perf lock contention: Account contending locks too

Currently it accounts the contention using delta between timestamps in
lock:contention_begin and lock:contention_end tracepoints.  But it means
the lock should see the both events during the monitoring period.

Actually there are 4 cases that happen with the monitoring:

                monitoring period
            /                       \
            |                       |
 1:  B------+-----------------------+--------E
 2:    B----+-------------E         |
 3:         |           B-----------+----E
 4:         |     B-------------E   |
            |                       |
            t0                      t1

where B and E mean contention BEGIN and END, respectively.  So it only
accounts the case 4 for now.  It seems there's no way to handle the case
1.  The case 2 might be handled if it saved the timestamp (t0), but it
lacks the information from the B notably the flags which shows the lock
types.  Also it could be a nested lock which it currently ignores.  So
I think we should ignore the case 2.

However we can handle the case 3 if we save the timestamp (t1) at the
end of the period.  And then it can iterate the map entries in the
userspace and update the lock stat accordinly.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reviewed-by: Ian Rogers <irogers@google.com>
Reviwed-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Song Liu <song@kernel.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20240228053335.312776-1-namhyung@kernel.org

2 files changed, 16 insertions, 7 deletions

diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 95cd8414f6ef..fb54bd38e7d0 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -19,13 +19,6 @@
 #define LCB_F_PERCPU	(1U << 4)
 #define LCB_F_MUTEX	(1U << 5)
 
-struct tstamp_data {
-	__u64 timestamp;
-	__u64 lock;
-	__u32 flags;
-	__s32 stack_id;
-};
-
 /* callstack storage  */
 struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
@@ -140,6 +133,8 @@ int perf_subsys_id = -1;
 /* determine the key of lock stat */
 int aggr_mode;
 
+__u64 end_ts;
+
 /* error stat */
 int task_fail;
 int stack_fail;
@@ -559,4 +554,11 @@ int BPF_PROG(collect_lock_syms)
 	return 0;
 }
 
+SEC("raw_tp/bpf_test_finish")
+int BPF_PROG(end_timestamp)
+{
+	end_ts = bpf_ktime_get_ns();
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
index 08482daf61be..36af11faad03 100644
--- a/tools/perf/util/bpf_skel/lock_data.h
+++ b/tools/perf/util/bpf_skel/lock_data.h
@@ -3,6 +3,13 @@
 #ifndef UTIL_BPF_SKEL_LOCK_DATA_H
 #define UTIL_BPF_SKEL_LOCK_DATA_H
 
+struct tstamp_data {
+	u64 timestamp;
+	u64 lock;
+	u32 flags;
+	u32 stack_id;
+};
+
 struct contention_key {
 	u32 stack_id;
 	u32 pid;