+
+/*
+ * ext4_access_path:
+ * Function to access the path buffer for marking it dirty.
+ * It also checks if there are sufficient credits left in the journal handle
+ * to update path.
+ */
+static int
+ext4_access_path(handle_t *handle, struct inode *inode,
+ struct ext4_ext_path *path)
+{
+ int credits, err;
+
+ if (!ext4_handle_valid(handle))
+ return 0;
+
+ /*
+ * Check if need to extend journal credits
+ * 3 for leaf, sb, and inode plus 2 (bmap and group
+ * descriptor) for each block group; assume two block
+ * groups
+ */
+ if (handle->h_buffer_credits < 7) {
+ credits = ext4_writepage_trans_blocks(inode);
+ err = ext4_ext_truncate_extend_restart(handle, inode, credits);
+ /* EAGAIN is success */
+ if (err && err != -EAGAIN)
+ return err;
+ }
+
+ err = ext4_ext_get_access(handle, inode, path);
+ return err;
+}
+
+/*
+ * ext4_ext_shift_path_extents:
+ * Shift the extents of a path structure lying between path[depth].p_ext
+ * and EXT_LAST_EXTENT(path[depth].p_hdr) downwards, by subtracting shift
+ * from starting block for each extent.
+ */
+static int
+ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift,
+ struct inode *inode, handle_t *handle,
+ ext4_lblk_t *start)
+{
+ int depth, err = 0;
+ struct ext4_extent *ex_start, *ex_last;
+ bool update = 0;
+ depth = path->p_depth;
+
+ while (depth >= 0) {
+ if (depth == path->p_depth) {
+ ex_start = path[depth].p_ext;
+ if (!ex_start)
+ return -EIO;
+
+ ex_last = EXT_LAST_EXTENT(path[depth].p_hdr);
+ if (!ex_last)
+ return -EIO;
+
+ err = ext4_access_path(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr))
+ update = 1;
+
+ *start = le32_to_cpu(ex_last->ee_block) +
+ ext4_ext_get_actual_len(ex_last);
+
+ while (ex_start <= ex_last) {
+ le32_add_cpu(&ex_start->ee_block, -shift);
+ /* Try to merge to the left. */
+ if ((ex_start >
+ EXT_FIRST_EXTENT(path[depth].p_hdr)) &&
+ ext4_ext_try_to_merge_right(inode,
+ path, ex_start - 1))
+ ex_last--;
+ else
+ ex_start++;
+ }
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ if (--depth < 0 || !update)
+ break;
+ }
+
+ /* Update index too */
+ err = ext4_access_path(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ le32_add_cpu(&path[depth].p_idx->ei_block, -shift);
+ err = ext4_ext_dirty(handle, inode, path + depth);
+ if (err)
+ goto out;
+
+ /* we are done if current index is not a starting index */
+ if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr))
+ break;
+
+ depth--;
+ }
+
+out:
+ return err;
+}
+
+/*
+ * ext4_ext_shift_extents:
+ * All the extents which lies in the range from start to the last allocated
+ * block for the file are shifted downwards by shift blocks.
+ * On success, 0 is returned, error otherwise.
+ */
+static int
+ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
+ ext4_lblk_t start, ext4_lblk_t shift)
+{
+ struct ext4_ext_path *path;
+ int ret = 0, depth;
+ struct ext4_extent *extent;
+ ext4_lblk_t stop_block, current_block;
+ ext4_lblk_t ex_start, ex_end;
+
+ /* Let path point to the last extent */
+ path = ext4_ext_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+
+ depth = path->p_depth;
+ extent = path[depth].p_ext;
+ if (!extent) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ return ret;
+ }
+
+ stop_block = le32_to_cpu(extent->ee_block) +
+ ext4_ext_get_actual_len(extent);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+
+ /* Nothing to shift, if hole is at the end of file */
+ if (start >= stop_block)
+ return ret;
+
+ /*
+ * Don't start shifting extents until we make sure the hole is big
+ * enough to accomodate the shift.
+ */
+ path = ext4_ext_find_extent(inode, start - 1, NULL, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ depth = path->p_depth;
+ extent = path[depth].p_ext;
+ if (extent) {
+ ex_start = le32_to_cpu(extent->ee_block);
+ ex_end = le32_to_cpu(extent->ee_block) +
+ ext4_ext_get_actual_len(extent);
+ } else {
+ ex_start = 0;
+ ex_end = 0;
+ }
+ ext4_ext_drop_refs(path);
+ kfree(path);
+
+ if ((start == ex_start && shift > ex_start) ||
+ (shift > start - ex_end))
+ return -EINVAL;
+
+ /* Its safe to start updating extents */
+ while (start < stop_block) {
+ path = ext4_ext_find_extent(inode, start, NULL, 0);
+ if (IS_ERR(path))
+ return PTR_ERR(path);
+ depth = path->p_depth;
+ extent = path[depth].p_ext;
+ if (!extent) {
+ EXT4_ERROR_INODE(inode, "unexpected hole at %lu",
+ (unsigned long) start);
+ return -EIO;
+ }
+
+ current_block = le32_to_cpu(extent->ee_block);
+ if (start > current_block) {
+ /* Hole, move to the next extent */
+ ret = mext_next_extent(inode, path, &extent);
+ if (ret != 0) {
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ if (ret == 1)
+ ret = 0;
+ break;
+ }
+ }
+ ret = ext4_ext_shift_path_extents(path, shift, inode,
+ handle, &start);
+ ext4_ext_drop_refs(path);
+ kfree(path);
+ if (ret)
+ break;
+ }
+
+ return ret;
+}
+
+/*
+ * ext4_collapse_range:
+ * This implements the fallocate's collapse range functionality for ext4
+ * Returns: 0 and non-zero on error.
+ */
+int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
+{
+ struct super_block *sb = inode->i_sb;
+ ext4_lblk_t punch_start, punch_stop;
+ handle_t *handle;
+ unsigned int credits;
+ loff_t new_size, ioffset;
+ int ret;
+
+ /* Collapse range works only on fs block size aligned offsets. */
+ if (offset & (EXT4_BLOCK_SIZE(sb) - 1) ||
+ len & (EXT4_BLOCK_SIZE(sb) - 1))
+ return -EINVAL;
+
+ if (!S_ISREG(inode->i_mode))
+ return -EINVAL;
+
+ if (EXT4_SB(inode->i_sb)->s_cluster_ratio > 1)
+ return -EOPNOTSUPP;
+
+ trace_ext4_collapse_range(inode, offset, len);
+
+ punch_start = offset >> EXT4_BLOCK_SIZE_BITS(sb);
+ punch_stop = (offset + len) >> EXT4_BLOCK_SIZE_BITS(sb);
+
+ /* Call ext4_force_commit to flush all data in case of data=journal. */
+ if (ext4_should_journal_data(inode)) {
+ ret = ext4_force_commit(inode->i_sb);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Need to round down offset to be aligned with page size boundary
+ * for page size > block size.
+ */
+ ioffset = round_down(offset, PAGE_SIZE);
+
+ /* Write out all dirty pages */
+ ret = filemap_write_and_wait_range(inode->i_mapping, ioffset,
+ LLONG_MAX);
+ if (ret)
+ return ret;
+
+ /* Take mutex lock */
+ mutex_lock(&inode->i_mutex);
+
+ /*
+ * There is no need to overlap collapse range with EOF, in which case
+ * it is effectively a truncate operation
+ */
+ if (offset + len >= i_size_read(inode)) {
+ ret = -EINVAL;
+ goto out_mutex;
+ }
+
+ /* Currently just for extent based files */
+ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) {
+ ret = -EOPNOTSUPP;
+ goto out_mutex;
+ }
+
+ truncate_pagecache(inode, ioffset);
+
+ /* Wait for existing dio to complete */
+ ext4_inode_block_unlocked_dio(inode);
+ inode_dio_wait(inode);
+
+ credits = ext4_writepage_trans_blocks(inode);
+ handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out_dio;
+ }
+
+ down_write(&EXT4_I(inode)->i_data_sem);
+ ext4_discard_preallocations(inode);
+
+ ret = ext4_es_remove_extent(inode, punch_start,
+ EXT_MAX_BLOCKS - punch_start);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+
+ ret = ext4_ext_remove_space(inode, punch_start, punch_stop - 1);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+ ext4_discard_preallocations(inode);
+
+ ret = ext4_ext_shift_extents(inode, handle, punch_stop,
+ punch_stop - punch_start);
+ if (ret) {
+ up_write(&EXT4_I(inode)->i_data_sem);
+ goto out_stop;
+ }
+
+ new_size = i_size_read(inode) - len;
+ i_size_write(inode, new_size);
+ EXT4_I(inode)->i_disksize = new_size;
+
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+ inode->i_mtime = inode->i_ctime = ext4_current_time(inode);
+ ext4_mark_inode_dirty(handle, inode);
+
+out_stop:
+ ext4_journal_stop(handle);
+out_dio:
+ ext4_inode_resume_unlocked_dio(inode);
+out_mutex:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}