x86/kexec: Keep CR4.MCE set during kexec for TDX guest

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.

Therefore, make sure the CR4.MCE setting is preserved over kexec too and avoid
raising any #VEs.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/r/20240614095904.1345461-7-kirill.shutemov@linux.intel.com

diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index 8b8922de37659c91500d9d45d71d426f283e337f..042c9a0334e94b87d4877b6a1c4a2d139c18c21d 100644 (file)
--- 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>
@@ -145,14 +147,15 @@ 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 be allowed in TDX guests, depending on setup.
+        *
+        * Use R13 that contains the original CR4 value, read in relocate_kernel().
+        * PAE is always set in the original CR4.
         */
-       movl    $X86_CR4_PAE, %eax
-       testq   $X86_CR4_LA57, %r13
-       jz      .Lno_la57
-       orl     $X86_CR4_LA57, %eax
-.Lno_la57:
-
-       movq    %rax, %cr4
+       andl    $(X86_CR4_PAE | X86_CR4_LA57), %r13d
+       ALTERNATIVE "", __stringify(orl $X86_CR4_MCE, %r13d), X86_FEATURE_TDX_GUEST
+       movq    %r13, %cr4
 
        /* Flush the TLB (needed?) */
        movq    %r9, %cr3