Re: [PATCH v4 2/3] ioremap: Update pgtable free interfaces with addr

From: Will Deacon
Date: Wed Jul 04 2018 - 13:35:55 EST


On Tue, Jul 03, 2018 at 11:02:15PM +0200, Thomas Gleixner wrote:
> On Fri, 29 Jun 2018, Kani, Toshi wrote:
> > On Fri, 2018-06-29 at 13:23 +0100, Will Deacon wrote:
> > > On Wed, Jun 27, 2018 at 04:13:22PM +0000, Kani, Toshi wrote:
> > > > On Wed, 2018-06-27 at 16:56 +0100, Will Deacon wrote:
> > > > > On Wed, Jun 27, 2018 at 08:13:47AM -0600, Toshi Kani wrote:
> > > > > > From: Chintan Pandya <cpandya@xxxxxxxxxxxxxx>
> > > > > >
> > > > > > The following kernel panic was observed on ARM64 platform due to a stale
> > > > > > TLB entry.
> > > > > >
> > > > > > 1. ioremap with 4K size, a valid pte page table is set.
> > > > > > 2. iounmap it, its pte entry is set to 0.
> > > > > > 3. ioremap the same address with 2M size, update its pmd entry with
> > > > > > a new value.
> > > > > > 4. CPU may hit an exception because the old pmd entry is still in TLB,
> > > > > > which leads to a kernel panic.
> > > > > >
> > > > > > Commit b6bdb7517c3d ("mm/vmalloc: add interfaces to free unmapped page
> > > > > > table") has addressed this panic by falling to pte mappings in the above
> > > > > > case on ARM64.
> > > > > >
> > > > > > To support pmd mappings in all cases, TLB purge needs to be performed
> > > > > > in this case on ARM64.
> > > > > >
> > > > > > Add a new arg, 'addr', to pud_free_pmd_page() and pmd_free_pte_page()
> > > > > > so that TLB purge can be added later in seprate patches.
> > > > >
> > > > > So I acked v13 of Chintan's series posted here:
> > > > >
> > > > > http://lists.infradead.org/pipermail/linux-arm-kernel/2018-June/582953.html
> > > > >
> > > > > any chance this lot could all be merged together, please?
> > > >
> > > > Chintan's patch 2/3 and 3/3 apply cleanly on top of my series. Can you
> > > > please coordinate with Thomas on the logistics?
> > >
> > > Sure. I guess having this series on a common branch that I can pull into
> > > arm64 and apply Chintan's other patches on top would work.
> > >
> > > How does that sound?
> >
> > Should this go thru -mm tree then?
> >
> > Andrew, Thomas, what do you think?
>
> I just pick it up and provide Will a branch to pull that lot from.

Thanks, Thomas. Please let me know once you've pushed something out.

Will