genirq/affinity: Add is_managed to struct irq_affinity_desc

douliyang · KAGA-KOKO · commit c410abbbacb9 · 2018-12-19T11:32:08.000+01:00
Devices which use managed interrupts usually have two classes of interrupts: - Interrupts for multiple device queues - Interrupts for general device management Currently both classes are treated the same way, i.e. as managed interrupts. The general interrupts get the default affinity mask assigned while the device queue interrupts are spread out over the possible CPUs. Treating the general interrupts as managed is both a limitation and under certain circumstances a bug. Assume the following situation: default_irq_affinity = 4..7 So if CPUs 4-7 are offlined, then the core code will shut down the device management interrupts because the last CPU in their affinity mask went offline. It's also a limitation because it's desired to allow manual placement of the general device interrupts for various reasons. If they are marked managed then the interrupt affinity setting from both user and kernel space is disabled. That limitation was reported by Kashyap and Sumit. Expand struct irq_affinity_desc with a new bit 'is_managed' which is set for truly managed interrupts (queue interrupts) and cleared for the general device interrupts. [ tglx: Simplify code and massage changelog ] Reported-by: Kashyap Desai <kashyap.desai@broadcom.com> Reported-by: Sumit Saxena <sumit.saxena@broadcom.com> Signed-off-by: Dou Liyang <douliyangs@gmail.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: linux-pci@vger.kernel.org Cc: shivasharan.srikanteshwara@broadcom.com Cc: ming.lei@redhat.com Cc: hch@lst.de Cc: bhelgaas@google.com Cc: douliyang1@huawei.com Link: https://lkml.kernel.org/r/20181204155122.6327-3-douliyangs@gmail.com
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
@@ -263,6 +263,7 @@ struct irq_affinity {
  */
 struct irq_affinity_desc {
 	struct cpumask	mask;
+	unsigned int	is_managed : 1;
 };
 
 #if defined(CONFIG_SMP)
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
@@ -289,6 +289,10 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	for (; curvec < nvecs; curvec++)
 		cpumask_copy(&masks[curvec].mask, irq_default_affinity);
 
+	/* Mark the managed interrupts */
+	for (i = affd->pre_vectors; i < nvecs - affd->post_vectors; i++)
+		masks[i].is_managed = 1;
+
 outnodemsk:
 	free_node_to_cpumask(node_to_cpumask);
 	return masks;
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
@@ -453,27 +453,30 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		       struct module *owner)
 {
 	struct irq_desc *desc;
-	unsigned int flags;
 	int i;
 
 	/* Validate affinity mask(s) */
 	if (affinity) {
-		for (i = 0; i < cnt; i++) {
+		for (i = 0; i < cnt; i++, i++) {
 			if (cpumask_empty(&affinity[i].mask))
 				return -EINVAL;
 		}
 	}
 
-	flags = affinity ? IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN : 0;
-
 	for (i = 0; i < cnt; i++) {
 		const struct cpumask *mask = NULL;
+		unsigned int flags = 0;
 
 		if (affinity) {
-			node = cpu_to_node(cpumask_first(affinity));
+			if (affinity->is_managed) {
+				flags = IRQD_AFFINITY_MANAGED |
+					IRQD_MANAGED_SHUTDOWN;
+			}
 			mask = &affinity->mask;
+			node = cpu_to_node(cpumask_first(mask));
 			affinity++;
 		}
+
 		desc = alloc_desc(start + i, node, flags, mask, owner);
 		if (!desc)
 			goto err;
