processor_idle.c

来自「linux 内核源代码」· C语言 代码 · 共 1,790 行 · 第 1/4 页

		}
	}

#ifdef CONFIG_HOTPLUG_CPU
	/*
	 * Check for P_LVL2_UP flag before entering C2 and above on
	 * an SMP system. We do it here instead of doing it at _CST/P_LVL
	 * detection phase, to work cleanly with logical CPU hotplug.
	 */
	if ((cx->type != ACPI_STATE_C1) && (num_online_cpus() > 1) &&
	    !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
		cx = &pr->power.states[ACPI_STATE_C1];
#endif

	/*
	 * Sleep:
	 * ------
	 * Invoke the current Cx state to put the processor to sleep.
	 */
	if (cx->type == ACPI_STATE_C2 || cx->type == ACPI_STATE_C3) {
		current_thread_info()->status &= ~TS_POLLING;
		/*
		 * TS_POLLING-cleared state must be visible before we
		 * test NEED_RESCHED:
		 */
		smp_mb();
		if (need_resched()) {
			current_thread_info()->status |= TS_POLLING;
			local_irq_enable();
			return;
		}
	}

	switch (cx->type) {

	case ACPI_STATE_C1:
		/*
		 * Invoke C1.
		 * Use the appropriate idle routine, the one that would
		 * be used without acpi C-states.
		 */
		if (pm_idle_save)
			pm_idle_save();
		else
			acpi_safe_halt();

		/*
		 * TBD: Can't get time duration while in C1, as resumes
		 *      go to an ISR rather than here.  Need to instrument
		 *      base interrupt handler.
		 *
		 * Note: the TSC better not stop in C1, sched_clock() will
		 *       skew otherwise.
		 */
		sleep_ticks = 0xFFFFFFFF;
		break;

	case ACPI_STATE_C2:
		/* Get start time (ticks) */
		t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
		/* Tell the scheduler that we are going deep-idle: */
		sched_clock_idle_sleep_event();
		/* Invoke C2 */
		acpi_state_timer_broadcast(pr, cx, 1);
		acpi_cstate_enter(cx);
		/* Get end time (ticks) */
		t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);

#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
		/* TSC halts in C2, so notify users */
		mark_tsc_unstable("possible TSC halt in C2");
#endif
		/* Compute time (ticks) that we were actually asleep */
		sleep_ticks = ticks_elapsed(t1, t2);

		/* Tell the scheduler how much we idled: */
		sched_clock_idle_wakeup_event(sleep_ticks*PM_TIMER_TICK_NS);

		/* Re-enable interrupts */
		local_irq_enable();
		/* Do not account our idle-switching overhead: */
		sleep_ticks -= cx->latency_ticks + C2_OVERHEAD;

		current_thread_info()->status |= TS_POLLING;
		acpi_state_timer_broadcast(pr, cx, 0);
		break;

	case ACPI_STATE_C3:
		/*
		 * Must be done before busmaster disable as we might
		 * need to access HPET !
		 */
		acpi_state_timer_broadcast(pr, cx, 1);
		/*
		 * disable bus master
		 * bm_check implies we need ARB_DIS
		 * !bm_check implies we need cache flush
		 * bm_control implies whether we can do ARB_DIS
		 *
		 * That leaves a case where bm_check is set and bm_control is
		 * not set. In that case we cannot do much, we enter C3
		 * without doing anything.
		 */
		if (pr->flags.bm_check && pr->flags.bm_control) {
			if (atomic_inc_return(&c3_cpu_count) ==
			    num_online_cpus()) {
				/*
				 * All CPUs are trying to go to C3
				 * Disable bus master arbitration
				 */
				acpi_set_register(ACPI_BITREG_ARB_DISABLE, 1);
			}
		} else if (!pr->flags.bm_check) {
			/* SMP with no shared cache... Invalidate cache  */
			ACPI_FLUSH_CPU_CACHE();
		}

		/* Get start time (ticks) */
		t1 = inl(acpi_gbl_FADT.xpm_timer_block.address);
		/* Invoke C3 */
		/* Tell the scheduler that we are going deep-idle: */
		sched_clock_idle_sleep_event();
		acpi_cstate_enter(cx);
		/* Get end time (ticks) */
		t2 = inl(acpi_gbl_FADT.xpm_timer_block.address);
		if (pr->flags.bm_check && pr->flags.bm_control) {
			/* Enable bus master arbitration */
			atomic_dec(&c3_cpu_count);
			acpi_set_register(ACPI_BITREG_ARB_DISABLE, 0);
		}

#if defined (CONFIG_GENERIC_TIME) && defined (CONFIG_X86_TSC)
		/* TSC halts in C3, so notify users */
		mark_tsc_unstable("TSC halts in C3");
#endif
		/* Compute time (ticks) that we were actually asleep */
		sleep_ticks = ticks_elapsed(t1, t2);
		/* Tell the scheduler how much we idled: */
		sched_clock_idle_wakeup_event(sleep_ticks*PM_TIMER_TICK_NS);

		/* Re-enable interrupts */
		local_irq_enable();
		/* Do not account our idle-switching overhead: */
		sleep_ticks -= cx->latency_ticks + C3_OVERHEAD;

		current_thread_info()->status |= TS_POLLING;
		acpi_state_timer_broadcast(pr, cx, 0);
		break;

	default:
		local_irq_enable();
		return;
	}
	cx->usage++;
	if ((cx->type != ACPI_STATE_C1) && (sleep_ticks > 0))
		cx->time += sleep_ticks;

	next_state = pr->power.state;

#ifdef CONFIG_HOTPLUG_CPU
	/* Don't do promotion/demotion */
	if ((cx->type == ACPI_STATE_C1) && (num_online_cpus() > 1) &&
	    !pr->flags.has_cst && !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED)) {
		next_state = cx;
		goto end;
	}
#endif

	/*
	 * Promotion?
	 * ----------
	 * Track the number of longs (time asleep is greater than threshold)
	 * and promote when the count threshold is reached.  Note that bus
	 * mastering activity may prevent promotions.
	 * Do not promote above max_cstate.
	 */
	if (cx->promotion.state &&
	    ((cx->promotion.state - pr->power.states) <= max_cstate)) {
		if (sleep_ticks > cx->promotion.threshold.ticks &&
		  cx->promotion.state->latency <= system_latency_constraint()) {
			cx->promotion.count++;
			cx->demotion.count = 0;
			if (cx->promotion.count >=
			    cx->promotion.threshold.count) {
				if (pr->flags.bm_check) {
					if (!
					    (pr->power.bm_activity & cx->
					     promotion.threshold.bm)) {
						next_state =
						    cx->promotion.state;
						goto end;
					}
				} else {
					next_state = cx->promotion.state;
					goto end;
				}
			}
		}
	}

	/*
	 * Demotion?
	 * ---------
	 * Track the number of shorts (time asleep is less than time threshold)
	 * and demote when the usage threshold is reached.
	 */
	if (cx->demotion.state) {
		if (sleep_ticks < cx->demotion.threshold.ticks) {
			cx->demotion.count++;
			cx->promotion.count = 0;
			if (cx->demotion.count >= cx->demotion.threshold.count) {
				next_state = cx->demotion.state;
				goto end;
			}
		}
	}

      end:
	/*
	 * Demote if current state exceeds max_cstate
	 * or if the latency of the current state is unacceptable
	 */
	if ((pr->power.state - pr->power.states) > max_cstate ||
		pr->power.state->latency > system_latency_constraint()) {
		if (cx->demotion.state)
			next_state = cx->demotion.state;
	}

	/*
	 * New Cx State?
	 * -------------
	 * If we're going to start using a new Cx state we must clean up
	 * from the previous and prepare to use the new.
	 */
	if (next_state != pr->power.state)
		acpi_processor_power_activate(pr, next_state);
}

static int acpi_processor_set_power_policy(struct acpi_processor *pr)
{
	unsigned int i;
	unsigned int state_is_set = 0;
	struct acpi_processor_cx *lower = NULL;
	struct acpi_processor_cx *higher = NULL;
	struct acpi_processor_cx *cx;


	if (!pr)
		return -EINVAL;

	/*
	 * This function sets the default Cx state policy (OS idle handler).
	 * Our scheme is to promote quickly to C2 but more conservatively
	 * to C3.  We're favoring C2  for its characteristics of low latency
	 * (quick response), good power savings, and ability to allow bus
	 * mastering activity.  Note that the Cx state policy is completely
	 * customizable and can be altered dynamically.
	 */

	/* startup state */
	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
		cx = &pr->power.states[i];
		if (!cx->valid)
			continue;

		if (!state_is_set)
			pr->power.state = cx;
		state_is_set++;
		break;
	}

	if (!state_is_set)
		return -ENODEV;

	/* demotion */
	for (i = 1; i < ACPI_PROCESSOR_MAX_POWER; i++) {
		cx = &pr->power.states[i];
		if (!cx->valid)
			continue;

		if (lower) {
			cx->demotion.state = lower;
			cx->demotion.threshold.ticks = cx->latency_ticks;
			cx->demotion.threshold.count = 1;
			if (cx->type == ACPI_STATE_C3)
				cx->demotion.threshold.bm = bm_history;
		}

		lower = cx;
	}

	/* promotion */
	for (i = (ACPI_PROCESSOR_MAX_POWER - 1); i > 0; i--) {
		cx = &pr->power.states[i];
		if (!cx->valid)
			continue;

		if (higher) {
			cx->promotion.state = higher;
			cx->promotion.threshold.ticks = cx->latency_ticks;
			if (cx->type >= ACPI_STATE_C2)
				cx->promotion.threshold.count = 4;
			else
				cx->promotion.threshold.count = 10;
			if (higher->type == ACPI_STATE_C3)
				cx->promotion.threshold.bm = bm_history;
		}

		higher = cx;
	}

	return 0;
}
#endif /* !CONFIG_CPU_IDLE */

static int acpi_processor_get_power_info_fadt(struct acpi_processor *pr)
{

	if (!pr)
		return -EINVAL;

	if (!pr->pblk)
		return -ENODEV;

	/* if info is obtained from pblk/fadt, type equals state */
	pr->power.states[ACPI_STATE_C2].type = ACPI_STATE_C2;
	pr->power.states[ACPI_STATE_C3].type = ACPI_STATE_C3;

#ifndef CONFIG_HOTPLUG_CPU
	/*
	 * Check for P_LVL2_UP flag before entering C2 and above on
	 * an SMP system.
	 */
	if ((num_online_cpus() > 1) &&
	    !(acpi_gbl_FADT.flags & ACPI_FADT_C2_MP_SUPPORTED))
		return -ENODEV;
#endif

	/* determine C2 and C3 address from pblk */
	pr->power.states[ACPI_STATE_C2].address = pr->pblk + 4;
	pr->power.states[ACPI_STATE_C3].address = pr->pblk + 5;

	/* determine latencies from FADT */
	pr->power.states[ACPI_STATE_C2].latency = acpi_gbl_FADT.C2latency;
	pr->power.states[ACPI_STATE_C3].latency = acpi_gbl_FADT.C3latency;

	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
			  "lvl2[0x%08x] lvl3[0x%08x]\n",
			  pr->power.states[ACPI_STATE_C2].address,
			  pr->power.states[ACPI_STATE_C3].address));

	return 0;
}

static int acpi_processor_get_power_info_default(struct acpi_processor *pr)
{
	if (!pr->power.states[ACPI_STATE_C1].valid) {
		/* set the first C-State to C1 */
		/* all processors need to support C1 */
		pr->power.states[ACPI_STATE_C1].type = ACPI_STATE_C1;
		pr->power.states[ACPI_STATE_C1].valid = 1;
	}
	/* the C0 state only exists as a filler in our array */
	pr->power.states[ACPI_STATE_C0].valid = 1;
	return 0;
}

static int acpi_processor_get_power_info_cst(struct acpi_processor *pr)
{
	acpi_status status = 0;
	acpi_integer count;
	int current_count;
	int i;
	struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL };
	union acpi_object *cst;


	if (nocst)
		return -ENODEV;

	current_count = 0;

	status = acpi_evaluate_object(pr->handle, "_CST", NULL, &buffer);
	if (ACPI_FAILURE(status)) {
		ACPI_DEBUG_PRINT((ACPI_DB_INFO, "No _CST, giving up\n"));
		return -ENODEV;
	}

	cst = buffer.pointer;

	/* There must be at least 2 elements */
	if (!cst || (cst->type != ACPI_TYPE_PACKAGE) || cst->package.count < 2) {
		printk(KERN_ERR PREFIX "not enough elements in _CST\n");
		status = -EFAULT;
		goto end;
	}

	count = cst->package.elements[0].integer.value;

	/* Validate number of power states. */
	if (count < 1 || count != cst->package.count - 1) {
		printk(KERN_ERR PREFIX "count given by _CST is not valid\n");
		status = -EFAULT;
		goto end;
	}

	/* Tell driver that at least _CST is supported. */
	pr->flags.has_cst = 1;

	for (i = 1; i <= count; i++) {
		union acpi_object *element;
		union acpi_object *obj;
		struct acpi_power_register *reg;
		struct acpi_processor_cx cx;

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

		element = &(cst->package.elements[i]);
		if (element->type != ACPI_TYPE_PACKAGE)
			continue;

		if (element->package.count != 4)
			continue;

		obj = &(element->package.elements[0]);

		if (obj->type != ACPI_TYPE_BUFFER)
			continue;

		reg = (struct acpi_power_register *)obj->buffer.pointer;

		if (reg->space_id != ACPI_ADR_SPACE_SYSTEM_IO &&
		    (reg->space_id != ACPI_ADR_SPACE_FIXED_HARDWARE))
			continue;

		/* There should be an easy way to extract an integer... */
		obj = &(element->package.elements[1]);
		if (obj->type != ACPI_TYPE_INTEGER)
			continue;

		cx.type = obj->integer.value;
		/*
		 * Some buggy BIOSes won't list C1 in _CST -
		 * Let acpi_processor_get_power_info_default() handle them later
		 */
		if (i == 1 && cx.type != ACPI_STATE_C1)
			current_count++;