From 6648bd7e0e62c0c8c03b15e00c9e7015e232feff Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Thu, 21 Jun 2012 13:58:31 +0000 Subject: ipv4: Add sysctl knob to control early socket demux This change is meant to add a control for disabling early socket demux. The main motivation behind this patch is to provide an option to disable the feature as it adds an additional cost to routing that reduces overall throughput by up to 5%. For example one of my systems went from 12.1Mpps to 11.6 after the early socket demux was added. It looks like the reason for the regression is that we are now having to perform two lookups, first the one for an established socket, and then the one for the routing table. By adding this patch and toggling the value for ip_early_demux to 0 I am able to get back to the 12.1Mpps I was previously seeing. [ Move local variables in ip_rcv_finish() down into the basic block in which they are actually used. -DaveM ] Signed-off-by: Alexander Duyck Signed-off-by: David S. Miller --- net/ipv4/sysctl_net_ipv4.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index ef32956ed65..12aa0c5867c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -300,6 +300,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "ip_early_demux", + .data = &sysctl_ip_early_demux, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "ip_dynaddr", .data = &sysctl_ip_dynaddr, -- cgit v1.2.3-70-g09d2 From 46d3ceabd8d98ed0ad10f20c595ca784e34786c5 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 11 Jul 2012 05:50:31 +0000 Subject: tcp: TCP Small Queues This introduce TSQ (TCP Small Queues) TSQ goal is to reduce number of TCP packets in xmit queues (qdisc & device queues), to reduce RTT and cwnd bias, part of the bufferbloat problem. sk->sk_wmem_alloc not allowed to grow above a given limit, allowing no more than ~128KB [1] per tcp socket in qdisc/dev layers at a given time. TSO packets are sized/capped to half the limit, so that we have two TSO packets in flight, allowing better bandwidth use. As a side effect, setting the limit to 40000 automatically reduces the standard gso max limit (65536) to 40000/2 : It can help to reduce latencies of high prio packets, having smaller TSO packets. This means we divert sock_wfree() to a tcp_wfree() handler, to queue/send following frames when skb_orphan() [2] is called for the already queued skbs. Results on my dev machines (tg3/ixgbe nics) are really impressive, using standard pfifo_fast, and with or without TSO/GSO. Without reduction of nominal bandwidth, we have reduction of buffering per bulk sender : < 1ms on Gbit (instead of 50ms with TSO) < 8ms on 100Mbit (instead of 132 ms) I no longer have 4 MBytes backlogged in qdisc by a single netperf session, and both side socket autotuning no longer use 4 Mbytes. As skb destructor cannot restart xmit itself ( as qdisc lock might be taken at this point ), we delegate the work to a tasklet. We use one tasklest per cpu for performance reasons. If tasklet finds a socket owned by the user, it sets TSQ_OWNED flag. This flag is tested in a new protocol method called from release_sock(), to eventually send new segments. [1] New /proc/sys/net/ipv4/tcp_limit_output_bytes tunable [2] skb_orphan() is usually called at TX completion time, but some drivers call it in their start_xmit() handler. These drivers should at least use BQL, or else a single TCP session can still fill the whole NIC TX ring, since TSQ will have no effect. Signed-off-by: Eric Dumazet Cc: Dave Taht Cc: Tom Herbert Cc: Matt Mathis Cc: Yuchung Cheng Cc: Nandita Dukkipati Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 14 +++ include/linux/tcp.h | 9 ++ include/net/sock.h | 2 + include/net/tcp.h | 4 + net/core/sock.c | 4 + net/ipv4/sysctl_net_ipv4.c | 7 ++ net/ipv4/tcp.c | 6 ++ net/ipv4/tcp_ipv4.c | 1 + net/ipv4/tcp_minisocks.c | 1 + net/ipv4/tcp_output.c | 154 ++++++++++++++++++++++++++++++++- net/ipv6/tcp_ipv6.c | 1 + 11 files changed, 202 insertions(+), 1 deletion(-) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 47b6c79e9b0..e20c17a7d34 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -551,6 +551,20 @@ tcp_thin_dupack - BOOLEAN Documentation/networking/tcp-thin.txt Default: 0 +tcp_limit_output_bytes - INTEGER + Controls TCP Small Queue limit per tcp socket. + TCP bulk sender tends to increase packets in flight until it + gets losses notifications. With SNDBUF autotuning, this can + result in a large amount of packets queued in qdisc/device + on the local machine, hurting latency of other flows, for + typical pfifo_fast qdiscs. + tcp_limit_output_bytes limits the number of bytes on qdisc + or device to reduce artificial RTT/cwnd and reduce bufferbloat. + Note: For GSO/TSO enabled flows, we try to have at least two + packets in flight. Reducing tcp_limit_output_bytes might also + reduce the size of individual GSO packet (64KB being the max) + Default: 131072 + UDP variables: udp_mem - vector of 3 INTEGERs: min, pressure, max diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 2de9cf46f9f..1888169e07c 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -339,6 +339,9 @@ struct tcp_sock { u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ u32 lsndtime; /* timestamp of last sent data packet (for restart window) */ + struct list_head tsq_node; /* anchor in tsq_tasklet.head list */ + unsigned long tsq_flags; + /* Data for direct copy to user */ struct { struct sk_buff_head prequeue; @@ -494,6 +497,12 @@ struct tcp_sock { struct tcp_cookie_values *cookie_values; }; +enum tsq_flags { + TSQ_THROTTLED, + TSQ_QUEUED, + TSQ_OWNED, /* tcp_tasklet_func() found socket was locked */ +}; + static inline struct tcp_sock *tcp_sk(const struct sock *sk) { return (struct tcp_sock *)sk; diff --git a/include/net/sock.h b/include/net/sock.h index dcb54a0793e..88de092df50 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -858,6 +858,8 @@ struct proto { int (*backlog_rcv) (struct sock *sk, struct sk_buff *skb); + void (*release_cb)(struct sock *sk); + /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); diff --git a/include/net/tcp.h b/include/net/tcp.h index 3618fefae04..439984b9af4 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -253,6 +253,7 @@ extern int sysctl_tcp_cookie_size; extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; +extern int sysctl_tcp_limit_output_bytes; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; @@ -321,6 +322,8 @@ extern struct proto tcp_prot; extern void tcp_init_mem(struct net *net); +extern void tcp_tasklet_init(void); + extern void tcp_v4_err(struct sk_buff *skb, u32); extern void tcp_shutdown (struct sock *sk, int how); @@ -334,6 +337,7 @@ extern int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t size); extern int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); +extern void tcp_release_cb(struct sock *sk); extern int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); extern int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, const struct tcphdr *th, unsigned int len); diff --git a/net/core/sock.c b/net/core/sock.c index 929bdcc2383..24039ac1242 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2159,6 +2159,10 @@ void release_sock(struct sock *sk) spin_lock_bh(&sk->sk_lock.slock); if (sk->sk_backlog.tail) __release_sock(sk); + + if (sk->sk_prot->release_cb) + sk->sk_prot->release_cb(sk); + sk->sk_lock.owned = 0; if (waitqueue_active(&sk->sk_lock.wq)) wake_up(&sk->sk_lock.wq); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 12aa0c5867c..70730f7aeaf 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -598,6 +598,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_limit_output_bytes", + .data = &sysctl_tcp_limit_output_bytes, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, #ifdef CONFIG_NET_DMA { .procname = "tcp_dma_copybreak", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d902da96d15..4252cd8f39f 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -376,6 +376,7 @@ void tcp_init_sock(struct sock *sk) skb_queue_head_init(&tp->out_of_order_queue); tcp_init_xmit_timers(sk); tcp_prequeue_init(tp); + INIT_LIST_HEAD(&tp->tsq_node); icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev = TCP_TIMEOUT_INIT; @@ -796,6 +797,10 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, inet_csk(sk)->icsk_ext_hdr_len - tp->tcp_header_len); + /* TSQ : try to have two TSO segments in flight */ + xmit_size_goal = min_t(u32, xmit_size_goal, + sysctl_tcp_limit_output_bytes >> 1); + xmit_size_goal = tcp_bound_to_half_wnd(tp, xmit_size_goal); /* We try hard to avoid divides here */ @@ -3574,4 +3579,5 @@ void __init tcp_init(void) tcp_secret_primary = &tcp_secret_one; tcp_secret_retiring = &tcp_secret_two; tcp_secret_secondary = &tcp_secret_two; + tcp_tasklet_init(); } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ddefd39ac0c..01545a3fc0f 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2588,6 +2588,7 @@ struct proto tcp_prot = { .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, + .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 65608863fde..c66f2ede160 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -424,6 +424,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, treq->snt_isn + 1 + tcp_s_data_size(oldtp); tcp_prequeue_init(newtp); + INIT_LIST_HEAD(&newtp->tsq_node); tcp_init_wl(newtp, treq->rcv_isn); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index c465d3e51e2..03854abfd9d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -50,6 +50,9 @@ int sysctl_tcp_retrans_collapse __read_mostly = 1; */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; +/* Default TSQ limit of two TSO segments */ +int sysctl_tcp_limit_output_bytes __read_mostly = 131072; + /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. @@ -65,6 +68,8 @@ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */ EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size); +static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp); /* Account for new data that has been sent to the network. */ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb) @@ -783,6 +788,140 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb return size; } + +/* TCP SMALL QUEUES (TSQ) + * + * TSQ goal is to keep small amount of skbs per tcp flow in tx queues (qdisc+dev) + * to reduce RTT and bufferbloat. + * We do this using a special skb destructor (tcp_wfree). + * + * Its important tcp_wfree() can be replaced by sock_wfree() in the event skb + * needs to be reallocated in a driver. + * The invariant being skb->truesize substracted from sk->sk_wmem_alloc + * + * Since transmit from skb destructor is forbidden, we use a tasklet + * to process all sockets that eventually need to send more skbs. + * We use one tasklet per cpu, with its own queue of sockets. + */ +struct tsq_tasklet { + struct tasklet_struct tasklet; + struct list_head head; /* queue of tcp sockets */ +}; +static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); + +/* + * One tasklest per cpu tries to send more skbs. + * We run in tasklet context but need to disable irqs when + * transfering tsq->head because tcp_wfree() might + * interrupt us (non NAPI drivers) + */ +static void tcp_tasklet_func(unsigned long data) +{ + struct tsq_tasklet *tsq = (struct tsq_tasklet *)data; + LIST_HEAD(list); + unsigned long flags; + struct list_head *q, *n; + struct tcp_sock *tp; + struct sock *sk; + + local_irq_save(flags); + list_splice_init(&tsq->head, &list); + local_irq_restore(flags); + + list_for_each_safe(q, n, &list) { + tp = list_entry(q, struct tcp_sock, tsq_node); + list_del(&tp->tsq_node); + + sk = (struct sock *)tp; + bh_lock_sock(sk); + + if (!sock_owned_by_user(sk)) { + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | + TCPF_CLOSING | TCPF_CLOSE_WAIT)) + tcp_write_xmit(sk, + tcp_current_mss(sk), + 0, 0, + GFP_ATOMIC); + } else { + /* defer the work to tcp_release_cb() */ + set_bit(TSQ_OWNED, &tp->tsq_flags); + } + bh_unlock_sock(sk); + + clear_bit(TSQ_QUEUED, &tp->tsq_flags); + sk_free(sk); + } +} + +/** + * tcp_release_cb - tcp release_sock() callback + * @sk: socket + * + * called from release_sock() to perform protocol dependent + * actions before socket release. + */ +void tcp_release_cb(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_OWNED, &tp->tsq_flags)) { + if ((1 << sk->sk_state) & + (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | + TCPF_CLOSING | TCPF_CLOSE_WAIT)) + tcp_write_xmit(sk, + tcp_current_mss(sk), + 0, 0, + GFP_ATOMIC); + } +} +EXPORT_SYMBOL(tcp_release_cb); + +void __init tcp_tasklet_init(void) +{ + int i; + + for_each_possible_cpu(i) { + struct tsq_tasklet *tsq = &per_cpu(tsq_tasklet, i); + + INIT_LIST_HEAD(&tsq->head); + tasklet_init(&tsq->tasklet, + tcp_tasklet_func, + (unsigned long)tsq); + } +} + +/* + * Write buffer destructor automatically called from kfree_skb. + * We cant xmit new skbs from this context, as we might already + * hold qdisc lock. + */ +void tcp_wfree(struct sk_buff *skb) +{ + struct sock *sk = skb->sk; + struct tcp_sock *tp = tcp_sk(sk); + + if (test_and_clear_bit(TSQ_THROTTLED, &tp->tsq_flags) && + !test_and_set_bit(TSQ_QUEUED, &tp->tsq_flags)) { + unsigned long flags; + struct tsq_tasklet *tsq; + + /* Keep a ref on socket. + * This last ref will be released in tcp_tasklet_func() + */ + atomic_sub(skb->truesize - 1, &sk->sk_wmem_alloc); + + /* queue this socket to tasklet queue */ + local_irq_save(flags); + tsq = &__get_cpu_var(tsq_tasklet); + list_add(&tp->tsq_node, &tsq->head); + tasklet_schedule(&tsq->tasklet); + local_irq_restore(flags); + } else { + sock_wfree(skb); + } +} + /* This routine actually transmits TCP packets queued in by * tcp_do_sendmsg(). This is used by both the initial * transmission and possible later retransmissions. @@ -844,7 +983,12 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); - skb_set_owner_w(skb, sk); + + skb_orphan(skb); + skb->sk = sk; + skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ? + tcp_wfree : sock_wfree; + atomic_add(skb->truesize, &sk->sk_wmem_alloc); /* Build TCP header and checksum it. */ th = tcp_hdr(skb); @@ -1780,6 +1924,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, while ((skb = tcp_send_head(sk))) { unsigned int limit; + tso_segs = tcp_init_tso_segs(sk, skb, mss_now); BUG_ON(!tso_segs); @@ -1800,6 +1945,13 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, break; } + /* TSQ : sk_wmem_alloc accounts skb truesize, + * including skb overhead. But thats OK. + */ + if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) { + set_bit(TSQ_THROTTLED, &tp->tsq_flags); + break; + } limit = mss_now; if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 61175cb2478..70458a9cd83 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1970,6 +1970,7 @@ struct proto tcpv6_prot = { .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, + .release_cb = tcp_release_cb, .hash = tcp_v6_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, -- cgit v1.2.3-70-g09d2 From 282f23c6ee343126156dd41218b22ece96d747e3 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 17 Jul 2012 10:13:05 +0200 Subject: tcp: implement RFC 5961 3.2 Implement the RFC 5691 mitigation against Blind Reset attack using RST bit. Idea is to validate incoming RST sequence, to match RCV.NXT value, instead of previouly accepted window : (RCV.NXT <= SEG.SEQ < RCV.NXT+RCV.WND) If sequence is in window but not an exact match, send a "challenge ACK", so that the other part can resend an RST with the appropriate sequence. Add a new sysctl, tcp_challenge_ack_limit, to limit number of challenge ACK sent per second. Add a new SNMP counter to count number of challenge acks sent. (netstat -s | grep TCPChallengeACK) Signed-off-by: Eric Dumazet Cc: Kiran Kumar Kella Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 5 +++++ include/linux/snmp.h | 1 + include/net/tcp.h | 1 + net/ipv4/proc.c | 1 + net/ipv4/sysctl_net_ipv4.c | 7 +++++++ net/ipv4/tcp_input.c | 31 ++++++++++++++++++++++++++++++- 6 files changed, 45 insertions(+), 1 deletion(-) (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index e20c17a7d34..e1e021594cf 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -565,6 +565,11 @@ tcp_limit_output_bytes - INTEGER reduce the size of individual GSO packet (64KB being the max) Default: 131072 +tcp_challenge_ack_limit - INTEGER + Limits number of Challenge ACK sent per second, as recommended + in RFC 5961 (Improving TCP's Robustness to Blind In-Window Attacks) + Default: 100 + UDP variables: udp_mem - vector of 3 INTEGERs: min, pressure, max diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 6e4c5112382..673e0e928b2 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -237,6 +237,7 @@ enum LINUX_MIB_TCPOFOQUEUE, /* TCPOFOQueue */ LINUX_MIB_TCPOFODROP, /* TCPOFODrop */ LINUX_MIB_TCPOFOMERGE, /* TCPOFOMerge */ + LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ __LINUX_MIB_MAX }; diff --git a/include/net/tcp.h b/include/net/tcp.h index 439984b9af4..85c5090bfe2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -254,6 +254,7 @@ extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; extern int sysctl_tcp_early_retrans; extern int sysctl_tcp_limit_output_bytes; +extern int sysctl_tcp_challenge_ack_limit; extern atomic_long_t tcp_memory_allocated; extern struct percpu_counter tcp_sockets_allocated; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index dae25e7622c..3e8e78f12a3 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -261,6 +261,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPOFOQueue", LINUX_MIB_TCPOFOQUEUE), SNMP_MIB_ITEM("TCPOFODrop", LINUX_MIB_TCPOFODROP), SNMP_MIB_ITEM("TCPOFOMerge", LINUX_MIB_TCPOFOMERGE), + SNMP_MIB_ITEM("TCPChallengeACK", LINUX_MIB_TCPCHALLENGEACK), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 70730f7aeaf..3f6a1e762e9 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -605,6 +605,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_challenge_ack_limit", + .data = &sysctl_tcp_challenge_ack_limit, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, #ifdef CONFIG_NET_DMA { .procname = "tcp_dma_copybreak", diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index cc4e12f1f2f..c841a899037 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -88,6 +88,9 @@ int sysctl_tcp_app_win __read_mostly = 31; int sysctl_tcp_adv_win_scale __read_mostly = 1; EXPORT_SYMBOL(sysctl_tcp_adv_win_scale); +/* rfc5961 challenge ack rate limiting */ +int sysctl_tcp_challenge_ack_limit = 100; + int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; @@ -5247,6 +5250,23 @@ out: } #endif /* CONFIG_NET_DMA */ +static void tcp_send_challenge_ack(struct sock *sk) +{ + /* unprotected vars, we dont care of overwrites */ + static u32 challenge_timestamp; + static unsigned int challenge_count; + u32 now = jiffies / HZ; + + if (now != challenge_timestamp) { + challenge_timestamp = now; + challenge_count = 0; + } + if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); + tcp_send_ack(sk); + } +} + /* Does PAWS and seqno based validation of an incoming segment, flags will * play significant role here. */ @@ -5283,7 +5303,16 @@ static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb, /* Step 2: check RST bit */ if (th->rst) { - tcp_reset(sk); + /* RFC 5961 3.2 : + * If sequence number exactly matches RCV.NXT, then + * RESET the connection + * else + * Send a challenge ACK + */ + if (TCP_SKB_CB(skb)->seq == tp->rcv_nxt) + tcp_reset(sk); + else + tcp_send_challenge_ack(sk); goto discard; } -- cgit v1.2.3-70-g09d2 From 2100c8d2d9db23c0a09901a782bb4e3b21bee298 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Thu, 19 Jul 2012 06:43:05 +0000 Subject: net-tcp: Fast Open base This patch impelements the common code for both the client and server. 1. TCP Fast Open option processing. Since Fast Open does not have an 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. This enables global experiments without clashing the scarce(2) experimental options available for TCP. When the draft status becomes standard (maybe), the client should switch to the new option number assigned while the server supports both numbers for transistion. 2. The new sysctl tcp_fastopen 3. A place holder init function Signed-off-by: Yuchung Cheng Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- 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 (limited to 'net/ipv4/sysctl_net_ipv4.c') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 1888169e07c..12948f54383 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 85c5090bfe2..5aed3718fde 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; @@ -418,7 +425,7 @@ 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 a677d804e53..ae2ccf2890e 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 eab2a7fb15d..650e1528e1e 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 3f6a1e762e9..5840c325572 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -366,6 +366,13 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, #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, diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c new file mode 100644 index 00000000000..a7f729c409d --- /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 fdd49f1b7a5..a06bb8959e7 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3732,7 +3732,8 @@ 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); @@ -3839,8 +3840,25 @@ 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; } @@ -3882,7 +3900,7 @@ 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; } @@ -5637,7 +5655,7 @@ 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 d7d2fa50f07..01aa77a9702 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1307,7 +1307,7 @@ 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 c66f2ede160..5912ac3fd24 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 15a7c7bc3e5..4849be76ccd 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 7bf3cc427c2..bb46061c813 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 c9dabdd832d..0302ec3fecf 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1033,7 +1033,7 @@ 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 && -- cgit v1.2.3-70-g09d2