1 files changed, 497 insertions, 107 deletions

diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index c0b7ac1c7594..feb1c3cf63e4 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -317,7 +317,8 @@ static u64 __grt_latency_data(struct perf_event *event, u64 status,
 {
 	u64 val;
 
-	WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
+	WARN_ON_ONCE(is_hybrid() &&
+		     hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
 
 	dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK;
 	val = hybrid_var(event->pmu, pebs_data_source)[dse];
@@ -625,13 +626,18 @@ static int alloc_pebs_buffer(int cpu)
 	int max, node = cpu_to_node(cpu);
 	void *buffer, *insn_buff, *cea;
 
-	if (!x86_pmu.ds_pebs)
+	if (!intel_pmu_has_pebs())
 		return 0;
 
 	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
 	if (unlikely(!buffer))
 		return -ENOMEM;
 
+	if (x86_pmu.arch_pebs) {
+		hwev->pebs_vaddr = buffer;
+		return 0;
+	}
+
 	/*
 	 * HSW+ already provides us the eventing ip; no need to allocate this
 	 * buffer then.
@@ -644,7 +650,7 @@ static int alloc_pebs_buffer(int cpu)
 		}
 		per_cpu(insn_buffer, cpu) = insn_buff;
 	}
-	hwev->ds_pebs_vaddr = buffer;
+	hwev->pebs_vaddr = buffer;
 	/* Update the cpu entry area mapping */
 	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
 	ds->pebs_buffer_base = (unsigned long) cea;
@@ -660,17 +666,20 @@ static void release_pebs_buffer(int cpu)
 	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
 	void *cea;
 
-	if (!x86_pmu.ds_pebs)
+	if (!intel_pmu_has_pebs())
 		return;
 
-	kfree(per_cpu(insn_buffer, cpu));
-	per_cpu(insn_buffer, cpu) = NULL;
+	if (x86_pmu.ds_pebs) {
+		kfree(per_cpu(insn_buffer, cpu));
+		per_cpu(insn_buffer, cpu) = NULL;
 
-	/* Clear the fixmap */
-	cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
-	ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
-	dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size);
-	hwev->ds_pebs_vaddr = NULL;
+		/* Clear the fixmap */
+		cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer;
+		ds_clear_cea(cea, x86_pmu.pebs_buffer_size);
+	}
+
+	dsfree_pages(hwev->pebs_vaddr, x86_pmu.pebs_buffer_size);
+	hwev->pebs_vaddr = NULL;
 }
 
 static int alloc_bts_buffer(int cpu)
@@ -823,6 +832,56 @@ void reserve_ds_buffers(void)
 	}
 }
 
+inline int alloc_arch_pebs_buf_on_cpu(int cpu)
+{
+	if (!x86_pmu.arch_pebs)
+		return 0;
+
+	return alloc_pebs_buffer(cpu);
+}
+
+inline void release_arch_pebs_buf_on_cpu(int cpu)
+{
+	if (!x86_pmu.arch_pebs)
+		return;
+
+	release_pebs_buffer(cpu);
+}
+
+void init_arch_pebs_on_cpu(int cpu)
+{
+	struct cpu_hw_events *cpuc = per_cpu_ptr(&cpu_hw_events, cpu);
+	u64 arch_pebs_base;
+
+	if (!x86_pmu.arch_pebs)
+		return;
+
+	if (!cpuc->pebs_vaddr) {
+		WARN(1, "Fail to allocate PEBS buffer on CPU %d\n", cpu);
+		x86_pmu.pebs_active = 0;
+		return;
+	}
+
+	/*
+	 * 4KB-aligned pointer of the output buffer
+	 * (__alloc_pages_node() return page aligned address)
+	 * Buffer Size = 4KB * 2^SIZE
+	 * contiguous physical buffer (__alloc_pages_node() with order)
+	 */
+	arch_pebs_base = virt_to_phys(cpuc->pebs_vaddr) | PEBS_BUFFER_SHIFT;
+	wrmsr_on_cpu(cpu, MSR_IA32_PEBS_BASE, (u32)arch_pebs_base,
+		     (u32)(arch_pebs_base >> 32));
+	x86_pmu.pebs_active = 1;
+}
+
+inline void fini_arch_pebs_on_cpu(int cpu)
+{
+	if (!x86_pmu.arch_pebs)
+		return;
+
+	wrmsr_on_cpu(cpu, MSR_IA32_PEBS_BASE, 0, 0);
+}
+
 /*
  * BTS
  */
@@ -1470,6 +1529,25 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc,
 	}
 }
 
+u64 intel_get_arch_pebs_data_config(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 pebs_data_cfg = 0;
+	u64 cntr_mask;
+
+	if (WARN_ON(event->hw.idx < 0 || event->hw.idx >= X86_PMC_IDX_MAX))
+		return 0;
+
+	pebs_data_cfg |= pebs_update_adaptive_cfg(event);
+
+	cntr_mask = (PEBS_DATACFG_CNTR_MASK << PEBS_DATACFG_CNTR_SHIFT) |
+		    (PEBS_DATACFG_FIX_MASK << PEBS_DATACFG_FIX_SHIFT) |
+		    PEBS_DATACFG_CNTR | PEBS_DATACFG_METRICS;
+	pebs_data_cfg |= cpuc->pebs_data_cfg & cntr_mask;
+
+	return pebs_data_cfg;
+}
+
 void intel_pmu_pebs_add(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1531,6 +1609,15 @@ static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
 		intel_pmu_drain_pebs_buffer();
 }
 
+static void __intel_pmu_pebs_enable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
+	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+}
+
 void intel_pmu_pebs_enable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1539,9 +1626,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
 	struct debug_store *ds = cpuc->ds;
 	unsigned int idx = hwc->idx;
 
-	hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT;
-
-	cpuc->pebs_enabled |= 1ULL << hwc->idx;
+	__intel_pmu_pebs_enable(event);
 
 	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5))
 		cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32);
@@ -1603,14 +1688,22 @@ void intel_pmu_pebs_del(struct perf_event *event)
 	pebs_update_state(needed_cb, cpuc, event, false);
 }
 
-void intel_pmu_pebs_disable(struct perf_event *event)
+static void __intel_pmu_pebs_disable(struct perf_event *event)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
 	intel_pmu_drain_large_pebs(cpuc);
-
 	cpuc->pebs_enabled &= ~(1ULL << hwc->idx);
+	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
+}
+
+void intel_pmu_pebs_disable(struct perf_event *event)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct hw_perf_event *hwc = &event->hw;
+
+	__intel_pmu_pebs_disable(event);
 
 	if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) &&
 	    (x86_pmu.version < 5))
@@ -1622,8 +1715,6 @@ void intel_pmu_pebs_disable(struct perf_event *event)
 
 	if (cpuc->enabled)
 		wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
-
-	hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
 }
 
 void intel_pmu_pebs_enable_all(void)
@@ -2059,6 +2150,90 @@ static inline void __setup_pebs_counter_group(struct cpu_hw_events *cpuc,
 
 #define PEBS_LATENCY_MASK			0xffff
 
+static inline void __setup_perf_sample_data(struct perf_event *event,
+					    struct pt_regs *iregs,
+					    struct perf_sample_data *data)
+{
+	perf_sample_data_init(data, 0, event->hw.last_period);
+
+	/*
+	 * We must however always use iregs for the unwinder to stay sane; the
+	 * record BP,SP,IP can point into thin air when the record is from a
+	 * previous PMI context or an (I)RET happened between the record and
+	 * PMI.
+	 */
+	perf_sample_save_callchain(data, event, iregs);
+}
+
+static inline void __setup_pebs_basic_group(struct perf_event *event,
+					    struct pt_regs *regs,
+					    struct perf_sample_data *data,
+					    u64 sample_type, u64 ip,
+					    u64 tsc, u16 retire)
+{
+	/* The ip in basic is EventingIP */
+	set_linear_ip(regs, ip);
+	regs->flags = PERF_EFLAGS_EXACT;
+	setup_pebs_time(event, data, tsc);
+
+	if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT)
+		data->weight.var3_w = retire;
+}
+
+static inline void __setup_pebs_gpr_group(struct perf_event *event,
+					  struct pt_regs *regs,
+					  struct pebs_gprs *gprs,
+					  u64 sample_type)
+{
+	if (event->attr.precise_ip < 2) {
+		set_linear_ip(regs, gprs->ip);
+		regs->flags &= ~PERF_EFLAGS_EXACT;
+	}
+
+	if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
+		adaptive_pebs_save_regs(regs, gprs);
+}
+
+static inline void __setup_pebs_meminfo_group(struct perf_event *event,
+					      struct perf_sample_data *data,
+					      u64 sample_type, u64 latency,
+					      u16 instr_latency, u64 address,
+					      u64 aux, u64 tsx_tuning, u64 ax)
+{
+	if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
+		u64 tsx_latency = intel_get_tsx_weight(tsx_tuning);
+
+		data->weight.var2_w = instr_latency;
+
+		/*
+		 * Although meminfo::latency is defined as a u64,
+		 * only the lower 32 bits include the valid data
+		 * in practice on Ice Lake and earlier platforms.
+		 */
+		if (sample_type & PERF_SAMPLE_WEIGHT)
+			data->weight.full = latency ?: tsx_latency;
+		else
+			data->weight.var1_dw = (u32)latency ?: tsx_latency;
+
+		data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
+	}
+
+	if (sample_type & PERF_SAMPLE_DATA_SRC) {
+		data->data_src.val = get_data_src(event, aux);
+		data->sample_flags |= PERF_SAMPLE_DATA_SRC;
+	}
+
+	if (sample_type & PERF_SAMPLE_ADDR_TYPE) {
+		data->addr = address;
+		data->sample_flags |= PERF_SAMPLE_ADDR;
+	}
+
+	if (sample_type & PERF_SAMPLE_TRANSACTION) {
+		data->txn = intel_get_tsx_transaction(tsx_tuning, ax);
+		data->sample_flags |= PERF_SAMPLE_TRANSACTION;
+	}
+}
+
 /*
  * With adaptive PEBS the layout depends on what fields are configured.
  */
@@ -2068,12 +2243,14 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 					    struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 sample_type = event->attr.sample_type;
 	struct pebs_basic *basic = __pebs;
 	void *next_record = basic + 1;
-	u64 sample_type, format_group;
 	struct pebs_meminfo *meminfo = NULL;
 	struct pebs_gprs *gprs = NULL;
 	struct x86_perf_regs *perf_regs;
+	u64 format_group;
+	u16 retire;
 
 	if (basic == NULL)
 		return;
@@ -2081,31 +2258,17 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	perf_regs = container_of(regs, struct x86_perf_regs, regs);
 	perf_regs->xmm_regs = NULL;
 
-	sample_type = event->attr.sample_type;
 	format_group = basic->format_group;
-	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	setup_pebs_time(event, data, basic->tsc);
-
-	/*
-	 * We must however always use iregs for the unwinder to stay sane; the
-	 * record BP,SP,IP can point into thin air when the record is from a
-	 * previous PMI context or an (I)RET happened between the record and
-	 * PMI.
-	 */
-	perf_sample_save_callchain(data, event, iregs);
+	__setup_perf_sample_data(event, iregs, data);
 
 	*regs = *iregs;
-	/* The ip in basic is EventingIP */
-	set_linear_ip(regs, basic->ip);
-	regs->flags = PERF_EFLAGS_EXACT;
 
-	if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
-		if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
-			data->weight.var3_w = basic->retire_latency;
-		else
-			data->weight.var3_w = 0;
-	}
+	/* basic group */
+	retire = x86_pmu.flags & PMU_FL_RETIRE_LATENCY ?
+			basic->retire_latency : 0;
+	__setup_pebs_basic_group(event, regs, data, sample_type,
+				 basic->ip, basic->tsc, retire);
 
 	/*
 	 * The record for MEMINFO is in front of GP
@@ -2121,54 +2284,20 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 		gprs = next_record;
 		next_record = gprs + 1;
 
-		if (event->attr.precise_ip < 2) {
-			set_linear_ip(regs, gprs->ip);
-			regs->flags &= ~PERF_EFLAGS_EXACT;
-		}
-
-		if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER))
-			adaptive_pebs_save_regs(regs, gprs);
+		__setup_pebs_gpr_group(event, regs, gprs, sample_type);
 	}
 
 	if (format_group & PEBS_DATACFG_MEMINFO) {
-		if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) {
-			u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
-					meminfo->cache_latency : meminfo->mem_latency;
-
-			if (x86_pmu.flags & PMU_FL_INSTR_LATENCY)
-				data->weight.var2_w = meminfo->instr_latency;
-
-			/*
-			 * Although meminfo::latency is defined as a u64,
-			 * only the lower 32 bits include the valid data
-			 * in practice on Ice Lake and earlier platforms.
-			 */
-			if (sample_type & PERF_SAMPLE_WEIGHT) {
-				data->weight.full = latency ?:
-					intel_get_tsx_weight(meminfo->tsx_tuning);
-			} else {
-				data->weight.var1_dw = (u32)latency ?:
-					intel_get_tsx_weight(meminfo->tsx_tuning);
-			}
-
-			data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
-		}
-
-		if (sample_type & PERF_SAMPLE_DATA_SRC) {
-			data->data_src.val = get_data_src(event, meminfo->aux);
-			data->sample_flags |= PERF_SAMPLE_DATA_SRC;
-		}
-
-		if (sample_type & PERF_SAMPLE_ADDR_TYPE) {
-			data->addr = meminfo->address;
-			data->sample_flags |= PERF_SAMPLE_ADDR;
-		}
-
-		if (sample_type & PERF_SAMPLE_TRANSACTION) {
-			data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning,
-							  gprs ? gprs->ax : 0);
-			data->sample_flags |= PERF_SAMPLE_TRANSACTION;
-		}
+		u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
+				meminfo->cache_latency : meminfo->mem_latency;
+		u64 instr_latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ?
+				meminfo->instr_latency : 0;
+		u64 ax = gprs ? gprs->ax : 0;
+
+		__setup_pebs_meminfo_group(event, data, sample_type, latency,
+					   instr_latency, meminfo->address,
+					   meminfo->aux, meminfo->tsx_tuning,
+					   ax);
 	}
 
 	if (format_group & PEBS_DATACFG_XMMS) {
@@ -2219,6 +2348,135 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 			format_group);
 }
 
+static inline bool arch_pebs_record_continued(struct arch_pebs_header *header)
+{
+	/* Continue bit or null PEBS record indicates fragment follows. */
+	return header->cont || !(header->format & GENMASK_ULL(63, 16));
+}
+
+static void setup_arch_pebs_sample_data(struct perf_event *event,
+					struct pt_regs *iregs,
+					void *__pebs,
+					struct perf_sample_data *data,
+					struct pt_regs *regs)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	u64 sample_type = event->attr.sample_type;
+	struct arch_pebs_header *header = NULL;
+	struct arch_pebs_aux *meminfo = NULL;
+	struct arch_pebs_gprs *gprs = NULL;
+	struct x86_perf_regs *perf_regs;
+	void *next_record;
+	void *at = __pebs;
+
+	if (at == NULL)
+		return;
+
+	perf_regs = container_of(regs, struct x86_perf_regs, regs);
+	perf_regs->xmm_regs = NULL;
+
+	__setup_perf_sample_data(event, iregs, data);
+
+	*regs = *iregs;
+
+again:
+	header = at;
+	next_record = at + sizeof(struct arch_pebs_header);
+	if (header->basic) {
+		struct arch_pebs_basic *basic = next_record;
+		u16 retire = 0;
+
+		next_record = basic + 1;
+
+		if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT)
+			retire = basic->valid ? basic->retire : 0;
+		__setup_pebs_basic_group(event, regs, data, sample_type,
+				 basic->ip, basic->tsc, retire);
+	}
+
+	/*
+	 * The record for MEMINFO is in front of GP
+	 * But PERF_SAMPLE_TRANSACTION needs gprs->ax.
+	 * Save the pointer here but process later.
+	 */
+	if (header->aux) {
+		meminfo = next_record;
+		next_record = meminfo + 1;
+	}
+
+	if (header->gpr) {
+		gprs = next_record;
+		next_record = gprs + 1;
+
+		__setup_pebs_gpr_group(event, regs,
+				       (struct pebs_gprs *)gprs,
+				       sample_type);
+	}
+
+	if (header->aux) {
+		u64 ax = gprs ? gprs->ax : 0;
+
+		__setup_pebs_meminfo_group(event, data, sample_type,
+					   meminfo->cache_latency,
+					   meminfo->instr_latency,
+					   meminfo->address, meminfo->aux,
+					   meminfo->tsx_tuning, ax);
+	}
+
+	if (header->xmm) {
+		struct pebs_xmm *xmm;
+
+		next_record += sizeof(struct arch_pebs_xer_header);
+
+		xmm = next_record;
+		perf_regs->xmm_regs = xmm->xmm;
+		next_record = xmm + 1;
+	}
+
+	if (header->lbr) {
+		struct arch_pebs_lbr_header *lbr_header = next_record;
+		struct lbr_entry *lbr;
+		int num_lbr;
+
+		next_record = lbr_header + 1;
+		lbr = next_record;
+
+		num_lbr = header->lbr == ARCH_PEBS_LBR_NUM_VAR ?
+				lbr_header->depth :
+				header->lbr * ARCH_PEBS_BASE_LBR_ENTRIES;
+		next_record += num_lbr * sizeof(struct lbr_entry);
+
+		if (has_branch_stack(event)) {
+			intel_pmu_store_pebs_lbrs(lbr);
+			intel_pmu_lbr_save_brstack(data, cpuc, event);
+		}
+	}
+
+	if (header->cntr) {
+		struct arch_pebs_cntr_header *cntr = next_record;
+		unsigned int nr;
+
+		next_record += sizeof(struct arch_pebs_cntr_header);
+
+		if (is_pebs_counter_event_group(event)) {
+			__setup_pebs_counter_group(cpuc, event,
+				(struct pebs_cntr_header *)cntr, next_record);
+			data->sample_flags |= PERF_SAMPLE_READ;
+		}
+
+		nr = hweight32(cntr->cntr) + hweight32(cntr->fixed);
+		if (cntr->metrics == INTEL_CNTR_METRICS)
+			nr += 2;
+		next_record += nr * sizeof(u64);
+	}
+
+	/* Parse followed fragments if there are. */
+	if (arch_pebs_record_continued(header)) {
+		at = at + header->size;
+		goto again;
+	}
+}
+
 static inline void *
 get_next_pebs_record_by_bit(void *base, void *top, int bit)
 {
@@ -2601,6 +2859,57 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 	}
 }
 
+static __always_inline void
+__intel_pmu_handle_pebs_record(struct pt_regs *iregs,
+			       struct pt_regs *regs,
+			       struct perf_sample_data *data,
+			       void *at, u64 pebs_status,
+			       short *counts, void **last,
+			       setup_fn setup_sample)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *event;
+	int bit;
+
+	for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) {
+		event = cpuc->events[bit];
+
+		if (WARN_ON_ONCE(!event) ||
+		    WARN_ON_ONCE(!event->attr.precise_ip))
+			continue;
+
+		if (counts[bit]++) {
+			__intel_pmu_pebs_event(event, iregs, regs, data,
+					       last[bit], setup_sample);
+		}
+
+		last[bit] = at;
+	}
+}
+
+static __always_inline void
+__intel_pmu_handle_last_pebs_record(struct pt_regs *iregs,
+				    struct pt_regs *regs,
+				    struct perf_sample_data *data,
+				    u64 mask, short *counts, void **last,
+				    setup_fn setup_sample)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	struct perf_event *event;
+	int bit;
+
+	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
+		if (!counts[bit])
+			continue;
+
+		event = cpuc->events[bit];
+
+		__intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit],
+					    counts[bit], setup_sample);
+	}
+
+}
+
 static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data)
 {
 	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
@@ -2610,9 +2919,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 	struct x86_perf_regs perf_regs;
 	struct pt_regs *regs = &perf_regs.regs;
 	struct pebs_basic *basic;
-	struct perf_event *event;
 	void *base, *at, *top;
-	int bit;
 	u64 mask;
 
 	if (!x86_pmu.pebs_active)
@@ -2625,6 +2932,7 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 
 	mask = hybrid(cpuc->pmu, pebs_events_mask) |
 	       (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
+	mask &= cpuc->pebs_enabled;
 
 	if (unlikely(base >= top)) {
 		intel_pmu_pebs_event_update_no_drain(cpuc, mask);
@@ -2642,38 +2950,114 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 		if (basic->format_size != cpuc->pebs_record_size)
 			continue;
 
-		pebs_status = basic->applicable_counters & cpuc->pebs_enabled & mask;
-		for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) {
-			event = cpuc->events[bit];
+		pebs_status = mask & basic->applicable_counters;
+		__intel_pmu_handle_pebs_record(iregs, regs, data, at,
+					       pebs_status, counts, last,
+					       setup_pebs_adaptive_sample_data);
+	}
 
-			if (WARN_ON_ONCE(!event) ||
-			    WARN_ON_ONCE(!event->attr.precise_ip))
-				continue;
+	__intel_pmu_handle_last_pebs_record(iregs, regs, data, mask, counts, last,
+					    setup_pebs_adaptive_sample_data);
+}
 
-			if (counts[bit]++) {
-				__intel_pmu_pebs_event(event, iregs, regs, data, last[bit],
-						       setup_pebs_adaptive_sample_data);
-			}
-			last[bit] = at;
-		}
+static void intel_pmu_drain_arch_pebs(struct pt_regs *iregs,
+				      struct perf_sample_data *data)
+{
+	short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+	void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS];
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	union arch_pebs_index index;
+	struct x86_perf_regs perf_regs;
+	struct pt_regs *regs = &perf_regs.regs;
+	void *base, *at, *top;
+	u64 mask;
+
+	rdmsrq(MSR_IA32_PEBS_INDEX, index.whole);
+
+	if (unlikely(!index.wr)) {
+		intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
+		return;
 	}
 
-	for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
-		if (!counts[bit])
+	base = cpuc->pebs_vaddr;
+	top = cpuc->pebs_vaddr + (index.wr << ARCH_PEBS_INDEX_WR_SHIFT);
+
+	index.wr = 0;
+	index.full = 0;
+	index.en = 1;
+	if (cpuc->n_pebs == cpuc->n_large_pebs)
+		index.thresh = ARCH_PEBS_THRESH_MULTI;
+	else
+		index.thresh = ARCH_PEBS_THRESH_SINGLE;
+	wrmsrq(MSR_IA32_PEBS_INDEX, index.whole);
+
+	mask = hybrid(cpuc->pmu, arch_pebs_cap).counters & cpuc->pebs_enabled;
+
+	if (!iregs)
+		iregs = &dummy_iregs;
+
+	/* Process all but the last event for each counter. */
+	for (at = base; at < top;) {
+		struct arch_pebs_header *header;
+		struct arch_pebs_basic *basic;
+		u64 pebs_status;
+
+		header = at;
+
+		if (WARN_ON_ONCE(!header->size))
+			break;
+
+		/* 1st fragment or single record must have basic group */
+		if (!header->basic) {
+			at += header->size;
 			continue;
+		}
 
-		event = cpuc->events[bit];
+		basic = at + sizeof(struct arch_pebs_header);
+		pebs_status = mask & basic->applicable_counters;
+		__intel_pmu_handle_pebs_record(iregs, regs, data, at,
+					       pebs_status, counts, last,
+					       setup_arch_pebs_sample_data);
+
+		/* Skip non-last fragments */
+		while (arch_pebs_record_continued(header)) {
+			if (!header->size)
+				break;
+			at += header->size;
+			header = at;
+		}
 
-		__intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit],
-					    counts[bit], setup_pebs_adaptive_sample_data);
+		/* Skip last fragment or the single record */
+		at += header->size;
 	}
+
+	__intel_pmu_handle_last_pebs_record(iregs, regs, data, mask,
+					    counts, last,
+					    setup_arch_pebs_sample_data);
+}
+
+static void __init intel_arch_pebs_init(void)
+{
+	/*
+	 * Current hybrid platforms always both support arch-PEBS or not
+	 * on all kinds of cores. So directly set x86_pmu.arch_pebs flag
+	 * if boot cpu supports arch-PEBS.
+	 */
+	x86_pmu.arch_pebs = 1;
+	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
+	x86_pmu.drain_pebs = intel_pmu_drain_arch_pebs;
+	x86_pmu.pebs_capable = ~0ULL;
+	x86_pmu.flags |= PMU_FL_PEBS_ALL;
+
+	x86_pmu.pebs_enable = __intel_pmu_pebs_enable;
+	x86_pmu.pebs_disable = __intel_pmu_pebs_disable;
 }
 
 /*
  * PEBS probe and setup
  */
 
-void __init intel_pebs_init(void)
+static void __init intel_ds_pebs_init(void)
 {
 	/*
 	 * No support for 32bit formats
@@ -2735,10 +3119,8 @@ void __init intel_pebs_init(void)
 			break;
 
 		case 6:
-			if (x86_pmu.intel_cap.pebs_baseline) {
+			if (x86_pmu.intel_cap.pebs_baseline)
 				x86_pmu.large_pebs_flags |= PERF_SAMPLE_READ;
-				x86_pmu.late_setup = intel_pmu_late_setup;
-			}
 			fallthrough;
 		case 5:
 			x86_pmu.pebs_ept = 1;
@@ -2788,6 +3170,14 @@ void __init intel_pebs_init(void)
 	}
 }
 
+void __init intel_pebs_init(void)
+{
+	if (x86_pmu.intel_cap.pebs_format == 0xf)
+		intel_arch_pebs_init();
+	else
+		intel_ds_pebs_init();
+}
+
 void perf_restore_debug_store(void)
 {
 	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);