Merge tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:

 - Intel PT support enhancements & fixes

 - Fix leaked SIGTRAP events

 - Improve and fix the Intel uncore driver

 - Add support for Intel HBM and CXL uncore counters

 - Add Intel Lake and Arrow Lake support

 - AMD uncore driver fixes

 - Make SIGTRAP and __perf_pending_irq() work on RT

 - Micro-optimizations

 - Misc cleanups and fixes

* tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  perf/x86/intel: Add a distinct name for Granite Rapids
  perf/x86/intel/ds: Fix non 0 retire latency on Raptorlake
  perf/x86/intel: Hide Topdown metrics events if the feature is not enumerated
  perf/x86/intel/uncore: Fix the bits of the CHA extended umask for SPR
  perf: Split __perf_pending_irq() out of perf_pending_irq()
  perf: Don't disable preemption in perf_pending_task().
  perf: Move swevent_htable::recursion into task_struct.
  perf: Shrink the size of the recursion counter.
  perf: Enqueue SIGTRAP always via task_work.
  task_work: Add TWA_NMI_CURRENT as an additional notify mode.
  perf: Move irq_work_queue() where the event is prepared.
  perf: Fix event leak upon exec and file release
  perf: Fix event leak upon exit
  task_work: Introduce task_work_cancel() again
  task_work: s/task_work_cancel()/task_work_cancel_func()/
  perf/x86/amd/uncore: Fix DF and UMC domain identification
  perf/x86/amd/uncore: Avoid PMU registration if counters are unavailable
  perf/x86/intel: Support Perfmon MSRs aliasing
  perf/x86/intel: Support PERFEVTSEL extension
  perf/x86: Add config_mask to represent EVENTSEL bitmask
  ...

arch/x86/events/amd/core.c

@@ -432,8 +432,10 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
 	 * be removed on one CPU at a time AND PMU is disabled
 	 * when we come here
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
-		if (cmpxchg(nb->owners + i, event, NULL) == event)
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+		struct perf_event *tmp = event;
+
+		if (try_cmpxchg(nb->owners + i, &tmp, NULL))
 			break;
 	}
 }
@@ -499,7 +501,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
 	 * because of successive calls to x86_schedule_events() from
 	 * hw_perf_group_sched_in() without hw_perf_enable()
 	 */
-	for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
+	for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
 		if (new == -1 || hwc->idx == idx)
 			/* assign free slot, prefer hwc->idx */
 			old = cmpxchg(nb->owners + idx, NULL, event);
@@ -542,7 +544,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
 	/*
 	 * initialize all possible NB constraints
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		__set_bit(i, nb->event_constraints[i].idxmsk);
 		nb->event_constraints[i].weight = 1;
 	}
@@ -735,7 +737,7 @@ static void amd_pmu_check_overflow(void)
 	 * counters are always enabled when this function is called and
 	 * ARCH_PERFMON_EVENTSEL_INT is always set.
 	 */
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -755,7 +757,7 @@ static void amd_pmu_enable_all(int added)
 
 	amd_brs_enable_all();
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		/* only activate events which are marked as active */
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -978,7 +980,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
 	/* Clear any reserved bits set by buggy microcode */
 	status &= amd_pmu_global_cntr_mask;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
 
@@ -1313,7 +1315,7 @@ static __initconst const struct x86_pmu amd_pmu = {
 	.addr_offset            = amd_pmu_addr_offset,
 	.event_map		= amd_pmu_event_map,
 	.max_events		= ARRAY_SIZE(amd_perfmon_event_map),
-	.num_counters		= AMD64_NUM_COUNTERS,
+	.cntr_mask64		= GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
 	.add			= amd_pmu_add_event,
 	.del			= amd_pmu_del_event,
 	.cntval_bits		= 48,
@@ -1412,7 +1414,7 @@ static int __init amd_core_pmu_init(void)
 	 */
 	x86_pmu.eventsel	= MSR_F15H_PERF_CTL;
 	x86_pmu.perfctr		= MSR_F15H_PERF_CTR;
-	x86_pmu.num_counters	= AMD64_NUM_COUNTERS_CORE;
+	x86_pmu.cntr_mask64	= GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
 
 	/* Check for Performance Monitoring v2 support */
 	if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
@@ -1422,9 +1424,9 @@ static int __init amd_core_pmu_init(void)
 		x86_pmu.version = 2;
 
 		/* Find the number of available Core PMCs */
-		x86_pmu.num_counters = ebx.split.num_core_pmc;
+		x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
 
-		amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
+		amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
 
 		/* Update PMC handling functions */
 		x86_pmu.enable_all = amd_pmu_v2_enable_all;
@@ -1452,12 +1454,12 @@ static int __init amd_core_pmu_init(void)
 		 * even numbered counter that has a consecutive adjacent odd
 		 * numbered counter following it.
 		 */
-		for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
+		for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
 			even_ctr_mask |= BIT_ULL(i);
 
 		pair_constraint = (struct event_constraint)
 				    __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
-				    x86_pmu.num_counters / 2, 0,
+				    x86_pmu_max_num_counters(NULL) / 2, 0,
 				    PERF_X86_EVENT_PAIR);
 
 		x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;

arch/x86/events/amd/uncore.c

@@ -162,7 +162,9 @@ static int amd_uncore_add(struct perf_event *event, int flags)
 	/* if not, take the first available counter */
 	hwc->idx = -1;
 	for (i = 0; i < pmu->num_counters; i++) {
-		if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
+		struct perf_event *tmp = NULL;
+
+		if (try_cmpxchg(&ctx->events[i], &tmp, event)) {
 			hwc->idx = i;
 			break;
 		}
@@ -196,7 +198,9 @@ static void amd_uncore_del(struct perf_event *event, int flags)
 	event->pmu->stop(event, PERF_EF_UPDATE);
 
 	for (i = 0; i < pmu->num_counters; i++) {
-		if (cmpxchg(&ctx->events[i], event, NULL) == event)
+		struct perf_event *tmp = event;
+
+		if (try_cmpxchg(&ctx->events[i], &tmp, NULL))
 			break;
 	}
 
@@ -639,7 +643,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	info.split.aux_data = 0;
 	info.split.num_pmcs = NUM_COUNTERS_NB;
 	info.split.gid = 0;
-	info.split.cid = topology_die_id(cpu);
+	info.split.cid = topology_logical_package_id(cpu);
 
 	if (pmu_version >= 2) {
 		ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
@@ -654,17 +658,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 {
 	struct attribute **df_attr = amd_uncore_df_format_attr;
 	struct amd_uncore_pmu *pmu;
+	int num_counters;
 
 	/* Run just once */
 	if (uncore->init_done)
 		return amd_uncore_ctx_init(uncore, cpu);
 
+	num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	if (!num_counters)
+		goto done;
+
 	/* No grouping, single instance for a system */
 	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
-	if (!uncore->pmus) {
-		uncore->num_pmus = 0;
+	if (!uncore->pmus)
 		goto done;
-	}
 
 	/*
 	 * For Family 17h and above, the Northbridge counters are repurposed
@@ -674,7 +681,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	pmu = &uncore->pmus[0];
 	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
 		sizeof(pmu->name));
-	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	pmu->num_counters = num_counters;
 	pmu->msr_base = MSR_F15H_NB_PERF_CTL;
 	pmu->rdpmc_base = RDPMC_BASE_NB;
 	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -785,17 +792,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 {
 	struct attribute **l3_attr = amd_uncore_l3_format_attr;
 	struct amd_uncore_pmu *pmu;
+	int num_counters;
 
 	/* Run just once */
 	if (uncore->init_done)
 		return amd_uncore_ctx_init(uncore, cpu);
 
+	num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	if (!num_counters)
+		goto done;
+
 	/* No grouping, single instance for a system */
 	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
-	if (!uncore->pmus) {
-		uncore->num_pmus = 0;
+	if (!uncore->pmus)
 		goto done;
-	}
 
 	/*
 	 * For Family 17h and above, L3 cache counters are available instead
@@ -805,7 +815,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
 	pmu = &uncore->pmus[0];
 	strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
 		sizeof(pmu->name));
-	pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
+	pmu->num_counters = num_counters;
 	pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
 	pmu->rdpmc_base = RDPMC_BASE_LLC;
 	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
@@ -893,8 +903,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 	cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
 	info.split.aux_data = ecx;	/* stash active mask */
 	info.split.num_pmcs = ebx.split.num_umc_pmc;
-	info.split.gid = topology_die_id(cpu);
-	info.split.cid = topology_die_id(cpu);
+	info.split.gid = topology_logical_package_id(cpu);
+	info.split.cid = topology_logical_package_id(cpu);
 	*per_cpu_ptr(uncore->info, cpu) = info;
 }
 

arch/x86/events/intel/cstate.c

@@ -41,7 +41,7 @@
  *	MSR_CORE_C1_RES: CORE C1 Residency Counter
  *			 perf code: 0x00
  *			 Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
- *					  MTL,SRF,GRR
+ *					  MTL,SRF,GRR,ARL,LNL
  *			 Scope: Core (each processor core has a MSR)
  *	MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
  *			       perf code: 0x01
@@ -53,50 +53,50 @@
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
  *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
- *						GRR
+ *						GRR,ARL,LNL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
  *			       Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
- *						ICL,TGL,RKL,ADL,RPL,MTL
+ *						ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
  *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
  *						KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
- *						RPL,SPR,MTL
+ *						RPL,SPR,MTL,ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
  *						GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
- *						ADL,RPL,MTL
+ *						ADL,RPL,MTL,ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
  *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
  *						SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
- *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
+ *						TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+ *						ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
  *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
- *						KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
+ *						KBL,CML,ICL,TGL,RKL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C8_RESIDENCY:  Package C8 Residency Counter.
  *			       perf code: 0x04
  *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL,MTL
+ *						ADL,RPL,MTL,ARL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C9_RESIDENCY:  Package C9 Residency Counter.
  *			       perf code: 0x05
- *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
- *						ADL,RPL,MTL
+ *			       Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
  *			       perf code: 0x06
  *			       Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
- *						TNT,RKL,ADL,RPL,MTL
+ *						TNT,RKL,ADL,RPL,MTL,ARL,LNL
  *			       Scope: Package (physical package)
  *	MSR_MODULE_C6_RES_MS:  Module C6 Residency Counter.
  *			       perf code: 0x00
@@ -637,9 +637,18 @@ static const struct cstate_model adl_cstates __initconst = {
 	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
 				  BIT(PERF_CSTATE_PKG_C3_RES) |
 				  BIT(PERF_CSTATE_PKG_C6_RES) |
-				  BIT(PERF_CSTATE_PKG_C7_RES) |
 				  BIT(PERF_CSTATE_PKG_C8_RES) |
-				  BIT(PERF_CSTATE_PKG_C9_RES) |
+				  BIT(PERF_CSTATE_PKG_C10_RES),
+};
+
+static const struct cstate_model lnl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C1_RES) |
+				  BIT(PERF_CSTATE_CORE_C6_RES) |
+				  BIT(PERF_CSTATE_CORE_C7_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES) |
 				  BIT(PERF_CSTATE_PKG_C10_RES),
 };
 
@@ -763,6 +772,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 	X86_MATCH_VFM(INTEL_RAPTORLAKE_S,	&adl_cstates),
 	X86_MATCH_VFM(INTEL_METEORLAKE,		&adl_cstates),
 	X86_MATCH_VFM(INTEL_METEORLAKE_L,	&adl_cstates),
+	X86_MATCH_VFM(INTEL_ARROWLAKE,		&adl_cstates),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_H,	&adl_cstates),
+	X86_MATCH_VFM(INTEL_ARROWLAKE_U,	&adl_cstates),
+	X86_MATCH_VFM(INTEL_LUNARLAKE_M,	&lnl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);

arch/x86/events/intel/knc.c

@@ -303,7 +303,7 @@ static const struct x86_pmu knc_pmu __initconst = {
 	.apic			= 1,
 	.max_period		= (1ULL << 39) - 1,
 	.version		= 0,
-	.num_counters		= 2,
+	.cntr_mask64		= 0x3,
 	.cntval_bits		= 40,
 	.cntval_mask		= (1ULL << 40) - 1,
 	.get_event_constraints	= x86_get_event_constraints,

arch/x86/events/intel/p4.c

@@ -919,7 +919,7 @@ static void p4_pmu_disable_all(void)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -998,7 +998,7 @@ static void p4_pmu_enable_all(int added)
 	struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
 	int idx;
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[idx];
 		if (!test_bit(idx, cpuc->active_mask))
 			continue;
@@ -1040,7 +1040,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc = this_cpu_ptr(&cpu_hw_events);
 
-	for (idx = 0; idx < x86_pmu.num_counters; idx++) {
+	for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		int overflow;
 
 		if (!test_bit(idx, cpuc->active_mask)) {
@@ -1353,7 +1353,7 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * though leave it restricted at moment assuming
 	 * HT is on
 	 */
-	.num_counters		= ARCH_P4_MAX_CCCR,
+	.cntr_mask64		= GENMASK_ULL(ARCH_P4_MAX_CCCR - 1, 0),
 	.apic			= 1,
 	.cntval_bits		= ARCH_P4_CNTRVAL_BITS,
 	.cntval_mask		= ARCH_P4_CNTRVAL_MASK,
@@ -1395,7 +1395,7 @@ __init int p4_pmu_init(void)
 	 *
 	 * Solve this by zero'ing out the registers to mimic a reset.
 	 */
-	for (i = 0; i < x86_pmu.num_counters; i++) {
+	for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
 		reg = x86_pmu_config_addr(i);
 		wrmsrl_safe(reg, 0ULL);
 	}

arch/x86/events/intel/p6.c

@@ -214,7 +214,7 @@ static __initconst const struct x86_pmu p6_pmu = {
 	.apic			= 1,
 	.max_period		= (1ULL << 31) - 1,
 	.version		= 0,
-	.num_counters		= 2,
+	.cntr_mask64		= 0x3,
 	/*
 	 * Events have 40 bits implemented. However they are designed such
 	 * that bits [32-39] are sign extensions of bit 31. As such the

arch/x86/events/intel/pt.c

@@ -878,7 +878,7 @@ static void pt_update_head(struct pt *pt)
  */
 static void *pt_buffer_region(struct pt_buffer *buf)
 {
-	return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
+	return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
 }
 
 /**
@@ -990,7 +990,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg)
 	 * order allocations, there shouldn't be many of these.
 	 */
 	list_for_each_entry(topa, &buf->tables, list) {
-		if (topa->offset + topa->size > pg << PAGE_SHIFT)
+		if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT)
 			goto found;
 	}
 

arch/x86/events/intel/pt.h

@@ -33,8 +33,8 @@ struct topa_entry {
 	u64	rsvd2	: 1;
 	u64	size	: 4;
 	u64	rsvd3	: 2;
-	u64	base	: 36;
-	u64	rsvd4	: 16;
+	u64	base	: 40;
+	u64	rsvd4	: 12;
 };
 
 /* TSC to Core Crystal Clock Ratio */

arch/x86/events/intel/uncore.c

@@ -264,6 +264,9 @@ static void uncore_assign_hw_event(struct intel_uncore_box *box,
 		return;
 	}
 
+	if (intel_generic_uncore_assign_hw_event(event, box))
+		return;
+
 	hwc->config_base = uncore_event_ctl(box, hwc->idx);
 	hwc->event_base  = uncore_perf_ctr(box, hwc->idx);
 }
@@ -844,7 +847,9 @@ static void uncore_pmu_disable(struct pmu *pmu)
 static ssize_t uncore_get_attr_cpumask(struct device *dev,
 				struct device_attribute *attr, char *buf)
 {
-	return cpumap_print_to_pagebuf(true, buf, &uncore_cpu_mask);
+	struct intel_uncore_pmu *pmu = container_of(dev_get_drvdata(dev), struct intel_uncore_pmu, pmu);
+
+	return cpumap_print_to_pagebuf(true, buf, &pmu->cpu_mask);
 }
 
 static DEVICE_ATTR(cpumask, S_IRUGO, uncore_get_attr_cpumask, NULL);
@@ -861,7 +866,10 @@ static const struct attribute_group uncore_pmu_attr_group = {
 static inline int uncore_get_box_id(struct intel_uncore_type *type,
 				    struct intel_uncore_pmu *pmu)
 {
-	return type->box_ids ? type->box_ids[pmu->pmu_idx] : pmu->pmu_idx;
+	if (type->boxes)
+		return intel_uncore_find_discovery_unit_id(type->boxes, -1, pmu->pmu_idx);
+
+	return pmu->pmu_idx;
 }
 
 void uncore_get_alias_name(char *pmu_name, struct intel_uncore_pmu *pmu)
@@ -962,6 +970,9 @@ static void uncore_type_exit(struct intel_uncore_type *type)
 	if (type->cleanup_mapping)
 		type->cleanup_mapping(type);
 
+	if (type->cleanup_extra_boxes)
+		type->cleanup_extra_boxes(type);
+
 	if (pmu) {
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
 			uncore_pmu_unregister(pmu);
@@ -970,10 +981,7 @@ static void uncore_type_exit(struct intel_uncore_type *type)
 		kfree(type->pmus);
 		type->pmus = NULL;
 	}
-	if (type->box_ids) {
-		kfree(type->box_ids);
-		type->box_ids = NULL;
-	}
+
 	kfree(type->events_group);
 	type->events_group = NULL;
 }
@@ -1077,22 +1085,19 @@ static struct intel_uncore_pmu *
 uncore_pci_find_dev_pmu_from_types(struct pci_dev *pdev)
 {
 	struct intel_uncore_type **types = uncore_pci_uncores;
+	struct intel_uncore_discovery_unit *unit;
 	struct intel_uncore_type *type;
-	u64 box_ctl;
-	int i, die;
+	struct rb_node *node;
 
 	for (; *types; types++) {
 		type = *types;
-		for (die = 0; die < __uncore_max_dies; die++) {
-			for (i = 0; i < type->num_boxes; i++) {
-				if (!type->box_ctls[die])
-					continue;
-				box_ctl = type->box_ctls[die] + type->pci_offsets[i];
-				if (pdev->devfn == UNCORE_DISCOVERY_PCI_DEVFN(box_ctl) &&
-				    pdev->bus->number == UNCORE_DISCOVERY_PCI_BUS(box_ctl) &&
-				    pci_domain_nr(pdev->bus) == UNCORE_DISCOVERY_PCI_DOMAIN(box_ctl))
-					return &type->pmus[i];
-			}
+
+		for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+			unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+			if (pdev->devfn == UNCORE_DISCOVERY_PCI_DEVFN(unit->addr) &&
+			    pdev->bus->number == UNCORE_DISCOVERY_PCI_BUS(unit->addr) &&
+			    pci_domain_nr(pdev->bus) == UNCORE_DISCOVERY_PCI_DOMAIN(unit->addr))
+				return &type->pmus[unit->pmu_idx];
 		}
 	}
 
@@ -1368,28 +1373,25 @@ static struct notifier_block uncore_pci_notifier = {
 static void uncore_pci_pmus_register(void)
 {
 	struct intel_uncore_type **types = uncore_pci_uncores;
+	struct intel_uncore_discovery_unit *unit;
 	struct intel_uncore_type *type;
 	struct intel_uncore_pmu *pmu;
+	struct rb_node *node;
 	struct pci_dev *pdev;
-	u64 box_ctl;
-	int i, die;
 
 	for (; *types; types++) {
 		type = *types;
-		for (die = 0; die < __uncore_max_dies; die++) {
-			for (i = 0; i < type->num_boxes; i++) {
-				if (!type->box_ctls[die])
-					continue;
-				box_ctl = type->box_ctls[die] + type->pci_offsets[i];
-				pdev = pci_get_domain_bus_and_slot(UNCORE_DISCOVERY_PCI_DOMAIN(box_ctl),
-								   UNCORE_DISCOVERY_PCI_BUS(box_ctl),
-								   UNCORE_DISCOVERY_PCI_DEVFN(box_ctl));
-				if (!pdev)
-					continue;
-				pmu = &type->pmus[i];
-
-				uncore_pci_pmu_register(pdev, type, pmu, die);
-			}
+
+		for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+			unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
+			pdev = pci_get_domain_bus_and_slot(UNCORE_DISCOVERY_PCI_DOMAIN(unit->addr),
+							   UNCORE_DISCOVERY_PCI_BUS(unit->addr),
+							   UNCORE_DISCOVERY_PCI_DEVFN(unit->addr));
+
+			if (!pdev)
+				continue;
+			pmu = &type->pmus[unit->pmu_idx];
+			uncore_pci_pmu_register(pdev, type, pmu, unit->die);
 		}
 	}
 
@@ -1454,6 +1456,18 @@ static void uncore_pci_exit(void)
 	}
 }
 
+static bool uncore_die_has_box(struct intel_uncore_type *type,
+			       int die, unsigned int pmu_idx)
+{
+	if (!type->boxes)
+		return true;
+
+	if (intel_uncore_find_discovery_unit_id(type->boxes, die, pmu_idx) < 0)
+		return false;
+
+	return true;
+}
+
 static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 				   int new_cpu)
 {
@@ -1469,18 +1483,25 @@ static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 
 		if (old_cpu < 0) {
 			WARN_ON_ONCE(box->cpu != -1);
-			box->cpu = new_cpu;
+			if (uncore_die_has_box(type, die, pmu->pmu_idx)) {
+				box->cpu = new_cpu;
+				cpumask_set_cpu(new_cpu, &pmu->cpu_mask);
+			}
 			continue;
 		}
 
-		WARN_ON_ONCE(box->cpu != old_cpu);
+		WARN_ON_ONCE(box->cpu != -1 && box->cpu != old_cpu);
 		box->cpu = -1;
+		cpumask_clear_cpu(old_cpu, &pmu->cpu_mask);
 		if (new_cpu < 0)
 			continue;
 
+		if (!uncore_die_has_box(type, die, pmu->pmu_idx))
+			continue;
 		uncore_pmu_cancel_hrtimer(box);
 		perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu);
 		box->cpu = new_cpu;
+		cpumask_set_cpu(new_cpu, &pmu->cpu_mask);
 	}
 }
 
@@ -1503,7 +1524,7 @@ static void uncore_box_unref(struct intel_uncore_type **types, int id)
 		pmu = type->pmus;
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
 			box = pmu->boxes[id];
-			if (box && atomic_dec_return(&box->refcnt) == 0)
+			if (box && box->cpu >= 0 && atomic_dec_return(&box->refcnt) == 0)
 				uncore_box_exit(box);
 		}
 	}
@@ -1593,7 +1614,7 @@ static int uncore_box_ref(struct intel_uncore_type **types,
 		pmu = type->pmus;
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
 			box = pmu->boxes[id];
-			if (box && atomic_inc_return(&box->refcnt) == 1)
+			if (box && box->cpu >= 0 && atomic_inc_return(&box->refcnt) == 1)
 				uncore_box_init(box);
 		}
 	}

arch/x86/events/intel/uncore.h

@@ -62,7 +62,6 @@ struct intel_uncore_type {
 	unsigned fixed_ctr;
 	unsigned fixed_ctl;
 	unsigned box_ctl;
-	u64 *box_ctls;	/* Unit ctrl addr of the first box of each die */
 	union {
 		unsigned msr_offset;
 		unsigned mmio_offset;
@@ -76,7 +75,6 @@ struct intel_uncore_type {
 		u64 *pci_offsets;
 		u64 *mmio_offsets;
 	};
-	unsigned *box_ids;
 	struct event_constraint unconstrainted;
 	struct event_constraint *constraints;
 	struct intel_uncore_pmu *pmus;
@@ -86,6 +84,7 @@ struct intel_uncore_type {
 	const struct attribute_group *attr_groups[4];
 	const struct attribute_group **attr_update;
 	struct pmu *pmu; /* for custom pmu ops */
+	struct rb_root *boxes;
 	/*
 	 * Uncore PMU would store relevant platform topology configuration here
 	 * to identify which platform component each PMON block of that type is
@@ -98,6 +97,10 @@ struct intel_uncore_type {
 	int (*get_topology)(struct intel_uncore_type *type);
 	void (*set_mapping)(struct intel_uncore_type *type);
 	void (*cleanup_mapping)(struct intel_uncore_type *type);
+	/*
+	 * Optional callbacks for extra uncore units cleanup
+	 */
+	void (*cleanup_extra_boxes)(struct intel_uncore_type *type);
 };
 
 #define pmu_group attr_groups[0]
@@ -125,6 +128,7 @@ struct intel_uncore_pmu {
 	int				func_id;
 	bool				registered;
 	atomic_t			activeboxes;
+	cpumask_t			cpu_mask;
 	struct intel_uncore_type	*type;
 	struct intel_uncore_box		**boxes;
 };

arch/x86/events/intel/uncore_discovery.h

@@ -113,19 +113,24 @@ struct uncore_unit_discovery {
 	};
 };
 
+struct intel_uncore_discovery_unit {
+	struct rb_node	node;
+	unsigned int	pmu_idx;	/* The idx of the corresponding PMU */
+	unsigned int	id;		/* Unit ID */
+	unsigned int	die;		/* Die ID */
+	u64		addr;		/* Unit Control Address */
+};
+
 struct intel_uncore_discovery_type {
 	struct rb_node	node;
 	enum uncore_access_type	access_type;
-	u64		box_ctrl;	/* Unit ctrl addr of the first box */
-	u64		*box_ctrl_die;	/* Unit ctrl addr of the first box of each die */
+	struct rb_root	units;		/* Unit ctrl addr for all units */
 	u16		type;		/* Type ID of the uncore block */
 	u8		num_counters;
 	u8		counter_width;
 	u8		ctl_offset;	/* Counter Control 0 offset */
 	u8		ctr_offset;	/* Counter 0 offset */
-	u16		num_boxes;	/* number of boxes for the uncore block */
-	unsigned int	*ids;		/* Box IDs */
-	u64		*box_offset;	/* Box offset */
+	u16		num_units;	/* number of units */
 };
 
 bool intel_uncore_has_discovery_tables(int *ignore);
@@ -156,3 +161,10 @@ u64 intel_generic_uncore_pci_read_counter(struct intel_uncore_box *box,
 
 struct intel_uncore_type **
 intel_uncore_generic_init_uncores(enum uncore_access_type type_id, int num_extra);
+
+int intel_uncore_find_discovery_unit_id(struct rb_root *units, int die,
+					unsigned int pmu_idx);
+bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
+					  struct intel_uncore_box *box);
+void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
+			  struct rb_root *root, u16 *num_units);

arch/x86/events/intel/uncore_snbep.c

@@ -462,6 +462,7 @@
 #define SPR_UBOX_DID				0x3250
 
 /* SPR CHA */
+#define SPR_CHA_EVENT_MASK_EXT			0xffffffff
 #define SPR_CHA_PMON_CTL_TID_EN			(1 << 16)
 #define SPR_CHA_PMON_EVENT_MASK			(SNBEP_PMON_RAW_EVENT_MASK | \
 						 SPR_CHA_PMON_CTL_TID_EN)
@@ -478,6 +479,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
 DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
 DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
 DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55");
+DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63");
 DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
 DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
 DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
@@ -5933,10 +5935,11 @@ static int spr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *ev
 	struct hw_perf_event_extra *reg1 = &event->hw.extra_reg;
 	bool tie_en = !!(event->hw.config & SPR_CHA_PMON_CTL_TID_EN);
 	struct intel_uncore_type *type = box->pmu->type;
+	int id = intel_uncore_find_discovery_unit_id(type->boxes, -1, box->pmu->pmu_idx);
 
 	if (tie_en) {
 		reg1->reg = SPR_C0_MSR_PMON_BOX_FILTER0 +
-			    HSWEP_CBO_MSR_OFFSET * type->box_ids[box->pmu->pmu_idx];
+			    HSWEP_CBO_MSR_OFFSET * id;
 		reg1->config = event->attr.config1 & SPR_CHA_PMON_BOX_FILTER_TID;
 		reg1->idx = 0;
 	}
@@ -5958,7 +5961,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = {
 
 static struct attribute *spr_uncore_cha_formats_attr[] = {
 	&format_attr_event.attr,
-	&format_attr_umask_ext4.attr,
+	&format_attr_umask_ext5.attr,
 	&format_attr_tid_en2.attr,
 	&format_attr_edge.attr,
 	&format_attr_inv.attr,
@@ -5994,7 +5997,7 @@ ATTRIBUTE_GROUPS(uncore_alias);
 static struct intel_uncore_type spr_uncore_chabox = {
 	.name			= "cha",
 	.event_mask		= SPR_CHA_PMON_EVENT_MASK,
-	.event_mask_ext		= SPR_RAW_EVENT_MASK_EXT,
+	.event_mask_ext		= SPR_CHA_EVENT_MASK_EXT,
 	.num_shared_regs	= 1,
 	.constraints		= skx_uncore_chabox_constraints,
 	.ops			= &spr_uncore_chabox_ops,
@@ -6162,7 +6165,55 @@ static struct intel_uncore_type spr_uncore_mdf = {
 	.name			= "mdf",
 };
 
-#define UNCORE_SPR_NUM_UNCORE_TYPES		12
+static void spr_uncore_mmio_offs8_init_box(struct intel_uncore_box *box)
+{
+	__set_bit(UNCORE_BOX_FLAG_CTL_OFFS8, &box->flags);
+	intel_generic_uncore_mmio_init_box(box);
+}
+
+static struct intel_uncore_ops spr_uncore_mmio_offs8_ops = {
+	.init_box		= spr_uncore_mmio_offs8_init_box,
+	.exit_box		= uncore_mmio_exit_box,
+	.disable_box		= intel_generic_uncore_mmio_disable_box,
+	.enable_box		= intel_generic_uncore_mmio_enable_box,
+	.disable_event		= intel_generic_uncore_mmio_disable_event,
+	.enable_event		= spr_uncore_mmio_enable_event,
+	.read_counter		= uncore_mmio_read_counter,
+};
+
+#define SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT()			\
+	SPR_UNCORE_COMMON_FORMAT(),				\
+	.ops			= &spr_uncore_mmio_offs8_ops
+
+static struct event_constraint spr_uncore_cxlcm_constraints[] = {
+	UNCORE_EVENT_CONSTRAINT(0x02, 0x0f),
+	UNCORE_EVENT_CONSTRAINT(0x05, 0x0f),
+	UNCORE_EVENT_CONSTRAINT(0x40, 0xf0),
+	UNCORE_EVENT_CONSTRAINT(0x41, 0xf0),
+	UNCORE_EVENT_CONSTRAINT(0x42, 0xf0),
+	UNCORE_EVENT_CONSTRAINT(0x43, 0xf0),
+	UNCORE_EVENT_CONSTRAINT(0x4b, 0xf0),
+	UNCORE_EVENT_CONSTRAINT(0x52, 0xf0),
+	EVENT_CONSTRAINT_END
+};
+
+static struct intel_uncore_type spr_uncore_cxlcm = {
+	SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT(),
+	.name			= "cxlcm",
+	.constraints		= spr_uncore_cxlcm_constraints,
+};
+
+static struct intel_uncore_type spr_uncore_cxldp = {
+	SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT(),
+	.name			= "cxldp",
+};
+
+static struct intel_uncore_type spr_uncore_hbm = {
+	SPR_UNCORE_COMMON_FORMAT(),
+	.name			= "hbm",
+};
+
+#define UNCORE_SPR_NUM_UNCORE_TYPES		15
 #define UNCORE_SPR_CHA				0
 #define UNCORE_SPR_IIO				1
 #define UNCORE_SPR_IMC				6
@@ -6186,6 +6237,9 @@ static struct intel_uncore_type *spr_uncores[UNCORE_SPR_NUM_UNCORE_TYPES] = {
 	NULL,
 	NULL,
 	&spr_uncore_mdf,
+	&spr_uncore_cxlcm,
+	&spr_uncore_cxldp,
+	&spr_uncore_hbm,
 };
 
 /*
@@ -6198,6 +6252,24 @@ static u64 spr_upi_pci_offsets[SPR_UNCORE_UPI_NUM_BOXES] = {
 	0, 0x8000, 0x10000, 0x18000
 };
 
+static void spr_extra_boxes_cleanup(struct intel_uncore_type *type)
+{
+	struct intel_uncore_discovery_unit *pos;
+	struct rb_node *node;
+
+	if (!type->boxes)
+		return;
+
+	while (!RB_EMPTY_ROOT(type->boxes)) {
+		node = rb_first(type->boxes);
+		pos = rb_entry(node, struct intel_uncore_discovery_unit, node);
+		rb_erase(node, type->boxes);
+		kfree(pos);
+	}
+	kfree(type->boxes);
+	type->boxes = NULL;
+}
+
 static struct intel_uncore_type spr_uncore_upi = {
 	.event_mask		= SNBEP_PMON_RAW_EVENT_MASK,
 	.event_mask_ext		= SPR_RAW_EVENT_MASK_EXT,
@@ -6212,10 +6284,11 @@ static struct intel_uncore_type spr_uncore_upi = {
 	.num_counters		= 4,
 	.num_boxes		= SPR_UNCORE_UPI_NUM_BOXES,
 	.perf_ctr_bits		= 48,
-	.perf_ctr		= ICX_UPI_PCI_PMON_CTR0,
-	.event_ctl		= ICX_UPI_PCI_PMON_CTL0,
+	.perf_ctr		= ICX_UPI_PCI_PMON_CTR0 - ICX_UPI_PCI_PMON_BOX_CTL,
+	.event_ctl		= ICX_UPI_PCI_PMON_CTL0 - ICX_UPI_PCI_PMON_BOX_CTL,
 	.box_ctl		= ICX_UPI_PCI_PMON_BOX_CTL,
 	.pci_offsets		= spr_upi_pci_offsets,
+	.cleanup_extra_boxes	= spr_extra_boxes_cleanup,
 };
 
 static struct intel_uncore_type spr_uncore_m3upi = {
@@ -6225,11 +6298,12 @@ static struct intel_uncore_type spr_uncore_m3upi = {
 	.num_counters		= 4,
 	.num_boxes		= SPR_UNCORE_UPI_NUM_BOXES,
 	.perf_ctr_bits		= 48,
-	.perf_ctr		= ICX_M3UPI_PCI_PMON_CTR0,
-	.event_ctl		= ICX_M3UPI_PCI_PMON_CTL0,
+	.perf_ctr		= ICX_M3UPI_PCI_PMON_CTR0 - ICX_M3UPI_PCI_PMON_BOX_CTL,
+	.event_ctl		= ICX_M3UPI_PCI_PMON_CTL0 - ICX_M3UPI_PCI_PMON_BOX_CTL,
 	.box_ctl		= ICX_M3UPI_PCI_PMON_BOX_CTL,
 	.pci_offsets		= spr_upi_pci_offsets,
 	.constraints		= icx_uncore_m3upi_constraints,
+	.cleanup_extra_boxes	= spr_extra_boxes_cleanup,
 };
 
 enum perf_uncore_spr_iio_freerunning_type_id {
@@ -6460,18 +6534,21 @@ uncore_find_type_by_id(struct intel_uncore_type **types, int type_id)
 static int uncore_type_max_boxes(struct intel_uncore_type **types,
 				 int type_id)
 {
+	struct intel_uncore_discovery_unit *unit;
 	struct intel_uncore_type *type;
-	int i, max = 0;
+	struct rb_node *node;
+	int max = 0;
 
 	type = uncore_find_type_by_id(types, type_id);
 	if (!type)
 		return 0;
 
-	for (i = 0; i < type->num_boxes; i++) {
-		if (type->box_ids[i] > max)
-			max = type->box_ids[i];
-	}
+	for (node = rb_first(type->boxes); node; node = rb_next(node)) {
+		unit = rb_entry(node, struct intel_uncore_discovery_unit, node);
 
+		if (unit->id > max)
+			max = unit->id;
+	}
 	return max + 1;
 }
 
@@ -6513,10 +6590,11 @@ void spr_uncore_cpu_init(void)
 
 static void spr_update_device_location(int type_id)
 {
+	struct intel_uncore_discovery_unit *unit;
 	struct intel_uncore_type *type;
 	struct pci_dev *dev = NULL;
+	struct rb_root *root;
 	u32 device, devfn;
-	u64 *ctls;
 	int die;
 
 	if (type_id == UNCORE_SPR_UPI) {
@@ -6530,27 +6608,35 @@ static void spr_update_device_location(int type_id)
 	} else
 		return;
 
-	ctls = kcalloc(__uncore_max_dies, sizeof(u64), GFP_KERNEL);
-	if (!ctls) {
+	root = kzalloc(sizeof(struct rb_root), GFP_KERNEL);
+	if (!root) {
 		type->num_boxes = 0;
 		return;
 	}
+	*root = RB_ROOT;
 
 	while ((dev = pci_get_device(PCI_VENDOR_ID_INTEL, device, dev)) != NULL) {
-		if (devfn != dev->devfn)
-			continue;
 
 		die = uncore_device_to_die(dev);
 		if (die < 0)
 			continue;
 
-		ctls[die] = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET |
-			    dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET |
-			    devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET |
-			    type->box_ctl;
+		unit = kzalloc(sizeof(*unit), GFP_KERNEL);
+		if (!unit)
+			continue;
+		unit->die = die;
+		unit->id = PCI_SLOT(dev->devfn) - PCI_SLOT(devfn);
+		unit->addr = pci_domain_nr(dev->bus) << UNCORE_DISCOVERY_PCI_DOMAIN_OFFSET |
+			     dev->bus->number << UNCORE_DISCOVERY_PCI_BUS_OFFSET |
+			     devfn << UNCORE_DISCOVERY_PCI_DEVFN_OFFSET |
+			     type->box_ctl;
+
+		unit->pmu_idx = unit->id;
+
+		uncore_find_add_unit(unit, root, NULL);
 	}
 
-	type->box_ctls = ctls;
+	type->boxes = root;
 }
 
 int spr_uncore_pci_init(void)
@@ -6623,7 +6709,7 @@ static struct intel_uncore_type gnr_uncore_b2cmi = {
 };
 
 static struct intel_uncore_type gnr_uncore_b2cxl = {
-	SPR_UNCORE_MMIO_COMMON_FORMAT(),
+	SPR_UNCORE_MMIO_OFFS8_COMMON_FORMAT(),
 	.name			= "b2cxl",
 };
 

arch/x86/events/perf_event.h

@@ -476,6 +476,14 @@ struct cpu_hw_events {
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID)
 
+#define INTEL_HYBRID_LDLAT_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_LD_HSW)
+
+#define INTEL_HYBRID_STLAT_CONSTRAINT(c, n)	\
+	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
+			  HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LAT_HYBRID|PERF_X86_EVENT_PEBS_ST_HSW)
+
 /* Event constraint, but match on all event flags too. */
 #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \
 	EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS)
@@ -655,8 +663,10 @@ enum {
 	x86_lbr_exclusive_max,
 };
 
-#define PERF_PEBS_DATA_SOURCE_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_MAX	0x100
 #define PERF_PEBS_DATA_SOURCE_MASK	(PERF_PEBS_DATA_SOURCE_MAX - 1)
+#define PERF_PEBS_DATA_SOURCE_GRT_MAX	0x10
+#define PERF_PEBS_DATA_SOURCE_GRT_MASK	(PERF_PEBS_DATA_SOURCE_GRT_MAX - 1)
 
 enum hybrid_cpu_type {
 	HYBRID_INTEL_NONE,
@@ -684,9 +694,16 @@ struct x86_hybrid_pmu {
 	cpumask_t			supported_cpus;
 	union perf_capabilities		intel_cap;
 	u64				intel_ctrl;
-	int				max_pebs_events;
-	int				num_counters;
-	int				num_counters_fixed;
+	u64				pebs_events_mask;
+	u64				config_mask;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	struct event_constraint		unconstrained;
 
 	u64				hw_cache_event_ids
@@ -770,12 +787,20 @@ struct x86_pmu {
 	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
+	unsigned	fixedctr;
 	int		(*addr_offset)(int index, bool eventsel);
 	int		(*rdpmc_index)(int index);
 	u64		(*event_map)(int);
 	int		max_events;
-	int		num_counters;
-	int		num_counters_fixed;
+	u64		config_mask;
+	union {
+			u64		cntr_mask64;
+			unsigned long	cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
+	union {
+			u64		fixed_cntr_mask64;
+			unsigned long	fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+	};
 	int		cntval_bits;
 	u64		cntval_mask;
 	union {
@@ -852,7 +877,7 @@ struct x86_pmu {
 			pebs_ept		:1;
 	int		pebs_record_size;
 	int		pebs_buffer_size;
-	int		max_pebs_events;
+	u64		pebs_events_mask;
 	void		(*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
 	struct event_constraint *pebs_constraints;
 	void		(*pebs_aliases)(struct perf_event *event);
@@ -1120,13 +1145,19 @@ static inline unsigned int x86_pmu_event_addr(int index)
 				  x86_pmu.addr_offset(index, false) : index);
 }
 
+static inline unsigned int x86_pmu_fixed_ctr_addr(int index)
+{
+	return x86_pmu.fixedctr + (x86_pmu.addr_offset ?
+				   x86_pmu.addr_offset(index, false) : index);
+}
+
 static inline int x86_pmu_rdpmc_index(int index)
 {
 	return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
 }
 
-bool check_hw_exists(struct pmu *pmu, int num_counters,
-		     int num_counters_fixed);
+bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
+		     unsigned long *fixed_cntr_mask);
 
 int x86_add_exclusive(unsigned int what);
 
@@ -1197,8 +1228,32 @@ void x86_pmu_enable_event(struct perf_event *event);
 
 int x86_pmu_handle_irq(struct pt_regs *regs);
 
-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
-			  u64 intel_ctrl);
+void x86_pmu_show_pmu_cap(struct pmu *pmu);
+
+static inline int x86_pmu_num_counters(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, cntr_mask64));
+}
+
+static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
+{
+	return hweight64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
+{
+	return fls64(hybrid(pmu, fixed_cntr_mask64));
+}
+
+static inline u64 x86_pmu_get_event_config(struct perf_event *event)
+{
+	return event->attr.config & hybrid(event->pmu, config_mask);
+}
 
 extern struct event_constraint emptyconstraint;
 
@@ -1517,9 +1572,11 @@ void intel_pmu_disable_bts(void);
 
 int intel_pmu_drain_bts_buffer(void);
 
-u64 adl_latency_data_small(struct perf_event *event, u64 status);
+u64 grt_latency_data(struct perf_event *event, u64 status);
 
-u64 mtl_latency_data_small(struct perf_event *event, u64 status);
+u64 cmt_latency_data(struct perf_event *event, u64 status);
+
+u64 lnl_latency_data(struct perf_event *event, u64 status);
 
 extern struct event_constraint intel_core2_pebs_event_constraints[];
 
@@ -1551,6 +1608,8 @@ extern struct event_constraint intel_icl_pebs_event_constraints[];
 
 extern struct event_constraint intel_glc_pebs_event_constraints[];
 
+extern struct event_constraint intel_lnc_pebs_event_constraints[];
+
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
 void intel_pmu_pebs_add(struct perf_event *event);
@@ -1640,6 +1699,8 @@ void intel_pmu_pebs_data_source_mtl(void);
 
 void intel_pmu_pebs_data_source_cmt(void);
 
+void intel_pmu_pebs_data_source_lnl(void);
+
 int intel_pmu_setup_lbr_filter(struct perf_event *event);
 
 void intel_pt_interrupt(void);
@@ -1661,6 +1722,17 @@ static inline int is_ht_workaround_enabled(void)
 	return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
 }
 
+static inline u64 intel_pmu_pebs_mask(u64 cntr_mask)
+{
+	return MAX_PEBS_EVENTS_MASK & cntr_mask;
+}
+
+static inline int intel_pmu_max_num_pebs(struct pmu *pmu)
+{
+	static_assert(MAX_PEBS_EVENTS == 32);
+	return fls((u32)hybrid(pmu, pebs_events_mask));
+}
+
 #else /* CONFIG_CPU_SUP_INTEL */
 
 static inline void reserve_ds_buffers(void)

arch/x86/events/zhaoxin/core.c

@@ -530,13 +530,13 @@ __init int zhaoxin_pmu_init(void)
 	pr_info("Version check pass!\n");
 
 	x86_pmu.version			= version;
-	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntr_mask64		= GENMASK_ULL(eax.split.num_counters - 1, 0);
 	x86_pmu.cntval_bits		= eax.split.bit_width;
 	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
 	x86_pmu.events_maskl		= ebx.full;
 	x86_pmu.events_mask_len		= eax.split.mask_length;
 
-	x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+	x86_pmu.fixed_cntr_mask64	= GENMASK_ULL(edx.split.num_counters_fixed - 1, 0);
 	x86_add_quirk(zhaoxin_arch_events_quirk);
 
 	switch (boot_cpu_data.x86) {
@@ -604,13 +604,13 @@ __init int zhaoxin_pmu_init(void)
 		return -ENODEV;
 	}
 
-	x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
-	x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+	x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+	x86_pmu.intel_ctrl |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
 
 	if (x86_pmu.event_constraints) {
 		for_each_event_constraint(c, x86_pmu.event_constraints) {
-			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
-			c->weight += x86_pmu.num_counters;
+			c->idxmsk64 |= x86_pmu.cntr_mask64;
+			c->weight += x86_pmu_num_counters(NULL);
 		}
 	}
 

arch/x86/include/asm/intel_ds.h

@@ -9,6 +9,7 @@
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS_FMT4	8
 #define MAX_PEBS_EVENTS		32
+#define MAX_PEBS_EVENTS_MASK	GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0)
 #define MAX_FIXED_PEBS_EVENTS	16
 
 /*

arch/x86/include/asm/msr-index.h

@@ -566,6 +566,12 @@
 #define MSR_RELOAD_PMC0			0x000014c1
 #define MSR_RELOAD_FIXED_CTR0		0x00001309
 
+/* V6 PMON MSR range */
+#define MSR_IA32_PMC_V6_GP0_CTR		0x1900
+#define MSR_IA32_PMC_V6_GP0_CFG_A	0x1901
+#define MSR_IA32_PMC_V6_FX0_CTR		0x1980
+#define MSR_IA32_PMC_V6_STEP		4
+
 /* KeyID partitioning between MKTME and TDX */
 #define MSR_IA32_MKTME_KEYID_PARTITIONING	0x00000087
 

arch/x86/include/asm/perf_event.h

@@ -32,6 +32,8 @@
 #define ARCH_PERFMON_EVENTSEL_INV			(1ULL << 23)
 #define ARCH_PERFMON_EVENTSEL_CMASK			0xFF000000ULL
 #define ARCH_PERFMON_EVENTSEL_BR_CNTR			(1ULL << 35)
+#define ARCH_PERFMON_EVENTSEL_EQ			(1ULL << 36)
+#define ARCH_PERFMON_EVENTSEL_UMASK2			(0xFFULL << 40)
 
 #define INTEL_FIXED_BITS_MASK				0xFULL
 #define INTEL_FIXED_BITS_STRIDE			4
@@ -185,6 +187,8 @@ union cpuid10_edx {
  * detection/enumeration details:
  */
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
+#define ARCH_PERFMON_EXT_UMASK2			0x1
+#define ARCH_PERFMON_EXT_EQ			0x2
 #define ARCH_PERFMON_NUM_COUNTER_LEAF_BIT	0x1
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
 
@@ -307,6 +311,10 @@ struct x86_pmu_capability {
 #define INTEL_PMC_IDX_FIXED_SLOTS	(INTEL_PMC_IDX_FIXED + 3)
 #define INTEL_PMC_MSK_FIXED_SLOTS	(1ULL << INTEL_PMC_IDX_FIXED_SLOTS)
 
+/* TOPDOWN_BAD_SPECULATION.ALL: fixed counter 4 (Atom only) */
+/* TOPDOWN_FE_BOUND.ALL: fixed counter 5 (Atom only) */
+/* TOPDOWN_RETIRING.ALL: fixed counter 6 (Atom only) */
+
 static inline bool use_fixed_pseudo_encoding(u64 code)
 {
 	return !(code & 0xff);

include/linux/perf_event.h

@@ -781,11 +781,12 @@ struct perf_event {
 	unsigned int			pending_wakeup;
 	unsigned int			pending_kill;
 	unsigned int			pending_disable;
-	unsigned int			pending_sigtrap;
 	unsigned long			pending_addr;	/* SIGTRAP */
 	struct irq_work			pending_irq;
+	struct irq_work			pending_disable_irq;
 	struct callback_head		pending_task;
 	unsigned int			pending_work;
+	struct rcuwait			pending_work_wait;
 
 	atomic_t			event_limit;
 
@@ -962,7 +963,7 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 
 	/*
-	 * Sum (event->pending_sigtrap + event->pending_work)
+	 * Sum (event->pending_work + event->pending_work)
 	 *
 	 * The SIGTRAP is targeted at ctx->task, as such it won't do changing
 	 * that until the signal is delivered.
@@ -970,12 +971,6 @@ struct perf_event_context {
 	local_t				nr_pending;
 };
 
-/*
- * Number of contexts where an event can trigger:
- *	task, softirq, hardirq, nmi.
- */
-#define PERF_NR_CONTEXTS	4
-
 struct perf_cpu_pmu_context {
 	struct perf_event_pmu_context	epc;
 	struct perf_event_pmu_context	*task_epc;

include/linux/sched.h

@@ -734,6 +734,12 @@ enum perf_event_task_context {
 	perf_nr_task_contexts,
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ *      task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
 struct wake_q_node {
 	struct wake_q_node *next;
 };
@@ -1256,6 +1262,7 @@ struct task_struct {
 	unsigned int			futex_state;
 #endif
 #ifdef CONFIG_PERF_EVENTS
+	u8				perf_recursion[PERF_NR_CONTEXTS];
 	struct perf_event_context	*perf_event_ctxp;
 	struct mutex			perf_event_mutex;
 	struct list_head		perf_event_list;

include/linux/task_work.h

@@ -18,6 +18,7 @@ enum task_work_notify_mode {
 	TWA_RESUME,
 	TWA_SIGNAL,
 	TWA_SIGNAL_NO_IPI,
+	TWA_NMI_CURRENT,
 };
 
 static inline bool task_work_pending(struct task_struct *task)
@@ -30,7 +31,8 @@ int task_work_add(struct task_struct *task, struct callback_head *twork,
 
 struct callback_head *task_work_cancel_match(struct task_struct *task,
 	bool (*match)(struct callback_head *, void *data), void *data);
-struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
+struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t);
+bool task_work_cancel(struct task_struct *task, struct callback_head *cb);
 void task_work_run(void);
 
 static inline void exit_task_work(struct task_struct *task)

include/uapi/linux/perf_event.h

@@ -1349,12 +1349,14 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_L2_MHB	0x05 /* L2 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
+/* 0x7 available */
 #define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / L1 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
 #define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
 #define PERF_MEM_LVLNUM_NA	0x0f /* N/A */

kernel/events/callchain.c

@@ -29,7 +29,7 @@ static inline size_t perf_callchain_entry__sizeof(void)
 				 sysctl_perf_event_max_contexts_per_stack));
 }
 
-static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]);
+static DEFINE_PER_CPU(u8, callchain_recursion[PERF_NR_CONTEXTS]);
 static atomic_t nr_callchain_events;
 static DEFINE_MUTEX(callchain_mutex);
 static struct callchain_cpus_entries *callchain_cpus_entries;

kernel/events/core.c

@@ -2283,21 +2283,6 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx)
 		state = PERF_EVENT_STATE_OFF;
 	}
 
-	if (event->pending_sigtrap) {
-		bool dec = true;
-
-		event->pending_sigtrap = 0;
-		if (state != PERF_EVENT_STATE_OFF &&
-		    !event->pending_work) {
-			event->pending_work = 1;
-			dec = false;
-			WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
-			task_work_add(current, &event->pending_task, TWA_RESUME);
-		}
-		if (dec)
-			local_dec(&event->ctx->nr_pending);
-	}
-
 	perf_event_set_state(event, state);
 
 	if (!is_software_event(event))
@@ -2466,7 +2451,7 @@ static void __perf_event_disable(struct perf_event *event,
  * hold the top-level event's child_mutex, so any descendant that
  * goes to exit will block in perf_event_exit_event().
  *
- * When called from perf_pending_irq it's OK because event->ctx
+ * When called from perf_pending_disable it's OK because event->ctx
  * is the current context on this CPU and preemption is disabled,
  * hence we can't get into perf_event_task_sched_out for this context.
  */
@@ -2506,7 +2491,7 @@ EXPORT_SYMBOL_GPL(perf_event_disable);
 void perf_event_disable_inatomic(struct perf_event *event)
 {
 	event->pending_disable = 1;
-	irq_work_queue(&event->pending_irq);
+	irq_work_queue(&event->pending_disable_irq);
 }
 
 #define MAX_INTERRUPTS (~0ULL)
@@ -5206,9 +5191,35 @@ static bool exclusive_event_installable(struct perf_event *event,
 static void perf_addr_filters_splice(struct perf_event *event,
 				       struct list_head *head);
 
+static void perf_pending_task_sync(struct perf_event *event)
+{
+	struct callback_head *head = &event->pending_task;
+
+	if (!event->pending_work)
+		return;
+	/*
+	 * If the task is queued to the current task's queue, we
+	 * obviously can't wait for it to complete. Simply cancel it.
+	 */
+	if (task_work_cancel(current, head)) {
+		event->pending_work = 0;
+		local_dec(&event->ctx->nr_pending);
+		return;
+	}
+
+	/*
+	 * All accesses related to the event are within the same RCU section in
+	 * perf_pending_task(). The RCU grace period before the event is freed
+	 * will make sure all those accesses are complete by then.
+	 */
+	rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
+}
+
 static void _free_event(struct perf_event *event)
 {
 	irq_work_sync(&event->pending_irq);
+	irq_work_sync(&event->pending_disable_irq);
+	perf_pending_task_sync(event);
 
 	unaccount_event(event);
 
@@ -6509,6 +6520,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
 			return -EINVAL;
 
 		nr_pages = vma_size / PAGE_SIZE;
+		if (nr_pages > INT_MAX)
+			return -ENOMEM;
 
 		mutex_lock(&event->mmap_mutex);
 		ret = -EINVAL;
@@ -6750,7 +6763,7 @@ static void perf_sigtrap(struct perf_event *event)
 /*
  * Deliver the pending work in-event-context or follow the context.
  */
-static void __perf_pending_irq(struct perf_event *event)
+static void __perf_pending_disable(struct perf_event *event)
 {
 	int cpu = READ_ONCE(event->oncpu);
 
@@ -6765,11 +6778,6 @@ static void __perf_pending_irq(struct perf_event *event)
 	 * Yay, we hit home and are in the context of the event.
 	 */
 	if (cpu == smp_processor_id()) {
-		if (event->pending_sigtrap) {
-			event->pending_sigtrap = 0;
-			perf_sigtrap(event);
-			local_dec(&event->ctx->nr_pending);
-		}
 		if (event->pending_disable) {
 			event->pending_disable = 0;
 			perf_event_disable_local(event);
@@ -6793,11 +6801,26 @@ static void __perf_pending_irq(struct perf_event *event)
 	 *				  irq_work_queue(); // FAILS
 	 *
 	 *  irq_work_run()
-	 *    perf_pending_irq()
+	 *    perf_pending_disable()
 	 *
 	 * But the event runs on CPU-B and wants disabling there.
 	 */
-	irq_work_queue_on(&event->pending_irq, cpu);
+	irq_work_queue_on(&event->pending_disable_irq, cpu);
+}
+
+static void perf_pending_disable(struct irq_work *entry)
+{
+	struct perf_event *event = container_of(entry, struct perf_event, pending_disable_irq);
+	int rctx;
+
+	/*
+	 * If we 'fail' here, that's OK, it means recursion is already disabled
+	 * and we won't recurse 'further'.
+	 */
+	rctx = perf_swevent_get_recursion_context();
+	__perf_pending_disable(event);
+	if (rctx >= 0)
+		perf_swevent_put_recursion_context(rctx);
 }
 
 static void perf_pending_irq(struct irq_work *entry)
@@ -6820,8 +6843,6 @@ static void perf_pending_irq(struct irq_work *entry)
 		perf_event_wakeup(event);
 	}
 
-	__perf_pending_irq(event);
-
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
 }
@@ -6831,24 +6852,28 @@ static void perf_pending_task(struct callback_head *head)
 	struct perf_event *event = container_of(head, struct perf_event, pending_task);
 	int rctx;
 
+	/*
+	 * All accesses to the event must belong to the same implicit RCU read-side
+	 * critical section as the ->pending_work reset. See comment in
+	 * perf_pending_task_sync().
+	 */
+	rcu_read_lock();
 	/*
 	 * If we 'fail' here, that's OK, it means recursion is already disabled
 	 * and we won't recurse 'further'.
 	 */
-	preempt_disable_notrace();
 	rctx = perf_swevent_get_recursion_context();
 
 	if (event->pending_work) {
 		event->pending_work = 0;
 		perf_sigtrap(event);
 		local_dec(&event->ctx->nr_pending);
+		rcuwait_wake_up(&event->pending_work_wait);
 	}
+	rcu_read_unlock();
 
 	if (rctx >= 0)
 		perf_swevent_put_recursion_context(rctx);
-	preempt_enable_notrace();
-
-	put_event(event);
 }
 
 #ifdef CONFIG_GUEST_PERF_EVENTS
@@ -9706,16 +9731,26 @@ static int __perf_event_overflow(struct perf_event *event,
 		 */
 		bool valid_sample = sample_is_allowed(event, regs);
 		unsigned int pending_id = 1;
+		enum task_work_notify_mode notify_mode;
 
 		if (regs)
 			pending_id = hash32_ptr((void *)instruction_pointer(regs)) ?: 1;
-		if (!event->pending_sigtrap) {
-			event->pending_sigtrap = pending_id;
+
+		notify_mode = in_nmi() ? TWA_NMI_CURRENT : TWA_RESUME;
+
+		if (!event->pending_work &&
+		    !task_work_add(current, &event->pending_task, notify_mode)) {
+			event->pending_work = pending_id;
 			local_inc(&event->ctx->nr_pending);
+
+			event->pending_addr = 0;
+			if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR))
+				event->pending_addr = data->addr;
+
 		} else if (event->attr.exclude_kernel && valid_sample) {
 			/*
 			 * Should not be able to return to user space without
-			 * consuming pending_sigtrap; with exceptions:
+			 * consuming pending_work; with exceptions:
 			 *
 			 *  1. Where !exclude_kernel, events can overflow again
 			 *     in the kernel without returning to user space.
@@ -9725,13 +9760,8 @@ static int __perf_event_overflow(struct perf_event *event,
 			 *     To approximate progress (with false negatives),
 			 *     check 32-bit hash of the current IP.
 			 */
-			WARN_ON_ONCE(event->pending_sigtrap != pending_id);
+			WARN_ON_ONCE(event->pending_work != pending_id);
 		}
-
-		event->pending_addr = 0;
-		if (valid_sample && (data->sample_flags & PERF_SAMPLE_ADDR))
-			event->pending_addr = data->addr;
-		irq_work_queue(&event->pending_irq);
 	}
 
 	READ_ONCE(event->overflow_handler)(event, data, regs);
@@ -9759,11 +9789,7 @@ struct swevent_htable {
 	struct swevent_hlist		*swevent_hlist;
 	struct mutex			hlist_mutex;
 	int				hlist_refcount;
-
-	/* Recursion avoidance in each contexts */
-	int				recursion[PERF_NR_CONTEXTS];
 };
-
 static DEFINE_PER_CPU(struct swevent_htable, swevent_htable);
 
 /*
@@ -9961,17 +9987,13 @@ DEFINE_PER_CPU(struct pt_regs, __perf_regs[4]);
 
 int perf_swevent_get_recursion_context(void)
 {
-	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
-
-	return get_recursion_context(swhash->recursion);
+	return get_recursion_context(current->perf_recursion);
 }
 EXPORT_SYMBOL_GPL(perf_swevent_get_recursion_context);
 
 void perf_swevent_put_recursion_context(int rctx)
 {
-	struct swevent_htable *swhash = this_cpu_ptr(&swevent_htable);
-
-	put_recursion_context(swhash->recursion, rctx);
+	put_recursion_context(current->perf_recursion, rctx);
 }
 
 void ___perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
@@ -11961,7 +11983,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
 
 	init_waitqueue_head(&event->waitq);
 	init_irq_work(&event->pending_irq, perf_pending_irq);
+	event->pending_disable_irq = IRQ_WORK_INIT_HARD(perf_pending_disable);
 	init_task_work(&event->pending_task, perf_pending_task);
+	rcuwait_init(&event->pending_work_wait);
 
 	mutex_init(&event->mmap_mutex);
 	raw_spin_lock_init(&event->addr_filters.lock);
@@ -13637,6 +13661,7 @@ int perf_event_init_task(struct task_struct *child, u64 clone_flags)
 {
 	int ret;
 
+	memset(child->perf_recursion, 0, sizeof(child->perf_recursion));
 	child->perf_event_ctxp = NULL;
 	mutex_init(&child->perf_event_mutex);
 	INIT_LIST_HEAD(&child->perf_event_list);

kernel/events/internal.h

@@ -128,7 +128,7 @@ static inline unsigned long perf_data_size(struct perf_buffer *rb)
 
 static inline unsigned long perf_aux_size(struct perf_buffer *rb)
 {
-	return rb->aux_nr_pages << PAGE_SHIFT;
+	return (unsigned long)rb->aux_nr_pages << PAGE_SHIFT;
 }
 
 #define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...)	\
@@ -208,7 +208,7 @@ arch_perf_out_copy_user(void *dst, const void *src, unsigned long n)
 
 DEFINE_OUTPUT_COPY(__output_copy_user, arch_perf_out_copy_user)
 
-static inline int get_recursion_context(int *recursion)
+static inline int get_recursion_context(u8 *recursion)
 {
 	unsigned char rctx = interrupt_context_level();
 
@@ -221,7 +221,7 @@ static inline int get_recursion_context(int *recursion)
 	return rctx;
 }
 
-static inline void put_recursion_context(int *recursion, int rctx)
+static inline void put_recursion_context(u8 *recursion, unsigned char rctx)
 {
 	barrier();
 	recursion[rctx]--;

kernel/events/ring_buffer.c

@@ -682,13 +682,18 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
 	if (!has_aux(event))
 		return -EOPNOTSUPP;
 
+	if (nr_pages <= 0)
+		return -EINVAL;
+
 	if (!overwrite) {
 		/*
 		 * Watermark defaults to half the buffer, and so does the
 		 * max_order, to aid PMU drivers in double buffering.
 		 */
 		if (!watermark)
-			watermark = nr_pages << (PAGE_SHIFT - 1);
+			watermark = min_t(unsigned long,
+					  U32_MAX,
+					  (unsigned long)nr_pages << (PAGE_SHIFT - 1));
 
 		/*
 		 * Use aux_watermark as the basis for chunking to

kernel/irq/manage.c

@@ -1337,7 +1337,7 @@ static int irq_thread(void *data)
 	 * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
 	 * oneshot mask bit can be set.
 	 */
-	task_work_cancel(current, irq_thread_dtor);
+	task_work_cancel_func(current, irq_thread_dtor);
 	return 0;
 }
 

kernel/task_work.c

 // SPDX-License-Identifier: GPL-2.0
+#include <linux/irq_work.h>
 #include <linux/spinlock.h>
 #include <linux/task_work.h>
 #include <linux/resume_user_mode.h>
 
 static struct callback_head work_exited; /* all we need is ->next == NULL */
 
+static void task_work_set_notify_irq(struct irq_work *entry)
+{
+	test_and_set_tsk_thread_flag(current, TIF_NOTIFY_RESUME);
+}
+static DEFINE_PER_CPU(struct irq_work, irq_work_NMI_resume) =
+	IRQ_WORK_INIT_HARD(task_work_set_notify_irq);
+
 /**
  * task_work_add - ask the @task to execute @work->func()
  * @task: the task which should run the callback
@@ -12,7 +20,7 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * @notify: how to notify the targeted task
  *
  * Queue @work for task_work_run() below and notify the @task if @notify
- * is @TWA_RESUME, @TWA_SIGNAL, or @TWA_SIGNAL_NO_IPI.
+ * is @TWA_RESUME, @TWA_SIGNAL, @TWA_SIGNAL_NO_IPI or @TWA_NMI_CURRENT.
  *
  * @TWA_SIGNAL works like signals, in that the it will interrupt the targeted
  * task and run the task_work, regardless of whether the task is currently
@@ -24,6 +32,8 @@ static struct callback_head work_exited; /* all we need is ->next == NULL */
  * kernel anyway.
  * @TWA_RESUME work is run only when the task exits the kernel and returns to
  * user mode, or before entering guest mode.
+ * @TWA_NMI_CURRENT works like @TWA_RESUME, except it can only be used for the
+ * current @task and if the current context is NMI.
  *
  * Fails if the @task is exiting/exited and thus it can't process this @work.
  * Otherwise @work->func() will be called when the @task goes through one of
@@ -44,8 +54,13 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 {
 	struct callback_head *head;
 
-	/* record the work call stack in order to print it in KASAN reports */
-	kasan_record_aux_stack(work);
+	if (notify == TWA_NMI_CURRENT) {
+		if (WARN_ON_ONCE(task != current))
+			return -EINVAL;
+	} else {
+		/* record the work call stack in order to print it in KASAN reports */
+		kasan_record_aux_stack(work);
+	}
 
 	head = READ_ONCE(task->task_works);
 	do {
@@ -66,6 +81,9 @@ int task_work_add(struct task_struct *task, struct callback_head *work,
 	case TWA_SIGNAL_NO_IPI:
 		__set_notify_signal(task);
 		break;
+	case TWA_NMI_CURRENT:
+		irq_work_queue(this_cpu_ptr(&irq_work_NMI_resume));
+		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
@@ -120,9 +138,9 @@ static bool task_work_func_match(struct callback_head *cb, void *data)
 }
 
 /**
- * task_work_cancel - cancel a pending work added by task_work_add()
- * @task: the task which should execute the work
- * @func: identifies the work to remove
+ * task_work_cancel_func - cancel a pending work matching a function added by task_work_add()
+ * @task: the task which should execute the func's work
+ * @func: identifies the func to match with a work to remove
  *
  * Find the last queued pending work with ->func == @func and remove
  * it from queue.
@@ -131,11 +149,35 @@ static bool task_work_func_match(struct callback_head *cb, void *data)
  * The found work or NULL if not found.
  */
 struct callback_head *
-task_work_cancel(struct task_struct *task, task_work_func_t func)
+task_work_cancel_func(struct task_struct *task, task_work_func_t func)
 {
 	return task_work_cancel_match(task, task_work_func_match, func);
 }
 
+static bool task_work_match(struct callback_head *cb, void *data)
+{
+	return cb == data;
+}
+
+/**
+ * task_work_cancel - cancel a pending work added by task_work_add()
+ * @task: the task which should execute the work
+ * @cb: the callback to remove if queued
+ *
+ * Remove a callback from a task's queue if queued.
+ *
+ * RETURNS:
+ * True if the callback was queued and got cancelled, false otherwise.
+ */
+bool task_work_cancel(struct task_struct *task, struct callback_head *cb)
+{
+	struct callback_head *ret;
+
+	ret = task_work_cancel_match(task, task_work_match, cb);
+
+	return ret == cb;
+}
+
 /**
  * task_work_run - execute the works added by task_work_add()
  *
@@ -168,7 +210,7 @@ void task_work_run(void)
 		if (!work)
 			break;
 		/*
-		 * Synchronize with task_work_cancel(). It can not remove
+		 * Synchronize with task_work_cancel_match(). It can not remove
 		 * the first entry == work, cmpxchg(task_works) must fail.
 		 * But it can remove another entry from the ->next list.
 		 */

security/keys/keyctl.c

@@ -1694,7 +1694,7 @@ long keyctl_session_to_parent(void)
 		goto unlock;
 
 	/* cancel an already pending keyring replacement */
-	oldwork = task_work_cancel(parent, key_change_session_keyring);
+	oldwork = task_work_cancel_func(parent, key_change_session_keyring);
 
 	/* the replacement session keyring is applied just prior to userspace
 	 * restarting */