19 files changed, 507 insertions, 327 deletions

diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 005907cb97d8..06d7c0205b3d 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -1,24 +1,20 @@
-perf-y += header.o
-perf-y += tsc.o
-perf-y += pmu.o
-perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
-perf-y += perf_regs.o
-perf-y += topdown.o
-perf-y += machine.o
-perf-y += event.o
-perf-y += evlist.o
-perf-y += mem-events.o
-perf-y += evsel.o
-perf-y += iostat.o
-perf-y += env.o
+perf-util-y += header.o
+perf-util-y += tsc.o
+perf-util-y += pmu.o
+perf-util-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
+perf-util-y += perf_regs.o
+perf-util-y += topdown.o
+perf-util-y += machine.o
+perf-util-y += event.o
+perf-util-y += evlist.o
+perf-util-y += mem-events.o
+perf-util-y += evsel.o
+perf-util-y += iostat.o
 
-perf-$(CONFIG_DWARF) += dwarf-regs.o
-perf-$(CONFIG_BPF_PROLOGUE) += dwarf-regs.o
+perf-util-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
+perf-util-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
-perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
-perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
-
-perf-$(CONFIG_AUXTRACE) += auxtrace.o
-perf-$(CONFIG_AUXTRACE) += archinsn.o
-perf-$(CONFIG_AUXTRACE) += intel-pt.o
-perf-$(CONFIG_AUXTRACE) += intel-bts.o
+perf-util-$(CONFIG_AUXTRACE) += auxtrace.o
+perf-util-y += archinsn.o
+perf-util-$(CONFIG_AUXTRACE) += intel-pt.o
+perf-util-$(CONFIG_AUXTRACE) += intel-bts.o
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 354780ff1605..ecbf61a7eb3a 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -55,11 +55,12 @@ struct auxtrace_record *auxtrace_record__init(struct evlist *evlist,
 					      int *err)
 {
 	char buffer[64];
+	struct perf_cpu cpu = perf_cpu_map__min(evlist->core.all_cpus);
 	int ret;
 
 	*err = 0;
 
-	ret = get_cpuid(buffer, sizeof(buffer));
+	ret = get_cpuid(buffer, sizeof(buffer), cpu);
 	if (ret) {
 		*err = ret;
 		return NULL;
diff --git a/tools/perf/arch/x86/util/dwarf-regs.c b/tools/perf/arch/x86/util/dwarf-regs.c
deleted file mode 100644
index 399c4a0a29d8..000000000000
--- a/tools/perf/arch/x86/util/dwarf-regs.c
+++ /dev/null
@@ -1,153 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * dwarf-regs.c : Mapping of DWARF debug register numbers into register names.
- * Extracted from probe-finder.c
- *
- * Written by Masami Hiramatsu <mhiramat@redhat.com>
- */
-
-#include <stddef.h>
-#include <errno.h> /* for EINVAL */
-#include <string.h> /* for strcmp */
-#include <linux/ptrace.h> /* for struct pt_regs */
-#include <linux/kernel.h> /* for offsetof */
-#include <dwarf-regs.h>
-
-/*
- * See arch/x86/kernel/ptrace.c.
- * Different from it:
- *
- *  - Since struct pt_regs is defined differently for user and kernel,
- *    but we want to use 'ax, bx' instead of 'rax, rbx' (which is struct
- *    field name of user's pt_regs), we make REG_OFFSET_NAME to accept
- *    both string name and reg field name.
- *
- *  - Since accessing x86_32's pt_regs from x86_64 building is difficult
- *    and vise versa, we simply fill offset with -1, so
- *    get_arch_regstr() still works but regs_query_register_offset()
- *    returns error.
- *    The only inconvenience caused by it now is that we are not allowed
- *    to generate BPF prologue for a x86_64 kernel if perf is built for
- *    x86_32. This is really a rare usecase.
- *
- *  - Order is different from kernel's ptrace.c for get_arch_regstr(). Use
- *    the order defined by dwarf.
- */
-
-struct pt_regs_offset {
-	const char *name;
-	int offset;
-};
-
-#define REG_OFFSET_END {.name = NULL, .offset = 0}
-
-#ifdef __x86_64__
-# define REG_OFFSET_NAME_64(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
-# define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = -1}
-#else
-# define REG_OFFSET_NAME_64(n, r) {.name = n, .offset = -1}
-# define REG_OFFSET_NAME_32(n, r) {.name = n, .offset = offsetof(struct pt_regs, r)}
-#endif
-
-/* TODO: switching by dwarf address size */
-#ifndef __x86_64__
-static const struct pt_regs_offset x86_32_regoffset_table[] = {
-	REG_OFFSET_NAME_32("%ax",	eax),
-	REG_OFFSET_NAME_32("%cx",	ecx),
-	REG_OFFSET_NAME_32("%dx",	edx),
-	REG_OFFSET_NAME_32("%bx",	ebx),
-	REG_OFFSET_NAME_32("$stack",	esp),	/* Stack address instead of %sp */
-	REG_OFFSET_NAME_32("%bp",	ebp),
-	REG_OFFSET_NAME_32("%si",	esi),
-	REG_OFFSET_NAME_32("%di",	edi),
-	REG_OFFSET_END,
-};
-
-#define regoffset_table x86_32_regoffset_table
-#else
-static const struct pt_regs_offset x86_64_regoffset_table[] = {
-	REG_OFFSET_NAME_64("%ax",	rax),
-	REG_OFFSET_NAME_64("%dx",	rdx),
-	REG_OFFSET_NAME_64("%cx",	rcx),
-	REG_OFFSET_NAME_64("%bx",	rbx),
-	REG_OFFSET_NAME_64("%si",	rsi),
-	REG_OFFSET_NAME_64("%di",	rdi),
-	REG_OFFSET_NAME_64("%bp",	rbp),
-	REG_OFFSET_NAME_64("%sp",	rsp),
-	REG_OFFSET_NAME_64("%r8",	r8),
-	REG_OFFSET_NAME_64("%r9",	r9),
-	REG_OFFSET_NAME_64("%r10",	r10),
-	REG_OFFSET_NAME_64("%r11",	r11),
-	REG_OFFSET_NAME_64("%r12",	r12),
-	REG_OFFSET_NAME_64("%r13",	r13),
-	REG_OFFSET_NAME_64("%r14",	r14),
-	REG_OFFSET_NAME_64("%r15",	r15),
-	REG_OFFSET_END,
-};
-
-#define regoffset_table x86_64_regoffset_table
-#endif
-
-/* Minus 1 for the ending REG_OFFSET_END */
-#define ARCH_MAX_REGS ((sizeof(regoffset_table) / sizeof(regoffset_table[0])) - 1)
-
-/* Return architecture dependent register string (for kprobe-tracer) */
-const char *get_arch_regstr(unsigned int n)
-{
-	return (n < ARCH_MAX_REGS) ? regoffset_table[n].name : NULL;
-}
-
-/* Reuse code from arch/x86/kernel/ptrace.c */
-/**
- * regs_query_register_offset() - query register offset from its name
- * @name:	the name of a register
- *
- * regs_query_register_offset() returns the offset of a register in struct
- * pt_regs from its name. If the name is invalid, this returns -EINVAL;
- */
-int regs_query_register_offset(const char *name)
-{
-	const struct pt_regs_offset *roff;
-	for (roff = regoffset_table; roff->name != NULL; roff++)
-		if (!strcmp(roff->name, name))
-			return roff->offset;
-	return -EINVAL;
-}
-
-struct dwarf_regs_idx {
-	const char *name;
-	int idx;
-};
-
-static const struct dwarf_regs_idx x86_regidx_table[] = {
-	{ "rax", 0 }, { "eax", 0 }, { "ax", 0 }, { "al", 0 },
-	{ "rdx", 1 }, { "edx", 1 }, { "dx", 1 }, { "dl", 1 },
-	{ "rcx", 2 }, { "ecx", 2 }, { "cx", 2 }, { "cl", 2 },
-	{ "rbx", 3 }, { "edx", 3 }, { "bx", 3 }, { "bl", 3 },
-	{ "rsi", 4 }, { "esi", 4 }, { "si", 4 }, { "sil", 4 },
-	{ "rdi", 5 }, { "edi", 5 }, { "di", 5 }, { "dil", 5 },
-	{ "rbp", 6 }, { "ebp", 6 }, { "bp", 6 }, { "bpl", 6 },
-	{ "rsp", 7 }, { "esp", 7 }, { "sp", 7 }, { "spl", 7 },
-	{ "r8", 8 }, { "r8d", 8 }, { "r8w", 8 }, { "r8b", 8 },
-	{ "r9", 9 }, { "r9d", 9 }, { "r9w", 9 }, { "r9b", 9 },
-	{ "r10", 10 }, { "r10d", 10 }, { "r10w", 10 }, { "r10b", 10 },
-	{ "r11", 11 }, { "r11d", 11 }, { "r11w", 11 }, { "r11b", 11 },
-	{ "r12", 12 }, { "r12d", 12 }, { "r12w", 12 }, { "r12b", 12 },
-	{ "r13", 13 }, { "r13d", 13 }, { "r13w", 13 }, { "r13b", 13 },
-	{ "r14", 14 }, { "r14d", 14 }, { "r14w", 14 }, { "r14b", 14 },
-	{ "r15", 15 }, { "r15d", 15 }, { "r15w", 15 }, { "r15b", 15 },
-	{ "rip", DWARF_REG_PC },
-};
-
-int get_arch_regnum(const char *name)
-{
-	unsigned int i;
-
-	if (*name != '%')
-		return -EINVAL;
-
-	for (i = 0; i < ARRAY_SIZE(x86_regidx_table); i++)
-		if (!strcmp(x86_regidx_table[i].name, name + 1))
-			return x86_regidx_table[i].idx;
-	return -ENOENT;
-}
diff --git a/tools/perf/arch/x86/util/env.c b/tools/perf/arch/x86/util/env.c
deleted file mode 100644
index 3e537ffb1353..000000000000
--- a/tools/perf/arch/x86/util/env.c
+++ /dev/null
@@ -1,19 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include "linux/string.h"
-#include "util/env.h"
-#include "env.h"
-
-bool x86__is_amd_cpu(void)
-{
-	struct perf_env env = { .total_mem = 0, };
-	static int is_amd; /* 0: Uninitialized, 1: Yes, -1: No */
-
-	if (is_amd)
-		goto ret;
-
-	perf_env__cpuid(&env);
-	is_amd = env.cpuid && strstarts(env.cpuid, "AuthenticAMD") ? 1 : -1;
-	perf_env__exit(&env);
-ret:
-	return is_amd >= 1 ? true : false;
-}
diff --git a/tools/perf/arch/x86/util/env.h b/tools/perf/arch/x86/util/env.h
deleted file mode 100644
index d78f080b6b3f..000000000000
--- a/tools/perf/arch/x86/util/env.h
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _X86_ENV_H
-#define _X86_ENV_H
-
-bool x86__is_amd_cpu(void);
-
-#endif /* _X86_ENV_H */
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index e65b7dbe27fb..a0400707180c 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -15,7 +15,7 @@
 #if defined(__x86_64__)
 
 struct perf_event__synthesize_extra_kmaps_cb_args {
-	struct perf_tool *tool;
+	const struct perf_tool *tool;
 	perf_event__handler_t process;
 	struct machine *machine;
 	union perf_event *event;
@@ -65,7 +65,7 @@ static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data)
 	return 0;
 }
 
-int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+int perf_event__synthesize_extra_kmaps(const struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine)
 {
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index b1ce0c52d88d..1969758cc8c1 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -1,94 +1,83 @@
 // SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include "util/pmu.h"
-#include "util/pmus.h"
-#include "util/evlist.h"
-#include "util/parse-events.h"
-#include "util/event.h"
+#include <string.h>
+#include "../../../util/evlist.h"
+#include "../../../util/evsel.h"
 #include "topdown.h"
 #include "evsel.h"
 
-static int ___evlist__add_default_attrs(struct evlist *evlist,
-					struct perf_event_attr *attrs,
-					size_t nr_attrs)
-{
-	LIST_HEAD(head);
-	size_t i = 0;
-
-	for (i = 0; i < nr_attrs; i++)
-		event_attr_init(attrs + i);
-
-	if (perf_pmus__num_core_pmus() == 1)
-		return evlist__add_attrs(evlist, attrs, nr_attrs);
-
-	for (i = 0; i < nr_attrs; i++) {
-		struct perf_pmu *pmu = NULL;
-
-		if (attrs[i].type == PERF_TYPE_SOFTWARE) {
-			struct evsel *evsel = evsel__new(attrs + i);
-
-			if (evsel == NULL)
-				goto out_delete_partial_list;
-			list_add_tail(&evsel->core.node, &head);
-			continue;
-		}
-
-		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
-			struct perf_cpu_map *cpus;
-			struct evsel *evsel;
-
-			evsel = evsel__new(attrs + i);
-			if (evsel == NULL)
-				goto out_delete_partial_list;
-			evsel->core.attr.config |= (__u64)pmu->type << PERF_PMU_TYPE_SHIFT;
-			cpus = perf_cpu_map__get(pmu->cpus);
-			evsel->core.cpus = cpus;
-			evsel->core.own_cpus = perf_cpu_map__get(cpus);
-			evsel->pmu_name = strdup(pmu->name);
-			list_add_tail(&evsel->core.node, &head);
-		}
-	}
-
-	evlist__splice_list_tail(evlist, &head);
-
-	return 0;
-
-out_delete_partial_list:
-	{
-		struct evsel *evsel, *n;
-
-		__evlist__for_each_entry_safe(&head, n, evsel)
-			evsel__delete(evsel);
-	}
-	return -1;
-}
-
-int arch_evlist__add_default_attrs(struct evlist *evlist,
-				   struct perf_event_attr *attrs,
-				   size_t nr_attrs)
-{
-	if (!nr_attrs)
-		return 0;
-
-	return ___evlist__add_default_attrs(evlist, attrs, nr_attrs);
-}
-
 int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 {
+	/*
+	 * Currently the following topdown events sequence are supported to
+	 * move and regroup correctly.
+	 *
+	 * a. all events in a group
+	 *    perf stat -e "{instructions,topdown-retiring,slots}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          15,066,240     slots
+	 *          1,899,760      instructions
+	 *          2,126,998      topdown-retiring
+	 * b. all events not in a group
+	 *    perf stat -e "instructions,topdown-retiring,slots" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *          2,045,561      instructions
+	 *          17,108,370     slots
+	 *          2,281,116      topdown-retiring
+	 * c. slots event in a group but topdown metrics events outside the group
+	 *    perf stat -e "{instructions,slots},topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         20,323,878      slots
+	 *          2,634,884      instructions
+	 *          3,028,656      topdown-retiring
+	 * d. slots event and topdown metrics events in two groups
+	 *    perf stat -e "{instructions,slots},{topdown-retiring}" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *     Performance counter stats for 'CPU(s) 0':
+	 *         26,319,024      slots
+	 *          2,427,791      instructions
+	 *          2,683,508      topdown-retiring
+	 * e. slots event and metrics event are not in a group and not adjacent
+	 *    perf stat -e "{instructions,slots},cycles,topdown-retiring" -C0 sleep 1
+	 *    WARNING: events were regrouped to match PMUs
+	 *         68,433,522      slots
+	 *          8,856,102      topdown-retiring
+	 *          7,791,494      instructions
+	 *         11,469,513      cycles
+	 */
 	if (topdown_sys_has_perf_metrics() &&
 	    (arch_evsel__must_be_in_group(lhs) || arch_evsel__must_be_in_group(rhs))) {
 		/* Ensure the topdown slots comes first. */
-		if (strcasestr(lhs->name, "slots") && !strcasestr(lhs->name, "uops_retired.slots"))
-			return -1;
-		if (strcasestr(rhs->name, "slots") && !strcasestr(rhs->name, "uops_retired.slots"))
-			return 1;
-		/* Followed by topdown events. */
-		if (strcasestr(lhs->name, "topdown") && !strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_slots(lhs))
 			return -1;
-		if (!strcasestr(lhs->name, "topdown") && strcasestr(rhs->name, "topdown"))
+		if (arch_is_topdown_slots(rhs))
 			return 1;
+
+		/*
+		 * Move topdown metrics events forward only when topdown metrics
+		 * events are not in same group with previous slots event. If
+		 * topdown metrics events are already in same group with slots
+		 * event, do nothing.
+		 */
+		if (lhs->core.leader != rhs->core.leader) {
+			bool lhs_topdown = arch_is_topdown_metrics(lhs);
+			bool rhs_topdown = arch_is_topdown_metrics(rhs);
+
+			if (lhs_topdown && !rhs_topdown)
+				return -1;
+			if (!lhs_topdown && rhs_topdown)
+				return 1;
+		}
 	}
 
+	/* Retire latency event should not be group leader*/
+	if (lhs->retire_lat && !rhs->retire_lat)
+		return 1;
+	if (!lhs->retire_lat && rhs->retire_lat)
+		return -1;
+
 	/* Default ordering by insertion index. */
 	return lhs->core.idx - rhs->core.idx;
 }
diff --git a/tools/perf/arch/x86/util/evsel.c b/tools/perf/arch/x86/util/evsel.c
index 090d0f371891..3dd29ba2c23b 100644
--- a/tools/perf/arch/x86/util/evsel.c
+++ b/tools/perf/arch/x86/util/evsel.c
@@ -6,6 +6,7 @@
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "linux/string.h"
+#include "topdown.h"
 #include "evsel.h"
 #include "util/debug.h"
 #include "env.h"
@@ -21,7 +22,8 @@ void arch_evsel__set_sample_weight(struct evsel *evsel)
 /* Check whether the evsel's PMU supports the perf metrics */
 bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 {
-	const char *pmu_name = evsel->pmu_name ? evsel->pmu_name : "cpu";
+	struct perf_pmu *pmu;
+	u32 type = evsel->core.attr.type;
 
 	/*
 	 * The PERF_TYPE_RAW type is the core PMU type, e.g., "cpu" PMU
@@ -31,11 +33,31 @@ bool evsel__sys_has_perf_metrics(const struct evsel *evsel)
 	 * Checking both the PERF_TYPE_RAW type and the slots event
 	 * should be good enough to detect the perf metrics feature.
 	 */
-	if ((evsel->core.attr.type == PERF_TYPE_RAW) &&
-	    perf_pmus__have_event(pmu_name, "slots"))
-		return true;
+again:
+	switch (type) {
+	case PERF_TYPE_HARDWARE:
+	case PERF_TYPE_HW_CACHE:
+		type = evsel->core.attr.config >> PERF_PMU_TYPE_SHIFT;
+		if (type)
+			goto again;
+		break;
+	case PERF_TYPE_RAW:
+		break;
+	default:
+		return false;
+	}
+
+	pmu = evsel->pmu;
+	if (pmu && perf_pmu__is_fake(pmu))
+		pmu = NULL;
 
-	return false;
+	if (!pmu) {
+		while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+			if (pmu->type == PERF_TYPE_RAW)
+				break;
+		}
+	}
+	return pmu && perf_pmu__have_event(pmu, "slots");
 }
 
 bool arch_evsel__must_be_in_group(const struct evsel *evsel)
@@ -44,7 +66,7 @@ bool arch_evsel__must_be_in_group(const struct evsel *evsel)
 	    strcasestr(evsel->name, "uops_retired.slots"))
 		return false;
 
-	return strcasestr(evsel->name, "topdown") || strcasestr(evsel->name, "slots");
+	return arch_is_topdown_metrics(evsel) || arch_is_topdown_slots(evsel);
 }
 
 int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
@@ -63,7 +85,7 @@ int arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size)
 		return  scnprintf(bf, size, "%s", event_name);
 
 	return scnprintf(bf, size, "%s/%s/",
-			 evsel->pmu_name ? evsel->pmu_name : "cpu",
+			 evsel->pmu ? evsel->pmu->name : "cpu",
 			 event_name);
 }
 
@@ -108,7 +130,7 @@ int arch_evsel__open_strerror(struct evsel *evsel, char *msg, size_t size)
 		return 0;
 
 	if (!evsel->core.attr.precise_ip &&
-	    !(evsel->pmu_name && !strncmp(evsel->pmu_name, "ibs", 3)))
+	    !(evsel->pmu && !strncmp(evsel->pmu->name, "ibs", 3)))
 		return 0;
 
 	/* More verbose IBS errors. */
diff --git a/tools/perf/arch/x86/util/header.c b/tools/perf/arch/x86/util/header.c
index a51444a77a5f..412977f8aa83 100644
--- a/tools/perf/arch/x86/util/header.c
+++ b/tools/perf/arch/x86/util/header.c
@@ -58,13 +58,12 @@ __get_cpuid(char *buffer, size_t sz, const char *fmt)
 }
 
 int
-get_cpuid(char *buffer, size_t sz)
+get_cpuid(char *buffer, size_t sz, struct perf_cpu cpu __maybe_unused)
 {
 	return __get_cpuid(buffer, sz, "%s,%u,%u,%u$");
 }
 
-char *
-get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+char *get_cpuid_str(struct perf_cpu cpu __maybe_unused)
 {
 	char *buf = malloc(128);
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index af8ae4647585..85c8186300c8 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -143,7 +143,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
-	if (opts->full_auxtrace && !perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (opts->full_auxtrace && !perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
 		return -EINVAL;
 	}
@@ -224,7 +224,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_bts_evsel, CPU);
 	}
 
@@ -434,7 +434,6 @@ struct auxtrace_record *intel_bts_recording_init(int *err)
 	}
 
 	btsr->intel_bts_pmu = intel_bts_pmu;
-	btsr->itr.pmu = intel_bts_pmu;
 	btsr->itr.recording_options = intel_bts_recording_options;
 	btsr->itr.info_priv_size = intel_bts_info_priv_size;
 	btsr->itr.info_fill = intel_bts_info_fill;
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index d199619df3ab..add33cb5d1da 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -19,6 +19,7 @@
 #include "../../../util/evlist.h"
 #include "../../../util/evsel.h"
 #include "../../../util/evsel_config.h"
+#include "../../../util/config.h"
 #include "../../../util/cpumap.h"
 #include "../../../util/mmap.h"
 #include <subcmd/parse-options.h>
@@ -32,6 +33,7 @@
 #include "../../../util/tsc.h"
 #include <internal/lib.h> // page_size
 #include "../../../util/intel-pt.h"
+#include <api/fs/fs.h>
 
 #define KiB(x) ((x) * 1024)
 #define MiB(x) ((x) * 1024 * 1024)
@@ -51,6 +53,7 @@ struct intel_pt_recording {
 	struct perf_pmu			*intel_pt_pmu;
 	int				have_sched_switch;
 	struct evlist		*evlist;
+	bool				all_switch_events;
 	bool				snapshot_mode;
 	bool				snapshot_init_done;
 	size_t				snapshot_size;
@@ -74,7 +77,8 @@ static int intel_pt_parse_terms_with_default(const struct perf_pmu *pmu,
 		goto out_free;
 
 	attr.config = *config;
-	err = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/true, /*err=*/NULL);
+	err = perf_pmu__config_terms(pmu, &attr, &terms, /*zero=*/true, /*apply_hardcoded=*/false,
+				     /*err=*/NULL);
 	if (err)
 		goto out_free;
 
@@ -369,7 +373,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 			ui__warning("Intel Processor Trace: TSC not available\n");
 	}
 
-	per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus);
+	per_cpu_mmaps = !perf_cpu_map__is_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus);
 
 	auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
 	auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
@@ -428,6 +432,16 @@ static int intel_pt_track_switches(struct evlist *evlist)
 }
 #endif
 
+static bool intel_pt_exclude_guest(void)
+{
+	int pt_mode;
+
+	if (sysfs__read_int("module/kvm_intel/parameters/pt_mode", &pt_mode))
+		pt_mode = 0;
+
+	return pt_mode == 1;
+}
+
 static void intel_pt_valid_str(char *str, size_t len, u64 valid)
 {
 	unsigned int val, last = 0, state = 1;
@@ -620,6 +634,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			}
 			evsel->core.attr.freq = 0;
 			evsel->core.attr.sample_period = 1;
+			evsel->core.attr.exclude_guest = intel_pt_exclude_guest();
 			evsel->no_aux_samples = true;
 			evsel->needs_auxtrace_mmap = true;
 			intel_pt_evsel = evsel;
@@ -758,7 +773,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	}
 
 	if (!opts->auxtrace_snapshot_mode && !opts->auxtrace_sample_mode) {
-		u32 aux_watermark = opts->auxtrace_mmap_pages * page_size / 4;
+		size_t aw = opts->auxtrace_mmap_pages * (size_t)page_size / 4;
+		u32 aux_watermark = aw > UINT_MAX ? UINT_MAX : aw;
 
 		intel_pt_evsel->core.attr.aux_watermark = aux_watermark;
 	}
@@ -774,13 +790,13 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Per-cpu recording needs sched_switch events to distinguish different
 	 * threads.
 	 */
-	if (have_timing_info && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
+	if (have_timing_info && !perf_cpu_map__is_any_cpu_or_is_empty(cpus) &&
 	    !record_opts__no_switch_events(opts)) {
 		if (perf_can_record_switch_events()) {
 			bool cpu_wide = !target__none(&opts->target) &&
 					!target__has_task(&opts->target);
 
-			if (!cpu_wide && perf_can_record_cpu_wide()) {
+			if (ptr->all_switch_events && !cpu_wide && perf_can_record_cpu_wide()) {
 				struct evsel *switch_evsel;
 
 				switch_evsel = evlist__add_dummy_on_all_cpus(evlist);
@@ -832,7 +848,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_pt_evsel, CPU);
 	}
 
@@ -858,7 +874,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			tracking_evsel->immediate = true;
 
 		/* In per-cpu case, always need the time of mmap events etc */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 			evsel__set_sample_bit(tracking_evsel, TIME);
 			/* And the CPU for switch events */
 			evsel__set_sample_bit(tracking_evsel, CPU);
@@ -870,7 +886,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Warn the user when we do not have enough information to decode i.e.
 	 * per-cpu with no sched_switch (except workload-only).
 	 */
-	if (!ptr->have_sched_switch && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
+	if (!ptr->have_sched_switch && !perf_cpu_map__is_any_cpu_or_is_empty(cpus) &&
 	    !target__none(&opts->target) &&
 	    !intel_pt_evsel->core.attr.exclude_user)
 		ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
@@ -1164,6 +1180,16 @@ static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
 	return rdtsc();
 }
 
+static int intel_pt_perf_config(const char *var, const char *value, void *data)
+{
+	struct intel_pt_recording *ptr = data;
+
+	if (!strcmp(var, "intel-pt.all-switch-events"))
+		ptr->all_switch_events = perf_config_bool(var, value);
+
+	return 0;
+}
+
 struct auxtrace_record *intel_pt_recording_init(int *err)
 {
 	struct perf_pmu *intel_pt_pmu = perf_pmus__find(INTEL_PT_PMU_NAME);
@@ -1183,8 +1209,9 @@ struct auxtrace_record *intel_pt_recording_init(int *err)
 		return NULL;
 	}
 
+	perf_config(intel_pt_perf_config, ptr);
+
 	ptr->intel_pt_pmu = intel_pt_pmu;
-	ptr->itr.pmu = intel_pt_pmu;
 	ptr->itr.recording_options = intel_pt_recording_options;
 	ptr->itr.info_priv_size = intel_pt_info_priv_size;
 	ptr->itr.info_fill = intel_pt_info_fill;
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index df7b5dfcc26a..7442a2cd87ed 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -32,7 +32,7 @@
 #define MAX_PATH 1024
 #endif
 
-#define UNCORE_IIO_PMU_PATH	"devices/uncore_iio_%d"
+#define UNCORE_IIO_PMU_PATH	"bus/event_source/devices/uncore_iio_%d"
 #define SYSFS_UNCORE_PMU_PATH	"%s/"UNCORE_IIO_PMU_PATH
 #define PLATFORM_MAPPING_PATH	UNCORE_IIO_PMU_PATH"/die%d"
 
@@ -403,6 +403,10 @@ void iostat_prefix(struct evlist *evlist,
 	struct iio_root_port *rp = evlist->selected->priv;
 
 	if (rp) {
+		/*
+		 * TODO: This is the incorrect format in JSON mode.
+		 *       See prepare_timestamp()
+		 */
 		if (ts)
 			sprintf(prefix, "%6lu.%09lu%s%04x:%02x%s",
 				ts->tv_sec, ts->tv_nsec,
@@ -444,7 +448,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
 		iostat_value = (count->val - prev_count_val) /
 			       ((double) count->run / count->ena);
 	}
-	out->print_metric(config, out->ctx, NULL, "%8.0f", iostat_metric,
+	out->print_metric(config, out->ctx, METRIC_THRESHOLD_UNKNOWN, "%8.0f", iostat_metric,
 			  iostat_value / (256 * 1024));
 }
 
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index 62df03e91c7e..b38f519020ff 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -26,3 +26,9 @@ struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
 	E(NULL,		NULL,		NULL,	false,	0),
 	E("mem-ldst",	"%s//",		NULL,	false,	0),
 };
+
+struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX] = {
+	E(NULL,		NULL,		NULL,	false,	0),
+	E(NULL,		NULL,		NULL,	false,	0),
+	E("mem-ldst",	"%s/ldlat=%u/",	NULL,	true,	0),
+};
diff --git a/tools/perf/arch/x86/util/mem-events.h b/tools/perf/arch/x86/util/mem-events.h
index f55c8d3b7d59..11e09a256f5b 100644
--- a/tools/perf/arch/x86/util/mem-events.h
+++ b/tools/perf/arch/x86/util/mem-events.h
@@ -6,5 +6,6 @@ extern struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX];
 extern struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX];
 
 extern struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX];
+extern struct perf_mem_event perf_mem_events_amd_ldlat[PERF_MEM_EVENTS__MAX];
 
 #endif /* _X86_MEM_EVENTS_H */
diff --git a/tools/perf/arch/x86/util/pmu.c b/tools/perf/arch/x86/util/pmu.c
index c3d89d6ba1bf..58113482654b 100644
--- a/tools/perf/arch/x86/util/pmu.c
+++ b/tools/perf/arch/x86/util/pmu.c
@@ -8,6 +8,8 @@
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
 #include <api/fs/fs.h>
+#include <api/io_dir.h>
+#include <internal/cpumap.h>
 #include <errno.h>
 
 #include "../../../util/intel-pt.h"
@@ -16,10 +18,261 @@
 #include "../../../util/fncache.h"
 #include "../../../util/pmus.h"
 #include "mem-events.h"
-#include "env.h"
+#include "util/debug.h"
+#include "util/env.h"
+#include "util/header.h"
 
-void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
+static bool x86__is_intel_graniterapids(void)
 {
+	static bool checked_if_graniterapids;
+	static bool is_graniterapids;
+
+	if (!checked_if_graniterapids) {
+		const char *graniterapids_cpuid = "GenuineIntel-6-A[DE]";
+		char *cpuid = get_cpuid_str((struct perf_cpu){0});
+
+		is_graniterapids = cpuid && strcmp_cpuid_str(graniterapids_cpuid, cpuid) == 0;
+		free(cpuid);
+		checked_if_graniterapids = true;
+	}
+	return is_graniterapids;
+}
+
+static struct perf_cpu_map *read_sysfs_cpu_map(const char *sysfs_path)
+{
+	struct perf_cpu_map *cpus;
+	char *buf = NULL;
+	size_t buf_len;
+
+	if (sysfs__read_str(sysfs_path, &buf, &buf_len) < 0)
+		return NULL;
+
+	cpus = perf_cpu_map__new(buf);
+	free(buf);
+	return cpus;
+}
+
+static int snc_nodes_per_l3_cache(void)
+{
+	static bool checked_snc;
+	static int snc_nodes;
+
+	if (!checked_snc) {
+		struct perf_cpu_map *node_cpus =
+			read_sysfs_cpu_map("devices/system/node/node0/cpulist");
+		struct perf_cpu_map *cache_cpus =
+			read_sysfs_cpu_map("devices/system/cpu/cpu0/cache/index3/shared_cpu_list");
+
+		snc_nodes = perf_cpu_map__nr(cache_cpus) / perf_cpu_map__nr(node_cpus);
+		perf_cpu_map__put(cache_cpus);
+		perf_cpu_map__put(node_cpus);
+		checked_snc = true;
+	}
+	return snc_nodes;
+}
+
+static bool starts_with(const char *str, const char *prefix)
+{
+	return !strncmp(prefix, str, strlen(prefix));
+}
+
+static int num_chas(void)
+{
+	static bool checked_chas;
+	static int num_chas;
+
+	if (!checked_chas) {
+		int fd = perf_pmu__event_source_devices_fd();
+		struct io_dir dir;
+		struct io_dirent64 *dent;
+
+		if (fd < 0)
+			return -1;
+
+		io_dir__init(&dir, fd);
+
+		while ((dent = io_dir__readdir(&dir)) != NULL) {
+			/* Note, dent->d_type will be DT_LNK and so isn't a useful filter. */
+			if (starts_with(dent->d_name, "uncore_cha_"))
+				num_chas++;
+		}
+		close(fd);
+		checked_chas = true;
+	}
+	return num_chas;
+}
+
+#define MAX_SNCS 6
+
+static int uncore_cha_snc(struct perf_pmu *pmu)
+{
+	// CHA SNC numbers are ordered correspond to the CHAs number.
+	unsigned int cha_num;
+	int num_cha, chas_per_node, cha_snc;
+	int snc_nodes = snc_nodes_per_l3_cache();
+
+	if (snc_nodes <= 1)
+		return 0;
+
+	num_cha = num_chas();
+	if (num_cha <= 0) {
+		pr_warning("Unexpected: no CHAs found\n");
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_cha_%u", &cha_num) != 1) {
+		pr_warning("Unexpected: unable to compute CHA number '%s'\n", pmu->name);
+		return 0;
+	}
+	chas_per_node = num_cha / snc_nodes;
+	cha_snc = cha_num / chas_per_node;
+
+	/* Range check cha_snc. for unexpected out of bounds. */
+	return cha_snc >= MAX_SNCS ? 0 : cha_snc;
+}
+
+static int uncore_imc_snc(struct perf_pmu *pmu)
+{
+	// Compute the IMC SNC using lookup tables.
+	unsigned int imc_num;
+	int snc_nodes = snc_nodes_per_l3_cache();
+	const u8 snc2_map[] = {1, 1, 0, 0, 1, 1, 0, 0};
+	const u8 snc3_map[] = {1, 1, 0, 0, 2, 2, 1, 1, 0, 0, 2, 2};
+	const u8 *snc_map;
+	size_t snc_map_len;
+
+	switch (snc_nodes) {
+	case 2:
+		snc_map = snc2_map;
+		snc_map_len = ARRAY_SIZE(snc2_map);
+		break;
+	case 3:
+		snc_map = snc3_map;
+		snc_map_len = ARRAY_SIZE(snc3_map);
+		break;
+	default:
+		/* Error or no lookup support for SNC with >3 nodes. */
+		return 0;
+	}
+
+	/* Compute SNC for PMU. */
+	if (sscanf(pmu->name, "uncore_imc_%u", &imc_num) != 1) {
+		pr_warning("Unexpected: unable to compute IMC number '%s'\n", pmu->name);
+		return 0;
+	}
+	if (imc_num >= snc_map_len) {
+		pr_warning("Unexpected IMC %d for SNC%d mapping\n", imc_num, snc_nodes);
+		return 0;
+	}
+	return snc_map[imc_num];
+}
+
+static int uncore_cha_imc_compute_cpu_adjust(int pmu_snc)
+{
+	static bool checked_cpu_adjust[MAX_SNCS];
+	static int cpu_adjust[MAX_SNCS];
+	struct perf_cpu_map *node_cpus;
+	char node_path[] = "devices/system/node/node0/cpulist";
+
+	/* Was adjust already computed? */
+	if (checked_cpu_adjust[pmu_snc])
+		return cpu_adjust[pmu_snc];
+
+	/* SNC0 doesn't need an adjust. */
+	if (pmu_snc == 0) {
+		cpu_adjust[0] = 0;
+		checked_cpu_adjust[0] = true;
+		return 0;
+	}
+
+	/*
+	 * Use NUMA topology to compute first CPU of the NUMA node, we want to
+	 * adjust CPU 0 to be this and similarly for other CPUs if there is >1
+	 * socket.
+	 */
+	assert(pmu_snc >= 0 && pmu_snc <= 9);
+	node_path[24] += pmu_snc; // Shift node0 to be node<pmu_snc>.
+	node_cpus = read_sysfs_cpu_map(node_path);
+	cpu_adjust[pmu_snc] = perf_cpu_map__cpu(node_cpus, 0).cpu;
+	if (cpu_adjust[pmu_snc] < 0) {
+		pr_debug("Failed to read valid CPU list from <sysfs>/%s\n", node_path);
+		cpu_adjust[pmu_snc] = 0;
+	} else {
+		checked_cpu_adjust[pmu_snc] = true;
+	}
+	perf_cpu_map__put(node_cpus);
+	return cpu_adjust[pmu_snc];
+}
+
+static void gnr_uncore_cha_imc_adjust_cpumask_for_snc(struct perf_pmu *pmu, bool cha)
+{
+	// With sub-NUMA clustering (SNC) there is a NUMA node per SNC in the
+	// topology. For example, a two socket graniterapids machine may be set
+	// up with 3-way SNC meaning there are 6 NUMA nodes that should be
+	// displayed with --per-node. The cpumask of the CHA and IMC PMUs
+	// reflects per-socket information meaning, for example, uncore_cha_60
+	// on a two socket graniterapids machine with 120 cores per socket will
+	// have a cpumask of "0,120". This cpumask needs adjusting to "40,160"
+	// to reflect that uncore_cha_60 is used for the 2nd SNC of each
+	// socket. Without the adjustment events on uncore_cha_60 will appear in
+	// node 0 and node 3 (in our example 2 socket 3-way set up), but with
+	// the adjustment they will appear in node 1 and node 4. The number of
+	// CHAs is typically larger than the number of cores. The CHA numbers
+	// are assumed to split evenly and inorder wrt core numbers. There are
+	// fewer memory IMC PMUs than cores and mapping is handled using lookup
+	// tables.
+	static struct perf_cpu_map *cha_adjusted[MAX_SNCS];
+	static struct perf_cpu_map *imc_adjusted[MAX_SNCS];
+	struct perf_cpu_map **adjusted = cha ? cha_adjusted : imc_adjusted;
+	int idx, pmu_snc, cpu_adjust;
+	struct perf_cpu cpu;
+	bool alloc;
+
+	// Cpus from the kernel holds first CPU of each socket. e.g. 0,120.
+	if (perf_cpu_map__cpu(pmu->cpus, 0).cpu != 0) {
+		pr_debug("Ignoring cpumask adjust for %s as unexpected first CPU\n", pmu->name);
+		return;
+	}
+
+	pmu_snc = cha ? uncore_cha_snc(pmu) : uncore_imc_snc(pmu);
+	if (pmu_snc == 0) {
+		// No adjustment necessary for the first SNC.
+		return;
+	}
+
+	alloc = adjusted[pmu_snc] == NULL;
+	if (alloc) {
+		// Hold onto the perf_cpu_map globally to avoid recomputation.
+		cpu_adjust = uncore_cha_imc_compute_cpu_adjust(pmu_snc);
+		adjusted[pmu_snc] = perf_cpu_map__empty_new(perf_cpu_map__nr(pmu->cpus));
+		if (!adjusted[pmu_snc])
+			return;
+	}
+
+	perf_cpu_map__for_each_cpu(cpu, idx, pmu->cpus) {
+		// Compute the new cpu map values or if not allocating, assert
+		// that they match expectations. asserts will be removed to
+		// avoid overhead in NDEBUG builds.
+		if (alloc) {
+			RC_CHK_ACCESS(adjusted[pmu_snc])->map[idx].cpu = cpu.cpu + cpu_adjust;
+		} else if (idx == 0) {
+			cpu_adjust = perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu - cpu.cpu;
+			assert(uncore_cha_imc_compute_cpu_adjust(pmu_snc) == cpu_adjust);
+		} else {
+			assert(perf_cpu_map__cpu(adjusted[pmu_snc], idx).cpu ==
+			       cpu.cpu + cpu_adjust);
+		}
+	}
+
+	perf_cpu_map__put(pmu->cpus);
+	pmu->cpus = perf_cpu_map__get(adjusted[pmu_snc]);
+}
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	struct perf_pmu_caps *ldlat_cap;
+
 #ifdef HAVE_AUXTRACE_SUPPORT
 	if (!strcmp(pmu->name, INTEL_PT_PMU_NAME)) {
 		pmu->auxtrace = true;
@@ -33,12 +286,31 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 #endif
 
 	if (x86__is_amd_cpu()) {
-		if (!strcmp(pmu->name, "ibs_op"))
-			pmu->mem_events = perf_mem_events_amd;
-	} else if (pmu->is_core) {
-		if (perf_pmu__have_event(pmu, "mem-loads-aux"))
-			pmu->mem_events = perf_mem_events_intel_aux;
-		else
-			pmu->mem_events = perf_mem_events_intel;
+		if (strcmp(pmu->name, "ibs_op"))
+			return;
+
+		pmu->mem_events = perf_mem_events_amd;
+
+		if (!perf_pmu__caps_parse(pmu))
+			return;
+
+		ldlat_cap = perf_pmu__get_cap(pmu, "ldlat");
+		if (!ldlat_cap || strcmp(ldlat_cap->value, "1"))
+			return;
+
+		perf_mem_events__loads_ldlat = 0;
+		pmu->mem_events = perf_mem_events_amd_ldlat;
+	} else {
+		if (pmu->is_core) {
+			if (perf_pmu__have_event(pmu, "mem-loads-aux"))
+				pmu->mem_events = perf_mem_events_intel_aux;
+			else
+				pmu->mem_events = perf_mem_events_intel;
+		} else if (x86__is_intel_graniterapids()) {
+			if (starts_with(pmu->name, "uncore_cha_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/true);
+			else if (starts_with(pmu->name, "uncore_imc_"))
+				gnr_uncore_cha_imc_adjust_cpumask_for_snc(pmu, /*cha=*/false);
+		}
 	}
 }
diff --git a/tools/perf/arch/x86/util/topdown.c b/tools/perf/arch/x86/util/topdown.c
index 3f9a267d4501..d1c654839049 100644
--- a/tools/perf/arch/x86/util/topdown.c
+++ b/tools/perf/arch/x86/util/topdown.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 #include "api/fs/fs.h"
 #include "util/evsel.h"
+#include "util/evlist.h"
 #include "util/pmu.h"
 #include "util/pmus.h"
 #include "util/topdown.h"
@@ -32,6 +33,31 @@ bool topdown_sys_has_perf_metrics(void)
 }
 
 #define TOPDOWN_SLOTS		0x0400
+bool arch_is_topdown_slots(const struct evsel *evsel)
+{
+	if (evsel->core.attr.config == TOPDOWN_SLOTS)
+		return true;
+
+	return false;
+}
+
+bool arch_is_topdown_metrics(const struct evsel *evsel)
+{
+	int config = evsel->core.attr.config;
+	const char *name_from_config;
+	struct perf_pmu *pmu;
+
+	/* All topdown events have an event code of 0. */
+	if ((config & 0xFF) != 0)
+		return false;
+
+	pmu = evsel__find_pmu(evsel);
+	if (!pmu || !pmu->is_core)
+		return false;
+
+	name_from_config = perf_pmu__name_from_config(pmu, config);
+	return name_from_config && strcasestr(name_from_config, "topdown");
+}
 
 /*
  * Check whether a topdown group supports sample-read.
@@ -41,11 +67,24 @@ bool topdown_sys_has_perf_metrics(void)
  */
 bool arch_topdown_sample_read(struct evsel *leader)
 {
+	struct evsel *evsel;
+
 	if (!evsel__sys_has_perf_metrics(leader))
 		return false;
 
-	if (leader->core.attr.config == TOPDOWN_SLOTS)
-		return true;
+	if (!arch_is_topdown_slots(leader))
+		return false;
+
+	/*
+	 * If slots event as leader event but no topdown metric events
+	 * in group, slots event should still sample as leader.
+	 */
+	evlist__for_each_entry(leader->evlist, evsel) {
+		if (evsel->core.leader != leader->core.leader)
+			continue;
+		if (evsel != leader && arch_is_topdown_metrics(evsel))
+			return true;
+	}
 
 	return false;
 }
diff --git a/tools/perf/arch/x86/util/topdown.h b/tools/perf/arch/x86/util/topdown.h
index 46bf9273e572..1bae9b1822d7 100644
--- a/tools/perf/arch/x86/util/topdown.h
+++ b/tools/perf/arch/x86/util/topdown.h
@@ -3,5 +3,7 @@
 #define _TOPDOWN_H 1
 
 bool topdown_sys_has_perf_metrics(void);
+bool arch_is_topdown_slots(const struct evsel *evsel);
+bool arch_is_topdown_metrics(const struct evsel *evsel);
 
 #endif
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index e2d6cfe21057..3a439e4b12d2 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -24,9 +24,9 @@ u64 rdtsc(void)
  * ...
  * will return 3000000000.
  */
-static double cpuinfo_tsc_freq(void)
+static u64 cpuinfo_tsc_freq(void)
 {
-	double result = 0;
+	u64 result = 0;
 	FILE *cpuinfo;
 	char *line = NULL;
 	size_t len = 0;
@@ -34,20 +34,22 @@ static double cpuinfo_tsc_freq(void)
 	cpuinfo = fopen("/proc/cpuinfo", "r");
 	if (!cpuinfo) {
 		pr_err("Failed to read /proc/cpuinfo for TSC frequency\n");
-		return NAN;
+		return 0;
 	}
 	while (getline(&line, &len, cpuinfo) > 0) {
 		if (!strncmp(line, "model name", 10)) {
 			char *pos = strstr(line + 11, " @ ");
+			double float_result;
 
-			if (pos && sscanf(pos, " @ %lfGHz", &result) == 1) {
-				result *= 1000000000;
+			if (pos && sscanf(pos, " @ %lfGHz", &float_result) == 1) {
+				float_result *= 1000000000;
+				result = (u64)float_result;
 				goto out;
 			}
 		}
 	}
 out:
-	if (fpclassify(result) == FP_ZERO)
+	if (result == 0)
 		pr_err("Failed to find TSC frequency in /proc/cpuinfo\n");
 
 	free(line);
@@ -55,7 +57,7 @@ out:
 	return result;
 }
 
-double arch_get_tsc_freq(void)
+u64 arch_get_tsc_freq(void)
 {
 	unsigned int a, b, c, d, lvl;
 	static bool cached;
@@ -86,6 +88,6 @@ double arch_get_tsc_freq(void)
 		return tsc;
 	}
 
-	tsc = (double)c * (double)b / (double)a;
+	tsc = (u64)c * (u64)b / (u64)a;
 	return tsc;
 }
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
index edb77e20e083..798493e887d7 100644
--- a/tools/perf/arch/x86/util/unwind-libdw.c
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -8,7 +8,7 @@
 bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
 {
 	struct unwind_info *ui = arg;
-	struct regs_dump *user_regs = &ui->sample->user_regs;
+	struct regs_dump *user_regs = perf_sample__user_regs(ui->sample);
 	Dwarf_Word dwarf_regs[17];
 	unsigned nregs;