Re: [PATCH 3/4] mm/tlb, x86/mm: Support invalidating TLB caches for RCU_TABLE_FREE

[Nicholas Piggin]

On Wed, 22 Aug 2018 17:30:15 +0200
Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:

> Jann reported that x86 was missing required TLB invalidates when he
> hit the !*batch slow path in tlb_remove_table().
> 
> This is indeed the case; RCU_TABLE_FREE does not provide TLB (cache)
> invalidates, the PowerPC-hash where this code originated and the
> Sparc-hash where this was subsequently used did not need that. ARM
> which later used this put an explicit TLB invalidate in their
> __p*_free_tlb() functions, and PowerPC-radix followed that example.

So this is interesting, I _think_ a145abf12c did fix this bug for
powerpc, but then it seem to have been re-broken by a46cc7a90f
because that one defers the flush back to tlb_flush time. There
was quite a lot of churn getting the radix MMU off the ground at
that point though so I'm not 100% sure.

But AFAIKS powerpc today has this same breakage, and this patch
should fix it.

I have a couple of patches that touch the same code I'll send, you
might have some opinions on them.

Thanks,
Nick