lkml.org 
[lkml]   [2021]   [Feb]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 38/49] perf list: Display pmu prefix for partially supported hybrid cache events
Date
From: Jin Yao <yao.jin@linux.intel.com>

Part of hardware cache events are only available on one cpu pmu.
For example, 'L1-dcache-load-misses' is only available on cpu_core.
perf list should clearly report this info.

root@otcpl-adl-s-2:~# ./perf list

Before:
L1-dcache-load-misses [Hardware cache event]
L1-dcache-loads [Hardware cache event]
L1-dcache-stores [Hardware cache event]
L1-icache-load-misses [Hardware cache event]
L1-icache-loads [Hardware cache event]
LLC-load-misses [Hardware cache event]
LLC-loads [Hardware cache event]
LLC-store-misses [Hardware cache event]
LLC-stores [Hardware cache event]
branch-load-misses [Hardware cache event]
branch-loads [Hardware cache event]
dTLB-load-misses [Hardware cache event]
dTLB-loads [Hardware cache event]
dTLB-store-misses [Hardware cache event]
dTLB-stores [Hardware cache event]
iTLB-load-misses [Hardware cache event]
node-load-misses [Hardware cache event]
node-loads [Hardware cache event]
node-store-misses [Hardware cache event]
node-stores [Hardware cache event]

After:
L1-dcache-loads [Hardware cache event]
L1-dcache-stores [Hardware cache event]
L1-icache-load-misses [Hardware cache event]
LLC-load-misses [Hardware cache event]
LLC-loads [Hardware cache event]
LLC-store-misses [Hardware cache event]
LLC-stores [Hardware cache event]
branch-load-misses [Hardware cache event]
branch-loads [Hardware cache event]
cpu_atom/L1-icache-loads/ [Hardware cache event]
cpu_core/L1-dcache-load-misses/ [Hardware cache event]
cpu_core/node-load-misses/ [Hardware cache event]
cpu_core/node-loads/ [Hardware cache event]
dTLB-load-misses [Hardware cache event]
dTLB-loads [Hardware cache event]
dTLB-store-misses [Hardware cache event]
dTLB-stores [Hardware cache event]
iTLB-load-misses [Hardware cache event]

Now we can clearly see 'L1-dcache-load-misses' is only available
on cpu_core.

If without pmu prefix, it indicates the event is available on both
cpu_core and cpu_atom.

Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
---
tools/perf/util/parse-events.c | 79 +++++++++++++++++++++++++++++++++++++-----
tools/perf/util/pmu.c | 11 ++++++
tools/perf/util/pmu.h | 2 ++
3 files changed, 84 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index bba7db3..ddf6f79 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -2809,7 +2809,7 @@ int is_valid_tracepoint(const char *event_string)
return 0;
}

-static bool is_event_supported(u8 type, unsigned config)
+static bool is_event_supported(u8 type, u64 config)
{
bool ret = true;
int open_return;
@@ -2929,10 +2929,21 @@ void print_sdt_events(const char *subsys_glob, const char *event_glob,

int print_hwcache_events(const char *event_glob, bool name_only)
{
- unsigned int type, op, i, evt_i = 0, evt_num = 0;
- char name[64];
- char **evt_list = NULL;
+ unsigned int type, op, i, evt_i = 0, evt_num = 0, npmus;
+ char name[64], new_name[128];
+ char **evt_list = NULL, **evt_pmus = NULL;
bool evt_num_known = false;
+ struct perf_pmu *pmu = NULL;
+
+ if (!perf_pmu__hybrid_exist())
+ perf_pmu__scan(NULL);
+
+ npmus = perf_pmu__hybrid_npmus();
+ if (npmus) {
+ evt_pmus = zalloc(sizeof(char *) * npmus);
+ if (!evt_pmus)
+ goto out_enomem;
+ }

restart:
if (evt_num_known) {
@@ -2948,20 +2959,61 @@ int print_hwcache_events(const char *event_glob, bool name_only)
continue;

for (i = 0; i < PERF_COUNT_HW_CACHE_RESULT_MAX; i++) {
+ unsigned int hybrid_supported = 0, j;
+ bool supported;
+
__evsel__hw_cache_type_op_res_name(type, op, i, name, sizeof(name));
if (event_glob != NULL && !strglobmatch(name, event_glob))
continue;

- if (!is_event_supported(PERF_TYPE_HW_CACHE,
- type | (op << 8) | (i << 16)))
- continue;
+ if (!perf_pmu__hybrid_exist()) {
+ if (!is_event_supported(PERF_TYPE_HW_CACHE,
+ type | (op << 8) | (i << 16))) {
+ continue;
+ }
+ } else {
+ perf_pmu__for_each_hybrid_pmus(pmu) {
+ if (!evt_num_known) {
+ evt_num++;
+ continue;
+ }
+
+ supported = is_event_supported(
+ PERF_TYPE_HW_CACHE_PMU,
+ type | (op << 8) | (i << 16) |
+ ((__u64)pmu->type << PERF_PMU_TYPE_SHIFT));
+ if (supported) {
+ snprintf(new_name, sizeof(new_name), "%s/%s/",
+ pmu->name, name);
+ evt_pmus[hybrid_supported] = strdup(new_name);
+ hybrid_supported++;
+ }
+ }
+
+ if (hybrid_supported == 0)
+ continue;
+ }

if (!evt_num_known) {
evt_num++;
continue;
}

- evt_list[evt_i] = strdup(name);
+ if ((hybrid_supported == 0) ||
+ (hybrid_supported == npmus)) {
+ evt_list[evt_i] = strdup(name);
+ if (npmus > 0) {
+ for (j = 0; j < npmus; j++)
+ zfree(&evt_pmus[j]);
+ }
+ } else {
+ for (j = 0; j < hybrid_supported; j++) {
+ evt_list[evt_i++] = evt_pmus[j];
+ evt_pmus[j] = NULL;
+ }
+ continue;
+ }
+
if (evt_list[evt_i] == NULL)
goto out_enomem;
evt_i++;
@@ -2973,6 +3025,13 @@ int print_hwcache_events(const char *event_glob, bool name_only)
evt_num_known = true;
goto restart;
}
+
+ for (evt_i = 0; evt_i < evt_num; evt_i++) {
+ if (!evt_list[evt_i])
+ break;
+ }
+
+ evt_num = evt_i;
qsort(evt_list, evt_num, sizeof(char *), cmp_string);
evt_i = 0;
while (evt_i < evt_num) {
@@ -2991,6 +3050,10 @@ int print_hwcache_events(const char *event_glob, bool name_only)
for (evt_i = 0; evt_i < evt_num; evt_i++)
zfree(&evt_list[evt_i]);
zfree(&evt_list);
+
+ for (evt_i = 0; evt_i < npmus; evt_i++)
+ zfree(&evt_pmus[evt_i]);
+ zfree(&evt_pmus);
return evt_num;

out_enomem:
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index ca2fc67..5ebb0da 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -1901,3 +1901,14 @@ char *perf_pmu__hybrid_type_to_pmu(const char *type)
free(pmu_name);
return NULL;;
}
+
+int perf_pmu__hybrid_npmus(void)
+{
+ struct perf_pmu *pmu;
+ int n = 0;
+
+ perf_pmu__for_each_hybrid_pmus(pmu)
+ n++;
+
+ return n;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index ccffc05..4bd7473 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -143,4 +143,6 @@ static inline bool perf_pmu__hybrid_exist(void)
return !list_empty(&perf_pmu__hybrid_pmus);
}

+int perf_pmu__hybrid_npmus(void);
+
#endif /* __PMU_H */
--
2.7.4
\
 
 \ /
  Last update: 2022-09-17 16:09    [W:1.172 / U:1.100 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site