diff --git a/Documentation/atomic_t.txt b/Documentation/atomic_t.txt
index b3afe69d03a1..0ab747e0d5ac 100644
--- a/Documentation/atomic_t.txt
+++ b/Documentation/atomic_t.txt
@@ -81,9 +81,11 @@ Non-RMW ops:
 
 The non-RMW ops are (typically) regular LOADs and STOREs and are canonically
 implemented using READ_ONCE(), WRITE_ONCE(), smp_load_acquire() and
-smp_store_release() respectively.
+smp_store_release() respectively. Therefore, if you find yourself only using
+the Non-RMW operations of atomic_t, you do not in fact need atomic_t at all
+and are doing it wrong.
 
-The one detail to this is that atomic_set{}() should be observable to the RMW
+A subtle detail of atomic_set{}() is that it should be observable to the RMW
 ops. That is:
 
   C atomic-set
@@ -200,6 +202,9 @@ These helper barriers exist because architectures have varying implicit
 ordering on their SMP atomic primitives. For example our TSO architectures
 provide full ordered atomics and these barriers are no-ops.
 
+NOTE: when the atomic RmW ops are fully ordered, they should also imply a
+compiler barrier.
+
 Thus:
 
   atomic_fetch_add();
diff --git a/Documentation/locking/lockdep-design.txt b/Documentation/locking/lockdep-design.txt
index 39fae143c9cb..f189d130e543 100644
--- a/Documentation/locking/lockdep-design.txt
+++ b/Documentation/locking/lockdep-design.txt
@@ -15,34 +15,48 @@ tens of thousands of) instantiations. For example a lock in the inode
 struct is one class, while each inode has its own instantiation of that
 lock class.
 
-The validator tracks the 'state' of lock-classes, and it tracks
-dependencies between different lock-classes. The validator maintains a
-rolling proof that the state and the dependencies are correct.
+The validator tracks the 'usage state' of lock-classes, and it tracks
+the dependencies between different lock-classes. Lock usage indicates
+how a lock is used with regard to its IRQ contexts, while lock
+dependency can be understood as lock order, where L1 -> L2 suggests that
+a task is attempting to acquire L2 while holding L1. From lockdep's
+perspective, the two locks (L1 and L2) are not necessarily related; that
+dependency just means the order ever happened. The validator maintains a
+continuing effort to prove lock usages and dependencies are correct or
+the validator will shoot a splat if incorrect.
 
-Unlike an lock instantiation, the lock-class itself never goes away: when
-a lock-class is used for the first time after bootup it gets registered,
-and all subsequent uses of that lock-class will be attached to this
-lock-class.
+A lock-class's behavior is constructed by its instances collectively:
+when the first instance of a lock-class is used after bootup the class
+gets registered, then all (subsequent) instances will be mapped to the
+class and hence their usages and dependecies will contribute to those of
+the class. A lock-class does not go away when a lock instance does, but
+it can be removed if the memory space of the lock class (static or
+dynamic) is reclaimed, this happens for example when a module is
+unloaded or a workqueue is destroyed.
 
 State
 -----
 
-The validator tracks lock-class usage history into 4 * nSTATEs + 1 separate
-state bits:
+The validator tracks lock-class usage history and divides the usage into
+(4 usages * n STATEs + 1) categories:
 
+where the 4 usages can be:
 - 'ever held in STATE context'
 - 'ever held as readlock in STATE context'
 - 'ever held with STATE enabled'
 - 'ever held as readlock with STATE enabled'
 
-Where STATE can be either one of (kernel/locking/lockdep_states.h)
- - hardirq
- - softirq
+where the n STATEs are coded in kernel/locking/lockdep_states.h and as of
+now they include:
+- hardirq
+- softirq
 
+where the last 1 category is:
 - 'ever used'                                       [ == !unused        ]
 
-When locking rules are violated, these state bits are presented in the
-locking error messages, inside curlies. A contrived example:
+When locking rules are violated, these usage bits are presented in the
+locking error messages, inside curlies, with a total of 2 * n STATEs bits.
+A contrived example:
 
    modprobe/2287 is trying to acquire lock:
     (&sio_locks[i].lock){-.-.}, at: [<c02867fd>] mutex_lock+0x21/0x24
@@ -51,28 +65,67 @@ locking error messages, inside curlies. A contrived example:
     (&sio_locks[i].lock){-.-.}, at: [<c02867fd>] mutex_lock+0x21/0x24
 
 
-The bit position indicates STATE, STATE-read, for each of the states listed
-above, and the character displayed in each indicates:
+For a given lock, the bit positions from left to right indicate the usage
+of the lock and readlock (if exists), for each of the n STATEs listed
+above respectively, and the character displayed at each bit position
+indicates:
 
    '.'  acquired while irqs disabled and not in irq context
    '-'  acquired in irq context
    '+'  acquired with irqs enabled
    '?'  acquired in irq context with irqs enabled.
 
-Unused mutexes cannot be part of the cause of an error.
+The bits are illustrated with an example:
+
+    (&sio_locks[i].lock){-.-.}, at: [<c02867fd>] mutex_lock+0x21/0x24
+                         ||||
+                         ||| \-> softirq disabled and not in softirq context
+                         || \--> acquired in softirq context
+                         | \---> hardirq disabled and not in hardirq context
+                          \----> acquired in hardirq context
+
+
+For a given STATE, whether the lock is ever acquired in that STATE
+context and whether that STATE is enabled yields four possible cases as
+shown in the table below. The bit character is able to indicate which
+exact case is for the lock as of the reporting time.
+
+   -------------------------------------------
+  |              | irq enabled | irq disabled |
+  |-------------------------------------------|
+  | ever in irq  |      ?      |       -      |
+  |-------------------------------------------|
+  | never in irq |      +      |       .      |
+   -------------------------------------------
+
+The character '-' suggests irq is disabled because if otherwise the
+charactor '?' would have been shown instead. Similar deduction can be
+applied for '+' too.
+
+Unused locks (e.g., mutexes) cannot be part of the cause of an error.
 
 
 Single-lock state rules:
 ------------------------
 
+A lock is irq-safe means it was ever used in an irq context, while a lock
+is irq-unsafe means it was ever acquired with irq enabled.
+
 A softirq-unsafe lock-class is automatically hardirq-unsafe as well. The
-following states are exclusive, and only one of them is allowed to be
-set for any lock-class:
+following states must be exclusive: only one of them is allowed to be set
+for any lock-class based on its usage:
 
- <hardirq-safe> and <hardirq-unsafe>
- <softirq-safe> and <softirq-unsafe>
+ <hardirq-safe> or <hardirq-unsafe>
+ <softirq-safe> or <softirq-unsafe>
 
-The validator detects and reports lock usage that violate these
+This is because if a lock can be used in irq context (irq-safe) then it
+cannot be ever acquired with irq enabled (irq-unsafe). Otherwise, a
+deadlock may happen. For example, in the scenario that after this lock
+was acquired but before released, if the context is interrupted this
+lock will be attempted to acquire twice, which creates a deadlock,
+referred to as lock recursion deadlock.
+
+The validator detects and reports lock usage that violates these
 single-lock state rules.
 
 Multi-lock dependency rules:
@@ -81,15 +134,18 @@ Multi-lock dependency rules:
 The same lock-class must not be acquired twice, because this could lead
 to lock recursion deadlocks.
 
-Furthermore, two locks may not be taken in different order:
+Furthermore, two locks can not be taken in inverse order:
 
  <L1> -> <L2>
  <L2> -> <L1>
 
-because this could lead to lock inversion deadlocks. (The validator
-finds such dependencies in arbitrary complexity, i.e. there can be any
-other locking sequence between the acquire-lock operations, the
-validator will still track all dependencies between locks.)
+because this could lead to a deadlock - referred to as lock inversion
+deadlock - as attempts to acquire the two locks form a circle which
+could lead to the two contexts waiting for each other permanently. The
+validator will find such dependency circle in arbitrary complexity,
+i.e., there can be any other locking sequence between the acquire-lock
+operations; the validator will still find whether these locks can be
+acquired in a circular fashion.
 
 Furthermore, the following usage based lock dependencies are not allowed
 between any two lock-classes:
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h
index 150a1c5d6a2c..2144530d1428 100644
--- a/arch/alpha/include/asm/atomic.h
+++ b/arch/alpha/include/asm/atomic.h
@@ -93,9 +93,9 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v)	\
 }
 
 #define ATOMIC64_OP(op, asm_op)						\
-static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
+static __inline__ void atomic64_##op(s64 i, atomic64_t * v)		\
 {									\
-	unsigned long temp;						\
+	s64 temp;							\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
 	"	" #asm_op " %0,%2,%0\n"					\
@@ -109,9 +109,9 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, asm_op)					\
-static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v)	\
+static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)	\
 {									\
-	long temp, result;						\
+	s64 temp, result;						\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %0,%1\n"						\
 	"	" #asm_op " %0,%3,%2\n"					\
@@ -128,9 +128,9 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v)	\
 }
 
 #define ATOMIC64_FETCH_OP(op, asm_op)					\
-static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)	\
+static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)	\
 {									\
-	long temp, result;						\
+	s64 temp, result;						\
 	__asm__ __volatile__(						\
 	"1:	ldq_l %2,%1\n"						\
 	"	" #asm_op " %2,%3,%0\n"					\
@@ -246,9 +246,9 @@ static __inline__ int atomic_fetch_add_unless(atomic_t *v, int a, int u)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
+static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	long c, new, old;
+	s64 c, new, old;
 	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l	%[old],%[mem]\n"
@@ -276,9 +276,9 @@ static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
  * The function returns the old value of *v minus 1, even if
  * the atomic variable, v, was not decremented.
  */
-static inline long atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
-	long old, tmp;
+	s64 old, tmp;
 	smp_mb();
 	__asm__ __volatile__(
 	"1:	ldq_l	%[old],%[mem]\n"
diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 17cf1c657cb3..7298ce84762e 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -321,14 +321,14 @@ ATOMIC_OPS(xor, ^=, CTOP_INST_AXOR_DI_R2_R2_R3)
  */
 
 typedef struct {
-	aligned_u64 counter;
+	s64 __aligned(8) counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(a) { (a) }
 
-static inline long long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
 {
-	unsigned long long val;
+	s64 val;
 
 	__asm__ __volatile__(
 	"	ldd   %0, [%1]	\n"
@@ -338,7 +338,7 @@ static inline long long atomic64_read(const atomic64_t *v)
 	return val;
 }
 
-static inline void atomic64_set(atomic64_t *v, long long a)
+static inline void atomic64_set(atomic64_t *v, s64 a)
 {
 	/*
 	 * This could have been a simple assignment in "C" but would need
@@ -359,9 +359,9 @@ static inline void atomic64_set(atomic64_t *v, long long a)
 }
 
 #define ATOMIC64_OP(op, op1, op2)					\
-static inline void atomic64_##op(long long a, atomic64_t *v)		\
+static inline void atomic64_##op(s64 a, atomic64_t *v)			\
 {									\
-	unsigned long long val;						\
+	s64 val;							\
 									\
 	__asm__ __volatile__(						\
 	"1:				\n"				\
@@ -372,13 +372,13 @@ static inline void atomic64_##op(long long a, atomic64_t *v)		\
 	"	bnz     1b		\n"				\
 	: "=&r"(val)							\
 	: "r"(&v->counter), "ir"(a)					\
-	: "cc");						\
+	: "cc");							\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, op1, op2)		        	\
-static inline long long atomic64_##op##_return(long long a, atomic64_t *v)	\
+static inline s64 atomic64_##op##_return(s64 a, atomic64_t *v)		\
 {									\
-	unsigned long long val;						\
+	s64 val;							\
 									\
 	smp_mb();							\
 									\
@@ -399,9 +399,9 @@ static inline long long atomic64_##op##_return(long long a, atomic64_t *v)	\
 }
 
 #define ATOMIC64_FETCH_OP(op, op1, op2)		        		\
-static inline long long atomic64_fetch_##op(long long a, atomic64_t *v)	\
+static inline s64 atomic64_fetch_##op(s64 a, atomic64_t *v)		\
 {									\
-	unsigned long long val, orig;					\
+	s64 val, orig;							\
 									\
 	smp_mb();							\
 									\
@@ -441,10 +441,10 @@ ATOMIC64_OPS(xor, xor, xor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-static inline long long
-atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new)
+static inline s64
+atomic64_cmpxchg(atomic64_t *ptr, s64 expected, s64 new)
 {
-	long long prev;
+	s64 prev;
 
 	smp_mb();
 
@@ -464,9 +464,9 @@ atomic64_cmpxchg(atomic64_t *ptr, long long expected, long long new)
 	return prev;
 }
 
-static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+static inline s64 atomic64_xchg(atomic64_t *ptr, s64 new)
 {
-	long long prev;
+	s64 prev;
 
 	smp_mb();
 
@@ -492,9 +492,9 @@ static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
  * the atomic variable, v, was not decremented.
  */
 
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
-	long long val;
+	s64 val;
 
 	smp_mb();
 
@@ -525,10 +525,9 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
  * Atomically adds @a to @v, if it was not @u.
  * Returns the old value of @v
  */
-static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
-						  long long u)
+static inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	long long old, temp;
+	s64 old, temp;
 
 	smp_mb();
 
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index 50c3ac5f0809..75bb2c543e59 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -246,15 +246,15 @@ ATOMIC_OPS(xor, ^=, eor)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
-	long long counter;
+	s64 counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i) { (i) }
 
 #ifdef CONFIG_ARM_LPAE
-static inline long long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
 {
-	long long result;
+	s64 result;
 
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrd	%0, %H0, [%1]"
@@ -265,7 +265,7 @@ static inline long long atomic64_read(const atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void atomic64_set(atomic64_t *v, s64 i)
 {
 	__asm__ __volatile__("@ atomic64_set\n"
 "	strd	%2, %H2, [%1]"
@@ -274,9 +274,9 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 	);
 }
 #else
-static inline long long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
 {
-	long long result;
+	s64 result;
 
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrexd	%0, %H0, [%1]"
@@ -287,9 +287,9 @@ static inline long long atomic64_read(const atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_set(atomic64_t *v, long long i)
+static inline void atomic64_set(atomic64_t *v, s64 i)
 {
-	long long tmp;
+	s64 tmp;
 
 	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_set\n"
@@ -304,9 +304,9 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 #endif
 
 #define ATOMIC64_OP(op, op1, op2)					\
-static inline void atomic64_##op(long long i, atomic64_t *v)		\
+static inline void atomic64_##op(s64 i, atomic64_t *v)			\
 {									\
-	long long result;						\
+	s64 result;							\
 	unsigned long tmp;						\
 									\
 	prefetchw(&v->counter);						\
@@ -323,10 +323,10 @@ static inline void atomic64_##op(long long i, atomic64_t *v)		\
 }									\
 
 #define ATOMIC64_OP_RETURN(op, op1, op2)				\
-static inline long long							\
-atomic64_##op##_return_relaxed(long long i, atomic64_t *v)		\
+static inline s64							\
+atomic64_##op##_return_relaxed(s64 i, atomic64_t *v)			\
 {									\
-	long long result;						\
+	s64 result;							\
 	unsigned long tmp;						\
 									\
 	prefetchw(&v->counter);						\
@@ -346,10 +346,10 @@ atomic64_##op##_return_relaxed(long long i, atomic64_t *v)		\
 }
 
 #define ATOMIC64_FETCH_OP(op, op1, op2)					\
-static inline long long							\
-atomic64_fetch_##op##_relaxed(long long i, atomic64_t *v)		\
+static inline s64							\
+atomic64_fetch_##op##_relaxed(s64 i, atomic64_t *v)			\
 {									\
-	long long result, val;						\
+	s64 result, val;						\
 	unsigned long tmp;						\
 									\
 	prefetchw(&v->counter);						\
@@ -403,10 +403,9 @@ ATOMIC64_OPS(xor, eor, eor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-static inline long long
-atomic64_cmpxchg_relaxed(atomic64_t *ptr, long long old, long long new)
+static inline s64 atomic64_cmpxchg_relaxed(atomic64_t *ptr, s64 old, s64 new)
 {
-	long long oldval;
+	s64 oldval;
 	unsigned long res;
 
 	prefetchw(&ptr->counter);
@@ -427,9 +426,9 @@ atomic64_cmpxchg_relaxed(atomic64_t *ptr, long long old, long long new)
 }
 #define atomic64_cmpxchg_relaxed	atomic64_cmpxchg_relaxed
 
-static inline long long atomic64_xchg_relaxed(atomic64_t *ptr, long long new)
+static inline s64 atomic64_xchg_relaxed(atomic64_t *ptr, s64 new)
 {
-	long long result;
+	s64 result;
 	unsigned long tmp;
 
 	prefetchw(&ptr->counter);
@@ -447,9 +446,9 @@ static inline long long atomic64_xchg_relaxed(atomic64_t *ptr, long long new)
 }
 #define atomic64_xchg_relaxed		atomic64_xchg_relaxed
 
-static inline long long atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 atomic64_dec_if_positive(atomic64_t *v)
 {
-	long long result;
+	s64 result;
 	unsigned long tmp;
 
 	smp_mb();
@@ -475,10 +474,9 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 }
 #define atomic64_dec_if_positive atomic64_dec_if_positive
 
-static inline long long atomic64_fetch_add_unless(atomic64_t *v, long long a,
-						  long long u)
+static inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	long long oldval, newval;
+	s64 oldval, newval;
 	unsigned long tmp;
 
 	smp_mb();
diff --git a/arch/arm64/include/asm/atomic_ll_sc.h b/arch/arm64/include/asm/atomic_ll_sc.h
index 23c378606aed..c8c850bc3dfb 100644
--- a/arch/arm64/include/asm/atomic_ll_sc.h
+++ b/arch/arm64/include/asm/atomic_ll_sc.h
@@ -122,9 +122,9 @@ ATOMIC_OPS(xor, eor)
 
 #define ATOMIC64_OP(op, asm_op)						\
 __LL_SC_INLINE void							\
-__LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v))		\
+__LL_SC_PREFIX(arch_atomic64_##op(s64 i, atomic64_t *v))		\
 {									\
-	long result;							\
+	s64 result;							\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_" #op "\n"				\
@@ -139,10 +139,10 @@ __LL_SC_PREFIX(arch_atomic64_##op(long i, atomic64_t *v))		\
 __LL_SC_EXPORT(arch_atomic64_##op);
 
 #define ATOMIC64_OP_RETURN(name, mb, acq, rel, cl, op, asm_op)		\
-__LL_SC_INLINE long							\
-__LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\
+__LL_SC_INLINE s64							\
+__LL_SC_PREFIX(arch_atomic64_##op##_return##name(s64 i, atomic64_t *v))\
 {									\
-	long result;							\
+	s64 result;							\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_" #op "_return" #name "\n"		\
@@ -161,10 +161,10 @@ __LL_SC_PREFIX(arch_atomic64_##op##_return##name(long i, atomic64_t *v))\
 __LL_SC_EXPORT(arch_atomic64_##op##_return##name);
 
 #define ATOMIC64_FETCH_OP(name, mb, acq, rel, cl, op, asm_op)		\
-__LL_SC_INLINE long							\
-__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(long i, atomic64_t *v))	\
+__LL_SC_INLINE s64							\
+__LL_SC_PREFIX(arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v))	\
 {									\
-	long result, val;						\
+	s64 result, val;						\
 	unsigned long tmp;						\
 									\
 	asm volatile("// atomic64_fetch_" #op #name "\n"		\
@@ -214,10 +214,10 @@ ATOMIC64_OPS(xor, eor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-__LL_SC_INLINE long
+__LL_SC_INLINE s64
 __LL_SC_PREFIX(arch_atomic64_dec_if_positive(atomic64_t *v))
 {
-	long result;
+	s64 result;
 	unsigned long tmp;
 
 	asm volatile("// atomic64_dec_if_positive\n"
diff --git a/arch/arm64/include/asm/atomic_lse.h b/arch/arm64/include/asm/atomic_lse.h
index 45e030d54332..69acb1c19a15 100644
--- a/arch/arm64/include/asm/atomic_lse.h
+++ b/arch/arm64/include/asm/atomic_lse.h
@@ -213,9 +213,9 @@ ATOMIC_FETCH_OP_SUB(        , al, "memory")
 
 #define __LL_SC_ATOMIC64(op)	__LL_SC_CALL(arch_atomic64_##op)
 #define ATOMIC64_OP(op, asm_op)						\
-static inline void arch_atomic64_##op(long i, atomic64_t *v)		\
+static inline void arch_atomic64_##op(s64 i, atomic64_t *v)		\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(__LL_SC_ATOMIC64(op),	\
@@ -233,9 +233,9 @@ ATOMIC64_OP(add, stadd)
 #undef ATOMIC64_OP
 
 #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...)			\
-static inline long arch_atomic64_fetch_##op##name(long i, atomic64_t *v)\
+static inline s64 arch_atomic64_fetch_##op##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -265,9 +265,9 @@ ATOMIC64_FETCH_OPS(add, ldadd)
 #undef ATOMIC64_FETCH_OPS
 
 #define ATOMIC64_OP_ADD_RETURN(name, mb, cl...)				\
-static inline long arch_atomic64_add_return##name(long i, atomic64_t *v)\
+static inline s64 arch_atomic64_add_return##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -291,9 +291,9 @@ ATOMIC64_OP_ADD_RETURN(        , al, "memory")
 
 #undef ATOMIC64_OP_ADD_RETURN
 
-static inline void arch_atomic64_and(long i, atomic64_t *v)
+static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	register long x0 asm ("x0") = i;
+	register s64 x0 asm ("x0") = i;
 	register atomic64_t *x1 asm ("x1") = v;
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
@@ -309,9 +309,9 @@ static inline void arch_atomic64_and(long i, atomic64_t *v)
 }
 
 #define ATOMIC64_FETCH_OP_AND(name, mb, cl...)				\
-static inline long arch_atomic64_fetch_and##name(long i, atomic64_t *v)	\
+static inline s64 arch_atomic64_fetch_and##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -335,9 +335,9 @@ ATOMIC64_FETCH_OP_AND(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_AND
 
-static inline void arch_atomic64_sub(long i, atomic64_t *v)
+static inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
-	register long x0 asm ("x0") = i;
+	register s64 x0 asm ("x0") = i;
 	register atomic64_t *x1 asm ("x1") = v;
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
@@ -353,9 +353,9 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
 }
 
 #define ATOMIC64_OP_SUB_RETURN(name, mb, cl...)				\
-static inline long arch_atomic64_sub_return##name(long i, atomic64_t *v)\
+static inline s64 arch_atomic64_sub_return##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -381,9 +381,9 @@ ATOMIC64_OP_SUB_RETURN(        , al, "memory")
 #undef ATOMIC64_OP_SUB_RETURN
 
 #define ATOMIC64_FETCH_OP_SUB(name, mb, cl...)				\
-static inline long arch_atomic64_fetch_sub##name(long i, atomic64_t *v)	\
+static inline s64 arch_atomic64_fetch_sub##name(s64 i, atomic64_t *v)	\
 {									\
-	register long x0 asm ("x0") = i;				\
+	register s64 x0 asm ("x0") = i;					\
 	register atomic64_t *x1 asm ("x1") = v;				\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
@@ -407,7 +407,7 @@ ATOMIC64_FETCH_OP_SUB(        , al, "memory")
 
 #undef ATOMIC64_FETCH_OP_SUB
 
-static inline long arch_atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
 	register long x0 asm ("x0") = (long)v;
 
diff --git a/arch/ia64/include/asm/atomic.h b/arch/ia64/include/asm/atomic.h
index 206530d0751b..50440f3ddc43 100644
--- a/arch/ia64/include/asm/atomic.h
+++ b/arch/ia64/include/asm/atomic.h
@@ -124,10 +124,10 @@ ATOMIC_FETCH_OP(xor, ^)
 #undef ATOMIC_OP
 
 #define ATOMIC64_OP(op, c_op)						\
-static __inline__ long							\
-ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
+static __inline__ s64							\
+ia64_atomic64_##op (s64 i, atomic64_t *v)				\
 {									\
-	__s64 old, new;							\
+	s64 old, new;							\
 	CMPXCHG_BUGCHECK_DECL						\
 									\
 	do {								\
@@ -139,10 +139,10 @@ ia64_atomic64_##op (__s64 i, atomic64_t *v)				\
 }
 
 #define ATOMIC64_FETCH_OP(op, c_op)					\
-static __inline__ long							\
-ia64_atomic64_fetch_##op (__s64 i, atomic64_t *v)			\
+static __inline__ s64							\
+ia64_atomic64_fetch_##op (s64 i, atomic64_t *v)				\
 {									\
-	__s64 old, new;							\
+	s64 old, new;							\
 	CMPXCHG_BUGCHECK_DECL						\
 									\
 	do {								\
@@ -162,7 +162,7 @@ ATOMIC64_OPS(sub, -)
 
 #define atomic64_add_return(i,v)					\
 ({									\
-	long __ia64_aar_i = (i);					\
+	s64 __ia64_aar_i = (i);						\
 	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(__ia64_aar_i, &(v)->counter)	\
 		: ia64_atomic64_add(__ia64_aar_i, v);			\
@@ -170,7 +170,7 @@ ATOMIC64_OPS(sub, -)
 
 #define atomic64_sub_return(i,v)					\
 ({									\
-	long __ia64_asr_i = (i);					\
+	s64 __ia64_asr_i = (i);						\
 	__ia64_atomic_const(i)						\
 		? ia64_fetch_and_add(-__ia64_asr_i, &(v)->counter)	\
 		: ia64_atomic64_sub(__ia64_asr_i, v);			\
@@ -178,7 +178,7 @@ ATOMIC64_OPS(sub, -)
 
 #define atomic64_fetch_add(i,v)						\
 ({									\
-	long __ia64_aar_i = (i);					\
+	s64 __ia64_aar_i = (i);						\
 	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(__ia64_aar_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_add(__ia64_aar_i, v);		\
@@ -186,7 +186,7 @@ ATOMIC64_OPS(sub, -)
 
 #define atomic64_fetch_sub(i,v)						\
 ({									\
-	long __ia64_asr_i = (i);					\
+	s64 __ia64_asr_i = (i);						\
 	__ia64_atomic_const(i)						\
 		? ia64_fetchadd(-__ia64_asr_i, &(v)->counter, acq)	\
 		: ia64_atomic64_fetch_sub(__ia64_asr_i, v);		\
diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 94096299fc56..9a82dd11c0e9 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -254,10 +254,10 @@ static __inline__ int atomic_sub_if_positive(int i, atomic_t * v)
 #define atomic64_set(v, i)	WRITE_ONCE((v)->counter, (i))
 
 #define ATOMIC64_OP(op, c_op, asm_op)					      \
-static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
+static __inline__ void atomic64_##op(s64 i, atomic64_t * v)		      \
 {									      \
 	if (kernel_uses_llsc) {						      \
-		long temp;						      \
+		s64 temp;						      \
 									      \
 		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
@@ -280,12 +280,12 @@ static __inline__ void atomic64_##op(long i, atomic64_t * v)		      \
 }
 
 #define ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
-static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
+static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v)   \
 {									      \
-	long result;							      \
+	s64 result;							      \
 									      \
 	if (kernel_uses_llsc) {						      \
-		long temp;						      \
+		s64 temp;						      \
 									      \
 		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
@@ -314,12 +314,12 @@ static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 }
 
 #define ATOMIC64_FETCH_OP(op, c_op, asm_op)				      \
-static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
+static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v)    \
 {									      \
-	long result;							      \
+	s64 result;							      \
 									      \
 	if (kernel_uses_llsc) {						      \
-		long temp;						      \
+		s64 temp;						      \
 									      \
 		loongson_llsc_mb();					      \
 		__asm__ __volatile__(					      \
@@ -386,14 +386,14 @@ ATOMIC64_OPS(xor, ^=, xor)
  * Atomically test @v and subtract @i if @v is greater or equal than @i.
  * The function returns the old value of @v minus @i.
  */
-static __inline__ long atomic64_sub_if_positive(long i, atomic64_t * v)
+static __inline__ s64 atomic64_sub_if_positive(s64 i, atomic64_t * v)
 {
-	long result;
+	s64 result;
 
 	smp_mb__before_llsc();
 
 	if (kernel_uses_llsc) {
-		long temp;
+		s64 temp;
 
 		__asm__ __volatile__(
 		"	.set	push					\n"
diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
index 52eafaf74054..31c231ea56b7 100644
--- a/arch/powerpc/include/asm/atomic.h
+++ b/arch/powerpc/include/asm/atomic.h
@@ -297,24 +297,24 @@ static __inline__ int atomic_dec_if_positive(atomic_t *v)
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-static __inline__ long atomic64_read(const atomic64_t *v)
+static __inline__ s64 atomic64_read(const atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m"(v->counter));
 
 	return t;
 }
 
-static __inline__ void atomic64_set(atomic64_t *v, long i)
+static __inline__ void atomic64_set(atomic64_t *v, s64 i)
 {
 	__asm__ __volatile__("std%U0%X0 %1,%0" : "=m"(v->counter) : "r"(i));
 }
 
 #define ATOMIC64_OP(op, asm_op)						\
-static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
+static __inline__ void atomic64_##op(s64 a, atomic64_t *v)		\
 {									\
-	long t;								\
+	s64 t;								\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%3		# atomic64_" #op "\n"			\
@@ -327,10 +327,10 @@ static __inline__ void atomic64_##op(long a, atomic64_t *v)		\
 }
 
 #define ATOMIC64_OP_RETURN_RELAXED(op, asm_op)				\
-static inline long							\
-atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
+static inline s64							\
+atomic64_##op##_return_relaxed(s64 a, atomic64_t *v)			\
 {									\
-	long t;								\
+	s64 t;								\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%3		# atomic64_" #op "_return_relaxed\n"	\
@@ -345,10 +345,10 @@ atomic64_##op##_return_relaxed(long a, atomic64_t *v)			\
 }
 
 #define ATOMIC64_FETCH_OP_RELAXED(op, asm_op)				\
-static inline long							\
-atomic64_fetch_##op##_relaxed(long a, atomic64_t *v)			\
+static inline s64							\
+atomic64_fetch_##op##_relaxed(s64 a, atomic64_t *v)			\
 {									\
-	long res, t;							\
+	s64 res, t;							\
 									\
 	__asm__ __volatile__(						\
 "1:	ldarx	%0,0,%4		# atomic64_fetch_" #op "_relaxed\n"	\
@@ -396,7 +396,7 @@ ATOMIC64_OPS(xor, xor)
 
 static __inline__ void atomic64_inc(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_inc\n\
@@ -409,9 +409,9 @@ static __inline__ void atomic64_inc(atomic64_t *v)
 }
 #define atomic64_inc atomic64_inc
 
-static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
+static __inline__ s64 atomic64_inc_return_relaxed(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_inc_return_relaxed\n"
@@ -427,7 +427,7 @@ static __inline__ long atomic64_inc_return_relaxed(atomic64_t *v)
 
 static __inline__ void atomic64_dec(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_dec\n\
@@ -440,9 +440,9 @@ static __inline__ void atomic64_dec(atomic64_t *v)
 }
 #define atomic64_dec atomic64_dec
 
-static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
+static __inline__ s64 atomic64_dec_return_relaxed(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 "1:	ldarx	%0,0,%2		# atomic64_dec_return_relaxed\n"
@@ -463,9 +463,9 @@ static __inline__ long atomic64_dec_return_relaxed(atomic64_t *v)
  * Atomically test *v and decrement if it is greater than 0.
  * The function returns the old value of *v minus 1.
  */
-static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
+static __inline__ s64 atomic64_dec_if_positive(atomic64_t *v)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__(
 	PPC_ATOMIC_ENTRY_BARRIER
@@ -502,9 +502,9 @@ static __inline__ long atomic64_dec_if_positive(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
+static __inline__ s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-	long t;
+	s64 t;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
@@ -534,7 +534,7 @@ static __inline__ long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
  */
 static __inline__ int atomic64_inc_not_zero(atomic64_t *v)
 {
-	long t1, t2;
+	s64 t1, t2;
 
 	__asm__ __volatile__ (
 	PPC_ATOMIC_ENTRY_BARRIER
diff --git a/arch/riscv/include/asm/atomic.h b/arch/riscv/include/asm/atomic.h
index 9038aeb900a6..96f95c9ebd97 100644
--- a/arch/riscv/include/asm/atomic.h
+++ b/arch/riscv/include/asm/atomic.h
@@ -38,11 +38,11 @@ static __always_inline void atomic_set(atomic_t *v, int i)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC64_INIT(i) { (i) }
-static __always_inline long atomic64_read(const atomic64_t *v)
+static __always_inline s64 atomic64_read(const atomic64_t *v)
 {
 	return READ_ONCE(v->counter);
 }
-static __always_inline void atomic64_set(atomic64_t *v, long i)
+static __always_inline void atomic64_set(atomic64_t *v, s64 i)
 {
 	WRITE_ONCE(v->counter, i);
 }
@@ -66,11 +66,11 @@ void atomic##prefix##_##op(c_type i, atomic##prefix##_t *v)		\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_OP (op, asm_op, I, w,  int,   )
+        ATOMIC_OP (op, asm_op, I, w, int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_OP (op, asm_op, I, w,  int,   )				\
-        ATOMIC_OP (op, asm_op, I, d, long, 64)
+        ATOMIC_OP (op, asm_op, I, w, int,   )				\
+        ATOMIC_OP (op, asm_op, I, d, s64, 64)
 #endif
 
 ATOMIC_OPS(add, add,  i)
@@ -127,14 +127,14 @@ c_type atomic##prefix##_##op##_return(c_type i, atomic##prefix##_t *v)	\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_FETCH_OP( op, asm_op,       I, w,  int,   )		\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w,  int,   )
+        ATOMIC_FETCH_OP( op, asm_op,       I, w, int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, c_op, I)					\
-        ATOMIC_FETCH_OP( op, asm_op,       I, w,  int,   )		\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w,  int,   )		\
-        ATOMIC_FETCH_OP( op, asm_op,       I, d, long, 64)		\
-        ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, long, 64)
+        ATOMIC_FETCH_OP( op, asm_op,       I, w, int,   )		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, w, int,   )		\
+        ATOMIC_FETCH_OP( op, asm_op,       I, d, s64, 64)		\
+        ATOMIC_OP_RETURN(op, asm_op, c_op, I, d, s64, 64)
 #endif
 
 ATOMIC_OPS(add, add, +,  i)
@@ -166,11 +166,11 @@ ATOMIC_OPS(sub, add, +, -i)
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_FETCH_OP(op, asm_op, I, w,  int,   )
+        ATOMIC_FETCH_OP(op, asm_op, I, w, int,   )
 #else
 #define ATOMIC_OPS(op, asm_op, I)					\
-        ATOMIC_FETCH_OP(op, asm_op, I, w,  int,   )			\
-        ATOMIC_FETCH_OP(op, asm_op, I, d, long, 64)
+        ATOMIC_FETCH_OP(op, asm_op, I, w, int,   )			\
+        ATOMIC_FETCH_OP(op, asm_op, I, d, s64, 64)
 #endif
 
 ATOMIC_OPS(and, and, i)
@@ -219,9 +219,10 @@ static __always_inline int atomic_fetch_add_unless(atomic_t *v, int a, int u)
 #define atomic_fetch_add_unless atomic_fetch_add_unless
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_fetch_add_unless(atomic64_t *v, long a, long u)
+static __always_inline s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
-       long prev, rc;
+       s64 prev;
+       long rc;
 
 	__asm__ __volatile__ (
 		"0:	lr.d     %[p],  %[c]\n"
@@ -290,11 +291,11 @@ c_t atomic##prefix##_cmpxchg(atomic##prefix##_t *v, c_t o, c_t n)	\
 
 #ifdef CONFIG_GENERIC_ATOMIC64
 #define ATOMIC_OPS()							\
-	ATOMIC_OP( int,   , 4)
+	ATOMIC_OP(int,   , 4)
 #else
 #define ATOMIC_OPS()							\
-	ATOMIC_OP( int,   , 4)						\
-	ATOMIC_OP(long, 64, 8)
+	ATOMIC_OP(int,   , 4)						\
+	ATOMIC_OP(s64, 64, 8)
 #endif
 
 ATOMIC_OPS()
@@ -332,9 +333,10 @@ static __always_inline int atomic_sub_if_positive(atomic_t *v, int offset)
 #define atomic_dec_if_positive(v)	atomic_sub_if_positive(v, 1)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
-static __always_inline long atomic64_sub_if_positive(atomic64_t *v, int offset)
+static __always_inline s64 atomic64_sub_if_positive(atomic64_t *v, s64 offset)
 {
-       long prev, rc;
+       s64 prev;
+       long rc;
 
 	__asm__ __volatile__ (
 		"0:	lr.d     %[p],  %[c]\n"
diff --git a/arch/s390/include/asm/atomic.h b/arch/s390/include/asm/atomic.h
index fd20ab5d4cf7..491ad53a0d4e 100644
--- a/arch/s390/include/asm/atomic.h
+++ b/arch/s390/include/asm/atomic.h
@@ -84,9 +84,9 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 
 #define ATOMIC64_INIT(i)  { (i) }
 
-static inline long atomic64_read(const atomic64_t *v)
+static inline s64 atomic64_read(const atomic64_t *v)
 {
-	long c;
+	s64 c;
 
 	asm volatile(
 		"	lg	%0,%1\n"
@@ -94,49 +94,49 @@ static inline long atomic64_read(const atomic64_t *v)
 	return c;
 }
 
-static inline void atomic64_set(atomic64_t *v, long i)
+static inline void atomic64_set(atomic64_t *v, s64 i)
 {
 	asm volatile(
 		"	stg	%1,%0\n"
 		: "=Q" (v->counter) : "d" (i));
 }
 
-static inline long atomic64_add_return(long i, atomic64_t *v)
+static inline s64 atomic64_add_return(s64 i, atomic64_t *v)
 {
-	return __atomic64_add_barrier(i, &v->counter) + i;
+	return __atomic64_add_barrier(i, (long *)&v->counter) + i;
 }
 
-static inline long atomic64_fetch_add(long i, atomic64_t *v)
+static inline s64 atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	return __atomic64_add_barrier(i, &v->counter);
+	return __atomic64_add_barrier(i, (long *)&v->counter);
 }
 
-static inline void atomic64_add(long i, atomic64_t *v)
+static inline void atomic64_add(s64 i, atomic64_t *v)
 {
 #ifdef CONFIG_HAVE_MARCH_Z196_FEATURES
 	if (__builtin_constant_p(i) && (i > -129) && (i < 128)) {
-		__atomic64_add_const(i, &v->counter);
+		__atomic64_add_const(i, (long *)&v->counter);
 		return;
 	}
 #endif
-	__atomic64_add(i, &v->counter);
+	__atomic64_add(i, (long *)&v->counter);
 }
 
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline s64 atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
-	return __atomic64_cmpxchg(&v->counter, old, new);
+	return __atomic64_cmpxchg((long *)&v->counter, old, new);
 }
 
 #define ATOMIC64_OPS(op)						\
-static inline void atomic64_##op(long i, atomic64_t *v)			\
+static inline void atomic64_##op(s64 i, atomic64_t *v)			\
 {									\
-	__atomic64_##op(i, &v->counter);				\
+	__atomic64_##op(i, (long *)&v->counter);			\
 }									\
-static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+static inline long atomic64_fetch_##op(s64 i, atomic64_t *v)		\
 {									\
-	return __atomic64_##op##_barrier(i, &v->counter);		\
+	return __atomic64_##op##_barrier(i, (long *)&v->counter);	\
 }
 
 ATOMIC64_OPS(and)
@@ -145,8 +145,8 @@ ATOMIC64_OPS(xor)
 
 #undef ATOMIC64_OPS
 
-#define atomic64_sub_return(_i, _v)	atomic64_add_return(-(long)(_i), _v)
-#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(long)(_i), _v)
-#define atomic64_sub(_i, _v)		atomic64_add(-(long)(_i), _v)
+#define atomic64_sub_return(_i, _v)	atomic64_add_return(-(s64)(_i), _v)
+#define atomic64_fetch_sub(_i, _v)	atomic64_fetch_add(-(s64)(_i), _v)
+#define atomic64_sub(_i, _v)		atomic64_add(-(s64)(_i), _v)
 
 #endif /* __ARCH_S390_ATOMIC__  */
diff --git a/arch/s390/pci/pci_debug.c b/arch/s390/pci/pci_debug.c
index 6b48ca7760a7..3408c0df3ebf 100644
--- a/arch/s390/pci/pci_debug.c
+++ b/arch/s390/pci/pci_debug.c
@@ -74,7 +74,7 @@ static void pci_sw_counter_show(struct seq_file *m)
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(pci_sw_names); i++, counter++)
-		seq_printf(m, "%26s:\t%lu\n", pci_sw_names[i],
+		seq_printf(m, "%26s:\t%llu\n", pci_sw_names[i],
 			   atomic64_read(counter));
 }
 
diff --git a/arch/sparc/include/asm/atomic_64.h b/arch/sparc/include/asm/atomic_64.h
index 6963482c81d8..b60448397d4f 100644
--- a/arch/sparc/include/asm/atomic_64.h
+++ b/arch/sparc/include/asm/atomic_64.h
@@ -23,15 +23,15 @@
 
 #define ATOMIC_OP(op)							\
 void atomic_##op(int, atomic_t *);					\
-void atomic64_##op(long, atomic64_t *);
+void atomic64_##op(s64, atomic64_t *);
 
 #define ATOMIC_OP_RETURN(op)						\
 int atomic_##op##_return(int, atomic_t *);				\
-long atomic64_##op##_return(long, atomic64_t *);
+s64 atomic64_##op##_return(s64, atomic64_t *);
 
 #define ATOMIC_FETCH_OP(op)						\
 int atomic_fetch_##op(int, atomic_t *);					\
-long atomic64_fetch_##op(long, atomic64_t *);
+s64 atomic64_fetch_##op(s64, atomic64_t *);
 
 #define ATOMIC_OPS(op) ATOMIC_OP(op) ATOMIC_OP_RETURN(op) ATOMIC_FETCH_OP(op)
 
@@ -61,7 +61,7 @@ static inline int atomic_xchg(atomic_t *v, int new)
 	((__typeof__((v)->counter))cmpxchg(&((v)->counter), (o), (n)))
 #define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
 
-long atomic64_dec_if_positive(atomic64_t *v);
+s64 atomic64_dec_if_positive(atomic64_t *v);
 #define atomic64_dec_if_positive atomic64_dec_if_positive
 
 #endif /* !(__ARCH_SPARC64_ATOMIC__) */
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 3cd94a21bd53..ceb712b0a1c6 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2179,7 +2179,7 @@ static void x86_pmu_event_mapped(struct perf_event *event, struct mm_struct *mm)
 	 * For now, this can't happen because all callers hold mmap_sem
 	 * for write.  If this changes, we'll need a different solution.
 	 */
-	lockdep_assert_held_exclusive(&mm->mmap_sem);
+	lockdep_assert_held_write(&mm->mmap_sem);
 
 	if (atomic_inc_return(&mm->context.perf_rdpmc_allowed) == 1)
 		on_each_cpu_mask(mm_cpumask(mm), refresh_pce, NULL, 1);
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index ea3d95275b43..115127c7ad28 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -54,7 +54,7 @@ static __always_inline void arch_atomic_add(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "addl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
@@ -68,7 +68,7 @@ static __always_inline void arch_atomic_sub(int i, atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "subl %1,%0"
 		     : "+m" (v->counter)
-		     : "ir" (i));
+		     : "ir" (i) : "memory");
 }
 
 /**
@@ -95,7 +95,7 @@ static __always_inline bool arch_atomic_sub_and_test(int i, atomic_t *v)
 static __always_inline void arch_atomic_inc(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "incl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_inc arch_atomic_inc
 
@@ -108,7 +108,7 @@ static __always_inline void arch_atomic_inc(atomic_t *v)
 static __always_inline void arch_atomic_dec(atomic_t *v)
 {
 	asm volatile(LOCK_PREFIX "decl %0"
-		     : "+m" (v->counter));
+		     : "+m" (v->counter) :: "memory");
 }
 #define arch_atomic_dec arch_atomic_dec
 
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 6a5b0ec460da..52cfaecb13f9 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -9,7 +9,7 @@
 /* An 64bit atomic type */
 
 typedef struct {
-	u64 __aligned(8) counter;
+	s64 __aligned(8) counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val)	{ (val) }
@@ -71,8 +71,7 @@ ATOMIC64_DECL(add_unless);
  * the old value.
  */
 
-static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o,
-					      long long n)
+static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	return arch_cmpxchg64(&v->counter, o, n);
 }
@@ -85,9 +84,9 @@ static inline long long arch_atomic64_cmpxchg(atomic64_t *v, long long o,
  * Atomically xchgs the value of @v to @n and returns
  * the old value.
  */
-static inline long long arch_atomic64_xchg(atomic64_t *v, long long n)
+static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 n)
 {
-	long long o;
+	s64 o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
 	alternative_atomic64(xchg, "=&A" (o),
@@ -103,7 +102,7 @@ static inline long long arch_atomic64_xchg(atomic64_t *v, long long n)
  *
  * Atomically sets the value of @v to @n.
  */
-static inline void arch_atomic64_set(atomic64_t *v, long long i)
+static inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
@@ -118,9 +117,9 @@ static inline void arch_atomic64_set(atomic64_t *v, long long i)
  *
  * Atomically reads the value of @v and returns it.
  */
-static inline long long arch_atomic64_read(const atomic64_t *v)
+static inline s64 arch_atomic64_read(const atomic64_t *v)
 {
-	long long r;
+	s64 r;
 	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
 	return r;
 }
@@ -132,7 +131,7 @@ static inline long long arch_atomic64_read(const atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + *@v
  */
-static inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(add_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -143,7 +142,7 @@ static inline long long arch_atomic64_add_return(long long i, atomic64_t *v)
 /*
  * Other variants with different arithmetic operators:
  */
-static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	alternative_atomic64(sub_return,
 			     ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -151,18 +150,18 @@ static inline long long arch_atomic64_sub_return(long long i, atomic64_t *v)
 	return i;
 }
 
-static inline long long arch_atomic64_inc_return(atomic64_t *v)
+static inline s64 arch_atomic64_inc_return(atomic64_t *v)
 {
-	long long a;
+	s64 a;
 	alternative_atomic64(inc_return, "=&A" (a),
 			     "S" (v) : "memory", "ecx");
 	return a;
 }
 #define arch_atomic64_inc_return arch_atomic64_inc_return
 
-static inline long long arch_atomic64_dec_return(atomic64_t *v)
+static inline s64 arch_atomic64_dec_return(atomic64_t *v)
 {
-	long long a;
+	s64 a;
 	alternative_atomic64(dec_return, "=&A" (a),
 			     "S" (v) : "memory", "ecx");
 	return a;
@@ -176,7 +175,7 @@ static inline long long arch_atomic64_dec_return(atomic64_t *v)
  *
  * Atomically adds @i to @v.
  */
-static inline long long arch_atomic64_add(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(add, add_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -191,7 +190,7 @@ static inline long long arch_atomic64_add(long long i, atomic64_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline long long arch_atomic64_sub(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	__alternative_atomic64(sub, sub_return,
 			       ASM_OUTPUT2("+A" (i), "+c" (v)),
@@ -234,8 +233,7 @@ static inline void arch_atomic64_dec(atomic64_t *v)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns non-zero if the add was done, zero otherwise.
  */
-static inline int arch_atomic64_add_unless(atomic64_t *v, long long a,
-					   long long u)
+static inline int arch_atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
@@ -254,9 +252,9 @@ static inline int arch_atomic64_inc_not_zero(atomic64_t *v)
 }
 #define arch_atomic64_inc_not_zero arch_atomic64_inc_not_zero
 
-static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
+static inline s64 arch_atomic64_dec_if_positive(atomic64_t *v)
 {
-	long long r;
+	s64 r;
 	alternative_atomic64(dec_if_positive, "=&A" (r),
 			     "S" (v) : "ecx", "memory");
 	return r;
@@ -266,17 +264,17 @@ static inline long long arch_atomic64_dec_if_positive(atomic64_t *v)
 #undef alternative_atomic64
 #undef __alternative_atomic64
 
-static inline void arch_atomic64_and(long long i, atomic64_t *v)
+static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
 		c = old;
 }
 
-static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c & i)) != c)
 		c = old;
@@ -284,17 +282,17 @@ static inline long long arch_atomic64_fetch_and(long long i, atomic64_t *v)
 	return old;
 }
 
-static inline void arch_atomic64_or(long long i, atomic64_t *v)
+static inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
 		c = old;
 }
 
-static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c | i)) != c)
 		c = old;
@@ -302,17 +300,17 @@ static inline long long arch_atomic64_fetch_or(long long i, atomic64_t *v)
 	return old;
 }
 
-static inline void arch_atomic64_xor(long long i, atomic64_t *v)
+static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
 		c = old;
 }
 
-static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c ^ i)) != c)
 		c = old;
@@ -320,9 +318,9 @@ static inline long long arch_atomic64_fetch_xor(long long i, atomic64_t *v)
 	return old;
 }
 
-static inline long long arch_atomic64_fetch_add(long long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
-	long long old, c = 0;
+	s64 old, c = 0;
 
 	while ((old = arch_atomic64_cmpxchg(v, c, c + i)) != c)
 		c = old;
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index dadc20adba21..95c6ceac66b9 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -17,7 +17,7 @@
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-static inline long arch_atomic64_read(const atomic64_t *v)
+static inline s64 arch_atomic64_read(const atomic64_t *v)
 {
 	return READ_ONCE((v)->counter);
 }
@@ -29,7 +29,7 @@ static inline long arch_atomic64_read(const atomic64_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-static inline void arch_atomic64_set(atomic64_t *v, long i)
+static inline void arch_atomic64_set(atomic64_t *v, s64 i)
 {
 	WRITE_ONCE(v->counter, i);
 }
@@ -41,11 +41,11 @@ static inline void arch_atomic64_set(atomic64_t *v, long i)
  *
  * Atomically adds @i to @v.
  */
-static __always_inline void arch_atomic64_add(long i, atomic64_t *v)
+static __always_inline void arch_atomic64_add(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "addq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
@@ -55,11 +55,11 @@ static __always_inline void arch_atomic64_add(long i, atomic64_t *v)
  *
  * Atomically subtracts @i from @v.
  */
-static inline void arch_atomic64_sub(long i, atomic64_t *v)
+static inline void arch_atomic64_sub(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "subq %1,%0"
 		     : "=m" (v->counter)
-		     : "er" (i), "m" (v->counter));
+		     : "er" (i), "m" (v->counter) : "memory");
 }
 
 /**
@@ -71,7 +71,7 @@ static inline void arch_atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline bool arch_atomic64_sub_and_test(long i, atomic64_t *v)
+static inline bool arch_atomic64_sub_and_test(s64 i, atomic64_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, e, "er", i);
 }
@@ -87,7 +87,7 @@ static __always_inline void arch_atomic64_inc(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "incq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 #define arch_atomic64_inc arch_atomic64_inc
 
@@ -101,7 +101,7 @@ static __always_inline void arch_atomic64_dec(atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "decq %0"
 		     : "=m" (v->counter)
-		     : "m" (v->counter));
+		     : "m" (v->counter) : "memory");
 }
 #define arch_atomic64_dec arch_atomic64_dec
 
@@ -142,7 +142,7 @@ static inline bool arch_atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
+static inline bool arch_atomic64_add_negative(s64 i, atomic64_t *v)
 {
 	return GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, s, "er", i);
 }
@@ -155,43 +155,43 @@ static inline bool arch_atomic64_add_negative(long i, atomic64_t *v)
  *
  * Atomically adds @i to @v and returns @i + @v
  */
-static __always_inline long arch_atomic64_add_return(long i, atomic64_t *v)
+static __always_inline s64 arch_atomic64_add_return(s64 i, atomic64_t *v)
 {
 	return i + xadd(&v->counter, i);
 }
 
-static inline long arch_atomic64_sub_return(long i, atomic64_t *v)
+static inline s64 arch_atomic64_sub_return(s64 i, atomic64_t *v)
 {
 	return arch_atomic64_add_return(-i, v);
 }
 
-static inline long arch_atomic64_fetch_add(long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_add(s64 i, atomic64_t *v)
 {
 	return xadd(&v->counter, i);
 }
 
-static inline long arch_atomic64_fetch_sub(long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_sub(s64 i, atomic64_t *v)
 {
 	return xadd(&v->counter, -i);
 }
 
-static inline long arch_atomic64_cmpxchg(atomic64_t *v, long old, long new)
+static inline s64 arch_atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
 {
 	return arch_cmpxchg(&v->counter, old, new);
 }
 
 #define arch_atomic64_try_cmpxchg arch_atomic64_try_cmpxchg
-static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, long new)
+static __always_inline bool arch_atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
 {
 	return try_cmpxchg(&v->counter, old, new);
 }
 
-static inline long arch_atomic64_xchg(atomic64_t *v, long new)
+static inline s64 arch_atomic64_xchg(atomic64_t *v, s64 new)
 {
 	return arch_xchg(&v->counter, new);
 }
 
-static inline void arch_atomic64_and(long i, atomic64_t *v)
+static inline void arch_atomic64_and(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "andq %1,%0"
 			: "+m" (v->counter)
@@ -199,7 +199,7 @@ static inline void arch_atomic64_and(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long arch_atomic64_fetch_and(long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_and(s64 i, atomic64_t *v)
 {
 	s64 val = arch_atomic64_read(v);
 
@@ -208,7 +208,7 @@ static inline long arch_atomic64_fetch_and(long i, atomic64_t *v)
 	return val;
 }
 
-static inline void arch_atomic64_or(long i, atomic64_t *v)
+static inline void arch_atomic64_or(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "orq %1,%0"
 			: "+m" (v->counter)
@@ -216,7 +216,7 @@ static inline void arch_atomic64_or(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long arch_atomic64_fetch_or(long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_or(s64 i, atomic64_t *v)
 {
 	s64 val = arch_atomic64_read(v);
 
@@ -225,7 +225,7 @@ static inline long arch_atomic64_fetch_or(long i, atomic64_t *v)
 	return val;
 }
 
-static inline void arch_atomic64_xor(long i, atomic64_t *v)
+static inline void arch_atomic64_xor(s64 i, atomic64_t *v)
 {
 	asm volatile(LOCK_PREFIX "xorq %1,%0"
 			: "+m" (v->counter)
@@ -233,7 +233,7 @@ static inline void arch_atomic64_xor(long i, atomic64_t *v)
 			: "memory");
 }
 
-static inline long arch_atomic64_fetch_xor(long i, atomic64_t *v)
+static inline s64 arch_atomic64_fetch_xor(s64 i, atomic64_t *v)
 {
 	s64 val = arch_atomic64_read(v);
 
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 14de0432d288..84f848c2541a 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -80,8 +80,8 @@ do {									\
 })
 
 /* Atomic operations are already serializing on x86 */
-#define __smp_mb__before_atomic()	barrier()
-#define __smp_mb__after_atomic()	barrier()
+#define __smp_mb__before_atomic()	do { } while (0)
+#define __smp_mb__after_atomic()	do { } while (0)
 
 #include <asm-generic/barrier.h>
 
diff --git a/arch/x86/include/asm/irq_regs.h b/arch/x86/include/asm/irq_regs.h
index 8f3bee821e6c..187ce59aea28 100644
--- a/arch/x86/include/asm/irq_regs.h
+++ b/arch/x86/include/asm/irq_regs.h
@@ -16,7 +16,7 @@ DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
 {
-	return this_cpu_read(irq_regs);
+	return __this_cpu_read(irq_regs);
 }
 
 static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
@@ -24,7 +24,7 @@ static inline struct pt_regs *set_irq_regs(struct pt_regs *new_regs)
 	struct pt_regs *old_regs;
 
 	old_regs = get_irq_regs();
-	this_cpu_write(irq_regs, new_regs);
+	__this_cpu_write(irq_regs, new_regs);
 
 	return old_regs;
 }
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index 65191ce8e1cf..06c3cc22a058 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -2,6 +2,8 @@
 #ifndef _ASM_X86_JUMP_LABEL_H
 #define _ASM_X86_JUMP_LABEL_H
 
+#define HAVE_JUMP_LABEL_BATCH
+
 #define JUMP_LABEL_NOP_SIZE 5
 
 #ifdef CONFIG_X86_64
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 1a19d11cfbbd..2278797c769d 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -87,7 +87,7 @@
  * don't give an lvalue though). */
 extern void __bad_percpu_size(void);
 
-#define percpu_to_op(op, var, val)			\
+#define percpu_to_op(qual, op, var, val)		\
 do {							\
 	typedef typeof(var) pto_T__;			\
 	if (0) {					\
@@ -97,22 +97,22 @@ do {							\
 	}						\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b %1,"__percpu_arg(0)		\
+		asm qual (op "b %1,"__percpu_arg(0)	\
 		    : "+m" (var)			\
 		    : "qi" ((pto_T__)(val)));		\
 		break;					\
 	case 2:						\
-		asm(op "w %1,"__percpu_arg(0)		\
+		asm qual (op "w %1,"__percpu_arg(0)	\
 		    : "+m" (var)			\
 		    : "ri" ((pto_T__)(val)));		\
 		break;					\
 	case 4:						\
-		asm(op "l %1,"__percpu_arg(0)		\
+		asm qual (op "l %1,"__percpu_arg(0)	\
 		    : "+m" (var)			\
 		    : "ri" ((pto_T__)(val)));		\
 		break;					\
 	case 8:						\
-		asm(op "q %1,"__percpu_arg(0)		\
+		asm qual (op "q %1,"__percpu_arg(0)	\
 		    : "+m" (var)			\
 		    : "re" ((pto_T__)(val)));		\
 		break;					\
@@ -124,7 +124,7 @@ do {							\
  * Generate a percpu add to memory instruction and optimize code
  * if one is added or subtracted.
  */
-#define percpu_add_op(var, val)						\
+#define percpu_add_op(qual, var, val)					\
 do {									\
 	typedef typeof(var) pao_T__;					\
 	const int pao_ID__ = (__builtin_constant_p(val) &&		\
@@ -138,41 +138,41 @@ do {									\
 	switch (sizeof(var)) {						\
 	case 1:								\
 		if (pao_ID__ == 1)					\
-			asm("incb "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("incb "__percpu_arg(0) : "+m" (var));	\
 		else if (pao_ID__ == -1)				\
-			asm("decb "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("decb "__percpu_arg(0) : "+m" (var));	\
 		else							\
-			asm("addb %1, "__percpu_arg(0)			\
+			asm qual ("addb %1, "__percpu_arg(0)		\
 			    : "+m" (var)				\
 			    : "qi" ((pao_T__)(val)));			\
 		break;							\
 	case 2:								\
 		if (pao_ID__ == 1)					\
-			asm("incw "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("incw "__percpu_arg(0) : "+m" (var));	\
 		else if (pao_ID__ == -1)				\
-			asm("decw "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("decw "__percpu_arg(0) : "+m" (var));	\
 		else							\
-			asm("addw %1, "__percpu_arg(0)			\
+			asm qual ("addw %1, "__percpu_arg(0)		\
 			    : "+m" (var)				\
 			    : "ri" ((pao_T__)(val)));			\
 		break;							\
 	case 4:								\
 		if (pao_ID__ == 1)					\
-			asm("incl "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("incl "__percpu_arg(0) : "+m" (var));	\
 		else if (pao_ID__ == -1)				\
-			asm("decl "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("decl "__percpu_arg(0) : "+m" (var));	\
 		else							\
-			asm("addl %1, "__percpu_arg(0)			\
+			asm qual ("addl %1, "__percpu_arg(0)		\
 			    : "+m" (var)				\
 			    : "ri" ((pao_T__)(val)));			\
 		break;							\
 	case 8:								\
 		if (pao_ID__ == 1)					\
-			asm("incq "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("incq "__percpu_arg(0) : "+m" (var));	\
 		else if (pao_ID__ == -1)				\
-			asm("decq "__percpu_arg(0) : "+m" (var));	\
+			asm qual ("decq "__percpu_arg(0) : "+m" (var));	\
 		else							\
-			asm("addq %1, "__percpu_arg(0)			\
+			asm qual ("addq %1, "__percpu_arg(0)		\
 			    : "+m" (var)				\
 			    : "re" ((pao_T__)(val)));			\
 		break;							\
@@ -180,27 +180,27 @@ do {									\
 	}								\
 } while (0)
 
-#define percpu_from_op(op, var)				\
+#define percpu_from_op(qual, op, var)			\
 ({							\
 	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm volatile(op "b "__percpu_arg(1)",%0"\
+		asm qual (op "b "__percpu_arg(1)",%0"	\
 		    : "=q" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm volatile(op "w "__percpu_arg(1)",%0"\
+		asm qual (op "w "__percpu_arg(1)",%0"	\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm volatile(op "l "__percpu_arg(1)",%0"\
+		asm qual (op "l "__percpu_arg(1)",%0"	\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 8:						\
-		asm volatile(op "q "__percpu_arg(1)",%0"\
+		asm qual (op "q "__percpu_arg(1)",%0"	\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
@@ -238,23 +238,23 @@ do {									\
 	pfo_ret__;					\
 })
 
-#define percpu_unary_op(op, var)			\
+#define percpu_unary_op(qual, op, var)			\
 ({							\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_arg(0)		\
+		asm qual (op "b "__percpu_arg(0)	\
 		    : "+m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_arg(0)		\
+		asm qual (op "w "__percpu_arg(0)	\
 		    : "+m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_arg(0)		\
+		asm qual (op "l "__percpu_arg(0)	\
 		    : "+m" (var));			\
 		break;					\
 	case 8:						\
-		asm(op "q "__percpu_arg(0)		\
+		asm qual (op "q "__percpu_arg(0)	\
 		    : "+m" (var));			\
 		break;					\
 	default: __bad_percpu_size();			\
@@ -264,27 +264,27 @@ do {									\
 /*
  * Add return operation
  */
-#define percpu_add_return_op(var, val)					\
+#define percpu_add_return_op(qual, var, val)				\
 ({									\
 	typeof(var) paro_ret__ = val;					\
 	switch (sizeof(var)) {						\
 	case 1:								\
-		asm("xaddb %0, "__percpu_arg(1)				\
+		asm qual ("xaddb %0, "__percpu_arg(1)			\
 			    : "+q" (paro_ret__), "+m" (var)		\
 			    : : "memory");				\
 		break;							\
 	case 2:								\
-		asm("xaddw %0, "__percpu_arg(1)				\
+		asm qual ("xaddw %0, "__percpu_arg(1)			\
 			    : "+r" (paro_ret__), "+m" (var)		\
 			    : : "memory");				\
 		break;							\
 	case 4:								\
-		asm("xaddl %0, "__percpu_arg(1)				\
+		asm qual ("xaddl %0, "__percpu_arg(1)			\
 			    : "+r" (paro_ret__), "+m" (var)		\
 			    : : "memory");				\
 		break;							\
 	case 8:								\
-		asm("xaddq %0, "__percpu_arg(1)				\
+		asm qual ("xaddq %0, "__percpu_arg(1)			\
 			    : "+re" (paro_ret__), "+m" (var)		\
 			    : : "memory");				\
 		break;							\
@@ -299,13 +299,13 @@ do {									\
  * expensive due to the implied lock prefix.  The processor cannot prefetch
  * cachelines if xchg is used.
  */
-#define percpu_xchg_op(var, nval)					\
+#define percpu_xchg_op(qual, var, nval)					\
 ({									\
 	typeof(var) pxo_ret__;						\
 	typeof(var) pxo_new__ = (nval);					\
 	switch (sizeof(var)) {						\
 	case 1:								\
-		asm("\n\tmov "__percpu_arg(1)",%%al"			\
+		asm qual ("\n\tmov "__percpu_arg(1)",%%al"		\
 		    "\n1:\tcmpxchgb %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
 			    : "=&a" (pxo_ret__), "+m" (var)		\
@@ -313,7 +313,7 @@ do {									\
 			    : "memory");				\
 		break;							\
 	case 2:								\
-		asm("\n\tmov "__percpu_arg(1)",%%ax"			\
+		asm qual ("\n\tmov "__percpu_arg(1)",%%ax"		\
 		    "\n1:\tcmpxchgw %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
 			    : "=&a" (pxo_ret__), "+m" (var)		\
@@ -321,7 +321,7 @@ do {									\
 			    : "memory");				\
 		break;							\
 	case 4:								\
-		asm("\n\tmov "__percpu_arg(1)",%%eax"			\
+		asm qual ("\n\tmov "__percpu_arg(1)",%%eax"		\
 		    "\n1:\tcmpxchgl %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
 			    : "=&a" (pxo_ret__), "+m" (var)		\
@@ -329,7 +329,7 @@ do {									\
 			    : "memory");				\
 		break;							\
 	case 8:								\
-		asm("\n\tmov "__percpu_arg(1)",%%rax"			\
+		asm qual ("\n\tmov "__percpu_arg(1)",%%rax"		\
 		    "\n1:\tcmpxchgq %2, "__percpu_arg(1)		\
 		    "\n\tjnz 1b"					\
 			    : "=&a" (pxo_ret__), "+m" (var)		\
@@ -345,32 +345,32 @@ do {									\
  * cmpxchg has no such implied lock semantics as a result it is much
  * more efficient for cpu local operations.
  */
-#define percpu_cmpxchg_op(var, oval, nval)				\
+#define percpu_cmpxchg_op(qual, var, oval, nval)			\
 ({									\
 	typeof(var) pco_ret__;						\
 	typeof(var) pco_old__ = (oval);					\
 	typeof(var) pco_new__ = (nval);					\
 	switch (sizeof(var)) {						\
 	case 1:								\
-		asm("cmpxchgb %2, "__percpu_arg(1)			\
+		asm qual ("cmpxchgb %2, "__percpu_arg(1)		\
 			    : "=a" (pco_ret__), "+m" (var)		\
 			    : "q" (pco_new__), "0" (pco_old__)		\
 			    : "memory");				\
 		break;							\
 	case 2:								\
-		asm("cmpxchgw %2, "__percpu_arg(1)			\
+		asm qual ("cmpxchgw %2, "__percpu_arg(1)		\
 			    : "=a" (pco_ret__), "+m" (var)		\
 			    : "r" (pco_new__), "0" (pco_old__)		\
 			    : "memory");				\
 		break;							\
 	case 4:								\
-		asm("cmpxchgl %2, "__percpu_arg(1)			\
+		asm qual ("cmpxchgl %2, "__percpu_arg(1)		\
 			    : "=a" (pco_ret__), "+m" (var)		\
 			    : "r" (pco_new__), "0" (pco_old__)		\
 			    : "memory");				\
 		break;							\
 	case 8:								\
-		asm("cmpxchgq %2, "__percpu_arg(1)			\
+		asm qual ("cmpxchgq %2, "__percpu_arg(1)		\
 			    : "=a" (pco_ret__), "+m" (var)		\
 			    : "r" (pco_new__), "0" (pco_old__)		\
 			    : "memory");				\
@@ -391,58 +391,70 @@ do {									\
  */
 #define this_cpu_read_stable(var)	percpu_stable_op("mov", var)
 
-#define raw_cpu_read_1(pcp)		percpu_from_op("mov", pcp)
-#define raw_cpu_read_2(pcp)		percpu_from_op("mov", pcp)
-#define raw_cpu_read_4(pcp)		percpu_from_op("mov", pcp)
+#define raw_cpu_read_1(pcp)		percpu_from_op(, "mov", pcp)
+#define raw_cpu_read_2(pcp)		percpu_from_op(, "mov", pcp)
+#define raw_cpu_read_4(pcp)		percpu_from_op(, "mov", pcp)
 
-#define raw_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define raw_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define raw_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define raw_cpu_add_1(pcp, val)		percpu_add_op((pcp), val)
-#define raw_cpu_add_2(pcp, val)		percpu_add_op((pcp), val)
-#define raw_cpu_add_4(pcp, val)		percpu_add_op((pcp), val)
-#define raw_cpu_and_1(pcp, val)		percpu_to_op("and", (pcp), val)
-#define raw_cpu_and_2(pcp, val)		percpu_to_op("and", (pcp), val)
-#define raw_cpu_and_4(pcp, val)		percpu_to_op("and", (pcp), val)
-#define raw_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
-#define raw_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
-#define raw_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
-#define raw_cpu_xchg_1(pcp, val)	percpu_xchg_op(pcp, val)
-#define raw_cpu_xchg_2(pcp, val)	percpu_xchg_op(pcp, val)
-#define raw_cpu_xchg_4(pcp, val)	percpu_xchg_op(pcp, val)
+#define raw_cpu_write_1(pcp, val)	percpu_to_op(, "mov", (pcp), val)
+#define raw_cpu_write_2(pcp, val)	percpu_to_op(, "mov", (pcp), val)
+#define raw_cpu_write_4(pcp, val)	percpu_to_op(, "mov", (pcp), val)
+#define raw_cpu_add_1(pcp, val)		percpu_add_op(, (pcp), val)
+#define raw_cpu_add_2(pcp, val)		percpu_add_op(, (pcp), val)
+#define raw_cpu_add_4(pcp, val)		percpu_add_op(, (pcp), val)
+#define raw_cpu_and_1(pcp, val)		percpu_to_op(, "and", (pcp), val)
+#define raw_cpu_and_2(pcp, val)		percpu_to_op(, "and", (pcp), val)
+#define raw_cpu_and_4(pcp, val)		percpu_to_op(, "and", (pcp), val)
+#define raw_cpu_or_1(pcp, val)		percpu_to_op(, "or", (pcp), val)
+#define raw_cpu_or_2(pcp, val)		percpu_to_op(, "or", (pcp), val)
+#define raw_cpu_or_4(pcp, val)		percpu_to_op(, "or", (pcp), val)
 
-#define this_cpu_read_1(pcp)		percpu_from_op("mov", pcp)
-#define this_cpu_read_2(pcp)		percpu_from_op("mov", pcp)
-#define this_cpu_read_4(pcp)		percpu_from_op("mov", pcp)
-#define this_cpu_write_1(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define this_cpu_write_2(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define this_cpu_write_4(pcp, val)	percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_1(pcp, val)	percpu_add_op((pcp), val)
-#define this_cpu_add_2(pcp, val)	percpu_add_op((pcp), val)
-#define this_cpu_add_4(pcp, val)	percpu_add_op((pcp), val)
-#define this_cpu_and_1(pcp, val)	percpu_to_op("and", (pcp), val)
-#define this_cpu_and_2(pcp, val)	percpu_to_op("and", (pcp), val)
-#define this_cpu_and_4(pcp, val)	percpu_to_op("and", (pcp), val)
-#define this_cpu_or_1(pcp, val)		percpu_to_op("or", (pcp), val)
-#define this_cpu_or_2(pcp, val)		percpu_to_op("or", (pcp), val)
-#define this_cpu_or_4(pcp, val)		percpu_to_op("or", (pcp), val)
-#define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(pcp, nval)
-#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(pcp, nval)
-#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(pcp, nval)
+/*
+ * raw_cpu_xchg() can use a load-store since it is not required to be
+ * IRQ-safe.
+ */
+#define raw_percpu_xchg_op(var, nval)					\
+({									\
+	typeof(var) pxo_ret__ = raw_cpu_read(var);			\
+	raw_cpu_write(var, (nval));					\
+	pxo_ret__;							\
+})
 
-#define raw_cpu_add_return_1(pcp, val)		percpu_add_return_op(pcp, val)
-#define raw_cpu_add_return_2(pcp, val)		percpu_add_return_op(pcp, val)
-#define raw_cpu_add_return_4(pcp, val)		percpu_add_return_op(pcp, val)
-#define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-#define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-#define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define raw_cpu_xchg_1(pcp, val)	raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
+#define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)
 
-#define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(pcp, val)
-#define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(pcp, val)
-#define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(pcp, val)
-#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
-#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define this_cpu_read_1(pcp)		percpu_from_op(volatile, "mov", pcp)
+#define this_cpu_read_2(pcp)		percpu_from_op(volatile, "mov", pcp)
+#define this_cpu_read_4(pcp)		percpu_from_op(volatile, "mov", pcp)
+#define this_cpu_write_1(pcp, val)	percpu_to_op(volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op(volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op(volatile, "mov", (pcp), val)
+#define this_cpu_add_1(pcp, val)	percpu_add_op(volatile, (pcp), val)
+#define this_cpu_add_2(pcp, val)	percpu_add_op(volatile, (pcp), val)
+#define this_cpu_add_4(pcp, val)	percpu_add_op(volatile, (pcp), val)
+#define this_cpu_and_1(pcp, val)	percpu_to_op(volatile, "and", (pcp), val)
+#define this_cpu_and_2(pcp, val)	percpu_to_op(volatile, "and", (pcp), val)
+#define this_cpu_and_4(pcp, val)	percpu_to_op(volatile, "and", (pcp), val)
+#define this_cpu_or_1(pcp, val)		percpu_to_op(volatile, "or", (pcp), val)
+#define this_cpu_or_2(pcp, val)		percpu_to_op(volatile, "or", (pcp), val)
+#define this_cpu_or_4(pcp, val)		percpu_to_op(volatile, "or", (pcp), val)
+#define this_cpu_xchg_1(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
+#define this_cpu_xchg_2(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
+#define this_cpu_xchg_4(pcp, nval)	percpu_xchg_op(volatile, pcp, nval)
+
+#define raw_cpu_add_return_1(pcp, val)		percpu_add_return_op(, pcp, val)
+#define raw_cpu_add_return_2(pcp, val)		percpu_add_return_op(, pcp, val)
+#define raw_cpu_add_return_4(pcp, val)		percpu_add_return_op(, pcp, val)
+#define raw_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
+#define raw_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
+#define raw_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
+
+#define this_cpu_add_return_1(pcp, val)		percpu_add_return_op(volatile, pcp, val)
+#define this_cpu_add_return_2(pcp, val)		percpu_add_return_op(volatile, pcp, val)
+#define this_cpu_add_return_4(pcp, val)		percpu_add_return_op(volatile, pcp, val)
+#define this_cpu_cmpxchg_1(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
+#define this_cpu_cmpxchg_2(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
+#define this_cpu_cmpxchg_4(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
 
 #ifdef CONFIG_X86_CMPXCHG64
 #define percpu_cmpxchg8b_double(pcp1, pcp2, o1, o2, n1, n2)		\
@@ -466,23 +478,23 @@ do {									\
  * 32 bit must fall back to generic operations.
  */
 #ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp)			percpu_from_op("mov", pcp)
-#define raw_cpu_write_8(pcp, val)		percpu_to_op("mov", (pcp), val)
-#define raw_cpu_add_8(pcp, val)			percpu_add_op((pcp), val)
-#define raw_cpu_and_8(pcp, val)			percpu_to_op("and", (pcp), val)
-#define raw_cpu_or_8(pcp, val)			percpu_to_op("or", (pcp), val)
-#define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(pcp, val)
-#define raw_cpu_xchg_8(pcp, nval)		percpu_xchg_op(pcp, nval)
-#define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define raw_cpu_read_8(pcp)			percpu_from_op(, "mov", pcp)
+#define raw_cpu_write_8(pcp, val)		percpu_to_op(, "mov", (pcp), val)
+#define raw_cpu_add_8(pcp, val)			percpu_add_op(, (pcp), val)
+#define raw_cpu_and_8(pcp, val)			percpu_to_op(, "and", (pcp), val)
+#define raw_cpu_or_8(pcp, val)			percpu_to_op(, "or", (pcp), val)
+#define raw_cpu_add_return_8(pcp, val)		percpu_add_return_op(, pcp, val)
+#define raw_cpu_xchg_8(pcp, nval)		raw_percpu_xchg_op(pcp, nval)
+#define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(, pcp, oval, nval)
 
-#define this_cpu_read_8(pcp)			percpu_from_op("mov", pcp)
-#define this_cpu_write_8(pcp, val)		percpu_to_op("mov", (pcp), val)
-#define this_cpu_add_8(pcp, val)		percpu_add_op((pcp), val)
-#define this_cpu_and_8(pcp, val)		percpu_to_op("and", (pcp), val)
-#define this_cpu_or_8(pcp, val)			percpu_to_op("or", (pcp), val)
-#define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(pcp, val)
-#define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(pcp, nval)
-#define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(pcp, oval, nval)
+#define this_cpu_read_8(pcp)			percpu_from_op(volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val)		percpu_to_op(volatile, "mov", (pcp), val)
+#define this_cpu_add_8(pcp, val)		percpu_add_op(volatile, (pcp), val)
+#define this_cpu_and_8(pcp, val)		percpu_to_op(volatile, "and", (pcp), val)
+#define this_cpu_or_8(pcp, val)			percpu_to_op(volatile, "or", (pcp), val)
+#define this_cpu_add_return_8(pcp, val)		percpu_add_return_op(volatile, pcp, val)
+#define this_cpu_xchg_8(pcp, nval)		percpu_xchg_op(volatile, pcp, nval)
+#define this_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(volatile, pcp, oval, nval)
 
 /*
  * Pretty complex macro to generate cmpxchg16 instruction.  The instruction
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index da545df207b2..0d3fe060a44f 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -162,7 +162,8 @@ __visible void smp_call_function_single_interrupt(struct pt_regs *r);
  * from the initial startup. We map APIC_BASE very early in page_setup(),
  * so this is correct in the x86 case.
  */
-#define raw_smp_processor_id() (this_cpu_read(cpu_number))
+#define raw_smp_processor_id()  this_cpu_read(cpu_number)
+#define __smp_processor_id() __this_cpu_read(cpu_number)
 
 #ifdef CONFIG_X86_32
 extern int safe_smp_processor_id(void);
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index 880b5515b1d6..d83e9f771d86 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -18,6 +18,20 @@ static inline void apply_paravirt(struct paravirt_patch_site *start,
 #define __parainstructions_end	NULL
 #endif
 
+/*
+ * Currently, the max observed size in the kernel code is
+ * JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
+ * Raise it if needed.
+ */
+#define POKE_MAX_OPCODE_SIZE	5
+
+struct text_poke_loc {
+	void *detour;
+	void *addr;
+	size_t len;
+	const char opcode[POKE_MAX_OPCODE_SIZE];
+};
+
 extern void text_poke_early(void *addr, const void *opcode, size_t len);
 
 /*
@@ -38,6 +52,7 @@ extern void *text_poke(void *addr, const void *opcode, size_t len);
 extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
 extern int poke_int3_handler(struct pt_regs *regs);
 extern void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler);
+extern void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries);
 extern int after_bootmem;
 extern __ro_after_init struct mm_struct *poking_mm;
 extern __ro_after_init unsigned long poking_addr;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 390596b761e3..bd542f9b0953 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -14,6 +14,7 @@
 #include <linux/kdebug.h>
 #include <linux/kprobes.h>
 #include <linux/mmu_context.h>
+#include <linux/bsearch.h>
 #include <asm/text-patching.h>
 #include <asm/alternative.h>
 #include <asm/sections.h>
@@ -848,81 +849,133 @@ static void do_sync_core(void *info)
 	sync_core();
 }
 
-static bool bp_patching_in_progress;
-static void *bp_int3_handler, *bp_int3_addr;
+static struct bp_patching_desc {
+	struct text_poke_loc *vec;
+	int nr_entries;
+} bp_patching;
+
+static int patch_cmp(const void *key, const void *elt)
+{
+	struct text_poke_loc *tp = (struct text_poke_loc *) elt;
+
+	if (key < tp->addr)
+		return -1;
+	if (key > tp->addr)
+		return 1;
+	return 0;
+}
+NOKPROBE_SYMBOL(patch_cmp);
 
 int poke_int3_handler(struct pt_regs *regs)
 {
+	struct text_poke_loc *tp;
+	unsigned char int3 = 0xcc;
+	void *ip;
+
 	/*
 	 * Having observed our INT3 instruction, we now must observe
-	 * bp_patching_in_progress.
+	 * bp_patching.nr_entries.
 	 *
-	 * 	in_progress = TRUE		INT3
+	 * 	nr_entries != 0			INT3
 	 * 	WMB				RMB
-	 * 	write INT3			if (in_progress)
+	 * 	write INT3			if (nr_entries)
 	 *
-	 * Idem for bp_int3_handler.
+	 * Idem for other elements in bp_patching.
 	 */
 	smp_rmb();
 
-	if (likely(!bp_patching_in_progress))
+	if (likely(!bp_patching.nr_entries))
 		return 0;
 
-	if (user_mode(regs) || regs->ip != (unsigned long)bp_int3_addr)
+	if (user_mode(regs))
 		return 0;
 
-	/* set up the specified breakpoint handler */
-	regs->ip = (unsigned long) bp_int3_handler;
+	/*
+	 * Discount the sizeof(int3). See text_poke_bp_batch().
+	 */
+	ip = (void *) regs->ip - sizeof(int3);
+
+	/*
+	 * Skip the binary search if there is a single member in the vector.
+	 */
+	if (unlikely(bp_patching.nr_entries > 1)) {
+		tp = bsearch(ip, bp_patching.vec, bp_patching.nr_entries,
+			     sizeof(struct text_poke_loc),
+			     patch_cmp);
+		if (!tp)
+			return 0;
+	} else {
+		tp = bp_patching.vec;
+		if (tp->addr != ip)
+			return 0;
+	}
+
+	/* set up the specified breakpoint detour */
+	regs->ip = (unsigned long) tp->detour;
 
 	return 1;
 }
 NOKPROBE_SYMBOL(poke_int3_handler);
 
 /**
- * text_poke_bp() -- update instructions on live kernel on SMP
- * @addr:	address to patch
- * @opcode:	opcode of new instruction
- * @len:	length to copy
- * @handler:	address to jump to when the temporary breakpoint is hit
+ * text_poke_bp_batch() -- update instructions on live kernel on SMP
+ * @tp:			vector of instructions to patch
+ * @nr_entries:		number of entries in the vector
  *
  * Modify multi-byte instruction by using int3 breakpoint on SMP.
  * We completely avoid stop_machine() here, and achieve the
  * synchronization using int3 breakpoint.
  *
  * The way it is done:
- *	- add a int3 trap to the address that will be patched
+ * 	- For each entry in the vector:
+ *		- add a int3 trap to the address that will be patched
  *	- sync cores
- *	- update all but the first byte of the patched range
+ *	- For each entry in the vector:
+ *		- update all but the first byte of the patched range
  *	- sync cores
- *	- replace the first byte (int3) by the first byte of
- *	  replacing opcode
+ *	- For each entry in the vector:
+ *		- replace the first byte (int3) by the first byte of
+ *		  replacing opcode
  *	- sync cores
  */
-void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
 {
+	int patched_all_but_first = 0;
 	unsigned char int3 = 0xcc;
-
-	bp_int3_handler = handler;
-	bp_int3_addr = (u8 *)addr + sizeof(int3);
-	bp_patching_in_progress = true;
+	unsigned int i;
 
 	lockdep_assert_held(&text_mutex);
 
+	bp_patching.vec = tp;
+	bp_patching.nr_entries = nr_entries;
+
 	/*
 	 * Corresponding read barrier in int3 notifier for making sure the
-	 * in_progress and handler are correctly ordered wrt. patching.
+	 * nr_entries and handler are correctly ordered wrt. patching.
 	 */
 	smp_wmb();
 
-	text_poke(addr, &int3, sizeof(int3));
+	/*
+	 * First step: add a int3 trap to the address that will be patched.
+	 */
+	for (i = 0; i < nr_entries; i++)
+		text_poke(tp[i].addr, &int3, sizeof(int3));
 
 	on_each_cpu(do_sync_core, NULL, 1);
 
-	if (len - sizeof(int3) > 0) {
-		/* patch all but the first byte */
-		text_poke((char *)addr + sizeof(int3),
-			  (const char *) opcode + sizeof(int3),
-			  len - sizeof(int3));
+	/*
+	 * Second step: update all but the first byte of the patched range.
+	 */
+	for (i = 0; i < nr_entries; i++) {
+		if (tp[i].len - sizeof(int3) > 0) {
+			text_poke((char *)tp[i].addr + sizeof(int3),
+				  (const char *)tp[i].opcode + sizeof(int3),
+				  tp[i].len - sizeof(int3));
+			patched_all_but_first++;
+		}
+	}
+
+	if (patched_all_but_first) {
 		/*
 		 * According to Intel, this core syncing is very likely
 		 * not necessary and we'd be safe even without it. But
@@ -931,14 +984,47 @@ void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 		on_each_cpu(do_sync_core, NULL, 1);
 	}
 
-	/* patch the first byte */
-	text_poke(addr, opcode, sizeof(int3));
+	/*
+	 * Third step: replace the first byte (int3) by the first byte of
+	 * replacing opcode.
+	 */
+	for (i = 0; i < nr_entries; i++)
+		text_poke(tp[i].addr, tp[i].opcode, sizeof(int3));
 
 	on_each_cpu(do_sync_core, NULL, 1);
 	/*
 	 * sync_core() implies an smp_mb() and orders this store against
 	 * the writing of the new instruction.
 	 */
-	bp_patching_in_progress = false;
+	bp_patching.vec = NULL;
+	bp_patching.nr_entries = 0;
 }
 
+/**
+ * text_poke_bp() -- update instructions on live kernel on SMP
+ * @addr:	address to patch
+ * @opcode:	opcode of new instruction
+ * @len:	length to copy
+ * @handler:	address to jump to when the temporary breakpoint is hit
+ *
+ * Update a single instruction with the vector in the stack, avoiding
+ * dynamically allocated memory. This function should be used when it is
+ * not possible to allocate memory.
+ */
+void text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
+{
+	struct text_poke_loc tp = {
+		.detour = handler,
+		.addr = addr,
+		.len = len,
+	};
+
+	if (len > POKE_MAX_OPCODE_SIZE) {
+		WARN_ONCE(1, "len is larger than %d\n", POKE_MAX_OPCODE_SIZE);
+		return;
+	}
+
+	memcpy((void *)tp.opcode, opcode, len);
+
+	text_poke_bp_batch(&tp, 1);
+}
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index e631c358f7f4..044053235302 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -35,41 +35,43 @@ static void bug_at(unsigned char *ip, int line)
 	BUG();
 }
 
-static void __ref __jump_label_transform(struct jump_entry *entry,
-					 enum jump_label_type type,
-					 int init)
+static void __jump_label_set_jump_code(struct jump_entry *entry,
+				       enum jump_label_type type,
+				       union jump_code_union *code,
+				       int init)
 {
-	union jump_code_union jmp;
 	const unsigned char default_nop[] = { STATIC_KEY_INIT_NOP };
 	const unsigned char *ideal_nop = ideal_nops[NOP_ATOMIC5];
-	const void *expect, *code;
+	const void *expect;
 	int line;
 
-	jmp.jump = 0xe9;
-	jmp.offset = jump_entry_target(entry) -
-		     (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
+	code->jump = 0xe9;
+	code->offset = jump_entry_target(entry) -
+		       (jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
 
-	if (type == JUMP_LABEL_JMP) {
-		if (init) {
-			expect = default_nop; line = __LINE__;
-		} else {
-			expect = ideal_nop; line = __LINE__;
-		}
-
-		code = &jmp.code;
+	if (init) {
+		expect = default_nop; line = __LINE__;
+	} else if (type == JUMP_LABEL_JMP) {
+		expect = ideal_nop; line = __LINE__;
 	} else {
-		if (init) {
-			expect = default_nop; line = __LINE__;
-		} else {
-			expect = &jmp.code; line = __LINE__;
-		}
-
-		code = ideal_nop;
+		expect = code->code; line = __LINE__;
 	}
 
 	if (memcmp((void *)jump_entry_code(entry), expect, JUMP_LABEL_NOP_SIZE))
 		bug_at((void *)jump_entry_code(entry), line);
 
+	if (type == JUMP_LABEL_NOP)
+		memcpy(code, ideal_nop, JUMP_LABEL_NOP_SIZE);
+}
+
+static void __ref __jump_label_transform(struct jump_entry *entry,
+					 enum jump_label_type type,
+					 int init)
+{
+	union jump_code_union code;
+
+	__jump_label_set_jump_code(entry, type, &code, init);
+
 	/*
 	 * As long as only a single processor is running and the code is still
 	 * not marked as RO, text_poke_early() can be used; Checking that
@@ -82,12 +84,12 @@ static void __ref __jump_label_transform(struct jump_entry *entry,
 	 * always nop being the 'currently valid' instruction
 	 */
 	if (init || system_state == SYSTEM_BOOTING) {
-		text_poke_early((void *)jump_entry_code(entry), code,
+		text_poke_early((void *)jump_entry_code(entry), &code,
 				JUMP_LABEL_NOP_SIZE);
 		return;
 	}
 
-	text_poke_bp((void *)jump_entry_code(entry), code, JUMP_LABEL_NOP_SIZE,
+	text_poke_bp((void *)jump_entry_code(entry), &code, JUMP_LABEL_NOP_SIZE,
 		     (void *)jump_entry_code(entry) + JUMP_LABEL_NOP_SIZE);
 }
 
@@ -99,6 +101,75 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	mutex_unlock(&text_mutex);
 }
 
+#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
+static struct text_poke_loc tp_vec[TP_VEC_MAX];
+static int tp_vec_nr;
+
+bool arch_jump_label_transform_queue(struct jump_entry *entry,
+				     enum jump_label_type type)
+{
+	struct text_poke_loc *tp;
+	void *entry_code;
+
+	if (system_state == SYSTEM_BOOTING) {
+		/*
+		 * Fallback to the non-batching mode.
+		 */
+		arch_jump_label_transform(entry, type);
+		return true;
+	}
+
+	/*
+	 * No more space in the vector, tell upper layer to apply
+	 * the queue before continuing.
+	 */
+	if (tp_vec_nr == TP_VEC_MAX)
+		return false;
+
+	tp = &tp_vec[tp_vec_nr];
+
+	entry_code = (void *)jump_entry_code(entry);
+
+	/*
+	 * The INT3 handler will do a bsearch in the queue, so we need entries
+	 * to be sorted. We can survive an unsorted list by rejecting the entry,
+	 * forcing the generic jump_label code to apply the queue. Warning once,
+	 * to raise the attention to the case of an unsorted entry that is
+	 * better not happen, because, in the worst case we will perform in the
+	 * same way as we do without batching - with some more overhead.
+	 */
+	if (tp_vec_nr > 0) {
+		int prev = tp_vec_nr - 1;
+		struct text_poke_loc *prev_tp = &tp_vec[prev];
+
+		if (WARN_ON_ONCE(prev_tp->addr > entry_code))
+			return false;
+	}
+
+	__jump_label_set_jump_code(entry, type,
+				   (union jump_code_union *) &tp->opcode, 0);
+
+	tp->addr = entry_code;
+	tp->detour = entry_code + JUMP_LABEL_NOP_SIZE;
+	tp->len = JUMP_LABEL_NOP_SIZE;
+
+	tp_vec_nr++;
+
+	return true;
+}
+
+void arch_jump_label_transform_apply(void)
+{
+	if (!tp_vec_nr)
+		return;
+
+	mutex_lock(&text_mutex);
+	text_poke_bp_batch(tp_vec, tp_vec_nr);
+	mutex_unlock(&text_mutex);
+
+	tp_vec_nr = 0;
+}
+
 static enum {
 	JL_STATE_START,
 	JL_STATE_NO_UPDATE,
diff --git a/drivers/crypto/nx/nx-842-pseries.c b/drivers/crypto/nx/nx-842-pseries.c
index 5c4aa606208c..2de5e3672e42 100644
--- a/drivers/crypto/nx/nx-842-pseries.c
+++ b/drivers/crypto/nx/nx-842-pseries.c
@@ -856,7 +856,7 @@ static ssize_t nx842_##_name##_show(struct device *dev,		\
 	rcu_read_lock();						\
 	local_devdata = rcu_dereference(devdata);			\
 	if (local_devdata)						\
-		p = snprintf(buf, PAGE_SIZE, "%ld\n",			\
+		p = snprintf(buf, PAGE_SIZE, "%lld\n",			\
 		       atomic64_read(&local_devdata->counters->_name));	\
 	rcu_read_unlock();						\
 	return p;							\
@@ -909,7 +909,7 @@ static ssize_t nx842_timehist_show(struct device *dev,
 	}
 
 	for (i = 0; i < (NX842_HIST_SLOTS - 2); i++) {
-		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%ld\n",
+		bytes = snprintf(p, bytes_remain, "%u-%uus:\t%lld\n",
 			       i ? (2<<(i-1)) : 0, (2<<i)-1,
 			       atomic64_read(&times[i]));
 		bytes_remain -= bytes;
@@ -917,7 +917,7 @@ static ssize_t nx842_timehist_show(struct device *dev,
 	}
 	/* The last bucket holds everything over
 	 * 2<<(NX842_HIST_SLOTS - 2) us */
-	bytes = snprintf(p, bytes_remain, "%uus - :\t%ld\n",
+	bytes = snprintf(p, bytes_remain, "%uus - :\t%lld\n",
 			2<<(NX842_HIST_SLOTS - 2),
 			atomic64_read(&times[(NX842_HIST_SLOTS - 1)]));
 	p += bytes;
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 29f7b15c81d9..d020bb4d03d5 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -457,7 +457,7 @@ static int alloc_name(struct ib_device *ibdev, const char *name)
 	int rc;
 	int i;
 
-	lockdep_assert_held_exclusive(&devices_rwsem);
+	lockdep_assert_held_write(&devices_rwsem);
 	ida_init(&inuse);
 	xa_for_each (&devices, index, device) {
 		char buf[IB_DEVICE_NAME_MAX];
diff --git a/drivers/tty/tty_ldisc.c b/drivers/tty/tty_ldisc.c
index e38f104db174..fde8d4073e74 100644
--- a/drivers/tty/tty_ldisc.c
+++ b/drivers/tty/tty_ldisc.c
@@ -487,7 +487,7 @@ static int tty_ldisc_open(struct tty_struct *tty, struct tty_ldisc *ld)
 
 static void tty_ldisc_close(struct tty_struct *tty, struct tty_ldisc *ld)
 {
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	WARN_ON(!test_bit(TTY_LDISC_OPEN, &tty->flags));
 	clear_bit(TTY_LDISC_OPEN, &tty->flags);
 	if (ld->ops->close)
@@ -509,7 +509,7 @@ static int tty_ldisc_failto(struct tty_struct *tty, int ld)
 	struct tty_ldisc *disc = tty_ldisc_get(tty, ld);
 	int r;
 
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	if (IS_ERR(disc))
 		return PTR_ERR(disc);
 	tty->ldisc = disc;
@@ -633,7 +633,7 @@ EXPORT_SYMBOL_GPL(tty_set_ldisc);
  */
 static void tty_ldisc_kill(struct tty_struct *tty)
 {
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	if (!tty->ldisc)
 		return;
 	/*
@@ -681,7 +681,7 @@ int tty_ldisc_reinit(struct tty_struct *tty, int disc)
 	struct tty_ldisc *ld;
 	int retval;
 
-	lockdep_assert_held_exclusive(&tty->ldisc_sem);
+	lockdep_assert_held_write(&tty->ldisc_sem);
 	ld = tty_ldisc_get(tty, disc);
 	if (IS_ERR(ld)) {
 		BUG_ON(disc == N_TTY);
diff --git a/fs/dax.c b/fs/dax.c
index d2c90bf1969a..fe5e33810cd4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1187,7 +1187,7 @@ dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 	unsigned flags = 0;
 
 	if (iov_iter_rw(iter) == WRITE) {
-		lockdep_assert_held_exclusive(&inode->i_rwsem);
+		lockdep_assert_held_write(&inode->i_rwsem);
 		flags |= IOMAP_WRITE;
 	} else {
 		lockdep_assert_held(&inode->i_rwsem);
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index d7a15096fb3b..370f01d4450f 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -10,24 +10,24 @@
 #include <linux/types.h>
 
 typedef struct {
-	long long counter;
+	s64 counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-extern long long atomic64_read(const atomic64_t *v);
-extern void	 atomic64_set(atomic64_t *v, long long i);
+extern s64 atomic64_read(const atomic64_t *v);
+extern void atomic64_set(atomic64_t *v, s64 i);
 
 #define atomic64_set_release(v, i)	atomic64_set((v), (i))
 
 #define ATOMIC64_OP(op)							\
-extern void	 atomic64_##op(long long a, atomic64_t *v);
+extern void	 atomic64_##op(s64 a, atomic64_t *v);
 
 #define ATOMIC64_OP_RETURN(op)						\
-extern long long atomic64_##op##_return(long long a, atomic64_t *v);
+extern s64 atomic64_##op##_return(s64 a, atomic64_t *v);
 
 #define ATOMIC64_FETCH_OP(op)						\
-extern long long atomic64_fetch_##op(long long a, atomic64_t *v);
+extern s64 atomic64_fetch_##op(s64 a, atomic64_t *v);
 
 #define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
 
@@ -46,11 +46,11 @@ ATOMIC64_OPS(xor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-extern long long atomic64_dec_if_positive(atomic64_t *v);
+extern s64 atomic64_dec_if_positive(atomic64_t *v);
 #define atomic64_dec_if_positive atomic64_dec_if_positive
-extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
-extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+extern s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n);
+extern s64 atomic64_xchg(atomic64_t *v, s64 new);
+extern s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u);
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 3e113a1fa0f1..3526c0aee954 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -215,6 +215,9 @@ extern void arch_jump_label_transform(struct jump_entry *entry,
 				      enum jump_label_type type);
 extern void arch_jump_label_transform_static(struct jump_entry *entry,
 					     enum jump_label_type type);
+extern bool arch_jump_label_transform_queue(struct jump_entry *entry,
+					    enum jump_label_type type);
+extern void arch_jump_label_transform_apply(void);
 extern int jump_label_text_reserved(void *start, void *end);
 extern void static_key_slow_inc(struct static_key *key);
 extern void static_key_slow_dec(struct static_key *key);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index e8eef38b2213..57baa27f238c 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -203,11 +203,17 @@ struct lock_list {
 	struct lock_list		*parent;
 };
 
-/*
- * We record lock dependency chains, so that we can cache them:
+/**
+ * struct lock_chain - lock dependency chain record
+ *
+ * @irq_context: the same as irq_context in held_lock below
+ * @depth:       the number of held locks in this chain
+ * @base:        the index in chain_hlocks for this chain
+ * @entry:       the collided lock chains in lock_chain hash list
+ * @chain_key:   the hash key of this lock_chain
  */
 struct lock_chain {
-	/* see BUILD_BUG_ON()s in lookup_chain_cache() */
+	/* see BUILD_BUG_ON()s in add_chain_cache() */
 	unsigned int			irq_context :  2,
 					depth       :  6,
 					base	    : 24;
@@ -217,12 +223,8 @@ struct lock_chain {
 };
 
 #define MAX_LOCKDEP_KEYS_BITS		13
-/*
- * Subtract one because we offset hlock->class_idx by 1 in order
- * to make 0 mean no class. This avoids overflowing the class_idx
- * bitfield and hitting the BUG in hlock_class().
- */
-#define MAX_LOCKDEP_KEYS		((1UL << MAX_LOCKDEP_KEYS_BITS) - 1)
+#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
+#define INITIAL_CHAIN_KEY		-1
 
 struct held_lock {
 	/*
@@ -247,6 +249,11 @@ struct held_lock {
 	u64 				waittime_stamp;
 	u64				holdtime_stamp;
 #endif
+	/*
+	 * class_idx is zero-indexed; it points to the element in
+	 * lock_classes this held lock instance belongs to. class_idx is in
+	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
+	 */
 	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
 	/*
 	 * The lock-stack is unified in that the lock chains of interrupt
@@ -281,6 +288,8 @@ extern void lockdep_free_key_range(void *start, unsigned long size);
 extern asmlinkage void lockdep_sys_exit(void);
 extern void lockdep_set_selftest_task(struct task_struct *task);
 
+extern void lockdep_init_task(struct task_struct *task);
+
 extern void lockdep_off(void);
 extern void lockdep_on(void);
 
@@ -385,7 +394,7 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 		WARN_ON(debug_locks && !lockdep_is_held(l));	\
 	} while (0)
 
-#define lockdep_assert_held_exclusive(l)	do {			\
+#define lockdep_assert_held_write(l)	do {			\
 		WARN_ON(debug_locks && !lockdep_is_held_type(l, 0));	\
 	} while (0)
 
@@ -405,6 +414,10 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 
 #else /* !CONFIG_LOCKDEP */
 
+static inline void lockdep_init_task(struct task_struct *task)
+{
+}
+
 static inline void lockdep_off(void)
 {
 }
@@ -466,7 +479,7 @@ struct lockdep_map { };
 #define lockdep_is_held_type(l, r)		(1)
 
 #define lockdep_assert_held(l)			do { (void)(l); } while (0)
-#define lockdep_assert_held_exclusive(l)	do { (void)(l); } while (0)
+#define lockdep_assert_held_write(l)	do { (void)(l); } while (0)
 #define lockdep_assert_held_read(l)		do { (void)(l); } while (0)
 #define lockdep_assert_held_once(l)		do { (void)(l); } while (0)
 
@@ -497,7 +510,6 @@ enum xhlock_context_t {
 	{ .name = (_name), .key = (void *)(_key), }
 
 static inline void lockdep_invariant_state(bool force) {}
-static inline void lockdep_init_task(struct task_struct *task) {}
 static inline void lockdep_free_task(struct task_struct *task) {}
 
 #ifdef CONFIG_LOCK_STAT
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 2809b44cbbee..3998cdf9cd14 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -121,7 +121,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 	lock_release(&sem->rw_sem.dep_map, 1, ip);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	if (!read)
-		sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN;
+		atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
 #endif
 }
 
@@ -131,7 +131,7 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
 	lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	if (!read)
-		sem->rw_sem.owner = current;
+		atomic_long_set(&sem->rw_sem.owner, (long)current);
 #endif
 }
 
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 2ea18a3def04..e401358c4e7e 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -34,12 +34,13 @@
  */
 struct rw_semaphore {
 	atomic_long_t count;
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	/*
-	 * Write owner. Used as a speculative check to see
-	 * if the owner is running on the cpu.
+	 * Write owner or one of the read owners as well flags regarding
+	 * the current state of the rwsem. Can be used as a speculative
+	 * check to see if the write owner is running on the cpu.
 	 */
-	struct task_struct *owner;
+	atomic_long_t owner;
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	struct optimistic_spin_queue osq; /* spinner MCS lock */
 #endif
 	raw_spinlock_t wait_lock;
@@ -50,10 +51,10 @@ struct rw_semaphore {
 };
 
 /*
- * Setting bit 1 of the owner field but not bit 0 will indicate
+ * Setting all bits of the owner field except bit 0 will indicate
  * that the rwsem is writer-owned with an unknown owner.
  */
-#define RWSEM_OWNER_UNKNOWN	((struct task_struct *)-2L)
+#define RWSEM_OWNER_UNKNOWN	(-2L)
 
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
@@ -73,13 +74,14 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 #endif
 
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
+#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED
 #else
 #define __RWSEM_OPT_INIT(lockname)
 #endif
 
 #define __RWSEM_INITIALIZER(name)				\
 	{ __RWSEM_INIT_COUNT(name),				\
+	  .owner = ATOMIC_LONG_INIT(0),				\
 	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
 	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
 	  __RWSEM_OPT_INIT(name)				\
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index ad826d2a4557..26a2013ac39c 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -51,6 +51,11 @@ static inline void wake_q_init(struct wake_q_head *head)
 	head->lastp = &head->first;
 }
 
+static inline bool wake_q_empty(struct wake_q_head *head)
+{
+	return head->first == WAKE_Q_TAIL;
+}
+
 extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
 extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
diff --git a/include/linux/smp.h b/include/linux/smp.h
index bb8b451ab01f..6fc856c9eda5 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -180,29 +180,46 @@ static inline int get_boot_cpu_id(void)
 
 #endif /* !SMP */
 
-/*
- * smp_processor_id(): get the current CPU ID.
+/**
+ * raw_processor_id() - get the current (unstable) CPU id
  *
- * if DEBUG_PREEMPT is enabled then we check whether it is
- * used in a preemption-safe way. (smp_processor_id() is safe
- * if it's used in a preemption-off critical section, or in
- * a thread that is bound to the current CPU.)
- *
- * NOTE: raw_smp_processor_id() is for internal use only
- * (smp_processor_id() is the preferred variant), but in rare
- * instances it might also be used to turn off false positives
- * (i.e. smp_processor_id() use that the debugging code reports but
- * which use for some reason is legal). Don't use this to hack around
- * the warning message, as your code might not work under PREEMPT.
+ * For then you know what you are doing and need an unstable
+ * CPU id.
  */
+
+/**
+ * smp_processor_id() - get the current (stable) CPU id
+ *
+ * This is the normal accessor to the CPU id and should be used
+ * whenever possible.
+ *
+ * The CPU id is stable when:
+ *
+ *  - IRQs are disabled;
+ *  - preemption is disabled;
+ *  - the task is CPU affine.
+ *
+ * When CONFIG_DEBUG_PREEMPT; we verify these assumption and WARN
+ * when smp_processor_id() is used when the CPU id is not stable.
+ */
+
+/*
+ * Allow the architecture to differentiate between a stable and unstable read.
+ * For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a
+ * regular asm read for the stable.
+ */
+#ifndef __smp_processor_id
+#define __smp_processor_id(x) raw_smp_processor_id(x)
+#endif
+
 #ifdef CONFIG_DEBUG_PREEMPT
   extern unsigned int debug_smp_processor_id(void);
 # define smp_processor_id() debug_smp_processor_id()
 #else
-# define smp_processor_id() raw_smp_processor_id()
+# define smp_processor_id() __smp_processor_id()
 #endif
 
-#define get_cpu()		({ preempt_disable(); smp_processor_id(); })
+#define get_cpu()		({ preempt_disable(); __smp_processor_id(); })
 #define put_cpu()		preempt_enable()
 
 /*
diff --git a/include/linux/types.h b/include/linux/types.h
index 231114ae38f4..05030f608be3 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -174,7 +174,7 @@ typedef struct {
 
 #ifdef CONFIG_64BIT
 typedef struct {
-	long counter;
+	s64 counter;
 } atomic64_t;
 #endif
 
diff --git a/init/init_task.c b/init/init_task.c
index c70ef656d0f4..afa6ad795355 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -166,6 +166,8 @@ struct task_struct init_task
 	.softirqs_enabled = 1,
 #endif
 #ifdef CONFIG_LOCKDEP
+	.lockdep_depth = 0, /* no locks held yet */
+	.curr_chain_key = INITIAL_CHAIN_KEY,
 	.lockdep_recursion = 0,
 #endif
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
diff --git a/kernel/fork.c b/kernel/fork.c
index a83ef7243ccc..d18e343d4aab 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1952,9 +1952,6 @@ static __latent_entropy struct task_struct *copy_process(
 	p->pagefault_disabled = 0;
 
 #ifdef CONFIG_LOCKDEP
-	p->lockdep_depth = 0; /* no locks held yet */
-	p->curr_chain_key = 0;
-	p->lockdep_recursion = 0;
 	lockdep_init_task(p);
 #endif
 
diff --git a/kernel/futex.c b/kernel/futex.c
index 4b5b468c58b6..6d50728ef2e7 100644
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -470,6 +470,37 @@ enum futex_access {
 	FUTEX_WRITE
 };
 
+/**
+ * futex_setup_timer - set up the sleeping hrtimer.
+ * @time:	ptr to the given timeout value
+ * @timeout:	the hrtimer_sleeper structure to be set up
+ * @flags:	futex flags
+ * @range_ns:	optional range in ns
+ *
+ * Return: Initialized hrtimer_sleeper structure or NULL if no timeout
+ *	   value given
+ */
+static inline struct hrtimer_sleeper *
+futex_setup_timer(ktime_t *time, struct hrtimer_sleeper *timeout,
+		  int flags, u64 range_ns)
+{
+	if (!time)
+		return NULL;
+
+	hrtimer_init_on_stack(&timeout->timer, (flags & FLAGS_CLOCKRT) ?
+			      CLOCK_REALTIME : CLOCK_MONOTONIC,
+			      HRTIMER_MODE_ABS);
+	hrtimer_init_sleeper(timeout, current);
+
+	/*
+	 * If range_ns is 0, calling hrtimer_set_expires_range_ns() is
+	 * effectively the same as calling hrtimer_set_expires().
+	 */
+	hrtimer_set_expires_range_ns(&timeout->timer, *time, range_ns);
+
+	return timeout;
+}
+
 /**
  * get_futex_key() - Get parameters which are the keys for a futex
  * @uaddr:	virtual address of the futex
@@ -2679,7 +2710,7 @@ out:
 static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 		      ktime_t *abs_time, u32 bitset)
 {
-	struct hrtimer_sleeper timeout, *to = NULL;
+	struct hrtimer_sleeper timeout, *to;
 	struct restart_block *restart;
 	struct futex_hash_bucket *hb;
 	struct futex_q q = futex_q_init;
@@ -2689,17 +2720,8 @@ static int futex_wait(u32 __user *uaddr, unsigned int flags, u32 val,
 		return -EINVAL;
 	q.bitset = bitset;
 
-	if (abs_time) {
-		to = &timeout;
-
-		hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
-				      CLOCK_REALTIME : CLOCK_MONOTONIC,
-				      HRTIMER_MODE_ABS);
-		hrtimer_init_sleeper(to, current);
-		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
-	}
-
+	to = futex_setup_timer(abs_time, &timeout, flags,
+			       current->timer_slack_ns);
 retry:
 	/*
 	 * Prepare to wait on uaddr. On success, holds hb lock and increments
@@ -2779,7 +2801,7 @@ static long futex_wait_restart(struct restart_block *restart)
 static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 			 ktime_t *time, int trylock)
 {
-	struct hrtimer_sleeper timeout, *to = NULL;
+	struct hrtimer_sleeper timeout, *to;
 	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
@@ -2792,13 +2814,7 @@ static int futex_lock_pi(u32 __user *uaddr, unsigned int flags,
 	if (refill_pi_state_cache())
 		return -ENOMEM;
 
-	if (time) {
-		to = &timeout;
-		hrtimer_init_on_stack(&to->timer, CLOCK_REALTIME,
-				      HRTIMER_MODE_ABS);
-		hrtimer_init_sleeper(to, current);
-		hrtimer_set_expires(&to->timer, *time);
-	}
+	to = futex_setup_timer(time, &timeout, FLAGS_CLOCKRT, 0);
 
 retry:
 	ret = get_futex_key(uaddr, flags & FLAGS_SHARED, &q.key, FUTEX_WRITE);
@@ -3195,7 +3211,7 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 				 u32 val, ktime_t *abs_time, u32 bitset,
 				 u32 __user *uaddr2)
 {
-	struct hrtimer_sleeper timeout, *to = NULL;
+	struct hrtimer_sleeper timeout, *to;
 	struct futex_pi_state *pi_state = NULL;
 	struct rt_mutex_waiter rt_waiter;
 	struct futex_hash_bucket *hb;
@@ -3212,15 +3228,8 @@ static int futex_wait_requeue_pi(u32 __user *uaddr, unsigned int flags,
 	if (!bitset)
 		return -EINVAL;
 
-	if (abs_time) {
-		to = &timeout;
-		hrtimer_init_on_stack(&to->timer, (flags & FLAGS_CLOCKRT) ?
-				      CLOCK_REALTIME : CLOCK_MONOTONIC,
-				      HRTIMER_MODE_ABS);
-		hrtimer_init_sleeper(to, current);
-		hrtimer_set_expires_range_ns(&to->timer, *abs_time,
-					     current->timer_slack_ns);
-	}
+	to = futex_setup_timer(abs_time, &timeout, flags,
+			       current->timer_slack_ns);
 
 	/*
 	 * The waiter is allocated on our stack, manipulated by the requeue
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 0bfa10f4410c..df3008419a1d 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -37,12 +37,26 @@ static int jump_label_cmp(const void *a, const void *b)
 	const struct jump_entry *jea = a;
 	const struct jump_entry *jeb = b;
 
+	/*
+	 * Entrires are sorted by key.
+	 */
 	if (jump_entry_key(jea) < jump_entry_key(jeb))
 		return -1;
 
 	if (jump_entry_key(jea) > jump_entry_key(jeb))
 		return 1;
 
+	/*
+	 * In the batching mode, entries should also be sorted by the code
+	 * inside the already sorted list of entries, enabling a bsearch in
+	 * the vector.
+	 */
+	if (jump_entry_code(jea) < jump_entry_code(jeb))
+		return -1;
+
+	if (jump_entry_code(jea) > jump_entry_code(jeb))
+		return 1;
+
 	return 0;
 }
 
@@ -384,25 +398,55 @@ static enum jump_label_type jump_label_type(struct jump_entry *entry)
 	return enabled ^ branch;
 }
 
+static bool jump_label_can_update(struct jump_entry *entry, bool init)
+{
+	/*
+	 * Cannot update code that was in an init text area.
+	 */
+	if (!init && jump_entry_is_init(entry))
+		return false;
+
+	if (!kernel_text_address(jump_entry_code(entry))) {
+		WARN_ONCE(1, "can't patch jump_label at %pS", (void *)jump_entry_code(entry));
+		return false;
+	}
+
+	return true;
+}
+
+#ifndef HAVE_JUMP_LABEL_BATCH
 static void __jump_label_update(struct static_key *key,
 				struct jump_entry *entry,
 				struct jump_entry *stop,
 				bool init)
 {
 	for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
-		/*
-		 * An entry->code of 0 indicates an entry which has been
-		 * disabled because it was in an init text area.
-		 */
-		if (init || !jump_entry_is_init(entry)) {
-			if (kernel_text_address(jump_entry_code(entry)))
-				arch_jump_label_transform(entry, jump_label_type(entry));
-			else
-				WARN_ONCE(1, "can't patch jump_label at %pS",
-					  (void *)jump_entry_code(entry));
-		}
+		if (jump_label_can_update(entry, init))
+			arch_jump_label_transform(entry, jump_label_type(entry));
 	}
 }
+#else
+static void __jump_label_update(struct static_key *key,
+				struct jump_entry *entry,
+				struct jump_entry *stop,
+				bool init)
+{
+	for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
+
+		if (!jump_label_can_update(entry, init))
+			continue;
+
+		if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) {
+			/*
+			 * Queue is full: Apply the current queue and try again.
+			 */
+			arch_jump_label_transform_apply();
+			BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry)));
+		}
+	}
+	arch_jump_label_transform_apply();
+}
+#endif
 
 void __init jump_label_init(void)
 {
diff --git a/kernel/locking/Makefile b/kernel/locking/Makefile
index 6fe2f333aecb..45452facff3b 100644
--- a/kernel/locking/Makefile
+++ b/kernel/locking/Makefile
@@ -3,7 +3,7 @@
 # and is generally not a function of system call inputs.
 KCOV_INSTRUMENT		:= n
 
-obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o rwsem-xadd.o
+obj-y += mutex.o semaphore.o rwsem.o percpu-rwsem.o
 
 ifdef CONFIG_FUNCTION_TRACER
 CFLAGS_REMOVE_lockdep.o = $(CC_FLAGS_FTRACE)
diff --git a/kernel/locking/lock_events.h b/kernel/locking/lock_events.h
index 46b71af8eef2..8c7e7d25f09c 100644
--- a/kernel/locking/lock_events.h
+++ b/kernel/locking/lock_events.h
@@ -31,50 +31,13 @@ enum lock_events {
 DECLARE_PER_CPU(unsigned long, lockevents[lockevent_num]);
 
 /*
- * The purpose of the lock event counting subsystem is to provide a low
- * overhead way to record the number of specific locking events by using
- * percpu counters. It is the percpu sum that matters, not specifically
- * how many of them happens in each cpu.
- *
- * It is possible that the same percpu counter may be modified in both
- * the process and interrupt contexts. For architectures that perform
- * percpu operation with multiple instructions, it is possible to lose
- * count if a process context percpu update is interrupted in the middle
- * and the same counter is updated in the interrupt context. Therefore,
- * the generated percpu sum may not be precise. The error, if any, should
- * be small and insignificant.
- *
- * For those architectures that do multi-instruction percpu operation,
- * preemption in the middle and moving the task to another cpu may cause
- * a larger error in the count. Again, this will be few and far between.
- * Given the imprecise nature of the count and the possibility of resetting
- * the count and doing the measurement again, this is not really a big
- * problem.
- *
- * To get a better picture of what is happening under the hood, it is
- * suggested that a few measurements should be taken with the counts
- * reset in between to stamp out outliner because of these possible
- * error conditions.
- *
- * To minimize overhead, we use __this_cpu_*() in all cases except when
- * CONFIG_DEBUG_PREEMPT is defined. In this particular case, this_cpu_*()
- * will be used to avoid the appearance of unwanted BUG messages.
- */
-#ifdef CONFIG_DEBUG_PREEMPT
-#define lockevent_percpu_inc(x)		this_cpu_inc(x)
-#define lockevent_percpu_add(x, v)	this_cpu_add(x, v)
-#else
-#define lockevent_percpu_inc(x)		__this_cpu_inc(x)
-#define lockevent_percpu_add(x, v)	__this_cpu_add(x, v)
-#endif
-
-/*
- * Increment the PV qspinlock statistical counters
+ * Increment the statistical counters. use raw_cpu_inc() because of lower
+ * overhead and we don't care if we loose the occasional update.
  */
 static inline void __lockevent_inc(enum lock_events event, bool cond)
 {
 	if (cond)
-		lockevent_percpu_inc(lockevents[event]);
+		raw_cpu_inc(lockevents[event]);
 }
 
 #define lockevent_inc(ev)	  __lockevent_inc(LOCKEVENT_ ##ev, true)
@@ -82,7 +45,7 @@ static inline void __lockevent_inc(enum lock_events event, bool cond)
 
 static inline void __lockevent_add(enum lock_events event, int inc)
 {
-	lockevent_percpu_add(lockevents[event], inc);
+	raw_cpu_add(lockevents[event], inc);
 }
 
 #define lockevent_add(ev, c)	__lockevent_add(LOCKEVENT_ ##ev, c)
diff --git a/kernel/locking/lock_events_list.h b/kernel/locking/lock_events_list.h
index ad7668cfc9da..239039d0ce21 100644
--- a/kernel/locking/lock_events_list.h
+++ b/kernel/locking/lock_events_list.h
@@ -56,12 +56,16 @@ LOCK_EVENT(rwsem_sleep_reader)	/* # of reader sleeps			*/
 LOCK_EVENT(rwsem_sleep_writer)	/* # of writer sleeps			*/
 LOCK_EVENT(rwsem_wake_reader)	/* # of reader wakeups			*/
 LOCK_EVENT(rwsem_wake_writer)	/* # of writer wakeups			*/
-LOCK_EVENT(rwsem_opt_wlock)	/* # of write locks opt-spin acquired	*/
-LOCK_EVENT(rwsem_opt_fail)	/* # of failed opt-spinnings		*/
+LOCK_EVENT(rwsem_opt_rlock)	/* # of opt-acquired read locks		*/
+LOCK_EVENT(rwsem_opt_wlock)	/* # of opt-acquired write locks	*/
+LOCK_EVENT(rwsem_opt_fail)	/* # of failed optspins			*/
+LOCK_EVENT(rwsem_opt_nospin)	/* # of disabled optspins		*/
+LOCK_EVENT(rwsem_opt_norspin)	/* # of disabled reader-only optspins	*/
+LOCK_EVENT(rwsem_opt_rlock2)	/* # of opt-acquired 2ndary read locks	*/
 LOCK_EVENT(rwsem_rlock)		/* # of read locks acquired		*/
 LOCK_EVENT(rwsem_rlock_fast)	/* # of fast read locks acquired	*/
 LOCK_EVENT(rwsem_rlock_fail)	/* # of failed read lock acquisitions	*/
-LOCK_EVENT(rwsem_rtrylock)	/* # of read trylock calls		*/
+LOCK_EVENT(rwsem_rlock_handoff)	/* # of read lock handoffs		*/
 LOCK_EVENT(rwsem_wlock)		/* # of write locks acquired		*/
 LOCK_EVENT(rwsem_wlock_fail)	/* # of failed write lock acquisitions	*/
-LOCK_EVENT(rwsem_wtrylock)	/* # of write trylock calls		*/
+LOCK_EVENT(rwsem_wlock_handoff)	/* # of write lock handoffs		*/
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index c47788fa85f9..341f52117f88 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -151,17 +151,28 @@ unsigned long nr_lock_classes;
 static
 #endif
 struct lock_class lock_classes[MAX_LOCKDEP_KEYS];
+static DECLARE_BITMAP(lock_classes_in_use, MAX_LOCKDEP_KEYS);
 
 static inline struct lock_class *hlock_class(struct held_lock *hlock)
 {
-	if (!hlock->class_idx) {
+	unsigned int class_idx = hlock->class_idx;
+
+	/* Don't re-read hlock->class_idx, can't use READ_ONCE() on bitfield */
+	barrier();
+
+	if (!test_bit(class_idx, lock_classes_in_use)) {
 		/*
 		 * Someone passed in garbage, we give up.
 		 */
 		DEBUG_LOCKS_WARN_ON(1);
 		return NULL;
 	}
-	return lock_classes + hlock->class_idx - 1;
+
+	/*
+	 * At this point, if the passed hlock->class_idx is still garbage,
+	 * we just have to live with it
+	 */
+	return lock_classes + class_idx;
 }
 
 #ifdef CONFIG_LOCK_STAT
@@ -359,6 +370,13 @@ static inline u64 iterate_chain_key(u64 key, u32 idx)
 	return k0 | (u64)k1 << 32;
 }
 
+void lockdep_init_task(struct task_struct *task)
+{
+	task->lockdep_depth = 0; /* no locks held yet */
+	task->curr_chain_key = INITIAL_CHAIN_KEY;
+	task->lockdep_recursion = 0;
+}
+
 void lockdep_off(void)
 {
 	current->lockdep_recursion++;
@@ -419,13 +437,6 @@ static int verbose(struct lock_class *class)
 	return 0;
 }
 
-/*
- * Stack-trace: tightly packed array of stack backtrace
- * addresses. Protected by the graph_lock.
- */
-unsigned long nr_stack_trace_entries;
-static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
-
 static void print_lockdep_off(const char *bug_msg)
 {
 	printk(KERN_DEBUG "%s\n", bug_msg);
@@ -435,6 +446,15 @@ static void print_lockdep_off(const char *bug_msg)
 #endif
 }
 
+unsigned long nr_stack_trace_entries;
+
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+/*
+ * Stack-trace: tightly packed array of stack backtrace
+ * addresses. Protected by the graph_lock.
+ */
+static unsigned long stack_trace[MAX_STACK_TRACE_ENTRIES];
+
 static int save_trace(struct lock_trace *trace)
 {
 	unsigned long *entries = stack_trace + nr_stack_trace_entries;
@@ -457,6 +477,7 @@ static int save_trace(struct lock_trace *trace)
 
 	return 1;
 }
+#endif
 
 unsigned int nr_hardirq_chains;
 unsigned int nr_softirq_chains;
@@ -470,6 +491,7 @@ unsigned int max_lockdep_depth;
 DEFINE_PER_CPU(struct lockdep_stats, lockdep_stats);
 #endif
 
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 /*
  * Locking printouts:
  */
@@ -487,6 +509,7 @@ static const char *usage_str[] =
 #undef LOCKDEP_STATE
 	[LOCK_USED] = "INITIAL USE",
 };
+#endif
 
 const char * __get_key_name(struct lockdep_subclass_key *key, char *str)
 {
@@ -500,15 +523,26 @@ static inline unsigned long lock_flag(enum lock_usage_bit bit)
 
 static char get_usage_char(struct lock_class *class, enum lock_usage_bit bit)
 {
+	/*
+	 * The usage character defaults to '.' (i.e., irqs disabled and not in
+	 * irq context), which is the safest usage category.
+	 */
 	char c = '.';
 
-	if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
+	/*
+	 * The order of the following usage checks matters, which will
+	 * result in the outcome character as follows:
+	 *
+	 * - '+': irq is enabled and not in irq context
+	 * - '-': in irq context and irq is disabled
+	 * - '?': in irq context and irq is enabled
+	 */
+	if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK)) {
 		c = '+';
-	if (class->usage_mask & lock_flag(bit)) {
-		c = '-';
-		if (class->usage_mask & lock_flag(bit + LOCK_USAGE_DIR_MASK))
+		if (class->usage_mask & lock_flag(bit))
 			c = '?';
-	}
+	} else if (class->usage_mask & lock_flag(bit))
+		c = '-';
 
 	return c;
 }
@@ -572,19 +606,22 @@ static void print_lock(struct held_lock *hlock)
 	/*
 	 * We can be called locklessly through debug_show_all_locks() so be
 	 * extra careful, the hlock might have been released and cleared.
+	 *
+	 * If this indeed happens, lets pretend it does not hurt to continue
+	 * to print the lock unless the hlock class_idx does not point to a
+	 * registered class. The rationale here is: since we don't attempt
+	 * to distinguish whether we are in this situation, if it just
+	 * happened we can't count on class_idx to tell either.
 	 */
-	unsigned int class_idx = hlock->class_idx;
+	struct lock_class *lock = hlock_class(hlock);
 
-	/* Don't re-read hlock->class_idx, can't use READ_ONCE() on bitfields: */
-	barrier();
-
-	if (!class_idx || (class_idx - 1) >= MAX_LOCKDEP_KEYS) {
+	if (!lock) {
 		printk(KERN_CONT "<RELEASED>\n");
 		return;
 	}
 
 	printk(KERN_CONT "%p", hlock->instance);
-	print_lock_name(lock_classes + class_idx - 1);
+	print_lock_name(lock);
 	printk(KERN_CONT ", at: %pS\n", (void *)hlock->acquire_ip);
 }
 
@@ -732,7 +769,8 @@ look_up_lock_class(const struct lockdep_map *lock, unsigned int subclass)
 			 * Huh! same key, different name? Did someone trample
 			 * on some memory? We're most confused.
 			 */
-			WARN_ON_ONCE(class->name != lock->name);
+			WARN_ON_ONCE(class->name != lock->name &&
+				     lock->key != &__lockdep_no_validate__);
 			return class;
 		}
 	}
@@ -838,11 +876,11 @@ static u16 chain_hlocks[MAX_LOCKDEP_CHAIN_HLOCKS];
 static bool check_lock_chain_key(struct lock_chain *chain)
 {
 #ifdef CONFIG_PROVE_LOCKING
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 	int i;
 
 	for (i = chain->base; i < chain->base + chain->depth; i++)
-		chain_key = iterate_chain_key(chain_key, chain_hlocks[i] + 1);
+		chain_key = iterate_chain_key(chain_key, chain_hlocks[i]);
 	/*
 	 * The 'unsigned long long' casts avoid that a compiler warning
 	 * is reported when building tools/lib/lockdep.
@@ -1117,6 +1155,7 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force)
 		return NULL;
 	}
 	nr_lock_classes++;
+	__set_bit(class - lock_classes, lock_classes_in_use);
 	debug_atomic_inc(nr_unused_locks);
 	class->key = key;
 	class->name = lock->name;
@@ -1228,13 +1267,17 @@ static int add_lock_to_list(struct lock_class *this,
 #define CQ_MASK				(MAX_CIRCULAR_QUEUE_SIZE-1)
 
 /*
- * The circular_queue and helpers is used to implement the
- * breadth-first search(BFS)algorithem, by which we can build
- * the shortest path from the next lock to be acquired to the
- * previous held lock if there is a circular between them.
+ * The circular_queue and helpers are used to implement graph
+ * breadth-first search (BFS) algorithm, by which we can determine
+ * whether there is a path from a lock to another. In deadlock checks,
+ * a path from the next lock to be acquired to a previous held lock
+ * indicates that adding the <prev> -> <next> lock dependency will
+ * produce a circle in the graph. Breadth-first search instead of
+ * depth-first search is used in order to find the shortest (circular)
+ * path.
  */
 struct circular_queue {
-	unsigned long element[MAX_CIRCULAR_QUEUE_SIZE];
+	struct lock_list *element[MAX_CIRCULAR_QUEUE_SIZE];
 	unsigned int  front, rear;
 };
 
@@ -1260,7 +1303,7 @@ static inline int __cq_full(struct circular_queue *cq)
 	return ((cq->rear + 1) & CQ_MASK) == cq->front;
 }
 
-static inline int __cq_enqueue(struct circular_queue *cq, unsigned long elem)
+static inline int __cq_enqueue(struct circular_queue *cq, struct lock_list *elem)
 {
 	if (__cq_full(cq))
 		return -1;
@@ -1270,14 +1313,21 @@ static inline int __cq_enqueue(struct circular_queue *cq, unsigned long elem)
 	return 0;
 }
 
-static inline int __cq_dequeue(struct circular_queue *cq, unsigned long *elem)
+/*
+ * Dequeue an element from the circular_queue, return a lock_list if
+ * the queue is not empty, or NULL if otherwise.
+ */
+static inline struct lock_list * __cq_dequeue(struct circular_queue *cq)
 {
-	if (__cq_empty(cq))
-		return -1;
+	struct lock_list * lock;
 
-	*elem = cq->element[cq->front];
+	if (__cq_empty(cq))
+		return NULL;
+
+	lock = cq->element[cq->front];
 	cq->front = (cq->front + 1) & CQ_MASK;
-	return 0;
+
+	return lock;
 }
 
 static inline unsigned int  __cq_get_elem_count(struct circular_queue *cq)
@@ -1322,13 +1372,32 @@ static inline int get_lock_depth(struct lock_list *child)
 	return depth;
 }
 
+/*
+ * Return the forward or backward dependency list.
+ *
+ * @lock:   the lock_list to get its class's dependency list
+ * @offset: the offset to struct lock_class to determine whether it is
+ *          locks_after or locks_before
+ */
+static inline struct list_head *get_dep_list(struct lock_list *lock, int offset)
+{
+	void *lock_class = lock->class;
+
+	return lock_class + offset;
+}
+
+/*
+ * Forward- or backward-dependency search, used for both circular dependency
+ * checking and hardirq-unsafe/softirq-unsafe checking.
+ */
 static int __bfs(struct lock_list *source_entry,
 		 void *data,
 		 int (*match)(struct lock_list *entry, void *data),
 		 struct lock_list **target_entry,
-		 int forward)
+		 int offset)
 {
 	struct lock_list *entry;
+	struct lock_list *lock;
 	struct list_head *head;
 	struct circular_queue *cq = &lock_cq;
 	int ret = 1;
@@ -1339,31 +1408,21 @@ static int __bfs(struct lock_list *source_entry,
 		goto exit;
 	}
 
-	if (forward)
-		head = &source_entry->class->locks_after;
-	else
-		head = &source_entry->class->locks_before;
-
+	head = get_dep_list(source_entry, offset);
 	if (list_empty(head))
 		goto exit;
 
 	__cq_init(cq);
-	__cq_enqueue(cq, (unsigned long)source_entry);
+	__cq_enqueue(cq, source_entry);
 
-	while (!__cq_empty(cq)) {
-		struct lock_list *lock;
-
-		__cq_dequeue(cq, (unsigned long *)&lock);
+	while ((lock = __cq_dequeue(cq))) {
 
 		if (!lock->class) {
 			ret = -2;
 			goto exit;
 		}
 
-		if (forward)
-			head = &lock->class->locks_after;
-		else
-			head = &lock->class->locks_before;
+		head = get_dep_list(lock, offset);
 
 		DEBUG_LOCKS_WARN_ON(!irqs_disabled());
 
@@ -1377,7 +1436,7 @@ static int __bfs(struct lock_list *source_entry,
 					goto exit;
 				}
 
-				if (__cq_enqueue(cq, (unsigned long)entry)) {
+				if (__cq_enqueue(cq, entry)) {
 					ret = -1;
 					goto exit;
 				}
@@ -1396,7 +1455,8 @@ static inline int __bfs_forwards(struct lock_list *src_entry,
 			int (*match)(struct lock_list *entry, void *data),
 			struct lock_list **target_entry)
 {
-	return __bfs(src_entry, data, match, target_entry, 1);
+	return __bfs(src_entry, data, match, target_entry,
+		     offsetof(struct lock_class, locks_after));
 
 }
 
@@ -1405,16 +1465,11 @@ static inline int __bfs_backwards(struct lock_list *src_entry,
 			int (*match)(struct lock_list *entry, void *data),
 			struct lock_list **target_entry)
 {
-	return __bfs(src_entry, data, match, target_entry, 0);
+	return __bfs(src_entry, data, match, target_entry,
+		     offsetof(struct lock_class, locks_before));
 
 }
 
-/*
- * Recursive, forwards-direction lock-dependency checking, used for
- * both noncyclic checking and for hardirq-unsafe/softirq-unsafe
- * checking.
- */
-
 static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
 {
 	unsigned long *entries = stack_trace + trace->offset;
@@ -1426,16 +1481,15 @@ static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
  * Print a dependency chain entry (this is only done when a deadlock
  * has been detected):
  */
-static noinline int
+static noinline void
 print_circular_bug_entry(struct lock_list *target, int depth)
 {
 	if (debug_locks_silent)
-		return 0;
+		return;
 	printk("\n-> #%u", depth);
 	print_lock_name(target->class);
 	printk(KERN_CONT ":\n");
 	print_lock_trace(&target->trace, 6);
-	return 0;
 }
 
 static void
@@ -1492,7 +1546,7 @@ print_circular_lock_scenario(struct held_lock *src,
  * When a circular dependency is detected, print the
  * header first:
  */
-static noinline int
+static noinline void
 print_circular_bug_header(struct lock_list *entry, unsigned int depth,
 			struct held_lock *check_src,
 			struct held_lock *check_tgt)
@@ -1500,7 +1554,7 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
 	struct task_struct *curr = current;
 
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("======================================================\n");
@@ -1518,8 +1572,6 @@ print_circular_bug_header(struct lock_list *entry, unsigned int depth,
 	pr_warn("\nthe existing dependency chain (in reverse order) is:\n");
 
 	print_circular_bug_entry(entry, depth);
-
-	return 0;
 }
 
 static inline int class_equal(struct lock_list *entry, void *data)
@@ -1527,10 +1579,10 @@ static inline int class_equal(struct lock_list *entry, void *data)
 	return entry->class == data;
 }
 
-static noinline int print_circular_bug(struct lock_list *this,
-				       struct lock_list *target,
-				       struct held_lock *check_src,
-				       struct held_lock *check_tgt)
+static noinline void print_circular_bug(struct lock_list *this,
+					struct lock_list *target,
+					struct held_lock *check_src,
+					struct held_lock *check_tgt)
 {
 	struct task_struct *curr = current;
 	struct lock_list *parent;
@@ -1538,10 +1590,10 @@ static noinline int print_circular_bug(struct lock_list *this,
 	int depth;
 
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	if (!save_trace(&this->trace))
-		return 0;
+		return;
 
 	depth = get_lock_depth(target);
 
@@ -1563,21 +1615,17 @@ static noinline int print_circular_bug(struct lock_list *this,
 
 	printk("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
-static noinline int print_bfs_bug(int ret)
+static noinline void print_bfs_bug(int ret)
 {
 	if (!debug_locks_off_graph_unlock())
-		return 0;
+		return;
 
 	/*
 	 * Breadth-first-search failed, graph got corrupted?
 	 */
 	WARN(1, "lockdep bfs error:%d\n", ret);
-
-	return 0;
 }
 
 static int noop_count(struct lock_list *entry, void *data)
@@ -1640,36 +1688,95 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
 }
 
 /*
- * Prove that the dependency graph starting at <entry> can not
- * lead to <target>. Print an error and return 0 if it does.
+ * Check that the dependency graph starting at <src> can lead to
+ * <target> or not. Print an error and return 0 if it does.
  */
 static noinline int
-check_noncircular(struct lock_list *root, struct lock_class *target,
-		struct lock_list **target_entry)
+check_path(struct lock_class *target, struct lock_list *src_entry,
+	   struct lock_list **target_entry)
 {
-	int result;
+	int ret;
+
+	ret = __bfs_forwards(src_entry, (void *)target, class_equal,
+			     target_entry);
+
+	if (unlikely(ret < 0))
+		print_bfs_bug(ret);
+
+	return ret;
+}
+
+/*
+ * Prove that the dependency graph starting at <src> can not
+ * lead to <target>. If it can, there is a circle when adding
+ * <target> -> <src> dependency.
+ *
+ * Print an error and return 0 if it does.
+ */
+static noinline int
+check_noncircular(struct held_lock *src, struct held_lock *target,
+		  struct lock_trace *trace)
+{
+	int ret;
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list src_entry = {
+		.class = hlock_class(src),
+		.parent = NULL,
+	};
 
 	debug_atomic_inc(nr_cyclic_checks);
 
-	result = __bfs_forwards(root, target, class_equal, target_entry);
+	ret = check_path(hlock_class(target), &src_entry, &target_entry);
 
-	return result;
+	if (unlikely(!ret)) {
+		if (!trace->nr_entries) {
+			/*
+			 * If save_trace fails here, the printing might
+			 * trigger a WARN but because of the !nr_entries it
+			 * should not do bad things.
+			 */
+			save_trace(trace);
+		}
+
+		print_circular_bug(&src_entry, target_entry, src, target);
+	}
+
+	return ret;
 }
 
+#ifdef CONFIG_LOCKDEP_SMALL
+/*
+ * Check that the dependency graph starting at <src> can lead to
+ * <target> or not. If it can, <src> -> <target> dependency is already
+ * in the graph.
+ *
+ * Print an error and return 2 if it does or 1 if it does not.
+ */
 static noinline int
-check_redundant(struct lock_list *root, struct lock_class *target,
-		struct lock_list **target_entry)
+check_redundant(struct held_lock *src, struct held_lock *target)
 {
-	int result;
+	int ret;
+	struct lock_list *uninitialized_var(target_entry);
+	struct lock_list src_entry = {
+		.class = hlock_class(src),
+		.parent = NULL,
+	};
 
 	debug_atomic_inc(nr_redundant_checks);
 
-	result = __bfs_forwards(root, target, class_equal, target_entry);
+	ret = check_path(hlock_class(target), &src_entry, &target_entry);
 
-	return result;
+	if (!ret) {
+		debug_atomic_inc(nr_redundant);
+		ret = 2;
+	} else if (ret < 0)
+		ret = 0;
+
+	return ret;
 }
+#endif
 
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
+#ifdef CONFIG_TRACE_IRQFLAGS
 
 static inline int usage_accumulate(struct lock_list *entry, void *mask)
 {
@@ -1766,7 +1873,7 @@ static void print_lock_class_header(struct lock_class *class, int depth)
  */
 static void __used
 print_shortest_lock_dependencies(struct lock_list *leaf,
-				struct lock_list *root)
+				 struct lock_list *root)
 {
 	struct lock_list *entry = leaf;
 	int depth;
@@ -1788,8 +1895,6 @@ print_shortest_lock_dependencies(struct lock_list *leaf,
 		entry = get_lock_parent(entry);
 		depth--;
 	} while (entry && (depth >= 0));
-
-	return;
 }
 
 static void
@@ -1848,7 +1953,7 @@ print_irq_lock_scenario(struct lock_list *safe_entry,
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
-static int
+static void
 print_bad_irq_dependency(struct task_struct *curr,
 			 struct lock_list *prev_root,
 			 struct lock_list *next_root,
@@ -1861,7 +1966,7 @@ print_bad_irq_dependency(struct task_struct *curr,
 			 const char *irqclass)
 {
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("=====================================================\n");
@@ -1907,19 +2012,17 @@ print_bad_irq_dependency(struct task_struct *curr,
 
 	pr_warn("\nthe dependencies between %s-irq-safe lock and the holding lock:\n", irqclass);
 	if (!save_trace(&prev_root->trace))
-		return 0;
+		return;
 	print_shortest_lock_dependencies(backwards_entry, prev_root);
 
 	pr_warn("\nthe dependencies between the lock to be acquired");
 	pr_warn(" and %s-irq-unsafe lock:\n", irqclass);
 	if (!save_trace(&next_root->trace))
-		return 0;
+		return;
 	print_shortest_lock_dependencies(forwards_entry, next_root);
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static const char *state_names[] = {
@@ -2066,8 +2169,10 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 	this.class = hlock_class(prev);
 
 	ret = __bfs_backwards(&this, &usage_mask, usage_accumulate, NULL);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 
 	usage_mask &= LOCKF_USED_IN_IRQ_ALL;
 	if (!usage_mask)
@@ -2083,8 +2188,10 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 	that.class = hlock_class(next);
 
 	ret = find_usage_forwards(&that, forward_mask, &target_entry1);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 	if (ret == 1)
 		return ret;
 
@@ -2096,8 +2203,10 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 	backward_mask = original_mask(target_entry1->class->usage_mask);
 
 	ret = find_usage_backwards(&this, backward_mask, &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 	if (DEBUG_LOCKS_WARN_ON(ret == 1))
 		return 1;
 
@@ -2111,11 +2220,13 @@ static int check_irq_usage(struct task_struct *curr, struct held_lock *prev,
 	if (DEBUG_LOCKS_WARN_ON(ret == -1))
 		return 1;
 
-	return print_bad_irq_dependency(curr, &this, &that,
-			target_entry, target_entry1,
-			prev, next,
-			backward_bit, forward_bit,
-			state_name(backward_bit));
+	print_bad_irq_dependency(curr, &this, &that,
+				 target_entry, target_entry1,
+				 prev, next,
+				 backward_bit, forward_bit,
+				 state_name(backward_bit));
+
+	return 0;
 }
 
 static void inc_chains(void)
@@ -2143,11 +2254,10 @@ static inline void inc_chains(void)
 	nr_process_chains++;
 }
 
-#endif
+#endif /* CONFIG_TRACE_IRQFLAGS */
 
 static void
-print_deadlock_scenario(struct held_lock *nxt,
-			     struct held_lock *prv)
+print_deadlock_scenario(struct held_lock *nxt, struct held_lock *prv)
 {
 	struct lock_class *next = hlock_class(nxt);
 	struct lock_class *prev = hlock_class(prv);
@@ -2165,12 +2275,12 @@ print_deadlock_scenario(struct held_lock *nxt,
 	printk(" May be due to missing lock nesting notation\n\n");
 }
 
-static int
+static void
 print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 		   struct held_lock *next)
 {
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("============================================\n");
@@ -2189,8 +2299,6 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 /*
@@ -2202,8 +2310,7 @@ print_deadlock_bug(struct task_struct *curr, struct held_lock *prev,
  * Returns: 0 on deadlock detected, 1 on OK, 2 on recursive read
  */
 static int
-check_deadlock(struct task_struct *curr, struct held_lock *next,
-	       struct lockdep_map *next_instance, int read)
+check_deadlock(struct task_struct *curr, struct held_lock *next)
 {
 	struct held_lock *prev;
 	struct held_lock *nest = NULL;
@@ -2222,7 +2329,7 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
 		 * Allow read-after-read recursion of the same
 		 * lock class (i.e. read_lock(lock)+read_lock(lock)):
 		 */
-		if ((read == 2) && prev->read)
+		if ((next->read == 2) && prev->read)
 			return 2;
 
 		/*
@@ -2232,14 +2339,15 @@ check_deadlock(struct task_struct *curr, struct held_lock *next,
 		if (nest)
 			return 2;
 
-		return print_deadlock_bug(curr, prev, next);
+		print_deadlock_bug(curr, prev, next);
+		return 0;
 	}
 	return 1;
 }
 
 /*
  * There was a chain-cache miss, and we are about to add a new dependency
- * to a previous lock. We recursively validate the following rules:
+ * to a previous lock. We validate the following rules:
  *
  *  - would the adding of the <prev> -> <next> dependency create a
  *    circular dependency in the graph? [== circular deadlock]
@@ -2263,9 +2371,7 @@ static int
 check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	       struct held_lock *next, int distance, struct lock_trace *trace)
 {
-	struct lock_list *uninitialized_var(target_entry);
 	struct lock_list *entry;
-	struct lock_list this;
 	int ret;
 
 	if (!hlock_class(prev)->key || !hlock_class(next)->key) {
@@ -2289,28 +2395,16 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 	/*
 	 * Prove that the new <prev> -> <next> dependency would not
 	 * create a circular dependency in the graph. (We do this by
-	 * forward-recursing into the graph starting at <next>, and
-	 * checking whether we can reach <prev>.)
+	 * a breadth-first search into the graph starting at <next>,
+	 * and check whether we can reach <prev>.)
 	 *
-	 * We are using global variables to control the recursion, to
-	 * keep the stackframe size of the recursive functions low:
+	 * The search is limited by the size of the circular queue (i.e.,
+	 * MAX_CIRCULAR_QUEUE_SIZE) which keeps track of a breadth of nodes
+	 * in the graph whose neighbours are to be checked.
 	 */
-	this.class = hlock_class(next);
-	this.parent = NULL;
-	ret = check_noncircular(&this, hlock_class(prev), &target_entry);
-	if (unlikely(!ret)) {
-		if (!trace->nr_entries) {
-			/*
-			 * If save_trace fails here, the printing might
-			 * trigger a WARN but because of the !nr_entries it
-			 * should not do bad things.
-			 */
-			save_trace(trace);
-		}
-		return print_circular_bug(&this, target_entry, next, prev);
-	}
-	else if (unlikely(ret < 0))
-		return print_bfs_bug(ret);
+	ret = check_noncircular(next, prev, trace);
+	if (unlikely(ret <= 0))
+		return 0;
 
 	if (!check_irq_usage(curr, prev, next))
 		return 0;
@@ -2341,19 +2435,14 @@ check_prev_add(struct task_struct *curr, struct held_lock *prev,
 		}
 	}
 
+#ifdef CONFIG_LOCKDEP_SMALL
 	/*
 	 * Is the <prev> -> <next> link redundant?
 	 */
-	this.class = hlock_class(prev);
-	this.parent = NULL;
-	ret = check_redundant(&this, hlock_class(next), &target_entry);
-	if (!ret) {
-		debug_atomic_inc(nr_redundant);
-		return 2;
-	}
-	if (ret < 0)
-		return print_bfs_bug(ret);
-
+	ret = check_redundant(prev, next);
+	if (ret != 1)
+		return ret;
+#endif
 
 	if (!trace->nr_entries && !save_trace(trace))
 		return 0;
@@ -2505,12 +2594,13 @@ static void
 print_chain_keys_held_locks(struct task_struct *curr, struct held_lock *hlock_next)
 {
 	struct held_lock *hlock;
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 	int depth = curr->lockdep_depth;
-	int i;
+	int i = get_first_held_lock(curr, hlock_next);
 
-	printk("depth: %u\n", depth + 1);
-	for (i = get_first_held_lock(curr, hlock_next); i < depth; i++) {
+	printk("depth: %u (irq_context %u)\n", depth - i + 1,
+		hlock_next->irq_context);
+	for (; i < depth; i++) {
 		hlock = curr->held_locks + i;
 		chain_key = print_chain_key_iteration(hlock->class_idx, chain_key);
 
@@ -2524,13 +2614,13 @@ print_chain_keys_held_locks(struct task_struct *curr, struct held_lock *hlock_ne
 static void print_chain_keys_chain(struct lock_chain *chain)
 {
 	int i;
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 	int class_id;
 
 	printk("depth: %u\n", chain->depth);
 	for (i = 0; i < chain->depth; i++) {
 		class_id = chain_hlocks[chain->base + i];
-		chain_key = print_chain_key_iteration(class_id + 1, chain_key);
+		chain_key = print_chain_key_iteration(class_id, chain_key);
 
 		print_lock_name(lock_classes + class_id);
 		printk("\n");
@@ -2581,7 +2671,7 @@ static int check_no_collision(struct task_struct *curr,
 	}
 
 	for (j = 0; j < chain->depth - 1; j++, i++) {
-		id = curr->held_locks[i].class_idx - 1;
+		id = curr->held_locks[i].class_idx;
 
 		if (DEBUG_LOCKS_WARN_ON(chain_hlocks[chain->base + j] != id)) {
 			print_collision(curr, hlock, chain);
@@ -2664,7 +2754,7 @@ static inline int add_chain_cache(struct task_struct *curr,
 	if (likely(nr_chain_hlocks + chain->depth <= MAX_LOCKDEP_CHAIN_HLOCKS)) {
 		chain->base = nr_chain_hlocks;
 		for (j = 0; j < chain->depth - 1; j++, i++) {
-			int lock_id = curr->held_locks[i].class_idx - 1;
+			int lock_id = curr->held_locks[i].class_idx;
 			chain_hlocks[chain->base + j] = lock_id;
 		}
 		chain_hlocks[chain->base + j] = class - lock_classes;
@@ -2754,8 +2844,9 @@ cache_hit:
 	return 1;
 }
 
-static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
-		struct held_lock *hlock, int chain_head, u64 chain_key)
+static int validate_chain(struct task_struct *curr,
+			  struct held_lock *hlock,
+			  int chain_head, u64 chain_key)
 {
 	/*
 	 * Trylock needs to maintain the stack of held locks, but it
@@ -2776,12 +2867,18 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
 		 * - is softirq-safe, if this lock is hardirq-unsafe
 		 *
 		 * And check whether the new lock's dependency graph
-		 * could lead back to the previous lock.
+		 * could lead back to the previous lock:
 		 *
-		 * any of these scenarios could lead to a deadlock. If
-		 * All validations
+		 * - within the current held-lock stack
+		 * - across our accumulated lock dependency records
+		 *
+		 * any of these scenarios could lead to a deadlock.
 		 */
-		int ret = check_deadlock(curr, hlock, lock, hlock->read);
+		/*
+		 * The simple case: does the current hold the same lock
+		 * already?
+		 */
+		int ret = check_deadlock(curr, hlock);
 
 		if (!ret)
 			return 0;
@@ -2812,16 +2909,12 @@ static int validate_chain(struct task_struct *curr, struct lockdep_map *lock,
 }
 #else
 static inline int validate_chain(struct task_struct *curr,
-	       	struct lockdep_map *lock, struct held_lock *hlock,
-		int chain_head, u64 chain_key)
+				 struct held_lock *hlock,
+				 int chain_head, u64 chain_key)
 {
 	return 1;
 }
-
-static void print_lock_trace(struct lock_trace *trace, unsigned int spaces)
-{
-}
-#endif
+#endif /* CONFIG_PROVE_LOCKING */
 
 /*
  * We are building curr_chain_key incrementally, so double-check
@@ -2832,7 +2925,7 @@ static void check_chain_key(struct task_struct *curr)
 #ifdef CONFIG_DEBUG_LOCKDEP
 	struct held_lock *hlock, *prev_hlock = NULL;
 	unsigned int i;
-	u64 chain_key = 0;
+	u64 chain_key = INITIAL_CHAIN_KEY;
 
 	for (i = 0; i < curr->lockdep_depth; i++) {
 		hlock = curr->held_locks + i;
@@ -2848,15 +2941,17 @@ static void check_chain_key(struct task_struct *curr)
 				(unsigned long long)hlock->prev_chain_key);
 			return;
 		}
+
 		/*
-		 * Whoops ran out of static storage again?
+		 * hlock->class_idx can't go beyond MAX_LOCKDEP_KEYS, but is
+		 * it registered lock class index?
 		 */
-		if (DEBUG_LOCKS_WARN_ON(hlock->class_idx > MAX_LOCKDEP_KEYS))
+		if (DEBUG_LOCKS_WARN_ON(!test_bit(hlock->class_idx, lock_classes_in_use)))
 			return;
 
 		if (prev_hlock && (prev_hlock->irq_context !=
 							hlock->irq_context))
-			chain_key = 0;
+			chain_key = INITIAL_CHAIN_KEY;
 		chain_key = iterate_chain_key(chain_key, hlock->class_idx);
 		prev_hlock = hlock;
 	}
@@ -2874,14 +2969,11 @@ static void check_chain_key(struct task_struct *curr)
 #endif
 }
 
+#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
 static int mark_lock(struct task_struct *curr, struct held_lock *this,
 		     enum lock_usage_bit new_bit);
 
-#if defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING)
-
-
-static void
-print_usage_bug_scenario(struct held_lock *lock)
+static void print_usage_bug_scenario(struct held_lock *lock)
 {
 	struct lock_class *class = hlock_class(lock);
 
@@ -2898,12 +2990,12 @@ print_usage_bug_scenario(struct held_lock *lock)
 	printk("\n *** DEADLOCK ***\n\n");
 }
 
-static int
+static void
 print_usage_bug(struct task_struct *curr, struct held_lock *this,
 		enum lock_usage_bit prev_bit, enum lock_usage_bit new_bit)
 {
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("================================\n");
@@ -2933,8 +3025,6 @@ print_usage_bug(struct task_struct *curr, struct held_lock *this,
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 /*
@@ -2944,8 +3034,10 @@ static inline int
 valid_state(struct task_struct *curr, struct held_lock *this,
 	    enum lock_usage_bit new_bit, enum lock_usage_bit bad_bit)
 {
-	if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit)))
-		return print_usage_bug(curr, this, bad_bit, new_bit);
+	if (unlikely(hlock_class(this)->usage_mask & (1 << bad_bit))) {
+		print_usage_bug(curr, this, bad_bit, new_bit);
+		return 0;
+	}
 	return 1;
 }
 
@@ -2953,7 +3045,7 @@ valid_state(struct task_struct *curr, struct held_lock *this,
 /*
  * print irq inversion bug:
  */
-static int
+static void
 print_irq_inversion_bug(struct task_struct *curr,
 			struct lock_list *root, struct lock_list *other,
 			struct held_lock *this, int forwards,
@@ -2964,7 +3056,7 @@ print_irq_inversion_bug(struct task_struct *curr,
 	int depth;
 
 	if (!debug_locks_off_graph_unlock() || debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("========================================================\n");
@@ -3005,13 +3097,11 @@ print_irq_inversion_bug(struct task_struct *curr,
 
 	pr_warn("\nthe shortest dependencies between 2nd lock and 1st lock:\n");
 	if (!save_trace(&root->trace))
-		return 0;
+		return;
 	print_shortest_lock_dependencies(other, root);
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 /*
@@ -3029,13 +3119,16 @@ check_usage_forwards(struct task_struct *curr, struct held_lock *this,
 	root.parent = NULL;
 	root.class = hlock_class(this);
 	ret = find_usage_forwards(&root, lock_flag(bit), &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, &root, target_entry,
-					this, 1, irqclass);
+	print_irq_inversion_bug(curr, &root, target_entry,
+				this, 1, irqclass);
+	return 0;
 }
 
 /*
@@ -3053,13 +3146,16 @@ check_usage_backwards(struct task_struct *curr, struct held_lock *this,
 	root.parent = NULL;
 	root.class = hlock_class(this);
 	ret = find_usage_backwards(&root, lock_flag(bit), &target_entry);
-	if (ret < 0)
-		return print_bfs_bug(ret);
+	if (ret < 0) {
+		print_bfs_bug(ret);
+		return 0;
+	}
 	if (ret == 1)
 		return ret;
 
-	return print_irq_inversion_bug(curr, &root, target_entry,
-					this, 0, irqclass);
+	print_irq_inversion_bug(curr, &root, target_entry,
+				this, 0, irqclass);
+	return 0;
 }
 
 void print_irqtrace_events(struct task_struct *curr)
@@ -3142,7 +3238,7 @@ mark_lock_irq(struct task_struct *curr, struct held_lock *this,
 	 * Validate that the lock dependencies don't have conflicting usage
 	 * states.
 	 */
-	if ((!read || !dir || STRICT_READ_CHECKS) &&
+	if ((!read || STRICT_READ_CHECKS) &&
 			!usage(curr, this, excl_bit, state_name(new_bit & ~LOCK_USAGE_READ_MASK)))
 		return 0;
 
@@ -3367,8 +3463,12 @@ void trace_softirqs_off(unsigned long ip)
 		debug_atomic_inc(redundant_softirqs_off);
 }
 
-static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
+static int
+mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 {
+	if (!check)
+		goto lock_used;
+
 	/*
 	 * If non-trylock use in a hardirq or softirq context, then
 	 * mark the lock as used in these contexts:
@@ -3412,6 +3512,11 @@ static int mark_irqflags(struct task_struct *curr, struct held_lock *hlock)
 		}
 	}
 
+lock_used:
+	/* mark it as used: */
+	if (!mark_lock(curr, hlock, LOCK_USED))
+		return 0;
+
 	return 1;
 }
 
@@ -3443,35 +3548,6 @@ static int separate_irq_context(struct task_struct *curr,
 	return 0;
 }
 
-#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
-
-static inline
-int mark_lock_irq(struct task_struct *curr, struct held_lock *this,
-		enum lock_usage_bit new_bit)
-{
-	WARN_ON(1); /* Impossible innit? when we don't have TRACE_IRQFLAG */
-	return 1;
-}
-
-static inline int mark_irqflags(struct task_struct *curr,
-		struct held_lock *hlock)
-{
-	return 1;
-}
-
-static inline unsigned int task_irq_context(struct task_struct *task)
-{
-	return 0;
-}
-
-static inline int separate_irq_context(struct task_struct *curr,
-		struct held_lock *hlock)
-{
-	return 0;
-}
-
-#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
-
 /*
  * Mark a lock with a usage bit, and validate the state transition:
  */
@@ -3480,6 +3556,11 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 {
 	unsigned int new_mask = 1 << new_bit, ret = 1;
 
+	if (new_bit >= LOCK_USAGE_STATES) {
+		DEBUG_LOCKS_WARN_ON(1);
+		return 0;
+	}
+
 	/*
 	 * If already set then do not dirty the cacheline,
 	 * nor do any checks:
@@ -3503,25 +3584,13 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 		return 0;
 
 	switch (new_bit) {
-#define LOCKDEP_STATE(__STATE)			\
-	case LOCK_USED_IN_##__STATE:		\
-	case LOCK_USED_IN_##__STATE##_READ:	\
-	case LOCK_ENABLED_##__STATE:		\
-	case LOCK_ENABLED_##__STATE##_READ:
-#include "lockdep_states.h"
-#undef LOCKDEP_STATE
-		ret = mark_lock_irq(curr, this, new_bit);
-		if (!ret)
-			return 0;
-		break;
 	case LOCK_USED:
 		debug_atomic_dec(nr_unused_locks);
 		break;
 	default:
-		if (!debug_locks_off_graph_unlock())
+		ret = mark_lock_irq(curr, this, new_bit);
+		if (!ret)
 			return 0;
-		WARN_ON(1);
-		return 0;
 	}
 
 	graph_unlock();
@@ -3539,6 +3608,27 @@ static int mark_lock(struct task_struct *curr, struct held_lock *this,
 	return ret;
 }
 
+#else /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
+
+static inline int
+mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
+{
+	return 1;
+}
+
+static inline unsigned int task_irq_context(struct task_struct *task)
+{
+	return 0;
+}
+
+static inline int separate_irq_context(struct task_struct *curr,
+		struct held_lock *hlock)
+{
+	return 0;
+}
+
+#endif /* defined(CONFIG_TRACE_IRQFLAGS) && defined(CONFIG_PROVE_LOCKING) */
+
 /*
  * Initialize a lock instance's lock-class mapping info:
  */
@@ -3602,15 +3692,15 @@ EXPORT_SYMBOL_GPL(lockdep_init_map);
 struct lock_class_key __lockdep_no_validate__;
 EXPORT_SYMBOL_GPL(__lockdep_no_validate__);
 
-static int
+static void
 print_lock_nested_lock_not_held(struct task_struct *curr,
 				struct held_lock *hlock,
 				unsigned long ip)
 {
 	if (!debug_locks_off())
-		return 0;
+		return;
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("==================================\n");
@@ -3632,8 +3722,6 @@ print_lock_nested_lock_not_held(struct task_struct *curr,
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static int __lock_is_held(const struct lockdep_map *lock, int read);
@@ -3698,24 +3786,24 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (DEBUG_LOCKS_WARN_ON(depth >= MAX_LOCK_DEPTH))
 		return 0;
 
-	class_idx = class - lock_classes + 1;
+	class_idx = class - lock_classes;
 
 	if (depth) {
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
-			if (hlock->references) {
-				/*
-				 * Check: unsigned int references:12, overflow.
-				 */
-				if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
-					return 0;
+			if (!references)
+				references++;
 
+			if (!hlock->references)
 				hlock->references++;
-			} else {
-				hlock->references = 2;
-			}
 
-			return 1;
+			hlock->references += references;
+
+			/* Overflow */
+			if (DEBUG_LOCKS_WARN_ON(hlock->references < references))
+				return 0;
+
+			return 2;
 		}
 	}
 
@@ -3742,11 +3830,8 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 #endif
 	hlock->pin_count = pin_count;
 
-	if (check && !mark_irqflags(curr, hlock))
-		return 0;
-
-	/* mark it as used: */
-	if (!mark_lock(curr, hlock, LOCK_USED))
+	/* Initialize the lock usage bit */
+	if (!mark_usage(curr, hlock, check))
 		return 0;
 
 	/*
@@ -3760,9 +3845,9 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	 * the hash, not class->key.
 	 */
 	/*
-	 * Whoops, we did it again.. ran straight out of our static allocation.
+	 * Whoops, we did it again.. class_idx is invalid.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(class_idx > MAX_LOCKDEP_KEYS))
+	if (DEBUG_LOCKS_WARN_ON(!test_bit(class_idx, lock_classes_in_use)))
 		return 0;
 
 	chain_key = curr->curr_chain_key;
@@ -3770,27 +3855,29 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 		/*
 		 * How can we have a chain hash when we ain't got no keys?!
 		 */
-		if (DEBUG_LOCKS_WARN_ON(chain_key != 0))
+		if (DEBUG_LOCKS_WARN_ON(chain_key != INITIAL_CHAIN_KEY))
 			return 0;
 		chain_head = 1;
 	}
 
 	hlock->prev_chain_key = chain_key;
 	if (separate_irq_context(curr, hlock)) {
-		chain_key = 0;
+		chain_key = INITIAL_CHAIN_KEY;
 		chain_head = 1;
 	}
 	chain_key = iterate_chain_key(chain_key, class_idx);
 
-	if (nest_lock && !__lock_is_held(nest_lock, -1))
-		return print_lock_nested_lock_not_held(curr, hlock, ip);
+	if (nest_lock && !__lock_is_held(nest_lock, -1)) {
+		print_lock_nested_lock_not_held(curr, hlock, ip);
+		return 0;
+	}
 
 	if (!debug_locks_silent) {
 		WARN_ON_ONCE(depth && !hlock_class(hlock - 1)->key);
 		WARN_ON_ONCE(!hlock_class(hlock)->key);
 	}
 
-	if (!validate_chain(curr, lock, hlock, chain_head, chain_key))
+	if (!validate_chain(curr, hlock, chain_head, chain_key))
 		return 0;
 
 	curr->curr_chain_key = chain_key;
@@ -3819,14 +3906,14 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	return 1;
 }
 
-static int
-print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
-			   unsigned long ip)
+static void print_unlock_imbalance_bug(struct task_struct *curr,
+				       struct lockdep_map *lock,
+				       unsigned long ip)
 {
 	if (!debug_locks_off())
-		return 0;
+		return;
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("=====================================\n");
@@ -3844,8 +3931,6 @@ print_unlock_imbalance_bug(struct task_struct *curr, struct lockdep_map *lock,
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static int match_held_lock(const struct held_lock *hlock,
@@ -3877,7 +3962,7 @@ static int match_held_lock(const struct held_lock *hlock,
 		if (DEBUG_LOCKS_WARN_ON(!hlock->nest_lock))
 			return 0;
 
-		if (hlock->class_idx == class - lock_classes + 1)
+		if (hlock->class_idx == class - lock_classes)
 			return 1;
 	}
 
@@ -3921,22 +4006,33 @@ out:
 }
 
 static int reacquire_held_locks(struct task_struct *curr, unsigned int depth,
-			      int idx)
+				int idx, unsigned int *merged)
 {
 	struct held_lock *hlock;
+	int first_idx = idx;
 
 	if (DEBUG_LOCKS_WARN_ON(!irqs_disabled()))
 		return 0;
 
 	for (hlock = curr->held_locks + idx; idx < depth; idx++, hlock++) {
-		if (!__lock_acquire(hlock->instance,
+		switch (__lock_acquire(hlock->instance,
 				    hlock_class(hlock)->subclass,
 				    hlock->trylock,
 				    hlock->read, hlock->check,
 				    hlock->hardirqs_off,
 				    hlock->nest_lock, hlock->acquire_ip,
-				    hlock->references, hlock->pin_count))
+				    hlock->references, hlock->pin_count)) {
+		case 0:
 			return 1;
+		case 1:
+			break;
+		case 2:
+			*merged += (idx == first_idx);
+			break;
+		default:
+			WARN_ON(1);
+			return 0;
+		}
 	}
 	return 0;
 }
@@ -3947,9 +4043,9 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 		 unsigned long ip)
 {
 	struct task_struct *curr = current;
+	unsigned int depth, merged = 0;
 	struct held_lock *hlock;
 	struct lock_class *class;
-	unsigned int depth;
 	int i;
 
 	if (unlikely(!debug_locks))
@@ -3964,24 +4060,26 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 		return 0;
 
 	hlock = find_held_lock(curr, lock, depth, &i);
-	if (!hlock)
-		return print_unlock_imbalance_bug(curr, lock, ip);
+	if (!hlock) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	lockdep_init_map(lock, name, key, 0);
 	class = register_lock_class(lock, subclass, 0);
-	hlock->class_idx = class - lock_classes + 1;
+	hlock->class_idx = class - lock_classes;
 
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
 
-	if (reacquire_held_locks(curr, depth, i))
+	if (reacquire_held_locks(curr, depth, i, &merged))
 		return 0;
 
 	/*
 	 * I took it apart and put it back together again, except now I have
 	 * these 'spare' parts.. where shall I put them.
 	 */
-	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
+	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - merged))
 		return 0;
 	return 1;
 }
@@ -3989,8 +4087,8 @@ __lock_set_class(struct lockdep_map *lock, const char *name,
 static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
+	unsigned int depth, merged = 0;
 	struct held_lock *hlock;
-	unsigned int depth;
 	int i;
 
 	if (unlikely(!debug_locks))
@@ -4005,8 +4103,10 @@ static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 		return 0;
 
 	hlock = find_held_lock(curr, lock, depth, &i);
-	if (!hlock)
-		return print_unlock_imbalance_bug(curr, lock, ip);
+	if (!hlock) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	curr->lockdep_depth = i;
 	curr->curr_chain_key = hlock->prev_chain_key;
@@ -4015,7 +4115,11 @@ static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 	hlock->read = 1;
 	hlock->acquire_ip = ip;
 
-	if (reacquire_held_locks(curr, depth, i))
+	if (reacquire_held_locks(curr, depth, i, &merged))
+		return 0;
+
+	/* Merging can't happen with unchanged classes.. */
+	if (DEBUG_LOCKS_WARN_ON(merged))
 		return 0;
 
 	/*
@@ -4024,6 +4128,7 @@ static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
 	 */
 	if (DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth))
 		return 0;
+
 	return 1;
 }
 
@@ -4035,11 +4140,11 @@ static int __lock_downgrade(struct lockdep_map *lock, unsigned long ip)
  * @nested is an hysterical artifact, needs a tree wide cleanup.
  */
 static int
-__lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
+__lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	struct task_struct *curr = current;
+	unsigned int depth, merged = 1;
 	struct held_lock *hlock;
-	unsigned int depth;
 	int i;
 
 	if (unlikely(!debug_locks))
@@ -4050,16 +4155,20 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 	 * So we're all set to release this lock.. wait what lock? We don't
 	 * own any locks, you've been drinking again?
 	 */
-	if (DEBUG_LOCKS_WARN_ON(depth <= 0))
-		 return print_unlock_imbalance_bug(curr, lock, ip);
+	if (depth <= 0) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	/*
 	 * Check whether the lock exists in the current stack
 	 * of held locks:
 	 */
 	hlock = find_held_lock(curr, lock, depth, &i);
-	if (!hlock)
-		return print_unlock_imbalance_bug(curr, lock, ip);
+	if (!hlock) {
+		print_unlock_imbalance_bug(curr, lock, ip);
+		return 0;
+	}
 
 	if (hlock->instance == lock)
 		lock_release_holdtime(hlock);
@@ -4094,14 +4203,15 @@ __lock_release(struct lockdep_map *lock, int nested, unsigned long ip)
 	if (i == depth-1)
 		return 1;
 
-	if (reacquire_held_locks(curr, depth, i + 1))
+	if (reacquire_held_locks(curr, depth, i + 1, &merged))
 		return 0;
 
 	/*
 	 * We had N bottles of beer on the wall, we drank one, but now
 	 * there's not N-1 bottles of beer left on the wall...
+	 * Pouring two of the bottles together is acceptable.
 	 */
-	DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth-1);
+	DEBUG_LOCKS_WARN_ON(curr->lockdep_depth != depth - merged);
 
 	/*
 	 * Since reacquire_held_locks() would have called check_chain_key()
@@ -4319,7 +4429,7 @@ void lock_release(struct lockdep_map *lock, int nested,
 	check_flags(flags);
 	current->lockdep_recursion = 1;
 	trace_lock_release(lock, ip);
-	if (__lock_release(lock, nested, ip))
+	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
@@ -4402,14 +4512,14 @@ void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie cookie)
 EXPORT_SYMBOL_GPL(lock_unpin_lock);
 
 #ifdef CONFIG_LOCK_STAT
-static int
-print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
-			   unsigned long ip)
+static void print_lock_contention_bug(struct task_struct *curr,
+				      struct lockdep_map *lock,
+				      unsigned long ip)
 {
 	if (!debug_locks_off())
-		return 0;
+		return;
 	if (debug_locks_silent)
-		return 0;
+		return;
 
 	pr_warn("\n");
 	pr_warn("=================================\n");
@@ -4427,8 +4537,6 @@ print_lock_contention_bug(struct task_struct *curr, struct lockdep_map *lock,
 
 	pr_warn("\nstack backtrace:\n");
 	dump_stack();
-
-	return 0;
 }
 
 static void
@@ -4573,9 +4681,7 @@ void lockdep_reset(void)
 	int i;
 
 	raw_local_irq_save(flags);
-	current->curr_chain_key = 0;
-	current->lockdep_depth = 0;
-	current->lockdep_recursion = 0;
+	lockdep_init_task(current);
 	memset(current->held_locks, 0, MAX_LOCK_DEPTH*sizeof(struct held_lock));
 	nr_hardirq_chains = 0;
 	nr_softirq_chains = 0;
@@ -4615,9 +4721,9 @@ static void remove_class_from_lock_chain(struct pending_free *pf,
 	return;
 
 recalc:
-	chain_key = 0;
+	chain_key = INITIAL_CHAIN_KEY;
 	for (i = chain->base; i < chain->base + chain->depth; i++)
-		chain_key = iterate_chain_key(chain_key, chain_hlocks[i] + 1);
+		chain_key = iterate_chain_key(chain_key, chain_hlocks[i]);
 	if (chain->depth && chain->chain_key == chain_key)
 		return;
 	/* Overwrite the chain key for concurrent RCU readers. */
@@ -4691,6 +4797,7 @@ static void zap_class(struct pending_free *pf, struct lock_class *class)
 		WRITE_ONCE(class->key, NULL);
 		WRITE_ONCE(class->name, NULL);
 		nr_lock_classes--;
+		__clear_bit(class - lock_classes, lock_classes_in_use);
 	} else {
 		WARN_ONCE(true, "%s() failed for class %s\n", __func__,
 			  class->name);
@@ -5036,6 +5143,7 @@ void __init lockdep_init(void)
 
 	printk(" memory used by lock dependency info: %zu kB\n",
 	       (sizeof(lock_classes) +
+		sizeof(lock_classes_in_use) +
 		sizeof(classhash_table) +
 		sizeof(list_entries) +
 		sizeof(list_entries_in_use) +
diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h
index 150ec3f0c5b5..cc83568d5012 100644
--- a/kernel/locking/lockdep_internals.h
+++ b/kernel/locking/lockdep_internals.h
@@ -131,7 +131,6 @@ extern unsigned int nr_hardirq_chains;
 extern unsigned int nr_softirq_chains;
 extern unsigned int nr_process_chains;
 extern unsigned int max_lockdep_depth;
-extern unsigned int max_recursion_depth;
 
 extern unsigned int max_bfs_queue_depth;
 
@@ -160,25 +159,22 @@ lockdep_count_backward_deps(struct lock_class *class)
  * and we want to avoid too much cache bouncing.
  */
 struct lockdep_stats {
-	int	chain_lookup_hits;
-	int	chain_lookup_misses;
-	int	hardirqs_on_events;
-	int	hardirqs_off_events;
-	int	redundant_hardirqs_on;
-	int	redundant_hardirqs_off;
-	int	softirqs_on_events;
-	int	softirqs_off_events;
-	int	redundant_softirqs_on;
-	int	redundant_softirqs_off;
-	int	nr_unused_locks;
-	int	nr_redundant_checks;
-	int	nr_redundant;
-	int	nr_cyclic_checks;
-	int	nr_cyclic_check_recursions;
-	int	nr_find_usage_forwards_checks;
-	int	nr_find_usage_forwards_recursions;
-	int	nr_find_usage_backwards_checks;
-	int	nr_find_usage_backwards_recursions;
+	unsigned long  chain_lookup_hits;
+	unsigned int   chain_lookup_misses;
+	unsigned long  hardirqs_on_events;
+	unsigned long  hardirqs_off_events;
+	unsigned long  redundant_hardirqs_on;
+	unsigned long  redundant_hardirqs_off;
+	unsigned long  softirqs_on_events;
+	unsigned long  softirqs_off_events;
+	unsigned long  redundant_softirqs_on;
+	unsigned long  redundant_softirqs_off;
+	int            nr_unused_locks;
+	unsigned int   nr_redundant_checks;
+	unsigned int   nr_redundant;
+	unsigned int   nr_cyclic_checks;
+	unsigned int   nr_find_usage_forwards_checks;
+	unsigned int   nr_find_usage_backwards_checks;
 
 	/*
 	 * Per lock class locking operation stat counts
diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
deleted file mode 100644
index 0b1f77957240..000000000000
--- a/kernel/locking/rwsem-xadd.c
+++ /dev/null
@@ -1,745 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* rwsem.c: R/W semaphores: contention handling functions
- *
- * Written by David Howells (dhowells@redhat.com).
- * Derived from arch/i386/kernel/semaphore.c
- *
- * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
- * and Michel Lespinasse <walken@google.com>
- *
- * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
- * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
- */
-#include <linux/rwsem.h>
-#include <linux/init.h>
-#include <linux/export.h>
-#include <linux/sched/signal.h>
-#include <linux/sched/rt.h>
-#include <linux/sched/wake_q.h>
-#include <linux/sched/debug.h>
-#include <linux/osq_lock.h>
-
-#include "rwsem.h"
-
-/*
- * Guide to the rw_semaphore's count field for common values.
- * (32-bit case illustrated, similar for 64-bit)
- *
- * 0x0000000X	(1) X readers active or attempting lock, no writer waiting
- *		    X = #active_readers + #readers attempting to lock
- *		    (X*ACTIVE_BIAS)
- *
- * 0x00000000	rwsem is unlocked, and no one is waiting for the lock or
- *		attempting to read lock or write lock.
- *
- * 0xffff000X	(1) X readers active or attempting lock, with waiters for lock
- *		    X = #active readers + # readers attempting lock
- *		    (X*ACTIVE_BIAS + WAITING_BIAS)
- *		(2) 1 writer attempting lock, no waiters for lock
- *		    X-1 = #active readers + #readers attempting lock
- *		    ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
- *		(3) 1 writer active, no waiters for lock
- *		    X-1 = #active readers + #readers attempting lock
- *		    ((X-1)*ACTIVE_BIAS + ACTIVE_WRITE_BIAS)
- *
- * 0xffff0001	(1) 1 reader active or attempting lock, waiters for lock
- *		    (WAITING_BIAS + ACTIVE_BIAS)
- *		(2) 1 writer active or attempting lock, no waiters for lock
- *		    (ACTIVE_WRITE_BIAS)
- *
- * 0xffff0000	(1) There are writers or readers queued but none active
- *		    or in the process of attempting lock.
- *		    (WAITING_BIAS)
- *		Note: writer can attempt to steal lock for this count by adding
- *		ACTIVE_WRITE_BIAS in cmpxchg and checking the old count
- *
- * 0xfffe0001	(1) 1 writer active, or attempting lock. Waiters on queue.
- *		    (ACTIVE_WRITE_BIAS + WAITING_BIAS)
- *
- * Note: Readers attempt to lock by adding ACTIVE_BIAS in down_read and checking
- *	 the count becomes more than 0 for successful lock acquisition,
- *	 i.e. the case where there are only readers or nobody has lock.
- *	 (1st and 2nd case above).
- *
- *	 Writers attempt to lock by adding ACTIVE_WRITE_BIAS in down_write and
- *	 checking the count becomes ACTIVE_WRITE_BIAS for successful lock
- *	 acquisition (i.e. nobody else has lock or attempts lock).  If
- *	 unsuccessful, in rwsem_down_write_failed, we'll check to see if there
- *	 are only waiters but none active (5th case above), and attempt to
- *	 steal the lock.
- *
- */
-
-/*
- * Initialize an rwsem:
- */
-void __init_rwsem(struct rw_semaphore *sem, const char *name,
-		  struct lock_class_key *key)
-{
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	/*
-	 * Make sure we are not reinitializing a held semaphore:
-	 */
-	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
-	lockdep_init_map(&sem->dep_map, name, key, 0);
-#endif
-	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
-	raw_spin_lock_init(&sem->wait_lock);
-	INIT_LIST_HEAD(&sem->wait_list);
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-	sem->owner = NULL;
-	osq_lock_init(&sem->osq);
-#endif
-}
-
-EXPORT_SYMBOL(__init_rwsem);
-
-enum rwsem_waiter_type {
-	RWSEM_WAITING_FOR_WRITE,
-	RWSEM_WAITING_FOR_READ
-};
-
-struct rwsem_waiter {
-	struct list_head list;
-	struct task_struct *task;
-	enum rwsem_waiter_type type;
-};
-
-enum rwsem_wake_type {
-	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
-	RWSEM_WAKE_READERS,	/* Wake readers only */
-	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
-};
-
-/*
- * handle the lock release when processes blocked on it that can now run
- * - if we come here from up_xxxx(), then:
- *   - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
- *   - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
- * - there must be someone on the queue
- * - the wait_lock must be held by the caller
- * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
- *   to actually wakeup the blocked task(s) and drop the reference count,
- *   preferably when the wait_lock is released
- * - woken process blocks are discarded from the list after having task zeroed
- * - writers are only marked woken if downgrading is false
- */
-static void __rwsem_mark_wake(struct rw_semaphore *sem,
-			      enum rwsem_wake_type wake_type,
-			      struct wake_q_head *wake_q)
-{
-	struct rwsem_waiter *waiter, *tmp;
-	long oldcount, woken = 0, adjustment = 0;
-	struct list_head wlist;
-
-	/*
-	 * Take a peek at the queue head waiter such that we can determine
-	 * the wakeup(s) to perform.
-	 */
-	waiter = list_first_entry(&sem->wait_list, struct rwsem_waiter, list);
-
-	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
-		if (wake_type == RWSEM_WAKE_ANY) {
-			/*
-			 * Mark writer at the front of the queue for wakeup.
-			 * Until the task is actually later awoken later by
-			 * the caller, other writers are able to steal it.
-			 * Readers, on the other hand, will block as they
-			 * will notice the queued writer.
-			 */
-			wake_q_add(wake_q, waiter->task);
-			lockevent_inc(rwsem_wake_writer);
-		}
-
-		return;
-	}
-
-	/*
-	 * Writers might steal the lock before we grant it to the next reader.
-	 * We prefer to do the first reader grant before counting readers
-	 * so we can bail out early if a writer stole the lock.
-	 */
-	if (wake_type != RWSEM_WAKE_READ_OWNED) {
-		adjustment = RWSEM_ACTIVE_READ_BIAS;
- try_reader_grant:
-		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
-		if (unlikely(oldcount < RWSEM_WAITING_BIAS)) {
-			/*
-			 * If the count is still less than RWSEM_WAITING_BIAS
-			 * after removing the adjustment, it is assumed that
-			 * a writer has stolen the lock. We have to undo our
-			 * reader grant.
-			 */
-			if (atomic_long_add_return(-adjustment, &sem->count) <
-			    RWSEM_WAITING_BIAS)
-				return;
-
-			/* Last active locker left. Retry waking readers. */
-			goto try_reader_grant;
-		}
-		/*
-		 * Set it to reader-owned to give spinners an early
-		 * indication that readers now have the lock.
-		 */
-		__rwsem_set_reader_owned(sem, waiter->task);
-	}
-
-	/*
-	 * Grant an infinite number of read locks to the readers at the front
-	 * of the queue. We know that woken will be at least 1 as we accounted
-	 * for above. Note we increment the 'active part' of the count by the
-	 * number of readers before waking any processes up.
-	 *
-	 * We have to do wakeup in 2 passes to prevent the possibility that
-	 * the reader count may be decremented before it is incremented. It
-	 * is because the to-be-woken waiter may not have slept yet. So it
-	 * may see waiter->task got cleared, finish its critical section and
-	 * do an unlock before the reader count increment.
-	 *
-	 * 1) Collect the read-waiters in a separate list, count them and
-	 *    fully increment the reader count in rwsem.
-	 * 2) For each waiters in the new list, clear waiter->task and
-	 *    put them into wake_q to be woken up later.
-	 */
-	list_for_each_entry(waiter, &sem->wait_list, list) {
-		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
-			break;
-
-		woken++;
-	}
-	list_cut_before(&wlist, &sem->wait_list, &waiter->list);
-
-	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;
-	lockevent_cond_inc(rwsem_wake_reader, woken);
-	if (list_empty(&sem->wait_list)) {
-		/* hit end of list above */
-		adjustment -= RWSEM_WAITING_BIAS;
-	}
-
-	if (adjustment)
-		atomic_long_add(adjustment, &sem->count);
-
-	/* 2nd pass */
-	list_for_each_entry_safe(waiter, tmp, &wlist, list) {
-		struct task_struct *tsk;
-
-		tsk = waiter->task;
-		get_task_struct(tsk);
-
-		/*
-		 * Ensure calling get_task_struct() before setting the reader
-		 * waiter to nil such that rwsem_down_read_failed() cannot
-		 * race with do_exit() by always holding a reference count
-		 * to the task to wakeup.
-		 */
-		smp_store_release(&waiter->task, NULL);
-		/*
-		 * Ensure issuing the wakeup (either by us or someone else)
-		 * after setting the reader waiter to nil.
-		 */
-		wake_q_add_safe(wake_q, tsk);
-	}
-}
-
-/*
- * This function must be called with the sem->wait_lock held to prevent
- * race conditions between checking the rwsem wait list and setting the
- * sem->count accordingly.
- */
-static inline bool rwsem_try_write_lock(long count, struct rw_semaphore *sem)
-{
-	/*
-	 * Avoid trying to acquire write lock if count isn't RWSEM_WAITING_BIAS.
-	 */
-	if (count != RWSEM_WAITING_BIAS)
-		return false;
-
-	/*
-	 * Acquire the lock by trying to set it to ACTIVE_WRITE_BIAS. If there
-	 * are other tasks on the wait list, we need to add on WAITING_BIAS.
-	 */
-	count = list_is_singular(&sem->wait_list) ?
-			RWSEM_ACTIVE_WRITE_BIAS :
-			RWSEM_ACTIVE_WRITE_BIAS + RWSEM_WAITING_BIAS;
-
-	if (atomic_long_cmpxchg_acquire(&sem->count, RWSEM_WAITING_BIAS, count)
-							== RWSEM_WAITING_BIAS) {
-		rwsem_set_owner(sem);
-		return true;
-	}
-
-	return false;
-}
-
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-/*
- * Try to acquire write lock before the writer has been put on wait queue.
- */
-static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
-{
-	long count = atomic_long_read(&sem->count);
-
-	while (!count || count == RWSEM_WAITING_BIAS) {
-		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
-					count + RWSEM_ACTIVE_WRITE_BIAS)) {
-			rwsem_set_owner(sem);
-			lockevent_inc(rwsem_opt_wlock);
-			return true;
-		}
-	}
-	return false;
-}
-
-static inline bool owner_on_cpu(struct task_struct *owner)
-{
-	/*
-	 * As lock holder preemption issue, we both skip spinning if
-	 * task is not on cpu or its cpu is preempted
-	 */
-	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
-}
-
-static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem)
-{
-	struct task_struct *owner;
-	bool ret = true;
-
-	BUILD_BUG_ON(!rwsem_has_anonymous_owner(RWSEM_OWNER_UNKNOWN));
-
-	if (need_resched())
-		return false;
-
-	rcu_read_lock();
-	owner = READ_ONCE(sem->owner);
-	if (owner) {
-		ret = is_rwsem_owner_spinnable(owner) &&
-		      owner_on_cpu(owner);
-	}
-	rcu_read_unlock();
-	return ret;
-}
-
-/*
- * Return true only if we can still spin on the owner field of the rwsem.
- */
-static noinline bool rwsem_spin_on_owner(struct rw_semaphore *sem)
-{
-	struct task_struct *owner = READ_ONCE(sem->owner);
-
-	if (!is_rwsem_owner_spinnable(owner))
-		return false;
-
-	rcu_read_lock();
-	while (owner && (READ_ONCE(sem->owner) == owner)) {
-		/*
-		 * Ensure we emit the owner->on_cpu, dereference _after_
-		 * checking sem->owner still matches owner, if that fails,
-		 * owner might point to free()d memory, if it still matches,
-		 * the rcu_read_lock() ensures the memory stays valid.
-		 */
-		barrier();
-
-		/*
-		 * abort spinning when need_resched or owner is not running or
-		 * owner's cpu is preempted.
-		 */
-		if (need_resched() || !owner_on_cpu(owner)) {
-			rcu_read_unlock();
-			return false;
-		}
-
-		cpu_relax();
-	}
-	rcu_read_unlock();
-
-	/*
-	 * If there is a new owner or the owner is not set, we continue
-	 * spinning.
-	 */
-	return is_rwsem_owner_spinnable(READ_ONCE(sem->owner));
-}
-
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
-{
-	bool taken = false;
-
-	preempt_disable();
-
-	/* sem->wait_lock should not be held when doing optimistic spinning */
-	if (!rwsem_can_spin_on_owner(sem))
-		goto done;
-
-	if (!osq_lock(&sem->osq))
-		goto done;
-
-	/*
-	 * Optimistically spin on the owner field and attempt to acquire the
-	 * lock whenever the owner changes. Spinning will be stopped when:
-	 *  1) the owning writer isn't running; or
-	 *  2) readers own the lock as we can't determine if they are
-	 *     actively running or not.
-	 */
-	while (rwsem_spin_on_owner(sem)) {
-		/*
-		 * Try to acquire the lock
-		 */
-		if (rwsem_try_write_lock_unqueued(sem)) {
-			taken = true;
-			break;
-		}
-
-		/*
-		 * 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 (!sem->owner && (need_resched() || rt_task(current)))
-			break;
-
-		/*
-		 * The cpu_relax() call is a compiler barrier which forces
-		 * everything in this loop to be re-loaded. We don't need
-		 * memory barriers as we'll eventually observe the right
-		 * values at the cost of a few extra spins.
-		 */
-		cpu_relax();
-	}
-	osq_unlock(&sem->osq);
-done:
-	preempt_enable();
-	lockevent_cond_inc(rwsem_opt_fail, !taken);
-	return taken;
-}
-
-/*
- * Return true if the rwsem has active spinner
- */
-static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
-{
-	return osq_is_locked(&sem->osq);
-}
-
-#else
-static bool rwsem_optimistic_spin(struct rw_semaphore *sem)
-{
-	return false;
-}
-
-static inline bool rwsem_has_spinner(struct rw_semaphore *sem)
-{
-	return false;
-}
-#endif
-
-/*
- * Wait for the read lock to be granted
- */
-static inline struct rw_semaphore __sched *
-__rwsem_down_read_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count, adjustment = -RWSEM_ACTIVE_READ_BIAS;
-	struct rwsem_waiter waiter;
-	DEFINE_WAKE_Q(wake_q);
-
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_READ;
-
-	raw_spin_lock_irq(&sem->wait_lock);
-	if (list_empty(&sem->wait_list)) {
-		/*
-		 * In case the wait queue is empty and the lock isn't owned
-		 * by a writer, this reader can exit the slowpath and return
-		 * immediately as its RWSEM_ACTIVE_READ_BIAS has already
-		 * been set in the count.
-		 */
-		if (atomic_long_read(&sem->count) >= 0) {
-			raw_spin_unlock_irq(&sem->wait_lock);
-			rwsem_set_reader_owned(sem);
-			lockevent_inc(rwsem_rlock_fast);
-			return sem;
-		}
-		adjustment += RWSEM_WAITING_BIAS;
-	}
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* we're now waiting on the lock, but no longer actively locking */
-	count = atomic_long_add_return(adjustment, &sem->count);
-
-	/*
-	 * If there are no active locks, wake the front queued process(es).
-	 *
-	 * If there are no writers and we are first in the queue,
-	 * wake our own waiter to join the existing active readers !
-	 */
-	if (count == RWSEM_WAITING_BIAS ||
-	    (count > RWSEM_WAITING_BIAS &&
-	     adjustment != -RWSEM_ACTIVE_READ_BIAS))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-
-	/* wait to be given the lock */
-	while (true) {
-		set_current_state(state);
-		if (!waiter.task)
-			break;
-		if (signal_pending_state(state, current)) {
-			raw_spin_lock_irq(&sem->wait_lock);
-			if (waiter.task)
-				goto out_nolock;
-			raw_spin_unlock_irq(&sem->wait_lock);
-			break;
-		}
-		schedule();
-		lockevent_inc(rwsem_sleep_reader);
-	}
-
-	__set_current_state(TASK_RUNNING);
-	lockevent_inc(rwsem_rlock);
-	return sem;
-out_nolock:
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	__set_current_state(TASK_RUNNING);
-	lockevent_inc(rwsem_rlock_fail);
-	return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_read_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_read_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_read_failed_killable);
-
-/*
- * Wait until we successfully acquire the write lock
- */
-static inline struct rw_semaphore *
-__rwsem_down_write_failed_common(struct rw_semaphore *sem, int state)
-{
-	long count;
-	bool waiting = true; /* any queued threads before us */
-	struct rwsem_waiter waiter;
-	struct rw_semaphore *ret = sem;
-	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);
-
-	/* do optimistic spinning and steal lock if possible */
-	if (rwsem_optimistic_spin(sem))
-		return sem;
-
-	/*
-	 * Optimistic spinning failed, proceed to the slowpath
-	 * and block until we can acquire the sem.
-	 */
-	waiter.task = current;
-	waiter.type = RWSEM_WAITING_FOR_WRITE;
-
-	raw_spin_lock_irq(&sem->wait_lock);
-
-	/* account for this before adding a new element to the list */
-	if (list_empty(&sem->wait_list))
-		waiting = false;
-
-	list_add_tail(&waiter.list, &sem->wait_list);
-
-	/* we're now waiting on the lock, but no longer actively locking */
-	if (waiting) {
-		count = atomic_long_read(&sem->count);
-
-		/*
-		 * If there were already threads queued before us and there are
-		 * no active writers, the lock must be read owned; so we try to
-		 * wake any read locks that were queued ahead of us.
-		 */
-		if (count > RWSEM_WAITING_BIAS) {
-			__rwsem_mark_wake(sem, RWSEM_WAKE_READERS, &wake_q);
-			/*
-			 * The wakeup is normally called _after_ the wait_lock
-			 * is released, but given that we are proactively waking
-			 * readers we can deal with the wake_q overhead as it is
-			 * similar to releasing and taking the wait_lock again
-			 * for attempting rwsem_try_write_lock().
-			 */
-			wake_up_q(&wake_q);
-
-			/*
-			 * Reinitialize wake_q after use.
-			 */
-			wake_q_init(&wake_q);
-		}
-
-	} else
-		count = atomic_long_add_return(RWSEM_WAITING_BIAS, &sem->count);
-
-	/* wait until we successfully acquire the lock */
-	set_current_state(state);
-	while (true) {
-		if (rwsem_try_write_lock(count, sem))
-			break;
-		raw_spin_unlock_irq(&sem->wait_lock);
-
-		/* Block until there are no active lockers. */
-		do {
-			if (signal_pending_state(state, current))
-				goto out_nolock;
-
-			schedule();
-			lockevent_inc(rwsem_sleep_writer);
-			set_current_state(state);
-		} while ((count = atomic_long_read(&sem->count)) & RWSEM_ACTIVE_MASK);
-
-		raw_spin_lock_irq(&sem->wait_lock);
-	}
-	__set_current_state(TASK_RUNNING);
-	list_del(&waiter.list);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	lockevent_inc(rwsem_wlock);
-
-	return ret;
-
-out_nolock:
-	__set_current_state(TASK_RUNNING);
-	raw_spin_lock_irq(&sem->wait_lock);
-	list_del(&waiter.list);
-	if (list_empty(&sem->wait_list))
-		atomic_long_add(-RWSEM_WAITING_BIAS, &sem->count);
-	else
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-	raw_spin_unlock_irq(&sem->wait_lock);
-	wake_up_q(&wake_q);
-	lockevent_inc(rwsem_wlock_fail);
-
-	return ERR_PTR(-EINTR);
-}
-
-__visible struct rw_semaphore * __sched
-rwsem_down_write_failed(struct rw_semaphore *sem)
-{
-	return __rwsem_down_write_failed_common(sem, TASK_UNINTERRUPTIBLE);
-}
-EXPORT_SYMBOL(rwsem_down_write_failed);
-
-__visible struct rw_semaphore * __sched
-rwsem_down_write_failed_killable(struct rw_semaphore *sem)
-{
-	return __rwsem_down_write_failed_common(sem, TASK_KILLABLE);
-}
-EXPORT_SYMBOL(rwsem_down_write_failed_killable);
-
-/*
- * handle waking up a waiter on the semaphore
- * - up_read/up_write has decremented the active part of count if we come here
- */
-__visible
-struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	DEFINE_WAKE_Q(wake_q);
-
-	/*
-	* __rwsem_down_write_failed_common(sem)
-	*   rwsem_optimistic_spin(sem)
-	*     osq_unlock(sem->osq)
-	*   ...
-	*   atomic_long_add_return(&sem->count)
-	*
-	*      - VS -
-	*
-	*              __up_write()
-	*                if (atomic_long_sub_return_release(&sem->count) < 0)
-	*                  rwsem_wake(sem)
-	*                    osq_is_locked(&sem->osq)
-	*
-	* And __up_write() must observe !osq_is_locked() when it observes the
-	* atomic_long_add_return() in order to not miss a wakeup.
-	*
-	* This boils down to:
-	*
-	* [S.rel] X = 1                [RmW] r0 = (Y += 0)
-	*         MB                         RMB
-	* [RmW]   Y += 1               [L]   r1 = X
-	*
-	* exists (r0=1 /\ r1=0)
-	*/
-	smp_rmb();
-
-	/*
-	 * If a spinner is present, it is not necessary to do the wakeup.
-	 * Try to do wakeup only if the trylock succeeds to minimize
-	 * spinlock contention which may introduce too much delay in the
-	 * unlock operation.
-	 *
-	 *    spinning writer		up_write/up_read caller
-	 *    ---------------		-----------------------
-	 * [S]   osq_unlock()		[L]   osq
-	 *	 MB			      RMB
-	 * [RmW] rwsem_try_write_lock() [RmW] spin_trylock(wait_lock)
-	 *
-	 * Here, it is important to make sure that there won't be a missed
-	 * wakeup while the rwsem is free and the only spinning writer goes
-	 * to sleep without taking the rwsem. Even when the spinning writer
-	 * is just going to break out of the waiting loop, it will still do
-	 * a trylock in rwsem_down_write_failed() before sleeping. IOW, if
-	 * rwsem_has_spinner() is true, it will guarantee at least one
-	 * trylock attempt on the rwsem later on.
-	 */
-	if (rwsem_has_spinner(sem)) {
-		/*
-		 * The smp_rmb() here is to make sure that the spinner
-		 * state is consulted before reading the wait_lock.
-		 */
-		smp_rmb();
-		if (!raw_spin_trylock_irqsave(&sem->wait_lock, flags))
-			return sem;
-		goto locked;
-	}
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-locked:
-
-	if (!list_empty(&sem->wait_list))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	wake_up_q(&wake_q);
-
-	return sem;
-}
-EXPORT_SYMBOL(rwsem_wake);
-
-/*
- * downgrade a write lock into a read lock
- * - caller incremented waiting part of count and discovered it still negative
- * - just wake up any readers at the front of the queue
- */
-__visible
-struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
-{
-	unsigned long flags;
-	DEFINE_WAKE_Q(wake_q);
-
-	raw_spin_lock_irqsave(&sem->wait_lock, flags);
-
-	if (!list_empty(&sem->wait_list))
-		__rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
-
-	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
-	wake_up_q(&wake_q);
-
-	return sem;
-}
-EXPORT_SYMBOL(rwsem_downgrade_wake);
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index ccbf18f560ff..37524a47f002 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -3,17 +3,1438 @@
  *
  * Written by David Howells (dhowells@redhat.com).
  * Derived from asm-i386/semaphore.h
+ *
+ * Writer lock-stealing by Alex Shi <alex.shi@intel.com>
+ * and Michel Lespinasse <walken@google.com>
+ *
+ * Optimistic spinning by Tim Chen <tim.c.chen@intel.com>
+ * and Davidlohr Bueso <davidlohr@hp.com>. Based on mutexes.
+ *
+ * Rwsem count bit fields re-definition and rwsem rearchitecture by
+ * Waiman Long <longman@redhat.com> and
+ * Peter Zijlstra <peterz@infradead.org>.
  */
 
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/rt.h>
+#include <linux/sched/task.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/wake_q.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/clock.h>
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
 
 #include "rwsem.h"
+#include "lock_events.h"
+
+/*
+ * The least significant 3 bits of the owner value has the following
+ * meanings when set.
+ *  - Bit 0: RWSEM_READER_OWNED - The rwsem is owned by readers
+ *  - Bit 1: RWSEM_RD_NONSPINNABLE - Readers cannot spin on this lock.
+ *  - Bit 2: RWSEM_WR_NONSPINNABLE - Writers cannot spin on this lock.
+ *
+ * When the rwsem is either owned by an anonymous writer, or it is
+ * reader-owned, but a spinning writer has timed out, both nonspinnable
+ * bits will be set to disable optimistic spinning by readers and writers.
+ * In the later case, the last unlocking reader should then check the
+ * writer nonspinnable bit and clear it only to give writers preference
+ * to acquire the lock via optimistic spinning, but not readers. Similar
+ * action is also done in the reader slowpath.
+
+ * When a writer acquires a rwsem, it puts its task_struct pointer
+ * into the owner field. It is cleared after an unlock.
+ *
+ * When a reader acquires a rwsem, it will also puts its task_struct
+ * pointer into the owner field with the RWSEM_READER_OWNED bit set.
+ * On unlock, the owner field will largely be left untouched. So
+ * for a free or reader-owned rwsem, the owner value may contain
+ * information about the last reader that acquires the rwsem.
+ *
+ * That information may be helpful in debugging cases where the system
+ * seems to hang on a reader owned rwsem especially if only one reader
+ * is involved. Ideally we would like to track all the readers that own
+ * a rwsem, but the overhead is simply too big.
+ *
+ * Reader optimistic spinning is helpful when the reader critical section
+ * is short and there aren't that many readers around. It makes readers
+ * relatively more preferred than writers. When a writer times out spinning
+ * on a reader-owned lock and set the nospinnable bits, there are two main
+ * reasons for that.
+ *
+ *  1) The reader critical section is long, perhaps the task sleeps after
+ *     acquiring the read lock.
+ *  2) There are just too many readers contending the lock causing it to
+ *     take a while to service all of them.
+ *
+ * In the former case, long reader critical section will impede the progress
+ * of writers which is usually more important for system performance. In
+ * the later case, reader optimistic spinning tends to make the reader
+ * groups that contain readers that acquire the lock together smaller
+ * leading to more of them. That may hurt performance in some cases. In
+ * other words, the setting of nonspinnable bits indicates that reader
+ * optimistic spinning may not be helpful for those workloads that cause
+ * it.
+ *
+ * Therefore, any writers that had observed the setting of the writer
+ * nonspinnable bit for a given rwsem after they fail to acquire the lock
+ * via optimistic spinning will set the reader nonspinnable bit once they
+ * acquire the write lock. Similarly, readers that observe the setting
+ * of reader nonspinnable bit at slowpath entry will set the reader
+ * nonspinnable bits when they acquire the read lock via the wakeup path.
+ *
+ * Once the reader nonspinnable bit is on, it will only be reset when
+ * a writer is able to acquire the rwsem in the fast path or somehow a
+ * reader or writer in the slowpath doesn't observe the nonspinable bit.
+ *
+ * This is to discourage reader optmistic spinning on that particular
+ * rwsem and make writers more preferred. This adaptive disabling of reader
+ * optimistic spinning will alleviate the negative side effect of this
+ * feature.
+ */
+#define RWSEM_READER_OWNED	(1UL << 0)
+#define RWSEM_RD_NONSPINNABLE	(1UL << 1)
+#define RWSEM_WR_NONSPINNABLE	(1UL << 2)
+#define RWSEM_NONSPINNABLE	(RWSEM_RD_NONSPINNABLE | RWSEM_WR_NONSPINNABLE)
+#define RWSEM_OWNER_FLAGS_MASK	(RWSEM_READER_OWNED | RWSEM_NONSPINNABLE)
+
+#ifdef CONFIG_DEBUG_RWSEMS
+# define DEBUG_RWSEMS_WARN_ON(c, sem)	do {			\
+	if (!debug_locks_silent &&				\
+	    WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
+		#c, atomic_long_read(&(sem)->count),		\
+		atomic_long_read(&(sem)->owner), (long)current,	\
+		list_empty(&(sem)->wait_list) ? "" : "not "))	\
+			debug_locks_off();			\
+	} while (0)
+#else
+# define DEBUG_RWSEMS_WARN_ON(c, sem)
+#endif
+
+/*
+ * On 64-bit architectures, the bit definitions of the count are:
+ *
+ * Bit  0    - writer locked bit
+ * Bit  1    - waiters present bit
+ * Bit  2    - lock handoff bit
+ * Bits 3-7  - reserved
+ * Bits 8-62 - 55-bit reader count
+ * Bit  63   - read fail bit
+ *
+ * On 32-bit architectures, the bit definitions of the count are:
+ *
+ * Bit  0    - writer locked bit
+ * Bit  1    - waiters present bit
+ * Bit  2    - lock handoff bit
+ * Bits 3-7  - reserved
+ * Bits 8-30 - 23-bit reader count
+ * Bit  31   - read fail bit
+ *
+ * It is not likely that the most significant bit (read fail bit) will ever
+ * be set. This guard bit is still checked anyway in the down_read() fastpath
+ * just in case we need to use up more of the reader bits for other purpose
+ * in the future.
+ *
+ * atomic_long_fetch_add() is used to obtain reader lock, whereas
+ * atomic_long_cmpxchg() will be used to obtain writer lock.
+ *
+ * There are three places where the lock handoff bit may be set or cleared.
+ * 1) rwsem_mark_wake() for readers.
+ * 2) rwsem_try_write_lock() for writers.
+ * 3) Error path of rwsem_down_write_slowpath().
+ *
+ * For all the above cases, wait_lock will be held. A writer must also
+ * be the first one in the wait_list to be eligible for setting the handoff
+ * bit. So concurrent setting/clearing of handoff bit is not possible.
+ */
+#define RWSEM_WRITER_LOCKED	(1UL << 0)
+#define RWSEM_FLAG_WAITERS	(1UL << 1)
+#define RWSEM_FLAG_HANDOFF	(1UL << 2)
+#define RWSEM_FLAG_READFAIL	(1UL << (BITS_PER_LONG - 1))
+
+#define RWSEM_READER_SHIFT	8
+#define RWSEM_READER_BIAS	(1UL << RWSEM_READER_SHIFT)
+#define RWSEM_READER_MASK	(~(RWSEM_READER_BIAS - 1))
+#define RWSEM_WRITER_MASK	RWSEM_WRITER_LOCKED
+#define RWSEM_LOCK_MASK		(RWSEM_WRITER_MASK|RWSEM_READER_MASK)
+#define RWSEM_READ_FAILED_MASK	(RWSEM_WRITER_MASK|RWSEM_FLAG_WAITERS|\
+				 RWSEM_FLAG_HANDOFF|RWSEM_FLAG_READFAIL)
+
+/*
+ * All writes to owner are protected by WRITE_ONCE() to make sure that
+ * store tearing can't happen as optimistic spinners may read and use
+ * the owner value concurrently without lock. Read from owner, however,
+ * may not need READ_ONCE() as long as the pointer value is only used
+ * for comparison and isn't being dereferenced.
+ */
+static inline void rwsem_set_owner(struct rw_semaphore *sem)
+{
+	atomic_long_set(&sem->owner, (long)current);
+}
+
+static inline void rwsem_clear_owner(struct rw_semaphore *sem)
+{
+	atomic_long_set(&sem->owner, 0);
+}
+
+/*
+ * Test the flags in the owner field.
+ */
+static inline bool rwsem_test_oflags(struct rw_semaphore *sem, long flags)
+{
+	return atomic_long_read(&sem->owner) & flags;
+}
+
+/*
+ * The task_struct pointer of the last owning reader will be left in
+ * the owner field.
+ *
+ * Note that the owner value just indicates the task has owned the rwsem
+ * previously, it may not be the real owner or one of the real owners
+ * anymore when that field is examined, so take it with a grain of salt.
+ *
+ * The reader non-spinnable bit is preserved.
+ */
+static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
+					    struct task_struct *owner)
+{
+	unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED |
+		(atomic_long_read(&sem->owner) & RWSEM_RD_NONSPINNABLE);
+
+	atomic_long_set(&sem->owner, val);
+}
+
+static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
+{
+	__rwsem_set_reader_owned(sem, current);
+}
+
+/*
+ * Return true if the rwsem is owned by a reader.
+ */
+static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
+{
+#ifdef CONFIG_DEBUG_RWSEMS
+	/*
+	 * Check the count to see if it is write-locked.
+	 */
+	long count = atomic_long_read(&sem->count);
+
+	if (count & RWSEM_WRITER_MASK)
+		return false;
+#endif
+	return rwsem_test_oflags(sem, RWSEM_READER_OWNED);
+}
+
+#ifdef CONFIG_DEBUG_RWSEMS
+/*
+ * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
+ * is a task pointer in owner of a reader-owned rwsem, it will be the
+ * real owner or one of the real owners. The only exception is when the
+ * unlock is done by up_read_non_owner().
+ */
+static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
+{
+	unsigned long val = atomic_long_read(&sem->owner);
+
+	while ((val & ~RWSEM_OWNER_FLAGS_MASK) == (unsigned long)current) {
+		if (atomic_long_try_cmpxchg(&sem->owner, &val,
+					    val & RWSEM_OWNER_FLAGS_MASK))
+			return;
+	}
+}
+#else
+static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
+{
+}
+#endif
+
+/*
+ * Set the RWSEM_NONSPINNABLE bits if the RWSEM_READER_OWNED flag
+ * remains set. Otherwise, the operation will be aborted.
+ */
+static inline void rwsem_set_nonspinnable(struct rw_semaphore *sem)
+{
+	unsigned long owner = atomic_long_read(&sem->owner);
+
+	do {
+		if (!(owner & RWSEM_READER_OWNED))
+			break;
+		if (owner & RWSEM_NONSPINNABLE)
+			break;
+	} while (!atomic_long_try_cmpxchg(&sem->owner, &owner,
+					  owner | RWSEM_NONSPINNABLE));
+}
+
+static inline bool rwsem_read_trylock(struct rw_semaphore *sem)
+{
+	long cnt = atomic_long_add_return_acquire(RWSEM_READER_BIAS, &sem->count);
+	if (WARN_ON_ONCE(cnt < 0))
+		rwsem_set_nonspinnable(sem);
+	return !(cnt & RWSEM_READ_FAILED_MASK);
+}
+
+/*
+ * Return just the real task structure pointer of the owner
+ */
+static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+{
+	return (struct task_struct *)
+		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
+}
+
+/*
+ * Return the real task structure pointer of the owner and the embedded
+ * flags in the owner. pflags must be non-NULL.
+ */
+static inline struct task_struct *
+rwsem_owner_flags(struct rw_semaphore *sem, unsigned long *pflags)
+{
+	unsigned long owner = atomic_long_read(&sem->owner);
+
+	*pflags = owner & RWSEM_OWNER_FLAGS_MASK;
+	return (struct task_struct *)(owner & ~RWSEM_OWNER_FLAGS_MASK);
+}
+
+/*
+ * Guide to the rw_semaphore's count field.
+ *
+ * When the RWSEM_WRITER_LOCKED bit in count is set, the lock is owned
+ * by a writer.
+ *
+ * The lock is owned by readers when
+ * (1) the RWSEM_WRITER_LOCKED isn't set in count,
+ * (2) some of the reader bits are set in count, and
+ * (3) the owner field has RWSEM_READ_OWNED bit set.
+ *
+ * Having some reader bits set is not enough to guarantee a readers owned
+ * lock as the readers may be in the process of backing out from the count
+ * and a writer has just released the lock. So another writer may steal
+ * the lock immediately after that.
+ */
+
+/*
+ * Initialize an rwsem:
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	atomic_long_set(&sem->count, RWSEM_UNLOCKED_VALUE);
+	raw_spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+	atomic_long_set(&sem->owner, 0L);
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+	osq_lock_init(&sem->osq);
+#endif
+}
+EXPORT_SYMBOL(__init_rwsem);
+
+enum rwsem_waiter_type {
+	RWSEM_WAITING_FOR_WRITE,
+	RWSEM_WAITING_FOR_READ
+};
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	enum rwsem_waiter_type type;
+	unsigned long timeout;
+	unsigned long last_rowner;
+};
+#define rwsem_first_waiter(sem) \
+	list_first_entry(&sem->wait_list, struct rwsem_waiter, list)
+
+enum rwsem_wake_type {
+	RWSEM_WAKE_ANY,		/* Wake whatever's at head of wait list */
+	RWSEM_WAKE_READERS,	/* Wake readers only */
+	RWSEM_WAKE_READ_OWNED	/* Waker thread holds the read lock */
+};
+
+enum writer_wait_state {
+	WRITER_NOT_FIRST,	/* Writer is not first in wait list */
+	WRITER_FIRST,		/* Writer is first in wait list     */
+	WRITER_HANDOFF		/* Writer is first & handoff needed */
+};
+
+/*
+ * The typical HZ value is either 250 or 1000. So set the minimum waiting
+ * time to at least 4ms or 1 jiffy (if it is higher than 4ms) in the wait
+ * queue before initiating the handoff protocol.
+ */
+#define RWSEM_WAIT_TIMEOUT	DIV_ROUND_UP(HZ, 250)
+
+/*
+ * Magic number to batch-wakeup waiting readers, even when writers are
+ * also present in the queue. This both limits the amount of work the
+ * waking thread must do and also prevents any potential counter overflow,
+ * however unlikely.
+ */
+#define MAX_READERS_WAKEUP	0x100
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here from up_xxxx(), then the RWSEM_FLAG_WAITERS bit must
+ *   have been set.
+ * - there must be someone on the queue
+ * - the wait_lock must be held by the caller
+ * - tasks are marked for wakeup, the caller must later invoke wake_up_q()
+ *   to actually wakeup the blocked task(s) and drop the reference count,
+ *   preferably when the wait_lock is released
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only marked woken if downgrading is false
+ */
+static void rwsem_mark_wake(struct rw_semaphore *sem,
+			    enum rwsem_wake_type wake_type,
+			    struct wake_q_head *wake_q)
+{
+	struct rwsem_waiter *waiter, *tmp;
+	long oldcount, woken = 0, adjustment = 0;
+	struct list_head wlist;
+
+	lockdep_assert_held(&sem->wait_lock);
+
+	/*
+	 * Take a peek at the queue head waiter such that we can determine
+	 * the wakeup(s) to perform.
+	 */
+	waiter = rwsem_first_waiter(sem);
+
+	if (waiter->type == RWSEM_WAITING_FOR_WRITE) {
+		if (wake_type == RWSEM_WAKE_ANY) {
+			/*
+			 * Mark writer at the front of the queue for wakeup.
+			 * Until the task is actually later awoken later by
+			 * the caller, other writers are able to steal it.
+			 * Readers, on the other hand, will block as they
+			 * will notice the queued writer.
+			 */
+			wake_q_add(wake_q, waiter->task);
+			lockevent_inc(rwsem_wake_writer);
+		}
+
+		return;
+	}
+
+	/*
+	 * No reader wakeup if there are too many of them already.
+	 */
+	if (unlikely(atomic_long_read(&sem->count) < 0))
+		return;
+
+	/*
+	 * Writers might steal the lock before we grant it to the next reader.
+	 * We prefer to do the first reader grant before counting readers
+	 * so we can bail out early if a writer stole the lock.
+	 */
+	if (wake_type != RWSEM_WAKE_READ_OWNED) {
+		struct task_struct *owner;
+
+		adjustment = RWSEM_READER_BIAS;
+		oldcount = atomic_long_fetch_add(adjustment, &sem->count);
+		if (unlikely(oldcount & RWSEM_WRITER_MASK)) {
+			/*
+			 * When we've been waiting "too" long (for writers
+			 * to give up the lock), request a HANDOFF to
+			 * force the issue.
+			 */
+			if (!(oldcount & RWSEM_FLAG_HANDOFF) &&
+			    time_after(jiffies, waiter->timeout)) {
+				adjustment -= RWSEM_FLAG_HANDOFF;
+				lockevent_inc(rwsem_rlock_handoff);
+			}
+
+			atomic_long_add(-adjustment, &sem->count);
+			return;
+		}
+		/*
+		 * Set it to reader-owned to give spinners an early
+		 * indication that readers now have the lock.
+		 * The reader nonspinnable bit seen at slowpath entry of
+		 * the reader is copied over.
+		 */
+		owner = waiter->task;
+		if (waiter->last_rowner & RWSEM_RD_NONSPINNABLE) {
+			owner = (void *)((unsigned long)owner | RWSEM_RD_NONSPINNABLE);
+			lockevent_inc(rwsem_opt_norspin);
+		}
+		__rwsem_set_reader_owned(sem, owner);
+	}
+
+	/*
+	 * Grant up to MAX_READERS_WAKEUP read locks to all the readers in the
+	 * queue. We know that the woken will be at least 1 as we accounted
+	 * for above. Note we increment the 'active part' of the count by the
+	 * number of readers before waking any processes up.
+	 *
+	 * This is an adaptation of the phase-fair R/W locks where at the
+	 * reader phase (first waiter is a reader), all readers are eligible
+	 * to acquire the lock at the same time irrespective of their order
+	 * in the queue. The writers acquire the lock according to their
+	 * order in the queue.
+	 *
+	 * We have to do wakeup in 2 passes to prevent the possibility that
+	 * the reader count may be decremented before it is incremented. It
+	 * is because the to-be-woken waiter may not have slept yet. So it
+	 * may see waiter->task got cleared, finish its critical section and
+	 * do an unlock before the reader count increment.
+	 *
+	 * 1) Collect the read-waiters in a separate list, count them and
+	 *    fully increment the reader count in rwsem.
+	 * 2) For each waiters in the new list, clear waiter->task and
+	 *    put them into wake_q to be woken up later.
+	 */
+	INIT_LIST_HEAD(&wlist);
+	list_for_each_entry_safe(waiter, tmp, &sem->wait_list, list) {
+		if (waiter->type == RWSEM_WAITING_FOR_WRITE)
+			continue;
+
+		woken++;
+		list_move_tail(&waiter->list, &wlist);
+
+		/*
+		 * Limit # of readers that can be woken up per wakeup call.
+		 */
+		if (woken >= MAX_READERS_WAKEUP)
+			break;
+	}
+
+	adjustment = woken * RWSEM_READER_BIAS - adjustment;
+	lockevent_cond_inc(rwsem_wake_reader, woken);
+	if (list_empty(&sem->wait_list)) {
+		/* hit end of list above */
+		adjustment -= RWSEM_FLAG_WAITERS;
+	}
+
+	/*
+	 * When we've woken a reader, we no longer need to force writers
+	 * to give up the lock and we can clear HANDOFF.
+	 */
+	if (woken && (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF))
+		adjustment -= RWSEM_FLAG_HANDOFF;
+
+	if (adjustment)
+		atomic_long_add(adjustment, &sem->count);
+
+	/* 2nd pass */
+	list_for_each_entry_safe(waiter, tmp, &wlist, list) {
+		struct task_struct *tsk;
+
+		tsk = waiter->task;
+		get_task_struct(tsk);
+
+		/*
+		 * Ensure calling get_task_struct() before setting the reader
+		 * waiter to nil such that rwsem_down_read_slowpath() cannot
+		 * race with do_exit() by always holding a reference count
+		 * to the task to wakeup.
+		 */
+		smp_store_release(&waiter->task, NULL);
+		/*
+		 * Ensure issuing the wakeup (either by us or someone else)
+		 * after setting the reader waiter to nil.
+		 */
+		wake_q_add_safe(wake_q, tsk);
+	}
+}
+
+/*
+ * This function must be called with the sem->wait_lock held to prevent
+ * race conditions between checking the rwsem wait list and setting the
+ * sem->count accordingly.
+ *
+ * If wstate is WRITER_HANDOFF, it will make sure that either the handoff
+ * bit is set or the lock is acquired with handoff bit cleared.
+ */
+static inline bool rwsem_try_write_lock(struct rw_semaphore *sem,
+					enum writer_wait_state wstate)
+{
+	long count, new;
+
+	lockdep_assert_held(&sem->wait_lock);
+
+	count = atomic_long_read(&sem->count);
+	do {
+		bool has_handoff = !!(count & RWSEM_FLAG_HANDOFF);
+
+		if (has_handoff && wstate == WRITER_NOT_FIRST)
+			return false;
+
+		new = count;
+
+		if (count & RWSEM_LOCK_MASK) {
+			if (has_handoff || (wstate != WRITER_HANDOFF))
+				return false;
+
+			new |= RWSEM_FLAG_HANDOFF;
+		} else {
+			new |= RWSEM_WRITER_LOCKED;
+			new &= ~RWSEM_FLAG_HANDOFF;
+
+			if (list_is_singular(&sem->wait_list))
+				new &= ~RWSEM_FLAG_WAITERS;
+		}
+	} while (!atomic_long_try_cmpxchg_acquire(&sem->count, &count, new));
+
+	/*
+	 * We have either acquired the lock with handoff bit cleared or
+	 * set the handoff bit.
+	 */
+	if (new & RWSEM_FLAG_HANDOFF)
+		return false;
+
+	rwsem_set_owner(sem);
+	return true;
+}
+
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
+/*
+ * Try to acquire read lock before the reader is put on wait queue.
+ * Lock acquisition isn't allowed if the rwsem is locked or a writer handoff
+ * is ongoing.
+ */
+static inline bool rwsem_try_read_lock_unqueued(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+
+	if (count & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))
+		return false;
+
+	count = atomic_long_fetch_add_acquire(RWSEM_READER_BIAS, &sem->count);
+	if (!(count & (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+		rwsem_set_reader_owned(sem);
+		lockevent_inc(rwsem_opt_rlock);
+		return true;
+	}
+
+	/* Back out the change */
+	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
+	return false;
+}
+
+/*
+ * Try to acquire write lock before the writer has been put on wait queue.
+ */
+static inline bool rwsem_try_write_lock_unqueued(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+
+	while (!(count & (RWSEM_LOCK_MASK|RWSEM_FLAG_HANDOFF))) {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &count,
+					count | RWSEM_WRITER_LOCKED)) {
+			rwsem_set_owner(sem);
+			lockevent_inc(rwsem_opt_wlock);
+			return true;
+		}
+	}
+	return false;
+}
+
+static inline bool owner_on_cpu(struct task_struct *owner)
+{
+	/*
+	 * As lock holder preemption issue, we both skip spinning if
+	 * task is not on cpu or its cpu is preempted
+	 */
+	return owner->on_cpu && !vcpu_is_preempted(task_cpu(owner));
+}
+
+static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem,
+					   unsigned long nonspinnable)
+{
+	struct task_struct *owner;
+	unsigned long flags;
+	bool ret = true;
+
+	BUILD_BUG_ON(!(RWSEM_OWNER_UNKNOWN & RWSEM_NONSPINNABLE));
+
+	if (need_resched()) {
+		lockevent_inc(rwsem_opt_fail);
+		return false;
+	}
+
+	preempt_disable();
+	rcu_read_lock();
+	owner = rwsem_owner_flags(sem, &flags);
+	if ((flags & nonspinnable) || (owner && !owner_on_cpu(owner)))
+		ret = false;
+	rcu_read_unlock();
+	preempt_enable();
+
+	lockevent_cond_inc(rwsem_opt_fail, !ret);
+	return ret;
+}
+
+/*
+ * The rwsem_spin_on_owner() function returns the folowing 4 values
+ * depending on the lock owner state.
+ *   OWNER_NULL  : owner is currently NULL
+ *   OWNER_WRITER: when owner changes and is a writer
+ *   OWNER_READER: when owner changes and the new owner may be a reader.
+ *   OWNER_NONSPINNABLE:
+ *		   when optimistic spinning has to stop because either the
+ *		   owner stops running, is unknown, or its timeslice has
+ *		   been used up.
+ */
+enum owner_state {
+	OWNER_NULL		= 1 << 0,
+	OWNER_WRITER		= 1 << 1,
+	OWNER_READER		= 1 << 2,
+	OWNER_NONSPINNABLE	= 1 << 3,
+};
+#define OWNER_SPINNABLE		(OWNER_NULL | OWNER_WRITER | OWNER_READER)
+
+static inline enum owner_state
+rwsem_owner_state(struct task_struct *owner, unsigned long flags, unsigned long nonspinnable)
+{
+	if (flags & nonspinnable)
+		return OWNER_NONSPINNABLE;
+
+	if (flags & RWSEM_READER_OWNED)
+		return OWNER_READER;
+
+	return owner ? OWNER_WRITER : OWNER_NULL;
+}
+
+static noinline enum owner_state
+rwsem_spin_on_owner(struct rw_semaphore *sem, unsigned long nonspinnable)
+{
+	struct task_struct *new, *owner;
+	unsigned long flags, new_flags;
+	enum owner_state state;
+
+	owner = rwsem_owner_flags(sem, &flags);
+	state = rwsem_owner_state(owner, flags, nonspinnable);
+	if (state != OWNER_WRITER)
+		return state;
+
+	rcu_read_lock();
+	for (;;) {
+		if (atomic_long_read(&sem->count) & RWSEM_FLAG_HANDOFF) {
+			state = OWNER_NONSPINNABLE;
+			break;
+		}
+
+		new = rwsem_owner_flags(sem, &new_flags);
+		if ((new != owner) || (new_flags != flags)) {
+			state = rwsem_owner_state(new, new_flags, nonspinnable);
+			break;
+		}
+
+		/*
+		 * Ensure we emit the owner->on_cpu, dereference _after_
+		 * checking sem->owner still matches owner, if that fails,
+		 * owner might point to free()d memory, if it still matches,
+		 * the rcu_read_lock() ensures the memory stays valid.
+		 */
+		barrier();
+
+		if (need_resched() || !owner_on_cpu(owner)) {
+			state = OWNER_NONSPINNABLE;
+			break;
+		}
+
+		cpu_relax();
+	}
+	rcu_read_unlock();
+
+	return state;
+}
+
+/*
+ * Calculate reader-owned rwsem spinning threshold for writer
+ *
+ * The more readers own the rwsem, the longer it will take for them to
+ * wind down and free the rwsem. So the empirical formula used to
+ * determine the actual spinning time limit here is:
+ *
+ *   Spinning threshold = (10 + nr_readers/2)us
+ *
+ * The limit is capped to a maximum of 25us (30 readers). This is just
+ * a heuristic and is subjected to change in the future.
+ */
+static inline u64 rwsem_rspin_threshold(struct rw_semaphore *sem)
+{
+	long count = atomic_long_read(&sem->count);
+	int readers = count >> RWSEM_READER_SHIFT;
+	u64 delta;
+
+	if (readers > 30)
+		readers = 30;
+	delta = (20 + readers) * NSEC_PER_USEC / 2;
+
+	return sched_clock() + delta;
+}
+
+static bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
+{
+	bool taken = false;
+	int prev_owner_state = OWNER_NULL;
+	int loop = 0;
+	u64 rspin_threshold = 0;
+	unsigned long nonspinnable = wlock ? RWSEM_WR_NONSPINNABLE
+					   : RWSEM_RD_NONSPINNABLE;
+
+	preempt_disable();
+
+	/* sem->wait_lock should not be held when doing optimistic spinning */
+	if (!osq_lock(&sem->osq))
+		goto done;
+
+	/*
+	 * Optimistically spin on the owner field and attempt to acquire the
+	 * lock whenever the owner changes. Spinning will be stopped when:
+	 *  1) the owning writer isn't running; or
+	 *  2) readers own the lock and spinning time has exceeded limit.
+	 */
+	for (;;) {
+		enum owner_state owner_state;
+
+		owner_state = rwsem_spin_on_owner(sem, nonspinnable);
+		if (!(owner_state & OWNER_SPINNABLE))
+			break;
+
+		/*
+		 * Try to acquire the lock
+		 */
+		taken = wlock ? rwsem_try_write_lock_unqueued(sem)
+			      : rwsem_try_read_lock_unqueued(sem);
+
+		if (taken)
+			break;
+
+		/*
+		 * Time-based reader-owned rwsem optimistic spinning
+		 */
+		if (wlock && (owner_state == OWNER_READER)) {
+			/*
+			 * Re-initialize rspin_threshold every time when
+			 * the owner state changes from non-reader to reader.
+			 * This allows a writer to steal the lock in between
+			 * 2 reader phases and have the threshold reset at
+			 * the beginning of the 2nd reader phase.
+			 */
+			if (prev_owner_state != OWNER_READER) {
+				if (rwsem_test_oflags(sem, nonspinnable))
+					break;
+				rspin_threshold = rwsem_rspin_threshold(sem);
+				loop = 0;
+			}
+
+			/*
+			 * Check time threshold once every 16 iterations to
+			 * avoid calling sched_clock() too frequently so
+			 * as to reduce the average latency between the times
+			 * when the lock becomes free and when the spinner
+			 * is ready to do a trylock.
+			 */
+			else if (!(++loop & 0xf) && (sched_clock() > rspin_threshold)) {
+				rwsem_set_nonspinnable(sem);
+				lockevent_inc(rwsem_opt_nospin);
+				break;
+			}
+		}
+
+		/*
+		 * An RT task cannot do optimistic spinning if it cannot
+		 * be sure the lock holder is running or live-lock may
+		 * happen if the current task and the lock holder happen
+		 * to run in the same CPU. However, aborting optimistic
+		 * spinning while a NULL owner is detected may miss some
+		 * opportunity where spinning can continue without causing
+		 * problem.
+		 *
+		 * There are 2 possible cases where an RT task may be able
+		 * to continue spinning.
+		 *
+		 * 1) The lock owner is in the process of releasing the
+		 *    lock, sem->owner is cleared but the lock has not
+		 *    been released yet.
+		 * 2) The lock was free and owner cleared, but another
+		 *    task just comes in and acquire the lock before
+		 *    we try to get it. The new owner may be a spinnable
+		 *    writer.
+		 *
+		 * To take advantage of two scenarios listed agove, the RT
+		 * task is made to retry one more time to see if it can
+		 * acquire the lock or continue spinning on the new owning
+		 * writer. Of course, if the time lag is long enough or the
+		 * new owner is not a writer or spinnable, the RT task will
+		 * quit spinning.
+		 *
+		 * If the owner is a writer, the need_resched() check is
+		 * done inside rwsem_spin_on_owner(). If the owner is not
+		 * a writer, need_resched() check needs to be done here.
+		 */
+		if (owner_state != OWNER_WRITER) {
+			if (need_resched())
+				break;
+			if (rt_task(current) &&
+			   (prev_owner_state != OWNER_WRITER))
+				break;
+		}
+		prev_owner_state = owner_state;
+
+		/*
+		 * The cpu_relax() call is a compiler barrier which forces
+		 * everything in this loop to be re-loaded. We don't need
+		 * memory barriers as we'll eventually observe the right
+		 * values at the cost of a few extra spins.
+		 */
+		cpu_relax();
+	}
+	osq_unlock(&sem->osq);
+done:
+	preempt_enable();
+	lockevent_cond_inc(rwsem_opt_fail, !taken);
+	return taken;
+}
+
+/*
+ * Clear the owner's RWSEM_WR_NONSPINNABLE bit if it is set. This should
+ * only be called when the reader count reaches 0.
+ *
+ * This give writers better chance to acquire the rwsem first before
+ * readers when the rwsem was being held by readers for a relatively long
+ * period of time. Race can happen that an optimistic spinner may have
+ * just stolen the rwsem and set the owner, but just clearing the
+ * RWSEM_WR_NONSPINNABLE bit will do no harm anyway.
+ */
+static inline void clear_wr_nonspinnable(struct rw_semaphore *sem)
+{
+	if (rwsem_test_oflags(sem, RWSEM_WR_NONSPINNABLE))
+		atomic_long_andnot(RWSEM_WR_NONSPINNABLE, &sem->owner);
+}
+
+/*
+ * This function is called when the reader fails to acquire the lock via
+ * optimistic spinning. In this case we will still attempt to do a trylock
+ * when comparing the rwsem state right now with the state when entering
+ * the slowpath indicates that the reader is still in a valid reader phase.
+ * This happens when the following conditions are true:
+ *
+ * 1) The lock is currently reader owned, and
+ * 2) The lock is previously not reader-owned or the last read owner changes.
+ *
+ * In the former case, we have transitioned from a writer phase to a
+ * reader-phase while spinning. In the latter case, it means the reader
+ * phase hasn't ended when we entered the optimistic spinning loop. In
+ * both cases, the reader is eligible to acquire the lock. This is the
+ * secondary path where a read lock is acquired optimistically.
+ *
+ * The reader non-spinnable bit wasn't set at time of entry or it will
+ * not be here at all.
+ */
+static inline bool rwsem_reader_phase_trylock(struct rw_semaphore *sem,
+					      unsigned long last_rowner)
+{
+	unsigned long owner = atomic_long_read(&sem->owner);
+
+	if (!(owner & RWSEM_READER_OWNED))
+		return false;
+
+	if (((owner ^ last_rowner) & ~RWSEM_OWNER_FLAGS_MASK) &&
+	    rwsem_try_read_lock_unqueued(sem)) {
+		lockevent_inc(rwsem_opt_rlock2);
+		lockevent_add(rwsem_opt_fail, -1);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool rwsem_can_spin_on_owner(struct rw_semaphore *sem,
+					   unsigned long nonspinnable)
+{
+	return false;
+}
+
+static inline bool rwsem_optimistic_spin(struct rw_semaphore *sem, bool wlock)
+{
+	return false;
+}
+
+static inline void clear_wr_nonspinnable(struct rw_semaphore *sem) { }
+
+static inline bool rwsem_reader_phase_trylock(struct rw_semaphore *sem,
+					      unsigned long last_rowner)
+{
+	return false;
+}
+#endif
+
+/*
+ * Wait for the read lock to be granted
+ */
+static struct rw_semaphore __sched *
+rwsem_down_read_slowpath(struct rw_semaphore *sem, int state)
+{
+	long count, adjustment = -RWSEM_READER_BIAS;
+	struct rwsem_waiter waiter;
+	DEFINE_WAKE_Q(wake_q);
+	bool wake = false;
+
+	/*
+	 * Save the current read-owner of rwsem, if available, and the
+	 * reader nonspinnable bit.
+	 */
+	waiter.last_rowner = atomic_long_read(&sem->owner);
+	if (!(waiter.last_rowner & RWSEM_READER_OWNED))
+		waiter.last_rowner &= RWSEM_RD_NONSPINNABLE;
+
+	if (!rwsem_can_spin_on_owner(sem, RWSEM_RD_NONSPINNABLE))
+		goto queue;
+
+	/*
+	 * Undo read bias from down_read() and do optimistic spinning.
+	 */
+	atomic_long_add(-RWSEM_READER_BIAS, &sem->count);
+	adjustment = 0;
+	if (rwsem_optimistic_spin(sem, false)) {
+		/*
+		 * Wake up other readers in the wait list if the front
+		 * waiter is a reader.
+		 */
+		if ((atomic_long_read(&sem->count) & RWSEM_FLAG_WAITERS)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (!list_empty(&sem->wait_list))
+				rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED,
+						&wake_q);
+			raw_spin_unlock_irq(&sem->wait_lock);
+			wake_up_q(&wake_q);
+		}
+		return sem;
+	} else if (rwsem_reader_phase_trylock(sem, waiter.last_rowner)) {
+		return sem;
+	}
+
+queue:
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_READ;
+	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+	if (list_empty(&sem->wait_list)) {
+		/*
+		 * In case the wait queue is empty and the lock isn't owned
+		 * by a writer or has the handoff bit set, this reader can
+		 * exit the slowpath and return immediately as its
+		 * RWSEM_READER_BIAS has already been set in the count.
+		 */
+		if (adjustment && !(atomic_long_read(&sem->count) &
+		     (RWSEM_WRITER_MASK | RWSEM_FLAG_HANDOFF))) {
+			raw_spin_unlock_irq(&sem->wait_lock);
+			rwsem_set_reader_owned(sem);
+			lockevent_inc(rwsem_rlock_fast);
+			return sem;
+		}
+		adjustment += RWSEM_FLAG_WAITERS;
+	}
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively locking */
+	if (adjustment)
+		count = atomic_long_add_return(adjustment, &sem->count);
+	else
+		count = atomic_long_read(&sem->count);
+
+	/*
+	 * If there are no active locks, wake the front queued process(es).
+	 *
+	 * If there are no writers and we are first in the queue,
+	 * wake our own waiter to join the existing active readers !
+	 */
+	if (!(count & RWSEM_LOCK_MASK)) {
+		clear_wr_nonspinnable(sem);
+		wake = true;
+	}
+	if (wake || (!(count & RWSEM_WRITER_MASK) &&
+		    (adjustment & RWSEM_FLAG_WAITERS)))
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+
+	/* wait to be given the lock */
+	while (true) {
+		set_current_state(state);
+		if (!waiter.task)
+			break;
+		if (signal_pending_state(state, current)) {
+			raw_spin_lock_irq(&sem->wait_lock);
+			if (waiter.task)
+				goto out_nolock;
+			raw_spin_unlock_irq(&sem->wait_lock);
+			break;
+		}
+		schedule();
+		lockevent_inc(rwsem_sleep_reader);
+	}
+
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock);
+	return sem;
+out_nolock:
+	list_del(&waiter.list);
+	if (list_empty(&sem->wait_list)) {
+		atomic_long_andnot(RWSEM_FLAG_WAITERS|RWSEM_FLAG_HANDOFF,
+				   &sem->count);
+	}
+	raw_spin_unlock_irq(&sem->wait_lock);
+	__set_current_state(TASK_RUNNING);
+	lockevent_inc(rwsem_rlock_fail);
+	return ERR_PTR(-EINTR);
+}
+
+/*
+ * This function is called by the a write lock owner. So the owner value
+ * won't get changed by others.
+ */
+static inline void rwsem_disable_reader_optspin(struct rw_semaphore *sem,
+						bool disable)
+{
+	if (unlikely(disable)) {
+		atomic_long_or(RWSEM_RD_NONSPINNABLE, &sem->owner);
+		lockevent_inc(rwsem_opt_norspin);
+	}
+}
+
+/*
+ * Wait until we successfully acquire the write lock
+ */
+static struct rw_semaphore *
+rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
+{
+	long count;
+	bool disable_rspin;
+	enum writer_wait_state wstate;
+	struct rwsem_waiter waiter;
+	struct rw_semaphore *ret = sem;
+	DEFINE_WAKE_Q(wake_q);
+
+	/* do optimistic spinning and steal lock if possible */
+	if (rwsem_can_spin_on_owner(sem, RWSEM_WR_NONSPINNABLE) &&
+	    rwsem_optimistic_spin(sem, true))
+		return sem;
+
+	/*
+	 * Disable reader optimistic spinning for this rwsem after
+	 * acquiring the write lock when the setting of the nonspinnable
+	 * bits are observed.
+	 */
+	disable_rspin = atomic_long_read(&sem->owner) & RWSEM_NONSPINNABLE;
+
+	/*
+	 * Optimistic spinning failed, proceed to the slowpath
+	 * and block until we can acquire the sem.
+	 */
+	waiter.task = current;
+	waiter.type = RWSEM_WAITING_FOR_WRITE;
+	waiter.timeout = jiffies + RWSEM_WAIT_TIMEOUT;
+
+	raw_spin_lock_irq(&sem->wait_lock);
+
+	/* account for this before adding a new element to the list */
+	wstate = list_empty(&sem->wait_list) ? WRITER_FIRST : WRITER_NOT_FIRST;
+
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we're now waiting on the lock */
+	if (wstate == WRITER_NOT_FIRST) {
+		count = atomic_long_read(&sem->count);
+
+		/*
+		 * If there were already threads queued before us and:
+		 *  1) there are no no active locks, wake the front
+		 *     queued process(es) as the handoff bit might be set.
+		 *  2) there are no active writers and some readers, the lock
+		 *     must be read owned; so we try to wake any read lock
+		 *     waiters that were queued ahead of us.
+		 */
+		if (count & RWSEM_WRITER_MASK)
+			goto wait;
+
+		rwsem_mark_wake(sem, (count & RWSEM_READER_MASK)
+					? RWSEM_WAKE_READERS
+					: RWSEM_WAKE_ANY, &wake_q);
+
+		if (!wake_q_empty(&wake_q)) {
+			/*
+			 * We want to minimize wait_lock hold time especially
+			 * when a large number of readers are to be woken up.
+			 */
+			raw_spin_unlock_irq(&sem->wait_lock);
+			wake_up_q(&wake_q);
+			wake_q_init(&wake_q);	/* Used again, reinit */
+			raw_spin_lock_irq(&sem->wait_lock);
+		}
+	} else {
+		atomic_long_or(RWSEM_FLAG_WAITERS, &sem->count);
+	}
+
+wait:
+	/* wait until we successfully acquire the lock */
+	set_current_state(state);
+	while (true) {
+		if (rwsem_try_write_lock(sem, wstate))
+			break;
+
+		raw_spin_unlock_irq(&sem->wait_lock);
+
+		/* Block until there are no active lockers. */
+		for (;;) {
+			if (signal_pending_state(state, current))
+				goto out_nolock;
+
+			schedule();
+			lockevent_inc(rwsem_sleep_writer);
+			set_current_state(state);
+			/*
+			 * If HANDOFF bit is set, unconditionally do
+			 * a trylock.
+			 */
+			if (wstate == WRITER_HANDOFF)
+				break;
+
+			if ((wstate == WRITER_NOT_FIRST) &&
+			    (rwsem_first_waiter(sem) == &waiter))
+				wstate = WRITER_FIRST;
+
+			count = atomic_long_read(&sem->count);
+			if (!(count & RWSEM_LOCK_MASK))
+				break;
+
+			/*
+			 * The setting of the handoff bit is deferred
+			 * until rwsem_try_write_lock() is called.
+			 */
+			if ((wstate == WRITER_FIRST) && (rt_task(current) ||
+			    time_after(jiffies, waiter.timeout))) {
+				wstate = WRITER_HANDOFF;
+				lockevent_inc(rwsem_wlock_handoff);
+				break;
+			}
+		}
+
+		raw_spin_lock_irq(&sem->wait_lock);
+	}
+	__set_current_state(TASK_RUNNING);
+	list_del(&waiter.list);
+	rwsem_disable_reader_optspin(sem, disable_rspin);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	lockevent_inc(rwsem_wlock);
+
+	return ret;
+
+out_nolock:
+	__set_current_state(TASK_RUNNING);
+	raw_spin_lock_irq(&sem->wait_lock);
+	list_del(&waiter.list);
+
+	if (unlikely(wstate == WRITER_HANDOFF))
+		atomic_long_add(-RWSEM_FLAG_HANDOFF,  &sem->count);
+
+	if (list_empty(&sem->wait_list))
+		atomic_long_andnot(RWSEM_FLAG_WAITERS, &sem->count);
+	else
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+	raw_spin_unlock_irq(&sem->wait_lock);
+	wake_up_q(&wake_q);
+	lockevent_inc(rwsem_wlock_fail);
+
+	return ERR_PTR(-EINTR);
+}
+
+/*
+ * handle waking up a waiter on the semaphore
+ * - up_read/up_write has decremented the active part of count if we come here
+ */
+static struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem, long count)
+{
+	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (!list_empty(&sem->wait_list))
+		rwsem_mark_wake(sem, RWSEM_WAKE_ANY, &wake_q);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	wake_up_q(&wake_q);
+
+	return sem;
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - caller incremented waiting part of count and discovered it still negative
+ * - just wake up any readers at the front of the queue
+ */
+static struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	DEFINE_WAKE_Q(wake_q);
+
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (!list_empty(&sem->wait_list))
+		rwsem_mark_wake(sem, RWSEM_WAKE_READ_OWNED, &wake_q);
+
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
+	wake_up_q(&wake_q);
+
+	return sem;
+}
+
+/*
+ * lock for reading
+ */
+inline void __down_read(struct rw_semaphore *sem)
+{
+	if (!rwsem_read_trylock(sem)) {
+		rwsem_down_read_slowpath(sem, TASK_UNINTERRUPTIBLE);
+		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+}
+
+static inline int __down_read_killable(struct rw_semaphore *sem)
+{
+	if (!rwsem_read_trylock(sem)) {
+		if (IS_ERR(rwsem_down_read_slowpath(sem, TASK_KILLABLE)))
+			return -EINTR;
+		DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+	} else {
+		rwsem_set_reader_owned(sem);
+	}
+	return 0;
+}
+
+static inline int __down_read_trylock(struct rw_semaphore *sem)
+{
+	/*
+	 * Optimize for the case when the rwsem is not locked at all.
+	 */
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	do {
+		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					tmp + RWSEM_READER_BIAS)) {
+			rwsem_set_reader_owned(sem);
+			return 1;
+		}
+	} while (!(tmp & RWSEM_READ_FAILED_MASK));
+	return 0;
+}
+
+/*
+ * lock for writing
+ */
+static inline void __down_write(struct rw_semaphore *sem)
+{
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	if (unlikely(!atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+						      RWSEM_WRITER_LOCKED)))
+		rwsem_down_write_slowpath(sem, TASK_UNINTERRUPTIBLE);
+	else
+		rwsem_set_owner(sem);
+}
+
+static inline int __down_write_killable(struct rw_semaphore *sem)
+{
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	if (unlikely(!atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+						      RWSEM_WRITER_LOCKED))) {
+		if (IS_ERR(rwsem_down_write_slowpath(sem, TASK_KILLABLE)))
+			return -EINTR;
+	} else {
+		rwsem_set_owner(sem);
+	}
+	return 0;
+}
+
+static inline int __down_write_trylock(struct rw_semaphore *sem)
+{
+	long tmp = RWSEM_UNLOCKED_VALUE;
+
+	if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
+					    RWSEM_WRITER_LOCKED)) {
+		rwsem_set_owner(sem);
+		return true;
+	}
+	return false;
+}
+
+/*
+ * unlock after reading
+ */
+inline void __up_read(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
+	rwsem_clear_reader_owned(sem);
+	tmp = atomic_long_add_return_release(-RWSEM_READER_BIAS, &sem->count);
+	DEBUG_RWSEMS_WARN_ON(tmp < 0, sem);
+	if (unlikely((tmp & (RWSEM_LOCK_MASK|RWSEM_FLAG_WAITERS)) ==
+		      RWSEM_FLAG_WAITERS)) {
+		clear_wr_nonspinnable(sem);
+		rwsem_wake(sem, tmp);
+	}
+}
+
+/*
+ * unlock after writing
+ */
+static inline void __up_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	/*
+	 * sem->owner may differ from current if the ownership is transferred
+	 * to an anonymous writer by setting the RWSEM_NONSPINNABLE bits.
+	 */
+	DEBUG_RWSEMS_WARN_ON((rwsem_owner(sem) != current) &&
+			    !rwsem_test_oflags(sem, RWSEM_NONSPINNABLE), sem);
+	rwsem_clear_owner(sem);
+	tmp = atomic_long_fetch_add_release(-RWSEM_WRITER_LOCKED, &sem->count);
+	if (unlikely(tmp & RWSEM_FLAG_WAITERS))
+		rwsem_wake(sem, tmp);
+}
+
+/*
+ * downgrade write lock to read lock
+ */
+static inline void __downgrade_write(struct rw_semaphore *sem)
+{
+	long tmp;
+
+	/*
+	 * When downgrading from exclusive to shared ownership,
+	 * anything inside the write-locked region cannot leak
+	 * into the read side. In contrast, anything in the
+	 * read-locked region is ok to be re-ordered into the
+	 * write side. As such, rely on RELEASE semantics.
+	 */
+	DEBUG_RWSEMS_WARN_ON(rwsem_owner(sem) != current, sem);
+	tmp = atomic_long_fetch_add_release(
+		-RWSEM_WRITER_LOCKED+RWSEM_READER_BIAS, &sem->count);
+	rwsem_set_reader_owned(sem);
+	if (tmp & RWSEM_FLAG_WAITERS)
+		rwsem_downgrade_wake(sem);
+}
 
 /*
  * lock for reading
@@ -25,7 +1446,6 @@ void __sched down_read(struct rw_semaphore *sem)
 
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
 }
-
 EXPORT_SYMBOL(down_read);
 
 int __sched down_read_killable(struct rw_semaphore *sem)
@@ -40,7 +1460,6 @@ int __sched down_read_killable(struct rw_semaphore *sem)
 
 	return 0;
 }
-
 EXPORT_SYMBOL(down_read_killable);
 
 /*
@@ -54,7 +1473,6 @@ int down_read_trylock(struct rw_semaphore *sem)
 		rwsem_acquire_read(&sem->dep_map, 0, 1, _RET_IP_);
 	return ret;
 }
-
 EXPORT_SYMBOL(down_read_trylock);
 
 /*
@@ -64,10 +1482,8 @@ void __sched down_write(struct rw_semaphore *sem)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
 }
-
 EXPORT_SYMBOL(down_write);
 
 /*
@@ -78,14 +1494,14 @@ int __sched down_write_killable(struct rw_semaphore *sem)
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, 0, 0, _RET_IP_);
 
-	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
+				  __down_write_killable)) {
 		rwsem_release(&sem->dep_map, 1, _RET_IP_);
 		return -EINTR;
 	}
 
 	return 0;
 }
-
 EXPORT_SYMBOL(down_write_killable);
 
 /*
@@ -100,7 +1516,6 @@ int down_write_trylock(struct rw_semaphore *sem)
 
 	return ret;
 }
-
 EXPORT_SYMBOL(down_write_trylock);
 
 /*
@@ -109,10 +1524,8 @@ EXPORT_SYMBOL(down_write_trylock);
 void up_read(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-
 	__up_read(sem);
 }
-
 EXPORT_SYMBOL(up_read);
 
 /*
@@ -121,10 +1534,8 @@ EXPORT_SYMBOL(up_read);
 void up_write(struct rw_semaphore *sem)
 {
 	rwsem_release(&sem->dep_map, 1, _RET_IP_);
-
 	__up_write(sem);
 }
-
 EXPORT_SYMBOL(up_write);
 
 /*
@@ -133,10 +1544,8 @@ EXPORT_SYMBOL(up_write);
 void downgrade_write(struct rw_semaphore *sem)
 {
 	lock_downgrade(&sem->dep_map, _RET_IP_);
-
 	__downgrade_write(sem);
 }
-
 EXPORT_SYMBOL(downgrade_write);
 
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
@@ -145,40 +1554,32 @@ void down_read_nested(struct rw_semaphore *sem, int subclass)
 {
 	might_sleep();
 	rwsem_acquire_read(&sem->dep_map, subclass, 0, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_read_trylock, __down_read);
 }
-
 EXPORT_SYMBOL(down_read_nested);
 
 void _down_write_nest_lock(struct rw_semaphore *sem, struct lockdep_map *nest)
 {
 	might_sleep();
 	rwsem_acquire_nest(&sem->dep_map, 0, 0, nest, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
 }
-
 EXPORT_SYMBOL(_down_write_nest_lock);
 
 void down_read_non_owner(struct rw_semaphore *sem)
 {
 	might_sleep();
-
 	__down_read(sem);
 	__rwsem_set_reader_owned(sem, NULL);
 }
-
 EXPORT_SYMBOL(down_read_non_owner);
 
 void down_write_nested(struct rw_semaphore *sem, int subclass)
 {
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
-
 	LOCK_CONTENDED(sem, __down_write_trylock, __down_write);
 }
-
 EXPORT_SYMBOL(down_write_nested);
 
 int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
@@ -186,23 +1587,21 @@ int __sched down_write_killable_nested(struct rw_semaphore *sem, int subclass)
 	might_sleep();
 	rwsem_acquire(&sem->dep_map, subclass, 0, _RET_IP_);
 
-	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock, __down_write_killable)) {
+	if (LOCK_CONTENDED_RETURN(sem, __down_write_trylock,
+				  __down_write_killable)) {
 		rwsem_release(&sem->dep_map, 1, _RET_IP_);
 		return -EINTR;
 	}
 
 	return 0;
 }
-
 EXPORT_SYMBOL(down_write_killable_nested);
 
 void up_read_non_owner(struct rw_semaphore *sem)
 {
-	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
-				sem);
+	DEBUG_RWSEMS_WARN_ON(!is_rwsem_reader_owned(sem), sem);
 	__up_read(sem);
 }
-
 EXPORT_SYMBOL(up_read_non_owner);
 
 #endif
diff --git a/kernel/locking/rwsem.h b/kernel/locking/rwsem.h
index 64877f5294e3..2534ce49f648 100644
--- a/kernel/locking/rwsem.h
+++ b/kernel/locking/rwsem.h
@@ -1,304 +1,10 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * The least significant 2 bits of the owner value has the following
- * meanings when set.
- *  - RWSEM_READER_OWNED (bit 0): The rwsem is owned by readers
- *  - RWSEM_ANONYMOUSLY_OWNED (bit 1): The rwsem is anonymously owned,
- *    i.e. the owner(s) cannot be readily determined. It can be reader
- *    owned or the owning writer is indeterminate.
- *
- * When a writer acquires a rwsem, it puts its task_struct pointer
- * into the owner field. It is cleared after an unlock.
- *
- * When a reader acquires a rwsem, it will also puts its task_struct
- * pointer into the owner field with both the RWSEM_READER_OWNED and
- * RWSEM_ANONYMOUSLY_OWNED bits set. On unlock, the owner field will
- * largely be left untouched. So for a free or reader-owned rwsem,
- * the owner value may contain information about the last reader that
- * acquires the rwsem. The anonymous bit is set because that particular
- * reader may or may not still own the lock.
- *
- * That information may be helpful in debugging cases where the system
- * seems to hang on a reader owned rwsem especially if only one reader
- * is involved. Ideally we would like to track all the readers that own
- * a rwsem, but the overhead is simply too big.
- */
-#include "lock_events.h"
 
-#define RWSEM_READER_OWNED	(1UL << 0)
-#define RWSEM_ANONYMOUSLY_OWNED	(1UL << 1)
+#ifndef __INTERNAL_RWSEM_H
+#define __INTERNAL_RWSEM_H
+#include <linux/rwsem.h>
 
-#ifdef CONFIG_DEBUG_RWSEMS
-# define DEBUG_RWSEMS_WARN_ON(c, sem)	do {			\
-	if (!debug_locks_silent &&				\
-	    WARN_ONCE(c, "DEBUG_RWSEMS_WARN_ON(%s): count = 0x%lx, owner = 0x%lx, curr 0x%lx, list %sempty\n",\
-		#c, atomic_long_read(&(sem)->count),		\
-		(long)((sem)->owner), (long)current,		\
-		list_empty(&(sem)->wait_list) ? "" : "not "))	\
-			debug_locks_off();			\
-	} while (0)
-#else
-# define DEBUG_RWSEMS_WARN_ON(c, sem)
-#endif
+extern void __down_read(struct rw_semaphore *sem);
+extern void __up_read(struct rw_semaphore *sem);
 
-/*
- * R/W semaphores originally for PPC using the stuff in lib/rwsem.c.
- * Adapted largely from include/asm-i386/rwsem.h
- * by Paul Mackerras <paulus@samba.org>.
- */
-
-/*
- * the semaphore definition
- */
-#ifdef CONFIG_64BIT
-# define RWSEM_ACTIVE_MASK		0xffffffffL
-#else
-# define RWSEM_ACTIVE_MASK		0x0000ffffL
-#endif
-
-#define RWSEM_ACTIVE_BIAS		0x00000001L
-#define RWSEM_WAITING_BIAS		(-RWSEM_ACTIVE_MASK-1)
-#define RWSEM_ACTIVE_READ_BIAS		RWSEM_ACTIVE_BIAS
-#define RWSEM_ACTIVE_WRITE_BIAS		(RWSEM_WAITING_BIAS + RWSEM_ACTIVE_BIAS)
-
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-/*
- * All writes to owner are protected by WRITE_ONCE() to make sure that
- * store tearing can't happen as optimistic spinners may read and use
- * the owner value concurrently without lock. Read from owner, however,
- * may not need READ_ONCE() as long as the pointer value is only used
- * for comparison and isn't being dereferenced.
- */
-static inline void rwsem_set_owner(struct rw_semaphore *sem)
-{
-	WRITE_ONCE(sem->owner, current);
-}
-
-static inline void rwsem_clear_owner(struct rw_semaphore *sem)
-{
-	WRITE_ONCE(sem->owner, NULL);
-}
-
-/*
- * The task_struct pointer of the last owning reader will be left in
- * the owner field.
- *
- * Note that the owner value just indicates the task has owned the rwsem
- * previously, it may not be the real owner or one of the real owners
- * anymore when that field is examined, so take it with a grain of salt.
- */
-static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
-					    struct task_struct *owner)
-{
-	unsigned long val = (unsigned long)owner | RWSEM_READER_OWNED
-						 | RWSEM_ANONYMOUSLY_OWNED;
-
-	WRITE_ONCE(sem->owner, (struct task_struct *)val);
-}
-
-static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
-{
-	__rwsem_set_reader_owned(sem, current);
-}
-
-/*
- * Return true if the a rwsem waiter can spin on the rwsem's owner
- * and steal the lock, i.e. the lock is not anonymously owned.
- * N.B. !owner is considered spinnable.
- */
-static inline bool is_rwsem_owner_spinnable(struct task_struct *owner)
-{
-	return !((unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED);
-}
-
-/*
- * Return true if rwsem is owned by an anonymous writer or readers.
- */
-static inline bool rwsem_has_anonymous_owner(struct task_struct *owner)
-{
-	return (unsigned long)owner & RWSEM_ANONYMOUSLY_OWNED;
-}
-
-#ifdef CONFIG_DEBUG_RWSEMS
-/*
- * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
- * is a task pointer in owner of a reader-owned rwsem, it will be the
- * real owner or one of the real owners. The only exception is when the
- * unlock is done by up_read_non_owner().
- */
-#define rwsem_clear_reader_owned rwsem_clear_reader_owned
-static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
-{
-	unsigned long val = (unsigned long)current | RWSEM_READER_OWNED
-						   | RWSEM_ANONYMOUSLY_OWNED;
-	if (READ_ONCE(sem->owner) == (struct task_struct *)val)
-		cmpxchg_relaxed((unsigned long *)&sem->owner, val,
-				RWSEM_READER_OWNED | RWSEM_ANONYMOUSLY_OWNED);
-}
-#endif
-
-#else
-static inline void rwsem_set_owner(struct rw_semaphore *sem)
-{
-}
-
-static inline void rwsem_clear_owner(struct rw_semaphore *sem)
-{
-}
-
-static inline void __rwsem_set_reader_owned(struct rw_semaphore *sem,
-					   struct task_struct *owner)
-{
-}
-
-static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
-{
-}
-#endif
-
-#ifndef rwsem_clear_reader_owned
-static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
-{
-}
-#endif
-
-extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem);
-extern struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem);
-
-/*
- * lock for reading
- */
-static inline void __down_read(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
-		rwsem_down_read_failed(sem);
-		DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
-					RWSEM_READER_OWNED), sem);
-	} else {
-		rwsem_set_reader_owned(sem);
-	}
-}
-
-static inline int __down_read_killable(struct rw_semaphore *sem)
-{
-	if (unlikely(atomic_long_inc_return_acquire(&sem->count) <= 0)) {
-		if (IS_ERR(rwsem_down_read_failed_killable(sem)))
-			return -EINTR;
-		DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner &
-					RWSEM_READER_OWNED), sem);
-	} else {
-		rwsem_set_reader_owned(sem);
-	}
-	return 0;
-}
-
-static inline int __down_read_trylock(struct rw_semaphore *sem)
-{
-	/*
-	 * Optimize for the case when the rwsem is not locked at all.
-	 */
-	long tmp = RWSEM_UNLOCKED_VALUE;
-
-	lockevent_inc(rwsem_rtrylock);
-	do {
-		if (atomic_long_try_cmpxchg_acquire(&sem->count, &tmp,
-					tmp + RWSEM_ACTIVE_READ_BIAS)) {
-			rwsem_set_reader_owned(sem);
-			return 1;
-		}
-	} while (tmp >= 0);
-	return 0;
-}
-
-/*
- * lock for writing
- */
-static inline void __down_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-					     &sem->count);
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		rwsem_down_write_failed(sem);
-	rwsem_set_owner(sem);
-}
-
-static inline int __down_write_killable(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	tmp = atomic_long_add_return_acquire(RWSEM_ACTIVE_WRITE_BIAS,
-					     &sem->count);
-	if (unlikely(tmp != RWSEM_ACTIVE_WRITE_BIAS))
-		if (IS_ERR(rwsem_down_write_failed_killable(sem)))
-			return -EINTR;
-	rwsem_set_owner(sem);
-	return 0;
-}
-
-static inline int __down_write_trylock(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	lockevent_inc(rwsem_wtrylock);
-	tmp = atomic_long_cmpxchg_acquire(&sem->count, RWSEM_UNLOCKED_VALUE,
-		      RWSEM_ACTIVE_WRITE_BIAS);
-	if (tmp == RWSEM_UNLOCKED_VALUE) {
-		rwsem_set_owner(sem);
-		return true;
-	}
-	return false;
-}
-
-/*
- * unlock after reading
- */
-static inline void __up_read(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	DEBUG_RWSEMS_WARN_ON(!((unsigned long)sem->owner & RWSEM_READER_OWNED),
-				sem);
-	rwsem_clear_reader_owned(sem);
-	tmp = atomic_long_dec_return_release(&sem->count);
-	if (unlikely(tmp < -1 && (tmp & RWSEM_ACTIVE_MASK) == 0))
-		rwsem_wake(sem);
-}
-
-/*
- * unlock after writing
- */
-static inline void __up_write(struct rw_semaphore *sem)
-{
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
-	rwsem_clear_owner(sem);
-	if (unlikely(atomic_long_sub_return_release(RWSEM_ACTIVE_WRITE_BIAS,
-						    &sem->count) < 0))
-		rwsem_wake(sem);
-}
-
-/*
- * downgrade write lock to read lock
- */
-static inline void __downgrade_write(struct rw_semaphore *sem)
-{
-	long tmp;
-
-	/*
-	 * When downgrading from exclusive to shared ownership,
-	 * anything inside the write-locked region cannot leak
-	 * into the read side. In contrast, anything in the
-	 * read-locked region is ok to be re-ordered into the
-	 * write side. As such, rely on RELEASE semantics.
-	 */
-	DEBUG_RWSEMS_WARN_ON(sem->owner != current, sem);
-	tmp = atomic_long_add_return_release(-RWSEM_WAITING_BIAS, &sem->count);
-	rwsem_set_reader_owned(sem);
-	if (tmp < 0)
-		rwsem_downgrade_wake(sem);
-}
+#endif /* __INTERNAL_RWSEM_H */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f35930f5e528..8591529e1753 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6189,6 +6189,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	u64 time, cost;
 	s64 delta;
 	int cpu, nr = INT_MAX;
+	int this = smp_processor_id();
 
 	this_sd = rcu_dereference(*this_cpu_ptr(&sd_llc));
 	if (!this_sd)
@@ -6212,7 +6213,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 			nr = 4;
 	}
 
-	time = local_clock();
+	time = cpu_clock(this);
 
 	for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
 		if (!--nr)
@@ -6223,7 +6224,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 			break;
 	}
 
-	time = local_clock() - time;
+	time = cpu_clock(this) - time;
 	cost = this_sd->avg_scan_cost;
 	delta = (s64)(time - cost) / 8;
 	this_sd->avg_scan_cost += delta;
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 6629cab453e8..06d9c9d70385 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -1095,7 +1095,7 @@ config PROVE_LOCKING
 	select DEBUG_SPINLOCK
 	select DEBUG_MUTEXES
 	select DEBUG_RT_MUTEXES if RT_MUTEXES
-	select DEBUG_RWSEMS if RWSEM_SPIN_ON_OWNER
+	select DEBUG_RWSEMS
 	select DEBUG_WW_MUTEX_SLOWPATH
 	select DEBUG_LOCK_ALLOC
 	select TRACE_IRQFLAGS
@@ -1199,10 +1199,10 @@ config DEBUG_WW_MUTEX_SLOWPATH
 
 config DEBUG_RWSEMS
 	bool "RW Semaphore debugging: basic checks"
-	depends on DEBUG_KERNEL && RWSEM_SPIN_ON_OWNER
+	depends on DEBUG_KERNEL
 	help
-	  This debugging feature allows mismatched rw semaphore locks and unlocks
-	  to be detected and reported.
+	  This debugging feature allows mismatched rw semaphore locks
+	  and unlocks to be detected and reported.
 
 config DEBUG_LOCK_ALLOC
 	bool "Lock debugging: detect incorrect freeing of live locks"
diff --git a/lib/atomic64.c b/lib/atomic64.c
index 7e6905751522..e98c85a99787 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -42,11 +42,11 @@ static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 	return &atomic64_lock[addr & (NR_LOCKS - 1)].lock;
 }
 
-long long atomic64_read(const atomic64_t *v)
+s64 atomic64_read(const atomic64_t *v)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
@@ -55,7 +55,7 @@ long long atomic64_read(const atomic64_t *v)
 }
 EXPORT_SYMBOL(atomic64_read);
 
-void atomic64_set(atomic64_t *v, long long i)
+void atomic64_set(atomic64_t *v, s64 i)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
@@ -67,7 +67,7 @@ void atomic64_set(atomic64_t *v, long long i)
 EXPORT_SYMBOL(atomic64_set);
 
 #define ATOMIC64_OP(op, c_op)						\
-void atomic64_##op(long long a, atomic64_t *v)				\
+void atomic64_##op(s64 a, atomic64_t *v)				\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
@@ -79,11 +79,11 @@ void atomic64_##op(long long a, atomic64_t *v)				\
 EXPORT_SYMBOL(atomic64_##op);
 
 #define ATOMIC64_OP_RETURN(op, c_op)					\
-long long atomic64_##op##_return(long long a, atomic64_t *v)		\
+s64 atomic64_##op##_return(s64 a, atomic64_t *v)			\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
-	long long val;							\
+	s64 val;							\
 									\
 	raw_spin_lock_irqsave(lock, flags);				\
 	val = (v->counter c_op a);					\
@@ -93,11 +93,11 @@ long long atomic64_##op##_return(long long a, atomic64_t *v)		\
 EXPORT_SYMBOL(atomic64_##op##_return);
 
 #define ATOMIC64_FETCH_OP(op, c_op)					\
-long long atomic64_fetch_##op(long long a, atomic64_t *v)		\
+s64 atomic64_fetch_##op(s64 a, atomic64_t *v)				\
 {									\
 	unsigned long flags;						\
 	raw_spinlock_t *lock = lock_addr(v);				\
-	long long val;							\
+	s64 val;							\
 									\
 	raw_spin_lock_irqsave(lock, flags);				\
 	val = v->counter;						\
@@ -130,11 +130,11 @@ ATOMIC64_OPS(xor, ^=)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-long long atomic64_dec_if_positive(atomic64_t *v)
+s64 atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter - 1;
@@ -145,11 +145,11 @@ long long atomic64_dec_if_positive(atomic64_t *v)
 }
 EXPORT_SYMBOL(atomic64_dec_if_positive);
 
-long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
@@ -160,11 +160,11 @@ long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
 }
 EXPORT_SYMBOL(atomic64_cmpxchg);
 
-long long atomic64_xchg(atomic64_t *v, long long new)
+s64 atomic64_xchg(atomic64_t *v, s64 new)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
@@ -174,11 +174,11 @@ long long atomic64_xchg(atomic64_t *v, long long new)
 }
 EXPORT_SYMBOL(atomic64_xchg);
 
-long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u)
+s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
 {
 	unsigned long flags;
 	raw_spinlock_t *lock = lock_addr(v);
-	long long val;
+	s64 val;
 
 	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
diff --git a/scripts/atomic/check-atomics.sh b/scripts/atomic/check-atomics.sh
index cfa0c2f71c84..8378c63a1e09 100755
--- a/scripts/atomic/check-atomics.sh
+++ b/scripts/atomic/check-atomics.sh
@@ -22,7 +22,7 @@ while read header; do
 	OLDSUM="$(tail -n 1 ${LINUXDIR}/include/${header})"
 	OLDSUM="${OLDSUM#// }"
 
-	NEWSUM="$(head -n -1 ${LINUXDIR}/include/${header} | sha1sum)"
+	NEWSUM="$(sed '$d' ${LINUXDIR}/include/${header} | sha1sum)"
 	NEWSUM="${NEWSUM%% *}"
 
 	if [ "${OLDSUM}" != "${NEWSUM}" ]; then
diff --git a/security/apparmor/label.c b/security/apparmor/label.c
index 068e93c5d29c..59f1cc2557a7 100644
--- a/security/apparmor/label.c
+++ b/security/apparmor/label.c
@@ -76,7 +76,7 @@ void __aa_proxy_redirect(struct aa_label *orig, struct aa_label *new)
 
 	AA_BUG(!orig);
 	AA_BUG(!new);
-	lockdep_assert_held_exclusive(&labels_set(orig)->lock);
+	lockdep_assert_held_write(&labels_set(orig)->lock);
 
 	tmp = rcu_dereference_protected(orig->proxy->label,
 					&labels_ns(orig)->lock);
@@ -566,7 +566,7 @@ static bool __label_remove(struct aa_label *label, struct aa_label *new)
 
 	AA_BUG(!ls);
 	AA_BUG(!label);
-	lockdep_assert_held_exclusive(&ls->lock);
+	lockdep_assert_held_write(&ls->lock);
 
 	if (new)
 		__aa_proxy_redirect(label, new);
@@ -603,7 +603,7 @@ static bool __label_replace(struct aa_label *old, struct aa_label *new)
 	AA_BUG(!ls);
 	AA_BUG(!old);
 	AA_BUG(!new);
-	lockdep_assert_held_exclusive(&ls->lock);
+	lockdep_assert_held_write(&ls->lock);
 	AA_BUG(new->flags & FLAG_IN_TREE);
 
 	if (!label_is_stale(old))
@@ -640,7 +640,7 @@ static struct aa_label *__label_insert(struct aa_labelset *ls,
 	AA_BUG(!ls);
 	AA_BUG(!label);
 	AA_BUG(labels_set(label) != ls);
-	lockdep_assert_held_exclusive(&ls->lock);
+	lockdep_assert_held_write(&ls->lock);
 	AA_BUG(label->flags & FLAG_IN_TREE);
 
 	/* Figure out where to put new node */