1 files changed, 52 insertions, 14 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 67877c36ed11..5077d52a775d 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -19,6 +19,7 @@
 #include "xfs_reflink.h"
 #include "xfs_errortag.h"
 #include "xfs_error.h"
+#include "xfs_icache.h"
 
 struct xfs_writepage_ctx {
 	struct iomap_writepage_ctx ctx;
@@ -114,7 +115,7 @@ 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) {
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
 			xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset,
 					offset + size);
@@ -125,9 +126,9 @@ xfs_end_ioend(
 	/*
 	 * Success: commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_flags & IOMAP_F_SHARED)
+	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))
@@ -395,10 +396,11 @@ 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;
 
 	/*
@@ -409,7 +411,7 @@ 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);
 	}
@@ -417,10 +419,14 @@ 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;
 }
 
 /*
@@ -462,7 +468,7 @@ xfs_discard_folio(
 
 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,
 };
 
@@ -528,12 +534,44 @@ xfs_vm_readahead(
 }
 
 static int
-xfs_iomap_swapfile_activate(
+xfs_vm_swap_activate(
 	struct swap_info_struct		*sis,
 	struct file			*swap_file,
 	sector_t			*span)
 {
-	sis->bdev = xfs_inode_buftarg(XFS_I(file_inode(swap_file)))->bt_bdev;
+	struct xfs_inode		*ip = XFS_I(file_inode(swap_file));
+
+	/*
+	 * 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);
 }
@@ -549,11 +587,11 @@ const struct address_space_operations xfs_address_space_operations = {
 	.migrate_folio		= filemap_migrate_folio,
 	.is_partially_uptodate  = iomap_is_partially_uptodate,
 	.error_remove_folio	= generic_error_remove_folio,
-	.swap_activate		= xfs_iomap_swapfile_activate,
+	.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_iomap_swapfile_activate,
+	.swap_activate		= xfs_vm_swap_activate,
 };