From nobody Wed Sep 10 06:01:04 2025 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 14B51313E1A; Mon, 8 Sep 2025 17:53:44 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1757354025; cv=none; b=qHZcjwTUFSDUt9A4/X/p4aGUdyYSNkO0ECU37lNQcr90uf0BcT9qd+I+17lWeKbbaygZXVO/meUCM++WfWoETt9k+Dynu5wPPTrWbgL1ieTkrYGNlaVyhbqFKyeGk21jByZ5HyT6CvBrEwP/dSDmoS4kPjGPOFaVU/SNQGlGpm8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1757354025; c=relaxed/simple; bh=pgny05s6Uy486RqRWzZN+GOJjzVyYvGnzNvG7oFsAJE=; h=Message-ID:Date:From:To:Cc:Subject:References:MIME-Version: Content-Type; b=rjUzEcWL2ZsTCJvz/Ji3Dp4AxBBUCH8T71Jqp9wPHZ3epcRihcFsW0r4diGSa60EJ266aT/wleedXESAFT2UNKVUEJ4aj5/tsGF83TOVe1oW7VLUmFlC47InV5tt4ZMG5TlhRPlaOcfsu9nViYGcTpZjI7wDVidKBUJy7Qkailo= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=t579DmEZ; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="t579DmEZ" Received: by smtp.kernel.org (Postfix) with ESMTPSA id A7A9AC4CEF1; Mon, 8 Sep 2025 17:53:44 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1757354024; bh=pgny05s6Uy486RqRWzZN+GOJjzVyYvGnzNvG7oFsAJE=; h=Date:From:To:Cc:Subject:References:From; b=t579DmEZvdZN31mI3+nHqcUBA0Kb4klvlfVqtqzZI4G5hu/oSJDLM18D+0Q+jZk3z Vmb5inRegnD6PXmRqjGka0efahwh812/8qW90VsIbubChNWxs8fb4eAzsyP97VPIB7 eWku13I9baSzAT+5n8ndTxBJx3Q4qrgycuZzaTxDxPpAtcQBc0qD95QgC3BDgRP026 M24Wo1ZVygJxgmCo1ZD8zDreb3V5cuBVvsHykQEKmToonc5UyYJ3N1ueYgVGtWPIpD e06H9vQhU4x/EOR0stqByxFlrPphHzVwEgldnZL8zP7oWhdv0ii033wwcqeQ9HGi6J kfvEHmttv98QA== Received: from rostedt by gandalf with local (Exim 4.98.2) (envelope-from ) id 1uvg4U-000000076Bb-3JPM; Mon, 08 Sep 2025 13:54:30 -0400 Message-ID: <20250908175430.639412649@kernel.org> User-Agent: quilt/0.68 Date: Mon, 08 Sep 2025 13:53:23 -0400 From: Steven Rostedt To: linux-kernel@vger.kernel.org, linux-trace-kernel@vger.kernel.org, bpf@vger.kernel.org, x86@kernel.org Cc: Masami Hiramatsu , Mathieu Desnoyers , Josh Poimboeuf , Peter Zijlstra , Ingo Molnar , Jiri Olsa , Arnaldo Carvalho de Melo , Namhyung Kim , Thomas Gleixner , Andrii Nakryiko , Indu Bhagat , "Jose E. Marchesi" , Beau Belgrave , Jens Remus , Linus Torvalds , Andrew Morton , Florian Weimer , Sam James , Kees Cook , "Carlos O'Donell" Subject: [PATCH v16 4/4] perf tools: Merge deferred user callchains References: <20250908175319.841517121@kernel.org> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Namhyung Kim Save samples with deferred callchains in a separate list and deliver them after merging the user callchains. If users don't want to merge they can set tool->merge_deferred_callchains to false to prevent the behavior. With previous result, now perf script will show the merged callchains. $ perf script perf 801 [000] 18.031793: 1 cycles:P: ffffffff91a14c36 __intel_pmu_enable_all.isra.0+0x56 ([kernel.kall= syms]) ffffffff91d373e9 perf_ctx_enable+0x39 ([kernel.kallsyms]) ffffffff91d36af7 event_function+0xd7 ([kernel.kallsyms]) ffffffff91d34222 remote_function+0x42 ([kernel.kallsyms]) ffffffff91c1ebe1 generic_exec_single+0x61 ([kernel.kallsyms]) ffffffff91c1edac smp_call_function_single+0xec ([kernel.kallsyms]) ffffffff91d37a9d event_function_call+0x10d ([kernel.kallsyms]) ffffffff91d33557 perf_event_for_each_child+0x37 ([kernel.kallsyms= ]) ffffffff91d47324 _perf_ioctl+0x204 ([kernel.kallsyms]) ffffffff91d47c43 perf_ioctl+0x33 ([kernel.kallsyms]) ffffffff91e2f216 __x64_sys_ioctl+0x96 ([kernel.kallsyms]) ffffffff9265f1ae do_syscall_64+0x9e ([kernel.kallsyms]) ffffffff92800130 entry_SYSCALL_64+0xb0 ([kernel.kallsyms]) 7fb5fc22034b __GI___ioctl+0x3b (/usr/lib/x86_64-linux-gnu/lib= c.so.6) ... The old output can be get using --no-merge-callchain option. Also perf report can get the user callchain entry at the end. $ perf report --no-children --percent-limit=3D0 --stdio -q -S __intel_pmu= _enable_all.isra.0 # symbol: __intel_pmu_enable_all.isra.0 0.00% perf [kernel.kallsyms] | ---__intel_pmu_enable_all.isra.0 perf_ctx_enable event_function remote_function generic_exec_single smp_call_function_single event_function_call perf_event_for_each_child _perf_ioctl perf_ioctl __x64_sys_ioctl do_syscall_64 entry_SYSCALL_64 __GI___ioctl Signed-off-by: Namhyung Kim Signed-off-by: Josh Poimboeuf Signed-off-by: Steven Rostedt (Google) --- Changes since v15: https://lore.kernel.org/20250825180802.725570056@kernel.= org - Have the matching deferred code only skip when TID does not match. Otherwise, process the sample but do not merge if the cookies do not matc= h. (Namhyung Kim) tools/perf/Documentation/perf-script.txt | 5 ++ tools/perf/builtin-script.c | 4 ++ tools/perf/util/callchain.c | 24 +++++++++ tools/perf/util/callchain.h | 3 ++ tools/perf/util/evlist.c | 1 + tools/perf/util/evlist.h | 1 + tools/perf/util/session.c | 65 +++++++++++++++++++++++- tools/perf/util/tool.c | 1 + tools/perf/util/tool.h | 1 + 9 files changed, 104 insertions(+), 1 deletion(-) diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Document= ation/perf-script.txt index 28bec7e78bc8..03d112960632 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -527,6 +527,11 @@ include::itrace.txt[] The known limitations include exception handing such as setjmp/longjmp will have calls/returns not match. =20 +--merge-callchains:: + Enable merging deferred user callchains if available. This is the + default behavior. If you want to see separate CALLCHAIN_DEFERRED + records for some reason, use --no-merge-callchains explicitly. + :GMEXAMPLECMD: script :GMEXAMPLESUBCMD: include::guest-files.txt[] diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 03ea7b7e5bc1..70e7658a61fb 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3785,6 +3785,7 @@ int cmd_script(int argc, const char **argv) bool header_only =3D false; bool script_started =3D false; bool unsorted_dump =3D false; + bool merge_deferred_callchains =3D true; char *rec_script_path =3D NULL; char *rep_script_path =3D NULL; struct perf_session *session; @@ -3938,6 +3939,8 @@ int cmd_script(int argc, const char **argv) "Guest code can be found in hypervisor process"), OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr, "Enable LBR callgraph stitching approach"), + OPT_BOOLEAN('\0', "merge-callchains", &merge_deferred_callchains, + "Enable merge deferred user callchains"), OPTS_EVSWITCH(&script.evswitch), OPT_END() }; @@ -4194,6 +4197,7 @@ int cmd_script(int argc, const char **argv) script.tool.throttle =3D process_throttle_event; script.tool.unthrottle =3D process_throttle_event; script.tool.ordering_requires_timestamps =3D true; + script.tool.merge_deferred_callchains =3D merge_deferred_callchains; session =3D perf_session__new(&data, &script.tool); if (IS_ERR(session)) return PTR_ERR(session); diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c index d7b7eef740b9..d2d672f1d6ba 100644 --- a/tools/perf/util/callchain.c +++ b/tools/perf/util/callchain.c @@ -1828,3 +1828,27 @@ int sample__for_each_callchain_node(struct thread *t= hread, struct evsel *evsel, } return 0; } + +int sample__merge_deferred_callchain(struct perf_sample *sample_orig, + struct perf_sample *sample_callchain) +{ + u64 nr_orig =3D sample_orig->callchain->nr - PERF_DEFERRED_ITEMS; + u64 nr_deferred =3D sample_callchain->callchain->nr; + struct ip_callchain *callchain; + + callchain =3D calloc(1 + nr_orig + nr_deferred, sizeof(u64)); + if (callchain =3D=3D NULL) { + sample_orig->deferred_callchain =3D false; + return -ENOMEM; + } + + callchain->nr =3D nr_orig + nr_deferred; + /* copy except for the last PERF_CONTEXT_USER_DEFERRED */ + memcpy(callchain->ips, sample_orig->callchain->ips, nr_orig * sizeof(u64)= ); + /* copy deferred use callchains */ + memcpy(&callchain->ips[nr_orig], sample_callchain->callchain->ips, + nr_deferred * sizeof(u64)); + + sample_orig->callchain =3D callchain; + return 0; +} diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h index 86ed9e4d04f9..89785125ed25 100644 --- a/tools/perf/util/callchain.h +++ b/tools/perf/util/callchain.h @@ -317,4 +317,7 @@ int sample__for_each_callchain_node(struct thread *thre= ad, struct evsel *evsel, struct perf_sample *sample, int max_stack, bool symbols, callchain_iter_fn cb, void *data); =20 +int sample__merge_deferred_callchain(struct perf_sample *sample_orig, + struct perf_sample *sample_callchain); + #endif /* __PERF_CALLCHAIN_H */ diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c index 80d8387e6b97..9518b45af393 100644 --- a/tools/perf/util/evlist.c +++ b/tools/perf/util/evlist.c @@ -85,6 +85,7 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_= map *cpus, evlist->ctl_fd.pos =3D -1; evlist->nr_br_cntr =3D -1; metricgroup__rblist_init(&evlist->metric_events); + INIT_LIST_HEAD(&evlist->deferred_samples); } =20 struct evlist *evlist__new(void) diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h index 5e71e3dc6042..309ef8d78495 100644 --- a/tools/perf/util/evlist.h +++ b/tools/perf/util/evlist.h @@ -92,6 +92,7 @@ struct evlist { * of struct metric_expr. */ struct rblist metric_events; + struct list_head deferred_samples; }; =20 struct evsel_str_handler { diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index a071006350f5..2527e4f18d9a 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -1283,6 +1283,58 @@ static int evlist__deliver_sample(struct evlist *evl= ist, const struct perf_tool per_thread); } =20 +struct deferred_event { + struct list_head list; + union perf_event *event; +}; + +static int evlist__deliver_deferred_samples(struct evlist *evlist, + const struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + struct deferred_event *de, *tmp; + struct evsel *evsel; + int ret =3D 0; + + if (!tool->merge_deferred_callchains) { + evsel =3D evlist__id2evsel(evlist, sample->id); + return tool->callchain_deferred(tool, event, sample, + evsel, machine); + } + + list_for_each_entry_safe(de, tmp, &evlist->deferred_samples, list) { + struct perf_sample orig_sample; + + ret =3D evlist__parse_sample(evlist, de->event, &orig_sample); + if (ret < 0) { + pr_err("failed to parse original sample\n"); + break; + } + + if (sample->tid !=3D orig_sample.tid) + continue; + + if (event->callchain_deferred.cookie =3D=3D orig_sample.deferred_cookie) + sample__merge_deferred_callchain(&orig_sample, sample); + + evsel =3D evlist__id2evsel(evlist, orig_sample.id); + ret =3D evlist__deliver_sample(evlist, tool, de->event, + &orig_sample, evsel, machine); + + if (orig_sample.deferred_callchain) + free(orig_sample.callchain); + + list_del(&de->list); + free(de); + + if (ret) + break; + } + return ret; +} + static int machines__deliver_event(struct machines *machines, struct evlist *evlist, union perf_event *event, @@ -1311,6 +1363,16 @@ static int machines__deliver_event(struct machines *= machines, return 0; } dump_sample(evsel, event, sample, perf_env__arch(machine->env)); + if (sample->deferred_callchain && tool->merge_deferred_callchains) { + struct deferred_event *de =3D malloc(sizeof(*de)); + + if (de =3D=3D NULL) + return -ENOMEM; + + de->event =3D event; + list_add_tail(&de->list, &evlist->deferred_samples); + return 0; + } return evlist__deliver_sample(evlist, tool, event, sample, evsel, machin= e); case PERF_RECORD_MMAP: return tool->mmap(tool, event, sample, machine); @@ -1370,7 +1432,8 @@ static int machines__deliver_event(struct machines *m= achines, return tool->aux_output_hw_id(tool, event, sample, machine); case PERF_RECORD_CALLCHAIN_DEFERRED: dump_deferred_callchain(evsel, event, sample); - return tool->callchain_deferred(tool, event, sample, evsel, machine); + return evlist__deliver_deferred_samples(evlist, tool, event, + sample, machine); default: ++evlist->stats.nr_unknown_events; return -1; diff --git a/tools/perf/util/tool.c b/tools/perf/util/tool.c index 8bf86af1ca90..9ab9e231b5d5 100644 --- a/tools/perf/util/tool.c +++ b/tools/perf/util/tool.c @@ -258,6 +258,7 @@ void perf_tool__init(struct perf_tool *tool, bool order= ed_events) tool->cgroup_events =3D false; tool->no_warn =3D false; tool->show_feat_hdr =3D SHOW_FEAT_NO_HEADER; + tool->merge_deferred_callchains =3D true; =20 tool->sample =3D process_event_sample_stub; tool->mmap =3D process_event_stub; diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h index 2676d84da80c..7165a487a485 100644 --- a/tools/perf/util/tool.h +++ b/tools/perf/util/tool.h @@ -88,6 +88,7 @@ struct perf_tool { bool cgroup_events; bool no_warn; bool dont_split_sample_group; + bool merge_deferred_callchains; enum show_feature_header show_feat_hdr; }; =20 --=20 2.50.1