Merge tag 'for-linus-v3.9-rc1' of git://oss.sgi.com/xfs/xfs

Pull xfs update from Ben Myers:
 "Primarily bugfixes and a few cleanups:

   - fix(es) for compound buffers

   - remove unused XFS_TRANS_DEBUG routines

   - fix for dquot soft timer asserts due to overflow of d_blk_softlimit

   - don't zero allocation args structure members after they are memset(0)

   - fix for regression in dir v2 code introduced in commit 20f7e9f3

   - remove obsolete simple_strto<foo>

   - fix return value when filesystem probe finds no XFS magic, a
     regression introduced in 9802182.

   - remove boolean_t typedef completely

   - fix stack switch in __xfs_bmapi_allocate by moving the check for
     stack switch up into xfs_bmapi_write.

   - fix build error due to incomplete boolean_t removal

   - fix oops in _xfs_buf_find by validating that the requested block is
     within the filesystem bounds.

   - limit speculative preallocation near ENOSPC.

   - fix an unmount hang in xfs_wait_buftarg by freeing the
     xfs_buf_log_item in xfs_buf_item_unlock.

   - fix a possible use after free with AIO.

   - fix xfs_swap_extents after removal of xfs_flushinval_pages, a
     regression introduced in fb59581404a.

   - replace hardcoded 128 with log header size

   - add memory barrier before wake_up_bit in xfs_ifunlock

   - limit speculative preallocation on sparse files

   - fix xa_lock recursion bug introduced in 90810b9e82a3

   - fix write verifier for symlinks"

Fixed up conflicts in fs/xfs/xfs_buf_item.c (due to bli_format rename in
commit 0f22f9d0cd8a affecting the removed XFS_TRANS_DEBUG routines in
commit ec47eb6b0b45).

* tag 'for-linus-v3.9-rc1' of git://oss.sgi.com/xfs/xfs: (36 commits)
  xfs: xfs_bmap_add_attrfork_local is too generic
  xfs: remove log force from xfs_buf_trylock()
  xfs: recheck buffer pinned status after push trylock failure
  xfs: limit speculative prealloc size on sparse files
  xfs: memory barrier before wake_up_bit()
  xfs: refactor space log reservation for XFS_TRANS_ATTR_SET
  xfs: make use of XFS_SB_LOG_RES() at xfs_fs_log_dummy()
  xfs: make use of XFS_SB_LOG_RES() at xfs_mount_log_sb()
  xfs: make use of XFS_SB_LOG_RES() at xfs_log_sbcount()
  xfs: introduce XFS_SB_LOG_RES() for transactions that modify sb on disk
  xfs: calculate XFS_TRANS_QM_QUOTAOFF_END space log reservation at mount time
  xfs: calculate XFS_TRANS_QM_QUOTAOFF space log reservation at mount time
  xfs: calculate XFS_TRANS_QM_DQALLOC space log reservation at mount time
  xfs: calcuate XFS_TRANS_QM_SETQLIM space log reservation at mount time
  xfs: calculate xfs_qm_write_sb_changes() space log reservation at mount time
  xfs: calculate XFS_TRANS_QM_SBCHANGE space log reservation at mount time
  xfs: make use of xfs_calc_buf_res() in xfs_trans.c
  xfs: add a helper to figure out the space log reservation per item
  xfs: Fix xfs_swap_extents() after removal of xfs_flushinval_pages()
  xfs: Fix possible use-after-free with AIO
  ...

1 files changed, 67 insertions, 10 deletions

diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 364818eef40..912d83d8860 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -311,6 +311,62 @@ xfs_iomap_eof_want_preallocate(
 }
 
 /*
+ * Determine the initial size of the preallocation. We are beyond the current
+ * EOF here, but we need to take into account whether this is a sparse write or
+ * an extending write when determining the preallocation size.  Hence we need to
+ * look up the extent that ends at the current write offset and use the result
+ * to determine the preallocation size.
+ *
+ * If the extent is a hole, then preallocation is essentially disabled.
+ * Otherwise we take the size of the preceeding data extent as the basis for the
+ * preallocation size. If the size of the extent is greater than half the
+ * maximum extent length, then use the current offset as the basis. This ensures
+ * that for large files the preallocation size always extends to MAXEXTLEN
+ * rather than falling short due to things like stripe unit/width alignment of
+ * real extents.
+ */
+STATIC int
+xfs_iomap_eof_prealloc_initial_size(
+	struct xfs_mount	*mp,
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_bmbt_irec_t		*imap,
+	int			nimaps)
+{
+	xfs_fileoff_t   start_fsb;
+	int		imaps = 1;
+	int		error;
+
+	ASSERT(nimaps >= imaps);
+
+	/* if we are using a specific prealloc size, return now */
+	if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
+		return 0;
+
+	/*
+	 * As we write multiple pages, the offset will always align to the
+	 * start of a page and hence point to a hole at EOF. i.e. if the size is
+	 * 4096 bytes, we only have one block at FSB 0, but XFS_B_TO_FSB(4096)
+	 * will return FSB 1. Hence if there are blocks in the file, we want to
+	 * point to the block prior to the EOF block and not the hole that maps
+	 * directly at @offset.
+	 */
+	start_fsb = XFS_B_TO_FSB(mp, offset);
+	if (start_fsb)
+		start_fsb--;
+	error = xfs_bmapi_read(ip, start_fsb, 1, imap, &imaps, XFS_BMAPI_ENTIRE);
+	if (error)
+		return 0;
+
+	ASSERT(imaps == 1);
+	if (imap[0].br_startblock == HOLESTARTBLOCK)
+		return 0;
+	if (imap[0].br_blockcount <= (MAXEXTLEN >> 1))
+		return imap[0].br_blockcount;
+	return XFS_B_TO_FSB(mp, offset);
+}
+
+/*
  * If we don't have a user specified preallocation size, dynamically increase
  * the preallocation size as the size of the file grows. Cap the maximum size
  * at a single extent or less if the filesystem is near full. The closer the
@@ -319,20 +375,19 @@ xfs_iomap_eof_want_preallocate(
 STATIC xfs_fsblock_t
 xfs_iomap_prealloc_size(
 	struct xfs_mount	*mp,
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	struct xfs_bmbt_irec	*imap,
+	int			nimaps)
 {
 	xfs_fsblock_t		alloc_blocks = 0;
 
-	if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
+	alloc_blocks = xfs_iomap_eof_prealloc_initial_size(mp, ip, offset,
+							   imap, nimaps);
+	if (alloc_blocks > 0) {
 		int shift = 0;
 		int64_t freesp;
 
-		/*
-		 * rounddown_pow_of_two() returns an undefined result
-		 * if we pass in alloc_blocks = 0. Hence the "+ 1" to
-		 * ensure we always pass in a non-zero value.
-		 */
-		alloc_blocks = XFS_B_TO_FSB(mp, XFS_ISIZE(ip)) + 1;
 		alloc_blocks = XFS_FILEOFF_MIN(MAXEXTLEN,
 					rounddown_pow_of_two(alloc_blocks));
 
@@ -399,7 +454,6 @@ xfs_iomap_write_delay(
 	extsz = xfs_get_extsz_hint(ip);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 
-
 	error = xfs_iomap_eof_want_preallocate(mp, ip, offset, count,
 				imap, XFS_WRITE_IMAPS, &prealloc);
 	if (error)
@@ -407,7 +461,10 @@ xfs_iomap_write_delay(
 
 retry:
 	if (prealloc) {
-		xfs_fsblock_t	alloc_blocks = xfs_iomap_prealloc_size(mp, ip);
+		xfs_fsblock_t	alloc_blocks;
+
+		alloc_blocks = xfs_iomap_prealloc_size(mp, ip, offset, imap,
+						       XFS_WRITE_IMAPS);
 
 		aligned_offset = XFS_WRITEIO_ALIGN(mp, (offset + count - 1));
 		ioalign = XFS_B_TO_FSBT(mp, aligned_offset);