diff options
Diffstat (limited to '')
30 files changed, 6166 insertions, 0 deletions
diff --git a/drivers/cpuidle/Kconfig b/drivers/cpuidle/Kconfig new file mode 100644 index 000000000..7e48eb5bf --- /dev/null +++ b/drivers/cpuidle/Kconfig @@ -0,0 +1,48 @@ +menu "CPU Idle" + +config CPU_IDLE + bool "CPU idle PM support" + default y if ACPI || PPC_PSERIES + select CPU_IDLE_GOV_LADDER if (!NO_HZ && !NO_HZ_IDLE) + select CPU_IDLE_GOV_MENU if (NO_HZ || NO_HZ_IDLE) + help + CPU idle is a generic framework for supporting software-controlled + idle processor power management. It includes modular cross-platform + governors that can be swapped during runtime. + + If you're using an ACPI-enabled platform, you should say Y here. + +if CPU_IDLE + +config CPU_IDLE_MULTIPLE_DRIVERS + bool + +config CPU_IDLE_GOV_LADDER + bool "Ladder governor (for periodic timer tick)" + +config CPU_IDLE_GOV_MENU + bool "Menu governor (for tickless system)" + +config DT_IDLE_STATES + bool + +menu "ARM CPU Idle Drivers" +depends on ARM || ARM64 +source "drivers/cpuidle/Kconfig.arm" +endmenu + +menu "MIPS CPU Idle Drivers" +depends on MIPS +source "drivers/cpuidle/Kconfig.mips" +endmenu + +menu "POWERPC CPU Idle Drivers" +depends on PPC +source "drivers/cpuidle/Kconfig.powerpc" +endmenu + +endif + +config ARCH_NEEDS_CPU_IDLE_COUPLED + def_bool n +endmenu diff --git a/drivers/cpuidle/Kconfig.arm b/drivers/cpuidle/Kconfig.arm new file mode 100644 index 000000000..f52144808 --- /dev/null +++ b/drivers/cpuidle/Kconfig.arm @@ -0,0 +1,77 @@ +# +# ARM CPU Idle drivers +# +config ARM_CPUIDLE + bool "Generic ARM/ARM64 CPU idle Driver" + select DT_IDLE_STATES + select CPU_IDLE_MULTIPLE_DRIVERS + help + Select this to enable generic cpuidle driver for ARM. + It provides a generic idle driver whose idle states are configured + at run-time through DT nodes. The CPUidle suspend backend is + initialized by calling the CPU operations init idle hook + provided by architecture code. + +config ARM_BIG_LITTLE_CPUIDLE + bool "Support for ARM big.LITTLE processors" + depends on ARCH_VEXPRESS_TC2_PM || ARCH_EXYNOS + depends on MCPM && !ARM64 + select ARM_CPU_SUSPEND + select CPU_IDLE_MULTIPLE_DRIVERS + select DT_IDLE_STATES + help + Select this option to enable CPU idle driver for big.LITTLE based + ARM systems. Driver manages CPUs coordination through MCPM and + define different C-states for little and big cores through the + multiple CPU idle drivers infrastructure. + +config ARM_CLPS711X_CPUIDLE + bool "CPU Idle Driver for CLPS711X processors" + depends on ARCH_CLPS711X && !ARM64 || COMPILE_TEST + help + Select this to enable cpuidle on Cirrus Logic CLPS711X SOCs. + +config ARM_HIGHBANK_CPUIDLE + bool "CPU Idle Driver for Calxeda processors" + depends on ARM_PSCI && !ARM64 + select ARM_CPU_SUSPEND + help + Select this to enable cpuidle on Calxeda processors. + +config ARM_KIRKWOOD_CPUIDLE + bool "CPU Idle Driver for Marvell Kirkwood SoCs" + depends on MACH_KIRKWOOD && !ARM64 + help + This adds the CPU Idle driver for Marvell Kirkwood SoCs. + +config ARM_ZYNQ_CPUIDLE + bool "CPU Idle Driver for Xilinx Zynq processors" + depends on ARCH_ZYNQ && !ARM64 + help + Select this to enable cpuidle on Xilinx Zynq processors. + +config ARM_U8500_CPUIDLE + bool "Cpu Idle Driver for the ST-E u8500 processors" + depends on ARCH_U8500 && !ARM64 + help + Select this to enable cpuidle for ST-E u8500 processors + +config ARM_AT91_CPUIDLE + bool "Cpu Idle Driver for the AT91 processors" + default y + depends on ARCH_AT91 && !ARM64 + help + Select this to enable cpuidle for AT91 processors + +config ARM_EXYNOS_CPUIDLE + bool "Cpu Idle Driver for the Exynos processors" + depends on ARCH_EXYNOS && !ARM64 + select ARCH_NEEDS_CPU_IDLE_COUPLED if SMP + help + Select this to enable cpuidle for Exynos processors + +config ARM_MVEBU_V7_CPUIDLE + bool "CPU Idle Driver for mvebu v7 family processors" + depends on ARCH_MVEBU && !ARM64 + help + Select this to enable cpuidle on Armada 370, 38x and XP processors. diff --git a/drivers/cpuidle/Kconfig.mips b/drivers/cpuidle/Kconfig.mips new file mode 100644 index 000000000..512ee37b3 --- /dev/null +++ b/drivers/cpuidle/Kconfig.mips @@ -0,0 +1,17 @@ +# +# MIPS CPU Idle Drivers +# +config MIPS_CPS_CPUIDLE + bool "CPU Idle driver for MIPS CPS platforms" + depends on CPU_IDLE && MIPS_CPS + depends on SYS_SUPPORTS_MIPS_CPS + select ARCH_NEEDS_CPU_IDLE_COUPLED if MIPS_MT || CPU_MIPSR6 + select GENERIC_CLOCKEVENTS_BROADCAST if SMP + select MIPS_CPS_PM + default y + help + Select this option to enable processor idle state management + through cpuidle for systems built around the MIPS Coherent + Processing System (CPS) architecture. In order to make use of + the deepest idle states you will need to ensure that you are + also using the CONFIG_MIPS_CPS SMP implementation. diff --git a/drivers/cpuidle/Kconfig.powerpc b/drivers/cpuidle/Kconfig.powerpc new file mode 100644 index 000000000..66c3a0957 --- /dev/null +++ b/drivers/cpuidle/Kconfig.powerpc @@ -0,0 +1,20 @@ +# +# POWERPC CPU Idle Drivers +# +config PSERIES_CPUIDLE + bool "Cpuidle driver for pSeries platforms" + depends on CPU_IDLE + depends on PPC_PSERIES + default y + help + Select this option to enable processor idle state management + through cpuidle subsystem. + +config POWERNV_CPUIDLE + bool "Cpuidle driver for powernv platforms" + depends on CPU_IDLE + depends on PPC_POWERNV + default y + help + Select this option to enable processor idle state management + through cpuidle subsystem. diff --git a/drivers/cpuidle/Makefile b/drivers/cpuidle/Makefile new file mode 100644 index 000000000..9d7176cee --- /dev/null +++ b/drivers/cpuidle/Makefile @@ -0,0 +1,31 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for cpuidle. +# + +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-$(CONFIG_ARCH_HAS_CPU_RELAX) += poll_state.o + +################################################################################## +# ARM SoC drivers +obj-$(CONFIG_ARM_MVEBU_V7_CPUIDLE) += cpuidle-mvebu-v7.o +obj-$(CONFIG_ARM_BIG_LITTLE_CPUIDLE) += cpuidle-big_little.o +obj-$(CONFIG_ARM_CLPS711X_CPUIDLE) += cpuidle-clps711x.o +obj-$(CONFIG_ARM_HIGHBANK_CPUIDLE) += cpuidle-calxeda.o +obj-$(CONFIG_ARM_KIRKWOOD_CPUIDLE) += cpuidle-kirkwood.o +obj-$(CONFIG_ARM_ZYNQ_CPUIDLE) += cpuidle-zynq.o +obj-$(CONFIG_ARM_U8500_CPUIDLE) += cpuidle-ux500.o +obj-$(CONFIG_ARM_AT91_CPUIDLE) += cpuidle-at91.o +obj-$(CONFIG_ARM_EXYNOS_CPUIDLE) += cpuidle-exynos.o +obj-$(CONFIG_ARM_CPUIDLE) += cpuidle-arm.o + +############################################################################### +# MIPS drivers +obj-$(CONFIG_MIPS_CPS_CPUIDLE) += cpuidle-cps.o + +############################################################################### +# POWERPC drivers +obj-$(CONFIG_PSERIES_CPUIDLE) += cpuidle-pseries.o +obj-$(CONFIG_POWERNV_CPUIDLE) += cpuidle-powernv.o diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c new file mode 100644 index 000000000..147f38ea0 --- /dev/null +++ b/drivers/cpuidle/coupled.c @@ -0,0 +1,800 @@ +/* + * coupled.c - helper functions to enter the same idle state on multiple cpus + * + * Copyright (c) 2011 Google, Inc. + * + * Author: Colin Cross <ccross@android.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/kernel.h> +#include <linux/cpu.h> +#include <linux/cpuidle.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/spinlock.h> + +#include "cpuidle.h" + +/** + * DOC: Coupled cpuidle states + * + * On some ARM SMP SoCs (OMAP4460, Tegra 2, and probably more), the + * cpus cannot be independently powered down, either due to + * sequencing restrictions (on Tegra 2, cpu 0 must be the last to + * power down), or due to HW bugs (on OMAP4460, a cpu powering up + * will corrupt the gic state unless the other cpu runs a work + * around). Each cpu has a power state that it can enter without + * coordinating with the other cpu (usually Wait For Interrupt, or + * WFI), and one or more "coupled" power states that affect blocks + * shared between the cpus (L2 cache, interrupt controller, and + * sometimes the whole SoC). Entering a coupled power state must + * be tightly controlled on both cpus. + * + * This file implements a solution, where each cpu will wait in the + * WFI state until all cpus are ready to enter a coupled state, at + * which point the coupled state function will be called on all + * cpus at approximately the same time. + * + * Once all cpus are ready to enter idle, they are woken by an smp + * cross call. At this point, there is a chance that one of the + * cpus will find work to do, and choose not to enter idle. A + * final pass is needed to guarantee that all cpus will call the + * power state enter function at the same time. During this pass, + * each cpu will increment the ready counter, and continue once the + * ready counter matches the number of online coupled cpus. If any + * cpu exits idle, the other cpus will decrement their counter and + * retry. + * + * requested_state stores the deepest coupled idle state each cpu + * is ready for. It is assumed that the states are indexed from + * shallowest (highest power, lowest exit latency) to deepest + * (lowest power, highest exit latency). The requested_state + * variable is not locked. It is only written from the cpu that + * it stores (or by the on/offlining cpu if that cpu is offline), + * and only read after all the cpus are ready for the coupled idle + * state are are no longer updating it. + * + * Three atomic counters are used. alive_count tracks the number + * of cpus in the coupled set that are currently or soon will be + * online. waiting_count tracks the number of cpus that are in + * the waiting loop, in the ready loop, or in the coupled idle state. + * ready_count tracks the number of cpus that are in the ready loop + * or in the coupled idle state. + * + * To use coupled cpuidle states, a cpuidle driver must: + * + * Set struct cpuidle_device.coupled_cpus to the mask of all + * coupled cpus, usually the same as cpu_possible_mask if all cpus + * are part of the same cluster. The coupled_cpus mask must be + * set in the struct cpuidle_device for each cpu. + * + * Set struct cpuidle_device.safe_state to a state that is not a + * coupled state. This is usually WFI. + * + * Set CPUIDLE_FLAG_COUPLED in struct cpuidle_state.flags for each + * state that affects multiple cpus. + * + * Provide a struct cpuidle_state.enter function for each state + * that affects multiple cpus. This function is guaranteed to be + * called on all cpus at approximately the same time. The driver + * should ensure that the cpus all abort together if any cpu tries + * to abort once the function is called. The function should return + * with interrupts still disabled. + */ + +/** + * struct cpuidle_coupled - data for set of cpus that share a coupled idle state + * @coupled_cpus: mask of cpus that are part of the coupled set + * @requested_state: array of requested states for cpus in the coupled set + * @ready_waiting_counts: combined count of cpus in ready or waiting loops + * @online_count: count of cpus that are online + * @refcnt: reference count of cpuidle devices that are using this struct + * @prevent: flag to prevent coupled idle while a cpu is hotplugging + */ +struct cpuidle_coupled { + cpumask_t coupled_cpus; + int requested_state[NR_CPUS]; + atomic_t ready_waiting_counts; + atomic_t abort_barrier; + int online_count; + int refcnt; + int prevent; +}; + +#define WAITING_BITS 16 +#define MAX_WAITING_CPUS (1 << WAITING_BITS) +#define WAITING_MASK (MAX_WAITING_CPUS - 1) +#define READY_MASK (~WAITING_MASK) + +#define CPUIDLE_COUPLED_NOT_IDLE (-1) + +static DEFINE_PER_CPU(call_single_data_t, cpuidle_coupled_poke_cb); + +/* + * The cpuidle_coupled_poke_pending mask is used to avoid calling + * __smp_call_function_single with the per cpu call_single_data_t struct already + * in use. This prevents a deadlock where two cpus are waiting for each others + * call_single_data_t struct to be available + */ +static cpumask_t cpuidle_coupled_poke_pending; + +/* + * The cpuidle_coupled_poked mask is used to ensure that each cpu has been poked + * once to minimize entering the ready loop with a poke pending, which would + * require aborting and retrying. + */ +static cpumask_t cpuidle_coupled_poked; + +/** + * cpuidle_coupled_parallel_barrier - synchronize all online coupled cpus + * @dev: cpuidle_device of the calling cpu + * @a: atomic variable to hold the barrier + * + * No caller to this function will return from this function until all online + * cpus in the same coupled group have called this function. Once any caller + * has returned from this function, the barrier is immediately available for + * reuse. + * + * The atomic variable must be initialized to 0 before any cpu calls + * this function, will be reset to 0 before any cpu returns from this function. + * + * Must only be called from within a coupled idle state handler + * (state.enter when state.flags has CPUIDLE_FLAG_COUPLED set). + * + * Provides full smp barrier semantics before and after calling. + */ +void cpuidle_coupled_parallel_barrier(struct cpuidle_device *dev, atomic_t *a) +{ + int n = dev->coupled->online_count; + + smp_mb__before_atomic(); + atomic_inc(a); + + while (atomic_read(a) < n) + cpu_relax(); + + if (atomic_inc_return(a) == n * 2) { + atomic_set(a, 0); + return; + } + + while (atomic_read(a) > n) + cpu_relax(); +} + +/** + * cpuidle_state_is_coupled - check if a state is part of a coupled set + * @drv: struct cpuidle_driver for the platform + * @state: index of the target state in drv->states + * + * Returns true if the target state is coupled with cpus besides this one + */ +bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state) +{ + return drv->states[state].flags & CPUIDLE_FLAG_COUPLED; +} + +/** + * cpuidle_coupled_state_verify - check if the coupled states are correctly set. + * @drv: struct cpuidle_driver for the platform + * + * Returns 0 for valid state values, a negative error code otherwise: + * * -EINVAL if any coupled state(safe_state_index) is wrongly set. + */ +int cpuidle_coupled_state_verify(struct cpuidle_driver *drv) +{ + int i; + + for (i = drv->state_count - 1; i >= 0; i--) { + if (cpuidle_state_is_coupled(drv, i) && + (drv->safe_state_index == i || + drv->safe_state_index < 0 || + drv->safe_state_index >= drv->state_count)) + return -EINVAL; + } + + return 0; +} + +/** + * cpuidle_coupled_set_ready - mark a cpu as ready + * @coupled: the struct coupled that contains the current cpu + */ +static inline void cpuidle_coupled_set_ready(struct cpuidle_coupled *coupled) +{ + atomic_add(MAX_WAITING_CPUS, &coupled->ready_waiting_counts); +} + +/** + * cpuidle_coupled_set_not_ready - mark a cpu as not ready + * @coupled: the struct coupled that contains the current cpu + * + * Decrements the ready counter, unless the ready (and thus the waiting) counter + * is equal to the number of online cpus. Prevents a race where one cpu + * decrements the waiting counter and then re-increments it just before another + * cpu has decremented its ready counter, leading to the ready counter going + * down from the number of online cpus without going through the coupled idle + * state. + * + * Returns 0 if the counter was decremented successfully, -EINVAL if the ready + * counter was equal to the number of online cpus. + */ +static +inline int cpuidle_coupled_set_not_ready(struct cpuidle_coupled *coupled) +{ + int all; + int ret; + + all = coupled->online_count | (coupled->online_count << WAITING_BITS); + ret = atomic_add_unless(&coupled->ready_waiting_counts, + -MAX_WAITING_CPUS, all); + + return ret ? 0 : -EINVAL; +} + +/** + * cpuidle_coupled_no_cpus_ready - check if no cpus in a coupled set are ready + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all of the cpus in a coupled set are out of the ready loop. + */ +static inline int cpuidle_coupled_no_cpus_ready(struct cpuidle_coupled *coupled) +{ + int r = atomic_read(&coupled->ready_waiting_counts) >> WAITING_BITS; + return r == 0; +} + +/** + * cpuidle_coupled_cpus_ready - check if all cpus in a coupled set are ready + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all cpus coupled to this target state are in the ready loop + */ +static inline bool cpuidle_coupled_cpus_ready(struct cpuidle_coupled *coupled) +{ + int r = atomic_read(&coupled->ready_waiting_counts) >> WAITING_BITS; + return r == coupled->online_count; +} + +/** + * cpuidle_coupled_cpus_waiting - check if all cpus in a coupled set are waiting + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all cpus coupled to this target state are in the wait loop + */ +static inline bool cpuidle_coupled_cpus_waiting(struct cpuidle_coupled *coupled) +{ + int w = atomic_read(&coupled->ready_waiting_counts) & WAITING_MASK; + return w == coupled->online_count; +} + +/** + * cpuidle_coupled_no_cpus_waiting - check if no cpus in coupled set are waiting + * @coupled: the struct coupled that contains the current cpu + * + * Returns true if all of the cpus in a coupled set are out of the waiting loop. + */ +static inline int cpuidle_coupled_no_cpus_waiting(struct cpuidle_coupled *coupled) +{ + int w = atomic_read(&coupled->ready_waiting_counts) & WAITING_MASK; + return w == 0; +} + +/** + * cpuidle_coupled_get_state - determine the deepest idle state + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * + * Returns the deepest idle state that all coupled cpus can enter + */ +static inline int cpuidle_coupled_get_state(struct cpuidle_device *dev, + struct cpuidle_coupled *coupled) +{ + int i; + int state = INT_MAX; + + /* + * Read barrier ensures that read of requested_state is ordered after + * reads of ready_count. Matches the write barriers + * cpuidle_set_state_waiting. + */ + smp_rmb(); + + for_each_cpu(i, &coupled->coupled_cpus) + if (cpu_online(i) && coupled->requested_state[i] < state) + state = coupled->requested_state[i]; + + return state; +} + +static void cpuidle_coupled_handle_poke(void *info) +{ + int cpu = (unsigned long)info; + cpumask_set_cpu(cpu, &cpuidle_coupled_poked); + cpumask_clear_cpu(cpu, &cpuidle_coupled_poke_pending); +} + +/** + * cpuidle_coupled_poke - wake up a cpu that may be waiting + * @cpu: target cpu + * + * Ensures that the target cpu exits it's waiting idle state (if it is in it) + * and will see updates to waiting_count before it re-enters it's waiting idle + * state. + * + * If cpuidle_coupled_poked_mask is already set for the target cpu, that cpu + * either has or will soon have a pending IPI that will wake it out of idle, + * or it is currently processing the IPI and is not in idle. + */ +static void cpuidle_coupled_poke(int cpu) +{ + call_single_data_t *csd = &per_cpu(cpuidle_coupled_poke_cb, cpu); + + if (!cpumask_test_and_set_cpu(cpu, &cpuidle_coupled_poke_pending)) + smp_call_function_single_async(cpu, csd); +} + +/** + * cpuidle_coupled_poke_others - wake up all other cpus that may be waiting + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * + * Calls cpuidle_coupled_poke on all other online cpus. + */ +static void cpuidle_coupled_poke_others(int this_cpu, + struct cpuidle_coupled *coupled) +{ + int cpu; + + for_each_cpu(cpu, &coupled->coupled_cpus) + if (cpu != this_cpu && cpu_online(cpu)) + cpuidle_coupled_poke(cpu); +} + +/** + * cpuidle_coupled_set_waiting - mark this cpu as in the wait loop + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * @next_state: the index in drv->states of the requested state for this cpu + * + * Updates the requested idle state for the specified cpuidle device. + * Returns the number of waiting cpus. + */ +static int cpuidle_coupled_set_waiting(int cpu, + struct cpuidle_coupled *coupled, int next_state) +{ + coupled->requested_state[cpu] = next_state; + + /* + * The atomic_inc_return provides a write barrier to order the write + * to requested_state with the later write that increments ready_count. + */ + return atomic_inc_return(&coupled->ready_waiting_counts) & WAITING_MASK; +} + +/** + * cpuidle_coupled_set_not_waiting - mark this cpu as leaving the wait loop + * @dev: struct cpuidle_device for this cpu + * @coupled: the struct coupled that contains the current cpu + * + * Removes the requested idle state for the specified cpuidle device. + */ +static void cpuidle_coupled_set_not_waiting(int cpu, + struct cpuidle_coupled *coupled) +{ + /* + * Decrementing waiting count can race with incrementing it in + * cpuidle_coupled_set_waiting, but that's OK. Worst case, some + * cpus will increment ready_count and then spin until they + * notice that this cpu has cleared it's requested_state. + */ + atomic_dec(&coupled->ready_waiting_counts); + + coupled->requested_state[cpu] = CPUIDLE_COUPLED_NOT_IDLE; +} + +/** + * cpuidle_coupled_set_done - mark this cpu as leaving the ready loop + * @cpu: the current cpu + * @coupled: the struct coupled that contains the current cpu + * + * Marks this cpu as no longer in the ready and waiting loops. Decrements + * the waiting count first to prevent another cpu looping back in and seeing + * this cpu as waiting just before it exits idle. + */ +static void cpuidle_coupled_set_done(int cpu, struct cpuidle_coupled *coupled) +{ + cpuidle_coupled_set_not_waiting(cpu, coupled); + atomic_sub(MAX_WAITING_CPUS, &coupled->ready_waiting_counts); +} + +/** + * cpuidle_coupled_clear_pokes - spin until the poke interrupt is processed + * @cpu - this cpu + * + * Turns on interrupts and spins until any outstanding poke interrupts have + * been processed and the poke bit has been cleared. + * + * Other interrupts may also be processed while interrupts are enabled, so + * need_resched() must be tested after this function returns to make sure + * the interrupt didn't schedule work that should take the cpu out of idle. + * + * Returns 0 if no poke was pending, 1 if a poke was cleared. + */ +static int cpuidle_coupled_clear_pokes(int cpu) +{ + if (!cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending)) + return 0; + + local_irq_enable(); + while (cpumask_test_cpu(cpu, &cpuidle_coupled_poke_pending)) + cpu_relax(); + local_irq_disable(); + + return 1; +} + +static bool cpuidle_coupled_any_pokes_pending(struct cpuidle_coupled *coupled) +{ + cpumask_t cpus; + int ret; + + cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus); + ret = cpumask_and(&cpus, &cpuidle_coupled_poke_pending, &cpus); + + return ret; +} + +/** + * cpuidle_enter_state_coupled - attempt to enter a state with coupled cpus + * @dev: struct cpuidle_device for the current cpu + * @drv: struct cpuidle_driver for the platform + * @next_state: index of the requested state in drv->states + * + * Coordinate with coupled cpus to enter the target state. This is a two + * stage process. In the first stage, the cpus are operating independently, + * and may call into cpuidle_enter_state_coupled at completely different times. + * To save as much power as possible, the first cpus to call this function will + * go to an intermediate state (the cpuidle_device's safe state), and wait for + * all the other cpus to call this function. Once all coupled cpus are idle, + * the second stage will start. Each coupled cpu will spin until all cpus have + * guaranteed that they will call the target_state. + * + * This function must be called with interrupts disabled. It may enable + * interrupts while preparing for idle, and it will always return with + * interrupts enabled. + */ +int cpuidle_enter_state_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state) +{ + int entered_state = -1; + struct cpuidle_coupled *coupled = dev->coupled; + int w; + + if (!coupled) + return -EINVAL; + + while (coupled->prevent) { + cpuidle_coupled_clear_pokes(dev->cpu); + if (need_resched()) { + local_irq_enable(); + return entered_state; + } + entered_state = cpuidle_enter_state(dev, drv, + drv->safe_state_index); + local_irq_disable(); + } + + /* Read barrier ensures online_count is read after prevent is cleared */ + smp_rmb(); + +reset: + cpumask_clear_cpu(dev->cpu, &cpuidle_coupled_poked); + + w = cpuidle_coupled_set_waiting(dev->cpu, coupled, next_state); + /* + * If this is the last cpu to enter the waiting state, poke + * all the other cpus out of their waiting state so they can + * enter a deeper state. This can race with one of the cpus + * exiting the waiting state due to an interrupt and + * decrementing waiting_count, see comment below. + */ + if (w == coupled->online_count) { + cpumask_set_cpu(dev->cpu, &cpuidle_coupled_poked); + cpuidle_coupled_poke_others(dev->cpu, coupled); + } + +retry: + /* + * Wait for all coupled cpus to be idle, using the deepest state + * allowed for a single cpu. If this was not the poking cpu, wait + * for at least one poke before leaving to avoid a race where + * two cpus could arrive at the waiting loop at the same time, + * but the first of the two to arrive could skip the loop without + * processing the pokes from the last to arrive. + */ + while (!cpuidle_coupled_cpus_waiting(coupled) || + !cpumask_test_cpu(dev->cpu, &cpuidle_coupled_poked)) { + if (cpuidle_coupled_clear_pokes(dev->cpu)) + continue; + + if (need_resched()) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + if (coupled->prevent) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + entered_state = cpuidle_enter_state(dev, drv, + drv->safe_state_index); + local_irq_disable(); + } + + cpuidle_coupled_clear_pokes(dev->cpu); + if (need_resched()) { + cpuidle_coupled_set_not_waiting(dev->cpu, coupled); + goto out; + } + + /* + * Make sure final poke status for this cpu is visible before setting + * cpu as ready. + */ + smp_wmb(); + + /* + * All coupled cpus are probably idle. There is a small chance that + * one of the other cpus just became active. Increment the ready count, + * and spin until all coupled cpus have incremented the counter. Once a + * cpu has incremented the ready counter, it cannot abort idle and must + * spin until either all cpus have incremented the ready counter, or + * another cpu leaves idle and decrements the waiting counter. + */ + + cpuidle_coupled_set_ready(coupled); + while (!cpuidle_coupled_cpus_ready(coupled)) { + /* Check if any other cpus bailed out of idle. */ + if (!cpuidle_coupled_cpus_waiting(coupled)) + if (!cpuidle_coupled_set_not_ready(coupled)) + goto retry; + + cpu_relax(); + } + + /* + * Make sure read of all cpus ready is done before reading pending pokes + */ + smp_rmb(); + + /* + * There is a small chance that a cpu left and reentered idle after this + * cpu saw that all cpus were waiting. The cpu that reentered idle will + * have sent this cpu a poke, which will still be pending after the + * ready loop. The pending interrupt may be lost by the interrupt + * controller when entering the deep idle state. It's not possible to + * clear a pending interrupt without turning interrupts on and handling + * it, and it's too late to turn on interrupts here, so reset the + * coupled idle state of all cpus and retry. + */ + if (cpuidle_coupled_any_pokes_pending(coupled)) { + cpuidle_coupled_set_done(dev->cpu, coupled); + /* Wait for all cpus to see the pending pokes */ + cpuidle_coupled_parallel_barrier(dev, &coupled->abort_barrier); + goto reset; + } + + /* all cpus have acked the coupled state */ + next_state = cpuidle_coupled_get_state(dev, coupled); + + entered_state = cpuidle_enter_state(dev, drv, next_state); + + cpuidle_coupled_set_done(dev->cpu, coupled); + +out: + /* + * Normal cpuidle states are expected to return with irqs enabled. + * That leads to an inefficiency where a cpu receiving an interrupt + * that brings it out of idle will process that interrupt before + * exiting the idle enter function and decrementing ready_count. All + * other cpus will need to spin waiting for the cpu that is processing + * the interrupt. If the driver returns with interrupts disabled, + * all other cpus will loop back into the safe idle state instead of + * spinning, saving power. + * + * Calling local_irq_enable here allows coupled states to return with + * interrupts disabled, but won't cause problems for drivers that + * exit with interrupts enabled. + */ + local_irq_enable(); + + /* + * Wait until all coupled cpus have exited idle. There is no risk that + * a cpu exits and re-enters the ready state because this cpu has + * already decremented its waiting_count. + */ + while (!cpuidle_coupled_no_cpus_ready(coupled)) + cpu_relax(); + + return entered_state; +} + +static void cpuidle_coupled_update_online_cpus(struct cpuidle_coupled *coupled) +{ + cpumask_t cpus; + cpumask_and(&cpus, cpu_online_mask, &coupled->coupled_cpus); + coupled->online_count = cpumask_weight(&cpus); +} + +/** + * cpuidle_coupled_register_device - register a coupled cpuidle device + * @dev: struct cpuidle_device for the current cpu + * + * Called from cpuidle_register_device to handle coupled idle init. Finds the + * cpuidle_coupled struct for this set of coupled cpus, or creates one if none + * exists yet. + */ +int cpuidle_coupled_register_device(struct cpuidle_device *dev) +{ + int cpu; + struct cpuidle_device *other_dev; + call_single_data_t *csd; + struct cpuidle_coupled *coupled; + + if (cpumask_empty(&dev->coupled_cpus)) + return 0; + + for_each_cpu(cpu, &dev->coupled_cpus) { + other_dev = per_cpu(cpuidle_devices, cpu); + if (other_dev && other_dev->coupled) { + coupled = other_dev->coupled; + goto have_coupled; + } + } + + /* No existing coupled info found, create a new one */ + coupled = kzalloc(sizeof(struct cpuidle_coupled), GFP_KERNEL); + if (!coupled) + return -ENOMEM; + + coupled->coupled_cpus = dev->coupled_cpus; + +have_coupled: + dev->coupled = coupled; + if (WARN_ON(!cpumask_equal(&dev->coupled_cpus, &coupled->coupled_cpus))) + coupled->prevent++; + + cpuidle_coupled_update_online_cpus(coupled); + + coupled->refcnt++; + + csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu); + csd->func = cpuidle_coupled_handle_poke; + csd->info = (void *)(unsigned long)dev->cpu; + + return 0; +} + +/** + * cpuidle_coupled_unregister_device - unregister a coupled cpuidle device + * @dev: struct cpuidle_device for the current cpu + * + * Called from cpuidle_unregister_device to tear down coupled idle. Removes the + * cpu from the coupled idle set, and frees the cpuidle_coupled_info struct if + * this was the last cpu in the set. + */ +void cpuidle_coupled_unregister_device(struct cpuidle_device *dev) +{ + struct cpuidle_coupled *coupled = dev->coupled; + + if (cpumask_empty(&dev->coupled_cpus)) + return; + + if (--coupled->refcnt) + kfree(coupled); + dev->coupled = NULL; +} + +/** + * cpuidle_coupled_prevent_idle - prevent cpus from entering a coupled state + * @coupled: the struct coupled that contains the cpu that is changing state + * + * Disables coupled cpuidle on a coupled set of cpus. Used to ensure that + * cpu_online_mask doesn't change while cpus are coordinating coupled idle. + */ +static void cpuidle_coupled_prevent_idle(struct cpuidle_coupled *coupled) +{ + int cpu = get_cpu(); + + /* Force all cpus out of the waiting loop. */ + coupled->prevent++; + cpuidle_coupled_poke_others(cpu, coupled); + put_cpu(); + while (!cpuidle_coupled_no_cpus_waiting(coupled)) + cpu_relax(); +} + +/** + * cpuidle_coupled_allow_idle - allows cpus to enter a coupled state + * @coupled: the struct coupled that contains the cpu that is changing state + * + * Enables coupled cpuidle on a coupled set of cpus. Used to ensure that + * cpu_online_mask doesn't change while cpus are coordinating coupled idle. + */ +static void cpuidle_coupled_allow_idle(struct cpuidle_coupled *coupled) +{ + int cpu = get_cpu(); + + /* + * Write barrier ensures readers see the new online_count when they + * see prevent == 0. + */ + smp_wmb(); + coupled->prevent--; + /* Force cpus out of the prevent loop. */ + cpuidle_coupled_poke_others(cpu, coupled); + put_cpu(); +} + +static int coupled_cpu_online(unsigned int cpu) +{ + struct cpuidle_device *dev; + + mutex_lock(&cpuidle_lock); + + dev = per_cpu(cpuidle_devices, cpu); + if (dev && dev->coupled) { + cpuidle_coupled_update_online_cpus(dev->coupled); + cpuidle_coupled_allow_idle(dev->coupled); + } + + mutex_unlock(&cpuidle_lock); + return 0; +} + +static int coupled_cpu_up_prepare(unsigned int cpu) +{ + struct cpuidle_device *dev; + + mutex_lock(&cpuidle_lock); + + dev = per_cpu(cpuidle_devices, cpu); + if (dev && dev->coupled) + cpuidle_coupled_prevent_idle(dev->coupled); + + mutex_unlock(&cpuidle_lock); + return 0; +} + +static int __init cpuidle_coupled_init(void) +{ + int ret; + + ret = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_COUPLED_PREPARE, + "cpuidle/coupled:prepare", + coupled_cpu_up_prepare, + coupled_cpu_online); + if (ret) + return ret; + ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "cpuidle/coupled:online", + coupled_cpu_online, + coupled_cpu_up_prepare); + if (ret < 0) + cpuhp_remove_state_nocalls(CPUHP_CPUIDLE_COUPLED_PREPARE); + return ret; +} +core_initcall(cpuidle_coupled_init); diff --git a/drivers/cpuidle/cpuidle-arm.c b/drivers/cpuidle/cpuidle-arm.c new file mode 100644 index 000000000..df564d783 --- /dev/null +++ b/drivers/cpuidle/cpuidle-arm.c @@ -0,0 +1,187 @@ +/* + * ARM/ARM64 generic CPU idle driver. + * + * Copyright (C) 2014 ARM Ltd. + * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) "CPUidle arm: " 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/slab.h> +#include <linux/topology.h> + +#include <asm/cpuidle.h> + +#include "dt_idle_states.h" + +/* + * arm_enter_idle_state - Programs CPU to enter the specified state + * + * dev: cpuidle device + * drv: cpuidle driver + * idx: state index + * + * Called from the CPUidle framework to program the device to the + * specified target state selected by the governor. + */ +static int arm_enter_idle_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx) +{ + /* + * Pass idle state index to arm_cpuidle_suspend which in turn + * will call the CPU ops suspend protocol with idle index as a + * parameter. + */ + return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, idx); +} + +static struct cpuidle_driver arm_idle_driver __initdata = { + .name = "arm_idle", + .owner = THIS_MODULE, + /* + * State at index 0 is standby wfi and considered standard + * on all ARM platforms. If in some platforms simple wfi + * can't be used as "state 0", DT bindings must be implemented + * to work around this issue and allow installing a special + * handler for idle state index 0. + */ + .states[0] = { + .enter = arm_enter_idle_state, + .exit_latency = 1, + .target_residency = 1, + .power_usage = UINT_MAX, + .name = "WFI", + .desc = "ARM WFI", + } +}; + +static const struct of_device_id arm_idle_state_match[] __initconst = { + { .compatible = "arm,idle-state", + .data = arm_enter_idle_state }, + { }, +}; + +/* + * arm_idle_init_cpu + * + * Registers the arm specific cpuidle driver with the cpuidle + * framework. It relies on core code to parse the idle states + * and initialize them using driver data structures accordingly. + */ +static int __init arm_idle_init_cpu(int cpu) +{ + int ret; + struct cpuidle_driver *drv; + struct cpuidle_device *dev; + + drv = kmemdup(&arm_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. This + * driver is DT only, 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. + */ + ret = dt_init_idle_driver(drv, arm_idle_state_match, 1); + if (ret <= 0) { + ret = ret ? : -ENODEV; + goto out_kfree_drv; + } + + /* + * Call arch CPU operations in order to initialize + * idle states suspend back-end specific data + */ + ret = arm_cpuidle_init(cpu); + + /* + * Allow the initialization to continue for other CPUs, if the reported + * failure is a HW misconfiguration/breakage (-ENXIO). + */ + if (ret) { + pr_err("CPU %d failed to init idle CPU ops\n", cpu); + ret = ret == -ENXIO ? 0 : ret; + goto out_kfree_drv; + } + + ret = cpuidle_register_driver(drv); + if (ret) { + if (ret != -EBUSY) + pr_err("Failed to register cpuidle driver\n"); + goto out_kfree_drv; + } + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) { + ret = -ENOMEM; + goto out_unregister_drv; + } + dev->cpu = cpu; + + ret = cpuidle_register_device(dev); + if (ret) { + pr_err("Failed to register cpuidle device for CPU %d\n", + cpu); + goto out_kfree_dev; + } + + return 0; + +out_kfree_dev: + kfree(dev); +out_unregister_drv: + cpuidle_unregister_driver(drv); +out_kfree_drv: + kfree(drv); + return ret; +} + +/* + * arm_idle_init - Initializes arm cpuidle driver + * + * Initializes arm cpuidle driver for all CPUs, if any CPU fails + * to register cpuidle driver then rollback to cancel all CPUs + * registeration. + */ +static int __init arm_idle_init(void) +{ + int cpu, ret; + struct cpuidle_driver *drv; + struct cpuidle_device *dev; + + for_each_possible_cpu(cpu) { + ret = arm_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_device(dev); + cpuidle_unregister_driver(drv); + kfree(dev); + kfree(drv); + } + + return ret; +} +device_initcall(arm_idle_init); diff --git a/drivers/cpuidle/cpuidle-at91.c b/drivers/cpuidle/cpuidle-at91.c new file mode 100644 index 000000000..9c5853b6c --- /dev/null +++ b/drivers/cpuidle/cpuidle-at91.c @@ -0,0 +1,65 @@ +/* + * based on arch/arm/mach-kirkwood/cpuidle.c + * + * CPU idle support for AT91 SoC + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + * + * The cpu idle uses wait-for-interrupt and RAM self refresh in order + * to implement two idle states - + * #1 wait-for-interrupt + * #2 wait-for-interrupt and RAM self refresh + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/cpuidle.h> +#include <linux/io.h> +#include <linux/export.h> +#include <asm/cpuidle.h> + +#define AT91_MAX_STATES 2 + +static void (*at91_standby)(void); + +/* Actual code that puts the SoC in different idle states */ +static int at91_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + at91_standby(); + return index; +} + +static struct cpuidle_driver at91_idle_driver = { + .name = "at91_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = at91_enter_idle, + .exit_latency = 10, + .target_residency = 10000, + .name = "RAM_SR", + .desc = "WFI and DDR Self Refresh", + }, + .state_count = AT91_MAX_STATES, +}; + +/* Initialize CPU idle by registering the idle states */ +static int at91_cpuidle_probe(struct platform_device *dev) +{ + at91_standby = (void *)(dev->dev.platform_data); + + return cpuidle_register(&at91_idle_driver, NULL); +} + +static struct platform_driver at91_cpuidle_driver = { + .driver = { + .name = "cpuidle-at91", + }, + .probe = at91_cpuidle_probe, +}; +builtin_platform_driver(at91_cpuidle_driver); diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c new file mode 100644 index 000000000..b44476a1b --- /dev/null +++ b/drivers/cpuidle/cpuidle-big_little.c @@ -0,0 +1,233 @@ +/* + * Copyright (c) 2013 ARM/Linaro + * + * Authors: Daniel Lezcano <daniel.lezcano@linaro.org> + * Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * Nicolas Pitre <nicolas.pitre@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Maintainer: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * Maintainer: Daniel Lezcano <daniel.lezcano@linaro.org> + */ +#include <linux/cpuidle.h> +#include <linux/cpu_pm.h> +#include <linux/slab.h> +#include <linux/of.h> + +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/cpuidle.h> +#include <asm/mcpm.h> +#include <asm/smp_plat.h> +#include <asm/suspend.h> + +#include "dt_idle_states.h" + +static int bl_enter_powerdown(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx); + +/* + * NB: Owing to current menu governor behaviour big and LITTLE + * index 1 states have to define exit_latency and target_residency for + * cluster state since, when all CPUs in a cluster hit it, the cluster + * can be shutdown. This means that when a single CPU enters this state + * the exit_latency and target_residency values are somewhat overkill. + * There is no notion of cluster states in the menu governor, so CPUs + * have to define CPU states where possibly the cluster will be shutdown + * depending on the state of other CPUs. idle states entry and exit happen + * at random times; however the cluster state provides target_residency + * values as if all CPUs in a cluster enter the state at once; this is + * somewhat optimistic and behaviour should be fixed either in the governor + * or in the MCPM back-ends. + * To make this driver 100% generic the number of states and the exit_latency + * target_residency values must be obtained from device tree bindings. + * + * exit_latency: refers to the TC2 vexpress test chip and depends on the + * current cluster operating point. It is the time it takes to get the CPU + * up and running when the CPU is powered up on cluster wake-up from shutdown. + * Current values for big and LITTLE clusters are provided for clusters + * running at default operating points. + * + * target_residency: it is the minimum amount of time the cluster has + * to be down to break even in terms of power consumption. cluster + * shutdown has inherent dynamic power costs (L2 writebacks to DRAM + * being the main factor) that depend on the current operating points. + * The current values for both clusters are provided for a CPU whose half + * of L2 lines are dirty and require cleaning to DRAM, and takes into + * account leakage static power values related to the vexpress TC2 testchip. + */ +static struct cpuidle_driver bl_idle_little_driver = { + .name = "little_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = bl_enter_powerdown, + .exit_latency = 700, + .target_residency = 2500, + .flags = CPUIDLE_FLAG_TIMER_STOP, + .name = "C1", + .desc = "ARM little-cluster power down", + }, + .state_count = 2, +}; + +static const struct of_device_id bl_idle_state_match[] __initconst = { + { .compatible = "arm,idle-state", + .data = bl_enter_powerdown }, + { }, +}; + +static struct cpuidle_driver bl_idle_big_driver = { + .name = "big_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = bl_enter_powerdown, + .exit_latency = 500, + .target_residency = 2000, + .flags = CPUIDLE_FLAG_TIMER_STOP, + .name = "C1", + .desc = "ARM big-cluster power down", + }, + .state_count = 2, +}; + +/* + * notrace prevents trace shims from getting inserted where they + * should not. Global jumps and ldrex/strex must not be inserted + * in power down sequences where caches and MMU may be turned off. + */ +static int notrace bl_powerdown_finisher(unsigned long arg) +{ + /* MCPM works with HW CPU identifiers */ + unsigned int mpidr = read_cpuid_mpidr(); + unsigned int cluster = MPIDR_AFFINITY_LEVEL(mpidr, 1); + unsigned int cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + + mcpm_set_entry_vector(cpu, cluster, cpu_resume); + mcpm_cpu_suspend(); + + /* return value != 0 means failure */ + return 1; +} + +/** + * bl_enter_powerdown - Programs CPU to enter the specified state + * @dev: cpuidle device + * @drv: The target state to be programmed + * @idx: state index + * + * Called from the CPUidle framework to program the device to the + * specified target state selected by the governor. + */ +static int bl_enter_powerdown(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int idx) +{ + cpu_pm_enter(); + + cpu_suspend(0, bl_powerdown_finisher); + + /* signals the MCPM core that CPU is out of low power state */ + mcpm_cpu_powered_up(); + + cpu_pm_exit(); + + return idx; +} + +static int __init bl_idle_driver_init(struct cpuidle_driver *drv, int part_id) +{ + struct cpumask *cpumask; + int cpu; + + cpumask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!cpumask) + return -ENOMEM; + + for_each_possible_cpu(cpu) + if (smp_cpuid_part(cpu) == part_id) + cpumask_set_cpu(cpu, cpumask); + + drv->cpumask = cpumask; + + return 0; +} + +static const struct of_device_id compatible_machine_match[] = { + { .compatible = "arm,vexpress,v2p-ca15_a7" }, + { .compatible = "samsung,exynos5420" }, + { .compatible = "samsung,exynos5800" }, + {}, +}; + +static int __init bl_idle_init(void) +{ + int ret; + struct device_node *root = of_find_node_by_path("/"); + const struct of_device_id *match_id; + + if (!root) + return -ENODEV; + + /* + * Initialize the driver just for a compliant set of machines + */ + match_id = of_match_node(compatible_machine_match, root); + + of_node_put(root); + + if (!match_id) + return -ENODEV; + + if (!mcpm_is_available()) + return -EUNATCH; + + /* + * For now the differentiation between little and big cores + * is based on the part number. A7 cores are considered little + * cores, A15 are considered big cores. This distinction may + * evolve in the future with a more generic matching approach. + */ + ret = bl_idle_driver_init(&bl_idle_little_driver, + ARM_CPU_PART_CORTEX_A7); + if (ret) + return ret; + + ret = bl_idle_driver_init(&bl_idle_big_driver, ARM_CPU_PART_CORTEX_A15); + if (ret) + goto out_uninit_little; + + /* Start at index 1, index 0 standard WFI */ + ret = dt_init_idle_driver(&bl_idle_big_driver, bl_idle_state_match, 1); + if (ret < 0) + goto out_uninit_big; + + /* Start at index 1, index 0 standard WFI */ + ret = dt_init_idle_driver(&bl_idle_little_driver, + bl_idle_state_match, 1); + if (ret < 0) + goto out_uninit_big; + + ret = cpuidle_register(&bl_idle_little_driver, NULL); + if (ret) + goto out_uninit_big; + + ret = cpuidle_register(&bl_idle_big_driver, NULL); + if (ret) + goto out_unregister_little; + + return 0; + +out_unregister_little: + cpuidle_unregister(&bl_idle_little_driver); +out_uninit_big: + kfree(bl_idle_big_driver.cpumask); +out_uninit_little: + kfree(bl_idle_little_driver.cpumask); + + return ret; +} +device_initcall(bl_idle_init); diff --git a/drivers/cpuidle/cpuidle-calxeda.c b/drivers/cpuidle/cpuidle-calxeda.c new file mode 100644 index 000000000..ea9728fde --- /dev/null +++ b/drivers/cpuidle/cpuidle-calxeda.c @@ -0,0 +1,83 @@ +/* + * Copyright 2012 Calxeda, Inc. + * + * Based on arch/arm/plat-mxc/cpuidle.c: #v3.7 + * Copyright 2012 Freescale Semiconductor, Inc. + * Copyright 2012 Linaro Ltd. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + * Maintainer: Rob Herring <rob.herring@calxeda.com> + */ + +#include <linux/cpuidle.h> +#include <linux/cpu_pm.h> +#include <linux/init.h> +#include <linux/mm.h> +#include <linux/platform_device.h> +#include <linux/psci.h> + +#include <asm/cpuidle.h> +#include <asm/suspend.h> + +#include <uapi/linux/psci.h> + +#define CALXEDA_IDLE_PARAM \ + ((0 << PSCI_0_2_POWER_STATE_ID_SHIFT) | \ + (0 << PSCI_0_2_POWER_STATE_AFFL_SHIFT) | \ + (PSCI_POWER_STATE_TYPE_POWER_DOWN << PSCI_0_2_POWER_STATE_TYPE_SHIFT)) + +static int calxeda_idle_finish(unsigned long val) +{ + return psci_ops.cpu_suspend(CALXEDA_IDLE_PARAM, __pa(cpu_resume)); +} + +static int calxeda_pwrdown_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + cpu_pm_enter(); + cpu_suspend(0, calxeda_idle_finish); + cpu_pm_exit(); + + return index; +} + +static struct cpuidle_driver calxeda_idle_driver = { + .name = "calxeda_idle", + .states = { + ARM_CPUIDLE_WFI_STATE, + { + .name = "PG", + .desc = "Power Gate", + .exit_latency = 30, + .power_usage = 50, + .target_residency = 200, + .enter = calxeda_pwrdown_idle, + }, + }, + .state_count = 2, +}; + +static int calxeda_cpuidle_probe(struct platform_device *pdev) +{ + return cpuidle_register(&calxeda_idle_driver, NULL); +} + +static struct platform_driver calxeda_cpuidle_plat_driver = { + .driver = { + .name = "cpuidle-calxeda", + }, + .probe = calxeda_cpuidle_probe, +}; +builtin_platform_driver(calxeda_cpuidle_plat_driver); diff --git a/drivers/cpuidle/cpuidle-clps711x.c b/drivers/cpuidle/cpuidle-clps711x.c new file mode 100644 index 000000000..66a9f231e --- /dev/null +++ b/drivers/cpuidle/cpuidle-clps711x.c @@ -0,0 +1,59 @@ +/* + * CLPS711X CPU idle driver + * + * Copyright (C) 2014 Alexander Shiyan <shc_work@mail.ru> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#include <linux/cpuidle.h> +#include <linux/err.h> +#include <linux/io.h> +#include <linux/init.h> +#include <linux/platform_device.h> + +#define CLPS711X_CPUIDLE_NAME "clps711x-cpuidle" + +static void __iomem *clps711x_halt; + +static int clps711x_cpuidle_halt(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + writel(0xaa, clps711x_halt); + + return index; +} + +static struct cpuidle_driver clps711x_idle_driver = { + .name = CLPS711X_CPUIDLE_NAME, + .owner = THIS_MODULE, + .states[0] = { + .name = "HALT", + .desc = "CLPS711X HALT", + .enter = clps711x_cpuidle_halt, + .exit_latency = 1, + }, + .state_count = 1, +}; + +static int __init clps711x_cpuidle_probe(struct platform_device *pdev) +{ + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + clps711x_halt = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(clps711x_halt)) + return PTR_ERR(clps711x_halt); + + return cpuidle_register(&clps711x_idle_driver, NULL); +} + +static struct platform_driver clps711x_cpuidle_driver = { + .driver = { + .name = CLPS711X_CPUIDLE_NAME, + }, +}; +builtin_platform_driver_probe(clps711x_cpuidle_driver, clps711x_cpuidle_probe); diff --git a/drivers/cpuidle/cpuidle-cps.c b/drivers/cpuidle/cpuidle-cps.c new file mode 100644 index 000000000..dac8ff639 --- /dev/null +++ b/drivers/cpuidle/cpuidle-cps.c @@ -0,0 +1,182 @@ +/* + * Copyright (C) 2014 Imagination Technologies + * Author: Paul Burton <paul.burton@mips.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + */ + +#include <linux/cpu_pm.h> +#include <linux/cpuidle.h> +#include <linux/init.h> + +#include <asm/idle.h> +#include <asm/pm-cps.h> + +/* Enumeration of the various idle states this driver may enter */ +enum cps_idle_state { + STATE_WAIT = 0, /* MIPS wait instruction, coherent */ + STATE_NC_WAIT, /* MIPS wait instruction, non-coherent */ + STATE_CLOCK_GATED, /* Core clock gated */ + STATE_POWER_GATED, /* Core power gated */ + STATE_COUNT +}; + +static int cps_nc_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + enum cps_pm_state pm_state; + int err; + + /* + * At least one core must remain powered up & clocked in order for the + * system to have any hope of functioning. + * + * TODO: don't treat core 0 specially, just prevent the final core + * TODO: remap interrupt affinity temporarily + */ + if (cpus_are_siblings(0, dev->cpu) && (index > STATE_NC_WAIT)) + index = STATE_NC_WAIT; + + /* Select the appropriate cps_pm_state */ + switch (index) { + case STATE_NC_WAIT: + pm_state = CPS_PM_NC_WAIT; + break; + case STATE_CLOCK_GATED: + pm_state = CPS_PM_CLOCK_GATED; + break; + case STATE_POWER_GATED: + pm_state = CPS_PM_POWER_GATED; + break; + default: + BUG(); + return -EINVAL; + } + + /* Notify listeners the CPU is about to power down */ + if ((pm_state == CPS_PM_POWER_GATED) && cpu_pm_enter()) + return -EINTR; + + /* Enter that state */ + err = cps_pm_enter_state(pm_state); + + /* Notify listeners the CPU is back up */ + if (pm_state == CPS_PM_POWER_GATED) + cpu_pm_exit(); + + return err ?: index; +} + +static struct cpuidle_driver cps_driver = { + .name = "cpc_cpuidle", + .owner = THIS_MODULE, + .states = { + [STATE_WAIT] = MIPS_CPUIDLE_WAIT_STATE, + [STATE_NC_WAIT] = { + .enter = cps_nc_enter, + .exit_latency = 200, + .target_residency = 450, + .name = "nc-wait", + .desc = "non-coherent MIPS wait", + }, + [STATE_CLOCK_GATED] = { + .enter = cps_nc_enter, + .exit_latency = 300, + .target_residency = 700, + .flags = CPUIDLE_FLAG_TIMER_STOP, + .name = "clock-gated", + .desc = "core clock gated", + }, + [STATE_POWER_GATED] = { + .enter = cps_nc_enter, + .exit_latency = 600, + .target_residency = 1000, + .flags = CPUIDLE_FLAG_TIMER_STOP, + .name = "power-gated", + .desc = "core power gated", + }, + }, + .state_count = STATE_COUNT, + .safe_state_index = 0, +}; + +static void __init cps_cpuidle_unregister(void) +{ + int cpu; + struct cpuidle_device *device; + + for_each_possible_cpu(cpu) { + device = &per_cpu(cpuidle_dev, cpu); + cpuidle_unregister_device(device); + } + + cpuidle_unregister_driver(&cps_driver); +} + +static int __init cps_cpuidle_init(void) +{ + int err, cpu, i; + struct cpuidle_device *device; + + /* Detect supported states */ + if (!cps_pm_support_state(CPS_PM_POWER_GATED)) + cps_driver.state_count = STATE_CLOCK_GATED + 1; + if (!cps_pm_support_state(CPS_PM_CLOCK_GATED)) + cps_driver.state_count = STATE_NC_WAIT + 1; + if (!cps_pm_support_state(CPS_PM_NC_WAIT)) + cps_driver.state_count = STATE_WAIT + 1; + + /* Inform the user if some states are unavailable */ + if (cps_driver.state_count < STATE_COUNT) { + pr_info("cpuidle-cps: limited to "); + switch (cps_driver.state_count - 1) { + case STATE_WAIT: + pr_cont("coherent wait\n"); + break; + case STATE_NC_WAIT: + pr_cont("non-coherent wait\n"); + break; + case STATE_CLOCK_GATED: + pr_cont("clock gating\n"); + break; + } + } + + /* + * Set the coupled flag on the appropriate states if this system + * requires it. + */ + if (coupled_coherence) + for (i = STATE_NC_WAIT; i < cps_driver.state_count; i++) + cps_driver.states[i].flags |= CPUIDLE_FLAG_COUPLED; + + err = cpuidle_register_driver(&cps_driver); + if (err) { + pr_err("Failed to register CPS cpuidle driver\n"); + return err; + } + + for_each_possible_cpu(cpu) { + device = &per_cpu(cpuidle_dev, cpu); + device->cpu = cpu; +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED + cpumask_copy(&device->coupled_cpus, &cpu_sibling_map[cpu]); +#endif + + err = cpuidle_register_device(device); + if (err) { + pr_err("Failed to register CPU%d cpuidle device\n", + cpu); + goto err_out; + } + } + + return 0; +err_out: + cps_cpuidle_unregister(); + return err; +} +device_initcall(cps_cpuidle_init); diff --git a/drivers/cpuidle/cpuidle-exynos.c b/drivers/cpuidle/cpuidle-exynos.c new file mode 100644 index 000000000..0171a6e19 --- /dev/null +++ b/drivers/cpuidle/cpuidle-exynos.c @@ -0,0 +1,146 @@ +/* + * Copyright (c) 2011-2014 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Coupled cpuidle support based on the work of: + * Colin Cross <ccross@android.com> + * Daniel Lezcano <daniel.lezcano@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. +*/ + +#include <linux/cpuidle.h> +#include <linux/cpu_pm.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/of.h> +#include <linux/platform_data/cpuidle-exynos.h> + +#include <asm/suspend.h> +#include <asm/cpuidle.h> + +static atomic_t exynos_idle_barrier; + +static struct cpuidle_exynos_data *exynos_cpuidle_pdata; +static void (*exynos_enter_aftr)(void); + +static int exynos_enter_coupled_lowpower(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + int ret; + + exynos_cpuidle_pdata->pre_enter_aftr(); + + /* + * Waiting all cpus to reach this point at the same moment + */ + cpuidle_coupled_parallel_barrier(dev, &exynos_idle_barrier); + + /* + * Both cpus will reach this point at the same time + */ + ret = dev->cpu ? exynos_cpuidle_pdata->cpu1_powerdown() + : exynos_cpuidle_pdata->cpu0_enter_aftr(); + if (ret) + index = ret; + + /* + * Waiting all cpus to finish the power sequence before going further + */ + cpuidle_coupled_parallel_barrier(dev, &exynos_idle_barrier); + + exynos_cpuidle_pdata->post_enter_aftr(); + + return index; +} + +static int exynos_enter_lowpower(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + int new_index = index; + + /* AFTR can only be entered when cores other than CPU0 are offline */ + if (num_online_cpus() > 1 || dev->cpu != 0) + new_index = drv->safe_state_index; + + if (new_index == 0) + return arm_cpuidle_simple_enter(dev, drv, new_index); + + exynos_enter_aftr(); + + return new_index; +} + +static struct cpuidle_driver exynos_idle_driver = { + .name = "exynos_idle", + .owner = THIS_MODULE, + .states = { + [0] = ARM_CPUIDLE_WFI_STATE, + [1] = { + .enter = exynos_enter_lowpower, + .exit_latency = 300, + .target_residency = 100000, + .name = "C1", + .desc = "ARM power down", + }, + }, + .state_count = 2, + .safe_state_index = 0, +}; + +static struct cpuidle_driver exynos_coupled_idle_driver = { + .name = "exynos_coupled_idle", + .owner = THIS_MODULE, + .states = { + [0] = ARM_CPUIDLE_WFI_STATE, + [1] = { + .enter = exynos_enter_coupled_lowpower, + .exit_latency = 5000, + .target_residency = 10000, + .flags = CPUIDLE_FLAG_COUPLED | + CPUIDLE_FLAG_TIMER_STOP, + .name = "C1", + .desc = "ARM power down", + }, + }, + .state_count = 2, + .safe_state_index = 0, +}; + +static int exynos_cpuidle_probe(struct platform_device *pdev) +{ + int ret; + + if (IS_ENABLED(CONFIG_SMP) && + (of_machine_is_compatible("samsung,exynos4210") || + of_machine_is_compatible("samsung,exynos3250"))) { + exynos_cpuidle_pdata = pdev->dev.platform_data; + + ret = cpuidle_register(&exynos_coupled_idle_driver, + cpu_possible_mask); + } else { + exynos_enter_aftr = (void *)(pdev->dev.platform_data); + + ret = cpuidle_register(&exynos_idle_driver, NULL); + } + + if (ret) { + dev_err(&pdev->dev, "failed to register cpuidle driver\n"); + return ret; + } + + return 0; +} + +static struct platform_driver exynos_cpuidle_driver = { + .probe = exynos_cpuidle_probe, + .driver = { + .name = "exynos_cpuidle", + }, +}; +builtin_platform_driver(exynos_cpuidle_driver); diff --git a/drivers/cpuidle/cpuidle-kirkwood.c b/drivers/cpuidle/cpuidle-kirkwood.c new file mode 100644 index 000000000..d23d8f468 --- /dev/null +++ b/drivers/cpuidle/cpuidle-kirkwood.c @@ -0,0 +1,87 @@ +/* + * CPU idle Marvell Kirkwood SoCs + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + * + * The cpu idle uses wait-for-interrupt and DDR self refresh in order + * to implement two idle states - + * #1 wait-for-interrupt + * #2 wait-for-interrupt and DDR self refresh + * + * Maintainer: Jason Cooper <jason@lakedaemon.net> + * Maintainer: Andrew Lunn <andrew@lunn.ch> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/cpuidle.h> +#include <linux/io.h> +#include <linux/export.h> +#include <asm/cpuidle.h> + +#define KIRKWOOD_MAX_STATES 2 + +static void __iomem *ddr_operation_base; + +/* Actual code that puts the SoC in different idle states */ +static int kirkwood_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + writel(0x7, ddr_operation_base); + cpu_do_idle(); + + return index; +} + +static struct cpuidle_driver kirkwood_idle_driver = { + .name = "kirkwood_idle", + .owner = THIS_MODULE, + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = kirkwood_enter_idle, + .exit_latency = 10, + .target_residency = 100000, + .name = "DDR SR", + .desc = "WFI and DDR Self Refresh", + }, + .state_count = KIRKWOOD_MAX_STATES, +}; + +/* Initialize CPU idle by registering the idle states */ +static int kirkwood_cpuidle_probe(struct platform_device *pdev) +{ + struct resource *res; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + ddr_operation_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(ddr_operation_base)) + return PTR_ERR(ddr_operation_base); + + return cpuidle_register(&kirkwood_idle_driver, NULL); +} + +static int kirkwood_cpuidle_remove(struct platform_device *pdev) +{ + cpuidle_unregister(&kirkwood_idle_driver); + return 0; +} + +static struct platform_driver kirkwood_cpuidle_driver = { + .probe = kirkwood_cpuidle_probe, + .remove = kirkwood_cpuidle_remove, + .driver = { + .name = "kirkwood_cpuidle", + }, +}; + +module_platform_driver(kirkwood_cpuidle_driver); + +MODULE_AUTHOR("Andrew Lunn <andrew@lunn.ch>"); +MODULE_DESCRIPTION("Kirkwood cpu idle driver"); +MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("platform:kirkwood-cpuidle"); diff --git a/drivers/cpuidle/cpuidle-mvebu-v7.c b/drivers/cpuidle/cpuidle-mvebu-v7.c new file mode 100644 index 000000000..01a856971 --- /dev/null +++ b/drivers/cpuidle/cpuidle-mvebu-v7.c @@ -0,0 +1,139 @@ +/* + * Marvell Armada 370, 38x and XP SoC cpuidle driver + * + * Copyright (C) 2014 Marvell + * + * Nadav Haklai <nadavh@marvell.com> + * Gregory CLEMENT <gregory.clement@free-electrons.com> + * + * This file is licensed under the terms of the GNU General Public + * License version 2. This program is licensed "as is" without any + * warranty of any kind, whether express or implied. + * + * Maintainer: Gregory CLEMENT <gregory.clement@free-electrons.com> + */ + +#include <linux/cpu_pm.h> +#include <linux/cpuidle.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/suspend.h> +#include <linux/platform_device.h> +#include <asm/cpuidle.h> + +#define MVEBU_V7_FLAG_DEEP_IDLE 0x10000 + +static int (*mvebu_v7_cpu_suspend)(int); + +static int mvebu_v7_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + int ret; + bool deepidle = false; + cpu_pm_enter(); + + if (drv->states[index].flags & MVEBU_V7_FLAG_DEEP_IDLE) + deepidle = true; + + ret = mvebu_v7_cpu_suspend(deepidle); + cpu_pm_exit(); + + if (ret) + return ret; + + return index; +} + +static struct cpuidle_driver armadaxp_idle_driver = { + .name = "armada_xp_idle", + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = mvebu_v7_enter_idle, + .exit_latency = 100, + .power_usage = 50, + .target_residency = 1000, + .name = "MV CPU IDLE", + .desc = "CPU power down", + }, + .states[2] = { + .enter = mvebu_v7_enter_idle, + .exit_latency = 1000, + .power_usage = 5, + .target_residency = 10000, + .flags = MVEBU_V7_FLAG_DEEP_IDLE, + .name = "MV CPU DEEP IDLE", + .desc = "CPU and L2 Fabric power down", + }, + .state_count = 3, +}; + +static struct cpuidle_driver armada370_idle_driver = { + .name = "armada_370_idle", + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = mvebu_v7_enter_idle, + .exit_latency = 100, + .power_usage = 5, + .target_residency = 1000, + .flags = MVEBU_V7_FLAG_DEEP_IDLE, + .name = "Deep Idle", + .desc = "CPU and L2 Fabric power down", + }, + .state_count = 2, +}; + +static struct cpuidle_driver armada38x_idle_driver = { + .name = "armada_38x_idle", + .states[0] = ARM_CPUIDLE_WFI_STATE, + .states[1] = { + .enter = mvebu_v7_enter_idle, + .exit_latency = 10, + .power_usage = 5, + .target_residency = 100, + .name = "Idle", + .desc = "CPU and SCU power down", + }, + .state_count = 2, +}; + +static int mvebu_v7_cpuidle_probe(struct platform_device *pdev) +{ + const struct platform_device_id *id = pdev->id_entry; + + if (!id) + return -EINVAL; + + mvebu_v7_cpu_suspend = pdev->dev.platform_data; + + return cpuidle_register((struct cpuidle_driver *)id->driver_data, NULL); +} + +static const struct platform_device_id mvebu_cpuidle_ids[] = { + { + .name = "cpuidle-armada-xp", + .driver_data = (unsigned long)&armadaxp_idle_driver, + }, { + .name = "cpuidle-armada-370", + .driver_data = (unsigned long)&armada370_idle_driver, + }, { + .name = "cpuidle-armada-38x", + .driver_data = (unsigned long)&armada38x_idle_driver, + }, + {} +}; + +static struct platform_driver mvebu_cpuidle_driver = { + .probe = mvebu_v7_cpuidle_probe, + .driver = { + .name = "cpuidle-mbevu", + .suppress_bind_attrs = true, + }, + .id_table = mvebu_cpuidle_ids, +}; + +builtin_platform_driver(mvebu_cpuidle_driver); + +MODULE_AUTHOR("Gregory CLEMENT <gregory.clement@free-electrons.com>"); +MODULE_DESCRIPTION("Marvell EBU v7 cpuidle driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/cpuidle/cpuidle-powernv.c b/drivers/cpuidle/cpuidle-powernv.c new file mode 100644 index 000000000..84b1ebe21 --- /dev/null +++ b/drivers/cpuidle/cpuidle-powernv.c @@ -0,0 +1,420 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * cpuidle-powernv - idle state cpuidle driver. + * Adapted from drivers/cpuidle/cpuidle-pseries + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/moduleparam.h> +#include <linux/cpuidle.h> +#include <linux/cpu.h> +#include <linux/notifier.h> +#include <linux/clockchips.h> +#include <linux/of.h> +#include <linux/slab.h> + +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/opal.h> +#include <asm/runlatch.h> +#include <asm/cpuidle.h> + +/* + * Expose only those Hardware idle states via the cpuidle framework + * that have latency value below POWERNV_THRESHOLD_LATENCY_NS. + */ +#define POWERNV_THRESHOLD_LATENCY_NS 200000 + +static struct cpuidle_driver powernv_idle_driver = { + .name = "powernv_idle", + .owner = THIS_MODULE, +}; + +static int max_idle_state __read_mostly; +static struct cpuidle_state *cpuidle_state_table __read_mostly; + +struct stop_psscr_table { + u64 val; + u64 mask; +}; + +static struct stop_psscr_table stop_psscr_table[CPUIDLE_STATE_MAX] __read_mostly; + +static u64 default_snooze_timeout __read_mostly; +static bool snooze_timeout_en __read_mostly; + +static u64 get_snooze_timeout(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + int i; + + if (unlikely(!snooze_timeout_en)) + return default_snooze_timeout; + + for (i = index + 1; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable) + continue; + + return s->target_residency * tb_ticks_per_usec; + } + + return default_snooze_timeout; +} + +static int snooze_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + u64 snooze_exit_time; + + set_thread_flag(TIF_POLLING_NRFLAG); + + local_irq_enable(); + + snooze_exit_time = get_tb() + get_snooze_timeout(dev, drv, index); + ppc64_runlatch_off(); + HMT_very_low(); + while (!need_resched()) { + if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) { + /* + * Task has not woken up but we are exiting the polling + * loop anyway. Require a barrier after polling is + * cleared to order subsequent test of need_resched(). + */ + clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb(); + break; + } + } + + HMT_medium(); + ppc64_runlatch_on(); + clear_thread_flag(TIF_POLLING_NRFLAG); + + local_irq_disable(); + + return index; +} + +static int nap_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + power7_idle_type(PNV_THREAD_NAP); + + return index; +} + +/* Register for fastsleep only in oneshot mode of broadcast */ +#ifdef CONFIG_TICK_ONESHOT +static int fastsleep_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long old_lpcr = mfspr(SPRN_LPCR); + unsigned long new_lpcr; + + if (unlikely(system_state < SYSTEM_RUNNING)) + return index; + + new_lpcr = old_lpcr; + /* Do not exit powersave upon decrementer as we've setup the timer + * offload. + */ + new_lpcr &= ~LPCR_PECE1; + + mtspr(SPRN_LPCR, new_lpcr); + + power7_idle_type(PNV_THREAD_SLEEP); + + mtspr(SPRN_LPCR, old_lpcr); + + return index; +} +#endif + +static int stop_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + power9_idle_type(stop_psscr_table[index].val, + stop_psscr_table[index].mask); + return index; +} + +/* + * States for dedicated partition case. + */ +static struct cpuidle_state powernv_states[CPUIDLE_STATE_MAX] = { + { /* Snooze */ + .name = "snooze", + .desc = "snooze", + .exit_latency = 0, + .target_residency = 0, + .enter = snooze_loop }, +}; + +static int powernv_cpuidle_cpu_online(unsigned int cpu) +{ + struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); + + if (dev && cpuidle_get_driver()) { + cpuidle_pause_and_lock(); + cpuidle_enable_device(dev); + cpuidle_resume_and_unlock(); + } + return 0; +} + +static int powernv_cpuidle_cpu_dead(unsigned int cpu) +{ + struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); + + if (dev && cpuidle_get_driver()) { + cpuidle_pause_and_lock(); + cpuidle_disable_device(dev); + cpuidle_resume_and_unlock(); + } + return 0; +} + +/* + * powernv_cpuidle_driver_init() + */ +static int powernv_cpuidle_driver_init(void) +{ + int idle_state; + struct cpuidle_driver *drv = &powernv_idle_driver; + + drv->state_count = 0; + + for (idle_state = 0; idle_state < max_idle_state; ++idle_state) { + /* Is the state not enabled? */ + if (cpuidle_state_table[idle_state].enter == NULL) + continue; + + drv->states[drv->state_count] = /* structure copy */ + cpuidle_state_table[idle_state]; + + drv->state_count += 1; + } + + /* + * On the PowerNV platform cpu_present may be less than cpu_possible in + * cases when firmware detects the CPU, but it is not available to the + * OS. If CONFIG_HOTPLUG_CPU=n, then such CPUs are not hotplugable at + * run time and hence cpu_devices are not created for those CPUs by the + * generic topology_init(). + * + * drv->cpumask defaults to cpu_possible_mask in + * __cpuidle_driver_init(). This breaks cpuidle on PowerNV where + * cpu_devices are not created for CPUs in cpu_possible_mask that + * cannot be hot-added later at run time. + * + * Trying cpuidle_register_device() on a CPU without a cpu_device is + * incorrect, so pass a correct CPU mask to the generic cpuidle driver. + */ + + drv->cpumask = (struct cpumask *)cpu_present_mask; + + return 0; +} + +static inline void add_powernv_state(int index, const char *name, + unsigned int flags, + int (*idle_fn)(struct cpuidle_device *, + struct cpuidle_driver *, + int), + unsigned int target_residency, + unsigned int exit_latency, + u64 psscr_val, u64 psscr_mask) +{ + strlcpy(powernv_states[index].name, name, CPUIDLE_NAME_LEN); + strlcpy(powernv_states[index].desc, name, CPUIDLE_NAME_LEN); + powernv_states[index].flags = flags; + powernv_states[index].target_residency = target_residency; + powernv_states[index].exit_latency = exit_latency; + powernv_states[index].enter = idle_fn; + /* For power8 and below psscr_* will be 0 */ + stop_psscr_table[index].val = psscr_val; + stop_psscr_table[index].mask = psscr_mask; +} + +/* + * Returns 0 if prop1_len == prop2_len. Else returns -1 + */ +static inline int validate_dt_prop_sizes(const char *prop1, int prop1_len, + const char *prop2, int prop2_len) +{ + if (prop1_len == prop2_len) + return 0; + + pr_warn("cpuidle-powernv: array sizes don't match for %s and %s\n", + prop1, prop2); + return -1; +} + +extern u32 pnv_get_supported_cpuidle_states(void); +static int powernv_add_idle_states(void) +{ + int nr_idle_states = 1; /* Snooze */ + int dt_idle_states; + u32 has_stop_states = 0; + int i; + u32 supported_flags = pnv_get_supported_cpuidle_states(); + + + /* Currently we have snooze statically defined */ + if (nr_pnv_idle_states <= 0) { + pr_warn("cpuidle-powernv : Only Snooze is available\n"); + goto out; + } + + /* TODO: Count only states which are eligible for cpuidle */ + dt_idle_states = nr_pnv_idle_states; + + /* + * Since snooze is used as first idle state, max idle states allowed is + * CPUIDLE_STATE_MAX -1 + */ + if (nr_pnv_idle_states > CPUIDLE_STATE_MAX - 1) { + pr_warn("cpuidle-powernv: discovered idle states more than allowed"); + dt_idle_states = CPUIDLE_STATE_MAX - 1; + } + + /* + * If the idle states use stop instruction, probe for psscr values + * and psscr mask which are necessary to specify required stop level. + */ + has_stop_states = (pnv_idle_states[0].flags & + (OPAL_PM_STOP_INST_FAST | OPAL_PM_STOP_INST_DEEP)); + + for (i = 0; i < dt_idle_states; i++) { + unsigned int exit_latency, target_residency; + bool stops_timebase = false; + struct pnv_idle_states_t *state = &pnv_idle_states[i]; + + /* + * Skip the platform idle state whose flag isn't in + * the supported_cpuidle_states flag mask. + */ + if ((state->flags & supported_flags) != state->flags) + continue; + /* + * If an idle state has exit latency beyond + * POWERNV_THRESHOLD_LATENCY_NS then don't use it + * in cpu-idle. + */ + if (state->latency_ns > POWERNV_THRESHOLD_LATENCY_NS) + continue; + /* + * Firmware passes residency and latency values in ns. + * cpuidle expects it in us. + */ + exit_latency = DIV_ROUND_UP(state->latency_ns, 1000); + target_residency = DIV_ROUND_UP(state->residency_ns, 1000); + + if (has_stop_states && !(state->valid)) + continue; + + if (state->flags & OPAL_PM_TIMEBASE_STOP) + stops_timebase = true; + + if (state->flags & OPAL_PM_NAP_ENABLED) { + /* Add NAP state */ + add_powernv_state(nr_idle_states, "Nap", + CPUIDLE_FLAG_NONE, nap_loop, + target_residency, exit_latency, 0, 0); + } else if (has_stop_states && !stops_timebase) { + add_powernv_state(nr_idle_states, state->name, + CPUIDLE_FLAG_NONE, stop_loop, + target_residency, exit_latency, + state->psscr_val, + state->psscr_mask); + } + + /* + * All cpuidle states with CPUIDLE_FLAG_TIMER_STOP set must come + * within this config dependency check. + */ +#ifdef CONFIG_TICK_ONESHOT + else if (state->flags & OPAL_PM_SLEEP_ENABLED || + state->flags & OPAL_PM_SLEEP_ENABLED_ER1) { + /* Add FASTSLEEP state */ + add_powernv_state(nr_idle_states, "FastSleep", + CPUIDLE_FLAG_TIMER_STOP, + fastsleep_loop, + target_residency, exit_latency, 0, 0); + } else if (has_stop_states && stops_timebase) { + add_powernv_state(nr_idle_states, state->name, + CPUIDLE_FLAG_TIMER_STOP, stop_loop, + target_residency, exit_latency, + state->psscr_val, + state->psscr_mask); + } +#endif + else + continue; + nr_idle_states++; + } +out: + return nr_idle_states; +} + +/* + * powernv_idle_probe() + * Choose state table for shared versus dedicated partition + */ +static int powernv_idle_probe(void) +{ + if (cpuidle_disable != IDLE_NO_OVERRIDE) + return -ENODEV; + + if (firmware_has_feature(FW_FEATURE_OPAL)) { + cpuidle_state_table = powernv_states; + /* Device tree can indicate more idle states */ + max_idle_state = powernv_add_idle_states(); + default_snooze_timeout = TICK_USEC * tb_ticks_per_usec; + if (max_idle_state > 1) + snooze_timeout_en = true; + } else + return -ENODEV; + + return 0; +} + +static int __init powernv_processor_idle_init(void) +{ + int retval; + + retval = powernv_idle_probe(); + if (retval) + return retval; + + powernv_cpuidle_driver_init(); + retval = cpuidle_register(&powernv_idle_driver, NULL); + if (retval) { + printk(KERN_DEBUG "Registration of powernv driver failed.\n"); + return retval; + } + + retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "cpuidle/powernv:online", + powernv_cpuidle_cpu_online, NULL); + WARN_ON(retval < 0); + retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD, + "cpuidle/powernv:dead", NULL, + powernv_cpuidle_cpu_dead); + WARN_ON(retval < 0); + printk(KERN_DEBUG "powernv_idle_driver registered\n"); + return 0; +} + +device_initcall(powernv_processor_idle_init); diff --git a/drivers/cpuidle/cpuidle-pseries.c b/drivers/cpuidle/cpuidle-pseries.c new file mode 100644 index 000000000..74c247972 --- /dev/null +++ b/drivers/cpuidle/cpuidle-pseries.c @@ -0,0 +1,301 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * cpuidle-pseries - idle state cpuidle driver. + * Adapted from drivers/idle/intel_idle.c and + * drivers/acpi/processor_idle.c + * + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/moduleparam.h> +#include <linux/cpuidle.h> +#include <linux/cpu.h> +#include <linux/notifier.h> + +#include <asm/paca.h> +#include <asm/reg.h> +#include <asm/machdep.h> +#include <asm/firmware.h> +#include <asm/runlatch.h> +#include <asm/plpar_wrappers.h> + +struct cpuidle_driver pseries_idle_driver = { + .name = "pseries_idle", + .owner = THIS_MODULE, +}; + +static int max_idle_state __read_mostly; +static struct cpuidle_state *cpuidle_state_table __read_mostly; +static u64 snooze_timeout __read_mostly; +static bool snooze_timeout_en __read_mostly; + +static inline void idle_loop_prolog(unsigned long *in_purr) +{ + ppc64_runlatch_off(); + *in_purr = mfspr(SPRN_PURR); + /* + * Indicate to the HV that we are idle. Now would be + * a good time to find other work to dispatch. + */ + get_lppaca()->idle = 1; +} + +static inline void idle_loop_epilog(unsigned long in_purr) +{ + u64 wait_cycles; + + wait_cycles = be64_to_cpu(get_lppaca()->wait_state_cycles); + wait_cycles += mfspr(SPRN_PURR) - in_purr; + get_lppaca()->wait_state_cycles = cpu_to_be64(wait_cycles); + get_lppaca()->idle = 0; + + ppc64_runlatch_on(); +} + +static int snooze_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long in_purr; + u64 snooze_exit_time; + + set_thread_flag(TIF_POLLING_NRFLAG); + + idle_loop_prolog(&in_purr); + local_irq_enable(); + snooze_exit_time = get_tb() + snooze_timeout; + + while (!need_resched()) { + HMT_low(); + HMT_very_low(); + if (likely(snooze_timeout_en) && get_tb() > snooze_exit_time) { + /* + * Task has not woken up but we are exiting the polling + * loop anyway. Require a barrier after polling is + * cleared to order subsequent test of need_resched(). + */ + clear_thread_flag(TIF_POLLING_NRFLAG); + smp_mb(); + break; + } + } + + HMT_medium(); + clear_thread_flag(TIF_POLLING_NRFLAG); + + local_irq_disable(); + + idle_loop_epilog(in_purr); + + return index; +} + +static void check_and_cede_processor(void) +{ + /* + * Ensure our interrupt state is properly tracked, + * also checks if no interrupt has occurred while we + * were soft-disabled + */ + if (prep_irq_for_idle()) { + cede_processor(); +#ifdef CONFIG_TRACE_IRQFLAGS + /* Ensure that H_CEDE returns with IRQs on */ + if (WARN_ON(!(mfmsr() & MSR_EE))) + __hard_irq_enable(); +#endif + } +} + +static int dedicated_cede_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long in_purr; + + idle_loop_prolog(&in_purr); + get_lppaca()->donate_dedicated_cpu = 1; + + HMT_medium(); + check_and_cede_processor(); + + local_irq_disable(); + get_lppaca()->donate_dedicated_cpu = 0; + + idle_loop_epilog(in_purr); + + return index; +} + +static int shared_cede_loop(struct cpuidle_device *dev, + struct cpuidle_driver *drv, + int index) +{ + unsigned long in_purr; + + idle_loop_prolog(&in_purr); + + /* + * Yield the processor to the hypervisor. We return if + * an external interrupt occurs (which are driven prior + * to returning here) or if a prod occurs from another + * processor. When returning here, external interrupts + * are enabled. + */ + check_and_cede_processor(); + + local_irq_disable(); + idle_loop_epilog(in_purr); + + return index; +} + +/* + * States for dedicated partition case. + */ +static struct cpuidle_state dedicated_states[] = { + { /* Snooze */ + .name = "snooze", + .desc = "snooze", + .exit_latency = 0, + .target_residency = 0, + .enter = &snooze_loop }, + { /* CEDE */ + .name = "CEDE", + .desc = "CEDE", + .exit_latency = 10, + .target_residency = 100, + .enter = &dedicated_cede_loop }, +}; + +/* + * States for shared partition case. + */ +static struct cpuidle_state shared_states[] = { + { /* Snooze */ + .name = "snooze", + .desc = "snooze", + .exit_latency = 0, + .target_residency = 0, + .enter = &snooze_loop }, + { /* Shared Cede */ + .name = "Shared Cede", + .desc = "Shared Cede", + .exit_latency = 10, + .target_residency = 100, + .enter = &shared_cede_loop }, +}; + +static int pseries_cpuidle_cpu_online(unsigned int cpu) +{ + struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); + + if (dev && cpuidle_get_driver()) { + cpuidle_pause_and_lock(); + cpuidle_enable_device(dev); + cpuidle_resume_and_unlock(); + } + return 0; +} + +static int pseries_cpuidle_cpu_dead(unsigned int cpu) +{ + struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu); + + if (dev && cpuidle_get_driver()) { + cpuidle_pause_and_lock(); + cpuidle_disable_device(dev); + cpuidle_resume_and_unlock(); + } + return 0; +} + +/* + * pseries_cpuidle_driver_init() + */ +static int pseries_cpuidle_driver_init(void) +{ + int idle_state; + struct cpuidle_driver *drv = &pseries_idle_driver; + + drv->state_count = 0; + + for (idle_state = 0; idle_state < max_idle_state; ++idle_state) { + /* Is the state not enabled? */ + if (cpuidle_state_table[idle_state].enter == NULL) + continue; + + drv->states[drv->state_count] = /* structure copy */ + cpuidle_state_table[idle_state]; + + drv->state_count += 1; + } + + return 0; +} + +/* + * pseries_idle_probe() + * Choose state table for shared versus dedicated partition + */ +static int pseries_idle_probe(void) +{ + + if (cpuidle_disable != IDLE_NO_OVERRIDE) + return -ENODEV; + + if (firmware_has_feature(FW_FEATURE_SPLPAR)) { + /* + * Use local_paca instead of get_lppaca() since + * preemption is not disabled, and it is not required in + * fact, since lppaca_ptr does not need to be the value + * associated to the current CPU, it can be from any CPU. + */ + if (lppaca_shared_proc(local_paca->lppaca_ptr)) { + cpuidle_state_table = shared_states; + max_idle_state = ARRAY_SIZE(shared_states); + } else { + cpuidle_state_table = dedicated_states; + max_idle_state = ARRAY_SIZE(dedicated_states); + } + } else + return -ENODEV; + + if (max_idle_state > 1) { + snooze_timeout_en = true; + snooze_timeout = cpuidle_state_table[1].target_residency * + tb_ticks_per_usec; + } + return 0; +} + +static int __init pseries_processor_idle_init(void) +{ + int retval; + + retval = pseries_idle_probe(); + if (retval) + return retval; + + pseries_cpuidle_driver_init(); + retval = cpuidle_register(&pseries_idle_driver, NULL); + if (retval) { + printk(KERN_DEBUG "Registration of pseries driver failed.\n"); + return retval; + } + + retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, + "cpuidle/pseries:online", + pseries_cpuidle_cpu_online, NULL); + WARN_ON(retval < 0); + retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD, + "cpuidle/pseries:DEAD", NULL, + pseries_cpuidle_cpu_dead); + WARN_ON(retval < 0); + printk(KERN_DEBUG "pseries_idle_driver registered\n"); + return 0; +} + +device_initcall(pseries_processor_idle_init); diff --git a/drivers/cpuidle/cpuidle-ux500.c b/drivers/cpuidle/cpuidle-ux500.c new file mode 100644 index 000000000..7941a090b --- /dev/null +++ b/drivers/cpuidle/cpuidle-ux500.c @@ -0,0 +1,127 @@ +/* + * Copyright (c) 2012 Linaro : Daniel Lezcano <daniel.lezcano@linaro.org> (IBM) + * + * Based on the work of Rickard Andersson <rickard.andersson@stericsson.com> + * and Jonas Aaberg <jonas.aberg@stericsson.com>. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/init.h> +#include <linux/cpuidle.h> +#include <linux/spinlock.h> +#include <linux/atomic.h> +#include <linux/smp.h> +#include <linux/mfd/dbx500-prcmu.h> +#include <linux/platform_data/arm-ux500-pm.h> +#include <linux/platform_device.h> + +#include <asm/cpuidle.h> + +static atomic_t master = ATOMIC_INIT(0); +static DEFINE_SPINLOCK(master_lock); + +static inline int ux500_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + int this_cpu = smp_processor_id(); + bool recouple = false; + + if (atomic_inc_return(&master) == num_online_cpus()) { + + /* With this lock, we prevent the other cpu to exit and enter + * this function again and become the master */ + if (!spin_trylock(&master_lock)) + goto wfi; + + /* decouple the gic from the A9 cores */ + if (prcmu_gic_decouple()) { + spin_unlock(&master_lock); + goto out; + } + + /* If an error occur, we will have to recouple the gic + * manually */ + recouple = true; + + /* At this state, as the gic is decoupled, if the other + * cpu is in WFI, we have the guarantee it won't be wake + * up, so we can safely go to retention */ + if (!prcmu_is_cpu_in_wfi(this_cpu ? 0 : 1)) + goto out; + + /* The prcmu will be in charge of watching the interrupts + * and wake up the cpus */ + if (prcmu_copy_gic_settings()) + goto out; + + /* Check in the meantime an interrupt did + * not occur on the gic ... */ + if (prcmu_gic_pending_irq()) + goto out; + + /* ... and the prcmu */ + if (prcmu_pending_irq()) + goto out; + + /* Go to the retention state, the prcmu will wait for the + * cpu to go WFI and this is what happens after exiting this + * 'master' critical section */ + if (prcmu_set_power_state(PRCMU_AP_IDLE, true, true)) + goto out; + + /* When we switch to retention, the prcmu is in charge + * of recoupling the gic automatically */ + recouple = false; + + spin_unlock(&master_lock); + } +wfi: + cpu_do_idle(); +out: + atomic_dec(&master); + + if (recouple) { + prcmu_gic_recouple(); + spin_unlock(&master_lock); + } + + return index; +} + +static struct cpuidle_driver ux500_idle_driver = { + .name = "ux500_idle", + .owner = THIS_MODULE, + .states = { + ARM_CPUIDLE_WFI_STATE, + { + .enter = ux500_enter_idle, + .exit_latency = 70, + .target_residency = 260, + .flags = CPUIDLE_FLAG_TIMER_STOP, + .name = "ApIdle", + .desc = "ARM Retention", + }, + }, + .safe_state_index = 0, + .state_count = 2, +}; + +static int dbx500_cpuidle_probe(struct platform_device *pdev) +{ + /* Configure wake up reasons */ + prcmu_enable_wakeups(PRCMU_WAKEUP(ARM) | PRCMU_WAKEUP(RTC) | + PRCMU_WAKEUP(ABB)); + + return cpuidle_register(&ux500_idle_driver, NULL); +} + +static struct platform_driver dbx500_cpuidle_plat_driver = { + .driver = { + .name = "cpuidle-dbx500", + }, + .probe = dbx500_cpuidle_probe, +}; +builtin_platform_driver(dbx500_cpuidle_plat_driver); diff --git a/drivers/cpuidle/cpuidle-zynq.c b/drivers/cpuidle/cpuidle-zynq.c new file mode 100644 index 000000000..6f4257fc5 --- /dev/null +++ b/drivers/cpuidle/cpuidle-zynq.c @@ -0,0 +1,76 @@ +/* + * Copyright (C) 2012-2013 Xilinx + * + * CPU idle support for Xilinx Zynq + * + * based on arch/arm/mach-at91/cpuidle.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program. If not, see <http://www.gnu.org/licenses/>. + * + * The cpu idle uses wait-for-interrupt and RAM self refresh in order + * to implement two idle states - + * #1 wait-for-interrupt + * #2 wait-for-interrupt and RAM self refresh + * + * Maintainer: Michal Simek <michal.simek@xilinx.com> + */ + +#include <linux/init.h> +#include <linux/cpuidle.h> +#include <linux/platform_device.h> +#include <asm/cpuidle.h> + +#define ZYNQ_MAX_STATES 2 + +/* Actual code that puts the SoC in different idle states */ +static int zynq_enter_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + /* Add code for DDR self refresh start */ + cpu_do_idle(); + + return index; +} + +static struct cpuidle_driver zynq_idle_driver = { + .name = "zynq_idle", + .owner = THIS_MODULE, + .states = { + ARM_CPUIDLE_WFI_STATE, + { + .enter = zynq_enter_idle, + .exit_latency = 10, + .target_residency = 10000, + .name = "RAM_SR", + .desc = "WFI and RAM Self Refresh", + }, + }, + .safe_state_index = 0, + .state_count = ZYNQ_MAX_STATES, +}; + +/* Initialize CPU idle by registering the idle states */ +static int zynq_cpuidle_probe(struct platform_device *pdev) +{ + pr_info("Xilinx Zynq CpuIdle Driver started\n"); + + return cpuidle_register(&zynq_idle_driver, NULL); +} + +static struct platform_driver zynq_cpuidle_driver = { + .driver = { + .name = "cpuidle-zynq", + }, + .probe = zynq_cpuidle_probe, +}; +builtin_platform_driver(zynq_cpuidle_driver); diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c new file mode 100644 index 000000000..2d182dc1b --- /dev/null +++ b/drivers/cpuidle/cpuidle.c @@ -0,0 +1,706 @@ +/* + * cpuidle.c - core cpuidle infrastructure + * + * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Shaohua Li <shaohua.li@intel.com> + * Adam Belay <abelay@novell.com> + * + * This code is licenced under the GPL. + */ + +#include <linux/clockchips.h> +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/sched.h> +#include <linux/sched/clock.h> +#include <linux/notifier.h> +#include <linux/pm_qos.h> +#include <linux/cpu.h> +#include <linux/cpuidle.h> +#include <linux/ktime.h> +#include <linux/hrtimer.h> +#include <linux/module.h> +#include <linux/suspend.h> +#include <linux/tick.h> +#include <trace/events/power.h> + +#include "cpuidle.h" + +DEFINE_PER_CPU(struct cpuidle_device *, cpuidle_devices); +DEFINE_PER_CPU(struct cpuidle_device, cpuidle_dev); + +DEFINE_MUTEX(cpuidle_lock); +LIST_HEAD(cpuidle_detected_devices); + +static int enabled_devices; +static int off __read_mostly; +static int initialized __read_mostly; + +int cpuidle_disabled(void) +{ + return off; +} +void disable_cpuidle(void) +{ + off = 1; +} + +bool cpuidle_not_available(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + return off || !initialized || !drv || !dev || !dev->enabled; +} + +/** + * cpuidle_play_dead - cpu off-lining + * + * Returns in case of an error or no driver + */ +int cpuidle_play_dead(void) +{ + struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int i; + + if (!drv) + return -ENODEV; + + /* Find lowest-power state that supports long-term idle */ + for (i = drv->state_count - 1; i >= 0; i--) + if (drv->states[i].enter_dead) + return drv->states[i].enter_dead(dev, i); + + return -ENODEV; +} + +static int find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev, + unsigned int max_latency, + unsigned int forbidden_flags, + bool s2idle) +{ + unsigned int latency_req = 0; + int i, ret = 0; + + for (i = 1; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable || s->exit_latency <= latency_req + || s->exit_latency > max_latency + || (s->flags & forbidden_flags) + || (s2idle && !s->enter_s2idle)) + continue; + + latency_req = s->exit_latency; + ret = i; + } + return ret; +} + +/** + * cpuidle_use_deepest_state - Set/clear governor override flag. + * @enable: New value of the flag. + * + * Set/unset the current CPU to use the deepest idle state (override governors + * going forward if set). + */ +void cpuidle_use_deepest_state(bool enable) +{ + struct cpuidle_device *dev; + + preempt_disable(); + dev = cpuidle_get_device(); + if (dev) + dev->use_deepest_state = enable; + preempt_enable(); +} + +/** + * cpuidle_find_deepest_state - Find the deepest available idle state. + * @drv: cpuidle driver for the given CPU. + * @dev: cpuidle device for the given CPU. + */ +int cpuidle_find_deepest_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + return find_deepest_state(drv, dev, UINT_MAX, 0, false); +} + +#ifdef CONFIG_SUSPEND +static void enter_s2idle_proper(struct cpuidle_driver *drv, + struct cpuidle_device *dev, int index) +{ + ktime_t time_start, time_end; + + time_start = ns_to_ktime(local_clock()); + + /* + * trace_suspend_resume() called by tick_freeze() for the last CPU + * executing it contains RCU usage regarded as invalid in the idle + * context, so tell RCU about that. + */ + RCU_NONIDLE(tick_freeze()); + /* + * The state used here cannot be a "coupled" one, because the "coupled" + * cpuidle mechanism enables interrupts and doing that with timekeeping + * suspended is generally unsafe. + */ + stop_critical_timings(); + drv->states[index].enter_s2idle(dev, drv, index); + if (WARN_ON_ONCE(!irqs_disabled())) + local_irq_disable(); + /* + * timekeeping_resume() that will be called by tick_unfreeze() for the + * first CPU executing it calls functions containing RCU read-side + * critical sections, so tell RCU about that. + */ + RCU_NONIDLE(tick_unfreeze()); + start_critical_timings(); + + time_end = ns_to_ktime(local_clock()); + + dev->states_usage[index].s2idle_time += ktime_us_delta(time_end, time_start); + dev->states_usage[index].s2idle_usage++; +} + +/** + * cpuidle_enter_s2idle - Enter an idle state suitable for suspend-to-idle. + * @drv: cpuidle driver for the given CPU. + * @dev: cpuidle device for the given CPU. + * + * If there are states with the ->enter_s2idle callback, find the deepest of + * them and enter it with frozen tick. + */ +int cpuidle_enter_s2idle(struct cpuidle_driver *drv, struct cpuidle_device *dev) +{ + int index; + + /* + * Find the deepest state with ->enter_s2idle present, which guarantees + * that interrupts won't be enabled when it exits and allows the tick to + * be frozen safely. + */ + index = find_deepest_state(drv, dev, UINT_MAX, 0, true); + if (index > 0) + enter_s2idle_proper(drv, dev, index); + + return index; +} +#endif /* CONFIG_SUSPEND */ + +/** + * cpuidle_enter_state - enter the state and update stats + * @dev: cpuidle device for this cpu + * @drv: cpuidle driver for this cpu + * @index: index into the states table in @drv of the state to enter + */ +int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, + int index) +{ + int entered_state; + + struct cpuidle_state *target_state = &drv->states[index]; + bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); + ktime_t time_start, time_end; + s64 diff; + + /* + * Tell the time framework to switch to a broadcast timer because our + * local timer will be shut down. If a local timer is used from another + * CPU as a broadcast timer, this call may fail if it is not available. + */ + if (broadcast && tick_broadcast_enter()) { + index = find_deepest_state(drv, dev, target_state->exit_latency, + CPUIDLE_FLAG_TIMER_STOP, false); + if (index < 0) { + default_idle_call(); + return -EBUSY; + } + target_state = &drv->states[index]; + broadcast = false; + } + + /* Take note of the planned idle state. */ + sched_idle_set_state(target_state); + + trace_cpu_idle_rcuidle(index, dev->cpu); + time_start = ns_to_ktime(local_clock()); + + stop_critical_timings(); + entered_state = target_state->enter(dev, drv, index); + start_critical_timings(); + + sched_clock_idle_wakeup_event(); + time_end = ns_to_ktime(local_clock()); + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + + /* The cpu is no longer idle or about to enter idle. */ + sched_idle_set_state(NULL); + + if (broadcast) { + if (WARN_ON_ONCE(!irqs_disabled())) + local_irq_disable(); + + tick_broadcast_exit(); + } + + if (!cpuidle_state_is_coupled(drv, index)) + local_irq_enable(); + + diff = ktime_us_delta(time_end, time_start); + if (diff > INT_MAX) + diff = INT_MAX; + + dev->last_residency = (int) diff; + + if (entered_state >= 0) { + /* Update cpuidle counters */ + /* This can be moved to within driver enter routine + * but that results in multiple copies of same code. + */ + dev->states_usage[entered_state].time += dev->last_residency; + dev->states_usage[entered_state].usage++; + } else { + dev->last_residency = 0; + } + + return entered_state; +} + +/** + * cpuidle_select - ask the cpuidle framework to choose an idle state + * + * @drv: the cpuidle driver + * @dev: the cpuidle device + * @stop_tick: indication on whether or not to stop the tick + * + * Returns the index of the idle state. The return value must not be negative. + * + * The memory location pointed to by @stop_tick is expected to be written the + * 'false' boolean value if the scheduler tick should not be stopped before + * entering the returned state. + */ +int cpuidle_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) +{ + return cpuidle_curr_governor->select(drv, dev, stop_tick); +} + +/** + * cpuidle_enter - enter into the specified idle state + * + * @drv: the cpuidle driver tied with the cpu + * @dev: the cpuidle device + * @index: the index in the idle state table + * + * Returns the index in the idle state, < 0 in case of error. + * The error code depends on the backend driver + */ +int cpuidle_enter(struct cpuidle_driver *drv, struct cpuidle_device *dev, + int index) +{ + if (cpuidle_state_is_coupled(drv, index)) + return cpuidle_enter_state_coupled(dev, drv, index); + return cpuidle_enter_state(dev, drv, index); +} + +/** + * cpuidle_reflect - tell the underlying governor what was the state + * we were in + * + * @dev : the cpuidle device + * @index: the index in the idle state table + * + */ +void cpuidle_reflect(struct cpuidle_device *dev, int index) +{ + if (cpuidle_curr_governor->reflect && index >= 0) + cpuidle_curr_governor->reflect(dev, index); +} + +/** + * cpuidle_install_idle_handler - installs the cpuidle idle loop handler + */ +void cpuidle_install_idle_handler(void) +{ + if (enabled_devices) { + /* Make sure all changes finished before we switch to new idle */ + smp_wmb(); + initialized = 1; + } +} + +/** + * cpuidle_uninstall_idle_handler - uninstalls the cpuidle idle loop handler + */ +void cpuidle_uninstall_idle_handler(void) +{ + if (enabled_devices) { + initialized = 0; + wake_up_all_idle_cpus(); + } + + /* + * Make sure external observers (such as the scheduler) + * are done looking at pointed idle states. + */ + synchronize_rcu(); +} + +/** + * cpuidle_pause_and_lock - temporarily disables CPUIDLE + */ +void cpuidle_pause_and_lock(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_uninstall_idle_handler(); +} + +EXPORT_SYMBOL_GPL(cpuidle_pause_and_lock); + +/** + * cpuidle_resume_and_unlock - resumes CPUIDLE operation + */ +void cpuidle_resume_and_unlock(void) +{ + cpuidle_install_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + +EXPORT_SYMBOL_GPL(cpuidle_resume_and_unlock); + +/* Currently used in suspend/resume path to suspend cpuidle */ +void cpuidle_pause(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_uninstall_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + +/* Currently used in suspend/resume path to resume cpuidle */ +void cpuidle_resume(void) +{ + mutex_lock(&cpuidle_lock); + cpuidle_install_idle_handler(); + mutex_unlock(&cpuidle_lock); +} + +/** + * cpuidle_enable_device - enables idle PM for a CPU + * @dev: the CPU + * + * This function must be called between cpuidle_pause_and_lock and + * cpuidle_resume_and_unlock when used externally. + */ +int cpuidle_enable_device(struct cpuidle_device *dev) +{ + int ret; + struct cpuidle_driver *drv; + + if (!dev) + return -EINVAL; + + if (dev->enabled) + return 0; + + if (!cpuidle_curr_governor) + return -EIO; + + drv = cpuidle_get_cpu_driver(dev); + + if (!drv) + return -EIO; + + if (!dev->registered) + return -EINVAL; + + ret = cpuidle_add_device_sysfs(dev); + if (ret) + return ret; + + if (cpuidle_curr_governor->enable) { + ret = cpuidle_curr_governor->enable(drv, dev); + if (ret) + goto fail_sysfs; + } + + smp_wmb(); + + dev->enabled = 1; + + enabled_devices++; + return 0; + +fail_sysfs: + cpuidle_remove_device_sysfs(dev); + + return ret; +} + +EXPORT_SYMBOL_GPL(cpuidle_enable_device); + +/** + * cpuidle_disable_device - disables idle PM for a CPU + * @dev: the CPU + * + * This function must be called between cpuidle_pause_and_lock and + * cpuidle_resume_and_unlock when used externally. + */ +void cpuidle_disable_device(struct cpuidle_device *dev) +{ + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + + if (!dev || !dev->enabled) + return; + + if (!drv || !cpuidle_curr_governor) + return; + + dev->enabled = 0; + + if (cpuidle_curr_governor->disable) + cpuidle_curr_governor->disable(drv, dev); + + cpuidle_remove_device_sysfs(dev); + enabled_devices--; +} + +EXPORT_SYMBOL_GPL(cpuidle_disable_device); + +static void __cpuidle_unregister_device(struct cpuidle_device *dev) +{ + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + + list_del(&dev->device_list); + per_cpu(cpuidle_devices, dev->cpu) = NULL; + module_put(drv->owner); + + dev->registered = 0; +} + +static void __cpuidle_device_init(struct cpuidle_device *dev) +{ + memset(dev->states_usage, 0, sizeof(dev->states_usage)); + dev->last_residency = 0; +} + +/** + * __cpuidle_register_device - internal register function called before register + * and enable routines + * @dev: the cpu + * + * cpuidle_lock mutex must be held before this is called + */ +static int __cpuidle_register_device(struct cpuidle_device *dev) +{ + int ret; + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + + if (!try_module_get(drv->owner)) + return -EINVAL; + + per_cpu(cpuidle_devices, dev->cpu) = dev; + list_add(&dev->device_list, &cpuidle_detected_devices); + + ret = cpuidle_coupled_register_device(dev); + if (ret) + __cpuidle_unregister_device(dev); + else + dev->registered = 1; + + return ret; +} + +/** + * cpuidle_register_device - registers a CPU's idle PM feature + * @dev: the cpu + */ +int cpuidle_register_device(struct cpuidle_device *dev) +{ + int ret = -EBUSY; + + if (!dev) + return -EINVAL; + + mutex_lock(&cpuidle_lock); + + if (dev->registered) + goto out_unlock; + + __cpuidle_device_init(dev); + + ret = __cpuidle_register_device(dev); + if (ret) + goto out_unlock; + + ret = cpuidle_add_sysfs(dev); + if (ret) + goto out_unregister; + + ret = cpuidle_enable_device(dev); + if (ret) + goto out_sysfs; + + cpuidle_install_idle_handler(); + +out_unlock: + mutex_unlock(&cpuidle_lock); + + return ret; + +out_sysfs: + cpuidle_remove_sysfs(dev); +out_unregister: + __cpuidle_unregister_device(dev); + goto out_unlock; +} + +EXPORT_SYMBOL_GPL(cpuidle_register_device); + +/** + * cpuidle_unregister_device - unregisters a CPU's idle PM feature + * @dev: the cpu + */ +void cpuidle_unregister_device(struct cpuidle_device *dev) +{ + if (!dev || dev->registered == 0) + return; + + cpuidle_pause_and_lock(); + + cpuidle_disable_device(dev); + + cpuidle_remove_sysfs(dev); + + __cpuidle_unregister_device(dev); + + cpuidle_coupled_unregister_device(dev); + + cpuidle_resume_and_unlock(); +} + +EXPORT_SYMBOL_GPL(cpuidle_unregister_device); + +/** + * cpuidle_unregister: unregister a driver and the devices. This function + * can be used only if the driver has been previously registered through + * the cpuidle_register function. + * + * @drv: a valid pointer to a struct cpuidle_driver + */ +void cpuidle_unregister(struct cpuidle_driver *drv) +{ + int cpu; + struct cpuidle_device *device; + + for_each_cpu(cpu, drv->cpumask) { + device = &per_cpu(cpuidle_dev, cpu); + cpuidle_unregister_device(device); + } + + cpuidle_unregister_driver(drv); +} +EXPORT_SYMBOL_GPL(cpuidle_unregister); + +/** + * cpuidle_register: registers the driver and the cpu devices with the + * coupled_cpus passed as parameter. This function is used for all common + * initialization pattern there are in the arch specific drivers. The + * devices is globally defined in this file. + * + * @drv : a valid pointer to a struct cpuidle_driver + * @coupled_cpus: a cpumask for the coupled states + * + * Returns 0 on success, < 0 otherwise + */ +int cpuidle_register(struct cpuidle_driver *drv, + const struct cpumask *const coupled_cpus) +{ + int ret, cpu; + struct cpuidle_device *device; + + ret = cpuidle_register_driver(drv); + if (ret) { + pr_err("failed to register cpuidle driver\n"); + return ret; + } + + for_each_cpu(cpu, drv->cpumask) { + device = &per_cpu(cpuidle_dev, cpu); + device->cpu = cpu; + +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED + /* + * On multiplatform for ARM, the coupled idle states could be + * enabled in the kernel even if the cpuidle driver does not + * use it. Note, coupled_cpus is a struct copy. + */ + if (coupled_cpus) + device->coupled_cpus = *coupled_cpus; +#endif + ret = cpuidle_register_device(device); + if (!ret) + continue; + + pr_err("Failed to register cpuidle device for cpu%d\n", cpu); + + cpuidle_unregister(drv); + break; + } + + return ret; +} +EXPORT_SYMBOL_GPL(cpuidle_register); + +#ifdef CONFIG_SMP + +/* + * This function gets called when a part of the kernel has a new latency + * requirement. This means we need to get all processors out of their C-state, + * and then recalculate a new suitable C-state. Just do a cross-cpu IPI; that + * wakes them all right up. + */ +static int cpuidle_latency_notify(struct notifier_block *b, + unsigned long l, void *v) +{ + wake_up_all_idle_cpus(); + return NOTIFY_OK; +} + +static struct notifier_block cpuidle_latency_notifier = { + .notifier_call = cpuidle_latency_notify, +}; + +static inline void latency_notifier_init(struct notifier_block *n) +{ + pm_qos_add_notifier(PM_QOS_CPU_DMA_LATENCY, n); +} + +#else /* CONFIG_SMP */ + +#define latency_notifier_init(x) do { } while (0) + +#endif /* CONFIG_SMP */ + +/** + * cpuidle_init - core initializer + */ +static int __init cpuidle_init(void) +{ + int ret; + + if (cpuidle_disabled()) + return -ENODEV; + + ret = cpuidle_add_interface(cpu_subsys.dev_root); + if (ret) + return ret; + + latency_notifier_init(&cpuidle_latency_notifier); + + return 0; +} + +module_param(off, int, 0444); +core_initcall(cpuidle_init); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h new file mode 100644 index 000000000..2965ab32a --- /dev/null +++ b/drivers/cpuidle/cpuidle.h @@ -0,0 +1,72 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * cpuidle.h - The internal header file + */ + +#ifndef __DRIVER_CPUIDLE_H +#define __DRIVER_CPUIDLE_H + +/* For internal use only */ +extern struct cpuidle_governor *cpuidle_curr_governor; +extern struct list_head cpuidle_governors; +extern struct list_head cpuidle_detected_devices; +extern struct mutex cpuidle_lock; +extern spinlock_t cpuidle_driver_lock; +extern int cpuidle_disabled(void); +extern int cpuidle_enter_state(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state); + +/* idle loop */ +extern void cpuidle_install_idle_handler(void); +extern void cpuidle_uninstall_idle_handler(void); + +/* governors */ +extern int cpuidle_switch_governor(struct cpuidle_governor *gov); + +/* sysfs */ + +struct device; + +extern int cpuidle_add_interface(struct device *dev); +extern void cpuidle_remove_interface(struct device *dev); +extern int cpuidle_add_device_sysfs(struct cpuidle_device *device); +extern void cpuidle_remove_device_sysfs(struct cpuidle_device *device); +extern int cpuidle_add_sysfs(struct cpuidle_device *dev); +extern void cpuidle_remove_sysfs(struct cpuidle_device *dev); + +#ifdef CONFIG_ARCH_NEEDS_CPU_IDLE_COUPLED +bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state); +int cpuidle_coupled_state_verify(struct cpuidle_driver *drv); +int cpuidle_enter_state_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state); +int cpuidle_coupled_register_device(struct cpuidle_device *dev); +void cpuidle_coupled_unregister_device(struct cpuidle_device *dev); +#else +static inline +bool cpuidle_state_is_coupled(struct cpuidle_driver *drv, int state) +{ + return false; +} + +static inline int cpuidle_coupled_state_verify(struct cpuidle_driver *drv) +{ + return 0; +} + +static inline int cpuidle_enter_state_coupled(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int next_state) +{ + return -1; +} + +static inline int cpuidle_coupled_register_device(struct cpuidle_device *dev) +{ + return 0; +} + +static inline void cpuidle_coupled_unregister_device(struct cpuidle_device *dev) +{ +} +#endif + +#endif /* __DRIVER_CPUIDLE_H */ diff --git a/drivers/cpuidle/driver.c b/drivers/cpuidle/driver.c new file mode 100644 index 000000000..01acd88c4 --- /dev/null +++ b/drivers/cpuidle/driver.c @@ -0,0 +1,355 @@ +/* + * driver.c - driver support + * + * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Shaohua Li <shaohua.li@intel.com> + * Adam Belay <abelay@novell.com> + * + * This code is licenced under the GPL. + */ + +#include <linux/mutex.h> +#include <linux/module.h> +#include <linux/sched.h> +#include <linux/sched/idle.h> +#include <linux/cpuidle.h> +#include <linux/cpumask.h> +#include <linux/tick.h> +#include <linux/cpu.h> + +#include "cpuidle.h" + +DEFINE_SPINLOCK(cpuidle_driver_lock); + +#ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS + +static DEFINE_PER_CPU(struct cpuidle_driver *, cpuidle_drivers); + +/** + * __cpuidle_get_cpu_driver - return the cpuidle driver tied to a CPU. + * @cpu: the CPU handled by the driver + * + * Returns a pointer to struct cpuidle_driver or NULL if no driver has been + * registered for @cpu. + */ +static struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu) +{ + return per_cpu(cpuidle_drivers, cpu); +} + +/** + * __cpuidle_unset_driver - unset per CPU driver variables. + * @drv: a valid pointer to a struct cpuidle_driver + * + * For each CPU in the driver's CPU mask, unset the registered driver per CPU + * variable. If @drv is different from the registered driver, the corresponding + * variable is not cleared. + */ +static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) +{ + int cpu; + + for_each_cpu(cpu, drv->cpumask) { + + if (drv != __cpuidle_get_cpu_driver(cpu)) + continue; + + per_cpu(cpuidle_drivers, cpu) = NULL; + } +} + +/** + * __cpuidle_set_driver - set per CPU driver variables for the given driver. + * @drv: a valid pointer to a struct cpuidle_driver + * + * Returns 0 on success, -EBUSY if any CPU in the cpumask have a driver + * different from drv already. + */ +static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) +{ + int cpu; + + for_each_cpu(cpu, drv->cpumask) { + struct cpuidle_driver *old_drv; + + old_drv = __cpuidle_get_cpu_driver(cpu); + if (old_drv && old_drv != drv) + return -EBUSY; + } + + for_each_cpu(cpu, drv->cpumask) + per_cpu(cpuidle_drivers, cpu) = drv; + + return 0; +} + +#else + +static struct cpuidle_driver *cpuidle_curr_driver; + +/** + * __cpuidle_get_cpu_driver - return the global cpuidle driver pointer. + * @cpu: ignored without the multiple driver support + * + * Return a pointer to a struct cpuidle_driver object or NULL if no driver was + * previously registered. + */ +static inline struct cpuidle_driver *__cpuidle_get_cpu_driver(int cpu) +{ + return cpuidle_curr_driver; +} + +/** + * __cpuidle_set_driver - assign the global cpuidle driver variable. + * @drv: pointer to a struct cpuidle_driver object + * + * Returns 0 on success, -EBUSY if the driver is already registered. + */ +static inline int __cpuidle_set_driver(struct cpuidle_driver *drv) +{ + if (cpuidle_curr_driver) + return -EBUSY; + + cpuidle_curr_driver = drv; + + return 0; +} + +/** + * __cpuidle_unset_driver - unset the global cpuidle driver variable. + * @drv: a pointer to a struct cpuidle_driver + * + * Reset the global cpuidle variable to NULL. If @drv does not match the + * registered driver, do nothing. + */ +static inline void __cpuidle_unset_driver(struct cpuidle_driver *drv) +{ + if (drv == cpuidle_curr_driver) + cpuidle_curr_driver = NULL; +} + +#endif + +/** + * cpuidle_setup_broadcast_timer - enable/disable the broadcast timer on a cpu + * @arg: a void pointer used to match the SMP cross call API + * + * If @arg is NULL broadcast is disabled otherwise enabled + * + * This function is executed per CPU by an SMP cross call. It's not + * supposed to be called directly. + */ +static void cpuidle_setup_broadcast_timer(void *arg) +{ + if (arg) + tick_broadcast_enable(); + else + tick_broadcast_disable(); +} + +/** + * __cpuidle_driver_init - initialize the driver's internal data + * @drv: a valid pointer to a struct cpuidle_driver + */ +static void __cpuidle_driver_init(struct cpuidle_driver *drv) +{ + int i; + + drv->refcnt = 0; + + /* + * Use all possible CPUs as the default, because if the kernel boots + * with some CPUs offline and then we online one of them, the CPU + * notifier has to know which driver to assign. + */ + if (!drv->cpumask) + drv->cpumask = (struct cpumask *)cpu_possible_mask; + + /* + * Look for the timer stop flag in the different states, so that we know + * if the broadcast timer has to be set up. The loop is in the reverse + * order, because usually one of the deeper states have this flag set. + */ + for (i = drv->state_count - 1; i >= 0 ; i--) { + if (drv->states[i].flags & CPUIDLE_FLAG_TIMER_STOP) { + drv->bctimer = 1; + break; + } + } +} + +/** + * __cpuidle_register_driver: register the driver + * @drv: a valid pointer to a struct cpuidle_driver + * + * Do some sanity checks, initialize the driver, assign the driver to the + * global cpuidle driver variable(s) and set up the broadcast timer if the + * cpuidle driver has some states that shut down the local timer. + * + * Returns 0 on success, a negative error code otherwise: + * * -EINVAL if the driver pointer is NULL or no idle states are available + * * -ENODEV if the cpuidle framework is disabled + * * -EBUSY if the driver is already assigned to the global variable(s) + */ +static int __cpuidle_register_driver(struct cpuidle_driver *drv) +{ + int ret; + + if (!drv || !drv->state_count) + return -EINVAL; + + ret = cpuidle_coupled_state_verify(drv); + if (ret) + return ret; + + if (cpuidle_disabled()) + return -ENODEV; + + __cpuidle_driver_init(drv); + + ret = __cpuidle_set_driver(drv); + if (ret) + return ret; + + if (drv->bctimer) + on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, + (void *)1, 1); + + return 0; +} + +/** + * __cpuidle_unregister_driver - unregister the driver + * @drv: a valid pointer to a struct cpuidle_driver + * + * Check if the driver is no longer in use, reset the global cpuidle driver + * variable(s) and disable the timer broadcast notification mechanism if it was + * in use. + * + */ +static void __cpuidle_unregister_driver(struct cpuidle_driver *drv) +{ + if (WARN_ON(drv->refcnt > 0)) + return; + + if (drv->bctimer) { + drv->bctimer = 0; + on_each_cpu_mask(drv->cpumask, cpuidle_setup_broadcast_timer, + NULL, 1); + } + + __cpuidle_unset_driver(drv); +} + +/** + * cpuidle_register_driver - registers a driver + * @drv: a pointer to a valid struct cpuidle_driver + * + * Register the driver under a lock to prevent concurrent attempts to + * [un]register the driver from occuring at the same time. + * + * Returns 0 on success, a negative error code (returned by + * __cpuidle_register_driver()) otherwise. + */ +int cpuidle_register_driver(struct cpuidle_driver *drv) +{ + int ret; + + spin_lock(&cpuidle_driver_lock); + ret = __cpuidle_register_driver(drv); + spin_unlock(&cpuidle_driver_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(cpuidle_register_driver); + +/** + * cpuidle_unregister_driver - unregisters a driver + * @drv: a pointer to a valid struct cpuidle_driver + * + * Unregisters the cpuidle driver under a lock to prevent concurrent attempts + * to [un]register the driver from occuring at the same time. @drv has to + * match the currently registered driver. + */ +void cpuidle_unregister_driver(struct cpuidle_driver *drv) +{ + spin_lock(&cpuidle_driver_lock); + __cpuidle_unregister_driver(drv); + spin_unlock(&cpuidle_driver_lock); +} +EXPORT_SYMBOL_GPL(cpuidle_unregister_driver); + +/** + * cpuidle_get_driver - return the driver tied to the current CPU. + * + * Returns a struct cpuidle_driver pointer, or NULL if no driver is registered. + */ +struct cpuidle_driver *cpuidle_get_driver(void) +{ + struct cpuidle_driver *drv; + int cpu; + + cpu = get_cpu(); + drv = __cpuidle_get_cpu_driver(cpu); + put_cpu(); + + return drv; +} +EXPORT_SYMBOL_GPL(cpuidle_get_driver); + +/** + * cpuidle_get_cpu_driver - return the driver registered for a CPU. + * @dev: a valid pointer to a struct cpuidle_device + * + * Returns a struct cpuidle_driver pointer, or NULL if no driver is registered + * for the CPU associated with @dev. + */ +struct cpuidle_driver *cpuidle_get_cpu_driver(struct cpuidle_device *dev) +{ + if (!dev) + return NULL; + + return __cpuidle_get_cpu_driver(dev->cpu); +} +EXPORT_SYMBOL_GPL(cpuidle_get_cpu_driver); + +/** + * cpuidle_driver_ref - get a reference to the driver. + * + * Increment the reference counter of the cpuidle driver associated with + * the current CPU. + * + * Returns a pointer to the driver, or NULL if the current CPU has no driver. + */ +struct cpuidle_driver *cpuidle_driver_ref(void) +{ + struct cpuidle_driver *drv; + + spin_lock(&cpuidle_driver_lock); + + drv = cpuidle_get_driver(); + if (drv) + drv->refcnt++; + + spin_unlock(&cpuidle_driver_lock); + return drv; +} + +/** + * cpuidle_driver_unref - puts down the refcount for the driver + * + * Decrement the reference counter of the cpuidle driver associated with + * the current CPU. + */ +void cpuidle_driver_unref(void) +{ + struct cpuidle_driver *drv; + + spin_lock(&cpuidle_driver_lock); + + drv = cpuidle_get_driver(); + if (drv && !WARN_ON(drv->refcnt <= 0)) + drv->refcnt--; + + spin_unlock(&cpuidle_driver_lock); +} diff --git a/drivers/cpuidle/dt_idle_states.c b/drivers/cpuidle/dt_idle_states.c new file mode 100644 index 000000000..53342b7f1 --- /dev/null +++ b/drivers/cpuidle/dt_idle_states.c @@ -0,0 +1,229 @@ +/* + * DT idle states parsing code. + * + * Copyright (C) 2014 ARM Ltd. + * Author: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#define pr_fmt(fmt) "DT idle-states: " fmt + +#include <linux/cpuidle.h> +#include <linux/cpumask.h> +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> + +#include "dt_idle_states.h" + +static int init_state_node(struct cpuidle_state *idle_state, + const struct of_device_id *matches, + struct device_node *state_node) +{ + int err; + const struct of_device_id *match_id; + const char *desc; + + match_id = of_match_node(matches, state_node); + if (!match_id) + return -ENODEV; + /* + * CPUidle drivers are expected to initialize the const void *data + * pointer of the passed in struct of_device_id array to the idle + * state enter function. + */ + idle_state->enter = match_id->data; + /* + * Since this is not a "coupled" state, it's safe to assume interrupts + * won't be enabled when it exits allowing the tick to be frozen + * safely. So enter() can be also enter_s2idle() callback. + */ + idle_state->enter_s2idle = match_id->data; + + err = of_property_read_u32(state_node, "wakeup-latency-us", + &idle_state->exit_latency); + if (err) { + u32 entry_latency, exit_latency; + + err = of_property_read_u32(state_node, "entry-latency-us", + &entry_latency); + if (err) { + pr_debug(" * %pOF missing entry-latency-us property\n", + state_node); + return -EINVAL; + } + + err = of_property_read_u32(state_node, "exit-latency-us", + &exit_latency); + if (err) { + pr_debug(" * %pOF missing exit-latency-us property\n", + state_node); + return -EINVAL; + } + /* + * If wakeup-latency-us is missing, default to entry+exit + * latencies as defined in idle states bindings + */ + idle_state->exit_latency = entry_latency + exit_latency; + } + + err = of_property_read_u32(state_node, "min-residency-us", + &idle_state->target_residency); + if (err) { + pr_debug(" * %pOF missing min-residency-us property\n", + state_node); + return -EINVAL; + } + + err = of_property_read_string(state_node, "idle-state-name", &desc); + if (err) + desc = state_node->name; + + idle_state->flags = 0; + if (of_property_read_bool(state_node, "local-timer-stop")) + idle_state->flags |= CPUIDLE_FLAG_TIMER_STOP; + /* + * TODO: + * replace with kstrdup and pointer assignment when name + * and desc become string pointers + */ + strncpy(idle_state->name, state_node->name, CPUIDLE_NAME_LEN - 1); + strncpy(idle_state->desc, desc, CPUIDLE_DESC_LEN - 1); + return 0; +} + +/* + * Check that the idle state is uniform across all CPUs in the CPUidle driver + * cpumask + */ +static bool idle_state_valid(struct device_node *state_node, unsigned int idx, + const cpumask_t *cpumask) +{ + int cpu; + struct device_node *cpu_node, *curr_state_node; + bool valid = true; + + /* + * Compare idle state phandles for index idx on all CPUs in the + * CPUidle driver cpumask. Start from next logical cpu following + * cpumask_first(cpumask) since that's the CPU state_node was + * retrieved from. If a mismatch is found bail out straight + * away since we certainly hit a firmware misconfiguration. + */ + for (cpu = cpumask_next(cpumask_first(cpumask), cpumask); + cpu < nr_cpu_ids; cpu = cpumask_next(cpu, cpumask)) { + cpu_node = of_cpu_device_node_get(cpu); + curr_state_node = of_parse_phandle(cpu_node, "cpu-idle-states", + idx); + if (state_node != curr_state_node) + valid = false; + + of_node_put(curr_state_node); + of_node_put(cpu_node); + if (!valid) + break; + } + + return valid; +} + +/** + * dt_init_idle_driver() - Parse the DT idle states and initialize the + * idle driver states array + * @drv: Pointer to CPU idle driver to be initialized + * @matches: Array of of_device_id match structures to search in for + * compatible idle state nodes. The data pointer for each valid + * struct of_device_id entry in the matches array must point to + * a function with the following signature, that corresponds to + * the CPUidle state enter function signature: + * + * int (*)(struct cpuidle_device *dev, + * struct cpuidle_driver *drv, + * int index); + * + * @start_idx: First idle state index to be initialized + * + * If DT idle states are detected and are valid the state count and states + * array entries in the cpuidle driver are initialized accordingly starting + * from index start_idx. + * + * Return: number of valid DT idle states parsed, <0 on failure + */ +int dt_init_idle_driver(struct cpuidle_driver *drv, + const struct of_device_id *matches, + unsigned int start_idx) +{ + struct cpuidle_state *idle_state; + struct device_node *state_node, *cpu_node; + int i, err = 0; + const cpumask_t *cpumask; + unsigned int state_idx = start_idx; + + if (state_idx >= CPUIDLE_STATE_MAX) + return -EINVAL; + /* + * We get the idle states for the first logical cpu in the + * driver mask (or cpu_possible_mask if the driver cpumask is not set) + * and we check through idle_state_valid() if they are uniform + * across CPUs, otherwise we hit a firmware misconfiguration. + */ + cpumask = drv->cpumask ? : cpu_possible_mask; + cpu_node = of_cpu_device_node_get(cpumask_first(cpumask)); + + for (i = 0; ; i++) { + state_node = of_parse_phandle(cpu_node, "cpu-idle-states", i); + if (!state_node) + break; + + if (!of_device_is_available(state_node)) { + of_node_put(state_node); + continue; + } + + if (!idle_state_valid(state_node, i, cpumask)) { + pr_warn("%pOF idle state not valid, bailing out\n", + state_node); + err = -EINVAL; + break; + } + + if (state_idx == CPUIDLE_STATE_MAX) { + pr_warn("State index reached static CPU idle driver states array size\n"); + break; + } + + idle_state = &drv->states[state_idx++]; + err = init_state_node(idle_state, matches, state_node); + if (err) { + pr_err("Parsing idle state node %pOF failed with err %d\n", + state_node, err); + err = -EINVAL; + break; + } + of_node_put(state_node); + } + + of_node_put(state_node); + of_node_put(cpu_node); + if (err) + return err; + /* + * Update the driver state count only if some valid DT idle states + * were detected + */ + if (i) + drv->state_count = state_idx; + + /* + * Return the number of present and valid DT idle states, which can + * also be 0 on platforms with missing DT idle states or legacy DT + * configuration predating the DT idle states bindings. + */ + return i; +} +EXPORT_SYMBOL_GPL(dt_init_idle_driver); diff --git a/drivers/cpuidle/dt_idle_states.h b/drivers/cpuidle/dt_idle_states.h new file mode 100644 index 000000000..14ae88cef --- /dev/null +++ b/drivers/cpuidle/dt_idle_states.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __DT_IDLE_STATES +#define __DT_IDLE_STATES + +int dt_init_idle_driver(struct cpuidle_driver *drv, + const struct of_device_id *matches, + unsigned int start_idx); +#endif diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c new file mode 100644 index 000000000..9fed1b829 --- /dev/null +++ b/drivers/cpuidle/governor.c @@ -0,0 +1,110 @@ +/* + * governor.c - governor support + * + * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Shaohua Li <shaohua.li@intel.com> + * Adam Belay <abelay@novell.com> + * + * This code is licenced under the GPL. + */ + +#include <linux/cpu.h> +#include <linux/cpuidle.h> +#include <linux/mutex.h> +#include <linux/pm_qos.h> + +#include "cpuidle.h" + +LIST_HEAD(cpuidle_governors); +struct cpuidle_governor *cpuidle_curr_governor; + +/** + * __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 *gov; + + list_for_each_entry(gov, &cpuidle_governors, governor_list) + if (!strncasecmp(str, gov->name, CPUIDLE_NAME_LEN)) + return gov; + + return NULL; +} + +/** + * cpuidle_switch_governor - changes the governor + * @gov: the new target governor + * Must be called with cpuidle_lock acquired. + */ +int cpuidle_switch_governor(struct cpuidle_governor *gov) +{ + struct cpuidle_device *dev; + + if (!gov) + return -EINVAL; + + if (gov == cpuidle_curr_governor) + return 0; + + cpuidle_uninstall_idle_handler(); + + if (cpuidle_curr_governor) { + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_disable_device(dev); + } + + cpuidle_curr_governor = gov; + + if (gov) { + list_for_each_entry(dev, &cpuidle_detected_devices, device_list) + cpuidle_enable_device(dev); + cpuidle_install_idle_handler(); + printk(KERN_INFO "cpuidle: using governor %s\n", gov->name); + } + + return 0; +} + +/** + * cpuidle_register_governor - registers a governor + * @gov: the governor + */ +int cpuidle_register_governor(struct cpuidle_governor *gov) +{ + int ret = -EEXIST; + + if (!gov || !gov->select) + return -EINVAL; + + if (cpuidle_disabled()) + return -ENODEV; + + mutex_lock(&cpuidle_lock); + if (__cpuidle_find_governor(gov->name) == NULL) { + ret = 0; + list_add_tail(&gov->governor_list, &cpuidle_governors); + if (!cpuidle_curr_governor || + cpuidle_curr_governor->rating < gov->rating) + cpuidle_switch_governor(gov); + } + mutex_unlock(&cpuidle_lock); + + return ret; +} + +/** + * cpuidle_governor_latency_req - Compute a latency constraint for CPU + * @cpu: Target CPU + */ +int cpuidle_governor_latency_req(unsigned int cpu) +{ + int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY); + struct device *device = get_cpu_device(cpu); + int device_req = dev_pm_qos_raw_read_value(device); + + return device_req < global_req ? device_req : global_req; +} diff --git a/drivers/cpuidle/governors/Makefile b/drivers/cpuidle/governors/Makefile new file mode 100644 index 000000000..1b5127226 --- /dev/null +++ b/drivers/cpuidle/governors/Makefile @@ -0,0 +1,6 @@ +# +# Makefile for cpuidle governors. +# + +obj-$(CONFIG_CPU_IDLE_GOV_LADDER) += ladder.o +obj-$(CONFIG_CPU_IDLE_GOV_MENU) += menu.o diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c new file mode 100644 index 000000000..704880a66 --- /dev/null +++ b/drivers/cpuidle/governors/ladder.c @@ -0,0 +1,199 @@ +/* + * ladder.c - the residency ladder algorithm + * + * Copyright (C) 2001, 2002 Andy Grover <andrew.grover@intel.com> + * Copyright (C) 2001, 2002 Paul Diefenbaugh <paul.s.diefenbaugh@intel.com> + * Copyright (C) 2004, 2005 Dominik Brodowski <linux@brodo.de> + * + * (C) 2006-2007 Venkatesh Pallipadi <venkatesh.pallipadi@intel.com> + * Shaohua Li <shaohua.li@intel.com> + * Adam Belay <abelay@novell.com> + * + * This code is licenced under the GPL. + */ + +#include <linux/kernel.h> +#include <linux/cpuidle.h> +#include <linux/jiffies.h> +#include <linux/tick.h> + +#include <asm/io.h> +#include <linux/uaccess.h> + +#define PROMOTION_COUNT 4 +#define DEMOTION_COUNT 1 + +struct ladder_device_state { + struct { + u32 promotion_count; + u32 demotion_count; + u32 promotion_time; + u32 demotion_time; + } threshold; + struct { + int promotion_count; + int demotion_count; + } stats; +}; + +struct ladder_device { + struct ladder_device_state states[CPUIDLE_STATE_MAX]; + int last_state_idx; +}; + +static DEFINE_PER_CPU(struct ladder_device, ladder_devices); + +/** + * ladder_do_selection - prepares private data for a state change + * @ldev: the ladder device + * @old_idx: the current state index + * @new_idx: the new target state index + */ +static inline void ladder_do_selection(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; +} + +/** + * ladder_select_state - selects the next state to enter + * @drv: cpuidle driver + * @dev: the CPU + * @dummy: not used + */ +static int ladder_select_state(struct cpuidle_driver *drv, + struct cpuidle_device *dev, bool *dummy) +{ + 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 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); + return 0; + } + + last_state = &ldev->states[last_idx]; + + last_residency = cpuidle_get_last_residency(dev) - drv->states[last_idx].exit_latency; + + /* consider promotion */ + if (last_idx < drv->state_count - 1 && + !drv->states[last_idx + 1].disabled && + !dev->states_usage[last_idx + 1].disable && + last_residency > last_state->threshold.promotion_time && + drv->states[last_idx + 1].exit_latency <= latency_req) { + 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); + return last_idx + 1; + } + } + + /* consider demotion */ + if (last_idx > first_idx && + (drv->states[last_idx].disabled || + dev->states_usage[last_idx].disable || + drv->states[last_idx].exit_latency > latency_req)) { + int i; + + for (i = last_idx - 1; i > first_idx; i--) { + if (drv->states[i].exit_latency <= latency_req) + break; + } + ladder_do_selection(ldev, last_idx, i); + return i; + } + + if (last_idx > first_idx && + last_residency < last_state->threshold.demotion_time) { + 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); + return last_idx - 1; + } + } + + /* otherwise remain at the current state */ + return last_idx; +} + +/** + * ladder_enable_device - setup for the governor + * @drv: cpuidle driver + * @dev: the CPU + */ +static int ladder_enable_device(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + int i; + int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0; + struct ladder_device *ldev = &per_cpu(ladder_devices, dev->cpu); + struct ladder_device_state *lstate; + struct cpuidle_state *state; + + ldev->last_state_idx = first_idx; + + for (i = first_idx; i < drv->state_count; i++) { + state = &drv->states[i]; + lstate = &ldev->states[i]; + + lstate->stats.promotion_count = 0; + lstate->stats.demotion_count = 0; + + lstate->threshold.promotion_count = PROMOTION_COUNT; + lstate->threshold.demotion_count = DEMOTION_COUNT; + + if (i < drv->state_count - 1) + lstate->threshold.promotion_time = state->exit_latency; + if (i > first_idx) + lstate->threshold.demotion_time = state->exit_latency; + } + + return 0; +} + +/** + * ladder_reflect - update the correct last_state_idx + * @dev: the CPU + * @index: the index of actual state entered + */ +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; +} + +static struct cpuidle_governor ladder_governor = { + .name = "ladder", + .rating = 10, + .enable = ladder_enable_device, + .select = ladder_select_state, + .reflect = ladder_reflect, +}; + +/** + * init_ladder - initializes the governor + */ +static int __init init_ladder(void) +{ + /* + * When NO_HZ is disabled, or when booting with nohz=off, the ladder + * governor is better so give it a higher rating than the menu + * governor. + */ + if (!tick_nohz_enabled) + ladder_governor.rating = 25; + + return cpuidle_register_governor(&ladder_governor); +} + +postcore_initcall(init_ladder); diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c new file mode 100644 index 000000000..6d7f6b9bb --- /dev/null +++ b/drivers/cpuidle/governors/menu.c @@ -0,0 +1,609 @@ +/* + * menu.c - the menu idle governor + * + * Copyright (C) 2006-2007 Adam Belay <abelay@novell.com> + * Copyright (C) 2009 Intel Corporation + * Author: + * Arjan van de Ven <arjan@linux.intel.com> + * + * This code is licenced under the GPL version 2 as described + * in the COPYING file that acompanies the Linux Kernel. + */ + +#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/sched/loadavg.h> +#include <linux/sched/stat.h> +#include <linux/math64.h> + +/* + * Please note when changing the tuning values: + * If (MAX_INTERESTING-1) * RESOLUTION > UINT_MAX, the result of + * a scaling operation multiplication may overflow on 32 bit platforms. + * In that case, #define RESOLUTION as ULL to get 64 bit result: + * #define RESOLUTION 1024ULL + * + * The default values do not overflow. + */ +#define BUCKETS 12 +#define INTERVAL_SHIFT 3 +#define INTERVALS (1UL << INTERVAL_SHIFT) +#define RESOLUTION 1024 +#define DECAY 8 +#define MAX_INTERESTING 50000 + + +/* + * Concepts and ideas behind the menu governor + * + * For the menu governor, there are 3 decision factors for picking a C + * state: + * 1) Energy break even point + * 2) Performance impact + * 3) Latency tolerance (from pmqos infrastructure) + * These these three factors are treated independently. + * + * Energy break even point + * ----------------------- + * C state entry and exit have an energy cost, and a certain amount of time in + * the C state is required to actually break even on this cost. CPUIDLE + * provides us this duration in the "target_residency" field. So all that we + * need is a good prediction of how long we'll be idle. Like the traditional + * menu governor, we start with the actual known "next timer event" time. + * + * Since there are other source of wakeups (interrupts for example) than + * the next timer event, this estimation is rather optimistic. To get a + * more realistic estimate, a correction factor is applied to the estimate, + * that is based on historic behavior. For example, if in the past the actual + * duration always was 50% of the next timer tick, the correction factor will + * be 0.5. + * + * menu uses a running average for this correction factor, however it uses a + * set of factors, not just a single factor. This stems from the realization + * that the ratio is dependent on the order of magnitude of the expected + * duration; if we expect 500 milliseconds of idle time the likelihood of + * getting an interrupt very early is much higher than if we expect 50 micro + * seconds of idle time. A second independent factor that has big impact on + * the actual factor is if there is (disk) IO outstanding or not. + * (as a special twist, we consider every sleep longer than 50 milliseconds + * as perfect; there are no power gains for sleeping longer than this) + * + * For these two reasons we keep an array of 12 independent factors, that gets + * indexed based on the magnitude of the expected duration as well as the + * "is IO outstanding" property. + * + * Repeatable-interval-detector + * ---------------------------- + * There are some cases where "next timer" is a completely unusable predictor: + * Those cases where the interval is fixed, for example due to hardware + * interrupt mitigation, but also due to fixed transfer rate devices such as + * mice. + * For this, we use a different predictor: We track the duration of the last 8 + * intervals and if the stand deviation of these 8 intervals is below a + * threshold value, we use the average of these intervals as prediction. + * + * Limiting Performance Impact + * --------------------------- + * C states, especially those with large exit latencies, can have a real + * noticeable impact on workloads, which is not acceptable for most sysadmins, + * and in addition, less performance has a power price of its own. + * + * As a general rule of thumb, menu assumes that the following heuristic + * holds: + * The busier the system, the less impact of C states is acceptable + * + * This rule-of-thumb is implemented using a performance-multiplier: + * If the exit latency times the performance multiplier is longer than + * the predicted duration, the C state is not considered a candidate + * for selection due to a too high performance impact. So the higher + * this multiplier is, the longer we need to be idle to pick a deep C + * state, and thus the less likely a busy CPU will hit such a deep + * C state. + * + * Two factors are used in determing this multiplier: + * a value of 10 is added for each point of "per cpu load average" we have. + * a value of 5 points is added for each process that is waiting for + * IO on this CPU. + * (these values are experimentally determined) + * + * The load average factor gives a longer term (few seconds) input to the + * decision, while the iowait value gives a cpu local instantanious input. + * The iowait factor may look low, but realize that this is also already + * represented in the system load average. + * + */ + +struct menu_device { + int last_state_idx; + int needs_update; + int tick_wakeup; + + unsigned int next_timer_us; + unsigned int predicted_us; + unsigned int bucket; + unsigned int correction_factor[BUCKETS]; + unsigned int intervals[INTERVALS]; + int interval_ptr; +}; + + +#define LOAD_INT(x) ((x) >> FSHIFT) +#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100) + +static inline int get_loadavg(unsigned long load) +{ + return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10; +} + +static inline int which_bucket(unsigned int duration, unsigned long nr_iowaiters) +{ + int bucket = 0; + + /* + * We keep two groups of stats; one with no + * IO pending, one without. + * This allows us to calculate + * E(duration)|iowait + */ + if (nr_iowaiters) + bucket = BUCKETS/2; + + if (duration < 10) + return bucket; + if (duration < 100) + return bucket + 1; + if (duration < 1000) + return bucket + 2; + if (duration < 10000) + return bucket + 3; + if (duration < 100000) + return bucket + 4; + return bucket + 5; +} + +/* + * Return a multiplier for the exit latency that is intended + * to take performance requirements into account. + * The more performance critical we estimate the system + * to be, the higher this multiplier, and thus the higher + * the barrier to go to an expensive C state. + */ +static inline int performance_multiplier(unsigned long nr_iowaiters, unsigned long load) +{ + int mult = 1; + + /* for higher loadavg, we are more reluctant */ + + mult += 2 * get_loadavg(load); + + /* for IO wait tasks (per cpu!) we add 5x each */ + mult += 10 * nr_iowaiters; + + return mult; +} + +static DEFINE_PER_CPU(struct menu_device, menu_devices); + +static void menu_update(struct cpuidle_driver *drv, struct cpuidle_device *dev); + +/* + * Try detecting repeating patterns by keeping track of the last 8 + * intervals, and checking if the standard deviation of that set + * of points is below a threshold. If it is... then use the + * average of these 8 points as the estimated value. + */ +static unsigned int get_typical_interval(struct menu_device *data) +{ + int i, divisor; + unsigned int max, thresh, avg; + uint64_t sum, variance; + + thresh = UINT_MAX; /* Discard outliers above this value */ + +again: + + /* First calculate the average of past intervals */ + max = 0; + sum = 0; + divisor = 0; + for (i = 0; i < INTERVALS; i++) { + unsigned int value = data->intervals[i]; + if (value <= thresh) { + sum += value; + divisor++; + if (value > max) + max = value; + } + } + if (divisor == INTERVALS) + avg = sum >> INTERVAL_SHIFT; + else + avg = div_u64(sum, divisor); + + /* Then try to determine variance */ + variance = 0; + for (i = 0; i < INTERVALS; i++) { + unsigned int value = data->intervals[i]; + if (value <= thresh) { + int64_t diff = (int64_t)value - avg; + variance += diff * diff; + } + } + if (divisor == INTERVALS) + variance >>= INTERVAL_SHIFT; + else + do_div(variance, divisor); + + /* + * The typical interval is obtained when standard deviation is + * small (stddev <= 20 us, variance <= 400 us^2) or standard + * deviation is small compared to the average interval (avg > + * 6*stddev, avg^2 > 36*variance). The average is smaller than + * UINT_MAX aka U32_MAX, so computing its square does not + * overflow a u64. We simply reject this candidate average if + * the standard deviation is greater than 715 s (which is + * rather unlikely). + * + * Use this result only if there is no timer to wake us up sooner. + */ + if (likely(variance <= U64_MAX/36)) { + if ((((u64)avg*avg > variance*36) && (divisor * 4 >= INTERVALS * 3)) + || variance <= 400) { + return avg; + } + } + + /* + * If we have outliers to the upside in our distribution, discard + * those by setting the threshold to exclude these outliers, then + * calculate the average and standard deviation again. Once we get + * down to the bottom 3/4 of our samples, stop excluding samples. + * + * This can deal with workloads that have long pauses interspersed + * with sporadic activity with a bunch of short pauses. + */ + if ((divisor * 4) <= INTERVALS * 3) + return UINT_MAX; + + thresh = max - 1; + goto again; +} + +/** + * menu_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 menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev, + bool *stop_tick) +{ + struct menu_device *data = this_cpu_ptr(&menu_devices); + int latency_req = cpuidle_governor_latency_req(dev->cpu); + int i; + int first_idx; + int idx; + unsigned int interactivity_req; + unsigned int expected_interval; + unsigned long nr_iowaiters, cpu_load; + ktime_t delta_next; + + if (data->needs_update) { + menu_update(drv, dev); + data->needs_update = 0; + } + + /* Special case when user has set very strict latency requirement */ + if (unlikely(latency_req == 0)) { + *stop_tick = false; + return 0; + } + + /* determine the expected residency time, round up */ + data->next_timer_us = ktime_to_us(tick_nohz_get_sleep_length(&delta_next)); + + get_iowait_load(&nr_iowaiters, &cpu_load); + data->bucket = which_bucket(data->next_timer_us, nr_iowaiters); + + /* + * Force the result of multiplication to be 64 bits even if both + * operands are 32 bits. + * Make sure to round up for half microseconds. + */ + data->predicted_us = DIV_ROUND_CLOSEST_ULL((uint64_t)data->next_timer_us * + data->correction_factor[data->bucket], + RESOLUTION * DECAY); + + expected_interval = get_typical_interval(data); + expected_interval = min(expected_interval, data->next_timer_us); + + first_idx = 0; + if (drv->states[0].flags & CPUIDLE_FLAG_POLLING) { + struct cpuidle_state *s = &drv->states[1]; + unsigned int polling_threshold; + + /* + * Default to a physical idle state, not to busy polling, unless + * a timer is going to trigger really really soon. + */ + polling_threshold = max_t(unsigned int, 20, s->target_residency); + if (data->next_timer_us > polling_threshold && + latency_req > s->exit_latency && !s->disabled && + !dev->states_usage[1].disable) + first_idx = 1; + } + + /* + * Use the lowest expected idle interval to pick the idle state. + */ + data->predicted_us = min(data->predicted_us, expected_interval); + + if (tick_nohz_tick_stopped()) { + /* + * If the tick is already stopped, the cost of possible short + * idle duration misprediction is much higher, because the CPU + * may be stuck in a shallow idle state for a long time as a + * result of it. In that case say we might mispredict and use + * the known time till the closest timer event for the idle + * state selection. + */ + if (data->predicted_us < TICK_USEC) + data->predicted_us = ktime_to_us(delta_next); + } else { + /* + * Use the performance multiplier and the user-configurable + * latency_req to determine the maximum exit latency. + */ + interactivity_req = data->predicted_us / performance_multiplier(nr_iowaiters, cpu_load); + if (latency_req > interactivity_req) + latency_req = interactivity_req; + } + + expected_interval = data->predicted_us; + /* + * Find the idle state with the lowest power while satisfying + * our constraints. + */ + idx = -1; + for (i = first_idx; i < drv->state_count; i++) { + struct cpuidle_state *s = &drv->states[i]; + struct cpuidle_state_usage *su = &dev->states_usage[i]; + + if (s->disabled || su->disable) + continue; + if (idx == -1) + idx = i; /* first enabled state */ + if (s->target_residency > data->predicted_us) { + if (data->predicted_us < TICK_USEC) + break; + + if (!tick_nohz_tick_stopped()) { + /* + * If the state selected so far is shallow, + * waking up early won't hurt, so retain the + * tick in that case and let the governor run + * again in the next iteration of the loop. + */ + expected_interval = drv->states[idx].target_residency; + break; + } + + /* + * If the state selected so far is shallow and this + * state's target residency matches the time till the + * closest timer event, select this one to avoid getting + * stuck in the shallow one for too long. + */ + if (drv->states[idx].target_residency < TICK_USEC && + s->target_residency <= ktime_to_us(delta_next)) + idx = i; + + goto out; + } + 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. + */ + expected_interval = drv->states[idx].target_residency; + break; + } + idx = i; + } + + if (idx == -1) + idx = 0; /* No states enabled. Must use 0. */ + + /* + * Don't stop the tick if the selected state is a polling one or if the + * expected idle duration is shorter than the tick period length. + */ + if (((drv->states[idx].flags & CPUIDLE_FLAG_POLLING) || + expected_interval < TICK_USEC) && !tick_nohz_tick_stopped()) { + unsigned int delta_next_us = ktime_to_us(delta_next); + + *stop_tick = false; + + if (idx > 0 && drv->states[idx].target_residency > delta_next_us) { + /* + * The tick is not going to be stopped and the target + * residency of the state to be returned is not within + * the time until the next timer event including the + * tick, so try to correct that. + */ + for (i = idx - 1; i >= 0; i--) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + idx = i; + if (drv->states[i].target_residency <= delta_next_us) + break; + } + } + } + +out: + data->last_state_idx = idx; + + return data->last_state_idx; +} + +/** + * menu_reflect - records that data structures need update + * @dev: the CPU + * @index: the index of actual entered state + * + * NOTE: it's important to be fast here because this operation will add to + * the overall exit latency. + */ +static void menu_reflect(struct cpuidle_device *dev, int index) +{ + struct menu_device *data = this_cpu_ptr(&menu_devices); + + data->last_state_idx = index; + data->needs_update = 1; + data->tick_wakeup = tick_nohz_idle_got_tick(); +} + +/** + * menu_update - attempts to guess what happened after entry + * @drv: cpuidle driver containing state data + * @dev: the CPU + */ +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; + struct cpuidle_state *target = &drv->states[last_idx]; + unsigned int measured_us; + unsigned int new_factor; + + /* + * Try to figure out how much time passed between entry to low + * power state and occurrence of the wakeup event. + * + * If the entered idle state didn't support residency measurements, + * we use them anyway if they are short, and if long, + * truncate to the whole expected time. + * + * Any measured amount of time will include the exit latency. + * Since we are interested in when the wakeup begun, not when it + * was completed, we must subtract the exit latency. However, if + * the measured amount of time is less than the exit latency, + * assume the state was never reached and the exit latency is 0. + */ + + if (data->tick_wakeup && data->next_timer_us > TICK_USEC) { + /* + * The nohz code said that there wouldn't be any events within + * the tick boundary (if the tick was stopped), but the idle + * duration predictor had a differing opinion. Since the CPU + * was woken up by a tick (that wasn't stopped after all), the + * predictor was not quite right, so assume that the CPU could + * have been idle long (but not forever) to help the idle + * duration predictor do a better job next time. + */ + measured_us = 9 * MAX_INTERESTING / 10; + } else if ((drv->states[last_idx].flags & CPUIDLE_FLAG_POLLING) && + dev->poll_time_limit) { + /* + * The CPU exited the "polling" state due to a time limit, so + * the idle duration prediction leading to the selection of that + * state was inaccurate. If a better prediction had been made, + * the CPU might have been woken up from idle by the next timer. + * Assume that to be the case. + */ + measured_us = data->next_timer_us; + } else { + /* measured value */ + measured_us = cpuidle_get_last_residency(dev); + + /* Deduct exit latency */ + if (measured_us > 2 * target->exit_latency) + measured_us -= target->exit_latency; + else + measured_us /= 2; + } + + /* Make sure our coefficients do not exceed unity */ + if (measured_us > data->next_timer_us) + measured_us = data->next_timer_us; + + /* Update our correction ratio */ + new_factor = data->correction_factor[data->bucket]; + new_factor -= new_factor / DECAY; + + if (data->next_timer_us > 0 && measured_us < MAX_INTERESTING) + new_factor += RESOLUTION * measured_us / data->next_timer_us; + else + /* + * we were idle so long that we count it as a perfect + * prediction + */ + new_factor += RESOLUTION; + + /* + * We don't want 0 as factor; we always want at least + * a tiny bit of estimated time. Fortunately, due to rounding, + * new_factor will stay nonzero regardless of measured_us values + * and the compiler can eliminate this test as long as DECAY > 1. + */ + if (DECAY == 1 && unlikely(new_factor == 0)) + new_factor = 1; + + data->correction_factor[data->bucket] = new_factor; + + /* update the repeating-pattern data */ + data->intervals[data->interval_ptr++] = measured_us; + if (data->interval_ptr >= INTERVALS) + data->interval_ptr = 0; +} + +/** + * menu_enable_device - scans a CPU's states and does setup + * @drv: cpuidle driver + * @dev: the CPU + */ +static int menu_enable_device(struct cpuidle_driver *drv, + struct cpuidle_device *dev) +{ + struct menu_device *data = &per_cpu(menu_devices, dev->cpu); + int i; + + memset(data, 0, sizeof(struct menu_device)); + + /* + * if the correction factor is 0 (eg first time init or cpu hotplug + * etc), we actually want to start out with a unity factor. + */ + for(i = 0; i < BUCKETS; i++) + data->correction_factor[i] = RESOLUTION * DECAY; + + return 0; +} + +static struct cpuidle_governor menu_governor = { + .name = "menu", + .rating = 20, + .enable = menu_enable_device, + .select = menu_select, + .reflect = menu_reflect, +}; + +/** + * init_menu - initializes the governor + */ +static int __init init_menu(void) +{ + return cpuidle_register_governor(&menu_governor); +} + +postcore_initcall(init_menu); diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c new file mode 100644 index 000000000..36ff5a1d9 --- /dev/null +++ b/drivers/cpuidle/poll_state.c @@ -0,0 +1,56 @@ +/* + * poll_state.c - Polling idle state + * + * This file is released under the GPLv2. + */ + +#include <linux/cpuidle.h> +#include <linux/sched.h> +#include <linux/sched/clock.h> +#include <linux/sched/idle.h> + +#define POLL_IDLE_TIME_LIMIT (TICK_NSEC / 16) +#define POLL_IDLE_RELAX_COUNT 200 + +static int __cpuidle poll_idle(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + u64 time_start = local_clock(); + + dev->poll_time_limit = false; + + local_irq_enable(); + if (!current_set_polling_and_test()) { + unsigned int loop_count = 0; + + while (!need_resched()) { + cpu_relax(); + if (loop_count++ < POLL_IDLE_RELAX_COUNT) + continue; + + loop_count = 0; + if (local_clock() - time_start > POLL_IDLE_TIME_LIMIT) { + dev->poll_time_limit = true; + break; + } + } + } + current_clr_polling(); + + return index; +} + +void cpuidle_poll_state_init(struct cpuidle_driver *drv) +{ + struct cpuidle_state *state = &drv->states[0]; + + snprintf(state->name, CPUIDLE_NAME_LEN, "POLL"); + snprintf(state->desc, CPUIDLE_DESC_LEN, "CPUIDLE CORE POLL IDLE"); + state->exit_latency = 0; + state->target_residency = 0; + state->power_usage = -1; + state->enter = poll_idle; + state->disabled = false; + state->flags = CPUIDLE_FLAG_POLLING; +} +EXPORT_SYMBOL_GPL(cpuidle_poll_state_init); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c new file mode 100644 index 000000000..d9b917529 --- /dev/null +++ b/drivers/cpuidle/sysfs.c @@ -0,0 +1,718 @@ +/* + * sysfs.c - sysfs support + * + * (C) 2006-2007 Shaohua Li <shaohua.li@intel.com> + * + * This code is licenced under the GPL. + */ + +#include <linux/kernel.h> +#include <linux/cpuidle.h> +#include <linux/sysfs.h> +#include <linux/slab.h> +#include <linux/cpu.h> +#include <linux/completion.h> +#include <linux/capability.h> +#include <linux/device.h> +#include <linux/kobject.h> + +#include "cpuidle.h" + +static unsigned int sysfs_switch; +static int __init cpuidle_sysfs_setup(char *unused) +{ + sysfs_switch = 1; + return 1; +} +__setup("cpuidle_sysfs_switch", cpuidle_sysfs_setup); + +static ssize_t show_available_governors(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + ssize_t i = 0; + struct cpuidle_governor *tmp; + + mutex_lock(&cpuidle_lock); + list_for_each_entry(tmp, &cpuidle_governors, governor_list) { + if (i >= (ssize_t) ((PAGE_SIZE/sizeof(char)) - + CPUIDLE_NAME_LEN - 2)) + goto out; + i += scnprintf(&buf[i], CPUIDLE_NAME_LEN, "%s ", tmp->name); + } + +out: + i+= sprintf(&buf[i], "\n"); + mutex_unlock(&cpuidle_lock); + return i; +} + +static ssize_t show_current_driver(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + ssize_t ret; + struct cpuidle_driver *drv; + + spin_lock(&cpuidle_driver_lock); + drv = cpuidle_get_driver(); + if (drv) + ret = sprintf(buf, "%s\n", drv->name); + else + ret = sprintf(buf, "none\n"); + spin_unlock(&cpuidle_driver_lock); + + return ret; +} + +static ssize_t show_current_governor(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + ssize_t ret; + + mutex_lock(&cpuidle_lock); + if (cpuidle_curr_governor) + ret = sprintf(buf, "%s\n", cpuidle_curr_governor->name); + else + ret = sprintf(buf, "none\n"); + mutex_unlock(&cpuidle_lock); + + return ret; +} + +static ssize_t store_current_governor(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + char gov_name[CPUIDLE_NAME_LEN]; + int ret = -EINVAL; + size_t len = count; + struct cpuidle_governor *gov; + + if (!len || len >= sizeof(gov_name)) + return -EINVAL; + + memcpy(gov_name, buf, len); + gov_name[len] = '\0'; + if (gov_name[len - 1] == '\n') + gov_name[--len] = '\0'; + + mutex_lock(&cpuidle_lock); + + list_for_each_entry(gov, &cpuidle_governors, governor_list) { + if (strlen(gov->name) == len && !strcmp(gov->name, gov_name)) { + ret = cpuidle_switch_governor(gov); + break; + } + } + + mutex_unlock(&cpuidle_lock); + + if (ret) + return ret; + else + return count; +} + +static DEVICE_ATTR(current_driver, 0444, show_current_driver, NULL); +static DEVICE_ATTR(current_governor_ro, 0444, show_current_governor, NULL); + +static struct attribute *cpuidle_default_attrs[] = { + &dev_attr_current_driver.attr, + &dev_attr_current_governor_ro.attr, + NULL +}; + +static DEVICE_ATTR(available_governors, 0444, show_available_governors, NULL); +static DEVICE_ATTR(current_governor, 0644, show_current_governor, + store_current_governor); + +static struct attribute *cpuidle_switch_attrs[] = { + &dev_attr_available_governors.attr, + &dev_attr_current_driver.attr, + &dev_attr_current_governor.attr, + NULL +}; + +static struct attribute_group cpuidle_attr_group = { + .attrs = cpuidle_default_attrs, + .name = "cpuidle", +}; + +/** + * cpuidle_add_interface - add CPU global sysfs attributes + */ +int cpuidle_add_interface(struct device *dev) +{ + if (sysfs_switch) + cpuidle_attr_group.attrs = cpuidle_switch_attrs; + + return sysfs_create_group(&dev->kobj, &cpuidle_attr_group); +} + +/** + * cpuidle_remove_interface - remove CPU global sysfs attributes + */ +void cpuidle_remove_interface(struct device *dev) +{ + sysfs_remove_group(&dev->kobj, &cpuidle_attr_group); +} + +struct cpuidle_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_device *, char *); + ssize_t (*store)(struct cpuidle_device *, const char *, size_t count); +}; + +#define define_one_ro(_name, show) \ + static struct cpuidle_attr attr_##_name = __ATTR(_name, 0444, show, NULL) +#define define_one_rw(_name, show, store) \ + static struct cpuidle_attr attr_##_name = __ATTR(_name, 0644, show, store) + +#define attr_to_cpuidleattr(a) container_of(a, struct cpuidle_attr, attr) + +struct cpuidle_device_kobj { + struct cpuidle_device *dev; + struct completion kobj_unregister; + struct kobject kobj; +}; + +static inline struct cpuidle_device *to_cpuidle_device(struct kobject *kobj) +{ + struct cpuidle_device_kobj *kdev = + container_of(kobj, struct cpuidle_device_kobj, kobj); + + return kdev->dev; +} + +static ssize_t cpuidle_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + int ret = -EIO; + struct cpuidle_device *dev = to_cpuidle_device(kobj); + struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr); + + if (cattr->show) { + mutex_lock(&cpuidle_lock); + ret = cattr->show(dev, buf); + mutex_unlock(&cpuidle_lock); + } + return ret; +} + +static ssize_t cpuidle_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t count) +{ + int ret = -EIO; + struct cpuidle_device *dev = to_cpuidle_device(kobj); + struct cpuidle_attr *cattr = attr_to_cpuidleattr(attr); + + if (cattr->store) { + mutex_lock(&cpuidle_lock); + ret = cattr->store(dev, buf, count); + mutex_unlock(&cpuidle_lock); + } + return ret; +} + +static const struct sysfs_ops cpuidle_sysfs_ops = { + .show = cpuidle_show, + .store = cpuidle_store, +}; + +static void cpuidle_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_device_kobj *kdev = + container_of(kobj, struct cpuidle_device_kobj, kobj); + + complete(&kdev->kobj_unregister); +} + +static struct kobj_type ktype_cpuidle = { + .sysfs_ops = &cpuidle_sysfs_ops, + .release = cpuidle_sysfs_release, +}; + +struct cpuidle_state_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_state *, \ + struct cpuidle_state_usage *, char *); + ssize_t (*store)(struct cpuidle_state *, \ + struct cpuidle_state_usage *, const char *, size_t); +}; + +#define define_one_state_ro(_name, show) \ +static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0444, show, NULL) + +#define define_one_state_rw(_name, show, store) \ +static struct cpuidle_state_attr attr_##_name = __ATTR(_name, 0644, show, store) + +#define define_show_state_function(_name) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, char *buf) \ +{ \ + return sprintf(buf, "%u\n", state->_name);\ +} + +#define define_store_state_ull_function(_name) \ +static ssize_t store_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + const char *buf, size_t size) \ +{ \ + unsigned long long value; \ + int err; \ + if (!capable(CAP_SYS_ADMIN)) \ + return -EPERM; \ + err = kstrtoull(buf, 0, &value); \ + if (err) \ + return err; \ + if (value) \ + state_usage->_name = 1; \ + else \ + state_usage->_name = 0; \ + return size; \ +} + +#define define_show_state_ull_function(_name) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + char *buf) \ +{ \ + return sprintf(buf, "%llu\n", state_usage->_name);\ +} + +#define define_show_state_str_function(_name) \ +static ssize_t show_state_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + char *buf) \ +{ \ + if (state->_name[0] == '\0')\ + return sprintf(buf, "<null>\n");\ + return sprintf(buf, "%s\n", state->_name);\ +} + +define_show_state_function(exit_latency) +define_show_state_function(target_residency) +define_show_state_function(power_usage) +define_show_state_ull_function(usage) +define_show_state_ull_function(time) +define_show_state_str_function(name) +define_show_state_str_function(desc) +define_show_state_ull_function(disable) +define_store_state_ull_function(disable) + +define_one_state_ro(name, show_state_name); +define_one_state_ro(desc, show_state_desc); +define_one_state_ro(latency, show_state_exit_latency); +define_one_state_ro(residency, show_state_target_residency); +define_one_state_ro(power, show_state_power_usage); +define_one_state_ro(usage, show_state_usage); +define_one_state_ro(time, show_state_time); +define_one_state_rw(disable, show_state_disable, store_state_disable); + +static struct attribute *cpuidle_state_default_attrs[] = { + &attr_name.attr, + &attr_desc.attr, + &attr_latency.attr, + &attr_residency.attr, + &attr_power.attr, + &attr_usage.attr, + &attr_time.attr, + &attr_disable.attr, + NULL +}; + +struct cpuidle_state_kobj { + struct cpuidle_state *state; + struct cpuidle_state_usage *state_usage; + struct completion kobj_unregister; + struct kobject kobj; +}; + +#ifdef CONFIG_SUSPEND +#define define_show_state_s2idle_ull_function(_name) \ +static ssize_t show_state_s2idle_##_name(struct cpuidle_state *state, \ + struct cpuidle_state_usage *state_usage, \ + char *buf) \ +{ \ + return sprintf(buf, "%llu\n", state_usage->s2idle_##_name);\ +} + +define_show_state_s2idle_ull_function(usage); +define_show_state_s2idle_ull_function(time); + +#define define_one_state_s2idle_ro(_name, show) \ +static struct cpuidle_state_attr attr_s2idle_##_name = \ + __ATTR(_name, 0444, show, NULL) + +define_one_state_s2idle_ro(usage, show_state_s2idle_usage); +define_one_state_s2idle_ro(time, show_state_s2idle_time); + +static struct attribute *cpuidle_state_s2idle_attrs[] = { + &attr_s2idle_usage.attr, + &attr_s2idle_time.attr, + NULL +}; + +static const struct attribute_group cpuidle_state_s2idle_group = { + .name = "s2idle", + .attrs = cpuidle_state_s2idle_attrs, +}; + +static void cpuidle_add_s2idle_attr_group(struct cpuidle_state_kobj *kobj) +{ + int ret; + + if (!kobj->state->enter_s2idle) + return; + + ret = sysfs_create_group(&kobj->kobj, &cpuidle_state_s2idle_group); + if (ret) + pr_debug("%s: sysfs attribute group not created\n", __func__); +} + +static void cpuidle_remove_s2idle_attr_group(struct cpuidle_state_kobj *kobj) +{ + if (kobj->state->enter_s2idle) + sysfs_remove_group(&kobj->kobj, &cpuidle_state_s2idle_group); +} +#else +static inline void cpuidle_add_s2idle_attr_group(struct cpuidle_state_kobj *kobj) { } +static inline void cpuidle_remove_s2idle_attr_group(struct cpuidle_state_kobj *kobj) { } +#endif /* CONFIG_SUSPEND */ + +#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 attr_to_stateattr(a) container_of(a, struct cpuidle_state_attr, attr) + +static ssize_t cpuidle_state_show(struct kobject *kobj, struct attribute *attr, + char * buf) +{ + int ret = -EIO; + 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); + + if (cattr->show) + ret = cattr->show(state, state_usage, buf); + + return ret; +} + +static ssize_t cpuidle_state_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t size) +{ + int ret = -EIO; + 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); + + if (cattr->store) + ret = cattr->store(state, state_usage, buf, size); + + return ret; +} + +static const struct sysfs_ops cpuidle_state_sysfs_ops = { + .show = cpuidle_state_show, + .store = cpuidle_state_store, +}; + +static void cpuidle_state_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_state_kobj *state_obj = kobj_to_state_obj(kobj); + + complete(&state_obj->kobj_unregister); +} + +static struct kobj_type ktype_state_cpuidle = { + .sysfs_ops = &cpuidle_state_sysfs_ops, + .default_attrs = cpuidle_state_default_attrs, + .release = cpuidle_state_sysfs_release, +}; + +static inline void cpuidle_free_state_kobj(struct cpuidle_device *device, int i) +{ + cpuidle_remove_s2idle_attr_group(device->kobjs[i]); + kobject_put(&device->kobjs[i]->kobj); + wait_for_completion(&device->kobjs[i]->kobj_unregister); + kfree(device->kobjs[i]); + device->kobjs[i] = NULL; +} + +/** + * cpuidle_add_state_sysfs - adds cpuidle states sysfs attributes + * @device: the target device + */ +static int cpuidle_add_state_sysfs(struct cpuidle_device *device) +{ + int i, ret = -ENOMEM; + struct cpuidle_state_kobj *kobj; + struct cpuidle_device_kobj *kdev = device->kobj_dev; + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); + + /* state statistics */ + for (i = 0; i < drv->state_count; i++) { + kobj = kzalloc(sizeof(struct cpuidle_state_kobj), GFP_KERNEL); + if (!kobj) { + ret = -ENOMEM; + goto error_state; + } + kobj->state = &drv->states[i]; + kobj->state_usage = &device->states_usage[i]; + init_completion(&kobj->kobj_unregister); + + ret = kobject_init_and_add(&kobj->kobj, &ktype_state_cpuidle, + &kdev->kobj, "state%d", i); + if (ret) { + kobject_put(&kobj->kobj); + kfree(kobj); + goto error_state; + } + cpuidle_add_s2idle_attr_group(kobj); + kobject_uevent(&kobj->kobj, KOBJ_ADD); + device->kobjs[i] = kobj; + } + + return 0; + +error_state: + for (i = i - 1; i >= 0; i--) + cpuidle_free_state_kobj(device, i); + return ret; +} + +/** + * cpuidle_remove_driver_sysfs - removes the cpuidle states sysfs attributes + * @device: the target device + */ +static void cpuidle_remove_state_sysfs(struct cpuidle_device *device) +{ + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(device); + int i; + + for (i = 0; i < drv->state_count; i++) + cpuidle_free_state_kobj(device, i); +} + +#ifdef CONFIG_CPU_IDLE_MULTIPLE_DRIVERS +#define kobj_to_driver_kobj(k) container_of(k, struct cpuidle_driver_kobj, kobj) +#define attr_to_driver_attr(a) container_of(a, struct cpuidle_driver_attr, attr) + +#define define_one_driver_ro(_name, show) \ + static struct cpuidle_driver_attr attr_driver_##_name = \ + __ATTR(_name, 0444, show, NULL) + +struct cpuidle_driver_kobj { + struct cpuidle_driver *drv; + struct completion kobj_unregister; + struct kobject kobj; +}; + +struct cpuidle_driver_attr { + struct attribute attr; + ssize_t (*show)(struct cpuidle_driver *, char *); + ssize_t (*store)(struct cpuidle_driver *, const char *, size_t); +}; + +static ssize_t show_driver_name(struct cpuidle_driver *drv, char *buf) +{ + ssize_t ret; + + spin_lock(&cpuidle_driver_lock); + ret = sprintf(buf, "%s\n", drv ? drv->name : "none"); + spin_unlock(&cpuidle_driver_lock); + + return ret; +} + +static void cpuidle_driver_sysfs_release(struct kobject *kobj) +{ + struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj); + complete(&driver_kobj->kobj_unregister); +} + +static ssize_t cpuidle_driver_show(struct kobject *kobj, struct attribute *attr, + char *buf) +{ + int ret = -EIO; + struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj); + struct cpuidle_driver_attr *dattr = attr_to_driver_attr(attr); + + if (dattr->show) + ret = dattr->show(driver_kobj->drv, buf); + + return ret; +} + +static ssize_t cpuidle_driver_store(struct kobject *kobj, struct attribute *attr, + const char *buf, size_t size) +{ + int ret = -EIO; + struct cpuidle_driver_kobj *driver_kobj = kobj_to_driver_kobj(kobj); + struct cpuidle_driver_attr *dattr = attr_to_driver_attr(attr); + + if (dattr->store) + ret = dattr->store(driver_kobj->drv, buf, size); + + return ret; +} + +define_one_driver_ro(name, show_driver_name); + +static const struct sysfs_ops cpuidle_driver_sysfs_ops = { + .show = cpuidle_driver_show, + .store = cpuidle_driver_store, +}; + +static struct attribute *cpuidle_driver_default_attrs[] = { + &attr_driver_name.attr, + NULL +}; + +static struct kobj_type ktype_driver_cpuidle = { + .sysfs_ops = &cpuidle_driver_sysfs_ops, + .default_attrs = cpuidle_driver_default_attrs, + .release = cpuidle_driver_sysfs_release, +}; + +/** + * cpuidle_add_driver_sysfs - adds the driver name sysfs attribute + * @device: the target device + */ +static int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) +{ + struct cpuidle_driver_kobj *kdrv; + struct cpuidle_device_kobj *kdev = dev->kobj_dev; + struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); + int ret; + + kdrv = kzalloc(sizeof(*kdrv), GFP_KERNEL); + if (!kdrv) + return -ENOMEM; + + kdrv->drv = drv; + init_completion(&kdrv->kobj_unregister); + + ret = kobject_init_and_add(&kdrv->kobj, &ktype_driver_cpuidle, + &kdev->kobj, "driver"); + if (ret) { + kobject_put(&kdrv->kobj); + kfree(kdrv); + return ret; + } + + kobject_uevent(&kdrv->kobj, KOBJ_ADD); + dev->kobj_driver = kdrv; + + return ret; +} + +/** + * cpuidle_remove_driver_sysfs - removes the driver name sysfs attribute + * @device: the target device + */ +static void cpuidle_remove_driver_sysfs(struct cpuidle_device *dev) +{ + struct cpuidle_driver_kobj *kdrv = dev->kobj_driver; + kobject_put(&kdrv->kobj); + wait_for_completion(&kdrv->kobj_unregister); + kfree(kdrv); +} +#else +static inline int cpuidle_add_driver_sysfs(struct cpuidle_device *dev) +{ + return 0; +} + +static inline void cpuidle_remove_driver_sysfs(struct cpuidle_device *dev) +{ + ; +} +#endif + +/** + * cpuidle_add_device_sysfs - adds device specific sysfs attributes + * @device: the target device + */ +int cpuidle_add_device_sysfs(struct cpuidle_device *device) +{ + int ret; + + ret = cpuidle_add_state_sysfs(device); + if (ret) + return ret; + + ret = cpuidle_add_driver_sysfs(device); + if (ret) + cpuidle_remove_state_sysfs(device); + return ret; +} + +/** + * cpuidle_remove_device_sysfs : removes device specific sysfs attributes + * @device : the target device + */ +void cpuidle_remove_device_sysfs(struct cpuidle_device *device) +{ + cpuidle_remove_driver_sysfs(device); + cpuidle_remove_state_sysfs(device); +} + +/** + * cpuidle_add_sysfs - creates a sysfs instance for the target device + * @dev: the target device + */ +int cpuidle_add_sysfs(struct cpuidle_device *dev) +{ + struct cpuidle_device_kobj *kdev; + struct device *cpu_dev = get_cpu_device((unsigned long)dev->cpu); + int error; + + /* + * Return if cpu_device is not setup for this CPU. + * + * This could happen if the arch did not set up cpu_device + * since this CPU is not in cpu_present mask and the + * driver did not send a correct CPU mask during registration. + * Without this check we would end up passing bogus + * value for &cpu_dev->kobj in kobject_init_and_add() + */ + if (!cpu_dev) + return -ENODEV; + + kdev = kzalloc(sizeof(*kdev), GFP_KERNEL); + if (!kdev) + return -ENOMEM; + kdev->dev = dev; + + init_completion(&kdev->kobj_unregister); + + error = kobject_init_and_add(&kdev->kobj, &ktype_cpuidle, &cpu_dev->kobj, + "cpuidle"); + if (error) { + kobject_put(&kdev->kobj); + kfree(kdev); + return error; + } + + dev->kobj_dev = kdev; + kobject_uevent(&kdev->kobj, KOBJ_ADD); + + return 0; +} + +/** + * cpuidle_remove_sysfs - deletes a sysfs instance on the target device + * @dev: the target device + */ +void cpuidle_remove_sysfs(struct cpuidle_device *dev) +{ + struct cpuidle_device_kobj *kdev = dev->kobj_dev; + + kobject_put(&kdev->kobj); + wait_for_completion(&kdev->kobj_unregister); + kfree(kdev); +} |