diff --git a/Documentation/virtual/kvm/msr.txt b/Documentation/virtual/kvm/msr.txt
index 2a71c8f..0a9ea51 100644
--- a/Documentation/virtual/kvm/msr.txt
+++ b/Documentation/virtual/kvm/msr.txt
@@ -208,7 +208,9 @@
 		__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 @@
 		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
diff --git a/arch/alpha/include/asm/mutex.h b/arch/alpha/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/alpha/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/alpha/include/asm/processor.h b/arch/alpha/include/asm/processor.h
index 43a7559..2fec2de 100644
--- a/arch/alpha/include/asm/processor.h
+++ b/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
diff --git a/arch/arc/include/asm/mutex.h b/arch/arc/include/asm/mutex.h
deleted file mode 100644
index a2f88ff..0000000
--- a/arch/arc/include/asm/mutex.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * 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
diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 16b630f..6e1242d 100644
--- a/arch/arc/include/asm/processor.h
+++ b/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)
diff --git a/arch/arm/include/asm/mutex.h b/arch/arm/include/asm/mutex.h
deleted file mode 100644
index 87c0449..0000000
--- a/arch/arm/include/asm/mutex.h
+++ /dev/null
@@ -1,21 +0,0 @@
-/*
- * 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 */
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 8a1e8e9..c3d5fc1 100644
--- a/arch/arm/include/asm/processor.h
+++ b/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)
 
diff --git a/arch/arm64/include/asm/Kbuild b/arch/arm64/include/asm/Kbuild
index 44e1d7f..b4ab238 100644
--- a/arch/arm64/include/asm/Kbuild
+++ b/arch/arm64/include/asm/Kbuild
@@ -24,7 +24,6 @@
 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
diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 60e3482..747c65a 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/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);
diff --git a/arch/avr32/include/asm/mutex.h b/arch/avr32/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/avr32/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/avr32/include/asm/processor.h b/arch/avr32/include/asm/processor.h
index 941593c..972adcc 100644
--- a/arch/avr32/include/asm/processor.h
+++ b/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 {
diff --git a/arch/blackfin/include/asm/Kbuild b/arch/blackfin/include/asm/Kbuild
index 91d49c0..2fb67b5 100644
--- a/arch/blackfin/include/asm/Kbuild
+++ b/arch/blackfin/include/asm/Kbuild
@@ -24,7 +24,6 @@
 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
diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h
index 0c265ab..85d4af9 100644
--- a/arch/blackfin/include/asm/processor.h
+++ b/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)
diff --git a/arch/c6x/include/asm/mutex.h b/arch/c6x/include/asm/mutex.h
deleted file mode 100644
index 7a7248e..0000000
--- a/arch/c6x/include/asm/mutex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_C6X_MUTEX_H
-#define _ASM_C6X_MUTEX_H
-
-#include <asm-generic/mutex-null.h>
-
-#endif /* _ASM_C6X_MUTEX_H */
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index f2ef31b..b9eb3da 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/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;
 
diff --git a/arch/cris/include/asm/mutex.h b/arch/cris/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/cris/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 862126b..15b815d 100644
--- a/arch/cris/include/asm/processor.h
+++ b/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);
 
diff --git a/arch/frv/include/asm/mutex.h b/arch/frv/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/frv/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h
index 73f0a79..ddaeb9c 100644
--- a/arch/frv/include/asm/processor.h
+++ b/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
diff --git a/arch/h8300/include/asm/mutex.h b/arch/h8300/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/h8300/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
index 111df73..65132d7 100644
--- a/arch/h8300/include/asm/processor.h
+++ b/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();		\
diff --git a/arch/hexagon/include/asm/mutex.h b/arch/hexagon/include/asm/mutex.h
deleted file mode 100644
index 58b52de..0000000
--- a/arch/hexagon/include/asm/mutex.h
+++ /dev/null
@@ -1,8 +0,0 @@
-/*
- * 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>
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index d850113..45a8254 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/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
diff --git a/arch/ia64/include/asm/mutex.h b/arch/ia64/include/asm/mutex.h
deleted file mode 100644
index 28cb819..0000000
--- a/arch/ia64/include/asm/mutex.h
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * 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
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index ce53c50..03911a3 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/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)
diff --git a/arch/m32r/include/asm/mutex.h b/arch/m32r/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/m32r/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h
index 9f8fd9b..5767367 100644
--- a/arch/m32r/include/asm/processor.h
+++ b/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 */
diff --git a/arch/m68k/include/asm/Kbuild b/arch/m68k/include/asm/Kbuild
index eb85bd9..1f2e5d3 100644
--- a/arch/m68k/include/asm/Kbuild
+++ b/arch/m68k/include/asm/Kbuild
@@ -20,7 +20,6 @@
 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
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index c84a218..f5f790c 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/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
diff --git a/arch/metag/include/asm/Kbuild b/arch/metag/include/asm/Kbuild
index 29acb89d..167150c 100644
--- a/arch/metag/include/asm/Kbuild
+++ b/arch/metag/include/asm/Kbuild
@@ -27,7 +27,6 @@
 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
diff --git a/arch/metag/include/asm/processor.h b/arch/metag/include/asm/processor.h
index a0333eb..ec6a490 100644
--- a/arch/metag/include/asm/processor.h
+++ b/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);
 
diff --git a/arch/microblaze/include/asm/mutex.h b/arch/microblaze/include/asm/mutex.h
deleted file mode 100644
index ff6101a..0000000
--- a/arch/microblaze/include/asm/mutex.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index c38d0dd..37ef196 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/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)
diff --git a/arch/mips/include/asm/Kbuild b/arch/mips/include/asm/Kbuild
index 9740066..3269b74 100644
--- a/arch/mips/include/asm/Kbuild
+++ b/arch/mips/include/asm/Kbuild
@@ -9,7 +9,6 @@
 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
diff --git a/arch/mips/include/asm/processor.h b/arch/mips/include/asm/processor.h
index 0d36c87..95b8c47 100644
--- a/arch/mips/include/asm/processor.h
+++ b/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)
diff --git a/arch/mn10300/include/asm/mutex.h b/arch/mn10300/include/asm/mutex.h
deleted file mode 100644
index 84f5490..0000000
--- a/arch/mn10300/include/asm/mutex.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/* 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>
diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h
index b10ba12..18e17ab 100644
--- a/arch/mn10300/include/asm/processor.h
+++ b/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).
diff --git a/arch/nios2/include/asm/mutex.h b/arch/nios2/include/asm/mutex.h
deleted file mode 100644
index ff6101a..0000000
--- a/arch/nios2/include/asm/mutex.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/mutex-dec.h>
diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h
index 1c953f0..3bbbc3d 100644
--- a/arch/nios2/include/asm/processor.h
+++ b/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__ */
 
diff --git a/arch/openrisc/include/asm/mutex.h b/arch/openrisc/include/asm/mutex.h
deleted file mode 100644
index b85a0cf..0000000
--- a/arch/openrisc/include/asm/mutex.h
+++ /dev/null
@@ -1,27 +0,0 @@
-/*
- * 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>
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index 70334c9..a908e6c 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/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 */
diff --git a/arch/parisc/include/asm/Kbuild b/arch/parisc/include/asm/Kbuild
index f9b3a81..91f53c0 100644
--- a/arch/parisc/include/asm/Kbuild
+++ b/arch/parisc/include/asm/Kbuild
@@ -16,7 +16,6 @@
 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
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index 2e674e1..ca40741 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/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
diff --git a/arch/powerpc/include/asm/mutex.h b/arch/powerpc/include/asm/mutex.h
deleted file mode 100644
index 078155f..0000000
--- a/arch/powerpc/include/asm/mutex.h
+++ /dev/null
@@ -1,132 +0,0 @@
-/*
- * 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
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index c07c31b..dac83fc 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/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);
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index fa37fe9..8c1b913 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/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;
diff --git a/arch/s390/include/asm/mutex.h b/arch/s390/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/s390/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 602af69..9d3a21a 100644
--- a/arch/s390/include/asm/processor.h
+++ b/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
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index 7e9e09f..7ecd890 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/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.
diff --git a/arch/s390/kernel/processor.c b/arch/s390/kernel/processor.c
index 81d0808..9e60ef1 100644
--- a/arch/s390/kernel/processor.c
+++ b/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.
diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c
index 35531fe..b988ed1 100644
--- a/arch/s390/kernel/smp.c
+++ b/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)
 {
diff --git a/arch/s390/lib/spinlock.c b/arch/s390/lib/spinlock.c
index e5f50a7..e48a48e 100644
--- a/arch/s390/lib/spinlock.c
+++ b/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);
 }
diff --git a/arch/score/include/asm/mutex.h b/arch/score/include/asm/mutex.h
deleted file mode 100644
index 10d48fe..0000000
--- a/arch/score/include/asm/mutex.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _ASM_SCORE_MUTEX_H
-#define _ASM_SCORE_MUTEX_H
-
-#include <asm-generic/mutex-dec.h>
-
-#endif /* _ASM_SCORE_MUTEX_H */
diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h
index 851f441..d9a922d 100644
--- a/arch/score/include/asm/processor.h
+++ b/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)
 
 /*
diff --git a/arch/sh/include/asm/mutex-llsc.h b/arch/sh/include/asm/mutex-llsc.h
deleted file mode 100644
index dad29b6..0000000
--- a/arch/sh/include/asm/mutex-llsc.h
+++ /dev/null
@@ -1,109 +0,0 @@
-/*
- * 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 */
diff --git a/arch/sh/include/asm/mutex.h b/arch/sh/include/asm/mutex.h
deleted file mode 100644
index d8e3771..0000000
--- a/arch/sh/include/asm/mutex.h
+++ /dev/null
@@ -1,12 +0,0 @@
-/*
- * 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
diff --git a/arch/sh/include/asm/processor.h b/arch/sh/include/asm/processor.h
index f9a0994..5addd69 100644
--- a/arch/sh/include/asm/processor.h
+++ b/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 *);
diff --git a/arch/sparc/include/asm/Kbuild b/arch/sparc/include/asm/Kbuild
index cfc9180..0569bfa 100644
--- a/arch/sparc/include/asm/Kbuild
+++ b/arch/sparc/include/asm/Kbuild
@@ -15,7 +15,6 @@
 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
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index 812fd08..365d4cb 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/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);
 
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index ce2595c..6448cfc 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/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
diff --git a/arch/tile/include/asm/Kbuild b/arch/tile/include/asm/Kbuild
index ba35c41..2d1f563 100644
--- a/arch/tile/include/asm/Kbuild
+++ b/arch/tile/include/asm/Kbuild
@@ -21,7 +21,6 @@
 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
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 0684e88..0bc9968 100644
--- a/arch/tile/include/asm/processor.h
+++ b/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;
diff --git a/arch/um/include/asm/Kbuild b/arch/um/include/asm/Kbuild
index 904f3eb..052f7f6 100644
--- a/arch/um/include/asm/Kbuild
+++ b/arch/um/include/asm/Kbuild
@@ -17,7 +17,6 @@
 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
diff --git a/arch/unicore32/include/asm/mutex.h b/arch/unicore32/include/asm/mutex.h
deleted file mode 100644
index fab7d0e..0000000
--- a/arch/unicore32/include/asm/mutex.h
+++ /dev/null
@@ -1,20 +0,0 @@
-/*
- * 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
diff --git a/arch/unicore32/include/asm/processor.h b/arch/unicore32/include/asm/processor.h
index 8d21b7a..4eaa421 100644
--- a/arch/unicore32/include/asm/processor.h
+++ b/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)
diff --git a/arch/x86/include/asm/mutex.h b/arch/x86/include/asm/mutex.h
deleted file mode 100644
index 7d3a482..0000000
--- 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 e9355a8..0000000
--- 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 d985075..0000000
--- 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 ce93281..6108b1f 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 0f400c0..3f2bc0f 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 984a7bf..c84605b 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 eaba080..c343ab5 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)
 {
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index 94dc8ca..1421a65 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/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
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index edbbfc8..52e90d6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/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)
diff --git a/arch/x86/kernel/paravirt-spinlocks.c b/arch/x86/kernel/paravirt-spinlocks.c
index 2c55a00..6d4bf81 100644
--- a/arch/x86/kernel/paravirt-spinlocks.c
+++ b/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);
diff --git a/arch/x86/kernel/paravirt_patch_32.c b/arch/x86/kernel/paravirt_patch_32.c
index 920c6ae..33cdec2 100644
--- a/arch/x86/kernel/paravirt_patch_32.c
+++ b/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;
 
diff --git a/arch/x86/kernel/paravirt_patch_64.c b/arch/x86/kernel/paravirt_patch_64.c
index bb3840c..b0fceff 100644
--- a/arch/x86/kernel/paravirt_patch_64.c
+++ b/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;
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 04c5d96..59c2d6f 100644
--- a/arch/x86/kvm/x86.c
+++ b/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();
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 233ee09..c77db22 100644
--- a/arch/x86/um/asm/processor.h
+++ b/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)
 
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 3d6e006..e8a9ea7 100644
--- a/arch/x86/xen/spinlock.c
+++ b/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);
 }
 
 /*
diff --git a/arch/xtensa/include/asm/mutex.h b/arch/xtensa/include/asm/mutex.h
deleted file mode 100644
index 458c1f7..0000000
--- a/arch/xtensa/include/asm/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * 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>
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index b42d68b..86ffcd6 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/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. */
 
diff --git a/drivers/gpu/drm/i915/i915_gem_request.c b/drivers/gpu/drm/i915/i915_gem_request.c
index 8832f8e..383d134 100644
--- a/drivers/gpu/drm/i915/i915_gem_request.c
+++ b/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;
diff --git a/drivers/gpu/drm/i915/i915_gem_shrinker.c b/drivers/gpu/drm/i915/i915_gem_shrinker.c
index 1c237d0..c450076 100644
--- a/drivers/gpu/drm/i915/i915_gem_shrinker.c
+++ b/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
diff --git a/drivers/gpu/drm/msm/msm_gem_shrinker.c b/drivers/gpu/drm/msm/msm_gem_shrinker.c
index 192b2d3..ab1dd02 100644
--- a/drivers/gpu/drm/msm/msm_gem_shrinker.c
+++ b/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)
-{
-	if (!mutex_is_locked(mutex))
-		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
-}
-
 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;
-		*unlock = false;
-	} else {
+	switch (mutex_trylock_recursive(&dev->struct_mutex)) {
+	case MUTEX_TRYLOCK_FAILED:
+		return false;
+
+	case MUTEX_TRYLOCK_SUCCESS:
 		*unlock = true;
+		return true;
+
+	case MUTEX_TRYLOCK_RECURSIVE:
+		*unlock = false;
+		return true;
 	}
 
-	return true;
+	BUG();
 }
 
-
 static unsigned long
 msm_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 5dc128a..5dc3465 100644
--- a/drivers/vhost/net.c
+++ b/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();
 
diff --git a/include/asm-generic/mutex-dec.h b/include/asm-generic/mutex-dec.h
deleted file mode 100644
index c54829d..0000000
--- a/include/asm-generic/mutex-dec.h
+++ /dev/null
@@ -1,88 +0,0 @@
-/*
- * 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
diff --git a/include/asm-generic/mutex-null.h b/include/asm-generic/mutex-null.h
deleted file mode 100644
index 61069ed..0000000
--- a/include/asm-generic/mutex-null.h
+++ /dev/null
@@ -1,19 +0,0 @@
-/*
- * 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
diff --git a/include/asm-generic/mutex-xchg.h b/include/asm-generic/mutex-xchg.h
deleted file mode 100644
index 3269ec4..0000000
--- a/include/asm-generic/mutex-xchg.h
+++ /dev/null
@@ -1,120 +0,0 @@
-/*
- * 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
diff --git a/include/asm-generic/mutex.h b/include/asm-generic/mutex.h
deleted file mode 100644
index fe91ab5..0000000
--- a/include/asm-generic/mutex.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#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 */
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 01c0b9c..6f00237 100644
--- a/include/linux/kvm_host.h
+++ b/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);
diff --git a/include/linux/mutex-debug.h b/include/linux/mutex-debug.h
deleted file mode 100644
index 4ac8b19..0000000
--- a/include/linux/mutex-debug.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#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
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 2cb7531..b97870f 100644
--- a/include/linux/mutex.h
+++ b/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 */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e9c009d..8863bdf 100644
--- a/include/linux/sched.h
+++ b/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);
 
diff --git a/include/linux/ww_mutex.h b/include/linux/ww_mutex.h
index 2bb5deb..7b00668 100644
--- a/include/linux/ww_mutex.h
+++ b/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;
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 8cbd6e6..7a2d8f0 100644
--- a/ipc/mqueue.c
+++ b/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);
 
diff --git a/ipc/msg.c b/ipc/msg.c
index e12307d..32e9bd8 100644
--- a/ipc/msg.c
+++ b/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;
 
diff --git a/kernel/Kconfig.locks b/kernel/Kconfig.locks
index ebdb004..84d882f 100644
--- a/kernel/Kconfig.locks
+++ b/kernel/Kconfig.locks
@@ -225,7 +225,7 @@
 
 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
diff --git a/kernel/futex.c b/kernel/futex.c
index 2c4be46..9246d9f 100644
--- a/kernel/futex.c
+++ b/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) {
 		/*
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 4d7ffc0..7bd265f 100644
--- a/kernel/locking/lockdep.c
+++ b/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)
diff --git a/kernel/locking/mcs_spinlock.h b/kernel/locking/mcs_spinlock.h
index c835270..6a385aa 100644
--- a/kernel/locking/mcs_spinlock.h
+++ b/kernel/locking/mcs_spinlock.h
@@ -28,7 +28,7 @@ struct mcs_spinlock {
 #define arch_mcs_spin_lock_contended(l)					\
 do {									\
 	while (!(smp_load_acquire(l)))					\
-		cpu_relax_lowlatency();					\
+		cpu_relax();						\
 } while (0)
 #endif
 
@@ -108,7 +108,7 @@ void mcs_spin_unlock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 			return;
 		/* Wait until the next pointer is set */
 		while (!(next = READ_ONCE(node->next)))
-			cpu_relax_lowlatency();
+			cpu_relax();
 	}
 
 	/* Pass lock to next waiter. */
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 9c951fa..9aa7136 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -73,21 +73,8 @@ void debug_mutex_unlock(struct mutex *lock)
 {
 	if (likely(debug_locks)) {
 		DEBUG_LOCKS_WARN_ON(lock->magic != lock);
-
-		if (!lock->owner)
-			DEBUG_LOCKS_WARN_ON(!lock->owner);
-		else
-			DEBUG_LOCKS_WARN_ON(lock->owner != current);
-
 		DEBUG_LOCKS_WARN_ON(!lock->wait_list.prev && !lock->wait_list.next);
 	}
-
-	/*
-	 * __mutex_slowpath_needs_to_unlock() is explicitly 0 for debug
-	 * mutexes so that we can do it here after we've verified state.
-	 */
-	mutex_clear_owner(lock);
-	atomic_set(&lock->count, 1);
 }
 
 void debug_mutex_init(struct mutex *lock, const char *name,
diff --git a/kernel/locking/mutex-debug.h b/kernel/locking/mutex-debug.h
index 57a871a..a459faa 100644
--- a/kernel/locking/mutex-debug.h
+++ b/kernel/locking/mutex-debug.h
@@ -27,16 +27,6 @@ extern void debug_mutex_unlock(struct mutex *lock);
 extern void debug_mutex_init(struct mutex *lock, const char *name,
 			     struct lock_class_key *key);
 
-static inline void mutex_set_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, current);
-}
-
-static inline void mutex_clear_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, NULL);
-}
-
 #define spin_lock_mutex(lock, flags)			\
 	do {						\
 		struct mutex *l = container_of(lock, struct mutex, wait_lock); \
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index a70b90d..9b34961 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -27,41 +27,176 @@
 #include <linux/debug_locks.h>
 #include <linux/osq_lock.h>
 
-/*
- * In the DEBUG case we are using the "NULL fastpath" for mutexes,
- * which forces all calls into the slowpath:
- */
 #ifdef CONFIG_DEBUG_MUTEXES
 # include "mutex-debug.h"
-# include <asm-generic/mutex-null.h>
-/*
- * Must be 0 for the debug case so we do not do the unlock outside of the
- * wait_lock region. debug_mutex_unlock() will do the actual unlock in this
- * case.
- */
-# undef __mutex_slowpath_needs_to_unlock
-# define  __mutex_slowpath_needs_to_unlock()	0
 #else
 # include "mutex.h"
-# include <asm/mutex.h>
 #endif
 
 void
 __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 {
-	atomic_set(&lock->count, 1);
+	atomic_long_set(&lock->owner, 0);
 	spin_lock_init(&lock->wait_lock);
 	INIT_LIST_HEAD(&lock->wait_list);
-	mutex_clear_owner(lock);
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
 	osq_lock_init(&lock->osq);
 #endif
 
 	debug_mutex_init(lock, name, key);
 }
-
 EXPORT_SYMBOL(__mutex_init);
 
+/*
+ * @owner: contains: 'struct task_struct *' to the current lock owner,
+ * NULL means not owned. Since task_struct pointers are aligned at
+ * ARCH_MIN_TASKALIGN (which is at least sizeof(void *)), we have low
+ * bits to store extra state.
+ *
+ * Bit0 indicates a non-empty waiter list; unlock must issue a wakeup.
+ * Bit1 indicates unlock needs to hand the lock to the top-waiter
+ */
+#define MUTEX_FLAG_WAITERS	0x01
+#define MUTEX_FLAG_HANDOFF	0x02
+
+#define MUTEX_FLAGS		0x03
+
+static inline struct task_struct *__owner_task(unsigned long owner)
+{
+	return (struct task_struct *)(owner & ~MUTEX_FLAGS);
+}
+
+static inline unsigned long __owner_flags(unsigned long owner)
+{
+	return owner & MUTEX_FLAGS;
+}
+
+/*
+ * Actual trylock that will work on any unlocked state.
+ *
+ * When setting the owner field, we must preserve the low flag bits.
+ *
+ * Be careful with @handoff, only set that in a wait-loop (where you set
+ * HANDOFF) to avoid recursive lock attempts.
+ */
+static inline bool __mutex_trylock(struct mutex *lock, const bool handoff)
+{
+	unsigned long owner, curr = (unsigned long)current;
+
+	owner = atomic_long_read(&lock->owner);
+	for (;;) { /* must loop, can race against a flag */
+		unsigned long old, flags = __owner_flags(owner);
+
+		if (__owner_task(owner)) {
+			if (handoff && unlikely(__owner_task(owner) == current)) {
+				/*
+				 * Provide ACQUIRE semantics for the lock-handoff.
+				 *
+				 * We cannot easily use load-acquire here, since
+				 * the actual load is a failed cmpxchg, which
+				 * doesn't imply any barriers.
+				 *
+				 * Also, this is a fairly unlikely scenario, and
+				 * this contains the cost.
+				 */
+				smp_mb(); /* ACQUIRE */
+				return true;
+			}
+
+			return false;
+		}
+
+		/*
+		 * We set the HANDOFF bit, we must make sure it doesn't live
+		 * past the point where we acquire it. This would be possible
+		 * if we (accidentally) set the bit on an unlocked mutex.
+		 */
+		if (handoff)
+			flags &= ~MUTEX_FLAG_HANDOFF;
+
+		old = atomic_long_cmpxchg_acquire(&lock->owner, owner, curr | flags);
+		if (old == owner)
+			return true;
+
+		owner = old;
+	}
+}
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
+/*
+ * Lockdep annotations are contained to the slow paths for simplicity.
+ * There is nothing that would stop spreading the lockdep annotations outwards
+ * except more code.
+ */
+
+/*
+ * Optimistic trylock that only works in the uncontended case. Make sure to
+ * follow with a __mutex_trylock() before failing.
+ */
+static __always_inline bool __mutex_trylock_fast(struct mutex *lock)
+{
+	unsigned long curr = (unsigned long)current;
+
+	if (!atomic_long_cmpxchg_acquire(&lock->owner, 0UL, curr))
+		return true;
+
+	return false;
+}
+
+static __always_inline bool __mutex_unlock_fast(struct mutex *lock)
+{
+	unsigned long curr = (unsigned long)current;
+
+	if (atomic_long_cmpxchg_release(&lock->owner, curr, 0UL) == curr)
+		return true;
+
+	return false;
+}
+#endif
+
+static inline void __mutex_set_flag(struct mutex *lock, unsigned long flag)
+{
+	atomic_long_or(flag, &lock->owner);
+}
+
+static inline void __mutex_clear_flag(struct mutex *lock, unsigned long flag)
+{
+	atomic_long_andnot(flag, &lock->owner);
+}
+
+static inline bool __mutex_waiter_is_first(struct mutex *lock, struct mutex_waiter *waiter)
+{
+	return list_first_entry(&lock->wait_list, struct mutex_waiter, list) == waiter;
+}
+
+/*
+ * Give up ownership to a specific task, when @task = NULL, this is equivalent
+ * to a regular unlock. Clears HANDOFF, preserves WAITERS. Provides RELEASE
+ * semantics like a regular unlock, the __mutex_trylock() provides matching
+ * ACQUIRE semantics for the handoff.
+ */
+static void __mutex_handoff(struct mutex *lock, struct task_struct *task)
+{
+	unsigned long owner = atomic_long_read(&lock->owner);
+
+	for (;;) {
+		unsigned long old, new;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+#endif
+
+		new = (owner & MUTEX_FLAG_WAITERS);
+		new |= (unsigned long)task;
+
+		old = atomic_long_cmpxchg_release(&lock->owner, owner, new);
+		if (old == owner)
+			break;
+
+		owner = old;
+	}
+}
+
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 /*
  * We split the mutex lock/unlock logic into separate fastpath and
@@ -69,7 +204,7 @@ EXPORT_SYMBOL(__mutex_init);
  * We also put the fastpath first in the kernel image, to make sure the
  * branch is predicted by the CPU as default-untaken.
  */
-__visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
+static void __sched __mutex_lock_slowpath(struct mutex *lock);
 
 /**
  * mutex_lock - acquire the mutex
@@ -95,14 +230,10 @@ __visible void __sched __mutex_lock_slowpath(atomic_t *lock_count);
 void __sched mutex_lock(struct mutex *lock)
 {
 	might_sleep();
-	/*
-	 * The locking fastpath is the 1->0 transition from
-	 * 'unlocked' into 'locked' state.
-	 */
-	__mutex_fastpath_lock(&lock->count, __mutex_lock_slowpath);
-	mutex_set_owner(lock);
-}
 
+	if (!__mutex_trylock_fast(lock))
+		__mutex_lock_slowpath(lock);
+}
 EXPORT_SYMBOL(mutex_lock);
 #endif
 
@@ -149,9 +280,6 @@ static __always_inline void ww_mutex_lock_acquired(struct ww_mutex *ww,
 /*
  * After acquiring lock with fastpath or when we lost out in contested
  * slowpath, set ctx and wake up any waiters so they can recheck.
- *
- * This function is never called when CONFIG_DEBUG_LOCK_ALLOC is set,
- * as the fastpath and opportunistic spinning are disabled in that case.
  */
 static __always_inline void
 ww_mutex_set_context_fastpath(struct ww_mutex *lock,
@@ -176,7 +304,7 @@ ww_mutex_set_context_fastpath(struct ww_mutex *lock,
 	/*
 	 * Check if lock is contended, if not there is nobody to wake up
 	 */
-	if (likely(atomic_read(&lock->base.count) == 0))
+	if (likely(!(atomic_long_read(&lock->base.owner) & MUTEX_FLAG_WAITERS)))
 		return;
 
 	/*
@@ -227,7 +355,7 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 	bool ret = true;
 
 	rcu_read_lock();
-	while (lock->owner == owner) {
+	while (__mutex_owner(lock) == owner) {
 		/*
 		 * Ensure we emit the owner->on_cpu, dereference _after_
 		 * checking lock->owner still matches owner. If that fails,
@@ -236,12 +364,16 @@ bool mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 		 */
 		barrier();
 
-		if (!owner->on_cpu || need_resched()) {
+		/*
+		 * Use vcpu_is_preempted to detect lock holder preemption issue.
+		 */
+		if (!owner->on_cpu || need_resched() ||
+				vcpu_is_preempted(task_cpu(owner))) {
 			ret = false;
 			break;
 		}
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	rcu_read_unlock();
 
@@ -260,27 +392,25 @@ static inline int mutex_can_spin_on_owner(struct mutex *lock)
 		return 0;
 
 	rcu_read_lock();
-	owner = READ_ONCE(lock->owner);
-	if (owner)
-		retval = owner->on_cpu;
-	rcu_read_unlock();
+	owner = __mutex_owner(lock);
+
 	/*
-	 * if lock->owner is not set, the mutex owner may have just acquired
-	 * it and not set the owner yet or the mutex has been released.
+	 * As lock holder preemption issue, we both skip spinning if task is not
+	 * on cpu or its cpu is preempted
+	 */
+	if (owner)
+		retval = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+	rcu_read_unlock();
+
+	/*
+	 * If lock->owner is not set, the mutex has been released. Return true
+	 * such that we'll trylock in the spin path, which is a faster option
+	 * than the blocking slow path.
 	 */
 	return retval;
 }
 
 /*
- * Atomically try to take the lock when it is available
- */
-static inline bool mutex_try_to_acquire(struct mutex *lock)
-{
-	return !mutex_is_locked(lock) &&
-		(atomic_cmpxchg_acquire(&lock->count, 1, 0) == 1);
-}
-
-/*
  * Optimistic spinning.
  *
  * We try to spin for acquisition when we find that the lock owner
@@ -288,13 +418,6 @@ static inline bool mutex_try_to_acquire(struct mutex *lock)
  * need to reschedule. The rationale is that if the lock owner is
  * running, it is likely to release the lock soon.
  *
- * Since this needs the lock owner, and this mutex implementation
- * doesn't track the owner atomically in the lock field, we need to
- * track it non-atomically.
- *
- * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
- * to serialize everything.
- *
  * The mutex spinners are queued up using MCS lock so that only one
  * spinner can compete for the mutex. However, if mutex spinning isn't
  * going to happen, there is no point in going through the lock/unlock
@@ -302,24 +425,39 @@ static inline bool mutex_try_to_acquire(struct mutex *lock)
  *
  * Returns true when the lock was taken, otherwise false, indicating
  * that we need to jump to the slowpath and sleep.
+ *
+ * The waiter flag is set to true if the spinner is a waiter in the wait
+ * queue. The waiter-spinner will spin on the lock directly and concurrently
+ * with the spinner at the head of the OSQ, if present, until the owner is
+ * changed to itself.
  */
 static bool mutex_optimistic_spin(struct mutex *lock,
-				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
+				  struct ww_acquire_ctx *ww_ctx,
+				  const bool use_ww_ctx, const bool waiter)
 {
 	struct task_struct *task = current;
 
-	if (!mutex_can_spin_on_owner(lock))
-		goto done;
+	if (!waiter) {
+		/*
+		 * The purpose of the mutex_can_spin_on_owner() function is
+		 * to eliminate the overhead of osq_lock() and osq_unlock()
+		 * in case spinning isn't possible. As a waiter-spinner
+		 * is not going to take OSQ lock anyway, there is no need
+		 * to call mutex_can_spin_on_owner().
+		 */
+		if (!mutex_can_spin_on_owner(lock))
+			goto fail;
 
-	/*
-	 * In order to avoid a stampede of mutex spinners trying to
-	 * acquire the mutex all at once, the spinners need to take a
-	 * MCS (queued) lock first before spinning on the owner field.
-	 */
-	if (!osq_lock(&lock->osq))
-		goto done;
+		/*
+		 * In order to avoid a stampede of mutex spinners trying to
+		 * acquire the mutex all at once, the spinners need to take a
+		 * MCS (queued) lock first before spinning on the owner field.
+		 */
+		if (!osq_lock(&lock->osq))
+			goto fail;
+	}
 
-	while (true) {
+	for (;;) {
 		struct task_struct *owner;
 
 		if (use_ww_ctx && ww_ctx->acquired > 0) {
@@ -335,40 +473,26 @@ static bool mutex_optimistic_spin(struct mutex *lock,
 			 * performed the optimistic spinning cannot be done.
 			 */
 			if (READ_ONCE(ww->ctx))
-				break;
+				goto fail_unlock;
 		}
 
 		/*
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
-		owner = READ_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner))
-			break;
-
-		/* Try to acquire the mutex if it is unlocked. */
-		if (mutex_try_to_acquire(lock)) {
-			lock_acquired(&lock->dep_map, ip);
-
-			if (use_ww_ctx) {
-				struct ww_mutex *ww;
-				ww = container_of(lock, struct ww_mutex, base);
-
-				ww_mutex_set_context_fastpath(ww, ww_ctx);
+		owner = __mutex_owner(lock);
+		if (owner) {
+			if (waiter && owner == task) {
+				smp_mb(); /* ACQUIRE */
+				break;
 			}
 
-			mutex_set_owner(lock);
-			osq_unlock(&lock->osq);
-			return true;
+			if (!mutex_spin_on_owner(lock, owner))
+				goto fail_unlock;
 		}
 
-		/*
-		 * When there's no owner, we might have preempted between the
-		 * owner acquiring the lock and setting the owner field. If
-		 * we're an RT task that will live-lock because we won't let
-		 * the owner complete.
-		 */
-		if (!owner && (need_resched() || rt_task(task)))
+		/* Try to acquire the mutex if it is unlocked. */
+		if (__mutex_trylock(lock, waiter))
 			break;
 
 		/*
@@ -377,11 +501,20 @@ static bool mutex_optimistic_spin(struct mutex *lock,
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 
-	osq_unlock(&lock->osq);
-done:
+	if (!waiter)
+		osq_unlock(&lock->osq);
+
+	return true;
+
+
+fail_unlock:
+	if (!waiter)
+		osq_unlock(&lock->osq);
+
+fail:
 	/*
 	 * If we fell out of the spin path because of need_resched(),
 	 * reschedule now, before we try-lock the mutex. This avoids getting
@@ -400,14 +533,14 @@ static bool mutex_optimistic_spin(struct mutex *lock,
 }
 #else
 static bool mutex_optimistic_spin(struct mutex *lock,
-				  struct ww_acquire_ctx *ww_ctx, const bool use_ww_ctx)
+				  struct ww_acquire_ctx *ww_ctx,
+				  const bool use_ww_ctx, const bool waiter)
 {
 	return false;
 }
 #endif
 
-__visible __used noinline
-void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
+static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip);
 
 /**
  * mutex_unlock - release the mutex
@@ -422,21 +555,12 @@ void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
  */
 void __sched mutex_unlock(struct mutex *lock)
 {
-	/*
-	 * The unlocking fastpath is the 0->1 transition from 'locked'
-	 * into 'unlocked' state:
-	 */
-#ifndef CONFIG_DEBUG_MUTEXES
-	/*
-	 * When debugging is enabled we must not clear the owner before time,
-	 * the slow path will always be taken, and that clears the owner field
-	 * after verifying that it was indeed current.
-	 */
-	mutex_clear_owner(lock);
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
+	if (__mutex_unlock_fast(lock))
+		return;
 #endif
-	__mutex_fastpath_unlock(&lock->count, __mutex_unlock_slowpath);
+	__mutex_unlock_slowpath(lock, _RET_IP_);
 }
-
 EXPORT_SYMBOL(mutex_unlock);
 
 /**
@@ -465,15 +589,7 @@ void __sched ww_mutex_unlock(struct ww_mutex *lock)
 		lock->ctx = NULL;
 	}
 
-#ifndef CONFIG_DEBUG_MUTEXES
-	/*
-	 * When debugging is enabled we must not clear the owner before time,
-	 * the slow path will always be taken, and that clears the owner field
-	 * after verifying that it was indeed current.
-	 */
-	mutex_clear_owner(&lock->base);
-#endif
-	__mutex_fastpath_unlock(&lock->base.count, __mutex_unlock_slowpath);
+	mutex_unlock(&lock->base);
 }
 EXPORT_SYMBOL(ww_mutex_unlock);
 
@@ -509,10 +625,12 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	struct task_struct *task = current;
 	struct mutex_waiter waiter;
 	unsigned long flags;
+	bool first = false;
+	struct ww_mutex *ww;
 	int ret;
 
 	if (use_ww_ctx) {
-		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+		ww = container_of(lock, struct ww_mutex, base);
 		if (unlikely(ww_ctx == READ_ONCE(ww->ctx)))
 			return -EALREADY;
 	}
@@ -520,20 +638,21 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	preempt_disable();
 	mutex_acquire_nest(&lock->dep_map, subclass, 0, nest_lock, ip);
 
-	if (mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx)) {
+	if (__mutex_trylock(lock, false) ||
+	    mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, false)) {
 		/* got the lock, yay! */
+		lock_acquired(&lock->dep_map, ip);
+		if (use_ww_ctx)
+			ww_mutex_set_context_fastpath(ww, ww_ctx);
 		preempt_enable();
 		return 0;
 	}
 
 	spin_lock_mutex(&lock->wait_lock, flags);
-
 	/*
-	 * Once more, try to acquire the lock. Only try-lock the mutex if
-	 * it is unlocked to reduce unnecessary xchg() operations.
+	 * After waiting to acquire the wait_lock, try again.
 	 */
-	if (!mutex_is_locked(lock) &&
-	    (atomic_xchg_acquire(&lock->count, 0) == 1))
+	if (__mutex_trylock(lock, false))
 		goto skip_wait;
 
 	debug_mutex_lock_common(lock, &waiter);
@@ -543,26 +662,26 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	list_add_tail(&waiter.list, &lock->wait_list);
 	waiter.task = task;
 
+	if (__mutex_waiter_is_first(lock, &waiter))
+		__mutex_set_flag(lock, MUTEX_FLAG_WAITERS);
+
 	lock_contended(&lock->dep_map, ip);
 
+	set_task_state(task, state);
 	for (;;) {
 		/*
-		 * Lets try to take the lock again - this is needed even if
-		 * we get here for the first time (shortly after failing to
-		 * acquire the lock), to make sure that we get a wakeup once
-		 * it's unlocked. Later on, if we sleep, this is the
-		 * operation that gives us the lock. We xchg it to -1, so
-		 * that when we release the lock, we properly wake up the
-		 * other waiters. We only attempt the xchg if the count is
-		 * non-negative in order to avoid unnecessary xchg operations:
+		 * Once we hold wait_lock, we're serialized against
+		 * mutex_unlock() handing the lock off to us, do a trylock
+		 * before testing the error conditions to make sure we pick up
+		 * the handoff.
 		 */
-		if (atomic_read(&lock->count) >= 0 &&
-		    (atomic_xchg_acquire(&lock->count, -1) == 1))
-			break;
+		if (__mutex_trylock(lock, first))
+			goto acquired;
 
 		/*
-		 * got a signal? (This code gets eliminated in the
-		 * TASK_UNINTERRUPTIBLE case.)
+		 * Check for signals and wound conditions while holding
+		 * wait_lock. This ensures the lock cancellation is ordered
+		 * against mutex_unlock() and wake-ups do not go missing.
 		 */
 		if (unlikely(signal_pending_state(state, task))) {
 			ret = -EINTR;
@@ -575,36 +694,49 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 				goto err;
 		}
 
-		__set_task_state(task, state);
-
-		/* didn't get the lock, go to sleep: */
 		spin_unlock_mutex(&lock->wait_lock, flags);
 		schedule_preempt_disabled();
+
+		if (!first && __mutex_waiter_is_first(lock, &waiter)) {
+			first = true;
+			__mutex_set_flag(lock, MUTEX_FLAG_HANDOFF);
+		}
+
+		set_task_state(task, state);
+		/*
+		 * Here we order against unlock; we must either see it change
+		 * state back to RUNNING and fall through the next schedule(),
+		 * or we must see its unlock and acquire.
+		 */
+		if ((first && mutex_optimistic_spin(lock, ww_ctx, use_ww_ctx, true)) ||
+		     __mutex_trylock(lock, first))
+			break;
+
 		spin_lock_mutex(&lock->wait_lock, flags);
 	}
+	spin_lock_mutex(&lock->wait_lock, flags);
+acquired:
 	__set_task_state(task, TASK_RUNNING);
 
 	mutex_remove_waiter(lock, &waiter, task);
-	/* set it to 0 if there are no waiters left: */
 	if (likely(list_empty(&lock->wait_list)))
-		atomic_set(&lock->count, 0);
+		__mutex_clear_flag(lock, MUTEX_FLAGS);
+
 	debug_mutex_free_waiter(&waiter);
 
 skip_wait:
 	/* got the lock - cleanup and rejoice! */
 	lock_acquired(&lock->dep_map, ip);
-	mutex_set_owner(lock);
 
-	if (use_ww_ctx) {
-		struct ww_mutex *ww = container_of(lock, struct ww_mutex, base);
+	if (use_ww_ctx)
 		ww_mutex_set_context_slowpath(ww, ww_ctx);
-	}
 
 	spin_unlock_mutex(&lock->wait_lock, flags);
 	preempt_enable();
 	return 0;
 
 err:
+	__set_task_state(task, TASK_RUNNING);
 	mutex_remove_waiter(lock, &waiter, task);
 	spin_unlock_mutex(&lock->wait_lock, flags);
 	debug_mutex_free_waiter(&waiter);
@@ -631,7 +763,6 @@ _mutex_lock_nest_lock(struct mutex *lock, struct lockdep_map *nest)
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE,
 			    0, nest, _RET_IP_, NULL, 0);
 }
-
 EXPORT_SYMBOL_GPL(_mutex_lock_nest_lock);
 
 int __sched
@@ -650,7 +781,6 @@ mutex_lock_interruptible_nested(struct mutex *lock, unsigned int subclass)
 	return __mutex_lock_common(lock, TASK_INTERRUPTIBLE,
 				   subclass, NULL, _RET_IP_, NULL, 0);
 }
-
 EXPORT_SYMBOL_GPL(mutex_lock_interruptible_nested);
 
 static inline int
@@ -715,56 +845,66 @@ EXPORT_SYMBOL_GPL(__ww_mutex_lock_interruptible);
 /*
  * Release the lock, slowpath:
  */
-static inline void
-__mutex_unlock_common_slowpath(struct mutex *lock, int nested)
+static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigned long ip)
 {
-	unsigned long flags;
-	WAKE_Q(wake_q);
+	struct task_struct *next = NULL;
+	unsigned long owner, flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	mutex_release(&lock->dep_map, 1, ip);
 
 	/*
-	 * As a performance measurement, release the lock before doing other
-	 * wakeup related duties to follow. This allows other tasks to acquire
-	 * the lock sooner, while still handling cleanups in past unlock calls.
-	 * This can be done as we do not enforce strict equivalence between the
-	 * mutex counter and wait_list.
+	 * Release the lock before (potentially) taking the spinlock such that
+	 * other contenders can get on with things ASAP.
 	 *
-	 *
-	 * Some architectures leave the lock unlocked in the fastpath failure
-	 * case, others need to leave it locked. In the later case we have to
-	 * unlock it here - as the lock counter is currently 0 or negative.
+	 * Except when HANDOFF, in that case we must not clear the owner field,
+	 * but instead set it to the top waiter.
 	 */
-	if (__mutex_slowpath_needs_to_unlock())
-		atomic_set(&lock->count, 1);
+	owner = atomic_long_read(&lock->owner);
+	for (;;) {
+		unsigned long old;
+
+#ifdef CONFIG_DEBUG_MUTEXES
+		DEBUG_LOCKS_WARN_ON(__owner_task(owner) != current);
+#endif
+
+		if (owner & MUTEX_FLAG_HANDOFF)
+			break;
+
+		old = atomic_long_cmpxchg_release(&lock->owner, owner,
+						  __owner_flags(owner));
+		if (old == owner) {
+			if (owner & MUTEX_FLAG_WAITERS)
+				break;
+
+			return;
+		}
+
+		owner = old;
+	}
 
 	spin_lock_mutex(&lock->wait_lock, flags);
-	mutex_release(&lock->dep_map, nested, _RET_IP_);
 	debug_mutex_unlock(lock);
-
 	if (!list_empty(&lock->wait_list)) {
 		/* get the first entry from the wait-list: */
 		struct mutex_waiter *waiter =
-				list_entry(lock->wait_list.next,
-					   struct mutex_waiter, list);
+			list_first_entry(&lock->wait_list,
+					 struct mutex_waiter, list);
+
+		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
-		wake_q_add(&wake_q, waiter->task);
+		wake_q_add(&wake_q, next);
 	}
 
+	if (owner & MUTEX_FLAG_HANDOFF)
+		__mutex_handoff(lock, next);
+
 	spin_unlock_mutex(&lock->wait_lock, flags);
+
 	wake_up_q(&wake_q);
 }
 
-/*
- * Release the lock, slowpath:
- */
-__visible void
-__mutex_unlock_slowpath(atomic_t *lock_count)
-{
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
-
-	__mutex_unlock_common_slowpath(lock, 1);
-}
-
 #ifndef CONFIG_DEBUG_LOCK_ALLOC
 /*
  * Here come the less common (and hence less performance-critical) APIs:
@@ -789,38 +929,30 @@ __mutex_lock_interruptible_slowpath(struct mutex *lock);
  */
 int __sched mutex_lock_interruptible(struct mutex *lock)
 {
-	int ret;
-
 	might_sleep();
-	ret =  __mutex_fastpath_lock_retval(&lock->count);
-	if (likely(!ret)) {
-		mutex_set_owner(lock);
+
+	if (__mutex_trylock_fast(lock))
 		return 0;
-	} else
-		return __mutex_lock_interruptible_slowpath(lock);
+
+	return __mutex_lock_interruptible_slowpath(lock);
 }
 
 EXPORT_SYMBOL(mutex_lock_interruptible);
 
 int __sched mutex_lock_killable(struct mutex *lock)
 {
-	int ret;
-
 	might_sleep();
-	ret = __mutex_fastpath_lock_retval(&lock->count);
-	if (likely(!ret)) {
-		mutex_set_owner(lock);
+
+	if (__mutex_trylock_fast(lock))
 		return 0;
-	} else
-		return __mutex_lock_killable_slowpath(lock);
+
+	return __mutex_lock_killable_slowpath(lock);
 }
 EXPORT_SYMBOL(mutex_lock_killable);
 
-__visible void __sched
-__mutex_lock_slowpath(atomic_t *lock_count)
+static noinline void __sched
+__mutex_lock_slowpath(struct mutex *lock)
 {
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
-
 	__mutex_lock_common(lock, TASK_UNINTERRUPTIBLE, 0,
 			    NULL, _RET_IP_, NULL, 0);
 }
@@ -856,37 +988,6 @@ __ww_mutex_lock_interruptible_slowpath(struct ww_mutex *lock,
 
 #endif
 
-/*
- * Spinlock based trylock, we take the spinlock and check whether we
- * can get the lock:
- */
-static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
-{
-	struct mutex *lock = container_of(lock_count, struct mutex, count);
-	unsigned long flags;
-	int prev;
-
-	/* No need to trylock if the mutex is locked. */
-	if (mutex_is_locked(lock))
-		return 0;
-
-	spin_lock_mutex(&lock->wait_lock, flags);
-
-	prev = atomic_xchg_acquire(&lock->count, -1);
-	if (likely(prev == 1)) {
-		mutex_set_owner(lock);
-		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
-	}
-
-	/* Set it back to 0 if there are no waiters: */
-	if (likely(list_empty(&lock->wait_list)))
-		atomic_set(&lock->count, 0);
-
-	spin_unlock_mutex(&lock->wait_lock, flags);
-
-	return prev == 1;
-}
-
 /**
  * mutex_trylock - try to acquire the mutex, without waiting
  * @lock: the mutex to be acquired
@@ -903,13 +1004,12 @@ static inline int __mutex_trylock_slowpath(atomic_t *lock_count)
  */
 int __sched mutex_trylock(struct mutex *lock)
 {
-	int ret;
+	bool locked = __mutex_trylock(lock, false);
 
-	ret = __mutex_fastpath_trylock(&lock->count, __mutex_trylock_slowpath);
-	if (ret)
-		mutex_set_owner(lock);
+	if (locked)
+		mutex_acquire(&lock->dep_map, 0, 1, _RET_IP_);
 
-	return ret;
+	return locked;
 }
 EXPORT_SYMBOL(mutex_trylock);
 
@@ -917,36 +1017,28 @@ EXPORT_SYMBOL(mutex_trylock);
 int __sched
 __ww_mutex_lock(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	int ret;
-
 	might_sleep();
 
-	ret = __mutex_fastpath_lock_retval(&lock->base.count);
-
-	if (likely(!ret)) {
+	if (__mutex_trylock_fast(&lock->base)) {
 		ww_mutex_set_context_fastpath(lock, ctx);
-		mutex_set_owner(&lock->base);
-	} else
-		ret = __ww_mutex_lock_slowpath(lock, ctx);
-	return ret;
+		return 0;
+	}
+
+	return __ww_mutex_lock_slowpath(lock, ctx);
 }
 EXPORT_SYMBOL(__ww_mutex_lock);
 
 int __sched
 __ww_mutex_lock_interruptible(struct ww_mutex *lock, struct ww_acquire_ctx *ctx)
 {
-	int ret;
-
 	might_sleep();
 
-	ret = __mutex_fastpath_lock_retval(&lock->base.count);
-
-	if (likely(!ret)) {
+	if (__mutex_trylock_fast(&lock->base)) {
 		ww_mutex_set_context_fastpath(lock, ctx);
-		mutex_set_owner(&lock->base);
-	} else
-		ret = __ww_mutex_lock_interruptible_slowpath(lock, ctx);
-	return ret;
+		return 0;
+	}
+
+	return __ww_mutex_lock_interruptible_slowpath(lock, ctx);
 }
 EXPORT_SYMBOL(__ww_mutex_lock_interruptible);
 
diff --git a/kernel/locking/mutex.h b/kernel/locking/mutex.h
index 6cd6b8e..4410a4a 100644
--- a/kernel/locking/mutex.h
+++ b/kernel/locking/mutex.h
@@ -16,32 +16,6 @@
 #define mutex_remove_waiter(lock, waiter, task) \
 		__list_del((waiter)->list.prev, (waiter)->list.next)
 
-#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
-/*
- * The mutex owner can get read and written to locklessly.
- * We should use WRITE_ONCE when writing the owner value to
- * avoid store tearing, otherwise, a thread could potentially
- * read a partially written and incomplete owner value.
- */
-static inline void mutex_set_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, current);
-}
-
-static inline void mutex_clear_owner(struct mutex *lock)
-{
-	WRITE_ONCE(lock->owner, NULL);
-}
-#else
-static inline void mutex_set_owner(struct mutex *lock)
-{
-}
-
-static inline void mutex_clear_owner(struct mutex *lock)
-{
-}
-#endif
-
 #define debug_mutex_wake_waiter(lock, waiter)		do { } while (0)
 #define debug_mutex_free_waiter(waiter)			do { } while (0)
 #define debug_mutex_add_waiter(lock, waiter, ti)	do { } while (0)
diff --git a/kernel/locking/osq_lock.c b/kernel/locking/osq_lock.c
index 05a3785..a316794 100644
--- a/kernel/locking/osq_lock.c
+++ b/kernel/locking/osq_lock.c
@@ -21,6 +21,11 @@ static inline int encode_cpu(int cpu_nr)
 	return cpu_nr + 1;
 }
 
+static inline int node_cpu(struct optimistic_spin_node *node)
+{
+	return node->cpu - 1;
+}
+
 static inline struct optimistic_spin_node *decode_cpu(int encoded_cpu_val)
 {
 	int cpu_nr = encoded_cpu_val - 1;
@@ -75,7 +80,7 @@ osq_wait_next(struct optimistic_spin_queue *lock,
 				break;
 		}
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 
 	return next;
@@ -118,11 +123,13 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 	while (!READ_ONCE(node->locked)) {
 		/*
 		 * If we need to reschedule bail... so we can block.
+		 * Use vcpu_is_preempted() to avoid waiting for a preempted
+		 * lock holder:
 		 */
-		if (need_resched())
+		if (need_resched() || vcpu_is_preempted(node_cpu(node->prev)))
 			goto unqueue;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	return true;
 
@@ -148,7 +155,7 @@ bool osq_lock(struct optimistic_spin_queue *lock)
 		if (smp_load_acquire(&node->locked))
 			return true;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 
 		/*
 		 * Or we race against a concurrent unqueue()'s step-B, in which
diff --git a/kernel/locking/qrwlock.c b/kernel/locking/qrwlock.c
index 19248dd..cc3ed0c 100644
--- a/kernel/locking/qrwlock.c
+++ b/kernel/locking/qrwlock.c
@@ -54,7 +54,7 @@ static __always_inline void
 rspin_until_writer_unlock(struct qrwlock *lock, u32 cnts)
 {
 	while ((cnts & _QW_WMASK) == _QW_LOCKED) {
-		cpu_relax_lowlatency();
+		cpu_relax();
 		cnts = atomic_read_acquire(&lock->cnts);
 	}
 }
@@ -130,7 +130,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
 		   (cmpxchg_relaxed(&l->wmode, 0, _QW_WAITING) == 0))
 			break;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 
 	/* When no more readers, set the locked flag */
@@ -141,7 +141,7 @@ void queued_write_lock_slowpath(struct qrwlock *lock)
 					    _QW_LOCKED) == _QW_WAITING))
 			break;
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 unlock:
 	arch_spin_unlock(&lock->wait_lock);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2c49d76..2f443ed 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1446,7 +1446,7 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
 		    bool (*slowfn)(struct rt_mutex *lock,
 				   struct wake_q_head *wqh))
 {
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	if (likely(rt_mutex_cmpxchg_release(lock, current, NULL))) {
 		rt_mutex_deadlock_account_unlock(current);
@@ -1619,11 +1619,15 @@ EXPORT_SYMBOL_GPL(__rt_mutex_init);
  * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a
  *				proxy owner
  *
- * @lock: 	the rt_mutex to be locked
+ * @lock:	the rt_mutex to be locked
  * @proxy_owner:the task to set as owner
  *
  * No locking. Caller has to do serializing itself
- * Special API call for PI-futex support
+ *
+ * Special API call for PI-futex support. This initializes the rtmutex and
+ * assigns it to @proxy_owner. Concurrent operations on the rtmutex are not
+ * possible at this point because the pi_state which contains the rtmutex
+ * is not yet visible to other tasks.
  */
 void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 				struct task_struct *proxy_owner)
@@ -1637,10 +1641,14 @@ void rt_mutex_init_proxy_locked(struct rt_mutex *lock,
 /**
  * rt_mutex_proxy_unlock - release a lock on behalf of owner
  *
- * @lock: 	the rt_mutex to be locked
+ * @lock:	the rt_mutex to be locked
  *
  * No locking. Caller has to do serializing itself
- * Special API call for PI-futex support
+ *
+ * Special API call for PI-futex support. This merrily cleans up the rtmutex
+ * (debugging) state. Concurrent operations on this rt_mutex are not
+ * possible because it belongs to the pi_state which is about to be freed
+ * and it is not longer visible to other tasks.
  */
 void rt_mutex_proxy_unlock(struct rt_mutex *lock,
 			   struct task_struct *proxy_owner)
diff --git a/kernel/locking/rtmutex_common.h b/kernel/locking/rtmutex_common.h
index e317e1c..9901346 100644
--- a/kernel/locking/rtmutex_common.h
+++ b/kernel/locking/rtmutex_common.h
@@ -71,13 +71,12 @@ task_top_pi_waiter(struct task_struct *p)
  * lock->owner state tracking:
  */
 #define RT_MUTEX_HAS_WAITERS	1UL
-#define RT_MUTEX_OWNER_MASKALL	1UL
 
 static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
 {
 	unsigned long owner = (unsigned long) READ_ONCE(lock->owner);
 
-	return (struct task_struct *) (owner & ~RT_MUTEX_OWNER_MASKALL);
+	return (struct task_struct *) (owner & ~RT_MUTEX_HAS_WAITERS);
 }
 
 /*
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 2337b4b..6315060 100644
--- a/kernel/locking/rwsem-xadd.c
+++ b/kernel/locking/rwsem-xadd.c
@@ -225,7 +225,7 @@ struct rw_semaphore __sched *rwsem_down_read_failed(struct rw_semaphore *sem)
 	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
 	struct rwsem_waiter waiter;
 	struct task_struct *tsk = current;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	waiter.task = tsk;
 	waiter.type = RWSEM_WAITING_FOR_READ;
@@ -336,7 +336,11 @@ static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
 		goto done;
 	}
 
-	ret = owner->on_cpu;
+	/*
+	 * As lock holder preemption issue, we both skip spinning if task is not
+	 * on cpu or its cpu is preempted
+	 */
+	ret = owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
 done:
 	rcu_read_unlock();
 	return ret;
@@ -362,13 +366,17 @@ static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
 		 */
 		barrier();
 
-		/* abort spinning when need_resched or owner is not running */
-		if (!owner->on_cpu || need_resched()) {
+		/*
+		 * abort spinning when need_resched or owner is not running or
+		 * owner's cpu is preempted.
+		 */
+		if (!owner->on_cpu || need_resched() ||
+				vcpu_is_preempted(task_cpu(owner))) {
 			rcu_read_unlock();
 			return false;
 		}
 
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	rcu_read_unlock();
 out:
@@ -423,7 +431,7 @@ static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
 		 * memory barriers as we'll eventually observe the right
 		 * values at the cost of a few extra spins.
 		 */
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	osq_unlock(&sem->osq);
 done:
@@ -461,7 +469,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 	bool waiting = true; /* any queued threads before us */
 	struct rwsem_waiter waiter;
 	struct rw_semaphore *ret = sem;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	/* undo write bias from down_write operation, stop active locking */
 	count = atomic_long_sub_return(RWSEM_ACTIVE_WRITE_BIAS, &sem->count);
@@ -495,7 +503,7 @@ __rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
 		 * wake any read locks that were queued ahead of us.
 		 */
 		if (count > RWSEM_WAITING_BIAS) {
-			WAKE_Q(wake_q);
+			DEFINE_WAKE_Q(wake_q);
 
 			__rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
 			/*
@@ -571,7 +579,7 @@ __visible
 struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	/*
 	 * If a spinner is present, it is not necessary to do the wakeup.
@@ -625,7 +633,7 @@ __visible
 struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
-	WAKE_Q(wake_q);
+	DEFINE_WAKE_Q(wake_q);
 
 	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 154fd68..8b08fb2 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -75,11 +75,11 @@
 #include <linux/compiler.h>
 #include <linux/frame.h>
 #include <linux/prefetch.h>
+#include <linux/mutex.h>
 
 #include <asm/switch_to.h>
 #include <asm/tlb.h>
 #include <asm/irq_regs.h>
-#include <asm/mutex.h>
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
 #endif
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index ec9ab2f..1eb8266 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -194,7 +194,7 @@ static int multi_cpu_stop(void *data)
 	/* Simple state machine */
 	do {
 		/* Chill out and ensure we re-read multi_stop_state. */
-		cpu_relax();
+		cpu_relax_yield();
 		if (msdata->state != curstate) {
 			curstate = msdata->state;
 			switch (curstate) {
diff --git a/lib/lockref.c b/lib/lockref.c
index 5a92189..c4bfcb8 100644
--- a/lib/lockref.c
+++ b/lib/lockref.c
@@ -20,7 +20,7 @@
 		if (likely(old.lock_count == prev.lock_count)) {		\
 			SUCCESS;						\
 		}								\
-		cpu_relax_lowlatency();						\
+		cpu_relax();							\
 	}									\
 } while (0)
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 1d33ce0..3fec23c 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5064,7 +5064,7 @@ bool sk_busy_loop(struct sock *sk, int nonblock)
 				return rc;
 			goto restart;
 		}
-		cpu_relax_lowlatency();
+		cpu_relax();
 	}
 	if (napi_poll)
 		busy_poll_stop(napi, have_poll_lock);
diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl
index a8368d1..23f462f6 100755
--- a/scripts/checkpatch.pl
+++ b/scripts/checkpatch.pl
@@ -6076,6 +6076,12 @@
 			}
 		}
 
+# check for mutex_trylock_recursive usage
+		if ($line =~ /mutex_trylock_recursive/) {
+			ERROR("LOCKING",
+			      "recursive locking is bad, do not use this ever.\n" . $herecurr);
+		}
+
 # check for lockdep_set_novalidate_class
 		if ($line =~ /^.\s*lockdep_set_novalidate_class\s*\(/ ||
 		    $line =~ /__lockdep_no_validate__\s*\)/ ) {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 7f9ee29..c55f5d6 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1972,30 +1972,38 @@ int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
 }
 EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
 
-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)
 {
 	struct kvm_memslots *slots = kvm_memslots(kvm);
 	int r;
+	gpa_t gpa = ghc->gpa + offset;
 
-	BUG_ON(len > ghc->len);
+	BUG_ON(len + offset > ghc->len);
 
 	if (slots->generation != ghc->generation)
 		kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len);
 
 	if (unlikely(!ghc->memslot))
-		return kvm_write_guest(kvm, ghc->gpa, data, len);
+		return kvm_write_guest(kvm, gpa, data, len);
 
 	if (kvm_is_error_hva(ghc->hva))
 		return -EFAULT;
 
-	r = __copy_to_user((void __user *)ghc->hva, data, len);
+	r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
 	if (r)
 		return -EFAULT;
-	mark_page_dirty_in_slot(ghc->memslot, ghc->gpa >> PAGE_SHIFT);
+	mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached);
+
+int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+			   void *data, unsigned long len)
+{
+	return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len);
+}
 EXPORT_SYMBOL_GPL(kvm_write_guest_cached);
 
 int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,