net/sched: cls_flower: Add offload support using egress Hardware device

In order to support hardware offloading when the device given by the tc
rule is different from the Hardware underline device, extract the mirred
(egress) device from the tc action when a filter is added, using the new
tc_action_ops, get_dev().

Flower caches the information about the mirred device and use it for
calling ndo_setup_tc in filter change, update stats and delete.

Calling ndo_setup_tc of the mirred (egress) device instead of the
ingress device will allow a resolution between the software ingress
device and the underline hardware device.

The resolution will take place inside the offloading driver using
'egress_device' flag added to tc_to_netdev struct which is provided to
the offloading driver.

Signed-off-by: Hadar Hen Zion <hadarh@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/linux/netdevice.h

@@ -802,6 +802,7 @@ struct tc_to_netdev {
 		struct tc_cls_matchall_offload *cls_mall;
 		struct tc_cls_bpf_offload *cls_bpf;
 	};
+	bool egress_dev;
 };
 
 /* These structures hold the attributes of xdp state that are being passed

include/net/pkt_cls.h

@@ -171,6 +171,8 @@ void tcf_exts_change(struct tcf_proto *tp, struct tcf_exts *dst,
 		     struct tcf_exts *src);
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts);
 int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts);
+int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
+		     struct net_device **hw_dev);
 
 /**
  * struct tcf_pkt_info - packet information

net/sched/cls_api.c

@@ -682,6 +682,30 @@ int tcf_exts_dump_stats(struct sk_buff *skb, struct tcf_exts *exts)
 }
 EXPORT_SYMBOL(tcf_exts_dump_stats);
 
+int tcf_exts_get_dev(struct net_device *dev, struct tcf_exts *exts,
+		     struct net_device **hw_dev)
+{
+#ifdef CONFIG_NET_CLS_ACT
+	const struct tc_action *a;
+	LIST_HEAD(actions);
+
+	if (tc_no_actions(exts))
+		return -EINVAL;
+
+	tcf_exts_to_list(exts, &actions);
+	list_for_each_entry(a, &actions, list) {
+		if (a->ops->get_dev) {
+			a->ops->get_dev(a, dev_net(dev), hw_dev);
+			break;
+		}
+	}
+	if (*hw_dev)
+		return 0;
+#endif
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(tcf_exts_get_dev);
+
 static int __init tc_filter_init(void)
 {
 	rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_ctl_tfilter, NULL, NULL);

net/sched/cls_flower.c

@@ -78,6 +78,8 @@ struct cls_fl_filter {
 	u32 handle;
 	u32 flags;
 	struct rcu_head	rcu;
+	struct tc_to_netdev tc;
+	struct net_device *hw_dev;
 };
 
 static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
@@ -203,9 +205,9 @@ static void fl_destroy_filter(struct rcu_head *head)
 
 static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload offload = {0};
-	struct tc_to_netdev tc;
+	struct net_device *dev = f->hw_dev;
+	struct tc_to_netdev *tc = &f->tc;
 
 	if (!tc_can_offload(dev, tp))
 		return;
@@ -213,10 +215,10 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f)
 	offload.command = TC_CLSFLOWER_DESTROY;
 	offload.cookie = (unsigned long)f;
 
-	tc.type = TC_SETUP_CLSFLOWER;
+	tc->type = TC_SETUP_CLSFLOWER;
-	tc.cls_flower = &offload;
+	tc->cls_flower = &offload;
 
-	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc);
 }
 
 static int fl_hw_replace_filter(struct tcf_proto *tp,
@@ -226,11 +228,17 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 {
 	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload offload = {0};
-	struct tc_to_netdev tc;
+	struct tc_to_netdev *tc = &f->tc;
 	int err;
 
-	if (!tc_can_offload(dev, tp))
+	if (!tc_can_offload(dev, tp)) {
-		return tc_skip_sw(f->flags) ? -EINVAL : 0;
+		if (tcf_exts_get_dev(dev, &f->exts, &f->hw_dev))
+			return tc_skip_sw(f->flags) ? -EINVAL : 0;
+		dev = f->hw_dev;
+		tc->egress_dev = true;
+	} else {
+		f->hw_dev = dev;
+	}
 
 	offload.command = TC_CLSFLOWER_REPLACE;
 	offload.cookie = (unsigned long)f;
@@ -239,23 +247,22 @@ static int fl_hw_replace_filter(struct tcf_proto *tp,
 	offload.key = &f->key;
 	offload.exts = &f->exts;
 
-	tc.type = TC_SETUP_CLSFLOWER;
+	tc->type = TC_SETUP_CLSFLOWER;
-	tc.cls_flower = &offload;
+	tc->cls_flower = &offload;
 
 	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
-					    &tc);
+					    tc);
 
 	if (tc_skip_sw(f->flags))
 		return err;
-
 	return 0;
 }
 
 static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 {
-	struct net_device *dev = tp->q->dev_queue->dev;
 	struct tc_cls_flower_offload offload = {0};
-	struct tc_to_netdev tc;
+	struct net_device *dev = f->hw_dev;
+	struct tc_to_netdev *tc = &f->tc;
 
 	if (!tc_can_offload(dev, tp))
 		return;
@@ -264,10 +271,10 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 	offload.cookie = (unsigned long)f;
 	offload.exts = &f->exts;
 
-	tc.type = TC_SETUP_CLSFLOWER;
+	tc->type = TC_SETUP_CLSFLOWER;
-	tc.cls_flower = &offload;
+	tc->cls_flower = &offload;
 
-	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, &tc);
+	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol, tc);
 }
 
 static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f)