io_uring: batch io_kiocb allocation

Similarly to how we use the state->ios_left to know how many references
to get to a file, we can use it to allocate the io_kiocb's we need in
bulk.

Reviewed-by: Hannes Reinecke <[e-mail]>
Signed-off-by: Jens Axboe <[e-mail]>

fs/io_uring.c

···
 	struct blk_plug		plug;
 
 	/*
+	 * io_kiocb alloc cache
+	 */
+	void			*reqs[IO_IOPOLL_BATCH];
+	unsigned		int free_reqs;
+	unsigned		int cur_req;
+
+	/*
 	 * File reference cache
 	 */
 	struct file		*file;
···
 		wake_up(&ctx->wait);
 }
 
-static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
+static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
+				   struct io_submit_state *state)
 {
 	struct io_kiocb *req;
 
 	if (!percpu_ref_tryget(&ctx->refs))
 		return NULL;
 
-	req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
-	if (req) {
-		req->ctx = ctx;
-		req->flags = 0;
-		return req;
+	if (!state) {
+		req = kmem_cache_alloc(req_cachep, __GFP_NOWARN);
+		if (unlikely(!req))
+			goto out;
+	} else if (!state->free_reqs) {
+		size_t sz;
+		int ret;
+
+		sz = min_t(size_t, state->ios_left, ARRAY_SIZE(state->reqs));
+		ret = kmem_cache_alloc_bulk(req_cachep, __GFP_NOWARN, sz,
+						state->reqs);
+		if (unlikely(ret <= 0))
+			goto out;
+		state->free_reqs = ret - 1;
+		state->cur_req = 1;
+		req = state->reqs[0];
+	} else {
+		req = state->reqs[state->cur_req];
+		state->free_reqs--;
+		state->cur_req++;
 	}
 
+	req->ctx = ctx;
+	req->flags = 0;
+	return req;
+out:
 	io_ring_drop_ctx_refs(ctx, 1);
 	return NULL;
 }
···
 	if (unlikely(s->sqe->flags))
 		return -EINVAL;
 
-	req = io_get_req(ctx);
+	req = io_get_req(ctx, state);
 	if (unlikely(!req))
 		return -EAGAIN;
 
···
 {
 	blk_finish_plug(&state->plug);
 	io_file_put(state, NULL);
+	if (state->free_reqs)
+		kmem_cache_free_bulk(req_cachep, state->free_reqs,
+					&state->reqs[state->cur_req]);
 }
 
 /*
···
 				  struct io_ring_ctx *ctx, unsigned max_ios)
 {
 	blk_start_plug(&state->plug);
+	state->free_reqs = 0;
 	state->file = NULL;
 	state->ios_left = max_ios;
 }