net/mlx5e: Timeout if SQ doesn't flush during close

Daniel Jurgens · davem330 · commit 29429f3300a3 · 2016-07-01T06:12:03.000-04:00
Avoid an infinite loop by timing out waiting for the SQ to flush. Also clean up the TX descriptors if that happens. Fixes: f62b8bb ('net/mlx5: Extend mlx5_core to support ConnectX-4 Ethernet functionality') Signed-off-by: Daniel Jurgens <danielj@mellanox.com> Signed-off-by: Saeed Mahameed <saeedm@mellanox.com> Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -305,6 +305,7 @@ struct mlx5e_sq_dma {
 enum {
 	MLX5E_SQ_STATE_WAKE_TXQ_ENABLE,
 	MLX5E_SQ_STATE_BF_ENABLE,
+	MLX5E_SQ_STATE_TX_TIMEOUT,
 };
 
 struct mlx5e_ico_wqe_info {
@@ -589,6 +590,7 @@ void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event);
 int mlx5e_napi_poll(struct napi_struct *napi, int budget);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget);
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq);
 
 void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
 void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -39,6 +39,13 @@
 #include "eswitch.h"
 #include "vxlan.h"
 
+enum {
+	MLX5_EN_QP_FLUSH_TIMEOUT_MS	= 5000,
+	MLX5_EN_QP_FLUSH_MSLEEP_QUANT	= 20,
+	MLX5_EN_QP_FLUSH_MAX_ITER	= MLX5_EN_QP_FLUSH_TIMEOUT_MS /
+					  MLX5_EN_QP_FLUSH_MSLEEP_QUANT,
+};
+
 struct mlx5e_rq_param {
 	u32                        rqc[MLX5_ST_SZ_DW(rqc)];
 	struct mlx5_wq_param       wq;
@@ -782,6 +789,9 @@ static inline void netif_tx_disable_queue(struct netdev_queue *txq)
 
 static void mlx5e_close_sq(struct mlx5e_sq *sq)
 {
+	int tout = 0;
+	int err;
+
 	if (sq->txq) {
 		clear_bit(MLX5E_SQ_STATE_WAKE_TXQ_ENABLE, &sq->state);
 		/* prevent netif_tx_wake_queue */
@@ -792,15 +802,24 @@ static void mlx5e_close_sq(struct mlx5e_sq *sq)
 		if (mlx5e_sq_has_room_for(sq, 1))
 			mlx5e_send_nop(sq, true);
 
-		mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY, MLX5_SQC_STATE_ERR);
+		err = mlx5e_modify_sq(sq, MLX5_SQC_STATE_RDY,
+				      MLX5_SQC_STATE_ERR);
+		if (err)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
 	}
 
-	while (sq->cc != sq->pc) /* wait till sq is empty */
-		msleep(20);
+	/* wait till sq is empty, unless a TX timeout occurred on this SQ */
+	while (sq->cc != sq->pc &&
+	       !test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)) {
+		msleep(MLX5_EN_QP_FLUSH_MSLEEP_QUANT);
+		if (tout++ > MLX5_EN_QP_FLUSH_MAX_ITER)
+			set_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state);
+	}
 
 	/* avoid destroying sq before mlx5e_poll_tx_cq() is done with it */
 	napi_synchronize(&sq->channel->napi);
 
+	mlx5e_free_tx_descs(sq);
 	mlx5e_disable_sq(sq);
 	mlx5e_destroy_sq(sq);
 }
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -341,6 +341,35 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev)
 	return mlx5e_sq_xmit(sq, skb);
 }
 
+void mlx5e_free_tx_descs(struct mlx5e_sq *sq)
+{
+	struct mlx5e_tx_wqe_info *wi;
+	struct sk_buff *skb;
+	u16 ci;
+	int i;
+
+	while (sq->cc != sq->pc) {
+		ci = sq->cc & sq->wq.sz_m1;
+		skb = sq->skb[ci];
+		wi = &sq->wqe_info[ci];
+
+		if (!skb) { /* nop */
+			sq->cc++;
+			continue;
+		}
+
+		for (i = 0; i < wi->num_dma; i++) {
+			struct mlx5e_sq_dma *dma =
+				mlx5e_dma_get(sq, sq->dma_fifo_cc++);
+
+			mlx5e_tx_dma_unmap(sq->pdev, dma);
+		}
+
+		dev_kfree_skb_any(skb);
+		sq->cc += wi->num_wqebbs;
+	}
+}
+
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 {
 	struct mlx5e_sq *sq;
@@ -352,6 +381,9 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
 	sq = container_of(cq, struct mlx5e_sq, cq);
 
+	if (unlikely(test_bit(MLX5E_SQ_STATE_TX_TIMEOUT, &sq->state)))
+		return false;
+
 	npkts = 0;
 	nbytes = 0;
 
