hollalinux
/
linux-sg2042
mirror of https://github.com/sophgo/linux-riscv.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge branches 'idle-remove-statedata', 'pm_idle' and 'idle-hsw-turbostat' into release

This commit is contained in:
Len Brown 2013-02-18 00:25:16 -05:00
parent 57fa8273a2 558bd3e8dc 1ed51011af
commit 2e7d0f60d8
26 changed files with 284 additions and 255 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
arch/arm/kernel/process.c
View File

@ -172,14 +172,9 @@ static void default_idle(void)
local_irq_enable();
}
void (*pm_idle)(void) = default_idle;
EXPORT_SYMBOL(pm_idle);
/*
* The idle thread, has rather strange semantics for calling pm_idle,
* but this is what x86 does and we need to do the same, so that
* things like cpuidle get called in the same way. The only difference
* is that we always respect 'hlt_counter' to prevent low power idle.
* The idle thread.
* We always respect 'hlt_counter' to prevent low power idle.
*/
void cpu_idle(void)
{
@ -210,10 +205,10 @@ void cpu_idle(void)
} else if (!need_resched()) {
stop_critical_timings();
if (cpuidle_idle_call())
pm_idle();
default_idle();
start_critical_timings();
/*
* pm_idle functions must always
* default_idle functions must always
* return with IRQs enabled.
*/
WARN_ON(irqs_disabled());

13
arch/arm64/kernel/process.c
View File

@ -97,14 +97,9 @@ static void default_idle(void)
local_irq_enable();
}
void (*pm_idle)(void) = default_idle;
EXPORT_SYMBOL_GPL(pm_idle);
/*
* The idle thread, has rather strange semantics for calling pm_idle,
* but this is what x86 does and we need to do the same, so that
* things like cpuidle get called in the same way. The only difference
* is that we always respect 'hlt_counter' to prevent low power idle.
* The idle thread.
* We always respect 'hlt_counter' to prevent low power idle.
*/
void cpu_idle(void)
{
@ -122,10 +117,10 @@ void cpu_idle(void)
local_irq_disable();
if (!need_resched()) {
stop_critical_timings();
pm_idle();
default_idle();
start_critical_timings();
/*
* pm_idle functions should always return
* default_idle functions should always return
* with IRQs enabled.
*/
WARN_ON(irqs_disabled());

7
arch/blackfin/kernel/process.c
View File

@ -39,12 +39,6 @@ int nr_l1stack_tasks;
void *l1_stack_base;
unsigned long l1_stack_len;
/*
* Powermanagement idle function, if any..
*/
void (*pm_idle)(void) = NULL;
EXPORT_SYMBOL(pm_idle);
void (*pm_power_off)(void) = NULL;
EXPORT_SYMBOL(pm_power_off);
@ -81,7 +75,6 @@ void cpu_idle(void)
{
/* endless idle loop with no priority at all */
while (1) {
void (*idle)(void) = pm_idle;
#ifdef CONFIG_HOTPLUG_CPU
if (cpu_is_offline(smp_processor_id()))

11
arch/cris/kernel/process.c
View File

@ -54,11 +54,6 @@ void enable_hlt(void)
EXPORT_SYMBOL(enable_hlt);
/*
* The following aren't currently used.
*/
void (*pm_idle)(void);
extern void default_idle(void);
void (*pm_power_off)(void);
@ -77,16 +72,12 @@ void cpu_idle (void)
while (1) {
rcu_idle_enter();
while (!need_resched()) {
void (*idle)(void);
/*
* Mark this as an RCU critical section so that
* synchronize_kernel() in the unload path waits
* for our completion.
*/
idle = pm_idle;
if (!idle)
idle = default_idle;
idle();
default_idle();
}
rcu_idle_exit();
schedule_preempt_disabled();

3
arch/ia64/kernel/process.c
View File

@ -57,8 +57,6 @@ void (*ia64_mark_idle)(int);
unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
EXPORT_SYMBOL(boot_option_idle_override);
void (*pm_idle) (void);
EXPORT_SYMBOL(pm_idle);
void (*pm_power_off) (void);
EXPORT_SYMBOL(pm_power_off);
@ -301,7 +299,6 @@ cpu_idle (void)
if (mark_idle)
(*mark_idle)(1);
idle = pm_idle;
if (!idle)
idle = default_idle;
(*idle)();

1
arch/ia64/kernel/setup.c
View File

@ -1051,7 +1051,6 @@ cpu_init (void)
max_num_phys_stacked = num_phys_stacked;
}
platform_cpu_init();
pm_idle = default_idle;
}
void __init

51
arch/m32r/kernel/process.c
View File

@ -44,35 +44,9 @@ unsigned long thread_saved_pc(struct task_struct *tsk)
return tsk->thread.lr;
}
/*
* Powermanagement idle function, if any..
*/
static void (*pm_idle)(void) = NULL;
void (*pm_power_off)(void) = NULL;
EXPORT_SYMBOL(pm_power_off);
/*
* We use this is we don't have any better
* idle routine..
*/
static void default_idle(void)
{
/* M32R_FIXME: Please use "cpu_sleep" mode. */
cpu_relax();
}
/*
* On SMP it's slightly faster (but much more power-consuming!)
* to poll the ->work.need_resched flag instead of waiting for the
* cross-CPU IPI to arrive. Use this option with caution.
*/
static void poll_idle (void)
{
/* M32R_FIXME */
cpu_relax();
}
/*
* The idle thread. There's no useful work to be
* done, so just try to conserve power and have a
@ -84,14 +58,8 @@ void cpu_idle (void)
/* endless idle loop with no priority at all */
while (1) {
rcu_idle_enter();
while (!need_resched()) {
void (*idle)(void) = pm_idle;
if (!idle)
idle = default_idle;
idle();
}
while (!need_resched())
cpu_relax();
rcu_idle_exit();
schedule_preempt_disabled();
}
@ -120,21 +88,6 @@ void machine_power_off(void)
/* M32R_FIXME */
}
static int __init idle_setup (char *str)
{
if (!strncmp(str, "poll", 4)) {
printk("using poll in idle threads.\n");
pm_idle = poll_idle;
} else if (!strncmp(str, "sleep", 4)) {
printk("using sleep in idle threads.\n");
pm_idle = default_idle;
}
return 1;
}
__setup("idle=", idle_setup);
void show_regs(struct pt_regs * regs)
{
printk("\n");

3
arch/microblaze/kernel/process.c
View File

@ -41,7 +41,6 @@ void show_regs(struct pt_regs *regs)
regs->msr, regs->ear, regs->esr, regs->fsr);
}
void (*pm_idle)(void);
void (*pm_power_off)(void) = NULL;
EXPORT_SYMBOL(pm_power_off);
@ -98,8 +97,6 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
while (1) {
void (*idle)(void) = pm_idle;
if (!idle)
idle = default_idle;

7
arch/mn10300/kernel/process.c
View File

@ -36,12 +36,6 @@
#include <asm/gdb-stub.h>
#include "internal.h"
/*
* power management idle function, if any..
*/
void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);
/*
* return saved PC of a blocked thread.
*/
@ -113,7 +107,6 @@ void cpu_idle(void)
void (*idle)(void);
smp_rmb();
idle = pm_idle;
if (!idle) {
#if defined(CONFIG_SMP) && !defined(CONFIG_HOTPLUG_CPU)
idle = poll_idle;

5
arch/openrisc/kernel/idle.c
View File

@ -39,11 +39,6 @@
void (*powersave) (void) = NULL;
static inline void pm_idle(void)
{
barrier();
}
void cpu_idle(void)
{
set_thread_flag(TIF_POLLING_NRFLAG);

12
arch/sh/kernel/idle.c
View File

@ -22,7 +22,7 @@
#include <asm/smp.h>
#include <asm/bl_bit.h>
void (*pm_idle)(void);
static void (*sh_idle)(void);
static int hlt_counter;
@ -103,9 +103,9 @@ void cpu_idle(void)
/* Don't trace irqs off for idle */
stop_critical_timings();
if (cpuidle_idle_call())
pm_idle();
sh_idle();
/*
* Sanity check to ensure that pm_idle() returns
* Sanity check to ensure that sh_idle() returns
* with IRQs enabled
*/
WARN_ON(irqs_disabled());
@ -123,13 +123,13 @@ void __init select_idle_routine(void)
/*
* If a platform has set its own idle routine, leave it alone.
*/
if (pm_idle)
if (sh_idle)
return;
if (hlt_works())
pm_idle = default_idle;
sh_idle = default_idle;
else
pm_idle = poll_idle;
sh_idle = poll_idle;
}
void stop_this_cpu(void *unused)

1
arch/sparc/include/asm/processor_32.h
View File

@ -118,6 +118,7 @@ extern unsigned long get_wchan(struct task_struct *);
extern struct task_struct *last_task_used_math;
#define cpu_relax() barrier()
extern void (*sparc_idle)(void);
#endif

3
arch/sparc/kernel/apc.c
View File

@ -20,6 +20,7 @@
#include <asm/uaccess.h>
#include <asm/auxio.h>
#include <asm/apc.h>
#include <asm/processor.h>
/* Debugging
*
@ -158,7 +159,7 @@ static int apc_probe(struct platform_device *op)
/* Assign power management IDLE handler */
if (!apc_no_idle)
pm_idle = apc_swift_idle;
sparc_idle = apc_swift_idle;
printk(KERN_INFO "%s: power management initialized%s\n",
APC_DEVNAME, apc_no_idle ? " (CPU idle disabled)" : "");

5
arch/sparc/kernel/leon_pmc.c
View File

@ -9,6 +9,7 @@
#include <asm/leon_amba.h>
#include <asm/cpu_type.h>
#include <asm/leon.h>
#include <asm/processor.h>
/* List of Systems that need fixup instructions around power-down instruction */
unsigned int pmc_leon_fixup_ids[] = {
@ -69,9 +70,9 @@ static int __init leon_pmc_install(void)
if (sparc_cpu_model == sparc_leon) {
/* Assign power management IDLE handler */
if (pmc_leon_need_fixup())
pm_idle = pmc_leon_idle_fixup;
sparc_idle = pmc_leon_idle_fixup;
else
pm_idle = pmc_leon_idle;
sparc_idle = pmc_leon_idle;
printk(KERN_INFO "leon: power management initialized\n");
}

3
arch/sparc/kernel/pmc.c
View File

@ -17,6 +17,7 @@
#include <asm/oplib.h>
#include <asm/uaccess.h>
#include <asm/auxio.h>
#include <asm/processor.h>
/* Debug
*
@ -63,7 +64,7 @@ static int pmc_probe(struct platform_device *op)
#ifndef PMC_NO_IDLE
/* Assign power management IDLE handler */
pm_idle = pmc_swift_idle;
sparc_idle = pmc_swift_idle;
#endif
printk(KERN_INFO "%s: power management initialized\n", PMC_DEVNAME);

7
arch/sparc/kernel/process_32.c
View File

@ -43,8 +43,7 @@
* Power management idle function
* Set in pm platform drivers (apc.c and pmc.c)
*/
void (*pm_idle)(void);
EXPORT_SYMBOL(pm_idle);
void (*sparc_idle)(void);
/*
* Power-off handler instantiation for pm.h compliance
@ -75,8 +74,8 @@ void cpu_idle(void)
/* endless idle loop with no priority at all */
for (;;) {
while (!need_resched()) {
if (pm_idle)
(*pm_idle)();
if (sparc_idle)
(*sparc_idle)();
else
cpu_relax();
}

5
arch/unicore32/kernel/process.c
View File

@ -45,11 +45,6 @@ static const char * const processor_modes[] = {
"UK18", "UK19", "UK1A", "EXTN", "UK1C", "UK1D", "UK1E", "SUSR"
};
/*
* The idle thread, has rather strange semantics for calling pm_idle,
* but this is what x86 does and we need to do the same, so that
* things like cpuidle get called in the same way.
*/
void cpu_idle(void)
{
/* endless idle loop with no priority at all */

1
arch/x86/Kconfig
View File

@ -1912,6 +1912,7 @@ config APM_DO_ENABLE
this feature.
config APM_CPU_IDLE
depends on CPU_IDLE
bool "Make CPU Idle calls when idle"
---help---
Enable calls to APM CPU Idle/CPU Busy inside the kernel's idle loop.

3
arch/x86/include/asm/mwait.h
View File

@ -4,7 +4,8 @@
#define MWAIT_SUBSTATE_MASK 0xf
#define MWAIT_CSTATE_MASK 0xf
#define MWAIT_SUBSTATE_SIZE 4
#define MWAIT_MAX_NUM_CSTATES 8
#define MWAIT_HINT2CSTATE(hint) (((hint) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK)
#define MWAIT_HINT2SUBSTATE(hint) ((hint) & MWAIT_CSTATE_MASK)
#define CPUID_MWAIT_LEAF 5
#define CPUID5_ECX_EXTENSIONS_SUPPORTED 0x1

3
arch/x86/include/uapi/asm/msr-index.h
View File

@ -103,6 +103,8 @@
#define DEBUGCTLMSR_BTS_OFF_USR (1UL << 10)
#define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI (1UL << 11)
#define MSR_IA32_POWER_CTL 0x000001fc
#define MSR_IA32_MC0_CTL 0x00000400
#define MSR_IA32_MC0_STATUS 0x00000401
#define MSR_IA32_MC0_ADDR 0x00000402
@ -272,6 +274,7 @@
#define MSR_IA32_PLATFORM_ID 0x00000017
#define MSR_IA32_EBL_CR_POWERON 0x0000002a
#define MSR_EBC_FREQUENCY_ID 0x0000002c
#define MSR_SMI_COUNT 0x00000034
#define MSR_IA32_FEATURE_CONTROL 0x0000003a
#define MSR_IA32_TSC_ADJUST 0x0000003b

57
arch/x86/kernel/apm_32.c
View File

@ -232,6 +232,7 @@
#include <linux/acpi.h>
#include <linux/syscore_ops.h>
#include <linux/i8253.h>
#include <linux/cpuidle.h>
#include <asm/uaccess.h>
#include <asm/desc.h>
@ -360,13 +361,35 @@ struct apm_user {
* idle percentage above which bios idle calls are done
*/
#ifdef CONFIG_APM_CPU_IDLE
#warning deprecated CONFIG_APM_CPU_IDLE will be deleted in 2012
#define DEFAULT_IDLE_THRESHOLD 95
#else
#define DEFAULT_IDLE_THRESHOLD 100
#endif
#define DEFAULT_IDLE_PERIOD (100 / 3)
static int apm_cpu_idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index);
static struct cpuidle_driver apm_idle_driver = {
.name = "apm_idle",
.owner = THIS_MODULE,
.en_core_tk_irqen = 1,
.states = {
{ /* entry 0 is for polling */ },
{ /* entry 1 is for APM idle */
.name = "APM",
.desc = "APM idle",
.flags = CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 250, /* WAG */
.target_residency = 500, /* WAG */
.enter = &apm_cpu_idle
},
},
.state_count = 2,
};
static struct cpuidle_device apm_cpuidle_device;
/*
* Local variables
*/
@ -377,7 +400,6 @@ static struct {
static int clock_slowed;
static int idle_threshold __read_mostly = DEFAULT_IDLE_THRESHOLD;
static int idle_period __read_mostly = DEFAULT_IDLE_PERIOD;
static int set_pm_idle;
static int suspends_pending;
static int standbys_pending;
static int ignore_sys_suspend;
@ -884,8 +906,6 @@ static void apm_do_busy(void)
#define IDLE_CALC_LIMIT (HZ * 100)
#define IDLE_LEAKY_MAX 16
static void (*original_pm_idle)(void) __read_mostly;
/**
* apm_cpu_idle - cpu idling for APM capable Linux
*
@ -894,7 +914,8 @@ static void (*original_pm_idle)(void) __read_mostly;
* Furthermore it calls the system default idle routine.
*/
static void apm_cpu_idle(void)
static int apm_cpu_idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
{
static int use_apm_idle; /* = 0 */
static unsigned int last_jiffies; /* = 0 */
@ -904,7 +925,6 @@ static void apm_cpu_idle(void)
unsigned int jiffies_since_last_check = jiffies - last_jiffies;
unsigned int bucket;
WARN_ONCE(1, "deprecated apm_cpu_idle will be deleted in 2012");
recalc:
if (jiffies_since_last_check > IDLE_CALC_LIMIT) {
use_apm_idle = 0;
@ -950,10 +970,7 @@ recalc:
break;
}
}
if (original_pm_idle)
original_pm_idle();
else
default_idle();
default_idle();
local_irq_disable();
jiffies_since_last_check = jiffies - last_jiffies;
if (jiffies_since_last_check > idle_period)
@ -963,7 +980,7 @@ recalc:
if (apm_idle_done)
apm_do_busy();
local_irq_enable();
return index;
}
/**
@ -2381,9 +2398,9 @@ static int __init apm_init(void)
if (HZ != 100)
idle_period = (idle_period * HZ) / 100;
if (idle_threshold < 100) {
original_pm_idle = pm_idle;
pm_idle = apm_cpu_idle;
set_pm_idle = 1;
if (!cpuidle_register_driver(&apm_idle_driver))
if (cpuidle_register_device(&apm_cpuidle_device))
cpuidle_unregister_driver(&apm_idle_driver);
}
return 0;
@ -2393,15 +2410,9 @@ static void __exit apm_exit(void)
{
int error;
if (set_pm_idle) {
pm_idle = original_pm_idle;
/*
* We are about to unload the current idle thread pm callback
* (pm_idle), Wait for all processors to update cached/local
* copies of pm_idle before proceeding.
*/
kick_all_cpus_sync();
}
cpuidle_unregister_device(&apm_cpuidle_device);
cpuidle_unregister_driver(&apm_idle_driver);
if (((apm_info.bios.flags & APM_BIOS_DISENGAGED) == 0)
&& (apm_info.connection_version > 0x0100)) {
error = apm_engage_power_management(APM_DEVICE_ALL, 0);

31
arch/x86/kernel/process.c
View File

@ -268,13 +268,7 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
unsigned long boot_option_idle_override = IDLE_NO_OVERRIDE;
EXPORT_SYMBOL(boot_option_idle_override);
/*
* Powermanagement idle function, if any..
*/
void (*pm_idle)(void);
#ifdef CONFIG_APM_MODULE
EXPORT_SYMBOL(pm_idle);
#endif
static void (*x86_idle)(void);
#ifndef CONFIG_SMP
static inline void play_dead(void)
@ -351,7 +345,7 @@ void cpu_idle(void)
rcu_idle_enter();
if (cpuidle_idle_call())
pm_idle();
x86_idle();
rcu_idle_exit();
start_critical_timings();
@ -398,9 +392,9 @@ EXPORT_SYMBOL(default_idle);
bool set_pm_idle_to_default(void)
{
bool ret = !!pm_idle;
bool ret = !!x86_idle;
pm_idle = default_idle;
x86_idle = default_idle;
return ret;
}
@ -567,11 +561,10 @@ static void amd_e400_idle(void)
void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
{
#ifdef CONFIG_SMP
if (pm_idle == poll_idle && smp_num_siblings > 1) {
if (x86_idle == poll_idle && smp_num_siblings > 1)
pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n");
}
#endif
if (pm_idle)
if (x86_idle)
return;
if (cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c)) {
@ -579,19 +572,19 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
* One CPU supports mwait => All CPUs supports mwait
*/
pr_info("using mwait in idle threads\n");
pm_idle = mwait_idle;
x86_idle = mwait_idle;
} else if (cpu_has_amd_erratum(amd_erratum_400)) {
/* E400: APIC timer interrupt does not wake up CPU from C1e */
pr_info("using AMD E400 aware idle routine\n");
pm_idle = amd_e400_idle;
x86_idle = amd_e400_idle;
} else
pm_idle = default_idle;
x86_idle = default_idle;
}
void __init init_amd_e400_c1e_mask(void)
{
/* If we're using amd_e400_idle, we need to allocate amd_e400_c1e_mask. */
if (pm_idle == amd_e400_idle)
if (x86_idle == amd_e400_idle)
zalloc_cpumask_var(&amd_e400_c1e_mask, GFP_KERNEL);
}
@ -602,7 +595,7 @@ static int __init idle_setup(char *str)
if (!strcmp(str, "poll")) {
pr_info("using polling idle threads\n");
pm_idle = poll_idle;
x86_idle = poll_idle;
boot_option_idle_override = IDLE_POLL;
} else if (!strcmp(str, "mwait")) {
boot_option_idle_override = IDLE_FORCE_MWAIT;
@ -615,7 +608,7 @@ static int __init idle_setup(char *str)
* To continue to load the CPU idle driver, don't touch
* the boot_option_idle_override.
*/
pm_idle = default_idle;
x86_idle = default_idle;
boot_option_idle_override = IDLE_HALT;
} else if (!strcmp(str, "nomwait")) {
/*

209
drivers/idle/intel_idle.c
View File

@ -74,7 +74,7 @@ static struct cpuidle_driver intel_idle_driver = {
.en_core_tk_irqen = 1,
};
/* intel_idle.max_cstate=0 disables driver */
static int max_cstate = MWAIT_MAX_NUM_CSTATES - 1;
static int max_cstate = CPUIDLE_STATE_MAX - 1;
static unsigned int mwait_substates;
@ -90,6 +90,7 @@ struct idle_cpu {
* Indicate which enable bits to clear here.
*/
unsigned long auto_demotion_disable_flags;
bool disable_promotion_to_c1e;
};
static const struct idle_cpu *icpu;
@ -123,127 +124,190 @@ static struct cpuidle_state *cpuidle_state_table;
* which is also the index into the MWAIT hint array.
* Thus C0 is a dummy.
*/
static struct cpuidle_state nehalem_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
static struct cpuidle_state nehalem_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-NHM",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 3,
.target_residency = 6,
.enter = &intel_idle },
{ /* MWAIT C2 */
{
.name = "C1E-NHM",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-NHM",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 20,
.target_residency = 80,
.enter = &intel_idle },
{ /* MWAIT C3 */
{
.name = "C6-NHM",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 200,
.target_residency = 800,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state snb_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
static struct cpuidle_state snb_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-SNB",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.exit_latency = 2,
.target_residency = 2,
.enter = &intel_idle },
{ /* MWAIT C2 */
{
.name = "C1E-SNB",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-SNB",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 80,
.target_residency = 211,
.enter = &intel_idle },
{ /* MWAIT C3 */
{
.name = "C6-SNB",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 104,
.target_residency = 345,
.enter = &intel_idle },
{ /* MWAIT C4 */
{
.name = "C7-SNB",
.desc = "MWAIT 0x30",
.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 109,
.target_residency = 345,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state ivb_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
static struct cpuidle_state ivb_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-IVB",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 1,
.enter = &intel_idle },
{ /* MWAIT C2 */
{
.name = "C1E-IVB",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-IVB",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 59,
.target_residency = 156,
.enter = &intel_idle },
{ /* MWAIT C3 */
{
.name = "C6-IVB",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 80,
.target_residency = 300,
.enter = &intel_idle },
{ /* MWAIT C4 */
{
.name = "C7-IVB",
.desc = "MWAIT 0x30",
.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 87,
.target_residency = 300,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state atom_cstates[MWAIT_MAX_NUM_CSTATES] = {
{ /* MWAIT C0 */ },
{ /* MWAIT C1 */
.name = "C1-ATM",
static struct cpuidle_state hsw_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1-HSW",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 1,
.target_residency = 4,
.exit_latency = 2,
.target_residency = 2,
.enter = &intel_idle },
{ /* MWAIT C2 */
{
.name = "C1E-HSW",
.desc = "MWAIT 0x01",
.flags = MWAIT2flg(0x01) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C3-HSW",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 33,
.target_residency = 100,
.enter = &intel_idle },
{
.name = "C6-HSW",
.desc = "MWAIT 0x20",
.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 133,
.target_residency = 400,
.enter = &intel_idle },
{
.name = "C7s-HSW",
.desc = "MWAIT 0x32",
.flags = MWAIT2flg(0x32) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 166,
.target_residency = 500,
.enter = &intel_idle },
{
.enter = NULL }
};
static struct cpuidle_state atom_cstates[CPUIDLE_STATE_MAX] = {
{
.name = "C1E-ATM",
.desc = "MWAIT 0x00",
.flags = MWAIT2flg(0x00) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 10,
.target_residency = 20,
.enter = &intel_idle },
{
.name = "C2-ATM",
.desc = "MWAIT 0x10",
.flags = MWAIT2flg(0x10) | CPUIDLE_FLAG_TIME_VALID,
.exit_latency = 20,
.target_residency = 80,
.enter = &intel_idle },
{ /* MWAIT C3 */ },
{ /* MWAIT C4 */
{
.name = "C4-ATM",
.desc = "MWAIT 0x30",
.flags = MWAIT2flg(0x30) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 100,
.target_residency = 400,
.enter = &intel_idle },
{ /* MWAIT C5 */ },
{ /* MWAIT C6 */
{
.name = "C6-ATM",
.desc = "MWAIT 0x52",
.flags = MWAIT2flg(0x52) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
.exit_latency = 140,
.target_residency = 560,
.enter = &intel_idle },
{
.enter = NULL }
};
/**
@ -342,10 +406,19 @@ static void auto_demotion_disable(void *dummy)
msr_bits &= ~(icpu->auto_demotion_disable_flags);
wrmsrl(MSR_NHM_SNB_PKG_CST_CFG_CTL, msr_bits);
}
static void c1e_promotion_disable(void *dummy)
{
unsigned long long msr_bits;
rdmsrl(MSR_IA32_POWER_CTL, msr_bits);
msr_bits &= ~0x2;
wrmsrl(MSR_IA32_POWER_CTL, msr_bits);
}
static const struct idle_cpu idle_cpu_nehalem = {
.state_table = nehalem_cstates,
.auto_demotion_disable_flags = NHM_C1_AUTO_DEMOTE | NHM_C3_AUTO_DEMOTE,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_atom = {
@ -359,10 +432,17 @@ static const struct idle_cpu idle_cpu_lincroft = {
static const struct idle_cpu idle_cpu_snb = {
.state_table = snb_cstates,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_ivb = {
.state_table = ivb_cstates,
.disable_promotion_to_c1e = true,
};
static const struct idle_cpu idle_cpu_hsw = {
.state_table = hsw_cstates,
.disable_promotion_to_c1e = true,
};
#define ICPU(model, cpu) \
@ -382,6 +462,9 @@ static const struct x86_cpu_id intel_idle_ids[] = {
ICPU(0x2d, idle_cpu_snb),
ICPU(0x3a, idle_cpu_ivb),
ICPU(0x3e, idle_cpu_ivb),
ICPU(0x3c, idle_cpu_hsw),
ICPU(0x3f, idle_cpu_hsw),
ICPU(0x45, idle_cpu_hsw),
{}
};
MODULE_DEVICE_TABLE(x86cpu, intel_idle_ids);
@ -464,32 +547,31 @@ static int intel_idle_cpuidle_driver_init(void)
drv->state_count = 1;
for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
int num_substates;
for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
int num_substates, mwait_hint, mwait_cstate, mwait_substate;
if (cstate > max_cstate) {
if (cpuidle_state_table[cstate].enter == NULL)
break;
if (cstate + 1 > max_cstate) {
printk(PREFIX "max_cstate %d reached\n",
max_cstate);
break;
}
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((cstate) * 4))
& MWAIT_SUBSTATE_MASK;
if (num_substates == 0)
continue;
/* is the state not enabled? */
if (cpuidle_state_table[cstate].enter == NULL) {
/* does the driver not know about the state? */
if (*cpuidle_state_table[cstate].name == '\0')
pr_debug(PREFIX "unaware of model 0x%x"
" MWAIT %d please"
" contact lenb@kernel.org\n",
boot_cpu_data.x86_model, cstate);
continue;
}
mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
if ((cstate > 2) &&
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
& MWAIT_SUBSTATE_MASK;
/* if sub-state in table is not enumerated by CPUID */
if ((mwait_substate + 1) > num_substates)
continue;
if (((mwait_cstate + 1) > 2) &&
!boot_cpu_has(X86_FEATURE_NONSTOP_TSC))
mark_tsc_unstable("TSC halts in idle"
" states deeper than C2");
@ -503,6 +585,9 @@ static int intel_idle_cpuidle_driver_init(void)
if (icpu->auto_demotion_disable_flags)
on_each_cpu(auto_demotion_disable, NULL, 1);
if (icpu->disable_promotion_to_c1e) /* each-cpu is redundant */
on_each_cpu(c1e_promotion_disable, NULL, 1);
return 0;
}
@ -521,21 +606,27 @@ static int intel_idle_cpu_init(int cpu)
dev->state_count = 1;
for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
int num_substates;
for (cstate = 0; cstate < CPUIDLE_STATE_MAX; ++cstate) {
int num_substates, mwait_hint, mwait_cstate, mwait_substate;
if (cstate > max_cstate) {
if (cpuidle_state_table[cstate].enter == NULL)
continue;
if (cstate + 1 > max_cstate) {
printk(PREFIX "max_cstate %d reached\n", max_cstate);
break;
}
mwait_hint = flg2MWAIT(cpuidle_state_table[cstate].flags);
mwait_cstate = MWAIT_HINT2CSTATE(mwait_hint);
mwait_substate = MWAIT_HINT2SUBSTATE(mwait_hint);
/* does the state exist in CPUID.MWAIT? */
num_substates = (mwait_substates >> ((cstate) * 4))
& MWAIT_SUBSTATE_MASK;
if (num_substates == 0)
continue;
/* is the state not enabled? */
if (cpuidle_state_table[cstate].enter == NULL)
num_substates = (mwait_substates >> ((mwait_cstate + 1) * 4))
& MWAIT_SUBSTATE_MASK;
/* if sub-state in table is not enumerated by CPUID */
if ((mwait_substate + 1) > num_substates)
continue;
dev->state_count += 1;

1
include/linux/pm.h
View File

@ -31,7 +31,6 @@
/*
* Callbacks for platform drivers to implement.
*/
extern void (*pm_idle)(void);
extern void (*pm_power_off)(void);
extern void (*pm_power_off_prepare)(void);

36
tools/power/x86/turbostat/turbostat.8
View File

@ -31,8 +31,6 @@ The \fB-S\fP option limits output to a 1-line System Summary for each interval.
.PP
The \fB-v\fP option increases verbosity.
.PP
The \fB-s\fP option prints the SMI counter, equivalent to "-c 0x34"
.PP
The \fB-c MSR#\fP option includes the delta of the specified 32-bit MSR counter.
.PP
The \fB-C MSR#\fP option includes the delta of the specified 64-bit MSR counter.
@ -186,26 +184,24 @@ This is a weighted average, where the weight is %c0. ie. it is the total number
un-halted cycles elapsed per time divided by the number of CPUs.
.SH SMI COUNTING EXAMPLE
On Intel Nehalem and newer processors, MSR 0x34 is a System Management Mode Interrupt (SMI) counter.
Using the -m option, you can display how many SMIs have fired since reset, or if there
are SMIs during the measurement interval, you can display the delta using the -d option.
This counter is shown by default under the "SMI" column.
.nf
[root@x980 ~]# turbostat -m 0x34
cor CPU %c0 GHz TSC MSR 0x034 %c1 %c3 %c6 %pc3 %pc6
1.41 1.82 3.38 0x00000000 8.92 37.82 51.85 17.37 0.55
0 0 3.73 2.03 3.38 0x00000055 1.72 48.25 46.31 17.38 0.55
0 6 0.14 1.63 3.38 0x00000056 5.30
1 2 2.51 1.80 3.38 0x00000056 15.65 29.33 52.52
1 8 0.10 1.65 3.38 0x00000056 18.05
2 4 1.16 1.68 3.38 0x00000056 5.87 24.47 68.50
2 10 0.10 1.63 3.38 0x00000056 6.93
8 1 3.84 1.91 3.38 0x00000056 1.36 50.65 44.16
8 7 0.08 1.64 3.38 0x00000056 5.12
9 3 1.82 1.73 3.38 0x00000056 7.59 24.21 66.38
9 9 0.09 1.68 3.38 0x00000056 9.32
10 5 1.66 1.65 3.38 0x00000056 15.10 50.00 33.23
10 11 1.72 1.65 3.38 0x00000056 15.05
[root@x980 ~]# turbostat
cor CPU %c0 GHz TSC SMI %c1 %c3 %c6 CTMP %pc3 %pc6
0.11 1.91 3.38 0 1.84 0.26 97.79 29 0.82 83.87
0 0 0.40 1.63 3.38 0 10.27 0.12 89.20 20 0.82 83.88
0 6 0.06 1.63 3.38 0 10.61
1 2 0.37 2.63 3.38 0 0.02 0.10 99.51 22
1 8 0.01 1.62 3.38 0 0.39
2 4 0.07 1.62 3.38 0 0.04 0.07 99.82 23
2 10 0.02 1.62 3.38 0 0.09
8 1 0.23 1.64 3.38 0 0.10 1.07 98.60 24
8 7 0.02 1.64 3.38 0 0.31
9 3 0.03 1.62 3.38 0 0.03 0.05 99.89 29
9 9 0.02 1.62 3.38 0 0.05
10 5 0.07 1.62 3.38 0 0.08 0.12 99.73 27
10 11 0.03 1.62 3.38 0 0.13
^C
[root@x980 ~]#
.fi
.SH NOTES

48
tools/power/x86/turbostat/turbostat.c
View File

@ -58,6 +58,7 @@ unsigned int extra_msr_offset32;
unsigned int extra_msr_offset64;
unsigned int extra_delta_offset32;
unsigned int extra_delta_offset64;
int do_smi;
double bclk;
unsigned int show_pkg;
unsigned int show_core;
@ -99,6 +100,7 @@ struct thread_data {
unsigned long long extra_delta64;
unsigned long long extra_msr32;
unsigned long long extra_delta32;
unsigned int smi_count;
unsigned int cpu_id;
unsigned int flags;
#define CPU_IS_FIRST_THREAD_IN_CORE 0x2
@ -248,6 +250,8 @@ void print_header(void)
if (has_aperf)
outp += sprintf(outp, " GHz");
outp += sprintf(outp, " TSC");
if (do_smi)
outp += sprintf(outp, " SMI");
if (extra_delta_offset32)
outp += sprintf(outp, " count 0x%03X", extra_delta_offset32);
if (extra_delta_offset64)
@ -314,6 +318,8 @@ int dump_counters(struct thread_data *t, struct core_data *c,
extra_msr_offset32, t->extra_msr32);
fprintf(stderr, "msr0x%x: %016llX\n",
extra_msr_offset64, t->extra_msr64);
if (do_smi)
fprintf(stderr, "SMI: %08X\n", t->smi_count);
}
if (c) {
@ -352,6 +358,7 @@ int dump_counters(struct thread_data *t, struct core_data *c,
* RAM_W: %5.2
* GHz: "GHz" 3 columns %3.2
* TSC: "TSC" 3 columns %3.2
* SMI: "SMI" 4 columns %4d
* percentage " %pc3" %6.2
* Perf Status percentage: %5.2
* "CTMP" 4 columns %4d
@ -431,6 +438,10 @@ int format_counters(struct thread_data *t, struct core_data *c,
/* TSC */
outp += sprintf(outp, "%5.2f", 1.0 * t->tsc/units/interval_float);
/* SMI */
if (do_smi)
outp += sprintf(outp, "%4d", t->smi_count);
/* delta */
if (extra_delta_offset32)
outp += sprintf(outp, " %11llu", t->extra_delta32);
@ -645,6 +656,9 @@ delta_thread(struct thread_data *new, struct thread_data *old,
*/
old->extra_msr32 = new->extra_msr32;
old->extra_msr64 = new->extra_msr64;
if (do_smi)
old->smi_count = new->smi_count - old->smi_count;
}
int delta_cpu(struct thread_data *t, struct core_data *c,
@ -672,6 +686,7 @@ void clear_counters(struct thread_data *t, struct core_data *c, struct pkg_data
t->mperf = 0;
t->c1 = 0;
t->smi_count = 0;
t->extra_delta32 = 0;
t->extra_delta64 = 0;
@ -802,6 +817,11 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
return -4;
}
if (do_smi) {
if (get_msr(cpu, MSR_SMI_COUNT, &msr))
return -5;
t->smi_count = msr & 0xFFFFFFFF;
}
if (extra_delta_offset32) {
if (get_msr(cpu, extra_delta_offset32, &msr))
return -5;
@ -908,8 +928,7 @@ void print_verbose_header(void)
get_msr(0, MSR_NHM_PLATFORM_INFO, &msr);
if (verbose)
fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
fprintf(stderr, "cpu0: MSR_NHM_PLATFORM_INFO: 0x%08llx\n", msr);
ratio = (msr >> 40) & 0xFF;
fprintf(stderr, "%d * %.0f = %.0f MHz max efficiency\n",
@ -919,13 +938,16 @@ void print_verbose_header(void)
fprintf(stderr, "%d * %.0f = %.0f MHz TSC frequency\n",
ratio, bclk, ratio * bclk);
get_msr(0, MSR_IA32_POWER_CTL, &msr);
fprintf(stderr, "cpu0: MSR_IA32_POWER_CTL: 0x%08llx (C1E: %sabled)\n",
msr, msr & 0x2 ? "EN" : "DIS");
if (!do_ivt_turbo_ratio_limit)
goto print_nhm_turbo_ratio_limits;
get_msr(0, MSR_IVT_TURBO_RATIO_LIMIT, &msr);
if (verbose)
fprintf(stderr, "cpu0: MSR_IVT_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
fprintf(stderr, "cpu0: MSR_IVT_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
ratio = (msr >> 56) & 0xFF;
if (ratio)
@ -1016,8 +1038,7 @@ print_nhm_turbo_ratio_limits:
get_msr(0, MSR_NHM_TURBO_RATIO_LIMIT, &msr);
if (verbose)
fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
fprintf(stderr, "cpu0: MSR_NHM_TURBO_RATIO_LIMIT: 0x%08llx\n", msr);
ratio = (msr >> 56) & 0xFF;
if (ratio)
@ -1397,6 +1418,9 @@ int has_nehalem_turbo_ratio_limit(unsigned int family, unsigned int model)
case 0x2D: /* SNB Xeon */
case 0x3A: /* IVB */
case 0x3E: /* IVB Xeon */
case 0x3C: /* HSW */
case 0x3F: /* HSW */
case 0x45: /* HSW */
return 1;
case 0x2E: /* Nehalem-EX Xeon - Beckton */
case 0x2F: /* Westmere-EX Xeon - Eagleton */
@ -1488,6 +1512,9 @@ void rapl_probe(unsigned int family, unsigned int model)
switch (model) {
case 0x2A:
case 0x3A:
case 0x3C: /* HSW */
case 0x3F: /* HSW */
case 0x45: /* HSW */
do_rapl = RAPL_PKG | RAPL_CORES | RAPL_GFX;
break;
case 0x2D:
@ -1724,6 +1751,9 @@ int is_snb(unsigned int family, unsigned int model)
case 0x2D:
case 0x3A: /* IVB */
case 0x3E: /* IVB Xeon */
case 0x3C: /* HSW */
case 0x3F: /* HSW */
case 0x45: /* HSW */
return 1;
}
return 0;
@ -1883,6 +1913,7 @@ void check_cpuid()
do_nehalem_platform_info = genuine_intel && has_invariant_tsc;
do_nhm_cstates = genuine_intel; /* all Intel w/ non-stop TSC have NHM counters */
do_smi = do_nhm_cstates;
do_snb_cstates = is_snb(family, model);
bclk = discover_bclk(family, model);
@ -2219,9 +2250,6 @@ void cmdline(int argc, char **argv)
case 'c':
sscanf(optarg, "%x", &extra_delta_offset32);
break;
case 's':
extra_delta_offset32 = 0x34; /* SMI counter */
break;
case 'C':
sscanf(optarg, "%x", &extra_delta_offset64);
break;
@ -2248,7 +2276,7 @@ int main(int argc, char **argv)
cmdline(argc, argv);
if (verbose)
fprintf(stderr, "turbostat v3.0 November 23, 2012"
fprintf(stderr, "turbostat v3.2 February 11, 2013"
" - Len Brown <lenb@kernel.org>\n");
turbostat_init();