fallocate should be a file operation
Currently all filesystems except XFS implement fallocate asynchronously,
while XFS forced a commit. Both of these are suboptimal - in case of O_SYNC
I/O we really want our allocation on disk, especially for the !KEEP_SIZE
case where we actually grow the file with user-visible zeroes. On the
other hand always commiting the transaction is a bad idea for fast-path
uses of fallocate like for example in recent Samba versions. Given
that block allocation is a data plane operation anyway change it from
an inode operation to a file operation so that we have the file structure
available that lets us check for O_SYNC.
This also includes moving the code around for a few of the filesystems,
and remove the already unnedded S_ISDIR checks given that we only wire
up fallocate for regular files.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index 66836d8..a9e0a4e 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -24,6 +24,7 @@
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mpage.h>
+#include <linux/falloc.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
@@ -1237,6 +1238,117 @@
return 0;
}
+static long btrfs_fallocate(struct file *file, int mode,
+ loff_t offset, loff_t len)
+{
+ struct inode *inode = file->f_path.dentry->d_inode;
+ struct extent_state *cached_state = NULL;
+ u64 cur_offset;
+ u64 last_byte;
+ u64 alloc_start;
+ u64 alloc_end;
+ u64 alloc_hint = 0;
+ u64 locked_end;
+ u64 mask = BTRFS_I(inode)->root->sectorsize - 1;
+ struct extent_map *em;
+ int ret;
+
+ alloc_start = offset & ~mask;
+ alloc_end = (offset + len + mask) & ~mask;
+
+ /* We only support the FALLOC_FL_KEEP_SIZE mode */
+ if (mode & ~FALLOC_FL_KEEP_SIZE)
+ return -EOPNOTSUPP;
+
+ /*
+ * wait for ordered IO before we have any locks. We'll loop again
+ * below with the locks held.
+ */
+ btrfs_wait_ordered_range(inode, alloc_start, alloc_end - alloc_start);
+
+ mutex_lock(&inode->i_mutex);
+ ret = inode_newsize_ok(inode, alloc_end);
+ if (ret)
+ goto out;
+
+ if (alloc_start > inode->i_size) {
+ ret = btrfs_cont_expand(inode, alloc_start);
+ if (ret)
+ goto out;
+ }
+
+ ret = btrfs_check_data_free_space(inode, alloc_end - alloc_start);
+ if (ret)
+ goto out;
+
+ locked_end = alloc_end - 1;
+ while (1) {
+ struct btrfs_ordered_extent *ordered;
+
+ /* the extent lock is ordered inside the running
+ * transaction
+ */
+ lock_extent_bits(&BTRFS_I(inode)->io_tree, alloc_start,
+ locked_end, 0, &cached_state, GFP_NOFS);
+ ordered = btrfs_lookup_first_ordered_extent(inode,
+ alloc_end - 1);
+ if (ordered &&
+ ordered->file_offset + ordered->len > alloc_start &&
+ ordered->file_offset < alloc_end) {
+ btrfs_put_ordered_extent(ordered);
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree,
+ alloc_start, locked_end,
+ &cached_state, GFP_NOFS);
+ /*
+ * we can't wait on the range with the transaction
+ * running or with the extent lock held
+ */
+ btrfs_wait_ordered_range(inode, alloc_start,
+ alloc_end - alloc_start);
+ } else {
+ if (ordered)
+ btrfs_put_ordered_extent(ordered);
+ break;
+ }
+ }
+
+ cur_offset = alloc_start;
+ while (1) {
+ em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+ alloc_end - cur_offset, 0);
+ BUG_ON(IS_ERR(em) || !em);
+ last_byte = min(extent_map_end(em), alloc_end);
+ last_byte = (last_byte + mask) & ~mask;
+ if (em->block_start == EXTENT_MAP_HOLE ||
+ (cur_offset >= inode->i_size &&
+ !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) {
+ ret = btrfs_prealloc_file_range(inode, mode, cur_offset,
+ last_byte - cur_offset,
+ 1 << inode->i_blkbits,
+ offset + len,
+ &alloc_hint);
+ if (ret < 0) {
+ free_extent_map(em);
+ break;
+ }
+ }
+ free_extent_map(em);
+
+ cur_offset = last_byte;
+ if (cur_offset >= alloc_end) {
+ ret = 0;
+ break;
+ }
+ }
+ unlock_extent_cached(&BTRFS_I(inode)->io_tree, alloc_start, locked_end,
+ &cached_state, GFP_NOFS);
+
+ btrfs_free_reserved_data_space(inode, alloc_end - alloc_start);
+out:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}
+
const struct file_operations btrfs_file_operations = {
.llseek = generic_file_llseek,
.read = do_sync_read,
@@ -1248,6 +1360,7 @@
.open = generic_file_open,
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
+ .fallocate = btrfs_fallocate,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
.compat_ioctl = btrfs_ioctl,