x86/boot: Avoid #VE during boot for TDX platforms

There are a few MSRs and control register bits that the kernel
normally needs to modify during boot. But, TDX disallows
modification of these registers to help provide consistent security
guarantees. Fortunately, TDX ensures that these are all in the correct
state before the kernel loads, which means the kernel does not need to
modify them.

The conditions to avoid are:

 * Any writes to the EFER MSR
 * Clearing CR4.MCE

This theoretically makes the guest boot more fragile. If, for instance,
EFER was set up incorrectly and a WRMSR was performed, it will trigger
early exception panic or a triple fault, if it's before early
exceptions are set up. However, this is likely to trip up the guest
BIOS long before control reaches the kernel. In any case, these kinds
of problems are unlikely to occur in production environments, and
developers have good debug tools to fix them quickly.

Change the common boot code to work on TDX and non-TDX systems.
This should have no functional effect on non-TDX systems.

Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20220405232939.73860-24-kirill.shutemov@linux.intel.com

arch/x86/Kconfig

@@ -884,6 +884,7 @@ config INTEL_TDX_GUEST
 	depends on X86_X2APIC
 	select ARCH_HAS_CC_PLATFORM
 	select DYNAMIC_PHYSICAL_MASK
+	select X86_MCE
 	help
 	  Support running as a guest under Intel TDX.  Without this support,
 	  the guest kernel can not boot or run under TDX.

arch/x86/boot/compressed/head_64.S

@@ -642,12 +642,28 @@ SYM_CODE_START(trampoline_32bit_src)
 	movl	$MSR_EFER, %ecx
 	rdmsr
 	btsl	$_EFER_LME, %eax
+	/* Avoid writing EFER if no change was made (for TDX guest) */
+	jc	1f
 	wrmsr
-	popl	%edx
+1:	popl	%edx
 	popl	%ecx
 
+#ifdef CONFIG_X86_MCE
+	/*
+	 * Preserve CR4.MCE if the kernel will enable #MC support.
+	 * Clearing MCE may fault in some environments (that also force #MC
+	 * support). Any machine check that occurs before #MC support is fully
+	 * configured will crash the system regardless of the CR4.MCE value set
+	 * here.
+	 */
+	movl	%cr4, %eax
+	andl	$X86_CR4_MCE, %eax
+#else
+	movl	$0, %eax
+#endif
+
 	/* Enable PAE and LA57 (if required) paging modes */
-	movl	$X86_CR4_PAE, %eax
+	orl	$X86_CR4_PAE, %eax
 	testl	%edx, %edx
 	jz	1f
 	orl	$X86_CR4_LA57, %eax

arch/x86/boot/compressed/pgtable.h

@@ -6,7 +6,7 @@
 #define TRAMPOLINE_32BIT_PGTABLE_OFFSET	0
 
 #define TRAMPOLINE_32BIT_CODE_OFFSET	PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE	0x70
+#define TRAMPOLINE_32BIT_CODE_SIZE	0x80
 
 #define TRAMPOLINE_32BIT_STACK_END	TRAMPOLINE_32BIT_SIZE
 

arch/x86/kernel/head_64.S

@@ -142,8 +142,22 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	addq	$(init_top_pgt - __START_KERNEL_map), %rax
 1:
 
+#ifdef CONFIG_X86_MCE
+	/*
+	 * Preserve CR4.MCE if the kernel will enable #MC support.
+	 * Clearing MCE may fault in some environments (that also force #MC
+	 * support). Any machine check that occurs before #MC support is fully
+	 * 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
+#endif
+
 	/* Enable PAE mode, PGE and LA57 */
-	movl	$(X86_CR4_PAE | X86_CR4_PGE), %ecx
+	orl	$(X86_CR4_PAE | X86_CR4_PGE), %ecx
 #ifdef CONFIG_X86_5LEVEL
 	testl	$1, __pgtable_l5_enabled(%rip)
 	jz	1f
@@ -249,13 +263,23 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	/* Setup EFER (Extended Feature Enable Register) */
 	movl	$MSR_EFER, %ecx
 	rdmsr
+	/*
+	 * Preserve current value of EFER for comparison and to skip
+	 * EFER writes if no change was made (for TDX guest)
+	 */
+	movl    %eax, %edx
 	btsl	$_EFER_SCE, %eax	/* Enable System Call */
 	btl	$20,%edi		/* No Execute supported? */
 	jnc     1f
 	btsl	$_EFER_NX, %eax
 	btsq	$_PAGE_BIT_NX,early_pmd_flags(%rip)
-1:	wrmsr				/* Make changes effective */
 
+	/* Avoid writing EFER if no change was made (for TDX guest) */
+1:	cmpl	%edx, %eax
+	je	1f
+	xor	%edx, %edx
+	wrmsr				/* Make changes effective */
+1:
 	/* Setup cr0 */
 	movl	$CR0_STATE, %eax
 	/* Make changes effective */

arch/x86/realmode/rm/trampoline_64.S

@@ -143,11 +143,22 @@ SYM_CODE_START(startup_32)
 	movl	%eax, %cr3
 
 	# Set up EFER
+	movl	$MSR_EFER, %ecx
+	rdmsr
+	/*
+	 * Skip writing to EFER if the register already has desired
+	 * value (to avoid #VE for the TDX guest).
+	 */
+	cmp	pa_tr_efer, %eax
+	jne	.Lwrite_efer
+	cmp	pa_tr_efer + 4, %edx
+	je	.Ldone_efer
+.Lwrite_efer:
 	movl	pa_tr_efer, %eax
 	movl	pa_tr_efer + 4, %edx
-	movl	$MSR_EFER, %ecx
 	wrmsr
 
+.Ldone_efer:
 	# Enable paging and in turn activate Long Mode.
 	movl	$CR0_STATE, %eax
 	movl	%eax, %cr0