[RFC PATCH 0/4] Add support for DCB and XPS with MACVLAN offload

[RFC PATCH 0/4] Add support for DCB and XPS with MACVLAN offload

[Alexander Duyck]

This patch set is meant to address a number of shortcomings in the current
implementation of MACVLAN offload. The main issue being the fact that the
current Tx queue implementation for ixgbe required the use of
ndo_select_queue which doesn't necessarily play well with DCB or XPS.

I started this patch set to address that and thought I would submit the
start of the series as an RFC just to make sure I am headed in the right
direction and to see if there is anything I am overlooking. With these
patches applied we now start seeing what I am calling "subordinate
channels" which show themselves via a "-x" suffix where the "-x" can be
anything from "-1" to "-32767". So for example traffic class 0 with a
subordinate class of 5 will be called out as "0-5" if you dump the traffic
class via the sysfs value for the queue.

The main pieces that still need to be handled are the updating of the
ndo_select_queue function and the fallback call to allow support for
passing the accel_priv which I am changing to a netdev. I figure those
patches will be mostly noise so I didn't see the need to include them in
this RFC.

---

Alexander Duyck (4):
      net-sysfs: Drop support for XPS and traffic_class on single queue device
      net: Add support for subordinate device traffic classes
      ixgbe: Add code to populate and use macvlan tc to Tx queue map
      net: Add support for subordinate traffic classes to netdev_pick_tx


 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |   55 +++++++---
 drivers/net/macvlan.c                         |   10 --
 include/linux/netdevice.h                     |   20 +++
 net/core/dev.c                                |  144 +++++++++++++++++++++----
 net/core/net-sysfs.c                          |   36 ++++++
 5 files changed, 215 insertions(+), 50 deletions(-)

[RFC PATCH 1/4] net-sysfs: Drop support for XPS and traffic_class on single queue device

[Alexander Duyck]

This patch makes it so that we do not report the traffic class or allow XPS
configuration on single queue devices. This is mostly to avoid unnecessary
complexity with changes I have planned that will allow us to reuse
the unused tc_to_txq and XPS configuration on a single queue device to
allow it to make use of a subset of queues on an underlying device.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
 net/core/net-sysfs.c |   15 +++++++++++++--
 1 file changed, 13 insertions(+), 2 deletions(-)

diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index bb7e80f..335c6a4 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1047,9 +1047,14 @@ static ssize_t traffic_class_show(struct netdev_queue *queue,
 				  char *buf)
 {
 	struct net_device *dev = queue->dev;
-	int index = get_netdev_queue_index(queue);
-	int tc = netdev_txq_to_tc(dev, index);
+	int index;
+	int tc;
 
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
+
+	index = get_netdev_queue_index(queue);
+	tc = netdev_txq_to_tc(dev, index);
 	if (tc < 0)
 		return -EINVAL;
 
@@ -1214,6 +1219,9 @@ static ssize_t xps_cpus_show(struct netdev_queue *queue,
 	cpumask_var_t mask;
 	unsigned long index;
 
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
+
 	index = get_netdev_queue_index(queue);
 
 	if (dev->num_tc) {
@@ -1260,6 +1268,9 @@ static ssize_t xps_cpus_store(struct netdev_queue *queue,
 	cpumask_var_t mask;
 	int err;
 
+	if (!netif_is_multiqueue(dev))
+		return -ENOENT;
+
 	if (!capable(CAP_NET_ADMIN))
 		return -EPERM;
 

[RFC PATCH 2/4] net: Add support for subordinate device traffic classes

[Alexander Duyck]

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 suboordinate
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>
---
 include/linux/netdevice.h |   16 ++++++++
 net/core/dev.c            |   89 +++++++++++++++++++++++++++++++++++++++++++++
 net/core/net-sysfs.c      |   21 ++++++++++-
 3 files changed, 124 insertions(+), 2 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 03ed492..bbc8045 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -569,6 +569,9 @@ struct netdev_queue {
 	 * (/sys/class/net/DEV/Q/trans_timeout)
 	 */
 	unsigned long		trans_timeout;
+
+	/* Suboordinate device that the queue has been assigned to */
+	struct net_device	*sb_dev;
 /*
  * write-mostly part
  */
@@ -1960,7 +1963,7 @@ 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];
 
@@ -2014,6 +2017,17 @@ 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)
diff --git a/net/core/dev.c b/net/core/dev.c
index 034c2a9..eba255d 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2068,11 +2068,13 @@ 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;
 	}
 
@@ -2215,7 +2217,14 @@ int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask,
 	bool active = false;
 
 	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;
@@ -2366,11 +2375,25 @@ 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));
@@ -2399,11 +2422,77 @@ 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.
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 335c6a4..bd067b1 100644
--- a/net/core/net-sysfs.c
+++ b/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;

[RFC PATCH 3/4] ixgbe: Add code to populate and use macvlan tc to Tx queue map

[Alexander Duyck]

This patch makes it so that we use the tc_to_txq mapping in the macvlan
device in order to select the Tx queue for outgoing packets.

The idea here is to try and move away from using ixgbe_select_queue and to
come up with a generic way to make this work for devices going forward. By
encoding this information in the netdev this can become something that can
be used generically as a solution for similar setups going forward.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |   44 ++++++++++++++++++++++---
 1 file changed, 38 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index f460c16..05d6d48 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -5271,6 +5271,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring)
 static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 			     struct ixgbe_fwd_adapter *accel)
 {
+	u16 rss_i = adapter->ring_feature[RING_F_RSS].indices;
+	int num_tc = netdev_get_num_tc(adapter->netdev);
 	struct net_device *vdev = accel->netdev;
 	int i, baseq, err;
 
@@ -5282,6 +5284,11 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 	accel->rx_base_queue = baseq;
 	accel->tx_base_queue = baseq;
 
+	/* record configuration for macvlan interface in vdev */
+	for (i = 0; i < num_tc; i++)
+		netdev_bind_sb_channel_queue(adapter->netdev, vdev,
+					     i, rss_i, baseq + (rss_i * i));
+
 	for (i = 0; i < adapter->num_rx_queues_per_pool; i++)
 		adapter->rx_ring[baseq + i]->netdev = vdev;
 
@@ -5306,6 +5313,10 @@ static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter,
 
 	netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n");
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 
@@ -8211,18 +8222,22 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			      void *accel_priv, select_queue_fallback_t fallback)
 {
 	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
-	struct ixgbe_adapter *adapter;
-	int txq;
 #ifdef IXGBE_FCOE
+	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
 #endif
+	int txq;
 
 	if (fwd_adapter) {
-		adapter = netdev_priv(dev);
-		txq = reciprocal_scale(skb_get_hash(skb),
-				       adapter->num_rx_queues_per_pool);
+		u8 tc = netdev_get_num_tc(dev) ?
+			netdev_get_prio_tc_map(dev, skb->priority) : 0;
+		struct net_device *vdev = fwd_adapter->netdev;
+
+		txq = vdev->tc_to_txq[tc].offset;
+		txq += reciprocal_scale(skb_get_hash(skb),
+					vdev->tc_to_txq[tc].count);
 
-		return txq + fwd_adapter->tx_base_queue;
+		return txq;
 	}
 
 #ifdef IXGBE_FCOE
@@ -8776,6 +8791,11 @@ static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data)
 	/* if we cannot find a free pool then disable the offload */
 	netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n");
 	macvlan_release_l2fw_offload(vdev);
+
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(adapter->netdev, vdev);
+	netdev_set_sb_channel(vdev, 0);
+
 	kfree(accel);
 
 	return 0;
@@ -9780,6 +9800,13 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 	if (!macvlan_supports_dest_filter(vdev))
 		return ERR_PTR(-EMEDIUMTYPE);
 
+	/* We need to lock down the macvlan to be a single queue device so that
+	 * we can reuse the tc_to_txq field in the macvlan netdev to represent
+	 * the queue mapping to our netdev.
+	 */
+	if (netif_is_multiqueue(vdev))
+		return ERR_PTR(-ERANGE);
+
 	pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools);
 	if (pool == adapter->num_rx_pools) {
 		u16 used_pools = adapter->num_vfs + adapter->num_rx_pools;
@@ -9836,6 +9863,7 @@ static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev)
 		return ERR_PTR(-ENOMEM);
 
 	set_bit(pool, adapter->fwd_bitmask);
+	netdev_set_sb_channel(vdev, pool);
 	accel->pool = pool;
 	accel->netdev = vdev;
 
@@ -9877,6 +9905,10 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv)
 		ring->netdev = NULL;
 	}
 
+	/* unbind the queues and drop the subordinate channel config */
+	netdev_unbind_sb_channel(pdev, accel->netdev);
+	netdev_set_sb_channel(accel->netdev, 0);
+
 	clear_bit(accel->pool, adapter->fwd_bitmask);
 	kfree(accel);
 }

[RFC PATCH 4/4] net: Add support for subordinate traffic classes to netdev_pick_tx

[Alexander Duyck]

This change makes it so that we can support the concept of subordinate
device traffic classes to the core networking code. In doing this we can
start pulling out the driver specific bits needed to support selecting a
queue based on an upper device.

The solution at is currently stands is only partially implemented. I have
the start of some XPS bits in here, but I would still need to allow for
configuration of the XPS maps on the queues reserved for the subordinate
devices. For now I am using the reference to the sb_dev XPS map as just a
way to skip the lookup of the lower device XPS map for now as that would
result in the wrong queue being picked.

Signed-off-by: Alexander Duyck <alexander.h.duyck@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/ixgbe_main.c |   15 ++-----
 drivers/net/macvlan.c                         |   10 +----
 include/linux/netdevice.h                     |    4 +-
 net/core/dev.c                                |   55 +++++++++++++++----------
 4 files changed, 42 insertions(+), 42 deletions(-)

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 05d6d48..c42498d 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -8218,20 +8218,18 @@ static void ixgbe_atr(struct ixgbe_ring *ring,
 					      input, common, ring->queue_index);
 }
 
+#ifdef IXGBE_FCOE
 static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 			      void *accel_priv, select_queue_fallback_t fallback)
 {
-	struct ixgbe_fwd_adapter *fwd_adapter = accel_priv;
-#ifdef IXGBE_FCOE
 	struct ixgbe_adapter *adapter;
 	struct ixgbe_ring_feature *f;
-#endif
 	int txq;
 
-	if (fwd_adapter) {
+	if (accel_priv) {
 		u8 tc = netdev_get_num_tc(dev) ?
 			netdev_get_prio_tc_map(dev, skb->priority) : 0;
-		struct net_device *vdev = fwd_adapter->netdev;
+		struct net_device *vdev = accel_priv;
 
 		txq = vdev->tc_to_txq[tc].offset;
 		txq += reciprocal_scale(skb_get_hash(skb),
@@ -8240,7 +8238,6 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		return txq;
 	}
 
-#ifdef IXGBE_FCOE
 
 	/*
 	 * only execute the code below if protocol is FCoE
@@ -8267,11 +8264,9 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb,
 		txq -= f->indices;
 
 	return txq + f->offset;
-#else
-	return fallback(dev, skb);
-#endif
 }
 
+#endif
 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter,
 			       struct xdp_frame *xdpf)
 {
@@ -10071,7 +10066,6 @@ static void ixgbe_xdp_flush(struct net_device *dev)
 	.ndo_open		= ixgbe_open,
 	.ndo_stop		= ixgbe_close,
 	.ndo_start_xmit		= ixgbe_xmit_frame,
-	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_set_rx_mode	= ixgbe_set_rx_mode,
 	.ndo_validate_addr	= eth_validate_addr,
 	.ndo_set_mac_address	= ixgbe_set_mac,
@@ -10094,6 +10088,7 @@ static void ixgbe_xdp_flush(struct net_device *dev)
 	.ndo_poll_controller	= ixgbe_netpoll,
 #endif
 #ifdef IXGBE_FCOE
+	.ndo_select_queue	= ixgbe_select_queue,
 	.ndo_fcoe_ddp_setup = ixgbe_fcoe_ddp_get,
 	.ndo_fcoe_ddp_target = ixgbe_fcoe_ddp_target,
 	.ndo_fcoe_ddp_done = ixgbe_fcoe_ddp_put,
diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index adde8fc..401e1d1 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -514,7 +514,6 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 	const struct macvlan_dev *vlan = netdev_priv(dev);
 	const struct macvlan_port *port = vlan->port;
 	const struct macvlan_dev *dest;
-	void *accel_priv = NULL;
 
 	if (vlan->mode == MACVLAN_MODE_BRIDGE) {
 		const struct ethhdr *eth = (void *)skb->data;
@@ -533,15 +532,10 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev)
 			return NET_XMIT_SUCCESS;
 		}
 	}
-
-	/* For packets that are non-multicast and not bridged we will pass
-	 * the necessary information so that the lowerdev can distinguish
-	 * the source of the packets via the accel_priv value.
-	 */
-	accel_priv = vlan->accel_priv;
 xmit_world:
 	skb->dev = vlan->lowerdev;
-	return dev_queue_xmit_accel(skb, accel_priv);
+	return dev_queue_xmit_accel(skb,
+				    netdev_get_sb_channel(dev) ? dev : NULL);
 }
 
 static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bbc8045..df5a582 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2072,7 +2072,7 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev,
 
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
-				    void *accel_priv);
+				    struct net_device *sb_dev);
 
 /* returns the headroom that the master device needs to take in account
  * when forwarding to this dev
@@ -2523,7 +2523,7 @@ struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
 int dev_queue_xmit(struct sk_buff *skb);
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv);
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev);
 int dev_direct_xmit(struct sk_buff *skb, u16 queue_id);
 int register_netdevice(struct net_device *dev);
 void unregister_netdevice_queue(struct net_device *dev, struct list_head *head);
diff --git a/net/core/dev.c b/net/core/dev.c
index eba255d..507e606 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2704,24 +2704,26 @@ void netif_device_attach(struct net_device *dev)
  * Returns a Tx hash based on the given packet descriptor a Tx queues' number
  * to be used as a distribution range.
  */
-static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb)
+static u16 skb_tx_hash(const struct net_device *dev,
+		       const struct net_device *sb_dev,
+		       struct sk_buff *skb)
 {
 	u32 hash;
 	u16 qoffset = 0;
 	u16 qcount = dev->real_num_tx_queues;
 
+	if (dev->num_tc) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+
+		qoffset = sb_dev->tc_to_txq[tc].offset;
+		qcount = sb_dev->tc_to_txq[tc].count;
+	}
+
 	if (skb_rx_queue_recorded(skb)) {
 		hash = skb_get_rx_queue(skb);
 		while (unlikely(hash >= qcount))
 			hash -= qcount;
-		return hash;
-	}
-
-	if (dev->num_tc) {
-		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
-
-		qoffset = dev->tc_to_txq[tc].offset;
-		qcount = dev->tc_to_txq[tc].count;
+		return hash + qoffset;
 	}
 
 	return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
@@ -3483,7 +3485,9 @@ int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *skb)
 }
 #endif /* CONFIG_NET_EGRESS */
 
-static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+static inline int get_xps_queue(struct net_device *dev,
+				struct net_device *sb_dev,
+				struct sk_buff *skb)
 {
 #ifdef CONFIG_XPS
 	struct xps_dev_maps *dev_maps;
@@ -3491,7 +3495,7 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 	int queue_index = -1;
 
 	rcu_read_lock();
-	dev_maps = rcu_dereference(dev->xps_maps);
+	dev_maps = rcu_dereference(sb_dev->xps_maps);
 	if (dev_maps) {
 		unsigned int tci = skb->sender_cpu - 1;
 
@@ -3519,17 +3523,18 @@ static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
 #endif
 }
 
-static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+static u16 ___netdev_pick_tx(struct net_device *dev, struct sk_buff *skb,
+			     struct net_device *sb_dev)
 {
 	struct sock *sk = skb->sk;
 	int queue_index = sk_tx_queue_get(sk);
 
 	if (queue_index < 0 || skb->ooo_okay ||
 	    queue_index >= dev->real_num_tx_queues) {
-		int new_index = get_xps_queue(dev, skb);
+		int new_index = get_xps_queue(dev, sb_dev, skb);
 
 		if (new_index < 0)
-			new_index = skb_tx_hash(dev, skb);
+			new_index = skb_tx_hash(dev, sb_dev, skb);
 
 		if (queue_index != new_index && sk &&
 		    sk_fullsock(sk) &&
@@ -3542,9 +3547,14 @@ static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
 	return queue_index;
 }
 
+static u16 __netdev_pick_tx(struct net_device *dev,
+			    struct sk_buff *skb)
+{
+	return ___netdev_pick_tx(dev, skb, NULL);
+}
 struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 				    struct sk_buff *skb,
-				    void *accel_priv)
+				    struct net_device *sb_dev)
 {
 	int queue_index = 0;
 
@@ -3559,10 +3569,11 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 		const struct net_device_ops *ops = dev->netdev_ops;
 
 		if (ops->ndo_select_queue)
-			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+			queue_index = ops->ndo_select_queue(dev, skb, sb_dev,
 							    __netdev_pick_tx);
 		else
-			queue_index = __netdev_pick_tx(dev, skb);
+			queue_index = ___netdev_pick_tx(dev, skb,
+							sb_dev ? : dev);
 
 		queue_index = netdev_cap_txqueue(dev, queue_index);
 	}
@@ -3574,7 +3585,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
 /**
  *	__dev_queue_xmit - transmit a buffer
  *	@skb: buffer to transmit
- *	@accel_priv: private data used for L2 forwarding offload
+ *	@sb_dev: suboordinate device used for L2 forwarding offload
  *
  *	Queue a buffer for transmission to a network device. The caller must
  *	have set the device and priority and built the buffer before calling
@@ -3597,7 +3608,7 @@ struct netdev_queue *netdev_pick_tx(struct net_device *dev,
  *      the BH enable code must have IRQs enabled so that it will not deadlock.
  *          --BLG
  */
-static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
+static int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev)
 {
 	struct net_device *dev = skb->dev;
 	struct netdev_queue *txq;
@@ -3636,7 +3647,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv)
 	else
 		skb_dst_force(skb);
 
-	txq = netdev_pick_tx(dev, skb, accel_priv);
+	txq = netdev_pick_tx(dev, skb, sb_dev);
 	q = rcu_dereference_bh(txq->qdisc);
 
 	trace_net_dev_queue(skb);
@@ -3710,9 +3721,9 @@ int dev_queue_xmit(struct sk_buff *skb)
 }
 EXPORT_SYMBOL(dev_queue_xmit);
 
-int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv)
+int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev)
 {
-	return __dev_queue_xmit(skb, accel_priv);
+	return __dev_queue_xmit(skb, sb_dev);
 }
 EXPORT_SYMBOL(dev_queue_xmit_accel);