Power management fixes for 3.13-rc3

- cpufreq regression fix from Bjørn Mork restoring the pre-3.12
    behavior of the framework during system suspend/hibernation to
    avoid garbage sysfs files from being left behind in case of a
    suspend error.
 
  - PNP regression fix to restore the correct states of devices after
    resume from hibernation broken in 3.12.  From Dmitry Torokhov.
 
  - cpuidle fix to prevent cpuidle device unregistration from crashing
    due to a NULL pointer dereference if cpuidle has been disabled
    from the kernel command line.  From Konrad Rzeszutek Wilk.
 
  - intel_idle fix for the C6 state definition on Intel Avoton/Rangeley
    processors from Arne Bockholdt.
 
  - Power capping framework fix to make the energy_uj sysfs attribute
    work in accordance with the documentation.  From Srinivas Pandruvada.
 
  - epoll fix to make it ignore the EPOLLWAKEUP flag if the kernel has
    been compiled with CONFIG_PM_SLEEP unset (in which case that flag
    should not have any effect).  From Amit Pundir.
 
  - cpufreq fix to prevent governor sysfs files from being lost over
    system suspend/resume in some (arguably unusual) situations.  From
    Viresh Kumar.
 
 /
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v2.0.19 (GNU/Linux)
 
 iQIcBAABCAAGBQJSoTE5AAoJEILEb/54YlRxh/sP/jFZhLTc8g4MC3XzhguuROzT
 u0Pu9VJVfACqz8LyiCOtfOvvb2EPV7VSq7qYqszL5y9Dn5gwIHvQMMBK2PjZ4cc2
 MtSiw02Bk/DEESXYOjt++n5ja/0lc05CtJTlb3uoJXBOCqp3cMrvW7+QqnLbEfbG
 S+TcPFBr+4Owt/J7r2Z2JBYGZ6NbVol/x1hAFjiM+rBan6UGw7uNcg2LgQrVHcs4
 S1Cm6lsJTwRcSiswvJv9/C+ML9Z/1gYYUyu7ijQnGdbNUolyzHY6AxLWZdnSkAQO
 s8JVDRKy9+V44LtnWSENnJNftjlOoXWcZRJxvDePyM3dVpxESBa8Z/AxYWwCcmcB
 e4rsgm/WOF86DMhRu+gfeTF+1OkU7KhuPhbXskbw+JDcZKCui2FP/xti6IAaTsU/
 9M30/VeOpD1UBqckLnDTGcsFif7hVZ9LOHH5wK8OctjyaTMfUYtPd7WxfTQCpcSc
 1M0NQapwfXHASmPmMW4SszAaeduecUdgXU1epOPx0EpOMQhvuLeENJBgVC5uu1cA
 KAQ7suOx9ReS3slso8lpTlTEw2rsDPRuiHcF3hv7YpklNXV2jvtxsl4upHT5VN2t
 3L59Unq8vY2lt3SdzWMypaAquphc3Te5woYoFwgsSPfw40Kr+jg+oUtO6IHqM/ga
 OATUkTffzp+Rp3pg036Y
 =gHBV
 -----END PGP SIGNATURE-----

Merge tag 'pm-3.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management fixes from Rafael Wysocki:

 - cpufreq regression fix from Bjørn Mork restoring the pre-3.12
   behavior of the framework during system suspend/hibernation to avoid
   garbage sysfs files from being left behind in case of a suspend error

 - PNP regression fix to restore the correct states of devices after
   resume from hibernation broken in 3.12.  From Dmitry Torokhov.

 - cpuidle fix to prevent cpuidle device unregistration from crashing
   due to a NULL pointer dereference if cpuidle has been disabled from
   the kernel command line.  From Konrad Rzeszutek Wilk.

 - intel_idle fix for the C6 state definition on Intel Avoton/Rangeley
   processors from Arne Bockholdt.

 - Power capping framework fix to make the energy_uj sysfs attribute
   work in accordance with the documentation.  From Srinivas Pandruvada.

 - epoll fix to make it ignore the EPOLLWAKEUP flag if the kernel has
   been compiled with CONFIG_PM_SLEEP unset (in which case that flag
   should not have any effect).  From Amit Pundir.

 - cpufreq fix to prevent governor sysfs files from being lost over
   system suspend/resume in some (arguably unusual) situations.  From
   Viresh Kumar.

* tag 'pm-3.13-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm:
  PowerCap: Fix mode for energy counter
  PNP: fix restoring devices after hibernation
  cpuidle: Check for dev before deregistering it.
  epoll: drop EPOLLWAKEUP if PM_SLEEP is disabled
  cpufreq: fix garbage kobjects on errors during suspend/resume
  cpufreq: suspend governors on system suspend/hibernate
  intel_idle: Fixed C6 state on Avoton/Rangeley processors

drivers/base/power/main.c

@@ -29,6 +29,7 @@
 #include <linux/async.h>
 #include <linux/suspend.h>
 #include <trace/events/power.h>
+#include <linux/cpufreq.h>
 #include <linux/cpuidle.h>
 #include <linux/timer.h>
 
@@ -540,6 +541,7 @@ static void dpm_resume_noirq(pm_message_t state)
 	dpm_show_time(starttime, state, "noirq");
 	resume_device_irqs();
 	cpuidle_resume();
+	cpufreq_resume();
 }
 
 /**
@@ -955,6 +957,7 @@ static int dpm_suspend_noirq(pm_message_t state)
 	ktime_t starttime = ktime_get();
 	int error = 0;
 
+	cpufreq_suspend();
 	cpuidle_pause();
 	suspend_device_irqs();
 	mutex_lock(&dpm_list_mtx);

drivers/cpufreq/cpufreq.c

@@ -26,6 +26,7 @@
 #include <linux/module.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/suspend.h>
 #include <linux/syscore_ops.h>
 #include <linux/tick.h>
 #include <trace/events/power.h>
@@ -47,6 +48,9 @@ static LIST_HEAD(cpufreq_policy_list);
 static DEFINE_PER_CPU(char[CPUFREQ_NAME_LEN], cpufreq_cpu_governor);
 #endif
 
+/* Flag to suspend/resume CPUFreq governors */
+static bool cpufreq_suspended;
+
 static inline bool has_target(void)
 {
 	return cpufreq_driver->target_index || cpufreq_driver->target;
@@ -1462,6 +1466,41 @@ static struct subsys_interface cpufreq_interface = {
 	.remove_dev	= cpufreq_remove_dev,
 };
 
+void cpufreq_suspend(void)
+{
+	struct cpufreq_policy *policy;
+
+	if (!has_target())
+		return;
+
+	pr_debug("%s: Suspending Governors\n", __func__);
+
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list)
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_STOP))
+			pr_err("%s: Failed to stop governor for policy: %p\n",
+				__func__, policy);
+
+	cpufreq_suspended = true;
+}
+
+void cpufreq_resume(void)
+{
+	struct cpufreq_policy *policy;
+
+	if (!has_target())
+		return;
+
+	pr_debug("%s: Resuming Governors\n", __func__);
+
+	cpufreq_suspended = false;
+
+	list_for_each_entry(policy, &cpufreq_policy_list, policy_list)
+		if (__cpufreq_governor(policy, CPUFREQ_GOV_START)
+		    || __cpufreq_governor(policy, CPUFREQ_GOV_LIMITS))
+			pr_err("%s: Failed to start governor for policy: %p\n",
+				__func__, policy);
+}
+
 /**
  * cpufreq_bp_suspend - Prepare the boot CPU for system suspend.
  *
@@ -1764,6 +1803,10 @@ static int __cpufreq_governor(struct cpufreq_policy *policy,
 	struct cpufreq_governor *gov = NULL;
 #endif
 
+	/* Don't start any governor operations if we are entering suspend */
+	if (cpufreq_suspended)
+		return 0;
+
 	if (policy->governor->max_transition_latency &&
 	    policy->cpuinfo.transition_latency >
 	    policy->governor->max_transition_latency) {
@@ -2076,9 +2119,6 @@ static int cpufreq_cpu_callback(struct notifier_block *nfb,
 	dev = get_cpu_device(cpu);
 	if (dev) {
 
-		if (action & CPU_TASKS_FROZEN)
-			frozen = true;
-
 		switch (action & ~CPU_TASKS_FROZEN) {
 		case CPU_ONLINE:
 			__cpufreq_add_dev(dev, NULL, frozen);

drivers/cpuidle/cpuidle.c

@@ -400,7 +400,7 @@ EXPORT_SYMBOL_GPL(cpuidle_register_device);
  */
 void cpuidle_unregister_device(struct cpuidle_device *dev)
 {
-	if (dev->registered == 0)
+	if (!dev || dev->registered == 0)
 		return;
 
 	cpuidle_pause_and_lock();

drivers/idle/intel_idle.c

@@ -329,7 +329,7 @@ static struct cpuidle_state atom_cstates[] __initdata = {
 	{
 		.enter = NULL }
 };
-static struct cpuidle_state avn_cstates[CPUIDLE_STATE_MAX] = {
+static struct cpuidle_state avn_cstates[] __initdata = {
 	{
 		.name = "C1-AVN",
 		.desc = "MWAIT 0x00",
@@ -340,7 +340,7 @@ static struct cpuidle_state avn_cstates[CPUIDLE_STATE_MAX] = {
 	{
 		.name = "C6-AVN",
 		.desc = "MWAIT 0x51",
-		.flags = MWAIT2flg(0x58) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
+		.flags = MWAIT2flg(0x51) | CPUIDLE_FLAG_TIME_VALID | CPUIDLE_FLAG_TLB_FLUSHED,
 		.exit_latency = 15,
 		.target_residency = 45,
 		.enter = &intel_idle },

drivers/pnp/driver.c

@@ -197,6 +197,11 @@ static int pnp_bus_freeze(struct device *dev)
 	return __pnp_bus_suspend(dev, PMSG_FREEZE);
 }
 
+static int pnp_bus_poweroff(struct device *dev)
+{
+	return __pnp_bus_suspend(dev, PMSG_HIBERNATE);
+}
+
 static int pnp_bus_resume(struct device *dev)
 {
 	struct pnp_dev *pnp_dev = to_pnp_dev(dev);
@@ -234,9 +239,14 @@ static int pnp_bus_resume(struct device *dev)
 }
 
 static const struct dev_pm_ops pnp_bus_dev_pm_ops = {
+	/* Suspend callbacks */
 	.suspend = pnp_bus_suspend,
-	.freeze = pnp_bus_freeze,
 	.resume = pnp_bus_resume,
+	/* Hibernate callbacks */
+	.freeze = pnp_bus_freeze,
+	.thaw = pnp_bus_resume,
+	.poweroff = pnp_bus_poweroff,
+	.restore = pnp_bus_resume,
 };
 
 struct bus_type pnp_bus_type = {

drivers/powercap/powercap_sys.c

@@ -377,9 +377,14 @@ static void create_power_zone_common_attributes(
 	if (power_zone->ops->get_max_energy_range_uj)
 		power_zone->zone_dev_attrs[count++] =
 					&dev_attr_max_energy_range_uj.attr;
-	if (power_zone->ops->get_energy_uj)
+	if (power_zone->ops->get_energy_uj) {
+		if (power_zone->ops->reset_energy_uj)
+			dev_attr_energy_uj.attr.mode = S_IWUSR | S_IRUGO;
+		else
+			dev_attr_energy_uj.attr.mode = S_IRUGO;
 		power_zone->zone_dev_attrs[count++] =
 					&dev_attr_energy_uj.attr;
+	}
 	if (power_zone->ops->get_power_uw)
 		power_zone->zone_dev_attrs[count++] =
 					&dev_attr_power_uw.attr;

fs/eventpoll.c

@@ -1852,8 +1852,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 		goto error_tgt_fput;
 
 	/* Check if EPOLLWAKEUP is allowed */
-	if ((epds.events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
-		epds.events &= ~EPOLLWAKEUP;
+	ep_take_care_of_epollwakeup(&epds);
 
 	/*
 	 * We have to check that the file structure underneath the file descriptor

include/linux/cpufreq.h

@@ -280,6 +280,14 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy)
 			policy->cpuinfo.max_freq);
 }
 
+#ifdef CONFIG_CPU_FREQ
+void cpufreq_suspend(void);
+void cpufreq_resume(void);
+#else
+static inline void cpufreq_suspend(void) {}
+static inline void cpufreq_resume(void) {}
+#endif
+
 /*********************************************************************
  *                     CPUFREQ NOTIFIER INTERFACE                    *
  *********************************************************************/

include/uapi/linux/eventpoll.h

@@ -61,5 +61,16 @@ struct epoll_event {
 	__u64 data;
 } EPOLL_PACKED;
 
-
+#ifdef CONFIG_PM_SLEEP
+static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev)
+{
+	if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND))
+		epev->events &= ~EPOLLWAKEUP;
+}
+#else
+static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev)
+{
+	epev->events &= ~EPOLLWAKEUP;
+}
+#endif
 #endif /* _UAPI_LINUX_EVENTPOLL_H */