net: thunderx: Fix transmit queue timeout issue

Transmit queue timeout issue is seen in two cases
- Due to a race condition btw setting stop_queue at xmit()
  and checking for stopped_queue in NAPI poll routine, at times
  transmission from a SQ comes to a halt. This is fixed
  by using barriers and also added a check for SQ free descriptors,
  incase SQ is stopped and there are only CQE_RX i.e no CQE_TX.
- Contrary to an assumption, a HW errata where HW doesn't stop transmission
  even though there are not enough CQEs available for a CQE_TX is
  not fixed in T88 pass 2.x. This results in a Qset error with
  'CQ_WR_FULL' stalling transmission. This is fixed by adjusting
  RXQ's  RED levels for CQ level such that there is always enough
  space left for CQE_TXs.

Signed-off-by: Sunil Goutham <sgoutham@cavium.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index 7b336cd..d2ac133 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -1190,30 +1190,12 @@ static int nicvf_sq_append_tso(struct nicvf *nic, struct snd_queue *sq,
 }
 
 /* Append an skb to a SQ for packet transfer. */
-int nicvf_sq_append_skb(struct nicvf *nic, struct sk_buff *skb)
+int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq,
+			struct sk_buff *skb, u8 sq_num)
 {
 	int i, size;
 	int subdesc_cnt, tso_sqe = 0;
-	int sq_num, qentry;
-	struct queue_set *qs;
-	struct snd_queue *sq;
-
-	sq_num = skb_get_queue_mapping(skb);
-	if (sq_num >= MAX_SND_QUEUES_PER_QS) {
-		/* Get secondary Qset's SQ structure */
-		i = sq_num / MAX_SND_QUEUES_PER_QS;
-		if (!nic->snicvf[i - 1]) {
-			netdev_warn(nic->netdev,
-				    "Secondary Qset#%d's ptr not initialized\n",
-				    i - 1);
-			return 1;
-		}
-		nic = (struct nicvf *)nic->snicvf[i - 1];
-		sq_num = sq_num % MAX_SND_QUEUES_PER_QS;
-	}
-
-	qs = nic->qs;
-	sq = &qs->sq[sq_num];
+	int qentry;
 
 	subdesc_cnt = nicvf_sq_subdesc_required(nic, skb);
 	if (subdesc_cnt > atomic_read(&sq->free_cnt))