Merge tag 'xfs-iomap-for-linus-4.8-rc3' of...

Merge tag 'xfs-iomap-for-linus-4.8-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs and iomap fixes from Dave Chinner:
 "Changes in this update:

  Regression fixes for XFS changes introduce in 4.8-rc1:
   - buffer IO accounting assert failure
   - ENOSPC block accounting reservation issue
   - DAX IO path page cache invalidation fix
   - rmapbt on-disk block count in agf
   - correct classification of rmap block type when updating AGFL.
   - iomap support for attribute fork mapping

  Regression fixes for iomap infrastructure in 4.8-rc1:
   - fiemap: honor FIEMAP_FLAG_SYNC
   - fiemap: implement FIEMAP_FLAG_XATTR support to fix XFS regression
   - make mark_page_accessed and pagefault_disable usage consistent with
     other IO paths"

* tag 'xfs-iomap-for-linus-4.8-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs:
  xfs: remove OWN_AG rmap when allocating a block from the AGFL
  xfs: (re-)implement FIEMAP_FLAG_XATTR
  xfs: simplify xfs_file_iomap_begin
  iomap: mark ->iomap_end as optional
  iomap: prepare iomap_fiemap for attribute mappings
  iomap: fiemap should honor the FIEMAP_FLAG_SYNC flag
  iomap: remove superflous pagefault_disable from iomap_write_actor
  iomap: remove superflous mark_page_accessed from iomap_write_actor
  xfs: store rmapbt block count in the AGF
  xfs: don't invalidate whole file on DAX read/write
  xfs: fix bogus space reservation in xfs_iomap_write_allocate
  xfs: don't assert fail on non-async buffers on ioacct decrement

fs/iomap.c

@@ -84,8 +84,11 @@ iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
 	 * Now the data has been copied, commit the range we've copied.  This
 	 * should not fail unless the filesystem has had a fatal error.
 	 */
-	ret = ops->iomap_end(inode, pos, length, written > 0 ? written : 0,
-			flags, &iomap);
+	if (ops->iomap_end) {
+		ret = ops->iomap_end(inode, pos, length,
+				     written > 0 ? written : 0,
+				     flags, &iomap);
+	}
 
 	return written ? written : ret;
 }
@@ -194,12 +197,9 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		if (mapping_writably_mapped(inode->i_mapping))
 			flush_dcache_page(page);
 
-		pagefault_disable();
 		copied = iov_iter_copy_from_user_atomic(page, i, offset, bytes);
-		pagefault_enable();
 
 		flush_dcache_page(page);
-		mark_page_accessed(page);
 
 		status = iomap_write_end(inode, pos, bytes, copied, page);
 		if (unlikely(status < 0))
@@ -470,13 +470,18 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 	if (ret)
 		return ret;
 
-	ret = filemap_write_and_wait(inode->i_mapping);
-	if (ret)
-		return ret;
+	if (fi->fi_flags & FIEMAP_FLAG_SYNC) {
+		ret = filemap_write_and_wait(inode->i_mapping);
+		if (ret)
+			return ret;
+	}
 
 	while (len > 0) {
 		ret = iomap_apply(inode, start, len, 0, ops, &ctx,
 				iomap_fiemap_actor);
+		/* inode with no (attribute) mapping will give ENOENT */
+		if (ret == -ENOENT)
+			break;
 		if (ret < 0)
 			return ret;
 		if (ret == 0)

fs/xfs/libxfs/xfs_alloc.c

@@ -1582,6 +1582,7 @@ xfs_alloc_ag_vextent_small(
 	xfs_extlen_t	*flenp,	/* result length */
 	int		*stat)	/* status: 0-freelist, 1-normal/none */
 {
+	struct xfs_owner_info	oinfo;
 	int		error;
 	xfs_agblock_t	fbno;
 	xfs_extlen_t	flen;
@@ -1624,6 +1625,18 @@ xfs_alloc_ag_vextent_small(
 				error0);
 			args->wasfromfl = 1;
 			trace_xfs_alloc_small_freelist(args);
+
+			/*
+			 * If we're feeding an AGFL block to something that
+			 * doesn't live in the free space, we need to clear
+			 * out the OWN_AG rmap.
+			 */
+			xfs_rmap_ag_owner(&oinfo, XFS_RMAP_OWN_AG);
+			error = xfs_rmap_free(args->tp, args->agbp, args->agno,
+					fbno, 1, &oinfo);
+			if (error)
+				goto error0;
+
 			*stat = 0;
 			return 0;
 		}
@@ -2264,6 +2277,7 @@ xfs_alloc_log_agf(
 		offsetof(xfs_agf_t, agf_longest),
 		offsetof(xfs_agf_t, agf_btreeblks),
 		offsetof(xfs_agf_t, agf_uuid),
+		offsetof(xfs_agf_t, agf_rmap_blocks),
 		sizeof(xfs_agf_t)
 	};
 

fs/xfs/libxfs/xfs_format.h

@@ -640,12 +640,15 @@ typedef struct xfs_agf {
 	__be32		agf_btreeblks;	/* # of blocks held in AGF btrees */
 	uuid_t		agf_uuid;	/* uuid of filesystem */
 
+	__be32		agf_rmap_blocks;	/* rmapbt blocks used */
+	__be32		agf_padding;		/* padding */
+
 	/*
 	 * reserve some contiguous space for future logged fields before we add
 	 * the unlogged fields. This makes the range logging via flags and
 	 * structure offsets much simpler.
 	 */
-	__be64		agf_spare64[16];
+	__be64		agf_spare64[15];
 
 	/* unlogged fields, written during buffer writeback. */
 	__be64		agf_lsn;	/* last write sequence */
@@ -670,7 +673,8 @@ typedef struct xfs_agf {
 #define	XFS_AGF_LONGEST		0x00000400
 #define	XFS_AGF_BTREEBLKS	0x00000800
 #define	XFS_AGF_UUID		0x00001000
-#define	XFS_AGF_NUM_BITS	13
+#define	XFS_AGF_RMAP_BLOCKS	0x00002000
+#define	XFS_AGF_NUM_BITS	14
 #define	XFS_AGF_ALL_BITS	((1 << XFS_AGF_NUM_BITS) - 1)
 
 #define XFS_AGF_FLAGS \
@@ -686,7 +690,8 @@ typedef struct xfs_agf {
 	{ XFS_AGF_FREEBLKS,	"FREEBLKS" }, \
 	{ XFS_AGF_LONGEST,	"LONGEST" }, \
 	{ XFS_AGF_BTREEBLKS,	"BTREEBLKS" }, \
-	{ XFS_AGF_UUID,		"UUID" }
+	{ XFS_AGF_UUID,		"UUID" }, \
+	{ XFS_AGF_RMAP_BLOCKS,	"RMAP_BLOCKS" }
 
 /* disk block (xfs_daddr_t) in the AG */
 #define XFS_AGF_DADDR(mp)	((xfs_daddr_t)(1 << (mp)->m_sectbb_log))

fs/xfs/libxfs/xfs_rmap_btree.c

@@ -98,6 +98,8 @@ xfs_rmapbt_alloc_block(
 	union xfs_btree_ptr	*new,
 	int			*stat)
 {
+	struct xfs_buf		*agbp = cur->bc_private.a.agbp;
+	struct xfs_agf		*agf = XFS_BUF_TO_AGF(agbp);
 	int			error;
 	xfs_agblock_t		bno;
 
@@ -124,6 +126,8 @@ xfs_rmapbt_alloc_block(
 
 	xfs_trans_agbtree_delta(cur->bc_tp, 1);
 	new->s = cpu_to_be32(bno);
+	be32_add_cpu(&agf->agf_rmap_blocks, 1);
+	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
 
 	XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 	*stat = 1;
@@ -143,6 +147,8 @@ xfs_rmapbt_free_block(
 	bno = xfs_daddr_to_agbno(cur->bc_mp, XFS_BUF_ADDR(bp));
 	trace_xfs_rmapbt_free_block(cur->bc_mp, cur->bc_private.a.agno,
 			bno, 1);
+	be32_add_cpu(&agf->agf_rmap_blocks, -1);
+	xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
 	error = xfs_alloc_put_freelist(cur->bc_tp, agbp, NULL, bno, 1);
 	if (error)
 		return error;

fs/xfs/xfs_buf.c

@@ -115,7 +115,6 @@ xfs_buf_ioacct_dec(
 	if (!(bp->b_flags & _XBF_IN_FLIGHT))
 		return;
 
-	ASSERT(bp->b_flags & XBF_ASYNC);
 	bp->b_flags &= ~_XBF_IN_FLIGHT;
 	percpu_counter_dec(&bp->b_target->bt_io_count);
 }

fs/xfs/xfs_file.c

@@ -741,9 +741,20 @@ xfs_file_dax_write(
 	 * page is inserted into the pagecache when we have to serve a write
 	 * fault on a hole.  It should never be dirtied and can simply be
 	 * dropped from the pagecache once we get real data for the page.
+	 *
+	 * XXX: This is racy against mmap, and there's nothing we can do about
+	 * it. dax_do_io() should really do this invalidation internally as
+	 * it will know if we've allocated over a holei for this specific IO and
+	 * if so it needs to update the mapping tree and invalidate existing
+	 * PTEs over the newly allocated range. Remove this invalidation when
+	 * dax_do_io() is fixed up.
 	 */
 	if (mapping->nrpages) {
-		ret = invalidate_inode_pages2(mapping);
+		loff_t end = iocb->ki_pos + iov_iter_count(from) - 1;
+
+		ret = invalidate_inode_pages2_range(mapping,
+						    iocb->ki_pos >> PAGE_SHIFT,
+						    end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 	}
 

fs/xfs/xfs_fsops.c

@@ -248,6 +248,7 @@ xfs_growfs_data_private(
 			agf->agf_roots[XFS_BTNUM_RMAPi] =
 						cpu_to_be32(XFS_RMAP_BLOCK(mp));
 			agf->agf_levels[XFS_BTNUM_RMAPi] = cpu_to_be32(1);
+			agf->agf_rmap_blocks = cpu_to_be32(1);
 		}
 
 		agf->agf_flfirst = cpu_to_be32(1);

fs/xfs/xfs_iomap.c

@@ -715,12 +715,16 @@ xfs_iomap_write_allocate(
 		 * is in the delayed allocation extent on which we sit
 		 * but before our buffer starts.
 		 */
-
 		nimaps = 0;
 		while (nimaps == 0) {
 			nres = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
-
-			error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, nres,
+			/*
+			 * We have already reserved space for the extent and any
+			 * indirect blocks when creating the delalloc extent,
+			 * there is no need to reserve space in this transaction
+			 * again.
+			 */
+			error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0,
 					0, XFS_TRANS_RESERVE, &tp);
 			if (error)
 				return error;
@@ -1037,20 +1041,14 @@ xfs_file_iomap_begin(
 			return error;
 
 		trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
-		xfs_bmbt_to_iomap(ip, iomap, &imap);
-	} else if (nimaps) {
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
-		xfs_bmbt_to_iomap(ip, iomap, &imap);
 	} else {
+		ASSERT(nimaps);
+
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		trace_xfs_iomap_not_found(ip, offset, length, 0, &imap);
-		iomap->blkno = IOMAP_NULL_BLOCK;
-		iomap->type = IOMAP_HOLE;
-		iomap->offset = offset;
-		iomap->length = length;
+		trace_xfs_iomap_found(ip, offset, length, 0, &imap);
 	}
 
+	xfs_bmbt_to_iomap(ip, iomap, &imap);
 	return 0;
 }
 
@@ -1112,3 +1110,48 @@ struct iomap_ops xfs_iomap_ops = {
 	.iomap_begin		= xfs_file_iomap_begin,
 	.iomap_end		= xfs_file_iomap_end,
 };
+
+static int
+xfs_xattr_iomap_begin(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			length,
+	unsigned		flags,
+	struct iomap		*iomap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + length);
+	struct xfs_bmbt_irec	imap;
+	int			nimaps = 1, error = 0;
+	unsigned		lockmode;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	lockmode = xfs_ilock_data_map_shared(ip);
+
+	/* if there are no attribute fork or extents, return ENOENT */
+	if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
+		error = -ENOENT;
+		goto out_unlock;
+	}
+
+	ASSERT(ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL);
+	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
+			       &nimaps, XFS_BMAPI_ENTIRE | XFS_BMAPI_ATTRFORK);
+out_unlock:
+	xfs_iunlock(ip, lockmode);
+
+	if (!error) {
+		ASSERT(nimaps);
+		xfs_bmbt_to_iomap(ip, iomap, &imap);
+	}
+
+	return error;
+}
+
+struct iomap_ops xfs_xattr_iomap_ops = {
+	.iomap_begin		= xfs_xattr_iomap_begin,
+};

fs/xfs/xfs_iomap.h

@@ -35,5 +35,6 @@ void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
 		struct xfs_bmbt_irec *);
 
 extern struct iomap_ops xfs_iomap_ops;
+extern struct iomap_ops xfs_xattr_iomap_ops;
 
 #endif /* __XFS_IOMAP_H__*/

fs/xfs/xfs_iops.c

@@ -1009,7 +1009,14 @@ xfs_vn_fiemap(
 	int			error;
 
 	xfs_ilock(XFS_I(inode), XFS_IOLOCK_SHARED);
-	error = iomap_fiemap(inode, fieinfo, start, length, &xfs_iomap_ops);
+	if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) {
+		fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR;
+		error = iomap_fiemap(inode, fieinfo, start, length,
+				&xfs_xattr_iomap_ops);
+	} else {
+		error = iomap_fiemap(inode, fieinfo, start, length,
+				&xfs_iomap_ops);
+	}
 	xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
 
 	return error;

fs/xfs/xfs_trace.h

@@ -1298,7 +1298,6 @@ DEFINE_IOMAP_EVENT(xfs_get_blocks_alloc);
 DEFINE_IOMAP_EVENT(xfs_get_blocks_map_direct);
 DEFINE_IOMAP_EVENT(xfs_iomap_alloc);
 DEFINE_IOMAP_EVENT(xfs_iomap_found);
-DEFINE_IOMAP_EVENT(xfs_iomap_not_found);
 
 DECLARE_EVENT_CLASS(xfs_simple_io_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count),