f2fs: don't sleep while grabing nat_tree_lock

This tries to fix priority inversion in the below condition resulting in
long checkpoint delay.

f2fs_get_node_info()
 - nat_tree_lock
  -> sleep to grab journal_rwsem by contention

                                     checkpoint
                                     - waiting for nat_tree_lock

In order to let checkpoint go, let's release nat_tree_lock, if there's a
journal_rwsem contention.

Signed-off-by: Daeho Jeong <daehojeong@google.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

1 files changed, 13 insertions, 4 deletions

diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index 0be9e2d7120e..c945a9730f3c 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -552,7 +552,7 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 	int i;
 
 	ni->nid = nid;
-
+retry:
 	/* Check nat cache */
 	down_read(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, nid);
@@ -564,10 +564,19 @@ int f2fs_get_node_info(struct f2fs_sb_info *sbi, nid_t nid,
 		return 0;
 	}
 
-	memset(&ne, 0, sizeof(struct f2fs_nat_entry));
+	/*
+	 * Check current segment summary by trying to grab journal_rwsem first.
+	 * This sem is on the critical path on the checkpoint requiring the above
+	 * nat_tree_lock. Therefore, we should retry, if we failed to grab here
+	 * while not bothering checkpoint.
+	 */
+	if (!rwsem_is_locked(&sbi->cp_global_sem)) {
+		down_read(&curseg->journal_rwsem);
+	} else if (!down_read_trylock(&curseg->journal_rwsem)) {
+		up_read(&nm_i->nat_tree_lock);
+		goto retry;
+	}
 
-	/* Check current segment summary */
-	down_read(&curseg->journal_rwsem);
 	i = f2fs_lookup_journal_in_cursum(journal, NAT_JOURNAL, nid, 0);
 	if (i >= 0) {
 		ne = nat_in_journal(journal, i);