Hold the path to the hwmon_pmu rather than the file descriptor. The
file descriptor is somewhat problematic in that it reflects the
directory state when opened, something that may vary in testing. Using
a path simplifies testing and to some extent cleanup as the hwmon_pmu
is owned by the pmus list and intentionally global and leaked when
perf terminates, the file descriptor being left open looks like a
leak.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250624190326.2038704-4-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
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>
perf_pmus__destroy() treats all PMUs as allocated and free's them so we
can't have any static PMUs that are added to the PMU lists. Fix it by
allocating the tool PMU in the same way as the others. Current users of
the tool PMU already use find_pmu() and not perf_pmus__tool_pmu(), so
rename the function to add 'new' to avoid it being misused in the
future.
perf_pmus__fake_pmu() can remain as static as it's not added to the
PMU lists.
Fixes the following error:
$ perf bench internals pmu-scan
# Running 'internals/pmu-scan' benchmark:
Computing performance of sysfs PMU event scan for 100 times
munmap_chunk(): invalid pointer
Aborted (core dumped)
Fixes: 240505b2d0 ("perf tool_pmu: Factor tool events into their own PMU")
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20250226104111.564443-2-james.clark@linaro.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Rather than scanning core or all PMUs, allow pmu_read_sysfs to read
some combination of core, other, hwmon and tool PMUs. The PMUs that
should be read and are already read are held as bitmaps. It is known
that a "hwmon_" prefix is necessary for a hwmon PMU's name, similarly
with "tool", so only scan those PMUs in situations the PMU name or the
PMU's type number make sense to.
The number of openat system calls reduces from 276 to 98 for a hwmon
event. The number of openats for regular perf events isn't changed.
Signed-off-by: Ian Rogers <irogers@google.com>
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20250201074320.746259-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Legacy events typically don't have a PMU when added leading to
mismatched legacy/non-legacy cases in find_stat. Use evsel__find_pmu
to make sure the evsel PMU is looked up. Update the evsel__find_pmu
code to look for the PMU using the extended config type or, for legacy
hardware/hw_cache events on non-hybrid systems, just use the core PMU.
Before:
```
$ perf stat -e cycles,cpu/instructions/ -a sleep 1
Performance counter stats for 'system wide':
215,309,764 cycles
44,326,491 cpu/instructions/
1.002555314 seconds time elapsed
```
After:
```
$ perf stat -e cycles,cpu/instructions/ -a sleep 1
Performance counter stats for 'system wide':
990,676,332 cycles
1,235,762,487 cpu/instructions/ # 1.25 insn per cycle
1.002667198 seconds time elapsed
```
Fixes: 3612ca8e29 ("perf stat: Fix the hard-coded metrics calculation on the hybrid")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: James Clark <james.clark@linaro.org>
Tested-by: Leo Yan <leo.yan@arm.com>
Tested-by: Atish Patra <atishp@rivosinc.com>
Link: https://lore.kernel.org/r/20250109222109.567031-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Use the regular PMU approaches with tool json events to reduce the
amount of special tool_pmu code - tool_pmu__config_terms and
tool_pmu__for_each_event_cb are removed. Some functions remain, like
tool_pmu__str_to_event, as conveniences to metricgroups. Add
tool_pmu__skip_event/tool_pmu__num_skip_events to handle the case that
tool json events shouldn't appear on certain architectures. This isn't
done in jevents.py due to complexity in the empty-pmu-events.c and
when all vendor json is built into the tool.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Rather than treat tool events as a special kind of event, create a
tool only PMU where the events/aliases match the existing
duration_time, user_time and system_time events. Remove special
parsing and printing support for the tool events, but add function
calls for when PMU functions are called on a tool_pmu.
Move the tool PMU code in evsel into tool_pmu.c to better encapsulate
the tool event behavior in that file.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20241002032016.333748-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The mrvl_ddr_pmu is uncore and has a hexadecimal address suffix while
the previous PMU sorting/merging code assumes uncore PMU names start
with uncore_ and have a decimal suffix. Because of the previous
assumption it isn't possible to wildcard the mrvl_ddr_pmu.
Modify pmu_name_len_no_suffix but also remove the suffix number out
argument, this is because we don't know if a suffix number of say 100
is in hexadecimal or decimal. As the only use of the suffix number is
in comparisons, it is safe there to compare the values as hexadecimal.
Modify perf_pmu__match_ignoring_suffix so that hexadecimal suffixes
are ignored.
Only allow hexadecimal suffixes to be greater than length 2 (ie 3 or
more) so that S390's cpum_cf PMU doesn't lose its suffix.
Change the return type of pmu_name_len_no_suffix to size_t to
workaround GCC incorrectly determining the result could be negative.
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: James Clark <james.clark@arm.com>
Cc: Robin Murphy <robin.murphy@arm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Will Deacon <will@kernel.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Bharat Bhushan <bbhushan2@marvell.com>
Cc: Bhaskara Budiredla <bbudiredla@marvell.com>
Cc: Tuan Phan <tuanphan@os.amperecomputing.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20240515060114.3268149-2-irogers@google.com
PMU alias names were computed when the first perf_pmu is created,
scanning all PMUs in event sources for a file called alias that
generally doesn't exist. Switch to trying to load the file when all
PMU related files are loaded in lookup. This would cause a PMU name
lookup of an alias name to fail if no PMUs were loaded, so in that
case all PMUs are loaded and the find repeated. The overhead is
similar but in the (very) general case not all PMUs are scanned for
the alias file.
As the overhead occurs once per invocation it doesn't show in perf
bench internals pmu-scan. On a tigerlake machine, the number of openat
system calls for an event of cpu/cycles/ with perf stat reduces from
94 to 69 (ie 25 fewer openat calls).
Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: James Clark <james.clark@arm.com>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Link: https://lore.kernel.org/r/20230925062323.840799-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
pmu__find_core_pmu() more logically belongs in pmus.c because it
iterates over all PMUs, so move it to pmus.c
At the same time rename it to perf_pmus__find_core_pmu() to match the
naming convention in this file.
list_prepare_entry() can't be used in perf_pmus__scan_core() anymore now
that it's called from the same compilation unit. This is with -O2
(specifically -O1 -ftree-vrp -finline-functions
-finline-small-functions) which allow the bounds of the array
access to be determined at compile time. list_prepare_entry() subtracts
the offset of the 'list' member in struct perf_pmu from &core_pmus,
which isn't a struct perf_pmu. The compiler sees that pmu results in
&core_pmus - 8 and refuses to compile. At runtime this works because
list_for_each_entry_continue() always adds the offset back again before
dereferencing ->next, but it's technically undefined behavior. With
-fsanitize=undefined an additional warning is generated.
Using list_first_entry_or_null() to get the first entry here avoids
doing &core_pmus - 8 but has the same result and fixes both the compile
warning and the undefined behavior warning. There are other uses of
list_prepare_entry() in pmus.c, but the compiler doesn't seem to be
able to see that they can also be called with &core_pmus, so I won't
change any at this time.
Signed-off-by: James Clark <james.clark@arm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Eduard Zingerman <eddyz87@gmail.com>
Cc: Will Deacon <will@kernel.org>
Cc: Leo Yan <leo.yan@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Jing Zhang <renyu.zj@linux.alibaba.com>
Cc: Haixin Yu <yuhaixin.yhx@linux.alibaba.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: linux-arm-kernel@lists.infradead.org
Link: https://lore.kernel.org/r/20230913153355.138331-2-james.clark@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Add a PMUs scan that ignores duplicates. When there are multiple PMUs
that differ only by suffix, by default just list the first one and
skip all others. The scan routine checks that the PMU names match but
doesn't enforce that the numbers are consecutive as for some PMUs
there are gaps. If "-v" is passed to "perf list" then list all PMUs.
With the previous change duplicate PMUs are no longer printed but the
suffix of the first is printed. When duplicate PMUs are being skipped
avoid printing the suffix.
Before:
$ perf list
...
uncore_imc_free_running_0/data_read/ [Kernel PMU event]
uncore_imc_free_running_0/data_total/ [Kernel PMU event]
uncore_imc_free_running_0/data_write/ [Kernel PMU event]
uncore_imc_free_running_1/data_read/ [Kernel PMU event]
uncore_imc_free_running_1/data_total/ [Kernel PMU event]
uncore_imc_free_running_1/data_write/ [Kernel PMU event]
After:
$ perf list
...
uncore_imc_free_running/data_read/ [Kernel PMU event]
uncore_imc_free_running/data_total/ [Kernel PMU event]
uncore_imc_free_running/data_write/ [Kernel PMU event]
...
$ perf list -v
uncore_imc_free_running_0/data_read/ [Kernel PMU event]
uncore_imc_free_running_0/data_total/ [Kernel PMU event]
uncore_imc_free_running_0/data_write/ [Kernel PMU event]
uncore_imc_free_running_1/data_read/ [Kernel PMU event]
uncore_imc_free_running_1/data_total/ [Kernel PMU event]
uncore_imc_free_running_1/data_write/ [Kernel PMU event]
...
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20230825135237.921058-3-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Sort PMUs by name. If two PMUs have the same name but differ by
suffix, sort the suffixes numerically.
For example, "breakpoint" comes before "cpu",
"uncore_imc_free_running_0" comes before "uncore_imc_free_running_1".
Suffixes need to be treated specially as otherwise they will be ordered
like 0, 1, 10, 11, .., 2, 20, 21, .., etc. Only PMUs starting 'uncore_'
are considered to have a potential suffix.
Sorting of PMUs is done so that later patches can skip duplicate uncore
PMUs that differ only by there suffix.
Committer notes:
Used the more compact, intention revealing strstarts() function we got
from the kernel sources:
- if (strncmp(str, "uncore_", 7))
+ if (!strstarts(str, "uncore_"))
Also in pmus_cmp() the lhs_num and rhs_num variables may end up not
being set for non "uncore_" prefixed PMUs in pmu_name_len_no_suffix(),
or at least gcc 7.5 in some distros (opensuse 15.5, to be EOLed in
Dec/2024) thins so, so initialize both to zero.
Reviewed-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: John Garry <john.g.garry@oracle.com>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Link: https://lore.kernel.org/r/20230825135237.921058-2-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Numeric events are either raw events or those with ABI defined numbers
matched by the lexer. PERF_TYPE_HARDWARE and PERF_TYPE_HW_CACHE events
should wildcard match on hybrid systems. So "cycles" should match each
PMU type with an extended type, not just PERF_TYPE_HARDWARE.
Change wildcard matching to add the event even if wildcard PMU
scanning fails, there will be no extended type but this best matches
previous behavior.
Only set the extended type when the event type supports it and when
perf_pmus__supports_extended_type is true. This new function returns
true if >1 core PMU and avoids potential errors on older kernels.
Modify evsel__compute_group_pmu_name using a helper
perf_pmu__is_software to determine when grouping should occur. Try to
use PMUs, and evsel__find_pmu, as being more dependable than
evsel->pmu_name.
Set a parse events error if a hardware term's PMU lookup fails, to
provide extra diagnostics.
Fixes: 8bc75f699c ("perf parse-events: Support wildcards on raw events")
Reported-by: Kan Liang <kan.liang@linux.intel.com>
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@amd.com>
Cc: Rob Herring <robh@kernel.org>
Cc: Thomas Richter <tmricht@linux.ibm.com>
Cc: Xing Zhengjun <zhengjun.xing@linux.intel.com>
Link: https://lore.kernel.org/r/20230601082954.754318-4-irogers@google.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
