linux-kernel - Re: [PATCH] KVM: x86: Increase the number of fixed MTRR regs to 10

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: <D020ADA9-A9D5-4F29-911A-4742E64E4DEC@gmail.com>
Date:	Mon, 18 Aug 2014 17:31:41 +0300
From:	Nadav Amit <nadav.amit@...il.com>
To:	Wanpeng Li <wanpeng.li@...ux.intel.com>,
	"pbonzini@...hat.com" <pbonzini@...hat.com>
Cc:	Nadav Amit <namit@...technion.ac.il>,
	"gleb@...nel.org" <gleb@...nel.org>,
	"tglx@...utronix.de" <tglx@...utronix.de>,
	"mingo@...hat.com" <mingo@...hat.com>,
	"hpa@...or.com" <hpa@...or.com>, "x86@...nel.org" <x86@...nel.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"kvm@...r.kernel.org" <kvm@...r.kernel.org>
Subject: Re: [PATCH] KVM: x86: Increase the number of fixed MTRR regs to 10

The cause for the blue-screen appears to be seabios, which leaves only 0x20 slots for “smp_mtrr”s.
Apparently, the increase in the variable range MTRR count caused it to exhaust the available slots.
As a result, some MSRs are not initialised by the BIOS (specifically, 3.5-4GB are not marked as UC), and cause Windows to panic.

Once we increase the size of the array smp_mtrr in seabios, Windows boots.

Paolo, you may wish to revert the patch. Please note that it was applied to some stable branches.

Nadav

On Aug 18, 2014, at 12:39 PM, Nadav Amit <nadav.amit@...il.com> wrote:

> I reproduced the blue-screen. Let me to to figure it out.
> 
> Nadav
> 
> On Aug 18, 2014, at 11:11 AM, Wanpeng Li <wanpeng.li@...ux.intel.com> wrote:
> 
>> On Mon, Aug 18, 2014 at 09:39:39AM +0300, Nadav Amit wrote:
>>> This should have been a benign patch. I'll try to get windows 7 installation disk and check ASAP.
>>> 
>> 
>> In addition, it just can be reproduced on 32bit win7 w/ MP enabled, in
>> case UP can't be reproduced.
>> 
>> Regards,
>> Wanpeng Li 
>> 
>>> Nadav
>>> 
>>>> On 18 Aug 2014, at 05:17, Wanpeng Li <wanpeng.li@...ux.intel.com> wrote:
>>>> 
>>>> Hi Nadav,
>>>>> On Wed, Jun 18, 2014 at 05:21:19PM +0300, Nadav Amit wrote:
>>>>> Recent Intel CPUs have 10 variable range MTRRs. Since operating systems
>>>>> sometime make assumptions on CPUs while they ignore capability MSRs, it is
>>>>> better for KVM to be consistent with recent CPUs. Reporting more MTRRs than
>>>>> actually supported has no functional implications.
>>>>> 
>>>>> Signed-off-by: Nadav Amit <namit@...technion.ac.il>
>>>>> ---
>>>>> arch/x86/include/asm/kvm_host.h | 2 +-
>>>>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>>>> 
>>>>> diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
>>>>> index 4931415..0bab29d 100644
>>>>> --- a/arch/x86/include/asm/kvm_host.h
>>>>> +++ b/arch/x86/include/asm/kvm_host.h
>>>>> @@ -95,7 +95,7 @@ static inline gfn_t gfn_to_index(gfn_t gfn, gfn_t base_gfn, int level)
>>>>> #define KVM_REFILL_PAGES 25
>>>>> #define KVM_MAX_CPUID_ENTRIES 80
>>>>> #define KVM_NR_FIXED_MTRR_REGION 88
>>>>> -#define KVM_NR_VAR_MTRR 8
>>>>> +#define KVM_NR_VAR_MTRR 10
>>>> 
>>>> We observed that there is obvious regression caused by this commit, 32bit 
>>>> win7 guest show blue screen during boot.
>>>> 
>>>> Regards,
>>>> Wanpeng Li 
>>>> 
>>>>> #define ASYNC_PF_PER_VCPU 64
>>>>> 
>>>>> -- 
>>>>> 1.9.1
>>>>> 
>>>>> --
>>>>> To unsubscribe from this list: send the line "unsubscribe kvm" in
>>>>> the body of a message to majordomo@...r.kernel.org
>>>>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
>>>> --
>>>> To unsubscribe from this list: send the line "unsubscribe kvm" in
>>>> the body of a message to majordomo@...r.kernel.org
>>>> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> 

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/