1 files changed, 152 insertions, 69 deletions

diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index efb8ccd6bbf2..cb62871fb91d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -84,6 +84,7 @@ xfs_zero_extent(
 		GFP_NOFS, true);
 }
 
+#ifdef CONFIG_XFS_RT
 int
 xfs_bmap_rtalloc(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
@@ -195,6 +196,7 @@ xfs_bmap_rtalloc(
 	}
 	return 0;
 }
+#endif /* CONFIG_XFS_RT */
 
 /*
  * Check if the endoff is outside the last extent. If so the caller will grow
@@ -588,9 +590,13 @@ xfs_getbmap(
 		}
 		break;
 	default:
+		/* Local format data forks report no extents. */
+		if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+			bmv->bmv_entries = 0;
+			return 0;
+		}
 		if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
-		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
-		    ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
+		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE)
 			return -EINVAL;
 
 		if (xfs_get_extsz_hint(ip) ||
@@ -718,7 +724,7 @@ xfs_getbmap(
 			 * extents.
 			 */
 			if (map[i].br_startblock == DELAYSTARTBLOCK &&
-			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+			    map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
 				ASSERT((iflags & BMV_IF_DELALLOC) != 0);
 
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
@@ -911,23 +917,22 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 }
 
 /*
- * This is called by xfs_inactive to free any blocks beyond eof
- * when the link count isn't zero and by xfs_dm_punch_hole() when
- * punching a hole to EOF.
+ * This is called to free any blocks beyond eof. The caller must hold
+ * IOLOCK_EXCL unless we are in the inode reclaim path and have the only
+ * reference to the inode.
  */
 int
 xfs_free_eofblocks(
-	xfs_mount_t	*mp,
-	xfs_inode_t	*ip,
-	bool		need_iolock)
+	struct xfs_inode	*ip)
 {
-	xfs_trans_t	*tp;
-	int		error;
-	xfs_fileoff_t	end_fsb;
-	xfs_fileoff_t	last_fsb;
-	xfs_filblks_t	map_len;
-	int		nimaps;
-	xfs_bmbt_irec_t	imap;
+	struct xfs_trans	*tp;
+	int			error;
+	xfs_fileoff_t		end_fsb;
+	xfs_fileoff_t		last_fsb;
+	xfs_filblks_t		map_len;
+	int			nimaps;
+	struct xfs_bmbt_irec	imap;
+	struct xfs_mount	*mp = ip->i_mount;
 
 	/*
 	 * Figure out if there are any blocks beyond the end
@@ -944,6 +949,10 @@ xfs_free_eofblocks(
 	error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
+	/*
+	 * If there are blocks after the end of file, truncate the file to its
+	 * current size to free them up.
+	 */
 	if (!error && (nimaps != 0) &&
 	    (imap.br_startblock != HOLESTARTBLOCK ||
 	     ip->i_delayed_blks)) {
@@ -954,22 +963,13 @@ xfs_free_eofblocks(
 		if (error)
 			return error;
 
-		/*
-		 * There are blocks after the end of file.
-		 * Free them up now by truncating the file to
-		 * its current size.
-		 */
-		if (need_iolock) {
-			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
-				return -EAGAIN;
-		}
+		/* wait on dio to ensure i_size has settled */
+		inode_dio_wait(VFS_I(ip));
 
 		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0,
 				&tp);
 		if (error) {
 			ASSERT(XFS_FORCED_SHUTDOWN(mp));
-			if (need_iolock)
-				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 			return error;
 		}
 
@@ -997,8 +997,6 @@ xfs_free_eofblocks(
 		}
 
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		if (need_iolock)
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	}
 	return error;
 }
@@ -1324,8 +1322,16 @@ xfs_free_file_space(
 	/*
 	 * Now that we've unmap all full blocks we'll have to zero out any
 	 * partial block at the beginning and/or end.  xfs_zero_range is
-	 * smart enough to skip any holes, including those we just created.
+	 * smart enough to skip any holes, including those we just created,
+	 * but we must take care not to zero beyond EOF and enlarge i_size.
 	 */
+
+	if (offset >= XFS_ISIZE(ip))
+		return 0;
+
+	if (offset + len > XFS_ISIZE(ip))
+		len = XFS_ISIZE(ip) - offset;
+
 	return xfs_zero_range(ip, offset, len, NULL);
 }
 
@@ -1393,10 +1399,16 @@ xfs_shift_file_space(
 	xfs_fileoff_t		stop_fsb;
 	xfs_fileoff_t		next_fsb;
 	xfs_fileoff_t		shift_fsb;
+	uint			resblks;
 
 	ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT);
 
 	if (direction == SHIFT_LEFT) {
+		/*
+		 * Reserve blocks to cover potential extent merges after left
+		 * shift operations.
+		 */
+		resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
 		next_fsb = XFS_B_TO_FSB(mp, offset + len);
 		stop_fsb = XFS_B_TO_FSB(mp, VFS_I(ip)->i_size);
 	} else {
@@ -1404,6 +1416,7 @@ xfs_shift_file_space(
 		 * If right shift, delegate the work of initialization of
 		 * next_fsb to xfs_bmap_shift_extent as it has ilock held.
 		 */
+		resblks = 0;
 		next_fsb = NULLFSBLOCK;
 		stop_fsb = XFS_B_TO_FSB(mp, offset);
 	}
@@ -1415,7 +1428,7 @@ xfs_shift_file_space(
 	 * into the accessible region of the file.
 	 */
 	if (xfs_can_free_eofblocks(ip, true)) {
-		error = xfs_free_eofblocks(mp, ip, false);
+		error = xfs_free_eofblocks(ip);
 		if (error)
 			return error;
 	}
@@ -1434,7 +1447,19 @@ xfs_shift_file_space(
 		return error;
 
 	/*
-	 * The extent shiting code works on extent granularity. So, if
+	 * Clean out anything hanging around in the cow fork now that
+	 * we've flushed all the dirty data out to disk to avoid having
+	 * CoW extents at the wrong offsets.
+	 */
+	if (xfs_is_reflink_inode(ip)) {
+		error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
+				true);
+		if (error)
+			return error;
+	}
+
+	/*
+	 * The extent shifting code works on extent granularity. So, if
 	 * stop_fsb is not the starting block of extent, we need to split
 	 * the extent at stop_fsb.
 	 */
@@ -1445,21 +1470,14 @@ xfs_shift_file_space(
 	}
 
 	while (!error && !done) {
-		/*
-		 * We would need to reserve permanent block for transaction.
-		 * This will come into picture when after shifting extent into
-		 * hole we found that adjacent extents can be merged which
-		 * may lead to freeing of a block during record update.
-		 */
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
-				XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
+					&tp);
 		if (error)
 			break;
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
-				ip->i_gdquot, ip->i_pdquot,
-				XFS_DIOSTRAT_SPACE_RES(mp, 0), 0,
+				ip->i_gdquot, ip->i_pdquot, resblks, 0,
 				XFS_QMOPT_RES_REGBLKS);
 		if (error)
 			goto out_trans_cancel;
@@ -1821,29 +1839,18 @@ xfs_swap_extent_forks(
 	}
 
 	/*
-	 * Before we've swapped the forks, lets set the owners of the forks
-	 * appropriately. We have to do this as we are demand paging the btree
-	 * buffers, and so the validation done on read will expect the owner
-	 * field to be correctly set. Once we change the owners, we can swap the
-	 * inode forks.
+	 * Btree format (v3) inodes have the inode number stamped in the bmbt
+	 * block headers. We can't start changing the bmbt blocks until the
+	 * inode owner change is logged so recovery does the right thing in the
+	 * event of a crash. Set the owner change log flags now and leave the
+	 * bmbt scan as the last step.
 	 */
 	if (ip->i_d.di_version == 3 &&
-	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+	    ip->i_d.di_format == XFS_DINODE_FMT_BTREE)
 		(*target_log_flags) |= XFS_ILOG_DOWNER;
-		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK,
-					      tip->i_ino, NULL);
-		if (error)
-			return error;
-	}
-
 	if (tip->i_d.di_version == 3 &&
-	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
+	    tip->i_d.di_format == XFS_DINODE_FMT_BTREE)
 		(*src_log_flags) |= XFS_ILOG_DOWNER;
-		error = xfs_bmbt_change_owner(tp, tip, XFS_DATA_FORK,
-					      ip->i_ino, NULL);
-		if (error)
-			return error;
-	}
 
 	/*
 	 * Swap the data forks of the inodes
@@ -1921,6 +1928,48 @@ xfs_swap_extent_forks(
 	return 0;
 }
 
+/*
+ * Fix up the owners of the bmbt blocks to refer to the current inode. The
+ * change owner scan attempts to order all modified buffers in the current
+ * transaction. In the event of ordered buffer failure, the offending buffer is
+ * physically logged as a fallback and the scan returns -EAGAIN. We must roll
+ * the transaction in this case to replenish the fallback log reservation and
+ * restart the scan. This process repeats until the scan completes.
+ */
+static int
+xfs_swap_change_owner(
+	struct xfs_trans	**tpp,
+	struct xfs_inode	*ip,
+	struct xfs_inode	*tmpip)
+{
+	int			error;
+	struct xfs_trans	*tp = *tpp;
+
+	do {
+		error = xfs_bmbt_change_owner(tp, ip, XFS_DATA_FORK, ip->i_ino,
+					      NULL);
+		/* success or fatal error */
+		if (error != -EAGAIN)
+			break;
+
+		error = xfs_trans_roll(tpp, NULL);
+		if (error)
+			break;
+		tp = *tpp;
+
+		/*
+		 * Redirty both inodes so they can relog and keep the log tail
+		 * moving forward.
+		 */
+		xfs_trans_ijoin(tp, ip, 0);
+		xfs_trans_ijoin(tp, tmpip, 0);
+		xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+		xfs_trans_log_inode(tp, tmpip, XFS_ILOG_CORE);
+	} while (true);
+
+	return error;
+}
+
 int
 xfs_swap_extents(
 	struct xfs_inode	*ip,	/* target inode */
@@ -1934,8 +1983,8 @@ xfs_swap_extents(
 	int			error = 0;
 	int			lock_flags;
 	struct xfs_ifork	*cowfp;
-	__uint64_t		f;
-	int			resblks;
+	uint64_t		f;
+	int			resblks = 0;
 
 	/*
 	 * Lock the inodes against other IO, page faults and truncate to
@@ -1983,11 +2032,8 @@ xfs_swap_extents(
 			  XFS_SWAP_RMAP_SPACE_RES(mp,
 				XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK),
 				XFS_DATA_FORK);
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks,
-				0, 0, &tp);
-	} else
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0,
-				0, 0, &tp);
+	}
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
 	if (error)
 		goto out_unlock;
 
@@ -2062,17 +2108,54 @@ xfs_swap_extents(
 		ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+	}
+
+	/* Swap the cow forks. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		xfs_extnum_t	extnum;
+
+		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+
+		extnum = ip->i_cnextents;
+		ip->i_cnextents = tip->i_cnextents;
+		tip->i_cnextents = extnum;
+
 		cowfp = ip->i_cowfp;
 		ip->i_cowfp = tip->i_cowfp;
 		tip->i_cowfp = cowfp;
-		xfs_inode_set_cowblocks_tag(ip);
-		xfs_inode_set_cowblocks_tag(tip);
+
+		if (ip->i_cowfp && ip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(ip);
+		else
+			xfs_inode_clear_cowblocks_tag(ip);
+		if (tip->i_cowfp && tip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(tip);
+		else
+			xfs_inode_clear_cowblocks_tag(tip);
 	}
 
 	xfs_trans_log_inode(tp, ip,  src_log_flags);
 	xfs_trans_log_inode(tp, tip, target_log_flags);
 
 	/*
+	 * The extent forks have been swapped, but crc=1,rmapbt=0 filesystems
+	 * have inode number owner values in the bmbt blocks that still refer to
+	 * the old inode. Scan each bmbt to fix up the owner values with the
+	 * inode number of the current inode.
+	 */
+	if (src_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(&tp, ip, tip);
+		if (error)
+			goto out_trans_cancel;
+	}
+	if (target_log_flags & XFS_ILOG_DOWNER) {
+		error = xfs_swap_change_owner(&tp, tip, ip);
+		if (error)
+			goto out_trans_cancel;
+	}
+
+	/*
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.
 	 */