io_uring: refactor __io_get_cqe()

Make __io_get_cqe simpler by not grabbing the cqe from refilled cached,
but letting io_get_cqe() do it for us. That's cleaner and removes some
duplication.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://lore.kernel.org/r/74dc8fdf2657e438b2e05e1d478a3596924604e9.1692916914.git.asml.silence@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>

Author: isilence

io_uring/io_uring.c

@@ -818,7 +818,7 @@ void io_req_cqe_overflow(struct io_kiocb *req)
  * control dependency is enough as we're using WRITE_ONCE to
  * fill the cq entry
  */
-struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow)
+bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow)
 {
 	struct io_rings *rings = ctx->rings;
 	unsigned int off = ctx->cached_cq_tail & (ctx->cq_entries - 1);
@@ -830,15 +830,15 @@ struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow)
 	 * Force overflow the completion.
 	 */
 	if (!overflow && (ctx->check_cq & BIT(IO_CHECK_CQ_OVERFLOW_BIT)))
-		return NULL;
+		return false;
 
 	/* userspace may cheat modifying the tail, be safe and do min */
 	queued = min(__io_cqring_events(ctx), ctx->cq_entries);
 	free = ctx->cq_entries - queued;
 	/* we need a contiguous range, limit based on the current array offset */
 	len = min(free, ctx->cq_entries - off);
 	if (!len)
-		return NULL;
+		return false;
 
 	if (ctx->flags & IORING_SETUP_CQE32) {
 		off <<= 1;
@@ -847,12 +847,7 @@ struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow)
 
 	ctx->cqe_cached = &rings->cqes[off];
 	ctx->cqe_sentinel = ctx->cqe_cached + len;
-
-	ctx->cached_cq_tail++;
-	ctx->cqe_cached++;
-	if (ctx->flags & IORING_SETUP_CQE32)
-		ctx->cqe_cached++;
-	return &rings->cqes[off];
+	return true;
 }
 
 static bool io_fill_cqe_aux(struct io_ring_ctx *ctx, u64 user_data, s32 res,

io_uring/io_uring.h

@@ -38,7 +38,7 @@ enum {
 	IOU_STOP_MULTISHOT	= -ECANCELED,
 };
 
-struct io_uring_cqe *__io_get_cqe(struct io_ring_ctx *ctx, bool overflow);
+bool io_cqe_cache_refill(struct io_ring_ctx *ctx, bool overflow);
 void io_req_cqe_overflow(struct io_kiocb *req);
 int io_run_task_work_sig(struct io_ring_ctx *ctx);
 void io_req_defer_failed(struct io_kiocb *req, s32 res);
@@ -112,19 +112,20 @@ static inline void io_req_task_work_add(struct io_kiocb *req)
 static inline struct io_uring_cqe *io_get_cqe_overflow(struct io_ring_ctx *ctx,
 						       bool overflow)
 {
-	io_lockdep_assert_cq_locked(ctx);
+	struct io_uring_cqe *cqe;
 
-	if (likely(ctx->cqe_cached < ctx->cqe_sentinel)) {
-		struct io_uring_cqe *cqe = ctx->cqe_cached;
+	io_lockdep_assert_cq_locked(ctx);
 
-		ctx->cached_cq_tail++;
-		ctx->cqe_cached++;
-		if (ctx->flags & IORING_SETUP_CQE32)
-			ctx->cqe_cached++;
-		return cqe;
+	if (unlikely(ctx->cqe_cached >= ctx->cqe_sentinel)) {
+		if (unlikely(!io_cqe_cache_refill(ctx, overflow)))
+			return NULL;
 	}
-
-	return __io_get_cqe(ctx, overflow);
+	cqe = ctx->cqe_cached;
+	ctx->cached_cq_tail++;
+	ctx->cqe_cached++;
+	if (ctx->flags & IORING_SETUP_CQE32)
+		ctx->cqe_cached++;
+	return cqe;
 }
 
 static inline struct io_uring_cqe *io_get_cqe(struct io_ring_ctx *ctx)