x86: make pda a percpu variable

[ Based on original patch from Christoph Lameter and Mike Travis. ]

As pda is now allocated in percpu area, it can easily be made a proper
percpu variable.  Make it so by defining per cpu symbol from linker
script and declaring it in C code for SMP and simply defining it for
UP.  This change cleans up code and brings SMP and UP closer a bit.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

5 files changed, 20 insertions, 18 deletions

diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 7041acdf557..c49498d4083 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -879,9 +879,6 @@ static __init int setup_disablecpuid(char *arg)
 __setup("clearcpuid=", setup_disablecpuid);
 
 #ifdef CONFIG_X86_64
-struct x8664_pda *_cpu_pda[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(_cpu_pda);
-
 struct desc_ptr idt_descr = { 256 * 16 - 1, (unsigned long) idt_table };
 
 static char boot_cpu_stack[IRQSTACKSIZE] __page_aligned_bss;
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index e99b661a97f..71b6f6ec96a 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -26,18 +26,8 @@
 #include <asm/bios_ebda.h>
 #include <asm/trampoline.h>
 
-#ifndef CONFIG_SMP
-/* boot cpu pda, referenced by head_64.S to initialize %gs on UP */
-struct x8664_pda _boot_cpu_pda;
-#endif
-
 void __init x86_64_init_pda(void)
 {
-#ifdef CONFIG_SMP
-	cpu_pda(0) = (void *)__per_cpu_load;
-#else
-	cpu_pda(0) = &_boot_cpu_pda;
-#endif
 	pda_init(0);
 }
 
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 7a995d0e9f7..c8ace880661 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -19,6 +19,7 @@
 #include <asm/msr.h>
 #include <asm/cache.h>
 #include <asm/processor-flags.h>
+#include <asm/percpu.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/asm-offsets.h>
@@ -250,7 +251,7 @@ ENTRY(secondary_startup_64)
 	 * secondary CPU,initial_gs should be set to its pda address
 	 * before the CPU runs this code.
 	 *
-	 * On UP, initial_gs points to _boot_cpu_pda and doesn't
+	 * On UP, initial_gs points to PER_CPU_VAR(__pda) and doesn't
 	 * change.
 	 */
 	movl	$MSR_GS_BASE,%ecx
@@ -284,7 +285,7 @@ ENTRY(secondary_startup_64)
 #ifdef CONFIG_SMP
 	.quad	__per_cpu_load
 #else
-	.quad	_boot_cpu_pda
+	.quad	PER_CPU_VAR(__pda)
 #endif
 	__FINITDATA
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index be1ff34db11..daeedf82c15 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -66,6 +66,16 @@ static void __init setup_node_to_cpumask_map(void);
 static inline void setup_node_to_cpumask_map(void) { }
 #endif
 
+/*
+ * Define load_pda_offset() and per-cpu __pda for x86_64.
+ * load_pda_offset() is responsible for loading the offset of pda into
+ * %gs.
+ *
+ * On SMP, pda offset also duals as percpu base address and thus it
+ * should be at the start of per-cpu area.  To achieve this, it's
+ * preallocated in vmlinux_64.lds.S directly instead of using
+ * DEFINE_PER_CPU().
+ */
 #ifdef CONFIG_X86_64
 void __cpuinit load_pda_offset(int cpu)
 {
@@ -74,6 +84,10 @@ void __cpuinit load_pda_offset(int cpu)
 	wrmsrl(MSR_GS_BASE, cpu_pda(cpu));
 	mb();
 }
+#ifndef CONFIG_SMP
+DEFINE_PER_CPU(struct x8664_pda, __pda);
+EXPORT_PER_CPU_SYMBOL(__pda);
+#endif
 
 #endif /* CONFIG_SMP && CONFIG_X86_64 */
 
@@ -180,8 +194,6 @@ void __init setup_per_cpu_areas(void)
 		memcpy(ptr, __per_cpu_load, __per_cpu_end - __per_cpu_start);
 		per_cpu_offset(cpu) = ptr - __per_cpu_start;
 #ifdef CONFIG_X86_64
-		cpu_pda(cpu) = (void *)ptr;
-
 		/*
 		 * CPU0 modified pda in the init data area, reload pda
 		 * offset for CPU0 and clear the area for others.
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 962f21f1d4d..d2a0baa87d1 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -217,10 +217,12 @@ SECTIONS
    * percpu offsets are zero-based on SMP.  PERCPU_VADDR() changes the
    * output PHDR, so the next output section - __data_nosave - should
    * switch it back to data.init.  Also, pda should be at the head of
-   * percpu area.  Preallocate it.
+   * percpu area.  Preallocate it and define the percpu offset symbol
+   * so that it can be accessed as a percpu variable.
    */
   . = ALIGN(PAGE_SIZE);
   PERCPU_VADDR_PREALLOC(0, :percpu, pda_size)
+  per_cpu____pda = __per_cpu_start;
 #else
   PERCPU(PAGE_SIZE)
 #endif