perf lock contention: Use lock_stat_find{,new}

This is a preparation work to support complex keys of BPF maps.  Now it
has single value key according to the aggregation mode like stack_id or
pid.  But we want to use a combination of those keys.

Then lock_contention_read() should still aggregate the result based on
the key that was requested by user.  The other key info will be used for
filtering.

So instead of creating a lock_stat entry always, Check if it's already
there using lock_stat_find() first.

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/20230203021324.143540-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

Author: namhyung

tools/perf/builtin-lock.c

@@ -465,7 +465,7 @@ static struct lock_stat *pop_from_result(void)
 	return container_of(node, struct lock_stat, rb);
 }
 
-static struct lock_stat *lock_stat_find(u64 addr)
+struct lock_stat *lock_stat_find(u64 addr)
 {
 	struct hlist_head *entry = lockhashentry(addr);
 	struct lock_stat *ret;
@@ -477,7 +477,7 @@ static struct lock_stat *lock_stat_find(u64 addr)
 	return NULL;
 }
 
-static struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags)
+struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags)
 {
 	struct hlist_head *entry = lockhashentry(addr);
 	struct lock_stat *ret, *new;

tools/perf/util/Build

@@ -154,7 +154,10 @@ perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_counter_cgroup.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_ftrace.o
 perf-$(CONFIG_PERF_BPF_SKEL) += bpf_off_cpu.o
-perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o
+
+ifeq ($(CONFIG_LIBTRACEEVENT),y)
+  perf-$(CONFIG_PERF_BPF_SKEL) += bpf_lock_contention.o
+endif
 
 ifeq ($(CONFIG_LIBTRACEEVENT),y)
   perf-$(CONFIG_PERF_BPF_SKEL) += bpf_kwork.o

tools/perf/util/bpf_lock_contention.c

@@ -256,12 +256,34 @@ int lock_contention_read(struct lock_contention *con)
 	prev_key = NULL;
 	while (!bpf_map_get_next_key(fd, prev_key, &key)) {
 		s32 stack_id;
+		const char *name;
 
 		/* to handle errors in the loop body */
 		err = -1;
 
 		bpf_map_lookup_elem(fd, &key, &data);
-		st = zalloc(sizeof(*st));
+
+		if (con->save_callstack) {
+			stack_id = key.aggr_key;
+			bpf_map_lookup_elem(stack, &stack_id, stack_trace);
+		}
+
+		st = lock_stat_find(key.aggr_key);
+		if (st != NULL) {
+			st->wait_time_total += data.total_time;
+			if (st->wait_time_max < data.max_time)
+				st->wait_time_max = data.max_time;
+			if (st->wait_time_min > data.min_time)
+				st->wait_time_min = data.min_time;
+
+			st->nr_contended += data.count;
+			if (st->nr_contended)
+				st->avg_wait_time = st->wait_time_total / st->nr_contended;
+			goto next;
+		}
+
+		name = lock_contention_get_name(con, &key, stack_trace);
+		st = lock_stat_findnew(key.aggr_key, name, data.flags);
 		if (st == NULL)
 			break;
 
@@ -274,34 +296,21 @@ int lock_contention_read(struct lock_contention *con)
 			st->avg_wait_time = data.total_time / data.count;
 
 		st->flags = data.flags;
-		st->addr = key.aggr_key;
-
-		stack_id = key.aggr_key;
-		bpf_map_lookup_elem(stack, &stack_id, stack_trace);
-
-		st->name = strdup(lock_contention_get_name(con, &key, stack_trace));
-		if (st->name == NULL)
-			break;
 
 		if (con->save_callstack) {
 			st->callstack = memdup(stack_trace, stack_size);
 			if (st->callstack == NULL)
 				break;
 		}
 
-		hlist_add_head(&st->hash_entry, con->result);
+next:
 		prev_key = &key;
 
-		/* we're fine now, reset the values */
-		st = NULL;
+		/* we're fine now, reset the error */
 		err = 0;
 	}
 
 	free(stack_trace);
-	if (st) {
-		free(st->name);
-		free(st);
-	}
 
 	return err;
 }

tools/perf/util/lock-contention.h

@@ -65,6 +65,9 @@ struct lock_stat {
  */
 #define MAX_LOCK_DEPTH 48
 
+struct lock_stat *lock_stat_find(u64 addr);
+struct lock_stat *lock_stat_findnew(u64 addr, const char *name, int flags);
+
 /*
  * struct lock_seq_stat:
  * Place to put on state of one lock sequence