x86: use linker to offset symbols by __per_cpu_load

Impact: cleanup and bug fix

Use the linker to create symbols for certain per-cpu variables
that are offset by __per_cpu_load.  This allows the removal of
the runtime fixup of the GDT pointer, which fixes a bug with
resume reported by Jiri Slaby.
Reported-by: NJiri Slaby <jirislaby@gmail.com>
Signed-off-by: NBrian Gerst <brgerst@gmail.com>
Acked-by: NJiri Slaby <jirislaby@gmail.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

arch/x86/include/asm/percpu.h

@@ -34,6 +34,12 @@
 #define PER_CPU_VAR(var)	per_cpu__##var
 #endif	/* SMP */
 
+#ifdef CONFIG_X86_64_SMP
+#define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
+#else
+#define INIT_PER_CPU_VAR(var)  per_cpu__##var
+#endif
+
 #else /* ...!ASSEMBLY */
 
 #include <linux/stringify.h>
@@ -45,6 +51,22 @@
 #define __percpu_arg(x)		"%" #x
 #endif
 
+/*
+ * Initialized pointers to per-cpu variables needed for the boot
+ * processor need to use these macros to get the proper address
+ * offset from __per_cpu_load on SMP.
+ *
+ * There also must be an entry in vmlinux_64.lds.S
+ */
+#define DECLARE_INIT_PER_CPU(var) \
+       extern typeof(per_cpu_var(var)) init_per_cpu_var(var)
+
+#ifdef CONFIG_X86_64_SMP
+#define init_per_cpu_var(var)  init_per_cpu__##var
+#else
+#define init_per_cpu_var(var)  per_cpu_var(var)
+#endif
+
 /* For arch-specific code, we can use direct single-insn ops (they
  * don't give an lvalue though). */
 extern void __bad_percpu_size(void);

arch/x86/include/asm/processor.h

@@ -393,6 +393,8 @@ union irq_stack_union {
 };
 
 DECLARE_PER_CPU(union irq_stack_union, irq_stack_union);
+DECLARE_INIT_PER_CPU(irq_stack_union);
+
 DECLARE_PER_CPU(char *, irq_stack_ptr);
 #endif
 

arch/x86/kernel/cpu/common.c

@@ -902,12 +902,8 @@ struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 
 DEFINE_PER_CPU_FIRST(union irq_stack_union,
 		     irq_stack_union) __aligned(PAGE_SIZE);
-#ifdef CONFIG_SMP
-DEFINE_PER_CPU(char *, irq_stack_ptr);	/* will be set during per cpu init */
-#else
 DEFINE_PER_CPU(char *, irq_stack_ptr) =
-	per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
-#endif
+	init_per_cpu_var(irq_stack_union.irq_stack) + IRQ_STACK_SIZE - 64;
 
 DEFINE_PER_CPU(unsigned long, kernel_stack) =
 	(unsigned long)&init_thread_union - KERNEL_STACK_OFFSET + THREAD_SIZE;

arch/x86/kernel/head_64.S

@@ -205,19 +205,6 @@ ENTRY(secondary_startup_64)
 	pushq $0
 	popfq
 
-#ifdef CONFIG_SMP
-	/*
-	 * Fix up static pointers that need __per_cpu_load added.  The assembler
-	 * is unable to do this directly.  This is only needed for the boot cpu.
-	 * These values are set up with the correct base addresses by C code for
-	 * secondary cpus.
-	 */
-	movq	initial_gs(%rip), %rax
-	cmpl	$0, per_cpu__cpu_number(%rax)
-	jne	1f
-	addq	%rax, early_gdt_descr_base(%rip)
-1:
-#endif
 	/*
 	 * We must switch to a new descriptor in kernel space for the GDT
 	 * because soon the kernel won't have access anymore to the userspace
@@ -275,11 +262,7 @@ ENTRY(secondary_startup_64)
 	ENTRY(initial_code)
 	.quad	x86_64_start_kernel
 	ENTRY(initial_gs)
-#ifdef CONFIG_SMP
-	.quad	__per_cpu_load
-#else
-	.quad	PER_CPU_VAR(irq_stack_union)
-#endif
+	.quad	INIT_PER_CPU_VAR(irq_stack_union)
 	__FINITDATA
 
 	ENTRY(stack_start)
@@ -425,7 +408,7 @@ NEXT_PAGE(level2_spare_pgt)
 early_gdt_descr:
 	.word	GDT_ENTRIES*8-1
 early_gdt_descr_base:
-	.quad	per_cpu__gdt_page
+	.quad	INIT_PER_CPU_VAR(gdt_page)
 
 ENTRY(phys_base)
 	/* This must match the first entry in level2_kernel_pgt */

arch/x86/kernel/vmlinux_64.lds.S

@@ -257,6 +257,14 @@ SECTIONS
   DWARF_DEBUG
 }
 
+ /*
+  * Per-cpu symbols which need to be offset from __per_cpu_load
+  * for the boot processor.
+  */
+#define INIT_PER_CPU(x) init_per_cpu__##x = per_cpu__##x + __per_cpu_load
+INIT_PER_CPU(gdt_page);
+INIT_PER_CPU(irq_stack_union);
+
 /*
  * Build-time check on the image size:
  */