Merge tag 'perf-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance event updates from Ingo Molnar:
 - Add AMD Unified Memory Controller (UMC) events introduced with Zen 4
 - Simplify & clean up the uncore management code
 - Fall back from RDPMC to RDMSR on certain uncore PMUs
 - Improve per-package and cstate event reading
 - Extend the Intel ref-cycles event to GP counters
 - Fix Intel MTL event constraints
 - Improve the Intel hybrid CPU handling code
 - Micro-optimize the RAPL code
 - Optimize perf_cgroup_switch()
 - Improve large AUX area error handling
 - Misc fixes and cleanups

* tag 'perf-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (26 commits)
  perf/x86/amd/uncore: Pass through error code for initialization failures, instead of -ENODEV
  perf/x86/amd/uncore: Fix uninitialized return value in amd_uncore_init()
  x86/cpu: Fix the AMD Fam 17h, Fam 19h, Zen2 and Zen4 MSR enumerations
  perf: Optimize perf_cgroup_switch()
  perf/x86/amd/uncore: Add memory controller support
  perf/x86/amd/uncore: Add group exclusivity
  perf/x86/amd/uncore: Use rdmsr if rdpmc is unavailable
  perf/x86/amd/uncore: Move discovery and registration
  perf/x86/amd/uncore: Refactor uncore management
  perf/core: Allow reading package events from perf_event_read_local
  perf/x86/cstate: Allow reading the package statistics from local CPU
  perf/x86/intel/pt: Fix kernel-doc comments
  perf/x86/rapl: Annotate 'struct rapl_pmus' with __counted_by
  perf/core: Rename perf_proc_update_handler() -> perf_event_max_sample_rate_handler(), for readability
  perf/x86/rapl: Fix "Using plain integer as NULL pointer" Sparse warning
  perf/x86/rapl: Use local64_try_cmpxchg in rapl_event_update()
  perf/x86/rapl: Stop doing cpu_relax() in the local64_cmpxchg() loop in rapl_event_update()
  perf/core: Bail out early if the request AUX area is out of bound
  perf/x86/intel: Extend the ref-cycles event to GP counters
  perf/x86/intel: Fix broken fixed event constraints extension
  ...

10 files changed, 1007 insertions, 627 deletions

diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 83f15fe411b3..4429eac00185 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -26,57 +26,66 @@
 #define RDPMC_BASE_LLC		10
 
 #define COUNTER_SHIFT		16
+#define UNCORE_NAME_LEN		16
+#define UNCORE_GROUP_MAX	256
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"amd_uncore: " fmt
 
 static int pmu_version;
-static int num_counters_llc;
-static int num_counters_nb;
-static bool l3_mask;
 
-static HLIST_HEAD(uncore_unused_list);
-
-struct amd_uncore {
-	int id;
+struct amd_uncore_ctx {
 	int refcnt;
 	int cpu;
+	struct perf_event **events;
+	struct hlist_node node;
+};
+
+struct amd_uncore_pmu {
+	char name[UNCORE_NAME_LEN];
 	int num_counters;
 	int rdpmc_base;
 	u32 msr_base;
-	cpumask_t *active_mask;
-	struct pmu *pmu;
-	struct perf_event **events;
-	struct hlist_node node;
+	int group;
+	cpumask_t active_mask;
+	struct pmu pmu;
+	struct amd_uncore_ctx * __percpu *ctx;
 };
 
-static struct amd_uncore * __percpu *amd_uncore_nb;
-static struct amd_uncore * __percpu *amd_uncore_llc;
+enum {
+	UNCORE_TYPE_DF,
+	UNCORE_TYPE_L3,
+	UNCORE_TYPE_UMC,
 
-static struct pmu amd_nb_pmu;
-static struct pmu amd_llc_pmu;
+	UNCORE_TYPE_MAX
+};
 
-static cpumask_t amd_nb_active_mask;
-static cpumask_t amd_llc_active_mask;
+union amd_uncore_info {
+	struct {
+		u64	aux_data:32;	/* auxiliary data */
+		u64	num_pmcs:8;	/* number of counters */
+		u64	gid:8;		/* group id */
+		u64	cid:8;		/* context id */
+	} split;
+	u64		full;
+};
 
-static bool is_nb_event(struct perf_event *event)
-{
-	return event->pmu->type == amd_nb_pmu.type;
-}
+struct amd_uncore {
+	union amd_uncore_info * __percpu info;
+	struct amd_uncore_pmu *pmus;
+	unsigned int num_pmus;
+	bool init_done;
+	void (*scan)(struct amd_uncore *uncore, unsigned int cpu);
+	int  (*init)(struct amd_uncore *uncore, unsigned int cpu);
+	void (*move)(struct amd_uncore *uncore, unsigned int cpu);
+	void (*free)(struct amd_uncore *uncore, unsigned int cpu);
+};
 
-static bool is_llc_event(struct perf_event *event)
-{
-	return event->pmu->type == amd_llc_pmu.type;
-}
+static struct amd_uncore uncores[UNCORE_TYPE_MAX];
 
-static struct amd_uncore *event_to_amd_uncore(struct perf_event *event)
+static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
 {
-	if (is_nb_event(event) && amd_uncore_nb)
-		return *per_cpu_ptr(amd_uncore_nb, event->cpu);
-	else if (is_llc_event(event) && amd_uncore_llc)
-		return *per_cpu_ptr(amd_uncore_llc, event->cpu);
-
-	return NULL;
+	return container_of(event->pmu, struct amd_uncore_pmu, pmu);
 }
 
 static void amd_uncore_read(struct perf_event *event)
@@ -91,7 +100,16 @@ static void amd_uncore_read(struct perf_event *event)
 	 */
 
 	prev = local64_read(&hwc->prev_count);
-	rdpmcl(hwc->event_base_rdpmc, new);
+
+	/*
+	 * Some uncore PMUs do not have RDPMC assignments. In such cases,
+	 * read counts directly from the corresponding PERF_CTR.
+	 */
+	if (hwc->event_base_rdpmc < 0)
+		rdmsrl(hwc->event_base, new);
+	else
+		rdpmcl(hwc->event_base_rdpmc, new);
+
 	local64_set(&hwc->prev_count, new);
 	delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
 	delta >>= COUNTER_SHIFT;
@@ -118,7 +136,7 @@ static void amd_uncore_stop(struct perf_event *event, int flags)
 	hwc->state |= PERF_HES_STOPPED;
 
 	if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
-		amd_uncore_read(event);
+		event->pmu->read(event);
 		hwc->state |= PERF_HES_UPTODATE;
 	}
 }
@@ -126,15 +144,16 @@ static void amd_uncore_stop(struct perf_event *event, int flags)
 static int amd_uncore_add(struct perf_event *event, int flags)
 {
 	int i;
-	struct amd_uncore *uncore = event_to_amd_uncore(event);
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
 	/* are we already assigned? */
-	if (hwc->idx != -1 && uncore->events[hwc->idx] == event)
+	if (hwc->idx != -1 && ctx->events[hwc->idx] == event)
 		goto out;
 
-	for (i = 0; i < uncore->num_counters; i++) {
-		if (uncore->events[i] == event) {
+	for (i = 0; i < pmu->num_counters; i++) {
+		if (ctx->events[i] == event) {
 			hwc->idx = i;
 			goto out;
 		}
@@ -142,8 +161,8 @@ 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 < uncore->num_counters; i++) {
-		if (cmpxchg(&uncore->events[i], NULL, event) == NULL) {
+	for (i = 0; i < pmu->num_counters; i++) {
+		if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
 			hwc->idx = i;
 			break;
 		}
@@ -153,23 +172,16 @@ out:
 	if (hwc->idx == -1)
 		return -EBUSY;
 
-	hwc->config_base = uncore->msr_base + (2 * hwc->idx);
-	hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx);
-	hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx;
+	hwc->config_base = pmu->msr_base + (2 * hwc->idx);
+	hwc->event_base = pmu->msr_base + 1 + (2 * hwc->idx);
+	hwc->event_base_rdpmc = pmu->rdpmc_base + hwc->idx;
 	hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
 
-	/*
-	 * The first four DF counters are accessible via RDPMC index 6 to 9
-	 * followed by the L3 counters from index 10 to 15. For processors
-	 * with more than four DF counters, the DF RDPMC assignments become
-	 * discontiguous as the additional counters are accessible starting
-	 * from index 16.
-	 */
-	if (is_nb_event(event) && hwc->idx >= NUM_COUNTERS_NB)
-		hwc->event_base_rdpmc += NUM_COUNTERS_L3;
+	if (pmu->rdpmc_base < 0)
+		hwc->event_base_rdpmc = -1;
 
 	if (flags & PERF_EF_START)
-		amd_uncore_start(event, PERF_EF_RELOAD);
+		event->pmu->start(event, PERF_EF_RELOAD);
 
 	return 0;
 }
@@ -177,55 +189,36 @@ out:
 static void amd_uncore_del(struct perf_event *event, int flags)
 {
 	int i;
-	struct amd_uncore *uncore = event_to_amd_uncore(event);
+	struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+	struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
 	struct hw_perf_event *hwc = &event->hw;
 
-	amd_uncore_stop(event, PERF_EF_UPDATE);
+	event->pmu->stop(event, PERF_EF_UPDATE);
 
-	for (i = 0; i < uncore->num_counters; i++) {
-		if (cmpxchg(&uncore->events[i], event, NULL) == event)
+	for (i = 0; i < pmu->num_counters; i++) {
+		if (cmpxchg(&ctx->events[i], event, NULL) == event)
 			break;
 	}
 
 	hwc->idx = -1;
 }
 
-/*
- * Return a full thread and slice mask unless user
- * has provided them
- */
-static u64 l3_thread_slice_mask(u64 config)
-{
-	if (boot_cpu_data.x86 <= 0x18)
-		return ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) |
-		       ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK);
-
-	/*
-	 * If the user doesn't specify a threadmask, they're not trying to
-	 * count core 0, so we enable all cores & threads.
-	 * We'll also assume that they want to count slice 0 if they specify
-	 * a threadmask and leave sliceid and enallslices unpopulated.
-	 */
-	if (!(config & AMD64_L3_F19H_THREAD_MASK))
-		return AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES |
-		       AMD64_L3_EN_ALL_CORES;
-
-	return config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK |
-			 AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES |
-			 AMD64_L3_COREID_MASK);
-}
-
 static int amd_uncore_event_init(struct perf_event *event)
 {
-	struct amd_uncore *uncore;
+	struct amd_uncore_pmu *pmu;
+	struct amd_uncore_ctx *ctx;
 	struct hw_perf_event *hwc = &event->hw;
-	u64 event_mask = AMD64_RAW_EVENT_MASK_NB;
 
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	if (pmu_version >= 2 && is_nb_event(event))
-		event_mask = AMD64_PERFMON_V2_RAW_EVENT_MASK_NB;
+	if (event->cpu < 0)
+		return -EINVAL;
+
+	pmu = event_to_amd_uncore_pmu(event);
+	ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
+	if (!ctx)
+		return -ENODEV;
 
 	/*
 	 * NB and Last level cache counters (MSRs) are shared across all cores
@@ -235,28 +228,14 @@ static int amd_uncore_event_init(struct perf_event *event)
 	 * out. So we do not support sampling and per-thread events via
 	 * CAP_NO_INTERRUPT, and we do not enable counter overflow interrupts:
 	 */
-	hwc->config = event->attr.config & event_mask;
+	hwc->config = event->attr.config;
 	hwc->idx = -1;
 
-	if (event->cpu < 0)
-		return -EINVAL;
-
-	/*
-	 * SliceMask and ThreadMask need to be set for certain L3 events.
-	 * For other events, the two fields do not affect the count.
-	 */
-	if (l3_mask && is_llc_event(event))
-		hwc->config |= l3_thread_slice_mask(event->attr.config);
-
-	uncore = event_to_amd_uncore(event);
-	if (!uncore)
-		return -ENODEV;
-
 	/*
 	 * since request can come in to any of the shared cores, we will remap
 	 * to a single common cpu.
 	 */
-	event->cpu = uncore->cpu;
+	event->cpu = ctx->cpu;
 
 	return 0;
 }
@@ -278,17 +257,10 @@ static ssize_t amd_uncore_attr_show_cpumask(struct device *dev,
 					    struct device_attribute *attr,
 					    char *buf)
 {
-	cpumask_t *active_mask;
-	struct pmu *pmu = dev_get_drvdata(dev);
+	struct pmu *ptr = dev_get_drvdata(dev);
+	struct amd_uncore_pmu *pmu = container_of(ptr, struct amd_uncore_pmu, pmu);
 
-	if (pmu->type == amd_nb_pmu.type)
-		active_mask = &amd_nb_active_mask;
-	else if (pmu->type == amd_llc_pmu.type)
-		active_mask = &amd_llc_active_mask;
-	else
-		return 0;
-
-	return cpumap_print_to_pagebuf(true, buf, active_mask);
+	return cpumap_print_to_pagebuf(true, buf, &pmu->active_mask);
 }
 static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL);
 
@@ -315,7 +287,7 @@ static struct device_attribute format_attr_##_var =			\
 DEFINE_UNCORE_FORMAT_ATTR(event12,	event,		"config:0-7,32-35");
 DEFINE_UNCORE_FORMAT_ATTR(event14,	event,		"config:0-7,32-35,59-60"); /* F17h+ DF */
 DEFINE_UNCORE_FORMAT_ATTR(event14v2,	event,		"config:0-7,32-37");	   /* PerfMonV2 DF */
-DEFINE_UNCORE_FORMAT_ATTR(event8,	event,		"config:0-7");		   /* F17h+ L3 */
+DEFINE_UNCORE_FORMAT_ATTR(event8,	event,		"config:0-7");		   /* F17h+ L3, PerfMonV2 UMC */
 DEFINE_UNCORE_FORMAT_ATTR(umask8,	umask,		"config:8-15");
 DEFINE_UNCORE_FORMAT_ATTR(umask12,	umask,		"config:8-15,24-27");	   /* PerfMonV2 DF */
 DEFINE_UNCORE_FORMAT_ATTR(coreid,	coreid,		"config:42-44");	   /* F19h L3 */
@@ -325,6 +297,7 @@ DEFINE_UNCORE_FORMAT_ATTR(threadmask2,	threadmask,	"config:56-57");	   /* F19h L
 DEFINE_UNCORE_FORMAT_ATTR(enallslices,	enallslices,	"config:46");		   /* F19h L3 */
 DEFINE_UNCORE_FORMAT_ATTR(enallcores,	enallcores,	"config:47");		   /* F19h L3 */
 DEFINE_UNCORE_FORMAT_ATTR(sliceid,	sliceid,	"config:48-50");	   /* F19h L3 */
+DEFINE_UNCORE_FORMAT_ATTR(rdwrmask,	rdwrmask,	"config:8-9");		   /* PerfMonV2 UMC */
 
 /* Common DF and NB attributes */
 static struct attribute *amd_uncore_df_format_attr[] = {
@@ -341,6 +314,13 @@ static struct attribute *amd_uncore_l3_format_attr[] = {
 	NULL,
 };
 
+/* Common UMC attributes */
+static struct attribute *amd_uncore_umc_format_attr[] = {
+	&format_attr_event8.attr,       /* event */
+	&format_attr_rdwrmask.attr,     /* rdwrmask */
+	NULL,
+};
+
 /* F17h unique L3 attributes */
 static struct attribute *amd_f17h_uncore_l3_format_attr[] = {
 	&format_attr_slicemask.attr,	/* slicemask */
@@ -378,6 +358,11 @@ static struct attribute_group amd_f19h_uncore_l3_format_group = {
 	.is_visible = amd_f19h_uncore_is_visible,
 };
 
+static struct attribute_group amd_uncore_umc_format_group = {
+	.name = "format",
+	.attrs = amd_uncore_umc_format_attr,
+};
+
 static const struct attribute_group *amd_uncore_df_attr_groups[] = {
 	&amd_uncore_attr_group,
 	&amd_uncore_df_format_group,
@@ -396,259 +381,636 @@ static const struct attribute_group *amd_uncore_l3_attr_update[] = {
 	NULL,
 };
 
-static struct pmu amd_nb_pmu = {
-	.task_ctx_nr	= perf_invalid_context,
-	.attr_groups	= amd_uncore_df_attr_groups,
-	.name		= "amd_nb",
-	.event_init	= amd_uncore_event_init,
-	.add		= amd_uncore_add,
-	.del		= amd_uncore_del,
-	.start		= amd_uncore_start,
-	.stop		= amd_uncore_stop,
-	.read		= amd_uncore_read,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
-	.module		= THIS_MODULE,
+static const struct attribute_group *amd_uncore_umc_attr_groups[] = {
+	&amd_uncore_attr_group,
+	&amd_uncore_umc_format_group,
+	NULL,
 };
 
-static struct pmu amd_llc_pmu = {
-	.task_ctx_nr	= perf_invalid_context,
-	.attr_groups	= amd_uncore_l3_attr_groups,
-	.attr_update	= amd_uncore_l3_attr_update,
-	.name		= "amd_l2",
-	.event_init	= amd_uncore_event_init,
-	.add		= amd_uncore_add,
-	.del		= amd_uncore_del,
-	.start		= amd_uncore_start,
-	.stop		= amd_uncore_stop,
-	.read		= amd_uncore_read,
-	.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
-	.module		= THIS_MODULE,
-};
+static __always_inline
+int amd_uncore_ctx_cid(struct amd_uncore *uncore, unsigned int cpu)
+{
+	union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
+	return info->split.cid;
+}
 
-static struct amd_uncore *amd_uncore_alloc(unsigned int cpu)
+static __always_inline
+int amd_uncore_ctx_gid(struct amd_uncore *uncore, unsigned int cpu)
 {
-	return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL,
-			cpu_to_node(cpu));
+	union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
+	return info->split.gid;
 }
 
-static inline struct perf_event **
-amd_uncore_events_alloc(unsigned int num, unsigned int cpu)
+static __always_inline
+int amd_uncore_ctx_num_pmcs(struct amd_uncore *uncore, unsigned int cpu)
 {
-	return kzalloc_node(sizeof(struct perf_event *) * num, GFP_KERNEL,
-			    cpu_to_node(cpu));
+	union amd_uncore_info *info = per_cpu_ptr(uncore->info, cpu);
+	return info->split.num_pmcs;
 }
 
-static int amd_uncore_cpu_up_prepare(unsigned int cpu)
+static void amd_uncore_ctx_free(struct amd_uncore *uncore, unsigned int cpu)
 {
-	struct amd_uncore *uncore_nb = NULL, *uncore_llc = NULL;
+	struct amd_uncore_pmu *pmu;
+	struct amd_uncore_ctx *ctx;
+	int i;
 
-	if (amd_uncore_nb) {
-		*per_cpu_ptr(amd_uncore_nb, cpu) = NULL;
-		uncore_nb = amd_uncore_alloc(cpu);
-		if (!uncore_nb)
-			goto fail;
-		uncore_nb->cpu = cpu;
-		uncore_nb->num_counters = num_counters_nb;
-		uncore_nb->rdpmc_base = RDPMC_BASE_NB;
-		uncore_nb->msr_base = MSR_F15H_NB_PERF_CTL;
-		uncore_nb->active_mask = &amd_nb_active_mask;
-		uncore_nb->pmu = &amd_nb_pmu;
-		uncore_nb->events = amd_uncore_events_alloc(num_counters_nb, cpu);
-		if (!uncore_nb->events)
-			goto fail;
-		uncore_nb->id = -1;
-		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore_nb;
+	if (!uncore->init_done)
+		return;
+
+	for (i = 0; i < uncore->num_pmus; i++) {
+		pmu = &uncore->pmus[i];
+		ctx = *per_cpu_ptr(pmu->ctx, cpu);
+		if (!ctx)
+			continue;
+
+		if (cpu == ctx->cpu)
+			cpumask_clear_cpu(cpu, &pmu->active_mask);
+
+		if (!--ctx->refcnt) {
+			kfree(ctx->events);
+			kfree(ctx);
+		}
+
+		*per_cpu_ptr(pmu->ctx, cpu) = NULL;
 	}
+}
 
-	if (amd_uncore_llc) {
-		*per_cpu_ptr(amd_uncore_llc, cpu) = NULL;
-		uncore_llc = amd_uncore_alloc(cpu);
-		if (!uncore_llc)
-			goto fail;
-		uncore_llc->cpu = cpu;
-		uncore_llc->num_counters = num_counters_llc;
-		uncore_llc->rdpmc_base = RDPMC_BASE_LLC;
-		uncore_llc->msr_base = MSR_F16H_L2I_PERF_CTL;
-		uncore_llc->active_mask = &amd_llc_active_mask;
-		uncore_llc->pmu = &amd_llc_pmu;
-		uncore_llc->events = amd_uncore_events_alloc(num_counters_llc, cpu);
-		if (!uncore_llc->events)
-			goto fail;
-		uncore_llc->id = -1;
-		*per_cpu_ptr(amd_uncore_llc, cpu) = uncore_llc;
+static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+{
+	struct amd_uncore_ctx *curr, *prev;
+	struct amd_uncore_pmu *pmu;
+	int node, cid, gid, i, j;
+
+	if (!uncore->init_done || !uncore->num_pmus)
+		return 0;
+
+	cid = amd_uncore_ctx_cid(uncore, cpu);
+	gid = amd_uncore_ctx_gid(uncore, cpu);
+
+	for (i = 0; i < uncore->num_pmus; i++) {
+		pmu = &uncore->pmus[i];
+		*per_cpu_ptr(pmu->ctx, cpu) = NULL;
+		curr = NULL;
+
+		/* Check for group exclusivity */
+		if (gid != pmu->group)
+			continue;
+
+		/* Find a sibling context */
+		for_each_online_cpu(j) {
+			if (cpu == j)
+				continue;
+
+			prev = *per_cpu_ptr(pmu->ctx, j);
+			if (!prev)
+				continue;
+
+			if (cid == amd_uncore_ctx_cid(uncore, j)) {
+				curr = prev;
+				break;
+			}
+		}
+
+		/* Allocate context if sibling does not exist */
+		if (!curr) {
+			node = cpu_to_node(cpu);
+			curr = kzalloc_node(sizeof(*curr), GFP_KERNEL, node);
+			if (!curr)
+				goto fail;
+
+			curr->cpu = cpu;
+			curr->events = kzalloc_node(sizeof(*curr->events) *
+						    pmu->num_counters,
+						    GFP_KERNEL, node);
+			if (!curr->events) {
+				kfree(curr);
+				goto fail;
+			}
+
+			cpumask_set_cpu(cpu, &pmu->active_mask);
+		}
+
+		curr->refcnt++;
+		*per_cpu_ptr(pmu->ctx, cpu) = curr;
 	}
 
 	return 0;
 
 fail:
-	if (uncore_nb) {
-		kfree(uncore_nb->events);
-		kfree(uncore_nb);
-	}
-
-	if (uncore_llc) {
-		kfree(uncore_llc->events);
-		kfree(uncore_llc);
-	}
+	amd_uncore_ctx_free(uncore, cpu);
 
 	return -ENOMEM;
 }
 
-static struct amd_uncore *
-amd_uncore_find_online_sibling(struct amd_uncore *this,
-			       struct amd_uncore * __percpu *uncores)
+static void amd_uncore_ctx_move(struct amd_uncore *uncore, unsigned int cpu)
 {
-	unsigned int cpu;
-	struct amd_uncore *that;
-
-	for_each_online_cpu(cpu) {
-		that = *per_cpu_ptr(uncores, cpu);
+	struct amd_uncore_ctx *curr, *next;
+	struct amd_uncore_pmu *pmu;
+	int i, j;
 
-		if (!that)
-			continue;
+	if (!uncore->init_done)
+		return;
 
-		if (this == that)
+	for (i = 0; i < uncore->num_pmus; i++) {
+		pmu = &uncore->pmus[i];
+		curr = *per_cpu_ptr(pmu->ctx, cpu);
+		if (!curr)
 			continue;
 
-		if (this->id == that->id) {
-			hlist_add_head(&this->node, &uncore_unused_list);
-			this = that;
-			break;
+		/* Migrate to a shared sibling if possible */
+		for_each_online_cpu(j) {
+			next = *per_cpu_ptr(pmu->ctx, j);
+			if (!next || cpu == j)
+				continue;
+
+			if (curr == next) {
+				perf_pmu_migrate_context(&pmu->pmu, cpu, j);
+				cpumask_clear_cpu(cpu, &pmu->active_mask);
+				cpumask_set_cpu(j, &pmu->active_mask);
+				next->cpu = j;
+				break;
+			}
 		}
 	}
-
-	this->refcnt++;
-	return this;
 }
 
 static int amd_uncore_cpu_starting(unsigned int cpu)
 {
-	unsigned int eax, ebx, ecx, edx;
 	struct amd_uncore *uncore;
+	int i;
+
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
+		uncore->scan(uncore, cpu);
+	}
+
+	return 0;
+}
 
-	if (amd_uncore_nb) {
-		uncore = *per_cpu_ptr(amd_uncore_nb, cpu);
-		cpuid(0x8000001e, &eax, &ebx, &ecx, &edx);
-		uncore->id = ecx & 0xff;
+static int amd_uncore_cpu_online(unsigned int cpu)
+{
+	struct amd_uncore *uncore;
+	int i;
 
-		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb);
-		*per_cpu_ptr(amd_uncore_nb, cpu) = uncore;
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
+		if (uncore->init(uncore, cpu))
+			break;
 	}
 
-	if (amd_uncore_llc) {
-		uncore = *per_cpu_ptr(amd_uncore_llc, cpu);
-		uncore->id = get_llc_id(cpu);
+	return 0;
+}
 
-		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_llc);
-		*per_cpu_ptr(amd_uncore_llc, cpu) = uncore;
+static int amd_uncore_cpu_down_prepare(unsigned int cpu)
+{
+	struct amd_uncore *uncore;
+	int i;
+
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
+		uncore->move(uncore, cpu);
 	}
 
 	return 0;
 }
 
-static void uncore_clean_online(void)
+static int amd_uncore_cpu_dead(unsigned int cpu)
 {
 	struct amd_uncore *uncore;
-	struct hlist_node *n;
+	int i;
 
-	hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
-		hlist_del(&uncore->node);
-		kfree(uncore->events);
-		kfree(uncore);
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
+		uncore->free(uncore, cpu);
 	}
+
+	return 0;
 }
 
-static void uncore_online(unsigned int cpu,
-			  struct amd_uncore * __percpu *uncores)
+static int amd_uncore_df_event_init(struct perf_event *event)
 {
-	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+	struct hw_perf_event *hwc = &event->hw;
+	int ret = amd_uncore_event_init(event);
 
-	uncore_clean_online();
+	if (ret || pmu_version < 2)
+		return ret;
 
-	if (cpu == uncore->cpu)
-		cpumask_set_cpu(cpu, uncore->active_mask);
+	hwc->config = event->attr.config &
+		      (pmu_version >= 2 ? AMD64_PERFMON_V2_RAW_EVENT_MASK_NB :
+					  AMD64_RAW_EVENT_MASK_NB);
+
+	return 0;
 }
 
-static int amd_uncore_cpu_online(unsigned int cpu)
+static int amd_uncore_df_add(struct perf_event *event, int flags)
 {
-	if (amd_uncore_nb)
-		uncore_online(cpu, amd_uncore_nb);
+	int ret = amd_uncore_add(event, flags & ~PERF_EF_START);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (ret)
+		return ret;
+
+	/*
+	 * The first four DF counters are accessible via RDPMC index 6 to 9
+	 * followed by the L3 counters from index 10 to 15. For processors
+	 * with more than four DF counters, the DF RDPMC assignments become
+	 * discontiguous as the additional counters are accessible starting
+	 * from index 16.
+	 */
+	if (hwc->idx >= NUM_COUNTERS_NB)
+		hwc->event_base_rdpmc += NUM_COUNTERS_L3;
 
-	if (amd_uncore_llc)
-		uncore_online(cpu, amd_uncore_llc);
+	/* Delayed start after rdpmc base update */
+	if (flags & PERF_EF_START)
+		amd_uncore_start(event, PERF_EF_RELOAD);
 
 	return 0;
 }
 
-static void uncore_down_prepare(unsigned int cpu,
-				struct amd_uncore * __percpu *uncores)
+static
+void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
-	unsigned int i;
-	struct amd_uncore *this = *per_cpu_ptr(uncores, cpu);
+	union cpuid_0x80000022_ebx ebx;
+	union amd_uncore_info info;
 
-	if (this->cpu != cpu)
+	if (!boot_cpu_has(X86_FEATURE_PERFCTR_NB))
 		return;
 
-	/* this cpu is going down, migrate to a shared sibling if possible */
-	for_each_online_cpu(i) {
-		struct amd_uncore *that = *per_cpu_ptr(uncores, i);
+	info.split.aux_data = 0;
+	info.split.num_pmcs = NUM_COUNTERS_NB;
+	info.split.gid = 0;
+	info.split.cid = topology_die_id(cpu);
 
-		if (cpu == i)
-			continue;
+	if (pmu_version >= 2) {
+		ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
+		info.split.num_pmcs = ebx.split.num_df_pmc;
+	}
 
-		if (this == that) {
-			perf_pmu_migrate_context(this->pmu, cpu, i);
-			cpumask_clear_cpu(cpu, that->active_mask);
-			cpumask_set_cpu(i, that->active_mask);
-			that->cpu = i;
-			break;
-		}
+	*per_cpu_ptr(uncore->info, cpu) = info;
+}
+
+static
+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;
+
+	/* Run just once */
+	if (uncore->init_done)
+		return amd_uncore_ctx_init(uncore, cpu);
+
+	/* No grouping, single instance for a system */
+	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
+	if (!uncore->pmus) {
+		uncore->num_pmus = 0;
+		goto done;
 	}
+
+	/*
+	 * For Family 17h and above, the Northbridge counters are repurposed
+	 * as Data Fabric counters. The PMUs are exported based on family as
+	 * either NB or DF.
+	 */
+	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->msr_base = MSR_F15H_NB_PERF_CTL;
+	pmu->rdpmc_base = RDPMC_BASE_NB;
+	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
+
+	if (pmu_version >= 2) {
+		*df_attr++ = &format_attr_event14v2.attr;
+		*df_attr++ = &format_attr_umask12.attr;
+	} else if (boot_cpu_data.x86 >= 0x17) {
+		*df_attr = &format_attr_event14.attr;
+	}
+
+	pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
+	if (!pmu->ctx)
+		goto done;
+
+	pmu->pmu = (struct pmu) {
+		.task_ctx_nr	= perf_invalid_context,
+		.attr_groups	= amd_uncore_df_attr_groups,
+		.name		= pmu->name,
+		.event_init	= amd_uncore_df_event_init,
+		.add		= amd_uncore_df_add,
+		.del		= amd_uncore_del,
+		.start		= amd_uncore_start,
+		.stop		= amd_uncore_stop,
+		.read		= amd_uncore_read,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+		.module		= THIS_MODULE,
+	};
+
+	if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
+		free_percpu(pmu->ctx);
+		pmu->ctx = NULL;
+		goto done;
+	}
+
+	pr_info("%d %s%s counters detected\n", pmu->num_counters,
+		boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?  "HYGON " : "",
+		pmu->pmu.name);
+
+	uncore->num_pmus = 1;
+
+done:
+	uncore->init_done = true;
+
+	return amd_uncore_ctx_init(uncore, cpu);
 }
 
-static int amd_uncore_cpu_down_prepare(unsigned int cpu)
+static int amd_uncore_l3_event_init(struct perf_event *event)
 {
-	if (amd_uncore_nb)
-		uncore_down_prepare(cpu, amd_uncore_nb);
+	int ret = amd_uncore_event_init(event);
+	struct hw_perf_event *hwc = &event->hw;
+	u64 config = event->attr.config;
+	u64 mask;
 
-	if (amd_uncore_llc)
-		uncore_down_prepare(cpu, amd_uncore_llc);
+	hwc->config = config & AMD64_RAW_EVENT_MASK_NB;
+
+	/*
+	 * SliceMask and ThreadMask need to be set for certain L3 events.
+	 * For other events, the two fields do not affect the count.
+	 */
+	if (ret || boot_cpu_data.x86 < 0x17)
+		return ret;
+
+	mask = config & (AMD64_L3_F19H_THREAD_MASK | AMD64_L3_SLICEID_MASK |
+			 AMD64_L3_EN_ALL_CORES | AMD64_L3_EN_ALL_SLICES |
+			 AMD64_L3_COREID_MASK);
+
+	if (boot_cpu_data.x86 <= 0x18)
+		mask = ((config & AMD64_L3_SLICE_MASK) ? : AMD64_L3_SLICE_MASK) |
+		       ((config & AMD64_L3_THREAD_MASK) ? : AMD64_L3_THREAD_MASK);
+
+	/*
+	 * If the user doesn't specify a ThreadMask, they're not trying to
+	 * count core 0, so we enable all cores & threads.
+	 * We'll also assume that they want to count slice 0 if they specify
+	 * a ThreadMask and leave SliceId and EnAllSlices unpopulated.
+	 */
+	else if (!(config & AMD64_L3_F19H_THREAD_MASK))
+		mask = AMD64_L3_F19H_THREAD_MASK | AMD64_L3_EN_ALL_SLICES |
+		       AMD64_L3_EN_ALL_CORES;
+
+	hwc->config |= mask;
 
 	return 0;
 }
 
-static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
+static
+void amd_uncore_l3_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
-	struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu);
+	union amd_uncore_info info;
 
-	if (cpu == uncore->cpu)
-		cpumask_clear_cpu(cpu, uncore->active_mask);
+	if (!boot_cpu_has(X86_FEATURE_PERFCTR_LLC))
+		return;
+
+	info.split.aux_data = 0;
+	info.split.num_pmcs = NUM_COUNTERS_L2;
+	info.split.gid = 0;
+	info.split.cid = get_llc_id(cpu);
 
-	if (!--uncore->refcnt) {
-		kfree(uncore->events);
-		kfree(uncore);
+	if (boot_cpu_data.x86 >= 0x17)
+		info.split.num_pmcs = NUM_COUNTERS_L3;
+
+	*per_cpu_ptr(uncore->info, cpu) = info;
+}
+
+static
+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;
+
+	/* Run just once */
+	if (uncore->init_done)
+		return amd_uncore_ctx_init(uncore, cpu);
+
+	/* No grouping, single instance for a system */
+	uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
+	if (!uncore->pmus) {
+		uncore->num_pmus = 0;
+		goto done;
 	}
 
-	*per_cpu_ptr(uncores, cpu) = NULL;
+	/*
+	 * For Family 17h and above, L3 cache counters are available instead
+	 * of L2 cache counters. The PMUs are exported based on family as
+	 * either L2 or L3.
+	 */
+	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->msr_base = MSR_F16H_L2I_PERF_CTL;
+	pmu->rdpmc_base = RDPMC_BASE_LLC;
+	pmu->group = amd_uncore_ctx_gid(uncore, cpu);
+
+	if (boot_cpu_data.x86 >= 0x17) {
+		*l3_attr++ = &format_attr_event8.attr;
+		*l3_attr++ = &format_attr_umask8.attr;
+		*l3_attr++ = boot_cpu_data.x86 >= 0x19 ?
+			     &format_attr_threadmask2.attr :
+			     &format_attr_threadmask8.attr;
+	}
+
+	pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
+	if (!pmu->ctx)
+		goto done;
+
+	pmu->pmu = (struct pmu) {
+		.task_ctx_nr	= perf_invalid_context,
+		.attr_groups	= amd_uncore_l3_attr_groups,
+		.attr_update	= amd_uncore_l3_attr_update,
+		.name		= pmu->name,
+		.event_init	= amd_uncore_l3_event_init,
+		.add		= amd_uncore_add,
+		.del		= amd_uncore_del,
+		.start		= amd_uncore_start,
+		.stop		= amd_uncore_stop,
+		.read		= amd_uncore_read,
+		.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+		.module		= THIS_MODULE,
+	};
+
+	if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
+		free_percpu(pmu->ctx);
+		pmu->ctx = NULL;
+		goto done;
+	}
+
+	pr_info("%d %s%s counters detected\n", pmu->num_counters,
+		boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?  "HYGON " : "",
+		pmu->pmu.name);
+
+	uncore->num_pmus = 1;
+
+done:
+	uncore->init_done = true;
+
+	return amd_uncore_ctx_init(uncore, cpu);
 }
 
-static int amd_uncore_cpu_dead(unsigned int cpu)
+static int amd_uncore_umc_event_init(struct perf_event *event)
 {
-	if (amd_uncore_nb)
-		uncore_dead(cpu, amd_uncore_nb);
+	struct hw_perf_event *hwc = &event->hw;
+	int ret = amd_uncore_event_init(event);
+
+	if (ret)
+		return ret;
 
-	if (amd_uncore_llc)
-		uncore_dead(cpu, amd_uncore_llc);
+	hwc->config = event->attr.config & AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC;
 
 	return 0;
 }
 
-static int __init amd_uncore_init(void)
+static void amd_uncore_umc_start(struct perf_event *event, int flags)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (flags & PERF_EF_RELOAD)
+		wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+
+	hwc->state = 0;
+	wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
+	perf_event_update_userpage(event);
+}
+
+static
+void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
 {
-	struct attribute **df_attr = amd_uncore_df_format_attr;
-	struct attribute **l3_attr = amd_uncore_l3_format_attr;
 	union cpuid_0x80000022_ebx ebx;
+	union amd_uncore_info info;
+	unsigned int eax, ecx, edx;
+
+	if (pmu_version < 2)
+		return;
+
+	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);
+	*per_cpu_ptr(uncore->info, cpu) = info;
+}
+
+static
+int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+{
+	DECLARE_BITMAP(gmask, UNCORE_GROUP_MAX) = { 0 };
+	u8 group_num_pmus[UNCORE_GROUP_MAX] = { 0 };
+	u8 group_num_pmcs[UNCORE_GROUP_MAX] = { 0 };
+	union amd_uncore_info info;
+	struct amd_uncore_pmu *pmu;
+	int index = 0, gid, i;
+
+	if (pmu_version < 2)
+		return 0;
+
+	/* Run just once */
+	if (uncore->init_done)
+		return amd_uncore_ctx_init(uncore, cpu);
+
+	/* Find unique groups */
+	for_each_online_cpu(i) {
+		info = *per_cpu_ptr(uncore->info, i);
+		gid = info.split.gid;
+		if (test_bit(gid, gmask))
+			continue;
+
+		__set_bit(gid, gmask);
+		group_num_pmus[gid] = hweight32(info.split.aux_data);
+		group_num_pmcs[gid] = info.split.num_pmcs;
+		uncore->num_pmus += group_num_pmus[gid];
+	}
+
+	uncore->pmus = kzalloc(sizeof(*uncore->pmus) * uncore->num_pmus,
+			       GFP_KERNEL);
+	if (!uncore->pmus) {
+		uncore->num_pmus = 0;
+		goto done;
+	}
+
+	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);
+			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;
+			pmu->group = gid;
+
+			pmu->ctx = alloc_percpu(struct amd_uncore_ctx *);
+			if (!pmu->ctx)
+				goto done;
+
+			pmu->pmu = (struct pmu) {
+				.task_ctx_nr	= perf_invalid_context,
+				.attr_groups	= amd_uncore_umc_attr_groups,
+				.name		= pmu->name,
+				.event_init	= amd_uncore_umc_event_init,
+				.add		= amd_uncore_add,
+				.del		= amd_uncore_del,
+				.start		= amd_uncore_umc_start,
+				.stop		= amd_uncore_stop,
+				.read		= amd_uncore_read,
+				.capabilities	= PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
+				.module		= THIS_MODULE,
+			};
+
+			if (perf_pmu_register(&pmu->pmu, pmu->pmu.name, -1)) {
+				free_percpu(pmu->ctx);
+				pmu->ctx = NULL;
+				goto done;
+			}
+
+			pr_info("%d %s counters detected\n", pmu->num_counters,
+				pmu->pmu.name);
+
+			index++;
+		}
+	}
+
+done:
+	uncore->num_pmus = index;
+	uncore->init_done = true;
+
+	return amd_uncore_ctx_init(uncore, cpu);
+}
+
+static struct amd_uncore uncores[UNCORE_TYPE_MAX] = {
+	/* UNCORE_TYPE_DF */
+	{
+		.scan = amd_uncore_df_ctx_scan,
+		.init = amd_uncore_df_ctx_init,
+		.move = amd_uncore_ctx_move,
+		.free = amd_uncore_ctx_free,
+	},
+	/* UNCORE_TYPE_L3 */
+	{
+		.scan = amd_uncore_l3_ctx_scan,
+		.init = amd_uncore_l3_ctx_init,
+		.move = amd_uncore_ctx_move,
+		.free = amd_uncore_ctx_free,
+	},
+	/* UNCORE_TYPE_UMC */
+	{
+		.scan = amd_uncore_umc_ctx_scan,
+		.init = amd_uncore_umc_ctx_init,
+		.move = amd_uncore_ctx_move,
+		.free = amd_uncore_ctx_free,
+	},
+};
+
+static int __init amd_uncore_init(void)
+{
+	struct amd_uncore *uncore;
 	int ret = -ENODEV;
+	int i;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
 	    boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -660,125 +1022,91 @@ static int __init amd_uncore_init(void)
 	if (boot_cpu_has(X86_FEATURE_PERFMON_V2))
 		pmu_version = 2;
 
-	num_counters_nb	= NUM_COUNTERS_NB;
-	num_counters_llc = NUM_COUNTERS_L2;
-	if (boot_cpu_data.x86 >= 0x17) {
-		/*
-		 * For F17h and above, the Northbridge counters are
-		 * repurposed as Data Fabric counters. Also, L3
-		 * counters are supported too. The PMUs are exported
-		 * based on family as either L2 or L3 and NB or DF.
-		 */
-		num_counters_llc	  = NUM_COUNTERS_L3;
-		amd_nb_pmu.name		  = "amd_df";
-		amd_llc_pmu.name	  = "amd_l3";
-		l3_mask			  = true;
-	}
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
 
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
-		if (pmu_version >= 2) {
-			*df_attr++ = &format_attr_event14v2.attr;
-			*df_attr++ = &format_attr_umask12.attr;
-		} else if (boot_cpu_data.x86 >= 0x17) {
-			*df_attr = &format_attr_event14.attr;
-		}
+		BUG_ON(!uncore->scan);
+		BUG_ON(!uncore->init);
+		BUG_ON(!uncore->move);
+		BUG_ON(!uncore->free);
 
-		amd_uncore_nb = alloc_percpu(struct amd_uncore *);
-		if (!amd_uncore_nb) {
+		uncore->info = alloc_percpu(union amd_uncore_info);
+		if (!uncore->info) {
 			ret = -ENOMEM;
-			goto fail_nb;
-		}
-		ret = perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1);
-		if (ret)
-			goto fail_nb;
-
-		if (pmu_version >= 2) {
-			ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
-			num_counters_nb = ebx.split.num_df_pmc;
-		}
-
-		pr_info("%d %s %s counters detected\n", num_counters_nb,
-			boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?  "HYGON" : "",
-			amd_nb_pmu.name);
-
-		ret = 0;
-	}
-
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
-		if (boot_cpu_data.x86 >= 0x19) {
-			*l3_attr++ = &format_attr_event8.attr;
-			*l3_attr++ = &format_attr_umask8.attr;
-			*l3_attr++ = &format_attr_threadmask2.attr;
-		} else if (boot_cpu_data.x86 >= 0x17) {
-			*l3_attr++ = &format_attr_event8.attr;
-			*l3_attr++ = &format_attr_umask8.attr;
-			*l3_attr++ = &format_attr_threadmask8.attr;
-		}
-
-		amd_uncore_llc = alloc_percpu(struct amd_uncore *);
-		if (!amd_uncore_llc) {
-			ret = -ENOMEM;
-			goto fail_llc;
+			goto fail;
 		}
-		ret = perf_pmu_register(&amd_llc_pmu, amd_llc_pmu.name, -1);
-		if (ret)
-			goto fail_llc;
-
-		pr_info("%d %s %s counters detected\n", num_counters_llc,
-			boot_cpu_data.x86_vendor == X86_VENDOR_HYGON ?  "HYGON" : "",
-			amd_llc_pmu.name);
-		ret = 0;
-	}
+	};
 
 	/*
 	 * Install callbacks. Core will call them for each online cpu.
 	 */
-	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
-			      "perf/x86/amd/uncore:prepare",
-			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
-		goto fail_llc;
-
-	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
-			      "perf/x86/amd/uncore:starting",
-			      amd_uncore_cpu_starting, NULL))
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
+				"perf/x86/amd/uncore:prepare",
+				NULL, amd_uncore_cpu_dead);
+	if (ret)
+		goto fail;
+
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
+				"perf/x86/amd/uncore:starting",
+				amd_uncore_cpu_starting, NULL);
+	if (ret)
 		goto fail_prep;
-	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
-			      "perf/x86/amd/uncore:online",
-			      amd_uncore_cpu_online,
-			      amd_uncore_cpu_down_prepare))
+
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
+				"perf/x86/amd/uncore:online",
+				amd_uncore_cpu_online,
+				amd_uncore_cpu_down_prepare);
+	if (ret)
 		goto fail_start;
+
 	return 0;
 
 fail_start:
 	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
 fail_prep:
 	cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
-fail_llc:
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
-		perf_pmu_unregister(&amd_nb_pmu);
-	free_percpu(amd_uncore_llc);
-fail_nb:
-	free_percpu(amd_uncore_nb);
+fail:
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
+		if (uncore->info) {
+			free_percpu(uncore->info);
+			uncore->info = NULL;
+		}
+	}
 
 	return ret;
 }
 
 static void __exit amd_uncore_exit(void)
 {
+	struct amd_uncore *uncore;
+	struct amd_uncore_pmu *pmu;
+	int i, j;
+
 	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE);
 	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
 	cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
 
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_LLC)) {
-		perf_pmu_unregister(&amd_llc_pmu);
-		free_percpu(amd_uncore_llc);
-		amd_uncore_llc = NULL;
-	}
+	for (i = 0; i < UNCORE_TYPE_MAX; i++) {
+		uncore = &uncores[i];
+		if (!uncore->info)
+			continue;
+
+		free_percpu(uncore->info);
+		uncore->info = NULL;
+
+		for (j = 0; j < uncore->num_pmus; j++) {
+			pmu = &uncore->pmus[j];
+			if (!pmu->ctx)
+				continue;
+
+			perf_pmu_unregister(&pmu->pmu);
+			free_percpu(pmu->ctx);
+			pmu->ctx = NULL;
+		}
 
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB)) {
-		perf_pmu_unregister(&amd_nb_pmu);
-		free_percpu(amd_uncore_nb);
-		amd_uncore_nb = NULL;
+		kfree(uncore->pmus);
+		uncore->pmus = NULL;
 	}
 }
 
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 185f902e5f28..40ad1425ffa2 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1887,9 +1887,9 @@ ssize_t events_hybrid_sysfs_show(struct device *dev,
 
 	str = pmu_attr->event_str;
 	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
-		if (!(x86_pmu.hybrid_pmu[i].cpu_type & pmu_attr->pmu_type))
+		if (!(x86_pmu.hybrid_pmu[i].pmu_type & pmu_attr->pmu_type))
 			continue;
-		if (x86_pmu.hybrid_pmu[i].cpu_type & pmu->cpu_type) {
+		if (x86_pmu.hybrid_pmu[i].pmu_type & pmu->pmu_type) {
 			next_str = strchr(str, ';');
 			if (next_str)
 				return snprintf(page, next_str - str + 1, "%s", str);
@@ -2169,7 +2169,7 @@ static int __init init_hw_perf_events(void)
 			hybrid_pmu->pmu.capabilities |= PERF_PMU_CAP_EXTENDED_HW_TYPE;
 
 			err = perf_pmu_register(&hybrid_pmu->pmu, hybrid_pmu->name,
-						(hybrid_pmu->cpu_type == hybrid_big) ? PERF_TYPE_RAW : -1);
+						(hybrid_pmu->pmu_type == hybrid_big) ? PERF_TYPE_RAW : -1);
 			if (err)
 				break;
 		}
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index fa355d3658a6..a08f794a0e79 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -211,6 +211,14 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly =
 	EVENT_CONSTRAINT_END
 };
 
+static struct event_constraint intel_grt_event_constraints[] __read_mostly = {
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */
+	FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */
+	FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF_TSC_P */
+	EVENT_CONSTRAINT_END
+};
+
 static struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
@@ -299,7 +307,7 @@ static struct extra_reg intel_icl_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
-static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
+static struct extra_reg intel_glc_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
@@ -309,11 +317,12 @@ static struct extra_reg intel_spr_extra_regs[] __read_mostly = {
 	EVENT_EXTRA_END
 };
 
-static struct event_constraint intel_spr_event_constraints[] = {
+static struct event_constraint intel_glc_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x00c0, 0),	/* INST_RETIRED.ANY */
 	FIXED_EVENT_CONSTRAINT(0x0100, 0),	/* INST_RETIRED.PREC_DIST */
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
+	FIXED_EVENT_CONSTRAINT(0x013c, 2),	/* CPU_CLK_UNHALTED.REF_TSC_P */
 	FIXED_EVENT_CONSTRAINT(0x0400, 3),	/* SLOTS */
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_RETIRING, 0),
 	METRIC_EVENT_CONSTRAINT(INTEL_TD_METRIC_BAD_SPEC, 1),
@@ -349,7 +358,7 @@ static struct event_constraint intel_spr_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-static struct extra_reg intel_gnr_extra_regs[] __read_mostly = {
+static struct extra_reg intel_rwc_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x012a, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x012b, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
@@ -473,7 +482,7 @@ static u64 intel_pmu_event_map(int hw_event)
 	return intel_perfmon_event_map[hw_event];
 }
 
-static __initconst const u64 spr_hw_cache_event_ids
+static __initconst const u64 glc_hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -552,7 +561,7 @@ static __initconst const u64 spr_hw_cache_event_ids
  },
 };
 
-static __initconst const u64 spr_hw_cache_extra_regs
+static __initconst const u64 glc_hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
 				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
@@ -2556,16 +2565,6 @@ static int icl_set_topdown_event_period(struct perf_event *event)
 	return 0;
 }
 
-static int adl_set_topdown_event_period(struct perf_event *event)
-{
-	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
-
-	if (pmu->cpu_type != hybrid_big)
-		return 0;
-
-	return icl_set_topdown_event_period(event);
-}
-
 DEFINE_STATIC_CALL(intel_pmu_set_topdown_event_period, x86_perf_event_set_period);
 
 static inline u64 icl_get_metrics_event_value(u64 metric, u64 slots, int idx)
@@ -2708,16 +2707,6 @@ static u64 icl_update_topdown_event(struct perf_event *event)
 						 x86_pmu.num_topdown_events - 1);
 }
 
-static u64 adl_update_topdown_event(struct perf_event *event)
-{
-	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
-
-	if (pmu->cpu_type != hybrid_big)
-		return 0;
-
-	return icl_update_topdown_event(event);
-}
-
 DEFINE_STATIC_CALL(intel_pmu_update_topdown_event, x86_perf_event_update);
 
 static void intel_pmu_read_topdown_event(struct perf_event *event)
@@ -3869,7 +3858,7 @@ static inline bool require_mem_loads_aux_event(struct perf_event *event)
 		return false;
 
 	if (is_hybrid())
-		return hybrid_pmu(event->pmu)->cpu_type == hybrid_big;
+		return hybrid_pmu(event->pmu)->pmu_type == hybrid_big;
 
 	return true;
 }
@@ -4273,7 +4262,7 @@ icl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 }
 
 static struct event_constraint *
-spr_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+glc_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			  struct perf_event *event)
 {
 	struct event_constraint *c;
@@ -4361,9 +4350,9 @@ adl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
 
-	if (pmu->cpu_type == hybrid_big)
-		return spr_get_event_constraints(cpuc, idx, event);
-	else if (pmu->cpu_type == hybrid_small)
+	if (pmu->pmu_type == hybrid_big)
+		return glc_get_event_constraints(cpuc, idx, event);
+	else if (pmu->pmu_type == hybrid_small)
 		return tnt_get_event_constraints(cpuc, idx, event);
 
 	WARN_ON(1);
@@ -4409,7 +4398,7 @@ rwc_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct event_constraint *c;
 
-	c = spr_get_event_constraints(cpuc, idx, event);
+	c = glc_get_event_constraints(cpuc, idx, event);
 
 	/* The Retire Latency is not supported by the fixed counter 0. */
 	if (event->attr.precise_ip &&
@@ -4433,9 +4422,9 @@ mtl_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 {
 	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
 
-	if (pmu->cpu_type == hybrid_big)
+	if (pmu->pmu_type == hybrid_big)
 		return rwc_get_event_constraints(cpuc, idx, event);
-	if (pmu->cpu_type == hybrid_small)
+	if (pmu->pmu_type == hybrid_small)
 		return cmt_get_event_constraints(cpuc, idx, event);
 
 	WARN_ON(1);
@@ -4446,18 +4435,18 @@ static int adl_hw_config(struct perf_event *event)
 {
 	struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu);
 
-	if (pmu->cpu_type == hybrid_big)
+	if (pmu->pmu_type == hybrid_big)
 		return hsw_hw_config(event);
-	else if (pmu->cpu_type == hybrid_small)
+	else if (pmu->pmu_type == hybrid_small)
 		return intel_pmu_hw_config(event);
 
 	WARN_ON(1);
 	return -EOPNOTSUPP;
 }
 
-static u8 adl_get_hybrid_cpu_type(void)
+static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
 {
-	return hybrid_big;
+	return HYBRID_INTEL_CORE;
 }
 
 /*
@@ -4490,7 +4479,7 @@ static void nhm_limit_period(struct perf_event *event, s64 *left)
 	*left = max(*left, 32LL);
 }
 
-static void spr_limit_period(struct perf_event *event, s64 *left)
+static void glc_limit_period(struct perf_event *event, s64 *left)
 {
 	if (event->attr.precise_ip == 3)
 		*left = max(*left, 128LL);
@@ -4618,6 +4607,23 @@ static void intel_pmu_check_num_counters(int *num_counters,
 					 int *num_counters_fixed,
 					 u64 *intel_ctrl, u64 fixed_mask);
 
+static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
+					      int num_counters,
+					      int num_counters_fixed,
+					      u64 intel_ctrl);
+
+static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
+
+static inline bool intel_pmu_broken_perf_cap(void)
+{
+	/* The Perf Metric (Bit 15) is always cleared */
+	if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) ||
+	    (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L))
+		return true;
+
+	return false;
+}
+
 static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 {
 	unsigned int sub_bitmaps = cpuid_eax(ARCH_PERFMON_EXT_LEAF);
@@ -4628,27 +4634,83 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
 			    &eax, &ebx, &ecx, &edx);
 		pmu->num_counters = fls(eax);
 		pmu->num_counters_fixed = fls(ebx);
-		intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
-					     &pmu->intel_ctrl, ebx);
+	}
+
+
+	if (!intel_pmu_broken_perf_cap()) {
+		/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
+		rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
 	}
 }
 
-static bool init_hybrid_pmu(int cpu)
+static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
+{
+	intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
+				     &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1);
+	pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+	pmu->unconstrained = (struct event_constraint)
+			     __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+						0, pmu->num_counters, 0, 0);
+
+	if (pmu->intel_cap.perf_metrics)
+		pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+	else
+		pmu->intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
+
+	if (pmu->intel_cap.pebs_output_pt_available)
+		pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+	else
+		pmu->pmu.capabilities |= ~PERF_PMU_CAP_AUX_OUTPUT;
+
+	intel_pmu_check_event_constraints(pmu->event_constraints,
+					  pmu->num_counters,
+					  pmu->num_counters_fixed,
+					  pmu->intel_ctrl);
+
+	intel_pmu_check_extra_regs(pmu->extra_regs);
+}
+
+static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void)
 {
-	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
 	u8 cpu_type = get_this_hybrid_cpu_type();
-	struct x86_hybrid_pmu *pmu = NULL;
 	int i;
 
-	if (!cpu_type && x86_pmu.get_hybrid_cpu_type)
-		cpu_type = x86_pmu.get_hybrid_cpu_type();
+	/*
+	 * This is running on a CPU model that is known to have hybrid
+	 * configurations. But the CPU told us it is not hybrid, shame
+	 * on it. There should be a fixup function provided for these
+	 * troublesome CPUs (->get_hybrid_cpu_type).
+	 */
+	if (cpu_type == HYBRID_INTEL_NONE) {
+		if (x86_pmu.get_hybrid_cpu_type)
+			cpu_type = x86_pmu.get_hybrid_cpu_type();
+		else
+			return NULL;
+	}
 
+	/*
+	 * This essentially just maps between the 'hybrid_cpu_type'
+	 * and 'hybrid_pmu_type' enums:
+	 */
 	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
-		if (x86_pmu.hybrid_pmu[i].cpu_type == cpu_type) {
-			pmu = &x86_pmu.hybrid_pmu[i];
-			break;
-		}
+		enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type;
+
+		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)
+			return &x86_pmu.hybrid_pmu[i];
 	}
+
+	return NULL;
+}
+
+static bool init_hybrid_pmu(int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	struct x86_hybrid_pmu *pmu = find_hybrid_pmu_for_cpu();
+
 	if (WARN_ON_ONCE(!pmu || (pmu->pmu.type == -1))) {
 		cpuc->pmu = NULL;
 		return false;
@@ -4661,6 +4723,8 @@ static bool init_hybrid_pmu(int cpu)
 	if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
 		update_pmu_cap(pmu);
 
+	intel_pmu_check_hybrid_pmus(pmu);
+
 	if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
 		return false;
 
@@ -5337,14 +5401,14 @@ static struct attribute *icl_tsx_events_attrs[] = {
 EVENT_ATTR_STR(mem-stores,	mem_st_spr,	"event=0xcd,umask=0x2");
 EVENT_ATTR_STR(mem-loads-aux,	mem_ld_aux,	"event=0x03,umask=0x82");
 
-static struct attribute *spr_events_attrs[] = {
+static struct attribute *glc_events_attrs[] = {
 	EVENT_PTR(mem_ld_hsw),
 	EVENT_PTR(mem_st_spr),
 	EVENT_PTR(mem_ld_aux),
 	NULL,
 };
 
-static struct attribute *spr_td_events_attrs[] = {
+static struct attribute *glc_td_events_attrs[] = {
 	EVENT_PTR(slots),
 	EVENT_PTR(td_retiring),
 	EVENT_PTR(td_bad_spec),
@@ -5357,7 +5421,7 @@ static struct attribute *spr_td_events_attrs[] = {
 	NULL,
 };
 
-static struct attribute *spr_tsx_events_attrs[] = {
+static struct attribute *glc_tsx_events_attrs[] = {
 	EVENT_PTR(tx_start),
 	EVENT_PTR(tx_abort),
 	EVENT_PTR(tx_commit),
@@ -5699,7 +5763,7 @@ static bool is_attr_for_this_pmu(struct kobject *kobj, struct attribute *attr)
 	struct perf_pmu_events_hybrid_attr *pmu_attr =
 		container_of(attr, struct perf_pmu_events_hybrid_attr, attr.attr);
 
-	return pmu->cpu_type & pmu_attr->pmu_type;
+	return pmu->pmu_type & pmu_attr->pmu_type;
 }
 
 static umode_t hybrid_events_is_visible(struct kobject *kobj,
@@ -5736,7 +5800,7 @@ static umode_t hybrid_format_is_visible(struct kobject *kobj,
 		container_of(attr, struct perf_pmu_format_hybrid_attr, attr.attr);
 	int cpu = hybrid_find_supported_cpu(pmu);
 
-	return (cpu >= 0) && (pmu->cpu_type & pmu_attr->pmu_type) ? attr->mode : 0;
+	return (cpu >= 0) && (pmu->pmu_type & pmu_attr->pmu_type) ? attr->mode : 0;
 }
 
 static struct attribute_group hybrid_group_events_td  = {
@@ -5880,40 +5944,105 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs)
 	}
 }
 
-static void intel_pmu_check_hybrid_pmus(u64 fixed_mask)
+static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = {
+	{ hybrid_small, "cpu_atom" },
+	{ hybrid_big, "cpu_core" },
+};
+
+static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
 {
+	unsigned long pmus_mask = pmus;
 	struct x86_hybrid_pmu *pmu;
-	int i;
+	int idx = 0, bit;
 
-	for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
-		pmu = &x86_pmu.hybrid_pmu[i];
+	x86_pmu.num_hybrid_pmus = hweight_long(pmus_mask);
+	x86_pmu.hybrid_pmu = kcalloc(x86_pmu.num_hybrid_pmus,
+				     sizeof(struct x86_hybrid_pmu),
+				     GFP_KERNEL);
+	if (!x86_pmu.hybrid_pmu)
+		return -ENOMEM;
 
-		intel_pmu_check_num_counters(&pmu->num_counters,
-					     &pmu->num_counters_fixed,
-					     &pmu->intel_ctrl,
-					     fixed_mask);
+	static_branch_enable(&perf_is_hybrid);
+	x86_pmu.filter = intel_pmu_filter;
 
-		if (pmu->intel_cap.perf_metrics) {
-			pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
-			pmu->intel_ctrl |= INTEL_PMC_MSK_FIXED_SLOTS;
+	for_each_set_bit(bit, &pmus_mask, ARRAY_SIZE(intel_hybrid_pmu_type_map)) {
+		pmu = &x86_pmu.hybrid_pmu[idx++];
+		pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id;
+		pmu->name = intel_hybrid_pmu_type_map[bit].name;
+
+		pmu->num_counters = x86_pmu.num_counters;
+		pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+		pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
+		pmu->unconstrained = (struct event_constraint)
+				     __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+							0, pmu->num_counters, 0, 0);
+
+		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
+		if (pmu->pmu_type & hybrid_small) {
+			pmu->intel_cap.perf_metrics = 0;
+			pmu->intel_cap.pebs_output_pt_available = 1;
+			pmu->mid_ack = true;
+		} else if (pmu->pmu_type & hybrid_big) {
+			pmu->intel_cap.perf_metrics = 1;
+			pmu->intel_cap.pebs_output_pt_available = 0;
+			pmu->late_ack = true;
 		}
+	}
 
-		if (pmu->intel_cap.pebs_output_pt_available)
-			pmu->pmu.capabilities |= PERF_PMU_CAP_AUX_OUTPUT;
+	return 0;
+}
 
-		intel_pmu_check_event_constraints(pmu->event_constraints,
-						  pmu->num_counters,
-						  pmu->num_counters_fixed,
-						  pmu->intel_ctrl);
+static __always_inline void intel_pmu_ref_cycles_ext(void)
+{
+	if (!(x86_pmu.events_maskl & (INTEL_PMC_MSK_FIXED_REF_CYCLES >> INTEL_PMC_IDX_FIXED)))
+		intel_perfmon_event_map[PERF_COUNT_HW_REF_CPU_CYCLES] = 0x013c;
+}
 
-		intel_pmu_check_extra_regs(pmu->extra_regs);
-	}
+static __always_inline void intel_pmu_init_glc(struct pmu *pmu)
+{
+	x86_pmu.late_ack = true;
+	x86_pmu.limit_period = glc_limit_period;
+	x86_pmu.pebs_aliases = NULL;
+	x86_pmu.pebs_prec_dist = true;
+	x86_pmu.pebs_block = true;
+	x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+	x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+	x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+	x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
+	x86_pmu.lbr_pt_coexist = true;
+	x86_pmu.num_topdown_events = 8;
+	static_call_update(intel_pmu_update_topdown_event,
+			   &icl_update_topdown_event);
+	static_call_update(intel_pmu_set_topdown_event_period,
+			   &icl_set_topdown_event_period);
+
+	memcpy(hybrid_var(pmu, hw_cache_event_ids), glc_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+	memcpy(hybrid_var(pmu, hw_cache_extra_regs), glc_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+	hybrid(pmu, event_constraints) = intel_glc_event_constraints;
+	hybrid(pmu, pebs_constraints) = intel_glc_pebs_event_constraints;
+
+	intel_pmu_ref_cycles_ext();
 }
 
-static __always_inline bool is_mtl(u8 x86_model)
+static __always_inline void intel_pmu_init_grt(struct pmu *pmu)
 {
-	return (x86_model == INTEL_FAM6_METEORLAKE) ||
-	       (x86_model == INTEL_FAM6_METEORLAKE_L);
+	x86_pmu.mid_ack = true;
+	x86_pmu.limit_period = glc_limit_period;
+	x86_pmu.pebs_aliases = NULL;
+	x86_pmu.pebs_prec_dist = true;
+	x86_pmu.pebs_block = true;
+	x86_pmu.lbr_pt_coexist = true;
+	x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+	x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
+
+	memcpy(hybrid_var(pmu, hw_cache_event_ids), glp_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+	memcpy(hybrid_var(pmu, hw_cache_extra_regs), tnt_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+	hybrid_var(pmu, hw_cache_event_ids)[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
+	hybrid(pmu, event_constraints) = intel_grt_event_constraints;
+	hybrid(pmu, pebs_constraints) = intel_grt_pebs_event_constraints;
+	hybrid(pmu, extra_regs) = intel_grt_extra_regs;
+
+	intel_pmu_ref_cycles_ext();
 }
 
 __init int intel_pmu_init(void)
@@ -6194,28 +6323,10 @@ __init int intel_pmu_init(void)
 		break;
 
 	case INTEL_FAM6_ATOM_GRACEMONT:
-		x86_pmu.mid_ack = true;
-		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
-		       sizeof(hw_cache_extra_regs));
-		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
-
-		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
-		x86_pmu.extra_regs = intel_grt_extra_regs;
-
-		x86_pmu.pebs_aliases = NULL;
-		x86_pmu.pebs_prec_dist = true;
-		x86_pmu.pebs_block = true;
-		x86_pmu.lbr_pt_coexist = true;
-		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
-		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-
+		intel_pmu_init_grt(NULL);
 		intel_pmu_pebs_data_source_grt();
 		x86_pmu.pebs_latency_data = adl_latency_data_small;
 		x86_pmu.get_event_constraints = tnt_get_event_constraints;
-		x86_pmu.limit_period = spr_limit_period;
 		td_attr = tnt_events_attrs;
 		mem_attr = grt_mem_attrs;
 		extra_attr = nhm_format_attr;
@@ -6225,28 +6336,11 @@ __init int intel_pmu_init(void)
 
 	case INTEL_FAM6_ATOM_CRESTMONT:
 	case INTEL_FAM6_ATOM_CRESTMONT_X:
-		x86_pmu.mid_ack = true;
-		memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
-		       sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, tnt_hw_cache_extra_regs,
-		       sizeof(hw_cache_extra_regs));
-		hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
-
-		x86_pmu.event_constraints = intel_slm_event_constraints;
-		x86_pmu.pebs_constraints = intel_grt_pebs_event_constraints;
+		intel_pmu_init_grt(NULL);
 		x86_pmu.extra_regs = intel_cmt_extra_regs;
-
-		x86_pmu.pebs_aliases = NULL;
-		x86_pmu.pebs_prec_dist = true;
-		x86_pmu.lbr_pt_coexist = true;
-		x86_pmu.pebs_block = true;
-		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
-		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-
 		intel_pmu_pebs_data_source_cmt();
 		x86_pmu.pebs_latency_data = mtl_latency_data_small;
 		x86_pmu.get_event_constraints = cmt_get_event_constraints;
-		x86_pmu.limit_period = spr_limit_period;
 		td_attr = cmt_events_attrs;
 		mem_attr = grt_mem_attrs;
 		extra_attr = cmt_format_attr;
@@ -6563,44 +6657,23 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_SAPPHIRERAPIDS_X:
 	case INTEL_FAM6_EMERALDRAPIDS_X:
 		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
-		x86_pmu.extra_regs = intel_spr_extra_regs;
+		x86_pmu.extra_regs = intel_glc_extra_regs;
 		fallthrough;
 	case INTEL_FAM6_GRANITERAPIDS_X:
 	case INTEL_FAM6_GRANITERAPIDS_D:
-		pmem = true;
-		x86_pmu.late_ack = true;
-		memcpy(hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(hw_cache_event_ids));
-		memcpy(hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
-
-		x86_pmu.event_constraints = intel_spr_event_constraints;
-		x86_pmu.pebs_constraints = intel_spr_pebs_event_constraints;
+		intel_pmu_init_glc(NULL);
 		if (!x86_pmu.extra_regs)
-			x86_pmu.extra_regs = intel_gnr_extra_regs;
-		x86_pmu.limit_period = spr_limit_period;
+			x86_pmu.extra_regs = intel_rwc_extra_regs;
 		x86_pmu.pebs_ept = 1;
-		x86_pmu.pebs_aliases = NULL;
-		x86_pmu.pebs_prec_dist = true;
-		x86_pmu.pebs_block = true;
-		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
-		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-
 		x86_pmu.hw_config = hsw_hw_config;
-		x86_pmu.get_event_constraints = spr_get_event_constraints;
+		x86_pmu.get_event_constraints = glc_get_event_constraints;
 		extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
 			hsw_format_attr : nhm_format_attr;
 		extra_skl_attr = skl_format_attr;
-		mem_attr = spr_events_attrs;
-		td_attr = spr_td_events_attrs;
-		tsx_attr = spr_tsx_events_attrs;
-		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
-		x86_pmu.lbr_pt_coexist = true;
-		intel_pmu_pebs_data_source_skl(pmem);
-		x86_pmu.num_topdown_events = 8;
-		static_call_update(intel_pmu_update_topdown_event,
-				   &icl_update_topdown_event);
-		static_call_update(intel_pmu_set_topdown_event_period,
-				   &icl_set_topdown_event_period);
+		mem_attr = glc_events_attrs;
+		td_attr = glc_td_events_attrs;
+		tsx_attr = glc_tsx_events_attrs;
+		intel_pmu_pebs_data_source_skl(true);
 		pr_cont("Sapphire Rapids events, ");
 		name = "sapphire_rapids";
 		break;
@@ -6610,47 +6683,17 @@ __init int intel_pmu_init(void)
 	case INTEL_FAM6_RAPTORLAKE:
 	case INTEL_FAM6_RAPTORLAKE_P:
 	case INTEL_FAM6_RAPTORLAKE_S:
-	case INTEL_FAM6_METEORLAKE:
-	case INTEL_FAM6_METEORLAKE_L:
 		/*
 		 * Alder Lake has 2 types of CPU, core and atom.
 		 *
 		 * Initialize the common PerfMon capabilities here.
 		 */
-		x86_pmu.hybrid_pmu = kcalloc(X86_HYBRID_NUM_PMUS,
-					     sizeof(struct x86_hybrid_pmu),
-					     GFP_KERNEL);
-		if (!x86_pmu.hybrid_pmu)
-			return -ENOMEM;
-		static_branch_enable(&perf_is_hybrid);
-		x86_pmu.num_hybrid_pmus = X86_HYBRID_NUM_PMUS;
+		intel_pmu_init_hybrid(hybrid_big_small);
 
-		x86_pmu.pebs_aliases = NULL;
-		x86_pmu.pebs_prec_dist = true;
-		x86_pmu.pebs_block = true;
-		x86_pmu.flags |= PMU_FL_HAS_RSP_1;
-		x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
-		x86_pmu.flags |= PMU_FL_INSTR_LATENCY;
-		x86_pmu.lbr_pt_coexist = true;
 		x86_pmu.pebs_latency_data = adl_latency_data_small;
-		x86_pmu.num_topdown_events = 8;
-		static_call_update(intel_pmu_update_topdown_event,
-				   &adl_update_topdown_event);
-		static_call_update(intel_pmu_set_topdown_event_period,
-				   &adl_set_topdown_event_period);
-
-		x86_pmu.filter = intel_pmu_filter;
 		x86_pmu.get_event_constraints = adl_get_event_constraints;
 		x86_pmu.hw_config = adl_hw_config;
-		x86_pmu.limit_period = spr_limit_period;
 		x86_pmu.get_hybrid_cpu_type = adl_get_hybrid_cpu_type;
-		/*
-		 * The rtm_abort_event is used to check whether to enable GPRs
-		 * for the RTM abort event. Atom doesn't have the RTM abort
-		 * event. There is no harmful to set it in the common
-		 * x86_pmu.rtm_abort_event.
-		 */
-		x86_pmu.rtm_abort_event = X86_CONFIG(.event=0xc9, .umask=0x04);
 
 		td_attr = adl_hybrid_events_attrs;
 		mem_attr = adl_hybrid_mem_attrs;
@@ -6660,9 +6703,7 @@ __init int intel_pmu_init(void)
 
 		/* Initialize big core specific PerfMon capabilities.*/
 		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
-		pmu->name = "cpu_core";
-		pmu->cpu_type = hybrid_big;
-		pmu->late_ack = true;
+		intel_pmu_init_glc(&pmu->pmu);
 		if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
 			pmu->num_counters = x86_pmu.num_counters + 2;
 			pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
@@ -6687,54 +6728,45 @@ __init int intel_pmu_init(void)
 		pmu->unconstrained = (struct event_constraint)
 					__EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
 							   0, pmu->num_counters, 0, 0);
-		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
-		pmu->intel_cap.perf_metrics = 1;
-		pmu->intel_cap.pebs_output_pt_available = 0;
+		pmu->extra_regs = intel_glc_extra_regs;
+
+		/* Initialize Atom core specific PerfMon capabilities.*/
+		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
+		intel_pmu_init_grt(&pmu->pmu);
+
+		x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
+		intel_pmu_pebs_data_source_adl();
+		pr_cont("Alderlake Hybrid events, ");
+		name = "alderlake_hybrid";
+		break;
+
+	case INTEL_FAM6_METEORLAKE:
+	case INTEL_FAM6_METEORLAKE_L:
+		intel_pmu_init_hybrid(hybrid_big_small);
 
-		memcpy(pmu->hw_cache_event_ids, spr_hw_cache_event_ids, sizeof(pmu->hw_cache_event_ids));
-		memcpy(pmu->hw_cache_extra_regs, spr_hw_cache_extra_regs, sizeof(pmu->hw_cache_extra_regs));
-		pmu->event_constraints = intel_spr_event_constraints;
-		pmu->pebs_constraints = intel_spr_pebs_event_constraints;
-		pmu->extra_regs = intel_spr_extra_regs;
+		x86_pmu.pebs_latency_data = mtl_latency_data_small;
+		x86_pmu.get_event_constraints = mtl_get_event_constraints;
+		x86_pmu.hw_config = adl_hw_config;
+
+		td_attr = adl_hybrid_events_attrs;
+		mem_attr = mtl_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_glc(&pmu->pmu);
+		pmu->extra_regs = intel_rwc_extra_regs;
 
 		/* Initialize Atom core specific PerfMon capabilities.*/
 		pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX];
-		pmu->name = "cpu_atom";
-		pmu->cpu_type = hybrid_small;
-		pmu->mid_ack = true;
-		pmu->num_counters = x86_pmu.num_counters;
-		pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
-		pmu->max_pebs_events = x86_pmu.max_pebs_events;
-		pmu->unconstrained = (struct event_constraint)
-					__EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
-							   0, pmu->num_counters, 0, 0);
-		pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
-		pmu->intel_cap.perf_metrics = 0;
-		pmu->intel_cap.pebs_output_pt_available = 1;
-
-		memcpy(pmu->hw_cache_event_ids, glp_hw_cache_event_ids, sizeof(pmu->hw_cache_event_ids));
-		memcpy(pmu->hw_cache_extra_regs, tnt_hw_cache_extra_regs, sizeof(pmu->hw_cache_extra_regs));
-		pmu->hw_cache_event_ids[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = -1;
-		pmu->event_constraints = intel_slm_event_constraints;
-		pmu->pebs_constraints = intel_grt_pebs_event_constraints;
-		pmu->extra_regs = intel_grt_extra_regs;
-		if (is_mtl(boot_cpu_data.x86_model)) {
-			x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].extra_regs = intel_gnr_extra_regs;
-			x86_pmu.pebs_latency_data = mtl_latency_data_small;
-			extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
-				mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr;
-			mem_attr = mtl_hybrid_mem_attrs;
-			intel_pmu_pebs_data_source_mtl();
-			x86_pmu.get_event_constraints = mtl_get_event_constraints;
-			pmu->extra_regs = intel_cmt_extra_regs;
-			pr_cont("Meteorlake Hybrid events, ");
-			name = "meteorlake_hybrid";
-		} else {
-			x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
-			intel_pmu_pebs_data_source_adl();
-			pr_cont("Alderlake Hybrid events, ");
-			name = "alderlake_hybrid";
-		}
+		intel_pmu_init_grt(&pmu->pmu);
+		pmu->extra_regs = intel_cmt_extra_regs;
+
+		intel_pmu_pebs_data_source_mtl();
+		pr_cont("Meteorlake Hybrid events, ");
+		name = "meteorlake_hybrid";
 		break;
 
 	default:
@@ -6846,9 +6878,6 @@ __init int intel_pmu_init(void)
 	if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics)
 		x86_pmu.intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
 
-	if (is_hybrid())
-		intel_pmu_check_hybrid_pmus((u64)fixed_mask);
-
 	if (x86_pmu.intel_cap.pebs_timing_info)
 		x86_pmu.flags |= PMU_FL_RETIRE_LATENCY;
 
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 96fffb2d521d..cbeb6d2bf5b4 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -336,6 +336,9 @@ static int cstate_pmu_event_init(struct perf_event *event)
 		cfg = array_index_nospec((unsigned long)cfg, PERF_CSTATE_PKG_EVENT_MAX);
 		if (!(pkg_msr_mask & (1 << cfg)))
 			return -EINVAL;
+
+		event->event_caps |= PERF_EV_CAP_READ_ACTIVE_PKG;
+
 		event->hw.event_base = pkg_msr[cfg].msr;
 		cpu = cpumask_any_and(&cstate_pkg_cpu_mask,
 				      topology_die_cpumask(event->cpu));
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index eb8dd8b8a1e8..bf97ab904d40 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -261,7 +261,7 @@ static u64 __adl_latency_data_small(struct perf_event *event, u64 status,
 {
 	u64 val;
 
-	WARN_ON_ONCE(hybrid_pmu(event->pmu)->cpu_type == hybrid_big);
+	WARN_ON_ONCE(hybrid_pmu(event->pmu)->pmu_type == hybrid_big);
 
 	dse &= PERF_PEBS_DATA_SOURCE_MASK;
 	val = hybrid_var(event->pmu, pebs_data_source)[dse];
@@ -1058,7 +1058,7 @@ struct event_constraint intel_icl_pebs_event_constraints[] = {
 	EVENT_CONSTRAINT_END
 };
 
-struct event_constraint intel_spr_pebs_event_constraints[] = {
+struct event_constraint intel_glc_pebs_event_constraints[] = {
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL),	/* INST_RETIRED.PREC_DIST */
 	INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL),
 
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 42a55794004a..8e2a12235e62 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -736,6 +736,7 @@ static bool topa_table_full(struct topa *topa)
 /**
  * topa_insert_pages() - create a list of ToPA tables
  * @buf:	PT buffer being initialized.
+ * @cpu:	CPU on which to allocate.
  * @gfp:	Allocation flags.
  *
  * This initializes a list of ToPA tables with entries from
@@ -1207,8 +1208,11 @@ static void pt_buffer_fini_topa(struct pt_buffer *buf)
 /**
  * pt_buffer_init_topa() - initialize ToPA table for pt buffer
  * @buf:	PT buffer.
- * @size:	Total size of all regions within this ToPA.
+ * @cpu:	CPU on which to allocate.
+ * @nr_pages:	No. of pages to allocate.
  * @gfp:	Allocation flags.
+ *
+ * Return:	0 on success or error code.
  */
 static int pt_buffer_init_topa(struct pt_buffer *buf, int cpu,
 			       unsigned long nr_pages, gfp_t gfp)
@@ -1281,7 +1285,7 @@ out:
 
 /**
  * pt_buffer_setup_aux() - set up topa tables for a PT buffer
- * @cpu:	Cpu on which to allocate, -1 means current.
+ * @event:	Performance event
  * @pages:	Array of pointers to buffer pages passed from perf core.
  * @nr_pages:	Number of pages in the buffer.
  * @snapshot:	If this is a snapshot/overwrite counter.
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index c8ba2be7585d..53dd5d495ba6 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -652,10 +652,29 @@ enum {
 #define PERF_PEBS_DATA_SOURCE_MAX	0x10
 #define PERF_PEBS_DATA_SOURCE_MASK	(PERF_PEBS_DATA_SOURCE_MAX - 1)
 
+enum hybrid_cpu_type {
+	HYBRID_INTEL_NONE,
+	HYBRID_INTEL_ATOM	= 0x20,
+	HYBRID_INTEL_CORE	= 0x40,
+};
+
+enum hybrid_pmu_type {
+	not_hybrid,
+	hybrid_small		= BIT(0),
+	hybrid_big		= BIT(1),
+
+	hybrid_big_small	= hybrid_big | hybrid_small, /* only used for matching */
+};
+
+#define X86_HYBRID_PMU_ATOM_IDX		0
+#define X86_HYBRID_PMU_CORE_IDX		1
+
+#define X86_HYBRID_NUM_PMUS		2
+
 struct x86_hybrid_pmu {
 	struct pmu			pmu;
 	const char			*name;
-	u8				cpu_type;
+	enum hybrid_pmu_type		pmu_type;
 	cpumask_t			supported_cpus;
 	union perf_capabilities		intel_cap;
 	u64				intel_ctrl;
@@ -721,18 +740,6 @@ extern struct static_key_false perf_is_hybrid;
 	__Fp;						\
 })
 
-enum hybrid_pmu_type {
-	hybrid_big		= 0x40,
-	hybrid_small		= 0x20,
-
-	hybrid_big_small	= hybrid_big | hybrid_small,
-};
-
-#define X86_HYBRID_PMU_ATOM_IDX		0
-#define X86_HYBRID_PMU_CORE_IDX		1
-
-#define X86_HYBRID_NUM_PMUS		2
-
 /*
  * struct x86_pmu - generic x86 pmu
  */
@@ -940,7 +947,7 @@ struct x86_pmu {
 	 */
 	int				num_hybrid_pmus;
 	struct x86_hybrid_pmu		*hybrid_pmu;
-	u8 (*get_hybrid_cpu_type)	(void);
+	enum hybrid_cpu_type (*get_hybrid_cpu_type)	(void);
 };
 
 struct x86_perf_task_context_opt {
@@ -1521,7 +1528,7 @@ extern struct event_constraint intel_skl_pebs_event_constraints[];
 
 extern struct event_constraint intel_icl_pebs_event_constraints[];
 
-extern struct event_constraint intel_spr_pebs_event_constraints[];
+extern struct event_constraint intel_glc_pebs_event_constraints[];
 
 struct event_constraint *intel_pebs_constraints(struct perf_event *event);
 
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 1579429846cc..8d98d468b976 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -115,7 +115,7 @@ struct rapl_pmu {
 struct rapl_pmus {
 	struct pmu		pmu;
 	unsigned int		maxdie;
-	struct rapl_pmu		*pmus[];
+	struct rapl_pmu		*pmus[] __counted_by(maxdie);
 };
 
 enum rapl_unit_quirk {
@@ -179,15 +179,11 @@ static u64 rapl_event_update(struct perf_event *event)
 	s64 delta, sdelta;
 	int shift = RAPL_CNTR_WIDTH;
 
-again:
 	prev_raw_count = local64_read(&hwc->prev_count);
-	rdmsrl(event->hw.event_base, new_raw_count);
-
-	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
-			    new_raw_count) != prev_raw_count) {
-		cpu_relax();
-		goto again;
-	}
+	do {
+		rdmsrl(event->hw.event_base, new_raw_count);
+	} while (!local64_try_cmpxchg(&hwc->prev_count,
+				      &prev_raw_count, new_raw_count));
 
 	/*
 	 * Now we have the new raw value and have updated the prev
@@ -537,11 +533,11 @@ static struct perf_msr intel_rapl_spr_msrs[] = {
  * - want to use same event codes across both architectures
  */
 static struct perf_msr amd_rapl_msrs[] = {
-	[PERF_RAPL_PP0]  = { 0, &rapl_events_cores_group, 0, false, 0 },
+	[PERF_RAPL_PP0]  = { 0, &rapl_events_cores_group, NULL, false, 0 },
 	[PERF_RAPL_PKG]  = { MSR_AMD_PKG_ENERGY_STATUS,  &rapl_events_pkg_group,   test_msr, false, RAPL_MSR_MASK },
-	[PERF_RAPL_RAM]  = { 0, &rapl_events_ram_group,   0, false, 0 },
-	[PERF_RAPL_PP1]  = { 0, &rapl_events_gpu_group,   0, false, 0 },
-	[PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group,  0, false, 0 },
+	[PERF_RAPL_RAM]  = { 0, &rapl_events_ram_group,   NULL, false, 0 },
+	[PERF_RAPL_PP1]  = { 0, &rapl_events_gpu_group,   NULL, false, 0 },
+	[PERF_RAPL_PSYS] = { 0, &rapl_events_psys_group,  NULL, false, 0 },
 };
 
 static int rapl_cpu_offline(unsigned int cpu)
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 61705dd0e94a..e3fa9cecd599 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -638,12 +638,16 @@
 #define MSR_AMD64_LBR_SELECT			0xc000010e
 
 /* Zen4 */
-#define MSR_ZEN4_BP_CFG			0xc001102e
+#define MSR_ZEN4_BP_CFG                 0xc001102e
 #define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
 
+/* Fam 19h MSRs */
+#define MSR_F19H_UMC_PERF_CTL           0xc0010800
+#define MSR_F19H_UMC_PERF_CTR           0xc0010801
+
 /* Zen 2 */
-#define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
-#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
+#define MSR_ZEN2_SPECTRAL_CHICKEN       0xc00110e3
+#define MSR_ZEN2_SPECTRAL_CHICKEN_BIT   BIT_ULL(1)
 
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 85a9fd5a3ec3..2618ec7c3d1d 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -112,6 +112,13 @@
 	(AMD64_PERFMON_V2_EVENTSEL_EVENT_NB	|	\
 	 AMD64_PERFMON_V2_EVENTSEL_UMASK_NB)
 
+#define AMD64_PERFMON_V2_ENABLE_UMC			BIT_ULL(31)
+#define AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC		GENMASK_ULL(7, 0)
+#define AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC		GENMASK_ULL(9, 8)
+#define AMD64_PERFMON_V2_RAW_EVENT_MASK_UMC		\
+	(AMD64_PERFMON_V2_EVENTSEL_EVENT_UMC	|	\
+	 AMD64_PERFMON_V2_EVENTSEL_RDWRMASK_UMC)
+
 #define AMD64_NUM_COUNTERS				4
 #define AMD64_NUM_COUNTERS_CORE				6
 #define AMD64_NUM_COUNTERS_NB				4
@@ -232,6 +239,8 @@ union cpuid_0x80000022_ebx {
 		unsigned int	lbr_v2_stack_sz:6;
 		/* Number of Data Fabric Counters */
 		unsigned int	num_df_pmc:6;
+		/* Number of Unified Memory Controller Counters */
+		unsigned int	num_umc_pmc:6;
 	} split;
 	unsigned int		full;
 };