Merge tag 'xfs-zoned-allocator-2025-03-03' of git://git.infradead.org/users/hch/xfs into xfs-6.15-zoned_devices

xfs: add support for zoned devices

Add support for the new zoned space allocator and thus for zoned devices:

    https://zonedstorage.io/docs/introduction/zoned-storage

to XFS. This has been developed for and tested on both SMR hard drives,
which are the oldest and most common class of zoned devices:

   https://zonedstorage.io/docs/introduction/smr

and ZNS SSDs:

   https://zonedstorage.io/docs/introduction/zns

It has not been tested with zoned UFS devices, as their current capacity
points and performance characteristics aren't too interesting for XFS
use cases (but never say never).

Sequential write only zones are only supported for data using a new
allocator for the RT device, which maps each zone to a rtgroup which
is written sequentially.  All metadata and (for now) the log require
using randomly writable space. This means a realtime device is required
to support zoned storage, but for the common case of SMR hard drives
that contain random writable zones and sequential write required zones
on the same block device, the concept of an internal RT device is added
which means using XFS on a SMR HDD is as simple as:

$ mkfs.xfs /dev/sda
$ mount /dev/sda /mnt

When using NVMe ZNS SSDs that do not support conventional zones, the
traditional multi-device RT configuration is required.  E.g. for an
SSD with a conventional namespace 1 and a zoned namespace 2:

$ mkfs.xfs /dev/nvme0n1 -o rtdev=/dev/nvme0n2
$ mount -o rtdev=/dev/nvme0n2 /dev/nvme0n1 /mnt

The zoned allocator can also be used on conventional block devices, or
on conventional zones (e.g. when using an SMR HDD as the external RT
device).  For example using zoned XFS on normal SSDs shows very nice
performance advantages and write amplification reduction for intelligent
workloads like RocksDB.

Some work is still in progress or planned, but should not affect the
integration with the rest of XFS or the on-disk format:

 - support for quotas
 - support for reflinks

Note that the I/O path already supports reflink, but garbage collection
isn't refcount aware yet and would unshare shared blocks, thus rendering
the feature useless.

21 files changed, 635 insertions, 415 deletions

diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 0ef19f1469ec..63255820b58a 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -34,13 +34,13 @@
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
-#include "xfs_icache.h"
 #include "xfs_iomap.h"
 #include "xfs_health.h"
 #include "xfs_bmap_item.h"
 #include "xfs_symlink_remote.h"
 #include "xfs_inode_util.h"
 #include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -171,18 +171,16 @@ xfs_bmbt_update(
  * Compute the worst-case number of indirect blocks that will be used
  * for ip's delayed extent of length "len".
  */
-STATIC xfs_filblks_t
+xfs_filblks_t
 xfs_bmap_worst_indlen(
-	xfs_inode_t	*ip,		/* incore inode pointer */
-	xfs_filblks_t	len)		/* delayed extent length */
+	struct xfs_inode	*ip,		/* incore inode pointer */
+	xfs_filblks_t		len)		/* delayed extent length */
 {
-	int		level;		/* btree level number */
-	int		maxrecs;	/* maximum record count at this level */
-	xfs_mount_t	*mp;		/* mount structure */
-	xfs_filblks_t	rval;		/* return value */
+	struct xfs_mount	*mp = ip->i_mount;
+	int			maxrecs = mp->m_bmap_dmxr[0];
+	int			level;
+	xfs_filblks_t		rval;
 
-	mp = ip->i_mount;
-	maxrecs = mp->m_bmap_dmxr[0];
 	for (level = 0, rval = 0;
 	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
 	     level++) {
@@ -2572,146 +2570,6 @@ done:
 }
 
 /*
- * Convert a hole to a delayed allocation.
- */
-STATIC void
-xfs_bmap_add_extent_hole_delay(
-	xfs_inode_t		*ip,	/* incore inode pointer */
-	int			whichfork,
-	struct xfs_iext_cursor	*icur,
-	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */
-{
-	struct xfs_ifork	*ifp;	/* inode fork pointer */
-	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */
-	xfs_filblks_t		newlen=0;	/* new indirect size */
-	xfs_filblks_t		oldlen=0;	/* old indirect size */
-	xfs_bmbt_irec_t		right;	/* right neighbor extent entry */
-	uint32_t		state = xfs_bmap_fork_to_state(whichfork);
-	xfs_filblks_t		temp;	 /* temp for indirect calculations */
-
-	ifp = xfs_ifork_ptr(ip, whichfork);
-	ASSERT(isnullstartblock(new->br_startblock));
-
-	/*
-	 * Check and set flags if this segment has a left neighbor
-	 */
-	if (xfs_iext_peek_prev_extent(ifp, icur, &left)) {
-		state |= BMAP_LEFT_VALID;
-		if (isnullstartblock(left.br_startblock))
-			state |= BMAP_LEFT_DELAY;
-	}
-
-	/*
-	 * Check and set flags if the current (right) segment exists.
-	 * If it doesn't exist, we're converting the hole at end-of-file.
-	 */
-	if (xfs_iext_get_extent(ifp, icur, &right)) {
-		state |= BMAP_RIGHT_VALID;
-		if (isnullstartblock(right.br_startblock))
-			state |= BMAP_RIGHT_DELAY;
-	}
-
-	/*
-	 * Set contiguity flags on the left and right neighbors.
-	 * Don't let extents get too large, even if the pieces are contiguous.
-	 */
-	if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
-	    left.br_startoff + left.br_blockcount == new->br_startoff &&
-	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
-		state |= BMAP_LEFT_CONTIG;
-
-	if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
-	    new->br_startoff + new->br_blockcount == right.br_startoff &&
-	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
-	    (!(state & BMAP_LEFT_CONTIG) ||
-	     (left.br_blockcount + new->br_blockcount +
-	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
-		state |= BMAP_RIGHT_CONTIG;
-
-	/*
-	 * Switch out based on the contiguity flags.
-	 */
-	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
-	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
-		/*
-		 * New allocation is contiguous with delayed allocations
-		 * on the left and on the right.
-		 * Merge all three into a single extent record.
-		 */
-		temp = left.br_blockcount + new->br_blockcount +
-			right.br_blockcount;
-
-		oldlen = startblockval(left.br_startblock) +
-			startblockval(new->br_startblock) +
-			startblockval(right.br_startblock);
-		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-					 oldlen);
-		left.br_startblock = nullstartblock(newlen);
-		left.br_blockcount = temp;
-
-		xfs_iext_remove(ip, icur, state);
-		xfs_iext_prev(ifp, icur);
-		xfs_iext_update_extent(ip, state, icur, &left);
-		break;
-
-	case BMAP_LEFT_CONTIG:
-		/*
-		 * New allocation is contiguous with a delayed allocation
-		 * on the left.
-		 * Merge the new allocation with the left neighbor.
-		 */
-		temp = left.br_blockcount + new->br_blockcount;
-
-		oldlen = startblockval(left.br_startblock) +
-			startblockval(new->br_startblock);
-		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-					 oldlen);
-		left.br_blockcount = temp;
-		left.br_startblock = nullstartblock(newlen);
-
-		xfs_iext_prev(ifp, icur);
-		xfs_iext_update_extent(ip, state, icur, &left);
-		break;
-
-	case BMAP_RIGHT_CONTIG:
-		/*
-		 * New allocation is contiguous with a delayed allocation
-		 * on the right.
-		 * Merge the new allocation with the right neighbor.
-		 */
-		temp = new->br_blockcount + right.br_blockcount;
-		oldlen = startblockval(new->br_startblock) +
-			startblockval(right.br_startblock);
-		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-					 oldlen);
-		right.br_startoff = new->br_startoff;
-		right.br_startblock = nullstartblock(newlen);
-		right.br_blockcount = temp;
-		xfs_iext_update_extent(ip, state, icur, &right);
-		break;
-
-	case 0:
-		/*
-		 * New allocation is not contiguous with another
-		 * delayed allocation.
-		 * Insert a new entry.
-		 */
-		oldlen = newlen = 0;
-		xfs_iext_insert(ip, icur, new, state);
-		break;
-	}
-	if (oldlen != newlen) {
-		ASSERT(oldlen > newlen);
-		xfs_add_fdblocks(ip->i_mount, oldlen - newlen);
-
-		/*
-		 * Nothing to do for disk quota accounting here.
-		 */
-		xfs_mod_delalloc(ip, 0, (int64_t)newlen - oldlen);
-	}
-}
-
-/*
  * Convert a hole to a real allocation.
  */
 STATIC int				/* error */
@@ -4039,144 +3897,6 @@ xfs_bmapi_read(
 	return 0;
 }
 
-/*
- * Add a delayed allocation extent to an inode. Blocks are reserved from the
- * global pool and the extent inserted into the inode in-core extent tree.
- *
- * On entry, got refers to the first extent beyond the offset of the extent to
- * allocate or eof is specified if no such extent exists. On return, got refers
- * to the extent record that was inserted to the inode fork.
- *
- * Note that the allocated extent may have been merged with contiguous extents
- * during insertion into the inode fork. Thus, got does not reflect the current
- * state of the inode fork on return. If necessary, the caller can use lastx to
- * look up the updated record in the inode fork.
- */
-int
-xfs_bmapi_reserve_delalloc(
-	struct xfs_inode	*ip,
-	int			whichfork,
-	xfs_fileoff_t		off,
-	xfs_filblks_t		len,
-	xfs_filblks_t		prealloc,
-	struct xfs_bmbt_irec	*got,
-	struct xfs_iext_cursor	*icur,
-	int			eof)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
-	xfs_extlen_t		alen;
-	xfs_extlen_t		indlen;
-	uint64_t		fdblocks;
-	int			error;
-	xfs_fileoff_t		aoff;
-	bool			use_cowextszhint =
-					whichfork == XFS_COW_FORK && !prealloc;
-
-retry:
-	/*
-	 * Cap the alloc length. Keep track of prealloc so we know whether to
-	 * tag the inode before we return.
-	 */
-	aoff = off;
-	alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);
-	if (!eof)
-		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
-	if (prealloc && alen >= len)
-		prealloc = alen - len;
-
-	/*
-	 * If we're targetting the COW fork but aren't creating a speculative
-	 * posteof preallocation, try to expand the reservation to align with
-	 * the COW extent size hint if there's sufficient free space.
-	 *
-	 * Unlike the data fork, the CoW cancellation functions will free all
-	 * the reservations at inactivation, so we don't require that every
-	 * delalloc reservation have a dirty pagecache.
-	 */
-	if (use_cowextszhint) {
-		struct xfs_bmbt_irec	prev;
-		xfs_extlen_t		extsz = xfs_get_cowextsz_hint(ip);
-
-		if (!xfs_iext_peek_prev_extent(ifp, icur, &prev))
-			prev.br_startoff = NULLFILEOFF;
-
-		error = xfs_bmap_extsize_align(mp, got, &prev, extsz, 0, eof,
-					       1, 0, &aoff, &alen);
-		ASSERT(!error);
-	}
-
-	/*
-	 * Make a transaction-less quota reservation for delayed allocation
-	 * blocks.  This number gets adjusted later.  We return if we haven't
-	 * allocated blocks already inside this loop.
-	 */
-	error = xfs_quota_reserve_blkres(ip, alen);
-	if (error)
-		goto out;
-
-	/*
-	 * Split changing sb for alen and indlen since they could be coming
-	 * from different places.
-	 */
-	indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen);
-	ASSERT(indlen > 0);
-
-	fdblocks = indlen;
-	if (XFS_IS_REALTIME_INODE(ip)) {
-		error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
-		if (error)
-			goto out_unreserve_quota;
-	} else {
-		fdblocks += alen;
-	}
-
-	error = xfs_dec_fdblocks(mp, fdblocks, false);
-	if (error)
-		goto out_unreserve_frextents;
-
-	ip->i_delayed_blks += alen;
-	xfs_mod_delalloc(ip, alen, indlen);
-
-	got->br_startoff = aoff;
-	got->br_startblock = nullstartblock(indlen);
-	got->br_blockcount = alen;
-	got->br_state = XFS_EXT_NORM;
-
-	xfs_bmap_add_extent_hole_delay(ip, whichfork, icur, got);
-
-	/*
-	 * Tag the inode if blocks were preallocated. Note that COW fork
-	 * preallocation can occur at the start or end of the extent, even when
-	 * prealloc == 0, so we must also check the aligned offset and length.
-	 */
-	if (whichfork == XFS_DATA_FORK && prealloc)
-		xfs_inode_set_eofblocks_tag(ip);
-	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
-		xfs_inode_set_cowblocks_tag(ip);
-
-	return 0;
-
-out_unreserve_frextents:
-	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
-out_unreserve_quota:
-	if (XFS_IS_QUOTA_ON(mp))
-		xfs_quota_unreserve_blkres(ip, alen);
-out:
-	if (error == -ENOSPC || error == -EDQUOT) {
-		trace_xfs_delalloc_enospc(ip, off, len);
-
-		if (prealloc || use_cowextszhint) {
-			/* retry without any preallocation */
-			use_cowextszhint = false;
-			prealloc = 0;
-			goto retry;
-		}
-	}
-	return error;
-}
-
 static int
 xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
@@ -4948,7 +4668,8 @@ xfs_bmap_del_extent_delay(
 	int			whichfork,
 	struct xfs_iext_cursor	*icur,
 	struct xfs_bmbt_irec	*got,
-	struct xfs_bmbt_irec	*del)
+	struct xfs_bmbt_irec	*del,
+	uint32_t		bflags)	/* bmapi flags */
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
@@ -5068,10 +4789,18 @@ xfs_bmap_del_extent_delay(
 	da_diff = da_old - da_new;
 	fdblocks = da_diff;
 
-	if (isrt)
-		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
-	else
+	if (bflags & XFS_BMAPI_REMAP) {
+		;
+	} else if (isrt) {
+		xfs_rtbxlen_t	rtxlen;
+
+		rtxlen = xfs_blen_to_rtbxlen(mp, del->br_blockcount);
+		if (xfs_is_zoned_inode(ip))
+			xfs_zoned_add_available(mp, rtxlen);
+		xfs_add_frextents(mp, rtxlen);
+	} else {
 		fdblocks += del->br_blockcount;
+	}
 
 	xfs_add_fdblocks(mp, fdblocks);
 	xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff);
@@ -5670,7 +5399,8 @@ __xfs_bunmapi(
 
 delete:
 		if (wasdel) {
-			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del);
+			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,
+					&del, flags);
 		} else {
 			error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,
 					&del, &tmp_logflags, whichfork,
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 4b721d935994..b4d9c6e0f3f9 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -204,7 +204,7 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extnum_t nexts, int *done);
 void	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
-		struct xfs_bmbt_irec *del);
+		struct xfs_bmbt_irec *del, uint32_t bflags);
 void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
 		struct xfs_bmbt_irec *del);
@@ -219,10 +219,6 @@ int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		bool *done, xfs_fileoff_t stop_fsb);
 int	xfs_bmap_split_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t split_offset);
-int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
-		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
-		struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
-		int eof);
 int	xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork,
 		xfs_off_t offset, struct iomap *iomap, unsigned int *seq);
 int	xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
@@ -233,6 +229,7 @@ xfs_extlen_t xfs_bmapi_minleft(struct xfs_trans *tp, struct xfs_inode *ip,
 		int fork);
 int	xfs_bmap_btalloc_low_space(struct xfs_bmalloca *ap,
 		struct xfs_alloc_arg *args);
+xfs_filblks_t xfs_bmap_worst_indlen(struct xfs_inode *ip, xfs_filblks_t len);
 
 enum xfs_bmap_intent_type {
 	XFS_BMAP_MAP = 1,
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index b1007fb661ba..9566a7623365 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -178,9 +178,10 @@ typedef struct xfs_sb {
 
 	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;
@@ -270,9 +271,10 @@ struct xfs_dsb {
 	__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.
@@ -395,6 +397,9 @@ xfs_sb_has_ro_compat_feature(
 #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_ZONE_GAPS	(1 << 10) /* RTGs have LBA gaps */
+
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE | \
 		 XFS_SB_FEAT_INCOMPAT_SPINODES | \
@@ -404,7 +409,9 @@ xfs_sb_has_ro_compat_feature(
 		 XFS_SB_FEAT_INCOMPAT_NREXT64 | \
 		 XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \
 		 XFS_SB_FEAT_INCOMPAT_PARENT | \
-		 XFS_SB_FEAT_INCOMPAT_METADIR)
+		 XFS_SB_FEAT_INCOMPAT_METADIR | \
+		 XFS_SB_FEAT_INCOMPAT_ZONED | \
+		 XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)
 
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool
@@ -952,7 +959,12 @@ struct xfs_dinode {
 	__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 */
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 2c3171262b44..12463ba766da 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -189,7 +189,9 @@ struct xfs_fsop_geom {
 	uint32_t	checked;	/* o: checked fs & rt metadata	*/
 	__u32		rgextents;	/* rt extents in a realtime group */
 	__u32		rgcount;	/* number of realtime groups	*/
-	__u64		reserved[16];	/* reserved space		*/
+	__u64		rtstart;	/* start of internal rt section */
+	__u64		rtreserved;	/* RT (zoned) reserved blocks	*/
+	__u64		reserved[14];	/* reserved space		*/
 };
 
 #define XFS_FSOP_GEOM_SICK_COUNTERS	(1 << 0)  /* summary counters */
@@ -247,6 +249,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */
 #define XFS_FSOP_GEOM_FLAGS_PARENT	(1 << 25) /* linux parent pointers */
 #define XFS_FSOP_GEOM_FLAGS_METADIR	(1 << 26) /* metadata directories */
+#define XFS_FSOP_GEOM_FLAGS_ZONED	(1 << 27) /* zoned rt device */
 
 /*
  * Minimum and maximum sizes need for growth checks.
@@ -1079,6 +1082,15 @@ struct xfs_rtgroup_geometry {
 #define XFS_IOC_COMMIT_RANGE	     _IOW ('X', 131, struct xfs_commit_range)
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */
 
+/*
+ * Devices supported by a single XFS file system.  Reported in fsmaps fmr_device
+ * when using internal RT devices.
+ */
+enum xfs_device {
+	XFS_DEV_DATA	= 1,
+	XFS_DEV_LOG	= 2,
+	XFS_DEV_RT	= 3,
+};
 
 #ifndef HAVE_BBMACROS
 /*
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index 242b05627c7a..4423932a2313 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -19,10 +19,23 @@ struct xfs_group {
 #ifdef __KERNEL__
 	/* -- kernel only structures below this line -- */
 
-	/*
-	 * Track freed but not yet committed extents.
-	 */
-	struct xfs_extent_busy_tree *xg_busy_extents;
+	union {
+		/*
+		 * For perags and non-zoned RT groups:
+		 * Track freed but not yet committed extents.
+		 */
+		struct xfs_extent_busy_tree	*xg_busy_extents;
+
+		/*
+		 * For zoned RT groups:
+		 * List of groups that need a zone reset.
+		 *
+		 * The zonegc code forces a log flush of the rtrmap inode before
+		 * resetting the write pointer, so there is no need for
+		 * individual busy extent tracking.
+		 */
+		struct xfs_group		*xg_next_reset;
+	};
 
 	/*
 	 * Bitsets of per-ag metadata that have been checked and/or are sick.
@@ -107,9 +120,15 @@ xfs_gbno_to_daddr(
 	xfs_agblock_t		gbno)
 {
 	struct xfs_mount	*mp = xg->xg_mount;
-	uint32_t		blocks = mp->m_groups[xg->xg_type].blocks;
+	struct xfs_groups	*g = &mp->m_groups[xg->xg_type];
+	xfs_fsblock_t		fsbno;
+
+	if (g->has_daddr_gaps)
+		fsbno = xfs_gbno_to_fsb(xg, gbno);
+	else
+		fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno;
 
-	return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno);
+	return XFS_FSB_TO_BB(mp, g->start_fsb + fsbno);
 }
 
 static inline uint32_t
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f3a840a425f5..57513ba19d6a 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1927,7 +1927,7 @@ xfs_dialloc(
 	 * that we can immediately allocate, but then we allow allocation on the
 	 * second pass if we fail to find an AG with free inodes in it.
 	 */
-	if (percpu_counter_read_positive(&mp->m_fdblocks) <
+	if (xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) <
 			mp->m_low_space[XFS_LOWSP_1_PCNT]) {
 		ok_alloc = false;
 		low_space = true;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index f24fa628fecf..992e6d337709 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -252,7 +252,10 @@ xfs_inode_from_disk(
 					   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);
@@ -349,6 +352,7 @@ xfs_inode_to_disk(
 		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);
@@ -752,11 +756,18 @@ xfs_dinode_verify(
 	    !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) &&
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index deb0b7c00a1f..48fe49a5f050 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -322,6 +322,7 @@ xfs_inode_init(
 
 	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;
 	}
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index a472ac2e45d0..0d637c276db0 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -475,7 +475,12 @@ struct xfs_log_dinode {
 	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 */
diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c
index 2f5f554a36d4..225923e463c4 100644
--- a/fs/xfs/libxfs/xfs_metafile.c
+++ b/fs/xfs/libxfs/xfs_metafile.c
@@ -21,6 +21,9 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_alloc.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtrefcount_btree.h"
 
 static const struct {
 	enum xfs_metafile_type	mtype;
@@ -74,12 +77,11 @@ xfs_metafile_clear_iflag(
 }
 
 /*
- * Is the amount of space that could be allocated towards a given metadata
- * file at or beneath a certain threshold?
+ * Is the metafile reservations at or beneath a certain threshold?
  */
 static inline bool
 xfs_metafile_resv_can_cover(
-	struct xfs_inode	*ip,
+	struct xfs_mount	*mp,
 	int64_t			rhs)
 {
 	/*
@@ -88,43 +90,38 @@ xfs_metafile_resv_can_cover(
 	 * global free block count.  Take care of the first case to avoid
 	 * touching the per-cpu counter.
 	 */
-	if (ip->i_delayed_blks >= rhs)
+	if (mp->m_metafile_resv_avail >= rhs)
 		return true;
 
 	/*
 	 * There aren't enough blocks left in the inode's reservation, but it
 	 * isn't critical unless there also isn't enough free space.
 	 */
-	return __percpu_counter_compare(&ip->i_mount->m_fdblocks,
-			rhs - ip->i_delayed_blks, 2048) >= 0;
+	return xfs_compare_freecounter(mp, XC_FREE_BLOCKS,
+			rhs - mp->m_metafile_resv_avail, 2048) >= 0;
 }
 
 /*
- * Is this metadata file critically low on blocks?  For now we'll define that
- * as the number of blocks we can get our hands on being less than 10% of what
- * we reserved or less than some arbitrary number (maximum btree height).
+ * Is the metafile reservation critically low on blocks?  For now we'll define
+ * that as the number of blocks we can get our hands on being less than 10% of
+ * what we reserved or less than some arbitrary number (maximum btree height).
  */
 bool
 xfs_metafile_resv_critical(
-	struct xfs_inode	*ip)
+	struct xfs_mount	*mp)
 {
-	uint64_t		asked_low_water;
+	ASSERT(xfs_has_metadir(mp));
 
-	if (!ip)
-		return false;
-
-	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_critical(ip, 0);
+	trace_xfs_metafile_resv_critical(mp, 0);
 
-	if (!xfs_metafile_resv_can_cover(ip, ip->i_mount->m_rtbtree_maxlevels))
+	if (!xfs_metafile_resv_can_cover(mp, mp->m_rtbtree_maxlevels))
 		return true;
 
-	asked_low_water = div_u64(ip->i_meta_resv_asked, 10);
-	if (!xfs_metafile_resv_can_cover(ip, asked_low_water))
+	if (!xfs_metafile_resv_can_cover(mp,
+			div_u64(mp->m_metafile_resv_target, 10)))
 		return true;
 
-	return XFS_TEST_ERROR(false, ip->i_mount,
-			XFS_ERRTAG_METAFILE_RESV_CRITICAL);
+	return XFS_TEST_ERROR(false, mp, XFS_ERRTAG_METAFILE_RESV_CRITICAL);
 }
 
 /* Allocate a block from the metadata file's reservation. */
@@ -133,22 +130,24 @@ xfs_metafile_resv_alloc_space(
 	struct xfs_inode	*ip,
 	struct xfs_alloc_arg	*args)
 {
+	struct xfs_mount	*mp = ip->i_mount;
 	int64_t			len = args->len;
 
 	ASSERT(xfs_is_metadir_inode(ip));
 	ASSERT(args->resv == XFS_AG_RESV_METAFILE);
 
-	trace_xfs_metafile_resv_alloc_space(ip, args->len);
+	trace_xfs_metafile_resv_alloc_space(mp, args->len);
 
 	/*
 	 * Allocate the blocks from the metadata inode's block reservation
 	 * and update the ondisk sb counter.
 	 */
-	if (ip->i_delayed_blks > 0) {
+	mutex_lock(&mp->m_metafile_resv_lock);
+	if (mp->m_metafile_resv_avail > 0) {
 		int64_t		from_resv;
 
-		from_resv = min_t(int64_t, len, ip->i_delayed_blks);
-		ip->i_delayed_blks -= from_resv;
+		from_resv = min_t(int64_t, len, mp->m_metafile_resv_avail);
+		mp->m_metafile_resv_avail -= from_resv;
 		xfs_mod_delalloc(ip, 0, -from_resv);
 		xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS,
 				-from_resv);
@@ -175,6 +174,9 @@ xfs_metafile_resv_alloc_space(
 		xfs_trans_mod_sb(args->tp, field, -len);
 	}
 
+	mp->m_metafile_resv_used += args->len;
+	mutex_unlock(&mp->m_metafile_resv_lock);
+
 	ip->i_nblocks += args->len;
 	xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE);
 }
@@ -186,26 +188,33 @@ xfs_metafile_resv_free_space(
 	struct xfs_trans	*tp,
 	xfs_filblks_t		len)
 {
+	struct xfs_mount	*mp = ip->i_mount;
 	int64_t			to_resv;
 
 	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_free_space(ip, len);
+
+	trace_xfs_metafile_resv_free_space(mp, len);
 
 	ip->i_nblocks -= len;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
+	mutex_lock(&mp->m_metafile_resv_lock);
+	mp->m_metafile_resv_used -= len;
+
 	/*
 	 * Add the freed blocks back into the inode's delalloc reservation
 	 * until it reaches the maximum size.  Update the ondisk fdblocks only.
 	 */
-	to_resv = ip->i_meta_resv_asked - (ip->i_nblocks + ip->i_delayed_blks);
+	to_resv = mp->m_metafile_resv_target -
+		(mp->m_metafile_resv_used + mp->m_metafile_resv_avail);
 	if (to_resv > 0) {
 		to_resv = min_t(int64_t, to_resv, len);
-		ip->i_delayed_blks += to_resv;
+		mp->m_metafile_resv_avail += to_resv;
 		xfs_mod_delalloc(ip, 0, to_resv);
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv);
 		len -= to_resv;
 	}
+	mutex_unlock(&mp->m_metafile_resv_lock);
 
 	/*
 	 * Everything else goes back to the filesystem, so update the in-core
@@ -215,61 +224,99 @@ xfs_metafile_resv_free_space(
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len);
 }
 
-/* Release a metadata file's space reservation. */
+static void
+__xfs_metafile_resv_free(
+	struct xfs_mount	*mp)
+{
+	if (mp->m_metafile_resv_avail) {
+		xfs_mod_sb_delalloc(mp, -(int64_t)mp->m_metafile_resv_avail);
+		xfs_add_fdblocks(mp, mp->m_metafile_resv_avail);
+	}
+	mp->m_metafile_resv_avail = 0;
+	mp->m_metafile_resv_used = 0;
+	mp->m_metafile_resv_target = 0;
+}
+
+/* Release unused metafile space reservation. */
 void
 xfs_metafile_resv_free(
-	struct xfs_inode	*ip)
+	struct xfs_mount	*mp)
 {
-	/* Non-btree metadata inodes don't need space reservations. */
-	if (!ip || !ip->i_meta_resv_asked)
+	if (!xfs_has_metadir(mp))
 		return;
 
-	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_free(ip, 0);
+	trace_xfs_metafile_resv_free(mp, 0);
 
-	if (ip->i_delayed_blks) {
-		xfs_mod_delalloc(ip, 0, -ip->i_delayed_blks);
-		xfs_add_fdblocks(ip->i_mount, ip->i_delayed_blks);
-		ip->i_delayed_blks = 0;
-	}
-	ip->i_meta_resv_asked = 0;
+	mutex_lock(&mp->m_metafile_resv_lock);
+	__xfs_metafile_resv_free(mp);
+	mutex_unlock(&mp->m_metafile_resv_lock);
 }
 
-/* Set up a metadata file's space reservation. */
+/* Set up a metafile space reservation. */
 int
 xfs_metafile_resv_init(
-	struct xfs_inode	*ip,
-	xfs_filblks_t		ask)
+	struct xfs_mount	*mp)
 {
+	struct xfs_rtgroup	*rtg = NULL;
+	xfs_filblks_t		used = 0, target = 0;
 	xfs_filblks_t		hidden_space;
-	xfs_filblks_t		used;
-	int			error;
+	xfs_rfsblock_t		dblocks_avail = mp->m_sb.sb_dblocks / 4;
+	int			error = 0;
 
-	if (!ip || ip->i_meta_resv_asked > 0)
+	if (!xfs_has_metadir(mp))
 		return 0;
 
-	ASSERT(xfs_is_metadir_inode(ip));
+	/*
+	 * Free any previous reservation to have a clean slate.
+	 */
+	mutex_lock(&mp->m_metafile_resv_lock);
+	__xfs_metafile_resv_free(mp);
+
+	/*
+	 * Currently the only btree metafiles that require reservations are the
+	 * rtrmap and the rtrefcount.  Anything new will have to be added here
+	 * as well.
+	 */
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		if (xfs_has_rtrmapbt(mp)) {
+			used += rtg_rmap(rtg)->i_nblocks;
+			target += xfs_rtrmapbt_calc_reserves(mp);
+		}
+		if (xfs_has_rtreflink(mp)) {
+			used += rtg_refcount(rtg)->i_nblocks;
+			target += xfs_rtrefcountbt_calc_reserves(mp);
+		}
+	}
+
+	if (!target)
+		goto out_unlock;
 
 	/*
-	 * Space taken by all other metadata btrees are accounted on-disk as
+	 * Space taken by the per-AG metadata btrees are accounted on-disk as
 	 * used space.  We therefore only hide the space that is reserved but
 	 * not used by the trees.
 	 */
-	used = ip->i_nblocks;
-	if (used > ask)
-		ask = used;
-	hidden_space = ask - used;
+	if (used > target)
+		target = used;
+	else if (target > dblocks_avail)
+		target = dblocks_avail;
+	hidden_space = target - used;
 
-	error = xfs_dec_fdblocks(ip->i_mount, hidden_space, true);
+	error = xfs_dec_fdblocks(mp, hidden_space, true);
 	if (error) {
-		trace_xfs_metafile_resv_init_error(ip, error, _RET_IP_);
-		return error;
+		trace_xfs_metafile_resv_init_error(mp, 0);
+		goto out_unlock;
 	}
 
-	xfs_mod_delalloc(ip, 0, hidden_space);
-	ip->i_delayed_blks = hidden_space;
-	ip->i_meta_resv_asked = ask;
+	xfs_mod_sb_delalloc(mp, hidden_space);
+
+	mp->m_metafile_resv_target = target;
+	mp->m_metafile_resv_used = used;
+	mp->m_metafile_resv_avail = hidden_space;
+
+	trace_xfs_metafile_resv_init(mp, target);
 
-	trace_xfs_metafile_resv_init(ip, ask);
-	return 0;
+out_unlock:
+	mutex_unlock(&mp->m_metafile_resv_lock);
+	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h
index 95af4b52e5a7..ae6f9e779b98 100644
--- a/fs/xfs/libxfs/xfs_metafile.h
+++ b/fs/xfs/libxfs/xfs_metafile.h
@@ -26,13 +26,13 @@ void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip);
 /* Space reservations for metadata inodes. */
 struct xfs_alloc_arg;
 
-bool xfs_metafile_resv_critical(struct xfs_inode *ip);
+bool xfs_metafile_resv_critical(struct xfs_mount *mp);
 void xfs_metafile_resv_alloc_space(struct xfs_inode *ip,
 		struct xfs_alloc_arg *args);
 void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp,
 		xfs_filblks_t len);
-void xfs_metafile_resv_free(struct xfs_inode *ip);
-int xfs_metafile_resv_init(struct xfs_inode *ip, xfs_filblks_t ask);
+void xfs_metafile_resv_free(struct xfs_mount *mp);
+int xfs_metafile_resv_init(struct xfs_mount *mp);
 
 /* Code specific to kernel/userspace; must be provided externally. */
 
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index a85ecddaa48e..5ed44fdf7491 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -233,8 +233,8 @@ xfs_check_ondisk_structs(void)
 			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);
@@ -295,6 +295,8 @@ xfs_check_ondisk_structs(void)
 	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 */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 770adf60dd73..5057536e586c 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1123,6 +1123,7 @@ xfs_rtfree_blocks(
 	xfs_extlen_t		mod;
 	int			error;
 
+	ASSERT(!xfs_has_zoned(mp));
 	ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
 
 	mod = xfs_blen_to_rtxoff(mp, rtlen);
@@ -1174,6 +1175,9 @@ xfs_rtalloc_query_range(
 
 	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;
@@ -1268,6 +1272,8 @@ xfs_rtbitmap_blockcount_len(
 	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));
 }
 
@@ -1308,6 +1314,11 @@ xfs_rtsummary_blockcount(
 	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);
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index d84d32f1b48f..9186c58e83d5 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -194,15 +194,17 @@ xfs_rtgroup_lock(
 	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))
@@ -228,11 +230,13 @@ xfs_rtgroup_unlock(
 	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);
+		}
 	}
 }
 
@@ -249,7 +253,8 @@ xfs_rtgroup_trans_join(
 	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);
 	}
@@ -270,7 +275,7 @@ xfs_rtgroup_get_geometry(
 	/* Fill out form. */
 	memset(rgeo, 0, sizeof(*rgeo));
 	rgeo->rg_number = rtg_rgno(rtg);
-	rgeo->rg_length = rtg_group(rtg)->xg_block_count;
+	rgeo->rg_length = rtg_blocks(rtg);
 	xfs_rtgroup_geom_health(rtg, rgeo);
 	return 0;
 }
@@ -354,6 +359,7 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 		.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] = {
@@ -362,6 +368,7 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 		.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] = {
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 03f39d4e43fc..d36a6ae0abe5 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -37,15 +37,33 @@ struct xfs_rtgroup {
 	xfs_rtxnum_t		rtg_extents;
 
 	/*
-	 * Cache of rt summary level per bitmap block with the invariant that
-	 * rtg_rsum_cache[bbno] > the maximum i for which rsum[i][bbno] != 0,
-	 * or 0 if rsum[i][bbno] == 0 for all i.
-	 *
+	 * For bitmap based RT devices this points to a cache of rt summary
+	 * level per bitmap block with the invariant that rtg_rsum_cache[bbno]
+	 * > the maximum i for which rsum[i][bbno] != 0, or 0 if
+	 * rsum[i][bbno] == 0 for all i.
 	 * Reads and writes are serialized by the rsumip inode lock.
+	 *
+	 * For zoned RT devices this points to the open zone structure for
+	 * a group that is open for writers, or is NULL.
 	 */
-	uint8_t			*rtg_rsum_cache;
+	union {
+		uint8_t			*rtg_rsum_cache;
+		struct xfs_open_zone	*rtg_open_zone;
+	};
 };
 
+/*
+ * For zoned RT devices this is set on groups that have no written blocks
+ * and can be picked by the allocator for opening.
+ */
+#define XFS_RTG_FREE			XA_MARK_0
+
+/*
+ * For zoned RT devices this is set on groups that are fully written and that
+ * have unused blocks.  Used by the garbage collection to pick targets.
+ */
+#define XFS_RTG_RECLAIMABLE		XA_MARK_1
+
 static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
 {
 	return container_of(xg, struct xfs_rtgroup, rtg_group);
@@ -66,6 +84,11 @@ static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
 	return rtg->rtg_group.xg_gno;
 }
 
+static inline xfs_rgblock_t rtg_blocks(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_block_count;
+}
+
 static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg)
 {
 	return rtg->rtg_inodes[XFS_RTGI_BITMAP];
@@ -222,10 +245,14 @@ xfs_rtb_to_daddr(
 	xfs_rtblock_t		rtbno)
 {
 	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
-	xfs_rgnumber_t		rgno = xfs_rtb_to_rgno(mp, rtbno);
-	uint64_t		start_bno = (xfs_rtblock_t)rgno * g->blocks;
 
-	return XFS_FSB_TO_BB(mp, start_bno + (rtbno & g->blkmask));
+	if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) {
+		xfs_rgnumber_t	rgno = xfs_rtb_to_rgno(mp, rtbno);
+
+		rtbno = (xfs_rtblock_t)rgno * g->blocks + (rtbno & g->blkmask);
+	}
+
+	return XFS_FSB_TO_BB(mp, g->start_fsb + rtbno);
 }
 
 static inline xfs_rtblock_t
@@ -233,10 +260,11 @@ xfs_daddr_to_rtb(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		daddr)
 {
-	xfs_rfsblock_t		bno = XFS_BB_TO_FSBT(mp, daddr);
+	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	xfs_rfsblock_t		bno;
 
-	if (xfs_has_rtgroups(mp)) {
-		struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG];
+	bno = XFS_BB_TO_FSBT(mp, daddr) - g->start_fsb;
+	if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) {
 		xfs_rgnumber_t	rgno;
 		uint32_t	rgbno;
 
diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c
index e4ec36943cb7..9bdc2cbfc113 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c
@@ -1033,3 +1033,22 @@ xfs_rtrmapbt_init_rtsb(
 	xfs_btree_del_cursor(cur, error);
 	return error;
 }
+
+/*
+ * Return the highest rgbno currently tracked by the rmap for this rtg.
+ */
+xfs_rgblock_t
+xfs_rtrmap_highest_rgbno(
+	struct xfs_rtgroup	*rtg)
+{
+	struct xfs_btree_block	*block = rtg_rmap(rtg)->i_df.if_broot;
+	union xfs_btree_key	key = {};
+	struct xfs_btree_cur	*cur;
+
+	if (block->bb_numrecs == 0)
+		return NULLRGBLOCK;
+	cur = xfs_rtrmapbt_init_cursor(NULL, rtg);
+	xfs_btree_get_keys(cur, block, &key);
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	return be32_to_cpu(key.__rmap_bigkey[1].rm_startblock);
+}
diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h
index 9d0915089891..e328fd62a149 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h
@@ -207,4 +207,6 @@ struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg,
 int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree,
 		struct xfs_buftarg *btp, xfs_rgnumber_t rgno);
 
+xfs_rgblock_t xfs_rtrmap_highest_rgbno(struct xfs_rtgroup *rtg);
+
 #endif /* __XFS_RTRMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 3dc5f5dba162..e42bfd04a7c6 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -30,6 +30,7 @@
 #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.
@@ -185,6 +186,8 @@ xfs_sb_version_to_features(
 		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;
 }
@@ -266,6 +269,9 @@ static uint64_t
 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));
 }
@@ -275,9 +281,15 @@ bool
 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 ||
@@ -435,6 +447,34 @@ xfs_validate_sb_rtgroups(
 	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(
@@ -523,6 +563,11 @@ 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,
@@ -835,6 +880,14 @@ __xfs_sb_from_disk(
 		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
@@ -1001,6 +1054,11 @@ xfs_sb_to_disk(
 		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);
+	}
 }
 
 /*
@@ -1146,6 +1204,10 @@ xfs_sb_mount_rextsize(
 		rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize;
 		rgs->blklog = mp->m_sb.sb_rgblklog;
 		rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog);
+		rgs->start_fsb = mp->m_sb.sb_rtstart;
+		if (xfs_sb_has_incompat_feature(sbp,
+				XFS_SB_FEAT_INCOMPAT_ZONE_GAPS))
+			rgs->has_daddr_gaps = true;
 	} else {
 		rgs->blocks = 0;
 		rgs->blklog = 0;
@@ -1265,8 +1327,7 @@ xfs_log_sb(
 		mp->m_sb.sb_ifree = min_t(uint64_t,
 				percpu_counter_sum_positive(&mp->m_ifree),
 				mp->m_sb.sb_icount);
-		mp->m_sb.sb_fdblocks =
-				percpu_counter_sum_positive(&mp->m_fdblocks);
+		mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS);
 	}
 
 	/*
@@ -1275,9 +1336,10 @@ xfs_log_sb(
 	 * we handle nearly-lockless reservations, so we must use the _positive
 	 * variant here to avoid writing out nonsense frextents.
 	 */
-	if (xfs_has_rtgroups(mp))
+	if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) {
 		mp->m_sb.sb_frextents =
-				percpu_counter_sum_positive(&mp->m_frextents);
+				xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS);
+	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
@@ -1510,6 +1572,8 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE;
 	if (xfs_has_metadir(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR;
+	if (xfs_has_zoned(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 
@@ -1530,6 +1594,10 @@ xfs_fs_geometry(
 		geo->rgcount = sbp->sb_rgcount;
 		geo->rgextents = sbp->sb_rgextents;
 	}
+	if (xfs_has_zoned(mp)) {
+		geo->rtstart = sbp->sb_rtstart;
+		geo->rtreserved = sbp->sb_rtreserved;
+	}
 }
 
 /* Read a secondary superblock. */
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index ca2401c1facd..f6f4f2d4b5db 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -233,6 +233,34 @@ enum xfs_group_type {
 	{ XG_TYPE_AG,	"ag" }, \
 	{ XG_TYPE_RTG,	"rtg" }
 
+enum xfs_free_counter {
+	/*
+	 * Number of free blocks on the data device.
+	 */
+	XC_FREE_BLOCKS,
+
+	/*
+	 * Number of free RT extents on the RT device.
+	 */
+	XC_FREE_RTEXTENTS,
+
+	/*
+	 * Number of available for use RT extents.
+	 *
+	 * This counter only exists for zoned RT device and indicates the number
+	 * of RT extents that can be directly used by writes.  XC_FREE_RTEXTENTS
+	 * also includes blocks that have been written previously and freed, but
+	 * sit in a rtgroup that still needs a zone reset.
+	 */
+	XC_FREE_RTAVAILABLE,
+	XC_FREE_NR,
+};
+
+#define XFS_FREECOUNTER_STR \
+	{ XC_FREE_BLOCKS,		"blocks" }, \
+	{ XC_FREE_RTEXTENTS,		"rtextents" }, \
+	{ XC_FREE_RTAVAILABLE,		"rtavailable" }
+
 /*
  * Type verifier functions
  */
diff --git a/fs/xfs/libxfs/xfs_zones.c b/fs/xfs/libxfs/xfs_zones.c
new file mode 100644
index 000000000000..b0791a71931c
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_zones.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023-2025 Christoph Hellwig.
+ * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_rtgroup.h"
+#include "xfs_zones.h"
+
+static bool
+xfs_zone_validate_empty(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	if (rtg_rmap(rtg)->i_used_blocks > 0) {
+		xfs_warn(mp, "empty zone %u has non-zero used counter (0x%x).",
+			 rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks);
+		return false;
+	}
+
+	*write_pointer = 0;
+	return true;
+}
+
+static bool
+xfs_zone_validate_wp(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rtblock_t		wp_fsb = xfs_daddr_to_rtb(mp, zone->wp);
+
+	if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) {
+		xfs_warn(mp, "zone %u has too large used counter (0x%x).",
+			 rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks);
+		return false;
+	}
+
+	if (xfs_rtb_to_rgno(mp, wp_fsb) != rtg_rgno(rtg)) {
+		xfs_warn(mp, "zone %u write pointer (0x%llx) outside of zone.",
+			 rtg_rgno(rtg), wp_fsb);
+		return false;
+	}
+
+	*write_pointer = xfs_rtb_to_rgbno(mp, wp_fsb);
+	if (*write_pointer >= rtg->rtg_extents) {
+		xfs_warn(mp, "zone %u has invalid write pointer (0x%x).",
+			 rtg_rgno(rtg), *write_pointer);
+		return false;
+	}
+
+	return true;
+}
+
+static bool
+xfs_zone_validate_full(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) {
+		xfs_warn(mp, "zone %u has too large used counter (0x%x).",
+			 rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks);
+		return false;
+	}
+
+	*write_pointer = rtg->rtg_extents;
+	return true;
+}
+
+static bool
+xfs_zone_validate_seq(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_EMPTY:
+		return xfs_zone_validate_empty(zone, rtg, write_pointer);
+	case BLK_ZONE_COND_IMP_OPEN:
+	case BLK_ZONE_COND_EXP_OPEN:
+	case BLK_ZONE_COND_CLOSED:
+		return xfs_zone_validate_wp(zone, rtg, write_pointer);
+	case BLK_ZONE_COND_FULL:
+		return xfs_zone_validate_full(zone, rtg, write_pointer);
+	case BLK_ZONE_COND_NOT_WP:
+	case BLK_ZONE_COND_OFFLINE:
+	case BLK_ZONE_COND_READONLY:
+		xfs_warn(mp, "zone %u has unsupported zone condition 0x%x.",
+			rtg_rgno(rtg), zone->cond);
+		return false;
+	default:
+		xfs_warn(mp, "zone %u has unknown zone condition 0x%x.",
+			rtg_rgno(rtg), zone->cond);
+		return false;
+	}
+}
+
+static bool
+xfs_zone_validate_conv(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_NOT_WP:
+		return true;
+	default:
+		xfs_warn(mp,
+"conventional zone %u has unsupported zone condition 0x%x.",
+			 rtg_rgno(rtg), zone->cond);
+		return false;
+	}
+}
+
+bool
+xfs_zone_validate(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	uint32_t		expected_size;
+
+	/*
+	 * Check that the zone capacity matches the rtgroup size stored in the
+	 * superblock.  Note that all zones including the last one must have a
+	 * uniform capacity.
+	 */
+	if (XFS_BB_TO_FSB(mp, zone->capacity) != g->blocks) {
+		xfs_warn(mp,
+"zone %u capacity (0x%llx) does not match RT group size (0x%x).",
+			rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->capacity),
+			g->blocks);
+		return false;
+	}
+
+	if (g->has_daddr_gaps) {
+		expected_size = 1 << g->blklog;
+	} else {
+		if (zone->len != zone->capacity) {
+			xfs_warn(mp,
+"zone %u has capacity != size ((0x%llx vs 0x%llx)",
+				rtg_rgno(rtg),
+				XFS_BB_TO_FSB(mp, zone->len),
+				XFS_BB_TO_FSB(mp, zone->capacity));
+			return false;
+		}
+		expected_size = g->blocks;
+	}
+
+	if (XFS_BB_TO_FSB(mp, zone->len) != expected_size) {
+		xfs_warn(mp,
+"zone %u length (0x%llx) does match geometry (0x%x).",
+			rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->len),
+			expected_size);
+	}
+
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		return xfs_zone_validate_conv(zone, rtg);
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+		return xfs_zone_validate_seq(zone, rtg, write_pointer);
+	default:
+		xfs_warn(mp, "zoned %u has unsupported type 0x%x.",
+			rtg_rgno(rtg), zone->type);
+		return false;
+	}
+}
diff --git a/fs/xfs/libxfs/xfs_zones.h b/fs/xfs/libxfs/xfs_zones.h
new file mode 100644
index 000000000000..c4f1367b2cca
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_zones.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIBXFS_ZONES_H
+#define _LIBXFS_ZONES_H
+
+struct xfs_rtgroup;
+
+/*
+ * In order to guarantee forward progress for GC we need to reserve at least
+ * two zones:  one that will be used for moving data into and one spare zone
+ * making sure that we have enough space to relocate a nearly-full zone.
+ * To allow for slightly sloppy accounting for when we need to reserve the
+ * second zone, we actually reserve three as that is easier than doing fully
+ * accurate bookkeeping.
+ */
+#define XFS_GC_ZONES		3U
+
+/*
+ * In addition we need two zones for user writes, one open zone for writing
+ * and one to still have available blocks without resetting the open zone
+ * when data in the open zone has been freed.
+ */
+#define XFS_RESERVED_ZONES	(XFS_GC_ZONES + 1)
+#define XFS_MIN_ZONES		(XFS_RESERVED_ZONES + 1)
+
+/*
+ * Always keep one zone out of the general open zone pool to allow for GC to
+ * happen while other writers are waiting for free space.
+ */
+#define XFS_OPEN_GC_ZONES	1U
+#define XFS_MIN_OPEN_ZONES	(XFS_OPEN_GC_ZONES + 1U)
+
+bool xfs_zone_validate(struct blk_zone *zone, struct xfs_rtgroup *rtg,
+	xfs_rgblock_t *write_pointer);
+
+#endif /* _LIBXFS_ZONES_H */