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
  ...

44 files changed, 1996 insertions, 1210 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);
 }