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, 35 insertions, 0 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 893286db4623..337f6011528a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -76,6 +76,8 @@
 #include <asm/unaligned.h>
 #include <linux/errqueue.h>
 #include <trace/events/tcp.h>
+#include <linux/unaligned/access_ok.h>
+#include <linux/static_key.h>
 
 int sysctl_tcp_fack __read_mostly;
 int sysctl_tcp_max_reordering __read_mostly = 300;
@@ -3737,6 +3739,21 @@ static void tcp_parse_fastopen_option(int len, const unsigned char *cookie,
         foc->exp = exp_opt;
 }
 
+static void smc_parse_options(const struct tcphdr *th,
+                              struct tcp_options_received *opt_rx,
+                              const unsigned char *ptr,
+                              int opsize)
+{
+#if IS_ENABLED(CONFIG_SMC)
+        if (static_branch_unlikely(&tcp_have_smc)) {
+                if (th->syn && !(opsize & 1) &&
+                    opsize >= TCPOLEN_EXP_SMC_BASE &&
+                    get_unaligned_be32(ptr) == TCPOPT_SMC_MAGIC)
+                        opt_rx->smc_ok = 1;
+        }
+#endif
+}
+
 /* Look for tcp options. Normally only called on SYN and SYNACK packets.
  * But, this can also be called on packets in the established flow when
  * the fast version below fails.
@@ -3844,6 +3861,9 @@ void tcp_parse_options(const struct net *net,
                                         tcp_parse_fastopen_option(opsize -
                                                 TCPOLEN_EXP_FASTOPEN_BASE,
                                                 ptr + 2, th->syn, foc, true);
+                                else
+                                        smc_parse_options(th, opt_rx, ptr,
+                                                          opsize);
                                 break;
 
                         }
@@ -5598,6 +5618,16 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
         return false;
 }
 
+static void smc_check_reset_syn(struct tcp_sock *tp)
+{
+#if IS_ENABLED(CONFIG_SMC)
+        if (static_branch_unlikely(&tcp_have_smc)) {
+                if (tp->syn_smc && !tp->rx_opt.smc_ok)
+                        tp->syn_smc = 0;
+        }
+#endif
+}
+
 static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
                                          const struct tcphdr *th)
 {
@@ -5704,6 +5734,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
                  * is initialized. */
                 tp->copied_seq = tp->rcv_nxt;
 
+                smc_check_reset_syn(tp);
+
                 smp_mb();
 
                 tcp_finish_connect(sk, skb);
@@ -6157,6 +6189,9 @@ static void tcp_openreq_init(struct request_sock *req,
         ireq->ir_rmt_port = tcp_hdr(skb)->source;
         ireq->ir_num = ntohs(tcp_hdr(skb)->dest);
         ireq->ir_mark = inet_request_mark(sk, skb);
+#if IS_ENABLED(CONFIG_SMC)
+        ireq->smc_ok = rx_opt->smc_ok;
+#endif
 }
 
 struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,