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

Pull core locking updates from Ingo Molnar:
 "The main changes in this cycle were:

   - reduced/streamlined smp_mb__*() interface that allows more usecases
     and makes the existing ones less buggy, especially in rarer
     architectures

   - add rwsem implementation comments

   - bump up lockdep limits"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  rwsem: Add comments to explain the meaning of the rwsem's count field
  lockdep: Increase static allocations
  arch: Mass conversion of smp_mb__*()
  arch,doc: Convert smp_mb__*()
  arch,xtensa: Convert smp_mb__*()
  arch,x86: Convert smp_mb__*()
  arch,tile: Convert smp_mb__*()
  arch,sparc: Convert smp_mb__*()
  arch,sh: Convert smp_mb__*()
  arch,score: Convert smp_mb__*()
  arch,s390: Convert smp_mb__*()
  arch,powerpc: Convert smp_mb__*()
  arch,parisc: Convert smp_mb__*()
  arch,openrisc: Convert smp_mb__*()
  arch,mn10300: Convert smp_mb__*()
  arch,mips: Convert smp_mb__*()
  arch,metag: Convert smp_mb__*()
  arch,m68k: Convert smp_mb__*()
  arch,m32r: Convert smp_mb__*()
  arch,ia64: Convert smp_mb__*()
  ...

arch/ia64/include/asm/atomic.h

@@ -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 */

arch/ia64/include/asm/barrier.h

@@ -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!

arch/ia64/include/asm/bitops.h

@@ -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

arch/ia64/include/uapi/asm/cmpxchg.h

@@ -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))