Merge v6.12.26linux-rolling-lts

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 37 insertions, 4 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 559a3a577097..ba6b4a180e80 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;
@@ -528,12 +529,44 @@ 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 +582,11 @@ 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,
 };