summaryrefslogtreecommitdiff
path: root/tools/perf/util/mem-events.c
diff options
context:
space:
mode:
Diffstat (limited to 'tools/perf/util/mem-events.c')
-rw-r--r--tools/perf/util/mem-events.c329
1 files changed, 281 insertions, 48 deletions
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 637cbd4a7bfb..80b3069427bc 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -8,9 +8,12 @@
#include <unistd.h>
#include <api/fs/fs.h>
#include <linux/kernel.h>
+#include "cpumap.h"
#include "map_symbol.h"
#include "mem-events.h"
+#include "mem-info.h"
#include "debug.h"
+#include "evsel.h"
#include "symbol.h"
#include "pmu.h"
#include "pmus.h"
@@ -26,8 +29,7 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
};
#undef E
-static char mem_loads_name[100];
-static char mem_stores_name[100];
+bool perf_mem_record[PERF_MEM_EVENTS__MAX] = { 0 };
struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i)
{
@@ -76,7 +78,8 @@ int perf_pmu__mem_events_num_mem_pmus(struct perf_pmu *pmu)
return num;
}
-static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu)
+static const char *perf_pmu__mem_events_name(struct perf_pmu *pmu, int i,
+ char *buf, size_t buf_size)
{
struct perf_mem_event *e;
@@ -84,38 +87,38 @@ static const char *perf_pmu__mem_events_name(int i, struct perf_pmu *pmu)
return NULL;
e = &pmu->mem_events[i];
- if (!e)
+ if (!e || !e->name)
return NULL;
if (i == PERF_MEM_EVENTS__LOAD || i == PERF_MEM_EVENTS__LOAD_STORE) {
if (e->ldlat) {
if (!e->aux_event) {
/* ARM and Most of Intel */
- scnprintf(mem_loads_name, sizeof(mem_loads_name),
+ scnprintf(buf, buf_size,
e->name, pmu->name,
perf_mem_events__loads_ldlat);
} else {
/* Intel with mem-loads-aux event */
- scnprintf(mem_loads_name, sizeof(mem_loads_name),
+ scnprintf(buf, buf_size,
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),
+ scnprintf(buf, buf_size,
e->name, pmu->name);
- } else
+ } else {
return NULL;
+ }
}
-
- return mem_loads_name;
+ return buf;
}
if (i == PERF_MEM_EVENTS__STORE) {
- scnprintf(mem_stores_name, sizeof(mem_stores_name),
+ scnprintf(buf, buf_size,
e->name, pmu->name);
- return mem_stores_name;
+ return buf;
}
return NULL;
@@ -160,7 +163,7 @@ int perf_pmu__mem_events_parse(struct perf_pmu *pmu, const char *str)
continue;
if (strstr(e->tag, tok))
- e->record = found = true;
+ perf_mem_record[j] = found = true;
}
tok = strtok_r(NULL, ",", &saveptr);
@@ -184,12 +187,12 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu
if (!e->event_name)
return true;
- scnprintf(path, PATH_MAX, "%s/devices/%s/events/%s", mnt, pmu->name, e->event_name);
+ scnprintf(path, PATH_MAX, "%s/bus/event_source/devices/%s/events/%s", mnt, pmu->name, e->event_name);
return !stat(path, &st);
}
-int perf_pmu__mem_events_init(struct perf_pmu *pmu)
+static int __perf_pmu__mem_events_init(struct perf_pmu *pmu)
{
const char *mnt = sysfs__mount();
bool found = false;
@@ -216,58 +219,101 @@ int perf_pmu__mem_events_init(struct perf_pmu *pmu)
return found ? 0 : -ENOENT;
}
+int perf_pmu__mem_events_init(void)
+{
+ struct perf_pmu *pmu = NULL;
+
+ while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) {
+ if (__perf_pmu__mem_events_init(pmu))
+ return -ENOENT;
+ }
+
+ return 0;
+}
+
void perf_pmu__mem_events_list(struct perf_pmu *pmu)
{
int j;
for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+ char buf[128];
struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j);
fprintf(stderr, "%-*s%-*s%s",
e->tag ? 13 : 0,
e->tag ? : "",
e->tag && verbose > 0 ? 25 : 0,
- e->tag && verbose > 0 ? perf_pmu__mem_events_name(j, pmu) : "",
+ e->tag && verbose > 0
+ ? perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf))
+ : "",
e->supported ? ": available\n" : "");
}
}
-int perf_mem_events__record_args(const char **rec_argv, int *argv_nr)
+int perf_mem_events__record_args(const char **rec_argv, int *argv_nr, char **event_name_storage_out)
{
const char *mnt = sysfs__mount();
struct perf_pmu *pmu = NULL;
- struct perf_mem_event *e;
int i = *argv_nr;
- const char *s;
- char *copy;
+ struct perf_cpu_map *cpu_map = NULL;
+ size_t event_name_storage_size =
+ perf_pmu__mem_events_num_mem_pmus(NULL) * PERF_MEM_EVENTS__MAX * 128;
+ size_t event_name_storage_remaining = event_name_storage_size;
+ char *event_name_storage = malloc(event_name_storage_size);
+ char *event_name_storage_ptr = event_name_storage;
+
+ if (!event_name_storage)
+ return -ENOMEM;
+ *event_name_storage_out = NULL;
while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) {
for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
- e = perf_pmu__mem_events_ptr(pmu, j);
+ const char *s;
+ struct perf_mem_event *e = perf_pmu__mem_events_ptr(pmu, j);
+ int ret;
- if (!e->record)
+ if (!perf_mem_record[j])
continue;
if (!e->supported) {
+ char buf[128];
+
pr_err("failed: event '%s' not supported\n",
- perf_pmu__mem_events_name(j, pmu));
+ perf_pmu__mem_events_name(pmu, j, buf, sizeof(buf)));
+ free(event_name_storage);
return -1;
}
- s = perf_pmu__mem_events_name(j, pmu);
+ s = perf_pmu__mem_events_name(pmu, j, event_name_storage_ptr,
+ event_name_storage_remaining);
if (!s || !perf_pmu__mem_events_supported(mnt, pmu, e))
continue;
- copy = strdup(s);
- if (!copy)
- return -1;
-
rec_argv[i++] = "-e";
- rec_argv[i++] = copy;
+ rec_argv[i++] = event_name_storage_ptr;
+ event_name_storage_remaining -= strlen(event_name_storage_ptr) + 1;
+ event_name_storage_ptr += strlen(event_name_storage_ptr) + 1;
+
+ ret = perf_cpu_map__merge(&cpu_map, pmu->cpus);
+ if (ret < 0) {
+ free(event_name_storage);
+ return ret;
+ }
+ }
+ }
+
+ if (cpu_map) {
+ if (!perf_cpu_map__equal(cpu_map, cpu_map__online())) {
+ char buf[200];
+
+ cpu_map__snprint(cpu_map, buf, sizeof(buf));
+ pr_warning("Memory events are enabled on a subset of CPUs: %s\n", buf);
}
+ perf_cpu_map__put(cpu_map);
}
*argv_nr = i;
+ *event_name_storage_out = event_name_storage;
return 0;
}
@@ -281,7 +327,7 @@ static const char * const tlb_access[] = {
"Fault",
};
-int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__tlb_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
size_t l = 0, i;
u64 m = PERF_MEM_TLB_NA;
@@ -291,7 +337,7 @@ int perf_mem__tlb_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
out[0] = '\0';
if (mem_info)
- m = mem_info->data_src.mem_dtlb;
+ m = mem_info__const_data_src(mem_info)->mem_dtlb;
hit = m & PERF_MEM_TLB_HIT;
miss = m & PERF_MEM_TLB_MISS;
@@ -336,6 +382,12 @@ static const char * const mem_lvl[] = {
};
static const char * const mem_lvlnum[] = {
+ [PERF_MEM_LVLNUM_L1] = "L1",
+ [PERF_MEM_LVLNUM_L2] = "L2",
+ [PERF_MEM_LVLNUM_L3] = "L3",
+ [PERF_MEM_LVLNUM_L4] = "L4",
+ [PERF_MEM_LVLNUM_L2_MHB] = "L2 MHB",
+ [PERF_MEM_LVLNUM_MSC] = "Memory-side Cache",
[PERF_MEM_LVLNUM_UNC] = "Uncached",
[PERF_MEM_LVLNUM_CXL] = "CXL",
[PERF_MEM_LVLNUM_IO] = "I/O",
@@ -359,13 +411,13 @@ static const char * const mem_hops[] = {
"board",
};
-static int perf_mem__op_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+static int perf_mem__op_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
u64 op = PERF_MEM_LOCK_NA;
int l;
if (mem_info)
- op = mem_info->data_src.mem_op;
+ op = mem_info__const_data_src(mem_info)->mem_op;
if (op & PERF_MEM_OP_NA)
l = scnprintf(out, sz, "N/A");
@@ -383,7 +435,7 @@ static int perf_mem__op_scnprintf(char *out, size_t sz, struct mem_info *mem_inf
return l;
}
-int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__lvl_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
union perf_mem_data_src data_src;
int printed = 0;
@@ -398,7 +450,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
if (!mem_info)
goto na;
- data_src = mem_info->data_src;
+ data_src = *mem_info__const_data_src(mem_info);
if (data_src.mem_lvl & PERF_MEM_LVL_HIT)
memcpy(hit_miss, "hit", 3);
@@ -418,7 +470,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
if (mem_lvlnum[lvl])
l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]);
else
- l += scnprintf(out + l, sz - l, "L%d", lvl);
+ l += scnprintf(out + l, sz - l, "Unknown level %d", lvl);
l += scnprintf(out + l, sz - l, " %s", hit_miss);
return l;
@@ -465,7 +517,7 @@ static const char * const snoopx_access[] = {
"Peer",
};
-int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__snp_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
size_t i, l = 0;
u64 m = PERF_MEM_SNOOP_NA;
@@ -474,7 +526,7 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
out[0] = '\0';
if (mem_info)
- m = mem_info->data_src.mem_snoop;
+ m = mem_info__const_data_src(mem_info)->mem_snoop;
for (i = 0; m && i < ARRAY_SIZE(snoop_access); i++, m >>= 1) {
if (!(m & 0x1))
@@ -488,7 +540,7 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
m = 0;
if (mem_info)
- m = mem_info->data_src.mem_snoopx;
+ m = mem_info__const_data_src(mem_info)->mem_snoopx;
for (i = 0; m && i < ARRAY_SIZE(snoopx_access); i++, m >>= 1) {
if (!(m & 0x1))
@@ -507,13 +559,13 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
return l;
}
-int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__lck_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
u64 mask = PERF_MEM_LOCK_NA;
int l;
if (mem_info)
- mask = mem_info->data_src.mem_lock;
+ mask = mem_info__const_data_src(mem_info)->mem_lock;
if (mask & PERF_MEM_LOCK_NA)
l = scnprintf(out, sz, "N/A");
@@ -525,7 +577,7 @@ int perf_mem__lck_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
return l;
}
-int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_mem__blk_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
size_t l = 0;
u64 mask = PERF_MEM_BLK_NA;
@@ -534,7 +586,7 @@ int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
out[0] = '\0';
if (mem_info)
- mask = mem_info->data_src.mem_blk;
+ mask = mem_info__const_data_src(mem_info)->mem_blk;
if (!mask || (mask & PERF_MEM_BLK_NA)) {
l += scnprintf(out + l, sz - l, " N/A");
@@ -548,7 +600,7 @@ int perf_mem__blk_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
return l;
}
-int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
+int perf_script__meminfo_scnprintf(char *out, size_t sz, const struct mem_info *mem_info)
{
int i = 0;
@@ -570,8 +622,8 @@ int perf_script__meminfo_scnprintf(char *out, size_t sz, struct mem_info *mem_in
int c2c_decode_stats(struct c2c_stats *stats, struct mem_info *mi)
{
- union perf_mem_data_src *data_src = &mi->data_src;
- u64 daddr = mi->daddr.addr;
+ union perf_mem_data_src *data_src = mem_info__data_src(mi);
+ u64 daddr = mem_info__daddr(mi)->addr;
u64 op = data_src->mem_op;
u64 lvl = data_src->mem_lvl;
u64 snoop = data_src->mem_snoop;
@@ -625,7 +677,10 @@ do { \
if (lvl & P(LVL, LFB)) stats->ld_fbhit++;
if (lvl & P(LVL, L1 )) stats->ld_l1hit++;
if (lvl & P(LVL, L2)) {
- stats->ld_l2hit++;
+ if (snoop & P(SNOOP, HITM))
+ HITM_INC(lcl_hitm);
+ else
+ stats->ld_l2hit++;
if (snoopx & P(SNOOPX, PEER))
PEER_INC(lcl_peer);
@@ -698,7 +753,7 @@ do { \
return -1;
}
- if (!mi->daddr.ms.map || !mi->iaddr.ms.map) {
+ if (!mem_info__daddr(mi)->ms.map || !mem_info__iaddr(mi)->ms.map) {
stats->nomap++;
return -1;
}
@@ -744,3 +799,181 @@ void c2c_add_stats(struct c2c_stats *stats, struct c2c_stats *add)
stats->nomap += add->nomap;
stats->noparse += add->noparse;
}
+
+/*
+ * It returns an index in hist_entry->mem_stat array for the given val which
+ * represents a data-src based on the mem_stat_type.
+ */
+int mem_stat_index(const enum mem_stat_type mst, const u64 val)
+{
+ union perf_mem_data_src src = {
+ .val = val,
+ };
+
+ switch (mst) {
+ case PERF_MEM_STAT_OP:
+ switch (src.mem_op) {
+ case PERF_MEM_OP_LOAD:
+ return MEM_STAT_OP_LOAD;
+ case PERF_MEM_OP_STORE:
+ return MEM_STAT_OP_STORE;
+ case PERF_MEM_OP_LOAD | PERF_MEM_OP_STORE:
+ return MEM_STAT_OP_LDST;
+ default:
+ if (src.mem_op & PERF_MEM_OP_PFETCH)
+ return MEM_STAT_OP_PFETCH;
+ if (src.mem_op & PERF_MEM_OP_EXEC)
+ return MEM_STAT_OP_EXEC;
+ return MEM_STAT_OP_OTHER;
+ }
+ case PERF_MEM_STAT_CACHE:
+ switch (src.mem_lvl_num) {
+ case PERF_MEM_LVLNUM_L1:
+ return MEM_STAT_CACHE_L1;
+ case PERF_MEM_LVLNUM_L2:
+ return MEM_STAT_CACHE_L2;
+ case PERF_MEM_LVLNUM_L3:
+ return MEM_STAT_CACHE_L3;
+ case PERF_MEM_LVLNUM_L4:
+ return MEM_STAT_CACHE_L4;
+ case PERF_MEM_LVLNUM_LFB:
+ return MEM_STAT_CACHE_L1_BUF;
+ case PERF_MEM_LVLNUM_L2_MHB:
+ return MEM_STAT_CACHE_L2_BUF;
+ default:
+ return MEM_STAT_CACHE_OTHER;
+ }
+ case PERF_MEM_STAT_MEMORY:
+ switch (src.mem_lvl_num) {
+ case PERF_MEM_LVLNUM_MSC:
+ return MEM_STAT_MEMORY_MSC;
+ case PERF_MEM_LVLNUM_RAM:
+ return MEM_STAT_MEMORY_RAM;
+ case PERF_MEM_LVLNUM_UNC:
+ return MEM_STAT_MEMORY_UNC;
+ case PERF_MEM_LVLNUM_CXL:
+ return MEM_STAT_MEMORY_CXL;
+ case PERF_MEM_LVLNUM_IO:
+ return MEM_STAT_MEMORY_IO;
+ case PERF_MEM_LVLNUM_PMEM:
+ return MEM_STAT_MEMORY_PMEM;
+ default:
+ return MEM_STAT_MEMORY_OTHER;
+ }
+ case PERF_MEM_STAT_SNOOP:
+ switch (src.mem_snoop) {
+ case PERF_MEM_SNOOP_HIT:
+ return MEM_STAT_SNOOP_HIT;
+ case PERF_MEM_SNOOP_HITM:
+ return MEM_STAT_SNOOP_HITM;
+ case PERF_MEM_SNOOP_MISS:
+ return MEM_STAT_SNOOP_MISS;
+ default:
+ return MEM_STAT_SNOOP_OTHER;
+ }
+ case PERF_MEM_STAT_DTLB:
+ switch (src.mem_dtlb) {
+ case PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT:
+ return MEM_STAT_DTLB_L1_HIT;
+ case PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT:
+ return MEM_STAT_DTLB_L2_HIT;
+ case PERF_MEM_TLB_L1 | PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT:
+ return MEM_STAT_DTLB_ANY_HIT;
+ default:
+ if (src.mem_dtlb & PERF_MEM_TLB_MISS)
+ return MEM_STAT_DTLB_MISS;
+ return MEM_STAT_DTLB_OTHER;
+ }
+ default:
+ break;
+ }
+ return -1;
+}
+
+/* To align output, returned string should be shorter than MEM_STAT_PRINT_LEN */
+const char *mem_stat_name(const enum mem_stat_type mst, const int idx)
+{
+ switch (mst) {
+ case PERF_MEM_STAT_OP:
+ switch (idx) {
+ case MEM_STAT_OP_LOAD:
+ return "Load";
+ case MEM_STAT_OP_STORE:
+ return "Store";
+ case MEM_STAT_OP_LDST:
+ return "Ld+St";
+ case MEM_STAT_OP_PFETCH:
+ return "Pfetch";
+ case MEM_STAT_OP_EXEC:
+ return "Exec";
+ case MEM_STAT_OP_OTHER:
+ default:
+ return "Other";
+ }
+ case PERF_MEM_STAT_CACHE:
+ switch (idx) {
+ case MEM_STAT_CACHE_L1:
+ return "L1";
+ case MEM_STAT_CACHE_L2:
+ return "L2";
+ case MEM_STAT_CACHE_L3:
+ return "L3";
+ case MEM_STAT_CACHE_L4:
+ return "L4";
+ case MEM_STAT_CACHE_L1_BUF:
+ return "L1-buf";
+ case MEM_STAT_CACHE_L2_BUF:
+ return "L2-buf";
+ case MEM_STAT_CACHE_OTHER:
+ default:
+ return "Other";
+ }
+ case PERF_MEM_STAT_MEMORY:
+ switch (idx) {
+ case MEM_STAT_MEMORY_RAM:
+ return "RAM";
+ case MEM_STAT_MEMORY_MSC:
+ return "MSC";
+ case MEM_STAT_MEMORY_UNC:
+ return "Uncach";
+ case MEM_STAT_MEMORY_CXL:
+ return "CXL";
+ case MEM_STAT_MEMORY_IO:
+ return "IO";
+ case MEM_STAT_MEMORY_PMEM:
+ return "PMEM";
+ case MEM_STAT_MEMORY_OTHER:
+ default:
+ return "Other";
+ }
+ case PERF_MEM_STAT_SNOOP:
+ switch (idx) {
+ case MEM_STAT_SNOOP_HIT:
+ return "Hit";
+ case MEM_STAT_SNOOP_HITM:
+ return "HitM";
+ case MEM_STAT_SNOOP_MISS:
+ return "Miss";
+ case MEM_STAT_SNOOP_OTHER:
+ default:
+ return "Other";
+ }
+ case PERF_MEM_STAT_DTLB:
+ switch (idx) {
+ case MEM_STAT_DTLB_L1_HIT:
+ return "L1-Hit";
+ case MEM_STAT_DTLB_L2_HIT:
+ return "L2-Hit";
+ case MEM_STAT_DTLB_ANY_HIT:
+ return "L?-Hit";
+ case MEM_STAT_DTLB_MISS:
+ return "Miss";
+ case MEM_STAT_DTLB_OTHER:
+ default:
+ return "Other";
+ }
+ default:
+ break;
+ }
+ return "N/A";
+}
generated by cgit (git 2.34.1) at 2025-07-25 17:39:55 +0000