linux-kernel - Re: [PATCHv3 15/27] x86/vdso: Allocate timens vdso

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: <CAG48ez3nT_RtaHrjpKPRZDYTyzxX49QBZXJ+u2AZmFy5Wao4wQ@mail.gmail.com>
Date:   Thu, 25 Apr 2019 20:32:17 +0200
From:   Jann Horn <jannh@...gle.com>
To:     Dmitry Safonov <dima@...sta.com>
Cc:     kernel list <linux-kernel@...r.kernel.org>,
        Adrian Reber <adrian@...as.de>,
        Andrei Vagin <avagin@...nvz.org>,
        Andy Lutomirski <luto@...nel.org>,
        Arnd Bergmann <arnd@...db.de>,
        Christian Brauner <christian.brauner@...ntu.com>,
        Cyrill Gorcunov <gorcunov@...nvz.org>,
        Dmitry Safonov <0x7f454c46@...il.com>,
        "Eric W. Biederman" <ebiederm@...ssion.com>,
        "H. Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...hat.com>,
        Jeff Dike <jdike@...toit.com>, Oleg Nesterov <oleg@...hat.com>,
        Pavel Emelyanov <xemul@...tuozzo.com>,
        Shuah Khan <shuah@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>,
        Vincenzo Frascino <vincenzo.frascino@....com>,
        containers@...ts.linux-foundation.org, criu@...nvz.org,
        Linux API <linux-api@...r.kernel.org>,
        "the arch/x86 maintainers" <x86@...nel.org>
Subject: Re: [PATCHv3 15/27] x86/vdso: Allocate timens vdso

On Thu, Apr 25, 2019 at 6:14 PM Dmitry Safonov <dima@...sta.com> wrote:
>
> As it has been discussed on timens RFC, adding a new conditional branch
> `if (inside_time_ns)` on VDSO for all processes is undesirable.
> It will add a penalty for everybody as branch predictor may mispredict
> the jump. Also there are instruction cache lines wasted on cmp/jmp.
>
> Those effects of introducing time namespace are very much unwanted
> having in mind how much work have been spent on micro-optimisation
> vdso code.
>
> The propose is to allocate a second vdso code with dynamically
> patched out (disabled by static_branch) timens code on boot time.
>
> Allocate another vdso and copy original code.
[...]
> diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
> index 80cbb2167eba..6aae9c0d400d 100644
> --- a/arch/x86/entry/vdso/vma.c
> +++ b/arch/x86/entry/vdso/vma.c
[...]
>  static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
>                       struct vm_area_struct *vma, struct vm_fault *vmf)
>  {
>         const struct vdso_image *image = vma->vm_mm->context.vdso_image;
> +       unsigned long offset = vmf->pgoff << PAGE_SHIFT;
>
>         if (!image || (vmf->pgoff << PAGE_SHIFT) >= image->size)
>                 return VM_FAULT_SIGBUS;
>
> -       vmf->page = virt_to_page(image->text + (vmf->pgoff << PAGE_SHIFT));
> +       if (current_timens_offsets() && image->text_timens)

I'm pretty sure that accessing `current` in here is wrong. AFAIK this
fault handler can be invoked on remote processes, through interfaces
like /proc/$pid/mem and process_vm_readv(); in that case, the kernel
should install a page based on the time namespace of the target
process, not based on the time namespace of the caller.

> +               vmf->page = vmalloc_to_page(image->text_timens + offset);
> +       else
> +               vmf->page = virt_to_page(image->text + offset);
> +
>         get_page(vmf->page);
>         return 0;
>  }
[...]