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
  ...

24 files changed, 384 insertions, 223 deletions

diff --git a/arch/Kconfig b/arch/Kconfig
index bd9f095d69fa..b4ad3a6d29f1 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -135,6 +135,7 @@ config KPROBES_ON_FTRACE
 config UPROBES
 	def_bool n
 	depends on ARCH_SUPPORTS_UPROBES
+	select TASKS_TRACE_RCU
 	help
 	  Uprobes is the user-space counterpart to kprobes: they
 	  enable instrumentation applications (such as 'perf probe')
diff --git a/arch/arm/include/asm/perf_event.h b/arch/arm/include/asm/perf_event.h
index bdbc1e590891..c08f16f2e243 100644
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@@ -8,13 +8,6 @@
 #ifndef __ARM_PERF_EVENT_H__
 #define __ARM_PERF_EVENT_H__
 
-#ifdef CONFIG_PERF_EVENTS
-struct pt_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)
-#endif
-
 #define perf_arch_fetch_caller_regs(regs, __ip) { \
 	(regs)->ARM_pc = (__ip); \
 	frame_pointer((regs)) = (unsigned long) __builtin_frame_address(0); \
diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
index 1d230ac9d0eb..a2601b1ef318 100644
--- a/arch/arm/kernel/perf_callchain.c
+++ b/arch/arm/kernel/perf_callchain.c
@@ -96,20 +96,3 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 	arm_get_current_stackframe(regs, &fr);
 	walk_stackframe(&fr, callchain_trace, entry);
 }
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
-	int misc = 0;
-
-	if (user_mode(regs))
-		misc |= PERF_RECORD_MISC_USER;
-	else
-		misc |= PERF_RECORD_MISC_KERNEL;
-
-	return misc;
-}
diff --git a/arch/arm64/include/asm/perf_event.h b/arch/arm64/include/asm/perf_event.h
index eb7071c9eb34..ee45b4e77347 100644
--- a/arch/arm64/include/asm/perf_event.h
+++ b/arch/arm64/include/asm/perf_event.h
@@ -10,10 +10,6 @@
 #include <asm/ptrace.h>
 
 #ifdef CONFIG_PERF_EVENTS
-struct pt_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)
 #define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 #endif
 
diff --git a/arch/arm64/kernel/perf_callchain.c b/arch/arm64/kernel/perf_callchain.c
index e8ed5673f481..9b7f26b128b5 100644
--- a/arch/arm64/kernel/perf_callchain.c
+++ b/arch/arm64/kernel/perf_callchain.c
@@ -38,31 +38,3 @@ void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry,
 
 	arch_stack_walk(callchain_trace, entry, current, regs);
 }
-
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
-{
-	if (perf_guest_state())
-		return perf_guest_get_ip();
-
-	return instruction_pointer(regs);
-}
-
-unsigned long perf_misc_flags(struct pt_regs *regs)
-{
-	unsigned int guest_state = perf_guest_state();
-	int misc = 0;
-
-	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 misc;
-}
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 5995614e9062..af0f46e2373b 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -102,8 +102,8 @@ struct power_pmu {
 int __init register_power_pmu(struct power_pmu *pmu);
 
 struct pt_regs;
-extern unsigned long perf_misc_flags(struct pt_regs *regs);
-extern unsigned long perf_instruction_pointer(struct pt_regs *regs);
+extern unsigned long perf_arch_misc_flags(struct pt_regs *regs);
+extern unsigned long perf_arch_instruction_pointer(struct pt_regs *regs);
 extern unsigned long int read_bhrb(int n);
 
 /*
@@ -111,7 +111,7 @@ extern unsigned long int read_bhrb(int n);
  * if we have hardware PMU support.
  */
 #ifdef CONFIG_PPC_PERF_CTRS
-#define perf_misc_flags(regs)	perf_misc_flags(regs)
+#define perf_arch_misc_flags(regs)	perf_arch_misc_flags(regs)
 #endif
 
 /*
diff --git a/arch/powerpc/perf/callchain.c b/arch/powerpc/perf/callchain.c
index 6b4434dd0ff3..26aa26482c9a 100644
--- a/arch/powerpc/perf/callchain.c
+++ b/arch/powerpc/perf/callchain.c
@@ -51,7 +51,7 @@ perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *re
 
 	lr = regs->link;
 	sp = regs->gpr[1];
-	perf_callchain_store(entry, perf_instruction_pointer(regs));
+	perf_callchain_store(entry, perf_arch_instruction_pointer(regs));
 
 	if (!validate_sp(sp, current))
 		return;
diff --git a/arch/powerpc/perf/callchain_32.c b/arch/powerpc/perf/callchain_32.c
index ea8cfe3806dc..ddcc2d8aa64a 100644
--- a/arch/powerpc/perf/callchain_32.c
+++ b/arch/powerpc/perf/callchain_32.c
@@ -139,7 +139,7 @@ void perf_callchain_user_32(struct perf_callchain_entry_ctx *entry,
 	long level = 0;
 	unsigned int __user *fp, *uregs;
 
-	next_ip = perf_instruction_pointer(regs);
+	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/callchain_64.c b/arch/powerpc/perf/callchain_64.c
index 488e8a21a11e..115d1c105e8a 100644
--- a/arch/powerpc/perf/callchain_64.c
+++ b/arch/powerpc/perf/callchain_64.c
@@ -74,7 +74,7 @@ void perf_callchain_user_64(struct perf_callchain_entry_ctx *entry,
 	struct signal_frame_64 __user *sigframe;
 	unsigned long __user *fp, *uregs;
 
-	next_ip = perf_instruction_pointer(regs);
+	next_ip = perf_arch_instruction_pointer(regs);
 	lr = regs->link;
 	sp = regs->gpr[1];
 	perf_callchain_store(entry, next_ip);
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 42867469752d..dc01aa604cc1 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -2332,7 +2332,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
  * Called from generic code to get the misc flags (i.e. processor mode)
  * for an event_id.
  */
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	u32 flags = perf_get_misc_flags(regs);
 
@@ -2346,7 +2346,7 @@ unsigned long perf_misc_flags(struct pt_regs *regs)
  * Called from generic code to get the instruction pointer
  * for an event_id.
  */
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	unsigned long siar = mfspr(SPRN_SIAR);
 
diff --git a/arch/s390/include/asm/perf_event.h b/arch/s390/include/asm/perf_event.h
index 29ee289108c5..e53894cedf08 100644
--- a/arch/s390/include/asm/perf_event.h
+++ b/arch/s390/include/asm/perf_event.h
@@ -37,9 +37,9 @@ extern ssize_t cpumf_events_sysfs_show(struct device *dev,
 
 /* Perf callbacks */
 struct pt_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);
+#define perf_arch_misc_flags(regs) perf_arch_misc_flags(regs)
 #define perf_arch_bpf_user_pt_regs(regs) &regs->user_regs
 
 /* Perf pt_regs extension for sample-data-entry indicators */
diff --git a/arch/s390/kernel/perf_event.c b/arch/s390/kernel/perf_event.c
index 0c65eaf099f9..2b9611c4718e 100644
--- a/arch/s390/kernel/perf_event.c
+++ b/arch/s390/kernel/perf_event.c
@@ -57,7 +57,7 @@ static unsigned long instruction_pointer_guest(struct pt_regs *regs)
 	return sie_block(regs)->gpsw.addr;
 }
 
-unsigned long perf_instruction_pointer(struct pt_regs *regs)
+unsigned long perf_arch_instruction_pointer(struct pt_regs *regs)
 {
 	return is_in_guest(regs) ? instruction_pointer_guest(regs)
 				 : instruction_pointer(regs);
@@ -84,7 +84,7 @@ static unsigned long perf_misc_flags_sf(struct pt_regs *regs)
 	return flags;
 }
 
-unsigned long perf_misc_flags(struct pt_regs *regs)
+unsigned long perf_arch_misc_flags(struct pt_regs *regs)
 {
 	/* Check if the cpum_sf PMU has created the pt_regs structure.
 	 * In this case, perf misc flags can be easily extracted.  Otherwise,
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_allow