[PATCH 12/17] io_uring: feed reqs back into alloc cache

[Pavel Begunkov <asml.silence@xxxxxxxxx>]

Make io_req_free_batch(), which is used for inline executed requests and
IOPOLL, to return requests back into the allocation cache, so avoid
most of kmalloc()/kfree() for those cases.

Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 fs/io_uring.c | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 3711ae2633cb..1918b410b6f2 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -266,7 +266,7 @@ struct io_sq_data {
 
 #define IO_IOPOLL_BATCH			8
 #define IO_COMPL_BATCH			32
-#define IO_REQ_CACHE_SIZE		8
+#define IO_REQ_CACHE_SIZE		32
 #define IO_REQ_ALLOC_BATCH		8
 
 struct io_comp_state {
@@ -2270,7 +2270,8 @@ static void io_req_free_batch_finish(struct io_ring_ctx *ctx,
 		percpu_ref_put_many(&ctx->refs, rb->ctx_refs);
 }
 
-static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
+static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req,
+			      struct io_submit_state *state)
 {
 	io_queue_next(req);
 
@@ -2284,9 +2285,13 @@ static void io_req_free_batch(struct req_batch *rb, struct io_kiocb *req)
 	rb->ctx_refs++;
 
 	io_dismantle_req(req);
-	rb->reqs[rb->to_free++] = req;
-	if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
-		__io_req_free_batch_flush(req->ctx, rb);
+	if (state->free_reqs != ARRAY_SIZE(state->reqs)) {
+		state->reqs[state->free_reqs++] = req;
+	} else {
+		rb->reqs[rb->to_free++] = req;
+		if (unlikely(rb->to_free == ARRAY_SIZE(rb->reqs)))
+			__io_req_free_batch_flush(req->ctx, rb);
+	}
 }
 
 static void io_submit_flush_completions(struct io_comp_state *cs,
@@ -2311,7 +2316,7 @@ static void io_submit_flush_completions(struct io_comp_state *cs,
 
 		/* submission and completion refs */
 		if (refcount_sub_and_test(2, &req->refs))
-			io_req_free_batch(&rb, req);
+			io_req_free_batch(&rb, req, &ctx->submit_state);
 	}
 
 	io_req_free_batch_finish(ctx, &rb);
@@ -2464,7 +2469,7 @@ static void io_iopoll_complete(struct io_ring_ctx *ctx, unsigned int *nr_events,
 		(*nr_events)++;
 
 		if (refcount_dec_and_test(&req->refs))
-			io_req_free_batch(&rb, req);
+			io_req_free_batch(&rb, req, &ctx->submit_state);
 	}
 
 	io_commit_cqring(ctx);
-- 
2.24.0