summaryrefslogtreecommitdiff
path: root/drivers/cpufreq/acpi-cpufreq.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/cpufreq/acpi-cpufreq.c')
-rw-r--r--drivers/cpufreq/acpi-cpufreq.c305
1 files changed, 175 insertions, 130 deletions
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index d62fd374d5c7..e73a66785d69 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* acpi-cpufreq.c - ACPI Processor P-States Driver
*
@@ -5,24 +6,6 @@
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
* Copyright (C) 2002 - 2004 Dominik Brodowski <linux@brodo.de>
* Copyright (C) 2006 Denis Sadykov <denis.m.sadykov@intel.com>
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
- *
- * 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.
- *
- * You should have received a copy of the GNU General Public License along
- * with this program; if not, write to the Free Software Foundation, Inc.,
- * 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA.
- *
- * ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -36,6 +19,8 @@
#include <linux/compiler.h>
#include <linux/dmi.h>
#include <linux/slab.h>
+#include <linux/string_helpers.h>
+#include <linux/platform_device.h>
#include <linux/acpi.h>
#include <linux/io.h>
@@ -43,10 +28,12 @@
#include <linux/uaccess.h>
#include <acpi/processor.h>
+#include <acpi/cppc_acpi.h>
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
+#include <asm/cpu_device_id.h>
MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
@@ -63,8 +50,6 @@ enum {
#define AMD_MSR_RANGE (0x7)
#define HYGON_MSR_RANGE (0x7)
-#define MSR_K7_HWCR_CPB_DIS (1ULL << 25)
-
struct acpi_cpufreq_data {
unsigned int resume;
unsigned int cpu_feature;
@@ -88,18 +73,17 @@ static unsigned int acpi_pstate_strict;
static bool boost_state(unsigned int cpu)
{
- u32 lo, hi;
u64 msr;
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_INTEL:
- rdmsr_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &lo, &hi);
- msr = lo | ((u64)hi << 32);
+ case X86_VENDOR_CENTAUR:
+ case X86_VENDOR_ZHAOXIN:
+ rdmsrq_on_cpu(cpu, MSR_IA32_MISC_ENABLE, &msr);
return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
case X86_VENDOR_HYGON:
case X86_VENDOR_AMD:
- rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
- msr = lo | ((u64)hi << 32);
+ rdmsrq_on_cpu(cpu, MSR_K7_HWCR, &msr);
return !(msr & MSR_K7_HWCR_CPB_DIS);
}
return false;
@@ -112,6 +96,8 @@ static int boost_set_msr(bool enable)
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_INTEL:
+ case X86_VENDOR_CENTAUR:
+ case X86_VENDOR_ZHAOXIN:
msr_addr = MSR_IA32_MISC_ENABLE;
msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
break;
@@ -124,14 +110,14 @@ static int boost_set_msr(bool enable)
return -EINVAL;
}
- rdmsrl(msr_addr, val);
+ rdmsrq(msr_addr, val);
if (enable)
val &= ~msr_mask;
else
val |= msr_mask;
- wrmsrl(msr_addr, val);
+ wrmsrq(msr_addr, val);
return 0;
}
@@ -142,12 +128,12 @@ static void boost_set_msr_each(void *p_en)
boost_set_msr(enable);
}
-static int set_boost(int val)
+static int set_boost(struct cpufreq_policy *policy, int val)
{
- get_online_cpus();
- on_each_cpu(boost_set_msr_each, (void *)(long)val, 1);
- put_online_cpus();
- pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");
+ on_each_cpu_mask(policy->cpus, boost_set_msr_each,
+ (void *)(long)val, 1);
+ pr_debug("CPU %*pbl: Core Boosting %s.\n",
+ cpumask_pr_args(policy->cpus), str_enabled_disabled(val));
return 0;
}
@@ -178,7 +164,9 @@ static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
if (ret || val > 1)
return -EINVAL;
- set_boost(val);
+ cpus_read_lock();
+ set_boost(policy, val);
+ cpus_read_unlock();
return count;
}
@@ -258,7 +246,7 @@ static unsigned extract_freq(struct cpufreq_policy *policy, u32 val)
static u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
{
- u32 val, dummy;
+ u32 val, dummy __always_unused;
rdmsr(MSR_IA32_PERF_CTL, val, dummy);
return val;
@@ -275,7 +263,7 @@ static void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
static u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
{
- u32 val, dummy;
+ u32 val, dummy __always_unused;
rdmsr(MSR_AMD_PERF_CTL, val, dummy);
return val;
@@ -330,7 +318,6 @@ static u32 drv_read(struct acpi_cpufreq_data *data, const struct cpumask *mask)
return cmd.val;
}
-/* Called via smp_call_function_many(), on the target CPUs */
static void do_drv_write(void *_cmd)
{
struct drv_cmd *cmd = _cmd;
@@ -347,14 +334,8 @@ static void drv_write(struct acpi_cpufreq_data *data,
.val = val,
.func.write = data->cpu_freq_write,
};
- int this_cpu;
- this_cpu = get_cpu();
- if (cpumask_test_cpu(this_cpu, mask))
- do_drv_write(&cmd);
-
- smp_call_function_many(mask, do_drv_write, &cmd, 1);
- put_cpu();
+ on_each_cpu_mask(mask, do_drv_write, &cmd, true);
}
static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
@@ -366,7 +347,7 @@ static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *dat
val = drv_read(data, mask);
- pr_debug("get_cur_val = %u\n", val);
+ pr_debug("%s = %u\n", __func__, val);
return val;
}
@@ -378,7 +359,7 @@ static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
unsigned int freq;
unsigned int cached_freq;
- pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
+ pr_debug("%s (%d)\n", __func__, cpu);
policy = cpufreq_cpu_get_raw(cpu);
if (unlikely(!policy))
@@ -414,7 +395,7 @@ static unsigned int check_freqs(struct cpufreq_policy *policy,
cur_freq = extract_freq(policy, get_cur_val(mask, data));
if (cur_freq == freq)
return 1;
- udelay(10);
+ usleep_range(10, 15);
}
return 0;
}
@@ -458,8 +439,7 @@ static int acpi_cpufreq_target(struct cpufreq_policy *policy,
if (acpi_pstate_strict) {
if (!check_freqs(policy, mask,
policy->freq_table[index].frequency)) {
- pr_debug("acpi_cpufreq_target failed (%d)\n",
- policy->cpu);
+ pr_debug("%s (%d)\n", __func__, policy->cpu);
result = -EAGAIN;
}
}
@@ -484,7 +464,8 @@ static unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
if (policy->cached_target_freq == target_freq)
index = policy->cached_resolved_idx;
else
- index = cpufreq_table_find_index_dl(policy, target_freq);
+ index = cpufreq_table_find_index_dl(policy, target_freq,
+ false);
entry = &policy->freq_table[index];
next_freq = entry->frequency;
@@ -544,15 +525,6 @@ static void free_acpi_perf_data(void)
free_percpu(acpi_perf_data);
}
-static int cpufreq_boost_online(unsigned int cpu)
-{
- /*
- * On the CPU_UP path we simply keep the boost-disable flag
- * in sync with the current global state.
- */
- return boost_set_msr(acpi_cpufreq_driver.boost_enabled);
-}
-
static int cpufreq_boost_down_prep(unsigned int cpu)
{
/*
@@ -573,7 +545,7 @@ static int cpufreq_boost_down_prep(unsigned int cpu)
static int __init acpi_cpufreq_early_init(void)
{
unsigned int i;
- pr_debug("acpi_cpufreq_early_init\n");
+ pr_debug("%s\n", __func__);
acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
if (!acpi_perf_data) {
@@ -627,7 +599,7 @@ static const struct dmi_system_id sw_any_bug_dmi_table[] = {
static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
{
/* Intel Xeon Processor 7100 Series Specification Update
- * http://www.intel.com/Assets/PDF/specupdate/314554.pdf
+ * https://www.intel.com/Assets/PDF/specupdate/314554.pdf
* AL30: A Machine Check Exception (MCE) Occurring during an
* Enhanced Intel SpeedStep Technology Ratio Change May Cause
* Both Processor Cores to Lock Up. */
@@ -643,21 +615,82 @@ static int acpi_cpufreq_blacklist(struct cpuinfo_x86 *c)
}
#endif
+#ifdef CONFIG_ACPI_CPPC_LIB
+/*
+ * get_max_boost_ratio: Computes the max_boost_ratio as the ratio
+ * between the highest_perf and the nominal_perf.
+ *
+ * Returns the max_boost_ratio for @cpu. Returns the CPPC nominal
+ * frequency via @nominal_freq if it is non-NULL pointer.
+ */
+static u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq)
+{
+ struct cppc_perf_caps perf_caps;
+ u64 highest_perf, nominal_perf;
+ int ret;
+
+ if (acpi_pstate_strict)
+ return 0;
+
+ ret = cppc_get_perf_caps(cpu, &perf_caps);
+ if (ret) {
+ pr_debug("CPU%d: Unable to get performance capabilities (%d)\n",
+ cpu, ret);
+ return 0;
+ }
+
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ ret = amd_get_boost_ratio_numerator(cpu, &highest_perf);
+ if (ret) {
+ pr_debug("CPU%d: Unable to get boost ratio numerator (%d)\n",
+ cpu, ret);
+ return 0;
+ }
+ } else {
+ highest_perf = perf_caps.highest_perf;
+ }
+
+ nominal_perf = perf_caps.nominal_perf;
+
+ if (nominal_freq)
+ *nominal_freq = perf_caps.nominal_freq * 1000;
+
+ if (!highest_perf || !nominal_perf) {
+ pr_debug("CPU%d: highest or nominal performance missing\n", cpu);
+ return 0;
+ }
+
+ if (highest_perf < nominal_perf) {
+ pr_debug("CPU%d: nominal performance above highest\n", cpu);
+ return 0;
+ }
+
+ return div_u64(highest_perf << SCHED_CAPACITY_SHIFT, nominal_perf);
+}
+
+#else
+static inline u64 get_max_boost_ratio(unsigned int cpu, u64 *nominal_freq)
+{
+ return 0;
+}
+#endif
+
static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
{
- unsigned int i;
- unsigned int valid_states = 0;
- unsigned int cpu = policy->cpu;
+ struct cpufreq_frequency_table *freq_table;
+ struct acpi_processor_performance *perf;
struct acpi_cpufreq_data *data;
+ unsigned int cpu = policy->cpu;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ u64 max_boost_ratio, nominal_freq = 0;
+ unsigned int valid_states = 0;
unsigned int result = 0;
- struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
- struct acpi_processor_performance *perf;
- struct cpufreq_frequency_table *freq_table;
+ unsigned int i;
#ifdef CONFIG_SMP
static int blacklisted;
#endif
- pr_debug("acpi_cpufreq_cpu_init\n");
+ pr_debug("%s\n", __func__);
#ifdef CONFIG_SMP
if (blacklisted)
@@ -706,7 +739,8 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
}
- if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
+ if (check_amd_hwpstate_cpu(cpu) && boot_cpu_data.x86 < 0x19 &&
+ !acpi_pstate_strict) {
cpumask_clear(policy->cpus);
cpumask_set_cpu(cpu, policy->cpus);
cpumask_copy(data->freqdomain_cpus,
@@ -799,6 +833,32 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
valid_states++;
}
freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
+
+ max_boost_ratio = get_max_boost_ratio(cpu, &nominal_freq);
+ if (max_boost_ratio) {
+ unsigned int freq = nominal_freq;
+
+ /*
+ * The loop above sorts the freq_table entries in the
+ * descending order. If ACPI CPPC has not advertised
+ * the nominal frequency (this is possible in CPPC
+ * revisions prior to 3), then use the first entry in
+ * the pstate table as a proxy for nominal frequency.
+ */
+ if (!freq)
+ freq = freq_table[0].frequency;
+
+ policy->cpuinfo.max_freq = freq * max_boost_ratio >> SCHED_CAPACITY_SHIFT;
+ } else {
+ /*
+ * If the maximum "boost" frequency is unknown, ask the arch
+ * scale-invariance code to use the "nominal" performance for
+ * CPU utilization scaling so as to prevent the schedutil
+ * governor from selecting inadequate CPU frequencies.
+ */
+ arch_set_max_freq_ratio(true);
+ }
+
policy->freq_table = freq_table;
perf->state = 0;
@@ -839,6 +899,23 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
policy->fast_switch_possible = !acpi_pstate_strict &&
!(policy_is_shared(policy) && policy->shared_type != CPUFREQ_SHARED_TYPE_ANY);
+ if (perf->states[0].core_frequency * 1000 != freq_table[0].frequency)
+ pr_warn(FW_WARN "P-state 0 is not max freq\n");
+
+ if (acpi_cpufreq_driver.set_boost) {
+ if (policy->boost_supported) {
+ /*
+ * The firmware may have altered boost state while the
+ * CPU was offline (for example during a suspend-resume
+ * cycle).
+ */
+ if (policy->boost_enabled != boost_state(cpu))
+ set_boost(policy, policy->boost_enabled);
+ } else {
+ policy->boost_supported = true;
+ }
+ }
+
return result;
err_unreg:
@@ -852,36 +929,26 @@ err_free:
return result;
}
-static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
+static void acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
struct acpi_cpufreq_data *data = policy->driver_data;
- pr_debug("acpi_cpufreq_cpu_exit\n");
+ pr_debug("%s\n", __func__);
+ cpufreq_boost_down_prep(policy->cpu);
policy->fast_switch_possible = false;
policy->driver_data = NULL;
acpi_processor_unregister_performance(data->acpi_perf_cpu);
free_cpumask_var(data->freqdomain_cpus);
kfree(policy->freq_table);
kfree(data);
-
- return 0;
-}
-
-static void acpi_cpufreq_cpu_ready(struct cpufreq_policy *policy)
-{
- struct acpi_processor_performance *perf = per_cpu_ptr(acpi_perf_data,
- policy->cpu);
-
- if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
- pr_warn(FW_WARN "P-state 0 is not max freq\n");
}
static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
{
struct acpi_cpufreq_data *data = policy->driver_data;
- pr_debug("acpi_cpufreq_resume\n");
+ pr_debug("%s\n", __func__);
data->resume = 1;
@@ -889,7 +956,6 @@ static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
}
static struct freq_attr *acpi_cpufreq_attr[] = {
- &cpufreq_freq_attr_scaling_available_freqs,
&freqdomain_cpus,
#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
&cpb,
@@ -904,44 +970,23 @@ static struct cpufreq_driver acpi_cpufreq_driver = {
.bios_limit = acpi_processor_get_bios_limit,
.init = acpi_cpufreq_cpu_init,
.exit = acpi_cpufreq_cpu_exit,
- .ready = acpi_cpufreq_cpu_ready,
.resume = acpi_cpufreq_resume,
.name = "acpi-cpufreq",
.attr = acpi_cpufreq_attr,
};
-static enum cpuhp_state acpi_cpufreq_online;
-
static void __init acpi_cpufreq_boost_init(void)
{
- int ret;
-
- if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)))
+ if (!(boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA))) {
+ pr_debug("Boost capabilities not present in the processor\n");
return;
+ }
acpi_cpufreq_driver.set_boost = set_boost;
acpi_cpufreq_driver.boost_enabled = boost_state(0);
-
- /*
- * This calls the online callback on all online cpu and forces all
- * MSRs to the same value.
- */
- ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpufreq/acpi:online",
- cpufreq_boost_online, cpufreq_boost_down_prep);
- if (ret < 0) {
- pr_err("acpi_cpufreq: failed to register hotplug callbacks\n");
- return;
- }
- acpi_cpufreq_online = ret;
-}
-
-static void acpi_cpufreq_boost_exit(void)
-{
- if (acpi_cpufreq_online > 0)
- cpuhp_remove_state_nocalls(acpi_cpufreq_online);
}
-static int __init acpi_cpufreq_init(void)
+static int __init acpi_cpufreq_probe(struct platform_device *pdev)
{
int ret;
@@ -950,9 +995,9 @@ static int __init acpi_cpufreq_init(void)
/* don't keep reloading if cpufreq_driver exists */
if (cpufreq_get_current_driver())
- return -EEXIST;
+ return -ENODEV;
- pr_debug("acpi_cpufreq_init\n");
+ pr_debug("%s\n", __func__);
ret = acpi_cpufreq_early_init();
if (ret)
@@ -982,22 +1027,36 @@ static int __init acpi_cpufreq_init(void)
ret = cpufreq_register_driver(&acpi_cpufreq_driver);
if (ret) {
free_acpi_perf_data();
- acpi_cpufreq_boost_exit();
}
return ret;
}
-static void __exit acpi_cpufreq_exit(void)
+static void acpi_cpufreq_remove(struct platform_device *pdev)
{
- pr_debug("acpi_cpufreq_exit\n");
-
- acpi_cpufreq_boost_exit();
+ pr_debug("%s\n", __func__);
cpufreq_unregister_driver(&acpi_cpufreq_driver);
free_acpi_perf_data();
}
+static struct platform_driver acpi_cpufreq_platdrv = {
+ .driver = {
+ .name = "acpi-cpufreq",
+ },
+ .remove = acpi_cpufreq_remove,
+};
+
+static int __init acpi_cpufreq_init(void)
+{
+ return platform_driver_probe(&acpi_cpufreq_platdrv, acpi_cpufreq_probe);
+}
+
+static void __exit acpi_cpufreq_exit(void)
+{
+ platform_driver_unregister(&acpi_cpufreq_platdrv);
+}
+
module_param(acpi_pstate_strict, uint, 0644);
MODULE_PARM_DESC(acpi_pstate_strict,
"value 0 or non-zero. non-zero -> strict ACPI checks are "
@@ -1006,18 +1065,4 @@ MODULE_PARM_DESC(acpi_pstate_strict,
late_initcall(acpi_cpufreq_init);
module_exit(acpi_cpufreq_exit);
-static const struct x86_cpu_id acpi_cpufreq_ids[] = {
- X86_FEATURE_MATCH(X86_FEATURE_ACPI),
- X86_FEATURE_MATCH(X86_FEATURE_HW_PSTATE),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, acpi_cpufreq_ids);
-
-static const struct acpi_device_id processor_device_ids[] = {
- {ACPI_PROCESSOR_OBJECT_HID, },
- {ACPI_PROCESSOR_DEVICE_HID, },
- {},
-};
-MODULE_DEVICE_TABLE(acpi, processor_device_ids);
-
-MODULE_ALIAS("acpi");
+MODULE_ALIAS("platform:acpi-cpufreq");
generated by cgit (git 2.34.1) at 2025-12-24 22:34:34 +0000