net/mlx5e: Remove wrong poll CQ optimization

commit 59a7c2fd upstream.

With the MLX5E_CQ_HAS_CQES optimization flag, the following buggy
flow might occur:
- Suppose RX is always busy, TX has a single packet every second.
- We poll a single TX cqe and clear its flag.
- We never arm it again as RX is always busy.
- TX CQ flag is never changed, and new TX cqes are not polled.

We revert this optimization.

Fixes: e586b3b0 ('net/mlx5: Ethernet Datapath files')
Signed-off-by: Tariq Toukan <tariqt@mellanox.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
[ kamal: backport to 4.2-stable: context around mlx5e_poll_rx_cq return ]
Signed-off-by: Kamal Mostafa <kamal@canonical.com>

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -201,14 +201,9 @@ enum {
 	MLX5E_RQ_STATE_POST_WQES_ENABLE,
 };
 
-enum cq_flags {
-	MLX5E_CQ_HAS_CQES = 1,
-};
-
 struct mlx5e_cq {
 	/* data path - accessed per cqe */
 	struct mlx5_cqwq           wq;
-	unsigned long              flags;
 
 	/* data path - accessed per napi poll */
 	struct napi_struct        *napi;

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -194,10 +194,6 @@ bool mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	struct mlx5e_rq *rq = container_of(cq, struct mlx5e_rq, cq);
 	int i;
 
-	/* avoid accessing cq (dma coherent memory) if not needed */
-	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
-		return false;
-
 	for (i = 0; i < budget; i++) {
 		struct mlx5e_rx_wqe *wqe;
 		struct mlx5_cqe64 *cqe;
@@ -243,10 +239,8 @@ bool mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget)
 	/* ensure cq space is freed before enabling more cqes */
 	wmb();
 
-	if (i == budget) {
-		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
+	if (i == budget)
 		return true;
-	}
 
 	return false;
 }

drivers/net/ethernet/mellanox/mlx5/core/en_tx.c

@@ -262,10 +262,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
 	u16 sqcc;
 	int i;
 
-	/* avoid accessing cq (dma coherent memory) if not needed */
-	if (!test_and_clear_bit(MLX5E_CQ_HAS_CQES, &cq->flags))
-		return false;
-
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
 	npkts = 0;
@@ -341,10 +337,6 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq)
 				netif_tx_wake_queue(sq->txq);
 				sq->stats.wake++;
 	}
-	if (i == MLX5E_TX_CQ_POLL_BUDGET) {
-		set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
-		return true;
-	}
 
-	return false;
+	return (i == MLX5E_TX_CQ_POLL_BUDGET);
 }

drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c

@@ -87,7 +87,6 @@ void mlx5e_completion_event(struct mlx5_core_cq *mcq)
 {
 	struct mlx5e_cq *cq = container_of(mcq, struct mlx5e_cq, mcq);
 
-	set_bit(MLX5E_CQ_HAS_CQES, &cq->flags);
 	set_bit(MLX5E_CHANNEL_NAPI_SCHED, &cq->channel->flags);
 	barrier();
 	napi_schedule(cq->napi);