kernel/tools/perf/util/event.c, branch master

perf map_symbol: Switch from holding maps to holding thread

2026-01-23T19:58:39Z

maps may belong to >1 thread. In contexts like symbolization information from the thread may be useful, such as the ELF machine. As the maps can be gained from the thread switch from holding maps in struct map_symbol to holding the thread. Holding the maps in addr_location is also redundant, switch this to using thread__maps. Reviewed-by: James Clark Signed-off-by: Ian Rogers Cc: Aditya Bodkhe Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Athira Rajeev Cc: Bill Wendling Cc: Dr. David Alan Gilbert Cc: Guo Ren Cc: Howard Chu Cc: Ingo Molnar Cc: Jiri Olsa Cc: John Garry Cc: Julia Lawall Cc: Justin Stitt Cc: Krzysztof Łopatowski Cc: Leo Yan Cc: Namhyung Kim Cc: Nathan Chancellor Cc: Nick Desaulniers Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Sergei Trofimovich Cc: Shimin Guo Cc: Suchit Karunakaran Cc: Thomas Falcon Cc: Tianyou Li Cc: Will Deacon Cc: Zecheng Li Signed-off-by: Arnaldo Carvalho de Melo

perf sched stats: Add schedstat v17 support

2026-01-22T15:31:51Z

The /proc/schedstat file output is standardized with version number. Add support to record and raw dump v17 version layout. Version 17 of schedstats removed 'lb_imbalance' field as it has no significance anymore and instead added more relevant fields namely 'lb_imbalance_load', 'lb_imbalance_util', 'lb_imbalance_task' and 'lb_imbalance_misfit'. The domain field prints the name of the corresponding sched domain from this version onwards. Co-developed-by: Ravi Bangoria Signed-off-by: Ravi Bangoria Signed-off-by: Swapnil Sapkal Tested-by: Chen Yu Acked-by: Ian Rogers Acked-by: Peter Zijlstra Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Anubhav Shelat Cc: Ben Gainey Cc: Blake Jones Cc: Chun-Tse Shao Cc: David Vernet Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Gautham Shenoy Cc: Graham Woodward Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Juri Lelli Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Madadi Vineeth Reddy Cc: Mark Rutland Cc: Namhyung Kim Cc: Sandipan Das Cc: Santosh Shukla Cc: Shrikanth Hegde Cc: Steven Rostedt (VMware) Cc: Tejun Heo Cc: Thomas Falcon Cc: Tim Chen Cc: Vincent Guittot Cc: Yang Jihong Cc: Yujie Liu Cc: Zhongqiu Han Signed-off-by: Arnaldo Carvalho de Melo

perf sched stats: Add schedstat v16 support

2026-01-22T15:30:16Z

The /proc/schedstat file output is standardized with version number. Add support to record and raw dump v16 version layout. Version 16 of schedstats changed the order of definitions within 'enum cpu_idle_type', which changed the order of [CPU_MAX_IDLE_TYPES] columns in show_schedstat(). In particular the position of CPU_IDLE and __CPU_NOT_IDLE changed places. Co-developed-by: Ravi Bangoria Signed-off-by: Ravi Bangoria Signed-off-by: Swapnil Sapkal Tested-by: Chen Yu Tested-by: James Clark Acked-by: Ian Rogers Acked-by: Peter Zijlstra Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Anubhav Shelat Cc: Ben Gainey Cc: Blake Jones Cc: Chun-Tse Shao Cc: David Vernet Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Gautham Shenoy Cc: Graham Woodward Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Juri Lelli Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Madadi Vineeth Reddy Cc: Mark Rutland Cc: Namhyung Kim Cc: Sandipan Das Cc: Santosh Shukla Cc: Shrikanth Hegde Cc: Steven Rostedt (VMware) Cc: Tejun Heo Cc: Thomas Falcon Cc: Tim Chen Cc: Vincent Guittot Cc: Yang Jihong Cc: Yujie Liu Cc: Zhongqiu Han Signed-off-by: Arnaldo Carvalho de Melo

perf sched stats: Add record and rawdump support

2026-01-22T15:29:28Z

Define new, perf tool only, sample types and their layouts. Add logic to parse /proc/schedstat, convert it to perf sample format and save samples to perf.data file with `perf sched stats record` command. Also add logic to read perf.data file, interpret schedstat samples and print rawdump of samples with `perf script -D`. Note that, /proc/schedstat file output is standardized with version number. The patch supports v15 but older or newer version can be added easily. Co-developed-by: Ravi Bangoria Signed-off-by: Ravi Bangoria Signed-off-by: Swapnil Sapkal Tested-by: Chen Yu Tested-by: James Clark Acked-by: Ian Rogers Acked-by: Peter Zijlstra Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Andi Kleen Cc: Anubhav Shelat Cc: Ben Gainey Cc: Blake Jones Cc: Chun-Tse Shao Cc: David Vernet Cc: Dmitriy Vyukov Cc: Dr. David Alan Gilbert Cc: Gautham Shenoy Cc: Graham Woodward Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Juri Lelli Cc: K Prateek Nayak Cc: Kan Liang Cc: Leo Yan Cc: Madadi Vineeth Reddy Cc: Mark Rutland Cc: Namhyung Kim Cc: Sandipan Das Cc: Santosh Shukla Cc: Shrikanth Hegde Cc: Steven Rostedt (VMware) Cc: Tejun Heo Cc: Thomas Falcon Cc: Tim Chen Cc: Vincent Guittot Cc: Yang Jihong Cc: Yujie Liu Cc: Zhongqiu Han [ PRIu64 needs uint64_t, not 'unsigned long' to work on both 32-bit and 64-bit ] Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Minimal DEFERRED_CALLCHAIN support

2025-12-03T00:13:32Z

Add a new event type for deferred callchains and a new callback for the struct perf_tool. For now it doesn't actually handle the deferred callchains but it just marks the sample if it has the PERF_CONTEXT_ USER_DEFFERED in the callchain array. At least, perf report can dump the raw data with this change. Actually this requires the next commit to enable attr.defer_callchain, but if you already have a data file, it'll show the following result. $ perf report -D ... 0x2158@perf.data [0x40]: event: 22 . . ... raw event: size 64 bytes . 0000: 16 00 00 00 02 00 40 00 06 00 00 00 0b 00 00 00 ......@......... . 0010: 03 00 00 00 00 00 00 00 a7 7f 33 fe 18 7f 00 00 ..........3..... . 0020: 0f 0e 33 fe 18 7f 00 00 48 14 33 fe 18 7f 00 00 ..3.....H.3..... . 0030: 08 09 00 00 08 09 00 00 e6 7a e7 35 1c 00 00 00 .........z.5.... 121163447014 0x2158 [0x40]: PERF_RECORD_CALLCHAIN_DEFERRED(IP, 0x2): 2312/2312: 0xb00000006 ... FP chain: nr:3 ..... 0: 00007f18fe337fa7 ..... 1: 00007f18fe330e0f ..... 2: 00007f18fe331448 : unhandled! Reviewed-by: Ian Rogers Signed-off-by: Namhyung Kim

perf build-id: Change sprintf functions to snprintf

2025-07-25T17:37:13Z

Pass in a size argument rather than implying all build id strings must be SBUILD_ID_SIZE. Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250724163302.596743-4-irogers@google.com [ fixed some build errors ] Signed-off-by: Namhyung Kim

perf tools: display the new PERF_RECORD_BPF_METADATA event

2025-06-20T21:48:56Z

Here's some example "perf script -D" output for the new event type. The ": unhandled!" message is from tool.c, analogous to other behavior there. I've elided some rows with all NUL characters for brevity, and I wrapped one of the >75-column lines to fit in the commit guidelines. 0x50fc8@perf.data [0x260]: event: 84 . . ... raw event: size 608 bytes . 0000: 54 00 00 00 00 00 60 02 62 70 66 5f 70 72 6f 67 T.....`.bpf_prog . 0010: 5f 31 65 30 61 32 65 33 36 36 65 35 36 66 31 61 _1e0a2e366e56f1a . 0020: 32 5f 70 65 72 66 5f 73 61 6d 70 6c 65 5f 66 69 2_perf_sample_fi . 0030: 6c 74 65 72 00 00 00 00 00 00 00 00 00 00 00 00 lter............ . 0040: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [...] . 0110: 74 65 73 74 5f 76 61 6c 75 65 00 00 00 00 00 00 test_value...... . 0120: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [...] . 0150: 34 32 00 00 00 00 00 00 00 00 00 00 00 00 00 00 42.............. . 0160: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ [...] 0 0x50fc8 [0x260]: PERF_RECORD_BPF_METADATA \ prog bpf_prog_1e0a2e366e56f1a2_perf_sample_filter entry 0: test_value = 42 : unhandled! Signed-off-by: Blake Jones Link: https://lore.kernel.org/r/20250612194939.162730-5-blakejones@google.com Signed-off-by: Namhyung Kim

perf script: Print PERF_AUX_FLAG_COLLISION flag

2025-05-28T18:08:25Z

Print out the collision flag for AUX trace data. This is helpful for inspecting sample collisions. After: 0x217b60@/data_nvme1n1/niayan01/upstream/perf.data [0x40]: event: 11 . . ... raw event: size 64 bytes . 0000: 0b 00 00 00 00 00 40 00 d2 ef 3f 00 00 00 00 00 ......@...?..... . 0010: ff 0f 00 00 00 00 00 00 08 00 00 00 00 00 00 00 ................ . 0020: 1c 01 00 00 1c 01 00 00 10 bf 38 d6 11 01 00 00 ..........8..... . 0030: 03 00 00 00 00 00 00 00 06 00 00 00 00 00 00 00 ................ 3 1176120114960 0x217b60 [0x40]: PERF_RECORD_AUX offset: 0x3fefd2 size: 0xfff flags: 0x8 [C] The added character '[C]' indicates the collision. Signed-off-by: Leo Yan Cc: Adrian Hunter Cc: Ian Rogers Cc: Jiri Olsa Cc: Kan Liang Cc: Namhyung Kim Link: https://lore.kernel.org/r/20250528153519.188644-1-leo.yan@arm.com Signed-off-by: Arnaldo Carvalho de Melo

perf record: Add 8-byte aligned event type PERF_RECORD_COMPRESSED2

2025-05-16T20:31:40Z

The original PERF_RECORD_COMPRESS is not 8-byte aligned, which can cause asan runtime error: # Build with asan $ make -C tools/perf O=/tmp/perf DEBUG=1 EXTRA_CFLAGS="-O0 -g -fno-omit-frame-pointer -fsanitize=undefined" # Test success with many asan runtime errors: $ /tmp/perf/perf test "Zstd perf.data compression/decompression" -vv 83: Zstd perf.data compression/decompression: ... util/session.c:1959:13: runtime error: member access within misaligned address 0x7f69e3f99653 for type 'union perf_event', which requires 13 byte alignment 0x7f69e3f99653: note: pointer points here d0 3a 50 69 44 00 00 00 00 00 08 00 bb 07 00 00 00 00 00 00 44 00 00 00 00 00 00 00 ff 07 00 00 ^ util/session.c:2163:22: runtime error: member access within misaligned address 0x7f69e3f99653 for type 'union perf_event', which requires 8 byte alignment 0x7f69e3f99653: note: pointer points here d0 3a 50 69 44 00 00 00 00 00 08 00 bb 07 00 00 00 00 00 00 44 00 00 00 00 00 00 00 ff 07 00 00 ^ ... Since there is no way to align compressed data in zstd compression, this patch add a new event type `PERF_RECORD_COMPRESSED2`, which adds a field `data_size` to specify the actual compressed data size. The `header.size` contains the total record size, including the padding at the end to make it 8-byte aligned. Tested with `Zstd perf.data compression/decompression` Signed-off-by: Chun-Tse Shao Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexander Shishkin Cc: Ben Gainey Cc: Christophe Leroy Cc: Ian Rogers Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Kan Liang Cc: Leo Yan Cc: Mark Rutland Cc: Namhyung Kim Cc: Nick Terrell Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20250303183646.327510-1-ctshao@google.com Signed-off-by: Arnaldo Carvalho de Melo

perf report: Add latency output field

2025-02-18T22:04:32Z

Latency output field is similar to overhead, but represents overhead for latency rather than CPU consumption. It's re-scaled from overhead by dividing weight by the current parallelism level at the time of the sample. It effectively models profiling with 1 sample taken per unit of wall-clock time rather than unit of CPU time. Signed-off-by: Dmitry Vyukov Reviewed-by: Andi Kleen Link: https://lore.kernel.org/r/b6269518758c2166e6ffdc2f0e24cfdecc8ef9c1.1739437531.git.dvyukov@google.com Signed-off-by: Namhyung Kim