Re: [BUG?] X86 arch_tlbbatch_flush() seems to be lacking mm_tlb_flush_nested() integration

[Kirill A. Shutemov]

On Sat, Oct 15, 2022 at 12:29:57AM +0200, Jann Horn wrote:
> On Sat, Oct 15, 2022 at 12:23 AM Kirill A. Shutemov
> <kirill@xxxxxxxxxxxxx> wrote:
> > On Fri, Oct 14, 2022 at 08:19:42PM +0200, Jann Horn wrote:
> > > Hi!
> > >
> > > I haven't actually managed to reproduce this behavior, so maybe I'm
> > > just misunderstanding how this works; but I think the
> > > arch_tlbbatch_flush() path for batched TLB flushing in vmscan ought to
> > > have some kind of integration with mm_tlb_flush_nested().
> > >
> > > I think that currently, the following race could happen:
> > >
> > > [initial situation: page P is mapped into a page table of task B, but
> > > the page is not referenced, the PTE's A/D bits are clear]
> > > A: vmscan begins
> > > A: vmscan looks at P and P's PTEs, and concludes that P is not currently in use
> > > B: reads from P through the PTE, setting the Accessed bit and creating
> > > a TLB entry
> > > A: vmscan enters try_to_unmap_one()
> > > A: try_to_unmap_one() calls should_defer_flush(), which returns true
> > > A: try_to_unmap_one() removes the PTE and queues a TLB flush
> > > (arch_tlbbatch_add_mm())
> > > A: try_to_unmap_one() returns, try_to_unmap() returns to shrink_folio_list()
> > > B: calls munmap() on the VMA that mapped P
> > > B: no PTEs are removed, so no TLB flush happens
> > > B: munmap() returns
> >
> > I think here we will serialize against anon_vma/i_mmap lock in
> > __do_munmap() -> unmap_region() -> free_pgtables() that A also holds.
> >
> > So I believe munmap() is safe, but MADV_DONTNEED (and its flavours) is not.
> 
> shrink_folio_list() is not in a context that is operating on a
> specific MM; it is operating on a list of pages that might be mapped
> into different processes all over the system.

s/specific MM/specific page/

> So A has temporarily held those locks somewhere inside
> try_to_unmap_one(), but it will drop them before it reaches the point

inside try_to_unmap(), which handles all mappings of the page.

> where it issues the batched TLB flush.
> And this batched TLB flush potentially covers multiple MMs at once; it
> is not targeted towards a specific MM, but towards all of the CPUs on
> which any of the touched MMs might be active.

But, yes, you are right. I thought that try_to_unmap_flush() called inside
try_to_unmap() under the lock.

-- 
  Kiryl Shutsemau / Kirill A. Shutemov