Skip to contentSkip to conversation

cpuidle: Consolidate disabled state checks

RFC PATCH In review Rafael J. Wysocki 4 participants 4 messages Sep 4, 2019 – Sep 20, 2019

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

RFC PATCH 1/1 cpuidle: Consolidate disabled state checks

From: Rafael J. Wysocki <[email protected]>

There are two reasons why CPU idle states may be disabled: either because the driver has disabled them or because they have been disabled by user space via sysfs.

In the former case, the state's "disabled" flag is set once during the initialization of the driver and it is never cleared later (it is read-only effectively). In the latter case, the "disable" field of the given state's cpuidle_state_usage struct is set and it may be changed via sysfs. Thus checking whether or not an idle state has been disabled involves reading these two flags every time.

In order to avoid the additional check of the state's "disabled" flag (which is effectively read-only anyway), use the value of it at the init time to set a (new) flag in the "disable" field of that state's cpuidle_state_usage structure and use the sysfs interface to manipulate another (new) flag in it. This way the state is disabled whenever the "disable" field of its cpuidle_state_usage structure is nonzero, whatever the reason, and it is the only place to look into to check whether or not the state has been disabled.

---

I have not tested this yet, hence RFC, so it is mainly for feedback.

---
 drivers/cpuidle/cpuidle-powernv.c  |    7 +-----
 drivers/cpuidle/cpuidle.c          |   24 +++++++++++----------
 drivers/cpuidle/governors/ladder.c |    4 ---
 drivers/cpuidle/governors/menu.c   |    8 ++-----
 drivers/cpuidle/governors/teo.c    |    5 +---
 drivers/cpuidle/sysfs.c            |   42 +++++++++++++++++++------------------
 include/linux/cpuidle.h            |    3 ++
 7 files changed, 46 insertions(+), 47 deletions(-)
drivers/cpuidle/cpuidle.c +13 -11
Index: linux-pm/drivers/cpuidle/cpuidle.c
===================================================================
@@ -84,12 +84,12 @@ static int find_deepest_state(struct cpu
 
 	for (i = 1; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable || s->exit_latency <= latency_req
-		    || s->exit_latency > max_latency
-		    || (s->flags & forbidden_flags)
-		    || (s2idle && !s->enter_s2idle))
+		if (dev->states_usage[i].disable ||
+		    s->exit_latency <= latency_req ||
+		    s->exit_latency > max_latency ||
+		    (s->flags & forbidden_flags) ||
+		    (s2idle && !s->enter_s2idle))
 			continue;
 
 		latency_req = s->exit_latency;
@@ -265,8 +265,7 @@ int cpuidle_enter_state(struct cpuidle_d
 
 		if (diff < drv->states[entered_state].target_residency) {
 			for (i = entered_state - 1; i >= 0; i--) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				/* Shallower states are enabled, so update. */
@@ -275,8 +274,7 @@ int cpuidle_enter_state(struct cpuidle_d
 			}
 		} else if (diff > delay) {
 			for (i = entered_state + 1; i < drv->state_count; i++) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				/*
@@ -380,7 +378,7 @@ u64 cpuidle_poll_time(struct cpuidle_dri
 
 	limit_ns = TICK_NSEC;
 	for (i = 1; i < drv->state_count; i++) {
-		if (drv->states[i].disabled || dev->states_usage[i].disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
 		limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
@@ -567,12 +565,16 @@ static void __cpuidle_device_init(struct
  */
 static int __cpuidle_register_device(struct cpuidle_device *dev)
 {
-	int ret;
 	struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev);
+	int i, ret;
 
 	if (!try_module_get(drv->owner))
 		return -EINVAL;
 
+	for (i = 0; i < drv->state_count; i++)
+		if (drv->states[i].disabled)
+			dev->states_usage[i].disable |= CPUIDLE_STATE_DISABLED_BY_DRIVER;
+
 	per_cpu(cpuidle_devices, dev->cpu) = dev;
 	list_add(&dev->device_list, &cpuidle_detected_devices);
 
drivers/cpuidle/sysfs.c +22 -20

57 lines not on this page · raw message

include/linux/cpuidle.h +3 -0
Index: linux-pm/include/linux/cpuidle.h
===================================================================
@@ -29,6 +29,9 @@ struct cpuidle_driver;
  * CPUIDLE DEVICE INTERFACE *
  ****************************/
 
+#define CPUIDLE_STATE_DISABLED_BY_USER		BIT(0)
+#define CPUIDLE_STATE_DISABLED_BY_DRIVER	BIT(1)
+
 struct cpuidle_state_usage {
 	unsigned long long	disable;
 	unsigned long long	usage;
drivers/cpuidle/governors/menu.c +3 -5
Index: linux-pm/drivers/cpuidle/governors/menu.c
===================================================================
@@ -298,7 +298,7 @@ static int menu_select(struct cpuidle_dr
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
 	    ((data->next_timer_us < drv->states[1].target_residency ||
 	      latency_req < drv->states[1].exit_latency) &&
-	     !drv->states[0].disabled && !dev->states_usage[0].disable)) {
+	     !dev->states_usage[0].disable)) {
 		/*
 		 * In this case state[0] will be used no matter what, so return
 		 * it right away and keep the tick running if state[0] is a
@@ -349,9 +349,8 @@ static int menu_select(struct cpuidle_dr
 	idx = -1;
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i]->disable)
 			continue;
 
 		if (idx == -1)
@@ -422,8 +421,7 @@ static int menu_select(struct cpuidle_dr
 			 * tick, so try to correct that.
 			 */
 			for (i = idx - 1; i >= 0; i--) {
-				if (drv->states[i].disabled ||
-				    dev->states_usage[i].disable)
+				if (dev->states_usage[i].disable)
 					continue;
 
 				idx = i;
drivers/cpuidle/governors/teo.c +2 -3
Index: linux-pm/drivers/cpuidle/governors/teo.c
===================================================================
@@ -212,7 +212,7 @@ static int teo_find_shallower_state(stru
 	int i;
 
 	for (i = state_idx - 1; i >= 0; i--) {
-		if (drv->states[i].disabled || dev->states_usage[i].disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
 		state_idx = i;
@@ -254,9 +254,8 @@ static int teo_select(struct cpuidle_dri
 
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable) {
+		if (dev->states_usage[i].disable) {
 			/*
 			 * If the "early hits" metric of a disabled state is
 			 * greater than the current maximum, it should be taken
drivers/cpuidle/governors/ladder.c +1 -3
Index: linux-pm/drivers/cpuidle/governors/ladder.c
===================================================================
@@ -84,7 +84,6 @@ static int ladder_select_state(struct cp
 
 	/* consider promotion */
 	if (last_idx < drv->state_count - 1 &&
-	    !drv->states[last_idx + 1].disabled &&
 	    !dev->states_usage[last_idx + 1].disable &&
 	    last_residency > last_state->threshold.promotion_time &&
 	    drv->states[last_idx + 1].exit_latency <= latency_req) {
@@ -98,8 +97,7 @@ static int ladder_select_state(struct cp
 
 	/* consider demotion */
 	if (last_idx > first_idx &&
-	    (drv->states[last_idx].disabled ||
-	    dev->states_usage[last_idx].disable ||
+	    (dev->states_usage[last_idx].disable ||
 	    drv->states[last_idx].exit_latency > latency_req)) {
 		int i;
 
drivers/cpuidle/cpuidle-powernv.c +2 -5
Index: linux-pm/drivers/cpuidle/cpuidle-powernv.c
===================================================================
@@ -56,13 +56,10 @@ static u64 get_snooze_timeout(struct cpu
 		return default_snooze_timeout;
 
 	for (i = index + 1; i < drv->state_count; i++) {
-		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
-
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i].disable)
 			continue;
 
-		return s->target_residency * tb_ticks_per_usec;
+		return drv->states[i].target_residency * tb_ticks_per_usec;
 	}
 
 	return default_snooze_timeout;
#1 lore raw
Quoted 13 lines · Rafael J. Wysocki

From: Rafael J. Wysocki <[email protected]>

There are two reasons why CPU idle states may be disabled: either because the driver has disabled them or because they have been disabled by user space via sysfs.

In the former case, the state's "disabled" flag is set once during the initialization of the driver and it is never cleared later (it is read-only effectively). In the latter case, the "disable" field of the given state's cpuidle_state_usage struct is set and it may be changed via sysfs. Thus checking whether or not an idle state has been disabled involves reading these two flags every time.

Quoted 8 lines

In order to avoid the additional check of the state's "disabled" flag (which is effectively read-only anyway), use the value of it at the init time to set a (new) flag in the "disable" field of that state's cpuidle_state_usage structure and use the sysfs interface to manipulate another (new) flag in it. This way the state is disabled whenever the "disable" field of its cpuidle_state_usage structure is nonzero, whatever the reason, and it is the only place to look into to check whether or not the state has been disabled.

Yay! That double disable stuff always confused me mightily. This seems like a sensible solution for it.

Acked-by on v1 1/1
#2 lore raw
In reply to Rafael J. Wysocki

Hi Rafael,

Quoted 22 lines · Rafael J. Wysocki

From: Rafael J. Wysocki <[email protected]>

There are two reasons why CPU idle states may be disabled: either because the driver has disabled them or because they have been disabled by user space via sysfs.

In the former case, the state's "disabled" flag is set once during the initialization of the driver and it is never cleared later (it is read-only effectively). In the latter case, the "disable" field of the given state's cpuidle_state_usage struct is set and it may be changed via sysfs. Thus checking whether or not an idle state has been disabled involves reading these two flags every time.

In order to avoid the additional check of the state's "disabled" flag (which is effectively read-only anyway), use the value of it at the init time to set a (new) flag in the "disable" field of that state's cpuidle_state_usage structure and use the sysfs interface to manipulate another (new) flag in it. This way the state is disabled whenever the "disable" field of its cpuidle_state_usage structure is nonzero, whatever the reason, and it is the only place to look into to check whether or not the state has been disabled.

Quoted 4 lines

---

I have not tested this yet, hence RFC, so it is mainly for feedback.

This change makes sense.

Signature · 5 lines
 <http://www.linaro.org/> Linaro.org │ Open source software for ARM SoCs

Follow Linaro:  <http://www.facebook.com/pages/Linaro> Facebook |
<http://twitter.com/#!/linaroorg> Twitter |
<http://www.linaro.org/linaro-blog/> Blog
#3 lore raw
In reply to Rafael J. Wysocki

Hi Rafael,

To be able to try this patch (and the nanosecond as unit of time one),
I simply waited until it would apply properly in the main git tree, which it now does.

However it does not compile:

On 2019.09.04 03:41 Rafael J. Wysocki wrote:

...

Quoted 14 lines

Index: linux-pm/drivers/cpuidle/governors/menu.c
===================================================================

drivers/cpuidle/governors/menu.c +1 -1
@@ -298,7 +298,7 @@ static int menu_select(struct cpuidle_dr
 	if (unlikely(drv->state_count <= 1 || latency_req == 0) ||
 	    ((data->next_timer_us < drv->states[1].target_residency ||
 	      latency_req < drv->states[1].exit_latency) &&
-	     !drv->states[0].disabled && !dev->states_usage[0].disable)) {
+	     !dev->states_usage[0].disable)) {
 		/*
 		 * In this case state[0] will be used no matter what, so return
 		 * it right away and keep the tick running if state[0] is a

drivers/cpuidle/governors/menu.c static int menu_select(struct cpuidle_dr · line 353

Quoted 7 lines
drivers/cpuidle/governors/menu.c +1 -2
@@ -349,9 +349,8 @@ static int menu_select(struct cpuidle_dr
 	idx = -1;
 	for (i = 0; i < drv->state_count; i++) {
 		struct cpuidle_state *s = &drv->states[i];
-		struct cpuidle_state_usage *su = &dev->states_usage[i];
 
-		if (s->disabled || su->disable)
+		if (dev->states_usage[i]->disable)
                                ^^^^^^^^^^

Should be (I think):
+ if (dev->states_usage[i].disable)

... Doug