irqchip/gic-v3-its: Track LPI distribution on a per CPU basis

In order to improve the distribution of LPIs among CPUs, let start by
tracking the number of LPIs assigned to CPUs, both for managed and
non-managed interrupts (as separate counters).
Signed-off-by: Marc Zyngier <maz@kernel.org>
Tested-by: John Garry <john.garry@huawei.com>
Link: https://lore.kernel.org/r/20200515165752.121296-2-maz@kernel.org

drivers/irqchip/irq-gic-v3-its.c

@@ -174,6 +174,13 @@ static struct {
 	int			next_victim;
 } vpe_proxy;
 
+struct cpu_lpi_count {
+	atomic_t	managed;
+	atomic_t	unmanaged;
+};
+
+static DEFINE_PER_CPU(struct cpu_lpi_count, cpu_lpi_count);
+
 static LIST_HEAD(its_nodes);
 static DEFINE_RAW_SPINLOCK(its_lock);
 static struct rdists *gic_rdists;
@@ -1510,6 +1517,30 @@ static void its_unmask_irq(struct irq_data *d)
 	lpi_update_config(d, 0, LPI_PROP_ENABLED);
 }
 
+static __maybe_unused u32 its_read_lpi_count(struct irq_data *d, int cpu)
+{
+	if (irqd_affinity_is_managed(d))
+		return atomic_read(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+
+	return atomic_read(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static void its_inc_lpi_count(struct irq_data *d, int cpu)
+{
+	if (irqd_affinity_is_managed(d))
+		atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+	else
+		atomic_inc(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
+static void its_dec_lpi_count(struct irq_data *d, int cpu)
+{
+	if (irqd_affinity_is_managed(d))
+		atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->managed);
+	else
+		atomic_dec(&per_cpu_ptr(&cpu_lpi_count, cpu)->unmanaged);
+}
+
 static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 			    bool force)
 {
@@ -1518,34 +1549,44 @@ static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val,
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	struct its_collection *target_col;
 	u32 id = its_get_event_id(d);
+	int prev_cpu;
 
 	/* A forwarded interrupt should use irq_set_vcpu_affinity */
 	if (irqd_is_forwarded_to_vcpu(d))
 		return -EINVAL;
 
+	prev_cpu = its_dev->event_map.col_map[id];
+	its_dec_lpi_count(d, prev_cpu);
+
        /* lpi cannot be routed to a redistributor that is on a foreign node */
 	if (its_dev->its->flags & ITS_FLAGS_WORKAROUND_CAVIUM_23144) {
 		if (its_dev->its->numa_node >= 0) {
 			cpu_mask = cpumask_of_node(its_dev->its->numa_node);
 			if (!cpumask_intersects(mask_val, cpu_mask))
-				return -EINVAL;
+				goto err;
 		}
 	}
 
 	cpu = cpumask_any_and(mask_val, cpu_mask);
 
 	if (cpu >= nr_cpu_ids)
-		return -EINVAL;
+		goto err;
 
 	/* don't set the affinity when the target cpu is same as current one */
-	if (cpu != its_dev->event_map.col_map[id]) {
+	if (cpu != prev_cpu) {
 		target_col = &its_dev->its->collections[cpu];
 		its_send_movi(its_dev, target_col, id);
 		its_dev->event_map.col_map[id] = cpu;
 		irq_data_update_effective_affinity(d, cpumask_of(cpu));
 	}
 
+	its_inc_lpi_count(d, cpu);
+
 	return IRQ_SET_MASK_OK_DONE;
+
+err:
+	its_inc_lpi_count(d, prev_cpu);
+	return -EINVAL;
 }
 
 static u64 its_irq_get_msi_base(struct its_device *its_dev)
@@ -3448,6 +3489,7 @@ static int its_irq_domain_activate(struct irq_domain *domain,
 		cpu = cpumask_first(cpu_online_mask);
 	}
 
+	its_inc_lpi_count(d, cpu);
 	its_dev->event_map.col_map[event] = cpu;
 	irq_data_update_effective_affinity(d, cpumask_of(cpu));
 
@@ -3462,6 +3504,7 @@ static void its_irq_domain_deactivate(struct irq_domain *domain,
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
 	u32 event = its_get_event_id(d);
 
+	its_dec_lpi_count(d, its_dev->event_map.col_map[event]);
 	/* Stop the delivery of interrupts */
 	its_send_discard(its_dev, event);
 }