Re: [RFC 2/3] CPPC: Add support for Collaborative Processor Performance Control
From: Ashwin Chaugule
Date: Thu Aug 14 2014 - 16:12:28 EST
+ Rafael [corrected email addr]
On 14 August 2014 15:57, Ashwin Chaugule <ashwin.chaugule@xxxxxxxxxx> wrote:
> Add support for parsing the CPC tables as described in the
> ACPI 5.1+ CPPC specification. When successfully parsed along
> with low level register accessors, then enable the PID
> (proportional-intergral-derivative) controller based algorithm
> to manage CPU performance.
>
> Signed-off-by: Ashwin Chaugule <ashwin.chaugule@xxxxxxxxxx>
> ---
> drivers/acpi/pcc.c | 109 ++++++
> drivers/cpufreq/Kconfig | 10 +
> drivers/cpufreq/Makefile | 1 +
> drivers/cpufreq/cppc.c | 874 +++++++++++++++++++++++++++++++++++++++++++++++
> drivers/cpufreq/cppc.h | 181 ++++++++++
> 5 files changed, 1175 insertions(+)
> create mode 100644 drivers/cpufreq/cppc.c
> create mode 100644 drivers/cpufreq/cppc.h
>
> diff --git a/drivers/acpi/pcc.c b/drivers/acpi/pcc.c
> index 105e11a..7743f12 100644
> --- a/drivers/acpi/pcc.c
> +++ b/drivers/acpi/pcc.c
> @@ -31,6 +31,12 @@
> #define PCC_CMD_COMPLETE 0x1
> #define PCC_VERSION "0.1"
>
> +#define PCC_HACK 1
> +
> +#ifdef PCC_HACK
> +static void *pcc_comm_addr;
> +#endif
> +
> struct pcc_ss_desc {
> struct acpi_pcct_subspace *pcc_ss_ptr;
> raw_spinlock_t lock;
> @@ -51,8 +57,13 @@ int get_pcc_comm_channel(u32 ss_idx, u64 __iomem *addr, int *len)
> struct acpi_pcct_subspace *pcct_subspace = pcc_ss_arr[ss_idx].pcc_ss_ptr;
>
> if (pcct_subspace) {
> +#ifndef PCC_HACK
> *addr = pcct_subspace->base_address;
> *len = pcct_subspace->length;
> +#else
> + *addr = (u64 *)pcc_comm_addr;
> + *len = PAGE_SIZE;
> +#endif
> } else
> return -EINVAL;
>
> @@ -61,6 +72,7 @@ int get_pcc_comm_channel(u32 ss_idx, u64 __iomem *addr, int *len)
> return 0;
> }
>
> +#ifndef PCC_HACK
> /* Send PCC cmd on behalf of this (subspace id) PCC client */
> u16 send_pcc_cmd(u8 cmd, u8 sci, u32 ss_idx, u64 __iomem *base_addr)
> {
> @@ -114,6 +126,93 @@ u16 send_pcc_cmd(u8 cmd, u8 sci, u32 ss_idx, u64 __iomem *base_addr)
> return generic_comm_base->status;
> }
>
> +#else
> +
> +#include <asm/msr.h>
> +
> +/* These offsets are from the SSDT9.asl table on the Thinkpad X240 */
> +
> +/* These are offsets per CPU from which its CPC table begins. */
> +int cpu_base[] = {0, 0x64, 0xC8, 0x12C, 0x190, 0x1F4, 0x258, 0x2BC};
> +
> +/* These are offsets of the registers in each CPC table. */
> +#define HIGHEST_PERF_OFFSET 0x0
> +#define LOWEST_PERF_OFFSET 0xc
> +#define DESIRED_PERF_OFFSET 0x14
> +
> +static int core_get_min(void)
> +{
> + u64 val;
> + rdmsrl(MSR_PLATFORM_INFO, val);
> + return (val >> 40) & 0xff;
> +}
> +
> +static int core_get_max(void)
> +{
> + u64 val;
> + rdmsrl(MSR_PLATFORM_INFO, val);
> + return (val >> 8) & 0xff;
> +}
> +
> +static int core_get_turbo(void)
> +{
> + u64 value;
> + int nont, ret;
> +
> + rdmsrl(MSR_NHM_TURBO_RATIO_LIMIT, value);
> + nont = core_get_max();
> + ret = ((value) & 255);
> + if (ret <= nont)
> + ret = nont;
> + return ret;
> +}
> +
> +u16 send_pcc_cmd(u8 cmd, u8 sci, u32 ss_idx, u64 __iomem *base_addr)
> +{
> + unsigned int cpu;
> + u64 desired_val;
> +
> + raw_spin_lock(&pcc_ss_arr[ss_idx].lock);
> + /*XXX: Instead of waiting for platform to consume the cmd,
> + * just do what the platform would've done.
> + */
> + switch (cmd) {
> + case 0: //PCC_CMD_READ
> +
> + /* XXX: Normally the Platform would need to update all the other CPPC registers as well.
> + * But for this experiment, since we're not really using all of them, we'll only update
> + * what we use.
> + */
> + for_each_possible_cpu(cpu) {
> + *(char*)(pcc_comm_addr + cpu_base[cpu] + HIGHEST_PERF_OFFSET) = core_get_turbo();
> + *(char*)(pcc_comm_addr + cpu_base[cpu] + LOWEST_PERF_OFFSET) = core_get_min();
> + }
> + break;
> + case 1: //PCC_CMD_WRITE
> +
> + /* XXX: All this hackery is very X86 Thinkpad X240 specific.
> + * Normally, the cpc_write64() would have all the info on
> + * how, where and what to write.
> + */
> + for_each_possible_cpu(cpu) {
> + desired_val = *(u64*)(pcc_comm_addr + cpu_base[cpu] + DESIRED_PERF_OFFSET);
> +
> + if (desired_val) {
> + wrmsrl_on_cpu(cpu, MSR_IA32_PERF_CTL, desired_val << 8);
> + *(u64*)(pcc_comm_addr + cpu_base[cpu] + DESIRED_PERF_OFFSET) = 0;
> + }
> + }
> + break;
> + default:
> + pr_err("Unknown PCC cmd from the OS\n");
> + return 0;
> + }
> +
> + raw_spin_unlock(&pcc_ss_arr[ss_idx].lock);
> + return 1;
> +}
> +#endif
> +
> static int parse_pcc_subspace(struct acpi_subtable_header *header,
> const unsigned long end)
> {
> @@ -185,6 +284,16 @@ static int __init pcc_init(void)
> return -EINVAL;
> }
>
> +#ifdef PCC_HACK
> + pcc_comm_addr = kzalloc(PAGE_SIZE, GFP_KERNEL);
> +
> + if (!pcc_comm_addr) {
> + pr_err("Could not allocate mem for pcc hack\n");
> + return -ENOMEM;
> + }
> +
> +#endif
> +
> return ret;
> }
> device_initcall(pcc_init);
> diff --git a/drivers/cpufreq/Kconfig b/drivers/cpufreq/Kconfig
> index ffe350f..d8e8335 100644
> --- a/drivers/cpufreq/Kconfig
> +++ b/drivers/cpufreq/Kconfig
> @@ -196,6 +196,16 @@ config GENERIC_CPUFREQ_CPU0
>
> If in doubt, say N.
>
> +config CPPC_CPUFREQ
> + bool "CPPC CPUFreq driver"
> + depends on ACPI && ACPI_PCC
> + default n
> + help
> + CPPC is Collaborative Processor Performance Control. It allows the OS
> + to request CPU performance with an abstract metric and lets the platform
> + (e.g. BMC) interpret and optimize it for power and performance in a
> + platform specific manner.
> +
> menu "x86 CPU frequency scaling drivers"
> depends on X86
> source "drivers/cpufreq/Kconfig.x86"
> diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
> index db6d9a2..b392c8c 100644
> --- a/drivers/cpufreq/Makefile
> +++ b/drivers/cpufreq/Makefile
> @@ -14,6 +14,7 @@ obj-$(CONFIG_CPU_FREQ_GOV_CONSERVATIVE) += cpufreq_conservative.o
> obj-$(CONFIG_CPU_FREQ_GOV_COMMON) += cpufreq_governor.o
>
> obj-$(CONFIG_GENERIC_CPUFREQ_CPU0) += cpufreq-cpu0.o
> +obj-$(CONFIG_CPPC_CPUFREQ) += cppc.o
>
> ##################################################################################
> # x86 drivers.
> diff --git a/drivers/cpufreq/cppc.c b/drivers/cpufreq/cppc.c
> new file mode 100644
> index 0000000..6917ce0
> --- /dev/null
> +++ b/drivers/cpufreq/cppc.c
> @@ -0,0 +1,874 @@
> +/*
> + * Copyright (C) 2014 Linaro Ltd.
> + * Author: Ashwin Chaugule <ashwin.chaugule@xxxxxxxxxx>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * PID algo bits are from intel_pstate.c and modified to use CPPC
> + * accessors.
> + *
> + */
> +
> +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
> +
> +#include <linux/kernel_stat.h>
> +#include <linux/module.h>
> +#include <linux/hrtimer.h>
> +#include <linux/tick.h>
> +#include <linux/slab.h>
> +#include <linux/sched.h>
> +#include <linux/list.h>
> +#include <linux/cpu.h>
> +#include <linux/cpufreq.h>
> +#include <linux/sysfs.h>
> +#include <linux/types.h>
> +#include <linux/fs.h>
> +#include <linux/debugfs.h>
> +#include <linux/acpi.h>
> +#include <linux/errno.h>
> +
> +#include <acpi/processor.h>
> +#include <acpi/actypes.h>
> +
> +#include <trace/events/power.h>
> +
> +#include <asm/div64.h>
> +#include <asm/msr.h>
> +
> +#include "cppc.h"
> +
> +#define FRAC_BITS 8
> +#define int_tofp(X) ((int64_t)(X) << FRAC_BITS)
> +#define fp_toint(X) ((X) >> FRAC_BITS)
> +
> +#define CPPC_EN 1
> +#define PCC_CMD_COMPLETE 1
> +
> +/* There is one CPC descriptor per CPU */
> +static DEFINE_PER_CPU(struct cpc_desc *, cpc_desc_ptr);
> +
> +/* PCC client specifics for the CPPC structure */
> +/* Returned by the PCCT Subspace structure */
> +static u64 pcc_comm_base_addr;
> +
> +/* ioremap the pcc_comm_base_addr*/
> +static void __iomem *comm_base_addr;
> +
> +/* The PCC subspace used by the CPC table */
> +static s8 pcc_subspace_idx = -1;
> +
> +extern int get_pcc_comm_channel(u32 ss_idx, u64* addr, int *len);
> +extern u16 send_pcc_cmd(u8 cmd, u8 sci, u32 ss_idx, u64 * __iomem base_addr);
> +
> +/*
> + * The low level platform specific accessors
> + * to the registers defined in the CPC table
> + */
> +struct cpc_funcs *cppc_func_ops;
> +
> +static struct cpudata **all_cpu_data;
> +static struct pstate_adjust_policy pid_params;
> +
> +/* PCC Commands used by CPPC */
> +enum cppc_ppc_cmds {
> + PCC_CMD_READ,
> + PCC_CMD_WRITE,
> + RESERVED,
> +};
> +
> +static struct perf_limits limits = {
> + .max_perf_pct = 100,
> + .max_perf = int_tofp(1),
> + .min_perf_pct = 0,
> + .min_perf = 0,
> + .max_policy_pct = 100,
> + .max_sysfs_pct = 100,
> +};
> +
> +u64 cpc_read64(struct cpc_register_resource *reg, void __iomem *base_addr)
> +{
> + u64 err = 0;
> + u64 val;
> +
> + switch (reg->space_id) {
> + case ACPI_ADR_SPACE_PLATFORM_COMM:
> + err = readq((void *) (reg->address + *(u64 *)base_addr));
> + break;
> + case ACPI_ADR_SPACE_FIXED_HARDWARE:
> + rdmsrl(reg->address, val);
> + return val;
> + break;
> + default:
> + pr_err("unknown space_id detected in cpc reg: %d\n", reg->space_id);
> + break;
> + }
> +
> + return err;
> +}
> +
> +int cpc_write64(u64 val, struct cpc_register_resource *reg, void __iomem *base_addr)
> +{
> + unsigned int err = 0;
> +
> + switch (reg->space_id) {
> + case ACPI_ADR_SPACE_PLATFORM_COMM:
> + writeq(val, (void *)(reg->address + *(u64 *)base_addr));
> + break;
> + case ACPI_ADR_SPACE_FIXED_HARDWARE:
> + wrmsrl(reg->address, val);
> + break;
> + default:
> + pr_err("unknown space_id detected in cpc reg: %d\n", reg->space_id);
> + break;
> + }
> +
> + return err;
> +}
> +
> +static inline int32_t mul_fp(int32_t x, int32_t y)
> +{
> + return ((int64_t)x * (int64_t)y) >> FRAC_BITS;
> +}
> +
> +static inline int32_t div_fp(int32_t x, int32_t y)
> +{
> + return div_s64((int64_t)x << FRAC_BITS, (int64_t)y);
> +}
> +
> +static inline void pid_reset(struct _pid *pid, int setpoint, int busy,
> + int deadband, int integral) {
> + pid->setpoint = setpoint;
> + pid->deadband = deadband;
> + pid->integral = int_tofp(integral);
> + pid->last_err = int_tofp(setpoint) - int_tofp(busy);
> +}
> +
> +static inline void pid_p_gain_set(struct _pid *pid, int percent)
> +{
> + pid->p_gain = div_fp(int_tofp(percent), int_tofp(100));
> +}
> +
> +static inline void pid_i_gain_set(struct _pid *pid, int percent)
> +{
> + pid->i_gain = div_fp(int_tofp(percent), int_tofp(100));
> +}
> +
> +static inline void pid_d_gain_set(struct _pid *pid, int percent)
> +{
> + pid->d_gain = div_fp(int_tofp(percent), int_tofp(100));
> +}
> +
> +static signed int pid_calc(struct _pid *pid, int32_t busy)
> +{
> + signed int result;
> + int32_t pterm, dterm, fp_error;
> + int32_t integral_limit;
> +
> + fp_error = int_tofp(pid->setpoint) - busy;
> +
> + if (abs(fp_error) <= int_tofp(pid->deadband))
> + return 0;
> +
> + pterm = mul_fp(pid->p_gain, fp_error);
> +
> + pid->integral += fp_error;
> +
> + /* limit the integral term */
> + integral_limit = int_tofp(30);
> + if (pid->integral > integral_limit)
> + pid->integral = integral_limit;
> + if (pid->integral < -integral_limit)
> + pid->integral = -integral_limit;
> +
> + dterm = mul_fp(pid->d_gain, fp_error - pid->last_err);
> + pid->last_err = fp_error;
> +
> + result = pterm + mul_fp(pid->integral, pid->i_gain) + dterm;
> + result = result + (1 << (FRAC_BITS-1));
> + return (signed int)fp_toint(result);
> +}
> +
> +static inline void pstate_busy_pid_reset(struct cpudata *cpu)
> +{
> + pid_p_gain_set(&cpu->pid, pid_params.p_gain_pct);
> + pid_d_gain_set(&cpu->pid, pid_params.d_gain_pct);
> + pid_i_gain_set(&cpu->pid, pid_params.i_gain_pct);
> +
> + pid_reset(&cpu->pid,
> + pid_params.setpoint,
> + 100,
> + pid_params.deadband,
> + 0);
> +}
> +
> +static inline void pstate_reset_all_pid(void)
> +{
> + unsigned int cpu;
> + for_each_online_cpu(cpu) {
> + if (all_cpu_data[cpu])
> + pstate_busy_pid_reset(all_cpu_data[cpu]);
> + }
> +}
> +
> +/************************** debugfs begin ************************/
> +static int pid_param_set(void *data, u64 val)
> +{
> + *(u32 *)data = val;
> + pstate_reset_all_pid();
> + return 0;
> +}
> +
> +static int pid_param_get(void *data, u64 *val)
> +{
> + *val = *(u32 *)data;
> + return 0;
> +}
> +DEFINE_SIMPLE_ATTRIBUTE(fops_pid_param, pid_param_get,
> + pid_param_set, "%llu\n");
> +
> +struct pid_param {
> + char *name;
> + void *value;
> +};
> +
> +static struct pid_param pid_files[] = {
> + {"sample_rate_ms", &pid_params.sample_rate_ms},
> + {"d_gain_pct", &pid_params.d_gain_pct},
> + {"i_gain_pct", &pid_params.i_gain_pct},
> + {"deadband", &pid_params.deadband},
> + {"setpoint", &pid_params.setpoint},
> + {"p_gain_pct", &pid_params.p_gain_pct},
> + {NULL, NULL}
> +};
> +
> +static struct dentry *debugfs_parent;
> +static void cppc_pstate_debug_expose_params(void)
> +{
> + int i = 0;
> +
> + debugfs_parent = debugfs_create_dir("pstate_snb", NULL);
> + if (IS_ERR_OR_NULL(debugfs_parent))
> + return;
> + while (pid_files[i].name) {
> + debugfs_create_file(pid_files[i].name, 0660,
> + debugfs_parent, pid_files[i].value,
> + &fops_pid_param);
> + i++;
> + }
> +}
> +
> +/************************** debugfs end ************************/
> +
> +/************************** sysfs begin ************************/
> +#define show_one(file_name, object) \
> + static ssize_t show_##file_name \
> + (struct kobject *kobj, struct attribute *attr, char *buf) \
> + { \
> + return sprintf(buf, "%u\n", limits.object); \
> + }
> +
> +static ssize_t store_max_perf_pct(struct kobject *a, struct attribute *b,
> + const char *buf, size_t count)
> +{
> + unsigned int input;
> + int ret;
> + ret = sscanf(buf, "%u", &input);
> + if (ret != 1)
> + return -EINVAL;
> +
> + limits.max_sysfs_pct = clamp_t(int, input, 0 , 100);
> + limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
> + limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
> + return count;
> +}
> +
> +static ssize_t store_min_perf_pct(struct kobject *a, struct attribute *b,
> + const char *buf, size_t count)
> +{
> + unsigned int input;
> + int ret;
> + ret = sscanf(buf, "%u", &input);
> + if (ret != 1)
> + return -EINVAL;
> + limits.min_perf_pct = clamp_t(int, input, 0 , 100);
> + limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
> +
> + return count;
> +}
> +
> +show_one(max_perf_pct, max_perf_pct);
> +show_one(min_perf_pct, min_perf_pct);
> +
> +define_one_global_rw(max_perf_pct);
> +define_one_global_rw(min_perf_pct);
> +
> +static struct attribute *cppc_pstate_attributes[] = {
> + &max_perf_pct.attr,
> + &min_perf_pct.attr,
> + NULL
> +};
> +
> +static struct attribute_group cppc_pstate_attr_group = {
> + .attrs = cppc_pstate_attributes,
> +};
> +static struct kobject *cppc_pstate_kobject;
> +
> +static void cppc_pstate_sysfs_expose_params(void)
> +{
> + int rc;
> +
> + cppc_pstate_kobject = kobject_create_and_add("cppc_pstate",
> + &cpu_subsys.dev_root->kobj);
> + BUG_ON(!cppc_pstate_kobject);
> + rc = sysfs_create_group(cppc_pstate_kobject,
> + &cppc_pstate_attr_group);
> + BUG_ON(rc);
> +}
> +
> +/************************** sysfs end ************************/
> +
> +static inline void pstate_calc_busy(struct cpudata *cpu)
> +{
> + struct sample *sample = &cpu->sample;
> + int64_t core_pct;
> + int32_t rem;
> +
> + core_pct = int_tofp(sample->delivered) * int_tofp(100);
> + core_pct = div_u64_rem(core_pct, int_tofp(sample->reference), &rem);
> +
> + if ((rem << 1) >= int_tofp(sample->reference))
> + core_pct += 1;
> +
> + sample->freq = fp_toint(
> + mul_fp(int_tofp(cpu->pstate.max_pstate * 1000), core_pct));
> +
> + sample->core_pct_busy = (int32_t)core_pct;
> +}
> +
> +static inline void pstate_sample(struct cpudata *cpu)
> +{
> + u64 delivered, reference;
> + unsigned int status;
> + /*
> + * If this platform has a PCCT, then
> + * send a command to the platform to update
> + * all PCC registers.
> + */
> + if (comm_base_addr) {
> + pr_debug("Sending PCC READ to update COMM space\n");
> + status = send_pcc_cmd(PCC_CMD_READ, 0, pcc_subspace_idx,
> + comm_base_addr);
> +
> + if (!(status & PCC_CMD_COMPLETE)) {
> + pr_err("Err updating PCC comm space\n");
> + return;
> + }
> + }
> +
> + reference = cppc_func_ops->get_ref_perf_ctr(cpu);
> + delivered = cppc_func_ops->get_delivered_ctr(cpu);
> +
> + delivered = delivered >> FRAC_BITS;
> + reference = reference >> FRAC_BITS;
> +
> + cpu->last_sample_time = cpu->sample.time;
> + cpu->sample.time = ktime_get();
> + cpu->sample.delivered = delivered;
> + cpu->sample.reference = reference;
> + cpu->sample.delivered -= cpu->prev_delivered;
> + cpu->sample.reference -= cpu->prev_reference;
> +
> + pstate_calc_busy(cpu);
> +
> + cpu->prev_delivered = delivered;
> + cpu->prev_reference = reference;
> +}
> +
> +static inline int32_t pstate_get_scaled_busy(struct cpudata *cpu)
> +{
> + int32_t core_busy, max_pstate, current_pstate, sample_ratio;
> + u32 duration_us;
> + u32 sample_time;
> +
> + core_busy = cpu->sample.core_pct_busy;
> + max_pstate = int_tofp(cpu->pstate.max_pstate);
> + current_pstate = int_tofp(cpu->pstate.current_pstate);
> + core_busy = mul_fp(core_busy, div_fp(max_pstate, current_pstate));
> +
> + sample_time = (pid_params.sample_rate_ms * USEC_PER_MSEC);
> + duration_us = (u32) ktime_us_delta(cpu->sample.time,
> + cpu->last_sample_time);
> + if (duration_us > sample_time * 3) {
> + sample_ratio = div_fp(int_tofp(sample_time),
> + int_tofp(duration_us));
> + core_busy = mul_fp(core_busy, sample_ratio);
> + }
> +
> + return core_busy;
> +}
> +
> +static inline void pstate_set_sample_time(struct cpudata *cpu)
> +{
> + int sample_time, delay;
> +
> + sample_time = pid_params.sample_rate_ms;
> + delay = msecs_to_jiffies(sample_time);
> + mod_timer_pinned(&cpu->timer, jiffies + delay);
> +}
> +
> +static void pstate_get_min_max(struct cpudata *cpu, int *min, int *max)
> +{
> + int max_perf = cpu->pstate.max_pstate;
> + int max_perf_adj;
> + int min_perf;
> +
> + max_perf_adj = fp_toint(mul_fp(int_tofp(max_perf), limits.max_perf));
> + *max = clamp_t(int, max_perf_adj,
> + cpu->pstate.min_pstate, cpu->pstate.max_pstate);
> +
> + min_perf = fp_toint(mul_fp(int_tofp(max_perf), limits.min_perf));
> + *min = clamp_t(int, min_perf,
> + cpu->pstate.min_pstate, max_perf);
> +}
> +
> +static void set_pstate(struct cpudata *cpu, int pstate)
> +{
> + int max_perf, min_perf;
> + unsigned int status;
> +
> + pstate_get_min_max(cpu, &min_perf, &max_perf);
> +
> + pstate = clamp_t(int, pstate, min_perf, max_perf);
> +
> + if (pstate == cpu->pstate.current_pstate)
> + return;
> +
> + trace_cpu_frequency(pstate * 100000, cpu->cpu);
> +
> + cpu->pstate.current_pstate = pstate;
> +
> + cppc_func_ops->set_desired_perf(cpu, pstate);
> +
> + /*
> + * Send a Write command to tell the platform that
> + * there is new data in the PCC registers.
> + */
> + if (comm_base_addr) {
> + pr_debug("Sending PCC WRITE to update COMM space\n");
> + status = send_pcc_cmd(PCC_CMD_WRITE, 0, pcc_subspace_idx,
> + comm_base_addr);
> +
> + if (!(status & PCC_CMD_COMPLETE)) {
> + pr_err("Err updating PCC comm space\n");
> + return;
> + }
> + }
> +}
> +
> +static inline void pstate_pstate_increase(struct cpudata *cpu, int steps)
> +{
> + int target;
> + target = cpu->pstate.current_pstate + steps;
> +
> + set_pstate(cpu, target);
> +}
> +
> +static inline void pstate_pstate_decrease(struct cpudata *cpu, int steps)
> +{
> + int target;
> + target = cpu->pstate.current_pstate - steps;
> + set_pstate(cpu, target);
> +}
> +
> +static inline void pstate_adjust_busy_pstate(struct cpudata *cpu)
> +{
> + int32_t busy_scaled;
> + struct _pid *pid;
> + signed int ctl = 0;
> + int steps;
> +
> + pid = &cpu->pid;
> + busy_scaled = pstate_get_scaled_busy(cpu);
> +
> + ctl = pid_calc(pid, busy_scaled);
> +
> + steps = abs(ctl);
> +
> + if (ctl < 0)
> + pstate_pstate_increase(cpu, steps);
> + else
> + pstate_pstate_decrease(cpu, steps);
> +}
> +
> +static void pstate_timer_func(unsigned long __data)
> +{
> + struct cpudata *cpu = (struct cpudata *) __data;
> + struct sample *sample;
> +
> + pstate_sample(cpu);
> +
> + sample = &cpu->sample;
> +
> + pstate_adjust_busy_pstate(cpu);
> +
> + trace_pstate_sample(fp_toint(sample->core_pct_busy),
> + fp_toint(pstate_get_scaled_busy(cpu)),
> + cpu->pstate.current_pstate,
> + sample->reference,
> + sample->delivered,
> + sample->freq);
> +
> + pstate_set_sample_time(cpu);
> +}
> +
> +static int cppc_cpufreq_init(struct cpufreq_policy *policy)
> +{
> + struct cpudata *cpu;
> + unsigned int cpunum = policy->cpu;
> + unsigned int status;
> + struct cpc_desc *current_cpu_cpc = per_cpu(cpc_desc_ptr, cpunum);
> +
> + all_cpu_data[cpunum] = kzalloc(sizeof(struct cpudata), GFP_KERNEL);
> + if (!all_cpu_data[cpunum])
> + return -ENOMEM;
> +
> + cpu = all_cpu_data[cpunum];
> +
> + cpu->cpu = cpunum;
> +
> + if (!cppc_func_ops) {
> + pr_err("CPPC is not supported on this platform\n");
> + return -ENOTSUPP;
> + }
> +
> + if (!current_cpu_cpc) {
> + pr_err("Undefined CPC descriptor for CPU:%d\n", cpunum);
> + return -ENODEV;
> + }
> +
> + /*
> + * If this platform has a PCCT, then
> + * send a command to the platform to update
> + * all PCC registers.
> + */
> + if (comm_base_addr) {
> + pr_debug("Sending PCC READ to update COMM space\n");
> + status = send_pcc_cmd(PCC_CMD_READ, 0, pcc_subspace_idx,
> + comm_base_addr);
> +
> + if (!(status & PCC_CMD_COMPLETE)) {
> + pr_err("Err updating PCC comm space\n");
> + return -EIO;
> + }
> + }
> +
> + cpu->cpc_desc = current_cpu_cpc;
> + cpu->pcc_comm_address = comm_base_addr;
> + cpu->pstate.min_pstate = cppc_func_ops->get_lowest_perf(cpu);
> + cpu->pstate.max_pstate = cppc_func_ops->get_highest_perf(cpu);
> + /* PCC reads/writes are made to offsets from this base address.*/
> +
> + set_pstate(cpu, cpu->pstate.min_pstate);
> +
> + init_timer_deferrable(&cpu->timer);
> + cpu->timer.function = pstate_timer_func;
> + cpu->timer.data =
> + (unsigned long)cpu;
> + cpu->timer.expires = jiffies + HZ/100;
> + pstate_busy_pid_reset(cpu);
> + pstate_sample(cpu);
> +
> + add_timer_on(&cpu->timer, cpunum);
> +
> + pr_info("CPPC PID pstate controlling: cpu %d\n", cpunum);
> +
> + if (limits.min_perf_pct == 100 && limits.max_perf_pct == 100)
> + policy->policy = CPUFREQ_POLICY_PERFORMANCE;
> + else
> + policy->policy = CPUFREQ_POLICY_POWERSAVE;
> +
> + policy->min = cpu->pstate.min_pstate * 100000;
> + policy->max = cpu->pstate.max_pstate * 100000;
> +
> + /* cpuinfo and default policy values */
> + policy->cpuinfo.min_freq = cpu->pstate.min_pstate * 100000;
> + policy->cpuinfo.max_freq = cpu->pstate.max_pstate * 100000;
> + policy->cpuinfo.transition_latency = CPUFREQ_ETERNAL;
> + cpumask_set_cpu(policy->cpu, policy->cpus);
> +
> + return 0;
> +}
> +
> +static void cppc_stop_cpu(struct cpufreq_policy *policy)
> +{
> + int cpu_num = policy->cpu;
> + struct cpudata *cpu = all_cpu_data[cpu_num];
> +
> + pr_info("CPPC PID controller CPU %d exiting\n", cpu_num);
> +
> + del_timer_sync(&all_cpu_data[cpu_num]->timer);
> + set_pstate(cpu, cpu->pstate.min_pstate);
> + kfree(all_cpu_data[cpu_num]);
> + all_cpu_data[cpu_num] = NULL;
> + kfree(cpu->cpc_desc);
> +}
> +
> +static int cppc_verify_policy(struct cpufreq_policy *policy)
> +{
> + cpufreq_verify_within_cpu_limits(policy);
> +
> + if ((policy->policy != CPUFREQ_POLICY_POWERSAVE) &&
> + (policy->policy != CPUFREQ_POLICY_PERFORMANCE))
> + return -EINVAL;
> +
> + return 0;
> +}
> +
> +static int cppc_set_policy(struct cpufreq_policy *policy)
> +{
> + struct cpudata *cpu;
> +
> + cpu = all_cpu_data[policy->cpu];
> +
> + if (!policy->cpuinfo.max_freq)
> + return -ENODEV;
> +
> + if (policy->policy == CPUFREQ_POLICY_PERFORMANCE) {
> + limits.min_perf_pct = 100;
> + limits.min_perf = int_tofp(1);
> + limits.max_perf_pct = 100;
> + limits.max_perf = int_tofp(1);
> + return 0;
> + }
> + limits.min_perf_pct = (policy->min * 100) / policy->cpuinfo.max_freq;
> + limits.min_perf_pct = clamp_t(int, limits.min_perf_pct, 0 , 100);
> + limits.min_perf = div_fp(int_tofp(limits.min_perf_pct), int_tofp(100));
> +
> + limits.max_policy_pct = policy->max * 100 / policy->cpuinfo.max_freq;
> + limits.max_policy_pct = clamp_t(int, limits.max_policy_pct, 0 , 100);
> + limits.max_perf_pct = min(limits.max_policy_pct, limits.max_sysfs_pct);
> + limits.max_perf = div_fp(int_tofp(limits.max_perf_pct), int_tofp(100));
> +
> + return 0;
> +}
> +
> +static unsigned int cppc_get(unsigned int cpu_num)
> +{
> + struct sample *sample;
> + struct cpudata *cpu;
> +
> + cpu = all_cpu_data[cpu_num];
> + if (!cpu)
> + return 0;
> + sample = &cpu->sample;
> + return sample->freq;
> +}
> +
> +static struct cpufreq_driver cppc_cpufreq = {
> + .flags = CPUFREQ_CONST_LOOPS,
> + .verify = cppc_verify_policy,
> + .setpolicy = cppc_set_policy,
> + .get = cppc_get,
> + .init = cppc_cpufreq_init,
> + .stop_cpu = cppc_stop_cpu,
> + .name = "cppc_cpufreq",
> +};
> +
> +static int cppc_processor_probe(void)
> +{
> + struct acpi_buffer output = {ACPI_ALLOCATE_BUFFER, NULL};
> + union acpi_object *out_obj, *cpc_obj;
> + struct cpc_desc *current_cpu_cpc;
> + struct cpc_register_resource *gas_t;
> + char proc_name[11];
> + unsigned int num_ent, ret = 0, i, cpu, len;
> + acpi_handle handle;
> + acpi_status status;
> +
> + /*Parse the ACPI _CPC table for each CPU. */
> + for_each_online_cpu(cpu) {
> + sprintf(proc_name, "\\_PR.CPU%d", cpu);
> +
> + status = acpi_get_handle(NULL, proc_name, &handle);
> + if (ACPI_FAILURE(status)) {
> + ret = -ENODEV;
> + goto out_free;
> + }
> +
> + if (!acpi_has_method(handle, "_CPC")) {
> + ret = -ENODEV;
> + goto out_free;
> + }
> +
> + status = acpi_evaluate_object(handle, "_CPC", NULL, &output);
> + if (ACPI_FAILURE(status)) {
> + ret = -ENODEV;
> + goto out_free;
> + }
> +
> + out_obj = (union acpi_object *) output.pointer;
> + if (out_obj->type != ACPI_TYPE_PACKAGE) {
> + ret = -ENODEV;
> + goto out_free;
> + }
> +
> + current_cpu_cpc = kzalloc(sizeof(struct cpc_desc), GFP_KERNEL);
> + if (!current_cpu_cpc) {
> + pr_err("Could not allocate per cpu CPC descriptors\n");
> + return -ENOMEM;
> + }
> + num_ent = out_obj->package.count;
> + current_cpu_cpc->num_entries = num_ent;
> +
> + pr_debug("num_ent in CPC table:%d\n", num_ent);
> +
> + /* Iterate through each entry in _CPC */
> + for (i = 2; i < num_ent; i++) {
> + cpc_obj = &out_obj->package.elements[i];
> +
> + if (cpc_obj->type != ACPI_TYPE_BUFFER) {
> + pr_err("Malformed PCC entry in CPC table\n");
> + ret = -EINVAL;
> + goto out_free;
> + }
> +
> + gas_t = (struct cpc_register_resource *) cpc_obj->buffer.pointer;
> +
> + if (gas_t->space_id == ACPI_ADR_SPACE_PLATFORM_COMM) {
> + if (pcc_subspace_idx < 0)
> + pcc_subspace_idx = gas_t->access_width;
> + }
> +
> + current_cpu_cpc->cpc_regs[i-2] = (struct cpc_register_resource) {
> + .space_id = gas_t->space_id,
> + .length = gas_t->length,
> + .bit_width = gas_t->bit_width,
> + .bit_offset = gas_t->bit_offset,
> + .address = gas_t->address,
> + .access_width = gas_t->access_width,
> + };
> + }
> + per_cpu(cpc_desc_ptr, cpu) = current_cpu_cpc;
> + }
> +
> + pr_debug("Completed parsing , now onto PCC init\n");
> +
> + if (pcc_subspace_idx >= 0) {
> + ret = get_pcc_comm_channel(pcc_subspace_idx, &pcc_comm_base_addr, &len);
> + if (ret) {
> + pr_err("No PCC Communication Channel found\n");
> + ret = -ENODEV;
> + goto out_free;
> + }
> +
> + //XXX: PCC HACK: The PCC hack in drivers/acpi/pcc.c just
> + //returns a kmallocd address, so no point in ioremapping
> + //it here. Instead we'll just use it directly.
> + //Normally, we'd ioremap the address specified in the PCCT
> + //header for this PCC subspace.
> +
> + comm_base_addr = &pcc_comm_base_addr;
> +
> + // comm_base_addr = ioremap_nocache(pcc_comm_base_addr, len);
> +
> + // if (!comm_base_addr) {
> + // pr_err("ioremapping pcc comm space failed\n");
> + // ret = -ENOMEM;
> + // goto out_free;
> + // }
> + pr_debug("PCC ioremapd space:%p, PCCT addr: %lld\n", comm_base_addr, pcc_comm_base_addr);
> +
> + } else {
> + pr_err("No PCC subspace detected in any CPC structure!\n");
> + ret = -EINVAL;
> + goto out_free;
> + }
> +
> + /* Everything looks okay */
> + pr_info("Successfully parsed all CPC structs\n");
> + pr_debug("Enable CPPC_EN\n");
> + /*XXX: Send write cmd to enable CPPC */
> +
> + kfree(output.pointer);
> + return 0;
> +
> +out_free:
> + for_each_online_cpu(cpu) {
> + current_cpu_cpc = per_cpu(cpc_desc_ptr, cpu);
> + if (current_cpu_cpc)
> + kfree(current_cpu_cpc);
> + }
> +
> + kfree(output.pointer);
> + return -ENODEV;
> +}
> +
> +static void copy_pid_params(struct pstate_adjust_policy *policy)
> +{
> + pid_params.sample_rate_ms = policy->sample_rate_ms;
> + pid_params.p_gain_pct = policy->p_gain_pct;
> + pid_params.i_gain_pct = policy->i_gain_pct;
> + pid_params.d_gain_pct = policy->d_gain_pct;
> + pid_params.deadband = policy->deadband;
> + pid_params.setpoint = policy->setpoint;
> +}
> +
> +static int __init cppc_init(void)
> +{
> + int ret = 0;
> + unsigned int cpu;
> +
> + /*
> + * Platform specific low level accessors should be
> + * initialized by now if CPPC is supported.
> + */
> + if (!cppc_func_ops) {
> + pr_err("No CPPC low level accessors found\n");
> + return -ENODEV;
> + }
> +
> + if(acpi_disabled || cppc_processor_probe()) {
> + pr_err("Err initializing CPC structures or ACPI is disabled\n");
> + return -ENODEV;
> + }
> +
> + copy_pid_params(&cppc_func_ops->pid_policy);
> +
> + pr_info("CPPC PID driver initializing.\n");
> +
> + all_cpu_data = vzalloc(sizeof(void *) * num_possible_cpus());
> + if (!all_cpu_data)
> + return -ENOMEM;
> +
> + /* Now register with CPUfreq */
> + ret = cpufreq_register_driver(&cppc_cpufreq);
> + if (ret)
> + goto out;
> +
> + cppc_pstate_debug_expose_params();
> + cppc_pstate_sysfs_expose_params();
> +
> + return ret;
> +
> +out:
> + get_online_cpus();
> + for_each_online_cpu(cpu) {
> + if (all_cpu_data[cpu]) {
> + del_timer_sync(&all_cpu_data[cpu]->timer);
> + kfree(all_cpu_data[cpu]);
> + }
> + }
> +
> + put_online_cpus();
> + vfree(all_cpu_data);
> + return -ENODEV;
> +}
> +device_initcall(cppc_init);
> diff --git a/drivers/cpufreq/cppc.h b/drivers/cpufreq/cppc.h
> new file mode 100644
> index 0000000..3adbd3d
> --- /dev/null
> +++ b/drivers/cpufreq/cppc.h
> @@ -0,0 +1,181 @@
> +/*
> + * Copyright (C) 2014 Linaro Ltd.
> + * Author: Ashwin Chaugule <ashwin.chaugule@xxxxxxxxxx>
> + *
> + * This program is free software; you can redistribute it and/or modify
> + * it under the terms of the GNU General Public License as published by
> + * the Free Software Foundation; either version 2 of the License, or
> + * (at your option) any later version.
> + *
> + * This program is distributed in the hope that it will be useful,
> + * but WITHOUT ANY WARRANTY; without even the implied warranty of
> + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> + * GNU General Public License for more details.
> + *
> + * PID algo bits are from intel_pstate.c and modified to use CPPC
> + * accessors.
> + *
> + */
> +
> +#ifndef _CPPC_H
> +#define _CPPC_H
> +
> +#include <linux/kernel.h>
> +#include <linux/types.h>
> +#include <linux/ktime.h>
> +#include <linux/hrtimer.h>
> +/*
> + * The max number of Register entries
> + * in the CPC table
> + */
> +#define MAX_CPC_REG_ENT 19
> +
> +/* These are indexes into the per-cpu cpc_regs[]. Order is important. */
> +enum cppc_pcc_regs {
> + HIGHEST_PERF, /* Highest Performance */
> + NOMINAL_PERF, /* Nominal Performance */
> + LOW_NON_LINEAR_PERF, /* Lowest Nonlinear Performance */
> + LOWEST_PERF, /* Lowest Performance */
> + GUARANTEED_PERF, /* Guaranteed Performance Register */
> + DESIRED_PERF, /* Desired Performance Register */
> + MIN_PERF, /* Minimum Performance Register */
> + MAX_PERF, /* Maximum Performance Register */
> + PERF_REDUC_TOLERANCE, /* Performance Reduction Tolerance Register */
> + TIME_WINDOW, /* Time Window Register */
> + CTR_WRAP_TIME, /* Counter Wraparound Time */
> + REFERENCE_CTR, /* Reference Counter Register */
> + DELIVERED_CTR, /* Delivered Counter Register */
> + PERF_LIMITED, /* Performance Limited Register */
> + ENABLE, /* Enable Register */
> + AUTO_SEL_ENABLE, /* Autonomous Selection Enable */
> + AUTO_ACT_WINDOW, /* Autonomous Activity Window */
> + ENERGY_PERF, /* Energy Performance Preference Register */
> + REFERENCE_PERF, /* Reference Performance */
> +};
> +
> +/* Each register in the CPC table has the following format */
> +struct cpc_register_resource {
> + u8 descriptor;
> + u16 length;
> + u8 space_id;
> + u8 bit_width;
> + u8 bit_offset;
> + u8 access_width;
> + u64 __iomem address;
> +} __attribute__ ((packed));
> +
> +struct cpc_desc {
> + unsigned int num_entries;
> + unsigned int version;
> + struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT];
> +};
> +
> +struct _pid {
> + int setpoint;
> + int32_t integral;
> + int32_t p_gain;
> + int32_t i_gain;
> + int32_t d_gain;
> + int deadband;
> + int32_t last_err;
> +};
> +
> +struct sample {
> + int32_t core_pct_busy;
> + u64 delivered;
> + u64 reference;
> + int freq;
> + ktime_t time;
> +};
> +
> +struct pstate_data {
> + int current_pstate;
> + int min_pstate;
> + int max_pstate;
> +};
> +
> +struct cpudata {
> + int cpu;
> +
> + struct timer_list timer;
> +
> + struct pstate_data pstate;
> + struct _pid pid;
> +
> + ktime_t last_sample_time;
> + u64 prev_delivered;
> + u64 prev_reference;
> + struct sample sample;
> + struct cpc_desc *cpc_desc;
> + void __iomem *pcc_comm_address;
> +};
> +
> +struct perf_limits {
> + int max_perf_pct;
> + int min_perf_pct;
> + int32_t max_perf;
> + int32_t min_perf;
> + int max_policy_pct;
> + int max_sysfs_pct;
> +};
> +
> +struct pstate_adjust_policy {
> + int sample_rate_ms;
> + int deadband;
> + int setpoint;
> + int p_gain_pct;
> + int d_gain_pct;
> + int i_gain_pct;
> +};
> +
> +struct cpc_funcs {
> + struct pstate_adjust_policy pid_policy;
> +
> + u32 (*get_highest_perf)(struct cpudata *);
> + u32 (*get_nominal_perf)(struct cpudata *);
> + u64 (*get_ref_perf_ctr)(struct cpudata *);
> + u32 (*get_lowest_nonlinear_perf)(struct cpudata *);
> + u32 (*get_lowest_perf)(struct cpudata *);
> + u32 (*get_guaranteed_perf)(struct cpudata *);
> +
> + u32 (*get_desired_perf)(struct cpudata *);
> + void (*set_desired_perf)(struct cpudata *, u32 val);
> +
> + u64 (*get_delivered_ctr)(struct cpudata *);
> +
> + /* Optional */
> + u32 (*get_max_perf)(struct cpudata *);
> + void (*set_max_perf)(struct cpudata *, u32 val);
> +
> + u32 (*get_min_perf)(struct cpudata *);
> + void (*set_min_perf)(struct cpudata *, u32 val);
> +
> + u32 (*get_perf_reduc)(struct cpudata *);
> + void (*set_perf_reduc)(struct cpudata *, u32 val);
> +
> + u32 (*get_time_window)(struct cpudata *);
> + void (*set_time_window)(struct cpudata *, u32 msecs);
> +
> + u64 (*get_ctr_wraparound)(struct cpudata *);
> + void (*set_ctr_wraparound)(struct cpudata *, u32 secs);
> +
> + u8 (*get_perf_limit)(struct cpudata *);
> + void (*set_perf_limit)(struct cpudata *);
> +
> + void (*set_cppc_enable)(struct cpudata *);
> +
> + u8 (*get_auto_sel_en)(struct cpudata *);
> + void (*set_auto_sel_en)(struct cpudata *);
> +
> + void (*set_auto_activity)(struct cpudata *, u32 val);
> +
> + void (*set_energy_pref)(struct cpudata *, u32 val);
> +
> + u32 (*get_ref_perf_rate)(struct cpudata *);
> +};
> +
> +extern struct cpc_funcs *cppc_func_ops;
> +extern u64 cpc_read64(struct cpc_register_resource *reg);
> +extern int cpc_write64(u64 val, struct cpc_register_resource *reg);
> +
> +#endif /* _CPPC_H */
> --
> 1.9.1
>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/