perf lock contention: Support filters for different aggregation

It'd be useful to filter other than the current aggregation mode.  For
example, users may want to see callstacks for specific locks only.  Or
they may want tasks from a certain callstack.

The tracepoints already collected the information but it needs to check
the condition again when processing the event.  And it needs to change
BPF to allow the key combinations.

The lock contentions on 'rcu_state' spinlock can be monitored:

  $ sudo perf lock con -abv -L rcu_state sleep 1
  ...
   contended   total wait     max wait     avg wait         type   caller

           4    151.39 us     62.57 us     37.85 us     spinlock   rcu_core+0xcb
                          0xffffffff81fd1666  _raw_spin_lock_irqsave+0x46
                          0xffffffff8172d76b  rcu_core+0xcb
                          0xffffffff822000eb  __softirqentry_text_start+0xeb
                          0xffffffff816a0ba9  __irq_exit_rcu+0xc9
                          0xffffffff81fc0112  sysvec_apic_timer_interrupt+0xa2
                          0xffffffff82000e46  asm_sysvec_apic_timer_interrupt+0x16
                          0xffffffff81d49f78  cpuidle_enter_state+0xd8
                          0xffffffff81d4a259  cpuidle_enter+0x29
           1     30.21 us     30.21 us     30.21 us     spinlock   rcu_core+0xcb
                          0xffffffff81fd1666  _raw_spin_lock_irqsave+0x46
                          0xffffffff8172d76b  rcu_core+0xcb
                          0xffffffff822000eb  __softirqentry_text_start+0xeb
                          0xffffffff816a0ba9  __irq_exit_rcu+0xc9
                          0xffffffff81fc00c4  sysvec_apic_timer_interrupt+0x54
                          0xffffffff82000e46  asm_sysvec_apic_timer_interrupt+0x16
           1     28.84 us     28.84 us     28.84 us     spinlock   rcu_accelerate_cbs_unlocked+0x40
                          0xffffffff81fd1c60  _raw_spin_lock+0x30
                          0xffffffff81728cf0  rcu_accelerate_cbs_unlocked+0x40
                          0xffffffff8172da82  rcu_core+0x3e2
                          0xffffffff822000eb  __softirqentry_text_start+0xeb
                          0xffffffff816a0ba9  __irq_exit_rcu+0xc9
                          0xffffffff81fc0112  sysvec_apic_timer_interrupt+0xa2
                          0xffffffff82000e46  asm_sysvec_apic_timer_interrupt+0x16
                          0xffffffff81d49f78  cpuidle_enter_state+0xd8
  ...

To see tasks calling 'rcu_core' function:

  $ sudo perf lock con -abt -S rcu_core sleep 1
   contended   total wait     max wait     avg wait          pid   comm

          19     23.46 us      2.21 us      1.23 us            0   swapper
           2     18.37 us     17.01 us      9.19 us      2061859   ThreadPoolForeg
           3      5.76 us      1.97 us      1.92 us         3909   pipewire-pulse
           1      2.26 us      2.26 us      2.26 us      1809271   MediaSu~isor #2
           1      1.97 us      1.97 us      1.97 us      1514882   Chrome_ChildIOT
           1       987 ns       987 ns       987 ns         3740   pipewire-pulse

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/20230203021324.143540-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

2 files changed, 13 insertions, 6 deletions

diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index ad0ca5d50557..7ce276ed987e 100644
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -82,6 +82,7 @@ int has_cpu;
 int has_task;
 int has_type;
 int has_addr;
+int needs_callstack;
 int stack_skip;
 
 /* determine the key of lock stat */
@@ -173,7 +174,7 @@ int contention_begin(u64 *ctx)
 	pelem->lock = (__u64)ctx[0];
 	pelem->flags = (__u32)ctx[1];
 
-	if (aggr_mode == LOCK_AGGR_CALLER) {
+	if (needs_callstack) {
 		pelem->stack_id = bpf_get_stackid(ctx, &stacks,
 						  BPF_F_FAST_STACK_CMP | stack_skip);
 		if (pelem->stack_id < 0)
@@ -188,7 +189,7 @@ int contention_end(u64 *ctx)
 {
 	__u32 pid;
 	struct tstamp_data *pelem;
-	struct contention_key key;
+	struct contention_key key = {};
 	struct contention_data *data;
 	__u64 duration;
 
@@ -204,14 +205,18 @@ int contention_end(u64 *ctx)
 
 	switch (aggr_mode) {
 	case LOCK_AGGR_CALLER:
-		key.aggr_key = pelem->stack_id;
+		key.stack_id = pelem->stack_id;
 		break;
 	case LOCK_AGGR_TASK:
-		key.aggr_key = pid;
+		key.pid = pid;
 		update_task_data(pid);
+		if (needs_callstack)
+			key.stack_id = pelem->stack_id;
 		break;
 	case LOCK_AGGR_ADDR:
-		key.aggr_key = pelem->lock;
+		key.lock_addr = pelem->lock;
+		if (needs_callstack)
+			key.stack_id = pelem->stack_id;
 		break;
 	default:
 		/* should not happen */
diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
index ce71cf1a7e1e..3d35fd4407ac 100644
--- a/tools/perf/util/bpf_skel/lock_data.h
+++ b/tools/perf/util/bpf_skel/lock_data.h
@@ -4,7 +4,9 @@
 #define UTIL_BPF_SKEL_LOCK_DATA_H
 
 struct contention_key {
-	u64 aggr_key;  /* can be stack_id, pid or lock addr */
+	u32 stack_id;
+	u32 pid;
+	u64 lock_addr;
 };
 
 #define TASK_COMM_LEN  16