linux-kernel - Re: 2f47e7e19f ("x86/mm/kaiser: Use PCID feature to make user and .."): WARNING: CPU: 0 PID: 1 at mm/early_ioremap.c:114 __early

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: <20171127190802.GC12661@u40b0340c692b58f6553c.ant.amazon.com>
Date:   Mon, 27 Nov 2017 11:08:02 -0800
From:   Eduardo Valentin <eduval@...zon.com>
To:     Dave Hansen <dave.hansen@...ux.intel.com>
CC:     Eduardo Valentin <eduval@...zon.com>,
        Ingo Molnar <mingo@...nel.org>,
        kernel test robot <fengguang.wu@...el.com>, LKP <lkp@...org>,
        <kvm@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        Thomas Gleixner <tglx@...utronix.de>, <wfg@...ux.intel.com>,
        <aliguori@...zon.com>
Subject: Re: 2f47e7e19f ("x86/mm/kaiser: Use PCID feature to make user and
 .."): WARNING: CPU: 0 PID: 1 at mm/early_ioremap.c:114 __early_ioremap

On Mon, Nov 27, 2017 at 10:28:35AM -0800, Dave Hansen wrote:
> On 11/27/2017 10:03 AM, Eduardo Valentin wrote:
> > On top of VM crashes, on your branch:
> > https://git.kernel.org/pub/scm/linux/kernel/git/daveh/x86-kaiser.git/log/?h=kaiser-414-tipwip-20171123
> > 
> > I am also getting crashes in early userspace, during tlb flushes. When KAISER is enabled and whenever userspace is loaded, I get a stack trace around __do_page_fault() called from restore_regs_and_return_to_kernel(). I saw this very same behavior in your v3 branch (kaiser-414-tipwip-20171121) too.
> > 
> > The crashes are followed by a machine halt via NMI. They also get the following warning:
> >  WARNING: can't dereference iret registers at fffffffffe198048 for ip page_fault+0x11/0x60
> 
> There was a known bug in my branch with not mapping some of the
> interrupt entry routines.  Random alignment makes it break or work.
> 
> Ingo/Thomas, correct me if I'm wrong, but I think we need folks testing
> here at the moment:
> 
> > https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/log/?h=auto-latest
> 
> My tree from last week is ancient gunk at this point. :)

OK, thanks for let me know, I will give it a shot on the tip tree today and send feed back.


-- 
All the best,
Eduardo Valentin