[PATCH 10/15] io_uring: batch io_kiocb allocation

[Jens Axboe <axboe@kernel.dk>]

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.

Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/io_uring.c | 66 ++++++++++++++++++++++++++++++++++++++-------------
 1 file changed, 50 insertions(+), 16 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index c0b61a25aaf6..b6e88a8f9d72 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -127,6 +127,13 @@ struct io_kiocb {
 struct io_submit_state {
 	struct blk_plug plug;
 
+	/*
+	 * io_kiocb alloc cache
+	 */
+	void *reqs[IO_IOPOLL_BATCH];
+	unsigned int free_reqs;
+	unsigned int cur_req;
+
 	/*
 	 * File reference cache
 	 */
@@ -242,29 +249,52 @@ static void io_fill_cq_error(struct io_ring_ctx *ctx, struct sqe_submit *s,
 		wake_up(&ctx->wait);
 }
 
-static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx)
+static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
 {
+	percpu_ref_put_many(&ctx->refs, refs);
+
+	if (waitqueue_active(&ctx->wait))
+		wake_up(&ctx->wait);
+}
+
+static struct io_kiocb *io_get_req(struct io_ring_ctx *ctx,
+				   struct io_submit_state *state)
+{
+	gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN;
 	struct io_kiocb *req;
 
 	if (!percpu_ref_tryget(&ctx->refs))
 		return NULL;
 
-	req = kmem_cache_alloc(req_cachep, GFP_ATOMIC | __GFP_NOWARN);
-	if (!req)
-		return NULL;
-
-	req->ctx = ctx;
-	INIT_LIST_HEAD(&req->list);
-	req->flags = 0;
-	return req;
-}
+	if (!state)
+		req = kmem_cache_alloc(req_cachep, gfp);
+	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, sz,
+						state->reqs);
+		if (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++;
+	}
 
-static void io_ring_drop_ctx_refs(struct io_ring_ctx *ctx, unsigned refs)
-{
-	percpu_ref_put_many(&ctx->refs, refs);
+	if (req) {
+		req->ctx = ctx;
+		req->flags = 0;
+		return req;
+	}
 
-	if (waitqueue_active(&ctx->wait))
-		wake_up(&ctx->wait);
+out:
+	io_ring_drop_ctx_refs(ctx, 1);
+	return NULL;
 }
 
 static void io_free_req_many(struct io_ring_ctx *ctx, void **reqs, int *nr)
@@ -871,7 +901,7 @@ static int io_submit_sqe(struct io_ring_ctx *ctx, struct sqe_submit *s,
 	struct io_kiocb *req;
 	ssize_t ret;
 
-	req = io_get_req(ctx);
+	req = io_get_req(ctx, state);
 	if (unlikely(!req))
 		return -EAGAIN;
 
@@ -895,6 +925,9 @@ static void io_submit_state_end(struct io_submit_state *state)
 {
 	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]);
 }
 
 /*
@@ -904,6 +937,7 @@ static void io_submit_state_start(struct io_submit_state *state,
 				  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;
 }
-- 
2.17.1