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

Pull core locking changes from Ingo Molnar:
 - futex performance increases: larger hashes, smarter wakeups
 - mutex debugging improvements
 - lots of SMP ordering documentation updates
 - introduce the smp_load_acquire(), smp_store_release() primitives.
   (There are WIP patches that make use of them - not yet merged)
 - lockdep micro-optimizations
 - lockdep improvement: better cover IRQ contexts
 - liblockdep at last. We'll continue to monitor how useful this is

* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (34 commits)
  futexes: Fix futex_hashsize initialization
  arch: Re-sort some Kbuild files to hopefully help avoid some conflicts
  futexes: Avoid taking the hb->lock if there's nothing to wake up
  futexes: Document multiprocessor ordering guarantees
  futexes: Increase hash table size for better performance
  futexes: Clean up various details
  arch: Introduce smp_load_acquire(), smp_store_release()
  arch: Clean up asm/barrier.h implementations using asm-generic/barrier.h
  arch: Move smp_mb__{before,after}_atomic_{inc,dec}.h into asm/atomic.h
  locking/doc: Rename LOCK/UNLOCK to ACQUIRE/RELEASE
  mutexes: Give more informative mutex warning in the !lock->owner case
  powerpc: Full barrier for smp_mb__after_unlock_lock()
  rcu: Apply smp_mb__after_unlock_lock() to preserve grace periods
  Documentation/memory-barriers.txt: Downgrade UNLOCK+BLOCK
  locking: Add an smp_mb__after_unlock_lock() for UNLOCK+BLOCK barrier
  Documentation/memory-barriers.txt: Document ACCESS_ONCE()
  Documentation/memory-barriers.txt: Prohibit speculative writes
  Documentation/memory-barriers.txt: Add long atomic examples to memory-barriers.txt
  Documentation/memory-barriers.txt: Add needed ACCESS_ONCE() calls to memory-barriers.txt
  Revert "smp/cpumask: Make CONFIG_CPUMASK_OFFSTACK=y usable without debug dependency"
  ...

Documentation/robust-futex-ABI.txt

@@ -146,8 +146,8 @@ On removal:
  1) set the 'list_op_pending' word to the address of the 'lock entry'
     to be removed,
  2) remove the lock entry for this lock from the 'head' list,
- 2) release the futex lock, and
- 2) clear the 'lock_op_pending' word.
+ 3) release the futex lock, and
+ 4) clear the 'lock_op_pending' word.
 
 On exit, the kernel will consider the address stored in
 'list_op_pending' and the address of each 'lock word' found by walking

MAINTAINERS

@@ -5141,6 +5141,11 @@ F:	drivers/lguest/
 F:	include/linux/lguest*.h
 F:	tools/lguest/
 
+LIBLOCKDEP
+M:	Sasha Levin <sasha.levin@oracle.com>
+S:	Maintained
+F:	tools/lib/lockdep/
+
 LINUX FOR IBM pSERIES (RS/6000)
 M:	Paul Mackerras <paulus@au.ibm.com>
 W:	http://www.ibm.com/linux/ltc/projects/ppc

arch/alpha/include/asm/barrier.h

@@ -3,33 +3,18 @@
 
 #include <asm/compiler.h>
 
-#define mb() \
-__asm__ __volatile__("mb": : :"memory")
+#define mb()	__asm__ __volatile__("mb": : :"memory")
+#define rmb()	__asm__ __volatile__("mb": : :"memory")
+#define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-#define rmb() \
-__asm__ __volatile__("mb": : :"memory")
-
-#define wmb() \
-__asm__ __volatile__("wmb": : :"memory")
-
-#define read_barrier_depends() \
-__asm__ __volatile__("mb": : :"memory")
+#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define __ASM_SMP_MB
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
 #endif
 
-#define set_mb(var, value) \
-do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif		/* __BARRIER_H */

arch/arc/include/asm/Kbuild

 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bugs.h
 generic-y += bitsperlong.h
 generic-y += clkdev.h

arch/arc/include/asm/atomic.h

@@ -190,6 +190,11 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
 
 #endif /* !CONFIG_ARC_HAS_LLSC */
 
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
 /**
  * __atomic_add_unless - add unless the number is a given value
  * @v: pointer of type atomic_t

arch/arc/include/asm/barrier.h

@@ -30,11 +30,6 @@
 #define smp_wmb()       barrier()
 #endif
 
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
-
 #define smp_read_barrier_depends()      do { } while (0)
 
 #endif

arch/arm/include/asm/barrier.h

@@ -59,6 +59,21 @@
 #define smp_wmb()	dmb(ishst)
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #define read_barrier_depends()		do { } while(0)
 #define smp_read_barrier_depends()	do { } while(0)
 

arch/arm64/include/asm/barrier.h

@@ -35,10 +35,60 @@
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #else
+
 #define smp_mb()	asm volatile("dmb ish" : : : "memory")
 #define smp_rmb()	asm volatile("dmb ishld" : : : "memory")
 #define smp_wmb()	asm volatile("dmb ishst" : : : "memory")
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("stlr %w1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	case 8:								\
+		asm volatile ("stlr %1, %0"				\
+				: "=Q" (*p) : "r" (v) : "memory");	\
+		break;							\
+	}								\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1;						\
+	compiletime_assert_atomic_type(*p);				\
+	switch (sizeof(*p)) {						\
+	case 4:								\
+		asm volatile ("ldar %w0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	case 8:								\
+		asm volatile ("ldar %0, %1"				\
+			: "=r" (___p1) : "Q" (*p) : "memory");		\
+		break;							\
+	}								\
+	___p1;								\
+})
+
 #endif
 
 #define read_barrier_depends()		do { } while(0)

arch/avr32/include/asm/barrier.h

@@ -8,22 +8,15 @@
 #ifndef __ASM_AVR32_BARRIER_H
 #define __ASM_AVR32_BARRIER_H
 
-#define nop()			asm volatile("nop")
-
-#define mb()			asm volatile("" : : : "memory")
-#define rmb()			mb()
+/*
+ * Weirdest thing ever.. no full barrier, but it has a write barrier!
+ */
 #define wmb()	asm volatile("sync 0" : : : "memory")
-#define read_barrier_depends()  do { } while(0)
-#define set_mb(var, value)      do { var = value; mb(); } while(0)
 
 #ifdef CONFIG_SMP
 # error "The AVR32 port does not support SMP"
-#else
-# define smp_mb()		barrier()
-# define smp_rmb()		barrier()
-# define smp_wmb()		barrier()
-# define smp_read_barrier_depends() do { } while(0)
 #endif
 
+#include <asm-generic/barrier.h>
 
 #endif /* __ASM_AVR32_BARRIER_H */

arch/blackfin/include/asm/barrier.h

@@ -23,26 +23,10 @@
 # define rmb()	do { barrier(); smp_check_barrier(); } while (0)
 # define wmb()	do { barrier(); smp_mark_barrier(); } while (0)
 # define read_barrier_depends()	do { barrier(); smp_check_barrier(); } while (0)
-#else
-# define mb()	barrier()
-# define rmb()	barrier()
-# define wmb()	barrier()
-# define read_barrier_depends()	do { } while (0)
 #endif
 
-#else /* !CONFIG_SMP */
-
-#define mb()	barrier()
-#define rmb()	barrier()
-#define wmb()	barrier()
-#define read_barrier_depends()	do { } while (0)
-
 #endif /* !CONFIG_SMP */
 
-#define smp_mb()  mb()
-#define smp_rmb() rmb()
-#define smp_wmb() wmb()
-#define set_mb(var, value) do { var = value; mb(); } while (0)
-#define smp_read_barrier_depends()	read_barrier_depends()
+#include <asm-generic/barrier.h>
 
 #endif /* _BLACKFIN_BARRIER_H */

arch/cris/include/asm/Kbuild

@@ -3,6 +3,7 @@ header-y += arch-v10/
 header-y += arch-v32/
 
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += kvm_para.h

arch/cris/include/asm/barrier.h

-#ifndef __ASM_CRIS_BARRIER_H
-#define __ASM_CRIS_BARRIER_H
-
-#define nop() __asm__ __volatile__ ("nop");
-
-#define barrier() __asm__ __volatile__("": : :"memory")
-#define mb() barrier()
-#define rmb() mb()
-#define wmb() mb()
-#define read_barrier_depends() do { } while(0)
-#define set_mb(var, value)  do { var = value; mb(); } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()        mb()
-#define smp_rmb()       rmb()
-#define smp_wmb()       wmb()
-#define smp_read_barrier_depends()     read_barrier_depends()
-#else
-#define smp_mb()        barrier()
-#define smp_rmb()       barrier()
-#define smp_wmb()       barrier()
-#define smp_read_barrier_depends()     do { } while(0)
-#endif
-
-#endif /* __ASM_CRIS_BARRIER_H */

arch/frv/include/asm/barrier.h

@@ -17,13 +17,7 @@
 #define mb()			asm volatile ("membar" : : :"memory")
 #define rmb()			asm volatile ("membar" : : :"memory")
 #define wmb()			asm volatile ("membar" : : :"memory")
-#define read_barrier_depends()	do { } while (0)
 
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define smp_read_barrier_depends()	do {} while(0)
-#define set_mb(var, value) \
-	do { var = (value); barrier(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* _ASM_BARRIER_H */

arch/hexagon/include/asm/Kbuild

@@ -2,6 +2,7 @@
 header-y += ucontext.h
 
 generic-y += auxvec.h
+generic-y += barrier.h
 generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h

arch/hexagon/include/asm/atomic.h

@@ -160,8 +160,12 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 #define atomic_sub_and_test(i, v) (atomic_sub_return(i, (v)) == 0)
 #define atomic_add_negative(i, v) (atomic_add_return(i, (v)) < 0)
 
-
 #define atomic_inc_return(v) (atomic_add_return(1, v))
 #define atomic_dec_return(v) (atomic_sub_return(1, v))
 
+#define smp_mb__before_atomic_dec()	barrier()
+#define smp_mb__after_atomic_dec()	barrier()
+#define smp_mb__before_atomic_inc()	barrier()
+#define smp_mb__after_atomic_inc()	barrier()
+
 #endif

arch/hexagon/include/asm/barrier.h

@@ -29,10 +29,6 @@
 #define smp_read_barrier_depends()	barrier()
 #define smp_wmb()			barrier()
 #define smp_mb()			barrier()
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
 
 /*  Set a value and use a memory barrier.  Used by the scheduler somewhere.  */
 #define set_mb(var, value) \

arch/ia64/include/asm/barrier.h

@@ -45,13 +45,36 @@
 # define smp_rmb()	rmb()
 # define smp_wmb()	wmb()
 # define smp_read_barrier_depends()	read_barrier_depends()
+
 #else
+
 # define smp_mb()	barrier()
 # define smp_rmb()	barrier()
 # define smp_wmb()	barrier()
 # define smp_read_barrier_depends()	do { } while(0)
+
 #endif
 
+/*
+ * IA64 GCC turns volatile stores into st.rel and volatile loads into ld.acq no
+ * need for asm trickery!
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 /*
  * XXX check on this ---I suspect what Linus really wants here is
  * acquire vs release semantics but we can't discuss this stuff with

arch/m32r/include/asm/barrier.h

@@ -11,84 +11,6 @@
 
 #define nop()  __asm__ __volatile__ ("nop" : : )
 
-/*
- * Memory barrier.
- *
- * mb() prevents loads and stores being reordered across this point.
- * rmb() prevents loads being reordered across this point.
- * wmb() prevents stores being reordered across this point.
- */
-#define mb()   barrier()
-#define rmb()  mb()
-#define wmb()  mb()
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      b = 2;
- *      memory_barrier();
- *      p = &b;                         q = p;
- *                                      read_barrier_depends();
- *                                      d = *q;
- * </programlisting>
- *
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *      CPU 0                           CPU 1
- *
- *      a = 2;
- *      memory_barrier();
- *      b = 3;                          y = b;
- *                                      read_barrier_depends();
- *                                      x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void) xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
+#include <asm-generic/barrier.h>
 
 #endif /* _ASM_M32R_BARRIER_H */

arch/m68k/include/asm/barrier.h

 #ifndef _M68K_BARRIER_H
 #define _M68K_BARRIER_H
 
-/*
- * Force strict CPU ordering.
- * Not really required on m68k...
- */
 #define nop()		do { asm volatile ("nop"); barrier(); } while (0)
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define read_barrier_depends()	((void)0)
-#define set_mb(var, value)	({ (var) = (value); wmb(); })
 
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	((void)0)
+#include <asm-generic/barrier.h>
 
 #endif /* _M68K_BARRIER_H */

arch/metag/include/asm/barrier.h

@@ -82,4 +82,19 @@ static inline void fence(void)
 #define smp_read_barrier_depends()     do { } while (0)
 #define set_mb(var, value) do { var = value; smp_mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* _ASM_METAG_BARRIER_H */

arch/microblaze/include/asm/Kbuild

 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h

arch/microblaze/include/asm/barrier.h

-/*
- * Copyright (C) 2006 Atmark Techno, Inc.
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License. See the file "COPYING" in the main directory of this archive
- * for more details.
- */
-
-#ifndef _ASM_MICROBLAZE_BARRIER_H
-#define _ASM_MICROBLAZE_BARRIER_H
-
-#define nop()                  asm volatile ("nop")
-
-#define smp_read_barrier_depends()	do {} while (0)
-#define read_barrier_depends()		do {} while (0)
-
-#define mb()			barrier()
-#define rmb()			mb()
-#define wmb()			mb()
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
-#define set_wmb(var, value)	do { var = value; wmb(); } while (0)
-
-#define smp_mb()		mb()
-#define smp_rmb()		rmb()
-#define smp_wmb()		wmb()
-
-#endif /* _ASM_MICROBLAZE_BARRIER_H */

arch/mips/include/asm/barrier.h

@@ -180,4 +180,19 @@
 #define nudge_writes() mb()
 #endif
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */

arch/mn10300/include/asm/Kbuild

 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += exec.h
 generic-y += trace_clock.h

arch/mn10300/include/asm/barrier.h

-/* MN10300 memory barrier definitions
- *
- * 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.
- */
-#ifndef _ASM_BARRIER_H
-#define _ASM_BARRIER_H
-
-#define nop()	asm volatile ("nop")
-
-#define mb()	asm volatile ("": : :"memory")
-#define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define set_mb(var, value)  do { xchg(&var, value); } while (0)
-#else  /* CONFIG_SMP */
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#endif /* CONFIG_SMP */
-
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#endif /* _ASM_BARRIER_H */

arch/parisc/include/asm/Kbuild

 
+generic-y += barrier.h
 generic-y += word-at-a-time.h auxvec.h user.h cputime.h emergency-restart.h \
 	  segment.h topology.h vga.h device.h percpu.h hw_irq.h mutex.h \
 	  div64.h irq_regs.h kdebug.h kvm_para.h local64.h local.h param.h \

arch/parisc/include/asm/barrier.h

-#ifndef __PARISC_BARRIER_H
-#define __PARISC_BARRIER_H
-
-/*
-** This is simply the barrier() macro from linux/kernel.h but when serial.c
-** uses tqueue.h uses smp_mb() defined using barrier(), linux/kernel.h
-** hasn't yet been included yet so it fails, thus repeating the macro here.
-**
-** PA-RISC architecture allows for weakly ordered memory accesses although
-** none of the processors use it. There is a strong ordered bit that is
-** set in the O-bit of the page directory entry. Operating systems that
-** can not tolerate out of order accesses should set this bit when mapping
-** pages. The O-bit of the PSW should also be set to 1 (I don't believe any
-** of the processor implemented the PSW O-bit). The PCX-W ERS states that
-** the TLB O-bit is not implemented so the page directory does not need to
-** have the O-bit set when mapping pages (section 3.1). This section also
-** states that the PSW Y, Z, G, and O bits are not implemented.
-** So it looks like nothing needs to be done for parisc-linux (yet).
-** (thanks to chada for the above comment -ggg)
-**
-** The __asm__ op below simple prevents gcc/ld from reordering
-** instructions across the mb() "call".
-*/
-#define mb()		__asm__ __volatile__("":::"memory")	/* barrier() */
-#define rmb()		mb()
-#define wmb()		mb()
-#define smp_mb()	mb()
-#define smp_rmb()	mb()
-#define smp_wmb()	mb()
-#define smp_read_barrier_depends()	do { } while(0)
-#define read_barrier_depends()		do { } while(0)
-
-#define set_mb(var, value)		do { var = value; mb(); } while (0)
-
-#endif /* __PARISC_BARRIER_H */

arch/powerpc/include/asm/barrier.h

@@ -45,11 +45,15 @@
 #    define SMPWMB      eieio
 #endif
 
+#define __lwsync()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+
 #define smp_mb()	mb()
-#define smp_rmb()	__asm__ __volatile__ (stringify_in_c(LWSYNC) : : :"memory")
+#define smp_rmb()	__lwsync()
 #define smp_wmb()	__asm__ __volatile__ (stringify_in_c(SMPWMB) : : :"memory")
 #define smp_read_barrier_depends()	read_barrier_depends()
 #else
+#define __lwsync()	barrier()
+
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
@@ -65,4 +69,19 @@
 #define data_barrier(x)	\
 	asm volatile("twi 0,%0,0; isync" : : "r" (x) : "memory");
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	__lwsync();							\
+	___p1;								\
+})
+
 #endif /* _ASM_POWERPC_BARRIER_H */

arch/powerpc/include/asm/spinlock.h

@@ -28,6 +28,8 @@
 #include <asm/synch.h>
 #include <asm/ppc-opcode.h>
 
+#define smp_mb__after_unlock_lock()	smp_mb()  /* Full ordering for lock. */
+
 #define arch_spin_is_locked(x)		((x)->slock != 0)
 
 #ifdef CONFIG_PPC64

arch/s390/include/asm/barrier.h

@@ -32,4 +32,19 @@
 
 #define set_mb(var, value)		do { var = value; mb(); } while (0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* __ASM_BARRIER_H */

arch/score/include/asm/Kbuild

 
 header-y +=
 
+generic-y += barrier.h
 generic-y += clkdev.h
 generic-y += trace_clock.h
 generic-y += xor.h

arch/score/include/asm/barrier.h

-#ifndef _ASM_SCORE_BARRIER_H
-#define _ASM_SCORE_BARRIER_H
-
-#define mb()		barrier()
-#define rmb()		barrier()
-#define wmb()		barrier()
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
-
-#define set_mb(var, value) 		do {var = value; wmb(); } while (0)
-
-#endif /* _ASM_SCORE_BARRIER_H */

arch/sh/include/asm/barrier.h

@@ -26,29 +26,14 @@
 #if defined(CONFIG_CPU_SH4A) || defined(CONFIG_CPU_SH5)
 #define mb()		__asm__ __volatile__ ("synco": : :"memory")
 #define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("synco": : :"memory")
+#define wmb()		mb()
 #define ctrl_barrier()	__icbi(PAGE_OFFSET)
-#define read_barrier_depends()	do { } while(0)
 #else
-#define mb()		__asm__ __volatile__ ("": : :"memory")
-#define rmb()		mb()
-#define wmb()		__asm__ __volatile__ ("": : :"memory")
 #define ctrl_barrier()	__asm__ __volatile__ ("nop;nop;nop;nop;nop;nop;nop;nop")
-#define read_barrier_depends()	do { } while(0)
-#endif
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while(0)
 #endif
 
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
 
+#include <asm-generic/barrier.h>
+
 #endif /* __ASM_SH_BARRIER_H */

arch/sparc/include/asm/barrier_32.h

 #ifndef __SPARC_BARRIER_H
 #define __SPARC_BARRIER_H
 
-/* XXX Change this if we ever use a PSO mode kernel. */
-#define mb()	__asm__ __volatile__ ("" : : : "memory")
-#define rmb()	mb()
-#define wmb()	mb()
-#define read_barrier_depends()	do { } while(0)
-#define set_mb(__var, __value)  do { __var = __value; mb(); } while(0)
-#define smp_mb()	__asm__ __volatile__("":::"memory")
-#define smp_rmb()	__asm__ __volatile__("":::"memory")
-#define smp_wmb()	__asm__ __volatile__("":::"memory")
-#define smp_read_barrier_depends()	do { } while(0)
+#include <asm/processor.h> /* for nop() */
+#include <asm-generic/barrier.h>
 
 #endif /* !(__SPARC_BARRIER_H) */

arch/sparc/include/asm/barrier_64.h

@@ -53,4 +53,19 @@ do {	__asm__ __volatile__("ba,pt	%%xcc, 1f\n\t" \
 
 #define smp_read_barrier_depends()	do { } while(0)
 
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif /* !(__SPARC64_BARRIER_H) */

arch/tile/include/asm/barrier.h

@@ -22,59 +22,6 @@
 #include <arch/spr_def.h>
 #include <asm/timex.h>
 
-/*
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends()	do { } while (0)
-
 #define __sync()	__insn_mf()
 
 #include <hv/syscall_public.h>
@@ -125,20 +72,7 @@ mb_incoherent(void)
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#define smp_rmb()	rmb()
-#define smp_wmb()	wmb()
-#define smp_read_barrier_depends()	read_barrier_depends()
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#endif
-
-#define set_mb(var, value) \
-	do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
 #endif /* _ASM_TILE_BARRIER_H */

arch/unicore32/include/asm/barrier.h

@@ -14,15 +14,6 @@
 #define dsb() __asm__ __volatile__ ("" : : : "memory")
 #define dmb() __asm__ __volatile__ ("" : : : "memory")
 
-#define mb()				barrier()
-#define rmb()				barrier()
-#define wmb()				barrier()
-#define smp_mb()			barrier()
-#define smp_rmb()			barrier()
-#define smp_wmb()			barrier()
-#define read_barrier_depends()		do { } while (0)
-#define smp_read_barrier_depends()	do { } while (0)
-
-#define set_mb(var, value)		do { var = value; smp_mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* __UNICORE_BARRIER_H__ */

arch/x86/include/asm/barrier.h

@@ -92,12 +92,53 @@
 #endif
 #define smp_read_barrier_depends()	read_barrier_depends()
 #define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
+#else /* !SMP */
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
 #define smp_read_barrier_depends()	do { } while (0)
 #define set_mb(var, value) do { var = value; barrier(); } while (0)
+#endif /* SMP */
+
+#if defined(CONFIG_X86_OOSTORE) || defined(CONFIG_X86_PPRO_FENCE)
+
+/*
+ * For either of these options x86 doesn't have a strong TSO memory
+ * model and we should fall back to full barriers.
+ */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
+
+#else /* regular x86 TSO memory ordering */
+
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
+
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	barrier();							\
+	___p1;								\
+})
+
 #endif
 
 /*

arch/xtensa/include/asm/barrier.h

@@ -9,21 +9,14 @@
 #ifndef _XTENSA_SYSTEM_H
 #define _XTENSA_SYSTEM_H
 
-#define smp_read_barrier_depends() do { } while(0)
-#define read_barrier_depends() do { } while(0)
-
 #define mb()  ({ __asm__ __volatile__("memw" : : : "memory"); })
 #define rmb() barrier()
 #define wmb() mb()
 
 #ifdef CONFIG_SMP
 #error smp_* not defined
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
 #endif
 
-#define set_mb(var, value)	do { var = value; mb(); } while (0)
+#include <asm-generic/barrier.h>
 
 #endif /* _XTENSA_SYSTEM_H */

include/asm-generic/barrier.h

-/* Generic barrier definitions, based on MN10300 definitions.
+/*
+ * Generic barrier definitions, originally based on MN10300 definitions.
  *
  * It should be possible to use these on really simple architectures,
  * but it serves more as a starting point for new ports.
@@ -16,35 +17,65 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/compiler.h>
+
+#ifndef nop
 #define nop()	asm volatile ("nop")
+#endif
 
 /*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
+ * Force strict CPU ordering. And yes, this is required on UP too when we're
+ * talking to devices.
  *
- * This implementation only contains a compiler barrier.
+ * Fall back to compiler barriers if nothing better is provided.
  */
 
-#define mb()	asm volatile ("": : :"memory")
+#ifndef mb
+#define mb()	barrier()
+#endif
+
+#ifndef rmb
 #define rmb()	mb()
-#define wmb()	asm volatile ("": : :"memory")
+#endif
+
+#ifndef wmb
+#define wmb()	mb()
+#endif
+
+#ifndef read_barrier_depends
+#define read_barrier_depends()		do { } while (0)
+#endif
 
 #ifdef CONFIG_SMP
 #define smp_mb()	mb()
 #define smp_rmb()	rmb()
 #define smp_wmb()	wmb()
+#define smp_read_barrier_depends()	read_barrier_depends()
 #else
 #define smp_mb()	barrier()
 #define smp_rmb()	barrier()
 #define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#endif
+
+#ifndef set_mb
+#define set_mb(var, value)  do { (var) = (value); mb(); } while (0)
 #endif
 
-#define set_mb(var, value)  do { var = value;  mb(); } while (0)
-#define set_wmb(var, value) do { var = value; wmb(); } while (0)
+#define smp_store_release(p, v)						\
+do {									\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	ACCESS_ONCE(*p) = (v);						\
+} while (0)
 
-#define read_barrier_depends()		do {} while (0)
-#define smp_read_barrier_depends()	do {} while (0)
+#define smp_load_acquire(p)						\
+({									\
+	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	compiletime_assert_atomic_type(*p);				\
+	smp_mb();							\
+	___p1;								\
+})
 
 #endif /* !__ASSEMBLY__ */
 #endif /* __ASM_GENERIC_BARRIER_H */

include/linux/compiler.h

@@ -298,6 +298,11 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 # define __same_type(a, b) __builtin_types_compatible_p(typeof(a), typeof(b))
 #endif
 
+/* Is this type a native word size -- useful for atomic operations */
+#ifndef __native_word
+# define __native_word(t) (sizeof(t) == sizeof(int) || sizeof(t) == sizeof(long))
+#endif
+
 /* Compile time object size, -1 for unknown */
 #ifndef __compiletime_object_size
 # define __compiletime_object_size(obj) -1
@@ -337,6 +342,10 @@ void ftrace_likely_update(struct ftrace_branch_data *f, int val, int expect);
 #define compiletime_assert(condition, msg) \
 	_compiletime_assert(condition, msg, __compiletime_assert_, __LINE__)
 
+#define compiletime_assert_atomic_type(t)				\
+	compiletime_assert(__native_word(t),				\
+		"Need native word sized stores/loads for atomicity.")
+
 /*
  * Prevent the compiler from merging or refetching accesses.  The compiler
  * is also forbidden from reordering successive instances of ACCESS_ONCE(),

include/linux/spinlock.h

@@ -130,6 +130,16 @@ do {								\
 #define smp_mb__before_spinlock()	smp_wmb()
 #endif
 
+/*
+ * Place this after a lock-acquisition primitive to guarantee that
+ * an UNLOCK+LOCK pair act as a full barrier.  This guarantee applies
+ * if the UNLOCK and LOCK are executed by the same CPU or if the
+ * UNLOCK and LOCK operate on the same lock variable.
+ */
+#ifndef smp_mb__after_unlock_lock
+#define smp_mb__after_unlock_lock()	do { } while (0)
+#endif
+
 /**
  * raw_spin_unlock_wait - wait until the spinlock gets unlocked
  * @lock: the spinlock in question.

kernel/locking/lockdep.c

@@ -590,6 +590,7 @@ static int very_verbose(struct lock_class *class)
 /*
  * Is this the address of a static object:
  */
+#ifdef __KERNEL__
 static int static_obj(void *obj)
 {
 	unsigned long start = (unsigned long) &_stext,
@@ -616,6 +617,7 @@ static int static_obj(void *obj)
 	 */
 	return is_module_address(addr) || is_module_percpu_address(addr);
 }
+#endif
 
 /*
  * To make lock name printouts unique, we calculate a unique
@@ -4115,6 +4117,7 @@ void debug_check_no_locks_held(void)
 }
 EXPORT_SYMBOL_GPL(debug_check_no_locks_held);
 
+#ifdef __KERNEL__
 void debug_show_all_locks(void)
 {
 	struct task_struct *g, *p;
@@ -4172,6 +4175,7 @@ void debug_show_all_locks(void)
 		read_unlock(&tasklist_lock);
 }
 EXPORT_SYMBOL_GPL(debug_show_all_locks);
+#endif
 
 /*
  * Careful: only use this function if you are sure that

kernel/locking/mutex-debug.c

@@ -75,7 +75,12 @@ void debug_mutex_unlock(struct mutex *lock)
 		return;
 
 	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_clear_owner(lock);
 }

kernel/rcu/tree.c

@@ -1133,8 +1133,10 @@ rcu_start_future_gp(struct rcu_node *rnp, struct rcu_data *rdp)
 	 * hold it, acquire the root rcu_node structure's lock in order to
 	 * start one (if needed).
 	 */
-	if (rnp != rnp_root)
+	if (rnp != rnp_root) {
 		raw_spin_lock(&rnp_root->lock);
+		smp_mb__after_unlock_lock();
+	}
 
 	/*
 	 * Get a new grace-period number.  If there really is no grace
@@ -1354,6 +1356,7 @@ static void note_gp_changes(struct rcu_state *rsp, struct rcu_data *rdp)
 		local_irq_restore(flags);
 		return;
 	}
+	smp_mb__after_unlock_lock();
 	__note_gp_changes(rsp, rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 }
@@ -1368,6 +1371,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 
 	rcu_bind_gp_kthread();
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	if (rsp->gp_flags == 0) {
 		/* Spurious wakeup, tell caller to go back to sleep.  */
 		raw_spin_unlock_irq(&rnp->lock);
@@ -1409,6 +1413,7 @@ static int rcu_gp_init(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rdp = this_cpu_ptr(rsp->rda);
 		rcu_preempt_check_blocked_tasks(rnp);
 		rnp->qsmask = rnp->qsmaskinit;
@@ -1463,6 +1468,7 @@ static int rcu_gp_fqs(struct rcu_state *rsp, int fqs_state_in)
 	/* Clear flag to prevent immediate re-entry. */
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		rsp->gp_flags &= ~RCU_GP_FLAG_FQS;
 		raw_spin_unlock_irq(&rnp->lock);
 	}
@@ -1480,6 +1486,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	struct rcu_node *rnp = rcu_get_root(rsp);
 
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	gp_duration = jiffies - rsp->gp_start;
 	if (gp_duration > rsp->gp_max)
 		rsp->gp_max = gp_duration;
@@ -1505,6 +1512,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	 */
 	rcu_for_each_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irq(&rnp->lock);
+		smp_mb__after_unlock_lock();
 		ACCESS_ONCE(rnp->completed) = rsp->gpnum;
 		rdp = this_cpu_ptr(rsp->rda);
 		if (rnp == rdp->mynode)
@@ -1515,6 +1523,7 @@ static void rcu_gp_cleanup(struct rcu_state *rsp)
 	}
 	rnp = rcu_get_root(rsp);
 	raw_spin_lock_irq(&rnp->lock);
+	smp_mb__after_unlock_lock();
 	rcu_nocb_gp_set(rnp, nocb);
 
 	rsp->completed = rsp->gpnum; /* Declare grace period done. */
@@ -1749,6 +1758,7 @@ rcu_report_qs_rnp(unsigned long mask, struct rcu_state *rsp,
 		rnp_c = rnp;
 		rnp = rnp->parent;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		WARN_ON_ONCE(rnp_c->qsmask);
 	}
 
@@ -1778,6 +1788,7 @@ rcu_report_qs_rdp(int cpu, struct rcu_state *rsp, struct rcu_data *rdp)
 
 	rnp = rdp->mynode;
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (rdp->passed_quiesce == 0 || rdp->gpnum != rnp->gpnum ||
 	    rnp->completed == rnp->gpnum) {
 
@@ -1992,6 +2003,7 @@ static void rcu_cleanup_dead_cpu(int cpu, struct rcu_state *rsp)
 	mask = rdp->grpmask;	/* rnp->grplo is constant. */
 	do {
 		raw_spin_lock(&rnp->lock);	/* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rnp->qsmaskinit &= ~mask;
 		if (rnp->qsmaskinit != 0) {
 			if (rnp != rdp->mynode)
@@ -2202,6 +2214,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 		cond_resched();
 		mask = 0;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		if (!rcu_gp_in_progress(rsp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
 			return;
@@ -2231,6 +2244,7 @@ static void force_qs_rnp(struct rcu_state *rsp,
 	rnp = rcu_get_root(rsp);
 	if (rnp->qsmask == 0) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rcu_initiate_boost(rnp, flags); /* releases rnp->lock. */
 	}
 }
@@ -2263,6 +2277,7 @@ static void force_quiescent_state(struct rcu_state *rsp)
 
 	/* Reached the root of the rcu_node tree, acquire lock. */
 	raw_spin_lock_irqsave(&rnp_old->lock, flags);
+	smp_mb__after_unlock_lock();
 	raw_spin_unlock(&rnp_old->fqslock);
 	if (ACCESS_ONCE(rsp->gp_flags) & RCU_GP_FLAG_FQS) {
 		rsp->n_force_qs_lh++;
@@ -2378,6 +2393,7 @@ static void __call_rcu_core(struct rcu_state *rsp, struct rcu_data *rdp,
 			struct rcu_node *rnp_root = rcu_get_root(rsp);
 
 			raw_spin_lock(&rnp_root->lock);
+			smp_mb__after_unlock_lock();
 			rcu_start_gp(rsp);
 			raw_spin_unlock(&rnp_root->lock);
 		} else {

kernel/rcu/tree_plugin.h

@@ -204,6 +204,7 @@ static void rcu_preempt_note_context_switch(int cpu)
 		rdp = per_cpu_ptr(rcu_preempt_state.rda, cpu);
 		rnp = rdp->mynode;
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		t->rcu_read_unlock_special |= RCU_READ_UNLOCK_BLOCKED;
 		t->rcu_blocked_node = rnp;
 
@@ -312,6 +313,7 @@ static void rcu_report_unblock_qs_rnp(struct rcu_node *rnp, unsigned long flags)
 	mask = rnp->grpmask;
 	raw_spin_unlock(&rnp->lock);	/* irqs remain disabled. */
 	raw_spin_lock(&rnp_p->lock);	/* irqs already disabled. */
+	smp_mb__after_unlock_lock();
 	rcu_report_qs_rnp(mask, &rcu_preempt_state, rnp_p, flags);
 }
 
@@ -381,6 +383,7 @@ void rcu_read_unlock_special(struct task_struct *t)
 		for (;;) {
 			rnp = t->rcu_blocked_node;
 			raw_spin_lock(&rnp->lock);  /* irqs already disabled. */
+			smp_mb__after_unlock_lock();
 			if (rnp == t->rcu_blocked_node)
 				break;
 			raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
@@ -605,6 +608,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	while (!list_empty(lp)) {
 		t = list_entry(lp->next, typeof(*t), rcu_node_entry);
 		raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		list_del(&t->rcu_node_entry);
 		t->rcu_blocked_node = rnp_root;
 		list_add(&t->rcu_node_entry, lp_root);
@@ -629,6 +633,7 @@ static int rcu_preempt_offline_tasks(struct rcu_state *rsp,
 	 * in this case.
 	 */
 	raw_spin_lock(&rnp_root->lock); /* irqs already disabled */
+	smp_mb__after_unlock_lock();
 	if (rnp_root->boost_tasks != NULL &&
 	    rnp_root->boost_tasks != rnp_root->gp_tasks &&
 	    rnp_root->boost_tasks != rnp_root->exp_tasks)
@@ -772,6 +777,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 	unsigned long mask;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	for (;;) {
 		if (!sync_rcu_preempt_exp_done(rnp)) {
 			raw_spin_unlock_irqrestore(&rnp->lock, flags);
@@ -787,6 +793,7 @@ static void rcu_report_exp_rnp(struct rcu_state *rsp, struct rcu_node *rnp,
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled */
 		rnp = rnp->parent;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled */
+		smp_mb__after_unlock_lock();
 		rnp->expmask &= ~mask;
 	}
 }
@@ -806,6 +813,7 @@ sync_rcu_preempt_exp_init(struct rcu_state *rsp, struct rcu_node *rnp)
 	int must_wait = 0;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	if (list_empty(&rnp->blkd_tasks)) {
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	} else {
@@ -886,6 +894,7 @@ void synchronize_rcu_expedited(void)
 	/* Initialize ->expmask for all non-leaf rcu_node structures. */
 	rcu_for_each_nonleaf_node_breadth_first(rsp, rnp) {
 		raw_spin_lock_irqsave(&rnp->lock, flags);
+		smp_mb__after_unlock_lock();
 		rnp->expmask = rnp->qsmaskinit;
 		raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	}
@@ -1191,6 +1200,7 @@ static int rcu_boost(struct rcu_node *rnp)
 		return 0;  /* Nothing left to boost. */
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 
 	/*
 	 * Recheck under the lock: all tasks in need of boosting
@@ -1377,6 +1387,7 @@ static int rcu_spawn_one_boost_kthread(struct rcu_state *rsp,
 	if (IS_ERR(t))
 		return PTR_ERR(t);
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	rnp->boost_kthread_task = t;
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 	sp.sched_priority = RCU_BOOST_PRIO;
@@ -1769,6 +1780,7 @@ static void rcu_prepare_for_idle(int cpu)
 			continue;
 		rnp = rdp->mynode;
 		raw_spin_lock(&rnp->lock); /* irqs already disabled. */
+		smp_mb__after_unlock_lock();
 		rcu_accelerate_cbs(rsp, rnp, rdp);
 		raw_spin_unlock(&rnp->lock); /* irqs remain disabled. */
 	}
@@ -2209,6 +2221,7 @@ static void rcu_nocb_wait_gp(struct rcu_data *rdp)
 	struct rcu_node *rnp = rdp->mynode;
 
 	raw_spin_lock_irqsave(&rnp->lock, flags);
+	smp_mb__after_unlock_lock();
 	c = rcu_start_future_gp(rnp, rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
 

kernel/softirq.c

@@ -211,14 +211,48 @@ EXPORT_SYMBOL(local_bh_enable_ip);
 #define MAX_SOFTIRQ_TIME  msecs_to_jiffies(2)
 #define MAX_SOFTIRQ_RESTART 10
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+/*
+ * When we run softirqs from irq_exit() and thus on the hardirq stack we need
+ * to keep the lockdep irq context tracking as tight as possible in order to
+ * not miss-qualify lock contexts and miss possible deadlocks.
+ */
+
+static inline bool lockdep_softirq_start(void)
+{
+	bool in_hardirq = false;
+
+	if (trace_hardirq_context(current)) {
+		in_hardirq = true;
+		trace_hardirq_exit();
+	}
+
+	lockdep_softirq_enter();
+
+	return in_hardirq;
+}
+
+static inline void lockdep_softirq_end(bool in_hardirq)
+{
+	lockdep_softirq_exit();
+
+	if (in_hardirq)
+		trace_hardirq_enter();
+}
+#else
+static inline bool lockdep_softirq_start(void) { return false; }
+static inline void lockdep_softirq_end(bool in_hardirq) { }
+#endif
+
 asmlinkage void __do_softirq(void)
 {
-	struct softirq_action *h;
-	__u32 pending;
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
-	int cpu;
 	unsigned long old_flags = current->flags;
 	int max_restart = MAX_SOFTIRQ_RESTART;
+	struct softirq_action *h;
+	bool in_hardirq;
+	__u32 pending;
+	int cpu;
 
 	/*
 	 * Mask out PF_MEMALLOC s current task context is borrowed for the
@@ -231,7 +265,7 @@ asmlinkage void __do_softirq(void)
 	account_irq_enter_time(current);
 
 	__local_bh_disable(_RET_IP_, SOFTIRQ_OFFSET);
-	lockdep_softirq_enter();
+	in_hardirq = lockdep_softirq_start();
 
 	cpu = smp_processor_id();
 restart:
@@ -278,16 +312,13 @@ asmlinkage void __do_softirq(void)
 		wakeup_softirqd();
 	}
 
-	lockdep_softirq_exit();
-
+	lockdep_softirq_end(in_hardirq);
 	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	tsk_restore_flags(current, old_flags, PF_MEMALLOC);
 }
 
-
-
 asmlinkage void do_softirq(void)
 {
 	__u32 pending;
@@ -375,13 +406,13 @@ void irq_exit(void)
 #endif
 
 	account_irq_exit_time(current);
-	trace_hardirq_exit();
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();
 
 	tick_irq_exit();
 	rcu_irq_exit();
+	trace_hardirq_exit(); /* must be last! */
 }
 
 /*

tools/lib/lockdep/Makefile

+# liblockdep version
+LL_VERSION = 0
+LL_PATCHLEVEL = 0
+LL_EXTRAVERSION = 1
+
+# file format version
+FILE_VERSION = 1
+
+MAKEFLAGS += --no-print-directory
+
+
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+
+INSTALL = install
+
+# Use DESTDIR for installing into a different root directory.
+# This is useful for building a package. The program will be
+# installed in this directory as if it was the root directory.
+# Then the build tool can move it later.
+DESTDIR ?=
+DESTDIR_SQ = '$(subst ','\'',$(DESTDIR))'
+
+prefix ?= /usr/local
+libdir_relative = lib
+libdir = $(prefix)/$(libdir_relative)
+bindir_relative = bin
+bindir = $(prefix)/$(bindir_relative)
+
+export DESTDIR DESTDIR_SQ INSTALL
+
+# copy a bit from Linux kbuild
+
+ifeq ("$(origin V)", "command line")
+  VERBOSE = $(V)
+endif
+ifndef VERBOSE
+  VERBOSE = 0
+endif
+
+ifeq ("$(origin O)", "command line")
+  BUILD_OUTPUT := $(O)
+endif
+
+ifeq ($(BUILD_SRC),)
+ifneq ($(BUILD_OUTPUT),)
+
+define build_output
+	$(if $(VERBOSE:1=),@)$(MAKE) -C $(BUILD_OUTPUT)	\
+	BUILD_SRC=$(CURDIR) -f $(CURDIR)/Makefile $1
+endef
+
+saved-output := $(BUILD_OUTPUT)
+BUILD_OUTPUT := $(shell cd $(BUILD_OUTPUT) && /bin/pwd)
+$(if $(BUILD_OUTPUT),, \
+     $(error output directory "$(saved-output)" does not exist))
+
+all: sub-make
+
+gui: force
+	$(call build_output, all_cmd)
+
+$(filter-out gui,$(MAKECMDGOALS)): sub-make
+
+sub-make: force
+	$(call build_output, $(MAKECMDGOALS))
+
+
+# Leave processing to above invocation of make
+skip-makefile := 1
+
+endif # BUILD_OUTPUT
+endif # BUILD_SRC
+
+# We process the rest of the Makefile if this is the final invocation of make
+ifeq ($(skip-makefile),)
+
+srctree		:= $(if $(BUILD_SRC),$(BUILD_SRC),$(CURDIR))
+objtree		:= $(CURDIR)
+src		:= $(srctree)
+obj		:= $(objtree)
+
+export prefix libdir bindir src obj
+
+# Shell quotes
+libdir_SQ = $(subst ','\'',$(libdir))
+bindir_SQ = $(subst ','\'',$(bindir))
+
+LIB_FILE = liblockdep.a liblockdep.so
+BIN_FILE = lockdep
+
+CONFIG_INCLUDES =
+CONFIG_LIBS	=
+CONFIG_FLAGS	=
+
+OBJ		= $@
+N		=
+
+export Q VERBOSE
+
+LIBLOCKDEP_VERSION = $(LL_VERSION).$(LL_PATCHLEVEL).$(LL_EXTRAVERSION)
+
+INCLUDES = -I. -I/usr/local/include -I./uinclude $(CONFIG_INCLUDES)
+
+# Set compile option CFLAGS if not set elsewhere
+CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g
+
+override CFLAGS += $(CONFIG_FLAGS) $(INCLUDES) $(PLUGIN_DIR_SQ)
+
+ifeq ($(VERBOSE),1)
+  Q =
+  print_compile =
+  print_app_build =
+  print_fpic_compile =
+  print_shared_lib_compile =
+  print_install =
+else
+  Q = @
+  print_compile =		echo '  CC                 '$(OBJ);
+  print_app_build =		echo '  BUILD              '$(OBJ);
+  print_fpic_compile =		echo '  CC FPIC            '$(OBJ);
+  print_shared_lib_compile =	echo '  BUILD SHARED LIB   '$(OBJ);
+  print_static_lib_build =	echo '  BUILD STATIC LIB   '$(OBJ);
+  print_install =		echo '  INSTALL     '$1'	to	$(DESTDIR_SQ)$2';
+endif
+
+do_fpic_compile =					\
+	($(print_fpic_compile)				\
+	$(CC) -c $(CFLAGS) $(EXT) -fPIC $< -o $@)
+
+do_app_build =						\
+	($(print_app_build)				\
+	$(CC) $^ -rdynamic -o $@ $(CONFIG_LIBS) $(LIBS))
+
+do_compile_shared_library =			\
+	($(print_shared_lib_compile)		\
+	$(CC) --shared $^ -o $@ -lpthread -ldl)
+
+do_build_static_lib =				\
+	($(print_static_lib_build)		\
+	$(RM) $@;  $(AR) rcs $@ $^)
+
+
+define do_compile
+	$(print_compile)						\
+	$(CC) -c $(CFLAGS) $(EXT) $< -o $(obj)/$@;
+endef
+
+$(obj)/%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+%.o: $(src)/%.c
+	$(Q)$(call do_compile)
+
+PEVENT_LIB_OBJS = common.o lockdep.o preload.o rbtree.o
+
+ALL_OBJS = $(PEVENT_LIB_OBJS)
+
+CMD_TARGETS = $(LIB_FILE)
+
+TARGETS = $(CMD_TARGETS)
+
+
+all: all_cmd
+
+all_cmd: $(CMD_TARGETS)
+
+liblockdep.so: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_compile_shared_library)
+
+liblockdep.a: $(PEVENT_LIB_OBJS)
+	$(Q)$(do_build_static_lib)
+
+$(PEVENT_LIB_OBJS): %.o: $(src)/%.c
+	$(Q)$(do_fpic_compile)
+
+## make deps
+
+all_objs := $(sort $(ALL_OBJS))
+all_deps := $(all_objs:%.o=.%.d)
+
+# let .d file also depends on the source and header files
+define check_deps
+		@set -e; $(RM) $@; \
+		$(CC) -MM $(CFLAGS) $< > $@.$$$$; \
+		sed 's,\($*\)\.o[ :]*,\1.o $@ : ,g' < $@.$$$$ > $@; \
+		$(RM) $@.$$$$
+endef
+
+$(all_deps): .%.d: $(src)/%.c
+	$(Q)$(call check_deps)
+
+$(all_objs) : %.o : .%.d
+
+dep_includes := $(wildcard $(all_deps))
+
+ifneq ($(dep_includes),)
+ include $(dep_includes)
+endif
+
+### Detect environment changes
+TRACK_CFLAGS = $(subst ','\'',$(CFLAGS)):$(ARCH):$(CROSS_COMPILE)
+
+tags:	force
+	$(RM) tags
+	find . -name '*.[ch]' | xargs ctags --extra=+f --c-kinds=+px \
+	--regex-c++='/_PE\(([^,)]*).*/PEVENT_ERRNO__\1/'
+
+TAGS:	force
+	$(RM) TAGS
+	find . -name '*.[ch]' | xargs etags \
+	--regex='/_PE(\([^,)]*\).*/PEVENT_ERRNO__\1/'
+
+define do_install
+	$(print_install)				\
+	if [ ! -d '$(DESTDIR_SQ)$2' ]; then		\
+		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$2';	\
+	fi;						\
+	$(INSTALL) $1 '$(DESTDIR_SQ)$2'
+endef
+
+install_lib: all_cmd
+	$(Q)$(call do_install,$(LIB_FILE),$(libdir_SQ))
+	$(Q)$(call do_install,$(BIN_FILE),$(bindir_SQ))
+
+install: install_lib
+
+clean:
+	$(RM) *.o *~ $(TARGETS) *.a *.so $(VERSION_FILES) .*.d
+	$(RM) tags TAGS
+
+endif # skip-makefile
+
+PHONY += force
+force:
+
+# Declare the contents of the .PHONY variable as phony.  We keep that
+# information in a variable so we can use it in if_changed and friends.
+.PHONY: $(PHONY)

tools/lib/lockdep/common.c

+#include <stddef.h>
+#include <stdbool.h>
+#include <linux/compiler.h>
+#include <linux/lockdep.h>
+#include <unistd.h>
+#include <sys/syscall.h>
+
+static __thread struct task_struct current_obj;
+
+/* lockdep wants these */
+bool debug_locks = true;
+bool debug_locks_silent;
+
+__attribute__((constructor)) static void liblockdep_init(void)
+{
+	lockdep_init();
+}
+
+__attribute__((destructor)) static void liblockdep_exit(void)
+{
+	debug_check_no_locks_held(&current_obj);
+}
+
+struct task_struct *__curr(void)
+{
+	if (current_obj.pid == 0) {
+		/* Makes lockdep output pretty */
+		prctl(PR_GET_NAME, current_obj.comm);
+		current_obj.pid = syscall(__NR_gettid);
+	}
+
+	return &current_obj;
+}

tools/lib/lockdep/include/liblockdep/common.h

+#ifndef _LIBLOCKDEP_COMMON_H
+#define _LIBLOCKDEP_COMMON_H
+
+#include <pthread.h>
+
+#define NR_LOCKDEP_CACHING_CLASSES 2
+#define MAX_LOCKDEP_SUBCLASSES 8UL
+
+#ifndef CALLER_ADDR0
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#endif
+
+#ifndef _RET_IP_
+#define _RET_IP_ CALLER_ADDR0
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
+
+struct lockdep_subclass_key {
+	char __one_byte;
+};
+
+struct lock_class_key {
+	struct lockdep_subclass_key subkeys[MAX_LOCKDEP_SUBCLASSES];
+};
+
+struct lockdep_map {
+	struct lock_class_key	*key;
+	struct lock_class	*class_cache[NR_LOCKDEP_CACHING_CLASSES];
+	const char		*name;
+#ifdef CONFIG_LOCK_STAT
+	int			cpu;
+	unsigned long		ip;
+#endif
+};
+
+void lockdep_init_map(struct lockdep_map *lock, const char *name,
+			struct lock_class_key *key, int subclass);
+void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
+			int trylock, int read, int check,
+			struct lockdep_map *nest_lock, unsigned long ip);
+void lock_release(struct lockdep_map *lock, int nested,
+			unsigned long ip);
+
+#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .name = (_name), .key = (void *)(_key), }
+
+#endif

tools/lib/lockdep/include/liblockdep/mutex.h

+#ifndef _LIBLOCKDEP_MUTEX_H
+#define _LIBLOCKDEP_MUTEX_H
+
+#include <pthread.h>
+#include "common.h"
+
+struct liblockdep_pthread_mutex {
+	pthread_mutex_t mutex;
+	struct lockdep_map dep_map;
+};
+
+typedef struct liblockdep_pthread_mutex liblockdep_pthread_mutex_t;
+
+#define LIBLOCKDEP_PTHREAD_MUTEX_INITIALIZER(mtx)			\
+		(const struct liblockdep_pthread_mutex) {		\
+	.mutex = PTHREAD_MUTEX_INITIALIZER,				\
+	.dep_map = STATIC_LOCKDEP_MAP_INIT(#mtx, &((&(mtx))->dep_map)),	\
+}
+
+static inline int __mutex_init(liblockdep_pthread_mutex_t *lock,
+				const char *name,
+				struct lock_class_key *key,
+				const pthread_mutexattr_t *__mutexattr)
+{
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+	return pthread_mutex_init(&lock->mutex, __mutexattr);
+}
+
+#define liblockdep_pthread_mutex_init(mutex, mutexattr)		\
+({								\
+	static struct lock_class_key __key;			\
+								\
+	__mutex_init((mutex), #mutex, &__key, (mutexattr));	\
+})
+
+static inline int liblockdep_pthread_mutex_lock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_mutex_lock(&lock->mutex);
+}
+
+static inline int liblockdep_pthread_mutex_unlock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	return pthread_mutex_unlock(&lock->mutex);
+}
+
+static inline int liblockdep_pthread_mutex_trylock(liblockdep_pthread_mutex_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_mutex_trylock(&lock->mutex) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_pthread_mutex_destroy(liblockdep_pthread_mutex_t *lock)
+{
+	return pthread_mutex_destroy(&lock->mutex);
+}
+
+#ifdef __USE_LIBLOCKDEP
+
+#define pthread_mutex_t         liblockdep_pthread_mutex_t
+#define pthread_mutex_init      liblockdep_pthread_mutex_init
+#define pthread_mutex_lock      liblockdep_pthread_mutex_lock
+#define pthread_mutex_unlock    liblockdep_pthread_mutex_unlock
+#define pthread_mutex_trylock   liblockdep_pthread_mutex_trylock
+#define pthread_mutex_destroy   liblockdep_pthread_mutex_destroy
+
+#endif
+
+#endif

tools/lib/lockdep/include/liblockdep/rwlock.h

+#ifndef _LIBLOCKDEP_RWLOCK_H
+#define _LIBLOCKDEP_RWLOCK_H
+
+#include <pthread.h>
+#include "common.h"
+
+struct liblockdep_pthread_rwlock {
+	pthread_rwlock_t rwlock;
+	struct lockdep_map dep_map;
+};
+
+typedef struct liblockdep_pthread_rwlock liblockdep_pthread_rwlock_t;
+
+#define LIBLOCKDEP_PTHREAD_RWLOCK_INITIALIZER(rwl)			\
+		(struct liblockdep_pthread_rwlock) {			\
+	.rwlock = PTHREAD_RWLOCK_INITIALIZER,				\
+	.dep_map = STATIC_LOCKDEP_MAP_INIT(#rwl, &((&(rwl))->dep_map)),	\
+}
+
+static inline int __rwlock_init(liblockdep_pthread_rwlock_t *lock,
+				const char *name,
+				struct lock_class_key *key,
+				const pthread_rwlockattr_t *attr)
+{
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+
+	return pthread_rwlock_init(&lock->rwlock, attr);
+}
+
+#define liblockdep_pthread_rwlock_init(lock, attr)		\
+({							\
+	static struct lock_class_key __key;		\
+							\
+	__rwlock_init((lock), #lock, &__key, (attr));	\
+})
+
+static inline int liblockdep_pthread_rwlock_rdlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 2, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_rdlock(&lock->rwlock);
+
+}
+
+static inline int liblockdep_pthread_rwlock_unlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_release(&lock->dep_map, 0, (unsigned long)_RET_IP_);
+	return pthread_rwlock_unlock(&lock->rwlock);
+}
+
+static inline int liblockdep_pthread_rwlock_wrlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 0, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_wrlock(&lock->rwlock);
+}
+
+static inline int liblockdep_pthread_rwlock_tryrdlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 2, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_tryrdlock(&lock->rwlock) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_pthread_rwlock_trywlock(liblockdep_pthread_rwlock_t *lock)
+{
+	lock_acquire(&lock->dep_map, 0, 1, 0, 2, NULL, (unsigned long)_RET_IP_);
+	return pthread_rwlock_trywlock(&lock->rwlock) == 0 ? 1 : 0;
+}
+
+static inline int liblockdep_rwlock_destroy(liblockdep_pthread_rwlock_t *lock)
+{
+	return pthread_rwlock_destroy(&lock->rwlock);
+}
+
+#ifdef __USE_LIBLOCKDEP
+
+#define pthread_rwlock_t		liblockdep_pthread_rwlock_t
+#define pthread_rwlock_init		liblockdep_pthread_rwlock_init
+#define pthread_rwlock_rdlock		liblockdep_pthread_rwlock_rdlock
+#define pthread_rwlock_unlock		liblockdep_pthread_rwlock_unlock
+#define pthread_rwlock_wrlock		liblockdep_pthread_rwlock_wrlock
+#define pthread_rwlock_tryrdlock	liblockdep_pthread_rwlock_tryrdlock
+#define pthread_rwlock_trywlock		liblockdep_pthread_rwlock_trywlock
+#define pthread_rwlock_destroy		liblockdep_rwlock_destroy
+
+#endif
+
+#endif

tools/lib/lockdep/lockdep

+#!/bin/bash
+
+LD_PRELOAD="./liblockdep.so $LD_PRELOAD" "$@"

tools/lib/lockdep/lockdep.c

+#include <linux/lockdep.h>
+#include "../../../kernel/locking/lockdep.c"

tools/lib/lockdep/lockdep_internals.h

+#include "../../../kernel/locking/lockdep_internals.h"

tools/lib/lockdep/lockdep_states.h

+#include "../../../kernel/locking/lockdep_states.h"

tools/lib/lockdep/rbtree.c

+#include "../../../lib/rbtree.c"

tools/lib/lockdep/run_tests.sh

+#! /bin/bash
+
+make &> /dev/null
+
+for i in `ls tests/*.c`; do
+	testname=$(basename -s .c "$i")
+	gcc -o tests/$testname -pthread -lpthread $i liblockdep.a -Iinclude -D__USE_LIBLOCKDEP &> /dev/null
+	echo -ne "$testname... "
+	if [ $(timeout 1 ./tests/$testname | wc -l) -gt 0 ]; then
+		echo "PASSED!"
+	else
+		echo "FAILED!"
+	fi
+	rm tests/$testname
+done
+
+for i in `ls tests/*.c`; do
+	testname=$(basename -s .c "$i")
+	gcc -o tests/$testname -pthread -lpthread -Iinclude $i &> /dev/null
+	echo -ne "(PRELOAD) $testname... "
+	if [ $(timeout 1 ./lockdep ./tests/$testname | wc -l) -gt 0 ]; then
+		echo "PASSED!"
+	else
+		echo "FAILED!"
+	fi
+	rm tests/$testname
+done

tools/lib/lockdep/tests/AA.c

+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_lock(&b);
+	pthread_mutex_lock(&a);
+}

tools/lib/lockdep/tests/ABBA.c

+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, a);
+}

tools/lib/lockdep/tests/ABBCCA.c

+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(c, a);
+}

tools/lib/lockdep/tests/ABBCCDDA.c

+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(d, a);
+}

tools/lib/lockdep/tests/ABCABC.c

+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, a);
+	LOCK_UNLOCK_2(b, c);
+}

tools/lib/lockdep/tests/ABCDBCDA.c

+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(b, c);
+	LOCK_UNLOCK_2(d, a);
+}

tools/lib/lockdep/tests/ABCDBDDA.c

+#include <liblockdep/mutex.h>
+#include "common.h"
+
+void main(void)
+{
+	pthread_mutex_t a, b, c, d;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+	pthread_mutex_init(&c, NULL);
+	pthread_mutex_init(&d, NULL);
+
+	LOCK_UNLOCK_2(a, b);
+	LOCK_UNLOCK_2(c, d);
+	LOCK_UNLOCK_2(b, d);
+	LOCK_UNLOCK_2(d, a);
+}

tools/lib/lockdep/tests/WW.c

+#include <liblockdep/rwlock.h>
+
+void main(void)
+{
+	pthread_rwlock_t a, b;
+
+	pthread_rwlock_init(&a, NULL);
+	pthread_rwlock_init(&b, NULL);
+
+	pthread_rwlock_wrlock(&a);
+	pthread_rwlock_rdlock(&b);
+	pthread_rwlock_wrlock(&a);
+}

tools/lib/lockdep/tests/common.h

+#ifndef _LIBLOCKDEP_TEST_COMMON_H
+#define _LIBLOCKDEP_TEST_COMMON_H
+
+#define LOCK_UNLOCK_2(a, b)			\
+	do {					\
+		pthread_mutex_lock(&(a));	\
+		pthread_mutex_lock(&(b));	\
+		pthread_mutex_unlock(&(b));	\
+		pthread_mutex_unlock(&(a));	\
+	} while(0)
+
+#endif

tools/lib/lockdep/tests/unlock_balance.c

+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a;
+
+	pthread_mutex_init(&a, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_unlock(&a);
+	pthread_mutex_unlock(&a);
+}

tools/lib/lockdep/uinclude/asm/hweight.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/asm/sections.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/bitops.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/compiler.h

+#ifndef _LIBLOCKDEP_LINUX_COMPILER_H_
+#define _LIBLOCKDEP_LINUX_COMPILER_H_
+
+#define __used		__attribute__((__unused__))
+#define unlikely
+
+#endif

tools/lib/lockdep/uinclude/linux/debug_locks.h

+#ifndef _LIBLOCKDEP_DEBUG_LOCKS_H_
+#define _LIBLOCKDEP_DEBUG_LOCKS_H_
+
+#include <stddef.h>
+#include <linux/compiler.h>
+
+#define DEBUG_LOCKS_WARN_ON(x) (x)
+
+extern bool debug_locks;
+extern bool debug_locks_silent;
+
+#endif

tools/lib/lockdep/uinclude/linux/delay.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/export.h

+#ifndef _LIBLOCKDEP_LINUX_EXPORT_H_
+#define _LIBLOCKDEP_LINUX_EXPORT_H_
+
+#define EXPORT_SYMBOL(sym)
+#define EXPORT_SYMBOL_GPL(sym)
+
+#endif

tools/lib/lockdep/uinclude/linux/ftrace.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/gfp.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/hardirq.h

+#ifndef _LIBLOCKDEP_LINUX_HARDIRQ_H_
+#define _LIBLOCKDEP_LINUX_HARDIRQ_H_
+
+#define SOFTIRQ_BITS	0UL
+#define HARDIRQ_BITS	0UL
+#define SOFTIRQ_SHIFT	0UL
+#define HARDIRQ_SHIFT	0UL
+#define hardirq_count()	0UL
+#define softirq_count()	0UL
+
+#endif

tools/lib/lockdep/uinclude/linux/hash.h

+#include "../../../include/linux/hash.h"

tools/lib/lockdep/uinclude/linux/interrupt.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/irqflags.h

+#ifndef _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
+#define _LIBLOCKDEP_LINUX_TRACE_IRQFLAGS_H_
+
+# define trace_hardirq_context(p)	0
+# define trace_softirq_context(p)	0
+# define trace_hardirqs_enabled(p)	0
+# define trace_softirqs_enabled(p)	0
+# define trace_hardirq_enter()		do { } while (0)
+# define trace_hardirq_exit()		do { } while (0)
+# define lockdep_softirq_enter()	do { } while (0)
+# define lockdep_softirq_exit()		do { } while (0)
+# define INIT_TRACE_IRQFLAGS
+
+# define stop_critical_timings() do { } while (0)
+# define start_critical_timings() do { } while (0)
+
+#define raw_local_irq_disable() do { } while (0)
+#define raw_local_irq_enable() do { } while (0)
+#define raw_local_irq_save(flags) ((flags) = 0)
+#define raw_local_irq_restore(flags) do { } while (0)
+#define raw_local_save_flags(flags) ((flags) = 0)
+#define raw_irqs_disabled_flags(flags) do { } while (0)
+#define raw_irqs_disabled() 0
+#define raw_safe_halt()
+
+#define local_irq_enable() do { } while (0)
+#define local_irq_disable() do { } while (0)
+#define local_irq_save(flags) ((flags) = 0)
+#define local_irq_restore(flags) do { } while (0)
+#define local_save_flags(flags)	((flags) = 0)
+#define irqs_disabled() (1)
+#define irqs_disabled_flags(flags) (0)
+#define safe_halt() do { } while (0)
+
+#define trace_lock_release(x, y)
+#define trace_lock_acquire(a, b, c, d, e, f, g)
+
+#endif

tools/lib/lockdep/uinclude/linux/kallsyms.h

+#ifndef _LIBLOCKDEP_LINUX_KALLSYMS_H_
+#define _LIBLOCKDEP_LINUX_KALLSYMS_H_
+
+#include <linux/kernel.h>
+#include <stdio.h>
+
+#define KSYM_NAME_LEN 128
+
+struct module;
+
+static inline const char *kallsyms_lookup(unsigned long addr,
+					  unsigned long *symbolsize,
+					  unsigned long *offset,
+					  char **modname, char *namebuf)
+{
+	return NULL;
+}
+
+#include <execinfo.h>
+#include <stdlib.h>
+static inline void print_ip_sym(unsigned long ip)
+{
+	char **name;
+
+	name = backtrace_symbols((void **)&ip, 1);
+
+	printf("%s\n", *name);
+
+	free(name);
+}
+
+#endif

tools/lib/lockdep/uinclude/linux/kern_levels.h

+#ifndef __KERN_LEVELS_H__
+#define __KERN_LEVELS_H__
+
+#define KERN_SOH	""		/* ASCII Start Of Header */
+#define KERN_SOH_ASCII	''
+
+#define KERN_EMERG	KERN_SOH ""	/* system is unusable */
+#define KERN_ALERT	KERN_SOH ""	/* action must be taken immediately */
+#define KERN_CRIT	KERN_SOH ""	/* critical conditions */
+#define KERN_ERR	KERN_SOH ""	/* error conditions */
+#define KERN_WARNING	KERN_SOH ""	/* warning conditions */
+#define KERN_NOTICE	KERN_SOH ""	/* normal but significant condition */
+#define KERN_INFO	KERN_SOH ""	/* informational */
+#define KERN_DEBUG	KERN_SOH ""	/* debug-level messages */
+
+#define KERN_DEFAULT	KERN_SOH ""	/* the default kernel loglevel */
+
+/*
+ * Annotation for a "continued" line of log printout (only done after a
+ * line that had no enclosing \n). Only to be used by core/arch code
+ * during early bootup (a continued line is not SMP-safe otherwise).
+ */
+#define KERN_CONT	""
+
+#endif

tools/lib/lockdep/uinclude/linux/kernel.h

+#ifndef _LIBLOCKDEP_LINUX_KERNEL_H_
+#define _LIBLOCKDEP_LINUX_KERNEL_H_
+
+#include <linux/export.h>
+#include <linux/types.h>
+#include <linux/rcu.h>
+#include <linux/hardirq.h>
+#include <linux/kern_levels.h>
+
+#ifndef container_of
+#define container_of(ptr, type, member) ({			\
+	const typeof(((type *)0)->member) * __mptr = (ptr);	\
+	(type *)((char *)__mptr - offsetof(type, member)); })
+#endif
+
+#define max(x, y) ({				\
+	typeof(x) _max1 = (x);			\
+	typeof(y) _max2 = (y);			\
+	(void) (&_max1 == &_max2);		\
+	_max1 > _max2 ? _max1 : _max2; })
+
+#define BUILD_BUG_ON(condition) ((void)sizeof(char[1 - 2*!!(condition)]))
+#define WARN_ON(x) (x)
+#define WARN_ON_ONCE(x) (x)
+#define likely(x) (x)
+#define WARN(x, y, z) (x)
+#define uninitialized_var(x) x
+#define __init
+#define noinline
+#define list_add_tail_rcu list_add_tail
+
+#ifndef CALLER_ADDR0
+#define CALLER_ADDR0 ((unsigned long)__builtin_return_address(0))
+#endif
+
+#ifndef _RET_IP_
+#define _RET_IP_ CALLER_ADDR0
+#endif
+
+#ifndef _THIS_IP_
+#define _THIS_IP_ ({ __label__ __here; __here: (unsigned long)&&__here; })
+#endif
+
+#endif

tools/lib/lockdep/uinclude/linux/kmemcheck.h

+#ifndef _LIBLOCKDEP_LINUX_KMEMCHECK_H_
+#define _LIBLOCKDEP_LINUX_KMEMCHECK_H_
+
+static inline void kmemcheck_mark_initialized(void *address, unsigned int n)
+{
+}
+
+#endif

tools/lib/lockdep/uinclude/linux/linkage.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/list.h

+#include "../../../include/linux/list.h"

tools/lib/lockdep/uinclude/linux/lockdep.h

+#ifndef _LIBLOCKDEP_LOCKDEP_H_
+#define _LIBLOCKDEP_LOCKDEP_H_
+
+#include <sys/prctl.h>
+#include <sys/syscall.h>
+#include <string.h>
+#include <limits.h>
+#include <linux/utsname.h>
+
+
+#define MAX_LOCK_DEPTH 2000UL
+
+#include "../../../include/linux/lockdep.h"
+
+struct task_struct {
+	u64 curr_chain_key;
+	int lockdep_depth;
+	unsigned int lockdep_recursion;
+	struct held_lock held_locks[MAX_LOCK_DEPTH];
+	gfp_t lockdep_reclaim_gfp;
+	int pid;
+	char comm[17];
+};
+
+extern struct task_struct *__curr(void);
+
+#define current (__curr())
+
+#define debug_locks_off() 1
+#define task_pid_nr(tsk) ((tsk)->pid)
+
+#define KSYM_NAME_LEN 128
+#define printk printf
+
+#define list_del_rcu list_del
+
+#define atomic_t unsigned long
+#define atomic_inc(x) ((*(x))++)
+
+static struct new_utsname *init_utsname(void)
+{
+	static struct new_utsname n = (struct new_utsname) {
+		.release = "liblockdep",
+		.version = LIBLOCKDEP_VERSION,
+	};
+
+	return &n;
+}
+
+#define print_tainted() ""
+#define static_obj(x) 1
+
+#define debug_show_all_locks()
+
+#endif

tools/lib/lockdep/uinclude/linux/module.h

+#ifndef _LIBLOCKDEP_LINUX_MODULE_H_
+#define _LIBLOCKDEP_LINUX_MODULE_H_
+
+#define module_param(name, type, perm)
+
+#endif

tools/lib/lockdep/uinclude/linux/mutex.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/poison.h

+#include "../../../include/linux/poison.h"

tools/lib/lockdep/uinclude/linux/prefetch.h

+#ifndef _LIBLOCKDEP_LINUX_PREFETCH_H_
+#define _LIBLOCKDEP_LINUX_PREFETCH_H
+
+static inline void prefetch(void *a __attribute__((unused))) { }
+
+#endif

tools/lib/lockdep/uinclude/linux/proc_fs.h

+
+/* empty file */
+

tools/lib/lockdep/uinclude/linux/rbtree.h

+#include "../../../include/linux/rbtree.h"

tools/lib/lockdep/uinclude/linux/rbtree_augmented.h

+#define __always_inline
+#include "../../../include/linux/rbtree_augmented.h"

tools/lib/lockdep/uinclude/linux/rcu.h

+#ifndef _LIBLOCKDEP_RCU_H_
+#define _LIBLOCKDEP_RCU_H_
+
+int rcu_scheduler_active;
+
+static inline int rcu_lockdep_current_cpu_online(void)
+{
+	return 1;
+}
+
+static inline int rcu_is_cpu_idle(void)
+{
+	return 1;
+}
+
+#endif

tools/lib/lockdep/uinclude/linux/seq_file.h

+
+/* empty file */
+