// SPDX-License-Identifier: GPL-2.0-only/* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h>#include <linux/slab.h>#include <linux/sched/autogroup.h>#include <linux/sched/mm.h>#include <linux/sched/stat.h>#include <linux/sched/task.h>#include <linux/sched/task_stack.h>#include <linux/sched/cputime.h>#include <linux/interrupt.h>#include <linux/module.h>#include <linux/capability.h>#include <linux/completion.h>#include <linux/personality.h>#include <linux/tty.h>#include <linux/iocontext.h>#include <linux/key.h>#include <linux/cpu.h>#include <linux/acct.h>#include <linux/tsacct_kern.h>#include <linux/file.h>#include <linux/fdtable.h>#include <linux/freezer.h>#include <linux/binfmts.h>#include <linux/nsproxy.h>#include <linux/pid_namespace.h>#include <linux/ptrace.h>#include <linux/profile.h>#include <linux/mount.h>#include <linux/proc_fs.h>#include <linux/kthread.h>#include <linux/mempolicy.h>#include <linux/taskstats_kern.h>#include <linux/delayacct.h>#include <linux/cgroup.h>#include <linux/syscalls.h>#include <linux/signal.h>#include <linux/posix-timers.h>#include <linux/cn_proc.h>#include <linux/mutex.h>#include <linux/futex.h>#include <linux/pipe_fs_i.h>#include <linux/audit.h> /* for audit_free() */#include <linux/resource.h>#include <linux/blkdev.h>#include <linux/task_io_accounting_ops.h>#include <linux/tracehook.h>#include <linux/fs_struct.h>#include <linux/init_task.h>#include <linux/perf_event.h>#include <trace/events/sched.h>#include <linux/hw_breakpoint.h>#include <linux/oom.h>#include <linux/writeback.h>#include <linux/shm.h>#include <linux/kcov.h>#include <linux/random.h>#include <linux/rcuwait.h>#include <linux/compat.h>#include <linux/io_uring.h> #include <linux/uaccess.h>#include <asm/unistd.h>#include <asm/mmu_context.h> static void __unhash_process(struct task_struct *p, bool group_dead){ nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_TGID); detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node);} /* * This function expects the tasklist_lock write-locked. */static void __exit_signal(struct task_struct *tsk){ struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk);#endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); }} static void delayed_put_task_struct(struct rcu_head *rhp){ struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk);} void put_task_struct_rcu_user(struct task_struct *task){ if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct);} void release_task(struct task_struct *p){ struct task_struct *leader; struct pid *thread_pid; int zap_leader;repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); atomic_dec(&__task_cred(p)->user->processes); rcu_read_unlock(); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); seccomp_filter_release(p); proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat;} int rcuwait_wake_up(struct rcuwait *w){ int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret;}EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task){ struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1;} int is_current_pgrp_orphaned(void){ int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval;} static bool has_stopped_jobs(struct pid *pgrp){ struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false;} /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */static voidkill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent){ struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); }} #ifdef CONFIG_MEMCG/* * A task is exiting. If it owned this mm, find a new owner for the mm. */void mm_update_next_owner(struct mm_struct *mm){ struct task_struct *c, *g, *p = current; retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(c, &p->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search in the siblings */ list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); /* * Delay read_unlock() till we have the task_lock() * to ensure that c does not slip away underneath us */ read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); put_task_struct(c); goto retry; } WRITE_ONCE(mm->owner, c); task_unlock(c); put_task_struct(c);}#endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */static void exit_mm(void){ struct mm_struct *mm = current->mm; struct core_state *core_state; exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); /* * Serialize with any possible pending coredump. * We must hold mmap_lock around checking core_state * and clearing tsk->mm. The core-inducing thread * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ mmap_read_lock(mm); core_state = mm->core_state; if (core_state) { struct core_thread self; mmap_read_unlock(mm); self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } __set_current_state(TASK_RUNNING); mmap_read_lock(mm); } mmgrab(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); /* * When a thread stops operating on an address space, the loop * in membarrier_private_expedited() may not observe that * tsk->mm, and the loop in membarrier_global_expedited() may * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED * rq->membarrier_state, so those would not issue an IPI. * Membarrier requires a memory barrier after accessing * user-space memory, before clearing tsk->mm or the * rq->membarrier_state. */ smp_mb__after_spinlock(); local_irq_disable(); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); local_irq_enable(); task_unlock(current); mmap_read_unlock(mm); mm_update_next_owner(mm);Lines 1–500 of 1817. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/blkdev.h> #include <linux/task_io_accounting_ops.h> #include <linux/tracehook.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <linux/kcov.h> #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <asm/mmu_context.h> static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_TGID); detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_group); list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk); #endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exit_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void put_task_struct_rcu_user(struct task_struct *task) { if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct); } void release_task(struct task_struct *p) { struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); atomic_dec(&__task_cred(p)->user->processes); rcu_read_unlock(); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); seccomp_filter_release(p); proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat; } int rcuwait_wake_up(struct rcuwait *w) { int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } #ifdef CONFIG_MEMCG /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(c, &p->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search in the siblings */ list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); /* * Delay read_unlock() till we have the task_lock() * to ensure that c does not slip away underneath us */ read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); put_task_struct(c); goto retry; } WRITE_ONCE(mm->owner, c); task_unlock(c); put_task_struct(c); } #endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(void) { struct mm_struct *mm = current->mm; struct core_state *core_state; exit_mm_release(current, mm); if (!mm) return; sync_mm_rss(mm); /* * Serialize with any possible pending coredump. * We must hold mmap_lock around checking core_state * and clearing tsk->mm. The core-inducing thread * will increment ->nr_threads for each thread in the * group with ->mm != NULL. */ mmap_read_lock(mm); core_state = mm->core_state; if (core_state) { struct core_thread self; mmap_read_unlock(mm); self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); if (!self.task) /* see coredump_finish() */ break; freezable_schedule(); } __set_current_state(TASK_RUNNING); mmap_read_lock(mm); } mmgrab(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); /* * When a thread stops operating on an address space, the loop * in membarrier_private_expedited() may not observe that * tsk->mm, and the loop in membarrier_global_expedited() may * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED * rq->membarrier_state, so those would not issue an IPI. * Membarrier requires a memory barrier after accessing * user-space memory, before clearing tsk->mm or the * rq->membarrier_state. */ smp_mb__after_spinlock(); local_irq_disable(); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); local_irq_enable(); task_unlock(current); mmap_read_unlock(mm); mm_update_next_owner(mm);