1 files changed, 324 insertions, 67 deletions

diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 559a3a577097..1ee4f835ac3c 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"
@@ -19,6 +19,9 @@
 #include "xfs_reflink.h"
 #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;
@@ -76,6 +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.
  */
@@ -85,6 +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;
@@ -114,10 +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;
 	}
@@ -125,14 +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))
-		error = xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
+	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);
 }
@@ -175,23 +207,74 @@ 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);
 }
 
 /*
+ * 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, ip->i_ino, 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_pos(folio) + folio_size(folio), NULL);
+}
+
+/*
  * Fast revalidation of the cached writeback mapping. Return true if the current
  * mapping is valid, false otherwise.
  */
@@ -236,13 +319,12 @@ xfs_imap_valid(
 static int
 xfs_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_inode	*ip = XFS_I(wpc->inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			count = i_blocksize(inode);
+	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;
@@ -394,76 +476,194 @@ allocate_blocks:
 	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;
+
+	/* Page cache invalidation cannot be done in irq context. */
+	if (ioend->io_flags & IOMAP_IOEND_DONTCACHE)
+		return true;
+
+	return false;
+}
+
 static int
-xfs_prepare_ioend(
-	struct iomap_ioend	*ioend,
-	int			status)
+xfs_writeback_submit(
+	struct iomap_writepage_ctx	*wpc,
+	int				error)
 {
-	unsigned int		nofs_flag;
+	struct iomap_ioend		*ioend = wpc->wb_ctx;
 
 	/*
-	 * We can allocate memory here while doing writeback on behalf of
-	 * memory reclaim.  To avoid memory allocation deadlocks set the
-	 * task-wide nofs context for the following operations.
+	 * 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.
 	 */
-	nofs_flag = memalloc_nofs_save();
+	if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
+		unsigned int		nofs_flag;
 
-	/* Convert CoW extents to regular */
-	if (!status && (ioend->io_flags & IOMAP_F_SHARED)) {
-		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
+		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);
 	}
 
-	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))
+	/*
+	 * Send ioends that might require a transaction to the completion wq.
+	 */
+	if (xfs_ioend_needs_wq_completion(ioend))
 		ioend->io_bio.bi_end_io = xfs_end_bio;
-	return status;
+
+	return iomap_ioend_writeback_submit(wpc, error);
 }
 
-/*
- * 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)
+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)
 {
-	struct xfs_inode	*ip = XFS_I(folio->mapping->host);
+	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;
+		return -EIO;
 
-	xfs_alert_ratelimited(mp,
-		"page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
-			folio, ip->i_ino, pos);
+	XFS_ERRORTAG_DELAY(mp, XFS_ERRTAG_WB_DELAY_MS);
 
 	/*
-	 * 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.
+	 * 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_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
-				folio_pos(folio) + folio_size(folio));
+	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 const struct iomap_writeback_ops xfs_writeback_ops = {
-	.map_blocks		= xfs_map_blocks,
-	.prepare_ioend		= xfs_prepare_ioend,
-	.discard_folio		= xfs_discard_folio,
+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;
+
+	ioend->io_bio.bi_end_io = xfs_end_bio;
+	if (error) {
+		ioend->io_bio.bi_status = errno_to_blk_status(error);
+		bio_endio(&ioend->io_bio);
+		return error;
+	}
+	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
@@ -471,10 +671,35 @@ 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(XFS_I(mapping->host), XFS_ITRUNCATED);
-	return iomap_writepages(mapping, wbc, &wpc.ctx, &xfs_writeback_ops);
+	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
@@ -528,12 +753,44 @@ 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 +806,11 @@ 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,
 };