[CORE] Stack changes to add multiqueue hardware support API

Add the multiqueue hardware device support API to the core network
stack.  Allow drivers to allocate multiple queues and manage them at
the netdev level if they choose to do so.

Added a new field to sk_buff, namely queue_mapping, for drivers to
know which tx_ring to select based on OS classification of the flow.

Signed-off-by: Peter P Waskiewicz Jr <peter.p.waskiewicz.jr@intel.com>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 51 insertions, 21 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 6dce9d2d46f2..7ddf66d0ad5e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1429,7 +1429,9 @@ gso:
 			skb->next = nskb;
 			return rc;
 		}
-		if (unlikely(netif_queue_stopped(dev) && skb->next))
+		if (unlikely((netif_queue_stopped(dev) ||
+			     netif_subqueue_stopped(dev, skb->queue_mapping)) &&
+			     skb->next))
 			return NETDEV_TX_BUSY;
 	} while (skb->next);
 
@@ -1547,6 +1549,8 @@ gso:
 		spin_lock(&dev->queue_lock);
 		q = dev->qdisc;
 		if (q->enqueue) {
+			/* reset queue_mapping to zero */
+			skb->queue_mapping = 0;
 			rc = q->enqueue(skb, q);
 			qdisc_run(dev);
 			spin_unlock(&dev->queue_lock);
@@ -1576,7 +1580,8 @@ gso:
 
 			HARD_TX_LOCK(dev, cpu);
 
-			if (!netif_queue_stopped(dev)) {
+			if (!netif_queue_stopped(dev) &&
+			    !netif_subqueue_stopped(dev, skb->queue_mapping)) {
 				rc = 0;
 				if (!dev_hard_start_xmit(skb, dev)) {
 					HARD_TX_UNLOCK(dev);
@@ -3539,16 +3544,18 @@ static struct net_device_stats *internal_stats(struct net_device *dev)
 }
 
 /**
- *	alloc_netdev - allocate network device
+ *	alloc_netdev_mq - allocate network device
  *	@sizeof_priv:	size of private data to allocate space for
  *	@name:		device name format string
  *	@setup:		callback to initialize device
+ *	@queue_count:	the number of subqueues to allocate
  *
  *	Allocates a struct net_device with private data area for driver use
- *	and performs basic initialization.
+ *	and performs basic initialization.  Also allocates subquue structs
+ *	for each queue on the device at the end of the netdevice.
  */
-struct net_device *alloc_netdev(int sizeof_priv, const char *name,
-		void (*setup)(struct net_device *))
+struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
+		void (*setup)(struct net_device *), unsigned int queue_count)
 {
 	void *p;
 	struct net_device *dev;
@@ -3557,7 +3564,9 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name,
 	BUG_ON(strlen(name) >= sizeof(dev->name));
 
 	/* ensure 32-byte alignment of both the device and private area */
-	alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST;
+	alloc_size = (sizeof(*dev) + NETDEV_ALIGN_CONST +
+		     (sizeof(struct net_device_subqueue) * queue_count)) &
+		     ~NETDEV_ALIGN_CONST;
 	alloc_size += sizeof_priv + NETDEV_ALIGN_CONST;
 
 	p = kzalloc(alloc_size, GFP_KERNEL);
@@ -3570,15 +3579,22 @@ struct net_device *alloc_netdev(int sizeof_priv, const char *name,
 		(((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST);
 	dev->padded = (char *)dev - (char *)p;
 
-	if (sizeof_priv)
-		dev->priv = netdev_priv(dev);
+	if (sizeof_priv) {
+		dev->priv = ((char *)dev +
+			     ((sizeof(struct net_device) +
+			       (sizeof(struct net_device_subqueue) *
+				queue_count) + NETDEV_ALIGN_CONST)
+			      & ~NETDEV_ALIGN_CONST));
+	}
+
+	dev->egress_subqueue_count = queue_count;
 
 	dev->get_stats = internal_stats;
 	setup(dev);
 	strcpy(dev->name, name);
 	return dev;
 }
-EXPORT_SYMBOL(alloc_netdev);
+EXPORT_SYMBOL(alloc_netdev_mq);
 
 /**
  *	free_netdev - free network device
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a0efdd7a6b37..4b06d1936375 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -66,8 +66,9 @@ static void queue_process(struct work_struct *work)
 
 		local_irq_save(flags);
 		netif_tx_lock(dev);
-		if (netif_queue_stopped(dev) ||
-		    dev->hard_start_xmit(skb, dev) != NETDEV_TX_OK) {
+		if ((netif_queue_stopped(dev) ||
+		     netif_subqueue_stopped(dev, skb->queue_mapping)) ||
+		     dev->hard_start_xmit(skb, dev) != NETDEV_TX_OK) {
 			skb_queue_head(&npinfo->txq, skb);
 			netif_tx_unlock(dev);
 			local_irq_restore(flags);
@@ -254,7 +255,8 @@ static void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb)
 		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
 		     tries > 0; --tries) {
 			if (netif_tx_trylock(dev)) {
-				if (!netif_queue_stopped(dev))
+				if (!netif_queue_stopped(dev) &&
+				    !netif_subqueue_stopped(dev, skb->queue_mapping))
 					status = dev->hard_start_xmit(skb, dev);
 				netif_tx_unlock(dev);
 
diff --git a/net/core/pktgen.c b/net/core/pktgen.c
index 9cd3a1cb60ef..dffe067e7a7b 100644
--- a/net/core/pktgen.c
+++ b/net/core/pktgen.c
@@ -3139,7 +3139,9 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
 		}
 	}
 
-	if (netif_queue_stopped(odev) || need_resched()) {
+	if ((netif_queue_stopped(odev) ||
+	     netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) ||
+	     need_resched()) {
 		idle_start = getCurUs();
 
 		if (!netif_running(odev)) {
@@ -3154,7 +3156,8 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
 
 		pkt_dev->idle_acc += getCurUs() - idle_start;
 
-		if (netif_queue_stopped(odev)) {
+		if (netif_queue_stopped(odev) ||
+		    netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) {
 			pkt_dev->next_tx_us = getCurUs();	/* TODO */
 			pkt_dev->next_tx_ns = 0;
 			goto out;	/* Try the next interface */
@@ -3181,7 +3184,8 @@ static __inline__ void pktgen_xmit(struct pktgen_dev *pkt_dev)
 	}
 
 	netif_tx_lock_bh(odev);
-	if (!netif_queue_stopped(odev)) {
+	if (!netif_queue_stopped(odev) &&
+	    !netif_subqueue_stopped(odev, pkt_dev->skb->queue_mapping)) {
 
 		atomic_inc(&(pkt_dev->skb->users));
 	      retry_now:
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index c989c3a0f907..6a41b96b3d37 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -419,6 +419,7 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 	n->nohdr = 0;
 	C(pkt_type);
 	C(ip_summed);
+	skb_copy_queue_mapping(n, skb);
 	C(priority);
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	C(ipvs_property);
@@ -460,6 +461,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 #endif
 	new->sk		= NULL;
 	new->dev	= old->dev;
+	skb_copy_queue_mapping(new, old);
 	new->priority	= old->priority;
 	new->protocol	= old->protocol;
 	new->dst	= dst_clone(old->dst);
@@ -1932,6 +1934,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features)
 		tail = nskb;
 
 		nskb->dev = skb->dev;
+		skb_copy_queue_mapping(nskb, skb);
 		nskb->priority = skb->priority;
 		nskb->protocol = skb->protocol;
 		nskb->dst = dst_clone(skb->dst);
diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c
index 0ac2524f3b68..1387e5411f77 100644
--- a/net/ethernet/eth.c
+++ b/net/ethernet/eth.c
@@ -316,9 +316,10 @@ void ether_setup(struct net_device *dev)
 EXPORT_SYMBOL(ether_setup);
 
 /**
- * alloc_etherdev - Allocates and sets up an Ethernet device
+ * alloc_etherdev_mq - Allocates and sets up an Ethernet device
  * @sizeof_priv: Size of additional driver-private structure to be allocated
  *	for this Ethernet device
+ * @queue_count: The number of queues this device has.
  *
  * Fill in the fields of the device structure with Ethernet-generic
  * values. Basically does everything except registering the device.
@@ -328,8 +329,8 @@ EXPORT_SYMBOL(ether_setup);
  * this private data area.
  */
 
-struct net_device *alloc_etherdev(int sizeof_priv)
+struct net_device *alloc_etherdev_mq(int sizeof_priv, unsigned int queue_count)
 {
-	return alloc_netdev(sizeof_priv, "eth%d", ether_setup);
+	return alloc_netdev_mq(sizeof_priv, "eth%d", ether_setup, queue_count);
 }
-EXPORT_SYMBOL(alloc_etherdev);
+EXPORT_SYMBOL(alloc_etherdev_mq);
diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c
index f05ad9a30b4c..dfe7e4520988 100644
--- a/net/sched/sch_teql.c
+++ b/net/sched/sch_teql.c
@@ -277,6 +277,7 @@ static int teql_master_xmit(struct sk_buff *skb, struct net_device *dev)
 	int busy;
 	int nores;
 	int len = skb->len;
+	int subq = skb->queue_mapping;
 	struct sk_buff *skb_res = NULL;
 
 	start = master->slaves;
@@ -293,7 +294,9 @@ restart:
 
 		if (slave->qdisc_sleeping != q)
 			continue;
-		if (netif_queue_stopped(slave) || ! netif_running(slave)) {
+		if (netif_queue_stopped(slave) ||
+		    netif_subqueue_stopped(slave, subq) ||
+		    !netif_running(slave)) {
 			busy = 1;
 			continue;
 		}
@@ -302,6 +305,7 @@ restart:
 		case 0:
 			if (netif_tx_trylock(slave)) {
 				if (!netif_queue_stopped(slave) &&
+				    !netif_subqueue_stopped(slave, subq) &&
 				    slave->hard_start_xmit(skb, slave) == 0) {
 					netif_tx_unlock(slave);
 					master->slaves = NEXT_SLAVE(q);