[RFC bpf-next 1/3] bpf: Add PPPoE encap support to bpf_skb_adjust_room

[ThisSeanZhang <thisseanzhang@gmail.com>]

Add a new BPF_F_ADJ_ROOM_ENCAP_PPPOE flag to bpf_skb_adjust_room() so
that a TC BPF program can encapsulate an IPv4 or IPv6 packet into a
PPPoE session header:

    bpf_skb_adjust_room(skb, PPPOE_SES_HLEN, BPF_ADJ_ROOM_MAC,
                        BPF_F_ADJ_ROOM_ENCAP_PPPOE);

The flag reserves room for the fixed-size PPPoE session header (the
6 byte session header plus the 2 byte PPP protocol field) between the
MAC header and the network header, and updates the skb metadata so
that the packet is consistent for later consumers: skb->protocol is
set to ETH_P_PPP_SES and the network header points at the inserted
PPPoE header. The header content itself, as well as the ethertype in
the MAC header, is left for the BPF program to fill in, e.g. via
bpf_skb_store_bytes().

So far a TC program could only add the header bytes manually, which
leaves skb->protocol and friends unchanged, so the skb keeps being
treated as a plain IP packet. In particular, software GSO can select
a segmentation handler based on the stale skb->protocol and process
the encapsulated packet incorrectly.

This pairs with the PPPoE GRO/GSO support in the PPPoE layer, which
registers a GRO/GSO handler for ETH_P_PPP_SES: once skb->protocol is
set correctly, such packets are segmented via pppoe_gso_segment() on
egress.

Signed-off-by: ThisSeanZhang <thisseanzhang@gmail.com>
---
 include/uapi/linux/bpf.h       | 12 ++++++++++++
 net/core/filter.c              | 22 ++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 12 ++++++++++++
 3 files changed, 46 insertions(+)

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 732b35cc0..30481d040 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3036,6 +3036,17 @@ union bpf_attr {
  *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
  *		  L2 type as Ethernet.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_PPPOE**:
+ *		  Encapsulate the packet in a PPPoE session header. Must be
+ *		  used with **BPF_ADJ_ROOM_MAC** mode and *len_diff* equal to
+ *		  the size of the PPPoE session header plus the PPP protocol
+ *		  field (8 bytes in total). The room is inserted between the
+ *		  MAC header and the network header, *skb->protocol* is set
+ *		  to **ETH_P_PPP_SES** and *skb->mac_len* is updated
+ *		  accordingly. The PPPoE header itself and the ethertype of
+ *		  the MAC header are filled in by the BPF program, e.g. via
+ *		  **bpf_skb_store_bytes**.
+ *
  *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
  *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
  *		  Indicate the new IP header version after decapsulating the
@@ -6323,6 +6334,7 @@ enum bpf_adj_room_flags {
 	BPF_F_ADJ_ROOM_DECAP_L4_UDP	= (1ULL << 10),
 	BPF_F_ADJ_ROOM_DECAP_IPXIP4	= (1ULL << 11),
 	BPF_F_ADJ_ROOM_DECAP_IPXIP6	= (1ULL << 12),
+	BPF_F_ADJ_ROOM_ENCAP_PPPOE	= (1ULL << 13),
 };
 
 enum {
diff --git a/net/core/filter.c b/net/core/filter.c
index 70dc62167..5b204e316 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -47,6 +47,7 @@
 #include <linux/ratelimit.h>
 #include <linux/seccomp.h>
 #include <linux/if_vlan.h>
+#include <linux/if_pppox.h>
 #include <linux/bpf.h>
 #include <linux/btf.h>
 #include <net/sch_generic.h>
@@ -3583,6 +3584,7 @@ static u32 bpf_skb_net_base_len(const struct sk_buff *skb)
 					 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_PPPOE | \
 					 BPF_F_ADJ_ROOM_ENCAP_L2( \
 					  BPF_ADJ_ROOM_ENCAP_L2_MASK))
 
@@ -3688,6 +3690,14 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
 			skb_dst_drop(skb);
 	}
 
+	if (flags & BPF_F_ADJ_ROOM_ENCAP_PPPOE) {
+		/* Network header points at the inserted PPPoE header. */
+		skb->protocol = htons(ETH_P_PPP_SES);
+		skb_reset_mac_len(skb);
+		if (skb_valid_dst(skb))
+			skb_dst_drop(skb);
+	}
+
 	if (skb_is_gso(skb)) {
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
 
@@ -3874,6 +3884,18 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff,
 		return -ENOTSUPP;
 	}
 
+	if (flags & BPF_F_ADJ_ROOM_ENCAP_PPPOE) {
+		/* The PPPoE session header has a fixed size and is
+		 * inserted directly after the MAC header.
+		 */
+		if (shrink || mode != BPF_ADJ_ROOM_MAC ||
+		    len_diff != PPPOE_SES_HLEN ||
+		    flags & ((BPF_F_ADJ_ROOM_ENCAP_MASK |
+			      BPF_F_ADJ_ROOM_DECAP_MASK) &
+			     ~BPF_F_ADJ_ROOM_ENCAP_PPPOE))
+			return -EINVAL;
+	}
+
 	if (flags & BPF_F_ADJ_ROOM_DECAP_MASK) {
 		u32 len_decap_min = 0;
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 732b35cc0..30481d040 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3036,6 +3036,17 @@ union bpf_attr {
  *		  Use with BPF_F_ADJ_ROOM_ENCAP_L2 flag to further specify the
  *		  L2 type as Ethernet.
  *
+ *		* **BPF_F_ADJ_ROOM_ENCAP_PPPOE**:
+ *		  Encapsulate the packet in a PPPoE session header. Must be
+ *		  used with **BPF_ADJ_ROOM_MAC** mode and *len_diff* equal to
+ *		  the size of the PPPoE session header plus the PPP protocol
+ *		  field (8 bytes in total). The room is inserted between the
+ *		  MAC header and the network header, *skb->protocol* is set
+ *		  to **ETH_P_PPP_SES** and *skb->mac_len* is updated
+ *		  accordingly. The PPPoE header itself and the ethertype of
+ *		  the MAC header are filled in by the BPF program, e.g. via
+ *		  **bpf_skb_store_bytes**.
+ *
  *		* **BPF_F_ADJ_ROOM_DECAP_L3_IPV4**,
  *		  **BPF_F_ADJ_ROOM_DECAP_L3_IPV6**:
  *		  Indicate the new IP header version after decapsulating the
@@ -6323,6 +6334,7 @@ enum bpf_adj_room_flags {
 	BPF_F_ADJ_ROOM_DECAP_L4_UDP	= (1ULL << 10),
 	BPF_F_ADJ_ROOM_DECAP_IPXIP4	= (1ULL << 11),
 	BPF_F_ADJ_ROOM_DECAP_IPXIP6	= (1ULL << 12),
+	BPF_F_ADJ_ROOM_ENCAP_PPPOE	= (1ULL << 13),
 };
 
 enum {
-- 
2.47.3