powerpc/qspinlock: add ability to prod new queue head CPU

After the head of the queue acquires the lock, it releases the
next waiter in the queue to become the new head. Add an option
to prod the new head if its vCPU was preempted. This may only
have an effect if queue waiters are yielding.

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/20221126095932.1234527-12-npiggin@gmail.com

arch/powerpc/lib/qspinlock.c

@@ -12,6 +12,7 @@
 struct qnode {
 	struct qnode	*next;
 	struct qspinlock *lock;
+	int		cpu;
 	int		yield_cpu;
 	u8		locked; /* 1 if lock acquired */
 };
@@ -30,6 +31,7 @@ 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 bool pv_yield_propagate_owner __read_mostly = true;
+static bool pv_prod_head __read_mostly = false;
 
 static DEFINE_PER_CPU_ALIGNED(struct qnodes, qnodes);
 
@@ -370,10 +372,11 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 	node = &qnodesp->nodes[idx];
 	node->next = NULL;
 	node->lock = lock;
+	node->cpu = smp_processor_id();
 	node->yield_cpu = -1;
 	node->locked = 0;
 
-	tail = encode_tail_cpu(smp_processor_id());
+	tail = encode_tail_cpu(node->cpu);
 
 	old = publish_tail_cpu(lock, tail);
 
@@ -439,7 +442,14 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
 	 * this store to locked. The corresponding barrier is the smp_rmb()
 	 * acquire barrier for mcs lock, above.
 	 */
-	WRITE_ONCE(next->locked, 1);
+	if (paravirt && pv_prod_head) {
+		int next_cpu = next->cpu;
+		WRITE_ONCE(next->locked, 1);
+		if (vcpu_is_preempted(next_cpu))
+			prod_cpu(next_cpu);
+	} else {
+		WRITE_ONCE(next->locked, 1);
+	}
 
 release:
 	qnodesp->count--; /* release the node */
@@ -590,6 +600,22 @@ static int pv_yield_propagate_owner_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_pv_yield_propagate_owner, pv_yield_propagate_owner_get, pv_yield_propagate_owner_set, "%llu\n");
 
+static int pv_prod_head_set(void *data, u64 val)
+{
+	pv_prod_head = !!val;
+
+	return 0;
+}
+
+static int pv_prod_head_get(void *data, u64 *val)
+{
+	*val = pv_prod_head;
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_pv_prod_head, pv_prod_head_get, pv_prod_head_set, "%llu\n");
+
 static __init int spinlock_debugfs_init(void)
 {
 	debugfs_create_file("qspl_steal_spins", 0600, arch_debugfs_dir, NULL, &fops_steal_spins);
@@ -599,6 +625,7 @@ static __init int spinlock_debugfs_init(void)
 		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);
 		debugfs_create_file("qspl_pv_yield_propagate_owner", 0600, arch_debugfs_dir, NULL, &fops_pv_yield_propagate_owner);
+		debugfs_create_file("qspl_pv_prod_head", 0600, arch_debugfs_dir, NULL, &fops_pv_prod_head);
 	}
 
 	return 0;