tcp: helpers to mitigate ACK loops by rate-limiting out-of-window dupacks

Helpers for mitigating ACK loops by rate-limiting dupacks sent in
response to incoming out-of-window packets.

This patch includes:

- rate-limiting logic
- sysctl to control how often we allow dupacks to out-of-window packets
- SNMP counter for cases where we rate-limited our dupack sending

The rate-limiting logic in this patch decides to not send dupacks in
response to out-of-window segments if (a) they are SYNs or pure ACKs
and (b) the remote endpoint is sending them faster than the configured
rate limit.

We rate-limit our responses rather than blocking them entirely or
resetting the connection, because legitimate connections can rely on
dupacks in response to some out-of-window segments. For example, zero
window probes are typically sent with a sequence number that is below
the current window, and ZWPs thus expect to thus elicit a dupack in
response.

We allow dupacks in response to TCP segments with data, because these
may be spurious retransmissions for which the remote endpoint wants to
receive DSACKs. This is safe because segments with data can't
realistically be part of ACK loops, which by their nature consist of
each side sending pure/data-less ACKs to each other.

The dupack interval is controlled by a new sysctl knob,
tcp_invalid_ratelimit, given in milliseconds, in case an administrator
needs to dial this upward in the face of a high-rate DoS attack. The
name and units are chosen to be analogous to the existing analogous
knob for ICMP, icmp_ratelimit.

The default value for tcp_invalid_ratelimit is 500ms, which allows at
most one such dupack per 500ms. This is chosen to be 2x faster than
the 1-second minimum RTO interval allowed by RFC 6298 (section 2, rule
2.4). We allow the extra 2x factor because network delay variations
can cause packets sent at 1 second intervals to be compressed and
arrive much closer.

Reported-by: Avery Fay <avery@mixpanel.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 74 insertions, 0 deletions

diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a5e4c813f17f..1b8c964b0d17 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -290,6 +290,28 @@ tcp_frto - INTEGER
 
         By default it's enabled with a non-zero value. 0 disables F-RTO.
 
+tcp_invalid_ratelimit - INTEGER
+        Limit the maximal rate for sending duplicate acknowledgments
+        in response to incoming TCP packets that are for an existing
+        connection but that are invalid due to any of these reasons:
+
+          (a) out-of-window sequence number,
+          (b) out-of-window acknowledgment number, or
+          (c) PAWS (Protection Against Wrapped Sequence numbers) check failure
+
+        This can help mitigate simple "ack loop" DoS attacks, wherein
+        a buggy or malicious middlebox or man-in-the-middle can
+        rewrite TCP header fields in manner that causes each endpoint
+        to think that the other is sending invalid TCP segments, thus
+        causing each side to send an unterminating stream of duplicate
+        acknowledgments for invalid segments.
+
+        Using 0 disables rate-limiting of dupacks in response to
+        invalid segments; otherwise this value specifies the minimal
+        space between sending such dupacks, in milliseconds.
+
+        Default: 500 (milliseconds).
+
 tcp_keepalive_time - INTEGER
         How often TCP sends out keepalive messages when keepalive is enabled.
         Default: 2hours.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 28e9bd3abceb..b81f45c67b2e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -274,6 +274,7 @@ extern int sysctl_tcp_challenge_ack_limit;
 extern unsigned int sysctl_tcp_notsent_lowat;
 extern int sysctl_tcp_min_tso_segs;
 extern int sysctl_tcp_autocorking;
+extern int sysctl_tcp_invalid_ratelimit;
 
 extern atomic_long_t tcp_memory_allocated;
 extern struct percpu_counter tcp_sockets_allocated;
@@ -1236,6 +1237,37 @@ static inline bool tcp_paws_reject(const struct tcp_options_received *rx_opt,
         return true;
 }
 
+/* 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
+ * attacks that send repeated SYNs or ACKs for the same connection. To
+ * do this, we do not send a duplicate SYNACK or ACK if the remote
+ * endpoint is sending out-of-window SYNs or pure ACKs at a high rate.
+ */
+static inline bool tcp_oow_rate_limited(struct net *net,
+                                        const struct sk_buff *skb,
+                                        int mib_idx, u32 *last_oow_ack_time)
+{
+        /* 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_BH(net, mib_idx);
+                        return true;    /* rate-limited: don't send yet! */
+                }
+        }
+
+        *last_oow_ack_time = tcp_time_stamp;
+
+not_rate_limited:
+        return false;   /* not rate-limited: go ahead, send dupack now! */
+}
+
 static inline void tcp_mib_init(struct net *net)
 {
         /* See RFC 2012 */
diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h
index b22224100011..6a6fb747c78d 100644
--- a/include/uapi/linux/snmp.h
+++ b/include/uapi/linux/snmp.h
@@ -270,6 +270,12 @@ enum
         LINUX_MIB_TCPHYSTARTTRAINCWND,          /* TCPHystartTrainCwnd */
         LINUX_MIB_TCPHYSTARTDELAYDETECT,        /* TCPHystartDelayDetect */
         LINUX_MIB_TCPHYSTARTDELAYCWND,          /* TCPHystartDelayCwnd */
+        LINUX_MIB_TCPACKSKIPPEDSYNRECV,         /* TCPACKSkippedSynRecv */
+        LINUX_MIB_TCPACKSKIPPEDPAWS,            /* TCPACKSkippedPAWS */
+        LINUX_MIB_TCPACKSKIPPEDSEQ,             /* TCPACKSkippedSeq */
+        LINUX_MIB_TCPACKSKIPPEDFINWAIT2,        /* TCPACKSkippedFinWait2 */
+        LINUX_MIB_TCPACKSKIPPEDTIMEWAIT,        /* TCPACKSkippedTimeWait */
+        LINUX_MIB_TCPACKSKIPPEDCHALLENGE,       /* TCPACKSkippedChallenge */
         __LINUX_MIB_MAX
 };
 
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8f9cd200ce20..d8953ef0770c 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -292,6 +292,12 @@ static const struct snmp_mib snmp4_net_list[] = {
         SNMP_MIB_ITEM("TCPHystartTrainCwnd", LINUX_MIB_TCPHYSTARTTRAINCWND),
         SNMP_MIB_ITEM("TCPHystartDelayDetect", LINUX_MIB_TCPHYSTARTDELAYDETECT),
         SNMP_MIB_ITEM("TCPHystartDelayCwnd", LINUX_MIB_TCPHYSTARTDELAYCWND),
+        SNMP_MIB_ITEM("TCPACKSkippedSynRecv", LINUX_MIB_TCPACKSKIPPEDSYNRECV),
+        SNMP_MIB_ITEM("TCPACKSkippedPAWS", LINUX_MIB_TCPACKSKIPPEDPAWS),
+        SNMP_MIB_ITEM("TCPACKSkippedSeq", LINUX_MIB_TCPACKSKIPPEDSEQ),
+        SNMP_MIB_ITEM("TCPACKSkippedFinWait2", LINUX_MIB_TCPACKSKIPPEDFINWAIT2),
+        SNMP_MIB_ITEM("TCPACKSkippedTimeWait", LINUX_MIB_TCPACKSKIPPEDTIMEWAIT),
+        SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE),
         SNMP_MIB_SENTINEL
 };
 
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e0ee384a448f..82601a68cf90 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -729,6 +729,13 @@ static struct ctl_table ipv4_table[] = {
                 .extra2         = &one,
         },
         {
+                .procname       = "tcp_invalid_ratelimit",
+                .data           = &sysctl_tcp_invalid_ratelimit,
+                .maxlen         = sizeof(int),
+                .mode           = 0644,
+                .proc_handler   = proc_dointvec_ms_jiffies,
+        },
+        {
                 .procname       = "icmp_msgs_per_sec",
                 .data           = &sysctl_icmp_msgs_per_sec,
                 .maxlen         = sizeof(int),
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index d3dfff78fa19..9401aa43b814 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -100,6 +100,7 @@ int sysctl_tcp_thin_dupack __read_mostly;
 
 int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
 int sysctl_tcp_early_retrans __read_mostly = 3;
+int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2;
 
 #define FLAG_DATA               0x01 /* Incoming frame contained data.          */
 #define FLAG_WIN_UPDATE         0x02 /* Incoming ACK was a window update.       */