@@ -42,6 +42,7 @@
#include <linux/zalloc.h>
#include <linux/err.h>
#include <linux/stringify.h>
+#include <linux/rbtree.h>
static struct perf_session *session;
static struct target target;
@@ -1926,6 +1927,24 @@ static void print_contention_result(struct lock_contention *con)
break;
}
+ if (con->owner && con->save_callstack) {
+ struct rb_root root = RB_ROOT;
+
+
+ if (symbol_conf.field_sep)
+ fprintf(lock_output, "# owner stack trace:\n");
+ else
+ fprintf(lock_output, "\n=== owner stack trace ===\n\n");
+ while ((st = pop_owner_stack_trace(con))) {
+ insert_to(&root, st, compare);
+ }
+
+ while ((st = pop_from(&root))) {
+ print_lock_stat(con, st);
+ zfree(st);
+ }
+ }
+
if (print_nr_entries) {
/* update the total/bad stats */
while ((st = pop_from_result())) {
@@ -2071,7 +2090,7 @@ static int check_lock_contention_options(const struct option *options,
}
}
- if (show_lock_owner)
+ if (show_lock_owner && !verbose)
show_thread_stats = true;
return 0;
@@ -414,6 +414,47 @@ static const char *lock_contention_get_name(struct lock_contention *con,
return name_buf;
}
+struct lock_stat *pop_owner_stack_trace(struct lock_contention *con)
+{
+ int fd;
+ u64 *stack_trace;
+ struct contention_data data = {};
+ size_t stack_size = con->max_stack * sizeof(*stack_trace);
+ struct lock_stat *st;
+ char name[KSYM_NAME_LEN];
+
+ fd = bpf_map__fd(skel->maps.owner_lock_stat);
+
+ stack_trace = zalloc(stack_size);
+ if (stack_trace == NULL)
+ return NULL;
+
+ if (bpf_map_get_next_key(fd, NULL, stack_trace))
+ return NULL;
+
+ bpf_map_lookup_elem(fd, stack_trace, &data);
+ st = zalloc(sizeof(struct lock_stat));
+
+ strcpy(name, stack_trace[0] ? lock_contention_get_name(con, NULL,
+ stack_trace, 0) :
+ "unknown");
+
+ st->name = strdup(name);
+ st->flags = data.flags;
+ st->nr_contended = data.count;
+ st->wait_time_total = data.total_time;
+ st->wait_time_max = data.max_time;
+ st->wait_time_min = data.min_time;
+ st->callstack = memdup(stack_trace, stack_size);
+
+ if (data.count)
+ st->avg_wait_time = data.total_time / data.count;
+
+ bpf_map_delete_elem(fd, stack_trace);
+ free(stack_trace);
+
+ return st;
+}
int lock_contention_read(struct lock_contention *con)
{
int fd, stack, err = 0;
@@ -156,6 +156,8 @@ int lock_contention_stop(void);
int lock_contention_read(struct lock_contention *con);
int lock_contention_finish(struct lock_contention *con);
+struct lock_stat *pop_owner_stack_trace(struct lock_contention *con);
+
#else /* !HAVE_BPF_SKEL */
static inline int lock_contention_prepare(struct lock_contention *con __maybe_unused)
Parse `owner_lock_stat` into a rb tree, and report owner lock stats with stack trace in order. Example output: $ sudo ~/linux/tools/perf/perf lock con -abvo -Y mutex-spin -E3 perf bench sched pipe ... contended total wait max wait avg wait type caller 171 1.55 ms 20.26 us 9.06 us mutex pipe_read+0x57 0xffffffffac6318e7 pipe_read+0x57 0xffffffffac623862 vfs_read+0x332 0xffffffffac62434b ksys_read+0xbb 0xfffffffface604b2 do_syscall_64+0x82 0xffffffffad00012f entry_SYSCALL_64_after_hwframe+0x76 36 193.71 us 15.27 us 5.38 us mutex pipe_write+0x50 0xffffffffac631ee0 pipe_write+0x50 0xffffffffac6241db vfs_write+0x3bb 0xffffffffac6244ab ksys_write+0xbb 0xfffffffface604b2 do_syscall_64+0x82 0xffffffffad00012f entry_SYSCALL_64_after_hwframe+0x76 4 51.22 us 16.47 us 12.80 us mutex do_epoll_wait+0x24d 0xffffffffac691f0d do_epoll_wait+0x24d 0xffffffffac69249b do_epoll_pwait.part.0+0xb 0xffffffffac693ba5 __x64_sys_epoll_pwait+0x95 0xfffffffface604b2 do_syscall_64+0x82 0xffffffffad00012f entry_SYSCALL_64_after_hwframe+0x76 === owner stack trace === 3 31.24 us 15.27 us 10.41 us mutex pipe_read+0x348 0xffffffffac631bd8 pipe_read+0x348 0xffffffffac623862 vfs_read+0x332 0xffffffffac62434b ksys_read+0xbb 0xfffffffface604b2 do_syscall_64+0x82 0xffffffffad00012f entry_SYSCALL_64_after_hwframe+0x76 ... Signed-off-by: Chun-Tse Shao <ctshao@google.com> --- tools/perf/builtin-lock.c | 21 +++++++++++++- tools/perf/util/bpf_lock_contention.c | 41 +++++++++++++++++++++++++++ tools/perf/util/lock-contention.h | 2 ++ 3 files changed, 63 insertions(+), 1 deletion(-)