diff mbox series

[bpf,v5,3/4] bpf: fix bpf socket lookup from tc/xdp to respect socket VRF bindings

Message ID 20230608114155.39367-4-gilad9366@gmail.com (mailing list archive)
State New
Headers show
Series Socket lookup BPF API from tc/xdp ingress does not respect VRF bindings. | expand

Commit Message

Gilad Sever June 8, 2023, 11:41 a.m. UTC 
When calling bpf_sk_lookup_tcp(), bpf_sk_lookup_udp() or
bpf_skc_lookup_tcp() from tc/xdp ingress, VRF socket bindings aren't
respoected, i.e. unbound sockets are returned, and bound sockets aren't
found.

VRF binding is determined by the sdif argument to sk_lookup(), however
when called from tc the IP SKB control block isn't initialized and thus
inet{,6}_sdif() always returns 0.

Fix by calculating sdif for the tc/xdp flows by observing the device's
l3 enslaved state.

The cg/sk_skb hooking points which are expected to support
inet{,6}_sdif() pass sdif=-1 which makes __bpf_skc_lookup() use the
existing logic.

Fixes: 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF")
Acked-by: Stanislav Fomichev <sdf@google.com>
Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
Signed-off-by: Gilad Sever <gilad9366@gmail.com>
---
v5: Use reverse xmas tree indentation

v4: Move dev_sdif() to include/linux/netdevice.h as suggested by Stanislav Fomichev

v3: Rename bpf_l2_sdif() to dev_sdif() as suggested by Stanislav Fomichev
---
 include/linux/netdevice.h |  9 +++++++
 net/core/filter.c         | 54 ++++++++++++++++++++++++---------------
 2 files changed, 42 insertions(+), 21 deletions(-)

Comments

Daniel Borkmann June 20, 2023, 10:30 p.m. UTC | #1 
On 6/8/23 1:41 PM, Gilad Sever wrote:
> When calling bpf_sk_lookup_tcp(), bpf_sk_lookup_udp() or
> bpf_skc_lookup_tcp() from tc/xdp ingress, VRF socket bindings aren't
> respoected, i.e. unbound sockets are returned, and bound sockets aren't
> found.
> 
> VRF binding is determined by the sdif argument to sk_lookup(), however
> when called from tc the IP SKB control block isn't initialized and thus
> inet{,6}_sdif() always returns 0.
> 
> Fix by calculating sdif for the tc/xdp flows by observing the device's
> l3 enslaved state.
> 
> The cg/sk_skb hooking points which are expected to support
> inet{,6}_sdif() pass sdif=-1 which makes __bpf_skc_lookup() use the
> existing logic.
> 
> Fixes: 6acc9b432e67 ("bpf: Add helper to retrieve socket in BPF")
> Acked-by: Stanislav Fomichev <sdf@google.com>
> Reviewed-by: Shmulik Ladkani <shmulik.ladkani@gmail.com>
> Reviewed-by: Eyal Birger <eyal.birger@gmail.com>
> Signed-off-by: Gilad Sever <gilad9366@gmail.com>

Overall this series looks good to go, just small nits which would be great
to still address.

> ---
> v5: Use reverse xmas tree indentation
> 
> v4: Move dev_sdif() to include/linux/netdevice.h as suggested by Stanislav Fomichev
> 
> v3: Rename bpf_l2_sdif() to dev_sdif() as suggested by Stanislav Fomichev
> ---
>   include/linux/netdevice.h |  9 +++++++
>   net/core/filter.c         | 54 ++++++++++++++++++++++++---------------
>   2 files changed, 42 insertions(+), 21 deletions(-)
> 
> diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
> index c2f0c6002a84..db1bfca6b8b4 100644
> --- a/include/linux/netdevice.h
> +++ b/include/linux/netdevice.h
> @@ -5093,6 +5093,15 @@ static inline bool netif_is_l3_slave(const struct net_device *dev)
>   	return dev->priv_flags & IFF_L3MDEV_SLAVE;
>   }
>   
> +static inline int dev_sdif(const struct net_device *dev)
> +{
> +#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)

Why IS_ENABLED? config NET_L3_MASTER_DEV says bool, so #ifdef CONFIG_NET_L3_MASTER_DEV
should suffice?

> +	if (netif_is_l3_slave(dev))
> +		return dev->ifindex;
> +#endif
> +	return 0;
> +}
> +
>   static inline bool netif_is_bridge_master(const struct net_device *dev)
>   {
>   	return dev->priv_flags & IFF_EBRIDGE;
[...]

>   static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = {
> @@ -6778,10 +6782,11 @@ BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb,
>   {
>   	struct net *caller_net = dev_net(skb->dev);
>   	int ifindex = skb->dev->ifindex;
> +	int sdif = dev_sdif(skb->dev);
>   
>   	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
>   					      ifindex, IPPROTO_UDP, netns_id,
> -					      flags);
> +					      flags, sdif);
>   }
>   
>   static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
> @@ -6814,11 +6819,13 @@ BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
>   	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
>   {
>   	struct net *caller_net = dev_net(ctx->rxq->dev);
> -	int ifindex = ctx->rxq->dev->ifindex;
> +	struct net_device *dev = ctx->rxq->dev;

Why not doing this before the struct net *caller_net and also use it there
for the dev_net()? Same in other XDP places. It would be nice to also do the
same for the tc helpers.

> +	int ifindex = dev->ifindex;
> +	int sdif = dev_sdif(dev);
>   
>   	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
>   					      ifindex, IPPROTO_UDP, netns_id,
> -					      flags);
> +					      flags, sdif);
>   }
>   
>   static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
> @@ -6837,11 +6844,13 @@ BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
>   	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
>   {
>   	struct net *caller_net = dev_net(ctx->rxq->dev);
> -	int ifindex = ctx->rxq->dev->ifindex;
> +	struct net_device *dev = ctx->rxq->dev;
> +	int ifindex = dev->ifindex;
> +	int sdif = dev_sdif(dev);
>   
>   	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
>   					       ifindex, IPPROTO_TCP, netns_id,
> -					       flags);
> +					       flags, sdif);
>   }
>   
>   static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
diff mbox series

Patch

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c2f0c6002a84..db1bfca6b8b4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5093,6 +5093,15 @@  static inline bool netif_is_l3_slave(const struct net_device *dev)
 	return dev->priv_flags & IFF_L3MDEV_SLAVE;
 }
 
+static inline int dev_sdif(const struct net_device *dev)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (netif_is_l3_slave(dev))
+		return dev->ifindex;
+#endif
+	return 0;
+}
+
 static inline bool netif_is_bridge_master(const struct net_device *dev)
 {
 	return dev->priv_flags & IFF_EBRIDGE;
diff --git a/net/core/filter.c b/net/core/filter.c
index e06547922edc..5f665845ae45 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -6555,12 +6555,11 @@  static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 static struct sock *
 __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		 struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		 u64 flags)
+		 u64 flags, int sdif)
 {
 	struct sock *sk = NULL;
 	struct net *net;
 	u8 family;
-	int sdif;
 
 	if (len == sizeof(tuple->ipv4))
 		family = AF_INET;
@@ -6572,10 +6571,12 @@  __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	if (unlikely(flags || !((s32)netns_id < 0 || netns_id <= S32_MAX)))
 		goto out;
 
-	if (family == AF_INET)
-		sdif = inet_sdif(skb);
-	else
-		sdif = inet6_sdif(skb);
+	if (sdif < 0) {
+		if (family == AF_INET)
+			sdif = inet_sdif(skb);
+		else
+			sdif = inet6_sdif(skb);
+	}
 
 	if ((s32)netns_id < 0) {
 		net = caller_net;
@@ -6595,10 +6596,11 @@  __bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 static struct sock *
 __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		u64 flags)
+		u64 flags, int sdif)
 {
 	struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
-					   ifindex, proto, netns_id, flags);
+					   ifindex, proto, netns_id, flags,
+					   sdif);
 
 	if (sk) {
 		struct sock *sk2 = sk_to_full_sk(sk);
@@ -6638,7 +6640,7 @@  bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 	}
 
 	return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
-				netns_id, flags);
+				netns_id, flags, -1);
 }
 
 static struct sock *
@@ -6732,10 +6734,11 @@  BPF_CALL_5(bpf_tc_skc_lookup_tcp, struct sk_buff *, skb,
 {
 	struct net *caller_net = dev_net(skb->dev);
 	int ifindex = skb->dev->ifindex;
+	int sdif = dev_sdif(skb->dev);
 
 	return (unsigned long)__bpf_skc_lookup(skb, tuple, len, caller_net,
 					       ifindex, IPPROTO_TCP, netns_id,
-					       flags);
+					       flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_tc_skc_lookup_tcp_proto = {
@@ -6755,10 +6758,11 @@  BPF_CALL_5(bpf_tc_sk_lookup_tcp, struct sk_buff *, skb,
 {
 	struct net *caller_net = dev_net(skb->dev);
 	int ifindex = skb->dev->ifindex;
+	int sdif = dev_sdif(skb->dev);
 
 	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
 					      ifindex, IPPROTO_TCP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_tc_sk_lookup_tcp_proto = {
@@ -6778,10 +6782,11 @@  BPF_CALL_5(bpf_tc_sk_lookup_udp, struct sk_buff *, skb,
 {
 	struct net *caller_net = dev_net(skb->dev);
 	int ifindex = skb->dev->ifindex;
+	int sdif = dev_sdif(skb->dev);
 
 	return (unsigned long)__bpf_sk_lookup(skb, tuple, len, caller_net,
 					      ifindex, IPPROTO_UDP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_tc_sk_lookup_udp_proto = {
@@ -6814,11 +6819,13 @@  BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int ifindex = dev->ifindex;
+	int sdif = dev_sdif(dev);
 
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
 					      ifindex, IPPROTO_UDP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -6837,11 +6844,13 @@  BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int ifindex = dev->ifindex;
+	int sdif = dev_sdif(dev);
 
 	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
 					       ifindex, IPPROTO_TCP, netns_id,
-					       flags);
+					       flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
@@ -6860,11 +6869,13 @@  BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
-	int ifindex = ctx->rxq->dev->ifindex;
+	struct net_device *dev = ctx->rxq->dev;
+	int ifindex = dev->ifindex;
+	int sdif = dev_sdif(dev);
 
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
 					      ifindex, IPPROTO_TCP, netns_id,
-					      flags);
+					      flags, sdif);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -6884,7 +6895,8 @@  BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
 					       sock_net(ctx->sk), 0,
-					       IPPROTO_TCP, netns_id, flags);
+					       IPPROTO_TCP, netns_id, flags,
+					       -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
@@ -6903,7 +6915,7 @@  BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
 					      sock_net(ctx->sk), 0, IPPROTO_TCP,
-					      netns_id, flags);
+					      netns_id, flags, -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -6922,7 +6934,7 @@  BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
 {
 	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
 					      sock_net(ctx->sk), 0, IPPROTO_UDP,
-					      netns_id, flags);
+					      netns_id, flags, -1);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {