linux_dsm_epyc7002/drivers/cpufreq/freq_table.c
Rafael J. Wysocki 0a5fcc0a21 cpufreq: ACPI: Set cpuinfo.max_freq directly if max boost is known
commit 538b0188da4653b9f4511a114f014354fb6fb7a5 upstream.

Commit 3c55e94c0ade ("cpufreq: ACPI: Extend frequency tables to cover
boost frequencies") attempted to address a performance issue involving
acpi-cpufreq, the schedutil governor and scale-invariance on x86 by
extending the frequency tables created by acpi-cpufreq to cover the
entire range of "turbo" (or "boost") frequencies, but that caused
frequencies reported via /proc/cpuinfo and the scaling_cur_freq
attribute in sysfs to change which may confuse users and monitoring
tools.

For this reason, revert the part of commit 3c55e94c0ade adding the
extra entry to the frequency table and use the observation that
in principle cpuinfo.max_freq need not be equal to the maximum
frequency listed in the frequency table for the given policy.

Namely, modify cpufreq_frequency_table_cpuinfo() to allow cpufreq
drivers to set their own cpuinfo.max_freq above that frequency and
change  acpi-cpufreq to set cpuinfo.max_freq to the maximum boost
frequency found via CPPC.

This should be sufficient to let all of the cpufreq subsystem know
the real maximum frequency of the CPU without changing frequency
reporting.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=211305
Fixes: 3c55e94c0ade ("cpufreq: ACPI: Extend frequency tables to cover boost frequencies")
Reported-by: Matt McDonald <gardotd426@gmail.com>
Tested-by: Matt McDonald <gardotd426@gmail.com>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Tested-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Tested-by: Michael Larabel <Michael@phoronix.com>
Cc: 5.11+ <stable@vger.kernel.org> # 5.11+
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2021-03-04 11:38:22 +01:00

371 lines
8.8 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/drivers/cpufreq/freq_table.c
*
* Copyright (C) 2002 - 2003 Dominik Brodowski
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cpufreq.h>
#include <linux/module.h>
/*********************************************************************
* FREQUENCY TABLE HELPERS *
*********************************************************************/
bool policy_has_boost_freq(struct cpufreq_policy *policy)
{
struct cpufreq_frequency_table *pos, *table = policy->freq_table;
if (!table)
return false;
cpufreq_for_each_valid_entry(pos, table)
if (pos->flags & CPUFREQ_BOOST_FREQ)
return true;
return false;
}
EXPORT_SYMBOL_GPL(policy_has_boost_freq);
int cpufreq_frequency_table_cpuinfo(struct cpufreq_policy *policy,
struct cpufreq_frequency_table *table)
{
struct cpufreq_frequency_table *pos;
unsigned int min_freq = ~0;
unsigned int max_freq = 0;
unsigned int freq;
cpufreq_for_each_valid_entry(pos, table) {
freq = pos->frequency;
if (!cpufreq_boost_enabled()
&& (pos->flags & CPUFREQ_BOOST_FREQ))
continue;
pr_debug("table entry %u: %u kHz\n", (int)(pos - table), freq);
if (freq < min_freq)
min_freq = freq;
if (freq > max_freq)
max_freq = freq;
}
policy->min = policy->cpuinfo.min_freq = min_freq;
policy->max = max_freq;
/*
* If the driver has set its own cpuinfo.max_freq above max_freq, leave
* it as is.
*/
if (policy->cpuinfo.max_freq < max_freq)
policy->max = policy->cpuinfo.max_freq = max_freq;
if (policy->min == ~0)
return -EINVAL;
else
return 0;
}
int cpufreq_frequency_table_verify(struct cpufreq_policy_data *policy,
struct cpufreq_frequency_table *table)
{
struct cpufreq_frequency_table *pos;
unsigned int freq, next_larger = ~0;
bool found = false;
pr_debug("request for verification of policy (%u - %u kHz) for cpu %u\n",
policy->min, policy->max, policy->cpu);
cpufreq_verify_within_cpu_limits(policy);
cpufreq_for_each_valid_entry(pos, table) {
freq = pos->frequency;
if ((freq >= policy->min) && (freq <= policy->max)) {
found = true;
break;
}
if ((next_larger > freq) && (freq > policy->max))
next_larger = freq;
}
if (!found) {
policy->max = next_larger;
cpufreq_verify_within_cpu_limits(policy);
}
pr_debug("verification lead to (%u - %u kHz) for cpu %u\n",
policy->min, policy->max, policy->cpu);
return 0;
}
EXPORT_SYMBOL_GPL(cpufreq_frequency_table_verify);
/*
* Generic routine to verify policy & frequency table, requires driver to set
* policy->freq_table prior to it.
*/
int cpufreq_generic_frequency_table_verify(struct cpufreq_policy_data *policy)
{
if (!policy->freq_table)
return -ENODEV;
return cpufreq_frequency_table_verify(policy, policy->freq_table);
}
EXPORT_SYMBOL_GPL(cpufreq_generic_frequency_table_verify);
int cpufreq_table_index_unsorted(struct cpufreq_policy *policy,
unsigned int target_freq,
unsigned int relation)
{
struct cpufreq_frequency_table optimal = {
.driver_data = ~0,
.frequency = 0,
};
struct cpufreq_frequency_table suboptimal = {
.driver_data = ~0,
.frequency = 0,
};
struct cpufreq_frequency_table *pos;
struct cpufreq_frequency_table *table = policy->freq_table;
unsigned int freq, diff, i = 0;
int index;
pr_debug("request for target %u kHz (relation: %u) for cpu %u\n",
target_freq, relation, policy->cpu);
switch (relation) {
case CPUFREQ_RELATION_H:
suboptimal.frequency = ~0;
break;
case CPUFREQ_RELATION_L:
case CPUFREQ_RELATION_C:
optimal.frequency = ~0;
break;
}
cpufreq_for_each_valid_entry_idx(pos, table, i) {
freq = pos->frequency;
if ((freq < policy->min) || (freq > policy->max))
continue;
if (freq == target_freq) {
optimal.driver_data = i;
break;
}
switch (relation) {
case CPUFREQ_RELATION_H:
if (freq < target_freq) {
if (freq >= optimal.frequency) {
optimal.frequency = freq;
optimal.driver_data = i;
}
} else {
if (freq <= suboptimal.frequency) {
suboptimal.frequency = freq;
suboptimal.driver_data = i;
}
}
break;
case CPUFREQ_RELATION_L:
if (freq > target_freq) {
if (freq <= optimal.frequency) {
optimal.frequency = freq;
optimal.driver_data = i;
}
} else {
if (freq >= suboptimal.frequency) {
suboptimal.frequency = freq;
suboptimal.driver_data = i;
}
}
break;
case CPUFREQ_RELATION_C:
diff = abs(freq - target_freq);
if (diff < optimal.frequency ||
(diff == optimal.frequency &&
freq > table[optimal.driver_data].frequency)) {
optimal.frequency = diff;
optimal.driver_data = i;
}
break;
}
}
if (optimal.driver_data > i) {
if (suboptimal.driver_data > i) {
WARN(1, "Invalid frequency table: %d\n", policy->cpu);
return 0;
}
index = suboptimal.driver_data;
} else
index = optimal.driver_data;
pr_debug("target index is %u, freq is:%u kHz\n", index,
table[index].frequency);
return index;
}
EXPORT_SYMBOL_GPL(cpufreq_table_index_unsorted);
int cpufreq_frequency_table_get_index(struct cpufreq_policy *policy,
unsigned int freq)
{
struct cpufreq_frequency_table *pos, *table = policy->freq_table;
int idx;
if (unlikely(!table)) {
pr_debug("%s: Unable to find frequency table\n", __func__);
return -ENOENT;
}
cpufreq_for_each_valid_entry_idx(pos, table, idx)
if (pos->frequency == freq)
return idx;
return -EINVAL;
}
EXPORT_SYMBOL_GPL(cpufreq_frequency_table_get_index);
/*
* show_available_freqs - show available frequencies for the specified CPU
*/
static ssize_t show_available_freqs(struct cpufreq_policy *policy, char *buf,
bool show_boost)
{
ssize_t count = 0;
struct cpufreq_frequency_table *pos, *table = policy->freq_table;
if (!table)
return -ENODEV;
cpufreq_for_each_valid_entry(pos, table) {
/*
* show_boost = true and driver_data = BOOST freq
* display BOOST freqs
*
* show_boost = false and driver_data = BOOST freq
* show_boost = true and driver_data != BOOST freq
* continue - do not display anything
*
* show_boost = false and driver_data != BOOST freq
* display NON BOOST freqs
*/
if (show_boost ^ (pos->flags & CPUFREQ_BOOST_FREQ))
continue;
count += sprintf(&buf[count], "%d ", pos->frequency);
}
count += sprintf(&buf[count], "\n");
return count;
}
#define cpufreq_attr_available_freq(_name) \
struct freq_attr cpufreq_freq_attr_##_name##_freqs = \
__ATTR_RO(_name##_frequencies)
/*
* show_scaling_available_frequencies - show available normal frequencies for
* the specified CPU
*/
static ssize_t scaling_available_frequencies_show(struct cpufreq_policy *policy,
char *buf)
{
return show_available_freqs(policy, buf, false);
}
cpufreq_attr_available_freq(scaling_available);
EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_available_freqs);
/*
* show_available_boost_freqs - show available boost frequencies for
* the specified CPU
*/
static ssize_t scaling_boost_frequencies_show(struct cpufreq_policy *policy,
char *buf)
{
return show_available_freqs(policy, buf, true);
}
cpufreq_attr_available_freq(scaling_boost);
EXPORT_SYMBOL_GPL(cpufreq_freq_attr_scaling_boost_freqs);
struct freq_attr *cpufreq_generic_attr[] = {
&cpufreq_freq_attr_scaling_available_freqs,
NULL,
};
EXPORT_SYMBOL_GPL(cpufreq_generic_attr);
static int set_freq_table_sorted(struct cpufreq_policy *policy)
{
struct cpufreq_frequency_table *pos, *table = policy->freq_table;
struct cpufreq_frequency_table *prev = NULL;
int ascending = 0;
policy->freq_table_sorted = CPUFREQ_TABLE_UNSORTED;
cpufreq_for_each_valid_entry(pos, table) {
if (!prev) {
prev = pos;
continue;
}
if (pos->frequency == prev->frequency) {
pr_warn("Duplicate freq-table entries: %u\n",
pos->frequency);
return -EINVAL;
}
/* Frequency increased from prev to pos */
if (pos->frequency > prev->frequency) {
/* But frequency was decreasing earlier */
if (ascending < 0) {
pr_debug("Freq table is unsorted\n");
return 0;
}
ascending++;
} else {
/* Frequency decreased from prev to pos */
/* But frequency was increasing earlier */
if (ascending > 0) {
pr_debug("Freq table is unsorted\n");
return 0;
}
ascending--;
}
prev = pos;
}
if (ascending > 0)
policy->freq_table_sorted = CPUFREQ_TABLE_SORTED_ASCENDING;
else
policy->freq_table_sorted = CPUFREQ_TABLE_SORTED_DESCENDING;
pr_debug("Freq table is sorted in %s order\n",
ascending > 0 ? "ascending" : "descending");
return 0;
}
int cpufreq_table_validate_and_sort(struct cpufreq_policy *policy)
{
int ret;
if (!policy->freq_table)
return 0;
ret = cpufreq_frequency_table_cpuinfo(policy, policy->freq_table);
if (ret)
return ret;
return set_freq_table_sorted(policy);
}
MODULE_AUTHOR("Dominik Brodowski <linux@brodo.de>");
MODULE_DESCRIPTION("CPUfreq frequency table helpers");
MODULE_LICENSE("GPL");