Merge branch 'xfs-4.10-misc-fixes-2' into iomap-4.10-directio

fs/iomap.c

@@ -433,8 +433,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	struct page *page = data;
 	int ret;
 
-	ret = __block_write_begin_int(page, pos & ~PAGE_MASK, length,
-			NULL, iomap);
+	ret = __block_write_begin_int(page, pos, length, NULL, iomap);
 	if (ret)
 		return ret;
 
@@ -562,7 +561,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 	}
 
 	while (len > 0) {
-		ret = iomap_apply(inode, start, len, 0, ops, &ctx,
+		ret = iomap_apply(inode, start, len, IOMAP_REPORT, ops, &ctx,
 				iomap_fiemap_actor);
 		/* inode with no (attribute) mapping will give ENOENT */
 		if (ret == -ENOENT)

fs/xfs/libxfs/xfs_bmap.c

@@ -49,6 +49,8 @@
 #include "xfs_rmap.h"
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_icache.h"
 
 
 kmem_zone_t		*xfs_bmap_free_item_zone;
@@ -190,8 +192,12 @@ xfs_bmap_worst_indlen(
 	int		maxrecs;	/* maximum record count at this level */
 	xfs_mount_t	*mp;		/* mount structure */
 	xfs_filblks_t	rval;		/* return value */
+	xfs_filblks_t   orig_len;
 
 	mp = ip->i_mount;
+
+	/* Calculate the worst-case size of the bmbt. */
+	orig_len = len;
 	maxrecs = mp->m_bmap_dmxr[0];
 	for (level = 0, rval = 0;
 	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
@@ -199,12 +205,20 @@ xfs_bmap_worst_indlen(
 		len += maxrecs - 1;
 		do_div(len, maxrecs);
 		rval += len;
-		if (len == 1)
-			return rval + XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
+		if (len == 1) {
+			rval += XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK) -
 				level - 1;
+			break;
+		}
 		if (level == 0)
 			maxrecs = mp->m_bmap_dmxr[1];
 	}
+
+	/* Calculate the worst-case size of the rmapbt. */
+	if (xfs_sb_version_hasrmapbt(&mp->m_sb))
+		rval += 1 + xfs_rmapbt_calc_size(mp, orig_len) +
+				mp->m_rmap_maxlevels;
+
 	return rval;
 }
 
@@ -515,7 +529,7 @@ xfs_bmap_trace_exlist(
 		state |= BMAP_ATTRFORK;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	ASSERT(cnt == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
+	ASSERT(cnt == xfs_iext_count(ifp));
 	for (idx = 0; idx < cnt; idx++)
 		trace_xfs_extlist(ip, idx, whichfork, caller_ip);
 }
@@ -811,7 +825,7 @@ xfs_bmap_extents_to_btree(
 				XFS_BTREE_LONG_PTRS);
 
 	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents =  xfs_iext_count(ifp);
 	for (cnt = i = 0; i < nextents; i++) {
 		ep = xfs_iext_get_ext(ifp, i);
 		if (!isnullstartblock(xfs_bmbt_get_startblock(ep))) {
@@ -1296,7 +1310,7 @@ xfs_bmap_read_extents(
 	/*
 	 * Here with bp and block set to the leftmost leaf node in the tree.
 	 */
-	room = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	room = xfs_iext_count(ifp);
 	i = 0;
 	/*
 	 * Loop over all leaf nodes.  Copy information to the extent records.
@@ -1361,7 +1375,7 @@ xfs_bmap_read_extents(
 			return error;
 		block = XFS_BUF_TO_BLOCK(bp);
 	}
-	ASSERT(i == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)));
+	ASSERT(i == xfs_iext_count(ifp));
 	ASSERT(i == XFS_IFORK_NEXTENTS(ip, whichfork));
 	XFS_BMAP_TRACE_EXLIST(ip, i, whichfork);
 	return 0;
@@ -1370,97 +1384,6 @@ xfs_bmap_read_extents(
 	return -EFSCORRUPTED;
 }
 
-
-/*
- * Search the extent records for the entry containing block bno.
- * If bno lies in a hole, point to the next entry.  If bno lies
- * past eof, *eofp will be set, and *prevp will contain the last
- * entry (null if none).  Else, *lastxp will be set to the index
- * of the found entry; *gotp will contain the entry.
- */
-STATIC xfs_bmbt_rec_host_t *		/* pointer to found extent entry */
-xfs_bmap_search_multi_extents(
-	xfs_ifork_t	*ifp,		/* inode fork pointer */
-	xfs_fileoff_t	bno,		/* block number searched for */
-	int		*eofp,		/* out: end of file found */
-	xfs_extnum_t	*lastxp,	/* out: last extent index */
-	xfs_bmbt_irec_t	*gotp,		/* out: extent entry found */
-	xfs_bmbt_irec_t	*prevp)		/* out: previous extent entry found */
-{
-	xfs_bmbt_rec_host_t *ep;		/* extent record pointer */
-	xfs_extnum_t	lastx;		/* last extent index */
-
-	/*
-	 * Initialize the extent entry structure to catch access to
-	 * uninitialized br_startblock field.
-	 */
-	gotp->br_startoff = 0xffa5a5a5a5a5a5a5LL;
-	gotp->br_blockcount = 0xa55a5a5a5a5a5a5aLL;
-	gotp->br_state = XFS_EXT_INVALID;
-	gotp->br_startblock = 0xffffa5a5a5a5a5a5LL;
-	prevp->br_startoff = NULLFILEOFF;
-
-	ep = xfs_iext_bno_to_ext(ifp, bno, &lastx);
-	if (lastx > 0) {
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx - 1), prevp);
-	}
-	if (lastx < (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))) {
-		xfs_bmbt_get_all(ep, gotp);
-		*eofp = 0;
-	} else {
-		if (lastx > 0) {
-			*gotp = *prevp;
-		}
-		*eofp = 1;
-		ep = NULL;
-	}
-	*lastxp = lastx;
-	return ep;
-}
-
-/*
- * Search the extents list for the inode, for the extent containing bno.
- * If bno lies in a hole, point to the next entry.  If bno lies past eof,
- * *eofp will be set, and *prevp will contain the last entry (null if none).
- * Else, *lastxp will be set to the index of the found
- * entry; *gotp will contain the entry.
- */
-xfs_bmbt_rec_host_t *                 /* pointer to found extent entry */
-xfs_bmap_search_extents(
-	xfs_inode_t     *ip,            /* incore inode pointer */
-	xfs_fileoff_t   bno,            /* block number searched for */
-	int             fork,      	/* data or attr fork */
-	int             *eofp,          /* out: end of file found */
-	xfs_extnum_t    *lastxp,        /* out: last extent index */
-	xfs_bmbt_irec_t *gotp,          /* out: extent entry found */
-	xfs_bmbt_irec_t *prevp)         /* out: previous extent entry found */
-{
-	xfs_ifork_t	*ifp;		/* inode fork pointer */
-	xfs_bmbt_rec_host_t  *ep;            /* extent record pointer */
-
-	XFS_STATS_INC(ip->i_mount, xs_look_exlist);
-	ifp = XFS_IFORK_PTR(ip, fork);
-
-	ep = xfs_bmap_search_multi_extents(ifp, bno, eofp, lastxp, gotp, prevp);
-
-	if (unlikely(!(gotp->br_startblock) && (*lastxp != NULLEXTNUM) &&
-		     !(XFS_IS_REALTIME_INODE(ip) && fork == XFS_DATA_FORK))) {
-		xfs_alert_tag(ip->i_mount, XFS_PTAG_FSBLOCK_ZERO,
-				"Access to block zero in inode %llu "
-				"start_block: %llx start_off: %llx "
-				"blkcnt: %llx extent-state: %x lastx: %x",
-			(unsigned long long)ip->i_ino,
-			(unsigned long long)gotp->br_startblock,
-			(unsigned long long)gotp->br_startoff,
-			(unsigned long long)gotp->br_blockcount,
-			gotp->br_state, *lastxp);
-		*lastxp = NULLEXTNUM;
-		*eofp = 1;
-		return NULL;
-	}
-	return ep;
-}
-
 /*
  * Returns the file-relative block number of the first unused block(s)
  * in the file with at least "len" logically contiguous blocks free.
@@ -1497,7 +1420,7 @@ xfs_bmap_first_unused(
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;
 	lowest = *first_unused;
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	for (idx = 0, lastaddr = 0, max = lowest; idx < nextents; idx++) {
 		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx);
 		off = xfs_bmbt_get_startoff(ep);
@@ -1523,44 +1446,44 @@ xfs_bmap_first_unused(
  */
 int						/* error */
 xfs_bmap_last_before(
-	xfs_trans_t	*tp,			/* transaction pointer */
-	xfs_inode_t	*ip,			/* incore inode */
-	xfs_fileoff_t	*last_block,		/* last block */
-	int		whichfork)		/* data or attr fork */
+	struct xfs_trans	*tp,		/* transaction pointer */
+	struct xfs_inode	*ip,		/* incore inode */
+	xfs_fileoff_t		*last_block,	/* last block */
+	int			whichfork)	/* data or attr fork */
 {
-	xfs_fileoff_t	bno;			/* input file offset */
-	int		eof;			/* hit end of file */
-	xfs_bmbt_rec_host_t *ep;		/* pointer to last extent */
-	int		error;			/* error return value */
-	xfs_bmbt_irec_t	got;			/* current extent value */
-	xfs_ifork_t	*ifp;			/* inode fork pointer */
-	xfs_extnum_t	lastx;			/* last extent used */
-	xfs_bmbt_irec_t	prev;			/* previous extent value */
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_bmbt_irec	got;
+	xfs_extnum_t		idx;
+	int			error;
 
-	if (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE &&
-	    XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
-	    XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL)
-	       return -EIO;
-	if (XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_LOCAL) {
+	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
+	case XFS_DINODE_FMT_LOCAL:
 		*last_block = 0;
 		return 0;
+	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_EXTENTS:
+		break;
+	default:
+		return -EIO;
 	}
-	ifp = XFS_IFORK_PTR(ip, whichfork);
-	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
-	    (error = xfs_iread_extents(tp, ip, whichfork)))
-		return error;
-	bno = *last_block - 1;
-	ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got,
-		&prev);
-	if (eof || xfs_bmbt_get_startoff(ep) > bno) {
-		if (prev.br_startoff == NULLFILEOFF)
-			*last_block = 0;
-		else
-			*last_block = prev.br_startoff + prev.br_blockcount;
+
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(tp, ip, whichfork);
+		if (error)
+			return error;
 	}
-	/*
-	 * Otherwise *last_block is already the right answer.
-	 */
+
+	if (xfs_iext_lookup_extent(ip, ifp, *last_block - 1, &idx, &got)) {
+		if (got.br_startoff <= *last_block - 1)
+			return 0;
+	}
+
+	if (xfs_iext_get_extent(ifp, idx - 1, &got)) {
+		*last_block = got.br_startoff + got.br_blockcount;
+		return 0;
+	}
+
+	*last_block = 0;
 	return 0;
 }
 
@@ -1582,7 +1505,7 @@ xfs_bmap_last_extent(
 			return error;
 	}
 
-	nextents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	if (nextents == 0) {
 		*is_empty = 1;
 		return 0;
@@ -1735,7 +1658,7 @@ xfs_bmap_add_extent_delay_real(
 						&bma->ip->i_d.di_nextents);
 
 	ASSERT(bma->idx >= 0);
-	ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(bma->idx <= xfs_iext_count(ifp));
 	ASSERT(!isnullstartblock(new->br_startblock));
 	ASSERT(!bma->cur ||
 	       (bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
@@ -1794,7 +1717,7 @@ xfs_bmap_add_extent_delay_real(
 	 * Don't set contiguous if the combined extent would be too large.
 	 * Also check for all-three-contiguous being too large.
 	 */
-	if (bma->idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
+	if (bma->idx < xfs_iext_count(ifp) - 1) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx + 1), &RIGHT);
 
@@ -2300,7 +2223,7 @@ xfs_bmap_add_extent_unwritten_real(
 	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
 
 	ASSERT(*idx >= 0);
-	ASSERT(*idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(*idx <= xfs_iext_count(ifp));
 	ASSERT(!isnullstartblock(new->br_startblock));
 
 	XFS_STATS_INC(mp, xs_add_exlist);
@@ -2356,7 +2279,7 @@ xfs_bmap_add_extent_unwritten_real(
 	 * Don't set contiguous if the combined extent would be too large.
 	 * Also check for all-three-contiguous being too large.
 	 */
-	if (*idx < ip->i_df.if_bytes / (uint)sizeof(xfs_bmbt_rec_t) - 1) {
+	if (*idx < xfs_iext_count(&ip->i_df) - 1) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT);
 		if (isnullstartblock(RIGHT.br_startblock))
@@ -2836,7 +2759,7 @@ xfs_bmap_add_extent_hole_delay(
 	 * Check and set flags if the current (right) segment exists.
 	 * If it doesn't exist, we're converting the hole at end-of-file.
 	 */
-	if (*idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)) {
+	if (*idx < xfs_iext_count(ifp)) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &right);
 
@@ -2966,7 +2889,7 @@ xfs_bmap_add_extent_hole_real(
 	ifp = XFS_IFORK_PTR(bma->ip, whichfork);
 
 	ASSERT(bma->idx >= 0);
-	ASSERT(bma->idx <= ifp->if_bytes / sizeof(struct xfs_bmbt_rec));
+	ASSERT(bma->idx <= xfs_iext_count(ifp));
 	ASSERT(!isnullstartblock(new->br_startblock));
 	ASSERT(!bma->cur ||
 	       !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
@@ -2992,7 +2915,7 @@ xfs_bmap_add_extent_hole_real(
 	 * Check and set flags if this segment has a current value.
 	 * Not true if we're inserting into the "hole" at eof.
 	 */
-	if (bma->idx < ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t)) {
+	if (bma->idx < xfs_iext_count(ifp)) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx), &right);
 		if (isnullstartblock(right.br_startblock))
@@ -3974,9 +3897,6 @@ xfs_bmap_remap_alloc(
 	 * allocating, so skip that check by pretending to be freeing.
 	 */
 	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
-	if (error)
-		goto error0;
-error0:
 	xfs_perag_put(args.pag);
 	if (error)
 		trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_);
@@ -3999,6 +3919,39 @@ xfs_bmap_alloc(
 	return xfs_bmap_btalloc(ap);
 }
 
+/* Trim extent to fit a logical block range. */
+void
+xfs_trim_extent(
+	struct xfs_bmbt_irec	*irec,
+	xfs_fileoff_t		bno,
+	xfs_filblks_t		len)
+{
+	xfs_fileoff_t		distance;
+	xfs_fileoff_t		end = bno + len;
+
+	if (irec->br_startoff + irec->br_blockcount <= bno ||
+	    irec->br_startoff >= end) {
+		irec->br_blockcount = 0;
+		return;
+	}
+
+	if (irec->br_startoff < bno) {
+		distance = bno - irec->br_startoff;
+		if (isnullstartblock(irec->br_startblock))
+			irec->br_startblock = DELAYSTARTBLOCK;
+		if (irec->br_startblock != DELAYSTARTBLOCK &&
+		    irec->br_startblock != HOLESTARTBLOCK)
+			irec->br_startblock += distance;
+		irec->br_startoff += distance;
+		irec->br_blockcount -= distance;
+	}
+
+	if (end < irec->br_startoff + irec->br_blockcount) {
+		distance = irec->br_startoff + irec->br_blockcount - end;
+		irec->br_blockcount -= distance;
+	}
+}
+
 /*
  * Trim the returned map to the required bounds
  */
@@ -4115,12 +4068,11 @@ xfs_bmapi_read(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp;
 	struct xfs_bmbt_irec	got;
-	struct xfs_bmbt_irec	prev;
 	xfs_fileoff_t		obno;
 	xfs_fileoff_t		end;
-	xfs_extnum_t		lastx;
+	xfs_extnum_t		idx;
 	int			error;
-	int			eof;
+	bool			eof = false;
 	int			n = 0;
 	int			whichfork = xfs_bmapi_whichfork(flags);
 
@@ -4160,7 +4112,8 @@ xfs_bmapi_read(
 			return error;
 	}
 
-	xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got, &prev);
+	if (!xfs_iext_lookup_extent(ip, ifp, bno, &idx, &got))
+		eof = true;
 	end = bno + len;
 	obno = bno;
 
@@ -4191,10 +4144,8 @@ xfs_bmapi_read(
 			break;
 
 		/* Else go on to the next record. */
-		if (++lastx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
-			xfs_bmbt_get_all(xfs_iext_get_ext(ifp, lastx), &got);
-		else
-			eof = 1;
+		if (!xfs_iext_get_extent(ifp, ++idx, &got))
+			eof = true;
 	}
 	*nmap = n;
 	return 0;
@@ -4204,10 +4155,10 @@ int
 xfs_bmapi_reserve_delalloc(
 	struct xfs_inode	*ip,
 	int			whichfork,
-	xfs_fileoff_t		aoff,
+	xfs_fileoff_t		off,
 	xfs_filblks_t		len,
+	xfs_filblks_t		prealloc,
 	struct xfs_bmbt_irec	*got,
-	struct xfs_bmbt_irec	*prev,
 	xfs_extnum_t		*lastx,
 	int			eof)
 {
@@ -4218,10 +4169,17 @@ xfs_bmapi_reserve_delalloc(
 	char			rt = XFS_IS_REALTIME_INODE(ip);
 	xfs_extlen_t		extsz;
 	int			error;
+	xfs_fileoff_t		aoff = off;
 
-	alen = XFS_FILBLKS_MIN(len, MAXEXTLEN);
+	/*
+	 * Cap the alloc length. Keep track of prealloc so we know whether to
+	 * tag the inode before we return.
+	 */
+	alen = XFS_FILBLKS_MIN(len + prealloc, MAXEXTLEN);
 	if (!eof)
 		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
+	if (prealloc && alen >= len)
+		prealloc = alen - len;
 
 	/* Figure out the extent size, adjust alen */
 	if (whichfork == XFS_COW_FORK)
@@ -4229,7 +4187,12 @@ xfs_bmapi_reserve_delalloc(
 	else
 		extsz = xfs_get_extsz_hint(ip);
 	if (extsz) {
-		error = xfs_bmap_extsize_align(mp, got, prev, extsz, rt, eof,
+		struct xfs_bmbt_irec	prev;
+
+		if (!xfs_iext_get_extent(ifp, *lastx - 1, &prev))
+			prev.br_startoff = NULLFILEOFF;
+
+		error = xfs_bmap_extsize_align(mp, got, &prev, extsz, rt, eof,
 					       1, 0, &aoff, &alen);
 		ASSERT(!error);
 	}
@@ -4282,6 +4245,16 @@ xfs_bmapi_reserve_delalloc(
 	 */
 	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
 
+	/*
+	 * Tag the inode if blocks were preallocated. Note that COW fork
+	 * preallocation can occur at the start or end of the extent, even when
+	 * prealloc == 0, so we must also check the aligned offset and length.
+	 */
+	if (whichfork == XFS_DATA_FORK && prealloc)
+		xfs_inode_set_eofblocks_tag(ip);
+	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));
@@ -4319,7 +4292,7 @@ xfs_bmapi_allocate(
 	if (bma->wasdel) {
 		bma->length = (xfs_extlen_t)bma->got.br_blockcount;
 		bma->offset = bma->got.br_startoff;
-		if (bma->idx != NULLEXTNUM && bma->idx) {
+		if (bma->idx) {
 			xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx - 1),
 					 &bma->prev);
 		}
@@ -4533,7 +4506,7 @@ xfs_bmapi_write(
 	struct xfs_ifork	*ifp;
 	struct xfs_bmalloca	bma = { NULL };	/* args for xfs_bmap_alloc */
 	xfs_fileoff_t		end;		/* end of mapped file region */
-	int			eof;		/* after the end of extents */
+	bool			eof = false;	/* after the end of extents */
 	int			error;		/* error return */
 	int			n;		/* current extent index */
 	xfs_fileoff_t		obno;		/* old block number (offset) */
@@ -4611,12 +4584,14 @@ xfs_bmapi_write(
 			goto error0;
 	}
 
-	xfs_bmap_search_extents(ip, bno, whichfork, &eof, &bma.idx, &bma.got,
-				&bma.prev);
 	n = 0;
 	end = bno + len;
 	obno = bno;
 
+	if (!xfs_iext_lookup_extent(ip, ifp, bno, &bma.idx, &bma.got))
+		eof = true;
+	if (!xfs_iext_get_extent(ifp, bma.idx - 1, &bma.prev))
+		bma.prev.br_startoff = NULLFILEOFF;
 	bma.tp = tp;
 	bma.ip = ip;
 	bma.total = total;
@@ -4703,11 +4678,8 @@ xfs_bmapi_write(
 
 		/* Else go on to the next record. */
 		bma.prev = bma.got;
-		if (++bma.idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t)) {
-			xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma.idx),
-					 &bma.got);
-		} else
-			eof = 1;
+		if (!xfs_iext_get_extent(ifp, ++bma.idx, &bma.got))
+			eof = true;
 	}
 	*nmap = n;
 
@@ -4829,6 +4801,219 @@ xfs_bmap_split_indlen(
 	return stolen;
 }
 
+int
+xfs_bmap_del_extent_delay(
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_extnum_t		*idx,
+	struct xfs_bmbt_irec	*got,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_bmbt_irec	new;
+	int64_t			da_old, da_new, da_diff = 0;
+	xfs_fileoff_t		del_endoff, got_endoff;
+	xfs_filblks_t		got_indlen, new_indlen, stolen;
+	int			error = 0, state = 0;
+	bool			isrt;
+
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got->br_startoff + got->br_blockcount;
+	da_old = startblockval(got->br_startblock);
+	da_new = 0;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx <= xfs_iext_count(ifp));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got->br_startoff <= del->br_startoff);
+	ASSERT(got_endoff >= del_endoff);
+
+	if (isrt) {
+		int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount);
+
+		do_div(rtexts, mp->m_sb.sb_rextsize);
+		xfs_mod_frextents(mp, rtexts);
+	}
+
+	/*
+	 * Update the inode delalloc counter now and wait to update the
+	 * sb counters as we might have to borrow some blocks for the
+	 * indirect block accounting.
+	 */
+	xfs_trans_reserve_quota_nblks(NULL, ip, -((long)del->br_blockcount), 0,
+			isrt ? XFS_QMOPT_RES_RTBLKS : XFS_QMOPT_RES_REGBLKS);
+	ip->i_delayed_blks -= del->br_blockcount;
+
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
+
+	if (got->br_startoff == del->br_startoff)
+		state |= BMAP_LEFT_CONTIG;
+	if (got_endoff == del_endoff)
+		state |= BMAP_RIGHT_CONTIG;
+
+	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, *idx, 1, state);
+		--*idx;
+		break;
+	case BMAP_LEFT_CONTIG:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_startoff = del_endoff;
+		got->br_blockcount -= del->br_blockcount;
+		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+				got->br_blockcount), da_old);
+		got->br_startblock = nullstartblock((int)da_new);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case BMAP_RIGHT_CONTIG:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount = got->br_blockcount - del->br_blockcount;
+		da_new = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip,
+				got->br_blockcount), da_old);
+		got->br_startblock = nullstartblock((int)da_new);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 *
+		 * Distribute the original indlen reservation across the two new
+		 * extents.  Steal blocks from the deleted extent if necessary.
+		 * Stealing blocks simply fudges the fdblocks accounting below.
+		 * Warn if either of the new indlen reservations is zero as this
+		 * can lead to delalloc problems.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+
+		got->br_blockcount = del->br_startoff - got->br_startoff;
+		got_indlen = xfs_bmap_worst_indlen(ip, got->br_blockcount);
+
+		new.br_blockcount = got_endoff - del_endoff;
+		new_indlen = xfs_bmap_worst_indlen(ip, new.br_blockcount);
+
+		WARN_ON_ONCE(!got_indlen || !new_indlen);
+		stolen = xfs_bmap_split_indlen(da_old, &got_indlen, &new_indlen,
+						       del->br_blockcount);
+
+		got->br_startblock = nullstartblock((int)got_indlen);
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, 0, _THIS_IP_);
+
+		new.br_startoff = del_endoff;
+		new.br_state = got->br_state;
+		new.br_startblock = nullstartblock((int)new_indlen);
+
+		++*idx;
+		xfs_iext_insert(ip, *idx, 1, &new, state);
+
+		da_new = got_indlen + new_indlen - stolen;
+		del->br_blockcount -= stolen;
+		break;
+	}
+
+	ASSERT(da_old >= da_new);
+	da_diff = da_old - da_new;
+	if (!isrt)
+		da_diff += del->br_blockcount;
+	if (da_diff)
+		xfs_mod_fdblocks(mp, da_diff, false);
+	return error;
+}
+
+void
+xfs_bmap_del_extent_cow(
+	struct xfs_inode	*ip,
+	xfs_extnum_t		*idx,
+	struct xfs_bmbt_irec	*got,
+	struct xfs_bmbt_irec	*del)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec	new;
+	xfs_fileoff_t		del_endoff, got_endoff;
+	int			state = BMAP_COWFORK;
+
+	XFS_STATS_INC(mp, xs_del_exlist);
+
+	del_endoff = del->br_startoff + del->br_blockcount;
+	got_endoff = got->br_startoff + got->br_blockcount;
+
+	ASSERT(*idx >= 0);
+	ASSERT(*idx <= xfs_iext_count(ifp));
+	ASSERT(del->br_blockcount > 0);
+	ASSERT(got->br_startoff <= del->br_startoff);
+	ASSERT(got_endoff >= del_endoff);
+	ASSERT(!isnullstartblock(got->br_startblock));
+
+	if (got->br_startoff == del->br_startoff)
+		state |= BMAP_LEFT_CONTIG;
+	if (got_endoff == del_endoff)
+		state |= BMAP_RIGHT_CONTIG;
+
+	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
+	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
+		/*
+		 * Matches the whole extent.  Delete the entry.
+		 */
+		xfs_iext_remove(ip, *idx, 1, state);
+		--*idx;
+		break;
+	case BMAP_LEFT_CONTIG:
+		/*
+		 * Deleting the first part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_startoff = del_endoff;
+		got->br_blockcount -= del->br_blockcount;
+		got->br_startblock = del->br_startblock + del->br_blockcount;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case BMAP_RIGHT_CONTIG:
+		/*
+		 * Deleting the last part of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount -= del->br_blockcount;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+		break;
+	case 0:
+		/*
+		 * Deleting the middle of the extent.
+		 */
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		got->br_blockcount = del->br_startoff - got->br_startoff;
+		xfs_bmbt_set_all(xfs_iext_get_ext(ifp, *idx), got);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
+
+		new.br_startoff = del_endoff;
+		new.br_blockcount = got_endoff - del_endoff;
+		new.br_state = got->br_state;
+		new.br_startblock = del->br_startblock + del->br_blockcount;
+
+		++*idx;
+		xfs_iext_insert(ip, *idx, 1, &new, state);
+		break;
+	}
+}
+
 /*
  * Called by xfs_bmapi to update file extent records and the btree
  * after removing space (or undoing a delayed allocation).
@@ -4876,8 +5061,7 @@ xfs_bmap_del_extent(
 		state |= BMAP_COWFORK;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	ASSERT((*idx >= 0) && (*idx < ifp->if_bytes /
-		(uint)sizeof(xfs_bmbt_rec_t)));
+	ASSERT((*idx >= 0) && (*idx < xfs_iext_count(ifp)));
 	ASSERT(del->br_blockcount > 0);
 	ep = xfs_iext_get_ext(ifp, *idx);
 	xfs_bmbt_get_all(ep, &got);
@@ -5171,175 +5355,6 @@ xfs_bmap_del_extent(
 	return error;
 }
 
-/* Remove an extent from the CoW fork.  Similar to xfs_bmap_del_extent. */
-int
-xfs_bunmapi_cow(
-	struct xfs_inode		*ip,
-	struct xfs_bmbt_irec		*del)
-{
-	xfs_filblks_t			da_new;
-	xfs_filblks_t			da_old;
-	xfs_fsblock_t			del_endblock = 0;
-	xfs_fileoff_t			del_endoff;
-	int				delay;
-	struct xfs_bmbt_rec_host	*ep;
-	int				error;
-	struct xfs_bmbt_irec		got;
-	xfs_fileoff_t			got_endoff;
-	struct xfs_ifork		*ifp;
-	struct xfs_mount		*mp;
-	xfs_filblks_t			nblks;
-	struct xfs_bmbt_irec		new;
-	/* REFERENCED */
-	uint				qfield;
-	xfs_filblks_t			temp;
-	xfs_filblks_t			temp2;
-	int				state = BMAP_COWFORK;
-	int				eof;
-	xfs_extnum_t			eidx;
-
-	mp = ip->i_mount;
-	XFS_STATS_INC(mp, xs_del_exlist);
-
-	ep = xfs_bmap_search_extents(ip, del->br_startoff, XFS_COW_FORK, &eof,
-			&eidx, &got, &new);
-
-	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK); ifp = ifp;
-	ASSERT((eidx >= 0) && (eidx < ifp->if_bytes /
-		(uint)sizeof(xfs_bmbt_rec_t)));
-	ASSERT(del->br_blockcount > 0);
-	ASSERT(got.br_startoff <= del->br_startoff);
-	del_endoff = del->br_startoff + del->br_blockcount;
-	got_endoff = got.br_startoff + got.br_blockcount;
-	ASSERT(got_endoff >= del_endoff);
-	delay = isnullstartblock(got.br_startblock);
-	ASSERT(isnullstartblock(del->br_startblock) == delay);
-	qfield = 0;
-	error = 0;
-	/*
-	 * If deleting a real allocation, must free up the disk space.
-	 */
-	if (!delay) {
-		nblks = del->br_blockcount;
-		qfield = XFS_TRANS_DQ_BCOUNT;
-		/*
-		 * Set up del_endblock and cur for later.
-		 */
-		del_endblock = del->br_startblock + del->br_blockcount;
-		da_old = da_new = 0;
-	} else {
-		da_old = startblockval(got.br_startblock);
-		da_new = 0;
-		nblks = 0;
-	}
-	qfield = qfield;
-	nblks = nblks;
-
-	/*
-	 * Set flag value to use in switch statement.
-	 * Left-contig is 2, right-contig is 1.
-	 */
-	switch (((got.br_startoff == del->br_startoff) << 1) |
-		(got_endoff == del_endoff)) {
-	case 3:
-		/*
-		 * Matches the whole extent.  Delete the entry.
-		 */
-		xfs_iext_remove(ip, eidx, 1, BMAP_COWFORK);
-		--eidx;
-		break;
-
-	case 2:
-		/*
-		 * Deleting the first part of the extent.
-		 */
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_startoff(ep, del_endoff);
-		temp = got.br_blockcount - del->br_blockcount;
-		xfs_bmbt_set_blockcount(ep, temp);
-		if (delay) {
-			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-				da_old);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-			da_new = temp;
-			break;
-		}
-		xfs_bmbt_set_startblock(ep, del_endblock);
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		break;
-
-	case 1:
-		/*
-		 * Deleting the last part of the extent.
-		 */
-		temp = got.br_blockcount - del->br_blockcount;
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		if (delay) {
-			temp = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-				da_old);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-			da_new = temp;
-			break;
-		}
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		break;
-
-	case 0:
-		/*
-		 * Deleting the middle of the extent.
-		 */
-		temp = del->br_startoff - got.br_startoff;
-		trace_xfs_bmap_pre_update(ip, eidx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(ep, temp);
-		new.br_startoff = del_endoff;
-		temp2 = got_endoff - del_endoff;
-		new.br_blockcount = temp2;
-		new.br_state = got.br_state;
-		if (!delay) {
-			new.br_startblock = del_endblock;
-		} else {
-			temp = xfs_bmap_worst_indlen(ip, temp);
-			xfs_bmbt_set_startblock(ep, nullstartblock((int)temp));
-			temp2 = xfs_bmap_worst_indlen(ip, temp2);
-			new.br_startblock = nullstartblock((int)temp2);
-			da_new = temp + temp2;
-			while (da_new > da_old) {
-				if (temp) {
-					temp--;
-					da_new--;
-					xfs_bmbt_set_startblock(ep,
-						nullstartblock((int)temp));
-				}
-				if (da_new == da_old)
-					break;
-				if (temp2) {
-					temp2--;
-					da_new--;
-					new.br_startblock =
-						nullstartblock((int)temp2);
-				}
-			}
-		}
-		trace_xfs_bmap_post_update(ip, eidx, state, _THIS_IP_);
-		xfs_iext_insert(ip, eidx + 1, 1, &new, state);
-		++eidx;
-		break;
-	}
-
-	/*
-	 * Account for change in delayed indirect blocks.
-	 * Nothing to do for disk quota accounting here.
-	 */
-	ASSERT(da_old >= da_new);
-	if (da_old > da_new)
-		xfs_mod_fdblocks(mp, (int64_t)(da_old - da_new), false);
-
-	return error;
-}
-
 /*
  * Unmap (remove) blocks from a file.
  * If nexts is nonzero then the number of extents to remove is limited to
@@ -5360,8 +5375,6 @@ __xfs_bunmapi(
 {
 	xfs_btree_cur_t		*cur;		/* bmap btree cursor */
 	xfs_bmbt_irec_t		del;		/* extent being deleted */
-	int			eof;		/* is deleting at eof */
-	xfs_bmbt_rec_host_t	*ep;		/* extent record pointer */
 	int			error;		/* error return value */
 	xfs_extnum_t		extno;		/* extent number in list */
 	xfs_bmbt_irec_t		got;		/* current extent record */
@@ -5371,8 +5384,6 @@ __xfs_bunmapi(
 	int			logflags;	/* transaction logging flags */
 	xfs_extlen_t		mod;		/* rt extent offset */
 	xfs_mount_t		*mp;		/* mount structure */
-	xfs_extnum_t		nextents;	/* number of file extents */
-	xfs_bmbt_irec_t		prev;		/* previous extent record */
 	xfs_fileoff_t		start;		/* first file offset deleted */
 	int			tmp_logflags;	/* partial logging flags */
 	int			wasdel;		/* was a delayed alloc extent */
@@ -5403,8 +5414,7 @@ __xfs_bunmapi(
 	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
-	if (nextents == 0) {
+	if (xfs_iext_count(ifp) == 0) {
 		*rlen = 0;
 		return 0;
 	}
@@ -5412,18 +5422,17 @@ __xfs_bunmapi(
 	isrt = (whichfork == XFS_DATA_FORK) && XFS_IS_REALTIME_INODE(ip);
 	start = bno;
 	bno = start + len - 1;
-	ep = xfs_bmap_search_extents(ip, bno, whichfork, &eof, &lastx, &got,
-		&prev);
 
 	/*
 	 * Check to see if the given block number is past the end of the
 	 * file, back up to the last block if so...
 	 */
-	if (eof) {
-		ep = xfs_iext_get_ext(ifp, --lastx);
-		xfs_bmbt_get_all(ep, &got);
+	if (!xfs_iext_lookup_extent(ip, ifp, bno, &lastx, &got)) {
+		ASSERT(lastx > 0);
+		xfs_iext_get_extent(ifp, --lastx, &got);
 		bno = got.br_startoff + got.br_blockcount - 1;
 	}
+
 	logflags = 0;
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
@@ -5454,8 +5463,7 @@ __xfs_bunmapi(
 		if (got.br_startoff > bno) {
 			if (--lastx < 0)
 				break;
-			ep = xfs_iext_get_ext(ifp, lastx);
-			xfs_bmbt_get_all(ep, &got);
+			xfs_iext_get_extent(ifp, lastx, &got);
 		}
 		/*
 		 * Is the last block of this extent before the range
@@ -5469,7 +5477,6 @@ __xfs_bunmapi(
 		 * Then deal with the (possibly delayed) allocated space
 		 * we found.
 		 */
-		ASSERT(ep != NULL);
 		del = got;
 		wasdel = isnullstartblock(del.br_startblock);
 		if (got.br_startoff < start) {
@@ -5550,15 +5557,12 @@ __xfs_bunmapi(
 				 */
 				ASSERT(bno >= del.br_blockcount);
 				bno -= del.br_blockcount;
-				if (got.br_startoff > bno) {
-					if (--lastx >= 0) {
-						ep = xfs_iext_get_ext(ifp,
-								      lastx);
-						xfs_bmbt_get_all(ep, &got);
-					}
-				}
+				if (got.br_startoff > bno && --lastx >= 0)
+					xfs_iext_get_extent(ifp, lastx, &got);
 				continue;
 			} else if (del.br_state == XFS_EXT_UNWRITTEN) {
+				struct xfs_bmbt_irec	prev;
+
 				/*
 				 * This one is already unwritten.
 				 * It must have a written left neighbor.
@@ -5566,8 +5570,7 @@ __xfs_bunmapi(
 				 * try again.
 				 */
 				ASSERT(lastx > 0);
-				xfs_bmbt_get_all(xfs_iext_get_ext(ifp,
-						lastx - 1), &prev);
+				xfs_iext_get_extent(ifp, lastx - 1, &prev);
 				ASSERT(prev.br_state == XFS_EXT_NORM);
 				ASSERT(!isnullstartblock(prev.br_startblock));
 				ASSERT(del.br_startblock ==
@@ -5665,13 +5668,9 @@ __xfs_bunmapi(
 		 */
 		if (bno != (xfs_fileoff_t)-1 && bno >= start) {
 			if (lastx >= 0) {
-				ep = xfs_iext_get_ext(ifp, lastx);
-				if (xfs_bmbt_get_startoff(ep) > bno) {
-					if (--lastx >= 0)
-						ep = xfs_iext_get_ext(ifp,
-								      lastx);
-				}
-				xfs_bmbt_get_all(ep, &got);
+				xfs_iext_get_extent(ifp, lastx, &got);
+				if (got.br_startoff > bno && --lastx >= 0)
+					xfs_iext_get_extent(ifp, lastx, &got);
 			}
 			extno++;
 		}
@@ -5889,7 +5888,7 @@ xfs_bmse_shift_one(
 
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+	total_extents = xfs_iext_count(ifp);
 
 	xfs_bmbt_get_all(gotp, &got);
 
@@ -6066,7 +6065,7 @@ xfs_bmap_shift_extents(
 	 * are collapsing out, so we cannot use the count of real extents here.
 	 * Instead we have to calculate it from the incore fork.
 	 */
-	total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+	total_extents = xfs_iext_count(ifp);
 	if (total_extents == 0) {
 		*done = 1;
 		goto del_cursor;
@@ -6126,7 +6125,7 @@ xfs_bmap_shift_extents(
 		 * count can change. Update the total and grade the next record.
 		 */
 		if (direction == SHIFT_LEFT) {
-			total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+			total_extents = xfs_iext_count(ifp);
 			stop_extent = total_extents;
 		}
 

fs/xfs/libxfs/xfs_bmap.h

@@ -190,6 +190,8 @@ void	xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
 #define	XFS_BMAP_TRACE_EXLIST(ip,c,w)
 #endif
 
+void	xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
+		xfs_filblks_t len);
 int	xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
 void	xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
 void	xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
@@ -221,7 +223,11 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
 		xfs_extnum_t nexts, xfs_fsblock_t *firstblock,
 		struct xfs_defer_ops *dfops, int *done);
-int	xfs_bunmapi_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *del);
+int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
+		xfs_extnum_t *idx, struct xfs_bmbt_irec *got,
+		struct xfs_bmbt_irec *del);
+void	xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
+		struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
 int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
 		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);
@@ -231,14 +237,9 @@ int	xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_defer_ops *dfops, enum shift_direction direction,
 		int num_exts);
 int	xfs_bmap_split_extent(struct xfs_inode *ip, xfs_fileoff_t split_offset);
-struct xfs_bmbt_rec_host *
-	xfs_bmap_search_extents(struct xfs_inode *ip, xfs_fileoff_t bno,
-		int fork, int *eofp, xfs_extnum_t *lastxp,
-		struct xfs_bmbt_irec *gotp, struct xfs_bmbt_irec *prevp);
 int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
-		xfs_fileoff_t aoff, xfs_filblks_t len,
-		struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *prev,
-		xfs_extnum_t *lastx, int eof);
+		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
+		struct xfs_bmbt_irec *got, xfs_extnum_t *lastx, int eof);
 
 enum xfs_bmap_intent_type {
 	XFS_BMAP_MAP = 1,

fs/xfs/libxfs/xfs_btree.c

@@ -4826,7 +4826,7 @@ xfs_btree_calc_size(
 	return rval;
 }
 
-int
+static int
 xfs_btree_count_blocks_helper(
 	struct xfs_btree_cur	*cur,
 	int			level,

fs/xfs/libxfs/xfs_defer.c

@@ -199,9 +199,9 @@ xfs_defer_intake_work(
 	struct xfs_defer_pending	*dfp;
 
 	list_for_each_entry(dfp, &dop->dop_intake, dfp_list) {
-		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
 		dfp->dfp_intent = dfp->dfp_type->create_intent(tp,
 				dfp->dfp_count);
+		trace_xfs_defer_intake_work(tp->t_mountp, dfp);
 		list_sort(tp->t_mountp, &dfp->dfp_work,
 				dfp->dfp_type->diff_items);
 		list_for_each(li, &dfp->dfp_work)
@@ -221,21 +221,14 @@ xfs_defer_trans_abort(
 	struct xfs_defer_pending	*dfp;
 
 	trace_xfs_defer_trans_abort(tp->t_mountp, dop);
-	/*
-	 * If the transaction was committed, drop the intent reference
-	 * since we're bailing out of here. The other reference is
-	 * dropped when the intent hits the AIL.  If the transaction
-	 * was not committed, the intent is freed by the intent item
-	 * unlock handler on abort.
-	 */
-	if (!dop->dop_committed)
-		return;
 
-	/* Abort intent items. */
+	/* Abort intent items that don't have a done item. */
 	list_for_each_entry(dfp, &dop->dop_pending, dfp_list) {
 		trace_xfs_defer_pending_abort(tp->t_mountp, dfp);
-		if (!dfp->dfp_done)
+		if (dfp->dfp_intent && !dfp->dfp_done) {
 			dfp->dfp_type->abort_intent(dfp->dfp_intent);
+			dfp->dfp_intent = NULL;
+		}
 	}
 
 	/* Shut down FS. */

fs/xfs/libxfs/xfs_dir2.c

@@ -93,7 +93,7 @@ xfs_ascii_ci_compname(
 	return result;
 }
 
-static struct xfs_nameops xfs_ascii_ci_nameops = {
+static const struct xfs_nameops xfs_ascii_ci_nameops = {
 	.hashname	= xfs_ascii_ci_hashname,
 	.compname	= xfs_ascii_ci_compname,
 };

fs/xfs/libxfs/xfs_dquot_buf.c

@@ -191,8 +191,7 @@ xfs_dquot_buf_verify_crc(
 	if (mp->m_quotainfo)
 		ndquots = mp->m_quotainfo->qi_dqperchunk;
 	else
-		ndquots = xfs_calc_dquots_per_chunk(
-					XFS_BB_TO_FSB(mp, bp->b_length));
+		ndquots = xfs_calc_dquots_per_chunk(bp->b_length);
 
 	for (i = 0; i < ndquots; i++, d++) {
 		if (!xfs_verify_cksum((char *)d, sizeof(struct xfs_dqblk),

fs/xfs/libxfs/xfs_format.h

@@ -865,7 +865,6 @@ typedef struct xfs_timestamp {
  * padding field for v3 inodes.
  */
 #define	XFS_DINODE_MAGIC		0x494e	/* 'IN' */
-#define XFS_DINODE_GOOD_VERSION(v)	((v) >= 1 && (v) <= 3)
 typedef struct xfs_dinode {
 	__be16		di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
 	__be16		di_mode;	/* mode and type of file */

fs/xfs/libxfs/xfs_inode_buf.c

@@ -57,6 +57,17 @@ xfs_inobp_check(
 }
 #endif
 
+bool
+xfs_dinode_good_version(
+	struct xfs_mount *mp,
+	__u8		version)
+{
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return version == 3;
+
+	return version == 1 || version == 2;
+}
+
 /*
  * If we are doing readahead on an inode buffer, we might be in log recovery
  * reading an inode allocation buffer that hasn't yet been replayed, and hence
@@ -91,7 +102,7 @@ xfs_inode_buf_verify(
 
 		dip = xfs_buf_offset(bp, (i << mp->m_sb.sb_inodelog));
 		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_version);
+			xfs_dinode_good_version(mp, dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
 						XFS_ERRTAG_ITOBP_INOTOBP,
 						XFS_RANDOM_ITOBP_INOTOBP))) {

fs/xfs/libxfs/xfs_inode_buf.h

@@ -74,6 +74,8 @@ void	xfs_inode_from_disk(struct xfs_inode *ip, struct xfs_dinode *from);
 void	xfs_log_dinode_to_disk(struct xfs_log_dinode *from,
 			       struct xfs_dinode *to);
 
+bool	xfs_dinode_good_version(struct xfs_mount *mp, __u8 version);
+
 #if defined(DEBUG)
 void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #else

fs/xfs/libxfs/xfs_inode_fork.c

@@ -775,6 +775,13 @@ xfs_idestroy_fork(
 	}
 }
 
+/* Count number of incore extents based on if_bytes */
+xfs_extnum_t
+xfs_iext_count(struct xfs_ifork *ifp)
+{
+	return ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+}
+
 /*
  * Convert in-core extents to on-disk form
  *
@@ -803,7 +810,7 @@ xfs_iextents_copy(
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL|XFS_ILOCK_SHARED));
 	ASSERT(ifp->if_bytes > 0);
 
-	nrecs = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nrecs = xfs_iext_count(ifp);
 	XFS_BMAP_TRACE_EXLIST(ip, nrecs, whichfork);
 	ASSERT(nrecs > 0);
 
@@ -941,7 +948,7 @@ xfs_iext_get_ext(
 	xfs_extnum_t	idx)		/* index of target extent */
 {
 	ASSERT(idx >= 0);
-	ASSERT(idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t));
+	ASSERT(idx < xfs_iext_count(ifp));
 
 	if ((ifp->if_flags & XFS_IFEXTIREC) && (idx == 0)) {
 		return ifp->if_u1.if_ext_irec->er_extbuf;
@@ -1017,7 +1024,7 @@ xfs_iext_add(
 	int		new_size;	/* size of extents after adding */
 	xfs_extnum_t	nextents;	/* number of extents in file */
 
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	ASSERT((idx >= 0) && (idx <= nextents));
 	byte_diff = ext_diff * sizeof(xfs_bmbt_rec_t);
 	new_size = ifp->if_bytes + byte_diff;
@@ -1241,7 +1248,7 @@ xfs_iext_remove(
 	trace_xfs_iext_remove(ip, idx, state, _RET_IP_);
 
 	ASSERT(ext_diff > 0);
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	new_size = (nextents - ext_diff) * sizeof(xfs_bmbt_rec_t);
 
 	if (new_size == 0) {
@@ -1270,7 +1277,7 @@ xfs_iext_remove_inline(
 
 	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
 	ASSERT(idx < XFS_INLINE_EXTS);
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	ASSERT(((nextents - ext_diff) > 0) &&
 		(nextents - ext_diff) < XFS_INLINE_EXTS);
 
@@ -1309,7 +1316,7 @@ xfs_iext_remove_direct(
 	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
 	new_size = ifp->if_bytes -
 		(ext_diff * sizeof(xfs_bmbt_rec_t));
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 
 	if (new_size == 0) {
 		xfs_iext_destroy(ifp);
@@ -1546,7 +1553,7 @@ xfs_iext_indirect_to_direct(
 	int		size;		/* size of file extents */
 
 	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	ASSERT(nextents <= XFS_LINEAR_EXTS);
 	size = nextents * sizeof(xfs_bmbt_rec_t);
 
@@ -1620,7 +1627,7 @@ xfs_iext_bno_to_ext(
 	xfs_extnum_t	nextents;	/* number of file extents */
 	xfs_fileoff_t	startoff = 0;	/* start offset of extent */
 
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	if (nextents == 0) {
 		*idxp = 0;
 		return NULL;
@@ -1733,8 +1740,8 @@ xfs_iext_idx_to_irec(
 
 	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
 	ASSERT(page_idx >= 0);
-	ASSERT(page_idx <= ifp->if_bytes / sizeof(xfs_bmbt_rec_t));
-	ASSERT(page_idx < ifp->if_bytes / sizeof(xfs_bmbt_rec_t) || realloc);
+	ASSERT(page_idx <= xfs_iext_count(ifp));
+	ASSERT(page_idx < xfs_iext_count(ifp) || realloc);
 
 	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
 	erp_idx = 0;
@@ -1782,7 +1789,7 @@ xfs_iext_irec_init(
 	xfs_extnum_t	nextents;	/* number of extents in file */
 
 	ASSERT(!(ifp->if_flags & XFS_IFEXTIREC));
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	ASSERT(nextents <= XFS_LINEAR_EXTS);
 
 	erp = kmem_alloc(sizeof(xfs_ext_irec_t), KM_NOFS);
@@ -1906,7 +1913,7 @@ xfs_iext_irec_compact(
 
 	ASSERT(ifp->if_flags & XFS_IFEXTIREC);
 	nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ;
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 
 	if (nextents == 0) {
 		xfs_iext_destroy(ifp);
@@ -1996,3 +2003,49 @@ xfs_ifork_init_cow(
 	ip->i_cformat = XFS_DINODE_FMT_EXTENTS;
 	ip->i_cnextents = 0;
 }
+
+/*
+ * Lookup the extent covering bno.
+ *
+ * If there is an extent covering bno return the extent index, and store the
+ * expanded extent structure in *gotp, and the extent index in *idx.
+ * If there is no extent covering bno, but there is an extent after it (e.g.
+ * it lies in a hole) return that extent in *gotp and its index in *idx
+ * instead.
+ * If bno is beyond the last extent return false, and return the index after
+ * the last valid index in *idxp.
+ */
+bool
+xfs_iext_lookup_extent(
+	struct xfs_inode	*ip,
+	struct xfs_ifork	*ifp,
+	xfs_fileoff_t		bno,
+	xfs_extnum_t		*idxp,
+	struct xfs_bmbt_irec	*gotp)
+{
+	struct xfs_bmbt_rec_host *ep;
+
+	XFS_STATS_INC(ip->i_mount, xs_look_exlist);
+
+	ep = xfs_iext_bno_to_ext(ifp, bno, idxp);
+	if (!ep)
+		return false;
+	xfs_bmbt_get_all(ep, gotp);
+	return true;
+}
+
+/*
+ * Return true if there is an extent at index idx, and return the expanded
+ * extent structure at idx in that case.  Else return false.
+ */
+bool
+xfs_iext_get_extent(
+	struct xfs_ifork	*ifp,
+	xfs_extnum_t		idx,
+	struct xfs_bmbt_irec	*gotp)
+{
+	if (idx < 0 || idx >= xfs_iext_count(ifp))
+		return false;
+	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, idx), gotp);
+	return true;
+}

fs/xfs/libxfs/xfs_inode_fork.h

@@ -152,6 +152,7 @@ void		xfs_init_local_fork(struct xfs_inode *, int, const void *, int);
 
 struct xfs_bmbt_rec_host *
 		xfs_iext_get_ext(struct xfs_ifork *, xfs_extnum_t);
+xfs_extnum_t	xfs_iext_count(struct xfs_ifork *);
 void		xfs_iext_insert(struct xfs_inode *, xfs_extnum_t, xfs_extnum_t,
 				struct xfs_bmbt_irec *, int);
 void		xfs_iext_add(struct xfs_ifork *, xfs_extnum_t, int);
@@ -181,6 +182,12 @@ void		xfs_iext_irec_compact_pages(struct xfs_ifork *);
 void		xfs_iext_irec_compact_full(struct xfs_ifork *);
 void		xfs_iext_irec_update_extoffs(struct xfs_ifork *, int, int);
 
+bool		xfs_iext_lookup_extent(struct xfs_inode *ip,
+			struct xfs_ifork *ifp, xfs_fileoff_t bno,
+			xfs_extnum_t *idxp, struct xfs_bmbt_irec *gotp);
+bool		xfs_iext_get_extent(struct xfs_ifork *ifp, xfs_extnum_t idx,
+			struct xfs_bmbt_irec *gotp);
+
 extern struct kmem_zone	*xfs_ifork_zone;
 
 extern void xfs_ifork_init_cow(struct xfs_inode *ip);

fs/xfs/libxfs/xfs_types.h

@@ -57,7 +57,6 @@ typedef __int64_t	xfs_sfiloff_t;	/* signed block number in a file */
 
 #define	NULLAGBLOCK	((xfs_agblock_t)-1)
 #define	NULLAGNUMBER	((xfs_agnumber_t)-1)
-#define	NULLEXTNUM	((xfs_extnum_t)-1)
 
 #define NULLCOMMITLSN	((xfs_lsn_t)-1)
 

fs/xfs/xfs_aops.c

@@ -777,7 +777,7 @@ xfs_map_cow(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_bmbt_irec	imap;
-	bool			is_cow = false, need_alloc = false;
+	bool			is_cow = false;
 	int			error;
 
 	/*
@@ -795,7 +795,7 @@ xfs_map_cow(
 	 * Else we need to check if there is a COW mapping at this offset.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap, &need_alloc);
+	is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
 	if (!is_cow)
@@ -805,7 +805,7 @@ xfs_map_cow(
 	 * And if the COW mapping has a delayed extent here we need to
 	 * allocate real space for it now.
 	 */
-	if (need_alloc) {
+	if (isnullstartblock(imap.br_startblock)) {
 		error = xfs_iomap_write_allocate(ip, XFS_COW_FORK, offset,
 				&imap);
 		if (error)
@@ -1311,7 +1311,6 @@ __xfs_get_blocks(
 	ssize_t			size;
 	int			new = 0;
 	bool			is_cow = false;
-	bool			need_alloc = false;
 
 	BUG_ON(create && !direct);
 
@@ -1337,9 +1336,11 @@ __xfs_get_blocks(
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + size);
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 
-	if (create && direct && xfs_is_reflink_inode(ip))
-		is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap,
-					&need_alloc);
+	if (create && direct && xfs_is_reflink_inode(ip)) {
+		is_cow = xfs_reflink_find_cow_mapping(ip, offset, &imap);
+		ASSERT(!is_cow || !isnullstartblock(imap.br_startblock));
+	}
+
 	if (!is_cow) {
 		error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
 					&imap, &nimaps, XFS_BMAPI_ENTIRE);
@@ -1356,10 +1357,29 @@ __xfs_get_blocks(
 			xfs_reflink_trim_irec_to_next_cow(ip, offset_fsb,
 					&imap);
 	}
-	ASSERT(!need_alloc);
 	if (error)
 		goto out_unlock;
 
+	/*
+	 * The only time we can ever safely find delalloc blocks on direct I/O
+	 * is a dio write to post-eof speculative preallocation. All other
+	 * scenarios are indicative of a problem or misuse (such as mixing
+	 * direct and mapped I/O).
+	 *
+	 * The file may be unmapped by the time we get here so we cannot
+	 * reliably fail the I/O based on mapping. Instead, fail the I/O if this
+	 * is a read or a write within eof. Otherwise, carry on but warn as a
+	 * precuation if the file happens to be mapped.
+	 */
+	if (direct && imap.br_startblock == DELAYSTARTBLOCK) {
+		if (!create || offset < i_size_read(VFS_I(ip))) {
+			WARN_ON_ONCE(1);
+			error = -EIO;
+			goto out_unlock;
+		}
+		WARN_ON_ONCE(mapping_mapped(VFS_I(ip)->i_mapping));
+	}
+
 	/* for DAX, we convert unwritten extents directly */
 	if (create &&
 	    (!nimaps ||
@@ -1444,8 +1464,6 @@ __xfs_get_blocks(
 	     (new || ISUNWRITTEN(&imap))))
 		set_buffer_new(bh_result);
 
-	BUG_ON(direct && imap.br_startblock == DELAYSTARTBLOCK);
-
 	return 0;
 
 out_unlock:

fs/xfs/xfs_bmap_util.c

@@ -359,9 +359,7 @@ xfs_bmap_count_blocks(
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
-		xfs_bmap_count_leaves(ifp, 0,
-			ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t),
-			count);
+		xfs_bmap_count_leaves(ifp, 0, xfs_iext_count(ifp), count);
 		return 0;
 	}
 
@@ -426,7 +424,7 @@ xfs_getbmapx_fix_eof_hole(
 		ifp = XFS_IFORK_PTR(ip, whichfork);
 		if (!moretocome &&
 		    xfs_iext_bno_to_ext(ifp, fileblock, &lastx) &&
-		   (lastx == (ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t))-1))
+		   (lastx == xfs_iext_count(ifp) - 1))
 			out->bmv_oflags |= BMV_OF_LAST;
 	}
 
@@ -1792,6 +1790,7 @@ xfs_swap_extent_forks(
 	struct xfs_ifork	tempifp, *ifp, *tifp;
 	int			aforkblks = 0;
 	int			taforkblks = 0;
+	xfs_extnum_t		nextents;
 	__uint64_t		tmp;
 	int			error;
 
@@ -1877,14 +1876,13 @@ xfs_swap_extent_forks(
 
 	switch (ip->i_d.di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		/* If the extents fit in the inode, fix the
-		 * pointer.  Otherwise it's already NULL or
-		 * pointing to the extent.
+		/*
+		 * If the extents fit in the inode, fix the pointer.  Otherwise
+		 * it's already NULL or pointing to the extent.
 		 */
-		if (ip->i_d.di_nextents <= XFS_INLINE_EXTS) {
-			ifp->if_u1.if_extents =
-				ifp->if_u2.if_inline_ext;
-		}
+		nextents = xfs_iext_count(&ip->i_df);
+		if (nextents <= XFS_INLINE_EXTS)
+			ifp->if_u1.if_extents = ifp->if_u2.if_inline_ext;
 		(*src_log_flags) |= XFS_ILOG_DEXT;
 		break;
 	case XFS_DINODE_FMT_BTREE:
@@ -1896,14 +1894,13 @@ xfs_swap_extent_forks(
 
 	switch (tip->i_d.di_format) {
 	case XFS_DINODE_FMT_EXTENTS:
-		/* If the extents fit in the inode, fix the
-		 * pointer.  Otherwise it's already NULL or
-		 * pointing to the extent.
+		/*
+		 * If the extents fit in the inode, fix the pointer.  Otherwise
+		 * it's already NULL or pointing to the extent.
 		 */
-		if (tip->i_d.di_nextents <= XFS_INLINE_EXTS) {
-			tifp->if_u1.if_extents =
-				tifp->if_u2.if_inline_ext;
-		}
+		nextents = xfs_iext_count(&tip->i_df);
+		if (nextents <= XFS_INLINE_EXTS)
+			tifp->if_u1.if_extents = tifp->if_u2.if_inline_ext;
 		(*target_log_flags) |= XFS_ILOG_DEXT;
 		break;
 	case XFS_DINODE_FMT_BTREE:

fs/xfs/xfs_buf.h

@@ -71,6 +71,7 @@ typedef unsigned int xfs_buf_flags_t;
 	{ XBF_READ,		"READ" }, \
 	{ XBF_WRITE,		"WRITE" }, \
 	{ XBF_READ_AHEAD,	"READ_AHEAD" }, \
+	{ XBF_NO_IOACCT,	"NO_IOACCT" }, \
 	{ XBF_ASYNC,		"ASYNC" }, \
 	{ XBF_DONE,		"DONE" }, \
 	{ XBF_STALE,		"STALE" }, \

fs/xfs/xfs_file.c

@@ -249,6 +249,7 @@ xfs_file_dio_aio_read(
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			isize = i_size_read(inode);
 	size_t			count = iov_iter_count(to);
+	loff_t			end = iocb->ki_pos + count - 1;
 	struct iov_iter		data;
 	struct xfs_buftarg	*target;
 	ssize_t			ret = 0;
@@ -272,49 +273,21 @@ xfs_file_dio_aio_read(
 
 	file_accessed(iocb->ki_filp);
 
-	/*
-	 * Locking is a bit tricky here. If we take an exclusive lock for direct
-	 * IO, we effectively serialise all new concurrent read IO to this file
-	 * and block it behind IO that is currently in progress because IO in
-	 * progress holds the IO lock shared. We only need to hold the lock
-	 * exclusive to blow away the page cache, so only take lock exclusively
-	 * if the page cache needs invalidation. This allows the normal direct
-	 * IO case of no page cache pages to proceeed concurrently without
-	 * serialisation.
-	 */
 	xfs_rw_ilock(ip, XFS_IOLOCK_SHARED);
 	if (mapping->nrpages) {
-		xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
-		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
+		if (ret)
+			goto out_unlock;
 
 		/*
-		 * The generic dio code only flushes the range of the particular
-		 * I/O. Because we take an exclusive lock here, this whole
-		 * sequence is considerably more expensive for us. This has a
-		 * noticeable performance impact for any file with cached pages,
-		 * even when outside of the range of the particular I/O.
-		 *
-		 * Hence, amortize the cost of the lock against a full file
-		 * flush and reduce the chances of repeated iolock cycles going
-		 * forward.
+		 * Invalidate whole pages. This can return an error if we fail
+		 * to invalidate a page, but this should never happen on XFS.
+		 * Warn if it does fail.
 		 */
-		if (mapping->nrpages) {
-			ret = filemap_write_and_wait(mapping);
-			if (ret) {
-				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
-				return ret;
-			}
-
-			/*
-			 * Invalidate whole pages. This can return an error if
-			 * we fail to invalidate a page, but this should never
-			 * happen on XFS. Warn if it does fail.
-			 */
-			ret = invalidate_inode_pages2(mapping);
-			WARN_ON_ONCE(ret);
-			ret = 0;
-		}
-		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
+		WARN_ON_ONCE(ret);
+		ret = 0;
 	}
 
 	data = *to;
@@ -324,8 +297,9 @@ xfs_file_dio_aio_read(
 		iocb->ki_pos += ret;
 		iov_iter_advance(to, ret);
 	}
-	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 
+out_unlock:
+	xfs_rw_iunlock(ip, XFS_IOLOCK_SHARED);
 	return ret;
 }
 
@@ -570,61 +544,49 @@ xfs_file_dio_aio_write(
 	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
 		return -EINVAL;
 
-	/* "unaligned" here means not aligned to a filesystem block */
-	if ((iocb->ki_pos & mp->m_blockmask) ||
-	    ((iocb->ki_pos + count) & mp->m_blockmask))
-		unaligned_io = 1;
-
 	/*
-	 * We don't need to take an exclusive lock unless there page cache needs
-	 * to be invalidated or unaligned IO is being executed. We don't need to
-	 * consider the EOF extension case here because
-	 * xfs_file_aio_write_checks() will relock the inode as necessary for
-	 * EOF zeroing cases and fill out the new inode size as appropriate.
+	 * Don't take the exclusive iolock here unless the I/O is unaligned to
+	 * the file system block size.  We don't need to consider the EOF
+	 * extension case here because xfs_file_aio_write_checks() will relock
+	 * the inode as necessary for EOF zeroing cases and fill out the new
+	 * inode size as appropriate.
 	 */
-	if (unaligned_io || mapping->nrpages)
+	if ((iocb->ki_pos & mp->m_blockmask) ||
+	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
+		unaligned_io = 1;
 		iolock = XFS_IOLOCK_EXCL;
-	else
+	} else {
 		iolock = XFS_IOLOCK_SHARED;
-	xfs_rw_ilock(ip, iolock);
-
-	/*
-	 * Recheck if there are cached pages that need invalidate after we got
-	 * the iolock to protect against other threads adding new pages while
-	 * we were waiting for the iolock.
-	 */
-	if (mapping->nrpages && iolock == XFS_IOLOCK_SHARED) {
-		xfs_rw_iunlock(ip, iolock);
-		iolock = XFS_IOLOCK_EXCL;
-		xfs_rw_ilock(ip, iolock);
 	}
 
+	xfs_rw_ilock(ip, iolock);
+
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
 	count = iov_iter_count(from);
 	end = iocb->ki_pos + count - 1;
 
-	/*
-	 * See xfs_file_dio_aio_read() for why we do a full-file flush here.
-	 */
 	if (mapping->nrpages) {
-		ret = filemap_write_and_wait(VFS_I(ip)->i_mapping);
+		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
 		if (ret)
 			goto out;
+
 		/*
 		 * Invalidate whole pages. This can return an error if we fail
 		 * to invalidate a page, but this should never happen on XFS.
 		 * Warn if it does fail.
 		 */
-		ret = invalidate_inode_pages2(VFS_I(ip)->i_mapping);
+		ret = invalidate_inode_pages2_range(mapping,
+				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
 		WARN_ON_ONCE(ret);
 		ret = 0;
 	}
 
 	/*
 	 * If we are doing unaligned IO, wait for all other IO to drain,
-	 * otherwise demote the lock if we had to flush cached pages
+	 * otherwise demote the lock if we had to take the exclusive lock
+	 * for other reasons in xfs_file_aio_write_checks.
 	 */
 	if (unaligned_io)
 		inode_dio_wait(inode);
@@ -947,134 +909,6 @@ xfs_file_fallocate(
 	return error;
 }
 
-/*
- * Flush all file writes out to disk.
- */
-static int
-xfs_file_wait_for_io(
-	struct inode	*inode,
-	loff_t		offset,
-	size_t		len)
-{
-	loff_t		rounding;
-	loff_t		ioffset;
-	loff_t		iendoffset;
-	loff_t		bs;
-	int		ret;
-
-	bs = inode->i_sb->s_blocksize;
-	inode_dio_wait(inode);
-
-	rounding = max_t(xfs_off_t, bs, PAGE_SIZE);
-	ioffset = round_down(offset, rounding);
-	iendoffset = round_up(offset + len, rounding) - 1;
-	ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
-					   iendoffset);
-	return ret;
-}
-
-/* Hook up to the VFS reflink function */
-STATIC int
-xfs_file_share_range(
-	struct file	*file_in,
-	loff_t		pos_in,
-	struct file	*file_out,
-	loff_t		pos_out,
-	u64		len,
-	bool		is_dedupe)
-{
-	struct inode	*inode_in;
-	struct inode	*inode_out;
-	ssize_t		ret;
-	loff_t		bs;
-	loff_t		isize;
-	int		same_inode;
-	loff_t		blen;
-	unsigned int	flags = 0;
-
-	inode_in = file_inode(file_in);
-	inode_out = file_inode(file_out);
-	bs = inode_out->i_sb->s_blocksize;
-
-	/* Don't touch certain kinds of inodes */
-	if (IS_IMMUTABLE(inode_out))
-		return -EPERM;
-	if (IS_SWAPFILE(inode_in) ||
-	    IS_SWAPFILE(inode_out))
-		return -ETXTBSY;
-
-	/* Reflink only works within this filesystem. */
-	if (inode_in->i_sb != inode_out->i_sb)
-		return -EXDEV;
-	same_inode = (inode_in->i_ino == inode_out->i_ino);
-
-	/* Don't reflink dirs, pipes, sockets... */
-	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
-		return -EISDIR;
-	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
-		return -EINVAL;
-	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
-		return -EINVAL;
-
-	/* Don't share DAX file data for now. */
-	if (IS_DAX(inode_in) || IS_DAX(inode_out))
-		return -EINVAL;
-
-	/* Are we going all the way to the end? */
-	isize = i_size_read(inode_in);
-	if (isize == 0)
-		return 0;
-	if (len == 0)
-		len = isize - pos_in;
-
-	/* Ensure offsets don't wrap and the input is inside i_size */
-	if (pos_in + len < pos_in || pos_out + len < pos_out ||
-	    pos_in + len > isize)
-		return -EINVAL;
-
-	/* Don't allow dedupe past EOF in the dest file */
-	if (is_dedupe) {
-		loff_t	disize;
-
-		disize = i_size_read(inode_out);
-		if (pos_out >= disize || pos_out + len > disize)
-			return -EINVAL;
-	}
-
-	/* If we're linking to EOF, continue to the block boundary. */
-	if (pos_in + len == isize)
-		blen = ALIGN(isize, bs) - pos_in;
-	else
-		blen = len;
-
-	/* Only reflink if we're aligned to block boundaries */
-	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
-	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
-		return -EINVAL;
-
-	/* Don't allow overlapped reflink within the same file */
-	if (same_inode && pos_out + blen > pos_in && pos_out < pos_in + blen)
-		return -EINVAL;
-
-	/* Wait for the completion of any pending IOs on srcfile */
-	ret = xfs_file_wait_for_io(inode_in, pos_in, len);
-	if (ret)
-		goto out;
-	ret = xfs_file_wait_for_io(inode_out, pos_out, len);
-	if (ret)
-		goto out;
-
-	if (is_dedupe)
-		flags |= XFS_REFLINK_DEDUPE;
-	ret = xfs_reflink_remap_range(XFS_I(inode_in), pos_in, XFS_I(inode_out),
-			pos_out, len, flags);
-	if (ret < 0)
-		goto out;
-
-out:
-	return ret;
-}
-
 STATIC ssize_t
 xfs_file_copy_range(
 	struct file	*file_in,
@@ -1086,7 +920,7 @@ xfs_file_copy_range(
 {
 	int		error;
 
-	error = xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	error = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 	if (error)
 		return error;
@@ -1101,7 +935,7 @@ xfs_file_clone_range(
 	loff_t		pos_out,
 	u64		len)
 {
-	return xfs_file_share_range(file_in, pos_in, file_out, pos_out,
+	return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out,
 				     len, false);
 }
 
@@ -1124,7 +958,7 @@ xfs_file_dedupe_range(
 	if (len > XFS_MAX_DEDUPE_LEN)
 		len = XFS_MAX_DEDUPE_LEN;
 
-	error = xfs_file_share_range(src_file, loff, dst_file, dst_loff,
+	error = xfs_reflink_remap_range(src_file, loff, dst_file, dst_loff,
 				     len, true);
 	if (error)
 		return error;

fs/xfs/xfs_icache.c

@@ -123,7 +123,6 @@ __xfs_inode_free(
 {
 	/* asserts to verify all state is correct here */
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!xfs_isiflocked(ip));
 	XFS_STATS_DEC(ip->i_mount, vn_active);
 
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
@@ -133,6 +132,8 @@ void
 xfs_inode_free(
 	struct xfs_inode	*ip)
 {
+	ASSERT(!xfs_isiflocked(ip));
+
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always
 	 * appears to be reclaimed with an invalid inode number when in the
@@ -981,6 +982,7 @@ xfs_reclaim_inode(
 
 	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		xfs_iunpin_wait(ip);
+		/* xfs_iflush_abort() drops the flush lock */
 		xfs_iflush_abort(ip, false);
 		goto reclaim;
 	}
@@ -989,10 +991,10 @@ xfs_reclaim_inode(
 			goto out_ifunlock;
 		xfs_iunpin_wait(ip);
 	}
-	if (xfs_iflags_test(ip, XFS_ISTALE))
-		goto reclaim;
-	if (xfs_inode_clean(ip))
+	if (xfs_iflags_test(ip, XFS_ISTALE) || xfs_inode_clean(ip)) {
+		xfs_ifunlock(ip);
 		goto reclaim;
+	}
 
 	/*
 	 * Never flush out dirty data during non-blocking reclaim, as it would
@@ -1030,25 +1032,24 @@ xfs_reclaim_inode(
 		xfs_buf_relse(bp);
 	}
 
-	xfs_iflock(ip);
 reclaim:
+	ASSERT(!xfs_isiflocked(ip));
+
 	/*
 	 * Because we use RCU freeing we need to ensure the inode always appears
 	 * to be reclaimed with an invalid inode number when in the free state.
-	 * We do this as early as possible under the ILOCK and flush lock so
-	 * that xfs_iflush_cluster() can be guaranteed to detect races with us
-	 * here. By doing this, we guarantee that once xfs_iflush_cluster has
-	 * locked both the XFS_ILOCK and the flush lock that it will see either
-	 * a valid, flushable inode that will serialise correctly against the
-	 * locks below, or it will see a clean (and invalid) inode that it can
-	 * skip.
+	 * We do this as early as possible under the ILOCK so that
+	 * xfs_iflush_cluster() can be guaranteed to detect races with us here.
+	 * By doing this, we guarantee that once xfs_iflush_cluster has locked
+	 * XFS_ILOCK that it will see either a valid, flushable inode that will
+	 * serialise correctly, or it will see a clean (and invalid) inode that
+	 * it can skip.
 	 */
 	spin_lock(&ip->i_flags_lock);
 	ip->i_flags = XFS_IRECLAIM;
 	ip->i_ino = 0;
 	spin_unlock(&ip->i_flags_lock);
 
-	xfs_ifunlock(ip);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 
 	XFS_STATS_INC(ip->i_mount, xs_ig_reclaims);
@@ -1580,10 +1581,15 @@ xfs_inode_free_cowblocks(
 	struct xfs_eofblocks *eofb = args;
 	bool need_iolock = true;
 	int match;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 
 	ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0));
 
-	if (!xfs_reflink_has_real_cow_blocks(ip)) {
+	/*
+	 * Just clear the tag if we have an empty cow fork or none at all. It's
+	 * possible the inode was fully unshared since it was originally tagged.
+	 */
+	if (!xfs_is_reflink_inode(ip) || !ifp->if_bytes) {
 		trace_xfs_inode_free_cowblocks_invalid(ip);
 		xfs_inode_clear_cowblocks_tag(ip);
 		return 0;
@@ -1656,9 +1662,9 @@ void
 xfs_inode_set_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_set_eofblocks_tag(ip);
+	trace_xfs_inode_set_cowblocks_tag(ip);
 	return __xfs_inode_set_eofblocks_tag(ip, xfs_queue_cowblocks,
-			trace_xfs_perag_set_eofblocks,
+			trace_xfs_perag_set_cowblocks,
 			XFS_ICI_COWBLOCKS_TAG);
 }
 
@@ -1666,7 +1672,7 @@ void
 xfs_inode_clear_cowblocks_tag(
 	xfs_inode_t	*ip)
 {
-	trace_xfs_inode_clear_eofblocks_tag(ip);
+	trace_xfs_inode_clear_cowblocks_tag(ip);
 	return __xfs_inode_clear_eofblocks_tag(ip,
-			trace_xfs_perag_clear_eofblocks, XFS_ICI_COWBLOCKS_TAG);
+			trace_xfs_perag_clear_cowblocks, XFS_ICI_COWBLOCKS_TAG);
 }

fs/xfs/xfs_icreate_item.c

@@ -133,7 +133,7 @@ xfs_icreate_item_committing(
 /*
  * This is the ops vector shared by all buf log items.
  */
-static struct xfs_item_ops xfs_icreate_item_ops = {
+static const struct xfs_item_ops xfs_icreate_item_ops = {
 	.iop_size	= xfs_icreate_item_size,
 	.iop_format	= xfs_icreate_item_format,
 	.iop_pin	= xfs_icreate_item_pin,

fs/xfs/xfs_inode.h

@@ -246,6 +246,11 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
  * Synchronize processes attempting to flush the in-core inode back to disk.
  */
 
+static inline int xfs_isiflocked(struct xfs_inode *ip)
+{
+	return xfs_iflags_test(ip, XFS_IFLOCK);
+}
+
 extern void __xfs_iflock(struct xfs_inode *ip);
 
 static inline int xfs_iflock_nowait(struct xfs_inode *ip)
@@ -261,16 +266,12 @@ static inline void xfs_iflock(struct xfs_inode *ip)
 
 static inline void xfs_ifunlock(struct xfs_inode *ip)
 {
+	ASSERT(xfs_isiflocked(ip));
 	xfs_iflags_clear(ip, XFS_IFLOCK);
 	smp_mb();
 	wake_up_bit(&ip->i_flags, __XFS_IFLOCK_BIT);
 }
 
-static inline int xfs_isiflocked(struct xfs_inode *ip)
-{
-	return xfs_iflags_test(ip, XFS_IFLOCK);
-}
-
 /*
  * Flags for inode locking.
  * Bit ranges:	1<<1  - 1<<16-1 -- iolock/ilock modes (bitfield)

fs/xfs/xfs_inode_item.c

@@ -164,7 +164,7 @@ xfs_inode_item_format_data_fork(
 			struct xfs_bmbt_rec *p;
 
 			ASSERT(ip->i_df.if_u1.if_extents != NULL);
-			ASSERT(ip->i_df.if_bytes / sizeof(xfs_bmbt_rec_t) > 0);
+			ASSERT(xfs_iext_count(&ip->i_df) > 0);
 
 			p = xlog_prepare_iovec(lv, vecp, XLOG_REG_TYPE_IEXT);
 			data_bytes = xfs_iextents_copy(ip, p, XFS_DATA_FORK);
@@ -261,7 +261,7 @@ xfs_inode_item_format_attr_fork(
 		    ip->i_afp->if_bytes > 0) {
 			struct xfs_bmbt_rec *p;
 
-			ASSERT(ip->i_afp->if_bytes / sizeof(xfs_bmbt_rec_t) ==
+			ASSERT(xfs_iext_count(ip->i_afp) ==
 				ip->i_d.di_anextents);
 			ASSERT(ip->i_afp->if_u1.if_extents != NULL);
 

fs/xfs/xfs_ioctl.c

@@ -910,16 +910,14 @@ xfs_ioc_fsgetxattr(
 	if (attr) {
 		if (ip->i_afp) {
 			if (ip->i_afp->if_flags & XFS_IFEXTENTS)
-				fa.fsx_nextents = ip->i_afp->if_bytes /
-							sizeof(xfs_bmbt_rec_t);
+				fa.fsx_nextents = xfs_iext_count(ip->i_afp);
 			else
 				fa.fsx_nextents = ip->i_d.di_anextents;
 		} else
 			fa.fsx_nextents = 0;
 	} else {
 		if (ip->i_df.if_flags & XFS_IFEXTENTS)
-			fa.fsx_nextents = ip->i_df.if_bytes /
-						sizeof(xfs_bmbt_rec_t);
+			fa.fsx_nextents = xfs_iext_count(&ip->i_df);
 		else
 			fa.fsx_nextents = ip->i_d.di_nextents;
 	}

fs/xfs/xfs_iomap.c

@@ -395,11 +395,12 @@ xfs_iomap_prealloc_size(
 	struct xfs_inode	*ip,
 	loff_t			offset,
 	loff_t			count,
-	xfs_extnum_t		idx,
-	struct xfs_bmbt_irec	*prev)
+	xfs_extnum_t		idx)
 {
 	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	struct xfs_bmbt_irec	prev;
 	int			shift = 0;
 	int64_t			freesp;
 	xfs_fsblock_t		qblocks;
@@ -419,8 +420,8 @@ xfs_iomap_prealloc_size(
 	 */
 	if ((mp->m_flags & XFS_MOUNT_DFLT_IOSIZE) ||
 	    XFS_ISIZE(ip) < XFS_FSB_TO_B(mp, mp->m_dalign) ||
-	    idx == 0 ||
-	    prev->br_startoff + prev->br_blockcount < offset_fsb)
+	    !xfs_iext_get_extent(ifp, idx - 1, &prev) ||
+	    prev.br_startoff + prev.br_blockcount < offset_fsb)
 		return mp->m_writeio_blocks;
 
 	/*
@@ -439,8 +440,8 @@ xfs_iomap_prealloc_size(
 	 * always extends to MAXEXTLEN rather than falling short due to things
 	 * like stripe unit/width alignment of real extents.
 	 */
-	if (prev->br_blockcount <= (MAXEXTLEN >> 1))
-		alloc_blocks = prev->br_blockcount << 1;
+	if (prev.br_blockcount <= (MAXEXTLEN >> 1))
+		alloc_blocks = prev.br_blockcount << 1;
 	else
 		alloc_blocks = XFS_B_TO_FSB(mp, offset);
 	if (!alloc_blocks)
@@ -535,11 +536,11 @@ xfs_file_iomap_begin_delay(
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		maxbytes_fsb =
 		XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
-	xfs_fileoff_t		end_fsb, orig_end_fsb;
+	xfs_fileoff_t		end_fsb;
 	int			error = 0, eof = 0;
 	struct xfs_bmbt_irec	got;
-	struct xfs_bmbt_irec	prev;
 	xfs_extnum_t		idx;
+	xfs_fsblock_t		prealloc_blocks = 0;
 
 	ASSERT(!XFS_IS_REALTIME_INODE(ip));
 	ASSERT(!xfs_get_extsz_hint(ip));
@@ -563,9 +564,19 @@ xfs_file_iomap_begin_delay(
 			goto out_unlock;
 	}
 
-	xfs_bmap_search_extents(ip, offset_fsb, XFS_DATA_FORK, &eof, &idx,
-			&got, &prev);
+	eof = !xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got);
 	if (!eof && got.br_startoff <= offset_fsb) {
+		if (xfs_is_reflink_inode(ip)) {
+			bool		shared;
+
+			end_fsb = min(XFS_B_TO_FSB(mp, offset + count),
+					maxbytes_fsb);
+			xfs_trim_extent(&got, offset_fsb, end_fsb - offset_fsb);
+			error = xfs_reflink_reserve_cow(ip, &got, &shared);
+			if (error)
+				goto out_unlock;
+		}
+
 		trace_xfs_iomap_found(ip, offset, count, 0, &got);
 		goto done;
 	}
@@ -584,35 +595,32 @@ xfs_file_iomap_begin_delay(
 	 * the lower level functions are updated.
 	 */
 	count = min_t(loff_t, count, 1024 * PAGE_SIZE);
-	end_fsb = orig_end_fsb =
-		min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb);
+	end_fsb = min(XFS_B_TO_FSB(mp, offset + count), maxbytes_fsb);
 
 	if (eof) {
-		xfs_fsblock_t	prealloc_blocks;
-
-		prealloc_blocks =
-			xfs_iomap_prealloc_size(ip, offset, count, idx, &prev);
+		prealloc_blocks = xfs_iomap_prealloc_size(ip, offset, count, idx);
 		if (prealloc_blocks) {
 			xfs_extlen_t	align;
 			xfs_off_t	end_offset;
+			xfs_fileoff_t	p_end_fsb;
 
 			end_offset = XFS_WRITEIO_ALIGN(mp, offset + count - 1);
-			end_fsb = XFS_B_TO_FSBT(mp, end_offset) +
-				prealloc_blocks;
+			p_end_fsb = XFS_B_TO_FSBT(mp, end_offset) +
+					prealloc_blocks;
 
 			align = xfs_eof_alignment(ip, 0);
 			if (align)
-				end_fsb = roundup_64(end_fsb, align);
+				p_end_fsb = roundup_64(p_end_fsb, align);
 
-			end_fsb = min(end_fsb, maxbytes_fsb);
-			ASSERT(end_fsb > offset_fsb);
+			p_end_fsb = min(p_end_fsb, maxbytes_fsb);
+			ASSERT(p_end_fsb > offset_fsb);
+			prealloc_blocks = p_end_fsb - end_fsb;
 		}
 	}
 
 retry:
 	error = xfs_bmapi_reserve_delalloc(ip, XFS_DATA_FORK, offset_fsb,
-			end_fsb - offset_fsb, &got,
-			&prev, &idx, eof);
+			end_fsb - offset_fsb, prealloc_blocks, &got, &idx, eof);
 	switch (error) {
 	case 0:
 		break;
@@ -620,8 +628,8 @@ xfs_file_iomap_begin_delay(
 	case -EDQUOT:
 		/* retry without any preallocation */
 		trace_xfs_delalloc_enospc(ip, offset, count);
-		if (end_fsb != orig_end_fsb) {
-			end_fsb = orig_end_fsb;
+		if (prealloc_blocks) {
+			prealloc_blocks = 0;
 			goto retry;
 		}
 		/*FALLTHRU*/
@@ -629,13 +637,6 @@ xfs_file_iomap_begin_delay(
 		goto out_unlock;
 	}
 
-	/*
-	 * Tag the inode as speculatively preallocated so we can reclaim this
-	 * space on demand, if necessary.
-	 */
-	if (end_fsb != orig_end_fsb)
-		xfs_inode_set_eofblocks_tag(ip);
-
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -961,19 +962,13 @@ xfs_file_iomap_begin(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_bmbt_irec	imap;
 	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			shared, trimmed;
 	int			nimaps = 1, error = 0;
+	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_reserve_cow_range(ip, offset, length);
-		if (error < 0)
-			return error;
-	}
-
 	if ((flags & IOMAP_WRITE) && !IS_DAX(inode) &&
 		   !xfs_get_extsz_hint(ip)) {
 		/* Reserve delalloc blocks for regular writeback. */
@@ -981,7 +976,16 @@ xfs_file_iomap_begin(
 				iomap);
 	}
 
-	lockmode = xfs_ilock_data_map_shared(ip);
+	/*
+	 * COW writes will allocate delalloc space, so we need to make sure
+	 * to take the lock exclusively here.
+	 */
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		lockmode = XFS_ILOCK_EXCL;
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+	} else {
+		lockmode = xfs_ilock_data_map_shared(ip);
+	}
 
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
@@ -991,16 +995,24 @@ xfs_file_iomap_begin(
 
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
 			       &nimaps, 0);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+	if (error)
+		goto out_unlock;
+
+	if (flags & IOMAP_REPORT) {
+		/* Trim the mapping to the nearest shared extent boundary. */
+		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
+				&trimmed);
+		if (error)
+			goto out_unlock;
 	}
 
-	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
-	if (error) {
-		xfs_iunlock(ip, lockmode);
-		return error;
+	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
+		error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+		if (error)
+			goto out_unlock;
+
+		end_fsb = imap.br_startoff + imap.br_blockcount;
+		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
 	}
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
@@ -1039,6 +1051,9 @@ xfs_file_iomap_begin(
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
+out_unlock:
+	xfs_iunlock(ip, lockmode);
+	return error;
 }
 
 static int

fs/xfs/xfs_mount.c

@@ -1009,6 +1009,7 @@ xfs_mountfs(
  out_quota:
 	xfs_qm_unmount_quotas(mp);
  out_rtunmount:
+	mp->m_super->s_flags &= ~MS_ACTIVE;
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
 	IRELE(rip);

fs/xfs/xfs_qm.c

@@ -1135,7 +1135,7 @@ xfs_qm_get_rtblks(
 			return error;
 	}
 	rtblks = 0;
-	nextents = ifp->if_bytes / (uint)sizeof(xfs_bmbt_rec_t);
+	nextents = xfs_iext_count(ifp);
 	for (idx = 0; idx < nextents; idx++)
 		rtblks += xfs_bmbt_get_blockcount(xfs_iext_get_ext(ifp, idx));
 	*O_rtblks = (xfs_qcnt_t)rtblks;

fs/xfs/xfs_reflink.c

@@ -182,7 +182,8 @@ xfs_reflink_trim_around_shared(
 	if (!xfs_is_reflink_inode(ip) ||
 	    ISUNWRITTEN(irec) ||
 	    irec->br_startblock == HOLESTARTBLOCK ||
-	    irec->br_startblock == DELAYSTARTBLOCK) {
+	    irec->br_startblock == DELAYSTARTBLOCK ||
+	    isnullstartblock(irec->br_startblock)) {
 		*shared = false;
 		return 0;
 	}
@@ -227,50 +228,54 @@ xfs_reflink_trim_around_shared(
 	}
 }
 
-/* Create a CoW reservation for a range of blocks within a file. */
-static int
-__xfs_reflink_reserve_cow(
+/*
+ * Trim the passed in imap to the next shared/unshared extent boundary, and
+ * if imap->br_startoff points to a shared extent reserve space for it in the
+ * COW fork.  In this case *shared is set to true, else to false.
+ *
+ * Note that imap will always contain the block numbers for the existing blocks
+ * in the data fork, as the upper layers need them for read-modify-write
+ * operations.
+ */
+int
+xfs_reflink_reserve_cow(
 	struct xfs_inode	*ip,
-	xfs_fileoff_t		*offset_fsb,
-	xfs_fileoff_t		end_fsb,
-	bool			*skipped)
+	struct xfs_bmbt_irec	*imap,
+	bool			*shared)
 {
-	struct xfs_bmbt_irec	got, prev, imap;
-	xfs_fileoff_t		orig_end_fsb;
-	int			nimaps, eof = 0, error = 0;
-	bool			shared = false, trimmed = false;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec	got;
+	int			error = 0;
+	bool			eof = false, trimmed;
 	xfs_extnum_t		idx;
-	xfs_extlen_t		align;
-
-	/* Already reserved?  Skip the refcount btree access. */
-	xfs_bmap_search_extents(ip, *offset_fsb, XFS_COW_FORK, &eof, &idx,
-			&got, &prev);
-	if (!eof && got.br_startoff <= *offset_fsb) {
-		end_fsb = orig_end_fsb = got.br_startoff + got.br_blockcount;
-		trace_xfs_reflink_cow_found(ip, &got);
-		goto done;
-	}
 
-	/* Read extent from the source file. */
-	nimaps = 1;
-	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
-			&imap, &nimaps, 0);
-	if (error)
-		goto out_unlock;
-	ASSERT(nimaps == 1);
+	/*
+	 * Search the COW fork extent list first.  This serves two purposes:
+	 * first this implement the speculative preallocation using cowextisze,
+	 * so that we also unshared block adjacent to shared blocks instead
+	 * of just the shared blocks themselves.  Second the lookup in the
+	 * extent list is generally faster than going out to the shared extent
+	 * tree.
+	 */
+
+	if (!xfs_iext_lookup_extent(ip, ifp, imap->br_startoff, &idx, &got))
+		eof = true;
+	if (!eof && got.br_startoff <= imap->br_startoff) {
+		trace_xfs_reflink_cow_found(ip, imap);
+		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
+
+		*shared = true;
+		return 0;
+	}
 
 	/* Trim the mapping to the nearest shared extent boundary. */
-	error = xfs_reflink_trim_around_shared(ip, &imap, &shared, &trimmed);
+	error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
 	if (error)
-		goto out_unlock;
-
-	end_fsb = orig_end_fsb = imap.br_startoff + imap.br_blockcount;
+		return error;
 
 	/* Not shared?  Just report the (potentially capped) extent. */
-	if (!shared) {
-		*skipped = true;
-		goto done;
-	}
+	if (!*shared)
+		return 0;
 
 	/*
 	 * Fork all the shared blocks from our write offset until the end of
@@ -278,72 +283,17 @@ __xfs_reflink_reserve_cow(
 	 */
 	error = xfs_qm_dqattach_locked(ip, 0);
 	if (error)
-		goto out_unlock;
-
-	align = xfs_eof_alignment(ip, xfs_get_cowextsz_hint(ip));
-	if (align)
-		end_fsb = roundup_64(end_fsb, align);
-
-retry:
-	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, *offset_fsb,
-			end_fsb - *offset_fsb, &got,
-			&prev, &idx, eof);
-	switch (error) {
-	case 0:
-		break;
-	case -ENOSPC:
-	case -EDQUOT:
-		/* retry without any preallocation */
-		trace_xfs_reflink_cow_enospc(ip, &imap);
-		if (end_fsb != orig_end_fsb) {
-			end_fsb = orig_end_fsb;
-			goto retry;
-		}
-		/*FALLTHRU*/
-	default:
-		goto out_unlock;
-	}
+		return error;
 
-	if (end_fsb != orig_end_fsb)
-		xfs_inode_set_cowblocks_tag(ip);
+	error = xfs_bmapi_reserve_delalloc(ip, XFS_COW_FORK, imap->br_startoff,
+			imap->br_blockcount, 0, &got, &idx, eof);
+	if (error == -ENOSPC || error == -EDQUOT)
+		trace_xfs_reflink_cow_enospc(ip, imap);
+	if (error)
+		return error;
 
 	trace_xfs_reflink_cow_alloc(ip, &got);
-done:
-	*offset_fsb = end_fsb;
-out_unlock:
-	return error;
-}
-
-/* Create a CoW reservation for part of a file. */
-int
-xfs_reflink_reserve_cow_range(
-	struct xfs_inode	*ip,
-	xfs_off_t		offset,
-	xfs_off_t		count)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb, end_fsb;
-	bool			skipped = false;
-	int			error;
-
-	trace_xfs_reflink_reserve_cow_range(ip, offset, count);
-
-	offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	end_fsb = XFS_B_TO_FSB(mp, offset + count);
-
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	while (offset_fsb < end_fsb) {
-		error = __xfs_reflink_reserve_cow(ip, &offset_fsb, end_fsb,
-				&skipped);
-		if (error) {
-			trace_xfs_reflink_reserve_cow_range_error(ip, error,
-				_RET_IP_);
-			break;
-		}
-	}
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
-	return error;
+	return 0;
 }
 
 /* Allocate all CoW reservations covering a range of blocks in a file. */
@@ -358,9 +308,8 @@ __xfs_reflink_allocate_cow(
 	struct xfs_defer_ops	dfops;
 	struct xfs_trans	*tp;
 	xfs_fsblock_t		first_block;
-	xfs_fileoff_t		next_fsb;
 	int			nimaps = 1, error;
-	bool			skipped = false;
+	bool			shared;
 
 	xfs_defer_init(&dfops, &first_block);
 
@@ -371,33 +320,38 @@ __xfs_reflink_allocate_cow(
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
-	next_fsb = *offset_fsb;
-	error = __xfs_reflink_reserve_cow(ip, &next_fsb, end_fsb, &skipped);
+	/* Read extent from the source file. */
+	nimaps = 1;
+	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
+			&imap, &nimaps, 0);
+	if (error)
+		goto out_unlock;
+	ASSERT(nimaps == 1);
+
+	error = xfs_reflink_reserve_cow(ip, &imap, &shared);
 	if (error)
 		goto out_trans_cancel;
 
-	if (skipped) {
-		*offset_fsb = next_fsb;
+	if (!shared) {
+		*offset_fsb = imap.br_startoff + imap.br_blockcount;
 		goto out_trans_cancel;
 	}
 
 	xfs_trans_ijoin(tp, ip, 0);
-	error = xfs_bmapi_write(tp, ip, *offset_fsb, next_fsb - *offset_fsb,
+	error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount,
 			XFS_BMAPI_COWFORK, &first_block,
 			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK),
 			&imap, &nimaps, &dfops);
 	if (error)
 		goto out_trans_cancel;
 
-	/* We might not have been able to map the whole delalloc extent */
-	*offset_fsb = min(*offset_fsb + imap.br_blockcount, next_fsb);
-
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
 		goto out_trans_cancel;
 
 	error = xfs_trans_commit(tp);
 
+	*offset_fsb = imap.br_startoff + imap.br_blockcount;
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
@@ -443,87 +397,65 @@ xfs_reflink_allocate_cow_range(
 }
 
 /*
- * Find the CoW reservation (and whether or not it needs block allocation)
- * for a given byte offset of a file.
+ * Find the CoW reservation for a given byte offset of a file.
  */
 bool
 xfs_reflink_find_cow_mapping(
 	struct xfs_inode		*ip,
 	xfs_off_t			offset,
-	struct xfs_bmbt_irec		*imap,
-	bool				*need_alloc)
+	struct xfs_bmbt_irec		*imap)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_ifork		*ifp;
-	struct xfs_bmbt_rec_host	*gotp;
-	xfs_fileoff_t			bno;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	xfs_fileoff_t			offset_fsb;
+	struct xfs_bmbt_irec		got;
 	xfs_extnum_t			idx;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
 	ASSERT(xfs_is_reflink_inode(ip));
 
-	/* Find the extent in the CoW fork. */
-	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	bno = XFS_B_TO_FSBT(ip->i_mount, offset);
-	gotp = xfs_iext_bno_to_ext(ifp, bno, &idx);
-	if (!gotp)
+	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
+	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
 		return false;
-
-	xfs_bmbt_get_all(gotp, &irec);
-	if (bno >= irec.br_startoff + irec.br_blockcount ||
-	    bno < irec.br_startoff)
+	if (got.br_startoff > offset_fsb)
 		return false;
 
 	trace_xfs_reflink_find_cow_mapping(ip, offset, 1, XFS_IO_OVERWRITE,
-			&irec);
-
-	/* If it's still delalloc, we must allocate later. */
-	*imap = irec;
-	*need_alloc = !!(isnullstartblock(irec.br_startblock));
-
+			&got);
+	*imap = got;
 	return true;
 }
 
 /*
  * Trim an extent to end at the next CoW reservation past offset_fsb.
  */
-int
+void
 xfs_reflink_trim_irec_to_next_cow(
 	struct xfs_inode		*ip,
 	xfs_fileoff_t			offset_fsb,
 	struct xfs_bmbt_irec		*imap)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_ifork		*ifp;
-	struct xfs_bmbt_rec_host	*gotp;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got;
 	xfs_extnum_t			idx;
 
 	if (!xfs_is_reflink_inode(ip))
-		return 0;
+		return;
 
 	/* Find the extent in the CoW fork. */
-	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	gotp = xfs_iext_bno_to_ext(ifp, offset_fsb, &idx);
-	if (!gotp)
-		return 0;
-	xfs_bmbt_get_all(gotp, &irec);
+	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
+		return;
 
 	/* This is the extent before; try sliding up one. */
-	if (irec.br_startoff < offset_fsb) {
-		idx++;
-		if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
-			return 0;
-		gotp = xfs_iext_get_ext(ifp, idx);
-		xfs_bmbt_get_all(gotp, &irec);
+	if (got.br_startoff < offset_fsb) {
+		if (!xfs_iext_get_extent(ifp, idx + 1, &got))
+			return;
 	}
 
-	if (irec.br_startoff >= imap->br_startoff + imap->br_blockcount)
-		return 0;
+	if (got.br_startoff >= imap->br_startoff + imap->br_blockcount)
+		return;
 
-	imap->br_blockcount = irec.br_startoff - imap->br_startoff;
+	imap->br_blockcount = got.br_startoff - imap->br_startoff;
 	trace_xfs_reflink_trim_irec(ip, imap);
-
-	return 0;
 }
 
 /*
@@ -536,58 +468,46 @@ xfs_reflink_cancel_cow_blocks(
 	xfs_fileoff_t			offset_fsb,
 	xfs_fileoff_t			end_fsb)
 {
-	struct xfs_bmbt_irec		irec;
-	xfs_filblks_t			count_fsb;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got, del;
+	xfs_extnum_t			idx;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
 	int				error = 0;
-	int				nimaps;
 
 	if (!xfs_is_reflink_inode(ip))
 		return 0;
+	if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got))
+		return 0;
 
-	/* Go find the old extent in the CoW fork. */
-	while (offset_fsb < end_fsb) {
-		nimaps = 1;
-		count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-		error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
-				&nimaps, XFS_BMAPI_COWFORK);
-		if (error)
-			break;
-		ASSERT(nimaps == 1);
-
-		trace_xfs_reflink_cancel_cow(ip, &irec);
-
-		if (irec.br_startblock == DELAYSTARTBLOCK) {
-			/* Free a delayed allocation. */
-			xfs_mod_fdblocks(ip->i_mount, irec.br_blockcount,
-					false);
-			ip->i_delayed_blks -= irec.br_blockcount;
+	while (got.br_startoff < end_fsb) {
+		del = got;
+		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
+		trace_xfs_reflink_cancel_cow(ip, &del);
 
-			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &irec);
+		if (isnullstartblock(del.br_startblock)) {
+			error = xfs_bmap_del_extent_delay(ip, XFS_COW_FORK,
+					&idx, &got, &del);
 			if (error)
 				break;
-		} else if (irec.br_startblock == HOLESTARTBLOCK) {
-			/* empty */
 		} else {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
 			/* Free the CoW orphan record. */
 			error = xfs_refcount_free_cow_extent(ip->i_mount,
-					&dfops, irec.br_startblock,
-					irec.br_blockcount);
+					&dfops, del.br_startblock,
+					del.br_blockcount);
 			if (error)
 				break;
 
 			xfs_bmap_add_free(ip->i_mount, &dfops,
-					irec.br_startblock, irec.br_blockcount,
+					del.br_startblock, del.br_blockcount,
 					NULL);
 
 			/* Update quota accounting */
 			xfs_trans_mod_dquot_byino(*tpp, ip, XFS_TRANS_DQ_BCOUNT,
-					-(long)irec.br_blockcount);
+					-(long)del.br_blockcount);
 
 			/* Roll the transaction */
 			error = xfs_defer_finish(tpp, &dfops, ip);
@@ -597,15 +517,17 @@ xfs_reflink_cancel_cow_blocks(
 			}
 
 			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &irec);
-			if (error)
-				break;
+			xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
 		}
 
-		/* Roll on... */
-		offset_fsb = irec.br_startoff + irec.br_blockcount;
+		if (!xfs_iext_get_extent(ifp, ++idx, &got))
+			break;
 	}
 
+	/* clear tag if cow fork is emptied */
+	if (!ifp->if_bytes)
+		xfs_inode_clear_cowblocks_tag(ip);
+
 	return error;
 }
 
@@ -668,25 +590,26 @@ xfs_reflink_end_cow(
 	xfs_off_t			offset,
 	xfs_off_t			count)
 {
-	struct xfs_bmbt_irec		irec;
-	struct xfs_bmbt_irec		uirec;
+	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	struct xfs_bmbt_irec		got, del;
 	struct xfs_trans		*tp;
 	xfs_fileoff_t			offset_fsb;
 	xfs_fileoff_t			end_fsb;
-	xfs_filblks_t			count_fsb;
 	xfs_fsblock_t			firstfsb;
 	struct xfs_defer_ops		dfops;
 	int				error;
 	unsigned int			resblks;
-	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
-	int				nimaps;
+	xfs_extnum_t			idx;
 
 	trace_xfs_reflink_end_cow(ip, offset, count);
 
+	/* No COW extents?  That's easy! */
+	if (ifp->if_bytes == 0)
+		return 0;
+
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
-	count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
 
 	/* Start a rolling transaction to switch the mappings */
 	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
@@ -698,72 +621,61 @@ xfs_reflink_end_cow(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	/* Go find the old extent in the CoW fork. */
-	while (offset_fsb < end_fsb) {
-		/* Read extent from the source file */
-		nimaps = 1;
-		count_fsb = (xfs_filblks_t)(end_fsb - offset_fsb);
-		error = xfs_bmapi_read(ip, offset_fsb, count_fsb, &irec,
-				&nimaps, XFS_BMAPI_COWFORK);
-		if (error)
-			goto out_cancel;
-		ASSERT(nimaps == 1);
+	/* If there is a hole at end_fsb - 1 go to the previous extent */
+	if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
+	    got.br_startoff > end_fsb) {
+		ASSERT(idx > 0);
+		xfs_iext_get_extent(ifp, --idx, &got);
+	}
 
-		ASSERT(irec.br_startblock != DELAYSTARTBLOCK);
-		trace_xfs_reflink_cow_remap(ip, &irec);
+	/* Walk backwards until we're out of the I/O range... */
+	while (got.br_startoff + got.br_blockcount > offset_fsb) {
+		del = got;
+		xfs_trim_extent(&del, offset_fsb, end_fsb - offset_fsb);
 
-		/*
-		 * We can have a hole in the CoW fork if part of a directio
-		 * write is CoW but part of it isn't.
-		 */
-		rlen = ilen = irec.br_blockcount;
-		if (irec.br_startblock == HOLESTARTBLOCK)
+		/* Extent delete may have bumped idx forward */
+		if (!del.br_blockcount) {
+			idx--;
 			goto next_extent;
+		}
+
+		ASSERT(!isnullstartblock(got.br_startblock));
 
 		/* Unmap the old blocks in the data fork. */
-		while (rlen) {
-			xfs_defer_init(&dfops, &firstfsb);
-			error = __xfs_bunmapi(tp, ip, irec.br_startoff,
-					&rlen, 0, 1, &firstfsb, &dfops);
-			if (error)
-				goto out_defer;
-
-			/*
-			 * Trim the extent to whatever got unmapped.
-			 * Remember, bunmapi works backwards.
-			 */
-			uirec.br_startblock = irec.br_startblock + rlen;
-			uirec.br_startoff = irec.br_startoff + rlen;
-			uirec.br_blockcount = irec.br_blockcount - rlen;
-			irec.br_blockcount = rlen;
-			trace_xfs_reflink_cow_remap_piece(ip, &uirec);
+		xfs_defer_init(&dfops, &firstfsb);
+		rlen = del.br_blockcount;
+		error = __xfs_bunmapi(tp, ip, del.br_startoff, &rlen, 0, 1,
+				&firstfsb, &dfops);
+		if (error)
+			goto out_defer;
 
-			/* Free the CoW orphan record. */
-			error = xfs_refcount_free_cow_extent(tp->t_mountp,
-					&dfops, uirec.br_startblock,
-					uirec.br_blockcount);
-			if (error)
-				goto out_defer;
+		/* Trim the extent to whatever got unmapped. */
+		if (rlen) {
+			xfs_trim_extent(&del, del.br_startoff + rlen,
+				del.br_blockcount - rlen);
+		}
+		trace_xfs_reflink_cow_remap(ip, &del);
 
-			/* Map the new blocks into the data fork. */
-			error = xfs_bmap_map_extent(tp->t_mountp, &dfops,
-					ip, &uirec);
-			if (error)
-				goto out_defer;
+		/* Free the CoW orphan record. */
+		error = xfs_refcount_free_cow_extent(tp->t_mountp, &dfops,
+				del.br_startblock, del.br_blockcount);
+		if (error)
+			goto out_defer;
 
-			/* Remove the mapping from the CoW fork. */
-			error = xfs_bunmapi_cow(ip, &uirec);
-			if (error)
-				goto out_defer;
+		/* Map the new blocks into the data fork. */
+		error = xfs_bmap_map_extent(tp->t_mountp, &dfops, ip, &del);
+		if (error)
+			goto out_defer;
 
-			error = xfs_defer_finish(&tp, &dfops, ip);
-			if (error)
-				goto out_defer;
-		}
+		/* Remove the mapping from the CoW fork. */
+		xfs_bmap_del_extent_cow(ip, &idx, &got, &del);
 
+		error = xfs_defer_finish(&tp, &dfops, ip);
+		if (error)
+			goto out_defer;
 next_extent:
-		/* Roll on... */
-		offset_fsb = irec.br_startoff + ilen;
+		if (!xfs_iext_get_extent(ifp, idx, &got))
+			break;
 	}
 
 	error = xfs_trans_commit(tp);
@@ -774,7 +686,6 @@ xfs_reflink_end_cow(
 
 out_defer:
 	xfs_defer_cancel(&dfops);
-out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
@@ -1312,19 +1223,26 @@ xfs_compare_extents(
  */
 int
 xfs_reflink_remap_range(
-	struct xfs_inode	*src,
-	xfs_off_t		srcoff,
-	struct xfs_inode	*dest,
-	xfs_off_t		destoff,
-	xfs_off_t		len,
-	unsigned int		flags)
+	struct file		*file_in,
+	loff_t			pos_in,
+	struct file		*file_out,
+	loff_t			pos_out,
+	u64			len,
+	bool			is_dedupe)
 {
+	struct inode		*inode_in = file_inode(file_in);
+	struct xfs_inode	*src = XFS_I(inode_in);
+	struct inode		*inode_out = file_inode(file_out);
+	struct xfs_inode	*dest = XFS_I(inode_out);
 	struct xfs_mount	*mp = src->i_mount;
+	loff_t			bs = inode_out->i_sb->s_blocksize;
+	bool			same_inode = (inode_in == inode_out);
 	xfs_fileoff_t		sfsbno, dfsbno;
 	xfs_filblks_t		fsblen;
-	int			error;
 	xfs_extlen_t		cowextsize;
-	bool			is_same;
+	loff_t			isize;
+	ssize_t			ret;
+	loff_t			blen;
 
 	if (!xfs_sb_version_hasreflink(&mp->m_sb))
 		return -EOPNOTSUPP;
@@ -1332,17 +1250,8 @@ xfs_reflink_remap_range(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	/* Don't reflink realtime inodes */
-	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
-		return -EINVAL;
-
-	if (flags & ~XFS_REFLINK_ALL)
-		return -EINVAL;
-
-	trace_xfs_reflink_remap_range(src, srcoff, len, dest, destoff);
-
 	/* Lock both files against IO */
-	if (src->i_ino == dest->i_ino) {
+	if (same_inode) {
 		xfs_ilock(src, XFS_IOLOCK_EXCL);
 		xfs_ilock(src, XFS_MMAPLOCK_EXCL);
 	} else {
@@ -1350,39 +1259,132 @@ xfs_reflink_remap_range(
 		xfs_lock_two_inodes(src, dest, XFS_MMAPLOCK_EXCL);
 	}
 
+	/* Don't touch certain kinds of inodes */
+	ret = -EPERM;
+	if (IS_IMMUTABLE(inode_out))
+		goto out_unlock;
+
+	ret = -ETXTBSY;
+	if (IS_SWAPFILE(inode_in) || IS_SWAPFILE(inode_out))
+		goto out_unlock;
+
+
+	/* Don't reflink dirs, pipes, sockets... */
+	ret = -EISDIR;
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		goto out_unlock;
+	ret = -EINVAL;
+	if (S_ISFIFO(inode_in->i_mode) || S_ISFIFO(inode_out->i_mode))
+		goto out_unlock;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		goto out_unlock;
+
+	/* Don't reflink realtime inodes */
+	if (XFS_IS_REALTIME_INODE(src) || XFS_IS_REALTIME_INODE(dest))
+		goto out_unlock;
+
+	/* Don't share DAX file data for now. */
+	if (IS_DAX(inode_in) || IS_DAX(inode_out))
+		goto out_unlock;
+
+	/* Are we going all the way to the end? */
+	isize = i_size_read(inode_in);
+	if (isize == 0) {
+		ret = 0;
+		goto out_unlock;
+	}
+
+	/* Zero length dedupe exits immediately; reflink goes to EOF. */
+	if (len == 0) {
+		if (is_dedupe) {
+			ret = 0;
+			goto out_unlock;
+		}
+		len = isize - pos_in;
+	}
+
+	/* Ensure offsets don't wrap and the input is inside i_size */
+	if (pos_in + len < pos_in || pos_out + len < pos_out ||
+	    pos_in + len > isize)
+		goto out_unlock;
+
+	/* Don't allow dedupe past EOF in the dest file */
+	if (is_dedupe) {
+		loff_t	disize;
+
+		disize = i_size_read(inode_out);
+		if (pos_out >= disize || pos_out + len > disize)
+			goto out_unlock;
+	}
+
+	/* If we're linking to EOF, continue to the block boundary. */
+	if (pos_in + len == isize)
+		blen = ALIGN(isize, bs) - pos_in;
+	else
+		blen = len;
+
+	/* Only reflink if we're aligned to block boundaries */
+	if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) ||
+	    !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs))
+		goto out_unlock;
+
+	/* Don't allow overlapped reflink within the same file */
+	if (same_inode) {
+		if (pos_out + blen > pos_in && pos_out < pos_in + blen)
+			goto out_unlock;
+	}
+
+	/* Wait for the completion of any pending IOs on both files */
+	inode_dio_wait(inode_in);
+	if (!same_inode)
+		inode_dio_wait(inode_out);
+
+	ret = filemap_write_and_wait_range(inode_in->i_mapping,
+			pos_in, pos_in + len - 1);
+	if (ret)
+		goto out_unlock;
+
+	ret = filemap_write_and_wait_range(inode_out->i_mapping,
+			pos_out, pos_out + len - 1);
+	if (ret)
+		goto out_unlock;
+
+	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
+
 	/*
 	 * Check that the extents are the same.
 	 */
-	if (flags & XFS_REFLINK_DEDUPE) {
-		is_same = false;
-		error = xfs_compare_extents(VFS_I(src), srcoff, VFS_I(dest),
-				destoff, len, &is_same);
-		if (error)
-			goto out_error;
+	if (is_dedupe) {
+		bool		is_same = false;
+
+		ret = xfs_compare_extents(inode_in, pos_in, inode_out, pos_out,
+				len, &is_same);
+		if (ret)
+			goto out_unlock;
 		if (!is_same) {
-			error = -EBADE;
-			goto out_error;
+			ret = -EBADE;
+			goto out_unlock;
 		}
 	}
 
-	error = xfs_reflink_set_inode_flag(src, dest);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_set_inode_flag(src, dest);
+	if (ret)
+		goto out_unlock;
 
 	/*
 	 * Invalidate the page cache so that we can clear any CoW mappings
 	 * in the destination file.
 	 */
-	truncate_inode_pages_range(&VFS_I(dest)->i_data, destoff,
-				   PAGE_ALIGN(destoff + len) - 1);
+	truncate_inode_pages_range(&inode_out->i_data, pos_out,
+				   PAGE_ALIGN(pos_out + len) - 1);
 
-	dfsbno = XFS_B_TO_FSBT(mp, destoff);
-	sfsbno = XFS_B_TO_FSBT(mp, srcoff);
+	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
+	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
 	fsblen = XFS_B_TO_FSB(mp, len);
-	error = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
-			destoff + len);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_remap_blocks(src, sfsbno, dest, dfsbno, fsblen,
+			pos_out + len);
+	if (ret)
+		goto out_unlock;
 
 	/*
 	 * Carry the cowextsize hint from src to dest if we're sharing the
@@ -1390,26 +1392,24 @@ xfs_reflink_remap_range(
 	 * has a cowextsize hint, and the destination file does not.
 	 */
 	cowextsize = 0;
-	if (srcoff == 0 && len == i_size_read(VFS_I(src)) &&
+	if (pos_in == 0 && len == i_size_read(inode_in) &&
 	    (src->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) &&
-	    destoff == 0 && len >= i_size_read(VFS_I(dest)) &&
+	    pos_out == 0 && len >= i_size_read(inode_out) &&
 	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
 		cowextsize = src->i_d.di_cowextsize;
 
-	error = xfs_reflink_update_dest(dest, destoff + len, cowextsize);
-	if (error)
-		goto out_error;
+	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize);
 
-out_error:
+out_unlock:
 	xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
 	xfs_iunlock(src, XFS_IOLOCK_EXCL);
 	if (src->i_ino != dest->i_ino) {
 		xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
 		xfs_iunlock(dest, XFS_IOLOCK_EXCL);
 	}
-	if (error)
-		trace_xfs_reflink_remap_range_error(dest, error, _RET_IP_);
-	return error;
+	if (ret)
+		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
+	return ret;
 }
 
 /*
@@ -1652,37 +1652,3 @@ xfs_reflink_unshare(
 	trace_xfs_reflink_unshare_error(ip, error, _RET_IP_);
 	return error;
 }
-
-/*
- * Does this inode have any real CoW reservations?
- */
-bool
-xfs_reflink_has_real_cow_blocks(
-	struct xfs_inode		*ip)
-{
-	struct xfs_bmbt_irec		irec;
-	struct xfs_ifork		*ifp;
-	struct xfs_bmbt_rec_host	*gotp;
-	xfs_extnum_t			idx;
-
-	if (!xfs_is_reflink_inode(ip))
-		return false;
-
-	/* Go find the old extent in the CoW fork. */
-	ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
-	gotp = xfs_iext_bno_to_ext(ifp, 0, &idx);
-	while (gotp) {
-		xfs_bmbt_get_all(gotp, &irec);
-
-		if (!isnullstartblock(irec.br_startblock))
-			return true;
-
-		/* Roll on... */
-		idx++;
-		if (idx >= ifp->if_bytes / sizeof(xfs_bmbt_rec_t))
-			break;
-		gotp = xfs_iext_get_ext(ifp, idx);
-	}
-
-	return false;
-}

fs/xfs/xfs_reflink.h

@@ -26,13 +26,13 @@ extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
 
-extern int xfs_reflink_reserve_cow_range(struct xfs_inode *ip,
-		xfs_off_t offset, xfs_off_t count);
+extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap, bool *shared);
 extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
 		xfs_off_t offset, xfs_off_t count);
 extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
-		struct xfs_bmbt_irec *imap, bool *need_alloc);
-extern int xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap);
+extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
 		xfs_fileoff_t offset_fsb, struct xfs_bmbt_irec *imap);
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
@@ -43,16 +43,11 @@ extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
 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);
-#define XFS_REFLINK_DEDUPE	1	/* only reflink if contents match */
-#define XFS_REFLINK_ALL		(XFS_REFLINK_DEDUPE)
-extern int xfs_reflink_remap_range(struct xfs_inode *src, xfs_off_t srcoff,
-		struct xfs_inode *dest, xfs_off_t destoff, xfs_off_t len,
-		unsigned int flags);
+extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
+		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
 		struct xfs_trans **tpp);
 extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t len);
 
-extern bool xfs_reflink_has_real_cow_blocks(struct xfs_inode *ip);
-
 #endif /* __XFS_REFLINK_H */

fs/xfs/xfs_sysfs.c

@@ -512,13 +512,13 @@ static struct attribute *xfs_error_attrs[] = {
 };
 
 
-struct kobj_type xfs_error_cfg_ktype = {
+static struct kobj_type xfs_error_cfg_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 	.default_attrs = xfs_error_attrs,
 };
 
-struct kobj_type xfs_error_ktype = {
+static struct kobj_type xfs_error_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 };

fs/xfs/xfs_trace.h

@@ -3346,7 +3346,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
 
-DEFINE_RW_EVENT(xfs_reflink_reserve_cow_range);
+DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
 DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
 
 DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
@@ -3356,9 +3356,7 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
-DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_piece);
 
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_reserve_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);

include/linux/iomap.h

@@ -19,11 +19,15 @@ struct vm_fault;
 #define IOMAP_UNWRITTEN	0x04	/* blocks allocated @blkno in unwritten state */
 
 /*
- * Flags for iomap mappings:
+ * Flags for all iomap mappings:
  */
-#define IOMAP_F_MERGED	0x01	/* contains multiple blocks/extents */
-#define IOMAP_F_SHARED	0x02	/* block shared with another file */
-#define IOMAP_F_NEW	0x04	/* blocks have been newly allocated */
+#define IOMAP_F_NEW	0x01	/* blocks have been newly allocated */
+
+/*
+ * Flags that only need to be reported for IOMAP_REPORT requests:
+ */
+#define IOMAP_F_MERGED	0x10	/* contains multiple blocks/extents */
+#define IOMAP_F_SHARED	0x20	/* block shared with another file */
 
 /*
  * Magic value for blkno:
@@ -42,8 +46,9 @@ struct iomap {
 /*
  * Flags for iomap_begin / iomap_end.  No flag implies a read.
  */
-#define IOMAP_WRITE		(1 << 0)
-#define IOMAP_ZERO		(1 << 1)
+#define IOMAP_WRITE		(1 << 0) /* writing, must allocate blocks */
+#define IOMAP_ZERO		(1 << 1) /* zeroing operation, may skip holes */
+#define IOMAP_REPORT		(1 << 2) /* report extent status, e.g. FIEMAP */
 #define IOMAP_FAULT		(1 << 3) /* mapping for page fault */
 
 struct iomap_ops {