Merge branch 'xfs-6.15-merge' into for-next

XFS code for 6.15 to be merged into linux-next

Signed-off-by: Carlos Maiolino <cem@kernel.org>

92 files changed, 6397 insertions, 1393 deletions

diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst
index b0d0188a095e..e29651a42eec 100644
--- a/Documentation/filesystems/iomap/design.rst
+++ b/Documentation/filesystems/iomap/design.rst
@@ -246,6 +246,10 @@ The fields are as follows:
    * **IOMAP_F_PRIVATE**: Starting with this value, the upper bits can
      be set by the filesystem for its own purposes.
 
+   * **IOMAP_F_ANON_WRITE**: Indicates that (write) I/O does not have a target
+     block assigned to it yet and the file system will do that in the bio
+     submission handler, splitting the I/O as needed.
+
    These flags can be set by iomap itself during file operations.
    The filesystem should supply an ``->iomap_end`` function if it needs
    to observe these flags:
@@ -352,6 +356,11 @@ operations:
    ``IOMAP_NOWAIT`` is often set on behalf of ``IOCB_NOWAIT`` or
    ``RWF_NOWAIT``.
 
+ * ``IOMAP_DONTCACHE`` is set when the caller wishes to perform a
+   buffered file I/O and would like the kernel to drop the pagecache
+   after the I/O completes, if it isn't already being used by another
+   thread.
+
 If it is necessary to read existing file contents from a `different
 <https://lore.kernel.org/all/20191008071527.29304-9-hch@lst.de/>`_
 device or address range on a device, the filesystem should return that
diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index 2c7f5df9d8b0..b08a79d11d9f 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -131,6 +131,8 @@ These ``struct kiocb`` flags are significant for buffered I/O with iomap:
 
  * ``IOCB_NOWAIT``: Turns on ``IOMAP_NOWAIT``.
 
+ * ``IOCB_DONTCACHE``: Turns on ``IOMAP_DONTCACHE``.
+
 Internal per-Folio State
 ------------------------
 
@@ -283,7 +285,7 @@ The ``ops`` structure must be specified and is as follows:
  struct iomap_writeback_ops {
      int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
                        loff_t offset, unsigned len);
-     int (*prepare_ioend)(struct iomap_ioend *ioend, int status);
+     int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
      void (*discard_folio)(struct folio *folio, loff_t pos);
  };
 
@@ -306,13 +308,12 @@ The fields are as follows:
     purpose.
     This function must be supplied by the filesystem.
 
-  - ``prepare_ioend``: Enables filesystems to transform the writeback
-    ioend or perform any other preparatory work before the writeback I/O
-    is submitted.
+  - ``submit_ioend``: Allows the file systems to hook into writeback bio
+    submission.
     This might include pre-write space accounting updates, or installing
     a custom ``->bi_end_io`` function for internal purposes, such as
     deferring the ioend completion to a workqueue to run metadata update
-    transactions from process context.
+    transactions from process context before submitting the bio.
     This function is optional.
 
   - ``discard_folio``: iomap calls this function after ``->map_blocks``
@@ -341,7 +342,7 @@ This can happen in interrupt or process context, depending on the
 storage device.
 
 Filesystems that need to update internal bookkeeping (e.g. unwritten
-extent conversions) should provide a ``->prepare_ioend`` function to
+extent conversions) should provide a ``->submit_ioend`` function to
 set ``struct iomap_end::bio::bi_end_io`` to its own function.
 This function should call ``iomap_finish_ioends`` after finishing its
 own work (e.g. unwritten extent conversion).
@@ -513,8 +514,8 @@ IOMAP_WRITE`` with any combination of the following enhancements:
    if the mapping is unwritten and the filesystem cannot handle zeroing
    the unaligned regions without exposing stale contents.
 
- * ``IOMAP_ATOMIC``: This write is being issued with torn-write
-   protection.
+ * ``IOMAP_ATOMIC_HW``: This write is being issued with torn-write
+   protection based on HW-offload support.
    Only a single bio can be created for the write, and the write must
    not be split into multiple I/O requests, i.e. flag REQ_ATOMIC must be
    set.
@@ -525,8 +526,20 @@ IOMAP_WRITE`` with any combination of the following enhancements:
    conversion or copy on write), all updates for the entire file range
    must be committed atomically as well.
    Only one space mapping is allowed per untorn write.
-   Untorn writes must be aligned to, and must not be longer than, a
-   single file block.
+   Untorn writes may be longer than a single file block. In all cases,
+   the mapping start disk block must have at least the same alignment as
+   the write offset.
+
+ * ``IOMAP_ATOMIC_SW``: This write is being issued with torn-write
+   protection via a software mechanism provided by the filesystem.
+   All the disk block alignment and single bio restrictions which apply
+   to IOMAP_ATOMIC_HW do not apply here.
+   SW-based untorn writes would typically be used as a fallback when
+   HW-based untorn writes may not be issued, e.g. the range of the write
+   covers multiple extents, meaning that it is not possible to issue
+   a single bio.
+   All filesystem metadata updates for the entire file range must be
+   committed atomically as well.
 
 Callers commonly hold ``i_rwsem`` in shared or exclusive mode before
 calling this function.
diff --git a/fs/dax.c b/fs/dax.c
index 21b47402b3dc..7fd4cd9a51f2 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1258,7 +1258,7 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 }
 #endif /* CONFIG_FS_DAX_PMD */
 
-static s64 dax_unshare_iter(struct iomap_iter *iter)
+static int dax_unshare_iter(struct iomap_iter *iter)
 {
 	struct iomap *iomap = &iter->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
@@ -1266,11 +1266,11 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 	u64 copy_len = iomap_length(iter);
 	u32 mod;
 	int id = 0;
-	s64 ret = 0;
+	s64 ret;
 	void *daddr = NULL, *saddr = NULL;
 
 	if (!iomap_want_unshare_iter(iter))
-		return iomap_length(iter);
+		return iomap_iter_advance_full(iter);
 
 	/*
 	 * Extend the file range to be aligned to fsblock/pagesize, because
@@ -1300,14 +1300,14 @@ static s64 dax_unshare_iter(struct iomap_iter *iter)
 	if (ret < 0)
 		goto out_unlock;
 
-	if (copy_mc_to_kernel(daddr, saddr, copy_len) == 0)
-		ret = iomap_length(iter);
-	else
+	if (copy_mc_to_kernel(daddr, saddr, copy_len) != 0)
 		ret = -EIO;
 
 out_unlock:
 	dax_read_unlock(id);
-	return dax_mem2blk_err(ret);
+	if (ret < 0)
+		return dax_mem2blk_err(ret);
+	return iomap_iter_advance_full(iter);
 }
 
 int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
@@ -1326,7 +1326,7 @@ int dax_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 
 	iter.len = min(len, size - pos);
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = dax_unshare_iter(&iter);
+		iter.status = dax_unshare_iter(&iter);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dax_file_unshare);
@@ -1354,17 +1354,16 @@ static int dax_memzero(struct iomap_iter *iter, loff_t pos, size_t size)
 	return ret;
 }
 
-static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
+static int dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
 {
 	const struct iomap *iomap = &iter->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
-	loff_t pos = iter->pos;
 	u64 length = iomap_length(iter);
-	s64 written = 0;
+	int ret;
 
 	/* already zeroed?  we're done. */
 	if (srcmap->type == IOMAP_HOLE || srcmap->type == IOMAP_UNWRITTEN)
-		return length;
+		return iomap_iter_advance(iter, &length);
 
 	/*
 	 * invalidate the pages whose sharing state is to be changed
@@ -1372,33 +1371,35 @@ static s64 dax_zero_iter(struct iomap_iter *iter, bool *did_zero)
 	 */
 	if (iomap->flags & IOMAP_F_SHARED)
 		invalidate_inode_pages2_range(iter->inode->i_mapping,
-					      pos >> PAGE_SHIFT,
-					      (pos + length - 1) >> PAGE_SHIFT);
+				iter->pos >> PAGE_SHIFT,
+				(iter->pos + length - 1) >> PAGE_SHIFT);
 
 	do {
+		loff_t pos = iter->pos;
 		unsigned offset = offset_in_page(pos);
-		unsigned size = min_t(u64, PAGE_SIZE - offset, length);
 		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
-		long rc;
 		int id;
 
+		length = min_t(u64, PAGE_SIZE - offset, length);
+
 		id = dax_read_lock();
-		if (IS_ALIGNED(pos, PAGE_SIZE) && size == PAGE_SIZE)
-			rc = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
+		if (IS_ALIGNED(pos, PAGE_SIZE) && length == PAGE_SIZE)
+			ret = dax_zero_page_range(iomap->dax_dev, pgoff, 1);
 		else
-			rc = dax_memzero(iter, pos, size);
+			ret = dax_memzero(iter, pos, length);
 		dax_read_unlock(id);
 
-		if (rc < 0)
-			return rc;
-		pos += size;
-		length -= size;
-		written += size;
+		if (ret < 0)
+			return ret;
+
+		ret = iomap_iter_advance(iter, &length);
+		if (ret)
+			return ret;
 	} while (length > 0);
 
 	if (did_zero)
 		*did_zero = true;
-	return written;
+	return ret;
 }
 
 int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
@@ -1413,7 +1414,7 @@ int dax_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 	int ret;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = dax_zero_iter(&iter, did_zero);
+		iter.status = dax_zero_iter(&iter, did_zero);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dax_zero_range);
@@ -1431,8 +1432,7 @@ int dax_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 }
 EXPORT_SYMBOL_GPL(dax_truncate_page);
 
-static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
-		struct iov_iter *iter)
+static int dax_iomap_iter(struct iomap_iter *iomi, struct iov_iter *iter)
 {
 	const struct iomap *iomap = &iomi->iomap;
 	const struct iomap *srcmap = iomap_iter_srcmap(iomi);
@@ -1451,8 +1451,10 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 		if (pos >= end)
 			return 0;
 
-		if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN)
-			return iov_iter_zero(min(length, end - pos), iter);
+		if (iomap->type == IOMAP_HOLE || iomap->type == IOMAP_UNWRITTEN) {
+			done = iov_iter_zero(min(length, end - pos), iter);
+			return iomap_iter_advance(iomi, &done);
+		}
 	}
 
 	/*
@@ -1485,7 +1487,7 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 	}
 
 	id = dax_read_lock();
-	while (pos < end) {
+	while ((pos = iomi->pos) < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
 		const size_t size = ALIGN(length + offset, PAGE_SIZE);
 		pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
@@ -1535,18 +1537,16 @@ static loff_t dax_iomap_iter(const struct iomap_iter *iomi,
 			xfer = dax_copy_to_iter(dax_dev, pgoff, kaddr,
 					map_len, iter);
 
-		pos += xfer;
-		length -= xfer;
-		done += xfer;
-
-		if (xfer == 0)
+		length = xfer;
+		ret = iomap_iter_advance(iomi, &length);
+		if (!ret && xfer == 0)
 			ret = -EFAULT;
 		if (xfer < map_len)
 			break;
 	}
 	dax_read_unlock(id);
 
-	return done ? done : ret;
+	return ret;
 }
 
 /**
@@ -1586,7 +1586,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		iomi.flags |= IOMAP_NOWAIT;
 
 	while ((ret = iomap_iter(&iomi, ops)) > 0)
-		iomi.processed = dax_iomap_iter(&iomi, iter);
+		iomi.status = dax_iomap_iter(&iomi, iter);
 
 	done = iomi.pos - iocb->ki_pos;
 	iocb->ki_pos = iomi.pos;
@@ -1757,7 +1757,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 
 	while ((error = iomap_iter(&iter, ops)) > 0) {
 		if (WARN_ON_ONCE(iomap_length(&iter) < PAGE_SIZE)) {
-			iter.processed = -EIO;	/* fs corruption? */
+			iter.status = -EIO;	/* fs corruption? */
 			continue;
 		}
 
@@ -1769,8 +1769,10 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			ret |= VM_FAULT_MAJOR;
 		}
 
-		if (!(ret & VM_FAULT_ERROR))
-			iter.processed = PAGE_SIZE;
+		if (!(ret & VM_FAULT_ERROR)) {
+			u64 length = PAGE_SIZE;
+			iter.status = iomap_iter_advance(&iter, &length);
+		}
 	}
 
 	if (iomap_errp)
@@ -1883,8 +1885,10 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 			continue; /* actually breaks out of the loop */
 
 		ret = dax_fault_iter(vmf, &iter, pfnp, &xas, &entry, true);
-		if (ret != VM_FAULT_FALLBACK)
-			iter.processed = PMD_SIZE;
+		if (ret != VM_FAULT_FALLBACK) {
+			u64 length = PMD_SIZE;
+			iter.status = iomap_iter_advance(&iter, &length);
+		}
 	}
 
 unlock_entry:
@@ -1999,12 +2003,13 @@ vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order,
 }
 EXPORT_SYMBOL_GPL(dax_finish_sync_fault);
 
-static loff_t dax_range_compare_iter(struct iomap_iter *it_src,
+static int dax_range_compare_iter(struct iomap_iter *it_src,
 		struct iomap_iter *it_dest, u64 len, bool *same)
 {
 	const struct iomap *smap = &it_src->iomap;
 	const struct iomap *dmap = &it_dest->iomap;
 	loff_t pos1 = it_src->pos, pos2 = it_dest->pos;
+	u64 dest_len;
 	void *saddr, *daddr;
 	int id, ret;
 
@@ -2012,7 +2017,7 @@ static loff_t dax_range_compare_iter(struct iomap_iter *it_src,
 
 	if (smap->type == IOMAP_HOLE && dmap->type == IOMAP_HOLE) {
 		*same = true;
-		return len;
+		goto advance;
 	}
 
 	if (smap->type == IOMAP_HOLE || dmap->type == IOMAP_HOLE) {
@@ -2035,7 +2040,13 @@ static loff_t dax_range_compare_iter(struct iomap_iter *it_src,
 	if (!*same)
 		len = 0;
 	dax_read_unlock(id);
-	return len;
+
+advance:
+	dest_len = len;
+	ret = iomap_iter_advance(it_src, &len);
+	if (!ret)
+		ret = iomap_iter_advance(it_dest, &dest_len);
+	return ret;
 
 out_unlock:
 	dax_read_unlock(id);
@@ -2058,15 +2069,15 @@ int dax_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
 		.len		= len,
 		.flags		= IOMAP_DAX,
 	};
-	int ret, compared = 0;
+	int ret, status;
 
 	while ((ret = iomap_iter(&src_iter, ops)) > 0 &&
 	       (ret = iomap_iter(&dst_iter, ops)) > 0) {
-		compared = dax_range_compare_iter(&src_iter, &dst_iter,
+		status = dax_range_compare_iter(&src_iter, &dst_iter,
 				min(src_iter.len, dst_iter.len), same);
-		if (compared < 0)
+		if (status < 0)
 			return ret;
-		src_iter.processed = dst_iter.processed = compared;
+		src_iter.status = dst_iter.status = status;
 	}
 	return ret;
 }
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 7c54ae5fcbd4..ba2f1e3db7c7 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -3467,7 +3467,7 @@ static inline bool ext4_want_directio_fallback(unsigned flags, ssize_t written)
 		return false;
 
 	/* atomic writes are all-or-nothing */
-	if (flags & IOMAP_ATOMIC)
+	if (flags & IOMAP_ATOMIC_HW)
 		return false;
 
 	/* can only try again if we wrote nothing */
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 1795c4e8dbf6..366516b98b3f 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -1300,7 +1300,8 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from,
 				 unsigned int length)
 {
 	BUG_ON(current->journal_info);
-	return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops);
+	return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops,
+			NULL);
 }
 
 #define GFS2_JTRUNC_REVOKES 8192
diff --git a/fs/iomap/Makefile b/fs/iomap/Makefile
index 381d76c5c232..69e8ebb41302 100644
--- a/fs/iomap/Makefile
+++ b/fs/iomap/Makefile
@@ -12,6 +12,7 @@ iomap-y				+= trace.o \
 				   iter.o
 iomap-$(CONFIG_BLOCK)		+= buffered-io.o \
 				   direct-io.o \
+				   ioend.o \
 				   fiemap.o \
 				   seek.o
 iomap-$(CONFIG_SWAP)		+= swapfile.o
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index d303e6c8900c..d52cfdc299c4 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -12,17 +12,15 @@
 #include <linux/buffer_head.h>
 #include <linux/dax.h>
 #include <linux/writeback.h>
-#include <linux/list_sort.h>
 #include <linux/swap.h>
 #include <linux/bio.h>
 #include <linux/sched/signal.h>
 #include <linux/migrate.h>
+#include "internal.h"
 #include "trace.h"
 
 #include "../internal.h"
 
-#define IOEND_BATCH_SIZE	4096
-
 /*
  * Structure allocated for each folio to track per-block uptodate, dirty state
  * and I/O completions.
@@ -40,8 +38,6 @@ struct iomap_folio_state {
 	unsigned long		state[];
 };
 
-static struct bio_set iomap_ioend_bioset;
-
 static inline bool ifs_is_fully_uptodate(struct folio *folio,
 		struct iomap_folio_state *ifs)
 {
@@ -366,15 +362,14 @@ static inline bool iomap_block_needs_zeroing(const struct iomap_iter *iter,
 		pos >= i_size_read(iter->inode);
 }
 
-static loff_t iomap_readpage_iter(const struct iomap_iter *iter,
-		struct iomap_readpage_ctx *ctx, loff_t offset)
+static int iomap_readpage_iter(struct iomap_iter *iter,
+		struct iomap_readpage_ctx *ctx)
 {
 	const struct iomap *iomap = &iter->iomap;
-	loff_t pos = iter->pos + offset;
-	loff_t length = iomap_length(iter) - offset;
+	loff_t pos = iter->pos;
+	loff_t length = iomap_length(iter);
 	struct folio *folio = ctx->cur_folio;
 	struct iomap_folio_state *ifs;
-	loff_t orig_pos = pos;
 	size_t poff, plen;
 	sector_t sector;
 
@@ -438,25 +433,22 @@ done:
 	 * we can skip trailing ones as they will be handled in the next
 	 * iteration.
 	 */
-	return pos - orig_pos + plen;
+	length = pos - iter->pos + plen;
+	return iomap_iter_advance(iter, &length);
 }
 
-static loff_t iomap_read_folio_iter(const struct iomap_iter *iter,
+static int iomap_read_folio_iter(struct iomap_iter *iter,
 		struct iomap_readpage_ctx *ctx)
 {
-	struct folio *folio = ctx->cur_folio;
-	size_t offset = offset_in_folio(folio, iter->pos);
-	loff_t length = min_t(loff_t, folio_size(folio) - offset,
-			      iomap_length(iter));
-	loff_t done, ret;
-
-	for (done = 0; done < length; done += ret) {
-		ret = iomap_readpage_iter(iter, ctx, done);
-		if (ret <= 0)
+	int ret;
+
+	while (iomap_length(iter)) {
+		ret = iomap_readpage_iter(iter, ctx);
+		if (ret)
 			return ret;
 	}
 
-	return done;
+	return 0;
 }
 
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
@@ -474,7 +466,7 @@ int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
 	trace_iomap_readpage(iter.inode, 1);
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_read_folio_iter(&iter, &ctx);
+		iter.status = iomap_read_folio_iter(&iter, &ctx);
 
 	if (ctx.bio) {
 		submit_bio(ctx.bio);
@@ -493,15 +485,14 @@ int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops)
 }
 EXPORT_SYMBOL_GPL(iomap_read_folio);
 
-static loff_t iomap_readahead_iter(const struct iomap_iter *iter,
+static int iomap_readahead_iter(struct iomap_iter *iter,
 		struct iomap_readpage_ctx *ctx)
 {
-	loff_t length = iomap_length(iter);
-	loff_t done, ret;
+	int ret;
 
-	for (done = 0; done < length; done += ret) {
+	while (iomap_length(iter)) {
 		if (ctx->cur_folio &&
-		    offset_in_folio(ctx->cur_folio, iter->pos + done) == 0) {
+		    offset_in_folio(ctx->cur_folio, iter->pos) == 0) {
 			if (!ctx->cur_folio_in_bio)
 				folio_unlock(ctx->cur_folio);
 			ctx->cur_folio = NULL;
@@ -510,12 +501,12 @@ static loff_t iomap_readahead_iter(const struct iomap_iter *iter,
 			ctx->cur_folio = readahead_folio(ctx->rac);
 			ctx->cur_folio_in_bio = false;
 		}
-		ret = iomap_readpage_iter(iter, ctx, done);
-		if (ret <= 0)
+		ret = iomap_readpage_iter(iter, ctx);
+		if (ret)
 			return ret;
 	}
 
-	return done;
+	return 0;
 }
 
 /**
@@ -547,7 +538,7 @@ void iomap_readahead(struct readahead_control *rac, const struct iomap_ops *ops)
 	trace_iomap_readahead(rac->mapping->host, readahead_count(rac));
 
 	while (iomap_iter(&iter, ops) > 0)
-		iter.processed = iomap_readahead_iter(&iter, &ctx);
+		iter.status = iomap_readahead_iter(&iter, &ctx);
 
 	if (ctx.bio)
 		submit_bio(ctx.bio);
@@ -603,6 +594,8 @@ struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len)
 
 	if (iter->flags & IOMAP_NOWAIT)
 		fgp |= FGP_NOWAIT;
+	if (iter->flags & IOMAP_DONTCACHE)
+		fgp |= FGP_DONTCACHE;
 	fgp |= fgf_set_order(len);
 
 	return __filemap_get_folio(iter->inode->i_mapping, pos >> PAGE_SHIFT,
@@ -907,12 +900,10 @@ static bool iomap_write_end(struct iomap_iter *iter, loff_t pos, size_t len,
 	return __iomap_write_end(iter->inode, pos, len, copied, folio);
 }
 
-static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
+static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 {
-	loff_t length = iomap_length(iter);
-	loff_t pos = iter->pos;
 	ssize_t total_written = 0;
-	long status = 0;
+	int status = 0;
 	struct address_space *mapping = iter->inode->i_mapping;
 	size_t chunk = mapping_max_folio_size(mapping);
 	unsigned int bdp_flags = (iter->flags & IOMAP_NOWAIT) ? BDP_ASYNC : 0;
@@ -923,7 +914,8 @@ static loff_t iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
 		size_t offset;		/* Offset into folio */
 		size_t bytes;		/* Bytes to write to folio */
 		size_t copied;		/* Bytes copied from user */
-		size_t written;		/* Bytes have been written */
+		u64 written;		/* Bytes have been written */
+		loff_t pos = iter->pos;
 
 		bytes = iov_iter_count(i);
 retry:
@@ -934,8 +926,8 @@ retry:
 		if (unlikely(status))
 			break;
 
-		if (bytes > length)
-			bytes = length;
+		if (bytes > iomap_length(iter))
+			bytes = iomap_length(iter);
 
 		/*
 		 * Bring in the user page that we'll copy from _first_.
@@ -1006,17 +998,12 @@ retry:
 				goto retry;
 			}
 		} else {
-			pos += written;
 			total_written += written;
-			length -= written;
+			iomap_iter_advance(iter, &written);
 		}
-	} while (iov_iter_count(i) && length);
+	} while (iov_iter_count(i) && iomap_length(iter));
 
-	if (status == -EAGAIN) {
-		iov_iter_revert(i, total_written);
-		return -EAGAIN;
-	}
-	return total_written ? total_written : status;
+	return total_written ? 0 : status;
 }
 
 ssize_t
@@ -1034,9 +1021,11 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		iter.flags |= IOMAP_NOWAIT;
+	if (iocb->ki_flags & IOCB_DONTCACHE)
+		iter.flags |= IOMAP_DONTCACHE;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_write_iter(&iter, i);
+		iter.status = iomap_write_iter(&iter, i);
 
 	if (unlikely(iter.pos == iocb->ki_pos))
 		return ret;
@@ -1270,23 +1259,22 @@ void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 }
 EXPORT_SYMBOL_GPL(iomap_write_delalloc_release);
 
-static loff_t iomap_unshare_iter(struct iomap_iter *iter)
+static int iomap_unshare_iter(struct iomap_iter *iter)
 {
 	struct iomap *iomap = &iter->iomap;
-	loff_t pos = iter->pos;
-	loff_t length = iomap_length(iter);
-	loff_t written = 0;
+	u64 bytes = iomap_length(iter);
+	int status;
 
 	if (!iomap_want_unshare_iter(iter))
-		return length;
+		return iomap_iter_advance(iter, &bytes);
 
 	do {
 		struct folio *folio;
-		int status;
 		size_t offset;
-		size_t bytes = min_t(u64, SIZE_MAX, length);
+		loff_t pos = iter->pos;
 		bool ret;
 
+		bytes = min_t(u64, SIZE_MAX, bytes);
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (unlikely(status))
 			return status;
@@ -1304,14 +1292,14 @@ static loff_t iomap_unshare_iter(struct iomap_iter *iter)
 
 		cond_resched();
 
-		pos += bytes;
-		written += bytes;
-		length -= bytes;
-
 		balance_dirty_pages_ratelimited(iter->inode->i_mapping);
-	} while (length > 0);
 
-	return written;
+		status = iomap_iter_advance(iter, &bytes);
+		if (status)
+			break;
+	} while (bytes > 0);
+
+	return status;
 }
 
 int
@@ -1331,7 +1319,7 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 
 	iter.len = min(len, size - pos);
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_unshare_iter(&iter);
+		iter.status = iomap_unshare_iter(&iter);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
@@ -1350,19 +1338,18 @@ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i)
 	return filemap_write_and_wait_range(mapping, i->pos, end);
 }
 
-static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
+static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 {
-	loff_t pos = iter->pos;
-	loff_t length = iomap_length(iter);
-	loff_t written = 0;
+	u64 bytes = iomap_length(iter);
+	int status;
 
 	do {
 		struct folio *folio;
-		int status;
 		size_t offset;
-		size_t bytes = min_t(u64, SIZE_MAX, length);
+		loff_t pos = iter->pos;
 		bool ret;
 
+		bytes = min_t(u64, SIZE_MAX, bytes);
 		status = iomap_write_begin(iter, pos, bytes, &folio);
 		if (status)
 			return status;
@@ -1383,25 +1370,26 @@ static loff_t iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
-		pos += bytes;
-		length -= bytes;
-		written += bytes;
-	} while (length > 0);
+		status = iomap_iter_advance(iter, &bytes);
+		if (status)
+			break;
+	} while (bytes > 0);
 
 	if (did_zero)
 		*did_zero = true;
-	return written;
+	return status;
 }
 
 int
 iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
-		const struct iomap_ops *ops)
+		const struct iomap_ops *ops, void *private)
 {
 	struct iomap_iter iter = {
 		.inode		= inode,
 		.pos		= pos,
 		.len		= len,
 		.flags		= IOMAP_ZERO,
+		.private	= private,
 	};
 	struct address_space *mapping = inode->i_mapping;
 	unsigned int blocksize = i_blocksize(inode);
@@ -1424,7 +1412,7 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 	    filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) {
 		iter.len = plen;
 		while ((ret = iomap_iter(&iter, ops)) > 0)
-			iter.processed = iomap_zero_iter(&iter, did_zero);
+			iter.status = iomap_zero_iter(&iter, did_zero);
 
 		iter.len = len - (iter.pos - pos);
 		if (ret || !iter.len)
@@ -1443,17 +1431,19 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 
 		if (srcmap->type == IOMAP_HOLE ||
 		    srcmap->type == IOMAP_UNWRITTEN) {
-			loff_t proc = iomap_length(&iter);
+			s64 status;
 
 			if (range_dirty) {
 				range_dirty = false;
-				proc = iomap_zero_iter_flush_and_stale(&iter);
+				status = iomap_zero_iter_flush_and_stale(&iter);
+			} else {
+				status = iomap_iter_advance_full(&iter);
 			}
-			iter.processed = proc;
+			iter.status = status;
 			continue;
 		}
 
-		iter.processed = iomap_zero_iter(&iter, did_zero);
+		iter.status = iomap_zero_iter(&iter, did_zero);
 	}
 	return ret;
 }
@@ -1461,7 +1451,7 @@ EXPORT_SYMBOL_GPL(iomap_zero_range);
 
 int
 iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops)
+		const struct iomap_ops *ops, void *private)
 {
 	unsigned int blocksize = i_blocksize(inode);
 	unsigned int off = pos & (blocksize - 1);
@@ -1469,11 +1459,12 @@ iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 	/* Block boundary? Nothing to do */
 	if (!off)
 		return 0;
-	return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops);
+	return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops,
+			private);
 }
 EXPORT_SYMBOL_GPL(iomap_truncate_page);
 
-static loff_t iomap_folio_mkwrite_iter(struct iomap_iter *iter,
+static int iomap_folio_mkwrite_iter(struct iomap_iter *iter,
 		struct folio *folio)
 {
 	loff_t length = iomap_length(iter);
@@ -1490,14 +1481,16 @@ static loff_t iomap_folio_mkwrite_iter(struct iomap_iter *iter,
 		folio_mark_dirty(folio);
 	}
 
-	return length;
+	return iomap_iter_advance(iter, &length);
 }
 
-vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
+		void *private)
 {
 	struct iomap_iter iter = {
 		.inode		= file_inode(vmf->vma->vm_file),
 		.flags		= IOMAP_WRITE | IOMAP_FAULT,
+		.private	= private,
 	};
 	struct folio *folio = page_folio(vmf->page);
 	ssize_t ret;
@@ -1509,7 +1502,7 @@ vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 	iter.pos = folio_pos(folio);
 	iter.len = ret;
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_folio_mkwrite_iter(&iter, folio);
+		iter.status = iomap_folio_mkwrite_iter(&iter, folio);
 
 	if (ret < 0)
 		goto out_unlock;
@@ -1538,16 +1531,15 @@ static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
  * state, release holds on bios, and finally free up memory.  Do not use the
  * ioend after this.
  */
-static u32
-iomap_finish_ioend(struct iomap_ioend *ioend, int error)
+u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
 {
 	struct inode *inode = ioend->io_inode;
 	struct bio *bio = &ioend->io_bio;
 	struct folio_iter fi;
 	u32 folio_count = 0;
 
-	if (error) {
-		mapping_set_error(inode->i_mapping, error);
+	if (ioend->io_error) {
+		mapping_set_error(inode->i_mapping, ioend->io_error);
 		if (!bio_flagged(bio, BIO_QUIET)) {
 			pr_err_ratelimited(
 "%s: writeback error on inode %lu, offset %lld, sector %llu",
@@ -1566,116 +1558,16 @@ iomap_finish_ioend(struct iomap_ioend *ioend, int error)
 	return folio_count;
 }
 
-/*
- * Ioend completion routine for merged bios. This can only be called from task
- * contexts as merged ioends can be of unbound length. Hence we have to break up
- * the writeback completions into manageable chunks to avoid long scheduler
- * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get
- * good batch processing throughput without creating adverse scheduler latency
- * conditions.
- */
-void
-iomap_finish_ioends(struct iomap_ioend *ioend, int error)
-{
-	struct list_head tmp;
-	u32 completions;
-
-	might_sleep();
-
-	list_replace_init(&ioend->io_list, &tmp);
-	completions = iomap_finish_ioend(ioend, error);
-
-	while (!list_empty(&tmp)) {
-		if (completions > IOEND_BATCH_SIZE * 8) {
-			cond_resched();
-			completions = 0;
-		}
-		ioend = list_first_entry(&tmp, struct iomap_ioend, io_list);
-		list_del_init(&ioend->io_list);
-		completions += iomap_finish_ioend(ioend, error);
-	}
-}
-EXPORT_SYMBOL_GPL(iomap_finish_ioends);
-
-/*
- * We can merge two adjacent ioends if they have the same set of work to do.
- */
-static bool
-iomap_ioend_can_merge(struct iomap_ioend *ioend, struct iomap_ioend *next)
-{
-	if (ioend->io_bio.bi_status != next->io_bio.bi_status)
-		return false;
-	if (next->io_flags & IOMAP_F_BOUNDARY)
-		return false;
-	if ((ioend->io_flags & IOMAP_F_SHARED) ^
-	    (next->io_flags & IOMAP_F_SHARED))
-		return false;
-	if ((ioend->io_type == IOMAP_UNWRITTEN) ^
-	    (next->io_type == IOMAP_UNWRITTEN))
-		return false;
-	if (ioend->io_offset + ioend->io_size != next->io_offset)
-		return false;
-	/*
-	 * Do not merge physically discontiguous ioends. The filesystem
-	 * completion functions will have to iterate the physical
-	 * discontiguities even if we merge the ioends at a logical level, so
-	 * we don't gain anything by merging physical discontiguities here.
-	 *
-	 * We cannot use bio->bi_iter.bi_sector here as it is modified during
-	 * submission so does not point to the start sector of the bio at
-	 * completion.
-	 */
-	if (ioend->io_sector + (ioend->io_size >> 9) != next->io_sector)
-		return false;
-	return true;
-}
-
-void
-iomap_ioend_try_merge(struct iomap_ioend *ioend, struct list_head *more_ioends)
-{
-	struct iomap_ioend *next;
-
-	INIT_LIST_HEAD(&ioend->io_list);
-
-	while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend,
-			io_list))) {
-		if (!iomap_ioend_can_merge(ioend, next))
-			break;
-		list_move_tail(&next->io_list, &ioend->io_list);
-		ioend->io_size += next->io_size;
-	}
-}
-EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);
-
-static int
-iomap_ioend_compare(void *priv, const struct list_head *a,
-		const struct list_head *b)
-{
-	struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list);
-	struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list);
-
-	if (ia->io_offset < ib->io_offset)
-		return -1;
-	if (ia->io_offset > ib->io_offset)
-		return 1;
-	return 0;
-}
-
-void
-iomap_sort_ioends(struct list_head *ioend_list)
-{
-	list_sort(NULL, ioend_list, iomap_ioend_compare);
-}
-EXPORT_SYMBOL_GPL(iomap_sort_ioends);
-
 static void iomap_writepage_end_bio(struct bio *bio)
 {
-	iomap_finish_ioend(iomap_ioend_from_bio(bio),
-			blk_status_to_errno(bio->bi_status));
+	struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
+
+	ioend->io_error = blk_status_to_errno(bio->bi_status);
+	iomap_finish_ioend_buffered(ioend);
 }
 
 /*
- * Submit the final bio for an ioend.
+ * Submit an ioend.
  *
  * If @error is non-zero, it means that we have a situation where some part of
  * the submission process has failed after we've marked pages for writeback.
@@ -1694,14 +1586,18 @@ static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
 	 * failure happened so that the file system end I/O handler gets called
 	 * to clean up.
 	 */
-	if (wpc->ops->prepare_ioend)
-		error = wpc->ops->prepare_ioend(wpc->ioend, error);
+	if (wpc->ops->submit_ioend) {
+		error = wpc->ops->submit_ioend(wpc, error);
+	} else {
+		if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE))
+			error = -EIO;
+		if (!error)
+			submit_bio(&wpc->ioend->io_bio);
+	}
 
 	if (error) {
 		wpc->ioend->io_bio.bi_status = errno_to_blk_status(error);
 		bio_endio(&wpc->ioend->io_bio);
-	} else {
-		submit_bio(&wpc->ioend->io_bio);
 	}
 
 	wpc->ioend = NULL;
@@ -1709,9 +1605,9 @@ static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
 }
 
 static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct inode *inode, loff_t pos)
+		struct writeback_control *wbc, struct inode *inode, loff_t pos,
+		u16 ioend_flags)
 {
-	struct iomap_ioend *ioend;
 	struct bio *bio;
 
 	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
@@ -1719,36 +1615,24 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
 			       GFP_NOFS, &iomap_ioend_bioset);
 	bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
 	bio->bi_end_io = iomap_writepage_end_bio;
-	wbc_init_bio(wbc, bio);
 	bio->bi_write_hint = inode->i_write_hint;
-
-	ioend = iomap_ioend_from_bio(bio);
-	INIT_LIST_HEAD(&ioend->io_list);
-	ioend->io_type = wpc->iomap.type;
-	ioend->io_flags = wpc->iomap.flags;
-	if (pos > wpc->iomap.offset)
-		wpc->iomap.flags &= ~IOMAP_F_BOUNDARY;
-	ioend->io_inode = inode;
-	ioend->io_size = 0;
-	ioend->io_offset = pos;
-	ioend->io_sector = bio->bi_iter.bi_sector;
-
+	wbc_init_bio(wbc, bio);
 	wpc->nr_folios = 0;
-	return ioend;
+	return iomap_init_ioend(inode, bio, pos, ioend_flags);
 }
 
-static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos)
+static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
+		u16 ioend_flags)
 {
-	if (wpc->iomap.offset == pos && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
+	if (ioend_flags & IOMAP_IOEND_BOUNDARY)
 		return false;
-	if ((wpc->iomap.flags & IOMAP_F_SHARED) !=
-	    (wpc->ioend->io_flags & IOMAP_F_SHARED))
-		return false;
-	if (wpc->iomap.type != wpc->ioend->io_type)
+	if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) !=
+	    (wpc->ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
 		return false;
 	if (pos != wpc->ioend->io_offset + wpc->ioend->io_size)
 		return false;
-	if (iomap_sector(&wpc->iomap, pos) !=
+	if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) &&
+	    iomap_sector(&wpc->iomap, pos) !=
 	    bio_end_sector(&wpc->ioend->io_bio))
 		return false;
 	/*
@@ -1779,14 +1663,23 @@ static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
 {
 	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
+	unsigned int ioend_flags = 0;
 	int error;
 
-	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos)) {
+	if (wpc->iomap.type == IOMAP_UNWRITTEN)
+		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
+	if (wpc->iomap.flags & IOMAP_F_SHARED)
+		ioend_flags |= IOMAP_IOEND_SHARED;
+	if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
+		ioend_flags |= IOMAP_IOEND_BOUNDARY;
+
+	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) {
 new_ioend:
 		error = iomap_submit_ioend(wpc, 0);
 		if (error)
 			return error;
-		wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos);
+		wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos,
+				ioend_flags);
 	}
 
 	if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff))
@@ -2062,11 +1955,3 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 	return iomap_submit_ioend(wpc, error);
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
-
-static int __init iomap_buffered_init(void)
-{
-	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
-			   offsetof(struct iomap_ioend, io_bio),
-			   BIOSET_NEED_BVECS);
-}
-fs_initcall(iomap_buffered_init);
diff --git a/fs/iomap/direct-io.c b/fs/iomap/direct-io.c
index b521eb15759e..5299f70428ef 100644
--- a/fs/iomap/direct-io.c
+++ b/fs/iomap/direct-io.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
  * Copyright (C) 2010 Red Hat, Inc.
- * Copyright (c) 2016-2021 Christoph Hellwig.
+ * Copyright (c) 2016-2025 Christoph Hellwig.
  */
 #include <linux/module.h>
 #include <linux/compiler.h>
@@ -12,6 +12,7 @@
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
 #include <linux/task_io_accounting_ops.h>
+#include "internal.h"
 #include "trace.h"
 
 #include "../internal.h"
@@ -20,6 +21,7 @@
  * Private flags for iomap_dio, must not overlap with the public ones in
  * iomap.h:
  */
+#define IOMAP_DIO_NO_INVALIDATE	(1U << 25)
 #define IOMAP_DIO_CALLER_COMP	(1U << 26)
 #define IOMAP_DIO_INLINE_COMP	(1U << 27)
 #define IOMAP_DIO_WRITE_THROUGH	(1U << 28)
@@ -81,10 +83,12 @@ static void iomap_dio_submit_bio(const struct iomap_iter *iter,
 		WRITE_ONCE(iocb->private, bio);
 	}
 
-	if (dio->dops && dio->dops->submit_io)
+	if (dio->dops && dio->dops->submit_io) {
 		dio->dops->submit_io(iter, bio, pos);
-	else
+	} else {
+		WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_ANON_WRITE);
 		submit_bio(bio);
+	}
 }
 
 ssize_t iomap_dio_complete(struct iomap_dio *dio)
@@ -117,7 +121,8 @@ ssize_t iomap_dio_complete(struct iomap_dio *dio)
 	 * ->end_io() when necessary, otherwise a racing buffer read would cache
 	 * zeros from unwritten extents.
 	 */
-	if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE))
+	if (!dio->error && dio->size && (dio->flags & IOMAP_DIO_WRITE) &&
+	    !(dio->flags & IOMAP_DIO_NO_INVALIDATE))
 		kiocb_invalidate_post_direct_write(iocb, dio->size);
 
 	inode_dio_end(file_inode(iocb->ki_filp));
@@ -163,43 +168,31 @@ static inline void iomap_dio_set_error(struct iomap_dio *dio, int ret)
 	cmpxchg(&dio->error, 0, ret);
 }
 
-void iomap_dio_bio_end_io(struct bio *bio)
+/*
+ * Called when dio->ref reaches zero from an I/O completion.
+ */
+static void iomap_dio_done(struct iomap_dio *dio)
 {
-	struct iomap_dio *dio = bio->bi_private;
-	bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
 	struct kiocb *iocb = dio->iocb;
 
-	if (bio->bi_status)
-		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
-	if (!atomic_dec_and_test(&dio->ref))
-		goto release_bio;
-
-	/*
-	 * Synchronous dio, task itself will handle any completion work
-	 * that needs after IO. All we need to do is wake the task.
-	 */
 	if (dio->wait_for_completion) {
+		/*
+		 * Synchronous I/O, task itself will handle any completion work
+		 * that needs after IO. All we need to do is wake the task.
+		 */
 		struct task_struct *waiter = dio->submit.waiter;
 
 		WRITE_ONCE(dio->submit.waiter, NULL);
 		blk_wake_io_task(waiter);
-		goto release_bio;
-	}
-
-	/*
-	 * Flagged with IOMAP_DIO_INLINE_COMP, we can complete it inline
-	 */
-	if (dio->flags & IOMAP_DIO_INLINE_COMP) {
+	} else if (dio->flags & IOMAP_DIO_INLINE_COMP) {
 		WRITE_ONCE(iocb->private, NULL);
 		iomap_dio_complete_work(&dio->aio.work);
-		goto release_bio;
-	}
-
-	/*
-	 * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then schedule
-	 * our completion that way to avoid an async punt to a workqueue.
-	 */
-	if (dio->flags & IOMAP_DIO_CALLER_COMP) {
+	} else if (dio->flags & IOMAP_DIO_CALLER_COMP) {
+		/*
+		 * If this dio is flagged with IOMAP_DIO_CALLER_COMP, then
+		 * schedule our completion that way to avoid an async punt to a
+		 * workqueue.
+		 */
 		/* only polled IO cares about private cleared */
 		iocb->private = dio;
 		iocb->dio_complete = iomap_dio_deferred_complete;
@@ -217,19 +210,31 @@ void iomap_dio_bio_end_io(struct bio *bio)
 		 * issuer.
 		 */
 		iocb->ki_complete(iocb, 0);
-		goto release_bio;
+	} else {
+		struct inode *inode = file_inode(iocb->ki_filp);
+
+		/*
+		 * Async DIO completion that requires filesystem level
+		 * completion work gets punted to a work queue to complete as
+		 * the operation may require more IO to be issued to finalise
+		 * filesystem metadata changes or guarantee data integrity.
+		 */
+		INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
+		queue_work(inode->i_sb->s_dio_done_wq, &dio->aio.work);
 	}
+}
+
+void iomap_dio_bio_end_io(struct bio *bio)
+{
+	struct iomap_dio *dio = bio->bi_private;
+	bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
+
+	if (bio->bi_status)
+		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
+
+	if (atomic_dec_and_test(&dio->ref))
+		iomap_dio_done(dio);
 
-	/*
-	 * Async DIO completion that requires filesystem level completion work
-	 * gets punted to a work queue to complete as the operation may require
-	 * more IO to be issued to finalise filesystem metadata changes or
-	 * guarantee data integrity.
-	 */
-	INIT_WORK(&dio->aio.work, iomap_dio_complete_work);
-	queue_work(file_inode(iocb->ki_filp)->i_sb->s_dio_done_wq,
-			&dio->aio.work);
-release_bio:
 	if (should_dirty) {
 		bio_check_pages_dirty(bio);
 	} else {
@@ -239,6 +244,47 @@ release_bio:
 }
 EXPORT_SYMBOL_GPL(iomap_dio_bio_end_io);
 
+u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend)
+{
+	struct iomap_dio *dio = ioend->io_bio.bi_private;
+	bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
+	u32 vec_count = ioend->io_bio.bi_vcnt;
+
+	if (ioend->io_error)
+		iomap_dio_set_error(dio, ioend->io_error);
+
+	if (atomic_dec_and_test(&dio->ref)) {
+		/*
+		 * Try to avoid another context switch for the completion given
+		 * that we are already called from the ioend completion
+		 * workqueue, but never invalidate pages from this thread to
+		 * avoid deadlocks with buffered I/O completions.  Tough luck if
+		 * you hit the tiny race with someone dirtying the range now
+		 * between this check and the actual completion.
+		 */
+		if (!dio->iocb->ki_filp->f_mapping->nrpages) {
+			dio->flags |= IOMAP_DIO_INLINE_COMP;
+			dio->flags |= IOMAP_DIO_NO_INVALIDATE;
+		}
+		dio->flags &= ~IOMAP_DIO_CALLER_COMP;
+		iomap_dio_done(dio);
+	}
+
+	if (should_dirty) {
+		bio_check_pages_dirty(&ioend->io_bio);
+	} else {
+		bio_release_pages(&ioend->io_bio, false);
+		bio_put(&ioend->io_bio);
+	}
+
+	/*
+	 * Return the number of bvecs completed as even direct I/O completions
+	 * do significant per-folio work and we'll still want to give up the
+	 * CPU after a lot of completions.
+	 */
+	return vec_count;
+}
+
 static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
 		loff_t pos, unsigned len)
 {
@@ -271,7 +317,7 @@ static int iomap_dio_zero(const struct iomap_iter *iter, struct iomap_dio *dio,
  * clearing the WRITE_THROUGH flag in the dio request.
  */
 static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
-		const struct iomap *iomap, bool use_fua, bool atomic)
+		const struct iomap *iomap, bool use_fua, bool atomic_hw)
 {
 	blk_opf_t opflags = REQ_SYNC | REQ_IDLE;
 
@@ -283,30 +329,29 @@ static inline blk_opf_t iomap_dio_bio_opflags(struct iomap_dio *dio,
 		opflags |= REQ_FUA;
 	else
 		dio->flags &= ~IOMAP_DIO_WRITE_THROUGH;
-	if (atomic)
+	if (atomic_hw)
 		opflags |= REQ_ATOMIC;
 
 	return opflags;
 }
 
-static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
-		struct iomap_dio *dio)
+static int iomap_dio_bio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 {
 	const struct iomap *iomap = &iter->iomap;
 	struct inode *inode = iter->inode;
 	unsigned int fs_block_size = i_blocksize(inode), pad;
+	bool atomic_hw = iter->flags & IOMAP_ATOMIC_HW;
 	const loff_t length = iomap_length(iter);
-	bool atomic = iter->flags & IOMAP_ATOMIC;
 	loff_t pos = iter->pos;
 	blk_opf_t bio_opf;
 	struct bio *bio;
 	bool need_zeroout = false;
 	bool use_fua = false;
 	int nr_pages, ret = 0;
-	size_t copied = 0;
+	u64 copied = 0;
 	size_t orig_count;
 
-	if (atomic && length != fs_block_size)
+	if (atomic_hw && length != iter->len)
 		return -EINVAL;
 
 	if ((pos | length) & (bdev_logical_block_size(iomap->bdev) - 1) ||
@@ -383,7 +428,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 			goto out;
 	}
 
-	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic);
+	bio_opf = iomap_dio_bio_opflags(dio, iomap, use_fua, atomic_hw);
 
 	nr_pages = bio_iov_vecs_to_alloc(dio->submit.iter, BIO_MAX_VECS);
 	do {
@@ -416,7 +461,7 @@ static loff_t iomap_dio_bio_iter(const struct iomap_iter *iter,
 		}
 
 		n = bio->bi_iter.bi_size;
-		if (WARN_ON_ONCE(atomic && n != length)) {
+		if (WARN_ON_ONCE(atomic_hw && n != length)) {
 			/*
 			 * This bio should have covered the complete length,
 			 * which it doesn't, so error. We may need to zero out
@@ -467,30 +512,28 @@ out:
 	/* Undo iter limitation to current extent */
 	iov_iter_reexpand(dio->submit.iter, orig_count - copied);
 	if (copied)
-		return copied;
+		return iomap_iter_advance(iter, &copied);
 	return ret;
 }
 
-static loff_t iomap_dio_hole_iter(const struct iomap_iter *iter,
-		struct iomap_dio *dio)
+static int iomap_dio_hole_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 {
 	loff_t length = iov_iter_zero(iomap_length(iter), dio->submit.iter);
 
 	dio->size += length;
 	if (!length)
 		return -EFAULT;
-	return length;
+	return iomap_iter_advance(iter, &length);
 }
 
-static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi,
-		struct iomap_dio *dio)
+static int iomap_dio_inline_iter(struct iomap_iter *iomi, struct iomap_dio *dio)
 {
 	const struct iomap *iomap = &iomi->iomap;
 	struct iov_iter *iter = dio->submit.iter;
 	void *inline_data = iomap_inline_data(iomap, iomi->pos);
 	loff_t length = iomap_length(iomi);
 	loff_t pos = iomi->pos;
-	size_t copied;
+	u64 copied;
 
 	if (WARN_ON_ONCE(!iomap_inline_data_valid(iomap)))
 		return -EIO;
@@ -512,11 +555,10 @@ static loff_t iomap_dio_inline_iter(const struct iomap_iter *iomi,
 	dio->size += copied;
 	if (!copied)
 		return -EFAULT;
-	return copied;
+	return iomap_iter_advance(iomi, &copied);
 }
 
-static loff_t iomap_dio_iter(const struct iomap_iter *iter,
-		struct iomap_dio *dio)
+static int iomap_dio_iter(struct iomap_iter *iter, struct iomap_dio *dio)
 {
 	switch (iter->iomap.type) {
 	case IOMAP_HOLE:
@@ -610,9 +652,6 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 	if (iocb->ki_flags & IOCB_NOWAIT)
 		iomi.flags |= IOMAP_NOWAIT;
 
-	if (iocb->ki_flags & IOCB_ATOMIC)
-		iomi.flags |= IOMAP_ATOMIC;
-
 	if (iov_iter_rw(iter) == READ) {
 		/* reads can always complete inline */
 		dio->flags |= IOMAP_DIO_INLINE_COMP;
@@ -647,6 +686,11 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 			iomi.flags |= IOMAP_OVERWRITE_ONLY;
 		}
 
+		if (dio_flags & IOMAP_DIO_ATOMIC_SW)
+			iomi.flags |= IOMAP_ATOMIC_SW;
+		else if (iocb->ki_flags & IOCB_ATOMIC)
+			iomi.flags |= IOMAP_ATOMIC_HW;
+
 		/* for data sync or sync, we need sync completion processing */
 		if (iocb_is_dsync(iocb)) {
 			dio->flags |= IOMAP_DIO_NEED_SYNC;
@@ -700,7 +744,7 @@ __iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 
 	blk_start_plug(&plug);
 	while ((ret = iomap_iter(&iomi, ops)) > 0) {
-		iomi.processed = iomap_dio_iter(&iomi, dio);
+		iomi.status = iomap_dio_iter(&iomi, dio);
 
 		/*
 		 * We can only poll for single bio I/Os.
diff --git a/fs/iomap/fiemap.c b/fs/iomap/fiemap.c
index 610ca6f1ec9b..80675c42e94e 100644
--- a/fs/iomap/fiemap.c
+++ b/fs/iomap/fiemap.c
@@ -39,24 +39,23 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi,
 			iomap->length, flags);
 }
 
-static loff_t iomap_fiemap_iter(const struct iomap_iter *iter,
+static int iomap_fiemap_iter(struct iomap_iter *iter,
 		struct fiemap_extent_info *fi, struct iomap *prev)
 {
 	int ret;
 
 	if (iter->iomap.type == IOMAP_HOLE)
-		return iomap_length(iter);
+		goto advance;
 
 	ret = iomap_to_fiemap(fi, prev, 0);
 	*prev = iter->iomap;
-	switch (ret) {
-	case 0:		/* success */
-		return iomap_length(iter);
-	case 1:		/* extent array full */
-		return 0;
-	default:	/* error */
+	if (ret < 0)
 		return ret;
-	}
+	if (ret == 1)	/* extent array full */
+		return 0;
+
+advance:
+	return iomap_iter_advance_full(iter);
 }
 
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
@@ -78,7 +77,7 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 		return ret;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_fiemap_iter(&iter, fi, &prev);
+		iter.status = iomap_fiemap_iter(&iter, fi, &prev);
 
 	if (prev.type != IOMAP_HOLE) {
 		ret = iomap_to_fiemap(fi, &prev, FIEMAP_EXTENT_LAST);
@@ -114,7 +113,7 @@ iomap_bmap(struct address_space *mapping, sector_t bno,
 	while ((ret = iomap_iter(&iter, ops)) > 0) {
 		if (iter.iomap.type == IOMAP_MAPPED)
 			bno = iomap_sector(&iter.iomap, iter.pos) >> blkshift;
-		/* leave iter.processed unset to abort loop */
+		/* leave iter.status unset to abort loop */
 	}
 	if (ret)
 		return 0;
diff --git a/fs/iomap/internal.h b/fs/iomap/internal.h
new file mode 100644
index 000000000000..f6992a3bf66a
--- /dev/null
+++ b/fs/iomap/internal.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _IOMAP_INTERNAL_H
+#define _IOMAP_INTERNAL_H 1
+
+#define IOEND_BATCH_SIZE	4096
+
+u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend);
+u32 iomap_finish_ioend_direct(struct iomap_ioend *ioend);
+
+#endif /* _IOMAP_INTERNAL_H */
diff --git a/fs/iomap/ioend.c b/fs/iomap/ioend.c
new file mode 100644
index 000000000000..18894ebba6db
--- /dev/null
+++ b/fs/iomap/ioend.c
@@ -0,0 +1,216 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024-2025 Christoph Hellwig.
+ */
+#include <linux/iomap.h>
+#include <linux/list_sort.h>
+#include "internal.h"
+
+struct bio_set iomap_ioend_bioset;
+EXPORT_SYMBOL_GPL(iomap_ioend_bioset);
+
+struct iomap_ioend *iomap_init_ioend(struct inode *inode,
+		struct bio *bio, loff_t file_offset, u16 ioend_flags)
+{
+	struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
+
+	atomic_set(&ioend->io_remaining, 1);
+	ioend->io_error = 0;
+	ioend->io_parent = NULL;
+	INIT_LIST_HEAD(&ioend->io_list);
+	ioend->io_flags = ioend_flags;
+	ioend->io_inode = inode;
+	ioend->io_offset = file_offset;
+	ioend->io_size = bio->bi_iter.bi_size;
+	ioend->io_sector = bio->bi_iter.bi_sector;
+	ioend->io_private = NULL;
+	return ioend;
+}
+EXPORT_SYMBOL_GPL(iomap_init_ioend);
+
+static u32 iomap_finish_ioend(struct iomap_ioend *ioend, int error)
+{
+	if (ioend->io_parent) {
+		struct bio *bio = &ioend->io_bio;
+
+		ioend = ioend->io_parent;
+		bio_put(bio);
+	}
+
+	if (error)
+		cmpxchg(&ioend->io_error, 0, error);
+
+	if (!atomic_dec_and_test(&ioend->io_remaining))
+		return 0;
+	if (ioend->io_flags & IOMAP_IOEND_DIRECT)
+		return iomap_finish_ioend_direct(ioend);
+	return iomap_finish_ioend_buffered(ioend);
+}
+
+/*
+ * Ioend completion routine for merged bios. This can only be called from task
+ * contexts as merged ioends can be of unbound length. Hence we have to break up
+ * the writeback completions into manageable chunks to avoid long scheduler
+ * holdoffs. We aim to keep scheduler holdoffs down below 10ms so that we get
+ * good batch processing throughput without creating adverse scheduler latency
+ * conditions.
+ */
+void iomap_finish_ioends(struct iomap_ioend *ioend, int error)
+{
+	struct list_head tmp;
+	u32 completions;
+
+	might_sleep();
+
+	list_replace_init(&ioend->io_list, &tmp);
+	completions = iomap_finish_ioend(ioend, error);
+
+	while (!list_empty(&tmp)) {
+		if (completions > IOEND_BATCH_SIZE * 8) {
+			cond_resched();
+			completions = 0;
+		}
+		ioend = list_first_entry(&tmp, struct iomap_ioend, io_list);
+		list_del_init(&ioend->io_list);
+		completions += iomap_finish_ioend(ioend, error);
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_finish_ioends);
+
+/*
+ * We can merge two adjacent ioends if they have the same set of work to do.
+ */
+static bool iomap_ioend_can_merge(struct iomap_ioend *ioend,
+		struct iomap_ioend *next)
+{
+	if (ioend->io_bio.bi_status != next->io_bio.bi_status)
+		return false;
+	if (next->io_flags & IOMAP_IOEND_BOUNDARY)
+		return false;
+	if ((ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS) !=
+	    (next->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
+		return false;
+	if (ioend->io_offset + ioend->io_size != next->io_offset)
+		return false;
+	/*
+	 * Do not merge physically discontiguous ioends. The filesystem
+	 * completion functions will have to iterate the physical
+	 * discontiguities even if we merge the ioends at a logical level, so
+	 * we don't gain anything by merging physical discontiguities here.
+	 *
+	 * We cannot use bio->bi_iter.bi_sector here as it is modified during
+	 * submission so does not point to the start sector of the bio at
+	 * completion.
+	 */
+	if (ioend->io_sector + (ioend->io_size >> SECTOR_SHIFT) !=
+	    next->io_sector)
+		return false;
+	return true;
+}
+
+void iomap_ioend_try_merge(struct iomap_ioend *ioend,
+		struct list_head *more_ioends)
+{
+	struct iomap_ioend *next;
+
+	INIT_LIST_HEAD(&ioend->io_list);
+
+	while ((next = list_first_entry_or_null(more_ioends, struct iomap_ioend,
+			io_list))) {
+		if (!iomap_ioend_can_merge(ioend, next))
+			break;
+		list_move_tail(&next->io_list, &ioend->io_list);
+		ioend->io_size += next->io_size;
+	}
+}
+EXPORT_SYMBOL_GPL(iomap_ioend_try_merge);
+
+static int iomap_ioend_compare(void *priv, const struct list_head *a,
+		const struct list_head *b)
+{
+	struct iomap_ioend *ia = container_of(a, struct iomap_ioend, io_list);
+	struct iomap_ioend *ib = container_of(b, struct iomap_ioend, io_list);
+
+	if (ia->io_offset < ib->io_offset)
+		return -1;
+	if (ia->io_offset > ib->io_offset)
+		return 1;
+	return 0;
+}
+
+void iomap_sort_ioends(struct list_head *ioend_list)
+{
+	list_sort(NULL, ioend_list, iomap_ioend_compare);
+}
+EXPORT_SYMBOL_GPL(iomap_sort_ioends);
+
+/*
+ * Split up to the first @max_len bytes from @ioend if the ioend covers more
+ * than @max_len bytes.
+ *
+ * If @is_append is set, the split will be based on the hardware limits for
+ * REQ_OP_ZONE_APPEND commands and can be less than @max_len if the hardware
+ * limits don't allow the entire @max_len length.
+ *
+ * The bio embedded into @ioend must be a REQ_OP_WRITE because the block layer
+ * does not allow splitting REQ_OP_ZONE_APPEND bios.  The file systems has to
+ * switch the operation after this call, but before submitting the bio.
+ */
+struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
+		unsigned int max_len, bool is_append)
+{
+	struct bio *bio = &ioend->io_bio;
+	struct iomap_ioend *split_ioend;
+	unsigned int nr_segs;
+	int sector_offset;
+	struct bio *split;
+
+	if (is_append) {
+		struct queue_limits *lim = bdev_limits(bio->bi_bdev);
+
+		max_len = min(max_len,
+			      lim->max_zone_append_sectors << SECTOR_SHIFT);
+
+		sector_offset = bio_split_rw_at(bio, lim, &nr_segs, max_len);
+		if (unlikely(sector_offset < 0))
+			return ERR_PTR(sector_offset);
+		if (!sector_offset)
+			return NULL;
+	} else {
+		if (bio->bi_iter.bi_size <= max_len)
+			return NULL;
+		sector_offset = max_len >> SECTOR_SHIFT;
+	}
+
+	/* ensure the split ioend is still block size aligned */
+	sector_offset = ALIGN_DOWN(sector_offset << SECTOR_SHIFT,
+			i_blocksize(ioend->io_inode)) >> SECTOR_SHIFT;
+
+	split = bio_split(bio, sector_offset, GFP_NOFS, &iomap_ioend_bioset);
+	if (IS_ERR(split))
+		return ERR_CAST(split);
+	split->bi_private = bio->bi_private;
+	split->bi_end_io = bio->bi_end_io;
+
+	split_ioend = iomap_init_ioend(ioend->io_inode, split, ioend->io_offset,
+			ioend->io_flags);
+	split_ioend->io_parent = ioend;
+
+	atomic_inc(&ioend->io_remaining);
+	ioend->io_offset += split_ioend->io_size;
+	ioend->io_size -= split_ioend->io_size;
+
+	split_ioend->io_sector = ioend->io_sector;
+	if (!is_append)
+		ioend->io_sector += (split_ioend->io_size >> SECTOR_SHIFT);
+	return split_ioend;
+}
+EXPORT_SYMBOL_GPL(iomap_split_ioend);
+
+static int __init iomap_ioend_init(void)
+{
+	return bioset_init(&iomap_ioend_bioset, 4 * (PAGE_SIZE / SECTOR_SIZE),
+			   offsetof(struct iomap_ioend, io_bio),
+			   BIOSET_NEED_BVECS);
+}
+fs_initcall(iomap_ioend_init);
diff --git a/fs/iomap/iter.c b/fs/iomap/iter.c
index 3790918646af..6ffc6a7b9ba5 100644
--- a/fs/iomap/iter.c
+++ b/fs/iomap/iter.c
@@ -7,40 +7,25 @@
 #include <linux/iomap.h>
 #include "trace.h"
 
-/*
- * Advance to the next range we need to map.
- *
- * If the iomap is marked IOMAP_F_STALE, it means the existing map was not fully
- * processed - it was aborted because the extent the iomap spanned may have been
- * changed during the operation. In this case, the iteration behaviour is to
- * remap the unprocessed range of the iter, and that means we may need to remap
- * even when we've made no progress (i.e. iter->processed = 0). Hence the
- * "finished iterating" case needs to distinguish between
- * (processed = 0) meaning we are done and (processed = 0 && stale) meaning we
- * need to remap the entire remaining range.
- */
-static inline int iomap_iter_advance(struct iomap_iter *iter)
+static inline void iomap_iter_reset_iomap(struct iomap_iter *iter)
 {
-	bool stale = iter->iomap.flags & IOMAP_F_STALE;
-	int ret = 1;
-
-	/* handle the previous iteration (if any) */
-	if (iter->iomap.length) {
-		if (iter->processed < 0)
-			return iter->processed;
-		if (WARN_ON_ONCE(iter->processed > iomap_length(iter)))
-			return -EIO;
-		iter->pos += iter->processed;
-		iter->len -= iter->processed;
-		if (!iter->len || (!iter->processed && !stale))
-			ret = 0;
-	}
-
-	/* clear the per iteration state */
-	iter->processed = 0;
+	iter->status = 0;
 	memset(&iter->iomap, 0, sizeof(iter->iomap));
 	memset(&iter->srcmap, 0, sizeof(iter->srcmap));
-	return ret;
+}
+
+/*
+ * Advance the current iterator position and output the length remaining for the
+ * current mapping.
+ */
+int iomap_iter_advance(struct iomap_iter *iter, u64 *count)
+{
+	if (WARN_ON_ONCE(*count > iomap_length(iter)))
+		return -EIO;
+	iter->pos += *count;
+	iter->len -= *count;
+	*count = iomap_length(iter);
+	return 0;
 }
 
 static inline void iomap_iter_done(struct iomap_iter *iter)
@@ -50,6 +35,8 @@ static inline void iomap_iter_done(struct iomap_iter *iter)
 	WARN_ON_ONCE(iter->iomap.offset + iter->iomap.length <= iter->pos);
 	WARN_ON_ONCE(iter->iomap.flags & IOMAP_F_STALE);
 
+	iter->iter_start_pos = iter->pos;
+
 	trace_iomap_iter_dstmap(iter->inode, &iter->iomap);
 	if (iter->srcmap.type != IOMAP_HOLE)
 		trace_iomap_iter_srcmap(iter->inode, &iter->srcmap);
@@ -67,26 +54,58 @@ static inline void iomap_iter_done(struct iomap_iter *iter)
  * function must be called in a loop that continues as long it returns a
  * positive value.  If 0 or a negative value is returned, the caller must not
  * return to the loop body.  Within a loop body, there are two ways to break out
- * of the loop body:  leave @iter.processed unchanged, or set it to a negative
+ * of the loop body:  leave @iter.status unchanged, or set it to a negative
  * errno.
  */
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops)
 {
+	bool stale = iter->iomap.flags & IOMAP_F_STALE;
+	ssize_t advanced;
+	u64 olen;
 	int ret;
 
-	if (iter->iomap.length && ops->iomap_end) {
-		ret = ops->iomap_end(iter->inode, iter->pos, iomap_length(iter),
-				iter->processed > 0 ? iter->processed : 0,
-				iter->flags, &iter->iomap);
-		if (ret < 0 && !iter->processed)
+	trace_iomap_iter(iter, ops, _RET_IP_);
+
+	if (!iter->iomap.length)
+		goto begin;
+
+	/*
+	 * Calculate how far the iter was advanced and the original length bytes
+	 * for ->iomap_end().
+	 */
+	advanced = iter->pos - iter->iter_start_pos;
+	olen = iter->len + advanced;
+
+	if (ops->iomap_end) {
+		ret = ops->iomap_end(iter->inode, iter->iter_start_pos,
+				iomap_length_trim(iter, iter->iter_start_pos,
+						  olen),
+				advanced, iter->flags, &iter->iomap);
+		if (ret < 0 && !advanced)
 			return ret;
 	}
 
-	trace_iomap_iter(iter, ops, _RET_IP_);
-	ret = iomap_iter_advance(iter);
+	/* detect old return semantics where this would advance */
+	if (WARN_ON_ONCE(iter->status > 0))
+		iter->status = -EIO;
+
+	/*
+	 * Use iter->len to determine whether to continue onto the next mapping.
+	 * Explicitly terminate on error status or if the current iter has not
+	 * advanced at all (i.e. no work was done for some reason) unless the
+	 * mapping has been marked stale and needs to be reprocessed.
+	 */
+	if (iter->status < 0)
+		ret = iter->status;
+	else if (iter->len == 0 || (!advanced && !stale))
+		ret = 0;
+	else
+		ret = 1;
+	iomap_iter_reset_iomap(iter);
 	if (ret <= 0)
 		return ret;
 
+begin:
 	ret = ops->iomap_begin(iter->inode, iter->pos, iter->len, iter->flags,
 			       &iter->iomap, &iter->srcmap);
 	if (ret < 0)
diff --git a/fs/iomap/seek.c b/fs/iomap/seek.c
index a845c012b50c..04d7919636c1 100644
--- a/fs/iomap/seek.c
+++ b/fs/iomap/seek.c
@@ -10,7 +10,7 @@
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
 
-static loff_t iomap_seek_hole_iter(const struct iomap_iter *iter,
+static int iomap_seek_hole_iter(struct iomap_iter *iter,
 		loff_t *hole_pos)
 {
 	loff_t length = iomap_length(iter);
@@ -20,13 +20,13 @@ static loff_t iomap_seek_hole_iter(const struct iomap_iter *iter,
 		*hole_pos = mapping_seek_hole_data(iter->inode->i_mapping,
 				iter->pos, iter->pos + length, SEEK_HOLE);
 		if (*hole_pos == iter->pos + length)
-			return length;
+			return iomap_iter_advance(iter, &length);
 		return 0;
 	case IOMAP_HOLE:
 		*hole_pos = iter->pos;
 		return 0;
 	default:
-		return length;
+		return iomap_iter_advance(iter, &length);
 	}
 }
 
@@ -47,7 +47,7 @@ iomap_seek_hole(struct inode *inode, loff_t pos, const struct iomap_ops *ops)
 
 	iter.len = size - pos;
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_seek_hole_iter(&iter, &pos);
+		iter.status = iomap_seek_hole_iter(&iter, &pos);
 	if (ret < 0)
 		return ret;
 	if (iter.len) /* found hole before EOF */
@@ -56,19 +56,19 @@ iomap_seek_hole(struct inode *inode, loff_t pos, const struct iomap_ops *ops)
 }
 EXPORT_SYMBOL_GPL(iomap_seek_hole);
 
-static loff_t iomap_seek_data_iter(const struct iomap_iter *iter,
+static int iomap_seek_data_iter(struct iomap_iter *iter,
 		loff_t *hole_pos)
 {
 	loff_t length = iomap_length(iter);
 
 	switch (iter->iomap.type) {
 	case IOMAP_HOLE:
-		return length;
+		return iomap_iter_advance(iter, &length);
 	case IOMAP_UNWRITTEN:
 		*hole_pos = mapping_seek_hole_data(iter->inode->i_mapping,
 				iter->pos, iter->pos + length, SEEK_DATA);
 		if (*hole_pos < 0)
-			return length;
+			return iomap_iter_advance(iter, &length);
 		return 0;
 	default:
 		*hole_pos = iter->pos;
@@ -93,7 +93,7 @@ iomap_seek_data(struct inode *inode, loff_t pos, const struct iomap_ops *ops)
 
 	iter.len = size - pos;
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_seek_data_iter(&iter, &pos);
+		iter.status = iomap_seek_data_iter(&iter, &pos);
 	if (ret < 0)
 		return ret;
 	if (iter.len) /* found data before EOF */
diff --git a/fs/iomap/swapfile.c b/fs/iomap/swapfile.c
index b90d0eda9e51..c1a762c10ce4 100644
--- a/fs/iomap/swapfile.c
+++ b/fs/iomap/swapfile.c
@@ -94,7 +94,7 @@ static int iomap_swapfile_fail(struct iomap_swapfile_info *isi, const char *str)
  * swap only cares about contiguous page-aligned physical extents and makes no
  * distinction between written and unwritten extents.
  */
-static loff_t iomap_swapfile_iter(const struct iomap_iter *iter,
+static int iomap_swapfile_iter(struct iomap_iter *iter,
 		struct iomap *iomap, struct iomap_swapfile_info *isi)
 {
 	switch (iomap->type) {
@@ -132,7 +132,8 @@ static loff_t iomap_swapfile_iter(const struct iomap_iter *iter,
 			return error;
 		memcpy(&isi->iomap, iomap, sizeof(isi->iomap));
 	}
-	return iomap_length(iter);
+
+	return iomap_iter_advance_full(iter);
 }
 
 /*
@@ -166,7 +167,7 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
 		return ret;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.processed = iomap_swapfile_iter(&iter, &iter.iomap, &isi);
+		iter.status = iomap_swapfile_iter(&iter, &iter.iomap, &isi);
 	if (ret < 0)
 		return ret;
 
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 4118a42cdab0..69af89044ebd 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -99,7 +99,7 @@ DEFINE_RANGE_EVENT(iomap_dio_rw_queued);
 	{ IOMAP_FAULT,		"FAULT" }, \
 	{ IOMAP_DIRECT,		"DIRECT" }, \
 	{ IOMAP_NOWAIT,		"NOWAIT" }, \
-	{ IOMAP_ATOMIC,		"ATOMIC" }
+	{ IOMAP_ATOMIC_HW,	"ATOMIC_HW" }
 
 #define IOMAP_F_FLAGS_STRINGS \
 	{ IOMAP_F_NEW,		"NEW" }, \
@@ -207,7 +207,7 @@ TRACE_EVENT(iomap_iter,
 		__field(u64, ino)
 		__field(loff_t, pos)
 		__field(u64, length)
-		__field(s64, processed)
+		__field(int, status)
 		__field(unsigned int, flags)
 		__field(const void *, ops)
 		__field(unsigned long, caller)
@@ -217,17 +217,17 @@ TRACE_EVENT(iomap_iter,
 		__entry->ino = iter->inode->i_ino;
 		__entry->pos = iter->pos;
 		__entry->length = iomap_length(iter);
-		__entry->processed = iter->processed;
+		__entry->status = iter->status;
 		__entry->flags = iter->flags;
 		__entry->ops = ops;
 		__entry->caller = caller;
 	),
-	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx processed %lld flags %s (0x%x) ops %ps caller %pS",
+	TP_printk("dev %d:%d ino 0x%llx pos 0x%llx length 0x%llx status %d flags %s (0x%x) ops %ps caller %pS",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		   __entry->ino,
 		   __entry->pos,
 		   __entry->length,
-		   __entry->processed,
+		   __entry->status,
 		   __print_flags(__entry->flags, "|", IOMAP_FLAGS_STRINGS),
 		   __entry->flags,
 		   __entry->ops,
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 7afa51e41427..5bf501cf8271 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -64,6 +64,7 @@ xfs-y				+= $(addprefix libxfs/, \
 xfs-$(CONFIG_XFS_RT)		+= $(addprefix libxfs/, \
 				   xfs_rtbitmap.o \
 				   xfs_rtgroup.o \
+				   xfs_zones.o \
 				   )
 
 # highlevel code
@@ -136,7 +137,11 @@ xfs-$(CONFIG_XFS_QUOTA)		+= xfs_dquot.o \
 				   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
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 0ef19f1469ec..63255820b58a 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -34,13 +34,13 @@
 #include "xfs_ag.h"
 #include "xfs_ag_resv.h"
 #include "xfs_refcount.h"
-#include "xfs_icache.h"
 #include "xfs_iomap.h"
 #include "xfs_health.h"
 #include "xfs_bmap_item.h"
 #include "xfs_symlink_remote.h"
 #include "xfs_inode_util.h"
 #include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
 
 struct kmem_cache		*xfs_bmap_intent_cache;
 
@@ -171,18 +171,16 @@ xfs_bmbt_update(
  * Compute the worst-case number of indirect blocks that will be used
  * for ip's delayed extent of length "len".
  */
-STATIC xfs_filblks_t
+xfs_filblks_t
 xfs_bmap_worst_indlen(
-	xfs_inode_t	*ip,		/* incore inode pointer */
-	xfs_filblks_t	len)		/* delayed extent length */
+	struct xfs_inode	*ip,		/* incore inode pointer */
+	xfs_filblks_t		len)		/* delayed extent length */
 {
-	int		level;		/* btree level number */
-	int		maxrecs;	/* maximum record count at this level */
-	xfs_mount_t	*mp;		/* mount structure */
-	xfs_filblks_t	rval;		/* return value */
+	struct xfs_mount	*mp = ip->i_mount;
+	int			maxrecs = mp->m_bmap_dmxr[0];
+	int			level;
+	xfs_filblks_t		rval;
 
-	mp = ip->i_mount;
-	maxrecs = mp->m_bmap_dmxr[0];
 	for (level = 0, rval = 0;
 	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);
 	     level++) {
@@ -2572,146 +2570,6 @@ done:
 }
 
 /*
- * Convert a hole to a delayed allocation.
- */
-STATIC void
-xfs_bmap_add_extent_hole_delay(
-	xfs_inode_t		*ip,	/* incore inode pointer */
-	int			whichfork,
-	struct xfs_iext_cursor	*icur,
-	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */
-{
-	struct xfs_ifork	*ifp;	/* inode fork pointer */
-	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */
-	xfs_filblks_t		newlen=0;	/* new indirect size */
-	xfs_filblks_t		oldlen=0;	/* old indirect size */
-	xfs_bmbt_irec_t		right;	/* right neighbor extent entry */
-	uint32_t		state = xfs_bmap_fork_to_state(whichfork);
-	xfs_filblks_t		temp;	 /* temp for indirect calculations */
-
-	ifp = xfs_ifork_ptr(ip, whichfork);
-	ASSERT(isnullstartblock(new->br_startblock));
-
-	/*
-	 * Check and set flags if this segment has a left neighbor
-	 */
-	if (xfs_iext_peek_prev_extent(ifp, icur, &left)) {
-		state |= BMAP_LEFT_VALID;
-		if (isnullstartblock(left.br_startblock))
-			state |= BMAP_LEFT_DELAY;
-	}
-
-	/*
-	 * Check and set flags if the current (right) segment exists.
-	 * If it doesn't exist, we're converting the hole at end-of-file.
-	 */
-	if (xfs_iext_get_extent(ifp, icur, &right)) {
-		state |= BMAP_RIGHT_VALID;
-		if (isnullstartblock(right.br_startblock))
-			state |= BMAP_RIGHT_DELAY;
-	}
-
-	/*
-	 * Set contiguity flags on the left and right neighbors.
-	 * Don't let extents get too large, even if the pieces are contiguous.
-	 */
-	if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&
-	    left.br_startoff + left.br_blockcount == new->br_startoff &&
-	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)
-		state |= BMAP_LEFT_CONTIG;
-
-	if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&
-	    new->br_startoff + new->br_blockcount == right.br_startoff &&
-	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&
-	    (!(state & BMAP_LEFT_CONTIG) ||
-	     (left.br_blockcount + new->br_blockcount +
-	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))
-		state |= BMAP_RIGHT_CONTIG;
-
-	/*
-	 * Switch out based on the contiguity flags.
-	 */
-	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {
-	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:
-		/*
-		 * New allocation is contiguous with delayed allocations
-		 * on the left and on the right.
-		 * Merge all three into a single extent record.
-		 */
-		temp = left.br_blockcount + new->br_blockcount +
-			right.br_blockcount;
-
-		oldlen = startblockval(left.br_startblock) +
-			startblockval(new->br_startblock) +
-			startblockval(right.br_startblock);
-		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-					 oldlen);
-		left.br_startblock = nullstartblock(newlen);
-		left.br_blockcount = temp;
-
-		xfs_iext_remove(ip, icur, state);
-		xfs_iext_prev(ifp, icur);
-		xfs_iext_update_extent(ip, state, icur, &left);
-		break;
-
-	case BMAP_LEFT_CONTIG:
-		/*
-		 * New allocation is contiguous with a delayed allocation
-		 * on the left.
-		 * Merge the new allocation with the left neighbor.
-		 */
-		temp = left.br_blockcount + new->br_blockcount;
-
-		oldlen = startblockval(left.br_startblock) +
-			startblockval(new->br_startblock);
-		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-					 oldlen);
-		left.br_blockcount = temp;
-		left.br_startblock = nullstartblock(newlen);
-
-		xfs_iext_prev(ifp, icur);
-		xfs_iext_update_extent(ip, state, icur, &left);
-		break;
-
-	case BMAP_RIGHT_CONTIG:
-		/*
-		 * New allocation is contiguous with a delayed allocation
-		 * on the right.
-		 * Merge the new allocation with the right neighbor.
-		 */
-		temp = new->br_blockcount + right.br_blockcount;
-		oldlen = startblockval(new->br_startblock) +
-			startblockval(right.br_startblock);
-		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
-					 oldlen);
-		right.br_startoff = new->br_startoff;
-		right.br_startblock = nullstartblock(newlen);
-		right.br_blockcount = temp;
-		xfs_iext_update_extent(ip, state, icur, &right);
-		break;
-
-	case 0:
-		/*
-		 * New allocation is not contiguous with another
-		 * delayed allocation.
-		 * Insert a new entry.
-		 */
-		oldlen = newlen = 0;
-		xfs_iext_insert(ip, icur, new, state);
-		break;
-	}
-	if (oldlen != newlen) {
-		ASSERT(oldlen > newlen);
-		xfs_add_fdblocks(ip->i_mount, oldlen - newlen);
-
-		/*
-		 * Nothing to do for disk quota accounting here.
-		 */
-		xfs_mod_delalloc(ip, 0, (int64_t)newlen - oldlen);
-	}
-}
-
-/*
  * Convert a hole to a real allocation.
  */
 STATIC int				/* error */
@@ -4039,144 +3897,6 @@ xfs_bmapi_read(
 	return 0;
 }
 
-/*
- * Add a delayed allocation extent to an inode. Blocks are reserved from the
- * global pool and the extent inserted into the inode in-core extent tree.
- *
- * On entry, got refers to the first extent beyond the offset of the extent to
- * allocate or eof is specified if no such extent exists. On return, got refers
- * to the extent record that was inserted to the inode fork.
- *
- * Note that the allocated extent may have been merged with contiguous extents
- * during insertion into the inode fork. Thus, got does not reflect the current
- * state of the inode fork on return. If necessary, the caller can use lastx to
- * look up the updated record in the inode fork.
- */
-int
-xfs_bmapi_reserve_delalloc(
-	struct xfs_inode	*ip,
-	int			whichfork,
-	xfs_fileoff_t		off,
-	xfs_filblks_t		len,
-	xfs_filblks_t		prealloc,
-	struct xfs_bmbt_irec	*got,
-	struct xfs_iext_cursor	*icur,
-	int			eof)
-{
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
-	xfs_extlen_t		alen;
-	xfs_extlen_t		indlen;
-	uint64_t		fdblocks;
-	int			error;
-	xfs_fileoff_t		aoff;
-	bool			use_cowextszhint =
-					whichfork == XFS_COW_FORK && !prealloc;
-
-retry:
-	/*
-	 * Cap the alloc length. Keep track of prealloc so we know whether to
-	 * tag the inode before we return.
-	 */
-	aoff = off;
-	alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);
-	if (!eof)
-		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);
-	if (prealloc && alen >= len)
-		prealloc = alen - len;
-
-	/*
-	 * If we're targetting the COW fork but aren't creating a speculative
-	 * posteof preallocation, try to expand the reservation to align with
-	 * the COW extent size hint if there's sufficient free space.
-	 *
-	 * Unlike the data fork, the CoW cancellation functions will free all
-	 * the reservations at inactivation, so we don't require that every
-	 * delalloc reservation have a dirty pagecache.
-	 */
-	if (use_cowextszhint) {
-		struct xfs_bmbt_irec	prev;
-		xfs_extlen_t		extsz = xfs_get_cowextsz_hint(ip);
-
-		if (!xfs_iext_peek_prev_extent(ifp, icur, &prev))
-			prev.br_startoff = NULLFILEOFF;
-
-		error = xfs_bmap_extsize_align(mp, got, &prev, extsz, 0, eof,
-					       1, 0, &aoff, &alen);
-		ASSERT(!error);
-	}
-
-	/*
-	 * Make a transaction-less quota reservation for delayed allocation
-	 * blocks.  This number gets adjusted later.  We return if we haven't
-	 * allocated blocks already inside this loop.
-	 */
-	error = xfs_quota_reserve_blkres(ip, alen);
-	if (error)
-		goto out;
-
-	/*
-	 * Split changing sb for alen and indlen since they could be coming
-	 * from different places.
-	 */
-	indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen);
-	ASSERT(indlen > 0);
-
-	fdblocks = indlen;
-	if (XFS_IS_REALTIME_INODE(ip)) {
-		error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
-		if (error)
-			goto out_unreserve_quota;
-	} else {
-		fdblocks += alen;
-	}
-
-	error = xfs_dec_fdblocks(mp, fdblocks, false);
-	if (error)
-		goto out_unreserve_frextents;
-
-	ip->i_delayed_blks += alen;
-	xfs_mod_delalloc(ip, alen, indlen);
-
-	got->br_startoff = aoff;
-	got->br_startblock = nullstartblock(indlen);
-	got->br_blockcount = alen;
-	got->br_state = XFS_EXT_NORM;
-
-	xfs_bmap_add_extent_hole_delay(ip, whichfork, icur, got);
-
-	/*
-	 * Tag the inode if blocks were preallocated. Note that COW fork
-	 * preallocation can occur at the start or end of the extent, even when
-	 * prealloc == 0, so we must also check the aligned offset and length.
-	 */
-	if (whichfork == XFS_DATA_FORK && prealloc)
-		xfs_inode_set_eofblocks_tag(ip);
-	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
-		xfs_inode_set_cowblocks_tag(ip);
-
-	return 0;
-
-out_unreserve_frextents:
-	if (XFS_IS_REALTIME_INODE(ip))
-		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));
-out_unreserve_quota:
-	if (XFS_IS_QUOTA_ON(mp))
-		xfs_quota_unreserve_blkres(ip, alen);
-out:
-	if (error == -ENOSPC || error == -EDQUOT) {
-		trace_xfs_delalloc_enospc(ip, off, len);
-
-		if (prealloc || use_cowextszhint) {
-			/* retry without any preallocation */
-			use_cowextszhint = false;
-			prealloc = 0;
-			goto retry;
-		}
-	}
-	return error;
-}
-
 static int
 xfs_bmapi_allocate(
 	struct xfs_bmalloca	*bma)
@@ -4948,7 +4668,8 @@ xfs_bmap_del_extent_delay(
 	int			whichfork,
 	struct xfs_iext_cursor	*icur,
 	struct xfs_bmbt_irec	*got,
-	struct xfs_bmbt_irec	*del)
+	struct xfs_bmbt_irec	*del,
+	uint32_t		bflags)	/* bmapi flags */
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
@@ -5068,10 +4789,18 @@ xfs_bmap_del_extent_delay(
 	da_diff = da_old - da_new;
 	fdblocks = da_diff;
 
-	if (isrt)
-		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));
-	else
+	if (bflags & XFS_BMAPI_REMAP) {
+		;
+	} else if (isrt) {
+		xfs_rtbxlen_t	rtxlen;
+
+		rtxlen = xfs_blen_to_rtbxlen(mp, del->br_blockcount);
+		if (xfs_is_zoned_inode(ip))
+			xfs_zoned_add_available(mp, rtxlen);
+		xfs_add_frextents(mp, rtxlen);
+	} else {
 		fdblocks += del->br_blockcount;
+	}
 
 	xfs_add_fdblocks(mp, fdblocks);
 	xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff);
@@ -5670,7 +5399,8 @@ __xfs_bunmapi(
 
 delete:
 		if (wasdel) {
-			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del);
+			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,
+					&del, flags);
 		} else {
 			error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,
 					&del, &tmp_logflags, whichfork,
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 4b721d935994..b4d9c6e0f3f9 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -204,7 +204,7 @@ int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_extnum_t nexts, int *done);
 void	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
-		struct xfs_bmbt_irec *del);
+		struct xfs_bmbt_irec *del, uint32_t bflags);
 void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
 		struct xfs_bmbt_irec *del);
@@ -219,10 +219,6 @@ int	xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		bool *done, xfs_fileoff_t stop_fsb);
 int	xfs_bmap_split_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t split_offset);
-int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,
-		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,
-		struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,
-		int eof);
 int	xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork,
 		xfs_off_t offset, struct iomap *iomap, unsigned int *seq);
 int	xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
@@ -233,6 +229,7 @@ xfs_extlen_t xfs_bmapi_minleft(struct xfs_trans *tp, struct xfs_inode *ip,
 		int fork);
 int	xfs_bmap_btalloc_low_space(struct xfs_bmalloca *ap,
 		struct xfs_alloc_arg *args);
+xfs_filblks_t xfs_bmap_worst_indlen(struct xfs_inode *ip, xfs_filblks_t len);
 
 enum xfs_bmap_intent_type {
 	XFS_BMAP_MAP = 1,
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index b1007fb661ba..9566a7623365 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -178,9 +178,10 @@ typedef struct xfs_sb {
 
 	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */
 	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */
-
 	uint8_t		sb_rgblklog;    /* rt group number shift */
 	uint8_t		sb_pad[7];	/* zeroes */
+	xfs_rfsblock_t	sb_rtstart;	/* start of internal RT section (FSB) */
+	xfs_filblks_t	sb_rtreserved;	/* reserved (zoned) RT blocks */
 
 	/* must be padded to 64 bit alignment */
 } xfs_sb_t;
@@ -270,9 +271,10 @@ struct xfs_dsb {
 	__be64		sb_metadirino;	/* metadata directory tree root */
 	__be32		sb_rgcount;	/* # of realtime groups */
 	__be32		sb_rgextents;	/* size of rtgroup in rtx */
-
 	__u8		sb_rgblklog;    /* rt group number shift */
 	__u8		sb_pad[7];	/* zeroes */
+	__be64		sb_rtstart;	/* start of internal RT section (FSB) */
+	__be64		sb_rtreserved;	/* reserved (zoned) RT blocks */
 
 	/*
 	 * The size of this structure must be padded to 64 bit alignment.
@@ -395,6 +397,9 @@ xfs_sb_has_ro_compat_feature(
 #define XFS_SB_FEAT_INCOMPAT_EXCHRANGE	(1 << 6)  /* exchangerange supported */
 #define XFS_SB_FEAT_INCOMPAT_PARENT	(1 << 7)  /* parent pointers */
 #define XFS_SB_FEAT_INCOMPAT_METADIR	(1 << 8)  /* metadata dir tree */
+#define XFS_SB_FEAT_INCOMPAT_ZONED	(1 << 9)  /* zoned RT allocator */
+#define XFS_SB_FEAT_INCOMPAT_ZONE_GAPS	(1 << 10) /* RTGs have LBA gaps */
+
 #define XFS_SB_FEAT_INCOMPAT_ALL \
 		(XFS_SB_FEAT_INCOMPAT_FTYPE | \
 		 XFS_SB_FEAT_INCOMPAT_SPINODES | \
@@ -404,7 +409,9 @@ xfs_sb_has_ro_compat_feature(
 		 XFS_SB_FEAT_INCOMPAT_NREXT64 | \
 		 XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \
 		 XFS_SB_FEAT_INCOMPAT_PARENT | \
-		 XFS_SB_FEAT_INCOMPAT_METADIR)
+		 XFS_SB_FEAT_INCOMPAT_METADIR | \
+		 XFS_SB_FEAT_INCOMPAT_ZONED | \
+		 XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)
 
 #define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL
 static inline bool
@@ -952,7 +959,12 @@ struct xfs_dinode {
 	__be64		di_changecount;	/* number of attribute changes */
 	__be64		di_lsn;		/* flush sequence */
 	__be64		di_flags2;	/* more random flags */
-	__be32		di_cowextsize;	/* basic cow extent size for file */
+	union {
+		/* basic cow extent size for (regular) file */
+		__be32		di_cowextsize;
+		/* used blocks in RTG for (zoned) rtrmap inode */
+		__be32		di_used_blocks;
+	};
 	__u8		di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index 2c3171262b44..12463ba766da 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -189,7 +189,9 @@ struct xfs_fsop_geom {
 	uint32_t	checked;	/* o: checked fs & rt metadata	*/
 	__u32		rgextents;	/* rt extents in a realtime group */
 	__u32		rgcount;	/* number of realtime groups	*/
-	__u64		reserved[16];	/* reserved space		*/
+	__u64		rtstart;	/* start of internal rt section */
+	__u64		rtreserved;	/* RT (zoned) reserved blocks	*/
+	__u64		reserved[14];	/* reserved space		*/
 };
 
 #define XFS_FSOP_GEOM_SICK_COUNTERS	(1 << 0)  /* summary counters */
@@ -247,6 +249,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE (1 << 24) /* exchange range */
 #define XFS_FSOP_GEOM_FLAGS_PARENT	(1 << 25) /* linux parent pointers */
 #define XFS_FSOP_GEOM_FLAGS_METADIR	(1 << 26) /* metadata directories */
+#define XFS_FSOP_GEOM_FLAGS_ZONED	(1 << 27) /* zoned rt device */
 
 /*
  * Minimum and maximum sizes need for growth checks.
@@ -1079,6 +1082,15 @@ struct xfs_rtgroup_geometry {
 #define XFS_IOC_COMMIT_RANGE	     _IOW ('X', 131, struct xfs_commit_range)
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */
 
+/*
+ * Devices supported by a single XFS file system.  Reported in fsmaps fmr_device
+ * when using internal RT devices.
+ */
+enum xfs_device {
+	XFS_DEV_DATA	= 1,
+	XFS_DEV_LOG	= 2,
+	XFS_DEV_RT	= 3,
+};
 
 #ifndef HAVE_BBMACROS
 /*
diff --git a/fs/xfs/libxfs/xfs_group.h b/fs/xfs/libxfs/xfs_group.h
index 242b05627c7a..4423932a2313 100644
--- a/fs/xfs/libxfs/xfs_group.h
+++ b/fs/xfs/libxfs/xfs_group.h
@@ -19,10 +19,23 @@ struct xfs_group {
 #ifdef __KERNEL__
 	/* -- kernel only structures below this line -- */
 
-	/*
-	 * Track freed but not yet committed extents.
-	 */
-	struct xfs_extent_busy_tree *xg_busy_extents;
+	union {
+		/*
+		 * For perags and non-zoned RT groups:
+		 * Track freed but not yet committed extents.
+		 */
+		struct xfs_extent_busy_tree	*xg_busy_extents;
+
+		/*
+		 * For zoned RT groups:
+		 * List of groups that need a zone reset.
+		 *
+		 * The zonegc code forces a log flush of the rtrmap inode before
+		 * resetting the write pointer, so there is no need for
+		 * individual busy extent tracking.
+		 */
+		struct xfs_group		*xg_next_reset;
+	};
 
 	/*
 	 * Bitsets of per-ag metadata that have been checked and/or are sick.
@@ -107,9 +120,15 @@ xfs_gbno_to_daddr(
 	xfs_agblock_t		gbno)
 {
 	struct xfs_mount	*mp = xg->xg_mount;
-	uint32_t		blocks = mp->m_groups[xg->xg_type].blocks;
+	struct xfs_groups	*g = &mp->m_groups[xg->xg_type];
+	xfs_fsblock_t		fsbno;
+
+	if (g->has_daddr_gaps)
+		fsbno = xfs_gbno_to_fsb(xg, gbno);
+	else
+		fsbno = (xfs_fsblock_t)xg->xg_gno * g->blocks + gbno;
 
-	return XFS_FSB_TO_BB(mp, (xfs_fsblock_t)xg->xg_gno * blocks + gbno);
+	return XFS_FSB_TO_BB(mp, g->start_fsb + fsbno);
 }
 
 static inline uint32_t
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f3a840a425f5..57513ba19d6a 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1927,7 +1927,7 @@ xfs_dialloc(
 	 * that we can immediately allocate, but then we allow allocation on the
 	 * second pass if we fail to find an AG with free inodes in it.
 	 */
-	if (percpu_counter_read_positive(&mp->m_fdblocks) <
+	if (xfs_estimate_freecounter(mp, XC_FREE_BLOCKS) <
 			mp->m_low_space[XFS_LOWSP_1_PCNT]) {
 		ok_alloc = false;
 		low_space = true;
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index f24fa628fecf..992e6d337709 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -252,7 +252,10 @@ xfs_inode_from_disk(
 					   be64_to_cpu(from->di_changecount));
 		ip->i_crtime = xfs_inode_from_disk_ts(from, from->di_crtime);
 		ip->i_diflags2 = be64_to_cpu(from->di_flags2);
+		/* also covers the di_used_blocks union arm: */
 		ip->i_cowextsize = be32_to_cpu(from->di_cowextsize);
+		BUILD_BUG_ON(sizeof(from->di_cowextsize) !=
+			     sizeof(from->di_used_blocks));
 	}
 
 	error = xfs_iformat_data_fork(ip, from);
@@ -349,6 +352,7 @@ xfs_inode_to_disk(
 		to->di_changecount = cpu_to_be64(inode_peek_iversion(inode));
 		to->di_crtime = xfs_inode_to_disk_ts(ip, ip->i_crtime);
 		to->di_flags2 = cpu_to_be64(ip->i_diflags2);
+		/* also covers the di_used_blocks union arm: */
 		to->di_cowextsize = cpu_to_be32(ip->i_cowextsize);
 		to->di_ino = cpu_to_be64(ip->i_ino);
 		to->di_lsn = cpu_to_be64(lsn);
@@ -752,11 +756,18 @@ xfs_dinode_verify(
 	    !xfs_has_rtreflink(mp))
 		return __this_address;
 
-	/* COW extent size hint validation */
-	fa = xfs_inode_validate_cowextsize(mp, be32_to_cpu(dip->di_cowextsize),
-			mode, flags, flags2);
-	if (fa)
-		return fa;
+	if (xfs_has_zoned(mp) &&
+	    dip->di_metatype == cpu_to_be16(XFS_METAFILE_RTRMAP)) {
+		if (be32_to_cpu(dip->di_used_blocks) > mp->m_sb.sb_rgextents)
+			return __this_address;
+	} else {
+		/* COW extent size hint validation */
+		fa = xfs_inode_validate_cowextsize(mp,
+				be32_to_cpu(dip->di_cowextsize),
+				mode, flags, flags2);
+		if (fa)
+			return fa;
+	}
 
 	/* bigtime iflag can only happen on bigtime filesystems */
 	if (xfs_dinode_has_bigtime(dip) &&
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
index deb0b7c00a1f..48fe49a5f050 100644
--- a/fs/xfs/libxfs/xfs_inode_util.c
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -322,6 +322,7 @@ xfs_inode_init(
 
 	if (xfs_has_v3inodes(mp)) {
 		inode_set_iversion(inode, 1);
+		/* also covers the di_used_blocks union arm: */
 		ip->i_cowextsize = 0;
 		times |= XFS_ICHGTIME_CREATE;
 	}
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index a472ac2e45d0..0d637c276db0 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -475,7 +475,12 @@ struct xfs_log_dinode {
 	xfs_lsn_t	di_lsn;
 
 	uint64_t	di_flags2;	/* more random flags */
-	uint32_t	di_cowextsize;	/* basic cow extent size for file */
+	union {
+		/* basic cow extent size for (regular) file */
+		uint32_t		di_cowextsize;
+		/* used blocks in RTG for (zoned) rtrmap inode */
+		uint32_t		di_used_blocks;
+	};
 	uint8_t		di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
diff --git a/fs/xfs/libxfs/xfs_metafile.c b/fs/xfs/libxfs/xfs_metafile.c
index 2f5f554a36d4..225923e463c4 100644
--- a/fs/xfs/libxfs/xfs_metafile.c
+++ b/fs/xfs/libxfs/xfs_metafile.c
@@ -21,6 +21,9 @@
 #include "xfs_errortag.h"
 #include "xfs_error.h"
 #include "xfs_alloc.h"
+#include "xfs_rtgroup.h"
+#include "xfs_rtrmap_btree.h"
+#include "xfs_rtrefcount_btree.h"
 
 static const struct {
 	enum xfs_metafile_type	mtype;
@@ -74,12 +77,11 @@ xfs_metafile_clear_iflag(
 }
 
 /*
- * Is the amount of space that could be allocated towards a given metadata
- * file at or beneath a certain threshold?
+ * Is the metafile reservations at or beneath a certain threshold?
  */
 static inline bool
 xfs_metafile_resv_can_cover(
-	struct xfs_inode	*ip,
+	struct xfs_mount	*mp,
 	int64_t			rhs)
 {
 	/*
@@ -88,43 +90,38 @@ xfs_metafile_resv_can_cover(
 	 * global free block count.  Take care of the first case to avoid
 	 * touching the per-cpu counter.
 	 */
-	if (ip->i_delayed_blks >= rhs)
+	if (mp->m_metafile_resv_avail >= rhs)
 		return true;
 
 	/*
 	 * There aren't enough blocks left in the inode's reservation, but it
 	 * isn't critical unless there also isn't enough free space.
 	 */
-	return __percpu_counter_compare(&ip->i_mount->m_fdblocks,
-			rhs - ip->i_delayed_blks, 2048) >= 0;
+	return xfs_compare_freecounter(mp, XC_FREE_BLOCKS,
+			rhs - mp->m_metafile_resv_avail, 2048) >= 0;
 }
 
 /*
- * Is this metadata file critically low on blocks?  For now we'll define that
- * as the number of blocks we can get our hands on being less than 10% of what
- * we reserved or less than some arbitrary number (maximum btree height).
+ * Is the metafile reservation critically low on blocks?  For now we'll define
+ * that as the number of blocks we can get our hands on being less than 10% of
+ * what we reserved or less than some arbitrary number (maximum btree height).
  */
 bool
 xfs_metafile_resv_critical(
-	struct xfs_inode	*ip)
+	struct xfs_mount	*mp)
 {
-	uint64_t		asked_low_water;
+	ASSERT(xfs_has_metadir(mp));
 
-	if (!ip)
-		return false;
-
-	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_critical(ip, 0);
+	trace_xfs_metafile_resv_critical(mp, 0);
 
-	if (!xfs_metafile_resv_can_cover(ip, ip->i_mount->m_rtbtree_maxlevels))
+	if (!xfs_metafile_resv_can_cover(mp, mp->m_rtbtree_maxlevels))
 		return true;
 
-	asked_low_water = div_u64(ip->i_meta_resv_asked, 10);
-	if (!xfs_metafile_resv_can_cover(ip, asked_low_water))
+	if (!xfs_metafile_resv_can_cover(mp,
+			div_u64(mp->m_metafile_resv_target, 10)))
 		return true;
 
-	return XFS_TEST_ERROR(false, ip->i_mount,
-			XFS_ERRTAG_METAFILE_RESV_CRITICAL);
+	return XFS_TEST_ERROR(false, mp, XFS_ERRTAG_METAFILE_RESV_CRITICAL);
 }
 
 /* Allocate a block from the metadata file's reservation. */
@@ -133,22 +130,24 @@ xfs_metafile_resv_alloc_space(
 	struct xfs_inode	*ip,
 	struct xfs_alloc_arg	*args)
 {
+	struct xfs_mount	*mp = ip->i_mount;
 	int64_t			len = args->len;
 
 	ASSERT(xfs_is_metadir_inode(ip));
 	ASSERT(args->resv == XFS_AG_RESV_METAFILE);
 
-	trace_xfs_metafile_resv_alloc_space(ip, args->len);
+	trace_xfs_metafile_resv_alloc_space(mp, args->len);
 
 	/*
 	 * Allocate the blocks from the metadata inode's block reservation
 	 * and update the ondisk sb counter.
 	 */
-	if (ip->i_delayed_blks > 0) {
+	mutex_lock(&mp->m_metafile_resv_lock);
+	if (mp->m_metafile_resv_avail > 0) {
 		int64_t		from_resv;
 
-		from_resv = min_t(int64_t, len, ip->i_delayed_blks);
-		ip->i_delayed_blks -= from_resv;
+		from_resv = min_t(int64_t, len, mp->m_metafile_resv_avail);
+		mp->m_metafile_resv_avail -= from_resv;
 		xfs_mod_delalloc(ip, 0, -from_resv);
 		xfs_trans_mod_sb(args->tp, XFS_TRANS_SB_RES_FDBLOCKS,
 				-from_resv);
@@ -175,6 +174,9 @@ xfs_metafile_resv_alloc_space(
 		xfs_trans_mod_sb(args->tp, field, -len);
 	}
 
+	mp->m_metafile_resv_used += args->len;
+	mutex_unlock(&mp->m_metafile_resv_lock);
+
 	ip->i_nblocks += args->len;
 	xfs_trans_log_inode(args->tp, ip, XFS_ILOG_CORE);
 }
@@ -186,26 +188,33 @@ xfs_metafile_resv_free_space(
 	struct xfs_trans	*tp,
 	xfs_filblks_t		len)
 {
+	struct xfs_mount	*mp = ip->i_mount;
 	int64_t			to_resv;
 
 	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_free_space(ip, len);
+
+	trace_xfs_metafile_resv_free_space(mp, len);
 
 	ip->i_nblocks -= len;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
+	mutex_lock(&mp->m_metafile_resv_lock);
+	mp->m_metafile_resv_used -= len;
+
 	/*
 	 * Add the freed blocks back into the inode's delalloc reservation
 	 * until it reaches the maximum size.  Update the ondisk fdblocks only.
 	 */
-	to_resv = ip->i_meta_resv_asked - (ip->i_nblocks + ip->i_delayed_blks);
+	to_resv = mp->m_metafile_resv_target -
+		(mp->m_metafile_resv_used + mp->m_metafile_resv_avail);
 	if (to_resv > 0) {
 		to_resv = min_t(int64_t, to_resv, len);
-		ip->i_delayed_blks += to_resv;
+		mp->m_metafile_resv_avail += to_resv;
 		xfs_mod_delalloc(ip, 0, to_resv);
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FDBLOCKS, to_resv);
 		len -= to_resv;
 	}
+	mutex_unlock(&mp->m_metafile_resv_lock);
 
 	/*
 	 * Everything else goes back to the filesystem, so update the in-core
@@ -215,61 +224,99 @@ xfs_metafile_resv_free_space(
 		xfs_trans_mod_sb(tp, XFS_TRANS_SB_FDBLOCKS, len);
 }
 
-/* Release a metadata file's space reservation. */
+static void
+__xfs_metafile_resv_free(
+	struct xfs_mount	*mp)
+{
+	if (mp->m_metafile_resv_avail) {
+		xfs_mod_sb_delalloc(mp, -(int64_t)mp->m_metafile_resv_avail);
+		xfs_add_fdblocks(mp, mp->m_metafile_resv_avail);
+	}
+	mp->m_metafile_resv_avail = 0;
+	mp->m_metafile_resv_used = 0;
+	mp->m_metafile_resv_target = 0;
+}
+
+/* Release unused metafile space reservation. */
 void
 xfs_metafile_resv_free(
-	struct xfs_inode	*ip)
+	struct xfs_mount	*mp)
 {
-	/* Non-btree metadata inodes don't need space reservations. */
-	if (!ip || !ip->i_meta_resv_asked)
+	if (!xfs_has_metadir(mp))
 		return;
 
-	ASSERT(xfs_is_metadir_inode(ip));
-	trace_xfs_metafile_resv_free(ip, 0);
+	trace_xfs_metafile_resv_free(mp, 0);
 
-	if (ip->i_delayed_blks) {
-		xfs_mod_delalloc(ip, 0, -ip->i_delayed_blks);
-		xfs_add_fdblocks(ip->i_mount, ip->i_delayed_blks);
-		ip->i_delayed_blks = 0;
-	}
-	ip->i_meta_resv_asked = 0;
+	mutex_lock(&mp->m_metafile_resv_lock);
+	__xfs_metafile_resv_free(mp);
+	mutex_unlock(&mp->m_metafile_resv_lock);
 }
 
-/* Set up a metadata file's space reservation. */
+/* Set up a metafile space reservation. */
 int
 xfs_metafile_resv_init(
-	struct xfs_inode	*ip,
-	xfs_filblks_t		ask)
+	struct xfs_mount	*mp)
 {
+	struct xfs_rtgroup	*rtg = NULL;
+	xfs_filblks_t		used = 0, target = 0;
 	xfs_filblks_t		hidden_space;
-	xfs_filblks_t		used;
-	int			error;
+	xfs_rfsblock_t		dblocks_avail = mp->m_sb.sb_dblocks / 4;
+	int			error = 0;
 
-	if (!ip || ip->i_meta_resv_asked > 0)
+	if (!xfs_has_metadir(mp))
 		return 0;
 
-	ASSERT(xfs_is_metadir_inode(ip));
+	/*
+	 * Free any previous reservation to have a clean slate.
+	 */
+	mutex_lock(&mp->m_metafile_resv_lock);
+	__xfs_metafile_resv_free(mp);
+
+	/*
+	 * Currently the only btree metafiles that require reservations are the
+	 * rtrmap and the rtrefcount.  Anything new will have to be added here
+	 * as well.
+	 */
+	while ((rtg = xfs_rtgroup_next(mp, rtg))) {
+		if (xfs_has_rtrmapbt(mp)) {
+			used += rtg_rmap(rtg)->i_nblocks;
+			target += xfs_rtrmapbt_calc_reserves(mp);
+		}
+		if (xfs_has_rtreflink(mp)) {
+			used += rtg_refcount(rtg)->i_nblocks;
+			target += xfs_rtrefcountbt_calc_reserves(mp);
+		}
+	}
+
+	if (!target)
+		goto out_unlock;
 
 	/*
-	 * Space taken by all other metadata btrees are accounted on-disk as
+	 * Space taken by the per-AG metadata btrees are accounted on-disk as
 	 * used space.  We therefore only hide the space that is reserved but
 	 * not used by the trees.
 	 */
-	used = ip->i_nblocks;
-	if (used > ask)
-		ask = used;
-	hidden_space = ask - used;
+	if (used > target)
+		target = used;
+	else if (target > dblocks_avail)
+		target = dblocks_avail;
+	hidden_space = target - used;
 
-	error = xfs_dec_fdblocks(ip->i_mount, hidden_space, true);
+	error = xfs_dec_fdblocks(mp, hidden_space, true);
 	if (error) {
-		trace_xfs_metafile_resv_init_error(ip, error, _RET_IP_);
-		return error;
+		trace_xfs_metafile_resv_init_error(mp, 0);
+		goto out_unlock;
 	}
 
-	xfs_mod_delalloc(ip, 0, hidden_space);
-	ip->i_delayed_blks = hidden_space;
-	ip->i_meta_resv_asked = ask;
+	xfs_mod_sb_delalloc(mp, hidden_space);
+
+	mp->m_metafile_resv_target = target;
+	mp->m_metafile_resv_used = used;
+	mp->m_metafile_resv_avail = hidden_space;
+
+	trace_xfs_metafile_resv_init(mp, target);
 
-	trace_xfs_metafile_resv_init(ip, ask);
-	return 0;
+out_unlock:
+	mutex_unlock(&mp->m_metafile_resv_lock);
+	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_metafile.h b/fs/xfs/libxfs/xfs_metafile.h
index 95af4b52e5a7..ae6f9e779b98 100644
--- a/fs/xfs/libxfs/xfs_metafile.h
+++ b/fs/xfs/libxfs/xfs_metafile.h
@@ -26,13 +26,13 @@ void xfs_metafile_clear_iflag(struct xfs_trans *tp, struct xfs_inode *ip);
 /* Space reservations for metadata inodes. */
 struct xfs_alloc_arg;
 
-bool xfs_metafile_resv_critical(struct xfs_inode *ip);
+bool xfs_metafile_resv_critical(struct xfs_mount *mp);
 void xfs_metafile_resv_alloc_space(struct xfs_inode *ip,
 		struct xfs_alloc_arg *args);
 void xfs_metafile_resv_free_space(struct xfs_inode *ip, struct xfs_trans *tp,
 		xfs_filblks_t len);
-void xfs_metafile_resv_free(struct xfs_inode *ip);
-int xfs_metafile_resv_init(struct xfs_inode *ip, xfs_filblks_t ask);
+void xfs_metafile_resv_free(struct xfs_mount *mp);
+int xfs_metafile_resv_init(struct xfs_mount *mp);
 
 /* Code specific to kernel/userspace; must be provided externally. */
 
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index a85ecddaa48e..5ed44fdf7491 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -233,8 +233,8 @@ xfs_check_ondisk_structs(void)
 			16299260424LL);
 
 	/* superblock field checks we got from xfs/122 */
-	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,		288);
-	XFS_CHECK_STRUCT_SIZE(struct xfs_sb,		288);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_dsb,		304);
+	XFS_CHECK_STRUCT_SIZE(struct xfs_sb,		304);
 	XFS_CHECK_SB_OFFSET(sb_magicnum,		0);
 	XFS_CHECK_SB_OFFSET(sb_blocksize,		4);
 	XFS_CHECK_SB_OFFSET(sb_dblocks,			8);
@@ -295,6 +295,8 @@ xfs_check_ondisk_structs(void)
 	XFS_CHECK_SB_OFFSET(sb_rgextents,		276);
 	XFS_CHECK_SB_OFFSET(sb_rgblklog,		280);
 	XFS_CHECK_SB_OFFSET(sb_pad,			281);
+	XFS_CHECK_SB_OFFSET(sb_rtstart,			288);
+	XFS_CHECK_SB_OFFSET(sb_rtreserved,		296);
 }
 
 #endif /* __XFS_ONDISK_H */
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index 770adf60dd73..5057536e586c 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -1123,6 +1123,7 @@ xfs_rtfree_blocks(
 	xfs_extlen_t		mod;
 	int			error;
 
+	ASSERT(!xfs_has_zoned(mp));
 	ASSERT(rtlen <= XFS_MAX_BMBT_EXTLEN);
 
 	mod = xfs_blen_to_rtxoff(mp, rtlen);
@@ -1174,6 +1175,9 @@ xfs_rtalloc_query_range(
 
 	end = min(end, rtg->rtg_extents - 1);
 
+	if (xfs_has_zoned(mp))
+		return -EINVAL;
+
 	/* Iterate the bitmap, looking for discrepancies. */
 	while (start <= end) {
 		struct xfs_rtalloc_rec	rec;
@@ -1268,6 +1272,8 @@ xfs_rtbitmap_blockcount_len(
 	struct xfs_mount	*mp,
 	xfs_rtbxlen_t		rtextents)
 {
+	if (xfs_has_zoned(mp))
+		return 0;
 	return howmany_64(rtextents, xfs_rtbitmap_rtx_per_rbmblock(mp));
 }
 
@@ -1308,6 +1314,11 @@ xfs_rtsummary_blockcount(
 	xfs_rtbxlen_t		rextents = xfs_rtbitmap_bitcount(mp);
 	unsigned long long	rsumwords;
 
+	if (xfs_has_zoned(mp)) {
+		*rsumlevels = 0;
+		return 0;
+	}
+
 	*rsumlevels = xfs_compute_rextslog(rextents) + 1;
 	rsumwords = xfs_rtbitmap_blockcount_len(mp, rextents) * (*rsumlevels);
 	return howmany_64(rsumwords, mp->m_blockwsize);
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index d84d32f1b48f..9186c58e83d5 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -194,15 +194,17 @@ xfs_rtgroup_lock(
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) ||
 	       !(rtglock_flags & XFS_RTGLOCK_BITMAP));
 
-	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
-		/*
-		 * Lock both realtime free space metadata inodes for a freespace
-		 * update.
-		 */
-		xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
-		xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL);
-	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
-		xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+	if (!xfs_has_zoned(rtg_mount(rtg))) {
+		if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+			/*
+			 * Lock both realtime free space metadata inodes for a
+			 * freespace update.
+			 */
+			xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
+			xfs_ilock(rtg_summary(rtg), XFS_ILOCK_EXCL);
+		} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+			xfs_ilock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+		}
 	}
 
 	if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
@@ -228,11 +230,13 @@ xfs_rtgroup_unlock(
 	if ((rtglock_flags & XFS_RTGLOCK_RMAP) && rtg_rmap(rtg))
 		xfs_iunlock(rtg_rmap(rtg), XFS_ILOCK_EXCL);
 
-	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
-		xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL);
-		xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
-	} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
-		xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+	if (!xfs_has_zoned(rtg_mount(rtg))) {
+		if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+			xfs_iunlock(rtg_summary(rtg), XFS_ILOCK_EXCL);
+			xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_EXCL);
+		} else if (rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED) {
+			xfs_iunlock(rtg_bitmap(rtg), XFS_ILOCK_SHARED);
+		}
 	}
 }
 
@@ -249,7 +253,8 @@ xfs_rtgroup_trans_join(
 	ASSERT(!(rtglock_flags & ~XFS_RTGLOCK_ALL_FLAGS));
 	ASSERT(!(rtglock_flags & XFS_RTGLOCK_BITMAP_SHARED));
 
-	if (rtglock_flags & XFS_RTGLOCK_BITMAP) {
+	if (!xfs_has_zoned(rtg_mount(rtg)) &&
+	    (rtglock_flags & XFS_RTGLOCK_BITMAP)) {
 		xfs_trans_ijoin(tp, rtg_bitmap(rtg), XFS_ILOCK_EXCL);
 		xfs_trans_ijoin(tp, rtg_summary(rtg), XFS_ILOCK_EXCL);
 	}
@@ -270,7 +275,7 @@ xfs_rtgroup_get_geometry(
 	/* Fill out form. */
 	memset(rgeo, 0, sizeof(*rgeo));
 	rgeo->rg_number = rtg_rgno(rtg);
-	rgeo->rg_length = rtg_group(rtg)->xg_block_count;
+	rgeo->rg_length = rtg_blocks(rtg);
 	xfs_rtgroup_geom_health(rtg, rgeo);
 	return 0;
 }
@@ -354,6 +359,7 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 		.sick		= XFS_SICK_RG_BITMAP,
 		.fmt_mask	= (1U << XFS_DINODE_FMT_EXTENTS) |
 				  (1U << XFS_DINODE_FMT_BTREE),
+		.enabled	= xfs_has_nonzoned,
 		.create		= xfs_rtbitmap_create,
 	},
 	[XFS_RTGI_SUMMARY] = {
@@ -362,6 +368,7 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 		.sick		= XFS_SICK_RG_SUMMARY,
 		.fmt_mask	= (1U << XFS_DINODE_FMT_EXTENTS) |
 				  (1U << XFS_DINODE_FMT_BTREE),
+		.enabled	= xfs_has_nonzoned,
 		.create		= xfs_rtsummary_create,
 	},
 	[XFS_RTGI_RMAP] = {
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 03f39d4e43fc..d36a6ae0abe5 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -37,15 +37,33 @@ struct xfs_rtgroup {
 	xfs_rtxnum_t		rtg_extents;
 
 	/*
-	 * Cache of rt summary level per bitmap block with the invariant that
-	 * rtg_rsum_cache[bbno] > the maximum i for which rsum[i][bbno] != 0,
-	 * or 0 if rsum[i][bbno] == 0 for all i.
-	 *
+	 * For bitmap based RT devices this points to a cache of rt summary
+	 * level per bitmap block with the invariant that rtg_rsum_cache[bbno]
+	 * > the maximum i for which rsum[i][bbno] != 0, or 0 if
+	 * rsum[i][bbno] == 0 for all i.
 	 * Reads and writes are serialized by the rsumip inode lock.
+	 *
+	 * For zoned RT devices this points to the open zone structure for
+	 * a group that is open for writers, or is NULL.
 	 */
-	uint8_t			*rtg_rsum_cache;
+	union {
+		uint8_t			*rtg_rsum_cache;
+		struct xfs_open_zone	*rtg_open_zone;
+	};
 };
 
+/*
+ * For zoned RT devices this is set on groups that have no written blocks
+ * and can be picked by the allocator for opening.
+ */
+#define XFS_RTG_FREE			XA_MARK_0
+
+/*
+ * For zoned RT devices this is set on groups that are fully written and that
+ * have unused blocks.  Used by the garbage collection to pick targets.
+ */
+#define XFS_RTG_RECLAIMABLE		XA_MARK_1
+
 static inline struct xfs_rtgroup *to_rtg(struct xfs_group *xg)
 {
 	return container_of(xg, struct xfs_rtgroup, rtg_group);
@@ -66,6 +84,11 @@ static inline xfs_rgnumber_t rtg_rgno(const struct xfs_rtgroup *rtg)
 	return rtg->rtg_group.xg_gno;
 }
 
+static inline xfs_rgblock_t rtg_blocks(const struct xfs_rtgroup *rtg)
+{
+	return rtg->rtg_group.xg_block_count;
+}
+
 static inline struct xfs_inode *rtg_bitmap(const struct xfs_rtgroup *rtg)
 {
 	return rtg->rtg_inodes[XFS_RTGI_BITMAP];
@@ -222,10 +245,14 @@ xfs_rtb_to_daddr(
 	xfs_rtblock_t		rtbno)
 {
 	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
-	xfs_rgnumber_t		rgno = xfs_rtb_to_rgno(mp, rtbno);
-	uint64_t		start_bno = (xfs_rtblock_t)rgno * g->blocks;
 
-	return XFS_FSB_TO_BB(mp, start_bno + (rtbno & g->blkmask));
+	if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) {
+		xfs_rgnumber_t	rgno = xfs_rtb_to_rgno(mp, rtbno);
+
+		rtbno = (xfs_rtblock_t)rgno * g->blocks + (rtbno & g->blkmask);
+	}
+
+	return XFS_FSB_TO_BB(mp, g->start_fsb + rtbno);
 }
 
 static inline xfs_rtblock_t
@@ -233,10 +260,11 @@ xfs_daddr_to_rtb(
 	struct xfs_mount	*mp,
 	xfs_daddr_t		daddr)
 {
-	xfs_rfsblock_t		bno = XFS_BB_TO_FSBT(mp, daddr);
+	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	xfs_rfsblock_t		bno;
 
-	if (xfs_has_rtgroups(mp)) {
-		struct xfs_groups *g = &mp->m_groups[XG_TYPE_RTG];
+	bno = XFS_BB_TO_FSBT(mp, daddr) - g->start_fsb;
+	if (xfs_has_rtgroups(mp) && !g->has_daddr_gaps) {
 		xfs_rgnumber_t	rgno;
 		uint32_t	rgbno;
 
diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c
index e4ec36943cb7..9bdc2cbfc113 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c
@@ -1033,3 +1033,22 @@ xfs_rtrmapbt_init_rtsb(
 	xfs_btree_del_cursor(cur, error);
 	return error;
 }
+
+/*
+ * Return the highest rgbno currently tracked by the rmap for this rtg.
+ */
+xfs_rgblock_t
+xfs_rtrmap_highest_rgbno(
+	struct xfs_rtgroup	*rtg)
+{
+	struct xfs_btree_block	*block = rtg_rmap(rtg)->i_df.if_broot;
+	union xfs_btree_key	key = {};
+	struct xfs_btree_cur	*cur;
+
+	if (block->bb_numrecs == 0)
+		return NULLRGBLOCK;
+	cur = xfs_rtrmapbt_init_cursor(NULL, rtg);
+	xfs_btree_get_keys(cur, block, &key);
+	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
+	return be32_to_cpu(key.__rmap_bigkey[1].rm_startblock);
+}
diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.h b/fs/xfs/libxfs/xfs_rtrmap_btree.h
index 9d0915089891..e328fd62a149 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.h
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.h
@@ -207,4 +207,6 @@ struct xfs_btree_cur *xfs_rtrmapbt_mem_cursor(struct xfs_rtgroup *rtg,
 int xfs_rtrmapbt_mem_init(struct xfs_mount *mp, struct xfbtree *xfbtree,
 		struct xfs_buftarg *btp, xfs_rgnumber_t rgno);
 
+xfs_rgblock_t xfs_rtrmap_highest_rgbno(struct xfs_rtgroup *rtg);
+
 #endif /* __XFS_RTRMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 3dc5f5dba162..e42bfd04a7c6 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -30,6 +30,7 @@
 #include "xfs_rtgroup.h"
 #include "xfs_rtrmap_btree.h"
 #include "xfs_rtrefcount_btree.h"
+#include "xfs_rtbitmap.h"
 
 /*
  * Physical superblock buffer manipulations. Shared with libxfs in userspace.
@@ -185,6 +186,8 @@ xfs_sb_version_to_features(
 		features |= XFS_FEAT_PARENT;
 	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)
 		features |= XFS_FEAT_METADIR;
+	if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)
+		features |= XFS_FEAT_ZONED;
 
 	return features;
 }
@@ -266,6 +269,9 @@ static uint64_t
 xfs_expected_rbmblocks(
 	struct xfs_sb		*sbp)
 {
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED))
+		return 0;
 	return howmany_64(xfs_extents_per_rbm(sbp),
 			  NBBY * xfs_rtbmblock_size(sbp));
 }
@@ -275,9 +281,15 @@ bool
 xfs_validate_rt_geometry(
 	struct xfs_sb		*sbp)
 {
-	if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
-	    sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)
-		return false;
+	if (xfs_sb_is_v5(sbp) &&
+	    (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED)) {
+		if (sbp->sb_rextsize != 1)
+			return false;
+	} else {
+		if (sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE ||
+		    sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE)
+			return false;
+	}
 
 	if (sbp->sb_rblocks == 0) {
 		if (sbp->sb_rextents != 0 || sbp->sb_rbmblocks != 0 ||
@@ -435,6 +447,34 @@ xfs_validate_sb_rtgroups(
 	return 0;
 }
 
+static int
+xfs_validate_sb_zoned(
+	struct xfs_mount	*mp,
+	struct xfs_sb		*sbp)
+{
+	if (sbp->sb_frextents != 0) {
+		xfs_warn(mp,
+"sb_frextents must be zero for zoned file systems.");
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rtstart && sbp->sb_rtstart < sbp->sb_dblocks) {
+		xfs_warn(mp,
+"sb_rtstart (%lld) overlaps sb_dblocks (%lld).",
+			sbp->sb_rtstart, sbp->sb_dblocks);
+		return -EINVAL;
+	}
+
+	if (sbp->sb_rtreserved && sbp->sb_rtreserved >= sbp->sb_rblocks) {
+		xfs_warn(mp,
+"sb_rtreserved (%lld) larger than sb_rblocks (%lld).",
+			sbp->sb_rtreserved, sbp->sb_rblocks);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 /* Check the validity of the SB. */
 STATIC int
 xfs_validate_sb_common(
@@ -523,6 +563,11 @@ xfs_validate_sb_common(
 			if (error)
 				return error;
 		}
+		if (sbp->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+			error = xfs_validate_sb_zoned(mp, sbp);
+			if (error)
+				return error;
+		}
 	} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
 				XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
 			xfs_notice(mp,
@@ -835,6 +880,14 @@ __xfs_sb_from_disk(
 		to->sb_rgcount = 1;
 		to->sb_rgextents = 0;
 	}
+
+	if (to->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+		to->sb_rtstart = be64_to_cpu(from->sb_rtstart);
+		to->sb_rtreserved = be64_to_cpu(from->sb_rtreserved);
+	} else {
+		to->sb_rtstart = 0;
+		to->sb_rtreserved = 0;
+	}
 }
 
 void
@@ -1001,6 +1054,11 @@ xfs_sb_to_disk(
 		to->sb_rbmino = cpu_to_be64(0);
 		to->sb_rsumino = cpu_to_be64(0);
 	}
+
+	if (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_ZONED) {
+		to->sb_rtstart = cpu_to_be64(from->sb_rtstart);
+		to->sb_rtreserved = cpu_to_be64(from->sb_rtreserved);
+	}
 }
 
 /*
@@ -1146,6 +1204,10 @@ xfs_sb_mount_rextsize(
 		rgs->blocks = sbp->sb_rgextents * sbp->sb_rextsize;
 		rgs->blklog = mp->m_sb.sb_rgblklog;
 		rgs->blkmask = xfs_mask32lo(mp->m_sb.sb_rgblklog);
+		rgs->start_fsb = mp->m_sb.sb_rtstart;
+		if (xfs_sb_has_incompat_feature(sbp,
+				XFS_SB_FEAT_INCOMPAT_ZONE_GAPS))
+			rgs->has_daddr_gaps = true;
 	} else {
 		rgs->blocks = 0;
 		rgs->blklog = 0;
@@ -1265,8 +1327,7 @@ xfs_log_sb(
 		mp->m_sb.sb_ifree = min_t(uint64_t,
 				percpu_counter_sum_positive(&mp->m_ifree),
 				mp->m_sb.sb_icount);
-		mp->m_sb.sb_fdblocks =
-				percpu_counter_sum_positive(&mp->m_fdblocks);
+		mp->m_sb.sb_fdblocks = xfs_sum_freecounter(mp, XC_FREE_BLOCKS);
 	}
 
 	/*
@@ -1275,9 +1336,10 @@ xfs_log_sb(
 	 * we handle nearly-lockless reservations, so we must use the _positive
 	 * variant here to avoid writing out nonsense frextents.
 	 */
-	if (xfs_has_rtgroups(mp))
+	if (xfs_has_rtgroups(mp) && !xfs_has_zoned(mp)) {
 		mp->m_sb.sb_frextents =
-				percpu_counter_sum_positive(&mp->m_frextents);
+				xfs_sum_freecounter(mp, XC_FREE_RTEXTENTS);
+	}
 
 	xfs_sb_to_disk(bp->b_addr, &mp->m_sb);
 	xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
@@ -1510,6 +1572,8 @@ xfs_fs_geometry(
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_EXCHANGE_RANGE;
 	if (xfs_has_metadir(mp))
 		geo->flags |= XFS_FSOP_GEOM_FLAGS_METADIR;
+	if (xfs_has_zoned(mp))
+		geo->flags |= XFS_FSOP_GEOM_FLAGS_ZONED;
 	geo->rtsectsize = sbp->sb_blocksize;
 	geo->dirblocksize = xfs_dir2_dirblock_bytes(sbp);
 
@@ -1530,6 +1594,10 @@ xfs_fs_geometry(
 		geo->rgcount = sbp->sb_rgcount;
 		geo->rgextents = sbp->sb_rgextents;
 	}
+	if (xfs_has_zoned(mp)) {
+		geo->rtstart = sbp->sb_rtstart;
+		geo->rtreserved = sbp->sb_rtreserved;
+	}
 }
 
 /* Read a secondary superblock. */
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index ca2401c1facd..f6f4f2d4b5db 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -233,6 +233,34 @@ enum xfs_group_type {
 	{ XG_TYPE_AG,	"ag" }, \
 	{ XG_TYPE_RTG,	"rtg" }
 
+enum xfs_free_counter {
+	/*
+	 * Number of free blocks on the data device.
+	 */
+	XC_FREE_BLOCKS,
+
+	/*
+	 * Number of free RT extents on the RT device.
+	 */
+	XC_FREE_RTEXTENTS,
+
+	/*
+	 * Number of available for use RT extents.
+	 *
+	 * This counter only exists for zoned RT device and indicates the number
+	 * of RT extents that can be directly used by writes.  XC_FREE_RTEXTENTS
+	 * also includes blocks that have been written previously and freed, but
+	 * sit in a rtgroup that still needs a zone reset.
+	 */
+	XC_FREE_RTAVAILABLE,
+	XC_FREE_NR,
+};
+
+#define XFS_FREECOUNTER_STR \
+	{ XC_FREE_BLOCKS,		"blocks" }, \
+	{ XC_FREE_RTEXTENTS,		"rtextents" }, \
+	{ XC_FREE_RTAVAILABLE,		"rtavailable" }
+
 /*
  * Type verifier functions
  */
diff --git a/fs/xfs/libxfs/xfs_zones.c b/fs/xfs/libxfs/xfs_zones.c
new file mode 100644
index 000000000000..b0791a71931c
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_zones.c
@@ -0,0 +1,186 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023-2025 Christoph Hellwig.
+ * Copyright (c) 2024-2025, Western Digital Corporation or its affiliates.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_rtgroup.h"
+#include "xfs_zones.h"
+
+static bool
+xfs_zone_validate_empty(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	if (rtg_rmap(rtg)->i_used_blocks > 0) {
+		xfs_warn(mp, "empty zone %u has non-zero used counter (0x%x).",
+			 rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks);
+		return false;
+	}
+
+	*write_pointer = 0;
+	return true;
+}
+
+static bool
+xfs_zone_validate_wp(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	xfs_rtblock_t		wp_fsb = xfs_daddr_to_rtb(mp, zone->wp);
+
+	if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) {
+		xfs_warn(mp, "zone %u has too large used counter (0x%x).",
+			 rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks);
+		return false;
+	}
+
+	if (xfs_rtb_to_rgno(mp, wp_fsb) != rtg_rgno(rtg)) {
+		xfs_warn(mp, "zone %u write pointer (0x%llx) outside of zone.",
+			 rtg_rgno(rtg), wp_fsb);
+		return false;
+	}
+
+	*write_pointer = xfs_rtb_to_rgbno(mp, wp_fsb);
+	if (*write_pointer >= rtg->rtg_extents) {
+		xfs_warn(mp, "zone %u has invalid write pointer (0x%x).",
+			 rtg_rgno(rtg), *write_pointer);
+		return false;
+	}
+
+	return true;
+}
+
+static bool
+xfs_zone_validate_full(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	if (rtg_rmap(rtg)->i_used_blocks > rtg->rtg_extents) {
+		xfs_warn(mp, "zone %u has too large used counter (0x%x).",
+			 rtg_rgno(rtg), rtg_rmap(rtg)->i_used_blocks);
+		return false;
+	}
+
+	*write_pointer = rtg->rtg_extents;
+	return true;
+}
+
+static bool
+xfs_zone_validate_seq(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_EMPTY:
+		return xfs_zone_validate_empty(zone, rtg, write_pointer);
+	case BLK_ZONE_COND_IMP_OPEN:
+	case BLK_ZONE_COND_EXP_OPEN:
+	case BLK_ZONE_COND_CLOSED:
+		return xfs_zone_validate_wp(zone, rtg, write_pointer);
+	case BLK_ZONE_COND_FULL:
+		return xfs_zone_validate_full(zone, rtg, write_pointer);
+	case BLK_ZONE_COND_NOT_WP:
+	case BLK_ZONE_COND_OFFLINE:
+	case BLK_ZONE_COND_READONLY:
+		xfs_warn(mp, "zone %u has unsupported zone condition 0x%x.",
+			rtg_rgno(rtg), zone->cond);
+		return false;
+	default:
+		xfs_warn(mp, "zone %u has unknown zone condition 0x%x.",
+			rtg_rgno(rtg), zone->cond);
+		return false;
+	}
+}
+
+static bool
+xfs_zone_validate_conv(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+
+	switch (zone->cond) {
+	case BLK_ZONE_COND_NOT_WP:
+		return true;
+	default:
+		xfs_warn(mp,
+"conventional zone %u has unsupported zone condition 0x%x.",
+			 rtg_rgno(rtg), zone->cond);
+		return false;
+	}
+}
+
+bool
+xfs_zone_validate(
+	struct blk_zone		*zone,
+	struct xfs_rtgroup	*rtg,
+	xfs_rgblock_t		*write_pointer)
+{
+	struct xfs_mount	*mp = rtg_mount(rtg);
+	struct xfs_groups	*g = &mp->m_groups[XG_TYPE_RTG];
+	uint32_t		expected_size;
+
+	/*
+	 * Check that the zone capacity matches the rtgroup size stored in the
+	 * superblock.  Note that all zones including the last one must have a
+	 * uniform capacity.
+	 */
+	if (XFS_BB_TO_FSB(mp, zone->capacity) != g->blocks) {
+		xfs_warn(mp,
+"zone %u capacity (0x%llx) does not match RT group size (0x%x).",
+			rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->capacity),
+			g->blocks);
+		return false;
+	}
+
+	if (g->has_daddr_gaps) {
+		expected_size = 1 << g->blklog;
+	} else {
+		if (zone->len != zone->capacity) {
+			xfs_warn(mp,
+"zone %u has capacity != size ((0x%llx vs 0x%llx)",
+				rtg_rgno(rtg),
+				XFS_BB_TO_FSB(mp, zone->len),
+				XFS_BB_TO_FSB(mp, zone->capacity));
+			return false;
+		}
+		expected_size = g->blocks;
+	}
+
+	if (XFS_BB_TO_FSB(mp, zone->len) != expected_size) {
+		xfs_warn(mp,
+"zone %u length (0x%llx) does match geometry (0x%x).",
+			rtg_rgno(rtg), XFS_BB_TO_FSB(mp, zone->len),
+			expected_size);
+	}
+
+	switch (zone->type) {
+	case BLK_ZONE_TYPE_CONVENTIONAL:
+		return xfs_zone_validate_conv(zone, rtg);
+	case BLK_ZONE_TYPE_SEQWRITE_REQ:
+		return xfs_zone_validate_seq(zone, rtg, write_pointer);
+	default:
+		xfs_warn(mp, "zoned %u has unsupported type 0x%x.",
+			rtg_rgno(rtg), zone->type);
+		return false;
+	}
+}
diff --git a/fs/xfs/libxfs/xfs_zones.h b/fs/xfs/libxfs/xfs_zones.h
new file mode 100644
index 000000000000..c4f1367b2cca
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_zones.h
@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LIBXFS_ZONES_H
+#define _LIBXFS_ZONES_H
+
+struct xfs_rtgroup;
+
+/*
+ * In order to guarantee forward progress for GC we need to reserve at least
+ * two zones:  one that will be used for moving data into and one spare zone
+ * making sure that we have enough space to relocate a nearly-full zone.
+ * To allow for slightly sloppy accounting for when we need to reserve the
+ * second zone, we actually reserve three as that is easier than doing fully
+ * accurate bookkeeping.
+ */
+#define XFS_GC_ZONES		3U
+
+/*
+ * In addition we need two zones for user writes, one open zone for writing
+ * and one to still have available blocks without resetting the open zone
+ * when data in the open zone has been freed.
+ */
+#define XFS_RESERVED_ZONES	(XFS_GC_ZONES + 1)
+#define XFS_MIN_ZONES		(XFS_RESERVED_ZONES + 1)
+
+/*
+ * Always keep one zone out of the general open zone pool to allow for GC to
+ * happen while other writers are waiting for free space.
+ */
+#define XFS_OPEN_GC_ZONES	1U
+#define XFS_MIN_OPEN_ZONES	(XFS_OPEN_GC_ZONES + 1U)
+
+bool xfs_zone_validate(struct blk_zone *zone, struct xfs_rtgroup *rtg,
+	xfs_rgblock_t *write_pointer);
+
+#endif /* _LIBXFS_ZONES_H */
diff --git a/fs/xfs/scrub/agheader.c b/fs/xfs/scrub/agheader.c
index 9f8c312dfd3c..303374df44bd 100644
--- a/fs/xfs/scrub/agheader.c
+++ b/fs/xfs/scrub/agheader.c
@@ -69,6 +69,8 @@ STATIC size_t
 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))
diff --git a/fs/xfs/scrub/bmap.c b/fs/xfs/scrub/bmap.c
index 66da7d4d56ba..4f1e2574660d 100644
--- a/fs/xfs/scrub/bmap.c
+++ b/fs/xfs/scrub/bmap.c
@@ -1038,8 +1038,8 @@ xchk_bmap(
 
 	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;
 		}
diff --git a/fs/xfs/scrub/fscounters.c b/fs/xfs/scrub/fscounters.c
index ca23cf4db6c5..e629663e460a 100644
--- a/fs/xfs/scrub/fscounters.c
+++ b/fs/xfs/scrub/fscounters.c
@@ -350,7 +350,7 @@ retry:
 	 * 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
@@ -413,7 +413,13 @@ xchk_fscount_count_frextents(
 
 	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))) {
@@ -513,8 +519,8 @@ xchk_fscounters(
 	/* 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)
@@ -589,15 +595,17 @@ xchk_fscounters(
 			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);
diff --git a/fs/xfs/scrub/fscounters_repair.c b/fs/xfs/scrub/fscounters_repair.c
index cda13447a373..f0d2b04644e4 100644
--- a/fs/xfs/scrub/fscounters_repair.c
+++ b/fs/xfs/scrub/fscounters_repair.c
@@ -64,7 +64,7 @@ xrep_fscounters(
 
 	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
@@ -74,10 +74,12 @@ xrep_fscounters(
 	 * 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;
 }
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index db6edd5a5fe5..bb3f475b6353 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -273,6 +273,13 @@ xchk_inode_cowextsize(
 	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);
diff --git a/fs/xfs/scrub/inode_repair.c b/fs/xfs/scrub/inode_repair.c
index 13ff1c933cb8..4299063ffe87 100644
--- a/fs/xfs/scrub/inode_repair.c
+++ b/fs/xfs/scrub/inode_repair.c
@@ -710,7 +710,9 @@ xrep_dinode_extsize_hints(
 					      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),
diff --git a/fs/xfs/scrub/newbt.c b/fs/xfs/scrub/newbt.c
index ac38f5843090..1588ce971cb8 100644
--- a/fs/xfs/scrub/newbt.c
+++ b/fs/xfs/scrub/newbt.c
@@ -62,7 +62,7 @@ xrep_newbt_estimate_slack(
 		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;
 	}
 
diff --git a/fs/xfs/scrub/reap.c b/fs/xfs/scrub/reap.c
index b32fb233cf84..8703897c0a9c 100644
--- a/fs/xfs/scrub/reap.c
+++ b/fs/xfs/scrub/reap.c
@@ -935,10 +935,13 @@ xrep_reap_metadir_fsblocks(
 	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);
 }
 
 /*
diff --git a/fs/xfs/scrub/repair.c b/fs/xfs/scrub/repair.c
index 3b5288d3ef4e..f8f9ed30f56b 100644
--- a/fs/xfs/scrub/repair.c
+++ b/fs/xfs/scrub/repair.c
@@ -43,6 +43,7 @@
 #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"
@@ -1050,7 +1051,13 @@ xrep_require_rtext_inuse(
 	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);
@@ -1386,11 +1393,12 @@ int
 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;
 
@@ -1401,11 +1409,11 @@ xrep_reset_metafile_resv(
 	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;
@@ -1413,24 +1421,23 @@ xrep_reset_metafile_resv(
 
 	/*
 	 * 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;
 }
diff --git a/fs/xfs/scrub/rtbitmap.c b/fs/xfs/scrub/rtbitmap.c
index e8c776a34c1d..d5ff8609dbfb 100644
--- a/fs/xfs/scrub/rtbitmap.c
+++ b/fs/xfs/scrub/rtbitmap.c
@@ -21,6 +21,7 @@
 #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"
@@ -272,7 +273,6 @@ xchk_xref_is_used_rt_space(
 	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;
@@ -281,6 +281,13 @@ xchk_xref_is_used_rt_space(
 	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,
@@ -288,5 +295,5 @@ xchk_xref_is_used_rt_space(
 	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);
 }
diff --git a/fs/xfs/scrub/rtrefcount_repair.c b/fs/xfs/scrub/rtrefcount_repair.c
index 257cfb24beb4..983362447826 100644
--- a/fs/xfs/scrub/rtrefcount_repair.c
+++ b/fs/xfs/scrub/rtrefcount_repair.c
@@ -697,32 +697,6 @@ err_cur:
 	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(
@@ -769,8 +743,12 @@ 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;
 
diff --git a/fs/xfs/scrub/rtrmap_repair.c b/fs/xfs/scrub/rtrmap_repair.c
index f2fdd7a9fc24..fc2592c53af5 100644
--- a/fs/xfs/scrub/rtrmap_repair.c
+++ b/fs/xfs/scrub/rtrmap_repair.c
@@ -810,28 +810,6 @@ err_cur:
 
 /* 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,
@@ -995,8 +973,11 @@ xrep_rtrmapbt(
 	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;
 
diff --git a/fs/xfs/scrub/scrub.c b/fs/xfs/scrub/scrub.c
index 6fa9e3e5bab7..9908850bf76f 100644
--- a/fs/xfs/scrub/scrub.c
+++ b/fs/xfs/scrub/scrub.c
@@ -399,12 +399,14 @@ static const struct xchk_meta_ops meta_scrub_ops[] = {
 	},
 	[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,
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 6d9965b546cb..26a04a783489 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1,7 +1,7 @@
 // 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"
@@ -20,6 +20,8 @@
 #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;
@@ -77,6 +79,26 @@ xfs_setfilesize(
 	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.
  */
@@ -86,6 +108,7 @@ xfs_end_ioend(
 {
 	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;
@@ -115,10 +138,11 @@ xfs_end_ioend(
 	 */
 	error = blk_status_to_errno(ioend->io_bio.bi_status);
 	if (unlikely(error)) {
-		if (ioend->io_flags & IOMAP_F_SHARED) {
+		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;
 	}
@@ -126,14 +150,21 @@ xfs_end_ioend(
 	/*
 	 * Success: commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_flags & IOMAP_F_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_type == IOMAP_UNWRITTEN)
+	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);
 }
@@ -176,17 +207,27 @@ xfs_end_io(
 	}
 }
 
-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);
@@ -396,10 +437,11 @@ allocate_blocks:
 }
 
 static int
-xfs_prepare_ioend(
-	struct iomap_ioend	*ioend,
+xfs_submit_ioend(
+	struct iomap_writepage_ctx *wpc,
 	int			status)
 {
+	struct iomap_ioend	*ioend = wpc->ioend;
 	unsigned int		nofs_flag;
 
 	/*
@@ -410,7 +452,7 @@ xfs_prepare_ioend(
 	nofs_flag = memalloc_nofs_save();
 
 	/* Convert CoW extents to regular */
-	if (!status && (ioend->io_flags & IOMAP_F_SHARED)) {
+	if (!status && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
 		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
 				ioend->io_offset, ioend->io_size);
 	}
@@ -418,10 +460,14 @@ xfs_prepare_ioend(
 	memalloc_nofs_restore(nofs_flag);
 
 	/* send ioends that might require a transaction to the completion wq */
-	if (xfs_ioend_is_append(ioend) || ioend->io_type == IOMAP_UNWRITTEN ||
-	    (ioend->io_flags & IOMAP_F_SHARED))
+	if (xfs_ioend_is_append(ioend) ||
+	    (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED)))
 		ioend->io_bio.bi_end_io = xfs_end_bio;
-	return status;
+
+	if (status)
+		return status;
+	submit_bio(&ioend->io_bio);
+	return 0;
 }
 
 /*
@@ -458,12 +504,107 @@ xfs_discard_folio(
 	 * 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 = {
 	.map_blocks		= xfs_map_blocks,
-	.prepare_ioend		= xfs_prepare_ioend,
+	.submit_ioend		= xfs_submit_ioend,
+	.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,
 };
 
@@ -472,10 +613,25 @@ 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(ip, XFS_ITRUNCATED);
 
-	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
-	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
+	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
diff --git a/fs/xfs/xfs_aops.h b/fs/xfs/xfs_aops.h
index e0bd68419764..5a7a0f1a0b49 100644
--- a/fs/xfs/xfs_aops.h
+++ b/fs/xfs/xfs_aops.h
@@ -9,6 +9,7 @@
 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__ */
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 0836fea2d6d8..06ca11731e43 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -30,6 +30,7 @@
 #include "xfs_reflink.h"
 #include "xfs_rtbitmap.h"
 #include "xfs_rtgroup.h"
+#include "xfs_zone_alloc.h"
 
 /* Kernel only BMAP related definitions and functions */
 
@@ -436,7 +437,8 @@ xfs_bmap_punch_delalloc_range(
 	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);
@@ -467,7 +469,21 @@ xfs_bmap_punch_delalloc_range(
 			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;
 	}
@@ -582,7 +598,7 @@ xfs_free_eofblocks(
 		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;
@@ -825,7 +841,8 @@ 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)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		startoffset_fsb;
@@ -880,7 +897,7 @@ xfs_free_file_space(
 		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;
 
@@ -968,7 +985,8 @@ int
 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;
@@ -981,7 +999,7 @@ xfs_collapse_file_space(
 
 	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;
 
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index b29760d36e1a..c477b3361630 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -15,6 +15,7 @@ struct xfs_inode;
 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);
@@ -31,7 +32,8 @@ 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 */
@@ -54,13 +56,13 @@ int	xfs_bmap_last_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 
 /* 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);
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 3f2403a7b49c..c1a306268ae4 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -844,7 +844,8 @@ xfs_ioc_trim(
 
 	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)
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index ea43c9a6e54c..da3161572735 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -671,7 +671,7 @@ xfs_extent_busy_wait_all(
 	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));
 }
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index a25c713ff888..777438b853da 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -29,6 +29,7 @@
 #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;
@@ -767,21 +768,35 @@ xfs_rtextent_free_finish_item(
 
 	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;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f7a7d89c345e..fe8cf9d96eb0 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -25,6 +25,8 @@
 #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>
@@ -150,7 +152,7 @@ xfs_file_fsync(
 	 * 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);
@@ -360,7 +362,8 @@ xfs_file_write_zero_eof(
 	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;
@@ -414,7 +417,7 @@ xfs_file_write_zero_eof(
 	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;
@@ -431,7 +434,8 @@ STATIC ssize_t
 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);
@@ -481,7 +485,7 @@ restart:
 	 */
 	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)
@@ -491,6 +495,48 @@ restart:
 	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
 xfs_dio_write_end_io(
 	struct kiocb		*iocb,
@@ -503,6 +549,9 @@ xfs_dio_write_end_io(
 	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);
 
 	if (xfs_is_shutdown(ip->i_mount))
@@ -582,14 +631,51 @@ static const struct iomap_dio_ops xfs_dio_write_ops = {
 	.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;
@@ -597,7 +683,7 @@ xfs_file_dio_write_aligned(
 	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;
 
@@ -611,11 +697,31 @@ xfs_file_dio_write_aligned(
 		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;
 }
 
@@ -675,7 +781,7 @@ retry_exclusive:
 		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;
 
@@ -721,9 +827,21 @@ xfs_file_dio_write(
 	/* 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
@@ -740,7 +858,7 @@ xfs_file_dax_write(
 	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;
 
@@ -784,7 +902,7 @@ write_retry:
 	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;
 
@@ -832,6 +950,67 @@ out:
 }
 
 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;
+}
+
+STATIC ssize_t
 xfs_file_write_iter(
 	struct kiocb		*iocb,
 	struct iov_iter		*from)
@@ -878,6 +1057,8 @@ xfs_file_write_iter(
 			return ret;
 	}
 
+	if (xfs_is_zoned_inode(ip))
+		return xfs_file_buffered_write_zoned(iocb, from);
 	return xfs_file_buffered_write(iocb, from);
 }
 
@@ -932,7 +1113,8 @@ static int
 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;
@@ -948,7 +1130,7 @@ xfs_falloc_collapse_range(
 	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);
@@ -1004,7 +1186,8 @@ xfs_falloc_zero_range(
 	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);
@@ -1017,7 +1200,7 @@ xfs_falloc_zero_range(
 	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;
 
@@ -1088,22 +1271,18 @@ xfs_falloc_allocate_range(
 		 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);
 	if (error)
@@ -1124,16 +1303,16 @@ xfs_file_fallocate(
 
 	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);
@@ -1154,6 +1333,54 @@ out_unlock:
 	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
 xfs_file_fadvise(
 	struct file	*file,
@@ -1347,15 +1574,22 @@ xfs_file_release(
 	 * 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))
@@ -1472,9 +1706,10 @@ xfs_dax_read_fault(
  *         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);
@@ -1511,13 +1746,50 @@ xfs_write_fault(
 	if (IS_DAX(inode))
 		ret = xfs_dax_fault_locked(vmf, order, true);
 	else
-		ret = iomap_page_mkwrite(vmf, &xfs_buffered_write_iomap_ops);
+		ret = iomap_page_mkwrite(vmf, &xfs_buffered_write_iomap_ops,
+				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
 xfs_is_write_fault(
 	struct vm_fault		*vmf)
@@ -1626,7 +1898,8 @@ const struct file_operations xfs_file_operations = {
 	.fadvise	= xfs_file_fadvise,
 	.remap_file_range = xfs_file_remap_range,
 	.fop_flags	= FOP_MMAP_SYNC | FOP_BUFFER_RASYNC |
-			  FOP_BUFFER_WASYNC | FOP_DIO_PARALLEL_WRITE,
+			  FOP_BUFFER_WASYNC | FOP_DIO_PARALLEL_WRITE |
+			  FOP_DONTCACHE,
 };
 
 const struct file_operations xfs_dir_file_operations = {
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
index 1dbd2d75f7ae..a4bc1642fe56 100644
--- a/fs/xfs/xfs_fsmap.c
+++ b/fs/xfs/xfs_fsmap.c
@@ -879,17 +879,39 @@ xfs_getfsmap_rtdev_rmapbt(
 	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;
 
@@ -1004,22 +1026,40 @@ xfs_getfsmap_rtdev_rmapbt(
 }
 #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. */
@@ -1126,7 +1166,7 @@ xfs_getfsmap(
 	/* 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
@@ -1134,13 +1174,17 @@ xfs_getfsmap(
 	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
@@ -1230,7 +1274,13 @@ xfs_getfsmap(
 
 	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;
 }
 
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 455298503d01..ee2cefbd5df8 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -24,6 +24,7 @@
 #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
@@ -307,6 +308,10 @@ xfs_growfs_data(
 	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)
+		return -EINVAL;
+
 	/* 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);
@@ -366,6 +371,7 @@ xfs_growfs_log(
 int
 xfs_reserve_blocks(
 	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr,
 	uint64_t		request)
 {
 	int64_t			lcounter, delta;
@@ -373,6 +379,8 @@ xfs_reserve_blocks(
 	int64_t			free;
 	int			error = 0;
 
+	ASSERT(ctr < XC_FREE_NR);
+
 	/*
 	 * With per-cpu counters, this becomes an interesting problem. we need
 	 * to work out if we are freeing or allocation blocks first, then we can
@@ -391,16 +399,16 @@ xfs_reserve_blocks(
 	 * 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);
 		}
 
@@ -409,7 +417,7 @@ xfs_reserve_blocks(
 
 	/*
 	 * 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
@@ -419,10 +427,10 @@ xfs_reserve_blocks(
 	 * 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
@@ -436,9 +444,9 @@ xfs_reserve_blocks(
 		 */
 		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:
@@ -558,15 +566,13 @@ xfs_fs_reserve_ag_blocks(
 		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;
 	}
 
@@ -582,9 +588,7 @@ xfs_fs_unreserve_ag_blocks(
 {
 	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);
 }
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index 3e2f73bcf831..9d23c361ef56 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -8,7 +8,8 @@
 
 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);
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 7b6c026d01a1..2f53ca7e12d4 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -2073,10 +2073,10 @@ xfs_inodegc_want_queue_rt_file(
 {
 	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;
@@ -2104,7 +2104,7 @@ xfs_inodegc_want_queue_work(
 	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;
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index b1f9f156ec88..7ded570e0191 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3074,5 +3074,6 @@ bool
 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));
 }
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index c08093a65352..4bb7a99e0dc4 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -25,19 +25,9 @@ struct xfs_dquot;
 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)*/
@@ -69,8 +59,13 @@ typedef struct xfs_inode {
 	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 */
 	};
@@ -309,6 +304,11 @@ static inline bool xfs_is_internal_inode(const struct xfs_inode *ip)
 	       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);
 
 static inline bool xfs_is_cow_inode(const struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 35803fcf0beb..40fc1bf900af 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -596,6 +596,7 @@ xfs_inode_to_log_dinode(
 		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;
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index f3bfb814378c..7205fd14f6b3 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -203,6 +203,7 @@ xfs_log_dinode_to_disk(
 		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);
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index ed85322507dd..d250f7f74e3b 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -1131,15 +1131,15 @@ xfs_ioctl_getset_resblocks(
 		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)))
@@ -1155,9 +1155,9 @@ xfs_ioctl_fs_counts(
 	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)))
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index d61460309a78..30e257f683bb 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -30,6 +30,8 @@
 #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)
@@ -431,13 +433,14 @@ xfs_quota_calc_throttle(
 
 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])
@@ -536,10 +539,10 @@ xfs_iomap_prealloc_size(
 
 	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);
 
 	/*
@@ -962,6 +965,59 @@ const struct iomap_ops xfs_direct_write_iomap_ops = {
 	.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,
@@ -987,6 +1043,455 @@ const struct iomap_ops xfs_dax_write_iomap_ops = {
 	.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(
 	struct inode		*inode,
@@ -1013,6 +1518,10 @@ 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))
 		return xfs_direct_write_iomap_begin(inode, offset, count,
@@ -1245,10 +1754,13 @@ xfs_buffered_write_delalloc_punch(
 	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
@@ -1485,6 +1997,7 @@ xfs_zero_range(
 	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);
@@ -1495,13 +2008,14 @@ xfs_zero_range(
 		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);
+				&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);
@@ -1510,5 +2024,5 @@ xfs_truncate_page(
 		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);
+				   &xfs_buffered_write_iomap_ops, ac);
 }
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 8347268af727..d330c4a581b1 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -10,6 +10,7 @@
 
 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,
@@ -24,8 +25,9 @@ int xfs_bmbt_to_iomap(struct xfs_inode *ip, struct iomap *iomap,
 		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(
@@ -49,6 +51,7 @@ 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;
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 40289fe6f5b2..444193f543ef 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -29,6 +29,7 @@
 #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>
@@ -854,6 +855,7 @@ xfs_setattr_size(
 	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));
@@ -890,6 +892,28 @@ xfs_setattr_size(
 	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
@@ -902,11 +926,14 @@ xfs_setattr_size(
 	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;
 
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f8851ff835de..6493bdb57351 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -20,6 +20,7 @@
 #include "xfs_sysfs.h"
 #include "xfs_sb.h"
 #include "xfs_health.h"
+#include "xfs_zone_alloc.h"
 
 struct kmem_cache	*xfs_log_ticket_cache;
 
@@ -3540,6 +3541,9 @@ xlog_force_shutdown(
 	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;
 }
 
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index 6ed485ff2756..15d410d16bb2 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -173,6 +173,10 @@ xfs_warn_experimental(
 			.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);
diff --git a/fs/xfs/xfs_message.h b/fs/xfs/xfs_message.h
index 7fb36ced9df7..a92a4d09c8e9 100644
--- a/fs/xfs/xfs_message.h
+++ b/fs/xfs/xfs_message.h
@@ -99,6 +99,7 @@ enum xfs_experimental_feat {
 	XFS_EXPERIMENTAL_EXCHRANGE,
 	XFS_EXPERIMENTAL_PPTR,
 	XFS_EXPERIMENTAL_METADIR,
+	XFS_EXPERIMENTAL_ZONED,
 
 	XFS_EXPERIMENTAL_MAX,
 };
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index b69356582b86..e65a659901d5 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -40,6 +40,7 @@
 #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;
@@ -461,22 +462,38 @@ xfs_mount_reset_sbqflags(
 	return xfs_sync_sb(mp, false);
 }
 
+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",
+};
+
 uint64_t
-xfs_default_resblks(xfs_mount_t *mp)
+xfs_default_resblks(
+	struct xfs_mount	*mp,
+	enum xfs_free_counter	ctr)
 {
-	uint64_t resblks;
-
-	/*
-	 * 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;
+	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. */
@@ -543,7 +560,7 @@ xfs_check_summary_counts(
 	 * 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;
@@ -678,6 +695,7 @@ xfs_mountfs(
 	uint			quotamount = 0;
 	uint			quotaflags = 0;
 	int			error = 0;
+	int			i;
 
 	xfs_sb_mount_common(mp, sbp);
 
@@ -747,27 +765,15 @@ xfs_mountfs(
 	/* 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");
+	error = xfs_mount_sysfs_init(mp);
 	if (error)
-		goto out_remove_sysfs;
+		goto out_remove_scrub_stats;
 
 	xchk_stats_register(mp->m_scrub_stats, mp->m_debugfs);
 
-	error = xfs_error_sysfs_init(mp);
-	if (error)
-		goto out_remove_scrub_stats;
-
 	error = xfs_errortag_init(mp);
 	if (error)
-		goto out_remove_error_sysfs;
+		goto out_remove_sysfs;
 
 	error = xfs_uuid_mount(mp);
 	if (error)
@@ -1031,6 +1037,12 @@ xfs_mountfs(
 	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.
 	 */
@@ -1046,22 +1058,28 @@ xfs_mountfs(
 	 * 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;
@@ -1069,6 +1087,8 @@ xfs_mountfs(
  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:
@@ -1116,13 +1136,10 @@ xfs_mountfs(
 	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;
 }
@@ -1148,8 +1165,12 @@ xfs_unmountfs(
 	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)
@@ -1173,7 +1194,7 @@ xfs_unmountfs(
 	 * 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.");
@@ -1195,10 +1216,8 @@ xfs_unmountfs(
 	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);
 }
 
 /*
@@ -1220,52 +1239,67 @@ xfs_fs_writable(
 	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
@@ -1275,7 +1309,7 @@ xfs_dec_freecounter(
 	 * 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
@@ -1292,34 +1326,34 @@ xfs_dec_freecounter(
 	 * 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;
+	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);
-		return 0;
 	}
-	xfs_warn_once(mp,
-"Reserve blocks depleted! Consider increasing reserve pool size.");
+
+	/* we had space! */
+	return 0;
 
 fdblocks_enospc:
+	trace_xfs_freecounter_enospc(mp, ctr, delta, _RET_IP_);
 	spin_unlock(&mp->m_sb_lock);
 	return -ENOSPC;
 }
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index fbed172d6770..799b84220ebb 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -98,11 +98,41 @@ struct xfs_groups {
 	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;
 };
 
 /*
@@ -198,6 +228,7 @@ typedef struct xfs_mount {
 	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.
@@ -222,8 +253,8 @@ typedef struct xfs_mount {
 	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,
@@ -245,10 +276,8 @@ typedef struct xfs_mount {
 	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;
@@ -258,10 +287,16 @@ typedef struct xfs_mount {
 #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;
 	/*
@@ -336,8 +371,10 @@ typedef struct xfs_mount {
 #define XFS_FEAT_NREXT64	(1ULL << 26)	/* large extent counters */
 #define XFS_FEAT_EXCHANGE_RANGE	(1ULL << 27)	/* exchange range */
 #define XFS_FEAT_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 */
@@ -392,6 +429,8 @@ __XFS_HAS_FEAT(needsrepair, NEEDSREPAIR)
 __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)
 {
@@ -402,7 +441,9 @@ 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)
@@ -417,6 +458,11 @@ static inline bool xfs_has_rtreflink(const struct xfs_mount *mp)
 	       xfs_has_reflink(mp);
 }
 
+static inline bool xfs_has_nonzoned(const struct xfs_mount *mp)
+{
+	return !xfs_has_zoned(mp);
+}
+
 /*
  * Some features are always on for v5 file systems, allow the compiler to
  * eliminiate dead code when building without v4 support.
@@ -520,6 +566,10 @@ __XFS_HAS_FEAT(nouuid, NOUUID)
 #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) \
@@ -564,6 +614,7 @@ static inline bool xfs_clear_resuming_quotaon(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)
@@ -633,7 +684,8 @@ xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 }
 
 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 *);
 
@@ -646,45 +698,74 @@ 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);
@@ -706,5 +787,9 @@ int xfs_add_incompat_log_feature(struct xfs_mount *mp, uint32_t feature);
 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__ */
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index e1ba5af6250f..417439b58785 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -1711,7 +1711,8 @@ xfs_qm_mount_quotas(
 	 * 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;
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 59f7fc16eb80..cc3b4df88110 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -235,7 +235,7 @@ xfs_reflink_trim_around_shared(
 	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;
 	}
@@ -651,7 +651,7 @@ xfs_reflink_cancel_cow_blocks(
 
 		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);
 
@@ -1207,15 +1207,9 @@ xfs_reflink_ag_has_free_space(
 	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);
@@ -1538,7 +1532,7 @@ xfs_reflink_zero_posteof(
 		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);
 }
 
 /*
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 57bef567e011..9a99629d7de4 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -33,6 +33,7 @@
 #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
@@ -663,7 +664,8 @@ xfs_rtunmount_rtg(
 
 	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
@@ -858,6 +860,84 @@ xfs_growfs_rt_init_rtsb(
 	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;
+}
+
 static int
 xfs_growfs_rt_bmblock(
 	struct xfs_rtgroup	*rtg,
@@ -943,24 +1023,7 @@ xfs_growfs_rt_bmblock(
 	/*
 	 * 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.
@@ -1127,6 +1190,11 @@ xfs_growfs_rtg(
 			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;
@@ -1146,8 +1214,7 @@ xfs_growfs_rtg(
 
 	if (old_rsum_cache)
 		kvfree(old_rsum_cache);
-	xfs_rtgroup_rele(rtg);
-	return 0;
+	goto out_rele;
 
 out_error:
 	/*
@@ -1195,6 +1262,22 @@ xfs_growfs_check_rtgeom(
 
 	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;
 }
 
@@ -1249,6 +1332,35 @@ xfs_grow_last_rtg(
 }
 
 /*
+ * 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), 0, &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
@@ -1259,7 +1371,6 @@ xfs_growfs_rt(
 	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;
 
@@ -1302,15 +1413,10 @@ xfs_growfs_rt(
 	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.
@@ -1376,8 +1482,7 @@ xfs_growfs_rt(
 			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;
 	}
@@ -1444,10 +1549,6 @@ int				/* 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) {
@@ -1458,25 +1559,7 @@ xfs_rtmount_init(
 
 	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
@@ -1519,50 +1602,10 @@ xfs_rtalloc_reinit_frextents(
 	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;
-}
-
 /*
  * Read in the bmbt of an rt metadata inode so that we never have to load them
  * at runtime.  This enables the use of shared ILOCKs for rtbitmap scans.  Use
@@ -1613,6 +1656,8 @@ xfs_rtmount_rtg(
 		}
 	}
 
+	if (xfs_has_zoned(mp))
+		return 0;
 	return xfs_alloc_rsum_cache(rtg, mp->m_sb.sb_rbmblocks);
 }
 
@@ -2097,6 +2142,8 @@ xfs_bmap_rtalloc(
 		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);
 	if (error)
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 0d95b29092c9..78a690b489ed 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -34,9 +34,6 @@ int					/* error */
 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.
  */
@@ -65,8 +62,6 @@ xfs_rtmount_init(
 }
 # 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,
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index 0055066fb1d9..af5e63cb6a99 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -46,6 +46,7 @@
 #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"
 
@@ -109,7 +110,8 @@ enum {
 	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[] = {
@@ -154,6 +156,9 @@ 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),
 	{}
 };
 
@@ -182,6 +187,7 @@ xfs_fs_show_options(
 		{ 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);
@@ -233,6 +239,9 @@ xfs_fs_show_options(
 	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;
 }
 
@@ -533,7 +542,15 @@ xfs_setup_devices(
 		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)
@@ -757,7 +774,7 @@ xfs_mount_free(
 {
 	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);
@@ -814,6 +831,7 @@ xfs_fs_sync_fs(
 	if (sb->s_writers.frozen == SB_FREEZE_PAGEFAULT) {
 		xfs_inodegc_stop(mp);
 		xfs_blockgc_stop(mp);
+		xfs_zone_gc_stop(mp);
 	}
 
 	return 0;
@@ -834,10 +852,12 @@ xfs_statfs_data(
 	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.
@@ -856,8 +876,9 @@ xfs_statfs_rt(
 	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
@@ -922,24 +943,32 @@ xfs_fs_statfs(
 }
 
 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);
+	}
 }
 
 /*
@@ -976,6 +1005,7 @@ xfs_fs_freeze(
 	if (ret && !xfs_is_readonly(mp)) {
 		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
+		xfs_zone_gc_start(mp);
 	}
 
 	return ret;
@@ -997,6 +1027,7 @@ xfs_fs_unfreeze(
 	 * filesystem.
 	 */
 	if (!xfs_is_readonly(mp)) {
+		xfs_zone_gc_start(mp);
 		xfs_blockgc_start(mp);
 		xfs_inodegc_start(mp);
 	}
@@ -1058,6 +1089,19 @@ xfs_finish_flags(
 		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;
 }
 
@@ -1065,7 +1109,8 @@ static int
 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)
@@ -1075,30 +1120,29 @@ xfs_init_percpu_counters(
 	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:
@@ -1112,24 +1156,28 @@ xfs_reinit_percpu_counters(
 {
 	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
@@ -1210,6 +1258,18 @@ xfs_fs_shutdown(
 	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,
@@ -1224,6 +1284,7 @@ static const struct super_operations xfs_super_operations = {
 	.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
@@ -1436,6 +1497,15 @@ xfs_fs_parse_param(
 		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);
 		return -EINVAL;
@@ -1780,8 +1850,17 @@ xfs_fs_fill_super(
 		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) &&
@@ -1793,6 +1872,13 @@ xfs_fs_fill_super(
 			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;
+		}
+
 		if (xfs_globals.always_cow) {
 			xfs_info(mp, "using DEBUG-only always_cow mode.");
 			mp->m_always_cow = true;
@@ -1917,6 +2003,9 @@ xfs_remount_rw(
 	/* Re-enable the background inode inactivation worker. */
 	xfs_inodegc_start(mp);
 
+	/* Restart zone reclaim */
+	xfs_zone_gc_start(mp);
+
 	return 0;
 }
 
@@ -1961,6 +2050,9 @@ xfs_remount_ro(
 	 */
 	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);
 
@@ -2082,6 +2174,7 @@ xfs_init_fs_context(
 	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;
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index 60cb5318fdae..b0857e3c1270 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -13,6 +13,7 @@
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
 #include "xfs_mount.h"
+#include "xfs_zones.h"
 
 struct xfs_sysfs_attr {
 	struct attribute attr;
@@ -69,7 +70,7 @@ static struct attribute *xfs_mp_attrs[] = {
 };
 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,
@@ -701,45 +702,103 @@ out_error:
 	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++) {
 			cfg = &mp->m_error_cfg[i][j];
@@ -749,6 +808,8 @@ xfs_error_sysfs_del(
 	}
 	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 *
diff --git a/fs/xfs/xfs_sysfs.h b/fs/xfs/xfs_sysfs.h
index 148893ebfdef..1622fe80ad3e 100644
--- a/fs/xfs/xfs_sysfs.h
+++ b/fs/xfs/xfs_sysfs.h
@@ -7,7 +7,6 @@
 #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 */
@@ -53,7 +52,7 @@ xfs_sysfs_del(
 	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__ */
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 8f530e69c18a..a60556dbd172 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -49,6 +49,8 @@
 #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
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index bfc2f1249022..83f894c07866 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -102,6 +102,7 @@ struct xfs_rmap_intent;
 struct xfs_refcount_intent;
 struct xfs_metadir_update;
 struct xfs_rtgroup;
+struct xfs_open_zone;
 
 #define XFS_ATTR_FILTER_FLAGS \
 	{ XFS_ATTR_ROOT,	"ROOT" }, \
@@ -265,6 +266,152 @@ 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),
 	TP_ARGS(mp, shrinker_hits),
@@ -1596,6 +1743,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write);
 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),
@@ -3983,6 +4131,7 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 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);
@@ -5606,11 +5755,10 @@ DEFINE_METADIR_EVENT(xfs_metadir_lookup);
 /* 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)
@@ -5618,19 +5766,15 @@ DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
 		__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,
@@ -5639,14 +5783,14 @@ DECLARE_EVENT_CLASS(xfs_metafile_resv_class,
 )
 #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,
@@ -5669,6 +5813,46 @@ TRACE_EVENT(xfs_growfs_check_rtgeom,
 );
 #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 */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_zone_alloc.c b/fs/xfs/xfs_zone_alloc.c
new file mode 100644
index 000000000000..fd4c60a050e6
--- /dev/null
+++ b/fs/xfs/xfs_zone_alloc.c
@@ -0,0 +1,1211 @@
+// 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);
+}
+
+void
+xfs_zoned_wake_all(
+	struct xfs_mount	*mp)
+{
+	if (!(mp->m_super->s_flags & SB_ACTIVE))
+		return; /* can happen during log recovery */
+	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);
+}
diff --git a/fs/xfs/xfs_zone_alloc.h b/fs/xfs/xfs_zone_alloc.h
new file mode 100644
index 000000000000..ecf39106704c
--- /dev/null
+++ b/fs/xfs/xfs_zone_alloc.h
@@ -0,0 +1,70 @@
+/* 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 */
diff --git a/fs/xfs/xfs_zone_gc.c b/fs/xfs/xfs_zone_gc.c
new file mode 100644
index 000000000000..c5136ea9bb1d
--- /dev/null
+++ b/fs/xfs/xfs_zone_gc.c
@@ -0,0 +1,1165 @@
+// 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);
+}
diff --git a/fs/xfs/xfs_zone_info.c b/fs/xfs/xfs_zone_info.c
new file mode 100644
index 000000000000..733bcc2f8645
--- /dev/null
+++ b/fs/xfs/xfs_zone_info.c
@@ -0,0 +1,105 @@
+// 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);
+}
diff --git a/fs/xfs/xfs_zone_priv.h b/fs/xfs/xfs_zone_priv.h
new file mode 100644
index 000000000000..ab696975a993
--- /dev/null
+++ b/fs/xfs/xfs_zone_priv.h
@@ -0,0 +1,119 @@
+/* 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 */
diff --git a/fs/xfs/xfs_zone_space_resv.c b/fs/xfs/xfs_zone_space_resv.c
new file mode 100644
index 000000000000..4bf1b18aa7a7
--- /dev/null
+++ b/fs/xfs/xfs_zone_space_resv.c
@@ -0,0 +1,253 @@
+// 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;
+
+		/*
+		 * 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);
+}
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 35166c92420c..42e2c0065bb3 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -299,7 +299,7 @@ static vm_fault_t zonefs_filemap_page_mkwrite(struct vm_fault *vmf)
 
 	/* Serialize against truncates */
 	filemap_invalidate_lock_shared(inode->i_mapping);
-	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops);
+	ret = iomap_page_mkwrite(vmf, &zonefs_write_iomap_ops, NULL);
 	filemap_invalidate_unlock_shared(inode->i_mapping);
 
 	sb_end_pagefault(inode->i_sb);
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 75bf54e76f3b..9cd93530013c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -56,6 +56,10 @@ struct vm_fault;
  *
  * IOMAP_F_BOUNDARY indicates that I/O and I/O completions for this iomap must
  * never be merged with the mapping before it.
+ *
+ * IOMAP_F_ANON_WRITE indicates that (write) I/O does not have a target block
+ * assigned to it yet and the file system will do that in the bio submission
+ * handler, splitting the I/O as needed.
  */
 #define IOMAP_F_NEW		(1U << 0)
 #define IOMAP_F_DIRTY		(1U << 1)
@@ -68,6 +72,7 @@ struct vm_fault;
 #endif /* CONFIG_BUFFER_HEAD */
 #define IOMAP_F_XATTR		(1U << 5)
 #define IOMAP_F_BOUNDARY	(1U << 6)
+#define IOMAP_F_ANON_WRITE	(1U << 7)
 
 /*
  * Flags set by the core iomap code during operations:
@@ -111,6 +116,8 @@ struct iomap {
 
 static inline sector_t iomap_sector(const struct iomap *iomap, loff_t pos)
 {
+	if (iomap->flags & IOMAP_F_ANON_WRITE)
+		return U64_MAX; /* invalid */
 	return (iomap->addr + pos - iomap->offset) >> SECTOR_SHIFT;
 }
 
@@ -182,7 +189,9 @@ struct iomap_folio_ops {
 #else
 #define IOMAP_DAX		0
 #endif /* CONFIG_FS_DAX */
-#define IOMAP_ATOMIC		(1 << 9)
+#define IOMAP_ATOMIC_HW		(1 << 9) /* HW-based torn-write protection */
+#define IOMAP_DONTCACHE		(1 << 10)
+#define IOMAP_ATOMIC_SW		(1 << 11)/* SW-based torn-write protection */
 
 struct iomap_ops {
 	/*
@@ -211,8 +220,10 @@ struct iomap_ops {
  *	calls to iomap_iter().  Treat as read-only in the body.
  * @len: The remaining length of the file segment we're operating on.
  *	It is updated at the same time as @pos.
- * @processed: The number of bytes processed by the body in the most recent
- *	iteration, or a negative errno. 0 causes the iteration to stop.
+ * @iter_start_pos: The original start pos for the current iomap. Used for
+ *	incremental iter advance.
+ * @status: Status of the most recent iteration. Zero on success or a negative
+ *	errno on error.
  * @flags: Zero or more of the iomap_begin flags above.
  * @iomap: Map describing the I/O iteration
  * @srcmap: Source map for COW operations
@@ -221,7 +232,8 @@ struct iomap_iter {
 	struct inode *inode;
 	loff_t pos;
 	u64 len;
-	s64 processed;
+	loff_t iter_start_pos;
+	int status;
 	unsigned flags;
 	struct iomap iomap;
 	struct iomap srcmap;
@@ -229,20 +241,46 @@ struct iomap_iter {
 };
 
 int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops);
+int iomap_iter_advance(struct iomap_iter *iter, u64 *count);
 
 /**
- * iomap_length - length of the current iomap iteration
+ * iomap_length_trim - trimmed length of the current iomap iteration
  * @iter: iteration structure
+ * @pos: File position to trim from.
+ * @len: Length of the mapping to trim to.
  *
- * Returns the length that the operation applies to for the current iteration.
+ * Returns a trimmed length that the operation applies to for the current
+ * iteration.
  */
-static inline u64 iomap_length(const struct iomap_iter *iter)
+static inline u64 iomap_length_trim(const struct iomap_iter *iter, loff_t pos,
+		u64 len)
 {
 	u64 end = iter->iomap.offset + iter->iomap.length;
 
 	if (iter->srcmap.type != IOMAP_HOLE)
 		end = min(end, iter->srcmap.offset + iter->srcmap.length);
-	return min(iter->len, end - iter->pos);
+	return min(len, end - pos);
+}
+
+/**
+ * iomap_length - length of the current iomap iteration
+ * @iter: iteration structure
+ *
+ * Returns the length that the operation applies to for the current iteration.
+ */
+static inline u64 iomap_length(const struct iomap_iter *iter)
+{
+	return iomap_length_trim(iter, iter->pos, iter->len);
+}
+
+/**
+ * iomap_iter_advance_full - advance by the full length of current map
+ */
+static inline int iomap_iter_advance_full(struct iomap_iter *iter)
+{
+	u64 length = iomap_length(iter);
+
+	return iomap_iter_advance(iter, &length);
 }
 
 /**
@@ -306,12 +344,11 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 		const struct iomap_ops *ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-		bool *did_zero, const struct iomap_ops *ops);
+		bool *did_zero, const struct iomap_ops *ops, void *private);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops);
-vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
-			const struct iomap_ops *ops);
-
+		const struct iomap_ops *ops, void *private);
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
+		void *private);
 typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length,
 		struct iomap *iomap);
 void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
@@ -328,16 +365,42 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 		const struct iomap_ops *ops);
 
 /*
+ * Flags for iomap_ioend->io_flags.
+ */
+/* shared COW extent */
+#define IOMAP_IOEND_SHARED		(1U << 0)
+/* unwritten extent */
+#define IOMAP_IOEND_UNWRITTEN		(1U << 1)
+/* don't merge into previous ioend */
+#define IOMAP_IOEND_BOUNDARY		(1U << 2)
+/* is direct I/O */
+#define IOMAP_IOEND_DIRECT		(1U << 3)
+
+/*
+ * Flags that if set on either ioend prevent the merge of two ioends.
+ * (IOMAP_IOEND_BOUNDARY also prevents merges, but only one-way)
+ */
+#define IOMAP_IOEND_NOMERGE_FLAGS \
+	(IOMAP_IOEND_SHARED | IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_DIRECT)
+
+/*
  * Structure for writeback I/O completions.
+ *
+ * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io
+ * for direct I/O) can split a bio generated by iomap.  In that case the parent
+ * ioend it was split from is recorded in ioend->io_parent.
  */
 struct iomap_ioend {
 	struct list_head	io_list;	/* next ioend in chain */
-	u16			io_type;
-	u16			io_flags;	/* IOMAP_F_* */
+	u16			io_flags;	/* IOMAP_IOEND_* */
 	struct inode		*io_inode;	/* file being written to */
-	size_t			io_size;	/* size of data within eof */
+	size_t			io_size;	/* size of the extent */
+	atomic_t		io_remaining;	/* completetion defer count */
+	int			io_error;	/* stashed away status */
+	struct iomap_ioend	*io_parent;	/* parent for completions */
 	loff_t			io_offset;	/* offset in the file */
 	sector_t		io_sector;	/* start sector of ioend */
+	void			*io_private;	/* file system private data */
 	struct bio		io_bio;		/* MUST BE LAST! */
 };
 
@@ -362,12 +425,14 @@ struct iomap_writeback_ops {
 			  loff_t offset, unsigned len);
 
 	/*
-	 * Optional, allows the file systems to perform actions just before
-	 * submitting the bio and/or override the bio end_io handler for complex
-	 * operations like copy on write extent manipulation or unwritten extent
-	 * conversions.
+	 * Optional, allows the file systems to hook into bio submission,
+	 * including overriding the bi_end_io handler.
+	 *
+	 * Returns 0 if the bio was successfully submitted, or a negative
+	 * error code if status was non-zero or another error happened and
+	 * the bio could not be submitted.
 	 */
-	int (*prepare_ioend)(struct iomap_ioend *ioend, int status);
+	int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
 
 	/*
 	 * Optional, allows the file system to discard state on a page where
@@ -383,6 +448,10 @@ struct iomap_writepage_ctx {
 	u32			nr_folios;	/* folios added to the ioend */
 };
 
+struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio,
+		loff_t file_offset, u16 ioend_flags);
+struct iomap_ioend *iomap_split_ioend(struct iomap_ioend *ioend,
+		unsigned int max_len, bool is_append);
 void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
@@ -434,6 +503,11 @@ struct iomap_dio_ops {
  */
 #define IOMAP_DIO_PARTIAL		(1 << 2)
 
+/*
+ * Use software-based torn-write protection.
+ */
+#define IOMAP_DIO_ATOMIC_SW		(1 << 3)
+
 ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops, const struct iomap_dio_ops *dops,
 		unsigned int dio_flags, void *private, size_t done_before);
@@ -454,4 +528,6 @@ int iomap_swapfile_activate(struct swap_info_struct *sis,
 # define iomap_swapfile_activate(sis, swapfile, pagespan, ops)	(-EIO)
 #endif /* CONFIG_SWAP */
 
+extern struct bio_set iomap_ioend_bioset;
+
 #endif /* LINUX_IOMAP_H */