linux-stable.git/tools/perf, branch v6.6.141

perf util: Kill die() prototype, dead for a long time

2026-05-23T11:03:20+00:00

[ Upstream commit e5cce1b9c82fbd48e2f1f7a25a9fad8ee228176f ]

In fef2a735167a827a ("perf tools: Kill die()") the die() function was
removed, but not the prototype in util.h, now when building with
LIBPERL=1, during a 'make -C tools/perf build-test' routine test, it is
failing as perl likes die() calls and then this clashes with this
remnant, remove it.

Fixes: fef2a735167a827a ("perf tools: Kill die()")
Reviewed-by: Ian Rogers 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf expr: Return -EINVAL for syntax error in expr__find_ids()

2026-05-23T11:03:20+00:00

[ Upstream commit 3a61fd866ef9aaa1d3158b460f852b74a2df07f4 ]

expr__find_ids() propagates the parser return value directly.  For syntax
errors, the parser can return a positive value, but callers treat it as
success, e.g., for below case on Arm64 platform:

  metric expr 100 * (STALL_SLOT_BACKEND / (CPU_CYCLES * #slots) - BR_MIS_PRED * 3 / CPU_CYCLES) for backend_bound
  parsing metric: 100 * (STALL_SLOT_BACKEND / (CPU_CYCLES * #slots) - BR_MIS_PRED * 3 / CPU_CYCLES)
  Failure to read '#slots' literal: #slots = nan
  syntax error

Convert positive parser returns in expr__find_ids() to -EINVAL, as a
result, the error value will be respected by callers.

Before:

  perf stat -C 5
  Failure to read '#slots'Failure to read '#slots'Failure to read '#slots'Failure to read '#slots'Segmentation fault

After:

  perf stat -C 5
  Failure to read '#slots'Cannot find metric or group `Default'

Fixes: ded80bda8bc9 ("perf expr: Migrate expr ids table to a hashmap")
Signed-off-by: Leo Yan 
Reviewed-by: Ian Rogers 
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf lock: Fix option value type in parse_max_stack

2026-05-23T11:03:20+00:00

[ Upstream commit cfaade34b52aa1ec553044255702c4b31b57c005 ]

The value is a void* and the address of an int, max_stack_depth, is
set up in the perf lock options. The parse_max_stack function treats
the int* as a long*, make this more correct by declaring the value to
be an int*.

Fixes: 0a277b622670 ("perf lock contention: Check --max-stack option")
Signed-off-by: Ian Rogers 
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf: tools: cs-etm: Fix print issue for Coresight debug in ETE/TRBE trace

2026-05-23T11:03:20+00:00

[ Upstream commit 6c478e7b3eba3f387a2d6c749e3e3ee0f8ad1c53 ]

Building perf with CORESIGHT=1 and the optional CSTRACE_RAW=1 enables
additional debug printing of raw trace data when using command:-
perf report --dump.

This raw trace prints the CoreSight formatted trace frames, which may be
used to investigate suspected issues with trace quality / corruption /
decode.

These frames are not present in ETE + TRBE trace.
This fix removes the unnecessary call to print these frames.

This fix also rationalises implementation - original code had helper
function that unnecessarily repeated initialisation calls that had
already been made.

Due to an addtional fault with the OpenCSD library, this call when ETE/TRBE
are being decoded will cause a segfault in perf. This fix also prevents
that problem for perf using older (<= 1.8.0 version) OpenCSD libraries.

Fixes: 68ffe3902898 ("perf tools: Add decoder mechanic to support dumping trace data")
Reported-by: Leo Yan 
Signed-off-by: Mike Leach 
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

perf branch: Avoid incrementing NULL

2026-05-23T11:03:20+00:00

[ Upstream commit c969a9d7bbf46f983c4a48566b3b2f7340b02296 ]

If the entry is NULL the value is meaningless so early return NULL to
avoid an increment of NULL. This was happening in calls from
has_stitched_lbr when running the "perf record LBR tests". The return
value isn't used in that case, so returning NULL as no effect.

Fixes: 42bbabed09ce ("perf tools: Add hw_idx in struct branch_stack")
Signed-off-by: Ian Rogers 
Signed-off-by: Namhyung Kim 
Signed-off-by: Sasha Levin

Revert "perf unwind-libdw: Fix invalid reference counts"

2026-04-27T13:23:33+00:00

This reverts commit eddddf4ed7f69697cb54e714e773f764c8d3b67e.

Upstream commit f815fc0c66e7 ("perf unwind-libdw: Fix invalid reference counts"),
was backported to v6.6.128 as eddddf4ed7f6.

However, this commit depends on map_symbol__exit, which was introduced
in v6.7 as commit 56e144fe9826 ("perf mem_info: Add and use
map_symbol__exit and addr_map_symbol__exit") and is absent in v6.6.y.
This results in a build failure.

This is a revert of a backport, so there is no upstream commit.

Signed-off-by: Kenta Akagi 
Signed-off-by: Sasha Levin

perf callchain: Fix srcline printing with inlines

2026-03-04T12:20:30+00:00

[ Upstream commit abec464767b5d26f0612250d511c18f420826ca1 ]

sample__fprintf_callchain() was using map__fprintf_srcline() which won't
report inline line numbers.

Fix by using the srcline from the callchain and falling back to the map
variant.

Fixes: 25da4fab5f66e659 ("perf evsel: Move fprintf methods to separate source file")
Reviewed-by: James Clark 
Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Howard Chu 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephen Brennan 
Cc: Tony Jones 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf unwind-libdw: Fix invalid reference counts

2026-03-04T12:20:30+00:00

[ Upstream commit f815fc0c66e777c727689666cfb46b8d461c2f99 ]

The addition of addr_location__exit() causes use-after put on the maps
and map references in the unwind info. Add the gets and then add the
map_symbol__exit() calls.

Fixes: 0dd5041c9a0eaf8c ("perf addr_location: Add init/exit/copy functions")
Reviewed-by: James Clark 
Signed-off-by: Ian Rogers 
Cc: Adrian Hunter 
Cc: Alexander Shishkin 
Cc: Howard Chu 
Cc: Ingo Molnar 
Cc: Jiri Olsa 
Cc: Namhyung Kim 
Cc: Peter Zijlstra 
Cc: Stephen Brennan 
Cc: Tony Jones 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf test stat tests: Fix for virtualized machines

2026-03-04T12:20:30+00:00

[ Upstream commit e272628902c1c96731e2d9f62a7fc77767686eb0 ]

On s390 'perf test's 'perf stat tests', subtest test_hybrid fails for
z/VM systems.  The root cause is this statement:

  $(perf stat -a -- sleep 0.1 2>&1 |\
                  grep -E "/cpu-cycles/[uH]*|  cpu-cycles[:uH]* -c)

The 'perf stat' output on a s390 z/VM system is

  # perf stat -a -- sleep 0.1 2>&1
  Performance counter stats for 'system wide':

        56      context-switches  #     46.3 cs/sec  cs_per_second
  1,210.41 msec cpu-clock         #     11.9 CPUs  CPUs_utilized
        12      cpu-migrations    #      9.9 migrations/sec ...
        81      page-faults       #     66.9 faults/sec ...

        0.100891009 seconds time elapsed

The grep command does not match any single line and exits with error
code 1.

As the bash script is executed with 'set -e', it aborts with the first
error code being non-zero.

Fix this and use 'wc -l' to count matching lines instead of 'grep ... -c'.

Output before:

  # perf test 102
  102: perf stat tests                      : FAILED!
  #

Output after:

  # perf test 102
  102: perf stat tests                      : Ok
  #

Fixes: bb6e7cb11d97ce19 ("perf tools: Add fallback for exclude_guest")
Reviewed-by: Ian Rogers 
Reviewed-by: James Clark 
Signed-off-by: Thomas Richter 
Cc: Alexander Gordeev 
Cc: Heiko Carstens 
Cc: Jan Polensky 
Cc: linux-s390@vger.kernel.org
Cc: Namhyung Kim 
Cc: Sumanth Korikkar 
Cc: Vasily Gorbik 
Signed-off-by: Arnaldo Carvalho de Melo 
Signed-off-by: Sasha Levin

perf test stat: Update test expectations and events

2026-03-04T12:20:30+00:00

[ Upstream commit a48cd551d7436be3b1bd65c63a6d00163f7e7706 ]

test_stat_record_report and test_stat_record_script used default
output which triggers a bug when sending metrics. As this isn't
relevant to the test switch to using named software events.

Update the match in test_hybrid as the cycles event is now cpu-cycles
to workaround potential ARM issues.

Signed-off-by: Ian Rogers 
Signed-off-by: Namhyung Kim 
Stable-dep-of: e272628902c1 ("perf test stat tests: Fix for virtualized machines")
Signed-off-by: Sasha Levin