Merge branch 'mptcp-checksums'

Mat Martineau says:

====================
mptcp: Fix checksum byte order on little-endian

These patches address a bug in the byte ordering of MPTCP checksums on
little-endian architectures. The __sum16 type is always big endian, but
was being cast to u16 and then byte-swapped (on little-endian archs)
when reading/writing the checksum field in MPTCP option headers.

MPTCP checksums are off by default, but are enabled if one or both peers
request it in the SYN/SYNACK handshake.

The corrected code is verified to interoperate between big-endian and
little-endian machines.

Patch 1 fixes the checksum byte order, patch 2 partially mitigates
interoperation with peers sending bad checksums by falling back to TCP
instead of resetting the connection.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 46 insertions, 18 deletions

diff --git a/net/mptcp/options.c b/net/mptcp/options.c
index 325383646f5c..b548cec86c9d 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;
 			}
 
@@ -1240,7 +1240,7 @@ static void mptcp_set_rwin(const struct tcp_sock *tp)
 		WRITE_ONCE(msk->rcv_wnd_sent, ack_seq);
 }
 
-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;
@@ -1256,15 +1256,25 @@ 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));
 }
 
+static void put_len_csum(u16 len, __sum16 csum, void *data)
+{
+	__sum16 *sumptr = data + 2;
+	__be16 *ptr = data;
+
+	put_unaligned_be16(len, ptr);
+
+	put_unaligned(csum, sumptr);
+}
+
 void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp,
 			 struct mptcp_out_options *opts)
 {
@@ -1340,8 +1350,9 @@ 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);
+				put_len_csum(mpext->data_len,
+					     mptcp_make_csum(mpext),
+					     ptr);
 			} else {
 				put_unaligned_be32(mpext->data_len << 16 |
 						   TCPOPT_NOP << 8 | TCPOPT_NOP, ptr);
@@ -1392,11 +1403,12 @@ 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);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index f4ce28bb0fdc..5655a63aa6a8 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -443,7 +443,8 @@ struct mptcp_subflow_context {
 		can_ack : 1,        /* only after processing the remote a key */
 		disposable : 1,	    /* ctx can be free at ulp release time */
 		stale : 1,	    /* unable to snd/rcv data, do not use for xmit */
-		local_id_valid : 1; /* local_id is correctly initialized */
+		local_id_valid : 1, /* local_id is correctly initialized */
+		valid_csum_seen : 1;        /* at least one csum validated */
 	enum mptcp_data_avail data_avail;
 	u32	remote_nonce;
 	u64	thmac;
@@ -723,7 +724,7 @@ void mptcp_token_destroy(struct mptcp_sock *msk);
 void mptcp_crypto_key_sha(u64 key, u32 *token, u64 *idsn);
 
 void mptcp_crypto_hmac_sha(u64 key1, u64 key2, u8 *msg, int len, void *hmac);
-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);
 
 void __init mptcp_pm_init(void);
 void mptcp_pm_data_init(struct mptcp_sock *msk);
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index 8c37087f0d84..be76ada89d96 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -888,7 +888,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	u32 offset, seq, delta;
-	u16 csum;
+	__sum16 csum;
 	int len;
 
 	if (!csum_reqd)
@@ -955,11 +955,14 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff *
 				 subflow->map_data_csum);
 	if (unlikely(csum)) {
 		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR);
-		subflow->send_mp_fail = 1;
-		MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
+		if (subflow->mp_join || subflow->valid_csum_seen) {
+			subflow->send_mp_fail = 1;
+			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX);
+		}
 		return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY;
 	}
 
+	subflow->valid_csum_seen = 1;
 	return MAPPING_OK;
 }
 
@@ -1141,6 +1144,18 @@ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ss
 	}
 }
 
+static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
+{
+	struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+	if (subflow->mp_join)
+		return false;
+	else if (READ_ONCE(msk->csum_enabled))
+		return !subflow->valid_csum_seen;
+	else
+		return !subflow->fully_established;
+}
+
 static bool subflow_check_data_avail(struct sock *ssk)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
@@ -1218,7 +1233,7 @@ fallback:
 		return true;
 	}
 
-	if (subflow->mp_join || subflow->fully_established) {
+	if (!subflow_can_fallback(subflow)) {
 		/* fatal protocol error, close the socket.
 		 * subflow_error_report() will introduce the appropriate barriers
 		 */