locking tree changes for v3.16

index 78b03ef..ed60a1e 100644
@@ -292,9 +292,4 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic_dec(v) atomic_sub(1,(v))
 #define atomic64_dec(v) atomic64_sub(1,(v))
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #endif /* _ALPHA_ATOMIC_H */

index a19ba5e..4bdfbd4 100644
@@ -53,9 +53,6 @@ __set_bit(unsigned long nr, volatile void * addr)
 	*m |= 1 << (nr & 31);
 }
 
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-
 static inline void
 clear_bit(unsigned long nr, volatile void * addr)
 {

index 03e494f..83f03ca 100644
@@ -190,11 +190,6 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 
 #endif /* !CONFIG_ARC_HAS_LLSC */
 
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 /**
  * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t

deleted file mode 100644
index c32245c..0000000
@@ -1,37 +0,0 @@
-/*
- * Copyright (C) 2004, 2007-2010, 2011-2012 Synopsys, Inc. (www.synopsys.com)
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-#ifndef __ASM_BARRIER_H
-#define __ASM_BARRIER_H
-
-#ifndef __ASSEMBLY__
-
-/* TODO-vineetg: Need to see what this does, don't we need sync anywhere */
-#define mb() __asm__ __volatile__ ("" : : : "memory")
-#define rmb() mb()
-#define wmb() mb()
-#define set_mb(var, value)  do { var = value; mb(); } while (0)
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-#define read_barrier_depends()  mb()
-
-/* TODO-vineetg verify the correctness of macros here */
-#ifdef CONFIG_SMP
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#endif
-
-#define smp_read_barrier_depends()      do { } while (0)
-
-#endif
-
-#endif

index 647a83a..ebc0cf3 100644
@@ -19,6 +19,7 @@
 
 #include <linux/types.h>
 #include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
  * Hardware assisted read-modify-write using ARC700 LLOCK/SCOND insns.

@@ -496,10 +497,6 @@ static inline __attribute__ ((const)) int __ffs(unsigned long word)
  */
 #define ffz(x)	__ffs(~(x))
 
-/* TODO does this affect uni-processor code */
-#define smp_mb__before_clear_bit()  barrier()
-#define smp_mb__after_clear_bit()   barrier()
-
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/sched.h>

index 9a92fd7..3040359 100644
@@ -241,11 +241,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
 	long long counter;

index 2f59f74..c6a3e73 100644
@@ -79,5 +79,8 @@ do {									\
 
 #define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
 
+#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__after_atomic()	smp_mb()
+
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_BARRIER_H */

index b2e298a..5638099 100644
@@ -25,9 +25,7 @@
 
 #include <linux/compiler.h>
 #include <linux/irqflags.h>
-
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
+#include <asm/barrier.h>
 
 /*
  * These functions are the basis of our bit ops.

index 0237f08..57e8cb4 100644
@@ -152,11 +152,6 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 /*
  * 64-bit atomic operations.
  */

index 66eb764..48b9e70 100644
@@ -98,6 +98,9 @@ do {									\
 #define set_mb(var, value)	do { var = value; smp_mb(); } while (0)
 #define nop()		asm volatile("nop");
 
+#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__after_atomic()	smp_mb()
+
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __ASM_BARRIER_H */

index aa5b59d..9c19594 100644
@@ -17,17 +17,8 @@
 #define __ASM_BITOPS_H
 
 #include <linux/compiler.h>
-
 #include <asm/barrier.h>
 
-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-#endif
-
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
 #endif

index 6140727..0780f3f 100644
@@ -183,9 +183,4 @@ static inline int atomic_sub_if_positive(int i, atomic_t *v)
 
 #define atomic_dec_if_positive(v) atomic_sub_if_positive(1, v)
 
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /*  __ASM_AVR32_ATOMIC_H */

index ebe7ad3..910d537 100644
@@ -13,12 +13,7 @@
 #endif
 
 #include <asm/byteorder.h>
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
+#include <asm/barrier.h>
 
 /*
  * set_bit - Atomically set a bit in memory

@@ -67,7 +62,7 @@ static inline void set_bit(int nr, volatile void * addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static inline void clear_bit(int nr, volatile void * addr)

index 19283a1..4200068 100644
@@ -27,6 +27,9 @@
 
 #endif /* !CONFIG_SMP */
 
+#define smp_mb__before_atomic()	barrier()
+#define smp_mb__after_atomic()	barrier()
+
 #include <asm-generic/barrier.h>
 
 #endif /* _BLACKFIN_BARRIER_H */

index 0ca40dd..b298b65 100644
@@ -27,21 +27,17 @@
 
 #include <asm-generic/bitops/ext2-atomic.h>
 
+#include <asm/barrier.h>
+
 #ifndef CONFIG_SMP
 #include <linux/irqflags.h>
-
 /*
  * clear_bit may not imply a memory barrier
  */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-#endif
 #include <asm-generic/bitops/atomic.h>
 #include <asm-generic/bitops/non-atomic.h>
 #else
 
-#include <asm/barrier.h>
 #include <asm/byteorder.h>	/* swab32 */
 #include <linux/linkage.h>
 

@@ -101,12 +97,6 @@ static inline int test_and_change_bit(int nr, volatile unsigned long *addr)
 	return __raw_bit_test_toggle_asm(a, nr & 0x1f);
 }
 
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 #define test_bit __skip_test_bit
 #include <asm-generic/bitops/non-atomic.h>
 #undef test_bit

index 0bec7e5..f0ab012 100644
@@ -14,14 +14,8 @@
 #ifdef __KERNEL__
 
 #include <linux/bitops.h>
-
 #include <asm/byteorder.h>
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit() barrier()
-#define smp_mb__after_clear_bit()  barrier()
+#include <asm/barrier.h>
 
 /*
  * We are lucky, DSP is perfect for bitops: do it in 3 cycles

index 1056a5d..aa429ba 100644
@@ -7,6 +7,8 @@
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
 #include <arch/atomic.h>
+#include <arch/system.h>
+#include <asm/barrier.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for

@@ -151,10 +153,4 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return ret;
 }
 
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()    barrier()
-#define smp_mb__after_atomic_dec()     barrier()
-#define smp_mb__before_atomic_inc()    barrier()
-#define smp_mb__after_atomic_inc()     barrier()
-
 #endif

index 053c17b..bd49a54 100644
@@ -21,6 +21,7 @@
 #include <arch/bitops.h>
 #include <linux/atomic.h>
 #include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
  * set_bit - Atomically set a bit in memory

@@ -42,7 +43,7 @@
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 

@@ -84,12 +85,6 @@ static inline int test_and_set_bit(int nr, volatile unsigned long *addr)
 	return retval;
 }
 
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()      barrier()
-#define smp_mb__after_clear_bit()       barrier()
-
 /**
  * test_and_clear_bit - Clear a bit and return its old value
  * @nr: Bit to clear

index b86329d..f6c3a16 100644
@@ -17,6 +17,7 @@
 #include <linux/types.h>
 #include <asm/spr-regs.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #ifdef CONFIG_SMP
 #error not SMP safe

@@ -29,12 +30,6 @@
  * We do not have SMP systems, so we don't have to deal with that.
  */
 
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #define ATOMIC_INIT(i)		{ (i) }
 #define atomic_read(v)		(*(volatile int *)&(v)->counter)
 #define atomic_set(v, i)	(((v)->counter) = (i))

index 57bf85d..96de220 100644
@@ -25,12 +25,6 @@
 
 #include <asm-generic/bitops/ffz.h>
 
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 #ifndef CONFIG_FRV_OUTOFLINE_ATOMIC_OPS
 static inline
 unsigned long atomic_test_and_ANDNOT_mask(unsigned long mask, volatile unsigned long *v)

index 17dc637..de916b1 100644
@@ -24,6 +24,7 @@
 
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 

@@ -176,9 +177,4 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_inc_return(v) (atomic_add_return(1, v))
 #define atomic_dec_return(v) (atomic_sub_return(1, v))
 
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif

deleted file mode 100644
index 4e863da..0000000
@@ -1,37 +0,0 @@
-/*
- * Memory barrier definitions for the Hexagon architecture
- *
- * Copyright (c) 2010-2011, The Linux Foundation. All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 and
- * only version 2 as published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
- * 02110-1301, USA.
- */
-
-#ifndef _ASM_BARRIER_H
-#define _ASM_BARRIER_H
-
-#define rmb()				barrier()
-#define read_barrier_depends()		barrier()
-#define wmb()				barrier()
-#define mb()				barrier()
-#define smp_rmb()			barrier()
-#define smp_read_barrier_depends()	barrier()
-#define smp_wmb()			barrier()
-#define smp_mb()			barrier()
-
-/*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
-#define set_mb(var, value) \
-	do { var = value; mb(); } while (0)
-
-#endif /* _ASM_BARRIER_H */

index 9b1e4af..5e4a59b 100644
@@ -25,12 +25,10 @@
 #include <linux/compiler.h>
 #include <asm/byteorder.h>
 #include <asm/atomic.h>
+#include <asm/barrier.h>
 
 #ifdef __KERNEL__
 
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 /*
  * The offset calculations for these are based on BITS_PER_LONG == 32
  * (i.e. I get to shift by #5-2 (32 bits per long, 4 bytes per access),

index 6e6fe18..0f8bf48 100644
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 
 #include <asm/intrinsics.h>
+#include <asm/barrier.h>
 
 
 #define ATOMIC_INIT(i)		{ (i) }

@@ -208,10 +209,4 @@ atomic64_add_negative (__s64 i, atomic64_t *v)
 #define atomic64_inc(v)			atomic64_add(1, (v))
 #define atomic64_dec(v)			atomic64_sub(1, (v))
 
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* _ASM_IA64_ATOMIC_H */

index d0a69aa..a48957c 100644
@@ -55,6 +55,9 @@
 
 #endif
 
+#define smp_mb__before_atomic()	barrier()
+#define smp_mb__after_atomic()	barrier()
+
 /*
  * IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
  * need for asm trickery!

index c27eccd..71e8145 100644
@@ -16,6 +16,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/intrinsics.h>
+#include <asm/barrier.h>
 
 /**
  * set_bit - Atomically set a bit in memory

@@ -65,12 +66,6 @@ __set_bit (int nr, volatile void *addr)
 	*((__u32 *) addr + (nr >> 5)) |= (1 << (nr & 31));
 }
 
-/*
- * clear_bit() has "acquire" semantics.
- */
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	do { /* skip */; } while (0)
-
 /**
  * clear_bit - Clears a bit in memory
  * @nr: Bit to clear

@@ -78,7 +73,7 @@ __set_bit (int nr, volatile void *addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static __inline__ void

index 4f37dbb..f35109b 100644
@@ -118,6 +118,15 @@ extern long ia64_cmpxchg_called_with_bad_pointer(void);
 #define cmpxchg_rel(ptr, o, n)	\
 	ia64_cmpxchg(rel, (ptr), (o), (n), sizeof(*(ptr)))
 
+/*
+ * Worse still - early processor implementations actually just ignored
+ * the acquire/release and did a full fence all the time.  Unfortunately
+ * this meant a lot of badly written code that used .acq when they really
+ * wanted .rel became legacy out in the wild - so when we made a cpu
+ * that strictly did the .acq or .rel ... all that code started breaking - so
+ * we had to back-pedal and keep the "legacy" behavior of a full fence :-(
+ */
+
 /* for compatibility with other platforms: */
 #define cmpxchg(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))
 #define cmpxchg64(ptr, o, n)	cmpxchg_acq((ptr), (o), (n))

index 0d81697..8ad0ed4 100644
@@ -13,6 +13,7 @@
 #include <asm/assembler.h>
 #include <asm/cmpxchg.h>
 #include <asm/dcache_clear.h>
+#include <asm/barrier.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for

@@ -308,10 +309,4 @@ static __inline__ void atomic_set_mask(unsigned long  mask, atomic_t *addr)
 	local_irq_restore(flags);
 }
 
-/* Atomic operations are already serializing on m32r */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif	/* _ASM_M32R_ATOMIC_H */

index d3dea9a..86ba2b4 100644
@@ -21,6 +21,7 @@
 #include <asm/byteorder.h>
 #include <asm/dcache_clear.h>
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /*
  * These have to be done with inline assembly: that way the bit-setting

@@ -73,7 +74,7 @@ static __inline__ void set_bit(int nr, volatile void * addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static __inline__ void clear_bit(int nr, volatile void * addr)

@@ -103,9 +104,6 @@ static __inline__ void clear_bit(int nr, volatile void * addr)
 	local_irq_restore(flags);
 }
 
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 /**
  * change_bit - Toggle a bit in memory
  * @nr: Bit to clear

index f4e32de..5569521 100644
@@ -4,6 +4,7 @@
 #include <linux/types.h>
 #include <linux/irqflags.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for

@@ -209,11 +210,4 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* __ARCH_M68K_ATOMIC __ */

index c6baa91..b4a9b0d 100644
@@ -13,6 +13,7 @@
 #endif
 
 #include <linux/compiler.h>
+#include <asm/barrier.h>
 
 /*
  *	Bit access functions vary across the ColdFire and 68k families.

@@ -67,12 +68,6 @@ static inline void bfset_mem_set_bit(int nr, volatile unsigned long *vaddr)
 #define __set_bit(nr, vaddr)	set_bit(nr, vaddr)
 
 
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 static inline void bclr_reg_clear_bit(int nr, volatile unsigned long *vaddr)
 {
 	char *p = (char *)vaddr + (nr ^ 31) / 8;

index 307ecd2..470e365 100644
@@ -4,6 +4,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #if defined(CONFIG_METAG_ATOMICITY_IRQSOFF)
 /* The simple UP case. */

@@ -39,11 +40,6 @@
 
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif
 
 #define atomic_dec_if_positive(v)       atomic_sub_if_positive(1, v)

index 5d6b4b4..d1768c6 100644
@@ -97,4 +97,7 @@ do {									\
 	___p1;								\
 })
 
+#define smp_mb__before_atomic()	barrier()
+#define smp_mb__after_atomic()	barrier()
+
 #endif /* _ASM_METAG_BARRIER_H */

index c0d0df0..2671134 100644
@@ -5,12 +5,6 @@
 #include <asm/barrier.h>
 #include <asm/global_lock.h>
 
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 #ifdef CONFIG_SMP
 /*
  * These functions are the basis of our bit ops.

index e8eb3d5..37b2bef 100644
@@ -761,13 +761,4 @@ static __inline__ int atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #endif /* CONFIG_64BIT */
 
-/*
- * atomic*_return operations are serializing but not the non-*_return
- * versions.
- */
-#define smp_mb__before_atomic_dec()	smp_mb__before_llsc()
-#define smp_mb__after_atomic_dec()	smp_llsc_mb()
-#define smp_mb__before_atomic_inc()	smp_mb__before_llsc()
-#define smp_mb__after_atomic_inc()	smp_llsc_mb()
-
 #endif /* _ASM_ATOMIC_H */

index e1aa4e4..d0101dd 100644
@@ -195,4 +195,7 @@ do {									\
 	___p1;								\
 })
 
+#define smp_mb__before_atomic()	smp_mb__before_llsc()
+#define smp_mb__after_atomic()	smp_llsc_mb()
+
 #endif /* __ASM_BARRIER_H */

index 6a65d49..7c8816f 100644
@@ -38,13 +38,6 @@
 #endif
 
 /*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	smp_mb__before_llsc()
-#define smp_mb__after_clear_bit()	smp_llsc_mb()
-
-
-/*
  * These are the "slower" versions of the functions and are in bitops.c.
  * These functions call raw_local_irq_{save,restore}().
  */

@@ -120,7 +113,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)

@@ -175,7 +168,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr)
  */
 static inline void clear_bit_unlock(unsigned long nr, volatile unsigned long *addr)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(nr, addr);
 }
 

index d1fea7a..1818da4 100644
@@ -62,9 +62,9 @@ void __init alloc_legacy_irqno(void)
 
 void free_irqno(unsigned int irq)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(irq, irq_map);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 /*

index 975e184..cadeb1e 100644
@@ -13,6 +13,7 @@
 
 #include <asm/irqflags.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #ifndef CONFIG_SMP
 #include <asm-generic/atomic.h>

@@ -234,12 +235,6 @@ static inline void atomic_set_mask(unsigned long mask, unsigned long *addr)
 #endif
 }
 
-/* Atomic operations are already serializing on MN10300??? */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* __KERNEL__ */
 #endif /* CONFIG_SMP */
 #endif /* _ASM_ATOMIC_H */

index 596bb27..fe6f8e2 100644
@@ -18,9 +18,7 @@
 #define __ASM_BITOPS_H
 
 #include <asm/cpu-regs.h>
-
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
+#include <asm/barrier.h>
 
 /*
  * set bit

index 3e57faf..e5d0ef7 100644
@@ -78,9 +78,9 @@ void smp_flush_tlb(void *unused)
 	else
 		local_flush_tlb_page(flush_mm, flush_va);
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	cpumask_clear_cpu(cpu_id, &flush_cpumask);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 out:
 	put_cpu();
 }

index 2c64f22..3003cda 100644
@@ -27,14 +27,7 @@
 
 #include <linux/irqflags.h>
 #include <linux/compiler.h>
-
-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-#endif
+#include <asm/barrier.h>
 
 #include <asm/bitops/__ffs.h>
 #include <asm-generic/bitops/ffz.h>

index 472886c..0be2db2 100644
@@ -7,6 +7,7 @@
 
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for

@@ -143,11 +144,6 @@ static __inline__ int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #define ATOMIC_INIT(i)	{ (i) }
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #ifdef CONFIG_64BIT
 
 #define ATOMIC64_INIT(i) { (i) }

index 8c9b631..3f9406d 100644
@@ -8,6 +8,7 @@
 #include <linux/compiler.h>
 #include <asm/types.h>		/* for BITS_PER_LONG/SHIFT_PER_LONG */
 #include <asm/byteorder.h>
+#include <asm/barrier.h>
 #include <linux/atomic.h>
 
 /*

@@ -19,9 +20,6 @@
 #define CHOP_SHIFTCOUNT(x) (((unsigned long) (x)) & (BITS_PER_LONG - 1))
 
 
-#define smp_mb__before_clear_bit()      smp_mb()
-#define smp_mb__after_clear_bit()       smp_mb()
-
 /* See http://marc.theaimsgroup.com/?t=108826637900003 for discussion
  * on use of volatile and __*_bit() (set/clear/change):
  *	*_bit() want use of volatile.

index e3b1d41..28992d0 100644
@@ -8,6 +8,7 @@
 #ifdef __KERNEL__
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 

@@ -270,11 +271,6 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 }
 #define atomic_dec_if_positive atomic_dec_if_positive
 
-#define smp_mb__before_atomic_dec()     smp_mb()
-#define smp_mb__after_atomic_dec()      smp_mb()
-#define smp_mb__before_atomic_inc()     smp_mb()
-#define smp_mb__after_atomic_inc()      smp_mb()
-
 #ifdef __powerpc64__
 
 #define ATOMIC64_INIT(i)	{ (i) }

index f89da80..bab79a1 100644
@@ -84,4 +84,7 @@ do {									\
 	___p1;								\
 })
 
+#define smp_mb__before_atomic()     smp_mb()
+#define smp_mb__after_atomic()      smp_mb()
+
 #endif /* _ASM_POWERPC_BARRIER_H */

index a5e9a7d..bd3bd57 100644
@@ -51,11 +51,7 @@
 #define PPC_BIT(bit)		(1UL << PPC_BITLSHIFT(bit))
 #define PPC_BITMASK(bs, be)	((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
 
-/*
- * clear_bit doesn't imply a memory barrier
- */
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
+#include <asm/barrier.h>
 
 /* Macro for generating the ***_bits() functions */
 #define DEFINE_BITOP(fn, op, prefix)		\

index 18d7c80..51dbace 100644
@@ -81,7 +81,7 @@ void crash_ipi_callback(struct pt_regs *regs)
 	}
 
 	atomic_inc(&cpus_in_crash);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 
 	/*
 	 * Starting the kdump boot.

index 1d47061..fa934fe 100644
@@ -412,9 +412,4 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 #define atomic64_dec_and_test(_v)	(atomic64_sub_return(1, _v) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #endif /* __ARCH_S390_ATOMIC__  */

index 578680f..19ff956 100644
@@ -27,8 +27,9 @@
 #define smp_rmb()			rmb()
 #define smp_wmb()			wmb()
 #define smp_read_barrier_depends()	read_barrier_depends()
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
+
+#define smp_mb__before_atomic()		smp_mb()
+#define smp_mb__after_atomic()		smp_mb()
 
 #define set_mb(var, value)		do { var = value; mb(); } while (0)
 

index a304096..c1bf8d6 100644
@@ -2,12 +2,7 @@
 #define _ASM_SCORE_BITOPS_H
 
 #include <asm/byteorder.h> /* swab32 */
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
+#include <asm/barrier.h>
 
 #include <asm-generic/bitops.h>
 #include <asm-generic/bitops/__fls.h>

index f4c1c20..f57b8a6 100644
@@ -10,6 +10,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
 

@@ -62,9 +63,4 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 #endif /* __ASM_SH_ATOMIC_H */

index ea8706d..fc8e652 100644
@@ -9,6 +9,7 @@
 
 /* For __swab32 */
 #include <asm/byteorder.h>
+#include <asm/barrier.h>
 
 #ifdef CONFIG_GUSA_RB
 #include <asm/bitops-grb.h>

@@ -22,12 +23,6 @@
 #include <asm-generic/bitops/non-atomic.h>
 #endif
 
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-
 #ifdef CONFIG_SUPERH32
 static inline unsigned long ffz(unsigned long word)
 {

index 905832a..f08fe51 100644
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 #include <asm-generic/atomic64.h>
 
 

@@ -52,10 +53,4 @@ extern void atomic_set(atomic_t *, int);
 #define atomic_dec_and_test(v) (atomic_dec_return(v) == 0)
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, v) == 0)
 
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* !(__ARCH_SPARC_ATOMIC__) */

index be56a24..8b2f1bd 100644
@@ -9,6 +9,7 @@
 
 #include <linux/types.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)		{ (i) }
 #define ATOMIC64_INIT(i)	{ (i) }

@@ -108,10 +109,4 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 extern long atomic64_dec_if_positive(atomic64_t *v);
 
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */

index b5aad96..305dcc3 100644
@@ -68,4 +68,7 @@ do {									\
 	___p1;								\
 })
 
+#define smp_mb__before_atomic()	barrier()
+#define smp_mb__after_atomic()	barrier()
+
 #endif /* !(__SPARC64_BARRIER_H) */

index 25a6766..88c9a96 100644
@@ -90,9 +90,6 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr)
 
 #include <asm-generic/bitops/non-atomic.h>
 
-#define smp_mb__before_clear_bit()	do { } while(0)
-#define smp_mb__after_clear_bit()	do { } while(0)
-
 #include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/sched.h>

index 29011cc..f1a051c 100644
@@ -13,6 +13,7 @@
 
 #include <linux/compiler.h>
 #include <asm/byteorder.h>
+#include <asm/barrier.h>
 
 extern int test_and_set_bit(unsigned long nr, volatile unsigned long *addr);
 extern int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr);

@@ -23,9 +24,6 @@ extern void change_bit(unsigned long nr, volatile unsigned long *addr);
 
 #include <asm-generic/bitops/non-atomic.h>
 
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/fls64.h>

index 1ad4a1f..1b109fa 100644
@@ -169,16 +169,6 @@ static inline void atomic64_set(atomic64_t *v, long long n)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
-/*
- * We need to barrier before modifying the word, since the _atomic_xxx()
- * routines just tns the lock and then read/modify/write of the word.
- * But after the word is updated, the routine issues an "mf" before returning,
- * and since it's a function call, we don't even need a compiler barrier.
- */
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_dec()	do { } while (0)
-#define smp_mb__after_atomic_inc()	do { } while (0)
 
 #endif /* !__ASSEMBLY__ */
 

index ad220ee..7b11c5f 100644
@@ -105,12 +105,6 @@ static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
 
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1, 0)
 
-/* Atomic dec and inc don't implement barrier, so provide them if needed. */
-#define smp_mb__before_atomic_dec()	smp_mb()
-#define smp_mb__after_atomic_dec()	smp_mb()
-#define smp_mb__before_atomic_inc()	smp_mb()
-#define smp_mb__after_atomic_inc()	smp_mb()
-
 /* Define this to indicate that cmpxchg is an efficient operation. */
 #define __HAVE_ARCH_CMPXCHG
 

index b5a05d0..96a42ae 100644
@@ -72,6 +72,20 @@ mb_incoherent(void)
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
+#ifndef __tilegx__ /* 32 bit */
+/*
+ * We need to barrier before modifying the word, since the _atomic_xxx()
+ * routines just tns the lock and then read/modify/write of the word.
+ * But after the word is updated, the routine issues an "mf" before returning,
+ * and since it's a function call, we don't even need a compiler barrier.
+ */
+#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__after_atomic()	do { } while (0)
+#else /* 64 bit */
+#define smp_mb__before_atomic()	smp_mb()
+#define smp_mb__after_atomic()	smp_mb()
+#endif
+
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */

index d5a2068..20caa34 100644
@@ -17,6 +17,7 @@
 #define _ASM_TILE_BITOPS_H
 
 #include <linux/types.h>
+#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly

index 386865a..bbf7b66 100644
@@ -49,8 +49,8 @@ static inline void set_bit(unsigned nr, volatile unsigned long *addr)
  * restricted to acting on a single-word quantity.
  *
  * clear_bit() may not contain a memory barrier, so if it is used for
- * locking purposes, you should call smp_mb__before_clear_bit() and/or
- * smp_mb__after_clear_bit() to ensure changes are visible on other cpus.
+ * locking purposes, you should call smp_mb__before_atomic() and/or
+ * smp_mb__after_atomic() to ensure changes are visible on other cpus.
  */
 static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
 {

@@ -121,10 +121,6 @@ static inline int test_and_change_bit(unsigned nr,
 	return (_atomic_xor(addr, mask) & mask) != 0;
 }
 
-/* See discussion at smp_mb__before_atomic_dec() in <asm/atomic_32.h>. */
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	do {} while (0)
-
 #include <asm-generic/bitops/ext2-atomic.h>
 
 #endif /* _ASM_TILE_BITOPS_32_H */

index ad34cd0..bb1a292 100644
@@ -32,10 +32,6 @@ static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
 	__insn_fetchand((void *)(addr + nr / BITS_PER_LONG), ~mask);
 }
 
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-
-
 static inline void change_bit(unsigned nr, volatile unsigned long *addr)
 {
 	unsigned long mask = (1UL << (nr % BITS_PER_LONG));

index b17f4f4..6dd1c7d 100644
@@ -7,6 +7,7 @@
 #include <asm/alternative.h>
 #include <asm/cmpxchg.h>
 #include <asm/rmwcc.h>
+#include <asm/barrier.h>
 
 /*
  * Atomic operations that C can't guarantee us.  Useful for

@@ -243,12 +244,6 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2)
 		     : : "r" ((unsigned)(mask)), "m" (*(addr))	\
 		     : "memory")
 
-/* Atomic operations are already serializing on x86 */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #ifdef CONFIG_X86_32
 # include <asm/atomic64_32.h>
 #else

index 69bbb48..5c7198c 100644
@@ -137,6 +137,10 @@ do {									\
 
 #endif
 
+/* Atomic operations are already serializing on x86 */
+#define smp_mb__before_atomic()	barrier()
+#define smp_mb__after_atomic()	barrier()
+
 /*
  * Stop RDTSC speculation. This is needed when you need to use RDTSC
  * (or get_cycles or vread that possibly accesses the TSC) in a defined

index 9fc1af7..afcd35d 100644
@@ -15,6 +15,7 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h>
 #include <asm/rmwcc.h>
+#include <asm/barrier.h>
 
 #if BITS_PER_LONG == 32
 # define _BITOPS_LONG_SHIFT 5

@@ -102,7 +103,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static __always_inline void

@@ -156,9 +157,6 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
 	__clear_bit(nr, addr);
 }
 
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
 /**
  * __change_bit - Toggle a bit in memory
  * @nr: the bit to change

index 05af3b3..f28a24b 100644
@@ -41,7 +41,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr)
  *
  * sync_clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static inline void sync_clear_bit(long nr, volatile unsigned long *addr)

index a698d71..eab6704 100644
@@ -57,7 +57,7 @@ void arch_trigger_all_cpu_backtrace(void)
 	}
 
 	clear_bit(0, &backtrace_flag);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static int __kprobes

index e7fb447..e5103b4 100644
@@ -19,6 +19,7 @@
 #ifdef __KERNEL__
 #include <asm/processor.h>
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #define ATOMIC_INIT(i)	{ (i) }
 

@@ -387,12 +388,6 @@ static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 #endif
 }
 
-/* Atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* __KERNEL__ */
 
 #endif /* _XTENSA_ATOMIC_H */

index 0a24b04..5b88774 100644
@@ -13,6 +13,9 @@
 #define rmb() barrier()
 #define wmb() mb()
 
+#define smp_mb__before_atomic()		barrier()
+#define smp_mb__after_atomic()		barrier()
+
 #include <asm-generic/barrier.h>
 
 #endif /* _XTENSA_SYSTEM_H */

index 7b6873a..3f44fa2 100644
@@ -21,9 +21,7 @@
 
 #include <asm/processor.h>
 #include <asm/byteorder.h>
-
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
+#include <asm/barrier.h>
 
 #include <asm-generic/bitops/non-atomic.h>
 

index c11d24e..f8c6a11 100644
@@ -49,7 +49,7 @@ EXPORT_SYMBOL(blk_iopoll_sched);
 void __blk_iopoll_complete(struct blk_iopoll *iop)
 {
 	list_del(&iop->list);
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
 }
 EXPORT_SYMBOL(__blk_iopoll_complete);

@@ -161,7 +161,7 @@ EXPORT_SYMBOL(blk_iopoll_disable);
 void blk_iopoll_enable(struct blk_iopoll *iop)
 {
 	BUG_ON(!test_bit(IOPOLL_F_SCHED, &iop->state));
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit_unlock(IOPOLL_F_SCHED, &iop->state);
 }
 EXPORT_SYMBOL(blk_iopoll_enable);

index 834d8dd..9c294c8 100644
@@ -126,7 +126,7 @@ static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
 	int err = ctx->err;
 
 	if (!ctx->queue.qlen) {
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(CHAINIV_STATE_INUSE, &ctx->state);
 
 		if (!ctx->queue.qlen ||

index ae098a2..eee55c1 100644
@@ -105,7 +105,7 @@ static bool genpd_sd_counter_dec(struct generic_pm_domain *genpd)
 static void genpd_sd_counter_inc(struct generic_pm_domain *genpd)
 {
 	atomic_inc(&genpd->sd_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 static void genpd_acquire_lock(struct generic_pm_domain *genpd)

index 59c5abe..4fd8d6c 100644
@@ -224,9 +224,9 @@ static int get_slot(struct mtip_port *port)
  */
 static inline void release_slot(struct mtip_port *port, int tag)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(tag, port->allocated);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 /*

index cb6654b..73fe2f8 100644
@@ -159,7 +159,7 @@ void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a)
 {
 	int n = dev->coupled->online_count;
 
-	smp_mb__before_atomic_inc();
+	smp_mb__before_atomic();
 	atomic_inc(a);
 
 	while (atomic_read(a) < n)

index 8db6632..995dd42 100644
@@ -3498,7 +3498,7 @@ static int ohci_flush_iso_completions(struct fw_iso_context *base)
 		}
 
 		clear_bit_unlock(0, &ctx->flushing_completions);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 	}
 
 	tasklet_enable(&ctx->context.tasklet);

index c2676b5..ec5c3f4 100644
@@ -156,7 +156,7 @@ static void vblank_disable_and_save(struct drm_device *dev, int crtc)
 	 */
 	if ((vblrc > 0) && (abs64(diff_ns) > 1000000)) {
 		atomic_inc(&dev->vblank[crtc].count);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 	}
 
 	/* Invalidate all timestamps while vblank irq's are off. */

@@ -864,9 +864,9 @@ static void drm_update_vblank_count(struct drm_device *dev, int crtc)
 		vblanktimestamp(dev, crtc, tslot) = t_vblank;
 	}
 
-	smp_mb__before_atomic_inc();
+	smp_mb__before_atomic();
 	atomic_add(diff, &dev->vblank[crtc].count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 /**

@@ -1330,9 +1330,9 @@ bool drm_handle_vblank(struct drm_device *dev, int crtc)
 		/* Increment cooked vblank count. This also atomically commits
 		 * the timestamp computed above.
 		 */
-		smp_mb__before_atomic_inc();
+		smp_mb__before_atomic();
 		atomic_inc(&dev->vblank[crtc].count);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 	} else {
 		DRM_DEBUG("crtc %d: Redundant vblirq ignored. diff_ns = %d\n",
 			  crtc, (int) diff_ns);

index 7753249..5409bfa 100644
@@ -2147,7 +2147,7 @@ static void i915_error_work_func(struct work_struct *work)
 			 * updates before
 			 * the counter increment.
 			 */
-			smp_mb__before_atomic_inc();
+			smp_mb__before_atomic();
 			atomic_inc(&dev_priv->gpu_error.reset_counter);
 
 			kobject_uevent_env(&dev->primary->kdev->kobj,

index 82c9c5d..d2ebcf3 100644
@@ -828,7 +828,7 @@ static inline bool cached_dev_get(struct cached_dev *dc)
 		return false;
 
 	/* Paired with the mb in cached_dev_attach */
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	return true;
 }
 

index 7ef7461..a08e3ee 100644
@@ -243,7 +243,7 @@ static inline void set_closure_fn(struct closure *cl, closure_fn *fn,
 	cl->fn = fn;
 	cl->wq = wq;
 	/* between atomic_dec() in closure_put() */
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 }
 
 static inline void closure_queue(struct closure *cl)

index 66c5d13..4e84095 100644
@@ -607,9 +607,9 @@ static void write_endio(struct bio *bio, int error)
 
 	BUG_ON(!test_bit(B_WRITING, &b->state));
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(B_WRITING, &b->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	wake_up_bit(&b->state, B_WRITING);
 }

@@ -997,9 +997,9 @@ static void read_endio(struct bio *bio, int error)
 
 	BUG_ON(!test_bit(B_READING, &b->state));
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(B_READING, &b->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	wake_up_bit(&b->state, B_READING);
 }

index ebddef5..8e0caed 100644
@@ -642,7 +642,7 @@ static void free_pending_exception(struct dm_snap_pending_exception *pe)
 	struct dm_snapshot *s = pe->snap;
 
 	mempool_free(pe, s->pending_pool);
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&s->pending_exceptions_count);
 }
 

@@ -783,7 +783,7 @@ static int init_hash_tables(struct dm_snapshot *s)
 static void merge_shutdown(struct dm_snapshot *s)
 {
 	clear_bit_unlock(RUNNING_MERGE, &s->state_bits);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&s->state_bits, RUNNING_MERGE);
 }
 

index 455e649..2db768e 100644
@@ -2447,7 +2447,7 @@ static void dm_wq_work(struct work_struct *work)
 static void dm_queue_flush(struct mapped_device *md)
 {
 	clear_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	queue_work(md->wq, &md->work);
 }
 

index ad1b9be..2afef4e 100644
@@ -4400,7 +4400,7 @@ static void raid5_unplug(struct blk_plug_cb *blk_cb, bool from_schedule)
 			 * STRIPE_ON_UNPLUG_LIST clear but the stripe
 			 * is still in our list
 			 */
-			smp_mb__before_clear_bit();
+			smp_mb__before_atomic();
 			clear_bit(STRIPE_ON_UNPLUG_LIST, &sh->state);
 			/*
 			 * STRIPE_ON_RELEASE_LIST could be set here. In that

index de02db8..e355806 100644
@@ -399,7 +399,7 @@ static int dvb_usb_stop_feed(struct dvb_demux_feed *dvbdmxfeed)
 
 	/* clear 'streaming' status bit */
 	clear_bit(ADAP_STREAMING, &adap->state_bits);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&adap->state_bits, ADAP_STREAMING);
 skip_feed_stop:
 

@@ -550,7 +550,7 @@ static int dvb_usb_fe_init(struct dvb_frontend *fe)
 err:
 	if (!adap->suspend_resume_active) {
 		clear_bit(ADAP_INIT, &adap->state_bits);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		wake_up_bit(&adap->state_bits, ADAP_INIT);
 	}
 

@@ -591,7 +591,7 @@ err:
 	if (!adap->suspend_resume_active) {
 		adap->active_fe = -1;
 		clear_bit(ADAP_SLEEP, &adap->state_bits);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		wake_up_bit(&adap->state_bits, ADAP_SLEEP);
 	}
 

index 9261d53..dd57c7c 100644
@@ -2781,7 +2781,7 @@ int bnx2x_nic_load(struct bnx2x *bp, int load_mode)
 
 	case LOAD_OPEN:
 		netif_tx_start_all_queues(bp->dev);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		break;
 
 	case LOAD_DIAG:

@@ -4939,9 +4939,9 @@ void bnx2x_update_coalesce_sb_index(struct bnx2x *bp, u8 fw_sb_id,
 void bnx2x_schedule_sp_rtnl(struct bnx2x *bp, enum sp_rtnl_flag flag,
 			    u32 verbose)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	set_bit(flag, &bp->sp_rtnl_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	DP((BNX2X_MSG_SP | verbose), "Scheduling sp_rtnl task [Flag: %d]\n",
 	   flag);
 	schedule_delayed_work(&bp->sp_rtnl_task, 0);

index a78edac..16391db 100644
@@ -1858,10 +1858,10 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe)
 		return;
 #endif
 
-	smp_mb__before_atomic_inc();
+	smp_mb__before_atomic();
 	atomic_inc(&bp->cq_spq_left);
 	/* push the change in bp->spq_left and towards the memory */
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 
 	DP(BNX2X_MSG_SP, "bp->cq_spq_left %x\n", atomic_read(&bp->cq_spq_left));
 

@@ -1876,11 +1876,11 @@ void bnx2x_sp_event(struct bnx2x_fastpath *fp, union eth_rx_cqe *rr_cqe)
 		 * sp_state is cleared, and this order prevents
 		 * races
 		 */
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		set_bit(BNX2X_AFEX_PENDING_VIFSET_MCP_ACK, &bp->sp_state);
 		wmb();
 		clear_bit(BNX2X_AFEX_FCOE_Q_UPDATE_PENDING, &bp->sp_state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 		/* schedule the sp task as mcp ack is required */
 		bnx2x_schedule_sp_task(bp);

@@ -5272,9 +5272,9 @@ static void bnx2x_after_function_update(struct bnx2x *bp)
 		__clear_bit(RAMROD_COMP_WAIT, &queue_params.ramrod_flags);
 
 		/* mark latest Q bit */
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		set_bit(BNX2X_AFEX_FCOE_Q_UPDATE_PENDING, &bp->sp_state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 		/* send Q update ramrod for FCoE Q */
 		rc = bnx2x_queue_state_change(bp, &queue_params);

@@ -5500,7 +5500,7 @@ next_spqe:
 		spqe_cnt++;
 	} /* for */
 
-	smp_mb__before_atomic_inc();
+	smp_mb__before_atomic();
 	atomic_add(spqe_cnt, &bp->eq_spq_left);
 
 	bp->eq_cons = sw_cons;

@@ -13869,9 +13869,9 @@ static int bnx2x_drv_ctl(struct net_device *dev, struct drv_ctl_info *ctl)
 	case DRV_CTL_RET_L2_SPQ_CREDIT_CMD: {
 		int count = ctl->data.credit.credit_count;
 
-		smp_mb__before_atomic_inc();
+		smp_mb__before_atomic();
 		atomic_add(count, &bp->cq_spq_left);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		break;
 	}
 	case DRV_CTL_ULP_REGISTER_CMD: {

index 31297266..d725317 100644
@@ -258,16 +258,16 @@ static bool bnx2x_raw_check_pending(struct bnx2x_raw_obj *o)
 
 static void bnx2x_raw_clear_pending(struct bnx2x_raw_obj *o)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(o->state, o->pstate);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static void bnx2x_raw_set_pending(struct bnx2x_raw_obj *o)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	set_bit(o->state, o->pstate);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 /**

@@ -2131,7 +2131,7 @@ static int bnx2x_set_rx_mode_e1x(struct bnx2x *bp,
 
 	/* The operation is completed */
 	clear_bit(p->state, p->pstate);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return 0;
 }

@@ -3576,16 +3576,16 @@ error_exit1:
 
 static void bnx2x_mcast_clear_sched(struct bnx2x_mcast_obj *o)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(o->sched_state, o->raw.pstate);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static void bnx2x_mcast_set_sched(struct bnx2x_mcast_obj *o)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	set_bit(o->sched_state, o->raw.pstate);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static bool bnx2x_mcast_check_sched(struct bnx2x_mcast_obj *o)

@@ -4200,7 +4200,7 @@ int bnx2x_queue_state_change(struct bnx2x *bp,
 		if (rc) {
 			o->next_state = BNX2X_Q_STATE_MAX;
 			clear_bit(pending_bit, pending);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 			return rc;
 		}
 

@@ -4288,7 +4288,7 @@ static int bnx2x_queue_comp_cmd(struct bnx2x *bp,
 	wmb();
 
 	clear_bit(cmd, &o->pending);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return 0;
 }

@@ -5279,7 +5279,7 @@ static inline int bnx2x_func_state_change_comp(struct bnx2x *bp,
 	wmb();
 
 	clear_bit(cmd, &o->pending);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return 0;
 }

@@ -5926,7 +5926,7 @@ int bnx2x_func_state_change(struct bnx2x *bp,
 		if (rc) {
 			o->next_state = BNX2X_F_STATE_MAX;
 			clear_bit(cmd, pending);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 			return rc;
 		}
 

index 5c523b3..f82ac5a 100644
@@ -1626,9 +1626,9 @@ static
 void bnx2x_vf_handle_filters_eqe(struct bnx2x *bp,
 				 struct bnx2x_virtf *vf)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(BNX2X_FILTER_RX_MODE_PENDING, &vf->filter_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static void bnx2x_vf_handle_rss_update_eqe(struct bnx2x *bp,

@@ -2960,9 +2960,9 @@ void bnx2x_iov_task(struct work_struct *work)
 
 void bnx2x_schedule_iov_task(struct bnx2x *bp, enum bnx2x_iov_flag flag)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	set_bit(flag, &bp->iov_task_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	DP(BNX2X_MSG_IOV, "Scheduling iov task [Flag: %d]\n", flag);
 	queue_delayed_work(bnx2x_iov_wq, &bp->iov_task, 0);
 }

index 09f3fef..4dd48d2 100644
@@ -436,7 +436,7 @@ static int cnic_offld_prep(struct cnic_sock *csk)
 static int cnic_close_prep(struct cnic_sock *csk)
 {
 	clear_bit(SK_F_CONNECT_START, &csk->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	if (test_and_clear_bit(SK_F_OFFLD_COMPLETE, &csk->flags)) {
 		while (test_and_set_bit(SK_F_OFFLD_SCHED, &csk->flags))

@@ -450,7 +450,7 @@ static int cnic_close_prep(struct cnic_sock *csk)
 static int cnic_abort_prep(struct cnic_sock *csk)
 {
 	clear_bit(SK_F_CONNECT_START, &csk->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	while (test_and_set_bit(SK_F_OFFLD_SCHED, &csk->flags))
 		msleep(1);

@@ -3646,7 +3646,7 @@ static int cnic_cm_destroy(struct cnic_sock *csk)
 
 	csk_hold(csk);
 	clear_bit(SK_F_INUSE, &csk->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	while (atomic_read(&csk->ref_count) != 1)
 		msleep(1);
 	cnic_cm_cleanup(csk);

@@ -4026,7 +4026,7 @@ static void cnic_cm_process_kcqe(struct cnic_dev *dev, struct kcqe *kcqe)
 			 L4_KCQE_COMPLETION_STATUS_PARITY_ERROR)
 			set_bit(SK_F_HW_ERR, &csk->flags);
 
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(SK_F_OFFLD_SCHED, &csk->flags);
 		cnic_cm_upcall(cp, csk, opcode);
 		break;

index 675550f..3a77f9e 100644
@@ -249,7 +249,7 @@ bnad_tx_complete(struct bnad *bnad, struct bna_tcb *tcb)
 	if (likely(test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags)))
 		bna_ib_ack(tcb->i_dbell, sent);
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(BNAD_TXQ_FREE_SENT, &tcb->flags);
 
 	return sent;

@@ -1126,7 +1126,7 @@ bnad_tx_cleanup(struct delayed_work *work)
 
 		bnad_txq_cleanup(bnad, tcb);
 
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(BNAD_TXQ_FREE_SENT, &tcb->flags);
 	}
 

@@ -2992,7 +2992,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev)
 			sent = bnad_txcmpl_process(bnad, tcb);
 			if (likely(test_bit(BNAD_TXQ_TX_STARTED, &tcb->flags)))
 				bna_ib_ack(tcb->i_dbell, sent);
-			smp_mb__before_clear_bit();
+			smp_mb__before_atomic();
 			clear_bit(BNAD_TXQ_FREE_SENT, &tcb->flags);
 		} else {
 			netif_stop_queue(netdev);

index 0fe7ff7..05613a8 100644
@@ -281,7 +281,7 @@ static int cxgb_close(struct net_device *dev)
 	if (adapter->params.stats_update_period &&
 	    !(adapter->open_device_map & PORT_MASK)) {
 		/* Stop statistics accumulation. */
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		spin_lock(&adapter->work_lock);   /* sync with update task */
 		spin_unlock(&adapter->work_lock);
 		cancel_mac_stats_update(adapter);

index 8b069f9..3dfcf60 100644
@@ -1379,7 +1379,7 @@ static inline int check_desc_avail(struct adapter *adap, struct sge_txq *q,
 		struct sge_qset *qs = txq_to_qset(q, qid);
 
 		set_bit(qid, &qs->txq_stopped);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 		if (should_restart_tx(q) &&
 		    test_and_clear_bit(qid, &qs->txq_stopped))

@@ -1492,7 +1492,7 @@ static void restart_ctrlq(unsigned long data)
 
 	if (!skb_queue_empty(&q->sendq)) {
 		set_bit(TXQ_CTRL, &qs->txq_stopped);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 		if (should_restart_tx(q) &&
 		    test_and_clear_bit(TXQ_CTRL, &qs->txq_stopped))

@@ -1697,7 +1697,7 @@ again:	reclaim_completed_tx(adap, q, TX_RECLAIM_CHUNK);
 
 		if (unlikely(q->size - q->in_use < ndesc)) {
 			set_bit(TXQ_OFLD, &qs->txq_stopped);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 
 			if (should_restart_tx(q) &&
 			    test_and_clear_bit(TXQ_OFLD, &qs->txq_stopped))

index ca95cf2..e249528 100644
@@ -2031,7 +2031,7 @@ static void sge_rx_timer_cb(unsigned long data)
 			struct sge_fl *fl = s->egr_map[id];
 
 			clear_bit(id, s->starving_fl);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 
 			if (fl_starving(fl)) {
 				rxq = container_of(fl, struct sge_eth_rxq, fl);

index 9cfa4b4..9d88c1d 100644
@@ -1951,7 +1951,7 @@ static void sge_rx_timer_cb(unsigned long data)
 			struct sge_fl *fl = s->egr_map[id];
 
 			clear_bit(id, s->starving_fl);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 
 			/*
 			 * Since we are accessing fl without a lock there's a

index 9125d9a..d82f092 100644
@@ -1797,9 +1797,9 @@ void stop_gfar(struct net_device *dev)
 
 	netif_tx_stop_all_queues(dev);
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	set_bit(GFAR_DOWN, &priv->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	disable_napi(priv);
 

@@ -2042,9 +2042,9 @@ int startup_gfar(struct net_device *ndev)
 
 	gfar_init_tx_rx_base(priv);
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(GFAR_DOWN, &priv->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	/* Start Rx/Tx DMA and enable the interrupts */
 	gfar_start(priv);

index 861b722..1e526c0 100644
@@ -4671,7 +4671,7 @@ static void i40e_service_event_complete(struct i40e_pf *pf)
 	BUG_ON(!test_bit(__I40E_SERVICE_SCHED, &pf->state));
 
 	/* flush memory to make sure state is correct before next watchog */
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__I40E_SERVICE_SCHED, &pf->state);
 }
 

index c4c526b..2fecc26 100644
@@ -376,7 +376,7 @@ static void ixgbe_service_event_complete(struct ixgbe_adapter *adapter)
 	BUG_ON(!test_bit(__IXGBE_SERVICE_SCHED, &adapter->state));
 
 	/* flush memory to make sure state is correct before next watchdog */
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__IXGBE_SERVICE_SCHED, &adapter->state);
 }
 

@@ -4671,7 +4671,7 @@ static void ixgbe_up_complete(struct ixgbe_adapter *adapter)
 	if (hw->mac.ops.enable_tx_laser)
 		hw->mac.ops.enable_tx_laser(hw);
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__IXGBE_DOWN, &adapter->state);
 	ixgbe_napi_enable_all(adapter);
 

@@ -5567,7 +5567,7 @@ static int ixgbe_resume(struct pci_dev *pdev)
 		e_dev_err("Cannot enable PCI device from suspend\n");
 		return err;
 	}
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__IXGBE_DISABLED, &adapter->state);
 	pci_set_master(pdev);
 

@@ -8541,7 +8541,7 @@ static pci_ers_result_t ixgbe_io_slot_reset(struct pci_dev *pdev)
 		e_err(probe, "Cannot re-enable PCI device after reset.\n");
 		result = PCI_ERS_RESULT_DISCONNECT;
 	} else {
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(__IXGBE_DISABLED, &adapter->state);
 		adapter->hw.hw_addr = adapter->io_addr;
 		pci_set_master(pdev);

index d0799e8..de2793b 100644
@@ -1668,7 +1668,7 @@ static void ixgbevf_up_complete(struct ixgbevf_adapter *adapter)
 
 	spin_unlock_bh(&adapter->mbx_lock);
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__IXGBEVF_DOWN, &adapter->state);
 	ixgbevf_napi_enable_all(adapter);
 

@@ -3354,7 +3354,7 @@ static int ixgbevf_resume(struct pci_dev *pdev)
 		dev_err(&pdev->dev, "Cannot enable PCI device from suspend\n");
 		return err;
 	}
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__IXGBEVF_DISABLED, &adapter->state);
 	pci_set_master(pdev);
 

@@ -3712,7 +3712,7 @@ static pci_ers_result_t ixgbevf_io_slot_reset(struct pci_dev *pdev)
 		return PCI_ERS_RESULT_DISCONNECT;
 	}
 
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(__IXGBEVF_DISABLED, &adapter->state);
 	pci_set_master(pdev);
 

index ed88d39..e71eae3 100644
@@ -543,7 +543,7 @@ static int wlcore_irq_locked(struct wl1271 *wl)
 		 * wl1271_ps_elp_wakeup cannot be called concurrently.
 		 */
 		clear_bit(WL1271_FLAG_IRQ_RUNNING, &wl->flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 		ret = wlcore_fw_status(wl, wl->fw_status);
 		if (ret < 0)

index 179b8ed..53df39a 100644
@@ -662,9 +662,9 @@ static void pcifront_do_aer(struct work_struct *data)
 	notify_remote_via_evtchn(pdev->evtchn);
 
 	/*in case of we lost an aer request in four lines time_window*/
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(_PDEVB_op_active, &pdev->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	schedule_pcifront_aer_op(pdev);
 

index 96a26f4..cc51f38 100644
@@ -1541,7 +1541,7 @@ void isci_remote_device_release(struct kref *kref)
 	clear_bit(IDEV_STOP_PENDING, &idev->flags);
 	clear_bit(IDEV_IO_READY, &idev->flags);
 	clear_bit(IDEV_GONE, &idev->flags);
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(IDEV_ALLOCATED, &idev->flags);
 	wake_up(&ihost->eventq);
 }

index c886ad1..73ab75d 100644
@@ -951,7 +951,7 @@ static int tcm_loop_port_link(
 	struct tcm_loop_hba *tl_hba = tl_tpg->tl_hba;
 
 	atomic_inc(&tl_tpg->tl_tpg_port_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	/*
 	 * Add Linux/SCSI struct scsi_device by HCTL
 	 */

@@ -986,7 +986,7 @@ static void tcm_loop_port_unlink(
 	scsi_device_put(sd);
 
 	atomic_dec(&tl_tpg->tl_tpg_port_count);
-	smp_mb__after_atomic_dec();
+	smp_mb__after_atomic();
 
 	pr_debug("TCM_Loop_ConfigFS: Port Unlink Successful\n");
 }

index fcbe612..0b79b85 100644
@@ -393,7 +393,7 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 					continue;
 
 				atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
-				smp_mb__after_atomic_inc();
+				smp_mb__after_atomic();
 
 				spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 

@@ -404,7 +404,7 @@ target_emulate_set_target_port_groups(struct se_cmd *cmd)
 
 				spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 				atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
-				smp_mb__after_atomic_dec();
+				smp_mb__after_atomic();
 				break;
 			}
 			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);

@@ -990,7 +990,7 @@ static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
 		 * TARGET PORT GROUPS command
 		 */
 		atomic_inc(&mem->tg_pt_gp_mem_ref_cnt);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 
 		spin_lock_bh(&port->sep_alua_lock);

@@ -1020,7 +1020,7 @@ static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
 
 		spin_lock(&tg_pt_gp->tg_pt_gp_lock);
 		atomic_dec(&mem->tg_pt_gp_mem_ref_cnt);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 	}
 	spin_unlock(&tg_pt_gp->tg_pt_gp_lock);
 	/*

@@ -1054,7 +1054,7 @@ static void core_alua_do_transition_tg_pt_work(struct work_struct *work)
 		core_alua_dump_state(tg_pt_gp->tg_pt_gp_alua_pending_state));
 	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 	atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
-	smp_mb__after_atomic_dec();
+	smp_mb__after_atomic();
 	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 	if (tg_pt_gp->tg_pt_gp_transition_complete)

@@ -1116,7 +1116,7 @@ static int core_alua_do_transition_tg_pt(
 	 */
 	spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 	atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 
 	if (!explicit && tg_pt_gp->tg_pt_gp_implicit_trans_secs) {

@@ -1159,7 +1159,7 @@ int core_alua_do_port_transition(
 	spin_lock(&local_lu_gp_mem->lu_gp_mem_lock);
 	lu_gp = local_lu_gp_mem->lu_gp;
 	atomic_inc(&lu_gp->lu_gp_ref_cnt);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	spin_unlock(&local_lu_gp_mem->lu_gp_mem_lock);
 	/*
 	 * For storage objects that are members of the 'default_lu_gp',

@@ -1176,7 +1176,7 @@ int core_alua_do_port_transition(
 		rc = core_alua_do_transition_tg_pt(l_tg_pt_gp,
 						   new_state, explicit);
 		atomic_dec(&lu_gp->lu_gp_ref_cnt);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 		return rc;
 	}
 	/*

@@ -1190,7 +1190,7 @@ int core_alua_do_port_transition(
 
 		dev = lu_gp_mem->lu_gp_mem_dev;
 		atomic_inc(&lu_gp_mem->lu_gp_mem_ref_cnt);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		spin_unlock(&lu_gp->lu_gp_lock);
 
 		spin_lock(&dev->t10_alua.tg_pt_gps_lock);

@@ -1219,7 +1219,7 @@ int core_alua_do_port_transition(
 				tg_pt_gp->tg_pt_gp_alua_nacl = NULL;
 			}
 			atomic_inc(&tg_pt_gp->tg_pt_gp_ref_cnt);
-			smp_mb__after_atomic_inc();
+			smp_mb__after_atomic();
 			spin_unlock(&dev->t10_alua.tg_pt_gps_lock);
 			/*
 			 * core_alua_do_transition_tg_pt() will always return

@@ -1230,7 +1230,7 @@ int core_alua_do_port_transition(
 
 			spin_lock(&dev->t10_alua.tg_pt_gps_lock);
 			atomic_dec(&tg_pt_gp->tg_pt_gp_ref_cnt);
-			smp_mb__after_atomic_dec();
+			smp_mb__after_atomic();
 			if (rc)
 				break;
 		}

@@ -1238,7 +1238,7 @@ int core_alua_do_port_transition(
 
 		spin_lock(&lu_gp->lu_gp_lock);
 		atomic_dec(&lu_gp_mem->lu_gp_mem_ref_cnt);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 	}
 	spin_unlock(&lu_gp->lu_gp_lock);
 

@@ -1252,7 +1252,7 @@ int core_alua_do_port_transition(
 	}
 
 	atomic_dec(&lu_gp->lu_gp_ref_cnt);
-	smp_mb__after_atomic_dec();
+	smp_mb__after_atomic();
 	return rc;
 }
 

index 65001e1..7261877 100644
@@ -225,7 +225,7 @@ struct se_dev_entry *core_get_se_deve_from_rtpi(
 			continue;
 
 		atomic_inc(&deve->pr_ref_count);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		spin_unlock_irq(&nacl->device_list_lock);
 
 		return deve;

@@ -1392,7 +1392,7 @@ int core_dev_add_initiator_node_lun_acl(
 	spin_lock(&lun->lun_acl_lock);
 	list_add_tail(&lacl->lacl_list, &lun->lun_acl_list);
 	atomic_inc(&lun->lun_acl_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	spin_unlock(&lun->lun_acl_lock);
 
 	pr_debug("%s_TPG[%hu]_LUN[%u->%u] - Added %s ACL for "

@@ -1426,7 +1426,7 @@ int core_dev_del_initiator_node_lun_acl(
 	spin_lock(&lun->lun_acl_lock);
 	list_del(&lacl->lacl_list);
 	atomic_dec(&lun->lun_acl_count);
-	smp_mb__after_atomic_dec();
+	smp_mb__after_atomic();
 	spin_unlock(&lun->lun_acl_lock);
 
 	core_disable_device_list_for_node(lun, NULL, lacl->mapped_lun,

index 9e0232c..7e6b857 100644
@@ -323,7 +323,7 @@ static void iblock_bio_done(struct bio *bio, int err)
 		 * Bump the ib_bio_err_cnt and release bio.
 		 */
 		atomic_inc(&ibr->ib_bio_err_cnt);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 	}
 
 	bio_put(bio);

214 lines not on this page · raw message

index d4b9869..4badca1 100644
@@ -736,7 +736,7 @@ void target_qf_do_work(struct work_struct *work)
 	list_for_each_entry_safe(cmd, cmd_tmp, &qf_cmd_list, se_qf_node) {
 		list_del(&cmd->se_qf_node);
 		atomic_dec(&dev->dev_qf_count);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 
 		pr_debug("Processing %s cmd: %p QUEUE_FULL in work queue"
 			" context: %s\n", cmd->se_tfo->get_fabric_name(), cmd,

@@ -1148,7 +1148,7 @@ transport_check_alloc_task_attr(struct se_cmd *cmd)
 	 * Dormant to Active status.
 	 */
 	cmd->se_ordered_id = atomic_inc_return(&dev->dev_ordered_id);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	pr_debug("Allocated se_ordered_id: %u for Task Attr: 0x%02x on %s\n",
 			cmd->se_ordered_id, cmd->sam_task_attr,
 			dev->transport->name);

@@ -1705,7 +1705,7 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 		return false;
 	case MSG_ORDERED_TAG:
 		atomic_inc(&dev->dev_ordered_sync);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 
 		pr_debug("Added ORDERED for CDB: 0x%02x to ordered list, "
 			 " se_ordered_id: %u\n",

@@ -1723,7 +1723,7 @@ static bool target_handle_task_attr(struct se_cmd *cmd)
 		 * For SIMPLE and UNTAGGED Task Attribute commands
 		 */
 		atomic_inc(&dev->simple_cmds);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		break;
 	}
 

@@ -1828,7 +1828,7 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 
 	if (cmd->sam_task_attr == MSG_SIMPLE_TAG) {
 		atomic_dec(&dev->simple_cmds);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 		dev->dev_cur_ordered_id++;
 		pr_debug("Incremented dev->dev_cur_ordered_id: %u for"
 			" SIMPLE: %u\n", dev->dev_cur_ordered_id,

@@ -1840,7 +1840,7 @@ static void transport_complete_task_attr(struct se_cmd *cmd)
 			cmd->se_ordered_id);
 	} else if (cmd->sam_task_attr == MSG_ORDERED_TAG) {
 		atomic_dec(&dev->dev_ordered_sync);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 
 		dev->dev_cur_ordered_id++;
 		pr_debug("Incremented dev_cur_ordered_id: %u for ORDERED:"

@@ -1899,7 +1899,7 @@ static void transport_handle_queue_full(
 	spin_lock_irq(&dev->qf_cmd_lock);
 	list_add_tail(&cmd->se_qf_node, &cmd->se_dev->qf_cmd_list);
 	atomic_inc(&dev->dev_qf_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	spin_unlock_irq(&cmd->se_dev->qf_cmd_lock);
 
 	schedule_work(&cmd->se_dev->qf_work_queue);

@@ -2875,7 +2875,7 @@ void transport_send_task_abort(struct se_cmd *cmd)
 		if (cmd->se_tfo->write_pending_status(cmd) != 0) {
 			cmd->transport_state |= CMD_T_ABORTED;
 			cmd->se_cmd_flags |= SCF_SEND_DELAYED_TAS;
-			smp_mb__after_atomic_inc();
+			smp_mb__after_atomic();
 			return;
 		}
 	}

index 505519b..101858e 100644
@@ -162,7 +162,7 @@ int core_scsi3_ua_allocate(
 		spin_unlock_irq(&nacl->device_list_lock);
 
 		atomic_inc(&deve->ua_count);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 		return 0;
 	}
 	list_add_tail(&ua->ua_nacl_list, &deve->ua_list);

@@ -175,7 +175,7 @@ int core_scsi3_ua_allocate(
 		asc, ascq);
 
 	atomic_inc(&deve->ua_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	return 0;
 }
 

@@ -190,7 +190,7 @@ void core_scsi3_ua_release_all(
 		kmem_cache_free(se_ua_cache, ua);
 
 		atomic_dec(&deve->ua_count);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 	}
 	spin_unlock(&deve->ua_lock);
 }

@@ -251,7 +251,7 @@ void core_scsi3_ua_for_check_condition(
 		kmem_cache_free(se_ua_cache, ua);
 
 		atomic_dec(&deve->ua_count);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 	}
 	spin_unlock(&deve->ua_lock);
 	spin_unlock_irq(&nacl->device_list_lock);

@@ -310,7 +310,7 @@ int core_scsi3_ua_clear_for_request_sense(
 		kmem_cache_free(se_ua_cache, ua);
 
 		atomic_dec(&deve->ua_count);
-		smp_mb__after_atomic_dec();
+		smp_mb__after_atomic();
 	}
 	spin_unlock(&deve->ua_lock);
 	spin_unlock_irq(&nacl->device_list_lock);

index 41fe8a0..746ae80 100644
@@ -2041,7 +2041,7 @@ static int canon_copy_from_read_buf(struct tty_struct *tty,
 
 	if (found)
 		clear_bit(eol, ldata->read_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	ldata->read_tail += c;
 
 	if (found) {

index aa97fd8..4b5b3c2 100644
@@ -200,7 +200,7 @@ static void dma_tx_callback(void *param)
 
 	/* clear the bit used to serialize the DMA tx. */
 	clear_bit(MXS_AUART_DMA_TX_SYNC, &s->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	/* wake up the possible processes. */
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)

@@ -275,7 +275,7 @@ static void mxs_auart_tx_chars(struct mxs_auart_port *s)
 			mxs_auart_dma_tx(s, i);
 		} else {
 			clear_bit(MXS_AUART_DMA_TX_SYNC, &s->flags);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 		}
 		return;
 	}

index f058c03..819875c 100644
@@ -1851,7 +1851,7 @@ static int usbg_port_link(struct se_portal_group *se_tpg, struct se_lun *lun)
 	struct usbg_tpg *tpg = container_of(se_tpg, struct usbg_tpg, se_tpg);
 
 	atomic_inc(&tpg->tpg_port_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	return 0;
 }
 

@@ -1861,7 +1861,7 @@ static void usbg_port_unlink(struct se_portal_group *se_tpg,
 	struct usbg_tpg *tpg = container_of(se_tpg, struct usbg_tpg, se_tpg);
 
 	atomic_dec(&tpg->tpg_port_count);
-	smp_mb__after_atomic_dec();
+	smp_mb__after_atomic();
 }
 
 static int usbg_check_stop_free(struct se_cmd *se_cmd)

index 640fe01..f1ec168 100644
@@ -325,7 +325,7 @@ static void usb_wwan_outdat_callback(struct urb *urb)
 
 	for (i = 0; i < N_OUT_URB; ++i) {
 		if (portdata->out_urbs[i] == urb) {
-			smp_mb__before_clear_bit();
+			smp_mb__before_atomic();
 			clear_bit(i, &portdata->out_busy);
 			break;
 		}

index cf50ce9..aeb5131 100644
@@ -1255,7 +1255,7 @@ vhost_scsi_set_endpoint(struct vhost_scsi *vs,
 			tpg->tv_tpg_vhost_count++;
 			tpg->vhost_scsi = vs;
 			vs_tpg[tpg->tport_tpgt] = tpg;
-			smp_mb__after_atomic_inc();
+			smp_mb__after_atomic();
 			match = true;
 		}
 		mutex_unlock(&tpg->tv_tpg_mutex);

index 3bff6b3..3651ec8 100644
@@ -139,9 +139,9 @@ void w1_family_get(struct w1_family *f)
 
 void __w1_family_get(struct w1_family *f)
 {
-	smp_mb__before_atomic_inc();
+	smp_mb__before_atomic();
 	atomic_inc(&f->refcnt);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 EXPORT_SYMBOL(w1_unregister_family);

index 607e414..c4a0666 100644
@@ -348,9 +348,9 @@ void xen_pcibk_do_op(struct work_struct *data)
 	notify_remote_via_irq(pdev->evtchn_irq);
 
 	/* Mark that we're done. */
-	smp_mb__before_clear_bit(); /* /after/ clearing PCIF_active */
+	smp_mb__before_atomic(); /* /after/ clearing PCIF_active */
 	clear_bit(_PDEVF_op_active, &pdev->flags);
-	smp_mb__after_clear_bit(); /* /before/ final check for work */
+	smp_mb__after_atomic(); /* /before/ final check for work */
 
 	/* Check to see if the driver domain tried to start another request in
 	 * between clearing _XEN_PCIF_active and clearing _PDEVF_op_active.

index c9a2444..2256e9c 100644
@@ -279,7 +279,7 @@ static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
 
 static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
 		  &BTRFS_I(inode)->runtime_flags);
 }

index 3955e47..f29a54e 100644
@@ -3458,7 +3458,7 @@ static int lock_extent_buffer_for_io(struct extent_buffer *eb,
 static void end_extent_buffer_writeback(struct extent_buffer *eb)
 {
 	clear_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&eb->bflags, EXTENT_BUFFER_WRITEBACK);
 }
 

index 5f805bc..5a3b837 100644
@@ -7126,7 +7126,7 @@ static void btrfs_end_dio_bio(struct bio *bio, int err)
 		 * before atomic variable goto zero, we must make sure
 		 * dip->errors is perceived to be set.
 		 */
-		smp_mb__before_atomic_dec();
+		smp_mb__before_atomic();
 	}
 
 	/* if there are more bios still pending for this dio, just exit */

@@ -7306,7 +7306,7 @@ out_err:
 	 * before atomic variable goto zero, we must
 	 * make sure dip->errors is perceived to be set.
 	 */
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	if (atomic_dec_and_test(&dip->pending_bios))
 		bio_io_error(dip->orig_bio);
 

@@ -7449,7 +7449,7 @@ static ssize_t btrfs_direct_IO(int rw, struct kiocb *iocb,
 		return 0;
 
 	atomic_inc(&inode->i_dio_count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 
 	/*
 	 * The generic stuff only does filemap_write_and_wait_range, which

index e79ff6b..f45040a 100644
@@ -642,7 +642,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 		return -EINVAL;
 
 	atomic_inc(&root->will_be_snapshoted);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 	btrfs_wait_nocow_write(root);
 
 	ret = btrfs_start_delalloc_inodes(root, 0);

index 9ddb9fc..6a8110c 100644
@@ -77,7 +77,7 @@ EXPORT_SYMBOL(__lock_buffer);
 void unlock_buffer(struct buffer_head *bh)
 {
 	clear_bit_unlock(BH_Lock, &bh->b_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&bh->b_state, BH_Lock);
 }
 EXPORT_SYMBOL(unlock_buffer);

index f3b84cd..08b3c11 100644
@@ -42,7 +42,7 @@ int ext4_resize_begin(struct super_block *sb)
 void ext4_resize_end(struct super_block *sb)
 {
 	clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static ext4_group_t ext4_meta_bg_first_group(struct super_block *sb,

index aec7f73..c355f73 100644
@@ -277,7 +277,7 @@ static inline int may_grant(const struct gfs2_glock *gl, const struct gfs2_holde
 static void gfs2_holder_wake(struct gfs2_holder *gh)
 {
 	clear_bit(HIF_WAIT, &gh->gh_iflags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&gh->gh_iflags, HIF_WAIT);
 }
 

@@ -411,7 +411,7 @@ static void gfs2_demote_wake(struct gfs2_glock *gl)
 {
 	gl->gl_demote_state = LM_ST_EXCLUSIVE;
 	clear_bit(GLF_DEMOTE, &gl->gl_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&gl->gl_flags, GLF_DEMOTE);
 }
 

@@ -620,7 +620,7 @@ out:
 
 out_sched:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	gl->gl_lockref.count++;
 	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
 		gl->gl_lockref.count--;

@@ -628,7 +628,7 @@ out_sched:
 
 out_unlock:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	return;
 }
 

index 54b66809..74d9a3d 100644
@@ -221,7 +221,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
 	 * Writeback of the data mapping may cause the dirty flag to be set
 	 * so we have to clear it again here.
 	 */
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(GLF_DIRTY, &gl->gl_flags);
 }
 

index c1eb555..91f274d 100644
@@ -1134,7 +1134,7 @@ static void gdlm_recover_done(void *arg, struct dlm_slot *slots, int num_slots,
 		queue_delayed_work(gfs2_control_wq, &sdp->sd_control_work, 0);
 
 	clear_bit(DFL_DLM_RECOVERY, &ls->ls_recover_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&ls->ls_recover_flags, DFL_DLM_RECOVERY);
 	spin_unlock(&ls->ls_recover_spin);
 }

@@ -1271,7 +1271,7 @@ static int gdlm_mount(struct gfs2_sbd *sdp, const char *table)
 
 	ls->ls_first = !!test_bit(DFL_FIRST_MOUNT, &ls->ls_recover_flags);
 	clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
 	return 0;
 

index 7ad4094..fe7a56f 100644
@@ -587,7 +587,7 @@ fail:
 	gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
 done:
 	clear_bit(JDF_RECOVERY, &jd->jd_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
 }
 

index de25d55..529d9a9 100644
@@ -333,7 +333,7 @@ static ssize_t block_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 		set_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
 	else if (val == 0) {
 		clear_bit(DFL_BLOCK_LOCKS, &ls->ls_recover_flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		gfs2_glock_thaw(sdp);
 	} else {
 		ret = -EINVAL;

@@ -482,7 +482,7 @@ static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
 		rv = jid = -EINVAL;
 	sdp->sd_lockstruct.ls_jid = jid;
 	clear_bit(SDF_NOJOURNALID, &sdp->sd_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
 out:
 	spin_unlock(&sdp->sd_jindex_spin);

index 5f26139..6fac743 100644
@@ -43,7 +43,7 @@ static void journal_end_buffer_io_sync(struct buffer_head *bh, int uptodate)
 		clear_buffer_uptodate(bh);
 	if (orig_bh) {
 		clear_bit_unlock(BH_Shadow, &orig_bh->b_state);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		wake_up_bit(&orig_bh->b_state, BH_Shadow);
 	}
 	unlock_buffer(bh);

@@ -239,7 +239,7 @@ static int journal_submit_data_buffers(journal_t *journal,
 		spin_lock(&journal->j_list_lock);
 		J_ASSERT(jinode->i_transaction == commit_transaction);
 		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 	spin_unlock(&journal->j_list_lock);

@@ -277,7 +277,7 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 		}
 		spin_lock(&journal->j_list_lock);
 		clear_bit(__JI_COMMIT_RUNNING, &jinode->i_flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		wake_up_bit(&jinode->i_flags, __JI_COMMIT_RUNNING);
 	}
 

index d9f3d06..4a3d4ef 100644
@@ -2032,9 +2032,9 @@ static void nfs_access_free_entry(struct nfs_access_entry *entry)
 {
 	put_rpccred(entry->cred);
 	kfree(entry);
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_long_dec(&nfs_access_nr_entries);
-	smp_mb__after_atomic_dec();
+	smp_mb__after_atomic();
 }
 
 static void nfs_access_free_list(struct list_head *head)

@@ -2082,9 +2082,9 @@ nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
 		else {
 remove_lru_entry:
 			list_del_init(&nfsi->access_cache_inode_lru);
-			smp_mb__before_clear_bit();
+			smp_mb__before_atomic();
 			clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
-			smp_mb__after_clear_bit();
+			smp_mb__after_atomic();
 		}
 		spin_unlock(&inode->i_lock);
 	}

@@ -2232,9 +2232,9 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 	nfs_access_add_rbtree(inode, cache);
 
 	/* Update accounting */
-	smp_mb__before_atomic_inc();
+	smp_mb__before_atomic();
 	atomic_long_inc(&nfs_access_nr_entries);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 
 	/* Add inode to global LRU list */
 	if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {

index 0c43897..e6f7398 100644
@@ -1085,7 +1085,7 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping)
 	trace_nfs_invalidate_mapping_exit(inode, ret);
 
 	clear_bit_unlock(NFS_INO_INVALIDATING, bitlock);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(bitlock, NFS_INO_INVALIDATING);
 out:
 	return ret;

index efac602..b9c61ef 100644
@@ -789,9 +789,9 @@ static void nfs4_wait_ds_connect(struct nfs4_pnfs_ds *ds)
 
 static void nfs4_clear_ds_conn_bit(struct nfs4_pnfs_ds *ds)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(NFS4DS_CONNECTING, &ds->ds_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&ds->ds_state, NFS4DS_CONNECTING);
 }
 

index 2349518..c0583b9 100644
@@ -1140,9 +1140,9 @@ static int nfs4_run_state_manager(void *);
 
 static void nfs4_clear_state_manager_bit(struct nfs_client *clp)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(NFS4CLNT_MANAGER_RUNNING, &clp->cl_state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING);
 	rpc_wake_up(&clp->cl_rpcwaitq);
 }

index 2ffebf2..03ed984 100644
@@ -95,7 +95,7 @@ nfs_iocounter_dec(struct nfs_io_counter *c)
 {
 	if (atomic_dec_and_test(&c->io_count)) {
 		clear_bit(NFS_IO_INPROGRESS, &c->flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		wake_up_bit(&c->flags, NFS_IO_INPROGRESS);
 	}
 }

@@ -193,9 +193,9 @@ void nfs_unlock_request(struct nfs_page *req)
 		printk(KERN_ERR "NFS: Invalid unlock attempted\n");
 		BUG();
 	}
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(PG_BUSY, &req->wb_flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&req->wb_flags, PG_BUSY);
 }
 

index cb53d45..fd9536e 100644
@@ -1810,7 +1810,7 @@ static void pnfs_clear_layoutcommitting(struct inode *inode)
 	unsigned long *bitlock = &NFS_I(inode)->flags;
 
 	clear_bit_unlock(NFS_INO_LAYOUTCOMMITTING, bitlock);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(bitlock, NFS_INO_LAYOUTCOMMITTING);
 }
 

index 0237939..c3058a0 100644
@@ -275,7 +275,7 @@ pnfs_get_lseg(struct pnfs_layout_segment *lseg)
 {
 	if (lseg) {
 		atomic_inc(&lseg->pls_refcount);
-		smp_mb__after_atomic_inc();
+		smp_mb__after_atomic();
 	}
 	return lseg;
 }

index 9a3b6a4..ffb9459 100644
@@ -405,7 +405,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	nfs_pageio_complete(&pgio);
 
 	clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(bitlock, NFS_INO_FLUSHING);
 
 	if (err < 0)

@@ -1458,7 +1458,7 @@ static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait)
 static void nfs_commit_clear_lock(struct nfs_inode *nfsi)
 {
 	clear_bit(NFS_INO_COMMIT, &nfsi->flags);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	wake_up_bit(&nfsi->flags, NFS_INO_COMMIT);
 }
 

index 4b826ab..45d4e96 100644
@@ -460,9 +460,9 @@ static int write_cnodes(struct ubifs_info *c)
 		 * important.
 		 */
 		clear_bit(DIRTY_CNODE, &cnode->flags);
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(COW_CNODE, &cnode->flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 		offs += len;
 		dbg_chk_lpt_sz(c, 1, len);
 		cnode = cnode->cnext;

index 52a6559..3600994 100644
@@ -895,9 +895,9 @@ static int write_index(struct ubifs_info *c)
 		 * the reason for the second barrier.
 		 */
 		clear_bit(DIRTY_ZNODE, &znode->flags);
-		smp_mb__before_clear_bit();
+		smp_mb__before_atomic();
 		clear_bit(COW_ZNODE, &znode->flags);
-		smp_mb__after_clear_bit();
+		smp_mb__after_atomic();
 
 		/*
 		 * We have marked the znode as clean but have not updated the

index 33bd2de..9c79e76 100644
@@ -16,6 +16,7 @@
 #define __ASM_GENERIC_ATOMIC_H
 
 #include <asm/cmpxchg.h>
+#include <asm/barrier.h>
 
 #ifdef CONFIG_SMP
 /* Force people to define core atomics */

@@ -182,11 +183,5 @@ static inline void atomic_set_mask(unsigned int mask, atomic_t *v)
 }
 #endif
 
-/* Assume that atomic operations are already serializing */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #endif /* __KERNEL__ */
 #endif /* __ASM_GENERIC_ATOMIC_H */

index 6f692f8..1402fa8 100644
@@ -62,6 +62,14 @@
 #define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
 #endif
 
+#ifndef smp_mb__before_atomic
+#define smp_mb__before_atomic()	smp_mb()
+#endif
+
+#ifndef smp_mb__after_atomic
+#define smp_mb__after_atomic()	smp_mb()
+#endif
+
 #define smp_store_release(p, v)						\
 do {									\
 	compiletime_assert_atomic_type(*p);				\

index 280ca7a..dcdcacf 100644
@@ -11,14 +11,7 @@
 
 #include <linux/irqflags.h>
 #include <linux/compiler.h>
-
-/*
- * clear_bit may not imply a memory barrier
- */
-#ifndef smp_mb__before_clear_bit
-#define smp_mb__before_clear_bit()	smp_mb()
-#define smp_mb__after_clear_bit()	smp_mb()
-#endif
+#include <asm/barrier.h>
 
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/ffz.h>

index 9ae6c34..4967351 100644
@@ -80,7 +80,7 @@ static inline void set_bit(int nr, volatile unsigned long *addr)
  *
  * clear_bit() is atomic and may not be reordered.  However, it does
  * not contain a memory barrier, so if it is used for locking purposes,
- * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit()
+ * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic()
  * in order to ensure changes are visible on other processors.
  */
 static inline void clear_bit(int nr, volatile unsigned long *addr)

index 308a9e2..c30266e 100644
@@ -20,7 +20,7 @@
  */
 #define clear_bit_unlock(nr, addr)	\
 do {					\
-	smp_mb__before_clear_bit();	\
+	smp_mb__before_atomic();	\
 	clear_bit(nr, addr);		\
 } while (0)
 

index 5b08a85..fef3a80 100644
@@ -3,6 +3,42 @@
 #define _LINUX_ATOMIC_H
 #include <asm/atomic.h>
 
+/*
+ * Provide __deprecated wrappers for the new interface, avoid flag day changes.
+ * We need the ugly external functions to break header recursion hell.
+ */
+#ifndef smp_mb__before_atomic_inc
+static inline void __deprecated smp_mb__before_atomic_inc(void)
+{
+	extern void __smp_mb__before_atomic(void);
+	__smp_mb__before_atomic();
+}
+#endif
+
+#ifndef smp_mb__after_atomic_inc
+static inline void __deprecated smp_mb__after_atomic_inc(void)
+{
+	extern void __smp_mb__after_atomic(void);
+	__smp_mb__after_atomic();
+}
+#endif
+
+#ifndef smp_mb__before_atomic_dec
+static inline void __deprecated smp_mb__before_atomic_dec(void)
+{
+	extern void __smp_mb__before_atomic(void);
+	__smp_mb__before_atomic();
+}
+#endif
+
+#ifndef smp_mb__after_atomic_dec
+static inline void __deprecated smp_mb__after_atomic_dec(void)
+{
+	extern void __smp_mb__after_atomic(void);
+	__smp_mb__after_atomic();
+}
+#endif
+
 /**
  * atomic_add_unless - add unless the number is already a given value
  * @v: pointer of type atomic_t

index be5fd38..cbc5833 100644
@@ -32,6 +32,26 @@ extern unsigned long __sw_hweight64(__u64 w);
  */
 #include <asm/bitops.h>
 
+/*
+ * Provide __deprecated wrappers for the new interface, avoid flag day changes.
+ * We need the ugly external functions to break header recursion hell.
+ */
+#ifndef smp_mb__before_clear_bit
+static inline void __deprecated smp_mb__before_clear_bit(void)
+{
+	extern void __smp_mb__before_atomic(void);
+	__smp_mb__before_atomic();
+}
+#endif
+
+#ifndef smp_mb__after_clear_bit
+static inline void __deprecated smp_mb__after_clear_bit(void)
+{
+	extern void __smp_mb__after_atomic(void);
+	__smp_mb__after_atomic();
+}
+#endif
+
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
 	     (bit) < (size);					\

index c40302f..7cbf837 100644
@@ -278,7 +278,7 @@ static inline void get_bh(struct buffer_head *bh)
 
 static inline void put_bh(struct buffer_head *bh)
 {
-        smp_mb__before_atomic_dec();
+        smp_mb__before_atomic();
         atomic_dec(&bh->b_count);
 }
 

index 9f3c275..ec274e0 100644
@@ -649,7 +649,7 @@ static inline void hd_ref_init(struct hd_struct *part)
 static inline void hd_struct_get(struct hd_struct *part)
 {
 	atomic_inc(&part->ref);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 static inline int hd_struct_try_get(struct hd_struct *part)

index c7bfac1..1571110 100644
@@ -453,7 +453,7 @@ static inline int tasklet_trylock(struct tasklet_struct *t)
 
 static inline void tasklet_unlock(struct tasklet_struct *t)
 {
-	smp_mb__before_clear_bit(); 
+	smp_mb__before_atomic();
 	clear_bit(TASKLET_STATE_RUN, &(t)->state);
 }
 

@@ -501,7 +501,7 @@ static inline void tasklet_hi_schedule_first(struct tasklet_struct *t)
 static inline void tasklet_disable_nosync(struct tasklet_struct *t)
 {
 	atomic_inc(&t->count);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 static inline void tasklet_disable(struct tasklet_struct *t)

@@ -513,13 +513,13 @@ static inline void tasklet_disable(struct tasklet_struct *t)
 
 static inline void tasklet_enable(struct tasklet_struct *t)
 {
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&t->count);
 }
 
 static inline void tasklet_hi_enable(struct tasklet_struct *t)
 {
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&t->count);
 }
 

index 7ed3a3a..616415a 100644
@@ -493,7 +493,7 @@ static inline void napi_disable(struct napi_struct *n)
 static inline void napi_enable(struct napi_struct *n)
 {
 	BUG_ON(!test_bit(NAPI_STATE_SCHED, &n->state));
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(NAPI_STATE_SCHED, &n->state);
 }
 

index 25f54c7..010cde3 100644
@@ -2782,10 +2782,8 @@ static inline bool __must_check current_set_polling_and_test(void)
 	/*
 	 * Polling state must be visible before we test NEED_RESCHED,
 	 * paired by resched_task()
-	 *
-	 * XXX: assumes set/clear bit are identical barrier wise.
 	 */
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return unlikely(tif_need_resched());
 }

@@ -2803,7 +2801,7 @@ static inline bool __must_check current_clr_polling_and_test(void)
 	 * Polling state must be visible before we test NEED_RESCHED,
 	 * paired by resched_task()
 	 */
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 
 	return unlikely(tif_need_resched());
 }

index 3a847de..ad7dbe2 100644
@@ -142,18 +142,18 @@ struct rpc_task_setup {
 				test_and_set_bit(RPC_TASK_RUNNING, &(t)->tk_runstate)
 #define rpc_clear_running(t)	\
 	do { \
-		smp_mb__before_clear_bit(); \
+		smp_mb__before_atomic(); \
 		clear_bit(RPC_TASK_RUNNING, &(t)->tk_runstate); \
-		smp_mb__after_clear_bit(); \
+		smp_mb__after_atomic(); \
 	} while (0)
 
 #define RPC_IS_QUEUED(t)	test_bit(RPC_TASK_QUEUED, &(t)->tk_runstate)
 #define rpc_set_queued(t)	set_bit(RPC_TASK_QUEUED, &(t)->tk_runstate)
 #define rpc_clear_queued(t)	\
 	do { \
-		smp_mb__before_clear_bit(); \
+		smp_mb__before_atomic(); \
 		clear_bit(RPC_TASK_QUEUED, &(t)->tk_runstate); \
-		smp_mb__after_clear_bit(); \
+		smp_mb__after_atomic(); \
 	} while (0)
 
 #define RPC_IS_ACTIVATED(t)	test_bit(RPC_TASK_ACTIVE, &(t)->tk_runstate)

index 3e5efb2..3876f0f 100644
@@ -379,9 +379,9 @@ static inline int xprt_test_and_clear_connected(struct rpc_xprt *xprt)
 
 static inline void xprt_clear_connecting(struct rpc_xprt *xprt)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(XPRT_CONNECTING, &xprt->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static inline int xprt_connecting(struct rpc_xprt *xprt)

@@ -411,9 +411,9 @@ static inline void xprt_clear_bound(struct rpc_xprt *xprt)
 
 static inline void xprt_clear_binding(struct rpc_xprt *xprt)
 {
-	smp_mb__before_clear_bit();
+	smp_mb__before_atomic();
 	clear_bit(XPRT_BINDING, &xprt->state);
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 }
 
 static inline int xprt_test_and_set_binding(struct rpc_xprt *xprt)

index 1e98b55..6f8ab7d 100644
@@ -191,7 +191,7 @@ static inline void tracehook_notify_resume(struct pt_regs *regs)
 	 * pairs with task_work_add()->set_notify_resume() after
 	 * hlist_add_head(task->task_works);
 	 */
-	smp_mb__after_clear_bit();
+	smp_mb__after_atomic();
 	if (unlikely(current->task_works))
 		task_work_run();
 }

index 5679d92..624a8a5 100644
@@ -1204,7 +1204,7 @@ static inline bool __ip_vs_conn_get(struct ip_vs_conn *cp)
 /* put back the conn without restarting its timer */
 static inline void __ip_vs_conn_put(struct ip_vs_conn *cp)
 {
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&cp->refcnt);
 }
 void ip_vs_conn_put(struct ip_vs_conn *cp);

@@ -1408,7 +1408,7 @@ static inline void ip_vs_dest_hold(struct ip_vs_dest *dest)
 
 static inline void ip_vs_dest_put(struct ip_vs_dest *dest)
 {
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&dest->refcnt);
 }
 

index 2956c8d..1adf62b 100644
@@ -534,7 +534,7 @@ return_normal:
 			kgdb_info[cpu].exception_state &=
 				~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
 			kgdb_info[cpu].enter_kgdb--;
-			smp_mb__before_atomic_dec();
+			smp_mb__before_atomic();
 			atomic_dec(&slaves_in_kgdb);
 			dbg_touch_watchdogs();
 			local_irq_restore(flags);

@@ -662,7 +662,7 @@ kgdb_restore:
 	kgdb_info[cpu].exception_state &=
 		~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
 	kgdb_info[cpu].enter_kgdb--;
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_dec(&masters_in_kgdb);
 	/* Free kgdb_active */
 	atomic_set(&kgdb_active, -1);

index 5f58927..b991ec0 100644
@@ -267,7 +267,7 @@ static inline void futex_get_mm(union futex_key *key)
 	 * get_futex_key() implies a full barrier. This is relied upon
 	 * as full barrier (B), see the ordering comment above.
 	 */
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 /*

@@ -280,7 +280,7 @@ static inline void hb_waiters_inc(struct futex_hash_bucket *hb)
 	/*
 	 * Full barrier (A), see the ordering comment above.
 	 */
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 #endif
 }
 

index 6b375af..0ac67a5 100644
@@ -498,7 +498,7 @@ int __usermodehelper_disable(enum umh_disable_depth depth)
 static void helper_lock(void)
 {
 	atomic_inc(&running_helpers);
-	smp_mb__after_atomic_inc();
+	smp_mb__after_atomic();
 }
 
 static void helper_unlock(void)

index 4f560cf..51c4b24 100644
@@ -54,9 +54,9 @@ enum {
  * table (if it's not there yet), and we check it for lock order
  * conflicts and deadlocks.
  */
-#define MAX_LOCKDEP_ENTRIES	16384UL
+#define MAX_LOCKDEP_ENTRIES	32768UL
 
-#define MAX_LOCKDEP_CHAINS_BITS	15
+#define MAX_LOCKDEP_CHAINS_BITS	16
 #define MAX_LOCKDEP_CHAINS	(1UL << MAX_LOCKDEP_CHAINS_BITS)
 
 #define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5)

@@ -65,7 +65,7 @@ enum {
  * Stack-trace: tightly packed array of stack backtrace
  * addresses. Protected by the hash_lock.
  */
-#define MAX_STACK_TRACE_ENTRIES	262144UL
+#define MAX_STACK_TRACE_ENTRIES	524288UL
 
 extern struct list_head all_lock_classes;
 extern struct lock_chain lock_chains[];

13 lines not on this page · raw message

index 0c47e30..88b4a1d 100644

Lines of this file are not shown. View the raw message.

index 962d1d5..56db2f8 100644

Lines of this file are not shown. View the raw message.

index 268a45e..8a70ec0 100644

Lines of this file are not shown. View the raw message.

index 8b836b3..746bc93 100644

Lines of this file are not shown. View the raw message.

index 7d50f79..0ffa20a 100644

Lines of this file are not shown. View the raw message.

index 09d9591..1706cbb 100644

Lines of this file are not shown. View the raw message.

index a82fbe4..c73535c 100644

Lines of this file are not shown. View the raw message.

index 8c93267..c4e0984 100644

Lines of this file are not shown. View the raw message.

index 4977491..7401442 100644

Lines of this file are not shown. View the raw message.

index 5b3042e..e14f1cb 100644

Lines of this file are not shown. View the raw message.

index 9c3a839..bd0767e 100644

Lines of this file are not shown. View the raw message.

index 48f4244..56cd458 100644

Lines of this file are not shown. View the raw message.

index 025e250..366cf06 100644

Lines of this file are not shown. View the raw message.

index 75421f2..1f4f954 100644

Lines of this file are not shown. View the raw message.

index b7ebe23..d67de45 100644

Lines of this file are not shown. View the raw message.

index 4503335..aa8bf67 100644

Lines of this file are not shown. View the raw message.

index a82fb66..2371816 100644

Lines of this file are not shown. View the raw message.

index 81cf5a4..53b17ca 100644

Lines of this file are not shown. View the raw message.

index 5285ead..247e973 100644

Lines of this file are not shown. View the raw message.

index 36e431e..b6e440b 100644

Lines of this file are not shown. View the raw message.

index 3513d55..9761a0d 100644

Lines of this file are not shown. View the raw message.

index d173f79..89d051d 100644

Lines of this file are not shown. View the raw message.

index 25a3dcf..402a7e9 100644

Lines of this file are not shown. View the raw message.

index bb7e8ba..749f80c 100644

Lines of this file are not shown. View the raw message.

index 8546711..70951fd 100644

Lines of this file are not shown. View the raw message.

diff -puN include/linux/rwsem.h~rwsem-support-optimistic-spinning include/linux/rwsem.h
@@ -16,6 +16,7 @@
 
 #include <linux/atomic.h>
 
+struct optimistic_spin_queue;
 struct rw_semaphore;
 
 #ifdef CONFIG_RWSEM_GENERIC_SPINLOCK

@@ -23,9 +24,17 @@ struct rw_semaphore;
 #else
 /* All arch specific implementations share the same struct */
 struct rw_semaphore {
-	long			count;
-	raw_spinlock_t		wait_lock;
-	struct list_head	wait_list;
+	long count;
+	raw_spinlock_t wait_lock;
+	struct list_head wait_list;
+#ifdef CONFIG_SMP
+	/*
+	 * Write owner. Used as a speculative check to see
+	 * if the owner is running on the cpu.
+	 */
+	struct task_struct *owner;
+	struct optimistic_spin_queue *osq; /* spinner MCS lock */
+#endif
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 	struct lockdep_map	dep_map;
 #endif

@@ -55,11 +64,21 @@ static inline int rwsem_is_locked(struct
 # define __RWSEM_DEP_MAP_INIT(lockname)
 #endif
 
+#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM)
+#define __RWSEM_INITIALIZER(name)			\
+	{ RWSEM_UNLOCKED_VALUE,				\
+	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
+	  LIST_HEAD_INIT((name).wait_list),		\
+	  NULL, /* owner */				\
+	  NULL /* mcs lock */                           \
+	  __RWSEM_DEP_MAP_INIT(name) }
+#else
 #define __RWSEM_INITIALIZER(name)			\
 	{ RWSEM_UNLOCKED_VALUE,				\
 	  __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock),	\
 	  LIST_HEAD_INIT((name).wait_list)		\
 	  __RWSEM_DEP_MAP_INIT(name) }
+#endif
 
 #define DECLARE_RWSEM(name) \
 	struct rw_semaphore name = __RWSEM_INITIALIZER(name)

295 lines not on this page · raw message

diff -puN kernel/locking/rwsem.c~rwsem-support-optimistic-spinning kernel/locking/rwsem.c
@@ -12,6 +12,27 @@
 
 #include <linux/atomic.h>
 
+#if defined(CONFIG_SMP) && defined(CONFIG_RWSEM_XCHGADD_ALGORITHM)
+static inline void rwsem_set_owner(struct rw_semaphore *sem)
+{
+	sem->owner = current;
+}
+
+static inline void rwsem_clear_owner(struct rw_semaphore *sem)
+{
+	sem->owner = NULL;
+}
+
+#else
+static inline void rwsem_set_owner(struct rw_semaphore *sem)
+{
+}
+
+static inline void rwsem_clear_owner(struct rw_semaphore *sem)
+{
+}
+#endif
+
 /*
  * lock for reading
  */

@@ -48,6 +69,7 @@ void __sched down_write(struct rw_semaph
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
+	rwsem_set_owner(sem);
 }
 
 EXPORT_SYMBOL(down_write);