Commit dc87efdb authored by Florian Westphal's avatar Florian Westphal Committed by David S. Miller
Browse files

mptcp: add mptcp reset option support 



The MPTCP reset option allows to carry a mptcp-specific error code that
provides more information on the nature of a connection reset.

Reset option data received gets stored in the subflow context so it can
be sent to userspace via the 'subflow closed' netlink event.

When a subflow is closed, the desired error code that should be sent to
the peer is also placed in the subflow context structure.

If a reset is sent before subflow establishment could complete, e.g. on
HMAC failure during an MP_JOIN operation, the mptcp skb extension is
used to store the reset information.

Signed-off-by: default avatarFlorian Westphal <fw@strlen.de>
Signed-off-by: default avatarMat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 781bf13d

include/net/mptcp.h

+16 −2
Original line number Diff line number Diff line
@@ -30,8 +30,8 @@ struct mptcp_ext { 
			ack64:1,

			mpc_map:1,

			frozen:1,

			__unused:1;

	/* one byte hole */

			reset_transient:1;

	u8		reset_reason:4;

};



#define MPTCP_RM_IDS_MAX	8
@@ -58,6 +58,8 @@ struct mptcp_out_options { 
	struct mptcp_rm_list rm_list;

	u8 join_id;

	u8 backup;

	u8 reset_reason:4;

	u8 reset_transient:1;

	u32 nonce;

	u64 thmac;

	u32 token;
@@ -156,6 +158,16 @@ void mptcp_seq_show(struct seq_file *seq); 
int mptcp_subflow_init_cookie_req(struct request_sock *req,

				  const struct sock *sk_listener,

				  struct sk_buff *skb);



__be32 mptcp_get_reset_option(const struct sk_buff *skb);



static inline __be32 mptcp_reset_option(const struct sk_buff *skb)

{

	if (skb_ext_exist(skb, SKB_EXT_MPTCP))

		return mptcp_get_reset_option(skb);



	return htonl(0u);

}

#else



static inline void mptcp_init(void)
@@ -236,6 +248,8 @@ static inline int mptcp_subflow_init_cookie_req(struct request_sock *req, 
{

	return 0; /* TCP fallback */

}



static inline __be32 mptcp_reset_option(const struct sk_buff *skb)  { return htonl(0u); }

#endif /* CONFIG_MPTCP */



#if IS_ENABLED(CONFIG_MPTCP_IPV6)

include/uapi/linux/mptcp.h

+11 −0
Original line number Diff line number Diff line
@@ -174,10 +174,21 @@ enum mptcp_event_attr { 
	MPTCP_ATTR_FLAGS,	/* u16 */

	MPTCP_ATTR_TIMEOUT,	/* u32 */

	MPTCP_ATTR_IF_IDX,	/* s32 */

	MPTCP_ATTR_RESET_REASON,/* u32 */

	MPTCP_ATTR_RESET_FLAGS, /* u32 */



	__MPTCP_ATTR_AFTER_LAST

};



#define MPTCP_ATTR_MAX (__MPTCP_ATTR_AFTER_LAST - 1)



/* MPTCP Reset reason codes, rfc8684 */

#define MPTCP_RST_EUNSPEC	0

#define MPTCP_RST_EMPTCP	1

#define MPTCP_RST_ERESOURCE	2

#define MPTCP_RST_EPROHIBIT	3

#define MPTCP_RST_EWQ2BIG	4

#define MPTCP_RST_EBADPERF	5

#define MPTCP_RST_EMIDDLEBOX	6



#endif /* _UAPI_MPTCP_H */

net/ipv4/tcp_ipv4.c

+18 −3
Original line number Diff line number Diff line
@@ -655,14 +655,18 @@ EXPORT_SYMBOL(tcp_v4_send_check); 
 *	Exception: precedence violation. We do not implement it in any case.

 */



#ifdef CONFIG_TCP_MD5SIG

#define OPTION_BYTES TCPOLEN_MD5SIG_ALIGNED

#else

#define OPTION_BYTES sizeof(__be32)

#endif



static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)

{

	const struct tcphdr *th = tcp_hdr(skb);

	struct {

		struct tcphdr th;

#ifdef CONFIG_TCP_MD5SIG

		__be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];

#endif

		__be32 opt[OPTION_BYTES / sizeof(__be32)];

	} rep;

	struct ip_reply_arg arg;

#ifdef CONFIG_TCP_MD5SIG
@@ -770,6 +774,17 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) 
				     ip_hdr(skb)->daddr, &rep.th);

	}

#endif

	/* Can't co-exist with TCPMD5, hence check rep.opt[0] */

	if (rep.opt[0] == 0) {

		__be32 mrst = mptcp_reset_option(skb);



		if (mrst) {

			rep.opt[0] = mrst;

			arg.iov[0].iov_len += sizeof(mrst);

			rep.th.doff = arg.iov[0].iov_len / 4;

		}

	}



	arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr,

				      ip_hdr(skb)->saddr, /* XXX */

				      arg.iov[0].iov_len, IPPROTO_TCP, 0);

net/ipv6/tcp_ipv6.c

+13 −1
Original line number Diff line number Diff line
@@ -879,8 +879,8 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 
	struct net *net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev);

	struct sock *ctl_sk = net->ipv6.tcp_sk;

	unsigned int tot_len = sizeof(struct tcphdr);

	__be32 mrst = 0, *topt;

	struct dst_entry *dst;

	__be32 *topt;

	__u32 mark = 0;



	if (tsecr)
@@ -890,6 +890,15 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 
		tot_len += TCPOLEN_MD5SIG_ALIGNED;

#endif



#ifdef CONFIG_MPTCP

	if (rst && !key) {

		mrst = mptcp_reset_option(skb);



		if (mrst)

			tot_len += sizeof(__be32);

	}

#endif



	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,

			 GFP_ATOMIC);

	if (!buff)
@@ -920,6 +929,9 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 
		*topt++ = htonl(tsecr);

	}



	if (mrst)

		*topt++ = mrst;



#ifdef CONFIG_TCP_MD5SIG

	if (key) {

		*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |

net/mptcp/options.c

+62 −5
Original line number Diff line number Diff line
@@ -305,6 +305,18 @@ static void mptcp_parse_option(const struct sk_buff *skb, 
		mp_opt->fastclose = 1;

		break;



	case MPTCPOPT_RST:

		if (opsize != TCPOLEN_MPTCP_RST)

			break;



		if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))

			break;

		mp_opt->reset = 1;

		flags = *ptr++;

		mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;

		mp_opt->reset_reason = *ptr;

		break;



	default:

		break;

	}
@@ -327,6 +339,7 @@ void mptcp_get_options(const struct sk_buff *skb, 
	mp_opt->rm_addr = 0;

	mp_opt->dss = 0;

	mp_opt->mp_prio = 0;

	mp_opt->reset = 0;



	length = (th->doff * 4) - sizeof(struct tcphdr);

	ptr = (const unsigned char *)(th + 1);
@@ -726,6 +739,22 @@ static bool mptcp_established_options_mp_prio(struct sock *sk, 
	return true;

}



static noinline void mptcp_established_options_rst(struct sock *sk, struct sk_buff *skb,

						   unsigned int *size,

						   unsigned int remaining,

						   struct mptcp_out_options *opts)

{

	const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);



	if (remaining < TCPOLEN_MPTCP_RST)

		return;



	*size = TCPOLEN_MPTCP_RST;

	opts->suboptions |= OPTION_MPTCP_RST;

	opts->reset_transient = subflow->reset_transient;

	opts->reset_reason = subflow->reset_reason;

}



bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,

			       unsigned int *size, unsigned int remaining,

			       struct mptcp_out_options *opts)
@@ -741,11 +770,10 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, 
	if (unlikely(__mptcp_check_fallback(msk)))

		return false;



	/* prevent adding of any MPTCP related options on reset packet

	 * until we support MP_TCPRST/MP_FASTCLOSE

	 */

	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))

		return false;

	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {

		mptcp_established_options_rst(sk, skb, size, remaining, opts);

		return true;

	}



	snd_data_fin = mptcp_data_fin_enabled(msk);

	if (mptcp_established_options_mp(sk, skb, snd_data_fin, &opt_size, remaining, opts))
@@ -1062,6 +1090,12 @@ void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) 
		mp_opt.mp_prio = 0;

	}



	if (mp_opt.reset) {

		subflow->reset_seen = 1;

		subflow->reset_reason = mp_opt.reset_reason;

		subflow->reset_transient = mp_opt.reset_transient;

	}



	if (!mp_opt.dss)

		return;
@@ -1289,6 +1323,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, 
		ptr += 5;

	}



	if (OPTION_MPTCP_RST & opts->suboptions)

		*ptr++ = mptcp_option(MPTCPOPT_RST,

				      TCPOLEN_MPTCP_RST,

				      opts->reset_transient,

				      opts->reset_reason);



	if (opts->ext_copy.use_ack || opts->ext_copy.use_map) {

		struct mptcp_ext *mpext = &opts->ext_copy;

		u8 len = TCPOLEN_MPTCP_DSS_BASE;
@@ -1340,3 +1380,20 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, 
	if (tp)

		mptcp_set_rwin(tp);

}



__be32 mptcp_get_reset_option(const struct sk_buff *skb)

{

	const struct mptcp_ext *ext = mptcp_get_ext(skb);

	u8 flags, reason;



	if (ext) {

		flags = ext->reset_transient;

		reason = ext->reset_reason;



		return mptcp_option(MPTCPOPT_RST, TCPOLEN_MPTCP_RST,

				    flags, reason);

	}



	return htonl(0u);

}

EXPORT_SYMBOL_GPL(mptcp_get_reset_option);