net/mlx5e: Extend SKB room check to include PTP-SQ

When tx_port_ts is set, the driver diverts all UPD traffic over PTP port
to a dedicated PTP-SQ. The SKBs are cached until the wire-CQE arrives.
When the packet size is greater then MTU, the firmware might drop it and
the packet won't be transmitted to the wire, hence the wire-CQE won't
reach the driver. In this case the SKBs are accumulated in the SKB fifo.
Add room check to consider the PTP-SQ SKB fifo, when the SKB fifo is
full, driver stops the queue resulting in a TX timeout. Devlink
TX-reporter can recover from it.

Fixes: 1880bc4e4a96 ("net/mlx5e: Add TX port timestamp support")
Signed-off-by: Aya Levin <ayal@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Saeed Mahameed <saeedm@nvidia.com>
Link: https://lore.kernel.org/r/20221026135153.154807-5-saeed@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
index 5bce554e131a9c8d526f3c8292fe51ff9441f0fc..cc7efde88ac3c69a4ff446261f6f6803f82fdbf2 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/ptp.h
@@ -6,6 +6,7 @@
 
 #include "en.h"
 #include "en_stats.h"
+#include "en/txrx.h"
 #include <linux/ptp_classify.h>
 
 #define MLX5E_PTP_CHANNEL_IX 0
@@ -68,6 +69,14 @@ static inline bool mlx5e_use_ptpsq(struct sk_buff *skb)
                fk.ports.dst == htons(PTP_EV_PORT));
 }
 
+static inline bool mlx5e_ptpsq_fifo_has_room(struct mlx5e_txqsq *sq)
+{
+       if (!sq->ptpsq)
+               return true;
+
+       return mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo);
+}
+
 int mlx5e_ptp_open(struct mlx5e_priv *priv, struct mlx5e_params *params,
                   u8 lag_port, struct mlx5e_ptp **cp);
 void mlx5e_ptp_close(struct mlx5e_ptp *c);

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
index 4456ad5cedf1ee536d813f5ac49822ed1e70e089..cb164b62f54365664ac52d541a5cb6f19fd0d0ff 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
@@ -57,6 +57,12 @@ netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev);
 bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget);
 void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq);
 
+static inline bool
+mlx5e_skb_fifo_has_room(struct mlx5e_skb_fifo *fifo)
+{
+       return (*fifo->pc - *fifo->cc) < fifo->mask;
+}
+
 static inline bool
 mlx5e_wqc_has_room_for(struct mlx5_wq_cyc *wq, u16 cc, u16 pc, u16 n)
 {

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
index bf2232a2a836bb8ca55fb1e92de74ce4d8452e8f..6adca01fbdc9dda097591722244e5f1555026351 100644 (file)
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c
@@ -392,6 +392,11 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb,
        if (unlikely(sq->ptpsq)) {
                mlx5e_skb_cb_hwtstamp_init(skb);
                mlx5e_skb_fifo_push(&sq->ptpsq->skb_fifo, skb);
+               if (!netif_tx_queue_stopped(sq->txq) &&
+                   !mlx5e_skb_fifo_has_room(&sq->ptpsq->skb_fifo)) {
+                       netif_tx_stop_queue(sq->txq);
+                       sq->stats->stopped++;
+               }
                skb_get(skb);
        }
 
@@ -868,6 +873,7 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget)
 
        if (netif_tx_queue_stopped(sq->txq) &&
            mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, sq->stop_room) &&
+           mlx5e_ptpsq_fifo_has_room(sq) &&
            !test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) {
                netif_tx_wake_queue(sq->txq);
                stats->wake++;