/* * Pushes a -rtws task to the latest rq if its currently executing task has lower priority. * Only remote rqs are consider here. */ static int push_latest_rtws(struct rq *this_rq, struct task_struct *p, int target_cpu) { struct rq *target_rq; int ret = 0; target_rq = cpu_rq(target_cpu); /* We might release rq lock */ get_task_struct(p); printk(KERN_INFO "check preempting other %llu - %llu\n", p->rtws.job.deadline, target_rq->rtws.earliest_dl); double_lock_balance(this_rq, target_rq); /* TODO check if in the meanwhile a task was dispatched to here */ if (target_rq->rtws.nr_running && !time_before_rtws(p->rtws.job.deadline, target_rq->rtws.earliest_dl)) goto unlock; set_task_cpu(p, target_cpu); activate_task(target_rq, p, ENQUEUE_HEAD); ret = 1; resched_task(target_rq->curr); unlock: double_unlock_balance(this_rq, target_rq); put_task_struct(p); return ret; }
void kthread_bind(struct task_struct *k, unsigned int cpu) { BUG_ON(k->state != TASK_INTERRUPTIBLE); /* Must have done schedule() in kthread() before we set_task_cpu */ wait_task_inactive(k); set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); }
/* * Tries to push a -rtws task to a "random" idle rq. */ static int push_idle_rtws(struct rq *this_rq, struct task_struct *p) { struct rq *target_rq; int ret = 0, target_cpu; struct cpudl *cp = &this_rq->rd->rtwsc_cpudl; retry: target_cpu = find_idle_cpu_rtws(cp); if (target_cpu == -1) return 0; printk(KERN_INFO "idle cpu %d\n", target_cpu); target_rq = cpu_rq(target_cpu); /* We might release rq lock */ get_task_struct(p); double_lock_balance(this_rq, target_rq); if (unlikely(target_rq->rtws.nr_running)) { double_unlock_balance(this_rq, target_rq); put_task_struct(p); target_rq = NULL; goto retry; } set_task_cpu(p, target_cpu); activate_task(target_rq, p, 0); ret = 1; resched_task(target_rq->curr); double_unlock_balance(this_rq, target_rq); put_task_struct(p); return ret; }
static int pull_task_rtws(struct rq *this_rq) { struct task_struct *p; struct sched_rtws_entity *rtws_se; struct global_rq *global_rq = this_rq->rtws.global_rq; int ret = 0; if (!global_rq->nr_running) return 0; rtws_se = __pick_next_task_rtws(global_rq); if (unlikely(!rtws_se)) return 0; p = task_of_rtws_se(rtws_se); WARN_ON(!rtws_task(p)); printk(KERN_INFO "= task %d stolen %d PULLED by cpu %d\n", p->pid, rtws_se->stolen, this_rq->cpu); /* * We tranfer the task from global rq to this rq */ __dequeue_task_rtws(global_rq, rtws_se); if (rtws_se->stolen == this_rq->cpu) rtws_se->stolen = -1; set_task_cpu(p, this_rq->cpu); activate_task(this_rq, p, ENQUEUE_HEAD); ret = 1; this_rq->rtws.tot_pulls++; return ret; }
/* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static task_t *copy_process(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *parent_tidptr, int __user *child_tidptr, int pid) { int retval; struct task_struct *p = NULL; if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); retval = security_task_create(clone_flags); if (retval) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current); if (!p) goto fork_out; retval = -EAGAIN; if (atomic_read(&p->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && p->user != &root_user) goto bad_fork_free; } atomic_inc(&p->user->__count); atomic_inc(&p->user->processes); get_group_info(p->group_info); /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ if (nr_threads >= max_threads) goto bad_fork_cleanup_count; if (!try_module_get(p->thread_info->exec_domain->module)) goto bad_fork_cleanup_count; if (p->binfmt && !try_module_get(p->binfmt->module)) goto bad_fork_cleanup_put_domain; p->did_exec = 0; copy_flags(clone_flags, p); p->pid = pid; retval = -EFAULT; if (clone_flags & CLONE_PARENT_SETTID) if (put_user(p->pid, parent_tidptr)) goto bad_fork_cleanup; p->proc_dentry = NULL; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); spin_lock_init(&p->proc_lock); clear_tsk_thread_flag(p, TIF_SIGPENDING); init_sigpending(&p->pending); p->it_real_value = 0; p->it_real_incr = 0; p->it_virt_value = cputime_zero; p->it_virt_incr = cputime_zero; p->it_prof_value = cputime_zero; p->it_prof_incr = cputime_zero; init_timer(&p->real_timer); p->real_timer.data = (unsigned long) p; p->utime = cputime_zero; p->stime = cputime_zero; p->rchar = 0; /* I/O counter: bytes read */ p->wchar = 0; /* I/O counter: bytes written */ p->syscr = 0; /* I/O counter: read syscalls */ p->syscw = 0; /* I/O counter: write syscalls */ acct_clear_integrals(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); p->security = NULL; p->io_context = NULL; p->io_wait = NULL; p->audit_context = NULL; #ifdef CONFIG_NUMA p->mempolicy = mpol_copy(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup; } #endif p->tgid = p->pid; if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; if ((retval = security_task_alloc(p))) goto bad_fork_cleanup_policy; if ((retval = audit_alloc(p))) goto bad_fork_cleanup_security; /* copy all the process information */ if ((retval = copy_semundo(clone_flags, p))) goto bad_fork_cleanup_audit; if ((retval = copy_files(clone_flags, p))) goto bad_fork_cleanup_semundo; if ((retval = copy_fs(clone_flags, p))) goto bad_fork_cleanup_files; if ((retval = copy_sighand(clone_flags, p))) goto bad_fork_cleanup_fs; if ((retval = copy_signal(clone_flags, p))) goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p))) goto bad_fork_cleanup_signal; if ((retval = copy_keys(clone_flags, p))) goto bad_fork_cleanup_mm; if ((retval = copy_namespace(clone_flags, p))) goto bad_fork_cleanup_keys; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); if (retval) goto bad_fork_cleanup_namespace; p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; /* * Syscall tracing should be turned off in the child regardless * of CLONE_PTRACE. */ clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); /* Our parent execution domain becomes current domain These must match for thread signalling to apply */ p->parent_exec_id = p->self_exec_id; /* ok, now we should be set up.. */ p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); p->pdeath_signal = 0; p->exit_state = 0; /* Perform scheduler related setup */ sched_fork(p); /* * Ok, make it visible to the rest of the system. * We dont wake it up yet. */ p->group_leader = p; INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* * The task hasn't been attached yet, so cpus_allowed mask cannot * have changed. The cpus_allowed mask of the parent may have * changed after it was copied first time, and it may then move to * another CPU - so we re-copy it here and set the child's CPU to * the parent's CPU. This avoids alot of nasty races. */ p->cpus_allowed = current->cpus_allowed; set_task_cpu(p, smp_processor_id()); /* * Check for pending SIGKILL! The new thread should not be allowed * to slip out of an OOM kill. (or normal SIGKILL.) */ if (sigismember(¤t->pending.signal, SIGKILL)) { write_unlock_irq(&tasklist_lock); retval = -EINTR; goto bad_fork_cleanup_namespace; } /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) p->real_parent = current->real_parent; else p->real_parent = current; p->parent = p->real_parent; if (clone_flags & CLONE_THREAD) { spin_lock(¤t->sighand->siglock); /* * Important: if an exit-all has been started then * do not create this new thread - the whole thread * group is supposed to exit anyway. */ if (current->signal->flags & SIGNAL_GROUP_EXIT) { spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -EAGAIN; goto bad_fork_cleanup_namespace; } p->group_leader = current->group_leader; if (current->signal->group_stop_count > 0) { /* * There is an all-stop in progress for the group. * We ourselves will stop as soon as we check signals. * Make the new thread part of that group stop too. */ current->signal->group_stop_count++; set_tsk_thread_flag(p, TIF_SIGPENDING); } spin_unlock(¤t->sighand->siglock); } SET_LINKS(p); if (unlikely(p->ptrace & PT_PTRACED)) __ptrace_link(p, current->parent); attach_pid(p, PIDTYPE_PID, p->pid); attach_pid(p, PIDTYPE_TGID, p->tgid); if (thread_group_leader(p)) { attach_pid(p, PIDTYPE_PGID, process_group(p)); attach_pid(p, PIDTYPE_SID, p->signal->session); if (p->pid) __get_cpu_var(process_counts)++; } nr_threads++; total_forks++; write_unlock_irq(&tasklist_lock); retval = 0; fork_out: if (retval) return ERR_PTR(retval); return p; bad_fork_cleanup_namespace: exit_namespace(p); bad_fork_cleanup_keys: exit_keys(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: exit_signal(p); bad_fork_cleanup_sighand: exit_sighand(p); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_free(p->mempolicy); #endif bad_fork_cleanup: if (p->binfmt) module_put(p->binfmt->module); bad_fork_cleanup_put_domain: module_put(p->thread_info->exec_domain->module); bad_fork_cleanup_count: put_group_info(p->group_info); atomic_dec(&p->user->processes); free_uid(p->user); bad_fork_free: free_task(p); goto fork_out; }
/* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static struct task_struct *copy_process(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *child_tidptr, struct pid *pid, int trace) { int retval; struct task_struct *p; int cgroup_callbacks_done = 0; if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); /* * Siblings of global init remain as zombies on exit since they are * not reaped by their parent (swapper). To solve this and to avoid * multi-rooted process trees, prevent global and container-inits * from creating siblings. */ if ((clone_flags & CLONE_PARENT) && current->signal->flags & SIGNAL_UNKILLABLE) return ERR_PTR(-EINVAL); retval = security_task_create(clone_flags); if (retval) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current); if (!p) goto fork_out; ftrace_graph_init_task(p); rt_mutex_init_task(p); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; if (atomic_read(&p->real_cred->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && p->real_cred->user != INIT_USER) goto bad_fork_free; } retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; #ifdef CONFIG_SECURITY_ANOUBIS anoubis_task_create(p); #endif /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ retval = -EAGAIN; if (nr_threads >= max_threads) goto bad_fork_cleanup_count; if (!try_module_get(task_thread_info(p)->exec_domain->module)) goto bad_fork_cleanup_count; p->did_exec = 0; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ copy_flags(clone_flags, p); INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); rcu_copy_process(p); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); init_sigpending(&p->pending); p->utime = cputime_zero; p->stime = cputime_zero; p->gtime = cputime_zero; p->utimescaled = cputime_zero; p->stimescaled = cputime_zero; p->prev_utime = cputime_zero; p->prev_stime = cputime_zero; p->default_timer_slack_ns = current->timer_slack_ns; task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cpu_timers_init(p); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); p->io_context = NULL; p->audit_context = NULL; cgroup_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_dup(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_cgroup; } mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW p->hardirqs_enabled = 1; #else p->hardirqs_enabled = 0; #endif p->hardirq_enable_ip = 0; p->hardirq_enable_event = 0; p->hardirq_disable_ip = _THIS_IP_; p->hardirq_disable_event = 0; p->softirqs_enabled = 1; p->softirq_enable_ip = _THIS_IP_; p->softirq_enable_event = 0; p->softirq_disable_ip = 0; p->softirq_disable_event = 0; p->hardirq_context = 0; p->softirq_context = 0; #endif #ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; p->lockdep_recursion = 0; #endif #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif p->bts = NULL; p->stack_start = stack_start; /* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); retval = perf_event_init_task(p); if (retval) goto bad_fork_cleanup_policy; if ((retval = audit_alloc(p))) goto bad_fork_cleanup_policy; /* copy all the process information */ if ((retval = copy_semundo(clone_flags, p))) goto bad_fork_cleanup_audit; if ((retval = copy_files(clone_flags, p))) goto bad_fork_cleanup_semundo; if ((retval = copy_fs(clone_flags, p))) goto bad_fork_cleanup_files; if ((retval = copy_sighand(clone_flags, p))) goto bad_fork_cleanup_fs; if ((retval = copy_signal(clone_flags, p))) goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p))) goto bad_fork_cleanup_signal; if ((retval = copy_namespaces(clone_flags, p))) goto bad_fork_cleanup_mm; if ((retval = copy_io(clone_flags, p))) goto bad_fork_cleanup_namespaces; retval = copy_thread(clone_flags, stack_start, stack_size, p, regs); if (retval) goto bad_fork_cleanup_io; if (pid != &init_struct_pid) { retval = -ENOMEM; pid = alloc_pid(p->nsproxy->pid_ns); if (!pid) goto bad_fork_cleanup_io; if (clone_flags & CLONE_NEWPID) { retval = pid_ns_prepare_proc(p->nsproxy->pid_ns); if (retval < 0) goto bad_fork_free_pid; } } p->pid = pid_nr(pid); p->tgid = p->pid; if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; if (current->nsproxy != p->nsproxy) { retval = ns_cgroup_clone(p, pid); if (retval) goto bad_fork_free_pid; } p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; #ifdef CONFIG_FUTEX p->robust_list = NULL; #ifdef CONFIG_COMPAT p->compat_robust_list = NULL; #endif INIT_LIST_HEAD(&p->pi_state_list); p->pi_state_cache = NULL; #endif /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) p->sas_ss_sp = p->sas_ss_size = 0; /* * Syscall tracing should be turned off in the child regardless * of CLONE_PTRACE. */ clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(p, TIF_SYSCALL_EMU); #endif clear_all_latency_tracing(p); /* ok, now we should be set up.. */ p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); p->pdeath_signal = 0; p->exit_state = 0; /* * Ok, make it visible to the rest of the system. * We dont wake it up yet. */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); /* Now that the task is set up, run cgroup callbacks if * necessary. We need to run them before the task is visible * on the tasklist. */ cgroup_fork_callbacks(p); cgroup_callbacks_done = 1; /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* * The task hasn't been attached yet, so its cpus_allowed mask will * not be changed, nor will its assigned CPU. * * The cpus_allowed mask of the parent may have changed after it was * copied first time - so re-copy it here, then check the child's CPU * to ensure it is on a valid CPU (and if not, just force it back to * parent's CPU). This avoids alot of nasty races. */ p->cpus_allowed = current->cpus_allowed; p->rt.nr_cpus_allowed = current->rt.nr_cpus_allowed; if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) || !cpu_online(task_cpu(p)))) set_task_cpu(p, smp_processor_id()); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) { p->real_parent = current->real_parent; p->parent_exec_id = current->parent_exec_id; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; } spin_lock(¤t->sighand->siglock); /* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the * fork. Restart if a signal comes in before we add the new process to * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). */ recalc_sigpending(); if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_free_pid; } if (clone_flags & CLONE_THREAD) { atomic_inc(¤t->signal->count); atomic_inc(¤t->signal->live); p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); } if (likely(p->pid)) { list_add_tail(&p->sibling, &p->real_parent->children); tracehook_finish_clone(p, clone_flags, trace); if (thread_group_leader(p)) { if (clone_flags & CLONE_NEWPID) p->nsproxy->pid_ns->child_reaper = p; p->signal->leader_pid = pid; tty_kref_put(p->signal->tty); p->signal->tty = tty_kref_get(current->signal->tty); attach_pid(p, PIDTYPE_PGID, task_pgrp(current)); attach_pid(p, PIDTYPE_SID, task_session(current)); list_add_tail_rcu(&p->tasks, &init_task.tasks); __get_cpu_var(process_counts)++; } attach_pid(p, PIDTYPE_PID, pid); nr_threads++; } total_forks++; spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); proc_fork_connector(p); cgroup_post_fork(p); perf_event_fork(p); return p; bad_fork_free_pid: if (pid != &init_struct_pid) free_pid(pid); bad_fork_cleanup_io: put_io_context(p->io_context); bad_fork_cleanup_namespaces: exit_task_namespaces(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: if (!(clone_flags & CLONE_THREAD)) __cleanup_signal(p->signal); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_policy: perf_event_free_task(p); #ifdef CONFIG_NUMA mpol_put(p->mempolicy); bad_fork_cleanup_cgroup: #endif cgroup_exit(p, cgroup_callbacks_done); delayacct_tsk_free(p); module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: atomic_dec(&p->cred->user->processes); anoubis_task_destroy(p); exit_creds(p); bad_fork_free: free_task(p); fork_out: return ERR_PTR(retval); }
static int steal_pjob_rtws(struct rq *this_rq) { int ret = 0, this_cpu = this_rq->cpu, target_cpu; struct task_struct *p; struct rq *target_rq; struct global_rq *global_rq = this_rq->rtws.global_rq; if (global_rq->random) { /* * Pseudo random selection of our victim rq, * among rqs with to-be-stolen pjobs, that's it. */ target_cpu = find_random_stealable_cpu_rtws(&this_rq->rd->rtwss_cpudl, this_rq->cpu); } else { /* * When not in random mode, we gotta find the rq with the earliest * deadline stealable pjob. */ target_cpu = find_earliest_stealable_cpu_rtws(&this_rq->rd->rtwss_cpudl); } if (target_cpu == -1) return 0; printk(KERN_INFO "stealable cpu %d\n", target_cpu); target_rq = cpu_rq(target_cpu); /* * We can potentially drop this_rq's lock in * double_lock_balance, and another CPU could alter this_rq */ double_lock_balance(this_rq, target_rq); if (unlikely(target_rq->rtws.nr_running <= 1)) goto unlock; if (unlikely(this_rq->rtws.nr_running)) goto unlock; p = pick_next_stealable_pjob_rtws(&target_rq->rtws); if (p) { WARN_ON(p == target_rq->curr); WARN_ON(!p->se.on_rq); WARN_ON(!rtws_task(p)); deactivate_task(target_rq, p, 0); p->rtws.stolen = target_cpu; set_task_cpu(p, this_cpu); activate_task(this_rq, p, 0); this_rq->rtws.tot_steals++; printk(KERN_INFO "=task %d STOLEN by cpu %d from cpu %d!\n", p->pid, this_cpu, target_cpu); ret = 1; } unlock: double_unlock_balance(this_rq, target_rq); return ret; }
static void create_kthread(struct kthread_create_info *create) { int pid; /* We want our own signal handler (we take no signals by default). */ pid = kernel_thread(kthread, create, CLONE_FS | CLONE_FILES | SIGCHLD); if (pid < 0) { create->result = ERR_PTR(pid); } else { struct sched_param param = { .sched_priority = 0 }; wait_for_completion(&create->started); read_lock(&tasklist_lock); create->result = find_task_by_pid_ns(pid, &init_pid_ns); read_unlock(&tasklist_lock); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. */ sched_setscheduler(create->result, SCHED_NORMAL, ¶m); set_user_nice(create->result, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(create->result, CPU_MASK_ALL_PTR); } complete(&create->done); } /** * kthread_create - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(), kthread_create_on_cpu(). * * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a * standalone thread for which noone 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 * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM). */ struct task_struct *kthread_create(int (*threadfn)(void *data), void *data, const char namefmt[], ...) { struct kthread_create_info create; create.threadfn = threadfn; create.data = data; init_completion(&create.started); init_completion(&create.done); spin_lock(&kthread_create_lock); list_add_tail(&create.list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); wait_for_completion(&create.done); if (!IS_ERR(create.result)) { va_list args; va_start(args, namefmt); vsnprintf(create.result->comm, sizeof(create.result->comm), namefmt, args); va_end(args); } return create.result; } EXPORT_SYMBOL(kthread_create); /** * kthread_bind - bind a just-created kthread to a cpu. * @k: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *k, unsigned int cpu) { if (k->state != TASK_UNINTERRUPTIBLE) { WARN_ON(1); return; } /* Must have done schedule() in kthread() before we set_task_cpu */ wait_task_inactive(k, 0); set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); k->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. Your threadfn() must not call do_exit() * itself if you use this function! This can also be called after * kthread_create() instead of calling wake_up_process(): the thread * will exit without calling threadfn(). * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { int ret; mutex_lock(&kthread_stop_lock); /* It could exit after stop_info.k set, but before wake_up_process. */ get_task_struct(k); /* Must init completion *before* thread sees kthread_stop_info.k */ init_completion(&kthread_stop_info.done); smp_wmb(); /* Now set kthread_should_stop() to true, and wake it up. */ kthread_stop_info.k = k; wake_up_process(k); /* Once it dies, reset stop ptr, gather result and we're done. */ wait_for_completion(&kthread_stop_info.done); kthread_stop_info.k = NULL; ret = kthread_stop_info.err; put_task_struct(k); mutex_unlock(&kthread_stop_lock); return ret; }
/* * This creates a new process as a copy of the old one, * but does not actually start it yet. * * It copies the registers, and all the appropriate * parts of the process environment (as per the clone * flags). The actual kick-off is left to the caller. */ static struct task_struct *copy_process(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *parent_tidptr, int __user *child_tidptr, int pid) { int retval; struct task_struct *p = NULL; if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); /* * Thread groups must share signals as well, and detached threads * can only be started up within the thread group. */ if ((clone_flags & CLONE_THREAD) && !(clone_flags & CLONE_SIGHAND)) return ERR_PTR(-EINVAL); /* * Shared signal handlers imply shared VM. By way of the above, * thread groups also imply shared VM. Blocking this case allows * for various simplifications in other code. */ if ((clone_flags & CLONE_SIGHAND) && !(clone_flags & CLONE_VM)) return ERR_PTR(-EINVAL); retval = security_task_create(clone_flags); if (retval) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current); if (!p) goto fork_out; #ifdef CONFIG_TRACE_IRQFLAGS DEBUG_LOCKS_WARN_ON(!p->hardirqs_enabled); DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; if (atomic_read(&p->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && p->user != &root_user) goto bad_fork_free; } atomic_inc(&p->user->__count); atomic_inc(&p->user->processes); get_group_info(p->group_info); /* * If multiple threads are within copy_process(), then this check * triggers too late. This doesn't hurt, the check is only there * to stop root fork bombs. */ if (nr_threads >= max_threads) goto bad_fork_cleanup_count; if (!try_module_get(task_thread_info(p)->exec_domain->module)) goto bad_fork_cleanup_count; if (p->binfmt && !try_module_get(p->binfmt->module)) goto bad_fork_cleanup_put_domain; p->did_exec = 0; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ copy_flags(clone_flags, p); p->pid = pid; retval = -EFAULT; if (clone_flags & CLONE_PARENT_SETTID) if (put_user(p->pid, parent_tidptr)) goto bad_fork_cleanup_delays_binfmt; INIT_LIST_HEAD(&p->children); INIT_LIST_HEAD(&p->sibling); p->vfork_done = NULL; spin_lock_init(&p->alloc_lock); clear_tsk_thread_flag(p, TIF_SIGPENDING); init_sigpending(&p->pending); p->utime = cputime_zero; p->stime = cputime_zero; p->sched_time = 0; p->rchar = 0; /* I/O counter: bytes read */ p->wchar = 0; /* I/O counter: bytes written */ p->syscr = 0; /* I/O counter: read syscalls */ p->syscw = 0; /* I/O counter: write syscalls */ acct_clear_integrals(p); p->it_virt_expires = cputime_zero; p->it_prof_expires = cputime_zero; p->it_sched_expires = 0; INIT_LIST_HEAD(&p->cpu_timers[0]); INIT_LIST_HEAD(&p->cpu_timers[1]); INIT_LIST_HEAD(&p->cpu_timers[2]); p->lock_depth = -1; /* -1 = no lock */ do_posix_clock_monotonic_gettime(&p->start_time); p->security = NULL; p->io_context = NULL; p->io_wait = NULL; p->audit_context = NULL; cpuset_fork(p); #ifdef CONFIG_NUMA p->mempolicy = mpol_copy(p->mempolicy); if (IS_ERR(p->mempolicy)) { retval = PTR_ERR(p->mempolicy); p->mempolicy = NULL; goto bad_fork_cleanup_cpuset; } mpol_fix_fork_child_flag(p); #endif #ifdef CONFIG_TRACE_IRQFLAGS p->irq_events = 0; p->hardirqs_enabled = 0; p->hardirq_enable_ip = 0; p->hardirq_enable_event = 0; p->hardirq_disable_ip = _THIS_IP_; p->hardirq_disable_event = 0; p->softirqs_enabled = 1; p->softirq_enable_ip = _THIS_IP_; p->softirq_enable_event = 0; p->softirq_disable_ip = 0; p->softirq_disable_event = 0; p->hardirq_context = 0; p->softirq_context = 0; #endif #ifdef CONFIG_LOCKDEP p->lockdep_depth = 0; /* no locks held yet */ p->curr_chain_key = 0; p->lockdep_recursion = 0; #endif rt_mutex_init_task(p); #ifdef CONFIG_DEBUG_MUTEXES p->blocked_on = NULL; /* not blocked yet */ #endif p->tgid = p->pid; if (clone_flags & CLONE_THREAD) p->tgid = current->tgid; if ((retval = security_task_alloc(p))) goto bad_fork_cleanup_policy; if ((retval = audit_alloc(p))) goto bad_fork_cleanup_security; /* copy all the process information */ if ((retval = copy_semundo(clone_flags, p))) goto bad_fork_cleanup_audit; if ((retval = copy_files(clone_flags, p))) goto bad_fork_cleanup_semundo; if ((retval = copy_fs(clone_flags, p))) goto bad_fork_cleanup_files; if ((retval = copy_sighand(clone_flags, p))) goto bad_fork_cleanup_fs; if ((retval = copy_signal(clone_flags, p))) goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p))) goto bad_fork_cleanup_signal; if ((retval = copy_keys(clone_flags, p))) goto bad_fork_cleanup_mm; if ((retval = copy_namespace(clone_flags, p))) goto bad_fork_cleanup_keys; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); if (retval) goto bad_fork_cleanup_namespace; p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? child_tidptr : NULL; /* * Clear TID on mm_release()? */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? child_tidptr: NULL; p->robust_list = NULL; #ifdef CONFIG_COMPAT p->compat_robust_list = NULL; #endif INIT_LIST_HEAD(&p->pi_state_list); p->pi_state_cache = NULL; /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) p->sas_ss_sp = p->sas_ss_size = 0; /* * Syscall tracing should be turned off in the child regardless * of CLONE_PTRACE. */ clear_tsk_thread_flag(p, TIF_SYSCALL_TRACE); #ifdef TIF_SYSCALL_EMU clear_tsk_thread_flag(p, TIF_SYSCALL_EMU); #endif /* Our parent execution domain becomes current domain These must match for thread signalling to apply */ p->parent_exec_id = p->self_exec_id; /* ok, now we should be set up.. */ p->exit_signal = (clone_flags & CLONE_THREAD) ? -1 : (clone_flags & CSIGNAL); p->pdeath_signal = 0; p->exit_state = 0; /* * Ok, make it visible to the rest of the system. * We dont wake it up yet. */ p->group_leader = p; INIT_LIST_HEAD(&p->thread_group); INIT_LIST_HEAD(&p->ptrace_children); INIT_LIST_HEAD(&p->ptrace_list); /* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); /* Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* * The task hasn't been attached yet, so its cpus_allowed mask will * not be changed, nor will its assigned CPU. * * The cpus_allowed mask of the parent may have changed after it was * copied first time - so re-copy it here, then check the child's CPU * to ensure it is on a valid CPU (and if not, just force it back to * parent's CPU). This avoids alot of nasty races. */ p->cpus_allowed = current->cpus_allowed; if (unlikely(!cpu_isset(task_cpu(p), p->cpus_allowed) || !cpu_online(task_cpu(p)))) set_task_cpu(p, smp_processor_id()); /* CLONE_PARENT re-uses the old parent */ if (clone_flags & (CLONE_PARENT|CLONE_THREAD)) p->real_parent = current->real_parent; else p->real_parent = current; p->parent = p->real_parent; spin_lock(¤t->sighand->siglock); /* * Process group and session signals need to be delivered to just the * parent before the fork or both the parent and the child after the * fork. Restart if a signal comes in before we add the new process to * it's process group. * A fatal signal pending means that current will exit, so the new * thread can't slip out of an OOM kill (or normal SIGKILL). */ recalc_sigpending(); if (signal_pending(current)) { spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); retval = -ERESTARTNOINTR; goto bad_fork_cleanup_namespace; } if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; list_add_tail_rcu(&p->thread_group, &p->group_leader->thread_group); if (!cputime_eq(current->signal->it_virt_expires, cputime_zero) || !cputime_eq(current->signal->it_prof_expires, cputime_zero) || current->signal->rlim[RLIMIT_CPU].rlim_cur != RLIM_INFINITY || !list_empty(¤t->signal->cpu_timers[0]) || !list_empty(¤t->signal->cpu_timers[1]) || !list_empty(¤t->signal->cpu_timers[2])) { /* * Have child wake up on its first tick to check * for process CPU timers. */ p->it_prof_expires = jiffies_to_cputime(1); } } /* * inherit ioprio */ p->ioprio = current->ioprio; if (likely(p->pid)) { add_parent(p); if (unlikely(p->ptrace & PT_PTRACED)) __ptrace_link(p, current->parent); if (thread_group_leader(p)) { p->signal->tty = current->signal->tty; p->signal->pgrp = process_group(current); p->signal->session = current->signal->session; attach_pid(p, PIDTYPE_PGID, process_group(p)); attach_pid(p, PIDTYPE_SID, p->signal->session); list_add_tail_rcu(&p->tasks, &init_task.tasks); __get_cpu_var(process_counts)++; } attach_pid(p, PIDTYPE_PID, p->pid); nr_threads++; } total_forks++; spin_unlock(¤t->sighand->siglock); write_unlock_irq(&tasklist_lock); proc_fork_connector(p); return p; bad_fork_cleanup_namespace: exit_namespace(p); bad_fork_cleanup_keys: exit_keys(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); bad_fork_cleanup_signal: cleanup_signal(p); bad_fork_cleanup_sighand: __cleanup_sighand(p->sighand); bad_fork_cleanup_fs: exit_fs(p); /* blocking */ bad_fork_cleanup_files: exit_files(p); /* blocking */ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); bad_fork_cleanup_security: security_task_free(p); bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_free(p->mempolicy); bad_fork_cleanup_cpuset: #endif cpuset_exit(p); bad_fork_cleanup_delays_binfmt: delayacct_tsk_free(p); if (p->binfmt) module_put(p->binfmt->module); bad_fork_cleanup_put_domain: module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: put_group_info(p->group_info); atomic_dec(&p->user->processes); free_uid(p->user); bad_fork_free: free_task(p); fork_out: return ERR_PTR(retval); }
/** * kthread_create - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(), kthread_create_on_cpu(). * * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a * standalone thread for which noone 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 * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM). */ struct task_struct *kthread_create(int (*threadfn)(void *data), void *data, const char namefmt[], ...) { struct kthread_create_info create; create.threadfn = threadfn; create.data = data; init_completion(&create.started); init_completion(&create.done); spin_lock(&kthread_create_lock); list_add_tail(&create.list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); wait_for_completion(&create.done); if (!IS_ERR(create.result)) { struct sched_param param = { .sched_priority = 0 }; va_list args; va_start(args, namefmt); vsnprintf(create.result->comm, sizeof(create.result->comm), namefmt, args); va_end(args); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. */ sched_setscheduler_nocheck(create.result, SCHED_NORMAL, ¶m); set_user_nice(create.result, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(create.result, cpu_all_mask); } return create.result; } EXPORT_SYMBOL(kthread_create); /** * kthread_bind - bind a just-created kthread to a cpu. * @k: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *k, unsigned int cpu) { /* Must have done schedule() in kthread() before we set_task_cpu */ if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) { WARN_ON(1); return; } set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); k->rt.nr_cpus_allowed = 1; k->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. Your threadfn() must not call do_exit() * itself if you use this function! This can also be called after * kthread_create() instead of calling wake_up_process(): the thread * will exit without calling threadfn(). * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { int ret; mutex_lock(&kthread_stop_lock); /* It could exit after stop_info.k set, but before wake_up_process. */ get_task_struct(k); trace_sched_kthread_stop(k); /* Must init completion *before* thread sees kthread_stop_info.k */ init_completion(&kthread_stop_info.done); smp_wmb(); /* Now set kthread_should_stop() to true, and wake it up. */ kthread_stop_info.k = k; wake_up_process(k); put_task_struct(k); /* Once it dies, reset stop ptr, gather result and we're done. */ wait_for_completion(&kthread_stop_info.done); kthread_stop_info.k = NULL; ret = kthread_stop_info.err; mutex_unlock(&kthread_stop_lock); trace_sched_kthread_stop_ret(ret); return ret; }
/* * Ok, this is the main fork-routine. * * It copies the process, and if successful kick-starts * it and waits for it to finish using the VM if required. */ long do_fork(unsigned long clone_flags, unsigned long stack_start, struct pt_regs *regs, unsigned long stack_size, int __user *parent_tidptr, int __user *child_tidptr) { struct task_struct *p; int trace = 0; long pid; if (unlikely(current->ptrace)) { trace = fork_traceflag (clone_flags); if (trace) clone_flags |= CLONE_PTRACE; } p = copy_process(clone_flags, stack_start, regs, stack_size, parent_tidptr, child_tidptr); /* * Do this prior waking up the new thread - the thread pointer * might get invalid after that point, if the thread exits quickly. */ pid = IS_ERR(p) ? PTR_ERR(p) : p->pid; if (!IS_ERR(p)) { struct completion vfork; if (clone_flags & CLONE_VFORK) { p->vfork_done = &vfork; init_completion(&vfork); } if ((p->ptrace & PT_PTRACED) || (clone_flags & CLONE_STOPPED)) { /* * We'll start up with an immediate SIGSTOP. */ sigaddset(&p->pending.signal, SIGSTOP); set_tsk_thread_flag(p, TIF_SIGPENDING); } if (!(clone_flags & CLONE_STOPPED)) { /* * Do the wakeup last. On SMP we treat fork() and * CLONE_VM separately, because fork() has already * created cache footprint on this CPU (due to * copying the pagetables), hence migration would * probably be costy. Threads on the other hand * have less traction to the current CPU, and if * there's an imbalance then the scheduler can * migrate this fresh thread now, before it * accumulates a larger cache footprint: */ if (clone_flags & CLONE_VM) wake_up_forked_thread(p); else wake_up_forked_process(p); } else { int cpu = get_cpu(); p->state = TASK_STOPPED; if (cpu_is_offline(task_cpu(p))) set_task_cpu(p, cpu); put_cpu(); } ++total_forks; if (unlikely (trace)) { current->ptrace_message = pid; ptrace_notify ((trace << 8) | SIGTRAP); } if (clone_flags & CLONE_VFORK) { wait_for_completion(&vfork); if (unlikely (current->ptrace & PT_TRACE_VFORK_DONE)) ptrace_notify ((PTRACE_EVENT_VFORK_DONE << 8) | SIGTRAP); } else /* * Let the child process run first, to avoid most of the * COW overhead when the child exec()s afterwards. */ set_need_resched(); } return pid; }
/** * kthread_create - create a kthread. * @threadfn: the function to run until signal_pending(current). * @data: data ptr for @threadfn. * @namefmt: printf-style name for the thread. * * Description: This helper function creates and names a kernel * thread. The thread will be stopped: use wake_up_process() to start * it. See also kthread_run(), kthread_create_on_cpu(). * * When woken, the thread will run @threadfn() with @data as its * argument. @threadfn() can either call do_exit() directly if it is a * standalone thread for which noone 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 * or a negative error number; it will be passed to kthread_stop(). * * Returns a task_struct or ERR_PTR(-ENOMEM). */ struct task_struct *kthread_create(int (*threadfn)(void *data), void *data, const char namefmt[], ...) { struct kthread_create_info create; create.threadfn = threadfn; create.data = data; init_completion(&create.done); spin_lock(&kthread_create_lock); list_add_tail(&create.list, &kthread_create_list); spin_unlock(&kthread_create_lock); wake_up_process(kthreadd_task); wait_for_completion(&create.done); if (!IS_ERR(create.result)) { struct sched_param param = { .sched_priority = 0 }; va_list args; va_start(args, namefmt); vsnprintf(create.result->comm, sizeof(create.result->comm), namefmt, args); va_end(args); /* * root may have changed our (kthreadd's) priority or CPU mask. * The kernel thread should not inherit these properties. */ sched_setscheduler_nocheck(create.result, SCHED_NORMAL, ¶m); set_user_nice(create.result, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(create.result, cpu_all_mask); } return create.result; } EXPORT_SYMBOL(kthread_create); /** * kthread_bind - bind a just-created kthread to a cpu. * @k: thread created by kthread_create(). * @cpu: cpu (might not be online, must be possible) for @k to run on. * * Description: This function is equivalent to set_cpus_allowed(), * except that @cpu doesn't need to be online, and the thread must be * stopped (i.e., just returned from kthread_create()). */ void kthread_bind(struct task_struct *k, unsigned int cpu) { /* Must have done schedule() in kthread() before we set_task_cpu */ if (!wait_task_inactive(k, TASK_UNINTERRUPTIBLE)) { WARN_ON(1); return; } set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); k->rt.nr_cpus_allowed = 1; k->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); /** * kthread_stop - stop a thread created by kthread_create(). * @k: thread created by kthread_create(). * * Sets kthread_should_stop() for @k to return true, wakes it, and * waits for it to exit. This can also be called after kthread_create() * instead of calling wake_up_process(): the thread will exit without * calling threadfn(). * * If threadfn() may call do_exit() itself, the caller must ensure * task_struct can't go away. * * Returns the result of threadfn(), or %-EINTR if wake_up_process() * was never called. */ int kthread_stop(struct task_struct *k) { struct kthread *kthread; int ret; trace_sched_kthread_stop(k); get_task_struct(k); kthread = to_kthread(k); barrier(); /* it might have exited */ if (k->vfork_done != NULL) { kthread->should_stop = 1; wake_up_process(k); wait_for_completion(&kthread->exited); } ret = k->exit_code; put_task_struct(k); trace_sched_kthread_stop_ret(ret); return ret; } EXPORT_SYMBOL(kthread_stop); int kthreadd(void *unused) { struct task_struct *tsk = current; /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); set_user_nice(tsk, KTHREAD_NICE_LEVEL); set_cpus_allowed_ptr(tsk, cpu_all_mask); set_mems_allowed(node_possible_map); current->flags |= PF_NOFREEZE | PF_FREEZER_NOSIG; for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (list_empty(&kthread_create_list)) schedule(); __set_current_state(TASK_RUNNING); spin_lock(&kthread_create_lock); while (!list_empty(&kthread_create_list)) { struct kthread_create_info *create; create = list_entry(kthread_create_list.next, struct kthread_create_info, list); list_del_init(&create->list); spin_unlock(&kthread_create_lock); create_kthread(create); spin_lock(&kthread_create_lock); } spin_unlock(&kthread_create_lock); } return 0; }