kernel/linux.git/tools/perf/builtin-kwork.c, branch v7.2-rc5

perf symbol: Add setters for bitfields sharing a byte to avoid concurrent update issues

2026-06-03T19:53:45+00:00

A problem with putting bitfields into struct symbol is that other bits in the symbol could be updated concurrently and only one update to the underlying storage unit happen, leading to lost updates. To avoid this, use atomics to atomically read or set part of 16-bits of flags in the symbol. Add accessors to simplify this. The idle value has 3 values in preparation for a later change that will lazily update it. Assisted-by: Gemini:gemini-3.1-pro-preview Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Alexander Gordeev Cc: Heiko Carstens Cc: Honglei Wang Cc: Jan Polensky Cc: Sumanth Korikkar Cc: Thomas Richter Cc: Vasily Gorbik Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Include file offset and event type name in skip messages

2026-06-03T19:31:03+00:00

Add the perf.data file offset and use perf_event__name() instead of raw event type integers in the 'problem processing event, skipping it' messages emitted by process_sample_event() callbacks across annotate, c2c, diff, kmem, kvm, kwork, lock, report, script, and build-id. This lets users cross-reference skipped events with 'perf report -D' output. Also add explicit #include "util/event.h" and where needed to avoid depending on transitive includes. Reviewed-by: Ian Rogers Assisted-by: Claude:claude-opus-4.6 Signed-off-by: Arnaldo Carvalho de Melo

perf kwork: Bounds check work->cpu before indexing cpus_runtime[]

2026-05-29T14:44:35+00:00

work->cpu comes from sample->cpu which is (u32)-1 when PERF_SAMPLE_CPU is absent. Stored as int, this becomes -1 which passes the signed BUG_ON(work->cpu >= MAX_NR_CPUS) but causes an out-of-bounds access on cpus_runtime[-1]. Replace the BUG_ON in top_calc_total_runtime() with an unsigned bounds check that skips entries with invalid CPU values, counting them for a summary warning. Guard the same index in profile_event_match() (bitmap OOB), top_calc_idle_time(), top_calc_irq_runtime(), top_calc_cpu_usage(), and top_calc_load_runtime(). Also guard against division by zero in top_calc_cpu_usage() when no runtime was accumulated. Reported-by: sashiko-bot@kernel.org # Running on a local machine Reviewed-by: Ian Rogers Cc: Jiri Olsa Cc: Namhyung Kim Cc: Yang Jihong Assisted-by: Claude:claude-opus-4.6-1m Signed-off-by: Arnaldo Carvalho de Melo

perf kwork: Fix memory management of kwork_work

2026-05-22T23:51:59+00:00

This commit addresses several memory management issues in builtin-kwork.c: 1. Implements a global cleanup function perf_kwork__exit to free all kwork_work and kwork_atom_page objects at the end of the command. 2. Ensures all 'name' fields in struct kwork_work are malloc-ed (or NULL) and properly freed by using strdup and zfree. 3. Fixes memory leaks in top_merge_tasks where kwork_work objects were dropped without being freed. 4. Adds robustness with NULL checks for name fields. 5. Fixes workqueue_work_init to correctly resolve and strdup kernel function names, preventing bad-free errors. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo

perf kwork: Fix address sanitizer issues

2026-05-22T23:51:01+00:00

There is a double free in the record array due to how parse_options will mutate the array. Fix by keeping an array that isn't mutated. Ensure kwork_usage is freed on all paths. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo

perf kwork: Don't pass evsel with sample

2026-05-20T19:39:40+00:00

As struct perf_sample now directly contains its own resolved evsel pointer, passing the evsel separately is redundant and clutters the interface. Remove the redundant evsel parameter from kwork-specific handlers and structures, ensuring the tool always directly accesses the evsel bound to the sample. This simplifies the API signatures and eliminates the risk of passing an inconsistent evsel. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Andrew Jones Cc: Anup Patel Cc: Athira Rajeev Cc: Blake Jones Cc: Chen Ni Cc: Chun-Tse Shao Cc: Dapeng Mi Cc: Derek Foreman Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Howard Chu Cc: Hrishikesh Suresh Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Quan Zhou Cc: Ravi Bangoria Cc: Swapnil Sapkal Cc: Thomas Falcon Cc: Tianyou Li Cc: Yujie Liu Cc: tanze Signed-off-by: Arnaldo Carvalho de Melo

perf callchain: Don't pass evsel and sample

2026-05-20T19:35:59+00:00

As struct perf_sample now directly contains its own resolved evsel pointer, passing the evsel separately is redundant and clutters the interface. Remove the redundant evsel parameter from callchain-specific handlers and structures, ensuring the tool always directly accesses the evsel bound to the sample. This simplifies the API signatures and eliminates the risk of passing an inconsistent evsel. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Andrew Jones Cc: Anup Patel Cc: Athira Rajeev Cc: Blake Jones Cc: Chen Ni Cc: Chun-Tse Shao Cc: Dapeng Mi Cc: Derek Foreman Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Howard Chu Cc: Hrishikesh Suresh Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Quan Zhou Cc: Ravi Bangoria Cc: Swapnil Sapkal Cc: Thomas Falcon Cc: Tianyou Li Cc: Yujie Liu Cc: tanze Signed-off-by: Arnaldo Carvalho de Melo

perf evsel: Refactor evsel tracepoint sample accessors perf_sample

2026-05-20T19:35:59+00:00

The evsel argument to evsel__intval, evsel__rawptr, and similar functions, is unnecessary as it can be read from the sample. Remove the evsel and rename the function to match that the data is coming from the sample. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Andrew Jones Cc: Anup Patel Cc: Athira Rajeev Cc: Blake Jones Cc: Chen Ni Cc: Chun-Tse Shao Cc: Dapeng Mi Cc: Derek Foreman Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Howard Chu Cc: Hrishikesh Suresh Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Quan Zhou Cc: Ravi Bangoria Cc: Swapnil Sapkal Cc: Thomas Falcon Cc: Tianyou Li Cc: Yujie Liu Cc: tanze Signed-off-by: Arnaldo Carvalho de Melo

perf tool: Remove evsel from tool APIs that pass the sample

2026-05-20T19:34:23+00:00

As struct perf_sample now directly contains its own resolved evsel pointer, passing the evsel separately is redundant and clutters the interface. Remove the redundant evsel parameter from tool-specific handlers and structures, ensuring the tool always directly accesses the evsel bound to the sample. This simplifies the API signatures and eliminates the risk of passing an inconsistent evsel. Signed-off-by: Ian Rogers Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Andi Kleen Cc: Andrew Jones Cc: Anup Patel Cc: Athira Rajeev Cc: Blake Jones Cc: Chen Ni Cc: Chun-Tse Shao Cc: Dapeng Mi Cc: Derek Foreman Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Howard Chu Cc: Hrishikesh Suresh Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Quan Zhou Cc: Ravi Bangoria Cc: Swapnil Sapkal Cc: Thomas Falcon Cc: Tianyou Li Cc: Yujie Liu Cc: tanze [ Fixed up conflict with "perf inject: Fix itrace branch stack synthesis" series ] Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Use calloc() where applicable

2026-04-09T02:21:05+00:00

Instead of using zalloc(nr_entries * sizeof_entry) that is what calloc() does. In some places where linux/zalloc.h isn't needed, remove it, add when needed and was getting it indirectly. Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim