Merge tag 'xfs-5.10-fixes-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs fixes from Darrick Wong:

 - Fix an uninitialized struct problem

 - Fix an iomap problem zeroing unwritten EOF blocks

 - Fix some clumsy error handling when writeback fails on filesystems
   with blocksize < pagesize

 - Fix a retry loop not resetting loop variables properly

 - Fix scrub flagging rtinherit inodes on a non-rt fs, since the kernel
   actually does permit that combination

 - Fix excessive page cache flushing when unsharing part of a file

* tag 'xfs-5.10-fixes-3' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux:
  xfs: only flush the unshared range in xfs_reflink_unshare
  xfs: fix scrub flagging rtinherit even if there is no rt device
  xfs: fix missing CoW blocks writeback conversion retry
  iomap: clean up writeback state logic on writepage error
  iomap: support partial page discard on writeback block mapping failure
  xfs: flush new eof page on truncate to avoid post-eof corruption
  xfs: set xefi_discard when creating a deferred agfl free log intent item

8 files changed, 38 insertions, 33 deletions

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8180061b9e16..10cc7979ce38 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1374,6 +1374,7 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	WARN_ON_ONCE(!wpc->ioend && !list_empty(&submit_list));
 	WARN_ON_ONCE(!PageLocked(page));
 	WARN_ON_ONCE(PageWriteback(page));
+	WARN_ON_ONCE(PageDirty(page));
 
 	/*
 	 * We cannot cancel the ioend directly here on error.  We may have
@@ -1382,33 +1383,22 @@ iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	 * appropriately.
 	 */
 	if (unlikely(error)) {
+		/*
+		 * Let the filesystem know what portion of the current page
+		 * failed to map. If the page wasn't been added to ioend, it
+		 * won't be affected by I/O completion and we must unlock it
+		 * now.
+		 */
+		if (wpc->ops->discard_page)
+			wpc->ops->discard_page(page, file_offset);
 		if (!count) {
-			/*
-			 * If the current page hasn't been added to ioend, it
-			 * won't be affected by I/O completions and we must
-			 * discard and unlock it right here.
-			 */
-			if (wpc->ops->discard_page)
-				wpc->ops->discard_page(page);
 			ClearPageUptodate(page);
 			unlock_page(page);
 			goto done;
 		}
-
-		/*
-		 * If the page was not fully cleaned, we need to ensure that the
-		 * higher layers come back to it correctly.  That means we need
-		 * to keep the page dirty, and for WB_SYNC_ALL writeback we need
-		 * to ensure the PAGECACHE_TAG_TOWRITE index mark is not removed
-		 * so another attempt to write this page in this writeback sweep
-		 * will be made.
-		 */
-		set_page_writeback_keepwrite(page);
-	} else {
-		clear_page_dirty_for_io(page);
-		set_page_writeback(page);
 	}
 
+	set_page_writeback(page);
 	unlock_page(page);
 
 	/*
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 852b536551b5..15640015be9d 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -2467,6 +2467,7 @@ xfs_defer_agfl_block(
 	new->xefi_startblock = XFS_AGB_TO_FSB(mp, agno, agbno);
 	new->xefi_blockcount = 1;
 	new->xefi_oinfo = *oinfo;
+	new->xefi_skip_discard = false;
 
 	trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
 
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index e1bd484e5548..6747e97a7949 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -52,9 +52,9 @@ struct xfs_extent_free_item
 {
 	xfs_fsblock_t		xefi_startblock;/* starting fs block number */
 	xfs_extlen_t		xefi_blockcount;/* number of blocks in extent */
+	bool			xefi_skip_discard;
 	struct list_head	xefi_list;
 	struct xfs_owner_info	xefi_oinfo;	/* extent owner */
-	bool			xefi_skip_discard;
 };
 
 #define	XFS_BMAP_MAX_NMAP	4
diff --git a/fs/xfs/scrub/inode.c b/fs/xfs/scrub/inode.c
index 3aa85b64de36..bb25ff1b770d 100644
--- a/fs/xfs/scrub/inode.c
+++ b/fs/xfs/scrub/inode.c
@@ -121,8 +121,7 @@ xchk_inode_flags(
 		goto bad;
 
 	/* rt flags require rt device */
-	if ((flags & (XFS_DIFLAG_REALTIME | XFS_DIFLAG_RTINHERIT)) &&
-	    !mp->m_rtdev_targp)
+	if ((flags & XFS_DIFLAG_REALTIME) && !mp->m_rtdev_targp)
 		goto bad;
 
 	/* new rt bitmap flag only valid for rbmino */
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 55d126d4e096..4304c6416fbb 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -346,8 +346,8 @@ xfs_map_blocks(
 	ssize_t			count = i_blocksize(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 = NULLFILEOFF;
-	int			whichfork = XFS_DATA_FORK;
+	xfs_fileoff_t		cow_fsb;
+	int			whichfork;
 	struct xfs_bmbt_irec	imap;
 	struct xfs_iext_cursor	icur;
 	int			retries = 0;
@@ -381,6 +381,8 @@ xfs_map_blocks(
 	 * landed in a hole and we skip the block.
 	 */
 retry:
+	cow_fsb = NULLFILEOFF;
+	whichfork = XFS_DATA_FORK;
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	ASSERT(ip->i_df.if_format != XFS_DINODE_FMT_BTREE ||
 	       (ip->i_df.if_flags & XFS_IFEXTENTS));
@@ -527,13 +529,15 @@ xfs_prepare_ioend(
  */
 static void
 xfs_discard_page(
-	struct page		*page)
+	struct page		*page,
+	loff_t			fileoff)
 {
 	struct inode		*inode = page->mapping->host;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	loff_t			offset = page_offset(page);
-	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	unsigned int		pageoff = offset_in_page(fileoff);
+	xfs_fileoff_t		start_fsb = XFS_B_TO_FSBT(mp, fileoff);
+	xfs_fileoff_t		pageoff_fsb = XFS_B_TO_FSBT(mp, pageoff);
 	int			error;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
@@ -541,14 +545,14 @@ xfs_discard_page(
 
 	xfs_alert_ratelimited(mp,
 		"page discard on page "PTR_FMT", inode 0x%llx, offset %llu.",
-			page, ip->i_ino, offset);
+			page, ip->i_ino, fileoff);
 
 	error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
-			i_blocks_per_page(inode, page));
+			i_blocks_per_page(inode, page) - pageoff_fsb);
 	if (error && !XFS_FORCED_SHUTDOWN(mp))
 		xfs_alert(mp, "page discard unable to remove delalloc mapping.");
 out_invalidate:
-	iomap_invalidatepage(page, 0, PAGE_SIZE);
+	iomap_invalidatepage(page, pageoff, PAGE_SIZE - pageoff);
 }
 
 static const struct iomap_writeback_ops xfs_writeback_ops = {
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 5e165456da68..1414ab79eacf 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -911,6 +911,16 @@ xfs_setattr_size(
 		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
 				&did_zeroing, &xfs_buffered_write_iomap_ops);
 	} else {
+		/*
+		 * iomap won't detect a dirty page over an unwritten block (or a
+		 * cow block over a hole) and subsequently skips zeroing the
+		 * newly post-EOF portion of the page. Flush the new EOF to
+		 * convert the block before the pagecache truncate.
+		 */
+		error = filemap_write_and_wait_range(inode->i_mapping, newsize,
+						     newsize);
+		if (error)
+			return error;
 		error = iomap_truncate_page(inode, newsize, &did_zeroing,
 				&xfs_buffered_write_iomap_ops);
 	}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 16098dc42add..6fa05fb78189 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1502,7 +1502,8 @@ xfs_reflink_unshare(
 			&xfs_buffered_write_iomap_ops);
 	if (error)
 		goto out;
-	error = filemap_write_and_wait(inode->i_mapping);
+
+	error = filemap_write_and_wait_range(inode->i_mapping, offset, len);
 	if (error)
 		goto out;
 
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 172b3397a1a3..5bd3cac4df9c 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -221,7 +221,7 @@ struct iomap_writeback_ops {
 	 * Optional, allows the file system to discard state on a page where
 	 * we failed to submit any I/O.
 	 */
-	void (*discard_page)(struct page *page);
+	void (*discard_page)(struct page *page, loff_t fileoff);
 };
 
 struct iomap_writepage_ctx {