[v5,07/16] x86/startup_64: Simplify CR4 handling in startup code

Message ID 20240221113506.2565718-25-ardb+git@google.com
State New
Headers
Series x86: Confine early 1:1 mapped startup code |

Commit Message

Ard Biesheuvel Feb. 21, 2024, 11:35 a.m. UTC
  From: Ard Biesheuvel <ardb@kernel.org>

When paging is enabled, the CR4.PAE and CR4.LA57 control bits cannot be
changed, and so they can simply be preserved rather than reason about
whether or not they need to be set. CR4.MCE should be preserved unless
the kernel was built without CONFIG_X86_MCE, in which case it must be
cleared.

CR4.PSE should be set explicitly, regardless of whether or not it was
set before.

CR4.PGE is set explicitly, and then cleared and set again after
programming CR3 in order to flush TLB entries based on global
translations. This makes the first assignment redundant, and can
therefore be omitted.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/x86/kernel/head_64.S | 24 +++++++-------------
 1 file changed, 8 insertions(+), 16 deletions(-)
  

Comments

Brian Gerst Feb. 21, 2024, 2:52 p.m. UTC | #1
On Wed, Feb 21, 2024 at 6:35 AM Ard Biesheuvel <ardb+git@google.com> wrote:
>
> From: Ard Biesheuvel <ardb@kernel.org>
>
> When paging is enabled, the CR4.PAE and CR4.LA57 control bits cannot be
> changed, and so they can simply be preserved rather than reason about
> whether or not they need to be set. CR4.MCE should be preserved unless
> the kernel was built without CONFIG_X86_MCE, in which case it must be
> cleared.
>
> CR4.PSE should be set explicitly, regardless of whether or not it was
> set before.
>
> CR4.PGE is set explicitly, and then cleared and set again after
> programming CR3 in order to flush TLB entries based on global
> translations. This makes the first assignment redundant, and can
> therefore be omitted.
>
> Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
> ---
>  arch/x86/kernel/head_64.S | 24 +++++++-------------
>  1 file changed, 8 insertions(+), 16 deletions(-)
>
> diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
> index fb2a98c29094..426f6fdc0075 100644
> --- a/arch/x86/kernel/head_64.S
> +++ b/arch/x86/kernel/head_64.S
> @@ -185,6 +185,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
>         addq    $(init_top_pgt - __START_KERNEL_map), %rax
>  1:
>
> +       /* Create a mask of CR4 bits to preserve */
> +       movl    $(X86_CR4_PAE | X86_CR4_LA57), %edx
>  #ifdef CONFIG_X86_MCE
>         /*
>          * Preserve CR4.MCE if the kernel will enable #MC support.
> @@ -193,20 +195,13 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
>          * configured will crash the system regardless of the CR4.MCE value set
>          * here.
>          */
> -       movq    %cr4, %rcx
> -       andl    $X86_CR4_MCE, %ecx
> -#else
> -       movl    $0, %ecx
> +       orl     $X86_CR4_MCE, %edx
>  #endif
> +       movq    %cr4, %rcx
> +       andl    %edx, %ecx
>
> -       /* Enable PAE mode, PSE, PGE and LA57 */
> -       orl     $(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
> -#ifdef CONFIG_X86_5LEVEL
> -       testb   $1, __pgtable_l5_enabled(%rip)
> -       jz      1f
> -       orl     $X86_CR4_LA57, %ecx
> -1:
> -#endif
> +       /* Even if ignored in long mode, set PSE uniformly on all logical CPUs. */
> +       btsl    $X86_CR4_PSE_BIT, %ecx
>         movq    %rcx, %cr4

This CR4 write now does the global flush - see below.

>
>         /* Setup early boot stage 4-/5-level pagetables. */
> @@ -226,11 +221,8 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
>          * Do a global TLB flush after the CR3 switch to make sure the TLB
>          * entries from the identity mapping are flushed.
>          */

This comment is misleading now since it's the first CR4 write above
(with PGE clear) that actually does the global flush.

> -       movq    %cr4, %rcx
> -       movq    %rcx, %rax
> -       xorq    $X86_CR4_PGE, %rcx
> +       btsl    $X86_CR4_PGE_BIT, %ecx
>         movq    %rcx, %cr4
> -       movq    %rax, %cr4
>
>         /* Ensure I am executing from virtual addresses */
>         movq    $1f, %rax
> --
> 2.44.0.rc0.258.g7320e95886-goog
>

Brian Gerst
  

Patch

diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index fb2a98c29094..426f6fdc0075 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -185,6 +185,8 @@  SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	addq	$(init_top_pgt - __START_KERNEL_map), %rax
 1:
 
+	/* Create a mask of CR4 bits to preserve */
+	movl	$(X86_CR4_PAE | X86_CR4_LA57), %edx
 #ifdef CONFIG_X86_MCE
 	/*
 	 * Preserve CR4.MCE if the kernel will enable #MC support.
@@ -193,20 +195,13 @@  SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	 * configured will crash the system regardless of the CR4.MCE value set
 	 * here.
 	 */
-	movq	%cr4, %rcx
-	andl	$X86_CR4_MCE, %ecx
-#else
-	movl	$0, %ecx
+	orl	$X86_CR4_MCE, %edx
 #endif
+	movq	%cr4, %rcx
+	andl	%edx, %ecx
 
-	/* Enable PAE mode, PSE, PGE and LA57 */
-	orl	$(X86_CR4_PAE | X86_CR4_PSE | X86_CR4_PGE), %ecx
-#ifdef CONFIG_X86_5LEVEL
-	testb	$1, __pgtable_l5_enabled(%rip)
-	jz	1f
-	orl	$X86_CR4_LA57, %ecx
-1:
-#endif
+	/* Even if ignored in long mode, set PSE uniformly on all logical CPUs. */
+	btsl	$X86_CR4_PSE_BIT, %ecx
 	movq	%rcx, %cr4
 
 	/* Setup early boot stage 4-/5-level pagetables. */
@@ -226,11 +221,8 @@  SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	 * Do a global TLB flush after the CR3 switch to make sure the TLB
 	 * entries from the identity mapping are flushed.
 	 */
-	movq	%cr4, %rcx
-	movq	%rcx, %rax
-	xorq	$X86_CR4_PGE, %rcx
+	btsl	$X86_CR4_PGE_BIT, %ecx
 	movq	%rcx, %cr4
-	movq	%rax, %cr4
 
 	/* Ensure I am executing from virtual addresses */
 	movq	$1f, %rax