diff options
Diffstat (limited to 'kernel/kthread.c')
| -rw-r--r-- | kernel/kthread.c | 671 |
1 files changed, 530 insertions, 141 deletions
diff --git a/kernel/kthread.c b/kernel/kthread.c index 132f84a5fde3..5dc5b0d7238e 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -27,6 +27,7 @@ #include <linux/ptrace.h> #include <linux/uaccess.h> #include <linux/numa.h> +#include <linux/sched/isolation.h> #include <trace/events/sched.h> @@ -34,9 +35,13 @@ static DEFINE_SPINLOCK(kthread_create_lock); static LIST_HEAD(kthread_create_list); struct task_struct *kthreadd_task; +static LIST_HEAD(kthreads_hotplug); +static DEFINE_MUTEX(kthreads_hotplug_lock); + struct kthread_create_info { /* Information passed to kthread() from kthreadd. */ + char *full_name; int (*threadfn)(void *data); void *data; int node; @@ -51,14 +56,21 @@ struct kthread_create_info struct kthread { unsigned long flags; unsigned int cpu; + unsigned int node; + int started; + int result; int (*threadfn)(void *); void *data; - mm_segment_t oldfs; struct completion parked; struct completion exited; #ifdef CONFIG_BLK_CGROUP struct cgroup_subsys_state *blkcg_css; #endif + /* To store the full name if task comm is truncated. */ + char *full_name; + struct task_struct *task; + struct list_head hotplug_node; + struct cpumask *preferred_affinity; }; enum KTHREAD_BITS { @@ -67,20 +79,63 @@ enum KTHREAD_BITS { KTHREAD_SHOULD_PARK, }; -static inline void set_kthread_struct(void *kthread) +static inline struct kthread *to_kthread(struct task_struct *k) { - /* - * We abuse ->set_child_tid to avoid the new member and because it - * can't be wrongly copied by copy_process(). We also rely on fact - * that the caller can't exec, so PF_KTHREAD can't be cleared. - */ - current->set_child_tid = (__force void __user *)kthread; + WARN_ON(!(k->flags & PF_KTHREAD)); + return k->worker_private; } -static inline struct kthread *to_kthread(struct task_struct *k) +/* + * Variant of to_kthread() that doesn't assume @p is a kthread. + * + * Per construction; when: + * + * (p->flags & PF_KTHREAD) && p->worker_private + * + * the task is both a kthread and struct kthread is persistent. However + * PF_KTHREAD on it's own is not, kernel_thread() can exec() (See umh.c and + * begin_new_exec()). + */ +static inline struct kthread *__to_kthread(struct task_struct *p) { - WARN_ON(!(k->flags & PF_KTHREAD)); - return (__force void *)k->set_child_tid; + void *kthread = p->worker_private; + if (kthread && !(p->flags & PF_KTHREAD)) + kthread = NULL; + return kthread; +} + +void get_kthread_comm(char *buf, size_t buf_size, struct task_struct *tsk) +{ + struct kthread *kthread = to_kthread(tsk); + + if (!kthread || !kthread->full_name) { + strscpy(buf, tsk->comm, buf_size); + return; + } + + strscpy_pad(buf, kthread->full_name, buf_size); +} + +bool set_kthread_struct(struct task_struct *p) +{ + struct kthread *kthread; + + if (WARN_ON_ONCE(to_kthread(p))) + return false; + + kthread = kzalloc(sizeof(*kthread), GFP_KERNEL); + if (!kthread) + return false; + + init_completion(&kthread->exited); + init_completion(&kthread->parked); + INIT_LIST_HEAD(&kthread->hotplug_node); + p->vfork_done = &kthread->exited; + + kthread->task = p; + kthread->node = tsk_fork_get_node(current); + p->worker_private = kthread; + return true; } void free_kthread_struct(struct task_struct *k) @@ -88,13 +143,17 @@ void free_kthread_struct(struct task_struct *k) struct kthread *kthread; /* - * Can be NULL if this kthread was created by kernel_thread() - * or if kmalloc() in kthread() failed. + * Can be NULL if kmalloc() in set_kthread_struct() failed. */ kthread = to_kthread(k); + if (!kthread) + return; + #ifdef CONFIG_BLK_CGROUP - WARN_ON_ONCE(kthread && kthread->blkcg_css); + WARN_ON_ONCE(kthread->blkcg_css); #endif + k->worker_private = NULL; + kfree(kthread->full_name); kfree(kthread); } @@ -111,11 +170,10 @@ bool kthread_should_stop(void) } EXPORT_SYMBOL(kthread_should_stop); -bool __kthread_should_park(struct task_struct *k) +static bool __kthread_should_park(struct task_struct *k) { return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(k)->flags); } -EXPORT_SYMBOL_GPL(__kthread_should_park); /** * kthread_should_park - should this kthread park now? @@ -134,6 +192,16 @@ bool kthread_should_park(void) } EXPORT_SYMBOL_GPL(kthread_should_park); +bool kthread_should_stop_or_park(void) +{ + struct kthread *kthread = __to_kthread(current); + + if (!kthread) + return false; + + return kthread->flags & (BIT(KTHREAD_SHOULD_STOP) | BIT(KTHREAD_SHOULD_PARK)); +} + /** * kthread_freezable_should_stop - should this freezable kthread return now? * @was_frozen: optional out parameter, indicates whether %current was frozen @@ -167,8 +235,9 @@ EXPORT_SYMBOL_GPL(kthread_freezable_should_stop); */ void *kthread_func(struct task_struct *task) { - if (task->flags & PF_KTHREAD) - return to_kthread(task)->threadfn; + struct kthread *kthread = __to_kthread(task); + if (kthread) + return kthread->threadfn; return NULL; } EXPORT_SYMBOL_GPL(kthread_func); @@ -198,10 +267,11 @@ EXPORT_SYMBOL_GPL(kthread_data); */ void *kthread_probe_data(struct task_struct *task) { - struct kthread *kthread = to_kthread(task); + struct kthread *kthread = __to_kthread(task); void *data = NULL; - copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); + if (kthread) + copy_from_kernel_nofault(&data, &kthread->data, sizeof(data)); return data; } @@ -240,8 +310,108 @@ void kthread_parkme(void) } EXPORT_SYMBOL_GPL(kthread_parkme); +/** + * kthread_exit - Cause the current kthread return @result to kthread_stop(). + * @result: The integer value to return to kthread_stop(). + * + * While kthread_exit can be called directly, it exists so that + * functions which do some additional work in non-modular code such as + * module_put_and_kthread_exit can be implemented. + * + * Does not return. + */ +void __noreturn kthread_exit(long result) +{ + struct kthread *kthread = to_kthread(current); + kthread->result = result; + if (!list_empty(&kthread->hotplug_node)) { + mutex_lock(&kthreads_hotplug_lock); + list_del(&kthread->hotplug_node); + mutex_unlock(&kthreads_hotplug_lock); + + if (kthread->preferred_affinity) { + kfree(kthread->preferred_affinity); + kthread->preferred_affinity = NULL; + } + } + do_exit(0); +} +EXPORT_SYMBOL(kthread_exit); + +/** + * kthread_complete_and_exit - Exit the current kthread. + * @comp: Completion to complete + * @code: The integer value to return to kthread_stop(). + * + * If present, complete @comp and then return code to kthread_stop(). + * + * A kernel thread whose module may be removed after the completion of + * @comp can use this function to exit safely. + * + * Does not return. + */ +void __noreturn kthread_complete_and_exit(struct completion *comp, long code) +{ + if (comp) + complete(comp); + + kthread_exit(code); +} +EXPORT_SYMBOL(kthread_complete_and_exit); + +static void kthread_fetch_affinity(struct kthread *kthread, struct cpumask *cpumask) +{ + const struct cpumask *pref; + + if (kthread->preferred_affinity) { + pref = kthread->preferred_affinity; + } else { + if (WARN_ON_ONCE(kthread->node == NUMA_NO_NODE)) + return; + pref = cpumask_of_node(kthread->node); + } + + cpumask_and(cpumask, pref, housekeeping_cpumask(HK_TYPE_KTHREAD)); + if (cpumask_empty(cpumask)) + cpumask_copy(cpumask, housekeeping_cpumask(HK_TYPE_KTHREAD)); +} + +static void kthread_affine_node(void) +{ + struct kthread *kthread = to_kthread(current); + cpumask_var_t affinity; + + WARN_ON_ONCE(kthread_is_per_cpu(current)); + + if (kthread->node == NUMA_NO_NODE) { + housekeeping_affine(current, HK_TYPE_KTHREAD); + } else { + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) { + WARN_ON_ONCE(1); + return; + } + + mutex_lock(&kthreads_hotplug_lock); + WARN_ON_ONCE(!list_empty(&kthread->hotplug_node)); + list_add_tail(&kthread->hotplug_node, &kthreads_hotplug); + /* + * The node cpumask is racy when read from kthread() but: + * - a racing CPU going down will either fail on the subsequent + * call to set_cpus_allowed_ptr() or be migrated to housekeepers + * afterwards by the scheduler. + * - a racing CPU going up will be handled by kthreads_online_cpu() + */ + kthread_fetch_affinity(kthread, affinity); + set_cpus_allowed_ptr(current, affinity); + mutex_unlock(&kthreads_hotplug_lock); + + free_cpumask_var(affinity); + } +} + static int kthread(void *_create) { + static const struct sched_param param = { .sched_priority = 0 }; /* Copy data: it's on kthread's stack */ struct kthread_create_info *create = _create; int (*threadfn)(void *data) = create->threadfn; @@ -250,27 +420,25 @@ static int kthread(void *_create) struct kthread *self; int ret; - self = kzalloc(sizeof(*self), GFP_KERNEL); - set_kthread_struct(self); + self = to_kthread(current); - /* If user was SIGKILLed, I release the structure. */ + /* Release the structure when caller killed by a fatal signal. */ done = xchg(&create->done, NULL); if (!done) { + kfree(create->full_name); kfree(create); - do_exit(-EINTR); - } - - if (!self) { - create->result = ERR_PTR(-ENOMEM); - complete(done); - do_exit(-ENOMEM); + kthread_exit(-EINTR); } + self->full_name = create->full_name; self->threadfn = threadfn; self->data = data; - init_completion(&self->exited); - init_completion(&self->parked); - current->vfork_done = &self->exited; + + /* + * The new thread inherited kthreadd's priority and CPU mask. Reset + * back to default in case they have been changed. + */ + sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m); /* OK, tell user we're spawned, wait for stop or wakeup */ __set_current_state(TASK_UNINTERRUPTIBLE); @@ -284,16 +452,21 @@ static int kthread(void *_create) schedule_preempt_disabled(); preempt_enable(); + self->started = 1; + + if (!(current->flags & PF_NO_SETAFFINITY) && !self->preferred_affinity) + kthread_affine_node(); + ret = -EINTR; if (!test_bit(KTHREAD_SHOULD_STOP, &self->flags)) { cgroup_kthread_ready(); __kthread_parkme(self); ret = threadfn(data); } - do_exit(ret); + kthread_exit(ret); } -/* called from do_fork() to get node information for about to be created task */ +/* called from kernel_clone() to get node information for about to be created task */ int tsk_fork_get_node(struct task_struct *tsk) { #ifdef CONFIG_NUMA @@ -311,11 +484,13 @@ static void create_kthread(struct kthread_create_info *create) current->pref_node_fork = create->node; #endif /* We want our own signal handler (we take no signals by default). */ - pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); + pid = kernel_thread(kthread, create, create->full_name, + CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { - /* If user was SIGKILLed, I release the structure. */ + /* Release the structure when caller killed by a fatal signal. */ struct completion *done = xchg(&create->done, NULL); + kfree(create->full_name); if (!done) { kfree(create); return; @@ -342,6 +517,11 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), create->data = data; create->node = node; create->done = &done; + create->full_name = kvasprintf(GFP_KERNEL, namefmt, args); + if (!create->full_name) { + task = ERR_PTR(-ENOMEM); + goto free_create; + } spin_lock(&kthread_create_lock); list_add_tail(&create->list, &kthread_create_list); @@ -355,9 +535,9 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), */ if (unlikely(wait_for_completion_killable(&done))) { /* - * If I was SIGKILLed before kthreadd (or new kernel thread) - * calls complete(), leave the cleanup of this structure to - * that thread. + * If I was killed by a fatal signal before kthreadd (or new + * kernel thread) calls complete(), leave the cleanup of this + * structure to that thread. */ if (xchg(&create->done, NULL)) return ERR_PTR(-EINTR); @@ -368,23 +548,7 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), wait_for_completion(&done); } task = create->result; - if (!IS_ERR(task)) { - static const struct sched_param param = { .sched_priority = 0 }; - char name[TASK_COMM_LEN]; - - /* - * task is already visible to other tasks, so updating - * COMM must be protected. - */ - vsnprintf(name, sizeof(name), namefmt, args); - set_task_comm(task, name); - /* - * root may have changed our (kthreadd's) priority or CPU mask. - * The kernel thread should not inherit these properties. - */ - sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(task, cpu_all_mask); - } +free_create: kfree(create); return task; } @@ -404,7 +568,7 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), * If thread is going to be bound on a particular cpu, give its node * in @node, to get NUMA affinity for kthread stack, or else give NUMA_NO_NODE. * When woken, the thread will run @threadfn() with @data as its - * argument. @threadfn() can either call do_exit() directly if it is a + * argument. @threadfn() can either return directly if it is a * standalone thread for which no one will call kthread_stop(), or * return when 'kthread_should_stop()' is true (which means * kthread_stop() has been called). The return value should be zero @@ -428,7 +592,7 @@ struct task_struct *kthread_create_on_node(int (*threadfn)(void *data), } EXPORT_SYMBOL(kthread_create_on_node); -static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, long state) +static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mask, unsigned int state) { unsigned long flags; @@ -444,14 +608,16 @@ static void __kthread_bind_mask(struct task_struct *p, const struct cpumask *mas raw_spin_unlock_irqrestore(&p->pi_lock, flags); } -static void __kthread_bind(struct task_struct *p, unsigned int cpu, long state) +static void __kthread_bind(struct task_struct *p, unsigned int cpu, unsigned int state) { __kthread_bind_mask(p, cpumask_of(cpu), state); } void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) { + struct kthread *kthread = to_kthread(p); __kthread_bind_mask(p, mask, TASK_UNINTERRUPTIBLE); + WARN_ON_ONCE(kthread->started); } /** @@ -465,7 +631,9 @@ void kthread_bind_mask(struct task_struct *p, const struct cpumask *mask) */ void kthread_bind(struct task_struct *p, unsigned int cpu) { + struct kthread *kthread = to_kthread(p); __kthread_bind(p, cpu, TASK_UNINTERRUPTIBLE); + WARN_ON_ONCE(kthread->started); } EXPORT_SYMBOL(kthread_bind); @@ -478,7 +646,6 @@ EXPORT_SYMBOL(kthread_bind); * to "name.*%u". Code fills in cpu number. * * Description: This helper function creates and names a kernel thread - * The thread will be woken and put into park mode. */ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), void *data, unsigned int cpu, @@ -492,10 +659,36 @@ struct task_struct *kthread_create_on_cpu(int (*threadfn)(void *data), return p; kthread_bind(p, cpu); /* CPU hotplug need to bind once again when unparking the thread. */ - set_bit(KTHREAD_IS_PER_CPU, &to_kthread(p)->flags); to_kthread(p)->cpu = cpu; return p; } +EXPORT_SYMBOL(kthread_create_on_cpu); + +void kthread_set_per_cpu(struct task_struct *k, int cpu) +{ + struct kthread *kthread = to_kthread(k); + if (!kthread) + return; + + WARN_ON_ONCE(!(k->flags & PF_NO_SETAFFINITY)); + + if (cpu < 0) { + clear_bit(KTHREAD_IS_PER_CPU, &kthread->flags); + return; + } + + kthread->cpu = cpu; + set_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} + +bool kthread_is_per_cpu(struct task_struct *p) +{ + struct kthread *kthread = __to_kthread(p); + if (!kthread) + return false; + + return test_bit(KTHREAD_IS_PER_CPU, &kthread->flags); +} /** * kthread_unpark - unpark a thread created by kthread_create(). @@ -509,6 +702,8 @@ void kthread_unpark(struct task_struct *k) { struct kthread *kthread = to_kthread(k); + if (!test_bit(KTHREAD_SHOULD_PARK, &kthread->flags)) + return; /* * Newly created kthread was parked when the CPU was offline. * The binding was lost and we need to set it again. @@ -574,7 +769,7 @@ EXPORT_SYMBOL_GPL(kthread_park); * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * - * If threadfn() may call do_exit() itself, the caller must ensure + * If threadfn() may call kthread_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() @@ -591,9 +786,10 @@ int kthread_stop(struct task_struct *k) kthread = to_kthread(k); set_bit(KTHREAD_SHOULD_STOP, &kthread->flags); kthread_unpark(k); + set_tsk_thread_flag(k, TIF_NOTIFY_SIGNAL); wake_up_process(k); wait_for_completion(&kthread->exited); - ret = k->exit_code; + ret = kthread->result; put_task_struct(k); trace_sched_kthread_stop_ret(ret); @@ -601,14 +797,33 @@ int kthread_stop(struct task_struct *k) } EXPORT_SYMBOL(kthread_stop); +/** + * kthread_stop_put - stop a thread and put its task struct + * @k: thread created by kthread_create(). + * + * Stops a thread created by kthread_create() and put its task_struct. + * Only use when holding an extra task struct reference obtained by + * calling get_task_struct(). + */ +int kthread_stop_put(struct task_struct *k) +{ + int ret; + + ret = kthread_stop(k); + put_task_struct(k); + return ret; +} +EXPORT_SYMBOL(kthread_stop_put); + int kthreadd(void *unused) { + static const char comm[TASK_COMM_LEN] = "kthreadd"; struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ - set_task_comm(tsk, "kthreadd"); + set_task_comm(tsk, comm); ignore_signals(tsk); - set_cpus_allowed_ptr(tsk, cpu_all_mask); + set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_TYPE_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; @@ -639,6 +854,92 @@ int kthreadd(void *unused) return 0; } +int kthread_affine_preferred(struct task_struct *p, const struct cpumask *mask) +{ + struct kthread *kthread = to_kthread(p); + cpumask_var_t affinity; + unsigned long flags; + int ret = 0; + + if (!wait_task_inactive(p, TASK_UNINTERRUPTIBLE) || kthread->started) { + WARN_ON(1); + return -EINVAL; + } + + WARN_ON_ONCE(kthread->preferred_affinity); + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return -ENOMEM; + + kthread->preferred_affinity = kzalloc(sizeof(struct cpumask), GFP_KERNEL); + if (!kthread->preferred_affinity) { + ret = -ENOMEM; + goto out; + } + + mutex_lock(&kthreads_hotplug_lock); + cpumask_copy(kthread->preferred_affinity, mask); + WARN_ON_ONCE(!list_empty(&kthread->hotplug_node)); + list_add_tail(&kthread->hotplug_node, &kthreads_hotplug); + kthread_fetch_affinity(kthread, affinity); + + /* It's safe because the task is inactive. */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + do_set_cpus_allowed(p, affinity); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + mutex_unlock(&kthreads_hotplug_lock); +out: + free_cpumask_var(affinity); + + return ret; +} + +/* + * Re-affine kthreads according to their preferences + * and the newly online CPU. The CPU down part is handled + * by select_fallback_rq() which default re-affines to + * housekeepers from other nodes in case the preferred + * affinity doesn't apply anymore. + */ +static int kthreads_online_cpu(unsigned int cpu) +{ + cpumask_var_t affinity; + struct kthread *k; + int ret; + + guard(mutex)(&kthreads_hotplug_lock); + + if (list_empty(&kthreads_hotplug)) + return 0; + + if (!zalloc_cpumask_var(&affinity, GFP_KERNEL)) + return -ENOMEM; + + ret = 0; + + list_for_each_entry(k, &kthreads_hotplug, hotplug_node) { + if (WARN_ON_ONCE((k->task->flags & PF_NO_SETAFFINITY) || + kthread_is_per_cpu(k->task))) { + ret = -EINVAL; + continue; + } + kthread_fetch_affinity(k, affinity); + set_cpus_allowed_ptr(k->task, affinity); + } + + free_cpumask_var(affinity); + + return ret; +} + +static int kthreads_init(void) +{ + return cpuhp_setup_state(CPUHP_AP_KTHREADS_ONLINE, "kthreads:online", + kthreads_online_cpu, NULL); +} +early_initcall(kthreads_init); + void __kthread_init_worker(struct kthread_worker *worker, const char *name, struct lock_class_key *key) @@ -703,10 +1004,25 @@ repeat: raw_spin_unlock_irq(&worker->lock); if (work) { + kthread_work_func_t func = work->func; __set_current_state(TASK_RUNNING); + trace_sched_kthread_work_execute_start(work); work->func(work); - } else if (!freezing(current)) + /* + * Avoid dereferencing work after this point. The trace + * event only cares about the address. + */ + trace_sched_kthread_work_execute_end(work, func); + } else if (!freezing(current)) { schedule(); + } else { + /* + * Handle the case where the current remains + * TASK_INTERRUPTIBLE. try_to_freeze() expects + * the current to be TASK_RUNNING. + */ + __set_current_state(TASK_RUNNING); + } try_to_freeze(); cond_resched(); @@ -715,12 +1031,11 @@ repeat: EXPORT_SYMBOL_GPL(kthread_worker_fn); static __printf(3, 0) struct kthread_worker * -__kthread_create_worker(int cpu, unsigned int flags, - const char namefmt[], va_list args) +__kthread_create_worker_on_node(unsigned int flags, int node, + const char namefmt[], va_list args) { struct kthread_worker *worker; struct task_struct *task; - int node = NUMA_NO_NODE; worker = kzalloc(sizeof(*worker), GFP_KERNEL); if (!worker) @@ -728,20 +1043,14 @@ __kthread_create_worker(int cpu, unsigned int flags, kthread_init_worker(worker); - if (cpu >= 0) - node = cpu_to_node(cpu); - task = __kthread_create_on_node(kthread_worker_fn, worker, - node, namefmt, args); + node, namefmt, args); if (IS_ERR(task)) goto fail_task; - if (cpu >= 0) - kthread_bind(task, cpu); - worker->flags = flags; worker->task = task; - wake_up_process(task); + return worker; fail_task: @@ -750,34 +1059,36 @@ fail_task: } /** - * kthread_create_worker - create a kthread worker + * kthread_create_worker_on_node - create a kthread worker * @flags: flags modifying the default behavior of the worker + * @node: task structure for the thread is allocated on this node * @namefmt: printf-style name for the kthread worker (task). * * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) - * when the worker was SIGKILLed. + * when the caller was killed by a fatal signal. */ struct kthread_worker * -kthread_create_worker(unsigned int flags, const char namefmt[], ...) +kthread_create_worker_on_node(unsigned int flags, int node, const char namefmt[], ...) { struct kthread_worker *worker; va_list args; va_start(args, namefmt); - worker = __kthread_create_worker(-1, flags, namefmt, args); + worker = __kthread_create_worker_on_node(flags, node, namefmt, args); va_end(args); return worker; } -EXPORT_SYMBOL(kthread_create_worker); +EXPORT_SYMBOL(kthread_create_worker_on_node); /** * kthread_create_worker_on_cpu - create a kthread worker and bind it - * it to a given CPU and the associated NUMA node. + * to a given CPU and the associated NUMA node. * @cpu: CPU number * @flags: flags modifying the default behavior of the worker - * @namefmt: printf-style name for the kthread worker (task). + * @namefmt: printf-style name for the thread. Format is restricted + * to "name.*%u". Code fills in cpu number. * * Use a valid CPU number if you want to bind the kthread worker * to the given CPU and the associated NUMA node. @@ -785,20 +1096,37 @@ EXPORT_SYMBOL(kthread_create_worker); * A good practice is to add the cpu number also into the worker name. * For example, use kthread_create_worker_on_cpu(cpu, "helper/%d", cpu). * - * Returns a pointer to the allocated worker on success, ERR_PTR(-ENOMEM) + * CPU hotplug: + * The kthread worker API is simple and generic. It just provides a way + * to create, use, and destroy workers. + * + * It is up to the API user how to handle CPU hotplug. They have to decide + * how to handle pending work items, prevent queuing new ones, and + * restore the functionality when the CPU goes off and on. There are a + * few catches: + * + * - CPU affinity gets lost when it is scheduled on an offline CPU. + * + * - The worker might not exist when the CPU was off when the user + * created the workers. + * + * Good practice is to implement two CPU hotplug callbacks and to + * destroy/create the worker when the CPU goes down/up. + * + * Return: + * The pointer to the allocated worker on success, ERR_PTR(-ENOMEM) * when the needed structures could not get allocated, and ERR_PTR(-EINTR) - * when the worker was SIGKILLed. + * when the caller was killed by a fatal signal. */ struct kthread_worker * kthread_create_worker_on_cpu(int cpu, unsigned int flags, - const char namefmt[], ...) + const char namefmt[]) { struct kthread_worker *worker; - va_list args; - va_start(args, namefmt); - worker = __kthread_create_worker(cpu, flags, namefmt, args); - va_end(args); + worker = kthread_create_worker_on_node(flags, cpu_to_node(cpu), namefmt, cpu); + if (!IS_ERR(worker)) + kthread_bind(worker->task, cpu); return worker; } @@ -833,6 +1161,8 @@ static void kthread_insert_work(struct kthread_worker *worker, { kthread_insert_work_sanity_check(worker, work); + trace_sched_kthread_work_queue_work(worker, work); + list_add_tail(&work->node, pos); work->worker = worker; if (!worker->current_work && likely(worker->task)) @@ -845,7 +1175,7 @@ static void kthread_insert_work(struct kthread_worker *worker, * @work: kthread_work to queue * * Queue @work to work processor @task for async execution. @task - * must have been created with kthread_worker_create(). Returns %true + * must have been created with kthread_create_worker(). Returns %true * if @work was successfully queued, %false if it was already pending. * * Reinitialize the work if it needs to be used by another worker. @@ -896,7 +1226,8 @@ void kthread_delayed_work_timer_fn(struct timer_list *t) /* Move the work from worker->delayed_work_list. */ WARN_ON_ONCE(list_empty(&work->node)); list_del_init(&work->node); - kthread_insert_work(worker, work, &worker->work_list); + if (!work->canceling) + kthread_insert_work(worker, work, &worker->work_list); raw_spin_unlock_irqrestore(&worker->lock, flags); } @@ -1017,8 +1348,38 @@ void kthread_flush_work(struct kthread_work *work) EXPORT_SYMBOL_GPL(kthread_flush_work); /* - * This function removes the work from the worker queue. Also it makes sure - * that it won't get queued later via the delayed work's timer. + * Make sure that the timer is neither set nor running and could + * not manipulate the work list_head any longer. + * + * The function is called under worker->lock. The lock is temporary + * released but the timer can't be set again in the meantime. + */ +static void kthread_cancel_delayed_work_timer(struct kthread_work *work, + unsigned long *flags) +{ + struct kthread_delayed_work *dwork = + container_of(work, struct kthread_delayed_work, work); + struct kthread_worker *worker = work->worker; + + /* + * del_timer_sync() must be called to make sure that the timer + * callback is not running. The lock must be temporary released + * to avoid a deadlock with the callback. In the meantime, + * any queuing is blocked by setting the canceling counter. + */ + work->canceling++; + raw_spin_unlock_irqrestore(&worker->lock, *flags); + del_timer_sync(&dwork->timer); + raw_spin_lock_irqsave(&worker->lock, *flags); + work->canceling--; +} + +/* + * This function removes the work from the worker queue. + * + * It is called under worker->lock. The caller must make sure that + * the timer used by delayed work is not running, e.g. by calling + * kthread_cancel_delayed_work_timer(). * * The work might still be in use when this function finishes. See the * current_work proceed by the worker. @@ -1026,28 +1387,8 @@ EXPORT_SYMBOL_GPL(kthread_flush_work); * Return: %true if @work was pending and successfully canceled, * %false if @work was not pending */ -static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, - unsigned long *flags) +static bool __kthread_cancel_work(struct kthread_work *work) { - /* Try to cancel the timer if exists. */ - if (is_dwork) { - struct kthread_delayed_work *dwork = - container_of(work, struct kthread_delayed_work, work); - struct kthread_worker *worker = work->worker; - - /* - * del_timer_sync() must be called to make sure that the timer - * callback is not running. The lock must be temporary released - * to avoid a deadlock with the callback. In the meantime, - * any queuing is blocked by setting the canceling counter. - */ - work->canceling++; - raw_spin_unlock_irqrestore(&worker->lock, *flags); - del_timer_sync(&dwork->timer); - raw_spin_lock_irqsave(&worker->lock, *flags); - work->canceling--; - } - /* * Try to remove the work from a worker list. It might either * be from worker->work_list or from worker->delayed_work_list. @@ -1070,14 +1411,14 @@ static bool __kthread_cancel_work(struct kthread_work *work, bool is_dwork, * modify @dwork's timer so that it expires after @delay. If @delay is zero, * @work is guaranteed to be queued immediately. * - * Return: %true if @dwork was pending and its timer was modified, - * %false otherwise. + * Return: %false if @dwork was idle and queued, %true otherwise. * * A special case is when the work is being canceled in parallel. * It might be caused either by the real kthread_cancel_delayed_work_sync() * or yet another kthread_mod_delayed_work() call. We let the other command - * win and return %false here. The caller is supposed to synchronize these - * operations a reasonable way. + * win and return %true here. The return value can be used for reference + * counting and the number of queued works stays the same. Anyway, the caller + * is supposed to synchronize these operations a reasonable way. * * This function is safe to call from any context including IRQ handler. * See __kthread_cancel_work() and kthread_delayed_work_timer_fn() @@ -1089,22 +1430,39 @@ bool kthread_mod_delayed_work(struct kthread_worker *worker, { struct kthread_work *work = &dwork->work; unsigned long flags; - int ret = false; + int ret; raw_spin_lock_irqsave(&worker->lock, flags); /* Do not bother with canceling when never queued. */ - if (!work->worker) + if (!work->worker) { + ret = false; goto fast_queue; + } /* Work must not be used with >1 worker, see kthread_queue_work() */ WARN_ON_ONCE(work->worker != worker); - /* Do not fight with another command that is canceling this work. */ - if (work->canceling) + /* + * Temporary cancel the work but do not fight with another command + * that is canceling the work as well. + * + * It is a bit tricky because of possible races with another + * mod_delayed_work() and cancel_delayed_work() callers. + * + * The timer must be canceled first because worker->lock is released + * when doing so. But the work can be removed from the queue (list) + * only when it can be queued again so that the return value can + * be used for reference counting. + */ + kthread_cancel_delayed_work_timer(work, &flags); + if (work->canceling) { + /* The number of works in the queue does not change. */ + ret = true; goto out; + } + ret = __kthread_cancel_work(work); - ret = __kthread_cancel_work(work, true, &flags); fast_queue: __kthread_queue_delayed_work(worker, dwork, delay); out: @@ -1126,7 +1484,10 @@ static bool __kthread_cancel_work_sync(struct kthread_work *work, bool is_dwork) /* Work must not be used with >1 worker, see kthread_queue_work(). */ WARN_ON_ONCE(work->worker != worker); - ret = __kthread_cancel_work(work, is_dwork, &flags); + if (is_dwork) + kthread_cancel_delayed_work_timer(work, &flags); + + ret = __kthread_cancel_work(work); if (worker->current_work != work) goto out_fast; @@ -1210,6 +1571,10 @@ EXPORT_SYMBOL_GPL(kthread_flush_worker); * Flush and destroy @worker. The simple flush is enough because the kthread * worker API is used only in trivial scenarios. There are no multi-step state * machines needed. + * + * Note that this function is not responsible for handling delayed work, so + * caller should be responsible for queuing or canceling all delayed work items + * before invoke this function. */ void kthread_destroy_worker(struct kthread_worker *worker) { @@ -1221,6 +1586,7 @@ void kthread_destroy_worker(struct kthread_worker *worker) kthread_flush_worker(worker); kthread_stop(task); + WARN_ON(!list_empty(&worker->delayed_work_list)); WARN_ON(!list_empty(&worker->work_list)); kfree(worker); } @@ -1238,24 +1604,37 @@ void kthread_use_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(tsk->mm); + /* + * It is possible for mm to be the same as tsk->active_mm, but + * we must still mmgrab(mm) and mmdrop_lazy_tlb(active_mm), + * because these references are not equivalent. + */ + mmgrab(mm); + task_lock(tsk); + /* Hold off tlb flush IPIs while switching mm's */ + local_irq_disable(); active_mm = tsk->active_mm; - if (active_mm != mm) { - mmgrab(mm); - tsk->active_mm = mm; - } + tsk->active_mm = mm; tsk->mm = mm; - switch_mm(active_mm, mm, tsk); + membarrier_update_current_mm(mm); + switch_mm_irqs_off(active_mm, mm, tsk); + local_irq_enable(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); #endif - if (active_mm != mm) - mmdrop(active_mm); - - to_kthread(tsk)->oldfs = get_fs(); - set_fs(USER_DS); + /* + * When a kthread starts operating on an address space, the loop + * in membarrier_{private,global}_expedited() may not observe + * that tsk->mm, and not issue an IPI. Membarrier requires a + * memory barrier after storing to tsk->mm, before accessing + * user-space memory. A full memory barrier for membarrier + * {PRIVATE,GLOBAL}_EXPEDITED is implicitly provided by + * mmdrop_lazy_tlb(). + */ + mmdrop_lazy_tlb(active_mm); } EXPORT_SYMBOL_GPL(kthread_use_mm); @@ -1270,14 +1649,25 @@ void kthread_unuse_mm(struct mm_struct *mm) WARN_ON_ONCE(!(tsk->flags & PF_KTHREAD)); WARN_ON_ONCE(!tsk->mm); - set_fs(to_kthread(tsk)->oldfs); - task_lock(tsk); - sync_mm_rss(mm); + /* + * When a kthread stops operating on an address space, the loop + * in membarrier_{private,global}_expedited() may not observe + * that tsk->mm, and not issue an IPI. Membarrier requires a + * memory barrier after accessing user-space memory, before + * clearing tsk->mm. + */ + smp_mb__after_spinlock(); + local_irq_disable(); tsk->mm = NULL; + membarrier_update_current_mm(NULL); + mmgrab_lazy_tlb(mm); /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); + local_irq_enable(); task_unlock(tsk); + + mmdrop(mm); } EXPORT_SYMBOL_GPL(kthread_unuse_mm); @@ -1329,5 +1719,4 @@ struct cgroup_subsys_state *kthread_blkcg(void) } return NULL; } -EXPORT_SYMBOL(kthread_blkcg); #endif |