LKML Archive on lore.kernel.org
 help / color / Atom feed
From: ira.weiny@intel.com
To: linux-kernel@vger.kernel.org, linux-xfs@vger.kernel.org,
	"Darrick J. Wong" <darrick.wong@oracle.com>
Cc: Ira Weiny <ira.weiny@intel.com>,
	Al Viro <viro@zeniv.linux.org.uk>, Jan Kara <jack@suse.cz>,
	Dan Williams <dan.j.williams@intel.com>,
	Dave Chinner <david@fromorbit.com>,
	Christoph Hellwig <hch@lst.de>,
	"Theodore Y. Ts'o" <tytso@mit.edu>,
	Jeff Moyer <jmoyer@redhat.com>,
	linux-ext4@vger.kernel.org, linux-fsdevel@vger.kernel.org,
	linux-api@vger.kernel.org
Subject: [PATCH V11 11/11] fs/xfs: Update xfs_ioctl_setattr_dax_invalidate()
Date: Mon, 27 Apr 2020 17:21:42 -0700
Message-ID: <20200428002142.404144-12-ira.weiny@intel.com> (raw)
In-Reply-To: <20200428002142.404144-1-ira.weiny@intel.com>

From: Ira Weiny <ira.weiny@intel.com>

Because of the separation of FS_XFLAG_DAX from S_DAX and the delayed
setting of S_DAX, data invalidation no longer needs to happen when
FS_XFLAG_DAX is changed.

Change xfs_ioctl_setattr_dax_invalidate() to be
xfs_ioctl_dax_check_set_cache() and alter the code to reflect the new
functionality.

Furthermore, we no longer need the locking so we remove the join_flags
logic.

Signed-off-by: Ira Weiny <ira.weiny@intel.com>

---
Changes from V10:
	adjust for renamed d_mark_dontcache() function

Changes from V9:
	Change name of function to xfs_ioctl_setattr_prepare_dax()

Changes from V8:
	Change name of function to xfs_ioctl_dax_check_set_cache()
	Update commit message
	Fix bit manipulations

Changes from V7:
	Use new flag_inode_dontcache()
	Skip don't cache if mount over ride is active.

Changes from v6:
	Fix completely broken implementation and update commit message.
	Use the new VFS layer I_DONTCACHE to facilitate inode eviction
	and S_DAX changing on drop_caches

Changes from v5:
	New patch
---
 fs/xfs/xfs_ioctl.c | 108 +++++++++------------------------------------
 1 file changed, 20 insertions(+), 88 deletions(-)

diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 104495ac187c..ff474f2c9acf 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1245,64 +1245,26 @@ xfs_ioctl_setattr_xflags(
 	return 0;
 }
 
-/*
- * 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(
+static void
+xfs_ioctl_setattr_prepare_dax(
 	struct xfs_inode	*ip,
-	struct fsxattr		*fa,
-	int			*join_flags)
+	struct fsxattr		*fa)
 {
-	struct inode		*inode = VFS_I(ip);
-	struct super_block	*sb = inode->i_sb;
-	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;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct inode            *inode = VFS_I(ip);
 
 	if (S_ISDIR(inode->i_mode))
-		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;
+		return;
 
-out_unlock:
-	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL | XFS_IOLOCK_EXCL);
-	return error;
+	if ((mp->m_flags & XFS_MOUNT_DAX_ALWAYS) ||
+	    (mp->m_flags & XFS_MOUNT_DAX_NEVER))
+		return;
 
+	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);
 }
 
 /*
@@ -1310,17 +1272,10 @@ xfs_ioctl_setattr_dax_invalidate(
  * 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,
-	int			join_flags)
+	struct xfs_inode	*ip)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
@@ -1337,8 +1292,7 @@ xfs_ioctl_setattr_get_trans(
 		goto out_unlock;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | join_flags);
-	join_flags = 0;
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 
 	/*
 	 * CAP_FOWNER overrides the following restrictions:
@@ -1359,8 +1313,6 @@ 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);
 }
 
@@ -1486,7 +1438,6 @@ xfs_ioctl_setattr(
 	struct xfs_dquot	*pdqp = NULL;
 	struct xfs_dquot	*olddquot = NULL;
 	int			code;
-	int			join_flags = 0;
 
 	trace_xfs_ioctl_setattr(ip);
 
@@ -1510,18 +1461,9 @@ xfs_ioctl_setattr(
 			return code;
 	}
 
-	/*
-	 * 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;
+	xfs_ioctl_setattr_prepare_dax(ip, fa);
 
-	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;
@@ -1651,7 +1593,6 @@ 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)))
@@ -1668,18 +1609,9 @@ xfs_ioc_setxflags(
 	if (error)
 		return error;
 
-	/*
-	 * 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;
+	xfs_ioctl_setattr_prepare_dax(ip, &fa);
 
-	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;
-- 
2.25.1


  parent reply index

Thread overview: 29+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-04-28  0:21 [PATCH V11 00/11] XFS - Enable per-file/per-directory DAX operations V11 ira.weiny
2020-04-28  0:21 ` [PATCH V11 01/11] fs/xfs: Remove unnecessary initialization of i_rwsem ira.weiny
2020-04-28  0:21 ` [PATCH V11 02/11] fs: Remove unneeded IS_DAX() check in io_is_direct() ira.weiny
2020-04-28  0:21 ` [PATCH V11 03/11] fs/stat: Define DAX statx attribute ira.weiny
2020-04-28  0:21 ` [PATCH V11 04/11] Documentation/dax: Update Usage section ira.weiny
2020-04-28 20:27   ` Darrick J. Wong
2020-04-28 20:53     ` Ira Weiny
2020-04-28 21:12       ` Darrick J. Wong
2020-04-28 22:21   ` [PATCH V11.1] " ira.weiny
2020-04-29  2:21     ` Randy Dunlap
2020-04-29  4:30       ` Ira Weiny
2020-04-29  4:33     ` [PATCH V11.2] " ira.weiny
2020-04-29  5:47       ` Randy Dunlap
2020-04-28  0:21 ` [PATCH V11 05/11] fs/xfs: Change XFS_MOUNT_DAX to XFS_MOUNT_DAX_ALWAYS ira.weiny
2020-04-28  0:21 ` [PATCH V11 06/11] fs/xfs: Make DAX mount option a tri-state ira.weiny
2020-04-28 20:08   ` Darrick J. Wong
2020-04-28  0:21 ` [PATCH V11 07/11] fs/xfs: Create function xfs_inode_should_enable_dax() ira.weiny
2020-04-28  0:21 ` [PATCH V11 08/11] fs/xfs: Combine xfs_diflags_to_linux() and xfs_diflags_to_iflags() ira.weiny
2020-04-28  0:21 ` [PATCH V11 09/11] fs: Lift XFS_IDONTCACHE to the VFS layer ira.weiny
2020-04-28 20:06   ` Darrick J. Wong
2020-04-28  0:21 ` [PATCH V11 10/11] fs: Introduce DCACHE_DONTCACHE ira.weiny
2020-04-28 13:04   ` Jan Kara
2020-04-28 20:09   ` Darrick J. Wong
2020-04-28  0:21 ` ira.weiny [this message]
2020-04-28 20:11   ` [PATCH V11 11/11] fs/xfs: Update xfs_ioctl_setattr_dax_invalidate() Darrick J. Wong
2020-06-02 17:23     ` Darrick J. Wong
2020-06-02 23:15       ` Ira Weiny
2020-06-03 10:10       ` Jan Kara
2020-06-03 17:03         ` Darrick J. Wong

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200428002142.404144-12-ira.weiny@intel.com \
    --to=ira.weiny@intel.com \
    --cc=dan.j.williams@intel.com \
    --cc=darrick.wong@oracle.com \
    --cc=david@fromorbit.com \
    --cc=hch@lst.de \
    --cc=jack@suse.cz \
    --cc=jmoyer@redhat.com \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-ext4@vger.kernel.org \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-xfs@vger.kernel.org \
    --cc=tytso@mit.edu \
    --cc=viro@zeniv.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git