perf mem: Clean up perf_mem_events__name()

Introduce a generic perf_mem_events__name(). Remove the ARCH-specific
one.

The mem_load events may have a different format. Add ldlat and aux_event
in the struct perf_mem_event to indicate the format and the extra aux
event.

Add perf_mem_events_intel_aux[] to support the extra mem_load_aux event.

Rename perf_mem_events__name to perf_pmu__mem_events_name.

Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ravi Bangoria <ravi.bangoria@amd.com>
Tested-by: Leo Yan <leo.yan@linaro.org>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: james.clark@arm.com
Cc: will@kernel.org
Cc: mike.leach@linaro.org
Cc: renyu.zj@linux.alibaba.com
Cc: yuhaixin.yhx@linux.alibaba.com
Cc: tmricht@linux.ibm.com
Cc: atrajeev@linux.vnet.ibm.com
Cc: linux-arm-kernel@lists.infradead.org
Cc: john.g.garry@oracle.com
Link: https://lore.kernel.org/r/20240123185036.3461837-4-kan.liang@linux.intel.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

tools/perf/arch/arm64/util/mem-events.c

@@ -3,28 +3,10 @@
 #include "util/mem-events.h"
 #include "mem-events.h"
 
-#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+#define E(t, n, s, l, a) { .tag = t, .name = n, .sysfs_name = s, .ldlat = l, .aux_event = a }
 
 struct perf_mem_event perf_mem_events_arm[PERF_MEM_EVENTS__MAX] = {
-	E("spe-load",	"arm_spe_0/ts_enable=1,pa_enable=1,load_filter=1,store_filter=0,min_latency=%u/",	"arm_spe_0"),
+	E("spe-load",	"%s/ts_enable=1,pa_enable=1,load_filter=1,store_filter=0,min_latency=%u/",	"arm_spe_0",	true,	0),
-	E("spe-store",	"arm_spe_0/ts_enable=1,pa_enable=1,load_filter=0,store_filter=1/",			"arm_spe_0"),
+	E("spe-store",	"%s/ts_enable=1,pa_enable=1,load_filter=0,store_filter=1/",			"arm_spe_0",	false,	0),
-	E("spe-ldst",	"arm_spe_0/ts_enable=1,pa_enable=1,load_filter=1,store_filter=1,min_latency=%u/",	"arm_spe_0"),
+	E("spe-ldst",	"%s/ts_enable=1,pa_enable=1,load_filter=1,store_filter=1,min_latency=%u/",	"arm_spe_0",	true,	0),
 };
-
-static char mem_ev_name[100];
-
-const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused)
-{
-	struct perf_mem_event *e = &perf_mem_events_arm[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;
-}

tools/perf/arch/powerpc/util/Build

@@ -2,6 +2,7 @@ perf-y += header.o
 perf-$(CONFIG_LIBTRACEEVENT) += kvm-stat.o
 perf-y += perf_regs.o
 perf-y += mem-events.o
+perf-y += pmu.o
 perf-y += sym-handling.o
 perf-y += evsel.o
 perf-y += event.o

tools/perf/arch/powerpc/util/mem-events.c

@@ -1,12 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-#include "map_symbol.h"
+#include "util/map_symbol.h"
+#include "util/mem-events.h"
 #include "mem-events.h"
 
-/* PowerPC does not support 'ldlat' parameter. */
+#define E(t, n, s, l, a) { .tag = t, .name = n, .sysfs_name = s, .ldlat = l, .aux_event = a }
-const char *perf_mem_events__name(int i, const char *pmu_name __maybe_unused)
-{
-	if (i == PERF_MEM_EVENTS__LOAD)
-		return "cpu/mem-loads/";
 
-	return "cpu/mem-stores/";
+struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX] = {
-}
+	E("ldlat-loads",	"%s/mem-loads/",	"cpu/events/mem-loads",		false,	0),
+	E("ldlat-stores",	"%s/mem-stores/",	"cpu/events/mem-stores",	false,	0),
+	E(NULL,			NULL,			NULL,				false,	0),
+};

tools/perf/arch/powerpc/util/mem-events.h

@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _POWER_MEM_EVENTS_H
+#define _POWER_MEM_EVENTS_H
+
+extern struct perf_mem_event perf_mem_events_power[PERF_MEM_EVENTS__MAX];
+
+#endif /* _POWER_MEM_EVENTS_H */

tools/perf/arch/powerpc/util/pmu.c

@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <string.h>
+
+#include "../../../util/pmu.h"
+#include "mem-events.h"
+
+void perf_pmu__arch_init(struct perf_pmu *pmu)
+{
+	if (pmu->is_core)
+		pmu->mem_events = perf_mem_events_power;
+}

tools/perf/arch/x86/util/mem-events.c

@@ -7,25 +7,26 @@
 #include "linux/string.h"
 #include "env.h"
 
-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     "{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P"
 
-#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+#define E(t, n, s, l, a) { .tag = t, .name = n, .sysfs_name = s, .ldlat = l, .aux_event = a }
 
 struct perf_mem_event perf_mem_events_intel[PERF_MEM_EVENTS__MAX] = {
-	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads"),
+	E("ldlat-loads",	"%s/mem-loads,ldlat=%u/P",	"%s/events/mem-loads",	true,	0),
-	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores"),
+	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores",	false,	0),
-	E(NULL,			NULL,				NULL),
+	E(NULL,			NULL,				NULL,			false,	0),
+};
+
+struct perf_mem_event perf_mem_events_intel_aux[PERF_MEM_EVENTS__MAX] = {
+	E("ldlat-loads",	"{%s/mem-loads-aux/,%s/mem-loads,ldlat=%u/}:P",	"%s/events/mem-loads",	true,	MEM_LOADS_AUX),
+	E("ldlat-stores",	"%s/mem-stores/P",		"%s/events/mem-stores",	false,	0),
+	E(NULL,			NULL,				NULL,			false,	0),
 };
 
 struct perf_mem_event perf_mem_events_amd[PERF_MEM_EVENTS__MAX] = {
-	E(NULL,		NULL,		NULL),
+	E(NULL,		NULL,		NULL,		false,	0),
-	E(NULL,		NULL,		NULL),
+	E(NULL,		NULL,		NULL,		false,	0),
-	E("mem-ldst",	"ibs_op//",	"ibs_op"),
+	E("mem-ldst",	"%s//",		"ibs_op",	false,	0),
 };
 
 bool is_mem_loads_aux_event(struct evsel *leader)
@@ -40,48 +41,3 @@ bool is_mem_loads_aux_event(struct evsel *leader)
 
 	return leader->core.attr.config == MEM_LOADS_AUX;
 }
-
-const char *perf_mem_events__name(int i, const char *pmu_name)
-{
-	struct perf_mem_event *e;
-
-	if (x86__is_amd_cpu())
-		e = &perf_mem_events_amd[i];
-	else
-		e = &perf_mem_events_intel[i];
-
-	if (!e)
-		return NULL;
-
-	if (i == PERF_MEM_EVENTS__LOAD) {
-		if (mem_loads_name__init && !pmu_name)
-			return mem_loads_name;
-
-		if (!pmu_name) {
-			mem_loads_name__init = true;
-			pmu_name = "cpu";
-		}
-
-		if (perf_pmus__have_event(pmu_name, "mem-loads-aux")) {
-			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  MEM_LOADS_AUX_NAME, pmu_name, pmu_name,
-				  perf_mem_events__loads_ldlat);
-		} else {
-			scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  e->name, pmu_name,
-				  perf_mem_events__loads_ldlat);
-		}
-		return mem_loads_name;
-	}
-
-	if (i == PERF_MEM_EVENTS__STORE) {
-		if (!pmu_name)
-			pmu_name = "cpu";
-
-		scnprintf(mem_stores_name, sizeof(mem_stores_name),
-			  e->name, pmu_name);
-		return mem_stores_name;
-	}
-
-	return e->name;
-}

tools/perf/arch/x86/util/mem-events.h

@@ -3,6 +3,7 @@
 #define _X86_MEM_EVENTS_H
 
 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];
 

tools/perf/arch/x86/util/pmu.c

@@ -35,8 +35,12 @@ void perf_pmu__arch_init(struct perf_pmu *pmu __maybe_unused)
 	if (x86__is_amd_cpu()) {
 		if (!strcmp(pmu->name, "ibs_op"))
 			pmu->mem_events = perf_mem_events_amd;
-	} else if (pmu->is_core)
+	} 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;
+	}
 }
 
 int perf_pmus__num_mem_pmus(void)

tools/perf/util/mem-events.c

@@ -17,17 +17,17 @@
 
 unsigned int perf_mem_events__loads_ldlat = 30;
 
-#define E(t, n, s) { .tag = t, .name = n, .sysfs_name = s }
+#define E(t, n, s, l, a) { .tag = t, .name = n, .sysfs_name = s, .ldlat = l, .aux_event = a }
 
 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-loads",	"%s/mem-loads,ldlat=%u/P",	"cpu/events/mem-loads",		true,	0),
-	E("ldlat-stores",	"cpu/mem-stores/P",		"cpu/events/mem-stores"),
+	E("ldlat-stores",	"%s/mem-stores/P",		"cpu/events/mem-stores",	false,	0),
-	E(NULL,			NULL,				NULL),
+	E(NULL,			NULL,				NULL,				false,	0),
 };
 #undef E
 
 static char mem_loads_name[100];
-static bool mem_loads_name__init;
+static char mem_stores_name[100];
 
 struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i)
 {
@@ -62,23 +62,49 @@ struct perf_pmu *perf_mem_events_find_pmu(void)
 	return perf_pmus__scan_mem(NULL);
 }
 
-const char * __weak perf_mem_events__name(int i, const char *pmu_name  __maybe_unused)
+static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu)
 {
-	struct perf_mem_event *e = &perf_mem_events[i];
+	struct perf_mem_event *e;
 
+	if (i >= PERF_MEM_EVENTS__MAX || !pmu)
+		return NULL;
+
+	e = &pmu->mem_events[i];
 	if (!e)
 		return NULL;
 
-	if (i == PERF_MEM_EVENTS__LOAD) {
+	if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) {
-		if (!mem_loads_name__init) {
+		if (e->ldlat) {
-			mem_loads_name__init = true;
+			if (!e->aux_event) {
+				/* ARM and Most of Intel */
 				scnprintf(mem_loads_name, sizeof(mem_loads_name),
-				  e->name, perf_mem_events__loads_ldlat);
+					  e->name, pmu->name,
+					  perf_mem_events__loads_ldlat);
+			} else {
+				/* Intel with mem-loads-aux event */
+				scnprintf(mem_loads_name, sizeof(mem_loads_name),
+					  e->name, pmu->name, pmu->name,
+					  perf_mem_events__loads_ldlat);
 			}
+		} else {
+			if (!e->aux_event) {
+				/* AMD and POWER */
+				scnprintf(mem_loads_name, sizeof(mem_loads_name),
+					  e->name, pmu->name);
+			} else
+				return NULL;
+		}
+
 		return mem_loads_name;
 	}
 
-	return e->name;
+	if (i == PERF_MEM_EVENTS__STORE) {
+		scnprintf(mem_stores_name, sizeof(mem_stores_name),
+			  e->name, pmu->name);
+		return mem_stores_name;
+	}
+
+	return NULL;
 }
 
 __weak bool is_mem_loads_aux_event(struct evsel *leader __maybe_unused)
@@ -175,7 +201,7 @@ void perf_pmu__mem_events_list(struct perf_pmu *pmu)
 			e->tag ? 13 : 0,
 			e->tag ? : "",
 			e->tag && verbose > 0 ? 25 : 0,
-			e->tag && verbose > 0 ? perf_mem_events__name(j, NULL) : "",
+			e->tag && verbose > 0 ? perf_pmu__mem_events_name(j, pmu) : "",
 			e->supported ? ": available\n" : "");
 	}
 }
@@ -198,15 +224,15 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr,
 
 			if (!e->supported) {
 				pr_err("failed: event '%s' not supported\n",
-					perf_mem_events__name(j, pmu->name));
+					perf_pmu__mem_events_name(j, pmu));
 				return -1;
 			}
 
 			if (perf_pmus__num_mem_pmus() == 1) {
 				rec_argv[i++] = "-e";
-				rec_argv[i++] = perf_mem_events__name(j, NULL);
+				rec_argv[i++] = perf_pmu__mem_events_name(j, pmu);
 			} else {
-				const char *s = perf_mem_events__name(j, pmu->name);
+				const char *s = perf_pmu__mem_events_name(j, pmu);
 
 				if (!perf_mem_event__supported(mnt, pmu, e))
 					continue;

tools/perf/util/mem-events.h

@@ -14,6 +14,8 @@
 struct perf_mem_event {
 	bool		record;
 	bool		supported;
+	bool		ldlat;
+	u32		aux_event;
 	const char	*tag;
 	const char	*name;
 	const char	*sysfs_name;
@@ -39,7 +41,6 @@ extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
 int perf_pmu__mem_events_parse(struct perf_pmu *pmu, const char *str);
 int perf_pmu__mem_events_init(struct perf_pmu *pmu);
 
-const char *perf_mem_events__name(int i, const char *pmu_name);
 struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i);
 struct perf_pmu *perf_mem_events_find_pmu(void);
 bool is_mem_loads_aux_event(struct evsel *leader);