io_uring: introduce io_req_cqe_overflow()

__io_fill_cqe_req() is hot and inlined, we want it to be as small as
possible. Add io_req_cqe_overflow() accepting only a request and doing
all overflow accounting, and replace with it two calls to 6 argument
io_cqring_event_overflow().

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/048b9fbcce56814d77a1a540409c98c3d383edcb.1655455613.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -643,8 +643,8 @@ static __cold void io_uring_drop_tctx_refs(struct task_struct *task)
 	}
 }
 
-bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, s32 res,
-			      u32 cflags, u64 extra1, u64 extra2)
+static bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data,
+				     s32 res, u32 cflags, u64 extra1, u64 extra2)
 {
 	struct io_overflow_cqe *ocqe;
 	size_t ocq_size = sizeof(struct io_overflow_cqe);
@@ -681,6 +681,17 @@ bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, s32 res,
 	return true;
 }
 
+bool io_req_cqe_overflow(struct io_kiocb *req)
+{
+	if (!(req->flags & REQ_F_CQE32_INIT)) {
+		req->extra1 = 0;
+		req->extra2 = 0;
+	}
+	return io_cqring_event_overflow(req->ctx, req->cqe.user_data,
+					req->cqe.res, req->cqe.flags,
+					req->extra1, req->extra2);
+}
+
 /*
  * writes to the cq entry need to come after reading head; the
  * control dependency is enough as we're using WRITE_ONCE to

io_uring/io_uring.h

@@ -15,8 +15,7 @@ enum {
 };
 
 struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx);
-bool io_cqring_event_overflow(struct io_ring_ctx *ctx, u64 user_data, s32 res,
-			      u32 cflags, u64 extra1, u64 extra2);
+bool io_req_cqe_overflow(struct io_kiocb *req);
 
 static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)
 {
@@ -56,10 +55,6 @@ static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
 			memcpy(cqe, &req->cqe, sizeof(*cqe));
 			return true;
 		}
-
-		return io_cqring_event_overflow(ctx, req->cqe.user_data,
-						req->cqe.res, req->cqe.flags,
-						0, 0);
 	} else {
 		u64 extra1 = 0, extra2 = 0;
 
@@ -83,11 +78,8 @@ static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
 			WRITE_ONCE(cqe->big_cqe[1], extra2);
 			return true;
 		}
-
-		return io_cqring_event_overflow(ctx, req->cqe.user_data,
-				req->cqe.res, req->cqe.flags,
-				extra1, extra2);
 	}
+	return io_req_cqe_overflow(req);
 }
 
 static inline void req_set_fail(struct io_kiocb *req)