diff options
Diffstat (limited to 'drivers/cpuidle')
-rw-r--r-- | drivers/cpuidle/Kconfig | 20 | ||||
-rw-r--r-- | drivers/cpuidle/Kconfig.arm | 10 | ||||
-rw-r--r-- | drivers/cpuidle/Makefile | 2 | ||||
-rw-r--r-- | drivers/cpuidle/cpuidle-arm.c | 13 | ||||
-rw-r--r-- | drivers/cpuidle/cpuidle-haltpoll.c | 134 | ||||
-rw-r--r-- | drivers/cpuidle/cpuidle-psci.c | 236 | ||||
-rw-r--r-- | drivers/cpuidle/cpuidle.c | 30 | ||||
-rw-r--r-- | drivers/cpuidle/cpuidle.h | 2 | ||||
-rw-r--r-- | drivers/cpuidle/driver.c | 25 | ||||
-rw-r--r-- | drivers/cpuidle/governor.c | 7 | ||||
-rw-r--r-- | drivers/cpuidle/governors/Makefile | 1 | ||||
-rw-r--r-- | drivers/cpuidle/governors/haltpoll.c | 150 | ||||
-rw-r--r-- | drivers/cpuidle/governors/ladder.c | 21 | ||||
-rw-r--r-- | drivers/cpuidle/governors/menu.c | 21 | ||||
-rw-r--r-- | drivers/cpuidle/governors/teo.c | 60 | ||||
-rw-r--r-- | drivers/cpuidle/poll_state.c | 11 | ||||
-rw-r--r-- | drivers/cpuidle/sysfs.c | 7 |
17 files changed, 675 insertions, 75 deletions
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig index a4ac31e4a58c..88727b7c0d59 100644 --- a/drivers/cpuidle/Kconfig +++ b/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 diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm index 48cb3d4bb7d1..d8530475493c 100644 --- a/drivers/cpuidle/Kconfig.arm +++ b/drivers/cpuidle/Kconfig.arm @@ -13,6 +13,16 @@ config ARM_CPUIDLE initialized by calling the CPU operations init idle hook provided by architecture code. +config ARM_PSCI_CPUIDLE + bool "PSCI CPU idle Driver" + depends on ARM_PSCI_FW + select DT_IDLE_STATES + select CPU_IDLE_MULTIPLE_DRIVERS + help + Select this to enable PSCI firmware based CPUidle driver for ARM. + It provides an idle driver that is capable of detecting and + managing idle states through the PSCI firmware interface. + config ARM_BIG_LITTLE_CPUIDLE bool "Support for ARM big.LITTLE processors" depends on ARCH_VEXPRESS_TC2_PM || ARCH_EXYNOS diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile index 9d7176cee3d3..ee70d5cc5b99 100644 --- a/drivers/cpuidle/Makefile +++ b/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 @@ -20,6 +21,7 @@ obj-$(CONFIG_ARM_U8500_CPUIDLE) += cpuidle-ux500.o obj-$(CONFIG_ARM_AT91_CPUIDLE) += cpuidle-at91.o obj-$(CONFIG_ARM_EXYNOS_CPUIDLE) += cpuidle-exynos.o obj-$(CONFIG_ARM_CPUIDLE) += cpuidle-arm.o +obj-$(CONFIG_ARM_PSCI_CPUIDLE) += cpuidle-psci.o ############################################################################### # MIPS drivers diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c index 5bcd82c35dcf..9e5156d39627 100644 --- a/drivers/cpuidle/cpuidle-arm.c +++ b/drivers/cpuidle/cpuidle-arm.c @@ -15,7 +15,6 @@ #include <linux/module.h> #include <linux/of.h> #include <linux/slab.h> -#include <linux/topology.h> #include <asm/cpuidle.h> @@ -106,11 +105,17 @@ static int __init arm_idle_init_cpu(int cpu) ret = arm_cpuidle_init(cpu); /* - * Allow the initialization to continue for other CPUs, if the reported - * failure is a HW misconfiguration/breakage (-ENXIO). + * Allow the initialization to continue for other CPUs, if the + * reported failure is a HW misconfiguration/breakage (-ENXIO). + * + * Some platforms do not support idle operations + * (arm_cpuidle_init() returning -EOPNOTSUPP), we should + * not flag this case as an error, it is a valid + * configuration. */ if (ret) { - pr_err("CPU %d failed to init idle CPU ops\n", cpu); + if (ret != -EOPNOTSUPP) + pr_err("CPU %d failed to init idle CPU ops\n", cpu); ret = ret == -ENXIO ? 0 : ret; goto out_kfree_drv; } diff --git a/drivers/cpuidle/cpuidle-haltpoll.c b/drivers/cpuidle/cpuidle-haltpoll.c new file mode 100644 index 000000000000..932390b028f1 --- /dev/null +++ b/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>"); diff --git a/drivers/cpuidle/cpuidle-psci.c b/drivers/cpuidle/cpuidle-psci.c new file mode 100644 index 000000000000..f3c1a2396f98 --- /dev/null +++ b/drivers/cpuidle/cpuidle-psci.c @@ -0,0 +1,236 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PSCI CPU idle driver. + * + * Copyright (C) 2019 ARM Ltd. + * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + */ + +#define pr_fmt(fmt) "CPUidle PSCI: " fmt + +#include <linux/cpuidle.h> +#include <linux/cpumask.h> +#include <linux/cpu_pm.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/psci.h> +#include <linux/slab.h> + +#include <asm/cpuidle.h> + +#include "dt_idle_states.h" + +static DEFINE_PER_CPU_READ_MOSTLY(u32 *, psci_power_state); + +static int psci_enter_idle_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx) +{ + u32 *state = __this_cpu_read(psci_power_state); + + return CPU_PM_CPU_IDLE_ENTER_PARAM(psci_cpu_suspend_enter, + idx, state[idx - 1]); +} + +static struct cpuidle_driver psci_idle_driver __initdata = { + .name = "psci_idle", + .owner = THIS_MODULE, + /* + * PSCI idle states relies on architectural WFI to + * be represented as state index 0. + */ + .states[0] = { + .enter = psci_enter_idle_state, + .exit_latency = 1, + .target_residency = 1, + .power_usage = UINT_MAX, + .name = "WFI", + .desc = "ARM WFI", + } +}; + +static const struct of_device_id psci_idle_state_match[] __initconst = { + { .compatible = "arm,idle-state", + .data = psci_enter_idle_state }, + { }, +}; + +static int __init psci_dt_parse_state_node(struct device_node *np, u32 *state) +{ + int err = of_property_read_u32(np, "arm,psci-suspend-param", state); + + if (err) { + pr_warn("%pOF missing arm,psci-suspend-param property\n", np); + return err; + } + + if (!psci_power_state_is_valid(*state)) { + pr_warn("Invalid PSCI power state %#x\n", *state); + return -EINVAL; + } + + return 0; +} + +static int __init psci_dt_cpu_init_idle(struct device_node *cpu_node, int cpu) +{ + int i, ret = 0, count = 0; + u32 *psci_states; + struct device_node *state_node; + + /* Count idle states */ + while ((state_node = of_parse_phandle(cpu_node, "cpu-idle-states", + count))) { + count++; + of_node_put(state_node); + } + + if (!count) + return -ENODEV; + + psci_states = kcalloc(count, sizeof(*psci_states), GFP_KERNEL); + if (!psci_states) + return -ENOMEM; + + for (i = 0; i < count; i++) { + state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i); + ret = psci_dt_parse_state_node(state_node, &psci_states[i]); + of_node_put(state_node); + + if (ret) + goto free_mem; + + pr_debug("psci-power-state %#x index %d\n", psci_states[i], i); + } + + /* Idle states parsed correctly, initialize per-cpu pointer */ + per_cpu(psci_power_state, cpu) = psci_states; + return 0; + +free_mem: + kfree(psci_states); + return ret; +} + +static __init int psci_cpu_init_idle(unsigned int cpu) +{ + struct device_node *cpu_node; + int ret; + + /* + * If the PSCI cpu_suspend function hook has not been initialized + * idle states must not be enabled, so bail out + */ + if (!psci_ops.cpu_suspend) + return -EOPNOTSUPP; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) + return -ENODEV; + + ret = psci_dt_cpu_init_idle(cpu_node, cpu); + + of_node_put(cpu_node); + + return ret; +} + +static int __init psci_idle_init_cpu(int cpu) +{ + struct cpuidle_driver *drv; + struct device_node *cpu_node; + const char *enable_method; + int ret = 0; + + cpu_node = of_cpu_device_node_get(cpu); + if (!cpu_node) + return -ENODEV; + + /* + * Check whether the enable-method for the cpu is PSCI, fail + * if it is not. + */ + enable_method = of_get_property(cpu_node, "enable-method", NULL); + if (!enable_method || (strcmp(enable_method, "psci"))) + ret = -ENODEV; + + of_node_put(cpu_node); + if (ret) + return ret; + + drv = kmemdup(&psci_idle_driver, sizeof(*drv), GFP_KERNEL); + if (!drv) + return -ENOMEM; + + drv->cpumask = (struct cpumask *)cpumask_of(cpu); + + /* + * Initialize idle states data, starting at index 1, since + * by default idle state 0 is the quiescent state reached + * by the cpu by executing the wfi instruction. + * + * If no DT idle states are detected (ret == 0) let the driver + * initialization fail accordingly since there is no reason to + * initialize the idle driver if only wfi is supported, the + * default archictectural back-end already executes wfi + * on idle entry. + */ + ret = dt_init_idle_driver(drv, psci_idle_state_match, 1); + if (ret <= 0) { + ret = ret ? : -ENODEV; + goto out_kfree_drv; + } + + /* + * Initialize PSCI idle states. + */ + ret = psci_cpu_init_idle(cpu); + if (ret) { + pr_err("CPU %d failed to PSCI idle\n", cpu); + goto out_kfree_drv; + } + + ret = cpuidle_register(drv, NULL); + if (ret) + goto out_kfree_drv; + + return 0; + +out_kfree_drv: + kfree(drv); + return ret; +} + +/* + * psci_idle_init - Initializes PSCI cpuidle driver + * + * Initializes PSCI cpuidle driver for all CPUs, if any CPU fails + * to register cpuidle driver then rollback to cancel all CPUs + * registration. + */ +static int __init psci_idle_init(void) +{ + int cpu, ret; + struct cpuidle_driver *drv; + struct cpuidle_device *dev; + + for_each_possible_cpu(cpu) { + ret = psci_idle_init_cpu(cpu); + if (ret) + goto out_fail; + } + + return 0; + +out_fail: + while (--cpu >= 0) { + dev = per_cpu(cpuidle_devices, cpu); + drv = cpuidle_get_cpu_driver(dev); + cpuidle_unregister(drv); + kfree(drv); + } + + return ret; +} +device_initcall(psci_idle_init); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 0f4b7c45df3e..0895b988fa92 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -362,6 +362,36 @@ void cpuidle_reflect(struct cpuidle_device *dev, int 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 */ void cpuidle_install_idle_handler(void) diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index d6613101af92..9f336af17fa6 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/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 */ diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c index dc32f34e68d9..80c1a830d991 100644 --- a/drivers/cpuidle/driver.c +++ b/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); diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index 2e3e14192bee..e9801f26c732 100644 --- a/drivers/cpuidle/governor.c +++ b/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 || diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile index 42f44cc610dd..63abb5393a4d 100644 --- a/drivers/cpuidle/governors/Makefile +++ b/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 diff --git a/drivers/cpuidle/governors/haltpoll.c b/drivers/cpuidle/governors/haltpoll.c new file mode 100644 index 000000000000..7a703d2e0064 --- /dev/null +++ b/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); diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c index f0dddc66af26..428eeb832fe7 100644 --- a/drivers/cpuidle/governors/ladder.c +++ b/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 = { diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c index e9a28c7846d6..e5a5d0c8d66b 100644 --- a/drivers/cpuidle/governors/menu.c +++ b/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 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; + if (s->exit_latency > latency_req) 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; diff --git a/drivers/cpuidle/governors/teo.c b/drivers/cpuidle/governors/teo.c index 7d05efdbd3c6..b5a0e498f798 100644 --- a/drivers/cpuidle/governors/teo.c +++ b/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 - * wakeup (or equivalent). + * One of the safety nets has triggered or the wakeup was close + * 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); /* @@ -189,15 +190,6 @@ static void teo_update(struct cpuidle_driver *drv, struct cpuidle_device *dev) } /* - * 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 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; - } + if (s->exit_latency > latency_req && constraint_idx > i) + constraint_idx = i; 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 - * max. + * the current expected idle duration value. */ 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 diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 02b9315a9e96..c8fa5f41dfc4 100644 --- a/drivers/cpuidle/poll_state.c +++ b/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; - int i; + u64 limit; - for (i = 1; i < drv->state_count; i++) { - if (drv->states[i].disabled || dev->states_usage[i].disable) - continue; - - limit = (u64)drv->states[i].target_residency * NSEC_PER_USEC; - break; - } + limit = cpuidle_poll_time(drv, dev); while (!need_resched()) { cpu_relax(); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index eb20adb5de23..2bb2683b493c 100644 --- a/drivers/cpuidle/sysfs.c +++ b/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, |