1 files changed, 99 insertions, 69 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 6467d5e1df2d..c5077e6326c7 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -55,6 +55,12 @@ xfs_extlen_t
 xfs_get_extsz_hint(
 	struct xfs_inode	*ip)
 {
+	/*
+	 * No point in aligning allocations if we need to COW to actually
+	 * write to them.
+	 */
+	if (xfs_is_always_cow_inode(ip))
+		return 0;
 	if ((ip->i_d.di_flags & XFS_DIFLAG_EXTSIZE) && ip->i_d.di_extsize)
 		return ip->i_d.di_extsize;
 	if (XFS_IS_REALTIME_INODE(ip))
@@ -809,7 +815,7 @@ xfs_ialloc(
 	ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
 	ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
 	inode->i_rdev = rdev;
-	xfs_set_projid(ip, prid);
+	ip->i_d.di_projid = prid;
 
 	if (pip && XFS_INHERIT_GID(pip)) {
 		ip->i_d.di_gid = pip->i_d.di_gid;
@@ -845,8 +851,7 @@ xfs_ialloc(
 		inode_set_iversion(inode, 1);
 		ip->i_d.di_flags2 = 0;
 		ip->i_d.di_cowextsize = 0;
-		ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec;
-		ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec;
+		ip->i_d.di_crtime = tv;
 	}
 
 
@@ -1418,7 +1423,7 @@ xfs_link(
 	 * the tree quota mechanism could be circumvented.
 	 */
 	if (unlikely((tdp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     (xfs_get_projid(tdp) != xfs_get_projid(sip)))) {
+		     tdp->i_d.di_projid != sip->i_d.di_projid)) {
 		error = -EXDEV;
 		goto error_return;
 	}
@@ -1513,10 +1518,8 @@ xfs_itruncate_extents_flags(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp = *tpp;
 	xfs_fileoff_t		first_unmap_block;
-	xfs_fileoff_t		last_block;
 	xfs_filblks_t		unmap_len;
 	int			error = 0;
-	int			done = 0;
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	ASSERT(!atomic_read(&VFS_I(ip)->i_count) ||
@@ -1536,21 +1539,22 @@ xfs_itruncate_extents_flags(
 	 * the end of the file (in a crash where the space is allocated
 	 * but the inode size is not yet updated), simply remove any
 	 * blocks which show up between the new EOF and the maximum
-	 * possible file size.  If the first block to be removed is
-	 * beyond the maximum file size (ie it is the same as last_block),
-	 * then there is nothing to do.
+	 * possible file size.
+	 *
+	 * We have to free all the blocks to the bmbt maximum offset, even if
+	 * the page cache can't scale that far.
 	 */
 	first_unmap_block = XFS_B_TO_FSB(mp, (xfs_ufsize_t)new_size);
-	last_block = XFS_B_TO_FSB(mp, mp->m_super->s_maxbytes);
-	if (first_unmap_block == last_block)
+	if (first_unmap_block >= XFS_MAX_FILEOFF) {
+		WARN_ON_ONCE(first_unmap_block > XFS_MAX_FILEOFF);
 		return 0;
+	}
 
-	ASSERT(first_unmap_block < last_block);
-	unmap_len = last_block - first_unmap_block + 1;
-	while (!done) {
+	unmap_len = XFS_MAX_FILEOFF - first_unmap_block + 1;
+	while (unmap_len > 0) {
 		ASSERT(tp->t_firstblock == NULLFSBLOCK);
-		error = xfs_bunmapi(tp, ip, first_unmap_block, unmap_len, flags,
-				    XFS_ITRUNC_MAX_EXTENTS, &done);
+		error = __xfs_bunmapi(tp, ip, first_unmap_block, &unmap_len,
+				flags, XFS_ITRUNC_MAX_EXTENTS);
 		if (error)
 			goto out;
 
@@ -1570,7 +1574,7 @@ xfs_itruncate_extents_flags(
 	if (whichfork == XFS_DATA_FORK) {
 		/* Remove all pending CoW reservations. */
 		error = xfs_reflink_cancel_cow_blocks(ip, &tp,
-				first_unmap_block, last_block, true);
+				first_unmap_block, XFS_MAX_FILEOFF, true);
 		if (error)
 			goto out;
 
@@ -2018,7 +2022,7 @@ xfs_iunlink_add_backref(
 	if (XFS_TEST_ERROR(false, pag->pag_mount, XFS_ERRTAG_IUNLINK_FALLBACK))
 		return 0;
 
-	iu = kmem_zalloc(sizeof(*iu), KM_SLEEP | KM_NOFS);
+	iu = kmem_zalloc(sizeof(*iu), KM_NOFS);
 	iu->iu_agino = prev_agino;
 	iu->iu_next_unlinked = this_agino;
 
@@ -2130,8 +2134,10 @@ xfs_iunlink_update_bucket(
 	 * passed in because either we're adding or removing ourselves from the
 	 * head of the list.
 	 */
-	if (old_value == new_agino)
+	if (old_value == new_agino) {
+		xfs_buf_corruption_error(agibp);
 		return -EFSCORRUPTED;
+	}
 
 	agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
 	offset = offsetof(struct xfs_agi, agi_unlinked) +
@@ -2194,6 +2200,8 @@ xfs_iunlink_update_inode(
 	/* Make sure the old pointer isn't garbage. */
 	old_value = be32_to_cpu(dip->di_next_unlinked);
 	if (!xfs_verify_agino_or_null(mp, agno, old_value)) {
+		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
+				sizeof(*dip), __this_address);
 		error = -EFSCORRUPTED;
 		goto out;
 	}
@@ -2205,8 +2213,11 @@ xfs_iunlink_update_inode(
 	 */
 	*old_next_agino = old_value;
 	if (old_value == next_agino) {
-		if (next_agino != NULLAGINO)
+		if (next_agino != NULLAGINO) {
+			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
+					dip, sizeof(*dip), __this_address);
 			error = -EFSCORRUPTED;
+		}
 		goto out;
 	}
 
@@ -2257,8 +2268,10 @@ xfs_iunlink(
 	 */
 	next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
 	if (next_agino == agino ||
-	    !xfs_verify_agino_or_null(mp, agno, next_agino))
+	    !xfs_verify_agino_or_null(mp, agno, next_agino)) {
+		xfs_buf_corruption_error(agibp);
 		return -EFSCORRUPTED;
+	}
 
 	if (next_agino != NULLAGINO) {
 		struct xfs_perag	*pag;
@@ -2533,6 +2546,7 @@ xfs_ifree_cluster(
 	struct xfs_perag	*pag;
 	struct xfs_ino_geometry	*igeo = M_IGEO(mp);
 	xfs_ino_t		inum;
+	int			error;
 
 	inum = xic->first_ino;
 	pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
@@ -2561,12 +2575,11 @@ xfs_ifree_cluster(
 		 * complete before we get a lock on it, and hence we may fail
 		 * to mark all the active inodes on the buffer stale.
 		 */
-		bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
-					mp->m_bsize * igeo->blocks_per_cluster,
-					XBF_UNMAPPED);
-
-		if (!bp)
-			return -ENOMEM;
+		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
+				mp->m_bsize * igeo->blocks_per_cluster,
+				XBF_UNMAPPED, &bp);
+		if (error)
+			return error;
 
 		/*
 		 * This buffer may not have been correctly initialised as we
@@ -3196,6 +3209,7 @@ xfs_rename(
 	struct xfs_trans	*tp;
 	struct xfs_inode	*wip = NULL;		/* whiteout inode */
 	struct xfs_inode	*inodes[__XFS_SORT_INODES];
+	struct xfs_buf		*agibp;
 	int			num_inodes = __XFS_SORT_INODES;
 	bool			new_parent = (src_dp != target_dp);
 	bool			src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
@@ -3270,7 +3284,7 @@ xfs_rename(
 	 * tree quota mechanism would be circumvented.
 	 */
 	if (unlikely((target_dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
-		     (xfs_get_projid(target_dp) != xfs_get_projid(src_ip)))) {
+		     target_dp->i_d.di_projid != src_ip->i_d.di_projid)) {
 		error = -EXDEV;
 		goto out_trans_cancel;
 	}
@@ -3282,7 +3296,8 @@ xfs_rename(
 					spaceres);
 
 	/*
-	 * Set up the target.
+	 * Check for expected errors before we dirty the transaction
+	 * so we can return an error without a transaction abort.
 	 */
 	if (target_ip == NULL) {
 		/*
@@ -3294,6 +3309,45 @@ xfs_rename(
 			if (error)
 				goto out_trans_cancel;
 		}
+	} else {
+		/*
+		 * If target exists and it's a directory, check that whether
+		 * it can be destroyed.
+		 */
+		if (S_ISDIR(VFS_I(target_ip)->i_mode) &&
+		    (!xfs_dir_isempty(target_ip) ||
+		     (VFS_I(target_ip)->i_nlink > 2))) {
+			error = -EEXIST;
+			goto out_trans_cancel;
+		}
+	}
+
+	/*
+	 * Directory entry creation below may acquire the AGF. Remove
+	 * the whiteout from the unlinked list first to preserve correct
+	 * AGI/AGF locking order. This dirties the transaction so failures
+	 * after this point will abort and log recovery will clean up the
+	 * mess.
+	 *
+	 * For whiteouts, we need to bump the link count on the whiteout
+	 * inode. After this point, we have a real link, clear the tmpfile
+	 * state flag from the inode so it doesn't accidentally get misused
+	 * in future.
+	 */
+	if (wip) {
+		ASSERT(VFS_I(wip)->i_nlink == 0);
+		error = xfs_iunlink_remove(tp, wip);
+		if (error)
+			goto out_trans_cancel;
+
+		xfs_bumplink(tp, wip);
+		VFS_I(wip)->i_state &= ~I_LINKABLE;
+	}
+
+	/*
+	 * Set up the target.
+	 */
+	if (target_ip == NULL) {
 		/*
 		 * If target does not exist and the rename crosses
 		 * directories, adjust the target directory link count
@@ -3312,22 +3366,6 @@ xfs_rename(
 		}
 	} else { /* target_ip != NULL */
 		/*
-		 * If target exists and it's a directory, check that both
-		 * target and source are directories and that target can be
-		 * destroyed, or that neither is a directory.
-		 */
-		if (S_ISDIR(VFS_I(target_ip)->i_mode)) {
-			/*
-			 * Make sure target dir is empty.
-			 */
-			if (!(xfs_dir_isempty(target_ip)) ||
-			    (VFS_I(target_ip)->i_nlink > 2)) {
-				error = -EEXIST;
-				goto out_trans_cancel;
-			}
-		}
-
-		/*
 		 * Link the source inode under the target name.
 		 * If the source inode is a directory and we are moving
 		 * it across directories, its ".." entry will be
@@ -3336,6 +3374,22 @@ xfs_rename(
 		 * In case there is already an entry with the same
 		 * name at the destination directory, remove it first.
 		 */
+
+		/*
+		 * Check whether the replace operation will need to allocate
+		 * blocks.  This happens when the shortform directory lacks
+		 * space and we have to convert it to a block format directory.
+		 * When more blocks are necessary, we must lock the AGI first
+		 * to preserve locking order (AGI -> AGF).
+		 */
+		if (xfs_dir2_sf_replace_needblock(target_dp, src_ip->i_ino)) {
+			error = xfs_read_agi(mp, tp,
+					XFS_INO_TO_AGNO(mp, target_ip->i_ino),
+					&agibp);
+			if (error)
+				goto out_trans_cancel;
+		}
+
 		error = xfs_dir_replace(tp, target_dp, target_name,
 					src_ip->i_ino, spaceres);
 		if (error)
@@ -3417,30 +3471,6 @@ xfs_rename(
 	if (error)
 		goto out_trans_cancel;
 
-	/*
-	 * For whiteouts, we need to bump the link count on the whiteout inode.
-	 * This means that failures all the way up to this point leave the inode
-	 * on the unlinked list and so cleanup is a simple matter of dropping
-	 * the remaining reference to it. If we fail here after bumping the link
-	 * count, we're shutting down the filesystem so we'll never see the
-	 * intermediate state on disk.
-	 */
-	if (wip) {
-		ASSERT(VFS_I(wip)->i_nlink == 0);
-		xfs_bumplink(tp, wip);
-		error = xfs_iunlink_remove(tp, wip);
-		if (error)
-			goto out_trans_cancel;
-		xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
-
-		/*
-		 * Now we have a real link, clear the "I'm a tmpfile" state
-		 * flag from the inode so it doesn't accidentally get misused in
-		 * future.
-		 */
-		VFS_I(wip)->i_state &= ~I_LINKABLE;
-	}
-
 	xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
 	if (new_parent)