Third part of new DAX code for 5.8:

- Teach XFS to ask the VFS to drop an inode if the administrator changes
   the FS_XFLAG_DAX inode flag such that the S_DAX state would change.
   This can result in files changing access modes without requiring an
   unmount cycle.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEEUzaAxoMeQq6m2jMV+H93GTRKtOsFAl7WezgACgkQ+H93GTRK
 tOvGCg//QCKK9yEBE0sjR0hjeJwmvoxAtdCGyrq+h1wZ1OI+iZCy3K4D9+/NSl/Z
 SajLB2bK2mJBBZmERJlRITnTwSFbHX5roMHK4NDTqRAusHdm92JxMWds5ZMXGuTD
 HiJ3Luu4VWHBuraRB5JKxHWyDc57xSE0kC1KwPySQCNAuDv+YS42uZMAM6284T/J
 hkE4odUztykN+tOZj/nY+FiRjhzLF93cghMmRlDlgmibyHGLMhrfEmaMj99eCA5O
 PVepVA6Vk0IHWviAWS8vqX2LADQaP1U2RP4racBAdmk+Z6kqUV+KSotJU1O+6ey/
 Zfnr4VytKxmxngXhR4wnQcu3sIZqDdZRF4mcngE/G1yJXKim5iwVX+D04BsvDOpo
 OpND9+dOuh4ecbayfOGxp9lmBsPQBzI/qPpUcpbtsRd5xN5IyTL6MyNsSPJg2ZrG
 5BaSUO+Hw6hmBcB5MLF36XBuj25QEITl/hxy66Ym2BiQT5im9a3JxRlj8OvoWEVI
 1323WehvPSA1bl7m1mNQyE7/h7TjeGA6LiTplSxPqencKzXn93wcTDV09GOZ11No
 UEb+yC97hzRepEq4hSTr7tu18RN04ryA28/Vtcm/YeeM2bQ5WpI6jTd3b7g55BE2
 EuUGAUFLZRKsvSnLhg/GbuaW442osAKuNttIL1NEyPs0Iw76Ero=
 =mKZf
 -----END PGP SIGNATURE-----

Merge tag 'vfs-5.8-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull DAX updates part three from Darrick Wong:
 "Now that the xfs changes have landed, this third piece changes the
  FS_XFLAG_DAX ioctl code in xfs to request that the inode be reloaded
  after the last program closes the file, if doing so would make a S_DAX
  change happen. The goal here is to make dax access mode switching
  quicker when possible.

  Summary:

   - Teach XFS to ask the VFS to drop an inode if the administrator
     changes the FS_XFLAG_DAX inode flag such that the S_DAX state would
     change. This can result in files changing access modes without
     requiring an unmount cycle"

* tag 'vfs-5.8-merge-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  fs/xfs: Update xfs_ioctl_setattr_dax_invalidate()
  fs/xfs: Combine xfs_diflags_to_linux() and xfs_diflags_to_iflags()
  fs/xfs: Create function xfs_inode_should_enable_dax()
  fs/xfs: Make DAX mount option a tri-state
  fs/xfs: Change XFS_MOUNT_DAX to XFS_MOUNT_DAX_ALWAYS
  fs/xfs: Remove unnecessary initialization of i_rwsem

fs/xfs/xfs_ioctl.c

@@ -1236,64 +1236,26 @@ xfs_ioctl_setattr_xflags(
 	return 0;
 }
 
-/*
+static void
- * If we are changing DAX flags, we have to ensure the file is clean and any
+xfs_ioctl_setattr_prepare_dax(
- * 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,
+	struct fsxattr		*fa)
-	int			*join_flags)
 {
-	struct inode		*inode = VFS_I(ip);
+	struct xfs_mount	*mp = ip->i_mount;
-	struct super_block	*sb = inode->i_sb;
+	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 inherited hint so we don't
-	 * have to check the device for dax support or flush pagecache.
-	 */
-	if (fa->fsx_xflags & FS_XFLAG_DAX) {
-		struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
-
-		if (!bdev_dax_supported(target->bt_bdev, sb->s_blocksize))
-			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;
 
 	if (S_ISDIR(inode->i_mode))
-		return 0;
+		return;
 
-	/* lock, flush and invalidate mapping in preparation for flag change */
+	if ((mp->m_flags & XFS_MOUNT_DAX_ALWAYS) ||
-	xfs_ilock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
+	    (mp->m_flags & XFS_MOUNT_DAX_NEVER))
-	error = filemap_write_and_wait(inode->i_mapping);
+		return;
-	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;
 
+	if (((fa->fsx_xflags & FS_XFLAG_DAX) &&
+	    !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)) ||
+	    (!(fa->fsx_xflags & FS_XFLAG_DAX) &&
+	     (ip->i_d.di_flags2 & XFS_DIFLAG2_DAX)))
+		d_mark_dontcache(inode);
 }
 
 /*
@@ -1301,17 +1263,10 @@ out_unlock:
  * 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;
@@ -1328,8 +1283,7 @@ xfs_ioctl_setattr_get_trans(
 		goto out_unlock;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
-	join_flags = 0;
 
 	/*
 	 * CAP_FOWNER overrides the following restrictions:
@@ -1350,8 +1304,6 @@ 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);
 }
 
@@ -1476,7 +1428,6 @@ xfs_ioctl_setattr(
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
 	int			code;
-	int			join_flags = 0;
 
 	trace_xfs_ioctl_setattr(ip);
 
@@ -1500,18 +1451,9 @@ xfs_ioctl_setattr(
 			return code;
 	}
 
-	/*
+	xfs_ioctl_setattr_prepare_dax(ip, fa);
-	 * 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);
+	tp = xfs_ioctl_setattr_get_trans(ip);
 	if (IS_ERR(tp)) {
 		code = PTR_ERR(tp);
 		goto error_free_dquots;
@@ -1639,7 +1581,6 @@ xfs_ioc_setxflags(
 	struct fsxattr		fa;
 	struct fsxattr		old_fa;
 	unsigned int		flags;
-	int			join_flags = 0;
 	int			error;
 
 	if (copy_from_user(&flags, arg, sizeof(flags)))
@@ -1656,18 +1597,9 @@ xfs_ioc_setxflags(
 	if (error)
 		return error;
 
-	/*
+	xfs_ioctl_setattr_prepare_dax(ip, &fa);
-	 * 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);
+	tp = xfs_ioctl_setattr_get_trans(ip);
 	if (IS_ERR(tp)) {
 		error = PTR_ERR(tp);
 		goto out_drop_write;