Merge tag 'xfs-for-linus-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs

Pull xfs updates from Dave Chinner:
 "There's quite a lot in this request, and there's some cross-over with
  ext4, dax and quota code due to the nature of the changes being made.

  As for the rest of the XFS changes, there are lots of little things
  all over the place, which add up to a lot of changes in the end.

  The major changes are that we've reduced the size of the struct
  xfs_inode by ~100 bytes (gives an inode cache footprint reduction of
  >10%), the writepage code now only does a single set of mapping tree
  lockups so uses less CPU, delayed allocation reservations won't
  overrun under random write loads anymore, and we added compile time
  verification for on-disk structure sizes so we find out when a commit
  or platform/compiler change breaks the on disk structure as early as
  possible.

  Change summary:

   - error propagation for direct IO failures fixes for both XFS and
     ext4
   - new quota interfaces and XFS implementation for iterating all the
     quota IDs in the filesystem
   - locking fixes for real-time device extent allocation
   - reduction of duplicate information in the xfs and vfs inode, saving
     roughly 100 bytes of memory per cached inode.
   - buffer flag cleanup
   - rework of the writepage code to use the generic write clustering
     mechanisms
   - several fixes for inode flag based DAX enablement
   - rework of remount option parsing
   - compile time verification of on-disk format structure sizes
   - delayed allocation reservation overrun fixes
   - lots of little error handling fixes
   - small memory leak fixes
   - enable xfsaild freezing again"

* tag 'xfs-for-linus-4.6-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/linux-xfs: (66 commits)
  xfs: always set rvalp in xfs_dir2_node_trim_free
  xfs: ensure committed is initialized in xfs_trans_roll
  xfs: borrow indirect blocks from freed extent when available
  xfs: refactor delalloc indlen reservation split into helper
  xfs: update freeblocks counter after extent deletion
  xfs: debug mode forced buffered write failure
  xfs: remove impossible condition
  xfs: check sizes of XFS on-disk structures at compile time
  xfs: ioends require logically contiguous file offsets
  xfs: use named array initializers for log item dumping
  xfs: fix computation of inode btree maxlevels
  xfs: reinitialise per-AG structures if geometry changes during recovery
  xfs: remove xfs_trans_get_block_res
  xfs: fix up inode32/64 (re)mount handling
  xfs: fix format specifier , should be %llx and not %llu
  xfs: sanitize remount options
  xfs: convert mount option parsing to tokens
  xfs: fix two memory leaks in xfs_attr_list.c error paths
  xfs: XFS_DIFLAG2_DAX limited by PAGE_SIZE
  xfs: dynamically switch modes when XFS_DIFLAG2_DAX is set/cleared
  ...

1 files changed, 106 insertions, 15 deletions

diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 478d04e07f95..bcb6c19ce3ea 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -114,7 +114,7 @@ xfs_find_handle(
 		handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
 					sizeof(handle.ha_fid.fid_len);
 		handle.ha_fid.fid_pad = 0;
-		handle.ha_fid.fid_gen = ip->i_d.di_gen;
+		handle.ha_fid.fid_gen = inode->i_generation;
 		handle.ha_fid.fid_ino = ip->i_ino;
 
 		hsize = XFS_HSIZE(handle);
@@ -963,7 +963,7 @@ xfs_set_diflags(
 		di_flags |= XFS_DIFLAG_NODEFRAG;
 	if (xflags & FS_XFLAG_FILESTREAM)
 		di_flags |= XFS_DIFLAG_FILESTREAM;
-	if (S_ISDIR(ip->i_d.di_mode)) {
+	if (S_ISDIR(VFS_I(ip)->i_mode)) {
 		if (xflags & FS_XFLAG_RTINHERIT)
 			di_flags |= XFS_DIFLAG_RTINHERIT;
 		if (xflags & FS_XFLAG_NOSYMLINKS)
@@ -972,7 +972,7 @@ xfs_set_diflags(
 			di_flags |= XFS_DIFLAG_EXTSZINHERIT;
 		if (xflags & FS_XFLAG_PROJINHERIT)
 			di_flags |= XFS_DIFLAG_PROJINHERIT;
-	} else if (S_ISREG(ip->i_d.di_mode)) {
+	} else if (S_ISREG(VFS_I(ip)->i_mode)) {
 		if (xflags & FS_XFLAG_REALTIME)
 			di_flags |= XFS_DIFLAG_REALTIME;
 		if (xflags & FS_XFLAG_EXTSIZE)
@@ -1060,23 +1060,86 @@ xfs_ioctl_setattr_xflags(
 }
 
 /*
+ * If we are changing DAX flags, we have to ensure the file is clean and any
+ * cached objects in the address space are invalidated and removed. This
+ * requires us to lock out other IO and page faults similar to a truncate
+ * operation. The locks need to be held until the transaction has been committed
+ * so that the cache invalidation is atomic with respect to the DAX flag
+ * manipulation.
+ */
+static int
+xfs_ioctl_setattr_dax_invalidate(
+	struct xfs_inode	*ip,
+	struct fsxattr		*fa,
+	int			*join_flags)
+{
+	struct inode		*inode = VFS_I(ip);
+	int			error;
+
+	*join_flags = 0;
+
+	/*
+	 * It is only valid to set the DAX flag on regular files and
+	 * directories on filesystems where the block size is equal to the page
+	 * size. On directories it serves as an inherit hint.
+	 */
+	if (fa->fsx_xflags & FS_XFLAG_DAX) {
+		if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+			return -EINVAL;
+		if (ip->i_mount->m_sb.sb_blocksize != PAGE_SIZE)
+			return -EINVAL;
+	}
+
+	/* If the DAX state is not changing, we have nothing to do here. */
+	if ((fa->fsx_xflags & FS_XFLAG_DAX) && IS_DAX(inode))
+		return 0;
+	if (!(fa->fsx_xflags & FS_XFLAG_DAX) && !IS_DAX(inode))
+		return 0;
+
+	/* lock, flush and invalidate mapping in preparation for flag change */
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	error = filemap_write_and_wait(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+	error = invalidate_inode_pages2(inode->i_mapping);
+	if (error)
+		goto out_unlock;
+
+	*join_flags = XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL;
+	return 0;
+
+out_unlock:
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	return error;
+
+}
+
+/*
  * Set up the transaction structure for the setattr operation, checking that we
  * have permission to do so. On success, return a clean transaction and the
  * inode locked exclusively ready for further operation specific checks. On
  * failure, return an error without modifying or locking the inode.
+ *
+ * The inode might already be IO locked on call. If this is the case, it is
+ * indicated in @join_flags and we take full responsibility for ensuring they
+ * are unlocked from now on. Hence if we have an error here, we still have to
+ * unlock them. Otherwise, once they are joined to the transaction, they will
+ * be unlocked on commit/cancel.
  */
 static struct xfs_trans *
 xfs_ioctl_setattr_get_trans(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			join_flags)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
-	int			error;
+	int			error = -EROFS;
 
 	if (mp->m_flags & XFS_MOUNT_RDONLY)
-		return ERR_PTR(-EROFS);
+		goto out_unlock;
+	error = -EIO;
 	if (XFS_FORCED_SHUTDOWN(mp))
-		return ERR_PTR(-EIO);
+		goto out_unlock;
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SETATTR_NOT_SIZE);
 	error = xfs_trans_reserve(tp, &M_RES(mp)->tr_ichange, 0, 0);
@@ -1084,7 +1147,8 @@ xfs_ioctl_setattr_get_trans(
 		goto out_cancel;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
+	join_flags = 0;
 
 	/*
 	 * CAP_FOWNER overrides the following restrictions:
@@ -1104,6 +1168,9 @@ xfs_ioctl_setattr_get_trans(
 
 out_cancel:
 	xfs_trans_cancel(tp);
+out_unlock:
+	if (join_flags)
+		xfs_iunlock(ip, join_flags);
 	return ERR_PTR(error);
 }
 
@@ -1128,14 +1195,14 @@ xfs_ioctl_setattr_check_extsize(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
-	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(ip->i_d.di_mode))
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(VFS_I(ip)->i_mode))
 		return -EINVAL;
 
 	if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
-	    !S_ISDIR(ip->i_d.di_mode))
+	    !S_ISDIR(VFS_I(ip)->i_mode))
 		return -EINVAL;
 
-	if (S_ISREG(ip->i_d.di_mode) && ip->i_d.di_nextents &&
+	if (S_ISREG(VFS_I(ip)->i_mode) && ip->i_d.di_nextents &&
 	    ((ip->i_d.di_extsize << mp->m_sb.sb_blocklog) != fa->fsx_extsize))
 		return -EINVAL;
 
@@ -1202,6 +1269,7 @@ xfs_ioctl_setattr(
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
 	int			code;
+	int			join_flags = 0;
 
 	trace_xfs_ioctl_setattr(ip);
 
@@ -1225,7 +1293,18 @@ xfs_ioctl_setattr(
 			return code;
 	}
 
-	tp = xfs_ioctl_setattr_get_trans(ip);
+	/*
+	 * Changing DAX config may require inode locking for mapping
+	 * invalidation. These need to be held all the way to transaction commit
+	 * or cancel time, so need to be passed through to
+	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
+	 * appropriately.
+	 */
+	code = xfs_ioctl_setattr_dax_invalidate(ip, fa, &join_flags);
+	if (code)
+		goto error_free_dquots;
+
+	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
 	if (IS_ERR(tp)) {
 		code = PTR_ERR(tp);
 		goto error_free_dquots;
@@ -1256,9 +1335,9 @@ xfs_ioctl_setattr(
 	 * successful return from chown()
 	 */
 
-	if ((ip->i_d.di_mode & (S_ISUID|S_ISGID)) &&
+	if ((VFS_I(ip)->i_mode & (S_ISUID|S_ISGID)) &&
 	    !capable_wrt_inode_uidgid(VFS_I(ip), CAP_FSETID))
-		ip->i_d.di_mode &= ~(S_ISUID|S_ISGID);
+		VFS_I(ip)->i_mode &= ~(S_ISUID|S_ISGID);
 
 	/* Change the ownerships and register project quota modifications */
 	if (xfs_get_projid(ip) != fa->fsx_projid) {
@@ -1341,6 +1420,7 @@ xfs_ioc_setxflags(
 	struct xfs_trans	*tp;
 	struct fsxattr		fa;
 	unsigned int		flags;
+	int			join_flags = 0;
 	int			error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1357,7 +1437,18 @@ xfs_ioc_setxflags(
 	if (error)
 		return error;
 
-	tp = xfs_ioctl_setattr_get_trans(ip);
+	/*
+	 * Changing DAX config may require inode locking for mapping
+	 * invalidation. These need to be held all the way to transaction commit
+	 * or cancel time, so need to be passed through to
+	 * xfs_ioctl_setattr_get_trans() so it can apply them to the join call
+	 * appropriately.
+	 */
+	error = xfs_ioctl_setattr_dax_invalidate(ip, &fa, &join_flags);
+	if (error)
+		goto out_drop_write;
+
+	tp = xfs_ioctl_setattr_get_trans(ip, join_flags);
 	if (IS_ERR(tp)) {
 		error = PTR_ERR(tp);
 		goto out_drop_write;