From: Eric Dumazet Date: Tue, 17 Jul 2012 08:13:05 +0000 (+0200) Subject: tcp: implement RFC 5961 3.2 X-Git-Tag: v3.0.58~16 X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=86791bbfe5ed7b275be040cfeff049a1624af1b7;p=karo-tx-linux.git tcp: implement RFC 5961 3.2 [ Upstream commit 282f23c6ee343126156dd41218b22ece96d747e3 ] 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 Signed-off-by: Greg Kroah-Hartman --- diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 7d4ecaa57cfa..890fce9b3683 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -534,6 +534,11 @@ tcp_thin_dupack - BOOLEAN Documentation/networking/tcp-thin.txt Default: 0 +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 12b2b18e50c1..f7f67a0ec64a 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -231,6 +231,7 @@ enum LINUX_MIB_TCPDEFERACCEPTDROP, LINUX_MIB_IPRPFILTER, /* IP Reverse Path Filter (rp_filter) */ LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */ + LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */ __LINUX_MIB_MAX }; diff --git a/include/net/tcp.h b/include/net/tcp.h index cda30ea354a2..b28a49f48a04 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -246,6 +246,7 @@ extern int sysctl_tcp_max_ssthresh; extern int sysctl_tcp_cookie_size; extern int sysctl_tcp_thin_linear_timeouts; extern int sysctl_tcp_thin_dupack; +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 b14ec7d03b6e..14f264dd1d9a 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -254,6 +254,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), + 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 57d0752e239a..46b595014212 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -566,6 +566,13 @@ 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 b76aa2d9624f..04ef087dff91 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -86,6 +86,9 @@ 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; @@ -5165,6 +5168,23 @@ 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. */ @@ -5201,7 +5221,16 @@ 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; }