1 files changed, 274 insertions, 72 deletions

diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 332d2e6d8ae4..3161ec0a3416 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -17,6 +17,7 @@
 #include <asm/fpu/xstate.h>
 #include <asm/intel_ds.h>
 #include <asm/cpu.h>
+#include <asm/msr.h>
 
 /* To enable MSR tracing please use the generic trace points. */
 
@@ -35,15 +36,17 @@
  * per-core reg tables.
  */
 enum extra_reg_type {
-	EXTRA_REG_NONE  = -1,	/* not used */
+	EXTRA_REG_NONE		= -1, /* not used */
 
-	EXTRA_REG_RSP_0 = 0,	/* offcore_response_0 */
-	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
-	EXTRA_REG_LBR   = 2,	/* lbr_select */
-	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
-	EXTRA_REG_FE    = 4,    /* fe_* */
+	EXTRA_REG_RSP_0		= 0,  /* offcore_response_0 */
+	EXTRA_REG_RSP_1		= 1,  /* offcore_response_1 */
+	EXTRA_REG_LBR		= 2,  /* lbr_select */
+	EXTRA_REG_LDLAT		= 3,  /* ld_lat_threshold */
+	EXTRA_REG_FE		= 4,  /* fe_* */
+	EXTRA_REG_SNOOP_0	= 5,  /* snoop response 0 */
+	EXTRA_REG_SNOOP_1	= 6,  /* snoop response 1 */
 
-	EXTRA_REG_MAX		/* number of entries needed */
+	EXTRA_REG_MAX		      /* number of entries needed */
 };
 
 struct event_constraint {
@@ -108,6 +111,28 @@ static inline bool is_topdown_event(struct perf_event *event)
 	return is_metric_event(event) || is_slots_event(event);
 }
 
+int is_x86_event(struct perf_event *event);
+
+static inline bool check_leader_group(struct perf_event *leader, int flags)
+{
+	return is_x86_event(leader) ? !!(leader->hw.flags & flags) : false;
+}
+
+static inline bool is_branch_counters_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_BRANCH_COUNTERS);
+}
+
+static inline bool is_pebs_counter_event_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR);
+}
+
+static inline bool is_acr_event_group(struct perf_event *event)
+{
+	return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR);
+}
+
 struct amd_nb {
 	int nb_id;  /* NorthBridge id */
 	int refcnt; /* reference count */
@@ -249,6 +274,7 @@ struct cpu_hw_events {
 	struct event_constraint	*event_constraint[X86_PMC_IDX_MAX];
 
 	int			n_excl; /* the number of exclusive events */
+	int			n_late_setup; /* the num of events needs late setup */
 
 	unsigned int		txn_flags;
 	int			is_fake;
@@ -257,8 +283,9 @@ struct cpu_hw_events {
 	 * Intel DebugStore bits
 	 */
 	struct debug_store	*ds;
-	void			*ds_pebs_vaddr;
 	void			*ds_bts_vaddr;
+	/* DS based PEBS or arch-PEBS buffer address */
+	void			*pebs_vaddr;
 	u64			pebs_enabled;
 	int			n_pebs;
 	int			n_large_pebs;
@@ -274,6 +301,12 @@ struct cpu_hw_events {
 	u64			fixed_ctrl_val;
 	u64			active_fixed_ctrl_val;
 
+	/* Intel ACR configuration */
+	u64			acr_cfg_b[X86_PMC_IDX_MAX];
+	u64			acr_cfg_c[X86_PMC_IDX_MAX];
+	/* Cached CFG_C values */
+	u64			cfg_c_val[X86_PMC_IDX_MAX];
+
 	/*
 	 * Intel LBR bits
 	 */
@@ -281,6 +314,7 @@ struct cpu_hw_events {
 	int				lbr_pebs_users;
 	struct perf_branch_stack	lbr_stack;
 	struct perf_branch_entry	lbr_entries[MAX_LBR_ENTRIES];
+	u64				lbr_counters[MAX_LBR_ENTRIES]; /* branch stack extra */
 	union {
 		struct er_account		*lbr_sel;
 		struct er_account		*lbr_ctl;
@@ -468,6 +502,14 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID)
 
+#define INTEL_HYBRID_LDLAT_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_LD_HSW)
+
+#define INTEL_HYBRID_STLAT_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_ST_HSW)
+
 /* Event constraint, but match on all event flags too. */
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
 	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
@@ -606,7 +648,9 @@ union perf_capabilities {
 		u64     pebs_baseline:1;
 		u64	perf_metrics:1;
 		u64	pebs_output_pt_available:1;
+		u64	pebs_timing_info:1;
 		u64	anythread_deprecated:1;
+		u64	rdpmc_metrics_clear:1;
 	};
 	u64	capabilities;
 };
@@ -646,18 +690,59 @@ enum {
 	x86_lbr_exclusive_max,
 };
 
-#define PERF_PEBS_DATA_SOURCE_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_MAX	0x100
+#define PERF_PEBS_DATA_SOURCE_MASK	(PERF_PEBS_DATA_SOURCE_MAX - 1)
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
+
+#define X86_HYBRID_PMU_ATOM_IDX		0
+#define X86_HYBRID_PMU_CORE_IDX		1
+#define X86_HYBRID_PMU_TINY_IDX		2
+
+enum hybrid_pmu_type {
+	not_hybrid,
+	hybrid_small		= BIT(X86_HYBRID_PMU_ATOM_IDX),
+	hybrid_big		= BIT(X86_HYBRID_PMU_CORE_IDX),
+	hybrid_tiny		= BIT(X86_HYBRID_PMU_TINY_IDX),
+
+	/* The belows are only used for matching */
+	hybrid_big_small	= hybrid_big   | hybrid_small,
+	hybrid_small_tiny	= hybrid_small | hybrid_tiny,
+	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
+};
+
+struct arch_pebs_cap {
+	u64 caps;
+	u64 counters;
+	u64 pdists;
+};
 
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
 	const char			*name;
-	u8				cpu_type;
+	enum hybrid_pmu_type		pmu_type;
 	cpumask_t			supported_cpus;
 	union perf_capabilities		intel_cap;
 	u64				intel_ctrl;
-	int				max_pebs_events;
-	int				num_counters;
-	int				num_counters_fixed;
+	u64				pebs_events_mask;
+	u64				config_mask;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -676,6 +761,8 @@ struct x86_hybrid_pmu {
 					mid_ack		:1,
 					enabled_ack	:1;
 
+	struct arch_pebs_cap		arch_pebs_cap;
+
 	u64				pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX];
 };
 
@@ -717,18 +804,6 @@ extern struct static_key_false perf_is_hybrid;
 	__Fp;						\
 })
 
-enum hybrid_pmu_type {
-	hybrid_big		= 0x40,
-	hybrid_small		= 0x20,
-
-	hybrid_big_small	= hybrid_big | hybrid_small,
-};
-
-#define X86_HYBRID_PMU_ATOM_IDX		0
-#define X86_HYBRID_PMU_CORE_IDX		1
-
-#define X86_HYBRID_NUM_PMUS		2
-
 /*
  * struct x86_pmu - generic x86 pmu
  */
@@ -751,14 +826,35 @@ struct x86_pmu {
 	u64		(*update)(struct perf_event *event);
 	int		(*hw_config)(struct perf_event *event);
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
+	void		(*late_setup)(void);
+	void		(*pebs_enable)(struct perf_event *event);
+	void		(*pebs_disable)(struct perf_event *event);
+	void		(*pebs_enable_all)(void);
+	void		(*pebs_disable_all)(void);
 	unsigned	eventsel;
 	unsigned	perfctr;
+	unsigned	fixedctr;
 	int		(*addr_offset)(int index, bool eventsel);
 	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
-	int		num_counters;
-	int		num_counters_fixed;
+	u64		config_mask;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cntr_mask64;
+			unsigned long	acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		acr_cause_mask64;
+			unsigned long	acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {
@@ -811,8 +907,8 @@ struct x86_pmu {
 	void		(*cpu_dead)(int cpu);
 
 	void		(*check_microcode)(void);
-	void		(*sched_task)(struct perf_event_context *ctx,
-				      bool sched_in);
+	void		(*sched_task)(struct perf_event_pmu_context *pmu_ctx,
+				      struct task_struct *task, bool sched_in);
 
 	/*
 	 * Intel Arch Perfmon v2+
@@ -821,21 +917,22 @@ struct x86_pmu {
 	union perf_capabilities intel_cap;
 
 	/*
-	 * Intel DebugStore bits
+	 * Intel DebugStore and PEBS bits
 	 */
 	unsigned int	bts			:1,
 			bts_active		:1,
-			pebs			:1,
+			ds_pebs			:1,
 			pebs_active		:1,
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
 			pebs_no_tlb		:1,
 			pebs_no_isolation	:1,
 			pebs_block		:1,
-			pebs_ept		:1;
+			pebs_ept		:1,
+			arch_pebs		:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
-	int		max_pebs_events;
+	u64		pebs_events_mask;
 	void		(*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
@@ -845,6 +942,11 @@ struct x86_pmu {
 	u64		pebs_capable;
 
 	/*
+	 * Intel Architectural PEBS
+	 */
+	struct arch_pebs_cap arch_pebs_cap;
+
+	/*
 	 * Intel LBR
 	 */
 	unsigned int	lbr_tos, lbr_from, lbr_to,
@@ -857,6 +959,7 @@ struct x86_pmu {
 		const int	*lbr_sel_map;	   /* lbr_select mappings */
 		int		*lbr_ctl_map;	   /* LBR_CTL mappings */
 	};
+	u64		lbr_callstack_users;	   /* lbr callstack system wide users */
 	bool		lbr_double_abort;	   /* duplicated lbr aborts */
 	bool		lbr_pt_coexist;		   /* (LBR|BTS) may coexist with PT */
 
@@ -877,6 +980,7 @@ struct x86_pmu {
 	unsigned int	lbr_mispred:1;
 	unsigned int	lbr_timed_lbr:1;
 	unsigned int	lbr_br_type:1;
+	unsigned int	lbr_counters:4;
 
 	void		(*lbr_reset)(void);
 	void		(*lbr_read)(struct cpu_hw_events *cpuc);
@@ -894,14 +998,6 @@ struct x86_pmu {
 	int		num_topdown_events;
 
 	/*
-	 * perf task context (i.e. struct perf_event_context::task_ctx_data)
-	 * switch helper to bridge calls from perf/core to perf/x86.
-	 * See struct pmu::swap_task_ctx() usage for examples;
-	 */
-	void		(*swap_task_ctx)(struct perf_event_context *prev,
-					 struct perf_event_context *next);
-
-	/*
 	 * AMD bits
 	 */
 	unsigned int	amd_nb_constraints : 1;
@@ -925,7 +1021,7 @@ struct x86_pmu {
 
 	int (*aux_output_match) (struct perf_event *event);
 
-	int (*filter_match)(struct perf_event *event);
+	void (*filter)(struct pmu *pmu, int cpu, bool *ret);
 	/*
 	 * Hybrid support
 	 *
@@ -936,7 +1032,7 @@ struct x86_pmu {
 	 */
 	int				num_hybrid_pmus;
 	struct x86_hybrid_pmu		*hybrid_pmu;
-	u8 (*get_hybrid_cpu_type)	(void);
+	enum intel_cpu_type (*get_hybrid_cpu_type)	(void);
 };
 
 struct x86_perf_task_context_opt {
@@ -1000,6 +1096,9 @@ do {									\
 #define PMU_FL_PAIR		0x40 /* merge counters for large incr. events */
 #define PMU_FL_INSTR_LATENCY	0x80 /* Support Instruction Latency in PEBS Memory Info Record */
 #define PMU_FL_MEM_LOADS_AUX	0x100 /* Require an auxiliary event for the complete memory info */
+#define PMU_FL_RETIRE_LATENCY	0x200 /* Support Retire Latency in PEBS */
+#define PMU_FL_BR_CNTR		0x400 /* Support branch counter logging */
+#define PMU_FL_DYN_CONSTRAINT	0x800 /* Needs dynamic constraint */
 
 #define EVENT_VAR(_id)  event_attr_##_id
 #define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1047,6 +1146,12 @@ extern struct x86_pmu x86_pmu __read_mostly;
 
 DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
 DECLARE_STATIC_CALL(x86_pmu_update,     *x86_pmu.update);
+DECLARE_STATIC_CALL(x86_pmu_drain_pebs,	*x86_pmu.drain_pebs);
+DECLARE_STATIC_CALL(x86_pmu_late_setup,	*x86_pmu.late_setup);
+DECLARE_STATIC_CALL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable);
+DECLARE_STATIC_CALL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable);
+DECLARE_STATIC_CALL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all);
+DECLARE_STATIC_CALL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all);
 
 static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
 {
@@ -1088,6 +1193,12 @@ extern u64 __read_mostly hw_cache_extra_regs
 
 u64 x86_perf_event_update(struct perf_event *event);
 
+static inline u64 intel_pmu_topdown_event_update(struct perf_event *event, u64 *val)
+{
+	return x86_perf_event_update(event);
+}
+DECLARE_STATIC_CALL(intel_pmu_update_topdown_event, intel_pmu_topdown_event_update);
+
 static inline unsigned int x86_pmu_config_addr(int index)
 {
 	return x86_pmu.eventsel + (x86_pmu.addr_offset ?
@@ -1100,13 +1211,19 @@ static inline unsigned int x86_pmu_event_addr(int index)
 				  x86_pmu.addr_offset(index, false) : index);
 }
 
+static inline unsigned int x86_pmu_fixed_ctr_addr(int index)
+{
+	return x86_pmu.fixedctr + (x86_pmu.addr_offset ?
+				   x86_pmu.addr_offset(index, false) : index);
+}
+
 static inline int x86_pmu_rdpmc_index(int index)
 {
 	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
 }
 
-bool check_hw_exists(struct pmu *pmu, int num_counters,
-		     int num_counters_fixed);
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+		     unsigned long *fixed_cntr_mask);
 
 int x86_add_exclusive(unsigned int what);
 
@@ -1116,7 +1233,7 @@ int x86_reserve_hardware(void);
 
 void x86_release_hardware(void);
 
-int x86_pmu_max_precise(void);
+int x86_pmu_max_precise(struct pmu *pmu);
 
 void hw_perf_lbr_event_destroy(struct perf_event *event);
 
@@ -1142,16 +1259,16 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
 	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
 
 	if (hwc->extra_reg.reg)
-		wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
+		wrmsrq(hwc->extra_reg.reg, hwc->extra_reg.config);
 
 	/*
 	 * Add enabled Merge event on next counter
 	 * if large increment event being enabled on this counter
 	 */
 	if (is_counter_pair(hwc))
-		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
+		wrmsrq(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
 
-	wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
+	wrmsrq(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
 }
 
 void x86_pmu_enable_all(int added);
@@ -1167,20 +1284,42 @@ static inline void x86_pmu_disable_event(struct perf_event *event)
 	u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
 	struct hw_perf_event *hwc = &event->hw;
 
-	wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
+	wrmsrq(hwc->config_base, hwc->config & ~disable_mask);
 
 	if (is_counter_pair(hwc))
-		wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
+		wrmsrq(x86_pmu_config_addr(hwc->idx + 1), 0);
 }
 
 void x86_pmu_enable_event(struct perf_event *event);
 
 int x86_pmu_handle_irq(struct pt_regs *regs);
 
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
-			  u64 intel_ctrl);
+void x86_pmu_show_pmu_cap(struct pmu *pmu);
+
+static inline int x86_pmu_num_counters(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, fixed_cntr_mask64));
+}
 
-void x86_pmu_update_cpu_context(struct pmu *pmu, int cpu);
+static inline u64 x86_pmu_get_event_config(struct perf_event *event)
+{
+	return event->attr.config & hybrid(event->pmu, config_mask);
+}
 
 extern struct event_constraint emptyconstraint;
 
@@ -1306,11 +1445,25 @@ void amd_pmu_lbr_reset(void);
 void amd_pmu_lbr_read(void);
 void amd_pmu_lbr_add(struct perf_event *event);
 void amd_pmu_lbr_del(struct perf_event *event);
-void amd_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in);
 void amd_pmu_lbr_enable_all(void);
 void amd_pmu_lbr_disable_all(void);
 int amd_pmu_lbr_hw_config(struct perf_event *event);
 
+static __always_inline void __amd_pmu_lbr_disable(void)
+{
+	u64 dbg_ctl, dbg_extn_cfg;
+
+	rdmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+	wrmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
+
+	if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
+		rdmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+		wrmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+	}
+}
+
 #ifdef CONFIG_PERF_EVENTS_AMD_BRS
 
 #define AMD_FAM19H_BRS_EVENT 0xc4 /* RETIRED_TAKEN_BRANCH_INSTRUCTIONS */
@@ -1322,7 +1475,6 @@ void amd_brs_enable_all(void);
 void amd_brs_disable_all(void);
 void amd_brs_drain(void);
 void amd_brs_lopwr_init(void);
-void amd_brs_disable_all(void);
 int amd_brs_hw_config(struct perf_event *event);
 void amd_brs_reset(void);
 
@@ -1330,7 +1482,7 @@ static inline void amd_pmu_brs_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	perf_sched_cb_inc(event->ctx->pmu);
+	perf_sched_cb_inc(event->pmu);
 	cpuc->lbr_users++;
 	/*
 	 * No need to reset BRS because it is reset
@@ -1345,10 +1497,11 @@ static inline void amd_pmu_brs_del(struct perf_event *event)
 	cpuc->lbr_users--;
 	WARN_ON_ONCE(cpuc->lbr_users < 0);
 
-	perf_sched_cb_dec(event->ctx->pmu);
+	perf_sched_cb_dec(event->pmu);
 }
 
-void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in);
+void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in);
 #else
 static inline int amd_brs_init(void)
 {
@@ -1373,7 +1526,8 @@ static inline void amd_pmu_brs_del(struct perf_event *event)
 {
 }
 
-static inline void amd_pmu_brs_sched_task(struct perf_event_context *ctx, bool sched_in)
+static inline void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx,
+					  struct task_struct *task, bool sched_in)
 {
 }
 
@@ -1438,21 +1592,21 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
 
 static __always_inline void __intel_pmu_pebs_disable_all(void)
 {
-	wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+	wrmsrq(MSR_IA32_PEBS_ENABLE, 0);
 }
 
 static __always_inline void __intel_pmu_arch_lbr_disable(void)
 {
-	wrmsrl(MSR_ARCH_LBR_CTL, 0);
+	wrmsrq(MSR_ARCH_LBR_CTL, 0);
 }
 
 static __always_inline void __intel_pmu_lbr_disable(void)
 {
 	u64 debugctl;
 
-	rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 	debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
-	wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+	wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
 }
 
 int intel_pmu_save_and_restart(struct perf_event *event);
@@ -1466,6 +1620,14 @@ extern void intel_cpuc_finish(struct cpu_hw_events *cpuc);
 
 int intel_pmu_init(void);
 
+int alloc_arch_pebs_buf_on_cpu(int cpu);
+
+void release_arch_pebs_buf_on_cpu(int cpu);
+
+void init_arch_pebs_on_cpu(int cpu);
+
+void fini_arch_pebs_on_cpu(int cpu);
+
 void init_debug_store_on_cpu(int cpu);
 
 void fini_debug_store_on_cpu(int cpu);
@@ -1487,7 +1649,15 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
-u64 adl_latency_data_small(struct perf_event *event, u64 status);
+void intel_pmu_late_setup(void);
+
+u64 grt_latency_data(struct perf_event *event, u64 status);
+
+u64 cmt_latency_data(struct perf_event *event, u64 status);
+
+u64 lnl_latency_data(struct perf_event *event, u64 status);
+
+u64 arl_h_latency_data(struct perf_event *event, u64 status);
 
 extern struct event_constraint intel_core2_pebs_event_constraints[];
 
@@ -1517,7 +1687,9 @@ extern struct event_constraint intel_skl_pebs_event_constraints[];
 
 extern struct event_constraint intel_icl_pebs_event_constraints[];
 
-extern struct event_constraint intel_spr_pebs_event_constraints[];
+extern struct event_constraint intel_glc_pebs_event_constraints[];
+
+extern struct event_constraint intel_lnc_pebs_event_constraints[];
 
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
@@ -1533,18 +1705,22 @@ void intel_pmu_pebs_enable_all(void);
 
 void intel_pmu_pebs_disable_all(void);
 
-void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in);
+void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
+
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc);
 
-void intel_pmu_auto_reload_read(struct perf_event *event);
+void intel_pmu_drain_pebs_buffer(void);
 
 void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
 
-void intel_ds_init(void);
+void intel_pebs_init(void);
 
-void intel_pmu_lbr_swap_task_ctx(struct perf_event_context *prev,
-				 struct perf_event_context *next);
+void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
+				struct cpu_hw_events *cpuc,
+				struct perf_event *event);
 
-void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in);
+void intel_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			      struct task_struct *task, bool sched_in);
 
 u64 lbr_from_signext_quirk_wr(u64 val);
 
@@ -1600,6 +1776,16 @@ void intel_pmu_pebs_data_source_adl(void);
 
 void intel_pmu_pebs_data_source_grt(void);
 
+void intel_pmu_pebs_data_source_mtl(void);
+
+void intel_pmu_pebs_data_source_arl_h(void);
+
+void intel_pmu_pebs_data_source_cmt(void);
+
+void intel_pmu_pebs_data_source_lnl(void);
+
+u64 intel_get_arch_pebs_data_config(struct perf_event *event);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
@@ -1621,6 +1807,22 @@ static inline int is_ht_workaround_enabled(void)
 	return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
 }
 
+static inline u64 intel_pmu_pebs_mask(u64 cntr_mask)
+{
+	return MAX_PEBS_EVENTS_MASK & cntr_mask;
+}
+
+static inline int intel_pmu_max_num_pebs(struct pmu *pmu)
+{
+	static_assert(MAX_PEBS_EVENTS == 32);
+	return fls((u32)hybrid(pmu, pebs_events_mask));
+}
+
+static inline bool intel_pmu_has_pebs(void)
+{
+	return x86_pmu.ds_pebs || x86_pmu.arch_pebs;
+}
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)