1 files changed, 70 insertions, 31 deletions

diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 1bb8628e7c9f..11b0fc7ee53b 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -5,24 +5,11 @@
 #include <bpf/bpf_tracing.h>
 #include <bpf/bpf_core_read.h>
 
-/* maximum stack trace depth */
-#define MAX_STACKS   8
+#include "lock_data.h"
 
 /* default buffer size */
 #define MAX_ENTRIES  10240
 
-struct contention_key {
-	__s32 stack_id;
-};
-
-struct contention_data {
-	__u64 total_time;
-	__u64 min_time;
-	__u64 max_time;
-	__u32 count;
-	__u32 flags;
-};
-
 struct tstamp_data {
 	__u64 timestamp;
 	__u64 lock;
@@ -34,16 +21,16 @@ struct tstamp_data {
 struct {
 	__uint(type, BPF_MAP_TYPE_STACK_TRACE);
 	__uint(key_size, sizeof(__u32));
-	__uint(value_size, MAX_STACKS * sizeof(__u64));
+	__uint(value_size, sizeof(__u64));
 	__uint(max_entries, MAX_ENTRIES);
 } stacks SEC(".maps");
 
 /* maintain timestamp at the beginning of contention */
 struct {
-	__uint(type, BPF_MAP_TYPE_TASK_STORAGE);
-	__uint(map_flags, BPF_F_NO_PREALLOC);
+	__uint(type, BPF_MAP_TYPE_HASH);
 	__type(key, int);
 	__type(value, struct tstamp_data);
+	__uint(max_entries, MAX_ENTRIES);
 } tstamp SEC(".maps");
 
 /* actual lock contention statistics */
@@ -57,6 +44,13 @@ struct {
 struct {
 	__uint(type, BPF_MAP_TYPE_HASH);
 	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(struct contention_task_data));
+	__uint(max_entries, MAX_ENTRIES);
+} task_data SEC(".maps");
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u32));
 	__uint(value_size, sizeof(__u8));
 	__uint(max_entries, 1);
 } cpu_filter SEC(".maps");
@@ -74,6 +68,9 @@ int has_cpu;
 int has_task;
 int stack_skip;
 
+/* determine the key of lock stat */
+int aggr_mode;
+
 /* error stat */
 int lost;
 
@@ -100,35 +97,62 @@ static inline int can_record(void)
 	return 1;
 }
 
+static inline void update_task_data(__u32 pid)
+{
+	struct contention_task_data *p;
+
+	p = bpf_map_lookup_elem(&task_data, &pid);
+	if (p == NULL) {
+		struct contention_task_data data;
+
+		bpf_get_current_comm(data.comm, sizeof(data.comm));
+		bpf_map_update_elem(&task_data, &pid, &data, BPF_NOEXIST);
+	}
+}
+
 SEC("tp_btf/contention_begin")
 int contention_begin(u64 *ctx)
 {
-	struct task_struct *curr;
+	__u32 pid;
 	struct tstamp_data *pelem;
 
 	if (!enabled || !can_record())
 		return 0;
 
-	curr = bpf_get_current_task_btf();
-	pelem = bpf_task_storage_get(&tstamp, curr, NULL,
-				     BPF_LOCAL_STORAGE_GET_F_CREATE);
-	if (!pelem || pelem->lock)
+	pid = bpf_get_current_pid_tgid();
+	pelem = bpf_map_lookup_elem(&tstamp, &pid);
+	if (pelem && pelem->lock)
 		return 0;
 
+	if (pelem == NULL) {
+		struct tstamp_data zero = {};
+
+		bpf_map_update_elem(&tstamp, &pid, &zero, BPF_ANY);
+		pelem = bpf_map_lookup_elem(&tstamp, &pid);
+		if (pelem == NULL) {
+			lost++;
+			return 0;
+		}
+	}
+
 	pelem->timestamp = bpf_ktime_get_ns();
 	pelem->lock = (__u64)ctx[0];
 	pelem->flags = (__u32)ctx[1];
-	pelem->stack_id = bpf_get_stackid(ctx, &stacks, BPF_F_FAST_STACK_CMP | stack_skip);
 
-	if (pelem->stack_id < 0)
-		lost++;
+	if (aggr_mode == LOCK_AGGR_CALLER) {
+		pelem->stack_id = bpf_get_stackid(ctx, &stacks,
+						  BPF_F_FAST_STACK_CMP | stack_skip);
+		if (pelem->stack_id < 0)
+			lost++;
+	}
+
 	return 0;
 }
 
 SEC("tp_btf/contention_end")
 int contention_end(u64 *ctx)
 {
-	struct task_struct *curr;
+	__u32 pid;
 	struct tstamp_data *pelem;
 	struct contention_key key;
 	struct contention_data *data;
@@ -137,14 +161,29 @@ int contention_end(u64 *ctx)
 	if (!enabled)
 		return 0;
 
-	curr = bpf_get_current_task_btf();
-	pelem = bpf_task_storage_get(&tstamp, curr, NULL, 0);
+	pid = bpf_get_current_pid_tgid();
+	pelem = bpf_map_lookup_elem(&tstamp, &pid);
 	if (!pelem || pelem->lock != ctx[0])
 		return 0;
 
 	duration = bpf_ktime_get_ns() - pelem->timestamp;
 
-	key.stack_id = pelem->stack_id;
+	switch (aggr_mode) {
+	case LOCK_AGGR_CALLER:
+		key.aggr_key = pelem->stack_id;
+		break;
+	case LOCK_AGGR_TASK:
+		key.aggr_key = pid;
+		update_task_data(pid);
+		break;
+	case LOCK_AGGR_ADDR:
+		key.aggr_key = pelem->lock;
+		break;
+	default:
+		/* should not happen */
+		return 0;
+	}
+
 	data = bpf_map_lookup_elem(&lock_stat, &key);
 	if (!data) {
 		struct contention_data first = {
@@ -156,7 +195,7 @@ int contention_end(u64 *ctx)
 		};
 
 		bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST);
-		pelem->lock = 0;
+		bpf_map_delete_elem(&tstamp, &pid);
 		return 0;
 	}
 
@@ -169,7 +208,7 @@ int contention_end(u64 *ctx)
 	if (data->min_time > duration)
 		data->min_time = duration;
 
-	pelem->lock = 0;
+	bpf_map_delete_elem(&tstamp, &pid);
 	return 0;
 }