Message-Id: <20240607143919.2622319-20-john.g.garry@oracle.com>
Date: Fri,  7 Jun 2024 14:39:16 +0000
From: John Garry <john.g.garry@...cle.com>
To: axboe@...nel.dk, tytso@....edu, dchinner@...hat.com,
        viro@...iv.linux.org.uk, brauner@...nel.org, djwong@...nel.org,
        jack@...e.com, chandan.babu@...cle.com, hch@....de
Cc: linux-block@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-btrfs@...r.kernel.org, linux-erofs@...ts.ozlabs.org,
        linux-ext4@...r.kernel.org, linux-f2fs-devel@...ts.sourceforge.net,
        linux-fsdevel@...r.kernel.org, gfs2@...ts.linux.dev,
        linux-xfs@...r.kernel.org, catherine.hoang@...cle.com,
        ritesh.list@...il.com, mcgrof@...nel.org,
        mikulas@...ax.karlin.mff.cuni.cz, agruenba@...hat.com,
        miklos@...redi.hu, martin.petersen@...cle.com,
        John Garry <john.g.garry@...cle.com>
Subject: [PATCH v4 19/22] xfs: Support FS_XFLAG_ATOMICWRITES for forcealign

Add initial support for FS_XFLAG_ATOMICWRITES for forcealign enabled.

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 also guarantees extent alignment, but we are basing support initially
on forcealign, which is not supported for rtvol yet.

Signed-off-by: John Garry <john.g.garry@...cle.com>
---
 fs/xfs/libxfs/xfs_format.h    | 11 ++++++--
 fs/xfs/libxfs/xfs_inode_buf.c | 52 +++++++++++++++++++++++++++++++++++
 fs/xfs/libxfs/xfs_inode_buf.h |  2 ++
 fs/xfs/libxfs/xfs_sb.c        |  2 ++
 fs/xfs/xfs_buf.c              | 15 +++++++++-
 fs/xfs/xfs_buf.h              |  4 ++-
 fs/xfs/xfs_buf_mem.c          |  2 +-
 fs/xfs/xfs_inode.c            |  9 ++++++
 fs/xfs/xfs_inode.h            |  5 ++++
 fs/xfs/xfs_ioctl.c            | 36 ++++++++++++++++++++++++
 fs/xfs/xfs_mount.h            |  2 ++
 fs/xfs/xfs_super.c            |  4 +++
 12 files changed, 139 insertions(+), 5 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 42e1f80206ab..e20880b6aff7 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -354,12 +354,16 @@ xfs_sb_has_compat_feature(
 #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_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_FORCEALIGN)
+		 XFS_SB_FEAT_RO_COMPAT_FORCEALIGN | \
+		 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(
@@ -1098,6 +1102,7 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #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_ATOMICWRITES_BIT 6
 
 #define XFS_DIFLAG2_DAX		(1 << XFS_DIFLAG2_DAX_BIT)
 #define XFS_DIFLAG2_REFLINK     (1 << XFS_DIFLAG2_REFLINK_BIT)
@@ -1105,10 +1110,12 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
 #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_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_FORCEALIGN)
+	 XFS_DIFLAG2_BIGTIME | XFS_DIFLAG2_NREXT64 | XFS_DIFLAG2_FORCEALIGN | \
+	 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 b2c5f466c1a9..046e72481b60 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -178,7 +178,10 @@ xfs_inode_from_disk(
 	struct xfs_inode	*ip,
 	struct xfs_dinode	*from)
 {
+	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
 	struct inode		*inode = VFS_I(ip);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_sb		*sbp = &mp->m_sb;
 	int			error;
 	xfs_failaddr_t		fa;
 
@@ -261,6 +264,13 @@ xfs_inode_from_disk(
 	}
 	if (xfs_is_reflink_inode(ip))
 		xfs_ifork_init_cow(ip);
+
+	if (xfs_inode_has_atomicwrites(ip)) {
+		if (sbp->sb_blocksize < target->bt_bdev_awu_min ||
+		    sbp->sb_blocksize * ip->i_extsize > target->bt_bdev_awu_max)
+			ip->i_diflags2 &= ~XFS_DIFLAG2_ATOMICWRITES;
+	}
+
 	return 0;
 
 out_destroy_data_fork:
@@ -653,6 +663,13 @@ xfs_dinode_verify(
 			return fa;
 	}
 
+	if (flags2 & XFS_DIFLAG2_ATOMICWRITES) {
+		fa = xfs_inode_validate_atomicwrites(mp,
+			be32_to_cpu(dip->di_extsize), flags2);
+		if (fa)
+			return fa;
+	}
+
 	return NULL;
 }
 
@@ -864,3 +881,38 @@ xfs_inode_validate_forcealign(
 
 	return NULL;
 }
+
+xfs_failaddr_t
+xfs_inode_validate_atomicwrites(
+	struct xfs_mount	*mp,
+	uint32_t		extsize,
+	uint64_t		flags2)
+{
+	/* superblock rocompat feature flag */
+	if (!xfs_has_atomicwrites(mp))
+		return __this_address;
+
+	/*
+	 * forcealign is required, so rely on sanity checks in
+	 * xfs_inode_validate_forcealign()
+	 */
+	if (!(flags2 & XFS_DIFLAG2_FORCEALIGN))
+		return __this_address;
+
+	/* extsize must be a power-of-2 */
+	if (!is_power_of_2(extsize))
+		return __this_address;
+
+	/* Required to guarnatee data block alignment */
+	if (mp->m_sb.sb_agblocks % extsize)
+		return __this_address;
+
+	/* Requires stripe unit+width be a multiple of extsize */
+	if (mp->m_dalign && (mp->m_dalign % extsize))
+		return __this_address;
+
+	if (mp->m_swidth && (mp->m_swidth % extsize))
+		return __this_address;
+
+	return NULL;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index b8b65287b037..c7613b1a05f2 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -36,6 +36,8 @@ xfs_failaddr_t xfs_inode_validate_cowextsize(struct xfs_mount *mp,
 xfs_failaddr_t xfs_inode_validate_forcealign(struct xfs_mount *mp,
 		uint32_t extsize, uint32_t cowextsize, uint16_t mode,
 		uint16_t flags, uint64_t flags2);
+xfs_failaddr_t xfs_inode_validate_atomicwrites(struct xfs_mount *mp,
+		uint32_t extsize, uint64_t flags2);
 
 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 515f5dd23b6d..aee285899ffc 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -166,6 +166,8 @@ xfs_sb_version_to_features(
 		features |= XFS_FEAT_INOBTCNT;
 	if (sbp->sb_features_ro_compat & XFS_SB_FEAT_RO_COMPAT_FORCEALIGN)
 		features |= XFS_FEAT_FORCEALIGN;
+	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..44bee3e2b2bb 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -2060,6 +2060,8 @@ int
 xfs_init_buftarg(
 	struct xfs_buftarg		*btp,
 	size_t				logical_sectorsize,
+	unsigned int			awu_min,
+	unsigned int			awu_max,
 	const char			*descr)
 {
 	/* Set up device logical sector size mask */
@@ -2086,6 +2088,9 @@ xfs_init_buftarg(
 	btp->bt_shrinker->scan_objects = xfs_buftarg_shrink_scan;
 	btp->bt_shrinker->private_data = btp;
 	shrinker_register(btp->bt_shrinker);
+
+	btp->bt_bdev_awu_min = awu_min;
+	btp->bt_bdev_awu_max = awu_max;
 	return 0;
 
 out_destroy_io_count:
@@ -2102,6 +2107,7 @@ xfs_alloc_buftarg(
 {
 	struct xfs_buftarg	*btp;
 	const struct dax_holder_operations *ops = NULL;
+	unsigned int awu_min = 0, awu_max = 0;
 
 #if defined(CONFIG_FS_DAX) && defined(CONFIG_MEMORY_FAILURE)
 	ops = &xfs_dax_holder_operations;
@@ -2115,6 +2121,13 @@ 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);
+
+		awu_min = queue_atomic_write_unit_min_bytes(q);
+		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.
@@ -2122,7 +2135,7 @@ xfs_alloc_buftarg(
 	if (xfs_setsize_buftarg(btp, bdev_logical_block_size(btp->bt_bdev)))
 		goto error_free;
 	if (xfs_init_buftarg(btp, bdev_logical_block_size(btp->bt_bdev),
-			mp->m_super->s_id))
+			awu_min, awu_max, mp->m_super->s_id))
 		goto error_free;
 
 	return btp;
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index b1580644501f..3bcd8137d739 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -124,6 +124,8 @@ struct xfs_buftarg {
 	struct percpu_counter	bt_io_count;
 	struct ratelimit_state	bt_ioerror_rl;
 
+	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[];
 };
@@ -393,7 +395,7 @@ bool xfs_verify_magic16(struct xfs_buf *bp, __be16 dmagic);
 
 /* for xfs_buf_mem.c only: */
 int xfs_init_buftarg(struct xfs_buftarg *btp, size_t logical_sectorsize,
-		const char *descr);
+		unsigned int awu_min, unsigned int awu_max, const char *descr);
 void xfs_destroy_buftarg(struct xfs_buftarg *btp);
 
 #endif	/* __XFS_BUF_H__ */
diff --git a/fs/xfs/xfs_buf_mem.c b/fs/xfs/xfs_buf_mem.c
index 9bb2d24de709..af48a8da2f0f 100644
--- a/fs/xfs/xfs_buf_mem.c
+++ b/fs/xfs/xfs_buf_mem.c
@@ -93,7 +93,7 @@ xmbuf_alloc(
 	btp->bt_meta_sectorsize = XMBUF_BLOCKSIZE;
 	btp->bt_meta_sectormask = XMBUF_BLOCKSIZE - 1;
 
-	error = xfs_init_buftarg(btp, XMBUF_BLOCKSIZE, descr);
+	error = xfs_init_buftarg(btp, XMBUF_BLOCKSIZE, 0, 0, descr);
 	if (error)
 		goto out_bcache;
 
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9c0ae5c3682e..e8d7ad4e6d38 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -610,6 +610,8 @@ xfs_ip2xflags(
 			flags |= FS_XFLAG_COWEXTSIZE;
 		if (ip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN)
 			flags |= FS_XFLAG_FORCEALIGN;
+		if (ip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES)
+			flags |= FS_XFLAG_ATOMICWRITES;
 	}
 
 	if (xfs_inode_has_attr_fork(ip))
@@ -758,6 +760,13 @@ xfs_inode_inherit_flags2(
 		if (failaddr)
 			ip->i_diflags2 &= ~XFS_DIFLAG2_FORCEALIGN;
 	}
+
+	if (ip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES) {
+		failaddr = xfs_inode_validate_atomicwrites(ip->i_mount,
+				ip->i_extsize, ip->i_diflags2);
+		if (failaddr)
+			ip->i_diflags2 &= ~XFS_DIFLAG2_ATOMICWRITES;
+	}
 }
 
 /*
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 7005ea29bf11..1e8a8778ce0b 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -334,6 +334,11 @@ static inline bool xfs_inode_has_forcealign(struct xfs_inode *ip)
 	return ip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN;
 }
 
+static inline bool xfs_inode_has_atomicwrites(struct xfs_inode *ip)
+{
+	return ip->i_diflags2 & XFS_DIFLAG2_ATOMICWRITES;
+}
+
 /*
  * Decide if this file is a realtime file whose data allocation unit is larger
  * than a single filesystem block.
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index 5eff8fd9fa3e..2877553b6151 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -527,6 +527,8 @@ xfs_flags2diflags2(
 		di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 	if (xflags & FS_XFLAG_FORCEALIGN)
 		di_flags2 |= XFS_DIFLAG2_FORCEALIGN;
+	if (xflags & FS_XFLAG_ATOMICWRITES)
+		di_flags2 |= XFS_DIFLAG2_ATOMICWRITES;
 
 	return di_flags2;
 }
@@ -567,15 +569,45 @@ xfs_ioctl_setattr_forcealign(
 	return 0;
 }
 
+static int
+xfs_ioctl_setattr_atomicwrites(
+	struct xfs_inode	*ip,
+	struct fileattr		*fa,
+	struct xfs_buftarg	*target)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_sb		*sbp = &mp->m_sb;
+
+	if (!xfs_has_atomicwrites(mp))
+		return -EINVAL;
+
+	if (!(fa->fsx_xflags & FS_XFLAG_FORCEALIGN))
+		return -EINVAL;
+
+	if (!is_power_of_2(fa->fsx_extsize))
+		return -EINVAL;
+
+	/* bdev can actually support atomic writes range required */
+	if (target->bt_bdev_awu_min > sbp->sb_blocksize)
+		return -EINVAL;
+
+	if (target->bt_bdev_awu_max < fa->fsx_extsize)
+		return -EINVAL;
+
+	return 0;
+}
+
 static int
 xfs_ioctl_setattr_xflags(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
 	struct fileattr		*fa)
 {
+	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
 	bool			forcealign = fa->fsx_xflags & FS_XFLAG_FORCEALIGN;
+	bool			atomicwrites = fa->fsx_xflags & FS_XFLAG_ATOMICWRITES;
 	uint64_t		i_flags2;
 
 	/* Can't change RT or forcealign flags if any extents are allocated. */
@@ -604,6 +636,10 @@ xfs_ioctl_setattr_xflags(
 	if (forcealign && (xfs_ioctl_setattr_forcealign(ip, fa) < 0))
 		return -EINVAL;
 
+	if (atomicwrites &&
+	    (xfs_ioctl_setattr_atomicwrites(ip, fa, target) < 0))
+		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 30228fea908d..0c5a3ae3cdaf 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -300,6 +300,7 @@ typedef struct xfs_mount {
 #define XFS_FEAT_NREXT64	(1ULL << 26)	/* large extent counters */
 #define XFS_FEAT_EXCHANGE_RANGE	(1ULL << 27)	/* exchange range */
 #define XFS_FEAT_FORCEALIGN	(1ULL << 28)	/* aligned file data extents */
+#define XFS_FEAT_ATOMICWRITES	(1ULL << 29)	/* atomic writes support */
 
 /* Mount features */
 #define XFS_FEAT_NOATTR2	(1ULL << 48)	/* disable attr2 creation */
@@ -387,6 +388,7 @@ __XFS_HAS_V4_FEAT(v3inodes, V3INODES)
 __XFS_HAS_V4_FEAT(crc, CRC)
 __XFS_HAS_V4_FEAT(pquotino, PQUOTINO)
 __XFS_HAS_FEAT(forcealign, FORCEALIGN)
+__XFS_HAS_FEAT(atomicwrites, ATOMICWRITES)
 
 /*
  * Mount features
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 852bbfb21506..85799bd12e92 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -1725,6 +1725,10 @@ xfs_fs_fill_super(
 		xfs_warn(mp,
 "EXPERIMENTAL forced data extent alignment feature in use. Use at your own risk!");
 
+	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,
-- 
2.31.1

Powered by blists - more mailing lists