linux-kernel - Re: [RFC PATCH v3 12/24] x86/mm: Modify ptep_set_wrprotect and pmdp_set_wrprotect for _PAGE_DIRTY

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <1535644924.26689.7.camel@intel.com>
Date:   Thu, 30 Aug 2018 09:02:04 -0700
From:   Yu-cheng Yu <yu-cheng.yu@...el.com>
To:     Jann Horn <jannh@...gle.com>
Cc:     the arch/x86 maintainers <x86@...nel.org>,
        "H . Peter Anvin" <hpa@...or.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        kernel list <linux-kernel@...r.kernel.org>,
        linux-doc@...r.kernel.org, Linux-MM <linux-mm@...ck.org>,
        linux-arch <linux-arch@...r.kernel.org>,
        Linux API <linux-api@...r.kernel.org>,
        Arnd Bergmann <arnd@...db.de>,
        Andy Lutomirski <luto@...capital.net>,
        Balbir Singh <bsingharora@...il.com>,
        Cyrill Gorcunov <gorcunov@...il.com>,
        Dave Hansen <dave.hansen@...ux.intel.com>,
        Florian Weimer <fweimer@...hat.com>, hjl.tools@...il.com,
        Jonathan Corbet <corbet@....net>, keescook@...omiun.org,
        Mike Kravetz <mike.kravetz@...cle.com>,
        Nadav Amit <nadav.amit@...il.com>,
        Oleg Nesterov <oleg@...hat.com>, Pavel Machek <pavel@....cz>,
        Peter Zijlstra <peterz@...radead.org>,
        ravi.v.shankar@...el.com, vedvyas.shanbhogue@...el.com
Subject: Re: [RFC PATCH v3 12/24] x86/mm: Modify ptep_set_wrprotect and
 pmdp_set_wrprotect for _PAGE_DIRTY_SW

On Thu, 2018-08-30 at 17:49 +0200, Jann Horn wrote:
> On Thu, Aug 30, 2018 at 4:43 PM Yu-cheng Yu <yu-cheng.yu@...el.com>
> wrote:
> > 
> > 
> > When Shadow Stack is enabled, the read-only and PAGE_DIRTY_HW PTE
> > setting is reserved only for the Shadow Stack.  To track dirty of
> > non-Shadow Stack read-only PTEs, we use PAGE_DIRTY_SW.
> > 
> > Update ptep_set_wrprotect() and pmdp_set_wrprotect().
> > 
> > Signed-off-by: Yu-cheng Yu <yu-cheng.yu@...el.com>
> > ---
> >  arch/x86/include/asm/pgtable.h | 42
> > ++++++++++++++++++++++++++++++++++
> >  1 file changed, 42 insertions(+)
> > 
> > diff --git a/arch/x86/include/asm/pgtable.h
> > b/arch/x86/include/asm/pgtable.h
> > index 4d50de77ea96..556ef258eeff 100644
> > --- a/arch/x86/include/asm/pgtable.h
> > +++ b/arch/x86/include/asm/pgtable.h
> > @@ -1203,7 +1203,28 @@ static inline pte_t
> > ptep_get_and_clear_full(struct mm_struct *mm,
> >  static inline void ptep_set_wrprotect(struct mm_struct *mm,
> >                                       unsigned long addr, pte_t
> > *ptep)
> >  {
> > +       pte_t pte;
> > +
> >         clear_bit(_PAGE_BIT_RW, (unsigned long *)&ptep->pte);
> > +       pte = *ptep;
> > +
> > +       /*
> > +        * Some processors can start a write, but ending up seeing
> > +        * a read-only PTE by the time they get to the Dirty bit.
> > +        * In this case, they will set the Dirty bit, leaving a
> > +        * read-only, Dirty PTE which looks like a Shadow Stack
> > PTE.
> > +        *
> > +        * However, this behavior has been improved and will not
> > occur
> > +        * on processors supporting Shadow Stacks.  Without this
> > +        * guarantee, a transition to a non-present PTE and flush
> > the
> > +        * TLB would be needed.
> > +        *
> > +        * When change a writable PTE to read-only and if the PTE
> > has
> > +        * _PAGE_DIRTY_HW set, we move that bit to _PAGE_DIRTY_SW
> > so
> > +        * that the PTE is not a valid Shadow Stack PTE.
> > +        */
> > +       pte = pte_move_flags(pte, _PAGE_DIRTY_HW, _PAGE_DIRTY_SW);
> > +       set_pte_at(mm, addr, ptep, pte);
> >  }
> I don't understand why it's okay that you first atomically clear the
> RW bit, then atomically switch from DIRTY_HW to DIRTY_SW. Doesn't
> that
> mean that between the two atomic writes, another core can
> incorrectly
> see a shadow stack?

Yes, we had that concern earlier and checked.
On processors supporting Shadow Stacks, that will not happen.

Yu-cheng