Merge tag 'perf-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Core:
   - Move perf_event sysctls into kernel/events/ (Joel Granados)
   - Use POLLHUP for pinned events in error (Namhyung Kim)
   - Avoid the read if the count is already updated (Peter Zijlstra)
   - Allow the EPOLLRDNORM flag for poll (Tao Chen)
   - locking/percpu-rwsem: Add guard support [ NOTE: this got
     (mis-)merged into the perf tree due to related work ] (Peter
     Zijlstra)

  perf_pmu_unregister() related improvements: (Peter Zijlstra)
   - Simplify the perf_event_alloc() error path
   - Simplify the perf_pmu_register() error path
   - Simplify perf_pmu_register()
   - Simplify perf_init_event()
   - Simplify perf_event_alloc()
   - Merge struct pmu::pmu_disable_count into struct
     perf_cpu_pmu_context::pmu_disable_count
   - Add this_cpc() helper
   - Introduce perf_free_addr_filters()
   - Robustify perf_event_free_bpf_prog()
   - Simplify the perf_mmap() control flow
   - Further simplify perf_mmap()
   - Remove retry loop from perf_mmap()
   - Lift event->mmap_mutex in perf_mmap()
   - Detach 'struct perf_cpu_pmu_context' and 'struct pmu' lifetimes
   - Fix perf_mmap() failure path

  Uprobes:
   - Harden x86 uretprobe syscall trampoline check (Jiri Olsa)
   - Remove redundant spinlock in uprobe_deny_signal() (Liao Chang)
   - Remove the spinlock within handle_singlestep() (Liao Chang)

  x86 Intel PMU enhancements:
   - Support PEBS counters snapshotting (Kan Liang)
   - Fix intel_pmu_read_event() (Kan Liang)
   - Extend per event callchain limit to branch stack (Kan Liang)
   - Fix system-wide LBR profiling (Kan Liang)
   - Allocate bts_ctx only if necessary (Li RongQing)
   - Apply static call for drain_pebs (Peter Zijlstra)

  x86 AMD PMU enhancements: (Ravi Bangoria)
   - Remove pointless sample period check
   - Fix ->config to sample period calculation for OP PMU
   - Fix perf_ibs_op.cnt_mask for CurCnt
   - Don't allow freq mode event creation through ->config interface
   - Add PMU specific minimum period
   - Add ->check_period() callback
   - Ceil sample_period to min_period
   - Add support for OP Load Latency Filtering
   - Update DTLB/PageSize decode logic

  Hardware breakpoints:
   - Return EOPNOTSUPP for unsupported breakpoint type (Saket Kumar
     Bhaskar)

  Hardlockup detector improvements: (Li Huafei)
   - perf_event memory leak
   - Warn if watchdog_ev is leaked

  Fixes and cleanups:
   - Misc fixes and cleanups (Andy Shevchenko, Kan Liang, Peter
     Zijlstra, Ravi Bangoria, Thorsten Blum, XieLudan)"

* tag 'perf-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
  perf: Fix __percpu annotation
  perf: Clean up pmu specific data
  perf/x86: Remove swap_task_ctx()
  perf/x86/lbr: Fix shorter LBRs call stacks for the system-wide mode
  perf: Supply task information to sched_task()
  perf: attach/detach PMU specific data
  locking/percpu-rwsem: Add guard support
  perf: Save PMU specific data in task_struct
  perf: Extend per event callchain limit to branch stack
  perf/ring_buffer: Allow the EPOLLRDNORM flag for poll
  perf/core: Use POLLHUP for pinned events in error
  perf/core: Use sysfs_emit() instead of scnprintf()
  perf/core: Remove optional 'size' arguments from strscpy() calls
  perf/x86/intel/bts: Check if bts_ctx is allocated when calling BTS functions
  uprobes/x86: Harden uretprobe syscall trampoline check
  watchdog/hardlockup/perf: Warn if watchdog_ev is leaked
  watchdog/hardlockup/perf: Fix perf_event memory leak
  perf/x86: Annotate struct bts_buffer::buf with __counted_by()
  perf/core: Clean up perf_try_init_event()
  perf/core: Fix perf_mmap() failure path
  ...

34 files changed, 1416 insertions, 737 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 2b79171ee185..f4e03aaabb4c 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -132,7 +132,10 @@ static unsigned long ebb_switch_in(bool ebb, struct cpu_hw_events *cpuhw)
 
 static inline void power_pmu_bhrb_enable(struct perf_event *event) {}
 static inline void power_pmu_bhrb_disable(struct perf_event *event) {}
-static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) {}
+static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				 struct task_struct *task, bool sched_in)
+{
+}
 static inline void power_pmu_bhrb_read(struct perf_event *event, struct cpu_hw_events *cpuhw) {}
 static void pmao_restore_workaround(bool ebb) { }
 #endif /* CONFIG_PPC32 */
@@ -444,7 +447,8 @@ static void power_pmu_bhrb_disable(struct perf_event *event)
 /* Called from ctxsw to prevent one process's branch entries to
  * mingle with the other process's entries during context switch.
  */
-static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void power_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				 struct task_struct *task, bool sched_in)
 {
 	if (!ppmu->bhrb_nr)
 		return;
diff --git a/arch/s390/kernel/perf_pai_crypto.c b/arch/s390/kernel/perf_pai_crypto.c
index 10725f5a6f0f..63875270941b 100644
--- a/arch/s390/kernel/perf_pai_crypto.c
+++ b/arch/s390/kernel/perf_pai_crypto.c
@@ -518,7 +518,8 @@ static void paicrypt_have_samples(void)
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event CRYPTO_ALL is allowed.
  */
-static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paicrypt_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				struct task_struct *task, bool sched_in)
 {
 	/* We started with a clean page on event installation. So read out
 	 * results on schedule_out and if page was dirty, save old values.
diff --git a/arch/s390/kernel/perf_pai_ext.c b/arch/s390/kernel/perf_pai_ext.c
index a8f0bad99cf0..fd14d5ebccbc 100644
--- a/arch/s390/kernel/perf_pai_ext.c
+++ b/arch/s390/kernel/perf_pai_ext.c
@@ -542,7 +542,8 @@ static void paiext_have_samples(void)
 /* Called on schedule-in and schedule-out. No access to event structure,
  * but for sampling only event NNPA_ALL is allowed.
  */
-static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+static void paiext_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			      struct task_struct *task, bool sched_in)
 {
 	/* We started with a clean page on event installation. So read out
 	 * results on schedule_out and if page was dirty, save old values.
diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c
index 780acd3dff22..ec3427463382 100644
--- a/arch/x86/events/amd/brs.c
+++ b/arch/x86/events/amd/brs.c
@@ -381,7 +381,8 @@ static void amd_brs_poison_buffer(void)
  * On ctxswin, sched_in = true, called after the PMU has started
  * On ctxswout, sched_in = false, called before the PMU is stopped
  */
-void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+void amd_pmu_brs_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index e36c9c63c97c..66f981865091 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -28,9 +28,6 @@ static u32 ibs_caps;
 #include <asm/nmi.h>
 #include <asm/amd-ibs.h>
 
-#define IBS_FETCH_CONFIG_MASK	(IBS_FETCH_RAND_EN | IBS_FETCH_MAX_CNT)
-#define IBS_OP_CONFIG_MASK	IBS_OP_MAX_CNT
-
 /* attr.config2 */
 #define IBS_SW_FILTER_MASK	1
 
@@ -89,6 +86,7 @@ struct perf_ibs {
 	u64				cnt_mask;
 	u64				enable_mask;
 	u64				valid_mask;
+	u16				min_period;
 	u64				max_period;
 	unsigned long			offset_mask[1];
 	int				offset_max;
@@ -270,11 +268,19 @@ static int validate_group(struct perf_event *event)
 	return 0;
 }
 
+static bool perf_ibs_ldlat_event(struct perf_ibs *perf_ibs,
+				 struct perf_event *event)
+{
+	return perf_ibs == &perf_ibs_op &&
+	       (ibs_caps & IBS_CAPS_OPLDLAT) &&
+	       (event->attr.config1 & 0xFFF);
+}
+
 static int perf_ibs_init(struct perf_event *event)
 {
 	struct hw_perf_event *hwc = &event->hw;
 	struct perf_ibs *perf_ibs;
-	u64 max_cnt, config;
+	u64 config;
 	int ret;
 
 	perf_ibs = get_ibs_pmu(event->attr.type);
@@ -310,25 +316,47 @@ static int perf_ibs_init(struct perf_event *event)
 		if (config & perf_ibs->cnt_mask)
 			/* raw max_cnt may not be set */
 			return -EINVAL;
-		if (!event->attr.sample_freq && hwc->sample_period & 0x0f)
-			/*
-			 * lower 4 bits can not be set in ibs max cnt,
-			 * but allowing it in case we adjust the
-			 * sample period to set a frequency.
-			 */
-			return -EINVAL;
-		hwc->sample_period &= ~0x0FULL;
-		if (!hwc->sample_period)
-			hwc->sample_period = 0x10;
+
+		if (event->attr.freq) {
+			hwc->sample_period = perf_ibs->min_period;
+		} else {
+			/* Silently mask off lower nibble. IBS hw mandates it. */
+			hwc->sample_period &= ~0x0FULL;
+			if (hwc->sample_period < perf_ibs->min_period)
+				return -EINVAL;
+		}
 	} else {
-		max_cnt = config & perf_ibs->cnt_mask;
+		u64 period = 0;
+
+		if (event->attr.freq)
+			return -EINVAL;
+
+		if (perf_ibs == &perf_ibs_op) {
+			period = (config & IBS_OP_MAX_CNT) << 4;
+			if (ibs_caps & IBS_CAPS_OPCNTEXT)
+				period |= config & IBS_OP_MAX_CNT_EXT_MASK;
+		} else {
+			period = (config & IBS_FETCH_MAX_CNT) << 4;
+		}
+
 		config &= ~perf_ibs->cnt_mask;
-		event->attr.sample_period = max_cnt << 4;
-		hwc->sample_period = event->attr.sample_period;
+		event->attr.sample_period = period;
+		hwc->sample_period = period;
+
+		if (hwc->sample_period < perf_ibs->min_period)
+			return -EINVAL;
 	}
 
-	if (!hwc->sample_period)
-		return -EINVAL;
+	if (perf_ibs_ldlat_event(perf_ibs, event)) {
+		u64 ldlat = event->attr.config1 & 0xFFF;
+
+		if (ldlat < 128 || ldlat > 2048)
+			return -EINVAL;
+		ldlat >>= 7;
+
+		config |= (ldlat - 1) << 59;
+		config |= IBS_OP_L3MISSONLY | IBS_OP_LDLAT_EN;
+	}
 
 	/*
 	 * If we modify hwc->sample_period, we also need to update
@@ -349,7 +377,8 @@ static int perf_ibs_set_period(struct perf_ibs *perf_ibs,
 	int overflow;
 
 	/* ignore lower 4 bits in min count: */
-	overflow = perf_event_set_period(hwc, 1<<4, perf_ibs->max_period, period);
+	overflow = perf_event_set_period(hwc, perf_ibs->min_period,
+					 perf_ibs->max_period, period);
 	local64_set(&hwc->prev_count, 0);
 
 	return overflow;
@@ -447,6 +476,9 @@ static void perf_ibs_start(struct perf_event *event, int flags)
 	WARN_ON_ONCE(!(hwc->state & PERF_HES_UPTODATE));
 	hwc->state = 0;
 
+	if (event->attr.freq && hwc->sample_period < perf_ibs->min_period)
+		hwc->sample_period = perf_ibs->min_period;
+
 	perf_ibs_set_period(perf_ibs, hwc, &period);
 	if (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_OPCNTEXT)) {
 		config |= period & IBS_OP_MAX_CNT_EXT_MASK;
@@ -554,6 +586,28 @@ static void perf_ibs_del(struct perf_event *event, int flags)
 
 static void perf_ibs_read(struct perf_event *event) { }
 
+static int perf_ibs_check_period(struct perf_event *event, u64 value)
+{
+	struct perf_ibs *perf_ibs;
+	u64 low_nibble;
+
+	if (event->attr.freq)
+		return 0;
+
+	perf_ibs = container_of(event->pmu, struct perf_ibs, pmu);
+	low_nibble = value & 0xFULL;
+
+	/*
+	 * This contradicts with perf_ibs_init() which allows sample period
+	 * with lower nibble bits set but silently masks them off. Whereas
+	 * this returns error.
+	 */
+	if (low_nibble || value < perf_ibs->min_period)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * We need to initialize with empty group if all attributes in the
  * group are dynamic.
@@ -572,7 +626,10 @@ PMU_FORMAT_ATTR(cnt_ctl,	"config:19");
 PMU_FORMAT_ATTR(swfilt,		"config2:0");
 PMU_EVENT_ATTR_STRING(l3missonly, fetch_l3missonly, "config:59");
 PMU_EVENT_ATTR_STRING(l3missonly, op_l3missonly, "config:16");
+PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_format, "config1:0-11");
 PMU_EVENT_ATTR_STRING(zen4_ibs_extensions, zen4_ibs_extensions, "1");
+PMU_EVENT_ATTR_STRING(ldlat, ibs_op_ldlat_cap, "1");
+PMU_EVENT_ATTR_STRING(dtlb_pgsize, ibs_op_dtlb_pgsize_cap, "1");
 
 static umode_t
 zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int i)
@@ -580,6 +637,18 @@ zen4_ibs_extensions_is_visible(struct kobject *kobj, struct attribute *attr, int
 	return ibs_caps & IBS_CAPS_ZEN4 ? attr->mode : 0;
 }
 
+static umode_t
+ibs_op_ldlat_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPLDLAT ? attr->mode : 0;
+}
+
+static umode_t
+ibs_op_dtlb_pgsize_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return ibs_caps & IBS_CAPS_OPDTLBPGSIZE ? attr->mode : 0;
+}
+
 static struct attribute *fetch_attrs[] = {
 	&format_attr_rand_en.attr,
 	&format_attr_swfilt.attr,
@@ -596,6 +665,16 @@ static struct attribute *zen4_ibs_extensions_attrs[] = {
 	NULL,
 };
 
+static struct attribute *ibs_op_ldlat_cap_attrs[] = {
+	&ibs_op_ldlat_cap.attr.attr,
+	NULL,
+};
+
+static struct attribute *ibs_op_dtlb_pgsize_cap_attrs[] = {
+	&ibs_op_dtlb_pgsize_cap.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_fetch_formats = {
 	.name = "format",
 	.attrs = fetch_attrs,
@@ -613,6 +692,18 @@ static struct attribute_group group_zen4_ibs_extensions = {
 	.is_visible = zen4_ibs_extensions_is_visible,
 };
 
+static struct attribute_group group_ibs_op_ldlat_cap = {
+	.name = "caps",
+	.attrs = ibs_op_ldlat_cap_attrs,
+	.is_visible = ibs_op_ldlat_is_visible,
+};
+
+static struct attribute_group group_ibs_op_dtlb_pgsize_cap = {
+	.name = "caps",
+	.attrs = ibs_op_dtlb_pgsize_cap_attrs,
+	.is_visible = ibs_op_dtlb_pgsize_is_visible,
+};
+
 static const struct attribute_group *fetch_attr_groups[] = {
 	&group_fetch_formats,
 	&empty_caps_group,
@@ -651,6 +742,11 @@ static struct attribute_group group_op_formats = {
 	.attrs = op_attrs,
 };
 
+static struct attribute *ibs_op_ldlat_format_attrs[] = {
+	&ibs_op_ldlat_format.attr.attr,
+	NULL,
+};
+
 static struct attribute_group group_cnt_ctl = {
 	.name = "format",
 	.attrs = cnt_ctl_attrs,
@@ -669,10 +765,19 @@ static const struct attribute_group *op_attr_groups[] = {
 	NULL,
 };
 
+static struct attribute_group group_ibs_op_ldlat_format = {
+	.name = "format",
+	.attrs = ibs_op_ldlat_format_attrs,
+	.is_visible = ibs_op_ldlat_is_visible,
+};
+
 static const struct attribute_group *op_attr_update[] = {
 	&group_cnt_ctl,
 	&group_op_l3missonly,
 	&group_zen4_ibs_extensions,
+	&group_ibs_op_ldlat_cap,
+	&group_ibs_op_ldlat_format,
+	&group_ibs_op_dtlb_pgsize_cap,
 	NULL,
 };
 
@@ -686,12 +791,14 @@ static struct perf_ibs perf_ibs_fetch = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.check_period	= perf_ibs_check_period,
 	},
 	.msr			= MSR_AMD64_IBSFETCHCTL,
-	.config_mask		= IBS_FETCH_CONFIG_MASK,
+	.config_mask		= IBS_FETCH_MAX_CNT | IBS_FETCH_RAND_EN,
 	.cnt_mask		= IBS_FETCH_MAX_CNT,
 	.enable_mask		= IBS_FETCH_ENABLE,
 	.valid_mask		= IBS_FETCH_VAL,
+	.min_period		= 0x10,
 	.max_period		= IBS_FETCH_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSFETCH_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSFETCH_REG_COUNT,
@@ -709,13 +816,15 @@ static struct perf_ibs perf_ibs_op = {
 		.start		= perf_ibs_start,
 		.stop		= perf_ibs_stop,
 		.read		= perf_ibs_read,
+		.check_period	= perf_ibs_check_period,
 	},
 	.msr			= MSR_AMD64_IBSOPCTL,
-	.config_mask		= IBS_OP_CONFIG_MASK,
+	.config_mask		= IBS_OP_MAX_CNT,
 	.cnt_mask		= IBS_OP_MAX_CNT | IBS_OP_CUR_CNT |
 				  IBS_OP_CUR_CNT_RAND,
 	.enable_mask		= IBS_OP_ENABLE,
 	.valid_mask		= IBS_OP_VAL,
+	.min_period		= 0x90,
 	.max_period		= IBS_OP_MAX_CNT << 4,
 	.offset_mask		= { MSR_AMD64_IBSOP_REG_MASK },
 	.offset_max		= MSR_AMD64_IBSOP_REG_COUNT,
@@ -917,6 +1026,10 @@ static void perf_ibs_get_tlb_lvl(union ibs_op_data3 *op_data3,
 	if (!op_data3->dc_lin_addr_valid)
 		return;
 
+	if ((ibs_caps & IBS_CAPS_OPDTLBPGSIZE) &&
+	    !op_data3->dc_phy_addr_valid)
+		return;
+
 	if (!op_data3->dc_l1tlb_miss) {
 		data_src->mem_dtlb = PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT;
 		return;
@@ -1023,15 +1136,25 @@ static void perf_ibs_parse_ld_st_data(__u64 sample_type,
 	}
 }
 
-static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs, u64 sample_type,
+static bool perf_ibs_is_mem_sample_type(struct perf_ibs *perf_ibs,
+					struct perf_event *event)
+{
+	u64 sample_type = event->attr.sample_type;
+
+	return perf_ibs == &perf_ibs_op &&
+	       sample_type & (PERF_SAMPLE_DATA_SRC |
+			      PERF_SAMPLE_WEIGHT_TYPE |
+			      PERF_SAMPLE_ADDR |
+			      PERF_SAMPLE_PHYS_ADDR);
+}
+
+static int perf_ibs_get_offset_max(struct perf_ibs *perf_ibs,
+				   struct perf_event *event,
 				   int check_rip)
 {
-	if (sample_type & PERF_SAMPLE_RAW ||
-	    (perf_ibs == &perf_ibs_op &&
-	     (sample_type & PERF_SAMPLE_DATA_SRC ||
-	      sample_type & PERF_SAMPLE_WEIGHT_TYPE ||
-	      sample_type & PERF_SAMPLE_ADDR ||
-	      sample_type & PERF_SAMPLE_PHYS_ADDR)))
+	if (event->attr.sample_type & PERF_SAMPLE_RAW ||
+	    perf_ibs_is_mem_sample_type(perf_ibs, event) ||
+	    perf_ibs_ldlat_event(perf_ibs, event))
 		return perf_ibs->offset_max;
 	else if (check_rip)
 		return 3;
@@ -1148,7 +1271,7 @@ fail:
 	offset = 1;
 	check_rip = (perf_ibs == &perf_ibs_op && (ibs_caps & IBS_CAPS_RIPINVALIDCHK));
 
-	offset_max = perf_ibs_get_offset_max(perf_ibs, event->attr.sample_type, check_rip);
+	offset_max = perf_ibs_get_offset_max(perf_ibs, event, check_rip);
 
 	do {
 		rdmsrl(msr + offset, *buf++);
@@ -1157,6 +1280,22 @@ fail:
 				       perf_ibs->offset_max,
 				       offset + 1);
 	} while (offset < offset_max);
+
+	if (perf_ibs_ldlat_event(perf_ibs, event)) {
+		union ibs_op_data3 op_data3;
+
+		op_data3.val = ibs_data.regs[ibs_op_msr_idx(MSR_AMD64_IBSOPDATA3)];
+		/*
+		 * Opening event is errored out if load latency threshold is
+		 * outside of [128, 2048] range. Since the event has reached
+		 * interrupt handler, we can safely assume the threshold is
+		 * within [128, 2048] range.
+		 */
+		if (!op_data3.ld_op || !op_data3.dc_miss ||
+		    op_data3.dc_miss_lat <= (event->attr.config1 & 0xFFF))
+			goto out;
+	}
+
 	/*
 	 * Read IbsBrTarget, IbsOpData4, and IbsExtdCtl separately
 	 * depending on their availability.
@@ -1229,6 +1368,10 @@ fail:
 	perf_sample_save_callchain(&data, event, iregs);
 
 	throttle = perf_event_overflow(event, &data, &regs);
+
+	if (event->attr.freq && hwc->sample_period < perf_ibs->min_period)
+		hwc->sample_period = perf_ibs->min_period;
+
 out:
 	if (throttle) {
 		perf_ibs_stop(event, 0);
@@ -1318,7 +1461,8 @@ static __init int perf_ibs_op_init(void)
 	if (ibs_caps & IBS_CAPS_OPCNTEXT) {
 		perf_ibs_op.max_period  |= IBS_OP_MAX_CNT_EXT_MASK;
 		perf_ibs_op.config_mask	|= IBS_OP_MAX_CNT_EXT_MASK;
-		perf_ibs_op.cnt_mask    |= IBS_OP_MAX_CNT_EXT_MASK;
+		perf_ibs_op.cnt_mask    |= (IBS_OP_MAX_CNT_EXT_MASK |
+					    IBS_OP_CUR_CNT_EXT_MASK);
 	}
 
 	if (ibs_caps & IBS_CAPS_ZEN4)
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index b15f7b950d2e..f8228d8243f7 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -30,7 +30,7 @@
 #define GET_DOMID_MASK(x)  (((x)->conf1 >> 16) & 0xFFFFULL)
 #define GET_PASID_MASK(x)  (((x)->conf1 >> 32) & 0xFFFFFULL)
 
-#define IOMMU_NAME_SIZE 16
+#define IOMMU_NAME_SIZE 24
 
 struct perf_amd_iommu {
 	struct list_head list;
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index 19c7b76e21bc..c06ccca96851 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -371,7 +371,8 @@ void amd_pmu_lbr_del(struct perf_event *event)
 	perf_sched_cb_dec(event->pmu);
 }
 
-void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
+void amd_pmu_lbr_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			    struct task_struct *task, bool sched_in)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2092d615333d..833478ffbbf5 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -87,13 +87,14 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_commit_scheduling, *x86_pmu.commit_scheduling);
 DEFINE_STATIC_CALL_NULL(x86_pmu_stop_scheduling,   *x86_pmu.stop_scheduling);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_sched_task,    *x86_pmu.sched_task);
-DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs,   *x86_pmu.drain_pebs);
 DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
 DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup);
+
 /*
  * 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.
@@ -1298,6 +1299,15 @@ static void x86_pmu_enable(struct pmu *pmu)
 
 	if (cpuc->n_added) {
 		int n_running = cpuc->n_events - cpuc->n_added;
+
+		/*
+		 * The late setup (after counters are scheduled)
+		 * is required for some cases, e.g., PEBS counters
+		 * snapshotting. Because an accurate counter index
+		 * is needed.
+		 */
+		static_call_cond(x86_pmu_late_setup)();
+
 		/*
 		 * apply assignment obtained either from
 		 * hw_perf_group_sched_in() or x86_pmu_enable()
@@ -2028,13 +2038,14 @@ static void x86_pmu_static_call_update(void)
 	static_call_update(x86_pmu_stop_scheduling, x86_pmu.stop_scheduling);
 
 	static_call_update(x86_pmu_sched_task, x86_pmu.sched_task);
-	static_call_update(x86_pmu_swap_task_ctx, x86_pmu.swap_task_ctx);
 
 	static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs);
 	static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases);
 
 	static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs);
 	static_call_update(x86_pmu_filter, x86_pmu.filter);
+
+	static_call_update(x86_pmu_late_setup, x86_pmu.late_setup);
 }
 
 static void _x86_pmu_read(struct perf_event *event)
@@ -2625,15 +2636,10 @@ static const struct attribute_group *x86_pmu_attr_groups[] = {
 	NULL,
 };
 
-static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in)
-{
-	static_call_cond(x86_pmu_sched_task)(pmu_ctx, sched_in);
-}
-
-static void x86_pmu_swap_task_ctx(struct perf_event_pmu_context *prev_epc,
-				  struct perf_event_pmu_context *next_epc)
+static void x86_pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+			       struct task_struct *task, bool sched_in)
 {
-	static_call_cond(x86_pmu_swap_task_ctx)(prev_epc, next_epc);
+	static_call_cond(x86_pmu_sched_task)(pmu_ctx, task, sched_in);
 }
 
 void perf_check_microcode(void)
@@ -2700,7 +2706,6 @@ static struct pmu pmu = {
 
 	.event_idx		= x86_pmu_event_idx,
 	.sched_task		= x86_pmu_sched_task,
-	.swap_task_ctx		= x86_pmu_swap_task_ctx,
 	.check_period		= x86_pmu_check_period,
 
 	.aux_output_match	= x86_pmu_aux_output_match,
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 8f78b0c900ef..39a987d5eb6e 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -36,7 +36,7 @@ enum {
 	BTS_STATE_ACTIVE,
 };
 
-static DEFINE_PER_CPU(struct bts_ctx, bts_ctx);
+static struct bts_ctx __percpu *bts_ctx;
 
 #define BTS_RECORD_SIZE		24
 #define BTS_SAFETY_MARGIN	4080
@@ -58,7 +58,7 @@ struct bts_buffer {
 	local_t		head;
 	unsigned long	end;
 	void		**data_pages;
-	struct bts_phys	buf[];
+	struct bts_phys	buf[] __counted_by(nr_bufs);
 };
 
 static struct pmu bts_pmu;
@@ -231,7 +231,7 @@ 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_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct bts_buffer *buf = perf_get_aux(&bts->handle);
 	u64 config = 0;
 
@@ -260,7 +260,7 @@ static void __bts_event_start(struct perf_event *event)
 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_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct bts_buffer *buf;
 
 	buf = perf_aux_output_begin(&bts->handle, event);
@@ -290,7 +290,7 @@ fail_stop:
 
 static void __bts_event_stop(struct perf_event *event, int state)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 
 	/* ACTIVE -> INACTIVE(PMI)/STOPPED(->stop()) */
 	WRITE_ONCE(bts->state, state);
@@ -305,7 +305,7 @@ static void __bts_event_stop(struct perf_event *event, int state)
 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_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct bts_buffer *buf = NULL;
 	int state = READ_ONCE(bts->state);
 
@@ -338,9 +338,14 @@ static void bts_event_stop(struct perf_event *event, int flags)
 
 void intel_bts_enable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	int state = READ_ONCE(bts->state);
+	struct bts_ctx *bts;
+	int state;
+
+	if (!bts_ctx)
+		return;
 
+	bts = this_cpu_ptr(bts_ctx);
+	state = READ_ONCE(bts->state);
 	/*
 	 * Here we transition from INACTIVE to ACTIVE;
 	 * if we instead are STOPPED from the interrupt handler,
@@ -358,7 +363,12 @@ void intel_bts_enable_local(void)
 
 void intel_bts_disable_local(void)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts;
+
+	if (!bts_ctx)
+		return;
+
+	bts = this_cpu_ptr(bts_ctx);
 
 	/*
 	 * Here we transition from ACTIVE to INACTIVE;
@@ -450,12 +460,17 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
 int intel_bts_interrupt(void)
 {
 	struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
-	struct perf_event *event = bts->handle.event;
+	struct bts_ctx *bts;
+	struct perf_event *event;
 	struct bts_buffer *buf;
 	s64 old_head;
 	int err = -ENOSPC, handled = 0;
 
+	if (!bts_ctx)
+		return 0;
+
+	bts = this_cpu_ptr(bts_ctx);
+	event = bts->handle.event;
 	/*
 	 * The only surefire way of knowing if this NMI is ours is by checking
 	 * the write ptr against the PMI threshold.
@@ -518,7 +533,7 @@ static void bts_event_del(struct perf_event *event, int mode)
 
 static int bts_event_add(struct perf_event *event, int mode)
 {
-	struct bts_ctx *bts = this_cpu_ptr(&bts_ctx);
+	struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	struct hw_perf_event *hwc = &event->hw;
 
@@ -605,6 +620,10 @@ static __init int bts_init(void)
 		return -ENODEV;
 	}
 
+	bts_ctx = alloc_percpu(struct bts_ctx);
+	if (!bts_ctx)
+		return -ENOMEM;
+
 	bts_pmu.capabilities	= PERF_PMU_CAP_AUX_NO_SG | PERF_PMU_CAP_ITRACE |
 				  PERF_PMU_CAP_EXCLUSIVE;
 	bts_pmu.task_ctx_nr	= perf_sw_context;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index cdb19e3ba3aa..dc38dec244c1 100644
--- a/