bpf: Add redirect_peer helper

Add an efficient ingress to ingress netns switch that can be used out of tc BPF
programs in order to redirect traffic from host ns ingress into a container
veth device ingress without having to go via CPU backlog queue [0]. For local
containers this can also be utilized and path via CPU backlog queue only needs
to be taken once, not twice. On a high level this borrows from ipvlan which does
similar switch in __netif_receive_skb_core() and then iterates via another_round.
This helps to reduce latency for mentioned use cases.

Pod to remote pod with redirect(), TCP_RR [1]:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:         122.450         (per CPU:         122.666         122.401         122.333         122.401 )
        MEAN_LATENCY:         121.210         (per CPU:         121.100         121.260         121.320         121.160 )
      STDDEV_LATENCY:         120.040         (per CPU:         119.420         119.910         125.460         115.370 )
         MIN_LATENCY:          46.500         (per CPU:          47.000          47.000          47.000          45.000 )
         P50_LATENCY:         118.500         (per CPU:         118.000         119.000         118.000         119.000 )
         P90_LATENCY:         127.500         (per CPU:         127.000         128.000         127.000         128.000 )
         P99_LATENCY:         130.750         (per CPU:         131.000         131.000         129.000         132.000 )

    TRANSACTION_RATE:       32666.400         (per CPU:        8152.200        8169.842        8174.439        8169.897 )

Pod to remote pod with redirect_peer(), TCP_RR:

  # percpu_netperf 10.217.1.33
          RT_LATENCY:          44.449         (per CPU:          43.767          43.127          45.279          45.622 )
        MEAN_LATENCY:          45.065         (per CPU:          44.030          45.530          45.190          45.510 )
      STDDEV_LATENCY:          84.823         (per CPU:          66.770          97.290          84.380          90.850 )
         MIN_LATENCY:          33.500         (per CPU:          33.000          33.000          34.000          34.000 )
         P50_LATENCY:          43.250         (per CPU:          43.000          43.000          43.000          44.000 )
         P90_LATENCY:          46.750         (per CPU:          46.000          47.000          47.000          47.000 )
         P99_LATENCY:          52.750         (per CPU:          51.000          54.000          53.000          53.000 )

    TRANSACTION_RATE:       90039.500         (per CPU:       22848.186       23187.089       22085.077       21919.130 )

  [0] https://linuxplumbersconf.org/event/7/contributions/674/attachments/568/1002/plumbers_2020_cilium_load_balancer.pdf
  [1] https://github.com/borkmann/netperf_scripts/blob/master/percpu_netperf

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20201010234006.7075-3-daniel@iogearbox.net

1 files changed, 47 insertions, 7 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index 5da44b11e1ec..fab951c6be57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2380,8 +2380,9 @@ out:
 
 /* Internal, non-exposed redirect flags. */
 enum {
-	BPF_F_NEIGH = (1ULL << 1),
-#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH)
+	BPF_F_NEIGH	= (1ULL << 1),
+	BPF_F_PEER	= (1ULL << 2),
+#define BPF_F_REDIRECT_INTERNAL	(BPF_F_NEIGH | BPF_F_PEER)
 };
 
 BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2430,19 +2431,35 @@ EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
 int skb_do_redirect(struct sk_buff *skb)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct net *net = dev_net(skb->dev);
 	struct net_device *dev;
 	u32 flags = ri->flags;
 
-	dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
+	dev = dev_get_by_index_rcu(net, ri->tgt_index);
 	ri->tgt_index = 0;
-	if (unlikely(!dev)) {
-		kfree_skb(skb);
-		return -EINVAL;
+	ri->flags = 0;
+	if (unlikely(!dev))
+		goto out_drop;
+	if (flags & BPF_F_PEER) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+
+		if (unlikely(!ops->ndo_get_peer_dev ||
+			     !skb_at_tc_ingress(skb)))
+			goto out_drop;
+		dev = ops->ndo_get_peer_dev(dev);
+		if (unlikely(!dev ||
+			     !is_skb_forwardable(dev, skb) ||
+			     net_eq(net, dev_net(dev))))
+			goto out_drop;
+		skb->dev = dev;
+		return -EAGAIN;
 	}
-
 	return flags & BPF_F_NEIGH ?
 	       __bpf_redirect_neigh(skb, dev) :
 	       __bpf_redirect(skb, dev, flags);
+out_drop:
+	kfree_skb(skb);
+	return -EINVAL;
 }
 
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
@@ -2466,6 +2483,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 	.arg2_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
+{
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	if (unlikely(flags))
+		return TC_ACT_SHOT;
+
+	ri->flags = BPF_F_PEER;
+	ri->tgt_index = ifindex;
+
+	return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_peer_proto = {
+	.func           = bpf_redirect_peer,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_ANYTHING,
+	.arg2_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
 {
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -7053,6 +7091,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_redirect_proto;
 	case BPF_FUNC_redirect_neigh:
 		return &bpf_redirect_neigh_proto;
+	case BPF_FUNC_redirect_peer:
+		return &bpf_redirect_peer_proto;
 	case BPF_FUNC_get_route_realm:
 		return &bpf_get_route_realm_proto;
 	case BPF_FUNC_get_hash_recalc: