Commit 3a53396b authored by ShuoX Liu's avatar ShuoX Liu Committed by Len Brown
Browse files

cpuidle: add a sysfs entry to disable specific C state for debug purpose. 



Some C states of new CPU might be not good.  One reason is BIOS might
configure them incorrectly.  To help developers root cause it quickly, the
patch adds a new sysfs entry, so developers could disable specific C state
manually.

In addition, C state might have much impact on performance tuning, as it
takes much time to enter/exit C states, which might delay interrupt
processing.  With the new debug option, developers could check if a deep C
state could impact performance and how much impact it could cause.

Also add this option in Documentation/cpuidle/sysfs.txt.

[akpm@linux-foundation.org: check kstrtol return value]
Signed-off-by: default avatarShuoX Liu <shuox.liu@intel.com>
Reviewed-by: default avatarYanmin Zhang <yanmin_zhang@intel.com>
Reviewed-and-Tested-by: default avatarDeepthi Dharwar <deepthi@linux.vnet.ibm.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLen Brown <len.brown@intel.com>
parent 6a6ea0ac

Documentation/cpuidle/sysfs.txt

+5 −0
Original line number Diff line number Diff line
@@ -36,6 +36,7 @@ drwxr-xr-x 2 root root 0 Feb 8 10:42 state3 
/sys/devices/system/cpu/cpu0/cpuidle/state0:

total 0

-r--r--r-- 1 root root 4096 Feb  8 10:42 desc

-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable

-r--r--r-- 1 root root 4096 Feb  8 10:42 latency

-r--r--r-- 1 root root 4096 Feb  8 10:42 name

-r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -45,6 +46,7 @@ total 0 
/sys/devices/system/cpu/cpu0/cpuidle/state1:

total 0

-r--r--r-- 1 root root 4096 Feb  8 10:42 desc

-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable

-r--r--r-- 1 root root 4096 Feb  8 10:42 latency

-r--r--r-- 1 root root 4096 Feb  8 10:42 name

-r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -54,6 +56,7 @@ total 0 
/sys/devices/system/cpu/cpu0/cpuidle/state2:

total 0

-r--r--r-- 1 root root 4096 Feb  8 10:42 desc

-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable

-r--r--r-- 1 root root 4096 Feb  8 10:42 latency

-r--r--r-- 1 root root 4096 Feb  8 10:42 name

-r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -63,6 +66,7 @@ total 0 
/sys/devices/system/cpu/cpu0/cpuidle/state3:

total 0

-r--r--r-- 1 root root 4096 Feb  8 10:42 desc

-rw-r--r-- 1 root root 4096 Feb  8 10:42 disable

-r--r--r-- 1 root root 4096 Feb  8 10:42 latency

-r--r--r-- 1 root root 4096 Feb  8 10:42 name

-r--r--r-- 1 root root 4096 Feb  8 10:42 power
@@ -72,6 +76,7 @@ total 0 




* desc : Small description about the idle state (string)

* disable : Option to disable this idle state (bool)

* latency : Latency to exit out of this idle state (in microseconds)

* name : Name of the idle state (string)

* power : Power consumed while in this idle state (in milliwatts)

drivers/cpuidle/cpuidle.c

+1 −0
Original line number Diff line number Diff line
@@ -245,6 +245,7 @@ static void poll_idle_init(struct cpuidle_driver *drv) 
	state->power_usage = -1;

	state->flags = 0;

	state->enter = poll_idle;

	state->disable = 0;

}

#else

static void poll_idle_init(struct cpuidle_driver *drv) {}

drivers/cpuidle/governors/menu.c

+4 −1
Original line number Diff line number Diff line
@@ -280,7 +280,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) 
	 * We want to default to C1 (hlt), not to busy polling

	 * unless the timer is happening really really soon.

	 */

	if (data->expected_us > 5)

	if (data->expected_us > 5 &&

		drv->states[CPUIDLE_DRIVER_STATE_START].disable == 0)

		data->last_state_idx = CPUIDLE_DRIVER_STATE_START;



	/*
@@ -290,6 +291,8 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev) 
	for (i = CPUIDLE_DRIVER_STATE_START; i < drv->state_count; i++) {

		struct cpuidle_state *s = &drv->states[i];



		if (s->disable)

			continue;

		if (s->target_residency > data->predicted_us)

			continue;

		if (s->exit_latency > latency_req)

drivers/cpuidle/sysfs.c

+40 −0
Original line number Diff line number Diff line
@@ -11,6 +11,7 @@ 
#include <linux/sysfs.h>

#include <linux/slab.h>

#include <linux/cpu.h>

#include <linux/capability.h>



#include "cpuidle.h"
@@ -222,6 +223,9 @@ struct cpuidle_state_attr { 
#define define_one_state_ro(_name, show) \

static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL)



#define define_one_state_rw(_name, show, store) \

static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0644, show, store)



#define define_show_state_function(_name) \

static ssize_t show_state_##_name(struct cpuidle_state *state, \

			 struct cpuidle_state_usage *state_usage, char *buf) \
@@ -229,6 +233,24 @@ static ssize_t show_state_##_name(struct cpuidle_state *state, \ 
	return sprintf(buf, "%u\n", state->_name);\

}



#define define_store_state_function(_name) \

static ssize_t store_state_##_name(struct cpuidle_state *state, \

		const char *buf, size_t size) \

{ \

	long value; \

	int err; \

	if (!capable(CAP_SYS_ADMIN)) \

		return -EPERM; \

	err = kstrtol(buf, 0, &value); \

	if (err) \

		return err; \

	if (value) \

		state->disable = 1; \

	else \

		state->disable = 0; \

	return size; \

}



#define define_show_state_ull_function(_name) \

static ssize_t show_state_##_name(struct cpuidle_state *state, \

			struct cpuidle_state_usage *state_usage, char *buf) \
@@ -251,6 +273,8 @@ define_show_state_ull_function(usage) 
define_show_state_ull_function(time)

define_show_state_str_function(name)

define_show_state_str_function(desc)

define_show_state_function(disable)

define_store_state_function(disable)



define_one_state_ro(name, show_state_name);

define_one_state_ro(desc, show_state_desc);
@@ -258,6 +282,7 @@ define_one_state_ro(latency, show_state_exit_latency); 
define_one_state_ro(power, show_state_power_usage);

define_one_state_ro(usage, show_state_usage);

define_one_state_ro(time, show_state_time);

define_one_state_rw(disable, show_state_disable, store_state_disable);



static struct attribute *cpuidle_state_default_attrs[] = {

	&attr_name.attr,
@@ -266,6 +291,7 @@ static struct attribute *cpuidle_state_default_attrs[] = { 
	&attr_power.attr,

	&attr_usage.attr,

	&attr_time.attr,

	&attr_disable.attr,

	NULL

};
@@ -287,8 +313,22 @@ static ssize_t cpuidle_state_show(struct kobject * kobj, 
	return ret;

}



static ssize_t cpuidle_state_store(struct kobject *kobj,

	struct attribute *attr, const char *buf, size_t size)

{

	int ret = -EIO;

	struct cpuidle_state *state = kobj_to_state(kobj);

	struct cpuidle_state_attr *cattr = attr_to_stateattr(attr);



	if (cattr->store)

		ret = cattr->store(state, buf, size);



	return ret;

}



static const struct sysfs_ops cpuidle_state_sysfs_ops = {

	.show = cpuidle_state_show,

	.store = cpuidle_state_store,

};



static void cpuidle_state_sysfs_release(struct kobject *kobj)

include/linux/cpuidle.h

+1 −0
Original line number Diff line number Diff line
@@ -46,6 +46,7 @@ struct cpuidle_state { 
	unsigned int	exit_latency; /* in US */

	unsigned int	power_usage; /* in mW */

	unsigned int	target_residency; /* in US */

	unsigned int    disable;



	int (*enter)	(struct cpuidle_device *dev,

			struct cpuidle_driver *drv,

CRA Git | Maintained and supported by SUSTech CRA and CCSE