ext4: Introduce FALLOC_FL_ZERO_RANGE flag for fallocate

Introduce new FALLOC_FL_ZERO_RANGE flag for fallocate. This has the same
functionality as xfs ioctl XFS_IOC_ZERO_RANGE.

It can be used to convert a range of file to zeros preferably without
issuing data IO. Blocks should be preallocated for the regions that span
holes in the file, and the entire range is preferable converted to
unwritten extents

This can be also used to preallocate blocks past EOF in the same way as
with fallocate. Flag FALLOC_FL_KEEP_SIZE which should cause the inode
size to remain the same.

Also add appropriate tracepoints.

Signed-off-by: Lukas Czerner <lczerner@redhat.com>
Signed-off-by: "Theodore Ts'o" <tytso@mit.edu>

4 files changed, 307 insertions, 53 deletions

diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index beec42750a8c..1b3cbf8cacf9 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -568,6 +568,8 @@ enum {
 #define EXT4_GET_BLOCKS_NO_LOCK                 0x0100
         /* Do not put hole in extent cache */
 #define EXT4_GET_BLOCKS_NO_PUT_HOLE             0x0200
+        /* Convert written extents to unwritten */
+#define EXT4_GET_BLOCKS_CONVERT_UNWRITTEN       0x0400
 
 /*
  * The bit position of these flags must not overlap with any of the
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 2db2d77769a2..464e95da716e 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -3602,6 +3602,8 @@ out:
  *   b> Splits in two extents: Write is happening at either end of the extent
  *   c> Splits in three extents: Somone is writing in middle of the extent
  *
+ * This works the same way in the case of initialized -> unwritten conversion.
+ *
  * One of more index blocks maybe needed if the extent tree grow after
  * the uninitialized extent split. To prevent ENOSPC occur at the IO
  * complete, we need to split the uninitialized extent before DIO submit
@@ -3612,7 +3614,7 @@ out:
  *
  * Returns the size of uninitialized extent to be written on success.
  */
-static int ext4_split_unwritten_extents(handle_t *handle,
+static int ext4_split_convert_extents(handle_t *handle,
                                         struct inode *inode,
                                         struct ext4_map_blocks *map,
                                         struct ext4_ext_path *path,
@@ -3624,9 +3626,9 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         unsigned int ee_len;
         int split_flag = 0, depth;
 
-        ext_debug("ext4_split_unwritten_extents: inode %lu, logical"
-                "block %llu, max_blocks %u\n", inode->i_ino,
-                (unsigned long long)map->m_lblk, map->m_len);
+        ext_debug("%s: inode %lu, logical block %llu, max_blocks %u\n",
+                  __func__, inode->i_ino,
+                  (unsigned long long)map->m_lblk, map->m_len);
 
         eof_block = (inode->i_size + inode->i_sb->s_blocksize - 1) >>
                 inode->i_sb->s_blocksize_bits;
@@ -3641,14 +3643,73 @@ static int ext4_split_unwritten_extents(handle_t *handle,
         ee_block = le32_to_cpu(ex->ee_block);
         ee_len = ext4_ext_get_actual_len(ex);
 
-        split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0;
-        split_flag |= EXT4_EXT_MARK_UNINIT2;
-        if (flags & EXT4_GET_BLOCKS_CONVERT)
-                split_flag |= EXT4_EXT_DATA_VALID2;
+        /* Convert to unwritten */
+        if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) {
+                split_flag |= EXT4_EXT_DATA_VALID1;
+        /* Convert to initialized */
+        } else if (flags & EXT4_GET_BLOCKS_CONVERT) {
+                split_flag |= ee_block + ee_len <= eof_block ?
+                              EXT4_EXT_MAY_ZEROOUT : 0;
+                split_flag |= (EXT4_EXT_MARK_UNINIT2 | EXT4_EXT_DATA_VALID2);
+        }
         flags |= EXT4_GET_BLOCKS_PRE_IO;
         return ext4_split_extent(handle, inode, path, map, split_flag, flags);
 }
 
+static int ext4_convert_initialized_extents(handle_t *handle,
+                                            struct inode *inode,
+                                            struct ext4_map_blocks *map,
+                                            struct ext4_ext_path *path)
+{
+        struct ext4_extent *ex;
+        ext4_lblk_t ee_block;
+        unsigned int ee_len;
+        int depth;
+        int err = 0;
+
+        depth = ext_depth(inode);
+        ex = path[depth].p_ext;
+        ee_block = le32_to_cpu(ex->ee_block);
+        ee_len = ext4_ext_get_actual_len(ex);
+
+        ext_debug("%s: inode %lu, logical"
+                "block %llu, max_blocks %u\n", __func__, inode->i_ino,
+                  (unsigned long long)ee_block, ee_len);
+
+        if (ee_block != map->m_lblk || ee_len > map->m_len) {
+                err = ext4_split_convert_extents(handle, inode, map, path,
+                                EXT4_GET_BLOCKS_CONVERT_UNWRITTEN);
+                if (err < 0)
+                        goto out;
+                ext4_ext_drop_refs(path);
+                path = ext4_ext_find_extent(inode, map->m_lblk, path, 0);
+                if (IS_ERR(path)) {
+                        err = PTR_ERR(path);
+                        goto out;
+                }
+                depth = ext_depth(inode);
+                ex = path[depth].p_ext;
+        }
+
+        err = ext4_ext_get_access(handle, inode, path + depth);
+        if (err)
+                goto out;
+        /* first mark the extent as uninitialized */
+        ext4_ext_mark_uninitialized(ex);
+
+        /* note: ext4_ext_correct_indexes() isn't needed here because
+         * borders are not changed
+         */
+        ext4_ext_try_to_merge(handle, inode, path, ex);
+
+        /* Mark modified extent as dirty */
+        err = ext4_ext_dirty(handle, inode, path + path->p_depth);
+out:
+        ext4_ext_show_leaf(inode, path);
+        return err;
+}
+
+
 static int ext4_convert_unwritten_extents_endio(handle_t *handle,
                                                 struct inode *inode,
                                                 struct ext4_map_blocks *map,
@@ -3682,8 +3743,8 @@ static int ext4_convert_unwritten_extents_endio(handle_t *handle,
                              inode->i_ino, (unsigned long long)ee_block, ee_len,
                              (unsigned long long)map->m_lblk, map->m_len);
 #endif
-                err = ext4_split_unwritten_extents(handle, inode, map, path,
-                                                   EXT4_GET_BLOCKS_CONVERT);
+                err = ext4_split_convert_extents(handle, inode, map, path,
+                                                 EXT4_GET_BLOCKS_CONVERT);
                 if (err < 0)
                         goto out;
                 ext4_ext_drop_refs(path);
@@ -3884,6 +3945,38 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start,
 }
 
 static int
+ext4_ext_convert_initialized_extent(handle_t *handle, struct inode *inode,
+                        struct ext4_map_blocks *map,
+                        struct ext4_ext_path *path, int flags,
+                        unsigned int allocated, ext4_fsblk_t newblock)
+{
+        int ret = 0;
+        int err = 0;
+
+        /*
+         * Make sure that the extent is no bigger than we support with
+         * uninitialized extent
+         */
+        if (map->m_len > EXT_UNINIT_MAX_LEN)
+                map->m_len = EXT_UNINIT_MAX_LEN / 2;
+
+        ret = ext4_convert_initialized_extents(handle, inode, map,
+                                                path);
+        if (ret >= 0) {
+                ext4_update_inode_fsync_trans(handle, inode, 1);
+                err = check_eofblocks_fl(handle, inode, map->m_lblk,
+                                         path, map->m_len);
+        } else
+                err = ret;
+        map->m_flags |= EXT4_MAP_UNWRITTEN;
+        if (allocated > map->m_len)
+                allocated = map->m_len;
+        map->m_len = allocated;
+
+        return err ? err : allocated;
+}
+
+static int
 ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
                         struct ext4_map_blocks *map,