Merge branch 'Add source ip in bpf tunnel key'

Kaixi Fan says:

====================
From: Kaixi Fan <[email protected]>

Now bpf code could not set tunnel source ip address of ip tunnel. So it
could not support flow based tunnel mode completely. Because flow based
tunnel mode could set tunnel source, destination ip address and tunnel
key simultaneously.

Flow based tunnel is useful for overlay networks. And by configuring tunnel
source ip address, user could make their networks more elastic.
For example, tunnel source ip could be used to select different egress
nic interface for different flows with same tunnel destination ip. Another
example, user could choose one of multiple ip address of the egress nic
interface as the packet's tunnel source ip.

Add tunnel and tunnel source testcases in test_progs. Other types of
tunnel testcases would be moved to test_progs step by step in the
future.

v6:
- use libbpf api to attach tc progs and remove some shell commands to reduce
  test runtime based on Alexei Starovoitov's suggestion

v5:
- fix some code format errors
- use bpf kernel code at namespace at_ns0 to set tunnel metadata

v4:
- fix subject error of first patch

v3:
- move vxlan tunnel testcases to test_progs
- replace bpf_trace_printk with bpf_printk
- rename bpf kernel prog section name to tic

v2:
- merge vxlan tunnel and tunnel source ip testcases in test_tunnel.sh
====================

Signed-off-by: Alexei Starovoitov <[email protected]>

Author: Alexei Starovoitov

include/uapi/linux/bpf.h

@@ -5604,6 +5604,10 @@ struct bpf_tunnel_key {
 	__u8 tunnel_ttl;
 	__u16 tunnel_ext;	/* Padding, future use. */
 	__u32 tunnel_label;
+	union {
+		__u32 local_ipv4;
+		__u32 local_ipv6[4];
+	};
 };
 
 /* user accessible mirror of in-kernel xfrm_state.

net/core/filter.c

@@ -4498,6 +4498,7 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key
 	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
 		err = -EINVAL;
 		switch (size) {
+		case offsetof(struct bpf_tunnel_key, local_ipv6[0]):
 		case offsetof(struct bpf_tunnel_key, tunnel_label):
 		case offsetof(struct bpf_tunnel_key, tunnel_ext):
 			goto set_compat;
@@ -4523,10 +4524,14 @@ BPF_CALL_4(bpf_skb_get_tunnel_key, struct sk_buff *, skb, struct bpf_tunnel_key
 	if (flags & BPF_F_TUNINFO_IPV6) {
 		memcpy(to->remote_ipv6, &info->key.u.ipv6.src,
 		       sizeof(to->remote_ipv6));
+		memcpy(to->local_ipv6, &info->key.u.ipv6.dst,
+		       sizeof(to->local_ipv6));
 		to->tunnel_label = be32_to_cpu(info->key.label);
 	} else {
 		to->remote_ipv4 = be32_to_cpu(info->key.u.ipv4.src);
 		memset(&to->remote_ipv6[1], 0, sizeof(__u32) * 3);
+		to->local_ipv4 = be32_to_cpu(info->key.u.ipv4.dst);
+		memset(&to->local_ipv6[1], 0, sizeof(__u32) * 3);
 		to->tunnel_label = 0;
 	}
 
@@ -4597,6 +4602,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 		return -EINVAL;
 	if (unlikely(size != sizeof(struct bpf_tunnel_key))) {
 		switch (size) {
+		case offsetof(struct bpf_tunnel_key, local_ipv6[0]):
 		case offsetof(struct bpf_tunnel_key, tunnel_label):
 		case offsetof(struct bpf_tunnel_key, tunnel_ext):
 		case offsetof(struct bpf_tunnel_key, remote_ipv6[1]):
@@ -4639,10 +4645,13 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 		info->mode |= IP_TUNNEL_INFO_IPV6;
 		memcpy(&info->key.u.ipv6.dst, from->remote_ipv6,
 		       sizeof(from->remote_ipv6));
+		memcpy(&info->key.u.ipv6.src, from->local_ipv6,
+		       sizeof(from->local_ipv6));
 		info->key.label = cpu_to_be32(from->tunnel_label) &
 				  IPV6_FLOWLABEL_MASK;
 	} else {
 		info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
+		info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4);
 	}
 
 	return 0;

tools/include/uapi/linux/bpf.h

@@ -5604,6 +5604,10 @@ struct bpf_tunnel_key {
 	__u8 tunnel_ttl;
 	__u16 tunnel_ext;	/* Padding, future use. */
 	__u32 tunnel_label;
+	union {
+		__u32 local_ipv4;
+		__u32 local_ipv6[4];
+	};
 };
 
 /* user accessible mirror of in-kernel xfrm_state.