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 tree got pretty big in this development cycle, but the net effect
  is pretty good:

    115 files changed, 673 insertions(+), 1522 deletions(-)

  The main changes were:

   - Rework and generalize the mutex code to remove per arch mutex
     primitives. (Peter Zijlstra)

   - Add vCPU preemption support: add an interface to query the
     preemption status of vCPUs and use it in locking primitives - this
     optimizes paravirt performance. (Pan Xinhui, Juergen Gross,
     Christian Borntraeger)

   - Introduce cpu_relax_yield() and remov cpu_relax_lowlatency() to
     clean up and improve the s390 lock yielding machinery and its core
     kernel impact. (Christian Borntraeger)

   - Micro-optimize mutexes some more. (Waiman Long)

   - Reluctantly add the to-be-deprecated mutex_trylock_recursive()
     interface on a temporary basis, to give the DRM code more time to
     get rid of its locking hacks. Any other users will be NAK-ed on
     sight. (We turned off the deprecation warning for the time being to
     not pollute the build log.) (Peter Zijlstra)

   - Improve the rtmutex code a bit, in light of recent long lived
     bugs/races. (Thomas Gleixner)

   - Misc fixes, cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (36 commits)
  x86/paravirt: Fix bool return type for PVOP_CALL()
  x86/paravirt: Fix native_patch()
  locking/ww_mutex: Use relaxed atomics
  locking/rtmutex: Explain locking rules for rt_mutex_proxy_unlock()/init_proxy_locked()
  locking/rtmutex: Get rid of RT_MUTEX_OWNER_MASKALL
  x86/paravirt: Optimize native pv_lock_ops.vcpu_is_preempted()
  locking/mutex: Break out of expensive busy-loop on {mutex,rwsem}_spin_on_owner() when owner vCPU is preempted
  locking/osq: Break out of spin-wait busy waiting loop for a preempted vCPU in osq_lock()
  Documentation/virtual/kvm: Support the vCPU preemption check
  x86/xen: Support the vCPU preemption check
  x86/kvm: Support the vCPU preemption check
  x86/kvm: Support the vCPU preemption check
  kvm: Introduce kvm_write_guest_offset_cached()
  locking/core, x86/paravirt: Implement vcpu_is_preempted(cpu) for KVM and Xen guests
  locking/spinlocks, s390: Implement vcpu_is_preempted(cpu)
  locking/core, powerpc: Implement vcpu_is_preempted(cpu)
  sched/core: Introduce the vcpu_is_preempted(cpu) interface
  sched/wake_q: Rename WAKE_Q to DEFINE_WAKE_Q
  locking/core: Provide common cpu_relax_yield() definition
  locking/mutex: Don't mark mutex_trylock_recursive() as deprecated, temporarily
  ...

7 files changed, 26 insertions, 245 deletions

diff --git a/arch/x86/include/asm/mutex.h b/arch/x86/include/asm/mutex.h
deleted file mode 100644
index 7d3a48275394..000000000000
--- a/arch/x86/include/asm/mutex.h
+++ /dev/null
@@ -1,5 +0,0 @@
-#ifdef CONFIG_X86_32
-# include <asm/mutex_32.h>
-#else
-# include <asm/mutex_64.h>
-#endif
diff --git a/arch/x86/include/asm/mutex_32.h b/arch/x86/include/asm/mutex_32.h
deleted file mode 100644
index e9355a84fc67..000000000000
--- a/arch/x86/include/asm/mutex_32.h
+++ /dev/null
@@ -1,110 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_32_H
-#define _ASM_X86_MUTEX_32_H
-
-#include <asm/alternative.h>
-
-/**
- *  __mutex_fastpath_lock - try to take the lock by moving the count
- *                          from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fn> if it
- * wasn't 1 originally. This function MUST leave the value lower than 1
- * even when the "1" assertion wasn't true.
- */
-#define __mutex_fastpath_lock(count, fail_fn)			\
-do {								\
-	unsigned int dummy;					\
-								\
-	typecheck(atomic_t *, count);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   decl (%%eax)\n"		\
-		     "   jns 1f	\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:\n"					\
-		     : "=a" (dummy)				\
-		     : "a" (count)				\
-		     : "memory", "ecx", "edx");			\
-} while (0)
-
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *
- * Change the count from 1 to a value lower than 1. This function returns 0
- * if the fastpath succeeds, or -1 otherwise.
- */
-static inline int __mutex_fastpath_lock_retval(atomic_t *count)
-{
-	if (unlikely(atomic_dec_return(count) < 0))
-		return -1;
-	else
-		return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the mutex from 0 to 1
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 0
- *
- * try to promote the mutex from 0 to 1. if it wasn't 0, call <fail_fn>.
- * In the failure case, this function is allowed to either set the value
- * to 1, or to set it to a value lower than 1.
- *
- * If the implementation sets it to a value of lower than 1, the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-#define __mutex_fastpath_unlock(count, fail_fn)			\
-do {								\
-	unsigned int dummy;					\
-								\
-	typecheck(atomic_t *, count);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   incl (%%eax)\n"		\
-		     "   jg	1f\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:\n"					\
-		     : "=a" (dummy)				\
-		     : "a" (count)				\
-		     : "memory", "ecx", "edx");			\
-} while (0)
-
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: fallback function
- *
- * Change the count from 1 to a value lower than 1, and return 0 (failure)
- * if it wasn't 1 originally, or return 1 (success) otherwise. This function
- * MUST leave the value lower than 1 even when the "1" assertion wasn't true.
- * Additionally, if the value was < 0 originally, this function must not leave
- * it to 0 on failure.
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
-					   int (*fail_fn)(atomic_t *))
-{
-	/* cmpxchg because it never induces a false contention state. */
-	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
-		return 1;
-
-	return 0;
-}
-
-#endif /* _ASM_X86_MUTEX_32_H */
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
deleted file mode 100644
index d9850758464e..000000000000
--- a/arch/x86/include/asm/mutex_64.h
+++ /dev/null
@@ -1,127 +0,0 @@
-/*
- * Assembly implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- *
- * started by Ingo Molnar:
- *
- *  Copyright (C) 2004, 2005, 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
- */
-#ifndef _ASM_X86_MUTEX_64_H
-#define _ASM_X86_MUTEX_64_H
-
-/**
- * __mutex_fastpath_lock - decrement and call function if negative
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is negative
- *
- * Atomically decrements @v and calls <fail_fn> if the result is negative.
- */
-#ifdef CC_HAVE_ASM_GOTO
-static inline void __mutex_fastpath_lock(atomic_t *v,
-					 void (*fail_fn)(atomic_t *))
-{
-	asm_volatile_goto(LOCK_PREFIX "   decl %0\n"
-			  "   jns %l[exit]\n"
-			  : : "m" (v->counter)
-			  : "memory", "cc"
-			  : exit);
-	fail_fn(v);
-exit:
-	return;
-}
-#else
-#define __mutex_fastpath_lock(v, fail_fn)			\
-do {								\
-	unsigned long dummy;					\
-								\
-	typecheck(atomic_t *, v);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   decl (%%rdi)\n"		\
-		     "   jns 1f		\n"			\
-		     "   call " #fail_fn "\n"			\
-		     "1:"					\
-		     : "=D" (dummy)				\
-		     : "D" (v)					\
-		     : "rax", "rsi", "rdx", "rcx",		\
-		       "r8", "r9", "r10", "r11", "memory");	\
-} while (0)
-#endif
-
-/**
- *  __mutex_fastpath_lock_retval - try to take the lock by moving the count
- *                                 from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *
- * Change the count from 1 to a value lower than 1. This function returns 0
- * if the fastpath succeeds, or -1 otherwise.
- */
-static inline int __mutex_fastpath_lock_retval(atomic_t *count)
-{
-	if (unlikely(atomic_dec_return(count) < 0))
-		return -1;
-	else
-		return 0;
-}
-
-/**
- * __mutex_fastpath_unlock - increment and call function if nonpositive
- * @v: pointer of type atomic_t
- * @fail_fn: function to call if the result is nonpositive
- *
- * Atomically increments @v and calls <fail_fn> if the result is nonpositive.
- */
-#ifdef CC_HAVE_ASM_GOTO
-static inline void __mutex_fastpath_unlock(atomic_t *v,
-					   void (*fail_fn)(atomic_t *))
-{
-	asm_volatile_goto(LOCK_PREFIX "   incl %0\n"
-			  "   jg %l[exit]\n"
-			  : : "m" (v->counter)
-			  : "memory", "cc"
-			  : exit);
-	fail_fn(v);
-exit:
-	return;
-}
-#else
-#define __mutex_fastpath_unlock(v, fail_fn)			\
-do {								\
-	unsigned long dummy;					\
-								\
-	typecheck(atomic_t *, v);				\
-	typecheck_fn(void (*)(atomic_t *), fail_fn);		\
-								\
-	asm volatile(LOCK_PREFIX "   incl (%%rdi)\n"		\
-		     "   jg 1f\n"				\
-		     "   call " #fail_fn "\n"			\
-		     "1:"					\
-		     : "=D" (dummy)				\
-		     : "D" (v)					\
-		     : "rax", "rsi", "rdx", "rcx",		\
-		       "r8", "r9", "r10", "r11", "memory");	\
-} while (0)
-#endif
-
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: fallback function
- *
- * Change the count from 1 to 0 and return 1 (success), or return 0 (failure)
- * if it wasn't 1 originally. [the fallback function is never used on
- * x86_64, because all x86_64 CPUs have a CMPXCHG instruction.]
- */
-static inline int __mutex_fastpath_trylock(atomic_t *count,
-					   int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
-		return 1;
-
-	return 0;
-}
-
-#endif /* _ASM_X86_MUTEX_64_H */
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index ce932812f142..6108b1fada2b 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -678,6 +678,11 @@ static __always_inline void pv_kick(int cpu)
 	PVOP_VCALL1(pv_lock_ops.kick, cpu);
 }
 
+static __always_inline bool pv_vcpu_is_preempted(int cpu)
+{
+	return PVOP_CALLEE1(bool, pv_lock_ops.vcpu_is_preempted, cpu);
+}
+
 #endif /* SMP && PARAVIRT_SPINLOCKS */
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 0f400c0e4979..3f2bc0f0d3e8 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -310,6 +310,8 @@ struct pv_lock_ops {
 
 	void (*wait)(u8 *ptr, u8 val);
 	void (*kick)(int cpu);
+
+	struct paravirt_callee_save vcpu_is_preempted;
 };
 
 /* This contains all the paravirt structures: we get a convenient
@@ -508,6 +510,18 @@ int paravirt_disable_iospace(void);
 #define PVOP_TEST_NULL(op)	((void)op)
 #endif
 
+#define PVOP_RETMASK(rettype)						\
+	({	unsigned long __mask = ~0UL;				\
+		switch (sizeof(rettype)) {				\
+		case 1: __mask =       0xffUL; break;			\
+		case 2: __mask =     0xffffUL; break;			\
+		case 4: __mask = 0xffffffffUL; break;			\
+		default: break;						\
+		}							\
+		__mask;							\
+	})
+
+
 #define ____PVOP_CALL(rettype, op, clbr, call_clbr, extra_clbr,		\
 		      pre, post, ...)					\
 	({								\
@@ -535,7 +549,7 @@ int paravirt_disable_iospace(void);
 				       paravirt_clobber(clbr),		\
 				       ##__VA_ARGS__			\
 				     : "memory", "cc" extra_clbr);	\
-			__ret = (rettype)__eax;				\
+			__ret = (rettype)(__eax & PVOP_RETMASK(rettype));	\
 		}							\
 		__ret;							\
 	})
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 984a7bf17f6a..c84605bb2a15 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -588,8 +588,6 @@ static __always_inline void cpu_relax(void)
 	rep_nop();
 }
 
-#define cpu_relax_lowlatency() cpu_relax()
-
 /* Stop speculative execution and prefetching of modified code. */
 static inline void sync_core(void)
 {
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index eaba08076030..c343ab52579f 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -32,6 +32,12 @@ static inline void queued_spin_unlock(struct qspinlock *lock)
 {
 	pv_queued_spin_unlock(lock);
 }
+
+#define vcpu_is_preempted vcpu_is_preempted
+static inline bool vcpu_is_preempted(int cpu)
+{
+	return pv_vcpu_is_preempted(cpu);
+}
 #else
 static inline void queued_spin_unlock(struct qspinlock *lock)
 {