f2fs: avoid deadlock in f2fs_shrink_extent_tree

While handling extent trees, we can enter into a reclaiming path anytime.
If it tries to release some extent nodes in the same extent tree,
write_lock(&et->lock) would be hanged.
In order to avoid the deadlock, we can just skip it.

Note that, if it is an unreferenced tree, we should get write_lock(&et->lock)
successfully and release all of therein nodes.

Reviewed-by: Chao Yu <chao2.yu@samsung.com>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>

diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 7ddba812e11b7508aa6d3511cae05093624d6562..de063f2b238473fd07906536df6c61c763fd20b6 100644 (file)
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -615,9 +615,10 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
                for (i = 0; i < found; i++) {
                        struct extent_tree *et = treevec[i];
 
-                       write_lock(&et->lock);
-                       node_cnt += __free_extent_tree(sbi, et, false);
-                       write_unlock(&et->lock);
+                       if (write_trylock(&et->lock)) {
+                               node_cnt += __free_extent_tree(sbi, et, false);
+                               write_unlock(&et->lock);
+                       }
 
                        if (node_cnt + tree_cnt >= nr_shrink)
                                goto unlock_out;