io_uring/rsrc: don't skip offset calculation

Don't optimise for requests with offset=0. Large registered buffers are
the preference and hence the user is likely to pass an offset, and the
adjustments are not expensive and will be made even cheaper in following
patches.

Signed-off-by: Pavel Begunkov <[email protected]>
Link: https://lore.kernel.org/r/1c2beb20470ee3c886a363d4d8340d3790db19f3.1744882081.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <[email protected]>

Author: isilence

io_uring/rsrc.c

@@ -1036,6 +1036,7 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 			   struct io_mapped_ubuf *imu,
 			   u64 buf_addr, size_t len)
 {
+	const struct bio_vec *bvec;
 	size_t offset;
 	int ret;
 
@@ -1054,47 +1055,45 @@ static int io_import_fixed(int ddir, struct iov_iter *iter,
 	offset = buf_addr - imu->ubuf;
 	iov_iter_bvec(iter, ddir, imu->bvec, imu->nr_bvecs, offset + len);
 
-	if (offset) {
-		/*
-		 * Don't use iov_iter_advance() here, as it's really slow for
-		 * using the latter parts of a big fixed buffer - it iterates
-		 * over each segment manually. We can cheat a bit here for user
-		 * registered nodes, because we know that:
-		 *
-		 * 1) it's a BVEC iter, we set it up
-		 * 2) all bvecs are the same in size, except potentially the
-		 *    first and last bvec
-		 *
-		 * So just find our index, and adjust the iterator afterwards.
-		 * If the offset is within the first bvec (or the whole first
-		 * bvec, just use iov_iter_advance(). This makes it easier
-		 * since we can just skip the first segment, which may not
-		 * be folio_size aligned.
-		 */
-		const struct bio_vec *bvec = imu->bvec;
+	/*
+	 * Don't use iov_iter_advance() here, as it's really slow for
+	 * using the latter parts of a big fixed buffer - it iterates
+	 * over each segment manually. We can cheat a bit here for user
+	 * registered nodes, because we know that:
+	 *
+	 * 1) it's a BVEC iter, we set it up
+	 * 2) all bvecs are the same in size, except potentially the
+	 *    first and last bvec
+	 *
+	 * So just find our index, and adjust the iterator afterwards.
+	 * If the offset is within the first bvec (or the whole first
+	 * bvec, just use iov_iter_advance(). This makes it easier
+	 * since we can just skip the first segment, which may not
+	 * be folio_size aligned.
+	 */
+	bvec = imu->bvec;
 
-		/*
-		 * Kernel buffer bvecs, on the other hand, don't necessarily
-		 * have the size property of user registered ones, so we have
-		 * to use the slow iter advance.
-		 */
-		if (offset < bvec->bv_len) {
-			iter->count -= offset;
-			iter->iov_offset = offset;
-		} else if (imu->is_kbuf) {
-			iov_iter_advance(iter, offset);
-		} else {
-			unsigned long seg_skip;
+	/*
+	 * Kernel buffer bvecs, on the other hand, don't necessarily
+	 * have the size property of user registered ones, so we have
+	 * to use the slow iter advance.
+	 */
+	if (offset < bvec->bv_len) {
+		iter->count -= offset;
+		iter->iov_offset = offset;
+	} else if (imu->is_kbuf) {
+		iov_iter_advance(iter, offset);
+	} else {
+		unsigned long seg_skip;
 
-			/* skip first vec */
-			offset -= bvec->bv_len;
-			seg_skip = 1 + (offset >> imu->folio_shift);
+		/* skip first vec */
+		offset -= bvec->bv_len;
+		seg_skip = 1 + (offset >> imu->folio_shift);
 
-			iter->bvec += seg_skip;
-			iter->nr_segs -= seg_skip;
-			iter->count -= bvec->bv_len + offset;
-			iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
-		}
+		iter->bvec += seg_skip;
+		iter->nr_segs -= seg_skip;
+		iter->count -= bvec->bv_len + offset;
+		iter->iov_offset = offset & ((1UL << imu->folio_shift) - 1);
 	}
 
 	return 0;