tcp: TCP experimental option for SMC

The SMC protocol [1] relies on the use of a new TCP experimental
option [2, 3]. With this option, SMC capabilities are exchanged
between peers during the TCP three way handshake. This patch adds
support for this experimental option to TCP.

References:
[1] SMC-R Informational RFC: http://www.rfc-editor.org/info/rfc7609
[2] Shared Use of TCP Experimental Options RFC 6994:
    https://tools.ietf.org/rfc/rfc6994.txt
[3] IANA ExID SMCR:
http://www.iana.org/assignments/tcp-parameters/tcp-parameters.xhtml#tcp-exids

Signed-off-by: Ursula Braun <ubraun@linux.vnet.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 60 insertions, 3 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1f01f4c9c738..c8fc512e0bbb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -41,6 +41,7 @@
 #include <linux/compiler.h>
 #include <linux/gfp.h>
 #include <linux/module.h>
+#include <linux/static_key.h>
 
 #include <trace/events/tcp.h>
 
@@ -422,6 +423,22 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
 #define OPTION_MD5              (1 << 2)
 #define OPTION_WSCALE           (1 << 3)
 #define OPTION_FAST_OPEN_COOKIE (1 << 8)
+#define OPTION_SMC              (1 << 9)
+
+static void smc_options_write(__be32 *ptr, u16 *options)
+{
+#if IS_ENABLED(CONFIG_SMC)
+        if (static_branch_unlikely(&tcp_have_smc)) {
+                if (unlikely(OPTION_SMC & *options)) {
+                        *ptr++ = htonl((TCPOPT_NOP  << 24) |
+                                       (TCPOPT_NOP  << 16) |
+                                       (TCPOPT_EXP <<  8) |
+                                       (TCPOLEN_EXP_SMC_BASE));
+                        *ptr++ = htonl(TCPOPT_SMC_MAGIC);
+                }
+        }
+#endif
+}
 
 struct tcp_out_options {
         u16 options;            /* bit field of OPTION_* */
@@ -540,6 +557,41 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
                 }
                 ptr += (len + 3) >> 2;
         }
+
+        smc_options_write(ptr, &options);
+}
+
+static void smc_set_option(const struct tcp_sock *tp,
+                           struct tcp_out_options *opts,
+                           unsigned int *remaining)
+{
+#if IS_ENABLED(CONFIG_SMC)
+        if (static_branch_unlikely(&tcp_have_smc)) {
+                if (tp->syn_smc) {
+                        if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+                                opts->options |= OPTION_SMC;
+                                *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
+                        }
+                }
+        }
+#endif
+}
+
+static void smc_set_option_cond(const struct tcp_sock *tp,
+                                const struct inet_request_sock *ireq,
+                                struct tcp_out_options *opts,
+                                unsigned int *remaining)
+{
+#if IS_ENABLED(CONFIG_SMC)
+        if (static_branch_unlikely(&tcp_have_smc)) {
+                if (tp->syn_smc && ireq->smc_ok) {
+                        if (*remaining >= TCPOLEN_EXP_SMC_BASE_ALIGNED) {
+                                opts->options |= OPTION_SMC;
+                                *remaining -= TCPOLEN_EXP_SMC_BASE_ALIGNED;
+                        }
+                }
+        }
+#endif
 }
 
 /* Compute TCP options for SYN packets. This is not the final
@@ -607,11 +659,14 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
                 }
         }
 
+        smc_set_option(tp, opts, &remaining);
+
         return MAX_TCP_OPTION_SPACE - remaining;
 }
 
 /* Set up TCP options for SYN-ACKs. */
-static unsigned int tcp_synack_options(struct request_sock *req,
+static unsigned int tcp_synack_options(const struct sock *sk,
+                                       struct request_sock *req,
                                        unsigned int mss, struct sk_buff *skb,
                                        struct tcp_out_options *opts,
                                        const struct tcp_md5sig_key *md5,
@@ -667,6 +722,8 @@ static unsigned int tcp_synack_options(struct request_sock *req,
                 }
         }
 
+        smc_set_option_cond(tcp_sk(sk), ireq, opts, &remaining);
+
         return MAX_TCP_OPTION_SPACE - remaining;
 }
 
@@ -3195,8 +3252,8 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst,
         md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req));
 #endif
         skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4);
-        tcp_header_size = tcp_synack_options(req, mss, skb, &opts, md5, foc) +
-                          sizeof(*th);
+        tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5,
+                                             foc) + sizeof(*th);
 
         skb_push(skb, tcp_header_size);
         skb_reset_transport_header(skb);