Commit d01b59c9 authored by Xuesen Huang's avatar Xuesen Huang Committed by Daniel Borkmann
Browse files

bpf: Add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_ENCAP_L2_ETH 



bpf_skb_adjust_room sets the inner_protocol as skb->protocol for packets
encapsulation. But that is not appropriate when pushing Ethernet header.

Add an option to further specify encap L2 type and set the inner_protocol
as ETH_P_TEB.

Suggested-by: default avatarWillem de Bruijn <willemb@google.com>
Signed-off-by: default avatarXuesen Huang <huangxuesen@kuaishou.com>
Signed-off-by: default avatarZhiyong Cheng <chengzhiyong@kuaishou.com>
Signed-off-by: default avatarLi Wang <wangli09@kuaishou.com>
Signed-off-by: default avatarDaniel Borkmann <daniel@iogearbox.net>
Acked-by: default avatarWillem de Bruijn <willemb@google.com>
Link: https://lore.kernel.org/bpf/20210304064046.6232-1-hxseverything@gmail.com
parent bce86231

include/uapi/linux/bpf.h

+5 −0
Original line number Diff line number Diff line
@@ -2484,6 +2484,10 @@ union bpf_attr { 
 *		  Use with ENCAP_L3/L4 flags to further specify the tunnel

 *		  type; *len* is the length of the inner MAC header.

 *

 *		* **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**:

 *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the

 *		  L2 type as Ethernet.

 *

 * 		A call to this helper is susceptible to change the underlying

 * 		packet buffer. Therefore, at load time, all checks on pointers

 * 		previously done by the verifier are invalidated and must be
@@ -4916,6 +4920,7 @@ enum { 
	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),

	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),

	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),

	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),

};



enum {

net/core/filter.c

+10 −1
Original line number Diff line number Diff line
@@ -3409,6 +3409,7 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb) 
					 BPF_F_ADJ_ROOM_ENCAP_L3_MASK | \

					 BPF_F_ADJ_ROOM_ENCAP_L4_GRE | \

					 BPF_F_ADJ_ROOM_ENCAP_L4_UDP | \

					 BPF_F_ADJ_ROOM_ENCAP_L2_ETH | \

					 BPF_F_ADJ_ROOM_ENCAP_L2( \

					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
@@ -3445,6 +3446,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, 
		    flags & BPF_F_ADJ_ROOM_ENCAP_L4_UDP)

			return -EINVAL;



		if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH &&

		    inner_mac_len < ETH_HLEN)

			return -EINVAL;



		if (skb->encapsulation)

			return -EALREADY;
@@ -3463,6 +3468,10 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff, 
		skb->inner_mac_header = inner_net - inner_mac_len;

		skb->inner_network_header = inner_net;

		skb->inner_transport_header = inner_trans;



		if (flags & BPF_F_ADJ_ROOM_ENCAP_L2_ETH)

			skb_set_inner_protocol(skb, htons(ETH_P_TEB));

		else

			skb_set_inner_protocol(skb, skb->protocol);



		skb->encapsulation = 1;

tools/include/uapi/linux/bpf.h

+5 −0
Original line number Diff line number Diff line
@@ -2484,6 +2484,10 @@ union bpf_attr { 
 *		  Use with ENCAP_L3/L4 flags to further specify the tunnel

 *		  type; *len* is the length of the inner MAC header.

 *

 *		* **BPF_F_ADJ_ROOM_ENCAP_L2_ETH**:

 *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the

 *		  L2 type as Ethernet.

 *

 * 		A call to this helper is susceptible to change the underlying

 * 		packet buffer. Therefore, at load time, all checks on pointers

 * 		previously done by the verifier are invalidated and must be
@@ -4916,6 +4920,7 @@ enum { 
	BPF_F_ADJ_ROOM_ENCAP_L4_GRE	= (1ULL << 3),

	BPF_F_ADJ_ROOM_ENCAP_L4_UDP	= (1ULL << 4),

	BPF_F_ADJ_ROOM_NO_CSUM_RESET	= (1ULL << 5),

	BPF_F_ADJ_ROOM_ENCAP_L2_ETH	= (1ULL << 6),

};



enum {