Merge branch 'xfs-7.1-merge' into for-next

Signed-off-by: Carlos Maiolino <cem@kernel.org>

fs/iomap/buffered-io.c

@@ -1632,16 +1632,12 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 	while ((ret = iomap_iter(&iter, ops)) > 0) {
 		const struct iomap *srcmap = iomap_iter_srcmap(&iter);
 
-		if (WARN_ON_ONCE((iter.iomap.flags & IOMAP_F_FOLIO_BATCH) &&
-				 srcmap->type != IOMAP_UNWRITTEN))
-			return -EIO;
-
 		if (!(iter.iomap.flags & IOMAP_F_FOLIO_BATCH) &&
 		    (srcmap->type == IOMAP_HOLE ||
 		     srcmap->type == IOMAP_UNWRITTEN)) {
 			s64 status;
 
-			if (range_dirty) {
+			if (range_dirty && srcmap->type == IOMAP_UNWRITTEN) {
 				range_dirty = false;
 				status = iomap_zero_iter_flush_and_stale(&iter);
 			} else {

fs/xfs/xfs_file.c

@@ -1306,6 +1306,23 @@ xfs_falloc_insert_range(
 	if (offset >= isize)
 		return -EINVAL;
 
+	/*
+	 * Let writeback clean up EOF folio state before we bump i_size. The
+	 * insert flushes before it starts shifting and under certain
+	 * circumstances we can write back blocks that should technically be
+	 * considered post-eof (and thus should not be submitted for writeback).
+	 *
+	 * For example, a large, dirty folio that spans EOF and is backed by
+	 * post-eof COW fork preallocation can cause block remap into the data
+	 * fork. This shifts back out beyond EOF, but creates an expectedly
+	 * written post-eof block. The insert is going to flush, unmap and
+	 * cancel prealloc across this whole range, so flush EOF now before we
+	 * bump i_size to provide consistent behavior.
+	 */
+	error = filemap_write_and_wait_range(inode->i_mapping, isize, isize);
+	if (error)
+		return error;
+
 	error = xfs_falloc_setsize(file, isize + len);
 	if (error)
 		return error;

fs/xfs/xfs_iomap.c

@@ -1590,6 +1590,7 @@ xfs_zoned_buffered_write_iomap_begin(
 {
 	struct iomap_iter	*iter =
 		container_of(iomap, struct iomap_iter, iomap);
+	struct address_space	*mapping = inode->i_mapping;
 	struct xfs_zone_alloc_ctx *ac = iter->private;
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
@@ -1614,6 +1615,7 @@ xfs_zoned_buffered_write_iomap_begin(
 	if (error)
 		return error;
 
+restart:
 	error = xfs_ilock_for_iomap(ip, flags, &lockmode);
 	if (error)
 		return error;
@@ -1651,14 +1653,6 @@ xfs_zoned_buffered_write_iomap_begin(
 				&smap))
 			smap.br_startoff = end_fsb; /* fake hole until EOF */
 		if (smap.br_startoff > offset_fsb) {
-			/*
-			 * We never need to allocate blocks for zeroing a hole.
-			 */
-			if (flags & IOMAP_ZERO) {
-				xfs_hole_to_iomap(ip, iomap, offset_fsb,
-						smap.br_startoff);
-				goto out_unlock;
-			}
 			end_fsb = min(end_fsb, smap.br_startoff);
 		} else {
 			end_fsb = min(end_fsb,
@@ -1690,6 +1684,33 @@ xfs_zoned_buffered_write_iomap_begin(
 	count_fsb = min3(end_fsb - offset_fsb, XFS_MAX_BMBT_EXTLEN,
 			 XFS_B_TO_FSB(mp, 1024 * PAGE_SIZE));
 
+	/*
+	 * When zeroing, don't allocate blocks for holes as they are already
+	 * zeroes, but we need to ensure that no extents exist in both the data
+	 * and COW fork to ensure this really is a hole.
+	 *
+	 * A window exists where we might observe a hole in both forks with
+	 * valid data in cache. Writeback removes the COW fork blocks on
+	 * submission but doesn't remap into the data fork until completion. If
+	 * the data fork was previously a hole, we'll fail to zero. Until we
+	 * find a way to avoid this transient state, check for dirty pagecache
+	 * and flush to wait on blocks to land in the data fork.
+	 */
+	if ((flags & IOMAP_ZERO) && srcmap->type == IOMAP_HOLE) {
+		if (filemap_range_needs_writeback(mapping, offset,
+				offset + count - 1)) {
+			xfs_iunlock(ip, lockmode);
+			error = filemap_write_and_wait_range(mapping, offset,
+					offset + count - 1);
+			if (error)
+				return error;
+			goto restart;
+		}
+
+		xfs_hole_to_iomap(ip, iomap, offset_fsb, end_fsb);
+		goto out_unlock;
+	}
+
 	/*
 	 * The block reservation is supposed to cover all blocks that the
 	 * operation could possible write, but there is a nasty corner case
@@ -1764,6 +1785,8 @@ xfs_buffered_write_iomap_begin(
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = xfs_iomap_end_fsb(mp, offset, count);
+	xfs_fileoff_t		cow_fsb = NULLFILEOFF;
+	xfs_fileoff_t		eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
 	struct xfs_bmbt_irec	imap, cmap;
 	struct xfs_iext_cursor	icur, ccur;
 	xfs_fsblock_t		prealloc_blocks = 0;
@@ -1808,30 +1831,96 @@ xfs_buffered_write_iomap_begin(
 		goto out_unlock;
 
 	/*
-	 * Search the data fork first to look up our source mapping.  We
-	 * always need the data fork map, as we have to return it to the
-	 * iomap code so that the higher level write code can read data in to
-	 * perform read-modify-write cycles for unaligned writes.
+	 * Search the data fork first to look up our source mapping. We always
+	 * need the data fork map, as we have to return it to the iomap code so
+	 * that the higher level write code can read data in to perform
+	 * read-modify-write cycles for unaligned writes.
+	 *
+	 * Then search the COW fork extent list even if we did not find a data
+	 * fork extent. This serves two purposes: first this implements the
+	 * speculative preallocation using cowextsize, so that we also unshare
+	 * block adjacent to shared blocks instead of just the shared blocks
+	 * themselves. Second the lookup in the extent list is generally faster
+	 * than going out to the shared extent tree.
 	 */
 	eof = !xfs_iext_lookup_extent(ip, &ip->i_df, offset_fsb, &icur, &imap);
 	if (eof)
 		imap.br_startoff = end_fsb; /* fake hole until the end */
+	if (xfs_is_cow_inode(ip)) {
+		if (!ip->i_cowfp) {
+			ASSERT(!xfs_is_reflink_inode(ip));
+			xfs_ifork_init_cow(ip);
+		}
+		cow_eof = !xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb,
+				&ccur, &cmap);
+		if (!cow_eof)
+			cow_fsb = cmap.br_startoff;
+	}
 
-	/* We never need to allocate blocks for zeroing or unsharing a hole. */
-	if ((flags & (IOMAP_UNSHARE | IOMAP_ZERO)) &&
-	    imap.br_startoff > offset_fsb) {
+	/* We never need to allocate blocks for unsharing a hole. */
+	if ((flags & IOMAP_UNSHARE) && imap.br_startoff > offset_fsb) {
 		xfs_hole_to_iomap(ip, iomap, offset_fsb, imap.br_startoff);
 		goto out_unlock;
 	}
 
+	/*
+	 * We may need to zero over a hole in the data fork if it's fronted by
+	 * COW blocks and dirty pagecache. Scan such file ranges for dirty
+	 * cache and fill the iomap batch with folios that need zeroing.
+	 */
+	if ((flags & IOMAP_ZERO) && imap.br_startoff > offset_fsb) {
+		loff_t		start, end;
+		unsigned int	fbatch_count;
+
+		imap.br_blockcount = imap.br_startoff - offset_fsb;
+		imap.br_startoff = offset_fsb;
+		imap.br_startblock = HOLESTARTBLOCK;
+		imap.br_state = XFS_EXT_NORM;
+
+		if (cow_fsb == NULLFILEOFF)
+			goto found_imap;
+		if (cow_fsb > offset_fsb) {
+			xfs_trim_extent(&imap, offset_fsb,
+					cow_fsb - offset_fsb);
+			goto found_imap;
+		}
+
+		/* no zeroing beyond eof, so split at the boundary */
+		if (offset_fsb >= eof_fsb)
+			goto found_imap;
+		if (offset_fsb < eof_fsb && end_fsb > eof_fsb)
+			xfs_trim_extent(&imap, offset_fsb,
+					eof_fsb - offset_fsb);
+
+		/* COW fork blocks overlap the hole */
+		xfs_trim_extent(&imap, offset_fsb,
+			    cmap.br_startoff + cmap.br_blockcount - offset_fsb);
+		start = XFS_FSB_TO_B(mp, imap.br_startoff);
+		end = XFS_FSB_TO_B(mp, imap.br_startoff + imap.br_blockcount);
+		fbatch_count = iomap_fill_dirty_folios(iter, &start, end,
+						       &iomap_flags);
+		xfs_trim_extent(&imap, offset_fsb,
+				XFS_B_TO_FSB(mp, start) - offset_fsb);
+
+		/*
+		 * Report the COW mapping if we have folios to zero. Otherwise
+		 * ignore the COW blocks as preallocation and report a hole.
+		 */
+		if (fbatch_count) {
+			xfs_trim_extent(&cmap, imap.br_startoff,
+					imap.br_blockcount);
+			imap.br_startoff = end_fsb;	/* fake hole */
+			goto found_cow;
+		}
+		goto found_imap;
+	}
+
 	/*
 	 * For zeroing, trim extents that extend beyond the EOF block. If a
 	 * delalloc extent starts beyond the EOF block, convert it to an
 	 * unwritten extent.
 	 */
 	if (flags & IOMAP_ZERO) {
-		xfs_fileoff_t eof_fsb = XFS_B_TO_FSB(mp, XFS_ISIZE(ip));
-
 		if (isnullstartblock(imap.br_startblock) &&
 		    offset_fsb >= eof_fsb)
 			goto convert_delay;
@@ -1864,24 +1953,13 @@ xfs_buffered_write_iomap_begin(
 	}
 
 	/*
-	 * Search the COW fork extent list even if we did not find a data fork
-	 * extent.  This serves two purposes: first this implements the
-	 * speculative preallocation using cowextsize, so that we also unshare
-	 * block adjacent to shared blocks instead of just the shared blocks
-	 * themselves.  Second the lookup in the extent list is generally faster
-	 * than going out to the shared extent tree.
+	 * Now that we've handled any operation specific special cases, at this
+	 * point we can report a COW mapping if found.
 	 */
-	if (xfs_is_cow_inode(ip)) {
-		if (!ip->i_cowfp) {
-			ASSERT(!xfs_is_reflink_inode(ip));
-			xfs_ifork_init_cow(ip);
-		}
-		cow_eof = !xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb,
-				&ccur, &cmap);
-		if (!cow_eof && cmap.br_startoff <= offset_fsb) {
-			trace_xfs_reflink_cow_found(ip, &cmap);
-			goto found_cow;
-		}
+	if (xfs_is_cow_inode(ip) &&
+	    !cow_eof && cmap.br_startoff <= offset_fsb) {
+		trace_xfs_reflink_cow_found(ip, &cmap);
+		goto found_cow;
 	}
 
 	if (imap.br_startoff <= offset_fsb) {

fs/xfs/xfs_mount.c

@@ -44,17 +44,36 @@
 #include "xfs_healthmon.h"
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
-static int xfs_uuid_table_size;
-static uuid_t *xfs_uuid_table;
+static DEFINE_XARRAY_ALLOC(xfs_uuid_table);
+
+static uuid_t *
+xfs_uuid_search(
+	uuid_t		*new_uuid)
+{
+	unsigned long	index = 0;
+	uuid_t		*uuid;
+
+	xa_for_each(&xfs_uuid_table, index, uuid) {
+		if (uuid_equal(uuid, new_uuid))
+			return uuid;
+	}
+	return NULL;
+}
+
+static void
+xfs_uuid_delete(
+	uuid_t		*uuid,
+	unsigned int	index)
+{
+	ASSERT(uuid_equal(xa_load(&xfs_uuid_table, index), uuid));
+	xa_erase(&xfs_uuid_table, index);
+}
 
 void
 xfs_uuid_table_free(void)
 {
-	if (xfs_uuid_table_size == 0)
-		return;
-	kfree(xfs_uuid_table);
-	xfs_uuid_table = NULL;
-	xfs_uuid_table_size = 0;
+	ASSERT(xa_empty(&xfs_uuid_table));
+	xa_destroy(&xfs_uuid_table);
 }
 
 /*
@@ -66,7 +85,7 @@ xfs_uuid_mount(
 	struct xfs_mount	*mp)
 {
 	uuid_t			*uuid = &mp->m_sb.sb_uuid;
-	int			hole, i;
+	int			ret;
 
 	/* Publish UUID in struct super_block */
 	super_set_uuid(mp->m_super, uuid->b, sizeof(*uuid));
@@ -80,30 +99,17 @@ xfs_uuid_mount(
 	}
 
 	mutex_lock(&xfs_uuid_table_mutex);
-	for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) {
-		if (uuid_is_null(&xfs_uuid_table[i])) {
-			hole = i;
-			continue;
-		}
-		if (uuid_equal(uuid, &xfs_uuid_table[i]))
-			goto out_duplicate;
+	if (unlikely(xfs_uuid_search(uuid))) {
+		xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount",
+				uuid);
+		mutex_unlock(&xfs_uuid_table_mutex);
+		return -EINVAL;
 	}
 
-	if (hole < 0) {
-		xfs_uuid_table = krealloc(xfs_uuid_table,
-			(xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
-			GFP_KERNEL | __GFP_NOFAIL);
-		hole = xfs_uuid_table_size++;
-	}
-	xfs_uuid_table[hole] = *uuid;
+	ret = xa_alloc(&xfs_uuid_table, &mp->m_uuid_table_index, uuid,
+				xa_limit_32b, GFP_KERNEL);
 	mutex_unlock(&xfs_uuid_table_mutex);
-
-	return 0;
-
- out_duplicate:
-	mutex_unlock(&xfs_uuid_table_mutex);
-	xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid);
-	return -EINVAL;
+	return ret;
 }
 
 STATIC void
@@ -111,21 +117,12 @@ xfs_uuid_unmount(
 	struct xfs_mount	*mp)
 {
 	uuid_t			*uuid = &mp->m_sb.sb_uuid;
-	int			i;
 
 	if (xfs_has_nouuid(mp))
 		return;
 
 	mutex_lock(&xfs_uuid_table_mutex);
-	for (i = 0; i < xfs_uuid_table_size; i++) {
-		if (uuid_is_null(&xfs_uuid_table[i]))
-			continue;
-		if (!uuid_equal(uuid, &xfs_uuid_table[i]))
-			continue;
-		memset(&xfs_uuid_table[i], 0, sizeof(uuid_t));
-		break;
-	}
-	ASSERT(i < xfs_uuid_table_size);
+	xfs_uuid_delete(uuid, mp->m_uuid_table_index);
 	mutex_unlock(&xfs_uuid_table_mutex);
 }
 

fs/xfs/xfs_mount.h

@@ -346,6 +346,9 @@ typedef struct xfs_mount {
 
 	/* Private data referring to a health monitor object. */
 	struct xfs_healthmon __rcu	*m_healthmon;
+
+	/* Index of uuid record in the uuid xarray. */
+	unsigned int		m_uuid_table_index;
 } xfs_mount_t;
 
 #define M_IGEO(mp)		(&(mp)->m_ino_geo)