* on error we return an unlocked page and the error value
* on success we return a locked page and 0
*/
-static int prepare_uptodate_page(struct page *page, u64 pos,
+static int prepare_uptodate_page(struct inode *inode,
+ struct page *page, u64 pos,
bool force_uptodate)
{
int ret = 0;
unlock_page(page);
return -EIO;
}
+ if (page->mapping != inode->i_mapping) {
+ unlock_page(page);
+ return -EAGAIN;
+ }
}
return 0;
}
int faili;
for (i = 0; i < num_pages; i++) {
+again:
pages[i] = find_or_create_page(inode->i_mapping, index + i,
mask | __GFP_WRITE);
if (!pages[i]) {
}
if (i == 0)
- err = prepare_uptodate_page(pages[i], pos,
+ err = prepare_uptodate_page(inode, pages[i], pos,
force_uptodate);
- if (i == num_pages - 1)
- err = prepare_uptodate_page(pages[i],
+ if (!err && i == num_pages - 1)
+ err = prepare_uptodate_page(inode, pages[i],
pos + write_bytes, false);
if (err) {
page_cache_release(pages[i]);
+ if (err == -EAGAIN) {
+ err = 0;
+ goto again;
+ }
faili = i - 1;
goto fail;
}
reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
- if (BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
- BTRFS_INODE_PREALLOC)) {
- ret = check_can_nocow(inode, pos, &write_bytes);
- if (ret < 0)
- break;
- if (ret > 0) {
- /*
- * For nodata cow case, no need to reserve
- * data space.
- */
- only_release_metadata = true;
- /*
- * our prealloc extent may be smaller than
- * write_bytes, so scale down.
- */
- num_pages = DIV_ROUND_UP(write_bytes + offset,
- PAGE_CACHE_SIZE);
- reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
- goto reserve_metadata;
- }
+ if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+ BTRFS_INODE_PREALLOC)) &&
+ check_can_nocow(inode, pos, &write_bytes) > 0) {
+ /*
+ * For nodata cow case, no need to reserve
+ * data space.
+ */
+ only_release_metadata = true;
+ /*
+ * our prealloc extent may be smaller than
+ * write_bytes, so scale down.
+ */
+ num_pages = DIV_ROUND_UP(write_bytes + offset,
+ PAGE_CACHE_SIZE);
+ reserve_bytes = num_pages << PAGE_CACHE_SHIFT;
+ goto reserve_metadata;
}
+
ret = btrfs_check_data_free_space(inode, pos, write_bytes);
if (ret < 0)
break;
static int start_ordered_ops(struct inode *inode, loff_t start, loff_t end)
{
int ret;
+ struct blk_plug plug;
+ /*
+ * This is only called in fsync, which would do synchronous writes, so
+ * a plug can merge adjacent IOs as much as possible. Esp. in case of
+ * multiple disks using raid profile, a large IO can be split to
+ * several segments of stripe length (currently 64K).
+ */
+ blk_start_plug(&plug);
atomic_inc(&BTRFS_I(inode)->sync_writers);
ret = btrfs_fdatawrite_range(inode, start, end);
atomic_dec(&BTRFS_I(inode)->sync_writers);
+ blk_finish_plug(&plug);
return ret;
}
*/
int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
- struct dentry *dentry = file->f_path.dentry;
+ struct dentry *dentry = file_dentry(file);
struct inode *inode = d_inode(dentry);
struct btrfs_root *root = BTRFS_I(inode)->root;
struct btrfs_trans_handle *trans;
if (!ret)
ret = btrfs_prealloc_file_range(inode, mode,
range->start,
- range->len, 1 << inode->i_blkbits,
+ range->len, i_blocksize(inode),
offset + len, &alloc_hint);
list_del(&range->list);
kfree(range);