Re: [RFC PATCH] sys_membarrier(): system/process-wide memory barrier (x86) (v12)

[Steven Rostedt]

On Mon, 16 Mar 2015 08:49:40 -0700
"Paul E. McKenney" <paulmck@xxxxxxxxxxxxxxxxxx> wrote:

> On Mon, Mar 16, 2015 at 10:24:30AM -0400, Steven Rostedt wrote:
> > On Mon, 16 Mar 2015 15:19:39 +0100
> > Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> > 
> > > 
> > > I suppose this is an unprivileged syscall; so what do we do about:
> > > 
> > > 	for (;;)
> > > 		sys_membar(EXPEDITED);
> > > 
> > > Which would spray the entire system with IPIs at break neck speed.
> > 
> > Perhaps it should be rate limited. Have parameters (controlled via
> > sysctl) that will only allow so many of these per ms. If it exceeds it,
> > then the call will end up being a schedule_timeout() till it is allowed
> > to continue. Thus, the above will spit out a few hundred IPIs, then
> > sleep for a millisecond, and then spit out another hundred IPIs and
> > sleep again.
> > 
> > That would prevent any DoS attacks.
> 
> But this would only qualify as a DoS if MEMBARRIER_EXPEDITED_FLAG and
> !MEMBARRIER_PRIVATE_FLAG.  Otherwise, the user's process is only DoSing
> itself, which is that user's problem, not anyone else's.  And it looks
> like the current patch refuses to implement this DoS case, unless I am
> really confused about the code in membarrier_expedited().  And in fact
> membarrier_validate_flags() checks for this DoS case and returns -EINVAL.
> 
> So I do not believe that this syscall permits that type of DoS.
> 
> What am I missing here?
>

That I wasn't replying about the patch but only to Peter's comment,
which made it appear that sys_membar() would spew IPIs over the entire
system. If this is not a case, then there's no need for rate limiting.

-- Steve
--
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/