linux-stable.git/tools/perf/tests, branch v6.18

perf test: Fix lock contention test

2025-11-13T20:29:00+00:00

Couple of independent fixes:

1. Wire in SIGSEGV handler that terminates the test with a failure code.

2. Use "--lock-cgroup" instead of "-g"; "-g" was proposed but never
   merged. See commit 4d1792d0a2564caf ("perf lock contention: Add
   --lock-cgroup option")

3. Call cleanup() on every normal exit so trap_cleanup() doesn't mistake
   it for an unexpected signal and emit a false-negative "Unexpected
   signal in main" message.

Before patch:

  # ./perf test -vv "lock contention"
   85: kernel lock contention analysis test:
  --- start ---
  test child forked, pid 610711
  Testing perf lock record and perf lock contention
  Testing perf lock contention --use-bpf
  Testing perf lock record and perf lock contention at the same time
  Testing perf lock contention --threads
  Testing perf lock contention --lock-addr
  Testing perf lock contention --lock-cgroup
  Unexpected signal in test_aggr_cgroup
  ---- end(0) ----
   85: kernel lock contention analysis test                            : Ok

After patch:

  # ./perf test -vv "lock contention"
   85: kernel lock contention analysis test:
  --- start ---
  test child forked, pid 602637
  Testing perf lock record and perf lock contention
  Testing perf lock contention --use-bpf
  Testing perf lock record and perf lock contention at the same time
  Testing perf lock contention --threads
  Testing perf lock contention --lock-addr
  Testing perf lock contention --lock-cgroup
  Testing perf lock contention --type-filter (w/ spinlock)
  Testing perf lock contention --lock-filter (w/ tasklist_lock)
  Testing perf lock contention --callstack-filter (w/ unix_stream)
  [Skip] Could not find 'unix_stream'
  Testing perf lock contention --callstack-filter with task aggregation
  [Skip] Could not find 'unix_stream'
  Testing perf lock contention --cgroup-filter
  Testing perf lock contention CSV output
  ---- end(0) ----
   85: kernel lock contention analysis test                            : Ok

Reviewed-by: Ian Rogers 
Signed-off-by: Ravi Bangoria 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ananth Narayan 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Sandipan Das 
Cc: Santosh Shukla 
Cc: Tycho Andersen 
Signed-off-by: Arnaldo Carvalho de Melo

perf tests: Don't retest sections in "Object code reading"

2025-10-06T19:59:11+00:00

We already only test each kcore map once, but on slow systems
(particularly with network filesystems) even the non-kcore maps are
slow.

The test can test the same objdump output over and over which only wastes
time. Generalize the skipping mechanism to track all DSOs and addresses
so that each section is only tested once.

On a fully loaded ARM Juno (simulating a parallel 'perf test' run) with
a network filesystem, the original runtime is:

  real  1m51.126s
  user  0m19.445s
  sys   1m15.431s

And the new runtime is:

  real  0m48.873s
  user  0m8.031s
  sys   0m32.353s

Committer testing:

  # perf test "code read"
   22: Object code reading          : Ok
  #

Reviewed-by: Ian Rogers 
Signed-off-by: James Clark 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Leo Yan 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Signed-off-by: Arnaldo Carvalho de Melo

perf test coresight: Dismiss clang warning for unroll loop thread

2025-10-06T19:49:25+00:00

clang-18.1.3 on Ubuntu 24.04.2 reports warning:

  unroll_loop_thread.c:35:25: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
     35 |                         : /* in */ [in] "r" (in)
        |                                              ^
  unroll_loop_thread.c:39:1: warning: non-void function does not return a value [-Wreturn-type]
     39 | }
        | ^

Use the modifier "w" for 32-bit register access and return NULL at the
end of thread function.

Signed-off-by: Leo Yan 
Reviewed-by: Ian Rogers 
Link: https://lore.kernel.org/r/20251006-perf_build_android_ndk-v3-7-4305590795b2@arm.com
Cc: Palmer Dabbelt 
Cc: Albert Ou 
Cc: Alexandre Ghiti 
Cc: Nick Desaulniers 
Cc: Justin Stitt 
Cc: Bill Wendling 
Cc: Adrian Hunter 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Nathan Chancellor 
Cc: James Clark 
Cc: linux-riscv@lists.infradead.org
Cc: llvm@lists.linux.dev
Cc: Paul Walmsley 
Cc: linux-kernel@vger.kernel.org
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf test coresight: Dismiss clang warning for thread loop

2025-10-06T19:49:25+00:00

clang-18.1.3 on Ubuntu 24.04.2 reports warning:

  thread_loop.c:41:23: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
     41 |                 : /* in */ [i] "r" (i), [len] "r" (len)
        |                                     ^
  thread_loop.c:37:8: note: use constraint modifier "w"
     37 |                 "add %[i], %[i], #1\n"
        |                      ^~~~
        |                      %w[i]
  thread_loop.c:41:23: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
     41 |                 : /* in */ [i] "r" (i), [len] "r" (len)
        |                                     ^
  thread_loop.c:37:14: note: use constraint modifier "w"
     37 |                 "add %[i], %[i], #1\n"
        |                            ^~~~
        |                            %w[i]
  thread_loop.c:41:23: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
     41 |                 : /* in */ [i] "r" (i), [len] "r" (len)
        |                                     ^
  thread_loop.c:38:8: note: use constraint modifier "w"
     38 |                 "cmp %[i], %[len]\n"
        |                      ^~~~
        |                      %w[i]
  thread_loop.c:41:38: warning: value size does not match register size specified by the constraint and modifier [-Wasm-operand-widths]
     41 |                 : /* in */ [i] "r" (i), [len] "r" (len)
        |                                                    ^
  thread_loop.c:38:14: note: use constraint modifier "w"
     38 |                 "cmp %[i], %[len]\n"
        |                            ^~~~~~
        |                            %w[len]

Use the modifier "w" for 32-bit register access.

Signed-off-by: Leo Yan 
Reviewed-by: Ian Rogers 
Link: https://lore.kernel.org/r/20251006-perf_build_android_ndk-v3-6-4305590795b2@arm.com
Cc: Palmer Dabbelt 
Cc: Albert Ou 
Cc: Alexandre Ghiti 
Cc: Nick Desaulniers 
Cc: Justin Stitt 
Cc: Bill Wendling 
Cc: Adrian Hunter 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Nathan Chancellor 
Cc: James Clark 
Cc: linux-riscv@lists.infradead.org
Cc: llvm@lists.linux.dev
Cc: Paul Walmsley 
Cc: linux-kernel@vger.kernel.org
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf test coresight: Dismiss clang warning for memcpy thread

2025-10-06T19:49:25+00:00

clang-18.1.3 on Ubuntu 24.04.2 reports warning:

  memcpy_thread.c:30:1: warning: non-void function does not return a value in all control paths [-Wreturn-type]
     30 | }
        | ^

Dismiss the warning with returning NULL from the thread function.

Signed-off-by: Leo Yan 
Reviewed-by: Ian Rogers 
Link: https://lore.kernel.org/r/20251006-perf_build_android_ndk-v3-5-4305590795b2@arm.com
Cc: Palmer Dabbelt 
Cc: Albert Ou 
Cc: Alexandre Ghiti 
Cc: Nick Desaulniers 
Cc: Justin Stitt 
Cc: Bill Wendling 
Cc: Adrian Hunter 
Cc: Arnaldo Carvalho de Melo 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Nathan Chancellor 
Cc: James Clark 
Cc: linux-riscv@lists.infradead.org
Cc: llvm@lists.linux.dev
Cc: Paul Walmsley 
Cc: linux-kernel@vger.kernel.org
Cc: linux-perf-users@vger.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo

perf record: Add auto counter reload parse and regression tests

2025-10-03T19:49:51+00:00

Include event parsing and regression tests for auto counter reload
and ratio-to-prev event term.

Reviewed-by: Ian Rogers 
Signed-off-by: Thomas Falcon 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Andi Kleen 
Cc: Dapeng Mi 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Signed-off-by: Arnaldo Carvalho de Melo

perf test: Stat std output don't fail metric only

2025-10-02T18:05:41+00:00

When running on a hypervisor the expected IPC metric may be missing as
the events may fail to be read. Don't expect metric output for this
test to avoid it failing.

Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Veronika Molnarova 
Signed-off-by: Arnaldo Carvalho de Melo

perf test: Remove C python_use test

2025-10-01T19:59:11+00:00

Removed in favor of the shell script version.

Signed-off-by: Ian Rogers 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Collin Funk 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Signed-off-by: Arnaldo Carvalho de Melo

perf test: Add an 'import perf' test shell script

2025-10-01T19:59:06+00:00

The 'import perf' test needs to set up a path to the python module as
well as to know the python command to invoke.

These are hard coded at build time to be build a directory and the
python used in the build, which is less than desirable.

Avoid the hard coded values by reusing the existing shell script python
setup and determine a potential built python module via the path of the
perf executable.

Signed-off-by: Ian Rogers 
Tested-by: Arnaldo Carvalho de Melo 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Collin Funk 
Cc: Ingo Molnar 
Cc: James Clark 
Cc: Jiri Olsa 
Cc: Kan Liang 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Ravi Bangoria 
Signed-off-by: Arnaldo Carvalho de Melo

perf test: Extend branch stack sampling test for Arm64 BRBE

2025-10-01T18:31:49+00:00

BRBE emits IRQ and ERET branches for branching and returning from
trapped instructions. Add a test that loops on a trapped instruction
(MRS - Read special register) for this.

Extend the expected 'any_call' branches to include FAULT_DATA and
FAULT_INST as these are emitted by BRBE.

Reviewed-by: Ian Rogers 
Co-developed-by: German Gomez 
Signed-off-by: German Gomez 
Signed-off-by: James Clark 
Cc: Adam Young 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Anshuman Khandual 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Mark Rutland 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Rob Herring 
Cc: Will Deacon 
Signed-off-by: Arnaldo Carvalho de Melo