[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>

drivers/net/Kconfig

@@ -25,6 +25,14 @@ menuconfig NETDEVICES
 # that for each of the symbols.
 if NETDEVICES
 
+config NETDEVICES_MULTIQUEUE
+	bool "Netdevice multiple hardware queue support"
+	---help---
+	  Say Y here if you want to allow the network stack to use multiple
+	  hardware TX queues on an ethernet device.
+
+	  Most people will say N here.
+
 config IFB
 	tristate "Intermediate Functional Block support"
 	depends on NET_CLS_ACT

include/linux/etherdevice.h

@@ -39,7 +39,8 @@ extern void		eth_header_cache_update(struct hh_cache *hh, struct net_device *dev
 extern int		eth_header_cache(struct neighbour *neigh,
 					 struct hh_cache *hh);
 
-extern struct net_device *alloc_etherdev(int sizeof_priv);
+extern struct net_device *alloc_etherdev_mq(int sizeof_priv, unsigned int queue_count);
+#define alloc_etherdev(sizeof_priv) alloc_etherdev_mq(sizeof_priv, 1)
 
 /**
  * is_zero_ether_addr - Determine if give Ethernet address is all zeros.

include/linux/netdevice.h

@@ -108,6 +108,14 @@ struct wireless_dev;
 #define MAX_HEADER (LL_MAX_HEADER + 48)
 #endif
 
+struct net_device_subqueue
+{
+	/* Give a control state for each queue.  This struct may contain
+	 * per-queue locks in the future.
+	 */
+	unsigned long   state;
+};
+
 /*
  *	Network device statistics. Akin to the 2.0 ether stats but
  *	with byte counters.
@@ -331,6 +339,7 @@ struct net_device
 #define NETIF_F_VLAN_CHALLENGED	1024	/* Device cannot handle VLAN packets */
 #define NETIF_F_GSO		2048	/* Enable software GSO. */
 #define NETIF_F_LLTX		4096	/* LockLess TX */
+#define NETIF_F_MULTI_QUEUE	16384	/* Has multiple TX/RX queues */
 
 	/* Segmentation offload features */
 #define NETIF_F_GSO_SHIFT	16
@@ -557,6 +566,10 @@ struct net_device
 
 	/* rtnetlink link ops */
 	const struct rtnl_link_ops *rtnl_link_ops;
+
+	/* The TX queue control structures */
+	unsigned int			egress_subqueue_count;
+	struct net_device_subqueue	egress_subqueue[0];
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
@@ -565,9 +578,7 @@ struct net_device
 
 static inline void *netdev_priv(const struct net_device *dev)
 {
-	return (char *)dev + ((sizeof(struct net_device)
-					+ NETDEV_ALIGN_CONST)
-				& ~NETDEV_ALIGN_CONST);
+	return dev->priv;
 }
 
 #define SET_MODULE_OWNER(dev) do { } while (0)
@@ -719,6 +730,62 @@ static inline int netif_running(const struct net_device *dev)
 	return test_bit(__LINK_STATE_START, &dev->state);
 }
 
+/*
+ * Routines to manage the subqueues on a device.  We only need start
+ * stop, and a check if it's stopped.  All other device management is
+ * done at the overall netdevice level.
+ * Also test the device if we're multiqueue.
+ */
+static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+	clear_bit(__LINK_STATE_XOFF, &dev->egress_subqueue[queue_index].state);
+#endif
+}
+
+static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+#ifdef CONFIG_NETPOLL_TRAP
+	if (netpoll_trap())
+		return;
+#endif
+	set_bit(__LINK_STATE_XOFF, &dev->egress_subqueue[queue_index].state);
+#endif
+}
+
+static inline int netif_subqueue_stopped(const struct net_device *dev,
+					 u16 queue_index)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+	return test_bit(__LINK_STATE_XOFF,
+			&dev->egress_subqueue[queue_index].state);
+#else
+	return 0;
+#endif
+}
+
+static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+#ifdef CONFIG_NETPOLL_TRAP
+	if (netpoll_trap())
+		return;
+#endif
+	if (test_and_clear_bit(__LINK_STATE_XOFF,
+			       &dev->egress_subqueue[queue_index].state))
+		__netif_schedule(dev);
+#endif
+}
+
+static inline int netif_is_multiqueue(const struct net_device *dev)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+	return (!!(NETIF_F_MULTI_QUEUE & dev->features));
+#else
+	return 0;
+#endif
+}
 
 /* Use this variant when it is known for sure that it
  * is executing from interrupt context.
@@ -1009,8 +1076,11 @@ static inline void netif_tx_disable(struct net_device *dev)
 extern void		ether_setup(struct net_device *dev);
 
 /* Support for loadable net-drivers */
-extern struct net_device *alloc_netdev(int sizeof_priv, const char *name,
-				       void (*setup)(struct net_device *));
+extern struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name,
+				       void (*setup)(struct net_device *),
+				       unsigned int queue_count);
+#define alloc_netdev(sizeof_priv, name, setup) \
+	alloc_netdev_mq(sizeof_priv, name, setup, 1)
 extern int		register_netdev(struct net_device *dev);
 extern void		unregister_netdev(struct net_device *dev);
 /* Functions used for secondary unicast and multicast support */

include/linux/skbuff.h

@@ -196,7 +196,6 @@ typedef unsigned char *sk_buff_data_t;
  *	@sk: Socket we are owned by
  *	@tstamp: Time we arrived
  *	@dev: Device we arrived on/are leaving by
- *	@iif: ifindex of device we arrived on
  *	@transport_header: Transport layer header
  *	@network_header: Network layer header
  *	@mac_header: Link layer header
@@ -231,6 +230,8 @@ typedef unsigned char *sk_buff_data_t;
  *	@nfctinfo: Relationship of this skb to the connection
  *	@nfct_reasm: netfilter conntrack re-assembly pointer
  *	@nf_bridge: Saved data about a bridged frame - see br_netfilter.c
+ *	@iif: ifindex of device we arrived on
+ *	@queue_mapping: Queue mapping for multiqueue devices
  *	@tc_index: Traffic control index
  *	@tc_verd: traffic control verdict
  *	@dma_cookie: a cookie to one of several possible DMA operations
@@ -246,8 +247,6 @@ struct sk_buff {
 	struct sock		*sk;
 	ktime_t			tstamp;
 	struct net_device	*dev;
-	int			iif;
-	/* 4 byte hole on 64 bit*/
 
 	struct  dst_entry	*dst;
 	struct	sec_path	*sp;
@@ -290,12 +289,18 @@ struct sk_buff {
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif
+
+	int			iif;
+	__u16			queue_mapping;
+
 #ifdef CONFIG_NET_SCHED
 	__u16			tc_index;	/* traffic control index */
 #ifdef CONFIG_NET_CLS_ACT
 	__u16			tc_verd;	/* traffic control verdict */
 #endif
 #endif
+	/* 2 byte hole */
+
 #ifdef CONFIG_NET_DMA
 	dma_cookie_t		dma_cookie;
 #endif
@@ -1725,6 +1730,20 @@ static inline void skb_init_secmark(struct sk_buff *skb)
 { }
 #endif
 
+static inline void skb_set_queue_mapping(struct sk_buff *skb, u16 queue_mapping)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+	skb->queue_mapping = queue_mapping;
+#endif
+}
+
+static inline void skb_copy_queue_mapping(struct sk_buff *to, const struct sk_buff *from)
+{
+#ifdef CONFIG_NETDEVICES_MULTIQUEUE
+	to->queue_mapping = from->queue_mapping;
+#endif
+}
+
 static inline int skb_is_gso(const struct sk_buff *skb)
 {
 	return skb_shinfo(skb)->gso_size;

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

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);
 

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:

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);

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);

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);