[RFC PATCH 10/14] powerpc/qspinlock: allow stealing when head of queue yields

[Nicholas Piggin]

If the head of queue is preventing stealing but it finds the owner vCPU
is preempted, it will yield its cycles to the owner which could cause it
to become preempted. Add an option to re-allow stealers before yielding,
and disallow them again after returning from the yield.

Disable this option by default for now, i.e., no logical change.
---
 arch/powerpc/lib/qspinlock.c | 49 +++++++++++++++++++++++++++++++++---
 1 file changed, 45 insertions(+), 4 deletions(-)

diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
index 1a58ed51c060..4f1dc3322485 100644
--- a/arch/powerpc/lib/qspinlock.c
+++ b/arch/powerpc/lib/qspinlock.c
@@ -26,6 +26,7 @@ static bool MAYBE_STEALERS __read_mostly = true;
 static int HEAD_SPINS __read_mostly = (1<<13);
 
 static bool pv_yield_owner __read_mostly = true;
+static bool pv_yield_allow_steal __read_mostly = false;
 static bool pv_yield_prev __read_mostly = false;
 
 static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
@@ -163,6 +164,24 @@ static __always_inline u32 lock_set_mustq(struct qspinlock *lock)
 	return prev;
 }
 
+static __always_inline u32 lock_clear_mustq(struct qspinlock *lock)
+{
+	u32 new = _Q_MUST_Q_VAL;
+	u32 prev;
+
+	asm volatile(
+"1:	lwarx	%0,0,%1		# queued_spin_set_mustq			\n"
+"	andc	%0,%0,%2						\n"
+"	stwcx.	%0,0,%1							\n"
+"	bne-	1b							\n"
+	: "=&r" (prev)
+	: "r" (&lock->val), "r" (new)
+	: "cr0", "memory");
+
+	return prev;
+}
+
+
 static inline struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
 {
 	int cpu = get_tail_cpu(val);
@@ -178,7 +197,7 @@ static inline struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
 	BUG();
 }
 
-static void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
+static void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt, bool clear_mustq)
 {
 	int owner;
 	u32 yield_count;
@@ -207,7 +226,11 @@ static void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt
 	smp_rmb();
 
 	if (READ_ONCE(lock->val) == val) {
+		if (clear_mustq)
+			lock_clear_mustq(lock);
 		yield_to_preempted(owner, yield_count);
+		if (clear_mustq)
+			lock_set_mustq(lock);
 		/* Don't relax if we yielded. Maybe we should? */
 		return;
 	}
@@ -253,7 +276,7 @@ static __always_inline bool try_to_steal_lock(struct qspinlock *lock, bool parav
 			break;
 
 		if (val & _Q_LOCKED_VAL) {
-			yield_to_locked_owner(lock, val, paravirt);
+			yield_to_locked_owner(lock, val, paravirt, false);
 			continue;
 		}
 
@@ -317,7 +340,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 	if (!MAYBE_STEALERS) {
 		/* We're at the head of the waitqueue, wait for the lock. */
 		while ((val = READ_ONCE(lock->val)) & _Q_LOCKED_VAL)
-			yield_to_locked_owner(lock, val, paravirt);
+			yield_to_locked_owner(lock, val, paravirt, false);
 
 		/* If we're the last queued, must clean up the tail. */
 		if ((val & _Q_TAIL_CPU_MASK) == tail) {
@@ -337,7 +360,8 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 				lock_set_mustq(lock);
 				val |= _Q_MUST_Q_VAL;
 			}
-			yield_to_locked_owner(lock, val, paravirt);
+			yield_to_locked_owner(lock, val, paravirt,
+				pv_yield_allow_steal && (iters > HEAD_SPINS));
 		}
 
 		/* If we're the last queued, must clean up the tail. */
@@ -457,6 +481,22 @@ static int pv_yield_owner_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_owner, pv_yield_owner_get, pv_yield_owner_set, "%llu\n");
 
+static int pv_yield_allow_steal_set(void *data, u64 val)
+{
+	pv_yield_allow_steal = !!val;
+
+	return 0;
+}
+
+static int pv_yield_allow_steal_get(void *data, u64 *val)
+{
+	*val = pv_yield_allow_steal;
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_allow_steal, pv_yield_allow_steal_get, pv_yield_allow_steal_set, "%llu\n");
+
 static int pv_yield_prev_set(void *data, u64 val)
 {
 	pv_yield_prev = !!val;
@@ -479,6 +519,7 @@ static __init int spinlock_debugfs_init(void)
 	debugfs_create_file("qspl_head_spins", 0600, arch_debugfs_dir, NULL, &fops_head_spins);
 	if (is_shared_processor()) {
 		debugfs_create_file("qspl_pv_yield_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_owner);
+		debugfs_create_file("qspl_pv_yield_allow_steal", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_allow_steal);
 		debugfs_create_file("qspl_pv_yield_prev", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_prev);
 	}
 
-- 
2.35.1