summaryrefslogtreecommitdiff
path: root/tools/perf/builtin-lock.c
diff options
context:
space:
mode:
authorNamhyung Kim <namhyung@kernel.org>2023-02-02 18:13:24 -0800
committerArnaldo Carvalho de Melo <acme@redhat.com>2023-02-03 17:12:26 -0300
commitebab291641bed48f62c608e3bf29071c435c2d9b (patch)
tree177f142a6940da555d64f00a3645ea42fc8124e6 /tools/perf/builtin-lock.c
parent16cad1d3597d32e470a4115f11c5e61cce6cd81b (diff)
perf lock contention: Support filters for different aggregation
It'd be useful to filter other than the current aggregation mode. For example, users may want to see callstacks for specific locks only. Or they may want tasks from a certain callstack. The tracepoints already collected the information but it needs to check the condition again when processing the event. And it needs to change BPF to allow the key combinations. The lock contentions on 'rcu_state' spinlock can be monitored: $ sudo perf lock con -abv -L rcu_state sleep 1 ... contended total wait max wait avg wait type caller 4 151.39 us 62.57 us 37.85 us spinlock rcu_core+0xcb 0xffffffff81fd1666 _raw_spin_lock_irqsave+0x46 0xffffffff8172d76b rcu_core+0xcb 0xffffffff822000eb __softirqentry_text_start+0xeb 0xffffffff816a0ba9 __irq_exit_rcu+0xc9 0xffffffff81fc0112 sysvec_apic_timer_interrupt+0xa2 0xffffffff82000e46 asm_sysvec_apic_timer_interrupt+0x16 0xffffffff81d49f78 cpuidle_enter_state+0xd8 0xffffffff81d4a259 cpuidle_enter+0x29 1 30.21 us 30.21 us 30.21 us spinlock rcu_core+0xcb 0xffffffff81fd1666 _raw_spin_lock_irqsave+0x46 0xffffffff8172d76b rcu_core+0xcb 0xffffffff822000eb __softirqentry_text_start+0xeb 0xffffffff816a0ba9 __irq_exit_rcu+0xc9 0xffffffff81fc00c4 sysvec_apic_timer_interrupt+0x54 0xffffffff82000e46 asm_sysvec_apic_timer_interrupt+0x16 1 28.84 us 28.84 us 28.84 us spinlock rcu_accelerate_cbs_unlocked+0x40 0xffffffff81fd1c60 _raw_spin_lock+0x30 0xffffffff81728cf0 rcu_accelerate_cbs_unlocked+0x40 0xffffffff8172da82 rcu_core+0x3e2 0xffffffff822000eb __softirqentry_text_start+0xeb 0xffffffff816a0ba9 __irq_exit_rcu+0xc9 0xffffffff81fc0112 sysvec_apic_timer_interrupt+0xa2 0xffffffff82000e46 asm_sysvec_apic_timer_interrupt+0x16 0xffffffff81d49f78 cpuidle_enter_state+0xd8 ... To see tasks calling 'rcu_core' function: $ sudo perf lock con -abt -S rcu_core sleep 1 contended total wait max wait avg wait pid comm 19 23.46 us 2.21 us 1.23 us 0 swapper 2 18.37 us 17.01 us 9.19 us 2061859 ThreadPoolForeg 3 5.76 us 1.97 us 1.92 us 3909 pipewire-pulse 1 2.26 us 2.26 us 2.26 us 1809271 MediaSu~isor #2 1 1.97 us 1.97 us 1.97 us 1514882 Chrome_ChildIOT 1 987 ns 987 ns 987 ns 3740 pipewire-pulse Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Hao Luo <haoluo@google.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Juri Lelli <juri.lelli@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <song@kernel.org> Cc: bpf@vger.kernel.org Link: https://lore.kernel.org/r/20230203021324.143540-4-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Diffstat (limited to 'tools/perf/builtin-lock.c')
-rw-r--r--tools/perf/builtin-lock.c75
1 files changed, 44 insertions, 31 deletions
diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 0593c6e636c6..0d11f301fd72 100644
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -509,6 +509,34 @@ alloc_failed:
return NULL;
}
+bool match_callstack_filter(struct machine *machine, u64 *callstack)
+{
+ struct map *kmap;
+ struct symbol *sym;
+ u64 ip;
+
+ if (list_empty(&callstack_filters))
+ return true;
+
+ for (int i = 0; i < max_stack_depth; i++) {
+ struct callstack_filter *filter;
+
+ if (!callstack || !callstack[i])
+ break;
+
+ ip = callstack[i];
+ sym = machine__find_kernel_symbol(machine, ip, &kmap);
+ if (sym == NULL)
+ continue;
+
+ list_for_each_entry(filter, &callstack_filters, list) {
+ if (strstr(sym->name, filter->name))
+ return true;
+ }
+ }
+ return false;
+}
+
struct trace_lock_handler {
/* it's used on CONFIG_LOCKDEP */
int (*acquire_event)(struct evsel *evsel,
@@ -1070,12 +1098,6 @@ static int report_lock_contention_begin_event(struct evsel *evsel,
ls = lock_stat_findnew(key, name, flags);
if (!ls)
return -ENOMEM;
-
- if (aggr_mode == LOCK_AGGR_CALLER && needs_callstack()) {
- ls->callstack = get_callstack(sample, max_stack_depth);
- if (ls->callstack == NULL)
- return -ENOMEM;
- }
}
if (filters.nr_types) {
@@ -1106,6 +1128,22 @@ static int report_lock_contention_begin_event(struct evsel *evsel,
return 0;
}
+ if (needs_callstack()) {
+ u64 *callstack = get_callstack(sample, max_stack_depth);
+ if (callstack == NULL)
+ return -ENOMEM;
+
+ if (!match_callstack_filter(machine, callstack)) {
+ free(callstack);
+ return 0;
+ }
+
+ if (ls->callstack == NULL)
+ ls->callstack = callstack;
+ else
+ free(callstack);
+ }
+
ts = thread_stat_findnew(sample->tid);
if (!ts)
return -ENOMEM;
@@ -1606,31 +1644,6 @@ static void print_contention_result(struct lock_contention *con)
if (!st->wait_time_total)
continue;
- if (aggr_mode == LOCK_AGGR_CALLER && !list_empty(&callstack_filters)) {
- struct map *kmap;
- struct symbol *sym;
- u64 ip;
-
- for (int i = 0; i < max_stack_depth; i++) {
- struct callstack_filter *filter;
-
- if (!st->callstack || !st->callstack[i])
- break;
-
- ip = st->callstack[i];
- sym = machine__find_kernel_symbol(con->machine, ip, &kmap);
- if (sym == NULL)
- continue;
-
- list_for_each_entry(filter, &callstack_filters, list) {
- if (strstr(sym->name, filter->name))
- goto found;
- }
- }
- continue;
- }
-
-found:
list_for_each_entry(key, &lock_keys, list) {
key->print(key, st);
pr_info(" ");