1 files changed, 169 insertions, 97 deletions

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 537803250ca9..941c1c0d5c6e 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -453,6 +453,35 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
 }
 #endif /* ES_AGGRESSIVE_TEST */
 
+static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
+				 struct ext4_map_blocks *map)
+{
+	unsigned int status;
+	int retval;
+
+	if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+		retval = ext4_ext_map_blocks(handle, inode, map, 0);
+	else
+		retval = ext4_ind_map_blocks(handle, inode, map, 0);
+
+	if (retval <= 0)
+		return retval;
+
+	if (unlikely(retval != map->m_len)) {
+		ext4_warning(inode->i_sb,
+			     "ES len assertion failed for inode "
+			     "%lu: retval %d != map->m_len %d",
+			     inode->i_ino, retval, map->m_len);
+		WARN_ON(1);
+	}
+
+	status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+			EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+	ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+			      map->m_pblk, status);
+	return retval;
+}
+
 /*
  * The ext4_map_blocks() function tries to look up the requested blocks,
  * and returns if the blocks are already mapped.
@@ -1450,9 +1479,9 @@ static int ext4_journalled_write_end(struct file *file,
 }
 
 /*
- * Reserve space for a single cluster
+ * Reserve space for 'nr_resv' clusters
  */
-static int ext4_da_reserve_space(struct inode *inode)
+static int ext4_da_reserve_space(struct inode *inode, int nr_resv)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -1463,18 +1492,18 @@ static int ext4_da_reserve_space(struct inode *inode)
 	 * us from metadata over-estimation, though we may go over by
 	 * a small amount in the end.  Here we just reserve for data.
 	 */
-	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, 1));
+	ret = dquot_reserve_block(inode, EXT4_C2B(sbi, nr_resv));
 	if (ret)
 		return ret;
 
 	spin_lock(&ei->i_block_reservation_lock);
-	if (ext4_claim_free_clusters(sbi, 1, 0)) {
+	if (ext4_claim_free_clusters(sbi, nr_resv, 0)) {
 		spin_unlock(&ei->i_block_reservation_lock);
-		dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1));
+		dquot_release_reservation_block(inode, EXT4_C2B(sbi, nr_resv));
 		return -ENOSPC;
 	}
-	ei->i_reserved_data_blocks++;
-	trace_ext4_da_reserve_space(inode);
+	ei->i_reserved_data_blocks += nr_resv;
+	trace_ext4_da_reserve_space(inode, nr_resv);
 	spin_unlock(&ei->i_block_reservation_lock);
 
 	return 0;       /* success */
@@ -1621,24 +1650,58 @@ static void ext4_print_free_blocks(struct inode *inode)
 }
 
 /*
- * ext4_insert_delayed_block - adds a delayed block to the extents status
- *                             tree, incrementing the reserved cluster/block
- *                             count or making a pending reservation
- *                             where needed
+ * Check whether the cluster containing lblk has been allocated or has
+ * delalloc reservation.
+ *
+ * Returns 0 if the cluster doesn't have either, 1 if it has delalloc
+ * reservation, 2 if it's already been allocated, negative error code on
+ * failure.
+ */
+static int ext4_clu_alloc_state(struct inode *inode, ext4_lblk_t lblk)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+	int ret;
+
+	/* Has delalloc reservation? */
+	if (ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk))
+		return 1;
+
+	/* Already been allocated? */
+	if (ext4_es_scan_clu(inode, &ext4_es_is_mapped, lblk))
+		return 2;
+	ret = ext4_clu_mapped(inode, EXT4_B2C(sbi, lblk));
+	if (ret < 0)
+		return ret;
+	if (ret > 0)
+		return 2;
+
+	return 0;
+}
+
+/*
+ * ext4_insert_delayed_blocks - adds a multiple delayed blocks to the extents
+ *                              status tree, incrementing the reserved
+ *                              cluster/block count or making pending
+ *                              reservations where needed
  *
  * @inode - file containing the newly added block
- * @lblk - logical block to be added
+ * @lblk - start logical block to be added
+ * @len - length of blocks to be added
  *
  * Returns 0 on success, negative error code on failure.
  */
-static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
+static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
+				      ext4_lblk_t len)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 	int ret;
-	bool allocated = false;
+	bool lclu_allocated = false;
+	bool end_allocated = false;
+	ext4_lblk_t resv_clu;
+	ext4_lblk_t end = lblk + len - 1;
 
 	/*
-	 * If the cluster containing lblk is shared with a delayed,
+	 * If the cluster containing lblk or end is shared with a delayed,
 	 * written, or unwritten extent in a bigalloc file system, it's
 	 * already been accounted for and does not need to be reserved.
 	 * A pending reservation must be made for the cluster if it's
@@ -1649,81 +1712,84 @@ static int ext4_insert_delayed_block(struct inode *inode, ext4_lblk_t lblk)
 	 * extents status tree doesn't get a match.
 	 */
 	if (sbi->s_cluster_ratio == 1) {
-		ret = ext4_da_reserve_space(inode);
+		ret = ext4_da_reserve_space(inode, len);
 		if (ret != 0)   /* ENOSPC */
 			return ret;
 	} else {   /* bigalloc */
-		if (!ext4_es_scan_clu(inode, &ext4_es_is_delonly, lblk)) {
-			if (!ext4_es_scan_clu(inode,
-					      &ext4_es_is_mapped, lblk)) {
-				ret = ext4_clu_mapped(inode,
-						      EXT4_B2C(sbi, lblk));
-				if (ret < 0)
-					return ret;
-				if (ret == 0) {
-					ret = ext4_da_reserve_space(inode);
-					if (ret != 0)   /* ENOSPC */
-						return ret;
-				} else {
-					allocated = true;
-				}
-			} else {
-				allocated = true;
+		resv_clu = EXT4_B2C(sbi, end) - EXT4_B2C(sbi, lblk) + 1;
+
+		ret = ext4_clu_alloc_state(inode, lblk);
+		if (ret < 0)
+			return ret;
+		if (ret > 0) {
+			resv_clu--;
+			lclu_allocated = (ret == 2);
+		}
+
+		if (EXT4_B2C(sbi, lblk) != EXT4_B2C(sbi, end)) {
+			ret = ext4_clu_alloc_state(inode, end);
+			if (ret < 0)
+				return ret;
+			if (ret > 0) {
+				resv_clu--;
+				end_allocated = (ret == 2);
 			}
 		}
+
+		if (resv_clu) {
+			ret = ext4_da_reserve_space(inode, resv_clu);
+			if (ret != 0)   /* ENOSPC */
+				return ret;
+		}
 	}
 
-	ext4_es_insert_delayed_block(inode, lblk, allocated);
+	ext4_es_insert_delayed_extent(inode, lblk, len, lclu_allocated,
+				      end_allocated);
 	return 0;
 }
 
 /*
- * This function is grabs code from the very beginning of
- * ext4_map_blocks, but assumes that the caller is from delayed write
- * time. This function looks up the requested blocks and sets the
- * buffer delay bit under the protection of i_data_sem.
+ * Looks up the requested blocks and sets the delalloc extent map.
+ * First try to look up for the extent entry that contains the requested
+ * blocks in the extent status tree without i_data_sem, then try to look
+ * up for the ondisk extent mapping with i_data_sem in read mode,
+ * finally hold i_data_sem in write mode, looks up again and add a
+ * delalloc extent entry if it still couldn't find any extent. Pass out
+ * the mapped extent through @map and return 0 on success.
  */
-static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
-			      struct ext4_map_blocks *map,
-			      struct buffer_head *bh)
+static int ext4_da_map_blocks(struct inode *inode, struct ext4_map_blocks *map)
 {
 	struct extent_status es;
 	int retval;
-	sector_t invalid_block = ~((sector_t) 0xffff);
 #ifdef ES_AGGRESSIVE_TEST
 	struct ext4_map_blocks orig_map;
 
 	memcpy(&orig_map, map, sizeof(*map));
 #endif
 
-	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
-		invalid_block = ~0;
-
 	map->m_flags = 0;
 	ext_debug(inode, "max_blocks %u, logical block %lu\n", map->m_len,
 		  (unsigned long) map->m_lblk);
 
 	/* Lookup extent status tree firstly */
-	if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+		map->m_len = min_t(unsigned int, map->m_len,
+				   es.es_len - (map->m_lblk - es.es_lblk));
+
 		if (ext4_es_is_hole(&es))
 			goto add_delayed;
 
+found:
 		/*
 		 * Delayed extent could be allocated by fallocate.
 		 * So we need to check it.
 		 */
-		if (ext4_es_is_delayed(&es) && !ext4_es_is_unwritten(&es)) {
-			map_bh(bh, inode->i_sb, invalid_block);
-			set_buffer_new(bh);
-			set_buffer_delay(bh);
+		if (ext4_es_is_delonly(&es)) {
+			map->m_flags |= EXT4_MAP_DELAYED;
 			return 0;
 		}
 
-		map->m_pblk = ext4_es_pblock(&es) + iblock - es.es_lblk;
-		retval = es.es_len - (iblock - es.es_lblk);
-		if (retval > map->m_len)
-			retval = map->m_len;
-		map->m_len = retval;
+		map->m_pblk = ext4_es_pblock(&es) + map->m_lblk - es.es_lblk;
 		if (ext4_es_is_written(&es))
 			map->m_flags |= EXT4_MAP_MAPPED;
 		else if (ext4_es_is_unwritten(&es))
@@ -1734,7 +1800,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 #ifdef ES_AGGRESSIVE_TEST
 		ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
 #endif
-		return retval;
+		return 0;
 	}
 
 	/*
@@ -1744,44 +1810,41 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
 	down_read(&EXT4_I(inode)->i_data_sem);
 	if (ext4_has_inline_data(inode))
 		retval = 0;
-	else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
-		retval = ext4_ext_map_blocks(NULL, inode, map, 0);
 	else
-		retval = ext4_ind_map_blocks(NULL, inode, map, 0);
-	if (retval < 0) {
-		up_read(&EXT4_I(inode)->i_data_sem);
-		return retval;
-	}
-	if (retval > 0) {
-		unsigned int status;
-
-		if (unlikely(retval != map->m_len)) {
-			ext4_warning(inode->i_sb,
-				     "ES len assertion failed for inode "
-				     "%lu: retval %d != map->m_len %d",
-				     inode->i_ino, retval, map->m_len);
-			WARN_ON(1);
-		}
-
-		status = map->m_flags & EXT4_MAP_UNWRITTEN ?
-				EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
-		ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
-				      map->m_pblk, status);
-		up_read(&EXT4_I(inode)->i_data_sem);
-		return retval;
-	}
+		retval = ext4_map_query_blocks(NULL, inode, map);
 	up_read(&EXT4_I(inode)->i_data_sem);
+	if (retval)
+		return retval < 0 ? retval : 0;
 
 add_delayed:
 	down_write(&EXT4_I(inode)->i_data_sem);
-	retval = ext4_insert_delayed_block(inode, map->m_lblk);
+	/*
+	 * Page fault path (ext4_page_mkwrite does not take i_rwsem)
+	 * and fallocate path (no folio lock) can race. Make sure we
+	 * lookup the extent status tree here again while i_data_sem
+	 * is held in write mode, before inserting a new da entry in
+	 * the extent status tree.
+	 */
+	if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
+		map->m_len = min_t(unsigned int, map->m_len,
+				   es.es_len - (map->m_lblk - es.es_lblk));
+
+		if (!ext4_es_is_hole(&es)) {
+			up_write(&EXT4_I(inode)->i_data_sem);
+			goto found;
+		}
+	} else if (!ext4_has_inline_data(inode)) {
+		retval = ext4_map_query_blocks(NULL, inode, map);
+		if (retval) {
+			up_write(&EXT4_I(inode)->i_data_sem);
+			return retval < 0 ? retval : 0;
+		}
+	}
+
+	map->m_flags |= EXT4_MAP_DELAYED;
+	retval = ext4_insert_delayed_blocks(inode, map->m_lblk, map->m_len);
 	up_write(&EXT4_I(inode)->i_data_sem);
-	if (retval)
-		return retval;
 
-	map_bh(bh, inode->i_sb, invalid_block);
-	set_buffer_new(bh);
-	set_buffer_delay(bh);
 	return retval;
 }
 
@@ -1801,11 +1864,15 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 			   struct buffer_head *bh, int create)
 {
 	struct ext4_map_blocks map;
+	sector_t invalid_block = ~((sector_t) 0xffff);
 	int ret = 0;
 
 	BUG_ON(create == 0);
 	BUG_ON(bh->b_size != inode->i_sb->s_blocksize);
 
+	if (invalid_block < ext4_blocks_count(EXT4_SB(inode->i_sb)->s_es))
+		invalid_block = ~0;
+
 	map.m_lblk = iblock;
 	map.m_len = 1;
 
@@ -1814,10 +1881,17 @@ int ext4_da_get_block_prep(struct inode *inode, sector_t iblock,
 	 * preallocated blocks are unmapped but should treated
 	 * the same as allocated blocks.
 	 */
-	ret = ext4_da_map_blocks(inode, iblock, &map, bh);
-	if (ret <= 0)
+	ret = ext4_da_map_blocks(inode, &map);
+	if (ret < 0)
 		return ret;
 
+	if (map.m_flags & EXT4_MAP_DELAYED) {
+		map_bh(bh, inode->i_sb, invalid_block);
+		set_buffer_new(bh);
+		set_buffer_delay(bh);
+		return 0;
+	}
+
 	map_bh(bh, inode->i_sb, map.m_pblk);
 	ext4_update_bh_state(bh, map.m_flags);
 
@@ -1865,7 +1939,7 @@ static int mpage_submit_folio(struct mpage_da_data *mpd, struct folio *folio)
 	len = folio_size(folio);
 	if (folio_pos(folio) + len > size &&
 	    !ext4_verity_in_progress(mpd->inode))
-		len = size & ~PAGE_MASK;
+		len = size & (len - 1);
 	err = ext4_bio_write_folio(&mpd->io_submit, folio, len);
 	if (!err)
 		mpd->wbc->nr_to_write--;
@@ -2334,7 +2408,7 @@ static int mpage_journal_page_buffers(handle_t *handle,
 
 	if (folio_pos(folio) + len > size &&
 	    !ext4_verity_in_progress(inode))
-		len = size - folio_pos(folio);
+		len = size & (len - 1);
 
 	return ext4_journal_folio_buffers(handle, folio, len);
 }
@@ -2887,9 +2961,6 @@ retry:
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	/* In case writeback began while the folio was unlocked */
-	folio_wait_stable(folio);
-
 #ifdef CONFIG_FS_ENCRYPTION
 	ret = ext4_block_write_begin(folio, pos, len, ext4_da_get_block_prep);
 #else
@@ -2948,6 +3019,11 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	bool disksize_changed = false;
 	loff_t new_i_size;
 
+	if (unlikely(!folio_buffers(folio))) {
+		folio_unlock(folio);
+		folio_put(folio);
+		return -EIO;
+	}
 	/*
 	 * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
 	 * flag, which all that's needed to trigger page writeback.
@@ -3530,7 +3606,6 @@ static const struct address_space_operations ext4_aops = {
 	.bmap			= ext4_bmap,
 	.invalidate_folio	= ext4_invalidate_folio,
 	.release_folio		= ext4_release_folio,
-	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_folio	= generic_error_remove_folio,
@@ -3547,7 +3622,6 @@ static const struct address_space_operations ext4_journalled_aops = {
 	.bmap			= ext4_bmap,
 	.invalidate_folio	= ext4_journalled_invalidate_folio,
 	.release_folio		= ext4_release_folio,
-	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio_norefs,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_folio	= generic_error_remove_folio,
@@ -3564,7 +3638,6 @@ static const struct address_space_operations ext4_da_aops = {
 	.bmap			= ext4_bmap,
 	.invalidate_folio	= ext4_invalidate_folio,
 	.release_folio		= ext4_release_folio,
-	.direct_IO		= noop_direct_IO,
 	.migrate_folio		= buffer_migrate_folio,
 	.is_partially_uptodate  = block_is_partially_uptodate,
 	.error_remove_folio	= generic_error_remove_folio,
@@ -3573,7 +3646,6 @@ static const struct address_space_operations ext4_da_aops = {
 
 static const struct address_space_operations ext4_dax_aops = {
 	.writepages		= ext4_dax_writepages,
-	.direct_IO		= noop_direct_IO,
 	.dirty_folio		= noop_dirty_folio,
 	.bmap			= ext4_bmap,
 	.swap_activate		= ext4_iomap_swap_activate,