From 172a50497ffaf84d60dff37fbeb03894268fe5c2 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Thu, 21 Feb 2013 02:48:22 -0700 Subject: [PATCH] Btrfs: fix wrong outstanding_extents when doing DIO write When running the 083th case of xfstests on the filesystem with "compress-force=lzo", the following WARNINGs were triggered. WARNING: at fs/btrfs/inode.c:7908 WARNING: at fs/btrfs/inode.c:7909 WARNING: at fs/btrfs/inode.c:7911 WARNING: at fs/btrfs/extent-tree.c:4510 WARNING: at fs/btrfs/extent-tree.c:4511 This problem was introduced by the patch "Btrfs: fix deadlock due to unsubmitted". In this patch, there are two bugs which caused the above problem. The 1st one is a off-by-one bug, if the DIO write return 0, it is also a short write, we need release the reserved space for it. But we didn't do it in that patch. Fix it by change "ret > 0" to "ret >= 0". The 2nd one is ->outstanding_extents was increased twice when a short write happened. As we know, ->outstanding_extents is a counter to keep track of the number of extent items we may use duo to delalloc, when we reserve the free space for a delalloc write, we assume that the write will introduce just one extent item, so we increase ->outstanding_extents by 1 at that time. And then we will increase it every time we split the write, it is done at the beginning of btrfs_get_blocks_direct(). So when a short write happens, we needn't increase ->outstanding_extents again. But this patch done. In order to fix the 2nd problem, I re-write the logic for ->outstanding_extents operation. We don't increase it at the beginning of btrfs_get_blocks_direct(), instead, we just increase it when the split actually happens. Reported-by: Mitch Harder Signed-off-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 4d0aec0cf5d8..40d49da5e846 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -6708,12 +6708,9 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock, int unlock_bits = EXTENT_LOCKED; int ret = 0; - if (create) { - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; - spin_unlock(&BTRFS_I(inode)->lock); + if (create) unlock_bits |= EXTENT_DELALLOC | EXTENT_DIRTY; - } else + else len = min_t(u64, len, root->sectorsize); lockstart = start; @@ -6855,6 +6852,10 @@ unlock: if (start + len > i_size_read(inode)) i_size_write(inode, start + len); + spin_lock(&BTRFS_I(inode)->lock); + BTRFS_I(inode)->outstanding_extents++; + spin_unlock(&BTRFS_I(inode)->lock); + ret = set_extent_bit(&BTRFS_I(inode)->io_tree, lockstart, lockstart + len - 1, EXTENT_DELALLOC, NULL, &cached_state, GFP_NOFS); @@ -7362,14 +7363,11 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb, if (rw & WRITE) { if (ret < 0 && ret != -EIOCBQUEUED) btrfs_delalloc_release_space(inode, count); - else if (ret > 0 && (size_t)ret < count) { - spin_lock(&BTRFS_I(inode)->lock); - BTRFS_I(inode)->outstanding_extents++; - spin_unlock(&BTRFS_I(inode)->lock); + else if (ret >= 0 && (size_t)ret < count) btrfs_delalloc_release_space(inode, count - (size_t)ret); - } - btrfs_delalloc_release_metadata(inode, 0); + else + btrfs_delalloc_release_metadata(inode, 0); } out: if (wakeup)