ext4: make ext4_da_map_blocks() buffer_head unaware

After calling the ext4_da_map_blocks(), a delalloc extent state could
be identified through the EXT4_MAP_DELAYED flag in map. So factor out
buffer_head related handles in ext4_da_map_blocks(), make this function
buffer_head unaware and becomes a common helper, and also update the
stale function commtents, preparing for the iomap da write path in the
future.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20240517124005.347221-11-yi.zhang@huaweicloud.com
Signed-off-by: Theodore Ts'o <tytso@mit.edu>

diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 91eb3ba6897003e4ae215e1f7593b8e854abc1e9..c81cf67d8e77ed5c3eff28c71f9475c97b048bb2 100644 (file)
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1749,36 +1749,32 @@ static int ext4_insert_delayed_blocks(struct inode *inode, ext4_lblk_t lblk,
 }
 
 /*
- * 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, 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, map->m_lblk, NULL, &es)) {
-               retval = es.es_len - (map->m_lblk - es.es_lblk);
-               if (retval > map->m_len)
-                       retval = map->m_len;
-               map->m_len = retval;
+               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;
@@ -1788,10 +1784,8 @@ 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;
                }
 
@@ -1806,7 +1800,7 @@ found:
 #ifdef ES_AGGRESSIVE_TEST
                ext4_map_blocks_es_recheck(NULL, inode, map, &orig_map, 0);
 #endif
-               return retval;
+               return 0;
        }
 
        /*
@@ -1820,7 +1814,7 @@ found:
                retval = ext4_map_query_blocks(NULL, inode, map);
        up_read(&EXT4_I(inode)->i_data_sem);
        if (retval)
-               return retval;
+               return retval < 0 ? retval : 0;
 
 add_delayed:
        down_write(&EXT4_I(inode)->i_data_sem);
@@ -1832,10 +1826,8 @@ add_delayed:
         * the extent status tree.
         */
        if (ext4_es_lookup_extent(inode, map->m_lblk, NULL, &es)) {
-               retval = es.es_len - (map->m_lblk - es.es_lblk);
-               if (retval > map->m_len)
-                       retval = map->m_len;
-               map->m_len = retval;
+               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);
@@ -1845,18 +1837,14 @@ add_delayed:
                retval = ext4_map_query_blocks(NULL, inode, map);
                if (retval) {
                        up_write(&EXT4_I(inode)->i_data_sem);
-                       return retval;
+                       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;
 }
 
@@ -1876,11 +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;
 
@@ -1889,10 +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, &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);