net/tcp-fastopen: Add new API support
This patch adds a new socket option, TCP_FASTOPEN_CONNECT, as an
alternative way to perform Fast Open on the active side (client). Prior
to this patch, a client needs to replace the connect() call with
sendto(MSG_FASTOPEN). This can be cumbersome for applications who want
to use Fast Open: these socket operations are often done in lower layer
libraries used by many other applications. Changing these libraries
and/or the socket call sequences are not trivial. A more convenient
approach is to perform Fast Open by simply enabling a socket option when
the socket is created w/o changing other socket calls sequence:
s = socket()
create a new socket
setsockopt(s, IPPROTO_TCP, TCP_FASTOPEN_CONNECT …);
newly introduced sockopt
If set, new functionality described below will be used.
Return ENOTSUPP if TFO is not supported or not enabled in the
kernel.
connect()
With cookie present, return 0 immediately.
With no cookie, initiate 3WHS with TFO cookie-request option and
return -1 with errno = EINPROGRESS.
write()/sendmsg()
With cookie present, send out SYN with data and return the number of
bytes buffered.
With no cookie, and 3WHS not yet completed, return -1 with errno =
EINPROGRESS.
No MSG_FASTOPEN flag is needed.
read()
Return -1 with errno = EWOULDBLOCK/EAGAIN if connect() is called but
write() is not called yet.
Return -1 with errno = EWOULDBLOCK/EAGAIN if connection is
established but no msg is received yet.
Return number of bytes read if socket is established and there is
msg received.
The new API simplifies life for applications that always perform a write()
immediately after a successful connect(). Such applications can now take
advantage of Fast Open by merely making one new setsockopt() call at the time
of creating the socket. Nothing else about the application's socket call
sequence needs to change.
Signed-off-by: Wei Wang <weiwan@google.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Acked-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 5371b3d..f88f464 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -222,7 +222,8 @@ struct tcp_sock {
u32 chrono_stat[3]; /* Time in jiffies for chrono_stat stats */
u8 chrono_type:2, /* current chronograph type */
rate_app_limited:1, /* rate_{delivered,interval_us} limited? */
- unused:5;
+ fastopen_connect:1, /* FASTOPEN_CONNECT sockopt */
+ unused:4;
u8 nonagle : 4,/* Disable Nagle algorithm? */
thin_lto : 1,/* Use linear timeouts for thin streams */
unused1 : 1,
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index c9cff97..aa95053 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -206,7 +206,11 @@ struct inet_sock {
transparent:1,
mc_all:1,
nodefrag:1;
- __u8 bind_address_no_port:1;
+ __u8 bind_address_no_port:1,
+ defer_connect:1; /* Indicates that fastopen_connect is set
+ * and cookie exists so we defer connect
+ * until first data frame is written
+ */
__u8 rcv_tos;
__u8 convert_csum;
int uc_index;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index de67541..6ec4ea6 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1495,6 +1495,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
void tcp_fastopen_init_key_once(bool publish);
bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss,
struct tcp_fastopen_cookie *cookie);
+bool tcp_fastopen_defer_connect(struct sock *sk, int *err);
#define TCP_FASTOPEN_KEY_LENGTH 16
/* Fastopen key context */
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index c53de26..6ff35eb 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -116,6 +116,7 @@ enum {
#define TCP_SAVE_SYN 27 /* Record SYN headers for new connections */
#define TCP_SAVED_SYN 28 /* Get SYN headers recorded for connection */
#define TCP_REPAIR_WINDOW 29 /* Get/set window parameters */
+#define TCP_FASTOPEN_CONNECT 30 /* Attempt FastOpen with connect */
struct tcp_repair_opt {
__u32 opt_code;