Changes since last update:

- Fix various iomap bugs
 - Fix overly aggressive CoW preallocation garbage collection
 - Fixes to CoW endio error handling
 - Fix some incorrect geometry calculations
 - Remove a potential system hang in bulkstat
 - Try to allocate blocks more aggressively to reduce ENOSPC errors
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQIcBAABCgAGBQJYwbgtAAoJEPh/dxk0SrTrsl8P/1cyLiDirZiUc/cToZamPTNb
 cvCNuM/m7OkocB4KQ/CsHNfJDiDGPfrAJ8fukJAGXB+ordun2kM7iTx3HQ1+qEvb
 pt+znR0MKgm3dCMdey8OA9UBl85GAG47jvioITUNg6/tse5u/WAaRcjISa30z/qb
 xv/guqx6AYyLtQ1K5v/j67w3lmeR8b9Qu0ze7sRTn7TP3cVpFZS6TeZT/hmV/ZMp
 3sG7rZFuC3c0b/b+CvyXufjDyqtIZ+yYENbmTDngyoTwOVsw66u0dZNHvV/L5RDe
 z1CBKZrp+PmTIWQJeSkwX26VnOxcL0sRsfareFIYLN2fKffCFAXtbrhIifuXYe5n
 a5tsyzd8jgOb6EHlKyA4Ls5o4Gqt5mUBEV1CCHVbcpSoGUMIBE3Vn7QrKjRaIGtF
 1EbUI969LBjBdw2cOAYZ3bUIAW7AfGtNh6nLBTkT1n2ATOS15o+1l7yXN3HkEiGv
 xyikBREp+jV8tR1ZaBNtHnPJeKYxMVAxoMw3ZfrHFA3wPbIKQwrhTZSYavrUN5YC
 6/7VyLWrt4Xy8NgzHOiHtvZCAYCzP6FwBOPALrqjOMJR5giSZ7VduV3WT2v0xJO/
 Cy9TsyTdjYy/dJe54KPC4jhCKkyNEGwB3VaGwifzSUcHVnYpbIBT/gDTSRNk1+xN
 U2ufq3mtoi+BM8/znImL
 =5WKj
 -----END PGP SIGNATURE-----

Merge tag 'xfs-4.11-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Darrick Wong:
 "Here are some bug fixes for -rc2 to clean up the copy on write
  handling and to remove a cause of hangs.

   - Fix various iomap bugs

   - Fix overly aggressive CoW preallocation garbage collection

   - Fixes to CoW endio error handling

   - Fix some incorrect geometry calculations

   - Remove a potential system hang in bulkstat

   - Try to allocate blocks more aggressively to reduce ENOSPC errors"

* tag 'xfs-4.11-fixes-1' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: try any AG when allocating the first btree block when reflinking
  xfs: use iomap new flag for newly allocated delalloc blocks
  xfs: remove kmem_zalloc_greedy
  xfs: Use xfs_icluster_size_fsb() to calculate inode alignment mask
  xfs: fix and streamline error handling in xfs_end_io
  xfs: only reclaim unwritten COW extents periodically
  iomap: invalidate page caches should be after iomap_dio_complete() in direct write

fs/iomap.c

@@ -846,7 +846,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	size_t count = iov_iter_count(iter);
-	loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0;
+	loff_t pos = iocb->ki_pos, start = pos;
+	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
 	struct blk_plug plug;
 	struct iomap_dio *dio;
@@ -887,12 +888,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	}
 
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		ret = filemap_write_and_wait_range(mapping, start, end);
 		if (ret)
 			goto out_free_dio;
 
 		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
@@ -941,6 +942,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		__set_current_state(TASK_RUNNING);
 	}
 
+	ret = iomap_dio_complete(dio);
+
 	/*
 	 * Try again to invalidate clean pages which might have been cached by
 	 * non-direct readahead, or faulted in by get_user_pages() if the source
@@ -949,12 +952,12 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	 * this invalidation fails, tough, the write still worked...
 	 */
 	if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
+		int err = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
+		WARN_ON_ONCE(err);
 	}
 
-	return iomap_dio_complete(dio);
+	return ret;
 
 out_free_dio:
 	kfree(dio);

fs/xfs/kmem.c

@@ -25,24 +25,6 @@
 #include "kmem.h"
 #include "xfs_message.h"
 
-/*
- * Greedy allocation.  May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
-	void		*ptr;
-	size_t		kmsize = maxsize;
-
-	while (!(ptr = vzalloc(kmsize))) {
-		if ((kmsize >>= 1) <= minsize)
-			kmsize = minsize;
-	}
-	if (ptr)
-		*size = kmsize;
-	return ptr;
-}
-
 void *
 kmem_alloc(size_t size, xfs_km_flags_t flags)
 {

fs/xfs/kmem.h

@@ -69,8 +69,6 @@ static inline void  kmem_free(const void *ptr)
 }
 
 
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
 static inline void *
 kmem_zalloc(size_t size, xfs_km_flags_t flags)
 {

fs/xfs/libxfs/xfs_bmap.c

@@ -763,8 +763,8 @@ xfs_bmap_extents_to_btree(
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
 	} else if (dfops->dop_low) {
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
 		args.fsbno = *firstblock;
 	} else {
 		args.type = XFS_ALLOCTYPE_NEAR_BNO;
@@ -790,13 +790,17 @@ try_another_ag:
 	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
 	    args.fsbno == NULLFSBLOCK &&
 	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		dfops->dop_low = true;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		goto try_another_ag;
 	}
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+		xfs_iroot_realloc(ip, -1, whichfork);
+		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+		return -ENOSPC;
+	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(*firstblock == NULLFSBLOCK ||
 	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
 	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
@@ -4150,6 +4154,19 @@ xfs_bmapi_read(
 	return 0;
 }
 
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
 int
 xfs_bmapi_reserve_delalloc(
 	struct xfs_inode	*ip,
@@ -4236,13 +4253,8 @@ xfs_bmapi_reserve_delalloc(
 	got->br_startblock = nullstartblock(indlen);
 	got->br_blockcount = alen;
 	got->br_state = XFS_EXT_NORM;
-	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
-	/*
+	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
-	 * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
-	 * might have merged it into one of the neighbouring ones.
-	 */
-	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
 
 	/*
 	 * Tag the inode if blocks were preallocated. Note that COW fork
@@ -4254,10 +4266,6 @@ xfs_bmapi_reserve_delalloc(
 	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
 		xfs_inode_set_cowblocks_tag(ip);
 
-	ASSERT(got->br_startoff <= aoff);
-	ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen);
-	ASSERT(isnullstartblock(got->br_startblock));
-	ASSERT(got->br_state == XFS_EXT_NORM);
 	return 0;
 
 out_unreserve_blocks:

fs/xfs/libxfs/xfs_bmap_btree.c

@@ -447,8 +447,8 @@ xfs_bmbt_alloc_block(
 
 	if (args.fsbno == NULLFSBLOCK) {
 		args.fsbno = be64_to_cpu(start->l);
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
+try_another_ag:
 		/*
 		 * Make sure there is sufficient room left in the AG to
 		 * complete a full tree split for an extent insert.  If
@@ -488,8 +488,8 @@ try_another_ag:
 	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
 	    args.fsbno == NULLFSBLOCK &&
 	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		cur->bc_private.b.dfops->dop_low = true;
 		args.fsbno = cur->bc_private.b.firstblock;
+		args.type = XFS_ALLOCTYPE_FIRST_AG;
 		goto try_another_ag;
 	}
 
@@ -506,7 +506,7 @@ try_another_ag:
 			goto error0;
 		cur->bc_private.b.dfops->dop_low = true;
 	}
-	if (args.fsbno == NULLFSBLOCK) {
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 		*stat = 0;
 		return 0;

fs/xfs/xfs_aops.c

@@ -274,54 +274,49 @@ xfs_end_io(
 	struct xfs_ioend	*ioend =
 		container_of(work, struct xfs_ioend, io_work);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	xfs_off_t		offset = ioend->io_offset;
+	size_t			size = ioend->io_size;
 	int			error = ioend->io_bio->bi_error;
 
 	/*
-	 * Set an error if the mount has shut down and proceed with end I/O
+	 * Just clean up the in-memory strutures if the fs has been shut down.
-	 * processing so it can perform whatever cleanups are necessary.
 	 */
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		error = -EIO;
-
+		goto done;
-	/*
-	 * For a CoW extent, we need to move the mapping from the CoW fork
-	 * to the data fork.  If instead an error happened, just dump the
-	 * new blocks.
-	 */
-	if (ioend->io_type == XFS_IO_COW) {
-		if (error)
-			goto done;
-		if (ioend->io_bio->bi_error) {
-			error = xfs_reflink_cancel_cow_range(ip,
-					ioend->io_offset, ioend->io_size);
-			goto done;
-		}
-		error = xfs_reflink_end_cow(ip, ioend->io_offset,
-				ioend->io_size);
-		if (error)
-			goto done;
 	}
 
 	/*
-	 * For unwritten extents we need to issue transactions to convert a
+	 * Clean up any COW blocks on an I/O error.
-	 * range to normal written extens after the data I/O has finished.
-	 * Detecting and handling completion IO errors is done individually
-	 * for each case as different cleanup operations need to be performed
-	 * on error.
 	 */
-	if (ioend->io_type == XFS_IO_UNWRITTEN) {
+	if (unlikely(error)) {
-		if (error)
+		switch (ioend->io_type) {
-			goto done;
+		case XFS_IO_COW:
-		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
+			xfs_reflink_cancel_cow_range(ip, offset, size, true);
-						  ioend->io_size);
+			break;
-	} else if (ioend->io_append_trans) {
+		}
-		error = xfs_setfilesize_ioend(ioend, error);
+
-	} else {
+		goto done;
-		ASSERT(!xfs_ioend_is_append(ioend) ||
+	}
-		       ioend->io_type == XFS_IO_COW);
+
+	/*
+	 * Success:  commit the COW or unwritten blocks if needed.
+	 */
+	switch (ioend->io_type) {
+	case XFS_IO_COW:
+		error = xfs_reflink_end_cow(ip, offset, size);
+		break;
+	case XFS_IO_UNWRITTEN:
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+		break;
+	default:
+		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+		break;
 	}
 
 done:
+	if (ioend->io_append_trans)
+		error = xfs_setfilesize_ioend(ioend, error);
 	xfs_destroy_ioend(ioend, error);
 }
 

fs/xfs/xfs_icache.c

@@ -1608,7 +1608,7 @@ xfs_inode_free_cowblocks(
 	xfs_ilock(ip, XFS_IOLOCK_EXCL);
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 
-	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	xfs_iunlock(ip, XFS_IOLOCK_EXCL);

fs/xfs/xfs_inode.c

@@ -1615,7 +1615,7 @@ xfs_itruncate_extents(
 
 	/* Remove all pending CoW reservations. */
 	error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block,
-			last_block);
+			last_block, true);
 	if (error)
 		goto out;
 

fs/xfs/xfs_iomap.c

@@ -630,6 +630,11 @@ retry:
 		goto out_unlock;
 	}
 
+	/*
+	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+	 * them out if the write happens to fail.
+	 */
+	iomap->flags = IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -1071,16 +1076,22 @@ xfs_file_iomap_end_delalloc(
 	struct xfs_inode	*ip,
 	loff_t			offset,
 	loff_t			length,
-	ssize_t			written)
+	ssize_t			written,
+	struct iomap		*iomap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_fsb;
 	xfs_fileoff_t		end_fsb;
 	int			error = 0;
 
-	/* behave as if the write failed if drop writes is enabled */
+	/*
-	if (xfs_mp_drop_writes(mp))
+	 * Behave as if the write failed if drop writes is enabled. Set the NEW
+	 * flag to force delalloc cleanup.
+	 */
+	if (xfs_mp_drop_writes(mp)) {
+		iomap->flags |= IOMAP_F_NEW;
 		written = 0;
+	}
 
 	/*
 	 * start_fsb refers to the first unused block after a short write. If
@@ -1094,14 +1105,14 @@ xfs_file_iomap_end_delalloc(
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
 	/*
-	 * Trim back delalloc blocks if we didn't manage to write the whole
+	 * Trim delalloc blocks if they were allocated by this write and we
-	 * range reserved.
+	 * didn't manage to write the whole range.
 	 *
 	 * We don't need to care about racing delalloc as we hold i_mutex
 	 * across the reserve/allocate/unreserve calls. If there are delalloc
 	 * blocks in the range, they are ours.
 	 */
-	if (start_fsb < end_fsb) {
+	if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
 		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
 					 XFS_FSB_TO_B(mp, end_fsb) - 1);
 
@@ -1131,7 +1142,7 @@ xfs_file_iomap_end(
 {
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
-				length, written);
+				length, written, iomap);
 	return 0;
 }
 

fs/xfs/xfs_itable.c

@@ -361,7 +361,6 @@ xfs_bulkstat(
 	xfs_agino_t		agino;	/* inode # in allocation group */
 	xfs_agnumber_t		agno;	/* allocation group number */
 	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
-	size_t			irbsize; /* size of irec buffer in bytes */
 	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
 	int			nirbuf;	/* size of irbuf */
 	int			ubcount; /* size of user's buffer */
@@ -388,11 +387,10 @@ xfs_bulkstat(
 	*ubcountp = 0;
 	*done = 0;
 
-	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
+	irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP);
 	if (!irbuf)
 		return -ENOMEM;
-
+	nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf);
-	nirbuf = irbsize / sizeof(*irbuf);
 
 	/*
 	 * Loop over the allocation groups, starting from the last

fs/xfs/xfs_mount.c

@@ -513,8 +513,7 @@ STATIC void
 xfs_set_inoalignment(xfs_mount_t *mp)
 {
 	if (xfs_sb_version_hasalign(&mp->m_sb) &&
-	    mp->m_sb.sb_inoalignmt >=
+		mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
-	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
 		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
 	else
 		mp->m_inoalign_mask = 0;

fs/xfs/xfs_reflink.c

@@ -548,14 +548,18 @@ xfs_reflink_trim_irec_to_next_cow(
 }
 
 /*
- * Cancel all pending CoW reservations for some block range of an inode.
+ * Cancel CoW reservations for some block range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_blocks(
 	struct xfs_inode		*ip,
 	struct xfs_trans		**tpp,
 	xfs_fileoff_t			offset_fsb,
-	xfs_fileoff_t			end_fsb)
+	xfs_fileoff_t			end_fsb,
+	bool				cancel_real)
 {
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
@@ -579,7 +583,7 @@ xfs_reflink_cancel_cow_blocks(
 					&idx, &got, &del);
 			if (error)
 				break;
-		} else {
+		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
@@ -621,13 +625,17 @@ xfs_reflink_cancel_cow_blocks(
 }
 
 /*
- * Cancel all pending CoW reservations for some byte range of an inode.
+ * Cancel CoW reservations for some byte range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_range(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		count)
+	xfs_off_t		count,
+	bool			cancel_real)
 {
 	struct xfs_trans	*tp;
 	xfs_fileoff_t		offset_fsb;
@@ -653,7 +661,8 @@ xfs_reflink_cancel_cow_range(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	/* Scrape out the old CoW reservations */
-	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb);
+	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
+			cancel_real);
 	if (error)
 		goto out_cancel;
 
@@ -1450,7 +1459,7 @@ next:
 	 * We didn't find any shared blocks so turn off the reflink flag.
 	 * First, get rid of any leftover CoW mappings.
 	 */
-	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF);
+	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
 	if (error)
 		return error;
 

fs/xfs/xfs_reflink.h

@@ -39,9 +39,9 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
-		xfs_fileoff_t end_fsb);
+		xfs_fileoff_t end_fsb, bool cancel_real);
 extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
-		xfs_off_t count);
+		xfs_off_t count, bool cancel_real);
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);

fs/xfs/xfs_super.c

@@ -953,7 +953,7 @@ xfs_fs_destroy_inode(
 	XFS_STATS_INC(ip->i_mount, vn_remove);
 
 	if (xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 		if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount))
 			xfs_warn(ip->i_mount,
 "Error %d while evicting CoW blocks for inode %llu.",