kernel/linux.git/tools/perf/util/sort.c, branch v7.1-rc5

perf sort: Sort disabled and full predicated flags

2026-04-10T16:52:06+00:00

According to the Arm ARM (ARM DDI 0487, L.a), section D18.2.6 "Events packet", apart from the empty predicate and partial predicates, an SVE or SME operation can be predicate-disabled or full predicated. To provide complete results, introduce two predicate types for these cases. Reviewed-by: James Clark Reviewed-by: Ian Rogers Signed-off-by: Leo Yan Signed-off-by: Namhyung Kim

perf sort: Support sort ASE and SME

2026-04-10T16:52:06+00:00

Support sort Advance SIMD extension (ASE) and SME. Reviewed-by: James Clark Reviewed-by: Ian Rogers Signed-off-by: Leo Yan Signed-off-by: Namhyung Kim

perf tools: Make more global variables static

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

`make check` will run sparse on the perf code base. A frequent warning is "warning: symbol '...' was not declared. Should it be static?" Go through and make global definitions without declarations static. In some cases it is deliberate due to dlsym accessing the symbol, this change doesn't clean up the missing declarations for perf test suites. Sometimes things can opportunistically be made const. Making somethings static exposed unused functions warnings, so restructuring of ifdefs was necessary for that. These changes reduce the size of the perf binary by 568 bytes. Committer notes: Refreshed the patch, the original one fell thru the cracks, updated the size reduction. Remove the trace-event-scripting.c changes, break the build, noticed with container builds and with sashiko: https://sashiko.dev/#/patchset/20260401215306.2152898-1-acme%40kernel.org Also make two variables static to address another sashiko review comment: https://sashiko.dev/#/patchset/20260402001740.2220481-1-acme%40kernel.org Signed-off-by: Ian Rogers Acked-by: Ankur Arora Acked-by: Namhyung Kim Cc: Adrian Hunter Cc: Albert Ou Cc: Alexander Shishkin Cc: Alexandre Ghiti Cc: Athira Rajeev Cc: Guo Ren Cc: Howard Chu Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Leo Yan Cc: Masami Hiramatsu Cc: Palmer Dabbelt Cc: Paul Walmsley Cc: Peter Zijlstra Cc: Yujie Liu Signed-off-by: Arnaldo Carvalho de Melo Signed-off-by: Namhyung Kim

perf tools: Save cln_size header

2026-04-06T05:30:52+00:00

Store cacheline size during perf record in header, so that cacheline size can be used for other features, like sort keys for perf report. Testing example with feat enabled: $ perf record ./Example $ perf report --header-only | grep -C 3 cacheline CPU_DOMAIN_INFO info available, use -I to display e_machine : 62 e_flags : 0 cacheline size: 64 missing features: TRACING_DATA BUILD_ID BRANCH_STACK GROUP_DESC AUXTRACE \ STAT CLOCKID DIR_FORMAT COMPRESSED CLOCK_DATA ======== [namhyung: Update the commit message and remove blank lines] Signed-off-by: Ricky Ringler Signed-off-by: Namhyung Kim

perf report: Add comm_nodigit sort key

2026-03-26T22:22:18+00:00

The "comm" column allows grouping events by the process command. It is intended to group like programs, despite having different PIDs. But some workloads may adjust their own command, so that a unique identifier (e.g. a PID or some other numeric value) is part of the command name. This destroys the utility of "comm", forcing perf to place each unique process name into its own bucket, which can contribute to a combinatorial explosion of memory use in perf report. Create a less strict version of this column, which ignores digits when comparing command names. Commands whose names are the same (ignoring digits) are sorted into the same histogram buckets, and displayed with the placeholder value "" in the place of digits. For example, hypothetical command names "kworker/1" "kworker/2" "kworker/3" would sort into the same bucket and be represented as "kworker/". Committer testing: $ perf report -s comm,comm_nodigit | grep -F "" 0.01% CPU 6/TCG CPU /TCG 0.01% kworker/53:2-mm kworker/:-mm 0.01% migration/24 migration/ 0.01% kworker/24:1-ev kworker/:-ev 0.01% llvmpipe-8 llvmpipe- Signed-off-by: Stephen Brennan Signed-off-by: Namhyung Kim

perf sort: Replace static cacheline size with sysconf cacheline size

2026-02-06T21:51:15+00:00

Testing: - Built perf - Executed perf mem record and report Committer notes: This addresses a TODO and improves the situation where record and report/c2c are performed on the same machine or in machines with the same cacheline size, but the proper way is to store the cacheline size in the perf.data header at 'record' time and then use it at post processing time. Signed-off-by: Ricky Ringler Cc: Ingo Molnar Cc: Namhyung Kim Cc: Peter Zijlstra Link: https://lore.kernel.org/r/20260129004223.26799-1-ricky.ringler@proton.me Signed-off-by: Arnaldo Carvalho de Melo

perf map_symbol: Switch from holding maps to holding thread

2026-01-23T19:58:39+00:00

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 report: Update sort key state from -F option

2025-12-17T12:30:37+00:00

Factor out __sort_dimension__update() so that it can be called from -s and -F option parsing logics. Otherwise the following command cannot go into the annotation mode. $ perf report -F overhead,type,sym Warning: Annotation is only available for symbolic views, include "sym*" in --sort to use it. Reviewed-by: Ian Rogers Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo

perf report: Fix histogram entry collapsing for -F option

2025-12-17T12:30:37+00:00

Users can use -F/--fields option to set output fields and sort keys together. But it missed to set perf_hpp_list->need_collapse for sort entries that have se_collapse callbacks. So it ends up with having duplicated entries separately. For example, let's run this command first. $ perf mem record -t load -U -- perf test -w datasym This will record samples for memory access (load) to struct 'buf' and a loop condition ('sig_atomic_t') types. So the following two commands should have identical output. $ perf report -s type --stdio --percent-limit=1 -q 87.80% perf buf 12.17% perf sig_atomic_t But using -F option didn't collapse the entries based on types so the result looked like below: $ perf report -F overhead,type --stdio --percent-limit=1 -q 23.31% perf buf 22.84% perf buf 21.26% perf buf 20.39% perf buf 12.17% perf sig_atomic_t Reviewed-by: Ian Rogers Signed-off-by: Namhyung Kim Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Ingo Molnar Cc: James Clark Cc: Jiri Olsa Cc: Peter Zijlstra Signed-off-by: Arnaldo Carvalho de Melo

perf sort: Use perf_env to set arch sort keys and header

2025-07-25T17:37:58+00:00

Previously arch_support_sort_key and arch_perf_header_entry used a weak symbol to compile as appropriate for x86 and powerpc. A limitation to this is that the handling of a data file could vary in cross-platform development. Change to using the perf_env of the current session to determine the architecture kind and set the sort key and header entries as appropriate. Signed-off-by: Ian Rogers Link: https://lore.kernel.org/r/20250724163302.596743-23-irogers@google.com Signed-off-by: Namhyung Kim