5 files changed, 210 insertions, 69 deletions

diff --git a/arch/x86/include/asm/qspinlock_paravirt.h b/arch/x86/include/asm/qspinlock_paravirt.h
index b002e711ba88..9f92c180ed2f 100644
--- a/arch/x86/include/asm/qspinlock_paravirt.h
+++ b/arch/x86/include/asm/qspinlock_paravirt.h
@@ -1,6 +1,65 @@
 #ifndef __ASM_QSPINLOCK_PARAVIRT_H
 #define __ASM_QSPINLOCK_PARAVIRT_H
 
+/*
+ * For x86-64, PV_CALLEE_SAVE_REGS_THUNK() saves and restores 8 64-bit
+ * registers. For i386, however, only 1 32-bit register needs to be saved
+ * and restored. So an optimized version of __pv_queued_spin_unlock() is
+ * hand-coded for 64-bit, but it isn't worthwhile to do it for 32-bit.
+ */
+#ifdef CONFIG_64BIT
+
+PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock_slowpath);
+#define __pv_queued_spin_unlock	__pv_queued_spin_unlock
+#define PV_UNLOCK		"__raw_callee_save___pv_queued_spin_unlock"
+#define PV_UNLOCK_SLOWPATH	"__raw_callee_save___pv_queued_spin_unlock_slowpath"
+
+/*
+ * Optimized assembly version of __raw_callee_save___pv_queued_spin_unlock
+ * which combines the registers saving trunk and the body of the following
+ * C code:
+ *
+ * void __pv_queued_spin_unlock(struct qspinlock *lock)
+ * {
+ *	struct __qspinlock *l = (void *)lock;
+ *	u8 lockval = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+ *
+ *	if (likely(lockval == _Q_LOCKED_VAL))
+ *		return;
+ *	pv_queued_spin_unlock_slowpath(lock, lockval);
+ * }
+ *
+ * For x86-64,
+ *   rdi = lock              (first argument)
+ *   rsi = lockval           (second argument)
+ *   rdx = internal variable (set to 0)
+ */
+asm    (".pushsection .text;"
+	".globl " PV_UNLOCK ";"
+	".align 4,0x90;"
+	PV_UNLOCK ": "
+	"push  %rdx;"
+	"mov   $0x1,%eax;"
+	"xor   %edx,%edx;"
+	"lock cmpxchg %dl,(%rdi);"
+	"cmp   $0x1,%al;"
+	"jne   .slowpath;"
+	"pop   %rdx;"
+	"ret;"
+	".slowpath: "
+	"push   %rsi;"
+	"movzbl %al,%esi;"
+	"call " PV_UNLOCK_SLOWPATH ";"
+	"pop    %rsi;"
+	"pop    %rdx;"
+	"ret;"
+	".size " PV_UNLOCK ", .-" PV_UNLOCK ";"
+	".popsection");
+
+#else /* CONFIG_64BIT */
+
+extern void __pv_queued_spin_unlock(struct qspinlock *lock);
 PV_CALLEE_SAVE_REGS_THUNK(__pv_queued_spin_unlock);
 
+#endif /* CONFIG_64BIT */
 #endif
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index e2aadbc7151f..39e1cb201b8e 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -12,8 +12,9 @@
  * GNU General Public License for more details.
  *
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <[email protected]>
+ * Authors: Waiman Long <[email protected]>
  */
 #ifndef __ASM_GENERIC_QSPINLOCK_H
 #define __ASM_GENERIC_QSPINLOCK_H
@@ -62,7 +63,7 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
 	if (!atomic_read(&lock->val) &&
-	   (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) == 0))
+	   (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
 		return 1;
 	return 0;
 }
@@ -77,7 +78,7 @@ static __always_inline void queued_spin_lock(struct qspinlock *lock)
 {
 	u32 val;
 
-	val = atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL);
+	val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
 	if (likely(val == 0))
 		return;
 	queued_spin_lock_slowpath(lock, val);
@@ -93,7 +94,7 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 	/*
 	 * smp_mb__before_atomic() in order to guarantee release semantics
 	 */
-	smp_mb__before_atomic_dec();
+	smp_mb__before_atomic();
 	atomic_sub(_Q_LOCKED_VAL, &lock->val);
 }
 #endif
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 87e9ce6a63c5..986207887def 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -14,8 +14,9 @@
  * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P.
  * (C) Copyright 2013-2014 Red Hat, Inc.
  * (C) Copyright 2015 Intel Corp.
+ * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP
  *
- * Authors: Waiman Long <[email protected]>
+ * Authors: Waiman Long <[email protected]>
  *          Peter Zijlstra <[email protected]>
  */
 
@@ -176,7 +177,12 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 {
 	struct __qspinlock *l = (void *)lock;
 
-	return (u32)xchg(&l->tail, tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
+	/*
+	 * Use release semantics to make sure that the MCS node is properly
+	 * initialized before changing the tail code.
+	 */
+	return (u32)xchg_release(&l->tail,
+				 tail >> _Q_TAIL_OFFSET) << _Q_TAIL_OFFSET;
 }
 
 #else /* _Q_PENDING_BITS == 8 */
@@ -208,7 +214,11 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 
 	for (;;) {
 		new = (val & _Q_LOCKED_PENDING_MASK) | tail;
-		old = atomic_cmpxchg(&lock->val, val, new);
+		/*
+		 * Use release semantics to make sure that the MCS node is
+		 * properly initialized before changing the tail code.
+		 */
+		old = atomic_cmpxchg_release(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -319,7 +329,11 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 		if (val == new)
 			new |= _Q_PENDING_VAL;
 
-		old = atomic_cmpxchg(&lock->val, val, new);
+		/*
+		 * Acquire semantic is required here as the function may
+		 * return immediately if the lock was free.
+		 */
+		old = atomic_cmpxchg_acquire(&lock->val, val, new);
 		if (old == val)
 			break;
 
@@ -382,6 +396,7 @@ queue:
 	 * p,*,* -> n,*,*
 	 */
 	old = xchg_tail(lock, tail);
+	next = NULL;
 
 	/*
 	 * if there was a previous node; link it and wait until reaching the
@@ -393,6 +408,16 @@ queue:
 
 		pv_wait_node(node);
 		arch_mcs_spin_lock_contended(&node->locked);
+
+		/*
+		 * While waiting for the MCS lock, the next pointer may have
+		 * been set by another lock waiter. We optimistically load
+		 * the next pointer & prefetch the cacheline for writing
+		 * to reduce latency in the upcoming MCS unlock operation.
+		 */
+		next = READ_ONCE(node->next);
+		if (next)
+			prefetchw(next);
 	}
 
 	/*
@@ -426,7 +451,12 @@ queue:
 			set_locked(lock);
 			break;
 		}
-		old = atomic_cmpxchg(&lock->val, val, _Q_LOCKED_VAL);
+		/*
+		 * The smp_load_acquire() call above has provided the necessary
+		 * acquire semantics required for locking. At most two
+		 * iterations of this loop may be ran.
+		 */
+		old = atomic_cmpxchg_relaxed(&lock->val, val, _Q_LOCKED_VAL);
 		if (old == val)
 			goto release;	/* No contention */
 
@@ -434,10 +464,12 @@ queue:
 	}
 
 	/*
-	 * contended path; wait for next, release.
+	 * contended path; wait for next if not observed yet, release.
 	 */
-	while (!(next = READ_ONCE(node->next)))
-		cpu_relax();
+	if (!next) {
+		while (!(next = READ_ONCE(node->next)))
+			cpu_relax();
+	}
 
 	arch_mcs_spin_unlock_contended(&next->locked);
 	pv_kick_node(lock, next);
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index f0450ff4829b..4bd323d38c60 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -308,23 +308,14 @@ static void pv_wait_head(struct qspinlock *lock, struct mcs_spinlock *node)
 }
 
 /*
- * PV version of the unlock function to be used in stead of
- * queued_spin_unlock().
+ * PV versions of the unlock fastpath and slowpath functions to be used
+ * instead of queued_spin_unlock().
  */
-__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+__visible void
+__pv_queued_spin_unlock_slowpath(struct qspinlock *lock, u8 locked)
 {
 	struct __qspinlock *l = (void *)lock;
 	struct pv_node *node;
-	u8 locked;
-
-	/*
-	 * We must not unlock if SLOW, because in that case we must first
-	 * unhash. Otherwise it would be possible to have multiple @lock
-	 * entries, which would be BAD.
-	 */
-	locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
-	if (likely(locked == _Q_LOCKED_VAL))
-		return;
 
 	if (unlikely(locked != _Q_SLOW_VAL)) {
 		WARN(!debug_locks_silent,
@@ -363,12 +354,32 @@ __visible void __pv_queued_spin_unlock(struct qspinlock *lock)
 	 */
 	pv_kick(node->cpu);
 }
+
 /*
  * Include the architecture specific callee-save thunk of the
  * __pv_queued_spin_unlock(). This thunk is put together with
- * __pv_queued_spin_unlock() near the top of the file to make sure
- * that the callee-save thunk and the real unlock function are close
- * to each other sharing consecutive instruction cachelines.
+ * __pv_queued_spin_unlock() to make the callee-save thunk and the real unlock
+ * function close to each other sharing consecutive instruction cachelines.
+ * Alternatively, architecture specific version of __pv_queued_spin_unlock()
+ * can be defined.
  */
 #include <asm/qspinlock_paravirt.h>
 
+#ifndef __pv_queued_spin_unlock
+__visible void __pv_queued_spin_unlock(struct qspinlock *lock)
+{
+	struct __qspinlock *l = (void *)lock;
+	u8 locked;
+
+	/*
+	 * We must not unlock if SLOW, because in that case we must first
+	 * unhash. Otherwise it would be possible to have multiple @lock
+	 * entries, which would be BAD.
+	 */
+	locked = cmpxchg(&l->locked, _Q_LOCKED_VAL, 0);
+	if (likely(locked == _Q_LOCKED_VAL))
+		return;
+
+	__pv_queued_spin_unlock_slowpath(lock, locked);
+}
+#endif /* __pv_queued_spin_unlock */
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 83c33a5bcffb..18e422b259cf 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -27,6 +27,65 @@ do {								\
 		(unsigned long long)r);				\
 } while (0)
 
+/*
+ * Test for a atomic operation family,
+ * @test should be a macro accepting parameters (bit, op, ...)
+ */
+
+#define FAMILY_TEST(test, bit, op, args...)	\
+do {						\
+	test(bit, op, ##args);		\
+	test(bit, op##_acquire, ##args);	\
+	test(bit, op##_release, ##args);	\
+	test(bit, op##_relaxed, ##args);	\
+} while (0)
+
+#define TEST_RETURN(bit, op, c_op, val)				\
+do {								\
+	atomic##bit##_set(&v, v0);				\
+	r = v0;							\
+	r c_op val;						\
+	BUG_ON(atomic##bit##_##op(val, &v) != r);		\
+	BUG_ON(atomic##bit##_read(&v) != r);			\
+} while (0)
+
+#define RETURN_FAMILY_TEST(bit, op, c_op, val)			\
+do {								\
+	FAMILY_TEST(TEST_RETURN, bit, op, c_op, val);		\
+} while (0)
+
+#define TEST_ARGS(bit, op, init, ret, expect, args...)		\
+do {								\
+	atomic##bit##_set(&v, init);				\
+	BUG_ON(atomic##bit##_##op(&v, ##args) != ret);		\
+	BUG_ON(atomic##bit##_read(&v) != expect);		\
+} while (0)
+
+#define XCHG_FAMILY_TEST(bit, init, new)				\
+do {									\
+	FAMILY_TEST(TEST_ARGS, bit, xchg, init, init, new, new);	\
+} while (0)
+
+#define CMPXCHG_FAMILY_TEST(bit, init, new, wrong)			\
+do {									\
+	FAMILY_TEST(TEST_ARGS, bit, cmpxchg, 				\
+			init, init, new, init, new);			\
+	FAMILY_TEST(TEST_ARGS, bit, cmpxchg,				\
+			init, init, init, wrong, new);			\
+} while (0)
+
+#define INC_RETURN_FAMILY_TEST(bit, i)			\
+do {							\
+	FAMILY_TEST(TEST_ARGS, bit, inc_return,		\
+			i, (i) + one, (i) + one);	\
+} while (0)
+
+#define DEC_RETURN_FAMILY_TEST(bit, i)			\
+do {							\
+	FAMILY_TEST(TEST_ARGS, bit, dec_return,		\
+			i, (i) - one, (i) - one);	\
+} while (0)
+
 static __init void test_atomic(void)
 {
 	int v0 = 0xaaa31337;
@@ -45,6 +104,18 @@ static __init void test_atomic(void)
 	TEST(, and, &=, v1);
 	TEST(, xor, ^=, v1);
 	TEST(, andnot, &= ~, v1);
+
+	RETURN_FAMILY_TEST(, add_return, +=, onestwos);
+	RETURN_FAMILY_TEST(, add_return, +=, -one);
+	RETURN_FAMILY_TEST(, sub_return, -=, onestwos);
+	RETURN_FAMILY_TEST(, sub_return, -=, -one);
+
+	INC_RETURN_FAMILY_TEST(, v0);
+	DEC_RETURN_FAMILY_TEST(, v0);
+
+	XCHG_FAMILY_TEST(, v0, v1);
+	CMPXCHG_FAMILY_TEST(, v0, v1, onestwos);
+
 }
 
 #define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)
@@ -74,25 +145,10 @@ static __init void test_atomic64(void)
 	TEST(64, xor, ^=, v1);
 	TEST(64, andnot, &= ~, v1);
 
-	INIT(v0);
-	r += onestwos;
-	BUG_ON(atomic64_add_return(onestwos, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r += -one;
-	BUG_ON(atomic64_add_return(-one, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r -= onestwos;
-	BUG_ON(atomic64_sub_return(onestwos, &v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	r -= -one;
-	BUG_ON(atomic64_sub_return(-one, &v) != r);
-	BUG_ON(v.counter != r);
+	RETURN_FAMILY_TEST(64, add_return, +=, onestwos);
+	RETURN_FAMILY_TEST(64, add_return, +=, -one);
+	RETURN_FAMILY_TEST(64, sub_return, -=, onestwos);
+	RETURN_FAMILY_TEST(64, sub_return, -=, -one);
 
 	INIT(v0);
 	atomic64_inc(&v);
@@ -100,33 +156,15 @@ static __init void test_atomic64(void)
 	BUG_ON(v.counter != r);
 
 	INIT(v0);
-	r += one;
-	BUG_ON(atomic64_inc_return(&v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
 	atomic64_dec(&v);
 	r -= one;
 	BUG_ON(v.counter != r);
 
-	INIT(v0);
-	r -= one;
-	BUG_ON(atomic64_dec_return(&v) != r);
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	BUG_ON(atomic64_xchg(&v, v1) != v0);
-	r = v1;
-	BUG_ON(v.counter != r);
-
-	INIT(v0);
-	BUG_ON(atomic64_cmpxchg(&v, v0, v1) != v0);
-	r = v1;
-	BUG_ON(v.counter != r);
+	INC_RETURN_FAMILY_TEST(64, v0);
+	DEC_RETURN_FAMILY_TEST(64, v0);
 
-	INIT(v0);
-	BUG_ON(atomic64_cmpxchg(&v, v2, v1) != v0);
-	BUG_ON(v.counter != r);
+	XCHG_FAMILY_TEST(64, v0, v1);
+	CMPXCHG_FAMILY_TEST(64, v0, v1, v2);
 
 	INIT(v0);
 	BUG_ON(atomic64_add_unless(&v, one, v0));