[ 40/49] tcp: implement RFC 5961 3.2
From: Ben Hutchings
Date: Sun Jan 13 2013 - 12:45:32 EST
3.2-stable review patch. If anyone has any objections, please let me know.
------------------
From: Eric Dumazet <edumazet@xxxxxxxxxx>
[ 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 <edumazet@xxxxxxxxxx>
Cc: Kiran Kumar Kella <kkiran@xxxxxxxxxxxx>
Signed-off-by: David S. Miller <davem@xxxxxxxxxxxxx>
Signed-off-by: Ben Hutchings <ben@xxxxxxxxxxxxxxx>
---
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(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a4399f5..3b979c6 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -524,6 +524,11 @@ 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 e16557a..6e310bb 100644
--- a/include/linux/snmp.h
+++ b/include/linux/snmp.h
@@ -233,6 +233,7 @@ enum
LINUX_MIB_TCPTIMEWAITOVERFLOW, /* TCPTimeWaitOverflow */
LINUX_MIB_TCPREQQFULLDOCOOKIES, /* TCPReqQFullDoCookies */
LINUX_MIB_TCPREQQFULLDROP, /* TCPReqQFullDrop */
+ LINUX_MIB_TCPCHALLENGEACK, /* TCPChallengeACK */
__LINUX_MIB_MAX
};
diff --git a/include/net/tcp.h b/include/net/tcp.h
index bb18c4d..0768715 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -251,6 +251,7 @@ 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 466ea8b..f46c478 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -257,6 +257,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW),
SNMP_MIB_ITEM("TCPReqQFullDoCookies", LINUX_MIB_TCPREQQFULLDOCOOKIES),
SNMP_MIB_ITEM("TCPReqQFullDrop", LINUX_MIB_TCPREQQFULLDROP),
+ 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 69fd720..5485077 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -552,6 +552,13 @@ 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 a08a621..a0d3b88 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;
@@ -5240,6 +5243,23 @@ 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.
*/
@@ -5276,7 +5296,16 @@ 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;
}
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/