sparse irq_desc[] array: core kernel and x86 changes

Impact: new feature

Problem on distro kernels: irq_desc[NR_IRQS] takes megabytes of RAM with
NR_CPUS set to large values. The goal is to be able to scale up to much
larger NR_IRQS value without impacting the (important) common case.

To solve this, we generalize irq_desc[NR_IRQS] to an (optional) array of
irq_desc pointers.

When CONFIG_SPARSE_IRQ=y is used, we use kzalloc_node to get irq_desc,
this also makes the IRQ descriptors NUMA-local (to the site that calls
request_irq()).

This gets rid of the irq_cfg[] static array on x86 as well: irq_cfg now
uses desc->chip_data for x86 to store irq_cfg.

Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This commit is contained in:
Yinghai Lu
2008-12-05 18:58:31 -08:00
committed by Ingo Molnar
parent 218d11a8b0
commit 0b8f1efad3
23 changed files with 659 additions and 173 deletions

View File

@@ -19,17 +19,75 @@ struct irq_2_iommu {
u8 irte_mask;
};
static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
#ifdef CONFIG_SPARSE_IRQ
static struct irq_2_iommu *get_one_free_irq_2_iommu(int cpu)
{
struct irq_2_iommu *iommu;
int node;
node = cpu_to_node(cpu);
iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
printk(KERN_DEBUG "alloc irq_2_iommu on cpu %d node %d\n", cpu, node);
return iommu;
}
static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
{
return (irq < nr_irqs) ? irq_2_iommuX + irq : NULL;
struct irq_desc *desc;
desc = irq_to_desc(irq);
if (WARN_ON_ONCE(!desc))
return NULL;
return desc->irq_2_iommu;
}
static struct irq_2_iommu *irq_2_iommu_alloc_cpu(unsigned int irq, int cpu)
{
struct irq_desc *desc;
struct irq_2_iommu *irq_iommu;
/*
* alloc irq desc if not allocated already.
*/
desc = irq_to_desc_alloc_cpu(irq, cpu);
if (!desc) {
printk(KERN_INFO "can not get irq_desc for %d\n", irq);
return NULL;
}
irq_iommu = desc->irq_2_iommu;
if (!irq_iommu)
desc->irq_2_iommu = get_one_free_irq_2_iommu(cpu);
return desc->irq_2_iommu;
}
static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
{
return irq_2_iommu_alloc_cpu(irq, boot_cpu_id);
}
#else /* !CONFIG_SPARSE_IRQ */
static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
{
if (irq < nr_irqs)
return &irq_2_iommuX[irq];
return NULL;
}
static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
{
return irq_2_iommu(irq);
}
#endif
static DEFINE_SPINLOCK(irq_2_ir_lock);
@@ -86,9 +144,11 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
if (!count)
return -1;
#ifndef CONFIG_SPARSE_IRQ
/* protect irq_2_iommu_alloc later */
if (irq >= nr_irqs)
return -1;
#endif
/*
* start the IRTE search from index 0.
@@ -130,6 +190,12 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
table->base[i].present = 1;
irq_iommu = irq_2_iommu_alloc(irq);
if (!irq_iommu) {
spin_unlock(&irq_2_ir_lock);
printk(KERN_ERR "can't allocate irq_2_iommu\n");
return -1;
}
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = 0;
@@ -177,6 +243,12 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
irq_iommu = irq_2_iommu_alloc(irq);
if (!irq_iommu) {
spin_unlock(&irq_2_ir_lock);
printk(KERN_ERR "can't allocate irq_2_iommu\n");
return -1;
}
irq_iommu->iommu = iommu;
irq_iommu->irte_index = index;
irq_iommu->sub_handle = subhandle;