[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <bf761da86e91c09e3d916a3f004101f4d4544407.1730150953.git.jpoimboe@kernel.org>
Date: Mon, 28 Oct 2024 14:48:06 -0700
From: Josh Poimboeuf <jpoimboe@...nel.org>
To: x86@...nel.org
Cc: Peter Zijlstra <peterz@...radead.org>,
Steven Rostedt <rostedt@...dmis.org>,
Ingo Molnar <mingo@...nel.org>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
linux-kernel@...r.kernel.org,
Indu Bhagat <indu.bhagat@...cle.com>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>,
Namhyung Kim <namhyung@...nel.org>,
Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
linux-perf-users@...r.kernel.org,
Mark Brown <broonie@...nel.org>,
linux-toolchains@...r.kernel.org,
Jordan Rome <jordalgo@...a.com>,
Sam James <sam@...too.org>,
linux-trace-kernel@...r.kerne.org,
Andrii Nakryiko <andrii.nakryiko@...il.com>,
Jens Remus <jremus@...ux.ibm.com>,
Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
Florian Weimer <fweimer@...hat.com>,
Andy Lutomirski <luto@...nel.org>
Subject: [PATCH v3 19/19] perf tools: Merge deferred user callchains
From: Namhyung Kim <namhyung@...nel.org>
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.kallsyms])
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/libc.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=0 --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 <namhyung@...nel.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@...nel.org>
---
tools/perf/Documentation/perf-script.txt | 5 ++
tools/perf/builtin-script.c | 5 +-
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 | 63 +++++++++++++++++++++++-
tools/perf/util/tool.c | 1 +
tools/perf/util/tool.h | 1 +
9 files changed, 102 insertions(+), 2 deletions(-)
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index b72866ef270b..69f018b3d199 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -518,6 +518,11 @@ include::itrace.txt[]
The known limitations include exception handing such as
setjmp/longjmp will have calls/returns not match.
+--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 311580e25f5b..e3acf4979c36 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -4031,6 +4031,7 @@ int cmd_script(int argc, const char **argv)
bool header_only = false;
bool script_started = false;
bool unsorted_dump = false;
+ bool merge_deferred_callchains = true;
char *rec_script_path = NULL;
char *rep_script_path = NULL;
struct perf_session *session;
@@ -4184,6 +4185,8 @@ 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()
};
@@ -4439,7 +4442,7 @@ int cmd_script(int argc, const char **argv)
script.tool.throttle = process_throttle_event;
script.tool.unthrottle = process_throttle_event;
script.tool.ordering_requires_timestamps = true;
- script.tool.merge_deferred_callchains = false;
+ script.tool.merge_deferred_callchains = merge_deferred_callchains;
session = 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 0c7564747a14..d1114491c3da 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1832,3 +1832,27 @@ int sample__for_each_callchain_node(struct thread *thread, struct evsel *evsel,
}
return 0;
}
+
+int sample__merge_deferred_callchain(struct perf_sample *sample_orig,
+ struct perf_sample *sample_callchain)
+{
+ u64 nr_orig = sample_orig->callchain->nr - 1;
+ u64 nr_deferred = sample_callchain->callchain->nr;
+ struct ip_callchain *callchain;
+
+ callchain = calloc(1 + nr_orig + nr_deferred, sizeof(u64));
+ if (callchain == NULL) {
+ sample_orig->deferred_callchain = false;
+ return -ENOMEM;
+ }
+
+ callchain->nr = 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 = 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 *thread, struct evsel *evsel,
struct perf_sample *sample, int max_stack,
bool symbols, callchain_iter_fn cb, void *data);
+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 f14b7e6ff1dc..f27d8c4a22aa 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -81,6 +81,7 @@ void evlist__init(struct evlist *evlist, struct perf_cpu_map *cpus,
evlist->ctl_fd.ack = -1;
evlist->ctl_fd.pos = -1;
evlist->nr_br_cntr = -1;
+ INIT_LIST_HEAD(&evlist->deferred_samples);
}
struct evlist *evlist__new(void)
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index bcc1c6984bb5..c26379366554 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -84,6 +84,7 @@ struct evlist {
int pos; /* index at evlist core object to check signals */
} ctl_fd;
struct event_enable_timer *eet;
+ struct list_head deferred_samples;
};
struct evsel_str_handler {
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 1248a0317a2f..e0a21b896b57 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1256,6 +1256,56 @@ static int evlist__deliver_sample(struct evlist *evlist, const struct perf_tool
&sample->read.one, machine);
}
+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 = 0;
+
+ if (!tool->merge_deferred_callchains) {
+ evsel = 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 = evlist__parse_sample(evlist, de->event, &orig_sample);
+ if (ret < 0) {
+ pr_err("failed to parse original sample\n");
+ break;
+ }
+
+ if (sample->tid != orig_sample.tid)
+ continue;
+
+ evsel = evlist__id2evsel(evlist, orig_sample.id);
+ sample__merge_deferred_callchain(&orig_sample, sample);
+ ret = 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,
@@ -1284,6 +1334,16 @@ 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 = malloc(sizeof(*de));
+
+ if (de == NULL)
+ return -ENOMEM;
+
+ de->event = event;
+ list_add_tail(&de->list, &evlist->deferred_samples);
+ return 0;
+ }
return evlist__deliver_sample(evlist, tool, event, sample, evsel, machine);
case PERF_RECORD_MMAP:
return tool->mmap(tool, event, sample, machine);
@@ -1343,7 +1403,8 @@ static int machines__deliver_event(struct machines *machines,
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 e78f16de912e..385043e06627 100644
--- a/tools/perf/util/tool.c
+++ b/tools/perf/util/tool.c
@@ -238,6 +238,7 @@ void perf_tool__init(struct perf_tool *tool, bool ordered_events)
tool->cgroup_events = false;
tool->no_warn = false;
tool->show_feat_hdr = SHOW_FEAT_NO_HEADER;
+ tool->merge_deferred_callchains = true;
tool->sample = process_event_sample_stub;
tool->mmap = process_event_stub;
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index 9987bbde6d5e..d06580478ab1 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -87,6 +87,7 @@ 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;
};
--
2.47.0
Powered by blists - more mailing lists