Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 25694738 authored by Alexei Starovoitov's avatar Alexei Starovoitov
Browse files

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: default avatarAlexei Starovoitov <ast@kernel.org>
parents 48e5d98a bafc0ba8

include/linux/bpf.h

+1 −0
Original line number Diff line number Diff line
@@ -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

+35 −1
Original line number Diff line number Diff line
@@ -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

+18 −15
Original line number Diff line number Diff line
@@ -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;

		}

	} 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

+194 −22
Original line number Diff line number Diff line
@@ -5156,13 +5156,13 @@ 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,

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)

{
@@ -5192,14 +5192,26 @@ __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,

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;
@@ -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 = {
@@ -5311,13 +5382,33 @@ static const struct bpf_func_proto bpf_xdp_sk_lookup_tcp_proto = { 
	.arg5_type      = ARG_ANYTHING,

};



BPF_CALL_5(bpf_sock_addr_sk_lookup_tcp, struct bpf_sock_addr_kern *, ctx,

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 __bpf_sk_lookup(NULL, tuple, len, sock_net(ctx->sk), 0,

	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 (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 = {

	.func		= bpf_sock_addr_sk_lookup_tcp,

	.gpl_only	= false,
@@ -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

+35 −1
Original line number Diff line number Diff line
@@ -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