[Patch RESEND] x86: don't rely on VMWare emulating PAT MSR correctly

[Patch RESEND] x86: don't rely on VMWare emulating PAT MSR correctly

[Juergen Gross]

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 <jongman.heo@samsung.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Tested-by: Jongman Heo <jongman.heo@samsung.com>
Acked-by: Alok N Kataria <akataria@vmware.com>
---
 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

Re: [Patch RESEND] x86: don't rely on VMWare emulating PAT MSR correctly

[Juergen Gross]

PING!

The patch repairs a bug with VMWARE, which has been reported by several
users. All of them have confirmed the patch is working. And VMWARE has
acked the patch. What else do you need to take it? It is available for
over a month now!

Juergen

On 01/12/2015 06:15 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 <jongman.heo@samsung.com>
> Signed-off-by: Juergen Gross <jgross@suse.com>
> Tested-by: Jongman Heo <jongman.heo@samsung.com>
> Acked-by: Alok N Kataria <akataria@vmware.com>
> ---
>   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);
>
>

Re: [Patch RESEND] x86: don't rely on VMWare emulating PAT MSR correctly

[Alok Kataria]

[-- Warning: decoded text below may be mangled, UTF-8 assumed --]
[-- Attachment #1: Type: text/plain; charset="utf-8", Size: 2065 bytes --]

Juergen, thanks for following up on this. 

X86 maintainers - If it helps let me also confirm that without this
patch the latest kernels *always* crash on VMware guest running HWv10
and earlier.

Please include the fix at your earliest. 

Thanks,
Alok

On Mon, 2015-01-19 at 06:05 +0100, Juergen Gross wrote:
> PING!
> 
> The patch repairs a bug with VMWARE, which has been reported by several
> users. All of them have confirmed the patch is working. And VMWARE has
> acked the patch. What else do you need to take it? It is available for
> over a month now!
> 
> Juergen
> 
> On 01/12/2015 06:15 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 <jongman.heo@samsung.com>
> > Signed-off-by: Juergen Gross <jgross@suse.com>
> > Tested-by: Jongman Heo <jongman.heo@samsung.com>
> > Acked-by: Alok N Kataria <akataria@vmware.com>
> > ---
> >   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);
> >
> >
> 

ÿôèº{.nÇ+‰·Ÿ®‰­†+%ŠËÿ±éݶ\x17¥Šwÿº{.nÇ+‰·¥Š{±þG«éÿŠ{ayº\x1dʇڙë,j\a­¢f£¢·hšïêÿ‘êçz_è®\x03(­éšŽŠÝ¢j"ú\x1a¶^[m§ÿÿ¾\a«þG«éÿ¢¸?™¨è­Ú&£ø§~á¶iO•æ¬z·švØ^\x14\x04\x1a¶^[m§ÿÿÃ\fÿ¶ìÿ¢¸?–I¥

[tip:x86/urgent] x86: Don' t rely on VMWare emulating PAT MSR correctly

[tip-bot for Juergen Gross]

Commit-ID:  9d34cfdf47963905d792ae9c000efa522739abe4
Gitweb:     http://git.kernel.org/tip/9d34cfdf47963905d792ae9c000efa522739abe4
Author:     Juergen Gross <jgross@suse.com>
AuthorDate: Mon, 12 Jan 2015 06:15:45 +0100
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Tue, 20 Jan 2015 14:33:45 +0100

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.

Commit bd809af16e3ab triggers this VMWare bug when the kernel is
booted as a VMWare guest.

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

Fixes: bd809af16e3ab "x86: Enable PAT to use cache mode translation tables"
Reported-and-tested-by: Jongman Heo <jongman.heo@samsung.com>
Acked-by: Alok N Kataria <akataria@vmware.com>
Signed-off-by: Juergen Gross <jgross@suse.com>
Link: http://lkml.kernel.org/r/1421039745-14335-1-git-send-email-jgross@suse.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 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);