Skip to contentSkip to conversation

mptcp: add reset option support

RFC PATCH In review Florian Westphal 2 participants 6 messages Sep 24, 2020 – Sep 25, 2020

Subsystems (3)
lore
Share & tools
lore

Florian Westphal

author
#0 lore raw

cover mptcp: add reset option support

This series adds initial support for the RESET option. First patch is a minor cleanup, I would propose to pass this to net-next.

Second patch moves a few helpers around so they can be used from tcp core (needed to add mtpcp reset option to 'active resets', as those do not use the normal tcp output option path).

Third patch adds mptcp reset option, both for sending and receiving.

Last patch adds a call to the mptcp layer for inbound resets.

At this time, this is non-sensical, as nothing makes use of the rest-option hint.

The option/reason code would have to be propagated to the PM so it could use that for e.g. reconnect decisions.

We can discuss further steps in todays meeting.

author
#1 lore raw

RFC PATCH 1/4 net: tcp: drop unused function argument from mptcp_incoming_options

Since commit cfde141ea3faa30e ("mptcp: move option parsing into mptcp_incoming_options()"), the 3rd function argument is no longer used.

Signed-off-by Florian Westphal <fw(a)strlen.de>
---
 include/net/mptcp.h  | 6 ++----
 net/ipv4/tcp_input.c | 4 ++--
 net/mptcp/options.c  | 3 +--
 3 files changed, 5 insertions(+), 8 deletions(-)
include/net/mptcp.h +2 -4
index a7fc486e1035..6e706d838e4e 100644
@@ -86,8 +86,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 			       unsigned int *size, unsigned int remaining,
 			       struct mptcp_out_options *opts);
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
 
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
 
@@ -199,8 +198,7 @@ static inline bool mptcp_established_options(struct sock *sk,
 }
 
 static inline void mptcp_incoming_options(struct sock *sk,
-					  struct sk_buff *skb,
-					  struct tcp_options_received *opt_rx)
+					  struct sk_buff *skb)
 {
 }
 
net/ipv4/tcp_input.c +2 -2
index 50834e7f958e..8afa4af30fdc 100644
@@ -4908,7 +4908,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	int eaten;
 
 	if (sk_is_mptcp(sk))
-		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+		mptcp_incoming_options(sk, skb);
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -6487,7 +6487,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 			if (sk_is_mptcp(sk))
-				mptcp_incoming_options(sk, skb, &tp->rx_opt);
+				mptcp_incoming_options(sk, skb);
 			break;
 		}
 		fallthrough;
net/mptcp/options.c +1 -2
index 14a290fae767..411fd4a41796 100644
@@ -859,8 +859,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx)
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
Signature · 1 line
2.26.2
Reviewed-by on v1 1/4
#2 lore raw

[MPTCP] Re: [RFC PATCH 1/4] net: tcp: drop unused function argument from mptcp_incoming_options

Quoted 72 lines · Florian Westphal

Since commit cfde141ea3faa30e ("mptcp: move option parsing into mptcp_incoming_options()"), the 3rd function argument is no longer used.

Signed-off-by Florian Westphal <fw(a)strlen.de>

---

include/net/mptcp.h  | 6 ++----
net/ipv4/tcp_input.c | 4 ++--
net/mptcp/options.c  | 3 +--
3 files changed, 5 insertions(+), 8 deletions(-)
include/net/mptcp.h +2 -4
index a7fc486e1035..6e706d838e4e 100644
@@ -86,8 +86,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
 bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 			       unsigned int *size, unsigned int remaining,
 			       struct mptcp_out_options *opts);
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx);
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb);
 
 void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
 
@@ -199,8 +198,7 @@ static inline bool mptcp_established_options(struct sock *sk,
 }
 
 static inline void mptcp_incoming_options(struct sock *sk,
-					  struct sk_buff *skb,
-					  struct tcp_options_received *opt_rx)
+					  struct sk_buff *skb)
 {
 }
 
net/ipv4/tcp_input.c +2 -2
index 50834e7f958e..8afa4af30fdc 100644
@@ -4908,7 +4908,7 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
 	int eaten;
 
 	if (sk_is_mptcp(sk))
-		mptcp_incoming_options(sk, skb, &tp->rx_opt);
+		mptcp_incoming_options(sk, skb);
 
 	if (TCP_SKB_CB(skb)->seq == TCP_SKB_CB(skb)->end_seq) {
 		__kfree_skb(skb);
@@ -6487,7 +6487,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 	case TCP_LAST_ACK:
 		if (!before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
 			if (sk_is_mptcp(sk))
-				mptcp_incoming_options(sk, skb, &tp->rx_opt);
+				mptcp_incoming_options(sk, skb);
 			break;
 		}
 		fallthrough;
net/mptcp/options.c +1 -2
index 14a290fae767..411fd4a41796 100644
@@ -859,8 +859,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 	return hmac == mp_opt->ahmac;
 }
 
-void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb,
-			    struct tcp_options_received *opt_rx)
+void mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
 	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
Signature · 1 line
2.26.2

I agree with Paolo, this can go to net-next soon.

Reviewed-by Mat Martineau <mathew.j.martineau(a)linux.intel.com>

--
Mat Martineau
Intel

author
#3 lore raw

RFC PATCH 2/4 tcp: move selected mptcp helpers to tcp.h/mptcp.h

In reply to Florian Westphal

Will be needed to fill in the MPTCP reset option from tcp_ipv4/ipv6.c.

It would make more sense to place mptcp_option() in mptcp.h, but TCPOPT_MPTCP is defined in tcp.h, and mptcp.h is included from tcp.h, not the other way around. Placing the helper in mptcp.h thus results in a build failure because TCPOPT_MPTCP is not defined.

Signed-off-by Florian Westphal <fw(a)strlen.de>
---
 include/net/mptcp.h  | 10 ++++++++++
 include/net/tcp.h    |  5 +++++
 net/mptcp/protocol.h | 11 -----------
 3 files changed, 15 insertions(+), 11 deletions(-)
include/net/mptcp.h +10 -0
index 6e706d838e4e..5f5062580e0e 100644
@@ -68,6 +68,11 @@ static inline bool sk_is_mptcp(const struct sock *sk)
 	return tcp_sk(sk)->is_mptcp;
 }
 
+static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
+{
+	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
+}
+
 static inline bool rsk_is_mptcp(const struct request_sock *req)
 {
 	return tcp_rsk(req)->is_mptcp;
@@ -153,6 +158,11 @@ static inline void mptcp_init(void)
 {
 }
 
+static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
+{
+	return NULL;
+}
+
 static inline bool sk_is_mptcp(const struct sock *sk)
 {
 	return false;
include/net/tcp.h +5 -0
index 852f0d71dd40..ea8c134802e8 100644
@@ -2406,4 +2406,9 @@ static inline u64 tcp_transmit_time(const struct sock *sk)
 	return 0;
 }
 
+static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
+{
+	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
+		     ((nib & 0xF) << 8) | field);
+}
 #endif	/* _TCP_H */
net/mptcp/protocol.h +0 -11
index 7cfe52aeb2b8..e8c873c66182 100644
@@ -130,12 +130,6 @@ struct mptcp_options_received {
 	u16	port;
 };
 
-static inline __be32 mptcp_option(u8 subopt, u8 len, u8 nib, u8 field)
-{
-	return htonl((TCPOPT_MPTCP << 24) | (len << 16) | (subopt << 12) |
-		     ((nib & 0xF) << 8) | field);
-}
-
 struct mptcp_addr_info {
 	sa_family_t		family;
 	__be16			port;
@@ -486,11 +480,6 @@ void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk);
 void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, u8 rm_id);
 int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
 
-static inline struct mptcp_ext *mptcp_get_ext(struct sk_buff *skb)
-{
-	return (struct mptcp_ext *)skb_ext_find(skb, SKB_EXT_MPTCP);
-}
-
 static inline bool before64(__u64 seq1, __u64 seq2)
 {
 	return (__s64)(seq1 - seq2) < 0;
Signature · 1 line
2.26.2
author
#4 lore raw

RFC PATCH 3/4 mptcp: add mptcp reset option support

In reply to Florian Westphal

Reset option data taht is received will be stored in the mptcp skb extension structure so it can be consumed by e.g. path management.

When a subflow gets closed, the desired error code is stored in the subflow context structure.

When the close happens before a suitable tcp socket has been created (for example, when HMAC fails validation), its possible to attach the mptcp skb extension and store the reset reason code there.

Signed-off-by Florian Westphal <fw(a)strlen.de>
---
 include/net/mptcp.h  |  6 ++++--
 include/net/tcp.h    |  3 +++
 net/ipv4/tcp_ipv4.c  | 21 ++++++++++++++++++++-
 net/ipv6/tcp_ipv6.c  | 19 +++++++++++++++++++
 net/mptcp/options.c  | 37 +++++++++++++++++++++++++++++++++++++
 net/mptcp/protocol.c | 12 +++++++++---
 net/mptcp/protocol.h | 18 ++++++++++++++++++
 net/mptcp/subflow.c  | 27 ++++++++++++++++++++++++---
 8 files changed, 134 insertions(+), 9 deletions(-)
include/net/mptcp.h +4 -2
index 5f5062580e0e..2fc556946ef6 100644
@@ -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;
 };
 
 struct mptcp_out_options {
@@ -50,6 +50,8 @@ struct mptcp_out_options {
 	u8 rm_id;
 	u8 join_id;
 	u8 backup;
+	u8 reset_reason:4;
+	u8 reset_transient:1;
 	u32 nonce;
 	u64 thmac;
 	u32 token;
include/net/tcp.h +3 -0
index ea8c134802e8..a981b5d60112 100644
@@ -193,6 +193,8 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOPT_FASTOPEN_MAGIC	0xF989
 #define TCPOPT_SMC_MAGIC	0xE2D4C3D9
 
+/* MPTCP suboptions used in TCP */
+#define MPTCPOPT_TCPRST		8
 /*
  *     TCP option lengths
  */
@@ -216,6 +218,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo);
 #define TCPOLEN_MD5SIG_ALIGNED		20
 #define TCPOLEN_MSS_ALIGNED		4
 #define TCPOLEN_EXP_SMC_BASE_ALIGNED	8
+#define TCPOLEN_MPTCP_TCPRST		4
 
 /* Flags in tp->nonagle */
 #define TCP_NAGLE_OFF		1	/* Nagle's algo is disabled */
net/ipv4/tcp_ipv4.c +20 -1
index ace48b2790ff..b4bc04586d73 100644
@@ -660,9 +660,11 @@ 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;
+		__be32 opt[(TCPOLEN_MPTCP_TCPRST >> 2)
 #ifdef CONFIG_TCP_MD5SIG
-		__be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];
+			   + (TCPOLEN_MD5SIG_ALIGNED >> 2)
 #endif
+			];
 	} rep;
 	struct ip_reply_arg arg;
 #ifdef CONFIG_TCP_MD5SIG
@@ -770,6 +772,23 @@ 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 (sk && sk_fullsock(sk) && sk_is_mptcp(sk) && rep.opt[0] == 0) {
+		const struct mptcp_ext *ext = mptcp_get_ext(skb);
+		u8 flags = 0, reason = 0;
+
+		if (ext) {
+			flags = ext->reset_transient;
+			reason = ext->reset_reason;
+		}
+
+		rep.opt[0] = mptcp_option(MPTCPOPT_TCPRST, TCPOLEN_MPTCP_TCPRST,
+					  flags, reason);
+
+		arg.iov[0].iov_len += TCPOLEN_MPTCP_TCPRST;
+		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 +19 -0
index 8db59f4e5f13..e8c2b68ec4f9 100644
@@ -868,6 +868,7 @@ 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);
+	bool mptcp_reset = false;
 	struct dst_entry *dst;
 	__be32 *topt;
 	__u32 mark = 0;
@@ -879,6 +880,11 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 		tot_len += TCPOLEN_MD5SIG_ALIGNED;
 #endif
 
+	if (rst && sk && sk_fullsock(sk) && sk_is_mptcp(sk) && !key) {
+		tot_len += TCPOLEN_MPTCP_TCPRST;
+		mptcp_reset = true;
+	}
+
 	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
 			 GFP_ATOMIC);
 	if (!buff)
@@ -909,6 +915,19 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32
 		*topt++ = htonl(tsecr);
 	}
 
+	if (mptcp_reset) {
+		const struct mptcp_ext *ext = mptcp_get_ext(skb);
+		u8 flags = 0, reason = 0;
+
+		if (ext) {
+			flags = ext->reset_transient;
+			reason = ext->reset_reason;
+		}
+
+		*topt++ = mptcp_option(MPTCPOPT_TCPRST, TCPOLEN_MPTCP_TCPRST,
+				       flags, reason);
+	}
+
 #ifdef CONFIG_TCP_MD5SIG
 	if (key) {
 		*topt++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
net/mptcp/options.c +37 -0
index 411fd4a41796..1eb395dfaa50 100644
@@ -280,7 +280,17 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		mp_opt->rm_id = *ptr++;
 		pr_debug("RM_ADDR: id=%d", mp_opt->rm_id);
 		break;
+	case MPTCPOPT_TCPRST:
+		if (opsize != TCPOLEN_MPTCP_TCPRST)
+			break;
 
+		if (!(TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST))
+			break;
+		mp_opt->reset = 1;
+		flags = *ptr++;
+		mp_opt->reset_transient = flags & MPTCP_TCPRST_TRANSIENT;
+		mp_opt->reset_reason = *ptr;
+		break;
 	default:
 		break;
 	}
@@ -299,6 +309,7 @@ void mptcp_get_options(const struct sk_buff *skb,
 	mp_opt->add_addr = 0;
 	mp_opt->rm_addr = 0;
 	mp_opt->dss = 0;
+	mp_opt->reset = 0;
 
 	length = (th->doff * 4) - sizeof(struct tcphdr);
 	ptr = (const unsigned char *)(th + 1);
@@ -477,6 +488,22 @@ static void mptcp_write_data_fin(struct mptcp_subflow_context *subflow,
 	}
 }
 
+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_TCPRST)
+		return;
+
+	*size = TCPOLEN_MPTCP_TCPRST;
+	opts->suboptions |= OPTION_MPTCP_TCPRST;
+	opts->reset_transient = subflow->reset_transient;
+	opts->reset_reason = subflow->reset_reason;
+}
+
 static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 					  unsigned int *size,
 					  unsigned int remaining,
@@ -535,6 +562,10 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb,
 	dss_size += ack_size;
 
 	*size = ALIGN(dss_size, 4);
+
+	if (unlikely(skb && (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)))
+		mptcp_established_options_rst(sk, skb, size, remaining, opts);
+
 	return true;
 }
 
@@ -1065,6 +1096,12 @@ void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
 		ptr += 5;
 	}
 
+	if (OPTION_MPTCP_TCPRST & opts->suboptions)
+		*ptr++ = mptcp_option(MPTCPOPT_TCPRST,
+				      TCPOLEN_MPTCP_TCPRST,
+				      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;
net/mptcp/protocol.c +9 -3
index 6677461efc85..c4f510f4c556 100644
@@ -2402,14 +2402,18 @@ bool mptcp_finish_join(struct sock *sk)
 	pr_debug("msk=%p, subflow=%p", msk, subflow);
 
 	/* mptcp socket already closing? */
-	if (!mptcp_is_fully_established(parent))
+	if (!mptcp_is_fully_established(parent)) {
+		subflow->reset_reason = MPTCP_TCPRST_EMPTCP;
 		return false;
+	}
 
 	if (!msk->pm.server_side)
 		return true;
 
-	if (!mptcp_pm_allow_new_subflow(msk))
+	if (!mptcp_pm_allow_new_subflow(msk)) {
+		subflow->reset_reason = MPTCP_TCPRST_EPROHIBIT;
 		return false;
+	}
 
 	/* active connections are already on conn_list, and we can't acquire
 	 * msk lock here.
@@ -2421,8 +2425,10 @@ bool mptcp_finish_join(struct sock *sk)
 	if (ret && !WARN_ON_ONCE(!list_empty(&subflow->node)))
 		list_add_tail(&subflow->node, &msk->join_list);
 	spin_unlock_bh(&msk->join_list_lock);
-	if (!ret)
+	if (!ret) {
+		subflow->reset_reason = MPTCP_TCPRST_EPROHIBIT;
 		return false;
+	}
 
 	/* attach to msk socket only after we are sure he will deal with us
 	 * at close time
net/mptcp/protocol.h +18 -0
index e8c873c66182..8ed09af586f0 100644
@@ -23,6 +23,7 @@
 #define OPTION_MPTCP_ADD_ADDR	BIT(6)
 #define OPTION_MPTCP_ADD_ADDR6	BIT(7)
 #define OPTION_MPTCP_RM_ADDR	BIT(8)
+#define OPTION_MPTCP_TCPRST	BIT(9)
 
 /* MPTCP option subtypes */
 #define MPTCPOPT_MP_CAPABLE	0
@@ -84,6 +85,18 @@
 #define MPTCP_ADDR_IPVERSION_4	4
 #define MPTCP_ADDR_IPVERSION_6	6
 
+/* MPTCP TCPRST flags */
+#define MPTCP_TCPRST_TRANSIENT	BIT(0)
+
+/* MPTCP TCPRST reason codes */
+#define MPTCP_TCPRST_EUNSPEC	0
+#define MPTCP_TCPRST_EMPTCP	1
+#define MPTCP_TCPRST_ERESOURCE	2
+#define MPTCP_TCPRST_EPROHIBIT	3
+#define MPTCP_TCPRST_EWQ2BIG	4
+#define MPTCP_TCPRST_EBADPERF	5
+#define MPTCP_TCPRST_EMIDDLEBOX	6
+
 /* MPTCP socket flags */
 #define MPTCP_DATA_READY	0
 #define MPTCP_SEND_SPACE	1
@@ -100,6 +113,7 @@ struct mptcp_options_received {
 	u16	data_len;
 	u16	mp_capable : 1,
 		mp_join : 1,
+		reset : 1,
 		dss : 1,
 		add_addr : 1,
 		rm_addr : 1,
@@ -120,6 +134,8 @@ struct mptcp_options_received {
 		__unused:2;
 	u8	addr_id;
 	u8	rm_id;
+	u8	reset_reason:4;
+	u8	reset_transient:1;
 	union {
 		struct in_addr	addr;
 #if IS_ENABLED(CONFIG_MPTCP_IPV6)
@@ -314,6 +330,8 @@ struct mptcp_subflow_context {
 	u8	hmac[MPTCPOPT_HMAC_LEN];
 	u8	local_id;
 	u8	remote_id;
+	u8	reset_transient:1;
+	u8	reset_reason:4;
 
 	struct	sock *tcp_sock;	    /* tcp sk backpointer */
 	struct	sock *conn;	    /* parent mptcp_sock */
net/mptcp/subflow.c +24 -3
index 07b07be3e307..f3a493324777 100644
@@ -312,8 +312,10 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	} else if (subflow->request_join) {
 		u8 hmac[SHA256_DIGEST_SIZE];
 
-		if (!mp_opt.mp_join)
+		if (!mp_opt.mp_join) {
+			subflow->reset_reason = MPTCP_TCPRST_EMPTCP;
 			goto do_reset;
+		}
 
 		subflow->thmac = mp_opt.thmac;
 		subflow->remote_nonce = mp_opt.nonce;
@@ -322,6 +324,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 
 		if (!subflow_thmac_valid(subflow)) {
 			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINACKMAC);
+			subflow->reset_reason = MPTCP_TCPRST_EMPTCP;
 			goto do_reset;
 		}
 
@@ -343,6 +346,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
 	return;
 
 do_reset:
+	subflow->reset_transient = 0;
 	tcp_send_active_reset(sk, GFP_ATOMIC);
 	tcp_done(sk);
 }
@@ -493,6 +497,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 	struct mptcp_options_received mp_opt;
 	bool fallback, fallback_is_fatal;
 	struct sock *new_msk = NULL;
+	struct mptcp_ext *mpext;
 	struct sock *child;
 
 	pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
@@ -553,8 +558,15 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 		 * to reset the context to non MPTCP status.
 		 */
 		if (!ctx || fallback) {
-			if (fallback_is_fatal)
+			if (fallback_is_fatal) {
+				mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
+				if (mpext) {
+					memset(mpext, 0, sizeof(*mpext));
+					mpext->reset_reason = MPTCP_TCPRST_EMPTCP;
+				}
+
 				goto dispose_child;
+			}
 
 			subflow_drop_ctx(child);
 			goto out;
@@ -584,8 +596,15 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
 			struct mptcp_sock *owner;
 
 			owner = subflow_req->msk;
-			if (!owner)
+			if (!owner) {
+				mpext = skb_ext_add(skb, SKB_EXT_MPTCP);
+				if (mpext) {
+					memset(mpext, 0, sizeof(*mpext));
+					mpext->reset_reason = MPTCP_TCPRST_EPROHIBIT;
+				}
+
 				goto dispose_child;
+			}
 
 			/* move the msk reference ownership to the subflow */
 			subflow_req->msk = NULL;
@@ -911,6 +930,8 @@ static bool subflow_check_data_avail(struct sock *ssk)
 	smp_wmb();
 	ssk->sk_error_report(ssk);
 	tcp_set_state(ssk, TCP_CLOSE);
+	subflow->reset_transient = 0;
+	subflow->reset_reason = MPTCP_TCPRST_EMPTCP;
 	tcp_send_active_reset(ssk, GFP_ATOMIC);
 	subflow->data_avail = 0;
 	return false;
Signature · 1 line
2.26.2
author
#5 lore raw

RFC PATCH 4/4 tcp: parse tcp options contained in reset packets

In reply to Florian Westphal

This will be used to handle MPTCP_TCPRST suboption.

It allows an MPTCP receiver to learn more information when a subflow is re-set. The MPTCP_TCPRST option gives an error code (protocol error, path too slow, middlebox interference detected, and so on).

This allows an MPTCP receiver to make a decision to reopen the subflow at a later time, or even completely disable the path.

Signed-off-by Florian Westphal <fw(a)strlen.de>
---
 include/net/tcp.h        |  2 +-
 net/ipv4/tcp_input.c     | 13 ++++++++-----
 net/ipv4/tcp_minisocks.c |  2 +-
 3 files changed, 10 insertions(+), 7 deletions(-)
include/net/tcp.h +1 -1
index a981b5d60112..92eee154e2a3 100644
@@ -609,7 +609,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
 /* tcp_input.c */
 void tcp_rearm_rto(struct sock *sk);
 void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
-void tcp_reset(struct sock *sk);
+void tcp_reset(struct sock *sk, struct sk_buff *skb);
 void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb);
 void tcp_fin(struct sock *sk);
 
net/ipv4/tcp_input.c +8 -5
index 8afa4af30fdc..0a10ba1df1a0 100644
@@ -4206,10 +4206,13 @@ static inline bool tcp_sequence(const struct tcp_sock *tp, u32 seq, u32 end_seq)
 }
 
 /* When we get a reset we do this. */
-void tcp_reset(struct sock *sk)
+void tcp_reset(struct sock *sk, struct sk_buff *skb)
 {
 	trace_tcp_receive_reset(sk);
 
+	if (sk_is_mptcp(sk))
+		mptcp_incoming_options(sk, skb);
+
 	/* We want the right error as BSD sees it (and indeed as we do). */
 	switch (sk->sk_state) {
 	case TCP_SYN_SENT:
@@ -5590,7 +5593,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 						  &tp->last_oow_ack_time))
 				tcp_send_dupack(sk, skb);
 		} else if (tcp_reset_check(sk, skb)) {
-			tcp_reset(sk);
+			tcp_reset(sk, skb);
 		}
 		goto discard;
 	}
@@ -5626,7 +5629,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
 		}
 
 		if (rst_seq_match)
-			tcp_reset(sk);
+			tcp_reset(sk, skb);
 		else {
 			/* Disable TFO if RST is out-of-order
 			 * and no data has been received
@@ -6059,7 +6062,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
 		 */
 
 		if (th->rst) {
-			tcp_reset(sk);
+			tcp_reset(sk, skb);
 			goto discard;
 		}
 
@@ -6501,7 +6504,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb)
 			if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
 			    after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt)) {
 				NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
-				tcp_reset(sk);
+				tcp_reset(sk, skb);
 				return 1;
 			}
 		}
net/ipv4/tcp_minisocks.c +1 -1
index 56c306e3cd2f..12f2495f98df 100644
@@ -802,7 +802,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
 		req->rsk_ops->send_reset(sk, skb);
 	} else if (fastopen) { /* received a valid RST pkt */
 		reqsk_fastopen_remove(sk, req, true);
-		tcp_reset(sk);
+		tcp_reset(sk, skb);
 	}
 	if (!fastopen) {
 		inet_csk_reqsk_queue_drop(sk, req);
Signature · 1 line
2.26.2