2014-12-16 09:58:46

by Juergen Gross

Subject: [PATCH] x86: don't rely on VMWare emulating PAT MSR correctly

VMWare seems not to emulate the PAT MSR correctly: reaeding
MSR_IA32_CR_PAT returns 0 even after writing another value to it.

Detect this bug and don't use the read value if it is 0.

Commit bd809af16e3ab1f8d55b3e2928c47c67e2a865d2 ("x86: Enable PAT to
use cache mode translation tables") triggers this VMWare bug when the
kernel is booted as a VMWare guest.

Reported-by: Jongman Heo <[email protected]>
Signed-off-by: Juergen Gross <[email protected]>
Tested-by: Jongman Heo <[email protected]>
---
arch/x86/mm/pat.c | 7 ++++++-
1 file changed, 6 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index edf299c..7ac6869 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -234,8 +234,13 @@ void pat_init(void)
PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);

/* Boot CPU check */
- if (!boot_pat_state)
+ if (!boot_pat_state) {
rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
+ if (!boot_pat_state) {
+ pat_disable("PAT read returns always zero, disabled.");
+ return;
+ }
+ }

wrmsrl(MSR_IA32_CR_PAT, pat);

--
2.1.2

2014-12-16 16:47:39

by H. Peter Anvin

Subject: Re: [PATCH] x86: don't rely on VMWare emulating PAT MSR correctly

On 12/16/2014 01:58 AM, Juergen Gross wrote:
> VMWare seems not to emulate the PAT MSR correctly: reaeding
> MSR_IA32_CR_PAT returns 0 even after writing another value to it.
>
> Detect this bug and don't use the read value if it is 0.
>
> Commit bd809af16e3ab1f8d55b3e2928c47c67e2a865d2 ("x86: Enable PAT to
> use cache mode translation tables") triggers this VMWare bug when the
> kernel is booted as a VMWare guest.
>
> Reported-by: Jongman Heo <[email protected]>
> Signed-off-by: Juergen Gross <[email protected]>
> Tested-by: Jongman Heo <[email protected]>

I presume cachability control is irrelevant for a VMware guest? I'm
wondering if it would be better to just plain ignore the failure rather
than disabling PAT.

-hpa

2014-12-17 04:53:05

by Juergen Gross

Subject: Re: [PATCH] x86: don't rely on VMWare emulating PAT MSR correctly

On 12/16/2014 05:47 PM, H. Peter Anvin wrote:
> On 12/16/2014 01:58 AM, Juergen Gross wrote:
>> VMWare seems not to emulate the PAT MSR correctly: reaeding
>> MSR_IA32_CR_PAT returns 0 even after writing another value to it.
>>
>> Detect this bug and don't use the read value if it is 0.
>>
>> Commit bd809af16e3ab1f8d55b3e2928c47c67e2a865d2 ("x86: Enable PAT to
>> use cache mode translation tables") triggers this VMWare bug when the
>> kernel is booted as a VMWare guest.
>>
>> Reported-by: Jongman Heo <[email protected]>
>> Signed-off-by: Juergen Gross <[email protected]>
>> Tested-by: Jongman Heo <[email protected]>
>
> I presume cachability control is irrelevant for a VMware guest? I'm
> wondering if it would be better to just plain ignore the failure rather
> than disabling PAT.

I'd rather disable PAT as this seems to be like a PAT erratum.

In case you want to keep PAT active I can redo the patch to not rely on
the read MSR value in the non-Xen case (under Xen reading the MSR is the
only way to obtain the correct settings).

Juergen

2014-12-17 04:57:06

by Alok Kataria

Subject: Re: [PATCH] x86: don't rely on VMWare emulating PAT MSR correctly

Hi,

On Tue, 2014-12-16 at 10:58 +0100, Juergen Gross wrote:
> VMWare seems not to emulate the PAT MSR correctly: reaeding
> MSR_IA32_CR_PAT returns 0 even after writing another value to it.
>
> Detect this bug and don't use the read value if it is 0.
>
> Commit bd809af16e3ab1f8d55b3e2928c47c67e2a865d2 ("x86: Enable PAT to
> use cache mode translation tables") triggers this VMWare bug when the
> kernel is booted as a VMWare guest.

Thanks for taking care of this, we are fine with this workaround. On
newer version of our product, where PAT is virtualized correctly on our
platform we will go back to using PAT, I will give it a spin sometime
later to verify it.

Acked-by: Alok N Kataria <[email protected]>

> Reported-by: Jongman Heo <[email protected]>
> Signed-off-by: Juergen Gross <[email protected]>
> Tested-by: Jongman Heo <[email protected]>
> ---
> arch/x86/mm/pat.c | 7 ++++++-
> 1 file changed, 6 insertions(+), 1 deletion(-)
>
> diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
> index edf299c..7ac6869 100644
> --- a/arch/x86/mm/pat.c
> +++ b/arch/x86/mm/pat.c
> @@ -234,8 +234,13 @@ void pat_init(void)
> PAT(4, WB) | PAT(5, WC) | PAT(6, UC_MINUS) | PAT(7, UC);
>
> /* Boot CPU check */
> - if (!boot_pat_state)
> + if (!boot_pat_state) {
> rdmsrl(MSR_IA32_CR_PAT, boot_pat_state);
> + if (!boot_pat_state) {
> + pat_disable("PAT read returns always zero, disabled.");
> + return;
> + }
> + }
>
> wrmsrl(MSR_IA32_CR_PAT, pat);
>

Alok
????{.n?+???????+%?????ݶ??w??{.n?+????{??G?????{ay?ʇڙ?,j??f???h?????????z_??(?階?ݢj"???m??????G????????????&???~???iO???z??v?^?m????????????I?