linuxmsm/laptops-kernel
0
0
Fork 0
mirror of https://github.com/linux-msm/laptops-kernel.git synced 2026-08-13 14:19:53 -07:00
Code Issues Packages Projects Releases Wiki Activity

perf drm_pmu: Add a tool like PMU to expose DRM information

Browse Source 
DRM clients expose information through usage stats as documented in
Documentation/gpu/drm-usage-stats.rst (available online at
https://docs.kernel.org/gpu/drm-usage-stats.html). Add a tool like
PMU, similar to the hwmon PMU, that exposes DRM information. For
example on a tigerlake laptop:
```
$ perf list drm

List of pre-defined events (to be used in -e or -M):

drm:
  drm-active-stolen-system0
       [Total memory active in one or more engines. Unit: drm_i915]
  drm-active-system0
       [Total memory active in one or more engines. Unit: drm_i915]
  drm-engine-capacity-video
       [Engine capacity. Unit: drm_i915]
  drm-engine-copy
       [Utilization in ns. Unit: drm_i915]
  drm-engine-render
       [Utilization in ns. Unit: drm_i915]
  drm-engine-video
       [Utilization in ns. Unit: drm_i915]
  drm-engine-video-enhance
       [Utilization in ns. Unit: drm_i915]
  drm-purgeable-stolen-system0
       [Size of resident and purgeable memory bufers. Unit: drm_i915]
  drm-purgeable-system0
       [Size of resident and purgeable memory bufers. Unit: drm_i915]
  drm-resident-stolen-system0
       [Size of resident memory bufers. Unit: drm_i915]
  drm-resident-system0
       [Size of resident memory bufers. Unit: drm_i915]
  drm-shared-stolen-system0
       [Size of shared memory bufers. Unit: drm_i915]
  drm-shared-system0
       [Size of shared memory bufers. Unit: drm_i915]
  drm-total-stolen-system0
       [Size of shared and private memory. Unit: drm_i915]
  drm-total-system0
       [Size of shared and private memory. Unit: drm_i915]
```

System wide data can be gathered:
```
$ perf stat -x, -I 1000 -e drm-active-stolen-system0,drm-active-system0,drm-engine-capacity-video,drm-engine-copy,drm-engine-render,drm-engine-video,drm-engine-video-enhance,drm-purgeable-stolen-system0,drm-purgeable-system0,drm-resident-stolen-system0,drm-resident-system0,drm-shared-stolen-system0,drm-shared-system0,drm-total-stolen-system0,drm-total-system0
1.000904910,0,bytes,drm-active-stolen-system0,1,100.00,,
1.000904910,0,bytes,drm-active-system0,1,100.00,,
1.000904910,36,capacity,drm-engine-capacity-video,1,100.00,,
1.000904910,0,ns,drm-engine-copy,1,100.00,,
1.000904910,1472970566175,ns,drm-engine-render,1,100.00,,
1.000904910,0,ns,drm-engine-video,1,100.00,,
1.000904910,0,ns,drm-engine-video-enhance,1,100.00,,
1.000904910,0,bytes,drm-purgeable-stolen-system0,1,100.00,,
1.000904910,38199296,bytes,drm-purgeable-system0,1,100.00,,
1.000904910,0,bytes,drm-resident-stolen-system0,1,100.00,,
1.000904910,4643196928,bytes,drm-resident-system0,1,100.00,,
1.000904910,0,bytes,drm-shared-stolen-system0,1,100.00,,
1.000904910,1886871552,bytes,drm-shared-system0,1,100.00,,
1.000904910,0,bytes,drm-total-stolen-system0,1,100.00,,
1.000904910,4643196928,bytes,drm-total-system0,1,100.00,,
2.264426839,0,bytes,drm-active-stolen-system0,1,100.00,,
```

Or for a particular process:
```
$ perf stat -x, -I 1000 -e drm-active-stolen-system0,drm-active-system0,drm-engine-capacity-video,drm-engine-copy,drm-engine-render,drm-engine-video,drm-engine-video-enhance,drm-purgeable-stolen-system0,drm-purgeable-system0,drm-resident-stolen-system0,drm-resident-system0,drm-shared-stolen-system0,drm-shared-system0,drm-total-stolen-system0,drm-total-system0 -p 200027
1.001040274,0,bytes,drm-active-stolen-system0,6,100.00,,
1.001040274,0,bytes,drm-active-system0,6,100.00,,
1.001040274,12,capacity,drm-engine-capacity-video,6,100.00,,
1.001040274,0,ns,drm-engine-copy,6,100.00,,
1.001040274,1542300,ns,drm-engine-render,6,100.00,,
1.001040274,0,ns,drm-engine-video,6,100.00,,
1.001040274,0,ns,drm-engine-video-enhance,6,100.00,,
1.001040274,0,bytes,drm-purgeable-stolen-system0,6,100.00,,
1.001040274,13516800,bytes,drm-purgeable-system0,6,100.00,,
1.001040274,0,bytes,drm-resident-stolen-system0,6,100.00,,
1.001040274,27746304,bytes,drm-resident-system0,6,100.00,,
1.001040274,0,bytes,drm-shared-stolen-system0,6,100.00,,
1.001040274,0,bytes,drm-shared-system0,6,100.00,,
1.001040274,0,bytes,drm-total-stolen-system0,6,100.00,,
1.001040274,27746304,bytes,drm-total-system0,6,100.00,,
2.016629075,0,bytes,drm-active-stolen-system0,6,100.00,,
```

As with the hwmon PMU, high numbered PMU types are used to encode
multiple possible "DRM" PMUs. The appropriate fdinfo is found by
scanning /proc and filtering which fdinfos to read with stat. To avoid
some unneeding scanning, events not starting with "drm-" are
ignored. The patch builds on commit 57e13264dc ("perf pmus:
Restructure pmu_read_sysfs to scan fewer PMUs") and later so that only
if full wild carding is being done, the PMU starts with "drm_" or the
event starts with "drm-" will /proc be scanned. That is there should
be little to no cost in this PMU unless DRM events are requested.

Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250624231837.179536-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
This commit is contained in:
Ian Rogers
2025-06-25 11:12:35 -07:00
committed by Namhyung Kim
parent e1ec69ed5d
commit 28917cb17f
7 changed files with 779 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/perf/util/Build
+1
View File
@@ -84,6 +84,7 @@ perf-util-y += pmu.o
perf-util-y += pmus.o
perf-util-y += pmu-flex.o
perf-util-y += pmu-bison.o
perf-util-y += drm_pmu.o
perf-util-y += hwmon_pmu.o
perf-util-y += tool_pmu.o
perf-util-y += svghelper.o
tools/perf/util/drm_pmu.c
+686
View File
File diff suppressed because it is too large Load Diff
tools/perf/util/drm_pmu.h
+39
View File
@@ -0,0 +1,39 @@
/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
#ifndef __DRM_PMU_H
#define __DRM_PMU_H
/*
* Linux DRM clients expose information through usage stats as documented in
* Documentation/gpu/drm-usage-stats.rst (available online at
* https://docs.kernel.org/gpu/drm-usage-stats.html). This is a tool like PMU
* that exposes DRM information.
*/
#include "pmu.h"
#include <stdbool.h>
struct list_head;
struct perf_thread_map;
void drm_pmu__exit(struct perf_pmu *pmu);
bool drm_pmu__have_event(const struct perf_pmu *pmu, const char *name);
int drm_pmu__for_each_event(const struct perf_pmu *pmu, void *state, pmu_event_callback cb);
size_t drm_pmu__num_events(const struct perf_pmu *pmu);
int drm_pmu__config_terms(const struct perf_pmu *pmu,
struct perf_event_attr *attr,
struct parse_events_terms *terms,
struct parse_events_error *err);
int drm_pmu__check_alias(const struct perf_pmu *pmu, struct parse_events_terms *terms,
struct perf_pmu_info *info, struct parse_events_error *err);
bool perf_pmu__is_drm(const struct perf_pmu *pmu);
bool evsel__is_drm(const struct evsel *evsel);
int perf_pmus__read_drm_pmus(struct list_head *pmus);
int evsel__drm_pmu_open(struct evsel *evsel,
struct perf_thread_map *threads,
int start_cpu_map_idx, int end_cpu_map_idx);
int evsel__drm_pmu_read(struct evsel *evsel, int cpu_map_idx, int thread);
#endif /* __DRM_PMU_H */
tools/perf/util/evsel.c
+9
View File
@@ -56,6 +56,7 @@
#include "off_cpu.h"
#include "pmu.h"
#include "pmus.h"
#include "drm_pmu.h"
#include "hwmon_pmu.h"
#include "tool_pmu.h"
#include "rlimit.h"
@@ -1889,6 +1890,9 @@ int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
if (evsel__is_hwmon(evsel))
return evsel__hwmon_pmu_read(evsel, cpu_map_idx, thread);
if (evsel__is_drm(evsel))
return evsel__drm_pmu_read(evsel, cpu_map_idx, thread);
if (evsel__is_retire_lat(evsel))
return evsel__tpebs_read(evsel, cpu_map_idx, thread);
@@ -2610,6 +2614,11 @@ fallback_missing_features:
start_cpu_map_idx,
end_cpu_map_idx);
}
if (evsel__is_drm(evsel)) {
return evsel__drm_pmu_open(evsel, threads,
start_cpu_map_idx,
end_cpu_map_idx);
}
for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
cpu = perf_cpu_map__cpu(cpus, idx);
tools/perf/util/pmu.c
+15
View File
@@ -20,6 +20,7 @@
#include "debug.h"
#include "evsel.h"
#include "pmu.h"
#include "drm_pmu.h"
#include "hwmon_pmu.h"
#include "pmus.h"
#include "tool_pmu.h"
@@ -1627,6 +1628,8 @@ int perf_pmu__config_terms(const struct perf_pmu *pmu,
if (perf_pmu__is_hwmon(pmu))
return hwmon_pmu__config_terms(pmu, attr, terms, err);
if (perf_pmu__is_drm(pmu))
return drm_pmu__config_terms(pmu, attr, terms, err);
list_for_each_entry(term, &terms->terms, list) {
if (pmu_config_term(pmu, attr, term, terms, zero, apply_hardcoded, err))
@@ -1767,6 +1770,10 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct parse_events_terms *head_
ret = hwmon_pmu__check_alias(head_terms, info, err);
goto out;
}
if (perf_pmu__is_drm(pmu)) {
ret = drm_pmu__check_alias(pmu, head_terms, info, err);
goto out;
}
/* Fake PMU doesn't rewrite terms. */
if (perf_pmu__is_fake(pmu))
@@ -1949,6 +1956,8 @@ bool perf_pmu__have_event(struct perf_pmu *pmu, const char *name)
return false;
if (perf_pmu__is_hwmon(pmu))
return hwmon_pmu__have_event(pmu, name);
if (perf_pmu__is_drm(pmu))
return drm_pmu__have_event(pmu, name);
if (perf_pmu__find_alias(pmu, name, /*load=*/ true) != NULL)
return true;
if (pmu->cpu_aliases_added || !pmu->events_table)
@@ -1962,6 +1971,8 @@ size_t perf_pmu__num_events(struct perf_pmu *pmu)
if (perf_pmu__is_hwmon(pmu))
return hwmon_pmu__num_events(pmu);
if (perf_pmu__is_drm(pmu))
return drm_pmu__num_events(pmu);
pmu_aliases_parse(pmu);
nr = pmu->sysfs_aliases + pmu->sys_json_aliases;
@@ -2030,6 +2041,8 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
if (perf_pmu__is_hwmon(pmu))
return hwmon_pmu__for_each_event(pmu, state, cb);
if (perf_pmu__is_drm(pmu))
return drm_pmu__for_each_event(pmu, state, cb);
strbuf_init(&sb, /*hint=*/ 0);
pmu_aliases_parse(pmu);
@@ -2511,6 +2524,8 @@ void perf_pmu__delete(struct perf_pmu *pmu)
if (perf_pmu__is_hwmon(pmu))
hwmon_pmu__exit(pmu);
else if (perf_pmu__is_drm(pmu))
drm_pmu__exit(pmu);
perf_pmu__del_formats(&pmu->format);
perf_pmu__del_aliases(pmu);
tools/perf/util/pmu.h
+3 -1
View File
@@ -39,7 +39,9 @@ struct perf_pmu_caps {
enum {
PERF_PMU_TYPE_PE_START = 0,
PERF_PMU_TYPE_PE_END = 0xFFFEFFFF,
PERF_PMU_TYPE_PE_END = 0xFFFDFFFF,
PERF_PMU_TYPE_DRM_START = 0xFFFE0000,
PERF_PMU_TYPE_DRM_END = 0xFFFEFFFF,
PERF_PMU_TYPE_HWMON_START = 0xFFFF0000,
PERF_PMU_TYPE_HWMON_END = 0xFFFFFFFD,
PERF_PMU_TYPE_TOOL = 0xFFFFFFFE,
tools/perf/util/pmus.c
+26 -4
View File
@@ -12,6 +12,7 @@
#include <unistd.h>
#include "cpumap.h"
#include "debug.h"
#include "drm_pmu.h"
#include "evsel.h"
#include "pmus.h"
#include "pmu.h"
@@ -43,16 +44,19 @@ enum perf_tool_pmu_type {
PERF_TOOL_PMU_TYPE_PE_OTHER,
PERF_TOOL_PMU_TYPE_TOOL,
PERF_TOOL_PMU_TYPE_HWMON,
PERF_TOOL_PMU_TYPE_DRM,
#define PERF_TOOL_PMU_TYPE_PE_CORE_MASK (1 << PERF_TOOL_PMU_TYPE_PE_CORE)
#define PERF_TOOL_PMU_TYPE_PE_OTHER_MASK (1 << PERF_TOOL_PMU_TYPE_PE_OTHER)
#define PERF_TOOL_PMU_TYPE_TOOL_MASK (1 << PERF_TOOL_PMU_TYPE_TOOL)
#define PERF_TOOL_PMU_TYPE_HWMON_MASK (1 << PERF_TOOL_PMU_TYPE_HWMON)
#define PERF_TOOL_PMU_TYPE_DRM_MASK (1 << PERF_TOOL_PMU_TYPE_DRM)
#define PERF_TOOL_PMU_TYPE_ALL_MASK (PERF_TOOL_PMU_TYPE_PE_CORE_MASK | \
PERF_TOOL_PMU_TYPE_PE_OTHER_MASK | \
PERF_TOOL_PMU_TYPE_TOOL_MASK | \
PERF_TOOL_PMU_TYPE_HWMON_MASK)
PERF_TOOL_PMU_TYPE_HWMON_MASK | \
PERF_TOOL_PMU_TYPE_DRM_MASK)
};
static unsigned int read_pmu_types;
@@ -173,6 +177,8 @@ struct perf_pmu *perf_pmus__find(const char *name)
/* Looking up an individual perf event PMU failed, check if a tool PMU should be read. */
if (!strncmp(name, "hwmon_", 6))
to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK;
else if (!strncmp(name, "drm_", 4))
to_read_pmus |= PERF_TOOL_PMU_TYPE_DRM_MASK;
else if (!strcmp(name, "tool"))
to_read_pmus |= PERF_TOOL_PMU_TYPE_TOOL_MASK;
@@ -273,6 +279,10 @@ skip_pe_pmus:
(read_pmu_types & PERF_TOOL_PMU_TYPE_HWMON_MASK) == 0)
perf_pmus__read_hwmon_pmus(&other_pmus);
if ((to_read_types & PERF_TOOL_PMU_TYPE_DRM_MASK) != 0 &&
(read_pmu_types & PERF_TOOL_PMU_TYPE_DRM_MASK) == 0)
perf_pmus__read_drm_pmus(&other_pmus);
list_sort(NULL, &other_pmus, pmus_cmp);
read_pmu_types |= to_read_types;
@@ -305,6 +315,8 @@ struct perf_pmu *perf_pmus__find_by_type(unsigned int type)
if (type >= PERF_PMU_TYPE_PE_START && type <= PERF_PMU_TYPE_PE_END) {
to_read_pmus = PERF_TOOL_PMU_TYPE_PE_CORE_MASK |
PERF_TOOL_PMU_TYPE_PE_OTHER_MASK;
} else if (type >= PERF_PMU_TYPE_DRM_START && type <= PERF_PMU_TYPE_DRM_END) {
to_read_pmus = PERF_TOOL_PMU_TYPE_DRM_MASK;
} else if (type >= PERF_PMU_TYPE_HWMON_START && type <= PERF_PMU_TYPE_HWMON_END) {
to_read_pmus = PERF_TOOL_PMU_TYPE_HWMON_MASK;
} else {
@@ -371,6 +383,10 @@ struct perf_pmu *perf_pmus__scan_for_event(struct perf_pmu *pmu, const char *eve
if (parse_hwmon_filename(event, &type, &number, /*item=*/NULL, /*alarm=*/NULL))
to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK;
/* Could the event be a DRM event? */
if (strlen(event) > 4 && strncmp("drm-", event, 4) == 0)
to_read_pmus |= PERF_TOOL_PMU_TYPE_DRM_MASK;
pmu_read_sysfs(to_read_pmus);
pmu = list_prepare_entry(pmu, &core_pmus, list);
}
@@ -403,11 +419,17 @@ struct perf_pmu *perf_pmus__scan_matching_wildcard(struct perf_pmu *pmu, const c
* Hwmon PMUs have an alias from a sysfs name like hwmon0,
* hwmon1, etc. or have a name of hwmon_<name>. They therefore
* can only have a wildcard match if the wildcard begins with
* "hwmon".
* "hwmon". Similarly drm PMUs must start "drm_", avoid reading
* such events unless the PMU could match.
*/
if (strisglob(wildcard) ||
(strlen(wildcard) >= 5 && strncmp("hwmon", wildcard, 5) == 0))
if (strisglob(wildcard)) {
to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK |
PERF_TOOL_PMU_TYPE_DRM_MASK;
} else if (strlen(wildcard) >= 4 && strncmp("drm_", wildcard, 4) == 0) {
to_read_pmus |= PERF_TOOL_PMU_TYPE_DRM_MASK;
} else if (strlen(wildcard) >= 5 && strncmp("hwmon", wildcard, 5) == 0) {
to_read_pmus |= PERF_TOOL_PMU_TYPE_HWMON_MASK;
}
pmu_read_sysfs(to_read_pmus);
pmu = list_prepare_entry(pmu, &core_pmus, list);