PM / QoS: Fix device resume latency framework

The special value of 0 for device resume latency PM QoS means
"no restriction", but there are two problems with that.

First, device resume latency PM QoS requests with 0 as the
value are always put in front of requests with positive
values in the priority lists used internally by the PM QoS
framework, causing 0 to be chosen as an effective constraint
value. However, that 0 is then interpreted as "no restriction"
effectively overriding the other requests with specific
restrictions which is incorrect.

Second, the users of device resume latency PM QoS have no
way to specify that *any* resume latency at all should be
avoided, which is an artificial limitation in general.

To address these issues, modify device resume latency PM QoS to
use S32_MAX as the "no constraint" value and 0 as the "no
latency at all" one and rework its users (the cpuidle menu
governor, the genpd QoS governor and the runtime PM framework)
to follow these changes.

Also add a special "n/a" value to the corresponding user space I/F
to allow user space to indicate that it cannot accept any resume
latencies at all for the given device.

Fixes: 85dc0b8a4019 (PM / QoS: Make it possible to expose PM QoS latency constraints)
Link: https://bugzilla.kernel.org/show_bug.cgi?id=197323
Reported-by: Reinette Chatre <[e-mail]>
Signed-off-by: Rafael J. Wysocki <[e-mail]>
Tested-by: Reinette Chatre <[e-mail]>
Tested-by: Geert Uytterhoeven <[e-mail]>
Tested-by: Tero Kristo <[e-mail]>
Reviewed-by: Ramesh Thomas <[e-mail]>

Documentation/ABI/testing/sysfs-devices-power

···
 		device, after it has been suspended at run time, from a resume
 		request to the moment the device will be ready to process I/O,
 		in microseconds.  If it is equal to 0, however, this means that
-		the PM QoS resume latency may be arbitrary.
+		the PM QoS resume latency may be arbitrary and the special value
+		"n/a" means that user space cannot accept any resume latency at
+		all for the given device.
 
 		Not all drivers support this attribute.  If it isn't supported,
 		it is not present.

drivers/base/cpu.c

···
 
 	per_cpu(cpu_sys_devices, num) = &cpu->dev;
 	register_cpu_under_node(num, cpu_to_node(num));
-	dev_pm_qos_expose_latency_limit(&cpu->dev, 0);
+	dev_pm_qos_expose_latency_limit(&cpu->dev,
+					PM_QOS_RESUME_LATENCY_NO_CONSTRAINT);
 
 	return 0;
 }

drivers/base/power/domain.c

···
 
 	gpd_data->base.dev = dev;
 	gpd_data->td.constraint_changed = true;
-	gpd_data->td.effective_constraint_ns = 0;
+	gpd_data->td.effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
 	gpd_data->nb.notifier_call = genpd_dev_pm_qos_notifier;
 
 	spin_lock_irq(&dev->power.lock);

drivers/base/power/domain_governor.c

···
 		 * known at this point anyway).
 		 */
 		constraint_ns = dev_pm_qos_read_value(dev);
-		if (constraint_ns > 0)
-			constraint_ns *= NSEC_PER_USEC;
+		constraint_ns *= NSEC_PER_USEC;
 	}
 
-	/* 0 means "no constraint" */
-	if (constraint_ns == 0)
-		return 0;
-
-	if (constraint_ns < *constraint_ns_p || *constraint_ns_p == 0)
+	if (constraint_ns < *constraint_ns_p)
 		*constraint_ns_p = constraint_ns;
 
 	return 0;
···
 	}
 	td->constraint_changed = false;
 	td->cached_suspend_ok = false;
-	td->effective_constraint_ns = -1;
+	td->effective_constraint_ns = 0;
 	constraint_ns = __dev_pm_qos_read_value(dev);
 
 	spin_unlock_irqrestore(&dev->power.lock, flags);
 
-	if (constraint_ns < 0)
+	if (constraint_ns == 0)
 		return false;
 
 	constraint_ns *= NSEC_PER_USEC;
···
 		device_for_each_child(dev, &constraint_ns,
 				      dev_update_qos_constraint);
 
-	if (constraint_ns == 0) {
+	if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS) {
 		/* "No restriction", so the device is allowed to suspend. */
-		td->effective_constraint_ns = 0;
+		td->effective_constraint_ns = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS;
 		td->cached_suspend_ok = true;
-	} else if (constraint_ns < 0) {
+	} else if (constraint_ns == 0) {
 		/*
 		 * This triggers if one of the children that don't belong to a
-		 * domain has a negative PM QoS constraint and it's better not
-		 * to suspend then.  effective_constraint_ns is negative already
-		 * and cached_suspend_ok is false, so bail out.
+		 * domain has a zero PM QoS constraint and it's better not to
+		 * suspend then.  effective_constraint_ns is zero already and
+		 * cached_suspend_ok is false, so bail out.
 		 */
 		return false;
 	} else {
 		constraint_ns -= td->suspend_latency_ns +
 				td->resume_latency_ns;
 		/*
-		 * effective_constraint_ns is negative already and
-		 * cached_suspend_ok is false, so if the computed value is not
-		 * positive, return right away.
+		 * effective_constraint_ns is zero already and cached_suspend_ok
+		 * is false, so if the computed value is not positive, return
+		 * right away.
 		 */
 		if (constraint_ns <= 0)
 			return false;
···
 		td = &to_gpd_data(pdd)->td;
 		constraint_ns = td->effective_constraint_ns;
 		/*
-		 * Negative values mean "no suspend at all" and this runs only
-		 * when all devices in the domain are suspended, so it must be
-		 * 0 at least.
-		 *
-		 * 0 means "no constraint"
+		 * Zero means "no suspend at all" and this runs only when all
+		 * devices in the domain are suspended, so it must be positive.
 		 */
-		if (constraint_ns == 0)
+		if (constraint_ns == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS)
 			continue;
 
 		if (constraint_ns <= off_on_time_ns)

drivers/base/power/qos.c

···
 
 	switch(req->type) {
 	case DEV_PM_QOS_RESUME_LATENCY:
+		if (WARN_ON(action != PM_QOS_REMOVE_REQ && value < 0))
+			value = 0;
+
 		ret = pm_qos_update_target(&qos->resume_latency,
 					   &req->data.pnode, action, value);
 		break;
···
 	plist_head_init(&c->list);
 	c->target_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
 	c->default_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
-	c->no_constraint_value = PM_QOS_RESUME_LATENCY_DEFAULT_VALUE;
+	c->no_constraint_value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
 	c->type = PM_QOS_MIN;
 	c->notifiers = n;
 

drivers/base/power/runtime.c

···
 	    || (dev->power.request_pending
 			&& dev->power.request == RPM_REQ_RESUME))
 		retval = -EAGAIN;
-	else if (__dev_pm_qos_read_value(dev) < 0)
+	else if (__dev_pm_qos_read_value(dev) == 0)
 		retval = -EPERM;
 	else if (dev->power.runtime_status == RPM_SUSPENDED)
 		retval = 1;

drivers/base/power/sysfs.c

···
 					  struct device_attribute *attr,
 					  char *buf)
 {
-	return sprintf(buf, "%d\n", dev_pm_qos_requested_resume_latency(dev));
+	s32 value = dev_pm_qos_requested_resume_latency(dev);
+
+	if (value == 0)
+		return sprintf(buf, "n/a\n");
+	else if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+		value = 0;
+
+	return sprintf(buf, "%d\n", value);
 }
 
 static ssize_t pm_qos_resume_latency_store(struct device *dev,
···
 	s32 value;
 	int ret;
 
-	if (kstrtos32(buf, 0, &value))
-		return -EINVAL;
+	if (!kstrtos32(buf, 0, &value)) {
+		/*
+		 * Prevent users from writing negative or "no constraint" values
+		 * directly.
+		 */
+		if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
+			return -EINVAL;
 
-	if (value < 0)
+		if (value == 0)
+			value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+	} else if (!strcmp(buf, "n/a") || !strcmp(buf, "n/a\n")) {
+		value = 0;
+	} else {
 		return -EINVAL;
+	}
 
 	ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req,
 					value);

drivers/cpuidle/governors/menu.c

···
 		data->needs_update = 0;
 	}
 
-	/* resume_latency is 0 means no restriction */
-	if (resume_latency && resume_latency < latency_req)
+	if (resume_latency < latency_req &&
+	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
 		latency_req = resume_latency;
 
 	/* Special case when user has set very strict latency requirement */

include/linux/pm_qos.h

···
 	PM_QOS_FLAGS_ALL,
 };
 
-#define PM_QOS_DEFAULT_VALUE -1
+#define PM_QOS_DEFAULT_VALUE	(-1)
+#define PM_QOS_LATENCY_ANY	S32_MAX
+#define PM_QOS_LATENCY_ANY_NS	((s64)PM_QOS_LATENCY_ANY * NSEC_PER_USEC)
 
 #define PM_QOS_CPU_DMA_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_LAT_DEFAULT_VALUE	(2000 * USEC_PER_SEC)
 #define PM_QOS_NETWORK_THROUGHPUT_DEFAULT_VALUE	0
 #define PM_QOS_MEMORY_BANDWIDTH_DEFAULT_VALUE	0
-#define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE	0
+#define PM_QOS_RESUME_LATENCY_DEFAULT_VALUE	PM_QOS_LATENCY_ANY
+#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT	PM_QOS_LATENCY_ANY
+#define PM_QOS_RESUME_LATENCY_NO_CONSTRAINT_NS	PM_QOS_LATENCY_ANY_NS
 #define PM_QOS_LATENCY_TOLERANCE_DEFAULT_VALUE	0
 #define PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT	(-1)
-#define PM_QOS_LATENCY_ANY			((s32)(~(__u32)0 >> 1))
 
 #define PM_QOS_FLAG_NO_POWER_OFF	(1 << 0)
 
···
 static inline s32 dev_pm_qos_raw_read_value(struct device *dev)
 {
 	return IS_ERR_OR_NULL(dev->power.qos) ?
-		0 : pm_qos_read_value(&dev->power.qos->resume_latency);
+		PM_QOS_RESUME_LATENCY_NO_CONSTRAINT :
+		pm_qos_read_value(&dev->power.qos->resume_latency);
 }
 #else
 static inline enum pm_qos_flags_status __dev_pm_qos_flags(struct device *dev,
···
 							s32 mask)
 			{ return PM_QOS_FLAGS_UNDEFINED; }
 static inline s32 __dev_pm_qos_read_value(struct device *dev)
-			{ return 0; }
+			{ return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; }
 static inline s32 dev_pm_qos_read_value(struct device *dev)
-			{ return 0; }
+			{ return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; }
 static inline int dev_pm_qos_add_request(struct device *dev,
 					 struct dev_pm_qos_request *req,
 					 enum dev_pm_qos_req_type type,
···
 			{ return 0; }
 static inline void dev_pm_qos_hide_latency_tolerance(struct device *dev) {}
 
-static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev) { return 0; }
+static inline s32 dev_pm_qos_requested_resume_latency(struct device *dev)
+{
+	return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+}
 static inline s32 dev_pm_qos_requested_flags(struct device *dev) { return 0; }
-static inline s32 dev_pm_qos_raw_read_value(struct device *dev) { return 0; }
+static inline s32 dev_pm_qos_raw_read_value(struct device *dev)
+{
+	return PM_QOS_RESUME_LATENCY_NO_CONSTRAINT;
+}
 #endif
 
 #endif