perf lock contention: Track and show mmap_lock with address

Sometimes there are severe contentions on the mmap_lock and we want
see it in the -l/--lock-addr output.  However it cannot symbolize
the mmap_lock because it's allocated dynamically without symbols.

Stephane and Hao gave me an idea separately to display mmap_lock by
following the current->mm pointer.  I added a flag to mark mmap_lock
after comparing the lock address so that it can show them differently.
With this change it can show mmap_lock like below:

  $ sudo ./perf lock con -abl -- sleep 10
   contended   total wait     max wait     avg wait            address   symbol
   ...
       16344    312.30 ms      2.22 ms     19.11 us   ffff8cc702595640
       17686    310.08 ms      1.49 ms     17.53 us   ffff8cc7025952c0
           3     84.14 ms     45.79 ms     28.05 ms   ffff8cc78114c478   mmap_lock
        3557     76.80 ms     68.75 us     21.59 us   ffff8cc77ca3af58
           1     68.27 ms     68.27 ms     68.27 ms   ffff8cda745dfd70
           9     54.53 ms      7.96 ms      6.06 ms   ffff8cc7642a48b8   mmap_lock
       14629     44.01 ms     60.00 us      3.01 us   ffff8cc7625f9ca0
        3481     42.63 ms    140.71 us     12.24 us   ffffffff937906ac   vmap_area_lock
       16194     38.73 ms     42.15 us      2.39 us   ffff8cd397cbc560
          11     38.44 ms     10.39 ms      3.49 ms   ffff8ccd6d12fbb8   mmap_lock
           1      5.43 ms      5.43 ms      5.43 ms   ffff8cd70018f0d8
        1674      5.38 ms    422.93 us      3.21 us   ffffffff92e06080   tasklist_lock
         581      4.51 ms    130.68 us      7.75 us   ffff8cc9b1259058
           5      3.52 ms      1.27 ms    703.23 us   ffff8cc754510070
         112      3.47 ms     56.47 us     31.02 us   ffff8ccee38b3120
         381      3.31 ms     73.44 us      8.69 us   ffffffff93790690   purge_vmap_area_lock
         255      3.19 ms     36.35 us     12.49 us   ffff8d053ce30c80

Note that mmap_lock was renamed some time ago and it needs to support
old kernels with a different name 'mmap_sem'.

Suggested-by: Hao Luo <haoluo@google.com>
Suggested-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
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: Suren Baghdasaryan <surenb@google.com>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: bpf@vger.kernel.org
Link: https://lore.kernel.org/r/20230313204825.2665483-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/builtin-lock.c b/tools/perf/builtin-lock.c
index 240d49a..1b0dc94 100644 (file)
--- a/tools/perf/builtin-lock.c
+++ b/tools/perf/builtin-lock.c
@@ -1663,7 +1663,7 @@ static void print_contention_result(struct lock_contention *con)
                        break;
                case LOCK_AGGR_ADDR:
                        pr_info("  %016llx   %s\n", (unsigned long long)st->addr,
-                               st->name ? : "");
+                               (st->flags & LCD_F_MMAP_LOCK) ? "mmap_lock" : st->name);
                        break;
                default:
                        break;

diff --git a/tools/perf/util/bpf_skel/lock_contention.bpf.c b/tools/perf/util/bpf_skel/lock_contention.bpf.c
index 141b36d..40ee3df 100644 (file)
--- a/tools/perf/util/bpf_skel/lock_contention.bpf.c
+++ b/tools/perf/util/bpf_skel/lock_contention.bpf.c
@@ -92,6 +92,14 @@ struct rw_semaphore___new {
        atomic_long_t owner;
 } __attribute__((preserve_access_index));
 
+struct mm_struct___old {
+       struct rw_semaphore mmap_sem;
+} __attribute__((preserve_access_index));
+
+struct mm_struct___new {
+       struct rw_semaphore mmap_lock;
+} __attribute__((preserve_access_index));
+
 /* control flags */
 int enabled;
 int has_cpu;
@@ -210,6 +218,36 @@ static inline struct task_struct *get_lock_owner(__u64 lock, __u32 flags)
        return task;
 }
 
+static inline __u32 check_lock_type(__u64 lock, __u32 flags)
+{
+       struct task_struct *curr;
+       struct mm_struct___old *mm_old;
+       struct mm_struct___new *mm_new;
+
+       switch (flags) {
+       case LCB_F_READ:  /* rwsem */
+       case LCB_F_WRITE:
+               curr = bpf_get_current_task_btf();
+               if (curr->mm == NULL)
+                       break;
+               mm_new = (void *)curr->mm;
+               if (bpf_core_field_exists(mm_new->mmap_lock)) {
+                       if (&mm_new->mmap_lock == (void *)lock)
+                               return LCD_F_MMAP_LOCK;
+                       break;
+               }
+               mm_old = (void *)curr->mm;
+               if (bpf_core_field_exists(mm_old->mmap_sem)) {
+                       if (&mm_old->mmap_sem == (void *)lock)
+                               return LCD_F_MMAP_LOCK;
+               }
+               break;
+       default:
+               break;
+       }
+       return 0;
+}
+
 SEC("tp_btf/contention_begin")
 int contention_begin(u64 *ctx)
 {
@@ -320,6 +358,9 @@ int contention_end(u64 *ctx)
                        .flags = pelem->flags,
                };
 
+               if (aggr_mode == LOCK_AGGR_ADDR)
+                       first.flags |= check_lock_type(pelem->lock, pelem->flags);
+
                bpf_map_update_elem(&lock_stat, &key, &first, BPF_NOEXIST);
                bpf_map_delete_elem(&tstamp, &pid);
                return 0;

diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
index 3d35fd4..789f208 100644 (file)
--- a/tools/perf/util/bpf_skel/lock_data.h
+++ b/tools/perf/util/bpf_skel/lock_data.h
@@ -15,6 +15,12 @@ struct contention_task_data {
        char comm[TASK_COMM_LEN];
 };
 
+/*
+ * Upper bits of the flags in the contention_data are used to identify
+ * some well-known locks which do not have symbols (non-global locks).
+ */
+#define LCD_F_MMAP_LOCK  (1U << 31)
+
 struct contention_data {
        u64 total_time;
        u64 min_time;