xfs: patches remaining for 4.4 merge window

index e4fff58..366e41eb 100644
@@ -1259,13 +1259,28 @@ xfs_vm_releasepage(
  * the DIO. There is only going to be one reference to the ioend and its life
  * cycle is constrained by the DIO completion code. hence we don't need
  * reference counting here.
+ *
+ * Note that for DIO, an IO to the highest supported file block offset (i.e.
+ * 2^63 - 1FSB bytes) will result in the offset + count overflowing a signed 64
+ * bit variable. Hence if we see this overflow, we have to assume that the IO is
+ * extending the file size. We won't know for sure until IO completion is run
+ * and the actual max write offset is communicated to the IO completion
+ * routine.
+ *
+ * For DAX page faults, we are preparing to never see unwritten extents here,
+ * nor should we ever extend the inode size. Hence we will soon have nothing to
+ * do here for this case, ensuring we don't have to provide an IO completion
+ * callback to free an ioend that we don't actually need for a fault into the
+ * page at offset (2^63 - 1FSB) bytes.
  */
+
 static void
 xfs_map_direct(
 	struct inode		*inode,
 	struct buffer_head	*bh_result,
 	struct xfs_bmbt_irec	*imap,
-	xfs_off_t		offset)
+	xfs_off_t		offset,
+	bool			dax_fault)
 {
 	struct xfs_ioend	*ioend;
 	xfs_off_t		size = bh_result->b_size;

@@ -1278,6 +1293,16 @@ xfs_map_direct(
 
 	trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
 
+	/* XXX: preparation for removing unwritten extents in DAX */
+#if 0
+	if (dax_fault) {
+		ASSERT(type == XFS_IO_OVERWRITE);
+		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
+					    imap);
+		return;
+	}
+#endif
+
 	if (bh_result->b_private) {
 		ioend = bh_result->b_private;
 		ASSERT(ioend->io_size > 0);

@@ -1292,7 +1317,8 @@ xfs_map_direct(
 					      ioend->io_size, ioend->io_type,
 					      imap);
 	} else if (type == XFS_IO_UNWRITTEN ||
-		   offset + size > i_size_read(inode)) {
+		   offset + size > i_size_read(inode) ||
+		   offset + size < 0) {
 		ioend = xfs_alloc_ioend(inode, type);
 		ioend->io_offset = offset;
 		ioend->io_size = size;

@@ -1354,7 +1380,8 @@ __xfs_get_blocks(
 	sector_t		iblock,
 	struct buffer_head	*bh_result,
 	int			create,
-	bool			direct)
+	bool			direct,
+	bool			dax_fault)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;

@@ -1467,7 +1494,8 @@ __xfs_get_blocks(
 			set_buffer_unwritten(bh_result);
 		/* direct IO needs special help */
 		if (create && direct)
-			xfs_map_direct(inode, bh_result, &imap, offset);
+			xfs_map_direct(inode, bh_result, &imap, offset,
+				       dax_fault);
 	}
 
 	/*

@@ -1514,7 +1542,7 @@ xfs_get_blocks(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, false);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, false, false);
 }
 
 int

@@ -1524,7 +1552,17 @@ xfs_get_blocks_direct(
 	struct buffer_head	*bh_result,
 	int			create)
 {
-	return __xfs_get_blocks(inode, iblock, bh_result, create, true);
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true, false);
+}
+
+int
+xfs_get_blocks_dax_fault(
+	struct inode		*inode,
+	sector_t		iblock,
+	struct buffer_head	*bh_result,
+	int			create)
+{
+	return __xfs_get_blocks(inode, iblock, bh_result, create, true, true);
 }
 
 static void

index 86afd1a..d39ba25 100644
@@ -58,6 +58,8 @@ int	xfs_get_blocks(struct inode *inode, sector_t offset,
 		       struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
+int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
+			         struct buffer_head *map_bh, int create);
 void	xfs_end_io_dax_write(struct buffer_head *bh, int uptodate);
 
 extern void xfs_count_page_state(struct page *, int *, int *);

index 2f7b6bd..7f873bc 100644
@@ -1508,7 +1508,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_direct,
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault,
 				    xfs_end_io_dax_write);
 	} else {
 		ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);

@@ -1543,7 +1543,7 @@ xfs_filemap_fault(
 		 * changes to xfs_get_blocks_direct() to map unwritten extent
 		 * ioend for conversion on read-only mappings.
 		 */
-		ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else
 		ret = filemap_fault(vma, vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);

@@ -1570,7 +1570,7 @@ xfs_filemap_pmd_fault(
 	sb_start_pagefault(inode->i_sb);
 	file_update_time(vma->vm_file);
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_direct,
+	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
 				    xfs_end_io_dax_write);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);

index e926197..3479294 100644
@@ -2509,7 +2509,7 @@ xfs_alloc_vextent(
 		 * Try near allocation first, then anywhere-in-ag after
 		 * the first a.g. fails.
 		 */
-		if ((args->userdata  == XFS_ALLOC_INITIAL_USER_DATA) &&
+		if ((args->userdata & XFS_ALLOC_INITIAL_USER_DATA) &&
 		    (mp->m_flags & XFS_MOUNT_32BITINODES)) {
 			args->fsbno = XFS_AGB_TO_FSB(mp,
 					((mp->m_agfrotor / rotorstep) %

@@ -2640,6 +2640,14 @@ xfs_alloc_vextent(
 		XFS_AG_CHECK_DADDR(mp, XFS_FSB_TO_DADDR(mp, args->fsbno),
 			args->len);
 #endif
+
+		/* Zero the extent if we were asked to do so */
+		if (args->userdata & XFS_ALLOC_USERDATA_ZERO) {
+			error = xfs_zero_extent(args->ip, args->fsbno, args->len);
+			if (error)
+				goto error0;
+		}
+
 	}
 	xfs_perag_put(args->pag);
 	return 0;

index ca1c816..0ecde4d 100644
@@ -101,6 +101,7 @@ typedef struct xfs_alloc_arg {
 	struct xfs_mount *mp;		/* file system mount point */
 	struct xfs_buf	*agbp;		/* buffer for a.g. freelist header */
 	struct xfs_perag *pag;		/* per-ag struct for this agno */
+	struct xfs_inode *ip;		/* for userdata zeroing method */
 	xfs_fsblock_t	fsbno;		/* file system block number */
 	xfs_agnumber_t	agno;		/* allocation group number */
 	xfs_agblock_t	agbno;		/* allocation group-relative block # */

@@ -120,15 +121,16 @@ typedef struct xfs_alloc_arg {
 	char		wasdel;		/* set if allocation was prev delayed */
 	char		wasfromfl;	/* set if allocation is from freelist */
 	char		isfl;		/* set if is freelist blocks - !acctg */
-	char		userdata;	/* set if this is user data */
+	char		userdata;	/* mask defining userdata treatment */
 	xfs_fsblock_t	firstblock;	/* io first block allocated */
 } xfs_alloc_arg_t;
 
 /*
  * Defines for userdata
  */
-#define XFS_ALLOC_USERDATA		1	/* allocation is for user data*/
-#define XFS_ALLOC_INITIAL_USER_DATA	2	/* special case start of file */
+#define XFS_ALLOC_USERDATA		(1 << 0)/* allocation is for user data*/
+#define XFS_ALLOC_INITIAL_USER_DATA	(1 << 1)/* special case start of file */
+#define XFS_ALLOC_USERDATA_ZERO		(1 << 2)/* zero extent on allocation */
 
 xfs_extlen_t xfs_alloc_longest_free_extent(struct xfs_mount *mp,
 		struct xfs_perag *pag, xfs_extlen_t need);

index ab92d10..119c242 100644
@@ -3802,8 +3802,13 @@ xfs_bmap_btalloc(
 	args.wasdel = ap->wasdel;
 	args.isfl = 0;
 	args.userdata = ap->userdata;
-	if ((error = xfs_alloc_vextent(&args)))
+	if (ap->userdata & XFS_ALLOC_USERDATA_ZERO)
+		args.ip = ap->ip;
+
+	error = xfs_alloc_vextent(&args);
+	if (error)
 		return error;
+
 	if (tryagain && args.fsbno == NULLFSBLOCK) {
 		/*
 		 * Exact allocation failed. Now try with alignment

@@ -4302,11 +4307,14 @@ xfs_bmapi_allocate(
 
 	/*
 	 * Indicate if this is the first user data in the file, or just any
-	 * user data.
+	 * user data. And if it is userdata, indicate whether it needs to
+	 * be initialised to zero during allocation.
 	 */
 	if (!(bma->flags & XFS_BMAPI_METADATA)) {
 		bma->userdata = (bma->offset == 0) ?
 			XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;
+		if (bma->flags & XFS_BMAPI_ZERO)
+			bma->userdata |= XFS_ALLOC_USERDATA_ZERO;
 	}
 
 	bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;

@@ -4421,6 +4429,17 @@ xfs_bmapi_convert_unwritten(
 	mval->br_state = (mval->br_state == XFS_EXT_UNWRITTEN)
 				? XFS_EXT_NORM : XFS_EXT_UNWRITTEN;
 
+	/*
+	 * Before insertion into the bmbt, zero the range being converted
+	 * if required.
+	 */
+	if (flags & XFS_BMAPI_ZERO) {
+		error = xfs_zero_extent(bma->ip, mval->br_startblock,
+					mval->br_blockcount);
+		if (error)
+			return error;
+	}
+
 	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx,
 			&bma->cur, mval, bma->firstblock, bma->flist,
 			&tmp_logflags);

@@ -4514,6 +4533,18 @@ xfs_bmapi_write(
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
+	/* zeroing is for currently only for data extents, not metadata */
+	ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) !=
+			(XFS_BMAPI_METADATA | XFS_BMAPI_ZERO));
+	/*
+	 * we can allocate unwritten extents or pre-zero allocated blocks,
+	 * but it makes no sense to do both at once. This would result in
+	 * zeroing the unwritten extent twice, but it still being an
+	 * unwritten extent....
+	 */
+	ASSERT((flags & (XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO)) !=
+			(XFS_BMAPI_PREALLOC | XFS_BMAPI_ZERO));
+
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),

index 6aaa0c1..a160f8a 100644
@@ -52,9 +52,9 @@ struct xfs_bmalloca {
 	xfs_extlen_t		minleft; /* amount must be left after alloc */
 	bool			eof;	/* set if allocating past last extent */
 	bool			wasdel;	/* replacing a delayed allocation */
-	bool			userdata;/* set if is user data */
 	bool			aeof;	/* allocated space at eof */
 	bool			conv;	/* overwriting unwritten extents */
+	char			userdata;/* userdata mask */
 	int			flags;
 };
 

@@ -109,6 +109,14 @@ typedef	struct xfs_bmap_free
  */
 #define XFS_BMAPI_CONVERT	0x040
 
+/*
+ * allocate zeroed extents - this requires all newly allocated user data extents
+ * to be initialised to zero. It will be ignored if XFS_BMAPI_METADATA is set.
+ * Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found
+ * during the allocation range to zeroed written extents.
+ */
+#define XFS_BMAPI_ZERO		0x080
+
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
 	{ XFS_BMAPI_METADATA,	"METADATA" }, \

@@ -116,7 +124,8 @@ typedef	struct xfs_bmap_free
 	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \
 	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \
 	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \
-	{ XFS_BMAPI_CONVERT,	"CONVERT" }
+	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \
+	{ XFS_BMAPI_ZERO,	"ZERO" }
 
 
 static inline int xfs_bmapi_aflag(int w)

index eca325e..dbae649 100644
@@ -57,6 +57,35 @@ xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 }
 
 /*
+ * Routine to zero an extent on disk allocated to the specific inode.
+ *
+ * The VFS functions take a linearised filesystem block offset, so we have to
+ * convert the sparse xfs fsb to the right format first.
+ * VFS types are real funky, too.
+ */
+int
+xfs_zero_extent(
+	struct xfs_inode *ip,
+	xfs_fsblock_t	start_fsb,
+	xfs_off_t	count_fsb)
+{
+	struct xfs_mount *mp = ip->i_mount;
+	xfs_daddr_t	sector = xfs_fsb_to_db(ip, start_fsb);
+	sector_t	block = XFS_BB_TO_FSBT(mp, sector);
+	ssize_t		size = XFS_FSB_TO_B(mp, count_fsb);
+
+	if (IS_DAX(VFS_I(ip)))
+		return dax_clear_blocks(VFS_I(ip), block, size);
+
+	/*
+	 * let the block layer decide on the fastest method of
+	 * implementing the zeroing.
+	 */
+	return sb_issue_zeroout(mp->m_super, block, count_fsb, GFP_NOFS);
+
+}
+
+/*
  * Routine to be called at transaction's end by xfs_bmapi, xfs_bunmapi
  * caller.  Frees all the extents that need freeing, which must be done
  * last due to locking considerations.  We never free any extents in

@@ -229,6 +258,13 @@ xfs_bmap_rtalloc(
 		xfs_trans_mod_dquot_byino(ap->tp, ap->ip,
 			ap->wasdel ? XFS_TRANS_DQ_DELRTBCOUNT :
 					XFS_TRANS_DQ_RTBCOUNT, (long) ralen);
+
+		/* Zero the extent if we were asked to do so */
+		if (ap->userdata & XFS_ALLOC_USERDATA_ZERO) {
+			error = xfs_zero_extent(ap->ip, ap->blkno, ap->length);
+			if (error)
+				return error;
+		}
 	} else {
 		ap->length = 0;
 	}

index 8795272..f20e5de 100644
@@ -337,4 +337,7 @@ extern int	xfs_dev_is_read_only(struct xfs_mount *, char *);
 
 extern void	xfs_set_low_space_thresholds(struct xfs_mount *);
 
+int	xfs_zero_extent(struct xfs_inode *ip, xfs_fsblock_t start_fsb,
+			xfs_off_t count_fsb);
+
 #endif	/* __XFS_MOUNT_H__ */

index a86d3cc..131fd35a 100644
@@ -29,6 +29,11 @@
 #include <linux/uio.h>
 #include <linux/vmstat.h>
 
+/*
+ * dax_clear_blocks() is called from within transaction context from XFS,
+ * and hence this means the stack from this point must follow GFP_NOFS
+ * semantics for all operations.
+ */
 int dax_clear_blocks(struct inode *inode, sector_t block, long size)
 {
 	struct block_device *bdev = inode->i_sb->s_bdev;

index 366e41eb..7b4f849 100644
@@ -1293,15 +1293,12 @@ xfs_map_direct(
 
 	trace_xfs_gbmap_direct(XFS_I(inode), offset, size, type, imap);
 
-	/* XXX: preparation for removing unwritten extents in DAX */
-#if 0
 	if (dax_fault) {
 		ASSERT(type == XFS_IO_OVERWRITE);
 		trace_xfs_gbmap_direct_none(XFS_I(inode), offset, size, type,
 					    imap);
 		return;
 	}
-#endif
 
 	if (bh_result->b_private) {
 		ioend = bh_result->b_private;

@@ -1429,10 +1426,12 @@ __xfs_get_blocks(
 	if (error)
 		goto out_unlock;
 
+	/* for DAX, we convert unwritten extents directly */
 	if (create &&
 	    (!nimaps ||
 	     (imap.br_startblock == HOLESTARTBLOCK ||
-	      imap.br_startblock == DELAYSTARTBLOCK))) {
+	      imap.br_startblock == DELAYSTARTBLOCK) ||
+	     (IS_DAX(inode) && ISUNWRITTEN(&imap)))) {
 		if (direct || xfs_get_extsz_hint(ip)) {
 			/*
 			 * xfs_iomap_write_direct() expects the shared lock. It

@@ -1477,6 +1476,12 @@ __xfs_get_blocks(
 		goto out_unlock;
 	}
 
+	if (IS_DAX(inode) && create) {
+		ASSERT(!ISUNWRITTEN(&imap));
+		/* zeroing is not needed at a higher layer */
+		new = 0;
+	}
+
 	/* trim mapping down to size requested */
 	if (direct || size > (1 << inode->i_blkbits))
 		xfs_map_trim_size(inode, iblock, bh_result,

index c3cb5a5..f4f5b43 100644
@@ -132,6 +132,7 @@ xfs_iomap_write_direct(
 	int		committed;
 	int		error;
 	int		lockmode;
+	int		bmapi_flags = XFS_BMAPI_PREALLOC;
 
 	rt = XFS_IS_REALTIME_INODE(ip);
 	extsz = xfs_get_extsz_hint(ip);

@@ -195,6 +196,23 @@ xfs_iomap_write_direct(
 	 * Allocate and setup the transaction
 	 */
 	tp = xfs_trans_alloc(mp, XFS_TRANS_DIOSTRAT);
+
+	/*
+	 * For DAX, we do not allocate unwritten extents, but instead we zero
+	 * the block before we commit the transaction.  Ideally we'd like to do
+	 * this outside the transaction context, but if we commit and then crash
+	 * we may not have zeroed the blocks and this will be exposed on
+	 * recovery of the allocation. Hence we must zero before commit.
+	 * Further, if we are mapping unwritten extents here, we need to zero
+	 * and convert them to written so that we don't need an unwritten extent
+	 * callback for DAX. This also means that we need to be able to dip into
+	 * the reserve block pool if there is no space left but we need to do
+	 * unwritten extent conversion.
+	 */
+	if (IS_DAX(VFS_I(ip))) {
+		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
+		tp->t_flags |= XFS_TRANS_RESERVE;
+	}
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_write,
 				  resblks, resrtextents);
 	/*

@@ -221,7 +239,7 @@ xfs_iomap_write_direct(
 	xfs_bmap_init(&free_list, &firstfsb);
 	nimaps = 1;
 	error = xfs_bmapi_write(tp, ip, offset_fsb, count_fsb,
-				XFS_BMAPI_PREALLOC, &firstfsb, resblks, imap,
+				bmapi_flags, &firstfsb, resblks, imap,
 				&nimaps, &free_list);
 	if (error)
 		goto out_bmap_cancel;

@@ -232,6 +250,7 @@ xfs_iomap_write_direct(
 	error = xfs_bmap_finish(&tp, &free_list, &committed);
 	if (error)
 		goto out_bmap_cancel;
+
 	error = xfs_trans_commit(tp);
 	if (error)
 		goto out_unlock;

index 7b4f849..29e7e5d 100644
@@ -1666,45 +1666,6 @@ xfs_end_io_direct_write(
 	__xfs_end_io_direct_write(inode, ioend, offset, size);
 }
 
-/*
- * For DAX we need a mapping buffer callback for unwritten extent conversion
- * when page faults allocate blocks and then zero them. Note that in this
- * case the mapping indicated by the ioend may extend beyond EOF. We most
- * definitely do not want to extend EOF here, so we trim back the ioend size to
- * EOF.
- */
-#ifdef CONFIG_FS_DAX
-void
-xfs_end_io_dax_write(
-	struct buffer_head	*bh,
-	int			uptodate)
-{
-	struct xfs_ioend	*ioend = bh->b_private;
-	struct inode		*inode = ioend->io_inode;
-	ssize_t			size = ioend->io_size;
-
-	ASSERT(IS_DAX(ioend->io_inode));
-
-	/* if there was an error zeroing, then don't convert it */
-	if (!uptodate)
-		ioend->io_error = -EIO;
-
-	/*
-	 * Trim update to EOF, so we don't extend EOF during unwritten extent
-	 * conversion of partial EOF blocks.
-	 */
-	spin_lock(&XFS_I(inode)->i_flags_lock);
-	if (ioend->io_offset + size > i_size_read(inode))
-		size = i_size_read(inode) - ioend->io_offset;
-	spin_unlock(&XFS_I(inode)->i_flags_lock);
-
-	__xfs_end_io_direct_write(inode, ioend, ioend->io_offset, size);
-
-}
-#else
-void xfs_end_io_dax_write(struct buffer_head *bh, int uptodate) { }
-#endif
-
 static inline ssize_t
 xfs_vm_do_dio(
 	struct inode		*inode,

index d39ba25..f6ffc9a 100644
@@ -60,7 +60,6 @@ int	xfs_get_blocks_direct(struct inode *inode, sector_t offset,
 			      struct buffer_head *map_bh, int create);
 int	xfs_get_blocks_dax_fault(struct inode *inode, sector_t offset,
 			         struct buffer_head *map_bh, int create);
-void	xfs_end_io_dax_write(struct buffer_head *bh, int uptodate);
 
 extern void xfs_count_page_state(struct page *, int *, int *);
 

index 7f873bc..403151a 100644
@@ -1508,8 +1508,7 @@ xfs_filemap_page_mkwrite(
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault,
-				    xfs_end_io_dax_write);
+		ret = __dax_mkwrite(vma, vmf, xfs_get_blocks_dax_fault, NULL);
 	} else {
 		ret = __block_page_mkwrite(vma, vmf, xfs_get_blocks);
 		ret = block_page_mkwrite_return(ret);

@@ -1571,7 +1570,7 @@ xfs_filemap_pmd_fault(
 	file_update_time(vma->vm_file);
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
-				    xfs_end_io_dax_write);
+			      NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);
 

index 403151a..e7cf9ec 100644
@@ -1577,11 +1577,46 @@ xfs_filemap_pmd_fault(
 	return ret;
 }
 
+/*
+ * pfn_mkwrite was originally inteneded to ensure we capture time stamp
+ * updates on write faults. In reality, it's need to serialise against
+ * truncate similar to page_mkwrite. Hence we open-code dax_pfn_mkwrite()
+ * here and cycle the XFS_MMAPLOCK_SHARED to ensure we serialise the fault
+ * barrier in place.
+ */
+static int
+xfs_filemap_pfn_mkwrite(
+	struct vm_area_struct	*vma,
+	struct vm_fault		*vmf)
+{
+
+	struct inode		*inode = file_inode(vma->vm_file);
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			ret = VM_FAULT_NOPAGE;
+	loff_t			size;
+
+	trace_xfs_filemap_pfn_mkwrite(ip);
+
+	sb_start_pagefault(inode->i_sb);
+	file_update_time(vma->vm_file);
+
+	/* check if the faulting page hasn't raced with truncate */
+	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
+	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	if (vmf->pgoff >= size)
+		ret = VM_FAULT_SIGBUS;
+	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	sb_end_pagefault(inode->i_sb);
+	return ret;
+
+}
+
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
 	.pmd_fault	= xfs_filemap_pmd_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
+	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
 };
 
 STATIC int

index 957f5cc..877079eb 100644
@@ -689,6 +689,7 @@ DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid);
 DEFINE_INODE_EVENT(xfs_filemap_fault);
 DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
+DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
 
 DECLARE_EVENT_CLASS(xfs_iref_class,
 	TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip),

index e7cf9ec..0045b0a 100644
@@ -1482,7 +1482,7 @@ xfs_file_llseek(
  *
  * mmap_sem (MM)
  *   sb_start_pagefault(vfs, freeze)
- *     i_mmap_lock (XFS - truncate serialisation)
+ *     i_mmaplock (XFS - truncate serialisation)
  *       page_lock (MM)
  *         i_lock (XFS - extent map serialisation)
  */

@@ -1550,6 +1550,13 @@ xfs_filemap_fault(
 	return ret;
 }
 
+/*
+ * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
+ * both read and write faults. Hence we need to handle both cases. There is no
+ * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * handle both cases here. @flags carries the information on the type of fault
+ * occuring.
+ */
 STATIC int
 xfs_filemap_pmd_fault(
 	struct vm_area_struct	*vma,

@@ -1566,13 +1573,18 @@ xfs_filemap_pmd_fault(
 
 	trace_xfs_filemap_pmd_fault(ip);
 
-	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	if (flags & FAULT_FLAG_WRITE) {
+		sb_start_pagefault(inode->i_sb);
+		file_update_time(vma->vm_file);
+	}
+
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	ret = __dax_pmd_fault(vma, addr, pmd, flags, xfs_get_blocks_dax_fault,
 			      NULL);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	sb_end_pagefault(inode->i_sb);
+
+	if (flags & FAULT_FLAG_WRITE)
+		sb_end_pagefault(inode->i_sb);
 
 	return ret;
 }

index 0045b0a..39743ef 100644
@@ -242,19 +242,30 @@ xfs_file_fsync(
 	}
 
 	/*
-	 * All metadata updates are logged, which means that we just have
-	 * to flush the log up to the latest LSN that touched the inode.
+	 * All metadata updates are logged, which means that we just have to
+	 * flush the log up to the latest LSN that touched the inode. If we have
+	 * concurrent fsync/fdatasync() calls, we need them to all block on the
+	 * log force before we clear the ili_fsync_fields field. This ensures
+	 * that we don't get a racing sync operation that does not wait for the
+	 * metadata to hit the journal before returning. If we race with
+	 * clearing the ili_fsync_fields, then all that will happen is the log
+	 * force will do nothing as the lsn will already be on disk. We can't
+	 * race with setting ili_fsync_fields because that is done under
+	 * XFS_ILOCK_EXCL, and that can't happen because we hold the lock shared
+	 * until after the ili_fsync_fields is cleared.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	if (xfs_ipincount(ip)) {
 		if (!datasync ||
-		    (ip->i_itemp->ili_fields & ~XFS_ILOG_TIMESTAMP))
+		    (ip->i_itemp->ili_fsync_fields & ~XFS_ILOG_TIMESTAMP))
 			lsn = ip->i_itemp->ili_last_lsn;
 	}
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
-	if (lsn)
+	if (lsn) {
 		error = _xfs_log_force_lsn(mp, lsn, XFS_LOG_SYNC, &log_flushed);
+		ip->i_itemp->ili_fsync_fields = 0;
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 	/*
 	 * If we only have a single device, and the log force about was

index a0f2bae..8ee3939 100644
@@ -2365,6 +2365,7 @@ retry:
 
 			iip->ili_last_fields = iip->ili_fields;
 			iip->ili_fields = 0;
+			iip->ili_fsync_fields = 0;
 			iip->ili_logged = 1;
 			xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,
 						&iip->ili_item.li_lsn);

@@ -3560,6 +3561,7 @@ xfs_iflush_int(
 	 */
 	iip->ili_last_fields = iip->ili_fields;
 	iip->ili_fields = 0;
+	iip->ili_fsync_fields = 0;
 	iip->ili_logged = 1;
 
 	xfs_trans_ail_copy_lsn(mp->m_ail, &iip->ili_flush_lsn,

index 62bd80f..d14b12b 100644
@@ -719,6 +719,7 @@ xfs_iflush_abort(
 		 * attempted.
 		 */
 		iip->ili_fields = 0;
+		iip->ili_fsync_fields = 0;
 	}
 	/*
 	 * Release the inode's flush lock since we're done with it.

index 488d812..4c7722e 100644
@@ -34,6 +34,7 @@ typedef struct xfs_inode_log_item {
 	unsigned short		ili_logged;	   /* flushed logged data */
 	unsigned int		ili_last_fields;   /* fields when flushed */
 	unsigned int		ili_fields;	   /* fields to be logged */
+	unsigned int		ili_fsync_fields;  /* logged since last fsync */
 } xfs_inode_log_item_t;
 
 static inline int xfs_inode_clean(xfs_inode_t *ip)

index 17280cd..b97f1df 100644
@@ -108,6 +108,15 @@ xfs_trans_log_inode(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	/*
+	 * Record the specific change for fdatasync optimisation. This
+	 * allows fdatasync to skip log forces for inodes that are only
+	 * timestamp dirty. We do this before the change count so that
+	 * the core being logged in this case does not impact on fdatasync
+	 * behaviour.
+	 */
+	ip->i_itemp->ili_fsync_fields |= flags;
+
+	/*
 	 * First time we log the inode in a transaction, bump the inode change
 	 * counter if it is configured for this to occur. We don't use
 	 * inode_inc_version() because there is no need for extra locking around