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>

1 files changed, 30 insertions, 14 deletions

diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
index ead2898ba377..72cf81114982 100644
--- a/tools/perf/util/bpf_lock_contention.c
+++ b/tools/perf/util/bpf_lock_contention.c
@@ -34,13 +34,15 @@ int lock_contention_prepare(struct lock_contention *con)
 	bpf_map__set_max_entries(skel->maps.lock_stat, con->map_nr_entries);
 	bpf_map__set_max_entries(skel->maps.tstamp, con->map_nr_entries);
 
-	if (con->aggr_mode == LOCK_AGGR_TASK) {
+	if (con->aggr_mode == LOCK_AGGR_TASK)
 		bpf_map__set_max_entries(skel->maps.task_data, con->map_nr_entries);
-		bpf_map__set_max_entries(skel->maps.stacks, 1);
-	} else {
+	else
 		bpf_map__set_max_entries(skel->maps.task_data, 1);
+
+	if (con->save_callstack)
 		bpf_map__set_max_entries(skel->maps.stacks, con->map_nr_entries);
-	}
+	else
+		bpf_map__set_max_entries(skel->maps.stacks, 1);
 
 	if (target__has_cpu(target))
 		ncpus = perf_cpu_map__nr(evlist->core.user_requested_cpus);
@@ -146,6 +148,7 @@ int lock_contention_prepare(struct lock_contention *con)
 	/* these don't work well if in the rodata section */
 	skel->bss->stack_skip = con->stack_skip;
 	skel->bss->aggr_mode = con->aggr_mode;
+	skel->bss->needs_callstack = con->save_callstack;
 
 	lock_contention_bpf__attach(skel);
 	return 0;
@@ -177,7 +180,7 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 
 	if (con->aggr_mode == LOCK_AGGR_TASK) {
 		struct contention_task_data task;
-		int pid = key->aggr_key;
+		int pid = key->pid;
 		int task_fd = bpf_map__fd(skel->maps.task_data);
 
 		/* do not update idle comm which contains CPU number */
@@ -194,7 +197,7 @@ static const char *lock_contention_get_name(struct lock_contention *con,
 	}
 
 	if (con->aggr_mode == LOCK_AGGR_ADDR) {
-		sym = machine__find_kernel_symbol(machine, key->aggr_key, &kmap);
+		sym = machine__find_kernel_symbol(machine, key->lock_addr, &kmap);
 		if (sym)
 			name = sym->name;
 		return name;
@@ -255,20 +258,35 @@ int lock_contention_read(struct lock_contention *con)
 
 	prev_key = NULL;
 	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
-		s32 stack_id;
+		s64 ls_key;
 		const char *name;
 
 		/* to handle errors in the loop body */
 		err = -1;
 
 		bpf_map_lookup_elem(fd, &key, &data);
-
 		if (con->save_callstack) {
-			stack_id = key.aggr_key;
-			bpf_map_lookup_elem(stack, &stack_id, stack_trace);
+			bpf_map_lookup_elem(stack, &key.stack_id, stack_trace);
+
+			if (!match_callstack_filter(machine, stack_trace))
+				goto next;
 		}
 
-		st = lock_stat_find(key.aggr_key);
+		switch (con->aggr_mode) {
+		case LOCK_AGGR_CALLER:
+			ls_key = key.stack_id;
+			break;
+		case LOCK_AGGR_TASK:
+			ls_key = key.pid;
+			break;
+		case LOCK_AGGR_ADDR:
+			ls_key = key.lock_addr;
+			break;
+		default:
+			goto next;
+		}
+
+		st = lock_stat_find(ls_key);
 		if (st != NULL) {
 			st->wait_time_total += data.total_time;
 			if (st->wait_time_max < data.max_time)
@@ -283,7 +301,7 @@ int lock_contention_read(struct lock_contention *con)
 		}
 
 		name = lock_contention_get_name(con, &key, stack_trace);
-		st = lock_stat_findnew(key.aggr_key, name, data.flags);
+		st = lock_stat_findnew(ls_key, name, data.flags);
 		if (st == NULL)
 			break;
 
@@ -295,8 +313,6 @@ int lock_contention_read(struct lock_contention *con)
 		if (data.count)
 			st->avg_wait_time = data.total_time / data.count;
 
-		st->flags = data.flags;
-
 		if (con->save_callstack) {
 			st->callstack = memdup(stack_trace, stack_size);
 			if (st->callstack == NULL)