linux-kernel - [PATCH AUTOSEL 4.19 142/146] f2fs: fix to flush all dirty inodes recovered in readonly fs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20181031230541.28822-142-sashal@kernel.org>
Date:   Wed, 31 Oct 2018 19:05:37 -0400
From:   Sasha Levin <sashal@...nel.org>
To:     stable@...r.kernel.org, linux-kernel@...r.kernel.org
Cc:     Chao Yu <yuchao0@...wei.com>, Jaegeuk Kim <jaegeuk@...nel.org>,
        Sasha Levin <sashal@...nel.org>
Subject: [PATCH AUTOSEL 4.19 142/146] f2fs: fix to flush all dirty inodes recovered in readonly fs

From: Chao Yu <yuchao0@...wei.com>

[ Upstream commit 1378752b9921e60749eaf18ec6c47b33f9001abb ]

generic/417 reported as blow:

------------[ cut here ]------------
kernel BUG at /home/yuchao/git/devf2fs/inode.c:695!
invalid opcode: 0000 [#1] PREEMPT SMP
CPU: 1 PID: 21697 Comm: umount Tainted: G        W  O      4.18.0-rc2+ #39
Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006
EIP: f2fs_evict_inode+0x556/0x580 [f2fs]
Call Trace:
 ? _raw_spin_unlock+0x2c/0x50
 evict+0xa8/0x170
 dispose_list+0x34/0x40
 evict_inodes+0x118/0x120
 generic_shutdown_super+0x41/0x100
 ? rcu_read_lock_sched_held+0x97/0xa0
 kill_block_super+0x22/0x50
 kill_f2fs_super+0x6f/0x80 [f2fs]
 deactivate_locked_super+0x3d/0x70
 deactivate_super+0x40/0x60
 cleanup_mnt+0x39/0x70
 __cleanup_mnt+0x10/0x20
 task_work_run+0x81/0xa0
 exit_to_usermode_loop+0x59/0xa7
 do_fast_syscall_32+0x1f5/0x22c
 entry_SYSENTER_32+0x53/0x86
EIP: f2fs_evict_inode+0x556/0x580 [f2fs]

It can simply reproduced with scripts:

Enable quota feature during mkfs.

Testcase1:
1. mkfs.f2fs /dev/zram0
2. mount -t f2fs /dev/zram0 /mnt/f2fs
3. xfs_io -f /mnt/f2fs/file -c "pwrite 0 4k" -c "fsync"
4. godown /mnt/f2fs
5. umount /mnt/f2fs
6. mount -t f2fs -o ro /dev/zram0 /mnt/f2fs
7. umount /mnt/f2fs

Testcase2:
1. mkfs.f2fs /dev/zram0
2. mount -t f2fs /dev/zram0 /mnt/f2fs
3. touch /mnt/f2fs/file
4. create process[pid = x] do:
	a) open /mnt/f2fs/file;
	b) unlink /mnt/f2fs/file
5. godown -f /mnt/f2fs
6. kill process[pid = x]
7. umount /mnt/f2fs
8. mount -t f2fs -o ro /dev/zram0 /mnt/f2fs
9. umount /mnt/f2fs

The reason is: during recovery, i_{c,m}time of inode will be updated, then
the inode can be set dirty w/o being tracked in sbi->inode_list[DIRTY_META]
global list, so later write_checkpoint will not flush such dirty inode into
node page.

Once umount is called, sync_filesystem() in generic_shutdown_super() will
skip syncng dirty inodes due to sb_rdonly check, leaving dirty inodes
there.

To solve this issue, during umount, add remove SB_RDONLY flag in
sb->s_flags, to make sure sync_filesystem() will not be skipped.

Signed-off-by: Chao Yu <yuchao0@...wei.com>

Signed-off-by: Jaegeuk Kim <jaegeuk@...nel.org>

Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 fs/f2fs/checkpoint.c |  2 ++
 fs/f2fs/f2fs.h       |  1 +
 fs/f2fs/recovery.c   | 14 +++++++++-----
 fs/f2fs/super.c      |  3 +++
 4 files changed, 15 insertions(+), 5 deletions(-)

diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index e8b6b89bddb8..59d0472013f4 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -696,6 +696,8 @@ int f2fs_recover_orphan_inodes(struct f2fs_sb_info *sbi)
 	/* clear Orphan Flag */
 	clear_ckpt_flags(sbi, CP_ORPHAN_PRESENT_FLAG);
 out:
+	set_sbi_flag(sbi, SBI_IS_RECOVERED);
+
 #ifdef CONFIG_QUOTA
 	/* Turn quotas off */
 	if (quota_enabled)
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index e146e6c443e8..ecb735142276 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -1089,6 +1089,7 @@ enum {
 	SBI_NEED_SB_WRITE,			/* need to recover superblock */
 	SBI_NEED_CP,				/* need to checkpoint */
 	SBI_IS_SHUTDOWN,			/* shutdown by ioctl */
+	SBI_IS_RECOVERED,			/* recovered orphan/data */
 };
 
 enum {
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 12a3293bcbc9..9a8579fb3a30 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -698,11 +698,15 @@ int f2fs_recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	/* let's drop all the directory inodes for clean checkpoint */
 	destroy_fsync_dnodes(&dir_list);
 
-	if (!err && need_writecp) {
-		struct cp_control cpc = {
-			.reason = CP_RECOVERY,
-		};
-		err = f2fs_write_checkpoint(sbi, &cpc);
+	if (need_writecp) {
+		set_sbi_flag(sbi, SBI_IS_RECOVERED);
+
+		if (!err) {
+			struct cp_control cpc = {
+				.reason = CP_RECOVERY,
+			};
+			err = f2fs_write_checkpoint(sbi, &cpc);
+		}
 	}
 
 	kmem_cache_destroy(fsync_entry_slab);
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index d0d016f21307..287c9fe9fff9 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -3188,6 +3188,9 @@ static void kill_f2fs_super(struct super_block *sb)
 			};
 			f2fs_write_checkpoint(sbi, &cpc);
 		}
+
+		if (is_sbi_flag_set(sbi, SBI_IS_RECOVERED) && f2fs_readonly(sb))
+			sb->s_flags &= ~SB_RDONLY;
 	}
 	kill_block_super(sb);
 }
-- 
2.17.1