qlcnic: Multi Tx queue support for 82xx Series adapter.

o  82xx firmware allows support for multiple Tx queues. This
   patch will enable multi Tx queue support for 82xx series
   adapter. Max number of Tx queues supported will be 8.

Signed-off-by: Himanshu Madhani <himanshu.madhani@qlogic.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 117 insertions, 23 deletions

diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index cec0908bb1d6..f4b09f44173c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -127,6 +127,21 @@
 struct sk_buff *qlcnic_process_rxbuf(struct qlcnic_adapter *,
 				     struct qlcnic_host_rds_ring *, u16, u16);
 
+inline void qlcnic_enable_tx_intr(struct qlcnic_adapter *adapter,
+				  struct qlcnic_host_tx_ring *tx_ring)
+{
+	if (qlcnic_check_multi_tx(adapter))
+		writel(0x0, tx_ring->crb_intr_mask);
+}
+
+
+static inline void qlcnic_disable_tx_int(struct qlcnic_adapter *adapter,
+					 struct qlcnic_host_tx_ring *tx_ring)
+{
+	if (qlcnic_check_multi_tx(adapter))
+		writel(1, tx_ring->crb_intr_mask);
+}
+
 inline void qlcnic_83xx_enable_tx_intr(struct qlcnic_adapter *adapter,
 				       struct qlcnic_host_tx_ring *tx_ring)
 {
@@ -354,14 +369,14 @@ static void qlcnic_send_filter(struct qlcnic_adapter *adapter,
 }
 
 static int qlcnic_tx_pkt(struct qlcnic_adapter *adapter,
-			 struct cmd_desc_type0 *first_desc, struct sk_buff *skb)
+			 struct cmd_desc_type0 *first_desc, struct sk_buff *skb,
+			 struct qlcnic_host_tx_ring *tx_ring)
 {
 	u8 l4proto, opcode = 0, hdr_len = 0;
 	u16 flags = 0, vlan_tci = 0;
 	int copied, offset, copy_len, size;
 	struct cmd_desc_type0 *hwdesc;
 	struct vlan_ethhdr *vh;
-	struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring;
 	u16 protocol = ntohs(skb->protocol);
 	u32 producer = tx_ring->producer;
 
@@ -544,7 +559,7 @@ static inline void qlcnic_clear_cmddesc(u64 *desc)
 netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 {
 	struct qlcnic_adapter *adapter = netdev_priv(netdev);
-	struct qlcnic_host_tx_ring *tx_ring = adapter->tx_ring;
+	struct qlcnic_host_tx_ring *tx_ring;
 	struct qlcnic_cmd_buffer *pbuf;
 	struct qlcnic_skb_frag *buffrag;
 	struct cmd_desc_type0 *hwdesc, *first_desc;
@@ -553,10 +568,8 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	int i, k, frag_count, delta = 0;
 	u32 producer, num_txd;
 
-	num_txd = tx_ring->num_desc;
-
 	if (!test_bit(__QLCNIC_DEV_UP, &adapter->state)) {
-		netif_stop_queue(netdev);
+		netif_tx_stop_all_queues(netdev);
 		return NETDEV_TX_BUSY;
 	}
 
@@ -566,7 +579,14 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 			goto drop_packet;
 	}
 
+	if (qlcnic_check_multi_tx(adapter))
+		tx_ring = &adapter->tx_ring[skb_get_queue_mapping(skb)];
+	else
+		tx_ring = &adapter->tx_ring[0];
+	num_txd = tx_ring->num_desc;
+
 	frag_count = skb_shinfo(skb)->nr_frags + 1;
+
 	/* 14 frags supported for normal packet and
 	 * 32 frags supported for TSO packet
 	 */
@@ -581,11 +601,12 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	}
 
 	if (unlikely(qlcnic_tx_avail(tx_ring) <= TX_STOP_THRESH)) {
-		netif_stop_queue(netdev);
+		netif_tx_stop_queue(tx_ring->txq);
 		if (qlcnic_tx_avail(tx_ring) > TX_STOP_THRESH) {
-			netif_start_queue(netdev);
+			netif_tx_start_queue(tx_ring->txq);
 		} else {
 			adapter->stats.xmit_off++;
+			tx_ring->xmit_off++;
 			return NETDEV_TX_BUSY;
 		}
 	}
@@ -640,7 +661,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	tx_ring->producer = get_next_index(producer, num_txd);
 	smp_mb();
 
-	if (unlikely(qlcnic_tx_pkt(adapter, first_desc, skb)))
+	if (unlikely(qlcnic_tx_pkt(adapter, first_desc, skb, tx_ring)))
 		goto unwind_buff;
 
 	if (adapter->drv_mac_learn)
@@ -648,6 +669,7 @@ netdev_tx_t qlcnic_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 
 	adapter->stats.txbytes += skb->len;
 	adapter->stats.xmitcalled++;
+	tx_ring->xmit_called++;
 
 	qlcnic_update_cmd_producer(tx_ring);
 
@@ -670,7 +692,7 @@ void qlcnic_advert_link_change(struct qlcnic_adapter *adapter, int linkup)
 		adapter->ahw->linkup = 0;
 		if (netif_running(netdev)) {
 			netif_carrier_off(netdev);
-			netif_stop_queue(netdev);
+			netif_tx_stop_all_queues(netdev);
 		}
 	} else if (!adapter->ahw->linkup && linkup) {
 		netdev_info(netdev, "NIC Link is up\n");
@@ -765,9 +787,6 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 	struct net_device *netdev = adapter->netdev;
 	struct qlcnic_skb_frag *frag;
 
-	if (!spin_trylock(&adapter->tx_clean_lock))
-		return 1;
-
 	sw_consumer = tx_ring->sw_consumer;
 	hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer));
 
@@ -785,6 +804,7 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 				frag->dma = 0ULL;
 			}
 			adapter->stats.xmitfinished++;
+			tx_ring->xmit_finished++;
 			dev_kfree_skb_any(buffer->skb);
 			buffer->skb = NULL;
 		}
@@ -797,10 +817,12 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 	if (count && netif_running(netdev)) {
 		tx_ring->sw_consumer = sw_consumer;
 		smp_mb();
-		if (netif_queue_stopped(netdev) && netif_carrier_ok(netdev)) {
+		if (netif_tx_queue_stopped(tx_ring->txq) &&
+		    netif_carrier_ok(netdev)) {
 			if (qlcnic_tx_avail(tx_ring) > TX_STOP_THRESH) {
-				netif_wake_queue(netdev);
+				netif_tx_wake_queue(tx_ring->txq);
 				adapter->stats.xmit_on++;
+				tx_ring->xmit_on++;
 			}
 		}
 		adapter->tx_timeo_cnt = 0;
@@ -820,7 +842,6 @@ static int qlcnic_process_cmd_ring(struct qlcnic_adapter *adapter,
 	 */
 	hw_consumer = le32_to_cpu(*(tx_ring->hw_consumer));
 	done = (sw_consumer == hw_consumer);
-	spin_unlock(&adapter->tx_clean_lock);
 
 	return done;
 }
@@ -830,16 +851,40 @@ static int qlcnic_poll(struct napi_struct *napi, int budget)
 	int tx_complete, work_done;
 	struct qlcnic_host_sds_ring *sds_ring;
 	struct qlcnic_adapter *adapter;
+	struct qlcnic_host_tx_ring *tx_ring;
 
 	sds_ring = container_of(napi, struct qlcnic_host_sds_ring, napi);
 	adapter = sds_ring->adapter;
-	tx_complete = qlcnic_process_cmd_ring(adapter, adapter->tx_ring,
+	tx_ring = sds_ring->tx_ring;
+
+	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring,
 					      budget);
 	work_done = qlcnic_process_rcv_ring(sds_ring, budget);
 	if ((work_done < budget) && tx_complete) {
 		napi_complete(&sds_ring->napi);
-		if (test_bit(__QLCNIC_DEV_UP, &adapter->state))
+		if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) {
 			qlcnic_enable_int(sds_ring);
+			qlcnic_enable_tx_intr(adapter, tx_ring);
+		}
+	}
+
+	return work_done;
+}
+
+static int qlcnic_tx_poll(struct napi_struct *napi, int budget)
+{
+	struct qlcnic_host_tx_ring *tx_ring;
+	struct qlcnic_adapter *adapter;
+	int work_done;
+
+	tx_ring = container_of(napi, struct qlcnic_host_tx_ring, napi);
+	adapter = tx_ring->adapter;
+
+	work_done = qlcnic_process_cmd_ring(adapter, tx_ring, budget);
+	if (work_done) {
+		napi_complete(&tx_ring->napi);
+		if (test_bit(__QLCNIC_DEV_UP, &adapter->state))
+			qlcnic_enable_tx_intr(adapter, tx_ring);
 	}
 
 	return work_done;
@@ -1411,6 +1456,7 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter,
 	int ring, max_sds_rings;
 	struct qlcnic_host_sds_ring *sds_ring;
 	struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx;
+	struct qlcnic_host_tx_ring *tx_ring;
 
 	if (qlcnic_alloc_sds_rings(recv_ctx, adapter->max_sds_rings))
 		return -ENOMEM;
@@ -1419,12 +1465,21 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter,
 
 	for (ring = 0; ring < adapter->max_sds_rings; ring++) {
 		sds_ring = &recv_ctx->sds_rings[ring];
-		if (ring == adapter->max_sds_rings - 1)
-			netif_napi_add(netdev, &sds_ring->napi, qlcnic_poll,
-				       QLCNIC_NETDEV_WEIGHT / max_sds_rings);
-		else
+		if (qlcnic_check_multi_tx(adapter) &&
+		    (adapter->max_drv_tx_rings > 1)) {
 			netif_napi_add(netdev, &sds_ring->napi, qlcnic_rx_poll,
-				       QLCNIC_NETDEV_WEIGHT*2);
+					QLCNIC_NETDEV_WEIGHT * 2);
+		} else {
+			if (ring == (adapter->max_sds_rings - 1))
+				netif_napi_add(netdev, &sds_ring->napi,
+					       qlcnic_poll,
+					       QLCNIC_NETDEV_WEIGHT /
+					       max_sds_rings);
+			else
+				netif_napi_add(netdev, &sds_ring->napi,
+					       qlcnic_rx_poll,
+					       QLCNIC_NETDEV_WEIGHT * 2);
+		}
 	}
 
 	if (qlcnic_alloc_tx_rings(adapter, netdev)) {
@@ -1432,6 +1487,14 @@ int qlcnic_82xx_napi_add(struct qlcnic_adapter *adapter,
 		return -ENOMEM;
 	}
 
+	if (qlcnic_check_multi_tx(adapter)) {
+		for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) {
+			tx_ring = &adapter->tx_ring[ring];
+			netif_napi_add(netdev, &tx_ring->napi, qlcnic_tx_poll,
+				       QLCNIC_NETDEV_WEIGHT);
+		}
+	}
+
 	return 0;
 }
 
@@ -1440,6 +1503,7 @@ void qlcnic_82xx_napi_del(struct qlcnic_adapter *adapter)
 	int ring;
 	struct qlcnic_host_sds_ring *sds_ring;
 	struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx;
+	struct qlcnic_host_tx_ring *tx_ring;
 
 	for (ring = 0; ring < adapter->max_sds_rings; ring++) {
 		sds_ring = &recv_ctx->sds_rings[ring];
@@ -1447,6 +1511,14 @@ void qlcnic_82xx_napi_del(struct qlcnic_adapter *adapter)
 	}
 
 	qlcnic_free_sds_rings(adapter->recv_ctx);
+
+	if (qlcnic_check_multi_tx(adapter)) {
+		for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) {
+			tx_ring = &adapter->tx_ring[ring];
+			netif_napi_del(&tx_ring->napi);
+		}
+	}
+
 	qlcnic_free_tx_rings(adapter);
 }
 
@@ -1454,6 +1526,7 @@ void qlcnic_82xx_napi_enable(struct qlcnic_adapter *adapter)
 {
 	int ring;
 	struct qlcnic_host_sds_ring *sds_ring;
+	struct qlcnic_host_tx_ring *tx_ring;
 	struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx;
 
 	if (adapter->is_up != QLCNIC_ADAPTER_UP_MAGIC)
@@ -1464,12 +1537,23 @@ void qlcnic_82xx_napi_enable(struct qlcnic_adapter *adapter)
 		napi_enable(&sds_ring->napi);
 		qlcnic_enable_int(sds_ring);
 	}
+
+	if (qlcnic_check_multi_tx(adapter) &&
+	    (adapter->flags & QLCNIC_MSIX_ENABLED) &&
+	    (adapter->max_drv_tx_rings > 1)) {
+		for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) {
+			tx_ring = &adapter->tx_ring[ring];
+			napi_enable(&tx_ring->napi);
+			qlcnic_enable_tx_intr(adapter, tx_ring);
+		}
+	}
 }
 
 void qlcnic_82xx_napi_disable(struct qlcnic_adapter *adapter)
 {
 	int ring;
 	struct qlcnic_host_sds_ring *sds_ring;
+	struct qlcnic_host_tx_ring *tx_ring;
 	struct qlcnic_recv_context *recv_ctx = adapter->recv_ctx;
 
 	if (adapter->is_up != QLCNIC_ADAPTER_UP_MAGIC)
@@ -1481,6 +1565,16 @@ void qlcnic_82xx_napi_disable(struct qlcnic_adapter *adapter)
 		napi_synchronize(&sds_ring->napi);
 		napi_disable(&sds_ring->napi);
 	}
+
+	if ((adapter->flags & QLCNIC_MSIX_ENABLED) &&
+	    qlcnic_check_multi_tx(adapter)) {
+		for (ring = 0; ring < adapter->max_drv_tx_rings; ring++) {
+			tx_ring = &adapter->tx_ring[ring];
+			qlcnic_disable_tx_int(adapter, tx_ring);
+			napi_synchronize(&tx_ring->napi);
+			napi_disable(&tx_ring->napi);
+		}
+	}
 }
 
 #define QLC_83XX_NORMAL_LB_PKT	(1ULL << 36)