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
  ...

1 files changed, 23 insertions, 13 deletions

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 4ccb8fa483e6..0bfde2ea5cb8 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/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;
 }