Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Content-Type: text/plain;
        charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 13.4 \(3608.120.23.2.4\))
Subject: Re: [PATCH] mm/userfaultfd: fix memory corruption due to writeprotect
From:   Nadav Amit <nadav.amit@gmail.com>
In-Reply-To: <X+P2OnR+ipY8d2qL@redhat.com>
Date:   Wed, 23 Dec 2020 19:09:10 -0800
Cc:     Andy Lutomirski <luto@amacapital.net>, Yu Zhao <yuzhao@google.com>,
        Andy Lutomirski <luto@kernel.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Peter Xu <peterx@redhat.com>, linux-mm <linux-mm@kvack.org>,
        lkml <linux-kernel@vger.kernel.org>,
        Pavel Emelyanov <xemul@openvz.org>,
        Mike Kravetz <mike.kravetz@oracle.com>,
        Mike Rapoport <rppt@linux.vnet.ibm.com>,
        stable <stable@vger.kernel.org>,
        Minchan Kim <minchan@kernel.org>,
        Will Deacon <will@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>
Content-Transfer-Encoding: quoted-printable
Message-Id: <3A6A1049-24C6-4B2D-8C59-21B549F742B4@gmail.com>
References: <X+PE38s2Egq4nzKv@google.com>
 <C332B03D-30B1-4C9C-99C2-E76988BFC4A1@amacapital.net>
 <X+P2OnR+ipY8d2qL@redhat.com>
To:     Andrea Arcangeli <aarcange@redhat.com>
Precedence: bulk

> On Dec 23, 2020, at 6:00 PM, Andrea Arcangeli <aarcange@redhat.com> =
wrote:
>=20
> On Wed, Dec 23, 2020 at 05:21:43PM -0800, Andy Lutomirski wrote:
>> I don=E2=80=99t love this as a long term fix. AFAICT we can have =
mm_tlb_flush_pending set for quite a while =E2=80=94 mprotect seems like =
it can wait in IO while splitting a huge page, for example. That gives =
us a window in which every write fault turns into a TLB flush.
>=20
> mprotect can't run concurrently with a page fault in the first place.
>=20
> One other near zero cost improvement easy to add if this would be "if
> (vma->vm_flags & (VM_SOFTDIRTY|VM_UFFD_WP))" and it could be made
> conditional to the two config options too.
>=20
> Still I don't mind doing it in some other way, uffd-wp has much easier
> time doing it in another way in fact.
>=20
> Whatever performs better is fine, but queuing up pending invalidate
> ranges don't look very attractive since it'd be a fixed cost that we'd
> always have to pay even when there's no fault (and there can't be any
> fault at least for mprotect).

I think there are other cases in which Andy=E2=80=99s concern is =
relevant
(MADV_PAGEOUT).

Perhaps holding some small bitmap based on part of the deferred flushed
pages (e.g., bits 12-17 of the address or some other kind of a single
hash-function bloom-filter) would be more performant to avoid (most)
unnecessary TLB flushes. It will be cleared before a TLB flush and set =
while
holding the PTL.

Checking if a flush is needed, under the PTL, would require a single =
memory
access (although potentially cache miss). It will however require one =
atomic
operation for each page-table whose PTEs=E2=80=99 flushes are deferred - =
in contrast
to the current scheme which requires two atomic operations for the =
*entire*
operation.