Merge branch 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu

* 'for-2.6.38' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/percpu: (30 commits)
  gameport: use this_cpu_read instead of lookup
  x86: udelay: Use this_cpu_read to avoid address calculation
  x86: Use this_cpu_inc_return for nmi counter
  x86: Replace uses of current_cpu_data with this_cpu ops
  x86: Use this_cpu_ops to optimize code
  vmstat: User per cpu atomics to avoid interrupt disable / enable
  irq_work: Use per cpu atomics instead of regular atomics
  cpuops: Use cmpxchg for xchg to avoid lock semantics
  x86: this_cpu_cmpxchg and this_cpu_xchg operations
  percpu: Generic this_cpu_cmpxchg() and this_cpu_xchg support
  percpu,x86: relocate this_cpu_add_return() and friends
  connector: Use this_cpu operations
  xen: Use this_cpu_inc_return
  taskstats: Use this_cpu_ops
  random: Use this_cpu_inc_return
  fs: Use this_cpu_inc_return in buffer.c
  highmem: Use this_cpu_xx_return() operations
  vmstat: Use this_cpu_inc_return for vm statistics
  x86: Support for this_cpu_add, sub, dec, inc_return
  percpu: Generic support for this_cpu_add, sub, dec, inc_return
  ...

Fixed up conflicts: in arch/x86/kernel/{apic/nmi.c, apic/x2apic_uv_x.c, process.c}
as per Tejun.

6 files changed, 222 insertions, 22 deletions

diff --git a/include/asm-generic/irq_regs.h b/include/asm-generic/irq_regs.h
index 5ae1d07d4a1..6bf9355fa7e 100644
--- a/include/asm-generic/irq_regs.h
+++ b/include/asm-generic/irq_regs.h
@@ -22,15 +22,15 @@ DECLARE_PER_CPU(struct pt_regs *, __irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
 {
-	return __get_cpu_var(__irq_regs);
+	return __this_cpu_read(__irq_regs);
 }
 
 static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
 {
-	struct pt_regs *old_regs, **pp_regs = &__get_cpu_var(__irq_regs);
+	struct pt_regs *old_regs;
 
-	old_regs = *pp_regs;
-	*pp_regs = new_regs;
+	old_regs = __this_cpu_read(__irq_regs);
+	__this_cpu_write(__irq_regs, new_regs);
 	return old_regs;
 }
 
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index 4fd978e7eb8..4d857973d2c 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -195,15 +195,9 @@ enum {
 /*
  * io context count accounting
  */
-#define elv_ioc_count_mod(name, __val)				\
-	do {							\
-		preempt_disable();				\
-		__get_cpu_var(name) += (__val);			\
-		preempt_enable();				\
-	} while (0)
-
-#define elv_ioc_count_inc(name)	elv_ioc_count_mod(name, 1)
-#define elv_ioc_count_dec(name)	elv_ioc_count_mod(name, -1)
+#define elv_ioc_count_mod(name, __val) this_cpu_add(name, __val)
+#define elv_ioc_count_inc(name)	this_cpu_inc(name)
+#define elv_ioc_count_dec(name)	this_cpu_dec(name)
 
 #define elv_ioc_count_read(name)				\
 ({								\
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index b676c585574..3a93f73a8ac 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -81,7 +81,8 @@ DECLARE_PER_CPU(int, __kmap_atomic_idx);
 
 static inline int kmap_atomic_idx_push(void)
 {
-	int idx = __get_cpu_var(__kmap_atomic_idx)++;
+	int idx = __this_cpu_inc_return(__kmap_atomic_idx) - 1;
+
 #ifdef CONFIG_DEBUG_HIGHMEM
 	WARN_ON_ONCE(in_irq() && !irqs_disabled());
 	BUG_ON(idx > KM_TYPE_NR);
@@ -91,16 +92,18 @@ static inline int kmap_atomic_idx_push(void)
 
 static inline int kmap_atomic_idx(void)
 {
-	return __get_cpu_var(__kmap_atomic_idx) - 1;
+	return __this_cpu_read(__kmap_atomic_idx) - 1;
 }
 
-static inline int kmap_atomic_idx_pop(void)
+static inline void kmap_atomic_idx_pop(void)
 {
-	int idx = --__get_cpu_var(__kmap_atomic_idx);
 #ifdef CONFIG_DEBUG_HIGHMEM
+	int idx = __this_cpu_dec_return(__kmap_atomic_idx);
+
 	BUG_ON(idx < 0);
+#else
+	__this_cpu_dec(__kmap_atomic_idx);
 #endif
-	return idx;
 }
 
 #endif
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index ad54c846911..44e83ba12b5 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -47,7 +47,7 @@ extern unsigned long long nr_context_switches(void);
 
 #ifndef CONFIG_GENERIC_HARDIRQS
 #define kstat_irqs_this_cpu(irq) \
-	(kstat_this_cpu.irqs[irq])
+	(this_cpu_read(kstat.irqs[irq])
 
 struct irq_desc;
 
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index b78edb58ee6..dd7c12e875b 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -305,12 +305,12 @@ struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk);
 /* kprobe_running() will just return the current_kprobe on this CPU */
 static inline struct kprobe *kprobe_running(void)
 {
-	return (__get_cpu_var(current_kprobe));
+	return (__this_cpu_read(current_kprobe));
 }
 
 static inline void reset_current_kprobe(void)
 {
-	__get_cpu_var(current_kprobe) = NULL;
+	__this_cpu_write(current_kprobe, NULL);
 }
 
 static inline struct kprobe_ctlblk *get_kprobe_ctlblk(void)
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 5095b834a6f..27c3c6fcfad 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -240,6 +240,21 @@ extern void __bad_size_call_parameter(void);
 	pscr_ret__;							\
 })
 
+#define __pcpu_size_call_return2(stem, variable, ...)			\
+({									\
+	typeof(variable) pscr2_ret__;					\
+	__verify_pcpu_ptr(&(variable));					\
+	switch(sizeof(variable)) {					\
+	case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break;	\
+	case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break;	\
+	case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break;	\
+	case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break;	\
+	default:							\
+		__bad_size_call_parameter(); break;			\
+	}								\
+	pscr2_ret__;							\
+})
+
 #define __pcpu_size_call(stem, variable, ...)				\
 do {									\
 	__verify_pcpu_ptr(&(variable));					\
@@ -402,6 +417,89 @@ do {									\
 # define this_cpu_xor(pcp, val)		__pcpu_size_call(this_cpu_or_, (pcp), (val))
 #endif
 
+#define _this_cpu_generic_add_return(pcp, val)				\
+({									\
+	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	__this_cpu_add(pcp, val);					\
+	ret__ = __this_cpu_read(pcp);					\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_add_return
+# ifndef this_cpu_add_return_1
+#  define this_cpu_add_return_1(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef this_cpu_add_return_2
+#  define this_cpu_add_return_2(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef this_cpu_add_return_4
+#  define this_cpu_add_return_4(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef this_cpu_add_return_8
+#  define this_cpu_add_return_8(pcp, val)	_this_cpu_generic_add_return(pcp, val)
+# endif
+# define this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
+#endif
+
+#define this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(val))
+#define this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
+#define this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
+
+#define _this_cpu_generic_xchg(pcp, nval)				\
+({	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	ret__ = __this_cpu_read(pcp);					\
+	__this_cpu_write(pcp, nval);					\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_xchg
+# ifndef this_cpu_xchg_1
+#  define this_cpu_xchg_1(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef this_cpu_xchg_2
+#  define this_cpu_xchg_2(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef this_cpu_xchg_4
+#  define this_cpu_xchg_4(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef this_cpu_xchg_8
+#  define this_cpu_xchg_8(pcp, nval)	_this_cpu_generic_xchg(pcp, nval)
+# endif
+# define this_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(this_cpu_xchg_, (pcp), nval)
+#endif
+
+#define _this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({	typeof(pcp) ret__;						\
+	preempt_disable();						\
+	ret__ = __this_cpu_read(pcp);					\
+	if (ret__ == (oval))						\
+		__this_cpu_write(pcp, nval);				\
+	preempt_enable();						\
+	ret__;								\
+})
+
+#ifndef this_cpu_cmpxchg
+# ifndef this_cpu_cmpxchg_1
+#  define this_cpu_cmpxchg_1(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef this_cpu_cmpxchg_2
+#  define this_cpu_cmpxchg_2(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef this_cpu_cmpxchg_4
+#  define this_cpu_cmpxchg_4(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef this_cpu_cmpxchg_8
+#  define this_cpu_cmpxchg_8(pcp, oval, nval)	_this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# define this_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
+#endif
+
 /*
  * Generic percpu operations that do not require preemption handling.
  * Either we do not care about races or the caller has the
@@ -529,11 +627,87 @@ do {									\
 # define __this_cpu_xor(pcp, val)	__pcpu_size_call(__this_cpu_xor_, (pcp), (val))
 #endif
 
+#define __this_cpu_generic_add_return(pcp, val)				\
+({									\
+	__this_cpu_add(pcp, val);					\
+	__this_cpu_read(pcp);						\
+})
+
+#ifndef __this_cpu_add_return
+# ifndef __this_cpu_add_return_1
+#  define __this_cpu_add_return_1(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef __this_cpu_add_return_2
+#  define __this_cpu_add_return_2(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef __this_cpu_add_return_4
+#  define __this_cpu_add_return_4(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# endif
+# ifndef __this_cpu_add_return_8
+#  define __this_cpu_add_return_8(pcp, val)	__this_cpu_generic_add_return(pcp, val)
+# endif
+# define __this_cpu_add_return(pcp, val)	__pcpu_size_call_return2(this_cpu_add_return_, pcp, val)
+#endif
+
+#define __this_cpu_sub_return(pcp, val)	this_cpu_add_return(pcp, -(val))
+#define __this_cpu_inc_return(pcp)	this_cpu_add_return(pcp, 1)
+#define __this_cpu_dec_return(pcp)	this_cpu_add_return(pcp, -1)
+
+#define __this_cpu_generic_xchg(pcp, nval)				\
+({	typeof(pcp) ret__;						\
+	ret__ = __this_cpu_read(pcp);					\
+	__this_cpu_write(pcp, nval);					\
+	ret__;								\
+})
+
+#ifndef __this_cpu_xchg
+# ifndef __this_cpu_xchg_1
+#  define __this_cpu_xchg_1(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef __this_cpu_xchg_2
+#  define __this_cpu_xchg_2(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef __this_cpu_xchg_4
+#  define __this_cpu_xchg_4(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# ifndef __this_cpu_xchg_8
+#  define __this_cpu_xchg_8(pcp, nval)	__this_cpu_generic_xchg(pcp, nval)
+# endif
+# define __this_cpu_xchg(pcp, nval)	\
+	__pcpu_size_call_return2(__this_cpu_xchg_, (pcp), nval)
+#endif
+
+#define __this_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) ret__;						\
+	ret__ = __this_cpu_read(pcp);					\
+	if (ret__ == (oval))						\
+		__this_cpu_write(pcp, nval);				\
+	ret__;								\
+})
+
+#ifndef __this_cpu_cmpxchg
+# ifndef __this_cpu_cmpxchg_1
+#  define __this_cpu_cmpxchg_1(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef __this_cpu_cmpxchg_2
+#  define __this_cpu_cmpxchg_2(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef __this_cpu_cmpxchg_4
+#  define __this_cpu_cmpxchg_4(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef __this_cpu_cmpxchg_8
+#  define __this_cpu_cmpxchg_8(pcp, oval, nval)	__this_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# define __this_cpu_cmpxchg(pcp, oval, nval)	\
+	__pcpu_size_call_return2(__this_cpu_cmpxchg_, pcp, oval, nval)
+#endif
+
 /*
  * IRQ safe versions of the per cpu RMW operations. Note that these operations
  * are *not* safe against modification of the same variable from another
  * processors (which one gets when using regular atomic operations)
- . They are guaranteed to be atomic vs. local interrupts and
+ * They are guaranteed to be atomic vs. local interrupts and
  * preemption only.
  */
 #define irqsafe_cpu_generic_to_op(pcp, val, op)				\
@@ -620,4 +794,33 @@ do {									\
 # define irqsafe_cpu_xor(pcp, val) __pcpu_size_call(irqsafe_cpu_xor_, (val))
 #endif
 
+#define irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)			\
+({									\
+	typeof(pcp) ret__;						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
+	ret__ = __this_cpu_read(pcp);					\
+	if (ret__ == (oval))						\
+		__this_cpu_write(pcp, nval);				\
+	local_irq_restore(flags);					\
+	ret__;								\
+})
+
+#ifndef irqsafe_cpu_cmpxchg
+# ifndef irqsafe_cpu_cmpxchg_1
+#  define irqsafe_cpu_cmpxchg_1(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_2
+#  define irqsafe_cpu_cmpxchg_2(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_4
+#  define irqsafe_cpu_cmpxchg_4(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# ifndef irqsafe_cpu_cmpxchg_8
+#  define irqsafe_cpu_cmpxchg_8(pcp, oval, nval)	irqsafe_cpu_generic_cmpxchg(pcp, oval, nval)
+# endif
+# define irqsafe_cpu_cmpxchg(pcp, oval, nval)		\
+	__pcpu_size_call_return2(irqsafe_cpu_cmpxchg_, (pcp), oval, nval)
+#endif
+
 #endif /* __LINUX_PERCPU_H */