Merge tag 'perf-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf events updates from Ingo Molnar:
 "Core & generic-arch updates:

   - Add support for dynamic constraints and propagate it to the Intel
     driver (Kan Liang)

   - Fix & enhance driver-specific throttling support (Kan Liang)

   - Record sample last_period before updating on the x86 and PowerPC
     platforms (Mark Barnett)

   - Make perf_pmu_unregister() usable (Peter Zijlstra)

   - Unify perf_event_free_task() / perf_event_exit_task_context()
     (Peter Zijlstra)

   - Simplify perf_event_release_kernel() and perf_event_free_task()
     (Peter Zijlstra)

   - Allocate non-contiguous AUX pages by default (Yabin Cui)

  Uprobes updates:

   - Add support to emulate NOP instructions (Jiri Olsa)

   - selftests/bpf: Add 5-byte NOP uprobe trigger benchmark (Jiri Olsa)

  x86 Intel PMU enhancements:

   - Support Intel Auto Counter Reload [ACR] (Kan Liang)

   - Add PMU support for Clearwater Forest (Dapeng Mi)

   - Arch-PEBS preparatory changes: (Dapeng Mi)
       - Parse CPUID archPerfmonExt leaves for non-hybrid CPUs
       - Decouple BTS initialization from PEBS initialization
       - Introduce pairs of PEBS static calls

  x86 AMD PMU enhancements:

   - Use hrtimer for handling overflows in the AMD uncore driver
     (Sandipan Das)

   - Prevent UMC counters from saturating (Sandipan Das)

  Fixes and cleanups:

   - Fix put_ctx() ordering (Frederic Weisbecker)

   - Fix irq work dereferencing garbage (Frederic Weisbecker)

   - Misc fixes and cleanups (Changbin Du, Frederic Weisbecker, Ian
     Rogers, Ingo Molnar, Kan Liang, Peter Zijlstra, Qing Wang, Sandipan
     Das, Thorsten Blum)"

* tag 'perf-core-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  perf/headers: Clean up <linux/perf_event.h> a bit
  perf/uapi: Clean up <uapi/linux/perf_event.h> a bit
  perf/uapi: Fix PERF_RECORD_SAMPLE comments in <uapi/linux/perf_event.h>
  mips/perf: Remove driver-specific throttle support
  xtensa/perf: Remove driver-specific throttle support
  sparc/perf: Remove driver-specific throttle support
  loongarch/perf: Remove driver-specific throttle support
  csky/perf: Remove driver-specific throttle support
  arc/perf: Remove driver-specific throttle support
  alpha/perf: Remove driver-specific throttle support
  perf/apple_m1: Remove driver-specific throttle support
  perf/arm: Remove driver-specific throttle support
  s390/perf: Remove driver-specific throttle support
  powerpc/perf: Remove driver-specific throttle support
  perf/x86/zhaoxin: Remove driver-specific throttle support
  perf/x86/amd: Remove driver-specific throttle support
  perf/x86/intel: Remove driver-specific throttle support
  perf: Only dump the throttle log for the leader
  perf: Fix the throttle logic for a group
  perf/core: Add the is_event_in_freq_mode() helper to simplify the code
  ...

29 files changed, 656 insertions, 220 deletions

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index 1f0eb4f25c0f..a3eaab094ece 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -852,14 +852,9 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 	alpha_perf_event_update(event, hwc, idx, alpha_pmu->pmc_max_period[idx]+1);
 	perf_sample_data_init(&data, 0, hwc->last_period);
 
-	if (alpha_perf_event_set_period(event, hwc, idx)) {
-		if (perf_event_overflow(event, &data, regs)) {
-			/* Interrupts coming too quickly; "throttle" the
-			 * counter, i.e., disable it for a little while.
-			 */
-			alpha_pmu_stop(event, 0);
-		}
-	}
+	if (alpha_perf_event_set_period(event, hwc, idx))
+		perf_event_overflow(event, &data, regs);
+
 	wrperfmon(PERFMON_CMD_ENABLE, cpuc->idx_mask);
 
 	return;
diff --git a/arch/arc/kernel/perf_event.c b/arch/arc/kernel/perf_event.c
index 6e5a651cd75c..ed6d4f0cd621 100644
--- a/arch/arc/kernel/perf_event.c
+++ b/arch/arc/kernel/perf_event.c
@@ -599,10 +599,8 @@ static irqreturn_t arc_pmu_intr(int irq, void *dev)
 
 		arc_perf_event_update(event, &event->hw, event->hw.idx);
 		perf_sample_data_init(&data, 0, hwc->last_period);
-		if (arc_pmu_event_set_period(event)) {
-			if (perf_event_overflow(event, &data, regs))
-				arc_pmu_stop(event, 0);
-		}
+		if (arc_pmu_event_set_period(event))
+			perf_event_overflow(event, &data, regs);
 
 		active_ints &= ~BIT(idx);
 	} while (active_ints);
diff --git a/arch/csky/kernel/perf_event.c b/arch/csky/kernel/perf_event.c
index e5f18420ce64..e0a36acd265b 100644
--- a/arch/csky/kernel/perf_event.c
+++ b/arch/csky/kernel/perf_event.c
@@ -1139,8 +1139,7 @@ static irqreturn_t csky_pmu_handle_irq(int irq_num, void *dev)
 		perf_sample_data_init(&data, 0, hwc->last_period);
 		csky_pmu_event_set_period(event);
 
-		if (perf_event_overflow(event, &data, regs))
-			csky_pmu_stop_event(event);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	csky_pmu_enable(&csky_pmu.pmu);
diff --git a/arch/loongarch/kernel/perf_event.c b/arch/loongarch/kernel/perf_event.c
index f86a4b838dd7..8ad098703488 100644
--- a/arch/loongarch/kernel/perf_event.c
+++ b/arch/loongarch/kernel/perf_event.c
@@ -479,8 +479,7 @@ static void handle_associated_event(struct cpu_hw_events *cpuc, int idx,
 	if (!loongarch_pmu_event_set_period(event, hwc, idx))
 		return;
 
-	if (perf_event_overflow(event, data, regs))
-		loongarch_pmu_disable_event(idx);
+	perf_event_overflow(event, data, regs);
 }
 
 static irqreturn_t pmu_handle_irq(int irq, void *dev)
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index c4d6b09136b1..196a070349b0 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -791,8 +791,7 @@ static void handle_associated_event(struct cpu_hw_events *cpuc,
 	if (!mipspmu_event_set_period(event, hwc, idx))
 		return;
 
-	if (perf_event_overflow(event, data, regs))
-		mipsxx_pmu_disable_event(idx);
+	perf_event_overflow(event, data, regs);
 }
 
 
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index b906d28f74fd..8b0081441f85 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2239,6 +2239,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
+	const u64 last_period = event->hw.last_period;
 	s64 prev, delta, left;
 	int record = 0;
 
@@ -2320,7 +2321,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, ~0ULL, event->hw.last_period);
+		perf_sample_data_init(&data, ~0ULL, last_period);
 
 		if (event->attr.sample_type & PERF_SAMPLE_ADDR_TYPE)
 			perf_get_data_addr(event, regs, &data.addr);
@@ -2343,12 +2344,10 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			ppmu->get_mem_weight(&data.weight.full, event->attr.sample_type);
 			data.sample_flags |= PERF_SAMPLE_WEIGHT_TYPE;
 		}
-		if (perf_event_overflow(event, &data, regs))
-			power_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	} else if (period) {
 		/* Account for interrupt in case of invalid SIAR */
-		if (perf_event_account_interrupt(event))
-			power_pmu_stop(event, 0);
+		perf_event_account_interrupt(event);
 	}
 }
 
diff --git a/arch/powerpc/perf/core-fsl-emb.c b/arch/powerpc/perf/core-fsl-emb.c
index 1a53ab08447c..7120ab20cbfe 100644
--- a/arch/powerpc/perf/core-fsl-emb.c
+++ b/arch/powerpc/perf/core-fsl-emb.c
@@ -590,6 +590,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 			       struct pt_regs *regs)
 {
 	u64 period = event->hw.sample_period;
+	const u64 last_period = event->hw.last_period;
 	s64 prev, delta, left;
 	int record = 0;
 
@@ -632,10 +633,9 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 	if (record) {
 		struct perf_sample_data data;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
-		if (perf_event_overflow(event, &data, regs))
-			fsl_emb_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 }
 
diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
index e657fad7e376..6a262e198e35 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -980,8 +980,6 @@ static int cfdiag_push_sample(struct perf_event *event,
 	}
 
 	overflow = perf_event_overflow(event, &data, &regs);
-	if (overflow)
-		event->pmu->stop(event, 0);
 
 	perf_event_update_userpage(event);
 	return overflow;
diff --git a/arch/s390/kernel/perf_cpum_sf.c b/arch/s390/kernel/perf_cpum_sf.c
index ad22799d8a7d..91469401f2c9 100644
--- a/arch/s390/kernel/perf_cpum_sf.c
+++ b/arch/s390/kernel/perf_cpum_sf.c
@@ -1072,10 +1072,7 @@ static int perf_push_sample(struct perf_event *event,
 	overflow = 0;
 	if (perf_event_exclude(event, &regs, sde_regs))
 		goto out;
-	if (perf_event_overflow(event, &data, &regs)) {
-		overflow = 1;
-		event->pmu->stop(event, 0);
-	}
+	overflow = perf_event_overflow(event, &data, &regs);
 	perf_event_update_userpage(event);
 out:
 	return overflow;
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index f02a283a8e8f..cae4d33002a5 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -1668,8 +1668,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
 		if (!sparc_perf_event_set_period(event, hwc, idx))
 			continue;
 
-		if (perf_event_overflow(event, &data, regs))
-			sparc_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	finish_clock = sched_clock();
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 30d6ceb4c8ad..5e64283b9bf2 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -1003,8 +1003,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 
 		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	/*
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 0252b7ea8bca..4bbbca02aeb1 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -1373,9 +1373,7 @@ fail:
 		hwc->sample_period = perf_ibs->min_period;
 
 out:
-	if (throttle) {
-		perf_ibs_stop(event, 0);
-	} else {
+	if (!throttle) {
 		if (perf_ibs == &perf_ibs_op) {
 			if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 				new_config = period & IBS_OP_MAX_CNT_EXT_MASK;
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 49c26ce2b115..d328de166481 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -21,6 +21,7 @@
 #define NUM_COUNTERS_NB		4
 #define NUM_COUNTERS_L2		4
 #define NUM_COUNTERS_L3		6
+#define NUM_COUNTERS_MAX	64
 
 #define RDPMC_BASE_NB		6
 #define RDPMC_BASE_LLC		10
@@ -38,7 +39,10 @@ struct amd_uncore_ctx {
 	int refcnt;
 	int cpu;
 	struct perf_event **events;
-	struct hlist_node node;
+	unsigned long active_mask[BITS_TO_LONGS(NUM_COUNTERS_MAX)];
+	int nr_active;
+	struct hrtimer hrtimer;
+	u64 hrtimer_duration;
 };
 
 struct amd_uncore_pmu {
@@ -83,11 +87,51 @@ struct amd_uncore {
 
 static struct amd_uncore uncores[UNCORE_TYPE_MAX];
 
+/* Interval for hrtimer, defaults to 60000 milliseconds */
+static unsigned int update_interval = 60 * MSEC_PER_SEC;
+module_param(update_interval, uint, 0444);
+
 static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
 {
 	return container_of(event->pmu, struct amd_uncore_pmu, pmu);
 }
 
+static enum hrtimer_restart amd_uncore_hrtimer(struct hrtimer *hrtimer)
+{
+	struct amd_uncore_ctx *ctx;
+	struct perf_event *event;
+	int bit;
+
+	ctx = container_of(hrtimer, struct amd_uncore_ctx, hrtimer);
+
+	if (!ctx->nr_active || ctx->cpu != smp_processor_id())
+		return HRTIMER_NORESTART;
+
+	for_each_set_bit(bit, ctx->active_mask, NUM_COUNTERS_MAX) {
+		event = ctx->events[bit];
+		event->pmu->read(event);
+	}
+
+	hrtimer_forward_now(hrtimer, ns_to_ktime(ctx->hrtimer_duration));
+	return HRTIMER_RESTART;
+}
+
+static void amd_uncore_start_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_start(&ctx->hrtimer, ns_to_ktime(ctx->hrtimer_duration),
+		      HRTIMER_MODE_REL_PINNED_HARD);
+}
+
+static void amd_uncore_cancel_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_cancel(&ctx->hrtimer);
+}
+
+static void amd_uncore_init_hrtimer(struct amd_uncore_ctx *ctx)
+{
+	hrtimer_setup(&ctx->hrtimer, amd_uncore_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+}
+
 static void amd_uncore_read(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
@@ -118,18 +162,26 @@ static void amd_uncore_read(struct perf_event *event)
 
 static void amd_uncore_start(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!ctx->nr_active++)
+		amd_uncore_start_hrtimer(ctx);
+
 	if (flags & PERF_EF_RELOAD)
 		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
 
 	hwc->state = 0;
+	__set_bit(hwc->idx, ctx->active_mask);
 	wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
 	perf_event_update_userpage(event);
 }
 
 static void amd_uncore_stop(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
 	wrmsrl(hwc->config_base, hwc->config);
@@ -139,6 +191,11 @@ static void amd_uncore_stop(struct perf_event *event, int flags)
 		event->pmu->read(event);
 		hwc->state |= PERF_HES_UPTODATE;
 	}
+
+	if (!--ctx->nr_active)
+		amd_uncore_cancel_hrtimer(ctx);
+
+	__clear_bit(hwc->idx, ctx->active_mask);
 }
 
 static int amd_uncore_add(struct perf_event *event, int flags)
@@ -491,6 +548,9 @@ static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				goto fail;
 			}
 
+			amd_uncore_init_hrtimer(curr);
+			curr->hrtimer_duration = (u64)update_interval * NSEC_PER_MSEC;
+
 			cpumask_set_cpu(cpu, &pmu->active_mask);
 		}
 
@@ -880,16 +940,55 @@ static int amd_uncore_umc_event_init(struct perf_event *event)
 
 static void amd_uncore_umc_start(struct perf_event *event, int flags)
 {
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
+	if (!ctx->nr_active++)
+		amd_uncore_start_hrtimer(ctx);
+
 	if (flags & PERF_EF_RELOAD)
 		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
 
 	hwc->state = 0;
+	__set_bit(hwc->idx, ctx->active_mask);
 	wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
 	perf_event_update_userpage(event);
 }
 
+static void amd_uncore_umc_read(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+	u64 prev, new, shift;
+	s64 delta;
+
+	shift = COUNTER_SHIFT + 1;
+	prev = local64_read(&hwc->prev_count);
+
+	/*
+	 * UMC counters do not have RDPMC assignments. Read counts directly
+	 * from the corresponding PERF_CTR.
+	 */
+	rdmsrl(hwc->event_base, new);
+
+	/*
+	 * Unlike the other uncore counters, UMC counters saturate and set the
+	 * Overflow bit (bit 48) on overflow. Since they do not roll over,
+	 * proactively reset the corresponding PERF_CTR when bit 47 is set so
+	 * that the counter never gets a chance to saturate.
+	 */
+	if (new & BIT_ULL(63 - COUNTER_SHIFT)) {
+		wrmsrl(hwc->event_base, 0);
+		local64_set(&hwc->prev_count, 0);
+	} else {
+		local64_set(&hwc->prev_count, new);
+	}
+
+	delta = (new << shift) - (prev << shift);
+	delta >>= shift;
+	local64_add(delta, &event->count);
+}
+
 static
 void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
@@ -968,7 +1067,7 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 				.del		= amd_uncore_del,
 				.start		= amd_uncore_umc_start,
 				.stop		= amd_uncore_stop,
-				.read		= amd_uncore_read,
+				.read		= amd_uncore_umc_read,
 				.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
 				.module		= THIS_MODULE,
 			};
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 139ad80d1df3..4c49eef8052e 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -95,6 +95,11 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all);
+
 /*
  * This one is magic, it will get called even when PMU init fails (because
  * there is no PMU), in which case it should simply return NULL.
@@ -674,6 +679,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
 	event->hw.idx = -1;
 	event->hw.last_cpu = -1;
 	event->hw.last_tag = ~0ULL;
+	event->hw.dyn_constraint = ~0ULL;
 
 	/* mark unused */
 	event->hw.extra_reg.idx = EXTRA_REG_NONE;
@@ -756,15 +762,16 @@ void x86_pmu_enable_all(int added)
 
 int is_x86_event(struct perf_event *event)
 {
-	int i;
-
-	if (!is_hybrid())
-		return event->pmu == &pmu;
-
-	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
-		if (event->pmu == &x86_pmu.hybrid_pmu[i].pmu)
-			return true;
-	}
+	/*
+	 * For a non-hybrid platforms, the type of X86 pmu is
+	 * always PERF_TYPE_RAW.
+	 * For a hybrid platform, the PERF_PMU_CAP_EXTENDED_HW_TYPE
+	 * is a unique capability for the X86 PMU.
+	 * Use them to detect a X86 event.
+	 */
+	if (event->pmu->type == PERF_TYPE_RAW ||
+	    event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE)
+		return true;
 
 	return false;
 }
@@ -1683,6 +1690,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 	struct cpu_hw_events *cpuc;
 	struct perf_event *event;
 	int idx, handled = 0;
+	u64 last_period;
 	u64 val;
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1702,6 +1710,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 		event = cpuc->events[idx];
+		last_period = event->hw.last_period;
 
 		val = static_call(x86_pmu_update)(event);
 		if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
@@ -1715,12 +1724,11 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
 		if (!static_call(x86_pmu_set_period)(event))
 			continue;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
 		perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	if (handled)
@@ -2046,6 +2054,11 @@ static void x86_pmu_static_call_update(void)
 	static_call_update(x86_pmu_filter, x86_pmu.filter);
 
 	static_call_update(x86_pmu_late_setup, x86_pmu.late_setup);
+
+	static_call_update(x86_pmu_pebs_enable, x86_pmu.pebs_enable);
+	static_call_update(x86_pmu_pebs_disable, x86_pmu.pebs_disable);
+	static_call_update(x86_pmu_pebs_enable_all, x86_pmu.pebs_enable_all);
+	static_call_update(x86_pmu_pebs_disable_all, x86_pmu.pebs_disable_all);
 }
 
 static void _x86_pmu_read(struct perf_event *event)
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index a95e6c91c4d7..9560f693fac0 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -80,54 +80,54 @@ static void *
 bts_buffer_setup_aux(struct perf_event *event, void **pages,
 		     int nr_pages, bool overwrite)
 {
-	struct bts_buffer *buf;
+	struct bts_buffer *bb;
 	struct page *page;
 	int cpu = event->cpu;
 	int node = (cpu == -1) ? cpu : cpu_to_node(cpu);
 	unsigned long offset;
 	size_t size = nr_pages << PAGE_SHIFT;
-	int pg, nbuf, pad;
+	int pg, nr_buf, pad;
 
 	/* count all the high order buffers */
-	for (pg = 0, nbuf = 0; pg < nr_pages;) {
+	for (pg = 0, nr_buf = 0; pg < nr_pages;) {
 		page = virt_to_page(pages[pg]);
 		pg += buf_nr_pages(page);
-		nbuf++;
+		nr_buf++;
 	}
 
 	/*
 	 * to avoid interrupts in overwrite mode, only allow one physical
 	 */
-	if (overwrite && nbuf > 1)
+	if (overwrite && nr_buf > 1)
 		return NULL;
 
-	buf = kzalloc_node(offsetof(struct bts_buffer, buf[nbuf]), GFP_KERNEL, node);
-	if (!buf)
+	bb = kzalloc_node(struct_size(bb, buf, nr_buf), GFP_KERNEL, node);
+	if (!bb)
 		return NULL;
 
-	buf->nr_pages = nr_pages;
-	buf->nr_bufs = nbuf;
-	buf->snapshot = overwrite;
-	buf->data_pages = pages;
-	buf->real_size = size - size % BTS_RECORD_SIZE;
+	bb->nr_pages = nr_pages;
+	bb->nr_bufs = nr_buf;
+	bb->snapshot = overwrite;
+	bb->data_pages = pages;
+	bb->real_size = size - size % BTS_RECORD_SIZE;
 
-	for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) {
+	for (pg = 0, nr_buf = 0, offset = 0, pad = 0; nr_buf < bb->nr_bufs; nr_buf++) {
 		unsigned int __nr_pages;
 
 		page = virt_to_page(pages[pg]);
 		__nr_pages = buf_nr_pages(page);
-		buf->buf[nbuf].page = page;
-		buf->buf[nbuf].offset = offset;
-		buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
-		buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement;
-		pad = buf->buf[nbuf].size % BTS_RECORD_SIZE;
-		buf->buf[nbuf].size -= pad;
+		bb->buf[nr_buf].page = page;
+		bb->buf[nr_buf].offset = offset;
+		bb->buf[nr_buf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
+		bb->buf[nr_buf].size = buf_size(page) - bb->buf[nr_buf].displacement;
+		pad = bb->buf[nr_buf].size % BTS_RECORD_SIZE;
+		bb->buf[nr_buf].size -= pad;
 
 		pg += __nr_pages;
 		offset += __nr_pages << PAGE_SHIFT;
 	}
 
-	return buf;
+	return bb;
 }
 
 static void bts_buffer_free_aux(void *data)
@@ -135,25 +135,25 @@ static void bts_buffer_free_aux(void *data)
 	kfree(data);
 }
 
-static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx)
+static unsigned long bts_buffer_offset(struct bts_buffer *bb, unsigned int idx)
 {
-	return buf->buf[idx].offset + buf->buf[idx].displacement;
+	return bb->buf[idx].offset + bb->buf[idx].displacement;
 }
 
 static void
-bts_config_buffer(struct bts_buffer *buf)
+bts_config_buffer(struct bts_buffer *bb)
 {
 	int cpu = raw_smp_processor_id();
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	struct bts_phys *phys = &buf->buf[buf->cur_buf];
+	struct bts_phys *phys = &bb->buf[bb->cur_buf];
 	unsigned long index, thresh = 0, end = phys->size;
 	struct page *page = phys->page;
 
-	index = local_read(&buf->head);
+	index = local_read(&bb->head);
 
-	if (!buf->snapshot) {
-		if (buf->end < phys->offset + buf_size(page))
-			end = buf->end - phys->offset - phys->displacement;
+	if (!bb->snapshot) {
+		if (bb->end < phys->offset + buf_size(page))
+			end = bb->end - phys->offset - phys->displacement;
 
 		index -= phys->offset + phys->displacement;
 
@@ -168,7 +168,7 @@ bts_config_buffer(struct bts_buffer *buf)
 	ds->bts_buffer_base = (u64)(long)page_address(page) + phys->displacement;
 	ds->bts_index = ds->bts_buffer_base + index;
 	ds->bts_absolute_maximum = ds->bts_buffer_base + end;
-	ds->bts_interrupt_threshold = !buf->snapshot
+	ds->bts_interrupt_threshold = !bb->snapshot
 		? ds->bts_buffer_base + thresh
 		: ds->bts_absolute_maximum + BTS_RECORD_SIZE;
 }
@@ -184,16 +184,16 @@ static void bts_update(struct bts_ctx *bts)
 {
 	int cpu = raw_smp_processor_id();
 	struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_buffer *bb = perf_get_aux(&bts->handle);
 	unsigned long index = ds->bts_index - ds->bts_buffer_base, old, head;
 
-	if (!buf)
+	if (!bb)
 		return;
 
-	head = index + bts_buffer_offset(buf, buf->cur_buf);
-	old = local_xchg(&buf->head, head);
+	head = index + bts_buffer_offset(bb, bb->cur_buf);
+	old = local_xchg(&bb->head, head);
 
-	if (!buf->snapshot) {
+	if (!bb->snapshot) {
 		if (old == head)
 			return;
 
@@ -205,9 +205,9 @@ static void bts_update(struct bts_ctx *bts)
 		 * old and head are always in the same physical buffer, so we
 		 * can subtract them to get the data size.
 		 */
-		local_add(head - old, &buf->data_size);
+		local_add(head - old, &bb->data_size);
 	} else {
-		local_set(&buf->data_size, head);
+		local_set(&bb->data_size, head);
 	}
 
 	/*
@@ -218,7 +218,7 @@ static void bts_update(struct bts_ctx *bts)
 }
 
 static int
-bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+bts_buffer_reset(struct bts_buffer *bb, struct perf_output_handle *handle);
 
 /*
  * Ordering PMU callbacks wrt themselves and the PMI is done by means
@@ -232,17 +232,17 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
 static void __bts_event_start(struct perf_event *event)
 {
 	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
-	struct bts_buffer *buf = perf_get_aux(&bts->handle);
+	struct bts_buffer *bb = perf_get_aux(&bts->handle);
 	u64 config = 0;
 
-	if (!buf->snapshot)
+	if (!bb->snapshot)
 		config |= ARCH_PERFMON_EVENTSEL_INT;
 	if (!event->attr.exclude_kernel)
 		config |= ARCH_PERFMON_EVENTSEL_OS;
 	if (!event->attr.exclude_user)
 		config |= ARCH_PERFMON_EVENTSEL_USR;
 
-	bts_config_buffer(buf);
+	bts_config_buffer(bb);
 
 	/*
 	 * local barrier to make sure that ds configuration made it
@@ -261,13 +261,13 @@ static void bts_event_start(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
-	struct bts_buffer *buf;
+	struct bts_buffer *bb;
 
-	buf = perf_aux_output_begin(&bts->handle, event);
-	if (!buf)
+	bb = perf_aux_output_begin(&bts->handle, event);
+	if (!bb)
 		goto fail_stop;
 
-	if (bts_buffer_reset(buf, &bts->handle))
+	if (bts_buffer_reset(bb, &bts->handle))
 		goto fail_end_stop;
 
 	bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
@@ -306,27 +306,27 @@ static void bts_event_stop(struct perf_event *event, int flags)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
-	struct bts_buffer *buf = NULL;
+	struct bts_buffer *bb = NULL;
 	int state = READ_ONCE(bts->state);
 
 	if (state == BTS_STATE_ACTIVE)
 		__bts_event_stop(event, BTS_STATE_STOPPED);
 
 	if (state != BTS_STATE_STOPPED)
-		buf = perf_get_aux(&bts->handle);
+		bb = perf_get_aux(&bts->handle);
 
 	event->hw.state |= PERF_HES_STOPPED;
 
 	if (flags & PERF_EF_UPDATE) {
 		bts_update(bts);
 
-		if (buf) {
-			if (buf->snapshot)
+		if (bb) {
+			if (bb->snapshot)
 				bts->handle.head =
-					local_xchg(&buf->data_size,
-						   buf->nr_pages << PAGE_SHIFT);
+					local_xchg(&bb->data_size,
+						   bb->nr_pages << PAGE_SHIFT);
 			perf_aux_output_end(&bts->handle,
-			                    local_xchg(&buf->data_size, 0));
+					    local_xchg(&bb->data_size, 0));
 		}
 
 		cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
@@ -382,19 +382,19 @@ void intel_bts_disable_local(void)
 }
 
 static int
-bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
+bts_buffer_reset(struct bts_buffer *bb, struct perf_output_handle *handle)
 {
 	unsigned long head, space, next_space, pad, gap, skip, wakeup;
 	unsigned int next_buf;
 	struct bts_phys *phys, *next_phys;
 	int ret;
 
-	if (buf->snapshot)
+	if (bb->snapshot)
 		return 0;
 
-	head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
+	head = handle->head & ((bb->nr_pages << PAGE_SHIFT) - 1);
 
-	phys = &buf->buf[buf->cur_buf];
+	phys = &bb->buf[bb->cur_buf];
 	space = phys->offset + phys->displacement + phys->size - head;
 	pad = space;
 	if (space > handle->size) {
@@ -403,10 +403,10 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 	}
 	if (space <= BTS_SAFETY_MARGIN) {
 		/* See if next phys buffer has more space */
-		next_buf = buf->cur_buf + 1;
-		if (next_buf >= buf->nr_bufs)
+		next_buf = bb->cur_buf + 1;
+		if (next_buf >= bb->nr_bufs)
 			next_buf = 0;
-		next_phys = &buf->buf[next_buf];
+		next_phys = &bb->buf[next_buf];
 		gap = buf_size(phys->page) - phys->displacement - phys->size +
 		      next_phys->displacement;
 		skip = pad + gap;
@@ -431,8 +431,8 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 				 * anymore, so we must not be racing with
 				 * bts_update().
 				 */
-				buf->cur_buf = next_buf;
-				local_set(&buf->head, head);
+				bb->cur_buf = next_buf;
+				local_set(&bb->head, head);
 			}
 		}
 	}
@@ -445,7 +445,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 		space -= space % BTS_RECORD_SIZE;
 	}
 
-	buf->end = head + space;
+	bb->end = head + space;
 
 	/*
 	 * If we have no space, the lost notification would have been sent when
@@ -462,7 +462,7 @@ int intel_bts_interrupt(void)
 	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
 	struct bts_ctx *bts;
 	struct perf_event *event;
-	struct bts_buffer *buf;
+	struct bts_buffer *bb;
 	s64 old_head;
 	int err = -ENOSPC, handled = 0;
 
@@ -485,8 +485,8 @@ int intel_bts_interrupt(void)
 	if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
 		return handled;
 
-	buf = perf_get_aux(&bts->handle);
-	if (!buf)
+	bb = perf_get_aux(&bts->handle);
+	if (!bb)
 		return handled;
 
 	/*
@@ -494,26 +494,26 @@ int intel_bts_interrupt(void)
 	 * there's no other way of telling, because the pointer will
 	 * keep moving
 	 */
-	if (buf->snapshot)
+	if (bb->snapshot)
 		return 0;
 
-	old_head = local_read(&buf->head);
+	old_head = local_read(&bb->head);
 	bts_update(bts);
 
 	/* no new data */
-	if (old_head == local_read(&buf->head))
+	if (old_head == local_read(&bb->head))
 		return handled;
 
-	perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0));
+	perf_aux_output_end(&bts->handle, local_xchg(&bb->data_size, 0));
 
-	buf = perf_aux_output_begin(&bts->handle, event);
-	if (buf)
-		err = bts_buffer_reset(buf, &bts->handle);
+	bb = perf_aux_output_begin(&bts->handle, event);
+	if (bb)
+		err = bts_buffer_reset(bb, &bts->handle);
 
 	if (err) {
 		WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
 
-		if (buf) {
+		if (bb) {
 			/*
 			 * BTS_STATE_STOPPED should be visible before
 			 * cleared handle::event
@@ -599,7 +599,11 @@ static void bts_event_read(struct perf_event *event)
 
 static __init int bts_init(void)
 {
-	if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
+	if (!boot_cpu_has(X86_FEATURE_DTES64))
+		return -ENODEV;
+
+	x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
+	if (!x86_pmu.bts)
 		return -ENODEV;
 
 	if (boot_cpu_has(X86_FEATURE_PTI)) {
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index c5f385413392..3204591249e8 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -2224,6 +2224,18 @@ static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
+EVENT_ATTR_STR(topdown-fe-bound,       td_fe_bound_skt,        "event=0x9c,umask=0x01");
+EVENT_ATTR_STR(topdown-retiring,       td_retiring_skt,        "event=0xc2,umask=0x02");
+EVENT_ATTR_STR(topdown-be-bound,       td_be_bound_skt,        "event=0xa4,umask=0x02");
+
+static struct attribute *skt_events_attrs[] = {
+	EVENT_PTR(td_fe_bound_skt),
+	EVENT_PTR(td_retiring_skt),
+	EVENT_PTR(td_bad_spec_cmt),
+	EVENT_PTR(td_be_bound_skt),
+	NULL,
+};
+
 #define KNL_OT_L2_HITE		BIT_ULL(19) /* Other Tile L2 Hit */
 #define KNL_OT_L2_HITF		BIT_ULL(20) /* Other Tile L2 Hit */
 #define KNL_MCDRAM_LOCAL	BIT_ULL(21)
@@ -2294,7 +2306,7 @@ static __always_inline void __intel_pmu_disable_all(bool bts)
 static __always_inline void intel_pmu_disable_all(void)
 {
 	__intel_pmu_disable_all(true);
-	intel_pmu_pebs_disable_all();
+	static_call_cond(x86_pmu_pebs_disable_all)();
 	intel_pmu_lbr_disable_all();
 }
 
@@ -2326,7 +2338,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
 
 static void intel_pmu_enable_all(int added)
 {
-	intel_pmu_pebs_enable_all();
+	static_call_cond(x86_pmu_pebs_enable_all)();
 	__intel_pmu_enable_all(added, false);
 }
 
@@ -2583,7 +2595,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
 	 * so we don't trigger the event without PEBS bit set.
 	 */
 	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_disable(event);
+		static_call(x86_pmu_pebs_disable)(event);
 }
 
 static void intel_pmu_assign_event(struct perf_event *event, int idx)
@@ -2603,6 +2615,9 @@ static void intel_pmu_del_event(struct perf_event *event)
 		intel_pmu_lbr_del(event);
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_del(event);
+	if (is_pebs_counter_event_group(event) ||
+	    is_acr_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
 }
 
 static int icl_set_topdown_event_period(struct perf_event *event)
@@ -2880,6 +2895,52 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
 	cpuc->fixed_ctrl_val |= bits;
 }
 
+static void intel_pmu_config_acr(int idx, u64 mask, u32 reload)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	int msr_b, msr_c;
+
+	if (!mask && !cpuc->acr_cfg_b[idx])
+		return;
+
+	if (idx < INTEL_PMC_IDX_FIXED) {
+		msr_b = MSR_IA32_PMC_V6_GP0_CFG_B;
+		msr_c = MSR_IA32_PMC_V6_GP0_CFG_C;
+	} else {
+		msr_b = MSR_IA32_PMC_V6_FX0_CFG_B;
+		msr_c = MSR_IA32_PMC_V6_FX0_CFG_C;
+		idx -= INTEL_PMC_IDX_FIXED;
+	}
+
+	if (cpuc->acr_cfg_b[idx] != mask) {
+		wrmsrl(msr_b + x86_pmu.addr_offset(idx, false), mask);
+		cpuc->acr_cfg_b[idx] = mask;
+	}
+	/* Only need to update the reload value when there is a valid config value. */
+	if (mask && cpuc->acr_cfg_c[idx] != reload) {
+		wrmsrl(msr_c + x86_pmu.addr_offset(idx, false), reload);
+		cpuc->acr_cfg_c[idx] = reload;
+	}
+}
+
+static void intel_pmu_enable_acr(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (!is_acr_event_group(event) || !event->attr.config2) {
+		/*
+		 * The disable doesn't clear the ACR CFG register.
+		 * Check and clear the ACR CFG register.
+		 */
+		intel_pmu_config_acr(hwc->idx, 0, 0);
+		return;
+	}
+
+	intel_pmu_config_acr(hwc->idx, hwc->config1, -hwc->sample_period);
+}
+
+DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
+
 static void intel_pmu_enable_event(struct perf_event *event)
 {
 	u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
@@ -2887,16 +2948,19 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	int idx = hwc->idx;
 
 	if (unlikely(event->attr.precise_ip))
-		intel_pmu_pebs_enable(event);
+		static_call(x86_pmu_pebs_enable)(event);
 
 	switch (idx) {
 	case 0 ... INTEL_PMC_IDX_FIXED - 1:
 		if (branch_sample_counters(event))
 			enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
 		intel_set_masks(event, idx);
+		static_call_cond(intel_pmu_enable_acr_event)(event);
 		__x86_pmu_enable_event(hwc, enable_mask);
 		break;
 	case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+		static_call_cond(intel_pmu_enable_acr_event)(event);
+		fallthrough;
 	case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
 		intel_pmu_enable_fixed(event);
 		break;
@@ -2914,12 +2978,51 @@ static void intel_pmu_enable_event(struct perf_event *event)
 	}
 }
 
+static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc)
+{
+	struct perf_event *event, *leader;
+	int i, j, idx;
+
+	for (i = 0; i < cpuc->n_events; i++) {
+		leader = cpuc->event_list[i];
+		if (!is_acr_event_group(leader))
+			continue;
+
+		/* The ACR events must be contiguous. */
+		for (j = i; j < cpuc->n_events; j++) {
+			event = cpuc->event_list[j];
+			if (event->group_leader != leader->group_leader)
+				break;
+			for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
+				if (WARN_ON_ONCE(i + idx > cpuc->n_events))
+					return;
+				__set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1);
+			}
+		}
+		i = j - 1;
+	}
+}
+
+void intel_pmu_late_setup(void)
+{
+	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+	if (!cpuc->n_late_setup)
+		return;
+
+	intel_pmu_pebs_late_setup(cpuc);
+	intel_pmu_acr_late_setup(cpuc);
+}
+
 static void intel_pmu_add_event(struct perf_event *event)
 {
 	if (event->attr.precise_ip)
 		intel_pmu_pebs_add(event);
 	if (intel_pmu_needs_branch_stack(event))
 		intel_pmu_lbr_add(event);
+	if (is_pebs_counter_event_group(event) ||
+	    is_acr_event_group(event))
+		this_cpu_ptr(&cpu_hw_events)->n_late_setup++;
 }
 
 /*
@@ -3035,8 +3138,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
 			continue;
 
 		perf_sample_data_init(data, 0, event->hw.last_period);
-		if (perf_event_overflow(event, data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, data, regs);
 
 		/* Inject one fake event is enough. */
 		break;
@@ -3141,6 +3243,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
+		u64 last_period;
 
 		handled++;
 
@@ -3168,16 +3271,17 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
 		if (is_pebs_counter_event_group(event))
 			x86_pmu.drain_pebs(regs, &data);
 
+		last_period = event->hw.last_period;
+
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
 		if (has_branch_stack(event))
 			intel_pmu_lbr_save_brstack(&data, cpuc, event);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	return handled;
@@ -3739,10 +3843,9 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 	if (cpuc->excl_cntrs)
 		return intel_get_excl_constraints(cpuc, event, idx, c2);
 
-	/* Not all counters support the branch counter feature. */
-	if (branch_sample_counters(event)) {
+	if (event->hw.dyn_constraint != ~0ULL) {
 		c2 = dyn_constraint(cpuc, c2, idx);
-		c2->idxmsk64 &= x86_pmu.lbr_counters;
+		c2->idxmsk64 &= event->hw.dyn_constraint;
 		c2->weight = hweight64(c2->idxmsk64);
 	}
 
@@ -4083,6 +4186,39 @@ end:
 	return start;
 }
 
+static inline bool intel_pmu_has_acr(struct pmu *pmu)
+{
+	return !!hybrid(pmu, acr_cause_mask64);
+}
+
+static bool intel_pmu_is_acr_group(struct perf_event *event)
+{
+	/* The group leader has the ACR flag set */
+	if (is_acr_event_group(event))
+		return true;
+
+	/* The acr_mask is set */
+	if (event->attr.config2)
+		return true;
+
+	return false;
+}
+
+static inline void intel_pmu_set_acr_cntr_constr(struct perf_event *event,
+						 u64 *cause_mask, int *num)
+{
+	event->hw.dyn_constraint &= hybrid(event->pmu, acr_cntr_mask64);
+	*cause_mask |= event->attr.config2;
+	*num += 1;
+}
+
+static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event,
+						   int idx, u64 cause_mask)
+{
+	if (test_bit(idx, (unsigned long *)&cause_mask))
+		event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64);
+}
+
 static int intel_pmu_hw_config(struct perf_event *event)
 {
 	int ret = x86_pmu_hw_config(event);
@@ -4144,15 +4280,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
 		leader = event->group_leader;
 		if (branch_sample_call_stack(leader))
 			return -EINVAL;
-		if (branch_sample_counters(leader))
+		if (branch_sample_counters(leader)) {
 			num++;
+			leader->hw.dyn_constraint &= x86_pmu.lbr_counters;
+		}
 		leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
 
 		for_each_sibling_event(sibling, leader) {
 			if (branch_sample_call_stack(sibling))
 				return -EINVAL;
-			if (branch_sample_counters(sibling))
+			if (branch_sample_counters(sibling)) {
 				num++;
+				sibling->hw.dyn_constraint &= x86_pmu.lbr_counters;
+			}
 		}
 
 		if (num > fls(x86_pmu.lbr_counters))
@@ -4207,6 +4347,94 @@ static int intel_pmu_hw_config(struct perf_event *event)
 	    event->attr.precise_ip)
 		event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR;
 
+	if (intel_pmu_has_acr(event->pmu) && intel_pmu_is_acr_group(event)) {
+		struct perf_event *sibling, *leader = event->group_leader;
+		struct pmu *pmu = event->pmu;
+		bool has_sw_event = false;
+		int num = 0, idx = 0;
+		u64 cause_mask = 0;
+
+		/* Not support perf metrics */
+		if (is_metric_event(event))
+			return -EINVAL;
+
+		/* Not support freq mode */
+		if (event->attr.freq)
+			return -EINVAL;
+
+		/* PDist is not supported */
+		if (event->attr.config2 && event->attr.precise_ip > 2)
+			return -EINVAL;
+
+		/* The reload value cannot exceeds the max period */
+		if (event->attr.sample_period > x86_pmu.max_period)
+			return -EINVAL;
+		/*
+		 * The counter-constraints of each event cannot be finalized
+		 * unless the whole group is scanned. However, it's hard
+		 * to know whether the event is the last one of the group.
+		 * Recalculate the counter-constraints for each event when
+		 * adding a new event.
+		 *
+		 * The group is traversed twice, which may be optimized later.
+		 * In the first round,
+		 * - Find all events which do reload when other events
+		 *   overflow and set the corresponding counter-constraints
+		 * - Add all events, which can cause other events reload,
+		 *   in the cause_mask
+		 * - Error out if the number of events exceeds the HW limit
+		 * - The ACR events must be contiguous.
+		 *   Error out if there are non-X86 events between ACR events.
+		 *   This is not a HW limit, but a SW limit.
+		 *   With the assumption, the intel_pmu_acr_late_setup() can
+		 *   easily convert the event idx to counter idx without
+		 *   traversing the whole event list.
+		 */
+		if (!is_x86_event(leader))
+			return -EINVAL;
+
+		if (leader->attr.config2)
+			intel_pmu_set_acr_cntr_constr(leader, &cause_mask, &num);
+
+		if (leader->nr_siblings) {
+			for_each_sibling_event(sibling, leader) {
+				if (!is_x86_event(sibling)) {
+					has_sw_event = true;
+					continue;
+				}
+				if (!sibling->attr.config2)
+					continue;
+				if (has_sw_event)
+					return -EINVAL;
+				intel_pmu_set_acr_cntr_constr(sibling, &cause_mask, &num);
+			}
+		}
+		if (leader != event && event->attr.config2) {
+			if (has_sw_event)
+				return -EINVAL;
+			intel_pmu_set_acr_cntr_constr(event, &cause_mask, &num);
+		}
+
+		if (hweight64(cause_mask) > hweight64(hybrid(pmu, acr_cause_mask64)) ||
+		    num > hweight64(hybrid(event->pmu, acr_cntr_mask64)))
+			return -EINVAL;
+		/*
+		 * In the second round, apply the counter-constraints for
+		 * the events which can cause other events reload.
+		 */
+		intel_pmu_set_acr_caused_constr(leader, idx++, cause_mask);
+
+		if (leader->nr_siblings) {
+			for_each_sibling_event(sibling, leader)
+				intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask);
+		}
+
+		if (leader != event)
+			intel_pmu_set_acr_caused_constr(event, idx, cause_mask);
+
+		leader->hw.flags |= PERF_X86_EVENT_ACR;
+	}
+
 	if ((event->attr.type == PERF_TYPE_HARDWARE) ||
 	    (event->attr.type == PERF_TYPE_HW_CACHE))
 		return 0;
@@ -4354,7 +4582,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
 		.guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask,
 	};
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		return arr;
 
 	/*
@@ -4952,7 +5180,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
 			goto err;
 	}
 
-	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
+	if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_DYN_CONSTRAINT)) {
 		size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
 
 		cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -5041,7 +5269,7 @@ static inline bool intel_pmu_broken_perf_cap(void)
 	return false;
 }
 
-static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+static void update_pmu_cap(struct pmu *pmu)
 {
 	unsigned int cntr, fixed_cntr, ecx, edx;
 	union cpuid35_eax eax;
@@ -5050,20 +5278,30 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 	cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
 
 	if (ebx.split.umask2)
-		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
+		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_UMASK2;
 	if (ebx.split.eq)
-		pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
+		hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_EQ;
 
 	if (eax.split.cntr_subleaf) {
 		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
 			    &cntr, &fixed_cntr, &ecx, &edx);
-		pmu->cntr_mask64 = cntr;
-		pmu->fixed_cntr_mask64 = fixed_cntr;
+		hybrid(pmu, cntr_mask64) = cntr;
+		hybrid(pmu, fixed_cntr_mask64) = fixed_cntr;
+	}
+
+	if (eax.split.acr_subleaf) {
+		cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
+			    &cntr, &fixed_cntr, &ecx, &edx);
+		/* The mask of the counters which can be reloaded */
+		hybrid(pmu, acr_cntr_mask64) = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
+
+		/* The mask of the counters which can cause a reload of reloadable counters */
+		hybrid(pmu, acr_cause_mask64) = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
 	}
 
 	if (!intel_pmu_broken_perf_cap()) {
 		/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
-		rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, hybrid(pmu, intel_cap).capabilities);
 	}
 }
 
@@ -5150,7 +5388,7 @@ static bool init_hybrid_pmu(int cpu)
 		goto end;
 
 	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
-		update_pmu_cap(pmu);
+		update_pmu_cap(&pmu->pmu);
 
 	intel_pmu_check_hybrid_pmus(pmu);
 
@@ -5524,7 +5762,7 @@ static __init void intel_clovertown_quirk(void)
 	 * these chips.
 	 */
 	pr_warn("PEBS disabled due to CPU errata\n");
-	x86_pmu.pebs = 0;
+	x86_pmu.ds_pebs = 0;
 	x86_pmu.pebs_constraints = NULL;
 }
 
@@ -6012,7 +6250,7 @@ tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 static umode_t
 pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 {
-	return x86_pmu.pebs ? attr->mode : 0;
+	return x86_pmu.ds_pebs ? attr->mode : 0;
 }
 
 static umode_t
@@ -6043,6 +6281,21 @@ td_is_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return attr->mode;
 }
 
+PMU_FORMAT_ATTR(acr_mask,	"config2:0-63");
+
+static struct attribute *format_acr_attrs[] = {
+	&format_attr_acr_mask.attr,
+	NULL
+};
+
+static umode_t
+acr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+
+	return intel_pmu_has_acr(dev_get_drvdata(dev)) ? attr->mode : 0;
+}
+
 static struct attribute_group group_events_td  = {
 	.name = "events",
 	.is_visible = td_is_visible,
@@ -6085,6 +6338,12 @@ static struct attribute_group group_format_evtsel_ext = {
 	.is_visible = evtsel_ext_is_visible,
 };
 
+static struct attribute_group group_format_acr = {
+	.name       = "format",
+	.attrs      = format_acr_attrs,
+	.is_visible = acr_is_visible,
+};
+
 static struct attribute_group group_default = {
 	.attrs      = intel_pmu_attrs,
 	.is_visible = default_is_visible,
@@ -6099,6 +6358,7 @@ static const struct attribute_group *attr_update[] = {
 	&group_format_extra,
 	&group_format_extra_skl,
 	&group_format_evtsel_ext,
+	&group_format_acr,
 	&group_default,
 	NULL,
 };
@@ -6383,6 +6643,7 @@ static const struct attribute_group *hybrid_attr_update[] = {
 	&group_caps_lbr,
 	&hybrid_group_format_extra,
 	&group_format_evtsel_ext,
+	&group_format_acr,
 	&group_default,
 	&hybrid_group_cpus,
 	NULL,
@@ -6575,6 +6836,7 @@ static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
 	intel_pmu_init_grt(pmu);
 	hybrid(pmu, event_constraints) = intel_skt_event_constraints;
 	hybrid(pmu, extra_regs) = intel_cmt_extra_regs;
+	static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
 }
 
 __init int intel_pmu_init(void)
@@ -6635,6 +6897,7 @@ __init int intel_pmu_init(void)
 
 	x86_pmu.pebs_events_mask	= intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
 	x86_pmu.pebs_capable		= PEBS_COUNTER_MASK;
+	x86_pmu.config_mask		= X86_RAW_EVENT_MASK;
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
@@ -6663,7 +6926,7 @@ __init int intel_pmu_init(void)
 	if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
 		intel_pmu_arch_lbr_init();
 
-	intel_ds_init();
+	intel_pebs_init();
 
 	x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
 
@@ -6674,6 +6937,12 @@ __init int intel_pmu_init(void)
 	}
 
 	/*
+	 * Many features on and after V6 require dynamic constraint,
+	 * e.g., Arch PEBS, ACR.
+	 */
+	if (version >= 6)
+		x86_pmu.flags |= PMU_FL_DYN_CONSTRAINT;
+	/*
 	 * Install the hw-cache-events table:
 	 */
 	switch (boot_cpu_data.x86_vfm) {
@@ -6884,6 +7153,18 @@ __init int intel_pmu_init(void)
 		name = "crestmont";
 		break;
 
+	case INTEL_ATOM_DARKMONT_X:
+		intel_pmu_init_skt(NULL);
+		intel_pmu_pebs_data_source_cmt();
+		x86_pmu.pebs_latency_data = cmt_latency_data;
+		x86_pmu.get_event_constraints = cmt_get_event_constraints;
+		td_attr = skt_events_attrs;
+		mem_attr = grt_mem_attrs;
+		extra_attr = cmt_format_attr;
+		pr_cont("Darkmont events, ");
+		name = "darkmont";
+		break;
+
 	case INTEL_WESTMERE:
 	case INTEL_WESTMERE_EP:
 	case INTEL_WESTMERE_EX:
@@ -7433,6 +7714,18 @@ __init int intel_pmu_init(void)
 		x86_pmu.attr_update = hybrid_attr_update;
 	}
 
+	/*
+	 * The archPerfmonExt (0x23) includes an enhanced enumeration of
+	 * PMU architectural features with a per-core view. For non-hybrid,
+	 * each core has the same PMU capabilities. It's good enough to
+	 * update the x86_pmu from the booting CPU. For hybrid, the x86_pmu
+	 * is used to keep the common capabilities. Still keep the values
+	 * from the leaf 0xa. The core specific update will be done later
+	 * when a new type is online.
+	 */
+	if (!is_hybrid() && boot_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+		update_pmu_cap(NULL);
+
 	intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
 				      &x86_pmu.fixed_cntr_mask64,
 				      &x86_pmu.intel_ctrl);
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8d86e91bd5e5..e2ea4fdedea9 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -624,7 +624,7 @@ static int alloc_pebs_buffer(int cpu)
 	int max, node = cpu_to_node(cpu);
 	void *buffer, *insn_buff, *cea;
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		return 0;
 
 	buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
@@ -659,7 +659,7 @@ static void release_pebs_buffer(int cpu)
 	struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
 	void *cea;
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		return;
 
 	kfree(per_cpu(insn_buffer, cpu));
@@ -734,7 +734,7 @@ void release_ds_buffers(void)
 {
 	int cpu;
 
-	if (!x86_pmu.bts && !x86_pmu.pebs)
+	if (!x86_pmu.bts && !x86_pmu.ds_pebs)
 		return;
 
 	for_each_possible_cpu(cpu)
@@ -750,7 +750,8 @@ void release_ds_buffers(void)
 	}
 
 	for_each_possible_cpu(cpu) {
-		release_pebs_buffer(cpu);
+		if (x86_pmu.ds_pebs)
+			release_pebs_buffer(cpu);
 		release_bts_buffer(cpu);
 	}
 }
@@ -761,15 +762,17 @@ void reserve_ds_buffers(void)
 	int cpu;
 
 	x86_pmu.bts_active = 0;
-	x86_pmu.pebs_active = 0;
 
-	if (!x86_pmu.bts && !x86_pmu.pebs)
+	if (x86_pmu.ds_pebs)
+		x86_pmu.pebs_active = 0;
+
+	if (!x86_pmu.bts && !x86_pmu.ds_pebs)
 		return;
 
 	if (!x86_pmu.bts)
 		bts_err = 1;
 
-	if (!x86_pmu.pebs)
+	if (!x86_pmu.ds_pebs)
 		pebs_err = 1;
 
 	for_each_possible_cpu(cpu) {
@@ -781,7 +784,8 @@ void reserve_ds_buffers(void)
 		if (!bts_err && alloc_bts_buffer(cpu))
 			bts_err = 1;
 
-		if (!pebs_err && alloc_pebs_buffer(cpu))
+		if (x86_pmu.ds_pebs && !pebs_err &&
+		    alloc_pebs_buffer(cpu))
 			pebs_err = 1;
 
 		if (bts_err && pebs_err)
@@ -793,7 +797,7 @@ void reserve_ds_buffers(void)
 			release_bts_buffer(cpu);
 	}
 
-	if (pebs_err) {
+	if (x86_pmu.ds_pebs && pebs_err) {
 		for_each_possible_cpu(cpu)
 			release_pebs_buffer(cpu);
 	}
@@ -805,7 +809,7 @@ void reserve_ds_buffers(void)
 		if (x86_pmu.bts && !bts_err)
 			x86_pmu.bts_active = 1;
 
-		if (x86_pmu.pebs && !pebs_err)
+		if (x86_pmu.ds_pebs && !pebs_err)
 			x86_pmu.pebs_active = 1;
 
 		for_each_possible_cpu(cpu) {
@@ -1355,9 +1359,8 @@ static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
 }
 
 
-static void intel_pmu_late_setup(void)
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc)
 {
-	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct perf_event *event;
 	u64 pebs_data_cfg = 0;
 	int i;
@@ -1828,8 +1831,6 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
 
 	perf_sample_data_init(data, 0, event->hw.last_period);
 
-	data->period = event->hw.last_period;
-
 	/*
 	 * Use latency for weight (only avail with PEBS-LL)
 	 */
@@ -2082,7 +2083,6 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
 	sample_type = event->attr.sample_type;
 	format_group = basic->format_group;
 	perf_sample_data_init(data, 0, event->hw.last_period);
-	data->period = event->hw.last_period;
 
 	setup_pebs_time(event, data, basic->tsc);
 
@@ -2359,8 +2359,7 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
 		 * All but the last records are processed.
 		 * The last one is left to be able to call the overflow handler.
 		 */
-		if (perf_event_overflow(event, data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, data, regs);
 	}
 
 	if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -2589,8 +2588,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
 		if (error[bit]) {
 			perf_log_lost_samples(event, error[bit]);
 
-			if (iregs && perf_event_account_interrupt(event))
-				x86_pmu_stop(event, 0);
+			if (iregs)
+				perf_event_account_interrupt(event);
 		}
 
 		if (counts[bit]) {
@@ -2670,10 +2669,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
 }
 
 /*
- * BTS, PEBS probe and setup
+ * PEBS probe and setup
  */
 
-void __init intel_ds_init(void)
+void __init intel_pebs_init(void)
 {
 	/*
 	 * No support for 32bit formats
@@ -2681,13 +2680,12 @@ void __init intel_ds_init(void)
 	if (!boot_cpu_has(X86_FEATURE_DTES64))
 		return;
 
-	x86_pmu.bts  = boot_cpu_has(X86_FEATURE_BTS);
-	x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+	x86_pmu.ds_pebs = boot_cpu_has(X86_FEATURE_PEBS);
 	x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
 	if (x86_pmu.version <= 4)
 		x86_pmu.pebs_no_isolation = 1;
 
-	if (x86_pmu.pebs) {
+	if (x86_pmu.ds_pebs) {
 		char pebs_type = x86_pmu.intel_cap.pebs_trap ?  '+' : '-';
 		char *pebs_qual = "";
 		int format = x86_pmu.intel_cap.pebs_format;
@@ -2695,6 +2693,11 @@ void __init intel_ds_init(void)
 		if (format < 4)
 			x86_pmu.intel_cap.pebs_baseline = 0;
 
+		x86_pmu.pebs_enable = intel_pmu_pebs_enable;
+		x86_pmu.pebs_disable = intel_pmu_pebs_disable;
+		x86_pmu.pebs_enable_all = intel_pmu_pebs_enable_all;
+		x86_pmu.pebs_disable_all = intel_pmu_pebs_disable_all;
+
 		switch (format) {
 		case 0:
 			pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -2779,7 +2782,7 @@ void __init intel_ds_init(void)
 
 		default:
 			pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
-			x86_pmu.pebs = 0;
+			x86_pmu.ds_pebs = 0;
 		}
 	}
 }
@@ -2788,7 +2791,7 @@ void perf_restore_debug_store(void)
 {
 	struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
 
-	if (!x86_pmu.bts && !x86_pmu.pebs)
+	if (!x86_pmu.bts && !x86_pmu.ds_pebs)
 		return;
 
 	wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 034a1f6a457c..384589168c1a 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -241,19 +241,20 @@ again:
 
 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];
+		u64 last_period;
 
 		handled++;
 
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;
 
+		last_period = event->hw.last_period;
 		if (!intel_pmu_save_and_restart(event))
 			continue;
 
-		perf_sample_data_init(&data, 0, event->hw.last_period);
+		perf_sample_data_init(&data, 0, last_period);
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	/*
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f44c3d866f24..05acd6449ceb 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -1618,7 +1618,7 @@ void __init intel_pmu_arch_lbr_init(void)
 	x86_pmu.lbr_nr = lbr_nr;
 
 	if (!!x86_pmu.lbr_counters)
-		x86_pmu.flags |= PMU_FL_BR_CNTR;
+		x86_pmu.flags |= PMU_FL_BR_CNTR | PMU_FL_DYN_CONSTRAINT;
 
 	if (x86_pmu.lbr_mispred)
 		static_branch_enable(&x86_lbr_mispred);
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index c85a9fc44355..126d5ae264cb 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -1072,8 +1072,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 			continue;
 
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	if (handled)
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fa37565f6418..25ead919fc48 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -1863,6 +1863,8 @@ static __init int pt_init(void)
 
 	if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
 		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
+	else
+		pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_PREFER_LARGE;
 
 	pt_pmu.pmu.capabilities		|= PERF_PMU_CAP_EXCLUSIVE |
 					   PERF_PMU_CAP_ITRACE |
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index a34e50fc4a8f..5811e172f721 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -305,17 +305,11 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 {
 	struct intel_uncore_box *box;
 	struct perf_event *event;
-	unsigned long flags;
 	int bit;
 
 	box = container_of(hrtimer, struct intel_uncore_box, hrtimer);
 	if (!box->n_active || box->cpu != smp_processor_id())
 		return HRTIMER_NORESTART;
-	/*
-	 * disable local interrupt to prevent uncore_pmu_event_start/stop
-	 * to interrupt the update process
-	 */
-	local_irq_save(flags);
 
 	/*
 	 * handle boxes with an active event list as opposed to active
@@ -328,8 +322,6 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 	for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
 		uncore_perf_event_update(box, box->events[bit]);
 
-	local_irq_restore(flags);
-
 	hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
 	return HRTIMER_RESTART;
 }
@@ -337,7 +329,7 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
 void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
 {
 	hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
-		      HRTIMER_MODE_REL_PINNED);
+		      HRTIMER_MODE_REL_PINNED_HARD);
 }
 
 void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -347,7 +339,7 @@ void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
 
 static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
 {
-	hrtimer_setup(&box->hrtimer, uncore_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	hrtimer_setup(&box->hrtimer, uncore_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
 }
 
 static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 46d120597bab..e8bce89821be 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -127,6 +127,11 @@ 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 */
@@ -268,6 +273,7 @@ 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;
@@ -293,6 +299,10 @@ 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];
+
 	/*
 	 * Intel LBR bits
 	 */
@@ -714,6 +724,15 @@ struct x86_hybrid_pmu {
 			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
@@ -796,6 +815,10 @@ struct x86_pmu {
 	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;
@@ -812,6 +835,14 @@ struct x86_pmu {
 			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 {
@@ -878,7 +909,7 @@ struct x86_pmu {
 	 */
 	unsigned int	bts			:1,
 			bts_active		:1,
-			pebs			:1,
+			ds_pebs			:1,
 			pebs_active		:1,
 			pebs_broken		:1,
 			pebs_prec_dist		:1,
@@ -1049,6 +1080,7 @@ do {									\
 #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
@@ -1091,6 +1123,7 @@ static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\
 	.pmu_type	= _pmu,						\
 }
 
+int is_x86_event(struct perf_event *event);
 struct pmu *x86_get_pmu(unsigned int cpu);
 extern struct x86_pmu x86_pmu __read_mostly;
 
@@ -1098,6 +1131,10 @@ 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)
 {
@@ -1587,6 +1624,8 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
+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);
@@ -1643,11 +1682,13 @@ void intel_pmu_pebs_disable_all(void);
 
 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_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_save_brstack(struct perf_sample_data *data,
 				struct cpu_hw_events *cpuc,
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index 1d9e385649b5..70078334e4a3 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -2,23 +2,24 @@
 /*
  * struct hw_perf_event.flags flags
  */
-PERF_ARCH(PEBS_LDLAT,		0x00001) /* ld+ldlat data address sampling */
-PERF_ARCH(PEBS_ST,		0x00002) /* st data address sampling */
-PERF_ARCH(PEBS_ST_HSW,		0x00004) /* haswell style datala, store */
-PERF_ARCH(PEBS_LD_HSW,		0x00008) /* haswell style datala, load */
-PERF_ARCH(PEBS_NA_HSW,		0x00010) /* haswell style datala, unknown */
-PERF_ARCH(EXCL,			0x00020) /* HT exclusivity on counter */
-PERF_ARCH(DYNAMIC,		0x00040) /* dynamic alloc'd constraint */
-PERF_ARCH(PEBS_CNTR,		0x00080) /* PEBS counters snapshot */
-PERF_ARCH(EXCL_ACCT,		0x00100) /* accounted EXCL event */
-PERF_ARCH(AUTO_RELOAD,		0x00200) /* use PEBS auto-reload */
-PERF_ARCH(LARGE_PEBS,		0x00400) /* use large PEBS */
-PERF_ARCH(PEBS_VIA_PT,		0x00800) /* use PT buffer for PEBS */
-PERF_ARCH(PAIR,			0x01000) /* Large Increment per Cycle */
-PERF_ARCH(LBR_SELECT,		0x02000) /* Save/Restore MSR_LBR_SELECT */
-PERF_ARCH(TOPDOWN,		0x04000) /* Count Topdown slots/metrics events */
-PERF_ARCH(PEBS_STLAT,		0x08000) /* st+stlat data address sampling */
-PERF_ARCH(AMD_BRS,		0x10000) /* AMD Branch Sampling */
-PERF_ARCH(PEBS_LAT_HYBRID,	0x20000) /* ld and st lat for hybrid */
-PERF_ARCH(NEEDS_BRANCH_STACK,	0x40000) /* require branch stack setup */
-PERF_ARCH(BRANCH_COUNTERS,	0x80000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(PEBS_LDLAT,		0x0000001) /* ld+ldlat data address sampling */
+PERF_ARCH(PEBS_ST,		0x0000002) /* st data address sampling */
+PERF_ARCH(PEBS_ST_HSW,		0x0000004) /* haswell style datala, store */
+PERF_ARCH(PEBS_LD_HSW,		0x0000008) /* haswell style datala, load */
+PERF_ARCH(PEBS_NA_HSW,		0x0000010) /* haswell style datala, unknown */
+PERF_ARCH(EXCL,			0x0000020) /* HT exclusivity on counter */
+PERF_ARCH(DYNAMIC,		0x0000040) /* dynamic alloc'd constraint */
+PERF_ARCH(PEBS_CNTR,		0x0000080) /* PEBS counters snapshot */
+PERF_ARCH(EXCL_ACCT,		0x0000100) /* accounted EXCL event */
+PERF_ARCH(AUTO_RELOAD,		0x0000200) /* use PEBS auto-reload */
+PERF_ARCH(LARGE_PEBS,		0x0000400) /* use large PEBS */
+PERF_ARCH(PEBS_VIA_PT,		0x0000800) /* use PT buffer for PEBS */
+PERF_ARCH(PAIR,			0x0001000) /* Large Increment per Cycle */
+PERF_ARCH(LBR_SELECT,		0x0002000) /* Save/Restore MSR_LBR_SELECT */
+PERF_ARCH(TOPDOWN,		0x0004000) /* Count Topdown slots/metrics events */
+PERF_ARCH(PEBS_STLAT,		0x0008000) /* st+stlat data address sampling */
+PERF_ARCH(AMD_BRS,		0x0010000) /* AMD Branch Sampling */
+PERF_ARCH(PEBS_LAT_HYBRID,	0x0020000) /* ld and st lat for hybrid */
+PERF_ARCH(NEEDS_BRANCH_STACK,	0x0040000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS,	0x0080000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(ACR,			0x0100000) /* Auto counter reload */
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 2fd9b0cf9a5e..49a5944fac63 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -397,8 +397,7 @@ again:
 		if (!x86_perf_event_set_period(event))
 			continue;
 
-		if (perf_event_overflow(event, &data, regs))
-			x86_pmu_stop(event, 0);
+		perf_event_overflow(event, &data, regs);
 	}
 
 	/*
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e7d2f460fcc6..7c3f5ef1a169 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -602,7 +602,11 @@
 /* V6 PMON MSR range */
 #define MSR_IA32_PMC_V6_GP0_CTR		0x1900
 #define MSR_IA32_PMC_V6_GP0_CFG_A	0x1901
+#define MSR_IA32_PMC_V6_GP0_CFG_B	0x1902
+#define MSR_IA32_PMC_V6_GP0_CFG_C	0x1903
 #define MSR_IA32_PMC_V6_FX0_CTR		0x1980
+#define MSR_IA32_PMC_V6_FX0_CFG_B	0x1982
+#define MSR_IA32_PMC_V6_FX0_CFG_C	0x1983
 #define MSR_IA32_PMC_V6_STEP		4
 
 /* KeyID partitioning between MKTME and TDX */
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 812dac3f79f0..70d1d94aca7e 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -195,6 +195,7 @@ union cpuid10_edx {
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
+#define ARCH_PERFMON_ACR_LEAF			0x2
 
 union cpuid35_eax {
 	struct {
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 9194695662b2..6d383839e839 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -840,6 +840,11 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
 	insn_byte_t p;
 	int i;
 
+	/* x86_nops[insn->length]; same as jmp with .offs = 0 */
+	if (insn->length <= ASM_NOP_MAX &&
+	    !memcmp(insn->kaddr, x86_nops[insn->length], insn->length))
+		goto setup;
+
 	switch (opc1) {
 	case 0xeb:	/* jmp 8 */
 	case 0xe9:	/* jmp 32 */
diff --git a/arch/xtensa/kernel/perf_event.c b/arch/xtensa/kernel/perf_event.c
index 183618090d05..223f1d452310 100644
--- a/arch/xtensa/kernel/perf_event.c
+++ b/arch/xtensa/kernel/perf_event.c
@@ -388,8 +388,7 @@ irqreturn_t xtensa_pmu_irq_handler(int irq, void *dev_id)
 			struct pt_regs *regs = get_irq_regs();
 
 			perf_sample_data_init(&data, 0, last_period);
-			if (perf_event_overflow(event, &data, regs))
-				xtensa_pmu_stop(event, 0);
+			perf_event_overflow(event, &data, regs);
 		}
 
 		rc = IRQ_HANDLED;