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
  ...

Documentation/virtual/kvm/msr.txt

@@ -208,7 +208,9 @@ MSR_KVM_STEAL_TIME: 0x4b564d03
 		__u64 steal;
 		__u32 version;
 		__u32 flags;
-		__u32 pad[12];
+		__u8  preempted;
+		__u8  u8_pad[3];
+		__u32 pad[11];
 	}
 
 	whose data will be filled in by the hypervisor periodically. Only one
@@ -232,6 +234,11 @@ MSR_KVM_STEAL_TIME: 0x4b564d03
 		nanoseconds. Time during which the vcpu is idle, will not be
 		reported as steal time.
 
+		preempted: indicate the vCPU who owns this struct is running or
+		not. Non-zero values mean the vCPU has been preempted. Zero
+		means the vCPU is not preempted. NOTE, it is always zero if the
+		the hypervisor doesn't support this field.
+
 MSR_KVM_EOI_EN: 0x4b564d04
 	data: Bit 0 is 1 when PV end of interrupt is enabled on the vcpu; 0
 	when disabled.  Bit 1 is reserved and must be zero.  When PV end of

arch/alpha/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/alpha/include/asm/processor.h

@@ -58,7 +58,6 @@ unsigned long get_wchan(struct task_struct *p);
   ((tsk) == current ? rdusp() : task_thread_info(tsk)->pcb.usp)
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 #define ARCH_HAS_PREFETCH
 #define ARCH_HAS_PREFETCHW

arch/arc/include/asm/mutex.h

-/*
- * 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.
- */
-
-/*
- * xchg() based mutex fast path maintains a state of 0 or 1, as opposed to
- * atomic dec based which can "count" any number of lock contenders.
- * This ideally needs to be fixed in core, but for now switching to dec ver.
- */
-#if defined(CONFIG_SMP) && (CONFIG_NR_CPUS > 2)
-#include <asm-generic/mutex-dec.h>
-#else
-#include <asm-generic/mutex-xchg.h>
-#endif

arch/arc/include/asm/processor.h

@@ -60,15 +60,12 @@ struct task_struct;
 #ifndef CONFIG_EZNPS_MTM_EXT
 
 #define cpu_relax()		barrier()
-#define cpu_relax_lowlatency()	cpu_relax()
 
 #else
 
 #define cpu_relax()     \
 	__asm__ __volatile__ (".word %0" : : "i"(CTOP_INST_SCHD_RW) : "memory")
 
-#define cpu_relax_lowlatency()	barrier()
-
 #endif
 
 #define copy_segments(tsk, mm)      do { } while (0)

arch/arm/include/asm/mutex.h

-/*
- * arch/arm/include/asm/mutex.h
- *
- * ARM optimized mutex locking primitives
- *
- * Please look into asm-generic/mutex-xchg.h for a formal definition.
- */
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_H
-/*
- * On pre-ARMv6 hardware this results in a swp-based implementation,
- * which is the most efficient. For ARMv6+, we have exclusive memory
- * accessors and use atomic_dec to avoid the extra xchg operations
- * on the locking slowpaths.
- */
-#if __LINUX_ARM_ARCH__ < 6
-#include <asm-generic/mutex-xchg.h>
-#else
-#include <asm-generic/mutex-dec.h>
-#endif
-#endif	/* _ASM_MUTEX_H */

arch/arm/include/asm/processor.h

@@ -82,8 +82,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define cpu_relax()			barrier()
 #endif
 
-#define cpu_relax_lowlatency()                cpu_relax()
-
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)
 

arch/arm64/include/asm/Kbuild

@@ -24,7 +24,6 @@ generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += msi.h
-generic-y += mutex.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h

arch/arm64/include/asm/processor.h

@@ -149,8 +149,6 @@ static inline void cpu_relax(void)
 	asm volatile("yield" ::: "memory");
 }
 
-#define cpu_relax_lowlatency()                cpu_relax()
-
 /* Thread switching */
 extern struct task_struct *cpu_switch_to(struct task_struct *prev,
 					 struct task_struct *next);

arch/avr32/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/avr32/include/asm/processor.h

@@ -92,7 +92,6 @@ extern struct avr32_cpuinfo boot_cpu_data;
 #define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
 
 #define cpu_relax()		barrier()
-#define cpu_relax_lowlatency()        cpu_relax()
 #define cpu_sync_pipeline()	asm volatile("sub pc, -2" : : : "memory")
 
 struct cpu_context {

arch/blackfin/include/asm/Kbuild

@@ -24,7 +24,6 @@ generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += mman.h
 generic-y += msgbuf.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += pgalloc.h

arch/blackfin/include/asm/processor.h

@@ -92,7 +92,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define	KSTK_ESP(tsk)	((tsk) == current ? rdusp() : (tsk)->thread.usp)
 
 #define cpu_relax()    	smp_mb()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /* Get the Silicon Revision of the chip */
 static inline uint32_t __pure bfin_revid(void)

arch/c6x/include/asm/mutex.h

-#ifndef _ASM_C6X_MUTEX_H
-#define _ASM_C6X_MUTEX_H
-
-#include <asm-generic/mutex-null.h>
-
-#endif /* _ASM_C6X_MUTEX_H */

arch/c6x/include/asm/processor.h

@@ -121,7 +121,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(task)	(task_pt_regs(task)->sp)
 
 #define cpu_relax()		do { } while (0)
-#define cpu_relax_lowlatency()        cpu_relax()
 
 extern const struct seq_operations cpuinfo_op;
 

arch/cris/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/cris/include/asm/processor.h

@@ -63,7 +63,6 @@ static inline void release_thread(struct task_struct *dead_task)
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 void default_idle(void);
 

arch/frv/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/frv/include/asm/processor.h

@@ -107,7 +107,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define	KSTK_ESP(tsk)	((tsk)->thread.frame0->sp)
 
 #define cpu_relax() barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /* data cache prefetch */
 #define ARCH_HAS_PREFETCH

arch/h8300/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/h8300/include/asm/processor.h

@@ -127,7 +127,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define	KSTK_ESP(tsk)	((tsk) == current ? rdusp() : (tsk)->thread.usp)
 
 #define cpu_relax()    barrier()
-#define cpu_relax_lowlatency()	cpu_relax()
 
 #define HARD_RESET_NOW() ({		\
 	local_irq_disable();		\

arch/hexagon/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-#include <asm-generic/mutex-xchg.h>

arch/hexagon/include/asm/processor.h

@@ -56,7 +56,6 @@ struct thread_struct {
 }
 
 #define cpu_relax() __vmyield()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * Decides where the kernel will search for a free chunk of vm space during

arch/ia64/include/asm/mutex.h

-/*
- * ia64 implementation of the mutex fastpath.
- *
- * Copyright (C) 2006 Ken Chen <kenneth.w.chen@intel.com>
- *
- */
-
-#ifndef _ASM_MUTEX_H
-#define _ASM_MUTEX_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
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function MUST leave the value lower than
- * 1 even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(ia64_fetchadd4_acq(count, -1) != 1))
-		fail_fn(count);
-}
-
-/**
- *  __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(ia64_fetchadd4_acq(count, -1) != 1))
-		return -1;
-	return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the count 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 count 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, then the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int ret = ia64_fetchadd4_rel(count, 1);
-	if (unlikely(ret < 0))
-		fail_fn(count);
-}
-
-#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.
- *
- * If the architecture has no effective trylock variant, it should call the
- * <fail_fn> spinlock-based trylock variant unconditionally.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	if (atomic_read(count) == 1 && cmpxchg_acq(count, 1, 0) == 1)
-		return 1;
-	return 0;
-}
-
-#endif

arch/ia64/include/asm/processor.h

@@ -547,7 +547,6 @@ ia64_eoi (void)
 }
 
 #define cpu_relax()	ia64_hint(ia64_hint_pause)
-#define cpu_relax_lowlatency() cpu_relax()
 
 static inline int
 ia64_get_irr(unsigned int vector)

arch/m32r/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/m32r/include/asm/processor.h

@@ -133,6 +133,5 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)  ((tsk)->thread.sp)
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 #endif /* _ASM_M32R_PROCESSOR_H */

arch/m68k/include/asm/Kbuild

@@ -20,7 +20,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += mman.h
-generic-y += mutex.h
 generic-y += percpu.h
 generic-y += preempt.h
 generic-y += resource.h

arch/m68k/include/asm/processor.h

@@ -156,6 +156,5 @@ unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk)	((struct pt_regs *) ((tsk)->thread.esp0))
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 #endif

arch/metag/include/asm/Kbuild

@@ -27,7 +27,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h

arch/metag/include/asm/processor.h

@@ -152,7 +152,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define user_stack_pointer(regs)        ((regs)->ctx.AX[0].U0)
 
 #define cpu_relax()     barrier()
-#define cpu_relax_lowlatency()  cpu_relax()
 
 extern void setup_priv(void);
 

arch/microblaze/include/asm/mutex.h

-#include <asm-generic/mutex-dec.h>

arch/microblaze/include/asm/processor.h

@@ -22,7 +22,6 @@
 extern const struct seq_operations cpuinfo_op;
 
 # define cpu_relax()		barrier()
-# define cpu_relax_lowlatency()	cpu_relax()
 
 #define task_pt_regs(tsk) \
 		(((struct pt_regs *)(THREAD_SIZE + task_stack_page(tsk))) - 1)

arch/mips/include/asm/Kbuild

@@ -9,7 +9,6 @@ generic-y += irq_work.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mutex.h
 generic-y += parport.h
 generic-y += percpu.h
 generic-y += preempt.h

arch/mips/include/asm/processor.h

@@ -389,7 +389,6 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_STATUS(tsk) (task_pt_regs(tsk)->cp0_status)
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * Return_address is a replacement for __builtin_return_address(count)

arch/mn10300/include/asm/mutex.h

-/* MN10300 Mutex fastpath
- *
- * 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.
- *
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-#include <asm-generic/mutex-null.h>

arch/mn10300/include/asm/processor.h

@@ -69,7 +69,6 @@ extern void print_cpu_info(struct mn10300_cpuinfo *);
 extern void dodgy_tsc(void);
 
 #define cpu_relax() barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * User space process size: 1.75GB (default).

arch/nios2/include/asm/mutex.h

-#include <asm-generic/mutex-dec.h>

arch/nios2/include/asm/processor.h

@@ -88,7 +88,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)	((tsk)->thread.kregs->sp)
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency()  cpu_relax()
 
 #endif /* __ASSEMBLY__ */
 

arch/openrisc/include/asm/mutex.h

-/*
- * OpenRISC Linux
- *
- * Linux architectural port borrowing liberally from similar works of
- * others.  All original copyrights apply as per the original source
- * declaration.
- *
- * OpenRISC implementation:
- * Copyright (C) 2003 Matjaz Breskvar <phoenix@bsemi.com>
- * Copyright (C) 2010-2011 Jonas Bonn <jonas@southpole.se>
- * et al.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- */
-
-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/openrisc/include/asm/processor.h

@@ -92,7 +92,6 @@ extern unsigned long thread_saved_pc(struct task_struct *t);
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_OPENRISC_PROCESSOR_H */

arch/parisc/include/asm/Kbuild

@@ -16,7 +16,6 @@ generic-y += local.h
 generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += percpu.h
 generic-y += poll.h

arch/parisc/include/asm/processor.h

@@ -309,7 +309,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)	((tsk)->thread.regs.gr[30])
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /*
  * parisc_requires_coherency() is used to identify the combined VIPT/PIPT

arch/powerpc/include/asm/mutex.h

-/*
- * Optimised mutex implementation of include/asm-generic/mutex-dec.h algorithm
- */
-#ifndef _ASM_POWERPC_MUTEX_H
-#define _ASM_POWERPC_MUTEX_H
-
-static inline int __mutex_cmpxchg_lock(atomic_t *v, int old, int new)
-{
-	int t;
-
-	__asm__ __volatile__ (
-"1:	lwarx	%0,0,%1		# mutex trylock\n\
-	cmpw	0,%0,%2\n\
-	bne-	2f\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%3,0,%1\n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	"\n\
-2:"
-	: "=&r" (t)
-	: "r" (&v->counter), "r" (old), "r" (new)
-	: "cc", "memory");
-
-	return t;
-}
-
-static inline int __mutex_dec_return_lock(atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-"1:	lwarx	%0,0,%1		# mutex lock\n\
-	addic	%0,%0,-1\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1\n\
-	bne-	1b"
-	PPC_ACQUIRE_BARRIER
-	: "=&r" (t)
-	: "r" (&v->counter)
-	: "cc", "memory");
-
-	return t;
-}
-
-static inline int __mutex_inc_return_unlock(atomic_t *v)
-{
-	int t;
-
-	__asm__ __volatile__(
-	PPC_RELEASE_BARRIER
-"1:	lwarx	%0,0,%1		# mutex unlock\n\
-	addic	%0,%0,1\n"
-	PPC405_ERR77(0,%1)
-"	stwcx.	%0,0,%1 \n\
-	bne-	1b"
-	: "=&r" (t)
-	: "r" (&v->counter)
-	: "cc", "memory");
-
-	return t;
-}
-
-/**
- *  __mutex_fastpath_lock - try to take the lock by moving the count
- *                          from 1 to a 0 value
- *  @count: pointer of type atomic_t
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function MUST leave the value lower than
- * 1 even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(__mutex_dec_return_lock(count) < 0))
-		fail_fn(count);
-}
-
-/**
- *  __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(__mutex_dec_return_lock(count) < 0))
-		return -1;
-	return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the count 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 count 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.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(__mutex_inc_return_unlock(count) <= 0))
-		fail_fn(count);
-}
-
-#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 if the count
- * was not 1, then return 0 (failure).
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_read(count) == 1 && __mutex_cmpxchg_lock(count, 1, 0) == 1))
-		return 1;
-	return 0;
-}
-
-#endif

arch/powerpc/include/asm/processor.h

@@ -404,8 +404,6 @@ static inline unsigned long __pack_fe01(unsigned int fpmode)
 #define cpu_relax()	barrier()
 #endif
 
-#define cpu_relax_lowlatency() cpu_relax()
-
 /* Check that a certain kernel stack pointer is valid in task_struct p */
 int validate_sp(unsigned long sp, struct task_struct *p,
                        unsigned long nbytes);

arch/powerpc/include/asm/spinlock.h

@@ -52,6 +52,14 @@
 #define SYNC_IO
 #endif
 
+#ifdef CONFIG_PPC_PSERIES
+#define vcpu_is_preempted vcpu_is_preempted
+static inline bool vcpu_is_preempted(int cpu)
+{
+	return !!(be32_to_cpu(lppaca_of(cpu).yield_count) & 1);
+}
+#endif
+
 static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 {
 	return lock.slock == 0;

arch/s390/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/s390/include/asm/processor.h

@@ -234,9 +234,10 @@ static inline unsigned short stap(void)
 /*
  * Give up the time slice of the virtual PU.
  */
-void cpu_relax(void);
+#define cpu_relax_yield cpu_relax_yield
+void cpu_relax_yield(void);
 
-#define cpu_relax_lowlatency()  barrier()
+#define cpu_relax() barrier()
 
 #define ECAG_CACHE_ATTRIBUTE	0
 #define ECAG_CPU_ATTRIBUTE	1

arch/s390/include/asm/spinlock.h

@@ -23,6 +23,14 @@ _raw_compare_and_swap(unsigned int *lock, unsigned int old, unsigned int new)
 	return __sync_bool_compare_and_swap(lock, old, new);
 }
 
+#ifndef CONFIG_SMP
+static inline bool arch_vcpu_is_preempted(int cpu) { return false; }
+#else
+bool arch_vcpu_is_preempted(int cpu);
+#endif
+
+#define vcpu_is_preempted arch_vcpu_is_preempted
+
 /*
  * Simple spin lock operations.  There are two variants, one clears IRQ's
  * on the local processor, one does not.

arch/s390/kernel/processor.c

@@ -53,7 +53,7 @@ void s390_update_cpu_mhz(void)
 		on_each_cpu(update_cpu_mhz, NULL, 0);
 }
 
-void notrace cpu_relax(void)
+void notrace cpu_relax_yield(void)
 {
 	if (!smp_cpu_mtid && MACHINE_HAS_DIAG44) {
 		diag_stat_inc(DIAG_STAT_X044);
@@ -61,7 +61,7 @@ void notrace cpu_relax(void)
 	}
 	barrier();
 }
-EXPORT_SYMBOL(cpu_relax);
+EXPORT_SYMBOL(cpu_relax_yield);
 
 /*
  * cpu_init - initializes state that is per-CPU.

arch/s390/kernel/smp.c

@@ -368,10 +368,15 @@ int smp_find_processor_id(u16 address)
 	return -1;
 }
 
-int smp_vcpu_scheduled(int cpu)
+bool arch_vcpu_is_preempted(int cpu)
 {
-	return pcpu_running(pcpu_devices + cpu);
+	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
+		return false;
+	if (pcpu_running(pcpu_devices + cpu))
+		return false;
+	return true;
 }
+EXPORT_SYMBOL(arch_vcpu_is_preempted);
 
 void smp_yield_cpu(int cpu)
 {

arch/s390/lib/spinlock.c

@@ -37,15 +37,6 @@ static inline void _raw_compare_and_delay(unsigned int *lock, unsigned int old)
 	asm(".insn rsy,0xeb0000000022,%0,0,%1" : : "d" (old), "Q" (*lock));
 }
 
-static inline int cpu_is_preempted(int cpu)
-{
-	if (test_cpu_flag_of(CIF_ENABLED_WAIT, cpu))
-		return 0;
-	if (smp_vcpu_scheduled(cpu))
-		return 0;
-	return 1;
-}
-
 void arch_spin_lock_wait(arch_spinlock_t *lp)
 {
 	unsigned int cpu = SPINLOCK_LOCKVAL;
@@ -62,7 +53,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 			continue;
 		}
 		/* First iteration: check if the lock owner is running. */
-		if (first_diag && cpu_is_preempted(~owner)) {
+		if (first_diag && arch_vcpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 			continue;
@@ -81,7 +72,7 @@ void arch_spin_lock_wait(arch_spinlock_t *lp)
 		 * yield the CPU unconditionally. For LPAR rely on the
 		 * sense running status.
 		 */
-		if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) {
+		if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 		}
@@ -108,7 +99,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 			continue;
 		}
 		/* Check if the lock owner is running. */
-		if (first_diag && cpu_is_preempted(~owner)) {
+		if (first_diag && arch_vcpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 			continue;
@@ -127,7 +118,7 @@ void arch_spin_lock_wait_flags(arch_spinlock_t *lp, unsigned long flags)
 		 * yield the CPU unconditionally. For LPAR rely on the
 		 * sense running status.
 		 */
-		if (!MACHINE_IS_LPAR || cpu_is_preempted(~owner)) {
+		if (!MACHINE_IS_LPAR || arch_vcpu_is_preempted(~owner)) {
 			smp_yield_cpu(~owner);
 			first_diag = 0;
 		}
@@ -165,7 +156,7 @@ void _raw_read_lock_wait(arch_rwlock_t *rw)
 	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			if (owner && cpu_is_preempted(~owner))
+			if (owner && arch_vcpu_is_preempted(~owner))
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
@@ -211,7 +202,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw, unsigned int prev)
 	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			if (owner && cpu_is_preempted(~owner))
+			if (owner && arch_vcpu_is_preempted(~owner))
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
@@ -241,7 +232,7 @@ void _raw_write_lock_wait(arch_rwlock_t *rw)
 	owner = 0;
 	while (1) {
 		if (count-- <= 0) {
-			if (owner && cpu_is_preempted(~owner))
+			if (owner && arch_vcpu_is_preempted(~owner))
 				smp_yield_cpu(~owner);
 			count = spin_retry;
 		}
@@ -285,7 +276,7 @@ void arch_lock_relax(unsigned int cpu)
 {
 	if (!cpu)
 		return;
-	if (MACHINE_IS_LPAR && !cpu_is_preempted(~cpu))
+	if (MACHINE_IS_LPAR && !arch_vcpu_is_preempted(~cpu))
 		return;
 	smp_yield_cpu(~cpu);
 }

arch/score/include/asm/mutex.h

-#ifndef _ASM_SCORE_MUTEX_H
-#define _ASM_SCORE_MUTEX_H
-
-#include <asm-generic/mutex-dec.h>
-
-#endif /* _ASM_SCORE_MUTEX_H */

arch/score/include/asm/processor.h

@@ -24,7 +24,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define current_text_addr() ({ __label__ _l; _l: &&_l; })
 
 #define cpu_relax()		barrier()
-#define cpu_relax_lowlatency()        cpu_relax()
 #define release_thread(thread)	do {} while (0)
 
 /*

arch/sh/include/asm/mutex-llsc.h

-/*
- * arch/sh/include/asm/mutex-llsc.h
- *
- * SH-4A optimized mutex locking primitives
- *
- * Please look into asm-generic/mutex-xchg.h for a formal definition.
- */
-#ifndef __ASM_SH_MUTEX_LLSC_H
-#define __ASM_SH_MUTEX_LLSC_H
-
-/*
- * Attempting to lock a mutex on SH4A is done like in ARMv6+ architecure.
- * with a bastardized atomic decrement (it is not a reliable atomic decrement
- * but it satisfies the defined semantics for our purpose, while being
- * smaller and faster than a real atomic decrement or atomic swap.
- * The idea is to attempt  decrementing the lock value only once. If once
- * decremented it isn't zero, or if its store-back fails due to a dispute
- * on the exclusive store, we simply bail out immediately through the slow
- * path where the lock will be reattempted until it succeeds.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __done, __res;
-
-	__asm__ __volatile__ (
-		"movli.l	@%2, %0	\n"
-		"add		#-1, %0	\n"
-		"movco.l	%0, @%2	\n"
-		"movt		%1	\n"
-		: "=&z" (__res), "=&r" (__done)
-		: "r" (&(count)->counter)
-		: "t");
-
-	if (unlikely(!__done || __res != 0))
-		fail_fn(count);
-}
-
-static inline int
-__mutex_fastpath_lock_retval(atomic_t *count)
-{
-	int __done, __res;
-
-	__asm__ __volatile__ (
-		"movli.l	@%2, %0	\n"
-		"add		#-1, %0	\n"
-		"movco.l	%0, @%2	\n"
-		"movt		%1	\n"
-		: "=&z" (__res), "=&r" (__done)
-		: "r" (&(count)->counter)
-		: "t");
-
-	if (unlikely(!__done || __res != 0))
-		__res = -1;
-
-	return __res;
-}
-
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	int __done, __res;
-
-	__asm__ __volatile__ (
-		"movli.l	@%2, %0	\n\t"
-		"add		#1, %0	\n\t"
-		"movco.l	%0, @%2 \n\t"
-		"movt		%1	\n\t"
-		: "=&z" (__res), "=&r" (__done)
-		: "r" (&(count)->counter)
-		: "t");
-
-	if (unlikely(!__done || __res <= 0))
-		fail_fn(count);
-}
-
-/*
- * If the unlock was done on a contended lock, or if the unlock simply fails
- * then the mutex remains locked.
- */
-#define __mutex_slowpath_needs_to_unlock()	1
-
-/*
- * For __mutex_fastpath_trylock we do an atomic decrement and check the
- * result and put it in the __res variable.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int __res, __orig;
-
-	__asm__ __volatile__ (
-		"1: movli.l	@%2, %0		\n\t"
-		"dt		%0		\n\t"
-		"movco.l	%0,@%2		\n\t"
-		"bf		1b		\n\t"
-		"cmp/eq		#0,%0		\n\t"
-		"bt		2f		\n\t"
-		"mov		#0, %1		\n\t"
-		"bf		3f		\n\t"
-		"2: mov		#1, %1		\n\t"
-		"3:				"
-		: "=&z" (__orig), "=&r" (__res)
-		: "r" (&count->counter)
-		: "t");
-
-	return __res;
-}
-#endif /* __ASM_SH_MUTEX_LLSC_H */

arch/sh/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-#if defined(CONFIG_CPU_SH4A)
-#include <asm/mutex-llsc.h>
-#else
-#include <asm-generic/mutex-dec.h>
-#endif

arch/sh/include/asm/processor.h

@@ -97,7 +97,6 @@ extern struct sh_cpuinfo cpu_data[];
 
 #define cpu_sleep()	__asm__ __volatile__ ("sleep" : : : "memory")
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 void default_idle(void);
 void stop_this_cpu(void *);

arch/sparc/include/asm/Kbuild

@@ -15,7 +15,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += module.h
-generic-y += mutex.h
 generic-y += preempt.h
 generic-y += rwsem.h
 generic-y += serial.h

arch/sparc/include/asm/processor_32.h

@@ -119,7 +119,6 @@ extern struct task_struct *last_task_used_math;
 int do_mathemu(struct pt_regs *regs, struct task_struct *fpt);
 
 #define cpu_relax()	barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 extern void (*sparc_idle)(void);
 

arch/sparc/include/asm/processor_64.h

@@ -216,7 +216,6 @@ unsigned long get_wchan(struct task_struct *task);
 				     "nop\n\t"				\
 				     ".previous"			\
 				     ::: "memory")
-#define cpu_relax_lowlatency() cpu_relax()
 
 /* Prefetch support.  This is tuned for UltraSPARC-III and later.
  * UltraSPARC-I will treat these as nops, and UltraSPARC-II has

arch/tile/include/asm/Kbuild

@@ -21,7 +21,6 @@ generic-y += local64.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
 generic-y += msgbuf.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += parport.h
 generic-y += poll.h

arch/tile/include/asm/processor.h

@@ -264,8 +264,6 @@ static inline void cpu_relax(void)
 	barrier();
 }
 
-#define cpu_relax_lowlatency() cpu_relax()
-
 /* Info on this processor (see fs/proc/cpuinfo.c) */
 struct seq_operations;
 extern const struct seq_operations cpuinfo_op;

arch/um/include/asm/Kbuild

@@ -17,7 +17,6 @@ generic-y += irq_work.h
 generic-y += kdebug.h
 generic-y += mcs_spinlock.h
 generic-y += mm-arch-hooks.h
-generic-y += mutex.h
 generic-y += param.h
 generic-y += pci.h
 generic-y += percpu.h

arch/unicore32/include/asm/mutex.h

-/*
- * linux/arch/unicore32/include/asm/mutex.h
- *
- * Code specific to PKUnity SoC and UniCore ISA
- *
- * Copyright (C) 2001-2010 GUAN Xue-tao
- *
- * 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.
- *
- * UniCore optimized mutex locking primitives
- *
- * Please look into asm-generic/mutex-xchg.h for a formal definition.
- */
-#ifndef __UNICORE_MUTEX_H__
-#define __UNICORE_MUTEX_H__
-
-# include <asm-generic/mutex-xchg.h>
-#endif

arch/unicore32/include/asm/processor.h

@@ -71,7 +71,6 @@ extern void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
 #define cpu_relax()			barrier()
-#define cpu_relax_lowlatency()                cpu_relax()
 
 #define task_pt_regs(p) \
 	((struct pt_regs *)(THREAD_START_SP + task_stack_page(p)) - 1)

arch/x86/include/asm/mutex.h

-#ifdef CONFIG_X86_32
-# include <asm/mutex_32.h>
-#else
-# include <asm/mutex_64.h>
-#endif

arch/x86/include/asm/mutex_32.h

-/*
- * 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 */

arch/x86/include/asm/mutex_64.h

-/*
- * 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 */

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

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;							\
 	})

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)
 {

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)
 {

arch/x86/include/uapi/asm/kvm_para.h

@@ -45,7 +45,9 @@ struct kvm_steal_time {
 	__u64 steal;
 	__u32 version;
 	__u32 flags;
-	__u32 pad[12];
+	__u8  preempted;
+	__u8  u8_pad[3];
+	__u32 pad[11];
 };
 
 #define KVM_STEAL_ALIGNMENT_BITS 5

arch/x86/kernel/kvm.c

@@ -592,6 +592,14 @@ static void kvm_wait(u8 *ptr, u8 val)
 	local_irq_restore(flags);
 }
 
+__visible bool __kvm_vcpu_is_preempted(int cpu)
+{
+	struct kvm_steal_time *src = &per_cpu(steal_time, cpu);
+
+	return !!src->preempted;
+}
+PV_CALLEE_SAVE_REGS_THUNK(__kvm_vcpu_is_preempted);
+
 /*
  * Setup pv_lock_ops to exploit KVM_FEATURE_PV_UNHALT if present.
  */
@@ -608,6 +616,11 @@ void __init kvm_spinlock_init(void)
 	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
 	pv_lock_ops.wait = kvm_wait;
 	pv_lock_ops.kick = kvm_kick_cpu;
+
+	if (kvm_para_has_feature(KVM_FEATURE_STEAL_TIME)) {
+		pv_lock_ops.vcpu_is_preempted =
+			PV_CALLEE_SAVE(__kvm_vcpu_is_preempted);
+	}
 }
 
 static __init int kvm_spinlock_init_jump(void)

arch/x86/kernel/paravirt-spinlocks.c

@@ -12,7 +12,6 @@ __visible void __native_queued_spin_unlock(struct qspinlock *lock)
 {
 	native_queued_spin_unlock(lock);
 }
-
 PV_CALLEE_SAVE_REGS_THUNK(__native_queued_spin_unlock);
 
 bool pv_is_native_spin_unlock(void)
@@ -21,12 +20,25 @@ bool pv_is_native_spin_unlock(void)
 		__raw_callee_save___native_queued_spin_unlock;
 }
 
+__visible bool __native_vcpu_is_preempted(int cpu)
+{
+	return false;
+}
+PV_CALLEE_SAVE_REGS_THUNK(__native_vcpu_is_preempted);
+
+bool pv_is_native_vcpu_is_preempted(void)
+{
+	return pv_lock_ops.vcpu_is_preempted.func ==
+		__raw_callee_save___native_vcpu_is_preempted;
+}
+
 struct pv_lock_ops pv_lock_ops = {
 #ifdef CONFIG_SMP
 	.queued_spin_lock_slowpath = native_queued_spin_lock_slowpath,
 	.queued_spin_unlock = PV_CALLEE_SAVE(__native_queued_spin_unlock),
 	.wait = paravirt_nop,
 	.kick = paravirt_nop,
+	.vcpu_is_preempted = PV_CALLEE_SAVE(__native_vcpu_is_preempted),
 #endif /* SMP */
 };
 EXPORT_SYMBOL(pv_lock_ops);

arch/x86/kernel/paravirt_patch_32.c

@@ -12,6 +12,7 @@ DEF_NATIVE(pv_cpu_ops, clts, "clts");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%eax)");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %eax, %eax");
 #endif
 
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -27,6 +28,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 }
 
 extern bool pv_is_native_spin_unlock(void);
+extern bool pv_is_native_vcpu_is_preempted(void);
 
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
@@ -56,9 +58,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 				end   = end_pv_lock_ops_queued_spin_unlock;
 				goto patch_site;
 			}
+			goto patch_default;
+
+		case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+			if (pv_is_native_vcpu_is_preempted()) {
+				start = start_pv_lock_ops_vcpu_is_preempted;
+				end   = end_pv_lock_ops_vcpu_is_preempted;
+				goto patch_site;
+			}
+			goto patch_default;
 #endif
 
 	default:
+patch_default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
 

arch/x86/kernel/paravirt_patch_64.c

@@ -21,6 +21,7 @@ DEF_NATIVE(, mov64, "mov %rdi, %rax");
 
 #if defined(CONFIG_PARAVIRT_SPINLOCKS)
 DEF_NATIVE(pv_lock_ops, queued_spin_unlock, "movb $0, (%rdi)");
+DEF_NATIVE(pv_lock_ops, vcpu_is_preempted, "xor %rax, %rax");
 #endif
 
 unsigned paravirt_patch_ident_32(void *insnbuf, unsigned len)
@@ -36,6 +37,7 @@ unsigned paravirt_patch_ident_64(void *insnbuf, unsigned len)
 }
 
 extern bool pv_is_native_spin_unlock(void);
+extern bool pv_is_native_vcpu_is_preempted(void);
 
 unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 		      unsigned long addr, unsigned len)
@@ -68,9 +70,19 @@ unsigned native_patch(u8 type, u16 clobbers, void *ibuf,
 				end   = end_pv_lock_ops_queued_spin_unlock;
 				goto patch_site;
 			}
+			goto patch_default;
+
+		case PARAVIRT_PATCH(pv_lock_ops.vcpu_is_preempted):
+			if (pv_is_native_vcpu_is_preempted()) {
+				start = start_pv_lock_ops_vcpu_is_preempted;
+				end   = end_pv_lock_ops_vcpu_is_preempted;
+				goto patch_site;
+			}
+			goto patch_default;
 #endif
 
 	default:
+patch_default:
 		ret = paravirt_patch_default(type, clobbers, ibuf, addr, len);
 		break;
 

arch/x86/kvm/x86.c

@@ -2071,6 +2071,8 @@ static void record_steal_time(struct kvm_vcpu *vcpu)
 		&vcpu->arch.st.steal, sizeof(struct kvm_steal_time))))
 		return;
 
+	vcpu->arch.st.steal.preempted = 0;
+
 	if (vcpu->arch.st.steal.version & 1)
 		vcpu->arch.st.steal.version += 1;  /* first time write, random junk */
 
@@ -2826,8 +2828,22 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
 }
 
+static void kvm_steal_time_set_preempted(struct kvm_vcpu *vcpu)
+{
+	if (!(vcpu->arch.st.msr_val & KVM_MSR_ENABLED))
+		return;
+
+	vcpu->arch.st.steal.preempted = 1;
+
+	kvm_write_guest_offset_cached(vcpu->kvm, &vcpu->arch.st.stime,
+			&vcpu->arch.st.steal.preempted,
+			offsetof(struct kvm_steal_time, preempted),
+			sizeof(vcpu->arch.st.steal.preempted));
+}
+
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
+	kvm_steal_time_set_preempted(vcpu);
 	kvm_x86_ops->vcpu_put(vcpu);
 	kvm_put_guest_fpu(vcpu);
 	vcpu->arch.last_host_tsc = rdtsc();

arch/x86/um/asm/processor.h

@@ -26,7 +26,6 @@ static inline void rep_nop(void)
 }
 
 #define cpu_relax()		rep_nop()
-#define cpu_relax_lowlatency()	cpu_relax()
 
 #define task_pt_regs(t) (&(t)->thread.regs)
 

arch/x86/xen/spinlock.c

@@ -114,6 +114,7 @@ void xen_uninit_lock_cpu(int cpu)
 	per_cpu(irq_name, cpu) = NULL;
 }
 
+PV_CALLEE_SAVE_REGS_THUNK(xen_vcpu_stolen);
 
 /*
  * Our init of PV spinlocks is split in two init functions due to us
@@ -137,6 +138,7 @@ void __init xen_init_spinlocks(void)
 	pv_lock_ops.queued_spin_unlock = PV_CALLEE_SAVE(__pv_queued_spin_unlock);
 	pv_lock_ops.wait = xen_qlock_wait;
 	pv_lock_ops.kick = xen_qlock_kick;
+	pv_lock_ops.vcpu_is_preempted = PV_CALLEE_SAVE(xen_vcpu_stolen);
 }
 
 /*

arch/xtensa/include/asm/mutex.h

-/*
- * Pull in the generic implementation for the mutex fastpath.
- *
- * TODO: implement optimized primitives instead, or leave the generic
- * implementation in place, or pick the atomic_xchg() based generic
- * implementation. (see asm-generic/mutex-xchg.h for details)
- */
-
-#include <asm-generic/mutex-dec.h>

arch/xtensa/include/asm/processor.h

@@ -206,7 +206,6 @@ extern unsigned long get_wchan(struct task_struct *p);
 #define KSTK_ESP(tsk)		(task_pt_regs(tsk)->areg[1])
 
 #define cpu_relax()  barrier()
-#define cpu_relax_lowlatency() cpu_relax()
 
 /* Special register access. */
 

drivers/gpu/drm/i915/i915_gem_request.c

@@ -723,7 +723,7 @@ bool __i915_spin_request(const struct drm_i915_gem_request *req,
 		if (busywait_stop(timeout_us, cpu))
 			break;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	} while (!need_resched());
 
 	return false;

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -35,19 +35,6 @@
 #include "i915_drv.h"
 #include "i915_trace.h"
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
-{
-	if (!mutex_is_locked(mutex))
-		return false;
-
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
-
 static bool any_vma_pinned(struct drm_i915_gem_object *obj)
 {
 	struct i915_vma *vma;
@@ -240,15 +227,20 @@ unsigned long i915_gem_shrink_all(struct drm_i915_private *dev_priv)
 
 static bool i915_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
+	switch (mutex_trylock_recursive(&dev->struct_mutex)) {
+	case MUTEX_TRYLOCK_FAILED:
+		return false;
 
-		*unlock = false;
-	} else
+	case MUTEX_TRYLOCK_SUCCESS:
 		*unlock = true;
+		return true;
 
-	return true;
+	case MUTEX_TRYLOCK_RECURSIVE:
+		*unlock = false;
+		return true;
+	}
+
+	BUG();
 }
 
 static unsigned long

drivers/gpu/drm/msm/msm_gem_shrinker.c

@@ -18,33 +18,24 @@
 #include "msm_drv.h"
 #include "msm_gem.h"
 
-static bool mutex_is_locked_by(struct mutex *mutex, struct task_struct *task)
+static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
 {
-	if (!mutex_is_locked(mutex))
+	switch (mutex_trylock_recursive(&dev->struct_mutex)) {
+	case MUTEX_TRYLOCK_FAILED:
 		return false;
 
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_MUTEXES)
-	return mutex->owner == task;
-#else
-	/* Since UP may be pre-empted, we cannot assume that we own the lock */
-	return false;
-#endif
-}
+	case MUTEX_TRYLOCK_SUCCESS:
+		*unlock = true;
+		return true;
 
-static bool msm_gem_shrinker_lock(struct drm_device *dev, bool *unlock)
-{
-	if (!mutex_trylock(&dev->struct_mutex)) {
-		if (!mutex_is_locked_by(&dev->struct_mutex, current))
-			return false;
+	case MUTEX_TRYLOCK_RECURSIVE:
 		*unlock = false;
-	} else {
-		*unlock = true;
+		return true;
 	}
 
-	return true;
+	BUG();
 }
 
-
 static unsigned long
 msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {

drivers/vhost/net.c

@@ -342,7 +342,7 @@ static int vhost_net_tx_get_vq_desc(struct vhost_net *net,
 		endtime = busy_clock() + vq->busyloop_timeout;
 		while (vhost_can_busy_poll(vq->dev, endtime) &&
 		       vhost_vq_avail_empty(vq->dev, vq))
-			cpu_relax_lowlatency();
+			cpu_relax();
 		preempt_enable();
 		r = vhost_get_vq_desc(vq, vq->iov, ARRAY_SIZE(vq->iov),
 				      out_num, in_num, NULL, NULL);
@@ -533,7 +533,7 @@ static int vhost_net_rx_peek_head_len(struct vhost_net *net, struct sock *sk)
 		while (vhost_can_busy_poll(&net->dev, endtime) &&
 		       !sk_has_rx_data(sk) &&
 		       vhost_vq_avail_empty(&net->dev, vq))
-			cpu_relax_lowlatency();
+			cpu_relax();
 
 		preempt_enable();
 

include/asm-generic/mutex-dec.h

-/*
- * include/asm-generic/mutex-dec.h
- *
- * Generic implementation of the mutex fastpath, based on atomic
- * decrement/increment.
- */
-#ifndef _ASM_GENERIC_MUTEX_DEC_H
-#define _ASM_GENERIC_MUTEX_DEC_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
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if
- * it wasn't 1 originally. This function MUST leave the value lower than
- * 1 even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_dec_return_acquire(count) < 0))
-		fail_fn(count);
-}
-
-/**
- *  __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_acquire(count) < 0))
-		return -1;
-	return 0;
-}
-
-/**
- *  __mutex_fastpath_unlock - try to promote the count 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 count 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, then the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_inc_return_release(count) <= 0))
-		fail_fn(count);
-}
-
-#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.
- *
- * If the architecture has no effective trylock variant, it should call the
- * <fail_fn> spinlock-based trylock variant unconditionally.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	if (likely(atomic_read(count) == 1 && atomic_cmpxchg_acquire(count, 1, 0) == 1))
-		return 1;
-	return 0;
-}
-
-#endif

include/asm-generic/mutex-null.h

-/*
- * include/asm-generic/mutex-null.h
- *
- * Generic implementation of the mutex fastpath, based on NOP :-)
- *
- * This is used by the mutex-debugging infrastructure, but it can also
- * be used by architectures that (for whatever reason) want to use the
- * spinlock based slowpath.
- */
-#ifndef _ASM_GENERIC_MUTEX_NULL_H
-#define _ASM_GENERIC_MUTEX_NULL_H
-
-#define __mutex_fastpath_lock(count, fail_fn)		fail_fn(count)
-#define __mutex_fastpath_lock_retval(count)		(-1)
-#define __mutex_fastpath_unlock(count, fail_fn)		fail_fn(count)
-#define __mutex_fastpath_trylock(count, fail_fn)	fail_fn(count)
-#define __mutex_slowpath_needs_to_unlock()		1
-
-#endif

include/asm-generic/mutex-xchg.h

-/*
- * include/asm-generic/mutex-xchg.h
- *
- * Generic implementation of the mutex fastpath, based on xchg().
- *
- * NOTE: An xchg based implementation might be less optimal than an atomic
- *       decrement/increment based implementation. If your architecture
- *       has a reasonable atomic dec/inc then you should probably use
- *	 asm-generic/mutex-dec.h instead, or you could open-code an
- *	 optimized version in asm/mutex.h.
- */
-#ifndef _ASM_GENERIC_MUTEX_XCHG_H
-#define _ASM_GENERIC_MUTEX_XCHG_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
- *  @fail_fn: function to call if the original value was not 1
- *
- * Change the count from 1 to a value lower than 1, and call <fail_fn> if it
- * wasn't 1 originally. This function MUST leave the value lower than 1
- * even when the "1" assertion wasn't true.
- */
-static inline void
-__mutex_fastpath_lock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_xchg(count, 0) != 1))
-		/*
-		 * We failed to acquire the lock, so mark it contended
-		 * to ensure that any waiting tasks are woken up by the
-		 * unlock slow path.
-		 */
-		if (likely(atomic_xchg_acquire(count, -1) != 1))
-			fail_fn(count);
-}
-
-/**
- *  __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_xchg_acquire(count, 0) != 1))
-		if (likely(atomic_xchg(count, -1) != 1))
-			return -1;
-	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 <function>
- * In the failure case, this function is allowed to either set the value to
- * 1, or to set it to a value lower than one.
- * If the implementation sets it to a value of lower than one, the
- * __mutex_slowpath_needs_to_unlock() macro needs to return 1, it needs
- * to return 0 otherwise.
- */
-static inline void
-__mutex_fastpath_unlock(atomic_t *count, void (*fail_fn)(atomic_t *))
-{
-	if (unlikely(atomic_xchg_release(count, 1) != 0))
-		fail_fn(count);
-}
-
-#define __mutex_slowpath_needs_to_unlock()		0
-
-/**
- * __mutex_fastpath_trylock - try to acquire the mutex, without waiting
- *
- *  @count: pointer of type atomic_t
- *  @fail_fn: spinlock based trylock implementation
- *
- * 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.
- *
- * If the architecture has no effective trylock variant, it should call the
- * <fail_fn> spinlock-based trylock variant unconditionally.
- */
-static inline int
-__mutex_fastpath_trylock(atomic_t *count, int (*fail_fn)(atomic_t *))
-{
-	int prev;
-
-	if (atomic_read(count) != 1)
-		return 0;
-
-	prev = atomic_xchg_acquire(count, 0);
-	if (unlikely(prev < 0)) {
-		/*
-		 * The lock was marked contended so we must restore that
-		 * state. If while doing so we get back a prev value of 1
-		 * then we just own it.
-		 *
-		 * [ In the rare case of the mutex going to 1, to 0, to -1
-		 *   and then back to 0 in this few-instructions window,
-		 *   this has the potential to trigger the slowpath for the
-		 *   owner's unlock path needlessly, but that's not a problem
-		 *   in practice. ]
-		 */
-		prev = atomic_xchg_acquire(count, prev);
-		if (prev < 0)
-			prev = 0;
-	}
-
-	return prev;
-}
-
-#endif

include/asm-generic/mutex.h

-#ifndef __ASM_GENERIC_MUTEX_H
-#define __ASM_GENERIC_MUTEX_H
-/*
- * Pull in the generic implementation for the mutex fastpath,
- * which is a reasonable default on many architectures.
- */
-
-#include <asm-generic/mutex-dec.h>
-#endif /* __ASM_GENERIC_MUTEX_H */

include/linux/kvm_host.h

@@ -645,6 +645,8 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data,
 		    unsigned long len);
 int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			   void *data, unsigned long len);
+int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, int offset, unsigned long len);
 int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 			      gpa_t gpa, unsigned long len);
 int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len);

include/linux/mutex-debug.h

-#ifndef __LINUX_MUTEX_DEBUG_H
-#define __LINUX_MUTEX_DEBUG_H
-
-#include <linux/linkage.h>
-#include <linux/lockdep.h>
-#include <linux/debug_locks.h>
-
-/*
- * Mutexes - debugging helpers:
- */
-
-#define __DEBUG_MUTEX_INITIALIZER(lockname)				\
-	, .magic = &lockname
-
-#define mutex_init(mutex)						\
-do {									\
-	static struct lock_class_key __key;				\
-									\
-	__mutex_init((mutex), #mutex, &__key);				\
-} while (0)
-
-extern void mutex_destroy(struct mutex *lock);
-
-#endif

include/linux/mutex.h

@@ -18,6 +18,7 @@
 #include <linux/atomic.h>
 #include <asm/processor.h>
 #include <linux/osq_lock.h>
+#include <linux/debug_locks.h>
 
 /*
  * Simple, straightforward mutexes with strict semantics:
@@ -48,16 +49,12 @@
  *   locks and tasks (and only those tasks)
  */
 struct mutex {
-	/* 1: unlocked, 0: locked, negative: locked, possible waiters */
-	atomic_t		count;
+	atomic_long_t		owner;
 	spinlock_t		wait_lock;
-	struct list_head	wait_list;
-#if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_MUTEX_SPIN_ON_OWNER)
-	struct task_struct	*owner;
-#endif
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	struct optimistic_spin_queue osq; /* Spinner MCS lock */
 #endif
+	struct list_head	wait_list;
 #ifdef CONFIG_DEBUG_MUTEXES
 	void			*magic;
 #endif
@@ -66,6 +63,11 @@ struct mutex {
 #endif
 };
 
+static inline struct task_struct *__mutex_owner(struct mutex *lock)
+{
+	return (struct task_struct *)(atomic_long_read(&lock->owner) & ~0x03);
+}
+
 /*
  * This is the control structure for tasks blocked on mutex,
  * which resides on the blocked task's kernel stack:
@@ -79,9 +81,20 @@ struct mutex_waiter {
 };
 
 #ifdef CONFIG_DEBUG_MUTEXES
-# include <linux/mutex-debug.h>
+
+#define __DEBUG_MUTEX_INITIALIZER(lockname)				\
+	, .magic = &lockname
+
+extern void mutex_destroy(struct mutex *lock);
+
 #else
+
 # define __DEBUG_MUTEX_INITIALIZER(lockname)
+
+static inline void mutex_destroy(struct mutex *lock) {}
+
+#endif
+
 /**
  * mutex_init - initialize the mutex
  * @mutex: the mutex to be initialized
@@ -90,14 +103,12 @@ struct mutex_waiter {
  *
  * It is not allowed to initialize an already locked mutex.
  */
-# define mutex_init(mutex) \
-do {							\
-	static struct lock_class_key __key;		\
-							\
-	__mutex_init((mutex), #mutex, &__key);		\
+#define mutex_init(mutex)						\
+do {									\
+	static struct lock_class_key __key;				\
+									\
+	__mutex_init((mutex), #mutex, &__key);				\
 } while (0)
-static inline void mutex_destroy(struct mutex *lock) {}
-#endif
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 # define __DEP_MAP_MUTEX_INITIALIZER(lockname) \
@@ -107,7 +118,7 @@ static inline void mutex_destroy(struct mutex *lock) {}
 #endif
 
 #define __MUTEX_INITIALIZER(lockname) \
-		{ .count = ATOMIC_INIT(1) \
+		{ .owner = ATOMIC_LONG_INIT(0) \
 		, .wait_lock = __SPIN_LOCK_UNLOCKED(lockname.wait_lock) \
 		, .wait_list = LIST_HEAD_INIT(lockname.wait_list) \
 		__DEBUG_MUTEX_INITIALIZER(lockname) \
@@ -127,7 +138,10 @@ extern void __mutex_init(struct mutex *lock, const char *name,
  */
 static inline int mutex_is_locked(struct mutex *lock)
 {
-	return atomic_read(&lock->count) != 1;
+	/*
+	 * XXX think about spin_is_locked
+	 */
+	return __mutex_owner(lock) != NULL;
 }
 
 /*
@@ -175,4 +189,35 @@ extern void mutex_unlock(struct mutex *lock);
 
 extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
+/*
+ * These values are chosen such that FAIL and SUCCESS match the
+ * values of the regular mutex_trylock().
+ */
+enum mutex_trylock_recursive_enum {
+	MUTEX_TRYLOCK_FAILED    = 0,
+	MUTEX_TRYLOCK_SUCCESS   = 1,
+	MUTEX_TRYLOCK_RECURSIVE,
+};
+
+/**
+ * mutex_trylock_recursive - trylock variant that allows recursive locking
+ * @lock: mutex to be locked
+ *
+ * This function should not be used, _ever_. It is purely for hysterical GEM
+ * raisins, and once those are gone this will be removed.
+ *
+ * Returns:
+ *  MUTEX_TRYLOCK_FAILED    - trylock failed,
+ *  MUTEX_TRYLOCK_SUCCESS   - lock acquired,
+ *  MUTEX_TRYLOCK_RECURSIVE - we already owned the lock.
+ */
+static inline /* __deprecated */ __must_check enum mutex_trylock_recursive_enum
+mutex_trylock_recursive(struct mutex *lock)
+{
+	if (unlikely(__mutex_owner(lock) == current))
+		return MUTEX_TRYLOCK_RECURSIVE;
+
+	return mutex_trylock(lock);
+}
+
 #endif /* __LINUX_MUTEX_H */

include/linux/sched.h

@@ -989,7 +989,7 @@ enum cpu_idle_type {
  * already in a wake queue, the wakeup will happen soon and the second
  * waker can just skip it.
  *
- * The WAKE_Q macro declares and initializes the list head.
+ * The DEFINE_WAKE_Q macro declares and initializes the list head.
  * wake_up_q() does NOT reinitialize the list; it's expected to be
  * called near the end of a function, where the fact that the queue is
  * not used again will be easy to see by inspection.
@@ -1009,7 +1009,7 @@ struct wake_q_head {
 
 #define WAKE_Q_TAIL ((struct wake_q_node *) 0x01)
 
-#define WAKE_Q(name)					\
+#define DEFINE_WAKE_Q(name)				\
 	struct wake_q_head name = { WAKE_Q_TAIL, &name.first }
 
 extern void wake_q_add(struct wake_q_head *head,
@@ -2444,6 +2444,10 @@ static inline void calc_load_enter_idle(void) { }
 static inline void calc_load_exit_idle(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
+#ifndef cpu_relax_yield
+#define cpu_relax_yield() cpu_relax()
+#endif
+
 /*
  * Do not use outside of architecture code which knows its limitations.
  *
@@ -3508,6 +3512,18 @@ static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 
 #endif /* CONFIG_SMP */
 
+/*
+ * In order to reduce various lock holder preemption latencies provide an
+ * interface to see if a vCPU is currently running or not.
+ *
+ * This allows us to terminate optimistic spin loops and block, analogous to
+ * the native optimistic spin heuristic of testing if the lock owner task is
+ * running or not.
+ */
+#ifndef vcpu_is_preempted
+# define vcpu_is_preempted(cpu)	false
+#endif
+
 extern long sched_setaffinity(pid_t pid, const struct cpumask *new_mask);
 extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 

include/linux/ww_mutex.h

@@ -120,7 +120,7 @@ static inline void ww_acquire_init(struct ww_acquire_ctx *ctx,
 				   struct ww_class *ww_class)
 {
 	ctx->task = current;
-	ctx->stamp = atomic_long_inc_return(&ww_class->stamp);
+	ctx->stamp = atomic_long_inc_return_relaxed(&ww_class->stamp);
 	ctx->acquired = 0;
 #ifdef CONFIG_DEBUG_MUTEXES
 	ctx->ww_class = ww_class;

ipc/mqueue.c

@@ -967,7 +967,7 @@ SYSCALL_DEFINE5(mq_timedsend, mqd_t, mqdes, const char __user *, u_msg_ptr,
 	struct timespec ts;
 	struct posix_msg_tree_node *new_leaf = NULL;
 	int ret = 0;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (u_abs_timeout) {
 		int res = prepare_timeout(u_abs_timeout, &expires, &ts);
@@ -1151,7 +1151,7 @@ SYSCALL_DEFINE5(mq_timedreceive, mqd_t, mqdes, char __user *, u_msg_ptr,
 			msg_ptr = wait.msg;
 		}
 	} else {
-		WAKE_Q(wake_q);
+		DEFINE_WAKE_Q(wake_q);
 
 		msg_ptr = msg_get(info);
 

ipc/msg.c

@@ -235,7 +235,7 @@ static void freeque(struct ipc_namespace *ns, struct kern_ipc_perm *ipcp)
 {
 	struct msg_msg *msg, *t;
 	struct msg_queue *msq = container_of(ipcp, struct msg_queue, q_perm);
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	expunge_all(msq, -EIDRM, &wake_q);
 	ss_wakeup(msq, &wake_q, true);
@@ -397,7 +397,7 @@ static int msgctl_down(struct ipc_namespace *ns, int msqid, int cmd,
 		goto out_up;
 	case IPC_SET:
 	{
-		WAKE_Q(wake_q);
+		DEFINE_WAKE_Q(wake_q);
 
 		if (msqid64.msg_qbytes > ns->msg_ctlmnb &&
 		    !capable(CAP_SYS_RESOURCE)) {
@@ -634,7 +634,7 @@ long do_msgsnd(int msqid, long mtype, void __user *mtext,
 	struct msg_msg *msg;
 	int err;
 	struct ipc_namespace *ns;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	ns = current->nsproxy->ipc_ns;
 
@@ -850,7 +850,7 @@ long do_msgrcv(int msqid, void __user *buf, size_t bufsz, long msgtyp, int msgfl
 	struct msg_queue *msq;
 	struct ipc_namespace *ns;
 	struct msg_msg *msg, *copy = NULL;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	ns = current->nsproxy->ipc_ns;
 

kernel/Kconfig.locks

@@ -225,7 +225,7 @@ config ARCH_SUPPORTS_ATOMIC_RMW
 
 config MUTEX_SPIN_ON_OWNER
 	def_bool y
-	depends on SMP && !DEBUG_MUTEXES && ARCH_SUPPORTS_ATOMIC_RMW
+	depends on SMP && ARCH_SUPPORTS_ATOMIC_RMW
 
 config RWSEM_SPIN_ON_OWNER
        def_bool y

kernel/futex.c

@@ -1298,7 +1298,7 @@ static int wake_futex_pi(u32 __user *uaddr, u32 uval, struct futex_q *this,
 	struct task_struct *new_owner;
 	struct futex_pi_state *pi_state = this->pi_state;
 	u32 uninitialized_var(curval), newval;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 	bool deboost;
 	int ret = 0;
 
@@ -1415,7 +1415,7 @@ futex_wake(u32 __user *uaddr, unsigned int flags, int nr_wake, u32 bitset)
 	struct futex_q *this, *next;
 	union futex_key key = FUTEX_KEY_INIT;
 	int ret;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (!bitset)
 		return -EINVAL;
@@ -1469,7 +1469,7 @@ futex_wake_op(u32 __user *uaddr1, unsigned int flags, u32 __user *uaddr2,
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
 	int ret, op_ret;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 retry:
 	ret = get_futex_key(uaddr1, flags & FLAGS_SHARED, &key1, VERIFY_READ);
@@ -1708,7 +1708,7 @@ static int futex_requeue(u32 __user *uaddr1, unsigned int flags,
 	struct futex_pi_state *pi_state = NULL;
 	struct futex_hash_bucket *hb1, *hb2;
 	struct futex_q *this, *next;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (requeue_pi) {
 		/*

kernel/locking/lockdep.c

@@ -840,9 +840,9 @@ static struct lock_list *alloc_list_entry(void)
 /*
  * Add a new dependency to the head of the list:
  */
-static int add_lock_to_list(struct lock_class *class, struct lock_class *this,
-			    struct list_head *head, unsigned long ip,
-			    int distance, struct stack_trace *trace)
+static int add_lock_to_list(struct lock_class *this, struct list_head *head,
+			    unsigned long ip, int distance,
+			    struct stack_trace *trace)
 {
 	struct lock_list *entry;
 	/*
@@ -1868,14 +1868,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	 * Ok, all validations passed, add the new lock
 	 * to the previous lock's dependency list:
 	 */
-	ret = add_lock_to_list(hlock_class(prev), hlock_class(next),
+	ret = add_lock_to_list(hlock_class(next),
 			       &hlock_class(prev)->locks_after,
 			       next->acquire_ip, distance, &trace);
 
 	if (!ret)
 		return 0;
 
-	ret = add_lock_to_list(hlock_class(next), hlock_class(prev),
+	ret = add_lock_to_list(hlock_class(prev),
 			       &hlock_class(next)->locks_before,
 			       next->acquire_ip, distance, &trace);
 	if (!ret)