1 files changed, 698 insertions, 0 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
new file mode 100644
index 000000000..8b6119776
--- /dev/null
+++ b/fs/xfs/xfs_aops.c
@@ -0,0 +1,698 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2005 Silicon Graphics, Inc.
+ * Copyright (c) 2016-2025 Christoph Hellwig.
+ * All Rights Reserved.
+ */
+#include "xfs_platform.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_trans.h"
+#include "xfs_iomap.h"
+#include "xfs_trace.h"
+#include "xfs_bmap.h"
+#include "xfs_bmap_util.h"
+#include "xfs_reflink.h"
+#include "xfs_errortag.h"
+#include "xfs_error.h"
+#include "xfs_icache.h"
+#include "xfs_ioend.h"
+#include "xfs_zone_alloc.h"
+#include "xfs_rtgroup.h"
+#include <linux/bio-integrity.h>
+
+struct xfs_writepage_ctx {
+	struct iomap_writepage_ctx ctx;
+	unsigned int		data_seq;
+	unsigned int		cow_seq;
+};
+
+static inline struct xfs_writepage_ctx *
+XFS_WPC(struct iomap_writepage_ctx *ctx)
+{
+	return container_of(ctx, struct xfs_writepage_ctx, ctx);
+}
+
+/*
+ * Update on-disk file size now that data has been written to disk.
+ */
+int
+xfs_setfilesize(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	size_t			size)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_trans	*tp;
+	xfs_fsize_t		isize;
+	int			error;
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	isize = xfs_new_eof(ip, offset + size);
+	if (!isize) {
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		xfs_trans_cancel(tp);
+		return 0;
+	}
+
+	trace_xfs_setfilesize(ip, offset, size);
+
+	ip->i_disk_size = isize;
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	return xfs_trans_commit(tp);
+}
+
+/*
+ * We cannot cancel the ioend directly on error.  We may have already set other
+ * pages under writeback and hence we have to run I/O completion to mark the
+ * error state of the pages under writeback appropriately.
+ *
+ * If the folio has delalloc blocks on it, the caller is asking us to punch them
+ * out. If we don't, we can leave a stale delalloc mapping covered by a clean
+ * page that needs to be dirtied again before the delalloc mapping can be
+ * converted. This stale delalloc mapping can trip up a later direct I/O read
+ * operation on the same region.
+ *
+ * We prevent this by truncating away the delalloc regions on the folio. Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why
+ * we see a ENOSPC in writeback).
+ */
+static void
+xfs_discard_folio(
+	struct folio		*folio,
+	loff_t			pos)
+{
+	struct xfs_inode	*ip = XFS_I(folio->mapping->host);
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (xfs_is_shutdown(mp))
+		return;
+
+	xfs_alert_ratelimited(mp,
+		"page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
+			folio, I_INO(ip), pos);
+
+	/*
+	 * The end of the punch range is always the offset of the first
+	 * byte of the next folio. Hence the end offset is only dependent on the
+	 * folio itself and not the start offset that is passed in.
+	 */
+	xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
+				folio_next_pos(folio), NULL);
+}
+
+/*
+ * Fast revalidation of the cached writeback mapping. Return true if the current
+ * mapping is valid, false otherwise.
+ */
+static bool
+xfs_imap_valid(
+	struct iomap_writepage_ctx	*wpc,
+	struct xfs_inode		*ip,
+	loff_t				offset)
+{
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length)
+		return false;
+	/*
+	 * If this is a COW mapping, it is sufficient to check that the mapping
+	 * covers the offset. Be careful to check this first because the caller
+	 * can revalidate a COW mapping without updating the data seqno.
+	 */
+	if (wpc->iomap.flags & IOMAP_F_SHARED)
+		return true;
+
+	/*
+	 * This is not a COW mapping. Check the sequence number of the data fork
+	 * because concurrent changes could have invalidated the extent. Check
+	 * the COW fork because concurrent changes since the last time we
+	 * checked (and found nothing at this offset) could have added
+	 * overlapping blocks.
+	 */
+	if (XFS_WPC(wpc)->data_seq != READ_ONCE(ip->i_df.if_seq)) {
+		trace_xfs_wb_data_iomap_invalid(ip, &wpc->iomap,
+				XFS_WPC(wpc)->data_seq, XFS_DATA_FORK);
+		return false;
+	}
+	if (xfs_inode_has_cow_data(ip) &&
+	    XFS_WPC(wpc)->cow_seq != READ_ONCE(ip->i_cowfp->if_seq)) {
+		trace_xfs_wb_cow_iomap_invalid(ip, &wpc->iomap,
+				XFS_WPC(wpc)->cow_seq, XFS_COW_FORK);
+		return false;
+	}
+	return true;
+}
+
+static int
+xfs_map_blocks(
+	struct iomap_writepage_ctx *wpc,
+	loff_t			offset,
+	unsigned int		len)
+{
+	struct xfs_inode	*ip = XFS_I(wpc->inode);
+	struct xfs_mount	*mp = ip->i_mount;
+	ssize_t			count = i_blocksize(wpc->inode);
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
+	xfs_fileoff_t		cow_fsb;
+	int			whichfork;
+	struct xfs_bmbt_irec	imap;
+	struct xfs_iext_cursor	icur;
+	int			retries = 0;
+	int			error = 0;
+	unsigned int		*seq;
+
+	if (xfs_is_shutdown(mp))
+		return -EIO;
+
+	XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS);
+
+	/*
+	 * COW fork blocks can overlap data fork blocks even if the blocks
+	 * aren't shared.  COW I/O always takes precedent, so we must always
+	 * check for overlap on reflink inodes unless the mapping is already a
+	 * COW one, or the COW fork hasn't changed from the last time we looked
+	 * at it.
+	 *
+	 * It's safe to check the COW fork if_seq here without the ILOCK because
+	 * we've indirectly protected against concurrent updates: writeback has
+	 * the page locked, which prevents concurrent invalidations by reflink
+	 * and directio and prevents concurrent buffered writes to the same
+	 * page.  Changes to if_seq always happen under i_lock, which protects
+	 * against concurrent updates and provides a memory barrier on the way
+	 * out that ensures that we always see the current value.
+	 */
+	if (xfs_imap_valid(wpc, ip, offset))
+		return 0;
+
+	/*
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.  If we return without a valid map, it means we
+	 * landed in a hole and we skip the block.
+	 */
+retry:
+	cow_fsb = NULLFILEOFF;
+	whichfork = XFS_DATA_FORK;
+	xfs_ilock(ip, XFS_ILOCK_SHARED);
+	ASSERT(!xfs_need_iread_extents(&ip->i_df));
+
+	/*
+	 * Check if this is offset is covered by a COW extents, and if yes use
+	 * it directly instead of looking up anything in the data fork.
+	 */
+	if (xfs_inode_has_cow_data(ip) &&
+	    xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &icur, &imap))
+		cow_fsb = imap.br_startoff;
+	if (cow_fsb != NULLFILEOFF && cow_fsb <= offset_fsb) {
+		XFS_WPC(wpc)->cow_seq = READ_ONCE(ip->i_cowfp->if_seq);
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+		whichfork = XFS_COW_FORK;
+		goto allocate_blocks;
+	}
+
+	/*
+	 * No COW extent overlap. Revalidate now that we may have updated
+	 * ->cow_seq. If the data mapping is still valid, we're done.
+	 */
+	if (xfs_imap_valid(wpc, ip, offset)) {
+		xfs_iunlock(ip, XFS_ILOCK_SHARED);
+		return 0;
+	}
+
+	/*
+	 * If we don't have a valid map, now it's time to get a new one for this
+	 * offset.  This will convert delayed allocations (including COW ones)
+	 * into real extents.
+	 */
+	if (!xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap))
+		imap.br_startoff = end_fsb;	/* fake a hole past EOF */
+	XFS_WPC(wpc)->data_seq = READ_ONCE(ip->i_df.if_seq);
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+
+	/* landed in a hole or beyond 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;
+	}
+
+	/*
+	 * Truncate to the next COW extent if there is one.  This is the only
+	 * opportunity to do this because we can skip COW fork lookups for the
+	 * subsequent blocks in the mapping; however, the requirement to treat
+	 * the COW range separately remains.
+	 */
+	if (cow_fsb != NULLFILEOFF &&
+	    cow_fsb < imap.br_startoff + imap.br_blockcount)
+		imap.br_blockcount = cow_fsb - imap.br_startoff;
+
+	/* got a delalloc extent? */
+	if (imap.br_startblock != HOLESTARTBLOCK &&
+	    isnullstartblock(imap.br_startblock))
+		goto allocate_blocks;
+
+	xfs_bmbt_to_iomap(ip, &wpc->iomap, &imap, 0, 0, XFS_WPC(wpc)->data_seq);
+	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
+	return 0;
+allocate_blocks:
+	/*
+	 * Convert a dellalloc extent to a real one. The current page is held
+	 * locked so nothing could have removed the block backing offset_fsb,
+	 * although it could have moved from the COW to the data fork by another
+	 * thread.
+	 */
+	if (whichfork == XFS_COW_FORK)
+		seq = &XFS_WPC(wpc)->cow_seq;
+	else
+		seq = &XFS_WPC(wpc)->data_seq;
+
+	error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
+				&wpc->iomap, seq);
+	if (error) {
+		/*
+		 * If we failed to find the extent in the COW fork we might have
+		 * raced with a COW to data fork conversion or truncate.
+		 * Restart the lookup to catch the extent in the data fork for
+		 * the former case, but prevent additional retries to avoid
+		 * looping forever for the latter case.
+		 */
+		if (error == -EAGAIN && whichfork == XFS_COW_FORK && !retries++)
+			goto retry;
+		ASSERT(error != -EAGAIN);
+		return error;
+	}
+
+	/*
+	 * Due to merging the return real extent might be larger than the
+	 * original delalloc one.  Trim the return extent to the next COW
+	 * boundary again to force a re-lookup.
+	 */
+	if (whichfork != XFS_COW_FORK && cow_fsb != NULLFILEOFF) {
+		loff_t		cow_offset = XFS_FSB_TO_B(mp, cow_fsb);
+
+		if (cow_offset < wpc->iomap.offset + wpc->iomap.length)
+			wpc->iomap.length = cow_offset - wpc->iomap.offset;
+	}
+
+	ASSERT(wpc->iomap.offset <= offset);
+	ASSERT(wpc->iomap.offset + wpc->iomap.length > offset);
+	trace_xfs_map_blocks_alloc(ip, offset, count, whichfork, &imap);
+	return 0;
+}
+
+static ssize_t
+xfs_writeback_range(
+	struct iomap_writepage_ctx *wpc,
+	struct folio		*folio,
+	u64			offset,
+	unsigned int		len,
+	u64			end_pos)
+{
+	ssize_t			ret;
+
+	ret = xfs_map_blocks(wpc, offset, len);
+	if (!ret)
+		ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+	if (ret < 0)
+		xfs_discard_folio(folio, offset);
+	return ret;
+}
+
+static bool
+xfs_ioend_needs_wq_completion(
+	struct iomap_ioend	*ioend)
+{
+	/* Changing inode size requires a transaction. */
+	if (xfs_ioend_is_append(ioend))
+		return true;
+
+	/* Extent manipulation requires a transaction. */
+	if (ioend->io_flags & (IOMAP_IOEND_UNWRITTEN | IOMAP_IOEND_SHARED))
+		return true;
+
+	return false;
+}
+
+static int
+xfs_writeback_submit(
+	struct iomap_writepage_ctx	*wpc,
+	int				error)
+{
+	struct iomap_ioend		*ioend = wpc->wb_ctx;
+
+	/*
+	 * Convert CoW extents to regular.
+	 *
+	 * We can allocate memory here while doing writeback on behalf of memory
+	 * reclaim.  To avoid memory allocation deadlocks, set the task-wide
+	 * nofs context.
+	 */
+	if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
+		unsigned int		nofs_flag;
+
+		nofs_flag = memalloc_nofs_save();
+		error = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
+				ioend->io_offset, ioend->io_size);
+		memalloc_nofs_restore(nofs_flag);
+	}
+
+	/*
+	 * Send ioends that might require a transaction to the completion wq,
+	 * and disable the block layer task completion for them as there is no
+	 * need to defer twice.
+	 */
+	if (xfs_ioend_needs_wq_completion(ioend)) {
+		ioend->io_bio.bi_end_io = xfs_end_bio;
+		bio_clear_flag(&ioend->io_bio, BIO_COMPLETE_IN_TASK);
+	}
+
+	return iomap_ioend_writeback_submit(wpc, error);
+}
+
+static const struct iomap_writeback_ops xfs_writeback_ops = {
+	.writeback_range	= xfs_writeback_range,
+	.writeback_submit	= xfs_writeback_submit,
+};
+
+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,
+	loff_t			offset,
+	unsigned int		len)
+{
+	struct xfs_inode	*ip = XFS_I(wpc->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);
+
+	xfs_iomap_set_anon_write(ip, &wpc->iomap, offset,
+			XFS_FSB_TO_B(mp, count_fsb));
+	trace_xfs_zoned_map_blocks(ip, offset, wpc->iomap.length);
+	return 0;
+}
+
+static ssize_t
+xfs_zoned_writeback_range(
+	struct iomap_writepage_ctx *wpc,
+	struct folio		*folio,
+	u64			offset,
+	unsigned int		len,
+	u64			end_pos)
+{
+	ssize_t			ret;
+
+	ret = xfs_zoned_map_blocks(wpc, offset, len);
+	if (!ret)
+		ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+	if (ret < 0)
+		xfs_discard_folio(folio, offset);
+	return ret;
+}
+
+static int
+xfs_zoned_writeback_submit(
+	struct iomap_writepage_ctx	*wpc,
+	int				error)
+{
+	struct iomap_ioend		*ioend = wpc->wb_ctx;
+
+	/*
+	 * Defer all completions to our workqueue as all zoned writes require a
+	 * transaction to be persisted. This also means we never need the block
+	 * layer in-task completion for a task context.
+	 */
+	ioend->io_bio.bi_end_io = xfs_end_bio;
+	bio_clear_flag(&ioend->io_bio, BIO_COMPLETE_IN_TASK);
+
+	if (error) {
+		ioend->io_bio.bi_status = errno_to_blk_status(error);
+		bio_endio(&ioend->io_bio);
+		return error;
+	}
+	if (wpc->iomap.flags & IOMAP_F_INTEGRITY)
+		fs_bio_integrity_generate(&ioend->io_bio);
+	xfs_zone_alloc_and_submit(ioend, &XFS_ZWPC(wpc)->open_zone);
+	return 0;
+}
+
+static const struct iomap_writeback_ops xfs_zoned_writeback_ops = {
+	.writeback_range	= xfs_zoned_writeback_range,
+	.writeback_submit	= xfs_zoned_writeback_submit,
+};
+
+STATIC int
+xfs_vm_writepages(
+	struct address_space	*mapping,
+	struct writeback_control *wbc)
+{
+	struct xfs_inode	*ip = XFS_I(mapping->host);
+
+	xfs_iflags_clear(ip, XFS_ITRUNCATED);
+
+	if (xfs_is_zoned_inode(ip)) {
+		struct xfs_zoned_writepage_ctx	xc = {
+			.ctx = {
+				.inode	= mapping->host,
+				.wbc	= wbc,
+				.ops	= &xfs_zoned_writeback_ops
+			},
+		};
+		int				error;
+
+		error = iomap_writepages(&xc.ctx);
+		if (xc.open_zone)
+			xfs_open_zone_put(xc.open_zone);
+		return error;
+	} else {
+		struct xfs_writepage_ctx	wpc = {
+			.ctx = {
+				.inode	= mapping->host,
+				.wbc	= wbc,
+				.ops	= &xfs_writeback_ops
+			},
+		};
+
+		return iomap_writepages(&wpc.ctx);
+	}
+}
+
+STATIC int
+xfs_dax_writepages(
+	struct address_space	*mapping,
+	struct writeback_control *wbc)
+{
+	struct xfs_inode	*ip = XFS_I(mapping->host);
+
+	xfs_iflags_clear(ip, XFS_ITRUNCATED);
+	return dax_writeback_mapping_range(mapping,
+			xfs_inode_buftarg(ip)->bt_daxdev, wbc);
+}
+
+STATIC sector_t
+xfs_vm_bmap(
+	struct address_space	*mapping,
+	sector_t		block)
+{
+	struct xfs_inode	*ip = XFS_I(mapping->host);
+
+	trace_xfs_vm_bmap(ip);
+
+	/*
+	 * The swap code (ab-)uses ->bmap to get a block mapping and then
+	 * bypasses the file system for actual I/O.  We really can't allow
+	 * that on reflinks inodes, so we have to skip out here.  And yes,
+	 * 0 is the magic code for a bmap error.
+	 *
+	 * Since we don't pass back blockdev info, we can't return bmap
+	 * information for rt files either.
+	 */
+	if (xfs_is_cow_inode(ip) || XFS_IS_REALTIME_INODE(ip))
+		return 0;
+	return iomap_bmap(mapping, block, &xfs_read_iomap_ops);
+}
+
+static void
+xfs_bio_submit_read(
+	const struct iomap_iter		*iter,
+	struct iomap_read_folio_ctx	*ctx)
+{
+	struct bio			*bio = ctx->read_ctx;
+
+	/* defer read completions to the ioend workqueue */
+	iomap_init_ioend(iter->inode, bio, ctx->read_ctx_file_offset, 0);
+	iomap_bio_submit_read_endio(iter, ctx, xfs_end_bio);
+}
+
+static const struct iomap_read_ops xfs_iomap_read_ops = {
+	.read_folio_range	= iomap_bio_read_folio_range,
+	.submit_read		= xfs_bio_submit_read,
+	.bio_set		= &iomap_ioend_bioset,
+};
+
+static inline const struct iomap_read_ops *
+xfs_get_iomap_read_ops(
+	const struct address_space	*mapping)
+{
+	struct xfs_inode		*ip = XFS_I(mapping->host);
+
+	if (bdev_has_integrity_csum(xfs_inode_buftarg(ip)->bt_bdev))
+		return &xfs_iomap_read_ops;
+	return &iomap_bio_read_ops;
+}
+
+STATIC int
+xfs_vm_read_folio(
+	struct file			*file,
+	struct folio			*folio)
+{
+	struct iomap_read_folio_ctx	ctx = { .cur_folio = folio };
+
+	ctx.ops = xfs_get_iomap_read_ops(folio->mapping);
+	iomap_read_folio(&xfs_read_iomap_ops, &ctx, NULL);
+	return 0;
+}
+
+STATIC void
+xfs_vm_readahead(
+	struct readahead_control	*rac)
+{
+	struct iomap_read_folio_ctx	ctx = { .rac = rac };
+
+	ctx.ops = xfs_get_iomap_read_ops(rac->mapping),
+	iomap_readahead(&xfs_read_iomap_ops, &ctx, NULL);
+}
+
+static int
+xfs_vm_swap_activate(
+	struct swap_info_struct		*sis,
+	struct file			*swap_file,
+	sector_t			*span)
+{
+	struct xfs_inode		*ip = XFS_I(file_inode(swap_file));
+
+	if (xfs_is_zoned_inode(ip))
+		return -EINVAL;
+
+	/*
+	 * Swap file activation can race against concurrent shared extent
+	 * removal in files that have been cloned.  If this happens,
+	 * iomap_swapfile_iter() can fail because it encountered a shared
+	 * extent even though an operation is in progress to remove those
+	 * shared extents.
+	 *
+	 * This race becomes problematic when we defer extent removal
+	 * operations beyond the end of a syscall (i.e. use async background
+	 * processing algorithms).  Users think the extents are no longer
+	 * shared, but iomap_swapfile_iter() still sees them as shared
+	 * because the refcountbt entries for the extents being removed have
+	 * not yet been updated.  Hence the swapon call fails unexpectedly.
+	 *
+	 * The race condition is currently most obvious from the unlink()
+	 * operation as extent removal is deferred until after the last
+	 * reference to the inode goes away.  We then process the extent
+	 * removal asynchronously, hence triggers the "syscall completed but
+	 * work not done" condition mentioned above.  To close this race
+	 * window, we need to flush any pending inodegc operations to ensure
+	 * they have updated the refcountbt records before we try to map the
+	 * swapfile.
+	 */
+	xfs_inodegc_flush(ip->i_mount);
+
+	/*
+	 * Direct the swap code to the correct block device when this file
+	 * sits on the RT device.
+	 */
+	sis->bdev = xfs_inode_buftarg(ip)->bt_bdev;
+
+	return iomap_swapfile_activate(sis, swap_file, span,
+			&xfs_read_iomap_ops);
+}
+
+const struct address_space_operations xfs_address_space_operations = {
+	.read_folio		= xfs_vm_read_folio,
+	.readahead		= xfs_vm_readahead,
+	.writepages		= xfs_vm_writepages,
+	.dirty_folio		= iomap_dirty_folio,
+	.release_folio		= iomap_release_folio,
+	.invalidate_folio	= iomap_invalidate_folio,
+	.bmap			= xfs_vm_bmap,
+	.migrate_folio		= filemap_migrate_folio,
+	.is_partially_uptodate  = iomap_is_partially_uptodate,
+	.error_remove_folio	= generic_error_remove_folio,
+	.swap_activate		= xfs_vm_swap_activate,
+};
+
+const struct address_space_operations xfs_dax_aops = {
+	.writepages		= xfs_dax_writepages,
+	.dirty_folio		= noop_dirty_folio,
+	.swap_activate		= xfs_vm_swap_activate,
+};