btrfs: trace: Introduce trace events for sleepable tree lock

There are two tree lock events which can sleep:
- btrfs_tree_read_lock()
- btrfs_tree_lock()

Sometimes we may need to look into the concurrency picture of the fs.
For that case, we need the execution time of above two functions and the
owner of @eb.

Here we introduce a trace events for user space tools like bcc, to get
the execution time of above two functions, and get detailed owner info
where eBPF code can't.

All the overhead is hidden behind the trace events, so if events are not
enabled, there is no overhead.

These trace events also output bytenr and generation, allow them to be
pared with unlock events to pin down deadlock.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: David Sterba <dsterba@suse.com>
Signed-off-by: David Sterba <dsterba@suse.com>

2 files changed, 56 insertions, 0 deletions

diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index 6df03ba36026..67b77f1d113e 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -158,6 +158,10 @@ void btrfs_clear_lock_blocking_write(struct extent_buffer *eb)
  */
 void btrfs_tree_read_lock(struct extent_buffer *eb)
 {
+	u64 start_ns = 0;
+
+	if (trace_btrfs_tree_read_lock_enabled())
+		start_ns = ktime_get_ns();
 again:
 	BUG_ON(!atomic_read(&eb->blocking_writers) &&
 	       current->pid == eb->lock_owner);
@@ -174,6 +178,7 @@ again:
 		BUG_ON(eb->lock_nested);
 		eb->lock_nested = true;
 		read_unlock(&eb->lock);
+		trace_btrfs_tree_read_lock(eb, start_ns);
 		return;
 	}
 	if (atomic_read(&eb->blocking_writers)) {
@@ -184,6 +189,7 @@ again:
 	}
 	btrfs_assert_tree_read_locks_get(eb);
 	btrfs_assert_spinning_readers_get(eb);
+	trace_btrfs_tree_read_lock(eb, start_ns);
 }
 
 /*
@@ -299,6 +305,11 @@ void btrfs_tree_read_unlock_blocking(struct extent_buffer *eb)
  */
 void btrfs_tree_lock(struct extent_buffer *eb)
 {
+	u64 start_ns = 0;
+
+	if (trace_btrfs_tree_lock_enabled())
+		start_ns = ktime_get_ns();
+
 	WARN_ON(eb->lock_owner == current->pid);
 again:
 	wait_event(eb->read_lock_wq, atomic_read(&eb->blocking_readers) == 0);
@@ -312,6 +323,7 @@ again:
 	btrfs_assert_spinning_writers_get(eb);
 	btrfs_assert_tree_write_locks_get(eb);
 	eb->lock_owner = current->pid;
+	trace_btrfs_tree_lock(eb, start_ns);
 }
 
 /*
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index 8b12753fee78..e27ed5afb958 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -2005,6 +2005,50 @@ TRACE_EVENT(btrfs_convert_extent_bit,
 		  __print_flags(__entry->clear_bits, "|", EXTENT_FLAGS))
 );
 
+DECLARE_EVENT_CLASS(btrfs_sleep_tree_lock,
+	TP_PROTO(const struct extent_buffer *eb, u64 start_ns),
+
+	TP_ARGS(eb, start_ns),
+
+	TP_STRUCT__entry_btrfs(
+		__field(	u64,	block		)
+		__field(	u64,	generation	)
+		__field(	u64,	start_ns	)
+		__field(	u64,	end_ns		)
+		__field(	u64,	diff_ns		)
+		__field(	u64,	owner		)
+		__field(	int,	is_log_tree	)
+	),
+
+	TP_fast_assign_btrfs(eb->fs_info,
+		__entry->block		= eb->start;
+		__entry->generation	= btrfs_header_generation(eb);
+		__entry->start_ns	= start_ns;
+		__entry->end_ns		= ktime_get_ns();
+		__entry->diff_ns	= __entry->end_ns - start_ns;
+		__entry->owner		= btrfs_header_owner(eb);
+		__entry->is_log_tree	= (eb->log_index >= 0);
+	),
+
+	TP_printk_btrfs(
+"block=%llu generation=%llu start_ns=%llu end_ns=%llu diff_ns=%llu owner=%llu is_log_tree=%d",
+		__entry->block, __entry->generation,
+		__entry->start_ns, __entry->end_ns, __entry->diff_ns,
+		__entry->owner, __entry->is_log_tree)
+);
+
+DEFINE_EVENT(btrfs_sleep_tree_lock, btrfs_tree_read_lock,
+	TP_PROTO(const struct extent_buffer *eb, u64 start_ns),
+
+	TP_ARGS(eb, start_ns)
+);
+
+DEFINE_EVENT(btrfs_sleep_tree_lock, btrfs_tree_lock,
+	TP_PROTO(const struct extent_buffer *eb, u64 start_ns),
+
+	TP_ARGS(eb, start_ns)
+);
+
 #endif /* _TRACE_BTRFS_H */
 
 /* This part must be outside protection */