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

Pull locking updates from Ingo Molnar:
 "The locking tree was busier in this cycle than the usual pattern - a
  couple of major projects happened to coincide.

  The main changes are:

   - implement the atomic_fetch_{add,sub,and,or,xor}() API natively
     across all SMP architectures (Peter Zijlstra)

   - add atomic_fetch_{inc/dec}() as well, using the generic primitives
     (Davidlohr Bueso)

   - optimize various aspects of rwsems (Jason Low, Davidlohr Bueso,
     Waiman Long)

   - optimize smp_cond_load_acquire() on arm64 and implement LSE based
     atomic{,64}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}()
     on arm64 (Will Deacon)

   - introduce smp_acquire__after_ctrl_dep() and fix various barrier
     mis-uses and bugs (Peter Zijlstra)

   - after discovering ancient spin_unlock_wait() barrier bugs in its
     implementation and usage, strengthen its semantics and update/fix
     usage sites (Peter Zijlstra)

   - optimize mutex_trylock() fastpath (Peter Zijlstra)

   - ... misc fixes and cleanups"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (67 commits)
  locking/atomic: Introduce inc/dec variants for the atomic_fetch_$op() API
  locking/barriers, arch/arm64: Implement LDXR+WFE based smp_cond_load_acquire()
  locking/static_keys: Fix non static symbol Sparse warning
  locking/qspinlock: Use __this_cpu_dec() instead of full-blown this_cpu_dec()
  locking/atomic, arch/tile: Fix tilepro build
  locking/atomic, arch/m68k: Remove comment
  locking/atomic, arch/arc: Fix build
  locking/Documentation: Clarify limited control-dependency scope
  locking/atomic, arch/rwsem: Employ atomic_long_fetch_add()
  locking/atomic, arch/qrwlock: Employ atomic_fetch_add_acquire()
  locking/atomic, arch/mips: Convert to _relaxed atomics
  locking/atomic, arch/alpha: Convert to _relaxed atomics
  locking/atomic: Remove the deprecated atomic_{set,clear}_mask() functions
  locking/atomic: Remove linux/atomic.h:atomic_fetch_or()
  locking/atomic: Implement atomic{,64,_long}_fetch_{add,sub,and,andnot,or,xor}{,_relaxed,_acquire,_release}()
  locking/atomic: Fix atomic64_relaxed() bits
  locking/atomic, arch/xtensa: Implement atomic_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/x86: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/tile: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  locking/atomic, arch/sparc: Implement atomic{,64}_fetch_{add,sub,and,or,xor}()
  ...

10 files changed, 203 insertions, 116 deletions

diff --git a/arch/tile/include/asm/atomic.h b/arch/tile/include/asm/atomic.h
index 9fc0107..8dda3c8 100644
--- a/arch/tile/include/asm/atomic.h
+++ b/arch/tile/include/asm/atomic.h
@@ -46,6 +46,8 @@ static inline int atomic_read(const atomic_t *v)
  */
 #define atomic_sub_return(i, v)		atomic_add_return((int)(-(i)), (v))
 
+#define atomic_fetch_sub(i, v)		atomic_fetch_add(-(int)(i), (v))
+
 /**
  * atomic_sub - subtract integer from atomic variable
  * @i: integer value to subtract
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index d320ce2..a9377425 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -34,18 +34,29 @@ static inline void atomic_add(int i, atomic_t *v)
 	_atomic_xchg_add(&v->counter, i);
 }
 
-#define ATOMIC_OP(op)							\
-unsigned long _atomic_##op(volatile unsigned long *p, unsigned long mask); \
+#define ATOMIC_OPS(op)							\
+unsigned long _atomic_fetch_##op(volatile unsigned long *p, unsigned long mask); \
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
-	_atomic_##op((unsigned long *)&v->counter, i);			\
+	_atomic_fetch_##op((unsigned long *)&v->counter, i);		\
+}									\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	smp_mb();							\
+	return _atomic_fetch_##op((unsigned long *)&v->counter, i);	\
 }
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+ATOMIC_OPS(xor)
 
-#undef ATOMIC_OP
+#undef ATOMIC_OPS
+
+static inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	smp_mb();
+	return _atomic_xchg_add(&v->counter, i);
+}
 
 /**
  * atomic_add_return - add integer and return
@@ -126,16 +137,29 @@ static inline void atomic64_add(long long i, atomic64_t *v)
 	_atomic64_xchg_add(&v->counter, i);
 }
 
-#define ATOMIC64_OP(op)						\
-long long _atomic64_##op(long long *v, long long n);		\
+#define ATOMIC64_OPS(op)					\
+long long _atomic64_fetch_##op(long long *v, long long n);	\
 static inline void atomic64_##op(long long i, atomic64_t *v)	\
 {								\
-	_atomic64_##op(&v->counter, i);				\
+	_atomic64_fetch_##op(&v->counter, i);			\
+}								\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{								\
+	smp_mb();						\
+	return _atomic64_fetch_##op(&v->counter, i);		\
 }
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+ATOMIC64_OPS(xor)
+
+#undef ATOMIC64_OPS
+
+static inline long long atomic64_fetch_add(long long i, atomic64_t *v)
+{
+	smp_mb();
+	return _atomic64_xchg_add(&v->counter, i);
+}
 
 /**
  * atomic64_add_return - add integer and return
@@ -186,6 +210,7 @@ static inline void atomic64_set(atomic64_t *v, long long n)
 #define atomic64_inc_return(v)		atomic64_add_return(1LL, (v))
 #define atomic64_inc_and_test(v)	(atomic64_inc_return(v) == 0)
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 #define atomic64_sub_and_test(a, v)	(atomic64_sub_return((a), (v)) == 0)
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_dec(v)			atomic64_sub(1LL, (v))
@@ -193,7 +218,6 @@ static inline void atomic64_set(atomic64_t *v, long long n)
 #define atomic64_dec_and_test(v)	(atomic64_dec_return((v)) == 0)
 #define atomic64_inc_not_zero(v)	atomic64_add_unless((v), 1LL, 0LL)
 
-
 #endif /* !__ASSEMBLY__ */
 
 /*
@@ -242,16 +266,16 @@ struct __get_user {
 	unsigned long val;
 	int err;
 };
-extern struct __get_user __atomic_cmpxchg(volatile int *p,
+extern struct __get_user __atomic32_cmpxchg(volatile int *p,
 					  int *lock, int o, int n);
-extern struct __get_user __atomic_xchg(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xchg_add(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xchg_add_unless(volatile int *p,
+extern struct __get_user __atomic32_xchg(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_xchg_add(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_xchg_add_unless(volatile int *p,
 						  int *lock, int o, int n);
-extern struct __get_user __atomic_or(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_and(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_andn(volatile int *p, int *lock, int n);
-extern struct __get_user __atomic_xor(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_or(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_and(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_andn(volatile int *p, int *lock, int n);
+extern struct __get_user __atomic32_fetch_xor(volatile int *p, int *lock, int n);
 extern long long __atomic64_cmpxchg(volatile long long *p, int *lock,
 					long long o, long long n);
 extern long long __atomic64_xchg(volatile long long *p, int *lock, long long n);
@@ -259,9 +283,9 @@ extern long long __atomic64_xchg_add(volatile long long *p, int *lock,
 					long long n);
 extern long long __atomic64_xchg_add_unless(volatile long long *p,
 					int *lock, long long o, long long n);
-extern long long __atomic64_and(volatile long long *p, int *lock, long long n);
-extern long long __atomic64_or(volatile long long *p, int *lock, long long n);
-extern long long __atomic64_xor(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_and(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_or(volatile long long *p, int *lock, long long n);
+extern long long __atomic64_fetch_xor(volatile long long *p, int *lock, long long n);
 
 /* Return failure from the atomic wrappers. */
 struct __get_user __atomic_bad_address(int __user *addr);
diff --git a/arch/tile/include/asm/atomic_64.h b/arch/tile/include/asm/atomic_64.h
index b0531a6..4cefa0c 100644
--- a/arch/tile/include/asm/atomic_64.h
+++ b/arch/tile/include/asm/atomic_64.h
@@ -32,11 +32,6 @@
  * on any routine which updates memory and returns a value.
  */
 
-static inline void atomic_add(int i, atomic_t *v)
-{
-	__insn_fetchadd4((void *)&v->counter, i);
-}
-
 /*
  * Note a subtlety of the locking here.  We are required to provide a
  * full memory barrier before and after the operation.  However, we
@@ -59,28 +54,39 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	return val;
 }
 
-static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+#define ATOMIC_OPS(op)							\
+static inline int atomic_fetch_##op(int i, atomic_t *v)			\
+{									\
+	int val;							\
+	smp_mb();							\
+	val = __insn_fetch##op##4((void *)&v->counter, i);		\
+	smp_mb();							\
+	return val;							\
+}									\
+static inline void atomic_##op(int i, atomic_t *v)			\
+{									\
+	__insn_fetch##op##4((void *)&v->counter, i);			\
+}
+
+ATOMIC_OPS(add)
+ATOMIC_OPS(and)
+ATOMIC_OPS(or)
+
+#undef ATOMIC_OPS
+
+static inline int atomic_fetch_xor(int i, atomic_t *v)
 {
 	int guess, oldval = v->counter;
+	smp_mb();
 	do {
-		if (oldval == u)
-			break;
 		guess = oldval;
-		oldval = cmpxchg(&v->counter, guess, guess + a);
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch4(&v->counter, guess ^ i);
 	} while (guess != oldval);
+	smp_mb();
 	return oldval;
 }
 
-static inline void atomic_and(int i, atomic_t *v)
-{
-	__insn_fetchand4((void *)&v->counter, i);
-}
-
-static inline void atomic_or(int i, atomic_t *v)
-{
-	__insn_fetchor4((void *)&v->counter, i);
-}
-
 static inline void atomic_xor(int i, atomic_t *v)
 {
 	int guess, oldval = v->counter;
@@ -91,6 +97,18 @@ static inline void atomic_xor(int i, atomic_t *v)
 	} while (guess != oldval);
 }
 
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int guess, oldval = v->counter;
+	do {
+		if (oldval == u)
+			break;
+		guess = oldval;
+		oldval = cmpxchg(&v->counter, guess, guess + a);
+	} while (guess != oldval);
+	return oldval;
+}
+
 /* Now the true 64-bit operations. */
 
 #define ATOMIC64_INIT(i)	{ (i) }
@@ -98,11 +116,6 @@ static inline void atomic_xor(int i, atomic_t *v)
 #define atomic64_read(v)	READ_ONCE((v)->counter)
 #define atomic64_set(v, i)	WRITE_ONCE((v)->counter, (i))
 
-static inline void atomic64_add(long i, atomic64_t *v)
-{
-	__insn_fetchadd((void *)&v->counter, i);
-}
-
 static inline long atomic64_add_return(long i, atomic64_t *v)
 {
 	int val;
@@ -112,26 +125,37 @@ static inline long atomic64_add_return(long i, atomic64_t *v)
 	return val;
 }
 
-static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+#define ATOMIC64_OPS(op)						\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	long val;							\
+	smp_mb();							\
+	val = __insn_fetch##op((void *)&v->counter, i);			\
+	smp_mb();							\
+	return val;							\
+}									\
+static inline void atomic64_##op(long i, atomic64_t *v)			\
+{									\
+	__insn_fetch##op((void *)&v->counter, i);			\
+}
+
+ATOMIC64_OPS(add)
+ATOMIC64_OPS(and)
+ATOMIC64_OPS(or)
+
+#undef ATOMIC64_OPS
+
+static inline long atomic64_fetch_xor(long i, atomic64_t *v)
 {
 	long guess, oldval = v->counter;
+	smp_mb();
 	do {
-		if (oldval == u)
-			break;
 		guess = oldval;
-		oldval = cmpxchg(&v->counter, guess, guess + a);
+		__insn_mtspr(SPR_CMPEXCH_VALUE, guess);
+		oldval = __insn_cmpexch(&v->counter, guess ^ i);
 	} while (guess != oldval);
-	return oldval != u;
-}
-
-static inline void atomic64_and(long i, atomic64_t *v)
-{
-	__insn_fetchand((void *)&v->counter, i);
-}
-
-static inline void atomic64_or(long i, atomic64_t *v)
-{
-	__insn_fetchor((void *)&v->counter, i);
+	smp_mb();
+	return oldval;
 }
 
 static inline void atomic64_xor(long i, atomic64_t *v)
@@ -144,7 +168,20 @@ static inline void atomic64_xor(long i, atomic64_t *v)
 	} while (guess != oldval);
 }
 
+static inline long atomic64_add_unless(atomic64_t *v, long a, long u)
+{
+	long guess, oldval = v->counter;
+	do {
+		if (oldval == u)
+			break;
+		guess = oldval;
+		oldval = cmpxchg(&v->counter, guess, guess + a);
+	} while (guess != oldval);
+	return oldval != u;
+}
+
 #define atomic64_sub_return(i, v)	atomic64_add_return(-(i), (v))
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
 #define atomic64_sub(i, v)		atomic64_add(-(i), (v))
 #define atomic64_inc_return(v)		atomic64_add_return(1, (v))
 #define atomic64_dec_return(v)		atomic64_sub_return(1, (v))
diff --git a/arch/tile/include/asm/barrier.h b/arch/tile/include/asm/barrier.h
index d552228..4c419ab 100644
--- a/arch/tile/include/asm/barrier.h
+++ b/arch/tile/include/asm/barrier.h
@@ -87,6 +87,13 @@ mb_incoherent(void)
 #define __smp_mb__after_atomic()	__smp_mb()
 #endif
 
+/*
+ * The TILE architecture does not do speculative reads; this ensures
+ * that a control dependency also orders against loads and already provides
+ * a LOAD->{LOAD,STORE} order and can forgo the additional RMB.
+ */
+#define smp_acquire__after_ctrl_dep()	barrier()
+
 #include <asm-generic/barrier.h>
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/tile/include/asm/bitops_32.h b/arch/tile/include/asm/bitops_32.h
index bbf7b66..d1406a9 100644
--- a/arch/tile/include/asm/bitops_32.h
+++ b/arch/tile/include/asm/bitops_32.h
@@ -19,9 +19,9 @@
 #include <asm/barrier.h>
 
 /* Tile-specific routines to support <asm/bitops.h>. */
-unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask);
-unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask);
-unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_or(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_andn(volatile unsigned long *p, unsigned long mask);
+unsigned long _atomic_fetch_xor(volatile unsigned long *p, unsigned long mask);
 
 /**
  * set_bit - Atomically set a bit in memory
@@ -35,7 +35,7 @@ unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask);
  */
 static inline void set_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_or(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_or(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -54,7 +54,7 @@ static inline void set_bit(unsigned nr, volatile unsigned long *addr)
  */
 static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_andn(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_andn(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -69,7 +69,7 @@ static inline void clear_bit(unsigned nr, volatile unsigned long *addr)
  */
 static inline void change_bit(unsigned nr, volatile unsigned long *addr)
 {
-	_atomic_xor(addr + BIT_WORD(nr), BIT_MASK(nr));
+	_atomic_fetch_xor(addr + BIT_WORD(nr), BIT_MASK(nr));
 }
 
 /**
@@ -85,7 +85,7 @@ static inline int test_and_set_bit(unsigned nr, volatile unsigned long *addr)
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_or(addr, mask) & mask) != 0;
+	return (_atomic_fetch_or(addr, mask) & mask) != 0;
 }
 
 /**
@@ -101,7 +101,7 @@ static inline int test_and_clear_bit(unsigned nr, volatile unsigned long *addr)
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_andn(addr, mask) & mask) != 0;
+	return (_atomic_fetch_andn(addr, mask) & mask) != 0;
 }
 
 /**
@@ -118,7 +118,7 @@ static inline int test_and_change_bit(unsigned nr,
 	unsigned long mask = BIT_MASK(nr);
 	addr += BIT_WORD(nr);
 	smp_mb();  /* barrier for proper semantics */
-	return (_atomic_xor(addr, mask) & mask) != 0;
+	return (_atomic_fetch_xor(addr, mask) & mask) != 0;
 }
 
 #include <asm-generic/bitops/ext2-atomic.h>
diff --git a/arch/tile/include/asm/futex.h b/arch/tile/include/asm/futex.h
index 1a6ef1b..e64a1b7 100644
--- a/arch/tile/include/asm/futex.h
+++ b/arch/tile/include/asm/futex.h
@@ -80,16 +80,16 @@
 		ret = gu.err;						\
 	}
 
-#define __futex_set() __futex_call(__atomic_xchg)
-#define __futex_add() __futex_call(__atomic_xchg_add)
-#define __futex_or() __futex_call(__atomic_or)
-#define __futex_andn() __futex_call(__atomic_andn)
-#define __futex_xor() __futex_call(__atomic_xor)
+#define __futex_set() __futex_call(__atomic32_xchg)
+#define __futex_add() __futex_call(__atomic32_xchg_add)
+#define __futex_or() __futex_call(__atomic32_fetch_or)
+#define __futex_andn() __futex_call(__atomic32_fetch_andn)
+#define __futex_xor() __futex_call(__atomic32_fetch_xor)
 
 #define __futex_cmpxchg()						\
 	{								\
-		struct __get_user gu = __atomic_cmpxchg((u32 __force *)uaddr, \
-							lock, oldval, oparg); \
+		struct __get_user gu = __atomic32_cmpxchg((u32 __force *)uaddr, \
+							  lock, oldval, oparg); \
 		val = gu.val;						\
 		ret = gu.err;						\
 	}
diff --git a/arch/tile/lib/atomic_32.c b/arch/tile/lib/atomic_32.c
index 298df1e..f812880 100644
--- a/arch/tile/lib/atomic_32.c
+++ b/arch/tile/lib/atomic_32.c
@@ -61,13 +61,13 @@ static inline int *__atomic_setup(volatile void *v)
 
 int _atomic_xchg(int *v, int n)
 {
-	return __atomic_xchg(v, __atomic_setup(v), n).val;
+	return __atomic32_xchg(v, __atomic_setup(v), n).val;
 }
 EXPORT_SYMBOL(_atomic_xchg);
 
 int _atomic_xchg_add(int *v, int i)
 {
-	return __atomic_xchg_add(v, __atomic_setup(v), i).val;
+	return __atomic32_xchg_add(v, __atomic_setup(v), i).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add);
 
@@ -78,39 +78,39 @@ int _atomic_xchg_add_unless(int *v, int a, int u)
 	 * to use the first argument consistently as the "old value"
 	 * in the assembly, as is done for _atomic_cmpxchg().
 	 */
-	return __atomic_xchg_add_unless(v, __atomic_setup(v), u, a).val;
+	return __atomic32_xchg_add_unless(v, __atomic_setup(v), u, a).val;
 }
 EXPORT_SYMBOL(_atomic_xchg_add_unless);
 
 int _atomic_cmpxchg(int *v, int o, int n)
 {
-	return __atomic_cmpxchg(v, __atomic_setup(v), o, n).val;
+	return __atomic32_cmpxchg(v, __atomic_setup(v), o, n).val;
 }
 EXPORT_SYMBOL(_atomic_cmpxchg);
 
-unsigned long _atomic_or(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_or(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_or((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_or((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_or);
+EXPORT_SYMBOL(_atomic_fetch_or);
 
-unsigned long _atomic_and(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_and(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_and((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_and((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_and);
+EXPORT_SYMBOL(_atomic_fetch_and);
 
-unsigned long _atomic_andn(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_andn(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_andn((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_andn((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_andn);
+EXPORT_SYMBOL(_atomic_fetch_andn);
 
-unsigned long _atomic_xor(volatile unsigned long *p, unsigned long mask)
+unsigned long _atomic_fetch_xor(volatile unsigned long *p, unsigned long mask)
 {
-	return __atomic_xor((int *)p, __atomic_setup(p), mask).val;
+	return __atomic32_fetch_xor((int *)p, __atomic_setup(p), mask).val;
 }
-EXPORT_SYMBOL(_atomic_xor);
+EXPORT_SYMBOL(_atomic_fetch_xor);
 
 
 long long _atomic64_xchg(long long *v, long long n)
@@ -142,23 +142,23 @@ long long _atomic64_cmpxchg(long long *v, long long o, long long n)
 }
 EXPORT_SYMBOL(_atomic64_cmpxchg);
 
-long long _atomic64_and(long long *v, long long n)
+long long _atomic64_fetch_and(long long *v, long long n)
 {
-	return __atomic64_and(v, __atomic_setup(v), n);
+	return __atomic64_fetch_and(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_and);
+EXPORT_SYMBOL(_atomic64_fetch_and);
 
-long long _atomic64_or(long long *v, long long n)
+long long _atomic64_fetch_or(long long *v, long long n)
 {
-	return __atomic64_or(v, __atomic_setup(v), n);
+	return __atomic64_fetch_or(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_or);
+EXPORT_SYMBOL(_atomic64_fetch_or);
 
-long long _atomic64_xor(long long *v, long long n)
+long long _atomic64_fetch_xor(long long *v, long long n)
 {
-	return __atomic64_xor(v, __atomic_setup(v), n);
+	return __atomic64_fetch_xor(v, __atomic_setup(v), n);
 }
-EXPORT_SYMBOL(_atomic64_xor);
+EXPORT_SYMBOL(_atomic64_fetch_xor);
 
 /*
  * If any of the atomic or futex routines hit a bad address (not in
diff --git a/arch/tile/lib/atomic_asm_32.S b/arch/tile/lib/atomic_asm_32.S
index f611265..1a70e6c 100644
--- a/arch/tile/lib/atomic_asm_32.S
+++ b/arch/tile/lib/atomic_asm_32.S
@@ -172,15 +172,20 @@ STD_ENTRY_SECTION(__atomic\name, .text.atomic)
 	.endif
 	.endm
 
-atomic_op _cmpxchg, 32, "seq r26, r22, r2; { bbns r26, 3f; move r24, r3 }"
-atomic_op _xchg, 32, "move r24, r2"
-atomic_op _xchg_add, 32, "add r24, r22, r2"
-atomic_op _xchg_add_unless, 32, \
+
+/*
+ * Use __atomic32 prefix to avoid collisions with GCC builtin __atomic functions.
+ */
+
+atomic_op 32_cmpxchg, 32, "seq r26, r22, r2; { bbns r26, 3f; move r24, r3 }"
+atomic_op 32_xchg, 32, "move r24, r2"
+atomic_op 32_xchg_add, 32, "add r24, r22, r2"
+atomic_op 32_xchg_add_unless, 32, \
 	"sne r26, r22, r2; { bbns r26, 3f; add r24, r22, r3 }"
-atomic_op _or, 32, "or r24, r22, r2"
-atomic_op _and, 32, "and r24, r22, r2"
-atomic_op _andn, 32, "nor r2, r2, zero; and r24, r22, r2"
-atomic_op _xor, 32, "xor r24, r22, r2"
+atomic_op 32_fetch_or, 32, "or r24, r22, r2"
+atomic_op 32_fetch_and, 32, "and r24, r22, r2"
+atomic_op 32_fetch_andn, 32, "nor r2, r2, zero; and r24, r22, r2"
+atomic_op 32_fetch_xor, 32, "xor r24, r22, r2"
 
 atomic_op 64_cmpxchg, 64, "{ seq r26, r22, r2; seq r27, r23, r3 }; \
 	{ bbns r26, 3f; move r24, r4 }; { bbns r27, 3f; move r25, r5 }"
@@ -192,9 +197,9 @@ atomic_op 64_xchg_add_unless, 64, \
 	{ bbns r26, 3f; add r24, r22, r4 }; \
 	{ bbns r27, 3f; add r25, r23, r5 }; \
 	slt_u r26, r24, r22; add r25, r25, r26"
-atomic_op 64_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
-atomic_op 64_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
-atomic_op 64_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
+atomic_op 64_fetch_or, 64, "{ or r24, r22, r2; or r25, r23, r3 }"
+atomic_op 64_fetch_and, 64, "{ and r24, r22, r2; and r25, r23, r3 }"
+atomic_op 64_fetch_xor, 64, "{ xor r24, r22, r2; xor r25, r23, r3 }"
 
 	jrp     lr              /* happy backtracer */
 
diff --git a/arch/tile/lib/spinlock_32.c b/arch/tile/lib/spinlock_32.c
index 88c2a53..076c6cc 100644
--- a/arch/tile/lib/spinlock_32.c
+++ b/arch/tile/lib/spinlock_32.c
@@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	do {
 		delay_backoff(iterations++);
 	} while (READ_ONCE(lock->current_ticket) == curr);
+
+	/*
+	 * The TILE architecture doesn't do read speculation; therefore
+	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
+	 */
+	barrier();
 }
 EXPORT_SYMBOL(arch_spin_unlock_wait);
 
diff --git a/arch/tile/lib/spinlock_64.c b/arch/tile/lib/spinlock_64.c
index c8d1f94..a4b5b2c 100644
--- a/arch/tile/lib/spinlock_64.c
+++ b/arch/tile/lib/spinlock_64.c
@@ -76,6 +76,12 @@ void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	do {
 		delay_backoff(iterations++);
 	} while (arch_spin_current(READ_ONCE(lock->lock)) == curr);
+
+	/*
+	 * The TILE architecture doesn't do read speculation; therefore
+	 * a control dependency guarantees a LOAD->{LOAD,STORE} order.
+	 */
+	barrier();
 }
 EXPORT_SYMBOL(arch_spin_unlock_wait);