On Tue, 2024-05-28 at 12:55 +0300, Kirill A. Shutemov wrote:
> TDX guests run with MCA enabled (CR4.MCE=1b) from the very start. If
> that bit is cleared during CR4 register reprogramming during boot or
> kexec flows, a #VE exception will be raised which the guest kernel
> cannot handle it.
Nit: the ending "it" isn't needed.
>
> Therefore, make sure the CR4.MCE setting is preserved over kexec too and
> avoid raising any #VEs.
>
> The change doesn't affect non-TDX-guest environments.
>
> Signed-off-by: Kirill A. Shutemov <[email protected]>
Reviewed-by: Kai Huang <[email protected]>
> ---
> arch/x86/kernel/relocate_kernel_64.S | 16 ++++++++++------
> 1 file changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
> index 085eef5c3904..b668a6be4f6f 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>
> @@ -143,15 +145,17 @@ 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 be allowed in TDX guests, depending on setup.
> + * - physical address extension enabled
> */
> - movl $X86_CR4_PAE, %eax
> - testq $X86_CR4_LA57, %r13
> - jz .Lno_la57
> - orl $X86_CR4_LA57, %eax
> -.Lno_la57:
> + movl $X86_CR4_LA57, %eax
> + ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %eax), X86_FEATURE_TDX_GUEST
>
> + /* R13 contains the original CR4 value, read in relocate_kernel() */
> + andl %r13d, %eax
> + orl $X86_CR4_PAE, %eax
> movq %rax, %cr4
>
> jmp 1f