Merge branch 'bpf-xfrm-states'

Eyal Birger says:

====================
This patchset adds support for fetching XFRM state information from
an eBPF program called from TC.

The first patch introduces a helper for fetching an XFRM state from the
skb's secpath. The XFRM state is modeled using a new virtual struct which
contains the SPI, peer address, and reqid values of the state; This struct
can be extended in the future to provide additional state information.

The second patch adds a test example in test_tunnel_bpf.sh. The sample
validates the correct extraction of state information by the eBPF program.

v3:
  - Kept SPI and peer IPv4 address in state in network byte order
    following suggestion from Alexei Starovoitov
v2:
  - Fixed two comments by Daniel Borkmann:
    - disallow reserved flags in helper call
    - avoid compiling in helper code when CONFIG_XFRM is off
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

include/uapi/linux/bpf.h

@@ -774,6 +774,15 @@ union bpf_attr {
  *     @xdp_md: pointer to xdp_md
  *     @delta: A negative integer to be added to xdp_md.data_end
  *     Return: 0 on success or negative on error
+ *
+ * int bpf_skb_get_xfrm_state(skb, index, xfrm_state, size, flags)
+ *     retrieve XFRM state
+ *     @skb: pointer to skb
+ *     @index: index of the xfrm state in the secpath
+ *     @key: pointer to 'struct bpf_xfrm_state'
+ *     @size: size of 'struct bpf_xfrm_state'
+ *     @flags: room for future extensions
+ *     Return: 0 on success or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -841,7 +850,8 @@ union bpf_attr {
 	FN(msg_cork_bytes),		\
 	FN(msg_pull_data),		\
 	FN(bind),			\
-	FN(xdp_adjust_tail),
+	FN(xdp_adjust_tail),		\
+	FN(skb_get_xfrm_state),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -947,6 +957,19 @@ struct bpf_tunnel_key {
 	__u32 tunnel_label;
 };
 
+/* user accessible mirror of in-kernel xfrm_state.
+ * new fields can only be added to the end of this structure
+ */
+struct bpf_xfrm_state {
+	__u32 reqid;
+	__u32 spi;	/* Stored in network byte order */
+	__u16 family;
+	union {
+		__u32 remote_ipv4;	/* Stored in network byte order */
+		__u32 remote_ipv6[4];	/* Stored in network byte order */
+	};
+};
+
 /* Generic BPF return codes which all BPF program types may support.
  * The values are binary compatible with their TC_ACT_* counter-part to
  * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT

net/core/filter.c

@@ -57,6 +57,7 @@
 #include <net/sock_reuseport.h>
 #include <net/busy_poll.h>
 #include <net/tcp.h>
+#include <net/xfrm.h>
 #include <linux/bpf_trace.h>
 
 /**
@@ -3743,6 +3744,49 @@ static const struct bpf_func_proto bpf_bind_proto = {
 	.arg3_type	= ARG_CONST_SIZE,
 };
 
+#ifdef CONFIG_XFRM
+BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index,
+	   struct bpf_xfrm_state *, to, u32, size, u64, flags)
+{
+	const struct sec_path *sp = skb_sec_path(skb);
+	const struct xfrm_state *x;
+
+	if (!sp || unlikely(index >= sp->len || flags))
+		goto err_clear;
+
+	x = sp->xvec[index];
+
+	if (unlikely(size != sizeof(struct bpf_xfrm_state)))
+		goto err_clear;
+
+	to->reqid = x->props.reqid;
+	to->spi = x->id.spi;
+	to->family = x->props.family;
+	if (to->family == AF_INET6) {
+		memcpy(to->remote_ipv6, x->props.saddr.a6,
+		       sizeof(to->remote_ipv6));
+	} else {
+		to->remote_ipv4 = x->props.saddr.a4;
+	}
+
+	return 0;
+err_clear:
+	memset(to, 0, size);
+	return -EINVAL;
+}
+
+static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = {
+	.func		= bpf_skb_get_xfrm_state,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+#endif
+
 static const struct bpf_func_proto *
 bpf_base_func_proto(enum bpf_func_id func_id)
 {
@@ -3884,6 +3928,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_socket_cookie_proto;
 	case BPF_FUNC_get_socket_uid:
 		return &bpf_get_socket_uid_proto;
+#ifdef CONFIG_XFRM
+	case BPF_FUNC_skb_get_xfrm_state:
+		return &bpf_skb_get_xfrm_state_proto;
+#endif
 	default:
 		return bpf_base_func_proto(func_id);
 	}

samples/bpf/tcbpf2_kern.c

@@ -593,4 +593,20 @@ int _ip6ip6_get_tunnel(struct __sk_buff *skb)
 	return TC_ACT_OK;
 }
 
+SEC("xfrm_get_state")
+int _xfrm_get_state(struct __sk_buff *skb)
+{
+	struct bpf_xfrm_state x;
+	char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n";
+	int ret;
+
+	ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0);
+	if (ret < 0)
+		return TC_ACT_OK;
+
+	bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi),
+			 bpf_ntohl(x.remote_ipv4));
+	return TC_ACT_OK;
+}
+
 char _license[] SEC("license") = "GPL";

samples/bpf/test_tunnel_bpf.sh

@@ -155,6 +155,57 @@ function add_ipip_tunnel {
 	ip addr add dev $DEV 10.1.1.200/24
 }
 
+function setup_xfrm_tunnel {
+	auth=0x$(printf '1%.0s' {1..40})
+	enc=0x$(printf '2%.0s' {1..32})
+	spi_in_to_out=0x1
+	spi_out_to_in=0x2
+	# in namespace
+	# in -> out
+	ip netns exec at_ns0 \
+		ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
+			spi $spi_in_to_out reqid 1 mode tunnel \
+			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+	ip netns exec at_ns0 \
+		ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \
+		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
+		mode tunnel
+	# out -> in
+	ip netns exec at_ns0 \
+		ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
+			spi $spi_out_to_in reqid 2 mode tunnel \
+			auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc
+	ip netns exec at_ns0 \
+		ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \
+		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
+		mode tunnel
+	# address & route
+	ip netns exec at_ns0 \
+		ip addr add dev veth0 10.1.1.100/32
+	ip netns exec at_ns0 \
+		ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \
+			src 10.1.1.100
+
+	# out of namespace
+	# in -> out
+	ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \
+		spi $spi_in_to_out reqid 1 mode tunnel \
+		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
+	ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \
+		tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \
+		mode tunnel
+	# out -> in
+	ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \
+		spi $spi_out_to_in reqid 2 mode tunnel \
+		auth-trunc 'hmac(sha1)' $auth 96  enc 'cbc(aes)' $enc
+	ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \
+		tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \
+		mode tunnel
+	# address & route
+	ip addr add dev veth1 10.1.1.200/32
+	ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200
+}
+
 function attach_bpf {
 	DEV=$1
 	SET_TUNNEL=$2
@@ -278,6 +329,22 @@ function test_ipip {
 	cleanup
 }
 
+function test_xfrm_tunnel {
+	config_device
+        tcpdump -nei veth1 ip &
+	output=$(mktemp)
+	cat /sys/kernel/debug/tracing/trace_pipe | tee $output &
+        setup_xfrm_tunnel
+	tc qdisc add dev veth1 clsact
+	tc filter add dev veth1 proto ip ingress bpf da obj tcbpf2_kern.o \
+		sec xfrm_get_state
+	ip netns exec at_ns0 ping -c 1 10.1.1.200
+	grep "reqid 1" $output
+	grep "spi 0x1" $output
+	grep "remote ip 0xac100164" $output
+	cleanup
+}
+
 function cleanup {
 	set +ex
 	pkill iperf
@@ -291,6 +358,8 @@ function cleanup {
 	ip link del geneve11
 	ip link del erspan11
 	ip link del ip6erspan11
+	ip x s flush
+	ip x p flush
 	pkill tcpdump
 	pkill cat
 	set -ex
@@ -316,4 +385,6 @@ echo "Testing GENEVE tunnel..."
 test_geneve
 echo "Testing IPIP tunnel..."
 test_ipip
+echo "Testing IPSec tunnel..."
+test_xfrm_tunnel
 echo "*** PASS ***"

tools/include/uapi/linux/bpf.h

@@ -774,6 +774,15 @@ union bpf_attr {
  *     @xdp_md: pointer to xdp_md
  *     @delta: A negative integer to be added to xdp_md.data_end
  *     Return: 0 on success or negative on error
+ *
+ * int bpf_skb_get_xfrm_state(skb, index, xfrm_state, size, flags)
+ *     retrieve XFRM state
+ *     @skb: pointer to skb
+ *     @index: index of the xfrm state in the secpath
+ *     @key: pointer to 'struct bpf_xfrm_state'
+ *     @size: size of 'struct bpf_xfrm_state'
+ *     @flags: room for future extensions
+ *     Return: 0 on success or negative error
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -841,7 +850,8 @@ union bpf_attr {
 	FN(msg_cork_bytes),		\
 	FN(msg_pull_data),		\
 	FN(bind),			\
-	FN(xdp_adjust_tail),
+	FN(xdp_adjust_tail),		\
+	FN(skb_get_xfrm_state),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call
@@ -946,6 +956,19 @@ struct bpf_tunnel_key {
 	__u32 tunnel_label;
 };
 
+/* user accessible mirror of in-kernel xfrm_state.
+ * new fields can only be added to the end of this structure
+ */
+struct bpf_xfrm_state {
+	__u32 reqid;
+	__u32 spi;	/* Stored in network byte order */
+	__u16 family;
+	union {
+		__u32 remote_ipv4;	/* Stored in network byte order */
+		__u32 remote_ipv6[4];	/* Stored in network byte order */
+	};
+};
+
 /* Generic BPF return codes which all BPF program types may support.
  * The values are binary compatible with their TC_ACT_* counter-part to
  * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT

tools/testing/selftests/bpf/bpf_helpers.h

@@ -98,7 +98,9 @@ static int (*bpf_bind)(void *ctx, void *addr, int addr_len) =
 	(void *) BPF_FUNC_bind;
 static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) =
 	(void *) BPF_FUNC_xdp_adjust_tail;
-
+static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state,
+				     int size, int flags) =
+	(void *) BPF_FUNC_skb_get_xfrm_state;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions