irq.c

来自「优龙2410linux2.6.8内核源代码」· C语言 代码 · 共 1,017 行 · 第 1/2 页

			/* This is not a real spurrious interrupt, we
			 * have to eoi it, so we jump to out
			 */
			mask_irq(irq);
			goto out;
		}
		status &= ~IRQ_PENDING; /* we commit to handling */
		status |= IRQ_INPROGRESS; /* we are handling it */
	}
	desc->status = status;

	/*
	 * If there is no IRQ handler or it was disabled, exit early.
	   Since we set PENDING, if another processor is handling
	   a different instance of this same irq, the other processor
	   will take care of it.
	 */
	if (unlikely(!action))
		goto out;

	/*
	 * Edge triggered interrupts need to remember
	 * pending events.
	 * This applies to any hw interrupts that allow a second
	 * instance of the same irq to arrive while we are in do_IRQ
	 * or in the handler. But the code here only handles the _second_
	 * instance of the irq, not the third or fourth. So it is mostly
	 * useful for irq hardware that does not mask cleanly in an
	 * SMP environment.
	 */
	for (;;) {
		spin_unlock(&desc->lock);

#ifdef CONFIG_IRQSTACKS
		/* Switch to the irq stack to handle this */
		curtp = current_thread_info();
		irqtp = hardirq_ctx[smp_processor_id()];
		if (curtp != irqtp) {
			irqtp->task = curtp->task;
			irqtp->flags = 0;
			action_ret = call_handle_irq_event(irq, regs, action, irqtp);
			irqtp->task = NULL;
			if (irqtp->flags)
				set_bits(irqtp->flags, &curtp->flags);
		} else
#endif
			action_ret = handle_irq_event(irq, regs, action);

		spin_lock(&desc->lock);
		if (!noirqdebug)
			note_interrupt(irq, desc, action_ret);
		if (likely(!(desc->status & IRQ_PENDING)))
			break;
		desc->status &= ~IRQ_PENDING;
	}
out:
	desc->status &= ~IRQ_INPROGRESS;
	/*
	 * The ->end() handler has to deal with interrupts which got
	 * disabled while the handler was running.
	 */
	if (desc->handler) {
		if (desc->handler->end)
			desc->handler->end(irq);
		else if (desc->handler->enable)
			desc->handler->enable(irq);
	}
	spin_unlock(&desc->lock);
}

#ifdef CONFIG_PPC_ISERIES
void do_IRQ(struct pt_regs *regs)
{
	struct paca_struct *lpaca;
	struct ItLpQueue *lpq;

	irq_enter();

#ifdef CONFIG_DEBUG_STACKOVERFLOW
	/* Debugging check for stack overflow: is there less than 4KB free? */
	{
		long sp;

		sp = __get_SP() & (THREAD_SIZE-1);

		if (unlikely(sp < (sizeof(struct thread_info) + 4096))) {
			printk("do_IRQ: stack overflow: %ld\n",
				sp - sizeof(struct thread_info));
			dump_stack();
		}
	}
#endif

	lpaca = get_paca();
#ifdef CONFIG_SMP
	if (lpaca->lppaca.xIntDword.xFields.xIpiCnt) {
		lpaca->lppaca.xIntDword.xFields.xIpiCnt = 0;
		iSeries_smp_message_recv(regs);
	}
#endif /* CONFIG_SMP */
	lpq = lpaca->lpqueue_ptr;
	if (lpq && ItLpQueue_isLpIntPending(lpq))
		lpevent_count += ItLpQueue_process(lpq, regs);

	irq_exit();

	if (lpaca->lppaca.xIntDword.xFields.xDecrInt) {
		lpaca->lppaca.xIntDword.xFields.xDecrInt = 0;
		/* Signal a fake decrementer interrupt */
		timer_interrupt(regs);
	}
}

#else	/* CONFIG_PPC_ISERIES */

void do_IRQ(struct pt_regs *regs)
{
	int irq;

	irq_enter();

#ifdef CONFIG_DEBUG_STACKOVERFLOW
	/* Debugging check for stack overflow: is there less than 4KB free? */
	{
		long sp;

		sp = __get_SP() & (THREAD_SIZE-1);

		if (unlikely(sp < (sizeof(struct thread_info) + 4096))) {
			printk("do_IRQ: stack overflow: %ld\n",
				sp - sizeof(struct thread_info));
			dump_stack();
		}
	}
#endif

	irq = ppc_md.get_irq(regs);

	if (irq >= 0)
		ppc_irq_dispatch_handler(regs, irq);
	else
		/* That's not SMP safe ... but who cares ? */
		ppc_spurious_interrupts++;

	irq_exit();
}
#endif	/* CONFIG_PPC_ISERIES */

unsigned long probe_irq_on (void)
{
	return 0;
}

EXPORT_SYMBOL(probe_irq_on);

int probe_irq_off (unsigned long irqs)
{
	return 0;
}

EXPORT_SYMBOL(probe_irq_off);

unsigned int probe_irq_mask(unsigned long irqs)
{
	return 0;
}

void __init init_IRQ(void)
{
	static int once = 0;

	if (once)
		return;

	once++;

	ppc_md.init_IRQ();
	irq_ctx_init();
}

static struct proc_dir_entry * root_irq_dir;
static struct proc_dir_entry * irq_dir [NR_IRQS];
static struct proc_dir_entry * smp_affinity_entry [NR_IRQS];

/* Protected by get_irq_desc(irq)->lock. */
#ifdef CONFIG_IRQ_ALL_CPUS
cpumask_t irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_ALL };
#else  /* CONFIG_IRQ_ALL_CPUS */
cpumask_t irq_affinity [NR_IRQS] = { [0 ... NR_IRQS-1] = CPU_MASK_NONE };
#endif /* CONFIG_IRQ_ALL_CPUS */

static int irq_affinity_read_proc (char *page, char **start, off_t off,
			int count, int *eof, void *data)
{
	int len = cpumask_scnprintf(page, count, irq_affinity[(long)data]);
	if (count - len < 2)
		return -EINVAL;
	len += sprintf(page + len, "\n");
	return len;
}

static int irq_affinity_write_proc (struct file *file, const char __user *buffer,
					unsigned long count, void *data)
{
	unsigned int irq = (long)data;
	irq_desc_t *desc = get_irq_desc(irq);
	int ret;
	cpumask_t new_value, tmp;

	if (!desc->handler->set_affinity)
		return -EIO;

	ret = cpumask_parse(buffer, count, new_value);
	if (ret != 0)
		return ret;

	/*
	 * We check for CPU_MASK_ALL in xics to send irqs to all cpus.
	 * In some cases CPU_MASK_ALL is smaller than the cpumask (eg
	 * NR_CPUS == 32 and cpumask is a long), so we mask it here to
	 * be consistent.
	 */
	cpus_and(new_value, new_value, CPU_MASK_ALL);

	/*
	 * Grab lock here so cpu_online_map can't change, and also
	 * protect irq_affinity[].
	 */
	spin_lock(&desc->lock);

	/*
	 * Do not allow disabling IRQs completely - it's a too easy
	 * way to make the system unusable accidentally :-) At least
	 * one online CPU still has to be targeted.
	 */
	cpus_and(tmp, new_value, cpu_online_map);
	if (cpus_empty(tmp)) {
		ret = -EINVAL;
		goto out;
	}

	irq_affinity[irq] = new_value;
	desc->handler->set_affinity(irq, new_value);
	ret = count;

out:
	spin_unlock(&desc->lock);
	return ret;
}

static int prof_cpu_mask_read_proc (char *page, char **start, off_t off,
			int count, int *eof, void *data)
{
	int len = cpumask_scnprintf(page, count, *(cpumask_t *)data);
	if (count - len < 2)
		return -EINVAL;
	len += sprintf(page + len, "\n");
	return len;
}

static int prof_cpu_mask_write_proc (struct file *file, const char __user *buffer,
					unsigned long count, void *data)
{
	cpumask_t *mask = (cpumask_t *)data;
	unsigned long full_count = count, err;
	cpumask_t new_value;

	err = cpumask_parse(buffer, count, new_value);
	if (err)
		return err;

	*mask = new_value;

#ifdef CONFIG_PPC_ISERIES
	{
		unsigned i;
		for (i=0; i<NR_CPUS; ++i) {
			if ( paca[i].prof_buffer && cpu_isset(i, new_value) )
				paca[i].prof_enabled = 1;
			else
				paca[i].prof_enabled = 0;
		}
	}
#endif

	return full_count;
}

#define MAX_NAMELEN 10

static void register_irq_proc (unsigned int irq)
{
	struct proc_dir_entry *entry;
	char name [MAX_NAMELEN];

	if (!root_irq_dir || (irq_desc[irq].handler == NULL) || irq_dir[irq])
		return;

	memset(name, 0, MAX_NAMELEN);
	sprintf(name, "%d", irq);

	/* create /proc/irq/1234 */
	irq_dir[irq] = proc_mkdir(name, root_irq_dir);

	/* create /proc/irq/1234/smp_affinity */
	entry = create_proc_entry("smp_affinity", 0600, irq_dir[irq]);

	if (entry) {
		entry->nlink = 1;
		entry->data = (void *)(long)irq;
		entry->read_proc = irq_affinity_read_proc;
		entry->write_proc = irq_affinity_write_proc;
	}

	smp_affinity_entry[irq] = entry;
}

unsigned long prof_cpu_mask = -1;

void init_irq_proc (void)
{
	struct proc_dir_entry *entry;
	int i;

	/* create /proc/irq */
	root_irq_dir = proc_mkdir("irq", NULL);

	/* create /proc/irq/prof_cpu_mask */
	entry = create_proc_entry("prof_cpu_mask", 0600, root_irq_dir);

	if (!entry)
		return;

	entry->nlink = 1;
	entry->data = (void *)&prof_cpu_mask;
	entry->read_proc = prof_cpu_mask_read_proc;
	entry->write_proc = prof_cpu_mask_write_proc;

	/*
	 * Create entries for all existing IRQs.
	 */
	for_each_irq(i) {
		if (get_irq_desc(i)->handler == NULL)
			continue;
		register_irq_proc(i);
	}
}

irqreturn_t no_action(int irq, void *dev, struct pt_regs *regs)
{
	return IRQ_NONE;
}

#ifndef CONFIG_PPC_ISERIES
/*
 * Virtual IRQ mapping code, used on systems with XICS interrupt controllers.
 */

#define UNDEFINED_IRQ 0xffffffff
unsigned int virt_irq_to_real_map[NR_IRQS];

/*
 * Don't use virtual irqs 0, 1, 2 for devices.
 * The pcnet32 driver considers interrupt numbers < 2 to be invalid,
 * and 2 is the XICS IPI interrupt.
 * We limit virtual irqs to 17 less than NR_IRQS so that when we
 * offset them by 16 (to reserve the first 16 for ISA interrupts)
 * we don't end up with an interrupt number >= NR_IRQS.
 */
#define MIN_VIRT_IRQ	3
#define MAX_VIRT_IRQ	(NR_IRQS - NUM_ISA_INTERRUPTS - 1)
#define NR_VIRT_IRQS	(MAX_VIRT_IRQ - MIN_VIRT_IRQ + 1)

void
virt_irq_init(void)
{
	int i;
	for (i = 0; i < NR_IRQS; i++)
		virt_irq_to_real_map[i] = UNDEFINED_IRQ;
}

/* Create a mapping for a real_irq if it doesn't already exist.
 * Return the virtual irq as a convenience.
 */
int virt_irq_create_mapping(unsigned int real_irq)
{
	unsigned int virq, first_virq;
	static int warned;

	if (naca->interrupt_controller == IC_OPEN_PIC)
		return real_irq;	/* no mapping for openpic (for now) */

	/* don't map interrupts < MIN_VIRT_IRQ */
	if (real_irq < MIN_VIRT_IRQ) {
		virt_irq_to_real_map[real_irq] = real_irq;
		return real_irq;
	}

	/* map to a number between MIN_VIRT_IRQ and MAX_VIRT_IRQ */
	virq = real_irq;
	if (virq > MAX_VIRT_IRQ)
		virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;

	/* search for this number or a free slot */
	first_virq = virq;
	while (virt_irq_to_real_map[virq] != UNDEFINED_IRQ) {
		if (virt_irq_to_real_map[virq] == real_irq)
			return virq;
		if (++virq > MAX_VIRT_IRQ)
			virq = MIN_VIRT_IRQ;
		if (virq == first_virq)
			goto nospace;	/* oops, no free slots */
	}

	virt_irq_to_real_map[virq] = real_irq;
	return virq;

 nospace:
	if (!warned) {
		printk(KERN_CRIT "Interrupt table is full\n");
		printk(KERN_CRIT "Increase NR_IRQS (currently %d) "
		       "in your kernel sources and rebuild.\n", NR_IRQS);
		warned = 1;
	}
	return NO_IRQ;
}

/*
 * In most cases will get a hit on the very first slot checked in the
 * virt_irq_to_real_map.  Only when there are a large number of
 * IRQs will this be expensive.
 */
unsigned int real_irq_to_virt_slowpath(unsigned int real_irq)
{
	unsigned int virq;
	unsigned int first_virq;

	virq = real_irq;

	if (virq > MAX_VIRT_IRQ)
		virq = (virq % NR_VIRT_IRQS) + MIN_VIRT_IRQ;

	first_virq = virq;

	do {
		if (virt_irq_to_real_map[virq] == real_irq)
			return virq;

		virq++;

		if (virq >= MAX_VIRT_IRQ)
			virq = 0;

	} while (first_virq != virq);

	return NO_IRQ;

}

#endif /* CONFIG_PPC_ISERIES */

#ifdef CONFIG_IRQSTACKS
struct thread_info *softirq_ctx[NR_CPUS];
struct thread_info *hardirq_ctx[NR_CPUS];

void irq_ctx_init(void)
{
	struct thread_info *tp;
	int i;

	for (i = 0; i < NR_CPUS; i++) {
		memset((void *)softirq_ctx[i], 0, THREAD_SIZE);
		tp = softirq_ctx[i];
		tp->cpu = i;
		tp->preempt_count = SOFTIRQ_OFFSET;

		memset((void *)hardirq_ctx[i], 0, THREAD_SIZE);
		tp = hardirq_ctx[i];
		tp->cpu = i;
		tp->preempt_count = HARDIRQ_OFFSET;
	}
}

void do_softirq(void)
{
	unsigned long flags;
	struct thread_info *curtp, *irqtp;

	if (in_interrupt())
		return;

	local_irq_save(flags);

	if (local_softirq_pending()) {
		curtp = current_thread_info();
		irqtp = softirq_ctx[smp_processor_id()];
		irqtp->task = curtp->task;
		call_do_softirq(irqtp);
		irqtp->task = NULL;
	}

	local_irq_restore(flags);
}
EXPORT_SYMBOL(do_softirq);

#endif /* CONFIG_IRQSTACKS */