Merge tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Uprobes:
    - Add BPF session support (Jiri Olsa)
    - Switch to RCU Tasks Trace flavor for better performance (Andrii
      Nakryiko)
    - Massively increase uretprobe SMP scalability by SRCU-protecting
      the uretprobe lifetime (Andrii Nakryiko)
    - Kill xol_area->slot_count (Oleg Nesterov)

  Core facilities:
    - Implement targeted high-frequency profiling by adding the ability
      for an event to "pause" or "resume" AUX area tracing (Adrian
      Hunter)

  VM profiling/sampling:
    - Correct perf sampling with guest VMs (Colton Lewis)

  New hardware support:
    - x86/intel: Add PMU support for Intel ArrowLake-H CPUs (Dapeng Mi)

  Misc fixes and enhancements:
    - x86/intel/pt: Fix buffer full but size is 0 case (Adrian Hunter)
    - x86/amd: Warn only on new bits set (Breno Leitao)
    - x86/amd/uncore: Avoid a false positive warning about snprintf
      truncation in amd_uncore_umc_ctx_init (Jean Delvare)
    - uprobes: Re-order struct uprobe_task to save some space
      (Christophe JAILLET)
    - x86/rapl: Move the pmu allocation out of CPU hotplug (Kan Liang)
    - x86/rapl: Clean up cpumask and hotplug (Kan Liang)
    - uprobes: Deuglify xol_get_insn_slot/xol_free_insn_slot paths (Oleg
      Nesterov)"

* tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  perf/core: Correct perf sampling with guest VMs
  perf/x86: Refactor misc flag assignments
  perf/powerpc: Use perf_arch_instruction_pointer()
  perf/core: Hoist perf_instruction_pointer() and perf_misc_flags()
  perf/arm: Drop unused functions
  uprobes: Re-order struct uprobe_task to save some space
  perf/x86/amd/uncore: Avoid a false positive warning about snprintf truncation in amd_uncore_umc_ctx_init
  perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
  perf/x86/intel/pt: Add support for pause / resume
  perf/core: Add aux_pause, aux_resume, aux_start_paused
  perf/x86/intel/pt: Fix buffer full but size is 0 case
  uprobes: SRCU-protect uretprobe lifetime (with timeout)
  uprobes: allow put_uprobe() from non-sleepable softirq context
  perf/x86/rapl: Clean up cpumask and hotplug
  perf/x86/rapl: Move the pmu allocation out of CPU hotplug
  uprobe: Add support for session consumer
  uprobe: Add data pointer to consumer handlers
  perf/x86/amd: Warn only on new bits set
  uprobes: fold xol_take_insn_slot() into xol_get_insn_slot()
  uprobes: kill xol_area->slot_count
  ...

12 files changed, 370 insertions, 154 deletions

diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 920e3a640cad..b4a1a2576510 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -943,11 +943,12 @@ static int amd_pmu_v2_snapshot_branch_stack(struct perf_branch_entry *entries, u
 static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+	static atomic64_t status_warned = ATOMIC64_INIT(0);
+	u64 reserved, status, mask, new_bits, prev_bits;
 	struct perf_sample_data data;
 	struct hw_perf_event *hwc;
 	struct perf_event *event;
 	int handled = 0, idx;
-	u64 reserved, status, mask;
 	bool pmu_enabled;
 
 	/*
@@ -1012,7 +1013,12 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	 * the corresponding PMCs are expected to be inactive according to the
 	 * active_mask
 	 */
-	WARN_ON(status > 0);
+	if (status > 0) {
+		prev_bits = atomic64_fetch_or(status, &status_warned);
+		// A new bit was set for the very first time.
+		new_bits = status & ~prev_bits;
+		WARN(new_bits, "New overflows for inactive PMCs: %llx\n", new_bits);
+	}
 
 	/* Clear overflow and freeze bits */
 	amd_pmu_ack_global_status(~status);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 0bfde2ea5cb8..49c26ce2b115 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -916,7 +916,8 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	u8 group_num_pmcs[UNCORE_GROUP_MAX] = { 0 };
 	union amd_uncore_info info;
 	struct amd_uncore_pmu *pmu;
-	int index = 0, gid, i;
+	int gid, i;
+	u16 index = 0;
 
 	if (pmu_version < 2)
 		return 0;
@@ -948,7 +949,7 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	for_each_set_bit(gid, gmask, UNCORE_GROUP_MAX) {
 		for (i = 0; i < group_num_pmus[gid]; i++) {
 			pmu = &uncore->pmus[index];
-			snprintf(pmu->name, sizeof(pmu->name), "amd_umc_%d", index);
+			snprintf(pmu->name, sizeof(pmu->name), "amd_umc_%hu", index);
 			pmu->num_counters = group_num_pmcs[gid] / group_num_pmus[gid];
 			pmu->msr_base = MSR_F19H_UMC_PERF_CTL + i * pmu->num_counters * 2;
 			pmu->rdpmc_base = -1;
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 65ab6460aed4..c75c482d4c52 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -3003,35 +3003,57 @@ static unsigned long code_segment_base(struct pt_regs *regs)
 	return 0;
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
-	if (perf_guest_state())
-		return perf_guest_get_ip();
-
 	return regs->ip + code_segment_base(regs);
 }
 
-unsigned long perf_misc_flags(struct pt_regs *regs)
+static unsigned long common_misc_flags(struct pt_regs *regs)
 {
-	unsigned int guest_state = perf_guest_state();
-	int misc = 0;
+	if (regs->flags & PERF_EFLAGS_EXACT)
+		return PERF_RECORD_MISC_EXACT_IP;
 
-	if (guest_state) {
-		if (guest_state & PERF_GUEST_USER)
-			misc |= PERF_RECORD_MISC_GUEST_USER;
-		else
-			misc |= PERF_RECORD_MISC_GUEST_KERNEL;
-	} else {
-		if (user_mode(regs))
-			misc |= PERF_RECORD_MISC_USER;
-		else
-			misc |= PERF_RECORD_MISC_KERNEL;
-	}
+	return 0;
+}
 
-	if (regs->flags & PERF_EFLAGS_EXACT)
-		misc |= PERF_RECORD_MISC_EXACT_IP;
+static unsigned long guest_misc_flags(struct pt_regs *regs)
+{
+	unsigned long guest_state = perf_guest_state();
+
+	if (!(guest_state & PERF_GUEST_ACTIVE))
+		return 0;
+
+	if (guest_state & PERF_GUEST_USER)
+		return PERF_RECORD_MISC_GUEST_USER;
+	else
+		return PERF_RECORD_MISC_GUEST_KERNEL;
+
+}
+
+static unsigned long host_misc_flags(struct pt_regs *regs)
+{
+	if (user_mode(regs))
+		return PERF_RECORD_MISC_USER;
+	else
+		return PERF_RECORD_MISC_KERNEL;
+}
+
+unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
+{
+	unsigned long flags = common_misc_flags(regs);
+
+	flags |= guest_misc_flags(regs);
+
+	return flags;
+}
+
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
+{
+	unsigned long flags = common_misc_flags(regs);
+
+	flags |= host_misc_flags(regs);
 
-	return misc;
+	return flags;
 }
 
 void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index d879478db3f5..bb284aff7bfd 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3962,8 +3962,8 @@ static int intel_pmu_hw_config(struct perf_event *event)
 
 		if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) {
 			event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD;
-			if (!(event->attr.sample_type &
-			      ~intel_pmu_large_pebs_flags(event))) {
+			if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event)) &&
+			    !has_aux_action(event)) {
 				event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS;
 				event->attach_state |= PERF_ATTACH_SCHED_CB;
 			}
@@ -4599,6 +4599,28 @@ static inline bool erratum_hsw11(struct perf_event *event)
 		X86_CONFIG(.event=0xc0, .umask=0x01);
 }
 
+static struct event_constraint *
+arl_h_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			  struct perf_event *event)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_tiny)
+		return cmt_get_event_constraints(cpuc, idx, event);
+
+	return mtl_get_event_constraints(cpuc, idx, event);
+}
+
+static int arl_h_hw_config(struct perf_event *event)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_tiny)
+		return intel_pmu_hw_config(event);
+
+	return adl_hw_config(event);
+}
+
 /*
  * The HSW11 requires a period larger than 100 which is the same as the BDM11.
  * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL.
@@ -4924,17 +4946,26 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 
 	/*
 	 * This essentially just maps between the 'hybrid_cpu_type'
-	 * and 'hybrid_pmu_type' enums:
+	 * and 'hybrid_pmu_type' enums except for ARL-H processor
+	 * which needs to compare atom uarch native id since ARL-H
+	 * contains two different atom uarchs.
 	 */
 	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
 		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
+		u32 native_id;
 
-		if (cpu_type == HYBRID_INTEL_CORE &&
-		    pmu_type == hybrid_big)
-			return &x86_pmu.hybrid_pmu[i];
-		if (cpu_type == HYBRID_INTEL_ATOM &&
-		    pmu_type == hybrid_small)
+		if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big)
 			return &x86_pmu.hybrid_pmu[i];
+		if (cpu_type == HYBRID_INTEL_ATOM) {
+			if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small)
+				return &x86_pmu.hybrid_pmu[i];
+
+			native_id = get_this_hybrid_cpu_native_id();
+			if (native_id == skt_native_id && pmu_type == hybrid_small)
+				return &x86_pmu.hybrid_pmu[i];
+			if (native_id == cmt_native_id && pmu_type == hybrid_tiny)
+				return &x86_pmu.hybrid_pmu[i];
+		}
 	}
 
 	return NULL;
@@ -5965,6 +5996,37 @@ static struct attribute *lnl_hybrid_events_attrs[] = {
 	NULL
 };
 
+/* The event string must be in PMU IDX order. */
+EVENT_ATTR_STR_HYBRID(topdown-retiring,
+		      td_retiring_arl_h,
+		      "event=0xc2,umask=0x02;event=0x00,umask=0x80;event=0xc2,umask=0x0",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(topdown-bad-spec,
+		      td_bad_spec_arl_h,
+		      "event=0x73,umask=0x0;event=0x00,umask=0x81;event=0x73,umask=0x0",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(topdown-fe-bound,
+		      td_fe_bound_arl_h,
+		      "event=0x9c,umask=0x01;event=0x00,umask=0x82;event=0x71,umask=0x0",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(topdown-be-bound,
+		      td_be_bound_arl_h,
+		      "event=0xa4,umask=0x02;event=0x00,umask=0x83;event=0x74,umask=0x0",
+		      hybrid_big_small_tiny);
+
+static struct attribute *arl_h_hybrid_events_attrs[] = {
+	EVENT_PTR(slots_adl),
+	EVENT_PTR(td_retiring_arl_h),
+	EVENT_PTR(td_bad_spec_arl_h),
+	EVENT_PTR(td_fe_bound_arl_h),
+	EVENT_PTR(td_be_bound_arl_h),
+	EVENT_PTR(td_heavy_ops_adl),
+	EVENT_PTR(td_br_mis_adl),
+	EVENT_PTR(td_fetch_lat_adl),
+	EVENT_PTR(td_mem_bound_adl),
+	NULL,
+};
+
 /* Must be in IDX order */
 EVENT_ATTR_STR_HYBRID(mem-loads,     mem_ld_adl,     "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3", hybrid_big_small);
 EVENT_ATTR_STR_HYBRID(mem-stores,    mem_st_adl,     "event=0xd0,umask=0x6;event=0xcd,umask=0x2",                 hybrid_big_small);
@@ -5983,6 +6045,21 @@ static struct attribute *mtl_hybrid_mem_attrs[] = {
 	NULL
 };
 
+EVENT_ATTR_STR_HYBRID(mem-loads,
+		      mem_ld_arl_h,
+		      "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3;event=0xd0,umask=0x5,ldlat=3",
+		      hybrid_big_small_tiny);
+EVENT_ATTR_STR_HYBRID(mem-stores,
+		      mem_st_arl_h,
+		      "event=0xd0,umask=0x6;event=0xcd,umask=0x2;event=0xd0,umask=0x6",
+		      hybrid_big_small_tiny);
+
+static struct attribute *arl_h_hybrid_mem_attrs[] = {
+	EVENT_PTR(mem_ld_arl_h),
+	EVENT_PTR(mem_st_arl_h),
+	NULL,
+};
+
 EVENT_ATTR_STR_HYBRID(tx-start,          tx_start_adl,          "event=0xc9,umask=0x1",          hybrid_big);
 EVENT_ATTR_STR_HYBRID(tx-commit,         tx_commit_adl,         "event=0xc9,umask=0x2",          hybrid_big);
 EVENT_ATTR_STR_HYBRID(tx-abort,          tx_abort_adl,          "event=0xc9,umask=0x4",          hybrid_big);
@@ -6006,8 +6083,8 @@ static struct attribute *adl_hybrid_tsx_attrs[] = {
 
 FORMAT_ATTR_HYBRID(in_tx,       hybrid_big);
 FORMAT_ATTR_HYBRID(in_tx_cp,    hybrid_big);
-FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small);
-FORMAT_ATTR_HYBRID(ldlat,       hybrid_big_small);
+FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small_tiny);
+FORMAT_ATTR_HYBRID(ldlat,       hybrid_big_small_tiny);
 FORMAT_ATTR_HYBRID(frontend,    hybrid_big);
 
 #define ADL_HYBRID_RTM_FORMAT_ATTR	\
@@ -6030,7 +6107,7 @@ static struct attribute *adl_hybrid_extra_attr[] = {
 	NULL
 };
 
-FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small);
+FORMAT_ATTR_HYBRID(snoop_rsp,	hybrid_small_tiny);
 
 static struct attribute *mtl_hybrid_extra_attr_rtm[] = {
 	ADL_HYBRID_RTM_FORMAT_ATTR,
@@ -6238,8 +6315,9 @@ static inline int intel_pmu_v6_addr_offset(int index, bool eventsel)
 }
 
 static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
-	{ hybrid_small, "cpu_atom" },
-	{ hybrid_big, "cpu_core" },
+	{ hybrid_small,	"cpu_atom" },
+	{ hybrid_big,	"cpu_core" },
+	{ hybrid_tiny,	"cpu_lowpower" },
 };
 
 static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
@@ -6272,7 +6350,7 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
 							0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
 
 		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
-		if (pmu->pmu_type & hybrid_small) {
+		if (pmu->pmu_type & hybrid_small_tiny) {
 			pmu->intel_cap.perf_metrics = 0;
 			pmu->intel_cap.pebs_output_pt_available = 1;
 			pmu->mid_ack = true;
@@ -7111,6 +7189,37 @@ __init int intel_pmu_init(void)
 		name = "lunarlake_hybrid";
 		break;
 
+	case INTEL_ARROWLAKE_H:
+		intel_pmu_init_hybrid(hybrid_big_small_tiny);
+
+		x86_pmu.pebs_latency_data = arl_h_latency_data;
+		x86_pmu.get_event_constraints = arl_h_get_event_constraints;
+		x86_pmu.hw_config = arl_h_hw_config;
+
+		td_attr = arl_h_hybrid_events_attrs;
+		mem_attr = arl_h_hybrid_mem_attrs;
+		tsx_attr = adl_hybrid_tsx_attrs;
+		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+			mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
+
+		/* Initialize big core specific PerfMon capabilities. */
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+		intel_pmu_init_lnc(&pmu->pmu);
+
+		/* Initialize Atom core specific PerfMon capabilities. */
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+		intel_pmu_init_skt(&pmu->pmu);
+
+		/* Initialize Lower Power Atom specific PerfMon capabilities. */
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_TINY_IDX];
+		intel_pmu_init_grt(&pmu->pmu);
+		pmu->extra_regs = intel_cmt_extra_regs;
+
+		intel_pmu_pebs_data_source_arl_h();
+		pr_cont("ArrowLake-H Hybrid events, ");
+		name = "arrowlake_h_hybrid";
+		break;
+
 	default:
 		switch (x86_pmu.version) {
 		case 1:
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index fa5ea65de0d0..8afc4ad3cd16 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -177,6 +177,17 @@ void __init intel_pmu_pebs_data_source_mtl(void)
 	__intel_pmu_pebs_data_source_cmt(data_source);
 }
 
+void __init intel_pmu_pebs_data_source_arl_h(void)
+{
+	u64 *data_source;
+
+	intel_pmu_pebs_data_source_lnl();
+
+	data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_TINY_IDX].pebs_data_source;
+	memcpy(data_source, pebs_data_source, sizeof(pebs_data_source));
+	__intel_pmu_pebs_data_source_cmt(data_source);
+}
+
 void __init intel_pmu_pebs_data_source_cmt(void)
 {
 	__intel_pmu_pebs_data_source_cmt(pebs_data_source);
@@ -388,6 +399,16 @@ u64 lnl_latency_data(struct perf_event *event, u64 status)
 	return lnc_latency_data(event, status);
 }
 
+u64 arl_h_latency_data(struct perf_event *event, u64 status)
+{
+	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
+
+	if (pmu->pmu_type == hybrid_tiny)
+		return cmt_latency_data(event, status);
+
+	return lnl_latency_data(event, status);
+}
+
 static u64 load_latency_data(struct perf_event *event, u64 status)
 {
 	union intel_x86_pebs_dse dse;
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fd4670a6694e..4b0373bc8ab4 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -418,6 +418,9 @@ static void pt_config_start(struct perf_event *event)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	u64 ctl = event->hw.aux_config;
 
+	if (READ_ONCE(event->hw.aux_paused))
+		return;
+
 	ctl |= RTIT_CTL_TRACEEN;
 	if (READ_ONCE(pt->vmx_on))
 		perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
@@ -534,7 +537,24 @@ static void pt_config(struct perf_event *event)
 	reg |= (event->attr.config & PT_CONFIG_MASK);
 
 	event->hw.aux_config = reg;
+
+	/*
+	 * Allow resume before starting so as not to overwrite a value set by a
+	 * PMI.
+	 */
+	barrier();
+	WRITE_ONCE(pt->resume_allowed, 1);
+	/* Configuration is complete, it is now OK to handle an NMI */
+	barrier();
+	WRITE_ONCE(pt->handle_nmi, 1);
+	barrier();
 	pt_config_start(event);
+	barrier();
+	/*
+	 * Allow pause after starting so its pt_config_stop() doesn't race with
+	 * pt_config_start().
+	 */
+	WRITE_ONCE(pt->pause_allowed, 1);
 }
 
 static void pt_config_stop(struct perf_event *event)
@@ -828,11 +848,13 @@ static void pt_buffer_advance(struct pt_buffer *buf)
 	buf->cur_idx++;
 
 	if (buf->cur_idx == buf->cur->last) {
-		if (buf->cur == buf->last)
+		if (buf->cur == buf->last) {
 			buf->cur = buf->first;
-		else
+			buf->wrapped = true;
+		} else {
 			buf->cur = list_entry(buf->cur->list.next, struct topa,
 					      list);
+		}
 		buf->cur_idx = 0;
 	}
 }
@@ -846,8 +868,11 @@ static void pt_buffer_advance(struct pt_buffer *buf)
 static void pt_update_head(struct pt *pt)
 {
 	struct pt_buffer *buf = perf_get_aux(&pt->handle);
+	bool wrapped = buf->wrapped;
 	u64 topa_idx, base, old;
 
+	buf->wrapped = false;
+
 	if (buf->single) {
 		local_set(&buf->data_size, buf->output_off);
 		return;
@@ -865,7 +890,7 @@ static void pt_update_head(struct pt *pt)
 	} else {
 		old = (local64_xchg(&buf->head, base) &
 		       ((buf->nr_pages << PAGE_SHIFT) - 1));
-		if (base < old)
+		if (base < old || (base == old && wrapped))
 			base += buf->nr_pages << PAGE_SHIFT;
 
 		local_add(base - old, &buf->data_size);
@@ -1511,6 +1536,7 @@ void intel_pt_interrupt(void)
 		buf = perf_aux_output_begin(&pt->handle, event);
 		if (!buf) {
 			event->hw.state = PERF_HES_STOPPED;
+			WRITE_ONCE(pt->resume_allowed, 0);
 			return;
 		}
 
@@ -1519,6 +1545,7 @@ void intel_pt_interrupt(void)
 		ret = pt_buffer_reset_markers(buf, &pt->handle);
 		if (ret) {
 			perf_aux_output_end(&pt->handle, 0);
+			WRITE_ONCE(pt->resume_allowed, 0);
 			return;
 		}
 
@@ -1573,6 +1600,26 @@ static void pt_event_start(struct perf_event *event, int mode)
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 	struct pt_buffer *buf;
 
+	if (mode & PERF_EF_RESUME) {
+		if (READ_ONCE(pt->resume_allowed)) {
+			u64 status;
+
+			/*
+			 * Only if the trace is not active and the error and
+			 * stopped bits are clear, is it safe to start, but a
+			 * PMI might have just cleared these, so resume_allowed
+			 * must be checked again also.
+			 */
+			rdmsrl(MSR_IA32_RTIT_STATUS, status);
+			if (!(status & (RTIT_STATUS_TRIGGEREN |
+					RTIT_STATUS_ERROR |
+					RTIT_STATUS_STOPPED)) &&
+			   READ_ONCE(pt->resume_allowed))
+				pt_config_start(event);
+		}
+		return;
+	}
+
 	buf = perf_aux_output_begin(&pt->handle, event);
 	if (!buf)
 		goto fail_stop;
@@ -1583,7 +1630,6 @@ static void pt_event_start(struct perf_event *event, int mode)
 			goto fail_end_stop;
 	}
 
-	WRITE_ONCE(pt->handle_nmi, 1);
 	hwc->state = 0;
 
 	pt_config_buffer(buf);
@@ -1601,6 +1647,12 @@ static void pt_event_stop(struct perf_event *event, int mode)
 {
 	struct pt *pt = this_cpu_ptr(&pt_ctx);
 
+	if (mode & PERF_EF_PAUSE) {
+		if (READ_ONCE(pt->pause_allowed))
+			pt_config_stop(event);
+		return;
+	}
+
 	/*
 	 * Protect against the PMI racing with disabling wrmsr,
 	 * see comment in intel_pt_interrupt().
@@ -1608,6 +1660,15 @@ static void pt_event_stop(struct perf_event *event, int mode)
 	WRITE_ONCE(pt->handle_nmi, 0);
 	barrier();
 
+	/*
+	 * Prevent a resume from attempting to restart tracing, or a pause
+	 * during a subsequent start. Do this after clearing handle_nmi so that
+	 * pt_event_snapshot_aux() will not re-allow them.
+	 */
+	WRITE_ONCE(pt->pause_allowed, 0);
+	WRITE_ONCE(pt->resume_allowed, 0);
+	barrier();
+
 	pt_config_stop(event);
 
 	if (event->hw.state == PERF_HES_STOPPED)
@@ -1657,6 +1718,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
 	if (WARN_ON_ONCE(!buf->snapshot))
 		return 0;
 
+	/* Prevent pause/resume from attempting to start/stop tracing */
+	WRITE_ONCE(pt->pause_allowed, 0);
+	WRITE_ONCE(pt->resume_allowed, 0);
+	barrier();
 	/*
 	 * There is no PT interrupt in this mode, so stop the trace and it will
 	 * remain stopped while the buffer is copied.
@@ -1676,8 +1741,13 @@ static long pt_event_snapshot_aux(struct perf_event *event,
 	 * Here, handle_nmi tells us if the tracing was on.
 	 * If the tracing was on, restart it.
 	 */
-	if (READ_ONCE(pt->handle_nmi))
+	if (READ_ONCE(pt->handle_nmi)) {
+		WRITE_ONCE(pt->resume_allowed, 1);
+		barrier();
 		pt_config_start(event);
+		barrier();
+		WRITE_ONCE(pt->pause_allowed, 1);
+	}
 
 	return ret;
 }
@@ -1793,7 +1863,9 @@ 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;
 
-	pt_pmu.pmu.capabilities	|= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE;
+	pt_pmu.pmu.capabilities		|= PERF_PMU_CAP_EXCLUSIVE |
+					   PERF_PMU_CAP_ITRACE |
+					   PERF_PMU_CAP_AUX_PAUSE;
 	pt_pmu.pmu.attr_groups		 = pt_attr_groups;
 	pt_pmu.pmu.task_ctx_nr		 = perf_sw_context;
 	pt_pmu.pmu.event_init		 = pt_event_init;
diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
index f5e46c04c145..7ee94fc6d7cb 100644
--- a/arch/x86/events/intel/pt.h
+++ b/arch/x86/events/intel/pt.h
@@ -65,6 +65,7 @@ struct pt_pmu {
  * @head:	logical write offset inside the buffer
  * @snapshot:	if this is for a snapshot/overwrite counter
  * @single:	use Single Range Output instead of ToPA
+ * @wrapped:	buffer advance wrapped back to the first topa table
  * @stop_pos:	STOP topa entry index
  * @intr_pos:	INT topa entry index
  * @stop_te:	STOP topa entry pointer
@@ -82,6 +83,7 @@ struct pt_buffer {
 	local64_t		head;
 	bool			snapshot;
 	bool			single;
+	bool			wrapped;
 	long			stop_pos, intr_pos;
 	struct topa_entry	*stop_te, *intr_te;
 	void			**data_pages;
@@ -117,6 +119,8 @@ struct pt_filters {
  * @filters:		last configured filters
  * @handle_nmi:		do handle PT PMI on this cpu, there's an active event
  * @vmx_on:		1 if VMX is ON on this cpu
+ * @pause_allowed:	PERF_EF_PAUSE is allowed to stop tracing
+ * @resume_allowed:	PERF_EF_RESUME is allowed to start tracing
  * @output_base:	cached RTIT_OUTPUT_BASE MSR value
  * @output_mask:	cached RTIT_OUTPUT_MASK MSR value
  */
@@ -125,6 +129,8 @@ struct pt {
 	struct pt_filters	filters;
 	int			handle_nmi;
 	int			vmx_on;
+	int			pause_allowed;
+	int			resume_allowed;
 	u64			output_base;
 	u64			output_mask;
 };
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index ac1182141bf6..82c6f45ce975 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -668,24 +668,38 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
+/*
+ * CPUID.1AH.EAX[31:0] uniquely identifies the microarchitecture
+ * of the core. Bits 31-24 indicates its core type (Core or Atom)
+ * and Bits [23:0] indicates the native model ID of the core.
+ * Core type and native model ID are defined in below enumerations.
+ */
 enum hybrid_cpu_type {
 	HYBRID_INTEL_NONE,
 	HYBRID_INTEL_ATOM	= 0x20,
 	HYBRID_INTEL_CORE	= 0x40,
 };
 
+#define X86_HYBRID_PMU_ATOM_IDX		0
+#define X86_HYBRID_PMU_CORE_IDX		1
+#define X86_HYBRID_PMU_TINY_IDX		2
+
 enum hybrid_pmu_type {
 	not_hybrid,
-	hybrid_small		= BIT(0),
-	hybrid_big		= BIT(1),
-
-	hybrid_big_small	= hybrid_big | hybrid_small, /* only used for matching */
+	hybrid_small		= BIT(X86_HYBRID_PMU_ATOM_IDX),
+	hybrid_big		= BIT(X86_HYBRID_PMU_CORE_IDX),
+	hybrid_tiny		= BIT(X86_HYBRID_PMU_TINY_IDX),
+
+	/* The belows are only used for matching */
+	hybrid_big_small	= hybrid_big   | hybrid_small,
+	hybrid_small_tiny	= hybrid_small | hybrid_tiny,
+	hybrid_big_small_tiny	= hybrid_big   | hybrid_small_tiny,
 };
 
-#define X86_HYBRID_PMU_ATOM_IDX		0
-#define X86_HYBRID_PMU_CORE_IDX		1
-
-#define X86_HYBRID_NUM_PMUS		2
+enum atom_native_id {
+	cmt_native_id           = 0x2,  /* Crestmont */
+	skt_native_id           = 0x3,  /* Skymont */
+};
 
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
@@ -1578,6 +1592,8 @@ u64 cmt_latency_data(struct perf_event *event, u64 status);
 
 u64 lnl_latency_data(struct perf_event *event, u64 status);
 
+u64 arl_h_latency_data(struct perf_event *event, u64 status);
+
 extern struct event_constraint intel_core2_pebs_event_constraints[];
 
 extern struct event_constraint intel_atom_pebs_event_constraints[];
@@ -1697,6 +1713,8 @@ void intel_pmu_pebs_data_source_grt(void);
 
 void intel_pmu_pebs_data_source_mtl(void);
 
+void intel_pmu_pebs_data_source_arl_h(void);
+
 void intel_pmu_pebs_data_source_cmt(void);
 
 void intel_pmu_pebs_data_source_lnl(void);
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index a481a939862e..a8defc813c36 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -148,7 +148,6 @@ struct rapl_model {
  /* 1/2^hw_unit Joule */
 static int rapl_hw_unit[NR_RAPL_DOMAINS] __read_mostly;
 static struct rapl_pmus *rapl_pmus;
-static cpumask_t rapl_cpu_mask;
 static unsigned int rapl_cntr_mask;
 static u64 rapl_timer_ms;
 static struct perf_msr *rapl_msrs;
@@ -369,8 +368,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	if (event->cpu < 0)
 		return -EINVAL;
 
-	event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
-
 	if (!cfg || cfg >= NR_RAPL_DOMAINS + 1)
 		return -EINVAL;
 
@@ -389,7 +386,6 @@ static int rapl_pmu_event_init(struct perf_event *event)
 	pmu = cpu_to_rapl_pmu(event->cpu);
 	if (!pmu)
 		return -EINVAL;
-	event->cpu = pmu->cpu;
 	event->pmu_private = pmu;
 	event->hw.event_base = rapl_msrs[bit].msr;
 	event->hw.config = cfg;
@@ -403,23 +399,6 @@ static void rapl_pmu_event_read(struct perf_event *event)
 	rapl_event_update(event);
 }
 
-static ssize_t rapl_get_attr_cpumask(struct device *dev,
-				struct device_attribute *attr, char *buf)
-{
-	return cpumap_print_to_pagebuf(true, buf, &rapl_cpu_mask);
-}
-
-static DEVICE_ATTR(cpumask, S_IRUGO, rapl_get_attr_cpumask, NULL);
-
-static struct attribute *rapl_pmu_attrs[] = {
-	&dev_attr_cpumask.attr,
-	NULL,
-};
-
-static struct attribute_group rapl_pmu_attr_group = {
-	.attrs = rapl_pmu_attrs,
-};
-
 RAPL_EVENT_ATTR_STR(energy-cores, rapl_cores, "event=0x01");
 RAPL_EVENT_ATTR_STR(energy-pkg  ,   rapl_pkg, "event=0x02");
 RAPL_EVENT_ATTR_STR(energy-ram  ,   rapl_ram, "event=0x03");
@@ -467,7 +446,6 @@ static struct attribute_group rapl_pmu_format_group = {
 };
 
 static const struct attribute_group *rapl_attr_groups[] = {
-	&rapl_pmu_attr_group,
 	&rapl_pmu_format_group,
 	&rapl_pmu_events_group,
 	NULL,
@@ -570,65 +548,6 @@ static struct perf_msr amd_rapl_msrs[] = {
 	[PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group,  NULL, false, 0 },
 };
 
-static int rapl_cpu_offline(unsigned int cpu)
-{
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-	int target;
-
-	/* Check if exiting cpu is used for collecting rapl events */
-	if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
-		return 0;
-
-	pmu->cpu = -1;
-	/* Find a new cpu to collect rapl events */
-	target = cpumask_any_but(get_rapl_pmu_cpumask(cpu), cpu);
-
-	/* Migrate rapl events to the new target */
-	if (target < nr_cpu_ids) {
-		cpumask_set_cpu(target, &rapl_cpu_mask);
-		pmu->cpu = target;
-		perf_pmu_migrate_context(pmu->pmu, cpu, target);
-	}
-	return 0;
-}
-
-static int rapl_cpu_online(unsigned int cpu)
-{
-	s32 rapl_pmu_idx = get_rapl_pmu_idx(cpu);
-	if (rapl_pmu_idx < 0) {
-		pr_err("topology_logical_(package/die)_id() returned a negative value");
-		return -EINVAL;
-	}
-	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
-	int target;
-
-	if (!pmu) {
-		pmu = kzalloc_node(sizeof(*pmu), GFP_KERNEL, cpu_to_node(cpu));
-		if (!pmu)
-			return -ENOMEM;
-
-		raw_spin_lock_init(&pmu->lock);
-		INIT_LIST_HEAD(&pmu->active_list);
-		pmu->pmu = &rapl_pmus->pmu;
-		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
-		rapl_hrtimer_init(pmu);
-
-		rapl_pmus->pmus[rapl_pmu_idx] = pmu;
-	}
-
-	/*
-	 * Check if there is an online cpu in the package which collects rapl
-	 * events already.
-	 */
-	target = cpumask_any_and(&rapl_cpu_mask, get_rapl_pmu_cpumask(cpu));
-	if (target < nr_cpu_ids)
-		return 0;
-
-	cpumask_set_cpu(cpu, &rapl_cpu_mask);
-	pmu->cpu = cpu;
-	return 0;
-}
-
 static int rapl_check_hw_unit(struct rapl_model *rm)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -707,12 +626,41 @@ static const struct attribute_group *rapl_attr_update[] = {
 	NULL,
 };
 
+static int __init init_rapl_pmu(void)
+{
+	struct rapl_pmu *pmu;
+	int idx;
+
+	for (idx = 0; idx < rapl_pmus->nr_rapl_pmu; idx++) {
+		pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
+		if (!pmu)
+			goto free;
+
+		raw_spin_lock_init(&pmu->lock);
+		INIT_LIST_HEAD(&pmu->active_list);
+		pmu->pmu = &rapl_pmus->pmu;
+		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
+		rapl_hrtimer_init(pmu);
+
+		rapl_pmus->pmus[idx] = pmu;
+	}
+
+	return 0;
+free:
+	for (; idx > 0; idx--)
+		kfree(rapl_pmus->pmus[idx - 1]);
+	return -ENOMEM;
+}
+
 static int __init init_rapl_pmus(void)
 {
 	int nr_rapl_pmu = topology_max_packages();
+	int rapl_pmu_scope = PERF_PMU_SCOPE_PKG;
 
-	if (!rapl_pmu_is_pkg_scope())
+	if (!rapl_pmu_is_pkg_scope()) {
 		nr_rapl_pmu *= topology_max_dies_per_package();
+		rapl_pmu_scope = PERF_PMU_SCOPE_DIE;
+	}
 
 	rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL);
 	if (!rapl_pmus)
@@ -728,9 +676,11 @@ static int __init init_rapl_pmus(void)
 	rapl_pmus->pmu.start		= rapl_pmu_event_start;
 	rapl_pmus->pmu.stop		= rapl_pmu_event_stop;
 	rapl_pmus->pmu.read		= rapl_pmu_event_read;
+	rapl_pmus->pmu.scope		= rapl_pmu_scope;
 	rapl_pmus->pmu.module		= THIS_MODULE;
 	rapl_pmus->pmu.capabilities	= PERF_PMU_CAP_NO_EXCLUDE;
-	return 0;
+
+	return init_rapl_pmu();
 }
 
 static struct rapl_model model_snb = {
@@ -876,24 +826,13 @@ static int __init rapl_pmu_init(void)
 	if (ret)
 		return ret;
 
-	/*
-	 * Install callbacks. Core will call them for each online cpu.
-	 */
-	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
-				"perf/x86/rapl:online",
-				rapl_cpu_online, rapl_cpu_offline);
-	if (ret)
-		goto out;
-
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out1;
+		goto out;
 
 	rapl_advertise();
 	return 0;
 
-out1:
-	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
@@ -903,7 +842,6 @@ module_init(rapl_pmu_init);
 
 static void __exit intel_rapl_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
 }
diff --git a/arch/x86/include/asm/cpu.h b/arch/x86/include/asm/cpu.h
index aa30fd8cad7f..5af69b5be2fb 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -32,6 +32,7 @@ extern bool handle_user_split_lock(struct pt_regs *regs, long error_code);
 extern bool handle_guest_split_lock(unsigned long ip);
 extern void handle_bus_lock(struct pt_regs *regs);
 u8 get_this_hybrid_cpu_type(void);
+u32 get_this_hybrid_cpu_native_id(void);
 #else
 static inline void __init sld_setup(struct cpuinfo_x86 *c) {}
 static inline bool handle_user_split_lock(struct pt_regs *regs, long error_code)
@@ -50,6 +51,11 @@ static inline u8 get_this_hybrid_cpu_type(void)
 {
 	return 0;
 }
+
+static inline u32 get_this_hybrid_cpu_native_id(void)
+{
+	return 0;
+}
 #endif
 #ifdef CONFIG_IA32_FEAT_CTL
 void init_ia32_feat_ctl(struct cpuinfo_x86 *c);
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 91b73571412f..d95f902acc52 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -536,15 +536,17 @@ struct x86_perf_regs {
 	u64		*xmm_regs;
 };
 
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
+extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs);
+#define perf_arch_misc_flags(regs)	perf_arch_misc_flags(regs)
+#define perf_arch_guest_misc_flags(regs)	perf_arch_guest_misc_flags(regs)
 
 #include <asm/stacktrace.h>
 
 /*
- * We abuse bit 3 from flags to pass exact information, see perf_misc_flags
- * and the comment with PERF_EFLAGS_EXACT.
+ * We abuse bit 3 from flags to pass exact information, see
+ * perf_arch_misc_flags() and the comment with PERF_EFLAGS_EXACT.
  */
 #define perf_arch_fetch_caller_regs(regs, __ip)		{	\
 	(regs)->ip = (__ip);					\
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index e7656cbef68d..624397e43ac6 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -1299,3 +1299,18 @@ u8 get_this_hybrid_cpu_type(void)
 
 	return cpuid_eax(0x0000001a) >> X86_HYBRID_CPU_TYPE_ID_SHIFT;
 }
+
+/**
+ * get_this_hybrid_cpu_native_id() - Get the native id of this hybrid CPU
+ *
+ * Returns the uarch native ID [23:0] of a CPU in a hybrid processor.
+ * If the processor is not hybrid, returns 0.
+ */
+u32 get_this_hybrid_cpu_native_id(void)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_HYBRID_CPU))
+		return 0;
+
+	return cpuid_eax(0x0000001a) &
+	       (BIT_ULL(X86_HYBRID_CPU_TYPE_ID_SHIFT) - 1);
+}