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

Pull locking and atomic updates from Ingo Molnar:
 "Main changes in this cycle are:

   - Extend atomic primitives with coherent logic op primitives
     (atomic_{or,and,xor}()) and deprecate the old partial APIs
     (atomic_{set,clear}_mask())

     The old ops were incoherent with incompatible signatures across
     architectures and with incomplete support.  Now every architecture
     supports the primitives consistently (by Peter Zijlstra)

   - Generic support for 'relaxed atomics':

       - _acquire/release/relaxed() flavours of xchg(), cmpxchg() and {add,sub}_return()
       - atomic_read_acquire()
       - atomic_set_release()

     This came out of porting qwrlock code to arm64 (by Will Deacon)

   - Clean up the fragile static_key APIs that were causing repeat bugs,
     by introducing a new one:

       DEFINE_STATIC_KEY_TRUE(name);
       DEFINE_STATIC_KEY_FALSE(name);

     which define a key of different types with an initial true/false
     value.

     Then allow:

       static_branch_likely()
       static_branch_unlikely()

     to take a key of either type and emit the right instruction for the
     case.  To be able to know the 'type' of the static key we encode it
     in the jump entry (by Peter Zijlstra)

   - Static key self-tests (by Jason Baron)

   - qrwlock optimizations (by Waiman Long)

   - small futex enhancements (by Davidlohr Bueso)

   - ... and misc other changes"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (63 commits)
  jump_label/x86: Work around asm build bug on older/backported GCCs
  locking, ARM, atomics: Define our SMP atomics in terms of _relaxed() operations
  locking, include/llist: Use linux/atomic.h instead of asm/cmpxchg.h
  locking/qrwlock: Make use of _{acquire|release|relaxed}() atomics
  locking/qrwlock: Implement queue_write_unlock() using smp_store_release()
  locking/lockref: Remove homebrew cmpxchg64_relaxed() macro definition
  locking, asm-generic: Add _{relaxed|acquire|release}() variants for 'atomic_long_t'
  locking, asm-generic: Rework atomic-long.h to avoid bulk code duplication
  locking/atomics: Add _{acquire|release|relaxed}() variants of some atomic operations
  locking, compiler.h: Cast away attributes in the WRITE_ONCE() magic
  locking/static_keys: Make verify_keys() static
  jump label, locking/static_keys: Update docs
  locking/static_keys: Provide a selftest
  jump_label: Provide a self-test
  s390/uaccess, locking/static_keys: employ static_branch_likely()
  x86, tsc, locking/static_keys: Employ static_branch_likely()
  locking/static_keys: Add selftest
  locking/static_keys: Add a new static_key interface
  locking/static_keys: Rework update logic
  locking/static_keys: Add static_key_{en,dis}able() helpers
  ...

4 files changed, 57 insertions, 70 deletions

diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index e22c11970b7b..fe3ef397f5a4 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -57,12 +57,11 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 }									\
 
 #define ATOMIC_OP_RETURN(op, c_op, asm_op)				\
-static inline int atomic_##op##_return(int i, atomic_t *v)		\
+static inline int atomic_##op##_return_relaxed(int i, atomic_t *v)	\
 {									\
 	unsigned long tmp;						\
 	int result;							\
 									\
-	smp_mb();							\
 	prefetchw(&v->counter);						\
 									\
 	__asm__ __volatile__("@ atomic_" #op "_return\n"		\
@@ -75,17 +74,17 @@ static inline int atomic_##op##_return(int i, atomic_t *v)		\
 	: "r" (&v->counter), "Ir" (i)					\
 	: "cc");							\
 									\
-	smp_mb();							\
-									\
 	return result;							\
 }
 
-static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+
+static inline int atomic_cmpxchg_relaxed(atomic_t *ptr, int old, int new)
 {
 	int oldval;
 	unsigned long res;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	do {
@@ -99,10 +98,9 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 		    : "cc");
 	} while (res);
 
-	smp_mb();
-
 	return oldval;
 }
+#define atomic_cmpxchg_relaxed		atomic_cmpxchg_relaxed
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
@@ -194,6 +192,13 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 ATOMIC_OPS(add, +=, add)
 ATOMIC_OPS(sub, -=, sub)
 
+#define atomic_andnot atomic_andnot
+
+ATOMIC_OP(and, &=, and)
+ATOMIC_OP(andnot, &= ~, bic)
+ATOMIC_OP(or,  |=, orr)
+ATOMIC_OP(xor, ^=, eor)
+
 #undef ATOMIC_OPS
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
@@ -290,12 +295,12 @@ 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(long long i, atomic64_t *v) \
+static inline long long							\
+atomic64_##op##_return_relaxed(long long i, atomic64_t *v)		\
 {									\
 	long long result;						\
 	unsigned long tmp;						\
 									\
-	smp_mb();							\
 	prefetchw(&v->counter);						\
 									\
 	__asm__ __volatile__("@ atomic64_" #op "_return\n"		\
@@ -309,8 +314,6 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 	: "r" (&v->counter), "r" (i)					\
 	: "cc");							\
 									\
-	smp_mb();							\
-									\
 	return result;							\
 }
 
@@ -321,17 +324,26 @@ static inline long long atomic64_##op##_return(long long i, atomic64_t *v) \
 ATOMIC64_OPS(add, adds, adc)
 ATOMIC64_OPS(sub, subs, sbc)
 
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+
+#define atomic64_andnot atomic64_andnot
+
+ATOMIC64_OP(and, and, and)
+ATOMIC64_OP(andnot, bic, bic)
+ATOMIC64_OP(or,  orr, orr)
+ATOMIC64_OP(xor, eor, eor)
+
 #undef ATOMIC64_OPS
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
-					long long new)
+static inline long long
+atomic64_cmpxchg_relaxed(atomic64_t *ptr, long long old, long long new)
 {
 	long long oldval;
 	unsigned long res;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	do {
@@ -346,17 +358,15 @@ static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
 		: "cc");
 	} while (res);
 
-	smp_mb();
-
 	return oldval;
 }
+#define atomic64_cmpxchg_relaxed	atomic64_cmpxchg_relaxed
 
-static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
+static inline long long atomic64_xchg_relaxed(atomic64_t *ptr, long long new)
 {
 	long long result;
 	unsigned long tmp;
 
-	smp_mb();
 	prefetchw(&ptr->counter);
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
@@ -368,10 +378,9 @@ static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
 	: "r" (&ptr->counter), "r" (new)
 	: "cc");
 
-	smp_mb();
-
 	return result;
 }
+#define atomic64_xchg_relaxed		atomic64_xchg_relaxed
 
 static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
diff --git a/arch/arm/include/asm/barrier.h b/arch/arm/include/asm/barrier.h
index 6c2327e1c732..70393574e0fa 100644
--- a/arch/arm/include/asm/barrier.h
+++ b/arch/arm/include/asm/barrier.h
@@ -67,12 +67,12 @@
 do {									\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
-	ACCESS_ONCE(*p) = (v);						\
+	WRITE_ONCE(*p, v);						\
 } while (0)
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1 = ACCESS_ONCE(*p);				\
+	typeof(*p) ___p1 = READ_ONCE(*p);				\
 	compiletime_assert_atomic_type(*p);				\
 	smp_mb();							\
 	___p1;								\
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 1692a05d3207..916a2744d5c6 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -35,7 +35,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	unsigned int tmp;
 #endif
 
-	smp_mb();
 	prefetchw((const void *)ptr);
 
 	switch (size) {
@@ -98,12 +97,11 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
-	smp_mb();
 
 	return ret;
 }
 
-#define xchg(ptr, x) ({							\
+#define xchg_relaxed(ptr, x) ({						\
 	(__typeof__(*(ptr)))__xchg((unsigned long)(x), (ptr),		\
 				   sizeof(*(ptr)));			\
 })
@@ -117,6 +115,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 #error "SMP is not supported on this platform"
 #endif
 
+#define xchg xchg_relaxed
+
 /*
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
@@ -194,23 +194,11 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	return oldval;
 }
 
-static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
-					 unsigned long new, int size)
-{
-	unsigned long ret;
-
-	smp_mb();
-	ret = __cmpxchg(ptr, old, new, size);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg(ptr,o,n) ({						\
-	(__typeof__(*(ptr)))__cmpxchg_mb((ptr),				\
-					 (unsigned long)(o),		\
-					 (unsigned long)(n),		\
-					 sizeof(*(ptr)));		\
+#define cmpxchg_relaxed(ptr,o,n) ({					\
+	(__typeof__(*(ptr)))__cmpxchg((ptr),				\
+				      (unsigned long)(o),		\
+				      (unsigned long)(n),		\
+				      sizeof(*(ptr)));			\
 })
 
 static inline unsigned long __cmpxchg_local(volatile void *ptr,
@@ -273,25 +261,6 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 
 #define cmpxchg64_local(ptr, o, n) cmpxchg64_relaxed((ptr), (o), (n))
 
-static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
-						unsigned long long old,
-						unsigned long long new)
-{
-	unsigned long long ret;
-
-	smp_mb();
-	ret = __cmpxchg64(ptr, old, new);
-	smp_mb();
-
-	return ret;
-}
-
-#define cmpxchg64(ptr, o, n) ({						\
-	(__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
-					   (unsigned long long)(o),	\
-					   (unsigned long long)(n));	\
-})
-
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
 #endif /* __ASM_ARM_CMPXCHG_H */
diff --git a/arch/arm/include/asm/jump_label.h b/arch/arm/include/asm/jump_label.h
index 5f337dc5c108..34f7b6980d21 100644
--- a/arch/arm/include/asm/jump_label.h
+++ b/arch/arm/include/asm/jump_label.h
@@ -4,23 +4,32 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/types.h>
+#include <asm/unified.h>
 
 #define JUMP_LABEL_NOP_SIZE 4
 
-#ifdef CONFIG_THUMB2_KERNEL
-#define JUMP_LABEL_NOP	"nop.w"
-#else
-#define JUMP_LABEL_NOP	"nop"
-#endif
+static __always_inline bool arch_static_branch(struct static_key *key, bool branch)
+{
+	asm_volatile_goto("1:\n\t"
+		 WASM(nop) "\n\t"
+		 ".pushsection __jump_table,  \"aw\"\n\t"
+		 ".word 1b, %l[l_yes], %c0\n\t"
+		 ".popsection\n\t"
+		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
+
+	return false;
+l_yes:
+	return true;
+}
 
-static __always_inline bool arch_static_branch(struct static_key *key)
+static __always_inline bool arch_static_branch_jump(struct static_key *key, bool branch)
 {
 	asm_volatile_goto("1:\n\t"
-		 JUMP_LABEL_NOP "\n\t"
+		 WASM(b) " %l[l_yes]\n\t"
 		 ".pushsection __jump_table,  \"aw\"\n\t"
 		 ".word 1b, %l[l_yes], %c0\n\t"
 		 ".popsection\n\t"
-		 : :  "i" (key) :  : l_yes);
+		 : :  "i" (&((char *)key)[branch]) :  : l_yes);
 
 	return false;
 l_yes: