1 files changed, 138 insertions, 49 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 645dd984fef0..30d289044e71 100644
--- a/net/mptcp/options.c
+++ b/net/mptcp/options.c
@@ -107,7 +107,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 			ptr += 2;
 		}
 		if (opsize == TCPOLEN_MPTCP_MPC_ACK_DATA_CSUM) {
-			mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+			mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
 			mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
 			ptr += 2;
 		}
@@ -221,7 +221,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 
 			if (opsize == expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) {
 				mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
-				mp_opt->csum = (__force __sum16)get_unaligned_be16(ptr);
+				mp_opt->csum = get_unaligned((__force __sum16 *)ptr);
 				ptr += 2;
 			}
 
@@ -323,6 +323,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		mp_opt->rcvr_key = get_unaligned_be64(ptr);
 		ptr += 8;
 		mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE;
+		pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key);
 		break;
 
 	case MPTCPOPT_RST:
@@ -336,6 +337,8 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 		flags = *ptr++;
 		mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
 		mp_opt->reset_reason = *ptr;
+		pr_debug("MP_RST: transient=%u reason=%u",
+			 mp_opt->reset_transient, mp_opt->reset_reason);
 		break;
 
 	case MPTCPOPT_MP_FAIL:
@@ -353,8 +356,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
 	}
 }
 
-void mptcp_get_options(const struct sock *sk,
-		       const struct sk_buff *skb,
+void mptcp_get_options(const struct sk_buff *skb,
 		       struct mptcp_options_received *mp_opt)
 {
 	const struct tcphdr *th = tcp_hdr(skb);
@@ -651,7 +653,6 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	bool drop_other_suboptions = false;
 	unsigned int opt_size = *size;
 	bool echo;
-	bool port;
 	int len;
 
 	/* add addr will strip the existing options, be sure to avoid breaking
@@ -660,12 +661,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
 	if (!mptcp_pm_should_add_signal(msk) ||
 	    (opts->suboptions & (OPTION_MPTCP_MPJ_ACK | OPTION_MPTCP_MPC_ACK)) ||
 	    !mptcp_pm_add_addr_signal(msk, skb, opt_size, remaining, &opts->addr,
-		    &echo, &port, &drop_other_suboptions))
+		    &echo, &drop_other_suboptions))
 		return false;
 
 	if (drop_other_suboptions)
 		remaining += opt_size;
-	len = mptcp_add_addr_len(opts->addr.family, echo, port);
+	len = mptcp_add_addr_len(opts->addr.family, echo, !!opts->addr.port);
 	if (remaining < len)
 		return false;
 
@@ -764,6 +765,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu
 	opts->suboptions |= OPTION_MPTCP_RST;
 	opts->reset_transient = subflow->reset_transient;
 	opts->reset_reason = subflow->reset_reason;
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX);
 
 	return true;
 }
@@ -787,6 +789,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
 	opts->rcvr_key = msk->remote_key;
 
 	pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
 	return true;
 }
 
@@ -808,6 +811,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
 	opts->fail_seq = subflow->map_seq;
 
 	pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
+	MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
 
 	return true;
 }
@@ -824,7 +828,7 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb,
 
 	opts->suboptions = 0;
 
-	if (unlikely(__mptcp_check_fallback(msk)))
+	if (unlikely(__mptcp_check_fallback(msk) && !mptcp_check_infinite_map(skb)))
 		return false;
 
 	if (unlikely(skb && TCP_SKB_CB(skb)->tcp_flags & TCPHDR_RST)) {
@@ -928,7 +932,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 		if (TCP_SKB_CB(skb)->seq == subflow->ssn_offset + 1 &&
 		    TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq &&
 		    subflow->mp_join && (mp_opt->suboptions & OPTIONS_MPTCP_MPJ) &&
-		    READ_ONCE(msk->pm.server_side))
+		    !subflow->request_join)
 			tcp_send_ack(ssk);
 		goto fully_established;
 	}
@@ -963,7 +967,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
 			goto reset;
 		subflow->mp_capable = 0;
 		pr_fallback(msk);
-		__mptcp_do_fallback(msk);
+		mptcp_do_fallback(ssk);
 		return false;
 	}
 
@@ -1084,8 +1088,7 @@ static bool add_addr_hmac_valid(struct mptcp_sock *msk,
 				      &mp_opt->addr);
 
 	pr_debug("msk=%p, ahmac=%llu, mp_opt->ahmac=%llu\n",
-		 msk, (unsigned long long)hmac,
-		 (unsigned long long)mp_opt->ahmac);
+		 msk, hmac, mp_opt->ahmac);
 
 	return hmac == mp_opt->ahmac;
 }
@@ -1112,7 +1115,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 		return true;
 	}
 
-	mptcp_get_options(sk, skb, &mp_opt);
+	mptcp_get_options(skb, &mp_opt);
 
 	/* The subflow can be in close state only if check_fully_established()
 	 * just sent a reset. If so, tell the caller to ignore the current packet.
@@ -1125,12 +1128,13 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 		    msk->local_key == mp_opt.rcvr_key) {
 			WRITE_ONCE(msk->rcv_fastclose, true);
 			mptcp_schedule_work((struct sock *)msk);
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSERX);
 		}
 
 		if ((mp_opt.suboptions & OPTION_MPTCP_ADD_ADDR) &&
 		    add_addr_hmac_valid(msk, &mp_opt)) {
 			if (!mp_opt.echo) {
-				mptcp_pm_add_addr_received(msk, &mp_opt.addr);
+				mptcp_pm_add_addr_received(sk, &mp_opt.addr);
 				MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDR);
 			} else {
 				mptcp_pm_add_addr_echoed(msk, &mp_opt.addr);
@@ -1159,6 +1163,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 			subflow->reset_seen = 1;
 			subflow->reset_reason = mp_opt.reset_reason;
 			subflow->reset_transient = mp_opt.reset_transient;
+			MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTRX);
 		}
 
 		if (!(mp_opt.suboptions & OPTION_MPTCP_DSS))
@@ -1220,23 +1225,65 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb)
 	return true;
 }
 
-static void mptcp_set_rwin(const struct tcp_sock *tp)
+static void mptcp_set_rwin(struct tcp_sock *tp, struct tcphdr *th)
 {
 	const struct sock *ssk = (const struct sock *)tp;
-	const struct mptcp_subflow_context *subflow;
+	struct mptcp_subflow_context *subflow;
+	u64 ack_seq, rcv_wnd_old, rcv_wnd_new;
 	struct mptcp_sock *msk;
-	u64 ack_seq;
+	u32 new_win;
+	u64 win;
 
 	subflow = mptcp_subflow_ctx(ssk);
 	msk = mptcp_sk(subflow->conn);
 
-	ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd;
+	ack_seq = READ_ONCE(msk->ack_seq);
+	rcv_wnd_new = ack_seq + tp->rcv_wnd;
+
+	rcv_wnd_old = atomic64_read(&msk->rcv_wnd_sent);
+	if (after64(rcv_wnd_new, rcv_wnd_old)) {
+		u64 rcv_wnd;
+
+		for (;;) {
+			rcv_wnd = atomic64_cmpxchg(&msk->rcv_wnd_sent, rcv_wnd_old, rcv_wnd_new);
+
+			if (rcv_wnd == rcv_wnd_old)
+				break;
+			if (before64(rcv_wnd_new, rcv_wnd)) {
+				MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE);
+				goto raise_win;
+			}
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT);
+			rcv_wnd_old = rcv_wnd;
+		}
+		return;
+	}
+
+	if (rcv_wnd_new != rcv_wnd_old) {
+raise_win:
+		win = rcv_wnd_old - ack_seq;
+		tp->rcv_wnd = min_t(u64, win, U32_MAX);
+		new_win = tp->rcv_wnd;
 
-	if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent)))
-		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
+		/* Make sure we do not exceed the maximum possible
+		 * scaled window.
+		 */
+		if (unlikely(th->syn))
+			new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale;
+		if (!tp->rx_opt.rcv_wscale &&
+		    READ_ONCE(sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows))
+			new_win = min(new_win, MAX_TCP_WINDOW);
+		else
+			new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale));
+
+		/* RFC1323 scaling applied */
+		new_win >>= tp->rx_opt.rcv_wscale;
+		th->window = htons(new_win);
+		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED);
+	}
 }
 
-u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
+__sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 {
 	struct csum_pseudo_header header;
 	__wsum csum;
@@ -1252,34 +1299,52 @@ u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum)
 	header.csum = 0;
 
 	csum = csum_partial(&header, sizeof(header), sum);
-	return (__force u16)csum_fold(csum);
+	return csum_fold(csum);
 }
 
-static u16 mptcp_make_csum(const struct mptcp_ext *mpext)
+static __sum16 mptcp_make_csum(const struct mptcp_ext *mpext)
 {
 	return __mptcp_make_csum(mpext->data_seq, mpext->subflow_seq, mpext->data_len,
 				 ~csum_unfold(mpext->csum));
 }
 
-void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
-			 struct mptcp_out_options *opts)
+static void put_len_csum(u16 len, __sum16 csum, void *data)
 {
-	if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) {
-		const struct sock *ssk = (const struct sock *)tp;
-		struct mptcp_subflow_context *subflow;
+	__sum16 *sumptr = data + 2;
+	__be16 *ptr = data;
 
-		subflow = mptcp_subflow_ctx(ssk);
-		subflow->send_mp_fail = 0;
+	put_unaligned_be16(len, ptr);
 
-		*ptr++ = mptcp_option(MPTCPOPT_MP_FAIL,
-				      TCPOLEN_MPTCP_FAIL,
-				      0, 0);
-		put_unaligned_be64(opts->fail_seq, ptr);
-		ptr += 2;
-	}
+	put_unaligned(csum, sumptr);
+}
 
-	/* DSS, MPC, MPJ, ADD_ADDR, FASTCLOSE and RST are mutually exclusive,
-	 * see mptcp_established_options*()
+void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp,
+			 struct mptcp_out_options *opts)
+{
+	const struct sock *ssk = (const struct sock *)tp;
+	struct mptcp_subflow_context *subflow;
+
+	/* Which options can be used together?
+	 *
+	 * X: mutually exclusive
+	 * O: often used together
+	 * C: can be used together in some cases
+	 * P: could be used together but we prefer not to (optimisations)
+	 *
+	 *  Opt: | MPC  | MPJ  | DSS  | ADD  |  RM  | PRIO | FAIL |  FC  |
+	 * ------|------|------|------|------|------|------|------|------|
+	 *  MPC  |------|------|------|------|------|------|------|------|
+	 *  MPJ  |  X   |------|------|------|------|------|------|------|
+	 *  DSS  |  X   |  X   |------|------|------|------|------|------|
+	 *  ADD  |  X   |  X   |  P   |------|------|------|------|------|
+	 *  RM   |  C   |  C   |  C   |  P   |------|------|------|------|
+	 *  PRIO |  X   |  C   |  C   |  C   |  C   |------|------|------|
+	 *  FAIL |  X   |  X   |  C   |  X   |  X   |  X   |------|------|
+	 *  FC   |  X   |  X   |  X   |  X   |  X   |  X   |  X   |------|
+	 *  RST  |  X   |  X   |  X   |  X   |  X   |  X   |  O   |  O   |
+	 * ------|------|------|------|------|------|------|------|------|
+	 *
+	 * The same applies in mptcp_established_options() function.
 	 */
 	if (likely(OPTION_MPTCP_DSS & opts->suboptions)) {
 		struct mptcp_ext *mpext = &opts->ext_copy;
@@ -1328,14 +1393,22 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			put_unaligned_be32(mpext->subflow_seq, ptr);
 			ptr += 1;
 			if (opts->csum_reqd) {
-				put_unaligned_be32(mpext->data_len << 16 |
-						   mptcp_make_csum(mpext), ptr);
+				/* data_len == 0 is reserved for the infinite mapping,
+				 * the checksum will also be set to 0.
+				 */
+				put_len_csum(mpext->data_len,
+					     (mpext->data_len ? mptcp_make_csum(mpext) : 0),
+					     ptr);
 			} else {
 				put_unaligned_be32(mpext->data_len << 16 |
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
 			}
 			ptr += 1;
 		}
+
+		/* We might need to add MP_FAIL options in rare cases */
+		if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions))
+			goto mp_fail;
 	} else if (OPTIONS_MPTCP_MPC & opts->suboptions) {
 		u8 len, flag = MPTCP_CAP_HMAC_SHA256;
 
@@ -1376,11 +1449,12 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			goto mp_capable_done;
 
 		if (opts->csum_reqd) {
-			put_unaligned_be32(opts->data_len << 16 |
-					   __mptcp_make_csum(opts->data_seq,
-							     opts->subflow_seq,
-							     opts->data_len,
-							     ~csum_unfold(opts->csum)), ptr);
+			put_len_csum(opts->data_len,
+				     __mptcp_make_csum(opts->data_seq,
+						       opts->subflow_seq,
+						       opts->data_len,
+						       ~csum_unfold(opts->csum)),
+				     ptr);
 		} else {
 			put_unaligned_be32(opts->data_len << 16 |
 					   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
@@ -1479,6 +1553,21 @@ void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 		if (OPTION_MPTCP_RST & opts->suboptions)
 			goto mp_rst;
 		return;
+	} else if (unlikely(OPTION_MPTCP_FAIL & opts->suboptions)) {
+mp_fail:
+		/* MP_FAIL is mutually exclusive with others except RST */
+		subflow = mptcp_subflow_ctx(ssk);
+		subflow->send_mp_fail = 0;
+
+		*ptr++ = mptcp_option(MPTCPOPT_MP_FAIL,
+				      TCPOLEN_MPTCP_FAIL,
+				      0, 0);
+		put_unaligned_be64(opts->fail_seq, ptr);
+		ptr += 2;
+
+		if (OPTION_MPTCP_RST & opts->suboptions)
+			goto mp_rst;
+		return;
 	} else if (unlikely(OPTION_MPTCP_RST & opts->suboptions)) {
 mp_rst:
 		*ptr++ = mptcp_option(MPTCPOPT_RST,
@@ -1489,15 +1578,15 @@ mp_rst:
 	}
 
 	if (OPTION_MPTCP_PRIO & opts->suboptions) {
-		const struct sock *ssk = (const struct sock *)tp;
-		struct mptcp_subflow_context *subflow;
-
 		subflow = mptcp_subflow_ctx(ssk);
 		subflow->send_mp_prio = 0;
 
 		*ptr++ = mptcp_option(MPTCPOPT_MP_PRIO,
 				      TCPOLEN_MPTCP_PRIO,
 				      opts->backup, TCPOPT_NOP);
+
+		MPTCP_INC_STATS(sock_net((const struct sock *)tp),
+				MPTCP_MIB_MPPRIOTX);
 	}
 
 mp_capable_done:
@@ -1522,7 +1611,7 @@ mp_capable_done:
 	}
 
 	if (tp)
-		mptcp_set_rwin(tp);
+		mptcp_set_rwin(tp, th);
 }
 
 __be32 mptcp_get_reset_option(const struct sk_buff *skb)