powerpc/qspinlock: allow stealing when head of queue yields

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.

Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20221126095932.1234527-10-npiggin@gmail.com

arch/powerpc/lib/qspinlock.c

@@ -26,6 +26,7 @@ static bool maybe_stealers __read_mostly = true;
 static int head_spins __read_mostly = (1 << 8);
 
 static bool pv_yield_owner __read_mostly = true;
+static bool pv_yield_allow_steal __read_mostly = false;
 static bool pv_yield_prev __read_mostly = true;
 
 static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
@@ -135,6 +136,22 @@ static __always_inline u32 set_mustq(struct qspinlock *lock)
 	return prev;
 }
 
+static __always_inline u32 clear_mustq(struct qspinlock *lock)
+{
+	u32 prev;
+
+	asm volatile(
+"1:	lwarx	%0,0,%1		# clear_mustq				\n"
+"	andc	%0,%0,%2						\n"
+"	stwcx.	%0,0,%1							\n"
+"	bne-	1b							\n"
+	: "=&r" (prev)
+	: "r" (&lock->val), "r" (_Q_MUST_Q_VAL)
+	: "cr0", "memory");
+
+	return prev;
+}
+
 static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
 {
 	int cpu = decode_tail_cpu(val);
@@ -159,7 +176,7 @@ static struct qnode *get_tail_qnode(struct qspinlock *lock, u32 val)
 	BUG();
 }
 
-static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
+static __always_inline void __yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt, bool mustq)
 {
 	int owner;
 	u32 yield_count;
@@ -188,14 +205,33 @@ static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 va
 	smp_rmb();
 
 	if (READ_ONCE(lock->val) == val) {
+		if (mustq)
+			clear_mustq(lock);
 		yield_to_preempted(owner, yield_count);
+		if (mustq)
+			set_mustq(lock);
 		/* Don't relax if we yielded. Maybe we should? */
 		return;
 	}
 relax:
 	cpu_relax();
 }
 
+static __always_inline void yield_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
+{
+	__yield_to_locked_owner(lock, val, paravirt, false);
+}
+
+static __always_inline void yield_head_to_locked_owner(struct qspinlock *lock, u32 val, bool paravirt)
+{
+	bool mustq = false;
+
+	if ((val & _Q_MUST_Q_VAL) && pv_yield_allow_steal)
+		mustq = true;
+
+	__yield_to_locked_owner(lock, val, paravirt, mustq);
+}
+
 static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *node, u32 val, bool paravirt)
 {
 	int prev_cpu = decode_tail_cpu(val);
@@ -211,7 +247,7 @@ static __always_inline void yield_to_prev(struct qspinlock *lock, struct qnode *
 	if ((yield_count & 1) == 0)
 		goto relax; /* owner vcpu is running */
 
-	smp_rmb(); /* See yield_to_locked_owner comment */
+	smp_rmb(); /* See __yield_to_locked_owner comment */
 
 	if (!node->locked) {
 		yield_to_preempted(prev_cpu, yield_count);
@@ -308,7 +344,7 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 		if (!(val & _Q_LOCKED_VAL))
 			break;
 
-		yield_to_locked_owner(lock, val, paravirt);
+		yield_head_to_locked_owner(lock, val, paravirt);
 		if (!maybe_stealers)
 			continue;
 		iters++;
@@ -444,6 +480,22 @@ 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;
@@ -466,6 +518,7 @@ 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);
 	}