From 1a2725f3ee5571cf07966f467b73a9941bcbacb8 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Thu, 2 Apr 2020 17:15:48 +0300 Subject: perf script: Simplify auxiliary event printing functions This simplifies the print functions for the following perf script options: --show-task-events --show-namespace-events --show-cgroup-events --show-mmap-events --show-switch-events --show-lost-events --show-bpf-events Example: # perf record --switch-events -a -e cycles -c 10000 sleep 1 Before: # perf script --show-task-events --show-namespace-events --show-cgroup-events --show-mmap-events --show-switch-events --show-lost-events --show-bpf-events > out-before.txt After: # perf script --show-task-events --show-namespace-events --show-cgroup-events --show-mmap-events --show-switch-events --show-lost-events --show-bpf-events > out-after.txt # diff -s out-before.txt out-after.txt Files out-before.txt and out-after.tx are identical Signed-off-by: Adrian Hunter Acked-by: Jiri Olsa Link: http://lore.kernel.org/lkml/20200402141548.21283-1-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/builtin-script.c | 304 ++++++++++---------------------------------- 1 file changed, 66 insertions(+), 238 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 1f57a7ecdf3d..8bf3ba280312 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -2040,7 +2040,7 @@ static int cleanup_scripting(void) static bool filter_cpu(struct perf_sample *sample) { - if (cpu_list) + if (cpu_list && sample->cpu != (u32)-1) return !test_bit(sample->cpu, cpu_bitmap); return false; } @@ -2138,41 +2138,59 @@ static int process_attr(struct perf_tool *tool, union perf_event *event, return err; } -static int process_comm_event(struct perf_tool *tool, - union perf_event *event, - struct perf_sample *sample, - struct machine *machine) +static int print_event_with_time(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine, + pid_t pid, pid_t tid, u64 timestamp) { - struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); struct perf_session *session = script->session; struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - int ret = -1; + struct thread *thread = NULL; - thread = machine__findnew_thread(machine, event->comm.pid, event->comm.tid); - if (thread == NULL) { - pr_debug("problem processing COMM event, skipping it.\n"); - return -1; + if (evsel && !evsel->core.attr.sample_id_all) { + sample->cpu = 0; + sample->time = timestamp; + sample->pid = pid; + sample->tid = tid; } - if (perf_event__process_comm(tool, event, sample, machine) < 0) - goto out; + if (filter_cpu(sample)) + return 0; - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->comm.tid; - sample->pid = event->comm.pid; - } - if (!filter_cpu(sample)) { + if (tid != -1) + thread = machine__findnew_thread(machine, pid, tid); + + if (thread && evsel) { perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_COMM, stdout); - perf_event__fprintf(event, stdout); + event->header.type, stdout); } - ret = 0; -out: + + perf_event__fprintf(event, stdout); + thread__put(thread); - return ret; + + return 0; +} + +static int print_event(struct perf_tool *tool, union perf_event *event, + struct perf_sample *sample, struct machine *machine, + pid_t pid, pid_t tid) +{ + return print_event_with_time(tool, event, sample, machine, pid, tid, 0); +} + +static int process_comm_event(struct perf_tool *tool, + union perf_event *event, + struct perf_sample *sample, + struct machine *machine) +{ + if (perf_event__process_comm(tool, event, sample, machine) < 0) + return -1; + + return print_event(tool, event, sample, machine, event->comm.pid, + event->comm.tid); } static int process_namespaces_event(struct perf_tool *tool, @@ -2180,37 +2198,11 @@ static int process_namespaces_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - int ret = -1; - - thread = machine__findnew_thread(machine, event->namespaces.pid, - event->namespaces.tid); - if (thread == NULL) { - pr_debug("problem processing NAMESPACES event, skipping it.\n"); - return -1; - } - if (perf_event__process_namespaces(tool, event, sample, machine) < 0) - goto out; + return -1; - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->namespaces.tid; - sample->pid = event->namespaces.pid; - } - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_NAMESPACES, stdout); - perf_event__fprintf(event, stdout); - } - ret = 0; -out: - thread__put(thread); - return ret; + return print_event(tool, event, sample, machine, event->namespaces.pid, + event->namespaces.tid); } static int process_cgroup_event(struct perf_tool *tool, @@ -2218,34 +2210,11 @@ static int process_cgroup_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - int ret = -1; - - thread = machine__findnew_thread(machine, sample->pid, sample->tid); - if (thread == NULL) { - pr_debug("problem processing CGROUP event, skipping it.\n"); - return -1; - } - if (perf_event__process_cgroup(tool, event, sample, machine) < 0) - goto out; + return -1; - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - } - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_CGROUP, stdout); - perf_event__fprintf(event, stdout); - } - ret = 0; -out: - thread__put(thread); - return ret; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } static int process_fork_event(struct perf_tool *tool, @@ -2253,69 +2222,24 @@ static int process_fork_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (perf_event__process_fork(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); - if (thread == NULL) { - pr_debug("problem processing FORK event, skipping it.\n"); - return -1; - } - - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = event->fork.time; - sample->tid = event->fork.tid; - sample->pid = event->fork.pid; - } - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_FORK, stdout); - perf_event__fprintf(event, stdout); - } - thread__put(thread); - - return 0; + return print_event_with_time(tool, event, sample, machine, + event->fork.pid, event->fork.tid, + event->fork.time); } static int process_exit_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample, struct machine *machine) { - int err = 0; - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - - thread = machine__findnew_thread(machine, event->fork.pid, event->fork.tid); - if (thread == NULL) { - pr_debug("problem processing EXIT event, skipping it.\n"); + /* Print before 'exit' deletes anything */ + if (print_event_with_time(tool, event, sample, machine, event->fork.pid, + event->fork.tid, event->fork.time)) return -1; - } - - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->fork.tid; - sample->pid = event->fork.pid; - } - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_EXIT, stdout); - perf_event__fprintf(event, stdout); - } - if (perf_event__process_exit(tool, event, sample, machine) < 0) - err = -1; - - thread__put(thread); - return err; + return perf_event__process_exit(tool, event, sample, machine); } static int process_mmap_event(struct perf_tool *tool, @@ -2323,33 +2247,11 @@ static int process_mmap_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (perf_event__process_mmap(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, event->mmap.pid, event->mmap.tid); - if (thread == NULL) { - pr_debug("problem processing MMAP event, skipping it.\n"); - return -1; - } - - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->mmap.tid; - sample->pid = event->mmap.pid; - } - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP, stdout); - perf_event__fprintf(event, stdout); - } - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, event->mmap.pid, + event->mmap.tid); } static int process_mmap2_event(struct perf_tool *tool, @@ -2357,33 +2259,11 @@ static int process_mmap2_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (perf_event__process_mmap2(tool, event, sample, machine) < 0) return -1; - thread = machine__findnew_thread(machine, event->mmap2.pid, event->mmap2.tid); - if (thread == NULL) { - pr_debug("problem processing MMAP2 event, skipping it.\n"); - return -1; - } - - if (!evsel->core.attr.sample_id_all) { - sample->cpu = 0; - sample->time = 0; - sample->tid = event->mmap2.tid; - sample->pid = event->mmap2.pid; - } - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_MMAP2, stdout); - perf_event__fprintf(event, stdout); - } - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, event->mmap2.pid, + event->mmap2.tid); } static int process_switch_event(struct perf_tool *tool, @@ -2391,10 +2271,7 @@ static int process_switch_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); if (perf_event__process_switch(tool, event, sample, machine) < 0) return -1; @@ -2405,20 +2282,8 @@ static int process_switch_event(struct perf_tool *tool, if (!script->show_switch_events) return 0; - thread = machine__findnew_thread(machine, sample->pid, - sample->tid); - if (thread == NULL) { - pr_debug("problem processing SWITCH event, skipping it.\n"); - return -1; - } - - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_SWITCH, stdout); - perf_event__fprintf(event, stdout); - } - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } static int @@ -2427,23 +2292,8 @@ process_lost_event(struct perf_tool *tool, struct perf_sample *sample, struct machine *machine) { - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - struct thread *thread; - - thread = machine__findnew_thread(machine, sample->pid, - sample->tid); - if (thread == NULL) - return -1; - - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - PERF_RECORD_LOST, stdout); - perf_event__fprintf(event, stdout); - } - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } static int @@ -2462,33 +2312,11 @@ process_bpf_events(struct perf_tool *tool __maybe_unused, struct perf_sample *sample, struct machine *machine) { - struct thread *thread; - struct perf_script *script = container_of(tool, struct perf_script, tool); - struct perf_session *session = script->session; - struct evsel *evsel = perf_evlist__id2evsel(session->evlist, sample->id); - if (machine__process_ksymbol(machine, event, sample) < 0) return -1; - if (!evsel->core.attr.sample_id_all) { - perf_event__fprintf(event, stdout); - return 0; - } - - thread = machine__findnew_thread(machine, sample->pid, sample->tid); - if (thread == NULL) { - pr_debug("problem processing MMAP event, skipping it.\n"); - return -1; - } - - if (!filter_cpu(sample)) { - perf_sample__fprintf_start(sample, thread, evsel, - event->header.type, stdout); - perf_event__fprintf(event, stdout); - } - - thread__put(thread); - return 0; + return print_event(tool, event, sample, machine, sample->pid, + sample->tid); } static void sig_handler(int sig __maybe_unused) -- cgit v1.2.3-59-g8ed1b From 1c5c25b3fdbd7035f6d53a1a99b5afd577ce13e1 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Wed, 1 Apr 2020 13:16:05 +0300 Subject: perf auxtrace: Add an option to synthesize callchains for regular events Currently, callchains can be synthesized only for synthesized events. Add an itrace option to synthesize callchains for regular events. Signed-off-by: Adrian Hunter Cc: Andi Kleen Cc: Jiri Olsa Link: http://lore.kernel.org/lkml/20200401101613.6201-9-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/itrace.txt | 1 + tools/perf/builtin-report.c | 3 ++- tools/perf/builtin-script.c | 2 +- tools/perf/util/auxtrace.c | 6 +++++- tools/perf/util/auxtrace.h | 2 ++ tools/perf/util/s390-cpumsf.c | 2 +- 6 files changed, 12 insertions(+), 4 deletions(-) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/Documentation/itrace.txt b/tools/perf/Documentation/itrace.txt index 82ff7dad40c2..671e154ede03 100644 --- a/tools/perf/Documentation/itrace.txt +++ b/tools/perf/Documentation/itrace.txt @@ -10,6 +10,7 @@ e synthesize error events d create a debug log g synthesize a call chain (use with i or x) + G synthesize a call chain on existing event records l synthesize last branch entries (use with i or x) s skip initial number of events diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c index 26d8fc27e427..c0cebd53ecf9 100644 --- a/tools/perf/builtin-report.c +++ b/tools/perf/builtin-report.c @@ -339,6 +339,7 @@ static int report__setup_sample_type(struct report *rep) bool is_pipe = perf_data__is_pipe(session->data); if (session->itrace_synth_opts->callchain || + session->itrace_synth_opts->add_callchain || (!is_pipe && perf_header__has_feat(&session->header, HEADER_AUXTRACE) && !session->itrace_synth_opts->set)) @@ -1332,7 +1333,7 @@ int cmd_report(int argc, const char **argv) if (symbol_conf.cumulate_callchain && !callchain_param.order_set) callchain_param.order = ORDER_CALLER; - if (itrace_synth_opts.callchain && + if ((itrace_synth_opts.callchain || itrace_synth_opts.add_callchain) && (int)itrace_synth_opts.callchain_sz > report.max_stack) report.max_stack = itrace_synth_opts.callchain_sz; diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 8bf3ba280312..06b511c0a539 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -3537,7 +3537,7 @@ int cmd_script(int argc, const char **argv) return -1; } - if (itrace_synth_opts.callchain && + if ((itrace_synth_opts.callchain || itrace_synth_opts.add_callchain) && itrace_synth_opts.callchain_sz > scripting_max_stack) scripting_max_stack = itrace_synth_opts.callchain_sz; diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c index b60bae8e395c..809a09e75c55 100644 --- a/tools/perf/util/auxtrace.c +++ b/tools/perf/util/auxtrace.c @@ -1462,8 +1462,12 @@ int itrace_parse_synth_opts(const struct option *opt, const char *str, synth_opts->branches = true; synth_opts->returns = true; break; + case 'G': case 'g': - synth_opts->callchain = true; + if (p[-1] == 'G') + synth_opts->add_callchain = true; + else + synth_opts->callchain = true; synth_opts->callchain_sz = PERF_ITRACE_DEFAULT_CALLCHAIN_SZ; while (*p == ' ' || *p == ',') diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h index db65aae5c2ea..dd8a4ff8209e 100644 --- a/tools/perf/util/auxtrace.h +++ b/tools/perf/util/auxtrace.h @@ -74,6 +74,7 @@ enum itrace_period_type { * @calls: limit branch samples to calls (can be combined with @returns) * @returns: limit branch samples to returns (can be combined with @calls) * @callchain: add callchain to 'instructions' events + * @add_callchain: add callchain to existing event records * @thread_stack: feed branches to the thread_stack * @last_branch: add branch context to 'instruction' events * @callchain_sz: maximum callchain size @@ -101,6 +102,7 @@ struct itrace_synth_opts { bool calls; bool returns; bool callchain; + bool add_callchain; bool thread_stack; bool last_branch; unsigned int callchain_sz; diff --git a/tools/perf/util/s390-cpumsf.c b/tools/perf/util/s390-cpumsf.c index d7779e48652f..38a942881d1a 100644 --- a/tools/perf/util/s390-cpumsf.c +++ b/tools/perf/util/s390-cpumsf.c @@ -1079,7 +1079,7 @@ static bool check_auxtrace_itrace(struct itrace_synth_opts *itops) itops->pwr_events || itops->errors || itops->dont_decode || itops->calls || itops->returns || itops->callchain || itops->thread_stack || - itops->last_branch; + itops->last_branch || itops->add_callchain; if (!ison) return true; pr_err("Unsupported --itrace options specified\n"); -- cgit v1.2.3-59-g8ed1b From 680d125cd522d460b24ccc8b29f03cdb62dea23e Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 19 Mar 2020 13:25:14 -0700 Subject: perf script: Add option to enable the LBR stitching approach With the LBR stitching approach, the reconstructed LBR call stack can break the HW limitation. However, it may reconstruct invalid call stacks in some cases, e.g. exception handing such as setjmp/longjmp. Also, it may impact the processing time especially when the number of samples with stitched LBRs are huge. Add an option to enable the approach. Committer testing: Using the same perf.data as with the latest cset committer testing section: $ perf script --stitch-lbr tchain_edit 11131 15164.984292: 437491 cycles:u: 401106 f43+0x0 (/wb/tchain_edit) 40114c f42+0x18 (/wb/tchain_edit) 401172 f41+0xe (/wb/tchain_edit) 401194 f40+0x0 (/wb/tchain_edit) 40119b f39+0x0 (/wb/tchain_edit) 4011a2 f38+0x0 (/wb/tchain_edit) 4011a9 f37+0x0 (/wb/tchain_edit) 4011b0 f36+0x0 (/wb/tchain_edit) 4011b7 f35+0x0 (/wb/tchain_edit) 4011be f34+0x0 (/wb/tchain_edit) 4011c5 f33+0x0 (/wb/tchain_edit) 4011cc f32+0x0 (/wb/tchain_edit) 401207 f31+0x34 (/wb/tchain_edit) 401212 f30+0x0 (/wb/tchain_edit) 401219 f29+0x0 (/wb/tchain_edit) 401220 f28+0x0 (/wb/tchain_edit) 401227 f27+0x0 (/wb/tchain_edit) 40122e f26+0x0 (/wb/tchain_edit) 401235 f25+0x0 (/wb/tchain_edit) 40123c f24+0x0 (/wb/tchain_edit) 401243 f23+0x0 (/wb/tchain_edit) 40124a f22+0x0 (/wb/tchain_edit) 401251 f21+0x0 (/wb/tchain_edit) 401258 f20+0x0 (/wb/tchain_edit) 40125f f19+0x0 (/wb/tchain_edit) 401266 f18+0x0 (/wb/tchain_edit) 40126d f17+0x0 (/wb/tchain_edit) 401274 f16+0x0 (/wb/tchain_edit) 40127b f15+0x0 (/wb/tchain_edit) 401282 f14+0x0 (/wb/tchain_edit) 401289 f13+0x0 (/wb/tchain_edit) 401290 f12+0x0 (/wb/tchain_edit) 401297 f11+0x0 (/wb/tchain_edit) 40129e f10+0x0 (/wb/tchain_edit) 4012a5 f9+0x0 (/wb/tchain_edit) 4012ac f8+0x0 (/wb/tchain_edit) 4012b3 f7+0x0 (/wb/tchain_edit) 4012ba f6+0x0 (/wb/tchain_edit) 4012c1 f5+0x0 (/wb/tchain_edit) 4012c8 f4+0x0 (/wb/tchain_edit) 4012cf f3+0x0 (/wb/tchain_edit) 4012d6 f2+0x0 (/wb/tchain_edit) 4012dd f1+0x0 (/wb/tchain_edit) 4012e4 main+0x0 (/wb/tchain_edit) 7f41a5016f41 __libc_start_main+0xf1 (/usr/lib64/libc-2.29.so) $ Signed-off-by: Kan Liang Reviewed-by: Andi Kleen Acked-by: Jiri Olsa Tested-by: Arnaldo Carvalho de Melo Cc: Adrian Hunter Cc: Alexey Budankov Cc: Mathieu Poirier Cc: Michael Ellerman Cc: Namhyung Kim Cc: Pavel Gerasimov Cc: Peter Zijlstra Cc: Ravi Bangoria Cc: Stephane Eranian Cc: Vitaly Slobodskoy Link: http://lore.kernel.org/lkml/20200319202517.23423-15-kan.liang@linux.intel.com Signed-off-by: Arnaldo Carvalho de Melo --- tools/perf/Documentation/perf-script.txt | 11 +++++++++++ tools/perf/builtin-script.c | 12 ++++++++++++ 2 files changed, 23 insertions(+) (limited to 'tools/perf/builtin-script.c') diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt index 963487e82edc..372dfd110e6d 100644 --- a/tools/perf/Documentation/perf-script.txt +++ b/tools/perf/Documentation/perf-script.txt @@ -440,6 +440,17 @@ include::itrace.txt[] --show-on-off-events:: Show the --switch-on/off events too. +--stitch-lbr:: + Show callgraph with stitched LBRs, which may have more complete + callgraph. The perf.data file must have been obtained using + perf record --call-graph lbr. + Disabled by default. In common cases with call stack overflows, + it can recreate better call stacks than the default lbr call stack + output. But this approach is not full proof. There can be cases + where it creates incorrect call stacks from incorrect matches. + The known limitations include exception handing such as + setjmp/longjmp will have calls/returns not match. + SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c index 06b511c0a539..a2236542900d 100644 --- a/tools/perf/builtin-script.c +++ b/tools/perf/builtin-script.c @@ -1697,6 +1697,7 @@ struct perf_script { bool show_cgroup_events; bool allocated; bool per_event_dump; + bool stitch_lbr; struct evswitch evswitch; struct perf_cpu_map *cpus; struct perf_thread_map *threads; @@ -1923,6 +1924,9 @@ static void process_event(struct perf_script *script, if (PRINT_FIELD(IP)) { struct callchain_cursor *cursor = NULL; + if (script->stitch_lbr) + al->thread->lbr_stitch_enable = true; + if (symbol_conf.use_callchain && sample->callchain && thread__resolve_callchain(al->thread, &callchain_cursor, evsel, sample, NULL, NULL, scripting_max_stack) == 0) @@ -3170,6 +3174,12 @@ static void script__setup_sample_type(struct perf_script *script) else callchain_param.record_mode = CALLCHAIN_FP; } + + if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) { + pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n" + "Please apply --call-graph lbr when recording.\n"); + script->stitch_lbr = false; + } } static int process_stat_round_event(struct perf_session *session, @@ -3481,6 +3491,8 @@ int cmd_script(int argc, const char **argv) "file", "file saving guest os /proc/kallsyms"), OPT_STRING(0, "guestmodules", &symbol_conf.default_guest_modules, "file", "file saving guest os /proc/modules"), + OPT_BOOLEAN('\0', "stitch-lbr", &script.stitch_lbr, + "Enable LBR callgraph stitching approach"), OPTS_EVSWITCH(&script.evswitch), OPT_END() }; -- cgit v1.2.3-59-g8ed1b