summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-script.c
diff options
context:
space:
mode:
authorAndi Kleen <ak@linux.intel.com>2018-09-20 21:05:39 +0300
committerArnaldo Carvalho de Melo <acme@redhat.com>2018-10-24 21:29:55 +0300
commit99f753f048b3f02f31a56951781672021af6cd0d (patch)
tree9c22f288e4be70e8c31d9c248657dcdd98231452 /tools/perf/builtin-script.c
parentd1b1552e15d41297abcaf3812378e3391d44fa6b (diff)
downloadlinux-99f753f048b3f02f31a56951781672021af6cd0d.tar.xz
perf script: Implement --graph-function
Add a ftrace style --graph-function argument to 'perf script' that allows to print itrace function calls only below a given function. This makes it easier to find the code of interest in a large trace. % perf record -e intel_pt//k -a sleep 1 % perf script --graph-function group_sched_in --call-trace perf 900 [000] 194167.205652203: ([kernel.kallsyms]) group_sched_in perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) event_sched_in.isra.107 perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_set_state.part.71 perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_time perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_disable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_log_itrace_start perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_event_update_userpage perf 900 [000] 194167.205652203: ([kernel.kallsyms]) calc_timer_values perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_cpu perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax perf 900 [000] 194167.205652203: ([kernel.kallsyms]) arch_perf_update_userpage perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __fentry__ perf 900 [000] 194167.205652203: ([kernel.kallsyms]) using_native_sched_clock perf 900 [000] 194167.205652203: ([kernel.kallsyms]) sched_clock_stable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) perf_pmu_enable perf 900 [000] 194167.205652203: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) group_sched_in swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) event_sched_in.isra.107 swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_set_state.part.71 swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_time swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_pmu_disable swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_log_itrace_start swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) perf_event_update_userpage swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) calc_timer_values swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_cpu swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __x86_indirect_thunk_rax swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) arch_perf_update_userpage swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) __fentry__ swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) using_native_sched_clock swapper 0 [001] 194167.205660693: ([kernel.kallsyms]) sched_clock_stable Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Tested-by: Leo Yan <leo.yan@linaro.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Kim Phillips <kim.phillips@arm.com> Link: http://lkml.kernel.org/r/20180920180540.14039-5-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/builtin-script.c')
-rw-r--r--tools/perf/builtin-script.c96
1 files changed, 78 insertions, 18 deletions
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 566e1450898a..9d2249ea75e3 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1105,6 +1105,35 @@ out:
return printed;
}
+static const char *resolve_branch_sym(struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct addr_location *al,
+ u64 *ip)
+{
+ struct addr_location addr_al;
+ struct perf_event_attr *attr = &evsel->attr;
+ const char *name = NULL;
+
+ if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
+ if (sample_addr_correlates_sym(attr)) {
+ thread__resolve(thread, &addr_al, sample);
+ if (addr_al.sym)
+ name = addr_al.sym->name;
+ else
+ *ip = sample->addr;
+ } else {
+ *ip = sample->addr;
+ }
+ } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
+ if (al->sym)
+ name = al->sym->name;
+ else
+ *ip = sample->ip;
+ }
+ return name;
+}
+
static int perf_sample__fprintf_callindent(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
@@ -1112,7 +1141,6 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
{
struct perf_event_attr *attr = &evsel->attr;
size_t depth = thread_stack__depth(thread);
- struct addr_location addr_al;
const char *name = NULL;
static int spacing;
int len = 0;
@@ -1126,22 +1154,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,
if (thread->ts && sample->flags & PERF_IP_FLAG_RETURN)
depth += 1;
- if (sample->flags & (PERF_IP_FLAG_CALL | PERF_IP_FLAG_TRACE_BEGIN)) {
- if (sample_addr_correlates_sym(attr)) {
- thread__resolve(thread, &addr_al, sample);
- if (addr_al.sym)
- name = addr_al.sym->name;
- else
- ip = sample->addr;
- } else {
- ip = sample->addr;
- }
- } else if (sample->flags & (PERF_IP_FLAG_RETURN | PERF_IP_FLAG_TRACE_END)) {
- if (al->sym)
- name = al->sym->name;
- else
- ip = sample->ip;
- }
+ name = resolve_branch_sym(sample, evsel, thread, al, &ip);
if (PRINT_FIELD(DSO) && !(PRINT_FIELD(IP) || PRINT_FIELD(ADDR))) {
dlen += fprintf(fp, "(");
@@ -1647,6 +1660,47 @@ static void perf_sample__fprint_metric(struct perf_script *script,
}
}
+static bool show_event(struct perf_sample *sample,
+ struct perf_evsel *evsel,
+ struct thread *thread,
+ struct addr_location *al)
+{
+ int depth = thread_stack__depth(thread);
+
+ if (!symbol_conf.graph_function)
+ return true;
+
+ if (thread->filter) {
+ if (depth <= thread->filter_entry_depth) {
+ thread->filter = false;
+ return false;
+ }
+ return true;
+ } else {
+ const char *s = symbol_conf.graph_function;
+ u64 ip;
+ const char *name = resolve_branch_sym(sample, evsel, thread, al,
+ &ip);
+ unsigned nlen;
+
+ if (!name)
+ return false;
+ nlen = strlen(name);
+ while (*s) {
+ unsigned len = strcspn(s, ",");
+ if (nlen == len && !strncmp(name, s, len)) {
+ thread->filter = true;
+ thread->filter_entry_depth = depth;
+ return true;
+ }
+ s += len;
+ if (*s == ',')
+ s++;
+ }
+ return false;
+ }
+}
+
static void process_event(struct perf_script *script,
struct perf_sample *sample, struct perf_evsel *evsel,
struct addr_location *al,
@@ -1661,6 +1715,9 @@ static void process_event(struct perf_script *script,
if (output[type].fields == 0)
return;
+ if (!show_event(sample, evsel, thread, al))
+ return;
+
++es->samples;
perf_sample__fprintf_start(sample, thread, evsel,
@@ -3237,6 +3294,8 @@ int cmd_script(int argc, const char **argv)
"Decode calls from from itrace", parse_call_trace),
OPT_CALLBACK_OPTARG(0, "call-ret-trace", &itrace_synth_opts, NULL, NULL,
"Decode calls and returns from itrace", parse_callret_trace),
+ OPT_STRING(0, "graph-function", &symbol_conf.graph_function, "symbol[,symbol...]",
+ "Only print symbols and callees with --call-trace/--call-ret-trace"),
OPT_STRING(0, "stop-bt", &symbol_conf.bt_stop_list_str, "symbol[,symbol...]",
"Stop display of callgraph at these symbols"),
OPT_STRING('C', "cpu", &cpu_list, "cpu", "list of cpus to profile"),
@@ -3494,7 +3553,8 @@ int cmd_script(int argc, const char **argv)
script.session = session;
script__setup_sample_type(&script);
- if (output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT)
+ if ((output[PERF_TYPE_HARDWARE].fields & PERF_OUTPUT_CALLINDENT) ||
+ symbol_conf.graph_function)
itrace_synth_opts.thread_stack = true;
session->itrace_synth_opts = &itrace_synth_opts;