Re: [PATCH RFC] btrfs: self heal from SB fail

["Austin S. Hemmelgarn" <ahferroin7@gmail.com>]

On 2017-12-08 02:57, Anand Jain wrote:
> -EXPERIMENTAL-
> As of now when primary SB fails we won't self heal and would fail mount,
> this is an experimental patch which thinks why not go and read backup
> copy.
I like the concept, and actually think this should be default behavior 
on a filesystem that's already mounted (we fix other errors, why not 
SB's), but I don't think it should be default behavior at mount time for 
the reasons Qu has outlined (picking up old BTRFS SB's after 
reformatting is bad).  However, I do think it's useful to be able to ask 
for this behavior on mount, so that you don't need to fight with the 
programs to get a filesystem to mount when the first SB is missing 
(perhaps add a 'usebackupsb' option to mirror 'usebackuproot'?).
> 
> Signed-off-by: Anand Jain <anand.jain@oracle.com>
> ---
>   fs/btrfs/disk-io.c |  8 +++++++-
>   fs/btrfs/volumes.c | 10 +++++++---
>   2 files changed, 14 insertions(+), 4 deletions(-)
> 
> diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> index 9b20c1f3563b..a791b8dfe8a8 100644
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -3190,7 +3190,7 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
>   	 * So, we need to add a special mount option to scan for
>   	 * later supers, using BTRFS_SUPER_MIRROR_MAX instead
>   	 */
> -	for (i = 0; i < 1; i++) {
> +	for (i = 0; i < BTRFS_SUPER_MIRROR_MAX; i++) {
>   		ret = btrfs_read_dev_one_super(bdev, i, &bh);
>   		if (ret)
>   			continue;
> @@ -4015,11 +4015,17 @@ static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
>   		ret = -EINVAL;
>   	}
>   
> +#if 0
> +	/*
> +	 * Need a way to check for any copy of SB, as its not a
> +	 * strong check, just ignore this for now.
> +	 */
>   	if (btrfs_super_bytenr(sb) != BTRFS_SUPER_INFO_OFFSET) {
>   		btrfs_err(fs_info, "super offset mismatch %llu != %u",
>   			  btrfs_super_bytenr(sb), BTRFS_SUPER_INFO_OFFSET);
>   		ret = -EINVAL;
>   	}
> +#endif
>   
>   	/*
>   	 * Obvious sys_chunk_array corruptions, it must hold at least one key
> diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
> index 9fa2539a8493..f368db94d62b 100644
> --- a/fs/btrfs/volumes.c
> +++ b/fs/btrfs/volumes.c
> @@ -1369,7 +1369,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
>   {
>   	struct btrfs_super_block *disk_super;
>   	struct block_device *bdev;
> -	struct page *page;
> +	struct buffer_head *sb_bh;
>   	int ret = -EINVAL;
>   	u64 devid;
>   	u64 transid;
> @@ -1392,8 +1392,12 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
>   		goto error;
>   	}
>   
> -	if (btrfs_read_disk_super(bdev, bytenr, &page, &disk_super))
> +	sb_bh = btrfs_read_dev_super(bdev);
> +	if (IS_ERR(sb_bh)) {
> +		ret = PTR_ERR(sb_bh);
>   		goto error_bdev_put;
> +	}
> +	disk_super = (struct btrfs_super_block *) sb_bh->b_data;
>   
>   	devid = btrfs_stack_device_id(&disk_super->dev_item);
>   	transid = btrfs_super_generation(disk_super);
> @@ -1413,7 +1417,7 @@ int btrfs_scan_one_device(const char *path, fmode_t flags, void *holder,
>   	if (!ret && fs_devices_ret)
>   		(*fs_devices_ret)->total_devices = total_devices;
>   
> -	btrfs_release_disk_super(page);
> +	brelse(sb_bh);
>   
>   error_bdev_put:
>   	blkdev_put(bdev, flags);
>