[PATCH v2 14/17] powerpc/qspinlock: use spin_begin/end API

[Nicholas Piggin <npiggin@gmail.com>]

Use the spin_begin/spin_cpu_relax/spin_end APIs in qspinlock, which helps
to prevent threads issuing a lot of expensive priority nops which may not
have much effect due to immediately executing low then medium priority.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
---
 arch/powerpc/lib/qspinlock.c | 41 ++++++++++++++++++++++++++++++++----
 1 file changed, 37 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 830a90a66f5f..ea8886e2922b 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -203,6 +203,7 @@ static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
 	BUG();
 }
 
+/* Called inside spin_begin() */
 static __always_inline void __yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt, bool mustq)
 {
 	int owner;
@@ -222,6 +223,8 @@ static __always_inline void __yield_to_locked_owner(struct qspinlock *lock, u32
 	if ((yield_count & 1) == 0)
 		goto relax; /* owner vcpu is running */
 
+	spin_end();
+
 	/*
 	 * Read the lock word after sampling the yield count. On the other side
 	 * there may a wmb because the yield count update is done by the
@@ -237,18 +240,22 @@ static __always_inline void __yield_to_locked_owner(struct qspinlock *lock, u32
 		yield_to_preempted(owner, yield_count);
 		if (mustq)
 			set_mustq(lock);
+		spin_begin();
 		/* Don't relax if we yielded. Maybe we should? */
 		return;
 	}
+	spin_begin();
 relax:
-	cpu_relax();
+	spin_cpu_relax();
 }
 
+/* Called inside spin_begin() */
 static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
 {
 	__yield_to_locked_owner(lock, val, paravirt, false);
 }
 
+/* Called inside spin_begin() */
 static __always_inline void yield_head_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
 {
 	bool mustq = false;
@@ -286,6 +293,7 @@ static __always_inline void propagate_yield_cpu(struct qnode *node, u32 val, int
 	}
 }
 
+/* Called inside spin_begin() */
 static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *node, u32 val, bool paravirt)
 {
 	int prev_cpu = decode_tail_cpu(val);
@@ -310,14 +318,18 @@ static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *
 	if ((yield_count & 1) == 0)
 		goto yield_prev; /* owner vcpu is running */
 
+	spin_end();
+
 	smp_rmb();
 
 	if (yield_cpu == node->yield_cpu) {
 		if (node->next && node->next->yield_cpu != yield_cpu)
 			node->next->yield_cpu = yield_cpu;
 		yield_to_preempted(yield_cpu, yield_count);
+		spin_begin();
 		return;
 	}
+	spin_begin();
 
 yield_prev:
 	if (!pv_yield_prev)
@@ -327,15 +339,19 @@ static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *
 	if ((yield_count & 1) == 0)
 		goto relax; /* owner vcpu is running */
 
+	spin_end();
+
 	smp_rmb(); /* See __yield_to_locked_owner comment */
 
 	if (!node->locked) {
 		yield_to_preempted(prev_cpu, yield_count);
+		spin_begin();
 		return;
 	}
+	spin_begin();
 
 relax:
-	cpu_relax();
+	spin_cpu_relax();
 }
 
 
@@ -347,6 +363,8 @@ static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool parav
 		return false;
 
 	/* Attempt to steal the lock */
+	spin_begin();
+
 	do {
 		u32 val = READ_ONCE(lock->val);
 
@@ -354,8 +372,10 @@ static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool parav
 			break;
 
 		if (unlikely(!(val & _Q_LOCKED_VAL))) {
+			spin_end();
 			if (trylock_with_tail_cpu(lock, val))
 				return true;
+			spin_begin();
 		} else {
 			yield_to_locked_owner(lock, val, paravirt);
 		}
@@ -363,6 +383,8 @@ static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool parav
 		iters++;
 	} while (iters < get_steal_spins(paravirt));
 
+	spin_end();
+
 	return false;
 }
 
@@ -411,8 +433,10 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 		WRITE_ONCE(prev->next, node);
 
 		/* Wait for mcs node lock to be released */
+		spin_begin();
 		while (!node->locked)
 			yield_to_prev(lock, node, old, paravirt);
+		spin_end();
 
 		/* Clear out stale propagated yield_cpu */
 		if (paravirt && pv_yield_propagate_owner && node->yield_cpu != -1)
@@ -425,6 +449,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 		int set_yield_cpu = -1;
 
 		/* We're at the head of the waitqueue, wait for the lock. */
+		spin_begin();
 		for (;;) {
 			val = READ_ONCE(lock->val);
 			if (!(val & _Q_LOCKED_VAL))
@@ -433,6 +458,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 			propagate_yield_cpu(node, val, &set_yield_cpu, paravirt);
 			yield_head_to_locked_owner(lock, val, paravirt);
 		}
+		spin_end();
 
 		/* If we're the last queued, must clean up the tail. */
 		if ((val & _Q_TAIL_CPU_MASK) == tail) {
@@ -450,6 +476,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 
 again:
 		/* We're at the head of the waitqueue, wait for the lock. */
+		spin_begin();
 		for (;;) {
 			val = READ_ONCE(lock->val);
 			if (!(val & _Q_LOCKED_VAL))
@@ -465,6 +492,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 				val |= _Q_MUST_Q_VAL;
 			}
 		}
+		spin_end();
 
 		/* If we're the last queued, must clean up the tail. */
 		if ((val & _Q_TAIL_CPU_MASK) == tail) {
@@ -480,8 +508,13 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 
 unlock_next:
 	/* contended path; must wait for next != NULL (MCS protocol) */
-	while (!(next = READ_ONCE(node->next)))
-		cpu_relax();
+	next = READ_ONCE(node->next);
+	if (!next) {
+		spin_begin();
+		while (!(next = READ_ONCE(node->next)))
+			cpu_relax();
+		spin_end();
+	}
 
 	/*
 	 * Unlock the next mcs waiter node. Release barrier is not required
-- 
2.37.2