Re: Silent data corruption caused by XPC V2.

[Dean Nelson <dcn@sgi.com>]

On Tue, Aug 08, 2006 at 11:52:41AM -0700, Yu, Fenghua wrote:
> 
> Seems the following part is missed in your patch:
> 
> --- arch/ia64/sn/kernel/xpc_main.c      2006-02-13 12:35:03.000000000
> -0800
> +++ arch/ia64/sn/kernel/xpc_main.c.new   2006-08-08 11:47:03.000000000
> -0700
> @@ -1374,6 +1374,7 @@ xpc_init(void)
>                 complete(&xpc_discovery_exited);
> 
>                 xpc_do_exit(xpcUnloading);
> +               kfree(xpc_remote_copy_buffer_base);
>                 return -EBUSY;
>         }


Actually, the very last line of xpc_do_exit() is the following:

        kfree(xpc_remote_copy_buffer_base);
}

I realize it's perhaps not the most straight-forward arrangement, but it
does have something to do with the various avenues through which our exit
processing can get invoked (not just by rmmod's call to xpc_exit()). 

I really do appreciate your feedback. Thanks.

Dean