From 75ff39ccc1bd5d3c455b6822ab09e533c551f758 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 10 Jul 2016 10:04:02 +0200 Subject: tcp: make challenge acks less predictable Yue Cao claims that current host rate limiting of challenge ACKS (RFC 5961) could leak enough information to allow a patient attacker to hijack TCP sessions. He will soon provide details in an academic paper. This patch increases the default limit from 100 to 1000, and adds some randomization so that the attacker can no longer hijack sessions without spending a considerable amount of probes. Based on initial analysis and patch from Linus. Note that we also have per socket rate limiting, so it is tempting to remove the host limit in the future. v2: randomize the count of challenge acks per second, not the period. Fixes: 282f23c6ee34 ("tcp: implement RFC 5961 3.2") Reported-by: Yue Cao Signed-off-by: Eric Dumazet Suggested-by: Linus Torvalds Cc: Yuchung Cheng Cc: Neal Cardwell Acked-by: Neal Cardwell Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d6c8f4cd0800..91868bb17818 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -87,7 +87,7 @@ 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_challenge_ack_limit = 1000; int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; @@ -3458,7 +3458,7 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) static u32 challenge_timestamp; static unsigned int challenge_count; struct tcp_sock *tp = tcp_sk(sk); - u32 now; + u32 count, now; /* First check our per-socket dupack rate limit. */ if (tcp_oow_rate_limited(sock_net(sk), skb, @@ -3466,13 +3466,18 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) &tp->last_oow_ack_time)) return; - /* Then check the check host-wide RFC 5961 rate limit. */ + /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { + u32 half = (sysctl_tcp_challenge_ack_limit + 1) >> 1; + challenge_timestamp = now; - challenge_count = 0; + WRITE_ONCE(challenge_count, half + + prandom_u32_max(sysctl_tcp_challenge_ack_limit)); } - if (++challenge_count <= sysctl_tcp_challenge_ack_limit) { + count = READ_ONCE(challenge_count); + if (count > 0) { + WRITE_ONCE(challenge_count, count - 1); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPCHALLENGEACK); tcp_send_ack(sk); } -- cgit From 083ae308280d13d187512b9babe3454342a7987e Mon Sep 17 00:00:00 2001 From: Jason Baron Date: Thu, 14 Jul 2016 11:38:40 -0400 Subject: tcp: enable per-socket rate limiting of all 'challenge acks' The per-socket rate limit for 'challenge acks' was introduced in the context of limiting ack loops: commit f2b2c582e824 ("tcp: mitigate ACK loops for connections as tcp_sock") And I think it can be extended to rate limit all 'challenge acks' on a per-socket basis. Since we have the global tcp_challenge_ack_limit, this patch allows for tcp_challenge_ack_limit to be set to a large value and effectively rely on the per-socket limit, or set tcp_challenge_ack_limit to a lower value and still prevents a single connections from consuming the entire challenge ack quota. It further moves in the direction of eliminating the global limit at some point, as Eric Dumazet has suggested. This a follow-up to: Subject: tcp: make challenge acks less predictable Cc: Eric Dumazet Cc: David S. Miller Cc: Neal Cardwell Cc: Yuchung Cheng Cc: Yue Cao Signed-off-by: Jason Baron Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 39 ++++++++++++++++++++++----------------- 1 file changed, 22 insertions(+), 17 deletions(-) (limited to 'net/ipv4/tcp_input.c') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 91868bb17818..42bf89aaf6a5 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3421,6 +3421,23 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 return flag; } +static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, + u32 *last_oow_ack_time) +{ + if (*last_oow_ack_time) { + s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); + + if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { + NET_INC_STATS(net, mib_idx); + return true; /* rate-limited: don't send yet! */ + } + } + + *last_oow_ack_time = tcp_time_stamp; + + return false; /* not rate-limited: go ahead, send dupack now! */ +} + /* Return true if we're currently rate-limiting out-of-window ACKs and * thus shouldn't send a dupack right now. We rate-limit dupacks in * response to out-of-window SYNs or ACKs to mitigate ACK loops or DoS @@ -3434,21 +3451,9 @@ bool tcp_oow_rate_limited(struct net *net, const struct sk_buff *skb, /* Data packets without SYNs are not likely part of an ACK loop. */ if ((TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) && !tcp_hdr(skb)->syn) - goto not_rate_limited; - - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_time_stamp - *last_oow_ack_time); - - if (0 <= elapsed && elapsed < sysctl_tcp_invalid_ratelimit) { - NET_INC_STATS(net, mib_idx); - return true; /* rate-limited: don't send yet! */ - } - } - - *last_oow_ack_time = tcp_time_stamp; + return false; -not_rate_limited: - return false; /* not rate-limited: go ahead, send dupack now! */ + return __tcp_oow_rate_limited(net, mib_idx, last_oow_ack_time); } /* RFC 5961 7 [ACK Throttling] */ @@ -3461,9 +3466,9 @@ static void tcp_send_challenge_ack(struct sock *sk, const struct sk_buff *skb) u32 count, now; /* First check our per-socket dupack rate limit. */ - if (tcp_oow_rate_limited(sock_net(sk), skb, - LINUX_MIB_TCPACKSKIPPEDCHALLENGE, - &tp->last_oow_ack_time)) + if (__tcp_oow_rate_limited(sock_net(sk), + LINUX_MIB_TCPACKSKIPPEDCHALLENGE, + &tp->last_oow_ack_time)) return; /* Then check host-wide RFC 5961 rate limit. */ -- cgit