mirror of
https://mirrors.bfsu.edu.cn/git/linux.git
synced 2024-11-14 15:54:15 +08:00
478735e388
In /proc/stat, the number of per-IRQ event is shown by making a sum each irq's events on all cpus. But we can make use of kstat_irqs(). kstat_irqs() do the same calculation, If !CONFIG_GENERIC_HARDIRQ, it's not a big cost. (Both of the number of cpus and irqs are small.) If a system is very big and CONFIG_GENERIC_HARDIRQ, it does for_each_irq() for_each_cpu() - look up a radix tree - read desc->irq_stat[cpu] This seems not efficient. This patch adds kstat_irqs() for CONFIG_GENRIC_HARDIRQ and change the calculation as for_each_irq() look up radix tree for_each_cpu() - read desc->irq_stat[cpu] This reduces cost. A test on (4096cpusp, 256 nodes, 4592 irqs) host (by Jack Steiner) %time cat /proc/stat > /dev/null Before Patch: 2.459 sec After Patch : .561 sec [akpm@linux-foundation.org: unexport kstat_irqs, coding-style tweaks] [akpm@linux-foundation.org: fix unused variable 'per_irq_sum'] Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Tested-by: Jack Steiner <steiner@sgi.com> Acked-by: Jack Steiner <steiner@sgi.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
411 lines
9.2 KiB
C
411 lines
9.2 KiB
C
/*
|
|
* Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
|
|
* Copyright (C) 2005-2006, Thomas Gleixner, Russell King
|
|
*
|
|
* This file contains the interrupt descriptor management code
|
|
*
|
|
* Detailed information is available in Documentation/DocBook/genericirq
|
|
*
|
|
*/
|
|
#include <linux/irq.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/module.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/radix-tree.h>
|
|
#include <linux/bitmap.h>
|
|
|
|
#include "internals.h"
|
|
|
|
/*
|
|
* lockdep: we want to handle all irq_desc locks as a single lock-class:
|
|
*/
|
|
static struct lock_class_key irq_desc_lock_class;
|
|
|
|
#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
|
|
static void __init init_irq_default_affinity(void)
|
|
{
|
|
alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
|
|
cpumask_setall(irq_default_affinity);
|
|
}
|
|
#else
|
|
static void __init init_irq_default_affinity(void)
|
|
{
|
|
}
|
|
#endif
|
|
|
|
#ifdef CONFIG_SMP
|
|
static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
|
|
{
|
|
if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
|
|
return -ENOMEM;
|
|
|
|
#ifdef CONFIG_GENERIC_PENDING_IRQ
|
|
if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
|
|
free_cpumask_var(desc->irq_data.affinity);
|
|
return -ENOMEM;
|
|
}
|
|
#endif
|
|
return 0;
|
|
}
|
|
|
|
static void desc_smp_init(struct irq_desc *desc, int node)
|
|
{
|
|
desc->irq_data.node = node;
|
|
cpumask_copy(desc->irq_data.affinity, irq_default_affinity);
|
|
#ifdef CONFIG_GENERIC_PENDING_IRQ
|
|
cpumask_clear(desc->pending_mask);
|
|
#endif
|
|
}
|
|
|
|
static inline int desc_node(struct irq_desc *desc)
|
|
{
|
|
return desc->irq_data.node;
|
|
}
|
|
|
|
#else
|
|
static inline int
|
|
alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
|
|
static inline void desc_smp_init(struct irq_desc *desc, int node) { }
|
|
static inline int desc_node(struct irq_desc *desc) { return 0; }
|
|
#endif
|
|
|
|
static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
|
|
{
|
|
desc->irq_data.irq = irq;
|
|
desc->irq_data.chip = &no_irq_chip;
|
|
desc->irq_data.chip_data = NULL;
|
|
desc->irq_data.handler_data = NULL;
|
|
desc->irq_data.msi_desc = NULL;
|
|
desc->status = IRQ_DEFAULT_INIT_FLAGS;
|
|
desc->handle_irq = handle_bad_irq;
|
|
desc->depth = 1;
|
|
desc->irq_count = 0;
|
|
desc->irqs_unhandled = 0;
|
|
desc->name = NULL;
|
|
memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
|
|
desc_smp_init(desc, node);
|
|
}
|
|
|
|
int nr_irqs = NR_IRQS;
|
|
EXPORT_SYMBOL_GPL(nr_irqs);
|
|
|
|
static DEFINE_MUTEX(sparse_irq_lock);
|
|
static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
|
|
|
|
#ifdef CONFIG_SPARSE_IRQ
|
|
|
|
static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
|
|
|
|
static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
|
|
{
|
|
radix_tree_insert(&irq_desc_tree, irq, desc);
|
|
}
|
|
|
|
struct irq_desc *irq_to_desc(unsigned int irq)
|
|
{
|
|
return radix_tree_lookup(&irq_desc_tree, irq);
|
|
}
|
|
|
|
static void delete_irq_desc(unsigned int irq)
|
|
{
|
|
radix_tree_delete(&irq_desc_tree, irq);
|
|
}
|
|
|
|
#ifdef CONFIG_SMP
|
|
static void free_masks(struct irq_desc *desc)
|
|
{
|
|
#ifdef CONFIG_GENERIC_PENDING_IRQ
|
|
free_cpumask_var(desc->pending_mask);
|
|
#endif
|
|
free_cpumask_var(desc->irq_data.affinity);
|
|
}
|
|
#else
|
|
static inline void free_masks(struct irq_desc *desc) { }
|
|
#endif
|
|
|
|
static struct irq_desc *alloc_desc(int irq, int node)
|
|
{
|
|
struct irq_desc *desc;
|
|
gfp_t gfp = GFP_KERNEL;
|
|
|
|
desc = kzalloc_node(sizeof(*desc), gfp, node);
|
|
if (!desc)
|
|
return NULL;
|
|
/* allocate based on nr_cpu_ids */
|
|
desc->kstat_irqs = kzalloc_node(nr_cpu_ids * sizeof(*desc->kstat_irqs),
|
|
gfp, node);
|
|
if (!desc->kstat_irqs)
|
|
goto err_desc;
|
|
|
|
if (alloc_masks(desc, gfp, node))
|
|
goto err_kstat;
|
|
|
|
raw_spin_lock_init(&desc->lock);
|
|
lockdep_set_class(&desc->lock, &irq_desc_lock_class);
|
|
|
|
desc_set_defaults(irq, desc, node);
|
|
|
|
return desc;
|
|
|
|
err_kstat:
|
|
kfree(desc->kstat_irqs);
|
|
err_desc:
|
|
kfree(desc);
|
|
return NULL;
|
|
}
|
|
|
|
static void free_desc(unsigned int irq)
|
|
{
|
|
struct irq_desc *desc = irq_to_desc(irq);
|
|
|
|
unregister_irq_proc(irq, desc);
|
|
|
|
mutex_lock(&sparse_irq_lock);
|
|
delete_irq_desc(irq);
|
|
mutex_unlock(&sparse_irq_lock);
|
|
|
|
free_masks(desc);
|
|
kfree(desc->kstat_irqs);
|
|
kfree(desc);
|
|
}
|
|
|
|
static int alloc_descs(unsigned int start, unsigned int cnt, int node)
|
|
{
|
|
struct irq_desc *desc;
|
|
int i;
|
|
|
|
for (i = 0; i < cnt; i++) {
|
|
desc = alloc_desc(start + i, node);
|
|
if (!desc)
|
|
goto err;
|
|
mutex_lock(&sparse_irq_lock);
|
|
irq_insert_desc(start + i, desc);
|
|
mutex_unlock(&sparse_irq_lock);
|
|
}
|
|
return start;
|
|
|
|
err:
|
|
for (i--; i >= 0; i--)
|
|
free_desc(start + i);
|
|
|
|
mutex_lock(&sparse_irq_lock);
|
|
bitmap_clear(allocated_irqs, start, cnt);
|
|
mutex_unlock(&sparse_irq_lock);
|
|
return -ENOMEM;
|
|
}
|
|
|
|
struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
|
|
{
|
|
int res = irq_alloc_descs(irq, irq, 1, node);
|
|
|
|
if (res == -EEXIST || res == irq)
|
|
return irq_to_desc(irq);
|
|
return NULL;
|
|
}
|
|
|
|
int __init early_irq_init(void)
|
|
{
|
|
int i, initcnt, node = first_online_node;
|
|
struct irq_desc *desc;
|
|
|
|
init_irq_default_affinity();
|
|
|
|
/* Let arch update nr_irqs and return the nr of preallocated irqs */
|
|
initcnt = arch_probe_nr_irqs();
|
|
printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
|
|
|
|
for (i = 0; i < initcnt; i++) {
|
|
desc = alloc_desc(i, node);
|
|
set_bit(i, allocated_irqs);
|
|
irq_insert_desc(i, desc);
|
|
}
|
|
return arch_early_irq_init();
|
|
}
|
|
|
|
#else /* !CONFIG_SPARSE_IRQ */
|
|
|
|
struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
|
|
[0 ... NR_IRQS-1] = {
|
|
.status = IRQ_DEFAULT_INIT_FLAGS,
|
|
.handle_irq = handle_bad_irq,
|
|
.depth = 1,
|
|
.lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
|
|
}
|
|
};
|
|
|
|
static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
|
|
int __init early_irq_init(void)
|
|
{
|
|
int count, i, node = first_online_node;
|
|
struct irq_desc *desc;
|
|
|
|
init_irq_default_affinity();
|
|
|
|
printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
|
|
|
|
desc = irq_desc;
|
|
count = ARRAY_SIZE(irq_desc);
|
|
|
|
for (i = 0; i < count; i++) {
|
|
desc[i].irq_data.irq = i;
|
|
desc[i].irq_data.chip = &no_irq_chip;
|
|
desc[i].kstat_irqs = kstat_irqs_all[i];
|
|
alloc_masks(desc + i, GFP_KERNEL, node);
|
|
desc_smp_init(desc + i, node);
|
|
lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
|
|
}
|
|
return arch_early_irq_init();
|
|
}
|
|
|
|
struct irq_desc *irq_to_desc(unsigned int irq)
|
|
{
|
|
return (irq < NR_IRQS) ? irq_desc + irq : NULL;
|
|
}
|
|
|
|
struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
|
|
{
|
|
return irq_to_desc(irq);
|
|
}
|
|
|
|
static void free_desc(unsigned int irq)
|
|
{
|
|
dynamic_irq_cleanup(irq);
|
|
}
|
|
|
|
static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
|
|
{
|
|
return start;
|
|
}
|
|
#endif /* !CONFIG_SPARSE_IRQ */
|
|
|
|
/* Dynamic interrupt handling */
|
|
|
|
/**
|
|
* irq_free_descs - free irq descriptors
|
|
* @from: Start of descriptor range
|
|
* @cnt: Number of consecutive irqs to free
|
|
*/
|
|
void irq_free_descs(unsigned int from, unsigned int cnt)
|
|
{
|
|
int i;
|
|
|
|
if (from >= nr_irqs || (from + cnt) > nr_irqs)
|
|
return;
|
|
|
|
for (i = 0; i < cnt; i++)
|
|
free_desc(from + i);
|
|
|
|
mutex_lock(&sparse_irq_lock);
|
|
bitmap_clear(allocated_irqs, from, cnt);
|
|
mutex_unlock(&sparse_irq_lock);
|
|
}
|
|
|
|
/**
|
|
* irq_alloc_descs - allocate and initialize a range of irq descriptors
|
|
* @irq: Allocate for specific irq number if irq >= 0
|
|
* @from: Start the search from this irq number
|
|
* @cnt: Number of consecutive irqs to allocate.
|
|
* @node: Preferred node on which the irq descriptor should be allocated
|
|
*
|
|
* Returns the first irq number or error code
|
|
*/
|
|
int __ref
|
|
irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
|
|
{
|
|
int start, ret;
|
|
|
|
if (!cnt)
|
|
return -EINVAL;
|
|
|
|
mutex_lock(&sparse_irq_lock);
|
|
|
|
start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
|
|
ret = -EEXIST;
|
|
if (irq >=0 && start != irq)
|
|
goto err;
|
|
|
|
ret = -ENOMEM;
|
|
if (start >= nr_irqs)
|
|
goto err;
|
|
|
|
bitmap_set(allocated_irqs, start, cnt);
|
|
mutex_unlock(&sparse_irq_lock);
|
|
return alloc_descs(start, cnt, node);
|
|
|
|
err:
|
|
mutex_unlock(&sparse_irq_lock);
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* irq_reserve_irqs - mark irqs allocated
|
|
* @from: mark from irq number
|
|
* @cnt: number of irqs to mark
|
|
*
|
|
* Returns 0 on success or an appropriate error code
|
|
*/
|
|
int irq_reserve_irqs(unsigned int from, unsigned int cnt)
|
|
{
|
|
unsigned int start;
|
|
int ret = 0;
|
|
|
|
if (!cnt || (from + cnt) > nr_irqs)
|
|
return -EINVAL;
|
|
|
|
mutex_lock(&sparse_irq_lock);
|
|
start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
|
|
if (start == from)
|
|
bitmap_set(allocated_irqs, start, cnt);
|
|
else
|
|
ret = -EEXIST;
|
|
mutex_unlock(&sparse_irq_lock);
|
|
return ret;
|
|
}
|
|
|
|
/**
|
|
* irq_get_next_irq - get next allocated irq number
|
|
* @offset: where to start the search
|
|
*
|
|
* Returns next irq number after offset or nr_irqs if none is found.
|
|
*/
|
|
unsigned int irq_get_next_irq(unsigned int offset)
|
|
{
|
|
return find_next_bit(allocated_irqs, nr_irqs, offset);
|
|
}
|
|
|
|
/**
|
|
* dynamic_irq_cleanup - cleanup a dynamically allocated irq
|
|
* @irq: irq number to initialize
|
|
*/
|
|
void dynamic_irq_cleanup(unsigned int irq)
|
|
{
|
|
struct irq_desc *desc = irq_to_desc(irq);
|
|
unsigned long flags;
|
|
|
|
raw_spin_lock_irqsave(&desc->lock, flags);
|
|
desc_set_defaults(irq, desc, desc_node(desc));
|
|
raw_spin_unlock_irqrestore(&desc->lock, flags);
|
|
}
|
|
|
|
unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
|
|
{
|
|
struct irq_desc *desc = irq_to_desc(irq);
|
|
return desc ? desc->kstat_irqs[cpu] : 0;
|
|
}
|
|
|
|
#ifdef CONFIG_GENERIC_HARDIRQS
|
|
unsigned int kstat_irqs(unsigned int irq)
|
|
{
|
|
struct irq_desc *desc = irq_to_desc(irq);
|
|
int cpu;
|
|
int sum = 0;
|
|
|
|
if (!desc)
|
|
return 0;
|
|
for_each_possible_cpu(cpu)
|
|
sum += desc->kstat_irqs[cpu];
|
|
return sum;
|
|
}
|
|
#endif /* CONFIG_GENERIC_HARDIRQS */
|