@@ -78,6 +78,16 @@ struct tcp_sack_block {
#define TCP_SACK_SEEN (1 << 0) /*1 = peer is SACK capable, */
#define TCP_DSACK_SEEN (1 << 2) /*1 = DSACK was received from peer*/
+#if IS_ENABLED(CONFIG_MPTCP)
+struct mptcp_options_received {
+ u64 sndr_key;
+ u64 rcvr_key;
+ u8 mp_capable : 1,
+ mp_join : 1,
+ dss : 1;
+};
+#endif
+
struct tcp_options_received {
/* PAWS/RTTM data */
int ts_recent_stamp;/* Time we stored ts_recent (for aging) */
@@ -95,6 +105,9 @@ struct tcp_options_received {
u8 num_sacks; /* Number of SACK blocks */
u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
+#if IS_ENABLED(CONFIG_MPTCP)
+ struct mptcp_options_received mptcp;
+#endif
};
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
@@ -104,6 +117,11 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
#if IS_ENABLED(CONFIG_SMC)
rx_opt->smc_ok = 0;
#endif
+#if IS_ENABLED(CONFIG_MPTCP)
+ rx_opt->mptcp.mp_capable = 0;
+ rx_opt->mptcp.mp_join = 0;
+ rx_opt->mptcp.dss = 0;
+#endif
}
/* This is the max number of SACKS that we'll generate and process. It's safe
@@ -9,6 +9,7 @@
#define __NET_MPTCP_H
#include <linux/skbuff.h>
+#include <linux/tcp.h>
#include <linux/types.h>
/* MPTCP sk_buff extension data */
@@ -26,10 +27,22 @@ struct mptcp_ext {
/* one byte hole */
};
+struct mptcp_out_options {
+#if IS_ENABLED(CONFIG_MPTCP)
+ u16 suboptions;
+ u64 sndr_key;
+ u64 rcvr_key;
+#endif
+};
+
#ifdef CONFIG_MPTCP
void mptcp_init(void);
+void mptcp_parse_option(const unsigned char *ptr, int opsize,
+ struct tcp_options_received *opt_rx);
+void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts);
+
/* move the skb extension owership, with the assumption that 'to' is
* newly allocated
*/
@@ -76,6 +89,11 @@ static inline void mptcp_init(void)
{
}
+static inline void mptcp_parse_option(const unsigned char *ptr, int opsize,
+ struct tcp_options_received *opt_rx)
+{
+}
+
static inline void mptcp_skb_ext_move(struct sk_buff *to,
const struct sk_buff *from)
{
@@ -79,6 +79,7 @@
#include <trace/events/tcp.h>
#include <linux/jump_label_ratelimit.h>
#include <net/busy_poll.h>
+#include <net/mptcp.h>
int sysctl_tcp_max_orphans __read_mostly = NR_FILE;
@@ -3924,6 +3925,10 @@ void tcp_parse_options(const struct net *net,
*/
break;
#endif
+ case TCPOPT_MPTCP:
+ mptcp_parse_option(ptr, opsize, opt_rx);
+ break;
+
case TCPOPT_FASTOPEN:
tcp_parse_fastopen_option(
opsize - TCPOLEN_FASTOPEN_BASE,
@@ -38,6 +38,7 @@
#define pr_fmt(fmt) "TCP: " fmt
#include <net/tcp.h>
+#include <net/mptcp.h>
#include <linux/compiler.h>
#include <linux/gfp.h>
@@ -414,6 +415,7 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_WSCALE (1 << 3)
#define OPTION_FAST_OPEN_COOKIE (1 << 8)
#define OPTION_SMC (1 << 9)
+#define OPTION_MPTCP (1 << 10)
static void smc_options_write(__be32 *ptr, u16 *options)
{
@@ -439,8 +441,17 @@ struct tcp_out_options {
__u8 *hash_location; /* temporary pointer, overloaded */
__u32 tsval, tsecr; /* need to include OPTION_TS */
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
+ struct mptcp_out_options mptcp;
};
+static void mptcp_options_write(__be32 *ptr, struct tcp_out_options *opts)
+{
+#if IS_ENABLED(CONFIG_MPTCP)
+ if (unlikely(OPTION_MPTCP & opts->options))
+ mptcp_write_options(ptr, &opts->mptcp);
+#endif
+}
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -549,6 +560,8 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
}
smc_options_write(ptr, &options);
+
+ mptcp_options_write(ptr, opts);
}
static void smc_set_option(const struct tcp_sock *tp,
@@ -1,4 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_MPTCP) += mptcp.o
-mptcp-y := protocol.o
+mptcp-y := protocol.o options.o
new file mode 100644
@@ -0,0 +1,97 @@
+// SPDX-License-Identifier: GPL-2.0
+/* Multipath TCP
+ *
+ * Copyright (c) 2017 - 2019, Intel Corporation.
+ */
+
+#include <linux/kernel.h>
+#include <net/tcp.h>
+#include <net/mptcp.h>
+#include "protocol.h"
+
+void mptcp_parse_option(const unsigned char *ptr, int opsize,
+ struct tcp_options_received *opt_rx)
+{
+ struct mptcp_options_received *mp_opt = &opt_rx->mptcp;
+ u8 subtype = *ptr >> 4;
+ u8 version;
+ u8 flags;
+
+ switch (subtype) {
+ case MPTCPOPT_MP_CAPABLE:
+ if (opsize != TCPOLEN_MPTCP_MPC_SYN &&
+ opsize != TCPOLEN_MPTCP_MPC_ACK)
+ break;
+
+ version = *ptr++ & MPTCP_VERSION_MASK;
+ if (version != MPTCP_SUPPORTED_VERSION)
+ break;
+
+ flags = *ptr++;
+ if (!((flags & MPTCP_CAP_FLAG_MASK) == MPTCP_CAP_HMAC_SHA1) ||
+ (flags & MPTCP_CAP_EXTENSIBILITY))
+ break;
+
+ /* RFC 6824, Section 3.1:
+ * "For the Checksum Required bit (labeled "A"), if either
+ * host requires the use of checksums, checksums MUST be used.
+ * In other words, the only way for checksums not to be used
+ * is if both hosts in their SYNs set A=0."
+ *
+ * Section 3.3.0:
+ * "If a checksum is not present when its use has been
+ * negotiated, the receiver MUST close the subflow with a RST as
+ * it is considered broken."
+ *
+ * We don't implement DSS checksum - fall back to TCP.
+ */
+ if (flags & MPTCP_CAP_CHECKSUM_REQD)
+ break;
+
+ mp_opt->mp_capable = 1;
+ mp_opt->sndr_key = get_unaligned_be64(ptr);
+ ptr += 8;
+
+ if (opsize == TCPOLEN_MPTCP_MPC_ACK) {
+ mp_opt->rcvr_key = get_unaligned_be64(ptr);
+ ptr += 8;
+ pr_debug("MP_CAPABLE sndr=%llu, rcvr=%llu",
+ mp_opt->sndr_key, mp_opt->rcvr_key);
+ } else {
+ pr_debug("MP_CAPABLE sndr=%llu", mp_opt->sndr_key);
+ }
+ break;
+
+ case MPTCPOPT_DSS:
+ pr_debug("DSS");
+ mp_opt->dss = 1;
+ break;
+
+ default:
+ break;
+ }
+}
+
+void mptcp_write_options(__be32 *ptr, struct mptcp_out_options *opts)
+{
+ if ((OPTION_MPTCP_MPC_SYN |
+ OPTION_MPTCP_MPC_ACK) & opts->suboptions) {
+ u8 len;
+
+ if (OPTION_MPTCP_MPC_SYN & opts->suboptions)
+ len = TCPOLEN_MPTCP_MPC_SYN;
+ else
+ len = TCPOLEN_MPTCP_MPC_ACK;
+
+ *ptr++ = htonl((TCPOPT_MPTCP << 24) | (len << 16) |
+ (MPTCPOPT_MP_CAPABLE << 12) |
+ (MPTCP_SUPPORTED_VERSION << 8) |
+ MPTCP_CAP_HMAC_SHA1);
+ put_unaligned_be64(opts->sndr_key, ptr);
+ ptr += 2;
+ if (OPTION_MPTCP_MPC_ACK & opts->suboptions) {
+ put_unaligned_be64(opts->rcvr_key, ptr);
+ ptr += 2;
+ }
+ }
+}
@@ -7,6 +7,35 @@
#ifndef __MPTCP_PROTOCOL_H
#define __MPTCP_PROTOCOL_H
+#define MPTCP_SUPPORTED_VERSION 0
+
+/* MPTCP option bits */
+#define OPTION_MPTCP_MPC_SYN BIT(0)
+#define OPTION_MPTCP_MPC_SYNACK BIT(1)
+#define OPTION_MPTCP_MPC_ACK BIT(2)
+
+/* MPTCP option subtypes */
+#define MPTCPOPT_MP_CAPABLE 0
+#define MPTCPOPT_MP_JOIN 1
+#define MPTCPOPT_DSS 2
+#define MPTCPOPT_ADD_ADDR 3
+#define MPTCPOPT_RM_ADDR 4
+#define MPTCPOPT_MP_PRIO 5
+#define MPTCPOPT_MP_FAIL 6
+#define MPTCPOPT_MP_FASTCLOSE 7
+
+/* MPTCP suboption lengths */
+#define TCPOLEN_MPTCP_MPC_SYN 12
+#define TCPOLEN_MPTCP_MPC_SYNACK 12
+#define TCPOLEN_MPTCP_MPC_ACK 20
+
+/* MPTCP MP_CAPABLE flags */
+#define MPTCP_VERSION_MASK (0x0F)
+#define MPTCP_CAP_CHECKSUM_REQD BIT(7)
+#define MPTCP_CAP_EXTENSIBILITY BIT(6)
+#define MPTCP_CAP_HMAC_SHA1 BIT(0)
+#define MPTCP_CAP_FLAG_MASK (0x3F)
+
/* MPTCP connection sock */
struct mptcp_sock {
/* inet_connection_sock must be the first member */