Merge branch 'bpf_tcp_check_syncookie'

Lorenz Bauer says:

====================
This series adds the necessary helpers to determine wheter a given
(encapsulated) TCP packet belongs to a connection known to the network stack.

* bpf_skc_lookup_tcp gives access to request and timewait sockets
* bpf_tcp_check_syncookie identifies the final 3WHS ACK when syncookies
  are enabled

The goal is to be able to implement load-balancing approaches like
glb-director [1] or Beamer [2] in pure eBPF. Specifically, we'd like to replace
the functionality of the glb-redirect kernel module [3] by an XDP program or
tc classifier.

Changes in v3:
* Fix missing check for ip4->ihl
* Only cast to unsigned long in BPF_CALLs

Changes in v2:
* Rename bpf_sk_check_syncookie to bpf_tcp_check_syncookie.
* Add bpf_skc_lookup_tcp. Without it bpf_tcp_check_syncookie doesn't make sense.
* Check tcp_synq_no_recent_overflow() in bpf_tcp_check_syncookie.
* Check th->syn in bpf_tcp_check_syncookie.
* Require CONFIG_IPV6 to be a built in.

1: https://github.com/github/glb-director
2: https://www.usenix.org/conference/nsdi18/presentation/olteanu
3: https://github.com/github/glb-director/tree/master/src/glb-redirect
====================
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -205,6 +205,7 @@ enum bpf_return_type {
 	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
 	RET_PTR_TO_SOCKET_OR_NULL,	/* returns a pointer to a socket or NULL */
 	RET_PTR_TO_TCP_SOCK_OR_NULL,	/* returns a pointer to a tcp_sock or NULL */
+	RET_PTR_TO_SOCK_COMMON_OR_NULL,	/* returns a pointer to a sock_common or NULL */
 };
 
 /* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs

include/uapi/linux/bpf.h

@@ -2431,6 +2431,38 @@ union bpf_attr {
  *	Return
  *		A **struct bpf_sock** pointer on success, or **NULL** in
  *		case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ *		This function is identical to bpf_sk_lookup_tcp, except that it
+ *		also returns timewait or request sockets. Use bpf_sk_fullsock
+ *		or bpf_tcp_socket to access the full structure.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
+ *
+ * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * 	Description
+ * 		Check whether iph and th contain a valid SYN cookie ACK for
+ * 		the listening socket in sk.
+ *
+ * 		iph points to the start of the IPv4 or IPv6 header, while
+ * 		iph_len contains sizeof(struct iphdr) or sizeof(struct ip6hdr).
+ *
+ * 		th points to the start of the TCP header, while th_len contains
+ * 		sizeof(struct tcphdr).
+ *
+ * 	Return
+ * 		0 if iph and th are a valid SYN cookie ACK, or a negative error
+ * 		otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2531,7 +2563,9 @@ union bpf_attr {
 	FN(sk_fullsock),		\
 	FN(tcp_sock),			\
 	FN(skb_ecn_set_ce),		\
-	FN(get_listener_sock),
+	FN(get_listener_sock),		\
+	FN(skc_lookup_tcp),		\
+	FN(tcp_check_syncookie),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/verifier.c

@@ -369,7 +369,8 @@ static bool is_release_function(enum bpf_func_id func_id)
 static bool is_acquire_function(enum bpf_func_id func_id)
 {
 	return func_id == BPF_FUNC_sk_lookup_tcp ||
-		func_id == BPF_FUNC_sk_lookup_udp;
+		func_id == BPF_FUNC_sk_lookup_udp ||
+		func_id == BPF_FUNC_skc_lookup_tcp;
 }
 
 static bool is_ptr_cast_function(enum bpf_func_id func_id)
@@ -3147,19 +3148,11 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 	} else if (fn->ret_type == RET_PTR_TO_SOCKET_OR_NULL) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_SOCKET_OR_NULL;
-		if (is_acquire_function(func_id)) {
-			int id = acquire_reference_state(env, insn_idx);
-
-			if (id < 0)
-				return id;
-			/* For mark_ptr_or_null_reg() */
-			regs[BPF_REG_0].id = id;
-			/* For release_reference() */
-			regs[BPF_REG_0].ref_obj_id = id;
-		} else {
-			/* For mark_ptr_or_null_reg() */
-			regs[BPF_REG_0].id = ++env->id_gen;
-		}
+		regs[BPF_REG_0].id = ++env->id_gen;
+	} else if (fn->ret_type == RET_PTR_TO_SOCK_COMMON_OR_NULL) {
+		mark_reg_known_zero(env, regs, BPF_REG_0);
+		regs[BPF_REG_0].type = PTR_TO_SOCK_COMMON_OR_NULL;
+		regs[BPF_REG_0].id = ++env->id_gen;
 	} else if (fn->ret_type == RET_PTR_TO_TCP_SOCK_OR_NULL) {
 		mark_reg_known_zero(env, regs, BPF_REG_0);
 		regs[BPF_REG_0].type = PTR_TO_TCP_SOCK_OR_NULL;
@@ -3170,9 +3163,19 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn
 		return -EINVAL;
 	}
 
-	if (is_ptr_cast_function(func_id))
+	if (is_ptr_cast_function(func_id)) {
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = meta.ref_obj_id;
+	} else if (is_acquire_function(func_id)) {
+		int id = acquire_reference_state(env, insn_idx);
+
+		if (id < 0)
+			return id;
+		/* For mark_ptr_or_null_reg() */
+		regs[BPF_REG_0].id = id;
+		/* For release_reference() */
+		regs[BPF_REG_0].ref_obj_id = id;
+	}
 
 	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
 

net/core/filter.c

@@ -5156,15 +5156,15 @@ static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple,
 	return sk;
 }
 
-/* bpf_sk_lookup performs the core lookup for different types of sockets,
+/* bpf_skc_lookup performs the core lookup for different types of sockets,
  * taking a reference on the socket if it doesn't have the flag SOCK_RCU_FREE.
  * Returns the socket as an 'unsigned long' to simplify the casting in the
  * callers to satisfy BPF_CALL declarations.
  */
-static unsigned long
-__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
-		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
-		u64 flags)
+static struct sock *
+__bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+		 struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+		 u64 flags)
 {
 	struct sock *sk = NULL;
 	u8 family = AF_UNSPEC;
@@ -5192,15 +5192,27 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		put_net(net);
 	}
 
+out:
+	return sk;
+}
+
+static struct sock *
+__bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+		struct net *caller_net, u32 ifindex, u8 proto, u64 netns_id,
+		u64 flags)
+{
+	struct sock *sk = __bpf_skc_lookup(skb, tuple, len, caller_net,
+					   ifindex, proto, netns_id, flags);
+
 	if (sk)
 		sk = sk_to_full_sk(sk);
-out:
-	return (unsigned long) sk;
+
+	return sk;
 }
 
-static unsigned long
-bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
-	      u8 proto, u64 netns_id, u64 flags)
+static struct sock *
+bpf_skc_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	       u8 proto, u64 netns_id, u64 flags)
 {
 	struct net *caller_net;
 	int ifindex;
@@ -5213,14 +5225,47 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
 		ifindex = 0;
 	}
 
-	return __bpf_sk_lookup(skb, tuple, len, caller_net, ifindex,
-			      proto, netns_id, flags);
+	return __bpf_skc_lookup(skb, tuple, len, caller_net, ifindex, proto,
+				netns_id, flags);
+}
+
+static struct sock *
+bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len,
+	      u8 proto, u64 netns_id, u64 flags)
+{
+	struct sock *sk = bpf_skc_lookup(skb, tuple, len, proto, netns_id,
+					 flags);
+
+	if (sk)
+		sk = sk_to_full_sk(sk);
+
+	return sk;
 }
 
+BPF_CALL_5(bpf_skc_lookup_tcp, struct sk_buff *, skb,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return (unsigned long)bpf_skc_lookup(skb, tuple, len, IPPROTO_TCP,
+					     netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_skc_lookup_tcp_proto = {
+	.func		= bpf_skc_lookup_tcp,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_sk_lookup_tcp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP, netns_id, flags);
+	return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_TCP,
+					    netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
@@ -5238,7 +5283,8 @@ static const struct bpf_func_proto bpf_sk_lookup_tcp_proto = {
 BPF_CALL_5(bpf_sk_lookup_udp, struct sk_buff *, skb,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP, netns_id, flags);
+	return (unsigned long)bpf_sk_lookup(skb, tuple, len, IPPROTO_UDP,
+					    netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sk_lookup_udp_proto = {
@@ -5273,8 +5319,9 @@ BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx,
 	struct net *caller_net = dev_net(ctx->rxq->dev);
 	int ifindex = ctx->rxq->dev->ifindex;
 
-	return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
-			      IPPROTO_UDP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
+					      ifindex, IPPROTO_UDP, netns_id,
+					      flags);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
@@ -5289,14 +5336,38 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_udp_proto = {
 	.arg5_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_5(bpf_xdp_skc_lookup_tcp, struct xdp_buff *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
+{
+	struct net *caller_net = dev_net(ctx->rxq->dev);
+	int ifindex = ctx->rxq->dev->ifindex;
+
+	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len, caller_net,
+					       ifindex, IPPROTO_TCP, netns_id,
+					       flags);
+}
+
+static const struct bpf_func_proto bpf_xdp_skc_lookup_tcp_proto = {
+	.func           = bpf_xdp_skc_lookup_tcp,
+	.gpl_only       = false,
+	.pkt_access     = true,
+	.ret_type       = RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type      = ARG_PTR_TO_CTX,
+	.arg2_type      = ARG_PTR_TO_MEM,
+	.arg3_type      = ARG_CONST_SIZE,
+	.arg4_type      = ARG_ANYTHING,
+	.arg5_type      = ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_xdp_sk_lookup_tcp, struct xdp_buff *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u32, netns_id, u64, flags)
 {
 	struct net *caller_net = dev_net(ctx->rxq->dev);
 	int ifindex = ctx->rxq->dev->ifindex;
 
-	return __bpf_sk_lookup(NULL, tuple, len, caller_net, ifindex,
-			      IPPROTO_TCP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len, caller_net,
+					      ifindex, IPPROTO_TCP, netns_id,
+					      flags);
 }
 
 static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
@@ -5311,11 +5382,31 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = {
 	.arg5_type      = ARG_ANYTHING,
 };
 
+BPF_CALL_5(bpf_sock_addr_skc_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
+	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
+{
+	return (unsigned long)__bpf_skc_lookup(NULL, tuple, len,
+					       sock_net(ctx->sk), 0,
+					       IPPROTO_TCP, netns_id, flags);
+}
+
+static const struct bpf_func_proto bpf_sock_addr_skc_lookup_tcp_proto = {
+	.func		= bpf_sock_addr_skc_lookup_tcp,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_SOCK_COMMON_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_CTX,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_ANYTHING,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
-			       IPPROTO_TCP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
+					      sock_net(ctx->sk), 0, IPPROTO_TCP,
+					      netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
@@ -5332,8 +5423,9 @@ static const struct bpf_func_proto bpf_sock_addr_sk_lookup_tcp_proto = {
 BPF_CALL_5(bpf_sock_addr_sk_lookup_udp, struct bpf_sock_addr_kern *, ctx,
 	   struct bpf_sock_tuple *, tuple, u32, len, u64, netns_id, u64, flags)
 {
-	return __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,
-			       IPPROTO_UDP, netns_id, flags);
+	return (unsigned long)__bpf_sk_lookup(NULL, tuple, len,
+					      sock_net(ctx->sk), 0, IPPROTO_UDP,
+					      netns_id, flags);
 }
 
 static const struct bpf_func_proto bpf_sock_addr_sk_lookup_udp_proto = {
@@ -5461,6 +5553,74 @@ static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = {
 	.ret_type       = RET_INTEGER,
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
+
+BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len,
+	   struct tcphdr *, th, u32, th_len)
+{
+#ifdef CONFIG_SYN_COOKIES
+	u32 cookie;
+	int ret;
+
+	if (unlikely(th_len < sizeof(*th)))
+		return -EINVAL;
+
+	/* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */
+	if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN)
+		return -EINVAL;
+
+	if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies)
+		return -EINVAL;
+
+	if (!th->ack || th->rst || th->syn)
+		return -ENOENT;
+
+	if (tcp_synq_no_recent_overflow(sk))
+		return -ENOENT;
+
+	cookie = ntohl(th->ack_seq) - 1;
+
+	switch (sk->sk_family) {
+	case AF_INET:
+		if (unlikely(iph_len < sizeof(struct iphdr)))
+			return -EINVAL;
+
+		ret = __cookie_v4_check((struct iphdr *)iph, th, cookie);
+		break;
+
+#if IS_BUILTIN(CONFIG_IPV6)
+	case AF_INET6:
+		if (unlikely(iph_len < sizeof(struct ipv6hdr)))
+			return -EINVAL;
+
+		ret = __cookie_v6_check((struct ipv6hdr *)iph, th, cookie);
+		break;
+#endif /* CONFIG_IPV6 */
+
+	default:
+		return -EPROTONOSUPPORT;
+	}
+
+	if (ret > 0)
+		return 0;
+
+	return -ENOENT;
+#else
+	return -ENOTSUPP;
+#endif
+}
+
+static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = {
+	.func		= bpf_tcp_check_syncookie,
+	.gpl_only	= true,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_SOCK_COMMON,
+	.arg2_type	= ARG_PTR_TO_MEM,
+	.arg3_type	= ARG_CONST_SIZE,
+	.arg4_type	= ARG_PTR_TO_MEM,
+	.arg5_type	= ARG_CONST_SIZE,
+};
+
 #endif /* CONFIG_INET */
 
 bool bpf_helper_changes_pkt_data(void *func)
@@ -5586,6 +5746,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sock_addr_sk_lookup_udp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_sock_addr_skc_lookup_tcp_proto;
 #endif /* CONFIG_INET */
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5719,6 +5881,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_tcp_sock_proto;
 	case BPF_FUNC_get_listener_sock:
 		return &bpf_get_listener_sock_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_skc_lookup_tcp_proto;
+	case BPF_FUNC_tcp_check_syncookie:
+		return &bpf_tcp_check_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5754,6 +5920,10 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_xdp_sk_lookup_tcp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_xdp_skc_lookup_tcp_proto;
+	case BPF_FUNC_tcp_check_syncookie:
+		return &bpf_tcp_check_syncookie_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);
@@ -5846,6 +6016,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_lookup_udp_proto;
 	case BPF_FUNC_sk_release:
 		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_skc_lookup_tcp_proto;
 #endif
 	default:
 		return bpf_base_func_proto(func_id);

tools/include/uapi/linux/bpf.h

@@ -2431,6 +2431,38 @@ union bpf_attr {
  *	Return
  *		A **struct bpf_sock** pointer on success, or **NULL** in
  *		case of failure.
+ *
+ * struct bpf_sock *bpf_skc_lookup_tcp(void *ctx, struct bpf_sock_tuple *tuple, u32 tuple_size, u64 netns, u64 flags)
+ *	Description
+ *		Look for TCP socket matching *tuple*, optionally in a child
+ *		network namespace *netns*. The return value must be checked,
+ *		and if non-**NULL**, released via **bpf_sk_release**\ ().
+ *
+ *		This function is identical to bpf_sk_lookup_tcp, except that it
+ *		also returns timewait or request sockets. Use bpf_sk_fullsock
+ *		or bpf_tcp_socket to access the full structure.
+ *
+ *		This helper is available only if the kernel was compiled with
+ *		**CONFIG_NET** configuration option.
+ *	Return
+ *		Pointer to **struct bpf_sock**, or **NULL** in case of failure.
+ *		For sockets with reuseport option, the **struct bpf_sock**
+ *		result is from **reuse->socks**\ [] using the hash of the tuple.
+ *
+ * int bpf_tcp_check_syncookie(struct bpf_sock *sk, void *iph, u32 iph_len, struct tcphdr *th, u32 th_len)
+ * 	Description
+ * 		Check whether iph and th contain a valid SYN cookie ACK for
+ * 		the listening socket in sk.
+ *
+ * 		iph points to the start of the IPv4 or IPv6 header, while
+ * 		iph_len contains sizeof(struct iphdr) or sizeof(struct ip6hdr).
+ *
+ * 		th points to the start of the TCP header, while th_len contains
+ * 		sizeof(struct tcphdr).
+ *
+ * 	Return
+ * 		0 if iph and th are a valid SYN cookie ACK, or a negative error
+ * 		otherwise.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -2531,7 +2563,9 @@ union bpf_attr {
 	FN(sk_fullsock),		\
 	FN(tcp_sock),			\
 	FN(skb_ecn_set_ce),		\
-	FN(get_listener_sock),
+	FN(get_listener_sock),		\
+	FN(skc_lookup_tcp),		\
+	FN(tcp_check_syncookie),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

tools/testing/selftests/bpf/.gitignore

@@ -30,4 +30,5 @@ test_netcnt
 test_section_names
 test_tcpnotify_user
 test_libbpf
+test_tcp_check_syncookie_user
 alu32

tools/testing/selftests/bpf/Makefile

@@ -51,7 +51,8 @@ TEST_PROGS := test_kmod.sh \
 	test_skb_cgroup_id.sh \
 	test_flow_dissector.sh \
 	test_xdp_vlan.sh \
-	test_lwt_ip_encap.sh
+	test_lwt_ip_encap.sh \
+	test_tcp_check_syncookie.sh
 
 TEST_PROGS_EXTENDED := with_addr.sh \
 	with_tunnels.sh \
@@ -60,7 +61,7 @@ TEST_PROGS_EXTENDED := with_addr.sh \
 
 # Compile but not part of 'make run_tests'
 TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr test_skb_cgroup_id_user \
-	flow_dissector_load test_flow_dissector
+	flow_dissector_load test_flow_dissector test_tcp_check_syncookie_user
 
 include ../lib.mk
 

tools/testing/selftests/bpf/bpf_helpers.h

@@ -159,6 +159,11 @@ static struct bpf_sock *(*bpf_sk_lookup_tcp)(void *ctx,
 					     int size, unsigned long long netns_id,
 					     unsigned long long flags) =
 	(void *) BPF_FUNC_sk_lookup_tcp;
+static struct bpf_sock *(*bpf_skc_lookup_tcp)(void *ctx,
+					     struct bpf_sock_tuple *tuple,
+					     int size, unsigned long long netns_id,
+					     unsigned long long flags) =
+	(void *) BPF_FUNC_skc_lookup_tcp;
 static struct bpf_sock *(*bpf_sk_lookup_udp)(void *ctx,
 					     struct bpf_sock_tuple *tuple,
 					     int size, unsigned long long netns_id,
@@ -184,6 +189,9 @@ static struct bpf_sock *(*bpf_get_listener_sock)(struct bpf_sock *sk) =
 	(void *) BPF_FUNC_get_listener_sock;
 static int (*bpf_skb_ecn_set_ce)(void *ctx) =
 	(void *) BPF_FUNC_skb_ecn_set_ce;
+static int (*bpf_tcp_check_syncookie)(struct bpf_sock *sk,
+	    void *ip, int ip_len, void *tcp, int tcp_len) =
+	(void *) BPF_FUNC_tcp_check_syncookie;
 
 /* llvm builtin functions that eBPF C program may use to
  * emit BPF_LD_ABS and BPF_LD_IND instructions

tools/testing/selftests/bpf/progs/test_tcp_check_syncookie_kern.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+// Copyright (c) 2019 Cloudflare
+
+#include <string.h>
+
+#include <linux/bpf.h>
+#include <linux/pkt_cls.h>
+#include <linux/if_ether.h>
+#include <linux/in.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <sys/socket.h>
+#include <linux/tcp.h>
+
+#include "bpf_helpers.h"
+#include "bpf_endian.h"
+
+struct bpf_map_def SEC("maps") results = {
+	.type = BPF_MAP_TYPE_ARRAY,
+	.key_size = sizeof(__u32),
+	.value_size = sizeof(__u64),
+	.max_entries = 1,
+};
+
+static __always_inline void check_syncookie(void *ctx, void *data,
+					    void *data_end)
+{
+	struct bpf_sock_tuple tup;
+	struct bpf_sock *sk;
+	struct ethhdr *ethh;
+	struct iphdr *ipv4h;
+	struct ipv6hdr *ipv6h;
+	struct tcphdr *tcph;
+	int ret;
+	__u32 key = 0;
+	__u64 value = 1;
+
+	ethh = data;
+	if (ethh + 1 > data_end)
+		return;
+
+	switch (bpf_ntohs(ethh->h_proto)) {
+	case ETH_P_IP:
+		ipv4h = data + sizeof(struct ethhdr);
+		if (ipv4h + 1 > data_end)
+			return;
+
+		if (ipv4h->ihl != 5)
+			return;
+
+		tcph = data + sizeof(struct ethhdr) + sizeof(struct iphdr);
+		if (tcph + 1 > data_end)
+			return;
+
+		tup.ipv4.saddr = ipv4h->saddr;
+		tup.ipv4.daddr = ipv4h->daddr;
+		tup.ipv4.sport = tcph->source;
+		tup.ipv4.dport = tcph->dest;
+
+		sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv4),
+					BPF_F_CURRENT_NETNS, 0);
+		if (!sk)
+			return;
+
+		if (sk->state != BPF_TCP_LISTEN)
+			goto release;
+
+		ret = bpf_tcp_check_syncookie(sk, ipv4h, sizeof(*ipv4h),
+					      tcph, sizeof(*tcph));
+		break;
+
+	case ETH_P_IPV6:
+		ipv6h = data + sizeof(struct ethhdr);
+		if (ipv6h + 1 > data_end)
+			return;
+
+		if (ipv6h->nexthdr != IPPROTO_TCP)
+			return;
+
+		tcph = data + sizeof(struct ethhdr) + sizeof(struct ipv6hdr);
+		if (tcph + 1 > data_end)
+			return;
+
+		memcpy(tup.ipv6.saddr, &ipv6h->saddr, sizeof(tup.ipv6.saddr));
+		memcpy(tup.ipv6.daddr, &ipv6h->daddr, sizeof(tup.ipv6.daddr));
+		tup.ipv6.sport = tcph->source;
+		tup.ipv6.dport = tcph->dest;
+
+		sk = bpf_skc_lookup_tcp(ctx, &tup, sizeof(tup.ipv6),
+					BPF_F_CURRENT_NETNS, 0);
+		if (!sk)
+			return;
+
+		if (sk->state != BPF_TCP_LISTEN)
+			goto release;
+
+		ret = bpf_tcp_check_syncookie(sk, ipv6h, sizeof(*ipv6h),
+					      tcph, sizeof(*tcph));
+		break;
+
+	default:
+		return;
+	}
+
+	if (ret == 0)
+		bpf_map_update_elem(&results, &key, &value, 0);
+
+release:
+	bpf_sk_release(sk);
+}
+
+SEC("clsact/check_syncookie")
+int check_syncookie_clsact(struct __sk_buff *skb)
+{
+	check_syncookie(skb, (void *)(long)skb->data,
+			(void *)(long)skb->data_end);
+	return TC_ACT_OK;
+}
+
+SEC("xdp/check_syncookie")
+int check_syncookie_xdp(struct xdp_md *ctx)
+{
+	check_syncookie(ctx, (void *)(long)ctx->data,
+			(void *)(long)ctx->data_end);
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/test_tcp_check_syncookie.sh

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# Copyright (c) 2018 Facebook
+# Copyright (c) 2019 Cloudflare
+
+set -eu
+
+wait_for_ip()
+{
+	local _i
+	printf "Wait for IP %s to become available " "$1"
+	for _i in $(seq ${MAX_PING_TRIES}); do
+		printf "."
+		if ns1_exec ping -c 1 -W 1 "$1" >/dev/null 2>&1; then
+			echo " OK"
+			return
+		fi
+		sleep 1
+	done
+	echo 1>&2 "ERROR: Timeout waiting for test IP to become available."
+	exit 1
+}
+
+get_prog_id()
+{
+	awk '/ id / {sub(/.* id /, "", $0); print($1)}'
+}
+
+ns1_exec()
+{
+	ip netns exec ns1 "$@"
+}
+
+setup()
+{
+	ip netns add ns1
+	ns1_exec ip link set lo up
+
+	ns1_exec sysctl -w net.ipv4.tcp_syncookies=2
+
+	wait_for_ip 127.0.0.1
+	wait_for_ip ::1
+}
+
+cleanup()
+{
+	ip netns del ns1 2>/dev/null || :
+}
+
+main()
+{
+	trap cleanup EXIT 2 3 6 15
+	setup
+
+	printf "Testing clsact..."
+	ns1_exec tc qdisc add dev "${TEST_IF}" clsact
+	ns1_exec tc filter add dev "${TEST_IF}" ingress \
+		bpf obj "${BPF_PROG_OBJ}" sec "${CLSACT_SECTION}" da
+
+	BPF_PROG_ID=$(ns1_exec tc filter show dev "${TEST_IF}" ingress | \
+		      get_prog_id)
+	ns1_exec "${PROG}" "${BPF_PROG_ID}"
+	ns1_exec tc qdisc del dev "${TEST_IF}" clsact
+
+	printf "Testing XDP..."
+	ns1_exec ip link set "${TEST_IF}" xdp \
+		object "${BPF_PROG_OBJ}" section "${XDP_SECTION}"
+	BPF_PROG_ID=$(ns1_exec ip link show "${TEST_IF}" | get_prog_id)
+	ns1_exec "${PROG}" "${BPF_PROG_ID}"
+}
+
+DIR=$(dirname $0)
+TEST_IF=lo
+MAX_PING_TRIES=5
+BPF_PROG_OBJ="${DIR}/test_tcp_check_syncookie_kern.o"
+CLSACT_SECTION="clsact/check_syncookie"
+XDP_SECTION="xdp/check_syncookie"
+BPF_PROG_ID=0
+PROG="${DIR}/test_tcp_check_syncookie_user"
+
+main

tools/testing/selftests/bpf/test_tcp_check_syncookie_user.c

+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Facebook
+// Copyright (c) 2019 Cloudflare
+
+#include <string.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <arpa/inet.h>
+#include <netinet/in.h>
+#include <sys/types.h>
+#include <sys/socket.h>
+
+#include <bpf/bpf.h>
+#include <bpf/libbpf.h>
+
+#include "bpf_rlimit.h"
+#include "cgroup_helpers.h"
+
+static int start_server(const struct sockaddr *addr, socklen_t len)
+{
+	int fd;
+
+	fd = socket(addr->sa_family, SOCK_STREAM, 0);
+	if (fd == -1) {
+		log_err("Failed to create server socket");
+		goto out;
+	}
+
+	if (bind(fd, addr, len) == -1) {
+		log_err("Failed to bind server socket");
+		goto close_out;
+	}
+
+	if (listen(fd, 128) == -1) {
+		log_err("Failed to listen on server socket");
+		goto close_out;
+	}
+
+	goto out;
+
+close_out:
+	close(fd);
+	fd = -1;
+out:
+	return fd;
+}
+
+static int connect_to_server(int server_fd)
+{
+	struct sockaddr_storage addr;
+	socklen_t len = sizeof(addr);
+	int fd = -1;
+
+	if (getsockname(server_fd, (struct sockaddr *)&addr, &len)) {
+		log_err("Failed to get server addr");
+		goto out;
+	}
+
+	fd = socket(addr.ss_family, SOCK_STREAM, 0);
+	if (fd == -1) {
+		log_err("Failed to create client socket");
+		goto out;
+	}
+
+	if (connect(fd, (const struct sockaddr *)&addr, len) == -1) {
+		log_err("Fail to connect to server");
+		goto close_out;
+	}
+
+	goto out;
+
+close_out:
+	close(fd);
+	fd = -1;
+out:
+	return fd;
+}
+
+static int get_map_fd_by_prog_id(int prog_id)
+{
+	struct bpf_prog_info info = {};
+	__u32 info_len = sizeof(info);
+	__u32 map_ids[1];
+	int prog_fd = -1;
+	int map_fd = -1;
+
+	prog_fd = bpf_prog_get_fd_by_id(prog_id);
+	if (prog_fd < 0) {
+		log_err("Failed to get fd by prog id %d", prog_id);
+		goto err;
+	}
+
+	info.nr_map_ids = 1;
+	info.map_ids = (__u64)(unsigned long)map_ids;
+
+	if (bpf_obj_get_info_by_fd(prog_fd, &info, &info_len)) {
+		log_err("Failed to get info by prog fd %d", prog_fd);
+		goto err;
+	}
+
+	if (!info.nr_map_ids) {
+		log_err("No maps found for prog fd %d", prog_fd);
+		goto err;
+	}
+
+	map_fd = bpf_map_get_fd_by_id(map_ids[0]);
+	if (map_fd < 0)
+		log_err("Failed to get fd by map id %d", map_ids[0]);
+err:
+	if (prog_fd >= 0)
+		close(prog_fd);
+	return map_fd;
+}
+
+static int run_test(int server_fd, int results_fd)
+{
+	int client = -1, srv_client = -1;
+	int ret = 0;
+	__u32 key = 0;
+	__u64 value = 0;
+
+	if (bpf_map_update_elem(results_fd, &key, &value, 0) < 0) {
+		log_err("Can't clear results");
+		goto err;
+	}
+
+	client = connect_to_server(server_fd);
+	if (client == -1)
+		goto err;
+
+	srv_client = accept(server_fd, NULL, 0);
+	if (srv_client == -1) {
+		log_err("Can't accept connection");
+		goto err;
+	}
+
+	if (bpf_map_lookup_elem(results_fd, &key, &value) < 0) {
+		log_err("Can't lookup result");
+		goto err;
+	}
+
+	if (value != 1) {
+		log_err("Didn't match syncookie: %llu", value);
+		goto err;
+	}
+
+	goto out;
+
+err:
+	ret = 1;
+out:
+	close(client);
+	close(srv_client);
+	return ret;
+}
+
+int main(int argc, char **argv)
+{
+	struct sockaddr_in addr4;
+	struct sockaddr_in6 addr6;
+	int server = -1;
+	int server_v6 = -1;
+	int results = -1;
+	int err = 0;
+
+	if (argc < 2) {
+		fprintf(stderr, "Usage: %s prog_id\n", argv[0]);
+		exit(1);
+	}
+
+	results = get_map_fd_by_prog_id(atoi(argv[1]));
+	if (results < 0) {
+		log_err("Can't get map");
+		goto err;
+	}
+
+	memset(&addr4, 0, sizeof(addr4));
+	addr4.sin_family = AF_INET;
+	addr4.sin_addr.s_addr = htonl(INADDR_LOOPBACK);
+	addr4.sin_port = 0;
+
+	memset(&addr6, 0, sizeof(addr6));
+	addr6.sin6_family = AF_INET6;
+	addr6.sin6_addr = in6addr_loopback;
+	addr6.sin6_port = 0;
+
+	server = start_server((const struct sockaddr *)&addr4, sizeof(addr4));
+	if (server == -1)
+		goto err;
+
+	server_v6 = start_server((const struct sockaddr *)&addr6,
+				 sizeof(addr6));
+	if (server_v6 == -1)
+		goto err;
+
+	if (run_test(server, results))
+		goto err;
+
+	if (run_test(server_v6, results))
+		goto err;
+
+	printf("ok\n");
+	goto out;
+err:
+	err = 1;
+out:
+	close(server);
+	close(server_v6);
+	close(results);
+	return err;
+}

tools/testing/selftests/bpf/test_verifier.c

@@ -198,7 +198,7 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 }
 
 /* BPF_SK_LOOKUP contains 13 instructions, if you need to fix up maps */
-#define BPF_SK_LOOKUP							\
+#define BPF_SK_LOOKUP(func)						\
 	/* struct bpf_sock_tuple tuple = {} */				\
 	BPF_MOV64_IMM(BPF_REG_2, 0),					\
 	BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_2, -8),			\
@@ -207,13 +207,13 @@ static void bpf_fill_rand_ld_dw(struct bpf_test *self)
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -32),		\
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -40),		\
 	BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -48),		\
-	/* sk = sk_lookup_tcp(ctx, &tuple, sizeof tuple, 0, 0) */	\
+	/* sk = func(ctx, &tuple, sizeof tuple, 0, 0) */		\
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),				\
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -48),				\
 	BPF_MOV64_IMM(BPF_REG_3, sizeof(struct bpf_sock_tuple)),	\
 	BPF_MOV64_IMM(BPF_REG_4, 0),					\
 	BPF_MOV64_IMM(BPF_REG_5, 0),					\
-	BPF_EMIT_CALL(BPF_FUNC_sk_lookup_tcp)
+	BPF_EMIT_CALL(BPF_FUNC_ ## func)
 
 /* BPF_DIRECT_PKT_R2 contains 7 instructions, it initializes default return
  * value into 0 and does necessary preparation for direct packet access

tools/testing/selftests/bpf/verifier/ref_tracking.c

 {
 	"reference tracking: leak potential reference",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.errstr = "Unreleased reference",
+	.result = REJECT,
+},
+{
+	"reference tracking: leak potential reference to sock_common",
+	.insns = {
+	BPF_SK_LOOKUP(skc_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0), /* leak reference */
 	BPF_EXIT_INSN(),
 	},
@@ -12,7 +23,7 @@
 {
 	"reference tracking: leak potential reference on stack",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
 	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
@@ -26,7 +37,7 @@
 {
 	"reference tracking: leak potential reference on stack 2",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
 	BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_0, 0),
@@ -41,7 +52,18 @@
 {
 	"reference tracking: zero potential reference",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.errstr = "Unreleased reference",
+	.result = REJECT,
+},
+{
+	"reference tracking: zero potential reference to sock_common",
+	.insns = {
+	BPF_SK_LOOKUP(skc_lookup_tcp),
 	BPF_MOV64_IMM(BPF_REG_0, 0), /* leak reference */
 	BPF_EXIT_INSN(),
 	},
@@ -52,7 +74,7 @@
 {
 	"reference tracking: copy and zero potential references",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_MOV64_IMM(BPF_REG_7, 0), /* leak reference */
@@ -65,7 +87,7 @@
 {
 	"reference tracking: release reference without check",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	/* reference in r0 may be NULL */
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_2, 0),
@@ -76,10 +98,36 @@
 	.errstr = "type=sock_or_null expected=sock",
 	.result = REJECT,
 },
+{
+	"reference tracking: release reference to sock_common without check",
+	.insns = {
+	BPF_SK_LOOKUP(skc_lookup_tcp),
+	/* reference in r0 may be NULL */
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_MOV64_IMM(BPF_REG_2, 0),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.errstr = "type=sock_common_or_null expected=sock",
+	.result = REJECT,
+},
 {
 	"reference tracking: release reference",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
+	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+	BPF_EMIT_CALL(BPF_FUNC_sk_release),
+	BPF_EXIT_INSN(),
+	},
+	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+	.result = ACCEPT,
+},
+{
+	"reference tracking: release reference to sock_common",
+	.insns = {
+	BPF_SK_LOOKUP(skc_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
 	BPF_EMIT_CALL(BPF_FUNC_sk_release),
@@ -91,7 +139,7 @@
 {
 	"reference tracking: release reference 2",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
@@ -104,7 +152,7 @@
 {
 	"reference tracking: release reference twice",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
@@ -120,7 +168,7 @@
 {
 	"reference tracking: release reference twice inside branch",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3), /* goto end */
@@ -147,7 +195,7 @@
 	BPF_EXIT_INSN(),
 	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
 		    offsetof(struct __sk_buff, mark)),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 1), /* mark == 0? */
 	/* Leak reference in R0 */
 	BPF_EXIT_INSN(),
@@ -175,7 +223,7 @@
 	BPF_EXIT_INSN(),
 	BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_2,
 		    offsetof(struct __sk_buff, mark)),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_6, 0, 4), /* mark == 0? */
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2), /* sk NULL? */
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
@@ -193,7 +241,7 @@
 {
 	"reference tracking in call: free reference in subprog",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
@@ -211,7 +259,7 @@
 {
 	"reference tracking in call: free reference in subprog and outside",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0), /* unchecked reference */
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
@@ -241,7 +289,7 @@
 
 	/* subprog 1 */
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_4),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	/* spill unchecked sk_ptr into stack of caller */
 	BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
@@ -262,7 +310,7 @@
 	BPF_EXIT_INSN(),
 
 	/* subprog 1 */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_EXIT_INSN(), /* return sk */
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -291,7 +339,7 @@
 	BPF_EXIT_INSN(),
 
 	/* subprog 2 */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -324,7 +372,7 @@
 	BPF_EXIT_INSN(),
 
 	/* subprog 2 */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SCHED_CLS,
@@ -334,7 +382,7 @@
 	"reference tracking: allow LD_ABS",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
 	BPF_EMIT_CALL(BPF_FUNC_sk_release),
@@ -350,7 +398,7 @@
 	"reference tracking: forbid LD_ABS while holding reference",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_LD_ABS(BPF_B, 0),
 	BPF_LD_ABS(BPF_H, 0),
 	BPF_LD_ABS(BPF_W, 0),
@@ -367,7 +415,7 @@
 	"reference tracking: allow LD_IND",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
 	BPF_EMIT_CALL(BPF_FUNC_sk_release),
@@ -384,7 +432,7 @@
 	"reference tracking: forbid LD_IND while holding reference",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_4, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_7, 1),
 	BPF_LD_IND(BPF_W, BPF_REG_7, -0x200000),
@@ -402,7 +450,7 @@
 	"reference tracking: check reference or tail call",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	/* if (sk) bpf_sk_release() */
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 7),
@@ -424,7 +472,7 @@
 	"reference tracking: release reference then tail call",
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	/* if (sk) bpf_sk_release() */
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
@@ -446,7 +494,7 @@
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
 	/* Look up socket and store in REG_6 */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	/* bpf_tail_call() */
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_MOV64_IMM(BPF_REG_3, 2),
@@ -470,7 +518,7 @@
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_7, BPF_REG_1),
 	/* Look up socket and store in REG_6 */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	/* if (!sk) goto end */
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7),
@@ -492,7 +540,7 @@
 {
 	"reference tracking: mangle and release sock_or_null",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
@@ -506,7 +554,7 @@
 {
 	"reference tracking: mangle and release sock",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
 	BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 5),
@@ -520,7 +568,7 @@
 {
 	"reference tracking: access member",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
 	BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_0, 4),
@@ -534,7 +582,7 @@
 {
 	"reference tracking: write to member",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
@@ -553,7 +601,7 @@
 {
 	"reference tracking: invalid 64-bit access of member",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
 	BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
@@ -568,7 +616,7 @@
 {
 	"reference tracking: access after release",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
 	BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
 	BPF_EMIT_CALL(BPF_FUNC_sk_release),
@@ -608,7 +656,7 @@
 {
 	"reference tracking: use ptr from bpf_tcp_sock() after release",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
@@ -631,7 +679,7 @@
 {
 	"reference tracking: use ptr from bpf_sk_fullsock() after release",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
@@ -654,7 +702,7 @@
 {
 	"reference tracking: use ptr from bpf_sk_fullsock(tp) after release",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
@@ -681,7 +729,7 @@
 {
 	"reference tracking: use sk after bpf_sk_release(tp)",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
@@ -703,7 +751,7 @@
 {
 	"reference tracking: use ptr from bpf_get_listener_sock() after bpf_sk_release(sk)",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
@@ -725,7 +773,7 @@
 {
 	"reference tracking: bpf_sk_release(listen_sk)",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),
@@ -750,7 +798,7 @@
 	/* !bpf_sk_fullsock(sk) is checked but !bpf_tcp_sock(sk) is not checked */
 	"reference tracking: tp->snd_cwnd after bpf_sk_fullsock(sk) and bpf_tcp_sock(sk)",
 	.insns = {
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
 	BPF_EXIT_INSN(),
 	BPF_MOV64_REG(BPF_REG_6, BPF_REG_0),

tools/testing/selftests/bpf/verifier/unpriv.c

@@ -242,7 +242,7 @@
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
 	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 	/* u64 foo; */
 	/* void *target = &foo; */
@@ -276,7 +276,7 @@
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
 	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 	/* u64 foo; */
 	/* void *target = &foo; */
@@ -307,7 +307,7 @@
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
 	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 	/* u64 foo; */
 	/* void *target = &foo; */
@@ -339,7 +339,7 @@
 	.insns = {
 	BPF_MOV64_REG(BPF_REG_8, BPF_REG_1),
 	/* struct bpf_sock *sock = bpf_sock_lookup(...); */
-	BPF_SK_LOOKUP,
+	BPF_SK_LOOKUP(sk_lookup_tcp),
 	BPF_MOV64_REG(BPF_REG_2, BPF_REG_0),
 	/* u64 foo; */
 	/* void *target = &foo; */