diff mbox series

[12/21] fs: xfs: Introduce FORCEALIGN inode flag

Message ID 20230929102726.2985188-13-john.g.garry@oracle.com (mailing list archive)
State New, archived
Headers show
Series block atomic writes | expand

Commit Message

John Garry Sept. 29, 2023, 10:27 a.m. UTC
From: "Darrick J. Wong" <djwong@kernel.org>

Add a new inode flag to require that all file data extent mappings must
be aligned (both the file offset range and the allocated space itself)
to the extent size hint.  Having a separate COW extent size hint is no
longer allowed.

The goal here is to enable sysadmins and users to mandate that all space
mappings in a file must have a startoff/blockcount that are aligned to
(say) a 2MB alignment and that the startblock/blockcount will follow the
same alignment.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Co-developed-by: John Garry <john.g.garry@oracle.com>
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
 fs/xfs/libxfs/xfs_format.h    |  6 +++++-
 fs/xfs/libxfs/xfs_inode_buf.c | 40 +++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_inode_buf.h |  3 +++
 fs/xfs/libxfs/xfs_sb.c        |  3 +++
 fs/xfs/xfs_inode.c            | 12 +++++++++++
 fs/xfs/xfs_inode.h            |  5 +++++
 fs/xfs/xfs_ioctl.c            | 18 ++++++++++++++++
 fs/xfs/xfs_mount.h            |  2 ++
 fs/xfs/xfs_super.c            |  4 ++++
 include/uapi/linux/fs.h       |  2 ++
 10 files changed, 94 insertions(+), 1 deletion(-)

Comments

Christoph Hellwig Nov. 9, 2023, 3:24 p.m. UTC | #1
On Fri, Sep 29, 2023 at 10:27:17AM +0000, John Garry wrote:
> From: "Darrick J. Wong" <djwong@kernel.org>
> 
> Add a new inode flag to require that all file data extent mappings must
> be aligned (both the file offset range and the allocated space itself)
> to the extent size hint.  Having a separate COW extent size hint is no
> longer allowed.
> 
> The goal here is to enable sysadmins and users to mandate that all space
> mappings in a file must have a startoff/blockcount that are aligned to
> (say) a 2MB alignment and that the startblock/blockcount will follow the
> same alignment.

This needs a good explanation of why someone would want this.
diff mbox series

Patch

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 371dc07233e0..d718b73f48ca 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -353,6 +353,7 @@  xfs_sb_has_compat_feature(
 #define XFS_SB_FEAT_RO_COMPAT_RMAPBT   (1 << 1)		/* reverse map btree */
 #define XFS_SB_FEAT_RO_COMPAT_REFLINK  (1 << 2)		/* reflinked files */
 #define XFS_SB_FEAT_RO_COMPAT_INOBTCNT (1 << 3)		/* inobt block counts */
+#define XFS_SB_FEAT_RO_COMPAT_FORCEALIGN (1 << 30)	/* aligned file data extents */
 #define XFS_SB_FEAT_RO_COMPAT_ALL \
 		(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
 		 XFS_SB_FEAT_RO_COMPAT_RMAPBT | \
@@ -1069,16 +1070,19 @@  static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #define XFS_DIFLAG2_COWEXTSIZE_BIT   2  /* copy on write extent size hint */
 #define XFS_DIFLAG2_BIGTIME_BIT	3	/* big timestamps */
 #define XFS_DIFLAG2_NREXT64_BIT 4	/* large extent counters */
+/* data extent mappings for regular files must be aligned to extent size hint */
+#define XFS_DIFLAG2_FORCEALIGN_BIT 5
 
 #define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
 #define XFS_DIFLAG2_REFLINK     (1 << XFS_DIFLAG2_REFLINK_BIT)
 #define XFS_DIFLAG2_COWEXTSIZE  (1 << XFS_DIFLAG2_COWEXTSIZE_BIT)
 #define XFS_DIFLAG2_BIGTIME	(1 << XFS_DIFLAG2_BIGTIME_BIT)
 #define XFS_DIFLAG2_NREXT64	(1 << XFS_DIFLAG2_NREXT64_BIT)
+#define XFS_DIFLAG2_FORCEALIGN	(1 << XFS_DIFLAG2_FORCEALIGN_BIT)
 
 #define XFS_DIFLAG2_ANY \
 	(XFS_DIFLAG2_DAX | XFS_DIFLAG2_REFLINK | XFS_DIFLAG2_COWEXTSIZE | \
-	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64)
+	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_FORCEALIGN)
 
 static inline bool xfs_dinode_has_bigtime(const struct xfs_dinode *dip)
 {
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index a35781577cad..0c4d492c9363 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -605,6 +605,14 @@  xfs_dinode_verify(
 	    !xfs_has_bigtime(mp))
 		return __this_address;
 
+	if (flags2 & XFS_DIFLAG2_FORCEALIGN) {
+		fa = xfs_inode_validate_forcealign(mp, mode, flags,
+				be32_to_cpu(dip->di_extsize),
+				be32_to_cpu(dip->di_cowextsize));
+		if (fa)
+			return fa;
+	}
+
 	return NULL;
 }
 
@@ -772,3 +780,35 @@  xfs_inode_validate_cowextsize(
 
 	return NULL;
 }
+
+/* Validate the forcealign inode flag */
+xfs_failaddr_t
+xfs_inode_validate_forcealign(
+	struct xfs_mount	*mp,
+	uint16_t		mode,
+	uint16_t		flags,
+	uint32_t		extsize,
+	uint32_t		cowextsize)
+{
+	/* superblock rocompat feature flag */
+	if (!xfs_has_forcealign(mp))
+		return __this_address;
+
+	/* Only regular files and directories */
+	if (!S_ISDIR(mode) && !S_ISREG(mode))
+		return __this_address;
+
+	/* Doesn't apply to realtime files */
+	if (flags & XFS_DIFLAG_REALTIME)
+		return __this_address;
+
+	/* Requires a nonzero extent size hint */
+	if (extsize == 0)
+		return __this_address;
+
+	/* Requires no cow extent size hint */
+	if (cowextsize != 0)
+		return __this_address;
+
+	return NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 585ed5a110af..50db17d22b68 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -33,6 +33,9 @@  xfs_failaddr_t xfs_inode_validate_extsize(struct xfs_mount *mp,
 xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp,
 		uint32_t cowextsize, uint16_t mode, uint16_t flags,
 		uint64_t flags2);
+xfs_failaddr_t xfs_inode_validate_forcealign(struct xfs_mount *mp,
+		uint16_t mode, uint16_t flags, uint32_t extsize,
+		uint32_t cowextsize);
 
 static inline uint64_t xfs_inode_encode_bigtime(struct timespec64 tv)
 {
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 6264daaab37b..c1be74222c70 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -162,6 +162,9 @@  xfs_sb_version_to_features(
 		features |= XFS_FEAT_REFLINK;
 	if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_INOBTCNT)
 		features |= XFS_FEAT_INOBTCNT;
+	if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FORCEALIGN)
+		features |= XFS_FEAT_FORCEALIGN;
+
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_FTYPE)
 		features |= XFS_FEAT_FTYPE;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_SPINODES)
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index f94f7b374041..3fbfb052c778 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -634,6 +634,8 @@  xfs_ip2xflags(
 			flags |= FS_XFLAG_DAX;
 		if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
 			flags |= FS_XFLAG_COWEXTSIZE;
+		if (ip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN)
+			flags |= FS_XFLAG_FORCEALIGN;
 	}
 
 	if (xfs_inode_has_attr_fork(ip))
@@ -761,6 +763,8 @@  xfs_inode_inherit_flags2(
 	}
 	if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
 		ip->i_diflags2 |= XFS_DIFLAG2_DAX;
+	if (pip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN)
+		ip->i_diflags2 |= XFS_DIFLAG2_FORCEALIGN;
 
 	/* Don't let invalid cowextsize hints propagate. */
 	failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
@@ -769,6 +773,14 @@  xfs_inode_inherit_flags2(
 		ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE;
 		ip->i_cowextsize = 0;
 	}
+
+	if (ip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN) {
+		failaddr = xfs_inode_validate_forcealign(ip->i_mount,
+				VFS_I(ip)->i_mode, ip->i_diflags, ip->i_extsize,
+				ip->i_cowextsize);
+		if (failaddr)
+			ip->i_diflags2 &= ~XFS_DIFLAG2_FORCEALIGN;
+	}
 }
 
 /*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 0c5bdb91152e..f66a57085908 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -305,6 +305,11 @@  static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_NREXT64;
 }
 
+static inline bool xfs_inode_forcealign(struct xfs_inode *ip)
+{
+	return ip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN;
+}
+
 /*
  * Return the buftarg used for data allocations on a given inode.
  */
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 55bb01173cde..4c147def835f 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1109,6 +1109,8 @@  xfs_flags2diflags2(
 		di_flags2 |= XFS_DIFLAG2_DAX;
 	if (xflags & FS_XFLAG_COWEXTSIZE)
 		di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+	if (xflags & FS_XFLAG_FORCEALIGN)
+		di_flags2 |= XFS_DIFLAG2_FORCEALIGN;
 
 	return di_flags2;
 }
@@ -1143,6 +1145,22 @@  xfs_ioctl_setattr_xflags(
 	if (i_flags2 && !xfs_has_v3inodes(mp))
 		return -EINVAL;
 
+	/*
+	 * Force-align requires a nonzero extent size hint and a zero cow
+	 * extent size hint.  It doesn't apply to realtime files.
+	 */
+	if (fa->fsx_xflags & FS_XFLAG_FORCEALIGN) {
+		if (!xfs_has_forcealign(mp))
+			return -EINVAL;
+		if (fa->fsx_xflags & FS_XFLAG_COWEXTSIZE)
+			return -EINVAL;
+		if (!(fa->fsx_xflags & (FS_XFLAG_EXTSIZE |
+					FS_XFLAG_EXTSZINHERIT)))
+			return -EINVAL;
+		if (fa->fsx_xflags & FS_XFLAG_REALTIME)
+			return -EINVAL;
+	}
+
 	ip->i_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
 	ip->i_diflags2 = i_flags2;
 
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index d19cca099bc3..a7553b8bcc64 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -287,6 +287,7 @@  typedef struct xfs_mount {
 #define XFS_FEAT_BIGTIME	(1ULL << 24)	/* large timestamps */
 #define XFS_FEAT_NEEDSREPAIR	(1ULL << 25)	/* needs xfs_repair */
 #define XFS_FEAT_NREXT64	(1ULL << 26)	/* large extent counters */
+#define XFS_FEAT_FORCEALIGN	(1ULL << 27)	/* aligned file data extents */
 
 /* Mount features */
 #define XFS_FEAT_NOATTR2	(1ULL << 48)	/* disable attr2 creation */
@@ -350,6 +351,7 @@  __XFS_HAS_FEAT(inobtcounts, INOBTCNT)
 __XFS_HAS_FEAT(bigtime, BIGTIME)
 __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR)
 __XFS_HAS_FEAT(large_extent_counts, NREXT64)
+__XFS_HAS_FEAT(forcealign, FORCEALIGN)
 
 /*
  * Mount features
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 819a3568b28f..1bbb25df23a7 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1703,6 +1703,10 @@  xfs_fs_fill_super(
 		mp->m_features &= ~XFS_FEAT_DISCARD;
 	}
 
+	if (xfs_has_forcealign(mp))
+		xfs_warn(mp,
+"EXPERIMENTAL forced data extent alignment feature in use. Use at your own risk!");
+
 	if (xfs_has_reflink(mp)) {
 		if (mp->m_sb.sb_rblocks) {
 			xfs_alert(mp,
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index e3b4f5bc6860..cbfb09bc1717 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -140,6 +140,8 @@  struct fsxattr {
 #define FS_XFLAG_FILESTREAM	0x00004000	/* use filestream allocator */
 #define FS_XFLAG_DAX		0x00008000	/* use DAX for IO */
 #define FS_XFLAG_COWEXTSIZE	0x00010000	/* CoW extent size allocator hint */
+/* data extent mappings for regular files must be aligned to extent size hint */
+#define FS_XFLAG_FORCEALIGN	0x00020000
 #define FS_XFLAG_HASATTR	0x80000000	/* no DIFLAG for this	*/
 
 /* the read-only stuff doesn't really belong here, but any other place is