diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt
index d3740c8f399bac1a03b75cc8484a40d21080fb60..079cdfabb35202968d44322ef7b49eb09504ea1f 100644
--- a/tools/perf/Documentation/itrace.txt
+++ b/tools/perf/Documentation/itrace.txt
@@ -11,6 +11,7 @@
 		d	create a debug log
 		f	synthesize first level cache events
 		m	synthesize last level cache events
+		M	synthesize memory events
 		t	synthesize TLB events
 		a	synthesize remote access events
 		g	synthesize a call chain (use with i or x)
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index b53294d74b0112de881d80842381556cad6f0d79..cf6d7e799f3315851e4a45dfd8af18642db66314 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -9,4 +9,4 @@ perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 perf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
 			      ../../arm/util/cs-etm.o \
-			      arm-spe.o
+			      arm-spe.o mem-events.o
diff --git a/tools/perf/arch/arm64/util/mem-events.c b/tools/perf/arch/arm64/util/mem-events.c
new file mode 100644
index 0000000000000000000000000000000000000000..2a24973726712c0697a6a8319ac615b32fd1cd59
--- /dev/null
+++ b/tools/perf/arch/arm64/util/mem-events.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "map_symbol.h"
+#include "mem-events.h"
+
+#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("spe-load",	"arm_spe_0/ts_enable=1,load_filter=1,store_filter=0,min_latency=%u/",	"arm_spe_0"),
+	E("spe-store",	"arm_spe_0/ts_enable=1,load_filter=0,store_filter=1/",			"arm_spe_0"),
+	E("spe-ldst",	"arm_spe_0/ts_enable=1,load_filter=1,store_filter=1,min_latency=%u/",	"arm_spe_0"),
+};
+
+static char mem_ev_name[100];
+
+struct perf_mem_event *perf_mem_events__ptr(int i)
+{
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	return &perf_mem_events[i];
+}
+
+char *perf_mem_events__name(int i)
+{
+	struct perf_mem_event *e = perf_mem_events__ptr(i);
+
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE)
+		scnprintf(mem_ev_name, sizeof(mem_ev_name),
+			  e->name, perf_mem_events__loads_ldlat);
+	else /* PERF_MEM_EVENTS__STORE */
+		scnprintf(mem_ev_name, sizeof(mem_ev_name), e->name);
+
+	return mem_ev_name;
+}
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 5a3b0bf455f4abc13f6828991084f7747c7af84e..a693abdfa9ee2db0c91dfe67708ae674e0ad569c 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -3048,6 +3048,7 @@ static int perf_c2c__record(int argc, const char **argv)
 	int ret;
 	bool all_user = false, all_kernel = false;
 	bool event_set = false;
+	struct perf_mem_event *e;
 	struct option options[] = {
 	OPT_CALLBACK('e', "event", &event_set, "event",
 		     "event selector. Use 'perf c2c record -e list' to list available events",
@@ -3075,11 +3076,15 @@ static int perf_c2c__record(int argc, const char **argv)
 	rec_argv[i++] = "record";
 
 	if (!event_set) {
-		perf_mem_events[PERF_MEM_EVENTS__LOAD].record  = true;
-		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+		e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+		e->record = true;
+
+		e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE);
+		e->record = true;
 	}
 
-	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
+	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+	if (e->record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
@@ -3087,12 +3092,13 @@ static int perf_c2c__record(int argc, const char **argv)
 	rec_argv[i++] = "--sample-cpu";
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		if (!perf_mem_events[j].record)
+		e = perf_mem_events__ptr(j);
+		if (!e->record)
 			continue;
 
-		if (!perf_mem_events[j].supported) {
+		if (!e->supported) {
 			pr_err("failed: event '%s' not supported\n",
-			       perf_mem_events[j].name);
+			       perf_mem_events__name(j));
 			free(rec_argv);
 			return -1;
 		}
diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
index 3523279af6afff7b9a804a8dcb68721a0218cbf2..fdfbff7592f4343dce3ee698558d55a14b895ffe 100644
--- a/tools/perf/builtin-mem.c
+++ b/tools/perf/builtin-mem.c
@@ -7,6 +7,7 @@
 #include "perf.h"
 
 #include <subcmd/parse-options.h>
+#include "util/auxtrace.h"
 #include "util/trace-event.h"
 #include "util/tool.h"
 #include "util/session.h"
@@ -64,6 +65,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	const char **rec_argv;
 	int ret;
 	bool all_user = false, all_kernel = false;
+	struct perf_mem_event *e;
 	struct option options[] = {
 	OPT_CALLBACK('e', "event", &mem, "event",
 		     "event selector. use 'perf mem record -e list' to list available events",
@@ -76,6 +78,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 	OPT_END()
 	};
 
+	if (perf_mem_events__init()) {
+		pr_err("failed: memory events not supported\n");
+		return -1;
+	}
+
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
@@ -86,13 +93,30 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 
 	rec_argv[i++] = "record";
 
-	if (mem->operation & MEM_OPERATION_LOAD)
-		perf_mem_events[PERF_MEM_EVENTS__LOAD].record = true;
+	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD_STORE);
+
+	/*
+	 * The load and store operations are required, use the event
+	 * PERF_MEM_EVENTS__LOAD_STORE if it is supported.
+	 */
+	if (e->tag &&
+	    (mem->operation & MEM_OPERATION_LOAD) &&
+	    (mem->operation & MEM_OPERATION_STORE)) {
+		e->record = true;
+	} else {
+		if (mem->operation & MEM_OPERATION_LOAD) {
+			e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+			e->record = true;
+		}
 
-	if (mem->operation & MEM_OPERATION_STORE)
-		perf_mem_events[PERF_MEM_EVENTS__STORE].record = true;
+		if (mem->operation & MEM_OPERATION_STORE) {
+			e = perf_mem_events__ptr(PERF_MEM_EVENTS__STORE);
+			e->record = true;
+		}
+	}
 
-	if (perf_mem_events[PERF_MEM_EVENTS__LOAD].record)
+	e = perf_mem_events__ptr(PERF_MEM_EVENTS__LOAD);
+	if (e->record)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
@@ -101,10 +125,11 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
 		rec_argv[i++] = "--phys-data";
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		if (!perf_mem_events[j].record)
+		e = perf_mem_events__ptr(j);
+		if (!e->record)
 			continue;
 
-		if (!perf_mem_events[j].supported) {
+		if (!e->supported) {
 			pr_err("failed: event '%s' not supported\n",
 			       perf_mem_events__name(j));
 			free(rec_argv);
@@ -231,6 +256,12 @@ static int process_sample_event(struct perf_tool *tool,
 
 static int report_raw_events(struct perf_mem *mem)
 {
+	struct itrace_synth_opts itrace_synth_opts = {
+		.set = true,
+		.mem = true,	/* Only enable memory event */
+		.default_no_sample = true,
+	};
+
 	struct perf_data data = {
 		.path  = input_name,
 		.mode  = PERF_DATA_MODE_READ,
@@ -243,6 +274,8 @@ static int report_raw_events(struct perf_mem *mem)
 	if (IS_ERR(session))
 		return PTR_ERR(session);
 
+	session->itrace_synth_opts = &itrace_synth_opts;
+
 	if (mem->cpu_list) {
 		ret = perf_session__cpu_bitmap(session, mem->cpu_list,
 					       mem->cpu_bitmap);
@@ -386,8 +419,12 @@ int cmd_mem(int argc, const char **argv)
 			.comm		= perf_event__process_comm,
 			.lost		= perf_event__process_lost,
 			.fork		= perf_event__process_fork,
+			.attr		= perf_event__process_attr,
 			.build_id	= perf_event__process_build_id,
 			.namespaces	= perf_event__process_namespaces,
+			.auxtrace_info  = perf_event__process_auxtrace_info,
+			.auxtrace       = perf_event__process_auxtrace,
+			.auxtrace_error = perf_event__process_auxtrace_error,
 			.ordered_events	= true,
 		},
 		.input_name		 = "perf.data",
@@ -422,11 +459,6 @@ int cmd_mem(int argc, const char **argv)
 		NULL
 	};
 
-	if (perf_mem_events__init()) {
-		pr_err("failed: memory events not supported\n");
-		return -1;
-	}
-
 	argc = parse_options_subcommand(argc, argv, mem_options, mem_subcommands,
 					mem_usage, PARSE_OPT_KEEP_UNKNOWN);
 
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index d20250c2e7c460b5c458ab24448593a9d367da5e..f6377a3cab1620fe48351bd8a9ddb776a54bc07e 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -1329,6 +1329,7 @@ void itrace_synth_opts__set_default(struct itrace_synth_opts *synth_opts,
 	synth_opts->flc = true;
 	synth_opts->llc = true;
 	synth_opts->tlb = true;
+	synth_opts->mem = true;
 	synth_opts->remote_access = true;
 
 	if (no_sample) {
@@ -1550,6 +1551,9 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str,
 		case 'a':
 			synth_opts->remote_access = true;
 			break;
+		case 'M':
+			synth_opts->mem = true;
+			break;
 		case 'q':
 			synth_opts->quick += 1;
 			break;
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index da8f3df70e4bc201b241f7a3ce2ec20f05156684..bbaa06a769fbb739743e41fa965358ae725f84e4 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -88,6 +88,7 @@ enum itrace_period_type {
  * @llc: whether to synthesize last level cache events
  * @tlb: whether to synthesize TLB events
  * @remote_access: whether to synthesize remote access events
+ * @mem: whether to synthesize memory events
  * @callchain_sz: maximum callchain size
  * @last_branch_sz: branch context size
  * @period: 'instructions' events period
@@ -126,6 +127,7 @@ struct itrace_synth_opts {
 	bool			llc;
 	bool			tlb;
 	bool			remote_access;
+	bool			mem;
 	unsigned int		callchain_sz;
 	unsigned int		last_branch_sz;
 	unsigned long long	period;
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 211565e74d7bb0dad853e9b6784d005900ef5f96..b174591479bf52c989e7a929759b97310a404853 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -17,9 +17,10 @@ unsigned int perf_mem_events__loads_ldlat = 30;
 
 #define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
 
-struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"mem-loads"),
-	E("ldlat-stores",	"cpu/mem-stores/P",		"mem-stores"),
+static struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"cpu/mem-loads,ldlat=%u/P",	"cpu/events/mem-loads"),
+	E("ldlat-stores",	"cpu/mem-stores/P",		"cpu/events/mem-stores"),
+	E(NULL,			NULL,				NULL),
 };
 #undef E
 
@@ -28,19 +29,31 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
 static char mem_loads_name[100];
 static bool mem_loads_name__init;
 
+struct perf_mem_event * __weak perf_mem_events__ptr(int i)
+{
+	if (i >= PERF_MEM_EVENTS__MAX)
+		return NULL;
+
+	return &perf_mem_events[i];
+}
+
 char * __weak perf_mem_events__name(int i)
 {
+	struct perf_mem_event *e = perf_mem_events__ptr(i);
+
+	if (!e)
+		return NULL;
+
 	if (i == PERF_MEM_EVENTS__LOAD) {
 		if (!mem_loads_name__init) {
 			mem_loads_name__init = true;
 			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  perf_mem_events[i].name,
-				  perf_mem_events__loads_ldlat);
+				  e->name, perf_mem_events__loads_ldlat);
 		}
 		return mem_loads_name;
 	}
 
-	return (char *)perf_mem_events[i].name;
+	return (char *)e->name;
 }
 
 int perf_mem_events__parse(const char *str)
@@ -61,7 +74,10 @@ int perf_mem_events__parse(const char *str)
 
 	while (tok) {
 		for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-			struct perf_mem_event *e = &perf_mem_events[j];
+			struct perf_mem_event *e = perf_mem_events__ptr(j);
+
+			if (!e->tag)
+				continue;
 
 			if (strstr(e->tag, tok))
 				e->record = found = true;
@@ -90,10 +106,17 @@ int perf_mem_events__init(void)
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
 		char path[PATH_MAX];
-		struct perf_mem_event *e = &perf_mem_events[j];
+		struct perf_mem_event *e = perf_mem_events__ptr(j);
 		struct stat st;
 
-		scnprintf(path, PATH_MAX, "%s/devices/cpu/events/%s",
+		/*
+		 * If the event entry isn't valid, skip initialization
+		 * and "e->supported" will keep false.
+		 */
+		if (!e->tag)
+			continue;
+
+		scnprintf(path, PATH_MAX, "%s/devices/%s",
 			  mnt, e->sysfs_name);
 
 		if (!stat(path, &st))
@@ -108,10 +131,10 @@ void perf_mem_events__list(void)
 	int j;
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
-		struct perf_mem_event *e = &perf_mem_events[j];
+		struct perf_mem_event *e = perf_mem_events__ptr(j);
 
 		fprintf(stderr, "%-13s%-*s%s\n",
-			e->tag,
+			e->tag ?: "",
 			verbose > 0 ? 25 : 0,
 			verbose > 0 ? perf_mem_events__name(j) : "",
 			e->supported ? ": available" : "");
diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
index 13c198003a57c6aaffdc57576c9db09e25025148..4fb9870971e09b10217823e6f20f72cdccd9741a 100644
--- a/tools/perf/util/mem-events.h
+++ b/tools/perf/util/mem-events.h
@@ -28,16 +28,17 @@ struct mem_info {
 enum {
 	PERF_MEM_EVENTS__LOAD,
 	PERF_MEM_EVENTS__STORE,
+	PERF_MEM_EVENTS__LOAD_STORE,
 	PERF_MEM_EVENTS__MAX,
 };
 
-extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 extern unsigned int perf_mem_events__loads_ldlat;
 
 int perf_mem_events__parse(const char *str);
 int perf_mem_events__init(void);
 
 char *perf_mem_events__name(int i);
+struct perf_mem_event *perf_mem_events__ptr(int i);
 
 void perf_mem_events__list(void);
 
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
index c84f5841c7abd3bed305a06aea0274a91dc61ddc..03a7d7b2773774a0775fe3a6706d5bb029b711cc 100644
--- a/tools/perf/util/mem2node.c
+++ b/tools/perf/util/mem2node.c
@@ -96,7 +96,8 @@ int mem2node__init(struct mem2node *map, struct perf_env *env)
 
 	/* Cut unused entries, due to merging. */
 	tmp_entries = realloc(entries, sizeof(*entries) * j);
-	if (tmp_entries || WARN_ON_ONCE(j == 0))
+	if (tmp_entries ||
+	    WARN_ONCE(j == 0, "No memory nodes, is CONFIG_MEMORY_HOTPLUG enabled?\n"))
 		entries = tmp_entries;
 
 	for (i = 0; i < j; i++) {