linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* Re: [PATCH] x86/cpu, x86/pti: Do not enable PTI on AMD processors
@ 2018-01-03 11:07 Ivan Ivanov
  0 siblings, 0 replies; 9+ messages in thread
From: Ivan Ivanov @ 2018-01-03 11:07 UTC (permalink / raw)
  To: linux-kernel, thomas.lendacky

Why this wonderful tiny patch by Tom Lendacky is still not merged? If
it is just Intel who made these insecure CPUs , for which this
"slowdown workaround" is required, ---> why the AMD CPU owners should
suffer from Intel's design faults ? " cpu_insecure " is Intel's
problem ; according to Tom Lendacky from AMD - AMD CPUs do not need
this "slowdown workaround" which is required for Intel CPUs. Please
merge this patch as soon as possible

Of course, the Intel employees would be happy to see this patch get
delayed or even not merged, because its a shame and bad reputation for
their company and products :
>
> I would rather not just hard-code it in a way that we say one vendor has never and will never be affected
>
> --- by Dave Hansen from Intel corporation
>

Luckily, according to LKML - a message with Tom's patch is the Top
Hottest Message viewed ! The fate of this patch is being closely
monitored by the people all over the world, and hopefully the Linux
community will not allow any injustice to happen

On Tue, Dec 26, 2017 at 11:43:54PM -0600, Tom Lendacky wrote:
> AMD processors are not subject to the types of attacks that the kernel
> page table isolation feature protects against.  The AMD microarchitecture
> does not allow memory references, including speculative references, that
> access higher privileged data when running in a lesser privileged mode
> when that access would result in a page fault.
>
> Disable page table isolation by default on AMD processors by not setting
> the X86_BUG_CPU_INSECURE feature, which controls whether X86_FEATURE_PTI
> is set.
>
> Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
> ---
>  arch/x86/kernel/cpu/common.c |    4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
> index c47de4e..7d9e3b0 100644
> --- a/arch/x86/kernel/cpu/common.c
> +++ b/arch/x86/kernel/cpu/common.c
> @@ -923,8 +923,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
>
>   setup_force_cpu_cap(X86_FEATURE_ALWAYS);
>
> - /* Assume for now that ALL x86 CPUs are insecure */
> - setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
> + if (c->x86_vendor != X86_VENDOR_AMD)
> + setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
>
>   fpu__init_system(c);

Reviewed-by: Ivan Ivanov <qmastery16@gmail.com>

Best regards,
Ivan Ivanov,
coreboot project developer
and open-source enthusiast

^ permalink raw reply	[flat|nested] 9+ messages in thread
* Re: [PATCH] x86/cpu, x86/pti: Do not enable PTI on AMD processors
@ 2018-01-03 19:38 Tim Mouraveiko
  0 siblings, 0 replies; 9+ messages in thread
From: Tim Mouraveiko @ 2018-01-03 19:38 UTC (permalink / raw)
  To: linux-kernel

On 12/26/2017 09:43 PM, Tom Lendacky wrote:
>AMD processors are not subject to the types of attacks that the kernel page table isolation 
feature protects against.

There is no doubt this is a serious flaw. This thread reminded me - about a year ago we 
discovered a software code that bricked an Intel CPU. The software code was executed and 
the processor seized. The Motherboard was reset via the reset button, but the processor 
never came back. It was rather dead - the CPU did not even draw any power. We contacted 
Intel and one of their personnel suggested that they were aware of it. I never quite 
understood if it was a processor feature or a flaw.

Tim

^ permalink raw reply	[flat|nested] 9+ messages in thread
* [PATCH] x86/cpu, x86/pti: Do not enable PTI on AMD processors
@ 2017-12-27  5:43 Tom Lendacky
  2017-12-27  8:48 ` Dave Hansen
                   ` (2 more replies)
  0 siblings, 3 replies; 9+ messages in thread
From: Tom Lendacky @ 2017-12-27  5:43 UTC (permalink / raw)
  To: x86
  Cc: Dave Hansen, linux-kernel, Ingo Molnar, Andy Lutomirski,
	H. Peter Anvin, Thomas Gleixner, Borislav Petkov

AMD processors are not subject to the types of attacks that the kernel
page table isolation feature protects against.  The AMD microarchitecture
does not allow memory references, including speculative references, that
access higher privileged data when running in a lesser privileged mode
when that access would result in a page fault.

Disable page table isolation by default on AMD processors by not setting
the X86_BUG_CPU_INSECURE feature, which controls whether X86_FEATURE_PTI
is set.

Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com>
---
 arch/x86/kernel/cpu/common.c |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index c47de4e..7d9e3b0 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -923,8 +923,8 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
 
 	setup_force_cpu_cap(X86_FEATURE_ALWAYS);
 
-	/* Assume for now that ALL x86 CPUs are insecure */
-	setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
+	if (c->x86_vendor != X86_VENDOR_AMD)
+		setup_force_cpu_bug(X86_BUG_CPU_INSECURE);
 
 	fpu__init_system(c);
 

^ permalink raw reply related	[flat|nested] 9+ messages in thread

end of thread, other threads:[~2018-02-13 13:21 UTC | newest]

Thread overview: 9+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-01-03 11:07 [PATCH] x86/cpu, x86/pti: Do not enable PTI on AMD processors Ivan Ivanov
  -- strict thread matches above, loose matches on Subject: below --
2018-01-03 19:38 Tim Mouraveiko
2017-12-27  5:43 Tom Lendacky
2017-12-27  8:48 ` Dave Hansen
2017-12-27 14:47   ` Tom Lendacky
2017-12-28  0:20 ` Borislav Petkov
2018-02-12 15:26 ` Pavel Machek
2018-02-12 15:37   ` Brian Gerst
2018-02-13 13:21   ` Thomas Gleixner

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).