From: Christoph Hellwig hch@lst.de
[ Upstream commit 610b29161b0aa9feb59b78dc867553274f17fb01 ]
xfs_can_free_eofblocks returns false for files that have persistent preallocations unless the force flag is passed and there are delayed blocks. This means it won't free delalloc reservations for files with persistent preallocations unless the force flag is set, and it will also free the persistent preallocations if the force flag is set and the file happens to have delayed allocations.
Both of these are bad, so do away with the force flag and always free only post-EOF delayed allocations for files with the XFS_DIFLAG_PREALLOC or APPEND flags set.
Signed-off-by: Christoph Hellwig hch@lst.de Reviewed-by: Darrick J. Wong djwong@kernel.org Signed-off-by: Chandan Babu R chandanbabu@kernel.org Signed-off-by: Leah Rumancik leah.rumancik@gmail.com Acked-by: "Darrick J. Wong" djwong@kernel.org --- fs/xfs/xfs_bmap_util.c | 30 ++++++++++++++++++++++-------- fs/xfs/xfs_bmap_util.h | 2 +- fs/xfs/xfs_icache.c | 2 +- fs/xfs/xfs_inode.c | 14 ++++---------- 4 files changed, 28 insertions(+), 20 deletions(-)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 399451aab26a..62b92e92a685 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -634,17 +634,15 @@ xfs_bmap_punch_delalloc_range( return error; }
/* * Test whether it is appropriate to check an inode for and free post EOF - * blocks. The 'force' parameter determines whether we should also consider - * regular files that are marked preallocated or append-only. + * blocks. */ bool xfs_can_free_eofblocks( - struct xfs_inode *ip, - bool force) + struct xfs_inode *ip) { struct xfs_bmbt_irec imap; struct xfs_mount *mp = ip->i_mount; xfs_fileoff_t end_fsb; xfs_fileoff_t last_fsb; @@ -674,15 +672,15 @@ xfs_can_free_eofblocks( /* If we haven't read in the extent list, then don't do it now. */ if (xfs_need_iread_extents(&ip->i_df)) return false;
/* - * Do not free real preallocated or append-only files unless the file - * has delalloc blocks and we are forced to remove them. + * Only free real extents for inodes with persistent preallocations or + * the append-only flag. */ if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) - if (!force || ip->i_delayed_blks == 0) + if (ip->i_delayed_blks == 0) return false;
/* * Do not try to free post-EOF blocks if EOF is beyond the end of the * range supported by the page cache, because the truncation will loop @@ -732,10 +730,26 @@ xfs_free_eofblocks( return error;
/* Wait on dio to ensure i_size has settled. */ inode_dio_wait(VFS_I(ip));
+ /* + * For preallocated files only free delayed allocations. + * + * Note that this means we also leave speculative preallocations in + * place for preallocated files. + */ + if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) { + if (ip->i_delayed_blks) { + xfs_bmap_punch_delalloc_range(ip, + round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize), + LLONG_MAX); + } + xfs_inode_clear_eofblocks_tag(ip); + return 0; + } + error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp); if (error) { ASSERT(xfs_is_shutdown(mp)); return error; } @@ -1046,11 +1060,11 @@ xfs_prepare_shift(
/* * Trim eofblocks to avoid shifting uninitialized post-eof preallocation * into the accessible region of the file. */ - if (xfs_can_free_eofblocks(ip, true)) { + if (xfs_can_free_eofblocks(ip)) { error = xfs_free_eofblocks(ip); if (error) return error; }
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h index 6888078f5c31..1383019ccdb7 100644 --- a/fs/xfs/xfs_bmap_util.h +++ b/fs/xfs/xfs_bmap_util.h @@ -61,11 +61,11 @@ int xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset, xfs_off_t len); int xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset, xfs_off_t len);
/* EOF block manipulation functions */ -bool xfs_can_free_eofblocks(struct xfs_inode *ip, bool force); +bool xfs_can_free_eofblocks(struct xfs_inode *ip); int xfs_free_eofblocks(struct xfs_inode *ip);
int xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip, struct xfs_swapext *sx);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c index 6df826fc787c..586d26c05160 100644 --- a/fs/xfs/xfs_icache.c +++ b/fs/xfs/xfs_icache.c @@ -1184,11 +1184,11 @@ xfs_inode_free_eofblocks( return -EAGAIN; return 0; } *lockflags |= XFS_IOLOCK_EXCL;
- if (xfs_can_free_eofblocks(ip, false)) + if (xfs_can_free_eofblocks(ip)) return xfs_free_eofblocks(ip);
/* inode could be preallocated or append-only */ trace_xfs_inode_free_eofblocks_invalid(ip); xfs_inode_clear_eofblocks_tag(ip); diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 26961b0dae03..b26d26d29273 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -1457,11 +1457,11 @@ xfs_release( * dropped, so we'll never leak blocks permanently. */ if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) return 0;
- if (xfs_can_free_eofblocks(ip, false)) { + if (xfs_can_free_eofblocks(ip)) { /* * Check if the inode is being opened, written and closed * frequently and we have delayed allocation blocks outstanding * (e.g. streaming writes from the NFS server), truncating the * blocks past EOF will cause fragmentation to occur. @@ -1673,19 +1673,17 @@ xfs_inode_needs_inactive( if (VFS_I(ip)->i_nlink == 0) return true;
/* * This file isn't being freed, so check if there are post-eof blocks - * to free. @force is true because we are evicting an inode from the - * cache. Post-eof blocks must be freed, lest we end up with broken - * free space accounting. + * to free. * * Note: don't bother with iolock here since lockdep complains about * acquiring it in reclaim context. We have the only reference to the * inode at this point anyways. */ - return xfs_can_free_eofblocks(ip, true); + return xfs_can_free_eofblocks(ip); }
/* * xfs_inactive * @@ -1732,19 +1730,15 @@ xfs_inactive( goto out; }
if (VFS_I(ip)->i_nlink != 0) { /* - * force is true because we are evicting an inode from the - * cache. Post-eof blocks must be freed, lest we end up with - * broken free space accounting. - * * Note: don't bother with iolock here since lockdep complains * about acquiring it in reclaim context. We have the only * reference to the inode at this point anyways. */ - if (xfs_can_free_eofblocks(ip, true)) + if (xfs_can_free_eofblocks(ip)) error = xfs_free_eofblocks(ip);
goto out; }