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}()
  ...

2 files changed, 154 insertions, 19 deletions

diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
index 835b402e4574..0ab176bdb8e8 100644
--- a/arch/mips/include/asm/atomic.h
+++ b/arch/mips/include/asm/atomic.h
@@ -66,7 +66,7 @@ static __inline__ void atomic_##op(int i, atomic_t * v)			      \
 			"	" #asm_op " %0, %2			\n"   \
 			"	sc	%0, %1				\n"   \
 			"	.set	mips0				\n"   \
-			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)      \
+			: "=&r" (temp), "+" GCC_OFF_SMALL_ASM() (v->counter)  \
 			: "Ir" (i));					      \
 		} while (unlikely(!temp));				      \
 	} else {							      \
@@ -79,12 +79,10 @@ 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)	      \
 {									      \
 	int result;							      \
 									      \
-	smp_mb__before_llsc();						      \
-									      \
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
 		int temp;						      \
 									      \
@@ -125,23 +123,84 @@ static __inline__ int atomic_##op##_return(int i, atomic_t * v)		      \
 		raw_local_irq_restore(flags);				      \
 	}								      \
 									      \
-	smp_llsc_mb();							      \
+	return result;							      \
+}
+
+#define ATOMIC_FETCH_OP(op, c_op, asm_op)				      \
+static __inline__ int atomic_fetch_##op##_relaxed(int i, atomic_t * v)	      \
+{									      \
+	int result;							      \
+									      \
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+		int temp;						      \
+									      \
+		__asm__ __volatile__(					      \
+		"	.set	arch=r4000				\n"   \
+		"1:	ll	%1, %2		# atomic_fetch_" #op "	\n"   \
+		"	" #asm_op " %0, %1, %3				\n"   \
+		"	sc	%0, %2					\n"   \
+		"	beqzl	%0, 1b					\n"   \
+		"	move	%0, %1					\n"   \
+		"	.set	mips0					\n"   \
+		: "=&r" (result), "=&r" (temp),				      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
+		: "Ir" (i));						      \
+	} else if (kernel_uses_llsc) {					      \
+		int temp;						      \
+									      \
+		do {							      \
+			__asm__ __volatile__(				      \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
+			"	ll	%1, %2	# atomic_fetch_" #op "	\n"   \
+			"	" #asm_op " %0, %1, %3			\n"   \
+			"	sc	%0, %2				\n"   \
+			"	.set	mips0				\n"   \
+			: "=&r" (result), "=&r" (temp),			      \
+			  "+" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i));					      \
+		} while (unlikely(!result));				      \
+									      \
+		result = temp;						      \
+	} else {							      \
+		unsigned long flags;					      \
+									      \
+		raw_local_irq_save(flags);				      \
+		result = v->counter;					      \
+		v->counter c_op i;					      \
+		raw_local_irq_restore(flags);				      \
+	}								      \
 									      \
 	return result;							      \
 }
 
 #define ATOMIC_OPS(op, c_op, asm_op)					      \
 	ATOMIC_OP(op, c_op, asm_op)					      \
-	ATOMIC_OP_RETURN(op, c_op, asm_op)
+	ATOMIC_OP_RETURN(op, c_op, asm_op)				      \
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC_OPS(add, +=, addu)
 ATOMIC_OPS(sub, -=, subu)
 
-ATOMIC_OP(and, &=, and)
-ATOMIC_OP(or, |=, or)
-ATOMIC_OP(xor, ^=, xor)
+#define atomic_add_return_relaxed	atomic_add_return_relaxed
+#define atomic_sub_return_relaxed	atomic_sub_return_relaxed
+#define atomic_fetch_add_relaxed	atomic_fetch_add_relaxed
+#define atomic_fetch_sub_relaxed	atomic_fetch_sub_relaxed
+
+#undef ATOMIC_OPS
+#define ATOMIC_OPS(op, c_op, asm_op)					      \
+	ATOMIC_OP(op, c_op, asm_op)					      \
+	ATOMIC_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC_OPS(and, &=, and)
+ATOMIC_OPS(or, |=, or)
+ATOMIC_OPS(xor, ^=, xor)
+
+#define atomic_fetch_and_relaxed	atomic_fetch_and_relaxed
+#define atomic_fetch_or_relaxed		atomic_fetch_or_relaxed
+#define atomic_fetch_xor_relaxed	atomic_fetch_xor_relaxed
 
 #undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP_RETURN
 #undef ATOMIC_OP
 
@@ -362,12 +421,10 @@ 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(long i, atomic64_t * v)	      \
+static __inline__ long atomic64_##op##_return_relaxed(long i, atomic64_t * v) \
 {									      \
 	long result;							      \
 									      \
-	smp_mb__before_llsc();						      \
-									      \
 	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
 		long temp;						      \
 									      \
@@ -409,22 +466,85 @@ static __inline__ long atomic64_##op##_return(long i, atomic64_t * v)	      \
 		raw_local_irq_restore(flags);				      \
 	}								      \
 									      \
-	smp_llsc_mb();							      \
+	return result;							      \
+}
+
+#define ATOMIC64_FETCH_OP(op, c_op, asm_op)				      \
+static __inline__ long atomic64_fetch_##op##_relaxed(long i, atomic64_t * v)  \
+{									      \
+	long result;							      \
+									      \
+	if (kernel_uses_llsc && R10000_LLSC_WAR) {			      \
+		long temp;						      \
+									      \
+		__asm__ __volatile__(					      \
+		"	.set	arch=r4000				\n"   \
+		"1:	lld	%1, %2		# atomic64_fetch_" #op "\n"   \
+		"	" #asm_op " %0, %1, %3				\n"   \
+		"	scd	%0, %2					\n"   \
+		"	beqzl	%0, 1b					\n"   \
+		"	move	%0, %1					\n"   \
+		"	.set	mips0					\n"   \
+		: "=&r" (result), "=&r" (temp),				      \
+		  "+" GCC_OFF_SMALL_ASM() (v->counter)			      \
+		: "Ir" (i));						      \
+	} else if (kernel_uses_llsc) {					      \
+		long temp;						      \
+									      \
+		do {							      \
+			__asm__ __volatile__(				      \
+			"	.set	"MIPS_ISA_LEVEL"		\n"   \
+			"	lld	%1, %2	# atomic64_fetch_" #op "\n"   \
+			"	" #asm_op " %0, %1, %3			\n"   \
+			"	scd	%0, %2				\n"   \
+			"	.set	mips0				\n"   \
+			: "=&r" (result), "=&r" (temp),			      \
+			  "=" GCC_OFF_SMALL_ASM() (v->counter)		      \
+			: "Ir" (i), GCC_OFF_SMALL_ASM() (v->counter)	      \
+			: "memory");					      \
+		} while (unlikely(!result));				      \
+									      \
+		result = temp;						      \
+	} else {							      \
+		unsigned long flags;					      \
+									      \
+		raw_local_irq_save(flags);				      \
+		result = v->counter;					      \
+		v->counter c_op i;					      \
+		raw_local_irq_restore(flags);				      \
+	}								      \
 									      \
 	return result;							      \
 }
 
 #define ATOMIC64_OPS(op, c_op, asm_op)					      \
 	ATOMIC64_OP(op, c_op, asm_op)					      \
-	ATOMIC64_OP_RETURN(op, c_op, asm_op)
+	ATOMIC64_OP_RETURN(op, c_op, asm_op)				      \
+	ATOMIC64_FETCH_OP(op, c_op, asm_op)
 
 ATOMIC64_OPS(add, +=, daddu)
 ATOMIC64_OPS(sub, -=, dsubu)
-ATOMIC64_OP(and, &=, and)
-ATOMIC64_OP(or, |=, or)
-ATOMIC64_OP(xor, ^=, xor)
+
+#define atomic64_add_return_relaxed	atomic64_add_return_relaxed
+#define atomic64_sub_return_relaxed	atomic64_sub_return_relaxed
+#define atomic64_fetch_add_relaxed	atomic64_fetch_add_relaxed
+#define atomic64_fetch_sub_relaxed	atomic64_fetch_sub_relaxed
+
+#undef ATOMIC64_OPS
+#define ATOMIC64_OPS(op, c_op, asm_op)					      \
+	ATOMIC64_OP(op, c_op, asm_op)					      \
+	ATOMIC64_FETCH_OP(op, c_op, asm_op)
+
+ATOMIC64_OPS(and, &=, and)
+ATOMIC64_OPS(or, |=, or)
+ATOMIC64_OPS(xor, ^=, xor)
+
+#define atomic64_fetch_and_relaxed	atomic64_fetch_and_relaxed
+#define atomic64_fetch_or_relaxed	atomic64_fetch_or_relaxed
+#define atomic64_fetch_xor_relaxed	atomic64_fetch_xor_relaxed
 
 #undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index 40196bebe849..f485afe51514 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -12,6 +12,7 @@
 #include <linux/compiler.h>
 
 #include <asm/barrier.h>
+#include <asm/processor.h>
 #include <asm/compiler.h>
 #include <asm/war.h>
 
@@ -48,8 +49,22 @@ static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
 }
 
 #define arch_spin_lock_flags(lock, flags) arch_spin_lock(lock)
-#define arch_spin_unlock_wait(x) \
-	while (arch_spin_is_locked(x)) { cpu_relax(); }
+
+static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
+{
+	u16 owner = READ_ONCE(lock->h.serving_now);
+	smp_rmb();
+	for (;;) {
+		arch_spinlock_t tmp = READ_ONCE(*lock);
+
+		if (tmp.h.serving_now == tmp.h.ticket ||
+		    tmp.h.serving_now != owner)
+			break;
+
+		cpu_relax();
+	}
+	smp_acquire__after_ctrl_dep();
+}
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
 {