* [PATCH 1/7] net-tcp: Fast Open base
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
2012-07-17 6:16 ` David Miller
2012-07-16 21:16 ` [PATCH 2/7] net-tcp: Fast Open client - cookie cache Yuchung Cheng
` (5 subsequent siblings)
6 siblings, 1 reply; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
This patch impelements the common code for both the client and server.
1. TCP Fast Open option processing. Since Fast Open does not have a
option number assigned by IANA yet, it shares the experiment option
code 254 by implementing draft-ietf-tcpm-experimental-options
with a 16 bits magic number 0xF989
2. The new sysctl tcp_fastopen
3. A place holder init function
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
include/linux/tcp.h | 10 ++++++++++
include/net/tcp.h | 9 ++++++++-
net/ipv4/Makefile | 2 +-
net/ipv4/syncookies.c | 2 +-
net/ipv4/sysctl_net_ipv4.c | 7 +++++++
net/ipv4/tcp_fastopen.c | 11 +++++++++++
net/ipv4/tcp_input.c | 26 ++++++++++++++++++++++----
net/ipv4/tcp_ipv4.c | 2 +-
net/ipv4/tcp_minisocks.c | 4 ++--
net/ipv4/tcp_output.c | 25 +++++++++++++++++++++----
net/ipv6/syncookies.c | 2 +-
net/ipv6/tcp_ipv6.c | 2 +-
12 files changed, 86 insertions(+), 16 deletions(-)
create mode 100644 net/ipv4/tcp_fastopen.c
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1888169..12948f5 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -243,6 +243,16 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
return (tcp_hdr(skb)->doff - 5) * 4;
}
+/* TCP Fast Open */
+#define TCP_FASTOPEN_COOKIE_MIN 4 /* Min Fast Open Cookie size in bytes */
+#define TCP_FASTOPEN_COOKIE_MAX 16 /* Max Fast Open Cookie size in bytes */
+
+/* TCP Fast Open Cookie as stored in memory */
+struct tcp_fastopen_cookie {
+ s8 len;
+ u8 val[TCP_FASTOPEN_COOKIE_MAX];
+};
+
/* This defines a selective acknowledgement block. */
struct tcp_sack_block_wire {
__be32 start_seq;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 439984b..87f486f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -170,6 +170,11 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
+#define TCPOPT_EXP 254 /* Experimental */
+/* Magic number to be after the option value for sharing TCP
+ * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
+ */
+#define TCPOPT_FASTOPEN_MAGIC 0xF989
/*
* TCP option lengths
@@ -180,6 +185,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_MD5SIG 18
+#define TCPOLEN_EXP_FASTOPEN_BASE 4
#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */
#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
@@ -222,6 +228,7 @@ extern int sysctl_tcp_retries1;
extern int sysctl_tcp_retries2;
extern int sysctl_tcp_orphan_retries;
extern int sysctl_tcp_syncookies;
+extern int sysctl_tcp_fastopen;
extern int sysctl_tcp_retrans_collapse;
extern int sysctl_tcp_stdurg;
extern int sysctl_tcp_rfc1337;
@@ -417,7 +424,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len, int nonblock, int flags, int *addr_len);
extern void tcp_parse_options(const struct sk_buff *skb,
struct tcp_options_received *opt_rx, const u8 **hvpp,
- int estab);
+ int estab, struct tcp_fastopen_cookie *foc);
extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
/*
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 5a23e8b..63e6995 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -7,7 +7,7 @@ obj-y := route.o inetpeer.o protocol.o \
ip_output.o ip_sockglue.o inet_hashtables.o \
inet_timewait_sock.o inet_connection_sock.o \
tcp.o tcp_input.o tcp_output.o tcp_timer.o tcp_ipv4.o \
- tcp_minisocks.o tcp_cong.o tcp_metrics.o \
+ tcp_minisocks.o tcp_cong.o tcp_metrics.o tcp_fastopen.o \
datagram.o raw.o udp.o udplite.o \
arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o \
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index eab2a7f..650e152 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -293,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
goto out;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 70730f7..2a946a19 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -367,6 +367,13 @@ static struct ctl_table ipv4_table[] = {
},
#endif
{
+ .procname = "tcp_fastopen",
+ .data = &sysctl_tcp_fastopen,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "tcp_tw_recycle",
.data = &tcp_death_row.sysctl_tw_recycle,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
new file mode 100644
index 0000000..a7f729c
--- /dev/null
+++ b/net/ipv4/tcp_fastopen.c
@@ -0,0 +1,11 @@
+#include <linux/init.h>
+#include <linux/kernel.h>
+
+int sysctl_tcp_fastopen;
+
+static int __init tcp_fastopen_init(void)
+{
+ return 0;
+}
+
+late_initcall(tcp_fastopen_init);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 055ac49..d6e16e2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3729,7 +3729,8 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx,
- const u8 **hvpp, int estab)
+ const u8 **hvpp, int estab,
+ struct tcp_fastopen_cookie *foc)
{
const unsigned char *ptr;
const struct tcphdr *th = tcp_hdr(skb);
@@ -3836,8 +3837,25 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
break;
}
break;
- }
+ case TCPOPT_EXP:
+ /* Fast Open option shares code 254 using a
+ * 16 bits magic number. It's valid only in
+ * SYN or SYN-ACK with an even size.
+ */
+ if (opsize < TCPOLEN_EXP_FASTOPEN_BASE ||
+ get_unaligned_be16(ptr) != TCPOPT_FASTOPEN_MAGIC ||
+ foc == NULL || !th->syn || (opsize & 1))
+ break;
+ foc->len = opsize - TCPOLEN_EXP_FASTOPEN_BASE;
+ if (foc->len >= TCP_FASTOPEN_COOKIE_MIN &&
+ foc->len <= TCP_FASTOPEN_COOKIE_MAX)
+ memcpy(foc->val, ptr + 2, foc->len);
+ else if (foc->len != 0)
+ foc->len = -1;
+ break;
+
+ }
ptr += opsize-2;
length -= opsize;
}
@@ -3879,7 +3897,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
if (tcp_parse_aligned_timestamp(tp, th))
return true;
}
- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
+ tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
return true;
}
@@ -5601,7 +5619,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcp_cookie_values *cvp = tp->cookie_values;
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, NULL);
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7a0062c..588200e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1314,7 +1314,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index c66f2ed..5912ac3 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -97,7 +97,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -534,7 +534,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 15a7c7b..4849be7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -385,15 +385,17 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_MD5 (1 << 2)
#define OPTION_WSCALE (1 << 3)
#define OPTION_COOKIE_EXTENSION (1 << 4)
+#define OPTION_FAST_OPEN_COOKIE (1 << 8)
struct tcp_out_options {
- u8 options; /* bit field of OPTION_* */
+ u16 options; /* bit field of OPTION_* */
+ u16 mss; /* 0 to disable */
u8 ws; /* window scale, 0 to disable */
u8 num_sack_blocks; /* number of SACK blocks to include */
u8 hash_size; /* bytes in hash_location */
- u16 mss; /* 0 to disable */
- __u32 tsval, tsecr; /* need to include OPTION_TS */
__u8 *hash_location; /* temporary pointer, overloaded */
+ __u32 tsval, tsecr; /* need to include OPTION_TS */
+ struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
};
/* The sysctl int routines are generic, so check consistency here.
@@ -442,7 +444,7 @@ static u8 tcp_cookie_size_check(u8 desired)
static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
struct tcp_out_options *opts)
{
- u8 options = opts->options; /* mungable copy */
+ u16 options = opts->options; /* mungable copy */
/* Having both authentication and cookies for security is redundant,
* and there's certainly not enough room. Instead, the cookie-less
@@ -564,6 +566,21 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
tp->rx_opt.dsack = 0;
}
+
+ if (unlikely(OPTION_FAST_OPEN_COOKIE & options)) {
+ struct tcp_fastopen_cookie *foc = opts->fastopen_cookie;
+
+ *ptr++ = htonl((TCPOPT_EXP << 24) |
+ ((TCPOLEN_EXP_FASTOPEN_BASE + foc->len) << 16) |
+ TCPOPT_FASTOPEN_MAGIC);
+
+ memcpy(ptr, foc->val, foc->len);
+ if ((foc->len & 3) == 2) {
+ u8 *align = ((u8 *)ptr) + foc->len;
+ align[0] = align[1] = TCPOPT_NOP;
+ }
+ ptr += (foc->len + 3) >> 2;
+ }
}
/* Compute TCP options for SYN packets. This is not the final
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 7bf3cc4..bb46061 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -177,7 +177,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, &ecn_ok))
goto out;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 3071f37..41eaeb5 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1062,7 +1062,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH 1/7] net-tcp: Fast Open base
2012-07-16 21:16 ` [PATCH 1/7] net-tcp: Fast Open base Yuchung Cheng
@ 2012-07-17 6:16 ` David Miller
2012-07-18 19:55 ` Eric Dumazet
0 siblings, 1 reply; 14+ messages in thread
From: David Miller @ 2012-07-17 6:16 UTC (permalink / raw)
To: ycheng; +Cc: hkchu, edumazet, ncardwell, sivasankar, netdev
From: Yuchung Cheng <ycheng@google.com>
Date: Mon, 16 Jul 2012 14:16:44 -0700
> +#define TCPOPT_EXP 254 /* Experimental */
> +/* Magic number to be after the option value for sharing TCP
> + * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
> + */
> +#define TCPOPT_FASTOPEN_MAGIC 0xF989
If I apply this, we're stuck supporting this experimental number
forever.
Because somewhere, someone will have a kernel running using this
number, so we have to support this option value as well as whatever
the official one is.
Therefore I think the only logical thing we can do is only deploy
this once an official option number is choosen.
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH 1/7] net-tcp: Fast Open base
2012-07-17 6:16 ` David Miller
@ 2012-07-18 19:55 ` Eric Dumazet
2012-07-18 20:18 ` David Miller
0 siblings, 1 reply; 14+ messages in thread
From: Eric Dumazet @ 2012-07-18 19:55 UTC (permalink / raw)
To: David Miller; +Cc: ycheng, hkchu, edumazet, ncardwell, sivasankar, netdev
On Mon, 2012-07-16 at 23:16 -0700, David Miller wrote:
> From: Yuchung Cheng <ycheng@google.com>
> Date: Mon, 16 Jul 2012 14:16:44 -0700
>
> > +#define TCPOPT_EXP 254 /* Experimental */
> > +/* Magic number to be after the option value for sharing TCP
> > + * experimental options. See draft-ietf-tcpm-experimental-options-00.txt
> > + */
> > +#define TCPOPT_FASTOPEN_MAGIC 0xF989
>
> If I apply this, we're stuck supporting this experimental number
> forever.
>
> Because somewhere, someone will have a kernel running using this
> number, so we have to support this option value as well as whatever
> the official one is.
>
> Therefore I think the only logical thing we can do is only deploy
> this once an official option number is choosen.
Hi David
This is a chicken and egg problem.
IANA wont grant an official number like that in 2012+. Maybe if billions
of Android/linux devices use TFO in 2015 IANA will grant an official
number.
So we chose to follow Joe touch proposal
(http://tools.ietf.org/html/draft-ietf-tcpm-experimental-options-01) and
the magic 0xF989 was generated according to section 3) to avoid possible
clashes with other experimental options using code option 254
(Code options 253 & 254 are reserved for experimental use.
Linux Cookie extension uses 253 without a magic cookie so 253 cannot be
shared. By the way I wonder if anybody uses it... oh well...)
Only servers will need to cope with this experimental option plus the
official one (_if_ IANA accepts to unblock one of the many reserved
options, in two or three years)
Yuchung only posted the Client side in this patch series. But we already
run the server side, and supporting the official TFO option plus the
experimental one is adding less than 10 lines of code.
So the plan would be :
1) Use the experimental 254 + magic on TFO Clients/Servers in 2012
2) When/If IANA grants an official number, add its support to servers
(keeping support for experimental option as well)
3) One/two years later, switch client side to use this official number
4) Ten years later, remove experimental from server side.
Thanks !
PS :
TFO is not mandatory : If the initial SYN TFO option is not understood
by a server, it will reply with a SYN/ACK without the option and cookie,
and client will proceed as today.
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH 1/7] net-tcp: Fast Open base
2012-07-18 19:55 ` Eric Dumazet
@ 2012-07-18 20:18 ` David Miller
0 siblings, 0 replies; 14+ messages in thread
From: David Miller @ 2012-07-18 20:18 UTC (permalink / raw)
To: eric.dumazet; +Cc: ycheng, hkchu, edumazet, ncardwell, sivasankar, netdev
From: Eric Dumazet <eric.dumazet@gmail.com>
Date: Wed, 18 Jul 2012 21:55:49 +0200
> So the plan would be :
>
> 1) Use the experimental 254 + magic on TFO Clients/Servers in 2012
>
> 2) When/If IANA grants an official number, add its support to servers
> (keeping support for experimental option as well)
>
> 3) One/two years later, switch client side to use this official number
>
> 4) Ten years later, remove experimental from server side.
Fair enough.
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH 2/7] net-tcp: Fast Open client - cookie cache
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
2012-07-16 21:16 ` [PATCH 1/7] net-tcp: Fast Open base Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
2012-07-17 6:15 ` David Miller
2012-07-16 21:16 ` [PATCH 3/7] net-tcp: Fast Open client - sending SYN-data Yuchung Cheng
` (4 subsequent siblings)
6 siblings, 1 reply; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
The Fast Open cookie cache is used by a TCP Fast Open client to store
remote servers' Fast Open cookies. It stores one Fast Open cookie
per IP (v4 or v6) and by default 1024 cookies total. The size is
tunable via /proc/sys/net/ipv4/tcp_fastopen_cookies. Setting it to 0
will flush the cache.
The inetpeer cache also caches remote peer's information but the
in-active cache entries are recycled on the scale of minutes. Therefore
a separate storage is required but the lookup is done via inetpeer.
Each inetpeer entry holds a cookie cache entry pointer (if TFO is used
on that IP). On cache write, the cookie cache entry is allocated and
stored in a list for LRU replacement. A spinlock protects any R/W
operation on the cookie cache entry and the list.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
include/net/inetpeer.h | 2 +
include/net/tcp.h | 6 ++
net/ipv4/inetpeer.c | 2 +
net/ipv4/sysctl_net_ipv4.c | 26 ++++++++
net/ipv4/tcp_fastopen.c | 140 ++++++++++++++++++++++++++++++++++++++++++++
5 files changed, 176 insertions(+), 0 deletions(-)
diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h
index 53f464d..0240709 100644
--- a/include/net/inetpeer.h
+++ b/include/net/inetpeer.h
@@ -11,6 +11,7 @@
#include <linux/init.h>
#include <linux/jiffies.h>
#include <linux/spinlock.h>
+#include <linux/tcp.h>
#include <linux/rtnetlink.h>
#include <net/ipv6.h>
#include <linux/atomic.h>
@@ -53,6 +54,7 @@ struct inet_peer {
struct rcu_head rcu;
struct inet_peer *gc_next;
};
+ struct fastopen_entry *fastopen;
/* following fields might be frequently dirtied */
__u32 dtime; /* the time of last use of not referenced entries */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 87f486f..4b29688 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -385,6 +385,12 @@ enum tcp_tw_status {
TCP_TW_SYN = 3
};
+/* From tcp_fastopen.c */
+extern int tcp_fastopen_size_cache(int size);
+extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
+ struct tcp_fastopen_cookie *cookie);
+extern void tcp_fastopen_cache_set(struct sock *sk, u16 *mss,
+ struct tcp_fastopen_cookie *cookie);
extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
struct sk_buff *skb,
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index e1e0a4e..9151ddc 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -63,6 +63,7 @@
* usually under some other lock to prevent node disappearing
* daddr: unchangeable
* ip_id_count: atomic value (no lock needed)
+ * fastopen_entry: TCP Fast Open cookie cache. See tcp_fastopen.c
*/
static struct kmem_cache *peer_cachep __read_mostly;
@@ -511,6 +512,7 @@ relookup:
p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW;
p->rate_tokens = 0;
p->rate_last = 0;
+ p->fastopen = NULL;
INIT_LIST_HEAD(&p->gc_list);
/* Link the node. */
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 2a946a19..8d4571a 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,7 @@
static int zero;
static int two = 2;
static int tcp_retr1_max = 255;
+static int tcp_fastopen_cookies_max = 65536;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
static int tcp_adv_win_scale_min = -31;
@@ -220,6 +221,25 @@ static int ipv4_tcp_mem(ctl_table *ctl, int write,
return 0;
}
+static int proc_tcp_fastopen_cache_size(ctl_table *ctl, int write,
+ void __user *buffer, size_t *lenp,
+ loff_t *ppos)
+{
+ int ret;
+ int max_cookies = tcp_fastopen_size_cache(-1);
+ ctl_table tbl = {
+ .data = &max_cookies,
+ .maxlen = sizeof(max_cookies),
+ .extra1 = &zero,
+ .extra2 = &tcp_fastopen_cookies_max,
+ };
+
+ ret = proc_dointvec_minmax(&tbl, write, buffer, lenp, ppos);
+ if (write && ret == 0)
+ tcp_fastopen_size_cache(max_cookies);
+ return ret;
+}
+
static struct ctl_table ipv4_table[] = {
{
.procname = "tcp_timestamps",
@@ -374,6 +394,12 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec,
},
{
+ .procname = "tcp_fastopen_cookies",
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_tcp_fastopen_cache_size,
+ },
+ {
.procname = "tcp_tw_recycle",
.data = &tcp_death_row.sysctl_tw_recycle,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index a7f729c..40fdf21 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -1,10 +1,150 @@
#include <linux/init.h>
#include <linux/kernel.h>
+#include <linux/list.h>
+#include <linux/tcp.h>
+#include <net/inetpeer.h>
int sysctl_tcp_fastopen;
+/* The Fast Open cookie cache is used by a TCP Fast Open client to store
+ * remote servers' Fast Open cookies. It stores one Fast Open cookie
+ * per IP and by default 1024 cookies total. The size is tunable via
+ * /proc/sys/net/ipv4/tcp_fastopen_cookies. Setting it to 0 will flush
+ * the cache.
+ *
+ * The inetpeer cache also caches remote peer's information but the
+ * in-active cache entries are recycled on the scale of minutes. Therefore
+ * a separate storage is required but the lookup is done via inetpeer.
+ * Each inetpeer entry holds a cookie cache entry pointer (if TFO is used
+ * on that IP). On cache write, the cookie cache entry is allocated and
+ * stored in a list for LRU replacement. A spinlock protects any R/W
+ * operation on the cookie cache entry and the list.
+ */
+struct fastopen_entry {
+ u16 mss; /* TCP MSS value */
+ struct tcp_fastopen_cookie cookie; /* TCP Fast Open cookie */
+ struct list_head lru_list; /* cookie cache lru_list node */
+ struct inet_peer *peer; /* inetpeer entry (for fast lookup) */
+};
+
+static struct tcp_fastopen_cookie_cache {
+ spinlock_t lock; /* for lru_list, cnt, size, entries */
+ struct list_head lru_list; /* head is the least recently used */
+ int cnt; /* size of lru_list */
+ int size; /* cache capacity */
+} cookie_cache;
+
+/* Evict the LRU entry if cache is full. Caller must hold cooke_cache.lock */
+static struct fastopen_entry *__tcp_fastopen_remove_lru(void)
+{
+ struct fastopen_entry *entry;
+
+ if (cookie_cache.cnt <= cookie_cache.size || cookie_cache.cnt <= 0)
+ return NULL;
+
+ entry = list_first_entry(&cookie_cache.lru_list,
+ struct fastopen_entry, lru_list);
+ list_del_init(&entry->lru_list);
+ --cookie_cache.cnt;
+ entry->peer->fastopen = NULL;
+ return entry;
+}
+
+int tcp_fastopen_size_cache(int size)
+{
+ while (size >= 0) {
+ struct fastopen_entry *lru_entry;
+
+ spin_lock_bh(&cookie_cache.lock);
+ cookie_cache.size = size;
+ lru_entry = __tcp_fastopen_remove_lru();
+ spin_unlock_bh(&cookie_cache.lock);
+
+ if (lru_entry == NULL)
+ break;
+ inet_putpeer(lru_entry->peer);
+ kfree(lru_entry);
+ }
+ return cookie_cache.size;
+}
+
+static struct inet_peer *tcp_fastopen_inetpeer(struct sock *sk, int create)
+{
+ struct net *net = dev_net(__sk_dst_get(sk)->dev);
+
+ if (sk->sk_family == AF_INET)
+ return inet_getpeer_v4(net->ipv4.peers,
+ inet_sk(sk)->inet_daddr, create);
+ else if (sk->sk_family == AF_INET6)
+ return inet_getpeer_v6(net->ipv6.peers,
+ &inet6_sk(sk)->daddr, create);
+ return NULL;
+}
+
+void tcp_fastopen_cache_get(struct sock *sk, u32 *mss,
+ struct tcp_fastopen_cookie *cookie)
+{
+ struct inet_peer *peer = tcp_fastopen_inetpeer(sk, 0);
+ struct fastopen_entry *entry;
+
+ if (peer == NULL)
+ return;
+
+ spin_lock_bh(&cookie_cache.lock);
+ entry = peer->fastopen;
+ if (entry != NULL) {
+ *mss = entry->mss;
+ *cookie = entry->cookie;
+ list_move_tail(&entry->lru_list, &cookie_cache.lru_list);
+ }
+ spin_unlock_bh(&cookie_cache.lock);
+
+ inet_putpeer(peer);
+}
+
+void tcp_fastopen_cache_set(struct sock *sk, u32 *mss,
+ struct tcp_fastopen_cookie *cookie)
+{
+ struct inet_peer *peer = tcp_fastopen_inetpeer(sk, 1);
+ struct fastopen_entry *entry = NULL, *new_entry = NULL;
+
+ if (peer == NULL)
+ return;
+
+ spin_lock_bh(&cookie_cache.lock);
+ if (peer->fastopen == NULL) {
+ new_entry = kmalloc(sizeof(struct fastopen_entry), GFP_ATOMIC);
+ if (new_entry == NULL) {
+ spin_unlock_bh(&cookie_cache.lock);
+ goto out;
+ }
+ new_entry->peer = peer;
+ INIT_LIST_HEAD(&new_entry->lru_list);
+ peer->fastopen = new_entry;
+ ++cookie_cache.cnt;
+ }
+ entry = peer->fastopen;
+ entry->mss = *mss;
+ if (cookie->len > 0)
+ entry->cookie = *cookie;
+ list_move_tail(&entry->lru_list, &cookie_cache.lru_list);
+ entry = __tcp_fastopen_remove_lru();
+ spin_unlock_bh(&cookie_cache.lock);
+
+ if (entry) {
+ inet_putpeer(entry->peer);
+ kfree(entry);
+ }
+out:
+ if (new_entry == NULL)
+ inet_putpeer(peer);
+}
+
static int __init tcp_fastopen_init(void)
{
+ INIT_LIST_HEAD(&cookie_cache.lru_list);
+ spin_lock_init(&cookie_cache.lock);
+ cookie_cache.size = 1024;
return 0;
}
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH 2/7] net-tcp: Fast Open client - cookie cache
2012-07-16 21:16 ` [PATCH 2/7] net-tcp: Fast Open client - cookie cache Yuchung Cheng
@ 2012-07-17 6:15 ` David Miller
0 siblings, 0 replies; 14+ messages in thread
From: David Miller @ 2012-07-17 6:15 UTC (permalink / raw)
To: ycheng; +Cc: hkchu, edumazet, ncardwell, sivasankar, netdev
From: Yuchung Cheng <ycheng@google.com>
Date: Mon, 16 Jul 2012 14:16:45 -0700
> The Fast Open cookie cache is used by a TCP Fast Open client to store
> remote servers' Fast Open cookies. It stores one Fast Open cookie
> per IP (v4 or v6) and by default 1024 cookies total. The size is
> tunable via /proc/sys/net/ipv4/tcp_fastopen_cookies. Setting it to 0
> will flush the cache.
>
> The inetpeer cache also caches remote peer's information but the
> in-active cache entries are recycled on the scale of minutes. Therefore
> a separate storage is required but the lookup is done via inetpeer.
> Each inetpeer entry holds a cookie cache entry pointer (if TFO is used
> on that IP). On cache write, the cookie cache entry is allocated and
> stored in a list for LRU replacement. A spinlock protects any R/W
> operation on the cookie cache entry and the list.
>
> Signed-off-by: Yuchung Cheng <ycheng@google.com>
I would store these in the new tcp metrics cache.
Any argument against doing so wrt. expiry is bogus, because you can
implement whatever time limit you want using a jiffies based
expiration value.
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH 3/7] net-tcp: Fast Open client - sending SYN-data
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
2012-07-16 21:16 ` [PATCH 1/7] net-tcp: Fast Open base Yuchung Cheng
2012-07-16 21:16 ` [PATCH 2/7] net-tcp: Fast Open client - cookie cache Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
2012-07-16 21:16 ` [PATCH 4/7] net-tcp: Fast Open client - receiving SYN-ACK Yuchung Cheng
` (3 subsequent siblings)
6 siblings, 0 replies; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
This patch implements sending SYN-data in tcp_connect(). The data is
from tcp_sendmsg() with flag MSG_FASTOPEN (implemented in a later patch).
The length of the cookie in tcp_fastopen_req, init'd to 0, controls the
type of the SYN. If the cookie is not cached (len==0), the host sends
data-less SYN with Fast Open cookie request option to solicit a cookie
from the remote. If cookie is not available (len > 0), the host sends
a SYN-data with Fast Open cookie option. If cookie length is negative,
the SYN will not include any Fast Open option (for fall back operations).
To deal with middleboxes that may drop SYN with data or experimental TCP
option, the SYN-data is only sent once. SYN retransmits do not include
data or Fast Open options. The connection will fall back to regular TCP
handshake.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
include/linux/snmp.h | 3 +-
include/linux/tcp.h | 6 ++-
include/net/tcp.h | 9 ++++
net/ipv4/af_inet.c | 7 +++
net/ipv4/proc.c | 1 +
net/ipv4/tcp_output.c | 115 +++++++++++++++++++++++++++++++++++++++++++++----
6 files changed, 130 insertions(+), 11 deletions(-)
diff --git a/include/linux/snmp.h b/include/linux/snmp.h
index 2e68f5b..c0a34c6 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -233,7 +233,8 @@ enum
LINUX_MIB_TCPREQQFULLDOCOOKIES, /* TCPReqQFullDoCookies */
LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */
LINUX_MIB_TCPRETRANSFAIL, /* TCPRetransFail */
- LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */
+ LINUX_MIB_TCPRCVCOALESCE, /* TCPRcvCoalesce */
+ LINUX_MIB_TCPFASTOPENACTIVE, /* TCPFastOpenActive */
__LINUX_MIB_MAX
};
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 12948f5..1edf96a 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -386,7 +386,8 @@ struct tcp_sock {
unused : 1;
u8 repair_queue;
u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */
- early_retrans_delayed:1; /* Delayed ER timer installed */
+ early_retrans_delayed:1, /* Delayed ER timer installed */
+ syn_fastopen:1; /* SYN includes Fast Open option */
/* RTT measurement */
u32 srtt; /* smoothed round trip time << 3 */
@@ -500,6 +501,9 @@ struct tcp_sock {
struct tcp_md5sig_info __rcu *md5sig_info;
#endif
+/* TCP fastopen related information */
+ struct tcp_fastopen_request *fastopen_req;
+
/* When the cookie options are generated and exchanged, then this
* object holds a reference to them (cookie_values->kref). Also
* contains related tcp_cookie_transactions fields.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 4b29688..2d3b09d2 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1290,6 +1290,15 @@ extern int tcp_md5_hash_skb_data(struct tcp_md5sig_pool *, const struct sk_buff
extern int tcp_md5_hash_key(struct tcp_md5sig_pool *hp,
const struct tcp_md5sig_key *key);
+struct tcp_fastopen_request {
+ /* Fast Open cookie. Size 0 means a cookie request */
+ struct tcp_fastopen_cookie cookie;
+ struct msghdr *data; /* data in MSG_FASTOPEN */
+ u16 copied; /* queued in tcp_connect() */
+};
+
+void tcp_free_fastopen_req(struct tcp_sock *tp);
+
/* write queue abstraction */
static inline void tcp_write_queue_purge(struct sock *sk)
{
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 07a02f6..6ef67b7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -558,9 +558,14 @@ EXPORT_SYMBOL(inet_dgram_connect);
static long inet_wait_for_connect(struct sock *sk, long timeo)
{
+ const bool write = (sk->sk_protocol == IPPROTO_TCP) &&
+ tcp_sk(sk)->fastopen_req &&
+ tcp_sk(sk)->fastopen_req->data;
DEFINE_WAIT(wait);
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+ if (write)
+ sk->sk_write_pending++;
/* Basic assumption: if someone sets sk->sk_err, he _must_
* change state of the socket from TCP_SYN_*.
@@ -576,6 +581,8 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
}
finish_wait(sk_sleep(sk), &wait);
+ if (write)
+ sk->sk_write_pending--;
return timeo;
}
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8af0d44..8f8c842 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -258,6 +258,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP),
SNMP_MIB_ITEM("TCPRetransFail", LINUX_MIB_TCPRETRANSFAIL),
SNMP_MIB_ITEM("TCPRcvCoalesce", LINUX_MIB_TCPRCVCOALESCE),
+ SNMP_MIB_ITEM("TCPFastOpenActive", LINUX_MIB_TCPFASTOPENACTIVE),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 4849be7..8869328 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -596,6 +596,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
tcp_cookie_size_check(cvp->cookie_desired) :
0;
+ struct tcp_fastopen_request *fastopen = tp->fastopen_req;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -636,6 +637,16 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
remaining -= TCPOLEN_SACKPERM_ALIGNED;
}
+ if (fastopen && fastopen->cookie.len >= 0) {
+ u32 need = TCPOLEN_EXP_FASTOPEN_BASE + fastopen->cookie.len;
+ need = (need + 3) & ~3U; /* Align to 32 bits */
+ if (remaining >= need) {
+ opts->options |= OPTION_FAST_OPEN_COOKIE;
+ opts->fastopen_cookie = &fastopen->cookie;
+ remaining -= need;
+ tp->syn_fastopen = 1;
+ }
+ }
/* Note that timestamps are required by the specification.
*
* Odd numbers of bytes are prohibited by the specification, ensuring
@@ -2824,6 +2835,96 @@ void tcp_connect_init(struct sock *sk)
tcp_clear_retrans(tp);
}
+static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_skb_cb *tcb = TCP_SKB_CB(skb);
+
+ tcb->end_seq += skb->len;
+ skb_header_release(skb);
+ __tcp_add_write_queue_tail(sk, skb);
+ sk->sk_wmem_queued += skb->truesize;
+ sk_mem_charge(sk, skb->truesize);
+ tp->write_seq = tcb->end_seq;
+ tp->packets_out += tcp_skb_pcount(skb);
+}
+
+/* Build and send a SYN with data and (cached) Fast Open cookie. However,
+ * queue a data-only packet after the regular SYN, such that regular SYNs
+ * are retransmitted on timeouts. Also if the remote SYN-ACK acknowledges
+ * only the SYN sequence, the data are retransmitted in the first ACK.
+ * If cookie is not cached or other error occurs, falls back to send a
+ * regular SYN with Fast Open cookie request option.
+ */
+static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct tcp_fastopen_request *fo = tp->fastopen_req;
+ int space, i, err = 0, iovlen = fo->data->msg_iovlen;
+ struct sk_buff *syn_data = NULL, *data;
+
+ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie);
+ if (fo->cookie.len <= 0)
+ goto fallback;
+
+ /* MSS for SYN-data is based on cached MSS and bounded by PMTU and
+ * user-MSS. Reserve maximum option space for middleboxes that add
+ * private TCP options. The cost is reduced data space in SYN :(
+ */
+ if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->rx_opt.mss_clamp)
+ tp->rx_opt.mss_clamp = tp->rx_opt.user_mss;
+ space = tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+ MAX_TCP_OPTION_SPACE;
+
+ syn_data = skb_copy_expand(syn, skb_headroom(syn), space,
+ sk->sk_allocation);
+ if (syn_data == NULL)
+ goto fallback;
+
+ for (i = 0; i < iovlen && syn_data->len < space; ++i) {
+ struct iovec *iov = &fo->data->msg_iov[i];
+ unsigned char __user *from = iov->iov_base;
+ int len = iov->iov_len;
+
+ if (syn_data->len + len > space)
+ len = space - syn_data->len;
+ else if (i + 1 == iovlen)
+ /* No more data pending in inet_wait_for_connect() */
+ fo->data = NULL;
+
+ if (skb_add_data(syn_data, from, len))
+ goto fallback;
+ }
+
+ /* Queue a data-only packet after the regular SYN for retransmission */
+ data = pskb_copy(syn_data, sk->sk_allocation);
+ if (data == NULL)
+ goto fallback;
+ TCP_SKB_CB(data)->seq++;
+ TCP_SKB_CB(data)->tcp_flags &= ~TCPHDR_SYN;
+ TCP_SKB_CB(data)->tcp_flags = (TCPHDR_ACK|TCPHDR_PSH);
+ tcp_connect_queue_skb(sk, data);
+ fo->copied = data->len;
+
+ if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
+ goto done;
+ }
+ syn_data = NULL;
+
+fallback:
+ /* Send a regular SYN with Fast Open cookie request option */
+ if (fo->cookie.len > 0)
+ fo->cookie.len = 0;
+ err = tcp_transmit_skb(sk, syn, 1, sk->sk_allocation);
+ if (err)
+ tp->syn_fastopen = 0;
+ kfree_skb(syn_data);
+done:
+ fo->cookie.len = -1; /* Exclude Fast Open option for SYN retries */
+ return err;
+}
+
/* Build a SYN and send it off. */
int tcp_connect(struct sock *sk)
{
@@ -2841,17 +2942,13 @@ int tcp_connect(struct sock *sk)
skb_reserve(buff, MAX_TCP_HEADER);
tcp_init_nondata_skb(buff, tp->write_seq++, TCPHDR_SYN);
+ tp->retrans_stamp = TCP_SKB_CB(buff)->when = tcp_time_stamp;
+ tcp_connect_queue_skb(sk, buff);
TCP_ECN_send_syn(sk, buff);
- /* Send it off. */
- TCP_SKB_CB(buff)->when = tcp_time_stamp;
- tp->retrans_stamp = TCP_SKB_CB(buff)->when;
- skb_header_release(buff);
- __tcp_add_write_queue_tail(sk, buff);
- sk->sk_wmem_queued += buff->truesize;
- sk_mem_charge(sk, buff->truesize);
- tp->packets_out += tcp_skb_pcount(buff);
- err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
+ /* Send off SYN; include data in Fast Open. */
+ err = tp->fastopen_req ? tcp_send_syn_data(sk, buff) :
+ tcp_transmit_skb(sk, buff, 1, sk->sk_allocation);
if (err == -ECONNREFUSED)
return err;
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 4/7] net-tcp: Fast Open client - receiving SYN-ACK
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
` (2 preceding siblings ...)
2012-07-16 21:16 ` [PATCH 3/7] net-tcp: Fast Open client - sending SYN-data Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
2012-07-16 22:57 ` Vijay Subramanian
2012-07-16 21:16 ` [PATCH 5/7] net-tcp: Fast Open client - sendmsg(MSG_FASTOPEN) Yuchung Cheng
` (2 subsequent siblings)
6 siblings, 1 reply; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
On receiving the SYN-ACK after SYN-data, the client needs to
a) update the cached MSS and cookie (if included in SYN-ACK)
b) retransmit the data yet acknowledged by the SYN-ACK in the final ACK of
the handshake.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
net/ipv4/tcp_input.c | 40 +++++++++++++++++++++++++++++++++++-----
1 files changed, 35 insertions(+), 5 deletions(-)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d6e16e2..5b09f71 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5610,6 +5610,34 @@ void tcp_finish_connect(struct sock *sk, struct sk_buff *skb)
}
}
+static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
+ struct tcp_fastopen_cookie *cookie)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ struct sk_buff *data = tcp_write_queue_head(sk);
+ u16 mss = tp->rx_opt.mss_clamp;
+
+ if (mss == tp->rx_opt.user_mss) {
+ struct tcp_options_received opt;
+ const u8 *hash_location;
+
+ /* Get original SYNACK MSS value if user MSS sets mss_clamp */
+ tcp_clear_options(&opt);
+ opt.user_mss = opt.mss_clamp = 0;
+ tcp_parse_options(synack, &opt, &hash_location, 0, NULL);
+ mss = opt.mss_clamp;
+ }
+
+ tcp_fastopen_cache_set(sk, &mss, cookie);
+
+ if (data) { /* Retransmit unacked data in SYN */
+ tcp_retransmit_skb(sk, data);
+ tcp_rearm_rto(sk);
+ return true;
+ }
+ return false;
+}
+
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, unsigned int len)
{
@@ -5617,9 +5645,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
+ struct tcp_fastopen_cookie foc = { .len = -1 };
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc);
if (th->ack) {
/* rfc793:
@@ -5629,11 +5658,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* If SEG.ACK =< ISS, or SEG.ACK > SND.NXT, send
* a reset (unless the RST bit is set, if so drop
* the segment and return)"
- *
- * We do not send data with SYN, so that RFC-correct
- * test reduces to:
*/
- if (TCP_SKB_CB(skb)->ack_seq != tp->snd_nxt)
+ if (!after(TCP_SKB_CB(skb)->ack_seq, tp->snd_una) ||
+ after(TCP_SKB_CB(skb)->ack_seq, tp->snd_nxt))
goto reset_and_undo;
if (tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr &&
@@ -5745,6 +5772,9 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
tcp_finish_connect(sk, skb);
+ if (tp->syn_fastopen && tcp_rcv_fastopen_synack(sk, skb, &foc))
+ return -1;
+
if (sk->sk_write_pending ||
icsk->icsk_accept_queue.rskq_defer_accept ||
icsk->icsk_ack.pingpong) {
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread* Re: [PATCH 4/7] net-tcp: Fast Open client - receiving SYN-ACK
2012-07-16 21:16 ` [PATCH 4/7] net-tcp: Fast Open client - receiving SYN-ACK Yuchung Cheng
@ 2012-07-16 22:57 ` Vijay Subramanian
2012-07-16 23:33 ` Yuchung Cheng
0 siblings, 1 reply; 14+ messages in thread
From: Vijay Subramanian @ 2012-07-16 22:57 UTC (permalink / raw)
To: Yuchung Cheng; +Cc: davem, hkchu, edumazet, ncardwell, sivasankar, netdev
On 16 July 2012 14:16, Yuchung Cheng <ycheng@google.com> wrote:
> On receiving the SYN-ACK after SYN-data, the client needs to
> a) update the cached MSS and cookie (if included in SYN-ACK)
> b) retransmit the data yet acknowledged by the SYN-ACK in the final ACK of
> the handshake.
I think you mean "data not yet acknowledged " in point (b).
Vijay
^ permalink raw reply [flat|nested] 14+ messages in thread
* Re: [PATCH 4/7] net-tcp: Fast Open client - receiving SYN-ACK
2012-07-16 22:57 ` Vijay Subramanian
@ 2012-07-16 23:33 ` Yuchung Cheng
0 siblings, 0 replies; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 23:33 UTC (permalink / raw)
To: Vijay Subramanian; +Cc: davem, hkchu, edumazet, ncardwell, sivasankar, netdev
On Mon, Jul 16, 2012 at 3:57 PM, Vijay Subramanian
<subramanian.vijay@gmail.com> wrote:
> On 16 July 2012 14:16, Yuchung Cheng <ycheng@google.com> wrote:
>> On receiving the SYN-ACK after SYN-data, the client needs to
>> a) update the cached MSS and cookie (if included in SYN-ACK)
>> b) retransmit the data yet acknowledged by the SYN-ACK in the final ACK of
>> the handshake.
>
> I think you mean "data not yet acknowledged " in point (b).
yes "not yet". I will fix it in the next round after I collect more
reviews. Thanks!
>
> Vijay
^ permalink raw reply [flat|nested] 14+ messages in thread
* [PATCH 5/7] net-tcp: Fast Open client - sendmsg(MSG_FASTOPEN)
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
` (3 preceding siblings ...)
2012-07-16 21:16 ` [PATCH 4/7] net-tcp: Fast Open client - receiving SYN-ACK Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
2012-07-16 21:16 ` [PATCH 6/7] net-tcp: Fast Open client - detecting SYN-data drops Yuchung Cheng
2012-07-16 21:16 ` [PATCH 7/7] net-tcp: Fast Open client - cookie-less mode Yuchung Cheng
6 siblings, 0 replies; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
sendmsg() (or sendto()) with MSG_FASTOPEN is a combo of connect(2)
and write(2). The application should replace connect() with it to
send data in the opening SYN packet.
For blocking socket, sendmsg() blocks until all the data are buffered
locally and the handshake is completed like connect() call. It
returns similar errno like connect() if the TCP handshake fails.
For non-blocking socket, it returns the number of bytes queued (and
transmitted in the SYN-data packet) if cookie is available. If cookie
is not available, it transmits a data-less SYN packet with Fast Open
cookie request option and returns -EINPROGRESS like connect().
Using MSG_FASTOPEN on connecting or connected socket will result in
simlar errno like repeating connect() calls. Therefore the application
should only use this flag on new sockets.
The buffer size of sendmsg() is independent of the MSS of the connection.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
Documentation/networking/ip-sysctl.txt | 11 ++++++
include/linux/socket.h | 1 +
include/net/inet_common.h | 6 ++-
include/net/tcp.h | 3 ++
net/ipv4/af_inet.c | 19 +++++++---
net/ipv4/tcp.c | 61 +++++++++++++++++++++++++++++---
net/ipv4/tcp_ipv4.c | 3 ++
7 files changed, 92 insertions(+), 12 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index e20c17a..b3c5225 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -468,6 +468,17 @@ tcp_syncookies - BOOLEAN
SYN flood warnings in logs not being really flooded, your server
is seriously misconfigured.
+tcp_fastopen - INTEGER
+ Enable TCP Fast Open feature (draft-ietf-tcpm-fastopen) to send data
+ in the opening SYN packet. To use this feature, the client application
+ must not use connect(). Instead, it should use sendmsg() or sendto()
+ with MSG_FASTOPEN flag which performs a TCP handshake automatically.
+
+ The values (bitmap) are:
+ 1: Enables sending data in the opening SYN on the client
+
+ Default: 0
+
tcp_syn_retries - INTEGER
Number of times initial SYNs for an active TCP connection attempt
will be retransmitted. Should not be higher than 255. Default value
diff --git a/include/linux/socket.h b/include/linux/socket.h
index 25d6322..90297db 100644
--- a/include/linux/socket.h
+++ b/include/linux/socket.h
@@ -276,6 +276,7 @@ struct ucred {
#else
#define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */
#endif
+#define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */
/* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */
diff --git a/include/net/inet_common.h b/include/net/inet_common.h
index 22fac98..2340087 100644
--- a/include/net/inet_common.h
+++ b/include/net/inet_common.h
@@ -14,9 +14,11 @@ struct sockaddr;
struct socket;
extern int inet_release(struct socket *sock);
-extern int inet_stream_connect(struct socket *sock, struct sockaddr * uaddr,
+extern int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags);
-extern int inet_dgram_connect(struct socket *sock, struct sockaddr * uaddr,
+extern int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags);
+extern int inet_dgram_connect(struct socket *sock, struct sockaddr *uaddr,
int addr_len, int flags);
extern int inet_accept(struct socket *sock, struct socket *newsock, int flags);
extern int inet_sendmsg(struct kiocb *iocb, struct socket *sock,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 2d3b09d2..8c20edd 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -212,6 +212,9 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
/* TCP initial congestion window as per draft-hkchu-tcpm-initcwnd-01 */
#define TCP_INIT_CWND 10
+/* Bit Flags for sysctl_tcp_fastopen */
+#define TFO_CLIENT_ENABLE 1
+
extern struct inet_timewait_death_row tcp_death_row;
/* sysctl variables for tcp */
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6ef67b7..c05ec41 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -590,8 +590,8 @@ static long inet_wait_for_connect(struct sock *sk, long timeo)
* Connect to a remote host. There is regrettably still a little
* TCP 'magic' in here.
*/
-int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
- int addr_len, int flags)
+int __inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
{
struct sock *sk = sock->sk;
int err;
@@ -600,8 +600,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
if (addr_len < sizeof(uaddr->sa_family))
return -EINVAL;
- lock_sock(sk);
-
if (uaddr->sa_family == AF_UNSPEC) {
err = sk->sk_prot->disconnect(sk, flags);
sock->state = err ? SS_DISCONNECTING : SS_UNCONNECTED;
@@ -664,7 +662,6 @@ int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
sock->state = SS_CONNECTED;
err = 0;
out:
- release_sock(sk);
return err;
sock_error:
@@ -674,6 +671,18 @@ sock_error:
sock->state = SS_DISCONNECTING;
goto out;
}
+EXPORT_SYMBOL(__inet_stream_connect);
+
+int inet_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ int addr_len, int flags)
+{
+ int err;
+
+ lock_sock(sock->sk);
+ err = __inet_stream_connect(sock, uaddr, addr_len, flags);
+ release_sock(sock->sk);
+ return err;
+}
EXPORT_SYMBOL(inet_stream_connect);
/*
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 4252cd8..581ecf0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -270,6 +270,7 @@
#include <linux/slab.h>
#include <net/icmp.h>
+#include <net/inet_common.h>
#include <net/tcp.h>
#include <net/xfrm.h>
#include <net/ip.h>
@@ -982,26 +983,67 @@ static inline int select_size(const struct sock *sk, bool sg)
return tmp;
}
+void tcp_free_fastopen_req(struct tcp_sock *tp)
+{
+ if (tp->fastopen_req != NULL) {
+ kfree(tp->fastopen_req);
+ tp->fastopen_req = NULL;
+ }
+}
+
+static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *size)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+ int err, flags;
+
+ if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE))
+ return -EOPNOTSUPP;
+ if (tp->fastopen_req != NULL)
+ return -EALREADY; /* Another Fast Open is in progress */
+
+ tp->fastopen_req = kzalloc(sizeof(struct tcp_fastopen_request),
+ sk->sk_allocation);
+ if (unlikely(tp->fastopen_req == NULL))
+ return -ENOBUFS;
+ tp->fastopen_req->data = msg;
+
+ flags = (msg->msg_flags & MSG_DONTWAIT) ? O_NONBLOCK : 0;
+ err = __inet_stream_connect(sk->sk_socket, msg->msg_name,
+ msg->msg_namelen, flags);
+ *size = tp->fastopen_req->copied;
+ tcp_free_fastopen_req(tp);
+ return err;
+}
+
int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t size)
{
struct iovec *iov;
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *skb;
- int iovlen, flags, err, copied;
- int mss_now = 0, size_goal;
+ int iovlen, flags, err, copied = 0;
+ int mss_now = 0, size_goal, copied_syn = 0, offset = 0;
bool sg;
long timeo;
lock_sock(sk);
flags = msg->msg_flags;
+ if (flags & MSG_FASTOPEN) {
+ err = tcp_sendmsg_fastopen(sk, msg, &copied_syn);
+ if (err == -EINPROGRESS && copied_syn > 0)
+ goto out;
+ else if (err)
+ goto out_err;
+ offset = copied_syn;
+ }
+
timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT);
/* Wait for a connection to finish. */
if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT))
if ((err = sk_stream_wait_connect(sk, &timeo)) != 0)
- goto out_err;
+ goto do_error;
if (unlikely(tp->repair)) {
if (tp->repair_queue == TCP_RECV_QUEUE) {
@@ -1037,6 +1079,15 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
unsigned char __user *from = iov->iov_base;
iov++;
+ if (unlikely(offset > 0)) { /* Skip bytes copied in SYN */
+ if (offset >= seglen) {
+ offset -= seglen;
+ continue;
+ }
+ seglen -= offset;
+ from += offset;
+ offset = 0;
+ }
while (seglen > 0) {
int copy = 0;
@@ -1199,7 +1250,7 @@ out:
if (copied && likely(!tp->repair))
tcp_push(sk, flags, mss_now, tp->nonagle);
release_sock(sk);
- return copied;
+ return copied + copied_syn;
do_fault:
if (!skb->len) {
@@ -1212,7 +1263,7 @@ do_fault:
}
do_error:
- if (copied)
+ if (copied + copied_syn)
goto out;
out_err:
err = sk_stream_error(sk, flags, err);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 588200e..b2f457f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1959,6 +1959,9 @@ void tcp_v4_destroy_sock(struct sock *sk)
tp->cookie_values = NULL;
}
+ /* If socket is aborted during connect operation */
+ tcp_free_fastopen_req(tp);
+
sk_sockets_allocated_dec(sk);
sock_release_memcg(sk);
}
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 6/7] net-tcp: Fast Open client - detecting SYN-data drops
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
` (4 preceding siblings ...)
2012-07-16 21:16 ` [PATCH 5/7] net-tcp: Fast Open client - sendmsg(MSG_FASTOPEN) Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
2012-07-16 21:16 ` [PATCH 7/7] net-tcp: Fast Open client - cookie-less mode Yuchung Cheng
6 siblings, 0 replies; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
On paths with firewalls dropping SYN with data or experimental TCP options,
Fast Open connections will have experience SYN timeout and bad performance.
The solution is to track such incidents in the cookie cache and disables
Fast Open temporarily.
Since only the original SYN includes data and/or Fast Open option, the
SYN-ACK has some tell-tale sign (tcp_rcv_fastopen_synack()) to detect
such drops. If a path has recurring Fast Open SYN drops, Fast Open is
disabled for 2^(recurring_losses) minutes starting from four minutes up to
roughly one and half day. sendmsg with MSG_FASTOPEN flag will succeed but
it behaves as connect() then write().
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
include/net/tcp.h | 6 ++++--
net/ipv4/tcp_fastopen.c | 16 ++++++++++++++--
net/ipv4/tcp_input.c | 10 +++++++++-
net/ipv4/tcp_output.c | 13 +++++++++++--
4 files changed, 38 insertions(+), 7 deletions(-)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 8c20edd..1b70444 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -391,9 +391,11 @@ enum tcp_tw_status {
/* From tcp_fastopen.c */
extern int tcp_fastopen_size_cache(int size);
extern void tcp_fastopen_cache_get(struct sock *sk, u16 *mss,
- struct tcp_fastopen_cookie *cookie);
+ struct tcp_fastopen_cookie *cookie,
+ int *syn_loss, unsigned long *last_syn_loss);
extern void tcp_fastopen_cache_set(struct sock *sk, u16 *mss,
- struct tcp_fastopen_cookie *cookie);
+ struct tcp_fastopen_cookie *cookie,
+ bool syn_lost);
extern enum tcp_tw_status tcp_timewait_state_process(struct inet_timewait_sock *tw,
struct sk_buff *skb,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 40fdf21..b10e8ca 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -22,6 +22,8 @@ int sysctl_tcp_fastopen;
*/
struct fastopen_entry {
u16 mss; /* TCP MSS value */
+ u16 syn_loss:10; /* Recurring Fast Open SYN losses */
+ unsigned long last_syn_loss; /* Last Fast Open SYN loss */
struct tcp_fastopen_cookie cookie; /* TCP Fast Open cookie */
struct list_head lru_list; /* cookie cache lru_list node */
struct inet_peer *peer; /* inetpeer entry (for fast lookup) */
@@ -82,7 +84,8 @@ static struct inet_peer *tcp_fastopen_inetpeer(struct sock *sk, int create)
}
void tcp_fastopen_cache_get(struct sock *sk, u32 *mss,
- struct tcp_fastopen_cookie *cookie)
+ struct tcp_fastopen_cookie *cookie,
+ int *syn_loss, unsigned long *last_syn_loss)
{
struct inet_peer *peer = tcp_fastopen_inetpeer(sk, 0);
struct fastopen_entry *entry;
@@ -95,6 +98,8 @@ void tcp_fastopen_cache_get(struct sock *sk, u32 *mss,
if (entry != NULL) {
*mss = entry->mss;
*cookie = entry->cookie;
+ *syn_loss = entry->syn_loss;
+ *last_syn_loss = *syn_loss ? entry->last_syn_loss : 0;
list_move_tail(&entry->lru_list, &cookie_cache.lru_list);
}
spin_unlock_bh(&cookie_cache.lock);
@@ -103,7 +108,7 @@ void tcp_fastopen_cache_get(struct sock *sk, u32 *mss,
}
void tcp_fastopen_cache_set(struct sock *sk, u32 *mss,
- struct tcp_fastopen_cookie *cookie)
+ struct tcp_fastopen_cookie *cookie, bool syn_lost)
{
struct inet_peer *peer = tcp_fastopen_inetpeer(sk, 1);
struct fastopen_entry *entry = NULL, *new_entry = NULL;
@@ -119,6 +124,8 @@ void tcp_fastopen_cache_set(struct sock *sk, u32 *mss,
goto out;
}
new_entry->peer = peer;
+ new_entry->mss = new_entry->cookie.len = 0;
+ new_entry->last_syn_loss = new_entry->syn_loss = 0;
INIT_LIST_HEAD(&new_entry->lru_list);
peer->fastopen = new_entry;
++cookie_cache.cnt;
@@ -127,6 +134,11 @@ void tcp_fastopen_cache_set(struct sock *sk, u32 *mss,
entry->mss = *mss;
if (cookie->len > 0)
entry->cookie = *cookie;
+ if (syn_lost) {
+ ++entry->syn_loss;
+ entry->last_syn_loss = jiffies;
+ } else
+ entry->syn_loss = 0;
list_move_tail(&entry->lru_list, &cookie_cache.lru_list);
entry = __tcp_fastopen_remove_lru();
spin_unlock_bh(&cookie_cache.lock);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 5b09f71..aef8514 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5616,6 +5616,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
struct tcp_sock *tp = tcp_sk(sk);
struct sk_buff *data = tcp_write_queue_head(sk);
u16 mss = tp->rx_opt.mss_clamp;
+ bool syn_drop;
if (mss == tp->rx_opt.user_mss) {
struct tcp_options_received opt;
@@ -5628,7 +5629,14 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
mss = opt.mss_clamp;
}
- tcp_fastopen_cache_set(sk, &mss, cookie);
+ /* The SYN-ACK neither has cookie nor acknowledges the data. Presumably
+ * the remote receives only the retransmitted (regular) SYNs: either
+ * the original SYN-data or the corresponding SYN-ACK is lost.
+ */
+ syn_drop = (cookie->len <= 0 && data &&
+ inet_csk(sk)->icsk_retransmits);
+
+ tcp_fastopen_cache_set(sk, &mss, cookie, syn_drop);
if (data) { /* Retransmit unacked data in SYN */
tcp_retransmit_skb(sk, data);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8869328..c5cfd5e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2860,10 +2860,19 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
- int space, i, err = 0, iovlen = fo->data->msg_iovlen;
+ int syn_loss = 0, space, i, err = 0, iovlen = fo->data->msg_iovlen;
struct sk_buff *syn_data = NULL, *data;
+ unsigned long last_syn_loss = 0;
+
+ tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
+ &syn_loss, &last_syn_loss);
+ /* Recurring FO SYN losses: revert to regular handshake temporarily */
+ if (syn_loss > 1 &&
+ time_before(jiffies, last_syn_loss + (60*HZ << syn_loss))) {
+ fo->cookie.len = -1;
+ goto fallback;
+ }
- tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie);
if (fo->cookie.len <= 0)
goto fallback;
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread* [PATCH 7/7] net-tcp: Fast Open client - cookie-less mode
2012-07-16 21:16 [PATCH 0/7] TCP Fast Open client Yuchung Cheng
` (5 preceding siblings ...)
2012-07-16 21:16 ` [PATCH 6/7] net-tcp: Fast Open client - detecting SYN-data drops Yuchung Cheng
@ 2012-07-16 21:16 ` Yuchung Cheng
6 siblings, 0 replies; 14+ messages in thread
From: Yuchung Cheng @ 2012-07-16 21:16 UTC (permalink / raw)
To: davem, hkchu, edumazet, ncardwell; +Cc: sivasankar, netdev, Yuchung Cheng
In trusted networks, e.g., intranet, data-center, the client does not
need to use Fast Open cookie to mitigate DoS attacks. In cookie-less
mode, sendmsg() with MSG_FASTOPEN flag will send SYN-data regardless
of cookie availability.
Signed-off-by: Yuchung Cheng <ycheng@google.com>
---
Documentation/networking/ip-sysctl.txt | 2 ++
include/linux/tcp.h | 1 +
include/net/tcp.h | 1 +
net/ipv4/tcp_input.c | 8 ++++++--
net/ipv4/tcp_output.c | 6 +++++-
5 files changed, 15 insertions(+), 3 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index b3c5225..d67d858 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -476,6 +476,8 @@ tcp_fastopen - INTEGER
The values (bitmap) are:
1: Enables sending data in the opening SYN on the client
+ 5: Enables sending data in the opening SYN on the client regardless
+ of cookie availability.
Default: 0
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1edf96a..9febfb6 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -387,6 +387,7 @@ struct tcp_sock {
u8 repair_queue;
u8 do_early_retrans:1,/* Enable RFC5827 early-retransmit */
early_retrans_delayed:1, /* Delayed ER timer installed */
+ syn_data:1, /* SYN includes data */
syn_fastopen:1; /* SYN includes Fast Open option */
/* RTT measurement */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 1b70444..99ec440 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -214,6 +214,7 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
/* Bit Flags for sysctl_tcp_fastopen */
#define TFO_CLIENT_ENABLE 1
+#define TFO_CLIENT_NO_COOKIE 4 /* Data in SYN w/o cookie option */
extern struct inet_timewait_death_row tcp_death_row;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index aef8514..5915ac2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5614,7 +5614,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
struct tcp_fastopen_cookie *cookie)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *data = tcp_write_queue_head(sk);
+ struct sk_buff *data = tp->syn_data ? tcp_write_queue_head(sk) : NULL;
u16 mss = tp->rx_opt.mss_clamp;
bool syn_drop;
@@ -5636,6 +5636,9 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
syn_drop = (cookie->len <= 0 && data &&
inet_csk(sk)->icsk_retransmits);
+ if (!tp->syn_fastopen) /* Ignore an unsolicited cookie */
+ cookie->len = -1;
+
tcp_fastopen_cache_set(sk, &mss, cookie, syn_drop);
if (data) { /* Retransmit unacked data in SYN */
@@ -5780,7 +5783,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
tcp_finish_connect(sk, skb);
- if (tp->syn_fastopen && tcp_rcv_fastopen_synack(sk, skb, &foc))
+ if ((tp->syn_fastopen || tp->syn_data) &&
+ tcp_rcv_fastopen_synack(sk, skb, &foc))
return -1;
if (sk->sk_write_pending ||
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c5cfd5e..27a32ac 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2864,6 +2864,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
struct sk_buff *syn_data = NULL, *data;
unsigned long last_syn_loss = 0;
+ tp->rx_opt.mss_clamp = tp->advmss; /* If MSS is not cached */
tcp_fastopen_cache_get(sk, &tp->rx_opt.mss_clamp, &fo->cookie,
&syn_loss, &last_syn_loss);
/* Recurring FO SYN losses: revert to regular handshake temporarily */
@@ -2873,7 +2874,9 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
goto fallback;
}
- if (fo->cookie.len <= 0)
+ if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE)
+ fo->cookie.len = -1;
+ else if (fo->cookie.len <= 0)
goto fallback;
/* MSS for SYN-data is based on cached MSS and bounded by PMTU and
@@ -2916,6 +2919,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
fo->copied = data->len;
if (tcp_transmit_skb(sk, syn_data, 0, sk->sk_allocation) == 0) {
+ tp->syn_data = (fo->copied > 0);
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE);
goto done;
}
--
1.7.7.3
^ permalink raw reply related [flat|nested] 14+ messages in thread