irqchip/gic-v3-its: Limit scope of VPE mapping to be per ITS

So far, we map all VPEs on all ITSs. While this is not wrong,
this is quite a big hammer, as moving a VPE around requires
all ITSs to be synchronized. Needles to say, this is an
expensive proposition.

Instead, let's switch to a mode where we issue VMAPP commands
only on ITSs that are actually involved in reporting interrupts
to the given VM.

For that purpose, we refcount the number of interrupts are are
mapped for this VM on each ITS, performing the map/unmap
operations as required. It then allows us to use this refcount
to only issue VMOVP to the ITSs that need to know about this
VM.

Signed-off-by: Marc Zyngier <marc.zyngier@arm.com>

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

@@ -971,6 +971,9 @@ static void its_send_vmovp(struct its_vpe *vpe)
 		if (!its->is_v4)
 			continue;
 
+		if (!vpe->its_vm->vlpi_count[its->list_nr])
+			continue;
+
 		desc.its_vmovp_cmd.col = &its->collections[col_id];
 		its_send_single_vcommand(its, its_build_vmovp_cmd, &desc);
 	}
@@ -1154,6 +1157,58 @@ static int its_irq_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+static void its_map_vm(struct its_node *its, struct its_vm *vm)
+{
+	unsigned long flags;
+
+	/* Not using the ITS list? Everything is always mapped. */
+	if (!its_list_map)
+		return;
+
+	raw_spin_lock_irqsave(&vmovp_lock, flags);
+
+	/*
+	 * If the VM wasn't mapped yet, iterate over the vpes and get
+	 * them mapped now.
+	 */
+	vm->vlpi_count[its->list_nr]++;
+
+	if (vm->vlpi_count[its->list_nr] == 1) {
+		int i;
+
+		for (i = 0; i < vm->nr_vpes; i++) {
+			struct its_vpe *vpe = vm->vpes[i];
+
+			/* Map the VPE to the first possible CPU */
+			vpe->col_idx = cpumask_first(cpu_online_mask);
+			its_send_vmapp(its, vpe, true);
+			its_send_vinvall(its, vpe);
+		}
+	}
+
+	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
+}
+
+static void its_unmap_vm(struct its_node *its, struct its_vm *vm)
+{
+	unsigned long flags;
+
+	/* Not using the ITS list? Everything is always mapped. */
+	if (!its_list_map)
+		return;
+
+	raw_spin_lock_irqsave(&vmovp_lock, flags);
+
+	if (!--vm->vlpi_count[its->list_nr]) {
+		int i;
+
+		for (i = 0; i < vm->nr_vpes; i++)
+			its_send_vmapp(its, vm->vpes[i], false);
+	}
+
+	raw_spin_unlock_irqrestore(&vmovp_lock, flags);
+}
+
 static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 {
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
@@ -1189,6 +1244,9 @@ static int its_vlpi_map(struct irq_data *d, struct its_cmd_info *info)
 		/* Already mapped, move it around */
 		its_send_vmovi(its_dev, event);
 	} else {
+		/* Ensure all the VPEs are mapped on this ITS */
+		its_map_vm(its_dev->its, info->map->vm);
+
 		/* Drop the physical mapping */
 		its_send_discard(its_dev, event);
 
@@ -1250,6 +1308,9 @@ static int its_vlpi_unmap(struct irq_data *d)
 				    LPI_PROP_ENABLED |
 				    LPI_PROP_GROUP1));
 
+	/* Potentially unmap the VM from this ITS */
+	its_unmap_vm(its_dev->its, its_dev->event_map.vm);
+
 	/*
 	 * Drop the refcount and make the device available again if
 	 * this was the last VLPI.
@@ -2463,6 +2524,9 @@ static void its_vpe_invall(struct its_vpe *vpe)
 		if (!its->is_v4)
 			continue;
 
+		if (its_list_map && !vpe->its_vm->vlpi_count[its->list_nr])
+			continue;
+
 		its_send_vinvall(its, vpe);
 	}
 }
@@ -2713,6 +2777,10 @@ static int its_vpe_irq_domain_activate(struct irq_domain *domain,
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	struct its_node *its;
 
+	/* If we use the list map, we issue VMAPP on demand... */
+	if (its_list_map)
+		return true;
+
 	/* Map the VPE to the first possible CPU */
 	vpe->col_idx = cpumask_first(cpu_online_mask);
 
@@ -2733,6 +2801,13 @@ static void its_vpe_irq_domain_deactivate(struct irq_domain *domain,
 	struct its_vpe *vpe = irq_data_get_irq_chip_data(d);
 	struct its_node *its;
 
+	/*
+	 * If we use the list map, we unmap the VPE once no VLPIs are
+	 * associated with the VM.
+	 */
+	if (its_list_map)
+		return;
+
 	list_for_each_entry(its, &its_nodes, entry) {
 		if (!its->is_v4)
 			continue;

include/linux/irqchip/arm-gic-v4.h

@@ -36,6 +36,7 @@ struct its_vm {
 	irq_hw_number_t		db_lpi_base;
 	unsigned long		*db_bitmap;
 	int			nr_db_lpis;
+	u32			vlpi_count[GICv4_ITS_LIST_MAX];
 };
 
 /* Embedded in kvm_vcpu.arch */