kernel/tools/perf/tests/shell, branch linux-6.13.y

perf bpf-filter: Fix a parsing error with comma

2025-04-10T12:41:50Z

[ Upstream commit 35d13f841a3d8159ef20d5e32a9ed3faa27875bc ] The previous change to support cgroup filters introduced a bug that pathname can include commas. It confused the lexer to treat an item and the trailing comma as a single token. And it resulted in a parse error: $ sudo perf record -e cycles:P --filter 'period > 0, ip > 64' -- true perf_bpf_filter: Error: Unexpected item: 0, perf_bpf_filter: syntax error, unexpected BFT_ERROR, expecting BFT_NUM Usage: perf record [] [] or: perf record [] -- [] --filter event filter It should get "0" and "," separately. An easiest fix would be to remove "," from the possible pathname characters. As it's for cgroup names, probably ok to assume it won't have commas in the pathname. I found that the existing BPF filtering test didn't have any complex filter condition with commas. Let's update the group filter test which is supposed to test filter combinations like this. Link: https://lore.kernel.org/r/20250307220922.434319-1-namhyung@kernel.org Fixes: 91e88437d5156b20 ("perf bpf-filter: Support filtering on cgroups") Reported-by: Sally Shi Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin

perf tools: annotate asm_pure_loop.S

2025-04-10T12:41:50Z

[ Upstream commit 9a352a90e88a041f4b26d359493e12a7f5ae1a6a ] Annotate so it is built with non-executable stack. Fixes: 8b97519711c3 ("perf test: Add asm pureloop test tool") Signed-off-by: Marcus Meissner Reviewed-by: Leo Yan Link: https://lore.kernel.org/r/20250323085410.23751-1-meissner@suse.de Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin

perf test stat_all_pmu.sh: Correctly check 'perf stat' result

2025-04-10T12:41:48Z

[ Upstream commit 02ba09c8ab9406f30c5c63b7cfd4b300c3c2c32c ] Test case "stat_all_pmu.sh" is not correctly checking 'perf stat' output due to a poor design. Firstly, having the 'set -e' option with a trap catching the sigexit causes the shell to exit immediately if 'perf stat' ends with any non-zero value, which is then caught by the trap reporting an unexpected signal. This causes events that should be parsed by the if-else statement to be caught by the trap handler and are reported as errors: $ perf test -vv "perf all pmu" Testing i915/actual-frequency/ Unexpected signal in main Error: Access to performance monitoring and observability operations is limited. Secondly, the if-else branches are not exclusive as the checking if the event is present in the output log covers also the "" events, which should be accepted, and also the "Bad name events", which should be rejected. Remove the "set -e" option from the test case, correctly parse the "perf stat" output log and check its return value. Add the missing outputs for the 'perf stat' result and also add logs messages to report the branch that parsed the event for more info. Fixes: 7e73ea40295620e7 ("perf test: Ignore security failures in all PMU test") Signed-off-by: Veronika Molnarova Tested-by: Qiao Zhao Link: https://lore.kernel.org/r/20241122231233.79509-1-vmolnaro@redhat.com Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin

perf test: Skip syscall enum test if no landlock syscall

2025-02-08T09:02:14Z

[ Upstream commit 72d81e10628be6a948463259cbb6d3b670b20054 ] The perf trace enum augmentation test specifically targets landlock_ add_rule syscall but IIUC it's an optional and can be opt-out by a kernel config. Currently trace_landlock() runs `perf test -w landlock` before the actual testing to check the availability but it's not enough since the workload always returns 0. Instead it could check if perf trace output has 'landlock' string. Fixes: d66763fed30f0bd8c ("perf test trace_btf_enum: Add regression test for the BTF augmentation of enums in 'perf trace'") Reviewed-by: Howard Chu Link: https://lore.kernel.org/r/20250128170629.1251574-1-namhyung@kernel.org Signed-off-by: Namhyung Kim Signed-off-by: Sasha Levin

perf test stat: Avoid hybrid assumption when virtualized

2025-02-08T09:01:38Z

[ Upstream commit f9c506fb69bdcfb9d7138281378129ff037f2aa1 ] The cycles event will fallback to task-clock in the hybrid test when running virtualized. Change the test to not fail for this. Fixes: 65d11821910bd910 ("perf test: Add a test for default perf stat command") Reviewed-by: James Clark Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20241212173354.9860-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf stat: Fix trailing comma when there is no metric unit

2025-02-08T09:01:34Z

[ Upstream commit 967364894e61b15819a0c11231512ecd5a46b503 ] Now that printing metric-value and metric-unit is optional, print_running_json() shouldn't add the comma in case it becomes trailing. Replace all manual JSON comma stuff with a json_out() function that uses the existing os->first tracking and auto inserts a comma if it's needed. Update the test to handle that two of the fields can be missing. This fixes the following test failure on Cortex A57 where the branch misses metric is missing a required event: $ perf test -vvv "json output" 106: perf stat JSON output linter: --- start --- test child forked, pid 665682 Checking json output: no args Test failed for input: {"counter-value" : "3112.000000", "unit" : "", "event" : "armv8_pmuv3_1/branch-misses/", "event-runtime" : 20699340, "pcnt-running" : 100.00, } ... json.decoder.JSONDecodeError: Expecting property name enclosed in double quotes: line 12 column 144 (char 2109) ---- end(-1) ---- 106: perf stat JSON output linter : FAILED! Fixes: e1cc918b6cfd1206 ("perf stat: Drop metric-unit if unit is NULL") Signed-off-by: James Clark Tested-by: Ian Rogers Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Tim Chen Cc: Yicong Yang Link: https://lore.kernel.org/r/20241112160048.951213-2-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Sasha Levin

perf/test: fix perf ftrace test on s390

2024-11-22T21:36:44Z

On s390 the perf test case ftrace sometimes fails as follows: # ./perf test ftrace 79: perf ftrace tests : FAILED! # The failure depends on the kernel .config file. Some configurations always work fine, some do not. The ftrace profile test mostly fails, because the ring buffer was not large enough, and some lines (especially the interesting ones with nanosleep in it) where dropped. To achieve success for all tested kernel configurations, enlarge the buffer to store the traces completely without wrapping. The default buffer size is too small for all kernel configurations. Set the buffer size of for the ftrace profile test to 16 MB. Output after: # ./perf test ftrace 79: perf ftrace tests : Ok # Signed-off-by: Thomas Richter Acked-by: Namhyung Kim Cc: agordeev@linux.ibm.com Cc: gor@linux.ibm.com Cc: hca@linux.ibm.com Cc: sumanthk@linux.ibm.com Link: https://lore.kernel.org/r/20241119064856.641446-1-tmricht@linux.ibm.com Suggested-by: Sven Schnelle Suggested-by: Namhyung Kim Signed-off-by: Namhyung Kim

perf tests: Make leader sampling test work without branch event

2024-11-16T19:30:39Z

Arm a57 only has speculative branch events so this test fails there. The test doesn't depend on branch instructions so change it to instructions which is pretty much guaranteed to be everywhere. The test_branch_counter() test above already tests for the existence of the branches event and skips if its not present. Reviewed-by: Ian Rogers Signed-off-by: James Clark Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Dapeng Mi Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Veronika Molnarova Link: https://lore.kernel.org/r/20241115161600.228994-1-james.clark@linaro.org Signed-off-by: Arnaldo Carvalho de Melo

perf test shell trace_exit_race: Use --no-comm to avoid cases where COMM isn't resolved

2024-11-16T19:30:32Z

The purpose of this test is to test for races in the exit of 'perf trace' missing the last events, it was failing when the COMM wasn't resolved either because we missed some PERF_RECORD_COMM or somehow raced on getting it from procfs. Add --no-comm to the 'perf trace' command line so that we get a consistent, pid only output, which allows the test to achieve its goal. This is the output from 'perf trace --no-comm -e syscalls:sys_enter_exit_group': 0.000 21953 syscalls:sys_enter_exit_group() 0.000 21955 syscalls:sys_enter_exit_group() 0.000 21957 syscalls:sys_enter_exit_group() 0.000 21959 syscalls:sys_enter_exit_group() 0.000 21961 syscalls:sys_enter_exit_group() 0.000 21963 syscalls:sys_enter_exit_group() 0.000 21965 syscalls:sys_enter_exit_group() 0.000 21967 syscalls:sys_enter_exit_group() 0.000 21969 syscalls:sys_enter_exit_group() 0.000 21971 syscalls:sys_enter_exit_group() Now it passes: root@number:~# perf test "trace exit race" 110: perf trace exit race : Ok root@number:~# root@number:~# perf test -v "trace exit race" 110: perf trace exit race : Ok root@number:~# If we artificially make it run just 9 times instead of the 10 it runs, i.e. by manually doing: trace_shutdown_race() { for _ in $(seq 9); do that 9 is $iter, 10 in the patch, we get: root@number:~# vim ~acme/libexec/perf-core/tests/shell/trace_exit_race.sh root@number:~# perf test -v "trace exit race" --- start --- test child forked, pid 24629 Missing output, expected 10 but only got 9 ---- end(-1) ---- 110: perf trace exit race : FAILED! root@number:~# I.e. 9 'perf trace' calls produced the expected output, the inverse grep didn't show anything, so the patch provided by Howard for the previous patch kicks in and shows a more informative message. Tested-by: Howard Chu Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Benjamin Peterson Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/lkml/ZzdknoHqrJbojb6P@x1 Signed-off-by: Arnaldo Carvalho de Melo

perf test shell trace_exit_race: Show what went wrong in verbose mode

2024-11-15T15:31:01Z

If it fails we need to check what was the reason, what were the lines that didn't match the expected format, so: root@number:~# perf test -v "trace exit race" --- start --- test child forked, pid 2028724 Lines not matching the expected regexp: ' +[0-9]+\.[0-9]+ +true/[0-9]+ syscalls:sys_enter_exit_group$': 0.000 :2028750/2028750 syscalls:sys_enter_exit_group() ---- end(-1) ---- 110: perf trace exit race : FAILED! root@number:~# In this case we're not resolving the process COMM for some reason and fallback to printing just the pid/tid, this will be fixed in a followup patch. Howard Chu spotted a problem with single code surrounding a regexp, that made the test always fail, but since there were some failures when I tested (COMM not being resolved in some of the results) the end inverse grep would show some lines and thus didn't notice the single quote problem. He also provided a patch to test if less than the number of expected matches took place but all of them with the expected output, in which case the inverse grep wouldn't show anything, confusing the tester. Reviewed-by: Howard Chu Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Benjamin Peterson Cc: Ian Rogers Cc: Ingo Molnar Cc: Jiri Olsa Cc: Kan Liang Cc: Mark Rutland Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/lkml/ZzdknoHqrJbojb6P@x1 Signed-off-by: Arnaldo Carvalho de Melo