--- zzzz-none-000/linux-3.10.107/kernel/stop_machine.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/kernel/stop_machine.c 2021-02-04 17:41:59.000000000 +0000 @@ -20,6 +20,7 @@ #include #include #include +#include /* * Structure to determine completion condition and record errors. May @@ -34,15 +35,26 @@ /* the actual stopper, one per every possible cpu, enabled on online cpus */ struct cpu_stopper { + struct task_struct *thread; + spinlock_t lock; bool enabled; /* is this stopper enabled? */ struct list_head works; /* list of pending works */ + + struct cpu_stop_work stop_work; /* for stop_cpus */ }; static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper); -static DEFINE_PER_CPU(struct task_struct *, cpu_stopper_task); static bool stop_machine_initialized = false; +/* + * Avoids a race between stop_two_cpus and global stop_cpus, where + * the stoppers could get queued up in reverse order, leading to + * system deadlock. Using an lglock means stop_two_cpus remains + * relatively cheap. + */ +DEFINE_STATIC_LGLOCK(stop_cpus_lock); + static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo) { memset(done, 0, sizeof(*done)); @@ -61,22 +73,24 @@ } } +static void __cpu_stop_queue_work(struct cpu_stopper *stopper, + struct cpu_stop_work *work) +{ + list_add_tail(&work->list, &stopper->works); + wake_up_process(stopper->thread); +} + /* queue @work to @stopper. if offline, @work is completed immediately */ static void cpu_stop_queue_work(unsigned int cpu, struct cpu_stop_work *work) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - struct task_struct *p = per_cpu(cpu_stopper_task, cpu); - unsigned long flags; spin_lock_irqsave(&stopper->lock, flags); - - if (stopper->enabled) { - list_add_tail(&work->list, &stopper->works); - wake_up_process(p); - } else + if (stopper->enabled) + __cpu_stop_queue_work(stopper, work); + else cpu_stop_signal_done(work->done, false); - spin_unlock_irqrestore(&stopper->lock, flags); } @@ -115,11 +129,172 @@ return done.executed ? done.ret : -ENOENT; } +/* This controls the threads on each CPU. */ +enum multi_stop_state { + /* Dummy starting state for thread. */ + MULTI_STOP_NONE, + /* Awaiting everyone to be scheduled. */ + MULTI_STOP_PREPARE, + /* Disable interrupts. */ + MULTI_STOP_DISABLE_IRQ, + /* Run the function */ + MULTI_STOP_RUN, + /* Exit */ + MULTI_STOP_EXIT, +}; + +struct multi_stop_data { + cpu_stop_fn_t fn; + void *data; + /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ + unsigned int num_threads; + const struct cpumask *active_cpus; + + enum multi_stop_state state; + atomic_t thread_ack; +}; + +static void set_state(struct multi_stop_data *msdata, + enum multi_stop_state newstate) +{ + /* Reset ack counter. */ + atomic_set(&msdata->thread_ack, msdata->num_threads); + smp_wmb(); + msdata->state = newstate; +} + +/* Last one to ack a state moves to the next state. */ +static void ack_state(struct multi_stop_data *msdata) +{ + if (atomic_dec_and_test(&msdata->thread_ack)) + set_state(msdata, msdata->state + 1); +} + +/* This is the cpu_stop function which stops the CPU. */ +static int multi_cpu_stop(void *data) +{ + struct multi_stop_data *msdata = data; + enum multi_stop_state curstate = MULTI_STOP_NONE; + int cpu = smp_processor_id(), err = 0; + unsigned long flags; + bool is_active; + + /* + * When called from stop_machine_from_inactive_cpu(), irq might + * already be disabled. Save the state and restore it on exit. + */ + local_save_flags(flags); + + if (!msdata->active_cpus) + is_active = cpu == cpumask_first(cpu_online_mask); + else + is_active = cpumask_test_cpu(cpu, msdata->active_cpus); + + /* Simple state machine */ + do { + /* Chill out and ensure we re-read multi_stop_state. */ + cpu_relax(); + if (msdata->state != curstate) { + curstate = msdata->state; + switch (curstate) { + case MULTI_STOP_DISABLE_IRQ: + local_irq_disable(); + hard_irq_disable(); + break; + case MULTI_STOP_RUN: + if (is_active) + err = msdata->fn(msdata->data); + break; + default: + break; + } + ack_state(msdata); + } + } while (curstate != MULTI_STOP_EXIT); + + local_irq_restore(flags); + return err; +} + +static int cpu_stop_queue_two_works(int cpu1, struct cpu_stop_work *work1, + int cpu2, struct cpu_stop_work *work2) +{ + struct cpu_stopper *stopper1 = per_cpu_ptr(&cpu_stopper, cpu1); + struct cpu_stopper *stopper2 = per_cpu_ptr(&cpu_stopper, cpu2); + int err; + + lg_double_lock(&stop_cpus_lock, cpu1, cpu2); + spin_lock_irq(&stopper1->lock); + spin_lock_nested(&stopper2->lock, SINGLE_DEPTH_NESTING); + + err = -ENOENT; + if (!stopper1->enabled || !stopper2->enabled) + goto unlock; + + err = 0; + __cpu_stop_queue_work(stopper1, work1); + __cpu_stop_queue_work(stopper2, work2); +unlock: + spin_unlock(&stopper2->lock); + spin_unlock_irq(&stopper1->lock); + lg_double_unlock(&stop_cpus_lock, cpu1, cpu2); + + return err; +} +/** + * stop_two_cpus - stops two cpus + * @cpu1: the cpu to stop + * @cpu2: the other cpu to stop + * @fn: function to execute + * @arg: argument to @fn + * + * Stops both the current and specified CPU and runs @fn on one of them. + * + * returns when both are completed. + */ +int stop_two_cpus(unsigned int cpu1, unsigned int cpu2, cpu_stop_fn_t fn, void *arg) +{ + struct cpu_stop_done done; + struct cpu_stop_work work1, work2; + struct multi_stop_data msdata; + + preempt_disable(); + msdata = (struct multi_stop_data){ + .fn = fn, + .data = arg, + .num_threads = 2, + .active_cpus = cpumask_of(cpu1), + }; + + work1 = work2 = (struct cpu_stop_work){ + .fn = multi_cpu_stop, + .arg = &msdata, + .done = &done + }; + + cpu_stop_init_done(&done, 2); + set_state(&msdata, MULTI_STOP_PREPARE); + + if (cpu1 > cpu2) + swap(cpu1, cpu2); + if (cpu_stop_queue_two_works(cpu1, &work1, cpu2, &work2)) { + preempt_enable(); + return -ENOENT; + } + + preempt_enable(); + + wait_for_completion(&done.completion); + + return done.executed ? done.ret : -ENOENT; +} + /** * stop_one_cpu_nowait - stop a cpu but don't wait for completion * @cpu: cpu to stop * @fn: function to execute * @arg: argument to @fn + * @work_buf: pointer to cpu_stop_work structure * * Similar to stop_one_cpu() but doesn't wait for completion. The * caller is responsible for ensuring @work_buf is currently unused @@ -137,7 +312,6 @@ /* static data for stop_cpus */ static DEFINE_MUTEX(stop_cpus_mutex); -static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work); static void queue_stop_cpus_work(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg, @@ -146,23 +320,20 @@ struct cpu_stop_work *work; unsigned int cpu; - /* initialize works and done */ - for_each_cpu(cpu, cpumask) { - work = &per_cpu(stop_cpus_work, cpu); - work->fn = fn; - work->arg = arg; - work->done = done; - } - /* * Disable preemption while queueing to avoid getting * preempted by a stopper which might wait for other stoppers * to enter @fn which can lead to deadlock. */ - preempt_disable(); - for_each_cpu(cpu, cpumask) - cpu_stop_queue_work(cpu, &per_cpu(stop_cpus_work, cpu)); - preempt_enable(); + lg_global_lock(&stop_cpus_lock); + for_each_cpu(cpu, cpumask) { + work = &per_cpu(cpu_stopper.stop_work, cpu); + work->fn = fn; + work->arg = arg; + work->done = done; + cpu_stop_queue_work(cpu, work); + } + lg_global_unlock(&stop_cpus_lock); } static int __stop_cpus(const struct cpumask *cpumask, @@ -298,45 +469,47 @@ } } +void stop_machine_park(int cpu) +{ + struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); + /* + * Lockless. cpu_stopper_thread() will take stopper->lock and flush + * the pending works before it parks, until then it is fine to queue + * the new works. + */ + stopper->enabled = false; + kthread_park(stopper->thread); +} + extern void sched_set_stop_task(int cpu, struct task_struct *stop); static void cpu_stop_create(unsigned int cpu) { - sched_set_stop_task(cpu, per_cpu(cpu_stopper_task, cpu)); + sched_set_stop_task(cpu, per_cpu(cpu_stopper.thread, cpu)); } static void cpu_stop_park(unsigned int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - struct cpu_stop_work *work; - unsigned long flags; - /* drain remaining works */ - spin_lock_irqsave(&stopper->lock, flags); - list_for_each_entry(work, &stopper->works, list) - cpu_stop_signal_done(work->done, false); - stopper->enabled = false; - spin_unlock_irqrestore(&stopper->lock, flags); + WARN_ON(!list_empty(&stopper->works)); } -static void cpu_stop_unpark(unsigned int cpu) +void stop_machine_unpark(int cpu) { struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu); - spin_lock_irq(&stopper->lock); stopper->enabled = true; - spin_unlock_irq(&stopper->lock); + kthread_unpark(stopper->thread); } static struct smp_hotplug_thread cpu_stop_threads = { - .store = &cpu_stopper_task, + .store = &cpu_stopper.thread, .thread_should_run = cpu_stop_should_run, .thread_fn = cpu_stopper_thread, .thread_comm = "migration/%u", .create = cpu_stop_create, - .setup = cpu_stop_unpark, .park = cpu_stop_park, - .pre_unpark = cpu_stop_unpark, .selfparking = true, }; @@ -352,105 +525,22 @@ } BUG_ON(smpboot_register_percpu_thread(&cpu_stop_threads)); + stop_machine_unpark(raw_smp_processor_id()); stop_machine_initialized = true; return 0; } early_initcall(cpu_stop_init); -#ifdef CONFIG_STOP_MACHINE - -/* This controls the threads on each CPU. */ -enum stopmachine_state { - /* Dummy starting state for thread. */ - STOPMACHINE_NONE, - /* Awaiting everyone to be scheduled. */ - STOPMACHINE_PREPARE, - /* Disable interrupts. */ - STOPMACHINE_DISABLE_IRQ, - /* Run the function */ - STOPMACHINE_RUN, - /* Exit */ - STOPMACHINE_EXIT, -}; - -struct stop_machine_data { - int (*fn)(void *); - void *data; - /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */ - unsigned int num_threads; - const struct cpumask *active_cpus; - - enum stopmachine_state state; - atomic_t thread_ack; -}; - -static void set_state(struct stop_machine_data *smdata, - enum stopmachine_state newstate) -{ - /* Reset ack counter. */ - atomic_set(&smdata->thread_ack, smdata->num_threads); - smp_wmb(); - smdata->state = newstate; -} - -/* Last one to ack a state moves to the next state. */ -static void ack_state(struct stop_machine_data *smdata) -{ - if (atomic_dec_and_test(&smdata->thread_ack)) - set_state(smdata, smdata->state + 1); -} +#if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU) -/* This is the cpu_stop function which stops the CPU. */ -static int stop_machine_cpu_stop(void *data) +static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { - struct stop_machine_data *smdata = data; - enum stopmachine_state curstate = STOPMACHINE_NONE; - int cpu = smp_processor_id(), err = 0; - unsigned long flags; - bool is_active; - - /* - * When called from stop_machine_from_inactive_cpu(), irq might - * already be disabled. Save the state and restore it on exit. - */ - local_save_flags(flags); - - if (!smdata->active_cpus) - is_active = cpu == cpumask_first(cpu_online_mask); - else - is_active = cpumask_test_cpu(cpu, smdata->active_cpus); - - /* Simple state machine */ - do { - /* Chill out and ensure we re-read stopmachine_state. */ - cpu_relax(); - if (smdata->state != curstate) { - curstate = smdata->state; - switch (curstate) { - case STOPMACHINE_DISABLE_IRQ: - local_irq_disable(); - hard_irq_disable(); - break; - case STOPMACHINE_RUN: - if (is_active) - err = smdata->fn(smdata->data); - break; - default: - break; - } - ack_state(smdata); - } - } while (curstate != STOPMACHINE_EXIT); - - local_irq_restore(flags); - return err; -} - -int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) -{ - struct stop_machine_data smdata = { .fn = fn, .data = data, - .num_threads = num_online_cpus(), - .active_cpus = cpus }; + struct multi_stop_data msdata = { + .fn = fn, + .data = data, + .num_threads = num_online_cpus(), + .active_cpus = cpus, + }; if (!stop_machine_initialized) { /* @@ -461,7 +551,7 @@ unsigned long flags; int ret; - WARN_ON_ONCE(smdata.num_threads != 1); + WARN_ON_ONCE(msdata.num_threads != 1); local_irq_save(flags); hard_irq_disable(); @@ -472,11 +562,11 @@ } /* Set the initial state and stop all online cpus. */ - set_state(&smdata, STOPMACHINE_PREPARE); - return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata); + set_state(&msdata, MULTI_STOP_PREPARE); + return stop_cpus(cpu_online_mask, multi_cpu_stop, &msdata); } -int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus) +int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { int ret; @@ -510,28 +600,28 @@ * 0 if all executions of @fn returned 0, any non zero return value if any * returned non zero. */ -int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data, +int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus) { - struct stop_machine_data smdata = { .fn = fn, .data = data, + struct multi_stop_data msdata = { .fn = fn, .data = data, .active_cpus = cpus }; struct cpu_stop_done done; int ret; /* Local CPU must be inactive and CPU hotplug in progress. */ BUG_ON(cpu_active(raw_smp_processor_id())); - smdata.num_threads = num_active_cpus() + 1; /* +1 for local */ + msdata.num_threads = num_active_cpus() + 1; /* +1 for local */ /* No proper task established and can't sleep - busy wait for lock. */ while (!mutex_trylock(&stop_cpus_mutex)) cpu_relax(); /* Schedule work on other CPUs and execute directly for local CPU */ - set_state(&smdata, STOPMACHINE_PREPARE); + set_state(&msdata, MULTI_STOP_PREPARE); cpu_stop_init_done(&done, num_active_cpus()); - queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata, + queue_stop_cpus_work(cpu_active_mask, multi_cpu_stop, &msdata, &done); - ret = stop_machine_cpu_stop(&smdata); + ret = multi_cpu_stop(&msdata); /* Busy wait for completion. */ while (!completion_done(&done.completion)) @@ -541,4 +631,4 @@ return ret ?: done.ret; } -#endif /* CONFIG_STOP_MACHINE */ +#endif /* CONFIG_SMP || CONFIG_HOTPLUG_CPU */