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
  ...

Author: torvalds

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;
 }