x86/trampoline: Bypass compat mode in trampoline_start64() if not needed

The trampoline_start64() vector is used when a secondary CPU starts in
64-bit mode. The current implementation directly enters compatibility
mode. It is necessary to disable paging and re-enable it in the correct
paging mode: either 4- or 5-level, depending on the configuration.

The X86S[1] ISA does not support compatibility mode in ring 0, and
paging cannot be disabled.

Rework the trampoline_start64() function to only enter compatibility
mode if it is necessary to change the paging mode. If the CPU is
already in the desired paging mode, proceed in long mode.

This allows a secondary CPU to boot on an X86S machine as long as the
CPU is already in the correct paging mode.

In the future, there will be a mechanism to switch between paging modes
without disabling paging.

[1] https://www.intel.com/content/www/us/en/developer/articles/technical/envisioning-future-simplified-architecture.html

[ dhansen: changelog tweaks ]
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: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/all/20240126100101.689090-1-kirill.shutemov%40linux.intel.com

arch/x86/realmode/rm/trampoline_64.S

@@ -37,13 +37,15 @@
 	.text
 	.code16
 
-.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0
+.macro LOCK_AND_LOAD_REALMODE_ESP lock_pa=0 lock_rip=0
 	/*
 	 * Make sure only one CPU fiddles with the realmode stack
 	 */
 .Llock_rm\@:
 	.if \lock_pa
         lock btsl       $0, pa_tr_lock
+	.elseif \lock_rip
+        lock btsl       $0, tr_lock(%rip)
 	.else
         lock btsl       $0, tr_lock
 	.endif
@@ -220,6 +222,35 @@ SYM_CODE_START(trampoline_start64)
 	lidt	tr_idt(%rip)
 	lgdt	tr_gdt64(%rip)
 
+	/* Check if paging mode has to be changed */
+	movq	%cr4, %rax
+	xorl	tr_cr4(%rip), %eax
+	testl	$X86_CR4_LA57, %eax
+	jnz	.L_switch_paging
+
+	/* Paging mode is correct proceed in 64-bit mode */
+
+	LOCK_AND_LOAD_REALMODE_ESP lock_rip=1
+
+	movw	$__KERNEL_DS, %dx
+	movl	%edx, %ss
+	addl	$pa_real_mode_base, %esp
+	movl	%edx, %ds
+	movl	%edx, %es
+	movl	%edx, %fs
+	movl	%edx, %gs
+
+	movl	$pa_trampoline_pgd, %eax
+	movq	%rax, %cr3
+
+	pushq	$__KERNEL_CS
+	pushq	tr_start(%rip)
+	lretq
+.L_switch_paging:
+	/*
+	 * To switch between 4- and 5-level paging modes, it is necessary
+	 * to disable paging. This must be done in the compatibility mode.
+	 */
 	ljmpl	*tr_compat(%rip)
 SYM_CODE_END(trampoline_start64)