Merge branch 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull core locking changes from Ingo Molnar:
 - futex performance increases: larger hashes, smarter wakeups
 - mutex debugging improvements
 - lots of SMP ordering documentation updates
 - introduce the smp_load_acquire(), smp_store_release() primitives.
   (There are WIP patches that make use of them - not yet merged)
 - lockdep micro-optimizations
 - lockdep improvement: better cover IRQ contexts
 - liblockdep at last. We'll continue to monitor how useful this is

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  futexes: Fix futex_hashsize initialization
  arch: Re-sort some Kbuild files to hopefully help avoid some conflicts
  futexes: Avoid taking the hb->lock if there's nothing to wake up
  futexes: Document multiprocessor ordering guarantees
  futexes: Increase hash table size for better performance
  futexes: Clean up various details
  arch: Introduce smp_load_acquire(), smp_store_release()
  arch: Clean up asm/barrier.h implementations using asm-generic/barrier.h
  arch: Move smp_mb__{before,after}_atomic_{inc,dec}.h into asm/atomic.h
  locking/doc: Rename LOCK/UNLOCK to ACQUIRE/RELEASE
  mutexes: Give more informative mutex warning in the !lock->owner case
  powerpc: Full barrier for smp_mb__after_unlock_lock()
  rcu: Apply smp_mb__after_unlock_lock() to preserve grace periods
  Documentation/memory-barriers.txt: Downgrade UNLOCK+BLOCK
  locking: Add an smp_mb__after_unlock_lock() for UNLOCK+BLOCK barrier
  Documentation/memory-barriers.txt: Document ACCESS_ONCE()
  Documentation/memory-barriers.txt: Prohibit speculative writes
  Documentation/memory-barriers.txt: Add long atomic examples to memory-barriers.txt
  Documentation/memory-barriers.txt: Add needed ACCESS_ONCE() calls to memory-barriers.txt
  Revert "smp/cpumask: Make CONFIG_CPUMASK_OFFSTACK=y usable without debug dependency"
  ...

37 files changed, 251 insertions, 413 deletions

diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h
index ce8860a0b32..3832bdb794f 100644
--- a/arch/alpha/include/asm/barrier.h
+++ b/arch/alpha/include/asm/barrier.h
@@ -3,33 +3,18 @@
 
 #include <asm/compiler.h>
 
-#define mb() \
-__asm__ __volatile__("mb": : :"memory")
+#define mb()	__asm__ __volatile__("mb": : :"memory")
+#define rmb()	__asm__ __volatile__("mb": : :"memory")
+#define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-#define rmb() \
-__asm__ __volatile__("mb": : :"memory")
-
-#define wmb() \
-__asm__ __volatile__("wmb": : :"memory")
-
-#define read_barrier_depends() \
-__asm__ __volatile__("mb": : :"memory")
+#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define __ASM_SMP_MB
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
 #endif
 
-#define set_mb(var, value) \
-do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif		/* __BARRIER_H */
diff --git a/arch/arc/include/asm/Kbuild b/arch/arc/include/asm/Kbuild
index 5943f7f9d32..9ae21c19800 100644
--- a/arch/arc/include/asm/Kbuild
+++ b/arch/arc/include/asm/Kbuild
@@ -1,4 +1,5 @@
 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bugs.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 83f03ca6caf..03e494f695d 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -190,6 +190,11 @@ 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
diff --git a/arch/arc/include/asm/barrier.h b/arch/arc/include/asm/barrier.h
index f6cb7c4ffb3..c32245c3d1e 100644
--- a/arch/arc/include/asm/barrier.h
+++ b/arch/arc/include/asm/barrier.h
@@ -30,11 +30,6 @@
 #define smp_wmb()       barrier()
 #endif
 
-#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 smp_read_barrier_depends()      do { } while (0)
 
 #endif
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 60f15e274e6..2f59f744339 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -59,6 +59,21 @@
 #define smp_wmb()	dmb(ishst)
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index d4a63338a53..78e20ba8806 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -35,10 +35,60 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #else
+
 #define smp_mb()	asm volatile("dmb ish" : : : "memory")
 #define smp_rmb()	asm volatile("dmb ishld" : : : "memory")
 #define smp_wmb()	asm volatile("dmb ishst" : : : "memory")
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	}								\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1;						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	}								\
+	___p1;								\
+})
+
 #endif
 
 #define read_barrier_depends()		do { } while(0)
diff --git a/arch/avr32/include/asm/barrier.h b/arch/avr32/include/asm/barrier.h
index 0961275373d..715100790fd 100644
--- a/arch/avr32/include/asm/barrier.h
+++ b/arch/avr32/include/asm/barrier.h
@@ -8,22 +8,15 @@
 #ifndef __ASM_AVR32_BARRIER_H
 #define __ASM_AVR32_BARRIER_H
 
-#define nop()			asm volatile("nop")
-
-#define mb()			asm volatile("" : : : "memory")
-#define rmb()			mb()
-#define wmb()			asm volatile("sync 0" : : : "memory")
-#define read_barrier_depends()  do { } while(0)
-#define set_mb(var, value)      do { var = value; mb(); } while(0)
+/*
+ * Weirdest thing ever.. no full barrier, but it has a write barrier!
+ */
+#define wmb()	asm volatile("sync 0" : : : "memory")
 
 #ifdef CONFIG_SMP
 # error "The AVR32 port does not support SMP"
-#else
-# define smp_mb()		barrier()
-# define smp_rmb()		barrier()
-# define smp_wmb()		barrier()
-# define smp_read_barrier_depends() do { } while(0)
 #endif
 
+#include <asm-generic/barrier.h>
 
 #endif /* __ASM_AVR32_BARRIER_H */
diff --git a/arch/blackfin/include/asm/barrier.h b/arch/blackfin/include/asm/barrier.h
index ebb189507dd..19283a16ac0 100644
--- a/arch/blackfin/include/asm/barrier.h
+++ b/arch/blackfin/include/asm/barrier.h
@@ -23,26 +23,10 @@
 # define rmb()	do { barrier(); smp_check_barrier(); } while (0)
 # define wmb()	do { barrier(); smp_mark_barrier(); } while (0)
 # define read_barrier_depends()	do { barrier(); smp_check_barrier(); } while (0)
-#else
-# define mb()	barrier()
-# define rmb()	barrier()
-# define wmb()	barrier()
-# define read_barrier_depends()	do { } while (0)
 #endif
 
-#else /* !CONFIG_SMP */
-
-#define mb()	barrier()
-#define rmb()	barrier()
-#define wmb()	barrier()
-#define read_barrier_depends()	do { } while (0)
-
 #endif /* !CONFIG_SMP */
 
-#define smp_mb()  mb()
-#define smp_rmb() rmb()
-#define smp_wmb() wmb()
-#define set_mb(var, value) do { var = value; mb(); } while (0)
-#define smp_read_barrier_depends()	read_barrier_depends()
+#include <asm-generic/barrier.h>
 
 #endif /* _BLACKFIN_BARRIER_H */
diff --git a/arch/cris/include/asm/Kbuild b/arch/cris/include/asm/Kbuild
index b06caf649a9..199b1a9dab8 100644
--- a/arch/cris/include/asm/Kbuild
+++ b/arch/cris/include/asm/Kbuild
@@ -3,6 +3,7 @@ header-y += arch-v10/
 header-y += arch-v32/
 
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h
diff --git a/arch/cris/include/asm/barrier.h b/arch/cris/include/asm/barrier.h
deleted file mode 100644
index 198ad7fa6b2..00000000000
--- a/arch/cris/include/asm/barrier.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __ASM_CRIS_BARRIER_H
-#define __ASM_CRIS_BARRIER_H
-
-#define nop() __asm__ __volatile__ ("nop");
-
-#define barrier() __asm__ __volatile__("": : :"memory")
-#define mb() barrier()
-#define rmb() mb()
-#define wmb() mb()
-#define read_barrier_depends() do { } while(0)
-#define set_mb(var, value)  do { var = value; mb(); } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
-#define smp_read_barrier_depends()     read_barrier_depends()
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#define smp_read_barrier_depends()     do { } while(0)
-#endif
-
-#endif /* __ASM_CRIS_BARRIER_H */
diff --git a/arch/frv/include/asm/barrier.h b/arch/frv/include/asm/barrier.h
index 06776ad9f5e..abbef470154 100644
--- a/arch/frv/include/asm/barrier.h
+++ b/arch/frv/include/asm/barrier.h
@@ -17,13 +17,7 @@
 #define mb()			asm volatile ("membar" : : :"memory")
 #define rmb()			asm volatile ("membar" : : :"memory")
 #define wmb()			asm volatile ("membar" : : :"memory")
-#define read_barrier_depends()	do { } while (0)
 
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define smp_read_barrier_depends()	do {} while(0)
-#define set_mb(var, value) \
-	do { var = (value); barrier(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* _ASM_BARRIER_H */
diff --git a/arch/hexagon/include/asm/Kbuild b/arch/hexagon/include/asm/Kbuild
index 67c3450309b..ada843c701e 100644
--- a/arch/hexagon/include/asm/Kbuild
+++ b/arch/hexagon/include/asm/Kbuild
@@ -2,6 +2,7 @@
 header-y += ucontext.h
 
 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index 8a64ff2337f..7aae4cb2a29 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -160,8 +160,12 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
 #define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
 
-
 #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
diff --git a/arch/hexagon/include/asm/barrier.h b/arch/hexagon/include/asm/barrier.h
index 1041a8e70ce..4e863daea25 100644
--- a/arch/hexagon/include/asm/barrier.h
+++ b/arch/hexagon/include/asm/barrier.h
@@ -29,10 +29,6 @@
 #define smp_read_barrier_depends()	barrier()
 #define smp_wmb()			barrier()
 #define smp_mb()			barrier()
-#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()
 
 /*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
 #define set_mb(var, value) \
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index 60576e06b6f..d0a69aa35e2 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -45,14 +45,37 @@
 # define smp_rmb()	rmb()
 # define smp_wmb()	wmb()
 # define smp_read_barrier_depends()	read_barrier_depends()
+
 #else
+
 # define smp_mb()	barrier()
 # define smp_rmb()	barrier()
 # define smp_wmb()	barrier()
 # define smp_read_barrier_depends()	do { } while(0)
+
 #endif
 
 /*
+ * IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
+ * need for asm trickery!
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
+/*
  * XXX check on this ---I suspect what Linus really wants here is
  * acquire vs release semantics but we can't discuss this stuff with
  * Linus just yet.  Grrr...
diff --git a/arch/m32r/include/asm/barrier.h b/arch/m32r/include/asm/barrier.h
index 6976621efd3..1a40265e8d8 100644
--- a/arch/m32r/include/asm/barrier.h
+++ b/arch/m32r/include/asm/barrier.h
@@ -11,84 +11,6 @@
 
 #define nop()  __asm__ __volatile__ ("nop" : : )
 
-/*
- * Memory barrier.
- *
- * mb() prevents loads and stores being reordered across this point.
- * rmb() prevents loads being reordered across this point.
- * wmb() prevents stores being reordered across this point.
- */
-#define mb()   barrier()
-#define rmb()  mb()
-#define wmb()  mb()
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      b = 2;
- *      memory_barrier();
- *      p = &b;                         q = p;
- *                                      read_barrier_depends();
- *                                      d = *q;
- * </programlisting>
- *
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      a = 2;
- *      memory_barrier();
- *      b = 3;                          y = b;
- *                                      read_barrier_depends();
- *                                      x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
+#include <asm-generic/barrier.h>
 
 #endif /* _ASM_M32R_BARRIER_H */
diff --git a/arch/m68k/include/asm/barrier.h b/arch/m68k/include/asm/barrier.h
index 445ce22c23c..15c5f77c161 100644
--- a/arch/m68k/include/asm/barrier.h
+++ b/arch/m68k/include/asm/barrier.h
@@ -1,20 +1,8 @@
 #ifndef _M68K_BARRIER_H
 #define _M68K_BARRIER_H
 
-/*
- * Force strict CPU ordering.
- * Not really required on m68k...
- */
 #define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define read_barrier_depends()	((void)0)
-#define set_mb(var, value)	({ (var) = (value); wmb(); })
 
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	((void)0)
+#include <asm-generic/barrier.h>
 
 #endif /* _M68K_BARRIER_H */
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index c90bfc6bf64..5d6b4b407dd 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -82,4 +82,19 @@ static inline void fence(void)
 #define smp_read_barrier_depends()     do { } while (0)
 #define set_mb(var, value) do { var = value; smp_mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* _ASM_METAG_BARRIER_H */
diff --git a/arch/microblaze/include/asm/Kbuild b/arch/microblaze/include/asm/Kbuild
index ce0bbf8f564..a82426589ff 100644
--- a/arch/microblaze/include/asm/Kbuild
+++ b/arch/microblaze/include/asm/Kbuild
@@ -1,4 +1,5 @@
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
diff --git a/arch/microblaze/include/asm/barrier.h b/arch/microblaze/include/asm/barrier.h
deleted file mode 100644
index df5be3e8704..00000000000
--- a/arch/microblaze/include/asm/barrier.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_BARRIER_H
-#define _ASM_MICROBLAZE_BARRIER_H
-
-#define nop()                  asm volatile ("nop")
-
-#define smp_read_barrier_depends()	do {} while (0)
-#define read_barrier_depends()		do {} while (0)
-
-#define mb()			barrier()
-#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 smp_mb()		mb()
-#define smp_rmb()		rmb()
-#define smp_wmb()		wmb()
-
-#endif /* _ASM_MICROBLAZE_BARRIER_H */
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index f26d8e1bf3c..e1aa4e4c298 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -180,4 +180,19 @@
 #define nudge_writes() mb()
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/mn10300/include/asm/Kbuild b/arch/mn10300/include/asm/Kbuild
index 74742dc6a3d..032143ec232 100644
--- a/arch/mn10300/include/asm/Kbuild
+++ b/arch/mn10300/include/asm/Kbuild
@@ -1,4 +1,5 @@
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h
diff --git a/arch/mn10300/include/asm/barrier.h b/arch/mn10300/include/asm/barrier.h
deleted file mode 100644
index 2bd97a5c8af..00000000000
--- a/arch/mn10300/include/asm/barrier.h
+++ /dev/null
@@ -1,37 +0,0 @@
-/* MN10300 memory barrier definitions
- *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
- */
-#ifndef _ASM_BARRIER_H
-#define _ASM_BARRIER_H
-
-#define nop()	asm volatile ("nop")
-
-#define mb()	asm volatile ("": : :"memory")
-#define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define set_mb(var, value)  do { xchg(&var, value); } while (0)
-#else  /* CONFIG_SMP */
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#endif /* CONFIG_SMP */
-
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#endif /* _ASM_BARRIER_H */
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index a603b9ebe54..34b0be4ca52 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -1,4 +1,5 @@
 
+generic-y += barrier.h
 generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
deleted file mode 100644
index e77d834aa80..00000000000
--- a/arch/parisc/include/asm/barrier.h
+++ /dev/null
@@ -1,35 +0,0 @@
-#ifndef __PARISC_BARRIER_H
-#define __PARISC_BARRIER_H
-
-/*
-** This is simply the barrier() macro from linux/kernel.h but when serial.c
-** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
-** hasn't yet been included yet so it fails, thus repeating the macro here.
-**
-** PA-RISC architecture allows for weakly ordered memory accesses although
-** none of the processors use it. There is a strong ordered bit that is
-** set in the O-bit of the page directory entry. Operating systems that
-** can not tolerate out of order accesses should set this bit when mapping
-** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
-** of the processor implemented the PSW O-bit). The PCX-W ERS states that
-** the TLB O-bit is not implemented so the page directory does not need to
-** have the O-bit set when mapping pages (section 3.1). This section also
-** states that the PSW Y, Z, G, and O bits are not implemented.
-** So it looks like nothing needs to be done for parisc-linux (yet).
-** (thanks to chada for the above comment -ggg)
-**
-** The __asm__ op below simple prevents gcc/ld from reordering
-** instructions across the mb() "call".
-*/
-#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
-#define rmb()		mb()
-#define wmb()		mb()
-#define smp_mb()	mb()
-#define smp_rmb()	mb()
-#define smp_wmb()	mb()
-#define smp_read_barrier_depends()	do { } while(0)
-#define read_barrier_depends()		do { } while(0)
-
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
-
-#endif /* __PARISC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index ae782254e73..f89da808ce3 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -45,11 +45,15 @@
 #    define SMPWMB      eieio
 #endif
 
+#define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+
 #define smp_mb()	mb()
-#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_rmb()	__lwsync()
 #define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()	read_barrier_depends()
 #else
+#define __lwsync()	barrier()
+
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
@@ -65,4 +69,19 @@
 #define data_barrier(x)	\
 	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	___p1;								\
+})
+
 #endif /* _ASM_POWERPC_BARRIER_H */
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 5f54a744dcc..f6e78d63fb6 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -28,6 +28,8 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+
 #define arch_spin_is_locked(x)		((x)->slock != 0)
 
 #ifdef CONFIG_PPC64
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 16760eeb79b..578680f6207 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -32,4 +32,19 @@
 
 #define set_mb(var, value)		do { var = value; mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */
diff --git a/arch/score/include/asm/Kbuild b/arch/score/include/asm/Kbuild
index f3414ade77a..fe7471eb016 100644
--- a/arch/score/include/asm/Kbuild
+++ b/arch/score/include/asm/Kbuild
@@ -1,6 +1,7 @@
 
 header-y +=
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += trace_clock.h
 generic-y += xor.h
diff --git a/arch/score/include/asm/barrier.h b/arch/score/include/asm/barrier.h
deleted file mode 100644
index 0eacb6471e6..00000000000
--- a/arch/score/include/asm/barrier.h
+++ /dev/null
@@ -1,16 +0,0 @@
-#ifndef _ASM_SCORE_BARRIER_H
-#define _ASM_SCORE_BARRIER_H
-
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#define set_mb(var, value) 		do {var = value; wmb(); } while (0)
-
-#endif /* _ASM_SCORE_BARRIER_H */
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 72c103dae30..43715308b06 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -26,29 +26,14 @@
 #if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
 #define mb()		__asm__ __volatile__ ("synco": : :"memory")
 #define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("synco": : :"memory")
+#define wmb()		mb()
 #define ctrl_barrier()	__icbi(PAGE_OFFSET)
-#define read_barrier_depends()	do { } while(0)
 #else
-#define mb()		__asm__ __volatile__ ("": : :"memory")
-#define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("": : :"memory")
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
-#define read_barrier_depends()	do { } while(0)
-#endif
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
 #endif
 
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
+#include <asm-generic/barrier.h>
+
 #endif /* __ASM_SH_BARRIER_H */
diff --git a/arch/sparc/include/asm/barrier_32.h b/arch/sparc/include/asm/barrier_32.h
index c1b76654ee7..ae69eda288f 100644
--- a/arch/sparc/include/asm/barrier_32.h
+++ b/arch/sparc/include/asm/barrier_32.h
@@ -1,15 +1,7 @@
 #ifndef __SPARC_BARRIER_H
 #define __SPARC_BARRIER_H
 
-/* XXX Change this if we ever use a PSO mode kernel. */
-#define mb()	__asm__ __volatile__ ("" : : : "memory")
-#define rmb()	mb()
-#define wmb()	mb()
-#define read_barrier_depends()	do { } while(0)
-#define set_mb(__var, __value)  do { __var = __value; mb(); } while(0)
-#define smp_mb()	__asm__ __volatile__("":::"memory")
-#define smp_rmb()	__asm__ __volatile__("":::"memory")
-#define smp_wmb()	__asm__ __volatile__("":::"memory")
-#define smp_read_barrier_depends()	do { } while(0)
+#include <asm/processor.h> /* for nop() */
+#include <asm-generic/barrier.h>
 
 #endif /* !(__SPARC_BARRIER_H) */
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 95d45986f90..b5aad964558 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -53,4 +53,19 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 
 #define smp_read_barrier_depends()	do { } while(0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* !(__SPARC64_BARRIER_H) */
diff --git a/arch/tile/include/asm/barrier.h b/arch/tile/include/asm/barrier.h
index a9a73da5865..b5a05d050a8 100644
--- a/arch/tile/include/asm/barrier.h
+++ b/arch/tile/include/asm/barrier.h
@@ -22,59 +22,6 @@
 #include <arch/spr_def.h>
 #include <asm/timex.h>
 
-/*
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends()	do { } while (0)
-
 #define __sync()	__insn_mf()
 
 #include <hv/syscall_public.h>
@@ -125,20 +72,7 @@ mb_incoherent(void)
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#endif
-
-#define set_mb(var, value) \
-	do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_TILE_BARRIER_H */
diff --git a/arch/unicore32/include/asm/barrier.h b/arch/unicore32/include/asm/barrier.h
index a6620e5336b..83d6a520f4b 100644
--- a/arch/unicore32/include/asm/barrier.h
+++ b/arch/unicore32/include/asm/barrier.h
@@ -14,15 +14,6 @@
 #define dsb() __asm__ __volatile__ ("" : : : "memory")
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 
-#define mb()				barrier()
-#define rmb()				barrier()
-#define wmb()				barrier()
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define read_barrier_depends()		do { } while (0)
-#define smp_read_barrier_depends()	do { } while (0)
-
-#define set_mb(var, value)		do { var = value; smp_mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* __UNICORE_BARRIER_H__ */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index c6cd358a1ee..04a48903b2e 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -92,12 +92,53 @@
 #endif
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
+#else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	do { } while (0)
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif /* SMP */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+/*
+ * For either of these options x86 doesn't have a strong TSO memory
+ * model and we should fall back to full barriers.
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#else /* regular x86 TSO memory ordering */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif
 
 /*
diff --git a/arch/xtensa/include/asm/barrier.h b/arch/xtensa/include/asm/barrier.h
index ef021677d53..e1ee6b51dfc 100644
--- a/arch/xtensa/include/asm/barrier.h
+++ b/arch/xtensa/include/asm/barrier.h
@@ -9,21 +9,14 @@
 #ifndef _XTENSA_SYSTEM_H
 #define _XTENSA_SYSTEM_H
 
-#define smp_read_barrier_depends() do { } while(0)
-#define read_barrier_depends() do { } while(0)
-
 #define mb()  ({ __asm__ __volatile__("memw" : : : "memory"); })
 #define rmb() barrier()
 #define wmb() mb()
 
 #ifdef CONFIG_SMP
 #error smp_* not defined
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
 #endif
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* _XTENSA_SYSTEM_H */