percpu: Remove irqsafe_cpu_xxx variants

We simply say that regular this_cpu use must be safe regardless of
preemption and interrupt state.  That has no material change for x86
and s390 implementations of this_cpu operations.  However, arches that
do not provide their own implementation for this_cpu operations will
now get code generated that disables interrupts instead of preemption.

-tj: This is part of on-going percpu API cleanup.  For detailed
     discussion of the subject, please refer to the following thread.

     http://thread.gmane.org/gmane.linux.kernel/1222078

Signed-off-by: Christoph Lameter <cl@linux.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
LKML-Reference: <alpine.DEB.2.00.1112221154380.11787@router.home>
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a82ad4d..ca8d9bc 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2115,7 +2115,7 @@
  */
 static inline void dev_put(struct net_device *dev)
 {
-	irqsafe_cpu_dec(*dev->pcpu_refcnt);
+	this_cpu_dec(*dev->pcpu_refcnt);
 }
 
 /**
@@ -2126,7 +2126,7 @@
  */
 static inline void dev_hold(struct net_device *dev)
 {
-	irqsafe_cpu_inc(*dev->pcpu_refcnt);
+	this_cpu_inc(*dev->pcpu_refcnt);
 }
 
 /* Carrier loss detection, dial on demand. The functions netif_carrier_on
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 32cddf7..8d674a7 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -471,7 +471,7 @@
  *
  * Begin packet processing : all readers must wait the end
  * 1) Must be called with preemption disabled
- * 2) softirqs must be disabled too (or we should use irqsafe_cpu_add())
+ * 2) softirqs must be disabled too (or we should use this_cpu_add())
  * Returns :
  *  1 if no recursion on this cpu
  *  0 if recursion detected
@@ -503,7 +503,7 @@
  *
  * End packet processing : all readers can proceed
  * 1) Must be called with preemption disabled
- * 2) softirqs must be disabled too (or we should use irqsafe_cpu_add())
+ * 2) softirqs must be disabled too (or we should use this_cpu_add())
  */
 static inline void xt_write_recseq_end(unsigned int addend)
 {
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 9ca008f..32cd1f6 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -172,10 +172,10 @@
  * equal char, int or long.  percpu_read() evaluates to a lvalue and
  * all others to void.
  *
- * These operations are guaranteed to be atomic w.r.t. preemption.
- * The generic versions use plain get/put_cpu_var().  Archs are
+ * These operations are guaranteed to be atomic.
+ * The generic versions disable interrupts.  Archs are
  * encouraged to implement single-instruction alternatives which don't
- * require preemption protection.
+ * require protection.
  */
 #ifndef percpu_read
 # define percpu_read(var)						\
@@ -347,9 +347,10 @@
 
 #define _this_cpu_generic_to_op(pcp, val, op)				\
 do {									\
-	preempt_disable();						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
 	*__this_cpu_ptr(&(pcp)) op val;					\
-	preempt_enable();						\
+	local_irq_restore(flags);					\
 } while (0)
 
 #ifndef this_cpu_write
@@ -447,10 +448,11 @@
 #define _this_cpu_generic_add_return(pcp, val)				\
 ({									\
 	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
 	__this_cpu_add(pcp, val);					\
 	ret__ = __this_cpu_read(pcp);					\
-	preempt_enable();						\
+	local_irq_restore(flags);					\
 	ret__;								\
 })
 
@@ -476,10 +478,11 @@
 
 #define _this_cpu_generic_xchg(pcp, nval)				\
 ({	typeof(pcp) ret__;						\
-	preempt_disable();						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
 	ret__ = __this_cpu_read(pcp);					\
 	__this_cpu_write(pcp, nval);					\
-	preempt_enable();						\
+	local_irq_restore(flags);					\
 	ret__;								\
 })
 
@@ -501,12 +504,14 @@
 #endif
 
 #define _this_cpu_generic_cmpxchg(pcp, oval, nval)			\
-({	typeof(pcp) ret__;						\
-	preempt_disable();						\
+({									\
+	typeof(pcp) ret__;						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
 	ret__ = __this_cpu_read(pcp);					\
 	if (ret__ == (oval))						\
 		__this_cpu_write(pcp, nval);				\
-	preempt_enable();						\
+	local_irq_restore(flags);					\
 	ret__;								\
 })
 
@@ -538,10 +543,11 @@
 #define _this_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
 ({									\
 	int ret__;							\
-	preempt_disable();						\
+	unsigned long flags;						\
+	local_irq_save(flags);						\
 	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
 			oval1, oval2, nval1, nval2);			\
-	preempt_enable();						\
+	local_irq_restore(flags);					\
 	ret__;								\
 })
 
@@ -567,9 +573,9 @@
 #endif
 
 /*
- * Generic percpu operations that do not require preemption handling.
+ * Generic percpu operations for context that are safe from preemption/interrupts.
  * Either we do not care about races or the caller has the
- * responsibility of handling preemptions issues. Arch code can still
+ * responsibility of handling preemption/interrupt issues. Arch code can still
  * override these instructions since the arch per cpu code may be more
  * efficient and may actually get race freeness for free (that is the
  * case for x86 for example).
@@ -802,156 +808,4 @@
 	__pcpu_double_call_return_bool(__this_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
 #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
- * preemption only.
- */
-#define irqsafe_cpu_generic_to_op(pcp, val, op)				\
-do {									\
-	unsigned long flags;						\
-	local_irq_save(flags);						\
-	*__this_cpu_ptr(&(pcp)) op val;					\
-	local_irq_restore(flags);					\
-} while (0)
-
-#ifndef irqsafe_cpu_add
-# ifndef irqsafe_cpu_add_1
-#  define irqsafe_cpu_add_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef irqsafe_cpu_add_2
-#  define irqsafe_cpu_add_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef irqsafe_cpu_add_4
-#  define irqsafe_cpu_add_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# ifndef irqsafe_cpu_add_8
-#  define irqsafe_cpu_add_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), +=)
-# endif
-# define irqsafe_cpu_add(pcp, val) __pcpu_size_call(irqsafe_cpu_add_, (pcp), (val))
-#endif
-
-#ifndef irqsafe_cpu_sub
-# define irqsafe_cpu_sub(pcp, val)	irqsafe_cpu_add((pcp), -(val))
-#endif
-
-#ifndef irqsafe_cpu_inc
-# define irqsafe_cpu_inc(pcp)	irqsafe_cpu_add((pcp), 1)
-#endif
-
-#ifndef irqsafe_cpu_dec
-# define irqsafe_cpu_dec(pcp)	irqsafe_cpu_sub((pcp), 1)
-#endif
-
-#ifndef irqsafe_cpu_and
-# ifndef irqsafe_cpu_and_1
-#  define irqsafe_cpu_and_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef irqsafe_cpu_and_2
-#  define irqsafe_cpu_and_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef irqsafe_cpu_and_4
-#  define irqsafe_cpu_and_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# ifndef irqsafe_cpu_and_8
-#  define irqsafe_cpu_and_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), &=)
-# endif
-# define irqsafe_cpu_and(pcp, val) __pcpu_size_call(irqsafe_cpu_and_, (val))
-#endif
-
-#ifndef irqsafe_cpu_or
-# ifndef irqsafe_cpu_or_1
-#  define irqsafe_cpu_or_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef irqsafe_cpu_or_2
-#  define irqsafe_cpu_or_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef irqsafe_cpu_or_4
-#  define irqsafe_cpu_or_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# ifndef irqsafe_cpu_or_8
-#  define irqsafe_cpu_or_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), |=)
-# endif
-# define irqsafe_cpu_or(pcp, val) __pcpu_size_call(irqsafe_cpu_or_, (val))
-#endif
-
-#ifndef irqsafe_cpu_xor
-# ifndef irqsafe_cpu_xor_1
-#  define irqsafe_cpu_xor_1(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef irqsafe_cpu_xor_2
-#  define irqsafe_cpu_xor_2(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef irqsafe_cpu_xor_4
-#  define irqsafe_cpu_xor_4(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# ifndef irqsafe_cpu_xor_8
-#  define irqsafe_cpu_xor_8(pcp, val) irqsafe_cpu_generic_to_op((pcp), (val), ^=)
-# endif
-# 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
-
-#define irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-({									\
-	int ret__;							\
-	unsigned long flags;						\
-	local_irq_save(flags);						\
-	ret__ = __this_cpu_generic_cmpxchg_double(pcp1, pcp2,		\
-			oval1, oval2, nval1, nval2);			\
-	local_irq_restore(flags);					\
-	ret__;								\
-})
-
-#ifndef irqsafe_cpu_cmpxchg_double
-# ifndef irqsafe_cpu_cmpxchg_double_1
-#  define irqsafe_cpu_cmpxchg_double_1(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef irqsafe_cpu_cmpxchg_double_2
-#  define irqsafe_cpu_cmpxchg_double_2(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef irqsafe_cpu_cmpxchg_double_4
-#  define irqsafe_cpu_cmpxchg_double_4(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# ifndef irqsafe_cpu_cmpxchg_double_8
-#  define irqsafe_cpu_cmpxchg_double_8(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	irqsafe_generic_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)
-# endif
-# define irqsafe_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2)	\
-	__pcpu_double_call_return_bool(irqsafe_cpu_cmpxchg_double_, (pcp1), (pcp2), (oval1), (oval2), (nval1), (nval2))
-#endif
-
 #endif /* __LINUX_PERCPU_H */