io_apic_64.c

linux 内核源代码

/*
 *	Intel IO-APIC support for multi-Pentium hosts.
 *
 *	Copyright (C) 1997, 1998, 1999, 2000 Ingo Molnar, Hajnalka Szabo
 *
 *	Many thanks to Stig Venaas for trying out countless experimental
 *	patches and reporting/debugging problems patiently!
 *
 *	(c) 1999, Multiple IO-APIC support, developed by
 *	Ken-ichi Yaku <[e-mail]> and
 *      Hidemi Kishimoto <[e-mail]>,
 *	further tested and cleaned up by Zach Brown <[e-mail]>
 *	and Ingo Molnar <[e-mail]>
 *
 *	Fixes
 *	Maciej W. Rozycki	:	Bits for genuine 82489DX APICs;
 *					thanks to Eric Gilmore
 *					and Rolf G. Tews
 *					for testing these extensively
 *	Paul Diefenbaugh	:	Added full ACPI support
 */

#include <linux/mm.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/delay.h>
#include <linux/sched.h>
#include <linux/pci.h>
#include <linux/mc146818rtc.h>
#include <linux/acpi.h>
#include <linux/sysdev.h>
#include <linux/msi.h>
#include <linux/htirq.h>
#include <linux/dmar.h>
#ifdef CONFIG_ACPI
#include <acpi/acpi_bus.h>
#endif

#include <asm/idle.h>
#include <asm/io.h>
#include <asm/smp.h>
#include <asm/desc.h>
#include <asm/proto.h>
#include <asm/mach_apic.h>
#include <asm/acpi.h>
#include <asm/dma.h>
#include <asm/nmi.h>
#include <asm/msidef.h>
#include <asm/hypertransport.h>

struct irq_cfg {
	cpumask_t domain;
	cpumask_t old_domain;
	unsigned move_cleanup_count;
	u8 vector;
	u8 move_in_progress : 1;
};

/* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
struct irq_cfg irq_cfg[NR_IRQS] __read_mostly = {
	[0]  = { .domain = CPU_MASK_ALL, .vector = IRQ0_VECTOR,  },
	[1]  = { .domain = CPU_MASK_ALL, .vector = IRQ1_VECTOR,  },
	[2]  = { .domain = CPU_MASK_ALL, .vector = IRQ2_VECTOR,  },
	[3]  = { .domain = CPU_MASK_ALL, .vector = IRQ3_VECTOR,  },
	[4]  = { .domain = CPU_MASK_ALL, .vector = IRQ4_VECTOR,  },
	[5]  = { .domain = CPU_MASK_ALL, .vector = IRQ5_VECTOR,  },
	[6]  = { .domain = CPU_MASK_ALL, .vector = IRQ6_VECTOR,  },
	[7]  = { .domain = CPU_MASK_ALL, .vector = IRQ7_VECTOR,  },
	[8]  = { .domain = CPU_MASK_ALL, .vector = IRQ8_VECTOR,  },
	[9]  = { .domain = CPU_MASK_ALL, .vector = IRQ9_VECTOR,  },
	[10] = { .domain = CPU_MASK_ALL, .vector = IRQ10_VECTOR, },
	[11] = { .domain = CPU_MASK_ALL, .vector = IRQ11_VECTOR, },
	[12] = { .domain = CPU_MASK_ALL, .vector = IRQ12_VECTOR, },
	[13] = { .domain = CPU_MASK_ALL, .vector = IRQ13_VECTOR, },
	[14] = { .domain = CPU_MASK_ALL, .vector = IRQ14_VECTOR, },
	[15] = { .domain = CPU_MASK_ALL, .vector = IRQ15_VECTOR, },
};

static int assign_irq_vector(int irq, cpumask_t mask);

#define __apicdebuginit  __init

int sis_apic_bug; /* not actually supported, dummy for compile */

static int no_timer_check;

static int disable_timer_pin_1 __initdata;

int timer_over_8254 __initdata = 1;

/* Where if anywhere is the i8259 connect in external int mode */
static struct { int pin, apic; } ioapic_i8259 = { -1, -1 };

static DEFINE_SPINLOCK(ioapic_lock);
DEFINE_SPINLOCK(vector_lock);

/*
 * # of IRQ routing registers
 */
int nr_ioapic_registers[MAX_IO_APICS];

/*
 * Rough estimation of how many shared IRQs there are, can
 * be changed anytime.
 */
#define MAX_PLUS_SHARED_IRQS NR_IRQS
#define PIN_MAP_SIZE (MAX_PLUS_SHARED_IRQS + NR_IRQS)

/*
 * This is performance-critical, we want to do it O(1)
 *
 * the indexing order of this array favors 1:1 mappings
 * between pins and IRQs.
 */

static struct irq_pin_list {
	short apic, pin, next;
} irq_2_pin[PIN_MAP_SIZE];

struct io_apic {
	unsigned int index;
	unsigned int unused[3];
	unsigned int data;
};

static __attribute_const__ struct io_apic __iomem *io_apic_base(int idx)
{
	return (void __iomem *) __fix_to_virt(FIX_IO_APIC_BASE_0 + idx)
		+ (mp_ioapics[idx].mpc_apicaddr & ~PAGE_MASK);
}

static inline unsigned int io_apic_read(unsigned int apic, unsigned int reg)
{
	struct io_apic __iomem *io_apic = io_apic_base(apic);
	writel(reg, &io_apic->index);
	return readl(&io_apic->data);
}

static inline void io_apic_write(unsigned int apic, unsigned int reg, unsigned int value)
{
	struct io_apic __iomem *io_apic = io_apic_base(apic);
	writel(reg, &io_apic->index);
	writel(value, &io_apic->data);
}

/*
 * Re-write a value: to be used for read-modify-write
 * cycles where the read already set up the index register.
 */
static inline void io_apic_modify(unsigned int apic, unsigned int value)
{
	struct io_apic __iomem *io_apic = io_apic_base(apic);
	writel(value, &io_apic->data);
}

static int io_apic_level_ack_pending(unsigned int irq)
{
	struct irq_pin_list *entry;
	unsigned long flags;
	int pending = 0;

	spin_lock_irqsave(&ioapic_lock, flags);
	entry = irq_2_pin + irq;
	for (;;) {
		unsigned int reg;
		int pin;

		pin = entry->pin;
		if (pin == -1)
			break;
		reg = io_apic_read(entry->apic, 0x10 + pin*2);
		/* Is the remote IRR bit set? */
		pending |= (reg >> 14) & 1;
		if (!entry->next)
			break;
		entry = irq_2_pin + entry->next;
	}
	spin_unlock_irqrestore(&ioapic_lock, flags);
	return pending;
}

/*
 * Synchronize the IO-APIC and the CPU by doing
 * a dummy read from the IO-APIC
 */
static inline void io_apic_sync(unsigned int apic)
{
	struct io_apic __iomem *io_apic = io_apic_base(apic);
	readl(&io_apic->data);
}

#define __DO_ACTION(R, ACTION, FINAL)					\
									\
{									\
	int pin;							\
	struct irq_pin_list *entry = irq_2_pin + irq;			\
									\
	BUG_ON(irq >= NR_IRQS);						\
	for (;;) {							\
		unsigned int reg;					\
		pin = entry->pin;					\
		if (pin == -1)						\
			break;						\
		reg = io_apic_read(entry->apic, 0x10 + R + pin*2);	\
		reg ACTION;						\
		io_apic_modify(entry->apic, reg);			\
		FINAL;							\
		if (!entry->next)					\
			break;						\
		entry = irq_2_pin + entry->next;			\
	}								\
}

union entry_union {
	struct { u32 w1, w2; };
	struct IO_APIC_route_entry entry;
};

static struct IO_APIC_route_entry ioapic_read_entry(int apic, int pin)
{
	union entry_union eu;
	unsigned long flags;
	spin_lock_irqsave(&ioapic_lock, flags);
	eu.w1 = io_apic_read(apic, 0x10 + 2 * pin);
	eu.w2 = io_apic_read(apic, 0x11 + 2 * pin);
	spin_unlock_irqrestore(&ioapic_lock, flags);
	return eu.entry;
}

/*
 * When we write a new IO APIC routing entry, we need to write the high
 * word first! If the mask bit in the low word is clear, we will enable
 * the interrupt, and we need to make sure the entry is fully populated
 * before that happens.
 */
static void
__ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
{
	union entry_union eu;
	eu.entry = e;
	io_apic_write(apic, 0x11 + 2*pin, eu.w2);
	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
}

static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
{
	unsigned long flags;
	spin_lock_irqsave(&ioapic_lock, flags);
	__ioapic_write_entry(apic, pin, e);
	spin_unlock_irqrestore(&ioapic_lock, flags);
}

/*
 * When we mask an IO APIC routing entry, we need to write the low
 * word first, in order to set the mask bit before we change the
 * high bits!
 */
static void ioapic_mask_entry(int apic, int pin)
{
	unsigned long flags;
	union entry_union eu = { .entry.mask = 1 };

	spin_lock_irqsave(&ioapic_lock, flags);
	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
	io_apic_write(apic, 0x11 + 2*pin, eu.w2);
	spin_unlock_irqrestore(&ioapic_lock, flags);
}

#ifdef CONFIG_SMP
static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, u8 vector)
{
	int apic, pin;
	struct irq_pin_list *entry = irq_2_pin + irq;

	BUG_ON(irq >= NR_IRQS);
	for (;;) {
		unsigned int reg;
		apic = entry->apic;
		pin = entry->pin;
		if (pin == -1)
			break;
		io_apic_write(apic, 0x11 + pin*2, dest);
		reg = io_apic_read(apic, 0x10 + pin*2);
		reg &= ~0x000000ff;
		reg |= vector;
		io_apic_modify(apic, reg);
		if (!entry->next)
			break;
		entry = irq_2_pin + entry->next;
	}
}

static void set_ioapic_affinity_irq(unsigned int irq, cpumask_t mask)
{
	struct irq_cfg *cfg = irq_cfg + irq;
	unsigned long flags;
	unsigned int dest;
	cpumask_t tmp;

	cpus_and(tmp, mask, cpu_online_map);
	if (cpus_empty(tmp))
		return;

	if (assign_irq_vector(irq, mask))
		return;

	cpus_and(tmp, cfg->domain, mask);
	dest = cpu_mask_to_apicid(tmp);

	/*
	 * Only the high 8 bits are valid.
	 */
	dest = SET_APIC_LOGICAL_ID(dest);

	spin_lock_irqsave(&ioapic_lock, flags);
	__target_IO_APIC_irq(irq, dest, cfg->vector);
	irq_desc[irq].affinity = mask;
	spin_unlock_irqrestore(&ioapic_lock, flags);
}
#endif

/*
 * The common case is 1:1 IRQ<->pin mappings. Sometimes there are
 * shared ISA-space IRQs, so we have to support them. We are super
 * fast in the common case, and fast for shared ISA-space IRQs.
 */
static void add_pin_to_irq(unsigned int irq, int apic, int pin)
{
	static int first_free_entry = NR_IRQS;
	struct irq_pin_list *entry = irq_2_pin + irq;

	BUG_ON(irq >= NR_IRQS);
	while (entry->next)
		entry = irq_2_pin + entry->next;

	if (entry->pin != -1) {
		entry->next = first_free_entry;
		entry = irq_2_pin + entry->next;
		if (++first_free_entry >= PIN_MAP_SIZE)
			panic("io_apic.c: ran out of irq_2_pin entries!");
	}
	entry->apic = apic;
	entry->pin = pin;
}


#define DO_ACTION(name,R,ACTION, FINAL)					\
									\
	static void name##_IO_APIC_irq (unsigned int irq)		\
	__DO_ACTION(R, ACTION, FINAL)

DO_ACTION( __mask,             0, |= 0x00010000, io_apic_sync(entry->apic) )
						/* mask = 1 */
DO_ACTION( __unmask,           0, &= 0xfffeffff, )
						/* mask = 0 */

static void mask_IO_APIC_irq (unsigned int irq)
{
	unsigned long flags;

	spin_lock_irqsave(&ioapic_lock, flags);
	__mask_IO_APIC_irq(irq);
	spin_unlock_irqrestore(&ioapic_lock, flags);
}

static void unmask_IO_APIC_irq (unsigned int irq)
{
	unsigned long flags;

	spin_lock_irqsave(&ioapic_lock, flags);
	__unmask_IO_APIC_irq(irq);
	spin_unlock_irqrestore(&ioapic_lock, flags);
}

static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
{
	struct IO_APIC_route_entry entry;

	/* Check delivery_mode to be sure we're not clearing an SMI pin */
	entry = ioapic_read_entry(apic, pin);
	if (entry.delivery_mode == dest_SMI)
		return;
	/*
	 * Disable it in the IO-APIC irq-routing table:
	 */
	ioapic_mask_entry(apic, pin);
}

static void clear_IO_APIC (void)
{
	int apic, pin;

	for (apic = 0; apic < nr_ioapics; apic++)
		for (pin = 0; pin < nr_ioapic_registers[apic]; pin++)
			clear_IO_APIC_pin(apic, pin);
}

int skip_ioapic_setup;
int ioapic_force;

static int __init parse_noapic(char *str)
{
	disable_ioapic_setup();
	return 0;
}
early_param("noapic", parse_noapic);

/* Actually the next is obsolete, but keep it for paranoid reasons -AK */
static int __init disable_timer_pin_setup(char *arg)
{
	disable_timer_pin_1 = 1;
	return 1;
}
__setup("disable_timer_pin_1", disable_timer_pin_setup);

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);


/*
 * Find the IRQ entry number of a certain pin.
 */
static int find_irq_entry(int apic, int pin, int type)
{
	int i;

	for (i = 0; i < mp_irq_entries; i++)
		if (mp_irqs[i].mpc_irqtype == type &&
		    (mp_irqs[i].mpc_dstapic == mp_ioapics[apic].mpc_apicid ||
		     mp_irqs[i].mpc_dstapic == MP_APIC_ALL) &&
		    mp_irqs[i].mpc_dstirq == pin)
			return i;

	return -1;
}

/*
 * Find the pin to which IRQ[irq] (ISA) is connected
 */
static int __init find_isa_irq_pin(int irq, int type)
{
	int i;

	for (i = 0; i < mp_irq_entries; i++) {
		int lbus = mp_irqs[i].mpc_srcbus;

		if (test_bit(lbus, mp_bus_not_pci) &&
		    (mp_irqs[i].mpc_irqtype == type) &&
		    (mp_irqs[i].mpc_srcbusirq == irq))

			return mp_irqs[i].mpc_dstirq;
	}
	return -1;
}

static int __init find_isa_irq_apic(int irq, int type)
{
	int i;

	for (i = 0; i < mp_irq_entries; i++) {
		int lbus = mp_irqs[i].mpc_srcbus;

		if (test_bit(lbus, mp_bus_not_pci) &&
		    (mp_irqs[i].mpc_irqtype == type) &&
		    (mp_irqs[i].mpc_srcbusirq == irq))
			break;
	}
	if (i < mp_irq_entries) {
		int apic;
		for(apic = 0; apic < nr_ioapics; apic++) {
			if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic)
				return apic;
		}
	}

	return -1;
}

/*
 * Find a specific PCI IRQ entry.
 * Not an __init, possibly needed by modules
 */
static int pin_2_irq(int idx, int apic, int pin);

int IO_APIC_get_PCI_irq_vector(int bus, int slot, int pin)
{
	int apic, i, best_guess = -1;

	apic_printk(APIC_DEBUG, "querying PCI -> IRQ mapping bus:%d, slot:%d, pin:%d.\n",
		bus, slot, pin);
	if (mp_bus_id_to_pci_bus[bus] == -1) {
		apic_printk(APIC_VERBOSE, "PCI BIOS passed nonexistent PCI bus %d!\n", bus);
		return -1;
	}
	for (i = 0; i < mp_irq_entries; i++) {
		int lbus = mp_irqs[i].mpc_srcbus;

		for (apic = 0; apic < nr_ioapics; apic++)
			if (mp_ioapics[apic].mpc_apicid == mp_irqs[i].mpc_dstapic ||
			    mp_irqs[i].mpc_dstapic == MP_APIC_ALL)
				break;

		if (!test_bit(lbus, mp_bus_not_pci) &&
		    !mp_irqs[i].mpc_irqtype &&
		    (bus == lbus) &&
		    (slot == ((mp_irqs[i].mpc_srcbusirq >> 2) & 0x1f))) {
			int irq = pin_2_irq(i,apic,mp_irqs[i].mpc_dstirq);

			if (!(apic || IO_APIC_IRQ(irq)))
				continue;

			if (pin == (mp_irqs[i].mpc_srcbusirq & 3))
				return irq;
			/*
			 * Use the first all-but-pin matching entry as a
			 * best-guess fuzzy result for broken mptables.
			 */
			if (best_guess < 0)
				best_guess = irq;
		}
	}
	BUG_ON(best_guess >= NR_IRQS);
	return best_guess;
}

/* ISA interrupts are always polarity zero edge triggered,
 * when listed as conforming in the MP table. */

#define default_ISA_trigger(idx)	(0)
#define default_ISA_polarity(idx)	(0)

/* PCI interrupts are always polarity one level triggered,
 * when listed as conforming in the MP table. */

#define default_PCI_trigger(idx)	(1)
#define default_PCI_polarity(idx)	(1)

static int MPBIOS_polarity(int idx)
{
	int bus = mp_irqs[idx].mpc_srcbus;
	int polarity;

	/*
	 * Determine IRQ line polarity (high active or low active):
	 */
	switch (mp_irqs[idx].mpc_irqflag & 3)
	{
		case 0: /* conforms, ie. bus-type dependent polarity */
			if (test_bit(bus, mp_bus_not_pci))
				polarity = default_ISA_polarity(idx);
			else
				polarity = default_PCI_polarity(idx);
			break;
		case 1: /* high active */
		{
			polarity = 0;
			break;
		}
		case 2: /* reserved */
		{
			printk(KERN_WARNING "broken BIOS!!\n");
			polarity = 1;