Merge tag 'xfs-6.15-merge' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Carlos Maiolino:

- XFS zoned allocator: Enables XFS to support zoned devices using its
real-time allocator

- Use folios/vmalloc for buffer cache backing memory

- Some code cleanups and bug fixes

* tag 'xfs-6.15-merge' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (70 commits)
xfs: remove the flags argument to xfs_buf_get_uncached
xfs: remove the flags argument to xfs_buf_read_uncached
xfs: remove xfs_buf_free_maps
xfs: remove xfs_buf_get_maps
xfs: call xfs_buf_alloc_backing_mem from _xfs_buf_alloc
xfs: remove unnecessary NULL check before kvfree()
xfs: don't wake zone space waiters without m_zone_info
xfs: don't increment m_generation for all errors in xfs_growfs_data
xfs: fix a missing unlock in xfs_growfs_data
xfs: Remove duplicate xfs_rtbitmap.h header
xfs: trigger zone GC when out of available rt blocks
xfs: trace what memory backs a buffer
xfs: cleanup mapping tmpfs folios into the buffer cache
xfs: use vmalloc instead of vm_map_area for buffer backing memory
xfs: buffer items don't straddle pages anymore
xfs: kill XBF_UNMAPPED
xfs: convert buffer cache to use high order folios
xfs: remove the kmalloc to page allocator fallback
xfs: refactor backing memory allocations for buffers
xfs: remove xfs_buf_is_vmapped
...

fs/xfs/Makefile

···
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix libxfs/, \
 				   xfs_rtbitmap.o \
 				   xfs_rtgroup.o \
+				   xfs_zones.o \
 				   )
 
 # highlevel code
···
 				   xfs_quotaops.o
 
 # xfs_rtbitmap is shared with libxfs
-xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o
+xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o \
+				   xfs_zone_alloc.o \
+				   xfs_zone_gc.o \
+				   xfs_zone_info.o \
+				   xfs_zone_space_resv.o
 
 xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o
 xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o

fs/xfs/libxfs/xfs_ag.c

···
 	struct xfs_buf		*bp;
 	int			error;
 
-	error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0, &bp);
+	error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, &bp);
 	if (error)
 		return error;
 

fs/xfs/libxfs/xfs_bmap.c

···
 #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;
 
···
  * 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++) {
···
 }
 
 /*
- * 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 */
···
 	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)
···
 	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);
···
 	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);
···
 
 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,

fs/xfs/libxfs/xfs_bmap.h

···
 		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);
···
 		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,
···
 		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,

fs/xfs/libxfs/xfs_format.h

···
 
 	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_ZONE_GAPS	(1 << 10) /* RTGs have LBA gaps */
+
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE | \
 		 XFS_SB_FEAT_INCOMPAT_SPINODES | \
···
 		 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
···
 	__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 */

fs/xfs/libxfs/xfs_fs.h

···
 	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 */
···
 #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.
···
 #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
 /*

fs/xfs/libxfs/xfs_group.h

···
 #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.
···
 	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;
 
-	return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno);
+	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, g->start_fsb + fsbno);
 }
 
 static inline uint32_t

fs/xfs/libxfs/xfs_ialloc.c

···
 				(j * M_IGEO(mp)->blocks_per_cluster));
 		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, d,
 				mp->m_bsize * M_IGEO(mp)->blocks_per_cluster,
-				XBF_UNMAPPED, &fbuf);
+				0, &fbuf);
 		if (error)
 			return error;
 
···
 	 * 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;

fs/xfs/libxfs/xfs_inode_buf.c

···
 	int			error;
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-			imap->im_len, XBF_UNMAPPED, bpp, &xfs_inode_buf_ops);
+			imap->im_len, 0, bpp, &xfs_inode_buf_ops);
 	if (xfs_metadata_is_sick(error))
 		xfs_agno_mark_sick(mp, xfs_daddr_to_agno(mp, imap->im_blkno),
 				XFS_SICK_AG_INODES);
···
 					   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) &&

fs/xfs/libxfs/xfs_inode_util.c

···
 
 	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;
 	}

fs/xfs/libxfs/xfs_log_format.h

···
 	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 */

fs/xfs/libxfs/xfs_metafile.c

···
 #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;
···
 }
 
 /*
- * 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)
 {
 	/*
···
 	 * 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;
+	trace_xfs_metafile_resv_critical(mp, 0);
 
-	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_critical(ip, 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. */
···
 	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);
···
 		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);
 }
···
 	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
···
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len);
 }
 
-/* Release a metadata file's space reservation. */
-void
-xfs_metafile_resv_free(
-	struct xfs_inode	*ip)
+static void
+__xfs_metafile_resv_free(
+	struct xfs_mount	*mp)
 {
-	/* Non-btree metadata inodes don't need space reservations. */
-	if (!ip || !ip->i_meta_resv_asked)
-		return;
-
-	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_free(ip, 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;
+	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);
 	}
-	ip->i_meta_resv_asked = 0;
+	mp->m_metafile_resv_avail = 0;
+	mp->m_metafile_resv_used = 0;
+	mp->m_metafile_resv_target = 0;
 }
 
-/* Set up a metadata file's space reservation. */
+/* Release unused metafile space reservation. */
+void
+xfs_metafile_resv_free(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_has_metadir(mp))
+		return;
+
+	trace_xfs_metafile_resv_free(mp, 0);
+
+	mutex_lock(&mp->m_metafile_resv_lock);
+	__xfs_metafile_resv_free(mp);
+	mutex_unlock(&mp->m_metafile_resv_lock);
+}
+
+/* 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);
 
 	/*
-	 * Space taken by all other metadata btrees are accounted on-disk as
+	 * 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 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);
 
-	trace_xfs_metafile_resv_init(ip, ask);
-	return 0;
+	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);
+
+out_unlock:
+	mutex_unlock(&mp->m_metafile_resv_lock);
+	return error;
 }

fs/xfs/libxfs/xfs_metafile.h

···
 /* 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. */
 

fs/xfs/libxfs/xfs_ondisk.h

···
 			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 */

fs/xfs/libxfs/xfs_rtbitmap.c

···
 	xfs_extlen_t		mod;
 	int			error;
 
+	ASSERT(!xfs_has_zoned(mp));
 	ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
 
 	mod = xfs_blen_to_rtxoff(mp, rtlen);
···
 		return 0;
 
 	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_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);

fs/xfs/libxfs/xfs_rtgroup.c

···
 	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);
 	}
···
 	/* 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;
 }
···
 		.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] = {

fs/xfs/libxfs/xfs_rtgroup.h

···
 	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)
 {
···
 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)
···
 	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
···
 	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;
 

fs/xfs/libxfs/xfs_rtrmap_btree.c

···
 	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);
+}

fs/xfs/libxfs/xfs_rtrmap_btree.h

···
 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__ */

fs/xfs/libxfs/xfs_sb.c

···
 		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(
···
 			}
 
 			error = xfs_validate_sb_rtgroups(mp, sbp);
+			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;
 		}
···
 		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);
+	}
 }
 
 /*
···
 		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;
···
 		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);
 	}
 
 	/*
···
 	 * 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);
···
 		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);
 
···
 	if (xfs_has_rtgroups(mp)) {
 		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;
 	}
 }
 

fs/xfs/libxfs/xfs_types.h

···
 	{ 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
  */

fs/xfs/libxfs/xfs_zones.c

···
+// 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;
+	}
+}

fs/xfs/libxfs/xfs_zones.h

···
+/* 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 */

fs/xfs/scrub/agheader.c

···
 xchk_superblock_ondisk_size(
 	struct xfs_mount	*mp)
 {
+	if (xfs_has_zoned(mp))
+		return offsetofend(struct xfs_dsb, sb_rtreserved);
 	if (xfs_has_metadir(mp))
 		return offsetofend(struct xfs_dsb, sb_pad);
 	if (xfs_has_metauuid(mp))

fs/xfs/scrub/bmap.c

···
 
 	switch (whichfork) {
 	case XFS_COW_FORK:
-		/* No CoW forks on non-reflink filesystems. */
-		if (!xfs_has_reflink(mp)) {
+		/* No CoW forks filesystem doesn't support out of place writes */
+		if (!xfs_has_reflink(mp) && !xfs_has_zoned(mp)) {
 			xchk_ino_set_corrupt(sc, sc->ip->i_ino);
 			return 0;
 		}

fs/xfs/scrub/fscounters.c

···
 	 * The global incore space reservation is taken from the incore
 	 * counters, so leave that out of the computation.
 	 */
-	fsc->fdblocks -= mp->m_resblks_avail;
+	fsc->fdblocks -= mp->m_free[XC_FREE_BLOCKS].res_avail;
 
 	/*
 	 * Delayed allocation reservations are taken out of the incore counters
···
 
 	fsc->frextents = 0;
 	fsc->frextents_delayed = 0;
-	if (!xfs_has_realtime(mp))
+
+	/*
+	 * Don't bother verifying and repairing the fs counters for zoned file
+	 * systems as they don't track an on-disk frextents count, and the
+	 * in-memory percpu counter also includes reservations.
+	 */
+	if (!xfs_has_realtime(mp) || xfs_has_zoned(mp))
 		return 0;
 
 	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
···
 	/* Snapshot the percpu counters. */
 	icount = percpu_counter_sum(&mp->m_icount);
 	ifree = percpu_counter_sum(&mp->m_ifree);
-	fdblocks = percpu_counter_sum(&mp->m_fdblocks);
-	frextents = percpu_counter_sum(&mp->m_frextents);
+	fdblocks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS);
+	frextents = xfs_sum_freecounter_raw(mp, XC_FREE_RTEXTENTS);
 
 	/* No negative values, please! */
 	if (icount < 0 || ifree < 0)
···
 			try_again = true;
 	}
 
-	if (!xchk_fscount_within_range(sc, fdblocks, &mp->m_fdblocks,
-			fsc->fdblocks)) {
+	if (!xchk_fscount_within_range(sc, fdblocks,
+			&mp->m_free[XC_FREE_BLOCKS].count, fsc->fdblocks)) {
 		if (fsc->frozen)
 			xchk_set_corrupt(sc);
 		else
 			try_again = true;
 	}
 
-	if (!xchk_fscount_within_range(sc, frextents, &mp->m_frextents,
+	if (!xfs_has_zoned(mp) &&
+	    !xchk_fscount_within_range(sc, frextents,
+			&mp->m_free[XC_FREE_RTEXTENTS].count,
 			fsc->frextents - fsc->frextents_delayed)) {
 		if (fsc->frozen)
 			xchk_set_corrupt(sc);

fs/xfs/scrub/fscounters_repair.c

···
 
 	percpu_counter_set(&mp->m_icount, fsc->icount);
 	percpu_counter_set(&mp->m_ifree, fsc->ifree);
-	percpu_counter_set(&mp->m_fdblocks, fsc->fdblocks);
+	xfs_set_freecounter(mp, XC_FREE_BLOCKS, fsc->fdblocks);
 
 	/*
 	 * Online repair is only supported on v5 file systems, which require
···
 	 * track of the delalloc reservations separately, as they are are
 	 * subtracted from m_frextents, but not included in sb_frextents.
 	 */
-	percpu_counter_set(&mp->m_frextents,
-		fsc->frextents - fsc->frextents_delayed);
-	if (!xfs_has_rtgroups(mp))
-		mp->m_sb.sb_frextents = fsc->frextents;
+	if (!xfs_has_zoned(mp)) {
+		xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
+				fsc->frextents - fsc->frextents_delayed);
+		if (!xfs_has_rtgroups(mp))
+			mp->m_sb.sb_frextents = fsc->frextents;
+	}
 
 	return 0;
 }

fs/xfs/scrub/inode.c

···
 	xfs_failaddr_t		fa;
 	uint32_t		value = be32_to_cpu(dip->di_cowextsize);
 
+	/*
+	 * The used block counter for rtrmap is checked and repaired elsewhere.
+	 */
+	if (xfs_has_zoned(sc->mp) &&
+	    dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP))
+		return;
+
 	fa = xfs_inode_validate_cowextsize(sc->mp, value, mode, flags, flags2);
 	if (fa)
 		xchk_ino_set_corrupt(sc, ino);

fs/xfs/scrub/inode_repair.c

···
 					      XFS_DIFLAG_EXTSZINHERIT);
 	}
 
-	if (dip->di_version < 3)
+	if (dip->di_version < 3 ||
+	    (xfs_has_zoned(sc->mp) &&
+	     dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)))
 		return;
 
 	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
···
 
 	/* Read the inode cluster buffer. */
 	error = xfs_trans_read_buf(sc->mp, sc->tp, sc->mp->m_ddev_targp,
-			ri->imap.im_blkno, ri->imap.im_len, XBF_UNMAPPED, &bp,
-			NULL);
+			ri->imap.im_blkno, ri->imap.im_len, 0, &bp, NULL);
 	if (error)
 		return error;
 

fs/xfs/scrub/newbt.c

···
 		free = sc->sa.pag->pagf_freeblks;
 		sz = xfs_ag_block_count(sc->mp, pag_agno(sc->sa.pag));
 	} else {
-		free = percpu_counter_sum(&sc->mp->m_fdblocks);
+		free = xfs_sum_freecounter_raw(sc->mp, XC_FREE_BLOCKS);
 		sz = sc->mp->m_sb.sb_dblocks;
 	}
 

fs/xfs/scrub/reap.c

···
 	if (error)
 		return error;
 
-	if (xreap_dirty(&rs))
-		return xrep_defer_finish(sc);
+	if (xreap_dirty(&rs)) {
+		error = xrep_defer_finish(sc);
+		if (error)
+			return error;
+	}
 
-	return 0;
+	return xrep_reset_metafile_resv(sc);
 }
 
 /*

fs/xfs/scrub/repair.c

···
 #include "xfs_rtalloc.h"
 #include "xfs_metafile.h"
 #include "xfs_rtrefcount_btree.h"
+#include "xfs_zone_alloc.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/trace.h"
···
 	xfs_rtxnum_t		startrtx;
 	xfs_rtxnum_t		endrtx;
 	bool			is_free = false;
-	int			error;
+	int			error = 0;
+
+	if (xfs_has_zoned(mp)) {
+		if (!xfs_zone_rgbno_is_valid(sc->sr.rtg, rgbno + len - 1))
+			return -EFSCORRUPTED;
+		return 0;
+	}
 
 	startrtx = xfs_rgbno_to_rtx(mp, rgbno);
 	endrtx = xfs_rgbno_to_rtx(mp, rgbno + len - 1);
···
 xrep_reset_metafile_resv(
 	struct xfs_scrub	*sc)
 {
-	struct xfs_inode	*ip = sc->ip;
+	struct xfs_mount	*mp = sc->mp;
 	int64_t			delta;
 	int			error;
 
-	delta = ip->i_nblocks + ip->i_delayed_blks - ip->i_meta_resv_asked;
+	delta = mp->m_metafile_resv_used + mp->m_metafile_resv_avail -
+		mp->m_metafile_resv_target;
 	if (delta == 0)
 		return 0;
 
···
 	if (delta > 0) {
 		int64_t		give_back;
 
-		give_back = min_t(uint64_t, delta, ip->i_delayed_blks);
+		give_back = min_t(uint64_t, delta, mp->m_metafile_resv_avail);
 		if (give_back > 0) {
-			xfs_mod_delalloc(ip, 0, -give_back);
-			xfs_add_fdblocks(ip->i_mount, give_back);
-			ip->i_delayed_blks -= give_back;
+			xfs_mod_sb_delalloc(mp, -give_back);
+			xfs_add_fdblocks(mp, give_back);
+			mp->m_metafile_resv_avail -= give_back;
 		}
 
 		return 0;
···
 
 	/*
 	 * Not enough reservation; try to take some blocks from the filesystem
-	 * to the metadata inode.  @delta is negative here, so invert the sign.
+	 * to the metabtree reservation.
 	 */
-	delta = -delta;
-	error = xfs_dec_fdblocks(sc->mp, delta, true);
+	delta = -delta; /* delta is negative here, so invert the sign. */
+	error = xfs_dec_fdblocks(mp, delta, true);
 	while (error == -ENOSPC) {
 		delta--;
 		if (delta == 0) {
 			xfs_warn(sc->mp,
-"Insufficient free space to reset space reservation for inode 0x%llx after repair.",
-					ip->i_ino);
+"Insufficient free space to reset metabtree reservation after repair.");
 			return 0;
 		}
-		error = xfs_dec_fdblocks(sc->mp, delta, true);
+		error = xfs_dec_fdblocks(mp, delta, true);
 	}
 	if (error)
 		return error;
 
-	xfs_mod_delalloc(ip, 0, delta);
-	ip->i_delayed_blks += delta;
+	xfs_mod_sb_delalloc(mp, delta);
+	mp->m_metafile_resv_avail += delta;
 	return 0;
 }

fs/xfs/scrub/rtbitmap.c

···
 #include "xfs_rmap.h"
 #include "xfs_rtrmap_btree.h"
 #include "xfs_exchmaps.h"
+#include "xfs_zone_alloc.h"
 #include "scrub/scrub.h"
 #include "scrub/common.h"
 #include "scrub/repair.h"
···
 	xfs_extlen_t		len)
 {
 	struct xfs_rtgroup	*rtg = sc->sr.rtg;
-	struct xfs_inode	*rbmip = rtg_bitmap(rtg);
 	xfs_rtxnum_t		startext;
 	xfs_rtxnum_t		endext;
 	bool			is_free;
···
 	if (xchk_skip_xref(sc->sm))
 		return;
 
+	if (xfs_has_zoned(sc->mp)) {
+		if (!xfs_zone_rgbno_is_valid(rtg,
+				xfs_rtb_to_rgbno(sc->mp, rtbno) + len - 1))
+			xchk_ino_xref_set_corrupt(sc, rtg_rmap(rtg)->i_ino);
+		return;
+	}
+
 	startext = xfs_rtb_to_rtx(sc->mp, rtbno);
 	endext = xfs_rtb_to_rtx(sc->mp, rtbno + len - 1);
 	error = xfs_rtalloc_extent_is_free(rtg, sc->tp, startext,
···
 	if (!xchk_should_check_xref(sc, &error, NULL))
 		return;
 	if (is_free)
-		xchk_ino_xref_set_corrupt(sc, rbmip->i_ino);
+		xchk_ino_xref_set_corrupt(sc, rtg_bitmap(rtg)->i_ino);
 }

fs/xfs/scrub/rtrefcount_repair.c

···
 	return error;
 }
 
-/*
- * Now that we've logged the roots of the new btrees, invalidate all of the
- * old blocks and free them.
- */
-STATIC int
-xrep_rtrefc_remove_old_tree(
-	struct xrep_rtrefc	*rr)
-{
-	int			error;
-
-	/*
-	 * Free all the extents that were allocated to the former rtrefcountbt
-	 * and aren't cross-linked with something else.
-	 */
-	error = xrep_reap_metadir_fsblocks(rr->sc,
-			&rr->old_rtrefcountbt_blocks);
-	if (error)
-		return error;
-
-	/*
-	 * Ensure the proper reservation for the rtrefcount inode so that we
-	 * don't fail to expand the btree.
-	 */
-	return xrep_reset_metafile_resv(rr->sc);
-}
-
 /* Rebuild the rt refcount btree. */
 int
 xrep_rtrefcountbt(
···
 	if (error)
 		goto out_bitmap;
 
-	/* Kill the old tree. */
-	error = xrep_rtrefc_remove_old_tree(rr);
+	/*
+	 * Free all the extents that were allocated to the former rtrefcountbt
+	 * and aren't cross-linked with something else.
+	 */
+	error = xrep_reap_metadir_fsblocks(rr->sc,
+			&rr->old_rtrefcountbt_blocks);
 	if (error)
 		goto out_bitmap;
 

fs/xfs/scrub/rtrmap_repair.c

···
 
 /* Reaping the old btree. */
 
-/* Reap the old rtrmapbt blocks. */
-STATIC int
-xrep_rtrmap_remove_old_tree(
-	struct xrep_rtrmap	*rr)
-{
-	int			error;
-
-	/*
-	 * Free all the extents that were allocated to the former rtrmapbt and
-	 * aren't cross-linked with something else.
-	 */
-	error = xrep_reap_metadir_fsblocks(rr->sc, &rr->old_rtrmapbt_blocks);
-	if (error)
-		return error;
-
-	/*
-	 * Ensure the proper reservation for the rtrmap inode so that we don't
-	 * fail to expand the new btree.
-	 */
-	return xrep_reset_metafile_resv(rr->sc);
-}
-
 static inline bool
 xrep_rtrmapbt_want_live_update(
 	struct xchk_iscan		*iscan,
···
 	if (error)
 		goto out_records;
 
-	/* Kill the old tree. */
-	error = xrep_rtrmap_remove_old_tree(rr);
+	/*
+	 * Free all the extents that were allocated to the former rtrmapbt and
+	 * aren't cross-linked with something else.
+	 */
+	error = xrep_reap_metadir_fsblocks(rr->sc, &rr->old_rtrmapbt_blocks);
 	if (error)
 		goto out_records;
 

fs/xfs/scrub/scrub.c

···
 	},
 	[XFS_SCRUB_TYPE_RTBITMAP] = {	/* realtime bitmap */
 		.type	= ST_RTGROUP,
+		.has	= xfs_has_nonzoned,
 		.setup	= xchk_setup_rtbitmap,
 		.scrub	= xchk_rtbitmap,
 		.repair	= xrep_rtbitmap,
 	},
 	[XFS_SCRUB_TYPE_RTSUM] = {	/* realtime summary */
 		.type	= ST_RTGROUP,
+		.has	= xfs_has_nonzoned,
 		.setup	= xchk_setup_rtsummary,
 		.scrub	= xchk_rtsummary,
 		.repair	= xrep_rtsummary,

fs/xfs/xfs_aops.c

···
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (c) 2000-2005 Silicon Graphics, Inc.
- * Copyright (c) 2016-2018 Christoph Hellwig.
+ * Copyright (c) 2016-2025 Christoph Hellwig.
  * All Rights Reserved.
  */
 #include "xfs.h"
···
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_icache.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_rtgroup.h"
 
 struct xfs_writepage_ctx {
 	struct iomap_writepage_ctx ctx;
···
 	return xfs_trans_commit(tp);
 }
 
+static void
+xfs_ioend_put_open_zones(
+	struct iomap_ioend	*ioend)
+{
+	struct iomap_ioend *tmp;
+
+	/*
+	 * Put the open zone for all ioends merged into this one (if any).
+	 */
+	list_for_each_entry(tmp, &ioend->io_list, io_list)
+		xfs_open_zone_put(tmp->io_private);
+
+	/*
+	 * The main ioend might not have an open zone if the submission failed
+	 * before xfs_zone_alloc_and_submit got called.
+	 */
+	if (ioend->io_private)
+		xfs_open_zone_put(ioend->io_private);
+}
+
 /*
  * IO write completion.
  */
···
 {
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	struct xfs_mount	*mp = ip->i_mount;
+	bool			is_zoned = xfs_is_zoned_inode(ip);
 	xfs_off_t		offset = ioend->io_offset;
 	size_t			size = ioend->io_size;
 	unsigned int		nofs_flag;
···
 	error = blk_status_to_errno(ioend->io_bio.bi_status);
 	if (unlikely(error)) {
 		if (ioend->io_flags & IOMAP_IOEND_SHARED) {
+			ASSERT(!is_zoned);
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
 			xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset,
-					offset + size);
+					offset + size, NULL);
 		}
 		goto done;
 	}
···
 	/*
 	 * Success: commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_flags & IOMAP_IOEND_SHARED)
+	if (is_zoned)
+		error = xfs_zoned_end_io(ip, offset, size, ioend->io_sector,
+				ioend->io_private, NULLFSBLOCK);
+	else if (ioend->io_flags & IOMAP_IOEND_SHARED)
 		error = xfs_reflink_end_cow(ip, offset, size);
 	else if (ioend->io_flags & IOMAP_IOEND_UNWRITTEN)
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
 
-	if (!error && xfs_ioend_is_append(ioend))
+	if (!error &&
+	    !(ioend->io_flags & IOMAP_IOEND_DIRECT) &&
+	    xfs_ioend_is_append(ioend))
 		error = xfs_setfilesize(ip, offset, size);
 done:
+	if (is_zoned)
+		xfs_ioend_put_open_zones(ioend);
 	iomap_finish_ioends(ioend, error);
 	memalloc_nofs_restore(nofs_flag);
 }
···
 	}
 }
 
-STATIC void
+void
 xfs_end_bio(
 	struct bio		*bio)
 {
 	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	struct xfs_mount	*mp = ip->i_mount;
 	unsigned long		flags;
+
+	/*
+	 * For Appends record the actually written block number and set the
+	 * boundary flag if needed.
+	 */
+	if (IS_ENABLED(CONFIG_XFS_RT) && bio_is_zone_append(bio)) {
+		ioend->io_sector = bio->bi_iter.bi_sector;
+		xfs_mark_rtg_boundary(ioend);
+	}
 
 	spin_lock_irqsave(&ip->i_ioend_lock, flags);
 	if (list_empty(&ip->i_ioend_list))
-		WARN_ON_ONCE(!queue_work(ip->i_mount->m_unwritten_workqueue,
+		WARN_ON_ONCE(!queue_work(mp->m_unwritten_workqueue,
 					 &ip->i_ioend_work));
 	list_add_tail(&ioend->io_list, &ip->i_ioend_list);
 	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
···
 	 * folio itself and not the start offset that is passed in.
 	 */
 	xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
-				folio_pos(folio) + folio_size(folio));
+				folio_pos(folio) + folio_size(folio), NULL);
 }
 
 static const struct iomap_writeback_ops xfs_writeback_ops = {
···
 	.discard_folio		= xfs_discard_folio,
 };
 
+struct xfs_zoned_writepage_ctx {
+	struct iomap_writepage_ctx	ctx;
+	struct xfs_open_zone		*open_zone;
+};
+
+static inline struct xfs_zoned_writepage_ctx *
+XFS_ZWPC(struct iomap_writepage_ctx *ctx)
+{
+	return container_of(ctx, struct xfs_zoned_writepage_ctx, ctx);
+}
+
+static int
+xfs_zoned_map_blocks(
+	struct iomap_writepage_ctx *wpc,
+	struct inode		*inode,
+	loff_t			offset,
+	unsigned int		len)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + len);
+	xfs_filblks_t		count_fsb;
+	struct xfs_bmbt_irec	imap, del;
+	struct xfs_iext_cursor	icur;
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS);
+
+	/*
+	 * All dirty data must be covered by delalloc extents.  But truncate can
+	 * remove delalloc extents underneath us or reduce their size.
+	 * Returning a hole tells iomap to not write back any data from this
+	 * range, which is the right thing to do in that case.
+	 *
+	 * Otherwise just tell iomap to treat ranges previously covered by a
+	 * delalloc extent as mapped.  The actual block allocation will be done
+	 * just before submitting the bio.
+	 *
+	 * This implies we never map outside folios that are locked or marked
+	 * as under writeback, and thus there is no need check the fork sequence
+	 * count here.
+	 */
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
+		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
+	if (imap.br_startoff > offset_fsb) {
+		imap.br_blockcount = imap.br_startoff - offset_fsb;
+		imap.br_startoff = offset_fsb;
+		imap.br_startblock = HOLESTARTBLOCK;
+		imap.br_state = XFS_EXT_NORM;
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, 0);
+		return 0;
+	}
+	end_fsb = min(end_fsb, imap.br_startoff + imap.br_blockcount);
+	count_fsb = end_fsb - offset_fsb;
+
+	del = imap;
+	xfs_trim_extent(&del, offset_fsb, count_fsb);
+	xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &icur, &imap, &del,
+			XFS_BMAPI_REMAP);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+
+	wpc->iomap.type = IOMAP_MAPPED;
+	wpc->iomap.flags = IOMAP_F_DIRTY;
+	wpc->iomap.bdev = mp->m_rtdev_targp->bt_bdev;
+	wpc->iomap.offset = offset;
+	wpc->iomap.length = XFS_FSB_TO_B(mp, count_fsb);
+	wpc->iomap.flags = IOMAP_F_ANON_WRITE;
+
+	trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length);
+	return 0;
+}
+
+static int
+xfs_zoned_submit_ioend(
+	struct iomap_writepage_ctx *wpc,
+	int			status)
+{
+	wpc->ioend->io_bio.bi_end_io = xfs_end_bio;
+	if (status)
+		return status;
+	xfs_zone_alloc_and_submit(wpc->ioend, &XFS_ZWPC(wpc)->open_zone);
+	return 0;
+}
+
+static const struct iomap_writeback_ops xfs_zoned_writeback_ops = {
+	.map_blocks		= xfs_zoned_map_blocks,
+	.submit_ioend		= xfs_zoned_submit_ioend,
+	.discard_folio		= xfs_discard_folio,
+};
+
 STATIC int
 xfs_vm_writepages(
 	struct address_space	*mapping,
 	struct writeback_control *wbc)
 {
-	struct xfs_writepage_ctx wpc = { };
+	struct xfs_inode	*ip = XFS_I(mapping->host);
 
-	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
-	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
+	xfs_iflags_clear(ip, XFS_ITRUNCATED);
+
+	if (xfs_is_zoned_inode(ip)) {
+		struct xfs_zoned_writepage_ctx	xc = { };
+		int				error;
+
+		error = iomap_writepages(mapping, wbc, &xc.ctx,
+					 &xfs_zoned_writeback_ops);
+		if (xc.open_zone)
+			xfs_open_zone_put(xc.open_zone);
+		return error;
+	} else {
+		struct xfs_writepage_ctx	wpc = { };
+
+		return iomap_writepages(mapping, wbc, &wpc.ctx,
+				&xfs_writeback_ops);
+	}
 }
 
 STATIC int

fs/xfs/xfs_aops.h

···
 extern const struct address_space_operations xfs_address_space_operations;
 extern const struct address_space_operations xfs_dax_aops;
 
-int	xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);
+int xfs_setfilesize(struct xfs_inode *ip, xfs_off_t offset, size_t size);
+void xfs_end_bio(struct bio *bio);
 
 #endif /* __XFS_AOPS_H__ */

fs/xfs/xfs_bmap_util.c

···
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
 
 /* Kernel only BMAP related definitions and functions */
 
···
 	struct xfs_inode	*ip,
 	int			whichfork,
 	xfs_off_t		start_byte,
-	xfs_off_t		end_byte)
+	xfs_off_t		end_byte,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
···
 			continue;
 		}
 
-		xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del);
+		if (xfs_is_zoned_inode(ip) && ac) {
+			/*
+			 * In a zoned buffered write context we need to return
+			 * the punched delalloc allocations to the allocation
+			 * context.  This allows reusing them in the following
+			 * iomap iterations.
+			 */
+			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,
+					&del, XFS_BMAPI_REMAP);
+			ac->reserved_blocks += del.br_blockcount;
+		} else {
+			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,
+					&del, 0);
+		}
+
 		if (!xfs_iext_get_extent(ifp, &icur, &got))
 			break;
 	}
···
 		if (ip->i_delayed_blks) {
 			xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK,
 				round_up(XFS_ISIZE(ip), mp->m_sb.sb_blocksize),
-				LLONG_MAX);
+				LLONG_MAX, NULL);
 		}
 		xfs_inode_clear_eofblocks_tag(ip);
 		return 0;
···
 xfs_free_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len)
+	xfs_off_t		len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		startoffset_fsb;
···
 		return 0;
 	if (offset + len > XFS_ISIZE(ip))
 		len = XFS_ISIZE(ip) - offset;
-	error = xfs_zero_range(ip, offset, len, NULL);
+	error = xfs_zero_range(ip, offset, len, ac, NULL);
 	if (error)
 		return error;
 
···
 xfs_collapse_file_space(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		len)
+	xfs_off_t		len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_trans	*tp;
···
 
 	trace_xfs_collapse_file_space(ip);
 
-	error = xfs_free_file_space(ip, offset, len);
+	error = xfs_free_file_space(ip, offset, len, ac);
 	if (error)
 		return error;
 

fs/xfs/xfs_bmap_util.h

···
 struct xfs_mount;
 struct xfs_trans;
 struct xfs_bmalloca;
+struct xfs_zone_alloc_ctx;
 
 #ifdef CONFIG_XFS_RT
 int	xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
···
 #endif /* CONFIG_XFS_RT */
 
 void	xfs_bmap_punch_delalloc_range(struct xfs_inode *ip, int whichfork,
-		xfs_off_t start_byte, xfs_off_t end_byte);
+		xfs_off_t start_byte, xfs_off_t end_byte,
+		struct xfs_zone_alloc_ctx *ac);
 
 struct kgetbmap {
 	__s64		bmv_offset;	/* file offset of segment in blocks */
···
 
 /* preallocation and hole punch interface */
 int	xfs_alloc_file_space(struct xfs_inode *ip, xfs_off_t offset,
-			     xfs_off_t len);
+		xfs_off_t len);
 int	xfs_free_file_space(struct xfs_inode *ip, xfs_off_t offset,
-			    xfs_off_t len);
+		xfs_off_t len, struct xfs_zone_alloc_ctx *ac);
 int	xfs_collapse_file_space(struct xfs_inode *, xfs_off_t offset,
-				xfs_off_t len);
+		xfs_off_t len, struct xfs_zone_alloc_ctx *ac);
 int	xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
-				xfs_off_t len);
+		xfs_off_t len);
 
 /* EOF block manipulation functions */
 bool	xfs_can_free_eofblocks(struct xfs_inode *ip);

fs/xfs/xfs_buf.c

···
 	return bp->b_rhash_key == XFS_BUF_DADDR_NULL;
 }
 
-static inline int
-xfs_buf_is_vmapped(
-	struct xfs_buf	*bp)
-{
-	/*
-	 * Return true if the buffer is vmapped.
-	 *
-	 * b_addr is null if the buffer is not mapped, but the code is clever
-	 * enough to know it doesn't have to map a single page, so the check has
-	 * to be both for b_addr and bp->b_page_count > 1.
-	 */
-	return bp->b_addr && bp->b_page_count > 1;
-}
-
-static inline int
-xfs_buf_vmap_len(
-	struct xfs_buf	*bp)
-{
-	return (bp->b_page_count * PAGE_SIZE);
-}
-
 /*
  * When we mark a buffer stale, we remove the buffer from the LRU and clear the
  * b_lru_ref count so that the buffer is freed immediately when the buffer
···
 	spin_unlock(&bp->b_lock);
 }
 
-static int
-xfs_buf_get_maps(
-	struct xfs_buf		*bp,
-	int			map_count)
+static void
+xfs_buf_free_callback(
+	struct callback_head	*cb)
 {
-	ASSERT(bp->b_maps == NULL);
-	bp->b_map_count = map_count;
+	struct xfs_buf		*bp = container_of(cb, struct xfs_buf, b_rcu);
 
-	if (map_count == 1) {
-		bp->b_maps = &bp->__b_map;
-		return 0;
-	}
-
-	bp->b_maps = kzalloc(map_count * sizeof(struct xfs_buf_map),
-			GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
-	if (!bp->b_maps)
-		return -ENOMEM;
-	return 0;
+	if (bp->b_maps != &bp->__b_map)
+		kfree(bp->b_maps);
+	kmem_cache_free(xfs_buf_cache, bp);
 }
 
 static void
-xfs_buf_free_maps(
-	struct xfs_buf	*bp)
+xfs_buf_free(
+	struct xfs_buf		*bp)
 {
-	if (bp->b_maps != &bp->__b_map) {
-		kfree(bp->b_maps);
-		bp->b_maps = NULL;
-	}
+	unsigned int		size = BBTOB(bp->b_length);
+
+	trace_xfs_buf_free(bp, _RET_IP_);
+
+	ASSERT(list_empty(&bp->b_lru));
+
+	if (!xfs_buftarg_is_mem(bp->b_target) && size >= PAGE_SIZE)
+		mm_account_reclaimed_pages(howmany(size, PAGE_SHIFT));
+
+	if (is_vmalloc_addr(bp->b_addr))
+		vfree(bp->b_addr);
+	else if (bp->b_flags & _XBF_KMEM)
+		kfree(bp->b_addr);
+	else
+		folio_put(virt_to_folio(bp->b_addr));
+
+	call_rcu(&bp->b_rcu, xfs_buf_free_callback);
 }
 
 static int
-_xfs_buf_alloc(
+xfs_buf_alloc_kmem(
+	struct xfs_buf		*bp,
+	size_t			size,
+	gfp_t			gfp_mask)
+{
+	ASSERT(is_power_of_2(size));
+	ASSERT(size < PAGE_SIZE);
+
+	bp->b_addr = kmalloc(size, gfp_mask | __GFP_NOFAIL);
+	if (!bp->b_addr)
+		return -ENOMEM;
+
+	/*
+	 * Slab guarantees that we get back naturally aligned allocations for
+	 * power of two sizes.  Keep this check as the canary in the coal mine
+	 * if anything changes in slab.
+	 */
+	if (WARN_ON_ONCE(!IS_ALIGNED((unsigned long)bp->b_addr, size))) {
+		kfree(bp->b_addr);
+		bp->b_addr = NULL;
+		return -ENOMEM;
+	}
+	bp->b_flags |= _XBF_KMEM;
+	trace_xfs_buf_backing_kmem(bp, _RET_IP_);
+	return 0;
+}
+
+/*
+ * Allocate backing memory for a buffer.
+ *
+ * For tmpfs-backed buffers used by in-memory btrees this directly maps the
+ * tmpfs page cache folios.
+ *
+ * For real file system buffers there are three different kinds backing memory:
+ *
+ * The first type backs the buffer by a kmalloc allocation.  This is done for
+ * less than PAGE_SIZE allocations to avoid wasting memory.
+ *
+ * The second type is a single folio buffer - this may be a high order folio or
+ * just a single page sized folio, but either way they get treated the same way
+ * by the rest of the code - the buffer memory spans a single contiguous memory
+ * region that we don't have to map and unmap to access the data directly.
+ *
+ * The third type of buffer is the vmalloc()d buffer. This provides the buffer
+ * with the required contiguous memory region but backed by discontiguous
+ * physical pages.
+ */
+static int
+xfs_buf_alloc_backing_mem(
+	struct xfs_buf	*bp,
+	xfs_buf_flags_t	flags)
+{
+	size_t		size = BBTOB(bp->b_length);
+	gfp_t		gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN;
+	struct folio	*folio;
+
+	if (xfs_buftarg_is_mem(bp->b_target))
+		return xmbuf_map_backing_mem(bp);
+
+	/* Assure zeroed buffer for non-read cases. */
+	if (!(flags & XBF_READ))
+		gfp_mask |= __GFP_ZERO;
+
+	if (flags & XBF_READ_AHEAD)
+		gfp_mask |= __GFP_NORETRY;
+
+	/*
+	 * For buffers smaller than PAGE_SIZE use a kmalloc allocation if that
+	 * is properly aligned.  The slab allocator now guarantees an aligned
+	 * allocation for all power of two sizes, which matches most of the
+	 * smaller than PAGE_SIZE buffers used by XFS.
+	 */
+	if (size < PAGE_SIZE && is_power_of_2(size))
+		return xfs_buf_alloc_kmem(bp, size, gfp_mask);
+
+	/*
+	 * Don't bother with the retry loop for single PAGE allocations: vmalloc
+	 * won't do any better.
+	 */
+	if (size <= PAGE_SIZE)
+		gfp_mask |= __GFP_NOFAIL;
+
+	/*
+	 * Optimistically attempt a single high order folio allocation for
+	 * larger than PAGE_SIZE buffers.
+	 *
+	 * Allocating a high order folio makes the assumption that buffers are a
+	 * power-of-2 size, matching the power-of-2 folios sizes available.
+	 *
+	 * The exception here are user xattr data buffers, which can be arbitrarily
+	 * sized up to 64kB plus structure metadata, skip straight to the vmalloc
+	 * path for them instead of wasting memory here.
+	 */
+	if (size > PAGE_SIZE) {
+		if (!is_power_of_2(size))
+			goto fallback;
+		gfp_mask &= ~__GFP_DIRECT_RECLAIM;
+		gfp_mask |= __GFP_NORETRY;
+	}
+	folio = folio_alloc(gfp_mask, get_order(size));
+	if (!folio) {
+		if (size <= PAGE_SIZE)
+			return -ENOMEM;
+		trace_xfs_buf_backing_fallback(bp, _RET_IP_);
+		goto fallback;
+	}
+	bp->b_addr = folio_address(folio);
+	trace_xfs_buf_backing_folio(bp, _RET_IP_);
+	return 0;
+
+fallback:
+	for (;;) {
+		bp->b_addr = __vmalloc(size, gfp_mask);
+		if (bp->b_addr)
+			break;
+		if (flags & XBF_READ_AHEAD)
+			return -ENOMEM;
+		XFS_STATS_INC(bp->b_mount, xb_page_retries);
+		memalloc_retry_wait(gfp_mask);
+	}
+
+	trace_xfs_buf_backing_vmalloc(bp, _RET_IP_);
+	return 0;
+}
+
+static int
+xfs_buf_alloc(
 	struct xfs_buftarg	*target,
 	struct xfs_buf_map	*map,
 	int			nmaps,
···
 	 * We don't want certain flags to appear in b_flags unless they are
 	 * specifically set by later operations on the buffer.
 	 */
-	flags &= ~(XBF_UNMAPPED | XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
+	flags &= ~(XBF_TRYLOCK | XBF_ASYNC | XBF_READ_AHEAD);
 
 	/*
 	 * A new buffer is held and locked by the owner.  This ensures that the
···
 	bp->b_target = target;
 	bp->b_mount = target->bt_mount;
 	bp->b_flags = flags;
-
-	error = xfs_buf_get_maps(bp, nmaps);
-	if (error)  {
-		kmem_cache_free(xfs_buf_cache, bp);
-		return error;
-	}
-
 	bp->b_rhash_key = map[0].bm_bn;
 	bp->b_length = 0;
+	bp->b_map_count = nmaps;
+	if (nmaps == 1)
+		bp->b_maps = &bp->__b_map;
+	else
+		bp->b_maps = kcalloc(nmaps, sizeof(struct xfs_buf_map),
+				GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL);
 	for (i = 0; i < nmaps; i++) {
 		bp->b_maps[i].bm_bn = map[i].bm_bn;
 		bp->b_maps[i].bm_len = map[i].bm_len;
···
 	XFS_STATS_INC(bp->b_mount, xb_create);
 	trace_xfs_buf_init(bp, _RET_IP_);
 
+	error = xfs_buf_alloc_backing_mem(bp, flags);
+	if (error) {
+		xfs_buf_free(bp);
+		return error;
+	}
+
 	*bpp = bp;
-	return 0;
-}
-
-static void
-xfs_buf_free_pages(
-	struct xfs_buf	*bp)
-{
-	uint		i;
-
-	ASSERT(bp->b_flags & _XBF_PAGES);
-
-	if (xfs_buf_is_vmapped(bp))
-		vm_unmap_ram(bp->b_addr, bp->b_page_count);
-
-	for (i = 0; i < bp->b_page_count; i++) {
-		if (bp->b_pages[i])
-			__free_page(bp->b_pages[i]);
-	}
-	mm_account_reclaimed_pages(bp->b_page_count);
-
-	if (bp->b_pages != bp->b_page_array)
-		kfree(bp->b_pages);
-	bp->b_pages = NULL;
-	bp->b_flags &= ~_XBF_PAGES;
-}
-
-static void
-xfs_buf_free_callback(
-	struct callback_head	*cb)
-{
-	struct xfs_buf		*bp = container_of(cb, struct xfs_buf, b_rcu);
-
-	xfs_buf_free_maps(bp);
-	kmem_cache_free(xfs_buf_cache, bp);
-}
-
-static void
-xfs_buf_free(
-	struct xfs_buf		*bp)
-{
-	trace_xfs_buf_free(bp, _RET_IP_);
-
-	ASSERT(list_empty(&bp->b_lru));
-
-	if (xfs_buftarg_is_mem(bp->b_target))
-		xmbuf_unmap_page(bp);
-	else if (bp->b_flags & _XBF_PAGES)
-		xfs_buf_free_pages(bp);
-	else if (bp->b_flags & _XBF_KMEM)
-		kfree(bp->b_addr);
-
-	call_rcu(&bp->b_rcu, xfs_buf_free_callback);
-}
-
-static int
-xfs_buf_alloc_kmem(
-	struct xfs_buf	*bp,
-	xfs_buf_flags_t	flags)
-{
-	gfp_t		gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOFAIL;
-	size_t		size = BBTOB(bp->b_length);
-
-	/* Assure zeroed buffer for non-read cases. */
-	if (!(flags & XBF_READ))
-		gfp_mask |= __GFP_ZERO;
-
-	bp->b_addr = kmalloc(size, gfp_mask);
-	if (!bp->b_addr)
-		return -ENOMEM;
-
-	if (((unsigned long)(bp->b_addr + size - 1) & PAGE_MASK) !=
-	    ((unsigned long)bp->b_addr & PAGE_MASK)) {
-		/* b_addr spans two pages - use alloc_page instead */
-		kfree(bp->b_addr);
-		bp->b_addr = NULL;
-		return -ENOMEM;
-	}
-	bp->b_offset = offset_in_page(bp->b_addr);
-	bp->b_pages = bp->b_page_array;
-	bp->b_pages[0] = kmem_to_page(bp->b_addr);
-	bp->b_page_count = 1;
-	bp->b_flags |= _XBF_KMEM;
-	return 0;
-}
-
-static int
-xfs_buf_alloc_pages(
-	struct xfs_buf	*bp,
-	xfs_buf_flags_t	flags)
-{
-	gfp_t		gfp_mask = GFP_KERNEL | __GFP_NOLOCKDEP | __GFP_NOWARN;
-	long		filled = 0;
-
-	if (flags & XBF_READ_AHEAD)
-		gfp_mask |= __GFP_NORETRY;
-
-	/* Make sure that we have a page list */
-	bp->b_page_count = DIV_ROUND_UP(BBTOB(bp->b_length), PAGE_SIZE);
-	if (bp->b_page_count <= XB_PAGES) {
-		bp->b_pages = bp->b_page_array;
-	} else {
-		bp->b_pages = kzalloc(sizeof(struct page *) * bp->b_page_count,
-					gfp_mask);
-		if (!bp->b_pages)
-			return -ENOMEM;
-	}
-	bp->b_flags |= _XBF_PAGES;
-
-	/* Assure zeroed buffer for non-read cases. */
-	if (!(flags & XBF_READ))
-		gfp_mask |= __GFP_ZERO;
-
-	/*
-	 * Bulk filling of pages can take multiple calls. Not filling the entire
-	 * array is not an allocation failure, so don't back off if we get at
-	 * least one extra page.
-	 */
-	for (;;) {
-		long	last = filled;
-
-		filled = alloc_pages_bulk(gfp_mask, bp->b_page_count,
-					  bp->b_pages);
-		if (filled == bp->b_page_count) {
-			XFS_STATS_INC(bp->b_mount, xb_page_found);
-			break;
-		}
-
-		if (filled != last)
-			continue;
-
-		if (flags & XBF_READ_AHEAD) {
-			xfs_buf_free_pages(bp);
-			return -ENOMEM;
-		}
-
-		XFS_STATS_INC(bp->b_mount, xb_page_retries);
-		memalloc_retry_wait(gfp_mask);
-	}
-	return 0;
-}
-
-/*
- *	Map buffer into kernel address-space if necessary.
- */
-STATIC int
-_xfs_buf_map_pages(
-	struct xfs_buf		*bp,
-	xfs_buf_flags_t		flags)
-{
-	ASSERT(bp->b_flags & _XBF_PAGES);
-	if (bp->b_page_count == 1) {
-		/* A single page buffer is always mappable */
-		bp->b_addr = page_address(bp->b_pages[0]);
-	} else if (flags & XBF_UNMAPPED) {
-		bp->b_addr = NULL;
-	} else {
-		int retried = 0;
-		unsigned nofs_flag;
-
-		/*
-		 * vm_map_ram() will allocate auxiliary structures (e.g.
-		 * pagetables) with GFP_KERNEL, yet we often under a scoped nofs
-		 * context here. Mixing GFP_KERNEL with GFP_NOFS allocations
-		 * from the same call site that can be run from both above and
-		 * below memory reclaim causes lockdep false positives. Hence we
-		 * always need to force this allocation to nofs context because
-		 * we can't pass __GFP_NOLOCKDEP down to auxillary structures to
-		 * prevent false positive lockdep reports.
-		 *
-		 * XXX(dgc): I think dquot reclaim is the only place we can get
-		 * to this function from memory reclaim context now. If we fix
-		 * that like we've fixed inode reclaim to avoid writeback from
-		 * reclaim, this nofs wrapping can go away.
-		 */
-		nofs_flag = memalloc_nofs_save();
-		do {
-			bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
-						-1);
-			if (bp->b_addr)
-				break;
-			vm_unmap_aliases();
-		} while (retried++ <= 1);
-		memalloc_nofs_restore(nofs_flag);
-
-		if (!bp->b_addr)
-			return -ENOMEM;
-	}
-
 	return 0;
 }
 
···
 			return -ENOENT;
 		}
 		ASSERT((bp->b_flags & _XBF_DELWRI_Q) == 0);
-		bp->b_flags &= _XBF_KMEM | _XBF_PAGES;
+		bp->b_flags &= _XBF_KMEM;
 		bp->b_ops = NULL;
 	}
 	return 0;
···
 	struct xfs_buf		*bp;
 	int			error;
 
-	error = _xfs_buf_alloc(btp, map, nmaps, flags, &new_bp);
+	error = xfs_buf_alloc(btp, map, nmaps, flags, &new_bp);
 	if (error)
 		goto out_drop_pag;
-
-	if (xfs_buftarg_is_mem(new_bp->b_target)) {
-		error = xmbuf_map_page(new_bp);
-	} else if (BBTOB(new_bp->b_length) >= PAGE_SIZE ||
-		   xfs_buf_alloc_kmem(new_bp, flags) < 0) {
-		/*
-		 * For buffers that fit entirely within a single page, first
-		 * attempt to allocate the memory from the heap to minimise
-		 * memory usage. If we can't get heap memory for these small
-		 * buffers, we fall back to using the page allocator.
-		 */
-		error = xfs_buf_alloc_pages(new_bp, flags);
-	}
-	if (error)
-		goto out_free_buf;
 
 	/* The new buffer keeps the perag reference until it is freed. */
 	new_bp->b_pag = pag;
···
 		XFS_STATS_INC(btp->bt_mount, xb_get_locked);
 		if (pag)
 			xfs_perag_put(pag);
-	}
-
-	/* We do not hold a perag reference anymore. */
-	if (!bp->b_addr) {
-		error = _xfs_buf_map_pages(bp, flags);
-		if (unlikely(error)) {
-			xfs_warn_ratelimited(btp->bt_mount,
-				"%s: failed to map %u pages", __func__,
-				bp->b_page_count);
-			xfs_buf_relse(bp);
-			return error;
-		}
 	}
 
 	/*
···
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		daddr,
 	size_t			numblks,
-	xfs_buf_flags_t		flags,
 	struct xfs_buf		**bpp,
 	const struct xfs_buf_ops *ops)
 {
···
 
 	*bpp = NULL;
 
-	error = xfs_buf_get_uncached(target, numblks, flags, &bp);
+	error = xfs_buf_get_uncached(target, numblks, &bp);
 	if (error)
 		return error;
 
···
 xfs_buf_get_uncached(
 	struct xfs_buftarg	*target,
 	size_t			numblks,
-	xfs_buf_flags_t		flags,
 	struct xfs_buf		**bpp)
 {
 	int			error;
-	struct xfs_buf		*bp;
 	DEFINE_SINGLE_BUF_MAP(map, XFS_BUF_DADDR_NULL, numblks);
 
-	/* there are currently no valid flags for xfs_buf_get_uncached */
-	ASSERT(flags == 0);
-
-	*bpp = NULL;
-
-	error = _xfs_buf_alloc(target, &map, 1, flags, &bp);
-	if (error)
-		return error;
-
-	if (xfs_buftarg_is_mem(bp->b_target))
-		error = xmbuf_map_page(bp);
-	else
-		error = xfs_buf_alloc_pages(bp, flags);
-	if (error)
-		goto fail_free_buf;
-
-	error = _xfs_buf_map_pages(bp, 0);
-	if (unlikely(error)) {
-		xfs_warn(target->bt_mount,
-			"%s: failed to map pages", __func__);
-		goto fail_free_buf;
-	}
-
-	trace_xfs_buf_get_uncached(bp, _RET_IP_);
-	*bpp = bp;
-	return 0;
-
-fail_free_buf:
-	xfs_buf_free(bp);
+	error = xfs_buf_alloc(target, &map, 1, 0, bpp);
+	if (!error)
+		trace_xfs_buf_get_uncached(*bpp, _RET_IP_);
 	return error;
 }
 
···
 	trace_xfs_buf_iodone(bp, _RET_IP_);
 
 	if (bp->b_flags & XBF_READ) {
-		if (!bp->b_error && xfs_buf_is_vmapped(bp))
+		if (!bp->b_error && is_vmalloc_addr(bp->b_addr))
 			invalidate_kernel_vmap_range(bp->b_addr,
-					xfs_buf_vmap_len(bp));
+				roundup(BBTOB(bp->b_length), PAGE_SIZE));
 		if (!bp->b_error && bp->b_ops)
 			bp->b_ops->verify_read(bp);
 		if (!bp->b_error)
···
 xfs_buf_submit_bio(
 	struct xfs_buf		*bp)
 {
-	unsigned int		size = BBTOB(bp->b_length);
-	unsigned int		map = 0, p;
+	unsigned int		map = 0;
 	struct blk_plug		plug;
 	struct bio		*bio;
 
-	bio = bio_alloc(bp->b_target->bt_bdev, bp->b_page_count,
-			xfs_buf_bio_op(bp), GFP_NOIO);
+	if (is_vmalloc_addr(bp->b_addr)) {
+		unsigned int	size = BBTOB(bp->b_length);
+		unsigned int	alloc_size = roundup(size, PAGE_SIZE);
+		void		*data = bp->b_addr;
+
+		bio = bio_alloc(bp->b_target->bt_bdev, alloc_size >> PAGE_SHIFT,
+				xfs_buf_bio_op(bp), GFP_NOIO);
+
+		do {
+			unsigned int	len = min(size, PAGE_SIZE);
+
+			ASSERT(offset_in_page(data) == 0);
+			__bio_add_page(bio, vmalloc_to_page(data), len, 0);
+			data += len;
+			size -= len;
+		} while (size);
+
+		flush_kernel_vmap_range(bp->b_addr, alloc_size);
+	} else {
+		/*
+		 * Single folio or slab allocation.  Must be contiguous and thus
+		 * only a single bvec is needed.
+		 *
+		 * This uses the page based bio add helper for now as that is
+		 * the lowest common denominator between folios and slab
+		 * allocations.  To be replaced with a better block layer
+		 * helper soon (hopefully).
+		 */
+		bio = bio_alloc(bp->b_target->bt_bdev, 1, xfs_buf_bio_op(bp),
+				GFP_NOIO);
+		__bio_add_page(bio, virt_to_page(bp->b_addr),
+				BBTOB(bp->b_length),
+				offset_in_page(bp->b_addr));
+	}
+
 	bio->bi_private = bp;
 	bio->bi_end_io = xfs_buf_bio_end_io;
-
-	if (bp->b_flags & _XBF_KMEM) {
-		__bio_add_page(bio, virt_to_page(bp->b_addr), size,
-				bp->b_offset);
-	} else {
-		for (p = 0; p < bp->b_page_count; p++)
-			__bio_add_page(bio, bp->b_pages[p], PAGE_SIZE, 0);
-		bio->bi_iter.bi_size = size; /* limit to the actual size used */
-
-		if (xfs_buf_is_vmapped(bp))
-			flush_kernel_vmap_range(bp->b_addr,
-					xfs_buf_vmap_len(bp));
-	}
 
 	/*
 	 * If there is more than one map segment, split out a new bio for each
···
 	}
 
 	xfs_buf_submit_bio(bp);
-}
-
-void *
-xfs_buf_offset(
-	struct xfs_buf		*bp,
-	size_t			offset)
-{
-	struct page		*page;
-
-	if (bp->b_addr)
-		return bp->b_addr + offset;
-
-	page = bp->b_pages[offset >> PAGE_SHIFT];
-	return page_address(page) + (offset & (PAGE_SIZE-1));
-}
-
-void
-xfs_buf_zero(
-	struct xfs_buf		*bp,
-	size_t			boff,
-	size_t			bsize)
-{
-	size_t			bend;
-
-	bend = boff + bsize;
-	while (boff < bend) {
-		struct page	*page;
-		int		page_index, page_offset, csize;
-
-		page_index = (boff + bp->b_offset) >> PAGE_SHIFT;
-		page_offset = (boff + bp->b_offset) & ~PAGE_MASK;
-		page = bp->b_pages[page_index];
-		csize = min_t(size_t, PAGE_SIZE - page_offset,
-				      BBTOB(bp->b_length) - boff);
-
-		ASSERT((csize + page_offset) <= PAGE_SIZE);
-
-		memset(page_address(page) + page_offset, 0, csize);
-
-		boff += csize;
-	}
 }
 
 /*

fs/xfs/xfs_buf.h

···
 #define _XBF_LOGRECOVERY (1u << 18)/* log recovery buffer */
 
 /* flags used only internally */
-#define _XBF_PAGES	 (1u << 20)/* backed by refcounted pages */
 #define _XBF_KMEM	 (1u << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	 (1u << 22)/* buffer on a delwri queue */
 
···
 #define XBF_LIVESCAN	 (1u << 28)
 #define XBF_INCORE	 (1u << 29)/* lookup only, return if found in cache */
 #define XBF_TRYLOCK	 (1u << 30)/* lock requested, but do not wait */
-#define XBF_UNMAPPED	 (1u << 31)/* do not map the buffer */
 
 
 typedef unsigned int xfs_buf_flags_t;
···
 	{ XBF_STALE,		"STALE" }, \
 	{ XBF_WRITE_FAIL,	"WRITE_FAIL" }, \
 	{ _XBF_LOGRECOVERY,	"LOG_RECOVERY" }, \
-	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
 	/* The following interface flags should never be set */ \
 	{ XBF_LIVESCAN,		"LIVESCAN" }, \
 	{ XBF_INCORE,		"INCORE" }, \
-	{ XBF_TRYLOCK,		"TRYLOCK" }, \
-	{ XBF_UNMAPPED,		"UNMAPPED" }
+	{ XBF_TRYLOCK,		"TRYLOCK" }
 
 /*
  * Internal state flags.
···
 	/* built-in cache, if we're not using the perag one */
 	struct xfs_buf_cache	bt_cache[];
 };
-
-#define XB_PAGES	2
 
 struct xfs_buf_map {
 	xfs_daddr_t		bm_bn;	/* block number for I/O */
···
 	struct xfs_buf_log_item	*b_log_item;
 	struct list_head	b_li_list;	/* Log items list head */
 	struct xfs_trans	*b_transp;
-	struct page		**b_pages;	/* array of page pointers */
-	struct page		*b_page_array[XB_PAGES]; /* inline pages */
 	struct xfs_buf_map	*b_maps;	/* compound buffer map */
 	struct xfs_buf_map	__b_map;	/* inline compound buffer map */
 	int			b_map_count;
 	atomic_t		b_pin_count;	/* pin count */
-	unsigned int		b_page_count;	/* size of page array */
-	unsigned int		b_offset;	/* page offset of b_addr,
-						   only for _XBF_KMEM buffers */
 	int			b_error;	/* error code on I/O */
 	void			(*b_iodone)(struct xfs_buf *bp);
 
···
 }
 
 int xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
-		xfs_buf_flags_t flags, struct xfs_buf **bpp);
+		struct xfs_buf **bpp);
 int xfs_buf_read_uncached(struct xfs_buftarg *target, xfs_daddr_t daddr,
-		size_t numblks, xfs_buf_flags_t flags, struct xfs_buf **bpp,
+		size_t numblks, struct xfs_buf **bpp,
 		const struct xfs_buf_ops *ops);
 int _xfs_buf_read(struct xfs_buf *bp);
 void xfs_buf_hold(struct xfs_buf *bp);
···
 #define xfs_buf_ioerror(bp, err) __xfs_buf_ioerror((bp), (err), __this_address)
 extern void xfs_buf_ioerror_alert(struct xfs_buf *bp, xfs_failaddr_t fa);
 void xfs_buf_ioend_fail(struct xfs_buf *);
-void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize);
 void __xfs_buf_mark_corrupt(struct xfs_buf *bp, xfs_failaddr_t fa);
 #define xfs_buf_mark_corrupt(bp) __xfs_buf_mark_corrupt((bp), __this_address)
 
 /* Buffer Utility Routines */
-extern void *xfs_buf_offset(struct xfs_buf *, size_t);
+static inline void *xfs_buf_offset(struct xfs_buf *bp, size_t offset)
+{
+	return bp->b_addr + offset;
+}
+
+static inline void xfs_buf_zero(struct xfs_buf *bp, size_t boff, size_t bsize)
+{
+	memset(bp->b_addr + boff, 0, bsize);
+}
+
 extern void xfs_buf_stale(struct xfs_buf *bp);
 
 /* Delayed Write Buffer Routines */

fs/xfs/xfs_buf_item.c

···
 			(blfp->blf_map_size * sizeof(blfp->blf_data_map[0]));
 }
 
-static inline bool
-xfs_buf_item_straddle(
-	struct xfs_buf		*bp,
-	uint			offset,
-	int			first_bit,
-	int			nbits)
-{
-	void			*first, *last;
-
-	first = xfs_buf_offset(bp, offset + (first_bit << XFS_BLF_SHIFT));
-	last = xfs_buf_offset(bp,
-			offset + ((first_bit + nbits) << XFS_BLF_SHIFT));
-
-	if (last - first != nbits * XFS_BLF_CHUNK)
-		return true;
-	return false;
-}
-
 /*
  * Return the number of log iovecs and space needed to log the given buf log
  * item segment.
···
 	int				*nvecs,
 	int				*nbytes)
 {
-	struct xfs_buf			*bp = bip->bli_buf;
 	int				first_bit;
 	int				nbits;
-	int				next_bit;
-	int				last_bit;
 
 	first_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size, 0);
 	if (first_bit == -1)
···
 		nbits = xfs_contig_bits(blfp->blf_data_map,
 					blfp->blf_map_size, first_bit);
 		ASSERT(nbits > 0);
-
-		/*
-		 * Straddling a page is rare because we don't log contiguous
-		 * chunks of unmapped buffers anywhere.
-		 */
-		if (nbits > 1 &&
-		    xfs_buf_item_straddle(bp, offset, first_bit, nbits))
-			goto slow_scan;
-
 		(*nvecs)++;
 		*nbytes += nbits * XFS_BLF_CHUNK;
 
···
 	} while (first_bit != -1);
 
 	return;
-
-slow_scan:
-	/* Count the first bit we jumped out of the above loop from */
-	(*nvecs)++;
-	*nbytes += XFS_BLF_CHUNK;
-	last_bit = first_bit;
-	while (last_bit != -1) {
-		/*
-		 * This takes the bit number to start looking from and
-		 * returns the next set bit from there.  It returns -1
-		 * if there are no more bits set or the start bit is
-		 * beyond the end of the bitmap.
-		 */
-		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
-					last_bit + 1);
-		/*
-		 * If we run out of bits, leave the loop,
-		 * else if we find a new set of bits bump the number of vecs,
-		 * else keep scanning the current set of bits.
-		 */
-		if (next_bit == -1) {
-			break;
-		} else if (next_bit != last_bit + 1 ||
-		           xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
-			last_bit = next_bit;
-			first_bit = next_bit;
-			(*nvecs)++;
-			nbits = 1;
-		} else {
-			last_bit++;
-			nbits++;
-		}
-		*nbytes += XFS_BLF_CHUNK;
-	}
 }
 
 /*
···
 	struct xfs_buf		*bp = bip->bli_buf;
 	uint			base_size;
 	int			first_bit;
-	int			last_bit;
-	int			next_bit;
 	uint			nbits;
 
 	/* copy the flags across from the base format item */
···
 		nbits = xfs_contig_bits(blfp->blf_data_map,
 					blfp->blf_map_size, first_bit);
 		ASSERT(nbits > 0);
-
-		/*
-		 * Straddling a page is rare because we don't log contiguous
-		 * chunks of unmapped buffers anywhere.
-		 */
-		if (nbits > 1 &&
-		    xfs_buf_item_straddle(bp, offset, first_bit, nbits))
-			goto slow_scan;
-
 		xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
 					first_bit, nbits);
 		blfp->blf_size++;
···
 	} while (first_bit != -1);
 
 	return;
-
-slow_scan:
-	ASSERT(bp->b_addr == NULL);
-	last_bit = first_bit;
-	nbits = 1;
-	for (;;) {
-		/*
-		 * This takes the bit number to start looking from and
-		 * returns the next set bit from there.  It returns -1
-		 * if there are no more bits set or the start bit is
-		 * beyond the end of the bitmap.
-		 */
-		next_bit = xfs_next_bit(blfp->blf_data_map, blfp->blf_map_size,
-					(uint)last_bit + 1);
-		/*
-		 * If we run out of bits fill in the last iovec and get out of
-		 * the loop.  Else if we start a new set of bits then fill in
-		 * the iovec for the series we were looking at and start
-		 * counting the bits in the new one.  Else we're still in the
-		 * same set of bits so just keep counting and scanning.
-		 */
-		if (next_bit == -1) {
-			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
-						first_bit, nbits);
-			blfp->blf_size++;
-			break;
-		} else if (next_bit != last_bit + 1 ||
-		           xfs_buf_item_straddle(bp, offset, first_bit, nbits)) {
-			xfs_buf_item_copy_iovec(lv, vecp, bp, offset,
-						first_bit, nbits);
-			blfp->blf_size++;
-			first_bit = next_bit;
-			last_bit = next_bit;
-			nbits = 1;
-		} else {
-			last_bit++;
-			nbits++;
-		}
-	}
 }
 
 /*

fs/xfs/xfs_buf_item_recover.c

···
 	struct xfs_mount		*mp = log->l_mp;
 	struct xfs_buf			*bp;
 	int				error;
-	uint				buf_flags;
 	xfs_lsn_t			lsn;
 
 	/*
···
 	}
 
 	trace_xfs_log_recover_buf_recover(log, buf_f);
-
-	buf_flags = 0;
-	if (buf_f->blf_flags & XFS_BLF_INODE_BUF)
-		buf_flags |= XBF_UNMAPPED;
-
 	error = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len,
-			  buf_flags, &bp, NULL);
+			  0, &bp, NULL);
 	if (error)
 		return error;
 

fs/xfs/xfs_buf_mem.c

···
 
 	/*
 	 * We don't want to bother with kmapping data during repair, so don't
-	 * allow highmem pages to back this mapping.
+	 * allow highmem folios to back this mapping.
 	 */
 	mapping_set_gfp_mask(inode->i_mapping, GFP_KERNEL);
 
···
 	kfree(btp);
 }
 
-/* Directly map a shmem page into the buffer cache. */
+/* Directly map a shmem folio into the buffer cache. */
 int
-xmbuf_map_page(
+xmbuf_map_backing_mem(
 	struct xfs_buf		*bp)
 {
 	struct inode		*inode = file_inode(bp->b_target->bt_file);
 	struct folio		*folio = NULL;
-	struct page		*page;
 	loff_t                  pos = BBTOB(xfs_buf_daddr(bp));
 	int			error;
 
···
 		return -EIO;
 	}
 
-	page = folio_file_page(folio, pos >> PAGE_SHIFT);
-
 	/*
-	 * Mark the page dirty so that it won't be reclaimed once we drop the
-	 * (potentially last) reference in xmbuf_unmap_page.
+	 * Mark the folio dirty so that it won't be reclaimed once we drop the
+	 * (potentially last) reference in xfs_buf_free.
 	 */
-	set_page_dirty(page);
-	unlock_page(page);
+	folio_set_dirty(folio);
+	folio_unlock(folio);
 
-	bp->b_addr = page_address(page);
-	bp->b_pages = bp->b_page_array;
-	bp->b_pages[0] = page;
-	bp->b_page_count = 1;
+	bp->b_addr = folio_address(folio);
 	return 0;
-}
-
-/* Unmap a shmem page that was mapped into the buffer cache. */
-void
-xmbuf_unmap_page(
-	struct xfs_buf		*bp)
-{
-	struct page		*page = bp->b_pages[0];
-
-	ASSERT(xfs_buftarg_is_mem(bp->b_target));
-
-	put_page(page);
-
-	bp->b_addr = NULL;
-	bp->b_pages[0] = NULL;
-	bp->b_pages = NULL;
-	bp->b_page_count = 0;
 }
 
 /* Is this a valid daddr within the buftarg? */
···
 	return daddr < (inode->i_sb->s_maxbytes >> BBSHIFT);
 }
 
-/* Discard the page backing this buffer. */
+/* Discard the folio backing this buffer. */
 static void
 xmbuf_stale(
 	struct xfs_buf		*bp)
···
 }
 
 /*
- * Finalize a buffer -- discard the backing page if it's stale, or run the
+ * Finalize a buffer -- discard the backing folio if it's stale, or run the
  * write verifier to detect problems.
  */
 int

fs/xfs/xfs_buf_mem.h

···
 		struct xfs_buftarg **btpp);
 void xmbuf_free(struct xfs_buftarg *btp);
 
-int xmbuf_map_page(struct xfs_buf *bp);
-void xmbuf_unmap_page(struct xfs_buf *bp);
 bool xmbuf_verify_daddr(struct xfs_buftarg *btp, xfs_daddr_t daddr);
 void xmbuf_trans_bdetach(struct xfs_trans *tp, struct xfs_buf *bp);
 int xmbuf_finalize(struct xfs_buf *bp);
 #else
 # define xfs_buftarg_is_mem(...)	(false)
-# define xmbuf_map_page(...)		(-ENOMEM)
-# define xmbuf_unmap_page(...)		((void)0)
 # define xmbuf_verify_daddr(...)	(false)
 #endif /* CONFIG_XFS_MEMORY_BUFS */
+
+int xmbuf_map_backing_mem(struct xfs_buf *bp);
 
 #endif /* __XFS_BUF_MEM_H__ */

fs/xfs/xfs_discard.c

···
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
-	if (mp->m_rtdev_targp &&
+
+	if (mp->m_rtdev_targp && !xfs_has_zoned(mp) &&
 	    bdev_max_discard_sectors(mp->m_rtdev_targp->bt_bdev))
 		rt_bdev = mp->m_rtdev_targp->bt_bdev;
 	if (!bdev_max_discard_sectors(mp->m_ddev_targp->bt_bdev) && !rt_bdev)

fs/xfs/xfs_extent_busy.c

···
 	while ((pag = xfs_perag_next(mp, pag)))
 		xfs_extent_busy_wait_group(pag_group(pag));
 
-	if (xfs_has_rtgroups(mp))
+	if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp))
 		while ((rtg = xfs_rtgroup_next(mp, rtg)))
 			xfs_extent_busy_wait_group(rtg_group(rtg));
 }

fs/xfs/xfs_extfree_item.c

···
 #include "xfs_inode.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
 
 struct kmem_cache	*xfs_efi_cache;
 struct kmem_cache	*xfs_efd_cache;
···
 
 	trace_xfs_extent_free_deferred(mp, xefi);
 
-	if (!(xefi->xefi_flags & XFS_EFI_CANCELLED)) {
-		if (*rtgp != to_rtg(xefi->xefi_group)) {
-			*rtgp = to_rtg(xefi->xefi_group);
-			xfs_rtgroup_lock(*rtgp, XFS_RTGLOCK_BITMAP);
-			xfs_rtgroup_trans_join(tp, *rtgp,
-					XFS_RTGLOCK_BITMAP);
-		}
-		error = xfs_rtfree_blocks(tp, *rtgp,
-				xefi->xefi_startblock, xefi->xefi_blockcount);
+	if (xefi->xefi_flags & XFS_EFI_CANCELLED)
+		goto done;
+
+	if (*rtgp != to_rtg(xefi->xefi_group)) {
+		unsigned int		lock_flags;
+
+		if (xfs_has_zoned(mp))
+			lock_flags = XFS_RTGLOCK_RMAP;
+		else
+			lock_flags = XFS_RTGLOCK_BITMAP;
+
+		*rtgp = to_rtg(xefi->xefi_group);
+		xfs_rtgroup_lock(*rtgp, lock_flags);
+		xfs_rtgroup_trans_join(tp, *rtgp, lock_flags);
 	}
+
+	if (xfs_has_zoned(mp)) {
+		error = xfs_zone_free_blocks(tp, *rtgp, xefi->xefi_startblock,
+				xefi->xefi_blockcount);
+	} else {
+		error = xfs_rtfree_blocks(tp, *rtgp, xefi->xefi_startblock,
+				xefi->xefi_blockcount);
+	}
+
 	if (error == -EAGAIN) {
 		xfs_efd_from_efi(efdp);
 		return error;
 	}
-
+done:
 	xfs_efd_add_extent(efdp, xefi);
 	xfs_extent_free_cancel_item(item);
 	return error;

fs/xfs/xfs_file.c

···
 #include "xfs_iomap.h"
 #include "xfs_reflink.h"
 #include "xfs_file.h"
+#include "xfs_aops.h"
+#include "xfs_zone_alloc.h"
 
 #include <linux/dax.h>
 #include <linux/falloc.h>
···
 	 * ensure newly written file data make it to disk before logging the new
 	 * inode size in case of an extending write.
 	 */
-	if (XFS_IS_REALTIME_INODE(ip))
+	if (XFS_IS_REALTIME_INODE(ip) && mp->m_rtdev_targp != mp->m_ddev_targp)
 		error = blkdev_issue_flush(mp->m_rtdev_targp->bt_bdev);
 	else if (mp->m_logdev_targp != mp->m_ddev_targp)
 		error = blkdev_issue_flush(mp->m_ddev_targp->bt_bdev);
···
 	struct iov_iter		*from,
 	unsigned int		*iolock,
 	size_t			count,
-	bool			*drained_dio)
+	bool			*drained_dio,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct xfs_inode	*ip = XFS_I(iocb->ki_filp->f_mapping->host);
 	loff_t			isize;
···
 	trace_xfs_zero_eof(ip, isize, iocb->ki_pos - isize);
 
 	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, NULL);
+	error = xfs_zero_range(ip, isize, iocb->ki_pos - isize, ac, NULL);
 	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 
 	return error;
···
 xfs_file_write_checks(
 	struct kiocb		*iocb,
 	struct iov_iter		*from,
-	unsigned int		*iolock)
+	unsigned int		*iolock,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct inode		*inode = iocb->ki_filp->f_mapping->host;
 	size_t			count = iov_iter_count(from);
···
 	 */
 	if (iocb->ki_pos > i_size_read(inode)) {
 		error = xfs_file_write_zero_eof(iocb, from, iolock, count,
-				&drained_dio);
+				&drained_dio, ac);
 		if (error == 1)
 			goto restart;
 		if (error)
···
 	}
 
 	return kiocb_modified(iocb);
+}
+
+static ssize_t
+xfs_zoned_write_space_reserve(
+	struct xfs_inode		*ip,
+	struct kiocb			*iocb,
+	struct iov_iter			*from,
+	unsigned int			flags,
+	struct xfs_zone_alloc_ctx	*ac)
+{
+	loff_t				count = iov_iter_count(from);
+	int				error;
+
+	if (iocb->ki_flags & IOCB_NOWAIT)
+		flags |= XFS_ZR_NOWAIT;
+
+	/*
+	 * Check the rlimit and LFS boundary first so that we don't over-reserve
+	 * by possibly a lot.
+	 *
+	 * The generic write path will redo this check later, and it might have
+	 * changed by then.  If it got expanded we'll stick to our earlier
+	 * smaller limit, and if it is decreased the new smaller limit will be
+	 * used and our extra space reservation will be returned after finishing
+	 * the write.
+	 */
+	error = generic_write_check_limits(iocb->ki_filp, iocb->ki_pos, &count);
+	if (error)
+		return error;
+
+	/*
+	 * Sloppily round up count to file system blocks.
+	 *
+	 * This will often reserve an extra block, but that avoids having to look
+	 * at the start offset, which isn't stable for O_APPEND until taking the
+	 * iolock.  Also we need to reserve a block each for zeroing the old
+	 * EOF block and the new start block if they are unaligned.
+	 *
+	 * Any remaining block will be returned after the write.
+	 */
+	return xfs_zoned_space_reserve(ip,
+			XFS_B_TO_FSB(ip->i_mount, count) + 1 + 2, flags, ac);
 }
 
 static int
···
 	struct xfs_inode	*ip = XFS_I(inode);
 	loff_t			offset = iocb->ki_pos;
 	unsigned int		nofs_flag;
+
+	ASSERT(!xfs_is_zoned_inode(ip) ||
+	       !(flags & (IOMAP_DIO_UNWRITTEN | IOMAP_DIO_COW)));
 
 	trace_xfs_end_io_direct_write(ip, offset, size);
 
···
 	.end_io		= xfs_dio_write_end_io,
 };
 
+static void
+xfs_dio_zoned_submit_io(
+	const struct iomap_iter	*iter,
+	struct bio		*bio,
+	loff_t			file_offset)
+{
+	struct xfs_mount	*mp = XFS_I(iter->inode)->i_mount;
+	struct xfs_zone_alloc_ctx *ac = iter->private;
+	xfs_filblks_t		count_fsb;
+	struct iomap_ioend	*ioend;
+
+	count_fsb = XFS_B_TO_FSB(mp, bio->bi_iter.bi_size);
+	if (count_fsb > ac->reserved_blocks) {
+		xfs_err(mp,
+"allocation (%lld) larger than reservation (%lld).",
+			count_fsb, ac->reserved_blocks);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		bio_io_error(bio);
+		return;
+	}
+	ac->reserved_blocks -= count_fsb;
+
+	bio->bi_end_io = xfs_end_bio;
+	ioend = iomap_init_ioend(iter->inode, bio, file_offset,
+			IOMAP_IOEND_DIRECT);
+	xfs_zone_alloc_and_submit(ioend, &ac->open_zone);
+}
+
+static const struct iomap_dio_ops xfs_dio_zoned_write_ops = {
+	.bio_set	= &iomap_ioend_bioset,
+	.submit_io	= xfs_dio_zoned_submit_io,
+	.end_io		= xfs_dio_write_end_io,
+};
+
 /*
- * Handle block aligned direct I/O writes
+ * Handle block aligned direct I/O writes.
  */
 static noinline ssize_t
 xfs_file_dio_write_aligned(
 	struct xfs_inode	*ip,
 	struct kiocb		*iocb,
-	struct iov_iter		*from)
+	struct iov_iter		*from,
+	const struct iomap_ops	*ops,
+	const struct iomap_dio_ops *dops,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	unsigned int		iolock = XFS_IOLOCK_SHARED;
 	ssize_t			ret;
···
 	ret = xfs_ilock_iocb_for_write(iocb, &iolock);
 	if (ret)
 		return ret;
-	ret = xfs_file_write_checks(iocb, from, &iolock);
+	ret = xfs_file_write_checks(iocb, from, &iolock, ac);
 	if (ret)
 		goto out_unlock;
 
···
 		iolock = XFS_IOLOCK_SHARED;
 	}
 	trace_xfs_file_direct_write(iocb, from);
-	ret = iomap_dio_rw(iocb, from, &xfs_direct_write_iomap_ops,
-			   &xfs_dio_write_ops, 0, NULL, 0);
+	ret = iomap_dio_rw(iocb, from, ops, dops, 0, ac, 0);
 out_unlock:
-	if (iolock)
-		xfs_iunlock(ip, iolock);
+	xfs_iunlock(ip, iolock);
+	return ret;
+}
+
+/*
+ * Handle block aligned direct I/O writes to zoned devices.
+ */
+static noinline ssize_t
+xfs_file_dio_write_zoned(
+	struct xfs_inode	*ip,
+	struct kiocb		*iocb,
+	struct iov_iter		*from)
+{
+	struct xfs_zone_alloc_ctx ac = { };
+	ssize_t			ret;
+
+	ret = xfs_zoned_write_space_reserve(ip, iocb, from, 0, &ac);
+	if (ret < 0)
+		return ret;
+	ret = xfs_file_dio_write_aligned(ip, iocb, from,
+			&xfs_zoned_direct_write_iomap_ops,
+			&xfs_dio_zoned_write_ops, &ac);
+	xfs_zoned_space_unreserve(ip, &ac);
 	return ret;
 }
 
···
 		goto out_unlock;
 	}
 
-	ret = xfs_file_write_checks(iocb, from, &iolock);
+	ret = xfs_file_write_checks(iocb, from, &iolock, NULL);
 	if (ret)
 		goto out_unlock;
 
···
 	/* direct I/O must be aligned to device logical sector size */
 	if ((iocb->ki_pos | count) & target->bt_logical_sectormask)
 		return -EINVAL;
-	if ((iocb->ki_pos | count) & ip->i_mount->m_blockmask)
+
+	/*
+	 * For always COW inodes we also must check the alignment of each
+	 * individual iovec segment, as they could end up with different
+	 * I/Os due to the way bio_iov_iter_get_pages works, and we'd
+	 * then overwrite an already written block.
+	 */
+	if (((iocb->ki_pos | count) & ip->i_mount->m_blockmask) ||
+	    (xfs_is_always_cow_inode(ip) &&
+	     (iov_iter_alignment(from) & ip->i_mount->m_blockmask)))
 		return xfs_file_dio_write_unaligned(ip, iocb, from);
-	return xfs_file_dio_write_aligned(ip, iocb, from);
+	if (xfs_is_zoned_inode(ip))
+		return xfs_file_dio_write_zoned(ip, iocb, from);
+	return xfs_file_dio_write_aligned(ip, iocb, from,
+			&xfs_direct_write_iomap_ops, &xfs_dio_write_ops, NULL);
 }
 
 static noinline ssize_t
···
 	ret = xfs_ilock_iocb(iocb, iolock);
 	if (ret)
 		return ret;
-	ret = xfs_file_write_checks(iocb, from, &iolock);
+	ret = xfs_file_write_checks(iocb, from, &iolock, NULL);
 	if (ret)
 		goto out;
 
···
 	if (ret)
 		return ret;
 
-	ret = xfs_file_write_checks(iocb, from, &iolock);
+	ret = xfs_file_write_checks(iocb, from, &iolock, NULL);
 	if (ret)
 		goto out;
 
···
 	if (ret > 0) {
 		XFS_STATS_ADD(ip->i_mount, xs_write_bytes, ret);
 		/* Handle various SYNC-type writes */
+		ret = generic_write_sync(iocb, ret);
+	}
+	return ret;
+}
+
+STATIC ssize_t
+xfs_file_buffered_write_zoned(
+	struct kiocb		*iocb,
+	struct iov_iter		*from)
+{
+	struct xfs_inode	*ip = XFS_I(iocb->ki_filp->f_mapping->host);
+	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		iolock = XFS_IOLOCK_EXCL;
+	bool			cleared_space = false;
+	struct xfs_zone_alloc_ctx ac = { };
+	ssize_t			ret;
+
+	ret = xfs_zoned_write_space_reserve(ip, iocb, from, XFS_ZR_GREEDY, &ac);
+	if (ret < 0)
+		return ret;
+
+	ret = xfs_ilock_iocb(iocb, iolock);
+	if (ret)
+		goto out_unreserve;
+
+	ret = xfs_file_write_checks(iocb, from, &iolock, &ac);
+	if (ret)
+		goto out_unlock;
+
+	/*
+	 * Truncate the iter to the length that we were actually able to
+	 * allocate blocks for.  This needs to happen after
+	 * xfs_file_write_checks, because that assigns ki_pos for O_APPEND
+	 * writes.
+	 */
+	iov_iter_truncate(from,
+			XFS_FSB_TO_B(mp, ac.reserved_blocks) -
+			(iocb->ki_pos & mp->m_blockmask));
+	if (!iov_iter_count(from))
+		goto out_unlock;
+
+retry:
+	trace_xfs_file_buffered_write(iocb, from);
+	ret = iomap_file_buffered_write(iocb, from,
+			&xfs_buffered_write_iomap_ops, &ac);
+	if (ret == -ENOSPC && !cleared_space) {
+		/*
+		 * Kick off writeback to convert delalloc space and release the
+		 * usually too pessimistic indirect block reservations.
+		 */
+		xfs_flush_inodes(mp);
+		cleared_space = true;
+		goto retry;
+	}
+
+out_unlock:
+	xfs_iunlock(ip, iolock);
+out_unreserve:
+	xfs_zoned_space_unreserve(ip, &ac);
+	if (ret > 0) {
+		XFS_STATS_ADD(mp, xs_write_bytes, ret);
 		ret = generic_write_sync(iocb, ret);
 	}
 	return ret;
···
 			return ret;
 	}
 
+	if (xfs_is_zoned_inode(ip))
+		return xfs_file_buffered_write_zoned(iocb, from);
 	return xfs_file_buffered_write(iocb, from);
 }
 
···
 xfs_falloc_collapse_range(
 	struct file		*file,
 	loff_t			offset,
-	loff_t			len)
+	loff_t			len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct inode		*inode = file_inode(file);
 	loff_t			new_size = i_size_read(inode) - len;
···
 	if (offset + len >= i_size_read(inode))
 		return -EINVAL;
 
-	error = xfs_collapse_file_space(XFS_I(inode), offset, len);
+	error = xfs_collapse_file_space(XFS_I(inode), offset, len, ac);
 	if (error)
 		return error;
 	return xfs_falloc_setsize(file, new_size);
···
 	struct file		*file,
 	int			mode,
 	loff_t			offset,
-	loff_t			len)
+	loff_t			len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct inode		*inode = file_inode(file);
 	unsigned int		blksize = i_blocksize(inode);
···
 	if (error)
 		return error;
 
-	error = xfs_free_file_space(XFS_I(inode), offset, len);
+	error = xfs_free_file_space(XFS_I(inode), offset, len, ac);
 	if (error)
 		return error;
 
···
 		 FALLOC_FL_INSERT_RANGE | FALLOC_FL_UNSHARE_RANGE)
 
 STATIC long
-xfs_file_fallocate(
+__xfs_file_fallocate(
 	struct file		*file,
 	int			mode,
 	loff_t			offset,
-	loff_t			len)
+	loff_t			len,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct inode		*inode = file_inode(file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	long			error;
 	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
-
-	if (!S_ISREG(inode->i_mode))
-		return -EINVAL;
-	if (mode & ~XFS_FALLOC_FL_SUPPORTED)
-		return -EOPNOTSUPP;
 
 	xfs_ilock(ip, iolock);
 	error = xfs_break_layouts(inode, &iolock, BREAK_UNMAP);
···
 
 	switch (mode & FALLOC_FL_MODE_MASK) {
 	case FALLOC_FL_PUNCH_HOLE:
-		error = xfs_free_file_space(ip, offset, len);
+		error = xfs_free_file_space(ip, offset, len, ac);
 		break;
 	case FALLOC_FL_COLLAPSE_RANGE:
-		error = xfs_falloc_collapse_range(file, offset, len);
+		error = xfs_falloc_collapse_range(file, offset, len, ac);
 		break;
 	case FALLOC_FL_INSERT_RANGE:
 		error = xfs_falloc_insert_range(file, offset, len);
 		break;
 	case FALLOC_FL_ZERO_RANGE:
-		error = xfs_falloc_zero_range(file, mode, offset, len);
+		error = xfs_falloc_zero_range(file, mode, offset, len, ac);
 		break;
 	case FALLOC_FL_UNSHARE_RANGE:
 		error = xfs_falloc_unshare_range(file, mode, offset, len);
···
 out_unlock:
 	xfs_iunlock(ip, iolock);
 	return error;
+}
+
+static long
+xfs_file_zoned_fallocate(
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct xfs_zone_alloc_ctx ac = { };
+	struct xfs_inode	*ip = XFS_I(file_inode(file));
+	int			error;
+
+	error = xfs_zoned_space_reserve(ip, 2, XFS_ZR_RESERVED, &ac);
+	if (error)
+		return error;
+	error = __xfs_file_fallocate(file, mode, offset, len, &ac);
+	xfs_zoned_space_unreserve(ip, &ac);
+	return error;
+}
+
+static long
+xfs_file_fallocate(
+	struct file		*file,
+	int			mode,
+	loff_t			offset,
+	loff_t			len)
+{
+	struct inode		*inode = file_inode(file);
+
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+	if (mode & ~XFS_FALLOC_FL_SUPPORTED)
+		return -EOPNOTSUPP;
+
+	/*
+	 * For zoned file systems, zeroing the first and last block of a hole
+	 * punch requires allocating a new block to rewrite the remaining data
+	 * and new zeroes out of place.  Get a reservations for those before
+	 * taking the iolock.  Dip into the reserved pool because we are
+	 * expected to be able to punch a hole even on a completely full
+	 * file system.
+	 */
+	if (xfs_is_zoned_inode(XFS_I(inode)) &&
+	    (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE |
+		     FALLOC_FL_COLLAPSE_RANGE)))
+		return xfs_file_zoned_fallocate(file, mode, offset, len);
+	return __xfs_file_fallocate(file, mode, offset, len, NULL);
 }
 
 STATIC int
···
 	 * blocks.  This avoids open/read/close workloads from removing EOF
 	 * blocks that other writers depend upon to reduce fragmentation.
 	 *
+	 * Inodes on the zoned RT device never have preallocations, so skip
+	 * taking the locks below.
+	 */
+	if (!inode->i_nlink ||
+	    !(file->f_mode & FMODE_WRITE) ||
+	    (ip->i_diflags & XFS_DIFLAG_APPEND) ||
+	    xfs_is_zoned_inode(ip))
+		return 0;
+
+	/*
 	 * If we can't get the iolock just skip truncating the blocks past EOF
 	 * because we could deadlock with the mmap_lock otherwise. We'll get
 	 * another chance to drop them once the last reference to the inode is
 	 * dropped, so we'll never leak blocks permanently.
 	 */
-	if (inode->i_nlink &&
-	    (file->f_mode & FMODE_WRITE) &&
-	    !(ip->i_diflags & XFS_DIFLAG_APPEND) &&
-	    !xfs_iflags_test(ip, XFS_EOFBLOCKS_RELEASED) &&
+	if (!xfs_iflags_test(ip, XFS_EOFBLOCKS_RELEASED) &&
 	    xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
 		if (xfs_can_free_eofblocks(ip) &&
 		    !xfs_iflags_test_and_set(ip, XFS_EOFBLOCKS_RELEASED))
···
  *         i_lock (XFS - extent map serialisation)
  */
 static vm_fault_t
-xfs_write_fault(
+__xfs_write_fault(
 	struct vm_fault		*vmf,
-	unsigned int		order)
+	unsigned int		order,
+	struct xfs_zone_alloc_ctx *ac)
 {
 	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
···
 		ret = xfs_dax_fault_locked(vmf, order, true);
 	else
 		ret = iomap_page_mkwrite(vmf, &xfs_buffered_write_iomap_ops,
-				NULL);
+				ac);
 	xfs_iunlock(ip, lock_mode);
 
 	sb_end_pagefault(inode->i_sb);
 	return ret;
+}
+
+static vm_fault_t
+xfs_write_fault_zoned(
+	struct vm_fault		*vmf,
+	unsigned int		order)
+{
+	struct xfs_inode	*ip = XFS_I(file_inode(vmf->vma->vm_file));
+	unsigned int		len = folio_size(page_folio(vmf->page));
+	struct xfs_zone_alloc_ctx ac = { };
+	int			error;
+	vm_fault_t		ret;
+
+	/*
+	 * This could over-allocate as it doesn't check for truncation.
+	 *
+	 * But as the overallocation is limited to less than a folio and will be
+	 * release instantly that's just fine.
+	 */
+	error = xfs_zoned_space_reserve(ip, XFS_B_TO_FSB(ip->i_mount, len), 0,
+			&ac);
+	if (error < 0)
+		return vmf_fs_error(error);
+	ret = __xfs_write_fault(vmf, order, &ac);
+	xfs_zoned_space_unreserve(ip, &ac);
+	return ret;
+}
+
+static vm_fault_t
+xfs_write_fault(
+	struct vm_fault		*vmf,
+	unsigned int		order)
+{
+	if (xfs_is_zoned_inode(XFS_I(file_inode(vmf->vma->vm_file))))
+		return xfs_write_fault_zoned(vmf, order);
+	return __xfs_write_fault(vmf, order, NULL);
 }
 
 static inline bool

fs/xfs/xfs_fsmap.c

···
 	struct xfs_mount		*mp = tp->t_mountp;
 	struct xfs_rtgroup		*rtg = NULL;
 	struct xfs_btree_cur		*bt_cur = NULL;
+	xfs_daddr_t			rtstart_daddr;
 	xfs_rtblock_t			start_rtb;
 	xfs_rtblock_t			end_rtb;
 	xfs_rgnumber_t			start_rg, end_rg;
 	uint64_t			eofs;
 	int				error = 0;
 
-	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart + mp->m_sb.sb_rblocks);
 	if (keys[0].fmr_physical >= eofs)
 		return 0;
-	start_rtb = xfs_daddr_to_rtb(mp, keys[0].fmr_physical);
-	end_rtb = xfs_daddr_to_rtb(mp, min(eofs - 1, keys[1].fmr_physical));
+
+	rtstart_daddr = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart);
+	if (keys[0].fmr_physical < rtstart_daddr) {
+		struct xfs_fsmap_irec		frec = {
+			.owner			= XFS_RMAP_OWN_FS,
+			.len_daddr		= rtstart_daddr,
+		};
+
+		/* Adjust the low key if we are continuing from where we left off. */
+		if (keys[0].fmr_length > 0) {
+			info->low_daddr = keys[0].fmr_physical + keys[0].fmr_length;
+			return 0;
+		}
+
+		/* Fabricate an rmap entry for space occupied by the data dev */
+		error = xfs_getfsmap_helper(tp, info, &frec);
+		if (error)
+			return error;
+	}
+
+	start_rtb = xfs_daddr_to_rtb(mp, rtstart_daddr + keys[0].fmr_physical);
+	end_rtb = xfs_daddr_to_rtb(mp, rtstart_daddr +
+			min(eofs - 1, keys[1].fmr_physical));
 
 	info->missing_owner = XFS_FMR_OWN_FREE;
 
···
 }
 #endif /* CONFIG_XFS_RT */
 
+static uint32_t
+xfs_getfsmap_device(
+	struct xfs_mount	*mp,
+	enum xfs_device		dev)
+{
+	if (mp->m_sb.sb_rtstart)
+		return dev;
+
+	switch (dev) {
+	case XFS_DEV_DATA:
+		return new_encode_dev(mp->m_ddev_targp->bt_dev);
+	case XFS_DEV_LOG:
+		return new_encode_dev(mp->m_logdev_targp->bt_dev);
+	case XFS_DEV_RT:
+		if (!mp->m_rtdev_targp)
+			break;
+		return new_encode_dev(mp->m_rtdev_targp->bt_dev);
+	}
+
+	return -1;
+}
+
 /* Do we recognize the device? */
 STATIC bool
 xfs_getfsmap_is_valid_device(
 	struct xfs_mount	*mp,
 	struct xfs_fsmap	*fm)
 {
-	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
-	    fm->fmr_device == new_encode_dev(mp->m_ddev_targp->bt_dev))
-		return true;
-	if (mp->m_logdev_targp &&
-	    fm->fmr_device == new_encode_dev(mp->m_logdev_targp->bt_dev))
-		return true;
-	if (mp->m_rtdev_targp &&
-	    fm->fmr_device == new_encode_dev(mp->m_rtdev_targp->bt_dev))
-		return true;
-	return false;
+	return fm->fmr_device == 0 ||
+		fm->fmr_device == UINT_MAX ||
+		fm->fmr_device == xfs_getfsmap_device(mp, XFS_DEV_DATA) ||
+		fm->fmr_device == xfs_getfsmap_device(mp, XFS_DEV_LOG) ||
+		(mp->m_rtdev_targp &&
+		 fm->fmr_device == xfs_getfsmap_device(mp, XFS_DEV_RT));
 }
 
 /* Ensure that the low key is less than the high key. */
···
 	/* Set up our device handlers. */
 	memset(handlers, 0, sizeof(handlers));
 	handlers[0].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
-	handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
+	handlers[0].dev = xfs_getfsmap_device(mp, XFS_DEV_DATA);
 	if (use_rmap)
 		handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
 	else
···
 	if (mp->m_logdev_targp != mp->m_ddev_targp) {
 		handlers[1].nr_sectors = XFS_FSB_TO_BB(mp,
 						       mp->m_sb.sb_logblocks);
-		handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
+		handlers[1].dev = xfs_getfsmap_device(mp, XFS_DEV_LOG);
 		handlers[1].fn = xfs_getfsmap_logdev;
 	}
 #ifdef CONFIG_XFS_RT
-	if (mp->m_rtdev_targp) {
+	/*
+	 * For zoned file systems there is no rtbitmap, so only support fsmap
+	 * if the callers is privileged enough to use the full rmap version.
+	 */
+	if (mp->m_rtdev_targp && (use_rmap || !xfs_has_zoned(mp))) {
 		handlers[2].nr_sectors = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
-		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
+		handlers[2].dev = xfs_getfsmap_device(mp, XFS_DEV_RT);
 		if (use_rmap)
 			handlers[2].fn = xfs_getfsmap_rtdev_rmapbt;
 		else
···
 
 	if (tp)
 		xfs_trans_cancel(tp);
-	head->fmh_oflags = FMH_OF_DEV_T;
+
+	/*
+	 * For internal RT device we need to report different synthetic devices
+	 * for a single physical device, and thus can't report the actual dev_t.
+	 */
+	if (!mp->m_sb.sb_rtstart)
+		head->fmh_oflags = FMH_OF_DEV_T;
 	return error;
 }
 

fs/xfs/xfs_fsops.c

···
 #include "xfs_rtalloc.h"
 #include "xfs_rtrmap_btree.h"
 #include "xfs_rtrefcount_btree.h"
+#include "xfs_metafile.h"
 
 /*
  * Write new AG headers to disk. Non-transactional, but need to be
···
 	if (nb > mp->m_sb.sb_dblocks) {
 		error = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
-				XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+				XFS_FSS_TO_BB(mp, 1), &bp, NULL);
 		if (error)
 			return error;
 		xfs_buf_relse(bp);
···
 	struct xfs_mount	*mp,
 	struct xfs_growfs_data	*in)
 {
-	int			error = 0;
+	int			error;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 	if (!mutex_trylock(&mp->m_growlock))
 		return -EWOULDBLOCK;
 
+	/* we can't grow the data section when an internal RT section exists */
+	if (in->newblocks != mp->m_sb.sb_dblocks && mp->m_sb.sb_rtstart) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+
 	/* update imaxpct separately to the physical grow of the filesystem */
 	if (in->imaxpct != mp->m_sb.sb_imax_pct) {
 		error = xfs_growfs_imaxpct(mp, in->imaxpct);
 		if (error)
-			goto out_error;
+			goto out_unlock;
 	}
 
 	if (in->newblocks != mp->m_sb.sb_dblocks) {
 		error = xfs_growfs_data_private(mp, in);
 		if (error)
-			goto out_error;
+			goto out_unlock;
 	}
 
 	/* Post growfs calculations needed to reflect new state in operations */
···
 	/* Update secondary superblocks now the physical grow has completed */
 	error = xfs_update_secondary_sbs(mp);
 
-out_error:
 	/*
-	 * Increment the generation unconditionally, the error could be from
-	 * updating the secondary superblocks, in which case the new size
-	 * is live already.
+	 * Increment the generation unconditionally, after trying to update the
+	 * secondary superblocks, as the new size is live already at this point.
 	 */
 	mp->m_generation++;
+out_unlock:
 	mutex_unlock(&mp->m_growlock);
 	return error;
 }
···
 int
 xfs_reserve_blocks(
 	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr,
 	uint64_t		request)
 {
 	int64_t			lcounter, delta;
 	int64_t			fdblks_delta = 0;
 	int64_t			free;
 	int			error = 0;
+
+	ASSERT(ctr < XC_FREE_NR);
 
 	/*
 	 * With per-cpu counters, this becomes an interesting problem. we need
···
 	 * counters directly since we shouldn't have any problems unreserving
 	 * space.
 	 */
-	if (mp->m_resblks > request) {
-		lcounter = mp->m_resblks_avail - request;
+	if (mp->m_free[ctr].res_total > request) {
+		lcounter = mp->m_free[ctr].res_avail - request;
 		if (lcounter > 0) {		/* release unused blocks */
 			fdblks_delta = lcounter;
-			mp->m_resblks_avail -= lcounter;
+			mp->m_free[ctr].res_avail -= lcounter;
 		}
-		mp->m_resblks = request;
+		mp->m_free[ctr].res_total = request;
 		if (fdblks_delta) {
 			spin_unlock(&mp->m_sb_lock);
-			xfs_add_fdblocks(mp, fdblks_delta);
+			xfs_add_freecounter(mp, ctr, fdblks_delta);
 			spin_lock(&mp->m_sb_lock);
 		}
 
···
 
 	/*
 	 * If the request is larger than the current reservation, reserve the
-	 * blocks before we update the reserve counters. Sample m_fdblocks and
+	 * blocks before we update the reserve counters. Sample m_free and
 	 * perform a partial reservation if the request exceeds free space.
 	 *
 	 * The code below estimates how many blocks it can request from
···
 	 * space to fill it because mod_fdblocks will refill an undersized
 	 * reserve when it can.
 	 */
-	free = percpu_counter_sum(&mp->m_fdblocks) -
-						xfs_fdblocks_unavailable(mp);
-	delta = request - mp->m_resblks;
-	mp->m_resblks = request;
+	free = xfs_sum_freecounter_raw(mp, ctr) -
+		xfs_freecounter_unavailable(mp, ctr);
+	delta = request - mp->m_free[ctr].res_total;
+	mp->m_free[ctr].res_total = request;
 	if (delta > 0 && free > 0) {
 		/*
 		 * We'll either succeed in getting space from the free block
···
 		 */
 		fdblks_delta = min(free, delta);
 		spin_unlock(&mp->m_sb_lock);
-		error = xfs_dec_fdblocks(mp, fdblks_delta, 0);
+		error = xfs_dec_freecounter(mp, ctr, fdblks_delta, 0);
 		if (!error)
-			xfs_add_fdblocks(mp, fdblks_delta);
+			xfs_add_freecounter(mp, ctr, fdblks_delta);
 		spin_lock(&mp->m_sb_lock);
 	}
 out:
···
 		return error;
 	}
 
-	if (xfs_has_realtime(mp)) {
-		err2 = xfs_rt_resv_init(mp);
-		if (err2 && err2 != -ENOSPC) {
-			xfs_warn(mp,
-		"Error %d reserving realtime metadata reserve pool.", err2);
-			xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
-		}
+	err2 = xfs_metafile_resv_init(mp);
+	if (err2 && err2 != -ENOSPC) {
+		xfs_warn(mp,
+	"Error %d reserving realtime metadata reserve pool.", err2);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
 
-		if (err2 && !error)
+		if (!error)
 			error = err2;
 	}
 
···
 {
 	struct xfs_perag	*pag = NULL;
 
-	if (xfs_has_realtime(mp))
-		xfs_rt_resv_free(mp);
-
+	xfs_metafile_resv_free(mp);
 	while ((pag = xfs_perag_next(mp, pag)))
 		xfs_ag_resv_free(pag);
 }

fs/xfs/xfs_fsops.h

···
 
 int xfs_growfs_data(struct xfs_mount *mp, struct xfs_growfs_data *in);
 int xfs_growfs_log(struct xfs_mount *mp, struct xfs_growfs_log *in);
-int xfs_reserve_blocks(struct xfs_mount *mp, uint64_t request);
+int xfs_reserve_blocks(struct xfs_mount *mp, enum xfs_free_counter cnt,
+		uint64_t request);
 int xfs_fs_goingdown(struct xfs_mount *mp, uint32_t inflags);
 
 int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);

fs/xfs/xfs_icache.c

···
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
-	if (!XFS_IS_REALTIME_INODE(ip))
+	if (!XFS_IS_REALTIME_INODE(ip) || xfs_has_zoned(mp))
 		return false;
 
-	if (__percpu_counter_compare(&mp->m_frextents,
+	if (xfs_compare_freecounter(mp, XC_FREE_RTEXTENTS,
 				mp->m_low_rtexts[XFS_LOWSP_5_PCNT],
 				XFS_FDBLOCKS_BATCH) < 0)
 		return true;
···
 	if (items > mp->m_ino_geo.inodes_per_cluster)
 		return true;
 
-	if (__percpu_counter_compare(&mp->m_fdblocks,
+	if (xfs_compare_freecounter(mp, XC_FREE_BLOCKS,
 				mp->m_low_space[XFS_LOWSP_5_PCNT],
 				XFS_FDBLOCKS_BATCH) < 0)
 		return true;

fs/xfs/xfs_inode.c

···
 		 * to mark all the active inodes on the buffer stale.
 		 */
 		error = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
-				mp->m_bsize * igeo->blocks_per_cluster,
-				XBF_UNMAPPED, &bp);
+				mp->m_bsize * igeo->blocks_per_cluster, 0, &bp);
 		if (error)
 			return error;
 
···
 xfs_is_always_cow_inode(
 	const struct xfs_inode	*ip)
 {
-	return ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount);
+	return xfs_is_zoned_inode(ip) ||
+		(ip->i_mount->m_always_cow && xfs_has_reflink(ip->i_mount));
 }

fs/xfs/xfs_inode.h

···
 typedef struct xfs_inode {
 	/* Inode linking and identification information. */
 	struct xfs_mount	*i_mount;	/* fs mount struct ptr */
-	union {
-		struct {
-			struct xfs_dquot *i_udquot;	/* user dquot */
-			struct xfs_dquot *i_gdquot;	/* group dquot */
-			struct xfs_dquot *i_pdquot;	/* project dquot */
-		};
-
-		/*
-		 * Space that has been set aside to accomodate expansions of a
-		 * metadata btree rooted in this file.
-		 */
-		uint64_t	i_meta_resv_asked;
-	};
+	struct xfs_dquot	*i_udquot;	/* user dquot */
+	struct xfs_dquot	*i_gdquot;	/* group dquot */
+	struct xfs_dquot	*i_pdquot;	/* project dquot */
 
 	/* Inode location stuff */
 	xfs_ino_t		i_ino;		/* inode number (agno/agino)*/
···
 	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 */
 	};
···
 	return ip->i_ino == mp->m_sb.sb_rbmino ||
 	       ip->i_ino == mp->m_sb.sb_rsumino ||
 	       xfs_is_quota_inode(&mp->m_sb, ip->i_ino);
+}
+
+static inline bool xfs_is_zoned_inode(const struct xfs_inode *ip)
+{
+	return xfs_has_zoned(ip->i_mount) && XFS_IS_REALTIME_INODE(ip);
 }
 
 bool xfs_is_always_cow_inode(const struct xfs_inode *ip);

fs/xfs/xfs_inode_item.c

···
 		to->di_changecount = inode_peek_iversion(inode);
 		to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime);
 		to->di_flags2 = ip->i_diflags2;
+		/* also covers the di_used_blocks union arm: */
 		to->di_cowextsize = ip->i_cowextsize;
 		to->di_ino = ip->i_ino;
 		to->di_lsn = lsn;

fs/xfs/xfs_inode_item_recover.c

···
 		to->di_crtime = xfs_log_dinode_to_disk_ts(from,
 							  from->di_crtime);
 		to->di_flags2 = cpu_to_be64(from->di_flags2);
+		/* also covers the di_used_blocks union arm: */
 		to->di_cowextsize = cpu_to_be32(from->di_cowextsize);
 		to->di_ino = cpu_to_be64(from->di_ino);
 		to->di_lsn = cpu_to_be64(lsn);

fs/xfs/xfs_ioctl.c

···
 		error = mnt_want_write_file(filp);
 		if (error)
 			return error;
-		error = xfs_reserve_blocks(mp, fsop.resblks);
+		error = xfs_reserve_blocks(mp, XC_FREE_BLOCKS, fsop.resblks);
 		mnt_drop_write_file(filp);
 		if (error)
 			return error;
 	}
 
 	spin_lock(&mp->m_sb_lock);
-	fsop.resblks = mp->m_resblks;
-	fsop.resblks_avail = mp->m_resblks_avail;
+	fsop.resblks = mp->m_free[XC_FREE_BLOCKS].res_total;
+	fsop.resblks_avail = mp->m_free[XC_FREE_BLOCKS].res_avail;
 	spin_unlock(&mp->m_sb_lock);
 
 	if (copy_to_user(arg, &fsop, sizeof(fsop)))
···
 	struct xfs_fsop_counts	out = {
 		.allocino = percpu_counter_read_positive(&mp->m_icount),
 		.freeino  = percpu_counter_read_positive(&mp->m_ifree),
-		.freedata = percpu_counter_read_positive(&mp->m_fdblocks) -
-				xfs_fdblocks_unavailable(mp),
-		.freertx  = percpu_counter_read_positive(&mp->m_frextents),
+		.freedata = xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) -
+				xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS),
+		.freertx  = xfs_estimate_freecounter(mp, XC_FREE_RTEXTENTS),
 	};
 
 	if (copy_to_user(uarg, &out, sizeof(out)))

fs/xfs/xfs_iomap.c

···
 #include "xfs_reflink.h"
 #include "xfs_health.h"
 #include "xfs_rtbitmap.h"
+#include "xfs_icache.h"
+#include "xfs_zone_alloc.h"
 
 #define XFS_ALLOC_ALIGN(mp, off) \
 	(((off) >> mp->m_allocsize_log) << mp->m_allocsize_log)
···
 
 static int64_t
 xfs_iomap_freesp(
-	struct percpu_counter	*counter,
+	struct xfs_mount	*mp,
+	unsigned int		idx,
 	uint64_t		low_space[XFS_LOWSP_MAX],
 	int			*shift)
 {
 	int64_t			freesp;
 
-	freesp = percpu_counter_read_positive(counter);
+	freesp = xfs_estimate_freecounter(mp, idx);
 	if (freesp < low_space[XFS_LOWSP_5_PCNT]) {
 		*shift = 2;
 		if (freesp < low_space[XFS_LOWSP_4_PCNT])
···
 
 	if (unlikely(XFS_IS_REALTIME_INODE(ip)))
 		freesp = xfs_rtbxlen_to_blen(mp,
-				xfs_iomap_freesp(&mp->m_frextents,
+				xfs_iomap_freesp(mp, XC_FREE_RTEXTENTS,
 					mp->m_low_rtexts, &shift));
 	else
-		freesp = xfs_iomap_freesp(&mp->m_fdblocks, mp->m_low_space,
+		freesp = xfs_iomap_freesp(mp, XC_FREE_BLOCKS, mp->m_low_space,
 				&shift);
 
 	/*
···
 	.iomap_begin		= xfs_direct_write_iomap_begin,
 };
 
+#ifdef CONFIG_XFS_RT
+/*
+ * This is really simple.  The space has already been reserved before taking the
+ * IOLOCK, the actual block allocation is done just before submitting the bio
+ * and only recorded in the extent map on I/O completion.
+ */
+static int
+xfs_zoned_direct_write_iomap_begin(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			length,
+	unsigned		flags,
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
+{
+	struct xfs_inode	*ip = XFS_I(inode);
+	int			error;
+
+	ASSERT(!(flags & IOMAP_OVERWRITE_ONLY));
+
+	/*
+	 * Needs to be pushed down into the allocator so that only writes into
+	 * a single zone can be supported.
+	 */
+	if (flags & IOMAP_NOWAIT)
+		return -EAGAIN;
+
+	/*
+	 * Ensure the extent list is in memory in so that we don't have to do
+	 * read it from the I/O completion handler.
+	 */
+	if (xfs_need_iread_extents(&ip->i_df)) {
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		if (error)
+			return error;
+	}
+
+	iomap->type = IOMAP_MAPPED;
+	iomap->flags = IOMAP_F_DIRTY;
+	iomap->bdev = ip->i_mount->m_rtdev_targp->bt_bdev;
+	iomap->offset = offset;
+	iomap->length = length;
+	iomap->flags = IOMAP_F_ANON_WRITE;
+	return 0;
+}
+
+const struct iomap_ops xfs_zoned_direct_write_iomap_ops = {
+	.iomap_begin		= xfs_zoned_direct_write_iomap_begin,
+};
+#endif /* CONFIG_XFS_RT */
+
 static int
 xfs_dax_write_iomap_end(
 	struct inode		*inode,
···
 	.iomap_begin	= xfs_direct_write_iomap_begin,
 	.iomap_end	= xfs_dax_write_iomap_end,
 };
+
+/*
+ * Convert a hole to a delayed allocation.
+ */
+static void
+xfs_bmap_add_extent_hole_delay(
+	struct xfs_inode	*ip,	/* incore inode pointer */
+	int			whichfork,
+	struct xfs_iext_cursor	*icur,
+	struct xfs_bmbt_irec	*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);
+	}
+}
+
+/*
+ * 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.
+ */
+static 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)) {
+		ASSERT(!xfs_is_zoned_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_zoned_buffered_write_iomap_begin(
+	struct inode		*inode,
+	loff_t			offset,
+	loff_t			count,
+	unsigned		flags,
+	struct iomap		*iomap,
+	struct iomap		*srcmap)
+{
+	struct iomap_iter	*iter =
+		container_of(iomap, struct iomap_iter, iomap);
+	struct xfs_zone_alloc_ctx *ac = iter->private;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, count);
+	u16			iomap_flags = IOMAP_F_SHARED;
+	unsigned int		lockmode = XFS_ILOCK_EXCL;
+	xfs_filblks_t		count_fsb;
+	xfs_extlen_t		indlen;
+	struct xfs_bmbt_irec	got;
+	struct xfs_iext_cursor	icur;
+	int			error = 0;
+
+	ASSERT(!xfs_get_extsz_hint(ip));
+	ASSERT(!(flags & IOMAP_UNSHARE));
+	ASSERT(ac);
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	error = xfs_qm_dqattach(ip);
+	if (error)
+		return error;
+
+	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
+	if (error)
+		return error;
+
+	if (XFS_IS_CORRUPT(mp, !xfs_ifork_has_extents(&ip->i_df)) ||
+	    XFS_TEST_ERROR(false, mp, XFS_ERRTAG_BMAPIFORMAT)) {
+		xfs_bmap_mark_sick(ip, XFS_DATA_FORK);
+		error = -EFSCORRUPTED;
+		goto out_unlock;
+	}
+
+	XFS_STATS_INC(mp, xs_blk_mapw);
+
+	error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+	if (error)
+		goto out_unlock;
+
+	/*
+	 * For zeroing operations check if there is any data to zero first.
+	 *
+	 * For regular writes we always need to allocate new blocks, but need to
+	 * provide the source mapping when the range is unaligned to support
+	 * read-modify-write of the whole block in the page cache.
+	 *
+	 * In either case we need to limit the reported range to the boundaries
+	 * of the source map in the data fork.
+	 */
+	if (!IS_ALIGNED(offset, mp->m_sb.sb_blocksize) ||
+	    !IS_ALIGNED(offset + count, mp->m_sb.sb_blocksize) ||
+	    (flags & IOMAP_ZERO)) {
+		struct xfs_bmbt_irec	smap;
+		struct xfs_iext_cursor	scur;
+
+		if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &scur,
+				&smap))
+			smap.br_startoff = end_fsb; /* fake hole until EOF */
+		if (smap.br_startoff > offset_fsb) {
+			/*
+			 * We never need to allocate blocks for zeroing a hole.
+			 */
+			if (flags & IOMAP_ZERO) {
+				xfs_hole_to_iomap(ip, iomap, offset_fsb,
+						smap.br_startoff);
+				goto out_unlock;
+			}
+			end_fsb = min(end_fsb, smap.br_startoff);
+		} else {
+			end_fsb = min(end_fsb,
+				smap.br_startoff + smap.br_blockcount);
+			xfs_trim_extent(&smap, offset_fsb,
+					end_fsb - offset_fsb);
+			error = xfs_bmbt_to_iomap(ip, srcmap, &smap, flags, 0,
+					xfs_iomap_inode_sequence(ip, 0));
+			if (error)
+				goto out_unlock;
+		}
+	}
+
+	if (!ip->i_cowfp)
+		xfs_ifork_init_cow(ip);
+
+	if (!xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &got))
+		got.br_startoff = end_fsb;
+	if (got.br_startoff <= offset_fsb) {
+		trace_xfs_reflink_cow_found(ip, &got);
+		goto done;
+	}
+
+	/*
+	 * Cap the maximum length to keep the chunks of work done here somewhat
+	 * symmetric with the work writeback does.
+	 */
+	end_fsb = min(end_fsb, got.br_startoff);
+	count_fsb = min3(end_fsb - offset_fsb, XFS_MAX_BMBT_EXTLEN,
+			 XFS_B_TO_FSB(mp, 1024 * PAGE_SIZE));
+
+	/*
+	 * The block reservation is supposed to cover all blocks that the
+	 * operation could possible write, but there is a nasty corner case
+	 * where blocks could be stolen from underneath us:
+	 *
+	 *  1) while this thread iterates over a larger buffered write,
+	 *  2) another thread is causing a write fault that calls into
+	 *     ->page_mkwrite in range this thread writes to, using up the
+	 *     delalloc reservation created by a previous call to this function.
+	 *  3) another thread does direct I/O on the range that the write fault
+	 *     happened on, which causes writeback of the dirty data.
+	 *  4) this then set the stale flag, which cuts the current iomap
+	 *     iteration short, causing the new call to ->iomap_begin that gets
+	 *     us here again, but now without a sufficient reservation.
+	 *
+	 * This is a very unusual I/O pattern, and nothing but generic/095 is
+	 * known to hit it. There's not really much we can do here, so turn this
+	 * into a short write.
+	 */
+	if (count_fsb > ac->reserved_blocks) {
+		xfs_warn_ratelimited(mp,
+"Short write on ino 0x%llx comm %.20s due to three-way race with write fault and direct I/O",
+			ip->i_ino, current->comm);
+		count_fsb = ac->reserved_blocks;
+		if (!count_fsb) {
+			error = -EIO;
+			goto out_unlock;
+		}
+	}
+
+	error = xfs_quota_reserve_blkres(ip, count_fsb);
+	if (error)
+		goto out_unlock;
+
+	indlen = xfs_bmap_worst_indlen(ip, count_fsb);
+	error = xfs_dec_fdblocks(mp, indlen, false);
+	if (error)
+		goto out_unlock;
+	ip->i_delayed_blks += count_fsb;
+	xfs_mod_delalloc(ip, count_fsb, indlen);
+
+	got.br_startoff = offset_fsb;
+	got.br_startblock = nullstartblock(indlen);
+	got.br_blockcount = count_fsb;
+	got.br_state = XFS_EXT_NORM;
+	xfs_bmap_add_extent_hole_delay(ip, XFS_COW_FORK, &icur, &got);
+	ac->reserved_blocks -= count_fsb;
+	iomap_flags |= IOMAP_F_NEW;
+
+	trace_xfs_iomap_alloc(ip, offset, XFS_FSB_TO_B(mp, count_fsb),
+			XFS_COW_FORK, &got);
+done:
+	error = xfs_bmbt_to_iomap(ip, iomap, &got, flags, iomap_flags,
+			xfs_iomap_inode_sequence(ip, IOMAP_F_SHARED));
+out_unlock:
+	xfs_iunlock(ip, lockmode);
+	return error;
+}
 
 static int
 xfs_buffered_write_iomap_begin(
···
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
+
+	if (xfs_is_zoned_inode(ip))
+		return xfs_zoned_buffered_write_iomap_begin(inode, offset,
+				count, flags, iomap, srcmap);
 
 	/* we can't use delayed allocations when using extent size hints */
 	if (xfs_get_extsz_hint(ip))
···
 	loff_t			length,
 	struct iomap		*iomap)
 {
+	struct iomap_iter	*iter =
+		container_of(iomap, struct iomap_iter, iomap);
+
 	xfs_bmap_punch_delalloc_range(XFS_I(inode),
 			(iomap->flags & IOMAP_F_SHARED) ?
 				XFS_COW_FORK : XFS_DATA_FORK,
-			offset, offset + length);
+			offset, offset + length, iter->private);
 }
 
 static int
···
 	struct xfs_inode	*ip,
 	loff_t			pos,
 	loff_t			len,
+	struct xfs_zone_alloc_ctx *ac,
 	bool			*did_zero)
 {
 	struct inode		*inode = VFS_I(ip);
···
 		return dax_zero_range(inode, pos, len, did_zero,
 				      &xfs_dax_write_iomap_ops);
 	return iomap_zero_range(inode, pos, len, did_zero,
-				&xfs_buffered_write_iomap_ops, NULL);
+				&xfs_buffered_write_iomap_ops, ac);
 }
 
 int
 xfs_truncate_page(
 	struct xfs_inode	*ip,
 	loff_t			pos,
+	struct xfs_zone_alloc_ctx *ac,
 	bool			*did_zero)
 {
 	struct inode		*inode = VFS_I(ip);
···
 		return dax_truncate_page(inode, pos, did_zero,
 					&xfs_dax_write_iomap_ops);
 	return iomap_truncate_page(inode, pos, did_zero,
-				   &xfs_buffered_write_iomap_ops, NULL);
+				   &xfs_buffered_write_iomap_ops, ac);
 }

fs/xfs/xfs_iomap.h

···
 
 struct xfs_inode;
 struct xfs_bmbt_irec;
+struct xfs_zone_alloc_ctx;
 
 int xfs_iomap_write_direct(struct xfs_inode *ip, xfs_fileoff_t offset_fsb,
 		xfs_fileoff_t count_fsb, unsigned int flags,
···
 		u16 iomap_flags, u64 sequence_cookie);
 
 int xfs_zero_range(struct xfs_inode *ip, loff_t pos, loff_t len,
-		bool *did_zero);
-int xfs_truncate_page(struct xfs_inode *ip, loff_t pos, bool *did_zero);
+		struct xfs_zone_alloc_ctx *ac, bool *did_zero);
+int xfs_truncate_page(struct xfs_inode *ip, loff_t pos,
+		struct xfs_zone_alloc_ctx *ac, bool *did_zero);
 
 static inline xfs_filblks_t
 xfs_aligned_fsb_count(
···
 
 extern const struct iomap_ops xfs_buffered_write_iomap_ops;
 extern const struct iomap_ops xfs_direct_write_iomap_ops;
+extern const struct iomap_ops xfs_zoned_direct_write_iomap_ops;
 extern const struct iomap_ops xfs_read_iomap_ops;
 extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;

fs/xfs/xfs_iops.c

···
 #include "xfs_xattr.h"
 #include "xfs_file.h"
 #include "xfs_bmap.h"
+#include "xfs_zone_alloc.h"
 
 #include <linux/posix_acl.h>
 #include <linux/security.h>
···
 	uint			lock_flags = 0;
 	uint			resblks = 0;
 	bool			did_zeroing = false;
+	struct xfs_zone_alloc_ctx ac = { };
 
 	xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL);
 	ASSERT(S_ISREG(inode->i_mode));
···
 	inode_dio_wait(inode);
 
 	/*
+	 * Normally xfs_zoned_space_reserve is supposed to be called outside the
+	 * IOLOCK.  For truncate we can't do that since ->setattr is called with
+	 * it already held by the VFS.  So for now chicken out and try to
+	 * allocate space under it.
+	 *
+	 * To avoid deadlocks this means we can't block waiting for space, which
+	 * can lead to spurious -ENOSPC if there are no directly available
+	 * blocks.  We mitigate this a bit by allowing zeroing to dip into the
+	 * reserved pool, but eventually the VFS calling convention needs to
+	 * change.
+	 */
+	if (xfs_is_zoned_inode(ip)) {
+		error = xfs_zoned_space_reserve(ip, 1,
+				XFS_ZR_NOWAIT | XFS_ZR_RESERVED, &ac);
+		if (error) {
+			if (error == -EAGAIN)
+				return -ENOSPC;
+			return error;
+		}
+	}
+
+	/*
 	 * File data changes must be complete before we start the transaction to
 	 * modify the inode.  This needs to be done before joining the inode to
 	 * the transaction because the inode cannot be unlocked once it is a
···
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
 		error = xfs_zero_range(ip, oldsize, newsize - oldsize,
-				&did_zeroing);
+				&ac, &did_zeroing);
 	} else {
-		error = xfs_truncate_page(ip, newsize, &did_zeroing);
+		error = xfs_truncate_page(ip, newsize, &ac, &did_zeroing);
 	}
+
+	if (xfs_is_zoned_inode(ip))
+		xfs_zoned_space_unreserve(ip, &ac);
 
 	if (error)
 		return error;

fs/xfs/xfs_log.c

···
 #include "xfs_sysfs.h"
 #include "xfs_sb.h"
 #include "xfs_health.h"
+#include "xfs_zone_alloc.h"
 
 struct kmem_cache	*xfs_log_ticket_cache;
 
···
 	spin_unlock(&log->l_icloglock);
 
 	wake_up_var(&log->l_opstate);
+	if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(log->l_mp))
+		xfs_zoned_wake_all(log->l_mp);
+
 	return log_error;
 }
 

fs/xfs/xfs_message.c

···
 			.opstate	= XFS_OPSTATE_WARNED_METADIR,
 			.name		= "metadata directory tree",
 		},
+		[XFS_EXPERIMENTAL_ZONED] = {
+			.opstate	= XFS_OPSTATE_WARNED_ZONED,
+			.name		= "zoned RT device",
+		},
 	};
 	ASSERT(feat >= 0 && feat < XFS_EXPERIMENTAL_MAX);
 	BUILD_BUG_ON(ARRAY_SIZE(features) != XFS_EXPERIMENTAL_MAX);

fs/xfs/xfs_message.h

···
 	XFS_EXPERIMENTAL_EXCHRANGE,
 	XFS_EXPERIMENTAL_PPTR,
 	XFS_EXPERIMENTAL_METADIR,
+	XFS_EXPERIMENTAL_ZONED,
 
 	XFS_EXPERIMENTAL_MAX,
 };

fs/xfs/xfs_mount.c

···
 #include "xfs_rtrmap_btree.h"
 #include "xfs_rtrefcount_btree.h"
 #include "scrub/stats.h"
+#include "xfs_zone_alloc.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
 static int xfs_uuid_table_size;
···
 	 */
 reread:
 	error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-				      BTOBB(sector_size), 0, &bp, buf_ops);
+				      BTOBB(sector_size), &bp, buf_ops);
 	if (error) {
 		if (loud)
 			xfs_warn(mp, "SB validate failed with error %d.", error);
···
 	}
 	error = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+					XFS_FSS_TO_BB(mp, 1), &bp, NULL);
 	if (error) {
 		xfs_warn(mp, "last sector read failed");
 		return error;
···
 	}
 	error = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+					XFS_FSB_TO_BB(mp, 1), &bp, NULL);
 	if (error) {
 		xfs_warn(mp, "log device read failed");
 		return error;
···
 	return xfs_sync_sb(mp, false);
 }
 
-uint64_t
-xfs_default_resblks(xfs_mount_t *mp)
-{
-	uint64_t resblks;
+static const char *const xfs_free_pool_name[] = {
+	[XC_FREE_BLOCKS]	= "free blocks",
+	[XC_FREE_RTEXTENTS]	= "free rt extents",
+	[XC_FREE_RTAVAILABLE]	= "available rt extents",
+};
 
-	/*
-	 * We default to 5% or 8192 fsbs of space reserved, whichever is
-	 * smaller.  This is intended to cover concurrent allocation
-	 * transactions when we initially hit enospc. These each require a 4
-	 * block reservation. Hence by default we cover roughly 2000 concurrent
-	 * allocation reservations.
-	 */
-	resblks = mp->m_sb.sb_dblocks;
-	do_div(resblks, 20);
-	resblks = min_t(uint64_t, resblks, 8192);
-	return resblks;
+uint64_t
+xfs_default_resblks(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr)
+{
+	switch (ctr) {
+	case XC_FREE_BLOCKS:
+		/*
+		 * Default to 5% or 8192 FSBs of space reserved, whichever is
+		 * smaller.
+		 *
+		 * This is intended to cover concurrent allocation transactions
+		 * when we initially hit ENOSPC.  These each require a 4 block
+		 * reservation. Hence by default we cover roughly 2000
+		 * concurrent allocation reservations.
+		 */
+		return min(div_u64(mp->m_sb.sb_dblocks, 20), 8192ULL);
+	case XC_FREE_RTEXTENTS:
+	case XC_FREE_RTAVAILABLE:
+		if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp))
+			return xfs_zoned_default_resblks(mp, ctr);
+		return 0;
+	default:
+		ASSERT(0);
+		return 0;
+	}
 }
 
 /* Ensure the summary counts are correct. */
···
 	 * If we're mounting the rt volume after recovering the log, recompute
 	 * frextents from the rtbitmap file to fix the inconsistency.
 	 */
-	if (xfs_has_realtime(mp) && !xfs_is_clean(mp)) {
+	if (xfs_has_realtime(mp) && !xfs_has_zoned(mp) && !xfs_is_clean(mp)) {
 		error = xfs_rtalloc_reinit_frextents(mp);
 		if (error)
 			return error;
···
 	uint			quotamount = 0;
 	uint			quotaflags = 0;
 	int			error = 0;
+	int			i;
 
 	xfs_sb_mount_common(mp, sbp);
 
···
 	/* enable fail_at_unmount as default */
 	mp->m_fail_unmount = true;
 
-	super_set_sysfs_name_id(mp->m_super);
-
-	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
-			       NULL, mp->m_super->s_id);
-	if (error)
-		goto out;
-
-	error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
-			       &mp->m_kobj, "stats");
-	if (error)
-		goto out_remove_sysfs;
-
-	xchk_stats_register(mp->m_scrub_stats, mp->m_debugfs);
-
-	error = xfs_error_sysfs_init(mp);
+	error = xfs_mount_sysfs_init(mp);
 	if (error)
 		goto out_remove_scrub_stats;
 
+	xchk_stats_register(mp->m_scrub_stats, mp->m_debugfs);
+
 	error = xfs_errortag_init(mp);
 	if (error)
-		goto out_remove_error_sysfs;
+		goto out_remove_sysfs;
 
 	error = xfs_uuid_mount(mp);
 	if (error)
···
 	if (xfs_is_readonly(mp) && !xfs_has_norecovery(mp))
 		xfs_log_clean(mp);
 
+	if (xfs_has_zoned(mp)) {
+		error = xfs_mount_zones(mp);
+		if (error)
+			goto out_rtunmount;
+	}
+
 	/*
 	 * Complete the quota initialisation, post-log-replay component.
 	 */
···
 	 * privileged transactions. This is needed so that transaction
 	 * space required for critical operations can dip into this pool
 	 * when at ENOSPC. This is needed for operations like create with
-	 * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
-	 * are not allowed to use this reserved space.
+	 * attr, unwritten extent conversion at ENOSPC, garbage collection
+	 * etc. Data allocations are not allowed to use this reserved space.
 	 *
 	 * This may drive us straight to ENOSPC on mount, but that implies
 	 * we were already there on the last unmount. Warn if this occurs.
 	 */
 	if (!xfs_is_readonly(mp)) {
-		error = xfs_reserve_blocks(mp, xfs_default_resblks(mp));
-		if (error)
-			xfs_warn(mp,
-	"Unable to allocate reserve blocks. Continuing without reserve pool.");
+		for (i = 0; i < XC_FREE_NR; i++) {
+			error = xfs_reserve_blocks(mp, i,
+					xfs_default_resblks(mp, i));
+			if (error)
+				xfs_warn(mp,
+"Unable to allocate reserve blocks. Continuing without reserve pool for %s.",
+					xfs_free_pool_name[i]);
+		}
 
 		/* Reserve AG blocks for future btree expansion. */
 		error = xfs_fs_reserve_ag_blocks(mp);
 		if (error && error != -ENOSPC)
 			goto out_agresv;
+
+		xfs_zone_gc_start(mp);
 	}
 
 	return 0;
···
  out_agresv:
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
+	if (xfs_has_zoned(mp))
+		xfs_unmount_zones(mp);
  out_rtunmount:
 	xfs_rtunmount_inodes(mp);
  out_rele_rip:
···
 	xfs_uuid_unmount(mp);
  out_remove_errortag:
 	xfs_errortag_del(mp);
- out_remove_error_sysfs:
-	xfs_error_sysfs_del(mp);
+ out_remove_sysfs:
+	xfs_mount_sysfs_del(mp);
  out_remove_scrub_stats:
 	xchk_stats_unregister(mp->m_scrub_stats);
-	xfs_sysfs_del(&mp->m_stats.xs_kobj);
- out_remove_sysfs:
-	xfs_sysfs_del(&mp->m_kobj);
  out:
 	return error;
 }
···
 	xfs_inodegc_flush(mp);
 
 	xfs_blockgc_stop(mp);
+	if (!test_bit(XFS_OPSTATE_READONLY, &mp->m_opstate))
+		xfs_zone_gc_stop(mp);
 	xfs_fs_unreserve_ag_blocks(mp);
 	xfs_qm_unmount_quotas(mp);
+	if (xfs_has_zoned(mp))
+		xfs_unmount_zones(mp);
 	xfs_rtunmount_inodes(mp);
 	xfs_irele(mp->m_rootip);
 	if (mp->m_metadirip)
···
 	 * we only every apply deltas to the superblock and hence the incore
 	 * value does not matter....
 	 */
-	error = xfs_reserve_blocks(mp, 0);
+	error = xfs_reserve_blocks(mp, XC_FREE_BLOCKS, 0);
 	if (error)
 		xfs_warn(mp, "Unable to free reserved block pool. "
 				"Freespace may not be correct on next mount.");
···
 	xfs_free_rtgroups(mp, 0, mp->m_sb.sb_rgcount);
 	xfs_free_perag_range(mp, 0, mp->m_sb.sb_agcount);
 	xfs_errortag_del(mp);
-	xfs_error_sysfs_del(mp);
 	xchk_stats_unregister(mp->m_scrub_stats);
-	xfs_sysfs_del(&mp->m_stats.xs_kobj);
-	xfs_sysfs_del(&mp->m_kobj);
+	xfs_mount_sysfs_del(mp);
 }
 
 /*
···
 	return true;
 }
 
+/*
+ * Estimate the amount of free space that is not available to userspace and is
+ * not explicitly reserved from the incore fdblocks.  This includes:
+ *
+ * - The minimum number of blocks needed to support splitting a bmap btree
+ * - The blocks currently in use by the freespace btrees because they record
+ *   the actual blocks that will fill per-AG metadata space reservations
+ */
+uint64_t
+xfs_freecounter_unavailable(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr)
+{
+	if (ctr != XC_FREE_BLOCKS)
+		return 0;
+	return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
+}
+
 void
 xfs_add_freecounter(
 	struct xfs_mount	*mp,
-	struct percpu_counter	*counter,
+	enum xfs_free_counter	ctr,
 	uint64_t		delta)
 {
-	bool			has_resv_pool = (counter == &mp->m_fdblocks);
+	struct xfs_freecounter	*counter = &mp->m_free[ctr];
 	uint64_t		res_used;
 
 	/*
 	 * If the reserve pool is depleted, put blocks back into it first.
 	 * Most of the time the pool is full.
 	 */
-	if (!has_resv_pool || mp->m_resblks == mp->m_resblks_avail) {
-		percpu_counter_add(counter, delta);
+	if (likely(counter->res_avail == counter->res_total)) {
+		percpu_counter_add(&counter->count, delta);
 		return;
 	}
 
 	spin_lock(&mp->m_sb_lock);
-	res_used = mp->m_resblks - mp->m_resblks_avail;
+	res_used = counter->res_total - counter->res_avail;
 	if (res_used > delta) {
-		mp->m_resblks_avail += delta;
+		counter->res_avail += delta;
 	} else {
 		delta -= res_used;
-		mp->m_resblks_avail = mp->m_resblks;
-		percpu_counter_add(counter, delta);
+		counter->res_avail = counter->res_total;
+		percpu_counter_add(&counter->count, delta);
 	}
 	spin_unlock(&mp->m_sb_lock);
 }
 
+
+/* Adjust in-core free blocks or RT extents. */
 int
 xfs_dec_freecounter(
 	struct xfs_mount	*mp,
-	struct percpu_counter	*counter,
+	enum xfs_free_counter	ctr,
 	uint64_t		delta,
 	bool			rsvd)
 {
-	int64_t			lcounter;
-	uint64_t		set_aside = 0;
+	struct xfs_freecounter	*counter = &mp->m_free[ctr];
 	s32			batch;
-	bool			has_resv_pool;
 
-	ASSERT(counter == &mp->m_fdblocks || counter == &mp->m_frextents);
-	has_resv_pool = (counter == &mp->m_fdblocks);
-	if (rsvd)
-		ASSERT(has_resv_pool);
+	ASSERT(ctr < XC_FREE_NR);
 
 	/*
 	 * Taking blocks away, need to be more accurate the closer we
···
 	 * then make everything serialise as we are real close to
 	 * ENOSPC.
 	 */
-	if (__percpu_counter_compare(counter, 2 * XFS_FDBLOCKS_BATCH,
+	if (__percpu_counter_compare(&counter->count, 2 * XFS_FDBLOCKS_BATCH,
 				     XFS_FDBLOCKS_BATCH) < 0)
 		batch = 1;
 	else
···
 	 * problems (i.e. transaction abort, pagecache discards, etc.) than
 	 * slightly premature -ENOSPC.
 	 */
-	if (has_resv_pool)
-		set_aside = xfs_fdblocks_unavailable(mp);
-	percpu_counter_add_batch(counter, -((int64_t)delta), batch);
-	if (__percpu_counter_compare(counter, set_aside,
-				     XFS_FDBLOCKS_BATCH) >= 0) {
-		/* we had space! */
-		return 0;
-	}
-
-	/*
-	 * lock up the sb for dipping into reserves before releasing the space
-	 * that took us to ENOSPC.
-	 */
-	spin_lock(&mp->m_sb_lock);
-	percpu_counter_add(counter, delta);
-	if (!has_resv_pool || !rsvd)
-		goto fdblocks_enospc;
-
-	lcounter = (long long)mp->m_resblks_avail - delta;
-	if (lcounter >= 0) {
-		mp->m_resblks_avail = lcounter;
-		spin_unlock(&mp->m_sb_lock);
-		return 0;
-	}
-	xfs_warn_once(mp,
+	percpu_counter_add_batch(&counter->count, -((int64_t)delta), batch);
+	if (__percpu_counter_compare(&counter->count,
+			xfs_freecounter_unavailable(mp, ctr),
+			XFS_FDBLOCKS_BATCH) < 0) {
+		/*
+		 * Lock up the sb for dipping into reserves before releasing the
+		 * space that took us to ENOSPC.
+		 */
+		spin_lock(&mp->m_sb_lock);
+		percpu_counter_add(&counter->count, delta);
+		if (!rsvd)
+			goto fdblocks_enospc;
+		if (delta > counter->res_avail) {
+			if (ctr == XC_FREE_BLOCKS)
+				xfs_warn_once(mp,
 "Reserve blocks depleted! Consider increasing reserve pool size.");
+			goto fdblocks_enospc;
+		}
+		counter->res_avail -= delta;
+		trace_xfs_freecounter_reserved(mp, ctr, delta, _RET_IP_);
+		spin_unlock(&mp->m_sb_lock);
+	}
+
+	/* we had space! */
+	return 0;
 
 fdblocks_enospc:
+	trace_xfs_freecounter_enospc(mp, ctr, delta, _RET_IP_);
 	spin_unlock(&mp->m_sb_lock);
 	return -ENOSPC;
 }

fs/xfs/xfs_mount.h

···
 	uint8_t			blklog;
 
 	/*
+	 * Zoned devices can have gaps beyond the usable capacity of a zone and
+	 * the end in the LBA/daddr address space.  In other words, the hardware
+	 * equivalent to the RT groups already takes care of the power of 2
+	 * alignment for us.  In this case the sparse FSB/RTB address space maps
+	 * 1:1 to the device address space.
+	 */
+	bool			has_daddr_gaps;
+
+	/*
 	 * Mask to extract the group-relative block number from a FSB.
 	 * For a pre-rtgroups filesystem we pretend to have one very large
 	 * rtgroup, so this mask must be 64-bit.
 	 */
 	uint64_t		blkmask;
+
+	/*
+	 * Start of the first group in the device.  This is used to support a
+	 * RT device following the data device on the same block device for
+	 * SMR hard drives.
+	 */
+	xfs_fsblock_t		start_fsb;
+};
+
+struct xfs_freecounter {
+	/* free blocks for general use: */
+	struct percpu_counter	count;
+
+	/* total reserved blocks: */
+	uint64_t		res_total;
+
+	/* available reserved blocks: */
+	uint64_t		res_avail;
+
+	/* reserved blks @ remount,ro: */
+	uint64_t		res_saved;
 };
 
 /*
···
 	bool			m_fail_unmount;
 	bool			m_finobt_nores; /* no per-AG finobt resv. */
 	bool			m_update_sb;	/* sb needs update in mount */
+	unsigned int		m_max_open_zones;
 
 	/*
 	 * Bitsets of per-fs metadata that have been checked and/or are sick.
···
 	spinlock_t ____cacheline_aligned m_sb_lock; /* sb counter lock */
 	struct percpu_counter	m_icount;	/* allocated inodes counter */
 	struct percpu_counter	m_ifree;	/* free inodes counter */
-	struct percpu_counter	m_fdblocks;	/* free block counter */
-	struct percpu_counter	m_frextents;	/* free rt extent counter */
+
+	struct xfs_freecounter	m_free[XC_FREE_NR];
 
 	/*
 	 * Count of data device blocks reserved for delayed allocations,
···
 	atomic64_t		m_allocbt_blks;
 
 	struct xfs_groups	m_groups[XG_TYPE_MAX];
-	uint64_t		m_resblks;	/* total reserved blocks */
-	uint64_t		m_resblks_avail;/* available reserved blocks */
-	uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
 	struct delayed_work	m_reclaim_work;	/* background inode reclaim */
+	struct xfs_zone_info	*m_zone_info;	/* zone allocator information */
 	struct dentry		*m_debugfs;	/* debugfs parent */
 	struct xfs_kobj		m_kobj;
 	struct xfs_kobj		m_error_kobj;
···
 #ifdef CONFIG_XFS_ONLINE_SCRUB_STATS
 	struct xchk_stats	*m_scrub_stats;
 #endif
+	struct xfs_kobj		m_zoned_kobj;
 	xfs_agnumber_t		m_agfrotor;	/* last ag where space found */
 	atomic_t		m_agirotor;	/* last ag dir inode alloced */
 	atomic_t		m_rtgrotor;	/* last rtgroup rtpicked */
+
+	struct mutex		m_metafile_resv_lock;
+	uint64_t		m_metafile_resv_target;
+	uint64_t		m_metafile_resv_used;
+	uint64_t		m_metafile_resv_avail;
 
 	/* Memory shrinker to throttle and reprioritize inodegc */
 	struct shrinker		*m_inodegc_shrinker;
···
 #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 */
 
 /* Mount features */
+#define XFS_FEAT_NOLIFETIME	(1ULL << 47)	/* disable lifetime hints */
 #define XFS_FEAT_NOATTR2	(1ULL << 48)	/* disable attr2 creation */
 #define XFS_FEAT_NOALIGN	(1ULL << 49)	/* ignore alignment */
 #define XFS_FEAT_ALLOCSIZE	(1ULL << 50)	/* user specified allocation size */
···
 __XFS_HAS_FEAT(large_extent_counts, NREXT64)
 __XFS_HAS_FEAT(exchange_range, EXCHANGE_RANGE)
 __XFS_HAS_FEAT(metadir, METADIR)
+__XFS_HAS_FEAT(zoned, ZONED)
+__XFS_HAS_FEAT(nolifetime, NOLIFETIME)
 
 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)
···
 {
 	return xfs_has_metadir(mp) && xfs_has_realtime(mp) &&
 	       xfs_has_reflink(mp);
+}
+
+static inline bool xfs_has_nonzoned(const struct xfs_mount *mp)
+{
+	return !xfs_has_zoned(mp);
 }
 
 /*
···
 #define XFS_OPSTATE_WARNED_METADIR	17
 /* Filesystem should use qflags to determine quotaon status */
 #define XFS_OPSTATE_RESUMING_QUOTAON	18
+/* Kernel has logged a warning about zoned RT device being used on this fs. */
+#define XFS_OPSTATE_WARNED_ZONED	19
+/* (Zoned) GC is in progress */
+#define XFS_OPSTATE_ZONEGC_RUNNING	20
 
 #define __XFS_IS_OPSTATE(name, NAME) \
 static inline bool xfs_is_ ## name (struct xfs_mount *mp) \
···
 #endif /* CONFIG_XFS_QUOTA */
 __XFS_IS_OPSTATE(done_with_log_incompat, UNSET_LOG_INCOMPAT)
 __XFS_IS_OPSTATE(using_logged_xattrs, USE_LARP)
+__XFS_IS_OPSTATE(zonegc_running, ZONEGC_RUNNING)
 
 static inline bool
 xfs_should_warn(struct xfs_mount *mp, long nr)
···
 }
 
 extern void	xfs_uuid_table_free(void);
-extern uint64_t xfs_default_resblks(xfs_mount_t *mp);
+uint64_t	xfs_default_resblks(struct xfs_mount *mp,
+			enum xfs_free_counter ctr);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 extern void	xfs_unmountfs(xfs_mount_t *);
 
···
  */
 #define XFS_FDBLOCKS_BATCH	1024
 
+uint64_t xfs_freecounter_unavailable(struct xfs_mount *mp,
+		enum xfs_free_counter ctr);
+
 /*
- * Estimate the amount of free space that is not available to userspace and is
- * not explicitly reserved from the incore fdblocks.  This includes:
- *
- * - The minimum number of blocks needed to support splitting a bmap btree
- * - The blocks currently in use by the freespace btrees because they record
- *   the actual blocks that will fill per-AG metadata space reservations
+ * Sum up the freecount, but never return negative values.
  */
-static inline uint64_t
-xfs_fdblocks_unavailable(
-	struct xfs_mount	*mp)
+static inline s64 xfs_sum_freecounter(struct xfs_mount *mp,
+		enum xfs_free_counter ctr)
 {
-	return mp->m_alloc_set_aside + atomic64_read(&mp->m_allocbt_blks);
+	return percpu_counter_sum_positive(&mp->m_free[ctr].count);
 }
 
-int xfs_dec_freecounter(struct xfs_mount *mp, struct percpu_counter *counter,
+/*
+ * Same as above, but does return negative values.  Mostly useful for
+ * special cases like repair and tracing.
+ */
+static inline s64 xfs_sum_freecounter_raw(struct xfs_mount *mp,
+		enum xfs_free_counter ctr)
+{
+	return percpu_counter_sum(&mp->m_free[ctr].count);
+}
+
+/*
+ * This just provides and estimate without the cpu-local updates, use
+ * xfs_sum_freecounter for the exact value.
+ */
+static inline s64 xfs_estimate_freecounter(struct xfs_mount *mp,
+		enum xfs_free_counter ctr)
+{
+	return percpu_counter_read_positive(&mp->m_free[ctr].count);
+}
+
+static inline int xfs_compare_freecounter(struct xfs_mount *mp,
+		enum xfs_free_counter ctr, s64 rhs, s32 batch)
+{
+	return __percpu_counter_compare(&mp->m_free[ctr].count, rhs, batch);
+}
+
+static inline void xfs_set_freecounter(struct xfs_mount *mp,
+		enum xfs_free_counter ctr, uint64_t val)
+{
+	percpu_counter_set(&mp->m_free[ctr].count, val);
+}
+
+int xfs_dec_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr,
 		uint64_t delta, bool rsvd);
-void xfs_add_freecounter(struct xfs_mount *mp, struct percpu_counter *counter,
+void xfs_add_freecounter(struct xfs_mount *mp, enum xfs_free_counter ctr,
 		uint64_t delta);
 
 static inline int xfs_dec_fdblocks(struct xfs_mount *mp, uint64_t delta,
 		bool reserved)
 {
-	return xfs_dec_freecounter(mp, &mp->m_fdblocks, delta, reserved);
+	return xfs_dec_freecounter(mp, XC_FREE_BLOCKS, delta, reserved);
 }
 
 static inline void xfs_add_fdblocks(struct xfs_mount *mp, uint64_t delta)
 {
-	xfs_add_freecounter(mp, &mp->m_fdblocks, delta);
+	xfs_add_freecounter(mp, XC_FREE_BLOCKS, delta);
 }
 
 static inline int xfs_dec_frextents(struct xfs_mount *mp, uint64_t delta)
 {
-	return xfs_dec_freecounter(mp, &mp->m_frextents, delta, false);
+	return xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, delta, false);
 }
 
 static inline void xfs_add_frextents(struct xfs_mount *mp, uint64_t delta)
 {
-	xfs_add_freecounter(mp, &mp->m_frextents, delta);
+	xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, delta);
 }
 
 extern int	xfs_readsb(xfs_mount_t *, int);
···
 bool xfs_clear_incompat_log_features(struct xfs_mount *mp);
 void xfs_mod_delalloc(struct xfs_inode *ip, int64_t data_delta,
 		int64_t ind_delta);
+static inline void xfs_mod_sb_delalloc(struct xfs_mount *mp, int64_t delta)
+{
+	percpu_counter_add(&mp->m_delalloc_blks, delta);
+}
 
 #endif	/* __XFS_MOUNT_H__ */

fs/xfs/xfs_qm.c

···
 	 * immediately.  We only support rtquota if rtgroups are enabled to
 	 * avoid problems with older kernels.
 	 */
-	if (mp->m_sb.sb_rextents && !xfs_has_rtgroups(mp)) {
+	if (mp->m_sb.sb_rextents &&
+	    (!xfs_has_rtgroups(mp) || xfs_has_zoned(mp))) {
 		xfs_notice(mp, "Cannot turn on quotas for realtime filesystem");
 		mp->m_qflags = 0;
 		goto write_changes;

fs/xfs/xfs_reflink.c

···
 	int			error = 0;
 
 	/* Holes, unwritten, and delalloc extents cannot be shared */
-	if (!xfs_is_cow_inode(ip) || !xfs_bmap_is_written_extent(irec)) {
+	if (!xfs_is_reflink_inode(ip) || !xfs_bmap_is_written_extent(irec)) {
 		*shared = false;
 		return 0;
 	}
···
 
 		if (isnullstartblock(del.br_startblock)) {
 			xfs_bmap_del_extent_delay(ip, XFS_COW_FORK, &icur, &got,
-					&del);
+					&del, 0);
 		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
 			ASSERT((*tpp)->t_highest_agno == NULLAGNUMBER);
 
···
 	if (!xfs_has_rmapbt(mp))
 		return 0;
 	if (XFS_IS_REALTIME_INODE(ip)) {
-		struct xfs_rtgroup	*rtg;
-		xfs_rgnumber_t		rgno;
-
-		rgno = xfs_rtb_to_rgno(mp, fsb);
-		rtg = xfs_rtgroup_get(mp, rgno);
-		if (xfs_metafile_resv_critical(rtg_rmap(rtg)))
-			error = -ENOSPC;
-		xfs_rtgroup_put(rtg);
-		return error;
+		if (xfs_metafile_resv_critical(mp))
+			return -ENOSPC;
+		return 0;
 	}
 
 	agno = XFS_FSB_TO_AGNO(mp, fsb);
···
 		return 0;
 
 	trace_xfs_zero_eof(ip, isize, pos - isize);
-	return xfs_zero_range(ip, isize, pos - isize, NULL);
+	return xfs_zero_range(ip, isize, pos - isize, NULL, NULL);
 }
 
 /*

fs/xfs/xfs_rtalloc.c

···
 #include "xfs_trace.h"
 #include "xfs_rtrefcount_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_zone_alloc.h"
 
 /*
  * Return whether there are any free extents in the size range given
···
 
 	for (i = 0; i < XFS_RTGI_MAX; i++)
 		xfs_rtginode_irele(&rtg->rtg_inodes[i]);
-	kvfree(rtg->rtg_rsum_cache);
+	if (!xfs_has_zoned(rtg_mount(rtg)))
+		kvfree(rtg->rtg_rsum_cache);
 }
 
 static int
···
 		return 0;
 
 	error = xfs_buf_get_uncached(mp->m_rtdev_targp, XFS_FSB_TO_BB(mp, 1),
-			0, &rtsb_bp);
+			&rtsb_bp);
 	if (error)
 		return error;
 
···
 	if (rtg_rmap(args->rtg) != NULL)
 		error = xfs_rtrmapbt_init_rtsb(nargs->mp, args->rtg, args->tp);
 
+	return error;
+}
+
+static void
+xfs_growfs_rt_sb_fields(
+	struct xfs_trans	*tp,
+	const struct xfs_mount	*nmp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	if (nmp->m_sb.sb_rextsize != mp->m_sb.sb_rextsize)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSIZE,
+			nmp->m_sb.sb_rextsize - mp->m_sb.sb_rextsize);
+	if (nmp->m_sb.sb_rbmblocks != mp->m_sb.sb_rbmblocks)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBMBLOCKS,
+			nmp->m_sb.sb_rbmblocks - mp->m_sb.sb_rbmblocks);
+	if (nmp->m_sb.sb_rblocks != mp->m_sb.sb_rblocks)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_RBLOCKS,
+			nmp->m_sb.sb_rblocks - mp->m_sb.sb_rblocks);
+	if (nmp->m_sb.sb_rextents != mp->m_sb.sb_rextents)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTENTS,
+			nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents);
+	if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_REXTSLOG,
+			nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog);
+	if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount)
+		xfs_trans_mod_sb(tp, XFS_TRANS_SB_RGCOUNT,
+			nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount);
+}
+
+static int
+xfs_growfs_rt_zoned(
+	struct xfs_rtgroup	*rtg,
+	xfs_rfsblock_t		nrblocks)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_mount	*nmp;
+	struct xfs_trans	*tp;
+	xfs_rtbxlen_t		freed_rtx;
+	int			error;
+
+	/*
+	 * Calculate new sb and mount fields for this round.  Also ensure the
+	 * rtg_extents value is uptodate as the rtbitmap code relies on it.
+	 */
+	nmp = xfs_growfs_rt_alloc_fake_mount(mp, nrblocks,
+			mp->m_sb.sb_rextsize);
+	if (!nmp)
+		return -ENOMEM;
+	freed_rtx = nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents;
+
+	xfs_rtgroup_calc_geometry(nmp, rtg, rtg_rgno(rtg),
+			nmp->m_sb.sb_rgcount, nmp->m_sb.sb_rextents);
+
+	error = xfs_trans_alloc(mp, &M_RES(nmp)->tr_growrtfree, 0, 0, 0, &tp);
+	if (error)
+		goto out_free;
+
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
+
+	xfs_growfs_rt_sb_fields(tp, nmp);
+	xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, freed_rtx);
+
+	error = xfs_trans_commit(tp);
+	if (error)
+		goto out_free;
+
+	/*
+	 * Ensure the mount RT feature flag is now set, and compute new
+	 * maxlevels for rt btrees.
+	 */
+	mp->m_features |= XFS_FEAT_REALTIME;
+	xfs_rtrmapbt_compute_maxlevels(mp);
+	xfs_rtrefcountbt_compute_maxlevels(mp);
+	xfs_zoned_add_available(mp, freed_rtx);
+out_free:
+	kfree(nmp);
 	return error;
 }
 
···
 	/*
 	 * Update superblock fields.
 	 */
-	if (nmp->m_sb.sb_rextsize != mp->m_sb.sb_rextsize)
-		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSIZE,
-			nmp->m_sb.sb_rextsize - mp->m_sb.sb_rextsize);
-	if (nmp->m_sb.sb_rbmblocks != mp->m_sb.sb_rbmblocks)
-		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RBMBLOCKS,
-			nmp->m_sb.sb_rbmblocks - mp->m_sb.sb_rbmblocks);
-	if (nmp->m_sb.sb_rblocks != mp->m_sb.sb_rblocks)
-		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RBLOCKS,
-			nmp->m_sb.sb_rblocks - mp->m_sb.sb_rblocks);
-	if (nmp->m_sb.sb_rextents != mp->m_sb.sb_rextents)
-		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTENTS,
-			nmp->m_sb.sb_rextents - mp->m_sb.sb_rextents);
-	if (nmp->m_sb.sb_rextslog != mp->m_sb.sb_rextslog)
-		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_REXTSLOG,
-			nmp->m_sb.sb_rextslog - mp->m_sb.sb_rextslog);
-	if (nmp->m_sb.sb_rgcount != mp->m_sb.sb_rgcount)
-		xfs_trans_mod_sb(args.tp, XFS_TRANS_SB_RGCOUNT,
-			nmp->m_sb.sb_rgcount - mp->m_sb.sb_rgcount);
+	xfs_growfs_rt_sb_fields(args.tp, nmp);
 
 	/*
 	 * Free the new extent.
···
 			goto out_rele;
 	}
 
+	if (xfs_has_zoned(mp)) {
+		error = xfs_growfs_rt_zoned(rtg, nrblocks);
+		goto out_rele;
+	}
+
 	error = xfs_growfs_rt_alloc_blocks(rtg, nrblocks, rextsize, &bmblocks);
 	if (error)
 		goto out_rele;
···
 			goto out_error;
 	}
 
-	if (old_rsum_cache)
-		kvfree(old_rsum_cache);
-	xfs_rtgroup_rele(rtg);
-	return 0;
+	kvfree(old_rsum_cache);
+	goto out_rele;
 
 out_error:
 	/*
···
 
 	if (min_logfsbs > mp->m_sb.sb_logblocks)
 		return -EINVAL;
+
+	if (xfs_has_zoned(mp)) {
+		uint32_t	gblocks = mp->m_groups[XG_TYPE_RTG].blocks;
+		uint32_t	rem;
+
+		if (rextsize != 1)
+			return -EINVAL;
+		div_u64_rem(mp->m_sb.sb_rblocks, gblocks, &rem);
+		if (rem) {
+			xfs_warn(mp,
+"new RT volume size (%lld) not aligned to RT group size (%d)",
+				mp->m_sb.sb_rblocks, gblocks);
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
···
 }
 
 /*
+ * Read in the last block of the RT device to make sure it is accessible.
+ */
+static int
+xfs_rt_check_size(
+	struct xfs_mount	*mp,
+	xfs_rfsblock_t		last_block)
+{
+	xfs_daddr_t		daddr = XFS_FSB_TO_BB(mp, last_block);
+	struct xfs_buf		*bp;
+	int			error;
+
+	if (XFS_BB_TO_FSB(mp, daddr) != last_block) {
+		xfs_warn(mp, "RT device size overflow: %llu != %llu",
+			XFS_BB_TO_FSB(mp, daddr), last_block);
+		return -EFBIG;
+	}
+
+	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
+			XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart) + daddr,
+			XFS_FSB_TO_BB(mp, 1), &bp, NULL);
+	if (error)
+		xfs_warn(mp, "cannot read last RT device sector (%lld)",
+				last_block);
+	else
+		xfs_buf_relse(bp);
+	return error;
+}
+
+/*
  * Grow the realtime area of the filesystem.
  */
 int
···
 	xfs_rgnumber_t		old_rgcount = mp->m_sb.sb_rgcount;
 	xfs_rgnumber_t		new_rgcount = 1;
 	xfs_rgnumber_t		rgno;
-	struct xfs_buf		*bp;
 	xfs_agblock_t		old_rextsize = mp->m_sb.sb_rextsize;
 	int			error;
 
···
 	error = xfs_sb_validate_fsb_count(&mp->m_sb, in->newblocks);
 	if (error)
 		goto out_unlock;
-	/*
-	 * Read in the last block of the device, make sure it exists.
-	 */
-	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
-				XFS_FSB_TO_BB(mp, in->newblocks - 1),
-				XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
+
+	error = xfs_rt_check_size(mp, in->newblocks - 1);
 	if (error)
 		goto out_unlock;
-	xfs_buf_relse(bp);
 
 	/*
 	 * Calculate new parameters.  These are the final values to be reached.
···
 			error = error2;
 
 		/* Reset the rt metadata btree space reservations. */
-		xfs_rt_resv_free(mp);
-		error2 = xfs_rt_resv_init(mp);
+		error2 = xfs_metafile_resv_init(mp);
 		if (error2 && error2 != -ENOSPC)
 			error = error2;
 	}
···
 
 	/* m_blkbb_log is not set up yet */
 	error = xfs_buf_read_uncached(mp->m_rtdev_targp, XFS_RTSB_DADDR,
-			mp->m_sb.sb_blocksize >> BBSHIFT, 0, &bp,
+			mp->m_sb.sb_blocksize >> BBSHIFT, &bp,
 			&xfs_rtsb_buf_ops);
 	if (error) {
 		xfs_warn(mp, "rt sb validate failed with error %d.", error);
···
 xfs_rtmount_init(
 	struct xfs_mount	*mp)	/* file system mount structure */
 {
-	struct xfs_buf		*bp;	/* buffer for last block of subvolume */
-	xfs_daddr_t		d;	/* address of last block of subvolume */
-	int			error;
-
 	if (mp->m_sb.sb_rblocks == 0)
 		return 0;
 	if (mp->m_rtdev_targp == NULL) {
···
 
 	mp->m_rsumblocks = xfs_rtsummary_blockcount(mp, &mp->m_rsumlevels);
 
-	/*
-	 * Check that the realtime section is an ok size.
-	 */
-	d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
-	if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_rblocks) {
-		xfs_warn(mp, "realtime mount -- %llu != %llu",
-			(unsigned long long) XFS_BB_TO_FSB(mp, d),
-			(unsigned long long) mp->m_sb.sb_rblocks);
-		return -EFBIG;
-	}
-	error = xfs_buf_read_uncached(mp->m_rtdev_targp,
-					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
-	if (error) {
-		xfs_warn(mp, "realtime device size check failed");
-		return error;
-	}
-	xfs_buf_relse(bp);
-	return 0;
+	return xfs_rt_check_size(mp, mp->m_sb.sb_rblocks - 1);
 }
 
 static int
···
 	spin_lock(&mp->m_sb_lock);
 	mp->m_sb.sb_frextents = val;
 	spin_unlock(&mp->m_sb_lock);
-	percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents);
+	xfs_set_freecounter(mp, XC_FREE_RTEXTENTS, mp->m_sb.sb_frextents);
 	return 0;
-}
-
-/* Free space reservations for rt metadata inodes. */
-void
-xfs_rt_resv_free(
-	struct xfs_mount	*mp)
-{
-	struct xfs_rtgroup	*rtg = NULL;
-	unsigned int		i;
-
-	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
-		for (i = 0; i < XFS_RTGI_MAX; i++)
-			xfs_metafile_resv_free(rtg->rtg_inodes[i]);
-	}
-}
-
-/* Reserve space for rt metadata inodes' space expansion. */
-int
-xfs_rt_resv_init(
-	struct xfs_mount	*mp)
-{
-	struct xfs_rtgroup	*rtg = NULL;
-	xfs_filblks_t		ask;
-	int			error = 0;
-
-	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
-		int		err2;
-
-		ask = xfs_rtrmapbt_calc_reserves(mp);
-		err2 = xfs_metafile_resv_init(rtg_rmap(rtg), ask);
-		if (err2 && !error)
-			error = err2;
-
-		ask = xfs_rtrefcountbt_calc_reserves(mp);
-		err2 = xfs_metafile_resv_init(rtg_refcount(rtg), ask);
-		if (err2 && !error)
-			error = err2;
-	}
-
-	return error;
 }
 
 /*
···
 		}
 	}
 
+	if (xfs_has_zoned(mp))
+		return 0;
 	return xfs_alloc_rsum_cache(rtg, mp->m_sb.sb_rbmblocks);
 }
 
···
 	bool			initial_user_data =
 		ap->datatype & XFS_ALLOC_INITIAL_USER_DATA;
 	int			error;
+
+	ASSERT(!xfs_has_zoned(ap->tp->t_mountp));
 
 retry:
 	error = xfs_rtallocate_align(ap, &ralen, &raminlen, &prod, &noalign);

fs/xfs/xfs_rtalloc.h

···
 xfs_rtmount_inodes(
 	struct xfs_mount	*mp);	/* file system mount structure */
 
-void xfs_rt_resv_free(struct xfs_mount *mp);
-int xfs_rt_resv_init(struct xfs_mount *mp);
-
 /*
  * Grow the realtime area of the filesystem.
  */
···
 }
 # define xfs_rtmount_inodes(m)  (((mp)->m_sb.sb_rblocks == 0)? 0 : (-ENOSYS))
 # define xfs_rtunmount_inodes(m)
-# define xfs_rt_resv_free(mp)				((void)0)
-# define xfs_rt_resv_init(mp)				(0)
 
 static inline int
 xfs_growfs_check_rtgeom(const struct xfs_mount *mp,

fs/xfs/xfs_super.c

···
 #include "xfs_exchmaps_item.h"
 #include "xfs_parent.h"
 #include "xfs_rtalloc.h"
+#include "xfs_zone_alloc.h"
 #include "scrub/stats.h"
 #include "scrub/rcbag_btree.h"
 
···
 	Opt_filestreams, Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota,
 	Opt_prjquota, Opt_uquota, Opt_gquota, Opt_pquota,
 	Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
-	Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum,
+	Opt_discard, Opt_nodiscard, Opt_dax, Opt_dax_enum, Opt_max_open_zones,
+	Opt_lifetime, Opt_nolifetime,
 };
 
 static const struct fs_parameter_spec xfs_fs_parameters[] = {
···
 	fsparam_flag("nodiscard",	Opt_nodiscard),
 	fsparam_flag("dax",		Opt_dax),
 	fsparam_enum("dax",		Opt_dax_enum, dax_param_enums),
+	fsparam_u32("max_open_zones",	Opt_max_open_zones),
+	fsparam_flag("lifetime",	Opt_lifetime),
+	fsparam_flag("nolifetime",	Opt_nolifetime),
 	{}
 };
 
···
 		{ XFS_FEAT_LARGE_IOSIZE,	",largeio" },
 		{ XFS_FEAT_DAX_ALWAYS,		",dax=always" },
 		{ XFS_FEAT_DAX_NEVER,		",dax=never" },
+		{ XFS_FEAT_NOLIFETIME,		",nolifetime" },
 		{ 0, NULL }
 	};
 	struct xfs_mount	*mp = XFS_M(root->d_sb);
···
 
 	if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
 		seq_puts(m, ",noquota");
+
+	if (mp->m_max_open_zones)
+		seq_printf(m, ",max_open_zones=%u", mp->m_max_open_zones);
 
 	return 0;
 }
···
 		if (error)
 			return error;
 	}
-	if (mp->m_rtdev_targp) {
+
+	if (mp->m_sb.sb_rtstart) {
+		if (mp->m_rtdev_targp) {
+			xfs_warn(mp,
+		"can't use internal and external rtdev at the same time");
+			return -EINVAL;
+		}
+		mp->m_rtdev_targp = mp->m_ddev_targp;
+	} else if (mp->m_rtname) {
 		error = xfs_setsize_buftarg(mp->m_rtdev_targp,
 					    mp->m_sb.sb_sectsize);
 		if (error)
···
 {
 	if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_logdev_targp);
-	if (mp->m_rtdev_targp)
+	if (mp->m_rtdev_targp && mp->m_rtdev_targp != mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_rtdev_targp);
 	if (mp->m_ddev_targp)
 		xfs_free_buftarg(mp->m_ddev_targp);
···
 	if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) {
 		xfs_inodegc_stop(mp);
 		xfs_blockgc_stop(mp);
+		xfs_zone_gc_stop(mp);
 	}
 
 	return 0;
···
 	struct kstatfs		*st)
 {
 	int64_t			fdblocks =
-		percpu_counter_sum(&mp->m_fdblocks);
+		xfs_sum_freecounter(mp, XC_FREE_BLOCKS);
 
 	/* make sure st->f_bfree does not underflow */
-	st->f_bfree = max(0LL, fdblocks - xfs_fdblocks_unavailable(mp));
+	st->f_bfree = max(0LL,
+		fdblocks - xfs_freecounter_unavailable(mp, XC_FREE_BLOCKS));
+
 	/*
 	 * sb_dblocks can change during growfs, but nothing cares about reporting
 	 * the old or new value during growfs.
···
 	struct kstatfs		*st)
 {
 	st->f_bfree = xfs_rtbxlen_to_blen(mp,
-			percpu_counter_sum_positive(&mp->m_frextents));
-	st->f_blocks = mp->m_sb.sb_rblocks;
+			xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS));
+	st->f_blocks = mp->m_sb.sb_rblocks - xfs_rtbxlen_to_blen(mp,
+			mp->m_free[XC_FREE_RTEXTENTS].res_total);
 }
 
 static void
···
 }
 
 STATIC void
-xfs_save_resvblks(struct xfs_mount *mp)
+xfs_save_resvblks(
+	struct xfs_mount	*mp)
 {
-	mp->m_resblks_save = mp->m_resblks;
-	xfs_reserve_blocks(mp, 0);
+	enum xfs_free_counter	i;
+
+	for (i = 0; i < XC_FREE_NR; i++) {
+		mp->m_free[i].res_saved = mp->m_free[i].res_total;
+		xfs_reserve_blocks(mp, i, 0);
+	}
 }
 
 STATIC void
-xfs_restore_resvblks(struct xfs_mount *mp)
+xfs_restore_resvblks(
+	struct xfs_mount	*mp)
 {
-	uint64_t resblks;
+	uint64_t		resblks;
+	enum xfs_free_counter	i;
 
-	if (mp->m_resblks_save) {
-		resblks = mp->m_resblks_save;
-		mp->m_resblks_save = 0;
-	} else
-		resblks = xfs_default_resblks(mp);
-
-	xfs_reserve_blocks(mp, resblks);
+	for (i = 0; i < XC_FREE_NR; i++) {
+		if (mp->m_free[i].res_saved) {
+			resblks = mp->m_free[i].res_saved;
+			mp->m_free[i].res_saved = 0;
+		} else
+			resblks = xfs_default_resblks(mp, i);
+		xfs_reserve_blocks(mp, i, resblks);
+	}
 }
 
 /*
···
 	if (ret && !xfs_is_readonly(mp)) {
 		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
+		xfs_zone_gc_start(mp);
 	}
 
 	return ret;
···
 	 * filesystem.
 	 */
 	if (!xfs_is_readonly(mp)) {
+		xfs_zone_gc_start(mp);
 		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
 	}
···
 		return -EINVAL;
 	}
 
+	if (!xfs_has_zoned(mp)) {
+		if (mp->m_max_open_zones) {
+			xfs_warn(mp,
+"max_open_zones mount option only supported on zoned file systems.");
+			return -EINVAL;
+		}
+		if (mp->m_features & XFS_FEAT_NOLIFETIME) {
+			xfs_warn(mp,
+"nolifetime mount option only supported on zoned file systems.");
+			return -EINVAL;
+		}
+	}
+
 	return 0;
 }
 
···
 xfs_init_percpu_counters(
 	struct xfs_mount	*mp)
 {
-	int		error;
+	int			error;
+	int			i;
 
 	error = percpu_counter_init(&mp->m_icount, 0, GFP_KERNEL);
 	if (error)
···
 	if (error)
 		goto free_icount;
 
-	error = percpu_counter_init(&mp->m_fdblocks, 0, GFP_KERNEL);
-	if (error)
-		goto free_ifree;
-
 	error = percpu_counter_init(&mp->m_delalloc_blks, 0, GFP_KERNEL);
 	if (error)
-		goto free_fdblocks;
+		goto free_ifree;
 
 	error = percpu_counter_init(&mp->m_delalloc_rtextents, 0, GFP_KERNEL);
 	if (error)
 		goto free_delalloc;
 
-	error = percpu_counter_init(&mp->m_frextents, 0, GFP_KERNEL);
-	if (error)
-		goto free_delalloc_rt;
+	for (i = 0; i < XC_FREE_NR; i++) {
+		error = percpu_counter_init(&mp->m_free[i].count, 0,
+				GFP_KERNEL);
+		if (error)
+			goto free_freecounters;
+	}
 
 	return 0;
 
-free_delalloc_rt:
+free_freecounters:
+	while (--i > 0)
+		percpu_counter_destroy(&mp->m_free[i].count);
 	percpu_counter_destroy(&mp->m_delalloc_rtextents);
 free_delalloc:
 	percpu_counter_destroy(&mp->m_delalloc_blks);
-free_fdblocks:
-	percpu_counter_destroy(&mp->m_fdblocks);
 free_ifree:
 	percpu_counter_destroy(&mp->m_ifree);
 free_icount:
···
 {
 	percpu_counter_set(&mp->m_icount, mp->m_sb.sb_icount);
 	percpu_counter_set(&mp->m_ifree, mp->m_sb.sb_ifree);
-	percpu_counter_set(&mp->m_fdblocks, mp->m_sb.sb_fdblocks);
-	percpu_counter_set(&mp->m_frextents, mp->m_sb.sb_frextents);
+	xfs_set_freecounter(mp, XC_FREE_BLOCKS, mp->m_sb.sb_fdblocks);
+	if (!xfs_has_zoned(mp))
+		xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
+				mp->m_sb.sb_frextents);
 }
 
 static void
 xfs_destroy_percpu_counters(
 	struct xfs_mount	*mp)
 {
+	enum xfs_free_counter	i;
+
+	for (i = 0; i < XC_FREE_NR; i++)
+		percpu_counter_destroy(&mp->m_free[i].count);
 	percpu_counter_destroy(&mp->m_icount);
 	percpu_counter_destroy(&mp->m_ifree);
-	percpu_counter_destroy(&mp->m_fdblocks);
 	ASSERT(xfs_is_shutdown(mp) ||
 	       percpu_counter_sum(&mp->m_delalloc_rtextents) == 0);
 	percpu_counter_destroy(&mp->m_delalloc_rtextents);
 	ASSERT(xfs_is_shutdown(mp) ||
 	       percpu_counter_sum(&mp->m_delalloc_blks) == 0);
 	percpu_counter_destroy(&mp->m_delalloc_blks);
-	percpu_counter_destroy(&mp->m_frextents);
 }
 
 static int
···
 	xfs_force_shutdown(XFS_M(sb), SHUTDOWN_DEVICE_REMOVED);
 }
 
+static int
+xfs_fs_show_stats(
+	struct seq_file		*m,
+	struct dentry		*root)
+{
+	struct xfs_mount	*mp = XFS_M(root->d_sb);
+
+	if (xfs_has_zoned(mp) && IS_ENABLED(CONFIG_XFS_RT))
+		xfs_zoned_show_stats(m, mp);
+	return 0;
+}
+
 static const struct super_operations xfs_super_operations = {
 	.alloc_inode		= xfs_fs_alloc_inode,
 	.destroy_inode		= xfs_fs_destroy_inode,
···
 	.nr_cached_objects	= xfs_fs_nr_cached_objects,
 	.free_cached_objects	= xfs_fs_free_cached_objects,
 	.shutdown		= xfs_fs_shutdown,
+	.show_stats		= xfs_fs_show_stats,
 };
 
 static int
···
 	case Opt_noattr2:
 		xfs_fs_warn_deprecated(fc, param, XFS_FEAT_NOATTR2, true);
 		parsing_mp->m_features |= XFS_FEAT_NOATTR2;
+		return 0;
+	case Opt_max_open_zones:
+		parsing_mp->m_max_open_zones = result.uint_32;
+		return 0;
+	case Opt_lifetime:
+		parsing_mp->m_features &= ~XFS_FEAT_NOLIFETIME;
+		return 0;
+	case Opt_nolifetime:
+		parsing_mp->m_features |= XFS_FEAT_NOLIFETIME;
 		return 0;
 	default:
 		xfs_warn(parsing_mp, "unknown mount option [%s].", param->key);
···
 		mp->m_features &= ~XFS_FEAT_DISCARD;
 	}
 
-	if (xfs_has_metadir(mp))
+	if (xfs_has_zoned(mp)) {
+		if (!xfs_has_metadir(mp)) {
+			xfs_alert(mp,
+		"metadir feature required for zoned realtime devices.");
+			error = -EINVAL;
+			goto out_filestream_unmount;
+		}
+		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_ZONED);
+	} else if (xfs_has_metadir(mp)) {
 		xfs_warn_experimental(mp, XFS_EXPERIMENTAL_METADIR);
+	}
 
 	if (xfs_has_reflink(mp)) {
 		if (xfs_has_realtime(mp) &&
···
 			xfs_alert(mp,
 	"reflink not compatible with realtime extent size %u!",
 					mp->m_sb.sb_rextsize);
+			error = -EINVAL;
+			goto out_filestream_unmount;
+		}
+
+		if (xfs_has_zoned(mp)) {
+			xfs_alert(mp,
+	"reflink not compatible with zoned RT device!");
 			error = -EINVAL;
 			goto out_filestream_unmount;
 		}
···
 	/* Re-enable the background inode inactivation worker. */
 	xfs_inodegc_start(mp);
 
+	/* Restart zone reclaim */
+	xfs_zone_gc_start(mp);
+
 	return 0;
 }
 
···
 	 * we send inodes straight to reclaim, so no inodes will be queued.
 	 */
 	xfs_inodegc_stop(mp);
+
+	/* Stop zone reclaim */
+	xfs_zone_gc_stop(mp);
 
 	/* Free the per-AG metadata reservation pool. */
 	xfs_fs_unreserve_ag_blocks(mp);
···
 	for (i = 0; i < XG_TYPE_MAX; i++)
 		xa_init(&mp->m_groups[i].xa);
 	mutex_init(&mp->m_growlock);
+	mutex_init(&mp->m_metafile_resv_lock);
 	INIT_WORK(&mp->m_flush_inodes_work, xfs_flush_inodes_worker);
 	INIT_DELAYED_WORK(&mp->m_reclaim_work, xfs_reclaim_worker);
 	mp->m_kobj.kobject.kset = xfs_kset;

fs/xfs/xfs_sysfs.c

···
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
 #include "xfs_mount.h"
+#include "xfs_zones.h"
 
 struct xfs_sysfs_attr {
 	struct attribute attr;
···
 };
 ATTRIBUTE_GROUPS(xfs_mp);
 
-const struct kobj_type xfs_mp_ktype = {
+static const struct kobj_type xfs_mp_ktype = {
 	.release = xfs_sysfs_release,
 	.sysfs_ops = &xfs_sysfs_ops,
 	.default_groups = xfs_mp_groups,
···
 	return error;
 }
 
+static inline struct xfs_mount *zoned_to_mp(struct kobject *kobj)
+{
+	return container_of(to_kobj(kobj), struct xfs_mount, m_zoned_kobj);
+}
+
+static ssize_t
+max_open_zones_show(
+	struct kobject		*kobj,
+	char			*buf)
+{
+	/* only report the open zones available for user data */
+	return sysfs_emit(buf, "%u\n",
+		zoned_to_mp(kobj)->m_max_open_zones - XFS_OPEN_GC_ZONES);
+}
+XFS_SYSFS_ATTR_RO(max_open_zones);
+
+static struct attribute *xfs_zoned_attrs[] = {
+	ATTR_LIST(max_open_zones),
+	NULL,
+};
+ATTRIBUTE_GROUPS(xfs_zoned);
+
+static const struct kobj_type xfs_zoned_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_groups = xfs_zoned_groups,
+};
+
 int
-xfs_error_sysfs_init(
+xfs_mount_sysfs_init(
 	struct xfs_mount	*mp)
 {
 	int			error;
+
+	super_set_sysfs_name_id(mp->m_super);
+
+	/* .../xfs/<dev>/ */
+	error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
+			       NULL, mp->m_super->s_id);
+	if (error)
+		return error;
+
+	/* .../xfs/<dev>/stats/ */
+	error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
+			       &mp->m_kobj, "stats");
+	if (error)
+		goto out_remove_fsdir;
 
 	/* .../xfs/<dev>/error/ */
 	error = xfs_sysfs_init(&mp->m_error_kobj, &xfs_error_ktype,
 				&mp->m_kobj, "error");
 	if (error)
-		return error;
+		goto out_remove_stats_dir;
 
+	/* .../xfs/<dev>/error/fail_at_unmount */
 	error = sysfs_create_file(&mp->m_error_kobj.kobject,
 				  ATTR_LIST(fail_at_unmount));
 
 	if (error)
-		goto out_error;
+		goto out_remove_error_dir;
 
 	/* .../xfs/<dev>/error/metadata/ */
 	error = xfs_error_sysfs_init_class(mp, XFS_ERR_METADATA,
 				"metadata", &mp->m_error_meta_kobj,
 				xfs_error_meta_init);
 	if (error)
-		goto out_error;
+		goto out_remove_error_dir;
+
+	if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp)) {
+		/* .../xfs/<dev>/zoned/ */
+		error = xfs_sysfs_init(&mp->m_zoned_kobj, &xfs_zoned_ktype,
+					&mp->m_kobj, "zoned");
+		if (error)
+			goto out_remove_error_dir;
+	}
 
 	return 0;
 
-out_error:
+out_remove_error_dir:
 	xfs_sysfs_del(&mp->m_error_kobj);
+out_remove_stats_dir:
+	xfs_sysfs_del(&mp->m_stats.xs_kobj);
+out_remove_fsdir:
+	xfs_sysfs_del(&mp->m_kobj);
 	return error;
 }
 
 void
-xfs_error_sysfs_del(
+xfs_mount_sysfs_del(
 	struct xfs_mount	*mp)
 {
 	struct xfs_error_cfg	*cfg;
 	int			i, j;
+
+	if (IS_ENABLED(CONFIG_XFS_RT) && xfs_has_zoned(mp))
+		xfs_sysfs_del(&mp->m_zoned_kobj);
 
 	for (i = 0; i < XFS_ERR_CLASS_MAX; i++) {
 		for (j = 0; j < XFS_ERR_ERRNO_MAX; j++) {
···
 	}
 	xfs_sysfs_del(&mp->m_error_meta_kobj);
 	xfs_sysfs_del(&mp->m_error_kobj);
+	xfs_sysfs_del(&mp->m_stats.xs_kobj);
+	xfs_sysfs_del(&mp->m_kobj);
 }
 
 struct xfs_error_cfg *

fs/xfs/xfs_sysfs.h

···
 #ifndef __XFS_SYSFS_H__
 #define __XFS_SYSFS_H__
 
-extern const struct kobj_type xfs_mp_ktype;	/* xfs_mount */
 extern const struct kobj_type xfs_dbg_ktype;	/* debug */
 extern const struct kobj_type xfs_log_ktype;	/* xlog */
 extern const struct kobj_type xfs_stats_ktype;	/* stats */
···
 	wait_for_completion(&kobj->complete);
 }
 
-int	xfs_error_sysfs_init(struct xfs_mount *mp);
-void	xfs_error_sysfs_del(struct xfs_mount *mp);
+int	xfs_mount_sysfs_init(struct xfs_mount *mp);
+void	xfs_mount_sysfs_del(struct xfs_mount *mp);
 
 #endif	/* __XFS_SYSFS_H__ */

fs/xfs/xfs_trace.c

···
 #include "xfs_metafile.h"
 #include "xfs_metadir.h"
 #include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_zone_priv.h"
 
 /*
  * We include this last to have the helpers above available for the trace

fs/xfs/xfs_trace.h

···
 struct xfs_refcount_intent;
 struct xfs_metadir_update;
 struct xfs_rtgroup;
+struct xfs_open_zone;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
···
 DEFINE_GROUP_REF_EVENT(xfs_group_grab);
 DEFINE_GROUP_REF_EVENT(xfs_group_grab_next_tag);
 DEFINE_GROUP_REF_EVENT(xfs_group_rele);
+
+#ifdef CONFIG_XFS_RT
+DECLARE_EVENT_CLASS(xfs_zone_class,
+	TP_PROTO(struct xfs_rtgroup *rtg),
+	TP_ARGS(rtg),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(unsigned int, nr_open)
+	),
+	TP_fast_assign(
+		struct xfs_mount	*mp = rtg_mount(rtg);
+
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->used = rtg_rmap(rtg)->i_used_blocks;
+		__entry->nr_open = mp->m_zone_info->zi_nr_open_zones;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x nr_open %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->nr_open)
+);
+
+#define DEFINE_ZONE_EVENT(name)				\
+DEFINE_EVENT(xfs_zone_class, name,			\
+	TP_PROTO(struct xfs_rtgroup *rtg),		\
+	TP_ARGS(rtg))
+DEFINE_ZONE_EVENT(xfs_zone_emptied);
+DEFINE_ZONE_EVENT(xfs_zone_full);
+DEFINE_ZONE_EVENT(xfs_zone_opened);
+DEFINE_ZONE_EVENT(xfs_zone_reset);
+DEFINE_ZONE_EVENT(xfs_zone_gc_target_opened);
+
+TRACE_EVENT(xfs_zone_free_blocks,
+	TP_PROTO(struct xfs_rtgroup *rtg, xfs_rgblock_t rgbno,
+		 xfs_extlen_t len),
+	TP_ARGS(rtg, rgbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(xfs_rgblock_t, rgbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->used = rtg_rmap(rtg)->i_used_blocks;
+		__entry->rgbno = rgbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x rgbno 0x%x len 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->rgbno,
+		  __entry->len)
+);
+
+DECLARE_EVENT_CLASS(xfs_zone_alloc_class,
+	TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno,
+		 xfs_extlen_t len),
+	TP_ARGS(oz, rgbno, len),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(xfs_rgblock_t, written)
+		__field(xfs_rgblock_t, write_pointer)
+		__field(xfs_rgblock_t, rgbno)
+		__field(xfs_extlen_t, len)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(oz->oz_rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(oz->oz_rtg);
+		__entry->used = rtg_rmap(oz->oz_rtg)->i_used_blocks;
+		__entry->written = oz->oz_written;
+		__entry->write_pointer = oz->oz_write_pointer;
+		__entry->rgbno = rgbno;
+		__entry->len = len;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x written 0x%x wp 0x%x rgbno 0x%x len 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->written,
+		  __entry->write_pointer,
+		  __entry->rgbno,
+		  __entry->len)
+);
+
+#define DEFINE_ZONE_ALLOC_EVENT(name)				\
+DEFINE_EVENT(xfs_zone_alloc_class, name,			\
+	TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno,	\
+		 xfs_extlen_t len),				\
+	TP_ARGS(oz, rgbno, len))
+DEFINE_ZONE_ALLOC_EVENT(xfs_zone_record_blocks);
+DEFINE_ZONE_ALLOC_EVENT(xfs_zone_alloc_blocks);
+
+TRACE_EVENT(xfs_zone_gc_select_victim,
+	TP_PROTO(struct xfs_rtgroup *rtg, unsigned int bucket),
+	TP_ARGS(rtg, bucket),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgno)
+		__field(xfs_rgblock_t, used)
+		__field(unsigned int, bucket)
+	),
+	TP_fast_assign(
+		__entry->dev = rtg_mount(rtg)->m_super->s_dev;
+		__entry->rgno = rtg_rgno(rtg);
+		__entry->used = rtg_rmap(rtg)->i_used_blocks;
+		__entry->bucket = bucket;
+	),
+	TP_printk("dev %d:%d rgno 0x%x used 0x%x bucket %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rgno,
+		  __entry->used,
+		  __entry->bucket)
+);
+
+TRACE_EVENT(xfs_zones_mount,
+	TP_PROTO(struct xfs_mount *mp),
+	TP_ARGS(mp),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(xfs_rgnumber_t, rgcount)
+		__field(uint32_t, blocks)
+		__field(unsigned int, max_open_zones)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->rgcount = mp->m_sb.sb_rgcount;
+		__entry->blocks = mp->m_groups[XG_TYPE_RTG].blocks;
+		__entry->max_open_zones = mp->m_max_open_zones;
+	),
+	TP_printk("dev %d:%d zoned %u blocks_per_zone %u, max_open %u",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		__entry->rgcount,
+		__entry->blocks,
+		__entry->max_open_zones)
+);
+#endif /* CONFIG_XFS_RT */
 
 TRACE_EVENT(xfs_inodegc_worker,
 	TP_PROTO(struct xfs_mount *mp, unsigned int shrinker_hits),
···
 DEFINE_BUF_EVENT(xfs_buf_error_relse);
 DEFINE_BUF_EVENT(xfs_buf_drain_buftarg);
 DEFINE_BUF_EVENT(xfs_trans_read_buf_shut);
+DEFINE_BUF_EVENT(xfs_buf_backing_folio);
+DEFINE_BUF_EVENT(xfs_buf_backing_kmem);
+DEFINE_BUF_EVENT(xfs_buf_backing_vmalloc);
+DEFINE_BUF_EVENT(xfs_buf_backing_fallback);
 
 /* not really buffer traces, but the buf provides useful information */
 DEFINE_BUF_EVENT(xfs_btree_corrupt);
···
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_unwritten);
 DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write_append);
 DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read);
+DEFINE_SIMPLE_IO_EVENT(xfs_zoned_map_blocks);
 
 DECLARE_EVENT_CLASS(xfs_itrunc_class,
 	TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size),
···
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_from);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_to);
+DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_skip);
 
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);
···
 /* metadata inode space reservations */
 
 DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
-	TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len),
-	TP_ARGS(ip, len),
+	TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len),
+	TP_ARGS(mp, len),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
 		__field(unsigned long long, freeblks)
 		__field(unsigned long long, reserved)
 		__field(unsigned long long, asked)
···
 		__field(unsigned long long, len)
 	),
 	TP_fast_assign(
-		struct xfs_mount *mp = ip->i_mount;
-
 		__entry->dev = mp->m_super->s_dev;
-		__entry->ino = ip->i_ino;
-		__entry->freeblks = percpu_counter_sum(&mp->m_fdblocks);
-		__entry->reserved = ip->i_delayed_blks;
-		__entry->asked = ip->i_meta_resv_asked;
-		__entry->used = ip->i_nblocks;
+		__entry->freeblks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS);
+		__entry->reserved = mp->m_metafile_resv_avail;
+		__entry->asked = mp->m_metafile_resv_target;
+		__entry->used = mp->m_metafile_resv_used;
 		__entry->len = len;
 	),
-	TP_printk("dev %d:%d ino 0x%llx freeblks %llu resv %llu ask %llu used %llu len %llu",
+	TP_printk("dev %d:%d freeblks %llu resv %llu ask %llu used %llu len %llu",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
 		  __entry->freeblks,
 		  __entry->reserved,
 		  __entry->asked,
···
 )
 #define DEFINE_METAFILE_RESV_EVENT(name) \
 DEFINE_EVENT(xfs_metafile_resv_class, name, \
-	TP_PROTO(struct xfs_inode *ip, xfs_filblks_t len), \
-	TP_ARGS(ip, len))
+	TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len), \
+	TP_ARGS(mp, len))
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space);
 DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical);
-DEFINE_INODE_ERROR_EVENT(xfs_metafile_resv_init_error);
+DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init_error);
 
 #ifdef CONFIG_XFS_RT
 TRACE_EVENT(xfs_growfs_check_rtgeom,
···
 		  __entry->min_logfsbs)
 );
 #endif /* CONFIG_XFS_RT */
+
+TRACE_DEFINE_ENUM(XC_FREE_BLOCKS);
+TRACE_DEFINE_ENUM(XC_FREE_RTEXTENTS);
+TRACE_DEFINE_ENUM(XC_FREE_RTAVAILABLE);
+
+DECLARE_EVENT_CLASS(xfs_freeblocks_resv_class,
+	TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr,
+		 uint64_t delta, unsigned long caller_ip),
+	TP_ARGS(mp, ctr, delta, caller_ip),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(enum xfs_free_counter, ctr)
+		__field(uint64_t, delta)
+		__field(uint64_t, avail)
+		__field(uint64_t, total)
+		__field(unsigned long, caller_ip)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->ctr = ctr;
+		__entry->delta = delta;
+		__entry->avail = mp->m_free[ctr].res_avail;
+		__entry->total = mp->m_free[ctr].res_total;
+		__entry->caller_ip = caller_ip;
+	),
+	TP_printk("dev %d:%d ctr %s delta %llu avail %llu total %llu caller %pS",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __print_symbolic(__entry->ctr, XFS_FREECOUNTER_STR),
+		  __entry->delta,
+		  __entry->avail,
+		  __entry->total,
+		  (char *)__entry->caller_ip)
+)
+#define DEFINE_FREEBLOCKS_RESV_EVENT(name) \
+DEFINE_EVENT(xfs_freeblocks_resv_class, name, \
+	TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr, \
+		 uint64_t delta, unsigned long caller_ip), \
+	TP_ARGS(mp, ctr, delta, caller_ip))
+DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_reserved);
+DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_enospc);
 
 #endif /* _TRACE_XFS_H */
 

fs/xfs/xfs_zone_alloc.c

···
+// 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_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_error.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_iomap.h"
+#include "xfs_trans.h"
+#include "xfs_alloc.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_refcount.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_zone_priv.h"
+#include "xfs_zones.h"
+#include "xfs_trace.h"
+
+void
+xfs_open_zone_put(
+	struct xfs_open_zone	*oz)
+{
+	if (atomic_dec_and_test(&oz->oz_ref)) {
+		xfs_rtgroup_rele(oz->oz_rtg);
+		kfree(oz);
+	}
+}
+
+static inline uint32_t
+xfs_zone_bucket(
+	struct xfs_mount	*mp,
+	uint32_t		used_blocks)
+{
+	return XFS_ZONE_USED_BUCKETS * used_blocks /
+			mp->m_groups[XG_TYPE_RTG].blocks;
+}
+
+static inline void
+xfs_zone_add_to_bucket(
+	struct xfs_zone_info	*zi,
+	xfs_rgnumber_t		rgno,
+	uint32_t		to_bucket)
+{
+	__set_bit(rgno, zi->zi_used_bucket_bitmap[to_bucket]);
+	zi->zi_used_bucket_entries[to_bucket]++;
+}
+
+static inline void
+xfs_zone_remove_from_bucket(
+	struct xfs_zone_info	*zi,
+	xfs_rgnumber_t		rgno,
+	uint32_t		from_bucket)
+{
+	__clear_bit(rgno, zi->zi_used_bucket_bitmap[from_bucket]);
+	zi->zi_used_bucket_entries[from_bucket]--;
+}
+
+static void
+xfs_zone_account_reclaimable(
+	struct xfs_rtgroup	*rtg,
+	uint32_t		freed)
+{
+	struct xfs_group	*xg = &rtg->rtg_group;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	uint32_t		used = rtg_rmap(rtg)->i_used_blocks;
+	xfs_rgnumber_t		rgno = rtg_rgno(rtg);
+	uint32_t		from_bucket = xfs_zone_bucket(mp, used + freed);
+	uint32_t		to_bucket = xfs_zone_bucket(mp, used);
+	bool			was_full = (used + freed == rtg_blocks(rtg));
+
+	/*
+	 * This can be called from log recovery, where the zone_info structure
+	 * hasn't been allocated yet.  Skip all work as xfs_mount_zones will
+	 * add the zones to the right buckets before the file systems becomes
+	 * active.
+	 */
+	if (!zi)
+		return;
+
+	if (!used) {
+		/*
+		 * The zone is now empty, remove it from the bottom bucket and
+		 * trigger a reset.
+		 */
+		trace_xfs_zone_emptied(rtg);
+
+		if (!was_full)
+			xfs_group_clear_mark(xg, XFS_RTG_RECLAIMABLE);
+
+		spin_lock(&zi->zi_used_buckets_lock);
+		if (!was_full)
+			xfs_zone_remove_from_bucket(zi, rgno, from_bucket);
+		spin_unlock(&zi->zi_used_buckets_lock);
+
+		spin_lock(&zi->zi_reset_list_lock);
+		xg->xg_next_reset = zi->zi_reset_list;
+		zi->zi_reset_list = xg;
+		spin_unlock(&zi->zi_reset_list_lock);
+
+		if (zi->zi_gc_thread)
+			wake_up_process(zi->zi_gc_thread);
+	} else if (was_full) {
+		/*
+		 * The zone transitioned from full, mark it up as reclaimable
+		 * and wake up GC which might be waiting for zones to reclaim.
+		 */
+		spin_lock(&zi->zi_used_buckets_lock);
+		xfs_zone_add_to_bucket(zi, rgno, to_bucket);
+		spin_unlock(&zi->zi_used_buckets_lock);
+
+		xfs_group_set_mark(xg, XFS_RTG_RECLAIMABLE);
+		if (zi->zi_gc_thread && xfs_zoned_need_gc(mp))
+			wake_up_process(zi->zi_gc_thread);
+	} else if (to_bucket != from_bucket) {
+		/*
+		 * Move the zone to a new bucket if it dropped below the
+		 * threshold.
+		 */
+		spin_lock(&zi->zi_used_buckets_lock);
+		xfs_zone_add_to_bucket(zi, rgno, to_bucket);
+		xfs_zone_remove_from_bucket(zi, rgno, from_bucket);
+		spin_unlock(&zi->zi_used_buckets_lock);
+	}
+}
+
+static void
+xfs_open_zone_mark_full(
+	struct xfs_open_zone	*oz)
+{
+	struct xfs_rtgroup	*rtg = oz->oz_rtg;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	uint32_t		used = rtg_rmap(rtg)->i_used_blocks;
+
+	trace_xfs_zone_full(rtg);
+
+	WRITE_ONCE(rtg->rtg_open_zone, NULL);
+
+	spin_lock(&zi->zi_open_zones_lock);
+	if (oz->oz_is_gc) {
+		ASSERT(current == zi->zi_gc_thread);
+		zi->zi_open_gc_zone = NULL;
+	} else {
+		zi->zi_nr_open_zones--;
+		list_del_init(&oz->oz_entry);
+	}
+	spin_unlock(&zi->zi_open_zones_lock);
+	xfs_open_zone_put(oz);
+
+	wake_up_all(&zi->zi_zone_wait);
+	if (used < rtg_blocks(rtg))
+		xfs_zone_account_reclaimable(rtg, rtg_blocks(rtg) - used);
+}
+
+static void
+xfs_zone_record_blocks(
+	struct xfs_trans	*tp,
+	xfs_fsblock_t		fsbno,
+	xfs_filblks_t		len,
+	struct xfs_open_zone	*oz,
+	bool			used)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_rtgroup	*rtg = oz->oz_rtg;
+	struct xfs_inode	*rmapip = rtg_rmap(rtg);
+
+	trace_xfs_zone_record_blocks(oz, xfs_rtb_to_rgbno(mp, fsbno), len);
+
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	xfs_rtgroup_trans_join(tp, rtg, XFS_RTGLOCK_RMAP);
+	if (used) {
+		rmapip->i_used_blocks += len;
+		ASSERT(rmapip->i_used_blocks <= rtg_blocks(rtg));
+	} else {
+		xfs_add_frextents(mp, len);
+	}
+	oz->oz_written += len;
+	if (oz->oz_written == rtg_blocks(rtg))
+		xfs_open_zone_mark_full(oz);
+	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
+}
+
+static int
+xfs_zoned_map_extent(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	struct xfs_bmbt_irec	*new,
+	struct xfs_open_zone	*oz,
+	xfs_fsblock_t		old_startblock)
+{
+	struct xfs_bmbt_irec	data;
+	int			nmaps = 1;
+	int			error;
+
+	/* Grab the corresponding mapping in the data fork. */
+	error = xfs_bmapi_read(ip, new->br_startoff, new->br_blockcount, &data,
+			       &nmaps, 0);
+	if (error)
+		return error;
+
+	/*
+	 * Cap the update to the existing extent in the data fork because we can
+	 * only overwrite one extent at a time.
+	 */
+	ASSERT(new->br_blockcount >= data.br_blockcount);
+	new->br_blockcount = data.br_blockcount;
+
+	/*
+	 * If a data write raced with this GC write, keep the existing data in
+	 * the data fork, mark our newly written GC extent as reclaimable, then
+	 * move on to the next extent.
+	 */
+	if (old_startblock != NULLFSBLOCK &&
+	    old_startblock != data.br_startblock)
+		goto skip;
+
+	trace_xfs_reflink_cow_remap_from(ip, new);
+	trace_xfs_reflink_cow_remap_to(ip, &data);
+
+	error = xfs_iext_count_extend(tp, ip, XFS_DATA_FORK,
+			XFS_IEXT_REFLINK_END_COW_CNT);
+	if (error)
+		return error;
+
+	if (data.br_startblock != HOLESTARTBLOCK) {
+		ASSERT(data.br_startblock != DELAYSTARTBLOCK);
+		ASSERT(!isnullstartblock(data.br_startblock));
+
+		xfs_bmap_unmap_extent(tp, ip, XFS_DATA_FORK, &data);
+		if (xfs_is_reflink_inode(ip)) {
+			xfs_refcount_decrease_extent(tp, true, &data);
+		} else {
+			error = xfs_free_extent_later(tp, data.br_startblock,
+					data.br_blockcount, NULL,
+					XFS_AG_RESV_NONE,
+					XFS_FREE_EXTENT_REALTIME);
+			if (error)
+				return error;
+		}
+	}
+
+	xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz,
+			true);
+
+	/* Map the new blocks into the data fork. */
+	xfs_bmap_map_extent(tp, ip, XFS_DATA_FORK, new);
+	return 0;
+
+skip:
+	trace_xfs_reflink_cow_remap_skip(ip, new);
+	xfs_zone_record_blocks(tp, new->br_startblock, new->br_blockcount, oz,
+			false);
+	return 0;
+}
+
+int
+xfs_zoned_end_io(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_off_t		count,
+	xfs_daddr_t		daddr,
+	struct xfs_open_zone	*oz,
+	xfs_fsblock_t		old_startblock)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
+	struct xfs_bmbt_irec	new = {
+		.br_startoff	= XFS_B_TO_FSBT(mp, offset),
+		.br_startblock	= xfs_daddr_to_rtb(mp, daddr),
+		.br_state	= XFS_EXT_NORM,
+	};
+	unsigned int		resblks =
+		XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
+	struct xfs_trans	*tp;
+	int			error;
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	while (new.br_startoff < end_fsb) {
+		new.br_blockcount = end_fsb - new.br_startoff;
+
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0,
+				XFS_TRANS_RESERVE | XFS_TRANS_RES_FDBLKS, &tp);
+		if (error)
+			return error;
+		xfs_ilock(ip, XFS_ILOCK_EXCL);
+		xfs_trans_ijoin(tp, ip, 0);
+
+		error = xfs_zoned_map_extent(tp, ip, &new, oz, old_startblock);
+		if (error)
+			xfs_trans_cancel(tp);
+		else
+			error = xfs_trans_commit(tp);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		if (error)
+			return error;
+
+		new.br_startoff += new.br_blockcount;
+		new.br_startblock += new.br_blockcount;
+		if (old_startblock != NULLFSBLOCK)
+			old_startblock += new.br_blockcount;
+	}
+
+	return 0;
+}
+
+/*
+ * "Free" blocks allocated in a zone.
+ *
+ * Just decrement the used blocks counter and report the space as freed.
+ */
+int
+xfs_zone_free_blocks(
+	struct xfs_trans	*tp,
+	struct xfs_rtgroup	*rtg,
+	xfs_fsblock_t		fsbno,
+	xfs_filblks_t		len)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*rmapip = rtg_rmap(rtg);
+
+	xfs_assert_ilocked(rmapip, XFS_ILOCK_EXCL);
+
+	if (len > rmapip->i_used_blocks) {
+		xfs_err(mp,
+"trying to free more blocks (%lld) than used counter (%u).",
+			len, rmapip->i_used_blocks);
+		ASSERT(len <= rmapip->i_used_blocks);
+		xfs_rtginode_mark_sick(rtg, XFS_RTGI_RMAP);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		return -EFSCORRUPTED;
+	}
+
+	trace_xfs_zone_free_blocks(rtg, xfs_rtb_to_rgbno(mp, fsbno), len);
+
+	rmapip->i_used_blocks -= len;
+	/*
+	 * Don't add open zones to the reclaimable buckets.  The I/O completion
+	 * for writing the last block will take care of accounting for already
+	 * unused blocks instead.
+	 */
+	if (!READ_ONCE(rtg->rtg_open_zone))
+		xfs_zone_account_reclaimable(rtg, len);
+	xfs_add_frextents(mp, len);
+	xfs_trans_log_inode(tp, rmapip, XFS_ILOG_CORE);
+	return 0;
+}
+
+/*
+ * Check if the zone containing the data just before the offset we are
+ * writing to is still open and has space.
+ */
+static struct xfs_open_zone *
+xfs_last_used_zone(
+	struct iomap_ioend	*ioend)
+{
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSB(mp, ioend->io_offset);
+	struct xfs_rtgroup	*rtg = NULL;
+	struct xfs_open_zone	*oz = NULL;
+	struct xfs_iext_cursor	icur;
+	struct xfs_bmbt_irec	got;
+
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	if (!xfs_iext_lookup_extent_before(ip, &ip->i_df, &offset_fsb,
+				&icur, &got)) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return NULL;
+	}
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+	rtg = xfs_rtgroup_grab(mp, xfs_rtb_to_rgno(mp, got.br_startblock));
+	if (!rtg)
+		return NULL;
+
+	xfs_ilock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
+	oz = READ_ONCE(rtg->rtg_open_zone);
+	if (oz && (oz->oz_is_gc || !atomic_inc_not_zero(&oz->oz_ref)))
+		oz = NULL;
+	xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_SHARED);
+
+	xfs_rtgroup_rele(rtg);
+	return oz;
+}
+
+static struct xfs_group *
+xfs_find_free_zone(
+	struct xfs_mount	*mp,
+	unsigned long		start,
+	unsigned long		end)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	XA_STATE		(xas, &mp->m_groups[XG_TYPE_RTG].xa, start);
+	struct xfs_group	*xg;
+
+	xas_lock(&xas);
+	xas_for_each_marked(&xas, xg, end, XFS_RTG_FREE)
+		if (atomic_inc_not_zero(&xg->xg_active_ref))
+			goto found;
+	xas_unlock(&xas);
+	return NULL;
+
+found:
+	xas_clear_mark(&xas, XFS_RTG_FREE);
+	atomic_dec(&zi->zi_nr_free_zones);
+	zi->zi_free_zone_cursor = xg->xg_gno;
+	xas_unlock(&xas);
+	return xg;
+}
+
+static struct xfs_open_zone *
+xfs_init_open_zone(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		write_pointer,
+	enum rw_hint		write_hint,
+	bool			is_gc)
+{
+	struct xfs_open_zone	*oz;
+
+	oz = kzalloc(sizeof(*oz), GFP_NOFS | __GFP_NOFAIL);
+	spin_lock_init(&oz->oz_alloc_lock);
+	atomic_set(&oz->oz_ref, 1);
+	oz->oz_rtg = rtg;
+	oz->oz_write_pointer = write_pointer;
+	oz->oz_written = write_pointer;
+	oz->oz_write_hint = write_hint;
+	oz->oz_is_gc = is_gc;
+
+	/*
+	 * All dereferences of rtg->rtg_open_zone hold the ILOCK for the rmap
+	 * inode, but we don't really want to take that here because we are
+	 * under the zone_list_lock.  Ensure the pointer is only set for a fully
+	 * initialized open zone structure so that a racy lookup finding it is
+	 * fine.
+	 */
+	WRITE_ONCE(rtg->rtg_open_zone, oz);
+	return oz;
+}
+
+/*
+ * Find a completely free zone, open it, and return a reference.
+ */
+struct xfs_open_zone *
+xfs_open_zone(
+	struct xfs_mount	*mp,
+	enum rw_hint		write_hint,
+	bool			is_gc)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_group	*xg;
+
+	xg = xfs_find_free_zone(mp, zi->zi_free_zone_cursor, ULONG_MAX);
+	if (!xg)
+		xg = xfs_find_free_zone(mp, 0, zi->zi_free_zone_cursor);
+	if (!xg)
+		return NULL;
+
+	set_current_state(TASK_RUNNING);
+	return xfs_init_open_zone(to_rtg(xg), 0, write_hint, is_gc);
+}
+
+static struct xfs_open_zone *
+xfs_try_open_zone(
+	struct xfs_mount	*mp,
+	enum rw_hint		write_hint)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_open_zone	*oz;
+
+	if (zi->zi_nr_open_zones >= mp->m_max_open_zones - XFS_OPEN_GC_ZONES)
+		return NULL;
+	if (atomic_read(&zi->zi_nr_free_zones) <
+	    XFS_GC_ZONES - XFS_OPEN_GC_ZONES)
+		return NULL;
+
+	/*
+	 * Increment the open zone count to reserve our slot before dropping
+	 * zi_open_zones_lock.
+	 */
+	zi->zi_nr_open_zones++;
+	spin_unlock(&zi->zi_open_zones_lock);
+	oz = xfs_open_zone(mp, write_hint, false);
+	spin_lock(&zi->zi_open_zones_lock);
+	if (!oz) {
+		zi->zi_nr_open_zones--;
+		return NULL;
+	}
+
+	atomic_inc(&oz->oz_ref);
+	list_add_tail(&oz->oz_entry, &zi->zi_open_zones);
+
+	/*
+	 * If this was the last free zone, other waiters might be waiting
+	 * on us to write to it as well.
+	 */
+	wake_up_all(&zi->zi_zone_wait);
+
+	if (xfs_zoned_need_gc(mp))
+		wake_up_process(zi->zi_gc_thread);
+
+	trace_xfs_zone_opened(oz->oz_rtg);
+	return oz;
+}
+
+/*
+ * For data with short or medium lifetime, try to colocated it into an
+ * already open zone with a matching temperature.
+ */
+static bool
+xfs_colocate_eagerly(
+	enum rw_hint		file_hint)
+{
+	switch (file_hint) {
+	case WRITE_LIFE_MEDIUM:
+	case WRITE_LIFE_SHORT:
+	case WRITE_LIFE_NONE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool
+xfs_good_hint_match(
+	struct xfs_open_zone	*oz,
+	enum rw_hint		file_hint)
+{
+	switch (oz->oz_write_hint) {
+	case WRITE_LIFE_LONG:
+	case WRITE_LIFE_EXTREME:
+		/* colocate long and extreme */
+		if (file_hint == WRITE_LIFE_LONG ||
+		    file_hint == WRITE_LIFE_EXTREME)
+			return true;
+		break;
+	case WRITE_LIFE_MEDIUM:
+		/* colocate medium with medium */
+		if (file_hint == WRITE_LIFE_MEDIUM)
+			return true;
+		break;
+	case WRITE_LIFE_SHORT:
+	case WRITE_LIFE_NONE:
+	case WRITE_LIFE_NOT_SET:
+		/* colocate short and none */
+		if (file_hint <= WRITE_LIFE_SHORT)
+			return true;
+		break;
+	}
+	return false;
+}
+
+static bool
+xfs_try_use_zone(
+	struct xfs_zone_info	*zi,
+	enum rw_hint		file_hint,
+	struct xfs_open_zone	*oz,
+	bool			lowspace)
+{
+	if (oz->oz_write_pointer == rtg_blocks(oz->oz_rtg))
+		return false;
+	if (!lowspace && !xfs_good_hint_match(oz, file_hint))
+		return false;
+	if (!atomic_inc_not_zero(&oz->oz_ref))
+		return false;
+
+	/*
+	 * If we have a hint set for the data, use that for the zone even if
+	 * some data was written already without any hint set, but don't change
+	 * the temperature after that as that would make little sense without
+	 * tracking per-temperature class written block counts, which is
+	 * probably overkill anyway.
+	 */
+	if (file_hint != WRITE_LIFE_NOT_SET &&
+	    oz->oz_write_hint == WRITE_LIFE_NOT_SET)
+		oz->oz_write_hint = file_hint;
+
+	/*
+	 * If we couldn't match by inode or life time we just pick the first
+	 * zone with enough space above.  For that we want the least busy zone
+	 * for some definition of "least" busy.  For now this simple LRU
+	 * algorithm that rotates every zone to the end of the list will do it,
+	 * even if it isn't exactly cache friendly.
+	 */
+	if (!list_is_last(&oz->oz_entry, &zi->zi_open_zones))
+		list_move_tail(&oz->oz_entry, &zi->zi_open_zones);
+	return true;
+}
+
+static struct xfs_open_zone *
+xfs_select_open_zone_lru(
+	struct xfs_zone_info	*zi,
+	enum rw_hint		file_hint,
+	bool			lowspace)
+{
+	struct xfs_open_zone	*oz;
+
+	lockdep_assert_held(&zi->zi_open_zones_lock);
+
+	list_for_each_entry(oz, &zi->zi_open_zones, oz_entry)
+		if (xfs_try_use_zone(zi, file_hint, oz, lowspace))
+			return oz;
+
+	cond_resched_lock(&zi->zi_open_zones_lock);
+	return NULL;
+}
+
+static struct xfs_open_zone *
+xfs_select_open_zone_mru(
+	struct xfs_zone_info	*zi,
+	enum rw_hint		file_hint)
+{
+	struct xfs_open_zone	*oz;
+
+	lockdep_assert_held(&zi->zi_open_zones_lock);
+
+	list_for_each_entry_reverse(oz, &zi->zi_open_zones, oz_entry)
+		if (xfs_try_use_zone(zi, file_hint, oz, false))
+			return oz;
+
+	cond_resched_lock(&zi->zi_open_zones_lock);
+	return NULL;
+}
+
+static inline enum rw_hint xfs_inode_write_hint(struct xfs_inode *ip)
+{
+	if (xfs_has_nolifetime(ip->i_mount))
+		return WRITE_LIFE_NOT_SET;
+	return VFS_I(ip)->i_write_hint;
+}
+
+/*
+ * Try to pack inodes that are written back after they were closed tight instead
+ * of trying to open new zones for them or spread them to the least recently
+ * used zone.  This optimizes the data layout for workloads that untar or copy
+ * a lot of small files.  Right now this does not separate multiple such
+ * streams.
+ */
+static inline bool xfs_zoned_pack_tight(struct xfs_inode *ip)
+{
+	return !inode_is_open_for_write(VFS_I(ip)) &&
+		!(ip->i_diflags & XFS_DIFLAG_APPEND);
+}
+
+/*
+ * Pick a new zone for writes.
+ *
+ * If we aren't using up our budget of open zones just open a new one from the
+ * freelist.  Else try to find one that matches the expected data lifetime.  If
+ * we don't find one that is good pick any zone that is available.
+ */
+static struct xfs_open_zone *
+xfs_select_zone_nowait(
+	struct xfs_mount	*mp,
+	enum rw_hint		write_hint,
+	bool			pack_tight)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_open_zone	*oz = NULL;
+
+	if (xfs_is_shutdown(mp))
+		return NULL;
+
+	/*
+	 * Try to fill up open zones with matching temperature if available.  It
+	 * is better to try to co-locate data when this is favorable, so we can
+	 * activate empty zones when it is statistically better to separate
+	 * data.
+	 */
+	spin_lock(&zi->zi_open_zones_lock);
+	if (xfs_colocate_eagerly(write_hint))
+		oz = xfs_select_open_zone_lru(zi, write_hint, false);
+	else if (pack_tight)
+		oz = xfs_select_open_zone_mru(zi, write_hint);
+	if (oz)
+		goto out_unlock;
+
+	/*
+	 * See if we can open a new zone and use that.
+	 */
+	oz = xfs_try_open_zone(mp, write_hint);
+	if (oz)
+		goto out_unlock;
+
+	/*
+	 * Try to colocate cold data with other cold data if we failed to open a
+	 * new zone for it.
+	 */
+	if (write_hint != WRITE_LIFE_NOT_SET &&
+	    !xfs_colocate_eagerly(write_hint))
+		oz = xfs_select_open_zone_lru(zi, write_hint, false);
+	if (!oz)
+		oz = xfs_select_open_zone_lru(zi, WRITE_LIFE_NOT_SET, false);
+	if (!oz)
+		oz = xfs_select_open_zone_lru(zi, WRITE_LIFE_NOT_SET, true);
+out_unlock:
+	spin_unlock(&zi->zi_open_zones_lock);
+	return oz;
+}
+
+static struct xfs_open_zone *
+xfs_select_zone(
+	struct xfs_mount	*mp,
+	enum rw_hint		write_hint,
+	bool			pack_tight)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	DEFINE_WAIT		(wait);
+	struct xfs_open_zone	*oz;
+
+	oz = xfs_select_zone_nowait(mp, write_hint, pack_tight);
+	if (oz)
+		return oz;
+
+	for (;;) {
+		prepare_to_wait(&zi->zi_zone_wait, &wait, TASK_UNINTERRUPTIBLE);
+		oz = xfs_select_zone_nowait(mp, write_hint, pack_tight);
+		if (oz)
+			break;
+		schedule();
+	}
+	finish_wait(&zi->zi_zone_wait, &wait);
+	return oz;
+}
+
+static unsigned int
+xfs_zone_alloc_blocks(
+	struct xfs_open_zone	*oz,
+	xfs_filblks_t		count_fsb,
+	sector_t		*sector,
+	bool			*is_seq)
+{
+	struct xfs_rtgroup	*rtg = oz->oz_rtg;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rgblock_t		rgbno;
+
+	spin_lock(&oz->oz_alloc_lock);
+	count_fsb = min3(count_fsb, XFS_MAX_BMBT_EXTLEN,
+		(xfs_filblks_t)rtg_blocks(rtg) - oz->oz_write_pointer);
+	if (!count_fsb) {
+		spin_unlock(&oz->oz_alloc_lock);
+		return 0;
+	}
+	rgbno = oz->oz_write_pointer;
+	oz->oz_write_pointer += count_fsb;
+	spin_unlock(&oz->oz_alloc_lock);
+
+	trace_xfs_zone_alloc_blocks(oz, rgbno, count_fsb);
+
+	*sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
+	*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *sector);
+	if (!*is_seq)
+		*sector += XFS_FSB_TO_BB(mp, rgbno);
+	return XFS_FSB_TO_B(mp, count_fsb);
+}
+
+void
+xfs_mark_rtg_boundary(
+	struct iomap_ioend	*ioend)
+{
+	struct xfs_mount	*mp = XFS_I(ioend->io_inode)->i_mount;
+	sector_t		sector = ioend->io_bio.bi_iter.bi_sector;
+
+	if (xfs_rtb_to_rgbno(mp, xfs_daddr_to_rtb(mp, sector)) == 0)
+		ioend->io_flags |= IOMAP_IOEND_BOUNDARY;
+}
+
+static void
+xfs_submit_zoned_bio(
+	struct iomap_ioend	*ioend,
+	struct xfs_open_zone	*oz,
+	bool			is_seq)
+{
+	ioend->io_bio.bi_iter.bi_sector = ioend->io_sector;
+	ioend->io_private = oz;
+	atomic_inc(&oz->oz_ref); /* for xfs_zoned_end_io */
+
+	if (is_seq) {
+		ioend->io_bio.bi_opf &= ~REQ_OP_WRITE;
+		ioend->io_bio.bi_opf |= REQ_OP_ZONE_APPEND;
+	} else {
+		xfs_mark_rtg_boundary(ioend);
+	}
+
+	submit_bio(&ioend->io_bio);
+}
+
+void
+xfs_zone_alloc_and_submit(
+	struct iomap_ioend	*ioend,
+	struct xfs_open_zone	**oz)
+{
+	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	enum rw_hint		write_hint = xfs_inode_write_hint(ip);
+	bool			pack_tight = xfs_zoned_pack_tight(ip);
+	unsigned int		alloc_len;
+	struct iomap_ioend	*split;
+	bool			is_seq;
+
+	if (xfs_is_shutdown(mp))
+		goto out_error;
+
+	/*
+	 * If we don't have a cached zone in this write context, see if the
+	 * last extent before the one we are writing to points to an active
+	 * zone.  If so, just continue writing to it.
+	 */
+	if (!*oz && ioend->io_offset)
+		*oz = xfs_last_used_zone(ioend);
+	if (!*oz) {
+select_zone:
+		*oz = xfs_select_zone(mp, write_hint, pack_tight);
+		if (!*oz)
+			goto out_error;
+	}
+
+	alloc_len = xfs_zone_alloc_blocks(*oz, XFS_B_TO_FSB(mp, ioend->io_size),
+			&ioend->io_sector, &is_seq);
+	if (!alloc_len) {
+		xfs_open_zone_put(*oz);
+		goto select_zone;
+	}
+
+	while ((split = iomap_split_ioend(ioend, alloc_len, is_seq))) {
+		if (IS_ERR(split))
+			goto out_split_error;
+		alloc_len -= split->io_bio.bi_iter.bi_size;
+		xfs_submit_zoned_bio(split, *oz, is_seq);
+		if (!alloc_len) {
+			xfs_open_zone_put(*oz);
+			goto select_zone;
+		}
+	}
+
+	xfs_submit_zoned_bio(ioend, *oz, is_seq);
+	return;
+
+out_split_error:
+	ioend->io_bio.bi_status = errno_to_blk_status(PTR_ERR(split));
+out_error:
+	bio_io_error(&ioend->io_bio);
+}
+
+/*
+ * Wake up all threads waiting for a zoned space allocation when the file system
+ * is shut down.
+ */
+void
+xfs_zoned_wake_all(
+	struct xfs_mount	*mp)
+{
+	/*
+	 * Don't wake up if there is no m_zone_info.  This is complicated by the
+	 * fact that unmount can't atomically clear m_zone_info and thus we need
+	 * to check SB_ACTIVE for that, but mount temporarily enables SB_ACTIVE
+	 * during log recovery so we can't entirely rely on that either.
+	 */
+	if ((mp->m_super->s_flags & SB_ACTIVE) && mp->m_zone_info)
+		wake_up_all(&mp->m_zone_info->zi_zone_wait);
+}
+
+/*
+ * Check if @rgbno in @rgb is a potentially valid block.  It might still be
+ * unused, but that information is only found in the rmap.
+ */
+bool
+xfs_zone_rgbno_is_valid(
+	struct xfs_rtgroup	*rtg,
+	xfs_rgnumber_t		rgbno)
+{
+	lockdep_assert_held(&rtg_rmap(rtg)->i_lock);
+
+	if (rtg->rtg_open_zone)
+		return rgbno < rtg->rtg_open_zone->oz_write_pointer;
+	return !xa_get_mark(&rtg_mount(rtg)->m_groups[XG_TYPE_RTG].xa,
+			rtg_rgno(rtg), XFS_RTG_FREE);
+}
+
+static void
+xfs_free_open_zones(
+	struct xfs_zone_info	*zi)
+{
+	struct xfs_open_zone	*oz;
+
+	spin_lock(&zi->zi_open_zones_lock);
+	while ((oz = list_first_entry_or_null(&zi->zi_open_zones,
+			struct xfs_open_zone, oz_entry))) {
+		list_del(&oz->oz_entry);
+		xfs_open_zone_put(oz);
+	}
+	spin_unlock(&zi->zi_open_zones_lock);
+}
+
+struct xfs_init_zones {
+	struct xfs_mount	*mp;
+	uint64_t		available;
+	uint64_t		reclaimable;
+};
+
+static int
+xfs_init_zone(
+	struct xfs_init_zones	*iz,
+	struct xfs_rtgroup	*rtg,
+	struct blk_zone		*zone)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	uint64_t		used = rtg_rmap(rtg)->i_used_blocks;
+	xfs_rgblock_t		write_pointer, highest_rgbno;
+	int			error;
+
+	if (zone && !xfs_zone_validate(zone, rtg, &write_pointer))
+		return -EFSCORRUPTED;
+
+	/*
+	 * For sequential write required zones we retrieved the hardware write
+	 * pointer above.
+	 *
+	 * For conventional zones or conventional devices we don't have that
+	 * luxury.  Instead query the rmap to find the highest recorded block
+	 * and set the write pointer to the block after that.  In case of a
+	 * power loss this misses blocks where the data I/O has completed but
+	 * not recorded in the rmap yet, and it also rewrites blocks if the most
+	 * recently written ones got deleted again before unmount, but this is
+	 * the best we can do without hardware support.
+	 */
+	if (!zone || zone->cond == BLK_ZONE_COND_NOT_WP) {
+		xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+		highest_rgbno = xfs_rtrmap_highest_rgbno(rtg);
+		if (highest_rgbno == NULLRGBLOCK)
+			write_pointer = 0;
+		else
+			write_pointer = highest_rgbno + 1;
+		xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
+	}
+
+	/*
+	 * If there are no used blocks, but the zone is not in empty state yet
+	 * we lost power before the zoned reset.  In that case finish the work
+	 * here.
+	 */
+	if (write_pointer == rtg_blocks(rtg) && used == 0) {
+		error = xfs_zone_gc_reset_sync(rtg);
+		if (error)
+			return error;
+		write_pointer = 0;
+	}
+
+	if (write_pointer == 0) {
+		/* zone is empty */
+		atomic_inc(&zi->zi_nr_free_zones);
+		xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE);
+		iz->available += rtg_blocks(rtg);
+	} else if (write_pointer < rtg_blocks(rtg)) {
+		/* zone is open */
+		struct xfs_open_zone *oz;
+
+		atomic_inc(&rtg_group(rtg)->xg_active_ref);
+		oz = xfs_init_open_zone(rtg, write_pointer, WRITE_LIFE_NOT_SET,
+				false);
+		list_add_tail(&oz->oz_entry, &zi->zi_open_zones);
+		zi->zi_nr_open_zones++;
+
+		iz->available += (rtg_blocks(rtg) - write_pointer);
+		iz->reclaimable += write_pointer - used;
+	} else if (used < rtg_blocks(rtg)) {
+		/* zone fully written, but has freed blocks */
+		xfs_zone_account_reclaimable(rtg, rtg_blocks(rtg) - used);
+		iz->reclaimable += (rtg_blocks(rtg) - used);
+	}
+
+	return 0;
+}
+
+static int
+xfs_get_zone_info_cb(
+	struct blk_zone		*zone,
+	unsigned int		idx,
+	void			*data)
+{
+	struct xfs_init_zones	*iz = data;
+	struct xfs_mount	*mp = iz->mp;
+	xfs_fsblock_t		zsbno = xfs_daddr_to_rtb(mp, zone->start);
+	xfs_rgnumber_t		rgno;
+	struct xfs_rtgroup	*rtg;
+	int			error;
+
+	if (xfs_rtb_to_rgbno(mp, zsbno) != 0) {
+		xfs_warn(mp, "mismatched zone start 0x%llx.", zsbno);
+		return -EFSCORRUPTED;
+	}
+
+	rgno = xfs_rtb_to_rgno(mp, zsbno);
+	rtg = xfs_rtgroup_grab(mp, rgno);
+	if (!rtg) {
+		xfs_warn(mp, "realtime group not found for zone %u.", rgno);
+		return -EFSCORRUPTED;
+	}
+	error = xfs_init_zone(iz, rtg, zone);
+	xfs_rtgroup_rele(rtg);
+	return error;
+}
+
+/*
+ * Calculate the max open zone limit based on the of number of
+ * backing zones available
+ */
+static inline uint32_t
+xfs_max_open_zones(
+	struct xfs_mount	*mp)
+{
+	unsigned int		max_open, max_open_data_zones;
+	/*
+	 * We need two zones for every open data zone,
+	 * one in reserve as we don't reclaim open zones. One data zone
+	 * and its spare is included in XFS_MIN_ZONES.
+	 */
+	max_open_data_zones = (mp->m_sb.sb_rgcount - XFS_MIN_ZONES) / 2 + 1;
+	max_open = max_open_data_zones + XFS_OPEN_GC_ZONES;
+
+	/*
+	 * Cap the max open limit to 1/4 of available space
+	 */
+	max_open = min(max_open, mp->m_sb.sb_rgcount / 4);
+
+	return max(XFS_MIN_OPEN_ZONES, max_open);
+}
+
+/*
+ * Normally we use the open zone limit that the device reports.  If there is
+ * none let the user pick one from the command line.
+ *
+ * If the device doesn't report an open zone limit and there is no override,
+ * allow to hold about a quarter of the zones open.  In theory we could allow
+ * all to be open, but at that point we run into GC deadlocks because we can't
+ * reclaim open zones.
+ *
+ * When used on conventional SSDs a lower open limit is advisable as we'll
+ * otherwise overwhelm the FTL just as much as a conventional block allocator.
+ *
+ * Note: To debug the open zone management code, force max_open to 1 here.
+ */
+static int
+xfs_calc_open_zones(
+	struct xfs_mount	*mp)
+{
+	struct block_device	*bdev = mp->m_rtdev_targp->bt_bdev;
+	unsigned int		bdev_open_zones = bdev_max_open_zones(bdev);
+
+	if (!mp->m_max_open_zones) {
+		if (bdev_open_zones)
+			mp->m_max_open_zones = bdev_open_zones;
+		else
+			mp->m_max_open_zones = xfs_max_open_zones(mp);
+	}
+
+	if (mp->m_max_open_zones < XFS_MIN_OPEN_ZONES) {
+		xfs_notice(mp, "need at least %u open zones.",
+			XFS_MIN_OPEN_ZONES);
+		return -EIO;
+	}
+
+	if (bdev_open_zones && bdev_open_zones < mp->m_max_open_zones) {
+		mp->m_max_open_zones = bdev_open_zones;
+		xfs_info(mp, "limiting open zones to %u due to hardware limit.\n",
+			bdev_open_zones);
+	}
+
+	if (mp->m_max_open_zones > xfs_max_open_zones(mp)) {
+		mp->m_max_open_zones = xfs_max_open_zones(mp);
+		xfs_info(mp,
+"limiting open zones to %u due to total zone count (%u)",
+			mp->m_max_open_zones, mp->m_sb.sb_rgcount);
+	}
+
+	return 0;
+}
+
+static unsigned long *
+xfs_alloc_bucket_bitmap(
+	struct xfs_mount	*mp)
+{
+	return kvmalloc_array(BITS_TO_LONGS(mp->m_sb.sb_rgcount),
+			sizeof(unsigned long), GFP_KERNEL | __GFP_ZERO);
+}
+
+static struct xfs_zone_info *
+xfs_alloc_zone_info(
+	struct xfs_mount	*mp)
+{
+	struct xfs_zone_info	*zi;
+	int			i;
+
+	zi = kzalloc(sizeof(*zi), GFP_KERNEL);
+	if (!zi)
+		return NULL;
+	INIT_LIST_HEAD(&zi->zi_open_zones);
+	INIT_LIST_HEAD(&zi->zi_reclaim_reservations);
+	spin_lock_init(&zi->zi_reset_list_lock);
+	spin_lock_init(&zi->zi_open_zones_lock);
+	spin_lock_init(&zi->zi_reservation_lock);
+	init_waitqueue_head(&zi->zi_zone_wait);
+	spin_lock_init(&zi->zi_used_buckets_lock);
+	for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) {
+		zi->zi_used_bucket_bitmap[i] = xfs_alloc_bucket_bitmap(mp);
+		if (!zi->zi_used_bucket_bitmap[i])
+			goto out_free_bitmaps;
+	}
+	return zi;
+
+out_free_bitmaps:
+	while (--i > 0)
+		kvfree(zi->zi_used_bucket_bitmap[i]);
+	kfree(zi);
+	return NULL;
+}
+
+static void
+xfs_free_zone_info(
+	struct xfs_zone_info	*zi)
+{
+	int			i;
+
+	xfs_free_open_zones(zi);
+	for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++)
+		kvfree(zi->zi_used_bucket_bitmap[i]);
+	kfree(zi);
+}
+
+int
+xfs_mount_zones(
+	struct xfs_mount	*mp)
+{
+	struct xfs_init_zones	iz = {
+		.mp		= mp,
+	};
+	struct xfs_buftarg	*bt = mp->m_rtdev_targp;
+	int			error;
+
+	if (!bt) {
+		xfs_notice(mp, "RT device missing.");
+		return -EINVAL;
+	}
+
+	if (!xfs_has_rtgroups(mp) || !xfs_has_rmapbt(mp)) {
+		xfs_notice(mp, "invalid flag combination.");
+		return -EFSCORRUPTED;
+	}
+	if (mp->m_sb.sb_rextsize != 1) {
+		xfs_notice(mp, "zoned file systems do not support rextsize.");
+		return -EFSCORRUPTED;
+	}
+	if (mp->m_sb.sb_rgcount < XFS_MIN_ZONES) {
+		xfs_notice(mp,
+"zoned file systems need to have at least %u zones.", XFS_MIN_ZONES);
+		return -EFSCORRUPTED;
+	}
+
+	error = xfs_calc_open_zones(mp);
+	if (error)
+		return error;
+
+	mp->m_zone_info = xfs_alloc_zone_info(mp);
+	if (!mp->m_zone_info)
+		return -ENOMEM;
+
+	xfs_info(mp, "%u zones of %u blocks size (%u max open)",
+		 mp->m_sb.sb_rgcount, mp->m_groups[XG_TYPE_RTG].blocks,
+		 mp->m_max_open_zones);
+	trace_xfs_zones_mount(mp);
+
+	if (bdev_is_zoned(bt->bt_bdev)) {
+		error = blkdev_report_zones(bt->bt_bdev,
+				XFS_FSB_TO_BB(mp, mp->m_sb.sb_rtstart),
+				mp->m_sb.sb_rgcount, xfs_get_zone_info_cb, &iz);
+		if (error < 0)
+			goto out_free_zone_info;
+	} else {
+		struct xfs_rtgroup	*rtg = NULL;
+
+		while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+			error = xfs_init_zone(&iz, rtg, NULL);
+			if (error)
+				goto out_free_zone_info;
+		}
+	}
+
+	xfs_set_freecounter(mp, XC_FREE_RTAVAILABLE, iz.available);
+	xfs_set_freecounter(mp, XC_FREE_RTEXTENTS,
+			iz.available + iz.reclaimable);
+
+	error = xfs_zone_gc_mount(mp);
+	if (error)
+		goto out_free_zone_info;
+	return 0;
+
+out_free_zone_info:
+	xfs_free_zone_info(mp->m_zone_info);
+	return error;
+}
+
+void
+xfs_unmount_zones(
+	struct xfs_mount	*mp)
+{
+	xfs_zone_gc_unmount(mp);
+	xfs_free_zone_info(mp->m_zone_info);
+}

fs/xfs/xfs_zone_alloc.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XFS_ZONE_ALLOC_H
+#define _XFS_ZONE_ALLOC_H
+
+struct iomap_ioend;
+struct xfs_open_zone;
+
+struct xfs_zone_alloc_ctx {
+	struct xfs_open_zone	*open_zone;
+	xfs_filblks_t		reserved_blocks;
+};
+
+/*
+ * Grab any available space, even if it is less than what the caller asked for.
+ */
+#define XFS_ZR_GREEDY		(1U << 0)
+/*
+ * Only grab instantly available space, don't wait or GC.
+ */
+#define XFS_ZR_NOWAIT		(1U << 1)
+/*
+ * Dip into the reserved pool.
+ */
+#define XFS_ZR_RESERVED		(1U << 2)
+
+int xfs_zoned_space_reserve(struct xfs_inode *ip, xfs_filblks_t count_fsb,
+		unsigned int flags, struct xfs_zone_alloc_ctx *ac);
+void xfs_zoned_space_unreserve(struct xfs_inode *ip,
+		struct xfs_zone_alloc_ctx *ac);
+void xfs_zoned_add_available(struct xfs_mount *mp, xfs_filblks_t count_fsb);
+
+void xfs_zone_alloc_and_submit(struct iomap_ioend *ioend,
+		struct xfs_open_zone **oz);
+int xfs_zone_free_blocks(struct xfs_trans *tp, struct xfs_rtgroup *rtg,
+		xfs_fsblock_t fsbno, xfs_filblks_t len);
+int xfs_zoned_end_io(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count,
+		xfs_daddr_t daddr, struct xfs_open_zone *oz,
+		xfs_fsblock_t old_startblock);
+void xfs_open_zone_put(struct xfs_open_zone *oz);
+
+void xfs_zoned_wake_all(struct xfs_mount *mp);
+bool xfs_zone_rgbno_is_valid(struct xfs_rtgroup *rtg, xfs_rgnumber_t rgbno);
+void xfs_mark_rtg_boundary(struct iomap_ioend *ioend);
+
+uint64_t xfs_zoned_default_resblks(struct xfs_mount *mp,
+		enum xfs_free_counter ctr);
+void xfs_zoned_show_stats(struct seq_file *m, struct xfs_mount *mp);
+
+#ifdef CONFIG_XFS_RT
+int xfs_mount_zones(struct xfs_mount *mp);
+void xfs_unmount_zones(struct xfs_mount *mp);
+void xfs_zone_gc_start(struct xfs_mount *mp);
+void xfs_zone_gc_stop(struct xfs_mount *mp);
+#else
+static inline int xfs_mount_zones(struct xfs_mount *mp)
+{
+	return -EIO;
+}
+static inline void xfs_unmount_zones(struct xfs_mount *mp)
+{
+}
+static inline void xfs_zone_gc_start(struct xfs_mount *mp)
+{
+}
+static inline void xfs_zone_gc_stop(struct xfs_mount *mp)
+{
+}
+#endif /* CONFIG_XFS_RT */
+
+#endif /* _XFS_ZONE_ALLOC_H */

fs/xfs/xfs_zone_gc.c

···
+// 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_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_btree.h"
+#include "xfs_trans.h"
+#include "xfs_icache.h"
+#include "xfs_rmap.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_zone_priv.h"
+#include "xfs_zones.h"
+#include "xfs_trace.h"
+
+/*
+ * Implement Garbage Collection (GC) of partially used zoned.
+ *
+ * To support the purely sequential writes in each zone, zoned XFS needs to be
+ * able to move data remaining in a zone out of it to reset the zone to prepare
+ * for writing to it again.
+ *
+ * This is done by the GC thread implemented in this file.  To support that a
+ * number of zones (XFS_GC_ZONES) is reserved from the user visible capacity to
+ * write the garbage collected data into.
+ *
+ * Whenever the available space is below the chosen threshold, the GC thread
+ * looks for potential non-empty but not fully used zones that are worth
+ * reclaiming.  Once found the rmap for the victim zone is queried, and after
+ * a bit of sorting to reduce fragmentation, the still live extents are read
+ * into memory and written to the GC target zone, and the bmap btree of the
+ * files is updated to point to the new location.  To avoid taking the IOLOCK
+ * and MMAPLOCK for the entire GC process and thus affecting the latency of
+ * user reads and writes to the files, the GC writes are speculative and the
+ * I/O completion checks that no other writes happened for the affected regions
+ * before remapping.
+ *
+ * Once a zone does not contain any valid data, be that through GC or user
+ * block removal, it is queued for for a zone reset.  The reset operation
+ * carefully ensures that the RT device cache is flushed and all transactions
+ * referencing the rmap have been committed to disk.
+ */
+
+/*
+ * Size of each GC scratch pad.  This is also the upper bound for each
+ * GC I/O, which helps to keep latency down.
+ */
+#define XFS_GC_CHUNK_SIZE	SZ_1M
+
+/*
+ * Scratchpad data to read GCed data into.
+ *
+ * The offset member tracks where the next allocation starts, and freed tracks
+ * the amount of space that is not used anymore.
+ */
+#define XFS_ZONE_GC_NR_SCRATCH	2
+struct xfs_zone_scratch {
+	struct folio			*folio;
+	unsigned int			offset;
+	unsigned int			freed;
+};
+
+/*
+ * Chunk that is read and written for each GC operation.
+ *
+ * Note that for writes to actual zoned devices, the chunk can be split when
+ * reaching the hardware limit.
+ */
+struct xfs_gc_bio {
+	struct xfs_zone_gc_data		*data;
+
+	/*
+	 * Entry into the reading/writing/resetting list.  Only accessed from
+	 * the GC thread, so no locking needed.
+	 */
+	struct list_head		entry;
+
+	/*
+	 * State of this gc_bio.  Done means the current I/O completed.
+	 * Set from the bio end I/O handler, read from the GC thread.
+	 */
+	enum {
+		XFS_GC_BIO_NEW,
+		XFS_GC_BIO_DONE,
+	} state;
+
+	/*
+	 * Pointer to the inode and byte range in the inode that this
+	 * GC chunk is operating on.
+	 */
+	struct xfs_inode		*ip;
+	loff_t				offset;
+	unsigned int			len;
+
+	/*
+	 * Existing startblock (in the zone to be freed) and newly assigned
+	 * daddr in the zone GCed into.
+	 */
+	xfs_fsblock_t			old_startblock;
+	xfs_daddr_t			new_daddr;
+	struct xfs_zone_scratch		*scratch;
+
+	/* Are we writing to a sequential write required zone? */
+	bool				is_seq;
+
+	/* Open Zone being written to */
+	struct xfs_open_zone		*oz;
+
+	/* Bio used for reads and writes, including the bvec used by it */
+	struct bio_vec			bv;
+	struct bio			bio;	/* must be last */
+};
+
+#define XFS_ZONE_GC_RECS		1024
+
+/* iterator, needs to be reinitialized for each victim zone */
+struct xfs_zone_gc_iter {
+	struct xfs_rtgroup		*victim_rtg;
+	unsigned int			rec_count;
+	unsigned int			rec_idx;
+	xfs_agblock_t			next_startblock;
+	struct xfs_rmap_irec		*recs;
+};
+
+/*
+ * Per-mount GC state.
+ */
+struct xfs_zone_gc_data {
+	struct xfs_mount		*mp;
+
+	/* bioset used to allocate the gc_bios */
+	struct bio_set			bio_set;
+
+	/*
+	 * Scratchpad used, and index to indicated which one is used.
+	 */
+	struct xfs_zone_scratch		scratch[XFS_ZONE_GC_NR_SCRATCH];
+	unsigned int			scratch_idx;
+
+	/*
+	 * List of bios currently being read, written and reset.
+	 * These lists are only accessed by the GC thread itself, and must only
+	 * be processed in order.
+	 */
+	struct list_head		reading;
+	struct list_head		writing;
+	struct list_head		resetting;
+
+	/*
+	 * Iterator for the victim zone.
+	 */
+	struct xfs_zone_gc_iter		iter;
+};
+
+/*
+ * We aim to keep enough zones free in stock to fully use the open zone limit
+ * for data placement purposes.
+ */
+bool
+xfs_zoned_need_gc(
+	struct xfs_mount	*mp)
+{
+	if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE))
+		return false;
+	if (xfs_estimate_freecounter(mp, XC_FREE_RTAVAILABLE) <
+	    mp->m_groups[XG_TYPE_RTG].blocks *
+	    (mp->m_max_open_zones - XFS_OPEN_GC_ZONES))
+		return true;
+	return false;
+}
+
+static struct xfs_zone_gc_data *
+xfs_zone_gc_data_alloc(
+	struct xfs_mount	*mp)
+{
+	struct xfs_zone_gc_data	*data;
+	int			i;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return NULL;
+	data->iter.recs = kcalloc(XFS_ZONE_GC_RECS, sizeof(*data->iter.recs),
+			GFP_KERNEL);
+	if (!data->iter.recs)
+		goto out_free_data;
+
+	/*
+	 * We actually only need a single bio_vec.  It would be nice to have
+	 * a flag that only allocates the inline bvecs and not the separate
+	 * bvec pool.
+	 */
+	if (bioset_init(&data->bio_set, 16, offsetof(struct xfs_gc_bio, bio),
+			BIOSET_NEED_BVECS))
+		goto out_free_recs;
+	for (i = 0; i < XFS_ZONE_GC_NR_SCRATCH; i++) {
+		data->scratch[i].folio =
+			folio_alloc(GFP_KERNEL, get_order(XFS_GC_CHUNK_SIZE));
+		if (!data->scratch[i].folio)
+			goto out_free_scratch;
+	}
+	INIT_LIST_HEAD(&data->reading);
+	INIT_LIST_HEAD(&data->writing);
+	INIT_LIST_HEAD(&data->resetting);
+	data->mp = mp;
+	return data;
+
+out_free_scratch:
+	while (--i >= 0)
+		folio_put(data->scratch[i].folio);
+	bioset_exit(&data->bio_set);
+out_free_recs:
+	kfree(data->iter.recs);
+out_free_data:
+	kfree(data);
+	return NULL;
+}
+
+static void
+xfs_zone_gc_data_free(
+	struct xfs_zone_gc_data	*data)
+{
+	int			i;
+
+	for (i = 0; i < XFS_ZONE_GC_NR_SCRATCH; i++)
+		folio_put(data->scratch[i].folio);
+	bioset_exit(&data->bio_set);
+	kfree(data->iter.recs);
+	kfree(data);
+}
+
+static void
+xfs_zone_gc_iter_init(
+	struct xfs_zone_gc_iter	*iter,
+	struct xfs_rtgroup	*victim_rtg)
+
+{
+	iter->next_startblock = 0;
+	iter->rec_count = 0;
+	iter->rec_idx = 0;
+	iter->victim_rtg = victim_rtg;
+}
+
+/*
+ * Query the rmap of the victim zone to gather the records to evacuate.
+ */
+static int
+xfs_zone_gc_query_cb(
+	struct xfs_btree_cur	*cur,
+	const struct xfs_rmap_irec *irec,
+	void			*private)
+{
+	struct xfs_zone_gc_iter	*iter = private;
+
+	ASSERT(!XFS_RMAP_NON_INODE_OWNER(irec->rm_owner));
+	ASSERT(!xfs_is_sb_inum(cur->bc_mp, irec->rm_owner));
+	ASSERT(!(irec->rm_flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK)));
+
+	iter->recs[iter->rec_count] = *irec;
+	if (++iter->rec_count == XFS_ZONE_GC_RECS) {
+		iter->next_startblock =
+			irec->rm_startblock + irec->rm_blockcount;
+		return 1;
+	}
+	return 0;
+}
+
+#define cmp_int(l, r)		((l > r) - (l < r))
+
+static int
+xfs_zone_gc_rmap_rec_cmp(
+	const void			*a,
+	const void			*b)
+{
+	const struct xfs_rmap_irec	*reca = a;
+	const struct xfs_rmap_irec	*recb = b;
+	int				diff;
+
+	diff = cmp_int(reca->rm_owner, recb->rm_owner);
+	if (diff)
+		return diff;
+	return cmp_int(reca->rm_offset, recb->rm_offset);
+}
+
+static int
+xfs_zone_gc_query(
+	struct xfs_mount	*mp,
+	struct xfs_zone_gc_iter	*iter)
+{
+	struct xfs_rtgroup	*rtg = iter->victim_rtg;
+	struct xfs_rmap_irec	ri_low = { };
+	struct xfs_rmap_irec	ri_high;
+	struct xfs_btree_cur	*cur;
+	struct xfs_trans	*tp;
+	int			error;
+
+	ASSERT(iter->next_startblock <= rtg_blocks(rtg));
+	if (iter->next_startblock == rtg_blocks(rtg))
+		goto done;
+
+	ASSERT(iter->next_startblock < rtg_blocks(rtg));
+	ri_low.rm_startblock = iter->next_startblock;
+	memset(&ri_high, 0xFF, sizeof(ri_high));
+
+	iter->rec_idx = 0;
+	iter->rec_count = 0;
+
+	error = xfs_trans_alloc_empty(mp, &tp);
+	if (error)
+		return error;
+
+	xfs_rtgroup_lock(rtg, XFS_RTGLOCK_RMAP);
+	cur = xfs_rtrmapbt_init_cursor(tp, rtg);
+	error = xfs_rmap_query_range(cur, &ri_low, &ri_high,
+			xfs_zone_gc_query_cb, iter);
+	xfs_rtgroup_unlock(rtg, XFS_RTGLOCK_RMAP);
+	xfs_btree_del_cursor(cur, error < 0 ? error : 0);
+	xfs_trans_cancel(tp);
+
+	if (error < 0)
+		return error;
+
+	/*
+	 * Sort the rmap records by inode number and increasing offset to
+	 * defragment the mappings.
+	 *
+	 * This could be further enhanced by an even bigger look ahead window,
+	 * but that's better left until we have better detection of changes to
+	 * inode mapping to avoid the potential of GCing already dead data.
+	 */
+	sort(iter->recs, iter->rec_count, sizeof(iter->recs[0]),
+			xfs_zone_gc_rmap_rec_cmp, NULL);
+
+	if (error == 0) {
+		/*
+		 * We finished iterating through the zone.
+		 */
+		iter->next_startblock = rtg_blocks(rtg);
+		if (iter->rec_count == 0)
+			goto done;
+	}
+
+	return 0;
+done:
+	xfs_rtgroup_rele(iter->victim_rtg);
+	iter->victim_rtg = NULL;
+	return 0;
+}
+
+static bool
+xfs_zone_gc_iter_next(
+	struct xfs_mount	*mp,
+	struct xfs_zone_gc_iter	*iter,
+	struct xfs_rmap_irec	*chunk_rec,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_rmap_irec	*irec;
+	int			error;
+
+	if (!iter->victim_rtg)
+		return false;
+
+retry:
+	if (iter->rec_idx == iter->rec_count) {
+		error = xfs_zone_gc_query(mp, iter);
+		if (error)
+			goto fail;
+		if (!iter->victim_rtg)
+			return false;
+	}
+
+	irec = &iter->recs[iter->rec_idx];
+	error = xfs_iget(mp, NULL, irec->rm_owner,
+			XFS_IGET_UNTRUSTED | XFS_IGET_DONTCACHE, 0, ipp);
+	if (error) {
+		/*
+		 * If the inode was already deleted, skip over it.
+		 */
+		if (error == -ENOENT) {
+			iter->rec_idx++;
+			goto retry;
+		}
+		goto fail;
+	}
+
+	if (!S_ISREG(VFS_I(*ipp)->i_mode) || !XFS_IS_REALTIME_INODE(*ipp)) {
+		iter->rec_idx++;
+		xfs_irele(*ipp);
+		goto retry;
+	}
+
+	*chunk_rec = *irec;
+	return true;
+
+fail:
+	xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+	return false;
+}
+
+static void
+xfs_zone_gc_iter_advance(
+	struct xfs_zone_gc_iter	*iter,
+	xfs_extlen_t		count_fsb)
+{
+	struct xfs_rmap_irec	*irec = &iter->recs[iter->rec_idx];
+
+	irec->rm_offset += count_fsb;
+	irec->rm_startblock += count_fsb;
+	irec->rm_blockcount -= count_fsb;
+	if (!irec->rm_blockcount)
+		iter->rec_idx++;
+}
+
+static struct xfs_rtgroup *
+xfs_zone_gc_pick_victim_from(
+	struct xfs_mount	*mp,
+	uint32_t		bucket)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	uint32_t		victim_used = U32_MAX;
+	struct xfs_rtgroup	*victim_rtg = NULL;
+	uint32_t		bit;
+
+	if (!zi->zi_used_bucket_entries[bucket])
+		return NULL;
+
+	for_each_set_bit(bit, zi->zi_used_bucket_bitmap[bucket],
+			mp->m_sb.sb_rgcount) {
+		struct xfs_rtgroup *rtg = xfs_rtgroup_grab(mp, bit);
+
+		if (!rtg)
+			continue;
+
+		/* skip zones that are just waiting for a reset */
+		if (rtg_rmap(rtg)->i_used_blocks == 0 ||
+		    rtg_rmap(rtg)->i_used_blocks >= victim_used) {
+			xfs_rtgroup_rele(rtg);
+			continue;
+		}
+
+		if (victim_rtg)
+			xfs_rtgroup_rele(victim_rtg);
+		victim_rtg = rtg;
+		victim_used = rtg_rmap(rtg)->i_used_blocks;
+
+		/*
+		 * Any zone that is less than 1 percent used is fair game for
+		 * instant reclaim. All of these zones are in the last
+		 * bucket, so avoid the expensive division for the zones
+		 * in the other buckets.
+		 */
+		if (bucket == 0 &&
+		    rtg_rmap(rtg)->i_used_blocks < rtg_blocks(rtg) / 100)
+			break;
+	}
+
+	return victim_rtg;
+}
+
+/*
+ * Iterate through all zones marked as reclaimable and find a candidate to
+ * reclaim.
+ */
+static bool
+xfs_zone_gc_select_victim(
+	struct xfs_zone_gc_data	*data)
+{
+	struct xfs_zone_gc_iter	*iter = &data->iter;
+	struct xfs_mount	*mp = data->mp;
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_rtgroup	*victim_rtg = NULL;
+	unsigned int		bucket;
+
+	if (xfs_is_shutdown(mp))
+		return false;
+
+	if (iter->victim_rtg)
+		return true;
+
+	/*
+	 * Don't start new work if we are asked to stop or park.
+	 */
+	if (kthread_should_stop() || kthread_should_park())
+		return false;
+
+	if (!xfs_zoned_need_gc(mp))
+		return false;
+
+	spin_lock(&zi->zi_used_buckets_lock);
+	for (bucket = 0; bucket < XFS_ZONE_USED_BUCKETS; bucket++) {
+		victim_rtg = xfs_zone_gc_pick_victim_from(mp, bucket);
+		if (victim_rtg)
+			break;
+	}
+	spin_unlock(&zi->zi_used_buckets_lock);
+
+	if (!victim_rtg)
+		return false;
+
+	trace_xfs_zone_gc_select_victim(victim_rtg, bucket);
+	xfs_zone_gc_iter_init(iter, victim_rtg);
+	return true;
+}
+
+static struct xfs_open_zone *
+xfs_zone_gc_steal_open(
+	struct xfs_zone_info	*zi)
+{
+	struct xfs_open_zone	*oz, *found = NULL;
+
+	spin_lock(&zi->zi_open_zones_lock);
+	list_for_each_entry(oz, &zi->zi_open_zones, oz_entry) {
+		if (!found ||
+		    oz->oz_write_pointer < found->oz_write_pointer)
+			found = oz;
+	}
+
+	if (found) {
+		found->oz_is_gc = true;
+		list_del_init(&found->oz_entry);
+		zi->zi_nr_open_zones--;
+	}
+
+	spin_unlock(&zi->zi_open_zones_lock);
+	return found;
+}
+
+static struct xfs_open_zone *
+xfs_zone_gc_select_target(
+	struct xfs_mount	*mp)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_open_zone	*oz = zi->zi_open_gc_zone;
+
+	/*
+	 * We need to wait for pending writes to finish.
+	 */
+	if (oz && oz->oz_written < rtg_blocks(oz->oz_rtg))
+		return NULL;
+
+	ASSERT(zi->zi_nr_open_zones <=
+		mp->m_max_open_zones - XFS_OPEN_GC_ZONES);
+	oz = xfs_open_zone(mp, WRITE_LIFE_NOT_SET, true);
+	if (oz)
+		trace_xfs_zone_gc_target_opened(oz->oz_rtg);
+	spin_lock(&zi->zi_open_zones_lock);
+	zi->zi_open_gc_zone = oz;
+	spin_unlock(&zi->zi_open_zones_lock);
+	return oz;
+}
+
+/*
+ * Ensure we have a valid open zone to write the GC data to.
+ *
+ * If the current target zone has space keep writing to it, else first wait for
+ * all pending writes and then pick a new one.
+ */
+static struct xfs_open_zone *
+xfs_zone_gc_ensure_target(
+	struct xfs_mount	*mp)
+{
+	struct xfs_open_zone	*oz = mp->m_zone_info->zi_open_gc_zone;
+
+	if (!oz || oz->oz_write_pointer == rtg_blocks(oz->oz_rtg))
+		return xfs_zone_gc_select_target(mp);
+	return oz;
+}
+
+static unsigned int
+xfs_zone_gc_scratch_available(
+	struct xfs_zone_gc_data	*data)
+{
+	return XFS_GC_CHUNK_SIZE - data->scratch[data->scratch_idx].offset;
+}
+
+static bool
+xfs_zone_gc_space_available(
+	struct xfs_zone_gc_data	*data)
+{
+	struct xfs_open_zone	*oz;
+
+	oz = xfs_zone_gc_ensure_target(data->mp);
+	if (!oz)
+		return false;
+	return oz->oz_write_pointer < rtg_blocks(oz->oz_rtg) &&
+		xfs_zone_gc_scratch_available(data);
+}
+
+static void
+xfs_zone_gc_end_io(
+	struct bio		*bio)
+{
+	struct xfs_gc_bio	*chunk =
+		container_of(bio, struct xfs_gc_bio, bio);
+	struct xfs_zone_gc_data	*data = chunk->data;
+
+	WRITE_ONCE(chunk->state, XFS_GC_BIO_DONE);
+	wake_up_process(data->mp->m_zone_info->zi_gc_thread);
+}
+
+static struct xfs_open_zone *
+xfs_zone_gc_alloc_blocks(
+	struct xfs_zone_gc_data	*data,
+	xfs_extlen_t		*count_fsb,
+	xfs_daddr_t		*daddr,
+	bool			*is_seq)
+{
+	struct xfs_mount	*mp = data->mp;
+	struct xfs_open_zone	*oz;
+
+	oz = xfs_zone_gc_ensure_target(mp);
+	if (!oz)
+		return NULL;
+
+	*count_fsb = min(*count_fsb,
+		XFS_B_TO_FSB(mp, xfs_zone_gc_scratch_available(data)));
+
+	/*
+	 * Directly allocate GC blocks from the reserved pool.
+	 *
+	 * If we'd take them from the normal pool we could be stealing blocks
+	 * from a regular writer, which would then have to wait for GC and
+	 * deadlock.
+	 */
+	spin_lock(&mp->m_sb_lock);
+	*count_fsb = min(*count_fsb,
+			rtg_blocks(oz->oz_rtg) - oz->oz_write_pointer);
+	*count_fsb = min3(*count_fsb,
+			mp->m_free[XC_FREE_RTEXTENTS].res_avail,
+			mp->m_free[XC_FREE_RTAVAILABLE].res_avail);
+	mp->m_free[XC_FREE_RTEXTENTS].res_avail -= *count_fsb;
+	mp->m_free[XC_FREE_RTAVAILABLE].res_avail -= *count_fsb;
+	spin_unlock(&mp->m_sb_lock);
+
+	if (!*count_fsb)
+		return NULL;
+
+	*daddr = xfs_gbno_to_daddr(&oz->oz_rtg->rtg_group, 0);
+	*is_seq = bdev_zone_is_seq(mp->m_rtdev_targp->bt_bdev, *daddr);
+	if (!*is_seq)
+		*daddr += XFS_FSB_TO_BB(mp, oz->oz_write_pointer);
+	oz->oz_write_pointer += *count_fsb;
+	atomic_inc(&oz->oz_ref);
+	return oz;
+}
+
+static bool
+xfs_zone_gc_start_chunk(
+	struct xfs_zone_gc_data	*data)
+{
+	struct xfs_zone_gc_iter	*iter = &data->iter;
+	struct xfs_mount	*mp = data->mp;
+	struct block_device	*bdev = mp->m_rtdev_targp->bt_bdev;
+	struct xfs_open_zone	*oz;
+	struct xfs_rmap_irec	irec;
+	struct xfs_gc_bio	*chunk;
+	struct xfs_inode	*ip;
+	struct bio		*bio;
+	xfs_daddr_t		daddr;
+	bool			is_seq;
+
+	if (xfs_is_shutdown(mp))
+		return false;
+
+	if (!xfs_zone_gc_iter_next(mp, iter, &irec, &ip))
+		return false;
+	oz = xfs_zone_gc_alloc_blocks(data, &irec.rm_blockcount, &daddr,
+			&is_seq);
+	if (!oz) {
+		xfs_irele(ip);
+		return false;
+	}
+
+	bio = bio_alloc_bioset(bdev, 1, REQ_OP_READ, GFP_NOFS, &data->bio_set);
+
+	chunk = container_of(bio, struct xfs_gc_bio, bio);
+	chunk->ip = ip;
+	chunk->offset = XFS_FSB_TO_B(mp, irec.rm_offset);
+	chunk->len = XFS_FSB_TO_B(mp, irec.rm_blockcount);
+	chunk->old_startblock =
+		xfs_rgbno_to_rtb(iter->victim_rtg, irec.rm_startblock);
+	chunk->new_daddr = daddr;
+	chunk->is_seq = is_seq;
+	chunk->scratch = &data->scratch[data->scratch_idx];
+	chunk->data = data;
+	chunk->oz = oz;
+
+	bio->bi_iter.bi_sector = xfs_rtb_to_daddr(mp, chunk->old_startblock);
+	bio->bi_end_io = xfs_zone_gc_end_io;
+	bio_add_folio_nofail(bio, chunk->scratch->folio, chunk->len,
+			chunk->scratch->offset);
+	chunk->scratch->offset += chunk->len;
+	if (chunk->scratch->offset == XFS_GC_CHUNK_SIZE) {
+		data->scratch_idx =
+			(data->scratch_idx + 1) % XFS_ZONE_GC_NR_SCRATCH;
+	}
+	WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW);
+	list_add_tail(&chunk->entry, &data->reading);
+	xfs_zone_gc_iter_advance(iter, irec.rm_blockcount);
+
+	submit_bio(bio);
+	return true;
+}
+
+static void
+xfs_zone_gc_free_chunk(
+	struct xfs_gc_bio	*chunk)
+{
+	list_del(&chunk->entry);
+	xfs_open_zone_put(chunk->oz);
+	xfs_irele(chunk->ip);
+	bio_put(&chunk->bio);
+}
+
+static void
+xfs_zone_gc_submit_write(
+	struct xfs_zone_gc_data	*data,
+	struct xfs_gc_bio	*chunk)
+{
+	if (chunk->is_seq) {
+		chunk->bio.bi_opf &= ~REQ_OP_WRITE;
+		chunk->bio.bi_opf |= REQ_OP_ZONE_APPEND;
+	}
+	chunk->bio.bi_iter.bi_sector = chunk->new_daddr;
+	chunk->bio.bi_end_io = xfs_zone_gc_end_io;
+	submit_bio(&chunk->bio);
+}
+
+static struct xfs_gc_bio *
+xfs_zone_gc_split_write(
+	struct xfs_zone_gc_data	*data,
+	struct xfs_gc_bio	*chunk)
+{
+	struct queue_limits	*lim =
+		&bdev_get_queue(chunk->bio.bi_bdev)->limits;
+	struct xfs_gc_bio	*split_chunk;
+	int			split_sectors;
+	unsigned int		split_len;
+	struct bio		*split;
+	unsigned int		nsegs;
+
+	if (!chunk->is_seq)
+		return NULL;
+
+	split_sectors = bio_split_rw_at(&chunk->bio, lim, &nsegs,
+			lim->max_zone_append_sectors << SECTOR_SHIFT);
+	if (!split_sectors)
+		return NULL;
+
+	/* ensure the split chunk is still block size aligned */
+	split_sectors = ALIGN_DOWN(split_sectors << SECTOR_SHIFT,
+			data->mp->m_sb.sb_blocksize) >> SECTOR_SHIFT;
+	split_len = split_sectors << SECTOR_SHIFT;
+
+	split = bio_split(&chunk->bio, split_sectors, GFP_NOFS, &data->bio_set);
+	split_chunk = container_of(split, struct xfs_gc_bio, bio);
+	split_chunk->data = data;
+	ihold(VFS_I(chunk->ip));
+	split_chunk->ip = chunk->ip;
+	split_chunk->is_seq = chunk->is_seq;
+	split_chunk->scratch = chunk->scratch;
+	split_chunk->offset = chunk->offset;
+	split_chunk->len = split_len;
+	split_chunk->old_startblock = chunk->old_startblock;
+	split_chunk->new_daddr = chunk->new_daddr;
+	split_chunk->oz = chunk->oz;
+	atomic_inc(&chunk->oz->oz_ref);
+
+	chunk->offset += split_len;
+	chunk->len -= split_len;
+	chunk->old_startblock += XFS_B_TO_FSB(data->mp, split_len);
+
+	/* add right before the original chunk */
+	WRITE_ONCE(split_chunk->state, XFS_GC_BIO_NEW);
+	list_add_tail(&split_chunk->entry, &chunk->entry);
+	return split_chunk;
+}
+
+static void
+xfs_zone_gc_write_chunk(
+	struct xfs_gc_bio	*chunk)
+{
+	struct xfs_zone_gc_data	*data = chunk->data;
+	struct xfs_mount	*mp = chunk->ip->i_mount;
+	unsigned int		folio_offset = chunk->bio.bi_io_vec->bv_offset;
+	struct xfs_gc_bio	*split_chunk;
+
+	if (chunk->bio.bi_status)
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+	if (xfs_is_shutdown(mp)) {
+		xfs_zone_gc_free_chunk(chunk);
+		return;
+	}
+
+	WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW);
+	list_move_tail(&chunk->entry, &data->writing);
+
+	bio_reset(&chunk->bio, mp->m_rtdev_targp->bt_bdev, REQ_OP_WRITE);
+	bio_add_folio_nofail(&chunk->bio, chunk->scratch->folio, chunk->len,
+			folio_offset);
+
+	while ((split_chunk = xfs_zone_gc_split_write(data, chunk)))
+		xfs_zone_gc_submit_write(data, split_chunk);
+	xfs_zone_gc_submit_write(data, chunk);
+}
+
+static void
+xfs_zone_gc_finish_chunk(
+	struct xfs_gc_bio	*chunk)
+{
+	uint			iolock = XFS_IOLOCK_EXCL | XFS_MMAPLOCK_EXCL;
+	struct xfs_inode	*ip = chunk->ip;
+	struct xfs_mount	*mp = ip->i_mount;
+	int			error;
+
+	if (chunk->bio.bi_status)
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+	if (xfs_is_shutdown(mp)) {
+		xfs_zone_gc_free_chunk(chunk);
+		return;
+	}
+
+	chunk->scratch->freed += chunk->len;
+	if (chunk->scratch->freed == chunk->scratch->offset) {
+		chunk->scratch->offset = 0;
+		chunk->scratch->freed = 0;
+	}
+
+	/*
+	 * Cycle through the iolock and wait for direct I/O and layouts to
+	 * ensure no one is reading from the old mapping before it goes away.
+	 *
+	 * Note that xfs_zoned_end_io() below checks that no other writer raced
+	 * with us to update the mapping by checking that the old startblock
+	 * didn't change.
+	 */
+	xfs_ilock(ip, iolock);
+	error = xfs_break_layouts(VFS_I(ip), &iolock, BREAK_UNMAP);
+	if (!error)
+		inode_dio_wait(VFS_I(ip));
+	xfs_iunlock(ip, iolock);
+	if (error)
+		goto free;
+
+	if (chunk->is_seq)
+		chunk->new_daddr = chunk->bio.bi_iter.bi_sector;
+	error = xfs_zoned_end_io(ip, chunk->offset, chunk->len,
+			chunk->new_daddr, chunk->oz, chunk->old_startblock);
+free:
+	if (error)
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+	xfs_zone_gc_free_chunk(chunk);
+}
+
+static void
+xfs_zone_gc_finish_reset(
+	struct xfs_gc_bio	*chunk)
+{
+	struct xfs_rtgroup	*rtg = chunk->bio.bi_private;
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+
+	if (chunk->bio.bi_status) {
+		xfs_force_shutdown(mp, SHUTDOWN_META_IO_ERROR);
+		goto out;
+	}
+
+	xfs_group_set_mark(&rtg->rtg_group, XFS_RTG_FREE);
+	atomic_inc(&zi->zi_nr_free_zones);
+
+	xfs_zoned_add_available(mp, rtg_blocks(rtg));
+
+	wake_up_all(&zi->zi_zone_wait);
+out:
+	list_del(&chunk->entry);
+	bio_put(&chunk->bio);
+}
+
+static bool
+xfs_zone_gc_prepare_reset(
+	struct bio		*bio,
+	struct xfs_rtgroup	*rtg)
+{
+	trace_xfs_zone_reset(rtg);
+
+	ASSERT(rtg_rmap(rtg)->i_used_blocks == 0);
+	bio->bi_iter.bi_sector = xfs_gbno_to_daddr(&rtg->rtg_group, 0);
+	if (!bdev_zone_is_seq(bio->bi_bdev, bio->bi_iter.bi_sector)) {
+		if (!bdev_max_discard_sectors(bio->bi_bdev))
+			return false;
+		bio->bi_opf = REQ_OP_DISCARD | REQ_SYNC;
+		bio->bi_iter.bi_size =
+			XFS_FSB_TO_B(rtg_mount(rtg), rtg_blocks(rtg));
+	}
+
+	return true;
+}
+
+int
+xfs_zone_gc_reset_sync(
+	struct xfs_rtgroup	*rtg)
+{
+	int			error = 0;
+	struct bio		bio;
+
+	bio_init(&bio, rtg_mount(rtg)->m_rtdev_targp->bt_bdev, NULL, 0,
+			REQ_OP_ZONE_RESET);
+	if (xfs_zone_gc_prepare_reset(&bio, rtg))
+		error = submit_bio_wait(&bio);
+	bio_uninit(&bio);
+
+	return error;
+}
+
+static void
+xfs_zone_gc_reset_zones(
+	struct xfs_zone_gc_data	*data,
+	struct xfs_group	*reset_list)
+{
+	struct xfs_group	*next = reset_list;
+
+	if (blkdev_issue_flush(data->mp->m_rtdev_targp->bt_bdev) < 0) {
+		xfs_force_shutdown(data->mp, SHUTDOWN_META_IO_ERROR);
+		return;
+	}
+
+	do {
+		struct xfs_rtgroup	*rtg = to_rtg(next);
+		struct xfs_gc_bio	*chunk;
+		struct bio		*bio;
+
+		xfs_log_force_inode(rtg_rmap(rtg));
+
+		next = rtg_group(rtg)->xg_next_reset;
+		rtg_group(rtg)->xg_next_reset = NULL;
+
+		bio = bio_alloc_bioset(rtg_mount(rtg)->m_rtdev_targp->bt_bdev,
+				0, REQ_OP_ZONE_RESET, GFP_NOFS, &data->bio_set);
+		bio->bi_private = rtg;
+		bio->bi_end_io = xfs_zone_gc_end_io;
+
+		chunk = container_of(bio, struct xfs_gc_bio, bio);
+		chunk->data = data;
+		WRITE_ONCE(chunk->state, XFS_GC_BIO_NEW);
+		list_add_tail(&chunk->entry, &data->resetting);
+
+		/*
+		 * Also use the bio to drive the state machine when neither
+		 * zone reset nor discard is supported to keep things simple.
+		 */
+		if (xfs_zone_gc_prepare_reset(bio, rtg))
+			submit_bio(bio);
+		else
+			bio_endio(bio);
+	} while (next);
+}
+
+/*
+ * Handle the work to read and write data for GC and to reset the zones,
+ * including handling all completions.
+ *
+ * Note that the order of the chunks is preserved so that we don't undo the
+ * optimal order established by xfs_zone_gc_query().
+ */
+static bool
+xfs_zone_gc_handle_work(
+	struct xfs_zone_gc_data	*data)
+{
+	struct xfs_zone_info	*zi = data->mp->m_zone_info;
+	struct xfs_gc_bio	*chunk, *next;
+	struct xfs_group	*reset_list;
+	struct blk_plug		plug;
+
+	spin_lock(&zi->zi_reset_list_lock);
+	reset_list = zi->zi_reset_list;
+	zi->zi_reset_list = NULL;
+	spin_unlock(&zi->zi_reset_list_lock);
+
+	if (!xfs_zone_gc_select_victim(data) ||
+	    !xfs_zone_gc_space_available(data)) {
+		if (list_empty(&data->reading) &&
+		    list_empty(&data->writing) &&
+		    list_empty(&data->resetting) &&
+		    !reset_list)
+			return false;
+	}
+
+	__set_current_state(TASK_RUNNING);
+	try_to_freeze();
+
+	if (reset_list)
+		xfs_zone_gc_reset_zones(data, reset_list);
+
+	list_for_each_entry_safe(chunk, next, &data->resetting, entry) {
+		if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE)
+			break;
+		xfs_zone_gc_finish_reset(chunk);
+	}
+
+	list_for_each_entry_safe(chunk, next, &data->writing, entry) {
+		if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE)
+			break;
+		xfs_zone_gc_finish_chunk(chunk);
+	}
+
+	blk_start_plug(&plug);
+	list_for_each_entry_safe(chunk, next, &data->reading, entry) {
+		if (READ_ONCE(chunk->state) != XFS_GC_BIO_DONE)
+			break;
+		xfs_zone_gc_write_chunk(chunk);
+	}
+	blk_finish_plug(&plug);
+
+	blk_start_plug(&plug);
+	while (xfs_zone_gc_start_chunk(data))
+		;
+	blk_finish_plug(&plug);
+	return true;
+}
+
+/*
+ * Note that the current GC algorithm would break reflinks and thus duplicate
+ * data that was shared by multiple owners before.  Because of that reflinks
+ * are currently not supported on zoned file systems and can't be created or
+ * mounted.
+ */
+static int
+xfs_zoned_gcd(
+	void			*private)
+{
+	struct xfs_zone_gc_data	*data = private;
+	struct xfs_mount	*mp = data->mp;
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	unsigned int		nofs_flag;
+
+	nofs_flag = memalloc_nofs_save();
+	set_freezable();
+
+	for (;;) {
+		set_current_state(TASK_INTERRUPTIBLE | TASK_FREEZABLE);
+		xfs_set_zonegc_running(mp);
+		if (xfs_zone_gc_handle_work(data))
+			continue;
+
+		if (list_empty(&data->reading) &&
+		    list_empty(&data->writing) &&
+		    list_empty(&data->resetting) &&
+		    !zi->zi_reset_list) {
+			xfs_clear_zonegc_running(mp);
+			xfs_zoned_resv_wake_all(mp);
+
+			if (kthread_should_stop()) {
+				__set_current_state(TASK_RUNNING);
+				break;
+			}
+
+			if (kthread_should_park()) {
+				__set_current_state(TASK_RUNNING);
+				kthread_parkme();
+				continue;
+			}
+		}
+
+		schedule();
+	}
+	xfs_clear_zonegc_running(mp);
+
+	if (data->iter.victim_rtg)
+		xfs_rtgroup_rele(data->iter.victim_rtg);
+
+	memalloc_nofs_restore(nofs_flag);
+	xfs_zone_gc_data_free(data);
+	return 0;
+}
+
+void
+xfs_zone_gc_start(
+	struct xfs_mount	*mp)
+{
+	if (xfs_has_zoned(mp))
+		kthread_unpark(mp->m_zone_info->zi_gc_thread);
+}
+
+void
+xfs_zone_gc_stop(
+	struct xfs_mount	*mp)
+{
+	if (xfs_has_zoned(mp))
+		kthread_park(mp->m_zone_info->zi_gc_thread);
+}
+
+int
+xfs_zone_gc_mount(
+	struct xfs_mount	*mp)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_zone_gc_data	*data;
+	struct xfs_open_zone	*oz;
+	int			error;
+
+	/*
+	 * If there are no free zones available for GC, pick the open zone with
+	 * the least used space to GC into.  This should only happen after an
+	 * unclean shutdown near ENOSPC while GC was ongoing.
+	 *
+	 * We also need to do this for the first gc zone allocation if we
+	 * unmounted while at the open limit.
+	 */
+	if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_FREE) ||
+	    zi->zi_nr_open_zones == mp->m_max_open_zones)
+		oz = xfs_zone_gc_steal_open(zi);
+	else
+		oz = xfs_open_zone(mp, WRITE_LIFE_NOT_SET, true);
+	if (!oz) {
+		xfs_warn(mp, "unable to allocate a zone for gc");
+		error = -EIO;
+		goto out;
+	}
+
+	trace_xfs_zone_gc_target_opened(oz->oz_rtg);
+	zi->zi_open_gc_zone = oz;
+
+	data = xfs_zone_gc_data_alloc(mp);
+	if (!data) {
+		error = -ENOMEM;
+		goto out_put_gc_zone;
+	}
+
+	mp->m_zone_info->zi_gc_thread = kthread_create(xfs_zoned_gcd, data,
+			"xfs-zone-gc/%s", mp->m_super->s_id);
+	if (IS_ERR(mp->m_zone_info->zi_gc_thread)) {
+		xfs_warn(mp, "unable to create zone gc thread");
+		error = PTR_ERR(mp->m_zone_info->zi_gc_thread);
+		goto out_free_gc_data;
+	}
+
+	/* xfs_zone_gc_start will unpark for rw mounts */
+	kthread_park(mp->m_zone_info->zi_gc_thread);
+	return 0;
+
+out_free_gc_data:
+	kfree(data);
+out_put_gc_zone:
+	xfs_open_zone_put(zi->zi_open_gc_zone);
+out:
+	return error;
+}
+
+void
+xfs_zone_gc_unmount(
+	struct xfs_mount	*mp)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+
+	kthread_stop(zi->zi_gc_thread);
+	if (zi->zi_open_gc_zone)
+		xfs_open_zone_put(zi->zi_open_gc_zone);
+}

fs/xfs/xfs_zone_info.c

···
+// 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_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_zone_priv.h"
+
+static const char xfs_write_hint_shorthand[6][16] = {
+	"NOT_SET", "NONE", "SHORT", "MEDIUM", "LONG", "EXTREME"};
+
+static inline const char *
+xfs_write_hint_to_str(
+	uint8_t			write_hint)
+{
+	if (write_hint > WRITE_LIFE_EXTREME)
+		return "UNKNOWN";
+	return xfs_write_hint_shorthand[write_hint];
+}
+
+static void
+xfs_show_open_zone(
+	struct seq_file		*m,
+	struct xfs_open_zone	*oz)
+{
+	seq_printf(m, "\t  zone %d, wp %u, written %u, used %u, hint %s\n",
+		rtg_rgno(oz->oz_rtg),
+		oz->oz_write_pointer, oz->oz_written,
+		rtg_rmap(oz->oz_rtg)->i_used_blocks,
+		xfs_write_hint_to_str(oz->oz_write_hint));
+}
+
+static void
+xfs_show_full_zone_used_distribution(
+	struct seq_file         *m,
+	struct xfs_mount        *mp)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	unsigned int		reclaimable = 0, full, i;
+
+	spin_lock(&zi->zi_used_buckets_lock);
+	for (i = 0; i < XFS_ZONE_USED_BUCKETS; i++) {
+		unsigned int entries = zi->zi_used_bucket_entries[i];
+
+		seq_printf(m, "\t  %2u..%2u%%: %u\n",
+				i * (100 / XFS_ZONE_USED_BUCKETS),
+				(i + 1) * (100 / XFS_ZONE_USED_BUCKETS) - 1,
+				entries);
+		reclaimable += entries;
+	}
+	spin_unlock(&zi->zi_used_buckets_lock);
+
+	full = mp->m_sb.sb_rgcount;
+	if (zi->zi_open_gc_zone)
+		full--;
+	full -= zi->zi_nr_open_zones;
+	full -= atomic_read(&zi->zi_nr_free_zones);
+	full -= reclaimable;
+
+	seq_printf(m, "\t     100%%: %u\n", full);
+}
+
+void
+xfs_zoned_show_stats(
+	struct seq_file		*m,
+	struct xfs_mount	*mp)
+{
+	struct xfs_zone_info	*zi = mp->m_zone_info;
+	struct xfs_open_zone	*oz;
+
+	seq_puts(m, "\n");
+
+	seq_printf(m, "\tuser free RT blocks: %lld\n",
+		xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS));
+	seq_printf(m, "\treserved free RT blocks: %lld\n",
+		mp->m_free[XC_FREE_RTEXTENTS].res_avail);
+	seq_printf(m, "\tuser available RT blocks: %lld\n",
+		xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE));
+	seq_printf(m, "\treserved available RT blocks: %lld\n",
+		mp->m_free[XC_FREE_RTAVAILABLE].res_avail);
+	seq_printf(m, "\tRT reservations required: %d\n",
+		!list_empty_careful(&zi->zi_reclaim_reservations));
+	seq_printf(m, "\tRT GC required: %d\n",
+		xfs_zoned_need_gc(mp));
+
+	seq_printf(m, "\tfree zones: %d\n", atomic_read(&zi->zi_nr_free_zones));
+	seq_puts(m, "\topen zones:\n");
+	spin_lock(&zi->zi_open_zones_lock);
+	list_for_each_entry(oz, &zi->zi_open_zones, oz_entry)
+		xfs_show_open_zone(m, oz);
+	if (zi->zi_open_gc_zone) {
+		seq_puts(m, "\topen gc zone:\n");
+		xfs_show_open_zone(m, zi->zi_open_gc_zone);
+	}
+	spin_unlock(&zi->zi_open_zones_lock);
+	seq_puts(m, "\tused blocks distribution (fully written zones):\n");
+	xfs_show_full_zone_used_distribution(m, mp);
+}

fs/xfs/xfs_zone_priv.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _XFS_ZONE_PRIV_H
+#define _XFS_ZONE_PRIV_H
+
+struct xfs_open_zone {
+	/*
+	 * Entry in the open zone list and refcount.  Protected by
+	 * zi_open_zones_lock in struct xfs_zone_info.
+	 */
+	struct list_head	oz_entry;
+	atomic_t		oz_ref;
+
+	/*
+	 * oz_write_pointer is the write pointer at which space is handed out
+	 * for conventional zones, or simple the count of blocks handed out
+	 * so far for sequential write required zones and is protected by
+	 * oz_alloc_lock/
+	 */
+	spinlock_t		oz_alloc_lock;
+	xfs_rgblock_t		oz_write_pointer;
+
+	/*
+	 * oz_written is the number of blocks for which we've received a
+	 * write completion.  oz_written must always be <= oz_write_pointer
+	 * and is protected by the ILOCK of the rmap inode.
+	 */
+	xfs_rgblock_t		oz_written;
+
+	/*
+	 * Write hint (data temperature) assigned to this zone, or
+	 * WRITE_LIFE_NOT_SET if none was set.
+	 */
+	enum rw_hint		oz_write_hint;
+
+	/*
+	 * Is this open zone used for garbage collection?  There can only be a
+	 * single open GC zone, which is pointed to by zi_open_gc_zone in
+	 * struct xfs_zone_info.  Constant over the life time of an open zone.
+	 */
+	bool			oz_is_gc;
+
+	/*
+	 * Pointer to the RT groups structure for this open zone.  Constant over
+	 * the life time of an open zone.
+	 */
+	struct xfs_rtgroup	*oz_rtg;
+};
+
+/*
+ * Number of bitmap buckets to track reclaimable zones.  There are 10 buckets
+ * so that each 10% of the usable capacity get their own bucket and GC can
+ * only has to walk the bitmaps of the lesser used zones if there are any.
+ */
+#define XFS_ZONE_USED_BUCKETS		10u
+
+struct xfs_zone_info {
+	/*
+	 * List of pending space reservations:
+	 */
+	spinlock_t		zi_reservation_lock;
+	struct list_head	zi_reclaim_reservations;
+
+	/*
+	 * List and number of open zones:
+	 */
+	spinlock_t		zi_open_zones_lock;
+	struct list_head	zi_open_zones;
+	unsigned int		zi_nr_open_zones;
+
+	/*
+	 * Free zone search cursor and number of free zones:
+	 */
+	unsigned long		zi_free_zone_cursor;
+	atomic_t		zi_nr_free_zones;
+
+	/*
+	 * Wait queue to wait for free zones or open zone resources to become
+	 * available:
+	 */
+	wait_queue_head_t	zi_zone_wait;
+
+	/*
+	 * Pointer to the GC thread, and the current open zone used by GC
+	 * (if any).
+	 *
+	 * zi_open_gc_zone is mostly private to the GC thread, but can be read
+	 * for debugging from other threads, in which case zi_open_zones_lock
+	 * must be taken to access it.
+	 */
+	struct task_struct      *zi_gc_thread;
+	struct xfs_open_zone	*zi_open_gc_zone;
+
+	/*
+	 * List of zones that need a reset:
+	 */
+	spinlock_t		zi_reset_list_lock;
+	struct xfs_group	*zi_reset_list;
+
+	/*
+	 * A set of bitmaps to bucket-sort reclaimable zones by used blocks to help
+	 * garbage collection to quickly find the best candidate for reclaim.
+	 */
+	spinlock_t		zi_used_buckets_lock;
+	unsigned int		zi_used_bucket_entries[XFS_ZONE_USED_BUCKETS];
+	unsigned long		*zi_used_bucket_bitmap[XFS_ZONE_USED_BUCKETS];
+
+};
+
+struct xfs_open_zone *xfs_open_zone(struct xfs_mount *mp,
+		enum rw_hint write_hint, bool is_gc);
+
+int xfs_zone_gc_reset_sync(struct xfs_rtgroup *rtg);
+bool xfs_zoned_need_gc(struct xfs_mount *mp);
+int xfs_zone_gc_mount(struct xfs_mount *mp);
+void xfs_zone_gc_unmount(struct xfs_mount *mp);
+
+void xfs_zoned_resv_wake_all(struct xfs_mount *mp);
+
+#endif /* _XFS_ZONE_PRIV_H */

fs/xfs/xfs_zone_space_resv.c

···
+// 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_shared.h"
+#include "xfs_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_rtbitmap.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_zone_priv.h"
+#include "xfs_zones.h"
+
+/*
+ * Note: the zoned allocator does not support a rtextsize > 1, so this code and
+ * the allocator itself uses file system blocks interchangeable with realtime
+ * extents without doing the otherwise required conversions.
+ */
+
+/*
+ * Per-task space reservation.
+ *
+ * Tasks that need to wait for GC to free up space allocate one of these
+ * on-stack and adds it to the per-mount zi_reclaim_reservations lists.
+ * The GC thread will then wake the tasks in order when space becomes available.
+ */
+struct xfs_zone_reservation {
+	struct list_head	entry;
+	struct task_struct	*task;
+	xfs_filblks_t		count_fsb;
+};
+
+/*
+ * Calculate the number of reserved blocks.
+ *
+ * XC_FREE_RTEXTENTS counts the user available capacity, to which the file
+ * system can be filled, while XC_FREE_RTAVAILABLE counts the blocks instantly
+ * available for writes without waiting for GC.
+ *
+ * For XC_FREE_RTAVAILABLE only the smaller reservation required for GC and
+ * block zeroing is excluded from the user capacity, while XC_FREE_RTEXTENTS
+ * is further restricted by at least one zone as well as the optional
+ * persistently reserved blocks.  This allows the allocator to run more
+ * smoothly by not always triggering GC.
+ */
+uint64_t
+xfs_zoned_default_resblks(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr)
+{
+	switch (ctr) {
+	case XC_FREE_RTEXTENTS:
+		return (uint64_t)XFS_RESERVED_ZONES *
+			mp->m_groups[XG_TYPE_RTG].blocks +
+			mp->m_sb.sb_rtreserved;
+	case XC_FREE_RTAVAILABLE:
+		return (uint64_t)XFS_GC_ZONES *
+			mp->m_groups[XG_TYPE_RTG].blocks;
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
+void
+xfs_zoned_resv_wake_all(
+	struct xfs_mount		*mp)
+{
+	struct xfs_zone_info		*zi = mp->m_zone_info;
+	struct xfs_zone_reservation	*reservation;
+
+	spin_lock(&zi->zi_reservation_lock);
+	list_for_each_entry(reservation, &zi->zi_reclaim_reservations, entry)
+		wake_up_process(reservation->task);
+	spin_unlock(&zi->zi_reservation_lock);
+}
+
+void
+xfs_zoned_add_available(
+	struct xfs_mount		*mp,
+	xfs_filblks_t			count_fsb)
+{
+	struct xfs_zone_info		*zi = mp->m_zone_info;
+	struct xfs_zone_reservation	*reservation;
+
+	if (list_empty_careful(&zi->zi_reclaim_reservations)) {
+		xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb);
+		return;
+	}
+
+	spin_lock(&zi->zi_reservation_lock);
+	xfs_add_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb);
+	count_fsb = xfs_sum_freecounter(mp, XC_FREE_RTAVAILABLE);
+	list_for_each_entry(reservation, &zi->zi_reclaim_reservations, entry) {
+		if (reservation->count_fsb > count_fsb)
+			break;
+		wake_up_process(reservation->task);
+		count_fsb -= reservation->count_fsb;
+
+	}
+	spin_unlock(&zi->zi_reservation_lock);
+}
+
+static int
+xfs_zoned_space_wait_error(
+	struct xfs_mount		*mp)
+{
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+	if (fatal_signal_pending(current))
+		return -EINTR;
+	return 0;
+}
+
+static int
+xfs_zoned_reserve_available(
+	struct xfs_inode		*ip,
+	xfs_filblks_t			count_fsb,
+	unsigned int			flags)
+{
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_zone_info		*zi = mp->m_zone_info;
+	struct xfs_zone_reservation	reservation = {
+		.task		= current,
+		.count_fsb	= count_fsb,
+	};
+	int				error;
+
+	/*
+	 * If there are no waiters, try to directly grab the available blocks
+	 * from the percpu counter.
+	 *
+	 * If the caller wants to dip into the reserved pool also bypass the
+	 * wait list.  This relies on the fact that we have a very graciously
+	 * sized reserved pool that always has enough space.  If the reserved
+	 * allocations fail we're in trouble.
+	 */
+	if (likely(list_empty_careful(&zi->zi_reclaim_reservations) ||
+	    (flags & XFS_ZR_RESERVED))) {
+		error = xfs_dec_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb,
+				flags & XFS_ZR_RESERVED);
+		if (error != -ENOSPC)
+			return error;
+	}
+
+	if (flags & XFS_ZR_NOWAIT)
+		return -EAGAIN;
+
+	spin_lock(&zi->zi_reservation_lock);
+	list_add_tail(&reservation.entry, &zi->zi_reclaim_reservations);
+	while ((error = xfs_zoned_space_wait_error(mp)) == 0) {
+		set_current_state(TASK_KILLABLE);
+
+		error = xfs_dec_freecounter(mp, XC_FREE_RTAVAILABLE, count_fsb,
+				flags & XFS_ZR_RESERVED);
+		if (error != -ENOSPC)
+			break;
+
+		/*
+		 * Make sure to start GC if it is not running already. As we
+		 * check the rtavailable count when filling up zones, GC is
+		 * normally already running at this point, but in some setups
+		 * with very few zones we may completely run out of non-
+		 * reserved blocks in between filling zones.
+		 */
+		if (!xfs_is_zonegc_running(mp))
+			wake_up_process(zi->zi_gc_thread);
+
+		/*
+		 * If there is no reclaimable group left and we aren't still
+		 * processing a pending GC request give up as we're fully out
+		 * of space.
+		 */
+		if (!xfs_group_marked(mp, XG_TYPE_RTG, XFS_RTG_RECLAIMABLE) &&
+		    !xfs_is_zonegc_running(mp))
+			break;
+
+		spin_unlock(&zi->zi_reservation_lock);
+		schedule();
+		spin_lock(&zi->zi_reservation_lock);
+	}
+	list_del(&reservation.entry);
+	spin_unlock(&zi->zi_reservation_lock);
+
+	__set_current_state(TASK_RUNNING);
+	return error;
+}
+
+/*
+ * Implement greedy space allocation for short writes by trying to grab all
+ * that is left after locking out other threads from trying to do the same.
+ *
+ * This isn't exactly optimal and can hopefully be replaced by a proper
+ * percpu_counter primitive one day.
+ */
+static int
+xfs_zoned_reserve_extents_greedy(
+	struct xfs_inode		*ip,
+	xfs_filblks_t			*count_fsb,
+	unsigned int			flags)
+{
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_zone_info		*zi = mp->m_zone_info;
+	s64				len = *count_fsb;
+	int				error = -ENOSPC;
+
+	spin_lock(&zi->zi_reservation_lock);
+	len = min(len, xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS));
+	if (len > 0) {
+		*count_fsb = len;
+		error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, *count_fsb,
+				flags & XFS_ZR_RESERVED);
+	}
+	spin_unlock(&zi->zi_reservation_lock);
+	return error;
+}
+
+int
+xfs_zoned_space_reserve(
+	struct xfs_inode		*ip,
+	xfs_filblks_t			count_fsb,
+	unsigned int			flags,
+	struct xfs_zone_alloc_ctx	*ac)
+{
+	struct xfs_mount		*mp = ip->i_mount;
+	int				error;
+
+	ASSERT(ac->reserved_blocks == 0);
+	ASSERT(ac->open_zone == NULL);
+
+	error = xfs_dec_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb,
+			flags & XFS_ZR_RESERVED);
+	if (error == -ENOSPC && (flags & XFS_ZR_GREEDY) && count_fsb > 1)
+		error = xfs_zoned_reserve_extents_greedy(ip, &count_fsb, flags);
+	if (error)
+		return error;
+
+	error = xfs_zoned_reserve_available(ip, count_fsb, flags);
+	if (error) {
+		xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, count_fsb);
+		return error;
+	}
+	ac->reserved_blocks = count_fsb;
+	return 0;
+}
+
+void
+xfs_zoned_space_unreserve(
+	struct xfs_inode		*ip,
+	struct xfs_zone_alloc_ctx	*ac)
+{
+	if (ac->reserved_blocks > 0) {
+		struct xfs_mount	*mp = ip->i_mount;
+
+		xfs_zoned_add_available(mp, ac->reserved_blocks);
+		xfs_add_freecounter(mp, XC_FREE_RTEXTENTS, ac->reserved_blocks);
+	}
+	if (ac->open_zone)
+		xfs_open_zone_put(ac->open_zone);
+}