1 files changed, 126 insertions, 183 deletions

diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index c99f26ebe7a6..eaae99602b61 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -32,30 +32,6 @@
  */
 #define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
 
-/* Reads to Local DRAM Memory */
-#define READS_TO_LOCAL_MEM		BIT(0)
-
-/* Reads to Remote DRAM Memory */
-#define READS_TO_REMOTE_MEM		BIT(1)
-
-/* Non-Temporal Writes to Local Memory */
-#define NON_TEMP_WRITE_TO_LOCAL_MEM	BIT(2)
-
-/* Non-Temporal Writes to Remote Memory */
-#define NON_TEMP_WRITE_TO_REMOTE_MEM	BIT(3)
-
-/* Reads to Local Memory the system identifies as "Slow Memory" */
-#define READS_TO_LOCAL_S_MEM		BIT(4)
-
-/* Reads to Remote Memory the system identifies as "Slow Memory" */
-#define READS_TO_REMOTE_S_MEM		BIT(5)
-
-/* Dirty Victims to All Types of Memory */
-#define DIRTY_VICTIMS_TO_ALL_MEM	BIT(6)
-
-/* Max event bits supported */
-#define MAX_EVT_CONFIG_BITS		GENMASK(6, 0)
-
 /**
  * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
  *			        aren't marked nohz_full
@@ -78,7 +54,8 @@ cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
 	else
 		cpu = cpumask_any_but(mask, exclude_cpu);
 
-	if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
+	/* Only continue if tick_nohz_full_mask has been initialized. */
+	if (!tick_nohz_full_enabled())
 		return cpu;
 
 	/* If the CPU picked isn't marked nohz_full nothing more needs doing. */
@@ -126,35 +103,59 @@ struct mon_evt {
 };
 
 /**
- * union mon_data_bits - Monitoring details for each event file
+ * union mon_data_bits - Monitoring details for each event file.
  * @priv:              Used to store monitoring event data in @u
- *                     as kernfs private data
- * @rid:               Resource id associated with the event file
- * @evtid:             Event id associated with the event file
- * @domid:             The domain to which the event file belongs
- * @u:                 Name of the bit fields struct
+ *                     as kernfs private data.
+ * @u.rid:             Resource id associated with the event file.
+ * @u.evtid:           Event id associated with the event file.
+ * @u.sum:             Set when event must be summed across multiple
+ *                     domains.
+ * @u.domid:           When @u.sum is zero this is the domain to which
+ *                     the event file belongs. When @sum is one this
+ *                     is the id of the L3 cache that all domains to be
+ *                     summed share.
+ * @u:                 Name of the bit fields struct.
  */
 union mon_data_bits {
 	void *priv;
 	struct {
 		unsigned int rid		: 10;
-		enum resctrl_event_id evtid	: 8;
+		enum resctrl_event_id evtid	: 7;
+		unsigned int sum		: 1;
 		unsigned int domid		: 14;
 	} u;
 };
 
+/**
+ * struct rmid_read - Data passed across smp_call*() to read event count.
+ * @rgrp:  Resource group for which the counter is being read. If it is a parent
+ *	   resource group then its event count is summed with the count from all
+ *	   its child resource groups.
+ * @r:	   Resource describing the properties of the event being read.
+ * @d:	   Domain that the counter should be read from. If NULL then sum all
+ *	   domains in @r sharing L3 @ci.id
+ * @evtid: Which monitor event to read.
+ * @first: Initialize MBM counter when true.
+ * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @err:   Error encountered when reading counter.
+ * @val:   Returned value of event counter. If @rgrp is a parent resource group,
+ *	   @val includes the sum of event counts from its child resource groups.
+ *	   If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
+ *	   (summed across child resource groups if @rgrp is a parent resource group).
+ * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
+ */
 struct rmid_read {
 	struct rdtgroup		*rgrp;
 	struct rdt_resource	*r;
-	struct rdt_domain	*d;
+	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
+	struct cacheinfo	*ci;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
 };
 
-extern unsigned int rdt_mon_features;
 extern struct list_head resctrl_schema_all;
 extern bool resctrl_mounted;
 
@@ -208,43 +209,6 @@ struct mongroup {
 };
 
 /**
- * struct pseudo_lock_region - pseudo-lock region information
- * @s:			Resctrl schema for the resource to which this
- *			pseudo-locked region belongs
- * @d:			RDT domain to which this pseudo-locked region
- *			belongs
- * @cbm:		bitmask of the pseudo-locked region
- * @lock_thread_wq:	waitqueue used to wait on the pseudo-locking thread
- *			completion
- * @thread_done:	variable used by waitqueue to test if pseudo-locking
- *			thread completed
- * @cpu:		core associated with the cache on which the setup code
- *			will be run
- * @line_size:		size of the cache lines
- * @size:		size of pseudo-locked region in bytes
- * @kmem:		the kernel memory associated with pseudo-locked region
- * @minor:		minor number of character device associated with this
- *			region
- * @debugfs_dir:	pointer to this region's directory in the debugfs
- *			filesystem
- * @pm_reqs:		Power management QoS requests related to this region
- */
-struct pseudo_lock_region {
-	struct resctrl_schema	*s;
-	struct rdt_domain	*d;
-	u32			cbm;
-	wait_queue_head_t	lock_thread_wq;
-	int			thread_done;
-	int			cpu;
-	unsigned int		line_size;
-	unsigned int		size;
-	void			*kmem;
-	unsigned int		minor;
-	struct dentry		*debugfs_dir;
-	struct list_head	pm_reqs;
-};
-
-/**
  * struct rdtgroup - store rdtgroup's data in resctrl file system.
  * @kn:				kernfs node
  * @rdtgroup_list:		linked list for all rdtgroups
@@ -257,6 +221,7 @@ struct pseudo_lock_region {
  *				monitor only or ctrl_mon group
  * @mon:			mongroup related data
  * @mode:			mode of resource group
+ * @mba_mbps_event:		input monitoring event id when mba_sc is enabled
  * @plr:			pseudo-locked region
  */
 struct rdtgroup {
@@ -269,6 +234,7 @@ struct rdtgroup {
 	enum rdt_group_type		type;
 	struct mongroup			mon;
 	enum rdtgrp_mode		mode;
+	enum resctrl_event_id		mba_mbps_event;
 	struct pseudo_lock_region	*plr;
 };
 
@@ -298,10 +264,7 @@ struct rdtgroup {
 /* List of all resource groups */
 extern struct list_head rdt_all_groups;
 
-extern int max_name_width, max_data_width;
-
-int __init rdtgroup_init(void);
-void __exit rdtgroup_exit(void);
+extern int max_name_width;
 
 /**
  * struct rftype - describe each file in the resctrl file system
@@ -354,70 +317,57 @@ struct arch_mbm_state {
 };
 
 /**
- * struct rdt_hw_domain - Arch private attributes of a set of CPUs that share
- *			  a resource
+ * struct rdt_hw_ctrl_domain - Arch private attributes of a set of CPUs that share
+ *			       a resource for a control function
  * @d_resctrl:	Properties exposed to the resctrl file system
  * @ctrl_val:	array of cache or mem ctrl values (indexed by CLOSID)
+ *
+ * Members of this structure are accessed via helpers that provide abstraction.
+ */
+struct rdt_hw_ctrl_domain {
+	struct rdt_ctrl_domain		d_resctrl;
+	u32				*ctrl_val;
+};
+
+/**
+ * struct rdt_hw_mon_domain - Arch private attributes of a set of CPUs that share
+ *			      a resource for a monitor function
+ * @d_resctrl:	Properties exposed to the resctrl file system
  * @arch_mbm_total:	arch private state for MBM total bandwidth
  * @arch_mbm_local:	arch private state for MBM local bandwidth
  *
  * Members of this structure are accessed via helpers that provide abstraction.
  */
-struct rdt_hw_domain {
-	struct rdt_domain		d_resctrl;
-	u32				*ctrl_val;
+struct rdt_hw_mon_domain {
+	struct rdt_mon_domain		d_resctrl;
 	struct arch_mbm_state		*arch_mbm_total;
 	struct arch_mbm_state		*arch_mbm_local;
 };
 
-static inline struct rdt_hw_domain *resctrl_to_arch_dom(struct rdt_domain *r)
+static inline struct rdt_hw_ctrl_domain *resctrl_to_arch_ctrl_dom(struct rdt_ctrl_domain *r)
+{
+	return container_of(r, struct rdt_hw_ctrl_domain, d_resctrl);
+}
+
+static inline struct rdt_hw_mon_domain *resctrl_to_arch_mon_dom(struct rdt_mon_domain *r)
 {
-	return container_of(r, struct rdt_hw_domain, d_resctrl);
+	return container_of(r, struct rdt_hw_mon_domain, d_resctrl);
 }
 
 /**
  * struct msr_param - set a range of MSRs from a domain
  * @res:       The resource to use
+ * @dom:       The domain to update
  * @low:       Beginning index from base MSR
  * @high:      End index
  */
 struct msr_param {
 	struct rdt_resource	*res;
+	struct rdt_ctrl_domain	*dom;
 	u32			low;
 	u32			high;
 };
 
-static inline bool is_llc_occupancy_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_OCCUP_EVENT_ID));
-}
-
-static inline bool is_mbm_total_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_TOTAL_EVENT_ID));
-}
-
-static inline bool is_mbm_local_enabled(void)
-{
-	return (rdt_mon_features & (1 << QOS_L3_MBM_LOCAL_EVENT_ID));
-}
-
-static inline bool is_mbm_enabled(void)
-{
-	return (is_mbm_total_enabled() || is_mbm_local_enabled());
-}
-
-static inline bool is_mbm_event(int e)
-{
-	return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
-		e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
-struct rdt_parse_data {
-	struct rdtgroup		*rdtgrp;
-	char			*buf;
-};
-
 /**
  * struct rdt_hw_resource - arch private attributes of a resctrl resource
  * @r_resctrl:		Attributes of the resource used directly by resctrl.
@@ -430,8 +380,6 @@ struct rdt_parse_data {
  * @msr_update:		Function pointer to update QOS MSRs
  * @mon_scale:		cqm counter * mon_scale = occupancy in bytes
  * @mbm_width:		Monitor width, to detect and correct for overflow.
- * @mbm_cfg_mask:	Bandwidth sources that can be tracked when Bandwidth
- *			Monitoring Event Configuration (BMEC) is supported.
  * @cdp_enabled:	CDP state of this resource
  *
  * Members of this structure are either private to the architecture
@@ -442,11 +390,9 @@ struct rdt_hw_resource {
 	struct rdt_resource	r_resctrl;
 	u32			num_closid;
 	unsigned int		msr_base;
-	void (*msr_update)	(struct rdt_domain *d, struct msr_param *m,
-				 struct rdt_resource *r);
+	void			(*msr_update)(struct msr_param *m);
 	unsigned int		mon_scale;
 	unsigned int		mbm_width;
-	unsigned int		mbm_cfg_mask;
 	bool			cdp_enabled;
 };
 
@@ -455,34 +401,17 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
 	return container_of(r, struct rdt_hw_resource, r_resctrl);
 }
 
-int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
-	      struct rdt_domain *d);
-int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
-	     struct rdt_domain *d);
-
 extern struct mutex rdtgroup_mutex;
 
+static inline const char *rdt_kn_name(const struct kernfs_node *kn)
+{
+	return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
+}
+
 extern struct rdt_hw_resource rdt_resources_all[];
 extern struct rdtgroup rdtgroup_default;
 extern struct dentry *debugfs_resctrl;
-
-enum resctrl_res_level {
-	RDT_RESOURCE_L3,
-	RDT_RESOURCE_L2,
-	RDT_RESOURCE_MBA,
-	RDT_RESOURCE_SMBA,
-
-	/* Must be the last */
-	RDT_NUM_RESOURCES,
-};
-
-static inline struct rdt_resource *resctrl_inc(struct rdt_resource *res)
-{
-	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(res);
-
-	hw_res++;
-	return &hw_res->r_resctrl;
-}
+extern enum resctrl_event_id mba_mbps_default_event;
 
 static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
 {
@@ -491,26 +420,7 @@ static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
 
 int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
 
-/*
- * To return the common struct rdt_resource, which is contained in struct
- * rdt_hw_resource, walk the resctrl member of struct rdt_hw_resource.
- */
-#define for_each_rdt_resource(r)					      \
-	for (r = &rdt_resources_all[0].r_resctrl;			      \
-	     r <= &rdt_resources_all[RDT_NUM_RESOURCES - 1].r_resctrl;	      \
-	     r = resctrl_inc(r))
-
-#define for_each_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_capable || r->mon_capable)
-
-#define for_each_alloc_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->alloc_capable)
-
-#define for_each_mon_capable_rdt_resource(r)				      \
-	for_each_rdt_resource(r)					      \
-		if (r->mon_capable)
+void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
 
 /* CPUID.(EAX=10H, ECX=ResID=1).EAX */
 union cpuid_0x10_1_eax {
@@ -556,55 +466,88 @@ void rdtgroup_kn_unlock(struct kernfs_node *kn);
 int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
 int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
 			     umode_t mask);
-struct rdt_domain *rdt_find_domain(struct rdt_resource *r, int id,
-				   struct list_head **pos);
 ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
 				char *buf, size_t nbytes, loff_t off);
 int rdtgroup_schemata_show(struct kernfs_open_file *of,
 			   struct seq_file *s, void *v);
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_domain *d,
+ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
+				      char *buf, size_t nbytes, loff_t off);
+int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
+				 struct seq_file *s, void *v);
+bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
 			   unsigned long cbm, int closid, bool exclusive);
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_domain *d,
+unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
 				  unsigned long cbm);
 enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
 int rdtgroup_tasks_assigned(struct rdtgroup *r);
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d);
-int rdt_pseudo_lock_init(void);
-void rdt_pseudo_lock_release(void);
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
-struct rdt_domain *get_domain_from_cpu(int cpu, struct rdt_resource *r);
 int closids_supported(void);
 void closid_free(int closid);
 int alloc_rmid(u32 closid);
 void free_rmid(u32 closid, u32 rmid);
 int rdt_get_mon_l3_config(struct rdt_resource *r);
-void __exit rdt_put_mon_l3_config(void);
+void resctrl_mon_resource_exit(void);
 bool __init rdt_cpu_has(int flag);
 void mon_event_count(void *info);
 int rdtgroup_mondata_show(struct seq_file *m, void *arg);
 void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
-		    struct rdt_domain *d, struct rdtgroup *rdtgrp,
-		    int evtid, int first);
-void mbm_setup_overflow_handler(struct rdt_domain *dom,
+		    struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
+		    cpumask_t *cpumask, int evtid, int first);
+int __init resctrl_mon_resource_init(void);
+void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
 				unsigned long delay_ms,
 				int exclude_cpu);
 void mbm_handle_overflow(struct work_struct *work);
 void __init intel_rdt_mbm_apply_quirk(void);
 bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
 			     int exclude_cpu);
 void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_domain *d);
-void __check_limbo(struct rdt_domain *d, bool force_free);
+bool has_busy_rmid(struct rdt_mon_domain *d);
+void __check_limbo(struct rdt_mon_domain *d, bool force_free);
 void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void __init thread_throttle_mode_init(void);
-void __init mbm_config_rftype_init(const char *config);
+void resctrl_file_fflags_init(const char *config, unsigned long fflags);
 void rdt_staged_configs_clear(void);
 bool closid_allocated(unsigned int closid);
 int resctrl_find_cleanest_closid(void);
 
+#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
+int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
+int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
+bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
+bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
+int rdt_pseudo_lock_init(void);
+void rdt_pseudo_lock_release(void);
+int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
+void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
+#else
+static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
+{
+	return false;
+}
+
+static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
+{
+	return false;
+}
+
+static inline int rdt_pseudo_lock_init(void) { return 0; }
+static inline void rdt_pseudo_lock_release(void) { }
+static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { }
+#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */
+
 #endif /* _ASM_X86_RESCTRL_INTERNAL_H */