io_apic.c

底层驱动开发

	v = apic_read(APIC_ICR);
	printk(KERN_DEBUG "... APIC ICR: %08x\n", v);
	v = apic_read(APIC_ICR2);
	printk(KERN_DEBUG "... APIC ICR2: %08x\n", v);

	v = apic_read(APIC_LVTT);
	printk(KERN_DEBUG "... APIC LVTT: %08x\n", v);

	if (maxlvt > 3) {                       /* PC is LVT#4. */
		v = apic_read(APIC_LVTPC);
		printk(KERN_DEBUG "... APIC LVTPC: %08x\n", v);
	}
	v = apic_read(APIC_LVT0);
	printk(KERN_DEBUG "... APIC LVT0: %08x\n", v);
	v = apic_read(APIC_LVT1);
	printk(KERN_DEBUG "... APIC LVT1: %08x\n", v);

	if (maxlvt > 2) {			/* ERR is LVT#3. */
		v = apic_read(APIC_LVTERR);
		printk(KERN_DEBUG "... APIC LVTERR: %08x\n", v);
	}

	v = apic_read(APIC_TMICT);
	printk(KERN_DEBUG "... APIC TMICT: %08x\n", v);
	v = apic_read(APIC_TMCCT);
	printk(KERN_DEBUG "... APIC TMCCT: %08x\n", v);
	v = apic_read(APIC_TDCR);
	printk(KERN_DEBUG "... APIC TDCR: %08x\n", v);
	printk("\n");
}

void print_all_local_APICs (void)
{
	on_each_cpu(print_local_APIC, NULL, 1, 1);
}

void /*__init*/ print_PIC(void)
{
	unsigned int v;
	unsigned long flags;

	if (apic_verbosity == APIC_QUIET)
		return;

	printk(KERN_DEBUG "\nprinting PIC contents\n");

	spin_lock_irqsave(&i8259A_lock, flags);

	v = inb(0xa1) << 8 | inb(0x21);
	printk(KERN_DEBUG "... PIC  IMR: %04x\n", v);

	v = inb(0xa0) << 8 | inb(0x20);
	printk(KERN_DEBUG "... PIC  IRR: %04x\n", v);

	outb(0x0b,0xa0);
	outb(0x0b,0x20);
	v = inb(0xa0) << 8 | inb(0x20);
	outb(0x0a,0xa0);
	outb(0x0a,0x20);

	spin_unlock_irqrestore(&i8259A_lock, flags);

	printk(KERN_DEBUG "... PIC  ISR: %04x\n", v);

	v = inb(0x4d1) << 8 | inb(0x4d0);
	printk(KERN_DEBUG "... PIC ELCR: %04x\n", v);
}

#endif  /*  0  */

static void __init enable_IO_APIC(void)
{
	union IO_APIC_reg_01 reg_01;
	int i;
	unsigned long flags;

	for (i = 0; i < PIN_MAP_SIZE; i++) {
		irq_2_pin[i].pin = -1;
		irq_2_pin[i].next = 0;
	}
	if (!pirqs_enabled)
		for (i = 0; i < MAX_PIRQS; i++)
			pirq_entries[i] = -1;

	/*
	 * The number of IO-APIC IRQ registers (== #pins):
	 */
	for (i = 0; i < nr_ioapics; i++) {
		spin_lock_irqsave(&ioapic_lock, flags);
		reg_01.raw = io_apic_read(i, 1);
		spin_unlock_irqrestore(&ioapic_lock, flags);
		nr_ioapic_registers[i] = reg_01.bits.entries+1;
	}

	/*
	 * Do not trust the IO-APIC being empty at bootup
	 */
	clear_IO_APIC();
}

/*
 * Not an __init, needed by the reboot code
 */
void disable_IO_APIC(void)
{
	int pin;
	/*
	 * Clear the IO-APIC before rebooting:
	 */
	clear_IO_APIC();

	/*
	 * If the i8259 is routed through an IOAPIC
	 * Put that IOAPIC in virtual wire mode
	 * so legacy interrupts can be delivered.
	 */
	pin = find_isa_irq_pin(0, mp_ExtINT);
	if (pin != -1) {
		struct IO_APIC_route_entry entry;
		unsigned long flags;

		memset(&entry, 0, sizeof(entry));
		entry.mask            = 0; /* Enabled */
		entry.trigger         = 0; /* Edge */
		entry.irr             = 0;
		entry.polarity        = 0; /* High */
		entry.delivery_status = 0;
		entry.dest_mode       = 0; /* Physical */
		entry.delivery_mode   = 7; /* ExtInt */
		entry.vector          = 0;
		entry.dest.physical.physical_dest = 0;


		/*
		 * Add it to the IO-APIC irq-routing table:
		 */
		spin_lock_irqsave(&ioapic_lock, flags);
		io_apic_write(0, 0x11+2*pin, *(((int *)&entry)+1));
		io_apic_write(0, 0x10+2*pin, *(((int *)&entry)+0));
		spin_unlock_irqrestore(&ioapic_lock, flags);
	}
	disconnect_bsp_APIC(pin != -1);
}

/*
 * function to set the IO-APIC physical IDs based on the
 * values stored in the MPC table.
 *
 * by Matt Domsch <[e-mail]>  Tue Dec 21 12:25:05 CST 1999
 */

#ifndef CONFIG_X86_NUMAQ
static void __init setup_ioapic_ids_from_mpc(void)
{
	union IO_APIC_reg_00 reg_00;
	physid_mask_t phys_id_present_map;
	int apic;
	int i;
	unsigned char old_id;
	unsigned long flags;

	/*
	 * Don't check I/O APIC IDs for xAPIC systems.  They have
	 * no meaning without the serial APIC bus.
	 */
	if (!(boot_cpu_data.x86_vendor == X86_VENDOR_INTEL && boot_cpu_data.x86 < 15))
		return;
	/*
	 * This is broken; anything with a real cpu count has to
	 * circumvent this idiocy regardless.
	 */
	phys_id_present_map = ioapic_phys_id_map(phys_cpu_present_map);

	/*
	 * Set the IOAPIC ID to the value stored in the MPC table.
	 */
	for (apic = 0; apic < nr_ioapics; apic++) {

		/* Read the register 0 value */
		spin_lock_irqsave(&ioapic_lock, flags);
		reg_00.raw = io_apic_read(apic, 0);
		spin_unlock_irqrestore(&ioapic_lock, flags);
		
		old_id = mp_ioapics[apic].mpc_apicid;

		if (mp_ioapics[apic].mpc_apicid >= get_physical_broadcast()) {
			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID is %d in the MPC table!...\n",
				apic, mp_ioapics[apic].mpc_apicid);
			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
				reg_00.bits.ID);
			mp_ioapics[apic].mpc_apicid = reg_00.bits.ID;
		}

		/*
		 * Sanity check, is the ID really free? Every APIC in a
		 * system must have a unique ID or we get lots of nice
		 * 'stuck on smp_invalidate_needed IPI wait' messages.
		 */
		if (check_apicid_used(phys_id_present_map,
					mp_ioapics[apic].mpc_apicid)) {
			printk(KERN_ERR "BIOS bug, IO-APIC#%d ID %d is already used!...\n",
				apic, mp_ioapics[apic].mpc_apicid);
			for (i = 0; i < get_physical_broadcast(); i++)
				if (!physid_isset(i, phys_id_present_map))
					break;
			if (i >= get_physical_broadcast())
				panic("Max APIC ID exceeded!\n");
			printk(KERN_ERR "... fixing up to %d. (tell your hw vendor)\n",
				i);
			physid_set(i, phys_id_present_map);
			mp_ioapics[apic].mpc_apicid = i;
		} else {
			physid_mask_t tmp;
			tmp = apicid_to_cpu_present(mp_ioapics[apic].mpc_apicid);
			apic_printk(APIC_VERBOSE, "Setting %d in the "
					"phys_id_present_map\n",
					mp_ioapics[apic].mpc_apicid);
			physids_or(phys_id_present_map, phys_id_present_map, tmp);
		}


		/*
		 * We need to adjust the IRQ routing table
		 * if the ID changed.
		 */
		if (old_id != mp_ioapics[apic].mpc_apicid)
			for (i = 0; i < mp_irq_entries; i++)
				if (mp_irqs[i].mpc_dstapic == old_id)
					mp_irqs[i].mpc_dstapic
						= mp_ioapics[apic].mpc_apicid;

		/*
		 * Read the right value from the MPC table and
		 * write it into the ID register.
	 	 */
		apic_printk(APIC_VERBOSE, KERN_INFO
			"...changing IO-APIC physical APIC ID to %d ...",
			mp_ioapics[apic].mpc_apicid);

		reg_00.bits.ID = mp_ioapics[apic].mpc_apicid;
		spin_lock_irqsave(&ioapic_lock, flags);
		io_apic_write(apic, 0, reg_00.raw);
		spin_unlock_irqrestore(&ioapic_lock, flags);

		/*
		 * Sanity check
		 */
		spin_lock_irqsave(&ioapic_lock, flags);
		reg_00.raw = io_apic_read(apic, 0);
		spin_unlock_irqrestore(&ioapic_lock, flags);
		if (reg_00.bits.ID != mp_ioapics[apic].mpc_apicid)
			printk("could not set ID!\n");
		else
			apic_printk(APIC_VERBOSE, " ok.\n");
	}
}
#else
static void __init setup_ioapic_ids_from_mpc(void) { }
#endif

/*
 * There is a nasty bug in some older SMP boards, their mptable lies
 * about the timer IRQ. We do the following to work around the situation:
 *
 *	- timer IRQ defaults to IO-APIC IRQ
 *	- if this function detects that timer IRQs are defunct, then we fall
 *	  back to ISA timer IRQs
 */
static int __init timer_irq_works(void)
{
	unsigned long t1 = jiffies;

	local_irq_enable();
	/* Let ten ticks pass... */
	mdelay((10 * 1000) / HZ);

	/*
	 * Expect a few ticks at least, to be sure some possible
	 * glue logic does not lock up after one or two first
	 * ticks in a non-ExtINT mode.  Also the local APIC
	 * might have cached one ExtINT interrupt.  Finally, at
	 * least one tick may be lost due to delays.
	 */
	if (jiffies - t1 > 4)
		return 1;

	return 0;
}

/*
 * In the SMP+IOAPIC case it might happen that there are an unspecified
 * number of pending IRQ events unhandled. These cases are very rare,
 * so we 'resend' these IRQs via IPIs, to the same CPU. It's much
 * better to do it this way as thus we do not have to be aware of
 * 'pending' interrupts in the IRQ path, except at this point.
 */
/*
 * Edge triggered needs to resend any interrupt
 * that was delayed but this is now handled in the device
 * independent code.
 */

/*
 * Starting up a edge-triggered IO-APIC interrupt is
 * nasty - we need to make sure that we get the edge.
 * If it is already asserted for some reason, we need
 * return 1 to indicate that is was pending.
 *
 * This is not complete - we should be able to fake
 * an edge even if it isn't on the 8259A...
 */
static unsigned int startup_edge_ioapic_irq(unsigned int irq)
{
	int was_pending = 0;
	unsigned long flags;

	spin_lock_irqsave(&ioapic_lock, flags);
	if (irq < 16) {
		disable_8259A_irq(irq);
		if (i8259A_irq_pending(irq))
			was_pending = 1;
	}
	__unmask_IO_APIC_irq(irq);
	spin_unlock_irqrestore(&ioapic_lock, flags);

	return was_pending;
}

/*
 * Once we have recorded IRQ_PENDING already, we can mask the
 * interrupt for real. This prevents IRQ storms from unhandled
 * devices.
 */
static void ack_edge_ioapic_irq(unsigned int irq)
{
	move_irq(irq);
	if ((irq_desc[irq].status & (IRQ_PENDING | IRQ_DISABLED))
					== (IRQ_PENDING | IRQ_DISABLED))
		mask_IO_APIC_irq(irq);
	ack_APIC_irq();
}

/*
 * Level triggered interrupts can just be masked,
 * and shutting down and starting up the interrupt
 * is the same as enabling and disabling them -- except
 * with a startup need to return a "was pending" value.
 *
 * Level triggered interrupts are special because we
 * do not touch any IO-APIC register while handling
 * them. We ack the APIC in the end-IRQ handler, not
 * in the start-IRQ-handler. Protection against reentrance
 * from the same interrupt is still provided, both by the
 * generic IRQ layer and by the fact that an unacked local
 * APIC does not accept IRQs.
 */
static unsigned int startup_level_ioapic_irq (unsigned int irq)
{
	unmask_IO_APIC_irq(irq);

	return 0; /* don't check for pending */
}

static void end_level_ioapic_irq (unsigned int irq)
{
	unsigned long v;
	int i;

	move_irq(irq);
/*
 * It appears there is an erratum which affects at least version 0x11
 * of I/O APIC (that's the 82093AA and cores integrated into various
 * chipsets).  Under certain conditions a level-triggered interrupt is
 * erroneously delivered as edge-triggered one but the respective IRR
 * bit gets set nevertheless.  As a result the I/O unit expects an EOI
 * message but it will never arrive and further interrupts are blocked
 * from the source.  The exact reason is so far unknown, but the
 * phenomenon was observed when two consecutive interrupt requests
 * from a given source get delivered to the same CPU and the source is
 * temporarily disabled in between.
 *
 * A workaround is to simulate an EOI message manually.  We achieve it
 * by setting the trigger mode to edge and then to level when the edge
 * trigger mode gets detected in the TMR of a local APIC for a
 * level-triggered interrupt.  We mask the source for the time of the
 * operation to prevent an edge-triggered interrupt escaping meanwhile.
 * The idea is from Manfred Spraul.  --macro
 */
	i = IO_APIC_VECTOR(irq);

	v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));

	ack_APIC_irq();

	if (!(v & (1 << (i & 0x1f)))) {
		atomic_inc(&irq_mis_count);
		spin_lock(&ioapic_lock);
		__mask_and_edge_IO_APIC_irq(irq);
		__unmask_and_level_IO_APIC_irq(irq);
		spin_unlock(&ioapic_lock);
	}
}

#ifdef CONFIG_PCI_MSI
static unsigned int startup_edge_ioapic_vector(unsigned int vector)
{
	int irq = vector_to_irq(vector);

	return startup_edge_ioapic_irq(irq);
}

static void ack_edge_ioapic_vector(unsigned int vector)
{
	int irq = vector_to_irq(vector);

	move_irq(vector);
	ack_edge_ioapic_irq(irq);
}

static unsigned int startup_level_ioapic_vector (unsigned int vector)
{
	int irq = vector_to_irq(vector);

	return startup_level_ioapic_irq (irq);
}

static void end_level_ioapic_vector (unsigned int vector)
{
	int irq = vector_to_irq(vector);

	move_irq(vector);
	end_level_ioapic_irq(irq);
}

static void mask_IO_APIC_vector (unsigned int vector)
{
	int irq = vector_to_irq(vector);

	mask_IO_APIC_irq(irq);
}

static void unmask_IO_APIC_vector (unsigned int vector)
{
	int irq = vector_to_irq(vector);

	unmask_IO_APIC_irq(irq);
}

#ifdef CONFIG_SMP
static void set_ioapic_affinity_vector (unsigned int vector,
					cpumask_t cpu_mask)
{
	int irq = vector_to_irq(vector);

	set_native_irq_info(vector, cpu_mask);
	set_ioapic_affinity_irq(irq, cpu_mask);
}
#endif
#endif

/*
 * Level and edge triggered IO-APIC interrupts need different handling,
 * so we use two separate IRQ descriptors. Edge triggered IRQs can be
 * handled with the level-triggered descriptor, but that one has slightly
 * more overhead. Level-triggered interrupts cannot be handled with the
 * edge-triggered handler, without risking IRQ storms and other ugly
 * races.
 */
static struct hw_interrupt_type ioapic_edge_type __read_mostly = {
	.typename 	= "IO-APIC-edge",
	.startup 	= startup_edge_ioapic,
	.shutdown 	= shutdown_edge_ioapic,
	.enable 	= enable_edge_ioapic,
	.disable 	= disable_edge_ioapic,
	.ack 		= ack_edge_ioapic,
	.end 		= end_edge_ioapic,
#ifdef CONFIG_SMP
	.set_affinity 	= set_ioapic_affinity,
#endif
};

static struct hw_interrupt_type ioapic_level_type __read_mostly = {
	.typename 	= "IO-APIC-level",
	.startup 	= startup_level_ioapic,
	.shutdown 	= shutdown_level_ioapic,
	.enable 	= enable_level_ioapic,
	.disable 	= disable_level_ioapic,
	.ack 		= mask_and_ack_level_ioapic,
	.end 		= end_level_ioapic,
#ifdef CONFIG_SMP
	.set_affinity 	= set_ioapic_affinity,
#endif
};

static inline void init_IO_APIC_traps(void)
{
	int irq;

	/*
	 * NOTE! The local APIC isn't very good at handling
	 * multiple interrupts at the same interrupt level.
	 * As the interrupt level is determined by taking the
	 * vector number and shifting that right by 4, we
	 * want to spread these out a bit so that they don't
	 * all fall in the same interrupt level.
	 *
	 * Also, we've got to be careful not to trash gate
	 * 0x80, because int 0x80 is hm, kind of importantish. ;)