[PATCHv10 05/18] x86/kexec: Keep CR4.MCE set during kexec for TDX guest

[Kirill A. Shutemov]

On Tue, Apr 09, 2024 at 07:22:24AM -0700, Sean Christopherson wrote:
> On Tue, Apr 09, 2024, Kirill A. Shutemov wrote:
> > Depending on setup, TDX guests might be allowed to clear CR4.MCE.
> > Attempt to clear it leads to #VE.
> > 
> > Use alternatives to keep the flag during kexec for TDX guests.
> > 
> > The change doesn't affect non-TDX-guest environments.
> > 
> > Signed-off-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
> > ---
> >  arch/x86/kernel/relocate_kernel_64.S | 8 ++++++++
> >  1 file changed, 8 insertions(+)
> > 
> > diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
> > index 56cab1bb25f5..8e2037d78a1f 100644
> > --- a/arch/x86/kernel/relocate_kernel_64.S
> > +++ b/arch/x86/kernel/relocate_kernel_64.S
> > @@ -5,6 +5,8 @@
> >   */
> >  
> >  #include <linux/linkage.h>
> > +#include <linux/stringify.h>
> > +#include <asm/alternative.h>
> >  #include <asm/page_types.h>
> >  #include <asm/kexec.h>
> >  #include <asm/processor-flags.h>
> > @@ -145,11 +147,17 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
> >  	 * Set cr4 to a known state:
> >  	 *  - physical address extension enabled
> >  	 *  - 5-level paging, if it was enabled before
> > +	 *  - Machine check exception on TDX guest, if it was enabled before.
> > +	 *    Clearing MCE might not allowed in TDX guests, depending on setup.
> >  	 */
> >  	movl	$X86_CR4_PAE, %eax
> >  	testq	$X86_CR4_LA57, %r13
> >  	jz	1f
> >  	orl	$X86_CR4_LA57, %eax
> > +1:
> > +	testq	$X86_CR4_MCE, %r13
> > +	jz	1f
> > +	ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %eax), X86_FEATURE_TDX_GUEST
> 
> The TEST+Jcc+OR sequences are rather odd, and require way more instructions and
> thus way more copy+paste than is necessary.
> 
> 	movl	$X86_CR4_LA57, %eax
> 	ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %eax), X86_FEATURE_TDX_GUEST
> 	andl	%r13d, %eax
> 	orl	$X86_CR4_PAE, %eax
> 	movq	%rax, %cr4
> 
> Then preserving new bits unconditionally only requires adding the flag to the
> initial move, and feature-dependent bits only need a single ALTERNATIVE line.

Thanks! It is much better.

> And there's no branches, blazing fast kexec! ;-)

kexec/sec STONKS! :D

Updated patch is below.

>From 6be428e3b1c6fb494b2c48ba6a7c133514a0b2b4 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov at linux.intel.com>
Date: Fri, 10 Feb 2023 12:53:11 +0300
Subject: [PATCHv10.1 05/18] x86/kexec: Keep CR4.MCE set during kexec for TDX guest

Depending on setup, TDX guests might be allowed to clear CR4.MCE.
Attempt to clear it leads to #VE.

Use alternatives to keep the flag during kexec for TDX guests.

The change doesn't affect non-TDX-guest environments.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov at linux.intel.com>
---
 arch/x86/kernel/relocate_kernel_64.S | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 56cab1bb25f5..90246d544eb1 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -5,6 +5,8 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/stringify.h>
+#include <asm/alternative.h>
 #include <asm/page_types.h>
 #include <asm/kexec.h>
 #include <asm/processor-flags.h>
@@ -143,14 +145,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
 
 	/*
 	 * Set cr4 to a known state:
-	 *  - physical address extension enabled
 	 *  - 5-level paging, if it was enabled before
+	 *  - Machine check exception on TDX guest, if it was enabled before.
+	 *    Clearing MCE might not allowed in TDX guests, depending on setup.
+	 *  - physical address extension enabled
 	 */
-	movl	$X86_CR4_PAE, %eax
-	testq	$X86_CR4_LA57, %r13
-	jz	1f
-	orl	$X86_CR4_LA57, %eax
-1:
+	movl	$X86_CR4_LA57, %eax
+	ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %eax), X86_FEATURE_TDX_GUEST
+	andl	%r13d, %eax
+	orl	$X86_CR4_PAE, %eax
 	movq	%rax, %cr4
 
 	jmp 1f
-- 
  Kiryl Shutsemau / Kirill A. Shutemov