tcp: fix memleak when tcp internal pacing is used

hulk inclusion
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I4S8PN
CVE: NA

--------------------------------

The sock_hold() in tcp_internal_pacing() is expected to pair with
sock_put() in tcp_pace_kick(). But in some path tcp_internal_pacing()
is called without checking if pacing timer is already armed, causing
sock_hold() to be called one more time and tcp sock can't be released.

As Neal pointed out, this could happen from some of the retransmission
code paths that don't use tcp_xmit_retransmit_queue(), such as
tcp_retransmit_timer() and tcp_send_loss_probe().

The fix is provided by Eric, it extends the timer to cover all these
points that Neal mentioned.

Following is the reproduce procedure provided by Jason:
0) cat /proc/slabinfo | grep TCP
1) switch net.ipv4.tcp_congestion_control to bbr
2) using wrk tool something like that to send packages
3) using tc to increase the delay and loss to simulate the RTO case.
4) cat /proc/slabinfo | grep TCP
5) kill the wrk command and observe the number of objects and slabs in
TCP.
6) at last, you could notice that the number would not decrease.

Link: https://lore.kernel.org/all/CANn89i+7-wE4xr5D9DpH+N-xkL1SB8oVghCKgz+CT5eG1ODQhA@mail.gmail.com/Signed-off-by: NZhang Changzhong <zhangchangzhong@huawei.com>
Reviewed-by: NWei Yongjun <weiyongjun1@huawei.com>
Signed-off-by: NYang Yingliang <yangyingliang@huawei.com>

net/ipv4/tcp_output.c

@@ -1021,6 +1021,8 @@ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer)
 
 static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 {
+	struct tcp_sock *tp = tcp_sk(sk);
+	ktime_t expire, now;
 	u64 len_ns;
 	u32 rate;
 
@@ -1032,12 +1034,28 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb)
 
 	len_ns = (u64)skb->len * NSEC_PER_SEC;
 	do_div(len_ns, rate);
-	hrtimer_start(&tcp_sk(sk)->pacing_timer,
-		      ktime_add_ns(ktime_get(), len_ns),
+	now = ktime_get();
+	/* If hrtimer is already armed, then our caller has not
+	 * used tcp_pacing_check().
+	 */
+	if (unlikely(hrtimer_is_queued(&tp->pacing_timer))) {
+		expire = hrtimer_get_softexpires(&tp->pacing_timer);
+		if (ktime_after(expire, now))
+			now = expire;
+		if (hrtimer_try_to_cancel(&tp->pacing_timer) == 1)
+			__sock_put(sk);
+	}
+	hrtimer_start(&tp->pacing_timer, ktime_add_ns(now, len_ns),
 		      HRTIMER_MODE_ABS_PINNED_SOFT);
 	sock_hold(sk);
 }
 
+static bool tcp_pacing_check(const struct sock *sk)
+{
+	return tcp_needs_internal_pacing(sk) &&
+	       hrtimer_is_queued(&tcp_sk(sk)->pacing_timer);
+}
+
 static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb)
 {
 	skb->skb_mstamp = tp->tcp_mstamp;
@@ -2174,6 +2192,9 @@ static int tcp_mtu_probe(struct sock *sk)
 	if (!tcp_can_coalesce_send_queue_head(sk, probe_size))
 		return -1;
 
+	if (tcp_pacing_check(sk))
+		return -1;
+
 	/* We're allowed to probe.  Build it now. */
 	nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false);
 	if (!nskb)
@@ -2247,12 +2268,6 @@ static int tcp_mtu_probe(struct sock *sk)
 	return -1;
 }
 
-static bool tcp_pacing_check(const struct sock *sk)
-{
-	return tcp_needs_internal_pacing(sk) &&
-	       hrtimer_is_queued(&tcp_sk(sk)->pacing_timer);
-}
-
 /* TCP Small Queues :
  * Control number of packets in qdisc/devices to two packets / or ~1 ms.
  * (These limits are doubled for retransmits)