Re: [PATCH] block: make sure last_lookup set as NULL after part deleted

[Yufen Yu <yuyufen@huawei.com>]

Hi, Ming

On 2020/1/3 23:16, Ming Lei wrote:
> Hello Yufen,
> 
> OK, we still can move clearing .last_lookup into __delete_partition(),
> at that time all IO path can observe the partition percpu-refcount killed.
> 
> Also the rcu work fn is run after one RCU grace period, at that time,
> the NULL .last_lookup becomes visible in all IO path too.
> 
> diff --git a/block/blk-core.c b/block/blk-core.c
> index 089e890ab208..79599f5fd5b7 100644
> --- a/block/blk-core.c
> +++ b/block/blk-core.c
> @@ -1365,18 +1365,6 @@ void blk_account_io_start(struct request *rq, bool new_io)
>   		part_stat_inc(part, merges[rw]);
>   	} else {
>   		part = disk_map_sector_rcu(rq->rq_disk, blk_rq_pos(rq));
> -		if (!hd_struct_try_get(part)) {
> -			/*
> -			 * The partition is already being removed,
> -			 * the request will be accounted on the disk only
> -			 *
> -			 * We take a reference on disk->part0 although that
> -			 * partition will never be deleted, so we can treat
> -			 * it as any other partition.
> -			 */
> -			part = &rq->rq_disk->part0;
> -			hd_struct_get(part);
> -		}
>   		part_inc_in_flight(rq->q, part, rw);
>   		rq->part = part;
>   	}
> diff --git a/block/genhd.c b/block/genhd.c
> index ff6268970ddc..e3dec90b1f43 100644
> --- a/block/genhd.c
> +++ b/block/genhd.c
> @@ -286,17 +286,21 @@ struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
>   	ptbl = rcu_dereference(disk->part_tbl);
>   
>   	part = rcu_dereference(ptbl->last_lookup);
> -	if (part && sector_in_part(part, sector))
> +	if (part && sector_in_part(part, sector) && hd_struct_try_get(part))
>   		return part;
>   
>   	for (i = 1; i < ptbl->len; i++) {
>   		part = rcu_dereference(ptbl->part[i]);
>   
>   		if (part && sector_in_part(part, sector)) {
> +                       if (!hd_struct_try_get(part))
> +                               goto exit;
>   			rcu_assign_pointer(ptbl->last_lookup, part);
>   			return part;
>   		}
>   	}
> + exit:
> +	hd_struct_get(&disk->part0);
>   	return &disk->part0;
>   }
>   EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
> diff --git a/block/partition-generic.c b/block/partition-generic.c
> index 1d20c9cf213f..1739f750dbf2 100644
> --- a/block/partition-generic.c
> +++ b/block/partition-generic.c
> @@ -262,6 +262,12 @@ static void delete_partition_work_fn(struct work_struct *work)
>   void __delete_partition(struct percpu_ref *ref)
>   {
>   	struct hd_struct *part = container_of(ref, struct hd_struct, ref);
> +	struct disk_part_tbl *ptbl =
> +		rcu_dereference_protected(part->disk->part_tbl, 1);
> +
> +	rcu_assign_pointer(ptbl->last_lookup, NULL);
> +	put_device(disk_to_dev(part->disk));
> +
>   	INIT_RCU_WORK(&part->rcu_work, delete_partition_work_fn);
>   	queue_rcu_work(system_wq, &part->rcu_work);
>   }
> @@ -283,8 +289,9 @@ void delete_partition(struct gendisk *disk, int partno)
>   	if (!part)
>   		return;
>   
> +	get_device(disk_to_dev(disk));
>   	rcu_assign_pointer(ptbl->part[partno], NULL);
> -	rcu_assign_pointer(ptbl->last_lookup, NULL);
> +
>   	kobject_put(part->holder_dir);
>   	device_del(part_to_dev(part));
>   
> @@ -349,6 +356,7 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
>   	p->nr_sects = len;
>   	p->partno = partno;
>   	p->policy = get_disk_ro(disk);
> +	p->disk = disk;
>   
>   	if (info) {
>   		struct partition_meta_info *pinfo = alloc_part_info(disk);
> diff --git a/include/linux/genhd.h b/include/linux/genhd.h
> index 8bb63027e4d6..66660ec5e8ee 100644
> --- a/include/linux/genhd.h
> +++ b/include/linux/genhd.h
> @@ -129,6 +129,7 @@ struct hd_struct {
>   #else
>   	struct disk_stats dkstats;
>   #endif
> +	struct gendisk *disk;
>   	struct percpu_ref ref;
>   	struct rcu_work rcu_work;
>   };


IMO, this change can solve the problem. But, __delete_partition will
depend on the implementation of disk_release(). If disk .release modify
as blocked in the future, then __delete_partition will also be blocked,
which is not expected in rcu callback function.

We may cache index of part[] instead of part[i] itself to fix the use-after-free bug.
https://patchwork.kernel.org/patch/11318767/

Thanks,
Yufen