Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Content-Type: text/plain;
        charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 16.0 \(3696.120.41.1.1\))
Subject: Re: [BUG?] X86 arch_tlbbatch_flush() seems to be lacking
 mm_tlb_flush_nested() integration
From:   Nadav Amit <nadav.amit@gmail.com>
In-Reply-To: <CAG48ez0B18eh3Q1853Cug8WSip7dPb2G9fhgqsPWzr0D_TBjRQ@mail.gmail.com>
Date:   Sat, 15 Oct 2022 06:51:47 +0300
Cc:     Andy Lutomirski <luto@kernel.org>, Linux-MM <linux-mm@kvack.org>,
        Mel Gorman <mgorman@suse.de>, Rik van Riel <riel@redhat.com>,
        kernel list <linux-kernel@vger.kernel.org>,
        Kees Cook <keescook@chromium.org>,
        Ingo Molnar <mingo@kernel.org>,
        Sasha Levin <sasha.levin@oracle.com>,
        Andrew Morton <akpm@linux-foundation.org>,
        Will Deacon <will@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Linus Torvalds <torvalds@linuxfoundation.org>
Content-Transfer-Encoding: quoted-printable
Message-Id: <0484E294-D6D6-45CE-87F7-5AFDA5309BA1@gmail.com>
References: <CAG48ez0B18eh3Q1853Cug8WSip7dPb2G9fhgqsPWzr0D_TBjRQ@mail.gmail.com>
To:     Jann Horn <jannh@google.com>
Precedence: bulk

On Oct 14, 2022, at 9:19 PM, Jann Horn <jannh@google.com> wrote:

> Hi!
>=20
> 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().
>=20
> I think that currently, the following race could happen:
>=20
> [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

Unless I am missing something, flush_tlb_batched_pending() is would be
called and do the flushing at this point, no?

IIUC the scenario, we had some similar cases in the past [1]. Discussing
these scenarios required too many arguments for my liking, and I =
would=E2=80=99ve
preferred an easier-to-reason batching coordination between the batching
mechanisms. I proposed some schemes in the past, but to be fair, I think
all of them would have some extra overhead.

[1] =
https://lore.kernel.org/linux-mm/69BBEB97-1B10-4229-9AEF-DE19C26D8DFF@gmai=
l.com/T/#u