@@ -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 | \
@@ -1094,16 +1095,19 @@ 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)
{
@@ -644,6 +644,15 @@ xfs_dinode_verify(
!xfs_has_bigtime(mp))
return __this_address;
+ if (flags2 & XFS_DIFLAG2_FORCEALIGN) {
+ fa = xfs_inode_validate_forcealign(mp,
+ be32_to_cpu(dip->di_extsize),
+ be32_to_cpu(dip->di_cowextsize),
+ mode, flags, flags2);
+ if (fa)
+ return fa;
+ }
+
return NULL;
}
@@ -811,3 +820,47 @@ xfs_inode_validate_cowextsize(
return NULL;
}
+
+/* Validate the forcealign inode flag */
+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)
+{
+ /* 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;
+
+ /* We require EXTSIZE or EXTSZINHERIT */
+ if (!(flags & (XFS_DIFLAG_EXTSIZE | XFS_DIFLAG_EXTSZINHERIT)))
+ return __this_address;
+
+ /* We require a non-zero extsize */
+ if (!extsize)
+ return __this_address;
+
+ /* Reflink'ed disallowed */
+ if (flags2 & XFS_DIFLAG2_REFLINK)
+ return __this_address;
+
+ /* COW extsize disallowed */
+ if (flags2 & XFS_DIFLAG2_COWEXTSIZE)
+ return __this_address;
+
+ if (cowextsize)
+ return __this_address;
+
+ /* A RT device with sb_rextsize=1 could make use of forcealign */
+ if (flags & XFS_DIFLAG_REALTIME && mp->m_sb.sb_rextsize != 1)
+ return __this_address;
+
+ return NULL;
+}
@@ -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,
+ uint32_t extsize, uint32_t cowextsize, uint16_t mode,
+ uint16_t flags, uint64_t flags2);
static inline uint64_t xfs_inode_encode_bigtime(struct timespec64 tv)
{
@@ -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_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)
@@ -608,6 +608,8 @@ 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))
@@ -737,6 +739,8 @@ 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,
@@ -745,6 +749,15 @@ 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,
+ ip->i_extsize, ip->i_cowextsize,
+ VFS_I(ip)->i_mode, ip->i_diflags,
+ ip->i_diflags2);
+ if (failaddr)
+ ip->i_diflags2 &= ~XFS_DIFLAG2_FORCEALIGN;
+ }
}
/*
@@ -301,6 +301,16 @@ static inline bool xfs_inode_has_cow_data(struct xfs_inode *ip)
return ip->i_cowfp && ip->i_cowfp->if_bytes;
}
+static inline bool xfs_is_always_cow_inode(struct xfs_inode *ip)
+{
+ return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount);
+}
+
+static inline bool xfs_is_cow_inode(struct xfs_inode *ip)
+{
+ return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip);
+}
+
static inline bool xfs_inode_has_bigtime(struct xfs_inode *ip)
{
return ip->i_diflags2 & XFS_DIFLAG2_BIGTIME;
@@ -313,7 +323,15 @@ static inline bool xfs_inode_has_large_extent_counts(struct xfs_inode *ip)
static inline bool xfs_inode_has_forcealign(struct xfs_inode *ip)
{
- return false;
+ if (!(ip->i_diflags & XFS_DIFLAG_EXTSIZE))
+ return false;
+ if (ip->i_extsize <= 1)
+ return false;
+ if (xfs_is_cow_inode(ip))
+ return false;
+ if (ip->i_diflags & XFS_DIFLAG_REALTIME)
+ return false;
+ return ip->i_diflags2 & XFS_DIFLAG2_FORCEALIGN;
}
/*
@@ -525,10 +525,48 @@ 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;
}
+/*
+ * Forcealign requires a non-zero extent size hint and a zero cow
+ * extent size hint. Don't allow set for RT files yet.
+ */
+static int
+xfs_ioctl_setattr_forcealign(
+ struct xfs_inode *ip,
+ struct fileattr *fa)
+{
+ struct xfs_mount *mp = ip->i_mount;
+
+ if (!xfs_has_forcealign(mp))
+ return -EINVAL;
+
+ if (xfs_is_reflink_inode(ip))
+ return -EINVAL;
+
+ if (!(fa->fsx_xflags & (FS_XFLAG_EXTSIZE |
+ FS_XFLAG_EXTSZINHERIT)))
+ return -EINVAL;
+
+ if (fa->fsx_xflags & FS_XFLAG_COWEXTSIZE)
+ return -EINVAL;
+
+ if (!fa->fsx_extsize)
+ return -EINVAL;
+
+ if (fa->fsx_cowextsize)
+ return -EINVAL;
+
+ if (fa->fsx_xflags & FS_XFLAG_REALTIME)
+ return -EINVAL;
+
+ return 0;
+}
+
static int
xfs_ioctl_setattr_xflags(
struct xfs_trans *tp,
@@ -537,10 +575,12 @@ xfs_ioctl_setattr_xflags(
{
struct xfs_mount *mp = ip->i_mount;
bool rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
+ bool forcealign = fa->fsx_xflags & FS_XFLAG_FORCEALIGN;
uint64_t i_flags2;
- if (rtflag != XFS_IS_REALTIME_INODE(ip)) {
- /* Can't change realtime flag if any extents are allocated. */
+ /* Can't change RT or forcealign flags if any extents are allocated. */
+ if (rtflag != XFS_IS_REALTIME_INODE(ip) ||
+ forcealign != xfs_inode_has_forcealign(ip)) {
if (ip->i_df.if_nextents || ip->i_delayed_blks)
return -EINVAL;
}
@@ -561,6 +601,9 @@ xfs_ioctl_setattr_xflags(
if (i_flags2 && !xfs_has_v3inodes(mp))
return -EINVAL;
+ if (forcealign && (xfs_ioctl_setattr_forcealign(ip, fa) < 0))
+ return -EINVAL;
+
ip->i_diflags = xfs_flags2diflags(ip, fa->fsx_xflags);
ip->i_diflags2 = i_flags2;
@@ -299,6 +299,7 @@ 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_FORCEALIGN (1ULL << 28) /* aligned file data extents */
/* Mount features */
#define XFS_FEAT_NOATTR2 (1ULL << 48) /* disable attr2 creation */
@@ -385,6 +386,7 @@ __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(forcealign, FORCEALIGN)
/*
* Mount features
@@ -6,16 +6,6 @@
#ifndef __XFS_REFLINK_H
#define __XFS_REFLINK_H 1
-static inline bool xfs_is_always_cow_inode(struct xfs_inode *ip)
-{
- return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount);
-}
-
-static inline bool xfs_is_cow_inode(struct xfs_inode *ip)
-{
- return xfs_is_reflink_inode(ip) || xfs_is_always_cow_inode(ip);
-}
-
extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
struct xfs_bmbt_irec *irec, bool *shared);
int xfs_bmap_trim_cow(struct xfs_inode *ip, struct xfs_bmbt_irec *imap,
@@ -1721,6 +1721,10 @@ 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,
@@ -158,6 +158,8 @@ 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