svn commit: r269800 - stable/10/sbin/ping6

[John Hay]

Hi Xin,

I have just upgraded one of my boxes to 10-stable and found one of my
scripts just hangs. I traced it to this change in ping6. If you do
"ping6 -c 3 <machine_that_is_now_dead>", ping6 will hang until you
^C it.

Regards

John

On Mon, Aug 11, 2014 at 06:54:07AM +0000, Xin LI wrote:
> Author: delphij
> Date: Mon Aug 11 06:54:07 2014
> New Revision: 269800
> URL: http://svnweb.freebsd.org/changeset/base/269800
> 
> Log:
>   MFC r269180:
>   
>   When interval is set to very small value with limited amount of packets,
>   ping6(8) would quit before the remote side gets a chance to respond.
>   
>   Solve this by resetting the itimer when we have reached the maximum packet
>   number have reached, but let the other handling to continue.
>   
>   PR:		bin/151023
>   Submitted by:	tjmao at tjmao.net
> 
> Modified:
>   stable/10/sbin/ping6/ping6.c
> Directory Properties:
>   stable/10/   (props changed)
> 
> Modified: stable/10/sbin/ping6/ping6.c
> ==============================================================================
> --- stable/10/sbin/ping6/ping6.c	Mon Aug 11 03:04:16 2014	(r269799)
> +++ stable/10/sbin/ping6/ping6.c	Mon Aug 11 06:54:07 2014	(r269800)
> @@ -1090,8 +1090,14 @@ main(int argc, char *argv[])
>  		/* signal handling */
>  		if (seenalrm) {
>  			/* last packet sent, timeout reached? */
> -			if (npackets && ntransmitted >= npackets)
> -				break;
> +			if (npackets && ntransmitted >= npackets) {
> +				struct timeval zerotime = {0, 0};
> +				itimer.it_value = zerotime;
> +				itimer.it_interval = zerotime;
> +				(void)setitimer(ITIMER_REAL, &itimer, NULL);
> +				seenalrm = 0;   /* clear flag */
> +				continue;
> +			}
>  			retransmit();
>  			seenalrm = 0;
>  			continue;