From 4577b014d1bc3db386da3246f625888fc48083a9 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 27 Sep 2013 13:33:09 +0000 Subject: Btrfs: relocate csums properly with prealloc extents A user reported a problem where they were getting csum errors when running a balance and running systemd's journal. This is because systemd is awesome and fallocate()'s its log space and writes into it. Unfortunately we assume that when we read in all the csums for an extent that they are sequential starting at the bytenr we care about. This obviously isn't the case for prealloc extents, where we could have written to the middle of the prealloc extent only, which means the csum would be for the bytenr in the middle of our range and not the front of our range. Fix this by offsetting the new bytenr we are logging to based on the original bytenr the csum was for. With this patch I no longer see the csum errors I was seeing. Thanks, Cc: stable@vger.kernel.org Reported-by: Chris Murphy Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c index dec4f5a..0359eec 100644 --- a/fs/btrfs/relocation.c +++ b/fs/btrfs/relocation.c @@ -4472,6 +4472,7 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len) struct btrfs_root *root = BTRFS_I(inode)->root; int ret; u64 disk_bytenr; + u64 new_bytenr; LIST_HEAD(list); ordered = btrfs_lookup_ordered_extent(inode, file_pos); @@ -4483,13 +4484,24 @@ int btrfs_reloc_clone_csums(struct inode *inode, u64 file_pos, u64 len) if (ret) goto out; - disk_bytenr = ordered->start; while (!list_empty(&list)) { sums = list_entry(list.next, struct btrfs_ordered_sum, list); list_del_init(&sums->list); - sums->bytenr = disk_bytenr; - disk_bytenr += sums->len; + /* + * We need to offset the new_bytenr based on where the csum is. + * We need to do this because we will read in entire prealloc + * extents but we may have written to say the middle of the + * prealloc extent, so we need to make sure the csum goes with + * the right disk offset. + * + * We can do this because the data reloc inode refers strictly + * to the on disk bytes, so we don't have to worry about + * disk_len vs real len like with real inodes since it's all + * disk length. + */ + new_bytenr = ordered->start + (sums->bytenr - disk_bytenr); + sums->bytenr = new_bytenr; btrfs_add_ordered_sum(inode, ordered, sums); } -- cgit v0.9.2