linux/drivers/cpufreq/acpi-cpufreq.c

1041 lines
25 KiB
C
Raw Normal View History

/*
* 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>
* 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
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/smp.h>
#include <linux/sched.h>
#include <linux/cpufreq.h>
#include <linux/compiler.h>
#include <linux/dmi.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include <linux/acpi.h>
#include <linux/io.h>
#include <linux/delay.h>
#include <linux/uaccess.h>
#include <acpi/processor.h>
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
MODULE_AUTHOR("Paul Diefenbaugh, Dominik Brodowski");
MODULE_DESCRIPTION("ACPI Processor P-States Driver");
MODULE_LICENSE("GPL");
enum {
UNDEFINED_CAPABLE = 0,
SYSTEM_INTEL_MSR_CAPABLE,
SYSTEM_AMD_MSR_CAPABLE,
SYSTEM_IO_CAPABLE,
};
#define INTEL_MSR_RANGE (0xffff)
#define AMD_MSR_RANGE (0x7)
#define MSR_K7_HWCR_CPB_DIS (1ULL << 25)
struct acpi_cpufreq_data {
unsigned int resume;
unsigned int cpu_feature;
unsigned int acpi_perf_cpu;
cpumask_var_t freqdomain_cpus;
void (*cpu_freq_write)(struct acpi_pct_register *reg, u32 val);
u32 (*cpu_freq_read)(struct acpi_pct_register *reg);
};
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance __percpu *acpi_perf_data;
static inline struct acpi_processor_performance *to_perf_data(struct acpi_cpufreq_data *data)
{
return per_cpu_ptr(acpi_perf_data, data->acpi_perf_cpu);
}
static struct cpufreq_driver acpi_cpufreq_driver;
static unsigned int acpi_pstate_strict;
static struct msr __percpu *msrs;
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);
return !(msr & MSR_IA32_MISC_ENABLE_TURBO_DISABLE);
case X86_VENDOR_AMD:
rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
msr = lo | ((u64)hi << 32);
return !(msr & MSR_K7_HWCR_CPB_DIS);
}
return false;
}
static void boost_set_msrs(bool enable, const struct cpumask *cpumask)
{
u32 cpu;
u32 msr_addr;
u64 msr_mask;
switch (boot_cpu_data.x86_vendor) {
case X86_VENDOR_INTEL:
msr_addr = MSR_IA32_MISC_ENABLE;
msr_mask = MSR_IA32_MISC_ENABLE_TURBO_DISABLE;
break;
case X86_VENDOR_AMD:
msr_addr = MSR_K7_HWCR;
msr_mask = MSR_K7_HWCR_CPB_DIS;
break;
default:
return;
}
rdmsr_on_cpus(cpumask, msr_addr, msrs);
for_each_cpu(cpu, cpumask) {
struct msr *reg = per_cpu_ptr(msrs, cpu);
if (enable)
reg->q &= ~msr_mask;
else
reg->q |= msr_mask;
}
wrmsr_on_cpus(cpumask, msr_addr, msrs);
}
static int set_boost(int val)
{
get_online_cpus();
boost_set_msrs(val, cpu_online_mask);
put_online_cpus();
pr_debug("Core Boosting %sabled.\n", val ? "en" : "dis");
return 0;
}
static ssize_t show_freqdomain_cpus(struct cpufreq_policy *policy, char *buf)
{
struct acpi_cpufreq_data *data = policy->driver_data;
cpufreq: acpi_cpufreq: prevent crash on reading freqdomain_cpus When freqdomain_cpus attribute is read from an offlined cpu, it will cause crash. This change prevents calling cpufreq_show_cpus when policy driver_data is NULL. Crash info: [ 170.814949] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 [ 170.814990] IP: [<ffffffff813b2490>] _find_next_bit.part.0+0x10/0x70 [ 170.815021] PGD 227d30067 PUD 229e56067 PMD 0 [ 170.815043] Oops: 0000 [#2] SMP [ 170.816022] CPU: 3 PID: 3121 Comm: cat Tainted: G D OE 4.3.0-rc3+ #33 ... ... [ 170.816657] Call Trace: [ 170.816672] [<ffffffff813b2505>] ? find_next_bit+0x15/0x20 [ 170.816696] [<ffffffff8160e47c>] cpufreq_show_cpus+0x5c/0xd0 [ 170.816722] [<ffffffffa031a409>] show_freqdomain_cpus+0x19/0x20 [acpi_cpufreq] [ 170.816749] [<ffffffff8160e65b>] show+0x3b/0x60 [ 170.816769] [<ffffffff8129b31c>] sysfs_kf_seq_show+0xbc/0x130 [ 170.816793] [<ffffffff81299be3>] kernfs_seq_show+0x23/0x30 [ 170.816816] [<ffffffff81240f2c>] seq_read+0xec/0x390 [ 170.816837] [<ffffffff8129a64a>] kernfs_fop_read+0x10a/0x160 [ 170.816861] [<ffffffff8121d9b7>] __vfs_read+0x37/0x100 [ 170.816883] [<ffffffff813217c0>] ? security_file_permission+0xa0/0xc0 [ 170.816909] [<ffffffff8121e2e3>] vfs_read+0x83/0x130 [ 170.816930] [<ffffffff8121f035>] SyS_read+0x55/0xc0 ... ... [ 170.817185] ---[ end trace bc6eadf82b2b965a ]--- Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com> Acked-by: Viresh Kumar <viresh.kumar@linaro.org> Cc: 4.2+ <stable@vger.kernel.org> # 4.2+ Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
2015-10-07 20:50:43 +00:00
if (unlikely(!data))
return -ENODEV;
return cpufreq_show_cpus(data->freqdomain_cpus, buf);
}
cpufreq_freq_attr_ro(freqdomain_cpus);
#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
size_t count)
{
int ret;
unsigned int val = 0;
if (!acpi_cpufreq_driver.set_boost)
return -EINVAL;
ret = kstrtouint(buf, 10, &val);
if (ret || val > 1)
return -EINVAL;
set_boost(val);
return count;
}
static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
{
return sprintf(buf, "%u\n", acpi_cpufreq_driver.boost_enabled);
}
cpufreq_freq_attr_rw(cpb);
#endif
static int check_est_cpu(unsigned int cpuid)
{
struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
return cpu_has(cpu, X86_FEATURE_EST);
}
static int check_amd_hwpstate_cpu(unsigned int cpuid)
{
struct cpuinfo_x86 *cpu = &cpu_data(cpuid);
return cpu_has(cpu, X86_FEATURE_HW_PSTATE);
}
static unsigned extract_io(struct cpufreq_policy *policy, u32 value)
{
struct acpi_cpufreq_data *data = policy->driver_data;
struct acpi_processor_performance *perf;
int i;
perf = to_perf_data(data);
for (i = 0; i < perf->state_count; i++) {
if (value == perf->states[i].status)
return policy->freq_table[i].frequency;
}
return 0;
}
static unsigned extract_msr(struct cpufreq_policy *policy, u32 msr)
{
struct acpi_cpufreq_data *data = policy->driver_data;
struct cpufreq_frequency_table *pos;
struct acpi_processor_performance *perf;
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD)
msr &= AMD_MSR_RANGE;
else
msr &= INTEL_MSR_RANGE;
perf = to_perf_data(data);
cpufreq_for_each_entry(pos, policy->freq_table)
if (msr == perf->states[pos->driver_data].status)
return pos->frequency;
return policy->freq_table[0].frequency;
}
static unsigned extract_freq(struct cpufreq_policy *policy, u32 val)
{
struct acpi_cpufreq_data *data = policy->driver_data;
switch (data->cpu_feature) {
case SYSTEM_INTEL_MSR_CAPABLE:
case SYSTEM_AMD_MSR_CAPABLE:
return extract_msr(policy, val);
case SYSTEM_IO_CAPABLE:
return extract_io(policy, val);
default:
return 0;
}
}
static u32 cpu_freq_read_intel(struct acpi_pct_register *not_used)
{
u32 val, dummy;
rdmsr(MSR_IA32_PERF_CTL, val, dummy);
return val;
}
static void cpu_freq_write_intel(struct acpi_pct_register *not_used, u32 val)
{
u32 lo, hi;
rdmsr(MSR_IA32_PERF_CTL, lo, hi);
lo = (lo & ~INTEL_MSR_RANGE) | (val & INTEL_MSR_RANGE);
wrmsr(MSR_IA32_PERF_CTL, lo, hi);
}
static u32 cpu_freq_read_amd(struct acpi_pct_register *not_used)
{
u32 val, dummy;
rdmsr(MSR_AMD_PERF_CTL, val, dummy);
return val;
}
static void cpu_freq_write_amd(struct acpi_pct_register *not_used, u32 val)
{
wrmsr(MSR_AMD_PERF_CTL, val, 0);
}
static u32 cpu_freq_read_io(struct acpi_pct_register *reg)
{
u32 val;
acpi_os_read_port(reg->address, &val, reg->bit_width);
return val;
}
static void cpu_freq_write_io(struct acpi_pct_register *reg, u32 val)
{
acpi_os_write_port(reg->address, val, reg->bit_width);
}
struct drv_cmd {
struct acpi_pct_register *reg;
u32 val;
union {
void (*write)(struct acpi_pct_register *reg, u32 val);
u32 (*read)(struct acpi_pct_register *reg);
} func;
};
/* Called via smp_call_function_single(), on the target CPU */
static void do_drv_read(void *_cmd)
{
struct drv_cmd *cmd = _cmd;
cmd->val = cmd->func.read(cmd->reg);
}
static u32 drv_read(struct acpi_cpufreq_data *data, const struct cpumask *mask)
{
struct acpi_processor_performance *perf = to_perf_data(data);
struct drv_cmd cmd = {
.reg = &perf->control_register,
.func.read = data->cpu_freq_read,
};
int err;
err = smp_call_function_any(mask, do_drv_read, &cmd, 1);
WARN_ON_ONCE(err); /* smp_call_function_any() was buggy? */
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;
cmd->func.write(cmd->reg, cmd->val);
}
static void drv_write(struct acpi_cpufreq_data *data,
const struct cpumask *mask, u32 val)
{
struct acpi_processor_performance *perf = to_perf_data(data);
struct drv_cmd cmd = {
.reg = &perf->control_register,
.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();
}
static u32 get_cur_val(const struct cpumask *mask, struct acpi_cpufreq_data *data)
{
u32 val;
if (unlikely(cpumask_empty(mask)))
return 0;
val = drv_read(data, mask);
pr_debug("get_cur_val = %u\n", val);
return val;
}
static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
struct acpi_cpufreq_data *data;
struct cpufreq_policy *policy;
unsigned int freq;
unsigned int cached_freq;
pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
policy = cpufreq_cpu_get_raw(cpu);
if (unlikely(!policy))
return 0;
data = policy->driver_data;
if (unlikely(!data || !policy->freq_table))
return 0;
cached_freq = policy->freq_table[to_perf_data(data)->state].frequency;
freq = extract_freq(policy, get_cur_val(cpumask_of(cpu), data));
if (freq != cached_freq) {
/*
* The dreaded BIOS frequency change behind our back.
* Force set the frequency on next target call.
*/
data->resume = 1;
}
pr_debug("cur freq = %u\n", freq);
return freq;
}
static unsigned int check_freqs(struct cpufreq_policy *policy,
const struct cpumask *mask, unsigned int freq)
{
struct acpi_cpufreq_data *data = policy->driver_data;
unsigned int cur_freq;
unsigned int i;
for (i = 0; i < 100; i++) {
cur_freq = extract_freq(policy, get_cur_val(mask, data));
if (cur_freq == freq)
return 1;
udelay(10);
}
return 0;
}
static int acpi_cpufreq_target(struct cpufreq_policy *policy,
cpufreq: Implement light weight ->target_index() routine Currently, the prototype of cpufreq_drivers target routines is: int target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); And most of the drivers call cpufreq_frequency_table_target() to get a valid index of their frequency table which is closest to the target_freq. And they don't use target_freq and relation after that. So, it makes sense to just do this work in cpufreq core before calling cpufreq_frequency_table_target() and simply pass index instead. But this can be done only with drivers which expose their frequency table with cpufreq core. For others we need to stick with the old prototype of target() until those drivers are converted to expose frequency tables. This patch implements the new light weight prototype for target_index() routine. It looks like this: int target_index(struct cpufreq_policy *policy, unsigned int index); CPUFreq core will call cpufreq_frequency_table_target() before calling this routine and pass index to it. Because CPUFreq core now requires to call routines present in freq_table.c CONFIG_CPU_FREQ_TABLE must be enabled all the time. This also marks target() interface as deprecated. So, that new drivers avoid using it. And Documentation is updated accordingly. It also converts existing .target() to newly defined light weight .target_index() routine for many driver. Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King <linux@arm.linux.org.uk> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rjw@rjwysocki.net>
2013-10-25 14:15:48 +00:00
unsigned int index)
{
struct acpi_cpufreq_data *data = policy->driver_data;
struct acpi_processor_performance *perf;
const struct cpumask *mask;
unsigned int next_perf_state = 0; /* Index into perf table */
int result = 0;
if (unlikely(!data)) {
return -ENODEV;
}
perf = to_perf_data(data);
next_perf_state = policy->freq_table[index].driver_data;
if (perf->state == next_perf_state) {
if (unlikely(data->resume)) {
pr_debug("Called after resume, resetting to P%d\n",
next_perf_state);
data->resume = 0;
} else {
pr_debug("Already at target state (P%d)\n",
next_perf_state);
return 0;
}
}
/*
* The core won't allow CPUs to go away until the governor has been
* stopped, so we can rely on the stability of policy->cpus.
*/
mask = policy->shared_type == CPUFREQ_SHARED_TYPE_ANY ?
cpumask_of(policy->cpu) : policy->cpus;
drv_write(data, mask, perf->states[next_perf_state].control);
if (acpi_pstate_strict) {
if (!check_freqs(policy, mask,
policy->freq_table[index].frequency)) {
pr_debug("acpi_cpufreq_target failed (%d)\n",
policy->cpu);
result = -EAGAIN;
}
}
if (!result)
perf->state = next_perf_state;
return result;
}
unsigned int acpi_cpufreq_fast_switch(struct cpufreq_policy *policy,
unsigned int target_freq)
{
struct acpi_cpufreq_data *data = policy->driver_data;
struct acpi_processor_performance *perf;
struct cpufreq_frequency_table *entry;
unsigned int next_perf_state, next_freq, freq;
/*
* Find the closest frequency above target_freq.
*
* The table is sorted in the reverse order with respect to the
* frequency and all of the entries are valid (see the initialization).
*/
entry = policy->freq_table;
do {
entry++;
freq = entry->frequency;
} while (freq >= target_freq && freq != CPUFREQ_TABLE_END);
entry--;
next_freq = entry->frequency;
next_perf_state = entry->driver_data;
perf = to_perf_data(data);
if (perf->state == next_perf_state) {
if (unlikely(data->resume))
data->resume = 0;
else
return next_freq;
}
data->cpu_freq_write(&perf->control_register,
perf->states[next_perf_state].control);
perf->state = next_perf_state;
return next_freq;
}
static unsigned long
acpi_cpufreq_guess_freq(struct acpi_cpufreq_data *data, unsigned int cpu)
{
struct acpi_processor_performance *perf;
perf = to_perf_data(data);
if (cpu_khz) {
/* search the closest match to cpu_khz */
unsigned int i;
unsigned long freq;
unsigned long freqn = perf->states[0].core_frequency * 1000;
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)) {
perf->state = i;
return freq;
}
}
perf->state = perf->state_count-1;
return freqn;
} else {
/* assume CPU is at P0... */
perf->state = 0;
return perf->states[0].core_frequency * 1000;
}
}
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);
}
static int boost_notify(struct notifier_block *nb, unsigned long action,
void *hcpu)
{
unsigned cpu = (long)hcpu;
const struct cpumask *cpumask;
cpumask = get_cpu_mask(cpu);
/*
* Clear the boost-disable bit on the CPU_DOWN path so that
* this cpu cannot block the remaining ones from boosting. On
* the CPU_UP path we simply keep the boost-disable flag in
* sync with the current global state.
*/
switch (action) {
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
boost_set_msrs(acpi_cpufreq_driver.boost_enabled, cpumask);
break;
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
boost_set_msrs(1, cpumask);
break;
default:
break;
}
return NOTIFY_OK;
}
static struct notifier_block boost_nb = {
.notifier_call = boost_notify,
};
/*
* acpi_cpufreq_early_init - initialize ACPI P-States library
*
* Initialize the ACPI P-States library (drivers/acpi/processor_perflib.c)
* in order to determine correct frequency and voltage pairings. We can
* do _PDC and _PSD and find out the processor dependency for the
* actual init that will happen later...
*/
static int __init acpi_cpufreq_early_init(void)
{
unsigned int i;
pr_debug("acpi_cpufreq_early_init\n");
acpi_perf_data = alloc_percpu(struct acpi_processor_performance);
if (!acpi_perf_data) {
pr_debug("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);
return 0;
}
#ifdef CONFIG_SMP
/*
* Some BIOSes do SW_ANY coordination internally, either set it up in hw
* or do it in BIOS firmware and won't inform about it to OS. If not
* detected, this has a side effect of making CPU run at a different speed
* than OS intended it to run at. Detect it and handle it cleanly.
*/
static int bios_with_sw_any_bug;
static int sw_any_bug_found(const struct dmi_system_id *d)
{
bios_with_sw_any_bug = 1;
return 0;
}
static const struct dmi_system_id sw_any_bug_dmi_table[] = {
{
.callback = sw_any_bug_found,
.ident = "Supermicro Server X6DLP",
.matches = {
DMI_MATCH(DMI_SYS_VENDOR, "Supermicro"),
DMI_MATCH(DMI_BIOS_VERSION, "080010"),
DMI_MATCH(DMI_PRODUCT_NAME, "X6DLP"),
},
},
{ }
};
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)) {
pr_info("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 i;
unsigned int valid_states = 0;
unsigned int cpu = policy->cpu;
struct acpi_cpufreq_data *data;
unsigned int result = 0;
struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
struct acpi_processor_performance *perf;
struct cpufreq_frequency_table *freq_table;
#ifdef CONFIG_SMP
static int blacklisted;
#endif
pr_debug("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(*data), GFP_KERNEL);
if (!data)
return -ENOMEM;
if (!zalloc_cpumask_var(&data->freqdomain_cpus, GFP_KERNEL)) {
result = -ENOMEM;
goto err_free;
}
perf = per_cpu_ptr(acpi_perf_data, cpu);
data->acpi_perf_cpu = cpu;
policy->driver_data = data;
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC))
acpi_cpufreq_driver.flags |= CPUFREQ_CONST_LOOPS;
result = acpi_processor_register_performance(perf, cpu);
if (result)
goto err_free_mask;
policy->shared_type = perf->shared_type;
/*
* Will let policy->cpus know about dependency only when software
* coordination is required.
*/
if (policy->shared_type == CPUFREQ_SHARED_TYPE_ALL ||
policy->shared_type == CPUFREQ_SHARED_TYPE_ANY) {
cpumask_copy(policy->cpus, perf->shared_cpu_map);
}
cpumask_copy(data->freqdomain_cpus, perf->shared_cpu_map);
#ifdef CONFIG_SMP
dmi_check_system(sw_any_bug_dmi_table);
if (bios_with_sw_any_bug && !policy_is_shared(policy)) {
policy->shared_type = CPUFREQ_SHARED_TYPE_ALL;
cpumask_copy(policy->cpus, topology_core_cpumask(cpu));
}
if (check_amd_hwpstate_cpu(cpu) && !acpi_pstate_strict) {
cpumask_clear(policy->cpus);
cpumask_set_cpu(cpu, policy->cpus);
cpumask_copy(data->freqdomain_cpus,
topology_sibling_cpumask(cpu));
policy->shared_type = CPUFREQ_SHARED_TYPE_HW;
pr_info_once("overriding BIOS provided _PSD data\n");
}
#endif
/* capability check */
if (perf->state_count <= 1) {
pr_debug("No P-States\n");
result = -ENODEV;
goto err_unreg;
}
if (perf->control_register.space_id != perf->status_register.space_id) {
result = -ENODEV;
goto err_unreg;
}
switch (perf->control_register.space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD &&
boot_cpu_data.x86 == 0xf) {
pr_debug("AMD K8 systems must use native drivers.\n");
result = -ENODEV;
goto err_unreg;
}
pr_debug("SYSTEM IO addr space\n");
data->cpu_feature = SYSTEM_IO_CAPABLE;
data->cpu_freq_read = cpu_freq_read_io;
data->cpu_freq_write = cpu_freq_write_io;
break;
case ACPI_ADR_SPACE_FIXED_HARDWARE:
pr_debug("HARDWARE addr space\n");
if (check_est_cpu(cpu)) {
data->cpu_feature = SYSTEM_INTEL_MSR_CAPABLE;
data->cpu_freq_read = cpu_freq_read_intel;
data->cpu_freq_write = cpu_freq_write_intel;
break;
}
if (check_amd_hwpstate_cpu(cpu)) {
data->cpu_feature = SYSTEM_AMD_MSR_CAPABLE;
data->cpu_freq_read = cpu_freq_read_amd;
data->cpu_freq_write = cpu_freq_write_amd;
break;
}
result = -ENODEV;
goto err_unreg;
default:
pr_debug("Unknown addr space %d\n",
(u32) (perf->control_register.space_id));
result = -ENODEV;
goto err_unreg;
}
freq_table = kzalloc(sizeof(*freq_table) *
(perf->state_count+1), GFP_KERNEL);
if (!freq_table) {
result = -ENOMEM;
goto err_unreg;
}
/* detect transition latency */
policy->cpuinfo.transition_latency = 0;
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;
}
/* 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;
pr_info_once("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 >=
freq_table[valid_states-1].frequency / 1000)
continue;
freq_table[valid_states].driver_data = i;
freq_table[valid_states].frequency =
perf->states[i].core_frequency * 1000;
valid_states++;
}
freq_table[valid_states].frequency = CPUFREQ_TABLE_END;
perf->state = 0;
result = cpufreq_table_validate_and_show(policy, freq_table);
if (result)
goto err_freqfree;
if (perf->states[0].core_frequency * 1000 != policy->cpuinfo.max_freq)
pr_warn(FW_WARN "P-state 0 is not max freq\n");
switch (perf->control_register.space_id) {
case ACPI_ADR_SPACE_SYSTEM_IO:
/*
* The core will not set policy->cur, because
* cpufreq_driver->get is NULL, so we need to set it here.
* However, we have to guess it, because the current speed is
* unknown and not detectable via IO ports.
*/
policy->cur = acpi_cpufreq_guess_freq(data, policy->cpu);
break;
case ACPI_ADR_SPACE_FIXED_HARDWARE:
acpi_cpufreq_driver.get = get_cur_freq_on_cpu;
break;
default:
break;
}
/* notify BIOS that we exist */
acpi_processor_notify_smm(THIS_MODULE);
pr_debug("CPU%u - ACPI performance management activated.\n", cpu);
for (i = 0; i < perf->state_count; i++)
pr_debug(" %cP%d: %d MHz, %d mW, %d uS\n",
(i == perf->state ? '*' : ' '), i,
(u32) perf->states[i].core_frequency,
(u32) perf->states[i].power,
(u32) perf->states[i].transition_latency);
/*
* the first call to ->target() should result in us actually
* writing something to the appropriate registers.
*/
data->resume = 1;
policy->fast_switch_possible = !acpi_pstate_strict &&
!(policy_is_shared(policy) && policy->shared_type != CPUFREQ_SHARED_TYPE_ANY);
return result;
err_freqfree:
kfree(freq_table);
err_unreg:
acpi_processor_unregister_performance(cpu);
err_free_mask:
free_cpumask_var(data->freqdomain_cpus);
err_free:
kfree(data);
policy->driver_data = NULL;
return result;
}
static int acpi_cpufreq_cpu_exit(struct cpufreq_policy *policy)
{
struct acpi_cpufreq_data *data = policy->driver_data;
pr_debug("acpi_cpufreq_cpu_exit\n");
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 int acpi_cpufreq_resume(struct cpufreq_policy *policy)
{
struct acpi_cpufreq_data *data = policy->driver_data;
pr_debug("acpi_cpufreq_resume\n");
data->resume = 1;
return 0;
}
static struct freq_attr *acpi_cpufreq_attr[] = {
&cpufreq_freq_attr_scaling_available_freqs,
&freqdomain_cpus,
#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
&cpb,
#endif
NULL,
};
static struct cpufreq_driver acpi_cpufreq_driver = {
.verify = cpufreq_generic_frequency_table_verify,
cpufreq: Implement light weight ->target_index() routine Currently, the prototype of cpufreq_drivers target routines is: int target(struct cpufreq_policy *policy, unsigned int target_freq, unsigned int relation); And most of the drivers call cpufreq_frequency_table_target() to get a valid index of their frequency table which is closest to the target_freq. And they don't use target_freq and relation after that. So, it makes sense to just do this work in cpufreq core before calling cpufreq_frequency_table_target() and simply pass index instead. But this can be done only with drivers which expose their frequency table with cpufreq core. For others we need to stick with the old prototype of target() until those drivers are converted to expose frequency tables. This patch implements the new light weight prototype for target_index() routine. It looks like this: int target_index(struct cpufreq_policy *policy, unsigned int index); CPUFreq core will call cpufreq_frequency_table_target() before calling this routine and pass index to it. Because CPUFreq core now requires to call routines present in freq_table.c CONFIG_CPU_FREQ_TABLE must be enabled all the time. This also marks target() interface as deprecated. So, that new drivers avoid using it. And Documentation is updated accordingly. It also converts existing .target() to newly defined light weight .target_index() routine for many driver. Acked-by: Hans-Christian Egtvedt <egtvedt@samfundet.no> Acked-by: Jesper Nilsson <jesper.nilsson@axis.com> Acked-by: Linus Walleij <linus.walleij@linaro.org> Acked-by: Russell King <linux@arm.linux.org.uk> Acked-by: David S. Miller <davem@davemloft.net> Tested-by: Andrew Lunn <andrew@lunn.ch> Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org> Signed-off-by: Rafael J. Wysocki <rjw@rjwysocki.net>
2013-10-25 14:15:48 +00:00
.target_index = acpi_cpufreq_target,
.fast_switch = acpi_cpufreq_fast_switch,
[ACPI/CPUFREQ] Introduce bios_limit per cpu cpufreq sysfs interface This interface is mainly intended (and implemented) for ACPI _PPC BIOS frequency limitations, but other cpufreq drivers can also use it for similar use-cases. Why is this needed: Currently it's not obvious why cpufreq got limited. People see cpufreq/scaling_max_freq reduced, but this could have happened by: - any userspace prog writing to scaling_max_freq - thermal limitations - hardware (_PPC in ACPI case) limitiations Therefore export bios_limit (in kHz) to: - Point the user that it's the BIOS (broken or intended) which limits frequency - Export it as a sysfs interface for userspace progs. While this was a rarely used feature on laptops, there will appear more and more server implemenations providing "Green IT" features like allowing the service processor to limit the frequency. People want to know about HW/BIOS frequency limitations. All ACPI P-state driven cpufreq drivers are covered with this patch: - powernow-k8 - powernow-k7 - acpi-cpufreq Tested with a patched DSDT which limits the first two cores (_PPC returns 1) via _PPC, exposed by bios_limit: # echo 2200000 >cpu2/cpufreq/scaling_max_freq # cat cpu*/cpufreq/scaling_max_freq 2600000 2600000 2200000 2200000 # #scaling_max_freq shows general user/thermal/BIOS limitations # cat cpu*/cpufreq/bios_limit 2600000 2600000 2800000 2800000 # #bios_limit only shows the HW/BIOS limitation CC: Pallipadi Venkatesh <venkatesh.pallipadi@intel.com> CC: Len Brown <lenb@kernel.org> CC: davej@codemonkey.org.uk CC: linux@dominikbrodowski.net Signed-off-by: Thomas Renninger <trenn@suse.de> Signed-off-by: Dave Jones <davej@redhat.com>
2009-11-19 11:31:01 +00:00
.bios_limit = acpi_processor_get_bios_limit,
.init = acpi_cpufreq_cpu_init,
.exit = acpi_cpufreq_cpu_exit,
.resume = acpi_cpufreq_resume,
.name = "acpi-cpufreq",
.attr = acpi_cpufreq_attr,
};
static void __init acpi_cpufreq_boost_init(void)
{
if (boot_cpu_has(X86_FEATURE_CPB) || boot_cpu_has(X86_FEATURE_IDA)) {
msrs = msrs_alloc();
if (!msrs)
return;
acpi_cpufreq_driver.set_boost = set_boost;
acpi_cpufreq_driver.boost_enabled = boost_state(0);
cpu_notifier_register_begin();
/* Force all MSRs to the same value */
boost_set_msrs(acpi_cpufreq_driver.boost_enabled,
cpu_online_mask);
__register_cpu_notifier(&boost_nb);
cpu_notifier_register_done();
}
}
static void acpi_cpufreq_boost_exit(void)
{
if (msrs) {
unregister_cpu_notifier(&boost_nb);
msrs_free(msrs);
msrs = NULL;
}
}
static int __init acpi_cpufreq_init(void)
{
int ret;
if (acpi_disabled)
return -ENODEV;
/* don't keep reloading if cpufreq_driver exists */
if (cpufreq_get_current_driver())
return -EEXIST;
pr_debug("acpi_cpufreq_init\n");
ret = acpi_cpufreq_early_init();
if (ret)
return ret;
#ifdef CONFIG_X86_ACPI_CPUFREQ_CPB
/* this is a sysfs file with a strange name and an even stranger
* semantic - per CPU instantiation, but system global effect.
* Lets enable it only on AMD CPUs for compatibility reasons and
* only if configured. This is considered legacy code, which
* will probably be removed at some point in the future.
*/
if (!check_amd_hwpstate_cpu(0)) {
struct freq_attr **attr;
pr_debug("CPB unsupported, do not expose it\n");
for (attr = acpi_cpufreq_attr; *attr; attr++)
if (*attr == &cpb) {
*attr = NULL;
break;
}
}
#endif
acpi_cpufreq_boost_init();
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)
{
pr_debug("acpi_cpufreq_exit\n");
acpi_cpufreq_boost_exit();
cpufreq_unregister_driver(&acpi_cpufreq_driver);
free_acpi_perf_data();
}
module_param(acpi_pstate_strict, uint, 0644);
MODULE_PARM_DESC(acpi_pstate_strict,
"value 0 or non-zero. non-zero -> strict ACPI checks are "
"performed during frequency changes.");
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");