From a612769774a30e4fc143c4cb6395c12573415660 Mon Sep 17 00:00:00 2001 From: Michal Kubeček Date: Fri, 8 Jul 2016 17:52:33 +0200 Subject: udp: prevent bugcheck if filter truncates packet too much If socket filter truncates an udp packet below the length of UDP header in udpv6_queue_rcv_skb() or udp_queue_rcv_skb(), it will trigger a BUG_ON in skb_pull_rcsum(). This BUG_ON (and therefore a system crash if kernel is configured that way) can be easily enforced by an unprivileged user which was reported as CVE-2016-6162. For a reproducer, see http://seclists.org/oss-sec/2016/q3/8 Fixes: e6afc8ace6dd ("udp: remove headers from UDP packets before queueing") Reported-by: Marco Grassi Signed-off-by: Michal Kubecek Acked-by: Eric Dumazet Acked-by: Willem de Bruijn Signed-off-by: David S. Miller --- net/ipv4/udp.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ca5e8ea29538..4aed8fc23d32 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1583,6 +1583,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (sk_filter(sk, skb)) goto drop; + if (unlikely(skb->len < sizeof(struct udphdr))) + goto drop; udp_csum_pull_header(skb); if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) { -- cgit v1.2.3 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') 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 v1.2.3 From 80610229ef7b26615dbb6cb6e873709a60bacc9f Mon Sep 17 00:00:00 2001 From: Julian Anastasov Date: Sun, 10 Jul 2016 21:11:55 +0300 Subject: ipv4: reject RTNH_F_DEAD and RTNH_F_LINKDOWN from user space Vegard Nossum is reporting for a crash in fib_dump_info when nh_dev = NULL and fib_nhs == 1: Pid: 50, comm: netlink.exe Not tainted 4.7.0-rc5+ RIP: 0033:[<00000000602b3d18>] RSP: 0000000062623890 EFLAGS: 00010202 RAX: 0000000000000000 RBX: 000000006261b800 RCX: 0000000000000000 RDX: 0000000000000000 RSI: 0000000000000024 RDI: 000000006245ba00 RBP: 00000000626238f0 R08: 000000000000029c R09: 0000000000000000 R10: 0000000062468038 R11: 000000006245ba00 R12: 000000006245ba00 R13: 00000000625f96c0 R14: 00000000601e16f0 R15: 0000000000000000 Kernel panic - not syncing: Kernel mode fault at addr 0x2e0, ip 0x602b3d18 CPU: 0 PID: 50 Comm: netlink.exe Not tainted 4.7.0-rc5+ #581 Stack: 626238f0 960226a02 00000400 000000fe 62623910 600afca7 62623970 62623a48 62468038 00000018 00000000 00000000 Call Trace: [<602b3e93>] rtmsg_fib+0xd3/0x190 [<602b6680>] fib_table_insert+0x260/0x500 [<602b0e5d>] inet_rtm_newroute+0x4d/0x60 [<60250def>] rtnetlink_rcv_msg+0x8f/0x270 [<60267079>] netlink_rcv_skb+0xc9/0xe0 [<60250d4b>] rtnetlink_rcv+0x3b/0x50 [<60265400>] netlink_unicast+0x1a0/0x2c0 [<60265e47>] netlink_sendmsg+0x3f7/0x470 [<6021dc9a>] sock_sendmsg+0x3a/0x90 [<6021e0d0>] ___sys_sendmsg+0x300/0x360 [<6021fa64>] __sys_sendmsg+0x54/0xa0 [<6021fac0>] SyS_sendmsg+0x10/0x20 [<6001ea68>] handle_syscall+0x88/0x90 [<600295fd>] userspace+0x3fd/0x500 [<6001ac55>] fork_handler+0x85/0x90 $ addr2line -e vmlinux -i 0x602b3d18 include/linux/inetdevice.h:222 net/ipv4/fib_semantics.c:1264 Problem happens when RTNH_F_LINKDOWN is provided from user space when creating routes that do not use the flag, catched with netlink fuzzer. Currently, the kernel allows user space to set both flags to nh_flags and fib_flags but this is not intentional, the assumption was that they are not set. Fix this by rejecting both flags with EINVAL. Reported-by: Vegard Nossum Fixes: 0eeb075fad73 ("net: ipv4 sysctl option to ignore routes when nexthop link is down") Signed-off-by: Julian Anastasov Cc: Andy Gospodarek Cc: Dinesh Dutt Cc: Scott Feldman Reviewed-by: Andy Gospodarek Signed-off-by: David S. Miller --- net/ipv4/fib_semantics.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index d09173bf9500..539fa264e67d 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (!rtnh_ok(rtnh, remaining)) return -EINVAL; + if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + return -EINVAL; + nexthop_nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags; nexthop_nh->nh_oif = rtnh->rtnh_ifindex; @@ -1003,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) if (fib_props[cfg->fc_type].scope > cfg->fc_scope) goto err_inval; + if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN)) + goto err_inval; + #ifdef CONFIG_IP_ROUTE_MULTIPATH if (cfg->fc_mp) { nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len); -- cgit v1.2.3 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') 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 v1.2.3