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

Pull locking updates from Ingo Molnar:
 "The main changes are:

   - 'qspinlock' support, enabled on x86: queued spinlocks - these are
     now the spinlock variant used by x86 as they outperform ticket
     spinlocks in every category.  (Waiman Long)

   - 'pvqspinlock' support on x86: paravirtualized variant of queued
     spinlocks.  (Waiman Long, Peter Zijlstra)

   - 'qrwlock' support, enabled on x86: queued rwlocks.  Similar to
     queued spinlocks, they are now the variant used by x86:

       CONFIG_ARCH_USE_QUEUED_SPINLOCKS=y
       CONFIG_QUEUED_SPINLOCKS=y
       CONFIG_ARCH_USE_QUEUED_RWLOCKS=y
       CONFIG_QUEUED_RWLOCKS=y

   - various lockdep fixlets

   - various locking primitives cleanups, further WRITE_ONCE()
     propagation"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  locking/lockdep: Remove hard coded array size dependency
  locking/qrwlock: Don't contend with readers when setting _QW_WAITING
  lockdep: Do not break user-visible string
  locking/arch: Rename set_mb() to smp_store_mb()
  locking/arch: Add WRITE_ONCE() to set_mb()
  rtmutex: Warn if trylock is called from hard/softirq context
  arch: Remove __ARCH_HAVE_CMPXCHG
  locking/rtmutex: Drop usage of __HAVE_ARCH_CMPXCHG
  locking/qrwlock: Rename QUEUE_RWLOCK to QUEUED_RWLOCKS
  locking/pvqspinlock: Rename QUEUED_SPINLOCK to QUEUED_SPINLOCKS
  locking/pvqspinlock: Replace xchg() by the more descriptive set_mb()
  locking/pvqspinlock, x86: Enable PV qspinlock for Xen
  locking/pvqspinlock, x86: Enable PV qspinlock for KVM
  locking/pvqspinlock, x86: Implement the paravirt qspinlock call patching
  locking/pvqspinlock: Implement simple paravirt support for the qspinlock
  locking/qspinlock: Revert to test-and-set on hypervisors
  locking/qspinlock: Use a simple write to grab the lock
  locking/qspinlock: Optimize for smaller NR_CPUS
  locking/qspinlock: Extract out code snippets for the next patch
  locking/qspinlock: Add pending bit
  ...

61 files changed, 1423 insertions, 102 deletions

diff --git a/Documentation/memory-barriers.txt b/Documentation/memory-barriers.txt
index 360841da3744..13feb697271f 100644
--- a/Documentation/memory-barriers.txt
+++ b/Documentation/memory-barriers.txt
@@ -1673,7 +1673,7 @@ CPU from reordering them.
 
 There are some more advanced barrier functions:
 
- (*) set_mb(var, value)
+ (*) smp_store_mb(var, value)
 
      This assigns the value to the variable and then inserts a full memory
      barrier after it, depending on the function.  It isn't guaranteed to
@@ -1985,7 +1985,7 @@ after it has altered the task state:
 	CPU 1
 	===============================
 	set_current_state();
-	  set_mb();
+	  smp_store_mb();
 	    STORE current->state
 	    <general barrier>
 	LOAD event_indicated
@@ -2026,7 +2026,7 @@ between the STORE to indicate the event and the STORE to set TASK_RUNNING:
 	CPU 1				CPU 2
 	===============================	===============================
 	set_current_state();		STORE event_indicated
-	  set_mb();			wake_up();
+	  smp_store_mb();		wake_up();
 	    STORE current->state	  <write barrier>
 	    <general barrier>		  STORE current->state
 	LOAD event_indicated
diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h
index 429e8cd0d78e..e5117766529e 100644
--- a/arch/alpha/include/asm/cmpxchg.h
+++ b/arch/alpha/include/asm/cmpxchg.h
@@ -66,6 +66,4 @@
 #undef __ASM__MB
 #undef ____cmpxchg
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #endif /* _ALPHA_CMPXCHG_H */
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index d2f81e6b8c1c..6c2327e1c732 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -81,7 +81,7 @@ do {									\
 #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)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_mb__before_atomic()	smp_mb()
 #define smp_mb__after_atomic()	smp_mb()
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 71f19c4dc0de..0fa47c4275cb 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -114,7 +114,7 @@ do {									\
 #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)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 #define nop()		asm volatile("nop");
 
 #define smp_mb__before_atomic()	smp_mb()
diff --git a/arch/avr32/include/asm/cmpxchg.h b/arch/avr32/include/asm/cmpxchg.h
index 962a6aeab787..366bbeaeb405 100644
--- a/arch/avr32/include/asm/cmpxchg.h
+++ b/arch/avr32/include/asm/cmpxchg.h
@@ -70,8 +70,6 @@ extern unsigned long __cmpxchg_u64_unsupported_on_32bit_kernels(
    if something tries to do an invalid cmpxchg().  */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				      unsigned long new, int size)
 {
diff --git a/arch/hexagon/include/asm/cmpxchg.h b/arch/hexagon/include/asm/cmpxchg.h
index 9e7802911a57..a6e34e2acbba 100644
--- a/arch/hexagon/include/asm/cmpxchg.h
+++ b/arch/hexagon/include/asm/cmpxchg.h
@@ -64,7 +64,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr,
  *  looks just like atomic_cmpxchg on our arch currently with a bunch of
  *  variable casting.
  */
-#define __HAVE_ARCH_CMPXCHG 1
 
 #define cmpxchg(ptr, old, new)					\
 ({								\
diff --git a/arch/ia64/include/asm/barrier.h b/arch/ia64/include/asm/barrier.h
index f6769eb2bbf9..843ba435e43b 100644
--- a/arch/ia64/include/asm/barrier.h
+++ b/arch/ia64/include/asm/barrier.h
@@ -77,12 +77,7 @@ do {									\
 	___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...
- */
-#define set_mb(var, value)	do { (var) = (value); mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 /*
  * The group barrier in front of the rsm & ssm are necessary to ensure
diff --git a/arch/ia64/include/uapi/asm/cmpxchg.h b/arch/ia64/include/uapi/asm/cmpxchg.h
index f35109b1d907..a0e3620f8f13 100644
--- a/arch/ia64/include/uapi/asm/cmpxchg.h
+++ b/arch/ia64/include/uapi/asm/cmpxchg.h
@@ -61,8 +61,6 @@ extern void ia64_xchg_called_with_bad_pointer(void);
  * indicated by comparing RETURN with OLD.
  */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 /*
  * This function doesn't exist, so you'll get a linker error
  * if something tries to do an invalid cmpxchg().
diff --git a/arch/m32r/include/asm/cmpxchg.h b/arch/m32r/include/asm/cmpxchg.h
index de651db20b43..14bf9b739dd2 100644
--- a/arch/m32r/include/asm/cmpxchg.h
+++ b/arch/m32r/include/asm/cmpxchg.h
@@ -107,8 +107,6 @@ __xchg_local(unsigned long x, volatile void *ptr, int size)
 	((__typeof__(*(ptr)))__xchg_local((unsigned long)(x), (ptr),	\
 			sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 static inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned int old, unsigned int new)
 {
diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
index bc755bc620ad..83b1df80f0ac 100644
--- a/arch/m68k/include/asm/cmpxchg.h
+++ b/arch/m68k/include/asm/cmpxchg.h
@@ -90,7 +90,6 @@ extern unsigned long __invalid_cmpxchg_size(volatile void *,
  * indicated by comparing RETURN with OLD.
  */
 #ifdef CONFIG_RMW_INSNS
-#define __HAVE_ARCH_CMPXCHG	1
 
 static inline unsigned long __cmpxchg(volatile void *p, unsigned long old,
 				      unsigned long new, int size)
diff --git a/arch/metag/include/asm/barrier.h b/arch/metag/include/asm/barrier.h
index d703d8e26a65..5a696e507930 100644
--- a/arch/metag/include/asm/barrier.h
+++ b/arch/metag/include/asm/barrier.h
@@ -84,7 +84,7 @@ static inline void fence(void)
 #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)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/metag/include/asm/cmpxchg.h b/arch/metag/include/asm/cmpxchg.h
index b1bc1be8540f..be29e3e44321 100644
--- a/arch/metag/include/asm/cmpxchg.h
+++ b/arch/metag/include/asm/cmpxchg.h
@@ -51,8 +51,6 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return old;
 }
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define cmpxchg(ptr, o, n)						\
 	({								\
 		__typeof__(*(ptr)) _o_ = (o);				\
diff --git a/arch/mips/include/asm/barrier.h b/arch/mips/include/asm/barrier.h
index 2b8bbbcb9be0..7ecba84656d4 100644
--- a/arch/mips/include/asm/barrier.h
+++ b/arch/mips/include/asm/barrier.h
@@ -112,8 +112,8 @@
 #define __WEAK_LLSC_MB		"		\n"
 #endif
 
-#define set_mb(var, value) \
-	do { var = value; smp_mb(); } while (0)
+#define smp_store_mb(var, value) \
+	do { WRITE_ONCE(var, value); smp_mb(); } while (0)
 
 #define smp_llsc_mb()	__asm__ __volatile__(__WEAK_LLSC_MB : : :"memory")
 
diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
index 412f945f1f5e..b71ab4a5fd50 100644
--- a/arch/mips/include/asm/cmpxchg.h
+++ b/arch/mips/include/asm/cmpxchg.h
@@ -138,8 +138,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz
 		__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))));	\
 })
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 #define __cmpxchg_asm(ld, st, m, old, new)				\
 ({									\
 	__typeof(*(m)) __ret;						\
diff --git a/arch/parisc/include/asm/cmpxchg.h b/arch/parisc/include/asm/cmpxchg.h
index dbd13354ec41..0a90b965cccb 100644
--- a/arch/parisc/include/asm/cmpxchg.h
+++ b/arch/parisc/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ __xchg(unsigned long x, __volatile__ void *ptr, int size)
 #define xchg(ptr, x) \
 	((__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr), sizeof(*(ptr))))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 /* bug catcher for when unsupported size is used - won't link */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
diff --git a/arch/powerpc/include/asm/barrier.h b/arch/powerpc/include/asm/barrier.h
index 1124f59b8df4..51ccc7232042 100644
--- a/arch/powerpc/include/asm/barrier.h
+++ b/arch/powerpc/include/asm/barrier.h
@@ -34,7 +34,7 @@
 #define rmb()  __asm__ __volatile__ ("sync" : : : "memory")
 #define wmb()  __asm__ __volatile__ ("sync" : : : "memory")
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#define smp_store_mb(var, value)	do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #ifdef __SUBARCH_HAS_LWSYNC
 #    define SMPWMB      LWSYNC
diff --git a/arch/powerpc/include/asm/cmpxchg.h b/arch/powerpc/include/asm/cmpxchg.h
index d463c68fe7f0..ad6263cffb0f 100644
--- a/arch/powerpc/include/asm/cmpxchg.h
+++ b/arch/powerpc/include/asm/cmpxchg.h
@@ -144,7 +144,6 @@ __xchg_local(volatile void *ptr, unsigned long x, unsigned int size)
  * Compare and exchange - if *p == old, set it to new,
  * and return the old value of *p.
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 static __always_inline unsigned long
 __cmpxchg_u32(volatile unsigned int *p, unsigned long old, unsigned long new)
diff --git a/arch/s390/include/asm/barrier.h b/arch/s390/include/asm/barrier.h
index 8d724718ec21..e6f8615a11eb 100644
--- a/arch/s390/include/asm/barrier.h
+++ b/arch/s390/include/asm/barrier.h
@@ -36,7 +36,7 @@
 #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)
+#define smp_store_mb(var, value)		do { WRITE_ONCE(var, value); mb(); } while (0)
 
 #define smp_store_release(p, v)						\
 do {									\
diff --git a/arch/s390/include/asm/cmpxchg.h b/arch/s390/include/asm/cmpxchg.h
index 4eadec466b8c..411464f4c97a 100644
--- a/arch/s390/include/asm/cmpxchg.h
+++ b/arch/s390/include/asm/cmpxchg.h
@@ -32,8 +32,6 @@
 	__old;								\
 })
 
-#define __HAVE_ARCH_CMPXCHG
-
 #define __cmpxchg_double_op(p1, p2, o1, o2, n1, n2, insn)		\
 ({									\
 	register __typeof__(*(p1)) __old1 asm("2") = (o1);		\
diff --git a/arch/score/include/asm/cmpxchg.h b/arch/score/include/asm/cmpxchg.h
index f384839c3ee5..cc3f6420b71c 100644
--- a/arch/score/include/asm/cmpxchg.h
+++ b/arch/score/include/asm/cmpxchg.h
@@ -42,8 +42,6 @@ static inline unsigned long __cmpxchg(volatile unsigned long *m,
 					(unsigned long)(o),	\
 					(unsigned long)(n)))
 
-#define __HAVE_ARCH_CMPXCHG	1
-
 #include <asm-generic/cmpxchg-local.h>
 
 #endif /* _ASM_SCORE_CMPXCHG_H */
diff --git a/arch/sh/include/asm/barrier.h b/arch/sh/include/asm/barrier.h
index 43715308b068..bf91037db4e0 100644
--- a/arch/sh/include/asm/barrier.h
+++ b/arch/sh/include/asm/barrier.h
@@ -32,7 +32,7 @@
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
 #endif
 
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/sh/include/asm/cmpxchg.h b/arch/sh/include/asm/cmpxchg.h
index f6bd1406b897..85c97b188d71 100644
--- a/arch/sh/include/asm/cmpxchg.h
+++ b/arch/sh/include/asm/cmpxchg.h
@@ -46,8 +46,6 @@ extern void __xchg_called_with_bad_pointer(void);
  * if something tries to do an invalid cmpxchg(). */
 extern void __cmpxchg_called_with_bad_pointer(void);
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long __cmpxchg(volatile void * ptr, unsigned long old,
 		unsigned long new, int size)
 {
diff --git a/arch/sparc/include/asm/barrier_64.h b/arch/sparc/include/asm/barrier_64.h
index 76648941fea7..809941e33e12 100644
--- a/arch/sparc/include/asm/barrier_64.h
+++ b/arch/sparc/include/asm/barrier_64.h
@@ -40,8 +40,8 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 #define dma_rmb()	rmb()
 #define dma_wmb()	wmb()
 
-#define set_mb(__var, __value) \
-	do { __var = __value; membar_safe("#StoreLoad"); } while(0)
+#define smp_store_mb(__var, __value) \
+	do { WRITE_ONCE(__var, __value); membar_safe("#StoreLoad"); } while(0)
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h
index d38b52dca216..83ffb83c5397 100644
--- a/arch/sparc/include/asm/cmpxchg_32.h
+++ b/arch/sparc/include/asm/cmpxchg_32.h
@@ -34,7 +34,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr, int
  *
  * Cribbed from <asm-parisc/atomic.h>
  */
-#define __HAVE_ARCH_CMPXCHG	1
 
 /* bug catcher for when unsupported size is used - won't link */
 void __cmpxchg_called_with_bad_pointer(void);
diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h
index 0e1ed6cfbf68..faa2f61058c2 100644
--- a/arch/sparc/include/asm/cmpxchg_64.h
+++ b/arch/sparc/include/asm/cmpxchg_64.h
@@ -65,8 +65,6 @@ static inline unsigned long __xchg(unsigned long x, __volatile__ void * ptr,
 
 #include <asm-generic/cmpxchg-local.h>
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 static inline unsigned long
 __cmpxchg_u32(volatile int *m, int old, int new)
 {
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index 7b11c5fadd42..0496970cef82 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -105,9 +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)
 
-/* Define this to indicate that cmpxchg is an efficient operation. */
-#define __HAVE_ARCH_CMPXCHG
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_TILE_ATOMIC_64_H */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 226d5696e1d1..4e986e809861 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -127,7 +127,8 @@ config X86
 	select MODULES_USE_ELF_RELA if X86_64
 	select CLONE_BACKWARDS if X86_32
 	select ARCH_USE_BUILTIN_BSWAP
-	select ARCH_USE_QUEUE_RWLOCK
+	select ARCH_USE_QUEUED_SPINLOCKS
+	select ARCH_USE_QUEUED_RWLOCKS
 	select OLD_SIGSUSPEND3 if X86_32 || IA32_EMULATION
 	select OLD_SIGACTION if X86_32
 	select COMPAT_OLD_SIGACTION if IA32_EMULATION
@@ -666,7 +667,7 @@ config PARAVIRT_DEBUG
 config PARAVIRT_SPINLOCKS
 	bool "Paravirtualization layer for spinlocks"
 	depends on PARAVIRT && SMP
-	select UNINLINE_SPIN_UNLOCK
+	select UNINLINE_SPIN_UNLOCK if !QUEUED_SPINLOCKS
 	---help---
 	  Paravirtualized spinlocks allow a pvops backend to replace the
 	  spinlock implementation with something virtualization-friendly
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 959e45b81fe2..e51a8f803f55 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -35,12 +35,12 @@
 #define smp_mb()	mb()
 #define smp_rmb()	dma_rmb()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+#define smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0)
 #else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
+#define smp_store_mb(var, value) do { WRITE_ONCE(var, value); barrier(); } while (0)
 #endif /* SMP */
 
 #define read_barrier_depends()		do { } while (0)
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index 99c105d78b7e..ad19841eddfe 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -4,8 +4,6 @@
 #include <linux/compiler.h>
 #include <asm/alternative.h> /* Provides LOCK_PREFIX */
 
-#define __HAVE_ARCH_CMPXCHG 1
-
 /*
  * Non-existant functions to indicate usage errors at link time
  * (or compile-time if the compiler implements __compiletime_error().
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 8957810ad7d1..d143bfad45d7 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -712,6 +712,31 @@ static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx,