From: John Garry <john.g.garry@oracle.com>
To: hch@lst.de, djwong@kernel.org, viro@zeniv.linux.org.uk,
brauner@kernel.org, dchinner@redhat.com, jack@suse.cz,
chandan.babu@oracle.com
Cc: martin.petersen@oracle.com, linux-kernel@vger.kernel.org,
linux-xfs@vger.kernel.org, linux-fsdevel@vger.kernel.org,
tytso@mit.edu, jbongio@google.com, ojaswin@linux.ibm.com,
John Garry <john.g.garry@oracle.com>
Subject: [PATCH 3/6] fs: xfs: Support FS_XFLAG_ATOMICWRITES for rtvol
Date: Wed, 24 Jan 2024 14:26:42 +0000 [thread overview]
Message-ID: <20240124142645.9334-4-john.g.garry@oracle.com> (raw)
In-Reply-To: <20240124142645.9334-1-john.g.garry@oracle.com>
Add initial support for FS_XFLAG_ATOMICWRITES in rtvol.
Current kernel support for atomic writes is based on HW support (for atomic
writes). As such, it is required to ensure extent alignment with
atomic_write_unit_max so that an atomic write can result in a single
HW-compliant IO operation.
rtvol already guarantees extent alignment, so initially add support there.
Signed-off-by: John Garry <john.g.garry@oracle.com>
---
fs/xfs/libxfs/xfs_format.h | 8 ++++++--
fs/xfs/libxfs/xfs_sb.c | 2 ++
fs/xfs/xfs_inode.c | 22 ++++++++++++++++++++++
fs/xfs/xfs_inode.h | 7 +++++++
fs/xfs/xfs_ioctl.c | 19 +++++++++++++++++--
fs/xfs/xfs_mount.h | 2 ++
fs/xfs/xfs_super.c | 4 ++++
7 files changed, 60 insertions(+), 4 deletions(-)
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 382ab1e71c0b..79fb0d4adeda 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -353,11 +353,13 @@ 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 << 29) /* aligned file data extents */
#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(
@@ -1085,16 +1087,18 @@ 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 6
#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_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 4a9e8588f4c9..28a98130a56d 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -163,6 +163,8 @@ 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_inode.c b/fs/xfs/xfs_inode.c
index 1fd94958aa97..0b0f525fd043 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -65,6 +65,26 @@ xfs_get_extsz_hint(
return 0;
}
+/*
+ * helper function to extract extent size
+ */
+xfs_extlen_t
+xfs_get_extsz(
+ struct xfs_inode *ip)
+{
+ /*
+ * No point in aligning allocations if we need to COW to actually
+ * write to them.
+ */
+ if (xfs_is_always_cow_inode(ip))
+ return 0;
+
+ if (XFS_IS_REALTIME_INODE(ip))
+ return ip->i_mount->m_sb.sb_rextsize;
+
+ return 1;
+}
+
/*
* Helper function to extract CoW extent size hint from inode.
* Between the extent size hint and the CoW extent size hint, we
@@ -629,6 +649,8 @@ 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))
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 97f63bacd4c2..0e0a21d9d30f 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_atomicwrites(struct xfs_inode *ip)
+{
+ return ip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES;
+}
+
/*
* Return the buftarg used for data allocations on a given inode.
*/
@@ -542,7 +547,9 @@ void xfs_lock_two_inodes(struct xfs_inode *ip0, uint ip0_mode,
struct xfs_inode *ip1, uint ip1_mode);
xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
+xfs_extlen_t xfs_get_extsz(struct xfs_inode *ip);
xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip);
+xfs_extlen_t xfs_get_atomicwrites_size(struct xfs_inode *ip);
int xfs_init_new_inode(struct mnt_idmap *idmap, struct xfs_trans *tp,
struct xfs_inode *pip, xfs_ino_t ino, umode_t mode,
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index f02b6e558af5..c380a3055be7 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1110,6 +1110,8 @@ 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;
}
@@ -1122,10 +1124,12 @@ xfs_ioctl_setattr_xflags(
{
struct xfs_mount *mp = ip->i_mount;
bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
+ bool atomic_writes = fa->fsx_xflags & FS_XFLAG_ATOMICWRITES;
uint64_t i_flags2;
- if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
- /* Can't change realtime flag if any extents are allocated. */
+
+ if (rtflag != XFS_IS_REALTIME_INODE(ip) ||
+ atomic_writes != xfs_inode_atomicwrites(ip)) {
if (ip->i_df.if_nextents || ip->i_delayed_blks)
return -EINVAL;
}
@@ -1146,6 +1150,17 @@ xfs_ioctl_setattr_xflags(
if (i_flags2 && !xfs_has_v3inodes(mp))
return -EINVAL;
+ if (atomic_writes) {
+ if (!xfs_has_atomicwrites(mp))
+ return -EINVAL;
+
+ if (!rtflag)
+ return -EINVAL;
+
+ if (!is_power_of_2(mp->m_sb.sb_rextsize))
+ 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 503fe3c7edbf..bcd591f52925 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -289,6 +289,7 @@ 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_ATOMICWRITES (1ULL << 28) /* atomic writes support */
/* Mount features */
#define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */
@@ -352,6 +353,7 @@ __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(atomicwrites, ATOMICWRITES)
/*
* Mount features
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index aff20ddd4a9f..263404f683d6 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1696,6 +1696,10 @@ xfs_fs_fill_super(
mp->m_features &= ~XFS_FEAT_DISCARD;
}
+ if (xfs_has_atomicwrites(mp))
+ xfs_warn(mp,
+"EXPERIMENTAL atomic writes feature in use. Use at your own risk!");
+
if (xfs_has_reflink(mp)) {
if (mp->m_sb.sb_rblocks) {
xfs_alert(mp,
--
2.31.1
next prev parent reply other threads:[~2024-01-24 14:30 UTC|newest]
Thread overview: 68+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-24 14:26 [PATCH 0/6] block atomic writes for XFS John Garry
2024-01-24 14:26 ` [PATCH 1/6] fs: iomap: Atomic write support John Garry
2024-02-02 17:25 ` Darrick J. Wong
2024-02-05 11:29 ` John Garry
2024-02-13 6:55 ` Christoph Hellwig
2024-02-13 8:20 ` John Garry
2024-02-15 11:08 ` John Garry
2024-02-13 18:08 ` Darrick J. Wong
2024-02-05 15:20 ` Pankaj Raghav (Samsung)
2024-02-05 15:41 ` John Garry
2024-01-24 14:26 ` [PATCH 2/6] fs: Add FS_XFLAG_ATOMICWRITES flag John Garry
2024-02-02 17:57 ` Darrick J. Wong
2024-02-05 12:58 ` John Garry
2024-02-13 6:56 ` Christoph Hellwig
2024-02-13 17:08 ` Darrick J. Wong
2024-01-24 14:26 ` John Garry [this message]
2024-02-02 17:52 ` [PATCH 3/6] fs: xfs: Support FS_XFLAG_ATOMICWRITES for rtvol Darrick J. Wong
2024-02-03 7:40 ` Ojaswin Mujoo
2024-02-05 12:51 ` John Garry
2024-02-13 17:22 ` Darrick J. Wong
2024-02-14 12:19 ` John Garry
2024-01-24 14:26 ` [PATCH 4/6] fs: xfs: Support atomic write for statx John Garry
2024-02-02 18:05 ` Darrick J. Wong
2024-02-05 13:10 ` John Garry
2024-02-13 17:37 ` Darrick J. Wong
2024-02-14 12:26 ` John Garry
2024-02-09 7:00 ` Ojaswin Mujoo
2024-02-09 17:30 ` John Garry
2024-02-12 11:48 ` Ojaswin Mujoo
2024-02-12 12:05 ` Ojaswin Mujoo
2024-01-24 14:26 ` [PATCH RFC 5/6] fs: xfs: iomap atomic write support John Garry
2024-02-02 18:47 ` Darrick J. Wong
2024-02-05 13:36 ` John Garry
2024-02-06 1:15 ` Dave Chinner
2024-02-06 9:53 ` John Garry
2024-02-07 0:06 ` Dave Chinner
2024-02-07 14:13 ` John Garry
2024-02-09 1:40 ` Dave Chinner
2024-02-09 12:47 ` John Garry
2024-02-13 23:41 ` Dave Chinner
2024-02-14 11:06 ` John Garry
2024-02-14 23:03 ` Dave Chinner
2024-02-15 9:53 ` John Garry
2024-02-13 17:50 ` Darrick J. Wong
2024-02-14 12:13 ` John Garry
2024-01-24 14:26 ` [PATCH 6/6] fs: xfs: Set FMODE_CAN_ATOMIC_WRITE for FS_XFLAG_ATOMICWRITES set John Garry
2024-02-02 18:06 ` Darrick J. Wong
2024-02-05 10:26 ` John Garry
2024-02-13 17:59 ` Darrick J. Wong
2024-02-14 12:36 ` John Garry
2024-02-21 17:00 ` Darrick J. Wong
2024-02-21 17:38 ` John Garry
2024-02-24 4:18 ` Darrick J. Wong
2024-02-09 7:14 ` [PATCH 0/6] block atomic writes for XFS Ojaswin Mujoo
2024-02-09 9:22 ` John Garry
2024-02-12 12:06 ` Ojaswin Mujoo
2024-02-13 7:22 ` Christoph Hellwig
2024-02-13 17:55 ` Darrick J. Wong
2024-02-14 7:45 ` Christoph Hellwig
2024-02-21 16:56 ` Darrick J. Wong
2024-02-23 6:57 ` Christoph Hellwig
2024-02-13 23:50 ` Dave Chinner
2024-02-14 7:38 ` Christoph Hellwig
2024-02-13 7:45 ` Ritesh Harjani
2024-02-13 8:41 ` John Garry
2024-02-13 9:10 ` Ritesh Harjani
2024-02-13 22:49 ` Dave Chinner
2024-02-14 10:10 ` John Garry
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=20240124142645.9334-4-john.g.garry@oracle.com \
--to=john.g.garry@oracle.com \
--cc=brauner@kernel.org \
--cc=chandan.babu@oracle.com \
--cc=dchinner@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jbongio@google.com \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-xfs@vger.kernel.org \
--cc=martin.petersen@oracle.com \
--cc=ojaswin@linux.ibm.com \
--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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).