x86: replace percpu_xxx funcs with this_cpu_xxx

Since percpu_xxx() serial functions are duplicated with this_cpu_xxx().
Removing percpu_xxx() definition and replacing them by this_cpu_xxx()
in code. There is no function change in this patch, just preparation for
later percpu_xxx serial function removing.

On x86 machine the this_cpu_xxx() serial functions are same as
__this_cpu_xxx() without no unnecessary premmpt enable/disable.

Thanks for Stephen Rothwell, he found and fixed a i386 build error in
the patch.

Also thanks for Andrew Morton, he kept updating the patchset in Linus'
tree.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Acked-by: Christoph Lameter <cl@gentwo.org>
Acked-by: Tejun Heo <tj@kernel.org>
Acked-by: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Tejun Heo <tj@kernel.org>

12 files changed, 30 insertions, 28 deletions

diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index d6805798d6fc9..fedf32b73e65d 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -229,7 +229,7 @@ static inline void __user *arch_compat_alloc_user_space(long len)
 		sp = task_pt_regs(current)->sp;
 	} else {
 		/* -128 for the x32 ABI redzone */
-		sp = percpu_read(old_rsp) - 128;
+		sp = this_cpu_read(old_rsp) - 128;
 	}
 
 	return (void __user *)round_down(sp - len, 16);
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index 4d447b732d82d..9476c04ee6357 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -11,7 +11,7 @@ DECLARE_PER_CPU(struct task_struct *, current_task);
 
 static __always_inline struct task_struct *get_current(void)
 {
-	return percpu_read_stable(current_task);
+	return this_cpu_read_stable(current_task);
 }
 
 #define current get_current()
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index e95822d683f46..8bf1c06070d56 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -6,6 +6,7 @@
 #include <asm/mmu.h>
 
 #include <linux/smp.h>
+#include <linux/percpu.h>
 
 static inline void fill_ldt(struct desc_struct *desc, const struct user_desc *info)
 {
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
index 4fa88154e4dec..75f4c6d6a3316 100644
--- a/arch/x86/include/asm/fpu-internal.h
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -290,14 +290,14 @@ static inline int __thread_has_fpu(struct task_struct *tsk)
 static inline void __thread_clear_has_fpu(struct task_struct *tsk)
 {
 	tsk->thread.fpu.has_fpu = 0;
-	percpu_write(fpu_owner_task, NULL);
+	this_cpu_write(fpu_owner_task, NULL);
 }
 
 /* Must be paired with a 'clts' before! */
 static inline void __thread_set_has_fpu(struct task_struct *tsk)
 {
 	tsk->thread.fpu.has_fpu = 1;
-	percpu_write(fpu_owner_task, tsk);
+	this_cpu_write(fpu_owner_task, tsk);
 }
 
 /*
@@ -344,7 +344,7 @@ typedef struct { int preload; } fpu_switch_t;
  */
 static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
 {
-	return new == percpu_read_stable(fpu_owner_task) &&
+	return new == this_cpu_read_stable(fpu_owner_task) &&
 		cpu == new->thread.fpu.last_cpu;
 }
 
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index 382f75d735f36..d3895dbf4ddb5 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -35,14 +35,15 @@ DECLARE_PER_CPU_SHARED_ALIGNED(irq_cpustat_t, irq_stat);
 
 #define __ARCH_IRQ_STAT
 
-#define inc_irq_stat(member)	percpu_inc(irq_stat.member)
+#define inc_irq_stat(member)	this_cpu_inc(irq_stat.member)
 
-#define local_softirq_pending()	percpu_read(irq_stat.__softirq_pending)
+#define local_softirq_pending()	this_cpu_read(irq_stat.__softirq_pending)
 
 #define __ARCH_SET_SOFTIRQ_PENDING
 
-#define set_softirq_pending(x)	percpu_write(irq_stat.__softirq_pending, (x))
-#define or_softirq_pending(x)	percpu_or(irq_stat.__softirq_pending, (x))
+#define set_softirq_pending(x)	\
+		this_cpu_write(irq_stat.__softirq_pending, (x))
+#define or_softirq_pending(x)	this_cpu_or(irq_stat.__softirq_pending, (x))
 
 extern void ack_bad_irq(unsigned int irq);
 
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
index 77843225b7eac..d82250b1debb8 100644
--- a/arch/x86/include/asm/irq_regs.h
+++ b/arch/x86/include/asm/irq_regs.h
@@ -15,7 +15,7 @@ DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
 {
-	return percpu_read(irq_regs);
+	return this_cpu_read(irq_regs);
 }
 
 static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
@@ -23,7 +23,7 @@ static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
 	struct pt_regs *old_regs;
 
 	old_regs = get_irq_regs();
-	percpu_write(irq_regs, new_regs);
+	this_cpu_write(irq_regs, new_regs);
 
 	return old_regs;
 }
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 69021528b43c2..cdbf36776106a 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -25,8 +25,8 @@ void destroy_context(struct mm_struct *mm);
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
-	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
-		percpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
+	if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
 }
 
@@ -37,8 +37,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 
 	if (likely(prev != next)) {
 #ifdef CONFIG_SMP
-		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		percpu_write(cpu_tlbstate.active_mm, next);
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		this_cpu_write(cpu_tlbstate.active_mm, next);
 #endif
 		cpumask_set_cpu(cpu, mm_cpumask(next));
 
@@ -56,8 +56,8 @@ static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	}
 #ifdef CONFIG_SMP
 	else {
-		percpu_write(cpu_tlbstate.state, TLBSTATE_OK);
-		BUG_ON(percpu_read(cpu_tlbstate.active_mm) != next);
+		this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
+		BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
 
 		if (!cpumask_test_and_set_cpu(cpu, mm_cpumask(next))) {
 			/* We were in lazy tlb mode and leave_mm disabled
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 7a11910a63c4d..967ee3be5c0aa 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -46,7 +46,7 @@
 
 #ifdef CONFIG_SMP
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
-#define __my_cpu_offset		percpu_read(this_cpu_off)
+#define __my_cpu_offset		this_cpu_read(this_cpu_off)
 
 /*
  * Compared to the generic __my_cpu_offset version, the following
@@ -352,15 +352,15 @@ do {									\
 
 /*
  * percpu_read() makes gcc load the percpu variable every time it is
- * accessed while percpu_read_stable() allows the value to be cached.
- * percpu_read_stable() is more efficient and can be used if its value
+ * accessed while this_cpu_read_stable() allows the value to be cached.
+ * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across cpus.  The current users include
  * get_current() and get_thread_info() both of which are actually
  * per-thread variables implemented as per-cpu variables and thus
  * stable for the duration of the respective task.
  */
 #define percpu_read(var)		percpu_from_op("mov", var, "m" (var))
-#define percpu_read_stable(var)		percpu_from_op("mov", var, "p" (&(var)))
+#define this_cpu_read_stable(var)	percpu_from_op("mov", var, "p" (&(var)))
 #define percpu_write(var, val)		percpu_to_op("mov", var, val)
 #define percpu_add(var, val)		percpu_add_op(var, val)
 #define percpu_sub(var, val)		percpu_add_op(var, -(val))
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0434c400287cf..e276f6bb65244 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -188,11 +188,11 @@ extern unsigned disabled_cpus __cpuinitdata;
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-#define raw_smp_processor_id() (percpu_read(cpu_number))
+#define raw_smp_processor_id() (this_cpu_read(cpu_number))
 extern int safe_smp_processor_id(void);
 
 #elif defined(CONFIG_X86_64_SMP)
-#define raw_smp_processor_id() (percpu_read(cpu_number))
+#define raw_smp_processor_id() (this_cpu_read(cpu_number))
 
 #define stack_smp_processor_id()					\
 ({								\
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index b5d9533d2c38f..6a998598f1724 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -75,9 +75,9 @@ static __always_inline void boot_init_stack_canary(void)
 
 	current->stack_canary = canary;
 #ifdef CONFIG_X86_64
-	percpu_write(irq_stack_union.stack_canary, canary);
+	this_cpu_write(irq_stack_union.stack_canary, canary);
 #else
-	percpu_write(stack_canary.canary, canary);
+	this_cpu_write(stack_canary.canary, canary);
 #endif
 }
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index ad6df8ccd7158..f67fd89c874b7 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -222,7 +222,7 @@ DECLARE_PER_CPU(unsigned long, kernel_stack);
 static inline struct thread_info *current_thread_info(void)
 {
 	struct thread_info *ti;
-	ti = (void *)(percpu_read_stable(kernel_stack) +
+	ti = (void *)(this_cpu_read_stable(kernel_stack) +
 		      KERNEL_STACK_OFFSET - THREAD_SIZE);
 	return ti;
 }
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index c0e108e08079e..1620d23f14d7a 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -156,8 +156,8 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate);
 
 static inline void reset_lazy_tlbstate(void)
 {
-	percpu_write(cpu_tlbstate.state, 0);
-	percpu_write(cpu_tlbstate.active_mm, &init_mm);
+	this_cpu_write(cpu_tlbstate.state, 0);
+	this_cpu_write(cpu_tlbstate.active_mm, &init_mm);
 }
 
 #endif	/* SMP */