[DO_NOT_APPLY v2 1/3] add xdp-forwarder

[Yureka Lilian <yureka@cyberchaos.dev>]

Signed-off-by: Yureka Lilian <yureka@cyberchaos.dev>
---
 pkgs/default.nix                              |   1 +
 tools/xdp-forwarder/Makefile                  |  28 ++
 tools/xdp-forwarder/default.nix               |  24 ++
 tools/xdp-forwarder/include/parsing_helpers.h | 273 ++++++++++++++++++
 tools/xdp-forwarder/include/rewrite_helpers.h | 145 ++++++++++
 tools/xdp-forwarder/prog_physical.c           |  37 +++
 tools/xdp-forwarder/prog_router.c             |  43 +++
 tools/xdp-forwarder/set_router_iface.c        |  32 ++
 8 files changed, 583 insertions(+)
 create mode 100644 tools/xdp-forwarder/Makefile
 create mode 100644 tools/xdp-forwarder/default.nix
 create mode 100644 tools/xdp-forwarder/include/parsing_helpers.h
 create mode 100644 tools/xdp-forwarder/include/rewrite_helpers.h
 create mode 100644 tools/xdp-forwarder/prog_physical.c
 create mode 100644 tools/xdp-forwarder/prog_router.c
 create mode 100644 tools/xdp-forwarder/set_router_iface.c

diff --git a/pkgs/default.nix b/pkgs/default.nix
index 3b81339..59b49fb 100644
--- a/pkgs/default.nix
+++ b/pkgs/default.nix
@@ -44,6 +44,7 @@ let
     };
     xdg-desktop-portal-spectrum-host =
       self.callSpectrumPackage ../tools/xdg-desktop-portal-spectrum-host {};
+    xdp-forwarder = self.callSpectrumPackage ../tools/xdp-forwarder {};
 
     # Packages from the overlay, so it's possible to build them from
     # the CLI easily.
diff --git a/tools/xdp-forwarder/Makefile b/tools/xdp-forwarder/Makefile
new file mode 100644
index 0000000..24268d9
--- /dev/null
+++ b/tools/xdp-forwarder/Makefile
@@ -0,0 +1,28 @@
+CC     ?= gcc
+CLANG  ?= clang
+prefix ?= /usr/local
+bindir ?= $(prefix)/bin
+xdpdir ?= $(prefix)/lib/xdp
+
+TOOLS = set_router_iface
+PROGS = prog_router.o prog_physical.o
+
+set_router_iface: set_router_iface.c
+	$(CC) `pkg-config --libs --cflags libbpf` -o $@ $^
+
+prog_%.o: prog_%.c
+	$(CLANG) $(NIX_CFLAGS_COMPILE) -target bpf -I include -g -c -o $@ $^
+
+tools: $(TOOLS)
+
+progs: $(PROGS)
+
+all: tools progs
+
+install_tools: $(TOOLS)
+	install -Dm755 -t $(bindir) $^
+
+install_progs: $(PROGS)
+	install -Dm755 -t $(xdpdir) $^
+
+install: install_tools install_progs
diff --git a/tools/xdp-forwarder/default.nix b/tools/xdp-forwarder/default.nix
new file mode 100644
index 0000000..e70ec5e
--- /dev/null
+++ b/tools/xdp-forwarder/default.nix
@@ -0,0 +1,24 @@
+# SPDX-License-Identifier: MIT
+# SPDX-FileCopyrightText: 2025 Yureka Lilian <yureka@cyberchaos.dev>
+
+import ../../lib/call-package.nix ({ src, pkgsMusl }:
+pkgsMusl.callPackage ({ lib, stdenv, clang, libbpf, linuxHeaders, pkg-config }:
+
+stdenv.mkDerivation {
+  pname = "xdp-forwarder";
+  version = "0";
+
+  src = lib.fileset.toSource {
+    root = ./.;
+    fileset = lib.fileset.fileFilter
+      ({ hasExt, ... }: !(hasExt "nix") && !(hasExt "md")) ./.;
+  };
+
+  buildInputs = [ libbpf linuxHeaders ];
+  nativeBuildInputs = [ clang pkg-config ];
+
+  makeFlags = [ "prefix=$(out)" ];
+  hardeningDisable = [ "stackprotector" "zerocallusedregs" ];
+}
+
+) {}) (_: {})
diff --git a/tools/xdp-forwarder/include/parsing_helpers.h b/tools/xdp-forwarder/include/parsing_helpers.h
new file mode 100644
index 0000000..3d240cd
--- /dev/null
+++ b/tools/xdp-forwarder/include/parsing_helpers.h
@@ -0,0 +1,273 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-clause) */
+/* Vendored from https://github.com/xdp-project/xdp-tutorial/blob/d3d3eed6ea9a63d1302bfa8b5a8e93862bfe11f0/common/parsing_helpers.h */
+/*
+ * This file contains parsing functions that are used in the packetXX XDP
+ * programs. The functions are marked as __always_inline, and fully defined in
+ * this header file to be included in the BPF program.
+ *
+ * Each helper parses a packet header, including doing bounds checking, and
+ * returns the type of its contents if successful, and -1 otherwise.
+ *
+ * For Ethernet and IP headers, the content type is the type of the payload
+ * (h_proto for Ethernet, nexthdr for IPv6), for ICMP it is the ICMP type field.
+ * All return values are in host byte order.
+ *
+ * The versions of the functions included here are slightly expanded versions of
+ * the functions in the packet01 lesson. For instance, the Ethernet header
+ * parsing has support for parsing VLAN tags.
+ */
+
+#ifndef __PARSING_HELPERS_H
+#define __PARSING_HELPERS_H
+
+#include <stddef.h>
+#include <linux/if_ether.h>
+#include <linux/if_packet.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/icmp.h>
+#include <linux/icmpv6.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+
+/* Header cursor to keep track of current parsing position */
+struct hdr_cursor {
+	void *pos;
+};
+
+/*
+ *	struct vlan_hdr - vlan header
+ *	@h_vlan_TCI: priority and VLAN ID
+ *	@h_vlan_encapsulated_proto: packet type ID or len
+ */
+struct vlan_hdr {
+	__be16 h_vlan_TCI;
+	__be16 h_vlan_encapsulated_proto;
+};
+
+/*
+ * Struct icmphdr_common represents the common part of the icmphdr and icmp6hdr
+ * structures.
+ */
+struct icmphdr_common {
+	__u8 type;
+	__u8 code;
+	__sum16 cksum;
+};
+
+/* Allow users of header file to redefine VLAN max depth */
+#ifndef VLAN_MAX_DEPTH
+#define VLAN_MAX_DEPTH 2
+#endif
+
+#define VLAN_VID_MASK           0x0fff /* VLAN Identifier */
+/* Struct for collecting VLANs after parsing via parse_ethhdr_vlan */
+struct collect_vlans {
+	__u16 id[VLAN_MAX_DEPTH];
+};
+
+static __always_inline int proto_is_vlan(__u16 h_proto)
+{
+	return !!(h_proto == bpf_htons(ETH_P_8021Q) ||
+	          h_proto == bpf_htons(ETH_P_8021AD));
+}
+
+/* Notice, parse_ethhdr() will skip VLAN tags, by advancing nh->pos and returns
+ * next header EtherType, BUT the ethhdr pointer supplied still points to the
+ * Ethernet header. Thus, caller can look at eth->h_proto to see if this was a
+ * VLAN tagged packet.
+ */
+static __always_inline int parse_ethhdr_vlan(struct hdr_cursor *nh,
+                                             void *data_end,
+                                             struct ethhdr **ethhdr,
+                                             struct collect_vlans *vlans)
+{
+	struct ethhdr *eth = nh->pos;
+	int hdrsize = sizeof(*eth);
+	struct vlan_hdr *vlh;
+	__u16 h_proto;
+	int i;
+
+	/* Byte-count bounds check; check if current pointer + size of header
+	 * is after data_end.
+	 */
+	if (nh->pos + hdrsize > data_end)
+		return -1;
+
+	nh->pos += hdrsize;
+	*ethhdr = eth;
+	vlh = nh->pos;
+	h_proto = eth->h_proto;
+
+	/* Use loop unrolling to avoid the verifier restriction on loops;
+	 * support up to VLAN_MAX_DEPTH layers of VLAN encapsulation.
+	 */
+	#pragma unroll
+	for (i = 0; i < VLAN_MAX_DEPTH; i++) {
+		if (!proto_is_vlan(h_proto))
+			break;
+
+		if (vlh + 1 > data_end)
+			break;
+
+		h_proto = vlh->h_vlan_encapsulated_proto;
+		if (vlans) /* collect VLAN ids */
+			vlans->id[i] =
+				(bpf_ntohs(vlh->h_vlan_TCI) & VLAN_VID_MASK);
+
+		vlh++;
+	}
+
+	nh->pos = vlh;
+	return h_proto; /* network-byte-order */
+}
+
+static __always_inline int parse_ethhdr(struct hdr_cursor *nh,
+                                        void *data_end,
+                                        struct ethhdr **ethhdr)
+{
+	/* Expect compiler removes the code that collects VLAN ids */
+	return parse_ethhdr_vlan(nh, data_end, ethhdr, NULL);
+}
+
+static __always_inline int parse_ip6hdr(struct hdr_cursor *nh,
+                                        void *data_end,
+                                        struct ipv6hdr **ip6hdr)
+{
+	struct ipv6hdr *ip6h = nh->pos;
+
+	/* Pointer-arithmetic bounds check; pointer +1 points to after end of
+	 * thing being pointed to. We will be using this style in the remainder
+	 * of the tutorial.
+	 */
+	if (ip6h + 1 > data_end)
+		return -1;
+
+	nh->pos = ip6h + 1;
+	*ip6hdr = ip6h;
+
+	return ip6h->nexthdr;
+}
+
+static __always_inline int parse_iphdr(struct hdr_cursor *nh,
+                                       void *data_end,
+                                       struct iphdr **iphdr)
+{
+	struct iphdr *iph = nh->pos;
+	int hdrsize;
+
+	if (iph + 1 > data_end)
+		return -1;
+
+	hdrsize = iph->ihl * 4;
+	/* Sanity check packet field is valid */
+	if(hdrsize < sizeof(*iph))
+		return -1;
+
+	/* Variable-length IPv4 header, need to use byte-based arithmetic */
+	if (nh->pos + hdrsize > data_end)
+		return -1;
+
+	nh->pos += hdrsize;
+	*iphdr = iph;
+
+	return iph->protocol;
+}
+
+static __always_inline int parse_icmp6hdr(struct hdr_cursor *nh,
+                                          void *data_end,
+                                          struct icmp6hdr **icmp6hdr)
+{
+	struct icmp6hdr *icmp6h = nh->pos;
+
+	if (icmp6h + 1 > data_end)
+		return -1;
+
+	nh->pos   = icmp6h + 1;
+	*icmp6hdr = icmp6h;
+
+	return icmp6h->icmp6_type;
+}
+
+static __always_inline int parse_icmphdr(struct hdr_cursor *nh,
+                                         void *data_end,
+                                         struct icmphdr **icmphdr)
+{
+	struct icmphdr *icmph = nh->pos;
+
+	if (icmph + 1 > data_end)
+		return -1;
+
+	nh->pos  = icmph + 1;
+	*icmphdr = icmph;
+
+	return icmph->type;
+}
+
+static __always_inline int parse_icmphdr_common(struct hdr_cursor *nh,
+                                                void *data_end,
+                                                struct icmphdr_common **icmphdr)
+{
+	struct icmphdr_common *h = nh->pos;
+
+	if (h + 1 > data_end)
+		return -1;
+
+	nh->pos  = h + 1;
+	*icmphdr = h;
+
+	return h->type;
+}
+
+/*
+ * parse_udphdr: parse the udp header and return the length of the udp payload
+ */
+static __always_inline int parse_udphdr(struct hdr_cursor *nh,
+                                        void *data_end,
+                                        struct udphdr **udphdr)
+{
+	int len;
+	struct udphdr *h = nh->pos;
+
+	if (h + 1 > data_end)
+		return -1;
+
+	nh->pos  = h + 1;
+	*udphdr = h;
+
+	len = bpf_ntohs(h->len) - sizeof(struct udphdr);
+	if (len < 0)
+		return -1;
+
+	return len;
+}
+
+/*
+ * parse_tcphdr: parse and return the length of the tcp header
+ */
+static __always_inline int parse_tcphdr(struct hdr_cursor *nh,
+                                        void *data_end,
+                                        struct tcphdr **tcphdr)
+{
+	int len;
+	struct tcphdr *h = nh->pos;
+
+	if (h + 1 > data_end)
+		return -1;
+
+	len = h->doff * 4;
+	/* Sanity check packet field is valid */
+	if(len < sizeof(*h))
+		return -1;
+
+	/* Variable-length TCP header, need to use byte-based arithmetic */
+	if (nh->pos + len > data_end)
+		return -1;
+
+	nh->pos += len;
+	*tcphdr = h;
+
+	return len;
+}
+
+#endif /* __PARSING_HELPERS_H */
diff --git a/tools/xdp-forwarder/include/rewrite_helpers.h b/tools/xdp-forwarder/include/rewrite_helpers.h
new file mode 100644
index 0000000..2deae9a
--- /dev/null
+++ b/tools/xdp-forwarder/include/rewrite_helpers.h
@@ -0,0 +1,145 @@
+/* SPDX-License-Identifier: (GPL-2.0-or-later OR BSD-2-clause) */
+/* Vendored from https://github.com/xdp-project/xdp-tutorial/blob/d3d3eed6ea9a63d1302bfa8b5a8e93862bfe11f0/common/rewrite_helpers.h */
+/*
+ * This file contains functions that are used in the packetXX XDP programs to
+ * manipulate on packets data. The functions are marked as __always_inline, and
+ * fully defined in this header file to be included in the BPF program.
+ */
+
+#ifndef __REWRITE_HELPERS_H
+#define __REWRITE_HELPERS_H
+
+#include <linux/bpf.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_endian.h>
+
+/* Pops the outermost VLAN tag off the packet. Returns the popped VLAN ID on
+ * success or negative errno on failure.
+ */
+static __always_inline int vlan_tag_pop(struct xdp_md *ctx, struct ethhdr *eth)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	struct ethhdr eth_cpy;
+	struct vlan_hdr *vlh;
+	__be16 h_proto;
+	int vlid;
+
+	if (!proto_is_vlan(eth->h_proto))
+		return -1;
+
+	/* Careful with the parenthesis here */
+	vlh = (void *)(eth + 1);
+
+	/* Still need to do bounds checking */
+	if (vlh + 1 > data_end)
+		return -1;
+
+	/* Save vlan ID for returning, h_proto for updating Ethernet header */
+	vlid = bpf_ntohs(vlh->h_vlan_TCI);
+	h_proto = vlh->h_vlan_encapsulated_proto;
+
+	/* Make a copy of the outer Ethernet header before we cut it off */
+	__builtin_memcpy(&eth_cpy, eth, sizeof(eth_cpy));
+
+	/* Actually adjust the head pointer */
+	if (bpf_xdp_adjust_head(ctx, (int)sizeof(*vlh)))
+		return -1;
+
+	/* Need to re-evaluate data *and* data_end and do new bounds checking
+	 * after adjusting head
+	 */
+	eth = (void *)(long)ctx->data;
+	data_end = (void *)(long)ctx->data_end;
+	if (eth + 1 > data_end)
+		return -1;
+
+	/* Copy back the old Ethernet header and update the proto type */
+	__builtin_memcpy(eth, &eth_cpy, sizeof(*eth));
+	eth->h_proto = h_proto;
+
+	return vlid;
+}
+
+/* Pushes a new VLAN tag after the Ethernet header. Returns 0 on success,
+ * -1 on failure.
+ */
+static __always_inline int vlan_tag_push(struct xdp_md *ctx,
+                                         struct ethhdr *eth, int vlid)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	struct ethhdr eth_cpy;
+	struct vlan_hdr *vlh;
+
+	/* First copy the original Ethernet header */
+	__builtin_memcpy(&eth_cpy, eth, sizeof(eth_cpy));
+
+	/* Then add space in front of the packet */
+	if (bpf_xdp_adjust_head(ctx, 0 - (int)sizeof(*vlh)))
+		return -1;
+
+	/* Need to re-evaluate data_end and data after head adjustment, and
+	 * bounds check, even though we know there is enough space (as we
+	 * increased it).
+	 */
+	data_end = (void *)(long)ctx->data_end;
+	eth = (void *)(long)ctx->data;
+
+	if (eth + 1 > data_end)
+		return -1;
+
+	/* Copy back Ethernet header in the right place, populate VLAN tag with
+	 * ID and proto, and set outer Ethernet header to VLAN type.
+	 */
+	__builtin_memcpy(eth, &eth_cpy, sizeof(*eth));
+
+	vlh = (void *)(eth + 1);
+
+	if (vlh + 1 > data_end)
+		return -1;
+
+	vlh->h_vlan_TCI = bpf_htons(vlid);
+	vlh->h_vlan_encapsulated_proto = eth->h_proto;
+
+	eth->h_proto = bpf_htons(ETH_P_8021Q);
+	return 0;
+}
+
+/*
+ * Swaps destination and source MAC addresses inside an Ethernet header
+ */
+static __always_inline void swap_src_dst_mac(struct ethhdr *eth)
+{
+	__u8 h_tmp[ETH_ALEN];
+
+	__builtin_memcpy(h_tmp, eth->h_source, ETH_ALEN);
+	__builtin_memcpy(eth->h_source, eth->h_dest, ETH_ALEN);
+	__builtin_memcpy(eth->h_dest, h_tmp, ETH_ALEN);
+}
+
+/*
+ * Swaps destination and source IPv6 addresses inside an IPv6 header
+ */
+static __always_inline void swap_src_dst_ipv6(struct ipv6hdr *ipv6)
+{
+	struct in6_addr tmp = ipv6->saddr;
+
+	ipv6->saddr = ipv6->daddr;
+	ipv6->daddr = tmp;
+}
+
+/*
+ * Swaps destination and source IPv4 addresses inside an IPv4 header
+ */
+static __always_inline void swap_src_dst_ipv4(struct iphdr *iphdr)
+{
+	__be32 tmp = iphdr->saddr;
+
+	iphdr->saddr = iphdr->daddr;
+	iphdr->daddr = tmp;
+}
+
+#endif /* __REWRITE_HELPERS_H */
diff --git a/tools/xdp-forwarder/prog_physical.c b/tools/xdp-forwarder/prog_physical.c
new file mode 100644
index 0000000..04b5131
--- /dev/null
+++ b/tools/xdp-forwarder/prog_physical.c
@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: EUPL-1.2+
+// SPDX-FileCopyrightText: 2025 Yureka Lilian <yureka@cyberchaos.dev>
+
+#define VLAN_MAX_DEPTH 1
+
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include "parsing_helpers.h"
+#include "rewrite_helpers.h"
+
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+} router_iface SEC(".maps");
+
+SEC("xdp")
+int physical(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+
+	struct hdr_cursor nh;
+	nh.pos = data;
+
+	struct ethhdr *eth;
+	if (parse_ethhdr(&nh, data_end, &eth) < 0)
+		return XDP_DROP;
+
+	if (ctx->ingress_ifindex < 1 || ctx->ingress_ifindex > 4096)
+		return XDP_DROP;
+
+	vlan_tag_push(ctx, eth, ctx->ingress_ifindex);
+	return bpf_redirect_map(&router_iface, 0, 0);
+}
diff --git a/tools/xdp-forwarder/prog_router.c b/tools/xdp-forwarder/prog_router.c
new file mode 100644
index 0000000..fe6a6b5
--- /dev/null
+++ b/tools/xdp-forwarder/prog_router.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: EUPL-1.2+
+// SPDX-FileCopyrightText: 2025 Yureka Lilian <yureka@cyberchaos.dev>
+
+#define VLAN_MAX_DEPTH 1
+
+#include <linux/bpf.h>
+#include <bpf/bpf_endian.h>
+#include "parsing_helpers.h"
+#include "rewrite_helpers.h"
+
+// The map is actually not used by this program, but just included
+// to keep the reference-counted pin alive before any physical interfaces
+// are added.
+struct {
+	__uint(type, BPF_MAP_TYPE_DEVMAP);
+	__type(key, int);
+	__type(value, int);
+	__uint(max_entries, 1);
+	__uint(pinning, LIBBPF_PIN_BY_NAME);
+} router_iface SEC(".maps");
+
+
+SEC("xdp")
+int router(struct xdp_md *ctx)
+{
+	void *data_end = (void *)(long)ctx->data_end;
+	void *data = (void *)(long)ctx->data;
+
+	struct hdr_cursor nh;
+	nh.pos = data;
+
+	struct ethhdr *eth;
+	int r;
+	if (r = parse_ethhdr(&nh, data_end, &eth) < 0)
+		return XDP_DROP;
+
+	int vlid = vlan_tag_pop(ctx, eth);
+	if (vlid < 0) {
+		return XDP_DROP;
+	}
+
+	return bpf_redirect(vlid, 0);
+}
diff --git a/tools/xdp-forwarder/set_router_iface.c b/tools/xdp-forwarder/set_router_iface.c
new file mode 100644
index 0000000..f1a2bac
--- /dev/null
+++ b/tools/xdp-forwarder/set_router_iface.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: EUPL-1.2+
+// SPDX-FileCopyrightText: 2025 Yureka Lilian <yureka@cyberchaos.dev>
+
+#include <stdio.h>
+#include <net/if.h>
+#include <bpf/bpf.h>
+
+int main(int argc, char **argv)
+{
+	if (argc < 2) {
+		fprintf(stderr, "missing interface name\n");
+		return 1;
+	}
+
+	int router_idx = if_nametoindex(argv[1]);
+	if (router_idx <= 0) {
+		perror("error getting router interface");
+		return 1;
+	}
+
+	int map_fd = bpf_obj_get("/sys/fs/bpf/router_iface");
+	if (map_fd < 0) {
+		perror("failed to open bpf map");
+		return 1;
+	}
+
+	int id = 0;
+	if (bpf_map_update_elem(map_fd, &id, &router_idx, 0) < 0) {
+		perror("failed to update bpf map");
+		return 1;
+	}
+}
-- 
2.50.1