io_uring: cache __io_free_req()'d requests

Don't kfree requests in __io_free_req() but put them back into the
internal request cache. That makes allocations more sustainable and will
be used for refcounting optimisations.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/9f4950fbe7771c8d41799366d0a3a08ac3040236.1628536684.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

fs/io_uring.c

@@ -1831,11 +1831,16 @@ static void io_dismantle_req(struct io_kiocb *req)
 static void __io_free_req(struct io_kiocb *req)
 {
 	struct io_ring_ctx *ctx = req->ctx;
+	unsigned long flags;
 
 	io_dismantle_req(req);
 	io_put_task(req->task, 1);
 
-	kmem_cache_free(req_cachep, req);
+	spin_lock_irqsave(&ctx->completion_lock, flags);
+	list_add(&req->compl.list, &ctx->locked_free_list);
+	ctx->locked_free_nr++;
+	spin_unlock_irqrestore(&ctx->completion_lock, flags);
+
 	percpu_ref_put(&ctx->refs);
 }