From 6fa291f8056bc57684ae668439eb413d30fab01a Mon Sep 17 00:00:00 2001 From: Ian Rogers Date: Wed, 16 Sep 2026 22:07:02 -0700 Subject: [PATCH] perf tools: Expose opt-in --hybrid-merge Add --hybrid-merge to perf report and perf top. It merges the events a wildcard expanded to across the core PMUs, and their histograms, so that a symbol which ran on more than one kind of core is reported once with the total rather than once per PMU. evlist__merge_hybrid() links the events and evlist__merge_hists_hybrid() links the histograms. There is nothing to merge on a machine with a single core PMU, or when the events didn't come from a wildcard, so warn in that case rather than quietly producing an unmerged report. Merging collapses the per-PMU entries into one set, which doesn't combine with the per-level breakdown of --hierarchy, so asking for both is an error. Signed-off-by: Ian Rogers Assisted-by: Antigravity:gemini-3.1-pro Tested-by: Arnaldo Carvalho de Melo Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-report.txt | 5 +++++ tools/perf/Documentation/perf-top.txt | 5 +++++ tools/perf/builtin-report.c | 19 +++++++++++++++++++ tools/perf/builtin-top.c | 17 +++++++++++++++++ tools/perf/util/symbol.c | 1 + 5 files changed, 47 insertions(+) diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt index 1a4706329c6c..3718ebd297ce 100644 --- a/tools/perf/Documentation/perf-report.txt +++ b/tools/perf/Documentation/perf-report.txt @@ -578,6 +578,11 @@ include::itrace.txt[] --raw-trace:: When displaying traceevent output, do not use print fmt or plugins. +--hybrid-merge:: + Merge matching events from all hybrid core PMUs into one + display. For example, if a wildcard expands to run on both p-cores and + e-cores, this aggregates them into a single view. + -H:: --hierarchy:: Enable hierarchical output. In the hierarchy mode, each sort key groups diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt index 2da2a16bbf26..c5e96da6ed82 100644 --- a/tools/perf/Documentation/perf-top.txt +++ b/tools/perf/Documentation/perf-top.txt @@ -49,6 +49,11 @@ Default is to monitor all CPUS. encoding with the layout of the event control registers as described by entries in /sys/bus/event_source/devices/cpu/format/*. +--hybrid-merge:: + Merge matching events from all hybrid core PMUs into one + display. For example, if a wildcard expands to run on both p-cores and + e-cores, this aggregates them into a single view. + --filter=:: Event filter. This option should follow an event selector (-e). For syntax see linkperf:perf-record[1]. diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 279e61c2366c..bda4836fc524 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -1114,6 +1114,17 @@ static int __cmd_report(struct report *rep) evlist__for_each_entry(session->evlist, pos) rep->nr_entries += evsel__hists(pos)->nr_entries; + if (symbol_conf.hybrid_merge) { + struct perf_env *env = perf_session__env(session); + + if (evlist__can_merge_hybrid(session->evlist, env)) { + evlist__merge_hybrid(session->evlist, env); + evlist__merge_hists_hybrid(session->evlist, false); + } else { + ui__warning("--hybrid-merge: no events to merge across core PMUs\n"); + } + } + if (use_browser == 0) { if (verbose > 3) perf_session__fprintf(session, stdout); @@ -1449,6 +1460,8 @@ int cmd_report(int argc, const char **argv) parse_branch_mode), OPT_BOOLEAN(0, "branch-history", &branch_call_mode, "add last branch records to call history"), + OPT_BOOLEAN(0, "hybrid-merge", &symbol_conf.hybrid_merge, + "merge the same event across hybrid core PMUs"), OPT_STRING(0, "objdump", &objdump_path, "path", "objdump binary to use for disassembly and annotations"), OPT_STRING(0, "addr2line", &addr2line_path, "path", @@ -1548,6 +1561,12 @@ int cmd_report(int argc, const char **argv) report.symbol_filter_str = argv[0]; } + if (symbol_conf.report_hierarchy && symbol_conf.hybrid_merge) { + pr_err("Error: --hierarchy and --hybrid-merge are mutually exclusive.\n"); + ret = -EINVAL; + goto exit; + } + if (disassembler_style) { annotate_opts.disassembler_style = strdup(disassembler_style); if (!annotate_opts.disassembler_style) diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c index c2562d49be46..3bb3337f1244 100644 --- a/tools/perf/builtin-top.c +++ b/tools/perf/builtin-top.c @@ -1336,6 +1336,15 @@ static int __cmd_top(struct perf_top *top) if (!target__none(&opts->target)) evlist__enable(top->evlist); + if (symbol_conf.hybrid_merge) { + if (evlist__can_merge_hybrid(top->evlist, /*env=*/NULL)) { + evlist__merge_hybrid(top->evlist, /*env=*/NULL); + evlist__merge_hists_hybrid(top->evlist, false); + } else { + ui__warning("--hybrid-merge: no events to merge across core PMUs\n"); + } + } + ret = -1; if (pthread_create(&thread_process, NULL, process_thread, top)) { ui__error("Could not create process thread.\n"); @@ -1491,6 +1500,8 @@ int cmd_top(int argc, const char **argv) OPT_CALLBACK('e', "event", &parse_events_option_args, "event", "event selector. use 'perf list' to list available events", parse_events_option), + OPT_BOOLEAN(0, "hybrid-merge", &symbol_conf.hybrid_merge, + "merge the same event across hybrid core PMUs"), OPT_CALLBACK(0, "filter", &top.evlist, "filter", "event filter", parse_filter), OPT_U64('c', "count", &opts->user_interval, "event period to sample"), @@ -1679,6 +1690,12 @@ int cmd_top(int argc, const char **argv) if (argc) usage_with_options(top_usage, options); + if (symbol_conf.report_hierarchy && symbol_conf.hybrid_merge) { + pr_err("Error: --hierarchy and --hybrid-merge are mutually exclusive.\n"); + status = -EINVAL; + goto out_put_evlist; + } + if (disassembler_style) { annotate_opts.disassembler_style = strdup(disassembler_style); if (!annotate_opts.disassembler_style) { diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c index 3587ad243159..4c1f8231d47f 100644 --- a/tools/perf/util/symbol.c +++ b/tools/perf/util/symbol.c @@ -73,6 +73,7 @@ struct symbol_conf symbol_conf = { .symfs = "", .symfs_layout_flat = false, .event_group = true, + .hybrid_merge = false, .inline_name = true, .res_sample = 0, .addr2line_timeout_ms = 5 * 1000,