18 files changed, 144 insertions, 187 deletions

diff --git a/tools/perf/arch/arm/include/arch-tests.h b/tools/perf/arch/arm/include/arch-tests.h
index 90ec4c8cb880..c62538052404 100644
--- a/tools/perf/arch/arm/include/arch-tests.h
+++ b/tools/perf/arch/arm/include/arch-tests.h
@@ -2,11 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-#endif
-
 extern struct test arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index d942f118d32c..85168d87b2d7 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -38,8 +38,6 @@ struct cs_etm_recording {
 	struct auxtrace_record	itr;
 	struct perf_pmu		*cs_etm_pmu;
 	struct evlist		*evlist;
-	int			wrapped_cnt;
-	bool			*wrapped;
 	bool			snapshot_mode;
 	size_t			snapshot_size;
 };
@@ -734,135 +732,6 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	return 0;
 }
 
-static int cs_etm_alloc_wrapped_array(struct cs_etm_recording *ptr, int idx)
-{
-	bool *wrapped;
-	int cnt = ptr->wrapped_cnt;
-
-	/* Make @ptr->wrapped as big as @idx */
-	while (cnt <= idx)
-		cnt++;
-
-	/*
-	 * Free'ed in cs_etm_recording_free().  Using realloc() to avoid
-	 * cross compilation problems where the host's system supports
-	 * reallocarray() but not the target.
-	 */
-	wrapped = realloc(ptr->wrapped, cnt * sizeof(bool));
-	if (!wrapped)
-		return -ENOMEM;
-
-	wrapped[cnt - 1] = false;
-	ptr->wrapped_cnt = cnt;
-	ptr->wrapped = wrapped;
-
-	return 0;
-}
-
-static bool cs_etm_buffer_has_wrapped(unsigned char *buffer,
-				      size_t buffer_size, u64 head)
-{
-	u64 i, watermark;
-	u64 *buf = (u64 *)buffer;
-	size_t buf_size = buffer_size;
-
-	/*
-	 * We want to look the very last 512 byte (chosen arbitrarily) in
-	 * the ring buffer.
-	 */
-	watermark = buf_size - 512;
-
-	/*
-	 * @head is continuously increasing - if its value is equal or greater
-	 * than the size of the ring buffer, it has wrapped around.
-	 */
-	if (head >= buffer_size)
-		return true;
-
-	/*
-	 * The value of @head is somewhere within the size of the ring buffer.
-	 * This can be that there hasn't been enough data to fill the ring
-	 * buffer yet or the trace time was so long that @head has numerically
-	 * wrapped around.  To find we need to check if we have data at the very
-	 * end of the ring buffer.  We can reliably do this because mmap'ed
-	 * pages are zeroed out and there is a fresh mapping with every new
-	 * session.
-	 */
-
-	/* @head is less than 512 byte from the end of the ring buffer */
-	if (head > watermark)
-		watermark = head;
-
-	/*
-	 * Speed things up by using 64 bit transactions (see "u64 *buf" above)
-	 */
-	watermark >>= 3;
-	buf_size >>= 3;
-
-	/*
-	 * If we find trace data at the end of the ring buffer, @head has
-	 * been there and has numerically wrapped around at least once.
-	 */
-	for (i = watermark; i < buf_size; i++)
-		if (buf[i])
-			return true;
-
-	return false;
-}
-
-static int cs_etm_find_snapshot(struct auxtrace_record *itr,
-				int idx, struct auxtrace_mmap *mm,
-				unsigned char *data,
-				u64 *head, u64 *old)
-{
-	int err;
-	bool wrapped;
-	struct cs_etm_recording *ptr =
-			container_of(itr, struct cs_etm_recording, itr);
-
-	/*
-	 * Allocate memory to keep track of wrapping if this is the first
-	 * time we deal with this *mm.
-	 */
-	if (idx >= ptr->wrapped_cnt) {
-		err = cs_etm_alloc_wrapped_array(ptr, idx);
-		if (err)
-			return err;
-	}
-
-	/*
-	 * Check to see if *head has wrapped around.  If it hasn't only the
-	 * amount of data between *head and *old is snapshot'ed to avoid
-	 * bloating the perf.data file with zeros.  But as soon as *head has
-	 * wrapped around the entire size of the AUX ring buffer it taken.
-	 */
-	wrapped = ptr->wrapped[idx];
-	if (!wrapped && cs_etm_buffer_has_wrapped(data, mm->len, *head)) {
-		wrapped = true;
-		ptr->wrapped[idx] = true;
-	}
-
-	pr_debug3("%s: mmap index %d old head %zu new head %zu size %zu\n",
-		  __func__, idx, (size_t)*old, (size_t)*head, mm->len);
-
-	/* No wrap has occurred, we can just use *head and *old. */
-	if (!wrapped)
-		return 0;
-
-	/*
-	 * *head has wrapped around - adjust *head and *old to pickup the
-	 * entire content of the AUX buffer.
-	 */
-	if (*head >= mm->len) {
-		*old = *head - mm->len;
-	} else {
-		*head += mm->len;
-		*old = *head - mm->len;
-	}
-
-	return 0;
-}
-
 static int cs_etm_snapshot_start(struct auxtrace_record *itr)
 {
 	struct cs_etm_recording *ptr =
@@ -900,7 +769,6 @@ static void cs_etm_recording_free(struct auxtrace_record *itr)
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 
-	zfree(&ptr->wrapped);
 	free(ptr);
 }
 
@@ -928,7 +796,6 @@ struct auxtrace_record *cs_etm_record_init(int *err)
 	ptr->itr.recording_options	= cs_etm_recording_options;
 	ptr->itr.info_priv_size		= cs_etm_info_priv_size;
 	ptr->itr.info_fill		= cs_etm_info_fill;
-	ptr->itr.find_snapshot		= cs_etm_find_snapshot;
 	ptr->itr.snapshot_start		= cs_etm_snapshot_start;
 	ptr->itr.snapshot_finish	= cs_etm_snapshot_finish;
 	ptr->itr.reference		= cs_etm_reference;
diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h
index 90ec4c8cb880..c62538052404 100644
--- a/tools/perf/arch/arm64/include/arch-tests.h
+++ b/tools/perf/arch/arm64/include/arch-tests.h
@@ -2,11 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-#endif
-
 extern struct test arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 414c8a5584b1..a4420d4df503 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -14,6 +14,7 @@
 #include "../../../util/cpumap.h"
 #include "../../../util/event.h"
 #include "../../../util/evsel.h"
+#include "../../../util/evsel_config.h"
 #include "../../../util/evlist.h"
 #include "../../../util/session.h"
 #include <internal/lib.h> // page_size
@@ -32,6 +33,29 @@ struct arm_spe_recording {
 	struct evlist		*evlist;
 };
 
+static void arm_spe_set_timestamp(struct auxtrace_record *itr,
+				  struct evsel *evsel)
+{
+	struct arm_spe_recording *ptr;
+	struct perf_pmu *arm_spe_pmu;
+	struct evsel_config_term *term = evsel__get_config_term(evsel, CFG_CHG);
+	u64 user_bits = 0, bit;
+
+	ptr = container_of(itr, struct arm_spe_recording, itr);
+	arm_spe_pmu = ptr->arm_spe_pmu;
+
+	if (term)
+		user_bits = term->val.cfg_chg;
+
+	bit = perf_pmu__format_bits(&arm_spe_pmu->format, "ts_enable");
+
+	/* Skip if user has set it */
+	if (bit & user_bits)
+		return;
+
+	evsel->core.attr.config |= bit;
+}
+
 static size_t
 arm_spe_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		       struct evlist *evlist __maybe_unused)
@@ -68,6 +92,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 			container_of(itr, struct arm_spe_recording, itr);
 	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
 	struct evsel *evsel, *arm_spe_evsel = NULL;
+	struct perf_cpu_map *cpus = evlist->core.cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
@@ -91,7 +116,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		return 0;
 
 	/* We are in full trace mode but '-m,xyz' wasn't specified */
-	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+	if (!opts->auxtrace_mmap_pages) {
 		if (privileged) {
 			opts->auxtrace_mmap_pages = MiB(4) / page_size;
 		} else {
@@ -120,9 +145,14 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 */
 	evlist__to_front(evlist, arm_spe_evsel);
 
-	evsel__set_sample_bit(arm_spe_evsel, CPU);
-	evsel__set_sample_bit(arm_spe_evsel, TIME);
-	evsel__set_sample_bit(arm_spe_evsel, TID);
+	/*
+	 * In the case of per-cpu mmaps, sample CPU for AUX event;
+	 * also enable the timestamp tracing for samples correlation.
+	 */
+	if (!perf_cpu_map__empty(cpus)) {
+		evsel__set_sample_bit(arm_spe_evsel, CPU);
+		arm_spe_set_timestamp(itr, arm_spe_evsel);
+	}
 
 	/* Add dummy event to keep tracking */
 	err = parse_events(evlist, "dummy:u", NULL);
@@ -134,9 +164,10 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 
 	tracking_evsel->core.attr.freq = 0;
 	tracking_evsel->core.attr.sample_period = 1;
-	evsel__set_sample_bit(tracking_evsel, TIME);
-	evsel__set_sample_bit(tracking_evsel, CPU);
-	evsel__reset_sample_bit(tracking_evsel, BRANCH_STACK);
+
+	/* In per-cpu case, always need the time of mmap events etc */
+	if (!perf_cpu_map__empty(cpus))
+		evsel__set_sample_bit(tracking_evsel, TIME);
 
 	return 0;
 }
diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c
index 2a2497372671..be41721b9aa1 100644
--- a/tools/perf/arch/arm64/util/mem-events.c
+++ b/tools/perf/arch/arm64/util/mem-events.c
@@ -20,7 +20,7 @@ struct perf_mem_event *perf_mem_events__ptr(int i)
 	return &perf_mem_events[i];
 }
 
-char *perf_mem_events__name(int i)
+char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 
diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
index 9cd1c34f31b5..ac653d08b1ea 100644
--- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
+++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl
@@ -357,7 +357,7 @@
 440	n64	process_madvise			sys_process_madvise
 441	n64	epoll_pwait2			sys_epoll_pwait2
 442	n64	mount_setattr			sys_mount_setattr
-# 443 reserved for quotactl_path
+443	n64	quotactl_fd			sys_quotactl_fd
 444	n64	landlock_create_ruleset		sys_landlock_create_ruleset
 445	n64	landlock_add_rule		sys_landlock_add_rule
 446	n64	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
index 8f052ff4058c..aef2a290e71a 100644
--- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl
@@ -522,7 +522,7 @@
 440	common	process_madvise			sys_process_madvise
 441	common	epoll_pwait2			sys_epoll_pwait2		compat_sys_epoll_pwait2
 442	common	mount_setattr			sys_mount_setattr
-# 443 reserved for quotactl_path
+443	common	quotactl_fd			sys_quotactl_fd
 444	common	landlock_create_ruleset		sys_landlock_create_ruleset
 445	common	landlock_add_rule		sys_landlock_add_rule
 446	common	landlock_restrict_self		sys_landlock_restrict_self
diff --git a/tools/perf/arch/powerpc/include/arch-tests.h b/tools/perf/arch/powerpc/include/arch-tests.h
index 1c7be75cbc78..c62538052404 100644
--- a/tools/perf/arch/powerpc/include/arch-tests.h
+++ b/tools/perf/arch/powerpc/include/arch-tests.h
@@ -2,13 +2,6 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-int test__arch_unwind_sample(struct perf_sample *sample,
-			     struct thread *thread);
-#endif
-
 extern struct test arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/powerpc/tests/dwarf-unwind.c b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
index 8efd9ed9e9db..c9cb4b059392 100644
--- a/tools/perf/arch/powerpc/tests/dwarf-unwind.c
+++ b/tools/perf/arch/powerpc/tests/dwarf-unwind.c
@@ -7,7 +7,6 @@
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
-#include "arch-tests.h"
 
 #define STACK_SIZE 8192
 
diff --git a/tools/perf/arch/powerpc/util/mem-events.c b/tools/perf/arch/powerpc/util/mem-events.c
index 07fb5e049488..4120fafe0be4 100644
--- a/tools/perf/arch/powerpc/util/mem-events.c
+++ b/tools/perf/arch/powerpc/util/mem-events.c
@@ -3,7 +3,7 @@
 #include "mem-events.h"
 
 /* PowerPC does not support 'ldlat' parameter. */
-char *perf_mem_events__name(int i)
+char *perf_mem_events__name(int i, char *pmu_name __maybe_unused)
 {
 	if (i == PERF_MEM_EVENTS__LOAD)
 		return (char *) "cpu/mem-loads/";
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
index 0690263df1dd..64d51ab5a8b4 100644
--- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -445,7 +445,7 @@
 440  common	process_madvise		sys_process_madvise		sys_process_madvise
 441  common	epoll_pwait2		sys_epoll_pwait2		compat_sys_epoll_pwait2
 442  common	mount_setattr		sys_mount_setattr		sys_mount_setattr
-# 443 reserved for quotactl_path
+443  common	quotactl_fd		sys_quotactl_fd			sys_quotactl_fd
 444  common	landlock_create_ruleset	sys_landlock_create_ruleset	sys_landlock_create_ruleset
 445  common	landlock_add_rule	sys_landlock_add_rule		sys_landlock_add_rule
 446  common	landlock_restrict_self	sys_landlock_restrict_self	sys_landlock_restrict_self
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index ce18119ea0d0..af973e400053 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -364,7 +364,7 @@
 440	common	process_madvise		sys_process_madvise
 441	common	epoll_pwait2		sys_epoll_pwait2
 442	common	mount_setattr		sys_mount_setattr
-# 443 reserved for quotactl_path
+443	common	quotactl_fd		sys_quotactl_fd
 444	common	landlock_create_ruleset	sys_landlock_create_ruleset
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
diff --git a/tools/perf/arch/x86/include/arch-tests.h b/tools/perf/arch/x86/include/arch-tests.h
index 0e20f3dc69f3..9599e7a3f1af 100644
--- a/tools/perf/arch/x86/include/arch-tests.h
+++ b/tools/perf/arch/x86/include/arch-tests.h
@@ -2,23 +2,15 @@
 #ifndef ARCH_TESTS_H
 #define ARCH_TESTS_H
 
-#include <linux/compiler.h>
 struct test;
 
 /* Tests */
-int test__rdpmc(struct test *test __maybe_unused, int subtest);
-int test__insn_x86(struct test *test __maybe_unused, int subtest);
+int test__rdpmc(struct test *test, int subtest);
+int test__insn_x86(struct test *test, int subtest);
 int test__intel_pt_pkt_decoder(struct test *test, int subtest);
 int test__bp_modify(struct test *test, int subtest);
 int test__x86_sample_parsing(struct test *test, int subtest);
 
-#ifdef HAVE_DWARF_UNWIND_SUPPORT
-struct thread;
-struct perf_sample;
-int test__arch_unwind_sample(struct perf_sample *sample,
-			     struct thread *thread);
-#endif
-
 extern struct test arch_tests[];
 
 #endif
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
index 478078fb0f22..a54dea7c112f 100644
--- a/tools/perf/arch/x86/tests/dwarf-unwind.c
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -7,7 +7,6 @@
 #include "event.h"
 #include "debug.h"
 #include "tests/tests.h"
-#include "arch-tests.h"
 
 #define STACK_SIZE 8192
 
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 8c6732cc7794..0b0951030a2f 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -5,11 +5,15 @@
 #include "util/parse-events.h"
 
 #define TOPDOWN_L1_EVENTS	"{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound}"
+#define TOPDOWN_L2_EVENTS	"{slots,topdown-retiring,topdown-bad-spec,topdown-fe-bound,topdown-be-bound,topdown-heavy-ops,topdown-br-mispredict,topdown-fetch-lat,topdown-mem-bound}"
 
 int arch_evlist__add_default_attrs(struct evlist *evlist)
 {
 	if (!pmu_have_event("cpu", "slots"))
 		return 0;
 
-	return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
+	if (pmu_have_event("cpu", "topdown-heavy-ops"))
+		return parse_events(evlist, TOPDOWN_L2_EVENTS, NULL);
+	else
+		return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
 }
diff --git a/tools/perf/arch/x86/util/iostat.c b/tools/perf/arch/x86/util/iostat.c
index d63acb782b63..eeafe97b8105 100644
--- a/tools/perf/arch/x86/util/iostat.c
+++ b/tools/perf/arch/x86/util/iostat.c
@@ -322,7 +322,7 @@ static int iostat_event_group(struct evlist *evl,
 	}
 
 	evlist__for_each_entry(evl, evsel) {
-		evsel->priv = list->rps[evsel->idx / metrics_count];
+		evsel->priv = list->rps[evsel->core.idx / metrics_count];
 	}
 	list->nr_entries = 0;
 err:
@@ -428,7 +428,7 @@ void iostat_print_metric(struct perf_stat_config *config, struct evsel *evsel,
 {
 	double iostat_value = 0;
 	u64 prev_count_val = 0;
-	const char *iostat_metric = iostat_metric_by_idx(evsel->idx);
+	const char *iostat_metric = iostat_metric_by_idx(evsel->core.idx);
 	u8 die = ((struct iio_root_port *)evsel->priv)->die;
 	struct perf_counts_values *count = perf_counts(evsel->counts, die, 0);
 
diff --git a/tools/perf/arch/x86/util/kvm-stat.c b/tools/perf/arch/x86/util/kvm-stat.c
index 072920475b65..c5dd54f6ef5e 100644
--- a/tools/perf/arch/x86/util/kvm-stat.c
+++ b/tools/perf/arch/x86/util/kvm-stat.c
@@ -133,11 +133,56 @@ static struct kvm_events_ops ioport_events = {
 	.name = "IO Port Access"
 };
 
+ /* The time of emulation msr is from kvm_msr to kvm_entry. */
+static void msr_event_get_key(struct evsel *evsel,
+				 struct perf_sample *sample,
+				 struct event_key *key)
+{
+	key->key  = evsel__intval(evsel, sample, "ecx");
+	key->info = evsel__intval(evsel, sample, "write");
+}
+
+static bool msr_event_begin(struct evsel *evsel,
+			       struct perf_sample *sample,
+			       struct event_key *key)
+{
+	if (!strcmp(evsel->name, "kvm:kvm_msr")) {
+		msr_event_get_key(evsel, sample, key);
+		return true;
+	}
+
+	return false;
+}
+
+static bool msr_event_end(struct evsel *evsel,
+			     struct perf_sample *sample __maybe_unused,
+			     struct event_key *key __maybe_unused)
+{
+	return kvm_entry_event(evsel);
+}
+
+static void msr_event_decode_key(struct perf_kvm_stat *kvm __maybe_unused,
+				    struct event_key *key,
+				    char *decode)
+{
+	scnprintf(decode, decode_str_len, "%#llx:%s",
+		  (unsigned long long)key->key,
+		  key->info ? "W" : "R");
+}
+
+static struct kvm_events_ops msr_events = {
+	.is_begin_event = msr_event_begin,
+	.is_end_event = msr_event_end,
+	.decode_key = msr_event_decode_key,
+	.name = "MSR Access"
+};
+
 const char *kvm_events_tp[] = {
 	"kvm:kvm_entry",
 	"kvm:kvm_exit",
 	"kvm:kvm_mmio",
 	"kvm:kvm_pio",
+	"kvm:kvm_msr",
 	NULL,
 };
 
@@ -145,6 +190,7 @@ struct kvm_reg_events_ops kvm_reg_events_ops[] = {
 	{ .name = "vmexit", .ops = &exit_events },
 	{ .name = "mmio", .ops = &mmio_events },
 	{ .name = "ioport", .ops = &ioport_events },
+	{ .name = "msr", .ops = &msr_events },
 	{ NULL, NULL },
 };
 
diff --git a/tools/perf/arch/x86/util/mem-events.c b/tools/perf/arch/x86/util/mem-events.c
index 588110fd8904..5214370ca4e4 100644
--- a/tools/perf/arch/x86/util/mem-events.c
+++ b/tools/perf/arch/x86/util/mem-events.c
@@ -5,19 +5,41 @@
 
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
+static char mem_stores_name[100];
 
 #define MEM_LOADS_AUX		0x8203
-#define MEM_LOADS_AUX_NAME	"{cpu/mem-loads-aux/,cpu/mem-loads,ldlat=%u/pp}:S"
+#define MEM_LOADS_AUX_NAME     "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P"
+
+#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+
+static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads"),
+	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores"),
+	E(NULL,			NULL,				NULL),
+};
+
+struct perf_mem_event *perf_mem_events__ptr(int i)
+{
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	return &perf_mem_events[i];
+}
 
 bool is_mem_loads_aux_event(struct evsel *leader)
 {
-	if (!pmu_have_event("cpu", "mem-loads-aux"))
-		return false;
+	if (perf_pmu__find("cpu")) {
+		if (!pmu_have_event("cpu", "mem-loads-aux"))
+			return false;
+	} else if (perf_pmu__find("cpu_core")) {
+		if (!pmu_have_event("cpu_core", "mem-loads-aux"))
+			return false;
+	}
 
 	return leader->core.attr.config == MEM_LOADS_AUX;
 }
 
-char *perf_mem_events__name(int i)
+char *perf_mem_events__name(int i, char *pmu_name)
 {
 	struct perf_mem_event *e = perf_mem_events__ptr(i);
 
@@ -25,20 +47,34 @@ char *perf_mem_events__name(int i)
 		return NULL;
 
 	if (i == PERF_MEM_EVENTS__LOAD) {
-		if (mem_loads_name__init)
+		if (mem_loads_name__init && !pmu_name)
 			return mem_loads_name;
 
-		mem_loads_name__init = true;
+		if (!pmu_name) {
+			mem_loads_name__init = true;
+			pmu_name = (char *)"cpu";
+		}
 
-		if (pmu_have_event("cpu", "mem-loads-aux")) {
+		if (pmu_have_event(pmu_name, "mem-loads-aux")) {
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  MEM_LOADS_AUX_NAME, perf_mem_events__loads_ldlat);
+				  MEM_LOADS_AUX_NAME, pmu_name, pmu_name,
+				  perf_mem_events__loads_ldlat);
 		} else {
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  e->name, perf_mem_events__loads_ldlat);
+				  e->name, pmu_name,
+				  perf_mem_events__loads_ldlat);
 		}
 		return mem_loads_name;
 	}
 
+	if (i == PERF_MEM_EVENTS__STORE) {
+		if (!pmu_name)
+			pmu_name = (char *)"cpu";
+
+		scnprintf(mem_stores_name, sizeof(mem_stores_name),
+			  e->name, pmu_name);
+		return mem_stores_name;
+	}
+
 	return (char *)e->name;
 }