f2fs: fix to do sanity check on dcc->discard_cmd_cnt conditionally

[ Upstream commit 6af249c ]

Syzbot reported a f2fs bug as below:

------------[ cut here ]------------
kernel BUG at fs/f2fs/segment.c:1900!
Oops: invalid opcode: 0000 [#1] SMP KASAN PTI
CPU: 1 UID: 0 PID: 6527 Comm: syz.5.110 Not tainted syzkaller #0 PREEMPT_{RT,(full)}
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 02/12/2026
RIP: 0010:f2fs_issue_discard_timeout+0x59b/0x5a0 fs/f2fs/segment.c:1900
Code: d9 80 e1 07 80 c1 03 38 c1 0f 8c d6 fe ff ff 48 89 df e8 a8 5e fa fd e9 c9 fe ff ff e8 4e 46 94 fd 90 0f 0b e8 46 46 94 fd 90 <0f> 0b 0f 1f 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3
RSP: 0018:ffffc9000494f940 EFLAGS: 00010283
RAX: ffffffff843009ca RBX: 0000000000000001 RCX: 0000000000080000
RDX: ffffc9001ca78000 RSI: 00000000000029f3 RDI: 00000000000029f4
RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000
R10: dffffc0000000000 R11: ffffed100893a431 R12: 1ffff1100893a430
R13: 1ffff1100c2b702c R14: dffffc0000000000 R15: ffff8880449d2160
FS:  00007ffa35fed6c0(0000) GS:ffff88812643d000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007f2b68634000 CR3: 0000000039f62000 CR4: 00000000003526f0
Call Trace:
 <TASK>
 __f2fs_remount fs/f2fs/super.c:2960 [inline]
 f2fs_reconfigure+0x108a/0x1710 fs/f2fs/super.c:5443
 reconfigure_super+0x227/0x8a0 fs/super.c:1080
 do_remount fs/namespace.c:3391 [inline]
 path_mount+0xdc5/0x10e0 fs/namespace.c:4151
 do_mount fs/namespace.c:4172 [inline]
 __do_sys_mount fs/namespace.c:4361 [inline]
 __se_sys_mount+0x31d/0x420 fs/namespace.c:4338
 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline]
 do_syscall_64+0x14d/0xf80 arch/x86/entry/syscall_64.c:94
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7ffa37dbda0a

The root cause is there will be race condition in between f2fs_ioc_fitrim()
and f2fs_remount():

- f2fs_remount			- f2fs_ioc_fitrim
 - f2fs_issue_discard_timeout
  - __issue_discard_cmd
  - __drop_discard_cmd
  - __wait_all_discard_cmd
				 - f2fs_trim_fs
				  - f2fs_write_checkpoint
				   - f2fs_clear_prefree_segments
				    - f2fs_issue_discard
				     - __issue_discard_async
				      - __queue_discard_cmd
				       - __update_discard_tree_range
				        - __insert_discard_cmd
				         - __create_discard_cmd
				         : atomic_inc(&dcc->discard_cmd_cnt);
  - sanity check on dcc->discard_cmd_cnt (expect discard_cmd_cnt to be zero)

This will only happen when fitrim races w/ remount rw, if we remount to
readonly filesystem, remount will wait until mnt_pcp.mnt_writers to zero,
that means fitrim is not in process at that time.

Cc: stable@kernel.org
Fixes: 2482c43 ("f2fs: detect bug_on in f2fs_wait_discard_bios")
Reported-by: syzbot+62538b67389ee582837a@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/linux-f2fs-devel/69b07d7c.050a0220.8df7.09a1.GAE@google.com
Signed-off-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
[ dereferenced flags pointer (`*flags & SB_RDONLY`) to match `int *flags` remount signature ]
Signed-off-by: Sasha Levin <sashal@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Author: chaseyu

fs/f2fs/f2fs.h

@@ -3722,7 +3722,7 @@ bool f2fs_is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
 int f2fs_start_discard_thread(struct f2fs_sb_info *sbi);
 void f2fs_drop_discard_cmd(struct f2fs_sb_info *sbi);
 void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi);
-bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi);
+bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi, bool need_check);
 void f2fs_clear_prefree_segments(struct f2fs_sb_info *sbi,
 					struct cp_control *cpc);
 void f2fs_dirty_to_prefree(struct f2fs_sb_info *sbi);

fs/f2fs/segment.c

@@ -1873,7 +1873,7 @@ void f2fs_stop_discard_thread(struct f2fs_sb_info *sbi)
  *
  * Return true if issued all discard cmd or no discard cmd need issue, otherwise return false.
  */
-bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
+bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi, bool need_check)
 {
 	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct discard_policy dpolicy;
@@ -1890,7 +1890,7 @@ bool f2fs_issue_discard_timeout(struct f2fs_sb_info *sbi)
 	/* just to make sure there is no pending discard commands */
 	__wait_all_discard_cmd(sbi, NULL);
 
-	f2fs_bug_on(sbi, atomic_read(&dcc->discard_cmd_cnt));
+	f2fs_bug_on(sbi, need_check && atomic_read(&dcc->discard_cmd_cnt));
 	return !dropped;
 }
 
@@ -2349,7 +2349,7 @@ static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
 	 * Recovery can cache discard commands, so in error path of
 	 * fill_super(), it needs to give a chance to handle them.
 	 */
-	f2fs_issue_discard_timeout(sbi);
+	f2fs_issue_discard_timeout(sbi, true);
 
 	kfree(dcc);
 	SM_I(sbi)->dcc_info = NULL;

fs/f2fs/super.c

@@ -1612,7 +1612,7 @@ static void f2fs_put_super(struct super_block *sb)
 	}
 
 	/* be sure to wait for any on-going discard commands */
-	done = f2fs_issue_discard_timeout(sbi);
+	done = f2fs_issue_discard_timeout(sbi, true);
 	if (f2fs_realtime_discard_enable(sbi) && !sbi->discard_blks && done) {
 		struct cp_control cpc = {
 			.reason = CP_UMOUNT | CP_TRIMMED,
@@ -1754,7 +1754,7 @@ static int f2fs_unfreeze(struct super_block *sb)
 	 * will recover after removal of snapshot.
 	 */
 	if (test_opt(sbi, DISCARD) && !f2fs_hw_support_discard(sbi))
-		f2fs_issue_discard_timeout(sbi);
+		f2fs_issue_discard_timeout(sbi, true);
 
 	clear_sbi_flag(F2FS_SB(sb), SBI_IS_FREEZING);
 	return 0;
@@ -2515,7 +2515,12 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			need_stop_discard = true;
 		} else {
 			f2fs_stop_discard_thread(sbi);
-			f2fs_issue_discard_timeout(sbi);
+			/*
+			 * f2fs_ioc_fitrim() won't race w/ "remount ro"
+			 * so it's safe to check discard_cmd_cnt in
+			 * f2fs_issue_discard_timeout().
+			 */
+			f2fs_issue_discard_timeout(sbi, *flags & SB_RDONLY);
 			need_restart_discard = true;
 		}
 	}