perf annotation: Switch lock from a mutex to a sharded_mutex

Remove the "struct mutex lock" variable from annotation that is
allocated per symbol. This removes in the region of 40 bytes per
symbol allocation. Use a sharded mutex where the number of shards is
set to the number of CPUs. Assuming good hashing of the annotation
(done based on the pointer), this means in order to contend there
needs to be more threads than CPUs, which is not currently true in any
perf command. Were contention an issue it is straightforward to
increase the number of shards in the mutex.

On my Debian/glibc based machine, this reduces the size of struct
annotation from 136 bytes to 96 bytes, or nearly 30%.

Signed-off-by: Ian Rogers <irogers@google.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Cc: Andres Freund <andres@anarazel.de>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Yuan Can <yuancan@huawei.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Ingo Molnar <mingo@redhat.com>
Link: https://lore.kernel.org/r/20230615040715.2064350-2-irogers@google.com
Signed-off-by: Namhyung Kim <namhyung@kernel.org>

1 files changed, 7 insertions, 7 deletions

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index c363c04e16df..1baa2acb3ced 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -137,10 +137,10 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 	}
 
 	notes = symbol__annotation(sym);
-	mutex_lock(&notes->lock);
+	annotation__lock(notes);
 
 	if (!symbol__hists(sym, top->evlist->core.nr_entries)) {
-		mutex_unlock(&notes->lock);
+		annotation__unlock(notes);
 		pr_err("Not enough memory for annotating '%s' symbol!\n",
 		       sym->name);
 		sleep(1);
@@ -156,7 +156,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		pr_err("Couldn't annotate %s: %s\n", sym->name, msg);
 	}
 
-	mutex_unlock(&notes->lock);
+	annotation__unlock(notes);
 	return err;
 }
 
@@ -211,12 +211,12 @@ static void perf_top__record_precise_ip(struct perf_top *top,
 
 	notes = symbol__annotation(sym);
 
-	if (!mutex_trylock(&notes->lock))
+	if (!annotation__trylock(notes))
 		return;
 
 	err = hist_entry__inc_addr_samples(he, sample, evsel, ip);
 
-	mutex_unlock(&notes->lock);
+	annotation__unlock(notes);
 
 	if (unlikely(err)) {
 		/*
@@ -253,7 +253,7 @@ static void perf_top__show_details(struct perf_top *top)
 	symbol = he->ms.sym;
 	notes = symbol__annotation(symbol);
 
-	mutex_lock(&notes->lock);
+	annotation__lock(notes);
 
 	symbol__calc_percent(symbol, evsel);
 
@@ -274,7 +274,7 @@ static void perf_top__show_details(struct perf_top *top)
 	if (more != 0)
 		printf("%d lines not displayed, maybe increase display entries [e]\n", more);
 out_unlock:
-	mutex_unlock(&notes->lock);
+	annotation__unlock(notes);
 }
 
 static void perf_top__resort_hists(struct perf_top *t)