From mboxrd@z Thu Jan 1 00:00:00 1970 From: Yuchung Cheng Subject: [PATCH 1/7] net-tcp: Fast Open base Date: Mon, 16 Jul 2012 14:16:44 -0700 Message-ID: <1342473410-6265-2-git-send-email-ycheng@google.com> References: <1342473410-6265-1-git-send-email-ycheng@google.com> Cc: sivasankar@cs.ucsd.edu, netdev@vger.kernel.org, Yuchung Cheng To: davem@davemloft.net, hkchu@google.com, edumazet@google.com, ncardwell@google.com Return-path: Received: from mail-wg0-f74.google.com ([74.125.82.74]:47212 "EHLO mail-wg0-f74.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753322Ab2GPVRF (ORCPT ); Mon, 16 Jul 2012 17:17:05 -0400 Received: by wgbdt11 with SMTP id dt11so328432wgb.1 for ; Mon, 16 Jul 2012 14:17:03 -0700 (PDT) In-Reply-To: <1342473410-6265-1-git-send-email-ycheng@google.com> Sender: netdev-owner@vger.kernel.org List-ID: 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 --- 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 +#include + +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