Re: [PATCH v6 00/10] Retpoline: Avoid speculative indirect calls in kernel

From: David Woodhouse
Date: Mon Jan 08 2018 - 07:49:47 EST



> On Mon, Jan 8, 2018 at 2:45 AM, David Woodhouse <dwmw2@xxxxxxxxxxxxx>
> wrote:
>> On Mon, 2018-01-08 at 02:34 -0800, Paul Turner wrote:
>>> One detail that is missing is that we still need RSB refill in some
>>> cases.
>>> This is not because the retpoline sequence itself will underflow (it
>>> is actually guaranteed not to, since it consumes only RSB entries
>>> that it generates.
>>> But either to avoid poisoning of the RSB entries themselves, or to
>>> avoid the hardware turning to alternate predictors on RSB underflow.
>>>
>>> Enumerating the cases we care about:
>>>
>>> â user->kernel in the absence of SMEP:
>>> In the absence of SMEP, we must worry about user-generated RSB
>>> entries being consumable by kernel execution.
>>> Generally speaking, for synchronous execution this will not occur
>>> (e.g. syscall, interrupt), however, one important case remains.
>>> When we context switch between two threads, we should flush the RSB
>>> so that execution generated from the unbalanced return path on the
>>> thread that we just scheduled into, cannot consume RSB entries
>>> potentially installed by the prior thread.
>>
>> Or IBPB here, yes? That's what we had in the original patch set when
>> retpoline came last, and what I assume will be put back again once we
>> *finally* get our act together and reinstate the full set of microcode
>> patches.
>
> IBPB is *much* more expensive than the sequence I suggested.
> If the kernel has been protected with a retpoline compilation, it is
> much faster to not use IBPB here; we only need to prevent
> ret-poisoning in this case.

Retpoline protects the kernel but IBPB is needed on context switch anyway
to protect userspace processes from each other.

But...

> A) I am enumerating all of the cases for completeness. It was missed
> by many that this detail was necessary on this patch, independently of
> IBRS.
> B) On the parts duplicated in (A), for specifics that are contributory to
> correctness in both cases, we should not hand-wave over the fact that
> they may or may not be covered by another patch-set. Users need to
> understand what's required for complete protection. Particularly if they
> are backporting.

... yes, agreed. Now we are putting retpoline first we shouldn't miss
things that we *were* doing anyway. TBH I really don't think we should
have spilt the patch sets apart; we'll work on getting the rest on top
ASAP.

--
dwmw2