Source kernel commit:
2167eaabe2fadde24cb8f1dafbec64da1d2ed2f5
Zone file systems reuse the basic RT group enabled XFS file system
structure to support a mode where each RT group is always written from
start to end and then reset for reuse (after moving out any remaining
data). There are few minor but important changes, which are indicated
by a new incompat flag:
1) there are no bitmap and summary inodes, thus the
/rtgroups/{rgno}.{bitmap,summary} metadir files do not exist and the
sb_rbmblocks superblock field must be cleared to zero.
2) there is a new superblock field that specifies the start of an
internal RT section. This allows supporting SMR HDDs that have random
writable space at the beginning which is used for the XFS data device
(which really is the metadata device for this configuration), directly
followed by a RT device on the same block device. While something
similar could be achieved using dm-linear just having a single device
directly consumed by XFS makes handling the file systems a lot easier.
3) Another superblock field that tracks the amount of reserved space (or
overprovisioning) that is never used for user capacity, but allows GC
to run more smoothly.
4) an overlay of the cowextsize field for the rtrmap inode so that we
can persistently track the total amount of rtblocks currently used in
a RT group. There is no data structure other than the rmap that
tracks used space in an RT group, and this counter is used to decide
when a RT group has been entirely emptied, and to select one that
is relatively empty if garbage collection needs to be performed.
While this counter could be tracked entirely in memory and rebuilt
from the rmap at mount time, that would lead to very long mount times
with the large number of RT groups implied by the number of hardware
zones especially on SMR hard drives with 256MB zone sizes.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christoph Hellwig <hch@lst.de>
xfs_rfsblock_t i_nblocks; /* # of direct & btree blocks */
prid_t i_projid; /* owner's project id */
xfs_extlen_t i_extsize; /* basic/minimum extent size */
- /* cowextsize is only used for v3 inodes, flushiter for v1/2 */
+ /*
+ * i_used_blocks is used for zoned rtrmap inodes,
+ * i_cowextsize is used for other v3 inodes,
+ * i_flushiter for v1/2 inodes
+ */
union {
+ uint32_t i_used_blocks; /* used blocks in RTG */
xfs_extlen_t i_cowextsize; /* basic cow extent size */
uint16_t i_flushiter; /* incremented on flush */
};
}
#define XFS_IS_REALTIME_INODE(ip) ((ip)->i_diflags & XFS_DIFLAG_REALTIME)
+static inline bool xfs_is_zoned_inode(struct xfs_inode *ip)
+{
+ return xfs_has_zoned(ip->i_mount) && XFS_IS_REALTIME_INODE(ip);
+}
+
/* inode link counts */
static inline void set_nlink(struct inode *inode, uint32_t nlink)
{
#define XFS_FEAT_NREXT64 (1ULL << 26) /* large extent counters */
#define XFS_FEAT_EXCHANGE_RANGE (1ULL << 27) /* exchange range */
#define XFS_FEAT_METADIR (1ULL << 28) /* metadata directory tree */
+#define XFS_FEAT_ZONED (1ULL << 29) /* zoned RT device */
#define __XFS_HAS_FEAT(name, NAME) \
static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \
__XFS_HAS_FEAT(large_extent_counts, NREXT64)
__XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
__XFS_HAS_FEAT(metadir, METADIR)
-
+__XFS_HAS_FEAT(zoned, ZONED)
static inline bool xfs_has_rtgroups(const struct xfs_mount *mp)
{
static inline bool xfs_has_rtsb(const struct xfs_mount *mp)
{
/* all rtgroups filesystems with an rt section have an rtsb */
- return xfs_has_rtgroups(mp) && xfs_has_realtime(mp);
+ return xfs_has_rtgroups(mp) &&
+ xfs_has_realtime(mp) &&
+ !xfs_has_zoned(mp);
}
static inline bool xfs_has_rtrmapbt(const struct xfs_mount *mp)
xfs_has_reflink(mp);
}
+static inline bool xfs_has_nonzoned(const struct xfs_mount *mp)
+{
+ return !xfs_has_zoned(mp);
+}
+
/* Kernel mount features that we don't support */
#define __XFS_UNSUPP_FEAT(name) \
static inline bool xfs_has_ ## name (const struct xfs_mount *mp) \
xfs_rgnumber_t sb_rgcount; /* number of realtime groups */
xfs_rtxlen_t sb_rgextents; /* size of a realtime group in rtx */
-
uint8_t sb_rgblklog; /* rt group number shift */
uint8_t sb_pad[7]; /* zeroes */
+ xfs_rfsblock_t sb_rtstart; /* start of internal RT section (FSB) */
+ xfs_filblks_t sb_rtreserved; /* reserved (zoned) RT blocks */
/* must be padded to 64 bit alignment */
} xfs_sb_t;
__be64 sb_metadirino; /* metadata directory tree root */
__be32 sb_rgcount; /* # of realtime groups */
__be32 sb_rgextents; /* size of rtgroup in rtx */
-
__u8 sb_rgblklog; /* rt group number shift */
__u8 sb_pad[7]; /* zeroes */
+ __be64 sb_rtstart; /* start of internal RT section (FSB) */
+ __be64 sb_rtreserved; /* reserved (zoned) RT blocks */
/*
* The size of this structure must be padded to 64 bit alignment.
#define XFS_SB_FEAT_INCOMPAT_EXCHRANGE (1 << 6) /* exchangerange supported */
#define XFS_SB_FEAT_INCOMPAT_PARENT (1 << 7) /* parent pointers */
#define XFS_SB_FEAT_INCOMPAT_METADIR (1 << 8) /* metadata dir tree */
+#define XFS_SB_FEAT_INCOMPAT_ZONED (1 << 9) /* zoned RT allocator */
+
#define XFS_SB_FEAT_INCOMPAT_ALL \
(XFS_SB_FEAT_INCOMPAT_FTYPE | \
XFS_SB_FEAT_INCOMPAT_SPINODES | \
__be64 di_changecount; /* number of attribute changes */
__be64 di_lsn; /* flush sequence */
__be64 di_flags2; /* more random flags */
- __be32 di_cowextsize; /* basic cow extent size for file */
+ union {
+ /* basic cow extent size for (regular) file */
+ __be32 di_cowextsize;
+ /* used blocks in RTG for (zoned) rtrmap inode */
+ __be32 di_used_blocks;
+ };
__u8 di_pad2[12]; /* more padding for future expansion */
/* fields only written to during inode creation */
be64_to_cpu(from->di_changecount));
ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
ip->i_diflags2 = be64_to_cpu(from->di_flags2);
+ /* also covers the di_used_blocks union arm: */
ip->i_cowextsize = be32_to_cpu(from->di_cowextsize);
+ BUILD_BUG_ON(sizeof(from->di_cowextsize) !=
+ sizeof(from->di_used_blocks));
}
error = xfs_iformat_data_fork(ip, from);
to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime);
to->di_flags2 = cpu_to_be64(ip->i_diflags2);
+ /* also covers the di_used_blocks union arm: */
to->di_cowextsize = cpu_to_be32(ip->i_cowextsize);
to->di_ino = cpu_to_be64(ip->i_ino);
to->di_lsn = cpu_to_be64(lsn);
!xfs_has_rtreflink(mp))
return __this_address;
- /* COW extent size hint validation */
- fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
- mode, flags, flags2);
- if (fa)
- return fa;
+ if (xfs_has_zoned(mp) &&
+ dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) {
+ if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents)
+ return __this_address;
+ } else {
+ /* COW extent size hint validation */
+ fa = xfs_inode_validate_cowextsize(mp,
+ be32_to_cpu(dip->di_cowextsize),
+ mode, flags, flags2);
+ if (fa)
+ return fa;
+ }
/* bigtime iflag can only happen on bigtime filesystems */
if (xfs_dinode_has_bigtime(dip) &&
if (xfs_has_v3inodes(mp)) {
inode_set_iversion(inode, 1);
+ /* also covers the di_used_blocks union arm: */
ip->i_cowextsize = 0;
times |= XFS_ICHGTIME_CREATE;
}
xfs_lsn_t di_lsn;
uint64_t di_flags2; /* more random flags */
- uint32_t di_cowextsize; /* basic cow extent size for file */
+ union {
+ /* basic cow extent size for (regular) file */
+ uint32_t di_cowextsize;
+ /* used blocks in RTG for (zoned) rtrmap inode */
+ uint32_t di_used_blocks;
+ };
uint8_t di_pad2[12]; /* more padding for future expansion */
/* fields only written to during inode creation */
16299260424LL);
/* superblock field checks we got from xfs/122 */
- XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 288);
- XFS_CHECK_STRUCT_SIZE(struct xfs_sb, 288);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_dsb, 304);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_sb, 304);
XFS_CHECK_SB_OFFSET(sb_magicnum, 0);
XFS_CHECK_SB_OFFSET(sb_blocksize, 4);
XFS_CHECK_SB_OFFSET(sb_dblocks, 8);
XFS_CHECK_SB_OFFSET(sb_rgextents, 276);
XFS_CHECK_SB_OFFSET(sb_rgblklog, 280);
XFS_CHECK_SB_OFFSET(sb_pad, 281);
+ XFS_CHECK_SB_OFFSET(sb_rtstart, 288);
+ XFS_CHECK_SB_OFFSET(sb_rtreserved, 296);
}
#endif /* __XFS_ONDISK_H */
xfs_extlen_t mod;
int error;
+ ASSERT(!xfs_has_zoned(mp));
ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
mod = xfs_blen_to_rtxoff(mp, rtlen);
end = min(end, rtg->rtg_extents - 1);
+ if (xfs_has_zoned(mp))
+ return -EINVAL;
+
/* Iterate the bitmap, looking for discrepancies. */
while (start <= end) {
struct xfs_rtalloc_rec rec;
struct xfs_mount *mp,
xfs_rtbxlen_t rtextents)
{
+ if (xfs_has_zoned(mp))
+ return 0;
return howmany_64(rtextents, xfs_rtbitmap_rtx_per_rbmblock(mp));
}
xfs_rtbxlen_t rextents = xfs_rtbitmap_bitcount(mp);
unsigned long long rsumwords;
+ if (xfs_has_zoned(mp)) {
+ *rsumlevels = 0;
+ return 0;
+ }
+
*rsumlevels = xfs_compute_rextslog(rextents) + 1;
rsumwords = xfs_rtbitmap_blockcount_len(mp, rextents) * (*rsumlevels);
return howmany_64(rsumwords, mp->m_blockwsize);
ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
!(rtglock_flags & XFS_RTGLOCK_BITMAP));
- if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
- /*
- * Lock both realtime free space metadata inodes for a freespace
- * update.
- */
- xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
- xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL);
- } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
- xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+ if (!xfs_has_zoned(rtg_mount(rtg))) {
+ if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+ /*
+ * Lock both realtime free space metadata inodes for a
+ * freespace update.
+ */
+ xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
+ xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL);
+ } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+ xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+ }
}
if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL);
- if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
- xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL);
- xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
- } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
- xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+ if (!xfs_has_zoned(rtg_mount(rtg))) {
+ if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+ xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL);
+ xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
+ } else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+ xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+ }
}
}
ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
- if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+ if (!xfs_has_zoned(rtg_mount(rtg)) &&
+ (rtglock_flags & XFS_RTGLOCK_BITMAP)) {
xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL);
xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL);
}
.sick = XFS_SICK_RG_BITMAP,
.fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) |
(1U << XFS_DINODE_FMT_BTREE),
+ .enabled = xfs_has_nonzoned,
.create = xfs_rtbitmap_create,
},
[XFS_RTGI_SUMMARY] = {
.sick = XFS_SICK_RG_SUMMARY,
.fmt_mask = (1U << XFS_DINODE_FMT_EXTENTS) |
(1U << XFS_DINODE_FMT_BTREE),
+ .enabled = xfs_has_nonzoned,
.create = xfs_rtsummary_create,
},
[XFS_RTGI_RMAP] = {
#include "xfs_rtgroup.h"
#include "xfs_rtrmap_btree.h"
#include "xfs_rtrefcount_btree.h"
+#include "xfs_rtbitmap.h"
/*
* Physical superblock buffer manipulations. Shared with libxfs in userspace.
features |= XFS_FEAT_PARENT;
if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
features |= XFS_FEAT_METADIR;
+ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)
+ features |= XFS_FEAT_ZONED;
return features;
}
xfs_expected_rbmblocks(
struct xfs_sb *sbp)
{
+ if (xfs_sb_is_v5(sbp) &&
+ (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED))
+ return 0;
return howmany_64(xfs_extents_per_rbm(sbp),
NBBY * xfs_rtbmblock_size(sbp));
}
xfs_validate_rt_geometry(
struct xfs_sb *sbp)
{
- if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
- sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)
- return false;
+ if (xfs_sb_is_v5(sbp) &&
+ (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) {
+ if (sbp->sb_rextsize != 1)
+ return false;
+ } else {
+ if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
+ sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)
+ return false;
+ }
if (sbp->sb_rblocks == 0) {
if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 ||
return 0;
}
+static int
+xfs_validate_sb_zoned(
+ struct xfs_mount *mp,
+ struct xfs_sb *sbp)
+{
+ if (sbp->sb_frextents != 0) {
+ xfs_warn(mp,
+"sb_frextents must be zero for zoned file systems.");
+ return -EINVAL;
+ }
+
+ if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) {
+ xfs_warn(mp,
+"sb_rtstart (%lld) overlaps sb_dblocks (%lld).",
+ sbp->sb_rtstart, sbp->sb_dblocks);
+ return -EINVAL;
+ }
+
+ if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) {
+ xfs_warn(mp,
+"sb_rtreserved (%lld) larger than sb_rblocks (%lld).",
+ sbp->sb_rtreserved, sbp->sb_rblocks);
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
/* Check the validity of the SB. */
STATIC int
xfs_validate_sb_common(
if (error)
return error;
}
+ if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+ error = xfs_validate_sb_zoned(mp, sbp);
+ if (error)
+ return error;
+ }
} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
xfs_notice(mp,
to->sb_rgcount = 1;
to->sb_rgextents = 0;
}
+
+ if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+ to->sb_rtstart = be64_to_cpu(from->sb_rtstart);
+ to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved);
+ } else {
+ to->sb_rtstart = 0;
+ to->sb_rtreserved = 0;
+ }
}
void
to->sb_rbmino = cpu_to_be64(0);
to->sb_rsumino = cpu_to_be64(0);
}
+
+ if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+ to->sb_rtstart = cpu_to_be64(from->sb_rtstart);
+ to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved);
+ }
}
/*