diff mbox series

[PATCH/v2] bpf: add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_ENCAP_L2_ETH

Message ID 20210218163903.60992-1-hxseverything@gmail.com
State Superseded
Headers show
Series [PATCH/v2] bpf: add bpf_skb_adjust_room flag BPF_F_ADJ_ROOM_ENCAP_L2_ETH | expand

Commit Message

Xuesen Huang Feb. 18, 2021, 4:39 p.m. UTC 
From: Xuesen Huang <huangxuesen@kuaishou.com>

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: Willem de Bruijn <willemb@google.com>
Signed-off-by: Xuesen Huang <huangxuesen@kuaishou.com>
Signed-off-by: Zhiyong Cheng <chengzhiyong@kuaishou.com>
Signed-off-by: Li Wang <wangli09@kuaishou.com>
---
 include/uapi/linux/bpf.h       |  5 +++++
 net/core/filter.c              | 11 ++++++++++-
 tools/include/uapi/linux/bpf.h |  5 +++++
 3 files changed, 20 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 77d7c1b..d791596 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1751,6 +1751,10 @@  struct bpf_stack_build_id {
  *		  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
@@ -4088,6 +4092,7 @@  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 {
diff --git a/net/core/filter.c b/net/core/filter.c
index 255aeee..8d1fb61 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3412,6 +3412,7 @@  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))
 
@@ -3448,6 +3449,10 @@  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;
 
@@ -3466,7 +3471,11 @@  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;
-		skb_set_inner_protocol(skb, skb->protocol);
+
+		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;
 		skb_set_network_header(skb, mac_len);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 77d7c1b..d791596 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1751,6 +1751,10 @@  struct bpf_stack_build_id {
  *		  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
@@ -4088,6 +4092,7 @@  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 {