Skip to contentSkip to conversation

bpf: Allow any source IP in bpf_skb_set_tunnel_key

PATCH Applied Paul Chaignon 2 participants 7 messages Jul 25, 2022 – Jul 26, 2022

Subsystems (7)
lore
Share & tools
lore
#0 lore raw

v3 cover bpf: Allow any source IP in bpf_skb_set_tunnel_key

Commit 26101f5ab6bd ("bpf: Add source ip in "struct bpf_tunnel_key"") added support for getting and setting the outer source IP of encapsulated packets via the bpf_skb_{get,set}_tunnel_key BPF helper. This change allows BPF programs to set any IP address as the source, including for example the IP address of a container running on the same host.

In that last case, however, the encapsulated packets are dropped when looking up the route because the source IP address isn't assigned to any interface on the host. To avoid this, we need to set the FLOWI_FLAG_ANYSRC flag.

Changes in v3:
- Rebased on top of bpf-next.
- Reworked the last patch, for the selftests. Several changes were required to the existing vxlan_tunnel test to be able to test the change in the bpf_skb_set_tunnel_key helper.
- Apart from the rebase, only the last selftests patch changed, so I kept the Reviewed-by and Acked-by tags on other patches.
Changes in v2:
- Removed changes to IPv6 code paths as they are unnecessary.

Paul Chaignon (5):
ip_tunnels: Add new flow flags field to ip_tunnel_key
vxlan: Use ip_tunnel_key flow flags in route lookups
geneve: Use ip_tunnel_key flow flags in route lookups
bpf: Set flow flag to allow any source IP in bpf_tunnel_key selftests/bpf: Don't assign outer source IP to host

 drivers/net/geneve.c                          |  1 +
 drivers/net/vxlan/vxlan_core.c                | 11 ++-
 include/net/ip_tunnels.h                      |  1 +
 net/core/filter.c                             |  1 +
 .../selftests/bpf/prog_tests/test_tunnel.c    | 17 +++-
 .../selftests/bpf/progs/test_tunnel_kern.c    | 80 ++++++++++++++++---
 6 files changed, 96 insertions(+), 15 deletions(-)
Signature · 1 line
2.25.1
#1 lore raw

PATCH v3 1/5 ip_tunnels: Add new flow flags field to ip_tunnel_key

This commit extends the ip_tunnel_key struct with a new field for the flow flags, to pass them to the route lookups. This new field will be populated and used in subsequent commits.

---
 include/net/ip_tunnels.h | 1 +
 1 file changed, 1 insertion(+)
include/net/ip_tunnels.h +1 -0
index 20db95055db3..63fac94f9ace 100644
@@ -54,6 +54,7 @@ struct ip_tunnel_key {
 	__be32			label;		/* Flow Label for IPv6 */
 	__be16			tp_src;
 	__be16			tp_dst;
+	__u8			flow_flags;
 };
 
 /* Flags for ip_tunnel_info mode. */
Signature · 1 line
2.25.1
#2 lore raw

PATCH v3 2/5 vxlan: Use ip_tunnel_key flow flags in route lookups

In reply to Paul Chaignon

Use the new ip_tunnel_key field with the flow flags in the IPv4 route lookups for the encapsulated packet. This will be used by the bpf_skb_set_tunnel_key helper in a subsequent commit.

---
 drivers/net/vxlan/vxlan_core.c | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)
drivers/net/vxlan/vxlan_core.c +7 -4
index 8b0710b576c2..90811ab851fd 100644
@@ -2243,7 +2243,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device
 				      struct vxlan_sock *sock4,
 				      struct sk_buff *skb, int oif, u8 tos,
 				      __be32 daddr, __be32 *saddr, __be16 dport, __be16 sport,
-				      struct dst_cache *dst_cache,
+				      __u8 flow_flags, struct dst_cache *dst_cache,
 				      const struct ip_tunnel_info *info)
 {
 	bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
@@ -2270,6 +2270,7 @@ static struct rtable *vxlan_get_route(struct vxlan_dev *vxlan, struct net_device
 	fl4.saddr = *saddr;
 	fl4.fl4_dport = dport;
 	fl4.fl4_sport = sport;
+	fl4.flowi4_flags = flow_flags;
 
 	rt = ip_route_output_key(vxlan->net, &fl4);
 	if (!IS_ERR(rt)) {
@@ -2459,7 +2460,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 	unsigned int pkt_len = skb->len;
 	__be16 src_port = 0, dst_port;
 	struct dst_entry *ndst = NULL;
-	__u8 tos, ttl;
+	__u8 tos, ttl, flow_flags = 0;
 	int ifindex;
 	int err;
 	u32 flags = vxlan->cfg.flags;
@@ -2525,6 +2526,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		}
 		dst = &remote_ip;
 		dst_port = info->key.tp_dst ? : vxlan->cfg.dst_port;
+		flow_flags = info->key.flow_flags;
 		vni = tunnel_id_to_key32(info->key.tun_id);
 		ifindex = 0;
 		dst_cache = &info->dst_cache;
@@ -2555,7 +2557,7 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev,
 		rt = vxlan_get_route(vxlan, dev, sock4, skb, ifindex, tos,
 				     dst->sin.sin_addr.s_addr,
 				     &local_ip.sin.sin_addr.s_addr,
-				     dst_port, src_port,
+				     dst_port, src_port, flow_flags,
 				     dst_cache, info);
 		if (IS_ERR(rt)) {
 			err = PTR_ERR(rt);
@@ -3061,7 +3063,8 @@ static int vxlan_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
 		rt = vxlan_get_route(vxlan, dev, sock4, skb, 0, info->key.tos,
 				     info->key.u.ipv4.dst,
 				     &info->key.u.ipv4.src, dport, sport,
-				     &info->dst_cache, info);
+				     info->key.flow_flags, &info->dst_cache,
+				     info);
 		if (IS_ERR(rt))
 			return PTR_ERR(rt);
 		ip_rt_put(rt);
Signature · 1 line
2.25.1
#3 lore raw

PATCH v3 3/5 geneve: Use ip_tunnel_key flow flags in route lookups

In reply to Paul Chaignon

Use the new ip_tunnel_key field with the flow flags in the IPv4 route lookups for the encapsulated packet. This will be used by the bpf_skb_set_tunnel_key helper in the subsequent commit.

---
 drivers/net/geneve.c | 1 +
 1 file changed, 1 insertion(+)
drivers/net/geneve.c +1 -0
index 2495a5719e1c..018d365f9deb 100644
@@ -815,6 +815,7 @@ static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
 	fl4->saddr = info->key.u.ipv4.src;
 	fl4->fl4_dport = dport;
 	fl4->fl4_sport = sport;
+	fl4->flowi4_flags = info->key.flow_flags;
 
 	tos = info->key.tos;
 	if ((tos == 1) && !geneve->cfg.collect_md) {
Signature · 1 line
2.25.1
#4 lore raw

PATCH v3 4/5 bpf: Set flow flag to allow any source IP in bpf_tunnel_key

In reply to Paul Chaignon

Commit 26101f5ab6bd ("bpf: Add source ip in "struct bpf_tunnel_key"") added support for getting and setting the outer source IP of encapsulated packets via the bpf_skb_{get,set}_tunnel_key BPF helper. This change allows BPF programs to set any IP address as the source, including for example the IP address of a container running on the same host.

In that last case, however, the encapsulated packets are dropped when looking up the route because the source IP address isn't assigned to any interface on the host. To avoid this, we need to set the FLOWI_FLAG_ANYSRC flag.

Fixes 26101f5ab6bd ("bpf: Add source ip in "struct bpf_tunnel_key"")
---
 net/core/filter.c | 1 +
 1 file changed, 1 insertion(+)
net/core/filter.c +1 -0
index 57c5e4c4efd2..dffc7dcda96a 100644
@@ -4653,6 +4653,7 @@ BPF_CALL_4(bpf_skb_set_tunnel_key, struct sk_buff *, skb,
 	} else {
 		info->key.u.ipv4.dst = cpu_to_be32(from->remote_ipv4);
 		info->key.u.ipv4.src = cpu_to_be32(from->local_ipv4);
+		info->key.flow_flags = FLOWI_FLAG_ANYSRC;
 	}
 
 	return 0;
Signature · 1 line
2.25.1
#5 lore raw

PATCH v3 5/5 selftests/bpf: Don't assign outer source IP to host

In reply to Paul Chaignon

The previous commit fixed a bug in the bpf_skb_set_tunnel_key helper to avoid dropping packets whose outer source IP address isn't assigned to a host interface. This commit changes the corresponding selftest to not assign the outer source IP address to an interface.

Not assigning the source IP to an interface causes two issues in the existing test:
1. The ARP requests will fail for that IP address so we need to add the ARP entry manually.
2. The encapsulated ICMP echo reply traffic will not reach the VXLAN device. It will be dropped by the stack before, because the outer destination IP is unknown.

To solve 2., we have two choices. Either we perform decapsulation ourselves in a BPF program attached at veth1 (the base device for the VXLAN device), or we switch the outer destination address when we receive the packet at veth1, such that the stack properly demultiplexes it to the VXLAN device afterward.

This commit implements the second approach, where we switch the outer destination address from the unassigned IP address to the assigned one, only for VXLAN traffic ingressing veth1.

Then, at the vxlan device, the BPF program that checks the output of bpf_skb_get_tunnel_key needs to be updated as the expected local IP address is now the unassigned one.

---
 .../selftests/bpf/prog_tests/test_tunnel.c    | 17 +++-
 .../selftests/bpf/progs/test_tunnel_kern.c    | 80 ++++++++++++++++---
 2 files changed, 86 insertions(+), 11 deletions(-)
tools/testing/selftests/bpf/prog_tests/test_tunnel.c +15 -2
index 3bba4a2a0530..eea274110267 100644
@@ -82,6 +82,7 @@
 
 #define MAC_TUNL_DEV0 "52:54:00:d9:01:00"
 #define MAC_TUNL_DEV1 "52:54:00:d9:02:00"
+#define MAC_VETH1 "52:54:00:d9:03:00"
 
 #define VXLAN_TUNL_DEV0 "vxlan00"
 #define VXLAN_TUNL_DEV1 "vxlan11"
@@ -108,10 +109,9 @@
 static int config_device(void)
 {
 	SYS("ip netns add at_ns0");
-	SYS("ip link add veth0 type veth peer name veth1");
+	SYS("ip link add veth0 address " MAC_VETH1 " type veth peer name veth1");
 	SYS("ip link set veth0 netns at_ns0");
 	SYS("ip addr add " IP4_ADDR1_VETH1 "/24 dev veth1");
-	SYS("ip addr add " IP4_ADDR2_VETH1 "/24 dev veth1");
 	SYS("ip link set dev veth1 up mtu 1500");
 	SYS("ip netns exec at_ns0 ip addr add " IP4_ADDR_VETH0 "/24 dev veth0");
 	SYS("ip netns exec at_ns0 ip link set dev veth0 up mtu 1500");
@@ -140,6 +140,8 @@ static int add_vxlan_tunnel(void)
 	    VXLAN_TUNL_DEV0, IP4_ADDR_TUNL_DEV0);
 	SYS("ip netns exec at_ns0 ip neigh add %s lladdr %s dev %s",
 	    IP4_ADDR_TUNL_DEV1, MAC_TUNL_DEV1, VXLAN_TUNL_DEV0);
+	SYS("ip netns exec at_ns0 ip neigh add %s lladdr %s dev veth0",
+	    IP4_ADDR2_VETH1, MAC_VETH1);
 
 	/* root namespace */
 	SYS("ip link add dev %s type vxlan external gbp dstport 4789",
@@ -277,6 +279,17 @@ static void test_vxlan_tunnel(void)
 	if (attach_tc_prog(&tc_hook, get_src_prog_fd, set_src_prog_fd))
 		goto done;
 
+	/* load and attach bpf prog to veth dev tc hook point */
+	ifindex = if_nametoindex("veth1");
+	if (!ASSERT_NEQ(ifindex, 0, "veth1 ifindex"))
+		goto done;
+	tc_hook.ifindex = ifindex;
+	set_dst_prog_fd = bpf_program__fd(skel->progs.veth_set_outer_dst);
+	if (!ASSERT_GE(set_dst_prog_fd, 0, "bpf_program__fd"))
+		goto done;
+	if (attach_tc_prog(&tc_hook, set_dst_prog_fd, -1))
+		goto done;
+
 	/* load and attach prog set_md to tunnel dev tc hook point at_ns0 */
 	nstoken = open_netns("at_ns0");
 	if (!ASSERT_OK_PTR(nstoken, "setns src"))
tools/testing/selftests/bpf/progs/test_tunnel_kern.c +71 -9

123 lines not on this page · raw message

Signature · 1 line
2.25.1
#6 lore raw
In reply to Paul Chaignon
This series was applied to bpf/bpf-next.git (master) by Daniel Borkmann <[email protected]>:

Hello:

This series was applied to bpf/bpf-next.git (master) by Daniel Borkmann <[email protected]>:

Quoted 6 lines · On Mon, 25 Jul 2022 16:31:07 +0200 you wrote:

Commit 26101f5ab6bd ("bpf: Add source ip in "struct bpf_tunnel_key"") added support for getting and setting the outer source IP of encapsulated packets via the bpf_skb_{get,set}_tunnel_key BPF helper. This change allows BPF programs to set any IP address as the source, including for example the IP address of a container running on the same host.

Quoted 6 lines

In that last case, however, the encapsulated packets are dropped when looking up the route because the source IP address isn't assigned to any interface on the host. To avoid this, we need to set the FLOWI_FLAG_ANYSRC flag.

[...]

Here is the summary with links:
- [bpf-next,v3,1/5] ip_tunnels: Add new flow flags field to ip_tunnel_key

    https://git.kernel.org/bpf/bpf-next/c/451ef36bd229
  - [bpf-next,v3,2/5] vxlan: Use ip_tunnel_key flow flags in route lookups
    https://git.kernel.org/bpf/bpf-next/c/7e2fb8bc7ef6
  - [bpf-next,v3,3/5] geneve: Use ip_tunnel_key flow flags in route lookups
    https://git.kernel.org/bpf/bpf-next/c/861396ac0b47
  - [bpf-next,v3,4/5] bpf: Set flow flag to allow any source IP in bpf_tunnel_key
    https://git.kernel.org/bpf/bpf-next/c/b8fff748521c
  - [bpf-next,v3,5/5] selftests/bpf: Don't assign outer source IP to host
    https://git.kernel.org/bpf/bpf-next/c/1115169f47ae

You are awesome, thank you!

Signature · 2 lines
Deet-doot-dot, I am a bot.
https://korg.docs.kernel.org/patchwork/pwbot.html