[PATCH v2 06/14] vlan: Centralize handling of hardware acceleration.

[Jesse Gross <jesse@nicira.com>]

Currently each driver that is capable of vlan hardware acceleration
must be aware of the vlan groups that are configured and then pass
the stripped tag to a specialized receive function.  This is
different from other types of hardware offload in that it places a
significant amount of knowledge in the driver itself rather keeping
it in the networking core.

This makes vlan offloading function more similarly to other forms
of offloading (such as checksum offloading or TSO) by doing the
following:
* On receive, stripped vlans are passed directly to the network
core, without attempting to check for vlan groups or reconstructing
the header if no group
* vlans are made less special by folding the logic into the main
receive routines
* On transmit, the device layer will add the vlan header in software
if the hardware doesn't support it, instead of spreading that logic
out in upper layers, such as bonding.

There are a number of advantages to this:
* Fixes all bugs with drivers incorrectly dropping vlan headers at once.
* Avoids having to disable VLAN acceleration when in promiscuous mode
(good for bridging since it always puts devices in promiscuous mode).
* Keeps VLAN tag separate until given to ultimate consumer, which
avoids needing to do header reconstruction as in tg3 unless absolutely
necessary.
* Consolidates common code in core networking.

Signed-off-by: Jesse Gross <jesse@nicira.com>
---
 include/linux/if_vlan.h   |    6 ++-
 include/linux/netdevice.h |    1 -
 net/8021q/vlan.c          |    9 +---
 net/8021q/vlan_core.c     |  125 ++++++++++-----------------------------------
 net/core/dev.c            |   47 +++++------------
 5 files changed, 48 insertions(+), 140 deletions(-)

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 4047781..a0d9786 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -132,7 +132,7 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev);
 
 extern int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
 			     u16 vlan_tci, int polling);
-extern void vlan_hwaccel_do_receive(struct sk_buff *skb);
+extern bool vlan_hwaccel_do_receive(struct sk_buff **skb);
 extern gro_result_t
 vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
 		 unsigned int vlan_tci, struct sk_buff *skb);
@@ -166,8 +166,10 @@ static inline int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
 	return NET_XMIT_SUCCESS;
 }
 
-static inline void vlan_hwaccel_do_receive(struct sk_buff *skb)
+static inline bool vlan_hwaccel_do_receive(struct sk_buff **skb)
 {
+	BUG();
+	return false;
 }
 
 static inline gro_result_t
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9c78312..ed7db7e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1768,7 +1768,6 @@ extern int netdev_rx_handler_register(struct net_device *dev,
 				      void *rx_handler_data);
 extern void netdev_rx_handler_unregister(struct net_device *dev);
 
-extern void		netif_nit_deliver(struct sk_buff *skb);
 extern int		dev_valid_name(const char *name);
 extern int		dev_ioctl(struct net *net, unsigned int cmd, void __user *);
 extern int		dev_ethtool(struct net *net, struct ifreq *);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index f862dcc..05b867e 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -135,7 +135,7 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head)
 		vlan_gvrp_uninit_applicant(real_dev);
 
 		rcu_assign_pointer(real_dev->vlgrp, NULL);
-		if (real_dev->features & NETIF_F_HW_VLAN_RX)
+		if (ops->ndo_vlan_rx_register)
 			ops->ndo_vlan_rx_register(real_dev, NULL);
 
 		/* Free the group, after all cpu's are done. */
@@ -156,11 +156,6 @@ int vlan_check_real_dev(struct net_device *real_dev, u16 vlan_id)
 		return -EOPNOTSUPP;
 	}
 
-	if ((real_dev->features & NETIF_F_HW_VLAN_RX) && !ops->ndo_vlan_rx_register) {
-		pr_info("8021q: device %s has buggy VLAN hw accel\n", name);
-		return -EOPNOTSUPP;
-	}
-
 	if ((real_dev->features & NETIF_F_HW_VLAN_FILTER) &&
 	    (!ops->ndo_vlan_rx_add_vid || !ops->ndo_vlan_rx_kill_vid)) {
 		pr_info("8021q: Device %s has buggy VLAN hw accel\n", name);
@@ -213,7 +208,7 @@ int register_vlan_dev(struct net_device *dev)
 	grp->nr_vlans++;
 
 	if (ngrp) {
-		if (real_dev->features & NETIF_F_HW_VLAN_RX)
+		if (ops->ndo_vlan_rx_register)
 			ops->ndo_vlan_rx_register(real_dev, ngrp);
 		rcu_assign_pointer(real_dev->vlgrp, ngrp);
 	}
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index dee727c..69b2f79 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -4,54 +4,29 @@
 #include <linux/netpoll.h>
 #include "vlan.h"
 
-/* VLAN rx hw acceleration helper.  This acts like netif_{rx,receive_skb}(). */
-int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
-		      u16 vlan_tci, int polling)
+bool vlan_hwaccel_do_receive(struct sk_buff **skbp)
 {
+	struct sk_buff *skb = *skbp;
+	u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK;
 	struct net_device *vlan_dev;
-	u16 vlan_id;
-
-	if (netpoll_rx(skb))
-		return NET_RX_DROP;
-
-	if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master)))
-		skb->deliver_no_wcard = 1;
+	struct vlan_rx_stats *rx_stats;
 
-	skb->skb_iif = skb->dev->ifindex;
-	__vlan_hwaccel_put_tag(skb, vlan_tci);
-	vlan_id = vlan_tci & VLAN_VID_MASK;
-	vlan_dev = vlan_group_get_device(grp, vlan_id);
-
-	if (vlan_dev)
-		skb->dev = vlan_dev;
-	else if (vlan_id) {
-		if (!(skb->dev->flags & IFF_PROMISC))
-			goto drop;
-		skb->pkt_type = PACKET_OTHERHOST;
+	vlan_dev = vlan_find_dev(skb->dev, vlan_id);
+	if (!vlan_dev) {
+		if (vlan_id)
+			skb->pkt_type = PACKET_OTHERHOST;
+		return false;
 	}
 
-	return polling ? netif_receive_skb(skb) : netif_rx(skb);
+	skb = *skbp = skb_share_check(skb, GFP_ATOMIC);
+	if (unlikely(!skb))
+		return false;
 
-drop:
-	atomic_long_inc(&skb->dev->rx_dropped);
-	dev_kfree_skb_any(skb);
-	return NET_RX_DROP;
-}
-EXPORT_SYMBOL(__vlan_hwaccel_rx);
-
-void vlan_hwaccel_do_receive(struct sk_buff *skb)
-{
-	struct net_device *dev = skb->dev;
-	struct vlan_rx_stats     *rx_stats;
-
-	skb->dev = vlan_dev_real_dev(dev);
-	netif_nit_deliver(skb);
-
-	skb->dev = dev;
-	skb->priority = vlan_get_ingress_priority(dev, skb->vlan_tci);
+	skb->dev = vlan_dev;
+	skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci);
 	skb->vlan_tci = 0;
 
-	rx_stats = this_cpu_ptr(vlan_dev_info(dev)->vlan_rx_stats);
+	rx_stats = this_cpu_ptr(vlan_dev_info(vlan_dev)->vlan_rx_stats);
 
 	u64_stats_update_begin(&rx_stats->syncp);
 	rx_stats->rx_packets++;
@@ -68,11 +43,13 @@ void vlan_hwaccel_do_receive(struct sk_buff *skb)
 		 * This allows the VLAN to have a different MAC than the
 		 * underlying device, and still route correctly. */
 		if (!compare_ether_addr(eth_hdr(skb)->h_dest,
-					dev->dev_addr))
+					vlan_dev->dev_addr))
 			skb->pkt_type = PACKET_HOST;
 		break;
 	}
 	u64_stats_update_end(&rx_stats->syncp);
+
+	return true;
 }
 
 struct net_device *vlan_dev_real_dev(const struct net_device *dev)
@@ -87,75 +64,27 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
 }
 EXPORT_SYMBOL(vlan_dev_vlan_id);
 
-static gro_result_t
-vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
-		unsigned int vlan_tci, struct sk_buff *skb)
+/* VLAN rx hw acceleration helper.  This acts like netif_{rx,receive_skb}(). */
+int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
+		      u16 vlan_tci, int polling)
 {
-	struct sk_buff *p;
-	struct net_device *vlan_dev;
-	u16 vlan_id;
-
-	if (skb_bond_should_drop(skb, ACCESS_ONCE(skb->dev->master)))
-		skb->deliver_no_wcard = 1;
-
-	skb->skb_iif = skb->dev->ifindex;
 	__vlan_hwaccel_put_tag(skb, vlan_tci);
-	vlan_id = vlan_tci & VLAN_VID_MASK;
-	vlan_dev = vlan_group_get_device(grp, vlan_id);
-
-	if (vlan_dev)
-		skb->dev = vlan_dev;
-	else if (vlan_id) {
-		if (!(skb->dev->flags & IFF_PROMISC))
-			goto drop;
-		skb->pkt_type = PACKET_OTHERHOST;
-	}
-
-	for (p = napi->gro_list; p; p = p->next) {
-		unsigned long diffs;
-
-		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
-		diffs |= compare_ether_header(skb_mac_header(p),
-					      skb_gro_mac_header(skb));
-		NAPI_GRO_CB(p)->same_flow = !diffs;
-		NAPI_GRO_CB(p)->flush = 0;
-	}
-
-	return dev_gro_receive(napi, skb);
-
-drop:
-	atomic_long_inc(&skb->dev->rx_dropped);
-	return GRO_DROP;
+	return polling ? netif_receive_skb(skb) : netif_rx(skb);
 }
+EXPORT_SYMBOL(__vlan_hwaccel_rx);
 
 gro_result_t vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
 			      unsigned int vlan_tci, struct sk_buff *skb)
 {
-	if (netpoll_rx_on(skb))
-		return vlan_hwaccel_receive_skb(skb, grp, vlan_tci)
-			? GRO_DROP : GRO_NORMAL;
-
-	skb_gro_reset_offset(skb);
-
-	return napi_skb_finish(vlan_gro_common(napi, grp, vlan_tci, skb), skb);
+	__vlan_hwaccel_put_tag(skb, vlan_tci);
+	return napi_gro_receive(napi, skb);
 }
 EXPORT_SYMBOL(vlan_gro_receive);
 
 gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
 			    unsigned int vlan_tci)
 {
-	struct sk_buff *skb = napi_frags_skb(napi);
-
-	if (!skb)
-		return GRO_DROP;
-
-	if (netpoll_rx_on(skb)) {
-		skb->protocol = eth_type_trans(skb, skb->dev);
-		return vlan_hwaccel_receive_skb(skb, grp, vlan_tci)
-			? GRO_DROP : GRO_NORMAL;
-	}
-
-	return napi_frags_finish(napi, skb,
-				 vlan_gro_common(napi, grp, vlan_tci, skb));
+	__vlan_hwaccel_put_tag(napi->skb, vlan_tci);
+	return napi_gro_frags(napi);
 }
 EXPORT_SYMBOL(vlan_gro_frags);
diff --git a/net/core/dev.c b/net/core/dev.c
index 1bfd96b..97fd6bc 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2789,33 +2789,6 @@ out:
 }
 #endif
 
-/*
- * 	netif_nit_deliver - deliver received packets to network taps
- * 	@skb: buffer
- *
- * 	This function is used to deliver incoming packets to network
- * 	taps. It should be used when the normal netif_receive_skb path
- * 	is bypassed, for example because of VLAN acceleration.
- */
-void netif_nit_deliver(struct sk_buff *skb)
-{
-	struct packet_type *ptype;
-
-	if (list_empty(&ptype_all))
-		return;
-
-	skb_reset_network_header(skb);
-	skb_reset_transport_header(skb);
-	skb->mac_len = skb->network_header - skb->mac_header;
-
-	rcu_read_lock();
-	list_for_each_entry_rcu(ptype, &ptype_all, list) {
-		if (!ptype->dev || ptype->dev == skb->dev)
-			deliver_skb(skb, ptype, skb->dev);
-	}
-	rcu_read_unlock();
-}
-
 /**
  *	netdev_rx_handler_register - register receive handler
  *	@dev: device to register a handler for
@@ -2925,9 +2898,6 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	if (!netdev_tstamp_prequeue)
 		net_timestamp_check(skb);
 
-	if (vlan_tx_tag_present(skb))
-		vlan_hwaccel_do_receive(skb);
-
 	/* if we've gotten here through NAPI, check netpoll */
 	if (netpoll_receive_skb(skb))
 		return NET_RX_DROP;
@@ -2940,8 +2910,7 @@ static int __netif_receive_skb(struct sk_buff *skb)
 	 * be delivered to pkt handlers that are exact matches.  Also
 	 * the deliver_no_wcard flag will be set.  If packet handlers
 	 * are sensitive to duplicate packets these skbs will need to
-	 * be dropped at the handler.  The vlan accel path may have
-	 * already set the deliver_no_wcard flag.
+	 * be dropped at the handler.
 	 */
 	null_or_orig = NULL;
 	orig_dev = skb->dev;
@@ -3000,6 +2969,18 @@ ncls:
 			goto out;
 	}
 
+	if (vlan_tx_tag_present(skb)) {
+		if (pt_prev) {
+			ret = deliver_skb(skb, pt_prev, orig_dev);
+			pt_prev = NULL;
+		}
+		if (vlan_hwaccel_do_receive(&skb)) {
+			ret = __netif_receive_skb(skb);
+			goto out;
+		} else if (unlikely(!skb))
+			goto out;
+	}
+
 	/*
 	 * Make sure frames received on VLAN interfaces stacked on
 	 * bonding interfaces still make their way to any base bonding
@@ -3264,6 +3245,7 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 		unsigned long diffs;
 
 		diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev;
+		diffs |= p->vlan_tci ^ skb->vlan_tci;
 		diffs |= compare_ether_header(skb_mac_header(p),
 					      skb_gro_mac_header(skb));
 		NAPI_GRO_CB(p)->same_flow = !diffs;
@@ -3323,6 +3305,7 @@ void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb)
 {
 	__skb_pull(skb, skb_headlen(skb));
 	skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb));
+	skb->vlan_tci = 0;
 
 	napi->skb = skb;
 }
-- 
1.7.1