1 files changed, 59 insertions, 62 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 813f85156b0c..6d9965b546cb 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;
@@ -112,11 +113,11 @@ xfs_end_ioend(
 	 * longer dirty. If we don't remove delalloc blocks here, they become
 	 * stale and can corrupt free space accounting on unmount.
 	 */
-	error = blk_status_to_errno(ioend->io_bio->bi_status);
+	error = blk_status_to_errno(ioend->io_bio.bi_status);
 	if (unlikely(error)) {
 		if (ioend->io_flags & IOMAP_F_SHARED) {
 			xfs_reflink_cancel_cow_range(ip, offset, size, true);
-			xfs_bmap_punch_delalloc_range(ip, offset,
+			xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, offset,
 					offset + size);
 		}
 		goto done;
@@ -131,7 +132,7 @@ xfs_end_ioend(
 		error = xfs_iomap_write_unwritten(ip, offset, size, false);
 
 	if (!error && xfs_ioend_is_append(ioend))
-		error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
+		error = xfs_setfilesize(ip, offset, size);
 done:
 	iomap_finish_ioends(ioend, error);
 	memalloc_nofs_restore(nofs_flag);
@@ -179,7 +180,7 @@ STATIC void
 xfs_end_bio(
 	struct bio		*bio)
 {
-	struct iomap_ioend	*ioend = bio->bi_private;
+	struct iomap_ioend	*ioend = iomap_ioend_from_bio(bio);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
 	unsigned long		flags;
 
@@ -233,50 +234,12 @@ xfs_imap_valid(
 	return true;
 }
 
-/*
- * Pass in a dellalloc extent and convert it to real extents, return the real
- * extent that maps offset_fsb in wpc->iomap.
- *
- * 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.
- */
-static int
-xfs_convert_blocks(
-	struct iomap_writepage_ctx *wpc,
-	struct xfs_inode	*ip,
-	int			whichfork,
-	loff_t			offset)
-{
-	int			error;
-	unsigned		*seq;
-
-	if (whichfork == XFS_COW_FORK)
-		seq = &XFS_WPC(wpc)->cow_seq;
-	else
-		seq = &XFS_WPC(wpc)->data_seq;
-
-	/*
-	 * Attempt to allocate whatever delalloc extent currently backs offset
-	 * and put the result into wpc->iomap.  Allocate in a loop because it
-	 * may take several attempts to allocate real blocks for a contiguous
-	 * delalloc extent if free space is sufficiently fragmented.
-	 */
-	do {
-		error = xfs_bmapi_convert_delalloc(ip, whichfork, offset,
-				&wpc->iomap, seq);
-		if (error)
-			return error;
-	} while (wpc->iomap.offset + wpc->iomap.length <= offset);
-
-	return 0;
-}
-
 static int
 xfs_map_blocks(
 	struct iomap_writepage_ctx *wpc,
 	struct inode		*inode,
-	loff_t			offset)
+	loff_t			offset,
+	unsigned int		len)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -289,6 +252,7 @@ xfs_map_blocks(
 	struct xfs_iext_cursor	icur;
 	int			retries = 0;
 	int			error = 0;
+	unsigned int		*seq;
 
 	if (xfs_is_shutdown(mp))
 		return -EIO;
@@ -386,7 +350,19 @@ retry:
 	trace_xfs_map_blocks_found(ip, offset, count, whichfork, &imap);
 	return 0;
 allocate_blocks:
-	error = xfs_convert_blocks(wpc, ip, whichfork, offset);
+	/*
+	 * 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
@@ -444,7 +420,7 @@ xfs_prepare_ioend(
 	/* 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))
-		ioend->io_bio->bi_end_io = xfs_end_bio;
+		ioend->io_bio.bi_end_io = xfs_end_bio;
 	return status;
 }
 
@@ -468,7 +444,6 @@ xfs_discard_folio(
 {
 	struct xfs_inode	*ip = XFS_I(folio->mapping->host);
 	struct xfs_mount	*mp = ip->i_mount;
-	int			error;
 
 	if (xfs_is_shutdown(mp))
 		return;
@@ -482,11 +457,8 @@ xfs_discard_folio(
 	 * 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.
 	 */
-	error = xfs_bmap_punch_delalloc_range(ip, pos,
+	xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
 				folio_pos(folio) + folio_size(folio));
-
-	if (error && !xfs_is_shutdown(mp))
-		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 }
 
 static const struct iomap_writeback_ops xfs_writeback_ops = {
@@ -502,13 +474,6 @@ xfs_vm_writepages(
 {
 	struct xfs_writepage_ctx wpc = { };
 
-	/*
-	 * Writing back data in a transaction context can result in recursive
-	 * transactions. This is bad, so issue a warning and get out of here.
-	 */
-	if (WARN_ON_ONCE(current->journal_info))
-		return 0;
-
 	xfs_iflags_clear(XFS_I(mapping->host), XFS_ITRUNCATED);
 	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
 }
@@ -564,12 +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);
 }
@@ -585,11 +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,
 };