vfs: make remap_file_range functions take and return bytes completed
Change the remap_file_range functions to take a number of bytes to
operate upon and return the number of bytes they operated on. This is a
requirement for allowing fs implementations to return short clone/dedupe
results to the user, which will enable us to obey resource limits in a
graceful manner.
A subsequent patch will enable copy_file_range to signal to the
->clone_file_range implementation that it can handle a short length,
which will be returned in the function's return value. For now the
short return is not implemented anywhere so the behavior won't change --
either copy_file_range manages to clone the entire range or it tries an
alternative.
Neither clone ioctl can take advantage of this, alas.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Dave Chinner <david@fromorbit.com>
diff --git a/fs/read_write.c b/fs/read_write.c
index b61bd3f..356641a 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1589,10 +1589,13 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
* more efficient if both clone and copy are supported (e.g. NFS).
*/
if (file_in->f_op->remap_file_range) {
- ret = file_in->f_op->remap_file_range(file_in, pos_in,
- file_out, pos_out, len, 0);
- if (ret == 0) {
- ret = len;
+ loff_t cloned;
+
+ cloned = file_in->f_op->remap_file_range(file_in, pos_in,
+ file_out, pos_out,
+ min_t(loff_t, MAX_RW_COUNT, len), 0);
+ if (cloned > 0) {
+ ret = cloned;
goto done;
}
}
@@ -1686,11 +1689,12 @@ SYSCALL_DEFINE6(copy_file_range, int, fd_in, loff_t __user *, off_in,
return ret;
}
-static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write)
+static int remap_verify_area(struct file *file, loff_t pos, loff_t len,
+ bool write)
{
struct inode *inode = file_inode(file);
- if (unlikely(pos < 0))
+ if (unlikely(pos < 0 || len < 0))
return -EINVAL;
if (unlikely((loff_t) (pos + len) < 0))
@@ -1721,7 +1725,7 @@ static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write)
static int generic_remap_check_len(struct inode *inode_in,
struct inode *inode_out,
loff_t pos_out,
- u64 *len,
+ loff_t *len,
unsigned int remap_flags)
{
u64 blkmask = i_blocksize(inode_in) - 1;
@@ -1747,7 +1751,7 @@ static int generic_remap_check_len(struct inode *inode_in,
*/
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
struct file *file_out, loff_t pos_out,
- u64 *len, unsigned int remap_flags)
+ loff_t *len, unsigned int remap_flags)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
@@ -1843,12 +1847,12 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
}
EXPORT_SYMBOL(generic_remap_file_range_prep);
-int do_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len)
+loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, loff_t len)
{
struct inode *inode_in = file_inode(file_in);
struct inode *inode_out = file_inode(file_out);
- int ret;
+ loff_t ret;
if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
return -EISDIR;
@@ -1881,19 +1885,19 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in,
ret = file_in->f_op->remap_file_range(file_in, pos_in,
file_out, pos_out, len, 0);
- if (!ret) {
- fsnotify_access(file_in);
- fsnotify_modify(file_out);
- }
+ if (ret < 0)
+ return ret;
+ fsnotify_access(file_in);
+ fsnotify_modify(file_out);
return ret;
}
EXPORT_SYMBOL(do_clone_file_range);
-int vfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len)
+loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out, loff_t len)
{
- int ret;
+ loff_t ret;
file_start_write(file_out);
ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len);
@@ -1999,10 +2003,11 @@ int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff,
}
EXPORT_SYMBOL(vfs_dedupe_file_range_compare);
-int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
- struct file *dst_file, loff_t dst_pos, u64 len)
+loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
+ struct file *dst_file, loff_t dst_pos,
+ loff_t len)
{
- s64 ret;
+ loff_t ret;
ret = mnt_want_write_file(dst_file);
if (ret)
@@ -2051,7 +2056,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same)
int i;
int ret;
u16 count = same->dest_count;
- int deduped;
+ loff_t deduped;
if (!(file->f_mode & FMODE_READ))
return -EINVAL;