x86/boot: Set CR0.NE early and keep it set during the boot

TDX guest requires CR0.NE to be set. Clearing the bit triggers #GP(0).

If CR0.NE is 0, the MS-DOS compatibility mode for handling floating-point
exceptions is selected. In this mode, the software exception handler for
floating-point exceptions is invoked externally using the processor’s
FERR#, INTR, and IGNNE# pins.

Using FERR# and IGNNE# to handle floating-point exception is deprecated.
CR0.NE=0 also limits newer processors to operate with one logical
processor active.

Kernel uses CR0_STATE constant to initialize CR0. It has NE bit set.
But during early boot kernel has more ad-hoc approach to setting bit
in the register. During some of this ad-hoc manipulation, CR0.NE is
cleared. This causes a #GP in TDX guests and makes it die in early boot.

Make CR0 initialization consistent, deriving the initial value of CR0
from CR0_STATE. Since CR0_STATE always has CR0.NE=1, this ensures that
CR0.NE is never 0 and avoids the #GP.

Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20220405232939.73860-23-kirill.shutemov@linux.intel.com

arch/x86/boot/compressed/head_64.S

@@ -289,7 +289,7 @@ SYM_FUNC_START(startup_32)
 	pushl	%eax
 
 	/* Enter paged protected Mode, activating Long Mode */
-	movl	$(X86_CR0_PG | X86_CR0_PE), %eax /* Enable Paging and Protected mode */
+	movl	$CR0_STATE, %eax
 	movl	%eax, %cr0
 
 	/* Jump from 32bit compatibility mode into 64bit mode. */
@@ -661,8 +661,9 @@ SYM_CODE_START(trampoline_32bit_src)
 	pushl	$__KERNEL_CS
 	pushl	%eax
 
-	/* Enable paging again */
-	movl	$(X86_CR0_PG | X86_CR0_PE), %eax
+	/* Enable paging again. */
+	movl	%cr0, %eax
+	btsl	$X86_CR0_PG_BIT, %eax
 	movl	%eax, %cr0
 
 	lret

arch/x86/realmode/rm/trampoline_64.S

@@ -70,7 +70,7 @@ SYM_CODE_START(trampoline_start)
 	movw	$__KERNEL_DS, %dx	# Data segment descriptor
 
 	# Enable protected mode
-	movl	$X86_CR0_PE, %eax	# protected mode (PE) bit
+	movl	$(CR0_STATE & ~X86_CR0_PG), %eax
 	movl	%eax, %cr0		# into protected mode
 
 	# flush prefetch and jump to startup_32
@@ -148,8 +148,8 @@ SYM_CODE_START(startup_32)
 	movl	$MSR_EFER, %ecx
 	wrmsr
 
-	# Enable paging and in turn activate Long Mode
-	movl	$(X86_CR0_PG | X86_CR0_WP | X86_CR0_PE), %eax
+	# Enable paging and in turn activate Long Mode.
+	movl	$CR0_STATE, %eax
 	movl	%eax, %cr0
 
 	/*
@@ -169,7 +169,7 @@ SYM_CODE_START(pa_trampoline_compat)
 	movl	$rm_stack_end, %esp
 	movw	$__KERNEL_DS, %dx
 
-	movl	$X86_CR0_PE, %eax
+	movl	$(CR0_STATE & ~X86_CR0_PG), %eax
 	movl	%eax, %cr0
 	ljmpl   $__KERNEL32_CS, $pa_startup_32
 SYM_CODE_END(pa_trampoline_compat)