| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20241004092254.3759210-6-john.g.garry@oracle.com>
Date: Fri, 4 Oct 2024 09:22:51 +0000
From: John Garry <john.g.garry@...cle.com>
To: axboe@...nel.dk, brauner@...nel.org, djwong@...nel.org,
viro@...iv.linux.org.uk, jack@...e.cz, dchinner@...hat.com, hch@....de,
cem@...nel.org
Cc: linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
linux-xfs@...r.kernel.org, linux-fsdevel@...r.kernel.org, hare@...e.de,
martin.petersen@...cle.com, catherine.hoang@...cle.com,
mcgrof@...nel.org, ritesh.list@...il.com, ojaswin@...ux.ibm.com,
John Garry <john.g.garry@...cle.com>
Subject: [PATCH v7 5/8] xfs: Support FS_XFLAG_ATOMICWRITES
Add initial support for new flag FS_XFLAG_ATOMICWRITES.
This flag is a file attribute that mirrors an ondisk inode flag. Actual
support for untorn file writes (for now) depends on both the iflag and the
underlying storage devices, which we can only really check at statx and
pwritev2() time. This is the same story as FS_XFLAG_DAX, which signals to
the fs that we should try to enable the fsdax IO path on the file (instead
of the regular page cache), but applications have to query STAT_ATTR_DAX to
find out if they really got that IO path.
Current kernel support for atomic writes is based on HW support (for atomic
writes). Since for regular files XFS has no way to specify extent alignment
or granularity, atomic write size is limited to the FS block size.
Signed-off-by: John Garry <john.g.garry@...cle.com>
---
fs/xfs/libxfs/xfs_format.h | 11 +++++++++--
fs/xfs/libxfs/xfs_inode_buf.c | 22 ++++++++++++++++++++++
fs/xfs/libxfs/xfs_inode_util.c | 6 ++++++
fs/xfs/libxfs/xfs_sb.c | 2 ++
fs/xfs/xfs_buf.c | 7 +++++++
fs/xfs/xfs_buf.h | 3 +++
fs/xfs/xfs_inode.h | 5 +++++
fs/xfs/xfs_ioctl.c | 27 +++++++++++++++++++++++++++
fs/xfs/xfs_mount.h | 2 ++
fs/xfs/xfs_super.c | 4 ++++
include/uapi/linux/fs.h | 1 +
11 files changed, 88 insertions(+), 2 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index e1bfee0c3b1a..ed5e5442f0d4 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -352,11 +352,15 @@ 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_ATOMICWRITES (1 << 31) /* atomicwrites enabled */
+
#define XFS_SB_FEAT_RO_COMPAT_ALL \
(XFS_SB_FEAT_RO_COMPAT_FINOBT | \
XFS_SB_FEAT_RO_COMPAT_RMAPBT | \
XFS_SB_FEAT_RO_COMPAT_REFLINK| \
- XFS_SB_FEAT_RO_COMPAT_INOBTCNT)
+ XFS_SB_FEAT_RO_COMPAT_INOBTCNT | \
+ XFS_SB_FEAT_RO_COMPAT_ATOMICWRITES)
+
#define XFS_SB_FEAT_RO_COMPAT_UNKNOWN ~XFS_SB_FEAT_RO_COMPAT_ALL
static inline bool
xfs_sb_has_ro_compat_feature(
@@ -1093,16 +1097,19 @@ 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 */
+#define XFS_DIFLAG2_ATOMICWRITES_BIT 5 /* atomic writes permitted */
#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_ATOMICWRITES (1 << XFS_DIFLAG2_ATOMICWRITES_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_ATOMICWRITES)
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 79babeac9d75..7fe94d038e83 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -483,6 +483,22 @@ xfs_dinode_verify_nrext64(
return NULL;
}
+static xfs_failaddr_t
+xfs_inode_validate_atomicwrites(
+ struct xfs_mount *mp,
+ uint16_t mode)
+{
+ /* superblock rocompat feature flag */
+ if (!xfs_has_atomicwrites(mp))
+ return __this_address;
+
+ /* Only regular files and directories */
+ if (!S_ISREG(mode) && !(S_ISDIR(mode)))
+ return __this_address;
+
+ return NULL;
+}
+
xfs_failaddr_t
xfs_dinode_verify(
struct xfs_mount *mp,
@@ -663,6 +679,12 @@ xfs_dinode_verify(
!xfs_has_bigtime(mp))
return __this_address;
+ if (flags2 & XFS_DIFLAG2_ATOMICWRITES) {
+ fa = xfs_inode_validate_atomicwrites(mp, mode);
+ if (fa)
+ return fa;
+ }
+
return NULL;
}
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index cc38e1c3c3e1..e59e98783bf7 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -80,6 +80,8 @@ xfs_flags2diflags2(
di_flags2 |= XFS_DIFLAG2_DAX;
if (xflags & FS_XFLAG_COWEXTSIZE)
di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+ if (xflags & FS_XFLAG_ATOMICWRITES)
+ di_flags2 |= XFS_DIFLAG2_ATOMICWRITES;
return di_flags2;
}
@@ -126,6 +128,8 @@ xfs_ip2xflags(
flags |= FS_XFLAG_DAX;
if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
flags |= FS_XFLAG_COWEXTSIZE;
+ if (ip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES)
+ flags |= FS_XFLAG_ATOMICWRITES;
}
if (xfs_inode_has_attr_fork(ip))
@@ -224,6 +228,8 @@ xfs_inode_inherit_flags2(
}
if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
ip->i_diflags2 |= XFS_DIFLAG2_DAX;
+ if (pip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES)
+ ip->i_diflags2 |= XFS_DIFLAG2_ATOMICWRITES;
/* Don't let invalid cowextsize hints propagate. */
failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index d95409f3cba6..dd819561d0a5 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -164,6 +164,8 @@ 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_ATOMICWRITES)
+ features |= XFS_FEAT_ATOMICWRITES;
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_buf.c b/fs/xfs/xfs_buf.c
index aa4dbda7b536..e279e5e139ff 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2115,6 +2115,13 @@ xfs_alloc_buftarg(
btp->bt_daxdev = fs_dax_get_by_bdev(btp->bt_bdev, &btp->bt_dax_part_off,
mp, ops);
+ if (bdev_can_atomic_write(btp->bt_bdev)) {
+ struct request_queue *q = bdev_get_queue(btp->bt_bdev);
+
+ btp->bt_bdev_awu_min = queue_atomic_write_unit_min_bytes(q);
+ btp->bt_bdev_awu_max = queue_atomic_write_unit_max_bytes(q);
+ }
+
/*
* When allocating the buftargs we have not yet read the super block and
* thus don't know the file system sector size yet.
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 209a389f2abc..2be28bd01087 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -124,6 +124,9 @@ struct xfs_buftarg {
struct percpu_counter bt_io_count;
struct ratelimit_state bt_ioerror_rl;
+ /* Atomic write unit values */
+ unsigned int bt_bdev_awu_min, bt_bdev_awu_max;
+
/* built-in cache, if we're not using the perag one */
struct xfs_buf_cache bt_cache[];
};
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 97ed912306fd..1c62ee294a5a 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -327,6 +327,11 @@ static inline bool xfs_inode_has_bigrtalloc(struct xfs_inode *ip)
(XFS_IS_REALTIME_INODE(ip) ? \
(ip)->i_mount->m_rtdev_targp : (ip)->i_mount->m_ddev_targp)
+static inline bool xfs_inode_has_atomicwrites(struct xfs_inode *ip)
+{
+ return ip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES;
+}
+
/*
* In-core inode flags.
*/
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index a20d426ef021..1c980c863ada 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -469,6 +469,26 @@ xfs_fileattr_get(
return 0;
}
+static int
+xfs_ioctl_setattr_atomicwrites(
+ struct xfs_inode *ip)
+{
+ struct xfs_buftarg *target = xfs_inode_buftarg(ip);
+ struct xfs_mount *mp = ip->i_mount;
+ struct xfs_sb *sbp = &mp->m_sb;
+
+ if (!xfs_has_atomicwrites(mp))
+ return -EINVAL;
+
+ if (target->bt_bdev_awu_min > sbp->sb_blocksize)
+ return -EINVAL;
+
+ if (target->bt_bdev_awu_max < sbp->sb_blocksize)
+ return -EINVAL;
+
+ return 0;
+}
+
static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,
@@ -478,6 +498,7 @@ xfs_ioctl_setattr_xflags(
struct xfs_mount *mp = ip->i_mount;
bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
uint64_t i_flags2;
+ int error;
if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
/* Can't change realtime flag if any extents are allocated. */
@@ -512,6 +533,12 @@ xfs_ioctl_setattr_xflags(
if (i_flags2 && !xfs_has_v3inodes(mp))
return -EINVAL;
+ if (fa->fsx_xflags & FS_XFLAG_ATOMICWRITES) {
+ error = xfs_ioctl_setattr_atomicwrites(ip);
+ if (error)
+ return error;
+ }
+
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 96496f39f551..6ac6518a2ef3 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -298,6 +298,7 @@ typedef struct xfs_mount {
#define XFS_FEAT_NEEDSREPAIR (1ULL << 25) /* needs xfs_repair */
#define XFS_FEAT_NREXT64 (1ULL << 26) /* large extent counters */
#define XFS_FEAT_EXCHANGE_RANGE (1ULL << 27) /* exchange range */
+#define XFS_FEAT_ATOMICWRITES (1ULL << 28) /* atomic writes support */
/* Mount features */
#define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */
@@ -384,6 +385,7 @@ __XFS_ADD_V4_FEAT(projid32, PROJID32)
__XFS_HAS_V4_FEAT(v3inodes, V3INODES)
__XFS_HAS_V4_FEAT(crc, CRC)
__XFS_HAS_V4_FEAT(pquotino, PQUOTINO)
+__XFS_HAS_FEAT(atomicwrites, ATOMICWRITES)
/*
* Mount features
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index fbb3a1594c0d..97c1d9493cdb 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1733,6 +1733,10 @@ xfs_fs_fill_super(
mp->m_features &= ~XFS_FEAT_DISCARD;
}
+ if (xfs_has_atomicwrites(mp))
+ xfs_warn(mp,
+ "EXPERIMENTAL atomicwrites 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 753971770733..e813217e0fe4 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -158,6 +158,7 @@ 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 */
+#define FS_XFLAG_ATOMICWRITES 0x00020000 /* atomic writes enabled */
#define FS_XFLAG_HASATTR 0x80000000 /* no DIFLAG for this */
/* the read-only stuff doesn't really belong here, but any other place is
--
2.31.1
Powered by blists - more mailing lists