Merge tag 'for-linus-v3.10-rc4' of git://oss.sgi.com/xfs/xfs

Pull xfs fixes from Ben Myers:
 - Fix nested transactions in xfs_qm_scall_setqlim
 - Clear suid/sgid bits when we truncate with size update
 - Fix recovery for split buffers
 - Fix block count on remote symlinks
 - Add fsgeom flag for v5 superblock support
 - Disable XFS_IOC_SWAPEXT for CRC enabled filesystems
 - Fix dirv3 freespace block corruption

* tag 'for-linus-v3.10-rc4' of git://oss.sgi.com/xfs/xfs:
  xfs: fix dir3 freespace block corruption
  xfs: disable swap extents ioctl on CRC enabled filesystems
  xfs: add fsgeom flag for v5 superblock support.
  xfs: fix incorrect remote symlink block count
  xfs: fix split buffer vector log recovery support
  xfs: kill suid/sgid through the truncate path.
  xfs: avoid nesting transactions in xfs_qm_scall_setqlim()

fs/xfs/xfs_buf_item.c

@@ -262,12 +262,7 @@ xfs_buf_item_format_segment(
 			vecp->i_addr = xfs_buf_offset(bp, buffer_offset);
 			vecp->i_len = nbits * XFS_BLF_CHUNK;
 			vecp->i_type = XLOG_REG_TYPE_BCHUNK;
-/*
- * You would think we need to bump the nvecs here too, but we do not
- * this number is used by recovery, and it gets confused by the boundary
- * split here
- *			nvecs++;
- */
+			nvecs++;
 			vecp++;
 			first_bit = next_bit;
 			last_bit = next_bit;

fs/xfs/xfs_dfrag.c

@@ -219,6 +219,14 @@ xfs_swap_extents(
 	int		taforkblks = 0;
 	__uint64_t	tmp;
 
+	/*
+	 * We have no way of updating owner information in the BMBT blocks for
+	 * each inode on CRC enabled filesystems, so to avoid corrupting the
+	 * this metadata we simply don't allow extent swaps to occur.
+	 */
+	if (xfs_sb_version_hascrc(&mp->m_sb))
+		return XFS_ERROR(EINVAL);
+
 	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
 	if (!tempifp) {
 		error = XFS_ERROR(ENOMEM);

fs/xfs/xfs_dir2_format.h

@@ -715,6 +715,7 @@ struct xfs_dir3_free_hdr {
 	__be32			firstdb;	/* db of first entry */
 	__be32			nvalid;		/* count of valid entries */
 	__be32			nused;		/* count of used entries */
+	__be32			pad;		/* 64 bit alignment. */
 };
 
 struct xfs_dir3_free {

fs/xfs/xfs_dir2_node.c

@@ -263,18 +263,19 @@ xfs_dir3_free_get_buf(
 	 * Initialize the new block to be empty, and remember
 	 * its first slot as our empty slot.
 	 */
-	hdr.magic = XFS_DIR2_FREE_MAGIC;
-	hdr.firstdb = 0;
-	hdr.nused = 0;
-	hdr.nvalid = 0;
+	memset(bp->b_addr, 0, sizeof(struct xfs_dir3_free_hdr));
+	memset(&hdr, 0, sizeof(hdr));
+
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_dir3_free_hdr *hdr3 = bp->b_addr;
 
 		hdr.magic = XFS_DIR3_FREE_MAGIC;
+
 		hdr3->hdr.blkno = cpu_to_be64(bp->b_bn);
 		hdr3->hdr.owner = cpu_to_be64(dp->i_ino);
 		uuid_copy(&hdr3->hdr.uuid, &mp->m_sb.sb_uuid);
-	}
+	} else
+		hdr.magic = XFS_DIR2_FREE_MAGIC;
 	xfs_dir3_free_hdr_to_disk(bp->b_addr, &hdr);
 	*bpp = bp;
 	return 0;
@@ -1921,8 +1922,6 @@ xfs_dir2_node_addname_int(
 			 */
 			freehdr.firstdb = (fbno - XFS_DIR2_FREE_FIRSTDB(mp)) *
 					xfs_dir3_free_max_bests(mp);
-			free->hdr.nvalid = 0;
-			free->hdr.nused = 0;
 		} else {
 			free = fbp->b_addr;
 			bests = xfs_dir3_free_bests_p(mp, free);

fs/xfs/xfs_fs.h

@@ -236,6 +236,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_PROJID32	0x0800  /* 32-bit project IDs	*/
 #define XFS_FSOP_GEOM_FLAGS_DIRV2CI	0x1000	/* ASCII only CI names	*/
 #define XFS_FSOP_GEOM_FLAGS_LAZYSB	0x4000	/* lazy superblock counters */
+#define XFS_FSOP_GEOM_FLAGS_V5SB	0x8000	/* version 5 superblock */
 
 
 /*

fs/xfs/xfs_fsops.c

@@ -99,7 +99,9 @@ xfs_fs_geometry(
 			(xfs_sb_version_hasattr2(&mp->m_sb) ?
 				XFS_FSOP_GEOM_FLAGS_ATTR2 : 0) |
 			(xfs_sb_version_hasprojid32bit(&mp->m_sb) ?
-				XFS_FSOP_GEOM_FLAGS_PROJID32 : 0);
+				XFS_FSOP_GEOM_FLAGS_PROJID32 : 0) |
+			(xfs_sb_version_hascrc(&mp->m_sb) ?
+				XFS_FSOP_GEOM_FLAGS_V5SB : 0);
 		geo->logsectsize = xfs_sb_version_hassector(&mp->m_sb) ?
 				mp->m_sb.sb_logsectsize : BBSIZE;
 		geo->rtsectsize = mp->m_sb.sb_blocksize;

fs/xfs/xfs_iops.c

@@ -455,6 +455,28 @@ xfs_vn_getattr(
 	return 0;
 }
 
+static void
+xfs_setattr_mode(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct iattr		*iattr)
+{
+	struct inode	*inode = VFS_I(ip);
+	umode_t		mode = iattr->ia_mode;
+
+	ASSERT(tp);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
+		mode &= ~S_ISGID;
+
+	ip->i_d.di_mode &= S_IFMT;
+	ip->i_d.di_mode |= mode & ~S_IFMT;
+
+	inode->i_mode &= S_IFMT;
+	inode->i_mode |= mode & ~S_IFMT;
+}
+
 int
 xfs_setattr_nonsize(
 	struct xfs_inode	*ip,
@@ -606,18 +628,8 @@ xfs_setattr_nonsize(
 	/*
 	 * Change file access modes.
 	 */
-	if (mask & ATTR_MODE) {
-		umode_t mode = iattr->ia_mode;
-
-		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
-			mode &= ~S_ISGID;
-
-		ip->i_d.di_mode &= S_IFMT;
-		ip->i_d.di_mode |= mode & ~S_IFMT;
-
-		inode->i_mode &= S_IFMT;
-		inode->i_mode |= mode & ~S_IFMT;
-	}
+	if (mask & ATTR_MODE)
+		xfs_setattr_mode(tp, ip, iattr);
 
 	/*
 	 * Change file access or modified times.
@@ -714,9 +726,8 @@ xfs_setattr_size(
 		return XFS_ERROR(error);
 
 	ASSERT(S_ISREG(ip->i_d.di_mode));
-	ASSERT((mask & (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
-			ATTR_MTIME_SET|ATTR_KILL_SUID|ATTR_KILL_SGID|
-			ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+	ASSERT((mask & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
+			ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
 
 	if (!(flags & XFS_ATTR_NOLOCK)) {
 		lock_flags |= XFS_IOLOCK_EXCL;
@@ -860,6 +871,12 @@ xfs_setattr_size(
 		xfs_inode_clear_eofblocks_tag(ip);
 	}
 
+	/*
+	 * Change file access modes.
+	 */
+	if (mask & ATTR_MODE)
+		xfs_setattr_mode(tp, ip, iattr);
+
 	if (mask & ATTR_CTIME) {
 		inode->i_ctime = iattr->ia_ctime;
 		ip->i_d.di_ctime.t_sec = iattr->ia_ctime.tv_sec;

fs/xfs/xfs_log_recover.c

@@ -2096,6 +2096,17 @@ xlog_recover_do_reg_buffer(
 		ASSERT(BBTOB(bp->b_io_length) >=
 		       ((uint)bit << XFS_BLF_SHIFT) + (nbits << XFS_BLF_SHIFT));
 
+		/*
+		 * The dirty regions logged in the buffer, even though
+		 * contiguous, may span multiple chunks. This is because the
+		 * dirty region may span a physical page boundary in a buffer
+		 * and hence be split into two separate vectors for writing into
+		 * the log. Hence we need to trim nbits back to the length of
+		 * the current region being copied out of the log.
+		 */
+		if (item->ri_buf[i].i_len < (nbits << XFS_BLF_SHIFT))
+			nbits = item->ri_buf[i].i_len >> XFS_BLF_SHIFT;
+
 		/*
 		 * Do a sanity check if this is a dquot buffer. Just checking
 		 * the first dquot in the buffer should do. XXXThis is

fs/xfs/xfs_qm_syscalls.c

@@ -489,31 +489,36 @@ xfs_qm_scall_setqlim(
 	if ((newlim->d_fieldmask & XFS_DQ_MASK) == 0)
 		return 0;
 
-	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
-	error = xfs_trans_reserve(tp, 0, XFS_QM_SETQLIM_LOG_RES(mp),
-				  0, 0, XFS_DEFAULT_LOG_COUNT);
-	if (error) {
-		xfs_trans_cancel(tp, 0);
-		return (error);
-	}
-
 	/*
 	 * We don't want to race with a quotaoff so take the quotaoff lock.
-	 * (We don't hold an inode lock, so there's nothing else to stop
-	 * a quotaoff from happening). (XXXThis doesn't currently happen
-	 * because we take the vfslock before calling xfs_qm_sysent).
+	 * We don't hold an inode lock, so there's nothing else to stop
+	 * a quotaoff from happening.
 	 */
 	mutex_lock(&q->qi_quotaofflock);
 
 	/*
-	 * Get the dquot (locked), and join it to the transaction.
-	 * Allocate the dquot if this doesn't exist.
+	 * Get the dquot (locked) before we start, as we need to do a
+	 * transaction to allocate it if it doesn't exist. Once we have the
+	 * dquot, unlock it so we can start the next transaction safely. We hold
+	 * a reference to the dquot, so it's safe to do this unlock/lock without
+	 * it being reclaimed in the mean time.
 	 */
-	if ((error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp))) {
-		xfs_trans_cancel(tp, XFS_TRANS_ABORT);
+	error = xfs_qm_dqget(mp, NULL, id, type, XFS_QMOPT_DQALLOC, &dqp);
+	if (error) {
 		ASSERT(error != ENOENT);
 		goto out_unlock;
 	}
+	xfs_dqunlock(dqp);
+
+	tp = xfs_trans_alloc(mp, XFS_TRANS_QM_SETQLIM);
+	error = xfs_trans_reserve(tp, 0, XFS_QM_SETQLIM_LOG_RES(mp),
+				  0, 0, XFS_DEFAULT_LOG_COUNT);
+	if (error) {
+		xfs_trans_cancel(tp, 0);
+		goto out_rele;
+	}
+
+	xfs_dqlock(dqp);
 	xfs_trans_dqjoin(tp, dqp);
 	ddq = &dqp->q_core;
 
@@ -621,9 +626,10 @@ xfs_qm_scall_setqlim(
 	xfs_trans_log_dquot(tp, dqp);
 
 	error = xfs_trans_commit(tp, 0);
-	xfs_qm_dqrele(dqp);
 
- out_unlock:
+out_rele:
+	xfs_qm_dqrele(dqp);
+out_unlock:
 	mutex_unlock(&q->qi_quotaofflock);
 	return error;
 }

fs/xfs/xfs_symlink.c

@@ -56,16 +56,9 @@ xfs_symlink_blocks(
 	struct xfs_mount *mp,
 	int		pathlen)
 {
-	int		fsblocks = 0;
-	int		len = pathlen;
+	int buflen = XFS_SYMLINK_BUF_SPACE(mp, mp->m_sb.sb_blocksize);
 
-	do {
-		fsblocks++;
-		len -= XFS_SYMLINK_BUF_SPACE(mp, mp->m_sb.sb_blocksize);
-	} while (len > 0);
-
-	ASSERT(fsblocks <= XFS_SYMLINK_MAPS);
-	return fsblocks;
+	return (pathlen + buflen - 1) / buflen;
 }
 
 static int
@@ -405,7 +398,7 @@ xfs_symlink(
 	if (pathlen <= XFS_LITINO(mp, dp->i_d.di_version))
 		fs_blocks = 0;
 	else
-		fs_blocks = XFS_B_TO_FSB(mp, pathlen);
+		fs_blocks = xfs_symlink_blocks(mp, pathlen);
 	resblks = XFS_SYMLINK_SPACE_RES(mp, link_name->len, fs_blocks);
 	error = xfs_trans_reserve(tp, resblks, XFS_SYMLINK_LOG_RES(mp), 0,
 			XFS_TRANS_PERM_LOG_RES, XFS_SYMLINK_LOG_COUNT);
@@ -512,7 +505,7 @@ xfs_symlink(
 		cur_chunk = target_path;
 		offset = 0;
 		for (n = 0; n < nmaps; n++) {
-			char *buf;
+			char	*buf;
 
 			d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
 			byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
@@ -525,9 +518,7 @@ xfs_symlink(
 			bp->b_ops = &xfs_symlink_buf_ops;
 
 			byte_cnt = XFS_SYMLINK_BUF_SPACE(mp, byte_cnt);
-			if (pathlen < byte_cnt) {
-				byte_cnt = pathlen;
-			}
+			byte_cnt = min(byte_cnt, pathlen);
 
 			buf = bp->b_addr;
 			buf += xfs_symlink_hdr_set(mp, ip->i_ino, offset,
@@ -542,6 +533,7 @@ xfs_symlink(
 			xfs_trans_log_buf(tp, bp, 0, (buf + byte_cnt - 1) -
 							(char *)bp->b_addr);
 		}
+		ASSERT(pathlen == 0);
 	}
 
 	/*