/*
- * acpi-cpufreq.c - ACPI Processor P-States Driver ($Revision: 1.4 $)
+ * acpi-cpufreq.c - ACPI Processor P-States Driver
*
* Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com>
* Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>
+#include <linux/slab.h>
+#include <trace/events/power.h>
#include <linux/acpi.h>
+#include <linux/io.h>
+#include <linux/delay.h>
+#include <linux/uaccess.h>
+
#include <acpi/processor.h>
-#include <asm/io.h>
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
-#include <asm/delay.h>
-#include <asm/uaccess.h>
-#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "acpi-cpufreq", msg)
+#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
+ "acpi-cpufreq", msg)
MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
};
#define INTEL_MSR_RANGE (0xffff)
-#define CPUID_6_ECX_APERFMPERF_CAPABILITY (0x1)
struct acpi_cpufreq_data {
struct acpi_processor_performance *acpi_data;
struct cpufreq_frequency_table *freq_table;
- unsigned int max_freq;
unsigned int resume;
unsigned int cpu_feature;
};
-static DEFINE_PER_CPU(struct acpi_cpufreq_data *, drv_data);
+static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
+
+static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance *acpi_perf_data;
{
struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
- if (cpu->x86_vendor != X86_VENDOR_INTEL ||
- !cpu_has(cpu, X86_FEATURE_EST))
- return 0;
-
- return 1;
+ return cpu_has(cpu, X86_FEATURE_EST);
}
static unsigned extract_io(u32 value, struct acpi_cpufreq_data *data)
perf = data->acpi_data;
- for (i=0; i<perf->state_count; i++) {
+ for (i = 0; i < perf->state_count; i++) {
if (value == perf->states[i].status)
return data->freq_table[i].frequency;
}
msr &= INTEL_MSR_RANGE;
perf = data->acpi_data;
- for (i=0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
+ for (i = 0; data->freq_table[i].frequency != CPUFREQ_TABLE_END; i++) {
if (msr == perf->states[data->freq_table[i].index].status)
return data->freq_table[i].frequency;
}
u8 bit_width;
};
-typedef union {
- struct msr_addr msr;
- struct io_addr io;
-} drv_addr_union;
-
struct drv_cmd {
unsigned int type;
- cpumask_t mask;
- drv_addr_union addr;
+ const struct cpumask *mask;
+ union {
+ struct msr_addr msr;
+ struct io_addr io;
+ } addr;
u32 val;
};
-static void do_drv_read(struct drv_cmd *cmd)
+/* Called via smp_call_function_single(), on the target CPU */
+static void do_drv_read(void *_cmd)
{
+ struct drv_cmd *cmd = _cmd;
u32 h;
switch (cmd->type) {
}
}
-static void do_drv_write(struct drv_cmd *cmd)
+/* Called via smp_call_function_many(), on the target CPUs */
+static void do_drv_write(void *_cmd)
{
+ struct drv_cmd *cmd = _cmd;
u32 lo, hi;
switch (cmd->type) {
static void drv_read(struct drv_cmd *cmd)
{
- cpumask_t saved_mask = current->cpus_allowed;
+ int err;
cmd->val = 0;
- set_cpus_allowed_ptr(current, &cmd->mask);
- do_drv_read(cmd);
- set_cpus_allowed_ptr(current, &saved_mask);
+ err = smp_call_function_any(cmd->mask, do_drv_read, cmd, 1);
+ WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */
}
static void drv_write(struct drv_cmd *cmd)
{
- cpumask_t saved_mask = current->cpus_allowed;
- unsigned int i;
+ int this_cpu;
- for_each_cpu_mask(i, cmd->mask) {
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(i));
+ this_cpu = get_cpu();
+ if (cpumask_test_cpu(this_cpu, cmd->mask))
do_drv_write(cmd);
- }
-
- set_cpus_allowed_ptr(current, &saved_mask);
- return;
+ smp_call_function_many(cmd->mask, do_drv_write, cmd, 1);
+ put_cpu();
}
-static u32 get_cur_val(const cpumask_t *mask)
+static u32 get_cur_val(const struct cpumask *mask)
{
struct acpi_processor_performance *perf;
struct drv_cmd cmd;
- if (unlikely(cpus_empty(*mask)))
+ if (unlikely(cpumask_empty(mask)))
return 0;
- switch (per_cpu(drv_data, first_cpu(*mask))->cpu_feature) {
+ switch (per_cpu(acfreq_data, cpumask_first(mask))->cpu_feature) {
case SYSTEM_INTEL_MSR_CAPABLE:
cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
cmd.addr.msr.reg = MSR_IA32_PERF_STATUS;
break;
case SYSTEM_IO_CAPABLE:
cmd.type = SYSTEM_IO_CAPABLE;
- perf = per_cpu(drv_data, first_cpu(*mask))->acpi_data;
+ perf = per_cpu(acfreq_data, cpumask_first(mask))->acpi_data;
cmd.addr.io.port = perf->control_register.address;
cmd.addr.io.bit_width = perf->control_register.bit_width;
break;
return 0;
}
- cmd.mask = *mask;
-
+ cmd.mask = mask;
drv_read(&cmd);
dprintk("get_cur_val = %u\n", cmd.val);
return cmd.val;
}
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
+{
+ struct aperfmperf *am = _cur;
+
+ get_aperfmperf(am);
+}
+
/*
* Return the measured active (C0) frequency on this CPU since last call
* to this function.
* Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
* no meaning should be associated with absolute values of these MSRs.
*/
-static unsigned int get_measured_perf(unsigned int cpu)
+static unsigned int get_measured_perf(struct cpufreq_policy *policy,
+ unsigned int cpu)
{
- union {
- struct {
- u32 lo;
- u32 hi;
- } split;
- u64 whole;
- } aperf_cur, mperf_cur;
-
- cpumask_t saved_mask;
- unsigned int perf_percent;
+ struct aperfmperf perf;
+ unsigned long ratio;
unsigned int retval;
- saved_mask = current->cpus_allowed;
- set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
- if (get_cpu() != cpu) {
- /* We were not able to run on requested processor */
- put_cpu();
+ if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
return 0;
- }
-
- rdmsr(MSR_IA32_APERF, aperf_cur.split.lo, aperf_cur.split.hi);
- rdmsr(MSR_IA32_MPERF, mperf_cur.split.lo, mperf_cur.split.hi);
-
- wrmsr(MSR_IA32_APERF, 0,0);
- wrmsr(MSR_IA32_MPERF, 0,0);
-#ifdef __i386__
- /*
- * We dont want to do 64 bit divide with 32 bit kernel
- * Get an approximate value. Return failure in case we cannot get
- * an approximate value.
- */
- if (unlikely(aperf_cur.split.hi || mperf_cur.split.hi)) {
- int shift_count;
- u32 h;
-
- h = max_t(u32, aperf_cur.split.hi, mperf_cur.split.hi);
- shift_count = fls(h);
-
- aperf_cur.whole >>= shift_count;
- mperf_cur.whole >>= shift_count;
- }
+ ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
+ per_cpu(acfreq_old_perf, cpu) = perf;
- if (((unsigned long)(-1) / 100) < aperf_cur.split.lo) {
- int shift_count = 7;
- aperf_cur.split.lo >>= shift_count;
- mperf_cur.split.lo >>= shift_count;
- }
-
- if (aperf_cur.split.lo && mperf_cur.split.lo)
- perf_percent = (aperf_cur.split.lo * 100) / mperf_cur.split.lo;
- else
- perf_percent = 0;
-
-#else
- if (unlikely(((unsigned long)(-1) / 100) < aperf_cur.whole)) {
- int shift_count = 7;
- aperf_cur.whole >>= shift_count;
- mperf_cur.whole >>= shift_count;
- }
+ retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
- if (aperf_cur.whole && mperf_cur.whole)
- perf_percent = (aperf_cur.whole * 100) / mperf_cur.whole;
- else
- perf_percent = 0;
-
-#endif
-
- retval = per_cpu(drv_data, cpu)->max_freq * perf_percent / 100;
-
- put_cpu();
- set_cpus_allowed_ptr(current, &saved_mask);
-
- dprintk("cpu %d: performance percent %d\n", cpu, perf_percent);
return retval;
}
static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
unsigned int freq;
unsigned int cached_freq;
}
cached_freq = data->freq_table[data->acpi_data->state].frequency;
- freq = extract_freq(get_cur_val(&cpumask_of_cpu(cpu)), data);
+ freq = extract_freq(get_cur_val(cpumask_of(cpu)), data);
if (freq != cached_freq) {
/*
* The dreaded BIOS frequency change behind our back.
return freq;
}
-static unsigned int check_freqs(const cpumask_t *mask, unsigned int freq,
+static unsigned int check_freqs(const struct cpumask *mask, unsigned int freq,
struct acpi_cpufreq_data *data)
{
unsigned int cur_freq;
unsigned int i;
- for (i=0; i<100; i++) {
+ for (i = 0; i < 100; i++) {
cur_freq = extract_freq(get_cur_val(mask), data);
if (cur_freq == freq)
return 1;
static int acpi_cpufreq_target(struct cpufreq_policy *policy,
unsigned int target_freq, unsigned int relation)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
struct acpi_processor_performance *perf;
struct cpufreq_freqs freqs;
- cpumask_t online_policy_cpus;
struct drv_cmd cmd;
unsigned int next_state = 0; /* Index into freq_table */
unsigned int next_perf_state = 0; /* Index into perf table */
data->freq_table,
target_freq,
relation, &next_state);
- if (unlikely(result))
- return -ENODEV;
-
-#ifdef CONFIG_HOTPLUG_CPU
- /* cpufreq holds the hotplug lock, so we are safe from here on */
- cpus_and(online_policy_cpus, cpu_online_map, policy->cpus);
-#else
- online_policy_cpus = policy->cpus;
-#endif
+ if (unlikely(result)) {
+ result = -ENODEV;
+ goto out;
+ }
next_perf_state = data->freq_table[next_state].index;
if (perf->state == next_perf_state) {
} else {
dprintk("Already at target state (P%d)\n",
next_perf_state);
- return 0;
+ goto out;
}
}
+ trace_power_frequency(POWER_PSTATE, data->freq_table[next_state].frequency);
+
switch (data->cpu_feature) {
case SYSTEM_INTEL_MSR_CAPABLE:
cmd.type = SYSTEM_INTEL_MSR_CAPABLE;
cmd.val = (u32) perf->states[next_perf_state].control;
break;
default:
- return -ENODEV;
+ result = -ENODEV;
+ goto out;
}
- cpus_clear(cmd.mask);
-
+ /* cpufreq holds the hotplug lock, so we are safe from here on */
if (policy->shared_type != CPUFREQ_SHARED_TYPE_ANY)
- cmd.mask = online_policy_cpus;
+ cmd.mask = policy->cpus;
else
- cpu_set(policy->cpu, cmd.mask);
+ cmd.mask = cpumask_of(policy->cpu);
freqs.old = perf->states[perf->state].core_frequency * 1000;
freqs.new = data->freq_table[next_state].frequency;
- for_each_cpu_mask(i, cmd.mask) {
+ for_each_cpu(i, cmd.mask) {
freqs.cpu = i;
cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
}
drv_write(&cmd);
if (acpi_pstate_strict) {
- if (!check_freqs(&cmd.mask, freqs.new, data)) {
+ if (!check_freqs(cmd.mask, freqs.new, data)) {
dprintk("acpi_cpufreq_target failed (%d)\n",
policy->cpu);
- return -EAGAIN;
+ result = -EAGAIN;
+ goto out;
}
}
- for_each_cpu_mask(i, cmd.mask) {
+ for_each_cpu(i, cmd.mask) {
freqs.cpu = i;
cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
}
perf->state = next_perf_state;
+out:
return result;
}
static int acpi_cpufreq_verify(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
dprintk("acpi_cpufreq_verify\n");
unsigned long freq;
unsigned long freqn = perf->states[0].core_frequency * 1000;
- for (i=0; i<(perf->state_count-1); i++) {
+ for (i = 0; i < (perf->state_count-1); i++) {
freq = freqn;
freqn = perf->states[i+1].core_frequency * 1000;
if ((2 * cpu_khz) > (freqn + freq)) {
}
}
+static void free_acpi_perf_data(void)
+{
+ unsigned int i;
+
+ /* Freeing a NULL pointer is OK, and alloc_percpu zeroes. */
+ for_each_possible_cpu(i)
+ free_cpumask_var(per_cpu_ptr(acpi_perf_data, i)
+ ->shared_cpu_map);
+ free_percpu(acpi_perf_data);
+}
+
/*
* acpi_cpufreq_early_init - initialize ACPI P-States library
*
*/
static int __init acpi_cpufreq_early_init(void)
{
+ unsigned int i;
dprintk("acpi_cpufreq_early_init\n");
acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
dprintk("Memory allocation error for acpi_perf_data.\n");
return -ENOMEM;
}
+ for_each_possible_cpu(i) {
+ if (!zalloc_cpumask_var_node(
+ &per_cpu_ptr(acpi_perf_data, i)->shared_cpu_map,
+ GFP_KERNEL, cpu_to_node(i))) {
+
+ /* Freeing a NULL pointer is OK: alloc_percpu zeroes. */
+ free_acpi_perf_data();
+ return -ENOMEM;
+ }
+ }
/* Do initialization in ACPI core */
acpi_processor_preregister_performance(acpi_perf_data);
},
{ }
};
+
+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
+ * AL30: A Machine Check Exception (MCE) Occurring during an
+ * Enhanced Intel SpeedStep Technology Ratio Change May Cause
+ * Both Processor Cores to Lock Up. */
+ if (c->x86_vendor == X86_VENDOR_INTEL) {
+ if ((c->x86 == 15) &&
+ (c->x86_model == 6) &&
+ (c->x86_mask == 8)) {
+ printk(KERN_INFO "acpi-cpufreq: Intel(R) "
+ "Xeon(R) 7100 Errata AL30, processors may "
+ "lock up on frequency changes: disabling "
+ "acpi-cpufreq.\n");
+ return -ENODEV;
+ }
+ }
+ return 0;
+}
#endif
static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
unsigned int result = 0;
struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
struct acpi_processor_performance *perf;
+#ifdef CONFIG_SMP
+ static int blacklisted;
+#endif
dprintk("acpi_cpufreq_cpu_init\n");
+#ifdef CONFIG_SMP
+ if (blacklisted)
+ return blacklisted;
+ blacklisted = acpi_cpufreq_blacklist(c);
+ if (blacklisted)
+ return blacklisted;
+#endif
+
data = kzalloc(sizeof(struct acpi_cpufreq_data), GFP_KERNEL);
if (!data)
return -ENOMEM;
- data->acpi_data = percpu_ptr(acpi_perf_data, cpu);
- per_cpu(drv_data, cpu) = data;
+ data->acpi_data = per_cpu_ptr(acpi_perf_data, cpu);
+ per_cpu(acfreq_data, cpu) = data;
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
*/
if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
- policy->cpus = perf->shared_cpu_map;
+ cpumask_copy(policy->cpus, perf->shared_cpu_map);
}
+ cpumask_copy(policy->related_cpus, perf->shared_cpu_map);
#ifdef CONFIG_SMP
dmi_check_system(sw_any_bug_dmi_table);
- if (bios_with_sw_any_bug && cpus_weight(policy->cpus) == 1) {
+ if (bios_with_sw_any_bug && cpumask_weight(policy->cpus) == 1) {
policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
- policy->cpus = per_cpu(cpu_core_map, cpu);
+ cpumask_copy(policy->cpus, cpu_core_mask(cpu));
}
#endif
/* detect transition latency */
policy->cpuinfo.transition_latency = 0;
- for (i=0; i<perf->state_count; i++) {
+ for (i = 0; i < perf->state_count; i++) {
if ((perf->states[i].transition_latency * 1000) >
policy->cpuinfo.transition_latency)
policy->cpuinfo.transition_latency =
perf->states[i].transition_latency * 1000;
}
- data->max_freq = perf->states[0].core_frequency * 1000;
+ /* Check for high latency (>20uS) from buggy BIOSes, like on T42 */
+ if (perf->control_register.space_id == ACPI_ADR_SPACE_FIXED_HARDWARE &&
+ policy->cpuinfo.transition_latency > 20 * 1000) {
+ policy->cpuinfo.transition_latency = 20 * 1000;
+ printk_once(KERN_INFO
+ "P-state transition latency capped at 20 uS\n");
+ }
+
/* table init */
- for (i=0; i<perf->state_count; i++) {
- if (i>0 && perf->states[i].core_frequency >=
+ for (i = 0; i < perf->state_count; i++) {
+ if (i > 0 && perf->states[i].core_frequency >=
data->freq_table[valid_states-1].frequency / 1000)
continue;
if (result)
goto err_freqfree;
+ if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
+ printk(KERN_WARNING FW_WARN "P-state 0 is not max freq\n");
+
switch (perf->control_register.space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
/* Current speed is unknown and not detectable by IO port */
acpi_processor_notify_smm(THIS_MODULE);
/* Check for APERF/MPERF support in hardware */
- if (c->x86_vendor == X86_VENDOR_INTEL && c->cpuid_level >= 6) {
- unsigned int ecx;
- ecx = cpuid_ecx(6);
- if (ecx & CPUID_6_ECX_APERFMPERF_CAPABILITY)
- acpi_cpufreq_driver.getavg = get_measured_perf;
- }
+ if (cpu_has(c, X86_FEATURE_APERFMPERF))
+ acpi_cpufreq_driver.getavg = get_measured_perf;
dprintk("CPU%u - ACPI performance management activated.\n", cpu);
for (i = 0; i < perf->state_count; i++)
acpi_processor_unregister_performance(perf, cpu);
err_free:
kfree(data);
- per_cpu(drv_data, cpu) = NULL;
+ per_cpu(acfreq_data, cpu) = NULL;
return result;
}
static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
dprintk("acpi_cpufreq_cpu_exit\n");
if (data) {
cpufreq_frequency_table_put_attr(policy->cpu);
- per_cpu(drv_data, policy->cpu) = NULL;
+ per_cpu(acfreq_data, policy->cpu) = NULL;
acpi_processor_unregister_performance(data->acpi_data,
policy->cpu);
kfree(data);
static int acpi_cpufreq_resume(struct cpufreq_policy *policy)
{
- struct acpi_cpufreq_data *data = per_cpu(drv_data, policy->cpu);
+ struct acpi_cpufreq_data *data = per_cpu(acfreq_data, policy->cpu);
dprintk("acpi_cpufreq_resume\n");
};
static struct cpufreq_driver acpi_cpufreq_driver = {
- .verify = acpi_cpufreq_verify,
- .target = acpi_cpufreq_target,
- .init = acpi_cpufreq_cpu_init,
- .exit = acpi_cpufreq_cpu_exit,
- .resume = acpi_cpufreq_resume,
- .name = "acpi-cpufreq",
- .owner = THIS_MODULE,
- .attr = acpi_cpufreq_attr,
+ .verify = acpi_cpufreq_verify,
+ .target = acpi_cpufreq_target,
+ .bios_limit = acpi_processor_get_bios_limit,
+ .init = acpi_cpufreq_cpu_init,
+ .exit = acpi_cpufreq_cpu_exit,
+ .resume = acpi_cpufreq_resume,
+ .name = "acpi-cpufreq",
+ .owner = THIS_MODULE,
+ .attr = acpi_cpufreq_attr,
};
static int __init acpi_cpufreq_init(void)
{
int ret;
+ if (acpi_disabled)
+ return 0;
+
dprintk("acpi_cpufreq_init\n");
ret = acpi_cpufreq_early_init();
if (ret)
return ret;
- return cpufreq_register_driver(&acpi_cpufreq_driver);
+ ret = cpufreq_register_driver(&acpi_cpufreq_driver);
+ if (ret)
+ free_acpi_perf_data();
+
+ return ret;
}
static void __exit acpi_cpufreq_exit(void)
cpufreq_unregister_driver(&acpi_cpufreq_driver);
free_percpu(acpi_perf_data);
-
- return;
}
module_param(acpi_pstate_strict, uint, 0644);
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff