From 433279beba1d4872da10b7b60a539e0cb828b32b Mon Sep 17 00:00:00 2001 From: Yu Kuai Date: Tue, 28 Mar 2023 17:44:00 +0800 Subject: [PATCH] md: fix regression for null-ptr-deference in __md_stop() Commit 3e453522593d ("md: Free resources in __md_stop") tried to fix null-ptr-deference for 'active_io' by moving percpu_ref_exit() to __md_stop(), however, the commit also moving 'writes_pending' to __md_stop(), and this will cause mdadm tests broken: BUG: kernel NULL pointer dereference, address: 0000000000000038 Oops: 0000 [#1] PREEMPT SMP CPU: 15 PID: 17830 Comm: mdadm Not tainted 6.3.0-rc3-next-20230324-00009-g520d37 RIP: 0010:free_percpu+0x465/0x670 Call Trace: __percpu_ref_exit+0x48/0x70 percpu_ref_exit+0x1a/0x90 __md_stop+0xe9/0x170 do_md_stop+0x1e1/0x7b0 md_ioctl+0x90c/0x1aa0 blkdev_ioctl+0x19b/0x400 vfs_ioctl+0x20/0x50 __x64_sys_ioctl+0xba/0xe0 do_syscall_64+0x6c/0xe0 entry_SYSCALL_64_after_hwframe+0x63/0xcd And the problem can be reporduced 100% by following test: mdadm -CR /dev/md0 -l1 -n1 /dev/sda --force echo inactive > /sys/block/md0/md/array_state echo read-auto > /sys/block/md0/md/array_state echo inactive > /sys/block/md0/md/array_state Root cause: // start raid raid1_run mddev_init_writes_pending percpu_ref_init // inactive raid array_state_store do_md_stop __md_stop percpu_ref_exit // start raid again array_state_store do_md_run raid1_run mddev_init_writes_pending if (mddev->writes_pending.percpu_count_ptr) // won't reinit // inactive raid again ... percpu_ref_exit -> null-ptr-deference Before the commit, 'writes_pending' is exited when mddev is freed, and it's safe to restart raid because mddev_init_writes_pending() already make sure that 'writes_pending' will only be initialized once. Fix the prblem by moving 'writes_pending' back, it's a litter hard to find the relationship between alloc memory and free memory, however, code changes is much less and we lived with this for a long time already. Fixes: 3e453522593d ("md: Free resources in __md_stop") Signed-off-by: Yu Kuai Reviewed-by: Xiao Ni Signed-off-by: Song Liu Link: https://lore.kernel.org/r/20230328094400.1448955-1-yukuai1@huaweicloud.com --- drivers/md/md.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/md/md.c b/drivers/md/md.c index 39e49e5d7182..13321dbb5fbc 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -6260,7 +6260,6 @@ static void __md_stop(struct mddev *mddev) module_put(pers->owner); clear_bit(MD_RECOVERY_FROZEN, &mddev->recovery); - percpu_ref_exit(&mddev->writes_pending); percpu_ref_exit(&mddev->active_io); bioset_exit(&mddev->bio_set); bioset_exit(&mddev->sync_set); @@ -6273,6 +6272,7 @@ void md_stop(struct mddev *mddev) */ __md_stop_writes(mddev); __md_stop(mddev); + percpu_ref_exit(&mddev->writes_pending); } EXPORT_SYMBOL_GPL(md_stop); @@ -7843,6 +7843,7 @@ static void md_free_disk(struct gendisk *disk) { struct mddev *mddev = disk->private_data; + percpu_ref_exit(&mddev->writes_pending); mddev_free(mddev); }