[v8,4/4] vfs: Add vfs_copy_file_range() support for pagecache copies

Commit Message

Schumaker, Anna Nov. 6, 2015, 9:18 p.m. UTC

This allows us to have an in-kernel copy mechanism that avoids frequent
switches between kernel and user space.  This is especially useful so
NFSD can support server-side copies.

The default (flags=0) means to first attempt copy acceleration, but use
the pagecache if that fails.

I moved the rw_verify_area() calls into the fallback code since some
filesystems can handle reflinking a large range.

Signed-off-by: Anna Schumaker <[e-mail]>
Reviewed-by: Darrick J. Wong <[e-mail]>
Reviewed-by: Padraig Brady <[e-mail]>
Reviewed-by: Christoph Hellwig <[e-mail]>
---
 fs/read_write.c | 37 ++++++++++++++++++++++++++-----------
 1 file changed, 26 insertions(+), 11 deletions(-)

Comments

Al Viro Nov. 10, 2015, 12:56 a.m. UTC | #1

On Fri, Nov 06, 2015 at 04:18:20PM -0500, Anna Schumaker wrote:

> I moved the rw_verify_area() calls into the fallback code since some
> filesystems can handle reflinking a large range.


Take a look at rw_verify_area() - it does a lot more than "trim down to
2Gb" - starting with "deal with mandatory locks".  LSM checks as well...

So that one is bogus, IMO.  I've no problem with fallback per se, but
rw_verify_area() should be unconditional here.  If anything, we might
add a variant that would skip the "trim down to 2Gb" and use it there,
but skipping it entirely is wrong.
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/fs/read_write.c b/fs/read_write.c
index 97c15ca..a093830 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -1329,6 +1329,24 @@  COMPAT_SYSCALL_DEFINE4(sendfile64, int, out_fd, int, in_fd,
 }
 #endif
 
+static ssize_t vfs_copy_fr_copy(struct file *file_in, loff_t pos_in,
+				struct file *file_out, loff_t pos_out,
+				size_t len)
+{
+	ssize_t ret = rw_verify_area(READ, file_in, &pos_in, len);
+
+	if (ret >= 0) {
+		len = ret;
+		ret = rw_verify_area(WRITE, file_out, &pos_out, len);
+		if (ret >= 0)
+			len = ret;
+	}
+	if (ret < 0)
+		return ret;
+
+	return do_splice_direct(file_in, &pos_in, file_out, &pos_out, len, 0);
+}
+
 /*
  * copy_file_range() differs from regular file read and write in that it
  * specifically allows return partial success.  When it does so is up to
@@ -1345,17 +1363,9 @@  ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (flags != 0)
 		return -EINVAL;
 
-	/* copy_file_range allows full ssize_t len, ignoring MAX_RW_COUNT  */
-	ret = rw_verify_area(READ, file_in, &pos_in, len);
-	if (ret >= 0)
-		ret = rw_verify_area(WRITE, file_out, &pos_out, len);
-	if (ret < 0)
-		return ret;
-
 	if (!(file_in->f_mode & FMODE_READ) ||
 	    !(file_out->f_mode & FMODE_WRITE) ||
-	    (file_out->f_flags & O_APPEND) ||
-	    !file_out->f_op->copy_file_range)
+	    (file_out->f_flags & O_APPEND))
 		return -EBADF;
 
 	/* this could be relaxed once a method supports cross-fs copies */
@@ -1369,8 +1379,13 @@  ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (ret)
 		return ret;
 
-	ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out, pos_out,
-					      len, flags);
+	ret = -EOPNOTSUPP;
+	if (file_out->f_op->copy_file_range)
+		ret = file_out->f_op->copy_file_range(file_in, pos_in, file_out,
+						      pos_out, len, flags);
+	if (ret == -EOPNOTSUPP)
+		ret = vfs_copy_fr_copy(file_in, pos_in, file_out, pos_out, len);
+
 	if (ret > 0) {
 		fsnotify_access(file_in);
 		add_rchar(current, ret);