Merge branch 'pm-cpuidle'

* pm-cpuidle:
  cpuidle-haltpoll: Enable kvm guest polling when dedicated physical CPUs are available
  cpuidle-haltpoll: do not set an owner to allow modunload
  cpuidle-haltpoll: return -ENODEV on modinit failure
  cpuidle-haltpoll: set haltpoll as preferred governor
  cpuidle: allow governor switch on cpuidle_register_driver()
  powercap: idle_inject: Use higher resolution for idle injection
  cpuidle: play_idle: Increase the resolution to usec
  cpuidle-haltpoll: vcpu hotplug support
  cpuidle: teo: Get rid of redundant check in teo_update()
  cpuidle: teo: Allow tick to be stopped if PM QoS is used
  cpuidle: menu: Allow tick to be stopped if PM QoS is used
  cpuidle: header file stubs must be "static inline"
  cpuidle-haltpoll: disable host side polling when kvm virtualized
  cpuidle: add haltpoll governor
  governors: unify last_state_idx
  cpuidle: add poll_limit_ns to cpuidle_device structure
  add cpuidle-haltpoll driver

Documentation/virtual/guest-halt-polling.txt

@@ -0,0 +1,78 @@
+Guest halt polling
+==================
+
+The cpuidle_haltpoll driver, with the haltpoll governor, allows
+the guest vcpus to poll for a specified amount of time before
+halting.
+This provides the following benefits to host side polling:
+
+	1) The POLL flag is set while polling is performed, which allows
+	   a remote vCPU to avoid sending an IPI (and the associated
+	   cost of handling the IPI) when performing a wakeup.
+
+	2) The VM-exit cost can be avoided.
+
+The downside of guest side polling is that polling is performed
+even with other runnable tasks in the host.
+
+The basic logic as follows: A global value, guest_halt_poll_ns,
+is configured by the user, indicating the maximum amount of
+time polling is allowed. This value is fixed.
+
+Each vcpu has an adjustable guest_halt_poll_ns
+("per-cpu guest_halt_poll_ns"), which is adjusted by the algorithm
+in response to events (explained below).
+
+Module Parameters
+=================
+
+The haltpoll governor has 5 tunable module parameters:
+
+1) guest_halt_poll_ns:
+Maximum amount of time, in nanoseconds, that polling is
+performed before halting.
+
+Default: 200000
+
+2) guest_halt_poll_shrink:
+Division factor used to shrink per-cpu guest_halt_poll_ns when
+wakeup event occurs after the global guest_halt_poll_ns.
+
+Default: 2
+
+3) guest_halt_poll_grow:
+Multiplication factor used to grow per-cpu guest_halt_poll_ns
+when event occurs after per-cpu guest_halt_poll_ns
+but before global guest_halt_poll_ns.
+
+Default: 2
+
+4) guest_halt_poll_grow_start:
+The per-cpu guest_halt_poll_ns eventually reaches zero
+in case of an idle system. This value sets the initial
+per-cpu guest_halt_poll_ns when growing. This can
+be increased from 10000, to avoid misses during the initial
+growth stage:
+
+10k, 20k, 40k, ... (example assumes guest_halt_poll_grow=2).
+
+Default: 50000
+
+5) guest_halt_poll_allow_shrink:
+
+Bool parameter which allows shrinking. Set to N
+to avoid it (per-cpu guest_halt_poll_ns will remain
+high once achieves global guest_halt_poll_ns value).
+
+Default: Y
+
+The module parameters can be set from the debugfs files in:
+
+	/sys/module/haltpoll/parameters/
+
+Further Notes
+=============
+
+- Care should be taken when setting the guest_halt_poll_ns parameter as a
+large value has the potential to drive the cpu usage to 100% on a machine which
+would be almost entirely idle otherwise.

arch/x86/Kconfig

@@ -794,6 +794,7 @@ config KVM_GUEST
 	bool "KVM Guest support (including kvmclock)"
 	depends on PARAVIRT
 	select PARAVIRT_CLOCK
+	select ARCH_CPUIDLE_HALTPOLL
 	default y
 	---help---
 	  This option enables various optimizations for running under the KVM
@@ -802,6 +803,12 @@ config KVM_GUEST
 	  underlying device model, the host provides the guest with
 	  timing infrastructure such as time of day, and system time
 
+config ARCH_CPUIDLE_HALTPOLL
+        def_bool n
+        prompt "Disable host haltpoll when loading haltpoll driver"
+        help
+	  If virtualized under KVM, disable host haltpoll.
+
 config PVH
 	bool "Support for running PVH guests"
 	---help---

arch/x86/include/asm/cpuidle_haltpoll.h

@@ -0,0 +1,8 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ARCH_HALTPOLL_H
+#define _ARCH_HALTPOLL_H
+
+void arch_haltpoll_enable(unsigned int cpu);
+void arch_haltpoll_disable(unsigned int cpu);
+
+#endif

arch/x86/kernel/kvm.c

@@ -705,6 +705,7 @@ unsigned int kvm_arch_para_hints(void)
 {
 	return cpuid_edx(kvm_cpuid_base() | KVM_CPUID_FEATURES);
 }
+EXPORT_SYMBOL_GPL(kvm_arch_para_hints);
 
 static uint32_t __init kvm_detect(void)
 {
@@ -867,3 +868,39 @@ void __init kvm_spinlock_init(void)
 }
 
 #endif	/* CONFIG_PARAVIRT_SPINLOCKS */
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+
+static void kvm_disable_host_haltpoll(void *i)
+{
+	wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+}
+
+static void kvm_enable_host_haltpoll(void *i)
+{
+	wrmsrl(MSR_KVM_POLL_CONTROL, 1);
+}
+
+void arch_haltpoll_enable(unsigned int cpu)
+{
+	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL)) {
+		pr_err_once("kvm: host does not support poll control\n");
+		pr_err_once("kvm: host upgrade recommended\n");
+		return;
+	}
+
+	/* Enable guest halt poll disables host halt poll */
+	smp_call_function_single(cpu, kvm_disable_host_haltpoll, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_enable);
+
+void arch_haltpoll_disable(unsigned int cpu)
+{
+	if (!kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
+		return;
+
+	/* Enable guest halt poll disables host halt poll */
+	smp_call_function_single(cpu, kvm_enable_host_haltpoll, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(arch_haltpoll_disable);
+#endif

arch/x86/kernel/process.c

@@ -580,7 +580,7 @@ void __cpuidle default_idle(void)
 	safe_halt();
 	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
 }
-#ifdef CONFIG_APM_MODULE
+#if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
 #endif
 

drivers/cpuidle/Kconfig

@@ -33,6 +33,17 @@ config CPU_IDLE_GOV_TEO
 	  Some workloads benefit from using it and it generally should be safe
 	  to use.  Say Y here if you are not happy with the alternatives.
 
+config CPU_IDLE_GOV_HALTPOLL
+	bool "Haltpoll governor (for virtualized systems)"
+	depends on KVM_GUEST
+	help
+	  This governor implements haltpoll idle state selection, to be
+	  used in conjunction with the haltpoll cpuidle driver, allowing
+	  for polling for a certain amount of time before entering idle
+	  state.
+
+	  Some virtualized workloads benefit from using it.
+
 config DT_IDLE_STATES
 	bool
 
@@ -51,6 +62,15 @@ depends on PPC
 source "drivers/cpuidle/Kconfig.powerpc"
 endmenu
 
+config HALTPOLL_CPUIDLE
+       tristate "Halt poll cpuidle driver"
+       depends on X86 && KVM_GUEST
+       default y
+       help
+         This option enables halt poll cpuidle driver, which allows to poll
+         before halting in the guest (more efficient than polling in the
+         host via halt_poll_ns for some scenarios).
+
 endif
 
 config ARCH_NEEDS_CPU_IDLE_COUPLED

drivers/cpuidle/Makefile

@@ -7,6 +7,7 @@ obj-y += cpuidle.o driver.o governor.o sysfs.o governors/
 obj-$(CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED) += coupled.o
 obj-$(CONFIG_DT_IDLE_STATES)		  += dt_idle_states.o
 obj-$(CONFIG_ARCH_HAS_CPU_RELAX)	  += poll_state.o
+obj-$(CONFIG_HALTPOLL_CPUIDLE)		  += cpuidle-haltpoll.o
 
 ##################################################################################
 # ARM SoC drivers

drivers/cpuidle/cpuidle-haltpoll.c

@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * cpuidle driver for haltpoll governor.
+ *
+ * Copyright 2019 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ */
+
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/cpuidle.h>
+#include <linux/module.h>
+#include <linux/sched/idle.h>
+#include <linux/kvm_para.h>
+#include <linux/cpuidle_haltpoll.h>
+
+static struct cpuidle_device __percpu *haltpoll_cpuidle_devices;
+static enum cpuhp_state haltpoll_hp_state;
+
+static int default_enter_idle(struct cpuidle_device *dev,
+			      struct cpuidle_driver *drv, int index)
+{
+	if (current_clr_polling_and_test()) {
+		local_irq_enable();
+		return index;
+	}
+	default_idle();
+	return index;
+}
+
+static struct cpuidle_driver haltpoll_driver = {
+	.name = "haltpoll",
+	.governor = "haltpoll",
+	.states = {
+		{ /* entry 0 is for polling */ },
+		{
+			.enter			= default_enter_idle,
+			.exit_latency		= 1,
+			.target_residency	= 1,
+			.power_usage		= -1,
+			.name			= "haltpoll idle",
+			.desc			= "default architecture idle",
+		},
+	},
+	.safe_state_index = 0,
+	.state_count = 2,
+};
+
+static int haltpoll_cpu_online(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	dev = per_cpu_ptr(haltpoll_cpuidle_devices, cpu);
+	if (!dev->registered) {
+		dev->cpu = cpu;
+		if (cpuidle_register_device(dev)) {
+			pr_notice("cpuidle_register_device %d failed!\n", cpu);
+			return -EIO;
+		}
+		arch_haltpoll_enable(cpu);
+	}
+
+	return 0;
+}
+
+static int haltpoll_cpu_offline(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	dev = per_cpu_ptr(haltpoll_cpuidle_devices, cpu);
+	if (dev->registered) {
+		arch_haltpoll_disable(cpu);
+		cpuidle_unregister_device(dev);
+	}
+
+	return 0;
+}
+
+static void haltpoll_uninit(void)
+{
+	if (haltpoll_hp_state)
+		cpuhp_remove_state(haltpoll_hp_state);
+	cpuidle_unregister_driver(&haltpoll_driver);
+
+	free_percpu(haltpoll_cpuidle_devices);
+	haltpoll_cpuidle_devices = NULL;
+}
+
+static int __init haltpoll_init(void)
+{
+	int ret;
+	struct cpuidle_driver *drv = &haltpoll_driver;
+
+	cpuidle_poll_state_init(drv);
+
+	if (!kvm_para_available() ||
+		!kvm_para_has_hint(KVM_HINTS_REALTIME))
+		return -ENODEV;
+
+	ret = cpuidle_register_driver(drv);
+	if (ret < 0)
+		return ret;
+
+	haltpoll_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+	if (haltpoll_cpuidle_devices == NULL) {
+		cpuidle_unregister_driver(drv);
+		return -ENOMEM;
+	}
+
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "cpuidle/haltpoll:online",
+				haltpoll_cpu_online, haltpoll_cpu_offline);
+	if (ret < 0) {
+		haltpoll_uninit();
+	} else {
+		haltpoll_hp_state = ret;
+		ret = 0;
+	}
+
+	return ret;
+}
+
+static void __exit haltpoll_exit(void)
+{
+	haltpoll_uninit();
+}
+
+module_init(haltpoll_init);
+module_exit(haltpoll_exit);
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Marcelo Tosatti <mtosatti@redhat.com>");

drivers/cpuidle/cpuidle.c

@@ -361,6 +361,36 @@ void cpuidle_reflect(struct cpuidle_device *dev, int index)
 		cpuidle_curr_governor->reflect(dev, index);
 }
 
+/**
+ * cpuidle_poll_time - return amount of time to poll for,
+ * governors can override dev->poll_limit_ns if necessary
+ *
+ * @drv:   the cpuidle driver tied with the cpu
+ * @dev:   the cpuidle device
+ *
+ */
+u64 cpuidle_poll_time(struct cpuidle_driver *drv,
+		      struct cpuidle_device *dev)
+{
+	int i;
+	u64 limit_ns;
+
+	if (dev->poll_limit_ns)
+		return dev->poll_limit_ns;
+
+	limit_ns = TICK_NSEC;
+	for (i = 1; i < drv->state_count; i++) {
+		if (drv->states[i].disabled || dev->states_usage[i].disable)
+			continue;
+
+		limit_ns = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
+	}
+
+	dev->poll_limit_ns = limit_ns;
+
+	return dev->poll_limit_ns;
+}
+
 /**
  * cpuidle_install_idle_handler - installs the cpuidle idle loop handler
  */

drivers/cpuidle/cpuidle.h

@@ -9,6 +9,7 @@
 /* For internal use only */
 extern char param_governor[];
 extern struct cpuidle_governor *cpuidle_curr_governor;
+extern struct cpuidle_governor *cpuidle_prev_governor;
 extern struct list_head cpuidle_governors;
 extern struct list_head cpuidle_detected_devices;
 extern struct mutex cpuidle_lock;
@@ -22,6 +23,7 @@ extern void cpuidle_install_idle_handler(void);
 extern void cpuidle_uninstall_idle_handler(void);
 
 /* governors */
+extern struct cpuidle_governor *cpuidle_find_governor(const char *str);
 extern int cpuidle_switch_governor(struct cpuidle_governor *gov);
 
 /* sysfs */

drivers/cpuidle/driver.c

@@ -254,12 +254,25 @@ static void __cpuidle_unregister_driver(struct cpuidle_driver *drv)
  */
 int cpuidle_register_driver(struct cpuidle_driver *drv)
 {
+	struct cpuidle_governor *gov;
 	int ret;
 
 	spin_lock(&cpuidle_driver_lock);
 	ret = __cpuidle_register_driver(drv);
 	spin_unlock(&cpuidle_driver_lock);
 
+	if (!ret && !strlen(param_governor) && drv->governor &&
+	    (cpuidle_get_driver() == drv)) {
+		mutex_lock(&cpuidle_lock);
+		gov = cpuidle_find_governor(drv->governor);
+		if (gov) {
+			cpuidle_prev_governor = cpuidle_curr_governor;
+			if (cpuidle_switch_governor(gov) < 0)
+				cpuidle_prev_governor = NULL;
+		}
+		mutex_unlock(&cpuidle_lock);
+	}
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpuidle_register_driver);
@@ -274,9 +287,21 @@ EXPORT_SYMBOL_GPL(cpuidle_register_driver);
  */
 void cpuidle_unregister_driver(struct cpuidle_driver *drv)
 {
+	bool enabled = (cpuidle_get_driver() == drv);
+
 	spin_lock(&cpuidle_driver_lock);
 	__cpuidle_unregister_driver(drv);
 	spin_unlock(&cpuidle_driver_lock);
+
+	if (!enabled)
+		return;
+
+	mutex_lock(&cpuidle_lock);
+	if (cpuidle_prev_governor) {
+		if (!cpuidle_switch_governor(cpuidle_prev_governor))
+			cpuidle_prev_governor = NULL;
+	}
+	mutex_unlock(&cpuidle_lock);
 }
 EXPORT_SYMBOL_GPL(cpuidle_unregister_driver);
 

drivers/cpuidle/governor.c

@@ -20,14 +20,15 @@ char param_governor[CPUIDLE_NAME_LEN];
 
 LIST_HEAD(cpuidle_governors);
 struct cpuidle_governor *cpuidle_curr_governor;
+struct cpuidle_governor *cpuidle_prev_governor;
 
 /**
- * __cpuidle_find_governor - finds a governor of the specified name
+ * cpuidle_find_governor - finds a governor of the specified name
  * @str: the name
  *
  * Must be called with cpuidle_lock acquired.
  */
-static struct cpuidle_governor * __cpuidle_find_governor(const char *str)
+struct cpuidle_governor *cpuidle_find_governor(const char *str)
 {
 	struct cpuidle_governor *gov;
 
@@ -87,7 +88,7 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
 		return -ENODEV;
 
 	mutex_lock(&cpuidle_lock);
-	if (__cpuidle_find_governor(gov->name) == NULL) {
+	if (cpuidle_find_governor(gov->name) == NULL) {
 		ret = 0;
 		list_add_tail(&gov->governor_list, &cpuidle_governors);
 		if (!cpuidle_curr_governor ||

drivers/cpuidle/governors/Makefile

@@ -6,3 +6,4 @@
 obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o
 obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o
 obj-$(CONFIG_CPU_IDLE_GOV_TEO) += teo.o
+obj-$(CONFIG_CPU_IDLE_GOV_HALTPOLL) += haltpoll.o

drivers/cpuidle/governors/haltpoll.c

@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * haltpoll.c - haltpoll idle governor
+ *
+ * Copyright 2019 Red Hat, Inc. and/or its affiliates.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Authors: Marcelo Tosatti <mtosatti@redhat.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/cpuidle.h>
+#include <linux/time.h>
+#include <linux/ktime.h>
+#include <linux/hrtimer.h>
+#include <linux/tick.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <linux/kvm_para.h>
+
+static unsigned int guest_halt_poll_ns __read_mostly = 200000;
+module_param(guest_halt_poll_ns, uint, 0644);
+
+/* division factor to shrink halt_poll_ns */
+static unsigned int guest_halt_poll_shrink __read_mostly = 2;
+module_param(guest_halt_poll_shrink, uint, 0644);
+
+/* multiplication factor to grow per-cpu poll_limit_ns */
+static unsigned int guest_halt_poll_grow __read_mostly = 2;
+module_param(guest_halt_poll_grow, uint, 0644);
+
+/* value in us to start growing per-cpu halt_poll_ns */
+static unsigned int guest_halt_poll_grow_start __read_mostly = 50000;
+module_param(guest_halt_poll_grow_start, uint, 0644);
+
+/* allow shrinking guest halt poll */
+static bool guest_halt_poll_allow_shrink __read_mostly = true;
+module_param(guest_halt_poll_allow_shrink, bool, 0644);
+
+/**
+ * haltpoll_select - selects the next idle state to enter
+ * @drv: cpuidle driver containing state data
+ * @dev: the CPU
+ * @stop_tick: indication on whether or not to stop the tick
+ */
+static int haltpoll_select(struct cpuidle_driver *drv,
+			   struct cpuidle_device *dev,
+			   bool *stop_tick)
+{
+	int latency_req = cpuidle_governor_latency_req(dev->cpu);
+
+	if (!drv->state_count || latency_req == 0) {
+		*stop_tick = false;
+		return 0;
+	}
+
+	if (dev->poll_limit_ns == 0)
+		return 1;
+
+	/* Last state was poll? */
+	if (dev->last_state_idx == 0) {
+		/* Halt if no event occurred on poll window */
+		if (dev->poll_time_limit == true)
+			return 1;
+
+		*stop_tick = false;
+		/* Otherwise, poll again */
+		return 0;
+	}
+
+	*stop_tick = false;
+	/* Last state was halt: poll */
+	return 0;
+}
+
+static void adjust_poll_limit(struct cpuidle_device *dev, unsigned int block_us)
+{
+	unsigned int val;
+	u64 block_ns = block_us*NSEC_PER_USEC;
+
+	/* Grow cpu_halt_poll_us if
+	 * cpu_halt_poll_us < block_ns < guest_halt_poll_us
+	 */
+	if (block_ns > dev->poll_limit_ns && block_ns <= guest_halt_poll_ns) {
+		val = dev->poll_limit_ns * guest_halt_poll_grow;
+
+		if (val < guest_halt_poll_grow_start)
+			val = guest_halt_poll_grow_start;
+		if (val > guest_halt_poll_ns)
+			val = guest_halt_poll_ns;
+
+		dev->poll_limit_ns = val;
+	} else if (block_ns > guest_halt_poll_ns &&
+		   guest_halt_poll_allow_shrink) {
+		unsigned int shrink = guest_halt_poll_shrink;
+
+		val = dev->poll_limit_ns;
+		if (shrink == 0)
+			val = 0;
+		else
+			val /= shrink;
+		dev->poll_limit_ns = val;
+	}
+}
+
+/**
+ * haltpoll_reflect - update variables and update poll time
+ * @dev: the CPU
+ * @index: the index of actual entered state
+ */
+static void haltpoll_reflect(struct cpuidle_device *dev, int index)
+{
+	dev->last_state_idx = index;
+
+	if (index != 0)
+		adjust_poll_limit(dev, dev->last_residency);
+}
+
+/**
+ * haltpoll_enable_device - scans a CPU's states and does setup
+ * @drv: cpuidle driver
+ * @dev: the CPU
+ */
+static int haltpoll_enable_device(struct cpuidle_driver *drv,
+				  struct cpuidle_device *dev)
+{
+	dev->poll_limit_ns = 0;
+
+	return 0;
+}
+
+static struct cpuidle_governor haltpoll_governor = {
+	.name =			"haltpoll",
+	.rating =		9,
+	.enable =		haltpoll_enable_device,
+	.select =		haltpoll_select,
+	.reflect =		haltpoll_reflect,
+};
+
+static int __init init_haltpoll(void)
+{
+	if (kvm_para_available())
+		return cpuidle_register_governor(&haltpoll_governor);
+
+	return 0;
+}
+
+postcore_initcall(init_haltpoll);

drivers/cpuidle/governors/ladder.c

@@ -38,7 +38,6 @@ struct ladder_device_state {
 
 struct ladder_device {
 	struct ladder_device_state states[CPUIDLE_STATE_MAX];
-	int last_state_idx;
 };
 
 static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
@@ -49,12 +48,13 @@ static DEFINE_PER_CPU(struct ladder_device, ladder_devices);
  * @old_idx: the current state index
  * @new_idx: the new target state index
  */
-static inline void ladder_do_selection(struct ladder_device *ldev,
+static inline void ladder_do_selection(struct cpuidle_device *dev,
+				       struct ladder_device *ldev,
 				       int old_idx, int new_idx)
 {
 	ldev->states[old_idx].stats.promotion_count = 0;
 	ldev->states[old_idx].stats.demotion_count = 0;
-	ldev->last_state_idx = new_idx;
+	dev->last_state_idx = new_idx;
 }
 
 /**
@@ -68,13 +68,13 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	struct ladder_device_state *last_state;
-	int last_residency, last_idx = ldev->last_state_idx;
+	int last_residency, last_idx = dev->last_state_idx;
 	int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
 	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
-		ladder_do_selection(ldev, last_idx, 0);
+		ladder_do_selection(dev, ldev, last_idx, 0);
 		return 0;
 	}
 
@@ -91,7 +91,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 		last_state->stats.promotion_count++;
 		last_state->stats.demotion_count = 0;
 		if (last_state->stats.promotion_count >= last_state->threshold.promotion_count) {
-			ladder_do_selection(ldev, last_idx, last_idx + 1);
+			ladder_do_selection(dev, ldev, last_idx, last_idx + 1);
 			return last_idx + 1;
 		}
 	}
@@ -107,7 +107,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 			if (drv->states[i].exit_latency <= latency_req)
 				break;
 		}
-		ladder_do_selection(ldev, last_idx, i);
+		ladder_do_selection(dev, ldev, last_idx, i);
 		return i;
 	}
 
@@ -116,7 +116,7 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 		last_state->stats.demotion_count++;
 		last_state->stats.promotion_count = 0;
 		if (last_state->stats.demotion_count >= last_state->threshold.demotion_count) {
-			ladder_do_selection(ldev, last_idx, last_idx - 1);
+			ladder_do_selection(dev, ldev, last_idx, last_idx - 1);
 			return last_idx - 1;
 		}
 	}
@@ -139,7 +139,7 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
 	struct ladder_device_state *lstate;
 	struct cpuidle_state *state;
 
-	ldev->last_state_idx = first_idx;
+	dev->last_state_idx = first_idx;
 
 	for (i = first_idx; i < drv->state_count; i++) {
 		state = &drv->states[i];
@@ -167,9 +167,8 @@ static int ladder_enable_device(struct cpuidle_driver *drv,
  */
 static void ladder_reflect(struct cpuidle_device *dev, int index)
 {
-	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
 	if (index > 0)
-		ldev->last_state_idx = index;
+		dev->last_state_idx = index;
 }
 
 static struct cpuidle_governor ladder_governor = {

drivers/cpuidle/governors/menu.c

@@ -117,7 +117,6 @@
  */
 
 struct menu_device {
-	int		last_state_idx;
 	int             needs_update;
 	int             tick_wakeup;
 
@@ -302,9 +301,10 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	     !drv->states[0].disabled && !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.
+		 * it right away and keep the tick running if state[0] is a
+		 * polling one.
 		 */
-		*stop_tick = false;
+		*stop_tick = !(drv->states[0].flags & CPUIDLE_FLAG_POLLING);
 		return 0;
 	}
 
@@ -395,16 +395,9 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 			return idx;
 		}
-		if (s->exit_latency > latency_req) {
+		if (s->exit_latency > latency_req)
-			/*
-			 * If we break out of the loop for latency reasons, use
-			 * the target residency of the selected state as the
-			 * expected idle duration so that the tick is retained
-			 * as long as that target residency is low enough.
-			 */
-			predicted_us = drv->states[idx].target_residency;
 			break;
-		}
+
 		idx = i;
 	}
 
@@ -455,7 +448,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
 
-	data->last_state_idx = index;
+	dev->last_state_idx = index;
 	data->needs_update = 1;
 	data->tick_wakeup = tick_nohz_idle_got_tick();
 }
@@ -468,7 +461,7 @@ static void menu_reflect(struct cpuidle_device *dev, int index)
 static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
-	int last_idx = data->last_state_idx;
+	int last_idx = dev->last_state_idx;
 	struct cpuidle_state *target = &drv->states[last_idx];
 	unsigned int measured_us;
 	unsigned int new_factor;

drivers/cpuidle/governors/teo.c

@@ -96,7 +96,6 @@ struct teo_idle_state {
  * @time_span_ns: Time between idle state selection and post-wakeup update.
  * @sleep_length_ns: Time till the closest timer event (at the selection time).
  * @states: Idle states data corresponding to this CPU.
- * @last_state: Idle state entered by the CPU last time.
  * @interval_idx: Index of the most recent saved idle interval.
  * @intervals: Saved idle duration values.
  */
@@ -104,7 +103,6 @@ struct teo_cpu {
 	u64 time_span_ns;
 	u64 sleep_length_ns;
 	struct teo_idle_state states[CPUIDLE_STATE_MAX];
-	int last_state;
 	int interval_idx;
 	unsigned int intervals[INTERVALS];
 };
@@ -125,12 +123,15 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 
 	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns) {
 		/*
-		 * One of the safety nets has triggered or this was a timer
+		 * One of the safety nets has triggered or the wakeup was close
-		 * wakeup (or equivalent).
+		 * enough to the closest timer event expected at the idle state
+		 * selection time to be discarded.
 		 */
-		measured_us = sleep_length_us;
+		measured_us = UINT_MAX;
 	} else {
-		unsigned int lat = drv->states[cpu_data->last_state].exit_latency;
+		unsigned int lat;
+
+		lat = drv->states[dev->last_state_idx].exit_latency;
 
 		measured_us = ktime_to_us(cpu_data->time_span_ns);
 		/*
@@ -188,15 +189,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev)
 		cpu_data->states[idx_timer].hits = hits;
 	}
 
-	/*
-	 * If the total time span between idle state selection and the "reflect"
-	 * callback is greater than or equal to the sleep length determined at
-	 * the idle state selection time, the wakeup is likely to be due to a
-	 * timer event.
-	 */
-	if (cpu_data->time_span_ns >= cpu_data->sleep_length_ns)
-		measured_us = UINT_MAX;
-
 	/*
 	 * Save idle duration values corresponding to non-timer wakeups for
 	 * pattern detection.
@@ -242,12 +234,12 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 	unsigned int duration_us, count;
-	int max_early_idx, idx, i;
+	int max_early_idx, constraint_idx, idx, i;
 	ktime_t delta_tick;
 
-	if (cpu_data->last_state >= 0) {
+	if (dev->last_state_idx >= 0) {
 		teo_update(drv, dev);
-		cpu_data->last_state = -1;
+		dev->last_state_idx = -1;
 	}
 
 	cpu_data->time_span_ns = local_clock();
@@ -257,6 +249,7 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 
 	count = 0;
 	max_early_idx = -1;
+	constraint_idx = drv->state_count;
 	idx = -1;
 
 	for (i = 0; i < drv->state_count; i++) {
@@ -286,16 +279,8 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		if (s->target_residency > duration_us)
 			break;
 
-		if (s->exit_latency > latency_req) {
+		if (s->exit_latency > latency_req && constraint_idx > i)
-			/*
+			constraint_idx = i;
-			 * If we break out of the loop for latency reasons, use
-			 * the target residency of the selected state as the
-			 * expected idle duration to avoid stopping the tick
-			 * as long as that target residency is low enough.
-			 */
-			duration_us = drv->states[idx].target_residency;
-			goto refine;
-		}
 
 		idx = i;
 
@@ -321,7 +306,13 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		duration_us = drv->states[idx].target_residency;
 	}
 
-refine:
+	/*
+	 * If there is a latency constraint, it may be necessary to use a
+	 * shallower idle state than the one selected so far.
+	 */
+	if (constraint_idx < idx)
+		idx = constraint_idx;
+
 	if (idx < 0) {
 		idx = 0; /* No states enabled. Must use 0. */
 	} else if (idx > 0) {
@@ -331,13 +322,12 @@ refine:
 
 		/*
 		 * Count and sum the most recent idle duration values less than
-		 * the target residency of the state selected so far, find the
+		 * the current expected idle duration value.
-		 * max.
 		 */
 		for (i = 0; i < INTERVALS; i++) {
 			unsigned int val = cpu_data->intervals[i];
 
-			if (val >= drv->states[idx].target_residency)
+			if (val >= duration_us)
 				continue;
 
 			count++;
@@ -356,8 +346,10 @@ refine:
 			 * would be too shallow.
 			 */
 			if (!(tick_nohz_tick_stopped() && avg_us < TICK_USEC)) {
-				idx = teo_find_shallower_state(drv, dev, idx, avg_us);
 				duration_us = avg_us;
+				if (drv->states[idx].target_residency > avg_us)
+					idx = teo_find_shallower_state(drv, dev,
+								       idx, avg_us);
 			}
 		}
 	}
@@ -394,7 +386,7 @@ static void teo_reflect(struct cpuidle_device *dev, int state)
 {
 	struct teo_cpu *cpu_data = per_cpu_ptr(&teo_cpus, dev->cpu);
 
-	cpu_data->last_state = state;
+	dev->last_state_idx = state;
 	/*
 	 * If the wakeup was not "natural", but triggered by one of the safety
 	 * nets, assume that the CPU might have been idle for the entire sleep

drivers/cpuidle/poll_state.c

@@ -20,16 +20,9 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev,
 	local_irq_enable();
 	if (!current_set_polling_and_test()) {
 		unsigned int loop_count = 0;
-		u64 limit = TICK_NSEC;
+		u64 limit;
-		int i;
 
-		for (i = 1; i < drv->state_count; i++) {
+		limit = cpuidle_poll_time(drv, dev);
-			if (drv->states[i].disabled || dev->states_usage[i].disable)
-				continue;
-
-			limit = (u64)drv->states[i].target_residency * NSEC_PER_USEC;
-			break;
-		}
 
 		while (!need_resched()) {
 			cpu_relax();

drivers/cpuidle/sysfs.c

@@ -334,6 +334,7 @@ struct cpuidle_state_kobj {
 	struct cpuidle_state_usage *state_usage;
 	struct completion kobj_unregister;
 	struct kobject kobj;
+	struct cpuidle_device *device;
 };
 
 #ifdef CONFIG_SUSPEND
@@ -391,6 +392,7 @@ static inline void cpuidle_remove_s2idle_attr_group(struct cpuidle_state_kobj *k
 #define kobj_to_state_obj(k) container_of(k, struct cpuidle_state_kobj, kobj)
 #define kobj_to_state(k) (kobj_to_state_obj(k)->state)
 #define kobj_to_state_usage(k) (kobj_to_state_obj(k)->state_usage)
+#define kobj_to_device(k) (kobj_to_state_obj(k)->device)
 #define attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr)
 
 static ssize_t cpuidle_state_show(struct kobject *kobj, struct attribute *attr,
@@ -414,10 +416,14 @@ static ssize_t cpuidle_state_store(struct kobject *kobj, struct attribute *attr,
 	struct cpuidle_state *state = kobj_to_state(kobj);
 	struct cpuidle_state_usage *state_usage = kobj_to_state_usage(kobj);
 	struct cpuidle_state_attr *cattr = attr_to_stateattr(attr);
+	struct cpuidle_device *dev = kobj_to_device(kobj);
 
 	if (cattr->store)
 		ret = cattr->store(state, state_usage, buf, size);
 
+	/* reset poll time cache */
+	dev->poll_limit_ns = 0;
+
 	return ret;
 }
 
@@ -468,6 +474,7 @@ static int cpuidle_add_state_sysfs(struct cpuidle_device *device)
 		}
 		kobj->state = &drv->states[i];
 		kobj->state_usage = &device->states_usage[i];
+		kobj->device = device;
 		init_completion(&kobj->kobj_unregister);
 
 		ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle,

drivers/powercap/idle_inject.c

@@ -59,14 +59,14 @@ struct idle_inject_thread {
 /**
  * struct idle_inject_device - idle injection data
  * @timer: idle injection period timer
- * @idle_duration_ms: duration of CPU idle time to inject
+ * @idle_duration_us: duration of CPU idle time to inject
- * @run_duration_ms: duration of CPU run time to allow
+ * @run_duration_us: duration of CPU run time to allow
  * @cpumask: mask of CPUs affected by idle injection
  */
 struct idle_inject_device {
 	struct hrtimer timer;
-	unsigned int idle_duration_ms;
+	unsigned int idle_duration_us;
-	unsigned int run_duration_ms;
+	unsigned int run_duration_us;
 	unsigned long int cpumask[0];
 };
 
@@ -104,16 +104,16 @@ static void idle_inject_wakeup(struct idle_inject_device *ii_dev)
  */
 static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
 {
-	unsigned int duration_ms;
+	unsigned int duration_us;
 	struct idle_inject_device *ii_dev =
 		container_of(timer, struct idle_inject_device, timer);
 
-	duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	duration_us = READ_ONCE(ii_dev->run_duration_us);
-	duration_ms += READ_ONCE(ii_dev->idle_duration_ms);
+	duration_us += READ_ONCE(ii_dev->idle_duration_us);
 
 	idle_inject_wakeup(ii_dev);
 
-	hrtimer_forward_now(timer, ms_to_ktime(duration_ms));
+	hrtimer_forward_now(timer, ns_to_ktime(duration_us * NSEC_PER_USEC));
 
 	return HRTIMER_RESTART;
 }
@@ -138,35 +138,35 @@ static void idle_inject_fn(unsigned int cpu)
 	 */
 	iit->should_run = 0;
 
-	play_idle(READ_ONCE(ii_dev->idle_duration_ms));
+	play_idle(READ_ONCE(ii_dev->idle_duration_us));
 }
 
 /**
  * idle_inject_set_duration - idle and run duration update helper
- * @run_duration_ms: CPU run time to allow in milliseconds
+ * @run_duration_us: CPU run time to allow in microseconds
- * @idle_duration_ms: CPU idle time to inject in milliseconds
+ * @idle_duration_us: CPU idle time to inject in microseconds
  */
 void idle_inject_set_duration(struct idle_inject_device *ii_dev,
-			      unsigned int run_duration_ms,
+			      unsigned int run_duration_us,
-			      unsigned int idle_duration_ms)
+			      unsigned int idle_duration_us)
 {
-	if (run_duration_ms && idle_duration_ms) {
+	if (run_duration_us && idle_duration_us) {
-		WRITE_ONCE(ii_dev->run_duration_ms, run_duration_ms);
+		WRITE_ONCE(ii_dev->run_duration_us, run_duration_us);
-		WRITE_ONCE(ii_dev->idle_duration_ms, idle_duration_ms);
+		WRITE_ONCE(ii_dev->idle_duration_us, idle_duration_us);
 	}
 }
 
 /**
  * idle_inject_get_duration - idle and run duration retrieval helper
- * @run_duration_ms: memory location to store the current CPU run time
+ * @run_duration_us: memory location to store the current CPU run time
- * @idle_duration_ms: memory location to store the current CPU idle time
+ * @idle_duration_us: memory location to store the current CPU idle time
  */
 void idle_inject_get_duration(struct idle_inject_device *ii_dev,
-			      unsigned int *run_duration_ms,
+			      unsigned int *run_duration_us,
-			      unsigned int *idle_duration_ms)
+			      unsigned int *idle_duration_us)
 {
-	*run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	*run_duration_us = READ_ONCE(ii_dev->run_duration_us);
-	*idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	*idle_duration_us = READ_ONCE(ii_dev->idle_duration_us);
 }
 
 /**
@@ -181,10 +181,10 @@ void idle_inject_get_duration(struct idle_inject_device *ii_dev,
  */
 int idle_inject_start(struct idle_inject_device *ii_dev)
 {
-	unsigned int idle_duration_ms = READ_ONCE(ii_dev->idle_duration_ms);
+	unsigned int idle_duration_us = READ_ONCE(ii_dev->idle_duration_us);
-	unsigned int run_duration_ms = READ_ONCE(ii_dev->run_duration_ms);
+	unsigned int run_duration_us = READ_ONCE(ii_dev->run_duration_us);
 
-	if (!idle_duration_ms || !run_duration_ms)
+	if (!idle_duration_us || !run_duration_us)
 		return -EINVAL;
 
 	pr_debug("Starting injecting idle cycles on CPUs '%*pbl'\n",
@@ -193,7 +193,8 @@ int idle_inject_start(struct idle_inject_device *ii_dev)
 	idle_inject_wakeup(ii_dev);
 
 	hrtimer_start(&ii_dev->timer,
-		      ms_to_ktime(idle_duration_ms + run_duration_ms),
+		      ns_to_ktime((idle_duration_us + run_duration_us) *
+				  NSEC_PER_USEC),
 		      HRTIMER_MODE_REL);
 
 	return 0;

drivers/thermal/intel/intel_powerclamp.c

@@ -430,7 +430,7 @@ static void clamp_idle_injection_func(struct kthread_work *work)
 	if (should_skip)
 		goto balance;
 
-	play_idle(jiffies_to_msecs(w_data->duration_jiffies));
+	play_idle(jiffies_to_usecs(w_data->duration_jiffies));
 
 balance:
 	if (clamping && w_data->clamping && cpu_online(w_data->cpu))

include/linux/cpu.h

@@ -179,7 +179,7 @@ void arch_cpu_idle_dead(void);
 int cpu_report_state(int cpu);
 int cpu_check_up_prepare(int cpu);
 void cpu_set_state_online(int cpu);
-void play_idle(unsigned long duration_ms);
+void play_idle(unsigned long duration_us);
 
 #ifdef CONFIG_HOTPLUG_CPU
 bool cpu_wait_death(unsigned int cpu, int seconds);

include/linux/cpuidle.h

@@ -85,7 +85,9 @@ struct cpuidle_device {
 	unsigned int		cpu;
 	ktime_t			next_hrtimer;
 
+	int			last_state_idx;
 	int			last_residency;
+	u64			poll_limit_ns;
 	struct cpuidle_state_usage	states_usage[CPUIDLE_STATE_MAX];
 	struct cpuidle_state_kobj *kobjs[CPUIDLE_STATE_MAX];
 	struct cpuidle_driver_kobj *kobj_driver;
@@ -119,6 +121,9 @@ struct cpuidle_driver {
 
 	/* the driver handles the cpus in cpumask */
 	struct cpumask		*cpumask;
+
+	/* preferred governor to switch at register time */
+	const char		*governor;
 };
 
 #ifdef CONFIG_CPU_IDLE
@@ -132,6 +137,8 @@ extern int cpuidle_select(struct cpuidle_driver *drv,
 extern int cpuidle_enter(struct cpuidle_driver *drv,
 			 struct cpuidle_device *dev, int index);
 extern void cpuidle_reflect(struct cpuidle_device *dev, int index);
+extern u64 cpuidle_poll_time(struct cpuidle_driver *drv,
+			     struct cpuidle_device *dev);
 
 extern int cpuidle_register_driver(struct cpuidle_driver *drv);
 extern struct cpuidle_driver *cpuidle_get_driver(void);
@@ -166,6 +173,9 @@ static inline int cpuidle_enter(struct cpuidle_driver *drv,
 				struct cpuidle_device *dev, int index)
 {return -ENODEV; }
 static inline void cpuidle_reflect(struct cpuidle_device *dev, int index) { }
+static inline u64 cpuidle_poll_time(struct cpuidle_driver *drv,
+			     struct cpuidle_device *dev)
+{return 0; }
 static inline int cpuidle_register_driver(struct cpuidle_driver *drv)
 {return -ENODEV; }
 static inline struct cpuidle_driver *cpuidle_get_driver(void) {return NULL; }

include/linux/cpuidle_haltpoll.h

@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _CPUIDLE_HALTPOLL_H
+#define _CPUIDLE_HALTPOLL_H
+
+#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
+#include <asm/cpuidle_haltpoll.h>
+#else
+static inline void arch_haltpoll_enable(unsigned int cpu)
+{
+}
+
+static inline void arch_haltpoll_disable(unsigned int cpu)
+{
+}
+#endif
+#endif

include/linux/idle_inject.h

@@ -20,10 +20,10 @@ int idle_inject_start(struct idle_inject_device *ii_dev);
 void idle_inject_stop(struct idle_inject_device *ii_dev);
 
 void idle_inject_set_duration(struct idle_inject_device *ii_dev,
-				 unsigned int run_duration_ms,
+				 unsigned int run_duration_us,
-				 unsigned int idle_duration_ms);
+				 unsigned int idle_duration_us);
 
 void idle_inject_get_duration(struct idle_inject_device *ii_dev,
-				 unsigned int *run_duration_ms,
+				 unsigned int *run_duration_us,
-				 unsigned int *idle_duration_ms);
+				 unsigned int *idle_duration_us);
 #endif /* __IDLE_INJECT_H__ */

kernel/sched/idle.c

@@ -311,7 +311,7 @@ static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer)
 	return HRTIMER_NORESTART;
 }
 
-void play_idle(unsigned long duration_ms)
+void play_idle(unsigned long duration_us)
 {
 	struct idle_timer it;
 
@@ -323,7 +323,7 @@ void play_idle(unsigned long duration_ms)
 	WARN_ON_ONCE(current->nr_cpus_allowed != 1);
 	WARN_ON_ONCE(!(current->flags & PF_KTHREAD));
 	WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY));
-	WARN_ON_ONCE(!duration_ms);
+	WARN_ON_ONCE(!duration_us);
 
 	rcu_sleep_check();
 	preempt_disable();
@@ -333,7 +333,8 @@ void play_idle(unsigned long duration_ms)
 	it.done = 0;
 	hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	it.timer.function = idle_inject_timer_fn;
-	hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED);
+	hrtimer_start(&it.timer, ns_to_ktime(duration_us * NSEC_PER_USEC),
+		      HRTIMER_MODE_REL_PINNED);
 
 	while (!READ_ONCE(it.done))
 		do_idle();