Re: [PATCH v4 5/7] btrfs: don't hold dev_replace rwsem over whole of btrfs_map_block

[Qu Wenruo <quwenruo.btrfs@gmx.com>]

在 2024/7/6 00:43, Johannes Thumshirn 写道:
> From: Johannes Thumshirn <johannes.thumshirn@wdc.com>
>
> Don't hold the dev_replace rwsem for the entirety of btrfs_map_block().
>
> It is only needed to protect
> a) calls to find_live_mirror() and
> b) calling into handle_ops_on_dev_replace().
>
> But there is no need to hold the rwsem for any kind of set_io_stripe()
> calls.
>
> So relax taking the dev_replace rwsem to only protect both cases and check
> if the device replace status has changed in the meantime, for which we have
> to re-do the find_live_mirror() calls.
>
> This fixes a deadlock on raid-stripe-tree where device replace performs a
> scrub operation, which in turn calls into btrfs_map_block() to find the
> physical location of the block.
>
> Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
> Reviewed-by: Josef Bacik <josef@toxicpanda.com>

Reviewed-by: Qu Wenruo <wqu@suse.com>

Thanks,
Qu
> ---
>   fs/btrfs/volumes.c | 28 +++++++++++++++++-----------
>   1 file changed, 17 insertions(+), 11 deletions(-)
>
> diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
> index fcedc43ef291..4209419244a1 100644
> --- a/fs/btrfs/volumes.c
> +++ b/fs/btrfs/volumes.c
> @@ -6650,14 +6650,9 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
>   	max_len = btrfs_max_io_len(map, map_offset, &io_geom);
>   	*length = min_t(u64, map->chunk_len - map_offset, max_len);
>
> +again:
>   	down_read(&dev_replace->rwsem);
>   	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(dev_replace);
> -	/*
> -	 * Hold the semaphore for read during the whole operation, write is
> -	 * requested at commit time but must wait.
> -	 */
> -	if (!dev_replace_is_ongoing)
> -		up_read(&dev_replace->rwsem);
>
>   	switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
>   	case BTRFS_BLOCK_GROUP_RAID0:
> @@ -6695,6 +6690,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
>   			   "stripe index math went horribly wrong, got stripe_index=%u, num_stripes=%u",
>   			   io_geom.stripe_index, map->num_stripes);
>   		ret = -EINVAL;
> +		up_read(&dev_replace->rwsem);
>   		goto out;
>   	}
>
> @@ -6710,6 +6706,8 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
>   		 */
>   		num_alloc_stripes += 2;
>
> +	up_read(&dev_replace->rwsem);
> +
>   	/*
>   	 * If this I/O maps to a single device, try to return the device and
>   	 * physical block information on the stack instead of allocating an
> @@ -6782,6 +6780,18 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
>   		goto out;
>   	}
>
> +	/*
> +	 * Check if something changed the dev_replace state since
> +	 * we've checked it for the last time and if redo the whole
> +	 * mapping operation.
> +	 */
> +	down_read(&dev_replace->rwsem);
> +	if (dev_replace_is_ongoing !=
> +	    btrfs_dev_replace_is_ongoing(dev_replace)) {
> +		up_read(&dev_replace->rwsem);
> +		goto again;
> +	}
> +
>   	if (op != BTRFS_MAP_READ)
>   		io_geom.max_errors = btrfs_chunk_max_errors(map);
>
> @@ -6789,6 +6799,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
>   	    op != BTRFS_MAP_READ) {
>   		handle_ops_on_dev_replace(bioc, dev_replace, logical, &io_geom);
>   	}
> +	up_read(&dev_replace->rwsem);
>
>   	*bioc_ret = bioc;
>   	bioc->num_stripes = io_geom.num_stripes;
> @@ -6796,11 +6807,6 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
>   	bioc->mirror_num = io_geom.mirror_num;
>
>   out:
> -	if (dev_replace_is_ongoing) {
> -		lockdep_assert_held(&dev_replace->rwsem);
> -		/* Unlock and let waiting writers proceed */
> -		up_read(&dev_replace->rwsem);
> -	}
>   	btrfs_free_chunk_map(map);
>   	return ret;
>   }
>