Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Jaegeuk Kim <jaegeuk@kernel.org>
To:     linux-kernel@vger.kernel.org,
        linux-f2fs-devel@lists.sourceforge.net
Cc:     Jaegeuk Kim <jaegeuk@kernel.org>
Subject: [PATCH 2/2] f2fs: avoid an infinite loop in f2fs_sync_dirty_inodes
Date:   Sat, 12 Feb 2022 06:20:23 -0800
Message-Id: <20220212142023.2508247-2-jaegeuk@kernel.org>
In-Reply-To: <20220212142023.2508247-1-jaegeuk@kernel.org>
References: <20220212142023.2508247-1-jaegeuk@kernel.org>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

If one read IO is always failing, we can fall into an infinite loop in
f2fs_sync_dirty_inodes. This happens during xfstests/generic/457.

[  142.803335] Buffer I/O error on dev dm-1, logical block 8388592, async page read
...
[  382.887210]  submit_bio_noacct+0xdd/0x2a0
[  382.887213]  submit_bio+0x80/0x110
[  382.887223]  __submit_bio+0x4d/0x300 [f2fs]
[  382.887282]  f2fs_submit_page_bio+0x125/0x200 [f2fs]
[  382.887299]  __get_meta_page+0xc9/0x280 [f2fs]
[  382.887315]  f2fs_get_meta_page+0x13/0x20 [f2fs]
[  382.887331]  f2fs_get_node_info+0x317/0x3c0 [f2fs]
[  382.887350]  f2fs_do_write_data_page+0x327/0x6f0 [f2fs]
[  382.887367]  f2fs_write_single_data_page+0x5b7/0x960 [f2fs]
[  382.887386]  f2fs_write_cache_pages+0x302/0x890 [f2fs]
[  382.887405]  ? preempt_count_add+0x7a/0xc0
[  382.887408]  f2fs_write_data_pages+0xfd/0x320 [f2fs]
[  382.887425]  ? _raw_spin_unlock+0x1a/0x30
[  382.887428]  do_writepages+0xd3/0x1d0
[  382.887432]  filemap_fdatawrite_wbc+0x69/0x90
[  382.887434]  filemap_fdatawrite+0x50/0x70
[  382.887437]  f2fs_sync_dirty_inodes+0xa4/0x270 [f2fs]
[  382.887453]  f2fs_write_checkpoint+0x189/0x1640 [f2fs]
[  382.887469]  ? schedule_timeout+0x114/0x150
[  382.887471]  ? ttwu_do_activate+0x6d/0xb0
[  382.887473]  ? preempt_count_add+0x7a/0xc0
[  382.887476]  kill_f2fs_super+0xca/0x100 [f2fs]
[  382.887491]  deactivate_locked_super+0x35/0xa0
[  382.887494]  deactivate_super+0x40/0x50
[  382.887497]  cleanup_mnt+0x139/0x190
[  382.887499]  __cleanup_mnt+0x12/0x20
[  382.887501]  task_work_run+0x64/0xa0
[  382.887505]  exit_to_user_mode_prepare+0x1b7/0x1c0
[  382.887508]  syscall_exit_to_user_mode+0x27/0x50
[  382.887510]  do_syscall_64+0x48/0xc0
[  382.887513]  entry_SYSCALL_64_after_hwframe+0x44/0xae

Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/checkpoint.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index 203a1577942d..756abfdf3628 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -1059,13 +1059,13 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 	struct inode *inode;
 	struct f2fs_inode_info *fi;
 	bool is_dir = (type == DIR_INODE);
-	unsigned long ino = 0;
+	unsigned long ino = 0, retry_count = DEFAULT_RETRY_IO_COUNT;
 
 	trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
 				get_pages(sbi, is_dir ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 retry:
-	if (unlikely(f2fs_cp_error(sbi))) {
+	if (unlikely(f2fs_cp_error(sbi) || !retry_count)) {
 		trace_f2fs_sync_dirty_inodes_exit(sbi->sb, is_dir,
 				get_pages(sbi, is_dir ?
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
@@ -1096,10 +1096,12 @@ int f2fs_sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 
 		iput(inode);
 		/* We need to give cpu to another writers. */
-		if (ino == cur_ino)
+		if (ino == cur_ino) {
+			retry_count--;
 			cond_resched();
-		else
+		} else {
 			ino = cur_ino;
+		}
 	} else {
 		/*
 		 * We should submit bio, since it exists several
-- 
2.35.1.265.g69c8d7142f-goog