[syzbot] [kernel?] general protection fault in __cpuhp_state_remove_instance

[syzbot] [kernel?] general protection fault in __cpuhp_state_remove_instance

[syzbot]

Hello,

syzbot found the following issue on:

HEAD commit:    330517c63aa9 Merge tag 'char-misc-7.4-rc1' of git://git.ke..
git tree:       upstream
console output: https://syzkaller.appspot.com/x/log.txt?x=13561459580000
kernel config:  https://syzkaller.appspot.com/x/.config?x=b03c85f3988bfcd5
dashboard link: https://syzkaller.appspot.com/bug?extid=08318698e045b4b85f51
compiler:       gcc (Debian 14.2.0-19) 14.2.0, GNU ld (GNU Binutils for Debian) 2.44
syz repro:      https://syzkaller.appspot.com/x/repro.syz?x=1062d695580000
C reproducer:   https://syzkaller.appspot.com/x/repro.c?x=15236fcd580000

Downloadable assets:
disk image (non-bootable): https://storage.googleapis.com/syzbot-assets/d900f083ada3/non_bootable_disk-330517c6.raw.xz
vmlinux: https://storage.googleapis.com/syzbot-assets/ecb230491807/vmlinux-330517c6.xz
kernel image: https://storage.googleapis.com/syzbot-assets/ace3132a7acc/bzImage-330517c6.xz

IMPORTANT: if you fix the issue, please add the following tag to the commit:
Reported-by: syzbot+08318698e045b4b85f51@syzkaller.appspotmail.com

md: array md0 already has disks!
md/raid:md0: not clean -- starting background reconstruction
raid456_cpu_up_prepare: failed memory allocation for cpu0
Oops: general protection fault, probably for non-canonical address 0xdffffc0000000000: 0000 [#1] SMP KASAN NOPTI
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
CPU: 1 UID: 0 PID: 6024 Comm: syz.0.22 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:__hlist_del include/linux/list.h:1045 [inline]
RIP: 0010:hlist_del include/linux/list.h:1059 [inline]
RIP: 0010:__cpuhp_state_remove_instance+0x227/0x5f0 kernel/cpu.c:2573
Code: 00 fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 78 03 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 65 08 4c 89 e2 48 c1 ea 03 <80> 3c 02 00 0f 85 4c 03 00 00 49 89 1c 24 48 85 db 74 28 e8 51 1f
RSP: 0018:ffffc90003c7f890 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff81c9fb54 RDI: ffff8880287a8440
RBP: ffff8880287a8438 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffffffffffffffff R14: 0000000000000004 R15: 0000000000000003
FS:  00007fcd283f56c0(0000) GS:ffff8880d45b4000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000001b30324228 CR3: 0000000037605000 CR4: 0000000000352ef0
Call Trace:
 <TASK>
 cpuhp_state_remove_instance include/linux/cpuhotplug.h:480 [inline]
 raid5_free_percpu drivers/md/raid5.c:7541 [inline]
 free_conf+0x238/0x710 drivers/md/raid5.c:7554
 setup_conf+0xd80/0x2a20 drivers/md/raid5.c:7885
 raid5_run+0x1260/0x1670 drivers/md/raid5.c:8129
 md_run+0xc2f/0x2510 drivers/md/md.c:6779
 do_md_run+0x36/0x660 drivers/md/md.c:6880
 md_ioctl+0x27e6/0x36c0 drivers/md/md.c:8515
 blkdev_ioctl+0x5ad/0x6f0 block/ioctl.c:798
 vfs_ioctl fs/ioctl.c:51 [inline]
 __do_sys_ioctl fs/ioctl.c:597 [inline]
 __se_sys_ioctl fs/ioctl.c:583 [inline]
 __x64_sys_ioctl+0x18e/0x210 fs/ioctl.c:583
 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: 0033:0x7fcd2759f559
Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007fcd283f5028 EFLAGS: 00000246 ORIG_RAX: 0000000000000010
RAX: ffffffffffffffda RBX: 00007fcd27825fa0 RCX: 00007fcd2759f559
RDX: 0000000000000000 RSI: 00000000400c0930 RDI: 0000000000000003
RBP: 00007fcd27636b20 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 00007fcd27826038 R14: 00007fcd27825fa0 R15: 00007ffd1d32f288
 </TASK>
Modules linked in:
---[ end trace 0000000000000000 ]---
RIP: 0010:__hlist_del include/linux/list.h:1045 [inline]
RIP: 0010:hlist_del include/linux/list.h:1059 [inline]
RIP: 0010:__cpuhp_state_remove_instance+0x227/0x5f0 kernel/cpu.c:2573
Code: 00 fc ff df 48 89 fa 48 c1 ea 03 80 3c 02 00 0f 85 78 03 00 00 48 b8 00 00 00 00 00 fc ff df 4c 8b 65 08 4c 89 e2 48 c1 ea 03 <80> 3c 02 00 0f 85 4c 03 00 00 49 89 1c 24 48 85 db 74 28 e8 51 1f
RSP: 0018:ffffc90003c7f890 EFLAGS: 00010246
RAX: dffffc0000000000 RBX: 0000000000000000 RCX: 0000000000000000
RDX: 0000000000000000 RSI: ffffffff81c9fb54 RDI: ffff8880287a8440
RBP: ffff8880287a8438 R08: 0000000000000007 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000
R13: ffffffffffffffff R14: 0000000000000004 R15: 0000000000000003
FS:  00007fcd283f56c0(0000) GS:ffff8880d44b4000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 00007fcd283d3ff8 CR3: 0000000037605000 CR4: 0000000000352ef0
----------------
Code disassembly (best guess):
   0:	00 fc                	add    %bh,%ah
   2:	ff                   	lcall  (bad)
   3:	df 48 89             	fisttps -0x77(%rax)
   6:	fa                   	cli
   7:	48 c1 ea 03          	shr    $0x3,%rdx
   b:	80 3c 02 00          	cmpb   $0x0,(%rdx,%rax,1)
   f:	0f 85 78 03 00 00    	jne    0x38d
  15:	48 b8 00 00 00 00 00 	movabs $0xdffffc0000000000,%rax
  1c:	fc ff df
  1f:	4c 8b 65 08          	mov    0x8(%rbp),%r12
  23:	4c 89 e2             	mov    %r12,%rdx
  26:	48 c1 ea 03          	shr    $0x3,%rdx
* 2a:	80 3c 02 00          	cmpb   $0x0,(%rdx,%rax,1) <-- trapping instruction
  2e:	0f 85 4c 03 00 00    	jne    0x380
  34:	49 89 1c 24          	mov    %rbx,(%r12)
  38:	48 85 db             	test   %rbx,%rbx
  3b:	74 28                	je     0x65
  3d:	e8                   	.byte 0xe8
  3e:	51                   	push   %rcx
  3f:	1f                   	(bad)


---
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 syzkaller@googlegroups.com.

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

[PATCH] md/raid5: Cancel remove instance if adding it fails

[Edward Adam Davis]

The failure of raid456_cpu_up_prepare() to allocate memory causes
cpuhp_state_add_instance() to fail; consequently, the corresponding
instance is not initialized, potentially hitting [1].

Additionally, there is another null-ptr-deref issue: conf->mddev is
assigned too late, meaning that any error-handling exit occurring before
this assignment, which jumps to the abort label, potentially hitting [2].

[1]
KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
Call Trace:
 cpuhp_state_remove_instance include/linux/cpuhotplug.h:480 [inline]
 raid5_free_percpu drivers/md/raid5.c:7541 [inline]
 free_conf+0x238/0x710 drivers/md/raid5.c:7554
 setup_conf+0xd80/0x2a20 drivers/md/raid5.c:7885
 raid5_run+0x1260/0x1670 drivers/md/raid5.c:8129

[2]
BUG: KASAN: null-ptr-deref in free_conf+0xfd/0x7e0
Read of size 8 at addr 0000000000000028 by task rp0/9459
Call Trace:
 free_conf+0xfd/0x7e0
 setup_conf.cold+0x6e/0x4a1
 raid5_run+0x1260/0x1670

Add a check before removing an instance, if the instance was not successfully
added, skip the removal process. Move the assignment of conf->mddev after the
memory allocation for conf.

Fixes: 29c6d1bbd7a2 ("md/raid5: Convert to hotplug state machine")
Reported-by: syzbot+08318698e045b4b85f51@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=08318698e045b4b85f51
Signed-off-by: Edward Adam Davis <eadavis@sina.com>
---
 drivers/md/raid5.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index b91545ce090d..e1f9ec8f25be 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -7538,7 +7538,8 @@ static void raid5_free_percpu(struct r5conf *conf)
 	if (!conf->percpu)
 		return;
 
-	cpuhp_state_remove_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
+	if (!hlist_unhashed(&conf->node))
+		cpuhp_state_remove_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
 	free_percpu(conf->percpu);
 }
 
@@ -7675,6 +7676,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	if (conf == NULL)
 		goto abort;
 
+	conf->mddev = mddev;
 #if PAGE_SIZE != DEFAULT_STRIPE_SIZE
 	conf->stripe_size = DEFAULT_STRIPE_SIZE;
 	conf->stripe_shift = ilog2(DEFAULT_STRIPE_SIZE) - 9;
@@ -7743,7 +7745,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
 	ret = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
 	if (ret)
 		goto abort;
-	conf->mddev = mddev;
 
 	ret = -ENOMEM;
 	conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL);
-- 
2.43.0

Re: [PATCH] md/raid5: Cancel remove instance if adding it fails

[yu kuai]

Hi,

在 2026/10/30 18:56, Edward Adam Davis 写道:
> The failure of raid456_cpu_up_prepare() to allocate memory causes
> cpuhp_state_add_instance() to fail; consequently, the corresponding
> instance is not initialized, potentially hitting [1].
>
> Additionally, there is another null-ptr-deref issue: conf->mddev is
> assigned too late, meaning that any error-handling exit occurring before
> this assignment, which jumps to the abort label, potentially hitting [2].
>
> [1]
> KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007]
> Call Trace:
>   cpuhp_state_remove_instance include/linux/cpuhotplug.h:480 [inline]
>   raid5_free_percpu drivers/md/raid5.c:7541 [inline]
>   free_conf+0x238/0x710 drivers/md/raid5.c:7554
>   setup_conf+0xd80/0x2a20 drivers/md/raid5.c:7885
>   raid5_run+0x1260/0x1670 drivers/md/raid5.c:8129
>
> [2]
> BUG: KASAN: null-ptr-deref in free_conf+0xfd/0x7e0
> Read of size 8 at addr 0000000000000028 by task rp0/9459
> Call Trace:
>   free_conf+0xfd/0x7e0
>   setup_conf.cold+0x6e/0x4a1
>   raid5_run+0x1260/0x1670
>
> Add a check before removing an instance, if the instance was not successfully
> added, skip the removal process. Move the assignment of conf->mddev after the
> memory allocation for conf.
>
> Fixes: 29c6d1bbd7a2 ("md/raid5: Convert to hotplug state machine")
> Reported-by: syzbot+08318698e045b4b85f51@syzkaller.appspotmail.com
> Closes: https://syzkaller.appspot.com/bug?extid=08318698e045b4b85f51
> Signed-off-by: Edward Adam Davis <eadavis@sina.com>
> ---
>   drivers/md/raid5.c | 5 +++--
>   1 file changed, 3 insertions(+), 2 deletions(-)

Looks like this problem is already fixed

https://patch.msgid.link/20260827080341.112296-2-ghuicao@163.com
https://patch.msgid.link/20260915081731.122933-1-chengzhihao1@huawei.com

>
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index b91545ce090d..e1f9ec8f25be 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -7538,7 +7538,8 @@ static void raid5_free_percpu(struct r5conf *conf)
>   	if (!conf->percpu)
>   		return;
>   
> -	cpuhp_state_remove_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
> +	if (!hlist_unhashed(&conf->node))
> +		cpuhp_state_remove_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
>   	free_percpu(conf->percpu);
>   }
>   
> @@ -7675,6 +7676,7 @@ static struct r5conf *setup_conf(struct mddev *mddev)
>   	if (conf == NULL)
>   		goto abort;
>   
> +	conf->mddev = mddev;
>   #if PAGE_SIZE != DEFAULT_STRIPE_SIZE
>   	conf->stripe_size = DEFAULT_STRIPE_SIZE;
>   	conf->stripe_shift = ilog2(DEFAULT_STRIPE_SIZE) - 9;
> @@ -7743,7 +7745,6 @@ static struct r5conf *setup_conf(struct mddev *mddev)
>   	ret = bioset_init(&conf->bio_split, BIO_POOL_SIZE, 0, 0);
>   	if (ret)
>   		goto abort;
> -	conf->mddev = mddev;
>   
>   	ret = -ENOMEM;
>   	conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL);

-- 
Thanks,
Kuai