apic.c

来自「LINUX 2.6.17.4的源码」· C语言 代码 · 共 1,188 行 · 第 1/2 页

	error = sysdev_class_register(&lapic_sysclass);
	if (!error)
		error = sysdev_register(&device_lapic);
	return error;
}
device_initcall(init_lapic_sysfs);

#else	/* CONFIG_PM */

static void apic_pm_activate(void) { }

#endif	/* CONFIG_PM */

static int __init apic_set_verbosity(char *str)
{
	if (strcmp("debug", str) == 0)
		apic_verbosity = APIC_DEBUG;
	else if (strcmp("verbose", str) == 0)
		apic_verbosity = APIC_VERBOSE;
	else
		printk(KERN_WARNING "APIC Verbosity level %s not recognised"
				" use apic=verbose or apic=debug", str);

	return 1;
}

__setup("apic=", apic_set_verbosity);

/*
 * Detect and enable local APICs on non-SMP boards.
 * Original code written by Keir Fraser.
 * On AMD64 we trust the BIOS - if it says no APIC it is likely
 * not correctly set up (usually the APIC timer won't work etc.) 
 */

static int __init detect_init_APIC (void)
{
	if (!cpu_has_apic) {
		printk(KERN_INFO "No local APIC present\n");
		return -1;
	}

	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
	boot_cpu_id = 0;
	return 0;
}

void __init init_apic_mappings(void)
{
	unsigned long apic_phys;

	/*
	 * If no local APIC can be found then set up a fake all
	 * zeroes page to simulate the local APIC and another
	 * one for the IO-APIC.
	 */
	if (!smp_found_config && detect_init_APIC()) {
		apic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
		apic_phys = __pa(apic_phys);
	} else
		apic_phys = mp_lapic_addr;

	set_fixmap_nocache(FIX_APIC_BASE, apic_phys);
	apic_printk(APIC_VERBOSE,"mapped APIC to %16lx (%16lx)\n", APIC_BASE, apic_phys);

	/*
	 * Fetch the APIC ID of the BSP in case we have a
	 * default configuration (or the MP table is broken).
	 */
	boot_cpu_id = GET_APIC_ID(apic_read(APIC_ID));

#ifdef CONFIG_X86_IO_APIC
	{
		unsigned long ioapic_phys, idx = FIX_IO_APIC_BASE_0;
		int i;

		for (i = 0; i < nr_ioapics; i++) {
			if (smp_found_config) {
				ioapic_phys = mp_ioapics[i].mpc_apicaddr;
			} else {
				ioapic_phys = (unsigned long) alloc_bootmem_pages(PAGE_SIZE);
				ioapic_phys = __pa(ioapic_phys);
			}
			set_fixmap_nocache(idx, ioapic_phys);
			apic_printk(APIC_VERBOSE,"mapped IOAPIC to %016lx (%016lx)\n",
					__fix_to_virt(idx), ioapic_phys);
			idx++;
		}
	}
#endif
}

/*
 * This function sets up the local APIC timer, with a timeout of
 * 'clocks' APIC bus clock. During calibration we actually call
 * this function twice on the boot CPU, once with a bogus timeout
 * value, second time for real. The other (noncalibrating) CPUs
 * call this function only once, with the real, calibrated value.
 *
 * We do reads before writes even if unnecessary, to get around the
 * P5 APIC double write bug.
 */

#define APIC_DIVISOR 16

static void __setup_APIC_LVTT(unsigned int clocks)
{
	unsigned int lvtt_value, tmp_value, ver;
	int cpu = smp_processor_id();

	ver = GET_APIC_VERSION(apic_read(APIC_LVR));
	lvtt_value = APIC_LVT_TIMER_PERIODIC | LOCAL_TIMER_VECTOR;

	if (cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask))
		lvtt_value |= APIC_LVT_MASKED;

	apic_write(APIC_LVTT, lvtt_value);

	/*
	 * Divide PICLK by 16
	 */
	tmp_value = apic_read(APIC_TDCR);
	apic_write(APIC_TDCR, (tmp_value
				& ~(APIC_TDR_DIV_1 | APIC_TDR_DIV_TMBASE))
				| APIC_TDR_DIV_16);

	apic_write(APIC_TMICT, clocks/APIC_DIVISOR);
}

static void setup_APIC_timer(unsigned int clocks)
{
	unsigned long flags;

	local_irq_save(flags);

	/* wait for irq slice */
 	if (vxtime.hpet_address && hpet_use_timer) {
 		int trigger = hpet_readl(HPET_T0_CMP);
 		while (hpet_readl(HPET_COUNTER) >= trigger)
 			/* do nothing */ ;
 		while (hpet_readl(HPET_COUNTER) <  trigger)
 			/* do nothing */ ;
 	} else {
		int c1, c2;
		outb_p(0x00, 0x43);
		c2 = inb_p(0x40);
		c2 |= inb_p(0x40) << 8;
		do {
			c1 = c2;
			outb_p(0x00, 0x43);
			c2 = inb_p(0x40);
			c2 |= inb_p(0x40) << 8;
		} while (c2 - c1 < 300);
	}
	__setup_APIC_LVTT(clocks);
	/* Turn off PIT interrupt if we use APIC timer as main timer.
	   Only works with the PM timer right now
	   TBD fix it for HPET too. */
	if (vxtime.mode == VXTIME_PMTMR &&
		smp_processor_id() == boot_cpu_id &&
		apic_runs_main_timer == 1 &&
		!cpu_isset(boot_cpu_id, timer_interrupt_broadcast_ipi_mask)) {
		stop_timer_interrupt();
		apic_runs_main_timer++;
	}
	local_irq_restore(flags);
}

/*
 * In this function we calibrate APIC bus clocks to the external
 * timer. Unfortunately we cannot use jiffies and the timer irq
 * to calibrate, since some later bootup code depends on getting
 * the first irq? Ugh.
 *
 * We want to do the calibration only once since we
 * want to have local timer irqs syncron. CPUs connected
 * by the same APIC bus have the very same bus frequency.
 * And we want to have irqs off anyways, no accidental
 * APIC irq that way.
 */

#define TICK_COUNT 100000000

static int __init calibrate_APIC_clock(void)
{
	int apic, apic_start, tsc, tsc_start;
	int result;
	/*
	 * Put whatever arbitrary (but long enough) timeout
	 * value into the APIC clock, we just want to get the
	 * counter running for calibration.
	 */
	__setup_APIC_LVTT(1000000000);

	apic_start = apic_read(APIC_TMCCT);
#ifdef CONFIG_X86_PM_TIMER
	if (apic_calibrate_pmtmr && pmtmr_ioport) {
		pmtimer_wait(5000);  /* 5ms wait */
		apic = apic_read(APIC_TMCCT);
		result = (apic_start - apic) * 1000L / 5;
	} else
#endif
	{
		rdtscl(tsc_start);

		do {
			apic = apic_read(APIC_TMCCT);
			rdtscl(tsc);
		} while ((tsc - tsc_start) < TICK_COUNT &&
				(apic - apic_start) < TICK_COUNT);

		result = (apic_start - apic) * 1000L * cpu_khz /
					(tsc - tsc_start);
	}
	printk("result %d\n", result);


	printk(KERN_INFO "Detected %d.%03d MHz APIC timer.\n",
		result / 1000 / 1000, result / 1000 % 1000);

	return result * APIC_DIVISOR / HZ;
}

static unsigned int calibration_result;

void __init setup_boot_APIC_clock (void)
{
	if (disable_apic_timer) { 
		printk(KERN_INFO "Disabling APIC timer\n"); 
		return; 
	} 

	printk(KERN_INFO "Using local APIC timer interrupts.\n");
	using_apic_timer = 1;

	local_irq_disable();

	calibration_result = calibrate_APIC_clock();
	/*
	 * Now set up the timer for real.
	 */
	setup_APIC_timer(calibration_result);

	local_irq_enable();
}

void __cpuinit setup_secondary_APIC_clock(void)
{
	local_irq_disable(); /* FIXME: Do we need this? --RR */
	setup_APIC_timer(calibration_result);
	local_irq_enable();
}

void disable_APIC_timer(void)
{
	if (using_apic_timer) {
		unsigned long v;

		v = apic_read(APIC_LVTT);
		apic_write(APIC_LVTT, v | APIC_LVT_MASKED);
	}
}

void enable_APIC_timer(void)
{
	int cpu = smp_processor_id();

	if (using_apic_timer &&
	    !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
		unsigned long v;

		v = apic_read(APIC_LVTT);
		apic_write(APIC_LVTT, v & ~APIC_LVT_MASKED);
	}
}

void switch_APIC_timer_to_ipi(void *cpumask)
{
	cpumask_t mask = *(cpumask_t *)cpumask;
	int cpu = smp_processor_id();

	if (cpu_isset(cpu, mask) &&
	    !cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
		disable_APIC_timer();
		cpu_set(cpu, timer_interrupt_broadcast_ipi_mask);
	}
}
EXPORT_SYMBOL(switch_APIC_timer_to_ipi);

void smp_send_timer_broadcast_ipi(void)
{
	cpumask_t mask;

	cpus_and(mask, cpu_online_map, timer_interrupt_broadcast_ipi_mask);
	if (!cpus_empty(mask)) {
		send_IPI_mask(mask, LOCAL_TIMER_VECTOR);
	}
}

void switch_ipi_to_APIC_timer(void *cpumask)
{
	cpumask_t mask = *(cpumask_t *)cpumask;
	int cpu = smp_processor_id();

	if (cpu_isset(cpu, mask) &&
	    cpu_isset(cpu, timer_interrupt_broadcast_ipi_mask)) {
		cpu_clear(cpu, timer_interrupt_broadcast_ipi_mask);
		enable_APIC_timer();
	}
}
EXPORT_SYMBOL(switch_ipi_to_APIC_timer);

int setup_profiling_timer(unsigned int multiplier)
{
	return -EINVAL;
}

#ifdef CONFIG_X86_MCE_AMD
void setup_threshold_lvt(unsigned long lvt_off)
{
	unsigned int v = 0;
	unsigned long reg = (lvt_off << 4) + 0x500;
	v |= THRESHOLD_APIC_VECTOR;
	apic_write(reg, v);
}
#endif /* CONFIG_X86_MCE_AMD */

#undef APIC_DIVISOR

/*
 * Local timer interrupt handler. It does both profiling and
 * process statistics/rescheduling.
 *
 * We do profiling in every local tick, statistics/rescheduling
 * happen only every 'profiling multiplier' ticks. The default
 * multiplier is 1 and it can be changed by writing the new multiplier
 * value into /proc/profile.
 */

void smp_local_timer_interrupt(struct pt_regs *regs)
{
	profile_tick(CPU_PROFILING, regs);
#ifdef CONFIG_SMP
	update_process_times(user_mode(regs));
#endif
	if (apic_runs_main_timer > 1 && smp_processor_id() == boot_cpu_id)
		main_timer_handler(regs);
	/*
	 * We take the 'long' return path, and there every subsystem
	 * grabs the appropriate locks (kernel lock/ irq lock).
	 *
	 * we might want to decouple profiling from the 'long path',
	 * and do the profiling totally in assembly.
	 *
	 * Currently this isn't too much of an issue (performance wise),
	 * we can take more than 100K local irqs per second on a 100 MHz P5.
	 */
}

/*
 * Local APIC timer interrupt. This is the most natural way for doing
 * local interrupts, but local timer interrupts can be emulated by
 * broadcast interrupts too. [in case the hw doesn't support APIC timers]
 *
 * [ if a single-CPU system runs an SMP kernel then we call the local
 *   interrupt as well. Thus we cannot inline the local irq ... ]
 */
void smp_apic_timer_interrupt(struct pt_regs *regs)
{
	/*
	 * the NMI deadlock-detector uses this.
	 */
	add_pda(apic_timer_irqs, 1);

	/*
	 * NOTE! We'd better ACK the irq immediately,
	 * because timer handling can be slow.
	 */
	ack_APIC_irq();
	/*
	 * update_process_times() expects us to have done irq_enter().
	 * Besides, if we don't timer interrupts ignore the global
	 * interrupt lock, which is the WrongThing (tm) to do.
	 */
	exit_idle();
	irq_enter();
	smp_local_timer_interrupt(regs);
	irq_exit();
}

/*
 * oem_force_hpet_timer -- force HPET mode for some boxes.
 *
 * Thus far, the major user of this is IBM's Summit2 series:
 *
 * Clustered boxes may have unsynced TSC problems if they are
 * multi-chassis. Use available data to take a good guess.
 * If in doubt, go HPET.
 */
__cpuinit int oem_force_hpet_timer(void)
{
	int i, clusters, zeros;
	unsigned id;
	DECLARE_BITMAP(clustermap, NUM_APIC_CLUSTERS);

	bitmap_zero(clustermap, NUM_APIC_CLUSTERS);

	for (i = 0; i < NR_CPUS; i++) {
		id = bios_cpu_apicid[i];
		if (id != BAD_APICID)
			__set_bit(APIC_CLUSTERID(id), clustermap);
	}

	/* Problem:  Partially populated chassis may not have CPUs in some of
	 * the APIC clusters they have been allocated.  Only present CPUs have
	 * bios_cpu_apicid entries, thus causing zeroes in the bitmap.  Since
	 * clusters are allocated sequentially, count zeros only if they are
	 * bounded by ones.
	 */
	clusters = 0;
	zeros = 0;
	for (i = 0; i < NUM_APIC_CLUSTERS; i++) {
		if (test_bit(i, clustermap)) {
			clusters += 1 + zeros;
			zeros = 0;
		} else
			++zeros;
	}

	/*
	 * If clusters > 2, then should be multi-chassis.  Return 1 for HPET.
	 * Else return 0 to use TSC.
	 * May have to revisit this when multi-core + hyperthreaded CPUs come
	 * out, but AFAIK this will work even for them.
	 */
	return (clusters > 2);
}

/*
 * This interrupt should _never_ happen with our APIC/SMP architecture
 */
asmlinkage void smp_spurious_interrupt(void)
{
	unsigned int v;
	exit_idle();
	irq_enter();
	/*
	 * Check if this really is a spurious interrupt and ACK it
	 * if it is a vectored one.  Just in case...
	 * Spurious interrupts should not be ACKed.
	 */
	v = apic_read(APIC_ISR + ((SPURIOUS_APIC_VECTOR & ~0x1f) >> 1));
	if (v & (1 << (SPURIOUS_APIC_VECTOR & 0x1f)))
		ack_APIC_irq();

#if 0
	static unsigned long last_warning; 
	static unsigned long skipped; 

	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
	if (time_before(last_warning+30*HZ,jiffies)) { 
		printk(KERN_INFO "spurious APIC interrupt on CPU#%d, %ld skipped.\n",
		       smp_processor_id(), skipped);
		last_warning = jiffies; 
		skipped = 0;
	} else { 
		skipped++; 
	} 
#endif 
	irq_exit();
}

/*
 * This interrupt should never happen with our APIC/SMP architecture
 */

asmlinkage void smp_error_interrupt(void)
{
	unsigned int v, v1;

	exit_idle();
	irq_enter();
	/* First tickle the hardware, only then report what went on. -- REW */
	v = apic_read(APIC_ESR);
	apic_write(APIC_ESR, 0);
	v1 = apic_read(APIC_ESR);
	ack_APIC_irq();
	atomic_inc(&irq_err_count);

	/* Here is what the APIC error bits mean:
	   0: Send CS error
	   1: Receive CS error
	   2: Send accept error
	   3: Receive accept error
	   4: Reserved
	   5: Send illegal vector
	   6: Received illegal vector
	   7: Illegal register address
	*/
	printk (KERN_DEBUG "APIC error on CPU%d: %02x(%02x)\n",
	        smp_processor_id(), v , v1);
	irq_exit();
}

int disable_apic; 

/*
 * This initializes the IO-APIC and APIC hardware if this is
 * a UP kernel.
 */
int __init APIC_init_uniprocessor (void)
{
	if (disable_apic) { 
		printk(KERN_INFO "Apic disabled\n");
		return -1; 
	}
	if (!cpu_has_apic) { 
		disable_apic = 1;
		printk(KERN_INFO "Apic disabled by BIOS\n");
		return -1;
	}

	verify_local_APIC();

	connect_bsp_APIC();

	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_id);
	apic_write(APIC_ID, SET_APIC_ID(boot_cpu_id));

	setup_local_APIC();

#ifdef CONFIG_X86_IO_APIC
	if (smp_found_config && !skip_ioapic_setup && nr_ioapics)
			setup_IO_APIC();
	else
		nr_ioapics = 0;
#endif
	setup_boot_APIC_clock();
	check_nmi_watchdog();
	return 0;
}

static __init int setup_disableapic(char *str) 
{ 
	disable_apic = 1;
	return 1;
} 

static __init int setup_nolapic(char *str) 
{ 
	disable_apic = 1;
	return 1;
} 

static __init int setup_noapictimer(char *str) 
{ 
	if (str[0] != ' ' && str[0] != 0)
		return 0;
	disable_apic_timer = 1;
	return 1;
} 

static __init int setup_apicmaintimer(char *str)
{
	apic_runs_main_timer = 1;
	nohpet = 1;
	return 1;
}
__setup("apicmaintimer", setup_apicmaintimer);

static __init int setup_noapicmaintimer(char *str)
{
	apic_runs_main_timer = -1;
	return 1;
}
__setup("noapicmaintimer", setup_noapicmaintimer);

static __init int setup_apicpmtimer(char *s)
{
	apic_calibrate_pmtmr = 1;
	notsc_setup(NULL);
	return setup_apicmaintimer(NULL);
}
__setup("apicpmtimer", setup_apicpmtimer);

/* dummy parsing: see setup.c */

__setup("disableapic", setup_disableapic); 
__setup("nolapic", setup_nolapic);  /* same as disableapic, for compatibility */

__setup("noapictimer", setup_noapictimer); 

/* no "lapic" flag - we only use the lapic when the BIOS tells us so. */