Force loading all PMUs adds significant cost because DRM and other
PMUs are loaded, it should also not be required if the pmus__
functions are used.
Tested by run perf test, in particular the pfm related tests. Also
`perf list` is identical before and after.
Before:
$ time ./perf test pfm
54: Test libpfm4 support :
54.1: test of individual --pfm-events : Ok
54.2: test groups of --pfm-events : Ok
103: perf all libpfm4 events test : Ok
real 0m8.933s
user 0m1.824s
sys 0m7.122s
After:
$ time ./perf test pfm
54: Test libpfm4 support :
54.1: test of individual --pfm-events : Ok
54.2: test groups of --pfm-events : Ok
103: perf all libpfm4 events test : Ok
real 0m5.259s
user 0m1.793s
sys 0m3.570s
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250722013449.146233-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
FILENAME_MAX is the same as PATH_MAX (4kb) in glibc rather than
NAME_MAX's 255. Switch to using NAME_MAX and ensure the '\0' is
accounted for in the path's buffer size.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250717150855.1032526-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
FILENAME_MAX is the same as PATH_MAX (4kb) in glibc rather than
NAME_MAX's 255. Switch to using NAME_MAX and ensure the '\0' is
accounted for in the path's buffer size.
Fixes: 754baf426e ("perf pmu: Change aliases from list to hashmap")
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250717150855.1032526-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
When the clang toolchain has stack protection enabled, the bpf
skeletons build fails with:
error: A call to built-in function '__stack_chk_fail' is not supported.
Since stack-protector makes no sense for the BPF bits, just unconditionally
disable it.
See also similar case at 878625e1c7
Signed-off-by: Federico Pellegrin <fede@evolware.org>
Link: https://lore.kernel.org/r/20250718041224.12389-1-fede@evolware.org
[ rearrange long lines ]
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Previously when running perf trace timehist --state, when recording
processes in the zombie state the process name would not be decoded
properly and appears with just the PID:
1140057.412177 [0006] Mutter Input Th[3139/3104] 0.956 0.019 0.041 S
1140057.412222 [0012] :1248612[1248612] 0.000 0.000 0.332 Z
1140057.412275 [0004] <idle> 0.052 0.052 0.953 I
1140057.412284 [0008] <idle> 0.070 0.070 0.932 I
1140057.412333 [0004] KMS thread[3126/3104] 0.953 0.112 0.058 S
Now some extra processing has been added to decode the process name:
1140057.412177 [0006] Mutter Input Th[3139/3104] 0.956 0.019 0.041 S
1140057.412222 [0012] sleep[1248612] 0.000 0.000 0.332 Z
1140057.412275 [0004] <idle> 0.052 0.052 0.953 I
1140057.412284 [0008] <idle> 0.070 0.070 0.932 I
1140057.412333 [0004] KMS thread[3126/3104] 0.953 0.112 0.058 S
Signed-off-by: Anubhav Shelat <ashelat@redhat.com>
Link: https://lore.kernel.org/r/20250716203914.45772-2-ashelat@redhat.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Switch to assuming python3. Fix minor pylint issues on line length,
repeated compares, not using f-strings and variable case. Add type
hints and check with mypy.
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250716004635.31161-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In addition to the function latency, it can measure events latencies.
Some kernel tracepoints are paired and it's menningful to measure how
long it takes between the two events. The latency is tracked for the
same thread.
Currently it only uses BPF to do the work but it can be lifted later.
Instead of having separate a BPF program for each tracepoint, it only
uses generic 'event_begin' and 'event_end' programs to attach to any
(raw) tracepoints.
$ sudo perf ftrace latency -a -b --hide-empty \
-e i915_request_wait_begin,i915_request_wait_end -- sleep 1
# DURATION | COUNT | GRAPH |
256 - 512 us | 4 | ###### |
2 - 4 ms | 2 | ### |
4 - 8 ms | 12 | ################### |
8 - 16 ms | 10 | ################ |
# statistics (in usec)
total time: 194915
avg time: 6961
max time: 12855
min time: 373
count: 28
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250714052143.342851-1-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Returning NULL for out of bound CPU or thread map items causes
internal errors. Fix by correctly setting the error to be an index
error.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-14-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The struct pyrf_evlist embeds the evlist requiring the copying from
things like parsed events. The copying logic handles the leader being
the event itself, but if the leader group event is a different in the
list it will cause an evsel to point to the evsel in the list that was
copied from which is bad. Fix this by adding another pass over the
evlist rewriting leaders, simplified by the introductin of two evlist
helpers.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-13-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tool PMUs assume that stat's process_counter_values is being used to
read the counters. Specifically they hold onto old values in
evsel->prev_raw_counts and give the cumulative count based off of this
value. Update pyrf_evsel__read to allocate counts and prev_raw_counts,
use evsel__read_counter rather than perf_evsel__read so tool PMUs are
read from not just perf_event_open events, make the returned
pyrf_counts_values contain the delta value rather than the cumulative
value.
Fixes: 739621f657 ("perf python: Add evsel read method")
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-12-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The evsel__pmu_name helper will internally use evsel__find_pmu that
handles legacy events, extended types, etc. in determining a PMU and
will provide a better value than just trying to access the PMU's name
directly as the PMU may not have been computed.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-10-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
If the short and long descriptions are the same then save space and
don't store both of them. When storing the desc in the perf_pmu_alias,
don't duplicate the desc into the long_desc.
By avoiding storing the duplicate the size of the events string in the
binary on x86 is reduced by 29,840 bytes.
Fix tests that expect a duplicated description.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-9-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Metrics will fill in the context to have mappings from an event to a
count. When counts are added they replace existing mappings which
generally shouldn't exist with aggregation. Switch to accumulating to
better support cases where perf stat's aggregation isn't used and we
may see a counter more than once.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-8-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The rblist of metric_event that then have a list of associated
metric_expr is moved out of the stat_config and into the evlist. This
is done as part of refactoring things for python, having the state
split in two places complicates that implementation. The evlist is
doing the harder work of enabling and disabling events, the metrics
are needed to compute a value and it doesn't seem unreasonable to hang
them from the evlist.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-7-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Factor metricgroup__for_each_metric into its own function handling
regular and sys metrics. Make the metric adding and printing code use
it, move the printing code into print-events files.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-6-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
If sysfs isn't mounted then we may fail to read a PMU's type. In this
situation resort to lookup of wellknown types. Only applies to
software, tracepoint and breakpoint PMUs.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-5-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Add missing breakpoint and raw types. Avoid a switch, just use a
lookup array. Switch the type to unsigned to avoid checking negative
values.
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-3-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Long names like ucsi_source_psy_USBC000:001 when prefixed with hwmon_
exceed the buffer size and the last digit is lost. This causes
confusion with similar names like ucsi_source_psy_USBC000:002. Extend
the buffer size to avoid this.
Fixes: 53cc0b351e ("perf hwmon_pmu: Add a tool PMU exposing events from hwmon in sysfs")
Signed-off-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250710235126.1086011-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Since the commit e9846f5ead ("perf test: In forked mode add check that
fds aren't leaked"), the test "Breakpoint accounting" reports the error:
# perf test -vvv "Breakpoint accounting"
20: Breakpoint accounting:
--- start ---
test child forked, pid 373
failed opening event 0
failed opening event 0
watchpoints count 4, breakpoints count 6, has_ioctl 1, share 0
wp 0 created
wp 1 created
wp 2 created
wp 3 created
wp 0 modified to bp
wp max created
---- end(0) ----
Leak of file descriptor 7 that opened: 'anon_inode:[perf_event]'
A watchpoint's file descriptor was not properly released. This patch
fixes the leak.
Fixes: 032db28e5f ("perf tests: Add breakpoint accounting/modify test")
Reported-by: Aishwarya TCV <aishwarya.tcv@arm.com>
Signed-off-by: Leo Yan <leo.yan@arm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250711-perf_fix_breakpoint_accounting-v1-1-b314393023f9@arm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It has been decided to remove the support IMMUTABLE futex.
perf bench was one of the eary users for testing purposes. Now that the
API is removed before it could be used in an official release, remove
the bits from perf, too.
Remove Remove support for IMMUTABLE futex.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250710110011.384614-7-bigeasy@linutronix.de
According to the z16 and z17 Principle of Operation documents
SA22-7832-13 and SA22-7832-14 the event 4210 is named
PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_AES_256
without a trailing 'A'. Adjust the json definition files
for this event and remove the trailing 'A' character.
PCC_COMPUTE_LAST_BLOCK_CMAC_USING_ENCRYPTED_AES_256A
Also remove a black ' ' between the dash '-' and the number:
xxx-AES- 192 ----> xxx-AES-192
Suggested-by: Ingo Franzki <ifranzki@linux.ibm.com>
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Ian Rogers <irogers@google.com>
Acked-by: Sumanth Korikkar <sumanthk@linux.ibm.com>
Link: https://lore.kernel.org/r/20250709072452.1595257-1-tmricht@linux.ibm.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The work_atoms should be freed after use. Add free_work_atoms() to
make sure to release all. It should use list_splice_init() when merging
atoms to prevent accessing invalid pointers.
Fixes: b1ffe8f3e0 ("perf sched: Finish latency => atom rename and misc cleanups")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-8-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
So that it can check two pointers to the same object properly when
REFCNT_CHECKING is on.
Fixes: 78c32f4cb1 ("libperf rc_check: Add RC_CHK_EQUAL")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-7-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It uses evsel->priv to save per-cpu timing information. It should be
freed when the evsel is released.
Add the priv destructor for evsel same as thread to handle that.
Fixes: 49394a2a24 ("perf sched timehist: Introduce timehist command")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-6-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Add missing thread__put() after machine__findnew_thread() or
timehist_get_thread(). Also idle threads' last_thread should be
refcounted properly.
Fixes: 699b5b920d ("perf sched timehist: Save callchain when entering idle")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-5-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
It maintains per-cpu pointers for the current thread but it doesn't
release the refcounts.
Fixes: 5e89527869 ("perf sched: Move curr_thread initialization to perf_sched__map()")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-4-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
In many perf sched subcommand saves priv data structure in the thread
but it forgot to free them. As it's an opaque type with 'void *', it
needs to register that knows how to free the data. In this case, just
regular 'free()' is fine.
Fixes: 04cb4fc4d4 ("perf thread: Allow tools to register a thread->priv destructor")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-3-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The parse_options_subcommand() allocates the usage string based on the
given subcommands. So it should reach the end of the function to free
the string to prevent memory leaks.
Fixes: 1a5efc9e13 ("libsubcmd: Don't free the usage string")
Reviewed-by: Ian Rogers <irogers@google.com>
Tested-by: Ian Rogers <irogers@google.com>
Link: https://lore.kernel.org/r/20250703014942.1369397-2-namhyung@kernel.org
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
The pipe mode header dumping was accidentally removed when tracing of
header feature events in pipe mode was added.
Minor spelling tweak to header test failure message.
Fixes: 61051f9a84 ("perf header: In pipe mode dump features without --header/-I")
Signed-off-by: Ian Rogers <irogers@google.com>
Tested-by: Namhyung Kim <namhyung@kernel.org>
Link: https://lore.kernel.org/r/20250703042000.2740640-1-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
