/**
 * acpi_idle_enter_bm - enters C3 with proper BM handling
 * @dev: the target CPU
 * @drv: cpuidle driver containing state data
 * @index: the index of suggested state
 *
 * If BM is detected, the deepest non-C3 idle state is entered instead.
 */
static int acpi_idle_enter_bm(struct cpuidle_device *dev,
		struct cpuidle_driver *drv, int index)
{
	struct acpi_processor *pr;
	struct acpi_processor_cx *cx = per_cpu(acpi_cstate[index], dev->cpu);

	pr = __this_cpu_read(processors);

	if (unlikely(!pr))
		return -EINVAL;

	if (!cx->bm_sts_skip && acpi_idle_bm_check()) {
		if (drv->safe_state_index >= 0) {
			return drv->states[drv->safe_state_index].enter(dev,
						drv, drv->safe_state_index);
		} else {
			acpi_safe_halt();
			return -EBUSY;
		}
	}

	if (cx->entry_method != ACPI_CSTATE_FFH) {
		current_thread_info()->status &= ~TS_POLLING;
		/*
		 * TS_POLLING-cleared state must be visible before we test
		 * NEED_RESCHED:
		 */
		smp_mb();

		if (unlikely(need_resched())) {
			current_thread_info()->status |= TS_POLLING;
			return -EINVAL;
		}
	}

	acpi_unlazy_tlb(smp_processor_id());

	/* Tell the scheduler that we are going deep-idle: */
	sched_clock_idle_sleep_event();
	/*
	 * Must be done before busmaster disable as we might need to
	 * access HPET !
	 */
	lapic_timer_state_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) {
		raw_spin_lock(&c3_lock);
		c3_cpu_count++;
		/* Disable bus master arbitration when all CPUs are in C3 */
		if (c3_cpu_count == num_online_cpus())
			acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 1);
		raw_spin_unlock(&c3_lock);
	} else if (!pr->flags.bm_check) {
		ACPI_FLUSH_CPU_CACHE();
	}

	acpi_idle_do_entry(cx);

	/* Re-enable bus master arbitration */
	if (pr->flags.bm_check && pr->flags.bm_control) {
		raw_spin_lock(&c3_lock);
		acpi_write_bit_register(ACPI_BITREG_ARB_DISABLE, 0);
		c3_cpu_count--;
		raw_spin_unlock(&c3_lock);
	}

	sched_clock_idle_wakeup_event(0);

	if (cx->entry_method != ACPI_CSTATE_FFH)
		current_thread_info()->status |= TS_POLLING;

	lapic_timer_state_broadcast(pr, cx, 0);
	return index;
}

/**
 * cppc_set_perf - Set a CPUs performance controls.
 * @cpu: CPU for which to set performance controls.
 * @perf_ctrls: ptr to cppc_perf_ctrls. See cppc_acpi.h
 *
 * Return: 0 for success, -ERRNO otherwise.
 */
int cppc_set_perf(int cpu, struct cppc_perf_ctrls *perf_ctrls)
{
	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpu);
	struct cpc_register_resource *desired_reg;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
	struct cppc_pcc_data *pcc_ss_data = NULL;
	int ret = 0;

	if (!cpc_desc) {
		pr_debug("No CPC descriptor for CPU:%d\n", cpu);
		return -ENODEV;
	}

	desired_reg = &cpc_desc->cpc_regs[DESIRED_PERF];

	/*
	 * This is Phase-I where we want to write to CPC registers
	 * -> We want all CPUs to be able to execute this phase in parallel
	 *
	 * Since read_lock can be acquired by multiple CPUs simultaneously we
	 * achieve that goal here
	 */
	if (CPC_IN_PCC(desired_reg)) {
		if (pcc_ss_id < 0) {
			pr_debug("Invalid pcc_ss_id\n");
			return -ENODEV;
		}
		pcc_ss_data = pcc_data[pcc_ss_id];
		down_read(&pcc_ss_data->pcc_lock); /* BEGIN Phase-I */
		if (pcc_ss_data->platform_owns_pcc) {
			ret = check_pcc_chan(pcc_ss_id, false);
			if (ret) {
				up_read(&pcc_ss_data->pcc_lock);
				return ret;
			}
		}
		/*
		 * Update the pending_write to make sure a PCC CMD_READ will not
		 * arrive and steal the channel during the switch to write lock
		 */
		pcc_ss_data->pending_pcc_write_cmd = true;
		cpc_desc->write_cmd_id = pcc_ss_data->pcc_write_cnt;
		cpc_desc->write_cmd_status = 0;
	}

	/*
	 * Skip writing MIN/MAX until Linux knows how to come up with
	 * useful values.
	 */
	cpc_write(cpu, desired_reg, perf_ctrls->desired_perf);

	if (CPC_IN_PCC(desired_reg))
		up_read(&pcc_ss_data->pcc_lock);	/* END Phase-I */
	/*
	 * This is Phase-II where we transfer the ownership of PCC to Platform
	 *
	 * Short Summary: Basically if we think of a group of cppc_set_perf
	 * requests that happened in short overlapping interval. The last CPU to
	 * come out of Phase-I will enter Phase-II and ring the doorbell.
	 *
	 * We have the following requirements for Phase-II:
	 *     1. We want to execute Phase-II only when there are no CPUs
	 * currently executing in Phase-I
	 *     2. Once we start Phase-II we want to avoid all other CPUs from
	 * entering Phase-I.
	 *     3. We want only one CPU among all those who went through Phase-I
	 * to run phase-II
	 *
	 * If write_trylock fails to get the lock and doesn't transfer the
	 * PCC ownership to the platform, then one of the following will be TRUE
	 *     1. There is at-least one CPU in Phase-I which will later execute
	 * write_trylock, so the CPUs in Phase-I will be responsible for
	 * executing the Phase-II.
	 *     2. Some other CPU has beaten this CPU to successfully execute the
	 * write_trylock and has already acquired the write_lock. We know for a
	 * fact it(other CPU acquiring the write_lock) couldn't have happened
	 * before this CPU's Phase-I as we held the read_lock.
	 *     3. Some other CPU executing pcc CMD_READ has stolen the
	 * down_write, in which case, send_pcc_cmd will check for pending
	 * CMD_WRITE commands by checking the pending_pcc_write_cmd.
	 * So this CPU can be certain that its request will be delivered
	 *    So in all cases, this CPU knows that its request will be delivered
	 * by another CPU and can return
	 *
	 * After getting the down_write we still need to check for
	 * pending_pcc_write_cmd to take care of the following scenario
	 *    The thread running this code could be scheduled out between
	 * Phase-I and Phase-II. Before it is scheduled back on, another CPU
	 * could have delivered the request to Platform by triggering the
	 * doorbell and transferred the ownership of PCC to platform. So this
	 * avoids triggering an unnecessary doorbell and more importantly before
	 * triggering the doorbell it makes sure that the PCC channel ownership
	 * is still with OSPM.
//.........这里部分代码省略.........

/**
 * acpi_get_psd_map - Map the CPUs in a common freq domain.
 * @all_cpu_data: Ptrs to CPU specific CPPC data including PSD info.
 *
 *	Return: 0 for success or negative value for err.
 */
int acpi_get_psd_map(struct cppc_cpudata **all_cpu_data)
{
	int count_target;
	int retval = 0;
	unsigned int i, j;
	cpumask_var_t covered_cpus;
	struct cppc_cpudata *pr, *match_pr;
	struct acpi_psd_package *pdomain;
	struct acpi_psd_package *match_pdomain;
	struct cpc_desc *cpc_ptr, *match_cpc_ptr;

	if (!zalloc_cpumask_var(&covered_cpus, GFP_KERNEL))
		return -ENOMEM;

	/*
	 * Now that we have _PSD data from all CPUs, lets setup P-state
	 * domain info.
	 */
	for_each_possible_cpu(i) {
		pr = all_cpu_data[i];
		if (!pr)
			continue;

		if (cpumask_test_cpu(i, covered_cpus))
			continue;

		cpc_ptr = per_cpu(cpc_desc_ptr, i);
		if (!cpc_ptr) {
			retval = -EFAULT;
			goto err_ret;
		}

		pdomain = &(cpc_ptr->domain_info);
		cpumask_set_cpu(i, pr->shared_cpu_map);
		cpumask_set_cpu(i, covered_cpus);
		if (pdomain->num_processors <= 1)
			continue;

		/* Validate the Domain info */
		count_target = pdomain->num_processors;
		if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ALL)
			pr->shared_type = CPUFREQ_SHARED_TYPE_ALL;
		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_HW_ALL)
			pr->shared_type = CPUFREQ_SHARED_TYPE_HW;
		else if (pdomain->coord_type == DOMAIN_COORD_TYPE_SW_ANY)
			pr->shared_type = CPUFREQ_SHARED_TYPE_ANY;

		for_each_possible_cpu(j) {
			if (i == j)
				continue;

			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
			if (!match_cpc_ptr) {
				retval = -EFAULT;
				goto err_ret;
			}

			match_pdomain = &(match_cpc_ptr->domain_info);
			if (match_pdomain->domain != pdomain->domain)
				continue;

			/* Here i and j are in the same domain */
			if (match_pdomain->num_processors != count_target) {
				retval = -EFAULT;
				goto err_ret;
			}

			if (pdomain->coord_type != match_pdomain->coord_type) {
				retval = -EFAULT;
				goto err_ret;
			}

			cpumask_set_cpu(j, covered_cpus);
			cpumask_set_cpu(j, pr->shared_cpu_map);
		}

		for_each_possible_cpu(j) {
			if (i == j)
				continue;

			match_pr = all_cpu_data[j];
			if (!match_pr)
				continue;

			match_cpc_ptr = per_cpu(cpc_desc_ptr, j);
			if (!match_cpc_ptr) {
				retval = -EFAULT;
				goto err_ret;
			}

			match_pdomain = &(match_cpc_ptr->domain_info);
			if (match_pdomain->domain != pdomain->domain)
				continue;

//.........这里部分代码省略.........

STATIC int
xfs_read_xfsstats(
	char		*buffer,
	char		**start,
	off_t		offset,
	int		count,
	int		*eof,
	void		*data)
{
	int		c, i, j, len, val;
	__uint64_t	xs_xstrat_bytes = 0;
	__uint64_t	xs_write_bytes = 0;
	__uint64_t	xs_read_bytes = 0;

	static struct xstats_entry {
		char	*desc;
		int	endpoint;
	} xstats[] = {
		{ "extent_alloc",	XFSSTAT_END_EXTENT_ALLOC	},
		{ "abt",		XFSSTAT_END_ALLOC_BTREE		},
		{ "blk_map",		XFSSTAT_END_BLOCK_MAPPING	},
		{ "bmbt",		XFSSTAT_END_BLOCK_MAP_BTREE	},
		{ "dir",		XFSSTAT_END_DIRECTORY_OPS	},
		{ "trans",		XFSSTAT_END_TRANSACTIONS	},
		{ "ig",			XFSSTAT_END_INODE_OPS		},
		{ "log",		XFSSTAT_END_LOG_OPS		},
		{ "push_ail",		XFSSTAT_END_TAIL_PUSHING	},
		{ "xstrat",		XFSSTAT_END_WRITE_CONVERT	},
		{ "rw",			XFSSTAT_END_READ_WRITE_OPS	},
		{ "attr",		XFSSTAT_END_ATTRIBUTE_OPS	},
		{ "icluster",		XFSSTAT_END_INODE_CLUSTER	},
		{ "vnodes",		XFSSTAT_END_VNODE_OPS		},
		{ "buf",		XFSSTAT_END_BUF			},
	};

	/* Loop over all stats groups */
	for (i=j=len = 0; i < sizeof(xstats)/sizeof(struct xstats_entry); i++) {
		len += sprintf(buffer + len, xstats[i].desc);
		/* inner loop does each group */
		while (j < xstats[i].endpoint) {
			val = 0;
			/* sum over all cpus */
			for (c = 0; c < NR_CPUS; c++) {
				if (!cpu_possible(c)) continue;
				val += *(((__u32*)&per_cpu(xfsstats, c) + j));
			}
			len += sprintf(buffer + len, " %u", val);
			j++;
		}
		buffer[len++] = '\n';
	}
	/* extra precision counters */
	for (i = 0; i < NR_CPUS; i++) {
		if (!cpu_possible(i)) continue;
		xs_xstrat_bytes += per_cpu(xfsstats, i).xs_xstrat_bytes;
		xs_write_bytes += per_cpu(xfsstats, i).xs_write_bytes;
		xs_read_bytes += per_cpu(xfsstats, i).xs_read_bytes;
	}

	len += sprintf(buffer + len, "xpc %Lu %Lu %Lu\n",
			xs_xstrat_bytes, xs_write_bytes, xs_read_bytes);
	len += sprintf(buffer + len, "debug %u\n",
#if defined(DEBUG)
		1);
#else
		0);
#endif

	if (offset >= len) {
		*start = buffer;
		*eof = 1;
		return 0;
	}
	*start = buffer + offset;
	if ((len -= offset) > count)
		return count;
	*eof = 1;

	return len;
}

/**
 * cppc_get_perf_caps - Get a CPUs performance capabilities.
 * @cpunum: CPU from which to get capabilities info.
 * @perf_caps: ptr to cppc_perf_caps. See cppc_acpi.h
 *
 * Return: 0 for success with perf_caps populated else -ERRNO.
 */
int cppc_get_perf_caps(int cpunum, struct cppc_perf_caps *perf_caps)
{
	struct cpc_desc *cpc_desc = per_cpu(cpc_desc_ptr, cpunum);
	struct cpc_register_resource *highest_reg, *lowest_reg,
		*lowest_non_linear_reg, *nominal_reg, *guaranteed_reg,
		*low_freq_reg = NULL, *nom_freq_reg = NULL;
	u64 high, low, guaranteed, nom, min_nonlinear, low_f = 0, nom_f = 0;
	int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpunum);
	struct cppc_pcc_data *pcc_ss_data = NULL;
	int ret = 0, regs_in_pcc = 0;

	if (!cpc_desc) {
		pr_debug("No CPC descriptor for CPU:%d\n", cpunum);
		return -ENODEV;
	}

	highest_reg = &cpc_desc->cpc_regs[HIGHEST_PERF];
	lowest_reg = &cpc_desc->cpc_regs[LOWEST_PERF];
	lowest_non_linear_reg = &cpc_desc->cpc_regs[LOW_NON_LINEAR_PERF];
	nominal_reg = &cpc_desc->cpc_regs[NOMINAL_PERF];
	low_freq_reg = &cpc_desc->cpc_regs[LOWEST_FREQ];
	nom_freq_reg = &cpc_desc->cpc_regs[NOMINAL_FREQ];
	guaranteed_reg = &cpc_desc->cpc_regs[GUARANTEED_PERF];

	/* Are any of the regs PCC ?*/
	if (CPC_IN_PCC(highest_reg) || CPC_IN_PCC(lowest_reg) ||
		CPC_IN_PCC(lowest_non_linear_reg) || CPC_IN_PCC(nominal_reg) ||
		CPC_IN_PCC(low_freq_reg) || CPC_IN_PCC(nom_freq_reg)) {
		if (pcc_ss_id < 0) {
			pr_debug("Invalid pcc_ss_id\n");
			return -ENODEV;
		}
		pcc_ss_data = pcc_data[pcc_ss_id];
		regs_in_pcc = 1;
		down_write(&pcc_ss_data->pcc_lock);
		/* Ring doorbell once to update PCC subspace */
		if (send_pcc_cmd(pcc_ss_id, CMD_READ) < 0) {
			ret = -EIO;
			goto out_err;
		}
	}

	cpc_read(cpunum, highest_reg, &high);
	perf_caps->highest_perf = high;

	cpc_read(cpunum, lowest_reg, &low);
	perf_caps->lowest_perf = low;

	cpc_read(cpunum, nominal_reg, &nom);
	perf_caps->nominal_perf = nom;

	cpc_read(cpunum, guaranteed_reg, &guaranteed);
	perf_caps->guaranteed_perf = guaranteed;

	cpc_read(cpunum, lowest_non_linear_reg, &min_nonlinear);
	perf_caps->lowest_nonlinear_perf = min_nonlinear;

	if (!high || !low || !nom || !min_nonlinear)
		ret = -EFAULT;

	/* Read optional lowest and nominal frequencies if present */
	if (CPC_SUPPORTED(low_freq_reg))
		cpc_read(cpunum, low_freq_reg, &low_f);

	if (CPC_SUPPORTED(nom_freq_reg))
		cpc_read(cpunum, nom_freq_reg, &nom_f);

	perf_caps->lowest_freq = low_f;
	perf_caps->nominal_freq = nom_f;


out_err:
	if (regs_in_pcc)
		up_write(&pcc_ss_data->pcc_lock);
	return ret;
}

//.........这里部分代码省略.........

	struct mode_of of_l2_modes[] = {
		{"qcom,saw2-spm-cmd-ret", MSM_SPM_L2_MODE_RETENTION, 1},
		{"qcom,saw2-spm-cmd-gdhs", MSM_SPM_L2_MODE_GDHS, 1},
		{"qcom,saw2-spm-cmd-pc", MSM_SPM_L2_MODE_POWER_COLLAPSE, 1},
	};

	struct mode_of *mode_of_data;
	int num_modes;

	memset(&spm_data, 0, sizeof(struct msm_spm_platform_data));
	memset(&modes, 0,
		(MSM_SPM_MODE_NR - 2) * sizeof(struct msm_spm_seq_entry));

	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
	if (!res)
		goto fail;

	spm_data.reg_base_addr = devm_ioremap(&pdev->dev, res->start,
					resource_size(res));
	if (!spm_data.reg_base_addr)
		return -ENOMEM;

	key = "qcom,core-id";
	ret = of_property_read_u32(node, key, &val);
	if (ret)
		goto fail;
	cpu = val;

	key = "qcom,saw2-ver-reg";
	ret = of_property_read_u32(node, key, &val);
	if (ret)
		goto fail;
	spm_data.ver_reg = val;

	key = "qcom,vctl-timeout-us";
	ret = of_property_read_u32(node, key, &val);
	if (!ret)
		spm_data.vctl_timeout_us = val;

	/* optional */
	key = "qcom,vctl-port";
	ret = of_property_read_u32(node, key, &val);
	if (!ret)
		spm_data.vctl_port = val;

	/* optional */
	key = "qcom,phase-port";
	ret = of_property_read_u32(node, key, &val);
	if (!ret)
		spm_data.phase_port = val;

	for (i = 0; i < ARRAY_SIZE(spm_of_data); i++) {
		ret = of_property_read_u32(node, spm_of_data[i].key, &val);
		if (ret)
			continue;
		spm_data.reg_init_values[spm_of_data[i].id] = val;
	}

	/*
	 * Device with id 0..NR_CPUS are SPM for apps cores
	 * Device with id 0xFFFF is for L2 SPM.
	 */
	if (cpu >= 0 && cpu < num_possible_cpus()) {
		mode_of_data = of_cpu_modes;
		num_modes = ARRAY_SIZE(of_cpu_modes);
		dev = &per_cpu(msm_cpu_spm_device, cpu);

	} else {
		mode_of_data = of_l2_modes;
		num_modes = ARRAY_SIZE(of_l2_modes);
		dev = &msm_spm_l2_device;
	}

	for (i = 0; i < num_modes; i++) {
		key = mode_of_data[i].key;
		modes[mode_count].cmd =
			(uint8_t *)of_get_property(node, key, &len);
		if (!modes[mode_count].cmd)
			continue;
		modes[mode_count].mode = mode_of_data[i].id;
		modes[mode_count].notify_rpm = mode_of_data[i].notify_rpm;
		mode_count++;
	}

	spm_data.modes = modes;
	spm_data.num_modes = mode_count;

	ret = msm_spm_dev_init(dev, &spm_data);

	if (ret < 0)
		pr_warn("%s():failed core-id:%u ret:%d\n", __func__, cpu, ret);

	return ret;

fail:
	pr_err("%s: Failed reading node=%s, key=%s\n",
			__func__, node->full_name, key);
	return -EFAULT;
}

/**
 * omap4_enter_lowpower: OMAP4 MPUSS Low Power Entry Function
 * The purpose of this function is to manage low power programming
 * of OMAP4 MPUSS subsystem
 * @cpu : CPU ID
 * @power_state: Low power state.
 *
 * MPUSS states for the context save:
 * save_state =
 *	0 - Nothing lost and no need to save: MPUSS INACTIVE
 *	1 - CPUx L1 and logic lost: MPUSS CSWR
 *	2 - CPUx L1 and logic lost + GIC lost: MPUSS OSWR
 *	3 - CPUx L1 and logic lost + GIC + L2 lost: DEVICE OFF
 */
int omap4_enter_lowpower(unsigned int cpu, unsigned int power_state)
{
	struct omap4_cpu_pm_info *pm_info = &per_cpu(omap4_pm_info, cpu);
	unsigned int save_state = 0, cpu_logic_state = PWRDM_POWER_RET;
	unsigned int wakeup_cpu;

	if (omap_rev() == OMAP4430_REV_ES1_0)
		return -ENXIO;

	switch (power_state) {
	case PWRDM_POWER_ON:
	case PWRDM_POWER_INACTIVE:
		save_state = 0;
		break;
	case PWRDM_POWER_OFF:
		cpu_logic_state = PWRDM_POWER_OFF;
		save_state = 1;
		break;
	case PWRDM_POWER_RET:
		if (IS_PM44XX_ERRATUM(PM_OMAP4_CPU_OSWR_DISABLE)) {
			save_state = 0;
			break;
		}
	default:
		/*
		 * CPUx CSWR is invalid hardware state. Also CPUx OSWR
		 * doesn't make much scense, since logic is lost and $L1
		 * needs to be cleaned because of coherency. This makes
		 * CPUx OSWR equivalent to CPUX OFF and hence not supported
		 */
		WARN_ON(1);
		return -ENXIO;
	}

	pwrdm_pre_transition(NULL);

	/*
	 * Check MPUSS next state and save interrupt controller if needed.
	 * In MPUSS OSWR or device OFF, interrupt controller  contest is lost.
	 */
	mpuss_clear_prev_logic_pwrst();
	if ((pwrdm_read_next_pwrst(mpuss_pd) == PWRDM_POWER_RET) &&
		(pwrdm_read_logic_retst(mpuss_pd) == PWRDM_POWER_OFF))
		save_state = 2;

	cpu_clear_prev_logic_pwrst(cpu);
	pwrdm_set_next_pwrst(pm_info->pwrdm, power_state);
	pwrdm_set_logic_retst(pm_info->pwrdm, cpu_logic_state);
	set_cpu_wakeup_addr(cpu, virt_to_phys(omap_pm_ops.resume));
	omap_pm_ops.scu_prepare(cpu, power_state);
	l2x0_pwrst_prepare(cpu, save_state);

	/*
	 * Call low level function  with targeted low power state.
	 */
	if (save_state)
		cpu_suspend(save_state, omap_pm_ops.finish_suspend);
	else
		omap_pm_ops.finish_suspend(save_state);

	if (IS_PM44XX_ERRATUM(PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD) && cpu)
		gic_dist_enable();

	/*
	 * Restore the CPUx power state to ON otherwise CPUx
	 * power domain can transitions to programmed low power
	 * state while doing WFI outside the low powe code. On
	 * secure devices, CPUx does WFI which can result in
	 * domain transition
	 */
	wakeup_cpu = smp_processor_id();
	pwrdm_set_next_pwrst(pm_info->pwrdm, PWRDM_POWER_ON);

	pwrdm_post_transition(NULL);

	return 0;
}

/*
 * Every sampling_rate, we check, if current idle time is less than 20%
 * (default), then we try to increase frequency. Every sampling_rate, we look
 * for the lowest frequency which can sustain the load while keeping idle time
 * over 30%. If such a frequency exist, we try to decrease to this frequency.
 *
 * Any frequency increase takes it to the maximum frequency. Frequency reduction
 * happens at minimum steps of 5% (default) of current frequency
 */
static void od_check_cpu(int cpu, unsigned int load_freq)
{
	struct od_cpu_dbs_info_s *dbs_info = &per_cpu(od_cpu_dbs_info, cpu);
	struct cpufreq_policy *policy = dbs_info->cdbs.cur_policy;
	struct dbs_data *dbs_data = policy->governor_data;
	struct od_dbs_tuners *od_tuners = dbs_data->tuners;

	dbs_info->freq_lo = 0;

	/* Check for frequency increase */
#ifdef CONFIG_ARCH_HI6XXX
    if(load_freq > od_tuners->od_6xxx_up_threshold * policy->cur) {
        unsigned int freq_next;
		/* If increase speed, apply sampling_down_factor */
		if (policy->cur < policy->max)
			dbs_info->rate_mult =
				od_tuners->sampling_down_factor;
		if (load_freq > od_tuners->up_threshold * policy->cur)
            freq_next = policy->max;
        else
            freq_next = load_freq / od_tuners->od_6xxx_up_threshold;

		dbs_freq_increase(policy, freq_next);
        return;
	}
#else
	if (load_freq > od_tuners->up_threshold * policy->cur) {
		/* If switching to max speed, apply sampling_down_factor */
		if (policy->cur < policy->max)
			dbs_info->rate_mult =
				od_tuners->sampling_down_factor;
		dbs_freq_increase(policy, policy->max);
		return;
	}
#endif

	/* Check for frequency decrease */
	/* if we cannot reduce the frequency anymore, break out early */
	if (policy->cur == policy->min)
		return;

	/*
	 * The optimal frequency is the frequency that is the lowest that can
	 * support the current CPU usage without triggering the up policy. To be
	 * safe, we focus 10 points under the threshold.
	 */
#ifdef CONFIG_ARCH_HI6XXX
    if (load_freq < od_tuners->od_6xxx_down_threshold
			* policy->cur) {
		unsigned int freq_next;
		freq_next = load_freq / od_tuners->od_6xxx_down_threshold;
#else		
	if (load_freq < od_tuners->adj_up_threshold
			* policy->cur) {
		unsigned int freq_next;
		freq_next = load_freq / od_tuners->adj_up_threshold;
#endif

		/* No longer fully busy, reset rate_mult */
		dbs_info->rate_mult = 1;

		if (freq_next < policy->min)
			freq_next = policy->min;

		if (!od_tuners->powersave_bias) {
			__cpufreq_driver_target(policy, freq_next,
					CPUFREQ_RELATION_L);
			return;
		}

		freq_next = od_ops.powersave_bias_target(policy, freq_next,
					CPUFREQ_RELATION_L);
		__cpufreq_driver_target(policy, freq_next, CPUFREQ_RELATION_L);
	}
}

static void od_dbs_timer(struct work_struct *work)
{
	struct od_cpu_dbs_info_s *dbs_info =
		container_of(work, struct od_cpu_dbs_info_s, cdbs.work.work);
	unsigned int cpu = dbs_info->cdbs.cur_policy->cpu;
	struct od_cpu_dbs_info_s *core_dbs_info = &per_cpu(od_cpu_dbs_info,
			cpu);
	struct dbs_data *dbs_data = dbs_info->cdbs.cur_policy->governor_data;
	struct od_dbs_tuners *od_tuners = dbs_data->tuners;
	int delay = 0, sample_type = core_dbs_info->sample_type;
	bool modify_all = true;

	mutex_lock(&core_dbs_info->cdbs.timer_mutex);
	if (!need_load_eval(&core_dbs_info->cdbs, od_tuners->sampling_rate)) {
		modify_all = false;
//.........这里部分代码省略.........

void msm_spm_reinit(void)
{
	unsigned int cpu;
	for_each_possible_cpu(cpu)
		msm_spm_drv_reinit(&per_cpu(msm_cpu_spm_device.reg_data, cpu));
}

/*
 *	switch_to(x,y) should switch tasks from x to y.
 *
 * We fsave/fwait so that an exception goes off at the right time
 * (as a call from the fsave or fwait in effect) rather than to
 * the wrong process. Lazy FP saving no longer makes any sense
 * with modern CPU's, and this simplifies a lot of things (SMP
 * and UP become the same).
 *
 * NOTE! We used to use the x86 hardware context switching. The
 * reason for not using it any more becomes apparent when you
 * try to recover gracefully from saved state that is no longer
 * valid (stale segment register values in particular). With the
 * hardware task-switch, there is no way to fix up bad state in
 * a reasonable manner.
 *
 * The fact that Intel documents the hardware task-switching to
 * be slow is a fairly red herring - this code is not noticeably
 * faster. However, there _is_ some room for improvement here,
 * so the performance issues may eventually be a valid point.
 * More important, however, is the fact that this allows us much
 * more flexibility.
 *
 * The return value (in %ax) will be the "prev" task after
 * the task-switch, and shows up in ret_from_fork in entry.S,
 * for example.
 */
__notrace_funcgraph struct task_struct *
__switch_to(struct task_struct *prev_p, struct task_struct *next_p)
{
	struct thread_struct *prev = &prev_p->thread,
				 *next = &next_p->thread;
	int cpu = smp_processor_id();
	struct tss_struct *tss = &per_cpu(init_tss, cpu);
	fpu_switch_t fpu;

	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */

	fpu = switch_fpu_prepare(prev_p, next_p, cpu);

	/*
	 * Reload esp0.
	 */
	load_sp0(tss, next);

	/*
	 * Save away %gs. No need to save %fs, as it was saved on the
	 * stack on entry.  No need to save %es and %ds, as those are
	 * always kernel segments while inside the kernel.  Doing this
	 * before setting the new TLS descriptors avoids the situation
	 * where we temporarily have non-reloadable segments in %fs
	 * and %gs.  This could be an issue if the NMI handler ever
	 * used %fs or %gs (it does not today), or if the kernel is
	 * running inside of a hypervisor layer.
	 */
	lazy_save_gs(prev->gs);

	/*
	 * Load the per-thread Thread-Local Storage descriptor.
	 */
	load_TLS(next, cpu);

	/*
	 * Restore IOPL if needed.  In normal use, the flags restore
	 * in the switch assembly will handle this.  But if the kernel
	 * is running virtualized at a non-zero CPL, the popf will
	 * not restore flags, so it must be done in a separate step.
	 */
	if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
		set_iopl_mask(next->iopl);

	/*
	 * Now maybe handle debug registers and/or IO bitmaps
	 */
	if (unlikely(task_thread_info(prev_p)->flags & _TIF_WORK_CTXSW_PREV ||
		     task_thread_info(next_p)->flags & _TIF_WORK_CTXSW_NEXT))
		__switch_to_xtra(prev_p, next_p, tss);

	/*
	 * Leave lazy mode, flushing any hypercalls made here.
	 * This must be done before restoring TLS segments so
	 * the GDT and LDT are properly updated, and must be
	 * done before math_state_restore, so the TS bit is up
	 * to date.
	 */
	arch_end_context_switch(next_p);

	/*
	 * Restore %gs if needed (which is common)
	 */
	if (prev->gs | next->gs)
		lazy_load_gs(next->gs);

	switch_fpu_finish(next_p, fpu);

	percpu_write(current_task, next_p);

	return prev_p;
}

//.........这里部分代码省略.........
	}

	if (!cpu_online(policy->cpu))
		return -EINVAL;

	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
		unsigned int freq = table[i].frequency;
		if (freq == CPUFREQ_ENTRY_INVALID)
			continue;
		if (freq < policy->min || freq > policy->max)
			continue;
		if (freq == target_freq) {
			optimal.index = i;
			break;
		}
		switch (relation) {
		case CPUFREQ_RELATION_H:
			if (freq < target_freq) {
				if (freq >= optimal.frequency) {
					optimal.frequency = freq;
					optimal.index = i;
				}
			} else {
				if (freq <= suboptimal.frequency) {
					suboptimal.frequency = freq;
					suboptimal.index = i;
				}
			}
			break;
		case CPUFREQ_RELATION_L:
			if (freq > target_freq) {
				if (freq <= optimal.frequency) {
					optimal.frequency = freq;
					optimal.index = i;
				}
			} else {
				if (freq >= suboptimal.frequency) {
					suboptimal.frequency = freq;
					suboptimal.index = i;
				}
			}
			break;
		case CPUFREQ_RELATION_C:
			diff = abs(freq - target_freq);
			if (diff < optimal.frequency ||
			    (diff == optimal.frequency &&
			     freq > table[optimal.index].frequency)) {
				optimal.frequency = diff;
				optimal.index = i;
			}
			break;
		}
	}
	if (optimal.index > i) {
		if (suboptimal.index > i)
			return -EINVAL;
		*index = suboptimal.index;
	} else
		*index = optimal.index;

	pr_debug("target is %u (%u kHz, %u)\n", *index, table[*index].frequency,
		table[*index].index);

	return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_frequency_table_target);

static DEFINE_PER_CPU(struct cpufreq_frequency_table *, cpufreq_show_table);
/**
 * show_available_freqs - show available frequencies for the specified CPU
 */
static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf)
{
	unsigned int i = 0;
	unsigned int cpu = policy->cpu;
	ssize_t count = 0;
	struct cpufreq_frequency_table *table;

	if (!per_cpu(cpufreq_show_table, cpu))
		return -ENODEV;

	table = per_cpu(cpufreq_show_table, cpu);

	for (i = 0; (table[i].frequency != CPUFREQ_TABLE_END); i++) {
		if (table[i].frequency == CPUFREQ_ENTRY_INVALID)
			continue;
		count += sprintf(&buf[count], "%d ", table[i].frequency);
	}
	count += sprintf(&buf[count], "\n");

	return count;

}

struct freq_attr cpufreq_freq_attr_scaling_available_freqs = {
	.attr = { .name = "scaling_available_frequencies",
		  .mode = 0444,
		},
	.show = show_available_freqs,
};

static const cpumask_t *vector_allocation_cpumask_x2apic_cluster(int cpu)
{
    return per_cpu(cluster_cpus, cpu);
}

static void
smp_callin (void)
{
	int cpuid, phys_id, itc_master;
	struct cpuinfo_ia64 *last_cpuinfo, *this_cpuinfo;
	extern void ia64_init_itm(void);
	extern volatile int time_keeper_id;

#ifdef CONFIG_PERFMON
	extern void pfm_init_percpu(void);
#endif

	cpuid = smp_processor_id();
	phys_id = hard_smp_processor_id();
	itc_master = time_keeper_id;

	if (cpu_online(cpuid)) {
		printk(KERN_ERR "huh, phys CPU#0x%x, CPU#0x%x already present??\n",
		       phys_id, cpuid);
		BUG();
	}

	fix_b0_for_bsp();

	/*
	 * numa_node_id() works after this.
	 */
	set_numa_node(cpu_to_node_map[cpuid]);
	set_numa_mem(local_memory_node(cpu_to_node_map[cpuid]));

	ipi_call_lock_irq();
	spin_lock(&vector_lock);
	/* Setup the per cpu irq handling data structures */
	__setup_vector_irq(cpuid);
	notify_cpu_starting(cpuid);
	set_cpu_online(cpuid, true);
	per_cpu(cpu_state, cpuid) = CPU_ONLINE;
	spin_unlock(&vector_lock);
	ipi_call_unlock_irq();

	smp_setup_percpu_timer();

	ia64_mca_cmc_vector_setup();	/* Setup vector on AP */

#ifdef CONFIG_PERFMON
	pfm_init_percpu();
#endif

	local_irq_enable();

	if (!(sal_platform_features & IA64_SAL_PLATFORM_FEATURE_ITC_DRIFT)) {
		/*
		 * Synchronize the ITC with the BP.  Need to do this after irqs are
		 * enabled because ia64_sync_itc() calls smp_call_function_single(), which
		 * calls spin_unlock_bh(), which calls spin_unlock_bh(), which calls
		 * local_bh_enable(), which bugs out if irqs are not enabled...
		 */
		Dprintk("Going to syncup ITC with ITC Master.\n");
		ia64_sync_itc(itc_master);
	}

	/*
	 * Get our bogomips.
	 */
	ia64_init_itm();

	/*
	 * Delay calibration can be skipped if new processor is identical to the
	 * previous processor.
	 */
	last_cpuinfo = cpu_data(cpuid - 1);
	this_cpuinfo = local_cpu_data;
	if (last_cpuinfo->itc_freq != this_cpuinfo->itc_freq ||
	    last_cpuinfo->proc_freq != this_cpuinfo->proc_freq ||
	    last_cpuinfo->features != this_cpuinfo->features ||
	    last_cpuinfo->revision != this_cpuinfo->revision ||
	    last_cpuinfo->family != this_cpuinfo->family ||
	    last_cpuinfo->archrev != this_cpuinfo->archrev ||
	    last_cpuinfo->model != this_cpuinfo->model)
		calibrate_delay();
	local_cpu_data->loops_per_jiffy = loops_per_jiffy;

	/*
	 * Allow the master to continue.
	 */
	cpu_set(cpuid, cpu_callin_map);
	Dprintk("Stack on CPU %d at about %p\n",cpuid, &cpuid);
}

/*
 * Initialise OMAP4 MPUSS
 */
int __init omap4_mpuss_init(void)
{
	struct omap4_cpu_pm_info *pm_info;

	if (omap_rev() == OMAP4430_REV_ES1_0) {
		WARN(1, "Power Management not supported on OMAP4430 ES1.0\n");
		return -ENODEV;
	}

	/* Initilaise per CPU PM information */
	pm_info = &per_cpu(omap4_pm_info, 0x0);
	if (sar_base) {
		pm_info->scu_sar_addr = sar_base + SCU_OFFSET0;
		pm_info->wkup_sar_addr = sar_base +
					CPU0_WAKEUP_NS_PA_ADDR_OFFSET;
		pm_info->l2x0_sar_addr = sar_base + L2X0_SAVE_OFFSET0;
	}
	pm_info->pwrdm = pwrdm_lookup("cpu0_pwrdm");
	if (!pm_info->pwrdm) {
		pr_err("Lookup failed for CPU0 pwrdm\n");
		return -ENODEV;
	}

	/* Clear CPU previous power domain state */
	pwrdm_clear_all_prev_pwrst(pm_info->pwrdm);
	cpu_clear_prev_logic_pwrst(0);

	/* Initialise CPU0 power domain state to ON */
	pwrdm_set_next_pwrst(pm_info->pwrdm, PWRDM_POWER_ON);

	pm_info = &per_cpu(omap4_pm_info, 0x1);
	if (sar_base) {
		pm_info->scu_sar_addr = sar_base + SCU_OFFSET1;
		pm_info->wkup_sar_addr = sar_base +
					CPU1_WAKEUP_NS_PA_ADDR_OFFSET;
		pm_info->l2x0_sar_addr = sar_base + L2X0_SAVE_OFFSET1;
	}

	pm_info->pwrdm = pwrdm_lookup("cpu1_pwrdm");
	if (!pm_info->pwrdm) {
		pr_err("Lookup failed for CPU1 pwrdm\n");
		return -ENODEV;
	}

	/* Clear CPU previous power domain state */
	pwrdm_clear_all_prev_pwrst(pm_info->pwrdm);
	cpu_clear_prev_logic_pwrst(1);

	/* Initialise CPU1 power domain state to ON */
	pwrdm_set_next_pwrst(pm_info->pwrdm, PWRDM_POWER_ON);

	mpuss_pd = pwrdm_lookup("mpu_pwrdm");
	if (!mpuss_pd) {
		pr_err("Failed to lookup MPUSS power domain\n");
		return -ENODEV;
	}
	pwrdm_clear_all_prev_pwrst(mpuss_pd);
	mpuss_clear_prev_logic_pwrst();

	if (sar_base) {
		/* Save device type on scratchpad for low level code to use */
		writel_relaxed((omap_type() != OMAP2_DEVICE_TYPE_GP) ? 1 : 0,
			       sar_base + OMAP_TYPE_OFFSET);
		save_l2x0_context();
	}

	if (cpu_is_omap44xx()) {
		omap_pm_ops.finish_suspend = omap4_finish_suspend;
		omap_pm_ops.resume = omap4_cpu_resume;
		omap_pm_ops.scu_prepare = scu_pwrst_prepare;
		omap_pm_ops.hotplug_restart = omap4_secondary_startup;
		cpu_context_offset = OMAP4_RM_CPU0_CPU0_CONTEXT_OFFSET;
	} else if (soc_is_omap54xx() || soc_is_dra7xx()) {
		cpu_context_offset = OMAP54XX_RM_CPU0_CPU0_CONTEXT_OFFSET;
		enable_mercury_retention_mode();
	}

	if (cpu_is_omap446x())
		omap_pm_ops.hotplug_restart = omap4460_secondary_startup;

	return 0;
}

/*
 * get the current cpu vdd;
 * return: cpu vdd, based on mv;
 */
static int sunxi_cpufreq_getvolt(unsigned int cpu)
{
    u32 cur_cluster = per_cpu(physical_cluster, cpu);
    return regulator_get_voltage(cpu_vdd[cur_cluster]) / 1000;
}

static void tick_nohz_stop_sched_tick(struct tick_sched *ts)
{
	unsigned long seq, last_jiffies, next_jiffies, delta_jiffies;
	unsigned long rcu_delta_jiffies;
	ktime_t last_update, expires, now;
	struct clock_event_device *dev = __get_cpu_var(tick_cpu_device).evtdev;
	u64 time_delta;
	int cpu;

	cpu = smp_processor_id();
	ts = &per_cpu(tick_cpu_sched, cpu);

	now = tick_nohz_start_idle(cpu, ts);

	/*
	 * If this cpu is offline and it is the one which updates
	 * jiffies, then give up the assignment and let it be taken by
	 * the cpu which runs the tick timer next. If we don't drop
	 * this here the jiffies might be stale and do_timer() never
	 * invoked.
	 */
	if (unlikely(!cpu_online(cpu))) {
		if (cpu == tick_do_timer_cpu)
			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
		return;
	}

	if (unlikely(ts->nohz_mode == NOHZ_MODE_INACTIVE))
		return;

	if (need_resched())
		return;

	if (unlikely(local_softirq_pending() && cpu_online(cpu))) {
		static int ratelimit;

		if (ratelimit < 10) {
			printk(KERN_ERR "NOHZ: local_softirq_pending %02x\n",
			       (unsigned int) local_softirq_pending());
			ratelimit++;
		}
		return;
	}

	ts->idle_calls++;
	/* Read jiffies and the time when jiffies were updated last */
	do {
		seq = read_seqbegin(&xtime_lock);
		last_update = last_jiffies_update;
		last_jiffies = jiffies;
		time_delta = timekeeping_max_deferment();
	} while (read_seqretry(&xtime_lock, seq));

	if (rcu_needs_cpu(cpu, &rcu_delta_jiffies) || printk_needs_cpu(cpu) ||
	    arch_needs_cpu(cpu)) {
		next_jiffies = last_jiffies + 1;
		delta_jiffies = 1;
	} else {
		/* Get the next timer wheel timer */
		next_jiffies = get_next_timer_interrupt(last_jiffies);
		delta_jiffies = next_jiffies - last_jiffies;
		if (rcu_delta_jiffies < delta_jiffies) {
			next_jiffies = last_jiffies + rcu_delta_jiffies;
			delta_jiffies = rcu_delta_jiffies;
		}
	}
	/*
	 * Do not stop the tick, if we are only one off
	 * or if the cpu is required for rcu
	 */
	if (!ts->tick_stopped && delta_jiffies == 1)
		goto out;

	/* Schedule the tick, if we are at least one jiffie off */
	if ((long)delta_jiffies >= 1) {

		/*
		 * If this cpu is the one which updates jiffies, then
		 * give up the assignment and let it be taken by the
		 * cpu which runs the tick timer next, which might be
		 * this cpu as well. If we don't drop this here the
		 * jiffies might be stale and do_timer() never
		 * invoked. Keep track of the fact that it was the one
		 * which had the do_timer() duty last. If this cpu is
		 * the one which had the do_timer() duty last, we
		 * limit the sleep time to the timekeeping
		 * max_deferement value which we retrieved
		 * above. Otherwise we can sleep as long as we want.
		 */
		if (cpu == tick_do_timer_cpu) {
			tick_do_timer_cpu = TICK_DO_TIMER_NONE;
			ts->do_timer_last = 1;
		} else if (tick_do_timer_cpu != TICK_DO_TIMER_NONE) {
			time_delta = KTIME_MAX;
			ts->do_timer_last = 0;
		} else if (!ts->do_timer_last) {
			time_delta = KTIME_MAX;
		}

		/*
//.........这里部分代码省略.........

static int cpufreq_stats_create_table(struct cpufreq_policy *policy,
		struct cpufreq_frequency_table *table)
{
	unsigned int i, j, k, l, count = 0, ret = 0;
	struct cpufreq_stats *stat;
	struct cpufreq_policy *data;
	unsigned int alloc_size;
	unsigned int cpu = policy->cpu;
	if (per_cpu(cpufreq_stats_table, cpu))
		return -EBUSY;
	stat = kzalloc(sizeof(struct cpufreq_stats), GFP_KERNEL);
	if ((stat) == NULL)
		return -ENOMEM;

	data = cpufreq_cpu_get(cpu);
	if (data == NULL) {
		ret = -EINVAL;
		goto error_get_fail;
	}

	ret = sysfs_create_group(&data->kobj, &stats_attr_group);
	if (ret)
		goto error_out;

	stat->cpu = cpu;
	per_cpu(cpufreq_stats_table, cpu) = stat;

	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
		unsigned int freq = table[i].frequency;
		if (freq == CPUFREQ_ENTRY_INVALID)
			continue;
		count++;
	}

	alloc_size = count * sizeof(int) + count * sizeof(cputime64_t);

#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
	alloc_size += count * count * sizeof(int);
#endif
	stat->max_state = count;
	stat->time_in_state = kzalloc(alloc_size, GFP_KERNEL);
	if (!stat->time_in_state) {
		ret = -ENOMEM;
		goto error_out;
	}
	stat->freq_table = (unsigned int *)(stat->time_in_state + count);

#ifdef CONFIG_CPU_FREQ_STAT_DETAILS
	stat->trans_table = stat->freq_table + count;
#endif
	j = 0;
	for (i = 0; table[i].frequency != CPUFREQ_TABLE_END; i++) {
		unsigned int freq = table[i].frequency;
		if (freq == CPUFREQ_ENTRY_INVALID)
			continue;

		/* Insert in sorted stat->freq_table */
		for (k = 0; k < j && stat->freq_table[k] < freq; k++)
			;
		if (stat->freq_table[k] == freq)
			continue;
		for (l = j; l > k; l--)
			stat->freq_table[l] = stat->freq_table[l - 1];
		stat->freq_table[k] = freq;
		j++;
	}
	stat->state_num = j;
	spin_lock(&cpufreq_stats_lock);
	stat->last_time = get_jiffies_64();
	stat->last_index = freq_table_get_index(stat, policy->cur);
	spin_unlock(&cpufreq_stats_lock);
	cpufreq_cpu_put(data);
	return 0;
error_out:
	cpufreq_cpu_put(data);
error_get_fail:
	kfree(stat);
	per_cpu(cpufreq_stats_table, cpu) = NULL;
	return ret;
}