1 files changed, 137 insertions, 103 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 19e11d1da660..06ca11731e43 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -29,6 +29,8 @@
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -41,16 +43,12 @@ xfs_daddr_t
 xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb)
 {
 	if (XFS_IS_REALTIME_INODE(ip))
-		return XFS_FSB_TO_BB(ip->i_mount, fsb);
+		return xfs_rtb_to_daddr(ip->i_mount, fsb);
 	return XFS_FSB_TO_DADDR(ip->i_mount, fsb);
 }
 
 /*
  * Routine to zero an extent on disk allocated to the specific inode.
- *
- * The VFS functions take a linearised filesystem block offset, so we have to
- * convert the sparse xfs fsb to the right format first.
- * VFS types are real funky, too.
  */
 int
 xfs_zero_extent(
@@ -58,15 +56,10 @@ xfs_zero_extent(
 	xfs_fsblock_t		start_fsb,
 	xfs_off_t		count_fsb)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
-	xfs_daddr_t		sector = xfs_fsb_to_db(ip, start_fsb);
-	sector_t		block = XFS_BB_TO_FSBT(mp, sector);
-
-	return blkdev_issue_zeroout(target->bt_bdev,
-		block << (mp->m_super->s_blocksize_bits - 9),
-		count_fsb << (mp->m_super->s_blocksize_bits - 9),
-		GFP_KERNEL, 0);
+	return blkdev_issue_zeroout(xfs_inode_buftarg(ip)->bt_bdev,
+			xfs_fsb_to_db(ip, start_fsb),
+			XFS_FSB_TO_BB(ip->i_mount, count_fsb),
+			GFP_KERNEL, 0);
 }
 
 /*
@@ -111,7 +104,7 @@ xfs_bmap_count_blocks(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	struct xfs_btree_cur	*cur;
-	xfs_extlen_t		btblocks = 0;
+	xfs_filblks_t		btblocks = 0;
 	int			error;
 
 	*nextents = 0;
@@ -331,8 +324,7 @@ xfs_getbmap(
 		}
 
 		if (xfs_get_extsz_hint(ip) ||
-		    (ip->i_diflags &
-		     (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)))
+		    (ip->i_diflags & XFS_DIFLAG_PREALLOC))
 			max_len = mp->m_super->s_maxbytes;
 		else
 			max_len = XFS_ISIZE(ip);
@@ -440,19 +432,20 @@ out_unlock_iolock:
  * if the ranges only partially overlap them, so it is up to the caller to
  * ensure that partial blocks are not passed in.
  */
-int
+void
 xfs_bmap_punch_delalloc_range(
 	struct xfs_inode	*ip,
+	int			whichfork,
 	xfs_off_t		start_byte,
-	xfs_off_t		end_byte)
+	xfs_off_t		end_byte,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_ifork	*ifp = &ip->i_df;
+	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
 	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, start_byte);
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, end_byte);
 	struct xfs_bmbt_irec	got, del;
 	struct xfs_iext_cursor	icur;
-	int			error = 0;
 
 	ASSERT(!xfs_need_iread_extents(ifp));
 
@@ -476,33 +469,46 @@ xfs_bmap_punch_delalloc_range(
 			continue;
 		}
 
-		error = xfs_bmap_del_extent_delay(ip, XFS_DATA_FORK, &icur,
-						  &got, &del);
-		if (error || !xfs_iext_get_extent(ifp, &icur, &got))
+		if (xfs_is_zoned_inode(ip) && ac) {
+			/*
+			 * In a zoned buffered write context we need to return
+			 * the punched delalloc allocations to the allocation
+			 * context.  This allows reusing them in the following
+			 * iomap iterations.
+			 */
+			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,
+					&del, XFS_BMAPI_REMAP);
+			ac->reserved_blocks += del.br_blockcount;
+		} else {
+			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,
+					&del, 0);
+		}
+
+		if (!xfs_iext_get_extent(ifp, &icur, &got))
 			break;
 	}
 
+	if (whichfork == XFS_COW_FORK && !ifp->if_bytes)
+		xfs_inode_clear_cowblocks_tag(ip);
+
 out_unlock:
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-	return error;
 }
 
 /*
  * Test whether it is appropriate to check an inode for and free post EOF
- * blocks. The 'force' parameter determines whether we should also consider
- * regular files that are marked preallocated or append-only.
+ * blocks.
  */
 bool
 xfs_can_free_eofblocks(
-	struct xfs_inode	*ip,
-	bool			force)
+	struct xfs_inode	*ip)
 {
-	struct xfs_bmbt_irec	imap;
 	struct xfs_mount	*mp = ip->i_mount;
+	bool			found_blocks = false;
 	xfs_fileoff_t		end_fsb;
 	xfs_fileoff_t		last_fsb;
-	int			nimaps = 1;
-	int			error;
+	struct xfs_bmbt_irec	imap;
+	struct xfs_iext_cursor	icur;
 
 	/*
 	 * Caller must either hold the exclusive io lock; or be inactivating
@@ -529,12 +535,11 @@ xfs_can_free_eofblocks(
 		return false;
 
 	/*
-	 * Do not free real preallocated or append-only files unless the file
-	 * has delalloc blocks and we are forced to remove them.
+	 * Do not free real extents in preallocated files unless the file has
+	 * delalloc blocks and we are forced to remove them.
 	 */
-	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND))
-		if (!force || ip->i_delayed_blks == 0)
-			return false;
+	if ((ip->i_diflags & XFS_DIFLAG_PREALLOC) && !ip->i_delayed_blks)
+		return false;
 
 	/*
 	 * Do not try to free post-EOF blocks if EOF is beyond the end of the
@@ -542,28 +547,24 @@ xfs_can_free_eofblocks(
 	 * forever.
 	 */
 	end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)XFS_ISIZE(ip));
-	if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1)
-		end_fsb = xfs_rtb_roundup_rtx(mp, end_fsb);
+	if (xfs_inode_has_bigrtalloc(ip))
+		end_fsb = xfs_fileoff_roundup_rtx(mp, end_fsb);
 	last_fsb = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
 	if (last_fsb <= end_fsb)
 		return false;
 
 	/*
-	 * Look up the mapping for the first block past EOF.  If we can't find
-	 * it, there's nothing to free.
+	 * Check if there is an post-EOF extent to free.  If there are any
+	 * delalloc blocks attached to the inode (data fork delalloc
+	 * reservations or CoW extents of any kind), we need to free them so
+	 * that inactivation doesn't fail to erase them.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
-	error = xfs_bmapi_read(ip, end_fsb, last_fsb - end_fsb, &imap, &nimaps,
-			0);
+	if (ip->i_delayed_blks ||
+	    xfs_iext_lookup_extent(ip, &ip->i_df, end_fsb, &icur, &imap))
+		found_blocks = true;
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-	if (error || nimaps == 0)
-		return false;
-
-	/*
-	 * If there's a real mapping there or there are delayed allocation
-	 * reservations, then we have post-EOF blocks to try to free.
-	 */
-	return imap.br_startblock != HOLESTARTBLOCK || ip->i_delayed_blks;
+	return found_blocks;
 }
 
 /*
@@ -587,6 +588,22 @@ xfs_free_eofblocks(
 	/* Wait on dio to ensure i_size has settled. */
 	inode_dio_wait(VFS_I(ip));
 
+	/*
+	 * For preallocated files only free delayed allocations.
+	 *
+	 * Note that this means we also leave speculative preallocations in
+	 * place for preallocated files.
+	 */
+	if (ip->i_diflags & (XFS_DIFLAG_PREALLOC | XFS_DIFLAG_APPEND)) {
+		if (ip->i_delayed_blks) {
+			xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK,
+				round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize),
+				LLONG_MAX, NULL);
+		}
+		xfs_inode_clear_eofblocks_tag(ip);
+		return 0;
+	}
+
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
 	if (error) {
 		ASSERT(xfs_is_shutdown(mp));
@@ -642,6 +659,9 @@ xfs_alloc_file_space(
 	xfs_bmbt_irec_t		imaps[1], *imapp;
 	int			error;
 
+	if (xfs_is_always_cow_inode(ip))
+		return 0;
+
 	trace_xfs_alloc_file_space(ip);
 
 	if (xfs_is_shutdown(mp))
@@ -713,41 +733,37 @@ xfs_alloc_file_space(
 		if (error)
 			break;
 
-		error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
+		error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
 				XFS_IEXT_ADD_NOSPLIT_CNT);
-		if (error == -EFBIG)
-			error = xfs_iext_count_upgrade(tp, ip,
-					XFS_IEXT_ADD_NOSPLIT_CNT);
-		if (error)
-			goto error;
-
-		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
-				allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
-				&nimaps);
 		if (error)
 			goto error;
 
-		ip->i_diflags |= XFS_DIFLAG_PREALLOC;
-		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
-
-		error = xfs_trans_commit(tp);
-		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		if (error)
-			break;
-
 		/*
 		 * If the allocator cannot find a single free extent large
 		 * enough to cover the start block of the requested range,
-		 * xfs_bmapi_write will return 0 but leave *nimaps set to 0.
+		 * xfs_bmapi_write will return -ENOSR.
 		 *
 		 * In that case we simply need to keep looping with the same
 		 * startoffset_fsb so that one of the following allocations
 		 * will eventually reach the requested range.
 		 */
-		if (nimaps) {
+		error = xfs_bmapi_write(tp, ip, startoffset_fsb,
+				allocatesize_fsb, XFS_BMAPI_PREALLOC, 0, imapp,
+				&nimaps);
+		if (error) {
+			if (error != -ENOSR)
+				goto error;
+			error = 0;
+		} else {
 			startoffset_fsb += imapp->br_blockcount;
 			allocatesize_fsb -= imapp->br_blockcount;
 		}
+
+		ip->i_diflags |= XFS_DIFLAG_PREALLOC;
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+		error = xfs_trans_commit(tp);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	}
 
 	return error;
@@ -775,10 +791,8 @@ xfs_unmap_extent(
 	if (error)
 		return error;
 
-	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
+	error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
 			XFS_IEXT_PUNCH_HOLE_CNT);
-	if (error == -EFBIG)
-		error = xfs_iext_count_upgrade(tp, ip, XFS_IEXT_PUNCH_HOLE_CNT);
 	if (error)
 		goto out_trans_cancel;
 
@@ -803,14 +817,18 @@ xfs_flush_unmap_range(
 	xfs_off_t		offset,
 	xfs_off_t		len)
 {
-	struct xfs_mount	*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
 	xfs_off_t		rounding, start, end;
 	int			error;
 
-	rounding = max_t(xfs_off_t, mp->m_sb.sb_blocksize, PAGE_SIZE);
-	start = round_down(offset, rounding);
-	end = round_up(offset + len, rounding) - 1;
+	/*
+	 * Make sure we extend the flush out to extent alignment
+	 * boundaries so any extent range overlapping the start/end
+	 * of the modification we are about to do is clean and idle.
+	 */
+	rounding = max_t(xfs_off_t, xfs_inode_alloc_unitsize(ip), PAGE_SIZE);
+	start = rounddown_64(offset, rounding);
+	end = roundup_64(offset + len, rounding) - 1;
 
 	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (error)
@@ -823,7 +841,8 @@ int
 xfs_free_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len)
+	xfs_off_t		len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		startoffset_fsb;
@@ -839,13 +858,21 @@ xfs_free_file_space(
 	if (len <= 0)	/* if nothing being freed */
 		return 0;
 
+	/*
+	 * Now AIO and DIO has drained we flush and (if necessary) invalidate
+	 * the cached range over the first operation we are about to run.
+	 */
+	error = xfs_flush_unmap_range(ip, offset, len);
+	if (error)
+		return error;
+
 	startoffset_fsb = XFS_B_TO_FSB(mp, offset);
 	endoffset_fsb = XFS_B_TO_FSBT(mp, offset + len);
 
 	/* We can only free complete realtime extents. */
-	if (XFS_IS_REALTIME_INODE(ip) && mp->m_sb.sb_rextsize > 1) {
-		startoffset_fsb = xfs_rtb_roundup_rtx(mp, startoffset_fsb);
-		endoffset_fsb = xfs_rtb_rounddown_rtx(mp, endoffset_fsb);
+	if (xfs_inode_has_bigrtalloc(ip)) {
+		startoffset_fsb = xfs_fileoff_roundup_rtx(mp, startoffset_fsb);
+		endoffset_fsb = xfs_fileoff_rounddown_rtx(mp, endoffset_fsb);
 	}
 
 	/*
@@ -870,7 +897,7 @@ xfs_free_file_space(
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = xfs_zero_range(ip, offset, len, NULL);
+	error = xfs_zero_range(ip, offset, len, ac, NULL);
 	if (error)
 		return error;
 
@@ -893,14 +920,14 @@ xfs_prepare_shift(
 	struct xfs_inode	*ip,
 	loff_t			offset)
 {
-	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		rounding;
 	int			error;
 
 	/*
 	 * Trim eofblocks to avoid shifting uninitialized post-eof preallocation
 	 * into the accessible region of the file.
 	 */
-	if (xfs_can_free_eofblocks(ip, true)) {
+	if (xfs_can_free_eofblocks(ip)) {
 		error = xfs_free_eofblocks(ip);
 		if (error)
 			return error;
@@ -911,11 +938,13 @@ xfs_prepare_shift(
 	 * with the full range of the operation. If we don't, a COW writeback
 	 * completion could race with an insert, front merge with the start
 	 * extent (after split) during the shift and corrupt the file. Start
-	 * with the block just prior to the start to stabilize the boundary.
+	 * with the allocation unit just prior to the start to stabilize the
+	 * boundary.
 	 */
-	offset = round_down(offset, mp->m_sb.sb_blocksize);
+	rounding = xfs_inode_alloc_unitsize(ip);
+	offset = rounddown_64(offset, rounding);
 	if (offset)
-		offset -= mp->m_sb.sb_blocksize;
+		offset -= rounding;
 
 	/*
 	 * Writeback and invalidate cache for the remainder of the file as we're
@@ -956,7 +985,8 @@ int
 xfs_collapse_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len)
+	xfs_off_t		len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
@@ -969,7 +999,7 @@ xfs_collapse_file_space(
 
 	trace_xfs_collapse_file_space(ip);
 
-	error = xfs_free_file_space(ip, offset, len);
+	error = xfs_free_file_space(ip, offset, len, ac);
 	if (error)
 		return error;
 
@@ -1054,10 +1084,8 @@ xfs_insert_file_space(
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
 	xfs_trans_ijoin(tp, ip, 0);
 
-	error = xfs_iext_count_may_overflow(ip, XFS_DATA_FORK,
+	error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
 			XFS_IEXT_PUNCH_HOLE_CNT);
-	if (error == -EFBIG)
-		error = xfs_iext_count_upgrade(tp, ip, XFS_IEXT_PUNCH_HOLE_CNT);
 	if (error)
 		goto out_trans_cancel;
 
@@ -1175,7 +1203,7 @@ xfs_swap_extents_check_format(
 	 */
 	if (tifp->if_format == XFS_DINODE_FMT_BTREE) {
 		if (xfs_inode_has_attr_fork(ip) &&
-		    XFS_BMAP_BMDR_SPACE(tifp->if_broot) > xfs_inode_fork_boff(ip))
+		    xfs_bmap_bmdr_space(tifp->if_broot) > xfs_inode_fork_boff(ip))
 			return -EINVAL;
 		if (tifp->if_nextents <= XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK))
 			return -EINVAL;
@@ -1184,7 +1212,7 @@ xfs_swap_extents_check_format(
 	/* Reciprocal target->temp btree format checks */
 	if (ifp->if_format == XFS_DINODE_FMT_BTREE) {
 		if (xfs_inode_has_attr_fork(tip) &&
-		    XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > xfs_inode_fork_boff(tip))
+		    xfs_bmap_bmdr_space(ip->i_df.if_broot) > xfs_inode_fork_boff(tip))
 			return -EINVAL;
 		if (ifp->if_nextents <= XFS_IFORK_MAXEXT(tip, XFS_DATA_FORK))
 			return -EINVAL;
@@ -1283,23 +1311,17 @@ xfs_swap_extent_rmap(
 			trace_xfs_swap_extent_rmap_remap_piece(tip, &uirec);
 
 			if (xfs_bmap_is_real_extent(&uirec)) {
-				error = xfs_iext_count_may_overflow(ip,
+				error = xfs_iext_count_extend(tp, ip,
 						XFS_DATA_FORK,
 						XFS_IEXT_SWAP_RMAP_CNT);
-				if (error == -EFBIG)
-					error = xfs_iext_count_upgrade(tp, ip,
-							XFS_IEXT_SWAP_RMAP_CNT);
 				if (error)
 					goto out;
 			}
 
 			if (xfs_bmap_is_real_extent(&irec)) {
-				error = xfs_iext_count_may_overflow(tip,
+				error = xfs_iext_count_extend(tp, tip,
 						XFS_DATA_FORK,
 						XFS_IEXT_SWAP_RMAP_CNT);
-				if (error == -EFBIG)
-					error = xfs_iext_count_upgrade(tp, ip,
-							XFS_IEXT_SWAP_RMAP_CNT);
 				if (error)
 					goto out;
 			}
@@ -1519,6 +1541,18 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
+	/*
+	 * The rmapbt implementation is unable to resume a swapext operation
+	 * after a crash if the allocation unit size is larger than a block.
+	 * This (deprecated) interface will not be upgraded to handle this
+	 * situation.  Defragmentation must be performed with the commit range
+	 * ioctl.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip) && xfs_has_rtgroups(ip->i_mount)) {
+		error = -EOPNOTSUPP;
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqattach(ip);
 	if (error)
 		goto out_unlock;