x86, irq: Allocate CPU vectors from device local CPUs if possible

On NUMA systems, an IO device may be associated with a NUMA node.
It may improve IO performance to allocate resources, such as memory
and interrupts, from device local node.

This patch introduces a mechanism to support CPU vector allocation
policies. It tries to allocate CPU vectors from CPUs on device local
node first, and then fallback to all online(global) CPUs.

This mechanism may be used to support NumaConnect systems to allocate
CPU vectors from device local node.

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Tested-by: Daniel J Blueman <daniel@numascale.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Link: http://lkml.kernel.org/r/1430967244-28905-1-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/kernel/apic/vector.c

@@ -210,6 +210,18 @@ static int assign_irq_vector(int irq, struct apic_chip_data *data,
 	return err;
 }
 
+static int assign_irq_vector_policy(int irq, int node,
+				    struct apic_chip_data *data,
+				    struct irq_alloc_info *info)
+{
+	if (info && info->mask)
+		return assign_irq_vector(irq, data, info->mask);
+	if (node != NUMA_NO_NODE &&
+	    assign_irq_vector(irq, data, cpumask_of_node(node)) == 0)
+		return 0;
+	return assign_irq_vector(irq, data, apic->target_cpus());
+}
+
 static void clear_irq_vector(int irq, struct apic_chip_data *data)
 {
 	int cpu, vector;
@@ -258,12 +270,6 @@ void copy_irq_alloc_info(struct irq_alloc_info *dst, struct irq_alloc_info *src)
 		memset(dst, 0, sizeof(*dst));
 }
 
-static inline const struct cpumask *
-irq_alloc_info_get_mask(struct irq_alloc_info *info)
-{
-	return (!info || !info->mask) ? apic->target_cpus() : info->mask;
-}
-
 static void x86_vector_free_irqs(struct irq_domain *domain,
 				 unsigned int virq, unsigned int nr_irqs)
 {
@@ -289,7 +295,6 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 {
 	struct irq_alloc_info *info = arg;
 	struct apic_chip_data *data;
-	const struct cpumask *mask;
 	struct irq_data *irq_data;
 	int i, err;
 
@@ -300,7 +305,6 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
 		return -ENOSYS;
 
-	mask = irq_alloc_info_get_mask(info);
 	for (i = 0; i < nr_irqs; i++) {
 		irq_data = irq_domain_get_irq_data(domain, virq + i);
 		BUG_ON(!irq_data);
@@ -318,7 +322,8 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irq_data->chip = &lapic_controller;
 		irq_data->chip_data = data;
 		irq_data->hwirq = virq + i;
-		err = assign_irq_vector(virq, data, mask);
+		err = assign_irq_vector_policy(virq, irq_data->node, data,
+					       info);
 		if (err)
 			goto error;
 	}