io_uring: only trace one of complete or overflow

In overflow we see a duplcate line in the trace, and in some cases 3
lines (if initial io_post_aux_cqe fails).
Instead just trace once for each CQE
Signed-off-by: Dylan Yudaken <dylany@fb.com>
Link: https://lore.kernel.org/r/20220630091231.1456789-13-dylany@fb.comSigned-off-by: Jens Axboe <axboe@kernel.dk>

io_uring/io_uring.c

@@ -742,7 +742,6 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx,
 	struct io_uring_cqe *cqe;
 
 	ctx->cq_extra++;
-	trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
 
 	/*
 	 * If we can't get a cq entry, userspace overflowed the
@@ -751,6 +750,8 @@ static bool io_fill_cqe_aux(struct io_ring_ctx *ctx,
 	 */
 	cqe = io_get_cqe(ctx);
 	if (likely(cqe)) {
+		trace_io_uring_complete(ctx, NULL, user_data, res, cflags, 0, 0);
+
 		WRITE_ONCE(cqe->user_data, user_data);
 		WRITE_ONCE(cqe->res, res);
 		WRITE_ONCE(cqe->flags, cflags);

io_uring/io_uring.h

@@ -101,10 +101,6 @@ static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
 {
 	struct io_uring_cqe *cqe;
 
-	trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
-				req->cqe.res, req->cqe.flags,
-				(req->flags & REQ_F_CQE32_INIT) ? req->extra1 : 0,
-				(req->flags & REQ_F_CQE32_INIT) ? req->extra2 : 0);
 	/*
 	 * If we can't get a cq entry, userspace overflowed the
 	 * submission (by quite a lot). Increment the overflow count in
@@ -113,6 +109,12 @@ static inline bool __io_fill_cqe_req(struct io_ring_ctx *ctx,
 	cqe = io_get_cqe(ctx);
 	if (unlikely(!cqe))
 		return io_req_cqe_overflow(req);
+
+	trace_io_uring_complete(req->ctx, req, req->cqe.user_data,
+				req->cqe.res, req->cqe.flags,
+				(req->flags & REQ_F_CQE32_INIT) ? req->extra1 : 0,
+				(req->flags & REQ_F_CQE32_INIT) ? req->extra2 : 0);
+
 	memcpy(cqe, &req->cqe, sizeof(*cqe));
 
 	if (ctx->flags & IORING_SETUP_CQE32) {