocol_descriptor dhchap;
 };
@@ -1687,7 +1915,7 @@ struct nvmf_auth_dhchap_success1_data {
 	__u8		rsvd2;
 	__u8		rvalid;
 	__u8		rsvd3[7];
-	/* 'hl' bytes of response value if 'rvalid' is set */
+	/* 'hl' bytes of response value */
 	__u8		rval[];
 };
 
@@ -1771,14 +1999,55 @@ struct nvme_command {
 		struct nvmf_auth_receive_command auth_receive;
 		struct nvme_dbbuf dbbuf;
 		struct nvme_directive_cmd directive;
+		struct nvme_io_mgmt_recv_cmd imr;
 	};
 };
 
-static inline bool nvme_is_fabrics(struct nvme_command *cmd)
+static inline bool nvme_is_fabrics(const struct nvme_command *cmd)
 {
 	return cmd->common.opcode == nvme_fabrics_command;
 }
 
+#ifdef CONFIG_NVME_VERBOSE_ERRORS
+const char *nvme_get_error_status_str(u16 status);
+const char *nvme_get_opcode_str(u8 opcode);
+const char *nvme_get_admin_opcode_str(u8 opcode);
+const char *nvme_get_fabrics_opcode_str(u8 opcode);
+#else /* CONFIG_NVME_VERBOSE_ERRORS */
+static inline const char *nvme_get_error_status_str(u16 status)
+{
+	return "I/O Error";
+}
+static inline const char *nvme_get_opcode_str(u8 opcode)
+{
+	return "I/O Cmd";
+}
+static inline const char *nvme_get_admin_opcode_str(u8 opcode)
+{
+	return "Admin Cmd";
+}
+
+static inline const char *nvme_get_fabrics_opcode_str(u8 opcode)
+{
+	return "Fabrics Cmd";
+}
+#endif /* CONFIG_NVME_VERBOSE_ERRORS */
+
+static inline const char *nvme_opcode_str(int qid, u8 opcode)
+{
+	return qid ? nvme_get_opcode_str(opcode) :
+		nvme_get_admin_opcode_str(opcode);
+}
+
+static inline const char *nvme_fabrics_opcode_str(
+		int qid, const struct nvme_command *cmd)
+{
+	if (nvme_is_fabrics(cmd))
+		return nvme_get_fabrics_opcode_str(cmd->fabrics.fctype);
+
+	return nvme_opcode_str(qid, cmd->common.opcode);
+}
+
 struct nvme_error_slot {
 	__le64		error_count;
 	__le16		sqid;
@@ -1793,7 +2062,7 @@ struct nvme_error_slot {
 	__u8		resv2[24];
 };
 
-static inline bool nvme_is_write(struct nvme_command *cmd)
+static inline bool nvme_is_write(const struct nvme_command *cmd)
 {
 	/*
 	 * What a mess...
@@ -1809,6 +2078,7 @@ enum {
 	/*
 	 * Generic Command Status:
 	 */
+	NVME_SCT_GENERIC		= 0x0,
 	NVME_SC_SUCCESS			= 0x0,
 	NVME_SC_INVALID_OPCODE		= 0x1,
 	NVME_SC_INVALID_FIELD		= 0x2,
@@ -1856,6 +2126,7 @@ enum {
 	/*
 	 * Command Specific Status:
 	 */
+	NVME_SCT_COMMAND_SPECIFIC	= 0x100,
 	NVME_SC_CQ_INVALID		= 0x100,
 	NVME_SC_QID_INVALID		= 0x101,
 	NVME_SC_QUEUE_SIZE		= 0x102,
@@ -1884,7 +2155,7 @@ enum {
 	NVME_SC_NS_NOT_ATTACHED		= 0x11a,
 	NVME_SC_THIN_PROV_NOT_SUPP	= 0x11b,
 	NVME_SC_CTRL_LIST_INVALID	= 0x11c,
-	NVME_SC_SELT_TEST_IN_PROGRESS	= 0x11d,
+	NVME_SC_SELF_TEST_IN_PROGRESS	= 0x11d,
 	NVME_SC_BP_WRITE_PROHIBITED	= 0x11e,
 	NVME_SC_CTRL_ID_INVALID		= 0x11f,
 	NVME_SC_SEC_CTRL_STATE_INVALID	= 0x120,
@@ -1900,7 +2171,7 @@ enum {
 	NVME_SC_BAD_ATTRIBUTES		= 0x180,
 	NVME_SC_INVALID_PI		= 0x181,
 	NVME_SC_READ_ONLY		= 0x182,
-	NVME_SC_ONCS_NOT_SUPPORTED	= 0x183,
+	NVME_SC_CMD_SIZE_LIM_EXCEEDED	= 0x183,
 
 	/*
 	 * I/O Command Set Specific - Fabrics commands:
@@ -1929,6 +2200,7 @@ enum {
 	/*
 	 * Media and Data Integrity Errors:
 	 */
+	NVME_SCT_MEDIA_ERROR		= 0x200,
 	NVME_SC_WRITE_FAULT		= 0x280,
 	NVME_SC_READ_ERROR		= 0x281,
 	NVME_SC_GUARD_CHECK		= 0x282,
@@ -1941,6 +2213,7 @@ enum {
 	/*
 	 * Path-related Errors:
 	 */
+	NVME_SCT_PATH			= 0x300,
 	NVME_SC_INTERNAL_PATH_ERROR	= 0x300,
 	NVME_SC_ANA_PERSISTENT_LOSS	= 0x301,
 	NVME_SC_ANA_INACCESSIBLE	= 0x302,
@@ -1949,11 +2222,17 @@ enum {
 	NVME_SC_HOST_PATH_ERROR		= 0x370,
 	NVME_SC_HOST_ABORTED_CMD	= 0x371,
 
-	NVME_SC_CRD			= 0x1800,
-	NVME_SC_MORE			= 0x2000,
-	NVME_SC_DNR			= 0x4000,
+	NVME_SC_MASK			= 0x00ff, /* Status Code */
+	NVME_SCT_MASK			= 0x0700, /* Status Code Type */
+	NVME_SCT_SC_MASK		= NVME_SCT_MASK | NVME_SC_MASK,
+
+	NVME_STATUS_CRD			= 0x1800, /* Command Retry Delayed */
+	NVME_STATUS_MORE		= 0x2000,
+	NVME_STATUS_DNR			= 0x4000, /* Do Not Retry */
 };
 
+#define NVME_SCT(status) ((status) >> 8 & 7)
+
 struct nvme_completion {
 	/*
 	 * Used by Admin and Fabrics commands to return data:
@@ -1976,4 +2255,81 @@ struct nvme_completion {
 #define NVME_MINOR(ver)		(((ver) >> 8) & 0xff)
 #define NVME_TERTIARY(ver)	((ver) & 0xff)
 
+enum {
+	NVME_AEN_RESV_LOG_PAGE_AVALIABLE	= 0x00,
+};
+
+enum {
+	NVME_PR_LOG_EMPTY_LOG_PAGE			= 0x00,
+	NVME_PR_LOG_REGISTRATION_PREEMPTED		= 0x01,
+	NVME_PR_LOG_RESERVATION_RELEASED		= 0x02,
+	NVME_PR_LOG_RESERVATOIN_PREEMPTED		= 0x03,
+};
+
+enum {
+	NVME_PR_NOTIFY_BIT_REG_PREEMPTED		= 1,
+	NVME_PR_NOTIFY_BIT_RESV_RELEASED		= 2,
+	NVME_PR_NOTIFY_BIT_RESV_PREEMPTED		= 3,
+};
+
+struct nvme_pr_log {
+	__le64			count;
+	__u8			type;
+	__u8			nr_pages;
+	__u8			rsvd1[2];
+	__le32			nsid;
+	__u8			rsvd2[48];
+};
+
+struct nvmet_pr_register_data {
+	__le64	crkey;
+	__le64	nrkey;
+};
+
+struct nvmet_pr_acquire_data {
+	__le64	crkey;
+	__le64	prkey;
+};
+
+struct nvmet_pr_release_data {
+	__le64	crkey;
+};
+
+enum nvme_pr_capabilities {
+	NVME_PR_SUPPORT_PTPL				= 1,
+	NVME_PR_SUPPORT_WRITE_EXCLUSIVE			= 1 << 1,
+	NVME_PR_SUPPORT_EXCLUSIVE_ACCESS		= 1 << 2,
+	NVME_PR_SUPPORT_WRITE_EXCLUSIVE_REG_ONLY	= 1 << 3,
+	NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_REG_ONLY	= 1 << 4,
+	NVME_PR_SUPPORT_WRITE_EXCLUSIVE_ALL_REGS	= 1 << 5,
+	NVME_PR_SUPPORT_EXCLUSIVE_ACCESS_ALL_REGS	= 1 << 6,
+	NVME_PR_SUPPORT_IEKEY_VER_1_3_DEF		= 1 << 7,
+};
+
+enum nvme_pr_register_action {
+	NVME_PR_REGISTER_ACT_REG		= 0,
+	NVME_PR_REGISTER_ACT_UNREG		= 1,
+	NVME_PR_REGISTER_ACT_REPLACE		= 1 << 1,
+};
+
+enum nvme_pr_acquire_action {
+	NVME_PR_ACQUIRE_ACT_ACQUIRE		= 0,
+	NVME_PR_ACQUIRE_ACT_PREEMPT		= 1,
+	NVME_PR_ACQUIRE_ACT_PREEMPT_AND_ABORT	= 1 << 1,
+};
+
+enum nvme_pr_release_action {
+	NVME_PR_RELEASE_ACT_RELEASE		= 0,
+	NVME_PR_RELEASE_ACT_CLEAR		= 1,
+};
+
+enum nvme_pr_change_ptpl {
+	NVME_PR_CPTPL_NO_CHANGE			= 0,
+	NVME_PR_CPTPL_RESV			= 1 << 30,
+	NVME_PR_CPTPL_CLEARED			= 2 << 30,
+	NVME_PR_CPTPL_PERSIST			= 3 << 30,
+};
+
+#define NVME_PR_IGNORE_KEY (1 << 3)
+
 #endif /* _LINUX_NVME_H */
diff --git a/include/linux/nvmem-consumer.h b/include/linux/nvmem-consumer.h
index fa030d93b768..34c0e58dfa26 100644
--- a/include/linux/nvmem-consumer.h
+++ b/include/linux/nvmem-consumer.h
@@ -43,6 +43,8 @@ enum {
 	NVMEM_REMOVE,
 	NVMEM_CELL_ADD,
 	NVMEM_CELL_REMOVE,
+	NVMEM_LAYOUT_ADD,
+	NVMEM_LAYOUT_REMOVE,
 };
 
 #if IS_ENABLED(CONFIG_NVMEM)
@@ -79,6 +81,7 @@ int nvmem_device_cell_write(struct nvmem_device *nvmem,
 			    struct nvmem_cell_info *info, void *buf);
 
 const char *nvmem_dev_name(struct nvmem_device *nvmem);
+size_t nvmem_dev_size(struct nvmem_device *nvmem);
 
 void nvmem_add_cell_lookups(struct nvmem_cell_lookup *entries,
 			    size_t nentries);
@@ -125,6 +128,12 @@ static inline int nvmem_cell_write(struct nvmem_cell *cell,
 	return -EOPNOTSUPP;
 }
 
+static inline int nvmem_cell_read_u8(struct device *dev,
+				     const char *cell_id, u8 *val)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int nvmem_cell_read_u16(struct device *dev,
 				      const char *cell_id, u16 *val)
 {
@@ -239,7 +248,6 @@ struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 				     const char *id);
 struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 					 const char *name);
-struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
 #else
 static inline struct nvmem_cell *of_nvmem_cell_get(struct device_node *np,
 						   const char *id)
@@ -252,12 +260,6 @@ static inline struct nvmem_device *of_nvmem_device_get(struct device_node *np,
 {
 	return ERR_PTR(-EOPNOTSUPP);
 }
-
-static inline struct device_node *
-of_nvmem_layout_get_container(struct nvmem_device *nvmem)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
 #endif /* CONFIG_NVMEM && CONFIG_OF */
 
 #endif  /* ifndef _LINUX_NVMEM_CONSUMER_H */
diff --git a/include/linux/nvmem-provider.h b/include/linux/nvmem-provider.h
index dae26295e6be..f3b13da78aac 100644
--- a/include/linux/nvmem-provider.h
+++ b/include/linux/nvmem-provider.h
@@ -9,6 +9,7 @@
 #ifndef _LINUX_NVMEM_PROVIDER_H
 #define _LINUX_NVMEM_PROVIDER_H
 
+#include <linux/device.h>
 #include <linux/device/driver.h>
 #include <linux/err.h>
 #include <linux/errno.h>
@@ -82,15 +83,17 @@ struct nvmem_cell_info {
  * @owner:	Pointer to exporter module. Used for refcounting.
  * @cells:	Optional array of pre-defined NVMEM cells.
  * @ncells:	Number of elements in cells.
+ * @add_legacy_fixed_of_cells:	Read fixed NVMEM cells from old OF syntax.
+ * @fixup_dt_cell_info: Will be called before a cell is added. Can be
+ *		used to modify the nvmem_cell_info.
  * @keepout:	Optional array of keepout ranges (sorted ascending by start).
  * @nkeepout:	Number of elements in the keepout array.
  * @type:	Type of the nvmem storage
  * @read_only:	Device is read-only.
  * @root_only:	Device is accessibly to root only.
  * @of_node:	If given, this will be used instead of the parent's of_node.
- * @no_of_node:	Device should not use the parent's of_node even if it's !NULL.
- * @reg_read:	Callback to read data.
- * @reg_write:	Callback to write data.
+ * @reg_read:	Callback to read data; return zero if successful.
+ * @reg_write:	Callback to write data; return zero if successful.
  * @size:	Device size.
  * @word_size:	Minimum read/write access granularity.
  * @stride:	Minimum read/write access stride.
@@ -100,7 +103,7 @@ struct nvmem_cell_info {
  *
  * Note: A default "nvmem<id>" name will be assigned to the device if
  * no name is specified in its configuration. In such case "<id>" is
- * generated with ida_simple_get() and provided id field is ignored.
+ * generated with ida_alloc() and provided id field is ignored.
  *
  * Note: Specifying name and setting id to -1 implies a unique device
  * whose name is provided as-is (kept unaltered).
@@ -112,6 +115,9 @@ struct nvmem_config {
 	struct module		*owner;
 	const struct nvmem_cell_info	*cells;
 	int			ncells;
+	bool			add_legacy_fixed_of_cells;
+	void (*fixup_dt_cell_info)(struct nvmem_device *nvmem,
+				   struct nvmem_cell_info *cell);
 	const struct nvmem_keepout *keepout;
 	unsigned int		nkeepout;
 	enum nvmem_type		type;
@@ -120,7 +126,6 @@ struct nvmem_config {
 	bool			ignore_wp;
 	struct nvmem_layout	*layout;
 	struct device_node	*of_node;
-	bool			no_of_node;
 	nvmem_reg_read_t	reg_read;
 	nvmem_reg_write_t	reg_write;
 	int	size;
@@ -133,36 +138,13 @@ struct nvmem_config {
 };
 
 /**
- * struct nvmem_cell_table - NVMEM cell definitions for given provider
- *
- * @nvmem_name:		Provider name.
- * @cells:		Array of cell definitions.
- * @ncells:		Number of cell definitions in the array.
- * @node:		List node.
- *
- * This structure together with related helper functions is provided for users
- * that don't can't access the nvmem provided structure but wish to register
- * cell definitions for it e.g. board files registering an EEPROM device.
- */
-struct nvmem_cell_table {
-	const char		*nvmem_name;
-	const struct nvmem_cell_info	*cells;
-	size_t			ncells;
-	struct list_head	node;
-};
-
-/**
  * struct nvmem_layout - NVMEM layout definitions
  *
- * @name:		Layout name.
- * @of_match_table:	Open firmware match table.
+ * @dev:		Device-model layout device.
+ * @nvmem:		The underlying NVMEM device
  * @add_cells:		Will be called if a nvmem device is found which
  *			has this layout. The function will add layout
  *			specific cells with nvmem_add_one_cell().
- * @fixup_cell_info:	Will be called before a cell is added. Can be
- *			used to modify the nvmem_cell_info.
- * @owner:		Pointer to struct module.
- * @node:		List node.
  *
  * A nvmem device can hold a well defined structure which can just be
  * evaluated during runtime. For example a TLV list, or a list of "name=val"
@@ -170,17 +152,15 @@ struct nvmem_cell_table {
  * cells.
  */
 struct nvmem_layout {
-	const char *name;
-	const struct of_device_id *of_match_table;
-	int (*add_cells)(struct device *dev, struct nvmem_device *nvmem,
-			 struct nvmem_layout *layout);
-	void (*fixup_cell_info)(struct nvmem_device *nvmem,
-				struct nvmem_layout *layout,
-				struct nvmem_cell_info *cell);
-
-	/* private */
-	struct module *owner;
-	struct list_head node;
+	struct device dev;
+	struct nvmem_device *nvmem;
+	int (*add_cells)(struct nvmem_layout *layout);
+};
+
+struct nvmem_layout_driver {
+	struct device_driver driver;
+	int (*probe)(struct nvmem_layout *layout);
+	void (*remove)(struct nvmem_layout *layout);
 };
 
 #if IS_ENABLED(CONFIG_NVMEM)
@@ -191,19 +171,20 @@ void nvmem_unregister(struct nvmem_device *nvmem);
 struct nvmem_device *devm_nvmem_register(struct device *dev,
 					 const struct nvmem_config *cfg);
 
-void nvmem_add_cell_table(struct nvmem_cell_table *table);
-void nvmem_del_cell_table(struct nvmem_cell_table *table);
-
 int nvmem_add_one_cell(struct nvmem_device *nvmem,
 		       const struct nvmem_cell_info *info);
 
-int __nvmem_layout_register(struct nvmem_layout *layout, struct module *owner);
-#define nvmem_layout_register(layout) \
-	__nvmem_layout_register(layout, THIS_MODULE)
+int nvmem_layout_register(struct nvmem_layout *layout);
 void nvmem_layout_unregister(struct nvmem_layout *layout);
 
-const void *nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-					struct nvmem_layout *layout);
+#define nvmem_layout_driver_register(drv) \
+	__nvmem_layout_driver_register(drv, THIS_MODULE)
+int __nvmem_layout_driver_register(struct nvmem_layout_driver *drv,
+				   struct module *owner);
+void nvmem_layout_driver_unregister(struct nvmem_layout_driver *drv);
+#define module_nvmem_layout_driver(__nvmem_layout_driver)		\
+	module_driver(__nvmem_layout_driver, nvmem_layout_driver_register, \
+		      nvmem_layout_driver_unregister)
 
 #else
 
@@ -220,8 +201,6 @@ devm_nvmem_register(struct device *dev, const struct nvmem_config *c)
 	return nvmem_register(c);
 }
 
-static inline void nvmem_add_cell_table(struct nvmem_cell_table *table) {}
-static inline void nvmem_del_cell_table(struct nvmem_cell_table *table) {}
 static inline int nvmem_add_one_cell(struct nvmem_device *nvmem,
 				     const struct nvmem_cell_info *info)
 {
@@ -235,17 +214,27 @@ static inline int nvmem_layout_register(struct nvmem_layout *layout)
 
 static inline void nvmem_layout_unregister(struct nvmem_layout *layout) {}
 
-static inline const void *
-nvmem_layout_get_match_data(struct nvmem_device *nvmem,
-			    struct nvmem_layout *layout)
+#endif /* CONFIG_NVMEM */
+
+#if IS_ENABLED(CONFIG_NVMEM) && IS_ENABLED(CONFIG_OF)
+
+/**
+ * of_nvmem_layout_get_container() - Get OF node of layout container
+ *
+ * @nvmem: nvmem device
+ *
+ * Return: a node pointer with refcount incremented or NULL if no
+ * container exists. Use of_node_put() on it when done.
+ */
+struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem);
+
+#else  /* CONFIG_NVMEM && CONFIG_OF */
+
+static inline struct device_node *of_nvmem_layout_get_container(struct nvmem_device *nvmem)
 {
 	return NULL;
 }
 
-#endif /* CONFIG_NVMEM */
-
-#define module_nvmem_layout_driver(__layout_driver)		\
-	module_driver(__layout_driver, nvmem_layout_register,	\
-		      nvmem_layout_unregister)
+#endif /* CONFIG_NVMEM && CONFIG_OF */
 
 #endif  /* ifndef _LINUX_NVMEM_PROVIDER_H */
diff --git a/include/linux/oa_tc6.h b/include/linux/oa_tc6.h
new file mode 100644
index 000000000000..15f58e3c56c7
--- /dev/null
+++ b/include/linux/oa_tc6.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0+ */
+/*
+ * OPEN Alliance 10BASE‑T1x MAC‑PHY Serial Interface framework
+ *
+ * Link: https://opensig.org/download/document/OPEN_Alliance_10BASET1x_MAC-PHY_Serial_Interface_V1.1.pdf
+ *
+ * Author: Parthiban Veerasooran <parthiban.veerasooran@microchip.com>
+ */
+
+#include <linux/etherdevice.h>
+#include <linux/spi/spi.h>
+
+struct oa_tc6;
+
+struct oa_tc6 *oa_tc6_init(struct spi_device *spi, struct net_device *netdev);
+void oa_tc6_exit(struct oa_tc6 *tc6);
+int oa_tc6_write_register(struct oa_tc6 *tc6, u32 address, u32 value);
+int oa_tc6_write_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
+			   u8 length);
+int oa_tc6_read_register(struct oa_tc6 *tc6, u32 address, u32 *value);
+int oa_tc6_read_registers(struct oa_tc6 *tc6, u32 address, u32 value[],
+			  u8 length);
+netdev_tx_t oa_tc6_start_xmit(struct oa_tc6 *tc6, struct sk_buff *skb);
+int oa_tc6_zero_align_receive_frame_enable(struct oa_tc6 *tc6);
diff --git a/include/linux/objagg.h b/include/linux/objagg.h
index 78021777df46..6df5b887dc54 100644
--- a/include/linux/objagg.h
+++ b/include/linux/objagg.h
@@ -8,7 +8,6 @@ struct objagg_ops {
 	size_t obj_size;
 	bool (*delta_check)(void *priv, const void *parent_obj,
 			    const void *obj);
-	int (*hints_obj_cmp)(const void *obj1, const void *obj2);
 	void * (*delta_create)(void *priv, void *parent_obj, void *obj);
 	void (*delta_destroy)(void *priv, void *delta_priv);
 	void * (*root_create)(void *priv, void *obj, unsigned int root_id);
diff --git a/include/linux/objpool.h b/include/linux/objpool.h
new file mode 100644
index 000000000000..b713a1fe7521
--- /dev/null
+++ b/include/linux/objpool.h
@@ -0,0 +1,277 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_OBJPOOL_H
+#define _LINUX_OBJPOOL_H
+
+#include <linux/types.h>
+#include <linux/refcount.h>
+#include <linux/atomic.h>
+#include <linux/cpumask.h>
+#include <linux/irqflags.h>
+#include <linux/smp.h>
+
+/*
+ * objpool: ring-array based lockless MPMC queue
+ *
+ * Copyright: wuqiang.matt@bytedance.com,mhiramat@kernel.org
+ *
+ * objpool is a scalable implementation of high performance queue for
+ * object allocation and reclamation, such as kretprobe instances.
+ *
+ * With leveraging percpu ring-array to mitigate hot spots of memory
+ * contention, it delivers near-linear scalability for high parallel
+ * scenarios. The objpool is best suited for the following cases:
+ * 1) Memory allocation or reclamation are prohibited or too expensive
+ * 2) Consumers are of different priorities, such as irqs and threads
+ *
+ * Limitations:
+ * 1) Maximum objects (capacity) is fixed after objpool creation
+ * 2) All pre-allocated objects are managed in percpu ring array,
+ *    which consumes more memory than linked lists
+ */
+
+/**
+ * struct objpool_slot - percpu ring array of objpool
+ * @head: head sequence of the local ring array (to retrieve at)
+ * @tail: tail sequence of the local ring array (to append at)
+ * @last: the last sequence number marked as ready for retrieve
+ * @mask: bits mask for modulo capacity to compute array indexes
+ * @entries: object entries on this slot
+ *
+ * Represents a cpu-local array-based ring buffer, its size is specialized
+ * during initialization of object pool. The percpu objpool node is to be
+ * allocated from local memory for NUMA system, and to be kept compact in
+ * continuous memory: CPU assigned number of objects are stored just after
+ * the body of objpool_node.
+ *
+ * Real size of the ring array is far too smaller than the value range of
+ * head and tail, typed as uint32_t: [0, 2^32), so only lower bits (mask)
+ * of head and tail are used as the actual position in the ring array. In
+ * general the ring array is acting like a small sliding window, which is
+ * always moving forward in the loop of [0, 2^32).
+ */
+struct objpool_slot {
+	uint32_t            head;
+	uint32_t            tail;
+	uint32_t            last;
+	uint32_t            mask;
+	void               *entries[];
+} __packed;
+
+struct objpool_head;
+
+/*
+ * caller-specified callback for object initial setup, it's only called
+ * once for each object (just after the memory allocation of the object)
+ */
+typedef int (*objpool_init_obj_cb)(void *obj, void *context);
+
+/* caller-specified cleanup callback for objpool destruction */
+typedef int (*objpool_fini_cb)(struct objpool_head *head, void *context);
+
+/**
+ * struct objpool_head - object pooling metadata
+ * @obj_size:   object size, aligned to sizeof(void *)
+ * @nr_objs:    total objs (to be pre-allocated with objpool)
+ * @nr_possible_cpus: cached value of num_possible_cpus()
+ * @capacity:   max objs can be managed by one objpool_slot
+ * @gfp:        gfp flags for kmalloc & vmalloc
+ * @ref:        refcount of objpool
+ * @flags:      flags for objpool management
+ * @cpu_slots:  pointer to the array of objpool_slot
+ * @release:    resource cleanup callback
+ * @context:    caller-provided context
+ */
+struct objpool_head {
+	int                     obj_size;
+	int                     nr_objs;
+	int                     nr_possible_cpus;
+	int                     capacity;
+	gfp_t                   gfp;
+	refcount_t              ref;
+	unsigned long           flags;
+	struct objpool_slot   **cpu_slots;
+	objpool_fini_cb         release;
+	void                   *context;
+};
+
+#define OBJPOOL_NR_OBJECT_MAX	(1UL << 24) /* maximum numbers of total objects */
+#define OBJPOOL_OBJECT_SIZE_MAX	(1UL << 16) /* maximum size of an object */
+
+/**
+ * objpool_init() - initialize objpool and pre-allocated objects
+ * @pool:    the object pool to be initialized, declared by caller
+ * @nr_objs: total objects to be pre-allocated by this object pool
+ * @object_size: size of an object (should be > 0)
+ * @gfp:     flags for memory allocation (via kmalloc or vmalloc)
+ * @context: user context for object initialization callback
+ * @objinit: object initialization callback for extra setup
+ * @release: cleanup callback for extra cleanup task
+ *
+ * return value: 0 for success, otherwise error code
+ *
+ * All pre-allocated objects are to be zeroed after memory allocation.
+ * Caller could do extra initialization in objinit callback. objinit()
+ * will be called just after slot allocation and called only once for
+ * each object. After that the objpool won't touch any content of the
+ * objects. It's caller's duty to perform reinitialization after each
+ * pop (object allocation) or do clearance before each push (object
+ * reclamation).
+ */
+int objpool_init(struct objpool_head *pool, int nr_objs, int object_size,
+		 gfp_t gfp, void *context, objpool_init_obj_cb objinit,
+		 objpool_fini_cb release);
+
+/* try to retrieve object from slot */
+static inline void *__objpool_try_get_slot(struct objpool_head *pool, int cpu)
+{
+	struct objpool_slot *slot = pool->cpu_slots[cpu];
+	/* load head snapshot, other cpus may change it */
+	uint32_t head = smp_load_acquire(&slot->head);
+
+	while (head != READ_ONCE(slot->last)) {
+		void *obj;
+
+		/*
+		 * data visibility of 'last' and 'head' could be out of
+		 * order since memory updating of 'last' and 'head' are
+		 * performed in push() and pop() independently
+		 *
+		 * before any retrieving attempts, pop() must guarantee
+		 * 'last' is behind 'head', that is to say, there must
+		 * be available objects in slot, which could be ensured
+		 * by condition 'last != head && last - head <= nr_objs'
+		 * that is equivalent to 'last - head - 1 < nr_objs' as
+		 * 'last' and 'head' are both unsigned int32
+		 */
+		if (READ_ONCE(slot->last) - head - 1 >= pool->nr_objs) {
+			head = READ_ONCE(slot->head);
+			continue;
+		}
+
+		/* obj must be retrieved before moving forward head */
+		obj = READ_ONCE(slot->entries[head & slot->mask]);
+
+		/* move head forward to mark it's consumption */
+		if (try_cmpxchg_release(&slot->head, &head, head + 1))
+			return obj;
+	}
+
+	return NULL;
+}
+
+/**
+ * objpool_pop() - allocate an object from objpool
+ * @pool: object pool
+ *
+ * return value: object ptr or NULL if failed
+ */
+static inline void *objpool_pop(struct objpool_head *pool)
+{
+	void *obj = NULL;
+	unsigned long flags;
+	int start, cpu;
+
+	/* disable local irq to avoid preemption & interruption */
+	raw_local_irq_save(flags);
+
+	start = raw_smp_processor_id();
+	for_each_possible_cpu_wrap(cpu, start) {
+		obj = __objpool_try_get_slot(pool, cpu);
+		if (obj)
+			break;
+	}
+	raw_local_irq_restore(flags);
+
+	return obj;
+}
+
+/* adding object to slot, abort if the slot was already full */
+static inline int
+__objpool_try_add_slot(void *obj, struct objpool_head *pool, int cpu)
+{
+	struct objpool_slot *slot = pool->cpu_slots[cpu];
+	uint32_t head, tail;
+
+	/* loading tail and head as a local snapshot, tail first */
+	tail = READ_ONCE(slot->tail);
+
+	do {
+		head = READ_ONCE(slot->head);
+		/* fault caught: something must be wrong */
+		WARN_ON_ONCE(tail - head > pool->nr_objs);
+	} while (!try_cmpxchg_acquire(&slot->tail, &tail, tail + 1));
+
+	/* now the tail position is reserved for the given obj */
+	WRITE_ONCE(slot->entries[tail & slot->mask], obj);
+	/* update sequence to make this obj available for pop() */
+	smp_store_release(&slot->last, tail + 1);
+
+	return 0;
+}
+
+/**
+ * objpool_push() - reclaim the object and return back to objpool
+ * @obj:  object ptr to be pushed to objpool
+ * @pool: object pool
+ *
+ * return: 0 or error code (it fails only when user tries to push
+ * the same object multiple times or wrong "objects" into objpool)
+ */
+static inline int objpool_push(void *obj, struct objpool_head *pool)
+{
+	unsigned long flags;
+	int rc;
+
+	/* disable local irq to avoid preemption & interruption */
+	raw_local_irq_save(flags);
+	rc = __objpool_try_add_slot(obj, pool, raw_smp_processor_id());
+	raw_local_irq_restore(flags);
+
+	return rc;
+}
+
+
+/**
+ * objpool_drop() - discard the object and deref objpool
+ * @obj:  object ptr to be discarded
+ * @pool: object pool
+ *
+ * return: 0 if objpool was released; -EAGAIN if there are still
+ *         outstanding objects
+ *
+ * objpool_drop is normally for the release of outstanding objects
+ * after objpool cleanup (objpool_fini). Thinking of this example:
+ * kretprobe is unregistered and objpool_fini() is called to release
+ * all remained objects, but there are still objects being used by
+ * unfinished kretprobes (like blockable function: sys_accept). So
+ * only when the last outstanding object is dropped could the whole
+ * objpool be released along with the call of objpool_drop()
+ */
+int objpool_drop(void *obj, struct objpool_head *pool);
+
+/**
+ * objpool_free() - release objpool forcely (all objects to be freed)
+ * @pool: object pool to be released
+ */
+void objpool_free(struct objpool_head *pool);
+
+/**
+ * objpool_fini() - deref object pool (also releasing unused objects)
+ * @pool: object pool to be dereferenced
+ *
+ * objpool_fini() will try to release all remained free objects and
+ * then drop an extra reference of the objpool. If all objects are
+ * already returned to objpool (so called synchronous use cases),
+ * the objpool itself will be freed together. But if there are still
+ * outstanding objects (so called asynchronous use cases, such like
+ * blockable kretprobe), the objpool won't be released until all
+ * the outstanding objects are dropped, but the caller must assure
+ * there are no concurrent objpool_push() on the fly. Normally RCU
+ * is being required to make sure all ongoing objpool_push() must
+ * be finished before calling objpool_fini(), so does test_objpool,
+ * kretprobe or rethook
+ */
+void objpool_fini(struct objpool_head *pool);
+
+#endif /* _LINUX_OBJPOOL_H */
diff --git a/include/linux/objtool.h b/include/linux/objtool.h
index 03f82c2c2ebf..9a00e701454c 100644
--- a/include/linux/objtool.h
+++ b/include/linux/objtool.h
@@ -3,16 +3,16 @@
 #define _LINUX_OBJTOOL_H
 
 #include <linux/objtool_types.h>
+#include <linux/annotate.h>
 
 #ifdef CONFIG_OBJTOOL
 
-#include <asm/asm.h>
-
 #ifndef __ASSEMBLY__
 
-#define UNWIND_HINT(type, sp_reg, sp_offset, signal)	\
+#define UNWIND_HINT(type, sp_reg, sp_offset, signal)		\
 	"987: \n\t"						\
 	".pushsection .discard.unwind_hints\n\t"		\
+	ANNOTATE_DATA_SPECIAL "\n\t"				\
 	/* struct unwind_hint */				\
 	".long 987b - .\n\t"					\
 	".short " __stringify(sp_offset) "\n\t"			\
@@ -45,35 +45,21 @@
 #define STACK_FRAME_NON_STANDARD_FP(func)
 #endif
 
-#define ANNOTATE_NOENDBR					\
-	"986: \n\t"						\
-	".pushsection .discard.noendbr\n\t"			\
-	".long 986b - .\n\t"					\
-	".popsection\n\t"
-
 #define ASM_REACHABLE							\
 	"998:\n\t"							\
 	".pushsection .discard.reachable\n\t"				\
-	".long 998b - .\n\t"						\
+	".long 998b\n\t"						\
 	".popsection\n\t"
 
-#else /* __ASSEMBLY__ */
+#define __ASM_BREF(label)	label ## b
 
-/*
- * This macro indicates that the following intra-function call is valid.
- * Any non-annotated intra-function call will cause objtool to issue a warning.
- */
-#define ANNOTATE_INTRA_FUNCTION_CALL				\
-	999:							\
-	.pushsection .discard.intra_function_calls;		\
-	.long 999b - .;						\
-	.popsection;
+#else /* __ASSEMBLY__ */
 
 /*
  * In asm, there are two kinds of code: normal C-type callable functions and
  * the rest.  The normal callable functions can be called by other code, and
  * don't do anything unusual with the stack.  Such normal callable functions
- * are annotated with the ENTRY/ENDPROC macros.  Most asm code falls in this
+ * are annotated with SYM_FUNC_{START,END}.  Most asm code falls in this
  * category.  In this case, no special debugging annotations are needed because
  * objtool can automatically generate the ORC data for the ORC unwinder to read
  * at runtime.
@@ -93,6 +79,7 @@
 .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0
 .Lhere_\@:
 	.pushsection .discard.unwind_hints
+		ANNOTATE_DATA_SPECIAL
 		/* struct unwind_hint */
 		.long .Lhere_\@ - .
 		.short \sp_offset
@@ -105,7 +92,7 @@
 
 .macro STACK_FRAME_NON_STANDARD func:req
 	.pushsection .discard.func_stack_frame_non_standard, "aw"
-	.long \func - .
+	.quad \func
 	.popsection
 .endm
 
@@ -115,36 +102,6 @@
 #endif
 .endm
 
-.macro ANNOTATE_NOENDBR
-.Lhere_\@:
-	.pushsection .discard.noendbr
-	.long	.Lhere_\@ - .
-	.popsection
-.endm
-
-/*
- * Use objtool to validate the entry requirement that all code paths do
- * VALIDATE_UNRET_END before RET.
- *
- * NOTE: The macro must be used at the beginning of a global symbol, otherwise
- * it will be ignored.
- */
-.macro VALIDATE_UNRET_BEGIN
-#if defined(CONFIG_NOINSTR_VALIDATION) && defined(CONFIG_CPU_UNRET_ENTRY)
-.Lhere_\@:
-	.pushsection .discard.validate_unret
-	.long	.Lhere_\@ - .
-	.popsection
-#endif
-.endm
-
-.macro REACHABLE
-.Lhere_\@:
-	.pushsection .discard.reachable
-	.long	.Lhere_\@ - .
-	.popsection
-.endm
-
 #endif /* __ASSEMBLY__ */
 
 #else /* !CONFIG_OBJTOOL */
@@ -154,20 +111,20 @@
 #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t"
 #define STACK_FRAME_NON_STANDARD(func)
 #define STACK_FRAME_NON_STANDARD_FP(func)
-#define ANNOTATE_NOENDBR
-#define ASM_REACHABLE
 #else
-#define ANNOTATE_INTRA_FUNCTION_CALL
 .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0
 .endm
 .macro STACK_FRAME_NON_STANDARD func:req
 .endm
-.macro ANNOTATE_NOENDBR
-.endm
-.macro REACHABLE
-.endm
 #endif
 
 #endif /* CONFIG_OBJTOOL */
 
+#if defined(CONFIG_NOINSTR_VALIDATION) && \
+	(defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO))
+#define VALIDATE_UNRET_BEGIN	ANNOTATE_UNRET_BEGIN
+#else
+#define VALIDATE_UNRET_BEGIN
+#endif
+
 #endif /* _LINUX_OBJTOOL_H */
diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h
index 453a4f4ef39d..c6def4049b1a 100644
--- a/include/linux/objtool_types.h
+++ b/include/linux/objtool_types.h
@@ -54,4 +54,19 @@ struct unwind_hint {
 #define UNWIND_HINT_TYPE_SAVE		6
 #define UNWIND_HINT_TYPE_RESTORE	7
 
+/*
+ * Annotate types
+ */
+#define ANNOTYPE_NOENDBR		1
+#define ANNOTYPE_RETPOLINE_SAFE		2
+#define ANNOTYPE_INSTR_BEGIN		3
+#define ANNOTYPE_INSTR_END		4
+#define ANNOTYPE_UNRET_BEGIN		5
+#define ANNOTYPE_IGNORE_ALTS		6
+#define ANNOTYPE_INTRA_FUNCTION_CALL	7
+#define ANNOTYPE_REACHABLE		8
+#define ANNOTYPE_NOCFI			9
+
+#define ANNOTYPE_DATA_SPECIAL		1
+
 #endif /* _LINUX_OBJTOOL_TYPES_H */
diff --git a/include/linux/of.h b/include/linux/of.h
index 6ecde0515677..01bb3affcd49 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -13,6 +13,7 @@
  */
 #include <linux/types.h>
 #include <linux/bitops.h>
+#include <linux/cleanup.h>
 #include <linux/errno.h>
 #include <linux/kobject.h>
 #include <linux/mod_devicetable.h>
@@ -66,7 +67,7 @@ struct device_node {
 #endif
 };
 
-#define MAX_PHANDLE_ARGS 16
+#define MAX_PHANDLE_ARGS NR_FWNODE_REFERENCE_ARGS
 struct of_phandle_args {
 	struct device_node *np;
 	int args_count;
@@ -96,10 +97,12 @@ struct of_reconfig_data {
 	struct property		*old_prop;
 };
 
+extern const struct kobj_type of_node_ktype;
+extern const struct fwnode_operations of_fwnode_ops;
+
 /**
  * of_node_init - initialize a devicetree node
  * @node: Pointer to device node that has been created by kzalloc()
- * @phandle_name: Name of property holding a phandle value
  *
  * On return the device_node refcount is set to one.  Use of_node_put()
  * on @node when done to free the memory allocated for it.  If the node
@@ -107,9 +110,6 @@ struct of_reconfig_data {
  * whether to free the memory will be done by node->release(), which is
  * of_node_release().
  */
-/* initialize a node */
-extern const struct kobj_type of_node_ktype;
-extern const struct fwnode_operations of_fwnode_ops;
 static inline void of_node_init(struct device_node *node)
 {
 #if defined(CONFIG_OF_KOBJ)
@@ -135,6 +135,7 @@ static inline struct device_node *of_node_get(struct device_node *node)
 }
 static inline void of_node_put(struct device_node *node) { }
 #endif /* !CONFIG_OF_DYNAMIC */
+DEFINE_FREE(device_node, struct device_node *, if (_T) of_node_put(_T))
 
 /* Pointer for first entry in chain of all nodes. */
 extern struct device_node *of_root;
@@ -181,11 +182,6 @@ static inline bool is_of_node(const struct fwnode_handle *fwnode)
 			&__of_fwnode_handle_node->fwnode : NULL;	\
 	})
 
-static inline bool of_have_populated_dt(void)
-{
-	return of_root != NULL;
-}
-
 static inline bool of_node_is_root(const struct device_node *node)
 {
 	return node && (node->parent == NULL);
@@ -293,13 +289,20 @@ extern struct device_node *of_get_parent(const struct device_node *node);
 extern struct device_node *of_get_next_parent(struct device_node *node);
 extern struct device_node *of_get_next_child(const struct device_node *node,
 					     struct device_node *prev);
+extern struct device_node *of_get_next_child_with_prefix(const struct device_node *node,
+							 struct device_node *prev,
+							 const char *prefix);
 extern struct device_node *of_get_next_available_child(
 	const struct device_node *node, struct device_node *prev);
+extern struct device_node *of_get_next_reserved_child(
+	const struct device_node *node, struct device_node *prev);
 
 extern struct device_node *of_get_compatible_child(const struct device_node *parent,
 					const char *compatible);
 extern struct device_node *of_get_child_by_name(const struct device_node *node,
 					const char *name);
+extern struct device_node *of_get_available_child_by_name(const struct device_node *node,
+							  const char *name);
 
 /* cache lookup */
 extern struct device_node *of_find_next_cache_node(const struct device_node *);
@@ -310,8 +313,12 @@ extern struct device_node *of_find_node_with_property(
 extern struct property *of_find_property(const struct device_node *np,
 					 const char *name,
 					 int *lenp);
+extern bool of_property_read_bool(const struct device_node *np, const char *propname);
 extern int of_property_count_elems_of_size(const struct device_node *np,
 				const char *propname, int elem_size);
+extern int of_property_read_u16_index(const struct device_node *np,
+				       const char *propname,
+				       u32 index, u16 *out_value);
 extern int of_property_read_u32_index(const struct device_node *np,
 				       const char *propname,
 				       u32 index, u32 *out_value);
@@ -359,13 +366,10 @@ extern struct device_node *of_get_cpu_node(int cpu, unsigned int *thread);
 extern struct device_node *of_cpu_device_node_get(int cpu);
 extern int of_cpu_node_to_id(struct device_node *np);
 extern struct device_node *of_get_next_cpu_node(struct device_node *prev);
-extern struct device_node *of_get_cpu_state_node(struct device_node *cpu_node,
+extern struct device_node *of_get_cpu_state_node(const struct device_node *cpu_node,
 						 int index);
 extern u64 of_get_cpu_hwid(struct device_node *cpun, unsigned int thread);
 
-#define for_each_property_of_node(dn, pp) \
-	for (pp = dn->properties; pp != NULL; pp = pp->next)
-
 extern int of_n_addr_cells(struct device_node *np);
 extern int of_n_size_cells(struct device_node *np);
 extern const struct of_device_id *of_match_node(
@@ -399,11 +403,25 @@ extern int of_phandle_iterator_args(struct of_phandle_iterator *it,
 				    uint32_t *args,
 				    int size);
 
-extern void of_alias_scan(void * (*dt_alloc)(u64 size, u64 align));
-extern int of_alias_get_id(struct device_node *np, const char *stem);
+extern int of_alias_get_id(const struct device_node *np, const char *stem);
 extern int of_alias_get_highest_id(const char *stem);
 
-extern int of_machine_is_compatible(const char *compat);
+bool of_machine_compatible_match(const char *const *compats);
+bool of_machine_device_match(const struct of_device_id *matches);
+const void *of_machine_get_match_data(const struct of_device_id *matches);
+
+/**
+ * of_machine_is_compatible - Test root of device tree for a given compatible value
+ * @compat: compatible string to look for in root node's compatible property.
+ *
+ * Return: true if the root node has the given value in its compatible property.
+ */
+static inline bool of_machine_is_compatible(const char *compat)
+{
+	const char *compats[] = { compat, NULL };
+
+	return of_machine_compatible_match(compats);
+}
 
 extern int of_add_property(struct device_node *np, struct property *prop);
 extern int of_remove_property(struct device_node *np, struct property *prop);
@@ -422,14 +440,12 @@ extern int of_detach_node(struct device_node *);
 #define of_match_ptr(_ptr)	(_ptr)
 
 /*
- * struct property *prop;
- * const __be32 *p;
  * u32 u;
  *
- * of_property_for_each_u32(np, "propname", prop, p, u)
+ * of_property_for_each_u32(np, "propname", u)
  *         printk("U32 value: %x\n", u);
  */
-const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur,
+const __be32 *of_prop_next_u32(const struct property *prop, const __be32 *cur,
 			       u32 *pu);
 /*
  * struct property *prop;
@@ -438,11 +454,11 @@ const __be32 *of_prop_next_u32(struct property *prop, const __be32 *cur,
  * of_property_for_each_string(np, "propname", prop, s)
  *         printk("String value: %s\n", s);
  */
-const char *of_prop_next_string(struct property *prop, const char *cur);
+const char *of_prop_next_string(const struct property *prop, const char *cur);
 
-bool of_console_check(struct device_node *dn, char *name, int index);
+bool of_console_check(const struct device_node *dn, char *name, int index);
 
-int of_map_id(struct device_node *np, u32 id,
+int of_map_id(const struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out);
 
@@ -536,12 +552,25 @@ static inline struct device_node *of_get_next_child(
 	return NULL;
 }
 
+static inline struct device_node *of_get_next_child_with_prefix(
+	const struct device_node *node, struct device_node *prev,
+	const char *prefix)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_get_next_available_child(
 	const struct device_node *node, struct device_node *prev)
 {
 	return NULL;
 }
 
+static inline struct device_node *of_get_next_reserved_child(
+	const struct device_node *node, struct device_node *prev)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_find_node_with_property(
 	struct device_node *from, const char *prop_name)
 {
@@ -550,11 +579,6 @@ static inline struct device_node *of_find_node_with_property(
 
 #define of_fwnode_handle(node) NULL
 
-static inline bool of_have_populated_dt(void)
-{
-	return false;
-}
-
 static inline struct device_node *of_get_compatible_child(const struct device_node *parent,
 					const char *compatible)
 {
@@ -568,6 +592,13 @@ static inline struct device_node *of_get_child_by_name(
 	return NULL;
 }
 
+static inline struct device_node *of_get_available_child_by_name(
+					const struct device_node *node,
+					const char *name)
+{
+	return NULL;
+}
+
 static inline int of_device_is_compatible(const struct device_node *device,
 					  const char *name)
 {
@@ -605,12 +636,24 @@ static inline struct device_node *of_find_compatible_node(
 	return NULL;
 }
 
+static inline bool of_property_read_bool(const struct device_node *np,
+					const char *propname)
+{
+	return false;
+}
+
 static inline int of_property_count_elems_of_size(const struct device_node *np,
 			const char *propname, int elem_size)
 {
 	return -ENOSYS;
 }
 
+static inline int of_property_read_u16_index(const struct device_node *np,
+			const char *propname, u32 index, u16 *out_value)
+{
+	return -ENOSYS;
+}
+
 static inline int of_property_read_u32_index(const struct device_node *np,
 			const char *propname, u32 index, u32 *out_value)
 {
@@ -809,18 +852,34 @@ static inline int of_remove_property(struct device_node *np, struct property *pr
 	return 0;
 }
 
+static inline bool of_machine_compatible_match(const char *const *compats)
+{
+	return false;
+}
+
+static inline bool of_machine_device_match(const struct of_device_id *matches)
+{
+	return false;
+}
+
+static inline const void *
+of_machine_get_match_data(const struct of_device_id *matches)
+{
+	return NULL;
+}
+
 static inline bool of_console_check(const struct device_node *dn, const char *name, int index)
 {
 	return false;
 }
 
-static inline const __be32 *of_prop_next_u32(struct property *prop,
+static inline const __be32 *of_prop_next_u32(const struct property *prop,
 		const __be32 *cur, u32 *pu)
 {
 	return NULL;
 }
 
-static inline const char *of_prop_next_string(struct property *prop,
+static inline const char *of_prop_next_string(const struct property *prop,
 		const char *cur)
 {
 	return NULL;
@@ -859,7 +918,7 @@ static inline void of_property_clear_flag(struct property *p, unsigned long flag
 {
 }
 
-static inline int of_map_id(struct device_node *np, u32 id,
+static inline int of_map_id(const struct device_node *np, u32 id,
 			     const char *map_name, const char *map_mask_name,
 			     struct device_node **target, u32 *id_out)
 {
@@ -887,11 +946,8 @@ static inline const void *of_device_get_match_data(const struct device *dev)
 #define of_node_cmp(s1, s2)		strcasecmp((s1), (s2))
 #endif
 
-static inline int of_prop_val_eq(struct property *p1, struct property *p2)
-{
-	return p1->length == p2->length &&
-	       !memcmp(p1->value, p2->value, (size_t)p1->length);
-}
+#define for_each_property_of_node(dn, pp) \
+	for (pp = dn->properties; pp != NULL; pp = pp->next)
 
 #if defined(CONFIG_OF) && defined(CONFIG_NUMA)
 extern int of_node_to_nid(struct device_node *np);
@@ -1067,6 +1123,22 @@ static inline int of_parse_phandle_with_optional_args(const struct device_node *
 }
 
 /**
+ * of_phandle_args_equal() - Compare two of_phandle_args
+ * @a1:		First of_phandle_args to compare
+ * @a2:		Second of_phandle_args to compare
+ *
+ * Return: True if a1 and a2 are the same (same node pointer, same phandle
+ * args), false otherwise.
+ */
+static inline bool of_phandle_args_equal(const struct of_phandle_args *a1,
+					 const struct of_phandle_args *a2)
+{
+	return a1->np == a2->np &&
+	       a1->args_count == a2->args_count &&
+	       !memcmp(a1->args, a2->args, sizeof(a1->args[0]) * a1->args_count);
+}
+
+/**
  * of_property_count_u8_elems - Count the number of u8 elements in a property
  *
  * @np:		device node from which the property value is to be read.
@@ -1075,7 +1147,7 @@ static inline int of_parse_phandle_with_optional_args(const struct device_node *
  * Search for a property in a device node and count the number of u8 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u8 and -ENODATA if the
  * property does not have a value.
  */
@@ -1094,7 +1166,7 @@ static inline int of_property_count_u8_elems(const struct device_node *np,
  * Search for a property in a device node and count the number of u16 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u16 and -ENODATA if the
  * property does not have a value.
  */
@@ -1113,7 +1185,7 @@ static inline int of_property_count_u16_elems(const struct device_node *np,
  * Search for a property in a device node and count the number of u32 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u32 and -ENODATA if the
  * property does not have a value.
  */
@@ -1132,7 +1204,7 @@ static inline int of_property_count_u32_elems(const struct device_node *np,
  * Search for a property in a device node and count the number of u64 elements
  * in it.
  *
- * Return: The number of elements on sucess, -EINVAL if the property does
+ * Return: The number of elements on success, -EINVAL if the property does
  * not exist or its length does not match a multiple of u64 and -ENODATA if the
  * property does not have a value.
  */
@@ -1209,24 +1281,6 @@ static inline int of_property_read_string_index(const struct device_node *np,
 }
 
 /**
- * of_property_read_bool - Find a property
- * @np:		device node from which the property value is to be read.
- * @propname:	name of the property to be searched.
- *
- * Search for a boolean property in a device node. Usage on non-boolean
- * property types is deprecated.
- *
- * Return: true if the property exists false otherwise.
- */
-static inline bool of_property_read_bool(const struct device_node *np,
-					 const char *propname)
-{
-	struct property *prop = of_find_property(np, propname, NULL);
-
-	return prop ? true : false;
-}
-
-/**
  * of_property_present - Test if a property is present in a node
  * @np:		device node to search for the property.
  * @propname:	name of the property to be searched.
@@ -1237,7 +1291,9 @@ static inline bool of_property_read_bool(const struct device_node *np,
  */
 static inline bool of_property_present(const struct device_node *np, const char *propname)
 {
-	return of_property_read_bool(np, propname);
+	struct property *prop = of_find_property(np, propname, NULL);
+
+	return prop ? true : false;
 }
 
 /**
@@ -1398,11 +1454,12 @@ static inline int of_property_read_s32(const struct device_node *np,
 	     err == 0;							\
 	     err = of_phandle_iterator_next(it))
 
-#define of_property_for_each_u32(np, propname, prop, p, u)	\
-	for (prop = of_find_property(np, propname, NULL),	\
-		p = of_prop_next_u32(prop, NULL, &u);		\
-		p;						\
-		p = of_prop_next_u32(prop, p, &u))
+#define of_property_for_each_u32(np, propname, u)			\
+	for (struct {const struct property *prop; const __be32 *item; } _it =	\
+		{of_find_property(np, propname, NULL),			\
+		 of_prop_next_u32(_it.prop, NULL, &u)};			\
+	     _it.item;							\
+	     _it.item = of_prop_next_u32(_it.prop, _it.item, &u))
 
 #define of_property_for_each_string(np, propname, prop, s)	\
 	for (prop = of_find_property(np, propname, NULL),	\
@@ -1429,9 +1486,31 @@ static inline int of_property_read_s32(const struct device_node *np,
 #define for_each_child_of_node(parent, child) \
 	for (child = of_get_next_child(parent, NULL); child != NULL; \
 	     child = of_get_next_child(parent, child))
+
+#define for_each_child_of_node_scoped(parent, child) \
+	for (struct device_node *child __free(device_node) =		\
+	     of_get_next_child(parent, NULL);				\
+	     child != NULL;						\
+	     child = of_get_next_child(parent, child))
+
+#define for_each_child_of_node_with_prefix(parent, child, prefix)	\
+	for (struct device_node *child __free(device_node) =		\
+	     of_get_next_child_with_prefix(parent, NULL, prefix);	\
+	     child != NULL;						\
+	     child = of_get_next_child_with_prefix(parent, child, prefix))
+
 #define for_each_available_child_of_node(parent, child) \
 	for (child = of_get_next_available_child(parent, NULL); child != NULL; \
 	     child = of_get_next_available_child(parent, child))
+#define for_each_reserved_child_of_node(parent, child)			\
+	for (child = of_get_next_reserved_child(parent, NULL); child != NULL; \
+	     child = of_get_next_reserved_child(parent, child))
+
+#define for_each_available_child_of_node_scoped(parent, child) \
+	for (struct device_node *child __free(device_node) =		\
+	     of_get_next_available_child(parent, NULL);			\
+	     child != NULL;						\
+	     child = of_get_next_available_child(parent, child))
 
 #define for_each_of_cpu_node(cpu) \
 	for (cpu = of_get_next_cpu_node(NULL); cpu != NULL; \
@@ -1580,6 +1659,36 @@ static inline int of_changeset_update_property(struct of_changeset *ocs,
 {
 	return of_changeset_action(ocs, OF_RECONFIG_UPDATE_PROPERTY, np, prop);
 }
+
+struct device_node *of_changeset_create_node(struct of_changeset *ocs,
+					     struct device_node *parent,
+					     const char *full_name);
+int of_changeset_add_prop_string(struct of_changeset *ocs,
+				 struct device_node *np,
+				 const char *prop_name, const char *str);
+int of_changeset_add_prop_string_array(struct of_changeset *ocs,
+				       struct device_node *np,
+				       const char *prop_name,
+				       const char * const *str_array, size_t sz);
+int of_changeset_add_prop_u32_array(struct of_changeset *ocs,
+				    struct device_node *np,
+				    const char *prop_name,
+				    const u32 *array, size_t sz);
+static inline int of_changeset_add_prop_u32(struct of_changeset *ocs,
+					    struct device_node *np,
+					    const char *prop_name,
+					    const u32 val)
+{
+	return of_changeset_add_prop_u32_array(ocs, np, prop_name, &val, 1);
+}
+
+int of_changeset_update_prop_string(struct of_changeset *ocs,
+				    struct device_node *np,
+				    const char *prop_name, const char *str);
+
+int of_changeset_add_prop_bool(struct of_changeset *ocs, struct device_node *np,
+			       const char *prop_name);
+
 #else /* CONFIG_OF_DYNAMIC */
 static inline int of_reconfig_notifier_register(struct notifier_block *nb)
 {
@@ -1612,6 +1721,21 @@ static inline bool of_device_is_system_power_controller(const struct device_node
 	return of_property_read_bool(np, "system-power-controller");
 }
 
+/**
+ * of_have_populated_dt() - Has DT been populated by bootloader
+ *
+ * Return: True if a DTB has been populated by the bootloader and it isn't the
+ * empty builtin one. False otherwise.
+ */
+static inline bool of_have_populated_dt(void)
+{
+#ifdef CONFIG_OF
+	return of_property_present(of_root, "compatible");
+#else
+	return false;
+#endif
+}
+
 /*
  * Overlay support
  */
@@ -1645,7 +1769,7 @@ struct of_overlay_notify_data {
 #ifdef CONFIG_OF_OVERLAY
 
 int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
-			 int *ovcs_id);
+			 int *ovcs_id, const struct device_node *target_base);
 int of_overlay_remove(int *ovcs_id);
 int of_overlay_remove_all(void);
 
@@ -1654,8 +1778,8 @@ int of_overlay_notifier_unregister(struct notifier_block *nb);
 
 #else
 
-static inline int of_overlay_fdt_apply(void *overlay_fdt, u32 overlay_fdt_size,
-				       int *ovcs_id)
+static inline int of_overlay_fdt_apply(const void *overlay_fdt, u32 overlay_fdt_size,
+				       int *ovcs_id, const struct device_node *target_base)
 {
 	return -ENOTSUPP;
 }
diff --git a/include/linux/of_address.h b/include/linux/of_address.h
index 26a19daf0d09..0cff90365391 100644
--- a/include/linux/of_address.h
+++ b/include/linux/of_address.h
@@ -10,7 +10,7 @@ struct of_bus;
 
 struct of_pci_range_parser {
 	struct device_node *node;
-	struct of_bus *bus;
+	const struct of_bus *bus;
 	const __be32 *range;
 	const __be32 *end;
 	int na;
@@ -26,6 +26,7 @@ struct of_pci_range {
 		u64 bus_addr;
 	};
 	u64 cpu_addr;
+	u64 parent_bus_addr;
 	u64 size;
 	u32 flags;
 };
@@ -83,8 +84,8 @@ extern struct of_pci_range *of_pci_range_parser_one(
 					struct of_pci_range *range);
 extern int of_pci_address_to_resource(struct device_node *dev, int bar,
 				      struct resource *r);
-extern int of_pci_range_to_resource(struct of_pci_range *range,
-				    struct device_node *np,
+extern int of_pci_range_to_resource(const struct of_pci_range *range,
+				    const struct device_node *np,
 				    struct resource *res);
 extern int of_range_to_resource(struct device_node *np, int index,
 				struct resource *res);
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 2c7a3d4bc775..9042bca5bb84 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -2,10 +2,7 @@
 #ifndef _LINUX_OF_DEVICE_H
 #define _LINUX_OF_DEVICE_H
 
-#include <linux/platform_device.h>
-#include <linux/of_platform.h> /* temporary until merge */
-
-#include <linux/of.h>
+#include <linux/device/driver.h>
 
 struct device;
 struct of_device_id;
@@ -40,6 +37,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return of_dma_configure_id(dev, np, force_dma, NULL);
 }
+
+void of_device_make_bus_id(struct device *dev);
+
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -82,6 +82,9 @@ static inline int of_dma_configure(struct device *dev,
 {
 	return 0;
 }
+
+static inline void of_device_make_bus_id(struct device *dev) {}
+
 #endif /* CONFIG_OF */
 
 #endif /* _LINUX_OF_DEVICE_H */
diff --git a/include/linux/of_fdt.h b/include/linux/of_fdt.h
index d69ad5bb1eb1..51dadbaa3d63 100644
--- a/include/linux/of_fdt.h
+++ b/include/linux/of_fdt.h
@@ -31,6 +31,7 @@ extern void *of_fdt_unflatten_tree(const unsigned long *blob,
 extern int __initdata dt_root_addr_cells;
 extern int __initdata dt_root_size_cells;
 extern void *initial_boot_params;
+extern phys_addr_t initial_boot_params_pa;
 
 extern char __dtb_start[];
 extern char __dtb_end[];
@@ -54,6 +55,15 @@ extern int of_get_flat_dt_subnode_by_name(unsigned long node,
 					  const char *uname);
 extern const void *of_get_flat_dt_prop(unsigned long node, const char *name,
 				       int *size);
+
+extern const __be32 *of_flat_dt_get_addr_size_prop(unsigned long node,
+						   const char *name,
+						   int *entries);
+extern bool of_flat_dt_get_addr_size(unsigned long node, const char *name,
+				     u64 *addr, u64 *size);
+extern void of_flat_dt_read_addr_size(const __be32 *prop, int entry_index,
+				      u64 *addr, u64 *size);
+
 extern int of_flat_dt_is_compatible(unsigned long node, const char *name);
 extern unsigned long of_get_flat_dt_root(void);
 extern uint32_t of_get_flat_dt_phandle(unsigned long node);
@@ -70,8 +80,8 @@ extern u64 dt_mem_next_cell(int s, const __be32 **cellp);
 /* Early flat tree scan hooks */
 extern int early_init_dt_scan_root(void);
 
-extern bool early_init_dt_scan(void *params);
-extern bool early_init_dt_verify(void *params);
+extern bool early_init_dt_scan(void *dt_virt, phys_addr_t dt_phys);
+extern bool early_init_dt_verify(void *dt_virt, phys_addr_t dt_phys);
 extern void early_init_dt_scan_nodes(void);
 
 extern const char *of_flat_dt_get_machine_name(void);
diff --git a/include/linux/of_graph.h b/include/linux/of_graph.h
index 4d7756087b6b..a692d9d979a6 100644
--- a/include/linux/of_graph.h
+++ b/include/linux/of_graph.h
@@ -11,6 +11,7 @@
 #ifndef __LINUX_OF_GRAPH_H
 #define __LINUX_OF_GRAPH_H
 
+#include <linux/cleanup.h>
 #include <linux/types.h>
 #include <linux/errno.h>
 
@@ -37,14 +38,43 @@ struct of_endpoint {
 	for (child = of_graph_get_next_endpoint(parent, NULL); child != NULL; \
 	     child = of_graph_get_next_endpoint(parent, child))
 
+/**
+ * for_each_of_graph_port - iterate over every port in a device or ports node
+ * @parent: parent device or ports node containing port
+ * @child: loop variable pointing to the current port node
+ *
+ * When breaking out of the loop, and continue to use the @child, you need to
+ * use return_ptr(@child) or no_free_ptr(@child) not to call __free() for it.
+ */
+#define for_each_of_graph_port(parent, child)			\
+	for (struct device_node *child __free(device_node) = of_graph_get_next_port(parent, NULL);\
+	     child != NULL; child = of_graph_get_next_port(parent, child))
+
+/**
+ * for_each_of_graph_port_endpoint - iterate over every endpoint in a port node
+ * @parent: parent port node
+ * @child: loop variable pointing to the current endpoint node
+ *
+ * When breaking out of the loop, and continue to use the @child, you need to
+ * use return_ptr(@child) or no_free_ptr(@child) not to call __free() for it.
+ */
+#define for_each_of_graph_port_endpoint(parent, child)			\
+	for (struct device_node *child __free(device_node) = of_graph_get_next_port_endpoint(parent, NULL);\
+	     child != NULL; child = of_graph_get_next_port_endpoint(parent, child))
+
 #ifdef CONFIG_OF
 bool of_graph_is_present(const struct device_node *node);
 int of_graph_parse_endpoint(const struct device_node *node,
 				struct of_endpoint *endpoint);
-int of_graph_get_endpoint_count(const struct device_node *np);
+unsigned int of_graph_get_endpoint_count(const struct device_node *np);
+unsigned int of_graph_get_port_count(struct device_node *np);
 struct device_node *of_graph_get_port_by_id(struct device_node *node, u32 id);
 struct device_node *of_graph_get_next_endpoint(const struct device_node *parent,
 					struct device_node *previous);
+struct device_node *of_graph_get_next_port(const struct device_node *parent,
+					   struct device_node *port);
+struct device_node *of_graph_get_next_port_endpoint(const struct device_node *port,
+						    struct device_node *prev);
 struct device_node *of_graph_get_endpoint_by_regs(
 		const struct device_node *parent, int port_reg, int reg);
 struct device_node *of_graph_get_remote_endpoint(
@@ -68,7 +98,12 @@ static inline int of_graph_parse_endpoint(const struct device_node *node,
 	return -ENOSYS;
 }
 
-static inline int of_graph_get_endpoint_count(const struct device_node *np)
+static inline unsigned int of_graph_get_endpoint_count(const struct device_node *np)
+{
+	return 0;
+}
+
+static inline unsigned int of_graph_get_port_count(struct device_node *np)
 {
 	return 0;
 }
@@ -86,6 +121,20 @@ static inline struct device_node *of_graph_get_next_endpoint(
 	return NULL;
 }
 
+static inline struct device_node *of_graph_get_next_port(
+					const struct device_node *parent,
+					struct device_node *previous)
+{
+	return NULL;
+}
+
+static inline struct device_node *of_graph_get_next_port_endpoint(
+					const struct device_node *parent,
+					struct device_node *previous)
+{
+	return NULL;
+}
+
 static inline struct device_node *of_graph_get_endpoint_by_regs(
 		const struct device_node *parent, int port_reg, int reg)
 {
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index 9a5e6b410dd2..e61cbbe12dac 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -8,20 +8,19 @@ struct iommu_ops;
 
 #ifdef CONFIG_OF_IOMMU
 
-extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np,
-					const u32 *id);
+extern int of_iommu_configure(struct device *dev, struct device_node *master_np,
+			      const u32 *id);
 
 extern void of_iommu_get_resv_regions(struct device *dev,
 				      struct list_head *list);
 
 #else
 
-static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np,
-					 const u32 *id)
+static inline int of_iommu_configure(struct device *dev,
+				     struct device_node *master_np,
+				     const u32 *id)
 {
-	return NULL;
+	return -ENODEV;
 }
 
 static inline void of_iommu_get_resv_regions(struct device *dev,
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index d6d3eae2f145..1c2bc0281807 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -43,18 +43,20 @@ extern int of_irq_parse_one(struct device_node *device, int index,
 			  struct of_phandle_args *out_irq);
 extern int of_irq_count(struct device_node *dev);
 extern int of_irq_get(struct device_node *dev, int index);
+extern const struct cpumask *of_irq_get_affinity(struct device_node *dev,
+						      int index);
 extern int of_irq_get_byname(struct device_node *dev, const char *name);
 extern int of_irq_to_resource_table(struct device_node *dev,
 		struct resource *res, int nr_irqs);
 extern struct device_node *of_irq_find_parent(struct device_node *child);
 extern struct irq_domain *of_msi_get_domain(struct device *dev,
-					    struct device_node *np,
+					    const struct device_node *np,
 					    enum irq_domain_bus_token token);
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
 							u32 id,
 							u32 bus_token);
-extern void of_msi_configure(struct device *dev, struct device_node *np);
-u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in);
+extern void of_msi_configure(struct device *dev, const struct device_node *np);
+extern u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in);
 #else
 static inline void of_irq_init(const struct of_device_id *matches)
 {
@@ -76,6 +78,11 @@ static inline int of_irq_get_byname(struct device_node *dev, const char *name)
 {
 	return 0;
 }
+static inline const struct cpumask *of_irq_get_affinity(struct device_node *dev,
+							int index)
+{
+	return NULL;
+}
 static inline int of_irq_to_resource_table(struct device_node *dev,
 					   struct resource *res, int nr_irqs)
 {
@@ -100,8 +107,7 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
-static inline u32 of_msi_map_id(struct device *dev,
-				 struct device_node *msi_np, u32 id_in)
+static inline u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in)
 {
 	return id_in;
 }
diff --git a/include/linux/of_platform.h b/include/linux/of_platform.h
index d8045bcfc35e..17471ef8e092 100644
--- a/include/linux/of_platform.h
+++ b/include/linux/of_platform.h
@@ -7,11 +7,11 @@
  */
 
 #include <linux/mod_devicetable.h>
-#include <linux/of_device.h>
-#include <linux/platform_device.h>
 
 struct device;
+struct device_node;
 struct of_device_id;
+struct platform_device;
 
 /**
  * struct of_dev_auxdata - lookup table entry for device names & platform_data
@@ -47,8 +47,6 @@ struct of_dev_auxdata {
 	{ .compatible = _compat, .phys_addr = _phys, .name = _name, \
 	  .platform_data = _pdata }
 
-extern const struct of_device_id of_default_bus_match_table[];
-
 /* Platform drivers register/unregister */
 extern struct platform_device *of_device_alloc(struct device_node *np,
 					 const char *bus_id,
@@ -127,10 +125,4 @@ static inline int devm_of_platform_populate(struct device *dev)
 static inline void devm_of_platform_depopulate(struct device *dev) { }
 #endif
 
-#if defined(CONFIG_OF_DYNAMIC) && defined(CONFIG_OF_ADDRESS)
-extern void of_platform_register_reconfig_notifier(void);
-#else
-static inline void of_platform_register_reconfig_notifier(void) { }
-#endif
-
 #endif	/* _LINUX_OF_PLATFORM_H */
diff --git a/include/linux/of_reserved_mem.h b/include/linux/of_reserved_mem.h
index 4de2a24cadc9..f573423359f4 100644
--- a/include/linux/of_reserved_mem.h
+++ b/include/linux/of_reserved_mem.h
@@ -7,11 +7,11 @@
 
 struct of_phandle_args;
 struct reserved_mem_ops;
+struct resource;
 
 struct reserved_mem {
 	const char			*name;
 	unsigned long			fdt_node;
-	unsigned long			phandle;
 	const struct reserved_mem_ops	*ops;
 	phys_addr_t			base;
 	phys_addr_t			size;
@@ -40,6 +40,12 @@ int of_reserved_mem_device_init_by_name(struct device *dev,
 void of_reserved_mem_device_release(struct device *dev);
 
 struct reserved_mem *of_reserved_mem_lookup(struct device_node *np);
+int of_reserved_mem_region_to_resource(const struct device_node *np,
+				       unsigned int idx, struct resource *res);
+int of_reserved_mem_region_to_resource_byname(const struct device_node *np,
+					      const char *name, struct resource *res);
+int of_reserved_mem_region_count(const struct device_node *np);
+
 #else
 
 #define RESERVEDMEM_OF_DECLARE(name, compat, init)			\
@@ -64,6 +70,25 @@ static inline struct reserved_mem *of_reserved_mem_lookup(struct device_node *np
 {
 	return NULL;
 }
+
+static inline int of_reserved_mem_region_to_resource(const struct device_node *np,
+						     unsigned int idx,
+						     struct resource *res)
+{
+	return -ENOSYS;
+}
+
+static inline int of_reserved_mem_region_to_resource_byname(const struct device_node *np,
+							    const char *name,
+							    struct resource *res)
+{
+	return -ENOSYS;
+}
+
+static inline int of_reserved_mem_region_count(const struct device_node *np)
+{
+	return 0;
+}
 #endif
 
 /**
diff --git a/include/linux/oid_registry.h b/include/linux/oid_registry.h
index 0f4a8903922a..6de479ebbe5d 100644
--- a/include/linux/oid_registry.h
+++ b/include/linux/oid_registry.h
@@ -30,9 +30,6 @@ enum OID {
 
 	/* PKCS#1 {iso(1) member-body(2) us(840) rsadsi(113549) pkcs(1) pkcs-1(1)} */
 	OID_rsaEncryption,		/* 1.2.840.113549.1.1.1 */
-	OID_md2WithRSAEncryption,	/* 1.2.840.113549.1.1.2 */
-	OID_md3WithRSAEncryption,	/* 1.2.840.113549.1.1.3 */
-	OID_md4WithRSAEncryption,	/* 1.2.840.113549.1.1.4 */
 	OID_sha1WithRSAEncryption,	/* 1.2.840.113549.1.1.5 */
 	OID_sha256WithRSAEncryption,	/* 1.2.840.113549.1.1.11 */
 	OID_sha384WithRSAEncryption,	/* 1.2.840.113549.1.1.12 */
@@ -49,11 +46,6 @@ enum OID {
 	OID_smimeCapabilites,		/* 1.2.840.113549.1.9.15 */
 	OID_smimeAuthenticatedAttrs,	/* 1.2.840.113549.1.9.16.2.11 */
 
-	/* {iso(1) member-body(2) us(840) rsadsi(113549) digestAlgorithm(2)} */
-	OID_md2,			/* 1.2.840.113549.2.2 */
-	OID_md4,			/* 1.2.840.113549.2.4 */
-	OID_md5,			/* 1.2.840.113549.2.5 */
-
 	OID_mskrb5,			/* 1.2.840.48018.1.2.2 */
 	OID_krb5,			/* 1.2.840.113554.1.2.2 */
 	OID_krb5u2u,			/* 1.2.840.113554.1.2.2.3 */
@@ -67,6 +59,7 @@ enum OID {
 	OID_msOutlookExpress,		/* 1.3.6.1.4.1.311.16.4 */
 
 	OID_ntlmssp,			/* 1.3.6.1.4.1.311.2.2.10 */
+	OID_negoex,			/* 1.3.6.1.4.1.311.2.2.30 */
 
 	OID_spnego,			/* 1.3.6.1.5.5.2 */
 
@@ -76,6 +69,7 @@ enum OID {
 	OID_certAuthInfoAccess,		/* 1.3.6.1.5.5.7.1.1 */
 	OID_sha1,			/* 1.3.14.3.2.26 */
 	OID_id_ansip384r1,		/* 1.3.132.0.34 */
+	OID_id_ansip521r1,		/* 1.3.132.0.35 */
 	OID_sha256,			/* 2.16.840.1.101.3.4.2.1 */
 	OID_sha384,			/* 2.16.840.1.101.3.4.2.2 */
 	OID_sha512,			/* 2.16.840.1.101.3.4.2.3 */
@@ -140,12 +134,22 @@ enum OID {
 	OID_TPMImportableKey,		/* 2.23.133.10.1.4 */
 	OID_TPMSealedData,		/* 2.23.133.10.1.5 */
 
+	/* CSOR FIPS-202 SHA-3 */
+	OID_sha3_256,                           /* 2.16.840.1.101.3.4.2.8 */
+	OID_sha3_384,                           /* 2.16.840.1.101.3.4.2.9 */
+	OID_sha3_512,                           /* 2.16.840.1.101.3.4.2.10 */
+	OID_id_ecdsa_with_sha3_256,             /* 2.16.840.1.101.3.4.3.10 */
+	OID_id_ecdsa_with_sha3_384,             /* 2.16.840.1.101.3.4.3.11 */
+	OID_id_ecdsa_with_sha3_512,             /* 2.16.840.1.101.3.4.3.12 */
+	OID_id_rsassa_pkcs1_v1_5_with_sha3_256, /* 2.16.840.1.101.3.4.3.14 */
+	OID_id_rsassa_pkcs1_v1_5_with_sha3_384, /* 2.16.840.1.101.3.4.3.15 */
+	OID_id_rsassa_pkcs1_v1_5_with_sha3_512, /* 2.16.840.1.101.3.4.3.16 */
+
 	OID__NR
 };
 
 extern enum OID look_up_OID(const void *data, size_t datasize);
 extern int parse_OID(const void *data, size_t datasize, enum OID *oid);
 extern int sprint_oid(const void *, size_t, char *, size_t);
-extern int sprint_OID(enum OID, char *, size_t);
 
 #endif /* _LINUX_OID_REGISTRY_H */
diff --git a/include/linux/olpc-ec.h b/include/linux/olpc-ec.h
index c4602364e909..3c2891d85c41 100644
--- a/include/linux/olpc-ec.h
+++ b/include/linux/olpc-ec.h
@@ -56,6 +56,8 @@ extern int olpc_ec_sci_query(u16 *sci_value);
 
 extern bool olpc_ec_wakeup_available(void);
 
+asmlinkage int xo1_do_sleep(u8 sleep_state);
+
 #else
 
 static inline int olpc_ec_cmd(u8 cmd, u8 *inbuf, size_t inlen, u8 *outbuf,
diff --git a/include/linux/omap-gpmc.h b/include/linux/omap-gpmc.h
index 082841908fe7..263b915df1fb 100644
--- a/include/linux/omap-gpmc.h
+++ b/include/linux/omap-gpmc.h
@@ -66,10 +66,6 @@ extern int gpmc_calc_timings(struct gpmc_timings *gpmc_t,
 
 struct device_node;
 
-extern int gpmc_get_client_irq(unsigned irq_config);
-
-extern unsigned int gpmc_ticks_to_ns(unsigned int ticks);
-
 extern void gpmc_cs_write_reg(int cs, int idx, u32 val);
 extern int gpmc_calc_divider(unsigned int sync_clk);
 extern int gpmc_cs_set_timings(int cs, const struct gpmc_timings *t,
@@ -84,13 +80,3 @@ extern void gpmc_read_settings_dt(struct device_node *np,
 struct gpmc_timings;
 struct omap_nand_platform_data;
 struct omap_onenand_platform_data;
-
-#if IS_ENABLED(CONFIG_MTD_ONENAND_OMAP2)
-extern int gpmc_onenand_init(struct omap_onenand_platform_data *d);
-#else
-#define board_onenand_data	NULL
-static inline int gpmc_onenand_init(struct omap_onenand_platform_data *d)
-{
-	return 0;
-}
-#endif
diff --git a/include/linux/omap-mailbox.h b/include/linux/omap-mailbox.h
index 8aa984ec1f38..3cc5c4ed7f5a 100644
--- a/include/linux/omap-mailbox.h
+++ b/include/linux/omap-mailbox.h
@@ -10,17 +10,4 @@ typedef uintptr_t mbox_msg_t;
 
 #define omap_mbox_message(data) (u32)(mbox_msg_t)(data)
 
-typedef int __bitwise omap_mbox_irq_t;
-#define IRQ_TX ((__force omap_mbox_irq_t) 1)
-#define IRQ_RX ((__force omap_mbox_irq_t) 2)
-
-struct mbox_chan;
-struct mbox_client;
-
-struct mbox_chan *omap_mbox_request_channel(struct mbox_client *cl,
-					    const char *chan_name);
-
-void omap_mbox_enable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq);
-void omap_mbox_disable_irq(struct mbox_chan *chan, omap_mbox_irq_t irq);
-
 #endif /* OMAP_MAILBOX_H */
diff --git a/include/linux/once.h b/include/linux/once.h
index bc714d414448..449a0e34ad5a 100644
--- a/include/linux/once.h
+++ b/include/linux/once.h
@@ -46,7 +46,7 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key,
 #define DO_ONCE(func, ...)						     \
 	({								     \
 		bool ___ret = false;					     \
-		static bool __section(".data.once") ___done = false;	     \
+		static bool __section(".data..do_once") ___done = false;     \
 		static DEFINE_STATIC_KEY_TRUE(___once_key);		     \
 		if (static_branch_unlikely(&___once_key)) {		     \
 			unsigned long ___flags;				     \
@@ -64,7 +64,7 @@ void __do_once_sleepable_done(bool *done, struct static_key_true *once_key,
 #define DO_ONCE_SLEEPABLE(func, ...)						\
 	({									\
 		bool ___ret = false;						\
-		static bool __section(".data.once") ___done = false;		\
+		static bool __section(".data..do_once") ___done = false;	\
 		static DEFINE_STATIC_KEY_TRUE(___once_key);			\
 		if (static_branch_unlikely(&___once_key)) {			\
 			___ret = __do_once_sleepable_start(&___done);		\
diff --git a/include/linux/once_lite.h b/include/linux/once_lite.h
index b7bce4983638..236592c4eeb1 100644
--- a/include/linux/once_lite.h
+++ b/include/linux/once_lite.h
@@ -12,11 +12,11 @@
 
 #define __ONCE_LITE_IF(condition)					\
 	({								\
-		static bool __section(".data.once") __already_done;	\
+		static bool __section(".data..once") __already_done;	\
 		bool __ret_cond = !!(condition);			\
 		bool __ret_once = false;				\
 									\
-		if (unlikely(__ret_cond && !__already_done)) {		\
+		if (unlikely(__ret_cond) && unlikely(!__already_done)) {\
 			__already_done = true;				\
 			__ret_once = true;				\
 		}							\
diff --git a/include/linux/oom.h b/include/linux/oom.h
index 7d0c9c48a0c5..7b02bc1d0a7e 100644
--- a/include/linux/oom.h
+++ b/include/linux/oom.h
@@ -7,7 +7,6 @@
 #include <linux/types.h>
 #include <linux/nodemask.h>
 #include <uapi/linux/oom.h>
-#include <linux/sched/coredump.h> /* MMF_* */
 #include <linux/mm.h> /* VM_FAULT* */
 
 struct zonelist;
@@ -92,7 +91,7 @@ static inline bool tsk_is_oom_victim(struct task_struct * tsk)
  */
 static inline vm_fault_t check_stable_address_space(struct mm_struct *mm)
 {
-	if (unlikely(test_bit(MMF_UNSTABLE, &mm->flags)))
+	if (unlikely(mm_flags_test(MMF_UNSTABLE, mm)))
 		return VM_FAULT_SIGBUS;
 	return 0;
 }
diff --git a/include/linux/osq_lock.h b/include/linux/osq_lock.h
index 5581dbd3bd34..ea8fb31379e3 100644
--- a/include/linux/osq_lock.h
+++ b/include/linux/osq_lock.h
@@ -6,11 +6,6 @@
  * An MCS like lock especially tailored for optimistic spinning for sleeping
  * lock implementations (mutex, rwsem, etc).
  */
-struct optimistic_spin_node {
-	struct optimistic_spin_node *next, *prev;
-	int locked; /* 1 if lock acquired */
-	int cpu; /* encoded CPU # + 1 value */
-};
 
 struct optimistic_spin_queue {
 	/*
diff --git a/include/linux/overflow.h b/include/linux/overflow.h
index 0e33b5cbdb9f..736f633b2d5f 100644
--- a/include/linux/overflow.h
+++ b/include/linux/overflow.h
@@ -31,8 +31,10 @@
  * credit to Christian Biere.
  */
 #define __type_half_max(type) ((type)1 << (8*sizeof(type) - 1 - is_signed_type(type)))
-#define type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
-#define type_min(T) ((T)((T)-type_max(T)-(T)1))
+#define __type_max(T) ((T)((__type_half_max(T) - 1) + __type_half_max(T)))
+#define type_max(t)	__type_max(typeof(t))
+#define __type_min(T) ((T)((T)-type_max(T)-(T)1))
+#define type_min(t)	__type_min(typeof(t))
 
 /*
  * Avoids triggering -Wtype-limits compilation warning,
@@ -57,46 +59,123 @@ static inline bool __must_check __must_check_overflow(bool overflow)
  * @b: second addend
  * @d: pointer to store sum
  *
- * Returns 0 on success.
+ * Returns true on wrap-around, false otherwise.
  *
- * *@d holds the results of the attempted addition, but is not considered
- * "safe for use" on a non-zero return value, which indicates that the
- * sum has overflowed or been truncated.
+ * *@d holds the results of the attempted addition, regardless of whether
+ * wrap-around occurred.
  */
 #define check_add_overflow(a, b, d)	\
 	__must_check_overflow(__builtin_add_overflow(a, b, d))
 
 /**
+ * wrapping_add() - Intentionally perform a wrapping addition
+ * @type: type for result of calculation
+ * @a: first addend
+ * @b: second addend
+ *
+ * Return the potentially wrapped-around addition without
+ * tripping any wrap-around sanitizers that may be enabled.
+ */
+#define wrapping_add(type, a, b)				\
+	({							\
+		type __val;					\
+		__builtin_add_overflow(a, b, &__val);		\
+		__val;						\
+	})
+
+/**
+ * wrapping_assign_add() - Intentionally perform a wrapping increment assignment
+ * @var: variable to be incremented
+ * @offset: amount to add
+ *
+ * Increments @var by @offset with wrap-around. Returns the resulting
+ * value of @var. Will not trip any wrap-around sanitizers.
+ *
+ * Returns the new value of @var.
+ */
+#define wrapping_assign_add(var, offset)				\
+	({								\
+		typeof(var) *__ptr = &(var);				\
+		*__ptr = wrapping_add(typeof(var), *__ptr, offset);	\
+	})
+
+/**
  * check_sub_overflow() - Calculate subtraction with overflow checking
  * @a: minuend; value to subtract from
  * @b: subtrahend; value to subtract from @a
  * @d: pointer to store difference
  *
- * Returns 0 on success.
+ * Returns true on wrap-around, false otherwise.
  *
- * *@d holds the results of the attempted subtraction, but is not considered
- * "safe for use" on a non-zero return value, which indicates that the
- * difference has underflowed or been truncated.
+ * *@d holds the results of the attempted subtraction, regardless of whether
+ * wrap-around occurred.
  */
 #define check_sub_overflow(a, b, d)	\
 	__must_check_overflow(__builtin_sub_overflow(a, b, d))
 
 /**
+ * wrapping_sub() - Intentionally perform a wrapping subtraction
+ * @type: type for result of calculation
+ * @a: minuend; value to subtract from
+ * @b: subtrahend; value to subtract from @a
+ *
+ * Return the potentially wrapped-around subtraction without
+ * tripping any wrap-around sanitizers that may be enabled.
+ */
+#define wrapping_sub(type, a, b)				\
+	({							\
+		type __val;					\
+		__builtin_sub_overflow(a, b, &__val);		\
+		__val;						\
+	})
+
+/**
+ * wrapping_assign_sub() - Intentionally perform a wrapping decrement assign
+ * @var: variable to be decremented
+ * @offset: amount to subtract
+ *
+ * Decrements @var by @offset with wrap-around. Returns the resulting
+ * value of @var. Will not trip any wrap-around sanitizers.
+ *
+ * Returns the new value of @var.
+ */
+#define wrapping_assign_sub(var, offset)				\
+	({								\
+		typeof(var) *__ptr = &(var);				\
+		*__ptr = wrapping_sub(typeof(var), *__ptr, offset);	\
+	})
+
+/**
  * check_mul_overflow() - Calculate multiplication with overflow checking
  * @a: first factor
  * @b: second factor
  * @d: pointer to store product
  *
- * Returns 0 on success.
+ * Returns true on wrap-around, false otherwise.
  *
- * *@d holds the results of the attempted multiplication, but is not
- * considered "safe for use" on a non-zero return value, which indicates
- * that the product has overflowed or been truncated.
+ * *@d holds the results of the attempted multiplication, regardless of whether
+ * wrap-around occurred.
  */
 #define check_mul_overflow(a, b, d)	\
 	__must_check_overflow(__builtin_mul_overflow(a, b, d))
 
 /**
+ * wrapping_mul() - Intentionally perform a wrapping multiplication
+ * @type: type for result of calculation
+ * @a: first factor
+ * @b: second factor
+ *
+ * Return the potentially wrapped-around multiplication without
+ * tripping any wrap-around sanitizers that may be enabled.
+ */
+#define wrapping_mul(type, a, b)				\
+	({							\
+		type __val;					\
+		__builtin_mul_overflow(a, b, &__val);		\
+		__val;						\
+	})
+
+/**
  * check_shl_overflow() - Calculate a left-shifted value and check overflow
  * @a: Value to be shifted
  * @s: How many bits left to shift
@@ -120,7 +199,7 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 	typeof(a) _a = a;						\
 	typeof(s) _s = s;						\
 	typeof(d) _d = d;						\
-	u64 _a_full = _a;						\
+	unsigned long long _a_full = _a;				\
 	unsigned int _to_shift =					\
 		is_non_negative(_s) && _s < 8 * sizeof(*d) ? _s : 0;	\
 	*_d = (_a_full << _to_shift);					\
@@ -130,10 +209,10 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 
 #define __overflows_type_constexpr(x, T) (			\
 	is_unsigned_type(typeof(x)) ?				\
-		(x) > type_max(typeof(T)) :			\
+		(x) > type_max(T) :				\
 	is_unsigned_type(typeof(T)) ?				\
-		(x) < 0 || (x) > type_max(typeof(T)) :		\
-	(x) < type_min(typeof(T)) || (x) > type_max(typeof(T)))
+		(x) < 0 || (x) > type_max(T) :			\
+	(x) < type_min(T) || (x) > type_max(T))
 
 #define __overflows_type(x, T)		({	\
 	typeof(T) v = 0;			\
@@ -160,6 +239,76 @@ static inline bool __must_check __must_check_overflow(bool overflow)
 			      __overflows_type(n, T))
 
 /**
+ * range_overflows() - Check if a range is out of bounds
+ * @start: Start of the range.
+ * @size:  Size of the range.
+ * @max:   Exclusive upper boundary.
+ *
+ * A strict check to determine if the range [@start, @start + @size) is
+ * invalid with respect to the allowable range [0, @max). Any range
+ * starting at or beyond @max is considered an overflow, even if @size is 0.
+ *
+ * Returns: true if the range is out of bounds.
+ */
+#define range_overflows(start, size, max) ({ \
+	typeof(start) start__ = (start); \
+	typeof(size) size__ = (size); \
+	typeof(max) max__ = (max); \
+	(void)(&start__ == &size__); \
+	(void)(&start__ == &max__); \
+	start__ >= max__ || size__ > max__ - start__; \
+})
+
+/**
+ * range_overflows_t() - Check if a range is out of bounds
+ * @type:  Data type to use.
+ * @start: Start of the range.
+ * @size:  Size of the range.
+ * @max:   Exclusive upper boundary.
+ *
+ * Same as range_overflows() but forcing the parameters to @type.
+ *
+ * Returns: true if the range is out of bounds.
+ */
+#define range_overflows_t(type, start, size, max) \
+	range_overflows((type)(start), (type)(size), (type)(max))
+
+/**
+ * range_end_overflows() - Check if a range's endpoint is out of bounds
+ * @start: Start of the range.
+ * @size:  Size of the range.
+ * @max:   Exclusive upper boundary.
+ *
+ * Checks only if the endpoint of a range (@start + @size) exceeds @max.
+ * Unlike range_overflows(), a zero-sized range at the boundary (@start == @max)
+ * is not considered an overflow. Useful for iterator-style checks.
+ *
+ * Returns: true if the endpoint exceeds the boundary.
+ */
+#define range_end_overflows(start, size, max) ({ \
+	typeof(start) start__ = (start); \
+	typeof(size) size__ = (size); \
+	typeof(max) max__ = (max); \
+	(void)(&start__ == &size__); \
+	(void)(&start__ == &max__); \
+	start__ > max__ || size__ > max__ - start__; \
+})
+
+/**
+ * range_end_overflows_t() - Check if a range's endpoint is out of bounds
+ * @type:  Data type to use.
+ * @start: Start of the range.
+ * @size:  Size of the range.
+ * @max:   Exclusive upper boundary.
+ *
+ * Same as range_end_overflows() but forcing the parameters to @type.
+ *
+ * Returns: true if the endpoint exceeds the boundary.
+ */
+#define range_end_overflows_t(type, start, size, max) \
+	range_end_overflows((type)(start), (type)(size), (type)(max))
+
+/**
  * castable_to_type - like __same_type(), but also allows for casted literals
  *
  * @n: variable or constant value
@@ -283,7 +432,7 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
  * @member: Name of the array member.
  * @count: Number of elements in the array.
  *
- * Calculates size of memory needed for structure @p followed by an
+ * Calculates size of memory needed for structure of @p followed by an
  * array of @count number of @member elements.
  *
  * Return: number of bytes needed or SIZE_MAX on overflow.
@@ -293,4 +442,114 @@ static inline size_t __must_check size_sub(size_t minuend, size_t subtrahend)
 		sizeof(*(p)) + flex_array_size(p, member, count),	\
 		size_add(sizeof(*(p)), flex_array_size(p, member, count)))
 
+/**
+ * struct_size_t() - Calculate size of structure with trailing flexible array
+ * @type: structure type name.
+ * @member: Name of the array member.
+ * @count: Number of elements in the array.
+ *
+ * Calculates size of memory needed for structure @type followed by an
+ * array of @count number of @member elements. Prefer using struct_size()
+ * when possible instead, to keep calculations associated with a specific
+ * instance variable of type @type.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define struct_size_t(type, member, count)					\
+	struct_size((type *)NULL, member, count)
+
+/**
+ * struct_offset() - Calculate the offset of a member within a struct
+ * @p: Pointer to the struct
+ * @member: Name of the member to get the offset of
+ *
+ * Calculates the offset of a particular @member of the structure pointed
+ * to by @p.
+ *
+ * Return: number of bytes to the location of @member.
+ */
+#define struct_offset(p, member) (offsetof(typeof(*(p)), member))
+
+/**
+ * __DEFINE_FLEX() - helper macro for DEFINE_FLEX() family.
+ * Enables caller macro to pass arbitrary trailing expressions
+ *
+ * @type: structure type name, including "struct" keyword.
+ * @name: Name for a variable to define.
+ * @member: Name of the array member.
+ * @count: Number of elements in the array; must be compile-time const.
+ * @trailer: Trailing expressions for attributes and/or initializers.
+ */
+#define __DEFINE_FLEX(type, name, member, count, trailer...)			\
+	_Static_assert(__builtin_constant_p(count),				\
+		       "onstack flex array members require compile-time const count"); \
+	union {									\
+		u8 bytes[struct_size_t(type, member, count)];			\
+		type obj;							\
+	} name##_u trailer;							\
+	type *name = (type *)&name##_u
+
+/**
+ * _DEFINE_FLEX() - helper macro for DEFINE_FLEX() family.
+ * Enables caller macro to pass (different) initializer.
+ *
+ * @type: structure type name, including "struct" keyword.
+ * @name: Name for a variable to define.
+ * @member: Name of the array member.
+ * @count: Number of elements in the array; must be compile-time const.
+ * @initializer: Initializer expression (e.g., pass `= { }` at minimum).
+ */
+#define _DEFINE_FLEX(type, name, member, count, initializer...)			\
+	__DEFINE_FLEX(type, name, member, count, = { .obj initializer })
+
+/**
+ * DEFINE_RAW_FLEX() - Define an on-stack instance of structure with a trailing
+ * flexible array member, when it does not have a __counted_by annotation.
+ *
+ * @type: structure type name, including "struct" keyword.
+ * @name: Name for a variable to define.
+ * @member: Name of the array member.
+ * @count: Number of elements in the array; must be compile-time const.
+ *
+ * Define a zeroed, on-stack, instance of @type structure with a trailing
+ * flexible array member.
+ * Use __struct_size(@name) to get compile-time size of it afterwards.
+ * Use __member_size(@name->member) to get compile-time size of @name members.
+ * Use STACK_FLEX_ARRAY_SIZE(@name, @member) to get compile-time number of
+ * elements in array @member.
+ */
+#define DEFINE_RAW_FLEX(type, name, member, count)	\
+	__DEFINE_FLEX(type, name, member, count, = { })
+
+/**
+ * DEFINE_FLEX() - Define an on-stack instance of structure with a trailing
+ * flexible array member.
+ *
+ * @TYPE: structure type name, including "struct" keyword.
+ * @NAME: Name for a variable to define.
+ * @MEMBER: Name of the array member.
+ * @COUNTER: Name of the __counted_by member.
+ * @COUNT: Number of elements in the array; must be compile-time const.
+ *
+ * Define a zeroed, on-stack, instance of @TYPE structure with a trailing
+ * flexible array member.
+ * Use __struct_size(@NAME) to get compile-time size of it afterwards.
+ * Use __member_size(@NAME->member) to get compile-time size of @NAME members.
+ * Use STACK_FLEX_ARRAY_SIZE(@name, @member) to get compile-time number of
+ * elements in array @member.
+ */
+#define DEFINE_FLEX(TYPE, NAME, MEMBER, COUNTER, COUNT)	\
+	_DEFINE_FLEX(TYPE, NAME, MEMBER, COUNT, = { .COUNTER = COUNT, })
+
+/**
+ * STACK_FLEX_ARRAY_SIZE() - helper macro for DEFINE_FLEX() family.
+ * Returns the number of elements in @array.
+ *
+ * @name: Name for a variable defined in DEFINE_RAW_FLEX()/DEFINE_FLEX().
+ * @array: Name of the array member.
+ */
+#define STACK_FLEX_ARRAY_SIZE(name, array)						\
+	(__member_size((name)->array) / sizeof(*(name)->array) +			\
+						__must_be_array((name)->array))
+
 #endif /* __LINUX_OVERFLOW_H */
diff --git a/include/linux/packing.h b/include/linux/packing.h
index 8d6571feb95d..20ae4d452c7b 100644
--- a/include/linux/packing.h
+++ b/include/linux/packing.h
@@ -5,8 +5,89 @@
 #ifndef _LINUX_PACKING_H
 #define _LINUX_PACKING_H
 
-#include <linux/types.h>
+#include <linux/array_size.h>
 #include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/minmax.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
+
+#define GEN_PACKED_FIELD_STRUCT(__type) \
+	struct packed_field_ ## __type { \
+		__type startbit; \
+		__type endbit; \
+		__type offset; \
+		__type size; \
+	}
+
+/* struct packed_field_u8. Use with bit offsets < 256, buffers < 32B and
+ * unpacked structures < 256B.
+ */
+GEN_PACKED_FIELD_STRUCT(u8);
+
+/* struct packed_field_u16. Use with bit offsets < 65536, buffers < 8KB and
+ * unpacked structures < 64KB.
+ */
+GEN_PACKED_FIELD_STRUCT(u16);
+
+#define PACKED_FIELD(start, end, struct_name, struct_field) \
+{ \
+	(start), \
+	(end), \
+	offsetof(struct_name, struct_field), \
+	sizeof_field(struct_name, struct_field), \
+}
+
+#define CHECK_PACKED_FIELD_OVERLAP(fields, index1, index2) ({ \
+	typeof(&(fields)[0]) __f = (fields); \
+	typeof(__f[0]) _f1 = __f[index1]; typeof(__f[0]) _f2 = __f[index2]; \
+	const bool _ascending = __f[0].startbit < __f[1].startbit; \
+	BUILD_BUG_ON_MSG(_ascending && _f1.startbit >= _f2.startbit, \
+			 __stringify(fields) " field " __stringify(index2) \
+			 " breaks ascending order"); \
+	BUILD_BUG_ON_MSG(!_ascending && _f1.startbit <= _f2.startbit, \
+			 __stringify(fields) " field " __stringify(index2) \
+			 " breaks descending order"); \
+	BUILD_BUG_ON_MSG(max(_f1.endbit, _f2.endbit) <= \
+			 min(_f1.startbit, _f2.startbit), \
+			 __stringify(fields) " field " __stringify(index2) \
+			 " overlaps with previous field"); \
+})
+
+#define CHECK_PACKED_FIELD(fields, index) ({ \
+	typeof(&(fields)[0]) _f = (fields); \
+	typeof(_f[0]) __f = _f[index]; \
+	BUILD_BUG_ON_MSG(__f.startbit < __f.endbit, \
+			 __stringify(fields) " field " __stringify(index) \
+			 " start bit must not be smaller than end bit"); \
+	BUILD_BUG_ON_MSG(__f.size != 1 && __f.size != 2 && \
+			 __f.size != 4 && __f.size != 8, \
+			 __stringify(fields) " field " __stringify(index) \
+			" has unsupported unpacked storage size"); \
+	BUILD_BUG_ON_MSG(__f.startbit - __f.endbit >= BITS_PER_BYTE * __f.size, \
+			 __stringify(fields) " field " __stringify(index) \
+			 " exceeds unpacked storage size"); \
+	__builtin_choose_expr(index != 0, \
+			      CHECK_PACKED_FIELD_OVERLAP(fields, index - 1, index), \
+			      1); \
+})
+
+/* Note that the packed fields may be either in ascending or descending order.
+ * Thus, we must check that both the first and last field wit within the
+ * packed buffer size.
+ */
+#define CHECK_PACKED_FIELDS_SIZE(fields, pbuflen) ({ \
+	typeof(&(fields)[0]) _f = (fields); \
+	typeof(pbuflen) _len = (pbuflen); \
+	const size_t num_fields = ARRAY_SIZE(fields); \
+	BUILD_BUG_ON_MSG(!__builtin_constant_p(_len), \
+			 __stringify(fields) " pbuflen " __stringify(pbuflen) \
+			 " must be a compile time constant"); \
+	BUILD_BUG_ON_MSG(_f[0].startbit >= BITS_PER_BYTE * _len, \
+			 __stringify(fields) " first field exceeds packed buffer size"); \
+	BUILD_BUG_ON_MSG(_f[num_fields - 1].startbit >= BITS_PER_BYTE * _len, \
+			 __stringify(fields) " last field exceeds packed buffer size"); \
+})
 
 #define QUIRK_MSB_ON_THE_RIGHT	BIT(0)
 #define QUIRK_LITTLE_ENDIAN	BIT(1)
@@ -17,33 +98,361 @@ enum packing_op {
 	UNPACK,
 };
 
-/**
- * packing - Convert numbers (currently u64) between a packed and an unpacked
- *	     format. Unpacked means laid out in memory in the CPU's native
- *	     understanding of integers, while packed means anything else that
- *	     requires translation.
- *
- * @pbuf: Pointer to a buffer holding the packed value.
- * @uval: Pointer to an u64 holding the unpacked value.
- * @startbit: The index (in logical notation, compensated for quirks) where
- *	      the packed value starts within pbuf. Must be larger than, or
- *	      equal to, endbit.
- * @endbit: The index (in logical notation, compensated for quirks) where
- *	    the packed value ends within pbuf. Must be smaller than, or equal
- *	    to, startbit.
- * @op: If PACK, then uval will be treated as const pointer and copied (packed)
- *	into pbuf, between startbit and endbit.
- *	If UNPACK, then pbuf will be treated as const pointer and the logical
- *	value between startbit and endbit will be copied (unpacked) to uval.
- * @quirks: A bit mask of QUIRK_LITTLE_ENDIAN, QUIRK_LSW32_IS_FIRST and
- *	    QUIRK_MSB_ON_THE_RIGHT.
- *
- * Return: 0 on success, EINVAL or ERANGE if called incorrectly. Assuming
- *	   correct usage, return code may be discarded.
- *	   If op is PACK, pbuf is modified.
- *	   If op is UNPACK, uval is modified.
- */
 int packing(void *pbuf, u64 *uval, int startbit, int endbit, size_t pbuflen,
 	    enum packing_op op, u8 quirks);
 
+int pack(void *pbuf, u64 uval, size_t startbit, size_t endbit, size_t pbuflen,
+	 u8 quirks);
+
+int unpack(const void *pbuf, u64 *uval, size_t startbit, size_t endbit,
+	   size_t pbuflen, u8 quirks);
+
+void pack_fields_u8(void *pbuf, size_t pbuflen, const void *ustruct,
+		    const struct packed_field_u8 *fields, size_t num_fields,
+		    u8 quirks);
+
+void pack_fields_u16(void *pbuf, size_t pbuflen, const void *ustruct,
+		     const struct packed_field_u16 *fields, size_t num_fields,
+		     u8 quirks);
+
+void unpack_fields_u8(const void *pbuf, size_t pbuflen, void *ustruct,
+		      const struct packed_field_u8 *fields, size_t num_fields,
+		      u8 quirks);
+
+void unpack_fields_u16(const void *pbuf, size_t pbuflen, void *ustruct,
+		       const struct packed_field_u16 *fields, size_t num_fields,
+		       u8 quirks);
+
+/* Do not hand-edit the following packed field check macros!
+ *
+ * They are generated using scripts/gen_packed_field_checks.c, which may be
+ * built via "make scripts_gen_packed_field_checks". If larger macro sizes are
+ * needed in the future, please use this program to re-generate the macros and
+ * insert them here.
+ */
+
+#define CHECK_PACKED_FIELDS_1(fields) \
+	CHECK_PACKED_FIELD(fields, 0)
+
+#define CHECK_PACKED_FIELDS_2(fields) do { \
+	CHECK_PACKED_FIELDS_1(fields); \
+	CHECK_PACKED_FIELD(fields, 1); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_3(fields) do { \
+	CHECK_PACKED_FIELDS_2(fields); \
+	CHECK_PACKED_FIELD(fields, 2); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_4(fields) do { \
+	CHECK_PACKED_FIELDS_3(fields); \
+	CHECK_PACKED_FIELD(fields, 3); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_5(fields) do { \
+	CHECK_PACKED_FIELDS_4(fields); \
+	CHECK_PACKED_FIELD(fields, 4); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_6(fields) do { \
+	CHECK_PACKED_FIELDS_5(fields); \
+	CHECK_PACKED_FIELD(fields, 5); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_7(fields) do { \
+	CHECK_PACKED_FIELDS_6(fields); \
+	CHECK_PACKED_FIELD(fields, 6); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_8(fields) do { \
+	CHECK_PACKED_FIELDS_7(fields); \
+	CHECK_PACKED_FIELD(fields, 7); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_9(fields) do { \
+	CHECK_PACKED_FIELDS_8(fields); \
+	CHECK_PACKED_FIELD(fields, 8); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_10(fields) do { \
+	CHECK_PACKED_FIELDS_9(fields); \
+	CHECK_PACKED_FIELD(fields, 9); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_11(fields) do { \
+	CHECK_PACKED_FIELDS_10(fields); \
+	CHECK_PACKED_FIELD(fields, 10); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_12(fields) do { \
+	CHECK_PACKED_FIELDS_11(fields); \
+	CHECK_PACKED_FIELD(fields, 11); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_13(fields) do { \
+	CHECK_PACKED_FIELDS_12(fields); \
+	CHECK_PACKED_FIELD(fields, 12); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_14(fields) do { \
+	CHECK_PACKED_FIELDS_13(fields); \
+	CHECK_PACKED_FIELD(fields, 13); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_15(fields) do { \
+	CHECK_PACKED_FIELDS_14(fields); \
+	CHECK_PACKED_FIELD(fields, 14); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_16(fields) do { \
+	CHECK_PACKED_FIELDS_15(fields); \
+	CHECK_PACKED_FIELD(fields, 15); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_17(fields) do { \
+	CHECK_PACKED_FIELDS_16(fields); \
+	CHECK_PACKED_FIELD(fields, 16); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_18(fields) do { \
+	CHECK_PACKED_FIELDS_17(fields); \
+	CHECK_PACKED_FIELD(fields, 17); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_19(fields) do { \
+	CHECK_PACKED_FIELDS_18(fields); \
+	CHECK_PACKED_FIELD(fields, 18); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_20(fields) do { \
+	CHECK_PACKED_FIELDS_19(fields); \
+	CHECK_PACKED_FIELD(fields, 19); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_21(fields) do { \
+	CHECK_PACKED_FIELDS_20(fields); \
+	CHECK_PACKED_FIELD(fields, 20); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_22(fields) do { \
+	CHECK_PACKED_FIELDS_21(fields); \
+	CHECK_PACKED_FIELD(fields, 21); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_23(fields) do { \
+	CHECK_PACKED_FIELDS_22(fields); \
+	CHECK_PACKED_FIELD(fields, 22); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_24(fields) do { \
+	CHECK_PACKED_FIELDS_23(fields); \
+	CHECK_PACKED_FIELD(fields, 23); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_25(fields) do { \
+	CHECK_PACKED_FIELDS_24(fields); \
+	CHECK_PACKED_FIELD(fields, 24); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_26(fields) do { \
+	CHECK_PACKED_FIELDS_25(fields); \
+	CHECK_PACKED_FIELD(fields, 25); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_27(fields) do { \
+	CHECK_PACKED_FIELDS_26(fields); \
+	CHECK_PACKED_FIELD(fields, 26); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_28(fields) do { \
+	CHECK_PACKED_FIELDS_27(fields); \
+	CHECK_PACKED_FIELD(fields, 27); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_29(fields) do { \
+	CHECK_PACKED_FIELDS_28(fields); \
+	CHECK_PACKED_FIELD(fields, 28); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_30(fields) do { \
+	CHECK_PACKED_FIELDS_29(fields); \
+	CHECK_PACKED_FIELD(fields, 29); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_31(fields) do { \
+	CHECK_PACKED_FIELDS_30(fields); \
+	CHECK_PACKED_FIELD(fields, 30); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_32(fields) do { \
+	CHECK_PACKED_FIELDS_31(fields); \
+	CHECK_PACKED_FIELD(fields, 31); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_33(fields) do { \
+	CHECK_PACKED_FIELDS_32(fields); \
+	CHECK_PACKED_FIELD(fields, 32); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_34(fields) do { \
+	CHECK_PACKED_FIELDS_33(fields); \
+	CHECK_PACKED_FIELD(fields, 33); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_35(fields) do { \
+	CHECK_PACKED_FIELDS_34(fields); \
+	CHECK_PACKED_FIELD(fields, 34); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_36(fields) do { \
+	CHECK_PACKED_FIELDS_35(fields); \
+	CHECK_PACKED_FIELD(fields, 35); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_37(fields) do { \
+	CHECK_PACKED_FIELDS_36(fields); \
+	CHECK_PACKED_FIELD(fields, 36); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_38(fields) do { \
+	CHECK_PACKED_FIELDS_37(fields); \
+	CHECK_PACKED_FIELD(fields, 37); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_39(fields) do { \
+	CHECK_PACKED_FIELDS_38(fields); \
+	CHECK_PACKED_FIELD(fields, 38); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_40(fields) do { \
+	CHECK_PACKED_FIELDS_39(fields); \
+	CHECK_PACKED_FIELD(fields, 39); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_41(fields) do { \
+	CHECK_PACKED_FIELDS_40(fields); \
+	CHECK_PACKED_FIELD(fields, 40); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_42(fields) do { \
+	CHECK_PACKED_FIELDS_41(fields); \
+	CHECK_PACKED_FIELD(fields, 41); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_43(fields) do { \
+	CHECK_PACKED_FIELDS_42(fields); \
+	CHECK_PACKED_FIELD(fields, 42); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_44(fields) do { \
+	CHECK_PACKED_FIELDS_43(fields); \
+	CHECK_PACKED_FIELD(fields, 43); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_45(fields) do { \
+	CHECK_PACKED_FIELDS_44(fields); \
+	CHECK_PACKED_FIELD(fields, 44); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_46(fields) do { \
+	CHECK_PACKED_FIELDS_45(fields); \
+	CHECK_PACKED_FIELD(fields, 45); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_47(fields) do { \
+	CHECK_PACKED_FIELDS_46(fields); \
+	CHECK_PACKED_FIELD(fields, 46); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_48(fields) do { \
+	CHECK_PACKED_FIELDS_47(fields); \
+	CHECK_PACKED_FIELD(fields, 47); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_49(fields) do { \
+	CHECK_PACKED_FIELDS_48(fields); \
+	CHECK_PACKED_FIELD(fields, 48); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS_50(fields) do { \
+	CHECK_PACKED_FIELDS_49(fields); \
+	CHECK_PACKED_FIELD(fields, 49); \
+} while (0)
+
+#define CHECK_PACKED_FIELDS(fields) \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 1, ({ CHECK_PACKED_FIELDS_1(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 2, ({ CHECK_PACKED_FIELDS_2(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 3, ({ CHECK_PACKED_FIELDS_3(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 4, ({ CHECK_PACKED_FIELDS_4(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 5, ({ CHECK_PACKED_FIELDS_5(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 6, ({ CHECK_PACKED_FIELDS_6(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 7, ({ CHECK_PACKED_FIELDS_7(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 8, ({ CHECK_PACKED_FIELDS_8(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 9, ({ CHECK_PACKED_FIELDS_9(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 10, ({ CHECK_PACKED_FIELDS_10(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 11, ({ CHECK_PACKED_FIELDS_11(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 12, ({ CHECK_PACKED_FIELDS_12(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 13, ({ CHECK_PACKED_FIELDS_13(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 14, ({ CHECK_PACKED_FIELDS_14(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 15, ({ CHECK_PACKED_FIELDS_15(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 16, ({ CHECK_PACKED_FIELDS_16(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 17, ({ CHECK_PACKED_FIELDS_17(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 18, ({ CHECK_PACKED_FIELDS_18(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 19, ({ CHECK_PACKED_FIELDS_19(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 20, ({ CHECK_PACKED_FIELDS_20(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 21, ({ CHECK_PACKED_FIELDS_21(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 22, ({ CHECK_PACKED_FIELDS_22(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 23, ({ CHECK_PACKED_FIELDS_23(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 24, ({ CHECK_PACKED_FIELDS_24(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 25, ({ CHECK_PACKED_FIELDS_25(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 26, ({ CHECK_PACKED_FIELDS_26(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 27, ({ CHECK_PACKED_FIELDS_27(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 28, ({ CHECK_PACKED_FIELDS_28(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 29, ({ CHECK_PACKED_FIELDS_29(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 30, ({ CHECK_PACKED_FIELDS_30(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 31, ({ CHECK_PACKED_FIELDS_31(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 32, ({ CHECK_PACKED_FIELDS_32(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 33, ({ CHECK_PACKED_FIELDS_33(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 34, ({ CHECK_PACKED_FIELDS_34(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 35, ({ CHECK_PACKED_FIELDS_35(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 36, ({ CHECK_PACKED_FIELDS_36(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 37, ({ CHECK_PACKED_FIELDS_37(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 38, ({ CHECK_PACKED_FIELDS_38(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 39, ({ CHECK_PACKED_FIELDS_39(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 40, ({ CHECK_PACKED_FIELDS_40(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 41, ({ CHECK_PACKED_FIELDS_41(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 42, ({ CHECK_PACKED_FIELDS_42(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 43, ({ CHECK_PACKED_FIELDS_43(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 44, ({ CHECK_PACKED_FIELDS_44(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 45, ({ CHECK_PACKED_FIELDS_45(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 46, ({ CHECK_PACKED_FIELDS_46(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 47, ({ CHECK_PACKED_FIELDS_47(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 48, ({ CHECK_PACKED_FIELDS_48(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 49, ({ CHECK_PACKED_FIELDS_49(fields); }), \
+	__builtin_choose_expr(ARRAY_SIZE(fields) == 50, ({ CHECK_PACKED_FIELDS_50(fields); }), \
+	({ BUILD_BUG_ON_MSG(1, "CHECK_PACKED_FIELDS() must be regenerated to support array sizes larger than 50."); }) \
+))))))))))))))))))))))))))))))))))))))))))))))))))
+
+/* End of generated content */
+
+#define pack_fields(pbuf, pbuflen, ustruct, fields, quirks) \
+	({ \
+		CHECK_PACKED_FIELDS(fields); \
+		CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \
+		_Generic((fields), \
+			 const struct packed_field_u8 * : pack_fields_u8, \
+			 const struct packed_field_u16 * : pack_fields_u16 \
+			)((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \
+	})
+
+#define unpack_fields(pbuf, pbuflen, ustruct, fields, quirks) \
+	({ \
+		CHECK_PACKED_FIELDS(fields); \
+		CHECK_PACKED_FIELDS_SIZE((fields), (pbuflen)); \
+		_Generic((fields), \
+			 const struct packed_field_u8 * : unpack_fields_u8, \
+			 const struct packed_field_u16 * : unpack_fields_u16 \
+			)((pbuf), (pbuflen), (ustruct), (fields), ARRAY_SIZE(fields), (quirks)); \
+	})
+
 #endif
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 495b16b6b4d7..765f2778e264 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -90,8 +90,6 @@ struct padata_cpumask {
  * @processed: Number of already processed objects.
  * @cpu: Next CPU to be processed.
  * @cpumask: The cpumasks in use for parallel and serial workers.
- * @reorder_work: work struct for reordering.
- * @lock: Reorder lock.
  */
 struct parallel_data {
 	struct padata_shell		*ps;
@@ -102,8 +100,6 @@ struct parallel_data {
 	unsigned int			processed;
 	int				cpu;
 	struct padata_cpumask		cpumask;
-	struct work_struct		reorder_work;
-	spinlock_t                      ____cacheline_aligned lock;
 };
 
 /**
@@ -137,6 +133,7 @@ struct padata_shell {
  *             appropriate for one worker thread to do at once.
  * @max_threads: Max threads to use for the job, actual number may be less
  *               depending on task size and minimum chunk size.
+ * @numa_aware: Distribute jobs to different nodes with CPU in a round robin fashion.
  */
 struct padata_mt_job {
 	void (*thread_fn)(unsigned long start, unsigned long end, void *arg);
@@ -146,6 +143,7 @@ struct padata_mt_job {
 	unsigned long		align;
 	unsigned long		min_chunk;
 	int			max_threads;
+	bool			numa_aware;
 };
 
 /**
@@ -178,10 +176,6 @@ struct padata_instance {
 
 #ifdef CONFIG_PADATA
 extern void __init padata_init(void);
-#else
-static inline void __init padata_init(void) {}
-#endif
-
 extern struct padata_instance *padata_alloc(const char *name);
 extern void padata_free(struct padata_instance *pinst);
 extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst);
@@ -192,4 +186,12 @@ extern void padata_do_serial(struct padata_priv *padata);
 extern void __init padata_do_multithreaded(struct padata_mt_job *job);
 extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
 			      cpumask_var_t cpumask);
+#else
+static inline void __init padata_init(void) {}
+static inline void __init padata_do_multithreaded(struct padata_mt_job *job)
+{
+	job->thread_fn(job->start, job->start + job->size, job->fn_arg);
+}
+#endif
+
 #endif
diff --git a/include/linux/page-flags-layout.h b/include/linux/page-flags-layout.h
index 7d79818dc065..760006b1c480 100644
--- a/include/linux/page-flags-layout.h
+++ b/include/linux/page-flags-layout.h
@@ -72,8 +72,10 @@
 #define NODE_NOT_IN_PAGE_FLAGS	1
 #endif
 
-#if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS)
+#if defined(CONFIG_KASAN_SW_TAGS)
 #define KASAN_TAG_WIDTH 8
+#elif defined(CONFIG_KASAN_HW_TAGS)
+#define KASAN_TAG_WIDTH 4
 #else
 #define KASAN_TAG_WIDTH 0
 #endif
@@ -111,5 +113,12 @@
 			    ZONES_WIDTH - LRU_GEN_WIDTH - SECTIONS_WIDTH - \
 			    NODES_WIDTH - KASAN_TAG_WIDTH - LAST_CPUPID_WIDTH)
 
+#define NR_NON_PAGEFLAG_BITS	(SECTIONS_WIDTH + NODES_WIDTH + ZONES_WIDTH + \
+				LAST_CPUPID_SHIFT + KASAN_TAG_WIDTH + \
+				LRU_GEN_WIDTH + LRU_REFS_WIDTH)
+
+#define NR_UNUSED_PAGEFLAG_BITS	(BITS_PER_LONG - \
+				(NR_NON_PAGEFLAG_BITS + NR_PAGEFLAGS))
+
 #endif
 #endif /* _LINUX_PAGE_FLAGS_LAYOUT */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 1c68d67b832f..f7a0e4af0c73 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -30,16 +30,11 @@
  * - Pages falling into physical memory gaps - not IORESOURCE_SYSRAM. Trying
  *   to read/write these pages might end badly. Don't touch!
  * - The zero page(s)
- * - Pages not added to the page allocator when onlining a section because
- *   they were excluded via the online_page_callback() or because they are
- *   PG_hwpoison.
  * - Pages allocated in the context of kexec/kdump (loaded kernel image,
  *   control pages, vmcoreinfo)
  * - MMIO/DMA pages. Some architectures don't allow to ioremap pages that are
  *   not marked PG_reserved (as they might be in use by somebody else who does
  *   not respect the caching strategy).
- * - Pages part of an offline section (struct pages of offline sections should
- *   not be trusted as they will be initialized when first onlined).
  * - MCA pages on ia64
  * - Pages holding CPU notes for POWER Firmware Assisted Dump
  * - Device memory (e.g. PMEM, DAX, HMM)
@@ -71,8 +66,6 @@
  * PG_referenced, PG_reclaim are used for page reclaim for anonymous and
  * file-backed pagecache (see mm/vmscan.c).
  *
- * PG_error is set to indicate that an I/O error occurred on this page.
- *
  * PG_arch_1 is an architecture specific page state bit.  The generic code
  * guarantees that this bit is cleared for a page when it first is entered into
  * the page cache.
@@ -99,32 +92,28 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
+	PG_writeback,		/* Page is under writeback */
 	PG_referenced,
 	PG_uptodate,
 	PG_dirty,
 	PG_lru,
+	PG_head,		/* Must be in bit 6 */
+	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
 	PG_active,
 	PG_workingset,
-	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
-	PG_error,
-	PG_slab,
-	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
+	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use */
+	PG_owner_2,		/* Owner use. If pagecache, fs may use */
 	PG_arch_1,
 	PG_reserved,
 	PG_private,		/* If pagecache, has fs-private data */
 	PG_private_2,		/* If pagecache, has fs aux data */
-	PG_writeback,		/* Page is under writeback */
-	PG_head,		/* A head page */
-	PG_mappedtodisk,	/* Has blocks allocated on-disk */
 	PG_reclaim,		/* To be reclaimed asap */
 	PG_swapbacked,		/* Page is backed by RAM/swap */
 	PG_unevictable,		/* Page is "unevictable"  */
+	PG_dropbehind,		/* drop pages on IO completion */
 #ifdef CONFIG_MMU
 	PG_mlocked,		/* Page is vma mlocked */
 #endif
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
-	PG_uncached,		/* Page has been mapped as uncached */
-#endif
 #ifdef CONFIG_MEMORY_FAILURE
 	PG_hwpoison,		/* hardware poisoned page. Don't touch */
 #endif
@@ -132,14 +121,21 @@ enum pageflags {
 	PG_young,
 	PG_idle,
 #endif
-#ifdef CONFIG_ARCH_USES_PG_ARCH_X
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
 	PG_arch_2,
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
 	PG_arch_3,
 #endif
 	__NR_PAGEFLAGS,
 
 	PG_readahead = PG_reclaim,
 
+	/* Anonymous memory (and shmem) */
+	PG_swapcache = PG_owner_priv_1, /* Swap page: swp_entry_t in private */
+	/* Some filesystems */
+	PG_checked = PG_owner_priv_1,
+
 	/*
 	 * Depending on the way an anonymous folio can be mapped into a page
 	 * table (e.g., single PMD/PUD/CONT of the head page vs. PTE-mapped
@@ -147,13 +143,13 @@ enum pageflags {
 	 * tail pages of an anonymous folio. For now, we only expect it to be
 	 * set on tail pages for PTE-mapped THP.
 	 */
-	PG_anon_exclusive = PG_mappedtodisk,
+	PG_anon_exclusive = PG_owner_2,
 
-	/* Filesystems */
-	PG_checked = PG_owner_priv_1,
-
-	/* SwapBacked */
-	PG_swapcache = PG_owner_priv_1,	/* Swap page: swp_entry_t in private */
+	/*
+	 * Set if all buffer heads in the folio are mapped.
+	 * Filesystems which do not use BHs can use it for their own purpose.
+	 */
+	PG_mappedtodisk = PG_owner_2,
 
 	/* Two page bits are conscripted by FS-Cache to maintain local caching
 	 * state.  These bits are set on pages belonging to the netfs's inodes
@@ -171,18 +167,13 @@ enum pageflags {
 	/* Remapped by swiotlb-xen. */
 	PG_xen_remapped = PG_owner_priv_1,
 
-#ifdef CONFIG_MEMORY_FAILURE
-	/*
-	 * Compound pages. Stored in first tail page's flags.
-	 * Indicates that at least one subpage is hwpoisoned in the
-	 * THP.
-	 */
-	PG_has_hwpoisoned = PG_error,
+#ifdef CONFIG_MIGRATION
+	/* movable_ops page that is isolated for migration */
+	PG_movable_ops_isolated = PG_reclaim,
+	/* this is a movable_ops page (for selected typed pages only) */
+	PG_movable_ops = PG_uptodate,
 #endif
 
-	/* non-lru isolated movable page */
-	PG_isolated = PG_reclaim,
-
 	/* Only valid for buddy pages. Used to track pages that are reported */
 	PG_reported = PG_uptodate,
 
@@ -190,6 +181,17 @@ enum pageflags {
 	/* For self-hosted memmap pages */
 	PG_vmemmap_self_hosted = PG_owner_priv_1,
 #endif
+
+	/*
+	 * Flags only valid for compound pages.  Stored in first tail page's
+	 * flags word.  Cannot use the first 8 flags or any flag marked as
+	 * PF_ANY.
+	 */
+
+	/* At least one page in this folio has the hwpoison flag set */
+	PG_has_hwpoisoned = PG_active,
+	PG_large_rmappable = PG_workingset, /* anon or file-backed */
+	PG_partially_mapped = PG_reclaim, /* was identified to be partially mapped */
 };
 
 #define PAGEFLAGS_MASK		((1UL << NR_PAGEFLAGS) - 1)
@@ -215,7 +217,7 @@ static __always_inline const struct page *page_fixed_fake_head(const struct page
 	 * cold cacheline in some cases.
 	 */
 	if (IS_ALIGNED((unsigned long)page, PAGE_SIZE) &&
-	    test_bit(PG_head, &page->flags)) {
+	    test_bit(PG_head, &page->flags.f)) {
 		/*
 		 * We can safely access the field of the @page[1] with PG_head
 		 * because the @page is a compound page composed with at least
@@ -228,19 +230,56 @@ static __always_inline const struct page *page_fixed_fake_head(const struct page
 	}
 	return page;
 }
+
+static __always_inline bool page_count_writable(const struct page *page, int u)
+{
+	if (!static_branch_unlikely(&hugetlb_optimize_vmemmap_key))
+		return true;
+
+	/*
+	 * The refcount check is ordered before the fake-head check to prevent
+	 * the following race:
+	 *   CPU 1 (HVO)                     CPU 2 (speculative PFN walker)
+	 *
+	 *   page_ref_freeze()
+	 *   synchronize_rcu()
+	 *                                   rcu_read_lock()
+	 *                                   page_is_fake_head() is false
+	 *   vmemmap_remap_pte()
+	 *   XXX: struct page[] becomes r/o
+	 *
+	 *   page_ref_unfreeze()
+	 *                                   page_ref_count() is not zero
+	 *
+	 *                                   atomic_add_unless(&page->_refcount)
+	 *                                   XXX: try to modify r/o struct page[]
+	 *
+	 * The refcount check also prevents modification attempts to other (r/o)
+	 * tail pages that are not fake heads.
+	 */
+	if (atomic_read_acquire(&page->_refcount) == u)
+		return false;
+
+	return page_fixed_fake_head(page) == page;
+}
 #else
 static inline const struct page *page_fixed_fake_head(const struct page *page)
 {
 	return page;
 }
+
+static inline bool page_count_writable(const struct page *page, int u)
+{
+	return true;
+}
 #endif
 
-static __always_inline int page_is_fake_head(struct page *page)
+static __always_inline int page_is_fake_head(const struct page *page)
 {
 	return page_fixed_fake_head(page) != page;
 }
 
-static inline unsigned long _compound_head(const struct page *page)
+static __always_inline unsigned long _compound_head(const struct page *page)
 {
 	unsigned long head = READ_ONCE(page->compound_head);
 
@@ -277,23 +316,23 @@ static inline unsigned long _compound_head(const struct page *page)
  * check that the page number lies within @folio; the caller is presumed
  * to have a reference to the page.
  */
-#define folio_page(folio, n)	nth_page(&(folio)->page, n)
+#define folio_page(folio, n)	(&(folio)->page + (n))
 
-static __always_inline int PageTail(struct page *page)
+static __always_inline int PageTail(const struct page *page)
 {
 	return READ_ONCE(page->compound_head) & 1 || page_is_fake_head(page);
 }
 
-static __always_inline int PageCompound(struct page *page)
+static __always_inline int PageCompound(const struct page *page)
 {
-	return test_bit(PG_head, &page->flags) ||
+	return test_bit(PG_head, &page->flags.f) ||
 	       READ_ONCE(page->compound_head) & 1;
 }
 
 #define	PAGE_POISON_PATTERN	-1l
 static inline int PagePoisoned(const struct page *page)
 {
-	return READ_ONCE(page->flags) == PAGE_POISON_PATTERN;
+	return READ_ONCE(page->flags.f) == PAGE_POISON_PATTERN;
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -304,13 +343,23 @@ static inline void page_init_poison(struct page *page, size_t size)
 }
 #endif
 
+static const unsigned long *const_folio_flags(const struct folio *folio,
+		unsigned n)
+{
+	const struct page *page = &folio->page;
+
+	VM_BUG_ON_PGFLAGS(page->compound_head & 1, page);
+	VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page);
+	return &page[n].flags.f;
+}
+
 static unsigned long *folio_flags(struct folio *folio, unsigned n)
 {
 	struct page *page = &folio->page;
 
-	VM_BUG_ON_PGFLAGS(PageTail(page), page);
-	VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags), page);
-	return &page[n].flags;
+	VM_BUG_ON_PGFLAGS(page->compound_head & 1, page);
+	VM_BUG_ON_PGFLAGS(n > 0 && !test_bit(PG_head, &page->flags.f), page);
+	return &page[n].flags.f;
 }
 
 /*
@@ -326,9 +375,6 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n)
  *     for compound page all operations related to the page flag applied to
  *     head page.
  *
- * PF_ONLY_HEAD:
- *     for compound page, callers only ever operate on the head page.
- *
  * PF_NO_TAIL:
  *     modifications of the page flag must be done on small or head pages,
  *     checks can be done on tail pages too.
@@ -344,9 +390,6 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n)
 		page; })
 #define PF_ANY(page, enforce)	PF_POISONED_CHECK(page)
 #define PF_HEAD(page, enforce)	PF_POISONED_CHECK(compound_head(page))
-#define PF_ONLY_HEAD(page, enforce) ({					\
-		VM_BUG_ON_PGFLAGS(PageTail(page), page);		\
-		PF_POISONED_CHECK(page); })
 #define PF_NO_TAIL(page, enforce) ({					\
 		VM_BUG_ON_PGFLAGS(enforce && PageTail(page), page);	\
 		PF_POISONED_CHECK(compound_head(page)); })
@@ -360,61 +403,83 @@ static unsigned long *folio_flags(struct folio *folio, unsigned n)
 /* Which page is the flag stored in */
 #define FOLIO_PF_ANY		0
 #define FOLIO_PF_HEAD		0
-#define FOLIO_PF_ONLY_HEAD	0
 #define FOLIO_PF_NO_TAIL	0
 #define FOLIO_PF_NO_COMPOUND	0
 #define FOLIO_PF_SECOND		1
 
+#define FOLIO_HEAD_PAGE		0
+#define FOLIO_SECOND_PAGE	1
+
 /*
  * Macros to create function definitions for page flags
  */
+#define FOLIO_TEST_FLAG(name, page)					\
+static __always_inline bool folio_test_##name(const struct folio *folio) \
+{ return test_bit(PG_##name, const_folio_flags(folio, page)); }
+
+#define FOLIO_SET_FLAG(name, page)					\
+static __always_inline void folio_set_##name(struct folio *folio)	\
+{ set_bit(PG_##name, folio_flags(folio, page)); }
+
+#define FOLIO_CLEAR_FLAG(name, page)					\
+static __always_inline void folio_clear_##name(struct folio *folio)	\
+{ clear_bit(PG_##name, folio_flags(folio, page)); }
+
+#define __FOLIO_SET_FLAG(name, page)					\
+static __always_inline void __folio_set_##name(struct folio *folio)	\
+{ __set_bit(PG_##name, folio_flags(folio, page)); }
+
+#define __FOLIO_CLEAR_FLAG(name, page)					\
+static __always_inline void __folio_clear_##name(struct folio *folio)	\
+{ __clear_bit(PG_##name, folio_flags(folio, page)); }
+
+#define FOLIO_TEST_SET_FLAG(name, page)					\
+static __always_inline bool folio_test_set_##name(struct folio *folio)	\
+{ return test_and_set_bit(PG_##name, folio_flags(folio, page)); }
+
+#define FOLIO_TEST_CLEAR_FLAG(name, page)				\
+static __always_inline bool folio_test_clear_##name(struct folio *folio) \
+{ return test_and_clear_bit(PG_##name, folio_flags(folio, page)); }
+
+#define FOLIO_FLAG(name, page)						\
+FOLIO_TEST_FLAG(name, page)						\
+FOLIO_SET_FLAG(name, page)						\
+FOLIO_CLEAR_FLAG(name, page)
+
 #define TESTPAGEFLAG(uname, lname, policy)				\
-static __always_inline bool folio_test_##lname(struct folio *folio)	\
-{ return test_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); }	\
-static __always_inline int Page##uname(struct page *page)		\
-{ return test_bit(PG_##lname, &policy(page, 0)->flags); }
+FOLIO_TEST_FLAG(lname, FOLIO_##policy)					\
+static __always_inline int Page##uname(const struct page *page)		\
+{ return test_bit(PG_##lname, &policy(page, 0)->flags.f); }
 
 #define SETPAGEFLAG(uname, lname, policy)				\
-static __always_inline							\
-void folio_set_##lname(struct folio *folio)				\
-{ set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); }		\
+FOLIO_SET_FLAG(lname, FOLIO_##policy)					\
 static __always_inline void SetPage##uname(struct page *page)		\
-{ set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ set_bit(PG_##lname, &policy(page, 1)->flags.f); }
 
 #define CLEARPAGEFLAG(uname, lname, policy)				\
-static __always_inline							\
-void folio_clear_##lname(struct folio *folio)				\
-{ clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); }		\
+FOLIO_CLEAR_FLAG(lname, FOLIO_##policy)					\
 static __always_inline void ClearPage##uname(struct page *page)		\
-{ clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ clear_bit(PG_##lname, &policy(page, 1)->flags.f); }
 
 #define __SETPAGEFLAG(uname, lname, policy)				\
-static __always_inline							\
-void __folio_set_##lname(struct folio *folio)				\
-{ __set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); }		\
+__FOLIO_SET_FLAG(lname, FOLIO_##policy)					\
 static __always_inline void __SetPage##uname(struct page *page)		\
-{ __set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ __set_bit(PG_##lname, &policy(page, 1)->flags.f); }
 
 #define __CLEARPAGEFLAG(uname, lname, policy)				\
-static __always_inline							\
-void __folio_clear_##lname(struct folio *folio)				\
-{ __clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); }	\
+__FOLIO_CLEAR_FLAG(lname, FOLIO_##policy)				\
 static __always_inline void __ClearPage##uname(struct page *page)	\
-{ __clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ __clear_bit(PG_##lname, &policy(page, 1)->flags.f); }
 
 #define TESTSETFLAG(uname, lname, policy)				\
-static __always_inline							\
-bool folio_test_set_##lname(struct folio *folio)			\
-{ return test_and_set_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
+FOLIO_TEST_SET_FLAG(lname, FOLIO_##policy)				\
 static __always_inline int TestSetPage##uname(struct page *page)	\
-{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags); }
+{ return test_and_set_bit(PG_##lname, &policy(page, 1)->flags.f); }
 
 #define TESTCLEARFLAG(uname, lname, policy)				\
-static __always_inline							\
-bool folio_test_clear_##lname(struct folio *folio)			\
-{ return test_and_clear_bit(PG_##lname, folio_flags(folio, FOLIO_##policy)); } \
+FOLIO_TEST_CLEAR_FLAG(lname, FOLIO_##policy)				\
 static __always_inline int TestClearPage##uname(struct page *page)	\
-{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags); }
+{ return test_and_clear_bit(PG_##lname, &policy(page, 1)->flags.f); }
 
 #define PAGEFLAG(uname, lname, policy)					\
 	TESTPAGEFLAG(uname, lname, policy)				\
@@ -430,30 +495,51 @@ static __always_inline int TestClearPage##uname(struct page *page)	\
 	TESTSETFLAG(uname, lname, policy)				\
 	TESTCLEARFLAG(uname, lname, policy)
 
+#define FOLIO_TEST_FLAG_FALSE(name)					\
+static inline bool folio_test_##name(const struct folio *folio)		\
+{ return false; }
+#define FOLIO_SET_FLAG_NOOP(name)					\
+static inline void folio_set_##name(struct folio *folio) { }
+#define FOLIO_CLEAR_FLAG_NOOP(name)					\
+static inline void folio_clear_##name(struct folio *folio) { }
+#define __FOLIO_SET_FLAG_NOOP(name)					\
+static inline void __folio_set_##name(struct folio *folio) { }
+#define __FOLIO_CLEAR_FLAG_NOOP(name)					\
+static inline void __folio_clear_##name(struct folio *folio) { }
+#define FOLIO_TEST_SET_FLAG_FALSE(name)					\
+static inline bool folio_test_set_##name(struct folio *folio)		\
+{ return false; }
+#define FOLIO_TEST_CLEAR_FLAG_FALSE(name)				\
+static inline bool folio_test_clear_##name(struct folio *folio)		\
+{ return false; }
+
+#define FOLIO_FLAG_FALSE(name)						\
+FOLIO_TEST_FLAG_FALSE(name)						\
+FOLIO_SET_FLAG_NOOP(name)						\
+FOLIO_CLEAR_FLAG_NOOP(name)
+
 #define TESTPAGEFLAG_FALSE(uname, lname)				\
-static inline bool folio_test_##lname(const struct folio *folio) { return false; } \
+FOLIO_TEST_FLAG_FALSE(lname)						\
 static inline int Page##uname(const struct page *page) { return 0; }
 
 #define SETPAGEFLAG_NOOP(uname, lname)					\
-static inline void folio_set_##lname(struct folio *folio) { }		\
+FOLIO_SET_FLAG_NOOP(lname)						\
 static inline void SetPage##uname(struct page *page) {  }
 
 #define CLEARPAGEFLAG_NOOP(uname, lname)				\
-static inline void folio_clear_##lname(struct folio *folio) { }		\
+FOLIO_CLEAR_FLAG_NOOP(lname)						\
 static inline void ClearPage##uname(struct page *page) {  }
 
 #define __CLEARPAGEFLAG_NOOP(uname, lname)				\
-static inline void __folio_clear_##lname(struct folio *folio) { }	\
+__FOLIO_CLEAR_FLAG_NOOP(lname)						\
 static inline void __ClearPage##uname(struct page *page) {  }
 
 #define TESTSETFLAG_FALSE(uname, lname)					\
-static inline bool folio_test_set_##lname(struct folio *folio)		\
-{ return 0; }								\
+FOLIO_TEST_SET_FLAG_FALSE(lname)					\
 static inline int TestSetPage##uname(struct page *page) { return 0; }
 
 #define TESTCLEARFLAG_FALSE(uname, lname)				\
-static inline bool folio_test_clear_##lname(struct folio *folio)	\
-{ return 0; }								\
+FOLIO_TEST_CLEAR_FLAG_FALSE(lname)					\
 static inline int TestClearPage##uname(struct page *page) { return 0; }
 
 #define PAGEFLAG_FALSE(uname, lname) TESTPAGEFLAG_FALSE(uname, lname)	\
@@ -463,20 +549,19 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 	TESTSETFLAG_FALSE(uname, lname) TESTCLEARFLAG_FALSE(uname, lname)
 
 __PAGEFLAG(Locked, locked, PF_NO_TAIL)
-PAGEFLAG(Waiters, waiters, PF_ONLY_HEAD)
-PAGEFLAG(Error, error, PF_NO_TAIL) TESTCLEARFLAG(Error, error, PF_NO_TAIL)
-PAGEFLAG(Referenced, referenced, PF_HEAD)
-	TESTCLEARFLAG(Referenced, referenced, PF_HEAD)
-	__SETPAGEFLAG(Referenced, referenced, PF_HEAD)
+FOLIO_FLAG(waiters, FOLIO_HEAD_PAGE)
+FOLIO_FLAG(referenced, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(referenced, FOLIO_HEAD_PAGE)
+	__FOLIO_SET_FLAG(referenced, FOLIO_HEAD_PAGE)
 PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
 	__CLEARPAGEFLAG(Dirty, dirty, PF_HEAD)
 PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
 	TESTCLEARFLAG(LRU, lru, PF_HEAD)
-PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
-	TESTCLEARFLAG(Active, active, PF_HEAD)
+FOLIO_FLAG(active, FOLIO_HEAD_PAGE)
+	__FOLIO_CLEAR_FLAG(active, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(active, FOLIO_HEAD_PAGE)
 PAGEFLAG(Workingset, workingset, PF_HEAD)
 	TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
-__PAGEFLAG(Slab, slab, PF_NO_TAIL)
 PAGEFLAG(Checked, checked, PF_NO_COMPOUND)	   /* Used by some filesystems */
 
 /* Xen */
@@ -490,9 +575,9 @@ PAGEFLAG(XenRemapped, xen_remapped, PF_NO_COMPOUND)
 PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
 	__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
 	__SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
-PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
-	__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
-	__SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
+FOLIO_FLAG(swapbacked, FOLIO_HEAD_PAGE)
+	__FOLIO_CLEAR_FLAG(swapbacked, FOLIO_HEAD_PAGE)
+	__FOLIO_SET_FLAG(swapbacked, FOLIO_HEAD_PAGE)
 
 /*
  * Private page markings that may be used by the filesystem that owns the page
@@ -500,9 +585,10 @@ PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
  * - PG_private and PG_private_2 cause release_folio() and co to be invoked
  */
 PAGEFLAG(Private, private, PF_ANY)
-PAGEFLAG(Private2, private_2, PF_ANY) TESTSCFLAG(Private2, private_2, PF_ANY)
-PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
-	TESTCLEARFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
+FOLIO_FLAG(private_2, FOLIO_HEAD_PAGE)
+
+/* owner_2 can be set on tail pages for anon memory */
+FOLIO_FLAG(owner_2, FOLIO_HEAD_PAGE)
 
 /*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
@@ -510,13 +596,17 @@ PAGEFLAG(OwnerPriv1, owner_priv_1, PF_ANY)
  */
 TESTPAGEFLAG(Writeback, writeback, PF_NO_TAIL)
 	TESTSCFLAG(Writeback, writeback, PF_NO_TAIL)
-PAGEFLAG(MappedToDisk, mappedtodisk, PF_NO_TAIL)
+FOLIO_FLAG(mappedtodisk, FOLIO_HEAD_PAGE)
 
 /* PG_readahead is only used for reads; PG_reclaim is only for writes */
 PAGEFLAG(Reclaim, reclaim, PF_NO_TAIL)
 	TESTCLEARFLAG(Reclaim, reclaim, PF_NO_TAIL)
-PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND)
-	TESTCLEARFLAG(Readahead, readahead, PF_NO_COMPOUND)
+FOLIO_FLAG(readahead, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(readahead, FOLIO_HEAD_PAGE)
+
+FOLIO_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(dropbehind, FOLIO_HEAD_PAGE)
+	__FOLIO_SET_FLAG(dropbehind, FOLIO_HEAD_PAGE)
 
 #ifdef CONFIG_HIGHMEM
 /*
@@ -528,63 +618,65 @@ PAGEFLAG(Readahead, readahead, PF_NO_COMPOUND)
 #else
 PAGEFLAG_FALSE(HighMem, highmem)
 #endif
+#define PhysHighMem(__p) (PageHighMem(phys_to_page(__p)))
+
+/* Does kmap_local_folio() only allow access to one page of the folio? */
+#ifdef CONFIG_DEBUG_KMAP_LOCAL_FORCE_MAP
+#define folio_test_partial_kmap(f)	true
+#else
+#define folio_test_partial_kmap(f)	folio_test_highmem(f)
+#endif
 
 #ifdef CONFIG_SWAP
-static __always_inline bool folio_test_swapcache(struct folio *folio)
+static __always_inline bool folio_test_swapcache(const struct folio *folio)
 {
 	return folio_test_swapbacked(folio) &&
-			test_bit(PG_swapcache, folio_flags(folio, 0));
-}
-
-static __always_inline bool PageSwapCache(struct page *page)
-{
-	return folio_test_swapcache(page_folio(page));
+			test_bit(PG_swapcache, const_folio_flags(folio, 0));
 }
 
-SETPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
-CLEARPAGEFLAG(SwapCache, swapcache, PF_NO_TAIL)
+FOLIO_SET_FLAG(swapcache, FOLIO_HEAD_PAGE)
+FOLIO_CLEAR_FLAG(swapcache, FOLIO_HEAD_PAGE)
 #else
-PAGEFLAG_FALSE(SwapCache, swapcache)
+FOLIO_FLAG_FALSE(swapcache)
 #endif
 
-PAGEFLAG(Unevictable, unevictable, PF_HEAD)
-	__CLEARPAGEFLAG(Unevictable, unevictable, PF_HEAD)
-	TESTCLEARFLAG(Unevictable, unevictable, PF_HEAD)
+FOLIO_FLAG(unevictable, FOLIO_HEAD_PAGE)
+	__FOLIO_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(unevictable, FOLIO_HEAD_PAGE)
 
 #ifdef CONFIG_MMU
-PAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
-	__CLEARPAGEFLAG(Mlocked, mlocked, PF_NO_TAIL)
-	TESTSCFLAG(Mlocked, mlocked, PF_NO_TAIL)
-#else
-PAGEFLAG_FALSE(Mlocked, mlocked) __CLEARPAGEFLAG_NOOP(Mlocked, mlocked)
-	TESTSCFLAG_FALSE(Mlocked, mlocked)
-#endif
-
-#ifdef CONFIG_ARCH_USES_PG_UNCACHED
-PAGEFLAG(Uncached, uncached, PF_NO_COMPOUND)
+FOLIO_FLAG(mlocked, FOLIO_HEAD_PAGE)
+	__FOLIO_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_CLEAR_FLAG(mlocked, FOLIO_HEAD_PAGE)
+	FOLIO_TEST_SET_FLAG(mlocked, FOLIO_HEAD_PAGE)
 #else
-PAGEFLAG_FALSE(Uncached, uncached)
+FOLIO_FLAG_FALSE(mlocked)
+	__FOLIO_CLEAR_FLAG_NOOP(mlocked)
+	FOLIO_TEST_CLEAR_FLAG_FALSE(mlocked)
+	FOLIO_TEST_SET_FLAG_FALSE(mlocked)
 #endif
 
 #ifdef CONFIG_MEMORY_FAILURE
 PAGEFLAG(HWPoison, hwpoison, PF_ANY)
 TESTSCFLAG(HWPoison, hwpoison, PF_ANY)
 #define __PG_HWPOISON (1UL << PG_hwpoison)
-#define MAGIC_HWPOISON	0x48575053U	/* HWPS */
-extern void SetPageHWPoisonTakenOff(struct page *page);
-extern void ClearPageHWPoisonTakenOff(struct page *page);
-extern bool take_page_off_buddy(struct page *page);
-extern bool put_page_back_buddy(struct page *page);
 #else
 PAGEFLAG_FALSE(HWPoison, hwpoison)
 #define __PG_HWPOISON 0
 #endif
 
-#if defined(CONFIG_PAGE_IDLE_FLAG) && defined(CONFIG_64BIT)
-TESTPAGEFLAG(Young, young, PF_ANY)
-SETPAGEFLAG(Young, young, PF_ANY)
-TESTCLEARFLAG(Young, young, PF_ANY)
-PAGEFLAG(Idle, idle, PF_ANY)
+#ifdef CONFIG_PAGE_IDLE_FLAG
+#ifdef CONFIG_64BIT
+FOLIO_TEST_FLAG(young, FOLIO_HEAD_PAGE)
+FOLIO_SET_FLAG(young, FOLIO_HEAD_PAGE)
+FOLIO_TEST_CLEAR_FLAG(young, FOLIO_HEAD_PAGE)
+FOLIO_FLAG(idle, FOLIO_HEAD_PAGE)
+#endif
+/* See page_idle.h for !64BIT workaround */
+#else /* !CONFIG_PAGE_IDLE_FLAG */
+FOLIO_FLAG_FALSE(young)
+FOLIO_TEST_CLEAR_FLAG_FALSE(young)
+FOLIO_FLAG_FALSE(idle)
 #endif
 
 /*
@@ -602,65 +694,47 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
 #endif
 
 /*
- * On an anonymous page mapped into a user virtual memory area,
- * page->mapping points to its anon_vma, not to a struct address_space;
- * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
+ * On an anonymous folio mapped into a user virtual memory area,
+ * folio->mapping points to its anon_vma, not to a struct address_space;
+ * with the FOLIO_MAPPING_ANON bit set to distinguish it.  See rmap.h.
  *
- * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
- * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON
- * bit; and then page->mapping points, not to an anon_vma, but to a private
- * structure which KSM associates with that merged page.  See ksm.h.
+ * On an anonymous folio in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
+ * the FOLIO_MAPPING_ANON_KSM bit may be set along with the FOLIO_MAPPING_ANON
+ * bit; and then folio->mapping points, not to an anon_vma, but to a private
+ * structure which KSM associates with that merged folio.  See ksm.h.
  *
- * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable
- * page and then page->mapping points to a struct movable_operations.
+ * Please note that, confusingly, "folio_mapping" refers to the inode
+ * address_space which maps the folio from disk; whereas "folio_mapped"
+ * refers to user virtual address space into which the folio is mapped.
  *
- * Please note that, confusingly, "page_mapping" refers to the inode
- * address_space which maps the page from disk; whereas "page_mapped"
- * refers to user virtual address space into which the page is mapped.
+ * For slab pages, since slab reuses the bits in struct page to store its
+ * internal states, the folio->mapping does not exist as such, nor do
+ * these flags below.  So in order to avoid testing non-existent bits,
+ * please make sure that folio_test_slab(folio) actually evaluates to
+ * false before calling the following functions (e.g., folio_test_anon).
+ * See mm/slab.h.
  */
-#define PAGE_MAPPING_ANON	0x1
-#define PAGE_MAPPING_MOVABLE	0x2
-#define PAGE_MAPPING_KSM	(PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
-#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
+#define FOLIO_MAPPING_ANON	0x1
+#define FOLIO_MAPPING_ANON_KSM	0x2
+#define FOLIO_MAPPING_KSM	(FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM)
+#define FOLIO_MAPPING_FLAGS	(FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM)
 
-/*
- * Different with flags above, this flag is used only for fsdax mode.  It
- * indicates that this page->mapping is now under reflink case.
- */
-#define PAGE_MAPPING_DAX_SHARED	((void *)0x1)
-
-static __always_inline bool folio_mapping_flags(struct folio *folio)
+static __always_inline bool folio_test_anon(const struct folio *folio)
 {
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0;
+	return ((unsigned long)folio->mapping & FOLIO_MAPPING_ANON) != 0;
 }
 
-static __always_inline int PageMappingFlags(struct page *page)
+static __always_inline bool PageAnonNotKsm(const struct page *page)
 {
-	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
-}
+	unsigned long flags = (unsigned long)page_folio(page)->mapping;
 
-static __always_inline bool folio_test_anon(struct folio *folio)
-{
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
+	return (flags & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_ANON;
 }
 
-static __always_inline bool PageAnon(struct page *page)
+static __always_inline bool PageAnon(const struct page *page)
 {
 	return folio_test_anon(page_folio(page));
 }
-
-static __always_inline bool __folio_test_movable(const struct folio *folio)
-{
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
-			PAGE_MAPPING_MOVABLE;
-}
-
-static __always_inline int __PageMovable(struct page *page)
-{
-	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
-				PAGE_MAPPING_MOVABLE;
-}
-
 #ifdef CONFIG_KSM
 /*
  * A KSM page is one of those write-protected "shared pages" or "merged pages"
@@ -668,21 +742,35 @@ static __always_inline int __PageMovable(struct page *page)
  * is found in VM_MERGEABLE vmas.  It's a PageAnon page, pointing not to any
  * anon_vma, but to that page's node of the stable tree.
  */
-static __always_inline bool folio_test_ksm(struct folio *folio)
+static __always_inline bool folio_test_ksm(const struct folio *folio)
 {
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
-				PAGE_MAPPING_KSM;
-}
-
-static __always_inline bool PageKsm(struct page *page)
-{
-	return folio_test_ksm(page_folio(page));
+	return ((unsigned long)folio->mapping & FOLIO_MAPPING_FLAGS) ==
+				FOLIO_MAPPING_KSM;
 }
 #else
-TESTPAGEFLAG_FALSE(Ksm, ksm)
+FOLIO_TEST_FLAG_FALSE(ksm)
 #endif
 
-u64 stable_page_flags(struct page *page);
+u64 stable_page_flags(const struct page *page);
+
+/**
+ * folio_xor_flags_has_waiters - Change some folio flags.
+ * @folio: The folio.
+ * @mask: Bits set in this word will be changed.
+ *
+ * This must only be used for flags which are changed with the folio
+ * lock held.  For example, it is unsafe to use for PG_dirty as that
+ * can be set without the folio lock held.  It can also only be used
+ * on flags which are in the range 0-6 as some of the implementations
+ * only affect those bits.
+ *
+ * Return: Whether there are tasks waiting on the folio.
+ */
+static inline bool folio_xor_flags_has_waiters(struct folio *folio,
+		unsigned long mask)
+{
+	return xor_unlock_is_negative_byte(mask, folio_flags(folio, 0));
+}
 
 /**
  * folio_test_uptodate - Is this folio up to date?
@@ -694,9 +782,9 @@ u64 stable_page_flags(struct page *page);
  * some of the bytes in it may be; see the is_partially_uptodate()
  * address_space operation.
  */
-static inline bool folio_test_uptodate(struct folio *folio)
+static inline bool folio_test_uptodate(const struct folio *folio)
 {
-	bool ret = test_bit(PG_uptodate, folio_flags(folio, 0));
+	bool ret = test_bit(PG_uptodate, const_folio_flags(folio, 0));
 	/*
 	 * Must ensure that the data we read out of the folio is loaded
 	 * _after_ we've loaded folio->flags to check the uptodate bit.
@@ -711,7 +799,7 @@ static inline bool folio_test_uptodate(struct folio *folio)
 	return ret;
 }
 
-static inline int PageUptodate(struct page *page)
+static inline bool PageUptodate(const struct page *page)
 {
 	return folio_test_uptodate(page_folio(page));
 }
@@ -745,28 +833,21 @@ static __always_inline void SetPageUptodate(struct page *page)
 
 CLEARPAGEFLAG(Uptodate, uptodate, PF_NO_TAIL)
 
-bool __folio_start_writeback(struct folio *folio, bool keep_write);
-bool set_page_writeback(struct page *page);
+void __folio_start_writeback(struct folio *folio, bool keep_write);
+void set_page_writeback(struct page *page);
 
 #define folio_start_writeback(folio)			\
 	__folio_start_writeback(folio, false)
-#define folio_start_writeback_keepwrite(folio)	\
-	__folio_start_writeback(folio, true)
 
-static inline bool test_set_page_writeback(struct page *page)
+static __always_inline bool folio_test_head(const struct folio *folio)
 {
-	return set_page_writeback(page);
+	return test_bit(PG_head, const_folio_flags(folio, FOLIO_PF_ANY));
 }
 
-static __always_inline bool folio_test_head(struct folio *folio)
-{
-	return test_bit(PG_head, folio_flags(folio, FOLIO_PF_ANY));
-}
-
-static __always_inline int PageHead(struct page *page)
+static __always_inline int PageHead(const struct page *page)
 {
 	PF_POISONED_CHECK(page);
-	return test_bit(PG_head, &page->flags) && !page_is_fake_head(page);
+	return test_bit(PG_head, &page->flags.f) && !page_is_fake_head(page);
 }
 
 __SETPAGEFLAG(Head, head, PF_ANY)
@@ -779,7 +860,7 @@ CLEARPAGEFLAG(Head, head, PF_ANY)
  *
  * Return: True if the folio is larger than one page.
  */
-static inline bool folio_test_large(struct folio *folio)
+static inline bool folio_test_large(const struct folio *folio)
 {
 	return folio_test_head(folio);
 }
@@ -800,61 +881,27 @@ static inline void ClearPageCompound(struct page *page)
 	BUG_ON(!PageHead(page));
 	ClearPageHead(page);
 }
+FOLIO_FLAG(large_rmappable, FOLIO_SECOND_PAGE)
+FOLIO_FLAG(partially_mapped, FOLIO_SECOND_PAGE)
+#else
+FOLIO_FLAG_FALSE(large_rmappable)
+FOLIO_FLAG_FALSE(partially_mapped)
 #endif
 
 #define PG_head_mask ((1UL << PG_head))
 
-#ifdef CONFIG_HUGETLB_PAGE
-int PageHuge(struct page *page);
-bool folio_test_hugetlb(struct folio *folio);
-#else
-TESTPAGEFLAG_FALSE(Huge, hugetlb)
-#endif
-
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
- * PageHuge() only returns true for hugetlbfs pages, but not for
- * normal or transparent huge pages.
- *
- * PageTransHuge() returns true for both transparent huge and
- * hugetlbfs pages, but not normal pages. PageTransHuge() can only be
- * called only in the core VM paths where hugetlbfs pages can't exist.
- */
-static inline int PageTransHuge(struct page *page)
-{
-	VM_BUG_ON_PAGE(PageTail(page), page);
-	return PageHead(page);
-}
-
-static inline bool folio_test_transhuge(struct folio *folio)
-{
-	return folio_test_head(folio);
-}
-
-/*
  * PageTransCompound returns true for both transparent huge pages
  * and hugetlbfs pages, so it should only be called when it's known
  * that hugetlbfs pages aren't involved.
  */
-static inline int PageTransCompound(struct page *page)
+static inline int PageTransCompound(const struct page *page)
 {
 	return PageCompound(page);
 }
-
-/*
- * PageTransTail returns true for both transparent huge pages
- * and hugetlbfs pages, so it should only be called when it's known
- * that hugetlbfs pages aren't involved.
- */
-static inline int PageTransTail(struct page *page)
-{
-	return PageTail(page);
-}
 #else
-TESTPAGEFLAG_FALSE(TransHuge, transhuge)
 TESTPAGEFLAG_FALSE(TransCompound, transcompound)
-TESTPAGEFLAG_FALSE(TransCompoundMap, transcompoundmap)
-TESTPAGEFLAG_FALSE(TransTail, transtail)
 #endif
 
 #if defined(CONFIG_MEMORY_FAILURE) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
@@ -864,76 +911,96 @@ TESTPAGEFLAG_FALSE(TransTail, transtail)
  *
  * This flag is set by hwpoison handler.  Cleared by THP split or free page.
  */
-PAGEFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
-	TESTSCFLAG(HasHWPoisoned, has_hwpoisoned, PF_SECOND)
+FOLIO_FLAG(has_hwpoisoned, FOLIO_SECOND_PAGE)
 #else
-PAGEFLAG_FALSE(HasHWPoisoned, has_hwpoisoned)
-	TESTSCFLAG_FALSE(HasHWPoisoned, has_hwpoisoned)
+FOLIO_FLAG_FALSE(has_hwpoisoned)
 #endif
 
 /*
- * Check if a page is currently marked HWPoisoned. Note that this check is
- * best effort only and inherently racy: there is no way to synchronize with
- * failing hardware.
+ * For pages that do not use mapcount, page_type may be used.
+ * The low 24 bits of pagetype may be used for your own purposes, as long
+ * as you are careful to not affect the top 8 bits.  The low bits of
+ * pagetype will be overwritten when you clear the page_type from the page.
  */
-static inline bool is_page_hwpoison(struct page *page)
+enum pagetype {
+	/* 0x00-0x7f are positive numbers, ie mapcount */
+	/* Reserve 0x80-0xef for mapcount overflow. */
+	PGTY_buddy		= 0xf0,
+	PGTY_offline		= 0xf1,
+	PGTY_table		= 0xf2,
+	PGTY_guard		= 0xf3,
+	PGTY_hugetlb		= 0xf4,
+	PGTY_slab		= 0xf5,
+	PGTY_zsmalloc		= 0xf6,
+	PGTY_unaccepted		= 0xf7,
+	PGTY_large_kmalloc	= 0xf8,
+
+	PGTY_mapcount_underflow = 0xff
+};
+
+static inline bool page_type_has_type(int page_type)
 {
-	if (PageHWPoison(page))
-		return true;
-	return PageHuge(page) && PageHWPoison(compound_head(page));
+	return page_type < (PGTY_mapcount_underflow << 24);
 }
 
-/*
- * For pages that are never mapped to userspace (and aren't PageSlab),
- * page_type may be used.  Because it is initialised to -1, we invert the
- * sense of the bit, so __SetPageFoo *clears* the bit used for PageFoo, and
- * __ClearPageFoo *sets* the bit used for PageFoo.  We reserve a few high and
- * low bits so that an underflow or overflow of page_mapcount() won't be
- * mistaken for a page type value.
- */
-
-#define PAGE_TYPE_BASE	0xf0000000
-/* Reserve		0x0000007f to catch underflows of page_mapcount */
-#define PAGE_MAPCOUNT_RESERVE	-128
-#define PG_buddy	0x00000080
-#define PG_offline	0x00000100
-#define PG_table	0x00000200
-#define PG_guard	0x00000400
-
-#define PageType(page, flag)						\
-	((page->page_type & (PAGE_TYPE_BASE | flag)) == PAGE_TYPE_BASE)
-
-static inline int page_type_has_type(unsigned int page_type)
+/* This takes a mapcount which is one more than page->_mapcount */
+static inline bool page_mapcount_is_type(unsigned int mapcount)
 {
-	return (int)page_type < PAGE_MAPCOUNT_RESERVE;
+	return page_type_has_type(mapcount - 1);
 }
 
-static inline int page_has_type(struct page *page)
+static inline bool page_has_type(const struct page *page)
 {
-	return page_type_has_type(page->page_type);
+	return page_type_has_type(data_race(page->page_type));
+}
+
+#define FOLIO_TYPE_OPS(lname, fname)					\
+static __always_inline bool folio_test_##fname(const struct folio *folio) \
+{									\
+	return data_race(folio->page.page_type >> 24) == PGTY_##lname;	\
+}									\
+static __always_inline void __folio_set_##fname(struct folio *folio)	\
+{									\
+	if (folio_test_##fname(folio))					\
+		return;							\
+	VM_BUG_ON_FOLIO(data_race(folio->page.page_type) != UINT_MAX,	\
+			folio);						\
+	folio->page.page_type = (unsigned int)PGTY_##lname << 24;	\
+}									\
+static __always_inline void __folio_clear_##fname(struct folio *folio)	\
+{									\
+	if (folio->page.page_type == UINT_MAX)				\
+		return;							\
+	VM_BUG_ON_FOLIO(!folio_test_##fname(folio), folio);		\
+	folio->page.page_type = UINT_MAX;				\
 }
 
-#define PAGE_TYPE_OPS(uname, lname)					\
-static __always_inline int Page##uname(struct page *page)		\
+#define PAGE_TYPE_OPS(uname, lname, fname)				\
+FOLIO_TYPE_OPS(lname, fname)						\
+static __always_inline int Page##uname(const struct page *page)		\
 {									\
-	return PageType(page, PG_##lname);				\
+	return data_race(page->page_type >> 24) == PGTY_##lname;	\
 }									\
 static __always_inline void __SetPage##uname(struct page *page)		\
 {									\
-	VM_BUG_ON_PAGE(!PageType(page, 0), page);			\
-	page->page_type &= ~PG_##lname;					\
+	if (Page##uname(page))						\
+		return;							\
+	VM_BUG_ON_PAGE(data_race(page->page_type) != UINT_MAX, page);	\
+	page->page_type = (unsigned int)PGTY_##lname << 24;		\
 }									\
 static __always_inline void __ClearPage##uname(struct page *page)	\
 {									\
+	if (page->page_type == UINT_MAX)				\
+		return;							\
 	VM_BUG_ON_PAGE(!Page##uname(page), page);			\
-	page->page_type |= PG_##lname;					\
+	page->page_type = UINT_MAX;					\
 }
 
 /*
  * PageBuddy() indicates that the page is free and in the buddy system
  * (see mm/page_alloc.c).
  */
-PAGE_TYPE_OPS(Buddy, buddy)
+PAGE_TYPE_OPS(Buddy, buddy, buddy)
 
 /*
  * PageOffline() indicates that the page is logically offline although the
@@ -942,22 +1009,29 @@ PAGE_TYPE_OPS(Buddy, buddy)
  * The content of these pages is effectively stale. Such pages should not
  * be touched (read/write/dump/save) except by their owner.
  *
+ * When a memory block gets onlined, all pages are initialized with a
+ * refcount of 1 and PageOffline(). generic_online_page() will
+ * take care of clearing PageOffline().
+ *
  * If a driver wants to allow to offline unmovable PageOffline() pages without
  * putting them back to the buddy, it can do so via the memory notifier by
  * decrementing the reference count in MEM_GOING_OFFLINE and incrementing the
  * reference count in MEM_CANCEL_OFFLINE. When offlining, the PageOffline()
- * pages (now with a reference count of zero) are treated like free pages,
- * allowing the containing memory block to get offlined. A driver that
+ * pages (now with a reference count of zero) are treated like free (unmanaged)
+ * pages, allowing the containing memory block to get offlined. A driver that
  * relies on this feature is aware that re-onlining the memory block will
- * require to re-set the pages PageOffline() and not giving them to the
- * buddy via online_page_callback_t.
+ * require not giving them to the buddy via generic_online_page().
+ *
+ * Memory offlining code will not adjust the managed page count for any
+ * PageOffline() pages, treating them like they were never exposed to the
+ * buddy using generic_online_page().
  *
  * There are drivers that mark a page PageOffline() and expect there won't be
  * any further access to page content. PFN walkers that read content of random
  * pages should check PageOffline() and synchronize with such drivers using
  * page_offline_freeze()/page_offline_thaw().
  */
-PAGE_TYPE_OPS(Offline, offline)
+PAGE_TYPE_OPS(Offline, offline, offline)
 
 extern void page_offline_freeze(void);
 extern void page_offline_thaw(void);
@@ -967,43 +1041,146 @@ extern void page_offline_end(void);
 /*
  * Marks pages in use as page tables.
  */
-PAGE_TYPE_OPS(Table, table)
+PAGE_TYPE_OPS(Table, table, pgtable)
 
 /*
  * Marks guardpages used with debug_pagealloc.
  */
-PAGE_TYPE_OPS(Guard, guard)
+PAGE_TYPE_OPS(Guard, guard, guard)
+
+PAGE_TYPE_OPS(Slab, slab, slab)
+
+#ifdef CONFIG_HUGETLB_PAGE
+FOLIO_TYPE_OPS(hugetlb, hugetlb)
+#else
+FOLIO_TEST_FLAG_FALSE(hugetlb)
+#endif
 
-extern bool is_free_buddy_page(struct page *page);
+PAGE_TYPE_OPS(Zsmalloc, zsmalloc, zsmalloc)
 
-PAGEFLAG(Isolated, isolated, PF_ANY);
+/*
+ * Mark pages that has to be accepted before touched for the first time.
+ *
+ * Serialized with zone lock.
+ */
+PAGE_TYPE_OPS(Unaccepted, unaccepted, unaccepted)
+PAGE_TYPE_OPS(LargeKmalloc, large_kmalloc, large_kmalloc)
 
-static __always_inline int PageAnonExclusive(struct page *page)
+/**
+ * PageHuge - Determine if the page belongs to hugetlbfs
+ * @page: The page to test.
+ *
+ * Context: Any context.
+ * Return: True for hugetlbfs pages, false for anon pages or pages
+ * belonging to other filesystems.
+ */
+static inline bool PageHuge(const struct page *page)
+{
+	return folio_test_hugetlb(page_folio(page));
+}
+
+/*
+ * Check if a page is currently marked HWPoisoned. Note that this check is
+ * best effort only and inherently racy: there is no way to synchronize with
+ * failing hardware.
+ */
+static inline bool is_page_hwpoison(const struct page *page)
+{
+	const struct folio *folio;
+
+	if (PageHWPoison(page))
+		return true;
+	folio = page_folio(page);
+	return folio_test_hugetlb(folio) && PageHWPoison(&folio->page);
+}
+
+static inline bool folio_contain_hwpoisoned_page(struct folio *folio)
+{
+	return folio_test_hwpoison(folio) ||
+	    (folio_test_large(folio) && folio_test_has_hwpoisoned(folio));
+}
+
+bool is_free_buddy_page(const struct page *page);
+
+#ifdef CONFIG_MIGRATION
+/*
+ * This page is migratable through movable_ops (for selected typed pages
+ * only).
+ *
+ * Page migration of such pages might fail, for example, if the page is
+ * already isolated by somebody else, or if the page is about to get freed.
+ *
+ * While a subsystem might set selected typed pages that support page migration
+ * as being movable through movable_ops, it must never clear this flag.
+ *
+ * This flag is only cleared when the page is freed back to the buddy.
+ *
+ * Only selected page types support this flag (see page_movable_ops()) and
+ * the flag might be used in other context for other pages. Always use
+ * page_has_movable_ops() instead.
+ */
+TESTPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL);
+SETPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL);
+/*
+ * A movable_ops page has this flag set while it is isolated for migration.
+ * This flag primarily protects against concurrent migration attempts.
+ *
+ * Once migration ended (success or failure), the flag is cleared. The
+ * flag is managed by the migration core.
+ */
+PAGEFLAG(MovableOpsIsolated, movable_ops_isolated, PF_NO_TAIL);
+#else /* !CONFIG_MIGRATION */
+TESTPAGEFLAG_FALSE(MovableOps, movable_ops);
+SETPAGEFLAG_NOOP(MovableOps, movable_ops);
+PAGEFLAG_FALSE(MovableOpsIsolated, movable_ops_isolated);
+#endif /* CONFIG_MIGRATION */
+
+/**
+ * page_has_movable_ops - test for a movable_ops page
+ * @page: The page to test.
+ *
+ * Test whether this is a movable_ops page. Such pages will stay that
+ * way until freed.
+ *
+ * Returns true if this is a movable_ops page, otherwise false.
+ */
+static inline bool page_has_movable_ops(const struct page *page)
+{
+	return PageMovableOps(page) &&
+	       (PageOffline(page) || PageZsmalloc(page));
+}
+
+static __always_inline int PageAnonExclusive(const struct page *page)
 {
 	VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
-	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
-	return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+	/*
+	 * HugeTLB stores this information on the head page; THP keeps it per
+	 * page
+	 */
+	if (PageHuge(page))
+		page = compound_head(page);
+	return test_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f);
 }
 
 static __always_inline void SetPageAnonExclusive(struct page *page)
 {
-	VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page);
+	VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page);
 	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
-	set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+	set_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f);
 }
 
 static __always_inline void ClearPageAnonExclusive(struct page *page)
 {
-	VM_BUG_ON_PGFLAGS(!PageAnon(page) || PageKsm(page), page);
+	VM_BUG_ON_PGFLAGS(!PageAnonNotKsm(page), page);
 	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
-	clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+	clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f);
 }
 
 static __always_inline void __ClearPageAnonExclusive(struct page *page)
 {
 	VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
 	VM_BUG_ON_PGFLAGS(PageHuge(page) && !PageHead(page), page);
-	__clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags);
+	__clear_bit(PG_anon_exclusive, &PF_ANY(page, 1)->flags.f);
 }
 
 #ifdef CONFIG_MMU
@@ -1020,7 +1197,7 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page)
 	(1UL << PG_lru		| 1UL << PG_locked	|	\
 	 1UL << PG_private	| 1UL << PG_private_2	|	\
 	 1UL << PG_writeback	| 1UL << PG_reserved	|	\
-	 1UL << PG_slab		| 1UL << PG_active 	|	\
+	 1UL << PG_active 	|				\
 	 1UL << PG_unevictable	| __PG_MLOCKED | LRU_GEN_MASK)
 
 /*
@@ -1034,28 +1211,30 @@ static __always_inline void __ClearPageAnonExclusive(struct page *page)
 #define PAGE_FLAGS_CHECK_AT_PREP	\
 	((PAGEFLAGS_MASK & ~__PG_HWPOISON) | LRU_GEN_MASK | LRU_REFS_MASK)
 
+/*
+ * Flags stored in the second page of a compound page.  They may overlap
+ * the CHECK_AT_FREE flags above, so need to be cleared.
+ */
+#define PAGE_FLAGS_SECOND						\
+	(0xffUL /* order */		| 1UL << PG_has_hwpoisoned |	\
+	 1UL << PG_large_rmappable	| 1UL << PG_partially_mapped)
+
 #define PAGE_FLAGS_PRIVATE				\
 	(1UL << PG_private | 1UL << PG_private_2)
 /**
- * page_has_private - Determine if page has private stuff
- * @page: The page to be checked
+ * folio_has_private - Determine if folio has private stuff
+ * @folio: The folio to be checked
  *
- * Determine if a page has private stuff, indicating that release routines
+ * Determine if a folio has private stuff, indicating that release routines
  * should be invoked upon it.
  */
-static inline int page_has_private(struct page *page)
-{
-	return !!(page->flags & PAGE_FLAGS_PRIVATE);
-}
-
-static inline bool folio_has_private(struct folio *folio)
+static inline int folio_has_private(const struct folio *folio)
 {
-	return page_has_private(&folio->page);
+	return !!(folio->flags.f & PAGE_FLAGS_PRIVATE);
 }
 
 #undef PF_ANY
 #undef PF_HEAD
-#undef PF_ONLY_HEAD
 #undef PF_NO_TAIL
 #undef PF_NO_COMPOUND
 #undef PF_SECOND
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 4ac34392823a..3e2f960e166c 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -3,10 +3,6 @@
 #define __LINUX_PAGEISOLATION_H
 
 #ifdef CONFIG_MEMORY_ISOLATION
-static inline bool has_isolate_pageblock(struct zone *zone)
-{
-	return zone->nr_isolate_pageblock;
-}
 static inline bool is_migrate_isolate_page(struct page *page)
 {
 	return get_pageblock_migratetype(page) == MIGRATE_ISOLATE;
@@ -15,34 +11,60 @@ static inline bool is_migrate_isolate(int migratetype)
 {
 	return migratetype == MIGRATE_ISOLATE;
 }
+#define get_pageblock_isolate(page) \
+	get_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate)
+#define clear_pageblock_isolate(page) \
+	clear_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate)
+#define set_pageblock_isolate(page) \
+	set_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate)
 #else
-static inline bool has_isolate_pageblock(struct zone *zone)
+static inline bool is_migrate_isolate_page(struct page *page)
 {
 	return false;
 }
-static inline bool is_migrate_isolate_page(struct page *page)
+static inline bool is_migrate_isolate(int migratetype)
 {
 	return false;
 }
-static inline bool is_migrate_isolate(int migratetype)
+static inline bool get_pageblock_isolate(struct page *page)
 {
 	return false;
 }
+static inline void clear_pageblock_isolate(struct page *page)
+{
+}
+static inline void set_pageblock_isolate(struct page *page)
+{
+}
 #endif
 
-#define MEMORY_OFFLINE	0x1
-#define REPORT_FAILURE	0x2
+/*
+ * Pageblock isolation modes:
+ * PB_ISOLATE_MODE_MEM_OFFLINE - isolate to offline (!allocate) memory
+ *				 e.g., skip over PageHWPoison() pages and
+ *				 PageOffline() pages. Unmovable pages will be
+ *				 reported in this mode.
+ * PB_ISOLATE_MODE_CMA_ALLOC   - isolate for CMA allocations
+ * PB_ISOLATE_MODE_OTHER       - isolate for other purposes
+ */
+enum pb_isolate_mode {
+	PB_ISOLATE_MODE_MEM_OFFLINE,
+	PB_ISOLATE_MODE_CMA_ALLOC,
+	PB_ISOLATE_MODE_OTHER,
+};
+
+void __meminit init_pageblock_migratetype(struct page *page,
+					  enum migratetype migratetype,
+					  bool isolate);
 
-void set_pageblock_migratetype(struct page *page, int migratetype);
-int move_freepages_block(struct zone *zone, struct page *page,
-				int migratetype, int *num_movable);
+bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page);
+bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page);
 
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype, int flags, gfp_t gfp_flags);
+			     enum pb_isolate_mode mode);
 
-void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype);
+void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
 
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
-			int isol_flags);
+			enum pb_isolate_mode mode);
 #endif
diff --git a/include/linux/page_counter.h b/include/linux/page_counter.h
index c141ea9a95ef..d649b6bbbc87 100644
--- a/include/linux/page_counter.h
+++ b/include/linux/page_counter.h
@@ -4,15 +4,17 @@
 
 #include <linux/atomic.h>
 #include <linux/cache.h>
-#include <linux/kernel.h>
+#include <linux/limits.h>
 #include <asm/page.h>
 
 struct page_counter {
 	/*
-	 * Make sure 'usage' does not share cacheline with any other field. The
-	 * memcg->memory.usage is a hot member of struct mem_cgroup.
+	 * Make sure 'usage' does not share cacheline with any other field in
+	 * v2. The memcg->memory.usage is a hot member of struct mem_cgroup.
 	 */
 	atomic_long_t usage;
+	unsigned long failcnt; /* v1-only field */
+
 	CACHELINE_PADDING(_pad1_);
 
 	/* effective memory.min and memory.min usage tracking */
@@ -26,11 +28,14 @@ struct page_counter {
 	atomic_long_t children_low_usage;
 
 	unsigned long watermark;
-	unsigned long failcnt;
+	/* Latest cg2 reset watermark */
+	unsigned long local_watermark;
 
 	/* Keep all the read most fields in a separete cacheline. */
 	CACHELINE_PADDING(_pad2_);
 
+	bool protection_support;
+	bool track_failcnt;
 	unsigned long min;
 	unsigned long low;
 	unsigned long high;
@@ -44,12 +49,18 @@ struct page_counter {
 #define PAGE_COUNTER_MAX (LONG_MAX / PAGE_SIZE)
 #endif
 
+/*
+ * Protection is supported only for the first counter (with id 0).
+ */
 static inline void page_counter_init(struct page_counter *counter,
-				     struct page_counter *parent)
+				     struct page_counter *parent,
+				     bool protection_support)
 {
-	atomic_long_set(&counter->usage, 0);
+	counter->usage = (atomic_long_t)ATOMIC_LONG_INIT(0);
 	counter->max = PAGE_COUNTER_MAX;
 	counter->parent = parent;
+	counter->protection_support = protection_support;
+	counter->track_failcnt = false;
 }
 
 static inline unsigned long page_counter_read(struct page_counter *counter)
@@ -78,7 +89,24 @@ int page_counter_memparse(const char *buf, const char *max,
 
 static inline void page_counter_reset_watermark(struct page_counter *counter)
 {
-	counter->watermark = page_counter_read(counter);
+	unsigned long usage = page_counter_read(counter);
+
+	/*
+	 * Update local_watermark first, so it's always <= watermark
+	 * (modulo CPU/compiler re-ordering)
+	 */
+	counter->local_watermark = usage;
+	counter->watermark = usage;
 }
 
+#if IS_ENABLED(CONFIG_MEMCG) || IS_ENABLED(CONFIG_CGROUP_DMEM)
+void page_counter_calculate_protection(struct page_counter *root,
+				       struct page_counter *counter,
+				       bool recursive_protection);
+#else
+static inline void page_counter_calculate_protection(struct page_counter *root,
+						     struct page_counter *counter,
+						     bool recursive_protection) {}
+#endif
+
 #endif /* _LINUX_PAGE_COUNTER_H */
diff --git a/include/linux/page_ext.h b/include/linux/page_ext.h
index 67314f648aeb..76c817162d2f 100644
--- a/include/linux/page_ext.h
+++ b/include/linux/page_ext.h
@@ -3,11 +3,12 @@
 #define __LINUX_PAGE_EXT_H
 
 #include <linux/types.h>
+#include <linux/mmzone.h>
 #include <linux/stacktrace.h>
-#include <linux/stackdepot.h>
 
 struct pglist_data;
 
+#ifdef CONFIG_PAGE_EXTENSION
 /**
  * struct page_ext_operations - per page_ext client operations
  * @offset: Offset to the client's data within page_ext. Offset is returned to
@@ -29,8 +30,6 @@ struct page_ext_operations {
 	bool need_shared_flags;
 };
 
-#ifdef CONFIG_PAGE_EXTENSION
-
 /*
  * The page_ext_flags users must set need_shared_flags to true.
  */
@@ -71,16 +70,37 @@ extern void page_ext_init(void);
 static inline void page_ext_init_flatmem_late(void)
 {
 }
+
+static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn)
+{
+	/*
+	 * page_ext is allocated per memory section. Once we cross a
+	 * memory section, we have to fetch the new pointer.
+	 */
+	return next_pfn % PAGES_PER_SECTION;
+}
 #else
 extern void page_ext_init_flatmem(void);
 extern void page_ext_init_flatmem_late(void);
 static inline void page_ext_init(void)
 {
 }
+
+static inline bool page_ext_iter_next_fast_possible(unsigned long next_pfn)
+{
+	return true;
+}
 #endif
 
-extern struct page_ext *page_ext_get(struct page *page);
+extern struct page_ext *page_ext_get(const struct page *page);
 extern void page_ext_put(struct page_ext *page_ext);
+extern struct page_ext *page_ext_lookup(unsigned long pfn);
+
+static inline void *page_ext_data(struct page_ext *page_ext,
+				  struct page_ext_operations *ops)
+{
+	return (void *)(page_ext) + ops->offset;
+}
 
 static inline struct page_ext *page_ext_next(struct page_ext *curr)
 {
@@ -89,6 +109,83 @@ static inline struct page_ext *page_ext_next(struct page_ext *curr)
 	return next;
 }
 
+struct page_ext_iter {
+	unsigned long index;
+	unsigned long start_pfn;
+	struct page_ext *page_ext;
+};
+
+/**
+ * page_ext_iter_begin() - Prepare for iterating through page extensions.
+ * @iter: page extension iterator.
+ * @pfn: PFN of the page we're interested in.
+ *
+ * Must be called with RCU read lock taken.
+ *
+ * Return: NULL if no page_ext exists for this page.
+ */
+static inline struct page_ext *page_ext_iter_begin(struct page_ext_iter *iter,
+						unsigned long pfn)
+{
+	iter->index = 0;
+	iter->start_pfn = pfn;
+	iter->page_ext = page_ext_lookup(pfn);
+
+	return iter->page_ext;
+}
+
+/**
+ * page_ext_iter_next() - Get next page extension
+ * @iter: page extension iterator.
+ *
+ * Must be called with RCU read lock taken.
+ *
+ * Return: NULL if no next page_ext exists.
+ */
+static inline struct page_ext *page_ext_iter_next(struct page_ext_iter *iter)
+{
+	unsigned long pfn;
+
+	if (WARN_ON_ONCE(!iter->page_ext))
+		return NULL;
+
+	iter->index++;
+	pfn = iter->start_pfn + iter->index;
+
+	if (page_ext_iter_next_fast_possible(pfn))
+		iter->page_ext = page_ext_next(iter->page_ext);
+	else
+		iter->page_ext = page_ext_lookup(pfn);
+
+	return iter->page_ext;
+}
+
+/**
+ * page_ext_iter_get() - Get current page extension
+ * @iter: page extension iterator.
+ *
+ * Return: NULL if no page_ext exists for this iterator.
+ */
+static inline struct page_ext *page_ext_iter_get(const struct page_ext_iter *iter)
+{
+	return iter->page_ext;
+}
+
+/**
+ * for_each_page_ext(): iterate through page_ext objects.
+ * @__page: the page we're interested in
+ * @__pgcount: how many pages to iterate through
+ * @__page_ext: struct page_ext pointer where the current page_ext
+ *              object is returned
+ * @__iter: struct page_ext_iter object (defined in the stack)
+ *
+ * IMPORTANT: must be called with RCU read lock taken.
+ */
+#define for_each_page_ext(__page, __pgcount, __page_ext, __iter) \
+	for (__page_ext = page_ext_iter_begin(&__iter, page_to_pfn(__page));\
+		__page_ext && __iter.index < __pgcount;          \
+		__page_ext = page_ext_iter_next(&__iter))
+
 #else /* !CONFIG_PAGE_EXTENSION */
 struct page_ext;
 
@@ -113,7 +210,7 @@ static inline void page_ext_init_flatmem(void)
 {
 }
 
-static inline struct page_ext *page_ext_get(struct page *page)
+static inline struct page_ext *page_ext_get(const struct page *page)
 {
 	return NULL;
 }
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
new file mode 100644
index 000000000000..41a91df82631
--- /dev/null
+++ b/include/linux/page_frag_cache.h
@@ -0,0 +1,61 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PAGE_FRAG_CACHE_H
+#define _LINUX_PAGE_FRAG_CACHE_H
+
+#include <linux/bits.h>
+#include <linux/log2.h>
+#include <linux/mm_types_task.h>
+#include <linux/types.h>
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+/* Use a full byte here to enable assembler optimization as the shift
+ * operation is usually expecting a byte.
+ */
+#define PAGE_FRAG_CACHE_ORDER_MASK		GENMASK(7, 0)
+#else
+/* Compiler should be able to figure out we don't read things as any value
+ * ANDed with 0 is 0.
+ */
+#define PAGE_FRAG_CACHE_ORDER_MASK		0
+#endif
+
+#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT		(PAGE_FRAG_CACHE_ORDER_MASK + 1)
+
+static inline bool encoded_page_decode_pfmemalloc(unsigned long encoded_page)
+{
+	return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT);
+}
+
+static inline void page_frag_cache_init(struct page_frag_cache *nc)
+{
+	nc->encoded_page = 0;
+}
+
+static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
+{
+	return encoded_page_decode_pfmemalloc(nc->encoded_page);
+}
+
+void page_frag_cache_drain(struct page_frag_cache *nc);
+void __page_frag_cache_drain(struct page *page, unsigned int count);
+void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
+			      gfp_t gfp_mask, unsigned int align_mask);
+
+static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
+					  unsigned int fragsz, gfp_t gfp_mask,
+					  unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
+}
+
+static inline void *page_frag_alloc(struct page_frag_cache *nc,
+				    unsigned int fragsz, gfp_t gfp_mask)
+{
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
+}
+
+void page_frag_free(void *addr);
+
+#endif
diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h
index 5cb7bd2078ec..89ca0d5dc1e7 100644
--- a/include/linux/page_idle.h
+++ b/include/linux/page_idle.h
@@ -6,14 +6,12 @@
 #include <linux/page-flags.h>
 #include <linux/page_ext.h>
 
-#ifdef CONFIG_PAGE_IDLE_FLAG
-
-#ifndef CONFIG_64BIT
+#if defined(CONFIG_PAGE_IDLE_FLAG) && !defined(CONFIG_64BIT)
 /*
  * If there is not enough space to store Idle and Young bits in page flags, use
  * page ext flags instead.
  */
-static inline bool folio_test_young(struct folio *folio)
+static inline bool folio_test_young(const struct folio *folio)
 {
 	struct page_ext *page_ext = page_ext_get(&folio->page);
 	bool page_young;
@@ -52,7 +50,7 @@ static inline bool folio_test_clear_young(struct folio *folio)
 	return page_young;
 }
 
-static inline bool folio_test_idle(struct folio *folio)
+static inline bool folio_test_idle(const struct folio *folio)
 {
 	struct page_ext *page_ext = page_ext_get(&folio->page);
 	bool page_idle;
@@ -60,7 +58,7 @@ static inline bool folio_test_idle(struct folio *folio)
 	if (unlikely(!page_ext))
 		return false;
 
-	page_idle =  test_bit(PAGE_EXT_IDLE, &page_ext->flags);
+	page_idle = test_bit(PAGE_EXT_IDLE, &page_ext->flags);
 	page_ext_put(page_ext);
 
 	return page_idle;
@@ -87,66 +85,5 @@ static inline void folio_clear_idle(struct folio *folio)
 	clear_bit(PAGE_EXT_IDLE, &page_ext->flags);
 	page_ext_put(page_ext);
 }
-#endif /* !CONFIG_64BIT */
-
-#else /* !CONFIG_PAGE_IDLE_FLAG */
-
-static inline bool folio_test_young(struct folio *folio)
-{
-	return false;
-}
-
-static inline void folio_set_young(struct folio *folio)
-{
-}
-
-static inline bool folio_test_clear_young(struct folio *folio)
-{
-	return false;
-}
-
-static inline bool folio_test_idle(struct folio *folio)
-{
-	return false;
-}
-
-static inline void folio_set_idle(struct folio *folio)
-{
-}
-
-static inline void folio_clear_idle(struct folio *folio)
-{
-}
-
-#endif /* CONFIG_PAGE_IDLE_FLAG */
-
-static inline bool page_is_young(struct page *page)
-{
-	return folio_test_young(page_folio(page));
-}
-
-static inline void set_page_young(struct page *page)
-{
-	folio_set_young(page_folio(page));
-}
-
-static inline bool test_and_clear_page_young(struct page *page)
-{
-	return folio_test_clear_young(page_folio(page));
-}
-
-static inline bool page_is_idle(struct page *page)
-{
-	return folio_test_idle(page_folio(page));
-}
-
-static inline void set_page_idle(struct page *page)
-{
-	folio_set_idle(page_folio(page));
-}
-
-static inline void clear_page_idle(struct page *page)
-{
-	folio_clear_idle(page_folio(page));
-}
+#endif /* CONFIG_PAGE_IDLE_FLAG && !64BIT */
 #endif /* _LINUX_MM_PAGE_IDLE_H */
diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index 119a0c9d2a8b..3328357f6dba 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -11,9 +11,10 @@ extern struct page_ext_operations page_owner_ops;
 extern void __reset_page_owner(struct page *page, unsigned short order);
 extern void __set_page_owner(struct page *page,
 			unsigned short order, gfp_t gfp_mask);
-extern void __split_page_owner(struct page *page, unsigned int nr);
+extern void __split_page_owner(struct page *page, int old_order,
+			int new_order);
 extern void __folio_copy_owner(struct folio *newfolio, struct folio *old);
-extern void __set_page_owner_migrate_reason(struct page *page, int reason);
+extern void __folio_set_owner_migrate_reason(struct folio *folio, int reason);
 extern void __dump_page_owner(const struct page *page);
 extern void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 					pg_data_t *pgdat, struct zone *zone);
@@ -31,20 +32,21 @@ static inline void set_page_owner(struct page *page,
 		__set_page_owner(page, order, gfp_mask);
 }
 
-static inline void split_page_owner(struct page *page, unsigned int nr)
+static inline void split_page_owner(struct page *page, int old_order,
+			int new_order)
 {
 	if (static_branch_unlikely(&page_owner_inited))
-		__split_page_owner(page, nr);
+		__split_page_owner(page, old_order, new_order);
 }
 static inline void folio_copy_owner(struct folio *newfolio, struct folio *old)
 {
 	if (static_branch_unlikely(&page_owner_inited))
 		__folio_copy_owner(newfolio, old);
 }
-static inline void set_page_owner_migrate_reason(struct page *page, int reason)
+static inline void folio_set_owner_migrate_reason(struct folio *folio, int reason)
 {
 	if (static_branch_unlikely(&page_owner_inited))
-		__set_page_owner_migrate_reason(page, reason);
+		__folio_set_owner_migrate_reason(folio, reason);
 }
 static inline void dump_page_owner(const struct page *page)
 {
@@ -56,17 +58,17 @@ static inline void reset_page_owner(struct page *page, unsigned short order)
 {
 }
 static inline void set_page_owner(struct page *page,
-			unsigned int order, gfp_t gfp_mask)
+			unsigned short order, gfp_t gfp_mask)
 {
 }
-static inline void split_page_owner(struct page *page,
-			unsigned short order)
+static inline void split_page_owner(struct page *page, int old_order,
+			int new_order)
 {
 }
 static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio)
 {
 }
-static inline void set_page_owner_migrate_reason(struct page *page, int reason)
+static inline void folio_set_owner_migrate_reason(struct folio *folio, int reason)
 {
 }
 static inline void dump_page_owner(const struct page *page)
diff --git a/include/linux/page_ref.h b/include/linux/page_ref.h
index d7c2d33baa7f..544150d1d5fd 100644
--- a/include/linux/page_ref.h
+++ b/include/linux/page_ref.h
@@ -139,20 +139,15 @@ static inline void folio_ref_sub(struct folio *folio, int nr)
 	page_ref_sub(&folio->page, nr);
 }
 
-static inline int page_ref_sub_return(struct page *page, int nr)
+static inline int folio_ref_sub_return(struct folio *folio, int nr)
 {
-	int ret = atomic_sub_return(nr, &page->_refcount);
+	int ret = atomic_sub_return(nr, &folio->_refcount);
 
 	if (page_ref_tracepoint_active(page_ref_mod_and_return))
-		__page_ref_mod_and_return(page, -nr, ret);
+		__page_ref_mod_and_return(&folio->page, -nr, ret);
 	return ret;
 }
 
-static inline int folio_ref_sub_return(struct folio *folio, int nr)
-{
-	return page_ref_sub_return(&folio->page, nr);
-}
-
 static inline void page_ref_inc(struct page *page)
 {
 	atomic_inc(&page->_refcount);
@@ -235,7 +230,13 @@ static inline int folio_ref_dec_return(struct folio *folio)
 
 static inline bool page_ref_add_unless(struct page *page, int nr, int u)
 {
-	bool ret = atomic_add_unless(&page->_refcount, nr, u);
+	bool ret = false;
+
+	rcu_read_lock();
+	/* avoid writing to the vmemmap area being remapped */
+	if (page_count_writable(page, u))
+		ret = atomic_add_unless(&page->_refcount, nr, u);
+	rcu_read_unlock();
 
 	if (page_ref_tracepoint_active(page_ref_mod_unless))
 		__page_ref_mod_unless(page, nr, ret);
@@ -263,54 +264,9 @@ static inline bool folio_try_get(struct folio *folio)
 	return folio_ref_add_unless(folio, 1, 0);
 }
 
-static inline bool folio_ref_try_add_rcu(struct folio *folio, int count)
-{
-#ifdef CONFIG_TINY_RCU
-	/*
-	 * The caller guarantees the folio will not be freed from interrupt
-	 * context, so (on !SMP) we only need preemption to be disabled
-	 * and TINY_RCU does that for us.
-	 */
-# ifdef CONFIG_PREEMPT_COUNT
-	VM_BUG_ON(!in_atomic() && !irqs_disabled());
-# endif
-	VM_BUG_ON_FOLIO(folio_ref_count(folio) == 0, folio);
-	folio_ref_add(folio, count);
-#else
-	if (unlikely(!folio_ref_add_unless(folio, count, 0))) {
-		/* Either the folio has been freed, or will be freed. */
-		return false;
-	}
-#endif
-	return true;
-}
-
-/**
- * folio_try_get_rcu - Attempt to increase the refcount on a folio.
- * @folio: The folio.
- *
- * This is a version of folio_try_get() optimised for non-SMP kernels.
- * If you are still holding the rcu_read_lock() after looking up the
- * page and know that the page cannot have its refcount decreased to
- * zero in interrupt context, you can use this instead of folio_try_get().
- *
- * Example users include get_user_pages_fast() (as pages are not unmapped
- * from interrupt context) and the page cache lookups (as pages are not
- * truncated from interrupt context).  We also know that pages are not
- * frozen in interrupt context for the purposes of splitting or migration.
- *
- * You can also use this function if you're holding a lock that prevents
- * pages being frozen & removed; eg the i_pages lock for the page cache
- * or the mmap_lock or page table lock for page tables.  In this case,
- * it will always succeed, and you could have used a plain folio_get(),
- * but it's sometimes more convenient to have a common function called
- * from both locked and RCU-protected contexts.
- *
- * Return: True if the reference count was successfully incremented.
- */
-static inline bool folio_try_get_rcu(struct folio *folio)
+static inline bool folio_ref_try_add(struct folio *folio, int count)
 {
-	return folio_ref_try_add_rcu(folio, 1);
+	return folio_ref_add_unless(folio, count, 0);
 }
 
 static inline int page_ref_freeze(struct page *page, int count)
diff --git a/include/linux/page_table_check.h b/include/linux/page_table_check.h
index 01e16c7696ec..289620d4aad3 100644
--- a/include/linux/page_table_check.h
+++ b/include/linux/page_table_check.h
@@ -14,18 +14,15 @@ extern struct static_key_true page_table_check_disabled;
 extern struct page_ext_operations page_table_check_ops;
 
 void __page_table_check_zero(struct page *page, unsigned int order);
-void __page_table_check_pte_clear(struct mm_struct *mm, unsigned long addr,
-				  pte_t pte);
-void __page_table_check_pmd_clear(struct mm_struct *mm, unsigned long addr,
-				  pmd_t pmd);
-void __page_table_check_pud_clear(struct mm_struct *mm, unsigned long addr,
-				  pud_t pud);
-void __page_table_check_pte_set(struct mm_struct *mm, unsigned long addr,
-				pte_t *ptep, pte_t pte);
-void __page_table_check_pmd_set(struct mm_struct *mm, unsigned long addr,
-				pmd_t *pmdp, pmd_t pmd);
-void __page_table_check_pud_set(struct mm_struct *mm, unsigned long addr,
-				pud_t *pudp, pud_t pud);
+void __page_table_check_pte_clear(struct mm_struct *mm, pte_t pte);
+void __page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd);
+void __page_table_check_pud_clear(struct mm_struct *mm, pud_t pud);
+void __page_table_check_ptes_set(struct mm_struct *mm, pte_t *ptep, pte_t pte,
+		unsigned int nr);
+void __page_table_check_pmds_set(struct mm_struct *mm, pmd_t *pmdp, pmd_t pmd,
+		unsigned int nr);
+void __page_table_check_puds_set(struct mm_struct *mm, pud_t *pudp, pud_t pud,
+		unsigned int nr);
 void __page_table_check_pte_clear_range(struct mm_struct *mm,
 					unsigned long addr,
 					pmd_t pmd);
@@ -46,61 +43,55 @@ static inline void page_table_check_free(struct page *page, unsigned int order)
 	__page_table_check_zero(page, order);
 }
 
-static inline void page_table_check_pte_clear(struct mm_struct *mm,
-					      unsigned long addr, pte_t pte)
+static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pte_clear(mm, addr, pte);
+	__page_table_check_pte_clear(mm, pte);
 }
 
-static inline void page_table_check_pmd_clear(struct mm_struct *mm,
-					      unsigned long addr, pmd_t pmd)
+static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pmd_clear(mm, addr, pmd);
+	__page_table_check_pmd_clear(mm, pmd);
 }
 
-static inline void page_table_check_pud_clear(struct mm_struct *mm,
-					      unsigned long addr, pud_t pud)
+static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pud_clear(mm, addr, pud);
+	__page_table_check_pud_clear(mm, pud);
 }
 
-static inline void page_table_check_pte_set(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep,
-					    pte_t pte)
+static inline void page_table_check_ptes_set(struct mm_struct *mm,
+		pte_t *ptep, pte_t pte, unsigned int nr)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pte_set(mm, addr, ptep, pte);
+	__page_table_check_ptes_set(mm, ptep, pte, nr);
 }
 
-static inline void page_table_check_pmd_set(struct mm_struct *mm,
-					    unsigned long addr, pmd_t *pmdp,
-					    pmd_t pmd)
+static inline void page_table_check_pmds_set(struct mm_struct *mm,
+		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pmd_set(mm, addr, pmdp, pmd);
+	__page_table_check_pmds_set(mm, pmdp, pmd, nr);
 }
 
-static inline void page_table_check_pud_set(struct mm_struct *mm,
-					    unsigned long addr, pud_t *pudp,
-					    pud_t pud)
+static inline void page_table_check_puds_set(struct mm_struct *mm,
+		pud_t *pudp, pud_t pud, unsigned int nr)
 {
 	if (static_branch_likely(&page_table_check_disabled))
 		return;
 
-	__page_table_check_pud_set(mm, addr, pudp, pud);
+	__page_table_check_puds_set(mm, pudp, pud, nr);
 }
 
 static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
@@ -123,36 +114,30 @@ static inline void page_table_check_free(struct page *page, unsigned int order)
 {
 }
 
-static inline void page_table_check_pte_clear(struct mm_struct *mm,
-					      unsigned long addr, pte_t pte)
+static inline void page_table_check_pte_clear(struct mm_struct *mm, pte_t pte)
 {
 }
 
-static inline void page_table_check_pmd_clear(struct mm_struct *mm,
-					      unsigned long addr, pmd_t pmd)
+static inline void page_table_check_pmd_clear(struct mm_struct *mm, pmd_t pmd)
 {
 }
 
-static inline void page_table_check_pud_clear(struct mm_struct *mm,
-					      unsigned long addr, pud_t pud)
+static inline void page_table_check_pud_clear(struct mm_struct *mm, pud_t pud)
 {
 }
 
-static inline void page_table_check_pte_set(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep,
-					    pte_t pte)
+static inline void page_table_check_ptes_set(struct mm_struct *mm,
+		pte_t *ptep, pte_t pte, unsigned int nr)
 {
 }
 
-static inline void page_table_check_pmd_set(struct mm_struct *mm,
-					    unsigned long addr, pmd_t *pmdp,
-					    pmd_t pmd)
+static inline void page_table_check_pmds_set(struct mm_struct *mm,
+		pmd_t *pmdp, pmd_t pmd, unsigned int nr)
 {
 }
 
-static inline void page_table_check_pud_set(struct mm_struct *mm,
-					    unsigned long addr, pud_t *pudp,
-					    pud_t pud)
+static inline void page_table_check_puds_set(struct mm_struct *mm,
+		pud_t *pudp, pud_t pud, unsigned int nr)
 {
 }
 
@@ -163,4 +148,8 @@ static inline void page_table_check_pte_clear_range(struct mm_struct *mm,
 }
 
 #endif /* CONFIG_PAGE_TABLE_CHECK */
+
+#define page_table_check_pmd_set(mm, pmdp, pmd)	page_table_check_pmds_set(mm, pmdp, pmd, 1)
+#define page_table_check_pud_set(mm, pudp, pud)	page_table_check_puds_set(mm, pudp, pud, 1)
+
 #endif /* __LINUX_PAGE_TABLE_CHECK_H */
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index e83c4c095041..e046278a01fa 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -13,22 +13,38 @@
 
 #include <linux/types.h>
 
-#define PB_migratetype_bits 3
 /* Bit indices that affect a whole block of pages */
 enum pageblock_bits {
-	PB_migrate,
-	PB_migrate_end = PB_migrate + PB_migratetype_bits - 1,
-			/* 3 bits required for migrate types */
-	PB_migrate_skip,/* If set the block is skipped by compaction */
+	PB_migrate_0,
+	PB_migrate_1,
+	PB_migrate_2,
+	PB_compact_skip,/* If set the block is skipped by compaction */
 
+#ifdef CONFIG_MEMORY_ISOLATION
+	/*
+	 * Pageblock isolation is represented with a separate bit, so that
+	 * the migratetype of a block is not overwritten by isolation.
+	 */
+	PB_migrate_isolate, /* If set the block is isolated */
+#endif
 	/*
 	 * Assume the bits will always align on a word. If this assumption
 	 * changes then get/set pageblock needs updating.
 	 */
-	NR_PAGEBLOCK_BITS
+	__NR_PAGEBLOCK_BITS
 };
 
-#ifdef CONFIG_HUGETLB_PAGE
+#define NR_PAGEBLOCK_BITS (roundup_pow_of_two(__NR_PAGEBLOCK_BITS))
+
+#define MIGRATETYPE_MASK (BIT(PB_migrate_0)|BIT(PB_migrate_1)|BIT(PB_migrate_2))
+
+#ifdef CONFIG_MEMORY_ISOLATION
+#define MIGRATETYPE_AND_ISO_MASK (MIGRATETYPE_MASK | BIT(PB_migrate_isolate))
+#else
+#define MIGRATETYPE_AND_ISO_MASK MIGRATETYPE_MASK
+#endif
+
+#if defined(CONFIG_HUGETLB_PAGE)
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
 
@@ -41,14 +57,18 @@ extern unsigned int pageblock_order;
  * Huge pages are a constant size, but don't exceed the maximum allocation
  * granularity.
  */
-#define pageblock_order		min_t(unsigned int, HUGETLB_PAGE_ORDER, MAX_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HUGETLB_PAGE_ORDER, PAGE_BLOCK_MAX_ORDER)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
-#else /* CONFIG_HUGETLB_PAGE */
+#elif defined(CONFIG_TRANSPARENT_HUGEPAGE)
+
+#define pageblock_order		MIN_T(unsigned int, HPAGE_PMD_ORDER, PAGE_BLOCK_MAX_ORDER)
 
-/* If huge pages are not used, group by MAX_ORDER_NR_PAGES */
-#define pageblock_order		MAX_ORDER
+#else /* CONFIG_TRANSPARENT_HUGEPAGE */
+
+/* If huge pages are not used, group by PAGE_BLOCK_MAX_ORDER */
+#define pageblock_order		PAGE_BLOCK_MAX_ORDER
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
@@ -61,27 +81,23 @@ extern unsigned int pageblock_order;
 /* Forward declaration */
 struct page;
 
-unsigned long get_pfnblock_flags_mask(const struct page *page,
-				unsigned long pfn,
-				unsigned long mask);
-
-void set_pfnblock_flags_mask(struct page *page,
-				unsigned long flags,
-				unsigned long pfn,
-				unsigned long mask);
+enum migratetype get_pfnblock_migratetype(const struct page *page,
+					  unsigned long pfn);
+bool get_pfnblock_bit(const struct page *page, unsigned long pfn,
+		      enum pageblock_bits pb_bit);
+void set_pfnblock_bit(const struct page *page, unsigned long pfn,
+		      enum pageblock_bits pb_bit);
+void clear_pfnblock_bit(const struct page *page, unsigned long pfn,
+			enum pageblock_bits pb_bit);
 
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
-	get_pfnblock_flags_mask(page, page_to_pfn(page),	\
-			(1 << (PB_migrate_skip)))
+	get_pfnblock_bit(page, page_to_pfn(page), PB_compact_skip)
 #define clear_pageblock_skip(page) \
-	set_pfnblock_flags_mask(page, 0, page_to_pfn(page),	\
-			(1 << PB_migrate_skip))
+	clear_pfnblock_bit(page, page_to_pfn(page), PB_compact_skip)
 #define set_pageblock_skip(page) \
-	set_pfnblock_flags_mask(page, (1 << PB_migrate_skip),	\
-			page_to_pfn(page),			\
-			(1 << PB_migrate_skip))
+	set_pfnblock_bit(page, page_to_pfn(page), PB_compact_skip)
 #else
 static inline bool get_pageblock_skip(struct page *page)
 {
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 716953ee1ebd..31a848485ad9 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -32,14 +32,19 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		pgoff_t start, pgoff_t end);
 int kiocb_invalidate_pages(struct kiocb *iocb, size_t count);
 void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count);
+int filemap_invalidate_pages(struct address_space *mapping,
+			     loff_t pos, loff_t end, bool nowait);
 
 int write_inode_now(struct inode *, int sync);
 int filemap_fdatawrite(struct address_space *);
 int filemap_flush(struct address_space *);
+int filemap_flush_nr(struct address_space *mapping, long *nr_to_write);
 int filemap_fdatawait_keep_errors(struct address_space *mapping);
 int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend);
 int filemap_fdatawait_range_keep_errors(struct address_space *mapping,
 		loff_t start_byte, loff_t end_byte);
+int filemap_invalidate_inode(struct inode *inode, bool flush,
+			     loff_t start, loff_t end);
 
 static inline int filemap_fdatawait(struct address_space *mapping)
 {
@@ -49,14 +54,10 @@ static inline int filemap_fdatawait(struct address_space *mapping)
 bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend);
 int filemap_write_and_wait_range(struct address_space *mapping,
 		loff_t lstart, loff_t lend);
-int __filemap_fdatawrite_range(struct address_space *mapping,
-		loff_t start, loff_t end, int sync_mode);
 int filemap_fdatawrite_range(struct address_space *mapping,
 		loff_t start, loff_t end);
 int filemap_check_errors(struct address_space *mapping);
 void __filemap_set_wb_err(struct address_space *mapping, int err);
-int filemap_fdatawrite_wbc(struct address_space *mapping,
-			   struct writeback_control *wbc);
 int kiocb_write_and_wait(struct kiocb *iocb, size_t count);
 
 static inline int filemap_write_and_wait(struct address_space *mapping)
@@ -136,7 +137,7 @@ static inline int inode_drain_writes(struct inode *inode)
 	return filemap_write_and_wait(inode->i_mapping);
 }
 
-static inline bool mapping_empty(struct address_space *mapping)
+static inline bool mapping_empty(const struct address_space *mapping)
 {
 	return xa_empty(&mapping->i_pages);
 }
@@ -162,7 +163,7 @@ static inline bool mapping_empty(struct address_space *mapping)
  * refcount and the referenced bit, which will be elevated or set in
  * the process of adding new cache pages to an inode.
  */
-static inline bool mapping_shrinkable(struct address_space *mapping)
+static inline bool mapping_shrinkable(const struct address_space *mapping)
 {
 	void *head;
 
@@ -202,9 +203,24 @@ enum mapping_flags {
 	AS_EXITING	= 4, 	/* final truncate in progress */
 	/* writeback related tags are not used */
 	AS_NO_WRITEBACK_TAGS = 5,
-	AS_LARGE_FOLIO_SUPPORT = 6,
+	AS_RELEASE_ALWAYS = 6,	/* Call ->release_folio(), even if no private data */
+	AS_STABLE_WRITES = 7,	/* must wait for writeback before modifying
+				   folio contents */
+	AS_INACCESSIBLE = 8,	/* Do not attempt direct R/W access to the mapping */
+	AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9,
+	AS_KERNEL_FILE = 10,	/* mapping for a fake kernel file that shouldn't
+				   account usage to user cgroups */
+	/* Bits 16-25 are used for FOLIO_ORDER */
+	AS_FOLIO_ORDER_BITS = 5,
+	AS_FOLIO_ORDER_MIN = 16,
+	AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS,
 };
 
+#define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1)
+#define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN)
+#define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX)
+#define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK)
+
 /**
  * mapping_set_error - record a writeback error in the address_space
  * @mapping: the mapping in which an error should be set
@@ -248,7 +264,7 @@ static inline void mapping_clear_unevictable(struct address_space *mapping)
 	clear_bit(AS_UNEVICTABLE, &mapping->flags);
 }
 
-static inline bool mapping_unevictable(struct address_space *mapping)
+static inline bool mapping_unevictable(const struct address_space *mapping)
 {
 	return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags);
 }
@@ -258,7 +274,7 @@ static inline void mapping_set_exiting(struct address_space *mapping)
 	set_bit(AS_EXITING, &mapping->flags);
 }
 
-static inline int mapping_exiting(struct address_space *mapping)
+static inline int mapping_exiting(const struct address_space *mapping)
 {
 	return test_bit(AS_EXITING, &mapping->flags);
 }
@@ -268,18 +284,74 @@ static inline void mapping_set_no_writeback_tags(struct address_space *mapping)
 	set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
 }
 
-static inline int mapping_use_writeback_tags(struct address_space *mapping)
+static inline int mapping_use_writeback_tags(const struct address_space *mapping)
 {
 	return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags);
 }
 
-static inline gfp_t mapping_gfp_mask(struct address_space * mapping)
+static inline bool mapping_release_always(const struct address_space *mapping)
+{
+	return test_bit(AS_RELEASE_ALWAYS, &mapping->flags);
+}
+
+static inline void mapping_set_release_always(struct address_space *mapping)
+{
+	set_bit(AS_RELEASE_ALWAYS, &mapping->flags);
+}
+
+static inline void mapping_clear_release_always(struct address_space *mapping)
+{
+	clear_bit(AS_RELEASE_ALWAYS, &mapping->flags);
+}
+
+static inline bool mapping_stable_writes(const struct address_space *mapping)
+{
+	return test_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_set_stable_writes(struct address_space *mapping)
+{
+	set_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_clear_stable_writes(struct address_space *mapping)
+{
+	clear_bit(AS_STABLE_WRITES, &mapping->flags);
+}
+
+static inline void mapping_set_inaccessible(struct address_space *mapping)
+{
+	/*
+	 * It's expected inaccessible mappings are also unevictable. Compaction
+	 * migrate scanner (isolate_migratepages_block()) relies on this to
+	 * reduce page locking.
+	 */
+	set_bit(AS_UNEVICTABLE, &mapping->flags);
+	set_bit(AS_INACCESSIBLE, &mapping->flags);
+}
+
+static inline bool mapping_inaccessible(const struct address_space *mapping)
+{
+	return test_bit(AS_INACCESSIBLE, &mapping->flags);
+}
+
+static inline void mapping_set_writeback_may_deadlock_on_reclaim(struct address_space *mapping)
+{
+	set_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags);
+}
+
+static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct address_space *mapping)
+{
+	return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags);
+}
+
+static inline gfp_t mapping_gfp_mask(const struct address_space *mapping)
 {
 	return mapping->gfp_mask;
 }
 
 /* Restricts the given gfp_mask to what the mapping allows. */
-static inline gfp_t mapping_gfp_constraint(struct address_space *mapping,
+static inline gfp_t mapping_gfp_constraint(const struct address_space *mapping,
 		gfp_t gfp_mask)
 {
 	return mapping_gfp_mask(mapping) & gfp_mask;
@@ -294,9 +366,84 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
 	m->gfp_mask = mask;
 }
 
+/*
+ * There are some parts of the kernel which assume that PMD entries
+ * are exactly HPAGE_PMD_ORDER.  Those should be fixed, but until then,
+ * limit the maximum allocation order to PMD size.  I'm not aware of any
+ * assumptions about maximum order if THP are disabled, but 8 seems like
+ * a good order (that's 1MB if you're using 4kB pages)
+ */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+#define PREFERRED_MAX_PAGECACHE_ORDER	HPAGE_PMD_ORDER
+#else
+#define PREFERRED_MAX_PAGECACHE_ORDER	8
+#endif
+
+/*
+ * xas_split_alloc() does not support arbitrary orders. This implies no
+ * 512MB THP on ARM64 with 64KB base page size.
+ */
+#define MAX_XAS_ORDER		(XA_CHUNK_SHIFT * 2 - 1)
+#define MAX_PAGECACHE_ORDER	min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER)
+
+/*
+ * mapping_max_folio_size_supported() - Check the max folio size supported
+ *
+ * The filesystem should call this function at mount time if there is a
+ * requirement on the folio mapping size in the page cache.
+ */
+static inline size_t mapping_max_folio_size_supported(void)
+{
+	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER);
+	return PAGE_SIZE;
+}
+
+/*
+ * mapping_set_folio_order_range() - Set the orders supported by a file.
+ * @mapping: The address space of the file.
+ * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive).
+ * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive).
+ *
+ * The filesystem should call this function in its inode constructor to
+ * indicate which base size (min) and maximum size (max) of folio the VFS
+ * can use to cache the contents of the file.  This should only be used
+ * if the filesystem needs special handling of folio sizes (ie there is
+ * something the core cannot know).
+ * Do not tune it based on, eg, i_size.
+ *
+ * Context: This should not be called while the inode is active as it
+ * is non-atomic.
+ */
+static inline void mapping_set_folio_order_range(struct address_space *mapping,
+						 unsigned int min,
+						 unsigned int max)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return;
+
+	if (min > MAX_PAGECACHE_ORDER)
+		min = MAX_PAGECACHE_ORDER;
+
+	if (max > MAX_PAGECACHE_ORDER)
+		max = MAX_PAGECACHE_ORDER;
+
+	if (max < min)
+		max = min;
+
+	mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) |
+		(min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX);
+}
+
+static inline void mapping_set_folio_min_order(struct address_space *mapping,
+					       unsigned int min)
+{
+	mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER);
+}
+
 /**
  * mapping_set_large_folios() - Indicate the file supports large folios.
- * @mapping: The file.
+ * @mapping: The address space of the file.
  *
  * The filesystem should call this function in its inode constructor to
  * indicate that the VFS can use large folios to cache the contents of
@@ -307,20 +454,72 @@ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask)
  */
 static inline void mapping_set_large_folios(struct address_space *mapping)
 {
-	__set_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+	mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER);
+}
+
+static inline unsigned int
+mapping_max_folio_order(const struct address_space *mapping)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 0;
+	return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX;
+}
+
+static inline unsigned int
+mapping_min_folio_order(const struct address_space *mapping)
+{
+	if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE))
+		return 0;
+	return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN;
+}
+
+static inline unsigned long
+mapping_min_folio_nrpages(const struct address_space *mapping)
+{
+	return 1UL << mapping_min_folio_order(mapping);
+}
+
+static inline unsigned long
+mapping_min_folio_nrbytes(const struct address_space *mapping)
+{
+	return mapping_min_folio_nrpages(mapping) << PAGE_SHIFT;
+}
+
+/**
+ * mapping_align_index() - Align index for this mapping.
+ * @mapping: The address_space.
+ * @index: The page index.
+ *
+ * The index of a folio must be naturally aligned.  If you are adding a
+ * new folio to the page cache and need to know what index to give it,
+ * call this function.
+ */
+static inline pgoff_t mapping_align_index(const struct address_space *mapping,
+					  pgoff_t index)
+{
+	return round_down(index, mapping_min_folio_nrpages(mapping));
 }
 
 /*
  * Large folio support currently depends on THP.  These dependencies are
  * being worked on but are not yet fixed.
  */
-static inline bool mapping_large_folio_support(struct address_space *mapping)
+static inline bool mapping_large_folio_support(const struct address_space *mapping)
 {
-	return IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
-		test_bit(AS_LARGE_FOLIO_SUPPORT, &mapping->flags);
+	/* AS_FOLIO_ORDER is only reasonable for pagecache folios */
+	VM_WARN_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON,
+			"Anonymous mapping always supports large folio");
+
+	return mapping_max_folio_order(mapping) > 0;
 }
 
-static inline int filemap_nr_thps(struct address_space *mapping)
+/* Return the maximum folio size for this pagecache mapping, in bytes. */
+static inline size_t mapping_max_folio_size(const struct address_space *mapping)
+{
+	return PAGE_SIZE << mapping_max_folio_order(mapping);
+}
+
+static inline int filemap_nr_thps(const struct address_space *mapping)
 {
 #ifdef CONFIG_READ_ONLY_THP_FOR_FS
 	return atomic_read(&mapping->nr_thps);
@@ -349,44 +548,25 @@ static inline void filemap_nr_thps_dec(struct address_space *mapping)
 #endif
 }
 
-struct address_space *page_mapping(struct page *);
-struct address_space *folio_mapping(struct folio *);
-struct address_space *swapcache_mapping(struct folio *);
+struct address_space *folio_mapping(const struct folio *folio);
 
 /**
- * folio_file_mapping - Find the mapping this folio belongs to.
+ * folio_flush_mapping - Find the file mapping this folio belongs to.
  * @folio: The folio.
  *
  * For folios which are in the page cache, return the mapping that this
- * page belongs to.  Folios in the swap cache return the mapping of the
- * swap file or swap device where the data is stored.  This is different
- * from the mapping returned by folio_mapping().  The only reason to
- * use it is if, like NFS, you return 0 from ->activate_swapfile.
+ * page belongs to.  Anonymous folios return NULL, even if they're in
+ * the swap cache.  Other kinds of folio also return NULL.
  *
- * Do not call this for folios which aren't in the page cache or swap cache.
+ * This is ONLY used by architecture cache flushing code.  If you aren't
+ * writing cache flushing code, you want either folio_mapping() or
+ * folio_file_mapping().
  */
-static inline struct address_space *folio_file_mapping(struct folio *folio)
+static inline struct address_space *folio_flush_mapping(struct folio *folio)
 {
 	if (unlikely(folio_test_swapcache(folio)))
-		return swapcache_mapping(folio);
-
-	return folio->mapping;
-}
-
-static inline struct address_space *page_file_mapping(struct page *page)
-{
-	return folio_file_mapping(page_folio(page));
-}
-
-/*
- * For file cache pages, return the address_space, otherwise return NULL
- */
-static inline struct address_space *page_mapping_file(struct page *page)
-{
-	struct folio *folio = page_folio(page);
-
-	if (unlikely(folio_test_swapcache(folio)))
 		return NULL;
+
 	return folio_mapping(folio);
 }
 
@@ -471,22 +651,22 @@ static inline void *detach_page_private(struct page *page)
 }
 
 #ifdef CONFIG_NUMA
-struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order);
+struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy);
 #else
-static inline struct folio *filemap_alloc_folio(gfp_t gfp, unsigned int order)
+static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order,
+		struct mempolicy *policy)
 {
-	return folio_alloc(gfp, order);
+	return folio_alloc_noprof(gfp, order);
 }
 #endif
 
-static inline struct page *__page_cache_alloc(gfp_t gfp)
-{
-	return &filemap_alloc_folio(gfp, 0)->page;
-}
+#define filemap_alloc_folio(...)				\
+	alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__))
 
-static inline struct page *page_cache_alloc(struct address_space *x)
+static inline struct page *__page_cache_alloc(gfp_t gfp)
 {
-	return __page_cache_alloc(mapping_gfp_mask(x));
+	return &filemap_alloc_folio(gfp, 0, NULL)->page;
 }
 
 static inline gfp_t readahead_gfp_mask(struct address_space *x)
@@ -501,22 +681,114 @@ pgoff_t page_cache_next_miss(struct address_space *mapping,
 pgoff_t page_cache_prev_miss(struct address_space *mapping,
 			     pgoff_t index, unsigned long max_scan);
 
-#define FGP_ACCESSED		0x00000001
-#define FGP_LOCK		0x00000002
-#define FGP_CREAT		0x00000004
-#define FGP_WRITE		0x00000008
-#define FGP_NOFS		0x00000010
-#define FGP_NOWAIT		0x00000020
-#define FGP_FOR_MMAP		0x00000040
-#define FGP_STABLE		0x00000080
+/**
+ * typedef fgf_t - Flags for getting folios from the page cache.
+ *
+ * Most users of the page cache will not need to use these flags;
+ * there are convenience functions such as filemap_get_folio() and
+ * filemap_lock_folio().  For users which need more control over exactly
+ * what is done with the folios, these flags to __filemap_get_folio()
+ * are available.
+ *
+ * * %FGP_ACCESSED - The folio will be marked accessed.
+ * * %FGP_LOCK - The folio is returned locked.
+ * * %FGP_CREAT - If no folio is present then a new folio is allocated,
+ *   added to the page cache and the VM's LRU list.  The folio is
+ *   returned locked.
+ * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the
+ *   folio is already in cache.  If the folio was allocated, unlock it
+ *   before returning so the caller can do the same dance.
+ * * %FGP_WRITE - The folio will be written to by the caller.
+ * * %FGP_NOFS - __GFP_FS will get cleared in gfp.
+ * * %FGP_NOWAIT - Don't block on the folio lock.
+ * * %FGP_STABLE - Wait for the folio to be stable (finished writeback)
+ * * %FGP_DONTCACHE - Uncached buffered IO
+ * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin()
+ *   implementation.
+ */
+typedef unsigned int __bitwise fgf_t;
+
+#define FGP_ACCESSED		((__force fgf_t)0x00000001)
+#define FGP_LOCK		((__force fgf_t)0x00000002)
+#define FGP_CREAT		((__force fgf_t)0x00000004)
+#define FGP_WRITE		((__force fgf_t)0x00000008)
+#define FGP_NOFS		((__force fgf_t)0x00000010)
+#define FGP_NOWAIT		((__force fgf_t)0x00000020)
+#define FGP_FOR_MMAP		((__force fgf_t)0x00000040)
+#define FGP_STABLE		((__force fgf_t)0x00000080)
+#define FGP_DONTCACHE		((__force fgf_t)0x00000100)
+#define FGF_GET_ORDER(fgf)	(((__force unsigned)fgf) >> 26)	/* top 6 bits */
 
 #define FGP_WRITEBEGIN		(FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE)
 
+static inline unsigned int filemap_get_order(size_t size)
+{
+	unsigned int shift = ilog2(size);
+
+	if (shift <= PAGE_SHIFT)
+		return 0;
+
+	return shift - PAGE_SHIFT;
+}
+
+/**
+ * fgf_set_order - Encode a length in the fgf_t flags.
+ * @size: The suggested size of the folio to create.
+ *
+ * The caller of __filemap_get_folio() can use this to suggest a preferred
+ * size for the folio that is created.  If there is already a folio at
+ * the index, it will be returned, no matter what its size.  If a folio
+ * is freshly created, it may be of a different size than requested
+ * due to alignment constraints, memory pressure, or the presence of
+ * other folios at nearby indices.
+ */
+static inline fgf_t fgf_set_order(size_t size)
+{
+	unsigned int order = filemap_get_order(size);
+
+	if (!order)
+		return 0;
+	return (__force fgf_t)(order << 26);
+}
+
 void *filemap_get_entry(struct address_space *mapping, pgoff_t index);
-struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
-		int fgp_flags, gfp_t gfp);
+struct folio *__filemap_get_folio_mpol(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy);
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
-		int fgp_flags, gfp_t gfp);
+		fgf_t fgp_flags, gfp_t gfp);
+
+static inline struct folio *__filemap_get_folio(struct address_space *mapping,
+		pgoff_t index, fgf_t fgf_flags, gfp_t gfp)
+{
+	return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL);
+}
+
+/**
+ * write_begin_get_folio - Get folio for write_begin with flags.
+ * @iocb: The kiocb passed from write_begin (may be NULL).
+ * @mapping: The address space to search.
+ * @index: The page cache index.
+ * @len: Length of data being written.
+ *
+ * This is a helper for filesystem write_begin() implementations.
+ * It wraps __filemap_get_folio(), setting appropriate flags in
+ * the write begin context.
+ *
+ * Return: A folio or an ERR_PTR.
+ */
+static inline struct folio *write_begin_get_folio(const struct kiocb *iocb,
+		  struct address_space *mapping, pgoff_t index, size_t len)
+{
+        fgf_t fgp_flags = FGP_WRITEBEGIN;
+
+        fgp_flags |= fgf_set_order(len);
+
+        if (iocb && iocb->ki_flags & IOCB_DONTCACHE)
+                fgp_flags |= FGP_DONTCACHE;
+
+        return __filemap_get_folio(mapping, index, fgp_flags,
+                                   mapping_gfp_mask(mapping));
+}
 
 /**
  * filemap_get_folio - Find and get a folio.
@@ -590,7 +862,7 @@ static inline struct page *find_get_page(struct address_space *mapping,
 }
 
 static inline struct page *find_get_page_flags(struct address_space *mapping,
-					pgoff_t offset, int fgp_flags)
+					pgoff_t offset, fgf_t fgp_flags)
 {
 	return pagecache_get_page(mapping, offset, fgp_flags, 0);
 }
@@ -646,7 +918,8 @@ static inline struct page *find_or_create_page(struct address_space *mapping,
  * @mapping: target address_space
  * @index: the page index
  *
- * Same as grab_cache_page(), but do not wait if the page is unavailable.
+ * Returns locked page at given index in given cache, creating it if
+ * needed, but do not wait if the page is locked or to reclaim memory.
  * This is intended for speculative data generators, where the data can
  * be regenerated if the page couldn't be grabbed.  This routine should
  * be safe to call while holding the lock for another page.
@@ -662,35 +935,26 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
 			mapping_gfp_mask(mapping));
 }
 
-#define swapcache_index(folio)	__page_file_index(&(folio)->page)
-
 /**
- * folio_index - File index of a folio.
- * @folio: The folio.
- *
- * For a folio which is either in the page cache or the swap cache,
- * return its index within the address_space it belongs to.  If you know
- * the page is definitely in the page cache, you can look at the folio's
- * index directly.
+ * folio_next_index - Get the index of the next folio.
+ * @folio: The current folio.
  *
- * Return: The index (offset in units of pages) of a folio in its file.
+ * Return: The index of the folio which follows this folio in the file.
  */
-static inline pgoff_t folio_index(struct folio *folio)
+static inline pgoff_t folio_next_index(const struct folio *folio)
 {
-        if (unlikely(folio_test_swapcache(folio)))
-                return swapcache_index(folio);
-        return folio->index;
+	return folio->index + folio_nr_pages(folio);
 }
 
 /**
- * folio_next_index - Get the index of the next folio.
+ * folio_next_pos - Get the file position of the next folio.
  * @folio: The current folio.
  *
- * Return: The index of the folio which follows this folio in the file.
+ * Return: The position of the folio which follows this folio in the file.
  */
-static inline pgoff_t folio_next_index(struct folio *folio)
+static inline loff_t folio_next_pos(const struct folio *folio)
 {
-	return folio->index + folio_nr_pages(folio);
+	return (loff_t)folio_next_index(folio) << PAGE_SHIFT;
 }
 
 /**
@@ -705,9 +969,6 @@ static inline pgoff_t folio_next_index(struct folio *folio)
  */
 static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
 {
-	/* HugeTLBfs indexes the page cache in units of hpage_size */
-	if (folio_test_hugetlb(folio))
-		return &folio->page;
 	return folio_page(folio, index & (folio_nr_pages(folio) - 1));
 }
 
@@ -716,30 +977,14 @@ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index)
  * @folio: The folio.
  * @index: The page index within the file.
  *
- * Context: The caller should have the page locked in order to prevent
- * (eg) shmem from moving the page between the page cache and swap cache
- * and changing its index in the middle of the operation.
+ * Context: The caller should have the folio locked and ensure
+ * e.g., shmem did not move this folio to the swap cache.
  * Return: true or false.
  */
-static inline bool folio_contains(struct folio *folio, pgoff_t index)
+static inline bool folio_contains(const struct folio *folio, pgoff_t index)
 {
-	/* HugeTLBfs indexes the page cache in units of hpage_size */
-	if (folio_test_hugetlb(folio))
-		return folio->index == index;
-	return index - folio_index(folio) < folio_nr_pages(folio);
-}
-
-/*
- * Given the page we found in the page cache, return the page corresponding
- * to this index in the file
- */
-static inline struct page *find_subpage(struct page *head, pgoff_t index)
-{
-	/* HugeTLBfs wants the head page regardless */
-	if (PageHuge(head))
-		return head;
-
-	return head + (index & (thp_nr_pages(head) - 1));
+	VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio);
+	return index - folio->index < folio_nr_pages(folio);
 }
 
 unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
@@ -748,18 +993,8 @@ unsigned filemap_get_folios_contig(struct address_space *mapping,
 		pgoff_t *start, pgoff_t end, struct folio_batch *fbatch);
 unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch);
-
-struct page *grab_cache_page_write_begin(struct address_space *mapping,
-			pgoff_t index);
-
-/*
- * Returns locked page at given index in given cache, creating it if needed.
- */
-static inline struct page *grab_cache_page(struct address_space *mapping,
-								pgoff_t index)
-{
-	return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
-}
+unsigned filemap_get_folios_dirty(struct address_space *mapping,
+		pgoff_t *start, pgoff_t end, struct folio_batch *fbatch);
 
 struct folio *read_cache_folio(struct address_space *, pgoff_t index,
 		filler_t *filler, struct file *file);
@@ -782,36 +1017,34 @@ static inline struct folio *read_mapping_folio(struct address_space *mapping,
 	return read_cache_folio(mapping, index, NULL, file);
 }
 
-/*
- * Get index of the page within radix-tree (but not for hugetlb pages).
- * (TODO: remove once hugetlb pages will have ->index in PAGE_SIZE)
+/**
+ * page_pgoff - Calculate the logical page offset of this page.
+ * @folio: The folio containing this page.
+ * @page: The page which we need the offset of.
+ *
+ * For file pages, this is the offset from the beginning of the file
+ * in units of PAGE_SIZE.  For anonymous pages, this is the offset from
+ * the beginning of the anon_vma in units of PAGE_SIZE.  This will
+ * return nonsense for KSM pages.
+ *
+ * Context: Caller must have a reference on the folio or otherwise
+ * prevent it from being split or freed.
+ *
+ * Return: The offset in units of PAGE_SIZE.
  */
-static inline pgoff_t page_to_index(struct page *page)
+static inline pgoff_t page_pgoff(const struct folio *folio,
+		const struct page *page)
 {
-	struct page *head;
-
-	if (likely(!PageTransTail(page)))
-		return page->index;
-
-	head = compound_head(page);
-	/*
-	 *  We don't initialize ->index for tail pages: calculate based on
-	 *  head page
-	 */
-	return head->index + page - head;
+	return folio->index + folio_page_idx(folio, page);
 }
 
-extern pgoff_t hugetlb_basepage_index(struct page *page);
-
-/*
- * Get the offset in PAGE_SIZE (even for hugetlb pages).
- * (TODO: hugetlb pages should have ->index in PAGE_SIZE)
+/**
+ * folio_pos - Returns the byte position of this folio in its file.
+ * @folio: The folio.
  */
-static inline pgoff_t page_to_pgoff(struct page *page)
+static inline loff_t folio_pos(const struct folio *folio)
 {
-	if (unlikely(PageHuge(page)))
-		return hugetlb_basepage_index(page);
-	return page_to_index(page);
+	return ((loff_t)folio->index) * PAGE_SIZE;
 }
 
 /*
@@ -819,55 +1052,23 @@ static inline pgoff_t page_to_pgoff(struct page *page)
  */
 static inline loff_t page_offset(struct page *page)
 {
-	return ((loff_t)page->index) << PAGE_SHIFT;
-}
-
-static inline loff_t page_file_offset(struct page *page)
-{
-	return ((loff_t)page_index(page)) << PAGE_SHIFT;
-}
-
-/**
- * folio_pos - Returns the byte position of this folio in its file.
- * @folio: The folio.
- */
-static inline loff_t folio_pos(struct folio *folio)
-{
-	return page_offset(&folio->page);
-}
+	struct folio *folio = page_folio(page);
 
-/**
- * folio_file_pos - Returns the byte position of this folio in its file.
- * @folio: The folio.
- *
- * This differs from folio_pos() for folios which belong to a swap file.
- * NFS is the only filesystem today which needs to use folio_file_pos().
- */
-static inline loff_t folio_file_pos(struct folio *folio)
-{
-	return page_file_offset(&folio->page);
+	return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE;
 }
 
 /*
  * Get the offset in PAGE_SIZE (even for hugetlb folios).
- * (TODO: hugetlb folios should have ->index in PAGE_SIZE)
  */
-static inline pgoff_t folio_pgoff(struct folio *folio)
+static inline pgoff_t folio_pgoff(const struct folio *folio)
 {
-	if (unlikely(folio_test_hugetlb(folio)))
-		return hugetlb_basepage_index(&folio->page);
 	return folio->index;
 }
 
-extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
-				     unsigned long address);
-
-static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
-					unsigned long address)
+static inline pgoff_t linear_page_index(const struct vm_area_struct *vma,
+					const unsigned long address)
 {
 	pgoff_t pgoff;
-	if (unlikely(is_vm_hugetlb_page(vma)))
-		return linear_hugepage_index(vma, address);
 	pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
 	pgoff += vma->vm_pgoff;
 	return pgoff;
@@ -900,8 +1101,7 @@ static inline bool wake_page_match(struct wait_page_queue *wait_page,
 
 void __folio_lock(struct folio *folio);
 int __folio_lock_killable(struct folio *folio);
-bool __folio_lock_or_retry(struct folio *folio, struct mm_struct *mm,
-				unsigned int flags);
+vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf);
 void unlock_page(struct page *page);
 void folio_unlock(struct folio *folio);
 
@@ -925,7 +1125,7 @@ static inline bool folio_trylock(struct folio *folio)
 /*
  * Return true if the page was successfully locked
  */
-static inline int trylock_page(struct page *page)
+static inline bool trylock_page(struct page *page)
 {
 	return folio_trylock(page_folio(page));
 }
@@ -1005,11 +1205,13 @@ static inline int folio_lock_killable(struct folio *folio)
  * Return value and mmap_lock implications depend on flags; see
  * __folio_lock_or_retry().
  */
-static inline bool folio_lock_or_retry(struct folio *folio,
-		struct mm_struct *mm, unsigned int flags)
+static inline vm_fault_t folio_lock_or_retry(struct folio *folio,
+					     struct vm_fault *vmf)
 {
 	might_sleep();
-	return folio_trylock(folio) || __folio_lock_or_retry(folio, mm, flags);
+	if (!folio_trylock(folio))
+		return __folio_lock_or_retry(folio, vmf);
+	return 0;
 }
 
 /*
@@ -1039,29 +1241,16 @@ static inline int folio_wait_locked_killable(struct folio *folio)
 	return folio_wait_bit_killable(folio, PG_locked);
 }
 
-static inline void wait_on_page_locked(struct page *page)
-{
-	folio_wait_locked(page_folio(page));
-}
-
-static inline int wait_on_page_locked_killable(struct page *page)
-{
-	return folio_wait_locked_killable(page_folio(page));
-}
-
+void folio_end_read(struct folio *folio, bool success);
 void wait_on_page_writeback(struct page *page);
 void folio_wait_writeback(struct folio *folio);
 int folio_wait_writeback_killable(struct folio *folio);
 void end_page_writeback(struct page *page);
 void folio_end_writeback(struct folio *folio);
-void wait_for_stable_page(struct page *page);
+void folio_end_writeback_no_dropbehind(struct folio *folio);
+void folio_end_dropbehind(struct folio *folio);
 void folio_wait_stable(struct folio *folio);
 void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn);
-static inline void __set_page_dirty(struct page *page,
-		struct address_space *mapping, int warn)
-{
-	__folio_mark_dirty(page_folio(page), mapping, warn);
-}
 void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb);
 void __folio_cancel_dirty(struct folio *folio);
 static inline void folio_cancel_dirty(struct folio *folio)
@@ -1073,7 +1262,6 @@ static inline void folio_cancel_dirty(struct folio *folio)
 bool folio_clear_dirty_for_io(struct folio *folio);
 bool clear_page_dirty_for_io(struct page *page);
 void folio_invalidate(struct folio *folio, size_t offset, size_t length);
-int __set_page_dirty_nobuffers(struct page *page);
 bool noop_dirty_folio(struct address_space *mapping, struct folio *folio);
 
 #ifdef CONFIG_MIGRATION
@@ -1087,11 +1275,6 @@ void folio_wait_private_2(struct folio *folio);
 int folio_wait_private_2_killable(struct folio *folio);
 
 /*
- * Add an arbitrary waiter to a page's wait queue
- */
-void folio_add_wait_queue(struct folio *folio, wait_queue_entry_t *waiter);
-
-/*
  * Fault in userspace address range.
  */
 size_t fault_in_writeable(char __user *uaddr, size_t size);
@@ -1149,9 +1332,9 @@ static inline bool filemap_range_needs_writeback(struct address_space *mapping,
  * struct readahead_control - Describes a readahead request.
  *
  * A readahead request is for consecutive pages.  Filesystems which
- * implement the ->readahead method should call readahead_page() or
- * readahead_page_batch() in a loop and attempt to start I/O against
- * each page in the request.
+ * implement the ->readahead method should call readahead_folio() or
+ * __readahead_batch() in a loop and attempt to start reads into each
+ * folio in the request.
  *
  * Most of the fields in this struct are private and should be accessed
  * by the functions below.
@@ -1169,6 +1352,7 @@ struct readahead_control {
 	pgoff_t _index;
 	unsigned int _nr_pages;
 	unsigned int _batch_count;
+	bool dropbehind;
 	bool _workingset;
 	unsigned long _pflags;
 };
@@ -1218,8 +1402,7 @@ void page_cache_sync_readahead(struct address_space *mapping,
  * @mapping: address_space which holds the pagecache and I/O vectors
  * @ra: file_ra_state which holds the readahead state
  * @file: Used by the filesystem for authentication.
- * @folio: The folio at @index which triggered the readahead call.
- * @index: Index of first page to be read.
+ * @folio: The folio which triggered the readahead call.
  * @req_count: Total number of pages being read by the caller.
  *
  * page_cache_async_readahead() should be called when a page is used which
@@ -1230,9 +1413,9 @@ void page_cache_sync_readahead(struct address_space *mapping,
 static inline
 void page_cache_async_readahead(struct address_space *mapping,
 		struct file_ra_state *ra, struct file *file,
-		struct folio *folio, pgoff_t index, unsigned long req_count)
+		struct folio *folio, unsigned long req_count)
 {
-	DEFINE_READAHEAD(ractl, file, ra, mapping, index);
+	DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index);
 	page_cache_async_ra(&ractl, folio, req_count);
 }
 
@@ -1257,22 +1440,6 @@ static inline struct folio *__readahead_folio(struct readahead_control *ractl)
 }
 
 /**
- * readahead_page - Get the next page to read.
- * @ractl: The current readahead request.
- *
- * Context: The page is locked and has an elevated refcount.  The caller
- * should decreases the refcount once the page has been submitted for I/O
- * and unlock the page once all I/O to that page has completed.
- * Return: A pointer to the next page, or %NULL if we are done.
- */
-static inline struct page *readahead_page(struct readahead_control *ractl)
-{
-	struct folio *folio = __readahead_folio(ractl);
-
-	return &folio->page;
-}
-
-/**
  * readahead_folio - Get the next folio to read.
  * @ractl: The current readahead request.
  *
@@ -1294,7 +1461,7 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 {
 	unsigned int i = 0;
 	XA_STATE(xas, &rac->mapping->i_pages, 0);
-	struct page *page;
+	struct folio *folio;
 
 	BUG_ON(rac->_batch_count > rac->_nr_pages);
 	rac->_nr_pages -= rac->_batch_count;
@@ -1303,13 +1470,12 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 
 	xas_set(&xas, rac->_index);
 	rcu_read_lock();
-	xas_for_each(&xas, page, rac->_index + rac->_nr_pages - 1) {
-		if (xas_retry(&xas, page))
+	xas_for_each(&xas, folio, rac->_index + rac->_nr_pages - 1) {
+		if (xas_retry(&xas, folio))
 			continue;
-		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		VM_BUG_ON_PAGE(PageTail(page), page);
-		array[i++] = page;
-		rac->_batch_count += thp_nr_pages(page);
+		VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
+		array[i++] = folio_page(folio, 0);
+		rac->_batch_count += folio_nr_pages(folio);
 		if (i == array_sz)
 			break;
 	}
@@ -1319,24 +1485,10 @@ static inline unsigned int __readahead_batch(struct readahead_control *rac,
 }
 
 /**
- * readahead_page_batch - Get a batch of pages to read.
- * @rac: The current readahead request.
- * @array: An array of pointers to struct page.
- *
- * Context: The pages are locked and have an elevated refcount.  The caller
- * should decreases the refcount once the page has been submitted for I/O
- * and unlock the page once all I/O to that page has completed.
- * Return: The number of pages placed in the array.  0 indicates the request
- * is complete.
- */
-#define readahead_page_batch(rac, array)				\
-	__readahead_batch(rac, array, ARRAY_SIZE(array))
-
-/**
  * readahead_pos - The byte offset into the file of this readahead request.
  * @rac: The readahead request.
  */
-static inline loff_t readahead_pos(struct readahead_control *rac)
+static inline loff_t readahead_pos(const struct readahead_control *rac)
 {
 	return (loff_t)rac->_index * PAGE_SIZE;
 }
@@ -1345,7 +1497,7 @@ static inline loff_t readahead_pos(struct readahead_control *rac)
  * readahead_length - The number of bytes in this readahead request.
  * @rac: The readahead request.
  */
-static inline size_t readahead_length(struct readahead_control *rac)
+static inline size_t readahead_length(const struct readahead_control *rac)
 {
 	return rac->_nr_pages * PAGE_SIZE;
 }
@@ -1354,7 +1506,7 @@ static inline size_t readahead_length(struct readahead_control *rac)
  * readahead_index - The index of the first page in this readahead request.
  * @rac: The readahead request.
  */
-static inline pgoff_t readahead_index(struct readahead_control *rac)
+static inline pgoff_t readahead_index(const struct readahead_control *rac)
 {
 	return rac->_index;
 }
@@ -1363,7 +1515,7 @@ static inline pgoff_t readahead_index(struct readahead_control *rac)
  * readahead_count - The number of pages in this readahead request.
  * @rac: The readahead request.
  */
-static inline unsigned int readahead_count(struct readahead_control *rac)
+static inline unsigned int readahead_count(const struct readahead_control *rac)
 {
 	return rac->_nr_pages;
 }
@@ -1372,12 +1524,12 @@ static inline unsigned int readahead_count(struct readahead_control *rac)
  * readahead_batch_length - The number of bytes in the current batch.
  * @rac: The readahead request.
  */
-static inline size_t readahead_batch_length(struct readahead_control *rac)
+static inline size_t readahead_batch_length(const struct readahead_control *rac)
 {
 	return rac->_batch_count * PAGE_SIZE;
 }
 
-static inline unsigned long dir_pages(struct inode *inode)
+static inline unsigned long dir_pages(const struct inode *inode)
 {
 	return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >>
 			       PAGE_SHIFT;
@@ -1391,8 +1543,8 @@ static inline unsigned long dir_pages(struct inode *inode)
  * Return: the number of bytes in the folio up to EOF,
  * or -EFAULT if the folio was truncated.
  */
-static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio,
-					      struct inode *inode)
+static inline ssize_t folio_mkwrite_check_truncate(const struct folio *folio,
+						   const struct inode *inode)
 {
 	loff_t size = i_size_read(inode);
 	pgoff_t index = size >> PAGE_SHIFT;
@@ -1412,34 +1564,6 @@ static inline ssize_t folio_mkwrite_check_truncate(struct folio *folio,
 }
 
 /**
- * page_mkwrite_check_truncate - check if page was truncated
- * @page: the page to check
- * @inode: the inode to check the page against
- *
- * Returns the number of bytes in the page up to EOF,
- * or -EFAULT if the page was truncated.
- */
-static inline int page_mkwrite_check_truncate(struct page *page,
-					      struct inode *inode)
-{
-	loff_t size = i_size_read(inode);
-	pgoff_t index = size >> PAGE_SHIFT;
-	int offset = offset_in_page(size);
-
-	if (page->mapping != inode->i_mapping)
-		return -EFAULT;
-
-	/* page is wholly inside EOF */
-	if (page->index < index)
-		return PAGE_SIZE;
-	/* page is wholly past EOF */
-	if (page->index > index || !offset)
-		return -EFAULT;
-	/* page is partially inside EOF */
-	return offset;
-}
-
-/**
  * i_blocks_per_folio - How many blocks fit in this folio.
  * @inode: The inode which contains the blocks.
  * @folio: The folio.
@@ -1451,14 +1575,9 @@ static inline int page_mkwrite_check_truncate(struct page *page,
  * Return: The number of filesystem blocks covered by this folio.
  */
 static inline
-unsigned int i_blocks_per_folio(struct inode *inode, struct folio *folio)
+unsigned int i_blocks_per_folio(const struct inode *inode,
+				const struct folio *folio)
 {
 	return folio_size(folio) >> inode->i_blkbits;
 }
-
-static inline
-unsigned int i_blocks_per_page(struct inode *inode, struct page *page)
-{
-	return i_blocks_per_folio(inode, page_folio(page));
-}
 #endif /* _LINUX_PAGEMAP_H */
diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h
index f582f7213ea5..63be5a451627 100644
--- a/