Re: [PATCH AUTOSEL 6.9 02/15] md: Fix overflow in is_mddev_idle

[Yu Kuai <yukuai3@xxxxxxxxxx>]

Hi,

在 2024/05/26 17:41, Sasha Levin 写道:
> From: Li Nan <linan122@xxxxxxxxxx>
>
> [ Upstream commit 3f9f231236ce7e48780d8a4f1f8cb9fae2df1e4e ]
>
> UBSAN reports this problem:
>
>    UBSAN: Undefined behaviour in drivers/md/md.c:8175:15
>    signed integer overflow:
>    -2147483291 - 2072033152 cannot be represented in type 'int'
>    Call trace:
>     dump_backtrace+0x0/0x310
>     show_stack+0x28/0x38
>     dump_stack+0xec/0x15c
>     ubsan_epilogue+0x18/0x84
>     handle_overflow+0x14c/0x19c
>     __ubsan_handle_sub_overflow+0x34/0x44
>     is_mddev_idle+0x338/0x3d8
>     md_do_sync+0x1bb8/0x1cf8
>     md_thread+0x220/0x288
>     kthread+0x1d8/0x1e0
>     ret_from_fork+0x10/0x18
>
> 'curr_events' will overflow when stat accum or 'sync_io' is greater than
> INT_MAX.
>
> Fix it by changing sync_io, last_events and curr_events to 64bit.
>
> Signed-off-by: Li Nan <linan122@xxxxxxxxxx>
> Reviewed-by: Yu Kuai <yukuai3@xxxxxxxxxx>
> Link: https://lore.kernel.org/r/20240117031946.2324519-2-linan666@xxxxxxxxxxxxxxx
> Signed-off-by: Song Liu <song@xxxxxxxxxx>
> Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>

Hi, please notice that this patch doesn't fix real issue expect for
the ubsan warning, and this patch is reverted:
> ---
>   drivers/md/md.c        | 7 ++++---
>   drivers/md/md.h        | 4 ++--
>   include/linux/blkdev.h | 2 +-
>   3 files changed, 7 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/md/md.c b/drivers/md/md.c
> index e575e74aabf5e..c88b50a4be82f 100644
> --- a/drivers/md/md.c
> +++ b/drivers/md/md.c
> @@ -8576,14 +8576,15 @@ static int is_mddev_idle(struct mddev *mddev, int init)
>   {
>   	struct md_rdev *rdev;
>   	int idle;
> -	int curr_events;
> +	long long curr_events;
>   
>   	idle = 1;
>   	rcu_read_lock();
>   	rdev_for_each_rcu(rdev, mddev) {
>   		struct gendisk *disk = rdev->bdev->bd_disk;
> -		curr_events = (int)part_stat_read_accum(disk->part0, sectors) -
> -			      atomic_read(&disk->sync_io);
> +		curr_events =
> +			(long long)part_stat_read_accum(disk->part0, sectors) -
> +			atomic64_read(&disk->sync_io);
>   		/* sync IO will cause sync_io to increase before the disk_stats
>   		 * as sync_io is counted when a request starts, and
>   		 * disk_stats is counted when it completes.
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index 097d9dbd69b83..d0db98c0d33be 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -51,7 +51,7 @@ struct md_rdev {
>   
>   	sector_t sectors;		/* Device size (in 512bytes sectors) */
>   	struct mddev *mddev;		/* RAID array if running */
> -	int last_events;		/* IO event timestamp */
> +	long long last_events;		/* IO event timestamp */
>   
>   	/*
>   	 * If meta_bdev is non-NULL, it means that a separate device is
> @@ -621,7 +621,7 @@ extern void mddev_unlock(struct mddev *mddev);
>   
>   static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
>   {
> -	atomic_add(nr_sectors, &bdev->bd_disk->sync_io);
> +	atomic64_add(nr_sectors, &bdev->bd_disk->sync_io);
>   }
>   
>   static inline void md_sync_acct_bio(struct bio *bio, unsigned long nr_sectors)
> diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
> index 69e7da33ca49a..f10fb01a629fb 100644
> --- a/include/linux/blkdev.h
> +++ b/include/linux/blkdev.h
> @@ -174,7 +174,7 @@ struct gendisk {
>   	struct list_head slave_bdevs;
>   #endif
>   	struct timer_rand_state *random;
> -	atomic_t sync_io;		/* RAID */
> +	atomic64_t sync_io;		/* RAID */
>   	struct disk_events *ev;
>   
>   #ifdef CONFIG_BLK_DEV_ZONED