Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "The irq department delivers:

   - Expand the generic infrastructure handling the irq migration on CPU
     hotplug and convert X86 over to it. (Thomas Gleixner)

     Aside of consolidating code this is a preparatory change for:

   - Finalizing the affinity management for multi-queue devices. The
     main change here is to shut down interrupts which are affine to a
     outgoing CPU and reenabling them when the CPU comes online again.
     That avoids moving interrupts pointlessly around and breaking and
     reestablishing affinities for no value. (Christoph Hellwig)

     Note: This contains also the BLOCK-MQ and NVME changes which depend
     on the rework of the irq core infrastructure. Jens acked them and
     agreed that they should go with the irq changes.

   - Consolidation of irq domain code (Marc Zyngier)

   - State tracking consolidation in the core code (Jeffy Chen)

   - Add debug infrastructure for hierarchical irq domains (Thomas
     Gleixner)

   - Infrastructure enhancement for managing generic interrupt chips via
     devmem (Bartosz Golaszewski)

   - Constification work all over the place (Tobias Klauser)

   - Two new interrupt controller drivers for MVEBU (Thomas Petazzoni)

   - The usual set of fixes, updates and enhancements all over the
     place"

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (112 commits)
  irqchip/or1k-pic: Fix interrupt acknowledgement
  irqchip/irq-mvebu-gicp: Allocate enough memory for spi_bitmap
  irqchip/gic-v3: Fix out-of-bound access in gic_set_affinity
  nvme: Allocate queues for all possible CPUs
  blk-mq: Create hctx for each present CPU
  blk-mq: Include all present CPUs in the default queue mapping
  genirq: Avoid unnecessary low level irq function calls
  genirq: Set irq masked state when initializing irq_desc
  genirq/timings: Add infrastructure for estimating the next interrupt arrival time
  genirq/timings: Add infrastructure to track the interrupt timings
  genirq/debugfs: Remove pointless NULL pointer check
  irqchip/gic-v3-its: Don't assume GICv3 hardware supports 16bit INTID
  irqchip/gic-v3-its: Add ACPI NUMA node mapping
  irqchip/gic-v3-its-platform-msi: Make of_device_ids const
  irqchip/gic-v3-its: Make of_device_ids const
  irqchip/irq-mvebu-icu: Add new driver for Marvell ICU
  irqchip/irq-mvebu-gicp: Add new driver for Marvell GICP
  dt-bindings/interrupt-controller: Add DT binding for the Marvell ICU
  genirq/irqdomain: Remove auto-recursive hierarchy support
  irqchip/MSI: Use irq_domain_update_bus_token instead of an open coded access
  ...

1 files changed, 63 insertions, 13 deletions

diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index e2d356dd7581..d2747f9c5707 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -1,4 +1,7 @@
-
+/*
+ * Copyright (C) 2016 Thomas Gleixner.
+ * Copyright (C) 2016-2017 Christoph Hellwig.
+ */
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
@@ -35,13 +38,54 @@ static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
 	}
 }
 
-static int get_nodes_in_cpumask(const struct cpumask *mask, nodemask_t *nodemsk)
+static cpumask_var_t *alloc_node_to_present_cpumask(void)
+{
+	cpumask_var_t *masks;
+	int node;
+
+	masks = kcalloc(nr_node_ids, sizeof(cpumask_var_t), GFP_KERNEL);
+	if (!masks)
+		return NULL;
+
+	for (node = 0; node < nr_node_ids; node++) {
+		if (!zalloc_cpumask_var(&masks[node], GFP_KERNEL))
+			goto out_unwind;
+	}
+
+	return masks;
+
+out_unwind:
+	while (--node >= 0)
+		free_cpumask_var(masks[node]);
+	kfree(masks);
+	return NULL;
+}
+
+static void free_node_to_present_cpumask(cpumask_var_t *masks)
+{
+	int node;
+
+	for (node = 0; node < nr_node_ids; node++)
+		free_cpumask_var(masks[node]);
+	kfree(masks);
+}
+
+static void build_node_to_present_cpumask(cpumask_var_t *masks)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu)
+		cpumask_set_cpu(cpu, masks[cpu_to_node(cpu)]);
+}
+
+static int get_nodes_in_cpumask(cpumask_var_t *node_to_present_cpumask,
+				const struct cpumask *mask, nodemask_t *nodemsk)
 {
 	int n, nodes = 0;
 
 	/* Calculate the number of nodes in the supplied affinity mask */
-	for_each_online_node(n) {
-		if (cpumask_intersects(mask, cpumask_of_node(n))) {
+	for_each_node(n) {
+		if (cpumask_intersects(mask, node_to_present_cpumask[n])) {
 			node_set(n, *nodemsk);
 			nodes++;
 		}
@@ -64,7 +108,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	int last_affv = affv + affd->pre_vectors;
 	nodemask_t nodemsk = NODE_MASK_NONE;
 	struct cpumask *masks;
-	cpumask_var_t nmsk;
+	cpumask_var_t nmsk, *node_to_present_cpumask;
 
 	if (!zalloc_cpumask_var(&nmsk, GFP_KERNEL))
 		return NULL;
@@ -73,13 +117,19 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	if (!masks)
 		goto out;
 
+	node_to_present_cpumask = alloc_node_to_present_cpumask();
+	if (!node_to_present_cpumask)
+		goto out;
+
 	/* Fill out vectors at the beginning that don't need affinity */
 	for (curvec = 0; curvec < affd->pre_vectors; curvec++)
 		cpumask_copy(masks + curvec, irq_default_affinity);
 
 	/* Stabilize the cpumasks */
 	get_online_cpus();
-	nodes = get_nodes_in_cpumask(cpu_online_mask, &nodemsk);
+	build_node_to_present_cpumask(node_to_present_cpumask);
+	nodes = get_nodes_in_cpumask(node_to_present_cpumask, cpu_present_mask,
+				     &nodemsk);
 
 	/*
 	 * If the number of nodes in the mask is greater than or equal the
@@ -87,7 +137,8 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 	 */
 	if (affv <= nodes) {
 		for_each_node_mask(n, nodemsk) {
-			cpumask_copy(masks + curvec, cpumask_of_node(n));
+			cpumask_copy(masks + curvec,
+				     node_to_present_cpumask[n]);
 			if (++curvec == last_affv)
 				break;
 		}
@@ -101,7 +152,7 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd)
 		vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes;
 
 		/* Get the cpus on this node which are in the mask */
-		cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n));
+		cpumask_and(nmsk, cpu_present_mask, node_to_present_cpumask[n]);
 
 		/* Calculate the number of cpus per vector */
 		ncpus = cpumask_weight(nmsk);
@@ -133,6 +184,7 @@ done:
 	/* Fill out vectors at the end that don't need affinity */
 	for (; curvec < nvecs; curvec++)
 		cpumask_copy(masks + curvec, irq_default_affinity);
+	free_node_to_present_cpumask(node_to_present_cpumask);
 out:
 	free_cpumask_var(nmsk);
 	return masks;
@@ -147,12 +199,10 @@ int irq_calc_affinity_vectors(int maxvec, const struct irq_affinity *affd)
 {
 	int resv = affd->pre_vectors + affd->post_vectors;
 	int vecs = maxvec - resv;
-	int cpus;
+	int ret;
 
-	/* Stabilize the cpumasks */
 	get_online_cpus();
-	cpus = cpumask_weight(cpu_online_mask);
+	ret = min_t(int, cpumask_weight(cpu_present_mask), vecs) + resv;
 	put_online_cpus();
-
-	return min(cpus, vecs) + resv;
+	return ret;
 }