Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 and cross-arch updates from Catalin Marinas:
 "Here's a slightly wider-spread set of updates for 5.9.

  Going outside the usual arch/arm64/ area is the removal of
  read_barrier_depends() series from Will and the MSI/IOMMU ID
  translation series from Lorenzo.

  The notable arm64 updates include ARMv8.4 TLBI range operations and
  translation level hint, time namespace support, and perf.

  Summary:

   - Removal of the tremendously unpopular read_barrier_depends()
     barrier, which is a NOP on all architectures apart from Alpha, in
     favour of allowing architectures to override READ_ONCE() and do
     whatever dance they need to do to ensure address dependencies
     provide LOAD -> LOAD/STORE ordering.

     This work also offers a potential solution if compilers are shown
     to convert LOAD -> LOAD address dependencies into control
     dependencies (e.g. under LTO), as weakly ordered architectures will
     effectively be able to upgrade READ_ONCE() to smp_load_acquire().
     The latter case is not used yet, but will be discussed further at
     LPC.

   - Make the MSI/IOMMU input/output ID translation PCI agnostic,
     augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID
     bus-specific parameter and apply the resulting changes to the
     device ID space provided by the Freescale FSL bus.

   - arm64 support for TLBI range operations and translation table level
     hints (part of the ARMv8.4 architecture version).

   - Time namespace support for arm64.

   - Export the virtual and physical address sizes in vmcoreinfo for
     makedumpfile and crash utilities.

   - CPU feature handling cleanups and checks for programmer errors
     (overlapping bit-fields).

   - ACPI updates for arm64: disallow AML accesses to EFI code regions
     and kernel memory.

   - perf updates for arm64.

   - Miscellaneous fixes and cleanups, most notably PLT counting
     optimisation for module loading, recordmcount fix to ignore
     relocations other than R_AARCH64_CALL26, CMA areas reserved for
     gigantic pages on 16K and 64K configurations.

   - Trivial typos, duplicate words"

Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org
Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits)
  arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack
  arm64/mm: save memory access in check_and_switch_context() fast switch path
  arm64: sigcontext.h: delete duplicated word
  arm64: ptrace.h: delete duplicated word
  arm64: pgtable-hwdef.h: delete duplicated words
  bus: fsl-mc: Add ACPI support for fsl-mc
  bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver
  of/irq: Make of_msi_map_rid() PCI bus agnostic
  of/irq: make of_msi_map_get_device_domain() bus agnostic
  dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus
  of/device: Add input id to of_dma_configure()
  of/iommu: Make of_map_rid() PCI agnostic
  ACPI/IORT: Add an input ID to acpi_dma_configure()
  ACPI/IORT: Remove useless PCI bus walk
  ACPI/IORT: Make iort_msi_map_rid() PCI agnostic
  ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic
  ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC
  arm64: enable time namespace support
  arm64/vdso: Restrict splitting VVAR VMA
  arm64/vdso: Handle faults on timens page
  ...

20 files changed, 302 insertions, 215 deletions

diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 5afb6ceb284f..a3abcc4b7d9f 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -588,8 +588,13 @@ bool acpi_dma_supported(struct acpi_device *adev);
 enum dev_dma_attr acpi_get_dma_attr(struct acpi_device *adev);
 int acpi_dma_get_range(struct device *dev, u64 *dma_addr, u64 *offset,
 		       u64 *size);
-int acpi_dma_configure(struct device *dev, enum dev_dma_attr attr);
-
+int acpi_dma_configure_id(struct device *dev, enum dev_dma_attr attr,
+			   const u32 *input_id);
+static inline int acpi_dma_configure(struct device *dev,
+				     enum dev_dma_attr attr)
+{
+	return acpi_dma_configure_id(dev, attr, NULL);
+}
 struct acpi_device *acpi_find_child_device(struct acpi_device *parent,
 					   u64 address, bool check_children);
 int acpi_is_root_bridge(acpi_handle);
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 44ec80e70518..74b0612601dd 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -45,6 +45,7 @@ mandatory-y += pci.h
 mandatory-y += percpu.h
 mandatory-y += pgalloc.h
 mandatory-y += preempt.h
+mandatory-y += rwonce.h
 mandatory-y += sections.h
 mandatory-y += serial.h
 mandatory-y += shmparam.h
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 2eacaf7d62f6..fec97dc34de7 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -13,7 +13,7 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/compiler.h>
+#include <asm/rwonce.h>
 
 #ifndef nop
 #define nop()	asm volatile ("nop")
@@ -46,10 +46,6 @@
 #define dma_wmb()	wmb()
 #endif
 
-#ifndef read_barrier_depends
-#define read_barrier_depends()		do { } while (0)
-#endif
-
 #ifndef __smp_mb
 #define __smp_mb()	mb()
 #endif
@@ -62,10 +58,6 @@
 #define __smp_wmb()	wmb()
 #endif
 
-#ifndef __smp_read_barrier_depends
-#define __smp_read_barrier_depends()	read_barrier_depends()
-#endif
-
 #ifdef CONFIG_SMP
 
 #ifndef smp_mb
@@ -80,10 +72,6 @@
 #define smp_wmb()	__smp_wmb()
 #endif
 
-#ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	__smp_read_barrier_depends()
-#endif
-
 #else	/* !CONFIG_SMP */
 
 #ifndef smp_mb
@@ -98,10 +86,6 @@
 #define smp_wmb()	barrier()
 #endif
 
-#ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	do { } while (0)
-#endif
-
 #endif	/* CONFIG_SMP */
 
 #ifndef __smp_store_mb
@@ -196,7 +180,6 @@ do {									\
 #define virt_mb() __smp_mb()
 #define virt_rmb() __smp_rmb()
 #define virt_wmb() __smp_wmb()
-#define virt_read_barrier_depends() __smp_read_barrier_depends()
 #define virt_store_mb(var, value) __smp_store_mb(var, value)
 #define virt_mb__before_atomic() __smp_mb__before_atomic()
 #define virt_mb__after_atomic()	__smp_mb__after_atomic()
diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h
new file mode 100644
index 000000000000..8d0a6280e982
--- /dev/null
+++ b/include/asm-generic/rwonce.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
+ *
+ * These two macros will also work on aggregate data types like structs or
+ * unions.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+#ifndef __ASM_GENERIC_RWONCE_H
+#define __ASM_GENERIC_RWONCE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler_types.h>
+#include <linux/kasan-checks.h>
+#include <linux/kcsan-checks.h>
+
+/*
+ * Yes, this permits 64-bit accesses on 32-bit architectures. These will
+ * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
+ * rely on the access being split into 2x32-bit accesses for a 32-bit quantity
+ * (e.g. a virtual address) and a strong prevailing wind.
+ */
+#define compiletime_assert_rwonce_type(t)					\
+	compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long),	\
+		"Unsupported access size for {READ,WRITE}_ONCE().")
+
+/*
+ * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
+ * atomicity. Note that this may result in tears!
+ */
+#ifndef __READ_ONCE
+#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
+#endif
+
+#define READ_ONCE(x)							\
+({									\
+	compiletime_assert_rwonce_type(x);				\
+	__READ_ONCE(x);							\
+})
+
+#define __WRITE_ONCE(x, val)						\
+do {									\
+	*(volatile typeof(x) *)&(x) = (val);				\
+} while (0)
+
+#define WRITE_ONCE(x, val)						\
+do {									\
+	compiletime_assert_rwonce_type(x);				\
+	__WRITE_ONCE(x, val);						\
+} while (0)
+
+static __no_sanitize_or_inline
+unsigned long __read_once_word_nocheck(const void *addr)
+{
+	return __READ_ONCE(*(unsigned long *)addr);
+}
+
+/*
+ * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
+ * word from memory atomically but without telling KASAN/KCSAN. This is
+ * usually used by unwinding code when walking the stack of a running process.
+ */
+#define READ_ONCE_NOCHECK(x)						\
+({									\
+	compiletime_assert(sizeof(x) == sizeof(unsigned long),		\
+		"Unsupported access size for READ_ONCE_NOCHECK().");	\
+	(typeof(x))__read_once_word_nocheck(&(x));			\
+})
+
+static __no_kasan_or_inline
+unsigned long read_word_at_a_time(const void *addr)
+{
+	kasan_check_read(addr, 1);
+	return *(unsigned long *)addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_GENERIC_RWONCE_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 3f1649a8cf55..ef75ec86f865 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -512,6 +512,38 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 }
 #endif
 
+/*
+ * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,
+ * and set corresponding cleared_*.
+ */
+static inline void tlb_flush_pte_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_ptes = 1;
+}
+
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_pmds = 1;
+}
+
+static inline void tlb_flush_pud_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_puds = 1;
+}
+
+static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_p4ds = 1;
+}
+
 #ifndef __tlb_remove_tlb_entry
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #endif
@@ -525,19 +557,17 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->cleared_ptes = 1;				\
+		tlb_flush_pte_range(tlb, address, PAGE_SIZE);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		__tlb_adjust_range(tlb, address, _sz);		\
 		if (_sz == PMD_SIZE)				\
-			tlb->cleared_pmds = 1;			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
 		else if (_sz == PUD_SIZE)			\
-			tlb->cleared_puds = 1;			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -551,8 +581,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
-		tlb->cleared_pmds = 1;					\
+		tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE);	\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
@@ -566,8 +595,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE);	\
-		tlb->cleared_puds = 1;					\
+		tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE);	\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
@@ -592,9 +620,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pte_free_tlb
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pmd_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
@@ -602,9 +629,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pud_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
@@ -612,9 +638,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_p4d_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index d661cd0ee64d..6d2c47489d90 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -905,6 +905,13 @@ static inline int acpi_dma_configure(struct device *dev,
 	return 0;
 }
 
+static inline int acpi_dma_configure_id(struct device *dev,
+					enum dev_dma_attr attr,
+					const u32 *input_id)
+{
+	return 0;
+}
+
 #define ACPI_PTR(_ptr)	(NULL)
 
 static inline void acpi_device_set_enumerated(struct acpi_device *adev)
diff --git a/include/linux/acpi_iort.h b/include/linux/acpi_iort.h
index 8e7e2ec37f1b..20a32120bb88 100644
--- a/include/linux/acpi_iort.h
+++ b/include/linux/acpi_iort.h
@@ -28,27 +28,29 @@ void iort_deregister_domain_token(int trans_id);
 struct fwnode_handle *iort_find_domain_token(int trans_id);
 #ifdef CONFIG_ACPI_IORT
 void acpi_iort_init(void);
-u32 iort_msi_map_rid(struct device *dev, u32 req_id);
-struct irq_domain *iort_get_device_domain(struct device *dev, u32 req_id);
+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);
 /* IOMMU interface */
 void iort_dma_setup(struct device *dev, u64 *dma_addr, u64 *size);
-const struct iommu_ops *iort_iommu_configure(struct device *dev);
+const struct iommu_ops *iort_iommu_configure_id(struct device *dev,
+						const u32 *id_in);
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head);
 #else
 static inline void acpi_iort_init(void) { }
-static inline u32 iort_msi_map_rid(struct device *dev, u32 req_id)
-{ return req_id; }
-static inline struct irq_domain *iort_get_device_domain(struct device *dev,
-							u32 req_id)
+static inline u32 iort_msi_map_id(struct device *dev, u32 id)
+{ return id; }
+static inline struct irq_domain *iort_get_device_domain(
+	struct device *dev, u32 id, enum irq_domain_bus_token bus_token)
 { return NULL; }
 static inline void acpi_configure_pmsi_domain(struct device *dev) { }
 /* IOMMU interface */
 static inline void iort_dma_setup(struct device *dev, u64 *dma_addr,
 				  u64 *size) { }
-static inline const struct iommu_ops *iort_iommu_configure(
-				      struct device *dev)
+static inline const struct iommu_ops *iort_iommu_configure_id(
+				      struct device *dev, const u32 *id_in)
 { return NULL; }
 static inline
 int iort_iommu_msi_get_resv_regions(struct device *dev, struct list_head *head)
diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 56d6a5c6e353..efcbde731f03 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -81,6 +81,28 @@
 			   ARM_SMCCC_SMC_32,				\
 			   0, 0x7fff)
 
+/* Paravirtualised time calls (defined by ARM DEN0057A) */
+#define ARM_SMCCC_HV_PV_TIME_FEATURES				\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x20)
+
+#define ARM_SMCCC_HV_PV_TIME_ST					\
+	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
+			   ARM_SMCCC_SMC_64,			\
+			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
+			   0x21)
+
+/*
+ * Return codes defined in ARM DEN 0070A
+ * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C
+ */
+#define SMCCC_RET_SUCCESS			0
+#define SMCCC_RET_NOT_SUPPORTED			-1
+#define SMCCC_RET_NOT_REQUIRED			-2
+#define SMCCC_RET_INVALID_PARAMETER		-3
+
 #ifndef __ASSEMBLY__
 
 #include <linux/linkage.h>
@@ -332,15 +354,6 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 #define arm_smccc_1_1_hvc(...)	__arm_smccc_1_1(SMCCC_HVC_INST, __VA_ARGS__)
 
 /*
- * Return codes defined in ARM DEN 0070A
- * ARM DEN 0070A is now merged/consolidated into ARM DEN 0028 C
- */
-#define SMCCC_RET_SUCCESS			0
-#define SMCCC_RET_NOT_SUPPORTED			-1
-#define SMCCC_RET_NOT_REQUIRED			-2
-#define SMCCC_RET_INVALID_PARAMETER		-3
-
-/*
  * Like arm_smccc_1_1* but always returns SMCCC_RET_NOT_SUPPORTED.
  * Used when the SMCCC conduit is not defined. The empty asm statement
  * avoids compiler warnings about unused variables.
@@ -385,18 +398,5 @@ asmlinkage void __arm_smccc_hvc(unsigned long a0, unsigned long a1,
 		method;							\
 	})
 
-/* Paravirtualised time calls (defined by ARM DEN0057A) */
-#define ARM_SMCCC_HV_PV_TIME_FEATURES				\
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
-			   ARM_SMCCC_SMC_64,			\
-			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
-			   0x20)
-
-#define ARM_SMCCC_HV_PV_TIME_ST					\
-	ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,			\
-			   ARM_SMCCC_SMC_64,			\
-			   ARM_SMCCC_OWNER_STANDARD_HYP,	\
-			   0x21)
-
 #endif /*__ASSEMBLY__*/
 #endif /*__LINUX_ARM_SMCCC_H*/
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 204e76856435..59f7194fdf08 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -230,28 +230,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__)
 #endif
 
-/*
- * Prevent the compiler from merging or refetching reads or writes. The
- * compiler is also forbidden from reordering successive instances of
- * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
- * particular ordering. One way to make the compiler aware of ordering is to
- * put the two invocations of READ_ONCE or WRITE_ONCE in different C
- * statements.
- *
- * These two macros will also work on aggregate data types like structs or
- * unions.
- *
- * Their two major use cases are: (1) Mediating communication between
- * process-level code and irq/NMI handlers, all running on the same CPU,
- * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
- * mutilate accesses that either do not require ordering or that interact
- * with an explicit memory barrier or atomic instruction that provides the
- * required ordering.
- */
-#include <asm/barrier.h>
-#include <linux/kasan-checks.h>
-#include <linux/kcsan-checks.h>
-
 /**
  * data_race - mark an expression as containing intentional data races
  *
@@ -272,65 +250,6 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
 	__v;								\
 })
 
-/*
- * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
- * atomicity or dependency ordering guarantees. Note that this may result
- * in tears!
- */
-#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
-
-#define __READ_ONCE_SCALAR(x)						\
-({									\
-	__unqual_scalar_typeof(x) __x = __READ_ONCE(x);			\
-	smp_read_barrier_depends();					\
-	(typeof(x))__x;							\
-})
-
-#define READ_ONCE(x)							\
-({									\
-	compiletime_assert_rwonce_type(x);				\
-	__READ_ONCE_SCALAR(x);						\
-})
-
-#define __WRITE_ONCE(x, val)						\
-do {									\
-	*(volatile typeof(x) *)&(x) = (val);				\
-} while (0)
-
-#define WRITE_ONCE(x, val)						\
-do {									\
-	compiletime_assert_rwonce_type(x);				\
-	__WRITE_ONCE(x, val);						\
-} while (0)
-
-static __no_sanitize_or_inline
-unsigned long __read_once_word_nocheck(const void *addr)
-{
-	return __READ_ONCE(*(unsigned long *)addr);
-}
-
-/*
- * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
- * word from memory atomically but without telling KASAN/KCSAN. This is
- * usually used by unwinding code when walking the stack of a running process.
- */
-#define READ_ONCE_NOCHECK(x)						\
-({									\
-	unsigned long __x;						\
-	compiletime_assert(sizeof(x) == sizeof(__x),			\
-		"Unsupported access size for READ_ONCE_NOCHECK().");	\
-	__x = __read_once_word_nocheck(&(x));				\
-	smp_read_barrier_depends();					\
-	(typeof(x))__x;							\
-})
-
-static __no_kasan_or_inline
-unsigned long read_word_at_a_time(const void *addr)
-{
-	kasan_check_read(addr, 1);
-	return *(unsigned long *)addr;
-}
-
 #endif /* __KERNEL__ */
 
 /*
@@ -354,57 +273,6 @@ static inline void *offset_to_ptr(const int *off)
 
 #endif /* __ASSEMBLY__ */
 
-/* Compile time object size, -1 for unknown */
-#ifndef __compiletime_object_size
-# define __compiletime_object_size(obj) -1
-#endif
-#ifndef __compiletime_warning
-# define __compiletime_warning(message)
-#endif
-#ifndef __compiletime_error
-# define __compiletime_error(message)
-#endif
-
-#ifdef __OPTIMIZE__
-# define __compiletime_assert(condition, msg, prefix, suffix)		\
-	do {								\
-		extern void prefix ## suffix(void) __compiletime_error(msg); \
-		if (!(condition))					\
-			prefix ## suffix();				\
-	} while (0)
-#else
-# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
-#endif
-
-#define _compiletime_assert(condition, msg, prefix, suffix) \
-	__compiletime_assert(condition, msg, prefix, suffix)
-
-/**
- * compiletime_assert - break build and emit msg if condition is false
- * @condition: a compile-time constant condition to check
- * @msg:       a message to emit if condition is false
- *
- * In tradition of POSIX assert, this macro will break the build if the
- * supplied condition is *false*, emitting the supplied error message if the
- * compiler has support to do so.
- */
-#define compiletime_assert(condition, msg) \
-	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
-
-#define compiletime_assert_atomic_type(t)				\
-	compiletime_assert(__native_word(t),				\
-		"Need native word sized stores/loads for atomicity.")
-
-/*
- * Yes, this permits 64-bit accesses on 32-bit architectures. These will
- * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
- * rely on the access being split into 2x32-bit accesses for a 32-bit quantity
- * (e.g. a virtual address) and a strong prevailing wind.
- */
-#define compiletime_assert_rwonce_type(t)					\
-	compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long),	\
-		"Unsupported access size for {READ,WRITE}_ONCE().")
-
 /* &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]))
 
@@ -414,4 +282,6 @@ static inline void *offset_to_ptr(const int *off)
  */
 #define prevent_tail_call_optimization()	mb()
 
+#include <asm/rwonce.h>
+
 #endif /* __LINUX_COMPILER_H */
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 01dd58c74d80..2e231ba8fe3f 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -275,6 +275,47 @@ struct ftrace_likely_data {
 	(sizeof(t) == sizeof(char) || sizeof(t) == sizeof(short) || \
 	 sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
 
+/* Compile time object size, -1 for unknown */
+#ifndef __compiletime_object_size
+# define __compiletime_object_size(obj) -1
+#endif
+#ifndef __compiletime_warning
+# define __compiletime_warning(message)
+#endif
+#ifndef __compiletime_error
+# define __compiletime_error(message)
+#endif
+
+#ifdef __OPTIMIZE__
+# define __compiletime_assert(condition, msg, prefix, suffix)		\
+	do {								\
+		extern void prefix ## suffix(void) __compiletime_error(msg); \
+		if (!(condition))					\
+			prefix ## suffix();				\
+	} while (0)
+#else
+# define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0)
+#endif
+
+#define _compiletime_assert(condition, msg, prefix, suffix) \
+	__compiletime_assert(condition, msg, prefix, suffix)
+
+/**
+ * compiletime_assert - break build and emit msg if condition is false
+ * @condition: a compile-time constant condition to check
+ * @msg:       a message to emit if condition is false
+ *
+ * In tradition of POSIX assert, this macro will break the build if the
+ * supplied condition is *false*, emitting the supplied error message if the
+ * compiler has support to do so.
+ */
+#define compiletime_assert(condition, msg) \
+	_compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__)
+
+#define compiletime_assert_atomic_type(t)				\
+	compiletime_assert(__native_word(t),				\
+		"Need native word sized stores/loads for atomicity.")
+
 /* Helpers for emitting diagnostics in pragmas. */
 #ifndef __diag
 #define __diag(string)
diff --git a/include/linux/nospec.h b/include/linux/nospec.h
index 0c5ef54fd416..c1e79f72cd89 100644
--- a/include/linux/nospec.h
+++ b/include/linux/nospec.h
@@ -5,6 +5,8 @@
 
 #ifndef _LINUX_NOSPEC_H
 #define _LINUX_NOSPEC_H
+
+#include <linux/compiler.h>
 #include <asm/barrier.h>
 
 struct task_struct;
diff --git a/include/linux/of.h b/include/linux/of.h
index c669c0a4732f..60abe3f636ad 100644
--- a/include/linux/of.h
+++ b/include/linux/of.h
@@ -554,7 +554,7 @@ bool of_console_check(struct device_node *dn, char *name, int index);
 
 extern int of_cpu_node_to_id(struct device_node *np);
 
-int of_map_rid(struct device_node *np, u32 rid,
+int of_map_id(struct device_node *np, u32 id,
 	       const char *map_name, const char *map_mask_name,
 	       struct device_node **target, u32 *id_out);
 
@@ -978,7 +978,7 @@ static inline int of_cpu_node_to_id(struct device_node *np)
 	return -ENODEV;
 }
 
-static inline int of_map_rid(struct device_node *np, u32 rid,
+static inline int of_map_id(struct device_node *np, u32 id,
 			     const char *map_name, const char *map_mask_name,
 			     struct device_node **target, u32 *id_out)
 {
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 8d31e39dd564..07ca187fc5e4 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -55,9 +55,15 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return of_node_get(cpu_dev->of_node);
 }
 
-int of_dma_configure(struct device *dev,
+int of_dma_configure_id(struct device *dev,
 		     struct device_node *np,
-		     bool force_dma);
+		     bool force_dma, const u32 *id);
+static inline int of_dma_configure(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
+{
+	return of_dma_configure_id(dev, np, force_dma, NULL);
+}
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
@@ -106,6 +112,12 @@ static inline struct device_node *of_cpu_device_node_get(int cpu)
 	return NULL;
 }
 
+static inline int of_dma_configure_id(struct device *dev,
+				   struct device_node *np,
+				   bool force_dma)
+{
+	return 0;
+}
 static inline int of_dma_configure(struct device *dev,
 				   struct device_node *np,
 				   bool force_dma)
diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h
index f3d40dd7bb66..16f4b3e87f20 100644
--- a/include/linux/of_iommu.h
+++ b/include/linux/of_iommu.h
@@ -13,7 +13,8 @@ extern int of_get_dma_window(struct device_node *dn, const char *prefix,
 			     size_t *size);
 
 extern const struct iommu_ops *of_iommu_configure(struct device *dev,
-					struct device_node *master_np);
+					struct device_node *master_np,
+					const u32 *id);
 
 #else
 
@@ -25,7 +26,8 @@ static inline int of_get_dma_window(struct device_node *dn, const char *prefix,
 }
 
 static inline const struct iommu_ops *of_iommu_configure(struct device *dev,
-					 struct device_node *master_np)
+					 struct device_node *master_np,
+					 const u32 *id)
 {
 	return NULL;
 }
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 1214cabb2247..e8b78139f78c 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -52,9 +52,10 @@ extern struct irq_domain *of_msi_get_domain(struct device *dev,
 					    struct device_node *np,
 					    enum irq_domain_bus_token token);
 extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
-						       u32 rid);
+							u32 id,
+							u32 bus_token);
 extern void of_msi_configure(struct device *dev, struct device_node *np);
-u32 of_msi_map_rid(struct device *dev, struct device_node *msi_np, u32 rid_in);
+u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in);
 #else
 static inline int of_irq_count(struct device_node *dev)
 {
@@ -85,17 +86,17 @@ static inline struct irq_domain *of_msi_get_domain(struct device *dev,
 	return NULL;
 }
 static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
-							      u32 rid)
+						u32 id, u32 bus_token)
 {
 	return NULL;
 }
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
-static inline u32 of_msi_map_rid(struct device *dev,
-				 struct device_node *msi_np, u32 rid_in)
+static inline u32 of_msi_map_id(struct device *dev,
+				 struct device_node *msi_np, u32 id_in)
 {
-	return rid_in;
+	return id_in;
 }
 #endif
 
diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 22d9d183950d..87d8a38bdea1 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -155,7 +155,7 @@ static inline bool __ref_is_percpu(struct percpu_ref *ref,
 	 * between contaminating the pointer value, meaning that
 	 * READ_ONCE() is required when fetching it.
 	 *
-	 * The smp_read_barrier_depends() implied by READ_ONCE() pairs
+	 * The dependency ordering from the READ_ONCE() pairs
 	 * with smp_store_release() in __percpu_ref_switch_to_percpu().
 	 */
 	percpu_ptr = READ_ONCE(ref->percpu_count_ptr);
diff --git a/include/linux/ptr_ring.h b/include/linux/ptr_ring.h
index 417db0a79a62..808f9d3ee546 100644
--- a/include/linux/ptr_ring.h
+++ b/include/linux/ptr_ring.h
@@ -107,7 +107,7 @@ static inline int __ptr_ring_produce(struct ptr_ring *r, void *ptr)
 		return -ENOSPC;
 
 	/* Make sure the pointer we are storing points to a valid data. */
-	/* Pairs with smp_read_barrier_depends in __ptr_ring_consume. */
+	/* Pairs with the dependency ordering in __ptr_ring_consume. */
 	smp_wmb();
 
 	WRITE_ONCE(r->queue[r->producer++], ptr);
diff --git a/include/linux/sched_clock.h b/include/linux/sched_clock.h
index 0bb04a96a6d4..528718e4ed52 100644
--- a/include/linux/sched_clock.h
+++ b/include/linux/sched_clock.h
@@ -6,6 +6,34 @@
 #define LINUX_SCHED_CLOCK
 
 #ifdef CONFIG_GENERIC_SCHED_CLOCK
+/**
+ * struct clock_read_data - data required to read from sched_clock()
+ *
+ * @epoch_ns:		sched_clock() value at last update
+ * @epoch_cyc:		Clock cycle value at last update.
+ * @sched_clock_mask:   Bitmask for two's complement subtraction of non 64bit
+ *			clocks.
+ * @read_sched_clock:	Current clock source (or dummy source when suspended).
+ * @mult:		Multipler for scaled math conversion.
+ * @shift:		Shift value for scaled math conversion.
+ *
+ * Care must be taken when updating this structure; it is read by
+ * some very hot code paths. It occupies <=40 bytes and, when combined
+ * with the seqcount used to synchronize access, comfortably fits into
+ * a 64 byte cache line.
+ */
+struct clock_read_data {
+	u64 epoch_ns;
+	u64 epoch_cyc;
+	u64 sched_clock_mask;
+	u64 (*read_sched_clock)(void);
+	u32 mult;
+	u32 shift;
+};
+
+extern struct clock_read_data *sched_clock_read_begin(unsigned int *seq);
+extern int sched_clock_read_retry(unsigned int seq);
+
 extern void generic_sched_clock_init(void);
 
 extern void sched_clock_register(u64 (*read)(void), int bits,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7b2d6fc9e6ed..21a1edd08cbe 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -532,9 +532,10 @@ struct perf_event_mmap_page {
 				cap_bit0_is_deprecated	: 1, /* Always 1, signals that bit 0 is zero */
 
 				cap_user_rdpmc		: 1, /* The RDPMC instruction can be used to read counts */
-				cap_user_time		: 1, /* The time_* fields are used */
+				cap_user_time		: 1, /* The time_{shift,mult,offset} fields are used */
 				cap_user_time_zero	: 1, /* The time_zero field is used */
-				cap_____res		: 59;
+				cap_user_time_short	: 1, /* the time_{cycle,mask} fields are used */
+				cap_____res		: 58;
 		};
 	};
 
@@ -593,13 +594,29 @@ struct perf_event_mmap_page {
 	 *               ((rem * time_mult) >> time_shift);
 	 */
 	__u64	time_zero;
+
 	__u32	size;			/* Header size up to __reserved[] fields. */
+	__u32	__reserved_1;
+
+	/*
+	 * If cap_usr_time_short, the hardware clock is less than 64bit wide
+	 * and we must compute the 'cyc' value, as used by cap_usr_time, as:
+	 *
+	 *   cyc = time_cycles + ((cyc - time_cycles) & time_mask)
+	 *
+	 * NOTE: this form is explicitly chosen such that cap_usr_time_short
+	 *       is a correction on top of cap_usr_time, and code that doesn't
+	 *       know about cap_usr_time_short still works under the assumption
+	 *       the counter doesn't wrap.
+	 */
+	__u64	time_cycles;
+	__u64	time_mask;
 
 		/*
 		 * Hole for extension of the self monitor capabilities
 		 */
 
-	__u8	__reserved[118*8+4];	/* align to 1k. */
+	__u8	__reserved[116*8];	/* align to 1k. */
 
 	/*
 	 * Control data for the mmap() data buffer.
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 7955c56d6b3c..ee810cae4e1e 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -109,6 +109,7 @@ struct vdso_data {
  * relocation, and this is what we need.
  */
 extern struct vdso_data _vdso_data[CS_BASES] __attribute__((visibility("hidden")));
+extern struct vdso_data _timens_data[CS_BASES] __attribute__((visibility("hidden")));
 
 /*
  * The generic vDSO implementation requires that gettimeofday.h