io_apic_32.c

linux 内核源代码

	pin  = find_isa_irq_pin(8, mp_INT);
	if (pin == -1) {
		WARN_ON_ONCE(1);
		return;
	}
	apic = find_isa_irq_apic(8, mp_INT);
	if (apic == -1) {
		WARN_ON_ONCE(1);
		return;
	}

	entry0 = ioapic_read_entry(apic, pin);
	clear_IO_APIC_pin(apic, pin);

	memset(&entry1, 0, sizeof(entry1));

	entry1.dest_mode = 0;			/* physical delivery */
	entry1.mask = 0;			/* unmask IRQ now */
	entry1.dest.physical.physical_dest = hard_smp_processor_id();
	entry1.delivery_mode = dest_ExtINT;
	entry1.polarity = entry0.polarity;
	entry1.trigger = 0;
	entry1.vector = 0;

	ioapic_write_entry(apic, pin, entry1);

	save_control = CMOS_READ(RTC_CONTROL);
	save_freq_select = CMOS_READ(RTC_FREQ_SELECT);
	CMOS_WRITE((save_freq_select & ~RTC_RATE_SELECT) | 0x6,
		   RTC_FREQ_SELECT);
	CMOS_WRITE(save_control | RTC_PIE, RTC_CONTROL);

	i = 100;
	while (i-- > 0) {
		mdelay(10);
		if ((CMOS_READ(RTC_INTR_FLAGS) & RTC_PF) == RTC_PF)
			i -= 10;
	}

	CMOS_WRITE(save_control, RTC_CONTROL);
	CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT);
	clear_IO_APIC_pin(apic, pin);

	ioapic_write_entry(apic, pin, entry0);
}

int timer_uses_ioapic_pin_0;

/*
 * This code may look a bit paranoid, but it's supposed to cooperate with
 * a wide range of boards and BIOS bugs.  Fortunately only the timer IRQ
 * is so screwy.  Thanks to Brian Perkins for testing/hacking this beast
 * fanatically on his truly buggy board.
 */
static inline void __init check_timer(void)
{
	int apic1, pin1, apic2, pin2;
	int vector;
	unsigned long flags;

	local_irq_save(flags);

	/*
	 * get/set the timer IRQ vector:
	 */
	disable_8259A_irq(0);
	vector = assign_irq_vector(0);
	set_intr_gate(vector, interrupt[0]);

	/*
	 * Subtle, code in do_timer_interrupt() expects an AEOI
	 * mode for the 8259A whenever interrupts are routed
	 * through I/O APICs.  Also IRQ0 has to be enabled in
	 * the 8259A which implies the virtual wire has to be
	 * disabled in the local APIC.
	 */
	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_EXTINT);
	init_8259A(1);
	timer_ack = 1;
	if (timer_over_8254 > 0)
		enable_8259A_irq(0);

	pin1  = find_isa_irq_pin(0, mp_INT);
	apic1 = find_isa_irq_apic(0, mp_INT);
	pin2  = ioapic_i8259.pin;
	apic2 = ioapic_i8259.apic;

	if (pin1 == 0)
		timer_uses_ioapic_pin_0 = 1;

	printk(KERN_INFO "..TIMER: vector=0x%02X apic1=%d pin1=%d apic2=%d pin2=%d\n",
		vector, apic1, pin1, apic2, pin2);

	if (pin1 != -1) {
		/*
		 * Ok, does IRQ0 through the IOAPIC work?
		 */
		unmask_IO_APIC_irq(0);
		if (timer_irq_works()) {
			if (nmi_watchdog == NMI_IO_APIC) {
				disable_8259A_irq(0);
				setup_nmi();
				enable_8259A_irq(0);
			}
			if (disable_timer_pin_1 > 0)
				clear_IO_APIC_pin(0, pin1);
			goto out;
		}
		clear_IO_APIC_pin(apic1, pin1);
		printk(KERN_ERR "..MP-BIOS bug: 8254 timer not connected to "
				"IO-APIC\n");
	}

	printk(KERN_INFO "...trying to set up timer (IRQ0) through the 8259A ... ");
	if (pin2 != -1) {
		printk("\n..... (found pin %d) ...", pin2);
		/*
		 * legacy devices should be connected to IO APIC #0
		 */
		setup_ExtINT_IRQ0_pin(apic2, pin2, vector);
		if (timer_irq_works()) {
			printk("works.\n");
			if (pin1 != -1)
				replace_pin_at_irq(0, apic1, pin1, apic2, pin2);
			else
				add_pin_to_irq(0, apic2, pin2);
			if (nmi_watchdog == NMI_IO_APIC) {
				setup_nmi();
			}
			goto out;
		}
		/*
		 * Cleanup, just in case ...
		 */
		clear_IO_APIC_pin(apic2, pin2);
	}
	printk(" failed.\n");

	if (nmi_watchdog == NMI_IO_APIC) {
		printk(KERN_WARNING "timer doesn't work through the IO-APIC - disabling NMI Watchdog!\n");
		nmi_watchdog = 0;
	}

	printk(KERN_INFO "...trying to set up timer as Virtual Wire IRQ...");

	disable_8259A_irq(0);
	set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
				      "fasteoi");
	apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);	/* Fixed mode */
	enable_8259A_irq(0);

	if (timer_irq_works()) {
		printk(" works.\n");
		goto out;
	}
	apic_write_around(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | vector);
	printk(" failed.\n");

	printk(KERN_INFO "...trying to set up timer as ExtINT IRQ...");

	timer_ack = 0;
	init_8259A(0);
	make_8259A_irq(0);
	apic_write_around(APIC_LVT0, APIC_DM_EXTINT);

	unlock_ExtINT_logic();

	if (timer_irq_works()) {
		printk(" works.\n");
		goto out;
	}
	printk(" failed :(.\n");
	panic("IO-APIC + timer doesn't work!  Boot with apic=debug and send a "
		"report.  Then try booting with the 'noapic' option");
out:
	local_irq_restore(flags);
}

/*
 *
 * IRQ's that are handled by the PIC in the MPS IOAPIC case.
 * - IRQ2 is the cascade IRQ, and cannot be a io-apic IRQ.
 *   Linux doesn't really care, as it's not actually used
 *   for any interrupt handling anyway.
 */
#define PIC_IRQS	(1 << PIC_CASCADE_IR)

void __init setup_IO_APIC(void)
{
	int i;

	/* Reserve all the system vectors. */
	for (i = FIRST_SYSTEM_VECTOR; i < NR_VECTORS; i++)
		set_bit(i, used_vectors);

	enable_IO_APIC();

	if (acpi_ioapic)
		io_apic_irqs = ~0;	/* all IRQs go through IOAPIC */
	else
		io_apic_irqs = ~PIC_IRQS;

	printk("ENABLING IO-APIC IRQs\n");

	/*
	 * Set up IO-APIC IRQ routing.
	 */
	if (!acpi_ioapic)
		setup_ioapic_ids_from_mpc();
	sync_Arb_IDs();
	setup_IO_APIC_irqs();
	init_IO_APIC_traps();
	check_timer();
	if (!acpi_ioapic)
		print_IO_APIC();
}

static int __init setup_disable_8254_timer(char *s)
{
	timer_over_8254 = -1;
	return 1;
}
static int __init setup_enable_8254_timer(char *s)
{
	timer_over_8254 = 2;
	return 1;
}

__setup("disable_8254_timer", setup_disable_8254_timer);
__setup("enable_8254_timer", setup_enable_8254_timer);

/*
 *	Called after all the initialization is done. If we didnt find any
 *	APIC bugs then we can allow the modify fast path
 */
 
static int __init io_apic_bug_finalize(void)
{
	if(sis_apic_bug == -1)
		sis_apic_bug = 0;
	return 0;
}

late_initcall(io_apic_bug_finalize);

struct sysfs_ioapic_data {
	struct sys_device dev;
	struct IO_APIC_route_entry entry[0];
};
static struct sysfs_ioapic_data * mp_ioapic_data[MAX_IO_APICS];

static int ioapic_suspend(struct sys_device *dev, pm_message_t state)
{
	struct IO_APIC_route_entry *entry;
	struct sysfs_ioapic_data *data;
	int i;
	
	data = container_of(dev, struct sysfs_ioapic_data, dev);
	entry = data->entry;
	for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
		entry[i] = ioapic_read_entry(dev->id, i);

	return 0;
}

static int ioapic_resume(struct sys_device *dev)
{
	struct IO_APIC_route_entry *entry;
	struct sysfs_ioapic_data *data;
	unsigned long flags;
	union IO_APIC_reg_00 reg_00;
	int i;
	
	data = container_of(dev, struct sysfs_ioapic_data, dev);
	entry = data->entry;

	spin_lock_irqsave(&ioapic_lock, flags);
	reg_00.raw = io_apic_read(dev->id, 0);
	if (reg_00.bits.ID != mp_ioapics[dev->id].mpc_apicid) {
		reg_00.bits.ID = mp_ioapics[dev->id].mpc_apicid;
		io_apic_write(dev->id, 0, reg_00.raw);
	}
	spin_unlock_irqrestore(&ioapic_lock, flags);
	for (i = 0; i < nr_ioapic_registers[dev->id]; i ++)
		ioapic_write_entry(dev->id, i, entry[i]);

	return 0;
}

static struct sysdev_class ioapic_sysdev_class = {
	set_kset_name("ioapic"),
	.suspend = ioapic_suspend,
	.resume = ioapic_resume,
};

static int __init ioapic_init_sysfs(void)
{
	struct sys_device * dev;
	int i, size, error = 0;

	error = sysdev_class_register(&ioapic_sysdev_class);
	if (error)
		return error;

	for (i = 0; i < nr_ioapics; i++ ) {
		size = sizeof(struct sys_device) + nr_ioapic_registers[i] 
			* sizeof(struct IO_APIC_route_entry);
		mp_ioapic_data[i] = kmalloc(size, GFP_KERNEL);
		if (!mp_ioapic_data[i]) {
			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
			continue;
		}
		memset(mp_ioapic_data[i], 0, size);
		dev = &mp_ioapic_data[i]->dev;
		dev->id = i; 
		dev->cls = &ioapic_sysdev_class;
		error = sysdev_register(dev);
		if (error) {
			kfree(mp_ioapic_data[i]);
			mp_ioapic_data[i] = NULL;
			printk(KERN_ERR "Can't suspend/resume IOAPIC %d\n", i);
			continue;
		}
	}

	return 0;
}

device_initcall(ioapic_init_sysfs);

/*
 * Dynamic irq allocate and deallocation
 */
int create_irq(void)
{
	/* Allocate an unused irq */
	int irq, new, vector = 0;
	unsigned long flags;

	irq = -ENOSPC;
	spin_lock_irqsave(&vector_lock, flags);
	for (new = (NR_IRQS - 1); new >= 0; new--) {
		if (platform_legacy_irq(new))
			continue;
		if (irq_vector[new] != 0)
			continue;
		vector = __assign_irq_vector(new);
		if (likely(vector > 0))
			irq = new;
		break;
	}
	spin_unlock_irqrestore(&vector_lock, flags);

	if (irq >= 0) {
		set_intr_gate(vector, interrupt[irq]);
		dynamic_irq_init(irq);
	}
	return irq;
}

void destroy_irq(unsigned int irq)
{
	unsigned long flags;

	dynamic_irq_cleanup(irq);

	spin_lock_irqsave(&vector_lock, flags);
	irq_vector[irq] = 0;
	spin_unlock_irqrestore(&vector_lock, flags);
}

/*
 * MSI message composition
 */
#ifdef CONFIG_PCI_MSI
static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
{
	int vector;
	unsigned dest;

	vector = assign_irq_vector(irq);
	if (vector >= 0) {
		dest = cpu_mask_to_apicid(TARGET_CPUS);

		msg->address_hi = MSI_ADDR_BASE_HI;
		msg->address_lo =
			MSI_ADDR_BASE_LO |
			((INT_DEST_MODE == 0) ?
				MSI_ADDR_DEST_MODE_PHYSICAL:
				MSI_ADDR_DEST_MODE_LOGICAL) |
			((INT_DELIVERY_MODE != dest_LowestPrio) ?
				MSI_ADDR_REDIRECTION_CPU:
				MSI_ADDR_REDIRECTION_LOWPRI) |
			MSI_ADDR_DEST_ID(dest);

		msg->data =
			MSI_DATA_TRIGGER_EDGE |
			MSI_DATA_LEVEL_ASSERT |
			((INT_DELIVERY_MODE != dest_LowestPrio) ?
				MSI_DATA_DELIVERY_FIXED:
				MSI_DATA_DELIVERY_LOWPRI) |
			MSI_DATA_VECTOR(vector);
	}
	return vector;
}

#ifdef CONFIG_SMP
static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
{
	struct msi_msg msg;
	unsigned int dest;
	cpumask_t tmp;
	int vector;

	cpus_and(tmp, mask, cpu_online_map);
	if (cpus_empty(tmp))
		tmp = TARGET_CPUS;

	vector = assign_irq_vector(irq);
	if (vector < 0)
		return;

	dest = cpu_mask_to_apicid(mask);

	read_msi_msg(irq, &msg);

	msg.data &= ~MSI_DATA_VECTOR_MASK;
	msg.data |= MSI_DATA_VECTOR(vector);
	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
	msg.address_lo |= MSI_ADDR_DEST_ID(dest);

	write_msi_msg(irq, &msg);
	irq_desc[irq].affinity = mask;
}
#endif /* CONFIG_SMP */

/*
 * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
 * which implement the MSI or MSI-X Capability Structure.
 */
static struct irq_chip msi_chip = {
	.name		= "PCI-MSI",
	.unmask		= unmask_msi_irq,
	.mask		= mask_msi_irq,
	.ack		= ack_ioapic_irq,
#ifdef CONFIG_SMP
	.set_affinity	= set_msi_irq_affinity,
#endif
	.retrigger	= ioapic_retrigger_irq,
};

int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
{
	struct msi_msg msg;
	int irq, ret;
	irq = create_irq();
	if (irq < 0)
		return irq;

	ret = msi_compose_msg(dev, irq, &msg);
	if (ret < 0) {
		destroy_irq(irq);
		return ret;
	}

	set_irq_msi(irq, desc);
	write_msi_msg(irq, &msg);

	set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq,
				      "edge");

	return 0;
}

void arch_teardown_msi_irq(unsigned int irq)
{
	destroy_irq(irq);
}

#endif /* CONFIG_PCI_MSI */

/*
 * Hypertransport interrupt support
 */
#ifdef CONFIG_HT_IRQ

#ifdef CONFIG_SMP

static void target_ht_irq(unsigned int irq, unsigned int dest)
{
	struct ht_irq_msg msg;
	fetch_ht_irq_msg(irq, &msg);

	msg.address_lo &= ~(HT_IRQ_LOW_DEST_ID_MASK);
	msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);

	msg.address_lo |= HT_IRQ_LOW_DEST_ID(dest);
	msg.address_hi |= HT_IRQ_HIGH_DEST_ID(dest);

	write_ht_irq_msg(irq, &msg);
}

static void set_ht_irq_affinity(unsigned int irq, cpumask_t mask)
{
	unsigned int dest;
	cpumask_t tmp;

	cpus_and(tmp, mask, cpu_online_map);
	if (cpus_empty(tmp))
		tmp = TARGET_CPUS;

	cpus_and(mask, tmp, CPU_MASK_ALL);

	dest = cpu_mask_to_apicid(mask);

	target_ht_irq(irq, dest);
	irq_desc[irq].affinity = mask;
}
#endif

static struct irq_chip ht_irq_chip = {
	.name		= "PCI-HT",
	.mask		= mask_ht_irq,
	.unmask		= unmask_ht_irq,
	.ack		= ack_ioapic_irq,
#ifdef CONFIG_SMP
	.set_af