diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index 780ba0ab94f908da84b44d71f1740d47ac2677de..90f06c25221d792dab33f662c25012b7d0c39f59 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -13,6 +13,7 @@ extern unsigned char *trampoline_base;
 
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
+extern unsigned long initial_gs;
 
 #define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 707c1f6f95faedfb7db7aed696c45c79461b0ea2..9ff67f8dc2c016e8016bd90c8c35d9f0c0359388 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -101,6 +101,7 @@ int acpi_save_state_mem(void)
 	stack_start.sp = temp_stack + sizeof(temp_stack);
 	early_gdt_descr.address =
 			(unsigned long)get_cpu_gdt_table(smp_processor_id());
+	initial_gs = (unsigned long)cpu_pda(smp_processor_id());
 #endif
 	initial_code = (unsigned long)wakeup_long64;
 	saved_magic = 0x123456789abcdef0;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index bc2900ca82c7d54b2b25718afaf78289dd8eff94..76ffba2aa66d590c8480f8f46c6e45db9f373b59 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -26,8 +26,8 @@
 #include <asm/bios_ebda.h>
 #include <asm/trampoline.h>
 
-/* boot cpu pda */
-static struct x8664_pda _boot_cpu_pda;
+/* boot cpu pda, referenced by head_64.S to initialize %gs for boot CPU */
+struct x8664_pda _boot_cpu_pda;
 
 #ifdef CONFIG_SMP
 /*
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7ee0363871e8c60f61ae14601f00b0126cd1706f..2f0ab00898836860c1cc9dd7ba448b8f552e988e 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -243,12 +243,15 @@ ENTRY(secondary_startup_64)
 	movl %eax,%fs
 	movl %eax,%gs
 
-	/* 
-	 * Setup up a dummy PDA. this is just for some early bootup code
-	 * that does in_interrupt() 
-	 */ 
+	/* Set up %gs.
+	 *
+	 * %gs should point to the pda.  For initial boot, make %gs point
+	 * to the _boot_cpu_pda in data section.  For a secondary CPU,
+	 * initial_gs should be set to its pda address before the CPU runs
+	 * this code.
+	 */
 	movl	$MSR_GS_BASE,%ecx
-	movq	$empty_zero_page,%rax
+	movq	initial_gs(%rip),%rax
 	movq    %rax,%rdx
 	shrq	$32,%rdx
 	wrmsr	
@@ -274,6 +277,8 @@ ENTRY(secondary_startup_64)
 	.align	8
 	ENTRY(initial_code)
 	.quad	x86_64_start_kernel
+	ENTRY(initial_gs)
+	.quad	_boot_cpu_pda
 	__FINITDATA
 
 	ENTRY(stack_start)
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 1a712da1dfa0ce99ac01299f766ad986548d05ef..70d846628bbfb9755a92232fffad3ea64668f133 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -854,6 +854,7 @@ static int __cpuinit do_boot_cpu(int apicid, int cpu)
 #else
 	cpu_pda(cpu)->pcurrent = c_idle.idle;
 	clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+	initial_gs = (unsigned long)cpu_pda(cpu);
 #endif
 	early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
 	initial_code = (unsigned long)start_secondary;