tc: bpf: add checksum helpers

Commit 608cd71a9c7c ("tc: bpf: generalize pedit action") has added the
possibility to mangle packet data to BPF programs in the tc pipeline.
This patch adds two helpers bpf_l3_csum_replace() and bpf_l4_csum_replace()
for fixing up the protocol checksums after the packet mangling.

It also adds 'flags' argument to bpf_skb_store_bytes() helper to avoid
unnecessary checksum recomputations when BPF programs adjusting l3/l4
checksums and documents all three helpers in uapi header.

Moreover, a sample program is added to show how BPF programs can make use
of the mangle and csum helpers.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 79 insertions, 0 deletions

diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index b5b3600dcdf5..d24f51bca465 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -17,6 +17,7 @@ sockex2-objs := bpf_load.o libbpf.o sockex2_user.o
 always := $(hostprogs-y)
 always += sockex1_kern.o
 always += sockex2_kern.o
+always += tcbpf1_kern.o
 
 HOSTCFLAGS += -I$(objtree)/usr/include
 
diff --git a/samples/bpf/bpf_helpers.h b/samples/bpf/bpf_helpers.h
index ca0333146006..72540ec1f003 100644
--- a/samples/bpf/bpf_helpers.h
+++ b/samples/bpf/bpf_helpers.h
@@ -37,4 +37,11 @@ struct bpf_map_def {
 	unsigned int max_entries;
 };
 
+static int (*bpf_skb_store_bytes)(void *ctx, int off, void *from, int len, int flags) =
+	(void *) BPF_FUNC_skb_store_bytes;
+static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flags) =
+	(void *) BPF_FUNC_l3_csum_replace;
+static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) =
+	(void *) BPF_FUNC_l4_csum_replace;
+
 #endif
diff --git a/samples/bpf/tcbpf1_kern.c b/samples/bpf/tcbpf1_kern.c
new file mode 100644
index 000000000000..7cf3f42a6e39
--- /dev/null
+++ b/samples/bpf/tcbpf1_kern.c
@@ -0,0 +1,71 @@
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/if_ether.h>
+#include <uapi/linux/if_packet.h>
+#include <uapi/linux/ip.h>
+#include <uapi/linux/in.h>
+#include <uapi/linux/tcp.h>
+#include "bpf_helpers.h"
+
+/* compiler workaround */
+#define _htonl __builtin_bswap32
+
+static inline void set_dst_mac(struct __sk_buff *skb, char *mac)
+{
+	bpf_skb_store_bytes(skb, 0, mac, ETH_ALEN, 1);
+}
+
+/* use 1 below for ingress qdisc and 0 for egress */
+#if 0
+#undef ETH_HLEN
+#define ETH_HLEN 0
+#endif
+
+#define IP_CSUM_OFF (ETH_HLEN + offsetof(struct iphdr, check))
+#define TOS_OFF (ETH_HLEN + offsetof(struct iphdr, tos))
+
+static inline void set_ip_tos(struct __sk_buff *skb, __u8 new_tos)
+{
+	__u8 old_tos = load_byte(skb, TOS_OFF);
+
+	bpf_l3_csum_replace(skb, IP_CSUM_OFF, htons(old_tos), htons(new_tos), 2);
+	bpf_skb_store_bytes(skb, TOS_OFF, &new_tos, sizeof(new_tos), 0);
+}
+
+#define TCP_CSUM_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, check))
+#define IP_SRC_OFF (ETH_HLEN + offsetof(struct iphdr, saddr))
+
+#define IS_PSEUDO 0x10
+
+static inline void set_tcp_ip_src(struct __sk_buff *skb, __u32 new_ip)
+{
+	__u32 old_ip = _htonl(load_word(skb, IP_SRC_OFF));
+
+	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_ip, new_ip, IS_PSEUDO | sizeof(new_ip));
+	bpf_l3_csum_replace(skb, IP_CSUM_OFF, old_ip, new_ip, sizeof(new_ip));
+	bpf_skb_store_bytes(skb, IP_SRC_OFF, &new_ip, sizeof(new_ip), 0);
+}
+
+#define TCP_DPORT_OFF (ETH_HLEN + sizeof(struct iphdr) + offsetof(struct tcphdr, dest))
+static inline void set_tcp_dest_port(struct __sk_buff *skb, __u16 new_port)
+{
+	__u16 old_port = htons(load_half(skb, TCP_DPORT_OFF));
+
+	bpf_l4_csum_replace(skb, TCP_CSUM_OFF, old_port, new_port, sizeof(new_port));
+	bpf_skb_store_bytes(skb, TCP_DPORT_OFF, &new_port, sizeof(new_port), 0);
+}
+
+SEC("classifier")
+int bpf_prog1(struct __sk_buff *skb)
+{
+	__u8 proto = load_byte(skb, ETH_HLEN + offsetof(struct iphdr, protocol));
+	long *value;
+
+	if (proto == IPPROTO_TCP) {
+		set_ip_tos(skb, 8);
+		set_tcp_ip_src(skb, 0xA010101);
+		set_tcp_dest_port(skb, 5001);
+	}
+
+	return 0;
+}
+char _license[] SEC("license") = "GPL";