struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|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); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_AUTOREAP) { if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_PARENT) return ERR_PTR(-EINVAL); if (args->exit_signal) return ERR_PTR(-EINVAL); } if ((clone_flags & CLONE_PARENT) && current->signal->autoreap) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_NNP) { if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD_AUTOKILL) { if (!(clone_flags & CLONE_PIDFD)) return ERR_PTR(-EINVAL); if (!(clone_flags & CLONE_AUTOREAP)) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); /* * Without CLONE_NNP the child could escalate privileges * after being spawned, so require CAP_SYS_ADMIN. * With CLONE_NNP the child can't gain new privileges, * so allow unprivileged usage. */ if (!(clone_flags & CLONE_NNP) && !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; retval = copy_exec_state(clone_flags, p); if (retval) goto bad_fork_free; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * TID is cleared in mm_release() when the task exits */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); raw_spin_lock_init(&p->blocked_lock); lockdep_assert_irqs_enabled();#ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled);#endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * 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 (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; 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 = p->stime = p->gtime = 0;#ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0;#endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE;#endif #ifdef CONFIG_IO_URING p->io_uring = NULL; retval = io_uring_fork(p); if (unlikely(retval)) goto bad_fork_cleanup_delayacct; retval = -EAGAIN;#endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0;#endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; }#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_delayacct; }#endif#ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock);#endif#ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0;#endif p->pagefault_disabled = 0; lockdep_init_task(p); p->blocked_on = NULL; /* not blocked yet */ p->blocked_donor = NULL; /* nobody is boosting p yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0;#endif unwind_task_init(p); /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { unsigned flags = PIDFD_STALE; if (clone_flags & CLONE_THREAD) flags |= PIDFD_THREAD; if (clone_flags & CLONE_PIDFD_AUTOKILL) flags |= PIDFD_AUTOKILL; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; p->flags &= ~PF_BLOCK_TS;#endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE);#if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU);#endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL;#endif#ifdef CONFIG_RETHOOK p->rethooks.first = NULL;#endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) goto bad_fork_cancel_cgroup; /* * If we fail beyond this point we don't free the allocated * futex hash map. We assume that another thread will be created * and makes use of it. The hash map will be freed once the main * thread terminates. */ } /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* 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; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* * If zap_pid_ns_processes() was called after alloc_pid(), the new * child missed SIGKILL. If current is not in the same namespace, * we can't rely on fatal_signal_pending() below. */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); if (clone_flags & CLONE_NNP) task_set_no_new_privs(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) {Lines 2001–2500 of 3409. Previous lines Load more
struct task_struct *p; struct multiprocess_signals delayed; struct file *pidfile = NULL; const u64 clone_flags = args->flags; struct nsproxy *nsp = current->nsproxy; /* * Don't allow sharing the root directory with processes in a different * namespace */ if ((clone_flags & (CLONE_NEWNS|CLONE_FS)) == (CLONE_NEWNS|CLONE_FS)) return ERR_PTR(-EINVAL); if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|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); /* * If the new process will be in a different pid or user namespace * do not allow it to share a thread group with the forking task. */ if (clone_flags & CLONE_THREAD) { if ((clone_flags & (CLONE_NEWUSER | CLONE_NEWPID)) || (task_active_pid_ns(current) != nsp->pid_ns_for_children)) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD) { /* * - CLONE_DETACHED is blocked so that we can potentially * reuse it later for CLONE_PIDFD. */ if (clone_flags & CLONE_DETACHED) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_AUTOREAP) { if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_PARENT) return ERR_PTR(-EINVAL); if (args->exit_signal) return ERR_PTR(-EINVAL); } if ((clone_flags & CLONE_PARENT) && current->signal->autoreap) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_NNP) { if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); } if (clone_flags & CLONE_PIDFD_AUTOKILL) { if (!(clone_flags & CLONE_PIDFD)) return ERR_PTR(-EINVAL); if (!(clone_flags & CLONE_AUTOREAP)) return ERR_PTR(-EINVAL); if (clone_flags & CLONE_THREAD) return ERR_PTR(-EINVAL); /* * Without CLONE_NNP the child could escalate privileges * after being spawned, so require CAP_SYS_ADMIN. * With CLONE_NNP the child can't gain new privileges, * so allow unprivileged usage. */ if (!(clone_flags & CLONE_NNP) && !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EPERM); } /* * Force any signals received before this point to be delivered * before the fork happens. Collect up signals sent to multiple * processes that happen during the fork and delay them so that * they appear to happen after the fork. */ sigemptyset(&delayed.signal); INIT_HLIST_NODE(&delayed.node); spin_lock_irq(¤t->sighand->siglock); if (!(clone_flags & CLONE_THREAD)) hlist_add_head(&delayed.node, ¤t->signal->multiprocess); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); retval = -ERESTARTNOINTR; if (task_sigpending(current)) goto fork_out; retval = -ENOMEM; p = dup_task_struct(current, node); if (!p) goto fork_out; retval = copy_exec_state(clone_flags, p); if (retval) goto bad_fork_free; p->flags &= ~PF_KTHREAD; if (args->kthread) p->flags |= PF_KTHREAD; if (args->user_worker) { /* * Mark us a user worker, and block any signal that isn't * fatal or STOP */ p->flags |= PF_USER_WORKER; siginitsetinv(&p->blocked, sigmask(SIGKILL)|sigmask(SIGSTOP)); } if (args->io_thread) p->flags |= PF_IO_WORKER; if (args->name) strscpy_pad(p->comm, args->name, sizeof(p->comm)); p->set_child_tid = (clone_flags & CLONE_CHILD_SETTID) ? args->child_tid : NULL; /* * TID is cleared in mm_release() when the task exits */ p->clear_child_tid = (clone_flags & CLONE_CHILD_CLEARTID) ? args->child_tid : NULL; ftrace_graph_init_task(p); rt_mutex_init_task(p); raw_spin_lock_init(&p->blocked_lock); lockdep_assert_irqs_enabled(); #ifdef CONFIG_PROVE_LOCKING DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = copy_creds(p, clone_flags); if (retval < 0) goto bad_fork_free; retval = -EAGAIN; if (is_rlimit_overlimit(task_ucounts(p), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { if (p->real_cred->user != INIT_USER && !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN)) goto bad_fork_cleanup_count; } current->flags &= ~PF_NPROC_EXCEEDED; /* * 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 (data_race(nr_threads >= max_threads)) goto bad_fork_cleanup_count; delayacct_tsk_init(p); /* Must remain after dup_task_struct() */ p->flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER | PF_IDLE | PF_NO_SETAFFINITY); p->flags |= PF_FORKNOEXEC; 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 = p->stime = p->gtime = 0; #ifdef CONFIG_ARCH_HAS_SCALED_CPUTIME p->utimescaled = p->stimescaled = 0; #endif prev_cputime_init(&p->prev_cputime); #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN seqcount_init(&p->vtime.seqcount); p->vtime.starttime = 0; p->vtime.state = VTIME_INACTIVE; #endif #ifdef CONFIG_IO_URING p->io_uring = NULL; retval = io_uring_fork(p); if (unlikely(retval)) goto bad_fork_cleanup_delayacct; retval = -EAGAIN; #endif p->default_timer_slack_ns = current->timer_slack_ns; #ifdef CONFIG_PSI p->psi_flags = 0; #endif task_io_accounting_init(&p->ioac); acct_clear_integrals(p); posix_cputimers_init(&p->posix_cputimers); tick_dep_init_task(p); p->io_context = NULL; audit_set_context(p, NULL); cgroup_fork(p); if (args->kthread) { if (!set_kthread_struct(p)) goto bad_fork_cleanup_delayacct; } #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_delayacct; } #endif #ifdef CONFIG_CPUSETS p->cpuset_mem_spread_rotor = NUMA_NO_NODE; seqcount_spinlock_init(&p->mems_allowed_seq, &p->alloc_lock); #endif #ifdef CONFIG_TRACE_IRQFLAGS memset(&p->irqtrace, 0, sizeof(p->irqtrace)); p->irqtrace.hardirq_disable_ip = _THIS_IP_; p->irqtrace.softirq_enable_ip = _THIS_IP_; p->softirqs_enabled = 1; p->softirq_context = 0; #endif p->pagefault_disabled = 0; lockdep_init_task(p); p->blocked_on = NULL; /* not blocked yet */ p->blocked_donor = NULL; /* nobody is boosting p yet */ #ifdef CONFIG_BCACHE p->sequential_io = 0; p->sequential_io_avg = 0; #endif unwind_task_init(p); /* Perform scheduler related setup. Assign this task to a CPU. */ retval = sched_fork(clone_flags, p); if (retval) goto bad_fork_cleanup_policy; retval = perf_event_init_task(p, clone_flags); if (retval) goto bad_fork_sched_cancel_fork; retval = audit_alloc(p); if (retval) goto bad_fork_cleanup_perf; /* copy all the process information */ shm_init_task(p); retval = security_task_alloc(p, clone_flags); if (retval) goto bad_fork_cleanup_audit; retval = copy_semundo(clone_flags, p); if (retval) goto bad_fork_cleanup_security; retval = copy_files(clone_flags, p, args->no_files); if (retval) goto bad_fork_cleanup_semundo; retval = copy_fs(clone_flags, p); if (retval) goto bad_fork_cleanup_files; retval = copy_sighand(clone_flags, p); if (retval) goto bad_fork_cleanup_fs; retval = copy_signal(clone_flags, p); if (retval) goto bad_fork_cleanup_sighand; retval = copy_mm(clone_flags, p); if (retval) goto bad_fork_cleanup_signal; retval = copy_namespaces(clone_flags, p); if (retval) goto bad_fork_cleanup_mm; retval = copy_io(clone_flags, p); if (retval) goto bad_fork_cleanup_namespaces; retval = copy_thread(p, args); if (retval) goto bad_fork_cleanup_io; stackleak_task_init(p); if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children, args->set_tid, args->set_tid_size); if (IS_ERR(pid)) { retval = PTR_ERR(pid); goto bad_fork_cleanup_thread; } } /* * This has to happen after we've potentially unshared the file * descriptor table (so that the pidfd doesn't leak into the child * if the fd table isn't shared). */ if (clone_flags & CLONE_PIDFD) { unsigned flags = PIDFD_STALE; if (clone_flags & CLONE_THREAD) flags |= PIDFD_THREAD; if (clone_flags & CLONE_PIDFD_AUTOKILL) flags |= PIDFD_AUTOKILL; /* * Note that no task has been attached to @pid yet indicate * that via CLONE_PIDFD. */ retval = pidfd_prepare(pid, flags, &pidfile); if (retval < 0) goto bad_fork_free_pid; pidfd = retval; retval = put_user(pidfd, args->pidfd); if (retval) goto bad_fork_put_pidfd; } #ifdef CONFIG_BLOCK p->plug = NULL; p->flags &= ~PF_BLOCK_TS; #endif futex_init_task(p); /* * sigaltstack should be cleared when sharing the same VM */ if ((clone_flags & (CLONE_VM|CLONE_VFORK)) == CLONE_VM) sas_ss_reset(p); /* * Syscall tracing and stepping should be turned off in the * child regardless of CLONE_PTRACE. */ user_disable_single_step(p); clear_task_syscall_work(p, SYSCALL_TRACE); #if defined(CONFIG_GENERIC_ENTRY) || defined(TIF_SYSCALL_EMU) clear_task_syscall_work(p, SYSCALL_EMU); #endif clear_tsk_latency_tracing(p); /* ok, now we should be set up.. */ p->pid = pid_nr(pid); if (clone_flags & CLONE_THREAD) { p->group_leader = current->group_leader; p->tgid = current->tgid; } else { p->group_leader = p; p->tgid = p->pid; } p->nr_dirtied = 0; p->nr_dirtied_pause = 128 >> (PAGE_SHIFT - 10); p->dirty_paused_when = 0; p->pdeath_signal = 0; p->task_works = NULL; clear_posix_cputimers_work(p); #ifdef CONFIG_KRETPROBES p->kretprobe_instances.first = NULL; #endif #ifdef CONFIG_RETHOOK p->rethooks.first = NULL; #endif /* * Ensure that the cgroup subsystem policies allow the new process to be * forked. It should be noted that the new process's css_set can be changed * between here and cgroup_post_fork() if an organisation operation is in * progress. */ retval = cgroup_can_fork(p, args); if (retval) goto bad_fork_put_pidfd; /* * Now that the cgroups are pinned, re-clone the parent cgroup and put * the new task on the correct runqueue. All this *before* the task * becomes visible. * * This isn't part of ->can_fork() because while the re-cloning is * cgroup specific, it unconditionally needs to place the task on a * runqueue. */ retval = sched_cgroup_fork(p, args); if (retval) goto bad_fork_cancel_cgroup; if (need_futex_hash_allocate_default(clone_flags)) { retval = futex_hash_allocate_default(); if (retval) goto bad_fork_cancel_cgroup; /* * If we fail beyond this point we don't free the allocated * futex hash map. We assume that another thread will be created * and makes use of it. The hash map will be freed once the main * thread terminates. */ } /* * From this point on we must avoid any synchronous user-space * communication until we take the tasklist-lock. In particular, we do * not want user-space to be able to predict the process start-time by * stalling fork(2) after we recorded the start_time but before it is * visible to the system. */ p->start_time = ktime_get_ns(); p->start_boottime = ktime_get_boottime_ns(); /* * Make it visible to the rest of the system, but dont wake it up yet. * Need tasklist lock for parent etc handling! */ write_lock_irq(&tasklist_lock); /* 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; if (clone_flags & CLONE_THREAD) p->exit_signal = -1; else p->exit_signal = current->group_leader->exit_signal; } else { p->real_parent = current; p->parent_exec_id = current->self_exec_id; p->exit_signal = args->exit_signal; } klp_copy_process(p); sched_core_fork(p); spin_lock(¤t->sighand->siglock); rv_task_fork(p); rseq_fork(p, clone_flags); /* * If zap_pid_ns_processes() was called after alloc_pid(), the new * child missed SIGKILL. If current is not in the same namespace, * we can't rely on fatal_signal_pending() below. */ if (unlikely(!(ns_of_pid(pid)->pid_allocated & PIDNS_ADDING))) { retval = -ENOMEM; goto bad_fork_core_free; } /* Let kill terminate clone/fork in the middle */ if (fatal_signal_pending(current)) { retval = -EINTR; goto bad_fork_core_free; } /* No more failure paths after this point. */ /* * Copy seccomp details explicitly here, in case they were changed * before holding sighand lock. */ copy_seccomp(p); if (clone_flags & CLONE_NNP) task_set_no_new_privs(p); init_task_pid_links(p); if (likely(p->pid)) { ptrace_init_task(p, (clone_flags & CLONE_PTRACE) || trace); init_task_pid(p, PIDTYPE_PID, pid); if (thread_group_leader(p)) { init_task_pid(p, PIDTYPE_TGID, pid); init_task_pid(p, PIDTYPE_PGID, task_pgrp(current)); init_task_pid(p, PIDTYPE_SID, task_session(current)); if (is_child_reaper(pid)) {