1 files changed, 177 insertions, 135 deletions

diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 18f4b262e61c..d1772786af29 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))
@@ -795,26 +801,18 @@ xfs_ialloc(
 		return error;
 	ASSERT(ip != NULL);
 	inode = VFS_I(ip);
-
-	/*
-	 * We always convert v1 inodes to v2 now - we only support filesystems
-	 * with >= v2 inode capability, so there is no reason for ever leaving
-	 * an inode in v1 format.
-	 */
-	if (ip->i_d.di_version == 1)
-		ip->i_d.di_version = 2;
-
 	inode->i_mode = mode;
 	set_nlink(inode, nlink);
-	ip->i_d.di_uid = xfs_kuid_to_uid(current_fsuid());
-	ip->i_d.di_gid = xfs_kgid_to_gid(current_fsgid());
+	inode->i_uid = current_fsuid();
 	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;
+		inode->i_gid = VFS_I(pip)->i_gid;
 		if ((VFS_I(pip)->i_mode & S_ISGID) && S_ISDIR(mode))
 			inode->i_mode |= S_ISGID;
+	} else {
+		inode->i_gid = current_fsgid();
 	}
 
 	/*
@@ -822,9 +820,8 @@ xfs_ialloc(
 	 * ID or one of the supplementary group IDs, the S_ISGID bit is cleared
 	 * (and only if the irix_sgid_inherit compatibility variable is set).
 	 */
-	if ((irix_sgid_inherit) &&
-	    (inode->i_mode & S_ISGID) &&
-	    (!in_group_p(xfs_gid_to_kgid(ip->i_d.di_gid))))
+	if (irix_sgid_inherit &&
+	    (inode->i_mode & S_ISGID) && !in_group_p(inode->i_gid))
 		inode->i_mode &= ~S_ISGID;
 
 	ip->i_d.di_size = 0;
@@ -841,15 +838,13 @@ xfs_ialloc(
 	ip->i_d.di_dmstate = 0;
 	ip->i_d.di_flags = 0;
 
-	if (ip->i_d.di_version == 3) {
+	if (xfs_sb_version_has_v3inode(&mp->m_sb)) {
 		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;
 	}
 
-
 	flags = XFS_ILOG_CORE;
 	switch (mode & S_IFMT) {
 	case S_IFIFO:
@@ -902,20 +897,13 @@ xfs_ialloc(
 
 			ip->i_d.di_flags |= di_flags;
 		}
-		if (pip &&
-		    (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY) &&
-		    pip->i_d.di_version == 3 &&
-		    ip->i_d.di_version == 3) {
-			uint64_t	di_flags2 = 0;
-
+		if (pip && (pip->i_d.di_flags2 & XFS_DIFLAG2_ANY)) {
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE) {
-				di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+				ip->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 				ip->i_d.di_cowextsize = pip->i_d.di_cowextsize;
 			}
 			if (pip->i_d.di_flags2 & XFS_DIFLAG2_DAX)
-				di_flags2 |= XFS_DIFLAG2_DAX;
-
-			ip->i_d.di_flags2 |= di_flags2;
+				ip->i_d.di_flags2 |= XFS_DIFLAG2_DAX;
 		}
 		/* FALLTHROUGH */
 	case S_IFLNK:
@@ -1117,7 +1105,6 @@ xfs_bumplink(
 {
 	xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
 
-	ASSERT(ip->i_d.di_version > 1);
 	inc_nlink(VFS_I(ip));
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 }
@@ -1153,8 +1140,7 @@ xfs_create(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
-					xfs_kgid_to_gid(current_fsgid()), prid,
+	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
 					XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
 					&udqp, &gdqp, &pdqp);
 	if (error)
@@ -1214,8 +1200,7 @@ xfs_create(
 	unlock_dp_on_error = false;
 
 	error = xfs_dir_createname(tp, dp, name, ip->i_ino,
-				   resblks ?
-					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
+					resblks - XFS_IALLOC_SPACE_RES(mp));
 	if (error) {
 		ASSERT(error != -ENOSPC);
 		goto out_trans_cancel;
@@ -1304,8 +1289,7 @@ xfs_create_tmpfile(
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
-	error = xfs_qm_vop_dqalloc(dp, xfs_kuid_to_uid(current_fsuid()),
-				xfs_kgid_to_gid(current_fsgid()), prid,
+	error = xfs_qm_vop_dqalloc(dp, current_fsuid(), current_fsgid(), prid,
 				XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT,
 				&udqp, &gdqp, &pdqp);
 	if (error)
@@ -1418,7 +1402,7 @@ 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 +1497,8 @@ 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 +1518,22 @@ 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 +1553,7 @@ 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;
 
@@ -2115,7 +2098,7 @@ xfs_iunlink_update_bucket(
 	unsigned int		bucket_index,
 	xfs_agino_t		new_agino)
 {
-	struct xfs_agi		*agi = XFS_BUF_TO_AGI(agibp);
+	struct xfs_agi		*agi = agibp->b_addr;
 	xfs_agino_t		old_value;
 	int			offset;
 
@@ -2130,8 +2113,10 @@ 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_mark_corrupt(agibp);
 		return -EFSCORRUPTED;
+	}
 
 	agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
 	offset = offsetof(struct xfs_agi, agi_unlinked) +
@@ -2194,6 +2179,8 @@ 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 +2192,11 @@ 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;
 	}
 
@@ -2248,7 +2238,7 @@ xfs_iunlink(
 	error = xfs_read_agi(mp, tp, agno, &agibp);
 	if (error)
 		return error;
-	agi = XFS_BUF_TO_AGI(agibp);
+	agi = agibp->b_addr;
 
 	/*
 	 * Get the index into the agi hash table for the list this inode will
@@ -2257,8 +2247,10 @@ 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_mark_corrupt(agibp);
 		return -EFSCORRUPTED;
+	}
 
 	if (next_agino != NULLAGINO) {
 		struct xfs_perag	*pag;
@@ -2430,7 +2422,7 @@ xfs_iunlink_remove(
 	error = xfs_read_agi(mp, tp, agno, &agibp);
 	if (error)
 		return error;
-	agi = XFS_BUF_TO_AGI(agibp);
+	agi = agibp->b_addr;
 
 	/*
 	 * Get the index into the agi hash table for the list this inode will
@@ -2511,6 +2503,88 @@ out:
 }
 
 /*
+ * Look up the inode number specified and mark it stale if it is found. If it is
+ * dirty, return the inode so it can be attached to the cluster buffer so it can
+ * be processed appropriately when the cluster free transaction completes.
+ */
+static struct xfs_inode *
+xfs_ifree_get_one_inode(
+	struct xfs_perag	*pag,
+	struct xfs_inode	*free_ip,
+	xfs_ino_t		inum)
+{
+	struct xfs_mount	*mp = pag->pag_mount;
+	struct xfs_inode	*ip;
+
+retry:
+	rcu_read_lock();
+	ip = radix_tree_lookup(&pag->pag_ici_root, XFS_INO_TO_AGINO(mp, inum));
+
+	/* Inode not in memory, nothing to do */
+	if (!ip)
+		goto out_rcu_unlock;
+
+	/*
+	 * because this is an RCU protected lookup, we could find a recently
+	 * freed or even reallocated inode during the lookup. We need to check
+	 * under the i_flags_lock for a valid inode here. Skip it if it is not
+	 * valid, the wrong inode or stale.
+	 */
+	spin_lock(&ip->i_flags_lock);
+	if (ip->i_ino != inum || __xfs_iflags_test(ip, XFS_ISTALE)) {
+		spin_unlock(&ip->i_flags_lock);
+		goto out_rcu_unlock;
+	}
+	spin_unlock(&ip->i_flags_lock);
+
+	/*
+	 * Don't try to lock/unlock the current inode, but we _cannot_ skip the
+	 * other inodes that we did not find in the list attached to the buffer
+	 * and are not already marked stale. If we can't lock it, back off and
+	 * retry.
+	 */
+	if (ip != free_ip) {
+		if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
+			rcu_read_unlock();
+			delay(1);
+			goto retry;
+		}
+
+		/*
+		 * Check the inode number again in case we're racing with
+		 * freeing in xfs_reclaim_inode().  See the comments in that
+		 * function for more information as to why the initial check is
+		 * not sufficient.
+		 */
+		if (ip->i_ino != inum) {
+			xfs_iunlock(ip, XFS_ILOCK_EXCL);
+			goto out_rcu_unlock;
+		}
+	}
+	rcu_read_unlock();
+
+	xfs_iflock(ip);
+	xfs_iflags_set(ip, XFS_ISTALE);
+
+	/*
+	 * We don't need to attach clean inodes or those only with unlogged
+	 * changes (which we throw away, anyway).
+	 */
+	if (!ip->i_itemp || xfs_inode_clean(ip)) {
+		ASSERT(ip != free_ip);
+		xfs_ifunlock(ip);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		goto out_no_inode;
+	}
+	return ip;
+
+out_rcu_unlock:
+	rcu_read_unlock();
+out_no_inode:
+	return NULL;
+}
+
+/*
  * A big issue when freeing the inode cluster is that we _cannot_ skip any
  * inodes that are in memory - they all must be marked stale and attached to
  * the cluster buffer.
@@ -2533,6 +2607,7 @@ 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 +2636,11 @@ 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
@@ -2610,77 +2684,11 @@ xfs_ifree_cluster(
 		 * even trying to lock them.
 		 */
 		for (i = 0; i < igeo->inodes_per_cluster; i++) {
-retry:
-			rcu_read_lock();
-			ip = radix_tree_lookup(&pag->pag_ici_root,
-					XFS_INO_TO_AGINO(mp, (inum + i)));
-
-			/* Inode not in memory, nothing to do */
-			if (!ip) {
-				rcu_read_unlock();
-				continue;
-			}
-
-			/*
-			 * because this is an RCU protected lookup, we could
-			 * find a recently freed or even reallocated inode
-			 * during the lookup. We need to check under the
-			 * i_flags_lock for a valid inode here. Skip it if it
-			 * is not valid, the wrong inode or stale.
-			 */
-			spin_lock(&ip->i_flags_lock);
-			if (ip->i_ino != inum + i ||
-			    __xfs_iflags_test(ip, XFS_ISTALE)) {
-				spin_unlock(&ip->i_flags_lock);
-				rcu_read_unlock();
+			ip = xfs_ifree_get_one_inode(pag, free_ip, inum + i);
+			if (!ip)
 				continue;
-			}
-			spin_unlock(&ip->i_flags_lock);
-
-			/*
-			 * Don't try to lock/unlock the current inode, but we
-			 * _cannot_ skip the other inodes that we did not find
-			 * in the list attached to the buffer and are not
-			 * already marked stale. If we can't lock it, back off
-			 * and retry.
-			 */
-			if (ip != free_ip) {
-				if (!xfs_ilock_nowait(ip, XFS_ILOCK_EXCL)) {
-					rcu_read_unlock();
-					delay(1);
-					goto retry;
-				}
 
-				/*
-				 * Check the inode number again in case we're
-				 * racing with freeing in xfs_reclaim_inode().
-				 * See the comments in that function for more
-				 * information as to why the initial check is
-				 * not sufficient.
-				 */
-				if (ip->i_ino != inum + i) {
-					xfs_iunlock(ip, XFS_ILOCK_EXCL);
-					rcu_read_unlock();
-					continue;
-				}
-			}
-			rcu_read_unlock();
-
-			xfs_iflock(ip);
-			xfs_iflags_set(ip, XFS_ISTALE);
-
-			/*
-			 * we don't need to attach clean inodes or those only
-			 * with unlogged changes (which we throw away, anyway).
-			 */
 			iip = ip->i_itemp;
-			if (!iip || xfs_inode_clean(ip)) {
-				ASSERT(ip != free_ip);
-				xfs_ifunlock(ip);
-				xfs_iunlock(ip, XFS_ILOCK_EXCL);
-				continue;
-			}
-
 			iip->ili_last_fields = iip->ili_fields;
 			iip->ili_fields = 0;
 			iip->ili_fsync_fields = 0;
@@ -3196,6 +3204,7 @@ 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 +3279,7 @@ 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;
 	}
@@ -3327,7 +3336,6 @@ xfs_rename(
 			goto out_trans_cancel;
 
 		xfs_bumplink(tp, wip);
-		xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
 		VFS_I(wip)->i_state &= ~I_LINKABLE;
 	}
 
@@ -3361,6 +3369,22 @@ 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)
@@ -3778,7 +3802,6 @@ xfs_iflush_int(
 	ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
 	       ip->i_d.di_nextents > XFS_IFORK_MAXEXT(ip, XFS_DATA_FORK));
 	ASSERT(iip != NULL && iip->ili_fields != 0);
-	ASSERT(ip->i_d.di_version > 1);
 
 	/* set *dip = inode's place in the buffer */
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
@@ -3839,7 +3862,7 @@ xfs_iflush_int(
 	 * backwards compatibility with old kernels that predate logging all
 	 * inode changes.
 	 */
-	if (ip->i_d.di_version < 3)
+	if (!xfs_sb_version_has_v3inode(&mp->m_sb))
 		ip->i_d.di_flushiter++;
 
 	/* Check the inline fork data before we write out. */
@@ -3922,3 +3945,22 @@ xfs_irele(
 	trace_xfs_irele(ip, _RET_IP_);
 	iput(VFS_I(ip));
 }
+
+/*
+ * Ensure all commited transactions touching the inode are written to the log.
+ */
+int
+xfs_log_force_inode(
+	struct xfs_inode	*ip)
+{
+	xfs_lsn_t		lsn = 0;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	if (xfs_ipincount(ip))
+		lsn = ip->i_itemp->ili_last_lsn;
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+	if (!lsn)
+		return 0;
+	return xfs_log_force_lsn(ip->i_mount, lsn, XFS_LOG_SYNC, NULL);
+}