x86: merge 64 and 32 SMP percpu handling

Now that pda is allocated as part of percpu, percpu doesn't need to be
accessed through pda.  Unify x86_64 SMP percpu access with x86_32 SMP
one.  Other than the segment register, operand size and the base of
percpu symbols, they behave identical now.

This patch replaces now unnecessary pda->data_offset with a dummy
field which is necessary to keep stack_canary at its place.  This
patch also moves per_cpu_offset initialization out of init_gdt() into
setup_per_cpu_areas().  Note that this change also necessitates
explicit per_cpu_offset initializations in voyager_smp.c.

With this change, x86_OP_percpu()'s are as efficient on x86_64 as on
x86_32 and also x86_64 can use assembly PER_CPU macros.

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

5 files changed, 13 insertions, 15 deletions

diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index f8d1b04..f4cc81b 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -55,7 +55,6 @@ int main(void)
 	ENTRY(irqcount);
 	ENTRY(cpunumber);
 	ENTRY(irqstackptr);
-	ENTRY(data_offset);
 	DEFINE(pda_size, sizeof(struct x8664_pda));
 	BLANK();
 #undef ENTRY
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index e28c7a9..4833f3a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -52,6 +52,7 @@
 #include <asm/irqflags.h>
 #include <asm/paravirt.h>
 #include <asm/ftrace.h>
+#include <asm/percpu.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
 #include <linux/elf-em.h>
@@ -1072,10 +1073,10 @@ ENTRY(\sym)
 	TRACE_IRQS_OFF
 	movq %rsp,%rdi		/* pt_regs pointer */
 	xorl %esi,%esi		/* no error code */
-	movq %gs:pda_data_offset, %rbp
-	subq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+	PER_CPU(init_tss, %rbp)
+	subq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
 	call \do_sym
-	addq $EXCEPTION_STKSZ, per_cpu__init_tss + TSS_ist + (\ist - 1) * 8(%rbp)
+	addq $EXCEPTION_STKSZ, TSS_ist + (\ist - 1) * 8(%rbp)
 	jmp paranoid_exit	/* %ebx: no swapgs flag */
 	CFI_ENDPROC
 END(\sym)
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 1a31129..e99b661 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -38,8 +38,6 @@ void __init x86_64_init_pda(void)
 #else
 	cpu_pda(0) = &_boot_cpu_pda;
 #endif
-	cpu_pda(0)->data_offset =
-		(unsigned long)(__per_cpu_load - __per_cpu_start);
 	pda_init(0);
 }
 
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 63d4628..be1ff34 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -125,14 +125,14 @@ static void __init setup_per_cpu_maps(void)
 #endif
 }
 
-#ifdef CONFIG_X86_32
-/*
- * Great future not-so-futuristic plan: make i386 and x86_64 do it
- * the same way
- */
+#ifdef CONFIG_X86_64
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly = {
+	[0] = (unsigned long)__per_cpu_load,
+};
+#else
 unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
-EXPORT_SYMBOL(__per_cpu_offset);
 #endif
+EXPORT_SYMBOL(__per_cpu_offset);
 
 /*
  * Great future plan:
@@ -178,6 +178,7 @@ void __init setup_per_cpu_areas(void)
 #endif
 
 		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;
 
@@ -190,7 +191,7 @@ void __init setup_per_cpu_areas(void)
 		else
 			memset(cpu_pda(cpu), 0, sizeof(*cpu_pda(cpu)));
 #endif
-		per_cpu_offset(cpu) = ptr - __per_cpu_start;
+		per_cpu(this_cpu_off, cpu) = per_cpu_offset(cpu);
 
 		DBG("PERCPU: cpu %4d %p\n", cpu, ptr);
 	}
diff --git a/arch/x86/kernel/smpcommon.c b/arch/x86/kernel/smpcommon.c
index 397e309..84395fa 100644
--- a/arch/x86/kernel/smpcommon.c
+++ b/arch/x86/kernel/smpcommon.c
@@ -4,10 +4,10 @@
 #include <linux/module.h>
 #include <asm/smp.h>
 
-#ifdef CONFIG_X86_32
 DEFINE_PER_CPU(unsigned long, this_cpu_off);
 EXPORT_PER_CPU_SYMBOL(this_cpu_off);
 
+#ifdef CONFIG_X86_32
 /*
  * Initialize the CPU's GDT.  This is either the boot CPU doing itself
  * (still using the master per-cpu area), or a CPU doing it for a
@@ -24,7 +24,6 @@ __cpuinit void init_gdt(int cpu)
 	write_gdt_entry(get_cpu_gdt_table(cpu),
 			GDT_ENTRY_PERCPU, &gdt, DESCTYPE_S);
 
-	per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
 	per_cpu(cpu_number, cpu) = cpu;
 }
 #endif