x86/smpboot: Remove initial_gs

Given its CPU#, each CPU can find its own per-cpu offset, and directly set
GSBASE accordingly. The global variable can be eliminated.
Signed-off-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Signed-off-by: Usama Arif <usama.arif@bytedance.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Usama Arif <usama.arif@bytedance.com>
Tested-by: Guilherme G. Piccoli <gpiccoli@igalia.com>
Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>
Link: https://lore.kernel.org/r/20230316222109.1940300-9-usama.arif@bytedance.com

arch/x86/include/asm/realmode.h

@@ -59,7 +59,6 @@ extern struct real_mode_header *real_mode_header;
 extern unsigned char real_mode_blob_end[];
 
 extern unsigned long initial_code;
-extern unsigned long initial_gs;
 extern unsigned long initial_stack;
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 extern unsigned long initial_vc_handler;

arch/x86/kernel/acpi/sleep.c

@@ -127,7 +127,6 @@ int x86_acpi_suspend_lowlevel(void)
 	 * value is in the actual %rsp register.
 	 */
 	current->thread.sp = (unsigned long)temp_stack + sizeof(temp_stack);
-	initial_gs = per_cpu_offset(smp_processor_id());
 	smpboot_control = smp_processor_id();
 #endif
 	initial_code = (unsigned long)wakeup_long64;

arch/x86/kernel/head_64.S

@@ -66,18 +66,10 @@ SYM_CODE_START_NOALIGN(startup_64)
 
 	leaq	_text(%rip), %rdi
 
-	/*
-	 * initial_gs points to initial fixed_percpu_data struct with storage for
-	 * the stack protector canary. Global pointer fixups are needed at this
-	 * stage, so apply them as is done in fixup_pointer(), and initialize %gs
-	 * such that the canary can be accessed at %gs:40 for subsequent C calls.
-	 */
+	/* Setup GSBASE to allow stack canary access for C code */
 	movl	$MSR_GS_BASE, %ecx
-	movq	initial_gs(%rip), %rax
-	movq	$_text, %rdx
-	subq	%rdx, %rax
-	addq	%rdi, %rax
-	movq	%rax, %rdx
+	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
+	movl	%edx, %eax
 	shrq	$32,  %rdx
 	wrmsr
 
@@ -294,8 +286,11 @@ SYM_INNER_LABEL(secondary_startup_64_no_verify, SYM_L_GLOBAL)
 	 * the per cpu areas are set up.
 	 */
 	movl	$MSR_GS_BASE,%ecx
-	movl	initial_gs(%rip),%eax
-	movl	initial_gs+4(%rip),%edx
+#ifndef CONFIG_SMP
+	leaq	INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
+#endif
+	movl	%edx, %eax
+	shrq	$32, %rdx
 	wrmsr
 
 	/* Setup and Load IDT */
@@ -437,7 +432,6 @@ SYM_CODE_END(vc_boot_ghcb)
 	__REFDATA
 	.balign	8
 SYM_DATA(initial_code,	.quad x86_64_start_kernel)
-SYM_DATA(initial_gs,	.quad INIT_PER_CPU_VAR(fixed_percpu_data))
 #ifdef CONFIG_AMD_MEM_ENCRYPT
 SYM_DATA(initial_vc_handler,	.quad handle_vc_boot_ghcb)
 #endif

arch/x86/kernel/smpboot.c

@@ -1059,8 +1059,6 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
 #ifdef CONFIG_X86_32
 	/* Stack for startup_32 can be just as for start_secondary onwards */
 	per_cpu(pcpu_hot.top_of_stack, cpu) = task_top_of_stack(idle);
-#else
-	initial_gs = per_cpu_offset(cpu);
 #endif
 	return 0;
 }