x86/startup_64: Simplify virtual switch on primary boot

The secondary startup code is used on the primary boot path as well, but
in this case, the initial part runs from a 1:1 mapping, until an
explicit cross-jump is made to the kernel virtual mapping of the same
code.

On the secondary boot path, this jump is pointless as the code already
executes from the mapping targeted by the jump. So combine this
cross-jump with the jump from startup_64() into the common boot path.
This simplifies the execution flow, and clearly separates code that runs
from a 1:1 mapping from code that runs from the kernel virtual mapping.

Note that this requires a page table switch, so hoist the CR3 assignment
into startup_64() as well. And since absolute symbol references will no
longer be permitted in .head.text once we enable the associated build
time checks, a RIP-relative memory operand is used in the JMP
instruction, referring to an absolute constant in the .init.rodata
section.

Given that the secondary startup code does not require a special
placement inside the executable, move it to the .text section.
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Tom Lendacky <thomas.lendacky@amd.com>
Link: https://lore.kernel.org/r/20240227151907.387873-15-ardb+git@google.com

arch/x86/kernel/head_64.S

@@ -39,7 +39,6 @@ L4_START_KERNEL = l4_index(__START_KERNEL_map)
 
 L3_START_KERNEL = pud_index(__START_KERNEL_map)
 
-	.text
 	__HEAD
 	.code64
 SYM_CODE_START_NOALIGN(startup_64)
@@ -126,9 +125,21 @@ SYM_CODE_START_NOALIGN(startup_64)
 	call	sev_verify_cbit
 #endif
 
-	jmp 1f
+	/*
+	 * Switch to early_top_pgt which still has the identity mappings
+	 * present.
+	 */
+	movq	%rax, %cr3
+
+	/* Branch to the common startup code at its kernel virtual address */
+	ANNOTATE_RETPOLINE_SAFE
+	jmp	*0f(%rip)
 SYM_CODE_END(startup_64)
 
+	__INITRODATA
+0:	.quad	common_startup_64
+
+	.text
 SYM_CODE_START(secondary_startup_64)
 	UNWIND_HINT_END_OF_STACK
 	ANNOTATE_NOENDBR
@@ -174,8 +185,15 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 	addq	sme_me_mask(%rip), %rax
 #endif
+	/*
+	 * Switch to the init_top_pgt here, away from the trampoline_pgd and
+	 * unmap the identity mapped ranges.
+	 */
+	movq	%rax, %cr3
 
-1:
+SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
+	UNWIND_HINT_END_OF_STACK
+	ANNOTATE_NOENDBR
 
 	/*
 	 * Create a mask of CR4 bits to preserve. Omit PGE in order to flush
@@ -204,30 +222,12 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	btsl	$X86_CR4_PSE_BIT, %ecx
 	movq	%rcx, %cr4
 
-	/*
-	 * Switch to new page-table
-	 *
-	 * For the boot CPU this switches to early_top_pgt which still has the
-	 * identity mappings present. The secondary CPUs will switch to the
-	 * init_top_pgt here, away from the trampoline_pgd and unmap the
-	 * identity mapped ranges.
-	 */
-	movq	%rax, %cr3
-
 	/*
 	 * Set CR4.PGE to re-enable global translations.
 	 */
 	btsl	$X86_CR4_PGE_BIT, %ecx
 	movq	%rcx, %cr4
 
-	/* Ensure I am executing from virtual addresses */
-	movq	$1f, %rax
-	ANNOTATE_RETPOLINE_SAFE
-	jmp	*%rax
-1:
-	UNWIND_HINT_END_OF_STACK
-	ANNOTATE_NOENDBR // above
-
 #ifdef CONFIG_SMP
 	/*
 	 * For parallel boot, the APIC ID is read from the APIC, and then