Skip to contentSkip to conversation

general protection fault in _wait_barrier

syzbot Superseded syzbot 4 participants 8 messages Aug 27 – Aug 28 MD RAID

lore
Share & tools
lore

syzbot

author syzbot
#0 lore raw

Hello,

syzbot found the following issue on:

HEAD commit:    818bebeb63dd drm/xe: Don't hand out the flat CCS storage a..
git tree:       git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
console output: https://syzkaller.appspot.com/x/log.txt?x=1255d415580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=ccca94d2c01b9e78
dashboard link: https://syzkaller.appspot.com/bug?extid=3fe892ea5fc292e1353f
compiler:       gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=13d96979580000

IMPORTANT: if you fix the issue, please add the following tag to the commit:

Reported-by [email protected]
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000024: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000120-0x0000000000000127]
CPU: 1 UID: 0 PID: 6010 Comm: syz-executor394 Not tainted syzkaller #0 PREEMPT(full) 
Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-debian-1.16.3-2 04/01/2014
RIP: 0010:_wait_barrier+0x8d/0x700 drivers/md/raid1.c:1066
Code: 08 00 00 00 f3 c7 40 0c f3 f3 f3 f3 65 48 8b 05 31 1e 0e 0c 48 89 84 24 d0 00 00 00 31 c0 e8 ea 3f 91 f9 48 89 e8 48 c1 e8 03 <42> 80 3c 20 00 0f 85 11 06 00 00 4c 8b a3 20 01 00 00 4a 8d 04 ad
RSP: 0018:ffffc90003487290 EFLAGS: 00010206
RAX: 0000000000000024 RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff888031924b00 RSI: ffffffff8879c1e6 RDI: 0000000000000000
RBP: 0000000000000120 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: ffffffff81d66229 R12: dffffc0000000000
R13: 0000000000000000 R14: ffff88802750c000 R15: ffffc900034879d0
FS:  00007fe51d1166c0(0000) GS:ffff8880d5ca2000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005599d4a2eb80 CR3: 0000000035c6b000 CR4: 0000000000352ef0
Call Trace:
 <TASK>
 wait_barrier drivers/md/raid1.c:1154 [inline]
 raid1_write_request drivers/md/raid1.c:1506 [inline]
 raid1_make_request+0x484/0x31a0 drivers/md/raid1.c:1696
 md_handle_request+0x824/0x1230 drivers/md/md.c:417
 md_submit_bio+0x1e9/0x350 drivers/md/md.c:458
 __submit_bio block/blk-core.c:681 [inline]
 __submit_bio+0x20e/0x3d0 block/blk-core.c:670
 __submit_bio_noacct block/blk-core.c:724 [inline]
 submit_bio_noacct_nocheck+0x736/0xc00 block/blk-core.c:792
 submit_bio_noacct+0xc93/0x2130 block/blk-core.c:925
 bio_await+0x1fa/0x240 block/bio.c:1580
 submit_bio_wait+0x19/0x60 block/bio.c:1598
 __blkdev_direct_IO_simple+0x4cb/0x8c0 block/fops.c:98
 blkdev_direct_IO+0xbee/0x2030 block/fops.c:429
 blkdev_direct_write block/fops.c:699 [inline]
 blkdev_write_iter+0x703/0xd30 block/fops.c:767
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x6af/0x1050 fs/read_write.c:687
 ksys_pwrite64 fs/read_write.c:794 [inline]
 __do_sys_pwrite64 fs/read_write.c:802 [inline]
 __se_sys_pwrite64 fs/read_write.c:799 [inline]
 __x64_sys_pwrite64+0x1eb/0x250 fs/read_write.c:799
 do_syscall_x64 arch/x86/entry/syscall_64.c:61 [inline]
 do_syscall_64+0x123/0x790 arch/x86/entry/syscall_64.c:84
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7fe51d1735de
Code: 08 0f 85 f5 e2 ff ff 49 89 fb 48 89 f0 48 89 d7 48 89 ce 4c 89 c2 4d 89 ca 4c 8b 44 24 08 4c 8b 4c 24 10 4c 89 5c 24 08 0f 05 <c3> 90 41 57 41 56 4d 89 c6 41 55 4d 89 cd 41 54 55 53 48 83 ec 08
RSP: 002b:00007fe51d116128 EFLAGS: 00000246 ORIG_RAX: 0000000000000012
RAX: ffffffffffffffda RBX: 00007fe51d1166c0 RCX: 00007fe51d1735de
RDX: 0000000000001000 RSI: 0000555588ed6000 RDI: 0000000000000005
RBP: 0000000000000021 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: ffffffffffffffd0
R13: 0000000000000002 R14: 00007ffdb60faaa0 R15: 00007ffdb60fab88
 </TASK>
Modules linked in:
---[ end trace 0000000000000000 ]---
RIP: 0010:_wait_barrier+0x8d/0x700 drivers/md/raid1.c:1066
Code: 08 00 00 00 f3 c7 40 0c f3 f3 f3 f3 65 48 8b 05 31 1e 0e 0c 48 89 84 24 d0 00 00 00 31 c0 e8 ea 3f 91 f9 48 89 e8 48 c1 e8 03 <42> 80 3c 20 00 0f 85 11 06 00 00 4c 8b a3 20 01 00 00 4a 8d 04 ad
RSP: 0018:ffffc90003487290 EFLAGS: 00010206
RAX: 0000000000000024 RBX: 0000000000000000 RCX: 0000000000000000
RDX: ffff888031924b00 RSI: ffffffff8879c1e6 RDI: 0000000000000000
RBP: 0000000000000120 R08: 0000000000000001 R09: 0000000000000000
R10: 0000000000000000 R11: ffffffff81d66229 R12: dffffc0000000000
R13: 0000000000000000 R14: ffff88802750c000 R15: ffffc900034879d0
FS:  00007fe51d1166c0(0000) GS:ffff8880d5ca2000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00005599d4a2eb80 CR3: 0000000035c6b000 CR4: 0000000000352ef0
----------------
Code disassembly (best guess):
   0:	08 00                	or     %al,(%rax)
   2:	00 00                	add    %al,(%rax)
   4:	f3 c7 40 0c f3 f3 f3 	xrelease movl $0xf3f3f3f3,0xc(%rax)
   b:	f3
   c:	65 48 8b 05 31 1e 0e 	mov    %gs:0xc0e1e31(%rip),%rax        # 0xc0e1e45
  13:	0c
  14:	48 89 84 24 d0 00 00 	mov    %rax,0xd0(%rsp)
  1b:	00
  1c:	31 c0                	xor    %eax,%eax
  1e:	e8 ea 3f 91 f9       	call   0xf991400d
  23:	48 89 e8             	mov    %rbp,%rax
  26:	48 c1 e8 03          	shr    $0x3,%rax
* 2a:	42 80 3c 20 00       	cmpb   $0x0,(%rax,%r12,1) <-- trapping instruction
  2f:	0f 85 11 06 00 00    	jne    0x646
  35:	4c 8b a3 20 01 00 00 	mov    0x120(%rbx),%r12
  3c:	4a                   	rex.WX
  3d:	8d                   	.byte 0x8d
  3e:	04 ad                	add    $0xad,%al

---
This report is generated by a bot. It may contain errors. See https://goo.gl/tpsmEJ for more information about syzbot. syzbot engineers can be reached at [email protected].

syzbot will keep track of this issue. See:
https://goo.gl/tpsmEJ#status for how to communicate with syzbot.

If the report is already addressed, let syzbot know by replying with:
#syz fix: exact-commit-title

If you want syzbot to run the reproducer, reply with:
#syz test: git://repo/address.git branch-or-commit-hash
If you attach or paste a git patch, syzbot will apply it before testing.

If you want to overwrite report's subsystems, reply with:
#syz set subsystems: new-subsystem
(See the list of subsystem names on the web dashboard)

If the report is a duplicate of another one, reply with:
#syz dup: exact-subject-of-another-report

If you want to undo deduplication, reply with:
#syz undup

#1 lore raw

From: Edward Aadm Davis <[email protected]>

#syz test: upstream 818bebeb63dd

drivers/md/raid1.c +24 -1
index f0646fb24371..8676b3bc463b 100644
@@ -1692,11 +1692,34 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
+		int err;
+
 		md_write_start(mddev, bio);
-		if (!raid1_write_request(mddev, bio, sectors))
+		err = mddev_lock(mddev);
+
+		if (err < 0) {
+			md_write_end(mddev);
+			goto done;
+		}
+
+		if (!mddev->private) {
+			mddev_unlock(mddev);
+			md_write_end(mddev);
+			goto done;
+		}
+
+		err = raid1_write_request(mddev, bio, sectors);
+		mddev_unlock(mddev);
+
+		if (!err)
 			md_write_end(mddev);
 	}
+out:
 	return true;
+done:
+	bio->bi_status = BLK_STS_OFFLINE;
+	bio_endio(bio);
+	goto out;
 }
 
 static void raid1_status(struct seq_file *seq, struct mddev *mddev)
author syzbot Tested-by
#2 lore raw
syzbot has tested the proposed patch and the reproducer did not trigger any issue:

Hello,

syzbot has tested the proposed patch and the reproducer did not trigger any issue:

Tested on:

commit:         818bebeb drm/xe: Don't hand out the flat CCS storage a..
git tree:       git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
console output: https://syzkaller.appspot.com/x/log.txt?x=163b7625580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=ccca94d2c01b9e78
dashboard link: https://syzkaller.appspot.com/bug?extid=3fe892ea5fc292e1353f
compiler:       gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44
patch:          https://syzkaller.appspot.com/x/patch.diff?x=10937625580000

Note: testing is done by a robot and is best-effort only.

#3 lore raw

PATCH 1/1 md/raid1: prevent a race between write and stop request

In reply to syzbot

A race condition exists between write and stop requests, leading to a null-ptr-deref in [1].

CPU0 CPU1
==== ====
md_submit_bio()
md_handle_request() do_md_stop()__md_stop()
raid1_make_request() __md_stop()
raid1_write_request() mddev->private = NULL
wait_barrier()
conf->nr_pending //trigger [1]

The intervention of a stop request causes inconsistencies in the state of mddev members (such as private and pers) while a write request is executing; the mddev lock is used to synchronize write and stop requests, thereby ensuring consistent mddev state throughout the execution of the write request.

Additionally, when a write operation reaches the RAID1 layer, if a stop request acquires the mddev lock first and releases mddev->private, the bio is terminated and the write request exits.

[1]

KASAN: null-ptr-deref in range [0x0000000000000120-0x0000000000000127]
RIP: 0010:_wait_barrier+0x8d/0x700 drivers/md/raid1.c:1066
Call Trace:
 wait_barrier drivers/md/raid1.c:1154 [inline]
 raid1_write_request drivers/md/raid1.c:1506 [inline]
 raid1_make_request+0x484/0x31a0 drivers/md/raid1.c:1696
 md_handle_request+0x824/0x1230 drivers/md/md.c:417
 md_submit_bio+0x1e9/0x350 drivers/md/md.c:458
 __submit_bio block/blk-core.c:681 [inline]
 __submit_bio+0x20e/0x3d0 block/blk-core.c:670
 __submit_bio_noacct block/blk-core.c:724 [inline]
 submit_bio_noacct_nocheck+0x736/0xc00 block/blk-core.c:792
 submit_bio_noacct+0xc93/0x2130 block/blk-core.c:925
 bio_await+0x1fa/0x240 block/bio.c:1580
 submit_bio_wait+0x19/0x60 block/bio.c:1598
 __blkdev_direct_IO_simple+0x4cb/0x8c0 block/fops.c:98
 blkdev_direct_IO+0xbee/0x2030 block/fops.c:429
 blkdev_direct_write block/fops.c:699 [inline]
 blkdev_write_iter+0x703/0xd30 block/fops.c:767
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x6af/0x1050 fs/read_write.c:687
---
 drivers/md/raid1.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)
drivers/md/raid1.c +27 -1
index f0646fb24371..3b9f1fa65e65 100644
@@ -1674,6 +1674,7 @@ static bool raid1_write_request(struct mddev *mddev, struct bio *bio,
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
+	blk_status_t status;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
 	    && md_flush_request(mddev, bio))
@@ -1692,11 +1693,36 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
+		int err;
+
 		md_write_start(mddev, bio);
-		if (!raid1_write_request(mddev, bio, sectors))
+		err = mddev_lock(mddev);
+
+		if (err < 0) {
+			md_write_end(mddev);
+			status = BLK_STS_IOERR;
+			goto done;
+		}
+
+		if (!mddev->private) {
+			mddev_unlock(mddev);
+			md_write_end(mddev);
+			status = BLK_STS_OFFLINE;
+			goto done;
+		}
+
+		err = raid1_write_request(mddev, bio, sectors);
+		mddev_unlock(mddev);
+
+		if (!err)
 			md_write_end(mddev);
 	}
+out:
 	return true;
+done:
+	bio->bi_status = status;
+	bio_endio(bio);
+	goto out;
 }
 
 static void raid1_status(struct seq_file *seq, struct mddev *mddev)
Signature · 1 line
2.43.0
#4 lore raw

PATCH v2 1/1 md/raid1: prevent a race between write and stop request

A race condition exists between write and stop requests, leading to a null-ptr-deref in [1].

CPU0 CPU1
==== ====
md_submit_bio()
md_handle_request() do_md_stop()
raid1_make_request() __md_stop()
raid1_write_request() mddev->private = NULL
wait_barrier()
conf->nr_pending //trigger [1]

The intervention of a stop request causes inconsistencies in the state of mddev members (such as private and pers) while a write request is executing; the mddev lock is used to synchronize write and stop requests, thereby ensuring consistent mddev state throughout the execution of the write request.

Additionally, when a write operation reaches the RAID1 layer, if a stop request acquires the mddev lock first and releases mddev->private, the bio is terminated and the write request exits.

[1]

KASAN: null-ptr-deref in range [0x0000000000000120-0x0000000000000127]
RIP: 0010:_wait_barrier+0x8d/0x700 drivers/md/raid1.c:1066
Call Trace:
 wait_barrier drivers/md/raid1.c:1154 [inline]
 raid1_write_request drivers/md/raid1.c:1506 [inline]
 raid1_make_request+0x484/0x31a0 drivers/md/raid1.c:1696
 md_handle_request+0x824/0x1230 drivers/md/md.c:417
 md_submit_bio+0x1e9/0x350 drivers/md/md.c:458
 __submit_bio block/blk-core.c:681 [inline]
 __submit_bio+0x20e/0x3d0 block/blk-core.c:670
 __submit_bio_noacct block/blk-core.c:724 [inline]
 submit_bio_noacct_nocheck+0x736/0xc00 block/blk-core.c:792
 submit_bio_noacct+0xc93/0x2130 block/blk-core.c:925
 bio_await+0x1fa/0x240 block/bio.c:1580
 submit_bio_wait+0x19/0x60 block/bio.c:1598
 __blkdev_direct_IO_simple+0x4cb/0x8c0 block/fops.c:98
 blkdev_direct_IO+0xbee/0x2030 block/fops.c:429
 blkdev_direct_write block/fops.c:699 [inline]
 blkdev_write_iter+0x703/0xd30 block/fops.c:767
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x6af/0x1050 fs/read_write.c:687

---
v1 -> v2: typo in comments

 drivers/md/raid1.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)
drivers/md/raid1.c +27 -1
index f0646fb24371..3b9f1fa65e65 100644
@@ -1674,6 +1674,7 @@ static bool raid1_write_request(struct mddev *mddev, struct bio *bio,
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
+	blk_status_t status;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
 	    && md_flush_request(mddev, bio))
@@ -1692,11 +1693,36 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
+		int err;
+
 		md_write_start(mddev, bio);
-		if (!raid1_write_request(mddev, bio, sectors))
+		err = mddev_lock(mddev);
+
+		if (err < 0) {
+			md_write_end(mddev);
+			status = BLK_STS_IOERR;
+			goto done;
+		}
+
+		if (!mddev->private) {
+			mddev_unlock(mddev);
+			md_write_end(mddev);
+			status = BLK_STS_OFFLINE;
+			goto done;
+		}
+
+		err = raid1_write_request(mddev, bio, sectors);
+		mddev_unlock(mddev);
+
+		if (!err)
 			md_write_end(mddev);
 	}
+out:
 	return true;
+done:
+	bio->bi_status = status;
+	bio_endio(bio);
+	goto out;
 }
 
 static void raid1_status(struct seq_file *seq, struct mddev *mddev)
Signature · 1 line
2.43.0
#5 lore raw

Re: [PATCH v2] md/raid1: prevent a race between write and stop request

Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:

Thank you for your contribution! Sashiko AI review found 4 potential issue(s) to consider:

New issues:
- [High] Acquiring a global configuration mutex (reconfig_mutex) in the I/O fast path serializes all RAID1 writes and violates non-blocking semantics.
- [High] Using an interruptible lock (mutex_lock_interruptible) in the block I/O submission path causes spurious block I/O errors (BLK_STS_IOERR) if the submitting process receives a signal.
- [High] Acquiring reconfig_mutex in the block I/O submission path (raid1_make_request) introduces a classic memory reclaim deadlock between in-flight IOs, kswapd, and array management.

Pre-existing issues:
- [Critical] The patch leaves the READ path completely unprotected against the concurrent do_md_stop Use-After-Free race that it was intended to fix for writes. --

commit d721c8b809d2e452fb1806262577569049151fb3
Author: Edward Adam Davis <[email protected]>

md/raid1: prevent a race between write and stop request

The commit aims to resolve a use-after-free triggered by a race condition between write requests and array stop requests. It does this by taking the array's reconfig_mutex inside the write I/O submission path.

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1694

Quoted 7 lines
drivers/md/raid1.c +0 -0
index f0646fb24371f..3b9f1fa65e654 100644
@@ -1692,11 +1693,36 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);

[Severity: Critical]
This is a pre-existing issue, but does this bypass leave the read path completely unprotected against the exact same race condition?

If an array stop operation clears mddev->private concurrently, wouldn't raid1_read_request() still dereference a freed or NULL conf pointer at:

wait_read_barrier(conf, bio->bi_iter.bi_sector);

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1699

Quoted 6 lines
drivers/md/raid1.c +3 -1
 	else {
+		int err;
+
 		md_write_start(mddev, bio);
-		if (!raid1_write_request(mddev, bio, sectors))
+		err = mddev_lock(mddev);

[Severity: High]
Does acquiring a global configuration mutex (reconfig_mutex) in the I/O fast path forcibly serialize all concurrent RAID1 writes and severely degrade block I/O performance?

Will taking a sleeping lock here also violate non-blocking semantics for asynchronous I/O if REQ_NOWAIT is set?

[Severity: High]
Can acquiring reconfig_mutex in the block I/O submission path introduce a memory reclaim deadlock?

If memory pressure forces kswapd to write out dirty pages to the RAID1 array, will those memory-reclaim writes attempt to acquire reconfig_mutex in raid1_make_request()?

Since configuration pathways like do_md_stop() hold reconfig_mutex while waiting for in-flight IOs to drain or performing memory allocations, wouldn't this create an ABBA deadlock that hangs the I/O subsystem?

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1703

Quoted 4 lines
drivers/md/raid1.c +4 -0
+
+		if (err < 0) {
+			md_write_end(mddev);
+			status = BLK_STS_IOERR;

[Severity: High]
Does this incorrectly convert a signal interruption into a hard I/O error?

Since mddev_lock() uses mutex_lock_interruptible() to acquire the lock, it returns -EINTR if the submitting process receives a signal.

Will converting this directly to BLK_STS_IOERR cause spurious block I/O errors for user space applications and potentially abort filesystem journals?

Quoted 2 lines
drivers/md/raid1.c +2 -0
+			goto done;
+		}
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
#6 lore raw

Re: [PATCH] md/raid1: prevent a race between write and stop request

In reply to Edward Adam Davis
Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:

Thank you for your contribution! Sashiko AI review found 5 potential issue(s) to consider:

New issues:
- [Critical] Using an interruptible mutex in the I/O path causes normal user-space signals to spuriously fail legitimate writes with I/O errors.
- [High] Global lock acquisition in the high-frequency block I/O fast path completely serializes all RAID1 write requests.
- [High] Acquiring reconfig_mutex in the block I/O submission path causes a fatal lock-inversion deadlock during memory reclaim.
- [High] Holding reconfig_mutex while sleeping in wait_blocked_rdev() indefinitely blocks the MD management thread from clearing the blocked state.

Pre-existing issues:
- [High] The patch only protects WRITE requests, leaving the READ path entirely unpatched and vulnerable to the original race condition causing a NULL pointer dereference. --

commit 75f3c8447cce610e8b9e2c583ca2b414877078df
Author: Edward Adam Davis <[email protected]>

md/raid1: prevent a race between write and stop request

This commit attempts to fix a race condition between write and stop requests that leads to a null pointer dereference. It introduces synchronization in the write path using the mddev lock to ensure the consistent state of mddev members during a write request.

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1694

Quoted 7 lines
drivers/md/raid1.c +0 -0
index f0646fb24371f..3b9f1fa65e654 100644
@@ -1692,11 +1693,36 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);

[Severity: High]
This is a pre-existing issue, but it appears the read path is still unprotected and vulnerable to the same race condition.

Since the patch only wraps the write path, if a concurrent do_md_stop() runs while a READ request is processed, raid1_read_request() will fetch mddev->private without protection. Could this result in the exact same null pointer dereference crash on reads when wait_read_barrier() is called?

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1699

Quoted 6 lines
drivers/md/raid1.c +3 -1
 	else {
+		int err;
+
 		md_write_start(mddev, bio);
-		if (!raid1_write_request(mddev, bio, sectors))
+		err = mddev_lock(mddev);

[Severity: High]
By acquiring mddev_lock() (which takes the global reconfig_mutex) in the hot I/O submission path, are all RAID1 write requests completely serialized? Taking a global reconfiguration mutex on every single write request could degrade array scalability and I/O concurrency.

[Severity: High]
Could acquiring reconfig_mutex in the block I/O submission path also cause a lock-inversion deadlock during memory reclaim?

If a thread holds reconfig_mutex (for example, during md_import_device()) and performs a GFP_KERNEL allocation, direct reclaim could write dirty pages to the RAID array. Since raid1_make_request() attempts to acquire reconfig_mutex via mddev_lock(), this might cause a direct self-deadlock.

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1705

Quoted 6 lines
drivers/md/raid1.c +6 -0
+
+		if (err < 0) {
+			md_write_end(mddev);
+			status = BLK_STS_IOERR;
+			goto done;
+		}

[Severity: Critical]
By translating a failed interruptible mutex lock into BLK_STS_IOERR, could normal user-space signals spuriously fail legitimate writes?

mddev_lock() uses mutex_lock_interruptible(), which returns -EINTR if a signal is pending. If a userspace process performing I/O receives a benign signal (like SIGALRM) while submitting a write, this path seems to fail the write with an I/O error instead of transparently retrying or blocking.

drivers/md/raid1.c static bool raid1_make_request(struct mddev *mddev, struct bio *bio) · line 1715

Quoted 10 lines
drivers/md/raid1.c +10 -0
+
+		if (!mddev->private) {
+			mddev_unlock(mddev);
+			md_write_end(mddev);
+			status = BLK_STS_OFFLINE;
+			goto done;
+		}
+
+		err = raid1_write_request(mddev, bio, sectors);
+		mddev_unlock(mddev);

[Severity: High]
Since reconfig_mutex is held across the entirety of raid1_write_request(), could this block the MD management thread indefinitely?

If a write request encounters a blocked device and sleeps in wait_blocked_rdev() inside raid1_write_request(), the I/O thread will be holding reconfig_mutex. The MD management thread (md_check_recovery()) needs to clear the blocked state, but it uses mddev_trylock() to acquire reconfig_mutex. Since the I/O thread holds the lock, the management thread will fail to acquire it, potentially leaving the I/O thread blocked forever.

Quoted 11 lines
drivers/md/raid1.c +7 -0
+
+		if (!err)
 			md_write_end(mddev);
 	}
+out:
 	return true;
+done:
+	bio->bi_status = status;
+	bio_endio(bio);
+	goto out;
 }
Signature · 1 line
Sashiko AI review · https://sashiko.dev/#/patchset/[email protected]?part=1
#7 lore raw

Re: [PATCH] md/raid1: prevent a race between write and stop request

In reply to Edward Adam Davis

Hi Edward,

Quoted 7 lines · Edward Adam Davis

A race condition exists between write and stop requests, leading to a null-ptr-deref in [1].

CPU0 CPU1
==== ====
md_submit_bio()
md_handle_request() do_md_stop()__md_stop()

do_md_stop() must never execute while the array device file is open. take a look if this rule is not meet.

Quoted 101 lines

raid1_make_request() __md_stop()
raid1_write_request() mddev->private = NULL
wait_barrier()
conf->nr_pending //trigger [1]

The intervention of a stop request causes inconsistencies in the state of mddev members (such as private and pers) while a write request is executing; the mddev lock is used to synchronize write and stop requests, thereby ensuring consistent mddev state throughout the execution of the write request.

Additionally, when a write operation reaches the RAID1 layer, if a stop request acquires the mddev lock first and releases mddev->private, the bio is terminated and the write request exits.

[1]

KASAN: null-ptr-deref in range [0x0000000000000120-0x0000000000000127]
RIP: 0010:_wait_barrier+0x8d/0x700 drivers/md/raid1.c:1066
Call Trace:
 wait_barrier drivers/md/raid1.c:1154 [inline]
 raid1_write_request drivers/md/raid1.c:1506 [inline]
 raid1_make_request+0x484/0x31a0 drivers/md/raid1.c:1696
 md_handle_request+0x824/0x1230 drivers/md/md.c:417
 md_submit_bio+0x1e9/0x350 drivers/md/md.c:458
 __submit_bio block/blk-core.c:681 [inline]
 __submit_bio+0x20e/0x3d0 block/blk-core.c:670
 __submit_bio_noacct block/blk-core.c:724 [inline]
 submit_bio_noacct_nocheck+0x736/0xc00 block/blk-core.c:792
 submit_bio_noacct+0xc93/0x2130 block/blk-core.c:925
 bio_await+0x1fa/0x240 block/bio.c:1580
 submit_bio_wait+0x19/0x60 block/bio.c:1598
 __blkdev_direct_IO_simple+0x4cb/0x8c0 block/fops.c:98
 blkdev_direct_IO+0xbee/0x2030 block/fops.c:429
 blkdev_direct_write block/fops.c:699 [inline]
 blkdev_write_iter+0x703/0xd30 block/fops.c:767
 new_sync_write fs/read_write.c:595 [inline]
 vfs_write+0x6af/0x1050 fs/read_write.c:687
---
 drivers/md/raid1.c | 28 +++++++++++++++++++++++++++-
 1 file changed, 27 insertions(+), 1 deletion(-)
drivers/md/raid1.c +27 -1
index f0646fb24371..3b9f1fa65e65 100644
@@ -1674,6 +1674,7 @@ static bool raid1_write_request(struct mddev *mddev, struct bio *bio,
 static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 {
 	sector_t sectors;
+	blk_status_t status;
 
 	if (unlikely(bio->bi_opf & REQ_PREFLUSH)
 	    && md_flush_request(mddev, bio))
@@ -1692,11 +1693,36 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
 	if (bio_data_dir(bio) == READ)
 		raid1_read_request(mddev, bio, sectors, NULL);
 	else {
+		int err;
+
 		md_write_start(mddev, bio);
-		if (!raid1_write_request(mddev, bio, sectors))
+		err = mddev_lock(mddev);
+
+		if (err < 0) {
+			md_write_end(mddev);
+			status = BLK_STS_IOERR;
+			goto done;
+		}
+
+		if (!mddev->private) {
+			mddev_unlock(mddev);
+			md_write_end(mddev);
+			status = BLK_STS_OFFLINE;
+			goto done;
+		}
+
+		err = raid1_write_request(mddev, bio, sectors);
+		mddev_unlock(mddev);
+
+		if (!err)
 			md_write_end(mddev);
 	}
+out:
 	return true;
+done:
+	bio->bi_status = status;
+	bio_endio(bio);
+	goto out;
 }
 
 static void raid1_status(struct seq_file *seq, struct mddev *mddev)
Signature · 1 line
2.43.0
Signature · 2 lines
Best Regards,
Abd-Alrhman