net: Add support for subordinate device traffic classes

This patch is meant to provide the basic tools needed to allow us to create
subordinate device traffic classes. The general idea here is to allow
subdividing the queues of a device into queue groups accessible through an
upper device such as a macvlan.

The idea here is to enforce the idea that an upper device has to be a
single queue device, ideally with IFF_NO_QUQUE set. With that being the
case we can pretty much guarantee that the tc_to_txq mappings and XPS maps
for the upper device are unused. As such we could reuse those in order to
support subdividing the lower device and distributing those queues between
the subordinate devices.

In order to distinguish between a regular set of traffic classes and if a
device is carrying subordinate traffic classes I changed num_tc from a u8
to a s16 value and use the negative values to represent the subordinate
pool values. So starting at -1 and running to -32768 we can encode those as
pool values, and the existing values of 0 to 15 can be maintained.
Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
Tested-by: Andrew Bowers <andrewx.bowers@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>

include/linux/netdevice.h

@@ -575,6 +575,9 @@ struct netdev_queue {
 	 * (/sys/class/net/DEV/Q/trans_timeout)
 	 */
 	unsigned long		trans_timeout;
+
+	/* Subordinate device that the queue has been assigned to */
+	struct net_device	*sb_dev;
 /*
  * write-mostly part
  */
@@ -1991,7 +1994,7 @@ struct net_device {
 #ifdef CONFIG_DCB
 	const struct dcbnl_rtnl_ops *dcbnl_ops;
 #endif
-	u8			num_tc;
+	s16			num_tc;
 	struct netdev_tc_txq	tc_to_txq[TC_MAX_QUEUE];
 	u8			prio_tc_map[TC_BITMASK + 1];
 
@@ -2045,6 +2048,17 @@ int netdev_get_num_tc(struct net_device *dev)
 	return dev->num_tc;
 }
 
+void netdev_unbind_sb_channel(struct net_device *dev,
+			      struct net_device *sb_dev);
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+				 struct net_device *sb_dev,
+				 u8 tc, u16 count, u16 offset);
+int netdev_set_sb_channel(struct net_device *dev, u16 channel);
+static inline int netdev_get_sb_channel(struct net_device *dev)
+{
+	return max_t(int, -dev->num_tc, 0);
+}
+
 static inline
 struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev,
 					 unsigned int index)

net/core/dev.c

@@ -2067,11 +2067,13 @@ int netdev_txq_to_tc(struct net_device *dev, unsigned int txq)
 		struct netdev_tc_txq *tc = &dev->tc_to_txq[0];
 		int i;
 
+		/* walk through the TCs and see if it falls into any of them */
 		for (i = 0; i < TC_MAX_QUEUE; i++, tc++) {
 			if ((txq - tc->offset) < tc->count)
 				return i;
 		}
 
+		/* didn't find it, just return -1 to indicate no match */
 		return -1;
 	}
 
@@ -2260,7 +2262,14 @@ int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask,
 	unsigned int nr_ids;
 
 	if (dev->num_tc) {
+		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
+		if (num_tc < 0)
+			return -EINVAL;
+
+		/* If queue belongs to subordinate dev use its map */
+		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
 		tc = netdev_txq_to_tc(dev, index);
 		if (tc < 0)
 			return -EINVAL;
@@ -2448,11 +2457,25 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 EXPORT_SYMBOL(netif_set_xps_queue);
 
 #endif
+static void netdev_unbind_all_sb_channels(struct net_device *dev)
+{
+	struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+	/* Unbind any subordinate channels */
+	while (txq-- != &dev->_tx[0]) {
+		if (txq->sb_dev)
+			netdev_unbind_sb_channel(dev, txq->sb_dev);
+	}
+}
+
 void netdev_reset_tc(struct net_device *dev)
 {
 #ifdef CONFIG_XPS
 	netif_reset_xps_queues_gt(dev, 0);
 #endif
+	netdev_unbind_all_sb_channels(dev);
+
+	/* Reset TC configuration of device */
 	dev->num_tc = 0;
 	memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq));
 	memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
@@ -2481,11 +2504,77 @@ int netdev_set_num_tc(struct net_device *dev, u8 num_tc)
 #ifdef CONFIG_XPS
 	netif_reset_xps_queues_gt(dev, 0);
 #endif
+	netdev_unbind_all_sb_channels(dev);
+
 	dev->num_tc = num_tc;
 	return 0;
 }
 EXPORT_SYMBOL(netdev_set_num_tc);
 
+void netdev_unbind_sb_channel(struct net_device *dev,
+			      struct net_device *sb_dev)
+{
+	struct netdev_queue *txq = &dev->_tx[dev->num_tx_queues];
+
+#ifdef CONFIG_XPS
+	netif_reset_xps_queues_gt(sb_dev, 0);
+#endif
+	memset(sb_dev->tc_to_txq, 0, sizeof(sb_dev->tc_to_txq));
+	memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));
+
+	while (txq-- != &dev->_tx[0]) {
+		if (txq->sb_dev == sb_dev)
+			txq->sb_dev = NULL;
+	}
+}
+EXPORT_SYMBOL(netdev_unbind_sb_channel);
+
+int netdev_bind_sb_channel_queue(struct net_device *dev,
+				 struct net_device *sb_dev,
+				 u8 tc, u16 count, u16 offset)
+{
+	/* Make certain the sb_dev and dev are already configured */
+	if (sb_dev->num_tc >= 0 || tc >= dev->num_tc)
+		return -EINVAL;
+
+	/* We cannot hand out queues we don't have */
+	if ((offset + count) > dev->real_num_tx_queues)
+		return -EINVAL;
+
+	/* Record the mapping */
+	sb_dev->tc_to_txq[tc].count = count;
+	sb_dev->tc_to_txq[tc].offset = offset;
+
+	/* Provide a way for Tx queue to find the tc_to_txq map or
+	 * XPS map for itself.
+	 */
+	while (count--)
+		netdev_get_tx_queue(dev, count + offset)->sb_dev = sb_dev;
+
+	return 0;
+}
+EXPORT_SYMBOL(netdev_bind_sb_channel_queue);
+
+int netdev_set_sb_channel(struct net_device *dev, u16 channel)
+{
+	/* Do not use a multiqueue device to represent a subordinate channel */
+	if (netif_is_multiqueue(dev))
+		return -ENODEV;
+
+	/* We allow channels 1 - 32767 to be used for subordinate channels.
+	 * Channel 0 is meant to be "native" mode and used only to represent
+	 * the main root device. We allow writing 0 to reset the device back
+	 * to normal mode after being used as a subordinate channel.
+	 */
+	if (channel > S16_MAX)
+		return -EINVAL;
+
+	dev->num_tc = -channel;
+
+	return 0;
+}
+EXPORT_SYMBOL(netdev_set_sb_channel);
+
 /*
  * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues
  * greater than real_num_tx_queues stale skbs on the qdisc must be flushed.

net/core/net-sysfs.c

@@ -1054,11 +1054,23 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 		return -ENOENT;
 
 	index = get_netdev_queue_index(queue);
+
+	/* If queue belongs to subordinate dev use its TC mapping */
+	dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
 	tc = netdev_txq_to_tc(dev, index);
 	if (tc < 0)
 		return -EINVAL;
 
-	return sprintf(buf, "%u\n", tc);
+	/* We can report the traffic class one of two ways:
+	 * Subordinate device traffic classes are reported with the traffic
+	 * class first, and then the subordinate class so for example TC0 on
+	 * subordinate device 2 will be reported as "0-2". If the queue
+	 * belongs to the root device it will be reported with just the
+	 * traffic class, so just "0" for TC 0 for example.
+	 */
+	return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) :
+				 sprintf(buf, "%u\n", tc);
 }
 
 #ifdef CONFIG_XPS
@@ -1225,7 +1237,14 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	index = get_netdev_queue_index(queue);
 
 	if (dev->num_tc) {
+		/* Do not allow XPS on subordinate device directly */
 		num_tc = dev->num_tc;
+		if (num_tc < 0)
+			return -EINVAL;
+
+		/* If queue belongs to subordinate dev use its map */
+		dev = netdev_get_tx_queue(dev, index)->sb_dev ? : dev;
+
 		tc = netdev_txq_to_tc(dev, index);
 		if (tc < 0)
 			return -EINVAL;